feat(mcp): expose maintainer queue-noise triage via gittensory_get_maintainer_noise

[oktofeesh1]

Summary

The deterministic maintainer-noise report (buildMaintainerNoiseReport, src/signals/reward-risk.ts) ranks which queue-noise sources a maintainer should clear first — open PRs without linked-issue context, broad/churn-style diffs, duplicate clusters, and contributor-intake pressure — and returns a score, level, noiseSources, and recommended maintainerActions. It already powers the @gittensory noise-report PR command but had no MCP surface, so agents/CLI couldn't pull it (it is also absent from gittensory_get_repo_context, which exposes a different subset, and from the decision-pack/miner-dashboard, which are contributor-scoped).

This adds gittensory_get_maintainer_noise (maintainer-authenticated via the existing requireRepoAccess, advisory only), mirroring the merged outcome-calibration serving (#1174): a thin load-or-compute service (src/services/maintainer-noise.ts) that loads the repo's cached signals and runs the existing builder, plus the MCP tool registration + output schema + method. Output flows through the existing redactSensitiveForMcp wrapper.

No linked issue: small, self-evident additive MCP surface over a live builder — same shape and scope as the merged gittensory_get_outcome_calibration (#1174). No new REST route (the per-builder REST routes were deliberately consolidated away), no migration, no auth-policy change.

Scope

• The PR title follows type(scope): short summary Conventional Commit format.
• This PR is focused and does not mix unrelated backend, UI, MCP, docs, dependency, and deploy changes.
• This follows CONTRIBUTING.md and does not reintroduce GitHub Pages, VitePress, site/, or CNAME.
• I linked an issue, or this is small enough that the summary explains why an issue is not needed.

Validation

• git diff --check
• npm run actionlint
• npm run typecheck
• npm run test:coverage — codecov/patch: every changed line and branch in src/services/maintainer-noise.ts and the new src/mcp/server.ts lines is covered (verified via lcov).
• npm run test:workers
• npm run build:mcp
• npm run test:mcp-pack
• npm run ui:openapi:check
• npm run ui:lint
• npm run ui:typecheck
• npm run ui:build
• npm audit --audit-level=moderate (0 vulnerabilities)
• New behavior has unit + integration tests: service unit test (test/unit/maintainer-noise.test.ts, incl. clean-queue + noisy-queue + sanitizer boundary), the MCP call-test in test/unit/mcp-output-schemas.test.ts, and the tool-list assertion in test/integration/api.test.ts.

Safety

• No secrets, wallets, hotkeys, raw trust scores, private rankings, or private maintainer evidence are exposed — output is the same public-safe report the @gittensory noise-report command already posts, routed through redactSensitiveForMcp; a test asserts no wallet/hotkey/payout/reward/trust score terms leak.
• Public text stays sanitized and low-noise; no compensation/optimization implications.
• No auth/cookie/CORS/session changes — the tool reuses the existing requireRepoAccess maintainer guard (no new auth surface).
• MCP behavior is updated and tested (new tool + output schema + call-test).
• No UI changes.
• No docs/changelog changes needed.

Notes

Mirrors the merged gittensory_get_outcome_calibration (#1174) pattern exactly: service + tool + output schema + output-schema test + integration assertion. MCP-tool-only (no REST route), so it does not touch the deliberately-consolidated /v1/contributors/:login/* surface.

[superagent-security]

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

[codecov]

Codecov Report

✅ All modified and coverable lines are covered by tests.
✅ Project coverage is 95.44%. Comparing base (372acb6) to head (0ce78d8).
✅ All tests successful. No failed tests found.

Additional details and impacted files

@@           Coverage Diff           @@
##             main    #1414   +/-   ##
=======================================
  Coverage   95.43%   95.44%           
=======================================
  Files         193      194    +1     
  Lines       21043    21053   +10     
  Branches     7618     7618           
=======================================
+ Hits        20083    20093   +10     
  Misses        383      383           
  Partials      577      577           

Files with missing lines	Coverage Δ
src/mcp/server.ts	95.61% <100.00%> (+0.04%)	⬆️
src/services/maintainer-noise.ts	100.00% <100.00%> (ø)

🚀 New features to boost your workflow:

• 📦 JS Bundle Analysis: Save yourself from yourself by tracking and limiting bundle sizes in JS merges.

[JSONbored]

Screen: ✅ low-risk, on-thesis. It wraps an existing builder already shipping via the @gittensory noise-report command — near-zero new maintenance surface, on the maintainer-agent MCP thesis. Verdict: MERGE — after stripping the "🤖 Generated with Claude Code" line from the PR body (House Rule §5) · gittensor:feature.