• 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 the docs clarification after normal docs review and current-head docs validation, without changing Voyage runtime credential resolution.

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

Not applicable as a runtime reproduction. The docs gap is source-verifiable on current main: the Voyage reference lacks setup steps while the memory config docs, plugin manifest, and doctor guidance define the credential path.

Is this the best way to solve the issue?

Yes. Adding a short Setup section to the Voyage plugin reference is a narrow maintainable fix for the linked docs gap and avoids duplicating the full memory configuration reference.

Label changes:

• add rating: 🐚 platinum hermit: Current PR rating is 🐚 platinum hermit because proof is 🌊 off-meta tidepool, patch quality is 🐚 platinum hermit, and Focused docs-only PR with no blocking findings and source-aligned content; merge confidence mainly depends on current-head docs validation.
• add status: 👀 ready for maintainer look: ClawSweeper has no concrete contributor-facing blocker left for this PR. Not applicable: Real behavior proof is not required because this PR only changes files under docs/.
• remove impact:auth-provider: Current review selected no impact labels.

Label justifications:

• P3: This is a low-risk docs-only clarification for an existing provider setup path.
• rating: 🐚 platinum hermit: Current PR rating is 🐚 platinum hermit because proof is 🌊 off-meta tidepool, patch quality is 🐚 platinum hermit, and Focused docs-only PR with no blocking findings and source-aligned content; merge confidence mainly depends on current-head docs validation.
• status: 👀 ready for maintainer look: ClawSweeper has no concrete contributor-facing blocker left for this PR. Not applicable: Real behavior proof is not required because this PR only changes files under docs/.

Acceptance criteria:

• node scripts/docs-list.js
• node scripts/check-docs-mdx.mjs docs README.md
• git diff --check

What I checked:

• PR diff scope: The provided live PR patch modifies only docs/plugins/reference/voyage.md, adding a Setup section with API key options, a memory-search config example, openclaw configure --section model, openclaw memory status --deep, and a link to /reference/memory-config. (docs/plugins/reference/voyage.md:9, 71ae12554e5c)
• Current main docs gap: Current main's Voyage reference contains only the short summary plus Distribution and Surface sections; it does not document the API key or memory-search setup path that this PR adds. Public docs: docs/plugins/reference/voyage.md. (docs/plugins/reference/voyage.md:10, 110042d840bb)
• Credential contract source: The canonical memory config reference already lists Voyage with VOYAGE_API_KEY and models.providers.voyage.apiKey, matching the PR's setup text. Public docs: docs/reference/memory-config.md. (docs/reference/memory-config.md:116, 110042d840bb)
• Plugin manifest source: The bundled Voyage plugin declares the memoryEmbeddingProviders contract for voyage and maps the provider auth env var to VOYAGE_API_KEY. (extensions/voyage/openclaw.plugin.json:8, 110042d840bb)
• Diagnostic command alignment: Doctor memory-search guidance already tells users with a configured remote provider and missing API key to use openclaw configure --section model and verify with openclaw memory status --deep. (src/commands/doctor-memory-search.ts:495, 110042d840bb)
• Docs index route: The docs index includes plugins/reference/voyage.md as the Voyage plugin reference and reference/memory-config.md as the memory configuration reference, so the PR's link target is discoverable in the current docs set. Public docs: docs/plugins/reference/voyage.md. (docs/plugins/reference/voyage.md:4, 110042d840bb)

Likely related people:

• Ayaan Zaidi: Current checkout blame and log for the Voyage reference, memory config reference, Voyage manifest, and memory doctor guidance point to this contributor on the relevant current-main lines. (role: recent area contributor; confidence: medium; commits: ac28341ebfcc; files: docs/plugins/reference/voyage.md, docs/reference/memory-config.md, extensions/voyage/openclaw.plugin.json)
• stielemans: The PR discussion includes a merge-gate pass from this reviewer for the same docs-only surface, making them a useful routing contact for the current review state. (role: recent reviewer; confidence: medium; files: docs/plugins/reference/voyage.md)

Codex review notes: model gpt-5.5, reasoning high; reviewed against 110042d840bb.

• 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.