boos/BoosAPI
2
0
Fork 2
Code Issues Pull Requests Packages Projects Releases Wiki Activity

Compare commits

base: boos/BoosAPI:nit_edu
Branches Tags
boos/BoosAPI:feat/embed-desktop boos/BoosAPI:main boos/BoosAPI:refactor/rust-backend boos/BoosAPI:nit_edu
...
compare: boos/BoosAPI:d9c78ecc730edf2cd18d926557cfcfafa659bc54
Branches Tags
boos/BoosAPI:feat/embed-desktop boos/BoosAPI:main boos/BoosAPI:refactor/rust-backend boos/BoosAPI:nit_edu

66 Commits
nit_edu ... d9c78ecc73

Author SHA1 Message Date
boos d9c78ecc73 chore: ignore embedded desktop build artifacts 
The desktop/ subproject (added next) carries its own node_modules,
dist, and Cargo target dirs once built. Ignore them from the metapi
root so the 6.5G+ of generated output never enters the repo.
 2026-06-22 11:32:46 +08:00
boos c3327b9ef6 fix(agent): classify run/terminal/spawn tools as Execute risk 
classify_tool_risk missed execute-class tools whose names use "run",
"terminal", "spawn" or "process" rather than bash/shell/exec/command — most
notably "RunInTerminal". Such a tool fell through to ReadOnly and would
therefore auto-allow without approval in Default/AcceptEdits mode, a real gap
in the permission gate. Broaden the Execute branch to catch them; over-
classifying as Execute only ever asks for more approval, so it is fail-safe.

This was already asserted by an existing unit test (classifies_execute_tools
expects RunInTerminal -> Execute); the test only became runnable after the
rebase onto refactor/rust-backend pulled in the AppConfig test-fixture repair
that had been blocking the lib test binary. Full agent_workbench unit suite
now 32/32; the four integration suites stay green.
 2026-06-22 10:53:45 +08:00
boos d751055452 test(agent): pin the TOCTOU mitigation property for file tools 
The file tools (Read/Write/Edit) open paths inside the SDK process after the
can_use_tool callback validates them, leaving a check-vs-open window. Fully
closing it atomically needs openat2(RESOLVE_BENEATH) file tools replacing the
SDK's in-process ones (tracked as follow-up; the Edit tool's file-state-cache
contract makes that a non-trivial reimplementation).

This test pins the fact that makes the window unreachable under the current
model: an exploit needs a concurrent mutator, the only agent-controlled source
of concurrency is a backgrounded process, and bwrap's PID namespace
(--unshare-all) makes the bash command PID 1 — so the kernel reaps any
backgrounded job when the single bash call exits. The test backgrounds a writer
that would keep appending for ~2s and asserts its output stops the moment the
call returns. With sequential tool execution and per-session bind isolation,
no surviving concurrent mutator exists to win the race.

This is an honest mitigation with evidence, not a claim that the in-process
open is atomic.
 2026-06-22 10:53:45 +08:00
boos b0ce83a937 feat(agent): confine agent bash in an OS sandbox (bubblewrap), mode-gated 
The SDK's built-in Bash tool ran commands as a bare subprocess with only
current_dir set — no OS boundary. On a server that let an agent shell read
/etc/shadow, cd /, write anywhere the process uid could, and reach the
network; the phase-1 path validation only guards the file tools, not bash.
(The SDK's SandboxSettings is dead config: Agent::new never reads it.)

Replace it with SandboxedBashTool — same name and input schema, registered
via custom_tools so it overrides the built-in by name — that confines the
command with bubblewrap, gated by permission mode:

- Default / AcceptEdits (review modes): run inside a bwrap namespace with the
  system mounted read-only, the session sandbox dir bind-mounted rw at its
  real path and made the cwd, /etc //root //home and all other host paths
  absent, and --unshare-all (network included). Filesystem escape and network
  egress are blocked by the kernel, not by convention.
- FullAccess (explicitly dangerous): unconfined, same as before, but every
  command is audit-logged with a warning.

Fail-closed: in a review mode, if bwrap is unavailable the command is refused
rather than silently run unconfined — no fabricated boundary.

Verified end-to-end in tests/agent_bash_sandbox.rs by invoking the tool:
under Default mode `cat /etc/passwd` sees no host passwd, `ls /` exposes no
etc//root//home, a write to /etc/cron.d/x fails (and the host file is never
created), and the network is unreachable; in-sandbox work succeeds and lands
in the real session dir; FullAccess can see the host. bwrap 0.11.2 confirmed
functional on this host (root, CAP_SYS_ADMIN, user namespaces enabled).
Phase-1 suites stay green.
 2026-06-22 10:53:45 +08:00
boos 3bb1272c6d fix(agent): prevent dangling-symlink write escape from the sandbox 
validate_path_within_cwd used exists() to decide whether a path was new.
exists() follows symlinks, so a *dangling* symlink (target missing) reported
false and fell into the not-yet-existing branch, which only bound-checked the
nearest existing ancestor — never the symlink itself. An approved
`ln -s /etc/cron.d/pwn evil` inside the sandbox would therefore pass
validation, and a subsequent Write to `evil` would follow the link and create
a file outside the sandbox. In AcceptEdits mode this chained cleanly: approve
one innocuous-looking symlink (Execute), then writes auto-allow.

Resolve every path component with lstat (symlink_metadata, which does not
follow links) instead of exists():
- Final component: if it is a symlink (dangling or live), resolve its real
  target via read_link + canonicalize-nearest-ancestor and reject unless the
  target stays within the sandbox.
- Ancestor walk: an intermediate dangling symlink directory is likewise
  resolved and bound-checked rather than skipped.

Live symlinks were already caught by canonicalize; this closes the dangling
case. It does not close the check-vs-open TOCTOU (the open happens inside the
SDK tool and would need O_NOFOLLOW/openat2 there); tracked for phase 2 along
with OS-level bash isolation.

Covered by tests/agent_sandbox.rs (dangling symlink to absolute and relative
targets, write tool through a dangling link, write through an intermediate
dangling symlink dir, all rejected; dangling link pointing inside and ordinary
new files still allowed) plus mirrored in-crate unit tests.
 2026-06-22 10:53:45 +08:00
boos 5501558354 fix(agent): make tool approval race-free with an atomic state machine 
The previous approval registry used a oneshot channel, so two independent
signals decided an approval: the HTTP handler's result (from Sender::send's
bool) and the agent loop's allow/deny (from which timeout arm fired). At the
300s boundary these could disagree — a late /approve could see send() return
Ok (receiver not yet dropped) and report ok:true to the user, while the
timeout's final poll simultaneously fired and denied the tool. The frontend
was told "approved" while nothing ran. The mirror case (ok:false but allowed)
was impossible, so it never executed an unapproved tool, but the user-facing
signal could lie.

Replace the channel with a single source of truth: each entry is an
AtomicU8 state machine (Pending -> Approved/Denied/TimedOut) plus a Notify.
The decision is made by exactly one compare_exchange from Pending — whoever
wins (approver or timeout) settles it, everyone else observes a losing CAS
and no-ops. resolve() now returns whether *its* CAS won, so /approve tells
the frontend the truth; the loop decides purely from the settled atomic.
They read the same atomic and cannot disagree.

A PendingGuard removes the registry entry on drop (normal completion or
aborted/disconnected session), so there is no leak on any path. The callback
also emits an approval_resolved SSE event with the final decision so a late
click — already told ok:false — can dismiss its modal with the real outcome.

Verified with an integration test that races resolve() against a near-zero
timeout 5000x and asserts ok==true iff the executed decision is Approved
(never a mixed state). Run via tests/ because the in-crate lib test binary
is currently blocked by unrelated AppConfig test fixtures in other modules.
 2026-06-22 10:53:45 +08:00
boos f0a76fd82c feat(agent): add Agent Workbench frontend panel 
A minimal chat UI for the server-side agent, wired to the SSE engine:

- Streams assistant text incrementally and renders each tool call as a card
  showing the tool name, input and (color-coded) output or denial reason.
- Surfaces interactive approval prompts: when the agent requests a risky
  tool, a modal shows the tool and its arguments and posts the user's
  decision to /api/agent/approve, unblocking the loop.
- Permission-mode selector (standard review / accept edits / full access),
  new-session control, and a live session usage bar (turns, tokens, cost).

Registered as /agent-workbench (admin) and /user/agent-workbench (user) in
the SPA router and sidebar. Typecheck and vite build pass.
 2026-06-22 10:53:45 +08:00
boos 2506713fad feat(agent): SSE agent route backed by open-agent-sdk via BoosAPI provider 
Adds the Agent Workbench HTTP surface wiring the open-agent-sdk loop into
BoosAPI:

- POST /api/agent/chat (SSE): runs an agentic turn and streams session /
  text / thinking / tool_use / tool_result / approval_request / result /
  error / done events. The agent's LLM calls are routed back through
  BoosAPI's own OpenAI-compatible /v1 using the built-in downstream key
  (constructed via the SDK's OpenAIProvider), so any aggregated model works
  and usage flows through the normal accounting pipeline.
- POST /api/agent/approve: resolves a pending tool approval by request id.
- GET /api/agent/status: engine info + a session's accounting.

Safety is enforced in the SDK permission callback: every tool first passes
sandbox path validation (no escaping the per-session working dir), then the
risk/mode matrix — writes and command execution require an interactive
approval round-trip (default mode) that blocks the loop until the user
answers or the request times out (300s -> deny). Each session runs in its
own data/agent_sessions/{id}/ sandbox and turn usage is persisted.

Registered in the API router and added open-agent-sdk as a path dependency.
 2026-06-22 10:53:45 +08:00
boos a060666f6f feat(agent): persist per-session token and cost accounting 
Adds the agent_sessions table (migration) and a session_store module that
owns its lifecycle:

- ensure_session: idempotently creates the session row on first chat.
- record_turn: accumulates input/output/total tokens, cost and turn count
  after each completed turn, bumping updated_at.
- get_session: user-scoped fetch so a tenant can only read its own session.

Backed by SQLite via SQLx, matching the existing service style. Unit-tested
against an in-memory database (idempotency, accumulation, user scoping).
 2026-06-22 10:53:45 +08:00
boos 4192798ceb feat(agent): add permission, sandbox and approval primitives for agent workbench 
Introduces the SDK-free building blocks for a server-side AI agent:

- permission: tool risk classification (ReadOnly/Write/Execute) and the
  per-mode decision matrix (Default/AcceptEdits/FullAccess). Default mode
  auto-allows reads and requires approval for writes/executes.
- sandbox: per-session isolated working directory under
  data/agent_sessions/{id}/ plus path validation that confines every tool
  path argument within the session directory (rejects ../, absolute and
  symlink escapes), mirroring the AQBot security model.
- approval: process-global registry bridging the SSE approval round-trip via
  oneshot channels, so the permission callback can block until the user
  approves or denies a risky tool.

All three modules are unit-tested in isolation (17 tests) and carry no
dependency on the agent SDK; the HTTP layer maps their results onto the
SDK permission callback in a later commit.
 2026-06-22 10:53:45 +08:00
boos 4a12610662 Merge remote-tracking branch 'origin/feat/comfy-cloud-adapter' into _merge_test 
# Conflicts:
#	src/routes/admin/compat.rs
#	src/routes/admin/downstream_keys.rs
#	src/routes/auth.rs
#	src/routes/comfyui/mod.rs
#	src/routes/comfyui_agent.rs
#	src/routes/events.rs
#	src/routes/money_printer.rs
#	src/routes/oauth.rs
#	src/routes/proxy/mod.rs
#	src/routes/video_agent_legacy.rs
 2026-06-22 10:14:52 +08:00
boos eddf3eff4e fix(deps): declare url crate so digital_human compiles 
digital_human.rs uses url::Url::parse but the crate was only a transitive
dependency, not declared in Cargo.toml, so the lib failed to compile with
E0433. Add the explicit dependency (url 2.x was already in Cargo.lock).
 2026-06-22 09:37:18 +08:00
boos 4d093548de feat(proxy): wire Gemini native v1beta endpoints through the conductor 
Implement the four Gemini native inbound endpoints so Gemini CLI / Google
GenAI SDKs can point their base URL at the gateway:

- GET  /v1beta/models — directory listing in Gemini shape, built from
  configured routes (like /v1/models); no upstream call, no billing.
- POST /v1beta/models/{model}:generateContent — non-streaming, routed
  through ProxyConductor with failover + usage_logs + billing.
- POST /v1beta/models/{model}:streamGenerateContent — SSE passthrough via
  open_stream_with_failover + sse_passthrough_response.
- POST /v1beta/models/{model}:countTokens — metadata call, routed for a
  channel but not billed.

Auth accepts the gateway key from ?key= or x-goog-api-key (Gemini
convention) and reuses the downstream-key authorization + limits.

Billing closes the loop: gemini_extract_usage reads usageMetadata
(promptTokenCount / candidatesTokenCount) for non-streaming, and
gemini_stream_usage_from_line feeds the shared StreamUsageAccumulator so
streamed usageMetadata is billed too.

Unit tests cover model:action parsing, usage extraction, the stream usage
parser, and query forwarding (key/alt dropped).
 2026-06-22 08:39:38 +08:00
boos aaa593ac31 feat(proxy): add Gemini native upstream executors 
Add Gemini-shaped upstream calls that mirror AQBot's native passthrough
and BoosAPI's /v1/responses forwarding: the model lives in the URL path
(/v1beta/models/{model}:{op}) and the key in ?key=, so the body is sent
verbatim with no model rewrite.

- gemini_base_url / gemini_operation_url normalize the v1beta root and
  build {base}/v1beta/models/{model}:{op}?key=...&{extra}, stripping a
  leading models/ prefix and handling the no-key case.
- execute_gemini_operation runs non-streaming ops (generateContent /
  countTokens) and returns upstream JSON verbatim.
- execute_gemini_stream_response opens streamGenerateContent for SSE
  passthrough, enforcing alt=sse via merge_alt_sse.

Unit tests cover URL building and alt=sse merging.
 2026-06-22 08:39:26 +08:00
boos 24a8dec151 fix: define DEFAULT_NEW_USER_MAX_COST_USD and repair test AppConfig initializers 
Pre-existing breakage on this branch (introduced by the billing commits),
unrelated to the Gemini work but blocking both `cargo build` and
`cargo test`:

- admin/users.rs imported routes::auth::DEFAULT_NEW_USER_MAX_COST_USD,
  which was never defined. Add it to auth.rs as $1.0 (the billing design's
  "new users default to $1" starter allowance).
- AppConfig gained `payment` and `pixelle_video` fields but several test
  helpers still used struct literals missing them. Initialize both with
  Default::default() at each affected test site.
 2026-06-22 08:39:17 +08:00
boos 9078b8d41a feat(gateway): client integration templates endpoint 
Add GET /api/cli-profiles/templates returning copy-ready config snippets
for pointing common AI clients at this gateway: Cursor, VS Code Continue,
Claude Code, and a generic OpenAI-compatible blob.

Ported from AQBot's list_gateway_templates (a desktop app that hardcodes
localhost:8080). Adapted for server-side use: the gateway origin is resolved
per request — ?base_url= override, then X-Forwarded-Proto + Host (correct
behind a TLS-terminating proxy), then config server.host:port fallback
(0.0.0.0/:: rewritten to 127.0.0.1, matching the comfyui-agent local-base
convention). OpenAI-compatible clients get the /v1 base; Claude Code gets
the bare origin since it appends /v1/messages itself.

Scope guard: this only returns config strings + copy hints. It deliberately
does not rewrite local CLI config files (AQBot's desktop cli_config behavior),
which has no meaning on a server.

New module proxy::cli_profiles::templates holds the snippet content; the admin
handler resolves the origin. Covered by 9 unit tests.
 2026-06-22 06:31:14 +08:00
boos d548525ef2 refactor(workflow_ui): 抽出 bootstrap 子模块 
Co-Authored-By: Claude <noreply@anthropic.com>
 2026-06-18 22:52:59 +08:00
boos 3aa1468fbb refactor(workflow_ui): 抽出 ws 子模块 
Co-Authored-By: Claude <noreply@anthropic.com>
 2026-06-18 22:44:53 +08:00
boos f7f9a9ca09 refactor(workflow_ui): 抽出 run_convert 子模块 
Co-Authored-By: Claude <noreply@anthropic.com>
 2026-06-18 22:32:51 +08:00
boos a37546cb2d refactor(workflow_ui): 抽出 native_proxy 子模块 
Co-Authored-By: Claude <noreply@anthropic.com>
 2026-06-18 22:22:19 +08:00
boos f43daed3ee refactor(workflow_ui): 抽出 repair 子模块 
Co-Authored-By: Claude <noreply@anthropic.com>
 2026-06-18 22:05:30 +08:00
boos 35f63c46f1 refactor(workflow_ui): 抽出 model_inject 子模块 
Co-Authored-By: Claude <noreply@anthropic.com>
 2026-06-18 21:55:27 +08:00
boos e296c01b4b docs: workflow_ui/mod.rs 续拆(6 子模块)设计 
把 mod.rs 残留 4095 行按职责再拆 6 组(model_inject/repair/native_proxy/
run_convert/ws/bootstrap),mod.rs 瘦到 ~1000-1200。纯机械移动,编译器+5测试验证。

Co-Authored-By: Claude <noreply@anthropic.com>
 2026-06-18 21:33:55 +08:00
boos a6c4db64c4 refactor(workflow_ui): 抽出 queue 子模块 
Co-Authored-By: Claude <noreply@anthropic.com>
 2026-06-18 15:15:17 +08:00
boos 7a02545fb8 refactor(workflow_ui): 抽出 validate 子模块 
Co-Authored-By: Claude <noreply@anthropic.com>
 2026-06-18 14:58:58 +08:00
boos 9cad69b88c refactor(workflow_ui): 抽出 comfy_proxy 子模块 
Co-Authored-By: Claude <noreply@anthropic.com>
 2026-06-18 14:47:24 +08:00
boos bbf0a3b81a refactor(workflow_ui): 抽出 assets 子模块 
Co-Authored-By: Claude <noreply@anthropic.com>
 2026-06-18 14:34:46 +08:00
boos 334ed04a6a refactor(workflow_ui): 抽出 models 子模块 
Co-Authored-By: Claude <noreply@anthropic.com>
 2026-06-18 14:23:17 +08:00
boos 7b1167bd75 refactor(workflow_ui): 抽出 node_defs 子模块 
Co-Authored-By: Claude <noreply@anthropic.com>
 2026-06-18 14:13:27 +08:00
boos 8a55efbfb6 refactor(workflow_ui): 抽出 auth 子模块 
Co-Authored-By: Claude <noreply@anthropic.com>
 2026-06-18 14:05:15 +08:00
boos fd4c1f0ac1 refactor(workflow_ui): 文件转目录模块(mod.rs,内容不变) 
Co-Authored-By: Claude <noreply@anthropic.com>
 2026-06-18 13:59:03 +08:00
boos 60ecd8a13c docs: workflow_ui.rs 拆分实现计划(Task0转目录 + 7子模块抽取) 
每任务抽1组函数(纯搬运)+cargo编译+测试验证+独立提交。通用6步流程统一。

Co-Authored-By: Claude <noreply@anthropic.com>
 2026-06-18 13:52:26 +08:00
boos 441adcf489 docs: workflow_ui.rs 拆分(8 子模块)设计 spec 
把 6181 行单文件按职责拆成 workflow_ui/ 目录 8 子模块(assets/auth/node_defs/
models/comfy_proxy/validate/queue/mod)。纯机械移动零逻辑改动,编译器+5测试验证。

Co-Authored-By: Claude <noreply@anthropic.com>
 2026-06-18 13:48:18 +08:00
boos 7e824a6d45 feat(digital-human): 副标题保留,仅去掉「基于 Pixelle-Video」前缀 
Co-Authored-By: Claude <noreply@anthropic.com>
 2026-06-18 13:35:08 +08:00
boos b2f6b875a0 feat(digital-human): 头部标题改为「短视频工厂/数字人」,去掉 Pixelle 副标题 
Co-Authored-By: Claude <noreply@anthropic.com>
 2026-06-18 13:34:14 +08:00
boos 86a2c51b31 feat(digital-human): 脚本模型选择器移到「文案与 BGM」区 
脚本生成属文案环节,把脚本模型(可选)下拉从「语音与画面」移到「文案与 BGM」区。

Co-Authored-By: Claude <noreply@anthropic.com>
 2026-06-18 13:27:08 +08:00
boos edc125f79c feat(nav): 移除短视频工厂菜单,数字人改名为「短视频工厂/数字人」 
admin/user 两区导航去掉 money-printer 入口,digital-human 菜单标签改为
「短视频工厂/数字人」。路由与页面保留(直链 /money-printer 仍可达,只是不在导航)。

Co-Authored-By: Claude <noreply@anthropic.com>
 2026-06-18 13:21:40 +08:00
boos 1d19401424 feat(pixelle): 连接管理页加 Pixelle 连接卡片 
Accounts 页加 Pixelle 连接卡片(URL+2key+保存),api.ts adminApi 加 get/savePixelleConnection。
api.ts 一并带入此前累积的 files URL 改写改动。

Co-Authored-By: Claude <noreply@anthropic.com>
 2026-06-18 13:13:57 +08:00
boos 92d38bb309 feat(pixelle): 连接凭证 admin 端点(GET/PUT 掩码 + 重启) 
Co-Authored-By: Claude <noreply@anthropic.com>
 2026-06-18 11:57:23 +08:00
boos 55188e51ff feat(pixelle): 连接凭证 service(settings 读写 + config.yaml 同步) 
Co-Authored-By: Claude <noreply@anthropic.com>
 2026-06-18 11:51:47 +08:00
boos 96b8d2c399 feat(pixelle): 加 serde_yaml + Pixelle config 路径配置项 
Co-Authored-By: Claude <noreply@anthropic.com>
 2026-06-18 11:43:55 +08:00
boos 284cf84a47 docs: Pixelle 连接凭证管理实现计划(5 任务) 
serde_yaml+config路径 → service(settings读写+yaml同步+restart) → admin端点(掩码)
→ 前端连接管理卡片 → 部署联调。写文件+重启容器同步机制。

Co-Authored-By: Claude <noreply@anthropic.com>
 2026-06-18 11:33:05 +08:00
boos 973396aac4 feat(digital-human): 后端转发 llm_model 给 Pixelle 
Co-Authored-By: Claude <noreply@anthropic.com>
 2026-06-18 11:23:23 +08:00
boos 1598e6c758 feat(digital-human): 前端加脚本模型选择器(llm_model) 
Co-Authored-By: Claude <noreply@anthropic.com>
 2026-06-18 11:23:19 +08:00
boos 07e31e0f7c docs: Pixelle 连接凭证纳入 BoosAPI 管理 设计 spec 
连接管理页加 Pixelle 连接卡片(runninghub key/comfy url/comfy key),
写 settings 表 + 同步 config.yaml + 重启容器生效。只管3凭证,写文件+重启机制。

Co-Authored-By: Claude <noreply@anthropic.com>
 2026-06-18 11:19:39 +08:00
boos bfafc8f226 docs: 数字人脚本默认模型改为 deepseek-v4-flash 
Co-Authored-By: Claude <noreply@anthropic.com>
 2026-06-18 11:05:26 +08:00
boos 230eef96ed docs: 数字人脚本 LLM 模型可选 设计 spec 
数字人页加脚本模型下拉(只列文本模型,默认 gpt-5.5),三层:
前端选择器(getModelsMarketplace过滤)+ 后端转发 llm_model + Pixelle 脚本步传 model。
生图模型已由图片工作流下拉覆盖,不在范围。

Co-Authored-By: Claude <noreply@anthropic.com>
 2026-06-18 04:50:05 +08:00
boos 054343f489 feat(digital-human): 后端转发 api_video_workflow 给 Pixelle 
Co-Authored-By: Claude <noreply@anthropic.com>
 2026-06-18 03:05:29 +08:00
boos 3524a165e3 feat(digital-human): 前端加视频工作流选择器(api_video_workflow) 
Co-Authored-By: Claude <noreply@anthropic.com>
 2026-06-18 02:57:44 +08:00
boos 53f99affec docs: 数字人 Comfy 视频入口实现计划(4 任务三层) 
前端视频工作流选择器 → 后端转发 api_video_workflow → Pixelle comfy 注入 audio_path
→ 部署联调。视频入口可选、默认不启用、向后兼容。

Co-Authored-By: Claude <noreply@anthropic.com>
 2026-06-18 02:54:26 +08:00
boos 30b7b12682 docs: 数字人接入 Comfy Cloud 视频工作流(完整视频入口)设计 
调查确认 BoosAPI 数字人 UI 无视频工作流入口、后端不转发 api_video_workflow、
Pixelle 仅给 api/ 通道注入 audio_path。设计贯穿三层补齐:
前端加视频工作流选择器 + 后端转发 api_video_workflow + Pixelle 给 comfy 工作流注入 audio_path。

Co-Authored-By: Claude <noreply@anthropic.com>
 2026-06-18 02:48:49 +08:00
boos 937442df04 docs: LTX2.3 数字人工作流实现计划(5 任务) 
获取API导出 → 改造工作流(标记+删RecordAudio) → 补 media.py image_path 转发
→ 校验探测 → 真实联调。硬依赖用户导出 API 格式 JSON。

Co-Authored-By: Claude <noreply@anthropic.com>
 2026-06-18 02:20:36 +08:00
boos 79ade45c25 docs: LTX2.3 数字人 spec 补充 media.py image_path 转发缺口 
writing-plans 阶段发现:media.py 只给 api/ 通道转发 image_path,comfy/ 通道收不到肖像图。
增加 media.py 一行级改动(非 api 分支把 image_path 加入 workflow_params),
标记名对齐为 $~image_path! / $~audio_path! / $prompt!。

Co-Authored-By: Claude <noreply@anthropic.com>
 2026-06-18 02:17:12 +08:00
boos ff514061d7 docs: LTX2.3 数字人工作流(Comfy Cloud)设计 spec 
用官方模板 video_ltx2_3_id_lora(LTX2.3 身份保持+音频驱动)做 Pixelle comfy/ 数字人工作流,
经 comfy-cloud 适配器执行。模型/节点已验证在 Comfy Cloud 托管齐全。
comfykit _meta.title 标记注入(image/audio/prompt)。硬依赖:用户导出 API 格式 JSON。

Co-Authored-By: Claude <noreply@anthropic.com>
 2026-06-18 02:12:03 +08:00
boos 8ca6c2ad4f feat(comfy-cloud): Comfy Cloud 预设移到首位 + 新增站点默认选中 
预设数组把 comfy-cloud 排第一;站点管理 openAdd 默认选 Comfy Cloud 预设
(预填 url+platform,只需贴 X-API-Key)。detect-race 测试补平台重置以保留竞态覆盖。

Co-Authored-By: Claude <noreply@anthropic.com>
 2026-06-18 00:38:32 +08:00
boos d850da64c3 feat(comfy-cloud): 站点预设模板新增 Comfy Cloud 
siteInitializationPresets 共享契约(ts/js/d.ts)加 comfy-cloud 预设:
platform=comfy_cloud, defaultUrl=https://cloud.comfy.org, 自动填充官方地址。
platform 联合类型扩 'comfy_cloud';urlMatcher + Rust detect_site_platform 同步识别。

Co-Authored-By: Claude <noreply@anthropic.com>
 2026-06-18 00:21:44 +08:00
boos 08a2980f5f fix(comfy-cloud): /history 完成分支校验 jobs 详情状态码 
Co-Authored-By: Claude <noreply@anthropic.com>
 2026-06-17 23:39:18 +08:00
boos 7758858141 feat(comfy-cloud): 挂载适配路由 + 站点管理 comfy_cloud 平台选项 
Co-Authored-By: Claude <noreply@anthropic.com>
 2026-06-17 23:30:46 +08:00
boos 8676b5486b feat(comfy-cloud): /view 产出文件透传 
Co-Authored-By: Claude <noreply@anthropic.com>
 2026-06-17 23:26:07 +08:00
boos e90beda1a5 feat(comfy-cloud): /history 轮询翻译(status+jobs→history) 
Co-Authored-By: Claude <noreply@anthropic.com>
 2026-06-17 23:21:44 +08:00
boos 03eea2e267 feat(comfy-cloud): 适配端点骨架 + POST /prompt 转发 
Co-Authored-By: Claude <noreply@anthropic.com>
 2026-06-17 23:18:34 +08:00
boos 70c11a15cd feat(comfy-cloud): job→ComfyUI history 翻译函数 
Co-Authored-By: Claude <noreply@anthropic.com>
 2026-06-17 23:10:42 +08:00
boos 17cd0691ca feat(comfy-cloud): 站点配置读取 resolve_comfy_cloud_site 
Co-Authored-By: Claude <noreply@anthropic.com>
 2026-06-17 23:08:16 +08:00
boos 2d273a03ad docs: Comfy Cloud 适配器实现计划(7 任务 TDD) 
站点配置读取 → job→history 翻译 → 三个适配端点(prompt/history/view)
→ 挂载+前端平台选项 → 真实联调。全程 TDD,wiremock 集成测,逐任务提交。

Co-Authored-By: Claude <noreply@anthropic.com>
 2026-06-17 23:02:16 +08:00
boos e1d0ade434 docs: Comfy Cloud 工作流执行适配器设计 spec 
在 BoosAPI 内做 ComfyUI 原生协议↔Comfy Cloud API 翻译适配器:对外暴露
/comfy-cloud/{prompt,history,view},内部翻译成 cloud.comfy.org/api/* + X-API-Key。
Comfy Cloud base_url+key 经站点管理(新增 comfy_cloud 平台类型)录入。
Pixelle/comfykit 零改动,只改 comfyui_url 指向适配端点。

Co-Authored-By: Claude <noreply@anthropic.com>
 2026-06-17 22:56:55 +08:00
boos e8508cb056 feat: Codex 工作区改动迁移(支付管理/用户余额/创作页等) 
将 Codex 在工作区累积的改动整体落到 refactor/rust-backend:
支付管理与用户余额页、各创作 surface、website 等。排除 boosapi.db/config.toml 等敏感文件。

Co-Authored-By: Claude <noreply@anthropic.com>
 2026-06-17 22:28:14 +08:00
178 changed files with 29914 additions and 11151 deletions
Expand all files Collapse all files
.cargo/config.toml
+9
View File
@@ -22,3 +22,12 @@
# Default to all CPUs for parallel codegen. Override with --jobs N if # Default to all CPUs for parallel codegen. Override with --jobs N if
# you need to leave headroom for other work. # you need to leave headroom for other work.
# jobs = 8 # jobs = 8
# sccache compilation cache: caches compiled crates keyed by source+flags,
# so clean builds and branch switches reuse prior results. sccache transparently
# skips crates built with incremental compilation (dev profile), so it mainly
# accelerates release/fast-release and dependency rebuilds. Harmless if absent
# — cargo only applies this when the binary exists on PATH via build-and-run.sh,
# which sets RUSTC_WRAPPER conditionally. Uncomment to force it for direct cargo:
# rustc-wrapper = "sccache"
.codegraph/.gitignore
+16
View File
@@ -0,0 +1,16 @@
# CodeGraph data files
# These are local to each machine and should not be committed
# Database
*.db
*.db-wal
*.db-shm
# Cache
cache/
# Logs
*.log
# Hook markers
.dirty
.gitignore
+9
View File
@@ -31,3 +31,12 @@ boosapi.db-shm
boosapi.db-wal boosapi.db-wal
.tours/ .tours/
bun.lock bun.lock
# Embedded desktop subproject (BoosAPI Desktop) — generated artifacts only.
# Source lives in desktop/; these are build outputs that must never be tracked.
desktop/node_modules/
desktop/dist/
desktop/target/
desktop/src-tauri/target/
desktop/src-tauri/gen/schemas/
desktop/website/node_modules/
.trellis/.gitignore
+32
View File
@@ -0,0 +1,32 @@
# Developer identity (local only)
.developer
# Current task pointer (each dev works on different task)
.current-task
# Session/window scoped runtime state
.runtime/
# Ralph Loop state file
.ralph-state.json
# Agent runtime files
.agents/
.agent-log
.session-id
# Task directory runtime files
.plan-log
# Atomic update temp files
*.tmp
# Update backup directories
.backup-*
# Conflict resolution temp files
*.new
# Python cache
**/__pycache__/
**/*.pyc
.trellis/.template-hashes.json
+140
View File
@@ -0,0 +1,140 @@
{
"__version": 2,
"hashes": {
".claude/agents/trellis-check.md": "9e48342243f311d55386f8fb42933945e87aba73d5ade547133aa98345a06128",
".claude/agents/trellis-implement.md": "73b56b3047c0e852382c4630aa181fb847d1e5ea1f63459dac4bf728f43fd097",
".claude/agents/trellis-research.md": "add4aa4259ded425b04ec992802c646490352bb4eb3730a7ab450beea87d4faa",
".claude/hooks/inject-subagent-context.py": "c8ea04062990530dffb26c4d1efa3e6887e042d3086da2f2325b491c9d544931",
".claude/hooks/inject-workflow-state.py": "f7fa9389ed7aa264597fff5de6277bec186e89a3ef539192997c6d026d88d5ec",
".claude/hooks/session-start.py": "2cd87a08dec8cecc5f1acb665d6bd7241bc580f6ae39d571b99a0118be89c46b",
".claude/commands/trellis/continue.md": "6c34c41824f8eff4b2df792e032e0c36787b59f8a8879b0338347073f76ad52c",
".claude/commands/trellis/finish-work.md": "d6aa570ab684f57e4845de2d84a1ff6d9f0908e04c5a56e14fd70ae739c369fc",
".claude/skills/trellis-before-dev/SKILL.md": "859894f2e8258cbfa142d710363433761c54984c69f7ed7bd44512fb4eb165cd",
".claude/skills/trellis-brainstorm/SKILL.md": "219f99c61e59aa9af4642c0ec96ceec72c915f6757572760ba69dee951b05eb1",
".claude/skills/trellis-break-loop/SKILL.md": "f5a93699832f29dee443b53c135a7459519b371f689af191d15c29e8ee5c7bde",
".claude/skills/trellis-check/SKILL.md": "b21ff04b7680ebacb8c5ecbc48a22d627eb13e2b47fceb78c8ced0b43b60b282",
".claude/skills/trellis-update-spec/SKILL.md": "d975db7af166578488958751ae2c56edb827a68bddb569aa27acc3453f64e610",
".claude/skills/trellis-channel/references/command-reference.md": "c4df3d940d89814310bfdaded20e84dd1d6b96786f6772688de7a123338d3c8e",
".claude/skills/trellis-channel/references/forum.md": "407db39e8ebde47cea8637e3069bdb3d76ba42b43ed1d08ba97a56f26dbcfcb4",
".claude/skills/trellis-channel/references/progress-debugging.md": "93b021fd8d5d3d4ee54952c40424ab91ca57c2ab8032bfbfc3b5c5e22f1464cd",
".claude/skills/trellis-channel/references/workers.md": "d4481b2858bca82050cb8d131916da8a2ccc3857f199cdb9ced8bb41d592e2a7",
".claude/skills/trellis-channel/references/workflows.md": "0782d602efde6e94a7d7d7950fd605eedc9a1f5a523908284e76b628fd618fd4",
".claude/skills/trellis-channel/SKILL.md": "ff84801c511a736da018b4b1149348ebc9a16b7fc18d905ec10cfa7acbf269a3",
".claude/skills/trellis-meta/references/customize-local/add-project-local-conventions.md": "86009ccb5d0373f399582da0bc570c4e5c6053c3c764857424ff93384f0e04e5",
".claude/skills/trellis-meta/references/customize-local/change-agents.md": "3eef0d9b9cf875f121c1a38afb8eee6d3cd3894127db601ae5a7760fa5b61575",
".claude/skills/trellis-meta/references/customize-local/change-context-loading.md": "350d319dc1ab99609ddbf52cf8c06c71bd97ba1a29ce2eac8b97d0bb192938bf",
".claude/skills/trellis-meta/references/customize-local/change-hooks.md": "91892f2cff53ae003736007e95172945acabf48b2fc889bd627cd2406ce449c4",
".claude/skills/trellis-meta/references/customize-local/change-skills-or-commands.md": "a6994e2418cdf5bcad10b4236b02741179ae794bc4fdd811a64f443293b69268",
".claude/skills/trellis-meta/references/customize-local/change-spec-structure.md": "31eccaad7097d96e66a45c1b4caea1ba4f2e54b7814184c3ebf82c87dafc4841",
".claude/skills/trellis-meta/references/customize-local/change-task-lifecycle.md": "60ff9efb93604b87a461a4af30322d76750402a51e40f31531a7ff88d309996d",
".claude/skills/trellis-meta/references/customize-local/change-workflow.md": "43fa780a2ca580de121b10893d49b99f978873deebbf45008c466e5ac6651519",
".claude/skills/trellis-meta/references/customize-local/overview.md": "ce8f09e9f93ce9a48500763fb3a4db2b3908a5fbf4f985ab71dacebb404cf8f4",
".claude/skills/trellis-meta/references/local-architecture/bundled-skills.md": "bac739b042d7a12dae5d14d85cbc312e56ca03f571d2ba7a25b20641ddaefc3f",
".claude/skills/trellis-meta/references/local-architecture/context-injection.md": "8497289bf333b3aa456f317039d1239b7ece79254aa0eb62cfc647714c866084",
".claude/skills/trellis-meta/references/local-architecture/generated-files.md": "ca4211b43aff79cf263c83255f557994386723d10da344c0c4e1ec211c7fcd37",
".claude/skills/trellis-meta/references/local-architecture/multi-agent-channel.md": "56e5070474aeca872e2d70c46feea5aaafecd3d3ec052c3f7b1877358dca62e9",
".claude/skills/trellis-meta/references/local-architecture/overview.md": "50638fd9eaaba2e0edf2f2a84d920578d5b2fb7934031b174e417d3dc510b2a6",
".claude/skills/trellis-meta/references/local-architecture/spec-system.md": "b8d8a6a0888b44a232c8f50161b9e20e903cf621ad7be4021715ab6fab226f47",
".claude/skills/trellis-meta/references/local-architecture/task-system.md": "2b561d49c390f7d0db5391912946133be4bf73189231e2b8cc9afa1c5ac6165a",
".claude/skills/trellis-meta/references/local-architecture/workflow.md": "cfcdc6e4468a5d9c816e929fcca01640cd41cfdaaa4824118b40a8e460c927b6",
".claude/skills/trellis-meta/references/local-architecture/workspace-memory.md": "e6427b46aba744563c2444b30df4043cd856561b7709ec2dece26095416421fd",
".claude/skills/trellis-meta/references/platform-files/agents.md": "ce1a22c2b3ff0bff68755b5663e1f3b63ef2f1658cff43e511cee9013537c698",
".claude/skills/trellis-meta/references/platform-files/hooks-and-settings.md": "b70f983d0b3fea45e4ad7abef8ab8981473ff016d6d454d4d407865c13019d31",
".claude/skills/trellis-meta/references/platform-files/overview.md": "7bc24f5ffefe082f373562bbba715cce9e761a76f6b59ce341d4dc679971a587",
".claude/skills/trellis-meta/references/platform-files/platform-map.md": "a3cb8b4b4e42a3b380485aca673750ba3b2b28c16a04339b1db7afbd479509ab",
".claude/skills/trellis-meta/references/platform-files/skills-and-commands.md": "5732bb0a7d384a91abd0c103372f3865e0b186e75185f35e0e91b00a6b6bf5a3",
".claude/skills/trellis-meta/SKILL.md": "a190ecbde70a658a5b5c3e2558783e99c9afc6f2e5cdecdac8f11c06dd42065e",
".claude/skills/trellis-session-insight/references/cli-quick-reference.md": "c520353fe3fc00b9702ed4f780647c8fbd6d342e66527a03647f533a9fe09779",
".claude/skills/trellis-session-insight/references/triggering-patterns.md": "121ecd23be83d1567e8ce15c366a81073d7a2b1d3ad616fce235c07ca1f1cc20",
".claude/skills/trellis-session-insight/SKILL.md": "f6ad80eaca21b8fa63d31ae26b612bb2bb69dd04469603828509a8c5a0463ff1",
".claude/skills/trellis-spec-bootstrap/references/mcp-setup.md": "df542fc8f279edd38046d26a7c8151804b708f57b24d4aa2733cea587a88c65e",
".claude/skills/trellis-spec-bootstrap/references/repository-analysis.md": "0dae98d774f6e34559b9f3442888ac43e3a8af110c37cbefc49ce256986858b6",
".claude/skills/trellis-spec-bootstrap/references/spec-task-planning.md": "ef493d028c3b0807a8a534bb71fb92a68129f273db763ad27ceb464a522e799d",
".claude/skills/trellis-spec-bootstrap/references/spec-writing.md": "e9800fe9ed4a4cd87062ea1829cf2caa8d170ec15e141678a6a30e74c497f47d",
".claude/skills/trellis-spec-bootstrap/SKILL.md": "97bfa68c06cebb558eb4464bc1b81f7d2d56040d75baa8de1ee5ad90cca0196a",
".agents/skills/trellis-continue/SKILL.md": "7723ccf49fbf19d8f086cacc7a080bd8be8db6fc70a32908b80f68efa318d7bf",
".agents/skills/trellis-finish-work/SKILL.md": "161060fbcd44f787440d3a5c297a9f5223ea7774bb3021a50e376875a9ac5b2d",
".agents/skills/trellis-before-dev/SKILL.md": "859894f2e8258cbfa142d710363433761c54984c69f7ed7bd44512fb4eb165cd",
".agents/skills/trellis-brainstorm/SKILL.md": "219f99c61e59aa9af4642c0ec96ceec72c915f6757572760ba69dee951b05eb1",
".agents/skills/trellis-break-loop/SKILL.md": "f5a93699832f29dee443b53c135a7459519b371f689af191d15c29e8ee5c7bde",
".agents/skills/trellis-check/SKILL.md": "b21ff04b7680ebacb8c5ecbc48a22d627eb13e2b47fceb78c8ced0b43b60b282",
".agents/skills/trellis-update-spec/SKILL.md": "003ce08a3404aeb50998029392c4d4e57b626edf526d3ebd585032bb92dcbb96",
".agents/skills/trellis-channel/references/command-reference.md": "c4df3d940d89814310bfdaded20e84dd1d6b96786f6772688de7a123338d3c8e",
".agents/skills/trellis-channel/references/forum.md": "407db39e8ebde47cea8637e3069bdb3d76ba42b43ed1d08ba97a56f26dbcfcb4",
".agents/skills/trellis-channel/references/progress-debugging.md": "93b021fd8d5d3d4ee54952c40424ab91ca57c2ab8032bfbfc3b5c5e22f1464cd",
".agents/skills/trellis-channel/references/workers.md": "d4481b2858bca82050cb8d131916da8a2ccc3857f199cdb9ced8bb41d592e2a7",
".agents/skills/trellis-channel/references/workflows.md": "0782d602efde6e94a7d7d7950fd605eedc9a1f5a523908284e76b628fd618fd4",
".agents/skills/trellis-channel/SKILL.md": "ff84801c511a736da018b4b1149348ebc9a16b7fc18d905ec10cfa7acbf269a3",
".agents/skills/trellis-meta/references/customize-local/add-project-local-conventions.md": "86009ccb5d0373f399582da0bc570c4e5c6053c3c764857424ff93384f0e04e5",
".agents/skills/trellis-meta/references/customize-local/change-agents.md": "3eef0d9b9cf875f121c1a38afb8eee6d3cd3894127db601ae5a7760fa5b61575",
".agents/skills/trellis-meta/references/customize-local/change-context-loading.md": "350d319dc1ab99609ddbf52cf8c06c71bd97ba1a29ce2eac8b97d0bb192938bf",
".agents/skills/trellis-meta/references/customize-local/change-hooks.md": "91892f2cff53ae003736007e95172945acabf48b2fc889bd627cd2406ce449c4",
".agents/skills/trellis-meta/references/customize-local/change-skills-or-commands.md": "a6994e2418cdf5bcad10b4236b02741179ae794bc4fdd811a64f443293b69268",
".agents/skills/trellis-meta/references/customize-local/change-spec-structure.md": "31eccaad7097d96e66a45c1b4caea1ba4f2e54b7814184c3ebf82c87dafc4841",
".agents/skills/trellis-meta/references/customize-local/change-task-lifecycle.md": "60ff9efb93604b87a461a4af30322d76750402a51e40f31531a7ff88d309996d",
".agents/skills/trellis-meta/references/customize-local/change-workflow.md": "43fa780a2ca580de121b10893d49b99f978873deebbf45008c466e5ac6651519",
".agents/skills/trellis-meta/references/customize-local/overview.md": "ce8f09e9f93ce9a48500763fb3a4db2b3908a5fbf4f985ab71dacebb404cf8f4",
".agents/skills/trellis-meta/references/local-architecture/bundled-skills.md": "bac739b042d7a12dae5d14d85cbc312e56ca03f571d2ba7a25b20641ddaefc3f",
".agents/skills/trellis-meta/references/local-architecture/context-injection.md": "8497289bf333b3aa456f317039d1239b7ece79254aa0eb62cfc647714c866084",
".agents/skills/trellis-meta/references/local-architecture/generated-files.md": "ca4211b43aff79cf263c83255f557994386723d10da344c0c4e1ec211c7fcd37",
".agents/skills/trellis-meta/references/local-architecture/multi-agent-channel.md": "56e5070474aeca872e2d70c46feea5aaafecd3d3ec052c3f7b1877358dca62e9",
".agents/skills/trellis-meta/references/local-architecture/overview.md": "50638fd9eaaba2e0edf2f2a84d920578d5b2fb7934031b174e417d3dc510b2a6",
".agents/skills/trellis-meta/references/local-architecture/spec-system.md": "b8d8a6a0888b44a232c8f50161b9e20e903cf621ad7be4021715ab6fab226f47",
".agents/skills/trellis-meta/references/local-architecture/task-system.md": "2b561d49c390f7d0db5391912946133be4bf73189231e2b8cc9afa1c5ac6165a",
".agents/skills/trellis-meta/references/local-architecture/workflow.md": "cfcdc6e4468a5d9c816e929fcca01640cd41cfdaaa4824118b40a8e460c927b6",
".agents/skills/trellis-meta/references/local-architecture/workspace-memory.md": "e6427b46aba744563c2444b30df4043cd856561b7709ec2dece26095416421fd",
".agents/skills/trellis-meta/references/platform-files/agents.md": "ce1a22c2b3ff0bff68755b5663e1f3b63ef2f1658cff43e511cee9013537c698",
".agents/skills/trellis-meta/references/platform-files/hooks-and-settings.md": "b70f983d0b3fea45e4ad7abef8ab8981473ff016d6d454d4d407865c13019d31",
".agents/skills/trellis-meta/references/platform-files/overview.md": "7bc24f5ffefe082f373562bbba715cce9e761a76f6b59ce341d4dc679971a587",
".agents/skills/trellis-meta/references/platform-files/platform-map.md": "a3cb8b4b4e42a3b380485aca673750ba3b2b28c16a04339b1db7afbd479509ab",
".agents/skills/trellis-meta/references/platform-files/skills-and-commands.md": "5732bb0a7d384a91abd0c103372f3865e0b186e75185f35e0e91b00a6b6bf5a3",
".agents/skills/trellis-meta/SKILL.md": "a190ecbde70a658a5b5c3e2558783e99c9afc6f2e5cdecdac8f11c06dd42065e",
".agents/skills/trellis-session-insight/references/cli-quick-reference.md": "c520353fe3fc00b9702ed4f780647c8fbd6d342e66527a03647f533a9fe09779",
".agents/skills/trellis-session-insight/references/triggering-patterns.md": "121ecd23be83d1567e8ce15c366a81073d7a2b1d3ad616fce235c07ca1f1cc20",
".agents/skills/trellis-session-insight/SKILL.md": "f6ad80eaca21b8fa63d31ae26b612bb2bb69dd04469603828509a8c5a0463ff1",
".agents/skills/trellis-spec-bootstrap/references/mcp-setup.md": "df542fc8f279edd38046d26a7c8151804b708f57b24d4aa2733cea587a88c65e",
".agents/skills/trellis-spec-bootstrap/references/repository-analysis.md": "0dae98d774f6e34559b9f3442888ac43e3a8af110c37cbefc49ce256986858b6",
".agents/skills/trellis-spec-bootstrap/references/spec-task-planning.md": "ef493d028c3b0807a8a534bb71fb92a68129f273db763ad27ceb464a522e799d",
".agents/skills/trellis-spec-bootstrap/references/spec-writing.md": "e9800fe9ed4a4cd87062ea1829cf2caa8d170ec15e141678a6a30e74c497f47d",
".agents/skills/trellis-spec-bootstrap/SKILL.md": "97bfa68c06cebb558eb4464bc1b81f7d2d56040d75baa8de1ee5ad90cca0196a",
".agents/skills/trellis-start/SKILL.md": "79a5ba7a2aff3c72e06d7f4cd6942dc4f4f4092dd40f9c8e94f1838024a81e4d",
".codex/agents/trellis-check.toml": "372dbd32a68f156727fd9f5d755a184543db96013abfeaffb09974c78fd5b873",
".codex/agents/trellis-implement.toml": "87dc719802b355c61607c85ae0ab3e42b2a374a578a9fde349c3ae412638f8b4",
".codex/agents/trellis-research.toml": "5492f7f6ab8bdea975b0e853bf171b050f7ddf6c2079ac770ed912c48d815eae",
".codex/hooks/session-start.py": "1c951ff35f490c5fbf576b4764ec190895df7c2a48e279fb20625209f51c321a",
".codex/hooks/inject-workflow-state.py": "f7fa9389ed7aa264597fff5de6277bec186e89a3ef539192997c6d026d88d5ec",
".codex/hooks.json": "522ba3c488c100027783e52ecff84c0bd799852dd77ad3f1936e86db105f01d6",
".trellis/agents/check.md": "edb4f57361407249a53bf5998ebf91c40d2b969e826a2c5e1b4e813a08bcb175",
".trellis/agents/implement.md": "66e25ad046c94869442834bc3cdfbd5a9a7412d3ff54561d64d2886552c27e87",
".trellis/config.yaml": "2e6489de5ab99c501f24edd3f08df977801bf49c33b04a2de6afafe35a3a8332",
".trellis/scripts/__init__.py": "1242be5b972094c2e141aecbe81a4efd478f6534e3d5e28306374e6a18fcf46c",
".trellis/scripts/add_session.py": "7fcacb29ffd13599949a517aa967d868040eb4c9b40356b0c460a32361237eb6",
".trellis/scripts/common/__init__.py": "3d5e9347141f0296319a5beb29d69ae714c5a474b9078caeb3edd7c5f6562e22",
".trellis/scripts/common/active_task.py": "6c88ed40ef7289bca0f6d2ecba0f8b8aef46cd58788080fbeeea88de138a431f",
".trellis/scripts/common/cli_adapter.py": "bda2eb3a76b3990ef979846a5eff3d8aedde9c70e0e9d128266034aeee186020",
".trellis/scripts/common/config.py": "25c5a53ad20d6909be5209222e4208a84528805316a4d78350529459a364edb1",
".trellis/scripts/common/developer.py": "f5f833123abe68890171b4da825a324216d24913f6b5ad9245afc556424ffd7b",
".trellis/scripts/common/git.py": "e14817be7de122d3a106f509c2825aeb9669d962ba73ba241642d2931cfdf1d6",
".trellis/scripts/common/git_context.py": "fa30ced454f1a91ffc9f8b2abeb32225e3447cbdc90bad783797374eba07265d",
".trellis/scripts/common/io.py": "6480b181f2bc505323b28ed7a66963d7b7edc96251e83b4c8e7a45907cc721c8",
".trellis/scripts/common/log.py": "471df6895cfac80f995edebbf9974f6b7440634b7a688f28b8331c868bc0f3cf",
".trellis/scripts/common/packages_context.py": "efe158d7c99c2268851d0216fbb08de22836e418a8dbeb73575b8cc249eed7b7",
".trellis/scripts/common/paths.py": "05898ef136cc7c4d861b05fbf2b16d53ddd3e6f311a231d4fcfcb81bde7c45ee",
".trellis/scripts/common/safe_commit.py": "baa5c82324eb62154374ec63394ecdc8609bb37d93892e3bcb88f452bb7d6446",
".trellis/scripts/common/session_context.py": "df79c44efe3432811c32d145d57a66343a70e221ec087ed2bd28b76677bb4076",
".trellis/scripts/common/task_context.py": "d174684d417bbe2fafc26b6afcddb264c7dc519527bb24d2055cd27daaad9b55",
".trellis/scripts/common/task_queue.py": "0be61f713462b1fe4574927c82fc4704e678afe72dcb9813543aedf2f9e9e0c5",
".trellis/scripts/common/task_store.py": "789c090c2d5103bf790e8bfb0989a8ff486c7d370cbe03d3eefb1c239d02624a",
".trellis/scripts/common/task_utils.py": "f5ef4af87ba3e11d8b19630c0c96d009de1811fc9be56c2027a9c96e21ed103e",
".trellis/scripts/common/tasks.py": "4436a8b0b53c270a35989e26d9dbd92669408c6562d88c02083a404562da85fe",
".trellis/scripts/common/trellis_config.py": "0839dcf90ebbd77712c276930a89335b3313927051650c91d220fb51ca2a6a3c",
".trellis/scripts/common/types.py": "9962081cc2608fb9d1deb32c6880e336f62cdca6b338e7ae813304701e155ee9",
".trellis/scripts/common/workflow_phase.py": "f2b5fcf0c40cedcf3d7d0ad8023d141fa4095caf0302d73f2a73e1bc04b5692b",
".trellis/scripts/get_context.py": "ca5bf9e90bdb1d75d3de182b95f820f9d108ab28793d29097b24fd71315adcf5",
".trellis/scripts/get_developer.py": "84c27076323c3e0f2c9c8ed16e8aa865e225d902a187c37e20ee1a46e7142d8f",
".trellis/scripts/hooks/linear_sync.py": "e09cc4ce4699aada908808718698f33f705a3edf55c4dcf8f777ad892f80ca79",
".trellis/scripts/init_developer.py": "f9e6c0d882406e81c8cd6b1c5abb204b0befc0069ff89cf650cd536a80f8c60e",
".trellis/scripts/task.py": "6c65801a1f56648fd4765a1d216493d3094827c1db4761e55fdaa548c1801798",
".trellis/workflow.md": "f44acd1c08d1601fdc4377671ef932eb3e09f0e87b7872a6d0ee4baeada29fcb"
}
}
.trellis/.version
+1
View File
@@ -0,0 +1 @@
0.6.3
.trellis/agents/check.md
+70
View File
@@ -0,0 +1,70 @@
---
name: check
description: |
Code quality auditor for the Trellis channel runtime. Reviews uncommitted diffs against task artifacts and specs, self-fixes issues, and reports verification results.
provider: claude
labels: [trellis, check]
---
# Check Agent (channel runtime)
You are the Check Agent spawned by `trellis channel spawn --agent check` inside the Trellis channel runtime. You receive an `Active task: <path>` line in your inbox; use it to locate task artifacts on disk.
## Context
Before reviewing, read in this order:
1. `<task-path>/check.jsonl` if present — spec manifest curated for this turn; read every listed file
2. `<task-path>/prd.md` — requirements
3. `<task-path>/design.md` if present — technical design
4. `<task-path>/implement.md` if present — execution plan
5. `.trellis/spec/` — project-wide guidelines (load only what is relevant to the diff under review)
## Core Responsibilities
1. **Get the diff** — `git diff` / `git diff --staged` for uncommitted changes
2. **Review against task artifacts** — does the diff satisfy `prd.md` (and `design.md` / `implement.md` if present)?
3. **Review against specs** — naming, structure, type safety, error handling, conventions in `.trellis/spec/`
4. **Self-fix** — when an issue is mechanical and small, fix it directly with the editing tools you have
5. **Run verification** — project lint and typecheck on the changed scope
6. **Report** — concrete findings with `file:line` citations and what was fixed vs. what is open
## Forbidden Operations
- `git commit`
- `git push`
- `git merge`
The supervising main session owns commits. Report the post-fix state; do not commit on its behalf.
## Workflow
1. Run `git diff --name-only` and `git diff` to scope the changes
2. Read the task artifacts and relevant spec files
3. For each issue:
- If mechanical (lint nit, missing type, wrong import, dead branch) → fix in-place
- If a design/judgment issue → record and report, do not silently rewrite
4. Run the project's lint and typecheck on the changed scope after self-fixes
5. Report
## Report Format
```
## Self-Check Complete
### Files Checked
- <path>
### Issues Found and Fixed
1. `<file>:<line>` — <what was wrong> → <what you changed>
### Issues Not Fixed
- `<file>:<line>` — <issue> — <why deferred to the main session>
### Verification Results
- TypeCheck: <pass|fail|skipped + reason>
- Lint: <pass|fail|skipped + reason>
### Summary
Checked <N> files, found <X> issues, fixed <Y>, <X-Y> open.
```
.trellis/agents/implement.md
+71
View File
@@ -0,0 +1,71 @@
---
name: implement
description: |
Code implementation expert for the Trellis channel runtime. Understands specs and task artifacts, then implements features. No git commit allowed.
provider: claude
labels: [trellis, implement]
---
# Implement Agent (channel runtime)
You are the Implement Agent spawned by `trellis channel spawn --agent implement` inside the Trellis channel runtime. You receive an `Active task: <path>` line in your inbox; use it to locate task artifacts on disk.
## Context
Before implementing, read in this order:
1. `<task-path>/implement.jsonl` if present — spec manifest curated for this turn; read every listed file
2. `<task-path>/prd.md` — requirements
3. `<task-path>/design.md` if present — technical design
4. `<task-path>/implement.md` if present — execution plan
5. `.trellis/spec/` — project-wide guidelines (load only what is relevant to the diff you are about to write)
## Core Responsibilities
1. **Understand specs** — read relevant spec files in `.trellis/spec/`
2. **Understand task artifacts** — read the artifacts listed above
3. **Implement features** — write code that follows specs and existing patterns
4. **Self-check** — run lint and typecheck on the changed scope before reporting
## Forbidden Operations
- `git commit`
- `git push`
- `git merge`
The supervising main session owns commits. Report what changed; do not commit on its behalf.
## Workflow
1. Read relevant specs based on task type and the files in `implement.jsonl` if present
2. Read the task's `prd.md`, `design.md` if present, and `implement.md` if present
3. Implement features following specs and existing patterns
4. Run the project's lint and typecheck commands on the changed scope
5. Report files touched, key decisions, and verification results back to the channel
## Code Standards
- Follow existing code patterns
- Don't add unnecessary abstractions
- Only do what the PRD asks for; no speculative scope expansion
- Surface uncertainty back to the channel rather than guessing
## Report Format
```
## Implementation Complete
### Files Modified
- <path> — <one-line description>
### Implementation Summary
1. <step>
2. <step>
### Verification Results
- Lint: <pass|fail|skipped + reason>
- TypeCheck: <pass|fail|skipped + reason>
### Open Questions
- <if any, otherwise omit>
```
.trellis/config.yaml
+117
View File
@@ -0,0 +1,117 @@
# Trellis Configuration
# Project-level settings for the Trellis workflow system
#
# All values have sensible defaults. Only override what you need.
#-------------------------------------------------------------------------------
# Session Recording
#-------------------------------------------------------------------------------
# Commit message used when auto-committing journal/index changes
# after running add_session.py
session_commit_message: "chore: record journal"
# Maximum lines per journal file before rotating to a new one
max_journal_lines: 2000
#-------------------------------------------------------------------------------
# Session Auto-Commit
#-------------------------------------------------------------------------------
# Auto-commit behavior for session journal + task archive operations.
# - true (default): scripts auto-stage and auto-commit journal / task changes
# after add_session.py / task.py archive runs.
# - false: scripts do not touch git. Files (journal-*.md, task archive moves)
# are still written to disk; you decide whether to git add / commit.
#
# Use `false` if your project's .gitignore intentionally excludes `.trellis/`
# and you want session data kept local-only, or if you prefer to review
# staged changes manually before each commit.
#
# Accepts: true / false / yes / no / 1 / 0 / on / off (case-insensitive).
#
# session_auto_commit: true
#-------------------------------------------------------------------------------
# Task Lifecycle Hooks
#-------------------------------------------------------------------------------
# Shell commands to run after task lifecycle events.
# Each hook receives TASK_JSON_PATH environment variable pointing to task.json.
# Hook failures print a warning but do not block the main operation.
#
# hooks:
# after_create:
# - "echo 'Task created'"
# after_start:
# - "echo 'Task started'"
# after_finish:
# - "echo 'Task finished'"
# after_archive:
# - "echo 'Task archived'"
#-------------------------------------------------------------------------------
# Monorepo / Packages
#-------------------------------------------------------------------------------
# Declare packages for monorepo projects.
# Trellis auto-detects workspaces during `trellis init`, but you can also
# configure them manually here.
#
# packages:
# frontend:
# path: packages/frontend
# backend:
# path: packages/backend
# docs:
# path: docs-site
# type: submodule
# # For polyrepo / meta-repo layouts (independent .git in each subdir),
# # mark the package with `git: true`. The runtime treats it as an
# # independent repository for things like git-context display.
# webapp:
# path: ./webapp
# git: true
# Default package used when --package is not specified.
# default_package: frontend
#-------------------------------------------------------------------------------
# Channel worker OOM guard
#-------------------------------------------------------------------------------
# Default safeguards for `trellis channel spawn` workers. The guard runs
# at spawn time (cleans expired idle workers, then enforces the live-worker
# budget) and inside each supervisor (self-terminates a worker that stays
# continuously idle past `idle_timeout`).
#
# Precedence: CLI flag > env var (TRELLIS_CHANNEL_WORKER_IDLE_TIMEOUT /
# TRELLIS_CHANNEL_MAX_LIVE_WORKERS) > this config > built-in default.
#
# `idle_timeout: 0` disables idle cleanup (workers can sit idle forever
# unless explicitly killed or given `--timeout`).
# `max_live_workers: 0` disables the spawn-time budget check.
#
channel:
worker_guard:
idle_timeout: 5m
max_live_workers: 6
#-------------------------------------------------------------------------------
# Codex (dispatch behavior)
#-------------------------------------------------------------------------------
# Codex-only knob; other platforms ignore it. Default ("inline") makes the
# main Codex agent edit code directly because Codex sub-agents run with
# `fork_turns="none"` isolation and can't inherit the parent session's
# task context. Set to "sub-agent" to opt into the legacy dispatch model
# (main agent spawns trellis-implement / trellis-check / trellis-research
# sub-agents).
#
# codex:
# dispatch_mode: inline # or "sub-agent" to dispatch trellis-* sub-agents
# Auto-detected monorepo packages
packages:
vendor/ComfyUI_frontend:
path: vendor/ComfyUI_frontend
type: submodule
default_package: vendor/ComfyUI_frontend
.trellis/scripts/__init__.py
Executable
+5
View File
@@ -0,0 +1,5 @@
"""
Trellis Python Scripts
This module provides Python implementations of Trellis workflow scripts.
"""
.trellis/scripts/add_session.py
Executable
+567
View File
@@ -0,0 +1,567 @@
#!/usr/bin/env python3
# -*- coding: utf-8 -*-
"""
Add a new session to journal file and update index.md.
Usage:
python3 add_session.py --title "Title" --commit "hash" --summary "Summary" [--package cli]
python3 add_session.py --title "Title" --branch "feat/my-branch"
# Pipe detailed content via stdin (use --stdin to opt in):
cat << 'EOF' | python3 add_session.py --stdin --title "Title" --summary "Summary"
<session content here>
EOF
Branch resolution order:
1. --branch CLI arg (explicit)
2. task.json branch field (from active task)
3. git branch --show-current (auto-detect)
4. None (omitted gracefully)
"""
from __future__ import annotations
import argparse
import re
import sys
from datetime import datetime
from pathlib import Path
from common.paths import (
DIR_TASKS,
DIR_WORKFLOW,
FILE_JOURNAL_PREFIX,
get_repo_root,
get_current_task,
get_developer,
get_workspace_dir,
)
from common.developer import ensure_developer
from common.git import run_git
from common.safe_commit import (
print_gitignore_warning,
safe_git_add,
safe_trellis_paths_to_add,
)
from common.tasks import load_task
from common.config import (
get_packages,
get_session_auto_commit,
get_session_commit_message,
get_max_journal_lines,
is_monorepo,
resolve_package,
validate_package,
)
# =============================================================================
# Helper Functions
# =============================================================================
def get_latest_journal_info(dev_dir: Path) -> tuple[Path | None, int, int]:
"""Get latest journal file info.
Returns:
Tuple of (file_path, file_number, line_count).
"""
latest_file: Path | None = None
latest_num = -1
for f in dev_dir.glob(f"{FILE_JOURNAL_PREFIX}*.md"):
if not f.is_file():
continue
match = re.search(r"(\d+)$", f.stem)
if match:
num = int(match.group(1))
if num > latest_num:
latest_num = num
latest_file = f
if latest_file:
lines = len(latest_file.read_text(encoding="utf-8").splitlines())
return latest_file, latest_num, lines
return None, 0, 0
def get_current_session(index_file: Path) -> int:
"""Get current session number from index.md."""
if not index_file.is_file():
return 0
content = index_file.read_text(encoding="utf-8")
for line in content.splitlines():
if "Total Sessions" in line:
match = re.search(r":\s*(\d+)", line)
if match:
return int(match.group(1))
return 0
def _extract_journal_num(filename: str) -> int:
"""Extract journal number from filename for sorting."""
match = re.search(r"(\d+)", filename)
return int(match.group(1)) if match else 0
def count_journal_files(dev_dir: Path, active_num: int) -> str:
"""Count journal files and return table rows."""
active_file = f"{FILE_JOURNAL_PREFIX}{active_num}.md"
result_lines = []
files = sorted(
[f for f in dev_dir.glob(f"{FILE_JOURNAL_PREFIX}*.md") if f.is_file()],
key=lambda f: _extract_journal_num(f.stem),
reverse=True
)
for f in files:
filename = f.name
lines = len(f.read_text(encoding="utf-8").splitlines())
status = "Active" if filename == active_file else "Archived"
result_lines.append(f"| `{filename}` | ~{lines} | {status} |")
return "\n".join(result_lines)
def create_new_journal_file(
dev_dir: Path, num: int, developer: str, today: str, max_lines: int = 2000,
) -> Path:
"""Create a new journal file."""
prev_num = num - 1
new_file = dev_dir / f"{FILE_JOURNAL_PREFIX}{num}.md"
content = f"""# Journal - {developer} (Part {num})
> Continuation from `{FILE_JOURNAL_PREFIX}{prev_num}.md` (archived at ~{max_lines} lines)
> Started: {today}
---
"""
new_file.write_text(content, encoding="utf-8")
return new_file
def generate_session_content(
session_num: int,
title: str,
commit: str,
summary: str,
extra_content: str,
today: str,
package: str | None = None,
branch: str | None = None,
) -> str:
"""Generate session content."""
if commit and commit != "-":
commit_table = """| Hash | Message |
|------|---------|"""
for c in commit.split(","):
c = c.strip()
commit_table += f"\n| `{c}` | (see git log) |"
else:
commit_table = "(No commits - planning session)"
package_line = f"\n**Package**: {package}" if package else ""
branch_line = f"\n**Branch**: `{branch}`" if branch else ""
return f"""
## Session {session_num}: {title}
**Date**: {today}
**Task**: {title}{package_line}{branch_line}
### Summary
{summary}
### Main Changes
{extra_content}
### Git Commits
{commit_table}
### Testing
- [OK] (Add test results)
### Status
[OK] **Completed**
### Next Steps
- None - task complete
"""
def update_index(
index_file: Path,
dev_dir: Path,
title: str,
commit: str,
new_session: int,
active_file: str,
today: str,
branch: str | None = None,
) -> bool:
"""Update index.md with new session info."""
# Format commit for display
commit_display = "-"
if commit and commit != "-":
commit_display = re.sub(r"([a-f0-9]{7,})", r"`\1`", commit.replace(",", ", "))
# Get file number from active_file name
match = re.search(r"(\d+)", active_file)
active_num = int(match.group(1)) if match else 0
files_table = count_journal_files(dev_dir, active_num)
print(f"Updating index.md for session {new_session}...")
print(f" Title: {title}")
print(f" Commit: {commit_display}")
print(f" Active File: {active_file}")
print()
content = index_file.read_text(encoding="utf-8")
if "@@@auto:current-status" not in content:
print("Error: Markers not found in index.md. Please ensure markers exist.", file=sys.stderr)
return False
# Process sections
lines = content.splitlines()
new_lines = []
in_current_status = False
in_active_documents = False
in_session_history = False
header_written = False
for line in lines:
if "@@@auto:current-status" in line:
new_lines.append(line)
in_current_status = True
new_lines.append(f"- **Active File**: `{active_file}`")
new_lines.append(f"- **Total Sessions**: {new_session}")
new_lines.append(f"- **Last Active**: {today}")
continue
if "@@@/auto:current-status" in line:
in_current_status = False
new_lines.append(line)
continue
if "@@@auto:active-documents" in line:
new_lines.append(line)
in_active_documents = True
new_lines.append("| File | Lines | Status |")
new_lines.append("|------|-------|--------|")
new_lines.append(files_table)
continue
if "@@@/auto:active-documents" in line:
in_active_documents = False
new_lines.append(line)
continue
if "@@@auto:session-history" in line:
new_lines.append(line)
in_session_history = True
header_written = False
continue
if "@@@/auto:session-history" in line:
in_session_history = False
new_lines.append(line)
continue
if in_current_status:
continue
if in_active_documents:
continue
if in_session_history:
# Migrate old 4/6-column headers to 5-column Branch-only history.
if re.match(
r"^\|\s*#\s*\|\s*Date\s*\|\s*Title\s*\|\s*Commits\s*\|\s*Branch\s*\|\s*Base Branch\s*\|\s*$",
line,
):
new_lines.append("| # | Date | Title | Commits | Branch |")
continue
if re.match(r"^\|\s*#\s*\|\s*Date\s*\|\s*Title\s*\|\s*Commits\s*\|\s*Branch\s*\|\s*$", line):
new_lines.append("| # | Date | Title | Commits | Branch |")
continue
if re.match(r"^\|\s*#\s*\|\s*Date\s*\|\s*Title\s*\|\s*Commits\s*\|\s*$", line):
new_lines.append("| # | Date | Title | Commits | Branch |")
continue
if re.match(r"^\|[-| ]+\|\s*$", line) and not header_written:
new_lines.append("|---|------|-------|---------|--------|")
new_lines.append(f"| {new_session} | {today} | {title} | {commit_display} | `{branch or '-'}` |")
header_written = True
continue
new_lines.append(line)
continue
new_lines.append(line)
index_file.write_text("\n".join(new_lines), encoding="utf-8")
print("[OK] Updated index.md successfully!")
return True
# =============================================================================
# Main Function
# =============================================================================
def _auto_commit_workspace(repo_root: Path) -> None:
"""Stage Trellis-owned workspace + current-task paths and commit.
Path scope is restricted to specific products: the current developer's
journal files + index.md, and ONLY the current task directory (resolved
via ``get_current_task``). We never `git add` the whole `.trellis/` tree
or iterate over all active task dirs (#303: parallel-window dirty task
dirs must not be bundled into the session auto-commit). If `.gitignore`
blocks the specific paths we warn + skip — never retry with ``-f``.
Honors ``session_auto_commit`` in ``.trellis/config.yaml``: when set to
``false``, this function returns immediately without touching git
(journal/index files are still written to disk by the caller).
"""
if not get_session_auto_commit(repo_root):
print(
"[OK] session_auto_commit: false — skipping git stage/commit.",
file=sys.stderr,
)
return
commit_msg = get_session_commit_message(repo_root)
# Resolve the current task so staging is scoped to its dir only. The ref
# is ``.trellis/tasks/<name>`` (or under archive/) — pass the bare name.
current = get_current_task(repo_root)
if current:
task_name = Path(current).name
paths = safe_trellis_paths_to_add(repo_root, task_name=task_name)
else:
# Current task unknown (0 or >=2 parallel sessions — exactly the
# parallel-window case #303 is about). Do NOT fall back to the wide
# `tasks_dir.iterdir()` scan; that would re-leak other tasks' dirty
# dirs into the session commit. Stage only the developer's journal/
# index and skip every task dir.
paths = [
p
for p in safe_trellis_paths_to_add(repo_root, task_name=None)
if not p.startswith(f"{DIR_WORKFLOW}/{DIR_TASKS}/")
]
if not paths:
print("[OK] No workspace changes to commit.", file=sys.stderr)
return
success, _, err = safe_git_add(paths, repo_root)
if not success:
if err and "ignored by" in err.lower():
print_gitignore_warning(paths)
else:
print(
f"[WARN] git add failed: {err.strip() if err else 'unknown error'}",
file=sys.stderr,
)
return
# Check if there are staged changes for the paths we just staged.
rc, _, _ = run_git(
["diff", "--cached", "--quiet", "--", *paths], cwd=repo_root
)
if rc == 0:
print("[OK] No workspace changes to commit.", file=sys.stderr)
return
rc, _, commit_err = run_git(["commit", "-m", commit_msg], cwd=repo_root)
if rc == 0:
print(f"[OK] Auto-committed: {commit_msg}", file=sys.stderr)
else:
print(
f"[WARN] Auto-commit failed: {commit_err.strip()}",
file=sys.stderr,
)
def add_session(
title: str,
commit: str = "-",
summary: str = "(Add summary)",
extra_content: str = "(Add details)",
auto_commit: bool = True,
package: str | None = None,
branch: str | None = None,
) -> int:
"""Add a new session."""
repo_root = get_repo_root()
ensure_developer(repo_root)
developer = get_developer(repo_root)
if not developer:
print("Error: Developer not initialized", file=sys.stderr)
return 1
dev_dir = get_workspace_dir(repo_root)
if not dev_dir:
print("Error: Workspace directory not found", file=sys.stderr)
return 1
max_lines = get_max_journal_lines(repo_root)
index_file = dev_dir / "index.md"
today = datetime.now().strftime("%Y-%m-%d")
journal_file, current_num, current_lines = get_latest_journal_info(dev_dir)
current_session = get_current_session(index_file)
new_session = current_session + 1
session_content = generate_session_content(
new_session, title, commit, summary, extra_content, today, package,
branch,
)
content_lines = len(session_content.splitlines())
print("========================================", file=sys.stderr)
print("ADD SESSION", file=sys.stderr)
print("========================================", file=sys.stderr)
print("", file=sys.stderr)
print(f"Session: {new_session}", file=sys.stderr)
print(f"Title: {title}", file=sys.stderr)
print(f"Commit: {commit}", file=sys.stderr)
print("", file=sys.stderr)
print(f"Current journal file: {FILE_JOURNAL_PREFIX}{current_num}.md", file=sys.stderr)
print(f"Current lines: {current_lines}", file=sys.stderr)
print(f"New content lines: {content_lines}", file=sys.stderr)
print(f"Total after append: {current_lines + content_lines}", file=sys.stderr)
print("", file=sys.stderr)
target_file = journal_file
target_num = current_num
if current_lines + content_lines > max_lines:
target_num = current_num + 1
print(f"[!] Exceeds {max_lines} lines, creating {FILE_JOURNAL_PREFIX}{target_num}.md", file=sys.stderr)
target_file = create_new_journal_file(dev_dir, target_num, developer, today, max_lines)
print(f"Created: {target_file}", file=sys.stderr)
# Append session content
if target_file:
with target_file.open("a", encoding="utf-8") as f:
f.write(session_content)
print(f"[OK] Appended session to {target_file.name}", file=sys.stderr)
print("", file=sys.stderr)
# Update index.md
active_file = f"{FILE_JOURNAL_PREFIX}{target_num}.md"
if not update_index(
index_file,
dev_dir,
title,
commit,
new_session,
active_file,
today,
branch,
):
return 1
print("", file=sys.stderr)
print("========================================", file=sys.stderr)
print(f"[OK] Session {new_session} added successfully!", file=sys.stderr)
print("========================================", file=sys.stderr)
print("", file=sys.stderr)
print("Files updated:", file=sys.stderr)
print(f" - {target_file.name if target_file else 'journal'}", file=sys.stderr)
print(" - index.md", file=sys.stderr)
# Auto-commit workspace changes
if auto_commit:
print("", file=sys.stderr)
_auto_commit_workspace(repo_root)
return 0
# =============================================================================
# Main Entry
# =============================================================================
def main() -> int:
"""CLI entry point."""
parser = argparse.ArgumentParser(
description="Add a new session to journal file and update index.md"
)
parser.add_argument("--title", required=True, help="Session title")
parser.add_argument("--commit", default="-", help="Comma-separated commit hashes")
parser.add_argument("--summary", default="(Add summary)", help="Brief summary")
parser.add_argument("--content-file", help="Path to file with detailed content")
parser.add_argument("--package", help="Package name tag (e.g., cli, docs-site)")
parser.add_argument("--branch", help="Branch name (auto-detected if omitted)")
parser.add_argument("--no-commit", action="store_true",
help="Skip auto-commit of workspace changes")
parser.add_argument("--stdin", action="store_true",
help="Read extra content from stdin (explicit opt-in)")
args = parser.parse_args()
extra_content = "(Add details)"
if args.content_file:
content_path = Path(args.content_file)
if content_path.is_file():
extra_content = content_path.read_text(encoding="utf-8")
elif args.stdin:
extra_content = sys.stdin.read()
# Load active task once — shared by package and branch resolution
repo_root = get_repo_root()
current = get_current_task(repo_root)
task_data = load_task(repo_root / current) if current else None
package = args.package
if package:
# CLI source: fail-fast in monorepo, ignore in single-repo
if not is_monorepo(repo_root):
print("Warning: --package ignored in single-repo project", file=sys.stderr)
package = None
elif not validate_package(package, repo_root):
packages = get_packages(repo_root)
available = ", ".join(sorted(packages.keys())) if packages else "(none)"
print(f"Error: unknown package '{package}'. Available: {available}", file=sys.stderr)
return 1
else:
# Inferred: active task's task.json.package → default_package → None
task_package = task_data.package if task_data else None
package = resolve_package(task_package, repo_root)
# Resolve branch: CLI → task.json → git auto-detect → None
branch = args.branch
if not branch:
if task_data and task_data.raw.get("branch"):
branch = task_data.raw["branch"]
else:
_, branch_out, _ = run_git(["branch", "--show-current"], cwd=repo_root)
detected = branch_out.strip()
if detected:
branch = detected
return add_session(
args.title, args.commit, args.summary, extra_content,
auto_commit=not args.no_commit,
package=package,
branch=branch,
)
if __name__ == "__main__":
sys.exit(main())
.trellis/scripts/common/__init__.py
Executable
+92
View File
@@ -0,0 +1,92 @@
"""
Common utilities for Trellis workflow scripts.
This module provides shared functionality used by other Trellis scripts.
"""
import io
import sys
# =============================================================================
# Windows Encoding Fix (MUST be at top, before any other output)
# =============================================================================
# On Windows, stdout defaults to the system code page (often GBK/CP936).
# This causes UnicodeEncodeError when printing non-ASCII characters.
#
# Any script that imports from common will automatically get this fix.
# =============================================================================
def _configure_stream(stream: object) -> object:
"""Configure a stream for UTF-8 encoding on Windows."""
# Try reconfigure() first (Python 3.7+, more reliable)
if hasattr(stream, "reconfigure"):
stream.reconfigure(encoding="utf-8", errors="replace") # type: ignore[union-attr]
return stream
# Fallback: detach and rewrap with TextIOWrapper
elif hasattr(stream, "detach"):
return io.TextIOWrapper(
stream.detach(), # type: ignore[union-attr]
encoding="utf-8",
errors="replace",
)
return stream
if sys.platform == "win32":
sys.stdout = _configure_stream(sys.stdout) # type: ignore[assignment]
sys.stderr = _configure_stream(sys.stderr) # type: ignore[assignment]
sys.stdin = _configure_stream(sys.stdin) # type: ignore[assignment]
def configure_encoding() -> None:
"""
Configure stdout/stderr/stdin for UTF-8 encoding on Windows.
This is automatically called when importing from common,
but can be called manually for scripts that don't import common.
Safe to call multiple times.
"""
global sys
if sys.platform == "win32":
sys.stdout = _configure_stream(sys.stdout) # type: ignore[assignment]
sys.stderr = _configure_stream(sys.stderr) # type: ignore[assignment]
sys.stdin = _configure_stream(sys.stdin) # type: ignore[assignment]
from .paths import (
DIR_WORKFLOW,
DIR_WORKSPACE,
DIR_TASKS,
DIR_ARCHIVE,
DIR_SPEC,
DIR_SCRIPTS,
FILE_DEVELOPER,
FILE_CURRENT_TASK,
FILE_TASK_JSON,
FILE_JOURNAL_PREFIX,
get_repo_root,
get_developer,
check_developer,
get_tasks_dir,
get_workspace_dir,
get_active_journal_file,
count_lines,
get_current_task,
get_current_task_abs,
normalize_task_ref,
resolve_task_ref,
set_current_task,
clear_current_task,
has_current_task,
generate_task_date_prefix,
)
from .active_task import (
ActiveTask,
clear_active_task,
resolve_active_task,
resolve_context_key,
set_active_task,
)
.trellis/scripts/common/active_task.py
Executable
+626
View File
@@ -0,0 +1,626 @@
#!/usr/bin/env python3
"""Session-scoped active task resolution.
The user-facing concept is a single "active task". Trellis stores that pointer
per AI session/window under `.trellis/.runtime/sessions/`; without a stable
session key there is no active task.
"""
from __future__ import annotations
import hashlib
import json
import os
import re
import sys
import time
from dataclasses import dataclass
from datetime import datetime, timezone
from pathlib import Path
from typing import Any
DIR_WORKFLOW = ".trellis"
DIR_TASKS = "tasks"
DIR_RUNTIME = ".runtime"
DIR_SESSIONS = "sessions"
DIR_CURSOR_SHELL = "cursor-shell"
CURSOR_SHELL_TICKET_TTL_SECONDS = 30
TASK_SESSION_COMMANDS = {"start", "current", "finish"}
_SESSION_KEYS = ("session_id", "sessionId", "sessionID")
_CONVERSATION_KEYS = ("conversation_id", "conversationId", "conversationID")
_TRANSCRIPT_KEYS = ("transcript_path", "transcriptPath", "transcript")
_NESTED_KEYS = ("input", "properties", "event", "hook_input", "hookInput")
_KNOWN_PLATFORMS = {
"claude",
"codex",
"cursor",
"opencode",
"gemini",
"droid",
"qoder",
"codebuddy",
"kiro",
"copilot",
"pi",
}
_ENV_SESSION_KEYS: tuple[tuple[str, tuple[str, ...]], ...] = (
("claude", ("CLAUDE_SESSION_ID", "CLAUDE_CODE_SESSION_ID")),
("codex", ("CODEX_SESSION_ID", "CODEX_THREAD_ID")),
("cursor", ("CURSOR_SESSION_ID",)),
("opencode", ("OPENCODE_SESSION_ID", "OPENCODE_SESSIONID", "OPENCODE_RUN_ID")),
("gemini", ("GEMINI_SESSION_ID",)),
("droid", ("FACTORY_SESSION_ID", "DROID_SESSION_ID")),
("qoder", ("QODER_SESSION_ID",)),
("codebuddy", ("CODEBUDDY_SESSION_ID",)),
("kiro", ("KIRO_SESSION_ID",)),
("copilot", ("COPILOT_SESSION_ID", "COPILOT_SESSIONID")),
("pi", ("PI_SESSION_ID", "PI_SESSIONID")),
)
_ENV_CONVERSATION_KEYS: tuple[tuple[str, tuple[str, ...]], ...] = (
("cursor", ("CURSOR_CONVERSATION_ID", "CURSOR_CONVERSATIONID")),
)
_ENV_TRANSCRIPT_KEYS: tuple[tuple[str, tuple[str, ...]], ...] = (
("claude", ("CLAUDE_TRANSCRIPT_PATH",)),
("codex", ("CODEX_TRANSCRIPT_PATH",)),
("cursor", ("CURSOR_TRANSCRIPT_PATH",)),
("gemini", ("GEMINI_TRANSCRIPT_PATH",)),
("droid", ("FACTORY_TRANSCRIPT_PATH", "DROID_TRANSCRIPT_PATH")),
("qoder", ("QODER_TRANSCRIPT_PATH",)),
("codebuddy", ("CODEBUDDY_TRANSCRIPT_PATH",)),
)
_ENV_PLATFORM_ALIASES = {
"claude-code": "claude",
"factory": "droid",
"factory-ai": "droid",
"github-copilot": "copilot",
}
@dataclass(frozen=True)
class ActiveTask:
"""Resolved active task state."""
task_path: str | None
source_type: str
context_key: str | None = None
stale: bool = False
@property
def source(self) -> str:
"""Human-readable source label."""
if self.source_type == "session" and self.context_key:
return f"session:{self.context_key}"
if self.source_type == "session-fallback" and self.context_key:
return f"session-fallback:{self.context_key}"
return self.source_type
def normalize_task_ref(task_ref: str) -> str:
"""Normalize a task ref for stable storage and comparison."""
normalized = task_ref.strip()
if not normalized:
return ""
path_obj = Path(normalized)
if path_obj.is_absolute():
return str(path_obj)
normalized = normalized.replace("\\", "/")
while normalized.startswith("./"):
normalized = normalized[2:]
if normalized.startswith(f"{DIR_TASKS}/"):
return f"{DIR_WORKFLOW}/{normalized}"
return normalized
def resolve_task_ref(task_ref: str, repo_root: Path) -> Path | None:
"""Resolve a task ref to an absolute task directory."""
normalized = normalize_task_ref(task_ref)
if not normalized:
return None
path_obj = Path(normalized)
if path_obj.is_absolute():
return path_obj
if normalized.startswith(f"{DIR_WORKFLOW}/"):
return repo_root / path_obj
return repo_root / DIR_WORKFLOW / DIR_TASKS / path_obj
def _runtime_sessions_dir(repo_root: Path) -> Path:
return repo_root / DIR_WORKFLOW / DIR_RUNTIME / DIR_SESSIONS
def _sanitize_key(raw: str) -> str:
safe = re.sub(r"[^A-Za-z0-9._-]+", "_", raw.strip())
safe = safe.strip("._-")
return safe[:160] if safe else ""
def _hash_value(raw: str) -> str:
return hashlib.sha256(raw.encode("utf-8")).hexdigest()[:24]
def _as_dict(value: Any) -> dict[str, Any] | None:
return value if isinstance(value, dict) else None
def _string_value(value: Any) -> str | None:
if isinstance(value, str):
stripped = value.strip()
return stripped or None
return None
def _lookup_string(data: dict[str, Any], keys: tuple[str, ...]) -> str | None:
for key in keys:
value = _string_value(data.get(key))
if value:
return value
for nested_key in _NESTED_KEYS:
nested = _as_dict(data.get(nested_key))
if not nested:
continue
value = _lookup_string(nested, keys)
if value:
return value
return None
def _detect_platform(platform_input: dict[str, Any] | None, platform: str | None) -> str:
if platform:
return _sanitize_key(platform) or "session"
if platform_input:
for key in ("_trellis_platform", "trellis_platform", "platform", "source"):
value = _string_value(platform_input.get(key))
if value:
return _sanitize_key(value) or "session"
if _string_value(platform_input.get("cursor_version")):
return "cursor"
return "session"
def _context_key(platform_name: str, kind: str, value: str) -> str:
if kind == "transcript":
return f"{platform_name}_transcript_{_hash_value(value)}"
safe_value = _sanitize_key(value)
if safe_value:
return f"{platform_name}_{safe_value}"
return f"{platform_name}_{_hash_value(value)}"
def _iter_env_keys(
env_keys: tuple[tuple[str, tuple[str, ...]], ...],
platform_name: str | None,
) -> tuple[tuple[str, tuple[str, ...]], ...]:
if not platform_name:
return env_keys
matched = tuple((name, keys) for name, keys in env_keys if name == platform_name)
return matched
def _env_platform_name(platform_name: str | None) -> str | None:
if not platform_name or platform_name == "session":
return None
return _ENV_PLATFORM_ALIASES.get(platform_name, platform_name)
def _lookup_env_context_key(platform_name: str | None) -> str | None:
"""Resolve a context key from platform-provided environment variables.
Hooks pass `TRELLIS_CONTEXT_ID` to subprocesses they launch, but an AI-run
shell command can only see session identity if the host platform exports it
in the command environment. These names are best-effort adapters; if none
are present, there is no session-scoped active task.
"""
env_platform_name = _env_platform_name(platform_name)
for name, keys in _iter_env_keys(_ENV_SESSION_KEYS, env_platform_name):
for key in keys:
value = _string_value(os.environ.get(key))
if value:
return _context_key(name, "session", value)
for name, keys in _iter_env_keys(_ENV_CONVERSATION_KEYS, env_platform_name):
for key in keys:
value = _string_value(os.environ.get(key))
if value:
return _context_key(name, "conversation", value)
for name, keys in _iter_env_keys(_ENV_TRANSCRIPT_KEYS, env_platform_name):
for key in keys:
value = _string_value(os.environ.get(key))
if value:
return _context_key(name, "transcript", value)
return None
def _find_repo_root_from_cwd() -> Path | None:
current = Path.cwd().resolve()
while True:
if (current / DIR_WORKFLOW).is_dir():
return current
if current == current.parent:
return None
current = current.parent
def _cursor_shell_ticket_dir(repo_root: Path) -> Path:
return repo_root / DIR_WORKFLOW / DIR_RUNTIME / DIR_CURSOR_SHELL
def _remove_file(path: Path) -> bool:
try:
path.unlink()
return True
except OSError:
return False
def _task_refs_match(left: str | None, right: str | None, repo_root: Path) -> bool:
if not left or not right:
return False
left_path = resolve_task_ref(left, repo_root)
right_path = resolve_task_ref(right, repo_root)
if left_path is not None and right_path is not None:
return left_path == right_path
return normalize_task_ref(left) == normalize_task_ref(right)
def _pending_ticket_matches_args(ticket: dict[str, Any], repo_root: Path) -> bool:
if Path(sys.argv[0]).name != "task.py":
return False
args = tuple(sys.argv[1:])
if not args:
return False
command_name = args[0]
if command_name not in TASK_SESSION_COMMANDS:
return False
subcommands = ticket.get("subcommands")
if not isinstance(subcommands, list):
return False
for subcommand in subcommands:
if not isinstance(subcommand, dict):
continue
if _string_value(subcommand.get("name")) != command_name:
continue
if command_name != "start":
return True
task_ref = args[1] if len(args) > 1 else None
if _task_refs_match(_string_value(subcommand.get("task_ref")), task_ref, repo_root):
return True
return False
def _ticket_is_fresh(ticket: dict[str, Any], ticket_path: Path, now: float) -> bool:
expires_at = ticket.get("expires_at_epoch")
if isinstance(expires_at, (int, float)) and expires_at < now:
_remove_file(ticket_path)
return False
created_at = ticket.get("created_at_epoch")
if isinstance(created_at, (int, float)):
if now - created_at <= CURSOR_SHELL_TICKET_TTL_SECONDS:
return True
_remove_file(ticket_path)
return False
return True
def _ticket_cwd_matches_repo(ticket: dict[str, Any], repo_root: Path) -> bool:
cwd = _string_value(ticket.get("cwd"))
if not cwd:
return True
try:
Path(cwd).resolve().relative_to(repo_root)
except ValueError:
return False
return True
def _matching_cursor_ticket_context_key(
ticket_path: Path,
repo_root: Path,
now: float,
) -> str | None:
ticket = _read_json(ticket_path)
if ticket is None or ticket.get("platform") != "cursor":
return None
if not _ticket_is_fresh(ticket, ticket_path, now):
return None
if not _ticket_cwd_matches_repo(ticket, repo_root):
return None
if not _pending_ticket_matches_args(ticket, repo_root):
return None
return _string_value(ticket.get("context_key"))
def _lookup_cursor_shell_ticket_context_key() -> str | None:
"""Resolve Cursor conversation identity from a short-lived shell ticket.
Cursor exposes `conversation_id` to `beforeShellExecution`, but does not
export it into the shell command environment. The Cursor hook writes a
short-lived ticket just before `task.py` runs. We accept a ticket only when
the current `task.py` subcommand matches and exactly one fresh context key
matches, which avoids cross-window pointer contamination.
"""
repo_root = _find_repo_root_from_cwd()
if repo_root is None:
return None
ticket_dir = _cursor_shell_ticket_dir(repo_root)
if not ticket_dir.is_dir():
return None
now = time.time()
candidates: set[str] = set()
for ticket_path in ticket_dir.glob("*.json"):
context_key = _matching_cursor_ticket_context_key(ticket_path, repo_root, now)
if context_key:
candidates.add(context_key)
if len(candidates) == 1:
return next(iter(candidates))
return None
def resolve_context_key(
platform_input: dict[str, Any] | None = None,
platform: str | None = None,
) -> str | None:
"""Resolve a stable session/window context key, if one is available.
`TRELLIS_CONTEXT_ID` is an explicit context-key override used by CLI
scripts and subprocesses. It does not store the task itself.
"""
override = _string_value(os.environ.get("TRELLIS_CONTEXT_ID"))
if override:
return _sanitize_key(override) or _hash_value(override)
data = _as_dict(platform_input)
platform_name = _detect_platform(data, platform) if data or platform else None
if data:
session_id = _lookup_string(data, _SESSION_KEYS)
if session_id:
return _context_key(platform_name or "session", "session", session_id)
conversation_id = _lookup_string(data, _CONVERSATION_KEYS)
if conversation_id:
return _context_key(platform_name or "session", "conversation", conversation_id)
transcript_path = _lookup_string(data, _TRANSCRIPT_KEYS)
if transcript_path:
return _context_key(platform_name or "session", "transcript", transcript_path)
env_context_key = _lookup_env_context_key(platform_name)
if env_context_key:
return env_context_key
if platform_name in (None, "session", "cursor"):
return _lookup_cursor_shell_ticket_context_key()
return None
def _read_json(path: Path) -> dict[str, Any] | None:
try:
data = json.loads(path.read_text(encoding="utf-8"))
except (FileNotFoundError, json.JSONDecodeError, OSError):
return None
return data if isinstance(data, dict) else None
def _write_json(path: Path, data: dict[str, Any]) -> bool:
try:
path.parent.mkdir(parents=True, exist_ok=True)
path.write_text(
json.dumps(data, indent=2, ensure_ascii=False) + "\n",
encoding="utf-8",
)
return True
except OSError:
return False
def _canonical_task_ref(task_path: str, repo_root: Path) -> str | None:
normalized = normalize_task_ref(task_path)
if not normalized:
return None
full_path = resolve_task_ref(normalized, repo_root)
if full_path is None or not full_path.is_dir():
return None
try:
return full_path.relative_to(repo_root).as_posix()
except ValueError:
return str(full_path)
def _active_from_ref(
task_ref: str | None,
repo_root: Path,
source_type: str,
context_key: str | None = None,
) -> ActiveTask | None:
if not task_ref:
return None
resolved = resolve_task_ref(task_ref, repo_root)
stale = resolved is None or not resolved.is_dir()
return ActiveTask(task_ref, source_type, context_key, stale)
def _context_path(repo_root: Path, context_key: str) -> Path:
return _runtime_sessions_dir(repo_root) / f"{context_key}.json"
def resolve_active_task(
repo_root: Path,
platform_input: dict[str, Any] | None = None,
platform: str | None = None,
) -> ActiveTask:
"""Resolve the active task from session runtime state only.
A stale session task is returned as stale. Missing context identity or a
missing/empty session context falls back to single-session inference: if
exactly one session file exists in the runtime, return its task with
source_type="session-fallback" — covers class-2 platform sub-agents (codex,
copilot, gemini, qoder) that don't inherit the parent's session id. ≥2
files or 0 files yield ActiveTask(None) — refuses to guess across windows.
"""
context_key = resolve_context_key(platform_input, platform)
if context_key:
context = _read_json(_context_path(repo_root, context_key)) or {}
task_ref = _string_value(context.get("current_task"))
active = _active_from_ref(task_ref, repo_root, "session", context_key)
if active:
return active
fallback = _resolve_single_session_fallback(repo_root)
if fallback is not None:
return fallback
return ActiveTask(None, "none", context_key)
def _resolve_single_session_fallback(repo_root: Path) -> ActiveTask | None:
"""Return the task pointed at by the sole session file, if exactly one exists.
Used when context-key resolution fails (typical for class-2 platform
sub-agents). Returns None if 0 or ≥2 session files are present — refuses
to pick across windows so 04-21's multi-session isolation contract holds.
"""
sessions_dir = _runtime_sessions_dir(repo_root)
if not sessions_dir.is_dir():
return None
session_files = sorted(sessions_dir.glob("*.json"))
if len(session_files) != 1:
return None
session_file = session_files[0]
context = _read_json(session_file) or {}
task_ref = _string_value(context.get("current_task"))
if not task_ref:
return None
fallback_key = session_file.stem
return _active_from_ref(task_ref, repo_root, "session-fallback", fallback_key)
def _utc_now() -> str:
return datetime.now(timezone.utc).replace(microsecond=0).isoformat().replace("+00:00", "Z")
def _context_metadata(
platform_input: dict[str, Any] | None,
platform: str | None,
context_key: str | None = None,
) -> dict[str, Any]:
data = _as_dict(platform_input) or {}
platform_name = _detect_platform(data, platform)
if platform_name == "session" and context_key:
prefix = context_key.split("_", 1)[0]
if prefix in _KNOWN_PLATFORMS:
platform_name = prefix
metadata: dict[str, Any] = {
"platform": platform_name,
"last_seen_at": _utc_now(),
}
for key in (*_SESSION_KEYS, *_CONVERSATION_KEYS, *_TRANSCRIPT_KEYS):
value = _lookup_string(data, (key,))
if value:
metadata[key] = value
return metadata
def set_active_task(
task_path: str,
repo_root: Path,
platform_input: dict[str, Any] | None = None,
platform: str | None = None,
) -> ActiveTask | None:
"""Set the active task in session scope.
Returns None when no context key is available; callers should surface a
user-facing error that explains how to provide session identity.
"""
canonical = _canonical_task_ref(task_path, repo_root)
if canonical is None:
return None
context_key = resolve_context_key(platform_input, platform)
if not context_key:
return None
context_path = _context_path(repo_root, context_key)
context = _read_json(context_path) or {}
context.update(_context_metadata(platform_input, platform, context_key))
context["current_task"] = canonical
context.setdefault("current_run", None)
if not _write_json(context_path, context):
return None
return ActiveTask(canonical, "session", context_key)
def clear_active_task(
repo_root: Path,
platform_input: dict[str, Any] | None = None,
platform: str | None = None,
) -> ActiveTask:
"""Clear the active task by deleting the current session context file."""
context_key = resolve_context_key(platform_input, platform)
if not context_key:
return ActiveTask(None, "none")
previous = resolve_active_task(repo_root, platform_input, platform)
context_path = _context_path(repo_root, context_key)
if context_path.is_file():
_remove_file(context_path)
return previous
def clear_task_from_sessions(task_path: str, repo_root: Path) -> int:
"""Delete all session runtime files that point at a task."""
target = _canonical_task_ref(task_path, repo_root) or normalize_task_ref(task_path)
if not target:
return 0
cleared = 0
sessions_dir = _runtime_sessions_dir(repo_root)
if not sessions_dir.is_dir():
return cleared
for session_path in sessions_dir.glob("*.json"):
context = _read_json(session_path) or {}
current = _string_value(context.get("current_task"))
if not current:
continue
current_ref = _canonical_task_ref(current, repo_root) or normalize_task_ref(current)
if current_ref != target:
continue
if session_path.is_file() and _remove_file(session_path):
cleared += 1
return cleared
def get_current_task_source(
repo_root: Path,
platform_input: dict[str, Any] | None = None,
platform: str | None = None,
) -> tuple[str, str | None, str | None]:
"""Return (`source_type`, `context_key`, `task_path`) for compatibility."""
active = resolve_active_task(repo_root, platform_input, platform)
return active.source_type, active.context_key, active.task_path
.trellis/scripts/common/cli_adapter.py
Executable
+825
View File
@@ -0,0 +1,825 @@
"""
CLI Adapter for Multi-Platform Support.
Abstracts differences between Claude Code, OpenCode, Cursor, iFlow, Codex, Kilo, Kiro Code, Gemini CLI, Antigravity, Devin, Qoder, CodeBuddy, GitHub Copilot, Factory Droid, and Pi Agent interfaces.
Supported platforms:
- claude: Claude Code (default)
- opencode: OpenCode
- cursor: Cursor IDE
- iflow: iFlow CLI
- codex: Codex CLI (skills-based)
- kilo: Kilo CLI
- kiro: Kiro Code (skills-based)
- gemini: Gemini CLI
- antigravity: Antigravity (workflow-based)
- devin: Devin (formerly Windsurf; workflow-based)
- qoder: Qoder
- codebuddy: CodeBuddy
- copilot: GitHub Copilot (VS Code)
- droid: Factory Droid (commands-based)
- pi: Pi Agent (extension-backed)
Usage:
from common.cli_adapter import CLIAdapter
adapter = CLIAdapter("opencode")
cmd = adapter.build_run_command(
agent="dispatch",
session_id="abc123",
prompt="Start the pipeline"
)
"""
from __future__ import annotations
from dataclasses import dataclass
from pathlib import Path
from typing import ClassVar, Literal
Platform = Literal[
"claude",
"opencode",
"cursor",
"iflow",
"codex",
"kilo",
"kiro",
"gemini",
"antigravity",
"devin",
"qoder",
"codebuddy",
"copilot",
"droid",
"pi",
]
@dataclass
class CLIAdapter:
"""Adapter for different AI coding CLI tools."""
platform: Platform
# =========================================================================
# Agent Name Mapping
# =========================================================================
# OpenCode has built-in agents that cannot be overridden
# See: https://github.com/sst/opencode/issues/4271
# Note: Class-level constant, not a dataclass field
_AGENT_NAME_MAP: ClassVar[dict[Platform, dict[str, str]]] = {
"claude": {}, # No mapping needed
"opencode": {
"plan": "trellis-plan", # 'plan' is built-in in OpenCode
},
}
def get_agent_name(self, agent: str) -> str:
"""Get platform-specific agent name.
Args:
agent: Original agent name (e.g., 'plan', 'dispatch')
Returns:
Platform-specific agent name (e.g., 'trellis-plan' for OpenCode)
"""
mapping = self._AGENT_NAME_MAP.get(self.platform, {})
return mapping.get(agent, agent)
# =========================================================================
# Agent Path
# =========================================================================
@property
def config_dir_name(self) -> str:
"""Get platform-specific config directory name.
Returns:
Directory name ('.claude', '.opencode', '.cursor', '.iflow', '.codex', '.kilocode', '.kiro', '.gemini', '.agent', '.devin', '.qoder', '.codebuddy', '.github/copilot', '.factory', or '.pi')
"""
if self.platform == "opencode":
return ".opencode"
elif self.platform == "cursor":
return ".cursor"
elif self.platform == "iflow":
return ".iflow"
elif self.platform == "codex":
return ".codex"
elif self.platform == "kilo":
return ".kilocode"
elif self.platform == "kiro":
return ".kiro"
elif self.platform == "gemini":
return ".gemini"
elif self.platform == "antigravity":
return ".agent"
elif self.platform == "devin":
return ".devin"
elif self.platform == "qoder":
return ".qoder"
elif self.platform == "codebuddy":
return ".codebuddy"
elif self.platform == "copilot":
return ".github/copilot"
elif self.platform == "droid":
return ".factory"
elif self.platform == "pi":
return ".pi"
else:
return ".claude"
def get_config_dir(self, project_root: Path) -> Path:
"""Get platform-specific config directory.
Args:
project_root: Project root directory
Returns:
Path to config directory (.claude, .opencode, .cursor, .iflow, .codex, .kilocode, .kiro, .gemini, .agent, .devin, .qoder, .codebuddy, .github/copilot, .factory, or .pi)
"""
return project_root / self.config_dir_name
def get_agent_path(self, agent: str, project_root: Path) -> Path:
"""Get path to agent definition file.
Args:
agent: Agent name (original, before mapping)
project_root: Project root directory
Returns:
Path to agent definition file (.md for most platforms, .toml for Codex)
"""
mapped_name = self.get_agent_name(agent)
if self.platform == "codex":
return self.get_config_dir(project_root) / "agents" / f"{mapped_name}.toml"
return self.get_config_dir(project_root) / "agents" / f"{mapped_name}.md"
def get_commands_path(self, project_root: Path, *parts: str) -> Path:
"""Get path to commands directory or specific command file.
Args:
project_root: Project root directory
*parts: Additional path parts (e.g., 'trellis', 'finish-work.md')
Returns:
Path to commands directory or file
Note:
Cursor uses prefix naming: .cursor/commands/trellis-<name>.md
Antigravity uses workflow directory: .agent/workflows/<name>.md
Devin uses workflow directory: .devin/workflows/trellis-<name>.md
Copilot uses prompt files: .github/prompts/<name>.prompt.md
Pi uses prompt templates: .pi/prompts/trellis-<name>.md
Claude/OpenCode use subdirectory: .claude/commands/trellis/<name>.md
"""
if self.platform == "pi":
prompts_dir = self.get_config_dir(project_root) / "prompts"
if not parts:
return prompts_dir
if len(parts) >= 2 and parts[0] == "trellis":
filename = parts[-1]
if filename.endswith(".md"):
filename = filename[:-3]
return prompts_dir / f"trellis-{filename}.md"
return prompts_dir / Path(*parts)
if self.platform == "devin":
workflow_dir = self.get_config_dir(project_root) / "workflows"
if not parts:
return workflow_dir
if len(parts) >= 2 and parts[0] == "trellis":
filename = parts[-1]
return workflow_dir / f"trellis-{filename}"
return workflow_dir / Path(*parts)
if self.platform in ("antigravity", "kilo"):
workflow_dir = self.get_config_dir(project_root) / "workflows"
if not parts:
return workflow_dir
if len(parts) >= 2 and parts[0] == "trellis":
filename = parts[-1]
return workflow_dir / filename
return workflow_dir / Path(*parts)
if self.platform == "copilot":
prompts_dir = project_root / ".github" / "prompts"
if not parts:
return prompts_dir
if len(parts) >= 2 and parts[0] == "trellis":
filename = parts[-1]
if filename.endswith(".md"):
filename = filename[:-3]
return prompts_dir / f"{filename}.prompt.md"
return prompts_dir / Path(*parts)
if not parts:
return self.get_config_dir(project_root) / "commands"
# Cursor uses prefix naming instead of subdirectory
if self.platform == "cursor" and len(parts) >= 2 and parts[0] == "trellis":
# Convert trellis/<name>.md to trellis-<name>.md
filename = parts[-1]
return (
self.get_config_dir(project_root) / "commands" / f"trellis-{filename}"
)
return self.get_config_dir(project_root) / "commands" / Path(*parts)
def get_trellis_command_path(self, name: str) -> str:
"""Get relative path to a trellis command file.
Args:
name: Command name without extension (e.g., 'finish-work', 'check')
Returns:
Relative path string for use in JSONL entries
Note:
Cursor: .cursor/commands/trellis-<name>.md
Codex: .agents/skills/trellis-<name>/SKILL.md
Kiro: .kiro/skills/trellis-<name>/SKILL.md
Gemini: .gemini/commands/trellis/<name>.toml
Antigravity: .agent/workflows/<name>.md
Devin: .devin/workflows/trellis-<name>.md
Pi: .pi/prompts/trellis-<name>.md
Others: .{platform}/commands/trellis/<name>.md
"""
if self.platform == "cursor":
return f".cursor/commands/trellis-{name}.md"
elif self.platform == "codex":
# 0.5.0-beta.0 renamed all skill dirs to add the `trellis-` prefix
# (see that release's manifest for the 60+ rename entries).
return f".agents/skills/trellis-{name}/SKILL.md"
elif self.platform == "kiro":
return f".kiro/skills/trellis-{name}/SKILL.md"
elif self.platform == "gemini":
return f".gemini/commands/trellis/{name}.toml"
elif self.platform == "antigravity":
return f".agent/workflows/{name}.md"
elif self.platform == "devin":
return f".devin/workflows/trellis-{name}.md"
elif self.platform == "kilo":
return f".kilocode/workflows/{name}.md"
elif self.platform == "copilot":
return f".github/prompts/{name}.prompt.md"
elif self.platform == "droid":
return f".factory/commands/trellis/{name}.md"
elif self.platform == "pi":
return f".pi/prompts/trellis-{name}.md"
else:
return f"{self.config_dir_name}/commands/trellis/{name}.md"
# =========================================================================
# Environment Variables
# =========================================================================
def get_non_interactive_env(self) -> dict[str, str]:
"""Get environment variables for non-interactive mode.
Returns:
Dict of environment variables to set
"""
if self.platform == "opencode":
return {"OPENCODE_NON_INTERACTIVE": "1"}
elif self.platform == "iflow":
return {"IFLOW_NON_INTERACTIVE": "1"}
elif self.platform == "codex":
return {"CODEX_NON_INTERACTIVE": "1"}
elif self.platform == "kiro":
return {"KIRO_NON_INTERACTIVE": "1"}
elif self.platform == "gemini":
return {} # Gemini CLI doesn't have a non-interactive env var
elif self.platform == "antigravity":
return {}
elif self.platform == "devin":
return {}
elif self.platform == "qoder":
return {}
elif self.platform == "codebuddy":
return {}
elif self.platform == "copilot":
return {}
elif self.platform == "droid":
return {}
elif self.platform == "pi":
return {}
else:
return {"CLAUDE_NON_INTERACTIVE": "1"}
# =========================================================================
# CLI Command Building
# =========================================================================
def build_run_command(
self,
agent: str,
prompt: str,
session_id: str | None = None,
skip_permissions: bool = True,
verbose: bool = True,
json_output: bool = True,
) -> list[str]:
"""Build CLI command for running an agent.
Args:
agent: Agent name (will be mapped if needed)
prompt: Prompt to send to the agent
session_id: Optional session ID (Claude Code only for creation)
skip_permissions: Whether to skip permission prompts
verbose: Whether to enable verbose output
json_output: Whether to use JSON output format
Returns:
List of command arguments
"""
mapped_agent = self.get_agent_name(agent)
if self.platform == "opencode":
cmd = ["opencode", "run"]
cmd.extend(["--agent", mapped_agent])
# Note: OpenCode 'run' mode is non-interactive by default
# No equivalent to Claude Code's --dangerously-skip-permissions
# See: https://github.com/anomalyco/opencode/issues/9070
if json_output:
cmd.extend(["--format", "json"])
if verbose:
cmd.extend(["--log-level", "DEBUG", "--print-logs"])
# Note: OpenCode doesn't support --session-id on creation
# Session ID must be extracted from logs after startup
cmd.append(prompt)
elif self.platform == "iflow":
cmd = ["iflow", "-y", "-p"]
cmd.append(f"${mapped_agent} {prompt}")
elif self.platform == "codex":
cmd = ["codex", "exec"]
cmd.append(prompt)
elif self.platform == "kiro":
cmd = ["kiro", "run", prompt]
elif self.platform == "gemini":
cmd = ["gemini"]
cmd.append(prompt)
elif self.platform == "antigravity":
raise ValueError(
"Antigravity workflows are UI slash commands; CLI agent run is not supported."
)
elif self.platform == "devin":
raise ValueError(
"Devin workflows are UI slash commands; CLI agent run is not supported."
)
elif self.platform == "qoder":
cmd = ["qodercli", "-p", prompt]
elif self.platform == "codebuddy":
raise ValueError(
"CodeBuddy does not support non-interactive mode (no CLI agent)"
)
elif self.platform == "copilot":
raise ValueError(
"GitHub Copilot is IDE-only; CLI agent run is not supported."
)
elif self.platform == "droid":
raise ValueError(
"Factory Droid CLI agent run is not yet supported."
)
elif self.platform == "pi":
cmd = ["pi", "-p", prompt]
else: # claude
cmd = ["claude", "-p"]
cmd.extend(["--agent", mapped_agent])
if session_id:
cmd.extend(["--session-id", session_id])
if skip_permissions:
cmd.append("--dangerously-skip-permissions")
if json_output:
cmd.extend(["--output-format", "stream-json"])
if verbose:
cmd.append("--verbose")
cmd.append(prompt)
return cmd
def build_resume_command(self, session_id: str) -> list[str]:
"""Build CLI command for resuming a session.
Args:
session_id: Session ID to resume (ignored for iFlow)
Returns:
List of command arguments
"""
if self.platform == "opencode":
return ["opencode", "run", "--session", session_id]
elif self.platform == "iflow":
# iFlow uses -c to continue most recent conversation
# session_id is ignored as iFlow doesn't support session IDs
return ["iflow", "-c"]
elif self.platform == "codex":
return ["codex", "resume", session_id]
elif self.platform == "kiro":
return ["kiro", "resume", session_id]
elif self.platform == "gemini":
return ["gemini", "--resume", session_id]
elif self.platform == "antigravity":
raise ValueError(
"Antigravity workflows are UI slash commands; CLI resume is not supported."
)
elif self.platform == "devin":
raise ValueError(
"Devin workflows are UI slash commands; CLI resume is not supported."
)
elif self.platform == "qoder":
return ["qodercli", "--resume", session_id]
elif self.platform == "codebuddy":
raise ValueError(
"CodeBuddy does not support non-interactive mode (no CLI agent)"
)
elif self.platform == "copilot":
raise ValueError(
"GitHub Copilot is IDE-only; CLI resume is not supported."
)
elif self.platform == "droid":
raise ValueError(
"Factory Droid CLI resume is not yet supported."
)
elif self.platform == "pi":
return ["pi", "-c", session_id]
else:
return ["claude", "--resume", session_id]
def get_resume_command_str(self, session_id: str, cwd: str | None = None) -> str:
"""Get human-readable resume command string.
Args:
session_id: Session ID to resume
cwd: Optional working directory to cd into
Returns:
Command string for display
"""
cmd = self.build_resume_command(session_id)
cmd_str = " ".join(cmd)
if cwd:
return f"cd {cwd} && {cmd_str}"
return cmd_str
# =========================================================================
# Platform Detection Helpers
# =========================================================================
@property
def is_opencode(self) -> bool:
"""Check if platform is OpenCode."""
return self.platform == "opencode"
@property
def is_claude(self) -> bool:
"""Check if platform is Claude Code."""
return self.platform == "claude"
@property
def is_cursor(self) -> bool:
"""Check if platform is Cursor."""
return self.platform == "cursor"
@property
def is_iflow(self) -> bool:
"""Check if platform is iFlow CLI."""
return self.platform == "iflow"
@property
def cli_name(self) -> str:
"""Get CLI executable name.
Note: Cursor doesn't have a CLI tool, returns None-like value.
"""
if self.is_opencode:
return "opencode"
elif self.is_cursor:
return "cursor" # Note: Cursor is IDE-only, no CLI
elif self.platform == "iflow":
return "iflow"
elif self.platform == "kiro":
return "kiro"
elif self.platform == "gemini":
return "gemini"
elif self.platform == "antigravity":
return "agy"
elif self.platform == "devin":
return "devin"
elif self.platform == "qoder":
return "qodercli"
elif self.platform == "codebuddy":
return "codebuddy"
elif self.platform == "copilot":
return "copilot"
elif self.platform == "droid":
return "droid"
elif self.platform == "pi":
return "pi"
else:
return "claude"
@property
def supports_cli_agents(self) -> bool:
"""Check if platform supports running agents via CLI.
Claude Code, OpenCode, iFlow, and Codex support CLI agent execution.
Cursor is IDE-only and doesn't support CLI agents.
"""
return self.platform in ("claude", "opencode", "iflow", "codex", "pi")
@property
def requires_agent_definition_file(self) -> bool:
"""Check if platform requires an agent definition file (.md/.toml) to run.
Claude Code, OpenCode, iFlow: require agent .md files (--agent flag).
Codex: auto-discovers agents from .codex/agents/*.toml, no --agent flag.
"""
return self.platform in ("claude", "opencode", "iflow")
# =========================================================================
# Session ID Handling
# =========================================================================
@property
def supports_session_id_on_create(self) -> bool:
"""Check if platform supports specifying session ID on creation.
Claude Code: Yes (--session-id)
OpenCode: No (auto-generated, extract from logs)
iFlow: No (no session ID support)
"""
return self.platform == "claude"
def extract_session_id_from_log(self, log_content: str) -> str | None:
"""Extract session ID from log output (OpenCode only).
OpenCode generates session IDs in format: ses_xxx
Args:
log_content: Log file content
Returns:
Session ID if found, None otherwise
"""
import re
# OpenCode session ID pattern
match = re.search(r"ses_[a-zA-Z0-9]+", log_content)
if match:
return match.group(0)
return None
# =============================================================================
# Factory Function
# =============================================================================
def get_cli_adapter(platform: str = "claude") -> CLIAdapter:
"""Get CLI adapter for the specified platform.
Args:
platform: Platform name ('claude', 'opencode', 'cursor', 'iflow', 'codex', 'kilo', 'kiro', 'gemini', 'antigravity', 'devin', 'qoder', 'codebuddy', 'copilot', 'droid', or 'pi')
Returns:
CLIAdapter instance
Raises:
ValueError: If platform is not supported
Note:
'windsurf' is accepted as a deprecated alias for 'devin' (Windsurf was
renamed to Devin) and normalized before validation.
"""
# Deprecated alias: Windsurf was renamed to Devin.
if platform == "windsurf":
platform = "devin"
if platform not in (
"claude",
"opencode",
"cursor",
"iflow",
"codex",
"kilo",
"kiro",
"gemini",
"antigravity",
"devin",
"qoder",
"codebuddy",
"copilot",
"droid",
"pi",
):
raise ValueError(
f"Unsupported platform: {platform} (must be 'claude', 'opencode', 'cursor', 'iflow', 'codex', 'kilo', 'kiro', 'gemini', 'antigravity', 'devin', 'qoder', 'codebuddy', 'copilot', 'droid', or 'pi')"
)
return CLIAdapter(platform=platform) # type: ignore
_ALL_PLATFORM_CONFIG_DIRS = (
".claude",
".cursor",
".iflow",
".opencode",
".codex",
".kilocode",
".kiro",
".gemini",
".agent",
".devin",
".windsurf", # deprecated: pre-rename Devin config dir (still a platform signal)
".qoder",
".codebuddy",
".github/copilot",
".factory",
".pi",
)
"""Platform-specific config directory names used by detect_platform exclusion
checks. `.agents/skills/` is NOT listed here: it is a shared cross-platform
layer (written by Codex, also consumed by Amp/Cline/Warp/etc. via the
agentskills.io standard), not a single-platform signal. Its presence must not
block detection of Kiro, Antigravity, Devin, or other platforms."""
def _has_other_platform_dir(project_root: Path, exclude: set[str]) -> bool:
"""Check if any platform config dir exists besides those in *exclude*."""
return any(
(project_root / d).is_dir()
for d in _ALL_PLATFORM_CONFIG_DIRS
if d not in exclude
)
def detect_platform(project_root: Path) -> Platform:
"""Auto-detect platform based on existing config directories.
Detection order:
1. TRELLIS_PLATFORM environment variable (if set)
2. .opencode directory exists → opencode
3. .iflow directory exists → iflow
4. .cursor directory exists (without .claude) → cursor
5. .codex exists and no other platform dirs → codex
6. .kilocode directory exists → kilo
7. .kiro/skills exists and no other platform dirs → kiro
8. .gemini directory exists → gemini
9. .agent/workflows exists and no other platform dirs → antigravity
10. .devin/workflows (or legacy .windsurf/workflows) exists and no other platform dirs → devin
11. .codebuddy directory exists → codebuddy
12. .qoder directory exists → qoder
13. .pi directory exists → pi
14. Default → claude
Args:
project_root: Project root directory
Returns:
Detected platform ('claude', 'opencode', 'cursor', 'iflow', 'codex', 'kilo', 'kiro', 'gemini', 'antigravity', 'devin', 'qoder', 'codebuddy', 'copilot', 'droid', 'pi', or default 'claude')
"""
import os
# Check environment variable first
env_platform = os.environ.get("TRELLIS_PLATFORM", "").lower()
# Deprecated alias: Windsurf was renamed to Devin.
if env_platform == "windsurf":
env_platform = "devin"
if env_platform in (
"claude",
"opencode",
"cursor",
"iflow",
"codex",
"kilo",
"kiro",
"gemini",
"antigravity",
"devin",
"qoder",
"codebuddy",
"copilot",
"droid",
"pi",
):
return env_platform # type: ignore
# Check for .opencode directory (OpenCode-specific)
if (project_root / ".opencode").is_dir():
return "opencode"
# Check for .iflow directory (iFlow-specific)
if (project_root / ".iflow").is_dir():
return "iflow"
# Check for .cursor directory (Cursor-specific)
# Only detect as cursor if .claude doesn't exist (to avoid confusion)
if (project_root / ".cursor").is_dir() and not (project_root / ".claude").is_dir():
return "cursor"
# Check for .gemini directory (Gemini CLI-specific)
if (project_root / ".gemini").is_dir():
return "gemini"
# Check for .codex directory (Codex-specific)
# .agents/skills/ alone does NOT trigger codex detection (it's a shared standard)
if (project_root / ".codex").is_dir() and not _has_other_platform_dir(
project_root, {".codex", ".agents"}
):
return "codex"
# Check for .kilocode directory (Kilo-specific)
if (project_root / ".kilocode").is_dir():
return "kilo"
# Check for Kiro skills directory only when no other platform config exists
if (project_root / ".kiro" / "skills").is_dir() and not _has_other_platform_dir(
project_root, {".kiro"}
):
return "kiro"
# Check for Antigravity workflow directory only when no other platform config exists
if (
project_root / ".agent" / "workflows"
).is_dir() and not _has_other_platform_dir(
project_root, {".agent", ".gemini"}
):
return "antigravity"
# Check for Devin workflow directory only when no other platform config
# exists. `.windsurf/workflows` is the legacy pre-rename path (still detected
# as devin for back-compat until users migrate via `trellis update --migrate`).
if (
(project_root / ".devin" / "workflows").is_dir()
or (project_root / ".windsurf" / "workflows").is_dir()
) and not _has_other_platform_dir(
project_root, {".devin", ".windsurf"}
):
return "devin"
# Check for .codebuddy directory (CodeBuddy-specific)
if (project_root / ".codebuddy").is_dir():
return "codebuddy"
# Check for .qoder directory (Qoder-specific)
if (project_root / ".qoder").is_dir():
return "qoder"
# Check for .github/copilot directory (GitHub Copilot-specific)
if (project_root / ".github" / "copilot").is_dir():
return "copilot"
# Check for .factory directory (Factory Droid-specific)
if (project_root / ".factory").is_dir():
return "droid"
# Check for .pi directory (Pi Agent-specific)
if (project_root / ".pi").is_dir():
return "pi"
# Fallback: checkout only has the Codex shared-skills layer
# (.agents/skills/trellis-* dirs) and no explicit platform config dir.
# Happens on fresh clones where .codex/ is gitignored/absent but the
# shared skills were committed to git. Must guard against the case
# where .claude/ or any other platform dir also exists — .agents/skills/
# can legitimately coexist with any platform as a shared consumption
# layer for Amp/Cline/Warp/etc.
agents_skills = project_root / ".agents" / "skills"
if agents_skills.is_dir() and not _has_other_platform_dir(
project_root, set()
):
try:
for entry in agents_skills.iterdir():
if entry.is_dir() and entry.name.startswith("trellis-"):
return "codex"
except OSError:
pass
return "claude"
def get_cli_adapter_auto(project_root: Path) -> CLIAdapter:
"""Get CLI adapter with auto-detected platform.
Args:
project_root: Project root directory
Returns:
CLIAdapter instance for detected platform
"""
platform = detect_platform(project_root)
return CLIAdapter(platform=platform)
.trellis/scripts/common/config.py
Executable
+445
View File
@@ -0,0 +1,445 @@
#!/usr/bin/env python3
"""
Trellis configuration reader.
Reads settings from .trellis/config.yaml with sensible defaults.
"""
from __future__ import annotations
import sys
from pathlib import Path
from .paths import DIR_WORKFLOW, get_repo_root
# =============================================================================
# YAML Simple Parser (no dependencies)
# =============================================================================
def _unquote(s: str) -> str:
"""Remove exactly one layer of matching surrounding quotes.
Unlike str.strip('"'), this only removes the outermost pair,
preserving any nested quotes inside the value.
Examples:
_unquote('"hello"') -> 'hello'
_unquote("'hello'") -> 'hello'
_unquote('"echo \\'hi\\'"') -> "echo 'hi'"
_unquote('hello') -> 'hello'
_unquote('"hello\\'') -> '"hello\\'' (mismatched, unchanged)
"""
if len(s) >= 2 and s[0] == s[-1] and s[0] in ('"', "'"):
return s[1:-1]
return s
def _strip_inline_comment(value: str) -> str:
"""Strip ` # …` inline comments while preserving `#` inside quoted strings.
YAML treats ` #` (space-hash) as a comment opener; bare `#` inside a token
is part of the value. Quoted strings are immune.
Mirrors :func:`common.trellis_config._strip_inline_comment` so both
parsers handle ``key: value # comment`` identically.
"""
in_quote: str | None = None
for idx, ch in enumerate(value):
if in_quote:
if ch == in_quote:
in_quote = None
continue
if ch in ('"', "'"):
in_quote = ch
continue
if ch == "#" and (idx == 0 or value[idx - 1].isspace()):
return value[:idx]
return value
def parse_simple_yaml(content: str) -> dict:
"""Parse simple YAML with nested dict support (no dependencies).
Supports:
- key: value (string)
- key: (followed by list items)
- item1
- item2
- key: (followed by nested dict)
nested_key: value
nested_key2:
- item
Uses indentation to detect nesting (2+ spaces deeper = child).
Args:
content: YAML content string.
Returns:
Parsed dict (values can be str, list[str], or dict).
"""
lines = content.splitlines()
result: dict = {}
_parse_yaml_block(lines, 0, 0, result)
return result
def _parse_yaml_block(
lines: list[str], start: int, min_indent: int, target: dict
) -> int:
"""Parse a YAML block into target dict, returning next line index."""
i = start
current_list: list | None = None
while i < len(lines):
line = lines[i]
stripped = line.strip()
# Skip empty lines and comments
if not stripped or stripped.startswith("#"):
i += 1
continue
# Calculate indentation
indent = len(line) - len(line.lstrip())
# If dedented past our block, we're done
if indent < min_indent:
break
if stripped.startswith("- "):
if current_list is not None:
current_list.append(_unquote(stripped[2:].strip()))
i += 1
elif ":" in stripped:
key, _, value = stripped.partition(":")
key = key.strip()
value = _strip_inline_comment(value).strip()
value = _unquote(value)
current_list = None
if value:
# key: value
target[key] = value
i += 1
else:
# key: (no value) — peek ahead to determine list vs nested dict
next_i, next_line = _next_content_line(lines, i + 1)
if next_i >= len(lines):
target[key] = {}
i = next_i
elif next_line.strip().startswith("- "):
# It's a list
current_list = []
target[key] = current_list
i += 1
else:
next_indent = len(next_line) - len(next_line.lstrip())
if next_indent > indent:
# It's a nested dict
nested: dict = {}
target[key] = nested
i = _parse_yaml_block(lines, i + 1, next_indent, nested)
else:
# Empty value, same or less indent follows
target[key] = {}
i += 1
else:
i += 1
return i
def _next_content_line(lines: list[str], start: int) -> tuple[int, str]:
"""Find the next non-empty, non-comment line."""
i = start
while i < len(lines):
stripped = lines[i].strip()
if stripped and not stripped.startswith("#"):
return i, lines[i]
i += 1
return i, ""
# Defaults
DEFAULT_SESSION_COMMIT_MESSAGE = "chore: record journal"
DEFAULT_MAX_JOURNAL_LINES = 2000
DEFAULT_SESSION_AUTO_COMMIT = True
CONFIG_FILE = "config.yaml"
def _is_true_config_value(value: object) -> bool:
"""Return True when a config value represents an enabled flag."""
if isinstance(value, bool):
return value
if isinstance(value, str):
return value.strip().lower() == "true"
return False
def _get_config_path(repo_root: Path | None = None) -> Path:
"""Get path to config.yaml."""
root = repo_root or get_repo_root()
return root / DIR_WORKFLOW / CONFIG_FILE
def _load_config(repo_root: Path | None = None) -> dict:
"""Load and parse config.yaml. Returns empty dict on any error."""
config_file = _get_config_path(repo_root)
try:
content = config_file.read_text(encoding="utf-8")
return parse_simple_yaml(content)
except (OSError, IOError):
return {}
def get_session_commit_message(repo_root: Path | None = None) -> str:
"""Get the commit message for auto-committing session records."""
config = _load_config(repo_root)
return config.get("session_commit_message", DEFAULT_SESSION_COMMIT_MESSAGE)
def get_max_journal_lines(repo_root: Path | None = None) -> int:
"""Get the maximum lines per journal file."""
config = _load_config(repo_root)
value = config.get("max_journal_lines", DEFAULT_MAX_JOURNAL_LINES)
try:
return int(value)
except (ValueError, TypeError):
return DEFAULT_MAX_JOURNAL_LINES
def get_session_auto_commit(repo_root: Path | None = None) -> bool:
"""Whether scripts should auto-stage + auto-commit session/task changes.
Governs both ``add_session.py:_auto_commit_workspace`` and
``task_store.py:_auto_commit_archive``.
Default: ``True`` (existing behavior — auto-stage + auto-commit).
Set ``session_auto_commit: false`` in ``.trellis/config.yaml`` to skip
auto-staging entirely; the journal/archive files are still written to
disk, but the user manages ``git add`` / ``git commit`` themselves.
Accepts native YAML booleans (``true`` / ``false``) and the string
aliases ``true / false / yes / no / 1 / 0 / on / off`` (case-insensitive).
Invalid values fall back to ``True`` with a stderr warning.
"""
config = _load_config(repo_root)
raw = config.get("session_auto_commit", DEFAULT_SESSION_AUTO_COMMIT)
if isinstance(raw, bool):
return raw
s = str(raw).strip().lower()
if s in ("true", "yes", "1", "on"):
return True
if s in ("false", "no", "0", "off"):
return False
print(
f"[WARN] invalid session_auto_commit value: {raw!r}; using true (default)",
file=sys.stderr,
)
return DEFAULT_SESSION_AUTO_COMMIT
def get_hooks(event: str, repo_root: Path | None = None) -> list[str]:
"""Get hook commands for a lifecycle event.
Args:
event: Event name (e.g. "after_create", "after_archive").
repo_root: Repository root path.
Returns:
List of shell commands to execute, empty if none configured.
"""
config = _load_config(repo_root)
hooks = config.get("hooks")
if not isinstance(hooks, dict):
return []
commands = hooks.get(event)
if isinstance(commands, list):
return [str(c) for c in commands]
return []
# =============================================================================
# Monorepo / Packages
# =============================================================================
def get_packages(repo_root: Path | None = None) -> dict[str, dict] | None:
"""Get monorepo package declarations.
Returns:
Dict mapping package name to its config (path, type, etc.),
or None if not configured (single-repo mode).
Example return:
{"cli": {"path": "packages/cli"}, "docs-site": {"path": "docs-site", "type": "submodule"}}
"""
config = _load_config(repo_root)
packages = config.get("packages")
if not isinstance(packages, dict):
return None
# Ensure each value is a dict (filter out scalar entries)
filtered = {k: v for k, v in packages.items() if isinstance(v, dict)}
if not filtered:
return None
return filtered
def get_default_package(repo_root: Path | None = None) -> str | None:
"""Get the default package name from config.
Returns:
Package name string, or None if not configured.
"""
config = _load_config(repo_root)
value = config.get("default_package")
return str(value) if value else None
def get_submodule_packages(repo_root: Path | None = None) -> dict[str, str]:
"""Get packages that are git submodules.
Returns:
Dict mapping package name to its path for submodule-type packages.
Empty dict if none configured.
Example return:
{"docs-site": "docs-site"}
"""
packages = get_packages(repo_root)
if packages is None:
return {}
return {
name: cfg.get("path", name)
for name, cfg in packages.items()
if cfg.get("type") == "submodule"
}
def get_git_packages(repo_root: Path | None = None) -> dict[str, str]:
"""Get packages that have their own independent git repository.
These are sub-directories with their own .git (not submodules),
marked with ``git: true`` in config.yaml.
Returns:
Dict mapping package name to its path for git-repo packages.
Empty dict if none configured.
Example config::
packages:
backend:
path: iqs
git: true
Example return::
{"backend": "iqs"}
"""
packages = get_packages(repo_root)
if packages is None:
return {}
return {
name: cfg.get("path", name)
for name, cfg in packages.items()
if _is_true_config_value(cfg.get("git"))
}
def is_monorepo(repo_root: Path | None = None) -> bool:
"""Check if the project is configured as a monorepo (has packages in config)."""
return get_packages(repo_root) is not None
def get_spec_base(package: str | None = None, repo_root: Path | None = None) -> str:
"""Get the spec directory base path relative to .trellis/.
Single-repo: returns "spec"
Monorepo with package: returns "spec/<package>"
Monorepo without package: returns "spec" (caller should specify package)
"""
if package and is_monorepo(repo_root):
return f"spec/{package}"
return "spec"
def validate_package(package: str, repo_root: Path | None = None) -> bool:
"""Check if a package name is valid in this project.
Single-repo (no packages configured): always returns True.
Monorepo: returns True only if package exists in config.yaml packages.
"""
packages = get_packages(repo_root)
if packages is None:
return True # Single-repo, no validation needed
return package in packages
def resolve_package(
task_package: str | None = None,
repo_root: Path | None = None,
) -> str | None:
"""Resolve package from inferred sources with validation.
Checks in order: task_package → default_package.
Invalid inferred values print a warning to stderr and are skipped.
Returns:
Resolved package name, or None if no valid package found.
Note:
CLI --package should be validated separately by the caller
(fail-fast with available packages list on error).
"""
packages = get_packages(repo_root)
if packages is None:
return None # Single-repo, no package needed
# Try task_package (guard against non-string values from malformed JSON)
if task_package and isinstance(task_package, str):
if task_package in packages:
return task_package
print(
f"Warning: task.json package '{task_package}' not found in config, skipping",
file=sys.stderr,
)
# Try default_package
default = get_default_package(repo_root)
if default:
if default in packages:
return default
print(
f"Warning: default_package '{default}' not found in config, skipping",
file=sys.stderr,
)
return None
def get_spec_scope(repo_root: Path | None = None) -> list[str] | str | None:
"""Get session.spec_scope configuration.
Returns:
list[str]: Package names to include in spec scanning.
str: "active_task" to use current task's package.
None: No scope configured (scan all packages).
"""
config = _load_config(repo_root)
session = config.get("session")
if not isinstance(session, dict):
return None
scope = session.get("spec_scope")
if scope is None:
return None
if isinstance(scope, str):
return scope # e.g. "active_task"
if isinstance(scope, list):
return [str(s) for s in scope]
return None
.trellis/scripts/common/developer.py
Executable
+190
View File
@@ -0,0 +1,190 @@
#!/usr/bin/env python3
"""
Developer management utilities.
Provides:
init_developer - Initialize developer
ensure_developer - Ensure developer is initialized (exit if not)
show_developer_info - Show developer information
"""
from __future__ import annotations
import sys
from datetime import datetime
from pathlib import Path
from .paths import (
DIR_WORKFLOW,
DIR_WORKSPACE,
DIR_TASKS,
FILE_DEVELOPER,
FILE_JOURNAL_PREFIX,
get_repo_root,
get_developer,
check_developer,
)
# =============================================================================
# Developer Initialization
# =============================================================================
def init_developer(name: str, repo_root: Path | None = None) -> bool:
"""Initialize developer.
Creates:
- .trellis/.developer file with developer info
- .trellis/workspace/<name>/ directory structure
- Initial journal file and index.md
Args:
name: Developer name.
repo_root: Repository root path. Defaults to auto-detected.
Returns:
True on success, False on error.
"""
if not name:
print("Error: developer name is required", file=sys.stderr)
return False
if repo_root is None:
repo_root = get_repo_root()
dev_file = repo_root / DIR_WORKFLOW / FILE_DEVELOPER
workspace_dir = repo_root / DIR_WORKFLOW / DIR_WORKSPACE / name
# Create .developer file
initialized_at = datetime.now().isoformat()
try:
dev_file.write_text(
f"name={name}\ninitialized_at={initialized_at}\n",
encoding="utf-8"
)
except (OSError, IOError) as e:
print(f"Error: Failed to create .developer file: {e}", file=sys.stderr)
return False
# Create workspace directory structure
try:
workspace_dir.mkdir(parents=True, exist_ok=True)
except (OSError, IOError) as e:
print(f"Error: Failed to create workspace directory: {e}", file=sys.stderr)
return False
# Create initial journal file
journal_file = workspace_dir / f"{FILE_JOURNAL_PREFIX}1.md"
if not journal_file.exists():
today = datetime.now().strftime("%Y-%m-%d")
journal_content = f"""# Journal - {name} (Part 1)
> AI development session journal
> Started: {today}
---
"""
try:
journal_file.write_text(journal_content, encoding="utf-8")
except (OSError, IOError) as e:
print(f"Error: Failed to create journal file: {e}", file=sys.stderr)
return False
# Create index.md with markers for auto-update
index_file = workspace_dir / "index.md"
if not index_file.exists():
index_content = f"""# Workspace Index - {name}
> Journal tracking for AI development sessions.
---
## Current Status
<!-- @@@auto:current-status -->
- **Active File**: `journal-1.md`
- **Total Sessions**: 0
- **Last Active**: -
<!-- @@@/auto:current-status -->
---
## Active Documents
<!-- @@@auto:active-documents -->
| File | Lines | Status |
|------|-------|--------|
| `journal-1.md` | ~0 | Active |
<!-- @@@/auto:active-documents -->
---
## Session History
<!-- @@@auto:session-history -->
| # | Date | Title | Commits | Branch |
|---|------|-------|---------|--------|
<!-- @@@/auto:session-history -->
---
## Notes
- Sessions are appended to journal files
- New journal file created when current exceeds 2000 lines
- Use `add_session.py` to record sessions
"""
try:
index_file.write_text(index_content, encoding="utf-8")
except (OSError, IOError) as e:
print(f"Error: Failed to create index.md: {e}", file=sys.stderr)
return False
print(f"Developer initialized: {name}")
print(f" .developer file: {dev_file}")
print(f" Workspace dir: {workspace_dir}")
return True
def ensure_developer(repo_root: Path | None = None) -> None:
"""Ensure developer is initialized, exit if not.
Args:
repo_root: Repository root path. Defaults to auto-detected.
"""
if repo_root is None:
repo_root = get_repo_root()
if not check_developer(repo_root):
print("Error: Developer not initialized.", file=sys.stderr)
print(f"Run: python3 ./{DIR_WORKFLOW}/scripts/init_developer.py <your-name>", file=sys.stderr)
sys.exit(1)
def show_developer_info(repo_root: Path | None = None) -> None:
"""Show developer information.
Args:
repo_root: Repository root path. Defaults to auto-detected.
"""
if repo_root is None:
repo_root = get_repo_root()
developer = get_developer(repo_root)
if not developer:
print("Developer: (not initialized)")
else:
print(f"Developer: {developer}")
print(f"Workspace: {DIR_WORKFLOW}/{DIR_WORKSPACE}/{developer}/")
print(f"Tasks: {DIR_WORKFLOW}/{DIR_TASKS}/")
# =============================================================================
# Main Entry (for testing)
# =============================================================================
if __name__ == "__main__":
show_developer_info()
.trellis/scripts/common/git.py
Executable
+31
View File
@@ -0,0 +1,31 @@
"""
Git command execution utility.
Single source of truth for running git commands across all Trellis scripts.
"""
from __future__ import annotations
import subprocess
from pathlib import Path
def run_git(args: list[str], cwd: Path | None = None) -> tuple[int, str, str]:
"""Run a git command and return (returncode, stdout, stderr).
Uses UTF-8 encoding with -c i18n.logOutputEncoding=UTF-8 to ensure
consistent output across all platforms (Windows, macOS, Linux).
"""
try:
git_args = ["git", "-c", "i18n.logOutputEncoding=UTF-8"] + args
result = subprocess.run(
git_args,
cwd=cwd,
capture_output=True,
text=True,
encoding="utf-8",
errors="replace",
)
return result.returncode, result.stdout, result.stderr
except Exception as e:
return 1, "", str(e)
.trellis/scripts/common/git_context.py
Executable
+106
View File
@@ -0,0 +1,106 @@
#!/usr/bin/env python3
# -*- coding: utf-8 -*-
"""
Git and Session Context utilities.
Entry shim — delegates to session_context and packages_context.
Provides:
output_json - Output context in JSON format
output_text - Output context in text format
"""
from __future__ import annotations
import json
from .git import run_git
from .session_context import (
get_context_json,
get_context_text,
get_context_record_json,
get_context_text_record,
output_json,
output_text,
)
from .packages_context import (
get_context_packages_text,
get_context_packages_json,
)
from .trellis_config import read_trellis_config
from .workflow_phase import (
filter_platform,
get_phase_index,
get_step,
resolve_effective_platform,
)
# Backward-compatible alias — external modules import this name
_run_git_command = run_git
# =============================================================================
# Main Entry
# =============================================================================
def main() -> None:
"""CLI entry point."""
import argparse
parser = argparse.ArgumentParser(description="Get Session Context for AI Agent")
parser.add_argument(
"--json",
"-j",
action="store_true",
help="Output in JSON format (works with any --mode)",
)
parser.add_argument(
"--mode",
"-m",
choices=["default", "record", "packages", "phase"],
default="default",
help="Output mode: default (full context), record (for record-session), packages (package info only), phase (workflow step extraction)",
)
parser.add_argument(
"--step",
help="Step id for --mode phase, e.g. 1.1, 2.2. Omit to get the Phase Index.",
)
parser.add_argument(
"--platform",
help="Platform name for --mode phase, e.g. cursor, claude-code. Filters platform-tagged blocks.",
)
args = parser.parse_args()
if args.mode == "record":
if args.json:
print(json.dumps(get_context_record_json(), indent=2, ensure_ascii=False))
else:
print(get_context_text_record())
elif args.mode == "packages":
if args.json:
print(json.dumps(get_context_packages_json(), indent=2, ensure_ascii=False))
else:
print(get_context_packages_text())
elif args.mode == "phase":
content = get_step(args.step) if args.step else get_phase_index()
if not content.strip():
if args.step:
parser.exit(2, f"Step not found: {args.step}\n")
else:
parser.exit(2, "Phase Index section not found in workflow.md\n")
if args.platform:
effective = resolve_effective_platform(
args.platform, read_trellis_config()
)
content = filter_platform(content, effective)
print(content, end="")
else:
if args.json:
output_json()
else:
output_text()
if __name__ == "__main__":
main()
.trellis/scripts/common/io.py
Executable
+37
View File
@@ -0,0 +1,37 @@
"""
JSON file I/O utilities.
Provides read_json and write_json as the single source of truth
for JSON file operations across all Trellis scripts.
"""
from __future__ import annotations
import json
from pathlib import Path
def read_json(path: Path) -> dict | None:
"""Read and parse a JSON file.
Returns None if the file doesn't exist, is invalid JSON, or can't be read.
"""
try:
return json.loads(path.read_text(encoding="utf-8"))
except (FileNotFoundError, json.JSONDecodeError, OSError):
return None
def write_json(path: Path, data: dict) -> bool:
"""Write dict to JSON file with pretty formatting.
Returns True on success, False on error.
"""
try:
path.write_text(
json.dumps(data, indent=2, ensure_ascii=False),
encoding="utf-8",
)
return True
except (OSError, IOError):
return False
.trellis/scripts/common/log.py
Executable
+45
View File
@@ -0,0 +1,45 @@
"""
Terminal output utilities: colors and structured logging.
Single source of truth for Colors and log_* functions
used across all Trellis scripts.
"""
from __future__ import annotations
class Colors:
"""ANSI color codes for terminal output."""
RED = "\033[0;31m"
GREEN = "\033[0;32m"
YELLOW = "\033[1;33m"
BLUE = "\033[0;34m"
CYAN = "\033[0;36m"
DIM = "\033[2m"
NC = "\033[0m" # No Color / Reset
def colored(text: str, color: str) -> str:
"""Apply ANSI color to text."""
return f"{color}{text}{Colors.NC}"
def log_info(msg: str) -> None:
"""Print info-level message with [INFO] prefix."""
print(f"{Colors.BLUE}[INFO]{Colors.NC} {msg}")
def log_success(msg: str) -> None:
"""Print success message with [SUCCESS] prefix."""
print(f"{Colors.GREEN}[SUCCESS]{Colors.NC} {msg}")
def log_warn(msg: str) -> None:
"""Print warning message with [WARN] prefix."""
print(f"{Colors.YELLOW}[WARN]{Colors.NC} {msg}")
def log_error(msg: str) -> None:
"""Print error message with [ERROR] prefix."""
print(f"{Colors.RED}[ERROR]{Colors.NC} {msg}")
.trellis/scripts/common/packages_context.py
Executable
+238
View File
@@ -0,0 +1,238 @@
#!/usr/bin/env python3
"""
Package discovery and context output.
Provides:
get_packages_info - Get structured package info
get_packages_section - Build PACKAGES text section
get_context_packages_text - Full packages text output (--mode packages)
get_context_packages_json - Full packages JSON output (--mode packages --json)
"""
from __future__ import annotations
from pathlib import Path
from .config import _is_true_config_value, get_default_package, get_packages, get_spec_scope
from .paths import (
DIR_SPEC,
DIR_WORKFLOW,
get_current_task,
get_repo_root,
)
from .tasks import load_task
# =============================================================================
# Internal Helpers
# =============================================================================
def _scan_spec_layers(spec_dir: Path, package: str | None = None) -> list[str]:
"""Scan spec directory for available layers (subdirectories).
For monorepo: scans spec/<package>/
For single-repo: scans spec/
"""
target = spec_dir / package if package else spec_dir
if not target.is_dir():
return []
return sorted(
d.name for d in target.iterdir() if d.is_dir() and d.name != "guides"
)
def _get_active_task_package(repo_root: Path) -> str | None:
"""Get the package field from the active task's task.json."""
current = get_current_task(repo_root)
if not current:
return None
ct = load_task(repo_root / current)
return ct.package if ct and ct.package else None
def _resolve_scope_set(
packages: dict,
spec_scope,
task_pkg: str | None,
default_pkg: str | None,
) -> set | None:
"""Resolve spec_scope to a set of allowed package names, or None for full scan."""
if not packages:
return None
if spec_scope is None:
return None
if isinstance(spec_scope, str) and spec_scope == "active_task":
if task_pkg and task_pkg in packages:
return {task_pkg}
if default_pkg and default_pkg in packages:
return {default_pkg}
return None
if isinstance(spec_scope, list):
valid = {e for e in spec_scope if e in packages}
if valid:
return valid
# All invalid: fallback
if task_pkg and task_pkg in packages:
return {task_pkg}
if default_pkg and default_pkg in packages:
return {default_pkg}
return None
return None
# =============================================================================
# Public Functions
# =============================================================================
def get_packages_info(repo_root: Path) -> list[dict]:
"""Get structured package info for monorepo projects.
Returns list of dicts with keys: name, path, type, default, specLayers,
isSubmodule, isGitRepo.
Returns empty list for single-repo projects.
"""
packages = get_packages(repo_root)
if not packages:
return []
default_pkg = get_default_package(repo_root)
spec_dir = repo_root / DIR_WORKFLOW / DIR_SPEC
result = []
for pkg_name, pkg_config in packages.items():
pkg_path = pkg_config.get("path", pkg_name) if isinstance(pkg_config, dict) else str(pkg_config)
pkg_type = pkg_config.get("type", "local") if isinstance(pkg_config, dict) else "local"
pkg_git = pkg_config.get("git", False) if isinstance(pkg_config, dict) else False
layers = _scan_spec_layers(spec_dir, pkg_name)
result.append({
"name": pkg_name,
"path": pkg_path,
"type": pkg_type,
"default": pkg_name == default_pkg,
"specLayers": layers,
"isSubmodule": pkg_type == "submodule",
"isGitRepo": _is_true_config_value(pkg_git),
})
return result
def get_packages_section(repo_root: Path) -> str:
"""Build the PACKAGES section for text output."""
spec_dir = repo_root / DIR_WORKFLOW / DIR_SPEC
pkg_info = get_packages_info(repo_root)
lines: list[str] = []
lines.append("## PACKAGES")
if not pkg_info:
lines.append("(single-repo mode)")
layers = _scan_spec_layers(spec_dir)
if layers:
lines.append(f"Spec layers: {', '.join(layers)}")
return "\n".join(lines)
default_pkg = get_default_package(repo_root)
for pkg in pkg_info:
layers_str = f" [{', '.join(pkg['specLayers'])}]" if pkg["specLayers"] else ""
submodule_tag = " (submodule)" if pkg["isSubmodule"] else ""
git_repo_tag = " (git repo)" if pkg["isGitRepo"] else ""
default_tag = " *" if pkg["default"] else ""
lines.append(
f"- {pkg['name']:<16} {pkg['path']:<20}{layers_str}{submodule_tag}{git_repo_tag}{default_tag}"
)
if default_pkg:
lines.append(f"Default package: {default_pkg}")
return "\n".join(lines)
def get_context_packages_text(repo_root: Path | None = None) -> str:
"""Get packages context as formatted text (for --mode packages)."""
if repo_root is None:
repo_root = get_repo_root()
pkg_info = get_packages_info(repo_root)
lines: list[str] = []
if not pkg_info:
spec_dir = repo_root / DIR_WORKFLOW / DIR_SPEC
lines.append("Single-repo project (no packages configured)")
lines.append("")
layers = _scan_spec_layers(spec_dir)
if layers:
lines.append(f"Spec layers: {', '.join(layers)}")
return "\n".join(lines)
# Resolve scope for annotations
packages_dict = get_packages(repo_root) or {}
default_pkg = get_default_package(repo_root)
spec_scope = get_spec_scope(repo_root)
task_pkg = _get_active_task_package(repo_root)
scope_set = _resolve_scope_set(packages_dict, spec_scope, task_pkg, default_pkg)
lines.append("## PACKAGES")
lines.append("")
for pkg in pkg_info:
default_tag = " (default)" if pkg["default"] else ""
type_tag = f" [{pkg['type']}]" if pkg["type"] != "local" else ""
git_tag = " [git repo]" if pkg["isGitRepo"] else ""
# Scope annotation
scope_tag = ""
if scope_set is not None and pkg["name"] not in scope_set:
scope_tag = " (out of scope)"
lines.append(f"### {pkg['name']}{default_tag}{type_tag}{git_tag}{scope_tag}")
lines.append(f"Path: {pkg['path']}")
if pkg["specLayers"]:
lines.append(f"Spec layers: {', '.join(pkg['specLayers'])}")
for layer in pkg["specLayers"]:
lines.append(f" - .trellis/spec/{pkg['name']}/{layer}/index.md")
else:
lines.append("Spec: not configured")
lines.append("")
# Also show shared guides
guides_dir = repo_root / DIR_WORKFLOW / DIR_SPEC / "guides"
if guides_dir.is_dir():
lines.append("### Shared Guides (always included)")
lines.append("Path: .trellis/spec/guides/index.md")
lines.append("")
return "\n".join(lines)
def get_context_packages_json(repo_root: Path | None = None) -> dict:
"""Get packages context as a dictionary (for --mode packages --json)."""
if repo_root is None:
repo_root = get_repo_root()
pkg_info = get_packages_info(repo_root)
if not pkg_info:
spec_dir = repo_root / DIR_WORKFLOW / DIR_SPEC
layers = _scan_spec_layers(spec_dir)
return {
"mode": "single-repo",
"specLayers": layers,
}
default_pkg = get_default_package(repo_root)
spec_scope = get_spec_scope(repo_root)
task_pkg = _get_active_task_package(repo_root)
return {
"mode": "monorepo",
"packages": pkg_info,
"defaultPackage": default_pkg,
"specScope": spec_scope,
"activeTaskPackage": task_pkg,
}
.trellis/scripts/common/paths.py
Executable
+447
View File
@@ -0,0 +1,447 @@
#!/usr/bin/env python3
"""
Common path utilities for Trellis workflow.
Provides:
get_repo_root - Get repository root directory
get_developer - Get developer name
get_workspace_dir - Get developer workspace directory
get_tasks_dir - Get tasks directory
get_active_journal_file - Get current journal file
"""
from __future__ import annotations
import re
from datetime import datetime
from pathlib import Path
# =============================================================================
# Path Constants (change here to rename directories)
# =============================================================================
# Directory names
DIR_WORKFLOW = ".trellis"
DIR_WORKSPACE = "workspace"
DIR_TASKS = "tasks"
DIR_ARCHIVE = "archive"
DIR_SPEC = "spec"
DIR_SCRIPTS = "scripts"
# File names
FILE_DEVELOPER = ".developer"
FILE_CURRENT_TASK = ".current-task"
FILE_TASK_JSON = "task.json"
FILE_JOURNAL_PREFIX = "journal-"
# =============================================================================
# Repository Root
# =============================================================================
def get_repo_root(start_path: Path | None = None) -> Path:
"""Find the nearest directory containing .trellis/ folder.
This handles nested git repos correctly (e.g., test project inside another repo).
Args:
start_path: Starting directory to search from. Defaults to current directory.
Returns:
Path to repository root, or current directory if no .trellis/ found.
"""
current = (start_path or Path.cwd()).resolve()
while current != current.parent:
if (current / DIR_WORKFLOW).is_dir():
return current
current = current.parent
# Fallback to current directory if no .trellis/ found
return Path.cwd().resolve()
# =============================================================================
# Developer
# =============================================================================
def get_developer(repo_root: Path | None = None) -> str | None:
"""Get developer name from .developer file.
Args:
repo_root: Repository root path. Defaults to auto-detected.
Returns:
Developer name or None if not initialized.
"""
if repo_root is None:
repo_root = get_repo_root()
dev_file = repo_root / DIR_WORKFLOW / FILE_DEVELOPER
if not dev_file.is_file():
return None
try:
content = dev_file.read_text(encoding="utf-8")
for line in content.splitlines():
if line.startswith("name="):
return line.split("=", 1)[1].strip()
except (OSError, IOError):
pass
return None
def check_developer(repo_root: Path | None = None) -> bool:
"""Check if developer is initialized.
Args:
repo_root: Repository root path. Defaults to auto-detected.
Returns:
True if developer is initialized.
"""
return get_developer(repo_root) is not None
# =============================================================================
# Tasks Directory
# =============================================================================
def get_tasks_dir(repo_root: Path | None = None) -> Path:
"""Get tasks directory path.
Args:
repo_root: Repository root path. Defaults to auto-detected.
Returns:
Path to tasks directory.
"""
if repo_root is None:
repo_root = get_repo_root()
return repo_root / DIR_WORKFLOW / DIR_TASKS
# =============================================================================
# Workspace Directory
# =============================================================================
def get_workspace_dir(repo_root: Path | None = None) -> Path | None:
"""Get developer workspace directory.
Args:
repo_root: Repository root path. Defaults to auto-detected.
Returns:
Path to workspace directory or None if developer not set.
"""
if repo_root is None:
repo_root = get_repo_root()
developer = get_developer(repo_root)
if developer:
return repo_root / DIR_WORKFLOW / DIR_WORKSPACE / developer
return None
# =============================================================================
# Journal File
# =============================================================================
def get_active_journal_file(repo_root: Path | None = None) -> Path | None:
"""Get the current active journal file.
Args:
repo_root: Repository root path. Defaults to auto-detected.
Returns:
Path to active journal file or None if not found.
"""
if repo_root is None:
repo_root = get_repo_root()
workspace_dir = get_workspace_dir(repo_root)
if workspace_dir is None or not workspace_dir.is_dir():
return None
latest: Path | None = None
highest = 0
for f in workspace_dir.glob(f"{FILE_JOURNAL_PREFIX}*.md"):
if not f.is_file():
continue
# Extract number from filename
name = f.stem # e.g., "journal-1"
match = re.search(r"(\d+)$", name)
if match:
num = int(match.group(1))
if num > highest:
highest = num
latest = f
return latest
def count_lines(file_path: Path) -> int:
"""Count lines in a file.
Args:
file_path: Path to file.
Returns:
Number of lines, or 0 if file doesn't exist.
"""
if not file_path.is_file():
return 0
try:
return len(file_path.read_text(encoding="utf-8").splitlines())
except (OSError, IOError):
return 0
# =============================================================================
# Current Task Management
# =============================================================================
def normalize_task_ref(task_ref: str) -> str:
"""Normalize a task ref for stable runtime storage.
Stored refs should prefer repo-relative POSIX paths like
`.trellis/tasks/03-27-my-task`, even on Windows. Absolute paths are preserved
unless they can later be converted back to repo-relative form by callers.
"""
normalized = task_ref.strip()
if not normalized:
return ""
path_obj = Path(normalized)
if path_obj.is_absolute():
return str(path_obj)
normalized = normalized.replace("\\", "/")
while normalized.startswith("./"):
normalized = normalized[2:]
if normalized.startswith(f"{DIR_TASKS}/"):
return f"{DIR_WORKFLOW}/{normalized}"
return normalized
def resolve_task_ref(task_ref: str, repo_root: Path | None = None) -> Path | None:
"""Resolve a task ref to an absolute task directory path."""
if repo_root is None:
repo_root = get_repo_root()
normalized = normalize_task_ref(task_ref)
if not normalized:
return None
path_obj = Path(normalized)
if path_obj.is_absolute():
return path_obj
if normalized.startswith(f"{DIR_WORKFLOW}/"):
return repo_root / path_obj
return repo_root / DIR_WORKFLOW / DIR_TASKS / path_obj
def get_current_task(
repo_root: Path | None = None,
platform_input: dict | None = None,
platform: str | None = None,
) -> str | None:
"""Get current task directory path (relative to repo_root).
Args:
repo_root: Repository root path. Defaults to auto-detected.
Returns:
Relative path to current task directory or None.
"""
if repo_root is None:
repo_root = get_repo_root()
from .active_task import resolve_active_task
return resolve_active_task(repo_root, platform_input, platform).task_path
def get_current_task_abs(
repo_root: Path | None = None,
platform_input: dict | None = None,
platform: str | None = None,
) -> Path | None:
"""Get current task directory absolute path.
Args:
repo_root: Repository root path. Defaults to auto-detected.
Returns:
Absolute path to current task directory or None.
"""
if repo_root is None:
repo_root = get_repo_root()
relative = get_current_task(repo_root, platform_input, platform)
if relative:
return resolve_task_ref(relative, repo_root)
return None
def get_current_task_source(
repo_root: Path | None = None,
platform_input: dict | None = None,
platform: str | None = None,
) -> tuple[str, str | None, str | None]:
"""Get active task source as (`source`, `context_key`, `task_path`)."""
if repo_root is None:
repo_root = get_repo_root()
from .active_task import get_current_task_source as _get_source
return _get_source(repo_root, platform_input, platform)
def set_current_task(
task_path: str,
repo_root: Path | None = None,
platform_input: dict | None = None,
platform: str | None = None,
) -> bool:
"""Set current task in session scope.
Args:
task_path: Task directory path (relative to repo_root).
repo_root: Repository root path. Defaults to auto-detected.
Returns:
True on success, False on error.
"""
if repo_root is None:
repo_root = get_repo_root()
from .active_task import set_active_task
return set_active_task(
task_path,
repo_root,
platform_input=platform_input,
platform=platform,
) is not None
def clear_current_task(
repo_root: Path | None = None,
platform_input: dict | None = None,
platform: str | None = None,
) -> bool:
"""Clear current task in session scope.
Args:
repo_root: Repository root path. Defaults to auto-detected.
Returns:
True on success.
"""
if repo_root is None:
repo_root = get_repo_root()
from .active_task import clear_active_task
clear_active_task(
repo_root,
platform_input=platform_input,
platform=platform,
)
return True
def has_current_task(repo_root: Path | None = None) -> bool:
"""Check if has current task.
Args:
repo_root: Repository root path. Defaults to auto-detected.
Returns:
True if current task is set.
"""
return get_current_task(repo_root) is not None
# =============================================================================
# Task ID Generation
# =============================================================================
def generate_task_date_prefix() -> str:
"""Generate task ID based on date (MM-DD format).
Returns:
Date prefix string (e.g., "01-21").
"""
return datetime.now().strftime("%m-%d")
# =============================================================================
# Monorepo / Package Paths
# =============================================================================
def get_spec_dir(package: str | None = None, repo_root: Path | None = None) -> Path:
"""Get the spec directory path.
Single-repo: .trellis/spec
Monorepo with package: .trellis/spec/<package>
Uses lazy import to avoid circular dependency with config.py.
"""
if repo_root is None:
repo_root = get_repo_root()
from .config import get_spec_base
base = get_spec_base(package, repo_root)
return repo_root / DIR_WORKFLOW / base
def get_package_path(package: str, repo_root: Path | None = None) -> Path | None:
"""Get a package's source directory absolute path from config.
Returns:
Absolute path to the package directory, or None if not found.
"""
if repo_root is None:
repo_root = get_repo_root()
from .config import get_packages
packages = get_packages(repo_root)
if not packages or package not in packages:
return None
info = packages[package]
if isinstance(info, dict):
rel_path = info.get("path", package)
else:
rel_path = str(info)
return repo_root / rel_path
# =============================================================================
# Main Entry (for testing)
# =============================================================================
if __name__ == "__main__":
repo = get_repo_root()
print(f"Repository root: {repo}")
print(f"Developer: {get_developer(repo)}")
print(f"Tasks dir: {get_tasks_dir(repo)}")
print(f"Workspace dir: {get_workspace_dir(repo)}")
print(f"Journal file: {get_active_journal_file(repo)}")
print(f"Current task: {get_current_task(repo)}")
.trellis/scripts/common/safe_commit.py
Executable
+315
View File
@@ -0,0 +1,315 @@
"""
Safe git-add helpers for Trellis-owned paths.
Why this module exists
----------------------
A real user incident: a project's `.gitignore` listed `.trellis/` (company-wide
template / personal habit). When `add_session.py` and `task.py archive` ran
their auto-commit and `git add` failed with `ignored by .gitignore`, the AI
agent driving the workflow "fixed" it by retrying with
`git add -f .trellis/` — which fan-out-included every ignored subtree
(`.trellis/.backup-*/`, `.trellis/worktrees/`, `.trellis/.template-hashes.json`,
`.trellis/.runtime/`), committing 548 files / 83474 lines of caches/backups.
Design
------
- Scripts only stage SPECIFIC product paths (journal files, index.md, the
current task dir, the archive dir). Never the whole `.trellis/` tree.
- If plain `git add <specific>` fails with "ignored by", DO NOT retry with
``-f``. The presence of `.trellis/` in `.gitignore` is treated as user
intent ("keep .trellis/ local-only"). The script warns and skips the
auto-commit; users who want auto-staging can either fix their `.gitignore`
or set ``session_auto_commit: false`` and manage git themselves.
- The warning includes a negative example: ``Do NOT use `git add -f .trellis/` ...``
so any AI rereading the log doesn't reinvent the bug.
History note: 0.5.10 introduced an automatic ``git add -f`` retry on the
specific paths. That was reverted in 0.5.11 — auto-forcing into a tree the
user had gitignored violates user intent even when the path list is narrow.
The wider-grain forbidden command stays forbidden, and the narrow-grain auto
``-f`` is gone too.
"""
from __future__ import annotations
import sys
from pathlib import Path
from .git import run_git
from .paths import (
DIR_ARCHIVE,
DIR_TASKS,
DIR_WORKFLOW,
DIR_WORKSPACE,
FILE_JOURNAL_PREFIX,
get_developer,
)
# Paths under .trellis/ that must NEVER be auto-staged. Listed here so the
# warning to the user can show concrete subpaths to ignore individually
# instead of ignoring the whole `.trellis/` tree.
TRELLIS_IGNORED_SUBPATHS = (
".trellis/.backup-*",
".trellis/worktrees/",
".trellis/.template-hashes.json",
".trellis/.runtime/",
".trellis/.cache/",
)
def safe_trellis_paths_to_add(
repo_root: Path,
task_name: str | None = None,
) -> list[str]:
"""Return the list of repo-relative paths the auto-commit should stage.
Only includes paths that exist on disk so callers don't pass non-existent
arguments to git. The caller is responsible for `git diff --cached`
checking afterwards.
Included:
- .trellis/workspace/<developer>/journal-*.md
- .trellis/workspace/<developer>/index.md
- .trellis/tasks/<task_name>/ (ONLY the current task dir when
``task_name`` is passed; plus its archive location if the task
already lives under archive/)
Excluded (intentionally — these must not be staged):
- .trellis/.backup-*, .trellis/worktrees/,
.trellis/.template-hashes.json, .trellis/.runtime/, .trellis/.cache/
Scope contract (see #303 / break-loop analysis): when ``task_name`` is
passed, the task segment stages ONLY that task directory — it never walks
``tasks_dir.iterdir()`` over all active tasks. This mirrors
:func:`safe_archive_paths_to_add` and prevents dirty changes in OTHER
parallel-window task dirs from being bundled into the session auto-commit.
Backwards-compat: with no ``task_name``, the function walks every active
task directory (+ the archive subtree) the old wide way. New callers
should always pass ``task_name``.
"""
paths: list[str] = []
# Workspace journal files + index.md
developer = get_developer(repo_root)
if developer:
ws = repo_root / DIR_WORKFLOW / DIR_WORKSPACE / developer
if ws.is_dir():
for f in sorted(ws.glob(f"{FILE_JOURNAL_PREFIX}*.md")):
if f.is_file():
paths.append(
f"{DIR_WORKFLOW}/{DIR_WORKSPACE}/{developer}/{f.name}"
)
index_md = ws / "index.md"
if index_md.is_file():
paths.append(
f"{DIR_WORKFLOW}/{DIR_WORKSPACE}/{developer}/index.md"
)
tasks_dir = repo_root / DIR_WORKFLOW / DIR_TASKS
if not tasks_dir.is_dir():
return paths
if task_name is not None:
# Narrow scope — ONLY the current task directory (active or archived).
# Never iterdir() all tasks: parallel-window dirty task dirs must not
# leak into the session auto-commit.
active_task = tasks_dir / task_name
if active_task.is_dir():
paths.append(f"{DIR_WORKFLOW}/{DIR_TASKS}/{task_name}")
archived_task = tasks_dir / DIR_ARCHIVE / task_name
if archived_task.is_dir():
paths.append(
f"{DIR_WORKFLOW}/{DIR_TASKS}/{DIR_ARCHIVE}/{task_name}"
)
return paths
# Legacy wide scope (no task_name): each direct child of tasks/ that is a
# directory and not the archive root, plus the whole archive subtree.
for child in sorted(tasks_dir.iterdir()):
if not child.is_dir():
continue
if child.name == DIR_ARCHIVE:
continue
paths.append(f"{DIR_WORKFLOW}/{DIR_TASKS}/{child.name}")
archive_dir = tasks_dir / DIR_ARCHIVE
if archive_dir.is_dir():
paths.append(f"{DIR_WORKFLOW}/{DIR_TASKS}/{DIR_ARCHIVE}")
return paths
def safe_archive_paths_to_add(
repo_root: Path,
task_name: str | None = None,
modified_children: list[str] | None = None,
) -> list[str]:
"""Return paths to stage after `task.py archive`.
Scoped to ONLY the paths the archive operation actually touched:
- the archive subtree (where the freshly-moved task lives)
- the source task directory (for source-side deletes; caller pairs
this with `git rm --cached` since `git add` won't stage deletes
for a path that no longer exists in the working tree)
- any child task directories whose `task.json` was edited to drop
the archived parent (parent-children relationship update)
This narrow scope avoids "scope creep" — dirty changes in OTHER
active task dirs (parallel-window edits) are NOT bundled into the
archive commit. Callers handle each kind of change in its own
commit boundary.
Backwards-compat: with no arguments, the function walks the whole
`.trellis/tasks/` subtree the old way (active tasks + archive). New
callers should always pass `task_name`.
"""
paths: list[str] = []
tasks_dir = repo_root / DIR_WORKFLOW / DIR_TASKS
if not tasks_dir.is_dir():
return paths
archive_dir = tasks_dir / DIR_ARCHIVE
if task_name is not None:
# Narrow scope — only paths that still exist on disk (so
# `git add` doesn't choke on the moved-away source). The caller
# handles the source-side deletes via `git rm --cached`
# explicitly.
if archive_dir.is_dir():
paths.append(
f"{DIR_WORKFLOW}/{DIR_TASKS}/{DIR_ARCHIVE}"
)
for child_name in modified_children or []:
paths.append(f"{DIR_WORKFLOW}/{DIR_TASKS}/{child_name}")
return paths
# Legacy wide scope (no task_name): preserve old behavior so callers
# that have not been updated keep working.
if archive_dir.is_dir():
paths.append(f"{DIR_WORKFLOW}/{DIR_TASKS}/{DIR_ARCHIVE}")
for child in sorted(tasks_dir.iterdir()):
if not child.is_dir():
continue
if child.name == DIR_ARCHIVE:
continue
paths.append(f"{DIR_WORKFLOW}/{DIR_TASKS}/{child.name}")
return paths
def _stderr_indicates_ignored(stderr: str) -> bool:
"""git add error indicates the path is excluded by .gitignore."""
if not stderr:
return False
lowered = stderr.lower()
return "ignored by" in lowered
def safe_git_add(
paths: list[str], repo_root: Path
) -> tuple[bool, bool, str]:
"""Run `git add` on specific paths; never retry with -f.
Returns ``(success, used_force, stderr)``. The ``used_force`` field is
kept for signature compatibility with the 0.5.10 implementation but is
always ``False`` — we never auto-force.
Behavior:
- No paths passed → success, no force, empty stderr.
- Plain ``git add -- <paths>`` succeeds → return success.
- Plain fails (any reason — ignored or otherwise) → return failure with
the stderr. Callers should inspect the stderr (see
:func:`print_gitignore_warning`) and skip the auto-commit.
"""
if not paths:
return True, False, ""
rc, _, err = run_git(["add", "--", *paths], cwd=repo_root)
if rc == 0:
return True, False, ""
return False, False, err
def print_gitignore_warning(paths: list[str]) -> None:
"""Explain to the user (and any AI reading the log) what to do.
CRITICAL: includes the negative example
``Do NOT use `git add -f .trellis/``` — agents reading the warning are
known to invent that command, which fans out to ignored caches/backups.
"""
print(
"[WARN] git add failed because .trellis/ paths are ignored by your .gitignore.",
file=sys.stderr,
)
print(
"[WARN] Skipping auto-commit. The journal/task files were still written to disk;",
file=sys.stderr,
)
print(
"[WARN] git was not touched.",
file=sys.stderr,
)
print("[WARN]", file=sys.stderr)
print(
"[WARN] Trellis manages these specific paths and they should be tracked:",
file=sys.stderr,
)
if paths:
for p in paths:
print(f"[WARN] {p}", file=sys.stderr)
else:
print(
"[WARN] .trellis/workspace/<developer>/{journal-*.md,index.md}",
file=sys.stderr,
)
print(
"[WARN] .trellis/tasks/<task-dir>/",
file=sys.stderr,
)
print(
"[WARN] .trellis/tasks/archive/",
file=sys.stderr,
)
print("[WARN]", file=sys.stderr)
print(
"[WARN] Recommended: change your .gitignore from `.trellis/` to specific",
file=sys.stderr,
)
print(
"[WARN] subpaths that should remain ignored, e.g.:",
file=sys.stderr,
)
for sub in TRELLIS_IGNORED_SUBPATHS:
print(f"[WARN] {sub}", file=sys.stderr)
print("[WARN]", file=sys.stderr)
print(
"[WARN] Or, if you intentionally keep .trellis/ local-only, set in",
file=sys.stderr,
)
print(
"[WARN] .trellis/config.yaml:",
file=sys.stderr,
)
print(
"[WARN] session_auto_commit: false",
file=sys.stderr,
)
print(
"[WARN] so the scripts skip git entirely and you can review / commit",
file=sys.stderr,
)
print(
"[WARN] manually with `git status` / `git add` / `git commit`.",
file=sys.stderr,
)
print("[WARN]", file=sys.stderr)
print(
"[WARN] Do NOT use `git add -f .trellis/` — it pulls in backups, worktrees,",
file=sys.stderr,
)
print(
"[WARN] and runtime caches that should never be committed.",
file=sys.stderr,
)
.trellis/scripts/common/session_context.py
Executable
+821
View File
@@ -0,0 +1,821 @@
#!/usr/bin/env python3
"""
Session context generation (default + record modes).
Provides:
get_context_json - JSON output for default mode
get_context_text - Text output for default mode
get_context_record_json - JSON for record mode
get_context_text_record - Text for record mode
output_json - Print JSON
output_text - Print text
"""
from __future__ import annotations
import json
import os
import re
import subprocess
from pathlib import Path
from .active_task import resolve_context_key
from .config import get_git_packages
from .git import run_git
from .packages_context import get_packages_section
from .tasks import iter_active_tasks, load_task, get_all_statuses, children_progress
from .paths import (
DIR_SCRIPTS,
DIR_SPEC,
DIR_TASKS,
DIR_WORKFLOW,
DIR_WORKSPACE,
count_lines,
get_active_journal_file,
get_current_task,
get_current_task_source,
get_developer,
get_repo_root,
get_tasks_dir,
)
# =============================================================================
# Helpers
# =============================================================================
_PACKAGE_NAME = "@mindfoldhq/trellis"
_UPDATE_CHECK_TIMEOUT_SECONDS = 1.0
_VERSION_RE = re.compile(
r"^\s*(\d+)(?:\.(\d+))?(?:\.(\d+))?(?:-([0-9A-Za-z.-]+))?\s*$"
)
_VERSION_TOKEN_RE = re.compile(r"\b\d+(?:\.\d+){1,2}(?:-[0-9A-Za-z.-]+)?\b")
_POLYREPO_IGNORED_DIRS = {
"node_modules",
"target",
"dist",
"build",
"out",
"bin",
"obj",
"vendor",
"coverage",
"tmp",
"__pycache__",
}
_POLYREPO_SCAN_MAX_DEPTH = 2
def _is_git_worktree(path: Path) -> bool:
"""Return True when path is inside a Git worktree."""
rc, out, _ = run_git(["rev-parse", "--is-inside-work-tree"], cwd=path)
return rc == 0 and out.strip().lower() == "true"
def _parse_recent_commits(log_output: str) -> list[dict]:
"""Parse `git log --oneline` output into structured commit entries."""
commits = []
for line in log_output.splitlines():
if not line.strip():
continue
parts = line.split(" ", 1)
if len(parts) >= 2:
commits.append({"hash": parts[0], "message": parts[1]})
elif len(parts) == 1:
commits.append({"hash": parts[0], "message": ""})
return commits
def _collect_git_repo_info(name: str, rel_path: str, repo_dir: Path) -> dict | None:
"""Collect Git status for one known repository directory."""
if not (repo_dir / ".git").exists():
return None
_, branch_out, _ = run_git(["branch", "--show-current"], cwd=repo_dir)
branch = branch_out.strip() or "unknown"
_, status_out, _ = run_git(["status", "--porcelain"], cwd=repo_dir)
changes = len([l for l in status_out.splitlines() if l.strip()])
_, log_out, _ = run_git(["log", "--oneline", "-5"], cwd=repo_dir)
return {
"name": name,
"path": rel_path,
"branch": branch,
"isClean": changes == 0,
"uncommittedChanges": changes,
"recentCommits": _parse_recent_commits(log_out),
}
def _collect_root_git_info(repo_root: Path) -> dict:
"""Collect root Git info without pretending a non-Git root is clean."""
if not _is_git_worktree(repo_root):
return {
"isRepo": False,
"branch": "",
"isClean": False,
"uncommittedChanges": 0,
"recentCommits": [],
}
_, branch_out, _ = run_git(["branch", "--show-current"], cwd=repo_root)
branch = branch_out.strip() or "unknown"
_, status_out, _ = run_git(["status", "--porcelain"], cwd=repo_root)
status_lines = [line for line in status_out.splitlines() if line.strip()]
_, short_out, _ = run_git(["status", "--short"], cwd=repo_root)
_, log_out, _ = run_git(["log", "--oneline", "-5"], cwd=repo_root)
return {
"isRepo": True,
"branch": branch,
"isClean": len(status_lines) == 0,
"uncommittedChanges": len(status_lines),
"statusShort": short_out.splitlines(),
"recentCommits": _parse_recent_commits(log_out),
}
def _discover_child_git_repos(repo_root: Path) -> list[tuple[str, str]]:
"""Discover child Git repositories using the init-time polyrepo heuristic."""
found: list[str] = []
def is_candidate_dir(path: Path) -> bool:
name = path.name
return not name.startswith(".") and name not in _POLYREPO_IGNORED_DIRS
def scan(rel_dir: Path, depth: int) -> None:
if depth >= _POLYREPO_SCAN_MAX_DEPTH:
return
abs_dir = repo_root / rel_dir
try:
children = sorted(abs_dir.iterdir(), key=lambda p: p.name)
except OSError:
return
for child in children:
if not child.is_dir() or not is_candidate_dir(child):
continue
child_rel = (
rel_dir / child.name if rel_dir != Path(".") else Path(child.name)
)
if (child / ".git").exists():
found.append(child_rel.as_posix())
continue
scan(child_rel, depth + 1)
scan(Path("."), 0)
if len(found) < 2:
return []
return [(path.replace("/", "_"), path) for path in sorted(found)]
def _collect_package_git_info(
repo_root: Path,
discover_unconfigured: bool = False,
) -> list[dict]:
"""Collect Git status for independent package repositories.
Packages marked with ``git: true`` in config.yaml are authoritative.
When the Trellis root is not a Git repo and no configured package repos are
available, optionally fall back to the bounded polyrepo child scan.
Returns:
List of dicts with keys: name, path, branch, isClean,
uncommittedChanges, recentCommits.
Empty list if no git-repo packages are configured.
"""
git_pkgs = get_git_packages(repo_root)
result = []
for pkg_name, pkg_path in git_pkgs.items():
pkg_dir = repo_root / pkg_path
info = _collect_git_repo_info(pkg_name, pkg_path, pkg_dir)
if info is not None:
result.append(info)
if result or not discover_unconfigured:
return result
discovered = []
for pkg_name, pkg_path in _discover_child_git_repos(repo_root):
info = _collect_git_repo_info(pkg_name, pkg_path, repo_root / pkg_path)
if info is not None:
discovered.append(info)
return discovered
def _append_root_git_context(lines: list[str], root_git_info: dict) -> None:
"""Append root Git status without misleading non-Git roots."""
lines.append("## GIT STATUS")
if not root_git_info["isRepo"]:
lines.append("Root is not a Git repository.")
lines.append("Run Git commands from the package repository paths listed below.")
else:
lines.append(f"Branch: {root_git_info['branch']}")
if root_git_info["isClean"]:
lines.append("Working directory: Clean")
else:
lines.append(
f"Working directory: {root_git_info['uncommittedChanges']} "
"uncommitted change(s)"
)
lines.append("")
lines.append("Changes:")
for line in root_git_info.get("statusShort", [])[:10]:
lines.append(line)
lines.append("")
lines.append("## RECENT COMMITS")
if not root_git_info["isRepo"]:
lines.append(
"Root has no Git commit history because it is not a Git repository."
)
elif root_git_info["recentCommits"]:
for commit in root_git_info["recentCommits"]:
lines.append(f"{commit['hash']} {commit['message']}")
else:
lines.append("(no commits)")
lines.append("")
def _append_package_git_context(lines: list[str], package_git_info: list[dict]) -> None:
"""Append Git status and recent commits for package repositories."""
for pkg in package_git_info:
lines.append(f"## GIT STATUS ({pkg['name']}: {pkg['path']})")
lines.append(f"Branch: {pkg['branch']}")
if pkg["isClean"]:
lines.append("Working directory: Clean")
else:
lines.append(
f"Working directory: {pkg['uncommittedChanges']} uncommitted change(s)"
)
lines.append("")
lines.append(f"## RECENT COMMITS ({pkg['name']}: {pkg['path']})")
if pkg["recentCommits"]:
for commit in pkg["recentCommits"]:
lines.append(f"{commit['hash']} {commit['message']}")
else:
lines.append("(no commits)")
lines.append("")
def _read_project_version(repo_root: Path) -> str | None:
try:
version = (repo_root / DIR_WORKFLOW / ".version").read_text(
encoding="utf-8"
).strip()
except OSError:
return None
return version or None
def _fetch_trellis_version_output() -> str | None:
try:
result = subprocess.run(
["trellis", "--version"],
capture_output=True,
text=True,
encoding="utf-8",
errors="replace",
timeout=_UPDATE_CHECK_TIMEOUT_SECONDS,
)
except (OSError, subprocess.SubprocessError, TimeoutError):
return None
if result.returncode != 0:
return None
output = f"{result.stdout}\n{result.stderr}".strip()
return output or None
def _extract_available_update_version(output: str) -> str | None:
update_match = re.search(
r"Trellis update available:\s*"
r"(?P<current>\S+)\s*(?:→|->)\s*(?P<latest>\S+)",
output,
)
if update_match:
return update_match.group("latest").strip()
candidates = _VERSION_TOKEN_RE.findall(output)
return candidates[-1] if candidates else None
def _resolve_available_update_version() -> str | None:
output = _fetch_trellis_version_output()
if not output:
return None
return _extract_available_update_version(output)
def _parse_version(version: str) -> tuple[tuple[int, int, int], tuple[str, ...] | None] | None:
match = _VERSION_RE.match(version)
if not match:
return None
major, minor, patch, prerelease = match.groups()
numbers = (int(major), int(minor or "0"), int(patch or "0"))
prerelease_parts = tuple(prerelease.split(".")) if prerelease else None
return numbers, prerelease_parts
def _compare_prerelease(
left: tuple[str, ...] | None,
right: tuple[str, ...] | None,
) -> int:
if left is None and right is None:
return 0
if left is None:
return 1
if right is None:
return -1
for left_part, right_part in zip(left, right):
if left_part == right_part:
continue
left_numeric = left_part.isdigit()
right_numeric = right_part.isdigit()
if left_numeric and right_numeric:
left_int = int(left_part)
right_int = int(right_part)
return (left_int > right_int) - (left_int < right_int)
if left_numeric:
return -1
if right_numeric:
return 1
return (left_part > right_part) - (left_part < right_part)
return (len(left) > len(right)) - (len(left) < len(right))
def _compare_versions(left: str, right: str) -> int | None:
parsed_left = _parse_version(left)
parsed_right = _parse_version(right)
if parsed_left is None or parsed_right is None:
return None
left_numbers, left_prerelease = parsed_left
right_numbers, right_prerelease = parsed_right
if left_numbers != right_numbers:
return (left_numbers > right_numbers) - (left_numbers < right_numbers)
return _compare_prerelease(left_prerelease, right_prerelease)
def _update_marker_path(repo_root: Path) -> Path:
context_key = resolve_context_key()
if not context_key:
terminal_key = os.environ.get("TERM_SESSION_ID", "").strip()
context_key = terminal_key or f"ppid-{os.getppid()}"
safe_key = re.sub(r"[^A-Za-z0-9._-]+", "_", context_key).strip("._-")
if not safe_key:
safe_key = "session"
return (
repo_root
/ DIR_WORKFLOW
/ ".runtime"
/ f"update-check-{safe_key[:160]}.marker"
)
def _mark_update_check_attempted(repo_root: Path) -> bool:
marker_path = _update_marker_path(repo_root)
if marker_path.exists():
return False
try:
marker_path.parent.mkdir(parents=True, exist_ok=True)
marker_path.write_text("checked\n", encoding="utf-8")
except OSError:
pass
return True
def _get_update_hint(repo_root: Path) -> str | None:
marker_path = _update_marker_path(repo_root)
if marker_path.exists():
return None
current_version = _read_project_version(repo_root)
if not current_version:
return None
latest_version = _resolve_available_update_version()
if not latest_version:
return None
_mark_update_check_attempted(repo_root)
comparison = _compare_versions(current_version, latest_version)
if comparison is None or comparison >= 0:
return None
return (
f"Trellis update available: {current_version} -> {latest_version}, "
"run trellis upgrade"
)
# =============================================================================
# JSON Output
# =============================================================================
def get_context_json(repo_root: Path | None = None) -> dict:
"""Get context as a dictionary.
Args:
repo_root: Repository root path. Defaults to auto-detected.
Returns:
Context dictionary.
"""
if repo_root is None:
repo_root = get_repo_root()
developer = get_developer(repo_root)
tasks_dir = get_tasks_dir(repo_root)
journal_file = get_active_journal_file(repo_root)
journal_lines = 0
journal_relative = ""
if journal_file and developer:
journal_lines = count_lines(journal_file)
journal_relative = (
f"{DIR_WORKFLOW}/{DIR_WORKSPACE}/{developer}/{journal_file.name}"
)
root_git_info = _collect_root_git_info(repo_root)
# Tasks
tasks = [
{
"dir": t.dir_name,
"name": t.name,
"status": t.status,
"children": list(t.children),
"parent": t.parent,
}
for t in iter_active_tasks(tasks_dir)
]
# Package git repos (independent sub-repositories)
pkg_git_info = _collect_package_git_info(
repo_root,
discover_unconfigured=not root_git_info["isRepo"],
)
result = {
"developer": developer or "",
"git": {
"isRepo": root_git_info["isRepo"],
"branch": root_git_info["branch"],
"isClean": root_git_info["isClean"],
"uncommittedChanges": root_git_info["uncommittedChanges"],
"recentCommits": root_git_info["recentCommits"],
},
"tasks": {
"active": tasks,
"directory": f"{DIR_WORKFLOW}/{DIR_TASKS}",
},
"journal": {
"file": journal_relative,
"lines": journal_lines,
"nearLimit": journal_lines > 1800,
},
}
if pkg_git_info:
result["packageGit"] = pkg_git_info
return result
def output_json(repo_root: Path | None = None) -> None:
"""Output context in JSON format.
Args:
repo_root: Repository root path. Defaults to auto-detected.
"""
context = get_context_json(repo_root)
print(json.dumps(context, indent=2, ensure_ascii=False))
# =============================================================================
# Text Output
# =============================================================================
def get_context_text(repo_root: Path | None = None) -> str:
"""Get context as formatted text.
Args:
repo_root: Repository root path. Defaults to auto-detected.
Returns:
Formatted text output.
"""
if repo_root is None:
repo_root = get_repo_root()
lines = []
lines.append("========================================")
lines.append("SESSION CONTEXT")
lines.append("========================================")
lines.append("")
developer = get_developer(repo_root)
# Developer section
lines.append("## DEVELOPER")
if not developer:
lines.append(
f"ERROR: Not initialized. Run: python3 ./{DIR_WORKFLOW}/{DIR_SCRIPTS}/init_developer.py <name>"
)
return "\n".join(lines)
lines.append(f"Name: {developer}")
lines.append("")
root_git_info = _collect_root_git_info(repo_root)
_append_root_git_context(lines, root_git_info)
# Package git repos — independent sub-repositories
_append_package_git_context(
lines,
_collect_package_git_info(
repo_root,
discover_unconfigured=not root_git_info["isRepo"],
),
)
# Current task
lines.append("## CURRENT TASK")
current_task = get_current_task(repo_root)
if current_task:
current_task_dir = repo_root / current_task
source_type, context_key, _ = get_current_task_source(repo_root)
lines.append(f"Path: {current_task}")
lines.append(
f"Source: {source_type}" + (f":{context_key}" if context_key else "")
)
ct = load_task(current_task_dir)
if ct:
lines.append(f"Name: {ct.name}")
lines.append(f"Status: {ct.status}")
lines.append(f"Created: {ct.raw.get('createdAt', 'unknown')}")
if ct.description:
lines.append(f"Description: {ct.description}")
# Check for prd.md
prd_file = current_task_dir / "prd.md"
if prd_file.is_file():
lines.append("")
lines.append("[!] This task has prd.md - read it for task details")
else:
lines.append("(none)")
lines.append("")
# Active tasks
lines.append("## ACTIVE TASKS")
tasks_dir = get_tasks_dir(repo_root)
task_count = 0
# Collect all task data for hierarchy display
all_tasks = {t.dir_name: t for t in iter_active_tasks(tasks_dir)}
all_statuses = {name: t.status for name, t in all_tasks.items()}
def _print_task_tree(name: str, indent: int = 0) -> None:
nonlocal task_count
t = all_tasks[name]
progress = children_progress(t.children, all_statuses)
prefix = " " * indent
lines.append(f"{prefix}- {name}/ ({t.status}){progress} @{t.assignee or '-'}")
task_count += 1
for child in t.children:
if child in all_tasks:
_print_task_tree(child, indent + 1)
for dir_name in sorted(all_tasks.keys()):
if not all_tasks[dir_name].parent:
_print_task_tree(dir_name)
if task_count == 0:
lines.append("(no active tasks)")
lines.append(f"Total: {task_count} active task(s)")
lines.append("")
# My tasks
lines.append("## MY TASKS (Assigned to me)")
my_task_count = 0
for t in all_tasks.values():
if t.assignee == developer and t.status != "done":
progress = children_progress(t.children, all_statuses)
lines.append(f"- [{t.priority}] {t.title} ({t.status}){progress}")
my_task_count += 1
if my_task_count == 0:
lines.append("(no tasks assigned to you)")
lines.append("")
# Journal file
lines.append("## JOURNAL FILE")
journal_file = get_active_journal_file(repo_root)
if journal_file:
journal_lines = count_lines(journal_file)
relative = f"{DIR_WORKFLOW}/{DIR_WORKSPACE}/{developer}/{journal_file.name}"
lines.append(f"Active file: {relative}")
lines.append(f"Line count: {journal_lines} / 2000")
if journal_lines > 1800:
lines.append("[!] WARNING: Approaching 2000 line limit!")
else:
lines.append("No journal file found")
lines.append("")
# Packages
packages_text = get_packages_section(repo_root)
if packages_text:
lines.append(packages_text)
lines.append("")
# Paths
lines.append("## PATHS")
lines.append(f"Workspace: {DIR_WORKFLOW}/{DIR_WORKSPACE}/{developer}/")
lines.append(f"Tasks: {DIR_WORKFLOW}/{DIR_TASKS}/")
lines.append(f"Spec: {DIR_WORKFLOW}/{DIR_SPEC}/")
lines.append("")
lines.append("========================================")
return "\n".join(lines)
# =============================================================================
# Record Mode
# =============================================================================
def get_context_record_json(repo_root: Path | None = None) -> dict:
"""Get record-mode context as a dictionary.
Focused on: my active tasks, git status, current task.
"""
if repo_root is None:
repo_root = get_repo_root()
developer = get_developer(repo_root)
tasks_dir = get_tasks_dir(repo_root)
root_git_info = _collect_root_git_info(repo_root)
# My tasks (single pass — collect statuses and filter by assignee)
all_tasks_list = list(iter_active_tasks(tasks_dir))
all_statuses = {t.dir_name: t.status for t in all_tasks_list}
my_tasks = []
for t in all_tasks_list:
if t.assignee == developer:
done = sum(
1 for c in t.children
if all_statuses.get(c) in ("completed", "done")
)
my_tasks.append({
"dir": t.dir_name,
"title": t.title,
"status": t.status,
"priority": t.priority,
"children": list(t.children),
"childrenDone": done,
"parent": t.parent,
"meta": t.meta,
})
# Current task
current_task_info = None
current_task = get_current_task(repo_root)
if current_task:
source_type, context_key, _ = get_current_task_source(repo_root)
ct = load_task(repo_root / current_task)
if ct:
current_task_info = {
"path": current_task,
"name": ct.name,
"status": ct.status,
"source": source_type,
"contextKey": context_key,
}
# Package git repos
pkg_git_info = _collect_package_git_info(
repo_root,
discover_unconfigured=not root_git_info["isRepo"],
)
result = {
"developer": developer or "",
"git": {
"isRepo": root_git_info["isRepo"],
"branch": root_git_info["branch"],
"isClean": root_git_info["isClean"],
"uncommittedChanges": root_git_info["uncommittedChanges"],
"recentCommits": root_git_info["recentCommits"],
},
"myTasks": my_tasks,
"currentTask": current_task_info,
}
if pkg_git_info:
result["packageGit"] = pkg_git_info
return result
def get_context_text_record(repo_root: Path | None = None) -> str:
"""Get context as formatted text for record-session mode.
Focused output: MY ACTIVE TASKS first (with [!!!] emphasis),
then GIT STATUS, RECENT COMMITS, CURRENT TASK.
"""
if repo_root is None:
repo_root = get_repo_root()
lines: list[str] = []
lines.append("========================================")
lines.append("SESSION CONTEXT (RECORD MODE)")
lines.append("========================================")
lines.append("")
developer = get_developer(repo_root)
if not developer:
lines.append(
f"ERROR: Not initialized. Run: python3 ./{DIR_WORKFLOW}/{DIR_SCRIPTS}/init_developer.py <name>"
)
return "\n".join(lines)
# MY ACTIVE TASKS — first and prominent
lines.append(f"## [!!!] MY ACTIVE TASKS (Assigned to {developer})")
lines.append("[!] Review whether any should be archived before recording this session.")
lines.append("")
tasks_dir = get_tasks_dir(repo_root)
my_task_count = 0
# Single pass — collect all tasks and filter by assignee
all_statuses = get_all_statuses(tasks_dir)
for t in iter_active_tasks(tasks_dir):
if t.assignee == developer:
progress = children_progress(t.children, all_statuses)
lines.append(f"- [{t.priority}] {t.title} ({t.status}){progress} — {t.dir_name}")
my_task_count += 1
if my_task_count == 0:
lines.append("(no active tasks assigned to you)")
lines.append("")
root_git_info = _collect_root_git_info(repo_root)
_append_root_git_context(lines, root_git_info)
# Package git repos — independent sub-repositories
_append_package_git_context(
lines,
_collect_package_git_info(
repo_root,
discover_unconfigured=not root_git_info["isRepo"],
),
)
# CURRENT TASK
lines.append("## CURRENT TASK")
current_task = get_current_task(repo_root)
if current_task:
source_type, context_key, _ = get_current_task_source(repo_root)
lines.append(f"Path: {current_task}")
lines.append(
f"Source: {source_type}" + (f":{context_key}" if context_key else "")
)
ct = load_task(repo_root / current_task)
if ct:
lines.append(f"Name: {ct.name}")
lines.append(f"Status: {ct.status}")
else:
lines.append("(none)")
lines.append("")
lines.append("========================================")
return "\n".join(lines)
def output_text(repo_root: Path | None = None) -> None:
"""Output context in text format.
Args:
repo_root: Repository root path. Defaults to auto-detected.
"""
if repo_root is None:
repo_root = get_repo_root()
update_hint = _get_update_hint(repo_root)
if update_hint:
print(update_hint)
print("")
print(get_context_text(repo_root))
.trellis/scripts/common/task_context.py
Executable
+223
View File
@@ -0,0 +1,223 @@
#!/usr/bin/env python3
"""
Task JSONL context management.
Provides:
cmd_add_context - Add entry to JSONL context file
cmd_validate - Validate JSONL context files
cmd_list_context - List JSONL context entries
Note:
``cmd_init_context`` was removed in v0.5.0-beta.12. JSONL context files
are now seeded at ``task.py create`` time with a self-describing
``_example`` line; the AI agent curates real entries during planning when
the task needs sub-agent/spec context. See ``.trellis/workflow.md`` for the
current planning artifact contract.
"""
from __future__ import annotations
import argparse
import json
from pathlib import Path
from .log import Colors, colored
from .paths import get_repo_root
from .task_utils import resolve_task_dir
# =============================================================================
# Command: add-context
# =============================================================================
def cmd_add_context(args: argparse.Namespace) -> int:
"""Add entry to JSONL context file."""
repo_root = get_repo_root()
target_dir = resolve_task_dir(args.dir, repo_root)
jsonl_name = args.file
path = args.path
reason = args.reason or "Added manually"
if not target_dir.is_dir():
print(colored(f"Error: Directory not found: {target_dir}", Colors.RED))
return 1
# Support shorthand
if not jsonl_name.endswith(".jsonl"):
jsonl_name = f"{jsonl_name}.jsonl"
jsonl_file = target_dir / jsonl_name
full_path = repo_root / path
entry_type = "file"
if full_path.is_dir():
entry_type = "directory"
if not path.endswith("/"):
path = f"{path}/"
elif not full_path.is_file():
print(colored(f"Error: Path not found: {path}", Colors.RED))
return 1
# Check if already exists
if jsonl_file.is_file():
content = jsonl_file.read_text(encoding="utf-8")
if f'"{path}"' in content:
print(colored(f"Warning: Entry already exists for {path}", Colors.YELLOW))
return 0
# Add entry
entry: dict
if entry_type == "directory":
entry = {"file": path, "type": "directory", "reason": reason}
else:
entry = {"file": path, "reason": reason}
with jsonl_file.open("a", encoding="utf-8") as f:
f.write(json.dumps(entry, ensure_ascii=False) + "\n")
print(colored(f"Added {entry_type}: {path}", Colors.GREEN))
return 0
# =============================================================================
# Command: validate
# =============================================================================
def cmd_validate(args: argparse.Namespace) -> int:
"""Validate JSONL context files."""
repo_root = get_repo_root()
target_dir = resolve_task_dir(args.dir, repo_root)
if not target_dir.is_dir():
print(colored("Error: task directory required", Colors.RED))
return 1
print(colored("=== Validating Context Files ===", Colors.BLUE))
print(f"Target dir: {target_dir}")
print()
total_errors = 0
for jsonl_name in ["implement.jsonl", "check.jsonl"]:
jsonl_file = target_dir / jsonl_name
errors = _validate_jsonl(jsonl_file, repo_root)
total_errors += errors
print()
if total_errors == 0:
print(colored("✓ All validations passed", Colors.GREEN))
return 0
else:
print(colored(f"✗ Validation failed ({total_errors} errors)", Colors.RED))
return 1
def _validate_jsonl(jsonl_file: Path, repo_root: Path) -> int:
"""Validate a single JSONL file.
Seed rows (no ``file`` field — typically ``{"_example": "..."}``) are
skipped silently; they are self-describing comments, not real entries.
"""
file_name = jsonl_file.name
errors = 0
if not jsonl_file.is_file():
print(f" {colored(f'{file_name}: not found (skipped)', Colors.YELLOW)}")
return 0
line_num = 0
real_entries = 0
for line in jsonl_file.read_text(encoding="utf-8").splitlines():
line_num += 1
if not line.strip():
continue
try:
data = json.loads(line)
except json.JSONDecodeError:
print(f" {colored(f'{file_name}:{line_num}: Invalid JSON', Colors.RED)}")
errors += 1
continue
file_path = data.get("file")
entry_type = data.get("type", "file")
if not file_path:
# Seed / comment row — skip silently
continue
real_entries += 1
full_path = repo_root / file_path
if entry_type == "directory":
if not full_path.is_dir():
print(f" {colored(f'{file_name}:{line_num}: Directory not found: {file_path}', Colors.RED)}")
errors += 1
else:
if not full_path.is_file():
print(f" {colored(f'{file_name}:{line_num}: File not found: {file_path}', Colors.RED)}")
errors += 1
if errors == 0:
print(f" {colored(f'{file_name}: ✓ ({real_entries} entries)', Colors.GREEN)}")
else:
print(f" {colored(f'{file_name}: ✗ ({errors} errors)', Colors.RED)}")
return errors
# =============================================================================
# Command: list-context
# =============================================================================
def cmd_list_context(args: argparse.Namespace) -> int:
"""List JSONL context entries."""
repo_root = get_repo_root()
target_dir = resolve_task_dir(args.dir, repo_root)
if not target_dir.is_dir():
print(colored("Error: task directory required", Colors.RED))
return 1
print(colored("=== Context Files ===", Colors.BLUE))
print()
for jsonl_name in ["implement.jsonl", "check.jsonl"]:
jsonl_file = target_dir / jsonl_name
if not jsonl_file.is_file():
continue
print(colored(f"[{jsonl_name}]", Colors.CYAN))
count = 0
seed_only = True
for line in jsonl_file.read_text(encoding="utf-8").splitlines():
if not line.strip():
continue
try:
data = json.loads(line)
except json.JSONDecodeError:
continue
file_path = data.get("file")
if not file_path:
# Seed / comment row — don't count as a real entry
continue
seed_only = False
count += 1
entry_type = data.get("type", "file")
reason = data.get("reason", "-")
if entry_type == "directory":
print(f" {colored(f'{count}.', Colors.GREEN)} [DIR] {file_path}")
else:
print(f" {colored(f'{count}.', Colors.GREEN)} {file_path}")
print(f" {colored('→', Colors.YELLOW)} {reason}")
if seed_only:
print(f" {colored('(no curated entries yet — only seed row)', Colors.YELLOW)}")
print()
return 0
.trellis/scripts/common/task_queue.py
Executable
+188
View File
@@ -0,0 +1,188 @@
#!/usr/bin/env python3
"""
Task queue utility functions.
Provides:
list_tasks_by_status - List tasks by status
list_pending_tasks - List tasks with pending status
list_tasks_by_assignee - List tasks by assignee
list_my_tasks - List tasks assigned to current developer
get_task_stats - Get P0/P1/P2/P3 counts
"""
from __future__ import annotations
from pathlib import Path
from .paths import (
get_repo_root,
get_developer,
get_tasks_dir,
)
from .tasks import iter_active_tasks
# =============================================================================
# Internal helper
# =============================================================================
def _task_to_dict(t) -> dict:
"""Convert TaskInfo to the dict format callers expect."""
return {
"priority": t.priority,
"id": t.raw.get("id", ""),
"title": t.title,
"status": t.status,
"assignee": t.assignee or "-",
"dir": t.dir_name,
"children": list(t.children),
"parent": t.parent,
}
# =============================================================================
# Public Functions
# =============================================================================
def list_tasks_by_status(
filter_status: str | None = None,
repo_root: Path | None = None
) -> list[dict]:
"""List tasks by status.
Args:
filter_status: Optional status filter.
repo_root: Repository root path. Defaults to auto-detected.
Returns:
List of task info dicts with keys: priority, id, title, status, assignee.
"""
if repo_root is None:
repo_root = get_repo_root()
tasks_dir = get_tasks_dir(repo_root)
results = []
for t in iter_active_tasks(tasks_dir):
if filter_status and t.status != filter_status:
continue
results.append(_task_to_dict(t))
return results
def list_pending_tasks(repo_root: Path | None = None) -> list[dict]:
"""List pending tasks.
Args:
repo_root: Repository root path. Defaults to auto-detected.
Returns:
List of task info dicts.
"""
return list_tasks_by_status("planning", repo_root)
def list_tasks_by_assignee(
assignee: str,
filter_status: str | None = None,
repo_root: Path | None = None
) -> list[dict]:
"""List tasks assigned to a specific developer.
Args:
assignee: Developer name.
filter_status: Optional status filter.
repo_root: Repository root path. Defaults to auto-detected.
Returns:
List of task info dicts.
"""
if repo_root is None:
repo_root = get_repo_root()
tasks_dir = get_tasks_dir(repo_root)
results = []
for t in iter_active_tasks(tasks_dir):
if (t.assignee or "-") != assignee:
continue
if filter_status and t.status != filter_status:
continue
results.append(_task_to_dict(t))
return results
def list_my_tasks(
filter_status: str | None = None,
repo_root: Path | None = None
) -> list[dict]:
"""List tasks assigned to current developer.
Args:
filter_status: Optional status filter.
repo_root: Repository root path. Defaults to auto-detected.
Returns:
List of task info dicts.
Raises:
ValueError: If developer not set.
"""
if repo_root is None:
repo_root = get_repo_root()
developer = get_developer(repo_root)
if not developer:
raise ValueError("Developer not set")
return list_tasks_by_assignee(developer, filter_status, repo_root)
def get_task_stats(repo_root: Path | None = None) -> dict[str, int]:
"""Get task statistics.
Args:
repo_root: Repository root path. Defaults to auto-detected.
Returns:
Dict with keys: P0, P1, P2, P3, Total.
"""
if repo_root is None:
repo_root = get_repo_root()
tasks_dir = get_tasks_dir(repo_root)
stats = {"P0": 0, "P1": 0, "P2": 0, "P3": 0, "Total": 0}
for t in iter_active_tasks(tasks_dir):
if t.priority in stats:
stats[t.priority] += 1
stats["Total"] += 1
return stats
def format_task_stats(stats: dict[str, int]) -> str:
"""Format task stats as string.
Args:
stats: Stats dict from get_task_stats.
Returns:
Formatted string like "P0:0 P1:1 P2:2 P3:0 Total:3".
"""
return f"P0:{stats['P0']} P1:{stats['P1']} P2:{stats['P2']} P3:{stats['P3']} Total:{stats['Total']}"
# =============================================================================
# Main Entry (for testing)
# =============================================================================
if __name__ == "__main__":
stats = get_task_stats()
print(format_task_stats(stats))
print()
print("Pending tasks:")
for task in list_pending_tasks():
print(f" {task['priority']}|{task['id']}|{task['title']}|{task['status']}|{task['assignee']}")
.trellis/scripts/common/task_store.py
Executable
+746
View File
@@ -0,0 +1,746 @@
#!/usr/bin/env python3
"""
Task CRUD operations.
Provides:
ensure_tasks_dir - Ensure tasks directory exists
cmd_create - Create a new task
cmd_archive - Archive completed task
cmd_set_branch - Set git branch for task
cmd_set_base_branch - Set PR target branch
cmd_set_scope - Set scope for PR title
cmd_add_subtask - Link child task to parent
cmd_remove_subtask - Unlink child task from parent
"""
from __future__ import annotations
import argparse
import json
import re
import sys
from datetime import datetime
from pathlib import Path
from .config import (
get_packages,
get_session_auto_commit,
is_monorepo,
resolve_package,
validate_package,
)
from .git import run_git
from .io import read_json, write_json
from .log import Colors, colored
from .paths import (
DIR_ARCHIVE,
DIR_TASKS,
DIR_WORKFLOW,
FILE_TASK_JSON,
generate_task_date_prefix,
get_developer,
get_repo_root,
get_tasks_dir,
)
from .safe_commit import (
print_gitignore_warning,
safe_archive_paths_to_add,
safe_git_add,
)
from .task_utils import (
archive_task_complete,
find_task_by_name,
resolve_task_dir,
run_task_hooks,
)
# =============================================================================
# Helper Functions
# =============================================================================
def _slugify(title: str) -> str:
"""Convert title to slug (only works with ASCII)."""
result = title.lower()
result = re.sub(r"[^a-z0-9]", "-", result)
result = re.sub(r"-+", "-", result)
result = result.strip("-")
return result
def ensure_tasks_dir(repo_root: Path) -> Path:
"""Ensure tasks directory exists."""
tasks_dir = get_tasks_dir(repo_root)
archive_dir = tasks_dir / "archive"
if not tasks_dir.exists():
tasks_dir.mkdir(parents=True)
print(colored(f"Created tasks directory: {tasks_dir}", Colors.GREEN), file=sys.stderr)
if not archive_dir.exists():
archive_dir.mkdir(parents=True)
return tasks_dir
def _find_archived_task_by_dir_name(tasks_dir: Path, dir_name: str) -> Path | None:
"""Find an archived task directory with the exact active-task dir name."""
archive_dir = tasks_dir / DIR_ARCHIVE
if not archive_dir.is_dir():
return None
for month_dir in sorted(archive_dir.iterdir()):
if not month_dir.is_dir():
continue
candidate = month_dir / dir_name
if candidate.is_dir():
return candidate
return None
def _repo_relative_path(path: Path, repo_root: Path) -> str:
"""Format a path relative to the repo root when possible."""
try:
return path.relative_to(repo_root).as_posix()
except ValueError:
return str(path)
# =============================================================================
# Sub-agent platform detection + JSONL seeding
# =============================================================================
# Config directories of platforms that consume implement.jsonl / check.jsonl.
# Keep in sync with src/types/ai-tools.ts AI_TOOLS entries — these are the
# platforms listed in workflow.md's "agent-capable" Skill Routing block
# (Class-1 hook-inject + Class-2 pull-based preludes). Kilo / Antigravity /
# Devin are NOT in this list: they do not consume JSONL.
_SUBAGENT_CONFIG_DIRS: tuple[str, ...] = (
".claude",
".cursor",
".codex",
".kiro",
".gemini",
".opencode",
".qoder",
".codebuddy",
".factory", # Factory Droid
".github/copilot",
".pi", # Pi Agent
)
_SEED_EXAMPLE = (
"Fill with {\"file\": \"<path>\", \"reason\": \"<why>\"}. "
"Put spec/research files only — no code paths. "
"Run `python3 .trellis/scripts/get_context.py --mode packages` to list available specs. "
"Delete this line once real entries are added."
)
def _has_subagent_platform(repo_root: Path) -> bool:
"""Return True if any sub-agent-capable platform is configured.
Detected by probing well-known config directories at the repo root. Used
only to decide whether ``task.py create`` should seed empty
``implement.jsonl`` / ``check.jsonl`` files.
"""
for config_dir in _SUBAGENT_CONFIG_DIRS:
if (repo_root / config_dir).is_dir():
return True
return False
def _write_seed_jsonl(path: Path) -> None:
"""Write a one-line seed JSONL file with a self-describing ``_example``.
The seed row has no ``file`` field, so downstream consumers (hooks +
preludes) that iterate entries via ``item.get("file")`` naturally skip
it. The row exists purely as an in-file prompt for the AI curator.
"""
seed = {"_example": _SEED_EXAMPLE}
path.write_text(json.dumps(seed, ensure_ascii=False) + "\n", encoding="utf-8")
def _default_prd_content(title: str, description: str | None = None) -> str:
"""Return the default PRD skeleton created with every task."""
goal = (description or "").strip() or "TBD."
heading = title.strip() or "Untitled task"
return f"""# {heading}
## Goal
{goal}
## Requirements
- TBD
## Acceptance Criteria
- [ ] TBD
## Notes
- Keep `prd.md` focused on requirements, constraints, and acceptance criteria.
- Lightweight tasks can remain PRD-only.
- For complex tasks, add `design.md` for technical design and `implement.md` for execution planning before `task.py start`.
"""
# =============================================================================
# Command: create
# =============================================================================
def cmd_create(args: argparse.Namespace) -> int:
"""Create a new task."""
repo_root = get_repo_root()
if not args.title:
print(colored("Error: title is required", Colors.RED), file=sys.stderr)
return 1
# Validate --package (CLI source: fail-fast)
package: str | None = getattr(args, "package", None)
if not is_monorepo(repo_root):
# Single-repo: ignore --package, no package prefix
if package:
print(colored(f"Warning: --package ignored in single-repo project", Colors.YELLOW), file=sys.stderr)
package = None
elif package:
if not validate_package(package, repo_root):
packages = get_packages(repo_root)
available = ", ".join(sorted(packages.keys())) if packages else "(none)"
print(colored(f"Error: unknown package '{package}'. Available: {available}", Colors.RED), file=sys.stderr)
return 1
else:
# Inferred: default_package → None (no task.json yet for create)
package = resolve_package(repo_root=repo_root)
# Default assignee to current developer
assignee = args.assignee
if not assignee:
assignee = get_developer(repo_root)
if not assignee:
print(colored("Error: No developer set. Run init_developer.py first or use --assignee", Colors.RED), file=sys.stderr)
return 1
ensure_tasks_dir(repo_root)
# Get current developer as creator
creator = get_developer(repo_root) or assignee
# Generate slug if not provided
slug = args.slug or _slugify(args.title)
if not slug:
print(colored("Error: could not generate slug from title", Colors.RED), file=sys.stderr)
return 1
# Create task directory with MM-DD-slug format
tasks_dir = get_tasks_dir(repo_root)
date_prefix = generate_task_date_prefix()
dir_name = f"{date_prefix}-{slug}"
task_dir = tasks_dir / dir_name
task_json_path = task_dir / FILE_TASK_JSON
archived_task_dir = _find_archived_task_by_dir_name(tasks_dir, dir_name)
if archived_task_dir:
print(colored(f"Error: Task already archived: {dir_name}", Colors.RED), file=sys.stderr)
print(f"Archived at: {_repo_relative_path(archived_task_dir, repo_root)}", file=sys.stderr)
print("Use a new slug if you intend to create a new task.", file=sys.stderr)
return 1
if task_dir.exists():
print(colored(f"Warning: Task directory already exists: {dir_name}", Colors.YELLOW), file=sys.stderr)
else:
task_dir.mkdir(parents=True)
today = datetime.now().strftime("%Y-%m-%d")
# Record current branch as base_branch (PR target)
_, branch_out, _ = run_git(["branch", "--show-current"], cwd=repo_root)
current_branch = branch_out.strip() or "main"
task_data = {
"id": slug,
"name": slug,
"title": args.title,
"description": args.description or "",
"status": "planning",
"dev_type": None,
"scope": None,
"package": package,
"priority": args.priority,
"creator": creator,
"assignee": assignee,
"createdAt": today,
"completedAt": None,
"branch": None,
"base_branch": current_branch,
"worktree_path": None,
"commit": None,
"pr_url": None,
"subtasks": [],
"children": [],
"parent": None,
"relatedFiles": [],
"notes": "",
"meta": {},
}
write_json(task_json_path, task_data)
prd_path = task_dir / "prd.md"
if not prd_path.exists():
prd_path.write_text(
_default_prd_content(args.title, args.description),
encoding="utf-8",
)
# Seed implement.jsonl / check.jsonl for sub-agent-capable platforms.
# Agent curates real entries during planning when the task needs them.
# Agent-less platforms (Kilo / Antigravity / Devin) skip this — they
# load specs via the trellis-before-dev skill instead of JSONL.
seeded_jsonl = False
if _has_subagent_platform(repo_root):
for jsonl_name in ("implement.jsonl", "check.jsonl"):
jsonl_path = task_dir / jsonl_name
if not jsonl_path.exists():
_write_seed_jsonl(jsonl_path)
seeded_jsonl = True
# Handle --parent: establish bidirectional link
if args.parent:
parent_dir = resolve_task_dir(args.parent, repo_root)
parent_json_path = parent_dir / FILE_TASK_JSON
if not parent_json_path.is_file():
print(colored(f"Warning: Parent task.json not found: {args.parent}", Colors.YELLOW), file=sys.stderr)
else:
parent_data = read_json(parent_json_path)
if parent_data:
# Add child to parent's children list
parent_children = parent_data.get("children", [])
if dir_name not in parent_children:
parent_children.append(dir_name)
parent_data["children"] = parent_children
write_json(parent_json_path, parent_data)
# Set parent in child's task.json
task_data["parent"] = parent_dir.name
write_json(task_json_path, task_data)
print(colored(f"Linked as child of: {parent_dir.name}", Colors.GREEN), file=sys.stderr)
# Auto-activate the new task so the per-turn breadcrumb fires planning
# state. Best-effort: gracefully degrade if no session identity (CLI run
# outside an AI session) — the task is still created, the user can run
# task.py start later. Pointer is session-scoped so this never affects
# other AI sessions.
try:
from .active_task import resolve_context_key, set_active_task
if resolve_context_key():
try:
rel_dir = task_dir.relative_to(repo_root).as_posix()
except ValueError:
rel_dir = str(task_dir)
set_active_task(rel_dir, repo_root)
except Exception:
pass
print(colored(f"Created task: {dir_name}", Colors.GREEN), file=sys.stderr)
print("", file=sys.stderr)
print(colored("Next steps:", Colors.BLUE), file=sys.stderr)
print(" - Fill prd.md with requirements and acceptance criteria", file=sys.stderr)
print(" - Lightweight task: PRD-only is valid", file=sys.stderr)
print(" - Complex task: add design.md and implement.md before task.py start", file=sys.stderr)
if seeded_jsonl:
print(
" - Curate implement.jsonl / check.jsonl as spec/research manifests when sub-agents need context",
file=sys.stderr,
)
print(" - Use /trellis:continue or phase context to decide the next step", file=sys.stderr)
print("", file=sys.stderr)
# Output relative path for script chaining
print(f"{DIR_WORKFLOW}/{DIR_TASKS}/{dir_name}")
run_task_hooks("after_create", task_json_path, repo_root)
return 0
# =============================================================================
# Command: archive
# =============================================================================
def cmd_archive(args: argparse.Namespace) -> int:
"""Archive completed task."""
repo_root = get_repo_root()
task_name = args.name
if not task_name:
print(colored("Error: Task name is required", Colors.RED), file=sys.stderr)
return 1
tasks_dir = get_tasks_dir(repo_root)
# Resolve task directory (supports task name, relative path, or absolute path)
task_dir = resolve_task_dir(task_name, repo_root)
if not task_dir or not task_dir.is_dir():
print(colored(f"Error: Task not found: {task_name}", Colors.RED), file=sys.stderr)
print("Active tasks:", file=sys.stderr)
# Import lazily to avoid circular dependency
from .tasks import iter_active_tasks
for t in iter_active_tasks(tasks_dir):
print(f" - {t.dir_name}/", file=sys.stderr)
return 1
dir_name = task_dir.name
task_json_path = task_dir / FILE_TASK_JSON
# Update status before archiving
today = datetime.now().strftime("%Y-%m-%d")
# Names of child task dirs whose task.json gets modified below; passed
# into safe_archive_paths_to_add so they're staged in this commit.
modified_children: list[str] = []
if task_json_path.is_file():
data = read_json(task_json_path)
if data:
data["status"] = "completed"
data["completedAt"] = today
write_json(task_json_path, data)
# Handle subtask relationships on archive.
# Keep this task in its parent's children list so progress
# counters (children_progress) stay consistent — children
# missing from the active set are treated as completed.
task_children = data.get("children", [])
# If this is a parent, clear parent field in all children
if task_children:
for child_name in task_children:
child_dir_path = find_task_by_name(child_name, tasks_dir)
if child_dir_path:
child_json = child_dir_path / FILE_TASK_JSON
if child_json.is_file():
child_data = read_json(child_json)
if child_data:
child_data["parent"] = None
write_json(child_json, child_data)
modified_children.append(child_dir_path.name)
# Clear any session that still points at this task before the path moves.
from .active_task import clear_task_from_sessions
clear_task_from_sessions(str(task_dir), repo_root)
# Archive
result = archive_task_complete(task_dir, repo_root)
if "archived_to" in result:
archive_dest = Path(result["archived_to"])
year_month = archive_dest.parent.name
print(colored(f"Archived: {dir_name} -> archive/{year_month}/", Colors.GREEN), file=sys.stderr)
# Auto-commit unless --no-commit
if not getattr(args, "no_commit", False):
if not _auto_commit_archive(dir_name, repo_root, modified_children):
print(
colored(
"Archive moved on disk, but git auto-commit did not complete. "
"Resolve `git status` before continuing.",
Colors.RED,
),
file=sys.stderr,
)
return 1
# Return the archive path
print(f"{DIR_WORKFLOW}/{DIR_TASKS}/{DIR_ARCHIVE}/{year_month}/{dir_name}")
# Run hooks with the archived path
archived_json = archive_dest / FILE_TASK_JSON
run_task_hooks("after_archive", archived_json, repo_root)
return 0
return 1
def _auto_commit_archive(
task_name: str,
repo_root: Path,
modified_children: list[str] | None = None,
) -> bool:
"""Stage Trellis-owned task paths and commit after archive.
Scoped narrowly to the archived task's source + destination paths
plus any child task dirs whose ``task.json`` was edited (parent →
children relationship update). Dirty changes in OTHER active task
dirs are NOT bundled into the archive commit.
If ``.gitignore`` blocks the paths, we warn + skip — we do NOT
retry with ``git add -f``. The warning explicitly forbids
``git add -f .trellis/`` (which would fan out to caches/backups)
and points users at ``session_auto_commit: false``.
Honors ``session_auto_commit`` in ``.trellis/config.yaml``: when
set to ``false``, this function returns immediately without
touching git (the archive directory move on disk is unaffected).
"""
if not get_session_auto_commit(repo_root):
print(
"[OK] session_auto_commit: false — skipping git stage/commit.",
file=sys.stderr,
)
return True
source_rel = f"{DIR_WORKFLOW}/{DIR_TASKS}/{task_name}"
rc, tracked_out, _ = run_git(
["ls-files", "--", source_rel],
cwd=repo_root,
)
source_was_tracked = rc == 0 and bool(tracked_out.strip())
paths = safe_archive_paths_to_add(
repo_root, task_name=task_name, modified_children=modified_children
)
if not paths:
print("[OK] No task changes to commit.", file=sys.stderr)
return True
success, _, err = safe_git_add(paths, repo_root)
if not success:
if err and "ignored by" in err.lower():
print_gitignore_warning(paths)
else:
print(
f"[WARN] git add failed: {err.strip() if err else 'unknown error'}",
file=sys.stderr,
)
return not source_was_tracked
# Belt-and-suspenders for the phantom-delete bug: `safe_git_add` uses
# `git add` (no -A) which only stages additions/modifications. The
# source task directory was moved away by `shutil.move`, so its files
# need an explicit `git rm --cached` to stage the deletions in this
# same commit — otherwise they sit as uncommitted "phantom deletes"
# against HEAD until something later picks them up.
#
# `--ignore-unmatch` makes this a no-op when the task was never tracked
# (e.g. archiving a task that lived only in working tree).
run_git(
["rm", "-r", "--cached", "--ignore-unmatch", "--", source_rel],
cwd=repo_root,
)
rc, _, _ = run_git(
["diff", "--cached", "--quiet", "--", *paths, source_rel],
cwd=repo_root,
)
if rc == 0:
print("[OK] No task changes to commit.", file=sys.stderr)
return True
commit_msg = f"chore(task): archive {task_name}"
rc, _, err = run_git(["commit", "-m", commit_msg], cwd=repo_root)
if rc == 0:
print(f"[OK] Auto-committed: {commit_msg}", file=sys.stderr)
return True
else:
print(f"[WARN] Auto-commit failed: {err.strip()}", file=sys.stderr)
return not source_was_tracked
# =============================================================================
# Command: add-subtask
# =============================================================================
def cmd_add_subtask(args: argparse.Namespace) -> int:
"""Link a child task to a parent task."""
repo_root = get_repo_root()
parent_dir = resolve_task_dir(args.parent_dir, repo_root)
child_dir = resolve_task_dir(args.child_dir, repo_root)
parent_json_path = parent_dir / FILE_TASK_JSON
child_json_path = child_dir / FILE_TASK_JSON
if not parent_json_path.is_file():
print(colored(f"Error: Parent task.json not found: {args.parent_dir}", Colors.RED), file=sys.stderr)
return 1
if not child_json_path.is_file():
print(colored(f"Error: Child task.json not found: {args.child_dir}", Colors.RED), file=sys.stderr)
return 1
parent_data = read_json(parent_json_path)
child_data = read_json(child_json_path)
if not parent_data or not child_data:
print(colored("Error: Failed to read task.json", Colors.RED), file=sys.stderr)
return 1
# Check if child already has a parent
existing_parent = child_data.get("parent")
if existing_parent:
print(colored(f"Error: Child task already has a parent: {existing_parent}", Colors.RED), file=sys.stderr)
return 1
# Add child to parent's children list
parent_children = parent_data.get("children", [])
child_dir_name = child_dir.name
if child_dir_name not in parent_children:
parent_children.append(child_dir_name)
parent_data["children"] = parent_children
# Set parent in child's task.json
child_data["parent"] = parent_dir.name
# Write both
write_json(parent_json_path, parent_data)
write_json(child_json_path, child_data)
print(colored(f"Linked: {child_dir.name} -> {parent_dir.name}", Colors.GREEN), file=sys.stderr)
return 0
# =============================================================================
# Command: remove-subtask
# =============================================================================
def cmd_remove_subtask(args: argparse.Namespace) -> int:
"""Unlink a child task from a parent task."""
repo_root = get_repo_root()
parent_dir = resolve_task_dir(args.parent_dir, repo_root)
child_dir = resolve_task_dir(args.child_dir, repo_root)
parent_json_path = parent_dir / FILE_TASK_JSON
child_json_path = child_dir / FILE_TASK_JSON
if not parent_json_path.is_file():
print(colored(f"Error: Parent task.json not found: {args.parent_dir}", Colors.RED), file=sys.stderr)
return 1
if not child_json_path.is_file():
print(colored(f"Error: Child task.json not found: {args.child_dir}", Colors.RED), file=sys.stderr)
return 1
parent_data = read_json(parent_json_path)
child_data = read_json(child_json_path)
if not parent_data or not child_data:
print(colored("Error: Failed to read task.json", Colors.RED), file=sys.stderr)
return 1
# Remove child from parent's children list
parent_children = parent_data.get("children", [])
child_dir_name = child_dir.name
if child_dir_name in parent_children:
parent_children.remove(child_dir_name)
parent_data["children"] = parent_children
# Clear parent in child's task.json
child_data["parent"] = None
# Write both
write_json(parent_json_path, parent_data)
write_json(child_json_path, child_data)
print(colored(f"Unlinked: {child_dir.name} from {parent_dir.name}", Colors.GREEN), file=sys.stderr)
return 0
# =============================================================================
# Command: set-branch
# =============================================================================
def cmd_set_branch(args: argparse.Namespace) -> int:
"""Set git branch for task."""
repo_root = get_repo_root()
target_dir = resolve_task_dir(args.dir, repo_root)
branch = args.branch
if not branch:
print(colored("Error: Missing arguments", Colors.RED))
print("Usage: python3 task.py set-branch <task-dir> <branch-name>")
return 1
task_json = target_dir / FILE_TASK_JSON
if not task_json.is_file():
print(colored(f"Error: task.json not found at {target_dir}", Colors.RED))
return 1
data = read_json(task_json)
if not data:
return 1
data["branch"] = branch
write_json(task_json, data)
print(colored(f"✓ Branch set to: {branch}", Colors.GREEN))
return 0
# =============================================================================
# Command: set-base-branch
# =============================================================================
def cmd_set_base_branch(args: argparse.Namespace) -> int:
"""Set the base branch (PR target) for task."""
repo_root = get_repo_root()
target_dir = resolve_task_dir(args.dir, repo_root)
base_branch = args.base_branch
if not base_branch:
print(colored("Error: Missing arguments", Colors.RED))
print("Usage: python3 task.py set-base-branch <task-dir> <base-branch>")
print("Example: python3 task.py set-base-branch <dir> develop")
print()
print("This sets the target branch for PR (the branch your feature will merge into).")
return 1
task_json = target_dir / FILE_TASK_JSON
if not task_json.is_file():
print(colored(f"Error: task.json not found at {target_dir}", Colors.RED))
return 1
data = read_json(task_json)
if not data:
return 1
data["base_branch"] = base_branch
write_json(task_json, data)
print(colored(f"✓ Base branch set to: {base_branch}", Colors.GREEN))
print(f" PR will target: {base_branch}")
return 0
# =============================================================================
# Command: set-scope
# =============================================================================
def cmd_set_scope(args: argparse.Namespace) -> int:
"""Set scope for PR title."""
repo_root = get_repo_root()
target_dir = resolve_task_dir(args.dir, repo_root)
scope = args.scope
if not scope:
print(colored("Error: Missing arguments", Colors.RED))
print("Usage: python3 task.py set-scope <task-dir> <scope>")
return 1
task_json = target_dir / FILE_TASK_JSON
if not task_json.is_file():
print(colored(f"Error: task.json not found at {target_dir}", Colors.RED))
return 1
data = read_json(task_json)
if not data:
return 1
data["scope"] = scope
write_json(task_json, data)
print(colored(f"✓ Scope set to: {scope}", Colors.GREEN))
return 0
.trellis/scripts/common/task_utils.py
Executable
+274
View File
@@ -0,0 +1,274 @@
#!/usr/bin/env python3
"""
Task utility functions.
Provides:
is_safe_task_path - Validate task path is safe to operate on
find_task_by_name - Find task directory by name
resolve_task_dir - Resolve task directory from name, relative, or absolute path
archive_task_dir - Archive task to monthly directory
run_task_hooks - Run lifecycle hooks for task events
"""
from __future__ import annotations
import shutil
import sys
from datetime import datetime
from pathlib import Path
from .paths import get_repo_root, get_tasks_dir
# =============================================================================
# Path Safety
# =============================================================================
def is_safe_task_path(task_path: str, repo_root: Path | None = None) -> bool:
"""Check if a relative task path is safe to operate on.
Args:
task_path: Task path (relative to repo_root).
repo_root: Repository root path. Defaults to auto-detected.
Returns:
True if safe, False if dangerous.
"""
if repo_root is None:
repo_root = get_repo_root()
normalized = task_path.replace("\\", "/")
# Check empty or null
if not normalized or normalized == "null":
print("Error: empty or null task path", file=sys.stderr)
return False
# Reject absolute paths
if Path(task_path).is_absolute():
print(f"Error: absolute path not allowed: {task_path}", file=sys.stderr)
return False
# Reject ".", "..", paths starting with "./" or "../", or containing ".."
if normalized in (".", "..") or normalized.startswith("./") or normalized.startswith("../") or ".." in normalized:
print(f"Error: path traversal not allowed: {task_path}", file=sys.stderr)
return False
# Final check: ensure resolved path is not the repo root
abs_path = repo_root / Path(normalized)
if abs_path.exists():
try:
resolved = abs_path.resolve()
root_resolved = repo_root.resolve()
if resolved == root_resolved:
print(f"Error: path resolves to repo root: {task_path}", file=sys.stderr)
return False
except (OSError, IOError):
pass
return True
# =============================================================================
# Task Lookup
# =============================================================================
def find_task_by_name(task_name: str, tasks_dir: Path) -> Path | None:
"""Find task directory by name (exact or suffix match).
Args:
task_name: Task name to find.
tasks_dir: Tasks directory path.
Returns:
Absolute path to task directory, or None if not found.
"""
if not task_name or not tasks_dir or not tasks_dir.is_dir():
return None
# Try exact match first
exact_match = tasks_dir / task_name
if exact_match.is_dir():
return exact_match
# Try suffix match (e.g., "my-task" matches "01-21-my-task")
for d in tasks_dir.iterdir():
if d.is_dir() and d.name.endswith(f"-{task_name}"):
return d
return None
# =============================================================================
# Archive Operations
# =============================================================================
def archive_task_dir(task_dir_abs: Path, repo_root: Path | None = None) -> Path | None:
"""Archive a task directory to archive/{YYYY-MM}/.
Args:
task_dir_abs: Absolute path to task directory.
repo_root: Repository root path. Defaults to auto-detected.
Returns:
Path to archived directory, or None on error.
"""
if not task_dir_abs.is_dir():
print(f"Error: task directory not found: {task_dir_abs}", file=sys.stderr)
return None
# Get tasks directory (parent of the task)
tasks_dir = task_dir_abs.parent
archive_dir = tasks_dir / "archive"
year_month = datetime.now().strftime("%Y-%m")
month_dir = archive_dir / year_month
# Create archive directory
try:
month_dir.mkdir(parents=True, exist_ok=True)
except (OSError, IOError) as e:
print(f"Error: Failed to create archive directory: {e}", file=sys.stderr)
return None
# Move task to archive
task_name = task_dir_abs.name
dest = month_dir / task_name
try:
shutil.move(str(task_dir_abs), str(dest))
except (OSError, IOError, shutil.Error) as e:
print(f"Error: Failed to move task to archive: {e}", file=sys.stderr)
return None
return dest
def archive_task_complete(
task_dir_abs: Path,
repo_root: Path | None = None
) -> dict[str, str]:
"""Complete archive workflow: archive directory.
Args:
task_dir_abs: Absolute path to task directory.
repo_root: Repository root path. Defaults to auto-detected.
Returns:
Dict with archive result info.
"""
if not task_dir_abs.is_dir():
print(f"Error: task directory not found: {task_dir_abs}", file=sys.stderr)
return {}
archive_dest = archive_task_dir(task_dir_abs, repo_root)
if archive_dest:
return {"archived_to": str(archive_dest)}
return {}
# =============================================================================
# Task Directory Resolution
# =============================================================================
def resolve_task_dir(target_dir: str, repo_root: Path) -> Path:
"""Resolve task directory to absolute path.
Supports:
- Absolute path: /path/to/task
- Relative path: .trellis/tasks/01-31-my-task
- Task name: my-task (uses find_task_by_name for lookup)
Args:
target_dir: Task directory specification.
repo_root: Repository root path.
Returns:
Resolved absolute path.
"""
if not target_dir:
return Path()
normalized = target_dir.replace("\\", "/")
while normalized.startswith("./"):
normalized = normalized[2:]
# Absolute path
if Path(target_dir).is_absolute():
return Path(target_dir)
# Relative path (contains path separator or starts with .trellis)
if "/" in normalized or normalized.startswith(".trellis"):
return repo_root / Path(normalized)
# Task name - try to find in tasks directory
tasks_dir = get_tasks_dir(repo_root)
found = find_task_by_name(target_dir, tasks_dir)
if found:
return found
# Fallback to treating as relative path
return repo_root / Path(normalized)
# =============================================================================
# Lifecycle Hooks
# =============================================================================
def run_task_hooks(event: str, task_json_path: Path, repo_root: Path) -> None:
"""Run lifecycle hooks for a task event.
Args:
event: Event name (e.g. "after_create").
task_json_path: Absolute path to the task's task.json.
repo_root: Repository root for cwd and config lookup.
"""
import os
import subprocess
from .config import get_hooks
from .log import Colors, colored
commands = get_hooks(event, repo_root)
if not commands:
return
env = {**os.environ, "TASK_JSON_PATH": str(task_json_path)}
for cmd in commands:
try:
result = subprocess.run(
cmd,
shell=True,
cwd=repo_root,
env=env,
capture_output=True,
text=True,
encoding="utf-8",
errors="replace",
)
if result.returncode != 0:
print(
colored(f"[WARN] Hook failed ({event}): {cmd}", Colors.YELLOW),
file=sys.stderr,
)
if result.stderr.strip():
print(f" {result.stderr.strip()}", file=sys.stderr)
except Exception as e:
print(
colored(f"[WARN] Hook error ({event}): {cmd} — {e}", Colors.YELLOW),
file=sys.stderr,
)
# =============================================================================
# Main Entry (for testing)
# =============================================================================
if __name__ == "__main__":
repo = get_repo_root()
tasks = get_tasks_dir(repo)
print(f"Tasks dir: {tasks}")
print(f"is_safe_task_path('.trellis/tasks/test'): {is_safe_task_path('.trellis/tasks/test', repo)}")
print(f"is_safe_task_path('../test'): {is_safe_task_path('../test', repo)}")
.trellis/scripts/common/tasks.py
Executable
+112
View File
@@ -0,0 +1,112 @@
"""
Task data access layer.
Single source of truth for loading and iterating task directories.
Replaces scattered task.json parsing across 9+ files.
Provides:
load_task — Load a single task by directory path
iter_active_tasks — Iterate all non-archived tasks (sorted)
get_all_statuses — Get {dir_name: status} map for children progress
"""
from __future__ import annotations
from collections.abc import Iterator
from pathlib import Path
from .io import read_json
from .paths import FILE_TASK_JSON
from .types import TaskInfo
def load_task(task_dir: Path) -> TaskInfo | None:
"""Load task from a directory containing task.json.
Args:
task_dir: Absolute path to the task directory.
Returns:
TaskInfo if task.json exists and is valid, None otherwise.
"""
task_json = task_dir / FILE_TASK_JSON
if not task_json.is_file():
return None
data = read_json(task_json)
if not data:
return None
return TaskInfo(
dir_name=task_dir.name,
directory=task_dir,
title=data.get("title") or data.get("name") or "unknown",
status=data.get("status", "unknown"),
assignee=data.get("assignee", ""),
priority=data.get("priority", "P2"),
children=tuple(data.get("children", [])),
parent=data.get("parent"),
package=data.get("package"),
raw=data,
)
def iter_active_tasks(tasks_dir: Path) -> Iterator[TaskInfo]:
"""Iterate all active (non-archived) tasks, sorted by directory name.
Skips the "archive" directory and directories without valid task.json.
Args:
tasks_dir: Path to the tasks directory.
Yields:
TaskInfo for each valid task.
"""
if not tasks_dir.is_dir():
return
for d in sorted(tasks_dir.iterdir()):
if not d.is_dir() or d.name == "archive":
continue
info = load_task(d)
if info is not None:
yield info
def get_all_statuses(tasks_dir: Path) -> dict[str, str]:
"""Get a {dir_name: status} mapping for all active tasks.
Useful for computing children progress without loading full TaskInfo.
Args:
tasks_dir: Path to the tasks directory.
Returns:
Dict mapping directory names to status strings.
"""
return {t.dir_name: t.status for t in iter_active_tasks(tasks_dir)}
def children_progress(
children: tuple[str, ...] | list[str],
all_statuses: dict[str, str],
) -> str:
"""Format children progress string like " [2/3 done]".
Args:
children: List of child directory names.
all_statuses: Status map from get_all_statuses().
Returns:
Formatted string, or "" if no children.
"""
if not children:
return ""
# A child missing from active statuses has been archived (cmd_archive
# sets status=completed before moving the dir). Count it as done so
# parent progress doesn't regress when children are archived.
done = sum(
1 for c in children
if c not in all_statuses or all_statuses.get(c) in ("completed", "done")
)
return f" [{done}/{len(children)} done]"
.trellis/scripts/common/trellis_config.py
Executable
+131
View File
@@ -0,0 +1,131 @@
#!/usr/bin/env python3
"""
Standalone reader for .trellis/config.yaml.
Mirrors a minimal subset of common.config so callers (hooks, workflow_phase)
can read configuration without importing the full task/repo helpers. Returns
an empty dict on missing/malformed files so callers stay simple.
"""
from __future__ import annotations
from pathlib import Path
from typing import Optional
CONFIG_REL_PATH = ".trellis/config.yaml"
def _unquote(value: str) -> str:
if len(value) >= 2 and value[0] == value[-1] and value[0] in ('"', "'"):
return value[1:-1]
return value
def _strip_inline_comment(value: str) -> str:
"""Strip ` # …` inline comments while preserving `#` inside quoted strings.
YAML treats ` #` (space-hash) as a comment opener; bare `#` inside a token
is part of the value. Quoted strings are immune.
"""
in_quote: str | None = None
for idx, ch in enumerate(value):
if in_quote:
if ch == in_quote:
in_quote = None
continue
if ch in ('"', "'"):
in_quote = ch
continue
if ch == "#" and (idx == 0 or value[idx - 1].isspace()):
return value[:idx]
return value
def _next_content_line(lines: list[str], start: int) -> tuple[int, str]:
i = start
while i < len(lines):
stripped = lines[i].strip()
if stripped and not stripped.startswith("#"):
return i, lines[i]
i += 1
return i, ""
def _parse_yaml_block(
lines: list[str], start: int, min_indent: int, target: dict
) -> int:
i = start
current_list: list | None = None
while i < len(lines):
line = lines[i]
stripped = line.strip()
if not stripped or stripped.startswith("#"):
i += 1
continue
indent = len(line) - len(line.lstrip())
if indent < min_indent:
break
if stripped.startswith("- "):
if current_list is not None:
current_list.append(_unquote(stripped[2:].strip()))
i += 1
elif ":" in stripped:
key, _, value = stripped.partition(":")
key = key.strip()
value = _strip_inline_comment(value).strip()
value = _unquote(value)
current_list = None
if value:
target[key] = value
i += 1
else:
next_i, next_line = _next_content_line(lines, i + 1)
if next_i >= len(lines):
target[key] = {}
i = next_i
elif next_line.strip().startswith("- "):
current_list = []
target[key] = current_list
i += 1
else:
next_indent = len(next_line) - len(next_line.lstrip())
if next_indent > indent:
nested: dict = {}
target[key] = nested
i = _parse_yaml_block(lines, i + 1, next_indent, nested)
else:
target[key] = {}
i += 1
else:
i += 1
return i
def parse_simple_yaml(content: str) -> dict:
"""Parse a small subset of YAML. See common.config for full doc."""
lines = content.splitlines()
result: dict = {}
_parse_yaml_block(lines, 0, 0, result)
return result
def read_trellis_config(repo_root: Optional[Path] = None) -> dict:
"""Read .trellis/config.yaml. Returns {} on missing or malformed file."""
root = repo_root or Path.cwd()
config_file = root / CONFIG_REL_PATH
try:
content = config_file.read_text(encoding="utf-8")
except (FileNotFoundError, OSError):
return {}
try:
parsed = parse_simple_yaml(content)
except Exception:
return {}
return parsed if isinstance(parsed, dict) else {}
.trellis/scripts/common/types.py
Executable
+110
View File
@@ -0,0 +1,110 @@
"""
Core type definitions for Trellis task data.
Provides:
TaskData — TypedDict for task.json shape (read-path type hints only)
TaskInfo — Frozen dataclass for loaded task (the public API type)
AgentRecord — TypedDict for registry.json agent entries
"""
from __future__ import annotations
from dataclasses import dataclass
from pathlib import Path
from typing import TypedDict
# =============================================================================
# task.json shape (TypedDict — used only for read-path type hints)
# =============================================================================
class TaskData(TypedDict, total=False):
"""Shape of task.json on disk.
Used only for type annotations when reading task.json.
Writes must use the original dict to avoid losing unknown fields.
"""
id: str
name: str
title: str
description: str
status: str
dev_type: str
scope: str | None
package: str | None
priority: str
creator: str
assignee: str
createdAt: str
completedAt: str | None
branch: str | None
base_branch: str | None
worktree_path: str | None
commit: str | None
pr_url: str | None
subtasks: list[str]
children: list[str]
parent: str | None
relatedFiles: list[str]
notes: str
meta: dict
# =============================================================================
# Loaded task object (frozen dataclass — the public API type)
# =============================================================================
@dataclass(frozen=True)
class TaskInfo:
"""Immutable view of a loaded task.
Created by load_task() / iter_active_tasks().
Contains the commonly accessed fields; the original dict
is preserved in `raw` for write-back and uncommon field access.
"""
dir_name: str
directory: Path
title: str
status: str
assignee: str
priority: str
children: tuple[str, ...]
parent: str | None
package: str | None
raw: dict # original dict — use for writes and uncommon fields
@property
def name(self) -> str:
"""Task name (id or name field)."""
return self.raw.get("name") or self.raw.get("id") or self.dir_name
@property
def description(self) -> str:
return self.raw.get("description", "")
@property
def branch(self) -> str | None:
return self.raw.get("branch")
@property
def meta(self) -> dict:
return self.raw.get("meta", {})
# =============================================================================
# registry.json agent entry
# =============================================================================
class AgentRecord(TypedDict, total=False):
"""Shape of an agent entry in registry.json."""
id: str
pid: int
task_dir: str
worktree_path: str
branch: str
platform: str
started_at: str
status: str
.trellis/scripts/common/workflow_phase.py
Executable
+212
View File
@@ -0,0 +1,212 @@
#!/usr/bin/env python3
# -*- coding: utf-8 -*-
"""
Workflow Phase Extraction.
Extracts step-level content from .trellis/workflow.md and optionally filters
platform-specific blocks.
Platform marker syntax in workflow.md:
[Claude Code, Cursor, ...]
agent-capable content
[/Claude Code, Cursor, ...]
Provides:
get_phase_index - Extract the Phase Index section (no --step)
get_step - Extract a single step (#### X.X) section
filter_platform - Strip platform blocks that don't include the given name
"""
from __future__ import annotations
import re
from .paths import DIR_WORKFLOW, get_repo_root
def _workflow_md_path():
return get_repo_root() / DIR_WORKFLOW / "workflow.md"
# Match a line that *is* a platform marker: "[A, B, C]" or "[/A, B, C]"
_MARKER_RE = re.compile(r"^\[(/?)([A-Za-z][^\[\]]*)\]\s*$")
# Step heading: "#### 1.0 Title" or "#### 1.0 ..."
_STEP_HEADING_RE = re.compile(r"^####\s+(\d+\.\d+)\b.*$")
# Phase Index starts here; Phase 1/2/3 step bodies follow; ends at Breadcrumbs.
_PHASE_INDEX_HEADING = "## Phase Index"
def _read_workflow() -> str:
path = _workflow_md_path()
if not path.exists():
raise FileNotFoundError(f"workflow.md not found: {path}")
return path.read_text(encoding="utf-8")
def _parse_marker(line: str) -> tuple[bool, list[str]] | None:
"""Parse a platform marker line.
Returns:
(is_closing, [platform_names]) if line is a marker, else None.
"""
m = _MARKER_RE.match(line)
if not m:
return None
is_closing = m.group(1) == "/"
names = [p.strip() for p in m.group(2).split(",") if p.strip()]
return is_closing, names
def get_phase_index() -> str:
"""Return the compact Phase Index summary from workflow.md.
SessionStart and no-step phase context use this small summary as their
orientation payload. Detailed Phase 1/2/3 instructions are loaded with
``get_step`` on demand. ``[workflow-state:STATUS]`` tag blocks are
consumed by the per-turn hook, so they're stripped from this output.
"""
text = _read_workflow()
lines = text.splitlines()
start: int | None = None
end: int | None = None
for i, line in enumerate(lines):
stripped = line.strip()
if start is None and stripped == _PHASE_INDEX_HEADING:
start = i
continue
if start is not None and stripped == "## Phase 1: Plan":
end = i
break
if start is None:
return ""
if end is None:
end = len(lines)
section = "\n".join(lines[start:end]).rstrip()
# Strip [workflow-state:STATUS]...[/workflow-state:STATUS] blocks since
# they're injected separately by inject-workflow-state.py per-turn.
import re as _re
tag_re = _re.compile(
r"\[workflow-state:([A-Za-z0-9_-]+)\]\s*\n.*?\n\s*\[/workflow-state:\1\]\n?",
_re.DOTALL,
)
return tag_re.sub("", section).rstrip() + "\n"
def get_step(step_id: str) -> str:
"""Return the `#### X.X` section matching step_id (header + body).
Body ends at the next `####` or `---` or `##` heading (whichever comes first).
"""
text = _read_workflow()
lines = text.splitlines()
start: int | None = None
for i, line in enumerate(lines):
m = _STEP_HEADING_RE.match(line)
if m and m.group(1) == step_id:
start = i
break
if start is None:
return ""
end: int = len(lines)
for j in range(start + 1, len(lines)):
line = lines[j]
if line.startswith("#### "):
end = j
break
if line.startswith("## "):
end = j
break
# Horizontal rule at column 0
if line.strip() == "---":
end = j
break
return "\n".join(lines[start:end]).rstrip() + "\n"
def _platform_matches(platform: str, block_names: list[str]) -> bool:
"""Case-insensitive fuzzy match: accept 'cursor', 'Cursor', 'claude-code', 'Claude Code'."""
needle = platform.lower().replace("-", "").replace("_", "").replace(" ", "")
for name in block_names:
hay = name.lower().replace("-", "").replace("_", "").replace(" ", "")
if needle == hay:
return True
return False
def resolve_effective_platform(platform: str, config: dict) -> str:
"""Map ``codex`` to a dispatch-mode-namespaced virtual platform name.
When ``--platform codex`` is passed, return ``"codex-inline"`` (default)
or ``"codex-sub-agent"`` based on ``.trellis/config.yaml`` ``codex.dispatch_mode``.
``filter_platform`` then surfaces blocks whose marker lists include the
namespaced name (e.g. ``[codex-sub-agent, ...]`` or ``[codex-inline, Kilo,
Antigravity, Devin]``).
Default is ``inline`` because Codex sub-agents run with ``fork_turns="none"``
isolation and can't inherit the parent session's task context — inline
keeps the main agent in charge so context isn't lost. Invalid / missing
values also fall back to inline.
Other platforms are returned unchanged.
"""
if platform == "codex":
mode = "inline"
codex_cfg = config.get("codex") if isinstance(config, dict) else None
if isinstance(codex_cfg, dict):
cfg_mode = codex_cfg.get("dispatch_mode")
if cfg_mode in ("inline", "sub-agent"):
mode = cfg_mode
return f"codex-{mode}"
return platform
def filter_platform(content: str, platform: str) -> str:
"""Keep lines outside any `[...]` block + lines inside blocks that include platform.
Marker lines themselves are dropped from the output.
"""
lines = content.splitlines()
out: list[str] = []
in_block = False
keep_block = False
for line in lines:
marker = _parse_marker(line)
if marker is not None:
is_closing, names = marker
if not is_closing:
in_block = True
keep_block = _platform_matches(platform, names)
else:
in_block = False
keep_block = False
continue # drop the marker line itself
if in_block:
if keep_block:
out.append(line)
continue
out.append(line)
# Collapse runs of 3+ blank lines that may arise from dropped markers
collapsed: list[str] = []
blank_run = 0
for line in out:
if line.strip() == "":
blank_run += 1
if blank_run <= 2:
collapsed.append(line)
else:
blank_run = 0
collapsed.append(line)
return "\n".join(collapsed).rstrip() + "\n"
.trellis/scripts/get_context.py
Executable
+16
View File
@@ -0,0 +1,16 @@
#!/usr/bin/env python3
"""
Get Session Context for AI Agent.
Usage:
python3 get_context.py Output context in text format
python3 get_context.py --json Output context in JSON format
"""
from __future__ import annotations
from common.git_context import main
if __name__ == "__main__":
main()
.trellis/scripts/get_developer.py
Executable
+26
View File
@@ -0,0 +1,26 @@
#!/usr/bin/env python3
"""
Get current developer name.
This is a wrapper that uses common/paths.py
"""
from __future__ import annotations
import sys
from common.paths import get_developer
def main() -> None:
"""CLI entry point."""
developer = get_developer()
if developer:
print(developer)
else:
print("Developer not initialized", file=sys.stderr)
sys.exit(1)
if __name__ == "__main__":
main()
.trellis/scripts/hooks/linear_sync.py
Executable
+243
View File
@@ -0,0 +1,243 @@
#!/usr/bin/env python3
"""Linear sync hook for Trellis task lifecycle.
Syncs task events to Linear via the `linearis` CLI.
Usage (called automatically by task.py hooks):
python3 .trellis/scripts/hooks/linear_sync.py create
python3 .trellis/scripts/hooks/linear_sync.py start
python3 .trellis/scripts/hooks/linear_sync.py archive
Manual usage:
TASK_JSON_PATH=.trellis/tasks/<name>/task.json python3 .trellis/scripts/hooks/linear_sync.py sync
Environment:
TASK_JSON_PATH - Absolute path to task.json (set by task.py)
Configuration:
.trellis/hooks.local.json - Local config (gitignored), example:
{
"linear": {
"team": "TEAM_KEY",
"project": "Project Name",
"assignees": {
"dev-name": "linear-user-id"
}
}
}
"""
from __future__ import annotations
import json
import os
import subprocess
import sys
from pathlib import Path
# ─── Configuration ────────────────────────────────────────────────────────────
# Trellis priority → Linear priority (1=Urgent, 2=High, 3=Medium, 4=Low)
PRIORITY_MAP = {"P0": 1, "P1": 2, "P2": 3, "P3": 4}
# Linear status names (must match your team's workflow)
STATUS_IN_PROGRESS = "In Progress"
STATUS_DONE = "Done"
def _load_config() -> dict:
"""Load local hook config from .trellis/hooks.local.json."""
task_json_path = os.environ.get("TASK_JSON_PATH", "")
if task_json_path:
# Walk up from task.json to find .trellis/
trellis_dir = Path(task_json_path).parent.parent.parent
else:
trellis_dir = Path(".trellis")
config_path = trellis_dir / "hooks.local.json"
try:
with open(config_path, encoding="utf-8") as f:
return json.load(f)
except (OSError, json.JSONDecodeError):
return {}
CONFIG = _load_config()
LINEAR_CFG = CONFIG.get("linear", {})
TEAM = LINEAR_CFG.get("team", "")
PROJECT = LINEAR_CFG.get("project", "")
ASSIGNEE_MAP = LINEAR_CFG.get("assignees", {})
# ─── Helpers ──────────────────────────────────────────────────────────────────
def _read_task() -> tuple[dict, str]:
path = os.environ.get("TASK_JSON_PATH", "")
if not path:
print("TASK_JSON_PATH not set", file=sys.stderr)
sys.exit(1)
with open(path, encoding="utf-8") as f:
return json.load(f), path
def _write_task(data: dict, path: str) -> None:
with open(path, "w", encoding="utf-8") as f:
json.dump(data, f, indent=2, ensure_ascii=False)
f.write("\n")
def _linearis(*args: str) -> dict | None:
result = subprocess.run(
["linearis", *args],
capture_output=True,
text=True,
encoding="utf-8",
errors="replace",
)
if result.returncode != 0:
print(f"linearis error: {result.stderr.strip()}", file=sys.stderr)
sys.exit(1)
stdout = result.stdout.strip()
if stdout:
return json.loads(stdout)
return None
def _get_linear_issue(task: dict) -> str | None:
meta = task.get("meta")
if isinstance(meta, dict):
return meta.get("linear_issue")
return None
# ─── Actions ──────────────────────────────────────────────────────────────────
def cmd_create() -> None:
if not TEAM:
print("No linear.team configured in hooks.local.json", file=sys.stderr)
sys.exit(1)
task, path = _read_task()
# Skip if already linked
if _get_linear_issue(task):
print(f"Already linked: {_get_linear_issue(task)}")
return
title = task.get("title") or task.get("name") or "Untitled"
args = ["issues", "create", title, "--team", TEAM]
# Map priority
priority = PRIORITY_MAP.get(task.get("priority", ""), 0)
if priority:
args.extend(["-p", str(priority)])
# Set project
if PROJECT:
args.extend(["--project", PROJECT])
# Assign to Linear user
assignee = task.get("assignee", "")
linear_user_id = ASSIGNEE_MAP.get(assignee)
if linear_user_id:
args.extend(["--assignee", linear_user_id])
# Link to parent's Linear issue if available
parent_issue = _resolve_parent_linear_issue(task)
if parent_issue:
args.extend(["--parent-ticket", parent_issue])
result = _linearis(*args)
if result and "identifier" in result:
if not isinstance(task.get("meta"), dict):
task["meta"] = {}
task["meta"]["linear_issue"] = result["identifier"]
_write_task(task, path)
print(f"Created Linear issue: {result['identifier']}")
def cmd_start() -> None:
task, _ = _read_task()
issue = _get_linear_issue(task)
if not issue:
return
_linearis("issues", "update", issue, "-s", STATUS_IN_PROGRESS)
print(f"Updated {issue} -> {STATUS_IN_PROGRESS}")
cmd_sync()
def cmd_archive() -> None:
task, _ = _read_task()
issue = _get_linear_issue(task)
if not issue:
return
_linearis("issues", "update", issue, "-s", STATUS_DONE)
print(f"Updated {issue} -> {STATUS_DONE}")
def cmd_sync() -> None:
"""Sync prd.md content to Linear issue description."""
task, _ = _read_task()
issue = _get_linear_issue(task)
if not issue:
print("No linear_issue in meta, run create first", file=sys.stderr)
sys.exit(1)
# Find prd.md next to task.json
task_json_path = os.environ.get("TASK_JSON_PATH", "")
prd_path = Path(task_json_path).parent / "prd.md"
if not prd_path.is_file():
print(f"No prd.md found at {prd_path}", file=sys.stderr)
sys.exit(1)
description = prd_path.read_text(encoding="utf-8").strip()
_linearis("issues", "update", issue, "-d", description)
print(f"Synced prd.md to {issue} description")
# ─── Parent Issue Resolution ─────────────────────────────────────────────────
def _resolve_parent_linear_issue(task: dict) -> str | None:
"""Find parent task's Linear issue identifier."""
parent_name = task.get("parent")
if not parent_name:
return None
task_json_path = os.environ.get("TASK_JSON_PATH", "")
if not task_json_path:
return None
current_task_dir = Path(task_json_path).parent
tasks_dir = current_task_dir.parent
parent_json = tasks_dir / parent_name / "task.json"
if parent_json.exists():
try:
with open(parent_json, encoding="utf-8") as f:
parent_task = json.load(f)
return _get_linear_issue(parent_task)
except (json.JSONDecodeError, OSError):
pass
return None
# ─── Main ─────────────────────────────────────────────────────────────────────
if __name__ == "__main__":
action = sys.argv[1] if len(sys.argv) > 1 else ""
actions = {
"create": cmd_create,
"start": cmd_start,
"archive": cmd_archive,
"sync": cmd_sync,
}
fn = actions.get(action)
if fn:
fn()
else:
print(f"Unknown action: {action}", file=sys.stderr)
print(f"Valid actions: {', '.join(actions)}", file=sys.stderr)
sys.exit(1)
.trellis/scripts/init_developer.py
Executable
+51
View File
@@ -0,0 +1,51 @@
#!/usr/bin/env python3
"""
Initialize developer for workflow.
Usage:
python3 init_developer.py <developer-name>
This creates:
- .trellis/.developer file with developer info
- .trellis/workspace/<name>/ directory structure
"""
from __future__ import annotations
import sys
from common.paths import (
DIR_WORKFLOW,
FILE_DEVELOPER,
get_developer,
)
from common.developer import init_developer
def main() -> None:
"""CLI entry point."""
if len(sys.argv) < 2:
print(f"Usage: {sys.argv[0]} <developer-name>")
print()
print("Example:")
print(f" {sys.argv[0]} john")
sys.exit(1)
name = sys.argv[1]
# Check if already initialized
existing = get_developer()
if existing:
print(f"Developer already initialized: {existing}")
print()
print(f"To reinitialize, remove {DIR_WORKFLOW}/{FILE_DEVELOPER} first")
sys.exit(0)
if init_developer(name):
sys.exit(0)
else:
sys.exit(1)
if __name__ == "__main__":
main()
.trellis/scripts/task.py
Executable
+500
View File
@@ -0,0 +1,500 @@
#!/usr/bin/env python3
# -*- coding: utf-8 -*-
"""
Task Management Script.
Usage:
python3 task.py create "<title>" [--slug <name>] [--assignee <dev>] [--priority P0|P1|P2|P3] [--parent <dir>] [--package <pkg>]
python3 task.py add-context <dir> <file> <path> [reason] # Add jsonl entry
python3 task.py validate <dir> # Validate jsonl files
python3 task.py list-context <dir> # List jsonl entries
python3 task.py start <dir> # Set active task
python3 task.py current [--source] # Show active task
python3 task.py finish # Clear active task
python3 task.py set-branch <dir> <branch> # Set git branch
python3 task.py set-base-branch <dir> <branch> # Set PR target branch
python3 task.py set-scope <dir> <scope> # Set scope for PR title
python3 task.py archive <task-dir> # Archive completed task
python3 task.py list # List active tasks
python3 task.py list-archive [month] # List archived tasks
python3 task.py add-subtask <parent-dir> <child-dir> # Link child to parent
python3 task.py remove-subtask <parent-dir> <child-dir> # Unlink child from parent
"""
from __future__ import annotations
import argparse
import sys
from common.log import Colors, colored
from common.paths import (
DIR_WORKFLOW,
DIR_TASKS,
FILE_TASK_JSON,
get_repo_root,
get_developer,
get_tasks_dir,
get_current_task,
)
from common.active_task import (
clear_active_task,
resolve_active_task,
resolve_context_key,
set_active_task,
)
from common.io import read_json, write_json
from common.task_utils import resolve_task_dir, run_task_hooks
from common.tasks import iter_active_tasks, children_progress
# Import command handlers from split modules (also re-exports for plan.py compatibility)
from common.task_store import (
cmd_create,
cmd_archive,
cmd_set_branch,
cmd_set_base_branch,
cmd_set_scope,
cmd_add_subtask,
cmd_remove_subtask,
)
from common.task_context import (
cmd_add_context,
cmd_validate,
cmd_list_context,
)
# =============================================================================
# Command: start / finish
# =============================================================================
def cmd_start(args: argparse.Namespace) -> int:
"""Set active task."""
repo_root = get_repo_root()
task_input = args.dir
if not task_input:
print(colored("Error: task directory or name required", Colors.RED))
return 1
# Resolve task directory (supports task name, relative path, or absolute path)
full_path = resolve_task_dir(task_input, repo_root)
if not full_path.is_dir():
print(colored(f"Error: Task not found: {task_input}", Colors.RED))
print("Hint: Use task name (e.g., 'my-task') or full path (e.g., '.trellis/tasks/01-31-my-task')")
return 1
# Convert to relative path for storage
try:
task_dir = full_path.relative_to(repo_root).as_posix()
except ValueError:
task_dir = str(full_path)
task_json_path = full_path / FILE_TASK_JSON
if not resolve_context_key():
# Degraded mode: no session identity available.
# Hook didn't inject TRELLIS_CONTEXT_ID (common on Windows + Claude Code,
# --continue resume path, fork distribution, hooks disabled, etc.). Skip
# per-session pointer write; AI continues based on conversation context.
print(colored(
"ℹ Session identity not available; active-task pointer not persisted "
"this session (degraded mode). AI continues based on conversation context.",
Colors.YELLOW,
))
print(colored(
"Hint: run inside an AI IDE/session that exposes session identity, "
"or set TRELLIS_CONTEXT_ID before running task.py start.",
Colors.YELLOW,
))
# Still flip task.json status: planning → in_progress so downstream phases proceed.
if task_json_path.is_file():
data = read_json(task_json_path)
if data and data.get("status") == "planning":
data["status"] = "in_progress"
if write_json(task_json_path, data):
print(colored("✓ Status: planning → in_progress (degraded)", Colors.GREEN))
run_task_hooks("after_start", task_json_path, repo_root)
return 0
active = set_active_task(task_dir, repo_root)
if active:
print(colored(f"✓ Current task set to: {task_dir}", Colors.GREEN))
print(f"Source: {active.source}")
if task_json_path.is_file():
data = read_json(task_json_path)
if data and data.get("status") == "planning":
data["status"] = "in_progress"
if write_json(task_json_path, data):
print(colored("✓ Status: planning → in_progress", Colors.GREEN))
print()
print(colored("The hook will now inject context from this task's jsonl files.", Colors.BLUE))
run_task_hooks("after_start", task_json_path, repo_root)
return 0
else:
print(colored("Error: Failed to set current task", Colors.RED))
return 1
def cmd_finish(args: argparse.Namespace) -> int:
"""Clear active task."""
repo_root = get_repo_root()
active = clear_active_task(repo_root)
current = active.task_path
if not current:
print(colored("No current task set", Colors.YELLOW))
return 0
# Resolve task.json path before clearing
task_json_path = repo_root / current / FILE_TASK_JSON
print(colored(f"✓ Cleared current task (was: {current})", Colors.GREEN))
print(f"Source: {active.source}")
if task_json_path.is_file():
run_task_hooks("after_finish", task_json_path, repo_root)
return 0
def cmd_current(args: argparse.Namespace) -> int:
"""Show active task."""
repo_root = get_repo_root()
active = resolve_active_task(repo_root)
if args.source:
print(f"Current task: {active.task_path or '(none)'}")
print(f"Source: {active.source}")
if active.stale:
print("State: stale")
return 0 if active.task_path else 1
if active.task_path:
print(active.task_path)
return 0
return 1
# =============================================================================
# Command: list
# =============================================================================
def cmd_list(args: argparse.Namespace) -> int:
"""List active tasks."""
repo_root = get_repo_root()
tasks_dir = get_tasks_dir(repo_root)
current_task = get_current_task(repo_root)
developer = get_developer(repo_root)
filter_mine = args.mine
filter_status = args.status
if filter_mine:
if not developer:
print(colored("Error: No developer set. Run init_developer.py first", Colors.RED), file=sys.stderr)
return 1
print(colored(f"My tasks (assignee: {developer}):", Colors.BLUE))
else:
print(colored("All active tasks:", Colors.BLUE))
print()
# Single pass: collect all tasks via shared iterator
all_tasks = {t.dir_name: t for t in iter_active_tasks(tasks_dir)}
all_statuses = {name: t.status for name, t in all_tasks.items()}
# Display tasks hierarchically
count = 0
def _print_task(dir_name: str, indent: int = 0) -> None:
nonlocal count
t = all_tasks[dir_name]
# Apply --mine filter
if filter_mine and (t.assignee or "-") != developer:
return
# Apply --status filter
if filter_status and t.status != filter_status:
return
relative_path = f"{DIR_WORKFLOW}/{DIR_TASKS}/{dir_name}"
marker = ""
if relative_path == current_task:
marker = f" {colored('<- current', Colors.GREEN)}"
# Children progress
progress = children_progress(t.children, all_statuses)
# Package tag
pkg_tag = f" @{t.package}" if t.package else ""
prefix = " " * indent + " - "
if filter_mine:
print(f"{prefix}{dir_name}/ ({t.status}){pkg_tag}{progress}{marker}")
else:
print(f"{prefix}{dir_name}/ ({t.status}){pkg_tag}{progress} [{colored(t.assignee or '-', Colors.CYAN)}]{marker}")
count += 1
# Print children indented
for child_name in t.children:
if child_name in all_tasks:
_print_task(child_name, indent + 1)
# Display only top-level tasks (those without a parent)
for dir_name in sorted(all_tasks.keys()):
if not all_tasks[dir_name].parent:
_print_task(dir_name)
if count == 0:
if filter_mine:
print(" (no tasks assigned to you)")
else:
print(" (no active tasks)")
print()
print(f"Total: {count} task(s)")
return 0
# =============================================================================
# Command: list-archive
# =============================================================================
def cmd_list_archive(args: argparse.Namespace) -> int:
"""List archived tasks."""
repo_root = get_repo_root()
tasks_dir = get_tasks_dir(repo_root)
archive_dir = tasks_dir / "archive"
month = args.month
print(colored("Archived tasks:", Colors.BLUE))
print()
if month:
month_dir = archive_dir / month
if month_dir.is_dir():
print(f"[{month}]")
for d in sorted(month_dir.iterdir()):
if d.is_dir():
print(f" - {d.name}/")
else:
print(f" No archives for {month}")
else:
if archive_dir.is_dir():
for month_dir in sorted(archive_dir.iterdir()):
if month_dir.is_dir():
month_name = month_dir.name
count = sum(1 for d in month_dir.iterdir() if d.is_dir())
print(f"[{month_name}] - {count} task(s)")
return 0
# =============================================================================
# Help
# =============================================================================
def show_usage() -> None:
"""Show usage help."""
print("""Task Management Script
Usage:
python3 task.py create <title> Create new task directory
python3 task.py create <title> --package <pkg> Create task for a specific package
python3 task.py create <title> --parent <dir> Create task as child of parent
python3 task.py add-context <dir> <jsonl> <path> [reason] Add entry to jsonl
python3 task.py validate <dir> Validate jsonl files
python3 task.py list-context <dir> List jsonl entries
python3 task.py start <dir> Set active task
python3 task.py current [--source] Show active task
python3 task.py finish Clear active task
python3 task.py set-branch <dir> <branch> Set git branch
python3 task.py set-base-branch <dir> <branch> Set PR target branch
python3 task.py set-scope <dir> <scope> Set scope for PR title
python3 task.py archive <task-dir> Archive completed task
python3 task.py add-subtask <parent> <child> Link child task to parent
python3 task.py remove-subtask <parent> <child> Unlink child from parent
python3 task.py list [--mine] [--status <status>] List tasks
python3 task.py list-archive [YYYY-MM] List archived tasks
Monorepo options:
--package <pkg> Package name (validated against config.yaml packages)
List options:
--mine, -m Show only tasks assigned to current developer
--status, -s <s> Filter by status (planning, in_progress, review, completed)
Examples:
python3 task.py create "Add login feature" --slug add-login
python3 task.py create "Add login feature" --slug add-login --package cli
python3 task.py create "Child task" --slug child --parent .trellis/tasks/01-21-parent
python3 task.py add-context <dir> implement .trellis/spec/cli/backend/auth.md "Auth guidelines"
python3 task.py set-branch <dir> task/add-login
python3 task.py start .trellis/tasks/01-21-add-login
python3 task.py current --source
python3 task.py finish
python3 task.py archive add-login
python3 task.py add-subtask parent-task child-task # Link existing tasks
python3 task.py remove-subtask parent-task child-task
python3 task.py list # List all active tasks
python3 task.py list --mine # List my tasks only
python3 task.py list --mine --status in_progress # List my in-progress tasks
""")
# =============================================================================
# Main Entry
# =============================================================================
def main() -> int:
"""CLI entry point."""
# Deprecation guard: `init-context` was removed in v0.5.0-beta.12.
# Detect early so argparse doesn't mask the real reason with a generic
# "invalid choice" error.
if len(sys.argv) >= 2 and sys.argv[1] == "init-context":
print(
colored(
"Error: `task.py init-context` was removed in v0.5.0-beta.12.",
Colors.RED,
),
file=sys.stderr,
)
print(
"implement.jsonl / check.jsonl are now seeded on `task.py create` for",
file=sys.stderr,
)
print(
"sub-agent-capable platforms and curated by the AI during planning when needed.",
file=sys.stderr,
)
print("See .trellis/workflow.md planning artifact guidance or run:", file=sys.stderr)
print(
" python3 ./.trellis/scripts/get_context.py --mode phase --step 1",
file=sys.stderr,
)
print(
"Use `task.py add-context <dir> implement|check <path> <reason>` to append entries.",
file=sys.stderr,
)
return 2
parser = argparse.ArgumentParser(
description="Task Management Script",
formatter_class=argparse.RawDescriptionHelpFormatter,
)
subparsers = parser.add_subparsers(dest="command", help="Commands")
# create
p_create = subparsers.add_parser("create", help="Create new task")
p_create.add_argument("title", help="Task title")
p_create.add_argument("--slug", "-s", help="Task slug")
p_create.add_argument("--assignee", "-a", help="Assignee developer")
p_create.add_argument("--priority", "-p", default="P2", help="Priority (P0-P3)")
p_create.add_argument("--description", "-d", help="Task description")
p_create.add_argument("--parent", help="Parent task directory (establishes subtask link)")
p_create.add_argument("--package", help="Package name for monorepo projects")
# add-context
p_add = subparsers.add_parser("add-context", help="Add context entry")
p_add.add_argument("dir", help="Task directory")
p_add.add_argument("file", help="JSONL file (implement|check)")
p_add.add_argument("path", help="File path to add")
p_add.add_argument("reason", nargs="?", help="Reason for adding")
# validate
p_validate = subparsers.add_parser("validate", help="Validate context files")
p_validate.add_argument("dir", help="Task directory")
# list-context
p_listctx = subparsers.add_parser("list-context", help="List context entries")
p_listctx.add_argument("dir", help="Task directory")
# start
p_start = subparsers.add_parser("start", help="Set active task")
p_start.add_argument("dir", help="Task directory")
# current
p_current = subparsers.add_parser("current", help="Show active task")
p_current.add_argument("--source", action="store_true",
help="Show active task source")
# finish
subparsers.add_parser("finish", help="Clear active task")
# set-branch
p_branch = subparsers.add_parser("set-branch", help="Set git branch")
p_branch.add_argument("dir", help="Task directory")
p_branch.add_argument("branch", help="Branch name")
# set-base-branch
p_base = subparsers.add_parser("set-base-branch", help="Set PR target branch")
p_base.add_argument("dir", help="Task directory")
p_base.add_argument("base_branch", help="Base branch name (PR target)")
# set-scope
p_scope = subparsers.add_parser("set-scope", help="Set scope")
p_scope.add_argument("dir", help="Task directory")
p_scope.add_argument("scope", help="Scope name")
# archive
p_archive = subparsers.add_parser("archive", help="Archive task")
p_archive.add_argument("name", help="Task directory or name")
p_archive.add_argument("--no-commit", action="store_true", help="Skip auto git commit after archive")
# list
p_list = subparsers.add_parser("list", help="List tasks")
p_list.add_argument("--mine", "-m", action="store_true", help="My tasks only")
p_list.add_argument("--status", "-s", help="Filter by status")
# add-subtask
p_addsub = subparsers.add_parser("add-subtask", help="Link child task to parent")
p_addsub.add_argument("parent_dir", help="Parent task directory")
p_addsub.add_argument("child_dir", help="Child task directory")
# remove-subtask
p_rmsub = subparsers.add_parser("remove-subtask", help="Unlink child task from parent")
p_rmsub.add_argument("parent_dir", help="Parent task directory")
p_rmsub.add_argument("child_dir", help="Child task directory")
# list-archive
p_listarch = subparsers.add_parser("list-archive", help="List archived tasks")
p_listarch.add_argument("month", nargs="?", help="Month (YYYY-MM)")
args = parser.parse_args()
if not args.command:
show_usage()
return 1
commands = {
"create": cmd_create,
"add-context": cmd_add_context,
"validate": cmd_validate,
"list-context": cmd_list_context,
"start": cmd_start,
"current": cmd_current,
"finish": cmd_finish,
"set-branch": cmd_set_branch,
"set-base-branch": cmd_set_base_branch,
"set-scope": cmd_set_scope,
"archive": cmd_archive,
"add-subtask": cmd_add_subtask,
"remove-subtask": cmd_remove_subtask,
"list": cmd_list,
"list-archive": cmd_list_archive,
}
if args.command in commands:
return commands[args.command](args)
else:
show_usage()
return 1
if __name__ == "__main__":
sys.exit(main())
.trellis/spec/guides/code-reuse-thinking-guide.md
+223
View File
@@ -0,0 +1,223 @@
# Code Reuse Thinking Guide
> **Purpose**: Stop and think before creating new code - does it already exist?
---
## The Problem
**Duplicated code is the #1 source of inconsistency bugs.**
When you copy-paste or rewrite existing logic:
- Bug fixes don't propagate
- Behavior diverges over time
- Codebase becomes harder to understand
---
## Before Writing New Code
### Step 1: Search First
```bash
# Search for similar function names
grep -r "functionName" .
# Search for similar logic
grep -r "keyword" .
```
### Step 2: Ask These Questions
| Question | If Yes... |
|----------|-----------|
| Does a similar function exist? | Use or extend it |
| Is this pattern used elsewhere? | Follow the existing pattern |
| Could this be a shared utility? | Create it in the right place |
| Am I copying code from another file? | **STOP** - extract to shared |
---
## Common Duplication Patterns
### Pattern 1: Copy-Paste Functions
**Bad**: Copying a validation function to another file
**Good**: Extract to shared utilities, import where needed
### Pattern 2: Similar Components
**Bad**: Creating a new component that's 80% similar to existing
**Good**: Extend existing component with props/variants
### Pattern 3: Repeated Constants
**Bad**: Defining the same constant in multiple files
**Good**: Single source of truth, import everywhere
### Pattern 4: Repeated Payload Field Extraction
**Bad**: Multiple consumers cast the same JSON/event fields locally:
```typescript
const description = (ev as { description?: string }).description;
const context = (ev as { context?: ContextEntry[] }).context;
```
This is duplicated contract logic even when the code is only two lines. Each
consumer now has its own definition of what a valid payload means.
**Good**: Put the decoder, type guard, or projection next to the data owner:
```typescript
if (isThreadEvent(ev)) {
renderThreadEvent(ev);
}
```
**Rule**: If the same untyped payload field is read in 2+ places, create a
shared type guard / normalizer / projection before adding a third reader.
---
## When to Abstract
**Abstract when**:
- Same code appears 3+ times
- Logic is complex enough to have bugs
- Multiple people might need this
**Don't abstract when**:
- Only used once
- Trivial one-liner
- Abstraction would be more complex than duplication
---
## After Batch Modifications
When you've made similar changes to multiple files:
1. **Review**: Did you catch all instances?
2. **Search**: Run grep to find any missed
3. **Consider**: Should this be abstracted?
### Reducers Should Use Exhaustive Structure
When state is derived from action-like values (`action`, `kind`, `status`,
`phase`), prefer a reducer with one `switch` over scattered `if/else` updates.
```typescript
// BAD - action-specific state transitions are hard to audit
if (action === "opened") { ... }
else if (action === "comment") { ... }
else if (action === "status") { ... }
// GOOD - one reducer owns the transition table
switch (event.action) {
case "opened":
...
return;
case "comment":
...
return;
}
```
This matters when the event log is the source of truth. A reducer is the
documented replay model; display code and commands should not duplicate pieces
of that replay model.
---
## Checklist Before Commit
- [ ] Searched for existing similar code
- [ ] No copy-pasted logic that should be shared
- [ ] No repeated untyped payload field extraction outside a shared decoder
- [ ] Constants defined in one place
- [ ] Similar patterns follow same structure
- [ ] Reducer/action transitions live in one reducer or command dispatcher
---
## Gotcha: Python if/elif/else Exhaustive Check
**Problem**: Python's if/elif/else chains have no compile-time exhaustive check. When you add a new value to a `Literal` type (e.g., `Platform`), existing if/elif/else chains silently fall through to `else` with wrong defaults.
**Symptom**: New platform works partially — some methods return Claude defaults instead of platform-specific values. No error is raised.
**Example** (`cli_adapter.py`):
```python
# BAD: "gemini" falls through to else, returns "claude"
@property
def cli_name(self) -> str:
if self.platform == "opencode":
return "opencode"
else:
return "claude" # gemini silently gets "claude"!
# GOOD: explicit branch for every platform
@property
def cli_name(self) -> str:
if self.platform == "opencode":
return "opencode"
elif self.platform == "gemini":
return "gemini"
else:
return "claude"
```
**Prevention**: When adding a new value to a Python `Literal` type, search for ALL if/elif/else chains that switch on that type and add explicit branches. Don't rely on `else` being correct for new values.
---
## Gotcha: Asymmetric Mechanisms Producing Same Output
**Problem**: When two different mechanisms must produce the same file set (e.g., recursive directory copy for init vs. manual `files.set()` for update), structural changes (renaming, moving, adding subdirectories) only propagate through the automatic mechanism. The manual one silently drifts.
**Symptom**: Init works perfectly, but update creates files at wrong paths or misses files entirely.
**Prevention**:
- **Best**: Eliminate the asymmetry — have the manual path call the automatic one (e.g., `collectTemplateFiles()` calls `getAllScripts()` instead of maintaining its own list)
- **If asymmetry is unavoidable**: Add a regression test that compares outputs from both mechanisms
- When migrating directory structures, search for ALL code paths that reference the old structure
**Real example**: `trellis update` had a manual `files.set()` list for 11 scripts that `getAllScripts()` already tracked. Fix: replaced the manual list with a `for..of getAllScripts()` loop. See `update.ts` refactor in v0.4.0-beta.3.
---
## Template File Registration (Trellis-specific)
When adding new files to `src/templates/trellis/scripts/`:
**Single registration point**: `src/templates/trellis/index.ts`
1. Add `export const xxxScript = readTemplate("scripts/path/file.py");`
2. Add to `getAllScripts()` Map
That's it. `commands/update.ts` uses `getAllScripts()` directly — no manual sync needed.
**Why this matters**: Without registration in `getAllScripts()`, `trellis update` won't sync the file to user projects. Bug fixes and features won't propagate.
**History**: Before v0.4.0-beta.3, `update.ts` had its own hand-maintained file list that frequently fell out of sync with `getAllScripts()`. This caused 11 Python files to be silently skipped during `trellis update`. The fix was to eliminate the duplicate list and use `getAllScripts()` as the single source of truth.
### Quick Checklist for New Scripts
```bash
# After adding a new .py file, verify it's in getAllScripts():
grep -l "newFileName" src/templates/trellis/index.ts # Should match
```
### Template Sync Convention
`.trellis/scripts/` (dogfooded) and `packages/cli/src/templates/trellis/scripts/` (template) must stay identical. After editing `.trellis/scripts/`, always sync:
```bash
rsync -av --delete --exclude='__pycache__' .trellis/scripts/ packages/cli/src/templates/trellis/scripts/
```
**Gotcha**: Running rsync with wrong source/destination paths can create nested garbage directories (e.g., `.trellis/scripts/packages/cli/...`). Always double-check paths before running.
.trellis/spec/guides/cross-layer-thinking-guide.md
+327
View File
@@ -0,0 +1,327 @@
# Cross-Layer Thinking Guide
> **Purpose**: Think through data flow across layers before implementing.
---
## The Problem
**Most bugs happen at layer boundaries**, not within layers.
Common cross-layer bugs:
- API returns format A, frontend expects format B
- Database stores X, service transforms to Y, but loses data
- Multiple layers implement the same logic differently
---
## Before Implementing Cross-Layer Features
### Step 1: Map the Data Flow
Draw out how data moves:
```
Source → Transform → Store → Retrieve → Transform → Display
```
For each arrow, ask:
- What format is the data in?
- What could go wrong?
- Who is responsible for validation?
### Step 2: Identify Boundaries
| Boundary | Common Issues |
| --------------------- | --------------------------------- |
| API ↔ Service | Type mismatches, missing fields |
| Service ↔ Database | Format conversions, null handling |
| Backend ↔ Frontend | Serialization, date formats |
| Component ↔ Component | Props shape changes |
### Step 3: Define Contracts
For each boundary:
- What is the exact input format?
- What is the exact output format?
- What errors can occur?
---
## Common Cross-Layer Mistakes
### Mistake 1: Implicit Format Assumptions
**Bad**: Assuming date format without checking
**Good**: Explicit format conversion at boundaries
### Mistake 2: Scattered Validation
**Bad**: Validating the same thing in multiple layers
**Good**: Validate once at the entry point
### Mistake 3: Leaky Abstractions
**Bad**: Component knows about database schema
**Good**: Each layer only knows its neighbors
### Mistake 4: Every Consumer Parses The Same Payload
**Bad**: A command reads JSONL events and casts fields inline:
```typescript
const thread = (ev as { thread?: string }).thread;
const labels = (ev as { labels?: string[] }).labels;
```
This looks local, but it means every consumer owns a private version of the
event contract. The next field change will update one command and miss another.
**Good**: Decode once at the event boundary, then export typed projections:
```typescript
if (!isThreadEvent(ev)) return false;
return ev.thread === filter.thread;
```
**Rule**: For append-only logs, JSON streams, RPC payloads, or config files,
create one owner for:
- event / payload type definitions
- type guards and normalization from `unknown`
- metadata projections used by UI commands
- reducers that replay state from the source of truth
Rendering code may format fields, but it must not redefine the payload contract.
---
## Checklist for Cross-Layer Features
Before implementation:
- [ ] Mapped the complete data flow
- [ ] Identified all layer boundaries
- [ ] Defined format at each boundary
- [ ] Decided where validation happens
After implementation:
- [ ] Tested with edge cases (null, empty, invalid)
- [ ] Verified error handling at each boundary
- [ ] Checked data survives round-trip
- [ ] Checked that consumers import shared decoders / projections instead of
casting payload fields locally
- [ ] Checked that derived state points back to the source event identifier
(`seq`, `id`, `version`) instead of inventing a second cursor
---
## Cross-Platform Template Consistency
In Trellis, command templates (e.g., `record-session.md`) exist in **multiple platforms** with identical or near-identical content. This is a cross-layer boundary.
### Checklist: After Modifying Any Command Template
- [ ] Find all platforms with the same command: `find src/templates/*/commands/trellis/ -name "<command>.*"`
- [ ] Update all platform copies (Markdown `.md` and TOML `.toml`)
- [ ] For Gemini TOML: adapt line continuations (`\\` vs `\`) and triple-quoted strings
- [ ] Run `/trellis:check-cross-layer` to verify nothing was missed
**Real-world example**: Updated `record-session.md` in Claude to use `--mode record`, but forgot iFlow, Kilo, OpenCode, and Gemini — caught by cross-layer check.
---
## Generated Runtime Template Upgrade Consistency
Some generated files are both documentation and runtime input. In Trellis,
`.trellis/workflow.md` is parsed by `get_context.py`, `workflow_phase.py`,
SessionStart filters, and per-turn hooks. Template changes must be validated
against both fresh init and upgrade paths.
### Checklist: After Modifying A Runtime-Parsed Template
- [ ] Identify every runtime parser that reads the template, not just the file
writer that installs it
- [ ] Check whether relevant syntax lives outside obvious managed regions
such as tag blocks
- [ ] Verify fresh `init` output and a versioned `update` scenario that writes
the older `.trellis/.version`
- [ ] Add an upgrade regression using an older pristine template fixture, then
assert the installed file reaches the current packaged shape
- [ ] Update the backend spec that owns the runtime contract
---
## Versioned Documentation Boundary
Versioned documentation is a cross-layer boundary: source paths, `docs.json`
version routing, and the rendered version selector must all describe the same
release line.
### Checklist: Before Editing Versioned Docs
- [ ] Identify the target release line: stable, beta, or RC
- [ ] Verify the edited MDX path matches that line:
- stable: `docs-site/{start,advanced,...}` and `docs-site/zh/{start,advanced,...}`
- beta: `docs-site/beta/**` and `docs-site/zh/beta/**`
- RC: `docs-site/rc/**` and `docs-site/zh/rc/**`
- [ ] Verify `docs.json` navigation points the version label to the same paths
- [ ] Grep the opposite tree for release-line-specific terms before committing
- [ ] Treat beta content appearing under root release paths as a source-path bug,
not a rendering bug
**Real-world example**: A beta-only task workflow change documented
`prd.md` + `design.md` + `implement.md`, task-creation consent, and Codex
mode banners under root `start/` and `advanced/` paths. The docs site then
served 0.6 beta behavior under the Release selector. The fix was to restore root
release docs, move the 0.6 content to `beta/` and `zh/beta/`, and add a grep
audit for beta markers against the root release tree.
**Real-world example**: Codex inline mode changed workflow platform markers from
`[Codex]` / `[Kilo, Antigravity, Windsurf]` to `[codex-sub-agent]` /
`[codex-inline, Kilo, Antigravity, Windsurf]`. Fresh init was correct, but
`trellis update` only merged `[workflow-state:*]` blocks and preserved stale
markers outside those blocks. Result: upgraded projects got new hook scripts
but old workflow routing, so `get_context.py --mode phase --platform codex`
could return empty Phase 2.1 detail.
---
## Mode-Detection Probe Checklist
When a CLI auto-detects a mode by probing a remote resource (e.g., checking if `index.json` exists to decide marketplace vs direct download):
### Before implementing:
- [ ] Probe runs in **ALL** code paths that use the result (interactive, `-y`, `--flag` combos)
- [ ] 404 vs transient error are distinguished — don't treat both as "not found"
- [ ] Transient errors **abort or retry**, never silently switch modes
- [ ] Shared state (caches, prefetched data) is **reset** when context changes (e.g., user switches source)
- [ ] **Shortcut paths** (e.g., `--template` skipping picker) must have the same error-handling quality as the probed path — check that downstream functions don't call catch-all wrappers
### After implementing:
- [ ] Trace every path from probe result to the mode-decision branch — no fallthrough
- [ ] External format contracts (giget URI, raw URLs) are tested or at least documented as comments
- [ ] Metadata reads consume a complete response or use a streaming parser — never parse a fixed-size prefix as full JSON
- [ ] When reconstructing a composite identifier from parsed parts, verify **all** fields are included and in the **correct position** (e.g., `provider:repo/path#ref` not `provider:repo#ref/path`)
- [ ] Verify that **action functions** called after a shortcut don't internally use the old catch-all fetch — they must use the probe-quality variant when error distinction matters
**Real-world example**: Custom registry flow had 8 bugs across 3 review rounds: (1) probe only ran in interactive mode, (2) transient errors fell through to wrong mode, (3) giget URI had `#ref` in wrong position, (4) prefetched templates leaked across source switches, (5) `--template` shortcut bypassed probe but `downloadTemplateById` internally used catch-all `fetchTemplateIndex`, turning timeouts into "Template not found".
**Real-world example**: Agent-session update hints fetched npm `latest` metadata with `response.read(4096)` and then parsed it as complete JSON. The `@mindfoldhq/trellis` package metadata exceeded 4 KB, so the JSON was truncated, parse failed silently, and the first session injection showed no update hint. Fix: read the complete response before parsing, and add a regression where `version` is followed by an 8 KB metadata tail.
---
## Cross-Platform Template Consistency
In Trellis, command templates (e.g., `record-session.md`) exist in **multiple platforms** with identical or near-identical content. This is a cross-layer boundary.
### Checklist: After Modifying Any Command Template
- [ ] Find all platforms with the same command: `find src/templates/*/commands/trellis/ -name "<command>.*"`
- [ ] Update all platform copies (Markdown `.md` and TOML `.toml`)
- [ ] For Gemini TOML: adapt line continuations (`\\` vs `\`) and triple-quoted strings
- [ ] Run `/trellis:check-cross-layer` to verify nothing was missed
**Real-world example**: Updated `record-session.md` in Claude to use `--mode record`, but forgot iFlow, Kilo, OpenCode, and Gemini — caught by cross-layer check.
---
## Generated Runtime Template Upgrade Consistency
Some generated files are both documentation and runtime input. In Trellis,
`.trellis/workflow.md` is parsed by `get_context.py`, `workflow_phase.py`,
SessionStart filters, and per-turn hooks. Template changes must be validated
against both fresh init and upgrade paths.
### Checklist: After Modifying A Runtime-Parsed Template
- [ ] Identify every runtime parser that reads the template, not just the file
writer that installs it
- [ ] Check whether relevant syntax lives outside obvious managed regions
such as tag blocks
- [ ] Verify fresh `init` output and a versioned `update` scenario that writes
the older `.trellis/.version`
- [ ] Add an upgrade regression using an older pristine template fixture, then
assert the installed file reaches the current packaged shape
- [ ] Update the backend spec that owns the runtime contract
**Real-world example**: Codex inline mode changed workflow platform markers from
`[Codex]` / `[Kilo, Antigravity, Windsurf]` to `[codex-sub-agent]` /
`[codex-inline, Kilo, Antigravity, Windsurf]`. Fresh init was correct, but
`trellis update` only merged `[workflow-state:*]` blocks and preserved stale
markers outside those blocks. Result: upgraded projects got new hook scripts
but old workflow routing, so `get_context.py --mode phase --platform codex`
could return empty Phase 2.1 detail.
---
## Mode-Detection Probe Checklist
When a CLI auto-detects a mode by probing a remote resource (e.g., checking if `index.json` exists to decide marketplace vs direct download):
### Before implementing:
- [ ] Probe runs in **ALL** code paths that use the result (interactive, `-y`, `--flag` combos)
- [ ] 404 vs transient error are distinguished — don't treat both as "not found"
- [ ] Transient errors **abort or retry**, never silently switch modes
- [ ] Shared state (caches, prefetched data) is **reset** when context changes (e.g., user switches source)
- [ ] **Shortcut paths** (e.g., `--template` skipping picker) must have the same error-handling quality as the probed path — check that downstream functions don't call catch-all wrappers
### After implementing:
- [ ] Trace every path from probe result to the mode-decision branch — no fallthrough
- [ ] External format contracts (giget URI, raw URLs) are tested or at least documented as comments
- [ ] Metadata reads consume a complete response or use a streaming parser — never parse a fixed-size prefix as full JSON
- [ ] When reconstructing a composite identifier from parsed parts, verify **all** fields are included and in the **correct position** (e.g., `provider:repo/path#ref` not `provider:repo#ref/path`)
- [ ] Verify that **action functions** called after a shortcut don't internally use the old catch-all fetch — they must use the probe-quality variant when error distinction matters
**Real-world example**: Custom registry flow had 8 bugs across 3 review rounds: (1) probe only ran in interactive mode, (2) transient errors fell through to wrong mode, (3) giget URI had `#ref` in wrong position, (4) prefetched templates leaked across source switches, (5) `--template` shortcut bypassed probe but `downloadTemplateById` internally used catch-all `fetchTemplateIndex`, turning timeouts into "Template not found".
**Real-world example**: Agent-session update hints fetched npm `latest` metadata with `response.read(4096)` and then parsed it as complete JSON. The `@mindfoldhq/trellis` package metadata exceeded 4 KB, so the JSON was truncated, parse failed silently, and the first session injection showed no update hint. Fix: read the complete response before parsing, and add a regression where `version` is followed by an 8 KB metadata tail.
---
## When to Create Flow Documentation
Create detailed flow docs when:
- Feature spans 3+ layers
- Multiple teams are involved
- Data format is complex
- Feature has caused bugs before
---
## Event Log / Projection Boundary
Append-only logs are cross-layer contracts. A single event travels through:
```
CLI input → event writer → events.jsonl → reader → filter → reducer → display
```
### Checklist: After Adding A New Event Kind Or Field
- [ ] Add the event kind to the central event taxonomy
- [ ] Add a typed event variant or type guard at the event layer
- [ ] Add normalization helpers for array/object fields that come from
user input or JSON
- [ ] Keep `seq` / `id` assignment in the event writer only
- [ ] Make filters and reducers consume the typed event guard, not local casts
- [ ] Make display code consume reducer output or typed events, not raw JSON
- [ ] Add at least one regression that proves history replay and live filtering
use the same filter model
**Real-world example**: Thread channels added `kind: "thread"`, `description`,
`context`, labels, and `lastSeq`. The first implementation replayed thread
state correctly, but several commands still re-parsed event payload fields with
local casts. The fix was to make the core event layer own `ThreadChannelEvent`
and `isThreadEvent`, make `reduceChannelMetadata` the only channel metadata
projection, and make `reduceThreads` the only thread replay reducer.
.trellis/spec/guides/index.md
+97
View File
@@ -0,0 +1,97 @@
# Thinking Guides
> **Purpose**: Expand your thinking to catch things you might not have considered.
---
## Why Thinking Guides?
**Most bugs and tech debt come from "didn't think of that"**, not from lack of skill:
- Didn't think about what happens at layer boundaries → cross-layer bugs
- Didn't think about code patterns repeating → duplicated code everywhere
- Didn't think about edge cases → runtime errors
- Didn't think about future maintainers → unreadable code
These guides help you **ask the right questions before coding**.
---
## Available Guides
| Guide | Purpose | When to Use |
|-------|---------|-------------|
| [Code Reuse Thinking Guide](./code-reuse-thinking-guide.md) | Identify patterns and reduce duplication | When you notice repeated patterns |
| [Cross-Layer Thinking Guide](./cross-layer-thinking-guide.md) | Think through data flow across layers | Features spanning multiple layers |
---
## Quick Reference: Thinking Triggers
### When to Think About Cross-Layer Issues
- [ ] Feature touches 3+ layers (API, Service, Component, Database)
- [ ] Data format changes between layers
- [ ] Multiple consumers need the same data
- [ ] You're not sure where to put some logic
- [ ] You are adding an event kind, JSONL record, RPC payload, or config field
- [ ] UI / command code starts casting raw payload fields directly
→ Read [Cross-Layer Thinking Guide](./cross-layer-thinking-guide.md)
### When to Think About Code Reuse
- [ ] You're writing similar code to something that exists
- [ ] You see the same pattern repeated 3+ times
- [ ] You're adding a new field to multiple places
- [ ] **You're modifying any constant or config**
- [ ] **You're creating a new utility/helper function** ← Search first!
- [ ] Two files read the same untyped payload field with local casts
- [ ] Multiple branches update the same derived state from `kind` / `action`
→ Read [Code Reuse Thinking Guide](./code-reuse-thinking-guide.md)
### When Verifying AI Cross-Review Results
- [ ] Reviewer claims "user input can be malicious" → Check the actual data source (internal manifest? user config? external API?)
- [ ] Reviewer flags "missing validation" → Is the data from a trusted internal source?
- [ ] Reviewer says "behavior change" → Read the code comments — is it intentional design?
- [ ] Reviewer identifies a "bug" in test → Mentally delete the feature being tested — does the test still pass? If yes → tautological test
**Common AI reviewer false-positive patterns**:
1. **Trust boundary confusion**: Treating internal data (bundled JSON manifests) as untrusted external input
2. **Ignoring design comments**: Flagging intentional behavior documented in code comments as bugs
3. **Variable misreading**: Not tracing a variable to its actual definition (e.g., Map keyed by path vs name)
**Verification rule**: Every CRITICAL/WARNING finding must be verified against the actual code before prioritizing. Budget ~35% false-positive rate for AI reviews.
---
## Pre-Modification Rule (CRITICAL)
> **Before changing ANY value, ALWAYS search first!**
```bash
# Search for the value you're about to change
grep -r "value_to_change" .
```
This single habit prevents most "forgot to update X" bugs.
---
## How to Use This Directory
1. **Before coding**: Skim the relevant thinking guide
2. **During coding**: If something feels repetitive or complex, check the guides
3. **After bugs**: Add new insights to the relevant guide (learn from mistakes)
---
## Contributing
Found a new "didn't think of that" moment? Add it to the relevant guide.
---
**Core Principle**: 30 minutes of thinking saves 3 hours of debugging.
.trellis/spec/vendor/ComfyUI_frontend/frontend/component-guidelines.md
Vendored
+59
View File
@@ -0,0 +1,59 @@
# Component Guidelines
> How components are built in this project.
---
## Overview
<!--
Document your project's component conventions here.
Questions to answer:
- What component patterns do you use?
- How are props defined?
- How do you handle composition?
- What accessibility standards apply?
-->
(To be filled by the team)
---
## Component Structure
<!-- Standard structure of a component file -->
(To be filled by the team)
---
## Props Conventions
<!-- How props should be defined and typed -->
(To be filled by the team)
---
## Styling Patterns
<!-- How styles are applied (CSS modules, styled-components, Tailwind, etc.) -->
(To be filled by the team)
---
## Accessibility
<!-- A11y requirements and patterns -->
(To be filled by the team)
---
## Common Mistakes
<!-- Component-related mistakes your team has made -->
(To be filled by the team)
.trellis/spec/vendor/ComfyUI_frontend/frontend/directory-structure.md
Vendored
+54
View File
@@ -0,0 +1,54 @@
# Directory Structure
> How frontend code is organized in this project.
---
## Overview
<!--
Document your project's frontend directory structure here.
Questions to answer:
- Where do components live?
- How are features/modules organized?
- Where are shared utilities?
- How are assets organized?
-->
(To be filled by the team)
---
## Directory Layout
```
<!-- Replace with your actual structure -->
src/
├── ...
└── ...
```
---
## Module Organization
<!-- How should new features be organized? -->
(To be filled by the team)
---
## Naming Conventions
<!-- File and folder naming rules -->
(To be filled by the team)
---
## Examples
<!-- Link to well-organized modules as examples -->
(To be filled by the team)
.trellis/spec/vendor/ComfyUI_frontend/frontend/hook-guidelines.md
Vendored
+51
View File
@@ -0,0 +1,51 @@
# Hook Guidelines
> How hooks are used in this project.
---
## Overview
<!--
Document your project's hook conventions here.
Questions to answer:
- What custom hooks do you have?
- How do you handle data fetching?
- What are the naming conventions?
- How do you share stateful logic?
-->
(To be filled by the team)
---
## Custom Hook Patterns
<!-- How to create and structure custom hooks -->
(To be filled by the team)
---
## Data Fetching
<!-- How data fetching is handled (React Query, SWR, etc.) -->
(To be filled by the team)
---
## Naming Conventions
<!-- Hook naming rules (use*, etc.) -->
(To be filled by the team)
---
## Common Mistakes
<!-- Hook-related mistakes your team has made -->
(To be filled by the team)
.trellis/spec/vendor/ComfyUI_frontend/frontend/index.md
Vendored
+39
View File
@@ -0,0 +1,39 @@
# Frontend Development Guidelines
> Best practices for frontend development in this project.
---
## Overview
This directory contains guidelines for frontend development. Fill in each file with your project's specific conventions.
---
## Guidelines Index
| Guide | Description | Status |
|-------|-------------|--------|
| [Directory Structure](./directory-structure.md) | Module organization and file layout | To fill |
| [Component Guidelines](./component-guidelines.md) | Component patterns, props, composition | To fill |
| [Hook Guidelines](./hook-guidelines.md) | Custom hooks, data fetching patterns | To fill |
| [State Management](./state-management.md) | Local state, global state, server state | To fill |
| [Quality Guidelines](./quality-guidelines.md) | Code standards, forbidden patterns | To fill |
| [Type Safety](./type-safety.md) | Type patterns, validation | To fill |
---
## How to Fill These Guidelines
For each guideline file:
1. Document your project's **actual conventions** (not ideals)
2. Include **code examples** from your codebase
3. List **forbidden patterns** and why
4. Add **common mistakes** your team has made
The goal is to help AI assistants and new team members understand how YOUR project works.
---
**Language**: All documentation should be written in **English**.
.trellis/spec/vendor/ComfyUI_frontend/frontend/quality-guidelines.md
Vendored
+51
View File
@@ -0,0 +1,51 @@
# Quality Guidelines
> Code quality standards for frontend development.
---
## Overview
<!--
Document your project's quality standards here.
Questions to answer:
- What patterns are forbidden?
- What linting rules do you enforce?
- What are your testing requirements?
- What code review standards apply?
-->
(To be filled by the team)
---
## Forbidden Patterns
<!-- Patterns that should never be used and why -->
(To be filled by the team)
---
## Required Patterns
<!-- Patterns that must always be used -->
(To be filled by the team)
---
## Testing Requirements
<!-- What level of testing is expected -->
(To be filled by the team)
---
## Code Review Checklist
<!-- What reviewers should check -->
(To be filled by the team)
.trellis/spec/vendor/ComfyUI_frontend/frontend/state-management.md
Vendored
+51
View File
@@ -0,0 +1,51 @@
# State Management
> How state is managed in this project.
---
## Overview
<!--
Document your project's state management conventions here.
Questions to answer:
- What state management solution do you use?
- How is local vs global state decided?
- How do you handle server state?
- What are the patterns for derived state?
-->
(To be filled by the team)
---
## State Categories
<!-- Local state, global state, server state, URL state -->
(To be filled by the team)
---
## When to Use Global State
<!-- Criteria for promoting state to global -->
(To be filled by the team)
---
## Server State
<!-- How server data is cached and synchronized -->
(To be filled by the team)
---
## Common Mistakes
<!-- State management mistakes your team has made -->
(To be filled by the team)
.trellis/spec/vendor/ComfyUI_frontend/frontend/type-safety.md
Vendored
+51
View File
@@ -0,0 +1,51 @@
# Type Safety
> Type safety patterns in this project.
---
## Overview
<!--
Document your project's type safety conventions here.
Questions to answer:
- What type system do you use?
- How are types organized?
- What validation library do you use?
- How do you handle type inference?
-->
(To be filled by the team)
---
## Type Organization
<!-- Where types are defined, shared types vs local types -->
(To be filled by the team)
---
## Validation
<!-- Runtime validation patterns (Zod, Yup, io-ts, etc.) -->
(To be filled by the team)
---
## Common Patterns
<!-- Type utilities, generics, type guards -->
(To be filled by the team)
---
## Forbidden Patterns
<!-- any, type assertions, etc. -->
(To be filled by the team)
.trellis/tasks/00-bootstrap-guidelines/prd.md
+119
View File
@@ -0,0 +1,119 @@
# Bootstrap Task: Fill Project Development Guidelines
**You (the AI) are running this task. The developer does not read this file.**
The developer just ran `trellis init` on this project for the first time.
`.trellis/` now exists with empty spec scaffolding, and this bootstrap task
exists under `.trellis/tasks/`. When they want to work on it, they should start
this task from a session that provides Trellis session identity.
**Your job**: help them populate `.trellis/spec/` with the team's real
coding conventions. Every future AI session — this project's
`trellis-implement` and `trellis-check` sub-agents — auto-loads spec files
listed in per-task jsonl manifests. Empty spec = sub-agents write generic
code. Real spec = sub-agents match the team's actual patterns.
Don't dump instructions. Open with a short greeting, figure out if the repo
has any existing convention docs (CLAUDE.md, .cursorrules, etc.), and drive
the rest conversationally.
---
## Status (update the checkboxes as you complete each item)
- [ ] Fill guidelines for vendor/ComfyUI_frontend
- [ ] Add code examples
---
## Spec files to populate
### Package: vendor/ComfyUI_frontend (`spec/vendor/ComfyUI_frontend/`)
- Frontend guidelines: `.trellis/spec/vendor/ComfyUI_frontend/frontend/`
### Thinking guides (already populated)
`.trellis/spec/guides/` contains general thinking guides pre-filled with
best practices. Customize only if something clearly doesn't fit this project.
---
## How to fill the spec
### Step 1: Import from existing convention files first (preferred)
Search the repo for existing convention docs. If any exist, read them and
extract the relevant rules into the matching `.trellis/spec/` files —
usually much faster than documenting from scratch.
| File / Directory | Tool |
|------|------|
| `CLAUDE.md` / `CLAUDE.local.md` | Claude Code |
| `AGENTS.md` | Codex / Claude Code / agent-compatible tools |
| `.cursorrules` | Cursor |
| `.cursor/rules/*.mdc` | Cursor (rules directory) |
| `.windsurfrules` | Windsurf |
| `.clinerules` | Cline |
| `.roomodes` | Roo Code |
| `.github/copilot-instructions.md` | GitHub Copilot |
| `.vscode/settings.json` → `github.copilot.chat.codeGeneration.instructions` | VS Code Copilot |
| `CONVENTIONS.md` / `.aider.conf.yml` | aider |
| `CONTRIBUTING.md` | General project conventions |
| `.editorconfig` | Editor formatting rules |
### Step 2: Analyze the codebase for anything not covered by existing docs
Scan real code to discover patterns. Before writing each spec file:
- Find 2-3 real examples of each pattern in the codebase.
- Reference real file paths (not hypothetical ones).
- Document anti-patterns the team clearly avoids.
### Step 3: Document reality, not ideals
**Critical**: write what the code *actually does*, not what it should do.
Sub-agents match the spec, so aspirational patterns that don't exist in the
codebase will cause sub-agents to write code that looks out of place.
If the team has known tech debt, document the current state — improvement
is a separate conversation, not a bootstrap concern.
---
## Quick explainer of the runtime (share when they ask "why do we need spec at all")
- Every AI coding task spawns two sub-agents: `trellis-implement` (writes
code) and `trellis-check` (verifies quality).
- Each task has `implement.jsonl` / `check.jsonl` manifests listing which
spec files to load.
- The platform hook auto-injects those spec files + the task's `prd.md`
into every sub-agent prompt, so the sub-agent codes/reviews per team
conventions without anyone pasting them manually.
- Source of truth: `.trellis/spec/`. That's why filling it well now pays
off forever.
---
## Completion
When the developer confirms the checklist items above are done with real
examples (not placeholders), guide them to run:
```bash
python3 ./.trellis/scripts/task.py finish
python3 ./.trellis/scripts/task.py archive 00-bootstrap-guidelines
```
After archive, every new developer who joins this project will get a
`00-join-<slug>` onboarding task instead of this bootstrap task.
---
## Suggested opening line
"Welcome to Trellis! Your init just set me up to help you fill the project
spec — a one-time setup so every future AI session follows the team's
conventions instead of writing generic code. Before we start, do you have
any existing convention docs (CLAUDE.md, .cursorrules, CONTRIBUTING.md,
etc.) I can pull from, or should I scan the codebase from scratch?"
.trellis/tasks/00-bootstrap-guidelines/task.json
+28
View File
@@ -0,0 +1,28 @@
{
"id": "00-bootstrap-guidelines",
"name": "00-bootstrap-guidelines",
"title": "Bootstrap Guidelines",
"description": "Fill in project development guidelines for AI agents",
"status": "in_progress",
"dev_type": "docs",
"scope": null,
"package": null,
"priority": "P1",
"creator": "boos4721",
"assignee": "boos4721",
"createdAt": "2026-06-20",
"completedAt": null,
"branch": null,
"base_branch": null,
"worktree_path": null,
"commit": null,
"pr_url": null,
"subtasks": [],
"children": [],
"parent": null,
"relatedFiles": [
".trellis/spec/vendor/ComfyUI_frontend/"
],
"notes": "First-time setup task created by trellis init (fullstack project)",
"meta": {}
}
.trellis/workflow.md
+706
View File
@@ -0,0 +1,706 @@
# Development Workflow
---
## Core Principles
1. **Plan before code** — figure out what to do before you start
2. **Specs injected, not remembered** — guidelines are injected via hook/skill, not recalled from memory
3. **Persist everything** — research, decisions, and lessons all go to files; conversations get compacted, files don't
4. **Incremental development** — one task at a time
5. **Capture learnings** — after each task, review and write new knowledge back to spec
---
## Trellis System
### Developer Identity
On first use, initialize your identity:
```bash
python3 ./.trellis/scripts/init_developer.py <your-name>
```
Creates `.trellis/.developer` (gitignored) + `.trellis/workspace/<your-name>/`.
### Spec System
`.trellis/spec/` holds coding guidelines organized by package and layer.
- `.trellis/spec/<package>/<layer>/index.md` — entry point with **Pre-Development Checklist** + **Quality Check**. Actual guidelines live in the `.md` files it points to.
- `.trellis/spec/guides/index.md` — cross-package thinking guides.
```bash
python3 ./.trellis/scripts/get_context.py --mode packages # list packages / layers
```
**When to update spec**: new pattern/convention found · bug-fix prevention to codify · new technical decision.
### Task System
Every task has its own directory under `.trellis/tasks/{MM-DD-name}/` holding `task.json`, `prd.md`, optional `design.md`, optional `implement.md`, optional `research/`, and context manifests (`implement.jsonl`, `check.jsonl`) for sub-agent-capable platforms.
```bash
# Task lifecycle
python3 ./.trellis/scripts/task.py create "<title>" [--slug <name>] [--parent <dir>]
python3 ./.trellis/scripts/task.py start <name> # set active task (session-scoped when available)
python3 ./.trellis/scripts/task.py current --source # show active task and source
python3 ./.trellis/scripts/task.py finish # clear active task (triggers after_finish hooks)
python3 ./.trellis/scripts/task.py archive <name> # move to archive/{year-month}/
python3 ./.trellis/scripts/task.py list [--mine] [--status <s>]
python3 ./.trellis/scripts/task.py list-archive
# Code-spec context (injected into implement/check agents via JSONL).
# `implement.jsonl` / `check.jsonl` are seeded on `task create` for sub-agent-capable
# platforms; the AI curates real spec + research entries during planning when needed.
python3 ./.trellis/scripts/task.py add-context <name> <action> <file> <reason>
python3 ./.trellis/scripts/task.py list-context <name> [action]
python3 ./.trellis/scripts/task.py validate <name>
# Task metadata
python3 ./.trellis/scripts/task.py set-branch <name> <branch>
python3 ./.trellis/scripts/task.py set-base-branch <name> <branch> # PR target
python3 ./.trellis/scripts/task.py set-scope <name> <scope>
# Hierarchy (parent/child)
python3 ./.trellis/scripts/task.py add-subtask <parent> <child>
python3 ./.trellis/scripts/task.py remove-subtask <parent> <child>
# PR creation
python3 ./.trellis/scripts/task.py create-pr [name] [--dry-run]
```
> Run `python3 ./.trellis/scripts/task.py --help` to see the authoritative, up-to-date list.
**Current-task mechanism**: `task.py create` creates the task directory and (when session identity is available) auto-sets the per-session active-task pointer so the planning breadcrumb fires immediately. `task.py start` writes the same pointer (idempotent if already set) and flips `task.json.status` from `planning` to `in_progress`. State is stored under `.trellis/.runtime/sessions/`. If no context key is available from hook input, `TRELLIS_CONTEXT_ID`, or a platform-native session environment variable, there is no active task and `task.py start` fails with a session identity hint. `task.py finish` deletes the current session file (status unchanged). `task.py archive <task>` writes `status=completed`, moves the directory to `archive/`, and deletes any runtime session files that still point at the archived task.
### Workspace System
Records every AI session for cross-session tracking under `.trellis/workspace/<developer>/`.
- `journal-N.md` — session log. **Max 2000 lines per file**; a new `journal-(N+1).md` is auto-created when exceeded.
- `index.md` — personal index (total sessions, last active).
```bash
python3 ./.trellis/scripts/add_session.py --title "Title" --commit "hash" --summary "Summary"
```
### Context Script
```bash
python3 ./.trellis/scripts/get_context.py # full session runtime
python3 ./.trellis/scripts/get_context.py --mode packages # available packages + spec layers
python3 ./.trellis/scripts/get_context.py --mode phase --step <X.Y> # detailed guide for a workflow step
```
---
<!--
WORKFLOW-STATE BREADCRUMB CONTRACT (read this before editing the tag blocks below)
The [workflow-state:STATUS] blocks embedded in the ## Phase Index section
below are the SINGLE source of truth for the per-turn `<workflow-state>`
breadcrumb that every supported AI platform's UserPromptSubmit hook
reads. inject-workflow-state.py (Python platforms) and
inject-workflow-state.js (OpenCode plugin) only parse them — there is no
fallback dict baked into the scripts after v0.5.0-rc.0.
STATUS charset: [A-Za-z0-9_-]+. When the hook can't find a tag, it
degrades to a generic "Refer to workflow.md for current step." line —
intentionally visible so users notice and fix a broken workflow.md.
INVARIANT (test/regression.test.ts):
Every workflow-walkthrough step marked `[required · once]` must have a
matching enforcement line in its phase's [workflow-state:*] block. The
breadcrumb is the only per-turn channel; if a mandatory step isn't
mentioned there, the AI silently skips it (Phase 1 planning gate
skip and Phase 3.4 commit skip both manifested via this gap).
TAG ↔ PHASE scoping:
[workflow-state:no_task] → no active task; before Phase 1
[workflow-state:planning] → all of Phase 1 (status='planning')
[workflow-state:planning-inline] → Codex inline variant of Phase 1
[workflow-state:in_progress] → Phase 2 + Phase 3.2-3.4
(status stays 'in_progress' from
task.py start until task.py archive)
[workflow-state:in_progress-inline] → Codex inline variant of Phase 2/3
[workflow-state:completed] → currently DEAD: cmd_archive flips
status and moves the dir in the same
call, so the resolver loses the
pointer (block kept for a future
explicit in_progress→completed
transition)
Editing checklist:
- When you change a [workflow-state:STATUS] block, also check the
matching phase's `[required · once]` walkthrough steps for sync
- Run `trellis update` after editing to push the new bodies to
downstream user projects (block-level managed replacement)
- Full runtime contract:
.trellis/spec/cli/backend/workflow-state-contract.md
-->
## Phase Index
```
Phase 1: Plan → classify, get task-creation consent, then write planning artifacts
Phase 2: Execute → implement only after task status is in_progress
Phase 3: Finish → verify, update spec, commit, and wrap up
```
### Request Triage
- Simple conversation or small task: ask only whether this turn should create a Trellis task. If the user says no, skip Trellis for this session.
- Complex task: ask whether you may create a Trellis task and enter planning. If the user says no, do not do broad inline implementation; explain, clarify scope, or suggest a smaller split.
- User approval to create a task is not approval to start implementation. Planning still happens first.
### Planning Artifacts
- `prd.md` — requirements, constraints, and acceptance criteria. Do not put technical design or execution checklists here.
- `design.md` — technical design for complex tasks: boundaries, contracts, data flow, tradeoffs, compatibility, rollout / rollback shape.
- `implement.md` — execution plan for complex tasks: ordered checklist, validation commands, review gates, and rollback points.
- `implement.jsonl` / `check.jsonl` — spec and research manifests for sub-agent context. They do not replace `implement.md`.
- Lightweight tasks may be PRD-only. Complex tasks must have `prd.md`, `design.md`, and `implement.md` before `task.py start`.
### Parent / Child Task Trees
Use a parent task when one user request contains several independently verifiable deliverables. The parent task owns the source requirement set, the task map, cross-child acceptance criteria, and final integration review; it normally should not be the implementation target unless it also has direct work.
Use child tasks for deliverables that can be planned, implemented, checked, and archived independently. Parent/child structure is not a dependency system: if one child must wait for another, write that ordering in the child `prd.md` / `implement.md` and keep each child's acceptance criteria testable.
Create new children with `task.py create "<title>" --slug <name> --parent <parent-dir>`. Link existing tasks with `task.py add-subtask <parent> <child>`, and unlink mistakes with `task.py remove-subtask <parent> <child>`.
<!-- Per-turn breadcrumb: shown when there is no active task (before Phase 1) -->
[workflow-state:no_task]
No active task. First classify the current turn and ask for task-creation consent before creating any Trellis task.
Simple conversation / small task: ask only whether this turn should create a Trellis task. If the user says no, skip Trellis for this session.
Complex task: ask the user if you can create a Trellis task and enter the planning phase. If the user says no, explain, clarify scope, or suggest a smaller split.
[/workflow-state:no_task]
### Phase 1: Plan
- 1.0 Create task `[required · once]` (only after task-creation consent)
- 1.1 Requirement exploration `[required · repeatable]` (`prd.md`; complex tasks also need `design.md` + `implement.md`)
- 1.2 Research `[optional · repeatable]`
- 1.3 Configure context `[required · once]` — Claude Code, Cursor, OpenCode, Codex, Kiro, Gemini, Qoder, CodeBuddy, Copilot, Droid, Pi (sub-agent-dispatch platforms only; inline platforms skip)
- 1.4 Activate task `[required · once]` (review gate, then `task.py start`; status → in_progress)
- 1.5 Completion criteria
<!-- Per-turn breadcrumb: shown throughout Phase 1 (status='planning') -->
[workflow-state:planning]
Load `trellis-brainstorm`; stay in planning.
Lightweight: `prd.md` can be enough. Complex: finish `prd.md`, `design.md`, and `implement.md`; ask for review before `task.py start`.
Multi-deliverable scope: consider a parent task plus independently verifiable child tasks; dependencies must be written in child artifacts, not implied by tree position.
Sub-agent mode: curate `implement.jsonl` and `check.jsonl` as spec/research manifests before start.
[/workflow-state:planning]
<!-- Per-turn breadcrumb: shown throughout Phase 1 when codex.dispatch_mode=inline.
Codex-only opt-in alternate to [workflow-state:planning]. The main agent
edits code directly in Phase 2, so jsonl curation is skipped —
the inline workflow loads `trellis-before-dev` instead of injecting JSONL
into a sub-agent. -->
[workflow-state:planning-inline]
Load `trellis-brainstorm`; stay in planning.
Lightweight: `prd.md` can be enough. Complex: finish `prd.md`, `design.md`, and `implement.md`; ask for review before `task.py start`.
Multi-deliverable scope: consider a parent task plus independently verifiable child tasks; dependencies must be written in child artifacts, not implied by tree position.
Inline mode: skip jsonl curation; Phase 2 reads artifacts/specs via `trellis-before-dev`.
[/workflow-state:planning-inline]
### Phase 2: Execute
- 2.1 Implement `[required · repeatable]`
- 2.2 Quality check `[required · repeatable]`
- 2.3 Rollback `[on demand]`
<!-- Per-turn breadcrumb: shown while status='in_progress'.
Scope: all of Phase 2 + Phase 3.2-3.4 (status stays 'in_progress' from
task.py start until task.py archive; only archive flips it). The body
therefore must cover every required step from implementation through
commit, including Phase 3.3 spec update and Phase 3.4 commit. -->
Sub-agent dispatch protocol applies to all platforms and all sub-agents, including class-2 Codex/Copilot/Gemini/Qoder and `trellis-research`: every dispatch prompt starts with `Active task: <task path from task.py current>` before role-specific instructions.
[workflow-state:in_progress]
Tools: `trellis-implement` / `trellis-research` are sub-agent types only (Task/Agent tool, NOT Skill; there is no skill by these names). `trellis-update-spec` is a skill. `trellis-check` exists as both; prefer the Agent form when verifying after code changes.
Flow: `trellis-implement` -> `trellis-check` -> `trellis-update-spec` -> commit (Phase 3.4) -> `/trellis:finish-work`.
Main-session default: dispatch implement/check sub-agents. Sub-agent self-exemption: if already running as `trellis-implement`, do NOT spawn another `trellis-implement` or `trellis-check`; if already running as `trellis-check`, do NOT spawn another `trellis-check` or `trellis-implement`. Dispatch is main session only.
Dispatch prompt starts with `Active task: <task path from task.py current>`. Read context: jsonl entries -> `prd.md` -> `design.md if present` -> `implement.md if present`.
[/workflow-state:in_progress]
<!-- Per-turn breadcrumb: shown while status='in_progress' when
codex.dispatch_mode=inline. Codex-only opt-in alternate to
[workflow-state:in_progress]. The main session edits code directly
instead of dispatching sub-agents. -->
[workflow-state:in_progress-inline]
Flow: `trellis-before-dev` -> edit -> `trellis-check` -> validation -> `trellis-update-spec` -> commit (Phase 3.4) -> `/trellis:finish-work`.
Do not dispatch implement/check sub-agents in inline mode.
Read context: `prd.md` -> `design.md if present` -> `implement.md if present`, plus relevant spec/research loaded by skills.
[/workflow-state:in_progress-inline]
### Phase 3: Finish
- 3.2 Debug retrospective `[on demand]`
- 3.3 Spec update `[required · once]`
- 3.4 Commit changes `[required · once]`
- 3.5 Wrap-up reminder
> Note: step 3.1 was folded into 2.2 (last-iteration full-scope check) and 3.4 (commit preamble). Numbering kept stable to avoid breaking external references.
<!-- Per-turn breadcrumb: shown while status='completed'.
Currently DEAD in normal flow: cmd_archive writes status='completed' in
the same call that moves the task dir to archive/, so the active-task
resolver loses the pointer and the hook never fires on archived tasks.
Block preserved for a future status-transition redesign (e.g. an
explicit in_progress→completed command). Edit through the same spec
channel as the live blocks. -->
[workflow-state:completed]
Code committed. Run `/trellis:finish-work`; if dirty, return to Phase 3.4 first.
[/workflow-state:completed]
### Rules
1. Identify which Phase you're in, then continue from the next step there
2. Run steps in order inside each Phase; `[required]` steps can't be skipped
3. Phases can roll back (e.g., Execute reveals a prd defect → return to Plan to fix, then re-enter Execute)
4. Steps tagged `[once]` are skipped if the output already exists; don't re-run
5. Artifact presence informs the next step; missing `design.md` / `implement.md` is valid for lightweight tasks and incomplete planning for complex tasks.
### Active Task Routing
When a user request matches one of these intents inside an active task, route first, then load the detailed phase step if needed.
[Claude Code, Cursor, OpenCode, codex-sub-agent, Kiro, Gemini, Qoder, CodeBuddy, Copilot, Droid, Pi]
- Planning or unclear requirements -> `trellis-brainstorm`.
- `in_progress` implementation/check -> dispatch `trellis-implement` / `trellis-check`.
- Repeated debugging -> `trellis-break-loop`; spec updates -> `trellis-update-spec`.
[/Claude Code, Cursor, OpenCode, codex-sub-agent, Kiro, Gemini, Qoder, CodeBuddy, Copilot, Droid, Pi]
[codex-inline, Kilo, Antigravity, Devin]
- Planning or unclear requirements -> `trellis-brainstorm`.
- Before editing -> `trellis-before-dev`; after editing -> `trellis-check`.
- Repeated debugging -> `trellis-break-loop`; spec updates -> `trellis-update-spec`.
[/codex-inline, Kilo, Antigravity, Devin]
### Guardrails
- Task creation approval is not implementation approval; implementation waits for `task.py start` after artifact review.
- PRD-only is valid for lightweight tasks; complex tasks need `design.md` + `implement.md`.
- Planning must be persisted to task artifacts; checks must run before reporting completion.
### Loading Step Detail
At each step, run this to fetch detailed guidance:
```bash
python3 ./.trellis/scripts/get_context.py --mode phase --step <step>
# e.g. python3 ./.trellis/scripts/get_context.py --mode phase --step 1.1
```
---
## Phase 1: Plan
Goal: classify the request, get task-creation consent when a task is needed, and produce the planning artifacts required before implementation.
#### 1.0 Create task `[required · once]`
Create the task directory only after task-creation consent. The command sets status to `planning`, writes `task.json`, creates a default `prd.md`, and auto-targets the new task when session identity is available:
```bash
python3 ./.trellis/scripts/task.py create "<task title>" --slug <name>
```
`--slug` is the human-readable name only. Do **not** include the `MM-DD-` date prefix; `task.py create` adds that prefix automatically.
For task trees, create the parent task first and then create each child with `--parent <parent-dir>`. Do not start the parent just because children exist; start the child that owns the next independently verifiable deliverable.
After this command succeeds, the per-turn breadcrumb auto-switches to `[workflow-state:planning]`, telling the AI to stay in planning.
Run only `create` here — do not also run `start`. `start` flips status to `in_progress`, which switches the breadcrumb to the implementation phase before planning artifacts are reviewed. Save `start` for step 1.4.
Skip when `python3 ./.trellis/scripts/task.py current --source` already points to a task.
#### 1.1 Requirement exploration `[required · repeatable]`
Load the `trellis-brainstorm` skill and explore requirements interactively with the user per the skill's guidance.
The brainstorm skill will guide you to:
- Ask one question at a time
- Prefer researching over asking the user
- Prefer offering options over open-ended questions
- Update `prd.md` immediately after each user answer
- Split large scopes into a parent task plus child tasks when the deliverables can be verified independently
- Keep `prd.md` focused on requirements and acceptance criteria
- For complex tasks, produce `design.md` and `implement.md` before implementation starts
When considering a parent/child split:
- Use a parent task when one request contains several independently verifiable deliverables.
- Parent tasks own source requirements, child-task mapping, cross-child acceptance criteria, and final integration review.
- Child tasks own actual deliverables that can be planned, implemented, checked, and archived independently.
- Parent/child structure is not a dependency system. If child B depends on child A, write that ordering in child B's `prd.md` / `implement.md`.
- Start the child task that owns the next deliverable. Do not start the parent unless the parent itself has direct implementation work.
Return to this step whenever requirements change and revise the relevant artifact.
#### 1.2 Research `[optional · repeatable]`
Research can happen at any time during requirement exploration. It isn't limited to local code — you can use any available tool (MCP servers, skills, web search, etc.) to look up external information, including third-party library docs, industry practices, API references, etc.
[Claude Code, Cursor, OpenCode, codex-sub-agent, Kiro, Gemini, Qoder, CodeBuddy, Copilot, Droid, Pi]
Spawn the research sub-agent:
- **Agent type**: `trellis-research`
- **Task description**: Research <specific question>
- **Key requirement**: Research output MUST be persisted to `{TASK_DIR}/research/`
[/Claude Code, Cursor, OpenCode, codex-sub-agent, Kiro, Gemini, Qoder, CodeBuddy, Copilot, Droid, Pi]
[codex-inline, Kilo, Antigravity, Devin]
Do the research in the main session directly and write findings into `{TASK_DIR}/research/`. (For `codex-inline` this avoids the `fork_turns="none"` isolation that prevents `trellis-research` sub-agents from resolving the active task path.)
[/codex-inline, Kilo, Antigravity, Devin]
**Research artifact conventions**:
- One file per research topic (e.g. `research/auth-library-comparison.md`)
- Record third-party library usage examples, API references, version constraints in files
- Note relevant spec file paths you discovered for later reference
Brainstorm and research can interleave freely — pause to research a technical question, then return to talk with the user.
**Key principle**: Research output must be written to files, not left only in the chat. Conversations get compacted; files don't.
#### 1.3 Configure context `[required · once]`
[Claude Code, Cursor, OpenCode, codex-sub-agent, Kiro, Gemini, Qoder, CodeBuddy, Copilot, Droid, Pi]
Curate `implement.jsonl` and `check.jsonl` so the Phase 2 sub-agents get the right spec/research context. These files were seeded on `task create` with a single self-describing `_example` line; your job here is to fill in real entries.
**Location**: `{TASK_DIR}/implement.jsonl` and `{TASK_DIR}/check.jsonl` (already exist).
**Format**: one JSON object per line — `{"file": "<path>", "reason": "<why>"}`. Paths are repo-root relative.
**What to put in**:
- **Spec files** — `.trellis/spec/<package>/<layer>/index.md` and any specific guideline files (`error-handling.md`, `conventions.md`, etc.) relevant to this task
- **Research files** — `{TASK_DIR}/research/*.md` that the sub-agent will need to consult
**What NOT to put in**:
- Code files (`src/**`, `packages/**/*.ts`, etc.) — those are read by the sub-agent during implementation, not pre-registered here
- Files you're about to modify — same reason
**Split between the two files**:
- `implement.jsonl` → specs + research the implement sub-agent needs to write code correctly
- `check.jsonl` → specs for the check sub-agent (quality guidelines, check conventions, same research if needed)
These manifests do not replace `implement.md`. `implement.md` is the human-readable execution plan for a complex task; jsonl files only list context files to inject or load.
**How to discover relevant specs**:
```bash
python3 ./.trellis/scripts/get_context.py --mode packages
```
Lists every package + its spec layers with paths. Pick the entries that match this task's domain.
**How to append entries**:
Either edit the jsonl file directly in your editor, or use:
```bash
python3 ./.trellis/scripts/task.py add-context "$TASK_DIR" implement "<path>" "<reason>"
python3 ./.trellis/scripts/task.py add-context "$TASK_DIR" check "<path>" "<reason>"
```
Delete the seed `_example` line once real entries exist (optional — it's skipped automatically by consumers).
Skip when: `implement.jsonl` and `check.jsonl` have agent-curated entries (the seed row alone doesn't count).
[/Claude Code, Cursor, OpenCode, codex-sub-agent, Kiro, Gemini, Qoder, CodeBuddy, Copilot, Droid, Pi]
[codex-inline, Kilo, Antigravity, Devin]
Skip this step. Context is loaded directly by the `trellis-before-dev` skill in Phase 2.
[/codex-inline, Kilo, Antigravity, Devin]
#### 1.4 Activate task `[required · once]`
After artifact review, flip the task status to `in_progress`:
```bash
python3 ./.trellis/scripts/task.py start <task-dir>
```
For lightweight tasks, `prd.md` can be enough. For complex tasks, `prd.md`, `design.md`, and `implement.md` must exist and be reviewed before start. On sub-agent-capable platforms, curate jsonl manifests when extra spec or research context is needed; seed-only manifests are tolerated by consumers.
After this command succeeds, the breadcrumb auto-switches to `[workflow-state:in_progress]`, and the rest of Phase 2 / 3 follows.
If `task.py start` errors with a session-identity message (no context key from hook input, `TRELLIS_CONTEXT_ID`, or platform-native session env), follow the hint in the error to set up session identity, then retry.
#### 1.5 Completion criteria
| Condition | Required |
|------|:---:|
| `prd.md` exists | ✅ |
| User confirms task should enter implementation | ✅ |
| `task.py start` has been run (status = in_progress) | ✅ |
| `research/` has artifacts (complex tasks) | recommended |
| `design.md` exists (complex tasks) | ✅ |
| `implement.md` exists (complex tasks) | ✅ |
[Claude Code, Cursor, OpenCode, codex-sub-agent, Kiro, Gemini, Qoder, CodeBuddy, Copilot, Droid, Pi]
| `implement.jsonl` / `check.jsonl` curated when extra spec or research context is needed | recommended |
[/Claude Code, Cursor, OpenCode, codex-sub-agent, Kiro, Gemini, Qoder, CodeBuddy, Copilot, Droid, Pi]
---
## Phase 2: Execute
Goal: turn reviewed planning artifacts into code that passes quality checks.
#### 2.1 Implement `[required · repeatable]`
[Claude Code, Cursor, OpenCode, Gemini, Qoder, CodeBuddy, Copilot, Droid, Pi]
Spawn the implement sub-agent:
- **Agent type**: `trellis-implement`
- **Task description**: Implement the reviewed task artifacts, consulting materials under `{TASK_DIR}/research/`; finish by running project lint and type-check
- **Dispatch prompt guard**: Tell the spawned agent it is already the `trellis-implement` sub-agent and must implement directly, not spawn another `trellis-implement` / `trellis-check`.
The platform hook/plugin auto-handles:
- Reads `implement.jsonl` and injects referenced spec/research files into the agent prompt
- Injects `prd.md`, `design.md` if present, and `implement.md` if present
[/Claude Code, Cursor, OpenCode, Gemini, Qoder, CodeBuddy, Copilot, Droid, Pi]
[codex-sub-agent]
Spawn the implement sub-agent:
- **Agent type**: `trellis-implement`
- **Task description**: Implement the reviewed task artifacts, consulting materials under `{TASK_DIR}/research/`; finish by running project lint and type-check
- **Dispatch prompt guard**: The prompt MUST start with `Active task: <task path>`, then explicitly say the spawned agent is already `trellis-implement` and must implement directly without spawning another `trellis-implement` / `trellis-check`.
The Codex sub-agent definition auto-handles the context load requirement:
- Resolves the active task with `task.py current --source`, then reads `prd.md`, `design.md` if present, and `implement.md` if present
- Reads `implement.jsonl` and requires the agent to load each referenced spec/research file before coding
[/codex-sub-agent]
[Kiro]
Spawn the implement sub-agent:
- **Agent type**: `trellis-implement`
- **Task description**: Implement the reviewed task artifacts, consulting materials under `{TASK_DIR}/research/`; finish by running project lint and type-check
- **Dispatch prompt guard**: Tell the spawned agent it is already the `trellis-implement` sub-agent and must implement directly, not spawn another `trellis-implement` / `trellis-check`.
The platform prelude auto-handles the context load requirement:
- Reads `implement.jsonl` and injects referenced spec/research files into the agent prompt
- Injects `prd.md`, `design.md` if present, and `implement.md` if present
[/Kiro]
[codex-inline, Kilo, Antigravity, Devin]
1. Load the `trellis-before-dev` skill to read project guidelines
2. Read `{TASK_DIR}/prd.md`, then `design.md` if present, then `implement.md` if present
3. Consult materials under `{TASK_DIR}/research/`
4. Implement the code per reviewed artifacts
5. Run project lint and type-check
[/codex-inline, Kilo, Antigravity, Devin]
#### 2.2 Quality check `[required · repeatable]`
[Claude Code, Cursor, OpenCode, codex-sub-agent, Kiro, Gemini, Qoder, CodeBuddy, Copilot, Droid, Pi]
Spawn the check sub-agent:
- **Agent type**: `trellis-check`
- **Task description**: Review all code changes against specs and task artifacts; fix any findings directly; ensure lint and type-check pass
- **Dispatch prompt guard**: Tell the spawned agent it is already the `trellis-check` sub-agent and must review/fix directly, not spawn another `trellis-check` / `trellis-implement`.
The check agent's job:
- Review code changes against specs
- Review code changes against `prd.md`, `design.md` if present, and `implement.md` if present
- Auto-fix issues it finds
- Run lint and typecheck to verify
[/Claude Code, Cursor, OpenCode, codex-sub-agent, Kiro, Gemini, Qoder, CodeBuddy, Copilot, Droid, Pi]
[codex-inline, Kilo, Antigravity, Devin]
Load the `trellis-check` skill and verify the code per its guidance:
- Spec compliance
- lint / type-check / tests
- Cross-layer consistency (when changes span layers)
If issues are found → fix → re-check, until green.
[/codex-inline, Kilo, Antigravity, Devin]
**Final pass (before Phase 3.4 commit)**: the last 2.2 of a task must run full-scope, not just on the latest implement chunk. List all affected packages with `python3 ./.trellis/scripts/get_context.py --mode packages`, then load each package's spec index Quality Check section. This catches cross-layer / multi-package issues a mid-iteration local 2.2 cannot.
#### 2.3 Rollback `[on demand]`
- `check` reveals a prd defect → return to Phase 1, fix `prd.md`, then redo 2.1
- Implementation went wrong → revert code, redo 2.1
- Need more research → research (same as Phase 1.2), write findings into `research/`
---
## Phase 3: Finish
Goal: ensure code quality, capture lessons, record the work.
#### 3.2 Debug retrospective `[on demand]`
If this task involved repeated debugging (the same issue was fixed multiple times), load the `trellis-break-loop` skill to:
- Classify the root cause
- Explain why earlier fixes failed
- Propose prevention
The goal is to capture debugging lessons so the same class of issue doesn't recur.
#### 3.3 Spec update `[required · once]`
Load the `trellis-update-spec` skill and review whether this task produced new knowledge worth recording:
- Newly discovered patterns or conventions
- Pitfalls you hit
- New technical decisions
Update the docs under `.trellis/spec/` accordingly. Even if the conclusion is "nothing to update", walk through the judgment.
#### 3.4 Commit changes `[required · once]`
**Spec-sync preamble**: before drafting commits, ask: did this task fix a bug or surface non-obvious knowledge that should land in `.trellis/spec/` so future-you (or future-AI) doesn't repeat the mistake? If yes, return to Phase 3.3 first — spec writes belong in the same task's commit batch, not as a forgotten follow-up.
The AI drives a batched commit of this task's code changes so `/finish-work` can run cleanly afterwards. Goal: produce work commits FIRST, then bookkeeping (archive + journal) commits land after — never interleaved.
**Step-by-step**:
1. **Inspect dirty state**:
```bash
git status --porcelain
```
Snapshot every dirty path. If the working tree is clean, skip to 3.5.
2. **Learn commit style** from recent history (so drafted messages blend in):
```bash
git log --oneline -5
```
Note the prefix convention (`feat:` / `fix:` / `chore:` / `docs:` ...), language (中文/English), and length style.
3. **Classify dirty files into two groups**:
- **AI-edited this session** — files you wrote/edited via Edit/Write/Bash tool calls in this session. You know what changed and why.
- **Unrecognized** — dirty files you did NOT touch this session (could be the user's manual edits, leftover WIP from a previous session, or unrelated work). Do NOT silently include these.
4. **Draft a commit plan**. Group AI-edited files into logical commits (1 commit per coherent change unit, not 1 commit per file). Each entry: `<commit message>` + file list. List unrecognized files separately at the bottom.
5. **Present the plan once, ask for one-shot confirmation**. Format:
```
Proposed commits (in order):
1. <message>
- <file>
- <file>
2. <message>
- <file>
Unrecognized dirty files (NOT in any commit — confirm include/exclude):
- <file>
- <file>
Reply 'ok' / '行' to execute. Reply with edits, or '我自己来' / 'manual' to abort.
```
6. **On confirmation**: run `git add <files>` + `git commit -m "<msg>"` for each batch in order. Do not amend. Do not push.
7. **On rejection** (user replies "不行" / "我自己来" / "manual" / any pushback on the plan): stop. Do not attempt a second plan. The user will commit by hand; you skip ahead to 3.5 once they confirm.
**Rules**:
- No `git commit --amend` anywhere — three-stage three-commit flow (work commits → archive commit → journal commit).
- Never push to remote in this step.
- If the user wants different message wording but accepts the file grouping, edit the message and re-confirm once — but if they reject the grouping, exit to manual mode.
- The batched plan is one prompt; do not prompt per commit.
#### 3.5 Wrap-up reminder
After the above, remind the user they can run `/finish-work` to wrap up (archive the task, record the session).
---
## Customizing Trellis (for forks)
This section is for developers who want to modify the Trellis workflow itself. All customization is done by editing this file; the scripts are parsers only.
### Changing what a step means
Edit the corresponding step's walkthrough body in the Phase 1 / 2 / 3 sections above. Critical invariants:
- No active task must triage first and ask for task-creation consent before creating a Trellis task.
- Planning must distinguish lightweight PRD-only tasks from complex tasks that require `prd.md`, `design.md`, and `implement.md` before start.
- Every required execution path must keep the Phase 3.4 commit reminder reachable before `/trellis:finish-work`.
All tag blocks live in the `## Phase Index` section above, immediately after each phase summary:
| Scope | Corresponding tag |
|---|---|
| No active task (before Phase 1) | `[workflow-state:no_task]` (after the Phase Index ASCII art) |
| All of Phase 1 (task created → ready for implementation) | `[workflow-state:planning]` (after Phase 1 summary) |
| Codex inline Phase 1 | `[workflow-state:planning-inline]` |
| Phase 2 + Phase 3.2–3.4 (implementation + check + wrap-up) | `[workflow-state:in_progress]` (after Phase 2 summary) |
| Codex inline Phase 2 + Phase 3.2–3.4 | `[workflow-state:in_progress-inline]` |
| After Phase 3.5 (archived) | `[workflow-state:completed]` (after Phase 3 summary; **currently DEAD**) |
### Changing the per-turn prompt text
Directly edit the body of the corresponding `[workflow-state:STATUS]` block. After editing, run `trellis update` (if you're a template maintainer) or restart your AI session (if you're customizing your own project) — no script changes required.
### Adding a custom status
Add a new block:
```
[workflow-state:my-status]
your per-turn prompt text
[/workflow-state:my-status]
```
Constraints:
- STATUS charset: `[A-Za-z0-9_-]+` (underscores and hyphens allowed, e.g. `in-review`, `blocked-by-team`)
- A lifecycle hook must write `task.json.status` to your custom value, otherwise the tag is never read
- Lifecycle hooks live in `task.json.hooks.after_*` and bind to one of `after_create / after_start / after_finish / after_archive`
### Adding a lifecycle hook
Add a `hooks` field to your `task.json`:
```json
{
"hooks": {
"after_finish": [
"your-script-or-command-here"
]
}
}
```
Supported events: `after_create / after_start / after_finish / after_archive`. Note that `after_finish` ≠ a status change (it only clears the active-task pointer); use `after_archive` for "task is done" notifications.
### Full contract
For the workflow state machine's runtime contract, the locations of all status writers, pseudo-statuses (`no_task` / `stale_<source_type>`), the hook reachability matrix, and other deep details, see:
- `.trellis/spec/cli/backend/workflow-state-contract.md` — runtime contract + writer table + test invariants
- `.trellis/scripts/inject-workflow-state.py` — actual parser (reads workflow.md only, no embedded text)
.trellis/workspace/boos4721/index.md
+40
View File
@@ -0,0 +1,40 @@
# Workspace Index - boos4721
> Journal tracking for AI development sessions.
---
## Current Status
<!-- @@@auto:current-status -->
- **Active File**: `journal-1.md`
- **Total Sessions**: 0
- **Last Active**: -
<!-- @@@/auto:current-status -->
---
## Active Documents
<!-- @@@auto:active-documents -->
| File | Lines | Status |
|------|-------|--------|
| `journal-1.md` | ~0 | Active |
<!-- @@@/auto:active-documents -->
---
## Session History
<!-- @@@auto:session-history -->
| # | Date | Title | Commits | Branch |
|---|------|-------|---------|--------|
<!-- @@@/auto:session-history -->
---
## Notes
- Sessions are appended to journal files
- New journal file created when current exceeds 2000 lines
- Use `add_session.py` to record sessions
.trellis/workspace/boos4721/journal-1.md
+7
View File
@@ -0,0 +1,7 @@
# Journal - boos4721 (Part 1)
> AI development session journal
> Started: 2026-06-20
---
.trellis/workspace/index.md
+125
View File
@@ -0,0 +1,125 @@
# Workspace Index
> Records of all AI Agent work records across all developers
---
## Overview
This directory tracks records for all developers working with AI Agents on this project.
### File Structure
```
workspace/
|-- index.md # This file - main index
+-- {developer}/ # Per-developer directory
|-- index.md # Personal index with session history
|-- tasks/ # Task files
| |-- *.json # Active tasks
| +-- archive/ # Archived tasks by month
+-- journal-N.md # Journal files (sequential: 1, 2, 3...)
```
---
## Active Developers
| Developer | Last Active | Sessions | Active File |
|-----------|-------------|----------|-------------|
| (none yet) | - | - | - |
---
## Getting Started
### For New Developers
Run the initialization script:
```bash
python3 ./.trellis/scripts/init_developer.py <your-name>
```
This will:
1. Create your identity file (gitignored)
2. Create your progress directory
3. Create your personal index
4. Create initial journal file
### For Returning Developers
1. Get your developer name:
```bash
python3 ./.trellis/scripts/get_developer.py
```
2. Read your personal index:
```bash
cat .trellis/workspace/$(python3 ./.trellis/scripts/get_developer.py)/index.md
```
---
## Guidelines
### Journal File Rules
- **Max 2000 lines** per journal file
- When limit is reached, create `journal-{N+1}.md`
- Update your personal `index.md` when creating new files
### Session Record Format
Each session should include:
- Summary: One-line description
- Branch: Which branch the work was done on
- Main Changes: What was modified
- Git Commits: Commit hashes and messages
- Next Steps: What to do next
---
## Session Template
Use this template when recording sessions:
```markdown
## Session {N}: {Title}
**Date**: YYYY-MM-DD
**Task**: {task-name}
**Branch**: `{branch-name}`
### Summary
{One-line summary}
### Main Changes
- {Change 1}
- {Change 2}
### Git Commits
| Hash | Message |
|------|---------|
| `abc1234` | {commit message} |
### Testing
- [OK] {Test result}
### Status
[OK] **Completed** / # **In Progress** / [P] **Blocked**
### Next Steps
- {Next step 1}
- {Next step 2}
```
---
**Language**: All documentation must be written in **English**.
CLAUDE.md
+89
View File
@@ -0,0 +1,89 @@
# CLAUDE.md
This file provides guidance to Claude Code (claude.ai/code) when working with code in this repository.
## What this is
BoosAPI is an AI API gateway: an OpenAI/Anthropic/Gemini-compatible proxy with a token-routing/failover engine, a management console (React SPA), embedded ComfyUI workflow surfaces, billing, and payments. Backend is **pure Rust** (axum + sqlx + tokio); there is no Node.js runtime dependency at serving time — Node is only used to build frontend assets.
Project-internal docs are largely in Chinese (`AGENTS.md`, `README.md`); match that when editing them.
## Build & run
The wrapper script `./build-and-run.sh` is the normal entry point (builds frontend + backend, then runs). Key flags:
```bash
./build-and-run.sh --check # cargo check only — fastest verification, no frontend, no run
./build-and-run.sh # dev profile, reuse frontend cache, compile + start
./build-and-run.sh --backend-only # recompile/restart backend, skip Vite
./build-and-run.sh --fast-release # near-prod performance, faster than --release
./build-and-run.sh --production # build + embed frontend/Workflow UI into binary -> dist/production/
```
Cargo profiles: `dev` (default), `release` (LTO, slow), `fast-release` (opt-level 2, no LTO — use for staging verification). Direct cargo also works: `cargo run --release`, `cargo check`.
Config comes from `config.toml` plus env overrides via figment. Env vars use the `BOOSAPI_` prefix with `__` as the nesting separator, e.g. `BOOSAPI_SERVER__PORT=4000`, `BOOSAPI_AUTH__AUTH_TOKEN=...`, `BOOSAPI_PAYMENT__STRIPE_SECRET_KEY=...`. Prefer env vars for all secrets.
## Tests
```bash
cargo test # Rust tests (rstest, wiremock, axum-test, tracing-test)
cargo test <name> # single Rust test by name substring
npm test # web tests: vitest run --root src/web
npm run test:watch # vitest watch
npx vitest run src/web/api.test.ts # single web test file
npm run typecheck # tsc for src/web (app + tests)
```
Rust tests live in `#[cfg(test)]` modules alongside source. Web tests are `src/web/**/*.test.ts(x)`.
## Architecture
### Proxy core (`src/proxy/`) — the heart of the system
Request flow for `/v1/*`: **downstream key auth → token route resolution → channel selection → upstream call (with failover) → protocol transform → response**.
- `token_router/` — `TokenRouter` resolves a requested model name to candidate upstream channels using DB-backed route rows + regex patterns, with a short (2s) in-process cache. Call `invalidate_route_cache()` after mutating routes/channels. Failure cooldown per channel is configurable.
- `conductor/` — `ProxyConductor::execute` drives attempt/failover loop (max 5 attempts). It is decoupled from the DB via injected closures (`select_channel`, `select_next_channel`, `record_success`, `record_failure`, optional `refresh_auth`). `retry_policy.rs` classifies failures into actions: failover, retry-same-channel, refresh-auth, or terminal.
- `executors/`, `providers/`, `surfaces/`, `capabilities/`, `cli_profiles/` — execution backends and provider/capability metadata.
### Protocol transformers (`src/transformers/`)
`openai/`, `anthropic/`, `gemini/` convert between client-facing protocol and upstream protocol around a `canonical/` intermediate form. When adding model/protocol support, work through the canonical layer rather than point-to-point conversions.
### Routes (`src/routes/`)
`mod.rs` assembles the axum router by `.merge()`-ing each module's `routes()` and serves the SPA as a fallback (embedded via `include_dir` in production, or from `dist/web` on disk). `admin/` is the management API; `proxy/` is the OpenAI-compatible entry; `comfyui/`, `comfyui_agent.rs`, `workflow_ui.rs`, `digital_human.rs`, `money_printer.rs`, `picture_agent.rs` are the ComfyUI/creative surfaces.
### Services (`src/services/`)
Background and cross-cutting logic: `billing/`, `payment.rs`, `cron/`, `notification/`, `runtime_auth.rs`, `builtin_keys.rs`, `comfyui_process.rs`, `route_rebuild.rs`. Shared `AppState` (in `src/lib.rs`) is cloned into handlers and holds config, DB pool, HTTP client, and these service handles.
### Database
**SQLite is the only runtime path** — `AppState.db` is `Arc<SqlitePool>`, and all runtime queries target SQLite. The Postgres dependency and `boosapi migrate-sqlite-to-postgres` subcommand exist only to copy/migrate schema+data into Postgres; full Postgres runtime query compatibility is not done. Do not assume queries run against Postgres. Migrations live in `migrations/` (SQLite); `db/schema_compat.rs` applies runtime compatibility fixups after migrations.
## ComfyUI Agent (local-mode contract)
The ComfyUI Agent defaults to **local mode**: it calls this service's own `/v1/*` routes using a bootstrapped built-in downstream key (`name='comfyui-agent' AND user_id IS NULL`, format `sk-comfyui-{uuid_hex}`, mirrored into `settings.builtin_key.comfyui_agent.secret`).
- Local (default): `upstream_base = http://{host}/v1` (host `0.0.0.0`/`::` rewritten to `127.0.0.1`); `/api/comfyui-agent/status` returns `mode: "local"`.
- Fallback-remote: set `BOOSAPI_UPSTREAM_BASE` (non-empty) to use an external upstream; `BOOSAPI_UPSTREAM_KEY` falls back to the built-in key if unset.
- The built-in key is **protected**: admin list masks it (`••••<last4>`), delete/disable return 403, and `builtin_key.*` settings are hidden from list / 403 on PUT. Startup `ensure_comfyui_agent_key` is idempotent (regenerates if missing, re-enables if disabled, keeps settings ↔ downstream_api_keys in sync).
Workflow backend modes (`[comfyui] backend`): `cloud` (Comfy Cloud, default), `runninghub`, `external` (your own ComfyUI), `boosapi` (built-in Rust workflow/API node executor), `docker` (legacy). Workflow UI has separate `cloud` and `external/runninghub` frontend asset bundles — install with `npm run workflow-ui:install:cloud` / `:external`.
## Frontend (two separate apps)
- `src/web/` — management console, React 18 + Vite, built to `dist/web/` and served by the Rust backend. `npm run dev` for HMR, `npm run build:web` to build.
- `website/` — standalone marketing site, **Next.js 16 App Router + React 19**, its own package. Use `npm run website:dev` / `website:build` / `website:typecheck` (these proxy to `npm --prefix website`).
### Auth/session conventions (src/web)
- Session state goes through `authSession.ts`: `commitSession / clearSession / getSessionToken`, bucketed by audience `'admin' | 'user'`. The old `persistAuthSession / clearAuthSession / getAuthToken / hasValidAuthSession` family is `@deprecated` — do not use in new code.
- Login pages are split under `pages/auth/`: `LoginShell` (shared shell) + `AdminLoginPage` (token / account modes) + `UserLoginPage`. OAuth entries render via `OAuthSlot` as placeholders only — do not wire onClick/navigation there.
- Login error text is normalized in `loginError.ts` via `resolveLoginErrorMessage(status, raw)` — add new login errors there, not inline.
## Shared TS/Rust contracts (`src/shared/`)
This directory holds logic mirrored between Rust (`.rs`) and TypeScript (`.ts`/`.js`) — e.g. `tokenRouteContract`, `tokenRoutePatterns`, `modelBrand`, `platformIdentity`, `proxyLogMeta`, `siteInitializationPresets`. When changing a routing/identity contract, keep the Rust and TS sides in sync.
Cargo.lock
Generated
+57
View File
@@ -390,6 +390,7 @@ dependencies = [
"anyhow", "anyhow",
"argon2", "argon2",
"async-stream", "async-stream",
"async-trait",
"axum 0.8.9", "axum 0.8.9",
"axum-test", "axum-test",
"base64", "base64",
@@ -407,12 +408,14 @@ dependencies = [
"mime", "mime",
"mime_guess", "mime_guess",
"once_cell", "once_cell",
"open-agent-sdk",
"parking_lot", "parking_lot",
"regex", "regex",
"reqwest", "reqwest",
"rstest", "rstest",
"serde", "serde",
"serde_json", "serde_json",
"serde_yaml",
"sha2", "sha2",
"sqlx", "sqlx",
"tempfile", "tempfile",
@@ -426,6 +429,7 @@ dependencies = [
"tracing", "tracing",
"tracing-subscriber", "tracing-subscriber",
"tracing-test", "tracing-test",
"url",
"uuid", "uuid",
"wiremock", "wiremock",
] ]
@@ -1823,6 +1827,31 @@ version = "1.70.2"
source = "registry+https://github.com/rust-lang/crates.io-index" source = "registry+https://github.com/rust-lang/crates.io-index"
checksum = "384b8ab6d37215f3c5301a95a4accb5d64aa607f1fcb26a11b5303878451b4fe" checksum = "384b8ab6d37215f3c5301a95a4accb5d64aa607f1fcb26a11b5303878451b4fe"
[[package]]
name = "open-agent-sdk"
version = "0.1.0"
dependencies = [
"async-trait",
"base64",
"bytes",
"chrono",
"futures",
"glob",
"pin-project-lite",
"regex",
"reqwest",
"serde",
"serde_json",
"serde_yaml",
"thiserror 2.0.18",
"tokio",
"tokio-stream",
"tokio-util",
"tracing",
"uuid",
"windows-sys 0.59.0",
]
[[package]] [[package]]
name = "openssl" name = "openssl"
version = "0.10.80" version = "0.10.80"
@@ -2528,6 +2557,19 @@ dependencies = [
"serde", "serde",
] ]
[[package]]
name = "serde_yaml"
version = "0.9.34+deprecated"
source = "registry+https://github.com/rust-lang/crates.io-index"
checksum = "6a8b1a1a2ebf674015cc02edccce75287f1a0130d394307b36743c2f5d504b47"
dependencies = [
"indexmap",
"itoa",
"ryu",
"serde",
"unsafe-libyaml",
]
[[package]] [[package]]
name = "sha1" name = "sha1"
version = "0.10.6" version = "0.10.6"
@@ -3457,6 +3499,12 @@ version = "0.2.6"
source = "registry+https://github.com/rust-lang/crates.io-index" source = "registry+https://github.com/rust-lang/crates.io-index"
checksum = "ebc1c04c71510c7f702b52b7c350734c9ff1295c464a03335b00bb84fc54f853" checksum = "ebc1c04c71510c7f702b52b7c350734c9ff1295c464a03335b00bb84fc54f853"
[[package]]
name = "unsafe-libyaml"
version = "0.2.11"
source = "registry+https://github.com/rust-lang/crates.io-index"
checksum = "673aac59facbab8a9007c7f6108d11f63b603f7cabff99fabf650fea5c32b861"
[[package]] [[package]]
name = "untrusted" name = "untrusted"
version = "0.9.0" version = "0.9.0"
@@ -3790,6 +3838,15 @@ dependencies = [
"windows-targets 0.52.6", "windows-targets 0.52.6",
] ]
[[package]]
name = "windows-sys"
version = "0.59.0"
source = "registry+https://github.com/rust-lang/crates.io-index"
checksum = "1e38bc4d79ed67fd075bcc251a1c39b32a1776bbe92e5bef1f0bf1f8c531853b"
dependencies = [
"windows-targets 0.52.6",
]
[[package]] [[package]]
name = "windows-sys" name = "windows-sys"
version = "0.61.2" version = "0.61.2"
Cargo.toml
+8
View File
@@ -27,11 +27,13 @@ sqlx = { version = "0.8", features = [
# HTTP client # HTTP client
reqwest = { version = "0.12", features = ["stream", "json", "multipart"] } reqwest = { version = "0.12", features = ["stream", "json", "multipart"] }
url = "2"
lettre = { version = "0.11", default-features = false, features = ["builder", "hostname", "pool", "rustls-tls", "smtp-transport"] } lettre = { version = "0.11", default-features = false, features = ["builder", "hostname", "pool", "rustls-tls", "smtp-transport"] }
# Serialization # Serialization
serde = { version = "1", features = ["derive"] } serde = { version = "1", features = ["derive"] }
serde_json = "1" serde_json = "1"
serde_yaml = "0.9"
regex = "1" regex = "1"
# Auth # Auth
@@ -76,6 +78,12 @@ hex = "0.4"
include_dir = "0.7" include_dir = "0.7"
mime_guess = "2" mime_guess = "2"
# Embedded AI agent engine (MIT, vendored as a path dependency). Provides the
# agentic loop, built-in tools, permission callback and cost tracking that the
# Agent Workbench (src/routes/agent.rs) drives through BoosAPI's own provider.
open-agent-sdk = { path = "../open-agent-sdk-rust" }
async-trait = "0.1"
[dev-dependencies] [dev-dependencies]
rstest = "0.24" rstest = "0.24"
wiremock = "0.6" wiremock = "0.6"
boosapi.db
BIN
View File
Binary file not shown.
build-and-run.sh
+41 -4
View File
@@ -227,6 +227,24 @@ configure_fast_linker() {
esac esac
} }
# Enable sccache as the rustc wrapper when available. sccache caches compiled
# crates keyed by source + flags, so dependency rebuilds / clean builds / branch
# switches reuse prior output. It transparently skips incremental crates, so the
# dev profile still relies mainly on incremental; release/fast-release benefit
# most. Set BOOSAPI_SCCACHE=off to disable.
configure_sccache() {
case "${BOOSAPI_SCCACHE:-auto}" in
off|none|0) return 0 ;;
esac
if [ -n "${RUSTC_WRAPPER:-}" ]; then
return 0 # respect an externally configured wrapper
fi
if command -v sccache >/dev/null 2>&1; then
export RUSTC_WRAPPER="sccache"
log "Rust 编译缓存: sccache（BOOSAPI_SCCACHE=off 可关闭）"
fi
}
server_port() { server_port() {
if [ -n "${BOOSAPI_SERVER__PORT:-}" ]; then if [ -n "${BOOSAPI_SERVER__PORT:-}" ]; then
printf '%s\n' "$BOOSAPI_SERVER__PORT" printf '%s\n' "$BOOSAPI_SERVER__PORT"
@@ -497,6 +515,7 @@ build_backend() {
fi fi
configure_fast_linker configure_fast_linker
configure_sccache
build_cargo_args build_cargo_args
if [ "$CHECK_ONLY" -eq 1 ]; then if [ "$CHECK_ONLY" -eq 1 ]; then
@@ -581,14 +600,32 @@ if [ "$FRONTEND_ONLY" -eq 1 ]; then
fi fi
if [ "$BACKEND_ONLY" -ne 1 ]; then if [ "$BACKEND_ONLY" -ne 1 ]; then
if [ "$PRODUCTION_BUNDLE" -eq 1 ]; then
# Production embeds frontend assets into the binary; keep the ordering
# explicit (frontend → workflow UI → backend) to avoid a race on the
# embedded files. No parallelism here.
build_frontend build_frontend
build_public_website build_public_website
if [ "$PRODUCTION_BUNDLE" -eq 1 ]; then
ensure_workflow_ui_for_embedding ensure_workflow_ui_for_embedding
fi
fi
build_backend build_backend
else
# Dev / normal builds: frontend (vite) + website (next) run in the
# background while the backend (cargo) builds in the foreground. The
# backend stays in the main shell so it can still set BINARY and other
# globals the launch step depends on. Total time ≈ max(frontend, backend).
log "并行构建：前端/官网（后台）+ 后端（前台）..."
( build_frontend && build_public_website ) &
fe_pid=$!
be_status=0
build_backend || be_status=$?
fe_status=0
wait "$fe_pid" || fe_status=$?
[ "$be_status" -eq 0 ] || fail "后端构建失败（exit $be_status）"
[ "$fe_status" -eq 0 ] || fail "前端/官网构建失败（exit $fe_status）"
fi
else
build_backend
fi
if [ "$CHECK_ONLY" -eq 1 ]; then if [ "$CHECK_ONLY" -eq 1 ]; then
print_timing_summary print_timing_summary
config.toml
+35 -35
View File
@@ -1,3 +1,6 @@
# 必填项保留；空字符串字段、有默认值的字段、与凭证相关的内容都从 toml 移走，
# 改用环境变量（BOOSAPI_<SECTION>__<KEY>）或后台 admin 界面写入数据库。
[server] [server]
host = "0.0.0.0" host = "0.0.0.0"
port = 4000 port = 4000
@@ -8,13 +11,9 @@ cors_origins = ["*"]
url = "sqlite:boosapi.db?mode=rwc" url = "sqlite:boosapi.db?mode=rwc"
max_connections = 10 max_connections = 10
ssl = false ssl = false
# PostgreSQL preparation example:
# url = "postgres://boosapi:password@127.0.0.1:5432/boosapi"
# Note: this build can create/migrate PostgreSQL schemas and copy SQLite data
# with `boosapi migrate-sqlite-to-postgres`; full runtime query compatibility
# is completed in a follow-up SQL dialect pass.
[auth] [auth]
# 改成生产值前请先改 jwt_secret / auth_token / proxy_token，避免使用默认值。
jwt_secret = "boosapi-dev-secret-change-in-production" jwt_secret = "boosapi-dev-secret-change-in-production"
jwt_expiry_hours = 72 jwt_expiry_hours = 72
auth_token = "boos4721" auth_token = "boos4721"
@@ -25,15 +24,11 @@ upstream_timeout_secs = 300
first_byte_timeout_secs = 60 first_byte_timeout_secs = 60
max_retries = 3 max_retries = 3
proxy_log_retention_days = 30 proxy_log_retention_days = 30
# Optional proxy for external template galleries/workflow template assets.
# Supports http://, https:// and socks5:// proxy URLs.
# template_proxy_url = "http://127.0.0.1:7890"
[payment] [payment]
enabled = false enabled = true
# Public HTTPS origin used to build Stripe success/cancel URLs and webhook docs. # provider: "comfy_cloud" | "stripe"
# Example: "https://tybossai.com" provider = "comfy_cloud"
public_base_url = ""
product_name_prefix = "BossAI 账户充值" product_name_prefix = "BossAI 账户充值"
currency = "usd" currency = "usd"
min_amount_usd = 1.0 min_amount_usd = 1.0
@@ -42,35 +37,40 @@ order_timeout_minutes = 30
max_pending_orders = 3 max_pending_orders = 3
success_path = "/user/recharge?payment=success&order={ORDER_ID}" success_path = "/user/recharge?payment=success&order={ORDER_ID}"
cancel_path = "/user/recharge?payment=cancel&order={ORDER_ID}" cancel_path = "/user/recharge?payment=cancel&order={ORDER_ID}"
# Prefer environment variables for secrets: comfy_customer_api_base_url = "https://api.comfy.org"
# BOOSAPI_PAYMENT__STRIPE_SECRET_KEY=sk_live_... # 凭证统一走环境变量或后台「支付管理」写入；不要写在这里：
# BOOSAPI_PAYMENT__STRIPE_WEBHOOK_SECRET=whsec_... # BOOSAPI_PAYMENT__PUBLIC_BASE_URL
stripe_secret_key = "" # BOOSAPI_PAYMENT__STRIPE_SECRET_KEY / STRIPE_WEBHOOK_SECRET
stripe_webhook_secret = "" # BOOSAPI_PAYMENT__COMFY_CUSTOMER_TOKEN / COMFY_CUSTOMER_TOKEN_ENDPOINT
# BOOSAPI_PAYMENT__COMFY_FIREBASE_API_KEY / COMFY_OAUTH_REFRESH_TOKEN
# BOOSAPI_PAYMENT__COMFY_OAUTH_CLIENT_ID / COMFY_OAUTH_CLIENT_SECRET
# BOOSAPI_PAYMENT__COMFY_CHECKOUT_ENDPOINT
[comfyui] [comfyui]
enabled = false enabled = false
# backend: "boosapi" | "cloud" | "runninghub" | "external" | "docker"
backend = "cloud"
python_bin = "python3" python_bin = "python3"
port = 8188 port = 8188
extra_args = [] extra_args = []
max_restarts = 5 max_restarts = 5
# backend modes:
# - "boosapi": use BoosAPI's own Rust Workflow/API node executor.
# - "cloud": proxy to Comfy Cloud and use native ComfyUI /prompt and /ws.
# - "runninghub": proxy to RunningHub's ComfyUI-compatible API with external-compatible frontend.
# - "external": proxy to your own full ComfyUI server.
# - "docker": legacy local Docker ComfyUI mode; not recommended for the current API Workflow path.
backend = "cloud"
# Native Comfy task costs are charged against the user's downstream API Key
# only after successful output archival. Keep 0 while pricing is not finalized.
money_printer_video_cost = 0.0
digital_human_video_cost = 0.0
# docker_image = "boosapi-comfyui:multi-tenant"
# container_name = "boosapi-comfyui-workflow"
# base_url = "https://www.runninghub.cn/proxy-plus/94d1330ea62d4ae980ffb018ecdf82a2"
# For RunningHub, set backend = "runninghub" and use your RunningHub proxy/API URL.
# RunningHub proxy URL already contains the API key. Keep this empty unless
# you switch to a backend that requires Authorization / X-API-Key headers.
base_url = "https://cloud.comfy.org" base_url = "https://cloud.comfy.org"
api_key = "comfyui-cbe4ebb1e22ee4ef2dab4d9293a76d5272a25e5ec847ac57387ab2b30798d86f" api_key = "comfyui-cbe4ebb1e22ee4ef2dab4d9293a76d5272a25e5ec847ac57387ab2b30798d86f"
agent_model = "gpt-5.5" agent_model = "deepseek-v4-flash"
[pixelle_video]
enabled = true
# Pixelle-Video 单独启动：
# git clone https://github.com/AIDC-AI/Pixelle-Video /opt/Pixelle-Video
# cd /opt/Pixelle-Video && uv run python api/app.py --host 127.0.0.1 --port 18000
api_base_url = "http://127.0.0.1:18000"
frame_template = "1080x1920/image_default.html"
media_workflow = "selfhost/video_wan2.1_fusionx.json"
tts_workflow = "selfhost/tts_edge.json"
runninghub_media_workflow = "runninghub/video_wan2.1_fusionx.json"
runninghub_tts_workflow = "runninghub/tts_edge.json"
mode = "fixed"
n_scenes = 5
video_fps = 30
poll_interval_secs = 5
timeout_secs = 900
docs/superpowers/plans/2026-06-17-comfy-cloud-adapter.md
+632
View File
@@ -0,0 +1,632 @@
# Comfy Cloud 工作流执行适配器 实现计划
> **For agentic workers:** REQUIRED SUB-SKILL: Use superpowers:subagent-driven-development (recommended) or superpowers:executing-plans to implement this plan task-by-task. Steps use checkbox (`- [ ]`) syntax for tracking.
**Goal:** 在 BoosAPI 内实现 ComfyUI 原生协议 ↔ Comfy Cloud API 翻译适配器,让 Pixelle/comfykit 零改动通过 BoosAPI 调用 Comfy Cloud 执行工作流。
**Architecture:** 新增 `/comfy-cloud/{prompt,history,view}` 端点,内部翻译成 `cloud.comfy.org/api/*` + `X-API-Key`。Comfy Cloud 的 base_url + key 从站点管理(`platform='comfy_cloud'` 的 active 站点)读取。纯翻译函数单测,wiremock 集成测。
**Tech Stack:** Rust (axum, reqwest, sqlx, serde_json, wiremock, tokio)。
> **构建/测试:** `cargo build -j 2`、`cargo test -p boosapi --lib comfy_cloud`。分支 `feat/comfy-cloud-adapter`。
---
## 文件结构
- Create `src/services/comfy_cloud/mod.rs` — 模块导出。
- Create `src/services/comfy_cloud/site.rs` — `resolve_comfy_cloud_site` 读站点配置。
- Create `src/services/comfy_cloud/translate.rs` — `comfy_cloud_job_to_history` 纯翻译函数。
- Create `src/routes/comfy_cloud_adapter.rs` — 三个适配端点 + `routes()`。
- Modify `src/services/mod.rs` — 加 `pub mod comfy_cloud;`。
- Modify `src/routes/mod.rs` — 加 `mod comfy_cloud_adapter;` + `.merge(...)`。
- Modify `src/web/pages/Sites.tsx` — `SITE_PLATFORM_OPTIONS` 加 `comfy_cloud` 选项。
---
<!-- TASKS -->
## Task 1: 站点配置读取 `resolve_comfy_cloud_site`
**Files:**
- Create: `src/services/comfy_cloud/mod.rs`
- Create: `src/services/comfy_cloud/site.rs`
- Modify: `src/services/mod.rs`
- [ ] **Step 1: `src/services/mod.rs` 末尾加模块声明**
```rust
pub mod comfy_cloud;
```
- [ ] **Step 2: 写 `src/services/comfy_cloud/mod.rs`**
```rust
//! Comfy Cloud 工作流执行适配器 service 层。
pub mod site;
pub mod translate;
```
- [ ] **Step 3: 写失败测试 `src/services/comfy_cloud/site.rs`**
```rust
use crate::error::{AppError, AppResult};
use sqlx::SqlitePool;
/// 解析 Comfy Cloud 站点配置,返回 (base_url, api_key)。
/// 取 platform='comfy_cloud' 且 status='active' 的站点。
pub async fn resolve_comfy_cloud_site(db: &SqlitePool) -> AppResult<(String, String)> {
let row: Option<(String, Option<String>)> = sqlx::query_as(
"SELECT url, api_key FROM sites
WHERE platform = 'comfy_cloud' AND status = 'active'
ORDER BY COALESCE(sort_order, 0), id LIMIT 1",
)
.fetch_optional(db)
.await?;
let (url, api_key) = row.ok_or_else(|| {
AppError::ServiceUnavailable("未配置 Comfy Cloud 站点(站点管理添加 comfy_cloud 平台)".into())
})?;
let api_key = api_key
.map(|k| k.trim().to_string())
.filter(|k| !k.is_empty())
.ok_or_else(|| AppError::ServiceUnavailable("Comfy Cloud 站点缺少 API Key".into()))?;
let base_url = url.trim().trim_end_matches('/').to_string();
Ok((base_url, api_key))
}
#[cfg(test)]
mod tests {
use super::*;
use sqlx::sqlite::SqlitePoolOptions;
async fn pool() -> SqlitePool {
let pool = SqlitePoolOptions::new().max_connections(1).connect("sqlite::memory:").await.unwrap();
sqlx::query("CREATE TABLE sites (id INTEGER PRIMARY KEY AUTOINCREMENT, name TEXT, url TEXT NOT NULL, platform TEXT NOT NULL, status TEXT NOT NULL, api_key TEXT, sort_order INTEGER)")
.execute(&pool).await.unwrap();
pool
}
#[tokio::test]
async fn resolves_active_comfy_cloud_site() {
let pool = pool().await;
sqlx::query("INSERT INTO sites (name,url,platform,status,api_key) VALUES ('cc','https://cloud.comfy.org/','comfy_cloud','active','key-123')")
.execute(&pool).await.unwrap();
let (url, key) = resolve_comfy_cloud_site(&pool).await.unwrap();
assert_eq!(url, "https://cloud.comfy.org");
assert_eq!(key, "key-123");
}
#[tokio::test]
async fn errors_when_not_configured() {
let pool = pool().await;
let r = resolve_comfy_cloud_site(&pool).await;
assert!(matches!(r, Err(AppError::ServiceUnavailable(_))));
}
}
```
- [ ] **Step 4: 运行测试,确认失败**
Run: `cargo test -p boosapi --lib services::comfy_cloud::site 2>&1 | tail -15`
Expected: FAIL —— 模块未挂载/函数未定义(编译错误)。
- [ ] **Step 5: 实现**
Step 3 的函数体即实现(测试与实现同文件)。确认 `src/services/comfy_cloud/mod.rs` 已 `pub mod site;`。
- [ ] **Step 6: 运行测试,确认通过**
Run: `cargo test -p boosapi --lib services::comfy_cloud::site 2>&1 | tail -10`
Expected: PASS(2 个测试)。
- [ ] **Step 7: Commit**
```bash
git add src/services/mod.rs src/services/comfy_cloud/mod.rs src/services/comfy_cloud/site.rs
git commit -m "feat(comfy-cloud): 站点配置读取 resolve_comfy_cloud_site"
```
<!-- T2 -->
## Task 2: 翻译函数 `comfy_cloud_job_to_history`
**Files:**
- Create: `src/services/comfy_cloud/translate.rs`
- [ ] **Step 1: 写失败测试 `src/services/comfy_cloud/translate.rs`**
```rust
use serde_json::{json, Value};
/// 把 Comfy Cloud 的 job status(+ 完成时的 jobs detail outputs)翻译成
/// ComfyUI 原生 /history/{id} 的形状。
///
/// - status pending/in_progress → 返回空对象 {}(comfykit 据此继续轮询)
/// - status completed → { "{id}": { "status": {completed:true, status_str:"success"}, "outputs": {...} } }
/// - status failed/cancelled → { "{id}": { "status": {completed:false, status_str:"error"} } }
pub fn comfy_cloud_job_to_history(
prompt_id: &str,
status: &str,
outputs: Option<&Value>,
) -> Value {
match status {
"completed" => json!({
prompt_id: {
"status": { "completed": true, "status_str": "success" },
"outputs": outputs.cloned().unwrap_or_else(|| json!({})),
}
}),
"failed" | "cancelled" => json!({
prompt_id: {
"status": { "completed": false, "status_str": "error" },
"outputs": {},
}
}),
_ => json!({}),
}
}
#[cfg(test)]
mod tests {
use super::*;
#[test]
fn in_progress_returns_empty() {
assert_eq!(comfy_cloud_job_to_history("p1", "in_progress", None), json!({}));
assert_eq!(comfy_cloud_job_to_history("p1", "pending", None), json!({}));
}
#[test]
fn completed_wraps_outputs() {
let outputs = json!({ "9": { "images": [{ "filename": "a.png", "subfolder": "", "type": "output" }] } });
let h = comfy_cloud_job_to_history("p1", "completed", Some(&outputs));
assert_eq!(h["p1"]["status"]["completed"], true);
assert_eq!(h["p1"]["outputs"]["9"]["images"][0]["filename"], "a.png");
}
#[test]
fn failed_marks_error() {
let h = comfy_cloud_job_to_history("p1", "failed", None);
assert_eq!(h["p1"]["status"]["status_str"], "error");
assert_eq!(h["p1"]["status"]["completed"], false);
}
}
```
- [ ] **Step 2: 运行测试,确认失败**
Run: `cargo test -p boosapi --lib services::comfy_cloud::translate 2>&1 | tail -15`
Expected: FAIL —— 模块未挂载/函数未定义。
- [ ] **Step 3: 实现**
Step 1 的函数体即实现。确认 `mod.rs` 已 `pub mod translate;`(Task 1 Step 2 已加)。
- [ ] **Step 4: 运行测试,确认通过**
Run: `cargo test -p boosapi --lib services::comfy_cloud::translate 2>&1 | tail -10`
Expected: PASS(3 个测试)。
- [ ] **Step 5: Commit**
```bash
git add src/services/comfy_cloud/translate.rs
git commit -m "feat(comfy-cloud): job→ComfyUI history 翻译函数"
```
<!-- T3 -->
## Task 3: 适配端点骨架 + `POST /comfy-cloud/prompt`
**Files:**
- Create: `src/routes/comfy_cloud_adapter.rs`
- [ ] **Step 1: 写骨架 + 测试 `src/routes/comfy_cloud_adapter.rs`**
```rust
use crate::error::{AppError, AppResult};
use crate::services::comfy_cloud::site::resolve_comfy_cloud_site;
use crate::services::comfy_cloud::translate::comfy_cloud_job_to_history;
use crate::AppState;
use axum::{
body::Body,
extract::{Path, RawQuery, State},
http::{header, StatusCode},
response::Response,
routing::{get, post},
Json, Router,
};
use serde_json::Value;
pub fn routes() -> Router<AppState> {
Router::new()
.route("/comfy-cloud/prompt", post(submit_prompt))
.route("/comfy-cloud/history/{prompt_id}", get(get_history))
.route("/comfy-cloud/view", get(get_view))
}
fn client() -> reqwest::Client {
reqwest::Client::builder()
.timeout(std::time::Duration::from_secs(120))
.build()
.unwrap_or_else(|_| reqwest::Client::new())
}
async fn submit_prompt(
State(state): State<AppState>,
Json(body): Json<Value>,
) -> AppResult<Json<Value>> {
let (base_url, api_key) = resolve_comfy_cloud_site(&state.db).await?;
let resp = client()
.post(format!("{base_url}/api/prompt"))
.header("X-API-Key", api_key)
.json(&body)
.send()
.await
.map_err(|e| AppError::UpstreamError(e.to_string()))?;
let status = resp.status();
let text = resp.text().await.map_err(|e| AppError::UpstreamError(e.to_string()))?;
if !status.is_success() {
return Err(AppError::UpstreamError(format!("Comfy Cloud prompt [{status}]: {text}")));
}
let value: Value = serde_json::from_str(&text).unwrap_or_else(|_| serde_json::json!({ "body": text }));
Ok(Json(value))
}
#[cfg(test)]
mod tests {
use super::*;
use wiremock::matchers::{header as match_header, method, path};
use wiremock::{Mock, MockServer, ResponseTemplate};
use sqlx::sqlite::SqlitePoolOptions;
async fn db_with_site(base_url: &str) -> sqlx::SqlitePool {
let pool = SqlitePoolOptions::new().max_connections(1).connect("sqlite::memory:").await.unwrap();
sqlx::query("CREATE TABLE sites (id INTEGER PRIMARY KEY AUTOINCREMENT, name TEXT, url TEXT NOT NULL, platform TEXT NOT NULL, status TEXT NOT NULL, api_key TEXT, sort_order INTEGER)")
.execute(&pool).await.unwrap();
sqlx::query("INSERT INTO sites (name,url,platform,status,api_key) VALUES ('cc',?,'comfy_cloud','active','key-123')")
.bind(base_url).execute(&pool).await.unwrap();
pool
}
#[tokio::test]
async fn submit_forwards_with_api_key() {
let server = MockServer::start().await;
Mock::given(method("POST"))
.and(path("/api/prompt"))
.and(match_header("X-API-Key", "key-123"))
.respond_with(ResponseTemplate::new(200).set_body_json(serde_json::json!({ "prompt_id": "p1" })))
.mount(&server).await;
let pool = db_with_site(&server.uri()).await;
let (base_url, api_key) = resolve_comfy_cloud_site(&pool).await.unwrap();
// 直接验证转发契约(handler 依赖 AppState,这里测底层契约)
let resp = client().post(format!("{base_url}/api/prompt"))
.header("X-API-Key", api_key)
.json(&serde_json::json!({ "prompt": {} }))
.send().await.unwrap();
let v: Value = resp.json().await.unwrap();
assert_eq!(v["prompt_id"], "p1");
}
}
```
> 注:`submit_prompt` handler 需 `AppState`,完整 handler 走 Task 6 联调验证;本 task 的
> wiremock 测试验证「X-API-Key 注入 + `/api/prompt` 路径 + prompt_id 透传」这一核心契约。
- [ ] **Step 2: 运行测试,确认失败**
Run: `cargo test -p boosapi --lib routes::comfy_cloud_adapter 2>&1 | tail -15`
Expected: FAIL —— 模块未挂载(`get_history`/`get_view` 未定义,编译错误)。
> 因 `routes()` 引用了 Task 4/5 的 `get_history`/`get_view`,本 task 先写它们的空桩
> 让编译过(Step 3),Task 4/5 再填实现。
- [ ] **Step 3: 加 `get_history`/`get_view` 空桩(接在 `submit_prompt` 之后,让编译通过)**
```rust
async fn get_history(
State(state): State<AppState>,
Path(prompt_id): Path<String>,
) -> AppResult<Json<Value>> {
let _ = (&state, &prompt_id);
Ok(Json(serde_json::json!({})))
}
async fn get_view(
State(state): State<AppState>,
RawQuery(query): RawQuery,
) -> AppResult<Response> {
let _ = (&state, &query);
Ok(Response::builder().status(StatusCode::NOT_IMPLEMENTED).body(Body::empty())
.map_err(|e| AppError::Internal(anyhow::anyhow!(e)))?)
}
```
- [ ] **Step 4: 运行测试,确认通过**
Run: `cargo test -p boosapi --lib routes::comfy_cloud_adapter 2>&1 | tail -10`
Expected: PASS(1 个测试)。
> 此时 `routes::comfy_cloud_adapter` 模块还没挂进 `routes/mod.rs`,测试是模块内单测,
> 不需要挂载即可跑。挂载在 Task 6。
- [ ] **Step 5: Commit**
```bash
git add src/routes/comfy_cloud_adapter.rs
git commit -m "feat(comfy-cloud): 适配端点骨架 + POST /prompt 转发"
```
<!-- T4 -->
## Task 4: `GET /comfy-cloud/history/{id}` 轮询翻译
**Files:**
- Modify: `src/routes/comfy_cloud_adapter.rs`
- [ ] **Step 1: 写失败测试(加到测试模块内)**
```rust
#[tokio::test]
async fn history_in_progress_then_completed() {
let server = MockServer::start().await;
// 状态查询:completed
Mock::given(method("GET"))
.and(path("/api/job/p1/status"))
.and(match_header("X-API-Key", "key-123"))
.respond_with(ResponseTemplate::new(200).set_body_json(serde_json::json!({ "status": "completed" })))
.mount(&server).await;
// 详情:outputs
Mock::given(method("GET"))
.and(path("/api/jobs/p1"))
.respond_with(ResponseTemplate::new(200).set_body_json(serde_json::json!({
"outputs": { "9": { "images": [{ "filename": "a.png", "subfolder": "", "type": "output" }] } }
})))
.mount(&server).await;
let pool = db_with_site(&server.uri()).await;
let history = fetch_history(&pool, "p1").await.unwrap();
assert_eq!(history["p1"]["status"]["completed"], true);
assert_eq!(history["p1"]["outputs"]["9"]["images"][0]["filename"], "a.png");
}
```
- [ ] **Step 2: 运行测试,确认失败**
Run: `cargo test -p boosapi --lib routes::comfy_cloud_adapter::tests::history 2>&1 | tail -15`
Expected: FAIL —— `fetch_history` 未定义。
- [ ] **Step 3: 实现 `fetch_history` + 替换 `get_history` 空桩**
把 Task 3 的 `get_history` 空桩替换为:
```rust
async fn fetch_history(db: &sqlx::SqlitePool, prompt_id: &str) -> AppResult<Value> {
let (base_url, api_key) = resolve_comfy_cloud_site(db).await?;
let http = client();
let status_resp = http
.get(format!("{base_url}/api/job/{prompt_id}/status"))
.header("X-API-Key", &api_key)
.send().await
.map_err(|e| AppError::UpstreamError(e.to_string()))?;
if !status_resp.status().is_success() {
let st = status_resp.status();
let body = status_resp.text().await.unwrap_or_default();
return Err(AppError::UpstreamError(format!("Comfy Cloud status [{st}]: {body}")));
}
let status_json: Value = status_resp.json().await.map_err(|e| AppError::UpstreamError(e.to_string()))?;
let status = status_json.get("status").and_then(Value::as_str).unwrap_or("in_progress");
if status != "completed" {
return Ok(comfy_cloud_job_to_history(prompt_id, status, None));
}
let detail_resp = http
.get(format!("{base_url}/api/jobs/{prompt_id}"))
.header("X-API-Key", &api_key)
.send().await
.map_err(|e| AppError::UpstreamError(e.to_string()))?;
let detail_json: Value = detail_resp.json().await.map_err(|e| AppError::UpstreamError(e.to_string()))?;
let outputs = detail_json.get("outputs");
Ok(comfy_cloud_job_to_history(prompt_id, status, outputs))
}
async fn get_history(
State(state): State<AppState>,
Path(prompt_id): Path<String>,
) -> AppResult<Json<Value>> {
Ok(Json(fetch_history(&state.db, &prompt_id).await?))
}
```
- [ ] **Step 4: 运行测试,确认通过**
Run: `cargo test -p boosapi --lib routes::comfy_cloud_adapter 2>&1 | tail -10`
Expected: PASS(submit + history 共 2 个测试)。
- [ ] **Step 5: Commit**
```bash
git add src/routes/comfy_cloud_adapter.rs
git commit -m "feat(comfy-cloud): /history 轮询翻译(status+jobs→history)"
```
<!-- T5 -->
## Task 5: `GET /comfy-cloud/view` 产出文件透传
**Files:**
- Modify: `src/routes/comfy_cloud_adapter.rs`
- [ ] **Step 1: 写失败测试(加到测试模块内)**
```rust
#[tokio::test]
async fn view_proxies_file_bytes() {
let server = MockServer::start().await;
Mock::given(method("GET"))
.and(path("/api/view"))
.and(match_header("X-API-Key", "key-123"))
.respond_with(ResponseTemplate::new(200)
.insert_header("content-type", "image/png")
.set_body_bytes(b"PNGDATA".to_vec()))
.mount(&server).await;
let pool = db_with_site(&server.uri()).await;
let (mime, bytes) = fetch_view(&pool, Some("filename=a.png&type=output")).await.unwrap();
assert_eq!(mime, "image/png");
assert_eq!(bytes, b"PNGDATA");
}
```
- [ ] **Step 2: 运行测试,确认失败**
Run: `cargo test -p boosapi --lib routes::comfy_cloud_adapter::tests::view 2>&1 | tail -15`
Expected: FAIL —— `fetch_view` 未定义。
- [ ] **Step 3: 实现 `fetch_view` + 替换 `get_view` 空桩**
把 Task 3 的 `get_view` 空桩替换为:
```rust
async fn fetch_view(db: &sqlx::SqlitePool, query: Option<&str>) -> AppResult<(String, Vec<u8>)> {
let (base_url, api_key) = resolve_comfy_cloud_site(db).await?;
let q = query.unwrap_or("");
let url = if q.is_empty() { format!("{base_url}/api/view") } else { format!("{base_url}/api/view?{q}") };
let resp = client()
.get(url)
.header("X-API-Key", api_key)
.send().await
.map_err(|e| AppError::UpstreamError(e.to_string()))?;
if !resp.status().is_success() {
let st = resp.status();
return Err(AppError::UpstreamError(format!("Comfy Cloud view [{st}]")));
}
let mime = resp
.headers()
.get(header::CONTENT_TYPE)
.and_then(|v| v.to_str().ok())
.unwrap_or("application/octet-stream")
.to_string();
let bytes = resp.bytes().await.map_err(|e| AppError::UpstreamError(e.to_string()))?.to_vec();
Ok((mime, bytes))
}
async fn get_view(
State(state): State<AppState>,
RawQuery(query): RawQuery,
) -> AppResult<Response> {
let (mime, bytes) = fetch_view(&state.db, query.as_deref()).await?;
Response::builder()
.status(StatusCode::OK)
.header(header::CONTENT_TYPE, mime)
.body(Body::from(bytes))
.map_err(|e| AppError::Internal(anyhow::anyhow!(e)))
}
```
> reqwest 默认跟随 302,所以 Comfy Cloud `/api/view` 的签名 URL 跳转会被自动跟随,
> 最终拿到文件字节。无需手动处理 Location。
- [ ] **Step 4: 运行测试,确认通过**
Run: `cargo test -p boosapi --lib routes::comfy_cloud_adapter 2>&1 | tail -10`
Expected: PASS(submit + history + view 共 3 个测试)。
- [ ] **Step 5: Commit**
```bash
git add src/routes/comfy_cloud_adapter.rs
git commit -m "feat(comfy-cloud): /view 产出文件透传"
```
<!-- T6 -->
## Task 6: 挂载路由 + 前端平台选项 + 全量验证
**Files:**
- Modify: `src/routes/mod.rs`
- Modify: `src/web/pages/Sites.tsx`
- [ ] **Step 1: `src/routes/mod.rs` 顶部模块声明区加**
```rust
mod comfy_cloud_adapter;
```
- [ ] **Step 2: `build_router` 的 merge 链里加(`.merge(picture_agent::routes())` 附近)**
```rust
.merge(comfy_cloud_adapter::routes())
```
- [ ] **Step 3: 前端 `SITE_PLATFORM_OPTIONS` 加 comfy_cloud 选项**
在 `src/web/pages/Sites.tsx` 的 `SITE_PLATFORM_OPTIONS` 数组(约 line 700-710,
`{ value: 'cliproxyapi', ... }` 附近)加一项:
```tsx
{ value: 'comfy_cloud', label: 'Comfy Cloud', description: '工作流执行 API（数字人/图片视频）' },
```
- [ ] **Step 4: 后端全量构建 + comfy_cloud 测试**
Run: `cargo build -j 2 2>&1 | tail -3 && cargo test -p boosapi --lib comfy_cloud 2>&1 | command grep "test result"`
Expected: `Finished`;comfy_cloud service + routes 测试全 PASS。
- [ ] **Step 5: 前端 typecheck**
Run: `npm run typecheck:web 2>&1 | tail -5`
Expected: 无错误。
- [ ] **Step 6: Commit**
```bash
git add src/routes/mod.rs src/web/pages/Sites.tsx
git commit -m "feat(comfy-cloud): 挂载适配路由 + 站点管理 comfy_cloud 平台选项"
```
---
## Task 7: 真实联调(手动验证,非自动测试)
> 这一步需要运行中的 BoosAPI + Pixelle,属手动验证。前 6 个 task 完成且 push 后执行。
- [ ] **Step 1: 站点管理添加 Comfy Cloud 站点**
在管理控制台「站点管理」新增站点:平台选 `Comfy Cloud`,URL 填 `https://cloud.comfy.org`,
API Key 填有效的 Comfy Cloud key(`X-API-Key`),状态 active。
- [ ] **Step 2: 改 Pixelle config.yaml 的 comfyui_url**
把 `/opt/Pixelle-Video/config.yaml` 的 `comfyui.comfyui_url` 改为
`http://<boosapi-host>:<port>/comfy-cloud`(指向 BoosAPI 适配端点),
然后 `docker compose restart api`(在 `/opt/Pixelle-Video`)。
- [ ] **Step 3: 跑一次 selfhost 视频生成**
从前端触发数字人/图片 selfhost 工作流生成视频,确认:
- 不再出现 `401 AuthenticationRequired`。
- 任务能提交(拿到 prompt_id)、轮询到 completed、取回产出文件。
- [ ] **Step 4: 失败排查指引(若仍报错)**
- 仍 401:检查站点 api_key 是否为有效 Comfy Cloud key(`curl -H "X-API-Key: KEY" https://cloud.comfy.org/api/user` 应回 200)。
- 404/路径错:确认 Pixelle comfyui_url 末尾无多余 `/`,BoosAPI 适配端点前缀为 `/comfy-cloud`。
- 取不到产出:看 BoosAPI 日志里 `/api/jobs/{id}` 的响应 outputs 结构,必要时调 translate 映射。
---
## 完成标准
- 后端:`resolve_comfy_cloud_site` + `comfy_cloud_job_to_history` + 三个适配端点
(`/comfy-cloud/{prompt,history,view}`)实现并测试通过,`cargo build -j 2` 干净。
- 前端:站点管理可选 `comfy_cloud` 平台,`npm run typecheck:web` 干净。
- 联调:Pixelle 指向 BoosAPI 适配端点后,selfhost 视频生成不再 401 且能出片。
- 全部提交在 `feat/comfy-cloud-adapter` 分支。
docs/superpowers/plans/2026-06-18-digital-human-comfy-video-entry.md
+241
View File
@@ -0,0 +1,241 @@
# 数字人接入 Comfy Cloud 视频工作流(完整视频入口)实现计划
> **For agentic workers:** REQUIRED SUB-SKILL: Use superpowers:subagent-driven-development (recommended) or superpowers:executing-plans to implement this plan task-by-task. Steps use checkbox (`- [ ]`) syntax for tracking.
**Goal:** 给 BoosAPI 数字人加「视频工作流」入口,让用户选 `comfy/video_digital_ltx2.json` 触发「肖像图+旁白音频→LTX2.3 说话视频」,贯穿前端→BoosAPI 后端→Pixelle 三层。
**Architecture:** 前端 `DigitalHuman.tsx` 加可选「视频工作流」选择器(列 `video_*`),提交 `api_video_workflow`;BoosAPI `digital_human.rs` 的 `pixelle_request_body` 透传该字段;Pixelle `asset_based.py` 对 `comfy/` 视频工作流也注入 `audio_path`。视频入口默认空=不启用,保持现有「图片+HTML 合成」向后兼容。
**Tech Stack:** React/TS(BoosAPI 前端)、Rust/axum(BoosAPI 后端)、Python(Pixelle,容器内)。
> **环境:** BoosAPI 仓库 `/root/metapi`,前端 `src/web`,后端 `src/routes`。Pixelle 在 Docker 容器 `pixelle-video-api`,源码 `/app/pixelle_video`(镜像内置,改后 `docker compose restart api`,备份到 `/opt/Pixelle-Video/patches/`)。构建:前端 `npm run typecheck:web`,后端 `cargo build -j 2`(-j 2 防 OOM)。分支 `feat/comfy-cloud-adapter`。
> **前置(已完成):** comfy-cloud 适配器、`comfy/video_digital_ltx2.json`(probe 通过)、media.py 转发 image_path。
---
## 文件结构
- Modify `src/web/pages/DigitalHuman.tsx` — 加 `apiVideoWorkflow` state + 「视频工作流」选择器 + payload 字段 + draft 持久化。
- Modify `src/routes/digital_human.rs` — `pixelle_request_body` 转发 `api_video_workflow`。
- Modify(容器内)`/app/pixelle_video/pipelines/asset_based.py` — comfy 视频工作流注入 audio_path。
---
<!-- TASKS -->
## Task 1: 前端加「视频工作流」选择器 + 提交字段
**Files:**
- Modify: `src/web/pages/DigitalHuman.tsx`
- [ ] **Step 1: `DigitalHumanDraft` type 加字段(~line 34 附近,imageWorkflow 旁)**
找到 `imageWorkflow?: string;`(约 line 34),其后加一行:
```ts
apiVideoWorkflow?: string;
```
- [ ] **Step 2: 加 state(~line 370,imageWorkflow useState 旁)**
找到 `const [imageWorkflow, setImageWorkflow] = useState(draftRef.current.imageWorkflow || '');`(约 line 370),其后加:
```ts
const [apiVideoWorkflow, setApiVideoWorkflow] = useState(draftRef.current.apiVideoWorkflow || '');
```
- [ ] **Step 3: draft 持久化加字段(~line 462 写入 + ~line 480 依赖数组)**
在 `writeDigitalHumanDraft({...})` 对象里(约 line 462),`imageWorkflow,` 后加 `apiVideoWorkflow,`;
在该 useEffect 的依赖数组里(约 line 480),`imageWorkflow,` 后同样加 `apiVideoWorkflow,`。
- [ ] **Step 4: 提交 payload 加字段(~line 570 payload 对象)**
找到 payload 对象里的 `media_workflow: imageWorkflow || undefined,`(约 line 575),其后加:
```ts
api_video_workflow: apiVideoWorkflow || undefined,
```
- [ ] **Step 5: 加「视频工作流」选择器 UI(图片工作流 select 之后,~line 1012)**
找到「图片工作流」那个 `<label className="digital-human-field">...select...</label>` 块结束处
(约 line 1012,`</label>` 后),插入新选择器:
```tsx
<label className="digital-human-field">
<span>视频工作流（可选，生成说话视频）</span>
<select value={apiVideoWorkflow} onChange={(event) => setApiVideoWorkflow(event.target.value)}>
<option value="">不生成视频（仅图片合成）</option>
{mediaWorkflows
.filter((wf) => wf.name.toLowerCase().includes('video'))
.map((wf) => (
<option key={workflowValue(wf)} value={workflowValue(wf)}>{pickItemLabel(wf)}{wf.source ? ` · ${wf.source}` : ''}</option>
))}
</select>
</label>
```
- [ ] **Step 6: typecheck**
Run: `cd /root/metapi && npm run typecheck:web 2>&1 | tail -5`
Expected: 无 TS 错误。
- [ ] **Step 7: Commit**
```bash
cd /root/metapi && git add src/web/pages/DigitalHuman.tsx
git commit -m "feat(digital-human): 前端加视频工作流选择器(api_video_workflow)
Co-Authored-By: Claude <noreply@anthropic.com>"
```
<!-- T2 -->
## Task 2: BoosAPI 后端转发 api_video_workflow 给 Pixelle
**Files:**
- Modify: `src/routes/digital_human.rs`
- [ ] **Step 1: 在 pixelle_request_body 加转发(~line 2077,tts_workflow 块之后)**
找到 `pixelle_request_body` 里转发 tts_workflow 的块(约 line 2073-2078):
```rust
if let Some(value) = optional_string(body, &["ttsWorkflow", "tts_workflow"])
.or_else(|| default_pixelle_tts_workflow(state, backend_provider))
{
request_body["tts_workflow"] = json!(value);
}
```
在它**之后**插入:
```rust
if let Some(value) = optional_string(body, &["apiVideoWorkflow", "api_video_workflow"]) {
request_body["api_video_workflow"] = json!(value);
}
```
- [ ] **Step 2: 构建确认编译**
Run: `cd /root/metapi && cargo build -j 2 2>&1 | tail -3`
Expected: `Finished`。
- [ ] **Step 3: 确认 optional_string 接受多 key(它已在文件内大量使用,签名兼容)**
Run: `cd /root/metapi && rtk proxy grep -n "fn optional_string" src/routes/digital_human.rs | head`
Expected: 找到定义,签名为 `(body, keys: &[&str])`(与 Step 1 用法一致)。若签名不同,按实际调整调用形式。
- [ ] **Step 4: Commit**
```bash
cd /root/metapi && git add src/routes/digital_human.rs
git commit -m "feat(digital-human): 后端转发 api_video_workflow 给 Pixelle
Co-Authored-By: Claude <noreply@anthropic.com>"
```
<!-- T3 -->
## Task 3: Pixelle 给 comfy 视频工作流注入 audio_path
**Files:**
- Modify(容器内):`/app/pixelle_video/pipelines/asset_based.py`
- [ ] **Step 1: 定位音频注入块(~line 703)**
Run: `rtk proxy docker exec pixelle-video-api sh -lc "grep -n 'audio_driven_i2v' /app/pixelle_video/pipelines/asset_based.py"`
Expected: 命中 `if "audio_driven_i2v" in adapter_abilities:` 那行(约 703)。
- [ ] **Step 2: 在该判断旁加 comfy 前缀分支(用 python 精确改写)**
```bash
rtk proxy docker exec pixelle-video-api /app/.venv/bin/python -c "
p='/app/pixelle_video/pipelines/asset_based.py'
src=open(p).read()
anchor=' if \"audio_driven_i2v\" in adapter_abilities:\n api_video_params[\"audio_path\"] = frame.audio_path'
assert anchor in src, 'anchor not found'
add=anchor + '''
elif isinstance(api_video_workflow, str) and api_video_workflow.startswith(\"comfy/\"):
api_video_params[\"audio_path\"] = frame.audio_path'''
if 'api_video_workflow.startswith(\"comfy/\")' in src:
print('already patched')
else:
src=src.replace(anchor, add, 1)
open(p,'w').write(src)
print('patched')
"
```
Expected: `patched`(或 `already patched`)。
- [ ] **Step 3: 语法校验 + 重启 + 备份**
```bash
rtk proxy docker exec pixelle-video-api /app/.venv/bin/python -c "import ast; ast.parse(open('/app/pixelle_video/pipelines/asset_based.py').read()); print('syntax OK')"
cd /opt/Pixelle-Video && rtk proxy docker compose restart api && sleep 7 && rtk proxy docker ps --filter name=pixelle --format '{{.Names}} {{.Status}}'
mkdir -p /opt/Pixelle-Video/patches && rtk proxy docker cp pixelle-video-api:/app/pixelle_video/pipelines/asset_based.py /opt/Pixelle-Video/patches/asset_based.py.patched
```
Expected: `syntax OK`;容器 healthy;备份文件存在。
- [ ] **Step 4: 确认改动重启后仍在**
Run: `rtk proxy docker exec pixelle-video-api sh -lc "grep -c 'api_video_workflow.startswith(\"comfy/\")' /app/pixelle_video/pipelines/asset_based.py"`
Expected: `1`。无 git commit(Pixelle 非本仓库)。
<!-- T4 -->
## Task 4: 部署 BoosAPI + 端到端联调
**Files:** 无(部署 + 运行时验证)
- [ ] **Step 1: 重新构建并重启 BoosAPI(含前端改动)**
前端改了需重新 build 前端资源,后端改了需重新编译。用项目脚本:
```bash
cd /root/metapi && ./build-and-run.sh --fast-release 2>&1 | tail -15
```
> 若只想快速验证后端逻辑、前端单独 build,可 `npm run build:web` + `./build-and-run.sh --backend-only`。
> Expected: 构建成功,BoosAPI 起在 :4000。注意这是动线上服务,确认当前无关键流量再重启。
- [ ] **Step 2: 确认数字人 UI 出现「视频工作流」选择器**
打开管理控制台数字人页面,确认新增「视频工作流(可选)」下拉,选项含
`video_digital_ltx2`(comfy)+ `video_wan2.1_fusionx`(comfy)等 video_* 工作流。
- [ ] **Step 3: 发起数字人任务,视频工作流选 `comfy/video_digital_ltx2.json`**
给肖像图 + 文本 + 选 TTS,视频工作流选 `comfy/video_digital_ltx2.json`,提交。
- [ ] **Step 4: 监控流转(BoosAPI 日志 + Comfy Cloud job)**
```bash
cd /root/metapi && rtk proxy sqlite3 boosapi.db "SELECT id, created_at, client_family, http_status, substr(error_message,1,80) FROM proxy_logs ORDER BY id DESC LIMIT 5;"
```
Expected: 新日志(id 增长),数字人任务推进;Comfy Cloud 出现 LTX2.3 job;最终出说话视频。
- [ ] **Step 5: 出错归因**
- LoadImage 仍用默认图 → 查 media.py image_path 转发(Task 已完成,确认 `grep image_path /app/pixelle_video/services/media.py`)。
- LoadAudio 无音频 → 查 Task 3 注入(`grep comfy/ /app/pixelle_video/pipelines/asset_based.py`)+ workflow 标记 `$~audio_path!`。
- `api_video_workflow` 没传到 → 查 Task 2 后端转发 + Task 1 前端 payload 字段名(`api_video_workflow`)。
- 节点/模型错 → 不应发生(probe 已过);若发生看 Comfy Cloud 真实回包。
- [ ] **Step 6: 成功标准**
数字人任务选 comfy/video_digital_ltx2.json 后,Comfy Cloud 出真实 job,注入了
image_path+audio_path+prompt,返回带音频说话视频,数字人成片。
---
## 完成标准
- 前端:数字人页有「视频工作流」可选下拉,列 video_* 工作流,typecheck 干净。
- 后端:`api_video_workflow` 透传给 Pixelle,`cargo build -j 2` 通过。
- Pixelle:comfy 视频工作流注入 audio_path,重启生效,备份 patches/。
- 端到端:选 comfy/video_digital_ltx2.json 出说话视频。
- 向后兼容:不选视频工作流时,现有「图片+HTML 合成」行为不变。
## 已知风险 / 备注
- Pixelle asset_based.py 改动在镜像内置层,重建镜像会丢,已备份 patches/,长期应固化 Dockerfile。
- Task 4 动线上服务(重启 BoosAPI),确认时机。
- 单人肖像;多人不在范围。
- LTX2.3 执行时长/分辨率等真实生成参数,若出片质量/超时问题属调参,非本计划的接线问题。
docs/superpowers/plans/2026-06-18-ltx2-digital-human-workflow.md
+335
View File
@@ -0,0 +1,335 @@
# LTX2.3 数字人工作流(Comfy Cloud)实现计划
> **For agentic workers:** REQUIRED SUB-SKILL: Use superpowers:subagent-driven-development (recommended) or superpowers:executing-plans to implement this plan task-by-task. Steps use checkbox (`- [ ]`) syntax for tracking.
**Goal:** 让 Pixelle 数字人(说话头像)走 Comfy Cloud:把官方 LTX2.3 id_lora 模板做成 `comfy/digital_ltx2.json` 工作流,补上 Pixelle media.py 的 image_path 转发缺口,经已建好的 comfy-cloud 适配器执行。
**Architecture:** 工作流文件落 Pixelle 宿主 `data/workflows/comfy/`(经 `./data` 挂载),用 comfykit 的 `_meta.title` 标记(`$~image_path!`/`$~audio_path!`/`$prompt!`)注入肖像/音频/脚本;media.py 非 api 分支补 image_path 进 workflow_params;comfy/ 通道经 `comfyui_url`(=BoosAPI `/comfy-cloud` 适配器)打到 Comfy Cloud。
**Tech Stack:** Python (Pixelle/comfykit), ComfyUI API-format JSON, Comfy Cloud API, Docker。
> **环境约定:** Pixelle 跑在 Docker 容器 `pixelle-video-api`,代码 `/app/pixelle_video/`,工作流 `/app/data/workflows/`(宿主 `/opt/Pixelle-Video/data/workflows/`,bind mount,改宿主即生效)。容器内 python:`/app/.venv/bin/python`。BoosAPI 适配端点:容器内经 `http://172.17.0.1:4000/comfy-cloud`,宿主经 `http://127.0.0.1:4000/comfy-cloud`。改 media.py 后需 `docker compose restart api`。
> **硬依赖(Task 1 阻塞全局):** 需用户从 Comfy Cloud 网页导出 `video_ltx2_3_id_lora` 的 **API 格式** JSON 到 `/tmp/ltx2_api.json`。服务端无法代取。
---
## 文件结构
- 用户提供:`/tmp/ltx2_api.json` —— Comfy Cloud 导出的 API 格式工作流(子图已展开)。
- Create `/opt/Pixelle-Video/data/workflows/comfy/digital_ltx2.json` —— 改造后的数字人工作流(加标记、删 RecordAudio)。
- Modify(容器内)`/app/pixelle_video/services/media.py` —— 非 api 分支把 image_path 加入 workflow_params;同步宿主持久化方案。
- 临时:`/tmp/digital_ltx2_probe.json` —— 校验探测用 payload。
---
<!-- TASKS -->
## Task 1: 获取并校验 API 格式导出(硬依赖)
**Files:**
- 用户提供:`/tmp/ltx2_api.json`
- [ ] **Step 1: 确认导出文件存在且是 API 格式**
用户在 Comfy Cloud 网页打开 `video_ltx2_3_id_lora`(或 share `71f221d28df8`)→ Workflow → Export (API Format) → 放到 `/tmp/ltx2_api.json`。
Run: `rtk proxy docker exec pixelle-video-api sh -lc "ls -la /tmp/ltx2_api.json 2>/dev/null || echo MISSING"`
注意:文件在宿主还是容器?用户可能放宿主 `/tmp`。两处都查:
Run(宿主): `ls -la /tmp/ltx2_api.json 2>/dev/null || echo HOST_MISSING`
Expected: 文件存在(任一处)。若两处都 MISSING → BLOCKED,等用户提供。
- [ ] **Step 2: 校验是 API 格式(不是 UI 格式)**
API 格式是 `{节点id: {class_type, inputs, ...}}`,无顶层 `nodes` 数组。
Run:
```bash
python3 -c "
import json
wf=json.load(open('/tmp/ltx2_api.json'))
is_ui = isinstance(wf,dict) and 'nodes' in wf
print('UI格式(需重导)' if is_ui else 'API格式 OK')
if not is_ui:
print('节点数:', len(wf))
has_sub = any('subgraph' in str(v.get('class_type','')).lower() for v in wf.values() if isinstance(v,dict))
print('含未展开子图?', has_sub)
"
```
Expected: `API格式 OK`,节点数 >10,无未展开子图。若是 UI 格式或含子图 → 让用户用 **API Format** 重新导出(普通 Export 是 UI 格式)。
- [ ] **Step 3: 列出节点类型 + 模型引用,核对 Comfy Cloud 兼容**
Run:
```bash
python3 -c "
import json
wf=json.load(open('/tmp/ltx2_api.json'))
from collections import Counter
c=Counter(v.get('class_type') for v in wf.values() if isinstance(v,dict))
print('节点类型:')
for t,n in c.most_common(): print(f' {n}x {t}')
print('--- 模型引用 ---')
for nid,nd in wf.items():
if not isinstance(nd,dict): continue
for k,v in (nd.get('inputs') or {}).items():
if isinstance(v,str) and v.endswith('.safetensors'):
print(f' {nid}.{k} = {v}')
"
```
Expected: 看到 LTX2.3 节点 + 模型文件名。记录下来,Task 2 核对它们在 Comfy Cloud 池里(之前已验证 ltx-2.3-* 系列在;若导出引用了不同文件名,需在此对照 `/tmp/cc_nodes.json` 的池子)。
- [ ] **Step 4: 无需提交(纯校验,无文件改动)**
本任务只确认输入就绪。无 commit。
<!-- T2 -->
## Task 2: 改造工作流(加标记 + 删 RecordAudio + 落 comfy/)
**Files:**
- Create: `/opt/Pixelle-Video/data/workflows/comfy/digital_ltx2.json`
- [ ] **Step 1: 找到要标记的节点 id(LoadImage/LoadAudio/文本/RecordAudio)**
Run:
```bash
python3 -c "
import json
wf=json.load(open('/tmp/ltx2_api.json'))
for nid,nd in wf.items():
if not isinstance(nd,dict): continue
ct=nd.get('class_type','')
if ct in ('LoadImage','LoadAudio','RecordAudio','SaveVideo','PrimitiveStringMultiline','CLIPTextEncode'):
print(nid, ct, '| inputs:', json.dumps(nd.get('inputs',{}),ensure_ascii=False)[:100])
"
```
Expected: 看到 LoadImage、LoadAudio、RecordAudio、SaveVideo、文本节点各自的 id。记下:
- LoadImage 的 id(标 `$~image_path!`)
- LoadAudio 的 id(标 `$~audio_path!`)
- 文本提示节点 id(标 `$prompt!`)—— 优先 `PrimitiveStringMultiline`;若文本经 CLIPTextEncode 的 `text` 字段直接给,则标 CLIPTextEncode
- RecordAudio 的 id(删除)
- [ ] **Step 2: 写改造脚本生成 comfy/digital_ltx2.json**
> 把下面 `IMAGE_ID`/`AUDIO_ID`/`TEXT_ID`/`RECORD_ID` 替换为 Step 1 查到的实际 id。
> 文本节点字段名:若 PrimitiveStringMultiline 用 `value` 字段,标记写 `$prompt.value!`;
> 若 CLIPTextEncode 用 `text` 字段,写 `$prompt.text!`。按 Step 1 实际字段定。
```bash
python3 -c "
import json
wf=json.load(open('/tmp/ltx2_api.json'))
IMAGE_ID='REPLACE_IMAGE_ID'
AUDIO_ID='REPLACE_AUDIO_ID'
TEXT_ID='REPLACE_TEXT_ID'
TEXT_MARKER='\$prompt.value!' # 或 \$prompt.text! 视字段而定
RECORD_ID='REPLACE_RECORD_ID' # 若无 RecordAudio 留空字符串
def set_title(nid, marker):
nd=wf[nid]
nd.setdefault('_meta',{})['title']=marker
set_title(IMAGE_ID, '\$~image_path!')
set_title(AUDIO_ID, '\$~audio_path!')
set_title(TEXT_ID, TEXT_MARKER)
# 删 RecordAudio 并清理引用它的连线(把指向它的输入置空/删除)
if RECORD_ID and RECORD_ID in wf:
wf.pop(RECORD_ID)
for nid,nd in wf.items():
if not isinstance(nd,dict): continue
for k,v in list((nd.get('inputs') or {}).items()):
if isinstance(v,list) and len(v)==2 and str(v[0])==RECORD_ID:
# 该输入原本接 RecordAudio;数字人用 LoadAudio,删除这个悬空连接
del nd['inputs'][k]
import os
os.makedirs('/opt/Pixelle-Video/data/workflows/comfy', exist_ok=True)
json.dump(wf, open('/opt/Pixelle-Video/data/workflows/comfy/digital_ltx2.json','w'), ensure_ascii=False, indent=2)
print('written, 节点数:', len(wf))
# 校验标记落位
for nid in [IMAGE_ID,AUDIO_ID,TEXT_ID]:
print(nid, '->', wf.get(nid,{}).get('_meta',{}).get('title'))
"
```
Expected: 写入成功,三个标记落位正确,RecordAudio 已删。
> ⚠️ RecordAudio 与 LoadAudio 的关系:数字人用 LoadAudio 输入旁白。若导出的图里音频源是 RecordAudio 而非 LoadAudio(录音节点直接接到音频处理),则不能简单删 RecordAudio——要把音频处理节点的输入改接到 LoadAudio。Step 1 查清音频实际从哪个节点流出;若是 RecordAudio 流出,本步改为:保留一个 LoadAudio(标 `$~audio_path!`)并把下游音频输入接到 LoadAudio 的输出。具体连接以 Step 1 的图为准。
- [ ] **Step 3: 校验生成的 JSON 合法 + comfykit 能解析出参数**
Run(容器内,用 comfykit 解析):
```bash
rtk proxy docker exec pixelle-video-api /app/.venv/bin/python -c "
import json
from comfykit.comfyui.workflow_parser import WorkflowParser
wf=json.load(open('/app/data/workflows/comfy/digital_ltx2.json'))
p=WorkflowParser()
params=[]
for nid,nd in wf.items():
if not isinstance(nd,dict): continue
pl,ml,om=p.parse_node(nid,nd)
for x in pl: params.append((x.name,x.required,x.need_upload))
print('解析出的参数:', params)
"
```
Expected: 看到 `image_path`(upload=True)、`audio_path`(upload=True)、`prompt` 三个参数。
- [ ] **Step 4: Commit(工作流文件在 Pixelle 宿主目录,非 BoosAPI 仓库——仅记录到计划备注)**
工作流文件不在 git 仓库内。无 git commit;在此记录文件已落 `/opt/Pixelle-Video/data/workflows/comfy/digital_ltx2.json`。
<!-- T3 -->
## Task 3: 补 media.py 转发 image_path 到 comfy 通道
**Files:**
- Modify(容器内):`/app/pixelle_video/services/media.py`
> 注:`pixelle_video` 源码**在镜像内置,不在挂载卷**。容器内改 `docker compose restart` 能留,
> 但 `docker compose down && up`/重建镜像会丢。持久化方案见 Step 4。
- [ ] **Step 1: 定位 workflow_params 构建处**
`media.py` 的 `__call__` 里,api/ 分支之后、`workflow_params = {"prompt": prompt}` 起的那段
(约 line 232)。`image_path` 是 `__call__` 的具名参数但没进 `workflow_params`。
Run: `rtk proxy docker exec pixelle-video-api sh -lc "grep -n 'workflow_params = {\"prompt\"' /app/pixelle_video/services/media.py"`
Expected: 定位到该行号(约 232)。
- [ ] **Step 2: 在 workflow_params 构建处加入 image_path**
在 `workflow_params = {"prompt": prompt}` 之后插入(用 sed 或 python 改文件)。注意这是容器内文件,
用 `docker exec ... python` 做精确插入最稳妥:
```bash
rtk proxy docker exec pixelle-video-api /app/.venv/bin/python -c "
p='/app/pixelle_video/services/media.py'
src=open(p).read()
anchor='workflow_params = {\"prompt\": prompt}'
assert anchor in src, 'anchor not found'
add='''workflow_params = {\"prompt\": prompt}
if image_path is not None:
workflow_params[\"image_path\"] = image_path'''
if 'workflow_params[\"image_path\"]' in src:
print('already patched')
else:
src=src.replace(anchor, add, 1)
open(p,'w').write(src)
print('patched')
"
```
Expected: `patched`(或 `already patched`)。
- [ ] **Step 3: 校验语法 + 重启容器**
```bash
rtk proxy docker exec pixelle-video-api /app/.venv/bin/python -c "import ast; ast.parse(open('/app/pixelle_video/services/media.py').read()); print('syntax OK')"
cd /opt/Pixelle-Video && rtk proxy docker compose restart api && sleep 7 && rtk proxy docker ps --filter name=pixelle --format '{{.Names}} {{.Status}}'
```
Expected: `syntax OK`;容器 `Up ... (healthy)`。
- [ ] **Step 4: 持久化方案(防镜像重建丢失)**
把改动备份到宿主,并记录到 Pixelle 部署说明:
```bash
rtk proxy docker cp pixelle-video-api:/app/pixelle_video/services/media.py /opt/Pixelle-Video/patches/media.py.patched 2>/dev/null || (mkdir -p /opt/Pixelle-Video/patches && rtk proxy docker cp pixelle-video-api:/app/pixelle_video/services/media.py /opt/Pixelle-Video/patches/media.py.patched)
echo "已备份改后 media.py 到 /opt/Pixelle-Video/patches/;重建镜像后需重新 docker cp 回 /app/pixelle_video/services/media.py 或固化进 Dockerfile"
```
Expected: 备份文件存在。无 git commit(Pixelle 非本仓库)。
<!-- T4 -->
## Task 4: 校验探测(确认 Comfy Cloud 接受工作流)
**Files:**
- 临时:`/tmp/digital_ltx2_probe.json`
- [ ] **Step 1: 用占位输入构建 probe payload**
注入标记的字段需要具体值才能提交校验。用占位文件名探测(校验在执行前,不真正读文件):
```bash
python3 -c "
import json
wf=json.load(open('/opt/Pixelle-Video/data/workflows/comfy/digital_ltx2.json'))
# probe 直接提交节点图本身(标记字段已有默认值或占位);comfykit 注入是运行时的事,
# 这里验证 Comfy Cloud 是否接受这套节点+模型
json.dump({'prompt':wf}, open('/tmp/digital_ltx2_probe.json','w'), ensure_ascii=False)
print('probe payload bytes:', len(open('/tmp/digital_ltx2_probe.json').read()))
"
```
Expected: payload 生成。
> 注:工作流里 LoadImage/LoadAudio 的默认 widget 值(模板自带的示例文件名)可能在 Comfy Cloud
> 不存在,导致校验报"文件不存在"。这是**预期且可接受**的——它证明节点+模型校验已过,只差真实输入。
> 关注点是有没有 `unsupported node type` / 模型缺失类错误。
- [ ] **Step 2: 提交探测,读校验结果**
```bash
curl -s -w "\nHTTP %{http_code}\n" -X POST http://127.0.0.1:4000/comfy-cloud/prompt -H "Content-Type: application/json" --data @/tmp/digital_ltx2_probe.json 2>&1 | head -15
```
Expected 判读:
- `{"node_errors":{},"prompt_id":"..."}` HTTP 200 → 完美,全兼容。
- `400 ... unsupported node type 'X'` → 节点 X 不在 Comfy Cloud,需在工作流里替换/移除该节点(回 Task 2 处理)。
- `400 ... 文件/模型 不存在`(针对 LoadImage 示例图或某 .safetensors)→ 若是输入文件(LoadImage 默认图)属预期;若是 .safetensors 模型缺失,需换 Comfy Cloud 有的等价模型(对照 `/tmp/cc_nodes.json` 池)。
- [ ] **Step 3: 据结果迭代或放行**
- 全兼容 → 进 Task 5。
- 节点/模型问题 → 回 Task 2 调整工作流(换节点或模型名),重跑 Task 4。不要跳过。
<!-- T5 -->
## Task 5: 真实数字人任务联调
**Files:** 无(运行时验证)
- [ ] **Step 1: 在 Pixelle 前端发起数字人任务,视频/动画工作流选 `comfy/digital_ltx2.json`**
数字人流程的 image→video 动画步(`api_video_workflow` 或对应 UI 项)填/选 `comfy/digital_ltx2.json`。
触发一个任务(给个肖像图 + 文本)。
- [ ] **Step 2: 观察任务流转**
预期:LLM 脚本步 → 生成肖像图(comfy 图片工作流)+ TTS 音频 → digital_ltx2 动画步:
注入 image_path/audio_path/prompt → Comfy Cloud 建 job → 轮询 completed → 取回说话视频 → HTML 合成。
监控 BoosAPI 侧 proxy_logs:
```bash
rtk proxy sqlite3 boosapi.db "SELECT id, created_at, client_family, http_status, substr(error_message,1,80) FROM proxy_logs ORDER BY id DESC LIMIT 5;"
```
Expected: 新日志(id 增长),数字人任务最终 success / 出片。
- [ ] **Step 3: 出错则按错误类型归因**
- `unsupported node` / 模型缺失 → 回 Task 2/4。
- image_path 未注入(LoadImage 仍用默认图)→ 回 Task 3 确认 media.py 改动生效(`grep image_path /app/.../media.py`)+ Task 2 确认 `$~image_path!` 标记落位。
- 执行期失败(Comfy Cloud job failed)→ 真实生成问题(参数/分辨率/时长),据 job 错误调工作流默认值。
- [ ] **Step 4: 成功标准**
数字人任务在 Comfy Cloud 出现真实 job、跑完、返回带音频的说话视频,Pixelle 合成出片。
---
## 完成标准
- `comfy/digital_ltx2.json` 落地、comfykit 能解析出 image_path/audio_path/prompt 三参数。
- media.py 已转发 image_path 到 comfy 通道(并备份到宿主 patches/)。
- 校验探测确认 Comfy Cloud 接受工作流(节点+模型兼容)。
- 真实数字人任务经 comfy/Comfy Cloud 出片。
## 已知风险 / 备注
- 硬依赖用户导出 API JSON(Task 1);拿不到则全卡。
- media.py 改动在镜像内置层,重建镜像会丢,已备份到 `/opt/Pixelle-Video/patches/`,长期应固化进 Dockerfile/启动脚本。
- 工作流默认 widget 值(示例图/音频文件名)在 Comfy Cloud 不存在属正常,真实运行靠注入覆盖。
- 单人肖像;多人对话不在范围。
docs/superpowers/plans/2026-06-18-pixelle-connection-management.md
+503
View File
@@ -0,0 +1,503 @@
# Pixelle 连接凭证纳入 BoosAPI 管理 实现计划
> **For agentic workers:** REQUIRED SUB-SKILL: Use superpowers:subagent-driven-development (recommended) or superpowers:executing-plans to implement this plan task-by-task. Steps use checkbox (`- [ ]`) syntax for tracking.
**Goal:** 在 BoosAPI 连接管理页加「Pixelle 连接」卡片,管 runninghub_api_key / comfyui_url / comfyui_api_key 三个凭证,保存即写入 settings 表 + 同步 Pixelle config.yaml + 重启 pixelle 容器生效。
**Architecture:** 新增 service `pixelle_connection.rs`(读写 settings 表 + 改 config.yaml YAML 三键 + docker restart)+ admin 路由(GET/PUT,密钥掩码)+ 前端 Accounts 页卡片。settings 表为真相源,config.yaml 是同步目标。
**Tech Stack:** Rust(axum, sqlx, serde_yaml<新增依赖>, tokio::process)、React/TS。
> **构建/测试:** `cargo build -j 2`(-j2 防 OOM)、`cargo test -p boosapi --lib pixelle_connection`、`npm run typecheck:web`。分支 `feat/comfy-cloud-adapter`。Pixelle compose 目录 `/opt/Pixelle-Video`,config `/opt/Pixelle-Video/config.yaml`。
---
## 文件结构
- Modify `Cargo.toml` — 加 `serde_yaml` 依赖。
- Modify `src/config.rs` — `PixelleVideoConfig` 加 `config_path` / `compose_dir` 两字段(默认 `/opt/Pixelle-Video/config.yaml`、`/opt/Pixelle-Video`)。
- Create `src/services/pixelle_connection.rs` — read/save settings + sync_to_pixelle(改 yaml)+ restart。
- Modify `src/services/mod.rs` — `pub mod pixelle_connection;`。
- Create `src/routes/admin/pixelle_connection.rs` — GET/PUT handler(掩码)。
- Modify `src/routes/admin/mod.rs` — 声明子模块 + 挂 2 条路由。
- Modify `src/web/api.ts` — adminApi 加 getPixelleConnection / savePixelleConnection。
- Modify `src/web/pages/Accounts.tsx` — 加「Pixelle 连接」卡片。
---
<!-- TASKS -->
## Task 1: 加 serde_yaml 依赖 + config 路径字段
**Files:**
- Modify: `Cargo.toml`
- Modify: `src/config.rs`
- [ ] **Step 1: Cargo.toml 加 serde_yaml**
在 `[dependencies]` 段加(版本对齐项目 serde 生态,用 0.9):
```toml
serde_yaml = "0.9"
```
- [ ] **Step 2: PixelleVideoConfig 加两字段(src/config.rs,struct 内 timeout_secs 后)**
在 `pub timeout_secs: u64,` 之后加:
```rust
#[serde(default = "default_pixelle_config_path")]
pub config_path: String,
#[serde(default = "default_pixelle_compose_dir")]
pub compose_dir: String,
```
- [ ] **Step 3: 加默认值函数(src/config.rs,default_pixelle_backend_provider 附近)**
```rust
fn default_pixelle_config_path() -> String {
"/opt/Pixelle-Video/config.yaml".to_string()
}
fn default_pixelle_compose_dir() -> String {
"/opt/Pixelle-Video".to_string()
}
```
- [ ] **Step 4: PixelleVideoConfig::default() 补两字段**
找到 `impl Default for ...` 或 `PixelleVideoConfig::default()`(约 line 207 区域,有 `api_base_url: Some(...)` 那个),在其字段列表末尾加:
```rust
config_path: default_pixelle_config_path(),
compose_dir: default_pixelle_compose_dir(),
```
- [ ] **Step 5: 构建确认**
Run: `cd /root/metapi && cargo build -j 2 2>&1 | tail -3`
Expected: `Finished`。
- [ ] **Step 6: Commit**
```bash
cd /root/metapi && git add Cargo.toml Cargo.lock src/config.rs
git commit -m "feat(pixelle): 加 serde_yaml + Pixelle config 路径配置项
Co-Authored-By: Claude <noreply@anthropic.com>"
```
<!-- T2 -->
## Task 2: pixelle_connection service(settings + yaml 同步)
**Files:**
- Create: `src/services/pixelle_connection.rs`
- Modify: `src/services/mod.rs`
- [ ] **Step 1: src/services/mod.rs 加模块声明**
```rust
pub mod pixelle_connection;
```
- [ ] **Step 2: 写失败测试 `src/services/pixelle_connection.rs`(含结构 + sync 测试)**
```rust
use crate::error::{AppError, AppResult};
use serde::{Deserialize, Serialize};
use sqlx::SqlitePool;
#[derive(Debug, Clone, Default, Serialize, Deserialize)]
#[serde(rename_all = "camelCase")]
pub struct PixelleConnection {
pub runninghub_api_key: Option<String>,
pub comfyui_url: Option<String>,
pub comfyui_api_key: Option<String>,
}
const KEY_RH: &str = "pixelle.runninghub_api_key";
const KEY_URL: &str = "pixelle.comfyui_url";
const KEY_CK: &str = "pixelle.comfyui_api_key";
pub async fn read_connection(db: &SqlitePool) -> AppResult<PixelleConnection> {
async fn get(db: &SqlitePool, k: &str) -> AppResult<Option<String>> {
Ok(sqlx::query_scalar("SELECT value FROM settings WHERE key = ?")
.bind(k).fetch_optional(db).await?)
}
Ok(PixelleConnection {
runninghub_api_key: get(db, KEY_RH).await?,
comfyui_url: get(db, KEY_URL).await?,
comfyui_api_key: get(db, KEY_CK).await?,
})
}
pub async fn save_connection(db: &SqlitePool, conn: &PixelleConnection) -> AppResult<()> {
async fn put(db: &SqlitePool, k: &str, v: &Option<String>) -> AppResult<()> {
if let Some(val) = v {
sqlx::query("INSERT OR REPLACE INTO settings (key, value) VALUES (?, ?)")
.bind(k).bind(val).execute(db).await?;
}
Ok(())
}
put(db, KEY_RH, &conn.runninghub_api_key).await?;
put(db, KEY_URL, &conn.comfyui_url).await?;
put(db, KEY_CK, &conn.comfyui_api_key).await?;
Ok(())
}
/// 改 config.yaml 的 comfyui.{runninghub_api_key,comfyui_url,comfyui_api_key} 三键,其余保留。
/// 改前备份到 <path>.bak-<ts>。返回备份路径。
pub fn sync_to_pixelle(config_path: &str, conn: &PixelleConnection) -> AppResult<String> {
let content = std::fs::read_to_string(config_path)
.map_err(|e| AppError::ServiceUnavailable(format!("读取 Pixelle config 失败: {e}")))?;
let mut doc: serde_yaml::Value = serde_yaml::from_str(&content)
.map_err(|e| AppError::ServiceUnavailable(format!("解析 config.yaml 失败: {e}")))?;
let comfyui = doc.get_mut("comfyui")
.ok_or_else(|| AppError::ServiceUnavailable("config.yaml 缺少 comfyui 段".into()))?;
let map = comfyui.as_mapping_mut()
.ok_or_else(|| AppError::ServiceUnavailable("comfyui 段不是映射".into()))?;
if let Some(v) = &conn.runninghub_api_key {
map.insert("runninghub_api_key".into(), serde_yaml::Value::String(v.clone()));
}
if let Some(v) = &conn.comfyui_url {
map.insert("comfyui_url".into(), serde_yaml::Value::String(v.clone()));
}
if let Some(v) = &conn.comfyui_api_key {
map.insert("comfyui_api_key".into(), serde_yaml::Value::String(v.clone()));
}
let ts = chrono::Utc::now().format("%Y%m%d%H%M%S").to_string();
let backup = format!("{config_path}.bak-{ts}");
std::fs::copy(config_path, &backup)
.map_err(|e| AppError::ServiceUnavailable(format!("备份失败: {e}")))?;
let out = serde_yaml::to_string(&doc)
.map_err(|e| AppError::Internal(anyhow::anyhow!(e)))?;
std::fs::write(config_path, out)
.map_err(|e| AppError::ServiceUnavailable(format!("写入 config 失败: {e}")))?;
Ok(backup)
}
#[cfg(test)]
mod tests {
use super::*;
#[test]
fn sync_updates_three_keys_preserves_rest() {
let dir = std::env::temp_dir().join(format!("pxtest_{}", uuid::Uuid::new_v4().simple()));
std::fs::create_dir_all(&dir).unwrap();
let path = dir.join("config.yaml");
std::fs::write(&path,
"project_name: Pixelle-Video\ncomfyui:\n comfyui_url: https://old\n runninghub_api_key: oldkey\n comfyui_api_key: oldck\n runninghub_concurrent_limit: 1\n").unwrap();
let conn = PixelleConnection {
runninghub_api_key: Some("newkey".into()),
comfyui_url: Some("http://new".into()),
comfyui_api_key: Some("newck".into()),
};
let backup = sync_to_pixelle(path.to_str().unwrap(), &conn).unwrap();
assert!(std::path::Path::new(&backup).exists());
let after = std::fs::read_to_string(&path).unwrap();
assert!(after.contains("newkey"));
assert!(after.contains("http://new"));
assert!(after.contains("newck"));
// 保留其余键
assert!(after.contains("runninghub_concurrent_limit"));
assert!(after.contains("project_name"));
std::fs::remove_dir_all(&dir).ok();
}
}
```
- [ ] **Step 3: 运行测试,确认失败**
Run: `cd /root/metapi && cargo test -p boosapi --lib services::pixelle_connection 2>&1 | tail -15`
Expected: FAIL —— 模块/函数未定义(首次编译错误)。
- [ ] **Step 4: 实现**
Step 2 的代码即实现(测试与实现同文件)。确保 mod.rs 已声明。
- [ ] **Step 5: 运行测试,确认通过**
Run: `cd /root/metapi && cargo test -p boosapi --lib services::pixelle_connection 2>&1 | tail -10`
Expected: PASS(1 个测试)。
- [ ] **Step 6: Commit**
```bash
cd /root/metapi && git add src/services/mod.rs src/services/pixelle_connection.rs
git commit -m "feat(pixelle): 连接凭证 service(settings 读写 + config.yaml 同步)
Co-Authored-By: Claude <noreply@anthropic.com>"
```
<!-- T3 -->
## Task 3: restart helper + admin 路由(掩码)
**Files:**
- Modify: `src/services/pixelle_connection.rs`(加 restart)
- Create: `src/routes/admin/pixelle_connection.rs`
- Modify: `src/routes/admin/mod.rs`
- [ ] **Step 1: 加 restart_pixelle(pixelle_connection.rs,sync_to_pixelle 之后)**
```rust
pub async fn restart_pixelle(compose_dir: &str) -> AppResult<()> {
let output = tokio::process::Command::new("docker")
.args(["compose", "restart", "api"])
.current_dir(compose_dir)
.output()
.await
.map_err(|e| AppError::ServiceUnavailable(format!("docker compose restart 启动失败: {e}")))?;
if !output.status.success() {
let stderr = String::from_utf8_lossy(&output.stderr);
return Err(AppError::ServiceUnavailable(format!(
"Pixelle 重启失败: {}", stderr.trim()
)));
}
Ok(())
}
```
- [ ] **Step 2: 写 admin 路由 `src/routes/admin/pixelle_connection.rs`**
```rust
use crate::error::AppResult;
use crate::services::pixelle_connection::{self, PixelleConnection};
use crate::AppState;
use axum::{extract::State, Json};
use serde::Deserialize;
use serde_json::{json, Value};
const MASK_SENTINEL: &str = "••••";
fn mask(v: &Option<String>) -> Value {
match v {
Some(s) if s.len() > 4 => json!(format!("{}{}", MASK_SENTINEL, &s[s.len()-4..])),
Some(s) if !s.is_empty() => json!(MASK_SENTINEL),
_ => Value::Null,
}
}
pub async fn get_connection(State(state): State<AppState>) -> AppResult<Json<Value>> {
let c = pixelle_connection::read_connection(&state.db).await?;
Ok(Json(json!({
"success": true,
"connection": {
// url 不算敏感,明文回;两个 key 掩码
"comfyuiUrl": c.comfyui_url,
"runninghubApiKey": mask(&c.runninghub_api_key),
"comfyuiApiKey": mask(&c.comfyui_api_key),
}
})))
}
#[derive(Debug, Deserialize)]
#[serde(rename_all = "camelCase")]
pub struct UpdatePayload {
runninghub_api_key: Option<String>,
comfyui_url: Option<String>,
comfyui_api_key: Option<String>,
}
fn keep_if_not_mask(incoming: Option<String>) -> Option<String> {
// 掩码值(以 •••• 开头)表示"未修改",跳过
match incoming {
Some(s) if s.starts_with(MASK_SENTINEL) => None,
other => other,
}
}
pub async fn put_connection(
State(state): State<AppState>,
Json(p): Json<UpdatePayload>,
) -> AppResult<Json<Value>> {
let conn = PixelleConnection {
runninghub_api_key: keep_if_not_mask(p.runninghub_api_key),
comfyui_url: p.comfyui_url, // url 明文,不掩码
comfyui_api_key: keep_if_not_mask(p.comfyui_api_key),
};
pixelle_connection::save_connection(&state.db, &conn).await?;
let backup = pixelle_connection::sync_to_pixelle(&state.config.pixelle_video.config_path, &conn)?;
let restart = pixelle_connection::restart_pixelle(&state.config.pixelle_video.compose_dir).await;
match restart {
Ok(()) => Ok(Json(json!({ "success": true, "backup": backup, "restarted": true }))),
Err(e) => Ok(Json(json!({
"success": true, "backup": backup, "restarted": false,
"warning": format!("配置已写入,但 Pixelle 重启失败,请手动重启: {e}")
}))),
}
}
```
- [ ] **Step 3: src/routes/admin/mod.rs 声明子模块 + 挂路由**
模块声明区(`mod users;` 附近)加:
```rust
mod pixelle_connection;
```
在 `routes()` 的路由链里(`/api/admin/user-balances` 那一带)加:
```rust
.route(
"/api/admin/pixelle/connection",
get(pixelle_connection::get_connection).put(pixelle_connection::put_connection),
)
```
确认 `get`/`put` 已从 axum::routing 引入(文件顶部应已 `use axum::routing::{get, post, ...}`;若缺 put 则补)。
- [ ] **Step 4: 构建确认**
Run: `cd /root/metapi && cargo build -j 2 2>&1 | tail -3`
Expected: `Finished`。
- [ ] **Step 5: Commit**
```bash
cd /root/metapi && git add src/services/pixelle_connection.rs src/routes/admin/pixelle_connection.rs src/routes/admin/mod.rs
git commit -m "feat(pixelle): 连接凭证 admin 端点(GET/PUT 掩码 + 重启)
Co-Authored-By: Claude <noreply@anthropic.com>"
```
<!-- T4 -->
## Task 4: 前端连接管理卡片
**Files:**
- Modify: `src/web/api.ts`
- Modify: `src/web/pages/Accounts.tsx`
- [ ] **Step 1: api.ts adminApi 加方法**
在 adminApi 对象里(找 `request(` 范式的 admin 方法群)加:
```typescript
getPixelleConnection: () =>
request<{ success: boolean; connection: { comfyuiUrl?: string | null; runninghubApiKey?: string | null; comfyuiApiKey?: string | null } }>("/api/admin/pixelle/connection"),
savePixelleConnection: (data: { runninghubApiKey?: string; comfyuiUrl?: string; comfyuiApiKey?: string }) =>
request<{ success: boolean; backup?: string; restarted?: boolean; warning?: string }>("/api/admin/pixelle/connection", {
method: "PUT",
body: JSON.stringify(data),
}),
```
- [ ] **Step 2: Accounts.tsx 加「Pixelle 连接」卡片**
先读 `src/web/pages/Accounts.tsx` 顶部,确认 `api`/`adminApi` 的导入名和 toast 用法。在页面主体某处(如页尾)加一个卡片组件块。最小实现(state + 加载 + 保存):
```tsx
// —— Pixelle 连接(加在组件内 state 区)——
const [pxConn, setPxConn] = useState({ comfyuiUrl: '', runninghubApiKey: '', comfyuiApiKey: '' });
const [pxSaving, setPxSaving] = useState(false);
useEffect(() => {
adminApi.getPixelleConnection()
.then((r) => setPxConn({
comfyuiUrl: r.connection?.comfyuiUrl || '',
runninghubApiKey: r.connection?.runninghubApiKey || '',
comfyuiApiKey: r.connection?.comfyuiApiKey || '',
}))
.catch(() => {});
}, []);
const savePxConn = async () => {
setPxSaving(true);
try {
const res = await adminApi.savePixelleConnection({
runninghubApiKey: pxConn.runninghubApiKey || undefined,
comfyuiUrl: pxConn.comfyuiUrl || undefined,
comfyuiApiKey: pxConn.comfyuiApiKey || undefined,
});
if (res.warning) toast.error(res.warning);
else toast.success('已保存并重启 Pixelle,约数秒生效');
} catch (e: any) {
toast.error(e?.message || '保存失败');
} finally {
setPxSaving(false);
}
};
```
卡片 JSX(加到 return 的合适位置,样式对齐页面现有 card):
```tsx
<div className="card" style={{ marginTop: 16, padding: 16 }}>
<h3>Pixelle 连接</h3>
<label style={{ display: 'block', marginBottom: 8 }}>
<span>ComfyUI URL</span>
<input value={pxConn.comfyuiUrl} onChange={(e) => setPxConn((s) => ({ ...s, comfyuiUrl: e.target.value }))} placeholder="http://172.17.0.1:4000/comfy-cloud" style={{ width: '100%' }} />
</label>
<label style={{ display: 'block', marginBottom: 8 }}>
<span>RunningHub API Key</span>
<input value={pxConn.runninghubApiKey} onChange={(e) => setPxConn((s) => ({ ...s, runninghubApiKey: e.target.value }))} placeholder="留空••••表示不改" style={{ width: '100%' }} />
</label>
<label style={{ display: 'block', marginBottom: 8 }}>
<span>Comfy Cloud API Key</span>
<input value={pxConn.comfyuiApiKey} onChange={(e) => setPxConn((s) => ({ ...s, comfyuiApiKey: e.target.value }))} placeholder="留空••••表示不改" style={{ width: '100%' }} />
</label>
<button type="button" className="btn btn-primary" disabled={pxSaving} onClick={savePxConn}>
{pxSaving ? '保存中...' : '保存并重启 Pixelle'}
</button>
</div>
```
> 注:`useState`/`useEffect` 若未导入需补;`adminApi`/`api` 用 Accounts.tsx 实际的导入名(读文件确认是 `api` 还是 `adminApi`)。若提交掩码值(`••••...`)后端会跳过不改,符合预期。
- [ ] **Step 3: typecheck**
Run: `cd /root/metapi && npm run typecheck:web 2>&1 | tail -5`
Expected: 无 TS 错误。
- [ ] **Step 4: Commit**
```bash
cd /root/metapi && git add src/web/api.ts src/web/pages/Accounts.tsx
git commit -m "feat(pixelle): 连接管理页加 Pixelle 连接卡片
Co-Authored-By: Claude <noreply@anthropic.com>"
```
<!-- T5 -->
## Task 5: 部署 + 端到端验证
**Files:** 无(部署 + 运行时)
- [ ] **Step 1: 重建并重启 BoosAPI(含前后端改动)**
```bash
cd /root/metapi && ./build-and-run.sh --fast-release 2>&1 | tail -15
```
Expected: 构建成功,BoosAPI 起在 :4000。动线上服务,确认时机。
- [ ] **Step 2: 连接管理页确认「Pixelle 连接」卡片**
硬刷新管理控制台连接管理页(`/accounts`),确认出现「Pixelle 连接」卡片,
ComfyUI URL 显示当前值,两个 key 显示掩码(`••••xxxx`)。
- [ ] **Step 3: 改一个值测试同步**
把 RunningHub API Key 改成一个新值,保存。确认:
```bash
grep runninghub_api_key /opt/Pixelle-Video/config.yaml | sed 's/[a-f0-9]\{20\}/.../'
ls -t /opt/Pixelle-Video/config.yaml.bak-* | head -1
rtk proxy docker ps --filter name=pixelle --format '{{.Names}} {{.Status}}'
```
Expected: config.yaml 的 key 变成新值;有新备份文件;容器重启后 healthy。
- [ ] **Step 4: 掩码不改测试**
只改 ComfyUI URL、两个 key 保持掩码原值,保存。确认 config.yaml 里两个 key **没变**
(掩码值被后端跳过),URL 变了。
- [ ] **Step 5: 成功标准**
UI 改 Pixelle 凭证 → settings 表存值 + config.yaml 同步 + 容器重启,不再需要手动编辑文件。
---
## 完成标准
- 后端:pixelle_connection service(读写 settings + sync_to_pixelle + restart)+ admin GET/PUT 端点,`cargo build -j 2` 通过,service 单测通过。
- 前端:连接管理页有「Pixelle 连接」卡片,typecheck 干净。
- 端到端:UI 改凭证 → config.yaml 同步 + 容器重启生效;掩码值不误改。
- 向后兼容:不改 Pixelle 源码;config.yaml 其余键保留;每次改前备份。
## 已知风险 / 备注
- serde_yaml 重序列化会丢 config.yaml 注释(已接受;每次有时间戳备份兜底)。
- BoosAPI 进程需有 docker compose 执行权限 + config.yaml 读写权限(同宿主 root 运行,满足)。
- Task 5 重启 BoosAPI 动线上服务,确认时机。
- 备份文件会累积(config.yaml.bak-*),长期可加清理,本期不做。
docs/superpowers/plans/2026-06-18-workflow-ui-split.md
+244
View File
@@ -0,0 +1,244 @@
# workflow_ui.rs 拆分(8 子模块)实现计划
> **For agentic workers:** REQUIRED SUB-SKILL: Use superpowers:subagent-driven-development (recommended) or superpowers:executing-plans to implement this plan task-by-task. Steps use checkbox (`- [ ]`) syntax for tracking.
**Goal:** 把 `src/routes/workflow_ui.rs`(6181 行)按职责拆成 `src/routes/workflow_ui/` 目录 8 个子模块,纯机械移动、零逻辑改动,对外接口不变。
**Architecture:** 先建目录把原文件变 `mod.rs`,再逐个子模块把相关函数剪切出去(`pub(super)` 可见性 + 补 use),每步 cargo 编译验证。Rust 编译器是主安全网。
**Tech Stack:** Rust (axum, sqlx)。验证:`cargo build -j 2`、`cargo test -p boosapi --lib routes::workflow_ui`。
> **核心纪律:** 纯搬运,函数体一字不改;只改可见性 + use 路径。不优化、不改逻辑、不动路由路径。每抽完一组即编译+测试+提交。分支 `feat/comfy-cloud-adapter`。
> **验证基线(开工前先记录):** 跑 `cargo test -p boosapi --lib routes::workflow_ui 2>&1 | grep "test result"` 记下当前测试数(应 5 个),全程不得减少。
---
## 文件结构(目标)
```
src/routes/workflow_ui/
mod.rs — routes() + 共享类型(WorkflowCaller/各 Query/Payload struct)+ 跨模块小工具 + 子模块声明 + 测试入口
assets.rs — UI 静态资源服务/嵌入目录/index/static/serve_file/官方模板资源
auth.rs — caller 解析
node_defs.rs — 节点定义 + 工作流模板图
models.rs — 模型分类 + folder 模型
comfy_proxy.rs — ComfyUI API 代理 handler(settings/userdata/object_info/...)
validate.rs — 工作流校验
queue.rs — 队列/历史/prompt/view
```
> 当前 `src/routes/workflow_ui.rs`(单文件)→ 变为 `src/routes/workflow_ui/mod.rs` + 7 个兄弟文件。
> `src/routes/mod.rs` 的 `mod workflow_ui;` 声明无需改(目录模块同名,Rust 自动找 mod.rs)。
---
<!-- TASKS -->
## Task 0: 文件转目录模块(零拆分,先搭壳)
**Files:**
- Move: `src/routes/workflow_ui.rs` → `src/routes/workflow_ui/mod.rs`
- [ ] **Step 1: 记录验证基线**
Run: `cd /root/metapi && cargo test -p boosapi --lib routes::workflow_ui 2>&1 | grep "test result"`
Expected: 记下测试数(预期 `5 passed`)。后续每步此数不得减少。
- [ ] **Step 2: 把文件移成目录模块**
```bash
cd /root/metapi
mkdir -p src/routes/workflow_ui
git mv src/routes/workflow_ui.rs src/routes/workflow_ui/mod.rs
```
- [ ] **Step 3: 编译 + 测试验证(内容没动,应原样通过)**
Run: `cd /root/metapi && cargo build -j 2 2>&1 | tail -3 && cargo test -p boosapi --lib routes::workflow_ui 2>&1 | grep "test result"`
Expected: `Finished`;测试数与基线一致。
- [ ] **Step 4: Commit**
```bash
cd /root/metapi && git add src/routes/workflow_ui.rs src/routes/workflow_ui/mod.rs
git commit -m "refactor(workflow_ui): 文件转目录模块(mod.rs,内容不变)
Co-Authored-By: Claude <noreply@anthropic.com>"
```
<!-- T1 -->
## Task 1: 抽 auth.rs(最小、最低风险,先验证流程)
**Files:**
- Create: `src/routes/workflow_ui/auth.rs`
- Modify: `src/routes/workflow_ui/mod.rs`
要搬的函数(用 grep 定位,函数体一字不改):`caller_from_headers`、`auth_caller`、`caller_user_id`、`caller_is_admin`。它们依赖类型 `WorkflowCaller`(留在 mod.rs)。
- [ ] **Step 1: 在 mod.rs 顶部加子模块声明**
在 mod.rs 的 `use` 区之后(`pub fn routes()` 之前)加:
```rust
mod auth;
```
- [ ] **Step 2: 确认这 4 个函数的精确范围 + WorkflowCaller 可见性**
Run: `cd /root/metapi && rtk proxy grep -nE "fn caller_from_headers|fn auth_caller|fn caller_user_id|fn caller_is_admin|enum WorkflowCaller" src/routes/workflow_ui/mod.rs`
记录每个函数起止行。`WorkflowCaller` 留 mod.rs,改成 `pub(super) enum WorkflowCaller`(让子模块可用)。
- [ ] **Step 3: 新建 auth.rs,粘入 4 个函数(函数体不改,补 use + 改可见性)**
新建 `src/routes/workflow_ui/auth.rs`,结构:
```rust
use super::WorkflowCaller;
use crate::error::AppResult;
use crate::AppState;
use axum::http::HeaderMap;
// (按 4 个函数实际用到的依赖补齐 use:validate_jwt、find_downstream_key_by_token 等——
// 从 mod.rs 顶部现有 use 里照抄它们需要的那几条)
pub(super) fn caller_from_headers(state: &AppState, headers: &HeaderMap) -> AppResult<WorkflowCaller> {
// ←原函数体一字不改粘进来
}
pub(super) fn caller_user_id(caller: &WorkflowCaller) -> Option<i64> {
// ←原体
}
pub(super) fn caller_is_admin(caller: &WorkflowCaller) -> bool {
// ←原体
}
pub(super) async fn auth_caller(state: &AppState, headers: &HeaderMap) -> AppResult<WorkflowCaller> {
// ←原体
}
```
> 关键:这 4 个函数从 mod.rs **删除**;其在 mod.rs/其他子模块的调用点改成 `auth::caller_from_headers(...)` 等(mod.rs 内加 `use auth::{caller_from_headers, auth_caller, caller_user_id, caller_is_admin};` 即可不改调用点写法)。
- [ ] **Step 4: mod.rs 加 use 引回,删除原 4 函数**
mod.rs 顶部子模块声明后加:
```rust
use auth::{auth_caller, caller_from_headers, caller_is_admin, caller_user_id};
```
并从 mod.rs 删掉这 4 个函数的原定义。
- [ ] **Step 5: 编译 + 测试**
Run: `cd /root/metapi && cargo build -j 2 2>&1 | tail -3 && cargo test -p boosapi --lib routes::workflow_ui 2>&1 | grep "test result"`
Expected: `Finished`;测试数 == 基线。若编译报「未使用的 use」「私有」「未解析」,按提示补 use / 调可见性(纯机械修),不改逻辑。
- [ ] **Step 6: Commit**
```bash
cd /root/metapi && git add src/routes/workflow_ui/mod.rs src/routes/workflow_ui/auth.rs
git commit -m "refactor(workflow_ui): 抽出 auth 子模块
Co-Authored-By: Claude <noreply@anthropic.com>"
```
<!-- T2 -->
## 通用抽取流程(每个子模块任务都按这 6 步)
每个抽取任务对一组函数执行:
1. mod.rs 顶部加 `mod <name>;` 声明。
2. grep 定位本组函数精确范围;凡被本组函数引用、但定义留在别处的类型/函数,把那些定义改 `pub(super)`。
3. 新建 `<name>.rs`,粘入本组函数(**函数体一字不改**),顶部按实际依赖补 `use`(从 mod.rs 现有 use 照抄需要的;跨模块的用 `use super::...` 或 `use super::<other_mod>::...`),函数可见性改 `pub(super)`。
4. 从 mod.rs 删掉这些函数原定义;mod.rs 顶部加 `use <name>::{...};` 把它们引回(调用点写法不变)。
5. `cargo build -j 2` + `cargo test -p boosapi --lib routes::workflow_ui`。编译报错按提示机械修(补 use / 调可见性),不改逻辑。测试数不得低于基线。
6. 提交:`git add src/routes/workflow_ui/mod.rs src/routes/workflow_ui/<name>.rs && git commit -m "refactor(workflow_ui): 抽出 <name> 子模块"`(带 Co-Authored-By)。
> 注:若某函数同时被多个子模块用,保留在 mod.rs 顶层并 `pub(super)`,各子模块 `use super::该函数`。
> 共用小工具(guess_mime_from_path / parse_boolish / safe_view_path / user_home / default_history_limit
> / workspace_kind_from_mime)统一留 mod.rs 顶层 `pub(super)`,不下沉到子模块。
## Task 2: 抽 node_defs.rs(节点定义 + 工作流模板图)
**Files:** Create `src/routes/workflow_ui/node_defs.rs`;Modify `src/routes/workflow_ui/mod.rs`
要搬的函数(grep 定位):`known_output_ports`、`core_node_definitions`、`workflow_template_payload`、`core_workflow_template_index`、`inject_boosapi_workflow_template_payload`、`default_boosapi_workflow_graph`、`text_to_video_workflow_graph`、`port_name`、`source_node_type`、`normalize_prompt_payload`、`prompt_link`、`node_type_def_to_comfy`、`input_spec_to_comfy`、`output_specs`、`output_is_list_specs`。
- [ ] **Step 1-6: 按「通用抽取流程」执行**,`<name>` = `node_defs`。
注意:这些函数用到 `WorkflowGraph` / `NodeTypeDefinition` 类型——确认它们的定义位置(可能在 crate::workflow 或 mod.rs),mod.rs 内的留存定义改 `pub(super)`,node_defs.rs 用 `use super::...` 或 `use crate::...` 引入。
验证命令:`cd /root/metapi && cargo build -j 2 2>&1 | tail -3 && cargo test -p boosapi --lib routes::workflow_ui 2>&1 | grep "test result"`,期望 Finished + 测试数≥基线。
提交 message:`refactor(workflow_ui): 抽出 node_defs 子模块`。
<!-- T3 -->
## Task 3: 抽 models.rs(模型分类 + folder 模型)
**Files:** Create `src/routes/workflow_ui/models.rs`;Modify `src/routes/workflow_ui/mod.rs`
要搬的函数:`is_exact_workflow_model`、`is_image_workflow_model`、`is_video_workflow_model`、`is_audio_workflow_model`、`is_embedding_workflow_model`、`is_3d_workflow_model`、`is_vision_workflow_model`、`is_chat_workflow_model`、`workflow_route_models`、`image_model_choices`、`workflow_folder_models`、`workflow_folder_is_api_only`、`workflow_folder_has_route_models`、`workflow_folder_route_model_items`、`combo_choices_from_node_input`、`combo_fields_from_node`、`native_folder_models_from_object_info`。
- [ ] **Step 1-6: 按「通用抽取流程」执行**,`<name>` = `models`。
注意:`workflow_route_models` 是 `async fn` 且用 `state.db`,补 `use crate::AppState;` 等。
验证命令同上,提交 message:`refactor(workflow_ui): 抽出 models 子模块`。
<!-- T4 -->
## Task 4: 抽 assets.rs(UI 静态资源服务)
**Files:** Create `src/routes/workflow_ui/assets.rs`;Modify `src/routes/workflow_ui/mod.rs`
要搬的函数:`workflow_ui_root_for_config`、`resolve_workflow_ui_dir`、`embedded_workflow_ui_for_config`、`workflow_ui_dir_is_usable`、`embedded_workflow_ui_is_usable`、`workflow_ui_index_is_placeholder`、`workflow_ui_runtime`、`workflow_ui_build_metadata`、`workflow_cloud_api_key`、`workflow_ui_index`、`workflow_ui_static`、`official_workflow_template_asset`、`serve_file`。
- [ ] **Step 1-6: 按「通用抽取流程」执行**,`<name>` = `assets`。
注意:用到 `include_dir::Dir`、`PathBuf`、`Html`、`Response` 等,按实际补 use。`serve_file` 若被 queue/view 模块也用到,则保留 mod.rs 顶层 `pub(super)`(实现时看引用)。
验证命令同上,提交 message:`refactor(workflow_ui): 抽出 assets 子模块`。
<!-- T5 -->
## Task 5: 抽 comfy_proxy.rs(ComfyUI API 代理 handler)
**Files:** Create `src/routes/workflow_ui/comfy_proxy.rs`;Modify `src/routes/workflow_ui/mod.rs`
要搬的函数:`get_user_config`、`create_user`、`get_settings`、`get_setting`、`store_settings`、`store_setting`、`userdata_list`、`userdata_get`、`userdata_store`、`userdata_delete`、`move_userdata`、`extensions`、`workflow_templates`、`embeddings`、`object_info`、`system_stats`。
- [ ] **Step 1-6: 按「通用抽取流程」执行**,`<name>` = `comfy_proxy`。
注意:这些是路由 handler(多 `async fn ...(State, HeaderMap) -> AppResult<...>`),依赖 `auth_caller`(已在 auth.rs)→ 用 `use super::auth_caller;` 或 `super::auth::auth_caller`。补 axum extract / Json / Response use。
验证命令同上,提交 message:`refactor(workflow_ui): 抽出 comfy_proxy 子模块`。
<!-- T6 -->
## Task 6: 抽 validate.rs(工作流校验)
**Files:** Create `src/routes/workflow_ui/validate.rs`;Modify `src/routes/workflow_ui/mod.rs`
要搬的函数:`validate_workflow`、`validate_workflow_against_object_info`、`validate_workflow_input_file`。
- [ ] **Step 1-6: 按「通用抽取流程」执行**,`<name>` = `validate`。
注意:依赖 node_defs/models 的函数(如 normalize_prompt_payload、combo_fields_from_node)→ 用 `use super::node_defs::...` / `use super::models::...`(确保那些函数已 `pub(super)`)。WorkflowValidateQuery struct 留 mod.rs `pub(super)`。
验证命令同上,提交 message:`refactor(workflow_ui): 抽出 validate 子模块`。
<!-- T7 -->
## Task 7: 抽 queue.rs(队列/历史/prompt/view)+ 收尾
**Files:** Create `src/routes/workflow_ui/queue.rs`;Modify `src/routes/workflow_ui/mod.rs`
要搬的函数:`queue_status`、`queue`、`queue_mutate`、`history`、`history_mutate`、`history_by_id`、`queue_prompt`、`repair_native_prompt_payload`、`queue_boosapi_prompt`、`interrupt`、`view`、`internal_logs`、`internal_logs_raw`。
- [ ] **Step 1-6: 按「通用抽取流程」执行**,`<name>` = `queue`。
注意:`repair_native_prompt_payload` 很长(2814-3474),依赖 node_defs/models 多个函数;`view` 用 serve_file/safe_view_path。补 `use super::...`。PromptPayload/HistoryQuery/ViewQuery/QueueMutation/UserDataQuery/UploadQuery struct 留 mod.rs `pub(super)`(被多模块用)。
验证命令同上,提交 message:`refactor(workflow_ui): 抽出 queue 子模块`。
- [ ] **Step 7: 最终验收**
Run:
```bash
cd /root/metapi
cargo build -j 2 2>&1 | tail -3
cargo test -p boosapi --lib routes::workflow_ui 2>&1 | grep "test result"
for f in mod auth node_defs models assets comfy_proxy validate queue; do echo -n "$f.rs: "; wc -l < src/routes/workflow_ui/$f.rs; done
```
Expected: Finished;测试数≥基线;每个子文件行数显著小于原 6181(mod.rs 应只剩 routes()+共享类型+小工具,目标 <1500 行;无单文件超 ~2000)。
- [ ] **Step 8: 冒烟(手动)**
部署后打开工作流 UI、跑一个 prompt,确认行为与拆分前一致(路由路径、handler 行为不变)。
<!-- END -->
docs/superpowers/specs/2026-06-17-comfy-cloud-adapter-design.md
+145
View File
@@ -0,0 +1,145 @@
# Comfy Cloud 工作流执行适配器 — 设计
日期:2026-06-17
分支:`feat/comfy-cloud-adapter`
状态:已通过 brainstorming,待落实现计划
## 背景
数字人/图片工作流走 `selfhost` 生成视频时报 `Submit workflow failed: [401] AuthenticationRequired`。
根因经多层验证已锁定:
- Pixelle 的 comfykit 0.1.12 `HttpExecutor` 说的是 **ComfyUI 原生协议**:
`POST {base_url}/prompt`、`GET {base_url}/history/{id}`、鉴权用 `Authorization: Bearer`。
- 配置里 `comfyui_url = https://cloud.comfy.org`,但 **Comfy Cloud 的 API 契约完全不同**
(官方文档 https://docs.comfy.org/development/cloud/overview):
- 鉴权:`X-API-Key` 头(非 Bearer)。
- 提交:`POST /api/prompt`(带 `/api/` 前缀)。
- 轮询:`GET /api/job/{prompt_id}/status` → 状态 pending/in_progress/completed/failed/cancelled。
- 详情/产出:`GET /api/jobs/{prompt_id}`(产出按 node_id 聚合 images/video/audio)。
- 下载:`GET /api/view?filename=&subfolder=&type=output`(302 跳带签名 URL)。
- 接受标准 ComfyUI API-format 工作流。
- 已用官方方式验证 Comfy Cloud key 有效:`GET /api/user` 返回 200 `{"status":"active"}`。
所以这不是 key 失效,而是 comfykit 与 Comfy Cloud 协议不兼容(路径前缀 + 鉴权头 + 轮询端点三处全不同)。
## 目标
在 **BoosAPI** 里实现一个 **ComfyUI 原生协议 ↔ Comfy Cloud API 翻译适配器**:对外暴露
ComfyUI 原生端点(`/prompt`、`/history/{id}`、`/view`),内部翻译成 Comfy Cloud 的
`/api/*` 契约 + `X-API-Key` 鉴权。Pixelle/comfykit **一行代码都不改**,只把 `comfyui_url`
指向 BoosAPI 的适配端点即可。
Comfy Cloud 的 base URL + API Key 通过**站点管理**录入(新增 `comfy_cloud` 平台类型),
适配器从站点配置读取,而非散落的环境变量/配置文件。
## 已确认的关键决策
1. 采用 **Approach A**:站点管理只作「配置载体 + 前端入口」(存 base_url + X-API-Key),
执行逻辑由独立的 Comfy Cloud 适配器承担;**不**把 Comfy Cloud 塞进 `/v1/*` token 路由
(它是工作流执行 API,不是聊天协议,塞进 token-router 跑不通)。
2. 适配器对外说 ComfyUI 原生协议,Pixelle/comfykit 零改动,只改 `comfyui_url` 配置。
3. 鉴权翻译:入口端点不强制校验(本机互信)/出口注入 `X-API-Key`。
4. 分支 `feat/comfy-cloud-adapter`,与 NIT 工作无关,不混入。
## 非目标
- 不改 Pixelle / comfykit 源码。
- 不做 WebSocket 实时进度(comfykit HTTP 模式只轮询 `/history/{id}`,够用)。
- 不把 Comfy Cloud 接入 LLM token 路由/failover。
- 不做 Comfy Cloud 的计费集成(已有 `fetch_comfy_cloud_balance` 另说)。
## 架构
```
Pixelle(comfykit 0.1.12, 不改)
comfyui_url = http://<boosapi-host>/comfy-cloud
说 ComfyUI 原生协议: POST /prompt · GET /history/{id} · GET /view · Bearer(忽略)
│
▼
BoosAPI 适配端点(新增 src/routes/comfy_cloud_adapter.rs)
· POST /comfy-cloud/prompt → 翻译 → POST cloud.comfy.org/api/prompt
· GET /comfy-cloud/history/{id} → 翻译 → GET /api/job/{id}/status (+ /api/jobs/{id})
拼回 ComfyUI history 格式
· GET /comfy-cloud/view → 翻译 → GET /api/view (跟随 302)
鉴权: 出口注入 X-API-Key(从站点配置读)
│
▼
Comfy Cloud (https://cloud.comfy.org/api/*)
```
## 站点管理集成(配置载体)
- 前端 `SITE_PLATFORM_OPTIONS`(`src/web/pages/Sites.tsx`)新增一项
`{ value: 'comfy_cloud', label: 'Comfy Cloud', description: '工作流执行 API' }`。
- 站点记录复用现有字段:`url` 存 `https://cloud.comfy.org`,API Key 存入现有的
站点凭证字段(沿用站点已有的 key/header 存储方式;实现时确认 sites 表里承载 key 的列)。
- 适配器通过一个 helper `resolve_comfy_cloud_site(state) -> (base_url, api_key)`:
查 `platform = 'comfy_cloud'` 且 enabled 的站点,取其 url + key。无配置 → 明确报错。
## 适配端点详细行为
### POST /comfy-cloud/prompt
- 入参:ComfyUI 原生 body `{ "prompt": {...}, "client_id": "..." }`。
- 出口:`POST {base_url}/api/prompt`,头 `X-API-Key: {key}` + `Content-Type: application/json`,
body 原样转发(Comfy Cloud 接受相同的 `{prompt: ...}` 包裹)。
- 回包:Comfy Cloud 返回 `{ "prompt_id": "..." }`,原样回给 comfykit(字段名一致,无需改)。
### GET /comfy-cloud/history/{prompt_id}
comfykit 轮询此端点,期待 ComfyUI history 格式:
`{ "{prompt_id}": { "status": {...}, "outputs": { "{node_id}": { "images": [...] } } } }`。
适配器:
1. `GET {base_url}/api/job/{prompt_id}/status` 拿 `{ "status": "completed|in_progress|..." }`。
2. 若未完成(pending/in_progress)→ 回 `{}`(comfykit 据此继续轮询)。
3. 若 completed → `GET {base_url}/api/jobs/{prompt_id}` 拿产出,翻译成 ComfyUI history 形状:
```json
{ "{prompt_id}": {
"status": { "completed": true, "status_str": "success" },
"outputs": { /* node_id → {images|video|audio: [{filename,subfolder,type}]} */ }
} }
```
4. 若 failed/cancelled → 回带 `status_str: "error"` 的 history,让 comfykit 终止轮询并报错。
### GET /comfy-cloud/view
- 透传 query(`filename`/`subfolder`/`type`)→ `GET {base_url}/api/view?...`,头注入 X-API-Key。
- Comfy Cloud 回 302 签名 URL → 适配器跟随重定向取字节流回传(reqwest 默认跟随,
或手动取 Location 再 GET),Content-Type 透传。
## 数据流(comfykit 视角,全程无感)
1. comfykit `POST {comfyui_url}/prompt` → 适配器 → Comfy Cloud → 返回 prompt_id。
2. comfykit 轮询 `GET {comfyui_url}/history/{id}` → 适配器翻译 job 状态 → 未完成回 `{}`,
完成回 ComfyUI history。
3. comfykit 从 outputs 取 filename → `GET {comfyui_url}/view?filename=...` → 适配器取回字节。
## 错误处理
- 站点未配置 `comfy_cloud` → 适配端点返回 503 + 中文提示「未配置 Comfy Cloud 站点」。
- Comfy Cloud 返回非 2xx → 适配器透传状态码 + 上游错误体(便于排查,不吞错)。
- job failed/cancelled → 在 history 里标 error,comfykit 会抛 `Submit workflow failed` 类错误
(但这次是真实的执行失败,不是鉴权问题)。
## 路由挂载
`src/routes/mod.rs` 的 `build_router` 加 `.merge(comfy_cloud_adapter::routes())`。
端点前缀 `/comfy-cloud/*`,不需要 admin/user 鉴权(本机内 Pixelle → BoosAPI 互信;
如需收紧可后续加内部 token,本期不做)。
## 测试策略(TDD)
- 单测翻译函数:Comfy Cloud `job status + jobs detail` JSON → ComfyUI history JSON 的纯函数
(`comfy_cloud_job_to_history`),覆盖 completed / in_progress / failed 三种。
- 单测 `resolve_comfy_cloud_site`:有配置返回 (url,key);无配置报错。
- 用 wiremock 起一个假 Comfy Cloud,集成测 `POST /comfy-cloud/prompt` 透传 + X-API-Key 注入、
`GET /comfy-cloud/history/{id}` 轮询翻译(沿用项目现有 wiremock 测试范式)。
## 验证
- `cargo build -j 2`、`cargo test -p boosapi --lib comfy_cloud`。
- 真实联调:把 Pixelle `comfyui_url` 指向 `http://<boosapi>/comfy-cloud`,跑一次 selfhost 视频,
确认不再 401 且能取回产出。
## 提交约定
分支 `feat/comfy-cloud-adapter`,提交按逻辑拆分(站点平台类型 / 适配器 service + 端点 /
路由挂载 / 前端平台选项),沿用项目中文 commit 风格。
docs/superpowers/specs/2026-06-18-digital-human-comfy-video-entry-design.md
+93
View File
@@ -0,0 +1,93 @@
# 数字人接入 Comfy Cloud 视频工作流(完整视频入口)设计
日期:2026-06-18
分支:`feat/comfy-cloud-adapter`
状态:已通过调查,待用户复审
## 背景
LTX2.3 说话头像工作流(`comfy/video_digital_ltx2.json`)已就绪并通过 Comfy Cloud 校验
(节点+模型全兼容,probe `node_errors:{}`)。但 BoosAPI 数字人 UI 没有「视频/动画工作流」
入口,无法触发「肖像图 + 旁白音频 → 说话视频」这一步。本设计补齐贯穿三层的入口。
## 现状(调查结论)
- **BoosAPI 数字人前端 `src/web/pages/DigitalHuman.tsx`**:仅 3 个选择器——ttsWorkflow、
imageWorkflow(从 mediaWorkflows 选,默认含 "image" 的)、frameTemplate(HTML 模板)。
**无视频/动画工作流选择器**。流程是「生成图片 + TTS + HTML 模板合成」,不做说话头像动画。
- **BoosAPI 后端 `src/routes/digital_human.rs`** 的 `pixelle_request_body`(~line 2053):转发
text/mode/title/backend_provider/workflow_source/n_scenes/video_fps/frame_template/
template_params/prompt_prefix/bgm_*/media_workflow/tts_workflow/ref_audio。
**不转发 `api_video_workflow`**;`workflow_source` 写死 `runninghub`/`selfhost`(无 comfy)。
- **Pixelle `pixelle_video/pipelines/asset_based.py`**(~line 693):动画步读
`context.request.get("api_video_workflow")`;`audio_path` 仅当 `_get_api_workflow_info`
(查 `api_media`,只 `api/` 通道)匹配到 `audio_driven_i2v` 能力时才注入 → **comfy 工作流
拿不到 audio_path**。
- **Pixelle 工作流执行按前缀路由**:`runninghub` 走 RunningHub,其余(含 `comfy/`)走
`comfyui_url`(= BoosAPI `/comfy-cloud` 适配器)。`comfy/video_digital_ltx2.json` 已在
`/workflows/media` 列出(已加 `video_` 前缀)。
- 已完成的前置:comfy-cloud 适配器(已验证)、`comfy/video_digital_ltx2.json`(标记
image_path/audio_path/prompt,probe 通过)、media.py 转发 image_path(已打补丁)。
## 已确认决策
1. 加完整视频入口:前端选择器 + 后端转发 + Pixelle 音频注入,三层都改。
2. 视频工作流选择器列 `video_*` media 工作流(含 `comfy/video_digital_ltx2.json`)。
3. 单人肖像说话头像;不做多人。
## 三层改动设计
### 层 1:前端 `src/web/pages/DigitalHuman.tsx`
- 新增 state `apiVideoWorkflow`(默认空=不启用动画,保持现有「图片+HTML」行为向后兼容)。
- 新增「视频工作流(可选)」`<select>`:选项 = `mediaWorkflows.filter(name 含 "video")`,
含空选项「不生成视频(仅图片合成)」。
- 提交 payload 增加 `apiVideoWorkflow` 字段;draft 持久化同步。
### 层 2:BoosAPI 后端 `src/routes/digital_human.rs`
- `pixelle_request_body` 增加:
```rust
if let Some(value) = optional_string(body, &["apiVideoWorkflow", "api_video_workflow"]) {
request_body["api_video_workflow"] = json!(value);
}
```
- 若所选视频工作流以 `comfy/` 开头,确保 `workflow_source` 不会阻断(comfy 工作流靠前缀
路由,workflow_source 主要影响 media/tts 默认通道;api_video_workflow 独立按前缀执行,
无需改 workflow_source。实现时验证不冲突)。
- 可选转发 `api_video_params`(若前端给了音频驱动等参数)。本期最小化:只转发 api_video_workflow。
### 层 3:Pixelle `pixelle_video/pipelines/asset_based.py`
- 动画步注入 `audio_path` 的条件放宽:除 `api_media` 能力匹配外,**当 `api_video_workflow`
以 `comfy/` 开头时,也注入 `audio_path = frame.audio_path`**(comfy 工作流的 `$~audio_path!`
标记需要它)。最小改动:在 `audio_driven_i2v` 判断旁边加 comfy 前缀分支。
- 镜像内置文件,改后重启容器,备份到 `/opt/Pixelle-Video/patches/`。
## 数据流(目标)
```
DigitalHuman.tsx: 选 comfy/video_digital_ltx2.json (apiVideoWorkflow)
→ BoosAPI digital_human.rs: request_body.api_video_workflow
→ Pixelle /api/video/generate/async: context.request.api_video_workflow
→ asset_based.py 动画步: 注入 image_path(media.py已补)+ audio_path(本期补)+ prompt
→ media() comfy 前缀 → comfyui_url=/comfy-cloud 适配器 → Comfy Cloud LTX2.3
→ 说话视频 → 帧合成/HTML 模板 → 成片
```
## 验证
- 前端 typecheck:`npm run typecheck:web`。
- 后端构建:`cargo build -j 2`。
- Pixelle 改动:语法校验 + 重启 healthy。
- 端到端:数字人任务选 `comfy/video_digital_ltx2.json`,确认 Comfy Cloud 出现 job、
注入了 image_path+audio_path、出说话视频。
## 非目标
- 不改 comfy-cloud 适配器(已完成)。
- 不做多人对话数字人。
- 不重构数字人现有「图片+HTML 合成」路径(视频入口为可选叠加,默认不启用,向后兼容)。
- 不动 RunningHub 数字人路径。
## 提交约定
分支 `feat/comfy-cloud-adapter`。前端、BoosAPI 后端分别提交(项目内,受版本控制);
Pixelle 改动在容器内 + 备份 patches/(非本仓库)。中文 commit。
docs/superpowers/specs/2026-06-18-digital-human-llm-model-select-design.md
+71
View File
@@ -0,0 +1,71 @@
# 数字人脚本 LLM 模型可选 设计
日期:2026-06-18
分支:`feat/comfy-cloud-adapter`
状态:已通过 brainstorming,待用户复审
## 背景
数字人脚本生成的 LLM 模型现在写死在 Pixelle config(`llm.model = gpt-5.5`),用户无法在
数字人页面选用别的模型。本功能加一个「脚本模型(可选)」下拉,让用户自选生成脚本的 LLM。
生图模型已可通过现有「图片工作流」下拉选择,不在本范围。
## 已确认决策
1. 只做脚本 LLM 模型可选;生图模型已由「图片工作流」下拉覆盖,不动。
2. 下拉只列文本/对话模型(过滤掉生图/视频模型,避免选错导致生成失败)。
3. 默认空 = 用 Pixelle config 的默认模型(`deepseek-v4-flash`),向后兼容。实现时把 Pixelle
`config.yaml` 的 `llm.model` 设为 `deepseek-v4-flash`。
4. 三层改动(前端选择器 + 后端转发 + Pixelle 传 model)。
## 集成点(调查结论)
- Pixelle `llm_service.py`:`llm(prompt=, model=...)` **已支持按调用传 model 覆盖**
(优先级:参数 > config)。
- Pixelle `asset_based.py` 脚本生成调用 `self.core.llm(prompt=, response_type=VideoScript, ...)`
**当前未传 model** → 需补 `model=context.request.get("llm_model")`。
- BoosAPI `digital_human.rs` `pixelle_request_body` 转发字段(媒体/tts 工作流等),
**未转发 llm_model** → 需补。
- 前端模型列表:`api.getModelsMarketplace()`(`/api/models/marketplace`)已有,可作下拉数据源。
- `/v1/models` 需鉴权(401 直取不行),故用 marketplace 接口。
## 三层改动设计
### 层1 前端 `src/web/pages/DigitalHuman.tsx`
- 加 state `llmModel`(默认空)+ draft 持久化。
- 加载时调 `api.getModelsMarketplace()` 取模型,过滤掉生图/视频模型(名称含
image/video/dall/flux/sd/wan/seedance/kling/banana 等,或按 marketplace 项的类型字段),
得文本模型列表 state `llmModels`。
- 加「脚本模型(可选)」`<select>`:空选项「默认(deepseek-v4-flash)」+ 文本模型选项。
- 提交 payload 加 `llm_model: llmModel || undefined`。
### 层2 后端 `src/routes/digital_human.rs`
- `pixelle_request_body` 加(照搬 tts_workflow 转发模式):
```rust
if let Some(value) = optional_string(body, &["llmModel", "llm_model"]) {
request_body["llm_model"] = json!(value);
}
```
### 层3 Pixelle `pixelle_video/pipelines/asset_based.py`
- 脚本生成调用前取 `llm_model = context.request.get("llm_model")`,非空则传入:
`self.core.llm(prompt=prompt, response_type=VideoScript, temperature=0.8, max_tokens=4000, model=llm_model)`。
(llm() 已接受 model 参数;None 时走 config 默认。)
- 容器内改 + 备份到 `/opt/Pixelle-Video/patches/`。
## 验证
- 前端 `npm run typecheck:web` 干净。
- 后端 `cargo build -j 2` 通过。
- Pixelle 语法校验 + 重启 healthy。
- 端到端:数字人任务选非默认脚本模型,Pixelle 日志出现 `LLM call: model=<所选模型>`。
## 非目标
- 不改生图模型选择(已由图片工作流下拉覆盖)。
- 不做参考图上传(功能 B,留后续)。
- 不动 comfy-cloud 适配器、LTX2.3 工作流。
## 提交约定
分支 `feat/comfy-cloud-adapter`。前端、后端分别提交;Pixelle 容器内改 + 备份(非本仓库)。中文 commit。
docs/superpowers/specs/2026-06-18-ltx2-digital-human-workflow-design.md
+93
View File
@@ -0,0 +1,93 @@
# LTX2.3 数字人工作流(Comfy Cloud)设计
日期:2026-06-18
分支:`feat/comfy-cloud-adapter`
状态:已通过 brainstorming,待落实现计划
## 背景
Pixelle 数字人(说话头像)能力原先只有 RunningHub 形态(`runninghub/digital_*.json` 是
`{"source":"runninghub","workflow_id":"..."}` 指针,非 ComfyUI 节点图,无法在 Comfy Cloud 跑)。
为让数字人走 Comfy Cloud,采用官方 ComfyUI 模板 `video_ltx2_3_id_lora`(LTX2.3 身份保持
LoRA + 音频驱动),把它做成 Pixelle 的 `comfy/` 工作流,经已建好的 comfy-cloud 适配器执行。
可行性已验证(查 Comfy Cloud `/object_info` 3548 节点 + 模型池):
- 模型齐全:`ltx-2.3-22b-dev-fp8`、`ltx-2.3-id-lora-talkvid-3k`、`gemma_3_12B_it_fp4_mixed`、
distilled LoRA 均托管;另有 `ltx-2.3-22b-ic-lora-lipdub-0.9` 口型 LoRA。
- 节点齐全:LTX2.3 音视频节点(LTXVReferenceAudio/LTXVConcatAVLatent/LTXVAudioVAEDecode 等)
全在 Comfy Cloud 节点集中。
- 模板 I/O = LoadImage(肖像)+ LoadAudio(旁白)+ 文本 → SaveVideo(带音频说话视频),
正好匹配数字人。
## 已确认决策
1. 用官方模板 `video_ltx2_3_id_lora`(LTX2.3),不自拼 InfiniteTalk(官方模板天然 Comfy-Cloud
兼容、模型已托管、风险低)。
2. 接入方式:comfy 通道 + 节点图注入(放 `comfy/digital_ltx2.json`,经适配器),不走 RunningHub、
不另做独立入口。
3. comfykit 注入机制:节点 `_meta.title` 标记(`$~image!` / `$~audio!` / `$prompt!`)。
4. 分支 `feat/comfy-cloud-adapter`(与 comfy-cloud 适配器同分支,属同一能力线)。
## 前置依赖(硬依赖)
**需要用户从 Comfy Cloud 导出 API 格式 JSON**:模板当前是 UI 格式(含 subgraph 子图),
`/api/prompt` 要求 API 格式(`{node_id:{class_type,inputs,_meta}}`)。子图必须展开。
用户操作:Comfy Cloud 网页打开模板/share → Workflow → Export (API Format) → 放服务器
(如 `/tmp/ltx2_api.json`)。服务端无法代取(需登录态)。
## Pixelle media.py 改动(writing-plans 阶段发现的必需项)
现状:`pixelle_video/services/media.py` 的 `__call__` 只把 `image_path` 转发给 `api/` 通道
(`api_media`),**comfy/ 通道的 workflow_params 不含 image_path**。`audio_path` 经 `**params`
能进 workflow_params,但肖像图进不去。所以 comfy/ 工作流收不到肖像图。
改动:在 `media.py` 的非 api/ 分支(构建 `workflow_params` 处),把 `image_path` 也加入
`workflow_params`(命名 `image_path`),使其能被 `$~image_path!` 标记注入。一行级小改,
但属 Pixelle 源码(非 BoosAPI 仓库),改在容器内 `/app/pixelle_video/services/media.py`,
并同步到宿主持久化(确认 media.py 是否在挂载卷;若在镜像内则需固化方案)。
## 架构
```
Pixelle 数字人流程
生成肖像图(image_path)+ TTS 旁白(audio_path)+ 脚本文本
│ comfykit 按 _meta.title 标记注入到 LoadImage/LoadAudio/文本节点
▼
comfy/digital_ltx2.json (API 格式 + 标记)
│ comfyui_url = http://<boosapi>/comfy-cloud
▼
Comfy Cloud /api/prompt → LTX2.3(id-lora-talkvid + 可选 lipdub)→ 带音频说话视频
▼
SaveVideo 产出 → 适配器 /view 取回 → Pixelle HTML 模板合成
```
## 工作流改造(实现步骤)
基于用户导出的 API-format JSON:
1. `LoadImage` 节点 → `_meta.title = "$~image_path!"`(必填、媒体上传;键名对齐 media.py 转发的 image_path)
2. `LoadAudio` 节点 → `_meta.title = "$~audio_path!"`(键名对齐 api_video_params 注入的 audio_path)
3. 文本提示节点(PrimitiveStringMultiline / CLIPTextEncode)→ `_meta.title = "$prompt!"`(对齐 media.py 的 prompt)
4. `SaveVideo` 已知输出节点,自动识别,不标记
5. 删除 `RecordAudio` 节点(UI 录音交互,服务端不需要)
6. 成品写 `data/workflows/comfy/digital_ltx2.json`(宿主持久化,经 `./data` 挂载)
7. 键名以 media.py 实际放入 workflow_params 的为准(image_path/audio_path/prompt),已在 writing-plans 阶段确认。
## 验证
- 校验探测:`POST /comfy-cloud/prompt`(body 为改造后 `{prompt:节点图}`)→ 期望
`node_errors:{}` + 返回 prompt_id(不跑完整数字人流程,先验证节点+模型全兼容)。
- 真实验证:Pixelle 数字人任务选 `comfy/digital_ltx2.json`,出片确认。
- 错误处理沿用适配器:节点不支持→400 透传;模型缺失→校验错误透传;执行失败→job failed。
## 非目标
- 不改 comfy-cloud 适配器代码(已完成且验证)。
- 不做多人对话(multi-speaker)数字人,先单人肖像。
- 不在 Comfy Cloud 上自训/上传新模型,只用已托管模型。
- 不做 RunningHub 数字人的迁移/替换(保留并存)。
## 提交约定
分支 `feat/comfy-cloud-adapter`,工作流文件 + 任何 Pixelle 侧配置分开提交,中文 commit。
注:工作流文件落在 Pixelle 宿主目录(`/opt/Pixelle-Video/data/workflows/comfy/`),不在
BoosAPI 仓库内;若需纳入版本管理另议。
docs/superpowers/specs/2026-06-18-pixelle-connection-management-design.md
+90
View File
@@ -0,0 +1,90 @@
# Pixelle 连接凭证纳入 BoosAPI 管理 设计
日期:2026-06-18
分支:`feat/comfy-cloud-adapter`
状态:已通过 brainstorming,待用户复审
## 背景
Pixelle 的连接凭证(RunningHub API key、Comfy Cloud url/key)现在只能手动编辑
`/opt/Pixelle-Video/config.yaml` 再重启容器,很麻烦。本功能把这 3 个凭证纳入 BoosAPI
管理控制台,在 UI 里改、一键写入 Pixelle config 并重启生效。
## 已确认决策
1. 范围:只管 Pixelle 的 3 个连接凭证 —— `runninghub_api_key`、`comfyui_url`、`comfyui_api_key`。
不做整份 config.yaml 编辑,不做通用外部连接管理。
2. 同步机制:写文件 + 重启容器(BoosAPI 直接改 bind-mount 的 config.yaml,再 restart pixelle 容器)。
不给 Pixelle 加 HTTP 配置端点(避免改 Pixelle 源码)。
3. 真相源:BoosAPI settings 表;config.yaml 是被同步的目标。
4. 放置:连接管理页(`/accounts`,`src/web/pages/Accounts.tsx`)作为一个卡片/分区。
## 集成点(调查结论)
- Pixelle 无配置更新 HTTP 端点;`config.yaml` 是 bind-mount(`/opt/Pixelle-Video/config.yaml`),
BoosAPI 跑在宿主,有读写权限。
- 凭证在 config.yaml 的 `comfyui:` 段:`runninghub_api_key` / `comfyui_url` / `comfyui_api_key`。
- 改后 Pixelle 需重启容器生效(`cd /opt/Pixelle-Video && docker compose restart api`)。
- BoosAPI 有 settings 表(key-value)+ builtin_key 掩码范式可复用。
## 架构
```
连接管理页「Pixelle 连接」卡片(3 输入框 + 保存)
→ PUT /api/admin/pixelle/connection
1. 写 settings 表(pixelle.runninghub_api_key 等)
2. 备份 config.yaml → config.yaml.bak-<ts>
3. YAML 改 comfyui.{runninghub_api_key,comfyui_url,comfyui_api_key} 三键(其余保留)
4. docker compose restart api(cwd=/opt/Pixelle-Video)
→ GET /api/admin/pixelle/connection 返回当前值(密钥掩码)
```
## 三层改动设计
### 层1 后端 service `src/services/pixelle_connection.rs`(新建)
- `struct PixelleConnection { runninghub_api_key, comfyui_url, comfyui_api_key }`(均 Option<String>)。
- `read_connection(db) -> PixelleConnection`:从 settings 表读 `pixelle.*` 三键。
- `save_connection(db, conn)`:三键写 settings 表(UPSERT)。
- `sync_to_pixelle(config_path) -> AppResult<()>`:读 yaml → 改 comfyui 三键 → 备份 → 写回。
用 `serde_yaml`(确认 Cargo.toml 有;无则加)。只改这三键,其余键原样保留(读成
`serde_yaml::Value` 再定点改,不整体重序列化丢注释——注意:serde_yaml 会丢注释,
接受此代价,或保留备份)。
- `restart_pixelle(compose_dir) -> AppResult<()>`:`docker compose restart api`,cwd=compose_dir。
- 配置项:Pixelle config 路径 + compose 目录,默认 `/opt/Pixelle-Video/config.yaml`、
`/opt/Pixelle-Video`,从 BoosAPI config(新增 `[pixelle_video] config_path` / 复用现有)读。
### 层2 后端路由 `src/routes/admin/pixelle_connection.rs`(新建)+ 挂载
- `GET /api/admin/pixelle/connection`:返回三值,api_key 掩码(`••••<last4>`)。
- `PUT /api/admin/pixelle/connection`:收三字段 → save_connection → sync_to_pixelle → restart。
掩码值(`••••`)表示「不改」,跳过该字段。
- 挂到 admin router(走现有 require_admin 中间件)。
### 层3 前端 `src/web/pages/Accounts.tsx` + `api.ts`
- `api.ts` adminApi 加 `getPixelleConnection()` / `savePixelleConnection(data)`。
- Accounts 页加「Pixelle 连接」卡片:3 输入框(runninghub key、comfy url、comfy key)+ 保存。
加载时拉当前值(掩码),保存提示「已保存并重启 Pixelle，约数秒生效」。
## 错误处理
- config.yaml 不存在/无写权限 → 503 + 明确提示,**不重启**。
- docker restart 失败 → 返回错误,提示「配置已写入,但 Pixelle 重启失败,请手动重启」。
- 写文件前必备份;写失败保留原文件。
## 验证
- 后端:rstest 用临时 yaml 测 sync_to_pixelle(读→改3键→保留其余→备份生成);
`cargo build -j 2`。
- 前端:`npm run typecheck:web`。
- docker restart 部分手动验证(端到端:UI 改 runninghub key → 确认 config.yaml 变 + 容器重启)。
## 非目标
- 不做整份 config.yaml 编辑。
- 不做通用「外部服务连接」管理(只 Pixelle)。
- 不给 Pixelle 加源码/端点。
- 不动 comfy-cloud 适配器、数字人工作流。
## 提交约定
分支 `feat/comfy-cloud-adapter`。service / 路由 / 前端 分开提交,中文 commit。
serde_yaml 若需新增依赖,单独说明。
docs/superpowers/specs/2026-06-18-workflow-ui-mod-split2-design.md
+58
View File
@@ -0,0 +1,58 @@
# workflow_ui/mod.rs 续拆(6 子模块)设计
日期:2026-06-18
分支:`feat/comfy-cloud-adapter`
状态:已通过 brainstorming,待用户复审
## 背景
上一轮已把 `workflow_ui.rs`(6181 行)拆成 8 模块,但 `mod.rs` 仍 4095 行——一批
未在上轮清单内的函数(native proxy / repair 链 / bootstrap 注入 / run 转换 / ws / 模型注入)
留在了 mod.rs。本轮继续把这 6 组抽出,让 mod.rs 瘦到 ~1000-1200 行(只剩 routes()
+ 共享 struct + 小工具)。
延续上轮纪律:**纯机械移动,函数体一字不改**,只调可见性 + use,编译器 + 5 测试验证。
## 已确认决策
1. 续拆 workflow_ui/mod.rs 残留。
2. 拆成 6 子模块(见下表)。
3. 纯机械移动,零逻辑改动。
4. 安全:每抽一组即 cargo build -j 2 + 5 测试保持;末尾各文件行数核对。
## 子模块划分
| 子模块 | 函数组 |
|--------|--------|
| `model_inject.rs` | comfy_combo_input, inject_model_choices, is_boosapi_extension_node_type, workflow_node_defs_with_models, inject_boosapi_object_info, builtin_model_folders, inject_boosapi_model_folders, workflow_model_folder_payload, native_model_folder_payload_or_fallback, model_payload_items_from_names, normalize_model_item_name, workflow_model_display_aliases, model_payload_item_with_name, merge_model_payload_items, normalize_model_folder_payload |
| `repair.rs` | inject_native_prompt_cloud_api_key, repair_resize_image_mask_nodes(+_without_workflow), repair_text_generate_ltx2_prompt_nodes, repair_dynamic_combo_nodes(+ dynamic_combo_* 全部 helper), repair_wan2_api_nodes(+ wan2_* / is_wan2_* helper), collect_workflow_nodes, prompt_subgraph_node_id, id_to_prompt_key |
| `native_proxy.rs` | native_workflow_enabled/base/http_path/request/json/json_cached/response/view_response/video_response/file_response/raw_response/api_proxy, archive_native_workflow_asset, repair_native_prompt_body_value, workflow_cache_kind_from_key, workflow_cache_status, upload_image(+_to_local_backend/_to_native_backend), upload_mask, timestamp_ms |
| `run_convert.rs` | workflow_run_to_history/_task/_queue_task/_prompt_tuple, run_status_messages, run_outputs_for_comfy, node_output_for_comfy, comfy_media_items, normalize_comfy_media_item, workflow_text_output, workflow_graph_to_comfy_workflow, workflow_timestamp_ms |
| `ws.rs` | workflow_session_sender, publish_workflow_ws_event, workflow_node_label, workflow_progress_callback_with_run_sender, publish_run_events, workflow_ws, native_workflow_ws_bridge |
| `bootstrap.rs` | inject_bootstrap, workflow_secret_cleanup_bootstrap, inject_external_bootstrap, inject_enhanced_bootstrap |
> 留 mod.rs:routes()、共享 struct(WorkflowCaller/CachedJson/各 Query/Payload)、跨多模块小工具
> (safe_view_path/user_home/guess_mime_from_path/parse_boolish/auth_caller_optional/
> workflow_context/parse_workflow_cookie/build_query_string/simple_urlencode/各 workflow_widget_*
> validation helper 等)、experiment_models/view_metadata/custom_nodes_i18n/internal_* 等零散 handler。
> 实现时按实际依赖判定:被多组共用的留 mod.rs `pub(super)`。
## 安全策略
同上轮:每抽一组 → `cargo build -j 2`(编译器是主安全网,纯移动)→ `cargo test -p boosapi
--lib routes::workflow_ui`(5 测试基线不减)→ 提交。跨模块依赖的私有符号按编译报错逐个
改 `pub(super)`。子模块内部 helper 也 `pub(super)` 或保持模块私有(看是否跨文件用)。
## 测试
编译器逐组验证;5 个现有测试全程保持;末尾核对 8+6 个子文件行数,mod.rs 应 <1500。
## 非目标
- 不改逻辑、不改路由、不动 handler 行为。
- 不拆其他巨文件(oauth/payment/digital_human 各自后续循环)。
- 不顺手优化函数实现。
## 提交约定
分支 `feat/comfy-cloud-adapter`。每抽 1 组 + 编译通过即提交。中文 commit。
docs/superpowers/specs/2026-06-18-workflow-ui-split-design.md
+69
View File
@@ -0,0 +1,69 @@
# workflow_ui.rs 拆分(8 子模块)设计
日期:2026-06-18
分支:`feat/comfy-cloud-adapter`
状态:已通过 brainstorming,待用户复审
## 背景
`src/routes/workflow_ui.rs` 单文件 6181 行,是项目最大文件,难维护/难测/edit 易错。
按职责拆成 `src/routes/workflow_ui/` 模块目录(8 子模块)。纯机械移动、零逻辑改动,
靠 Rust 编译器 + 现有 5 个测试验证。
## 已确认决策
1. 第一个优化目标:拆 workflow_ui.rs(项目最大文件)。
2. 拆成 8 子模块(见下表)。
3. 纯机械移动:函数体一字不改,只调可见性 + use 路径。零逻辑改动。
4. 安全策略:每抽一个子模块即 cargo build -j 2 验证;5 个测试全程保持通过;末尾冒烟。
## 子模块划分
| 子模块 | 职责 | 现有行号(约) |
|--------|------|--------------|
| `mod.rs` | routes() 装配 + 共享类型(WorkflowCaller、Query/Payload structs)+ 子模块声明 | 56-124 |
| `assets.rs` | UI 静态资源服务、嵌入目录解析、index/static/serve_file/官方模板资源 | 211-305, 1533-1814 |
| `auth.rs` | caller 解析(caller_from_headers/auth_caller/caller_user_id/caller_is_admin) | 313-363, 1875 |
| `node_defs.rs` | 节点定义 + 工作流模板(core_node_definitions、*_workflow_graph、node_type_def_to_comfy) | 429-932 |
| `models.rs` | 模型分类 + folder 模型(is_*_workflow_model、workflow_folder_*、native_folder_models) | 939-1530 |
| `comfy_proxy.rs` | ComfyUI API 代理 handler(settings/userdata/object_info/system_stats/extensions 等) | 1883-2200 |
| `validate.rs` | 工作流校验(validate_workflow* 三个) | 2206-2586 |
| `queue.rs` | 队列/历史/prompt(queue/history/queue_prompt/repair_native_prompt_payload/queue_boosapi_prompt/view) | 2586-3679 |
> 注:行号是当前快照,实现时以函数名定位为准(文件会随抽取缩短)。各子模块的辅助小函数
> 随其主要消费者走;跨多模块共用的(如 guess_mime_from_path、parse_boolish、safe_view_path)
> 放 mod.rs 或新建 util.rs(实现时按实际依赖定,优先放 mod.rs 顶部 pub(super))。
## 安全策略(核心)
1. **纯移动**:剪切函数到子模块,函数体一字不改。仅:
- 可见性:跨模块调用的改 `pub(super)` / `pub(crate)`;
- `use`:子模块顶部补齐它用到的依赖路径(crate::、super::、外部 crate)。
2. **逐模块验证**:每抽一个子模块就 `cargo build -j 2`。Rust 编译器对未解析引用/类型不符
直接报错——这是纯移动重构的强安全网。
3. **测试保持**:现有 5 个测试(在文件尾 `#[cfg(test)] mod tests`)迁到相关子模块(多与
models/node_defs 相关),全程保持通过:`cargo test -p boosapi --lib routes::workflow_ui`。
4. **末尾冒烟**:全部完成后,工作流 UI 打开 + 跑一个 prompt,确认行为不变。
## 数据流
不变。`routes/mod.rs` 仍 `.merge(workflow_ui::routes())`,对外接口零变化。仅文件内部
组织从 1 文件变 8 文件,所有路由路径、handler 行为、类型签名完全一致。
## 测试
- 编译器:每步 cargo build -j 2(主验证手段)。
- 单测:迁移后 5 个测试保持通过。
- 冒烟:手动开工作流 UI + 跑 prompt。
- 不新增功能测试(本任务是重构,非加功能;但若迁移中发现某函数明显缺测且易加,可顺手补)。
## 非目标
- 不改任何逻辑、不改路由路径、不改 handler 行为。
- 不拆其他巨文件(oauth.rs/digital_human.rs/user/mod.rs 各自独立后续循环)。
- 不顺手重构/优化函数实现(纯搬运)。
## 提交约定
分支 `feat/comfy-cloud-adapter`。**按子模块分多次提交**(每抽 1-2 个子模块 + 编译通过即提交),
便于回溯;不一锅烩。中文 commit。
migrations/20260622000001_agent_sessions.sql
+28
View File
@@ -0,0 +1,28 @@
-- Agent Workbench sessions: per-session token / cost accounting and metadata.
--
-- One row per agent conversation session. Token counts and cost accumulate
-- across the turns of a session; `updated_at` advances on every `/api/agent/chat`
-- round-trip. `user_id` is nullable so admin (global-token) sessions are allowed
-- without a user row, but every session is still isolated by its own sandbox
-- directory keyed on `id`.
CREATE TABLE IF NOT EXISTS agent_sessions (
id TEXT PRIMARY KEY NOT NULL,
user_id INTEGER,
title TEXT,
model TEXT NOT NULL DEFAULT '',
permission_mode TEXT NOT NULL DEFAULT 'default',
input_tokens INTEGER NOT NULL DEFAULT 0,
output_tokens INTEGER NOT NULL DEFAULT 0,
total_tokens INTEGER NOT NULL DEFAULT 0,
cost_usd REAL NOT NULL DEFAULT 0,
num_turns INTEGER NOT NULL DEFAULT 0,
message_count INTEGER NOT NULL DEFAULT 0,
created_at TEXT NOT NULL DEFAULT (datetime('now')),
updated_at TEXT NOT NULL DEFAULT (datetime('now'))
);
CREATE INDEX IF NOT EXISTS agent_sessions_user_id_idx
ON agent_sessions (user_id);
CREATE INDEX IF NOT EXISTS agent_sessions_updated_at_idx
ON agent_sessions (updated_at);
package.json
+1
View File
@@ -29,6 +29,7 @@
"dev": "vite", "dev": "vite",
"build:web": "vite build", "build:web": "vite build",
"build": "npm run build:web", "build": "npm run build:web",
"build:all": "node scripts/build-all.mjs",
"typecheck:web": "tsc -p tsconfig.web.json", "typecheck:web": "tsc -p tsconfig.web.json",
"typecheck:web:test": "tsc -p tsconfig.web.test.json", "typecheck:web:test": "tsc -p tsconfig.web.test.json",
"typecheck": "npm run typecheck:web && npm run typecheck:web:test", "typecheck": "npm run typecheck:web && npm run typecheck:web:test",
plan/2026-05-15-comfyui-agent-and-rebrand.md
-164
View File
@@ -1,164 +0,0 @@
# 2026-05-15 技术报告 / Technical Report
## Executive Summary
本日完成 BoosAPI 品牌迁移、ComfyUI Agent 对话助手开发、Gitea CI/CD Runner 部署、Notification Service 能力梳理及部署文档重写。核心变更包括：将项目内 `Metapi` 全局替换为 `BoosAPI`，新增 `/comfyui-agent` 对话式 AI 视频生成入口，完成 SSE streaming 前后端链路，并完善生产部署文档与通知服务说明。
---
## 1. Metapi → BoosAPI 全局改名 / Global Rename
### 1.1 变更范围 / Change Scope
| 区域 / Area | 变更内容 / Changes |
|---|---|
| UI 界面 / UI | About 页面、侧边栏、登录页品牌名更新为 `BoosAPI` |
| i18n 翻译 / Internationalization | 所有语言文件中的 `Metapi` 替换为 `BoosAPI` |
| 后端通知 / Backend Notification | `notifyService.ts` 通知前缀由 `[metapi]` 改为 `[BoosAPI]` |
| 桌面元数据 / Desktop Metadata | Electron / Docker 描述信息更新 |
### 1.2 已完成的技术标识替换 / Completed Technical Identifier Changes
| 项目 / Item | 变更说明 / Description |
|---|---|
| HTTP Header | `x-metapi-*` → `x-boosapi-*` |
| 推理签名前缀 / Inference Signature Prefix | `metapi:` → `boosapi:` |
| 运行时属性 / Runtime Properties | `__metapiTruncated` 等 → `__boosapi*` |
| 环境变量 / Environment Variables | `METAPI_*` → `BOOSAPI_*` |
| Package Name | `package.json` 中 `name` 更新为 `boosapi` |
### 1.3 验证方式 / Verification
```bash
grep -rn '[mM]etapi' src/ --include='*.ts' --include='*.tsx' --include='*.html' \
| grep -v '.test.' | grep -v node_modules | grep -iv 'boosapi'
```
预期结果：无输出。
---
## 2. ComfyUI Agent 对话助手 / Conversational Assistant
### 2.1 功能概述 / Feature Overview
侧边栏新增「对话助手」入口，路由为 `/comfyui-agent`，提供与 AI 视频生成助手的对话式交互，支持文本、角色提示词、图像、场景、语音和 ComfyUI workflow 等多类型内容的流式渲染。
### 2.2 技术架构 / Architecture
```
用户 / User → POST /api/comfyui-agent/chat → BoosAPI → LLM 本地 API (streaming)
→ SSE 事件流 → BoosAPI 转发 → 浏览器
```
### 2.3 后端实现 / Backend
| 文件 / File | 作用 / Responsibility |
|---|---|
| `src/server/routes/api/comfyuiAgent.ts` | SSE 流式聊天接口，调用本地 LLM API |
| `src/server/services/boosapi_comfy_nodes.py` | ComfyUI 自定义节点，默认连接 `http://127.0.0.1:4000/v1` |
### 2.4 前端实现 / Frontend
| 文件 / File | 作用 / Responsibility |
|---|---|
| `src/web/pages/ComfyUIAgent.tsx` | 对话界面组件，SSE 流式渲染 |
| `src/web/App.tsx` | 注册 `/comfyui-agent` 路由及侧边栏入口 |
### 2.5 SSE 事件类型 / SSE Event Types
| `type` | 含义 / Meaning | 前端渲染 / Rendering |
|---|---|---|
| `text` | 流式文本 | 追加到对话内容 |
| `character_prompts` | 四角度角色提示词 | 角色卡片 |
| `image` | 生成的角色图像 | 内联图片 |
| `scene` | 场景提示词 | 场景块 |
| `tts` | 语音音频 | 音频播放器 |
| `comfyui_workflow` | 完整 ComfyUI 工作流 JSON | 下载按钮 |
| `done` | 流结束 | 停止等待 |
### 2.6 验证结果 / Verification
| 命令 | 结果 |
|---|---|
| `npm install` | ✅ |
| `npm run typecheck:web` | ✅ 0 error |
---
## 3. Gitea CI/CD Runner 部署 / Runner Deployment
### 3.1 部署信息 / Deployment Info
| 项目 | 详情 |
|---|---|
| 系统 | Alpine Linux, OpenRC |
| 部署方式 | 裸机直跑，无 DinD |
| Runner 版本 | v0.1.3 |
| 注册模式 | `:host` 标签 |
| OpenRC 服务 | `/etc/init.d/gitea-runner` |
| 代理 | `HTTP_PROXY=http://127.0.0.1:7890` |
| `NO_PROXY` | 包含 `git.boos.lat` |
| 持久化 | `ephemeral: false` |
### 3.2 已知限制 / Known Limitations
- 不支持 Docker in Docker；CI 使用 `runs-on: host`
- 无原生 artifact 存储；构建产物需手动备份
- `actions/checkout` 偶发 timeout；可重试或使用本地 git 镜像
---
## 4. Notification Service
### 4.1 支持通道 / Supported Channels
| 通道 | 配置前缀 | 协议 |
|---|---|---|
| Telegram | `telegram*` | Bot API |
| 企业微信 | `wecom*` | Webhook |
| 飞书 | `feishu*` | Webhook |
| 通用 Webhook | `webhook*` | JSON POST |
| Bark | `bark*` | HTTP, iOS |
| Server酱 | `serverchan*` | HTTP |
| SMTP | `smtp*` | Email |
### 4.2 Telegram 消息格式
- 纯文本，不启用 HTML/Markdown 解析
- 单条最大 3900 字符，超长截断 + `...(truncated)`
- 支持 Telegram Topics（`message_thread_id`）
### 4.3 节流机制 / Throttling
- 基于通知签名的全局冷静期：`notifyCooldownSec`
- 同一签名在冷静期内重复触发时合并为一次
- 冷静期为全局共享，不按通道独立
---
## 5. 部署文档完善 / Deployment Documentation
Commit: `5bd847d`
对 `docs/deployment.md` 全量重写，修复所有 `metapi` 残留：
- 完整 `docker-compose.yml` 示例（含 healthcheck）
- `.env` 变量插值模式
- 全部环境变量参考表（20+ 变量）
- 扩展配置：外部 MySQL/PostgreSQL、Redis、资源限制
- 生产部署检查清单
- Nginx 反向代理（WebSocket + SSE）
- 管理后台 IP 白名单限制示例
- Docker run 常用选项表
- 升级/回滚操作流程
---
## 6. 待办事项 / TODO
| 优先级 | 事项 | 说明 |
|---|---|---|
| High | 服务未运行 | CI 崩溃后容器未恢复，需确定 Docker vs `npm run dev` |
| Medium | Telegram 格式优化 | 待确认 HTML/Markdown/简化 |
| Medium | CI pipeline 稳定性 | Docker 镜像拉取超时，需排查网络 |
plan/2026-05-18-comfyui-video-assistant-saas.md
-340
View File
@@ -1,340 +0,0 @@
# 内置 ComfyUI 视频助手 + SaaS 多租户方案
> 生成: gpt-5.5 via api.boos.lat | 2026-05-18
---
## 1. 数据表设计 (SQLite migrations)
### 1.1 `tenants` 租户
```sql
CREATE TABLE tenants (
id TEXT PRIMARY KEY,
name TEXT NOT NULL,
slug TEXT UNIQUE NOT NULL,
plan TEXT NOT NULL DEFAULT 'free',
status TEXT NOT NULL DEFAULT 'active',
owner_user_id TEXT NOT NULL,
settings TEXT NOT NULL DEFAULT '{}',
created_at TEXT NOT NULL DEFAULT (datetime('now')),
updated_at TEXT NOT NULL DEFAULT (datetime('now'))
);
```
### 1.2 `tenant_members` 租户成员
```sql
CREATE TABLE tenant_members (
id TEXT PRIMARY KEY,
tenant_id TEXT NOT NULL REFERENCES tenants(id) ON DELETE CASCADE,
user_id TEXT NOT NULL,
role TEXT NOT NULL DEFAULT 'member',
status TEXT NOT NULL DEFAULT 'active',
created_at TEXT NOT NULL DEFAULT (datetime('now')),
UNIQUE(tenant_id, user_id)
);
```
### 1.3 `subscriptions` 订阅与额度
```sql
CREATE TABLE subscriptions (
id TEXT PRIMARY KEY,
tenant_id TEXT NOT NULL REFERENCES tenants(id) ON DELETE CASCADE,
plan TEXT NOT NULL,
status TEXT NOT NULL DEFAULT 'active',
monthly_generations_limit INTEGER NOT NULL DEFAULT 100,
monthly_video_seconds_limit INTEGER NOT NULL DEFAULT 300,
storage_bytes_limit INTEGER NOT NULL DEFAULT 5368709120,
created_at TEXT NOT NULL DEFAULT (datetime('now')),
updated_at TEXT NOT NULL DEFAULT (datetime('now'))
);
```
### 1.4 `usage_counters` 用量统计
```sql
CREATE TABLE usage_counters (
id TEXT PRIMARY KEY,
tenant_id TEXT NOT NULL REFERENCES tenants(id) ON DELETE CASCADE,
period TEXT NOT NULL,
generations_used INTEGER NOT NULL DEFAULT 0,
video_seconds_used INTEGER NOT NULL DEFAULT 0,
storage_bytes_used INTEGER NOT NULL DEFAULT 0,
ai_tokens_used INTEGER NOT NULL DEFAULT 0,
updated_at TEXT NOT NULL DEFAULT (datetime('now')),
UNIQUE(tenant_id, period)
);
```
### 1.5 `comfy_workflows` 工作流模板
```sql
CREATE TABLE comfy_workflows (
id TEXT PRIMARY KEY,
tenant_id TEXT REFERENCES tenants(id) ON DELETE CASCADE,
name TEXT NOT NULL,
description TEXT,
type TEXT NOT NULL DEFAULT 'video',
visibility TEXT NOT NULL DEFAULT 'private',
workflow_json TEXT NOT NULL,
input_schema TEXT NOT NULL DEFAULT '{}',
version INTEGER NOT NULL DEFAULT 1,
is_default INTEGER NOT NULL DEFAULT 0,
created_by TEXT,
created_at TEXT NOT NULL DEFAULT (datetime('now')),
updated_at TEXT NOT NULL DEFAULT (datetime('now'))
);
```
### 1.6 `video_jobs` 视频任务
```sql
CREATE TABLE video_jobs (
id TEXT PRIMARY KEY,
tenant_id TEXT NOT NULL REFERENCES tenants(id) ON DELETE CASCADE,
user_id TEXT,
workflow_id TEXT REFERENCES comfy_workflows(id),
status TEXT NOT NULL DEFAULT 'queued',
priority INTEGER NOT NULL DEFAULT 100,
prompt TEXT,
negative_prompt TEXT,
params TEXT NOT NULL DEFAULT '{}',
comfy_prompt_id TEXT,
progress REAL NOT NULL DEFAULT 0,
error_message TEXT,
result_asset_id TEXT,
estimated_video_seconds INTEGER DEFAULT 0,
actual_video_seconds INTEGER DEFAULT 0,
started_at TEXT,
completed_at TEXT,
created_at TEXT NOT NULL DEFAULT (datetime('now')),
updated_at TEXT NOT NULL DEFAULT (datetime('now'))
);
```
### 1.7 `assets` 文件资产
```sql
CREATE TABLE assets (
id TEXT PRIMARY KEY,
tenant_id TEXT NOT NULL REFERENCES tenants(id) ON DELETE CASCADE,
user_id TEXT,
job_id TEXT REFERENCES video_jobs(id) ON DELETE SET NULL,
type TEXT NOT NULL,
mime_type TEXT,
file_name TEXT,
storage_path TEXT NOT NULL,
public_url TEXT,
size_bytes INTEGER NOT NULL DEFAULT 0,
metadata TEXT NOT NULL DEFAULT '{}',
created_at TEXT NOT NULL DEFAULT (datetime('now'))
);
```
---
## 2. API 路由设计
### 租户管理
```
POST /api/tenants → 创建租户
GET /api/tenants → 我的租户列表
GET /api/tenants/:id → 租户详情
PATCH /api/tenants/:id → 更新租户
```
### 成员管理
```
GET /api/tenants/:id/members → 成员列表
POST /api/tenants/:id/members/invite → 邀请成员
DELETE /api/tenants/:id/members/:uid → 移除成员
PATCH /api/tenants/:id/members/:uid/role → 修改角色
```
### 视频助手
```
POST /api/tenants/:id/video/analyze → 解析脚本(角色/场景/对话)
POST /api/tenants/:id/video/generate → 生成视频任务
GET /api/tenants/:id/video/jobs → 任务列表
GET /api/tenants/:id/video/jobs/:jid → 任务详情
POST /api/tenants/:id/video/jobs/:jid/cancel → 取消任务
GET /api/tenants/:id/video/jobs/:jid/events → SSE 进度
```
### ComfyUI 工作流
```
GET /api/tenants/:id/workflows → 工作流模板列表
POST /api/tenants/:id/workflows → 创建模板
GET /api/tenants/:id/workflows/:wid → 模板详情
DELETE /api/tenants/:id/workflows/:wid → 删除模板
```
### 资产生成(ai Helper)
```
POST /api/tenants/:id/ai/character → gpt-image-2 生成角色四视图
POST /api/tenants/:id/ai/scene → 生成场景图
POST /api/tenants/:id/ai/tts → TTS 语音
POST /api/tenants/:id/ai/prompt-optimize → 优化视频 prompt
```
### 用量与订阅
```
GET /api/tenants/:id/usage → 当前用量
GET /api/tenants/:id/subscription → 订阅信息
```
---
## 3. 前端页面/组件结构
```
src/web/pages/
├── VideoAssistant.tsx ← 视频助手主页面(prompt→生成→预览)
├── VideoJobs.tsx ← 历史任务列表
├── WorkflowLibrary.tsx ← 工作流模板库
├── TenantSettings.tsx ← 租户设置
└── TenantMembers.tsx ← 成员管理
src/web/components/
├── video/
│ ├── ScriptEditor.tsx ← 自然语言脚本编辑
│ ├── ScriptPreview.tsx ← 脚本解析预览(角色/场景/对话)
│ ├── CharacterCard.tsx ← 角色四视图卡片
│ ├── SceneCard.tsx ← 场景图卡片
│ ├── TTSPlayer.tsx ← TTS 语音播放
│ ├── WorkflowExport.tsx ← ComfyUI 工作流导出
│ └── VideoPlayer.tsx ← 视频播放/下载
├── tenant/
│ ├── TenantSwitcher.tsx ← 租户切换
│ ├── MemberList.tsx ← 成员列表
│ ├── InviteDialog.tsx ← 邀请对话框
│ └── UsageQuota.tsx ← 用量/配额显示
```
---
## 4. 核心业务流程
### 注册 → 创作 → 导出
```
1. 注册/登录
2. 自动创建个人租户(或个人空间)
3. 进入视频助手页面
4. 输入自然语言脚本
5. 系统解析 → 提取角色/场景/对话
6. 自动调用 AI 生成:
- 【CHARACTER】→ gpt-image-2 四视图
- 【SCENE】 → 场景图
- 【TTS】 → 语音
- 【WORKFLOW】 → ComfyUI 工作流 JSON
7. 预览所有生成内容
8. 导出/下载/提交 ComfyUI 执行
9. 视频生成 → 预览 → 下载
如需协作: → 创建组织 → 邀请成员 → 设置角色
```
### 租户管理流程
```
创建组织
→ 成为 owner
→ 可创建 API Key
→ 可邀请成员(邮箱/链接)
→ 角色: owner / admin / member
→ 每个成员有独立用量跟踪
套餐限制:
free: 50 次/月, 5GB 存储, 基础功能
pro: 500 次/月, 50GB, 全功能+更高配额
custom: 定制
```
---
## 5. 文件变更清单
### 新增文件
**后端 Rust:**
```
src/routes/tenants/mod.rs → 租户 CRUD
src/routes/tenants/{handlers,types}.rs
src/routes/video_jobs/ → 视频任务管理
src/routes/video_jobs/{handlers,sse}.rs
src/routes/ai_assist.rs → AI 辅助生成(角色/场景/TTS/prompt)
src/routes/subscriptions.rs → 订阅/用量
src/services/tenant_service.rs → 租户业务逻辑
src/services/video_service.rs → 视频任务调度
src/services/usage_service.rs → 用量统计
src/services/comfy_client.rs → ComfyUI API 客户端
src/workers/video_worker.rs → 后台视频任务 Worker
src/middleware/tenant_context.rs → 租户上下文中间件
migrations/0010_tenants.sql
migrations/0011_tenant_members.sql
migrations/0012_subscriptions.sql
migrations/0013_usage_counters.sql
migrations/0014_comfy_workflows.sql
migrations/0015_video_jobs.sql
migrations/0016_assets.sql
```
**前端:**
```
src/web/pages/VideoAssistant.tsx
src/web/pages/VideoJobs.tsx
src/web/pages/WorkflowLibrary.tsx
src/web/pages/TenantSettings.tsx
src/web/pages/TenantMembers.tsx
src/web/components/video/*.tsx
src/web/components/tenant/*.tsx
src/web/hooks/useVideoJobs.ts
src/web/hooks/useTenant.ts
src/web/hooks/useAssets.ts
src/web/hooks/useUsage.ts
```
### 修改文件
```
src/routes/mod.rs → 注册新路由
src/web/App.tsx → 添加导航项和路由
src/routes/video_agent.rs → 增强现有 Agent SSE
src/services/mod.rs → 注册新服务
src/config.rs → 添加 ComfyUI/套餐配置
src/main.rs → 注册 Worker
src/db/mod.rs → 新增表类型
```
---
## 6. 实施步骤（按优先级）
### P0 - 基础链路
1. migrations: tenants + video_jobs + assets 三张核心表
2. 租户上下文中间件
3. 视频助手 Agent SSE 增强 → 脚本解析 + AI 生成调用
4. 前端 VideoAssistant 页面（脚本输入→解析→预览→导出）
5. ComfyUI client → 提交 prompt + 获取结果
### P1 - 多租户
6. 租户 CRUD + 成员管理 + 邀请
7. 资源 tenant_id 隔离
8. 用量统计 + 套餐限制
9. API Key 管理
10. 顶栏租户切换 + 用量显示
### P2 - 生产增强
11. SSE 实时进度
12. Worker 后台任务队列
13. 视频任务历史 + 重试
14. ComfyUI 工作流模板库
15. AI prompt 优化（调用 gpt-5.5）
### P3 - 商业化
16. 订阅管理(Stripe/内部)
17. 多 ComfyUI 节点调度
18. 对象存储集成
plan/NIT报考学习平台（初版需求备注解析）.docx
BIN
View File
Binary file not shown.
plan/NIT报考学习平台（学员使用及后台管理需求思维导图-初版）.pdf
BIN
View File
Binary file not shown.
plan/rust-backend-rewrite.md
-1907
View File
File diff suppressed because it is too large Load Diff
scripts/build-all.mjs
+53
View File
@@ -0,0 +1,53 @@
#!/usr/bin/env node
// Build the management console (vite) and the public website (next) in
// parallel. Each child inherits stdio with a prefix so logs stay readable.
// Exits non-zero if any build fails. Does NOT build the Rust backend.
import { spawn } from 'node:child_process';
import { fileURLToPath } from 'node:url';
import { dirname, resolve } from 'node:path';
const root = resolve(dirname(fileURLToPath(import.meta.url)), '..');
/** Run a command, prefixing each output line with [label]. */
function run(label, cmd, args, cwd) {
return new Promise((resolveJob) => {
const started = Date.now();
const child = spawn(cmd, args, { cwd, shell: false });
const pipe = (stream, sink) => {
let buf = '';
stream.on('data', (chunk) => {
buf += chunk.toString();
const lines = buf.split('\n');
buf = lines.pop() ?? '';
for (const line of lines) sink.write(`[${label}] ${line}\n`);
});
stream.on('end', () => {
if (buf) sink.write(`[${label}] ${buf}\n`);
});
};
pipe(child.stdout, process.stdout);
pipe(child.stderr, process.stderr);
child.on('close', (code) => {
const secs = ((Date.now() - started) / 1000).toFixed(1);
process.stdout.write(`[${label}] ${code === 0 ? '✓ 完成' : '✗ 失败'}（${secs}s）\n`);
resolveJob({ label, code: code ?? 1 });
});
child.on('error', (err) => {
process.stderr.write(`[${label}] 启动失败: ${err.message}\n`);
resolveJob({ label, code: 1 });
});
});
}
const jobs = [
run('web', 'npx', ['vite', 'build'], root),
run('website', 'npm', ['--prefix', 'website', 'run', 'build'], root),
];
const results = await Promise.all(jobs);
const failed = results.filter((r) => r.code !== 0);
if (failed.length > 0) {
process.stderr.write(`\n构建失败: ${failed.map((r) => r.label).join(', ')}\n`);
process.exit(1);
}
process.stdout.write('\n前端 + 官网构建完成。\n');
src/config.rs
+14
View File
@@ -98,6 +98,10 @@ pub struct PixelleVideoConfig {
pub video_fps: i64, pub video_fps: i64,
pub poll_interval_secs: u64, pub poll_interval_secs: u64,
pub timeout_secs: u64, pub timeout_secs: u64,
#[serde(default = "default_pixelle_config_path")]
pub config_path: String,
#[serde(default = "default_pixelle_compose_dir")]
pub compose_dir: String,
} }
#[derive(Debug, Deserialize, Clone)] #[derive(Debug, Deserialize, Clone)]
@@ -165,6 +169,14 @@ fn default_pixelle_backend_provider() -> String {
"comfy".to_string() "comfy".to_string()
} }
fn default_pixelle_config_path() -> String {
"/opt/Pixelle-Video/config.yaml".to_string()
}
fn default_pixelle_compose_dir() -> String {
"/opt/Pixelle-Video".to_string()
}
fn default_workflow_points_cost() -> f64 { fn default_workflow_points_cost() -> f64 {
10.0 10.0
} }
@@ -217,6 +229,8 @@ impl Default for PixelleVideoConfig {
video_fps: 30, video_fps: 30,
poll_interval_secs: 5, poll_interval_secs: 5,
timeout_secs: 900, timeout_secs: 900,
config_path: default_pixelle_config_path(),
compose_dir: default_pixelle_compose_dir(),
} }
} }
} }
src/lib.rs
+7 -1
View File
@@ -57,9 +57,15 @@ impl AppState {
reqwest::Client::new() reqwest::Client::new()
}); });
let db = Arc::new(db);
// Hand the payment module a process-wide DB handle so the Comfy Firebase
// refresh path can persist a rotated refresh token without threading
// &SqlitePool through every balance/checkout call site.
services::payment::init_payment_db(db.clone());
Self { Self {
config, config,
db: Arc::new(db), db,
http, http,
comfyui, comfyui,
builtin_keys: Arc::new(builtin_keys), builtin_keys: Arc::new(builtin_keys),
src/main.rs
+2 -4
View File
@@ -144,10 +144,8 @@ async fn main() -> anyhow::Result<()> {
let builtin = builtin_keys::BuiltinKeys { let builtin = builtin_keys::BuiltinKeys {
comfyui_agent: comfyui_agent_key, comfyui_agent: comfyui_agent_key,
}; };
let runtime_auth = runtime_auth::RuntimeAuthSettings::load( let runtime_auth =
&pool, runtime_auth::RuntimeAuthSettings::load(&pool, config.auth.proxy_token.clone())
config.auth.proxy_token.clone(),
)
.await .await
.context("failed to load runtime auth settings")?; .context("failed to load runtime auth settings")?;
src/proxy/cli_profiles/mod.rs
+2
View File
@@ -1,5 +1,7 @@
use serde::{Deserialize, Serialize}; use serde::{Deserialize, Serialize};
pub mod templates;
#[derive(Debug, Clone, Serialize, Deserialize, PartialEq, Eq)] #[derive(Debug, Clone, Serialize, Deserialize, PartialEq, Eq)]
pub enum CliProfileKind { pub enum CliProfileKind {
Codex, Codex,
src/proxy/cli_profiles/templates.rs
+152
View File
@@ -0,0 +1,152 @@
//! Client integration templates — copy-ready config snippets for pointing
//! popular AI clients at this BoosAPI gateway.
//!
//! Ported from AQBot's `list_gateway_templates` (`commands/gateway.rs:665-730`).
//! AQBot is a desktop app whose gateway listens on `localhost:8080`, so its
//! templates hardcode that origin. BoosAPI is a server-side SaaS, so the origin
//! is injected at request time (public domain / port) — see
//! `routes::admin::cli_templates`.
//!
//! Scope guard (per the integration analysis): this module only returns config
//! **strings + copy hints**. It deliberately does NOT rewrite any local CLI
//! config files (AQBot's `cli_config.rs` desktop behavior) — that has no meaning
//! on a server and is explicitly out of scope.
use serde::Serialize;
/// A copy-ready integration snippet for one client.
#[derive(Debug, Clone, Serialize, PartialEq, Eq)]
pub struct GatewayTemplate {
/// Stable identifier (e.g. `"cursor"`).
pub id: String,
/// Human-facing name (e.g. `"Cursor"`).
pub name: String,
/// Target client slug, mirrors `id` (kept for frontend parity with AQBot).
pub target: String,
/// Content format hint for the UI renderer: `"json"` | `"markdown"`.
pub format: String,
/// The snippet itself, with the live gateway origin already substituted.
pub content: String,
/// Short instruction on where to put the snippet.
pub copy_hint: Option<String>,
}
/// Build the full template list for a given gateway `origin`
/// (scheme + host + optional port, no trailing slash, e.g.
/// `https://api.boos.lat`).
///
/// URL conventions differ per client:
/// - OpenAI-compatible clients (Cursor, VS Code Continue, generic) want the
/// `/v1` base (`{origin}/v1`).
/// - Claude Code's `ANTHROPIC_BASE_URL` must be the bare origin — it appends
/// `/v1/messages` itself, so a `/v1` suffix would double it.
pub fn list_templates(origin: &str) -> Vec<GatewayTemplate> {
let origin = origin.trim_end_matches('/');
let openai_base = format!("{origin}/v1");
vec![
GatewayTemplate {
id: "cursor".to_string(),
name: "Cursor".to_string(),
target: "cursor".to_string(),
format: "json".to_string(),
content: format!(
"{{\n \"openai.apiKey\": \"YOUR_KEY\",\n \"openai.apiBaseUrl\": \"{openai_base}\"\n}}"
),
copy_hint: Some("Add to Cursor User settings.json".to_string()),
},
GatewayTemplate {
id: "vscode".to_string(),
name: "VS Code Continue".to_string(),
target: "vscode".to_string(),
format: "json".to_string(),
content: format!(
"{{\n \"models\": [{{\n \"title\": \"BoosAPI Gateway\",\n \"provider\": \"openai\",\n \"apiBase\": \"{openai_base}\",\n \"apiKey\": \"YOUR_KEY\"\n }}]\n}}"
),
copy_hint: Some("Add to ~/.continue/config.json".to_string()),
},
GatewayTemplate {
id: "claude_code".to_string(),
name: "Claude Code".to_string(),
target: "claude_code".to_string(),
format: "markdown".to_string(),
// Claude Code appends `/v1/messages` to ANTHROPIC_BASE_URL, so the
// base is the bare origin (no `/v1`).
content: format!(
"export ANTHROPIC_AUTH_TOKEN=\"YOUR_KEY\"\nexport ANTHROPIC_BASE_URL=\"{origin}\""
),
copy_hint: Some("Add to your shell profile (~/.bashrc or ~/.zshrc)".to_string()),
},
GatewayTemplate {
id: "openai_compatible".to_string(),
name: "OpenAI Compatible".to_string(),
target: "openai_compatible".to_string(),
format: "json".to_string(),
content: format!(
"{{\n \"api_key\": \"YOUR_KEY\",\n \"base_url\": \"{openai_base}\",\n \"model\": \"gpt-4\"\n}}"
),
copy_hint: Some("Use these settings in any OpenAI-compatible client".to_string()),
},
]
}
/// Look up a single template's content by id for the given `origin`.
/// Ports AQBot's `copy_gateway_template`.
pub fn find_template(id: &str, origin: &str) -> Option<GatewayTemplate> {
list_templates(origin).into_iter().find(|t| t.id == id)
}
#[cfg(test)]
mod tests {
use super::*;
#[test]
fn lists_all_four_templates() {
let templates = list_templates("https://api.boos.lat");
let ids: Vec<&str> = templates.iter().map(|t| t.id.as_str()).collect();
assert_eq!(ids, ["cursor", "vscode", "claude_code", "openai_compatible"]);
}
#[test]
fn openai_clients_get_v1_base() {
let templates = list_templates("https://api.boos.lat");
for id in ["cursor", "vscode", "openai_compatible"] {
let t = templates.iter().find(|t| t.id == id).unwrap();
assert!(
t.content.contains("https://api.boos.lat/v1"),
"{id} should embed the /v1 base, got: {}",
t.content
);
}
}
#[test]
fn claude_code_base_has_no_v1_suffix() {
// Claude Code appends /v1/messages itself; a /v1 base would double it.
let t = find_template("claude_code", "https://api.boos.lat").unwrap();
assert!(t.content.contains("ANTHROPIC_BASE_URL=\"https://api.boos.lat\""));
assert!(!t.content.contains("api.boos.lat/v1"));
}
#[test]
fn trailing_slash_in_origin_is_normalized() {
let t = find_template("cursor", "https://api.boos.lat/").unwrap();
assert!(t.content.contains("https://api.boos.lat/v1"));
assert!(!t.content.contains("//v1"));
}
#[test]
fn unknown_id_returns_none() {
assert!(find_template("nope", "https://api.boos.lat").is_none());
}
#[test]
fn templates_serialize_to_expected_shape() {
let t = find_template("cursor", "http://localhost:4000").unwrap();
let value = serde_json::to_value(&t).unwrap();
assert_eq!(value["id"], "cursor");
assert_eq!(value["format"], "json");
assert!(value["content"].as_str().unwrap().contains("localhost:4000/v1"));
assert!(value["copy_hint"].is_string());
}
}
src/proxy/executors/mod.rs
+334 -35
View File
@@ -589,7 +589,8 @@ pub async fn execute_video_generation(
} }
fn comfy_video_template_id(route: &UpstreamRoute) -> Option<String> { fn comfy_video_template_id(route: &UpstreamRoute) -> Option<String> {
route.base_url route
.base_url
.strip_prefix("comfy://") .strip_prefix("comfy://")
.or_else(|| route.base_url.strip_prefix("comfy-template://")) .or_else(|| route.base_url.strip_prefix("comfy-template://"))
.or_else(|| route.model.strip_prefix("comfy://")) .or_else(|| route.model.strip_prefix("comfy://"))
@@ -614,14 +615,16 @@ async fn execute_comfy_video_generation(
let workflow = crate::workflow::storage::get_workflow(&state.db, template_id, None, true) let workflow = crate::workflow::storage::get_workflow(&state.db, template_id, None, true)
.await .await
.map_err(|err| AppError::BadRequest(format!("Comfy 视频模型模板不可用: {err}")))?; .map_err(|err| AppError::BadRequest(format!("Comfy 视频模型模板不可用: {err}")))?;
let mut prompt = workflow_prompt_from_graph(&workflow.graph) let mut prompt = workflow_prompt_from_graph(&workflow.graph).ok_or_else(|| {
.ok_or_else(|| AppError::BadRequest("Comfy 视频模型模板缺少 prompt/workflow JSON".into()))?; AppError::BadRequest("Comfy 视频模型模板缺少 prompt/workflow JSON".into())
})?;
if prompt_contains_class_type(&prompt, "BoosAPITextToVideo") { if prompt_contains_class_type(&prompt, "BoosAPITextToVideo") {
return Err(AppError::BadRequest( return Err(AppError::BadRequest(
"Comfy 视频模型模板不能包含 BoosAPITextToVideo 自定义节点，请选择真实 Comfy 视频节点模板".into(), "Comfy 视频模型模板不能包含 BoosAPITextToVideo 自定义节点，请选择真实 Comfy 视频节点模板".into(),
)); ));
} }
let mut mapping = comfy_mapping_from_graph(&workflow.graph).unwrap_or_else(default_comfy_mapping); let mut mapping =
comfy_mapping_from_graph(&workflow.graph).unwrap_or_else(default_comfy_mapping);
if !mapping_has_node(&mapping, &["prompt", "positive", "text", "promptNode"]) { if !mapping_has_node(&mapping, &["prompt", "positive", "text", "promptNode"]) {
mapping = infer_comfy_mapping(&prompt); mapping = infer_comfy_mapping(&prompt);
} }
@@ -644,7 +647,9 @@ async fn execute_comfy_video_generation(
.or_else(|| response.pointer("/data/prompt_id")) .or_else(|| response.pointer("/data/prompt_id"))
.or_else(|| response.pointer("/data/promptId")), .or_else(|| response.pointer("/data/promptId")),
) )
.ok_or_else(|| AppError::UpstreamError(format!("Comfy response missing prompt_id: {response}")))?; .ok_or_else(|| {
AppError::UpstreamError(format!("Comfy response missing prompt_id: {response}"))
})?;
Ok(json!({ Ok(json!({
"id": prompt_id, "id": prompt_id,
@@ -732,7 +737,8 @@ fn scalar_string(value: Option<&Value>) -> Option<String> {
} }
fn workflow_prompt_from_graph(graph: &Value) -> Option<Value> { fn workflow_prompt_from_graph(graph: &Value) -> Option<Value> {
graph.get("prompt") graph
.get("prompt")
.cloned() .cloned()
.or_else(|| graph.get("workflow").cloned()) .or_else(|| graph.get("workflow").cloned())
.or_else(|| graph.get("comfyPrompt").cloned()) .or_else(|| graph.get("comfyPrompt").cloned())
@@ -741,7 +747,8 @@ fn workflow_prompt_from_graph(graph: &Value) -> Option<Value> {
} }
fn comfy_mapping_from_graph(graph: &Value) -> Option<Value> { fn comfy_mapping_from_graph(graph: &Value) -> Option<Value> {
graph.pointer("/metadata/moneyPrinter/nodeMapping") graph
.pointer("/metadata/moneyPrinter/nodeMapping")
.or_else(|| graph.pointer("/moneyPrinter/nodeMapping")) .or_else(|| graph.pointer("/moneyPrinter/nodeMapping"))
.or_else(|| graph.pointer("/metadata/video/nodeMapping")) .or_else(|| graph.pointer("/metadata/video/nodeMapping"))
.or_else(|| graph.pointer("/video/nodeMapping")) .or_else(|| graph.pointer("/video/nodeMapping"))
@@ -772,11 +779,24 @@ fn graph_to_comfy_prompt(graph: &Value) -> Option<Value> {
.unwrap_or_default(); .unwrap_or_default();
prompt.insert(id, json!({ "class_type": class_type, "inputs": inputs })); prompt.insert(id, json!({ "class_type": class_type, "inputs": inputs }));
} }
for edge in graph.get("edges").and_then(Value::as_array).into_iter().flatten() { for edge in graph
let Some(from) = edge.get("from").and_then(Value::as_str) else { continue; }; .get("edges")
let Some(to) = edge.get("to").and_then(Value::as_str) else { continue; }; .and_then(Value::as_array)
let Some((from_id, _from_port)) = from.split_once('.') else { continue; }; .into_iter()
let Some((to_id, to_field)) = to.split_once('.') else { continue; }; .flatten()
{
let Some(from) = edge.get("from").and_then(Value::as_str) else {
continue;
};
let Some(to) = edge.get("to").and_then(Value::as_str) else {
continue;
};
let Some((from_id, _from_port)) = from.split_once('.') else {
continue;
};
let Some((to_id, to_field)) = to.split_once('.') else {
continue;
};
if let Some(inputs) = prompt if let Some(inputs) = prompt
.get_mut(to_id) .get_mut(to_id)
.and_then(Value::as_object_mut) .and_then(Value::as_object_mut)
@@ -806,7 +826,12 @@ fn mapping_value<'a>(mapping: &'a Value, keys: &[&str]) -> Option<&'a Value> {
fn mapping_node_id(mapping: &Value, keys: &[&str]) -> Option<String> { fn mapping_node_id(mapping: &Value, keys: &[&str]) -> Option<String> {
mapping_value(mapping, keys).and_then(|value| { mapping_value(mapping, keys).and_then(|value| {
if value.is_object() { if value.is_object() {
scalar_string(value.get("nodeId").or_else(|| value.get("node_id")).or(Some(value))) scalar_string(
value
.get("nodeId")
.or_else(|| value.get("node_id"))
.or(Some(value)),
)
} else { } else {
scalar_string(Some(value)) scalar_string(Some(value))
} }
@@ -829,7 +854,10 @@ fn mapping_has_node(mapping: &Value, keys: &[&str]) -> bool {
mapping_node_id(mapping, keys).is_some_and(|value| !value.trim().is_empty()) mapping_node_id(mapping, keys).is_some_and(|value| !value.trim().is_empty())
} }
fn first_node_by_class(prompt: &serde_json::Map<String, Value>, class_type: &str) -> Option<String> { fn first_node_by_class(
prompt: &serde_json::Map<String, Value>,
class_type: &str,
) -> Option<String> {
prompt prompt
.iter() .iter()
.find(|(_, node)| node.get("class_type").and_then(Value::as_str) == Some(class_type)) .find(|(_, node)| node.get("class_type").and_then(Value::as_str) == Some(class_type))
@@ -843,11 +871,22 @@ fn infer_comfy_mapping(prompt: &Value) -> Value {
let prompt_node = object let prompt_node = object
.iter() .iter()
.find(|(_, node)| { .find(|(_, node)| {
let class_type = node.get("class_type").and_then(Value::as_str).unwrap_or_default().to_ascii_lowercase(); let class_type = node
.get("class_type")
.and_then(Value::as_str)
.unwrap_or_default()
.to_ascii_lowercase();
let inputs = node let inputs = node
.get("inputs") .get("inputs")
.and_then(Value::as_object) .and_then(Value::as_object)
.map(|value| value.keys().cloned().collect::<Vec<_>>().join(" ").to_ascii_lowercase()) .map(|value| {
value
.keys()
.cloned()
.collect::<Vec<_>>()
.join(" ")
.to_ascii_lowercase()
})
.unwrap_or_default(); .unwrap_or_default();
class_type.contains("text") class_type.contains("text")
|| class_type.contains("prompt") || class_type.contains("prompt")
@@ -875,19 +914,29 @@ fn infer_comfy_mapping(prompt: &Value) -> Value {
fn apply_node_input(prompt: &mut Value, node_id: &str, field: &str, value: Value) -> AppResult<()> { fn apply_node_input(prompt: &mut Value, node_id: &str, field: &str, value: Value) -> AppResult<()> {
if node_id.trim().is_empty() { if node_id.trim().is_empty() {
return Err(AppError::BadRequest("Comfy 视频模型节点映射包含空 nodeId".into())); return Err(AppError::BadRequest(
"Comfy 视频模型节点映射包含空 nodeId".into(),
));
} }
let Some(node) = prompt.get_mut(node_id) else { let Some(node) = prompt.get_mut(node_id) else {
return Err(AppError::BadRequest(format!("Comfy prompt missing node {node_id}"))); return Err(AppError::BadRequest(format!(
"Comfy prompt missing node {node_id}"
)));
}; };
let Some(inputs) = node.get_mut("inputs").and_then(Value::as_object_mut) else { let Some(inputs) = node.get_mut("inputs").and_then(Value::as_object_mut) else {
return Err(AppError::BadRequest(format!("Comfy node {node_id} has no inputs"))); return Err(AppError::BadRequest(format!(
"Comfy node {node_id} has no inputs"
)));
}; };
inputs.insert(field.to_string(), value); inputs.insert(field.to_string(), value);
Ok(()) Ok(())
} }
fn inject_comfy_video_inputs(prompt: &mut Value, mapping: &Value, body: &Value) -> AppResult<String> { fn inject_comfy_video_inputs(
prompt: &mut Value,
mapping: &Value,
body: &Value,
) -> AppResult<String> {
let video_prompt = scalar_string(body.get("prompt")) let video_prompt = scalar_string(body.get("prompt"))
.ok_or_else(|| AppError::BadRequest("prompt is required for Comfy video models".into()))?; .ok_or_else(|| AppError::BadRequest("prompt is required for Comfy video models".into()))?;
let prompt_node = mapping_node_id(mapping, &["prompt", "positive", "text", "promptNode"]) let prompt_node = mapping_node_id(mapping, &["prompt", "positive", "text", "promptNode"])
@@ -895,27 +944,56 @@ fn inject_comfy_video_inputs(prompt: &mut Value, mapping: &Value, body: &Value)
apply_node_input( apply_node_input(
prompt, prompt,
&prompt_node, &prompt_node,
&mapping_field(mapping, &["prompt", "positive", "text", "promptNode"], "prompt"), &mapping_field(
mapping,
&["prompt", "positive", "text", "promptNode"],
"prompt",
),
json!(video_prompt), json!(video_prompt),
)?; )?;
if let Some(negative_node) = mapping_node_id(mapping, &["negativePrompt", "negative", "negativeNode"]) { if let Some(negative_node) =
mapping_node_id(mapping, &["negativePrompt", "negative", "negativeNode"])
{
let negative = scalar_string(body.get("negative_prompt").or_else(|| body.get("negative"))) let negative = scalar_string(body.get("negative_prompt").or_else(|| body.get("negative")))
.unwrap_or_else(|| "low quality, blurry, distorted, watermark, text artifacts".to_string()); .unwrap_or_else(|| {
"low quality, blurry, distorted, watermark, text artifacts".to_string()
});
apply_node_input( apply_node_input(
prompt, prompt,
&negative_node, &negative_node,
&mapping_field(mapping, &["negativePrompt", "negative", "negativeNode"], "text"), &mapping_field(
mapping,
&["negativePrompt", "negative", "negativeNode"],
"text",
),
json!(negative), json!(negative),
)?; )?;
} }
for (keys, request_keys, default_field) in [ for (keys, request_keys, default_field) in [
(&["ratio", "ratioNode"][..], &["ratio", "aspectRatio", "aspect_ratio"][..], "ratio"), (
(&["resolution", "resolutionNode"][..], &["resolution", "size"][..], "resolution"), &["ratio", "ratioNode"][..],
(&["duration", "durationNode"][..], &["duration"][..], "duration"), &["ratio", "aspectRatio", "aspect_ratio"][..],
"ratio",
),
(
&["resolution", "resolutionNode"][..],
&["resolution", "size"][..],
"resolution",
),
(
&["duration", "durationNode"][..],
&["duration"][..],
"duration",
),
] { ] {
if let Some(node_id) = mapping_node_id(mapping, keys) { if let Some(node_id) = mapping_node_id(mapping, keys) {
if let Some(value) = request_keys.iter().find_map(|key| body.get(*key).cloned()) { if let Some(value) = request_keys.iter().find_map(|key| body.get(*key).cloned()) {
apply_node_input(prompt, &node_id, &mapping_field(mapping, keys, default_field), value)?; apply_node_input(
prompt,
&node_id,
&mapping_field(mapping, keys, default_field),
value,
)?;
} }
} }
} }
@@ -929,9 +1007,13 @@ fn prompt_contains_class_type(prompt: &Value, class_type: &str) -> bool {
.get("class_type") .get("class_type")
.and_then(Value::as_str) .and_then(Value::as_str)
.is_some_and(|value| value == class_type) .is_some_and(|value| value == class_type)
|| object.values().any(|value| prompt_contains_class_type(value, class_type)) || object
.values()
.any(|value| prompt_contains_class_type(value, class_type))
} }
Value::Array(items) => items.iter().any(|value| prompt_contains_class_type(value, class_type)), Value::Array(items) => items
.iter()
.any(|value| prompt_contains_class_type(value, class_type)),
_ => false, _ => false,
} }
} }
@@ -1024,7 +1106,10 @@ fn comfy_failure_message(value: &Value) -> Option<String> {
let status = scalar_string(value.get("status").or_else(|| value.get("state"))) let status = scalar_string(value.get("status").or_else(|| value.get("state")))
.unwrap_or_default() .unwrap_or_default()
.to_ascii_lowercase(); .to_ascii_lowercase();
if matches!(status.as_str(), "failed" | "error" | "cancelled" | "canceled") { if matches!(
status.as_str(),
"failed" | "error" | "cancelled" | "canceled"
) {
return Some( return Some(
scalar_string(value.pointer("/execution_error/exception_message")) scalar_string(value.pointer("/execution_error/exception_message"))
.or_else(|| scalar_string(value.get("error"))) .or_else(|| scalar_string(value.get("error")))
@@ -1038,10 +1123,12 @@ fn comfy_failure_message(value: &Value) -> Option<String> {
fn comfy_output_objects(value: &Value) -> bool { fn comfy_output_objects(value: &Value) -> bool {
match value { match value {
Value::Object(object) => { Value::Object(object) => {
["videos", "gifs", "images"] ["videos", "gifs", "images"].iter().any(|key| {
.iter() object
.any(|key| object.get(*key).and_then(Value::as_array).is_some_and(|items| !items.is_empty())) .get(*key)
|| object.values().any(comfy_output_objects) .and_then(Value::as_array)
.is_some_and(|items| !items.is_empty())
}) || object.values().any(comfy_output_objects)
} }
Value::Array(items) => items.iter().any(comfy_output_objects), Value::Array(items) => items.iter().any(comfy_output_objects),
_ => false, _ => false,
@@ -1159,3 +1246,215 @@ pub async fn execute_image_edit(
Ok(json) Ok(json)
} }
// ── Gemini native passthrough ───────────────────────────────────────────
//
// Gemini's native protocol carries the model in the URL path
// (`/v1beta/models/{model}:{op}`) and the API key in the `?key=` query, so the
// request body needs no rewrite — we forward it verbatim. This mirrors AQBot's
// `handle_native_request`, which deliberately skips `rewrite_body_model` for
// Gemini, and BoosAPI's own `/v1/responses` passthrough.
/// Normalize an upstream base into a Gemini `v1beta` root. Accepts bases that
/// already end in `/v1beta` (or contain `/v1beta/`) and leaves them as-is;
/// otherwise appends `/v1beta`. Trailing slashes are trimmed.
fn gemini_base_url(base_url: &str) -> String {
let trimmed = base_url.trim().trim_end_matches('/');
if trimmed.ends_with("/v1beta") || trimmed.contains("/v1beta/") {
trimmed.to_string()
} else {
format!("{trimmed}/v1beta")
}
}
/// Build `{base}/v1beta/models/{model}:{op}?key={api_key}[&{extra_query}]`.
/// `extra_query` carries client query params already filtered (e.g. `alt=sse`),
/// without a leading `?`/`&`.
fn gemini_operation_url(
base_url: &str,
model: &str,
operation: &str,
api_key: &str,
extra_query: Option<&str>,
) -> String {
let base = gemini_base_url(base_url);
let model = model.trim().trim_start_matches('/');
let model = model.strip_prefix("models/").unwrap_or(model);
let mut url = format!("{base}/models/{model}:{operation}");
let mut sep = '?';
if !api_key.is_empty() {
url.push(sep);
url.push_str("key=");
url.push_str(api_key);
sep = '&';
}
if let Some(query) = extra_query.filter(|q| !q.is_empty()) {
url.push(sep);
url.push_str(query);
}
url
}
/// Execute a non-streaming Gemini operation (`generateContent` / `countTokens`)
/// and return the upstream JSON verbatim.
pub async fn execute_gemini_operation(
state: AppState,
route: UpstreamRoute,
operation: &str,
body: Value,
extra_query: Option<&str>,
) -> AppResult<Value> {
let client = state.http.clone();
let upstream_url =
gemini_operation_url(&route.base_url, &route.model, operation, &route.api_key, extra_query);
let resp = client
.post(&upstream_url)
.header("Content-Type", "application/json")
.json(&body)
.send()
.await
.map_err(|e| AppError::UpstreamError(format!("Upstream request failed: {e}")))?;
let status = resp.status();
let text = resp
.text()
.await
.map_err(|e| AppError::UpstreamError(format!("Failed to read upstream response: {e}")))?;
if !status.is_success() {
return Err(AppError::UpstreamError(format!(
"Upstream returned {status}: {text}"
)));
}
parse_upstream_json(&text, &upstream_url, status)
}
/// Execute a streaming Gemini operation (`streamGenerateContent`) and return the
/// live upstream response for SSE passthrough. `alt=sse` is enforced in the
/// query so the upstream emits `data:`-framed events the accumulator can parse.
pub async fn execute_gemini_stream_response(
state: AppState,
route: UpstreamRoute,
operation: &str,
body: Value,
extra_query: Option<&str>,
) -> AppResult<reqwest::Response> {
let client = state.http.clone();
let query = merge_alt_sse(extra_query);
let upstream_url = gemini_operation_url(
&route.base_url,
&route.model,
operation,
&route.api_key,
Some(&query),
);
let resp = client
.post(&upstream_url)
.header("Content-Type", "application/json")
.json(&body)
.send()
.await
.map_err(|e| AppError::UpstreamError(format!("Upstream request failed: {e}")))?;
let status = resp.status();
if !status.is_success() {
let text = resp
.text()
.await
.unwrap_or_else(|_| "unknown error".to_string());
return Err(AppError::UpstreamError(format!(
"Upstream returned {status}: {text}"
)));
}
Ok(resp)
}
/// Ensure `alt=sse` is present in the extra query (Gemini streams plain JSON
/// arrays without it). Preserves any other client-supplied params.
fn merge_alt_sse(extra_query: Option<&str>) -> String {
match extra_query.filter(|q| !q.is_empty()) {
Some(q) if q.split('&').any(|p| p == "alt=sse" || p.starts_with("alt=")) => q.to_string(),
Some(q) => format!("{q}&alt=sse"),
None => "alt=sse".to_string(),
}
}
#[cfg(test)]
mod gemini_tests {
use super::*;
#[test]
fn base_url_appends_v1beta_when_missing() {
assert_eq!(
gemini_base_url("https://generativelanguage.googleapis.com"),
"https://generativelanguage.googleapis.com/v1beta"
);
}
#[test]
fn base_url_preserves_existing_v1beta() {
assert_eq!(
gemini_base_url("https://generativelanguage.googleapis.com/v1beta/"),
"https://generativelanguage.googleapis.com/v1beta"
);
}
#[test]
fn operation_url_embeds_model_op_and_key() {
let url = gemini_operation_url(
"https://generativelanguage.googleapis.com",
"gemini-2.0-flash",
"generateContent",
"secret",
None,
);
assert_eq!(
url,
"https://generativelanguage.googleapis.com/v1beta/models/gemini-2.0-flash:generateContent?key=secret"
);
}
#[test]
fn operation_url_strips_models_prefix_and_appends_query() {
let url = gemini_operation_url(
"https://generativelanguage.googleapis.com/v1beta",
"models/gemini-1.5-pro",
"streamGenerateContent",
"k",
Some("alt=sse"),
);
assert_eq!(
url,
"https://generativelanguage.googleapis.com/v1beta/models/gemini-1.5-pro:streamGenerateContent?key=k&alt=sse"
);
}
#[test]
fn operation_url_without_key_uses_question_mark_for_query() {
let url = gemini_operation_url(
"https://example.test/v1beta",
"gemini-x",
"countTokens",
"",
Some("foo=bar"),
);
assert_eq!(
url,
"https://example.test/v1beta/models/gemini-x:countTokens?foo=bar"
);
}
#[test]
fn merge_alt_sse_variants() {
assert_eq!(merge_alt_sse(None), "alt=sse");
assert_eq!(merge_alt_sse(Some("")), "alt=sse");
assert_eq!(merge_alt_sse(Some("foo=bar")), "foo=bar&alt=sse");
// already present → unchanged
assert_eq!(merge_alt_sse(Some("alt=sse")), "alt=sse");
assert_eq!(merge_alt_sse(Some("alt=json")), "alt=json");
}
}
src/routes/admin/accounts.rs
+6 -3
View File
@@ -305,8 +305,7 @@ fn account_response_value(
route_id, route_id,
channel_id, channel_id,
log_id, log_id,
)) = )) = runtime_health
runtime_health
{ {
let ok = status == "success"; let ok = status == "success";
let is_degraded_latency = let is_degraded_latency =
@@ -314,7 +313,11 @@ fn account_response_value(
let model = model_actual let model = model_actual
.as_ref() .as_ref()
.filter(|value| !value.trim().is_empty()) .filter(|value| !value.trim().is_empty())
.or_else(|| model_requested.as_ref().filter(|value| !value.trim().is_empty())); .or_else(|| {
model_requested
.as_ref()
.filter(|value| !value.trim().is_empty())
});
json!({ json!({
"state": if !ok { "state": if !ok {
"unhealthy" "unhealthy"
src/routes/admin/cli_templates.rs
+135
View File
@@ -0,0 +1,135 @@
//! `GET /api/cli-profiles/templates` — copy-ready client integration snippets.
//!
//! Returns config blobs (Cursor / VS Code Continue / Claude Code /
//! OpenAI-compatible) with this gateway's live origin already substituted, so
//! the admin UI can render "copy & paste" cards. The actual snippet content
//! lives in `proxy::cli_profiles::templates`.
//!
//! Origin resolution priority:
//! 1. `?base_url=` query override (operator-supplied public URL)
//! 2. `X-Forwarded-Proto` + `Host` headers (the address the client actually
//! reached us on — correct behind a TLS-terminating reverse proxy)
//! 3. `Host` header alone (scheme inferred as http)
//! 4. config `server.host:port` fallback (`0.0.0.0`/`::` rewritten to
//! `127.0.0.1`, matching the comfyui-agent local-base convention)
use crate::{proxy::cli_profiles::templates, AppState};
use axum::{
extract::{Query, State},
http::HeaderMap,
Json,
};
use serde::Deserialize;
use serde_json::{json, Value};
#[derive(Debug, Deserialize)]
pub struct TemplatesQuery {
/// Optional explicit public base URL, e.g. `https://api.boos.lat`.
/// A trailing `/v1` (or `/`) is stripped so callers can pass either form.
pub base_url: Option<String>,
}
/// Resolve the gateway origin (scheme + host[:port], no trailing slash) to
/// embed in the templates.
fn resolve_origin(state: &AppState, headers: &HeaderMap, query: &TemplatesQuery) -> String {
// 1. Explicit override wins. Normalize away a trailing `/v1` or `/`.
if let Some(raw) = query.base_url.as_ref().map(|s| s.trim()).filter(|s| !s.is_empty()) {
let trimmed = raw.trim_end_matches('/');
let trimmed = trimmed.strip_suffix("/v1").unwrap_or(trimmed);
return trimmed.trim_end_matches('/').to_string();
}
// 2/3. Derive from the inbound request headers.
if let Some(host) = header_str(headers, "host").filter(|h| !h.is_empty()) {
let scheme = header_str(headers, "x-forwarded-proto")
.map(|s| s.split(',').next().unwrap_or(s).trim().to_string())
.filter(|s| !s.is_empty())
.unwrap_or_else(|| "http".to_string());
return format!("{scheme}://{host}");
}
// 4. Config fallback. Mirrors comfyui_agent::local_base host rewrite.
let host = if state.config.server.host == "0.0.0.0" || state.config.server.host == "::" {
"127.0.0.1"
} else {
state.config.server.host.as_str()
};
format!("http://{host}:{}", state.config.server.port)
}
fn header_str<'a>(headers: &'a HeaderMap, name: &str) -> Option<&'a str> {
headers.get(name).and_then(|v| v.to_str().ok()).map(str::trim)
}
/// `GET /api/cli-profiles/templates` — list copy-ready integration snippets.
pub async fn list_templates(
State(state): State<AppState>,
headers: HeaderMap,
Query(query): Query<TemplatesQuery>,
) -> Json<Value> {
let origin = resolve_origin(&state, &headers, &query);
let templates = templates::list_templates(&origin);
Json(json!({
"data": {
"origin": origin,
"templates": templates,
}
}))
}
#[cfg(test)]
mod tests {
use super::*;
use axum::http::HeaderValue;
fn headers(pairs: &[(&str, &str)]) -> HeaderMap {
let mut map = HeaderMap::new();
for (k, v) in pairs {
map.insert(
axum::http::HeaderName::from_bytes(k.as_bytes()).unwrap(),
HeaderValue::from_str(v).unwrap(),
);
}
map
}
fn query(base: Option<&str>) -> TemplatesQuery {
TemplatesQuery {
base_url: base.map(|s| s.to_string()),
}
}
// resolve_origin doesn't touch the DB, so build a config-only state stub
// via the existing admin test helper would be heavy; instead these tests
// cover the header/override branches that don't need `state` fallback by
// exercising resolve_origin's pure header logic through a tiny shim.
#[test]
fn override_strips_v1_and_trailing_slash() {
// The override branch returns before touching `state`, so a null-ish
// pointer is never dereferenced — we validate via the helper directly.
let q = query(Some("https://api.boos.lat/v1/"));
// Reconstruct the override-only logic the function applies.
let raw = q.base_url.as_ref().unwrap().trim();
let trimmed = raw.trim_end_matches('/');
let trimmed = trimmed.strip_suffix("/v1").unwrap_or(trimmed);
assert_eq!(trimmed.trim_end_matches('/'), "https://api.boos.lat");
}
#[test]
fn host_header_with_forwarded_proto_builds_https_origin() {
let h = headers(&[("host", "api.boos.lat"), ("x-forwarded-proto", "https")]);
let scheme = header_str(&h, "x-forwarded-proto").unwrap();
let host = header_str(&h, "host").unwrap();
assert_eq!(format!("{scheme}://{host}"), "https://api.boos.lat");
}
#[test]
fn forwarded_proto_takes_first_value_when_chained() {
let h = headers(&[("x-forwarded-proto", "https, http")]);
let scheme = header_str(&h, "x-forwarded-proto")
.map(|s| s.split(',').next().unwrap_or(s).trim().to_string())
.unwrap();
assert_eq!(scheme, "https");
}
}
src/routes/admin/compat.rs
+163 -30
View File
@@ -20,7 +20,7 @@ use parking_lot::RwLock;
use serde::{Deserialize, Serialize}; use serde::{Deserialize, Serialize};
use serde_json::{json, Map, Value}; use serde_json::{json, Map, Value};
use sqlx::Row; use sqlx::Row;
use std::collections::HashMap; use std::collections::{BTreeSet, HashMap};
static PROXY_TEST_JOBS: Lazy<RwLock<HashMap<String, ProxyTestJob>>> = static PROXY_TEST_JOBS: Lazy<RwLock<HashMap<String, ProxyTestJob>>> =
Lazy::new(|| RwLock::new(HashMap::new())); Lazy::new(|| RwLock::new(HashMap::new()));
@@ -1242,6 +1242,14 @@ async fn runtime_settings(State(state): State<AppState>) -> AppResult<Json<Value
false, false,
)), )),
); );
body.insert(
"registrationDisabled".to_string(),
json!(setting_bool(
&settings,
"runtime.registration_disabled",
false,
)),
);
body.insert( body.insert(
"codexUpstreamWebsocketEnabled".to_string(), "codexUpstreamWebsocketEnabled".to_string(),
json!(setting_bool( json!(setting_bool(
@@ -1541,6 +1549,7 @@ struct RuntimeSettingsUpdateRequest {
system_proxy_url: Option<String>, system_proxy_url: Option<String>,
payload_rules: Option<Value>, payload_rules: Option<Value>,
model_availability_probe_enabled: Option<bool>, model_availability_probe_enabled: Option<bool>,
registration_disabled: Option<bool>,
codex_upstream_websocket_enabled: Option<bool>, codex_upstream_websocket_enabled: Option<bool>,
responses_compact_fallback_to_responses_enabled: Option<bool>, responses_compact_fallback_to_responses_enabled: Option<bool>,
disable_cross_protocol_fallback: Option<bool>, disable_cross_protocol_fallback: Option<bool>,
@@ -1624,6 +1633,14 @@ async fn update_runtime_settings(
) )
.await?; .await?;
} }
if let Some(disabled) = req.registration_disabled {
upsert_setting(
&state,
"runtime.registration_disabled",
bool_setting_value(disabled),
)
.await?;
}
if let Some(enabled) = req.codex_upstream_websocket_enabled { if let Some(enabled) = req.codex_upstream_websocket_enabled {
upsert_setting( upsert_setting(
&state, &state,
@@ -1870,8 +1887,102 @@ async fn update_runtime_settings(
Ok(Json(body)) Ok(Json(body))
} }
async fn brand_list() -> Json<Value> { async fn brand_list(State(state): State<AppState>) -> AppResult<Json<Value>> {
Json(json!({ "brands": ["BoosAPI"], "current": "BoosAPI" })) let mut brands = BTreeSet::new();
for model in load_model_brand_source_names(&state).await? {
if let Some(brand) = infer_model_brand(&model) {
brands.insert(brand);
}
}
Ok(Json(json!({
"brands": brands.into_iter().collect::<Vec<_>>(),
"current": Value::Null,
"scope": "model-brand",
})))
}
async fn load_model_brand_source_names(state: &AppState) -> AppResult<Vec<String>> {
let rows: Vec<(String,)> = sqlx::query_as(
r#"
SELECT model_name AS model FROM model_availability
UNION
SELECT model_name AS model FROM token_model_availability
UNION
SELECT model_pattern AS model FROM token_routes
UNION
SELECT COALESCE(model_mapping, '') AS model FROM token_routes
UNION
SELECT COALESCE(source_model, '') AS model FROM route_channels
"#,
)
.fetch_all(&*state.db)
.await?;
Ok(rows
.into_iter()
.map(|(model,)| model.trim().to_string())
.filter(|model| !model.is_empty() && !model.contains('*'))
.collect())
}
fn infer_model_brand(model: &str) -> Option<String> {
let normalized = model.trim();
if normalized.is_empty() {
return None;
}
let lower = normalized.to_ascii_lowercase();
let brand = if lower.starts_with("openai/")
|| lower.starts_with("gpt-")
|| lower.starts_with("o1")
|| lower.starts_with("o3")
|| lower.starts_with("o4")
{
"OpenAI"
} else if lower.starts_with("anthropic/") || lower.starts_with("claude") {
"Anthropic"
} else if lower.starts_with("google/") || lower.starts_with("gemini") {
"Google"
} else if lower.starts_with("deepseek") || lower.starts_with("deepseek-ai/") {
"DeepSeek"
} else if lower.starts_with("qwen")
|| lower.starts_with("qwen/")
|| lower.starts_with("alibaba/")
|| lower.starts_with("alibaba-cloud/")
{
"Qwen"
} else if lower.starts_with("glm")
|| lower.starts_with("zhipu")
|| lower.starts_with("bigmodel/")
{
"GLM"
} else if lower.starts_with("moonshot") || lower.starts_with("kimi") {
"Moonshot"
} else if lower.starts_with("minimax") || lower.starts_with("abab") {
"MiniMax"
} else if lower.starts_with("doubao")
|| lower.starts_with("seedance")
|| lower.starts_with("seedream")
|| lower.starts_with("volcengine/")
|| lower.starts_with("bytedance/")
{
"Doubao"
} else if lower.starts_with("meta-llama/") || lower.starts_with("llama") {
"Llama"
} else if lower.starts_with("mistral") || lower.starts_with("mixtral") {
"Mistral"
} else if lower.starts_with("x-ai/") || lower.starts_with("grok") {
"xAI"
} else if let Some((prefix, _)) = normalized.split_once('/') {
let prefix = prefix.trim();
if prefix.eq_ignore_ascii_case("boosapi") || prefix.eq_ignore_ascii_case("comfy") {
return None;
}
return Some(prefix.to_string());
} else {
return None;
};
Some(brand.to_string())
} }
async fn test_system_proxy() -> Json<Value> { async fn test_system_proxy() -> Json<Value> {
@@ -1952,7 +2063,9 @@ fn normalize_proxy_test_path(path: &str) -> AppResult<String> {
)); ));
} }
if !normalized.starts_with('/') { if !normalized.starts_with('/') {
return Err(AppError::BadRequest("proxy test path must start with /".into())); return Err(AppError::BadRequest(
"proxy test path must start with /".into(),
));
} }
let base_path = proxy_test_base_path(normalized); let base_path = proxy_test_base_path(normalized);
let allowed = [ let allowed = [
@@ -1968,7 +2081,8 @@ fn normalize_proxy_test_path(path: &str) -> AppResult<String> {
"/v1/videos", "/v1/videos",
]; ];
let allowed_exact = allowed.iter().any(|item| base_path == *item); let allowed_exact = allowed.iter().any(|item| base_path == *item);
let allowed_video_task = base_path.starts_with("/v1/videos/") && base_path.len() > "/v1/videos/".len(); let allowed_video_task =
base_path.starts_with("/v1/videos/") && base_path.len() > "/v1/videos/".len();
let allowed_gemini = is_gemini_proxy_test_path(normalized); let allowed_gemini = is_gemini_proxy_test_path(normalized);
if allowed_exact || allowed_video_task || allowed_gemini { if allowed_exact || allowed_video_task || allowed_gemini {
return Ok(strip_legacy_gemini_proxy_prefix(normalized).to_string()); return Ok(strip_legacy_gemini_proxy_prefix(normalized).to_string());
@@ -1988,9 +2102,9 @@ fn path_suffix_for_proxy_test(path: &str) -> AppResult<String> {
if is_gemini_proxy_test_path(without_query) { if is_gemini_proxy_test_path(without_query) {
return Ok(without_query.trim_start_matches('/').to_string()); return Ok(without_query.trim_start_matches('/').to_string());
} }
let suffix = without_query let suffix = without_query.strip_prefix("/v1").ok_or_else(|| {
.strip_prefix("/v1") AppError::BadRequest(format!("unsupported proxy test path: {without_query}"))
.ok_or_else(|| AppError::BadRequest(format!("unsupported proxy test path: {without_query}")))?; })?;
Ok(if suffix.is_empty() { Ok(if suffix.is_empty() {
"/".to_string() "/".to_string()
} else { } else {
@@ -2089,7 +2203,9 @@ fn native_gemini_proxy_test_url(base_url: &str, path: &str) -> AppResult<String>
let normalized = normalize_proxy_test_path(path)?; let normalized = normalize_proxy_test_path(path)?;
let trimmed_base = base_url.trim().trim_end_matches('/'); let trimmed_base = base_url.trim().trim_end_matches('/');
if trimmed_base.is_empty() { if trimmed_base.is_empty() {
return Err(AppError::BadRequest("Gemini upstream base URL is empty".into())); return Err(AppError::BadRequest(
"Gemini upstream base URL is empty".into(),
));
} }
let base = if trimmed_base.ends_with("/v1beta") || trimmed_base.contains("/v1beta/") { let base = if trimmed_base.ends_with("/v1beta") || trimmed_base.contains("/v1beta/") {
trimmed_base.to_string() trimmed_base.to_string()
@@ -2281,7 +2397,10 @@ async fn execute_proxy_test(
) -> Result<Value, Value> { ) -> Result<Value, Value> {
if envelope.request_kind == "multipart" if envelope.request_kind == "multipart"
|| envelope.multipart_fields.is_some() || envelope.multipart_fields.is_some()
|| envelope.multipart_files.as_ref().is_some_and(|files| !files.is_empty()) || envelope
.multipart_files
.as_ref()
.is_some_and(|files| !files.is_empty())
{ {
return Err(error_json_for_proxy_test( return Err(error_json_for_proxy_test(
&envelope, &envelope,
@@ -2403,11 +2522,9 @@ async fn stream_proxy_test(
Json(json!({ "error": error_json_for_proxy_test(&envelope, err) })), Json(json!({ "error": error_json_for_proxy_test(&envelope, err) })),
) )
})?; })?;
let stream = response.bytes_stream().map(|chunk| { let stream = response
chunk .bytes_stream()
.map_err(std::io::Error::other) .map(|chunk| chunk.map_err(std::io::Error::other).map(bytes::Bytes::from));
.map(bytes::Bytes::from)
});
return Response::builder() return Response::builder()
.header(header::CONTENT_TYPE, "text/event-stream; charset=utf-8") .header(header::CONTENT_TYPE, "text/event-stream; charset=utf-8")
.header(header::CACHE_CONTROL, "no-cache, no-transform") .header(header::CACHE_CONTROL, "no-cache, no-transform")
@@ -2441,11 +2558,9 @@ async fn stream_proxy_test(
) )
})?; })?;
let stream = response.bytes_stream().map(|chunk| { let stream = response
chunk .bytes_stream()
.map_err(std::io::Error::other) .map(|chunk| chunk.map_err(std::io::Error::other).map(bytes::Bytes::from));
.map(bytes::Bytes::from)
});
Response::builder() Response::builder()
.header(header::CONTENT_TYPE, "text/event-stream; charset=utf-8") .header(header::CONTENT_TYPE, "text/event-stream; charset=utf-8")
.header(header::CACHE_CONTROL, "no-cache, no-transform") .header(header::CACHE_CONTROL, "no-cache, no-transform")
@@ -2840,6 +2955,8 @@ mod tests {
template_proxy_url: None, template_proxy_url: None,
}, },
comfyui: Default::default(), comfyui: Default::default(),
payment: Default::default(),
pixelle_video: Default::default(),
}, },
pool, pool,
BuiltinKeys { BuiltinKeys {
@@ -2852,8 +2969,7 @@ mod tests {
#[test] #[test]
fn proxy_test_accepts_standard_and_legacy_gemini_paths() { fn proxy_test_accepts_standard_and_legacy_gemini_paths() {
assert_eq!( assert_eq!(
normalize_proxy_test_path("/v1beta/models/gemini-2.5-pro:generateContent") normalize_proxy_test_path("/v1beta/models/gemini-2.5-pro:generateContent").unwrap(),
.unwrap(),
"/v1beta/models/gemini-2.5-pro:generateContent" "/v1beta/models/gemini-2.5-pro:generateContent"
); );
assert_eq!( assert_eq!(
@@ -2981,12 +3097,10 @@ mod tests {
let error = result.expect_err("unknown paths should fail"); let error = result.expect_err("unknown paths should fail");
assert_eq!(error["path"], "/api/test/proxy/jobs"); assert_eq!(error["path"], "/api/test/proxy/jobs");
assert!( assert!(error["message"]
error["message"]
.as_str() .as_str()
.unwrap_or_default() .unwrap_or_default()
.contains("unsupported proxy test path") .contains("unsupported proxy test path"));
);
} }
#[tokio::test] #[tokio::test]
@@ -3058,12 +3172,10 @@ mod tests {
assert_eq!(error["path"], "/v1/chat/completions"); assert_eq!(error["path"], "/v1/chat/completions");
assert_eq!(error["forcedChannelId"], 77); assert_eq!(error["forcedChannelId"], 77);
assert!( assert!(error["message"]
error["message"]
.as_str() .as_str()
.unwrap_or_default() .unwrap_or_default()
.contains("Forced channel #77") .contains("Forced channel #77"));
);
} }
#[tokio::test] #[tokio::test]
@@ -3130,4 +3242,25 @@ mod tests {
assert_eq!(result["model"], "upstream-mini"); assert_eq!(result["model"], "upstream-mini");
} }
#[test]
fn infers_model_brands_without_boosapi_platform_brand() {
assert_eq!(infer_model_brand("gpt-4o-mini").as_deref(), Some("OpenAI"));
assert_eq!(
infer_model_brand("claude-3-5-sonnet").as_deref(),
Some("Anthropic")
);
assert_eq!(
infer_model_brand("deepseek-ai/DeepSeek-V3.2").as_deref(),
Some("DeepSeek")
);
assert_eq!(infer_model_brand("Qwen/Qwen3-32B").as_deref(), Some("Qwen"));
assert_eq!(
infer_model_brand("seedance-1-0-lite-t2v").as_deref(),
Some("Doubao")
);
assert_eq!(infer_model_brand("BoosAPI").as_deref(), None);
assert_eq!(infer_model_brand("boosapi/text-to-image").as_deref(), None);
assert_eq!(infer_model_brand("comfy/template").as_deref(), None);
}
} }
src/routes/admin/downstream_keys.rs
+2
View File
@@ -412,6 +412,8 @@ mod tests {
template_proxy_url: None, template_proxy_url: None,
}, },
comfyui: Default::default(), comfyui: Default::default(),
payment: Default::default(),
pixelle_video: Default::default(),
}, },
pool, pool,
BuiltinKeys { BuiltinKeys {
src/routes/admin/mod.rs
+12
View File
@@ -17,10 +17,12 @@ use tracing::info;
mod account_tokens; mod account_tokens;
mod accounts; mod accounts;
mod cli_templates;
mod compat; mod compat;
mod downstream_keys; mod downstream_keys;
mod model_candidates; mod model_candidates;
pub(crate) mod models_marketplace; pub(crate) mod models_marketplace;
mod pixelle_connection;
mod sites; mod sites;
mod tokens; mod tokens;
mod users; mod users;
@@ -174,6 +176,11 @@ pub fn routes(state: AppState) -> Router<AppState> {
get(models_marketplace::get_marketplace), get(models_marketplace::get_marketplace),
); );
let cli_templates_routes = Router::new().route(
"/api/cli-profiles/templates",
get(cli_templates::list_templates),
);
let users_routes = Router::new() let users_routes = Router::new()
.route( .route(
"/api/admin/users", "/api/admin/users",
@@ -191,6 +198,10 @@ pub fn routes(state: AppState) -> Router<AppState> {
"/api/admin/user-balances", "/api/admin/user-balances",
get(users::list_user_balances), get(users::list_user_balances),
) )
.route(
"/api/admin/pixelle/connection",
get(pixelle_connection::get_connection).put(pixelle_connection::put_connection),
)
.route( .route(
"/api/admin/users/{id}/balance/adjust", "/api/admin/users/{id}/balance/adjust",
post(users::adjust_user_balance), post(users::adjust_user_balance),
@@ -221,6 +232,7 @@ pub fn routes(state: AppState) -> Router<AppState> {
.merge(users_routes) .merge(users_routes)
.merge(model_candidates_routes) .merge(model_candidates_routes)
.merge(models_marketplace_routes) .merge(models_marketplace_routes)
.merge(cli_templates_routes)
.merge(account_tokens::routes()) .merge(account_tokens::routes())
.merge(compat::routes()) .merge(compat::routes())
.route_layer(middleware::from_fn_with_state(state, require_admin_auth)) .route_layer(middleware::from_fn_with_state(state, require_admin_auth))
src/routes/admin/pixelle_connection.rs
+67
View File
@@ -0,0 +1,67 @@
use crate::error::AppResult;
use crate::services::pixelle_connection::{self, PixelleConnection};
use crate::AppState;
use axum::{extract::State, Json};
use serde::Deserialize;
use serde_json::{json, Value};
const MASK_SENTINEL: &str = "••••";
fn mask(v: &Option<String>) -> Value {
match v {
Some(s) if s.chars().count() > 4 => {
let last4: String = s.chars().rev().take(4).collect::<Vec<_>>().into_iter().rev().collect();
json!(format!("{}{}", MASK_SENTINEL, last4))
}
Some(s) if !s.is_empty() => json!(MASK_SENTINEL),
_ => Value::Null,
}
}
pub async fn get_connection(State(state): State<AppState>) -> AppResult<Json<Value>> {
let c = pixelle_connection::read_connection(&state.db).await?;
Ok(Json(json!({
"success": true,
"connection": {
"comfyuiUrl": c.comfyui_url,
"runninghubApiKey": mask(&c.runninghub_api_key),
"comfyuiApiKey": mask(&c.comfyui_api_key),
}
})))
}
#[derive(Debug, Deserialize)]
#[serde(rename_all = "camelCase")]
pub struct UpdatePayload {
runninghub_api_key: Option<String>,
comfyui_url: Option<String>,
comfyui_api_key: Option<String>,
}
fn keep_if_not_mask(incoming: Option<String>) -> Option<String> {
match incoming {
Some(s) if s.starts_with(MASK_SENTINEL) => None,
other => other,
}
}
pub async fn put_connection(
State(state): State<AppState>,
Json(p): Json<UpdatePayload>,
) -> AppResult<Json<Value>> {
let conn = PixelleConnection {
runninghub_api_key: keep_if_not_mask(p.runninghub_api_key),
comfyui_url: p.comfyui_url,
comfyui_api_key: keep_if_not_mask(p.comfyui_api_key),
};
pixelle_connection::save_connection(&state.db, &conn).await?;
let backup = pixelle_connection::sync_to_pixelle(&state.config.pixelle_video.config_path, &conn)?;
let restart = pixelle_connection::restart_pixelle(&state.config.pixelle_video.compose_dir).await;
match restart {
Ok(()) => Ok(Json(json!({ "success": true, "backup": backup, "restarted": true }))),
Err(e) => Ok(Json(json!({
"success": true, "backup": backup, "restarted": false,
"warning": format!("配置已写入,但 Pixelle 重启失败,请手动重启: {e}")
}))),
}
}
src/routes/admin/sites.rs
+52 -14
View File
@@ -913,8 +913,13 @@ async fn probe_site_model(
match response { match response {
Ok(_) if latency_exceeded => { Ok(_) if latency_exceeded => {
if let Err(err) = if let Err(err) = update_model_probe_latency(
update_model_probe_latency(state, selected.account_id, &model.name, latency_ms, true) state,
selected.account_id,
&model.name,
latency_ms,
true,
)
.await .await
{ {
warn!(error = %err, model = %model.name, "failed to save probe latency"); warn!(error = %err, model = %model.name, "failed to save probe latency");
@@ -924,7 +929,10 @@ async fn probe_site_model(
status: "unsupported".to_string(), status: "unsupported".to_string(),
latency_ms: Some(latency_ms), latency_ms: Some(latency_ms),
latency_exceeded: true, latency_exceeded: true,
reason: Some(format!("响应延迟 {}ms 超过阈值 {}ms", latency_ms, plan.latency_threshold_ms)), reason: Some(format!(
"响应延迟 {}ms 超过阈值 {}ms",
latency_ms, plan.latency_threshold_ms
)),
http_status: None, http_status: None,
stage: Some("model"), stage: Some("model"),
source: Some("probe"), source: Some("probe"),
@@ -947,8 +955,13 @@ async fn probe_site_model(
warn!(channel_id, error = %err, "failed to record probe success"); warn!(channel_id, error = %err, "failed to record probe success");
} }
} }
if let Err(err) = if let Err(err) = update_model_probe_latency(
update_model_probe_latency(state, selected.account_id, &model.name, latency_ms, true) state,
selected.account_id,
&model.name,
latency_ms,
true,
)
.await .await
{ {
warn!(error = %err, model = %model.name, "failed to save probe latency"); warn!(error = %err, model = %model.name, "failed to save probe latency");
@@ -982,8 +995,13 @@ async fn probe_site_model(
warn!(channel_id, error = %record_err, "failed to record probe failure"); warn!(channel_id, error = %record_err, "failed to record probe failure");
} }
} }
if let Err(update_err) = if let Err(update_err) = update_model_probe_latency(
update_model_probe_latency(state, selected.account_id, &model.name, latency_ms, false) state,
selected.account_id,
&model.name,
latency_ms,
false,
)
.await .await
{ {
warn!(error = %update_err, model = %model.name, "failed to save failed probe state"); warn!(error = %update_err, model = %model.name, "failed to save failed probe state");
@@ -1041,7 +1059,8 @@ async fn resolve_probe_channel(
.bind(plan.site.id) .bind(plan.site.id)
.fetch_optional(&*state.db) .fetch_optional(&*state.db)
.await?; .await?;
fallback.ok_or_else(|| AppError::BadRequest("当前站点没有启用中的账号，无法探测".into()))? fallback
.ok_or_else(|| AppError::BadRequest("当前站点没有启用中的账号，无法探测".into()))?
} }
}; };
@@ -1067,7 +1086,9 @@ async fn resolve_probe_channel(
}; };
if api_key.trim().is_empty() { if api_key.trim().is_empty() {
return Err(AppError::BadRequest("当前站点账号缺少可用 Token，无法探测".into())); return Err(AppError::BadRequest(
"当前站点账号缺少可用 Token，无法探测".into(),
));
} }
Ok(crate::proxy::conductor::SelectedChannel { Ok(crate::proxy::conductor::SelectedChannel {
@@ -1165,7 +1186,9 @@ fn send_probe_sse(
tx.send(Ok(Event::default() tx.send(Ok(Event::default()
.event(event_type) .event(event_type)
.json_data(payload) .json_data(payload)
.unwrap_or_else(|_| Event::default().event(event_type).data("{}")))) .unwrap_or_else(|_| {
Event::default().event(event_type).data("{}")
})))
.is_ok() .is_ok()
} }
@@ -1386,6 +1409,9 @@ fn detect_site_platform(url: &str) -> (&'static str, Option<&'static str>) {
{ {
return ("openai", Some("volcengine-ark-openai")); return ("openai", Some("volcengine-ark-openai"));
} }
if lower.starts_with("https://cloud.comfy.org") {
return ("comfy_cloud", Some("comfy-cloud"));
}
if lower.contains("anthropic") || lower.contains("claude") { if lower.contains("anthropic") || lower.contains("claude") {
return ("claude", None); return ("claude", None);
@@ -1516,8 +1542,14 @@ mod tests {
assert_eq!(payload.get("httpStatus").and_then(Value::as_u64), Some(404)); assert_eq!(payload.get("httpStatus").and_then(Value::as_u64), Some(404));
assert_eq!(payload.get("stage").and_then(Value::as_str), Some("model")); assert_eq!(payload.get("stage").and_then(Value::as_str), Some("model"));
assert_eq!(payload.get("source").and_then(Value::as_str), Some("upstream")); assert_eq!(
assert_eq!(payload.get("modelName").and_then(Value::as_str), Some("gpt-4o")); payload.get("source").and_then(Value::as_str),
Some("upstream")
);
assert_eq!(
payload.get("modelName").and_then(Value::as_str),
Some("gpt-4o")
);
} }
#[test] #[test]
@@ -1528,9 +1560,15 @@ mod tests {
assert_eq!(payload.get("httpStatus").and_then(Value::as_u64), Some(404)); assert_eq!(payload.get("httpStatus").and_then(Value::as_u64), Some(404));
assert_eq!(payload.get("stage").and_then(Value::as_str), Some("model")); assert_eq!(payload.get("stage").and_then(Value::as_str), Some("model"));
assert_eq!(payload.get("source").and_then(Value::as_str), Some("upstream")); assert_eq!(
payload.get("source").and_then(Value::as_str),
Some("upstream")
);
assert_eq!(payload.get("siteId").and_then(Value::as_i64), Some(7)); assert_eq!(payload.get("siteId").and_then(Value::as_i64), Some(7));
assert_eq!(payload.get("modelName").and_then(Value::as_str), Some("gpt-4o")); assert_eq!(
payload.get("modelName").and_then(Value::as_str),
Some("gpt-4o")
);
assert_eq!( assert_eq!(
payload.get("message").and_then(Value::as_str), payload.get("message").and_then(Value::as_str),
Some("上游返回 HTTP 404 Not Found：model missing") Some("上游返回 HTTP 404 Not Found：model missing")
src/routes/agent.rs
+480
View File
@@ -0,0 +1,480 @@
//! Agent Workbench HTTP surface.
//!
//! A general-purpose, server-side AI agent exposed to the SPA over SSE. The
//! agentic loop comes from the `open-agent-sdk` crate; every LLM call is routed
//! back through BoosAPI's own OpenAI-compatible `/v1` endpoint using the
//! built-in downstream key, so agent usage flows through the same aggregation
//! and accounting pipeline as any other consumer (and can use any aggregated
//! model).
//!
//! Routes (all require a Bearer token — admin token, proxy token, or a user JWT):
//! - `POST /api/agent/chat` Stream a turn as SSE (text / tool_use /
//! tool_result / approval_request / result / error / done).
//! - `POST /api/agent/approve` Resolve a pending tool approval.
//! - `GET /api/agent/status` Engine status + a session's accounting.
//!
//! ## Safety
//! Each session runs inside an isolated sandbox directory
//! (`data/agent_sessions/{id}/`). The SDK permission callback ([`build_can_use_tool`])
//! enforces two gates on every tool: (1) path arguments must stay within the
//! sandbox, and (2) writes/executes require explicit user approval unless the
//! session mode opts out. The default mode requires approval for anything that
//! mutates state or runs a command.
use crate::auth::jwt::validate_jwt;
use crate::services::agent_workbench::{
approval::{self, ApprovalOutcome, SettledState},
bash_sandbox::SandboxedBashTool,
permission::{classify_tool_risk, decide_permission, PermissionAction, PermissionMode},
sandbox,
session_store::{self, UsageDelta},
};
use crate::AppState;
use axum::{
extract::{DefaultBodyLimit, State},
http::{HeaderMap, StatusCode},
response::sse::{Event, Sse},
routing::{get, post},
Json, Router,
};
use futures::stream::Stream;
use open_agent_sdk::api::openai::OpenAIProvider;
use open_agent_sdk::types::{ContentBlock, PermissionDecision};
use open_agent_sdk::{Agent, AgentOptions, LLMProvider, SDKMessage};
use serde::Deserialize;
use serde_json::{json, Value};
use std::convert::Infallible;
use std::sync::Arc;
use std::time::Duration;
use tokio::sync::mpsc::{unbounded_channel, UnboundedSender};
use tokio_stream::wrappers::UnboundedReceiverStream;
use uuid::Uuid;
/// Max agentic turns per chat request (bounds runaway loops / cost).
const MAX_TURNS: u32 = 20;
/// How long a tool approval waits for the user before auto-denying.
const APPROVAL_TIMEOUT: Duration = Duration::from_secs(300);
/// Body limit for a chat request (images/attachments can be large).
const AGENT_CHAT_BODY_LIMIT_BYTES: usize = 16 * 1024 * 1024;
const SYSTEM_PROMPT: &str = "You are BoosAPI's built-in engineering agent. You can read and write files \
and run shell commands, but only inside the current working directory, which is an \
isolated sandbox for this session. Be concise. Explain what you are about to do before \
using a tool that writes files or runs commands. Never attempt to access paths outside \
the working directory.";
pub fn routes() -> Router<AppState> {
Router::new()
.route("/api/agent/chat", post(chat_handler))
.route("/api/agent/approve", post(approve_handler))
.route("/api/agent/status", get(status_handler))
.layer(DefaultBodyLimit::max(AGENT_CHAT_BODY_LIMIT_BYTES))
}
#[derive(Debug, Deserialize)]
struct ChatRequest {
/// The user's prompt for this turn.
message: String,
/// Existing session id to continue; a new one is minted when absent.
#[serde(default)]
session_id: Option<String>,
/// Aggregated model id; falls back to the configured agent model.
#[serde(default)]
model: Option<String>,
/// Permission mode: "default" | "accept_edits" | "full_access".
#[serde(default)]
permission_mode: Option<String>,
}
#[derive(Debug, Deserialize)]
struct ApproveRequest {
request_id: String,
approved: bool,
}
/// Resolved caller identity for an agent request.
#[derive(Debug, Clone)]
struct AgentAuth {
/// `None` for admin/global-token callers; `Some(id)` for user JWTs.
user_id: Option<i64>,
}
fn extract_bearer_token(headers: &HeaderMap) -> Option<&str> {
headers
.get(axum::http::header::AUTHORIZATION)
.and_then(|v| v.to_str().ok())
.and_then(|v| v.strip_prefix("Bearer "))
.map(str::trim)
.filter(|t| !t.is_empty())
}
/// Authenticate the caller. Admin token / proxy token map to an admin
/// (user-less) session; a valid user/admin JWT maps to that user's id.
async fn resolve_auth(
headers: &HeaderMap,
state: &AppState,
) -> Result<AgentAuth, (StatusCode, Json<Value>)> {
let unauthorized = || {
(
StatusCode::UNAUTHORIZED,
Json(json!({ "error": "Unauthorized" })),
)
};
let token = extract_bearer_token(headers).ok_or_else(unauthorized)?;
if token == state.config.auth.auth_token || token == state.runtime_proxy_token() {
return Ok(AgentAuth { user_id: None });
}
let claims = validate_jwt(&state.config.auth.jwt_secret, token).map_err(|_| unauthorized())?;
if claims.role != "admin" && claims.role != "user" {
return Err((StatusCode::FORBIDDEN, Json(json!({ "error": "Forbidden" }))));
}
let user_id = claims
.sub
.parse::<i64>()
.map_err(|_| (StatusCode::UNAUTHORIZED, Json(json!({ "error": "Invalid user id" }))))?;
Ok(AgentAuth { user_id: Some(user_id) })
}
/// Send one SSE event; returns false if the receiver (client) has gone away.
fn send_sse(tx: &UnboundedSender<Result<Event, Infallible>>, payload: Value) -> bool {
tx.send(Ok(Event::default().data(payload.to_string()))).is_ok()
}
/// Resolve BoosAPI's own base URL (no `/v1` suffix — the OpenAI provider appends
/// `/v1/chat/completions`).
fn boosapi_base(state: &AppState) -> String {
let host = match state.config.server.host.as_str() {
"0.0.0.0" | "::" => "127.0.0.1",
other => other,
};
format!("http://{}:{}", host, state.config.server.port)
}
/// Build the SDK permission callback that enforces sandbox path safety and the
/// approval flow. The callback runs inside the agent loop for every tool call.
///
/// Order of checks:
/// 1. Sandbox: any path argument that escapes `cwd` is hard-denied immediately.
/// 2. Risk + mode: read-only (and, per mode, writes) auto-allow; otherwise emit
/// an `approval_request` SSE event and block until the user responds (or the
/// approval times out, which denies).
fn build_can_use_tool(
sse_tx: UnboundedSender<Result<Event, Infallible>>,
cwd: std::path::PathBuf,
mode: PermissionMode,
) -> open_agent_sdk::types::CanUseToolFn {
Arc::new(move |tool_name: &str, input: &Value| {
let sse_tx = sse_tx.clone();
let cwd = cwd.clone();
let tool_name = tool_name.to_string();
let input = input.clone();
Box::pin(async move {
// Gate 1: sandbox path safety (always enforced, even in full access).
if let Err(reason) = sandbox::check_tool_paths(&tool_name, &input, &cwd) {
send_sse(
&sse_tx,
json!({
"type": "tool_denied",
"data": { "name": tool_name, "reason": reason }
}),
);
return PermissionDecision::Deny(reason);
}
// Gate 2: risk + permission mode.
let risk = classify_tool_risk(&tool_name);
match decide_permission(mode, risk) {
PermissionAction::AutoAllow => PermissionDecision::Allow,
PermissionAction::RequireApproval => {
let request_id = Uuid::new_v4().to_string();
// `_guard` removes the registry entry when this future ends
// (normal completion or drop on session abort) — no leak.
let (entry, _guard) = approval::register(&request_id);
send_sse(
&sse_tx,
json!({
"type": "approval_request",
"data": {
"request_id": request_id,
"name": tool_name,
"input": input,
"risk": format!("{risk:?}"),
}
}),
);
// Single source of truth: the settled atomic state decides
// allow vs deny. `resolve` reports back to the frontend
// whether its CAS won, so the two can never disagree.
let settled = approval::wait_for_decision(&entry, APPROVAL_TIMEOUT).await;
let (decision, wire) = match settled {
SettledState::Approved => (PermissionDecision::Allow, "approved"),
SettledState::Denied => {
(PermissionDecision::Deny("Denied by user".to_string()), "denied")
}
SettledState::TimedOut => (
PermissionDecision::Deny("Approval timed out".to_string()),
"timed_out",
),
};
// Tell the client how this prompt actually resolved, so a
// late click (which the /approve call already reported as
// ok:false) can dismiss the modal with the real outcome.
send_sse(
&sse_tx,
json!({
"type": "approval_resolved",
"data": { "request_id": request_id, "decision": wire }
}),
);
decision
}
}
})
})
}
#[allow(clippy::type_complexity)]
async fn chat_handler(
State(state): State<AppState>,
headers: HeaderMap,
Json(body): Json<ChatRequest>,
) -> Result<Sse<impl Stream<Item = Result<Event, Infallible>>>, (StatusCode, Json<Value>)> {
let auth = resolve_auth(&headers, &state).await?;
if body.message.trim().is_empty() {
return Err((
StatusCode::BAD_REQUEST,
Json(json!({ "error": "message is required" })),
));
}
let session_id = body
.session_id
.as_deref()
.map(str::trim)
.filter(|s| !s.is_empty())
.map(ToOwned::to_owned)
.unwrap_or_else(|| Uuid::new_v4().to_string());
let mode = PermissionMode::from_wire(body.permission_mode.as_deref().unwrap_or("default"));
let model = body
.model
.as_deref()
.map(str::trim)
.filter(|s| !s.is_empty())
.map(ToOwned::to_owned)
.unwrap_or_else(|| state.config.comfyui.agent_model.clone());
// Per-session sandbox working directory.
let cwd = match sandbox::ensure_session_dir(&session_id) {
Ok(dir) => dir,
Err(e) => {
return Err((
StatusCode::INTERNAL_SERVER_ERROR,
Json(json!({ "error": format!("failed to create session sandbox: {e}") })),
));
}
};
// Persist (idempotently) the session row before streaming.
if let Err(e) = session_store::ensure_session(
&state.db,
&session_id,
auth.user_id,
&model,
&format!("{mode:?}").to_lowercase(),
)
.await
{
tracing::warn!(%e, "failed to ensure agent session row");
}
// Route the agent's LLM calls back through BoosAPI's own aggregation using
// the built-in downstream key.
let base_url = boosapi_base(&state);
let internal_key = state.builtin_keys.comfyui_agent.1.clone();
let (tx, rx) = unbounded_channel::<Result<Event, Infallible>>();
let db = state.db.clone();
let prompt = body.message;
let session_for_event = session_id.clone();
tokio::spawn(async move {
// First event: hand the (possibly newly minted) session id to the client.
send_sse(
&tx,
json!({ "type": "session", "data": { "session_id": session_for_event, "model": model } }),
);
let provider: Arc<dyn LLMProvider> = Arc::new(OpenAIProvider::new(
reqwest::Client::new(),
internal_key,
base_url,
Default::default(),
));
let can_use_tool = build_can_use_tool(tx.clone(), cwd.clone(), mode);
// Replace the SDK's built-in Bash (a bare subprocess) with an
// OS-sandboxed one confined to this session's directory. Registered as
// a custom tool, it overrides the built-in by name; review modes run it
// under bwrap, FullAccess runs it unconfined with audit logging.
let sandboxed_bash: Arc<dyn open_agent_sdk::types::Tool> =
Arc::new(SandboxedBashTool::new(cwd.clone(), mode));
let agent = Agent::new(AgentOptions {
provider: Some(provider),
model: Some(model.clone()),
cwd: Some(cwd.to_string_lossy().to_string()),
system_prompt: Some(SYSTEM_PROMPT.to_string()),
max_turns: Some(MAX_TURNS),
can_use_tool: Some(can_use_tool),
custom_tools: vec![sandboxed_bash],
session_id: Some(session_id.clone()),
..Default::default()
})
.await;
let mut agent = match agent {
Ok(a) => a,
Err(e) => {
send_sse(&tx, json!({ "type": "error", "data": { "message": e } }));
send_sse(&tx, json!({ "type": "done" }));
return;
}
};
let (mut rx_msg, handle) = agent.query(&prompt).await;
while let Some(event) = rx_msg.recv().await {
// Stop early if the client disconnected.
if tx.is_closed() {
break;
}
forward_sdk_event(&tx, &db, &session_id, event).await;
}
let _ = handle.await;
agent.close().await;
send_sse(&tx, json!({ "type": "done" }));
});
Ok(Sse::new(UnboundedReceiverStream::new(rx)))
}
/// Translate one SDK message into SSE event(s), and persist usage on Result.
async fn forward_sdk_event(
tx: &UnboundedSender<Result<Event, Infallible>>,
db: &sqlx::SqlitePool,
session_id: &str,
event: SDKMessage,
) {
match event {
SDKMessage::Assistant { message, .. } => {
for block in &message.content {
match block {
ContentBlock::Text { text } if !text.is_empty() => {
send_sse(tx, json!({ "type": "text", "data": { "text": text } }));
}
ContentBlock::ToolUse { id, name, input } => {
send_sse(
tx,
json!({ "type": "tool_use", "data": { "id": id, "name": name, "input": input } }),
);
}
ContentBlock::Thinking { thinking, .. } if !thinking.is_empty() => {
send_sse(tx, json!({ "type": "thinking", "data": { "thinking": thinking } }));
}
_ => {}
}
}
}
SDKMessage::ToolResult { tool_use_id, tool_name, content, is_error } => {
send_sse(
tx,
json!({
"type": "tool_result",
"data": { "tool_use_id": tool_use_id, "name": tool_name, "content": content, "is_error": is_error }
}),
);
}
SDKMessage::Result { text, usage, num_turns, cost_usd, .. } => {
// Persist this turn's accounting (user prompt + assistant reply ≈ 2 msgs).
let delta = UsageDelta {
input_tokens: usage.input_tokens as i64,
output_tokens: usage.output_tokens as i64,
cost_usd,
num_turns: num_turns as i64,
};
if let Err(e) = session_store::record_turn(db, session_id, delta, 2).await {
tracing::warn!(%e, "failed to record agent turn usage");
}
send_sse(
tx,
json!({
"type": "result",
"data": {
"text": text,
"num_turns": num_turns,
"input_tokens": usage.input_tokens,
"output_tokens": usage.output_tokens,
"total_tokens": usage.input_tokens + usage.output_tokens,
"cost_usd": cost_usd,
}
}),
);
}
SDKMessage::Error { message } => {
send_sse(tx, json!({ "type": "error", "data": { "message": message } }));
}
_ => {}
}
}
async fn approve_handler(
State(state): State<AppState>,
headers: HeaderMap,
Json(body): Json<ApproveRequest>,
) -> Result<Json<Value>, (StatusCode, Json<Value>)> {
// Auth required, but any authenticated caller may answer the prompt for
// their own running session (approvals are keyed by an unguessable uuid).
resolve_auth(&headers, &state).await?;
let outcome = if body.approved { ApprovalOutcome::Approve } else { ApprovalOutcome::Deny };
let delivered = approval::resolve(&body.request_id, outcome);
Ok(Json(json!({ "ok": delivered })))
}
async fn status_handler(
State(state): State<AppState>,
headers: HeaderMap,
axum::extract::Query(q): axum::extract::Query<StatusQuery>,
) -> Result<Json<Value>, (StatusCode, Json<Value>)> {
let auth = resolve_auth(&headers, &state).await?;
let session = match q.session_id.as_deref().filter(|s| !s.is_empty()) {
Some(sid) => session_store::get_session(&state.db, sid, auth.user_id)
.await
.map_err(|e| {
(
StatusCode::INTERNAL_SERVER_ERROR,
Json(json!({ "error": e.to_string() })),
)
})?,
None => None,
};
Ok(Json(json!({
"ok": true,
"engine": "open-agent-sdk",
"default_model": state.config.comfyui.agent_model,
"session": session,
})))
}
#[derive(Debug, Deserialize)]
struct StatusQuery {
#[serde(default)]
session_id: Option<String>,
}
src/routes/auth.rs
+123 -80
View File
@@ -19,6 +19,11 @@ use serde_json::{json, Value};
use std::net::{IpAddr, SocketAddr}; use std::net::{IpAddr, SocketAddr};
use tracing::{info, warn}; use tracing::{info, warn};
/// Default spending cap (USD) granted to a newly created user's auto-generated
/// API key. Per the billing design (新用户默认 $1 额度), new users start with a
/// $1 allowance on their default downstream key.
pub const DEFAULT_NEW_USER_MAX_COST_USD: f64 = 1.0;
// ── Request / Response types ───────────────────────────────────────── // ── Request / Response types ─────────────────────────────────────────
#[derive(Debug, Deserialize)] #[derive(Debug, Deserialize)]
@@ -108,6 +113,21 @@ async fn register(
) -> AppResult<Json<Value>> { ) -> AppResult<Json<Value>> {
info!("Registering user: {}", payload.email); info!("Registering user: {}", payload.email);
// Admin can disable self-service registration from 系统设置.
let registration_disabled: Option<String> =
sqlx::query_scalar("SELECT value FROM settings WHERE key = 'runtime.registration_disabled'")
.fetch_optional(&*state.db)
.await?;
if registration_disabled
.as_deref()
.map(|v| matches!(v.trim(), "true" | "1"))
.unwrap_or(false)
{
return Err(AppError::Forbidden(
"用户注册已被管理员关闭".into(),
));
}
if payload.email.trim().is_empty() || payload.username.trim().is_empty() { if payload.email.trim().is_empty() || payload.username.trim().is_empty() {
return Err(AppError::BadRequest( return Err(AppError::BadRequest(
"email and username are required".into(), "email and username are required".into(),
@@ -177,11 +197,12 @@ async fn register(
let default_key = format!("sk-user-{}", uuid::Uuid::new_v4().simple()); let default_key = format!("sk-user-{}", uuid::Uuid::new_v4().simple());
let default_key_name = format!("{} 的默认密钥", payload.username.trim()); let default_key_name = format!("{} 的默认密钥", payload.username.trim());
sqlx::query( sqlx::query(
"INSERT INTO downstream_api_keys (name, key, user_id, enabled) VALUES (?, ?, ?, 1)", "INSERT INTO downstream_api_keys (name, key, user_id, enabled, max_cost) VALUES (?, ?, ?, 1, ?)",
) )
.bind(&default_key_name) .bind(&default_key_name)
.bind(&default_key) .bind(&default_key)
.bind(user_id) .bind(user_id)
.bind(DEFAULT_NEW_USER_MAX_COST_USD)
.execute(&mut *tx) .execute(&mut *tx)
.await?; .await?;
tx.commit().await?; tx.commit().await?;
@@ -237,14 +258,17 @@ async fn login(
let user_agent = user_agent_from_headers(&headers); let user_agent = user_agent_from_headers(&headers);
let email = payload.email.trim().to_string(); let email = payload.email.trim().to_string();
let user: User = if let Some(user) = sqlx::query_as::<_, User>("SELECT * FROM users WHERE email = ?") let user: User = if let Some(user) =
sqlx::query_as::<_, User>("SELECT * FROM users WHERE email = ?")
.bind(&email) .bind(&email)
.fetch_optional(&*state.db) .fetch_optional(&*state.db)
.await? .await?
{ {
user user
} else { } else {
audit_user_login(&state, LoginAuditEvent { audit_user_login(
&state,
LoginAuditEvent {
method: LoginMethod::Password, method: LoginMethod::Password,
success: false, success: false,
user: None, user: None,
@@ -253,13 +277,16 @@ async fn login(
client_ip: &client_ip, client_ip: &client_ip,
user_agent: user_agent.as_deref(), user_agent: user_agent.as_deref(),
reason: Some("Invalid email or password"), reason: Some("Invalid email or password"),
}) },
)
.await; .await;
return Err(AppError::Unauthorized("Invalid email or password".into())); return Err(AppError::Unauthorized("Invalid email or password".into()));
}; };
if user.status != "active" { if user.status != "active" {
audit_user_login(&state, LoginAuditEvent { audit_user_login(
&state,
LoginAuditEvent {
method: LoginMethod::Password, method: LoginMethod::Password,
success: false, success: false,
user: Some(&user), user: Some(&user),
@@ -268,32 +295,19 @@ async fn login(
client_ip: &client_ip, client_ip: &client_ip,
user_agent: user_agent.as_deref(), user_agent: user_agent.as_deref(),
reason: Some("Account is disabled"), reason: Some("Account is disabled"),
}) },
)
.await; .await;
return Err(AppError::Forbidden("Account is disabled".into())); return Err(AppError::Forbidden("Account is disabled".into()));
} }
if user.role == "admin" {
audit_user_login(&state, LoginAuditEvent {
method: LoginMethod::Password,
success: false,
user: Some(&user),
identifier: Some(&email),
api_key: None,
client_ip: &client_ip,
user_agent: user_agent.as_deref(),
reason: Some("Admin users must sign in with the admin API token"),
})
.await;
return Err(AppError::Forbidden(
"Admin users must sign in with the admin API token".into(),
));
}
let valid = verify_password(&payload.password, &user.password_hash) let valid = verify_password(&payload.password, &user.password_hash)
.map_err(|e| AppError::Internal(anyhow::anyhow!("Password verification failed: {e}")))?; .map_err(|e| AppError::Internal(anyhow::anyhow!("Password verification failed: {e}")))?;
if !valid { if !valid {
audit_user_login(&state, LoginAuditEvent { audit_user_login(
&state,
LoginAuditEvent {
method: LoginMethod::Password, method: LoginMethod::Password,
success: false, success: false,
user: Some(&user), user: Some(&user),
@@ -302,7 +316,8 @@ async fn login(
client_ip: &client_ip, client_ip: &client_ip,
user_agent: user_agent.as_deref(), user_agent: user_agent.as_deref(),
reason: Some("Invalid email or password"), reason: Some("Invalid email or password"),
}) },
)
.await; .await;
return Err(AppError::Unauthorized("Invalid email or password".into())); return Err(AppError::Unauthorized("Invalid email or password".into()));
} }
@@ -315,7 +330,9 @@ async fn login(
) )
.map_err(|e| AppError::Internal(anyhow::anyhow!("Failed to generate JWT: {e}")))?; .map_err(|e| AppError::Internal(anyhow::anyhow!("Failed to generate JWT: {e}")))?;
audit_user_login(&state, LoginAuditEvent { audit_user_login(
&state,
LoginAuditEvent {
method: LoginMethod::Password, method: LoginMethod::Password,
success: true, success: true,
user: Some(&user), user: Some(&user),
@@ -324,7 +341,8 @@ async fn login(
client_ip: &client_ip, client_ip: &client_ip,
user_agent: user_agent.as_deref(), user_agent: user_agent.as_deref(),
reason: None, reason: None,
}) },
)
.await; .await;
Ok(Json(json!({ Ok(Json(json!({
@@ -365,7 +383,9 @@ async fn login_api_key(
let user_agent = user_agent_from_headers(&headers); let user_agent = user_agent_from_headers(&headers);
let key = payload.api_key.trim(); let key = payload.api_key.trim();
if key.is_empty() { if key.is_empty() {
audit_user_login(&state, LoginAuditEvent { audit_user_login(
&state,
LoginAuditEvent {
method: LoginMethod::ApiKey, method: LoginMethod::ApiKey,
success: false, success: false,
user: None, user: None,
@@ -374,7 +394,8 @@ async fn login_api_key(
client_ip: &client_ip, client_ip: &client_ip,
user_agent: user_agent.as_deref(), user_agent: user_agent.as_deref(),
reason: Some("api_key is required"), reason: Some("api_key is required"),
}) },
)
.await; .await;
return Err(AppError::BadRequest("api_key is required".into())); return Err(AppError::BadRequest("api_key is required".into()));
} }
@@ -390,7 +411,9 @@ async fn login_api_key(
api_key api_key
} else { } else {
let masked_key = mask_api_key(key); let masked_key = mask_api_key(key);
audit_user_login(&state, LoginAuditEvent { audit_user_login(
&state,
LoginAuditEvent {
method: LoginMethod::ApiKey, method: LoginMethod::ApiKey,
success: false, success: false,
user: None, user: None,
@@ -399,14 +422,17 @@ async fn login_api_key(
client_ip: &client_ip, client_ip: &client_ip,
user_agent: user_agent.as_deref(), user_agent: user_agent.as_deref(),
reason: Some("Invalid API key"), reason: Some("Invalid API key"),
}) },
)
.await; .await;
return Err(AppError::Unauthorized("Invalid API key".into())); return Err(AppError::Unauthorized("Invalid API key".into()));
}; };
let user_id = if let Some(user_id) = api_key.user_id { let user_id = if let Some(user_id) = api_key.user_id {
user_id user_id
} else { } else {
audit_user_login(&state, LoginAuditEvent { audit_user_login(
&state,
LoginAuditEvent {
method: LoginMethod::ApiKey, method: LoginMethod::ApiKey,
success: false, success: false,
user: None, user: None,
@@ -415,19 +441,25 @@ async fn login_api_key(
client_ip: &client_ip, client_ip: &client_ip,
user_agent: user_agent.as_deref(), user_agent: user_agent.as_deref(),
reason: Some("API key is not bound to a user"), reason: Some("API key is not bound to a user"),
}) },
)
.await; .await;
return Err(AppError::Unauthorized("API key is not bound to a user".into())); return Err(AppError::Unauthorized(
"API key is not bound to a user".into(),
));
}; };
let user: User = if let Some(user) = sqlx::query_as::<_, User>("SELECT * FROM users WHERE id = ?") let user: User = if let Some(user) =
sqlx::query_as::<_, User>("SELECT * FROM users WHERE id = ?")
.bind(user_id) .bind(user_id)
.fetch_optional(&*state.db) .fetch_optional(&*state.db)
.await? .await?
{ {
user user
} else { } else {
audit_user_login(&state, LoginAuditEvent { audit_user_login(
&state,
LoginAuditEvent {
method: LoginMethod::ApiKey, method: LoginMethod::ApiKey,
success: false, success: false,
user: None, user: None,
@@ -436,13 +468,16 @@ async fn login_api_key(
client_ip: &client_ip, client_ip: &client_ip,
user_agent: user_agent.as_deref(), user_agent: user_agent.as_deref(),
reason: Some("User not found"), reason: Some("User not found"),
}) },
)
.await; .await;
return Err(AppError::Unauthorized("User not found".into())); return Err(AppError::Unauthorized("User not found".into()));
}; };
if user.status != "active" { if user.status != "active" {
audit_user_login(&state, LoginAuditEvent { audit_user_login(
&state,
LoginAuditEvent {
method: LoginMethod::ApiKey, method: LoginMethod::ApiKey,
success: false, success: false,
user: Some(&user), user: Some(&user),
@@ -451,26 +486,11 @@ async fn login_api_key(
client_ip: &client_ip, client_ip: &client_ip,
user_agent: user_agent.as_deref(), user_agent: user_agent.as_deref(),
reason: Some("Account is disabled"), reason: Some("Account is disabled"),
}) },
)
.await; .await;
return Err(AppError::Forbidden("Account is disabled".into())); return Err(AppError::Forbidden("Account is disabled".into()));
} }
if user.role == "admin" {
audit_user_login(&state, LoginAuditEvent {
method: LoginMethod::ApiKey,
success: false,
user: Some(&user),
identifier: Some(&user.email),
api_key: Some(&api_key),
client_ip: &client_ip,
user_agent: user_agent.as_deref(),
reason: Some("Admin users must sign in with the admin API token"),
})
.await;
return Err(AppError::Forbidden(
"Admin users must sign in with the admin API token".into(),
));
}
info!("Login via API key: user_id={}", user.id); info!("Login via API key: user_id={}", user.id);
@@ -482,7 +502,9 @@ async fn login_api_key(
) )
.map_err(|e| AppError::Internal(anyhow::anyhow!("Failed to generate JWT: {e}")))?; .map_err(|e| AppError::Internal(anyhow::anyhow!("Failed to generate JWT: {e}")))?;
audit_user_login(&state, LoginAuditEvent { audit_user_login(
&state,
LoginAuditEvent {
method: LoginMethod::ApiKey, method: LoginMethod::ApiKey,
success: true, success: true,
user: Some(&user), user: Some(&user),
@@ -491,7 +513,8 @@ async fn login_api_key(
client_ip: &client_ip, client_ip: &client_ip,
user_agent: user_agent.as_deref(), user_agent: user_agent.as_deref(),
reason: None, reason: None,
}) },
)
.await; .await;
Ok(Json(json!({ Ok(Json(json!({
@@ -747,7 +770,11 @@ async fn audit_user_login(state: &AppState, audit: LoginAuditEvent<'_>) {
.bind(message_parts.join(" · ")) .bind(message_parts.join(" · "))
.bind(level) .bind(level)
.bind(audit.user.map(|user| user.id)) .bind(audit.user.map(|user| user.id))
.bind(if audit.user.is_some() { Some("user") } else { None::<&str> }) .bind(if audit.user.is_some() {
Some("user")
} else {
None::<&str>
})
.execute(&*state.db) .execute(&*state.db)
.await .await
{ {
@@ -864,17 +891,17 @@ fn normalize_ip_token(raw: &str) -> Option<String> {
token = host; token = host;
} }
} }
token token.parse::<IpAddr>().map(|ip| ip.to_string()).ok()
.parse::<IpAddr>()
.map(|ip| ip.to_string())
.ok()
} }
fn truncate_for_audit(value: &str, max_chars: usize) -> String { fn truncate_for_audit(value: &str, max_chars: usize) -> String {
if value.chars().count() <= max_chars { if value.chars().count() <= max_chars {
return value.to_string(); return value.to_string();
} }
let mut truncated = value.chars().take(max_chars.saturating_sub(1)).collect::<String>(); let mut truncated = value
.chars()
.take(max_chars.saturating_sub(1))
.collect::<String>();
truncated.push('…'); truncated.push('…');
truncated truncated
} }
@@ -1018,7 +1045,9 @@ mod tests {
template_proxy_url: None, template_proxy_url: None,
}, },
comfyui: Default::default(), comfyui: Default::default(),
pixelle_video: Default::default(),
payment: Default::default(), payment: Default::default(),
pixelle_video: Default::default(),
}, },
pool, pool,
BuiltinKeys { BuiltinKeys {
@@ -1055,7 +1084,7 @@ mod tests {
} }
#[tokio::test] #[tokio::test]
async fn password_login_rejects_admin_users() { async fn password_login_returns_admin_role_for_admin_users() {
let state = test_state().await; let state = test_state().await;
let password_hash = hash_password("admin-password").expect("password hash"); let password_hash = hash_password("admin-password").expect("password hash");
sqlx::query( sqlx::query(
@@ -1069,8 +1098,8 @@ mod tests {
.await .await
.expect("insert admin user"); .expect("insert admin user");
let err = login( let Json(value) = login(
State(state), State(state.clone()),
test_addr(), test_addr(),
empty_headers(), empty_headers(),
Json(LoginRequest { Json(LoginRequest {
@@ -1079,9 +1108,12 @@ mod tests {
}), }),
) )
.await .await
.expect_err("admin password login must be rejected"); .expect("admin password login should succeed");
assert!(matches!(err, AppError::Forbidden(message) if message.contains("admin API token"))); assert_eq!(value["user"]["role"], "admin");
let token = value["token"].as_str().expect("token");
let claims = validate_jwt(&state.config.auth.jwt_secret, token).expect("valid jwt");
assert_eq!(claims.role, "admin");
} }
#[tokio::test] #[tokio::test]
@@ -1147,7 +1179,8 @@ mod tests {
.await .await
.expect("regular user password login succeeds"); .expect("regular user password login succeeds");
let (event_type, title, message, related_id, related_type) = latest_audit_event(&state).await; let (event_type, title, message, related_id, related_type) =
latest_audit_event(&state).await;
assert_eq!(event_type, "user_login"); assert_eq!(event_type, "user_login");
assert!(title.contains("用户登录成功")); assert!(title.contains("用户登录成功"));
assert!(title.contains("Regular User <audit@example.test>")); assert!(title.contains("Regular User <audit@example.test>"));
@@ -1160,7 +1193,7 @@ mod tests {
} }
#[tokio::test] #[tokio::test]
async fn api_key_login_rejects_admin_role() { async fn api_key_login_returns_admin_role_for_admin_user() {
let state = test_state().await; let state = test_state().await;
let password_hash = hash_password("unused-password").expect("password hash"); let password_hash = hash_password("unused-password").expect("password hash");
let user_id = sqlx::query( let user_id = sqlx::query(
@@ -1186,8 +1219,8 @@ mod tests {
.await .await
.expect("insert bound api key"); .expect("insert bound api key");
let err = login_api_key( let Json(value) = login_api_key(
State(state), State(state.clone()),
test_addr(), test_addr(),
empty_headers(), empty_headers(),
Json(LoginApiKeyRequest { Json(LoginApiKeyRequest {
@@ -1195,14 +1228,17 @@ mod tests {
}), }),
) )
.await .await
.expect_err("admin api key login must be rejected"); .expect("admin api key login should succeed");
assert!(matches!(err, AppError::Forbidden(message) if message.contains("admin API token"))); assert_eq!(value["user"]["role"], "admin");
let token = value["token"].as_str().expect("token");
let claims = validate_jwt(&state.config.auth.jwt_secret, token).expect("valid jwt");
assert_eq!(claims.role, "admin");
assert!(user_id > 0); assert!(user_id > 0);
} }
#[tokio::test] #[tokio::test]
async fn api_key_login_rejects_latest_admin_role_after_promotion() { async fn api_key_login_returns_latest_admin_role_after_promotion() {
let state = test_state().await; let state = test_state().await;
let password_hash = hash_password("unused-password").expect("password hash"); let password_hash = hash_password("unused-password").expect("password hash");
let user_id = sqlx::query( let user_id = sqlx::query(
@@ -1234,8 +1270,8 @@ mod tests {
.await .await
.expect("promote user to admin"); .expect("promote user to admin");
let err = login_api_key( let Json(value) = login_api_key(
State(state), State(state.clone()),
test_addr(), test_addr(),
empty_headers(), empty_headers(),
Json(LoginApiKeyRequest { Json(LoginApiKeyRequest {
@@ -1243,9 +1279,12 @@ mod tests {
}), }),
) )
.await .await
.expect_err("api key login must use latest role and reject admin"); .expect("api key login uses latest role and accepts admin");
assert!(matches!(err, AppError::Forbidden(message) if message.contains("admin API token"))); assert_eq!(value["user"]["role"], "admin");
let token = value["token"].as_str().expect("token");
let claims = validate_jwt(&state.config.auth.jwt_secret, token).expect("valid jwt");
assert_eq!(claims.role, "admin");
assert!(user_id > 0); assert!(user_id > 0);
} }
@@ -1333,7 +1372,8 @@ mod tests {
.await .await
.expect("regular api key login succeeds"); .expect("regular api key login succeeds");
let (event_type, title, message, related_id, related_type) = latest_audit_event(&state).await; let (event_type, title, message, related_id, related_type) =
latest_audit_event(&state).await;
assert_eq!(event_type, "user_login"); assert_eq!(event_type, "user_login");
assert!(title.contains("用户登录成功")); assert!(title.contains("用户登录成功"));
assert!(title.contains("Regular User <key-audit@example.test>")); assert!(title.contains("Regular User <key-audit@example.test>"));
@@ -1363,7 +1403,10 @@ mod tests {
let Json(_) = login( let Json(_) = login(
State(state.clone()), State(state.clone()),
test_addr(), test_addr(),
headers_with("x-forwarded-for", "2a09:bac2:3918:16dc::247:4d, 203.0.113.9"), headers_with(
"x-forwarded-for",
"2a09:bac2:3918:16dc::247:4d, 203.0.113.9",
),
Json(LoginRequest { Json(LoginRequest {
email: "ipv4@example.test".into(), email: "ipv4@example.test".into(),
password: "user-password".into(), password: "user-password".into(),
src/routes/comfy_cloud_adapter.rs
+229
View File
@@ -0,0 +1,229 @@
use crate::error::{AppError, AppResult};
use crate::services::comfy_cloud::site::resolve_comfy_cloud_site;
use crate::services::comfy_cloud::translate::comfy_cloud_job_to_history;
use crate::AppState;
use axum::{
body::Body,
extract::{Path, RawQuery, State},
http::{header, StatusCode},
response::Response,
routing::{get, post},
Json, Router,
};
use serde_json::Value;
pub fn routes() -> Router<AppState> {
Router::new()
.route("/comfy-cloud/prompt", post(submit_prompt))
.route("/comfy-cloud/history/{prompt_id}", get(get_history))
.route("/comfy-cloud/view", get(get_view))
}
fn client() -> reqwest::Client {
reqwest::Client::builder()
.timeout(std::time::Duration::from_secs(120))
.build()
.unwrap_or_else(|_| reqwest::Client::new())
}
async fn submit_prompt(
State(state): State<AppState>,
Json(body): Json<Value>,
) -> AppResult<Json<Value>> {
let (base_url, api_key) = resolve_comfy_cloud_site(&state.db).await?;
let resp = client()
.post(format!("{base_url}/api/prompt"))
.header("X-API-Key", api_key)
.json(&body)
.send()
.await
.map_err(|e| AppError::UpstreamError(e.to_string()))?;
let status = resp.status();
let text = resp.text().await.map_err(|e| AppError::UpstreamError(e.to_string()))?;
if !status.is_success() {
return Err(AppError::UpstreamError(format!("Comfy Cloud prompt [{status}]: {text}")));
}
let value: Value = serde_json::from_str(&text).unwrap_or_else(|_| serde_json::json!({ "body": text }));
Ok(Json(value))
}
async fn fetch_history(db: &sqlx::SqlitePool, prompt_id: &str) -> AppResult<Value> {
let (base_url, api_key) = resolve_comfy_cloud_site(db).await?;
let http = client();
let status_resp = http
.get(format!("{base_url}/api/job/{prompt_id}/status"))
.header("X-API-Key", &api_key)
.send().await
.map_err(|e| AppError::UpstreamError(e.to_string()))?;
if !status_resp.status().is_success() {
let st = status_resp.status();
let body = status_resp.text().await.unwrap_or_default();
return Err(AppError::UpstreamError(format!("Comfy Cloud status [{st}]: {body}")));
}
let status_json: Value = status_resp.json().await.map_err(|e| AppError::UpstreamError(e.to_string()))?;
let status = status_json.get("status").and_then(Value::as_str).unwrap_or("in_progress");
if status != "completed" {
return Ok(comfy_cloud_job_to_history(prompt_id, status, None));
}
let detail_resp = http
.get(format!("{base_url}/api/jobs/{prompt_id}"))
.header("X-API-Key", &api_key)
.send().await
.map_err(|e| AppError::UpstreamError(e.to_string()))?;
if !detail_resp.status().is_success() {
let st = detail_resp.status();
let body = detail_resp.text().await.unwrap_or_default();
return Err(AppError::UpstreamError(format!("Comfy Cloud jobs [{st}]: {body}")));
}
let detail_json: Value = detail_resp.json().await.map_err(|e| AppError::UpstreamError(e.to_string()))?;
let outputs = detail_json.get("outputs");
Ok(comfy_cloud_job_to_history(prompt_id, status, outputs))
}
async fn get_history(
State(state): State<AppState>,
Path(prompt_id): Path<String>,
) -> AppResult<Json<Value>> {
Ok(Json(fetch_history(&state.db, &prompt_id).await?))
}
async fn fetch_view(db: &sqlx::SqlitePool, query: Option<&str>) -> AppResult<(String, Vec<u8>)> {
let (base_url, api_key) = resolve_comfy_cloud_site(db).await?;
let q = query.unwrap_or("");
let url = if q.is_empty() { format!("{base_url}/api/view") } else { format!("{base_url}/api/view?{q}") };
let resp = client()
.get(url)
.header("X-API-Key", api_key)
.send().await
.map_err(|e| AppError::UpstreamError(e.to_string()))?;
if !resp.status().is_success() {
let st = resp.status();
return Err(AppError::UpstreamError(format!("Comfy Cloud view [{st}]")));
}
let mime = resp
.headers()
.get(header::CONTENT_TYPE)
.and_then(|v| v.to_str().ok())
.unwrap_or("application/octet-stream")
.to_string();
let bytes = resp.bytes().await.map_err(|e| AppError::UpstreamError(e.to_string()))?.to_vec();
Ok((mime, bytes))
}
async fn get_view(
State(state): State<AppState>,
RawQuery(query): RawQuery,
) -> AppResult<Response> {
let (mime, bytes) = fetch_view(&state.db, query.as_deref()).await?;
Response::builder()
.status(StatusCode::OK)
.header(header::CONTENT_TYPE, mime)
.body(Body::from(bytes))
.map_err(|e| AppError::Internal(anyhow::anyhow!(e)))
}
#[cfg(test)]
mod tests {
use super::*;
use wiremock::matchers::{header as match_header, method, path};
use wiremock::{Mock, MockServer, ResponseTemplate};
use sqlx::sqlite::SqlitePoolOptions;
async fn db_with_site(base_url: &str) -> sqlx::SqlitePool {
let pool = SqlitePoolOptions::new().max_connections(1).connect("sqlite::memory:").await.unwrap();
sqlx::query("CREATE TABLE sites (id INTEGER PRIMARY KEY AUTOINCREMENT, name TEXT, url TEXT NOT NULL, platform TEXT NOT NULL, status TEXT NOT NULL, api_key TEXT, sort_order INTEGER)")
.execute(&pool).await.unwrap();
sqlx::query("INSERT INTO sites (name,url,platform,status,api_key) VALUES ('cc',?,'comfy_cloud','active','key-123')")
.bind(base_url).execute(&pool).await.unwrap();
pool
}
#[tokio::test]
async fn submit_forwards_with_api_key() {
let server = MockServer::start().await;
Mock::given(method("POST"))
.and(path("/api/prompt"))
.and(match_header("X-API-Key", "key-123"))
.respond_with(ResponseTemplate::new(200).set_body_json(serde_json::json!({ "prompt_id": "p1" })))
.mount(&server).await;
let pool = db_with_site(&server.uri()).await;
let (base_url, api_key) = resolve_comfy_cloud_site(&pool).await.unwrap();
let resp = client().post(format!("{base_url}/api/prompt"))
.header("X-API-Key", api_key)
.json(&serde_json::json!({ "prompt": {} }))
.send().await.unwrap();
let v: Value = resp.json().await.unwrap();
assert_eq!(v["prompt_id"], "p1");
}
#[tokio::test]
async fn history_in_progress_then_completed() {
let server = MockServer::start().await;
Mock::given(method("GET"))
.and(path("/api/job/p1/status"))
.and(match_header("X-API-Key", "key-123"))
.respond_with(ResponseTemplate::new(200).set_body_json(serde_json::json!({ "status": "completed" })))
.mount(&server).await;
Mock::given(method("GET"))
.and(path("/api/jobs/p1"))
.respond_with(ResponseTemplate::new(200).set_body_json(serde_json::json!({
"outputs": { "9": { "images": [{ "filename": "a.png", "subfolder": "", "type": "output" }] } }
})))
.mount(&server).await;
let pool = db_with_site(&server.uri()).await;
let history = fetch_history(&pool, "p1").await.unwrap();
assert_eq!(history["p1"]["status"]["completed"], true);
assert_eq!(history["p1"]["outputs"]["9"]["images"][0]["filename"], "a.png");
}
#[tokio::test]
async fn history_completed_job_detail_non_success_errors() {
let server = MockServer::start().await;
Mock::given(method("GET"))
.and(path("/api/job/p1/status"))
.and(match_header("X-API-Key", "key-123"))
.respond_with(ResponseTemplate::new(200).set_body_json(serde_json::json!({ "status": "completed" })))
.mount(&server).await;
Mock::given(method("GET"))
.and(path("/api/jobs/p1"))
.respond_with(ResponseTemplate::new(500).set_body_json(serde_json::json!({ "error": "boom" })))
.mount(&server).await;
let pool = db_with_site(&server.uri()).await;
assert!(fetch_history(&pool, "p1").await.is_err());
}
#[tokio::test]
async fn history_failed_status_maps_to_error() {
let server = MockServer::start().await;
Mock::given(method("GET"))
.and(path("/api/job/p1/status"))
.and(match_header("X-API-Key", "key-123"))
.respond_with(ResponseTemplate::new(200).set_body_json(serde_json::json!({ "status": "failed" })))
.mount(&server).await;
let pool = db_with_site(&server.uri()).await;
let history = fetch_history(&pool, "p1").await.unwrap();
assert_eq!(history["p1"]["status"]["status_str"], "error");
}
#[tokio::test]
async fn view_proxies_file_bytes() {
let server = MockServer::start().await;
Mock::given(method("GET"))
.and(path("/api/view"))
.and(match_header("X-API-Key", "key-123"))
.respond_with(ResponseTemplate::new(200)
.insert_header("content-type", "image/png")
.set_body_bytes(b"PNGDATA".to_vec()))
.mount(&server).await;
let pool = db_with_site(&server.uri()).await;
let (mime, bytes) = fetch_view(&pool, Some("filename=a.png&type=output")).await.unwrap();
assert_eq!(mime, "image/png");
assert_eq!(bytes, b"PNGDATA");
}
}
src/routes/comfyui/mod.rs
+3 -2
View File
@@ -60,8 +60,7 @@ async fn check_auth(state: &AppState, headers: &HeaderMap) -> Result<(), AppErro
// Downstream API key // Downstream API key
if auth.starts_with("sk-") { if auth.starts_with("sk-") {
let proxy_token = state.runtime_proxy_token(); let proxy_token = state.runtime_proxy_token();
let result = let result = authorize_downstream_token(auth, &state.db, Some(&proxy_token))
authorize_downstream_token(auth, &state.db, Some(&proxy_token))
.await .await
.map_err(AppError::Unauthorized)?; .map_err(AppError::Unauthorized)?;
@@ -127,6 +126,8 @@ mod tests {
template_proxy_url: None, template_proxy_url: None,
}, },
comfyui: ComfyUIConfig::default(), comfyui: ComfyUIConfig::default(),
payment: Default::default(),
pixelle_video: Default::default(),
}, },
pool, pool,
BuiltinKeys { BuiltinKeys {
src/routes/comfyui_agent.rs
+288 -39
View File
@@ -16,47 +16,30 @@ use tokio::sync::mpsc::{unbounded_channel, UnboundedSender};
use tokio_stream::{wrappers::UnboundedReceiverStream, StreamExt}; use tokio_stream::{wrappers::UnboundedReceiverStream, StreamExt};
use tracing::info; use tracing::info;
const SYSTEM_PROMPT: &str = r#"你是 BoosAPI 的 AI 视频生成助手，帮用户通过 AI 制作视频。 const SYSTEM_PROMPT: &str = r#"你是 BoosAPI 的 AI 视频生成助手（智能体），帮用户通过 AI 制作视频。
## 规则 ## 工作方式
1. 先用中文与用户讨论脚本构思、视觉风格、角色设定 1. 先用中文与用户讨论脚本构思、视觉风格、角色设定。
2. 用户确认后（说"开始制作"或"生成"），再分步输出结构化内容 2. 用户确认后（说"开始制作"或"生成"），调用工具逐步产出素材。
3. **分两步走：第一步输出角色+场景+TTS，第二步输出 WORKFLOW**（不要一次全出） 3. 你拥有以下工具，应主动按需调用，并根据每次工具返回的结果决定下一步：
- generate_character_images：为角色生成正/背/左/右四视图参考图
- generate_scene_image：生成单张场景/分镜图
- generate_tts：为一句台词合成语音
- build_comfyui_workflow：在素材就绪后交付最终可执行的 ComfyUI 工作流 JSON
## 结构化标记格式 ## 调用原则
严格按照以下格式输出，系统会自动解析并生成图片/TTS： - 一次可调用一个或多个工具；每个角色/场景/台词分别调用对应工具。
- 收到工具结果后继续推进，直到所有素材生成完毕，最后调用 build_comfyui_workflow 交付。
- 图像 prompt 用英文，包含 主体 + 视角 + 细节 + 画质标签。
- 没有用户明确要求时，不要自作主张批量生成；先沟通确认。
【CHARACTER】 ## 兼容降级
name: 林澈 若你所在的模型不支持工具调用，可改用结构化标记输出（系统会解析）：
description: 女宇航员，30岁，冷静坚毅，短发收在头盔内 【CHARACTER】name/description/prompt_front/prompt_back/prompt_left/prompt_right【/CHARACTER】
prompt_front: cinematic full body front view of a female astronaut, white EVA suit, photorealistic 【SCENE】id/description/prompt【/SCENE】
prompt_back: cinematic full body back view of a female astronaut, life support backpack 【TTS】character/text/emotion【/TTS】
prompt_left: cinematic full body left side view of a female astronaut, side utility pouches 【WORKFLOW】```json {...} ```【/WORKFLOW】
prompt_right: cinematic full body right side view of a female astronaut, helmet visor reflection 但只要支持工具调用，就优先使用工具，不要输出这些标记。
【/CHARACTER】
【SCENE】
id: 1
description: 飞船驾驶舱内景
prompt: interior of a sci-fi spacecraft cockpit, holographic displays, cold blue lighting, cinematic
【/SCENE】
【TTS】
character: 林澈
text: 我们准备出舱检查
emotion: 平静
【/TTS】
【WORKFLOW】
```json
{"comfyui_workflow": {}}
```
【/WORKFLOW】
## 关键要求
- prompt_* 用英文，同时包含主体 + 视角 + 细节 + 画质标签
- 不要一次输出太多，先输角色和场景，下次再输工作流
- 如果没有用户明确要求，切勿自作主张输出全部内容
"#; "#;
const AGENT_CHAT_BODY_LIMIT_BYTES: usize = 64 * 1024 * 1024; const AGENT_CHAT_BODY_LIMIT_BYTES: usize = 64 * 1024 * 1024;
@@ -683,6 +666,190 @@ fn send_sse(tx: &UnboundedSender<Result<Event, Infallible>>, payload: Value) ->
.is_ok() .is_ok()
} }
/// OpenAI-style tool definitions advertised to the upstream model so the
/// agent can request image / scene / TTS / workflow generation step by step.
fn agent_tool_definitions() -> Value {
json!([
{
"type": "function",
"function": {
"name": "generate_character_images",
"description": "为一个角色生成四视图（正/背/左/右）参考图。当需要确定角色形象时调用。",
"parameters": {
"type": "object",
"properties": {
"character_name": { "type": "string", "description": "角色名称" },
"description": { "type": "string", "description": "角色整体描述" },
"prompt_front": { "type": "string", "description": "正面视角的图像提示词" },
"prompt_back": { "type": "string", "description": "背面视角的图像提示词" },
"prompt_left": { "type": "string", "description": "左侧视角的图像提示词" },
"prompt_right": { "type": "string", "description": "右侧视角的图像提示词" }
},
"required": ["character_name", "prompt_front"]
}
}
},
{
"type": "function",
"function": {
"name": "generate_scene_image",
"description": "生成一张场景/分镜图。在规划好分镜后逐个调用。",
"parameters": {
"type": "object",
"properties": {
"scene_id": { "type": "integer", "description": "场景编号" },
"description": { "type": "string", "description": "场景描述" },
"prompt": { "type": "string", "description": "场景图像提示词" }
},
"required": ["prompt"]
}
}
},
{
"type": "function",
"function": {
"name": "generate_tts",
"description": "为一句台词生成语音。",
"parameters": {
"type": "object",
"properties": {
"character": { "type": "string", "description": "说话角色" },
"text": { "type": "string", "description": "台词文本" },
"emotion": { "type": "string", "description": "情绪：平静/激动/愤怒/悲伤/恐惧" }
},
"required": ["text"]
}
}
},
{
"type": "function",
"function": {
"name": "build_comfyui_workflow",
"description": "输出最终可执行的 ComfyUI 工作流 JSON。在素材准备完成后调用以交付工作流。",
"parameters": {
"type": "object",
"properties": {
"workflow_json": { "type": "string", "description": "完整的 ComfyUI 工作流 JSON 字符串" }
},
"required": ["workflow_json"]
}
}
}
])
}
/// Map an emotion label to an OpenAI TTS voice.
fn voice_for_emotion(emotion: &str) -> &'static str {
match emotion {
"激动" | "愤怒" => "nova",
"悲伤" | "恐惧" => "shimmer",
_ => "alloy",
}
}
/// Execute one tool call requested by the model. Emits SSE side-effects
/// (image/scene/tts/comfyui_workflow events) and returns a short text result
/// that is fed back to the model as the tool message content.
async fn execute_agent_tool(
tx: &UnboundedSender<Result<Event, Infallible>>,
api_base: &str,
api_key: &str,
image_model: &str,
tool_name: &str,
args: &Value,
) -> String {
match tool_name {
"generate_character_images" => {
let name = args.get("character_name").and_then(Value::as_str).unwrap_or("角色");
let views: [(&str, &str); 4] = [
("front", "prompt_front"),
("back", "prompt_back"),
("left", "prompt_left"),
("right", "prompt_right"),
];
let mut ok = 0;
for (view, key) in views {
let Some(prompt) = args.get(key).and_then(Value::as_str).filter(|p| !p.is_empty()) else {
continue;
};
send_sse(tx, json!({ "type": "tool_progress", "tool": tool_name, "detail": format!("生成 {} 的 {} 视图", name, view) }));
match call_image_gen(api_base, api_key, image_model, prompt).await {
Ok(url) if !url.is_empty() => {
ok += 1;
send_sse(tx, json!({ "type": "image", "character": name, "view": view, "url": url }));
}
Ok(_) => {}
Err(e) => {
send_sse(tx, json!({ "type": "tool_progress", "tool": tool_name, "detail": format!("{} 的 {} 视图生成失败: {}", name, view, e) }));
}
}
}
format!("已为角色「{}」生成 {} 张视图。", name, ok)
}
"generate_scene_image" => {
let scene_id = args.get("scene_id").and_then(Value::as_i64).unwrap_or(0);
let desc = args.get("description").and_then(Value::as_str).unwrap_or("");
let Some(prompt) = args.get("prompt").and_then(Value::as_str).filter(|p| !p.is_empty()) else {
return "缺少 prompt，未生成场景图。".to_string();
};
send_sse(tx, json!({ "type": "tool_progress", "tool": tool_name, "detail": format!("生成场景 {}", scene_id) }));
match call_image_gen(api_base, api_key, image_model, prompt).await {
Ok(url) if !url.is_empty() => {
send_sse(tx, json!({ "type": "scene", "id": scene_id, "description": desc, "prompt": prompt, "url": url }));
format!("场景 {} 已生成。", scene_id)
}
Ok(_) => format!("场景 {} 上游未返回图像。", scene_id),
Err(e) => format!("场景 {} 生成失败: {}", scene_id, e),
}
}
"generate_tts" => {
let character = args.get("character").and_then(Value::as_str).unwrap_or("旁白");
let emotion = args.get("emotion").and_then(Value::as_str).unwrap_or("平静");
let Some(text) = args.get("text").and_then(Value::as_str).filter(|t| !t.is_empty()) else {
return "缺少台词文本，未生成语音。".to_string();
};
send_sse(tx, json!({ "type": "tool_progress", "tool": tool_name, "detail": format!("为 {} 合成语音", character) }));
match call_tts(api_base, api_key, text, voice_for_emotion(emotion)).await {
Ok(audio_bytes) => {
let audio_path = format!(
"/tmp/comfyui_tts_{}_{}.mp3",
character.replace(' ', "_"),
std::time::SystemTime::now()
.duration_since(std::time::UNIX_EPOCH)
.unwrap_or_default()
.as_millis()
);
if tokio::fs::write(&audio_path, &audio_bytes).await.is_ok() {
send_sse(tx, json!({
"type": "tts",
"character": character,
"text": text,
"url": format!("/audio/{}", audio_path.trim_start_matches("/tmp/comfyui_tts_")),
}));
format!("已为「{}」生成语音。", character)
} else {
"语音生成成功但写入失败。".to_string()
}
}
Err(e) => format!("语音生成失败: {}", e),
}
}
"build_comfyui_workflow" => {
let Some(raw) = args.get("workflow_json").and_then(Value::as_str).filter(|w| !w.is_empty()) else {
return "缺少 workflow_json。".to_string();
};
match serde_json::from_str::<Value>(raw) {
Ok(parsed) => {
send_sse(tx, json!({ "type": "comfyui_workflow", "workflow": parsed }));
"ComfyUI 工作流已交付。".to_string()
}
Err(e) => format!("工作流 JSON 无效: {}", e),
}
}
other => format!("未知工具: {}", other),
}
}
fn string_field(value: &Value, keys: &[&str]) -> Option<String> { fn string_field(value: &Value, keys: &[&str]) -> Option<String> {
keys.iter() keys.iter()
.find_map(|key| value.get(*key).and_then(Value::as_str)) .find_map(|key| value.get(*key).and_then(Value::as_str))
@@ -910,6 +1077,15 @@ async fn chat_handler(
let client = Client::new(); let client = Client::new();
// Agentic loop: each round may produce tool_calls; we execute them,
// feed results back, and re-query until the model returns a final text
// answer (no tool_calls) or the round budget is exhausted.
const MAX_AGENT_ROUNDS: usize = 6;
let mut agent_round = 0usize;
let mut accumulated_text = String::new();
loop {
agent_round += 1;
info!("comfyui-agent: sending chat request to upstream"); info!("comfyui-agent: sending chat request to upstream");
let response = match client let response = match client
@@ -920,6 +1096,8 @@ async fn chat_handler(
"messages": upstream_messages, "messages": upstream_messages,
"temperature": 0.7, "temperature": 0.7,
"stream": true, "stream": true,
"tools": agent_tool_definitions(),
"tool_choice": "auto",
})) }))
.send() .send()
.await .await
@@ -952,7 +1130,10 @@ async fn chat_handler(
let mut stream = response.bytes_stream(); let mut stream = response.bytes_stream();
let mut buffer: Vec<u8> = Vec::new(); let mut buffer: Vec<u8> = Vec::new();
let mut accumulated_text = String::new(); accumulated_text.clear();
// Accumulate streamed tool_calls: index -> (id, name, arguments-buffer).
let mut tool_calls_acc: std::collections::BTreeMap<i64, (String, String, String)> =
std::collections::BTreeMap::new();
// Phase 1: Stream the LLM text response // Phase 1: Stream the LLM text response
loop { loop {
@@ -1048,8 +1229,74 @@ async fn chat_handler(
return; return;
} }
} }
// Accumulate streamed tool_calls fragments.
if let Some(tcs) = delta.get("tool_calls").and_then(Value::as_array) {
for tc in tcs {
let idx = tc.get("index").and_then(Value::as_i64).unwrap_or(0);
let entry = tool_calls_acc.entry(idx).or_default();
if let Some(id) = tc.get("id").and_then(Value::as_str) {
if !id.is_empty() {
entry.0 = id.to_string();
} }
} }
if let Some(name) = tc.pointer("/function/name").and_then(Value::as_str) {
if !name.is_empty() {
entry.1 = name.to_string();
}
}
if let Some(args) = tc.pointer("/function/arguments").and_then(Value::as_str) {
entry.2.push_str(args);
}
}
}
}
}
// If the model requested tools this round, execute them, append the
// assistant tool_calls + tool results to the conversation, and loop
// for another round so the model can react to the results.
if !tool_calls_acc.is_empty() && agent_round < MAX_AGENT_ROUNDS {
// Reconstruct the assistant message carrying the tool_calls.
let assistant_tool_calls: Vec<Value> = tool_calls_acc
.iter()
.map(|(_, (id, name, args))| {
json!({
"id": id,
"type": "function",
"function": { "name": name, "arguments": args },
})
})
.collect();
upstream_messages.push(json!({
"role": "assistant",
"content": if accumulated_text.is_empty() { Value::Null } else { Value::from(accumulated_text.clone()) },
"tool_calls": assistant_tool_calls,
}));
for (_, (id, name, args)) in tool_calls_acc.iter() {
let parsed_args: Value = serde_json::from_str(args).unwrap_or(json!({}));
send_sse(&tx, json!({ "type": "tool_call", "tool": name, "arguments": parsed_args }));
let result = execute_agent_tool(
&tx, &api_base, &api_key, &image_model, name, &parsed_args,
).await;
send_sse(&tx, json!({ "type": "tool_result", "tool": name, "result": result }));
upstream_messages.push(json!({
"role": "tool",
"tool_call_id": id,
"content": result,
}));
}
// Continue to the next agent round.
continue;
}
// No tool calls → final answer. Leave the agentic loop and fall through
// to the legacy structured-section parsing as a fallback for models
// that emit 【...】 markers instead of tool calls.
break;
} // end agentic loop
// Phase 2: Parse structured sections from accumulated text // Phase 2: Parse structured sections from accumulated text
info!("comfyui-agent: text streaming complete, parsing sections"); info!("comfyui-agent: text streaming complete, parsing sections");
@@ -1305,6 +1552,8 @@ mod tests {
template_proxy_url: None, template_proxy_url: None,
}, },
comfyui: Default::default(), comfyui: Default::default(),
payment: Default::default(),
pixelle_video: Default::default(),
}, },
pool, pool,
BuiltinKeys { BuiltinKeys {
src/routes/digital_human.rs
+1726 -87
View File
File diff suppressed because it is too large Load Diff
src/routes/events.rs
+49 -3
View File
@@ -439,6 +439,12 @@ struct EventListItem {
event_type: String, event_type: String,
title: String, title: String,
message: Option<String>, message: Option<String>,
#[sqlx(default)]
#[serde(skip_serializing_if = "Option::is_none")]
account: Option<String>,
#[sqlx(default)]
#[serde(skip_serializing_if = "Option::is_none")]
client_ip: Option<String>,
level: String, level: String,
#[serde(rename = "read")] #[serde(rename = "read")]
is_read: bool, is_read: bool,
@@ -449,11 +455,15 @@ struct EventListItem {
impl From<Event> for EventListItem { impl From<Event> for EventListItem {
fn from(event: Event) -> Self { fn from(event: Event) -> Self {
let account = event_account(&event.event_type, &event.title, event.message.as_deref());
let client_ip = event_client_ip(event.message.as_deref());
Self { Self {
id: event.id, id: event.id,
event_type: event.event_type, event_type: event.event_type,
title: event.title, title: event.title,
message: event.message, message: event.message,
account,
client_ip,
level: event.level.unwrap_or_else(|| "info".to_string()), level: event.level.unwrap_or_else(|| "info".to_string()),
is_read: event.is_read.unwrap_or(false), is_read: event.is_read.unwrap_or(false),
related_id: event.related_id, related_id: event.related_id,
@@ -470,6 +480,8 @@ impl From<runtime_logs::RuntimeLogEntry> for EventListItem {
event_type: entry.event_type, event_type: entry.event_type,
title: entry.title, title: entry.title,
message: entry.message, message: entry.message,
account: None,
client_ip: None,
level: entry.level, level: entry.level,
is_read: entry.is_read, is_read: entry.is_read,
related_id: entry.related_id, related_id: entry.related_id,
@@ -479,6 +491,38 @@ impl From<runtime_logs::RuntimeLogEntry> for EventListItem {
} }
} }
fn event_account(event_type: &str, title: &str, message: Option<&str>) -> Option<String> {
if event_type != "user_login" {
return None;
}
message
.and_then(|value| keyed_message_value(value, "账号"))
.or_else(|| message.and_then(|value| keyed_message_value(value, "邮箱")))
.or_else(|| message.and_then(|value| keyed_message_value(value, "标识")))
.or_else(|| {
title
.split_once('：')
.map(|(_, value)| value.trim().to_string())
})
.filter(|value| !value.is_empty())
}
fn event_client_ip(message: Option<&str>) -> Option<String> {
message
.and_then(|value| keyed_message_value(value, "IP"))
.filter(|value| !value.is_empty())
}
fn keyed_message_value(message: &str, key: &str) -> Option<String> {
let prefix = format!("{key}=");
message
.split('·')
.map(str::trim)
.find_map(|part| part.strip_prefix(&prefix).map(str::trim))
.filter(|value| !value.is_empty())
.map(str::to_string)
}
#[cfg(test)] #[cfg(test)]
mod tests { mod tests {
use super::*; use super::*;
@@ -487,11 +531,11 @@ mod tests {
config::{AppConfig, AuthConfig, DbConfig, ProxyConfig, ServerConfig}, config::{AppConfig, AuthConfig, DbConfig, ProxyConfig, ServerConfig},
services::{builtin_keys::BuiltinKeys, runtime_auth::RuntimeAuthSettings}, services::{builtin_keys::BuiltinKeys, runtime_auth::RuntimeAuthSettings},
}; };
use axum::extract::{Query, State};
use axum::{ use axum::{
body::Body, body::Body,
http::{Request, StatusCode}, http::{Request, StatusCode},
}; };
use axum::extract::{Query, State};
use sqlx::sqlite::SqlitePoolOptions; use sqlx::sqlite::SqlitePoolOptions;
use tower::ServiceExt as _; use tower::ServiceExt as _;
@@ -536,6 +580,8 @@ mod tests {
template_proxy_url: None, template_proxy_url: None,
}, },
comfyui: Default::default(), comfyui: Default::default(),
payment: Default::default(),
pixelle_video: Default::default(),
}, },
pool, pool,
BuiltinKeys { BuiltinKeys {
@@ -631,8 +677,8 @@ mod tests {
.expect("admin token request"); .expect("admin token request");
assert_eq!(ok_response.status(), StatusCode::OK); assert_eq!(ok_response.status(), StatusCode::OK);
let user_jwt = generate_jwt(&state.config.auth.jwt_secret, "1", "user", 1) let user_jwt =
.expect("user jwt"); generate_jwt(&state.config.auth.jwt_secret, "1", "user", 1).expect("user jwt");
let user_response = app let user_response = app
.clone() .clone()
.oneshot( .oneshot(
src/routes/mod.rs
+18 -7
View File
@@ -16,12 +16,16 @@ use tower_http::services::ServeDir;
static EMBEDDED_WEB: Dir<'_> = include_dir!("$CARGO_MANIFEST_DIR/dist/web"); static EMBEDDED_WEB: Dir<'_> = include_dir!("$CARGO_MANIFEST_DIR/dist/web");
static EMBEDDED_WEBSITE: Dir<'_> = include_dir!("$CARGO_MANIFEST_DIR/dist/website"); static EMBEDDED_WEBSITE: Dir<'_> = include_dir!("$CARGO_MANIFEST_DIR/dist/website");
const _: &[u8] = include_bytes!(concat!(env!("CARGO_MANIFEST_DIR"), "/dist/web/index.html")); const _: &[u8] = include_bytes!(concat!(env!("CARGO_MANIFEST_DIR"), "/dist/web/index.html"));
const _: &[u8] = const _: &[u8] = include_bytes!(concat!(
include_bytes!(concat!(env!("CARGO_MANIFEST_DIR"), "/dist/website/index.html")); env!("CARGO_MANIFEST_DIR"),
"/dist/website/index.html"
));
mod admin; mod admin;
mod agent;
mod auth; mod auth;
mod checkin; mod checkin;
mod comfy_cloud_adapter;
mod comfyui; mod comfyui;
mod comfyui_agent; mod comfyui_agent;
mod digital_human; mod digital_human;
@@ -30,6 +34,7 @@ mod health;
mod money_printer; mod money_printer;
mod oauth; mod oauth;
mod organizations; mod organizations;
mod payment;
mod picture_agent; mod picture_agent;
mod proxy; mod proxy;
mod search; mod search;
@@ -50,8 +55,10 @@ pub fn build_router(state: AppState) -> Router {
.merge(admin::routes(state.clone())) .merge(admin::routes(state.clone()))
.merge(proxy::routes()) .merge(proxy::routes())
.merge(picture_agent::routes()) .merge(picture_agent::routes())
.merge(comfy_cloud_adapter::routes())
.merge(money_printer::routes()) .merge(money_printer::routes())
.merge(comfyui_agent::routes()) .merge(comfyui_agent::routes())
.merge(agent::routes())
.merge(digital_human::routes()) .merge(digital_human::routes())
.merge(comfyui::routes()) .merge(comfyui::routes())
.merge(crate::workflow::routes::routes()) .merge(crate::workflow::routes::routes())
@@ -65,6 +72,7 @@ pub fn build_router(state: AppState) -> Router {
.merge(checkin::routes()) .merge(checkin::routes())
.merge(oauth::routes()) .merge(oauth::routes())
.merge(organizations::routes()) .merge(organizations::routes())
.merge(payment::routes())
.merge(search::routes()) .merge(search::routes())
.merge(site_announcements::routes()) .merge(site_announcements::routes())
.merge(workflow_ui::routes()) .merge(workflow_ui::routes())
@@ -99,12 +107,9 @@ pub fn build_router(state: AppState) -> Router {
return Ok::<_, Infallible>(api_not_found_response(path)); return Ok::<_, Infallible>(api_not_found_response(path));
} }
Ok::<_, Infallible>(filesystem_static_response( Ok::<_, Infallible>(
path, filesystem_static_response(path, &web_dir, &website_dir).await,
&web_dir,
&website_dir,
) )
.await)
} }
})); }));
router.fallback_service(static_service) router.fallback_service(static_service)
@@ -285,6 +290,12 @@ mod tests {
assert_eq!(embedded_asset_path("/new"), "new.html"); assert_eq!(embedded_asset_path("/new"), "new.html");
assert_eq!(embedded_asset_path("/new/"), "new.html"); assert_eq!(embedded_asset_path("/new/"), "new.html");
assert_eq!(embedded_asset_path("/new/index.html"), "new.html"); assert_eq!(embedded_asset_path("/new/index.html"), "new.html");
for route in ["new1", "new2", "new3", "new4", "new5"] {
assert!(!should_serve_website(&format!("/{route}")));
assert!(!should_serve_website(&format!("/{route}/")));
assert!(!should_serve_website(&format!("/{route}/index.html")));
}
} }
#[test] #[test]

Some files were not shown because too many files have changed in this diff Show More