Commit Graph

8 Commits

Author SHA1 Message Date
dev
98847adfd6 refactor(gateway): collapse chat.go four-way duplication
singleChat / singleChatAuto / streamChat / streamChatAuto shared ~260 near-
identical lines (diff after stripping comments was empty). Extract three
shared bodies and shrink all four entry points to thin dispatchers:

- failChat: error → record + writeError, shared ChainErr extraction
  (errors.As returns false for direct-path errors, so the two paths stay
  equivalent without a branch)
- recordChatUsage: exact upstream numbers win, byte estimates fill gaps
- writeChatCompletion: unified ChatCompletion rendering (model name is the
  only direct/auto difference, passed in)
- pumpStream: the full SSE pump (preamble, delta loop, terminal finish +
  usage chunk, [DONE]) — shared by both streaming entries

Behavior change (pinned by TestDirectStreamFailoverAuditSource): direct
streams now pin rec.Source to the source that actually served the stream
after a failover, instead of discarding it (_, usedModel). The audit row
previously recorded the first candidate, which was wrong on failover.

chat.go: 982 → 896 lines (−86).
2026-08-24 22:38:38 +08:00
dev
c8a300c998 fix(gateway): forward Flush through statusRecorder so SSE streams in real time
statusRecorder (the access-log wrapper) did not implement http.Flusher, so
w.(http.Flusher) inside streamChat/streamChatAuto returned nil and every SSE
chunk stayed buffered until the response ended. Add Flush() that delegates to
the underlying writer when it supports flushing.

Regression test: TestStatusRecorderFlusher pins the interface assertion and
the forwarding path.
2026-08-24 22:22:38 +08:00
31b1ed2c96 feat(gateway): collapse multi-tier failure details into short client message
Clients saw the full per-tier chain error including upstream HTML WAF
pages and JSON quota payloads. The response now carries one capped
one-line reason per tier (quota/cooling skips preserved); full detail
remains in rec.Err / stats API and is logged server-side.
2026-08-24 16:02:31 +08:00
d06210204b feat: config.yaml only, OpenRouter free models, remove runtime.json config
- Move all config (auto rules, keys) from runtime.json to config.yaml
- Store now only holds runtime sources (WebUI-created)
- Add OpenRouter free models to config.yaml
- One-time migration from legacy runtime.json on startup
- Fix gateway tests for new config structure
- Update core.go with migrateFromRuntime, saveConfig, seedKeys/seedAuto
- Remove SaveKey/KeyByValue/AutoRules from Store
- Add Config.Save() with YAML marshaling
- Update WebUI admin keys visibility (show all keys including admin)
- Bump binary to 11MB with luajit
2026-08-13 10:18:19 +08:00
20d2268546 fix: close P10 audit items — P10-1 sources API admin guard, P10-2 scope prefix strip, P10-3 runtime source timeout w/ stream-safe clients
- api.go: handleSourcesAPI now requires admin role (GET leaks upstream api_keys, POST/DELETE mutate routing)
- chat.go: hasScopeModel made a Gateway method that strips source-model/:// prefix strictly via Registry.EffectiveModel (only when the prefix names a real source serving the bare model) so dash-bearing ids like deepseek-v4-flash-free are never corrupted; +TestHasScopeModelWithSourcePrefix
- config.go: DefaultSourceTimeout/QueueTimeout/Concurrency constants shared by YAML ApplyDefaults and runtime sources
- core.go: mergedSources applies the same defaults to runtime sources (JSON never persisted timeout fields); a dead upstream can no longer hold a concurrency slot forever
- provider.go: split non-streaming client{Timeout} vs stream client{} sharing a Transport with ResponseHeaderTimeout, so long SSE bodies are not cut by client.Timeout; ChatStream uses doRawStream
- plan.md: mark P4-4/5/6 done, record P4-7/8 (tier-order, audit export, UI key view, zen upstream diagnosis)
- online verified: user key -> /api/sources 403 (GET+POST), admin 200, AUTO stream/non-stream healthy
2026-08-11 15:22:20 +08:00
88802f9ef6 feat: AUTO chain rewrite — silent failover+busy skip+pref round-robin+503 tier summary; chain edits reset slot cooldowns (P0/P1); stats by_status + audit jsonl rotation; UI priority-page health badges & status-code card; ctx-menu capture-phase close (outside-press guard); main.go ops warnings; local bundled-Lua verified tests (3 latent bugs fixed); plan.md 2026-08-11 00:03:11 +08:00
ccbcede581 feat: LuaJIT worker-pool VM, multimodal/disable-thinking passthrough, WebUI redesign, DeepSeek V4 2026-08-07 13:34:16 +08:00
f7f76e097d feat: ModelRouter — unified OpenAI-compatible multi-source LLM gateway
- Lua adapters per upstream (transform_request/response/stream_chunk, build_headers signing hooks)
- AUTO priority routing with per-model kind (chat/image), explicit source/model routing
- Per-source concurrency caps with queueing, exponential backoff, AUTO failover
- OpenAI-compatible API: chat completions, SSE streaming, image generations, models
- Gateway key auth, web UI for adapter/source management, runtime persistence
- e2e test running the real binary against mocked upstreams
2026-08-05 15:25:47 +08:00