feat(mcp): add REST + CLI + stdio surfaces for loopover_plan_repo_issues

[xfodev]

Summary

loopover_plan_repo_issues (backed by generateIssuePlanDrafts) shipped only as a remote MCP tool (via Epic #7424, after the MCP-parity milestone closed), so it never got the REST + CLI + local-stdio mirror every other repo-scoped tool has. This adds all three:

• REST: POST /v1/repos/:owner/:repo/issue-plan-drafts/generate (src/api/routes.ts + src/openapi/spec.ts), gated by requireAppRole + requireSessionRepoAccess, with the explicit_create_requires_dry_run_false create-safety guard (a bare create is rejected; only {create:true, dryRun:false} reaches the write path).
• CLI: loopover-mcp maintain plan-issues --goal "..." (dry-run by default; --create/--limit/--json).
• stdio tool: loopover_plan_repo_issues, proxying the REST mirror.

Coverage / testability

packages/loopover-mcp/bin/loopover-mcp.ts is a CLI dispatcher otherwise only exercised via subprocess spawn (which v8 can't instrument). It adds an isProcessEntrypoint() guard + runAsCliEntrypoint flag so a unit test can import the module and drive runCli/maintainCli in-process without hijacking argv or binding stdin (the untestable server.connect(new StdioServerTransport()) carries a /* v8 ignore */). test/unit/mcp-cli-plan-issues.test.ts drives both the maintain plan-issues CLI (incl. --help) and the stdio tool in-process against both the built .js and .ts; test/unit/routes-issue-plan-draft.test.ts covers the REST route (session + static-token, cross-repo rejection, create-safety); and test/unit/mcp-tool-rename-aliases.test.ts's tool-count invariant is bumped 79 → 80.

Verified on latest main: mcp-cli + routes + openapi + tool-count tests pass, tsc --noEmit clean, ui:openapi:check / command-reference:check / test:mcp-pack clean, git diff --check clean, and every changed line in routes.ts / spec.ts / loopover-mcp.ts is Codecov-covered.

Closes #7764

_{(Supersedes #7834 and #7846. #7834 was gate-closed on a base conflict — the bin migration removed the committed loopover-mcp.js from main, making its .js edit a modify/delete conflict; this branch is .ts-only. #7846 was gate-closed because the new tool takes the registered count 79 → 80, which the mcp-tool-rename-aliases invariant asserts — now updated.)}

[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 83.25%. Comparing base (fa21f3e) to head (4cebe58).

Additional details and impacted files

@@            Coverage Diff             @@
##             main    #7856      +/-   ##
==========================================
- Coverage   91.40%   83.25%   -8.15%     
==========================================
  Files         730       91     -639     
  Lines       74763    26027   -48736     
  Branches    22815     5325   -17490     
==========================================
- Hits        68335    21669   -46666     
+ Misses       5385     4051    -1334     
+ Partials     1043      307     -736     

Flag	Coverage Δ
shard-1	18.51% <6.12%> (-37.75%)	⬇️
shard-2	33.03% <57.14%> (-18.10%)	⬇️
shard-3	40.36% <48.97%> (-13.49%)	⬇️

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	13.20% <100.00%> (+13.20%)	⬆️
src/api/routes.ts	95.16% <100.00%> (+0.04%)	⬆️
src/openapi/spec.ts	99.48% <100.00%> (+<0.01%)	⬆️

... and 639 files with indirect coverage changes

[loopover-orb]

Caution

🛑 LoopOver review result - fixes required

_{Review updated: 2026-07-21 15:24:08 UTC}

10 files · 1 AI reviewer · no blockers · CI failing · blocked

🛑 Suggested Action - Fix Blockers

Review summary
This PR adds a REST route, CLI subcommand, and stdio tool for `loopover_plan_repo_issues`, mirroring the existing `contributor-issue-drafts` pattern closely (same auth gate ordering, same create-safety guard shape, same file-layout conventions). The `isProcessEntrypoint()` guard is a reasonable, minimally invasive way to make the CLI dispatcher unit-testable without subprocess spawn, and it correctly gates both the CLI dispatch and the stdio `server.connect()` so an in-process import can't hijack test argv or bind stdin. The route wiring (`requireAppRole` → `requireSessionRepoAccess` → create-safety check → `requireRepoWriteAccess`) matches the sibling route exactly, and the CLI's `--create` maps to the literal `{create:true, dryRun:false}` shape the route's guard demands. The tool-count bump (79→80) and OpenAPI/spec additions are consistent and covered by the added tests.

Nits — 6 non-blocking

• The 'generic_secret_assignment' flag on test/unit/mcp-cli-plan-issues.test.ts:31 is almost certainly a false positive — it's `process.env.LOOPOVER_API_TOKEN = "in-process-token"`, a hardcoded test fixture token, not a real credential; still worth a quick look to confirm nothing sensitive slipped in.
• packages/loopover-mcp/bin/loopover-mcp.ts: the new `planRepoIssuesShape`/CLI `--limit` cap of 10 (vs. the sibling `generate-issue-drafts`' 20) is explained in the comment (LLM cost) but consider extracting a shared named constant instead of repeating the literal `10`/`2000` across routes.ts and the bin file.
• test/unit/routes-issue-plan-draft.test.ts and mcp-cli-plan-issues.test.ts are thorough but somewhat verbose given how closely they mirror the sibling contributor-issue-draft tests — acceptable given the coverage bar, but worth noting for future reviewers scanning for genuine novel logic.
• The `any` annotations at loopover-mcp.ts:2651/3282/3527 are consistent with existing patterns in this file (loosely-typed CLI options plumbing) but still a nit worth tightening opportunistically.
• Consider factoring the repeated `goal`/`limit` schema shape (z.string().min(1).max(2000), limit min(1).max(10).optional().default(5)) shared between src/api/routes.ts's issuePlanDraftGenerateSchema and the bin's planRepoIssuesShape into one exported source of truth to prevent future drift between the two independently-hand-synced schemas.
• Possible secret-shaped assignment in the diff (generic_secret_assignment) — Verify the value is not a real credential.

CI checks failing

• validate
• validate-tests-merge

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	#7764
Related work	✅ No active overlap found	No same-issue or scoped active PR overlap found.
Change scope	✅ 20/20	Low 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: 80 registered-repo PR(s), 46 merged, 0 issue(s).
Contributor context	✅ Confirmed Gittensor contributor	xfodev; Gittensor profile; 80 PR(s), 0 issue(s).
Improvement	✅ Minor	risk: clean · value: minor · LLM: moderate

Linked issue satisfaction

Addressed
The diff adds all three required mirror surfaces: a REST route `/v1/repos/:owner/:repo/issue-plan-drafts/generate` in routes.ts gated by requireAppRole/requireSessionRepoAccess/requireRepoWriteAccess mirroring the contributor-issue-drafts route, a `maintain plan-issues` CLI command, and a `loopover_plan_repo_issues` registerStdioTool block proxying the new route, plus corresponding regression test

Review context

• Author: xfodev
• 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: 80 PR(s), 0 issue(s).
• PR-specific overlap: none found.

Contributor next steps

• Keep the PR focused and include validation evidence before maintainer review.

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.

Visual preview

Route	Viewport	Before (production)	After (this PR's preview)	Diff
/	desktop	before /	after /	diff /
/	mobile	before / (mobile)	after / (mobile)	—

Click any thumbnail to open the full-size screenshot. Before = production · After = this PR's preview deploy · Diff highlights exactly what changed.

Scroll preview

Route	Before (production)	After (this PR's preview)
/	before / (scroll)	after / (scroll)

A short scroll-through clip (desktop) — click either thumbnail to open the full animation. Evidence for scroll-linked behavior a single screenshot can't show.

_{🟩 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]

This pull request changes UI/visual code but its screenshot evidence is incomplete. Every required viewport × theme combination needs its own before/after image pair in a labeled table row (e.g. "Desktop · Light | before | after"). Still missing: Desktop · Dark, Tablet · Dark, Mobile · Dark.

Please resubmit with the remaining rows filled in.

See https://github.com/JSONbored/loopover/blob/main/.claude/skills/contributing-to-loopover/SKILL.md for the exact format and examples. This is an automated maintenance action.