finalize_wave_run
[SUPPORT] 2a654cb0 — IDEMPOTENT FINALIZATION: close a wave run opened by start_wave_run. Safe to retry: if the run is already merged this returns the ORIGINAL result with already_finalized=true, writes no row and appends no event (event_count is identical across the retry — that is the observable...
This record as markdown: /tools/io-github-ajc3xc-meridian/finalize-wave-run.md
What finalize_wave_run does on Meridian
AI agents use finalize_wave_run to create or update resources in Meridian, usually the action step of a workflow, after the agent has gathered context. Every call changes real data in your Meridian environment.
| Parameter | Type | Required | Description |
|---|---|---|---|
actor | string | — | Optional session_id or actor name recorded as finalizing the run. |
evidence | object | — | The FULL dict returned by run_verification. Must have status='ok' and exit_code=0. Not required when replaying an already-finalized run. |
wave_run_id | string | Yes | The immutable id returned by start_wave_run. |
expected_revision_hash | string | — | Optional staleness gate: the board revision_hash you believe this run was planned against. A mismatch refuses the finalization instead of merging against unseen |
Parameters from the server's own tool schema.
Why finalize_wave_run is rated Medium
The tool closes/merges a wave run, which is a state-changing write operation against a coordination board. It is idempotent and has guards (revision hash check, failure mode checks), but it does commit a finalization record and appends events. It does not delete data irreversibly, execute code, or move money, placing it in Write.
From the tool's definition IDEMPOTENT FINALIZATION: close a wave run opened by start_wave_run. Safe to retry: if the run is already merged this returns the ORIGINAL result with already_finalized=true, writes no row and appends no event
Attacks that exploit this kind of access
The rule that runs finalize_wave_run safely
PolicyLayer is an MCP gateway: it sits between your AI agents and Meridian, and checks every tool call against a rule you set before the call runs. Nothing changes on the server itself. For finalize_wave_run, this is the rule to start with:
finalize_wave_run stays usable, but capped: an agent stuck in a loop can't make hundreds of changes a minute. Everything else on the server is denied unless you say otherwise.
The button opens the PolicyLayer dashboard: create your workspace, connect Meridian, apply this rule, and every finalize_wave_run call is checked against it from then on.
Questions about finalize_wave_run
[SUPPORT] 2a654cb0 — IDEMPOTENT FINALIZATION: close a wave run opened by start_wave_run. Safe to retry: if the run is already merged this returns the ORIGINAL result with already_finalized=true, writes no row and appends no event (event_count is identical across the retry — that is the observable proof). Fails CLOSED in three cases: (1) a failure_mode='stop' child has failed — returns {finalized: false, blocked_by: [...]} naming the items; (2) expected_revision_hash does not match the board the run was planned against — you are holding a stale manifest, re-read the board first; (3) evidence is not a genuine run_verification result (status='ok', exit_code=0) — the SAME evidence contract complete_wave_gate enforces; a self-report is rejected. Returns {finalized, already_finalized, wave_run_id, status, finalized_at, finalizer_evidence, children_summary, event_count}. Persistent-state disclosure: on hosted Meridian, supplied text and project/session metadata are sent to and stored in Meridian's service; self-hosted deployments keep them in the configured local SQLite/Postgres database. This data is visible in the dashboard/API and later project context or handoffs. Delete individual tasks, notes, or decisions where supported, or delete the project/account using the documented controls. Do not include secrets. It is categorised as a Write tool in the Meridian MCP Server, which means it can create or modify data. Consider rate limits to prevent runaway writes.
finalize_wave_run accepts 4 parameters: actor, evidence, wave_run_id, expected_revision_hash. Required: wave_run_id. 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 finalize_wave_run: 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.
finalize_wave_run is a Write tool with medium risk. Write tools should be rate-limited to prevent accidental bulk modifications.
Yes. Add a rate_limit block to the finalize_wave_run 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 finalize_wave_run. 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.
finalize_wave_run 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.
More on Meridian, and thousands of servers like it.
This server
Across the catalogue