reconcile_stale_claims

[MAINTENANCE] 56e9b3c7 — project/version-scoped, auditable stale-claim reconciliation sweep. The bulk counterpart to claim_sprint_item's own inline autonomous reconciliation (which only ever fires reactively, on a claim attempt against one already-claimed item) — use this for a scheduler path, or an explicit human/planner/executor-triggered audit across a whole board. Scans in_progress items in project_id (optionally narrowed to one version and/or an explicit item_ids allow-list — never cross-project), classifies each claim as active/stale/ambiguous via the same multi-signal check claim_sprint_item uses (session heartbeat liveness, claimed_at age vs. a 2h threshold, worktree/pid evidence — never age alone), and — ONLY when dry_run=False — resets every 'stale' verdict: atomically returns the item to pending, clears claimed_at/actor, releases the file/symbol resource locks the abandoned claim held, and writes an audit record. 'active' and 'ambiguous' verdicts are NEVER touched, dry-run or not — this never force-releases a genuinely live owner or treats an inconclusive signal as proof of abandonment. dry_run=True (the default) performs the full scan/classification and reports exactly what WOULD happen without writing anything — safe to run against any project, including live production boards, at any time. max_batch bounds how many in_progress candidates are scanned in one call (capped server-side); truncated=true on the result means more candidates exist than were scanned — page through with a follow-up call. Returns {project_id, version, dry_run, max_batch, candidates_total, scanned, truncated, active: [...], ambiguous: [...], stale: [...], reset: [...], errors: [...]} — active/ambiguous/stale hold classification verdicts, reset holds what was actually written back (only populated when dry_run=False), errors holds {item_id, error} for any one candidate whose classification or reset failed (never aborts the rest of the sweep). Persistent-state disclosure: on hosted Meridian, supplied text and project/session metadata -- including task log entries, pinned decisions, sprint items, notes, handoff/goal state, and HITL queue items -- are sent to and stored in Meridian's service, in an isolated per-tenant Postgres database (Neon); self-hosted deployments keep the same categories in the configured local SQLite/Postgres database. This data is visible in the dashboard and API, and may resurface in later project context or handoffs. Notes and pinned decisions can be deleted individually; task log entries and sprint items can be deleted via the dashboard/API (not exposed as an agent-facing tool); HITL queue items and handoff state have no per-record delete. Full removal of any of this data is available via project or account deletion, using the documented controls. Do not include secrets. It is categorised as a Destructive tool in the Meridian MCP Server, which means it can permanently delete or destroy data. Block by default and require explicit approval.

reconcile_stale_claims accepts 8 parameters: actor, dry_run, version, item_ids, max_batch, repo_root, project_id, project_name. The full parameter table on this page comes from the server's own tool schema.

Register the Meridian MCP server in PolicyLayer and add a rule for reconcile_stale_claims: allow, deny, rate-limit, or require approval. Point your MCP client at the PolicyLayer proxy URL and the rule is enforced on every call, before it reaches Meridian. Nothing to install.

reconcile_stale_claims is a Destructive tool with critical risk. Critical-risk tools should be blocked by default and only enabled with explicit human approval.

Yes. Add a rate_limit block to the reconcile_stale_claims rule in your PolicyLayer policy. For example, setting max: 10 and window: 60 limits the tool to 10 calls per minute. Rate limits are tracked per agent session and reset automatically.

Set action: deny in the PolicyLayer policy for reconcile_stale_claims. The AI agent will receive a policy violation error and cannot call the tool. You can also include a reason field to explain why the tool is blocked.

reconcile_stale_claims is provided by the Meridian MCP server (@meridianmcp/mcp). PolicyLayer sits as a proxy in front of this server to enforce policies before tool calls reach the server.