feat(mcp): register loopover_watch_issues as a local stdio tool (#7763)

[kai392]

Summary

• Registers loopover_watch_issues as a local stdio MCP tool (tool count 89 → 90), mirroring the existing remote tool + watch CLI.
• Proxies the same /v1/contributors/:login/watches REST routes (list/watch/unwatch) via manageIssueWatches.
• Follows the feat(mcp): register the maintain REST surface as local stdio tools #6382 / feat(mcp): register loopover_get_outcome_calibration as a local stdio tool #7877 registerStdioTool + stdioToolDescription pattern (no stdio outputSchema).

Closes #7763

Note

Replaces #7948, which was auto-closed after a Codecov uploader GPG signature verification flake on validate-tests (2) (the vitest shard itself passed).

Test plan

• build:mcp + typecheck + branding-drift:check
• vitest coverage: mcp-cli-watch-issues-tool, mcp-tool-rename-aliases (patch ~100%)
• CI green on this PR

[superagent-security]

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

[codecov]

Codecov Report

❌ Patch coverage is 85.71429% with 2 lines in your changes missing coverage. Please review.
⚠️ Please upload report for BASE (main@002a864). Learn more about missing BASE report.

Files with missing lines	Patch %	Lines
packages/loopover-mcp/bin/loopover-mcp.ts	85.71%	0 Missing and 2 partials ⚠️

❌ Your patch status has failed because the patch coverage (85.71%) is below the target coverage (99.00%). You can increase the patch coverage or adjust the target coverage.

Additional details and impacted files

@@           Coverage Diff           @@
##             main    #7953   +/-   ##
=======================================
  Coverage        ?   11.91%           
=======================================
  Files           ?        1           
  Lines           ?     2199           
  Branches        ?      845           
=======================================
  Hits            ?      262           
  Misses          ?     1917           
  Partials        ?       20           

Flag	Coverage Δ
shard-1	0.00% <0.00%> (?)
shard-2	11.91% <85.71%> (?)
shard-3	0.00% <0.00%> (?)

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

Files with missing lines	Coverage Δ
packages/loopover-mcp/bin/loopover-mcp.ts	11.91% <85.71%> (ø)

[loopover-orb]

Caution

🛑 LoopOver review result - fixes required

_{Review updated: 2026-07-21 22:12:25 UTC}

3 files · 1 AI reviewer · no blockers · CI failing · unstable

🛑 Suggested Action - Fix Blockers

Review summary
This registers loopover_watch_issues as a local stdio MCP tool mirroring the existing remote tool and watch CLI, proxying to the same /v1/contributors/:login/watches REST routes via a new manageIssueWatches helper. The wiring is straightforward and consistent with the established registerStdioTool pattern (#6382/#7877), the tool-count bump from 89→90 is correctly reflected in mcp-tool-rename-aliases.test.ts, and the new test exercises list/watch/unwatch/default-action/missing-repoFullName paths against an in-process fixture server. The main gap is codecov/patch failing at 85.71% (below the 99% target), meaning some branch in the new code is untested.

Nits — 6 non-blocking

• The 'leaked secret' flagged at test/unit/mcp-cli-watch-issues-tool.test.ts:36 is just the hardcoded test fixture token `"in-process-token"` used to satisfy the API auth check in tests — not a real secret, no action needed.
• packages/loopover-mcp/bin/loopover-mcp.ts:2328 uses `async (input: any) =>` for the tool handler; the file already uses `any` pervasively for handler inputs elsewhere so this is consistent with existing convention, not a new pattern.
• The magic numbers 3/200/50 in watchIssuesShape (loopover-mcp.ts:461-462) mirror the same bounds used by other write-tool shapes in this file (e.g. writeToolRepoFullName's 3/200, fileIssueShape's labels bound) — consistent with existing style, not worth a new named constant.
• codecov/patch is failing at 85.71%; worth identifying which branch in manageIssueWatches or the new tool handler (e.g. the `changed` payload formatting, or the list-vs-watch-vs-unwatch branches) isn't covered before merge.
• Check the codecov patch report to find the specific uncovered line/branch in loopover-mcp.ts and add a targeted test case for it (e.g., the `payload.changed` truthy branch in the toolResult summary at line ~2330 doesn't look exercised by the current test, which only checks for 'watching|Watching' in the JSON string).
• Possible secret-shaped assignment in the diff (generic_secret_assignment) — Verify the value is not a real credential.

CI checks failing

• codecov/patch — 85.71% of diff hit (target 99.00%)

Decision drivers

• ✅ Code review — No blockers (1 reviewer)
• ✅ Gate result — Passing (No configured blocker found.)

Context & advisory signals — never blocks the verdict

Signal	Result	Evidence
Linked issue	✅ Linked	#7763
Related work	⚠️ 1 scoped overlap	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: 78 registered-repo PR(s), 44 merged, 0 issue(s).
Contributor context	✅ Confirmed Gittensor contributor	kai392; Gittensor profile; 78 PR(s), 0 issue(s).
Improvement	✅ Minor	risk: clean · value: minor · LLM: minor

Linked issue satisfaction

Addressed
The PR adds a registerStdioTool("loopover_watch_issues", ...) block following the same pattern as the PR #6382 siblings, using stdioToolDescription for the description, and reuses a single manageIssueWatches helper for the HTTP calls shared with the existing watch CLI command instead of duplicating logic; it also updates the tool-count tests accordingly.

Review context

• Author: kai392
• Role context: outside_contributor
• Public audience mode: oss maintainer
• Lane context: Repository is configured for direct PR review.
• Public profile languages: JavaScript, Kotlin, Perl, TypeScript, Vue
• Official Gittensor activity: 78 PR(s), 0 issue(s).
• Related work: Titles/paths share 7 meaningful terms. (PR #7950)

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://loopover.ai/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)). 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.