Best possible solution:

Land after maintainers explicitly accept the read-only command/output contract and the safe-profile exposure, keeping accept/reject mutation and style-only suggestions out of this PR.

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

Not applicable as a bug reproduction; this is a feature PR for a missing Docs suggestions surface. Source inspection confirms current main lacks the command and any SUGGESTIONS_INLINE request path, while the PR adds focused fixtures and command-path coverage.

Is this the best way to solve the issue?

Yes, if maintainers accept the product and safety scope: a dedicated read-only suggestions list command using SUGGESTIONS_INLINE is a narrow implementation for the linked request. The safer alternative, if the profile exposure is too broad, is to ship the command without adding it to baked safe profiles yet.

AGENTS.md: found and applied where relevant.

Codex review notes: model internal, reasoning high; reviewed against 65e1c851ee5f.

Label changes:

• add merge-risk: 🚨 security-boundary: The PR expands baked safe-profile read access to pending/deleted Docs suggestion text, which can expose content outside the accepted document body.
• add status: ⏳ waiting on author: ClawSweeper has contributor-facing work open and is waiting for author action. Not applicable: The external-contributor proof gate does not apply to this collaborator-authored PR; the PR body nevertheless records exact-head local/CI/live read proof and clearly documents the blocked live pending-suggestion fixture.
• remove status: 👀 ready for maintainer look: Current PR status label is status: ⏳ waiting on author.

Label justifications:

• P2: This is a bounded Docs CLI feature in an existing area with limited blast radius but real maintainer-facing contract decisions.
• merge-risk: 🚨 security-boundary: The PR expands baked safe-profile read access to pending/deleted Docs suggestion text, which can expose content outside the accepted document body.
• merge-risk: 🚨 other: Green CI does not settle the new public command/output contract or the documented live pending-suggestion proof gap.
• rating: 🦐 gold shrimp: Overall readiness is 🦐 gold shrimp; proof is 🦐 gold shrimp and patch quality is 🦐 gold shrimp.
• status: ⏳ waiting on author: ClawSweeper has contributor-facing work open and is waiting for author action. Not applicable: The external-contributor proof gate does not apply to this collaborator-authored PR; the PR body nevertheless records exact-head local/CI/live read proof and clearly documents the blocked live pending-suggestion fixture.

Security concerns:

• [medium] Accept safe-profile suggestion text exposure — safety-profiles/readonly.yaml:147
  The diff adds docs.suggestions.list to both bundled read-only profiles, which lets those profiles read pending/deleted suggestion text that normal document text reads may not show; maintainers should accept or narrow that policy before merge.
  Confidence: 0.83

What I checked:

• Repository policy read: AGENTS.md was read fully; its PR review guidance to inspect with gh pr view and gh pr diff without switching branches was applied. (AGENTS.md:37, 65e1c851ee5f)
• No maintainer notes present: The checkout has skill files under .agents/, but no .agents/maintainer-notes/ files matching the touched Docs, generated-docs, or safety-profile surfaces. (65e1c851ee5f)
• Current main lacks the suggestions surface: A current-main search found no docs suggestions command registration, no SuggestionsViewMode( setter, and no suggested insertion/deletion renderer in the inspected command/docs/profile paths. (65e1c851ee5f)
• Latest release shares the missing Docs surface: No relevant Docs command/read/docs/profile files differ between v0.31.1 and current main, so the latest release also lacks this suggestions command. (608aa46e7b9c)
• PR implements the read path: The PR head adds DocsSuggestionsListCmd, calls Documents.Get(...).SuggestionsViewMode("SUGGESTIONS_INLINE"), optionally includes tab content, and emits JSON/table output. (internal/cmd/docs_suggestions.go:43, cdcd3019d995)
• PR covers the reviewed suggestion carriers: The added tests cover text runs, structural table/row/cell/TOC IDs, non-text paragraph elements, section breaks, positioned objects, inline-object maps, list maps, request parameters, tab projection, and output formatting. (internal/cmd/docs_suggestions_test.go:15, cdcd3019d995)

Likely related people:

• steipete: Current-main blame and history tie the Docs command registry, raw/tab projection, recent Docs command expansion, safety-profile surface, and this PR's implementation to this person. (role: recent Docs command/read area contributor; confidence: high; commits: 608aa46e7b9c, 0a7e6425384b, 454d116856f1; files: internal/cmd/docs.go, internal/cmd/docs_read.go, internal/cmd/docs_helpers.go)
• alexknowshtml: History shows the core Docs tab support and read/edit command structure that this PR's --tab suggestions path builds on dates to the tab support feature work. (role: Docs tabs/read feature introducer; confidence: medium; commits: 2f5131995552; files: internal/cmd/docs.go, internal/cmd/docs_commands_test.go)
• johnbenjaminlewis: History shows adjacent per-tab Google Doc export and tab flag naming work relevant to the PR's tab-selection contract. (role: adjacent tab export contributor; confidence: medium; commits: 26e01cfa972a, 50f506dd3aad; files: internal/cmd/docs_tab_export.go, internal/cmd/docs.go)

• 🦀 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.

• 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.