fix: review fires for all tasks — commit then review committed diff, merge on pass

Previous flow reviewed uncommitted changes, so when a task agent
self-committed its work the review was silently skipped (no uncommitted
changes → review loop body never entered). This caused reviews to fire
inconsistently across tasks.

New review-gated flow (when autoReview is on):
1. Execute task
2. Ensure committed — commit session fallback when the agent didn't
   self-commit (handles both self-commit and no-commit agents)
3. Review the COMPLETE task diff (baseRef..HEAD) captured before
   execution, so the reviewer sees all commits not just the latest
4. On fail → re-execute with feedback → commit → re-review (same
   baseRef, so reviewer sees complete state including fixes)
5. On pass → merge worktree (all changes already committed)

Commit is now mandated when autoReview is on (autoCommit forced true,
not asked at startup). autoCommit only asked when autoReview is off.

Add captureGitHead + getCommitRangeDiff helpers to utils.ts. Switch
review prompt from buildReviewPromptUncommitted to buildReviewPrompt
(reviewing committed changes, not uncommitted).
This commit is contained in:
2026-07-22 18:29:29 -04:00
parent 0ef540ed47
commit 74c9ead7af
5 changed files with 200 additions and 98 deletions

View File

@@ -211,12 +211,13 @@ export interface RalpiConfig {
models: string[];
/** Spawn a follow-up agent to commit changes after each task completes */
autoCommit: boolean;
/** Spawn a review agent to review uncommitted changes against the
* task description BEFORE committing. On a 'fail' verdict the task is
* re-executed with the review feedback injected (loops until pass or
* maxReviewRetries is exhausted). When autoCommit is also enabled, the
* commit runs after the review passes (or retries exhaust); otherwise
* changes are left uncommitted. */
/** Spawn a review agent to review the task's committed changes against
* the task description. When autoReview is on, commit is mandated:
* changes are committed (via commit session fallback when the agent
* didn't self-commit), then the COMPLETE diff (baseRef..HEAD) is
* reviewed. On 'fail' the task is re-executed with feedback (loops
* until pass or maxReviewRetries). On pass the worktree merges.
* When autoReview is off, autoCommit controls standalone commit. */
autoReview: boolean;
/** Persist the full review output to `.ralpi/reviews/<task-id>.md`.
* Only active when autoReview is true and the user opts in at loop start. */
@@ -236,13 +237,12 @@ export interface RalpiConfig {
reviewTimeoutMs: number;
/** Max review-fix re-execution attempts before giving up (0 = no retries;
* review runs once, reject = stop). Active whenever autoReview is
* enabled. On exhaustion: if autoCommit is enabled, the changes are
* committed anyway; if reviewBlockOnFail is set, the task is marked
* failed instead of committing. */
* enabled. On exhaustion the task proceeds with its committed changes
* (the worktree merges) unless reviewBlockOnFail is set. */
maxReviewRetries: number;
/** When true, a 'fail' review verdict after exhausting maxReviewRetries
* marks the task as failed instead of leaving changes (committing when
* autoCommit, or leaving uncommitted otherwise). */
* marks the task as failed instead of proceeding with its committed
* changes (the worktree does not merge). */
reviewBlockOnFail: boolean;
/** Maximum total duration for the entire loop execution in milliseconds (0 = no limit). Checked between batches — in-progress tasks finish naturally. */
loopTimeoutMs: number;