Conversation
An explicit upstreamWebsocket: false now routes streaming canonical ChatGPT turns over HTTP/SSE before sending. This gives operators a supported escape from intermittent post-send WebSocket closes without replaying ambiguous turns. The default remains WebSocket and native WS controls are unavailable when HTTP is selected. Verified: focused Responses/provider suites, typecheck, structure check, privacy scan, docs build. Changed-area suite rerun pending.
|
Important Draft PR not reviewedDraft PRs are not automatically reviewed by default.
To automatically review draft PRs, update your CodeRabbit configuration: reviews:
auto_review:
drafts: trueThanks for using CodeRabbit! It's free for OSS, and your support helps us grow. If you like it, consider giving us a shout-out. Comment |
github-actions
Bot
added
the
intake: hygiene-blocked
|
⏳ DRAFT
What to do
Review readiness checklist
0/4 boxes ticked. This pull request was already a draft. Its draft status will be preserved after every issue above is resolved. |
ildunari
changed the title
리뷰 · 우선순위 54 / 80이 PR은 ChatGPT 기본 공급자 라인 - 라인 - 메인테이너의 판단이 필요한 지점 너의 추천 이 댓글은 grok-bot이 작성했습니다 |
…, #5714, #5704, #5707) (#5738) * fix(claude): bound Responses user to 64 chars for long metadata.user_id Claude Code sends metadata.user_id as a ~186-char JSON string. It was copied verbatim into the Responses 'user' field, which Azure OpenAI and other OpenAI-compatible backends cap at 64 chars, so every Claude Code request routed to Azure failed with 400 "Invalid 'user': string too long". Keep short ids as-is and send the SHA-256 hex digest (already computed for prompt_cache_key) when the id exceeds 64 chars. Fixes #5705 Co-authored-by: Giulio Leone <giulioleone097@gmail.com> * Fix plaintext V2 SSE responses with missing content type Co-authored-by: Jerry WANG <jerrywang@Jerrys-MacBook-Pro-2.local> * fix(responses): exclude dropped chat reasoning from input admission * test(admission): verify reasoning payload matches gate decisions Co-authored-by: 정우철 <oocheol@naver.com> * Allow HTTP upstream for canonical ChatGPT provider An explicit upstreamWebsocket: false now routes streaming canonical ChatGPT turns over HTTP/SSE before sending. This gives operators a supported escape from intermittent post-send WebSocket closes without replaying ambiguous turns. The default remains WebSocket and native WS controls are unavailable when HTTP is selected. Verified: focused Responses/provider suites, typecheck, structure check, privacy scan, docs build. Changed-area suite rerun pending. Co-authored-by: kosta <kosta963@gmail.com> * test(claude): pin exact user hash and the 64/65-char boundary Refs #5705 Co-authored-by: Giulio Leone <giulioleone097@gmail.com> * docs(architecture): attribute the admission fix to excluding unsent thinking Split the preserved-reasoning statement from the refusal rationale in the English and Korean paragraphs, as review of #5714 asked. Refs #5696 Co-authored-by: 정우철 <oocheol@naver.com> * fix(anthropic): count ping events as upstream liveness Anthropic streams may include any number of ping events. The adapter only turned SSE comments into heartbeats, so a long silent thinking phase that pinged was cut off at stallTimeoutSec with upstream_stall_timeout. Named and data-only ping records now yield the same heartbeat. Refs #5707 * fix(management): report upstreamWebsocket as configured in GET /api/providers The row coerced an unset value to false. After the canonical ChatGPT opt-out, unset means upstream WebSocket and false means HTTP/SSE, so a save built from the row could turn WebSocket off. The row now omits the key when it is unset. Co-authored-by: kosta <kosta963@gmail.com> * docs(providers): describe the canonical ChatGPT upstreamWebsocket opt-out The reference row, its seven translations, and the provider type and schema comments still said the canonical ChatGPT transport ignores upstreamWebsocket. It now selects HTTP/SSE when set to false. The locale rows were also behind the English row on the first-party-only restriction; they are retranslated from it. Co-authored-by: kosta <kosta963@gmail.com> * fix(responses): bound the plaintext V2 SSE prefix probe by stallTimeoutSec The carried probe read the first chunk of an unlabeled body with no deadline, before the passthrough stall guard is attached. An upstream that sent headers but no body held the request and its host lease until the client gave up, and a failed read escaped the classifier. Each probe read now races a per-read inactivity window and one total budget, both stallTimeoutSec, plus the client abort signal. Timeout, abort, and read errors cancel the reader and return the existing unsupported-content-type 502. Docs now scope the recovery to missing or unrecognized non-JSON content types. Follow-up to #5683 review (maintainer, Codex, CodeRabbit). Co-authored-by: Jerry WANG <jerrywang@Jerrys-MacBook-Pro-2.local> --------- Co-authored-by: Giulio Leone <giulioleone097@gmail.com> Co-authored-by: Jerry WANG <jerrywang@Jerrys-MacBook-Pro-2.local> Co-authored-by: 정우철 <oocheol@naver.com> Co-authored-by: kosta <kosta963@gmail.com>
2 participants
Summary
openaiprovider to setupstreamWebsocket: falseand send streaming Responses turns over HTTP/SSE. Omitted keeps the current WebSocket default; explicittrueremains outside the canonical provider seed.websocketsindependent and disable WebSocket-only native steering/injection when the upstream opt-out is active.This addresses a field report of intermittent upstream WebSocket close 1006 with no response frame on requests around 2.7–3.6 MB. The proxy currently returns 502 for those ambiguous post-send closes; it cannot safely replay the same turn. The option lets affected hosts choose HTTP before sending without changing credentials or destination. It does not claim that every 1006 has the same cause or that HTTP cannot have its own transport failures.
Verification
bun test tests/responses/ws-upstream.test.ts tests/responses/ws-native-injection.test.ts— 172 passed, 1 skipped.bun test tests/server/management-provider-validation.test.ts— 137 passed.bun run typecheck— passed.bun run structure:check— passed.bun run privacy:scan— passed.cd docs-site && bun install --frozen-lockfile && bun run build— passed, 505 pages built.bun run test:changed— 10,369 passed, 5 skipped, 2 failed under four-worker parallelism. Both failures passed when rerun individually:native-codex-toggle.test.tsandopenai-provider-option-e2e.test.ts.bun run test:changed --parallel=2— timed out at 15 minutes whiletests/server/audio-dictation.test.tshad been running for 826 seconds. The changed-area gate is not green; this test is outside the modified transport and provider-validation files.Checklist
Review readiness checklist
This PR stays in draft until every box below is ticked. Tick all four boxes once the requirements are met:
Required local validation passed; commands, results, and any full-suite exception are documented.
I pushed my PR to a recent dev commit (at most 10 behind; a maintainer may still ask for the exact tip before merge).
I resolved all correct Codex and CodeRabbit findings.
My PR is ready for review.