fix(goal): remove time budget cap and exclude offline time - #3657
Conversation
🦋 Changeset detectedLatest commit: fabe97d The changes in this PR will be included in the next version bump. This PR includes changesets to release 1 package
Not sure what this means? Click here to learn what changesets are. Click here if you're a maintainer who wants to add another changeset to this PR |
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. |
commit: |
![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: 3820bc5ae9
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".
| A time budget must be at least 1 second and convert to a finite number of milliseconds. | ||
| There is no upper duration limit. Turn and token budgets must be positive and are rounded | ||
| to the nearest whole number (minimum 1). |
There was a problem hiding this comment.
Changing this raw description changes both the serialized llm.tools_snapshot payload and its hash, but the exact inline snapshots still contain the old 24-hour wording in test/agent/loop/loop.test.ts:155 and test/tool/tool.test.ts:4324,4403. Any full run containing those tests will therefore fail; update the affected snapshot text and hashes alongside this change.
Useful? React with 👍 / 👎.
|
Codex Review: Didn't find any major issues. Keep it up! Reviewed commit: ℹ️ About Codex in GitHubYour team has set up Codex to review pull requests in this repo. Reviews are triggered when you
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". |
🛡️ Codex Security Review · Automatically triggeredSecurity review completed. No security issues were found in this pull request. Reviewed commit: Only the user who started this review can view the report in Codex. ℹ️ About Codex security reviews in GitHubThis is an experimental Codex feature. Security reviews are triggered when:
Once complete, Codex will leave suggestions, or a comment if no findings are found. |
|
Codex Review: Didn't find any major issues. Breezy! Reviewed commit: ℹ️ About Codex in GitHubYour team has set up Codex to review pull requests in this repo. Reviews are triggered when you
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". |
🛡️ Codex Security Review · Automatically triggeredSecurity review completed. No security issues were found in this pull request. Reviewed commit: Only the user who started this review can view the report in Codex. ℹ️ About Codex security reviews in GitHubThis is an experimental Codex feature. Security reviews are triggered when:
Once complete, Codex will leave suggestions, or a comment if no findings are found. |
1 participant
Related Issue
No linked issue. This fixes goal time-budget limits and accounting across session shutdown and resume.
Problem
Goal time budgets above 24 hours were rejected. Restoring an active goal also charged the time spent with the program closed: a goal with 2 seconds of saved usage could return with 7 seconds used after 5 seconds offline.
What changed
Validation: 241 tests passed across goal, wire resume, and agent lifecycle suites. All 181 tests in the loop and tool suites also passed after regenerating snapshots and rerunning without snapshot updates. Agent-core-v2 typecheck, import-boundary checks, no-comments checks, and
git diff --checkpassed. Type-aware lint reported no errors (existing warnings remain).Checklist
/approve).gen-changesetsskill, or this PR needs no changeset.gen-docsskill, or this PR needs no doc update.