feat(mcp): add loopover_set_agent_paused and loopover_set_action_autonomy tools

[nghetienhiep]

Summary

• maintain pause/resume/set-level (the write-side kill-switch + per-action autonomy dial) had no MCP tool, even though maintain status/queue/approve/reject are already mirrored as loopover_get_automation_state/loopover_list_pending_actions/loopover_decide_pending_action. Added loopover_set_agent_paused and loopover_set_action_autonomy to close that gap.
• Both tools require the same maintainer-manage authorization as loopover_propose_action (requireRepoManageAccess) and read-merge-write over the repo settings row so unrelated fields (and, for autonomy, other action classes) are preserved — matching the CLI's own pattern.
• loopover_set_action_autonomy's action enum mirrors the CLI's MAINTAIN_ACTION_CLASSES exactly. Its level enum intentionally validates against the live AUTONOMY_LEVELS (src/settings/autonomy.ts) rather than the CLI's own MAINTAIN_AUTONOMY_LEVELS, which still lists suggest/propose — both removed server-side by Resolve dead config branches (wire or remove) #4620 and silently dropped by normalizeAutonomyPolicy on persist. Accepting them here would report a successful write that never actually took effect.

Closes #6087

Scope

• The PR title follows type(scope): short summary Conventional Commit format, for example fix(api): restore profile access checks.
• This PR is focused and does not mix unrelated backend, UI, MCP, docs, dependency, and deploy changes.
• This follows CONTRIBUTING.md and does not reintroduce GitHub Pages, VitePress, site/, or CNAME.
• I linked a currently open issue this PR resolves (e.g. Closes #123) — a linked open issue is required for every contributor PR.

Validation

• git diff --check
• npm run actionlint
• npm run typecheck
• npm run test:coverage locally; codecov/patch requires ≥99% coverage of the lines AND branches you changed (aim for 100% on your diff so CI variance does not fail near the threshold). Global coverage is a non-blocking trend with a loose 90% backstop, not the gate.
• npm run test:workers
• npm run build:mcp
• npm run test:mcp-pack
• npm run ui:openapi:check
• npm run ui:lint
• npm run ui:typecheck
• npm run ui:build
• npm audit --audit-level=moderate
• New or changed behavior has unit/integration tests for new branches, fallback paths, and sanitizer boundaries

If any required check was skipped, explain why:

• ui:lint/ui:typecheck/ui:build skipped: this PR only touches src/mcp/server.ts + its unit test, no apps/loopover-ui/** files.
• npm run test:coverage (full unsharded run) fails 3 pre-existing test files in this sandbox (selfhost-ams-reporting.test.ts needs a sqlite3 binary not installed here; miner-live-issue-snapshot.test.ts picks up a stray local GITHUB_TOKEN-shaped env var) — reproduced identically on a clean main stash, so unrelated to this diff. test/unit/mcp-automation-state.test.ts (this PR's tests) passes fully; verified via coverage/lcov.info that every changed line and branch in src/mcp/server.ts is hit (100% line + branch on the diff).

Safety

• No secrets, wallet details, hotkeys, coldkeys, user PATs, private keys, raw trust scores, private rankings, or private maintainer evidence are exposed.
• Public GitHub text stays sanitized, low-noise, and does not imply compensation guarantees or optimization tactics.
• Auth, cookie, CORS, GitHub App, Cloudflare, or session changes include negative-path tests.
• API/OpenAPI/MCP behavior is updated and tested where needed.
• UI changes use live API data or real empty/error/loading states, not production mock/demo fallbacks.
• Visible UI changes include a UI Evidence section below with JPG/JPEG or PNG screenshots arranged as organized, captioned, clickable thumbnails. SVG screenshots are not used as review evidence. Review-only screenshots or recordings are not committed to the repository.
• Public docs/changelogs are updated where needed; changelogs are only edited for release-prep PRs.

Not applicable: this is a backend-only MCP tool addition with no UI/docs/changelog surface.

UI Evidence

Not applicable — no UI/frontend change.

Notes

• New tests added to test/unit/mcp-automation-state.test.ts (alongside the existing loopover_get_automation_state/loopover_propose_action coverage in the same file): successful pause/resume with unrelated-settings preservation, successful set-level confirming other action classes are untouched, schema rejection of an out-of-surface action class and of the CLI's stale suggest level, and an unauthorized-caller (write-access + MCP actuation allowlist) rejection test mirroring the sibling write tools.

[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 95.24%. Comparing base (0760e1f) to head (a430d67).
⚠️ Report is 9 commits behind head on main.

Additional details and impacted files

@@           Coverage Diff           @@
##             main    #6102   +/-   ##
=======================================
  Coverage   95.24%   95.24%           
=======================================
  Files         595      595           
  Lines       47035    47067   +32     
  Branches    15015    15016    +1     
=======================================
+ Hits        44797    44829   +32     
  Misses       1493     1493           
  Partials      745      745           

Flag	Coverage Δ
shard-1	43.95% <33.33%> (-0.06%)	⬇️
shard-2	36.62% <33.33%> (+<0.01%)	⬆️
shard-3	31.98% <33.33%> (-0.08%)	⬇️
shard-4	31.99% <33.33%> (-1.15%)	⬇️
shard-5	32.66% <33.33%> (+0.44%)	⬆️
shard-6	44.86% <100.00%> (+0.37%)	⬆️

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

Files with missing lines	Coverage Δ
src/mcp/server.ts	96.21% <100.00%> (+0.08%)	⬆️

[loopover-orb]

Tip

🟩🟩🟩🟩🟩🟩🟩🟩🟩🟩🟩🟩

✅ LoopOver review result - approve/merge recommended

_{Review updated: 2026-07-15 09:33:14 UTC}

2 files · 1 AI reviewer · no blockers · readiness 80/100 · CI green · clean

✅ Suggested Action - Approve/Merge

• safe to merge

Review summary
Adds two MCP tools, loopover_set_agent_paused and loopover_set_action_autonomy, mirroring the CLI's maintain pause/resume/set-level as read-merge-write operations over the repo settings row, matching the existing get_automation_state/propose_action patterns and access controls. The autonomy level enum is deliberately validated against the live AUTONOMY_LEVELS rather than the CLI's stale list, correctly closing a real gap where stale levels (suggest/propose) would silently no-op on persist. Tests cover pause/resume, autonomy read-merge-write, access denial, and rejection of out-of-surface action/level values, closing the linked issue #6087.

Nits — 5 non-blocking

• src/mcp/server.ts: setAgentPaused/setActionAutonomy call getRepositorySettings then spread `...current` into upsertRepositorySettings — confirm getRepositorySettings returns a plain object safe to spread (not a class instance or containing extra derived fields) so the read-merge-write doesn't accidentally write back computed values.
• The action enum MAINTAIN_AUTONOMY_ACTION_CLASSES duplicates the CLI's MAINTAIN_ACTION_CLASSES as a hardcoded literal array in server.ts rather than importing it, risking future drift if the CLI's list changes.
• Consider adding a JSDoc-level comment noting why MAINTAIN_AUTONOMY_ACTION_CLASSES isn't imported from the CLI module, since the inline comment covers the AUTONOMY_LEVELS choice but not this one.
• src/mcp/server.ts: import MAINTAIN_ACTION_CLASSES from the CLI module (if exported) instead of re-declaring MAINTAIN_AUTONOMY_ACTION_CLASSES, or add a comment/test asserting the two arrays stay in sync.
• Add a test asserting agentPaused defaults correctly when getRepositorySettings returns no prior row for the repo (new repo, first pause call).

Signal	Result	Evidence
Code review	✅ No blockers	1 reviewer
Linked issue	✅ Linked	#6087
Related work	⚠️ 2 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: 70 registered-repo PR(s), 36 merged, 0 issue(s).
Contributor context	✅ Confirmed Gittensor contributor	nghetienhiep; Gittensor profile; 70 PR(s), 0 issue(s).
Gate result	✅ Passing	No configured blocker found.
Improvement	✅ Minor	risk: clean · value: minor · LLM: moderate

Linked issue satisfaction

Addressed
The diff adds loopover_set_agent_paused and loopover_set_action_autonomy MCP tools that mirror the CLI's pause/resume/set-level operations, gate both behind requireRepoManageAccess matching sibling write tools, use a read-merge-write pattern preserving unrelated settings/action classes, and validate inputs against enums with tests covering success, preserved-other-classes, and unauthorized-caller

Review context

• Author: nghetienhiep
• 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: 70 PR(s), 0 issue(s).
• Related work: Items reference the same linked issue feat(mcp): expose maintain pause/resume/set-level as MCP tools (write-side gap in the automation control surface) #6087. (issue #6087)
• Related work: Open PR work references issue feat(mcp): expose maintain pause/resume/set-level as MCP tools (write-side gap in the automation control surface) #6087. (issue #6087)

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://gittensory.aethereal.dev/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.