Repository navigation
fix(mcp): clarify delegation parent and result delivery - #151
Merged
EvilWeasel merged 2 commits intoNov 13, 2026
Merged
Conversation
Codex Review Summary: ✅ CompletedThis 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. |
![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: dea1998878
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".
This file contains hidden or bidirectional Unicode text that may be interpreted or compiled differently than what appears below. To review, open the file in an editor that reveals hidden Unicode characters.
Learn more about bidirectional Unicode characters
Sign up for free
to join this conversation on GitHub.
Already have an account?
Sign in to comment
Add this suggestion to a batch that can be applied as a single commit.This suggestion is invalid because no changes were made to the code.Suggestions cannot be applied while the pull request is closed.Suggestions cannot be applied while viewing a subset of changes.Only one suggestion per line can be applied in a batch.Add this suggestion to a batch that can be applied as a single commit.Applying suggestions on deleted lines is not supported.You must change the existing code in this line in order to create a valid suggestion.Outdated suggestions cannot be applied.This suggestion has been applied or marked resolved.Suggestions cannot be applied from pending reviews.Suggestions cannot be applied on multi-line comments.Suggestions cannot be applied while the pull request is queued to merge.Suggestion cannot be applied right now. Please check back later.
t3_thread_sendwithdelegationcould be mistaken for a normal child follow-up, leaving the caller waiting for a result published in the target thread. Clarify target-thread ownership, result publication and the lack of automatic caller resumption; point normal child continuations and caller-owned independent work to their respective paths.The change contains two metadata descriptions and two anonymized cases in the existing MCP tool-use eval. Runtime behavior and schema fields stay unchanged, and the total tool-list context budget is unchanged.
Validation on Boat: the advertised schema differs only in the two descriptions;
check:integrationpasses format, lint and all 10 adjacent tests. The existing independent-admission and completed-child follow-up cases also pass.Native Sol A/B used
ultra/priority, three samples per case and text version, with exactly 12 unique model starts. Both frozen arms scored 3/6 because the original oracle incorrectly required an exact message string and rejected the requiredKurz:prefix. After removing unrelated wording checks, all six samples per arm satisfy the API/parent/receipt checks on the same immutable trajectories. Exported model inputs are byte-identical before and after this oracle correction; no model samples were rerun. The baseline already chose the correct routing, so this does not demonstrate a causal model-behavior improvement. Tool execution in this eval is simulated; actual child execution and result delivery are outside this evidence.Model: gpt-6.1-sol. Harness: Codex through T3 Code.