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

[xfodev]

Summary

loopover_plan_repo_issues (generateIssuePlanDrafts, src/services/issue-plan-draft.ts) shipped only as a remote MCP tool and never got the REST + CLI + local-stdio mirror surfaces its repo-scoped, requireRepoManageAccess-gated siblings all have. Mirrors loopover_generate_contributor_issue_drafts exactly:

• REST route — POST /v1/repos/:owner/:repo/issue-plan-drafts/generate in src/api/routes.ts, calling generateIssuePlanDrafts (required goal from the body), gated identically to the contributor sibling, plus the canSessionAccessPath matcher and the OpenAPI registerPath.
• CLI command — loopover-mcp maintain plan-issues (dry-run by default; --create opts in).
• Local stdio MCP tool — loopover_plan_repo_issues, calling the new CLI logic.

generateIssuePlanDrafts, the remote tool, and src/services/** are unchanged. Rebased onto latest main (incl. #7705 — mcp/miner no longer commit the compiled .js; this PR touches only the tracked .ts).

Tests

• test/unit/routes-issue-plan-draft.test.ts: success, both auth-gate branches incl. write-granted create fall-through, invalid-JSON, invalid-body, explicit-create guard, cross-repo/forbidden — the new routes.ts lines are 100% statement + branch covered.
• test/unit/mcp-cli-plan-issues.test.ts: in-process coverage of the CLI command + stdio tool via the .ts source.

UI Evidence

The only apps/loopover-ui/** change is the regenerated public/openapi.json (required by ui:openapi:check for the new backend route). Its sole rendered effect is that the new POST …/issue-plan-drafts/generate operation now appears in the API reference (/api) endpoint list + sidebar. loopover-ui is a dark-only build.

Viewport × Theme	Before (no route)	After (route listed)
Desktop · Dark
Tablet · Dark
Mobile · Dark

Validation

• Root tsc --noEmit clean (my files); new route/CLI/stdio + mcp-cli-completion-spec (CLI_COMMAND_SPEC parity) tests pass; ui:openapi:check, command-reference:check, docs:drift-check green; OpenAPI regenerated; rebased on latest main.
• Auth/CORS negative-path tests included (forbidden / cross-repo / unauthorized). No wallet/hotkey/trust-score/reward terms in route output or CLI text.

Closes #7764

[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 83.24%. Comparing base (e7e10e7) to head (6bc8c7f).
⚠️ Report is 1 commits behind head on main.

Additional details and impacted files

@@            Coverage Diff             @@
##             main    #7890      +/-   ##
==========================================
- Coverage   91.39%   83.24%   -8.16%     
==========================================
  Files         730       91     -639     
  Lines       74774    26032   -48742     
  Branches    22818     5326   -17492     
==========================================
- Hits        68343    21671   -46672     
+ Misses       5389     4054    -1335     
+ Partials     1042      307     -735     

Flag	Coverage Δ
shard-1	18.49% <6.12%> (-40.08%)	⬇️
shard-2	33.04% <57.14%> (-18.80%)	⬇️
shard-3	40.32% <48.97%> (-9.89%)	⬇️

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	13.26% <100.00%> (+13.26%)	⬆️
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]

Tip

✅ LoopOver review result - approve/merge recommended

_{Review updated: 2026-07-21 16:45:38 UTC}

10 files · 1 AI reviewer · no blockers · readiness 100/100 · CI green · clean

✅ Suggested Action - Approve/Merge

• safe to merge

Review summary
This PR mirrors the existing generate-issue-drafts pattern (REST route, CLI subcommand, stdio tool) to add loopover_plan_repo_issues surfaces, reusing the identical requireAppRole/requireSessionRepoAccess/requireRepoWriteAccess gate and the same explicit_create_requires_dry_run_false safety contract as the contributor-issue-draft sibling. The new isProcessEntrypoint() guard in loopover-mcp.ts is a sound, already-precedented technique (mirrors bin/loopover-miner-mcp.ts) that lets in-process tests exercise the CLI dispatcher and stdio server without hijacking argv or binding stdin — the new tests genuinely drive the real dispatcher/tool code, not fabricated payloads. Wiring is complete end-to-end: schema (src/api/routes.ts), path matcher (isRepoIssuePlanDraftGeneratePath/canSessionAccessPath), OpenAPI (spec.ts + regenerated openapi.json), CLI dispatch table, stdio descriptor list, and the tool-count test (80→81) are all updated together.

Nits — 6 non-blocking

• The screenshot evidence for this PR reportedly shows the before/after API-docs images as visually identical, which doesn't demonstrate the new /issue-plan-drafts/generate route actually rendering in the UI — worth asking the contributor to regenerate the screenshot pair even though the diff itself (openapi.json + spec.ts) correctly adds the route.
• packages/loopover-mcp/bin/loopover-mcp.ts: the stdio tool's planRepoIssuesShape uses z.string().min(1).max(2000) for goal without .trim(), while the REST schema (src/api/routes.ts issuePlanDraftGenerateSchema) and the CLI both trim — a whitespace-only goal from the stdio path would pass client-side validation and only get rejected server-side; consider aligning for a faster client-side error.
• test/unit/mcp-cli-plan-issues.test.ts:31 sets process.env.LOOPOVER_API_TOKEN to a placeholder test string flagged by secret scanning — verify it's just a dummy in-process value (it is, per the surrounding fixture setup) and not an actual leaked credential.
• The several new magic numbers (2000 char goal cap, limit min/max of 1/10, HTTP status literals) mirror the existing sibling schema's style, so no action needed beyond what the codebase already does elsewhere.
• Trim the stdio tool's `goal` field client-side (packages/loopover-mcp/bin/loopover-mcp.ts's planRepoIssuesShape) to match the CLI/REST behavior and fail fast on whitespace-only input.
• 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	#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

Linked issue satisfaction

Addressed
The diff adds a REST route (POST /v1/repos/:owner/:repo/issue-plan-drafts/generate) gated with requireAppRole/requireSessionRepoAccess mirroring the contributor-issue-drafts route, a CLI command (maintain plan-issues) that calls this route, and a registerStdioTool block for loopover_plan_repo_issues that proxies the CLI logic, matching the three-surface pattern requested.

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: JavaScript, TypeScript
• 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]

LoopOver approves — the gate is satisfied and CI is green.