docs: cover impossible goals, reactive compression, and SDK canUseTool timeout#331
Merged
Conversation
…sion, SDK canUseTool timeout) Documents behavior shipped in 0.51.x–0.52.0 that lacked coverage: - guides/goal.md: the evaluator's three verdicts (met / not met / impossible), the conservative impossible→abandoned terminal state, and how `/goal` status reports an abandoned goal. (QwenLM#4230) - explanation/agent-harness.md: new "Reactive compression" section — proactive vs. reactive compression and the one-shot force-compress-and-retry on a provider context-overflow rejection. (QwenLM#3879) - reference/sdk-api.md + contributing/sdk-typescript.md: document the `timeout.canUseTool` option and that the SDK now forwards it to the CLI so the control-plane timeout matches the callback's. (QwenLM#4491) (The `--max-tool-calls` / `--max-wall-time` budgets were already documented in guides/run-headless.md when those features shipped.) Co-Authored-By: Claude Opus 4.7 <noreply@anthropic.com>
|
👀 Quinn is reviewing — verdict (PASS / WARN / FAIL) + findings to follow. |
|
No actionable comments were generated in the recent review. 🎉 ℹ️ Recent review info⚙️ Run configurationConfiguration used: Path: .coderabbit.yaml Review profile: CHILL Plan: Pro Plus Run ID: 📒 Files selected for processing (4)
WalkthroughThis PR updates documentation across SDK references and guides to document three new or clarified behaviors: the ChangesTimeout Option Documentation
Goal Evaluation and Agent Behavior
🎯 1 (Trivial) | ⏱️ ~3 minutes 🚥 Pre-merge checks | ✅ 4 | ❌ 1❌ Failed checks (1 warning)
✅ Passed checks (4 passed)
✏️ Tip: You can configure your own custom pre-merge checks in the settings. ✨ Finishing Touches🧪 Generate unit tests (beta)
Comment |
There was a problem hiding this comment.
QA Audit — PR #331 | docs: cover impossible goals, reactive compression, and SDK canUseTool timeout
VERDICT: PASS (pending CI)
CI Status
- Lint: queued
- CodeQL: queued
Diff Review
Docs-only PR adding targeted coverage for three 0.51.x–0.52.0 features:
guides/goal.md: Documents the evaluator's three-verdict model (met / not met / impossible), the conservativeimpossible→abandonedpath, and how/goalreports the final outcome. Language is precise — the evaluator independently confirms impossibility rather than taking the assistant's claim at face value. No risk.explanation/agent-harness.md: New "Reactive compression" section clearly distinguishes proactive vs. reactive compression and explains the one-shot force-compress-and-retry with the overflow-vs-timeout distinction and at-most-once guard. Correct framing.reference/sdk-api.md+contributing/sdk-typescript.md: Documentstimeout.canUseTool, the forwarding behavior, the 10-minute cap, and the interaction with the CLI's control-plane timeout. Table and callout are clean.
No file conflicts. No test or build changes. No self-review issues.
Observations
- Gap: clawpatch unavailable for structural review (checkout cache returned invalid SHA for
main). Low impact — this is a docs-only PR with no logic to audit.
Once CI clears, this is a straightforward APPROVE.
— Quinn, QA Engineer
|
CI is still in progress. Submitted a COMMENT review on |
Code Coverage Summary
CLI Package - Full Text ReportCore Package - Full Text ReportFor detailed HTML reports, please see the 'coverage-reports-22.x-ubuntu-latest' artifact from the main CI run. |
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
1 participant
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.
Documents behavior shipped this cycle (0.51.x–0.52.0) that lacked doc coverage.
guides/goal.md(feat(core): fail impossible goals QwenLM/qwen-code#4230 fail-impossible-goals): the evaluator's three verdicts (met / not met / impossible), the conservative impossible→abandoned terminal state, and how/goalstatus reports an abandoned goal.explanation/agent-harness.md(feat(core): add reactive compression on context overflow QwenLM/qwen-code#3879 reactive compression): new section explaining proactive vs. reactive compression and the one-shot force-compress-and-retry when a provider rejects for context overflow (with the timeout-vs-overflow distinction and the at-most-once guard).reference/sdk-api.md+contributing/sdk-typescript.md(fix(sdk): honor canUseTool timeout in CLI control requests QwenLM/qwen-code#4491): document thetimeout.canUseTooloption and that the SDK now forwards it to the CLI so the control-plane timeout matches the callback's (no more 60s cut-off of long approval handlers).The
--max-tool-calls/--max-wall-timebudgets were already documented inguides/run-headless.mdwhen those features shipped, so no change there.Docs-only.
🤖 Generated with Claude Code
Summary by CodeRabbit
timeoutoption toQueryOptionswith 10-minute cap for per-operation timeouts./goalcommand documentation with three-verdict evaluation model (Met, Not met, Impossible) and enhanced status output clarity.