• ClawSweeper keeps one durable marker-backed review comment per issue or PR.
• Re-runs edit this comment so the latest verdict, findings, and automation markers stay together instead of adding duplicate bot comments.
• A fresh review can be triggered by eligible @clawsweeper re-review comments, exact-item GitHub events, scheduled/background review runs, or manual workflow dispatch.
• PR/issue authors and users with repository write access can comment @clawsweeper re-review or @clawsweeper re-run on an open PR or issue to request a fresh review only.
• Maintainers can also comment @clawsweeper review to request a fresh review only.
• Fresh-review commands do not start repair, autofix, rebase, CI repair, or automerge.
• Maintainer-only repair and merge flows require explicit commands such as @clawsweeper autofix, @clawsweeper automerge, @clawsweeper fix ci, or @clawsweeper address review.
• Maintainers can comment @clawsweeper explain to ask for more context, or @clawsweeper stop to stop active automation.

• 🦀 challenger crab: rare, exceptional readiness with strong proof, clean implementation, and convincing validation.
• 🦞 diamond lobster: very strong readiness with only minor maintainer review expected.
• 🐚 platinum hermit: good normal PR, likely mergeable with ordinary maintainer review.
• 🦐 gold shrimp: useful signal, but proof or patch confidence is still limited.
• 🦪 silver shellfish: thin signal; proof, validation, or implementation needs work.
• 🧂 unranked krab: not merge-ready because proof is missing/unusable or there are serious correctness or safety concerns.
• 🌊 off-meta tidepool: rating does not apply to this item.

Shiny media proof means a screenshot, video, or linked artifact directly shows the changed behavior. Runtime, network, CSP, and security claims still need visible diagnostics.

Best possible solution:

Land this after normal maintainer review and CI, keeping the coalescing opt-in to the idle abort notice so other TUI system messages remain unchanged.

Do we have a high-confidence way to reproduce the issue?

Yes from source inspection: current main appends no active run on every idle Esc abort, so repeated calls produce repeated rows. I did not drive an interactive TUI in this read-only review.

Is this the best way to solve the issue?

Yes; the PR uses a narrow opt-in coalescing path on the one noisy idle-abort notice and preserves ordinary system-message behavior.

Label changes:

• add P3: This is a small TUI ergonomics improvement with focused tests and limited blast radius.
• add proof: 📸 screenshot: Contributor real behavior proof includes screenshot evidence. The external proof gate does not apply to this MEMBER/maintainer-labeled PR, though the attached before/after screenshots visibly show the changed TUI row behavior.
• add rating: 🦞 diamond lobster: Current PR rating is 🦞 diamond lobster because proof is 🦞 diamond lobster, patch quality is 🦞 diamond lobster, and Small, well-scoped TUI patch with focused tests, visual proof, and no blocking findings in this review.
• add status: 👀 ready for maintainer look: ClawSweeper has no concrete contributor-facing blocker left for this PR. Not applicable: The external proof gate does not apply to this MEMBER/maintainer-labeled PR, though the attached before/after screenshots visibly show the changed TUI row behavior.

Label justifications:

• P3: This is a small TUI ergonomics improvement with focused tests and limited blast radius.
• rating: 🦞 diamond lobster: Current PR rating is 🦞 diamond lobster because proof is 🦞 diamond lobster, patch quality is 🦞 diamond lobster, and Small, well-scoped TUI patch with focused tests, visual proof, and no blocking findings in this review.
• status: 👀 ready for maintainer look: ClawSweeper has no concrete contributor-facing blocker left for this PR. Not applicable: The external proof gate does not apply to this MEMBER/maintainer-labeled PR, though the attached before/after screenshots visibly show the changed TUI row behavior.
• proof: 📸 screenshot: Contributor real behavior proof includes screenshot evidence. The external proof gate does not apply to this MEMBER/maintainer-labeled PR, though the attached before/after screenshots visibly show the changed TUI row behavior.

What I checked:

• Current main behavior: On current main, the idle abort path appends a fresh no active run system message whenever there is no active or pending run. (src/tui/tui-session-actions.ts:400, 60d200f79719)
• Patch implementation: The PR keeps coalescing opt-in by adding coalesceConsecutive handling to ChatLog.addSystem, updates the existing text node with an xN suffix, and resets the repeatable state when non-system content is appended. (src/tui/components/chat-log.ts:128, f715aa5db9a5)
• Idle abort route: The PR routes only the no-active-run Esc abort notice through the coalescing option, leaving other system messages on the ordinary append path. (src/tui/tui-session-actions.ts:400, f715aa5db9a5)
• Focused coverage: New tests cover repeated coalescing, ordinary non-coalesced system messages, reset after user content, and the idle abort action passing coalesceConsecutive: true. (src/tui/components/chat-log.test.ts:18, f715aa5db9a5)
• Session-action coverage: The session-action test checks that abortActive() calls addSystem("no active run", { coalesceConsecutive: true }) and requests a render when idle. (src/tui/tui-session-actions.test.ts:389, f715aa5db9a5)
• Visual proof: The PR body includes before/after screenshots; the inspected after screenshot shows a single no active run x35 row where the before screenshot showed repeated duplicate rows. (f715aa5db9a5)

Likely related people:

• Super Zheng: git blame and git log --follow show the current ChatLog and abortActive TUI surface landing in b77f36fb1cbdc48d9c0a8c02e3e526599547a4d4. (role: introduced behavior; confidence: high; commits: b77f36fb1cbd; files: src/tui/components/chat-log.ts, src/tui/tui-session-actions.ts)
• medns: The commit that introduced the current TUI chat-log/session-action files lists medns as a co-author in the commit metadata. (role: co-author on relevant surface; confidence: medium; commits: b77f36fb1cbd; files: src/tui/components/chat-log.ts, src/tui/tui-session-actions.ts)
• odysseus0: The same introducing commit lists odysseus0 as a co-author and reviewed-by route for the current TUI surface. (role: co-author and reviewer on relevant surface; confidence: medium; commits: b77f36fb1cbd; files: src/tui/components/chat-log.ts, src/tui/tui-session-actions.ts)

Codex review notes: model gpt-5.5, reasoning high; reviewed against 60d200f79719.

• Eggs appear after the PR passes real-behavior proof. It is here for vibes, not verdicts: it does not change labels, ratings, merge decisions, or automation.
• The shell reacts to review momentum: open follow-up work warms it up, re-review makes it wobble, and a clean final review lets it hatch.
• Hatchability usually comes from sufficient real-behavior proof, no blocking P0/P1/P2 findings, no security attention needed, and clean correctness. A merged PR is already final, so merge makes the egg hatchable independently.
• The hatch is seeded from this repository and PR number, so the same PR keeps the same creature; the reviewed head SHA can only change safe visual details.
• Rarity is just collectible sparkle: 🥚 common, 🌱 uncommon, 💎 rare, ✨ glimmer, and 🌈 legendary.