Skip to content

[WRONG BRANCH] fix(claude): bound streamed reasoning part identity - #38

Draft
luvs01 wants to merge 1 commit into
mainfrom
codex/propose-fix-for-unbounded-reasoning-keys
Draft

[WRONG BRANCH] fix(claude): bound streamed reasoning part identity#38
luvs01 wants to merge 1 commit into
mainfrom
codex/propose-fix-for-unbounded-reasoning-keys

Conversation

@luvs01

@luvs01 luvs01 commented Aug 7, 2026

Copy link
Copy Markdown
Owner

Motivation

  • Upstream SSE frames previously fed untrusted item_id/index strings into retained per-stream state, allowing a malicious upstream to leak large strings into long-lived OpenBlock fields and bypass the translator memory budget.
  • The intent is to ensure retained reasoning identity state is size-bounded and validated so stalled or malicious streams cannot exhaust process memory.

Description

  • Add a boundedReasoningIndex helper that validates and normalizes reasoning indexes to a non-negative safe integer or a bounded sentinel value.
  • Replace construction of the retained reasoningPartKey with a fixed-size key derived only from validated numeric indexes (output/part indexes) and drop retention of arbitrary upstream item_id strings.
  • Update the OpenBlock.reasoningPartKey comment to clarify it stores a bounded identity, and preserve the existing multi-part separator behavior for valid frames.
  • Add a regression test that injects oversized/malformed upstream metadata and verifies the adapter ignores untrusted string identities while preserving reasoning-part joining semantics.

Testing

  • ✅ Ran the focused module tests: bun test tests/claude-outbound.test.ts and they passed.
  • ✅ Ran the typechecker: bun run typecheck and it passed.
  • ✅ Ran the privacy scanner: bun run privacy:scan and it passed.
  • ⚠️ Attempted the full suite with bun run test, but CI-equivalent GUI dependency downloads failed in this environment (HTTP 403) causing unrelated build failures, so the full matrix could not be completed here.

@chatgpt-codex-connector

Copy link
Copy Markdown

You have reached your Codex usage limits for code reviews. You can see your limits in the Codex usage dashboard.
To continue using code reviews, add credits to your account and enable them for code reviews in your settings.

@coderabbitai

coderabbitai Bot commented Aug 7, 2026

Copy link
Copy Markdown

Warning

Review limit reached

@luvs01, you've reached your PR review limit, so we couldn't start this review.

Next review available in: 3 minutes

Enable usage-based reviews in Billing to review now. Otherwise, wait until the next included review is available.
You're only billed for reviews past your plan's rate limits ($0.25/file).

How can I continue?

After more reviews become available, a review can be triggered using the @coderabbitai review command as a PR comment. Alternatively, push new commits to this PR.

To avoid repeated limits, reduce automatic review volume by pausing incremental auto-reviews earlier, using label-based review opt-in, excluding WIP or generated PR titles, or requesting reviews manually when the PR is ready. If your team needs uninterrupted high-volume reviews, an organization admin can enable usage-based reviews.

How do review limits work?

CodeRabbit enforces per-developer PR review limits for each organization. Most developers receive the normal plan review availability.

For paid Pro and Pro+ PR reviews, CodeRabbit uses adaptive limits for sustained high-volume activity. When a developer's recent PR review activity reaches the 95th percentile or higher among CodeRabbit users, additional reviews become available more gradually as earlier reviews age out of the rolling window.

Please refer docs for additional details.

Review details
⚙️ Run configuration

Configuration used: Path: .coderabbit.yaml

Review profile: ASSERTIVE

Plan: Pro Plus

Run ID: 146ce7db-b87b-48e3-b187-12bb2d5b551c

📥 Commits

Reviewing files that changed from the base of the PR and between 2468502 and 348f5de.

📒 Files selected for processing (2)
  • src/claude/outbound.ts
  • tests/claude-outbound.test.ts

Comment @coderabbitai help to get the list of available commands.

@github-actions

github-actions Bot commented Aug 7, 2026

Copy link
Copy Markdown

⏳ DRAFT

  • wrong target branch (main); retarget to dev. UI screenshot required.

What to do

  • Retarget this PR to dev — all contributions go to dev.
  • Add a screenshot of the UI change to the PR description.

Its title has been prefixed with [WRONG BRANCH].
This pull request was already a draft. Its draft status will be preserved after every issue above is resolved.

@github-actions github-actions Bot changed the title fix(claude): bound streamed reasoning part identity [WRONG BRANCH] fix(claude): bound streamed reasoning part identity Aug 7, 2026
@github-actions
github-actions Bot marked this pull request as draft August 7, 2026 07:31
@github-actions github-actions Bot added the bug Something isn't working label Aug 7, 2026
@github-actions

github-actions Bot commented Aug 7, 2026

Copy link
Copy Markdown

Deterministic PR hygiene checks passed.

Sign up for free to join this conversation on GitHub. Already have an account? Sign in to comment

Labels

aardvark bug Something isn't working codex

Projects

None yet

Development

Successfully merging this pull request may close these issues.

1 participant