Commit Graph

4 Commits

Author SHA1 Message Date
Rodin b78d9972ac fix: remove worst-wins escalation logic (#28)
CI / test (pull_request) Successful in 14s
CI / review (gpt-4.1, gpt, GPT_REVIEW_TOKEN) (pull_request) Successful in 23s
CI / review (gpt-5, security, SECURITY_REVIEW.md, SONNET_REVIEW_TOKEN) (pull_request) Successful in 36s
CI / review (gpt-5, sonnet, SONNET_REVIEW_TOKEN) (pull_request) Successful in 39s
2026-05-02 07:04:33 -07:00
Rodin e261976dd8 feat: edit-in-place review updates (no more delete)
CI / test (pull_request) Successful in 13s
CI / review (gpt-4.1, gpt, GPT_REVIEW_TOKEN) (pull_request) Successful in 23s
CI / review (gpt-5, sonnet, SONNET_REVIEW_TOKEN) (pull_request) Successful in 1m37s
CI / review (gpt-5, security, SECURITY_REVIEW.md, SONNET_REVIEW_TOKEN) (pull_request) Successful in 1m43s
Replace the delete-and-repost strategy with edit-in-place:

1. No existing review → POST new (first run)
2. Same state, same body → skip entirely (threads preserved)
3. Same state, body changed → PATCH body in place via timeline API
4. State change needed → PATCH old body to "Superseded", POST new

This preserves conversation threads on inline comments. Replies to
findings are never lost. The only time a new review is posted is on
first run or when the state transitions (APPROVED ↔ REQUEST_CHANGES).

New Gitea client methods:
- EditComment: PATCH /repos/{owner}/{repo}/issues/comments/{id}
- GetTimelineReviewCommentID: finds the comment ID for a review body
  by scanning the issue timeline for the sentinel

Also simplifies shouldEscalate: removes the login parameter requirement
for pre-posting scenarios (uses findOwnReview to get login from existing
review instead).

Tests: findOwnReview (4 cases), EditComment (2 cases),
GetTimelineReviewCommentID (2 cases), shouldEscalate (8 cases updated).
2026-05-01 22:46:45 -07:00
Rodin 1c2292265b feat: skip re-posting when review is unchanged (preserve threads)
CI / test (pull_request) Successful in 14s
CI / review (gpt-4.1, gpt, GPT_REVIEW_TOKEN) (pull_request) Successful in 23s
CI / review (gpt-5, security, SECURITY_REVIEW.md, SONNET_REVIEW_TOKEN) (pull_request) Successful in 1m1s
CI / review (gpt-5, sonnet, SONNET_REVIEW_TOKEN) (pull_request) Successful in 1m28s
Before posting, compare the new review body+event against the existing
review with the same sentinel. If identical, skip entirely — this
preserves conversation threads on inline comments and avoids
re-notifying reviewers for findings they already know about.

Only re-posts when findings actually change (fixed, new, or different).

Tests: 6 cases covering identical, different body, different state,
stale reviews, and different sentinels.
2026-05-01 22:17:36 -07:00
Rodin 436e6a8824 fix: symlink traversal + worst-wins pre-check + user scoping
CI / test (pull_request) Successful in 14s
CI / review (gpt-4.1, gpt, GPT_REVIEW_TOKEN) (pull_request) Successful in 20s
CI / review (gpt-5, security, SECURITY_REVIEW.md, SONNET_REVIEW_TOKEN) (pull_request) Successful in 1m11s
CI / review (gpt-5, sonnet, SONNET_REVIEW_TOKEN) (pull_request) Successful in 1m16s
Security (MAJOR):
- Add filepath.EvalSymlinks after Clean for system-prompt-file
- Re-validate resolved path is still within workspace
- Prevents symlink → /etc/shadow exfiltration via malicious repo

Worst-wins:
- Check BEFORE posting (not after) — no delete+repost dance
- Identify sibling bots by <!-- review-bot: prefix in body
- Only escalates for bot reviews, not human REQUEST_CHANGES
- If sibling bot has REQUEST_CHANGES and we would APPROVE → post
  REQUEST_CHANGES instead

Addresses security review finding #1 (MAJOR) and sonnet finding #1.
2026-05-01 21:31:17 -07:00