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.
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.
Previously every executor took `_state: AppState` (unused) and `check_auth`
discarded the matched downstream key id, so `usage_logs` was orphan code.
This change plumbs the key id from auth → handlers → executors → billing,
adds the OpenAI Responses API endpoint, and exposes shim aliases under
`/api/comfyui-agent/proxy/openai/*` so embedded ComfyUI's OpenAI nodes
flow through the same auth/conductor/billing pipeline.
- check_auth now returns Option<i64> (managed key id) instead of unit
- record_billing helper writes usage_logs after each successful upstream call
- extract_usage handles both chat-completions and responses usage shapes
- conductor wrappers record billing post-Success; stream variant scans
chunks in reverse for the final usage event
- POST /v1/responses (stream + non-stream) via ProxyConductor
- shim aliases mounted on the same Router so auth/failover/billing work for free
- ComfyUIProcess injects BOOSAPI_BUILTIN_KEY env + --comfy-api-base on spawn
- bootstrap built-in `comfyui-agent` downstream key at startup (idempotent)
- get_auth_header in vendored ComfyUI falls back to BOOSAPI_BUILTIN_KEY env
Co-Authored-By: Kiro <noreply@kiro.dev>
boos