feat(mcp): add loopover_get_pr_reviewability tool on both MCP servers

[lourincedaging0-commits]

Summary

The GET /v1/repos/:owner/:repo/pulls/:number/reviewability route is already MCP-auth-aware (isMcpReadRepoAllowed, the same repo-allowlist gate /intelligence → loopover_get_repo_context and /issue-quality → loopover_get_issue_quality use) but had no tool on either server. This wires it up.

• Remote server (src/mcp/server.ts): adds loopover_get_pr_reviewability, mirroring loopover_get_issue_quality exactly — the same canAccessRepo gate, the cached-snapshot-then-compute pattern (serving the persisted pr-reviewability snapshot the route already writes before recomputing), and the same freshnessResponseOutputSchema. Reuses the existing loadContributorFastContext loader and calls the same buildPullRequestReviewability the route does, with identical inputs.
• Local server (packages/loopover-mcp): adds the equivalent apiGet proxy tool, per the convention that a new remote tool gets a local mirror.
• Tests: server-level coverage (forbidden / not_found / cached-snapshot / snapshot timestamp fallback / computed-with-contributor / computed-no-author) and a stdio-proxy test asserting the tool registers and proxies to the correct route.

Response shape matches the loopover_get_issue_quality wrapper; no new response shape invented.

Closes #6154.

[codecov]

Codecov Report

❌ Patch coverage is 94.73684% with 1 line in your changes missing coverage. Please review.
✅ Project coverage is 89.10%. Comparing base (4a5bd94) to head (c436f54).
⚠️ Report is 6 commits behind head on main.

Files with missing lines	Patch %	Lines
src/mcp/server.ts	94.73%	0 Missing and 1 partial ⚠️

❗ There is a different number of reports uploaded between BASE (4a5bd94) and HEAD (c436f54). Click for more details.

HEAD has 1 upload less than BASE

Flag	BASE (4a5bd94)	HEAD (c436f54)
shard-3	1	0

Additional details and impacted files

@@            Coverage Diff             @@
##             main    #6197      +/-   ##
==========================================
- Coverage   95.33%   89.10%   -6.23%     
==========================================
  Files         599      599              
  Lines       47186    47205      +19     
  Branches    15032    15037       +5     
==========================================
- Hits        44983    42063    -2920     
- Misses       1477     3643    +2166     
- Partials      726     1499     +773     

Flag	Coverage Δ
shard-1	43.92% <10.52%> (-0.02%)	⬇️
shard-2	36.65% <10.52%> (-0.02%)	⬇️
shard-3	?
shard-4	34.13% <10.52%> (+0.13%)	⬆️
shard-5	32.20% <10.52%> (+0.71%)	⬆️
shard-6	44.91% <94.73%> (-0.29%)	⬇️

Flags with carried forward coverage won't be shown. Click here to find out more.

Files with missing lines	Coverage Δ
src/mcp/server.ts	94.12% <94.73%> (-2.09%)	⬇️

... and 106 files with indirect coverage changes

[superagent-security]

Superagent didn't find any vulnerabilities or security issues in this PR.

[loopover-orb]

Caution

🟥🟥🟥🟥🟥🟥🟥🟥🟥🟥🟥🟥

🛑 LoopOver review result - fixes required

_{Review updated: 2026-07-15 21:17:08 UTC}

5 files · 1 AI reviewer · no blockers · readiness 82/100 · CI failing · blocked

🛑 Suggested Action - Fix Blockers

Review summary
The AI review returned non-blocking notes for this change but did not include a separate narrative summary. Review the nits below before deciding this PR.

Nits — 2 non-blocking

• Consider adding a light runtime check (e.g. verifying `payload.pullNumber` matches `input.number`) before trusting a cached snapshot, so a targetKey collision or schema drift surfaces as a mismatch rather than a silently wrong report.
• The local server's `apiGet` proxy test only exercises the happy path with `number: 7`; consider asserting the client-side zod validation rejects `number: 0` or a negative number to lock in the `positive()` constraint client-side too.

CI checks failing

• codecov/patch — 94.73% of diff hit (target 99.00%)
• validate
• validate-tests (3)

Signal	Result	Evidence
Code review	✅ No blockers	1 reviewer
Linked issue	✅ Linked	#6154
Related work	⚠️ 3 scoped overlaps	Top overlaps are listed below; lower-confidence bulk is hidden.
Change scope	❌ 8/20	High review scope from cached public metadata (1 linked issue).
Validation posture	✅ 25/25	PR body includes validation/test evidence.
Contributor workload	✅ 10/10	Author activity: 85 registered-repo PR(s), 35 merged, 5 issue(s).
Contributor context	✅ Confirmed Gittensor contributor	lourincedaging0-commits; Gittensor profile; 85 PR(s), 5 issue(s).
Gate result	✅ Passing	No configured blocker found.
Improvement	✅ Minor	risk: clean · value: minor · LLM: minor

Review context

• Author: lourincedaging0-commits
• Role context: outside_contributor
• Public audience mode: oss maintainer
• Lane context: Repository is configured for direct PR review.
• Public profile languages: not available
• Official Gittensor activity: 85 PR(s), 5 issue(s).
• Related work: Items reference the same linked issue feat(mcp): add an MCP tool for GET /v1/repos/:owner/:repo/pulls/:number/reviewability (route already MCP-auth-aware, no tool on either server) #6154. (issue #6154)
• Related work: Open PR work references issue feat(mcp): add an MCP tool for GET /v1/repos/:owner/:repo/pulls/:number/reviewability (route already MCP-auth-aware, no tool on either server) #6154. (issue #6154)
• Related work: Items reference the same linked issue feat(mcp): register 4 maintainer/repo-owner intake tools in packages/loopover-mcp (get_skipped_pr_audit/get_issue_quality/get_registration_readiness/get_config_recommendation) #6151. (issue #6151, PR #6199)
• Additional title-only matches omitted; title-only overlap does not block.

Contributor next steps

• Start here: Review top overlaps.
• Then work through the remaining 2 steps in the Signals table above.

Signal definitions

• Related work = same linked issue, overlapping active PRs, or title/path similarity.
• Change scope = cached public metadata such as size labels, draft state, and review-burden hints.
• Validation posture = whether the PR provides enough public validation/test evidence for maintainer review.
• Contributor workload = public contributor activity and cleanup pressure, not a repo-wide quality failure.
• Contributor context = public GitHub/Gittensor identity context; non-Gittensor status is not a blocker.

🧪 Chat with LoopOver

Ask LoopOver a question about this PR directly in a comment — grounded only in the same cached, public-safe facts shown above, never a new claim.

• @loopover ask <question> answers contribution-quality Q&A with source citations and freshness.
• @loopover chat <question> answers in natural prose from cached decision-pack facts via local inference (maintainer/collaborator; read-only).
• A plain-language @loopover mention with a real question is routed to the closest matching read-only command automatically — no exact syntax required.

Full command reference: https://gittensory.aethereal.dev/docs/loopover-commands

🧪 Experimental — new and may change.

_{🟩 Safe / merged · 🟦 Advisory · 🟨 Held for review · 🟥 Blocked / closed}

---

💰 Earn for open-source contributions like this. Gittensor lets GitHub contributors earn for the work they already do — register to start earning →.

Checked by LoopOver, a quiet PR intelligence layer for OSS maintainers.

• Re-run LoopOver review

[loopover-orb]

LoopOver is closing this pull request on the maintainer's behalf (CI is failing (codecov/patch, validate, validate-tests (3))). This is an automated maintenance action — to pursue this change, please open a new pull request with the issues resolved. Closed PRs may be analyzed later to improve review accuracy, but they are not automatically reopened or re-reviewed.