fix(openai-chat): bound reasoning_details snapshots and account them to TranslatorBudget - #412
fix(openai-chat): bound reasoning_details snapshots and account them to TranslatorBudget#412luvs01 wants to merge 20 commits into
Conversation
release: promote dev into main for v2.32.1
# Conflicts: # package.json
[WRONG BRANCH] merge dev into main for the v2.33.0 release
Promotes the dev integration line onto main. The resulting tree is byte-identical to origin/dev, including package.json at 2.34.0. The package.json conflict is resolved to dev's side, NOT to main's stale 2.33.0. Earlier promotions (lidge-jun#2553, lidge-jun#2507) kept the target's version so the release bump would land on its own "release: vX.Y.Z" commit. That is no longer legal: this very delta adds tests/release-version-line.test.ts, which fails when the in-tree version sits behind the highest release tag. With v2.34.0-preview.20260827 now published, 2.33.0 orders behind it, so a promotion carrying the stale line turns CI red on every shard that runs the suite. The consequence for the release step is that scripts/release.ts skips the bump (release.ts:568, currentVersion === version), so v2.34.0 gets tagged on this merge commit rather than on a separate release commit. The workflow creates the tag itself after publishing and validates expected-sha against the checked-out commit, so the tag still names exactly the audited tree.
[WRONG BRANCH] promote dev onto main for v2.34.0
[WRONG BRANCH] promote dev onto main for v2.35.0
[WRONG BRANCH] promote dev onto main for v2.36.0
[WRONG BRANCH] promote dev to main for the v2.37.0 release
[WRONG BRANCH] promote dev onto main for v2.38.0
[WRONG BRANCH] promote dev onto main for v2.39.0
release: promote dev to main for v2.40.0
…rkflow call (lidge-jun#3262) Both v2.40.0 release dispatches (33615174183 preview, 33615177849 main) died at startup_failure: a workflow_call cannot grant its callee more than the calling job holds, and dev-version-bump.yml's job declares contents+pull- requests write. lidge-jun#3129 wired the call but never dispatched a release, so this is its first live run. The caller job now declares exactly the callee's two permissions; no other job in release.yml gains anything. Co-authored-by: jun <jun@lidge.dev> (cherry picked from commit 7ce0ba5)
…400-relfix release: carry the release.yml permissions fix onto main for v2.40.0
Codex Review SummaryThis comment shows the latest Codex review activity on this pull request.
ℹ️ About Codex in GitHubYour team has set up Codex to review pull requests in this repo. Reviews are triggered when you
Codex reacts with 👀 while any review is running, comments if it has suggestions, and reacts with 👍 once all reviews finish with no findings. |
|
Important
This repository does not receive automatic reviews because it has fewer than 10 stars. ⚙️ Run configurationConfiguration used: Path: .coderabbit.yaml Review profile: ASSERTIVE Plan: Team Run ID: Thanks 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 |
|
✅ Deterministic PR hygiene checks passed. |
✅ READY
Hygiene✅ Deterministic PR hygiene checks passed. |
github-actions
Bot
changed the title
![chatgpt-codex-connector[bot]](https://avatars.githubusercontent.com/in/1144995?s=60&v=4){kind=small}
There was a problem hiding this comment.
💡 Codex Review
Here are some automated review suggestions for this pull request.
Reviewed commit: c3a289d13e
ℹ️ About Codex in GitHub
Your team has set up Codex to review pull requests in this repo. Reviews are triggered when you
- Open a pull request for review
- Mark a draft as ready
- Comment "@codex review".
If Codex has suggestions, it will comment; otherwise it will react with 👍.
Codex can also answer questions or update the PR. Try commenting "@codex address that feedback".
| let key: string; | ||
| if (typeof item.id === "string" && item.id.length > 0) { | ||
| if (new TextEncoder().encode(item.id).byteLength > MAX_REASONING_DETAIL_ID_BYTES) { |
There was a problem hiding this comment.
For a non-streaming MiniMax completion that omits reasoning_content and supplies only reasoning_details, parseResponse also calls this shared helper at line 2131, even though that path discards every key and retains only the extracted text. Consequently, an otherwise valid response containing an ID over 1,024 bytes now throws TranslatorBudgetExceededError and loses the entire completion, despite the complete response already being charged to the translator budget. Apply the ID validation only in the streaming snapshot path, or let the helper skip key validation when keys are not needed.
AGENTS.md reference: src/AGENTS.md:L19-L19
Useful? React with 👍 / 👎.
luvs01
changed the title
2 participants
Motivation
reasoning_detailscould introduce attacker-controlled, arbitrarily longidkeys and unbounded numbers of distinct segments that were retained for the lifetime of the stream without chargingTranslatorBudget.reasoning_detailsremain supported for opted-in models while preventing unbounded memory growth from hostile upstreams.Description
MAX_REASONING_DETAIL_ID_BYTES = 1024andMAX_REASONING_DETAIL_SEGMENTS = 1024, and reject oversized ids or excessive segment counts by raising a translator budget error. (src/adapters/openai-chat.ts).reasoningbuffer kind. (src/adapters/openai-chat.ts).TranslatorBudget, and release those retained bytes in the parserfinallyblock and clear the per-stream snapshot map on stream cleanup. (src/adapters/openai-chat.ts).tests/minimax-reasoning-split.test.ts).Testing
bun test tests/minimax-reasoning-split.test.ts, and the modified MiniMax reasoning tests passed (all added and existing MiniMax reasoning assertions passed).bun x tsc --noEmitandbun run privacy:scan(no new privacy regressions introduced).bun run testwas executed; the MiniMax tests passed in that full run, while unrelated integration tests (environment/timing/systemd expectations and a few timeouts) failed in the CI-like full-suite run and are not related to these changes. The patch is focused and covered by the added unit tests above.Codex Task