[Alan-TheGentleman]

Summary

Refs #1494. Run-only STATUS opt-in.

Enables the native question only inside the asynchronous gentle_review_run scope. Direct status/inspect and capture remain unchanged, overlapping runs stay isolated, and malformed response data is rejected rather than admitted.

This is one bounded slice of the existing implementation and archived experiments, not a new design or a new benchmark. 320 additions plus deletions; no tests or comments are discarded to meet the 400-line limit.

Stack and dependencies

Order: decoder #3174 → optional transport → bounded result → run-only scope → integration → benchmark/reference documentation. These drafts allow review/CI in parallel. Merge sequentially only after provider support in Gentleman-Programming/gentle-ai#6107 and #6108 is delivered and each current-head check passes. Direct native calls, consent and closure authority remain unchanged.

Verification

• Current-main integrated stack: TypeScript check PASS; 49 focused tests PASS.
• Full exported test runner: 10,095 PASS, 0 FAIL, 94 skipped; provider-contract and runtime-harness stages PASS. Unit file concurrency was 2; no runner source, assertions or timeouts changed. This does not claim the earlier default-concurrency attempts passed.
• Independent packaging probes: four worker-executed cases; four additional worker-authored public probes executed by the parent after mandatory isolated preparation. Public checks cover concurrent scope isolation, malformed rejection/no authority writes, narrow old-provider fallback/cache, direct/capture parity and correction payload behavior. The source was subsequently integrated with current main and checked again as above.
• Main's new bug(review): gh pr create from a linked worktree is always denied with "Native preflight is unavailable" on Linux, while git -C push of the same range passes #3169 fixture failed on both unchanged main and candidate because /tmp aliases /private/tmp. Canonical root fixes preserve the assertions. The initial current-main test command mistakenly requested absent tsx and ran no product tests; the repository-native runner was used thereafter.
• Earlier default-concurrency failures and the old-provider/static benchmark limitations remain recorded. This PR does not claim new live-model quality or performance measurements. Existing raw evidence and gentle-shell-bench archive commit 2486ec4 are preserved.
• Current-head GitHub CI remains required before merge.

AI assistance

Material assistance: el Gentleman / Pi agents for implementation packaging, tests, independent probes, documentation and integration. Parent reviewed the partition, retained all coverage and measured its size. No actual RDD mode change or native review was performed.

Risk

Shared review-client and prompt contracts; independent verification retained. Provider permission, consent, correction selection and closure authority are not broadened.

Summary by CodeRabbit

• New Features
  • Review runs can now include a bounded set of non-blocking findings and related claims in their results. When findings are unavailable or declined, the response preserves the provider’s status without adding unsupported correction details.
• Bug Fixes
  • Non-blocking findings are limited in size and are not surfaced by direct review calls or included in nested provider records.

[coderabbitai]

No actionable comments were generated in the recent review.

Walkthrough

gentle_review_run now scopes the non-blocking findings option to its native INSPECT and STATUS requests. Added tests cover direct-call behavior, bounded findings output, and correction-gate responses.

Changes: Non-blocking findings

Layer / File(s)	Summary
Scope the request option extensions/gentle-ai.ts	An async-local scope supplies nonBlockingFindings: true to native INSPECT and STATUS requests dispatched within gentle_review_run. Direct gentle_review calls remain outside this scope.
Validate scope and correction responses tests/support/review-coordinator-runtime.ts, tests/review-coordinator-correction-gate.test.ts, tests/review-coordinator-nonblocking-scope.test.ts, tests/review-one-call-reviewer-requests.test.ts, odd/tasks/nonblocking-delivery-slices.md	Tests cover request scope, output limits, malformed findings, and correction-gate responses. Runtime fixtures add correction and escalation scenarios. The task log records verification and delivery status.

Estimated code review effort: 3 (Moderate) | ~20 minutes

Change: Feature

Sequence Diagram(s)

sequenceDiagram
  participant gentle_review_run
  participant AsyncLocalStorage
  participant INSPECT
  participant STATUS
  gentle_review_run->>AsyncLocalStorage: enter review-run scope
  AsyncLocalStorage->>INSPECT: supply nonBlockingFindings when scoped
  AsyncLocalStorage->>STATUS: supply nonBlockingFindings when scoped

Loading

Possibly related PRs

• Gentleman-Programming/gentle-shell#3134: Adds the gentle_review_run coordinator whose scoped provider requests change here.
• Gentleman-Programming/gentle-shell#3136: Adds the provider-request parity test that this change updates for the new option.

Merge Risk: Minimal · up to 40c15

The change limits the non-blocking findings option to review runs, and direct calls are unchanged. No actionable merge-blocking risk was found. Current-head CI is still required before merge.

Pre-merge checks: 4

Check name	Status	Explanation
Description Check		Check skipped - CodeRabbit’s high-level summary is enabled.
Title check		The title "feat(review): scope non-blocking findings to review runs" matches the main change. The raw summary and objectives both describe run-only opt-in for non-blocking findings inside the gentle_r…
Linked Issues check		Check skipped because no linked issues were found for this pull request.
Out of Scope Changes check		Check skipped because no linked issues were found for this pull request.

Full details: Title check

Explanation

The title "feat(review): scope non-blocking findings to review runs" matches the main change. The raw summary and objectives both describe run-only opt-in for non-blocking findings inside the gentle_review_run scope, with direct status and inspect calls left without the flag. The title is short, specific, and follows a conventional commit style.

Finishing Touches

Generate unit tests (beta)

• Commit to this branch
• Create a new PR

• Autofix · Keep fixing CodeRabbit findings and required CI, and resolving merge conflicts

Recent review info

Run configuration

• Source mode: Auto
• Repository: Unavailable
• Branch: Unavailable
• File: No configuration file from this repository applied
• Commit: Unavailable
• Layers: Repository UI
• Review profile: ASSERTIVE
• Plan: Team
• Run ID: e08cc666-3feb-41f8-869f-d5876176d6cb

Commits

Reviewing files that changed from the base of the PR and between ca9993e and 40c1545.

Files selected for processing: 6

• extensions/gentle-ai.ts
• odd/tasks/nonblocking-delivery-slices.md
• tests/review-coordinator-correction-gate.test.ts
• tests/review-coordinator-nonblocking-scope.test.ts
• tests/review-one-call-reviewer-requests.test.ts
• tests/support/review-coordinator-runtime.ts

Included review availability: This review used your included allowance. Your plan provides up to 8 included reviews per hour; 5 remain after this review.