Commit Graph
5 Commits
Author SHA1 Message Date
lukaszraczylo 8d470b173b feat: native provider passthrough with key injection and best-effort accounting 2026-08-20 11:24:24 +01:00
lukaszraczylo dcfcfb7e48 feat: unified chat and embeddings endpoints with limits and accounting
Implements Task 12: POST /v1/chat/completions and POST /v1/embeddings
through a shared pipeline (routes_unified.go: handleChat, handleEmbeddings,
runUnified) wired into ServeHTTP's dispatch in llmgateway.go.

Pipeline: decode (10MiB cap) -> resolve model -> enforce user/group
limits -> call adapter -> account usage, translating every failure mode
into its HTTP envelope per the task brief's carried rulings:

- ALIAS ECHO (ruling a): the client-requested model id is threaded to the
  adapter via the internal gatewayAliasKey convention and echoed back in
  anthropic/gemini's translated response model field; every adapter
  strips the key before building its upstream wire body so it never
  leaks to a real provider.
- Limit violations (ruling b): storeDown -> 503 server_error; otherwise
  429 rate_limit_error with Retry-After when the violation names a
  window.
- Stream-safe error handling (ruling c): statusTrackingWriter.wroteHeader
  gates whether an adapter error still gets an envelope; providerHTTPError
  wraps into {error:{message,type,code,upstream}}; translateError maps to
  400/501; context.Canceled logs quietly; anything else is a 502.
- Usage/accounting (ruling d): zero non-streaming usage gets a
  ceil(len(body)/4) prompt-token estimate; zero streaming usage logs once
  and accounts the request only. unifiedCostMicros extends costMicros'
  single-id lookup to canonical-then-bare without changing its signature.
- Scopes (ruling e): user scope only when u.limits is set, group scope
  only when grp.limits is set, user first.

routes_unified_test.go drives every case end-to-end through
Gateway.ServeHTTP against httptest fake upstreams (openai- and
anthropic-shaped): happy path with counters asserted via the limiter's
own store, incremental stream flushing, 401/403/404/429/503, embeddings,
alias echo through a provider-prefixed anthropic request, wrapped
upstream error envelopes, and a mid-stream drop that must not append a
second envelope to an already-committed response.

Gates: gofmt, go vet, fieldalignment, golangci-lint (incl. gosec) all
clean; go test ./... -race -count=1 passes.
2026-08-20 10:45:12 +01:00
lukaszraczylo c0f31a3bc0 fix(openai): case-insensitive content-type gate
Content-Type header values are case-insensitive per RFC 7231, but
chatCompletion's streaming-vs-JSON-fallback gate used a plain
strings.Contains against "text/event-stream", so an upstream that
sent "Text/Event-Stream" or similar would silently fall through to
the non-streaming passthrough path. Carried item (a) from Task 9's
brief.
2026-08-20 03:36:34 +01:00
lukaszraczylo 543f358c7f fix(providers): preserve captured usage on stream errors, %w wrapping, defensive transport clone, JSON fallback for ignored stream flag 2026-08-20 03:15:51 +01:00
lukaszraczylo 6275daa702 feat: provider adapter interface and openai-type adapter with streaming usage capture 2026-08-20 03:06:08 +01:00