• 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:

Merge the focused table-mode threading after adding visible Telegram proof that a chunked Markdown table with markdown.tables: bullets renders as bullet-style content rather than raw pipes.

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

Yes, source inspection gives a high-confidence path: call telegramOutbound.chunker on a Markdown table with formatting.tableMode: "bullets"; current main drops that option before markdownToTelegramChunks, while the PR forwards it.

Is this the best way to solve the issue?

Yes, the PR is the narrow maintainable fix for the functional bug because it reuses the existing outbound formatting contract and keeps explicit HTML parse-mode chunking unchanged.

Label changes:

• remove merge-risk: 🚨 compatibility: Current PR review selected no merge-risk labels.

Label justifications:

• P2: This fixes a normal Telegram rendering bug with a narrow channel/outbound chunking surface and no evidence of data loss, security impact, or core runtime outage.
• rating: 🦪 silver shellfish: Current PR rating is 🦪 silver shellfish because proof is 🦪 silver shellfish, patch quality is 🐚 platinum hermit, and The patch is small and well targeted with focused regression coverage, but merge readiness is capped by missing real Telegram proof.
• status: 📣 needs proof: The PR needs real behavior proof before ClawSweeper can clear the contributor ask. Needs real behavior proof before merge: The PR body provides local Vitest/autoreview output only and explicitly says a live Telegram send was not tested; a redacted screenshot, recording, transcript, terminal output, or log from a real Telegram send is still needed. After adding proof, update the PR body; ClawSweeper should re-review automatically. If it does not, the PR author or someone with repository write access can comment @clawsweeper re-review.
• mantis: telegram-visible-proof: Mantis should capture Telegram visible proof. This changes visible Telegram chat rendering for chunked Markdown tables, which is straightforward to show in a short Telegram Desktop proof.

What I checked:

• Current main drops table mode in the HTML chunk wrapper: markdownToTelegramChunks accepts options.tableMode, but markdownToTelegramHtmlChunks on current main calls it without forwarding options. (extensions/telegram/src/format.ts:776, 87b204657570)
• Current main outbound chunker omits table mode: The Telegram outbound chunker receives formatting context but calls markdownToTelegramHtmlChunks(text, limit) without ctx.formatting.tableMode. (extensions/telegram/src/outbound-adapter.ts:49, 87b204657570)
• Existing formatting contract already carries table mode: OutboundDeliveryFormattingOptions includes tableMode, and the outbound planner passes formatting into channel chunkers, so the PR uses an existing contract rather than adding a new config surface. (src/infra/outbound/formatting.ts:4, 87b204657570)
• PR diff is focused on Telegram source/test plus changelog: Live PR files show only CHANGELOG.md, extensions/telegram/src/format.ts, extensions/telegram/src/outbound-adapter.ts, and extensions/telegram/src/telegram-outbound.test.ts changed at head e697596bfcb7624bcbcbc49b46cd8ad207cd261e. (extensions/telegram/src/outbound-adapter.ts:53, e697596bfcb7)
• PR body lacks live Telegram proof: The PR body reports a local Telegram extension Vitest shard and autoreview, and explicitly says a live Telegram send was not tested. (e697596bfcb7)
• Telegram maintainer review standard requires live proof here: The Telegram maintainer note says behavior PRs touching transport, streaming, topics, callbacks, authorization, or reply context need real Telegram proof over synthetic-only validation. (.agents/maintainer-notes/telegram.md:37, 87b204657570)

Likely related people:

• steipete: Local git blame on current main attributes the current Telegram outbound chunker and formatter wrapper lines to Peter Steinberger, and the related issue review also identifies him with recent markdown table configuration work. (role: recent area contributor; confidence: high; commits: c21ca883b0cc, b77e73065775, bd7d362d3b32; files: extensions/telegram/src/format.ts, extensions/telegram/src/outbound-adapter.ts, src/config/markdown-tables.ts)
• scoootscooob: The related issue review identifies the Telegram extension move/refactor as carrying the affected formatter and outbound adapter surfaces into extensions/telegram/src. (role: major Telegram refactor contributor; confidence: medium; commits: e5bca0832fbd; files: extensions/telegram/src/format.ts, extensions/telegram/src/outbound-adapter.ts)
• George Zhang: The related issue review identifies prior Telegram Markdown table conversion work in the Markdown IR and Telegram formatter path as relevant to this bug's table-mode behavior. (role: introduced Telegram table rendering behavior; confidence: medium; commits: a1413a011e86; files: src/markdown/ir.ts, extensions/telegram/src/format.ts)

Codex review notes: model gpt-5.5, reasoning high; reviewed against 87b204657570.

• The egg game starts only after the PR passes the real-behavior proof check.
• Before that, no creature or rarity is rolled. The treat waits for real proof.
• This is still just collectible flavor: proof affects review readiness, not creature quality.