034f774529
test / integration (pull_request) Successful in 10s
tracker-policy-pr / check-pr (pull_request) Successful in 11s
test / coverage (pull_request) Successful in 39s
test / unit (pull_request) Successful in 1m30s
prd-number / assign-numbers (push) Failing after 10s
test / integration (push) Successful in 7s
test / unit (push) Successful in 30s
lint / lint (push) Successful in 42s
test / coverage (push) Successful in 35s
Update Quality Badges / update-badges (push) Successful in 34s
Closes #412. The supervise MCP server blocked the agent's tool call polling for the operator's decision, and on timeout returned `status: pending` with no proposal id and no way to poll a specific proposal — so the only way to learn a late decision was to re-propose (a duplicate). - `handle_tools_call` pending timeout now returns the `proposal_id` and points the agent at `check-proposal`. - New `check-proposal` MCP tool: non-blocking status lookup by proposal id (pending | approved | modified | rejected | unknown). Reuses the queue's FileNotFoundError semantics; archives a decided proposal exactly like the synchronous path, so a pending proposal stays visible to the operator until it's both decided and polled. - `TOOL_CHECK_PROPOSAL` constant, re-exported from supervise; kept out of TOOLS since it never becomes a Proposal.tool. Enforcement is unchanged — the tools only propose policy; the egress proxy and git-gate still enforce — so returning early opens no hole. Follow-ups (git-gate reject-requeue, backpressure, notifications, web console) are in the PRD. Co-Authored-By: Claude Opus 4.8 <noreply@anthropic.com> Claude-Session: https://claude.ai/code/session_01YBCHap11yGAKuKfsehNPaD