feat(mcp): register loopover_get_repo_onboarding_pack as a local stdio tool

[rsnetworkinginc]

Summary

Closes #7756 — loopover_get_repo_onboarding_pack has a remote MCP tool (src/mcp/server.ts) and a maintain onboarding-pack CLI command, but no local stdio MCP tool registration. #6738 added the REST route + CLI but never the matching stdio tool, so a self-host operator using the local MCP server (not the CLI or remote MCP) couldn't call it.

What changed (packages/loopover-mcp/bin/loopover-mcp.ts)

• A registerStdioTool("loopover_get_repo_onboarding_pack", …) block, following the existing sibling get-repo pattern exactly.
• **Reuses the same apiGet(\${prefix}/onboarding-pack/preview${query}`)call** themaintain onboarding-pack CLI already makes (query = refresh === true ? "?refresh=true" : ""`) — no duplicated HTTP logic.
• A repoOnboardingPackShape (owner/repo required, refresh optional boolean) and a STDIO_TOOL_DESCRIPTORS entry (category maintainer, matching the remote registration).

owner/repo resolve the same way as the sibling repo-scoped stdio tools; refresh is optional (omit for the cached preview, true to force a refresh — the server treats only the exact string "true" as a refresh, matching the CLI).

Tests

• New test/unit/mcp-cli-get-repo-onboarding-pack.test.ts drives the tool in-process (the loopover_plan_repo_issues has no REST route, CLI command, or local stdio MCP tool #7764 entrypoint-guard pattern — InMemoryTransport against the exported server) so the registration + handler get real Codecov coverage. Both arms of the refresh ternary are covered (omitted → no query; refresh: true → ?refresh=true). The mcp-cli-harness already had the /v1/repos/:owner/:repo/onboarding-pack/preview route + fixture, so no new harness hook was needed.
• Tool-count invariant in mcp-tool-rename-aliases.test.ts bumped 91 → 92.

Verified locally on top of current main: npm run typecheck clean, npm run build:mcp clean, git diff --check clean, test/unit/mcp-cli-get-repo-onboarding-pack.test.ts + test/unit/mcp-tool-rename-aliases.test.ts all green, and 100% patch coverage on the changed bin/loopover-mcp.ts lines (the single refresh branch covered both ways).

[superagent-security]

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

[loopover-orb]

Warning

⏸️ LoopOver review result - manual review recommended

_{Review updated: 2026-07-22 00:41:08 UTC}

3 files · 1 AI reviewer · no blockers · CI green · dirty

⏸️ Suggested Action - Manual Review

Review summary
This PR registers loopover_get_repo_onboarding_pack as a local stdio tool by adding a Zod input shape, a STDIO_TOOL_DESCRIPTORS entry, and a registerStdioTool handler that proxies to the existing /v1/repos/:owner/:repo/onboarding-pack/preview route, exactly mirroring the sibling get-repo stdio tools and reusing the same query-building logic the CLI already uses. The change is well-scoped, closes issue #7756 as described, and the tool-count invariant bump (94→95) is correctly threaded through both the descriptor test and the tool-rename-aliases test. The new in-process test exercises both arms of the refresh ternary against a real registered handler, which is solid coverage for this thin proxy.

Nits — 5 non-blocking

• The flagged 'generic_secret_assignment' at test/unit/mcp-cli-get-repo-onboarding-pack.test.ts:34 is just a literal placeholder string `"in-process-token"` used as a fixture credential, consistent with the sibling test files — not a real secret, but worth confirming no real token ever ends up in this pattern.
• packages/loopover-mcp/bin/loopover-mcp.ts:1721 uses `any` for the handler args (`async ({ owner, repo, refresh }: any) =>`), matching the existing convention in this file for other registerStdioTool handlers, but it would be nice to type it against `repoOnboardingPackShape` if this file is ever tightened up.
• The long-file smell on loopover-mcp.ts (~1733 lines) is pre-existing and not something this PR should be expected to address given the file's stated single-file design decision noted in its header comment.
• Consider adding a one-line reference in the new test file's header comment to the exact CLI command (`maintain onboarding-pack`) whose apiGet call is being reused, for future readers scanning test intent quickly.
• Possible secret-shaped assignment in the diff (generic_secret_assignment) — Verify the value is not a real credential.

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	#7756
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: 5 registered-repo PR(s), 0 merged, 0 issue(s).
Contributor context	✅ Confirmed Gittensor contributor	rsnetworkinginc; Gittensor profile; 5 PR(s), 0 issue(s).
Improvement	✅ Minor	risk: clean · value: minor

Linked issue satisfaction

Addressed
The PR adds a registerStdioTool block for loopover_get_repo_onboarding_pack that mirrors the sibling pattern, reuses the apiGet call to the same onboarding-pack/preview endpoint used by the CLI, and centralizes the description via stdioToolDescription/STDIO_TOOL_DESCRIPTORS as required, with accompanying tests updating the tool-count invariant.

Review context

• Author: rsnetworkinginc
• 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: 5 PR(s), 0 issue(s).
• Related work: Titles/paths share 8 meaningful terms. (PR #7969)
• Related work: Titles/paths share 10 meaningful terms. (PR #7966)
• Related work: Titles/paths share 8 meaningful terms. (PR #7967)
• 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

[codecov]

Codecov Report

✅ All modified and coverable lines are covered by tests.
✅ Project coverage is 81.78%. Comparing base (8c2950c) to head (6033692).

Additional details and impacted files

@@             Coverage Diff             @@
##             main    #7968       +/-   ##
===========================================
- Coverage   91.87%   81.78%   -10.09%     
===========================================
  Files         735       91      -644     
  Lines       75477    23718    -51759     
  Branches    22960     4552    -18408     
===========================================
- Hits        69344    19398    -49946     
+ Misses       5041     4124      -917     
+ Partials     1092      196      -896     

Flag	Coverage Δ
shard-1	0.00% <0.00%> (-58.35%)	⬇️
shard-2	11.69% <100.00%> (-40.45%)	⬇️
shard-3	0.00% <0.00%> (-50.10%)	⬇️

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	11.69% <100.00%> (-4.69%)	⬇️

... and 644 files with indirect coverage changes

[loopover-orb]

LoopOver is closing this pull request on the maintainer's behalf (conflicts with the base branch — resolve and open a fresh PR). 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.