feat(mcp): CLI stdio mirror for loopover_get_repo_outcome_patterns

[RealDiligent]

Summary

• Register loopover_get_repo_outcome_patterns as a stdio CLI tool that proxies GET /v1/repos/:owner/:repo/outcome-patterns (same ownerRepoShape + apiGet pattern as loopover_get_maintainer_noise).
• Bump the stdio tool-count pin from 74 → 75 and add fixture + unit coverage.

Closes #6734.

Test plan

• CI validate-code / unit tests green
• codecov/patch ≥ 99%
• loopover-mcp tools --json includes the new tool and reports count 75
• Stdio call hits /outcome-patterns and returns the fixture payload

[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 93.71%. Comparing base (a4310f1) to head (03b78dd).
⚠️ Report is 1 commits behind head on main.

Additional details and impacted files

@@             Coverage Diff             @@
##             main    #6962       +/-   ##
===========================================
+ Coverage   82.38%   93.71%   +11.32%     
===========================================
  Files         685      685               
  Lines       68379    68379               
  Branches    18730    18730               
===========================================
+ Hits        56337    64080     +7743     
+ Misses       9594     3302     -6292     
+ Partials     2448      997     -1451     

Flag	Coverage Δ
shard-1	43.75% <ø> (?)
shard-2	36.80% <ø> (+0.01%)	⬆️
shard-3	32.93% <ø> (+0.17%)	⬆️
shard-4	33.85% <ø> (?)
shard-5	32.13% <ø> (-0.04%)	⬇️
shard-6	45.74% <ø> (ø)

Flags with carried forward coverage won't be shown. Click here to find out more.
see 202 files with indirect coverage changes

[loopover-orb]

Tip

✅ LoopOver review result - approve/merge recommended

_{Review updated: 2026-07-17 16:04:43 UTC}

4 files · 1 AI reviewer · no blockers · readiness 80/100 · CI green · unknown

✅ Suggested Action - Approve/Merge

• safe to merge

Review summary
This PR registers loopover_get_repo_outcome_patterns as a thin stdio GET proxy to /v1/repos/:owner/:repo/outcome-patterns, following the exact same ownerRepoShape + apiGet pattern used by loopover_get_maintainer_noise. The tool-count pin bump from 74 to 75 is consistent across the descriptor list and the alias-retirement test, and new fixture + unit coverage (registration, proxy call, CLI listing) directly exercises the added code. The change is narrow, closes #6734, and CI is green across all checks.

Nits — 5 non-blocking

• The stdioToolDescription lookup for 'loopover_get_repo_outcome_patterns' isn't shown in this diff — confirm the description-generation function has a matching entry or falls back safely (packages/loopover-mcp/bin/loopover-mcp.js:1904).
• test/unit/mcp-cli-repo-outcome-patterns.test.ts duplicates a large amount of harness boilerplate (connect/disconnect) already present in mcp-tool-rename-aliases.test.ts — consider factoring into the shared support module.
• The fixture payload in mcp-cli-harness.ts includes a full nested 'patterns' object with evidenceCompleteness, but the test only loosely asserts substrings ('patterns', 'fresh') rather than validating the evidenceCompleteness field is actually surfaced end-to-end.
• Verify stdioToolDescription('loopover_get_repo_outcome_patterns') resolves to a non-empty string used at packages/loopover-mcp/bin/loopover-mcp.js:1904, since the inline description constant defined a few lines above appears unused by the registerStdioTool call.
• Consider asserting the exact JSON shape of the proxied response (e.g., evidenceCompleteness: 'partial') in mcp-cli-repo-outcome-patterns.test.ts rather than loose substring checks, to guard against silent payload drift.

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	#6734
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: 389 registered-repo PR(s), 194 merged, 33 issue(s).
Contributor context	✅ Confirmed Gittensor contributor	RealDiligent; Gittensor profile; 389 PR(s), 33 issue(s).
Improvement	✅ Minor	risk: clean · value: minor · LLM: minor

Linked issue satisfaction

Addressed
The PR registers loopover_get_repo_outcome_patterns as a stdio tool using ownerRepoShape + apiGet against GET /v1/repos/:owner/:repo/outcome-patterns exactly as requested, bumps the tool-count pin from 74 to 75, and adds both a dedicated unit test and a fixture. The description doesn't explicitly claim --json support, but the tool follows the existing registerStdioTool pattern which already provid

Review context

• Author: RealDiligent
• 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: 389 PR(s), 33 issue(s).
• Related work: Titles/paths share 6 meaningful terms. (issue #6747)
• Related work: Titles/paths share 5 meaningful terms. (PR #6963)
• Related work: Titles/paths share 7 meaningful terms. (PR #6958)
• 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://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 approves — the gate is satisfied and CI is green.