record_handoff_correction
[MAINTENANCE] 3af86d28 — record a corrective handoff when a blocked executor session reaches a wall after receiving a handoff (its evidence/scope no longer holds, a pointer stopped resolving, a required capability went away, etc.). Links to the immutable source_handoff_id (never mutated), classif...
This record as markdown: /tools/io-github-ajc3xc-meridian/record-handoff-correction.md
What record_handoff_correction does on Meridian
AI agents call record_handoff_correction to permanently remove resources in Meridian, typically in cleanup and lifecycle workflows. It does its job in a single call, and there is no undo.
| Parameter | Type | Required | Description |
|---|---|---|---|
mode | string | — | Only used when regenerate=true — forwarded to generate_handoff. |
status | string | — | Initial status. Default draft. |
version | string | — | Sprint-version bucket in scope, if any — also used to scope the regenerated revision when regenerate=true. |
output_dir | string | — | Only used when regenerate=true; defaults to the server's data directory. |
project_id | string | — | |
regenerate | boolean | — | When true, also repairs pointers, invalidates the source handoff, and produces a new deterministic revision in this SAME call. Default false (record only). |
session_id | string | — | The blocked executor session recording this correction. |
project_name | string | — | Project name — an alternative to project_id; resolved to the id internally. project_id wins if both are given. |
source_token | string | — | Optional: the <goal_token> value from the original /goal block, preserved for audit only (not re-verified by this call). |
added_pointers | array | — | Pointer dicts (same shape as add_sprint_item_pointer's source_type/targets/label) asserting new evidence. Re-resolved live when regenerate=true. |
idempotency_key | string | — | Optional caller-supplied dedup key so a retried call returns the existing correction instead of duplicating it. |
requested_scope | object | — | Free-form JSON describing the scope the ORIGINAL handoff asked for, for comparison against what actually got emitted. |
Parameters from the server's own tool schema.
Why record_handoff_correction is rated Critical
An AI agent that decides to call record_handoff_correction doesn't hesitate, doesn't double-check, and doesn't stop at one. Whatever it removes from Meridian is gone. There is no undo for destructive operations.
Risk signalsHigh parameter count (18 properties) · Bulk/mass operation — affects multiple targets
Attacks that exploit this kind of access
The rule that runs record_handoff_correction 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 record_handoff_correction, this is the rule to start with:
record_handoff_correction is removed from the agent's tool list entirely, so the agent never calls it. The rest of the server keeps working.
The button opens the PolicyLayer dashboard: create your workspace, connect Meridian, apply this rule, and every record_handoff_correction call is checked against it from then on.
Questions about record_handoff_correction
[MAINTENANCE] 3af86d28 — record a corrective handoff when a blocked executor session reaches a wall after receiving a handoff (its evidence/scope no longer holds, a pointer stopped resolving, a required capability went away, etc.). Links to the immutable source_handoff_id (never mutated), classifies the blocker, and carries structured investigation evidence, added/removed/superseded pointers, and changed resources. Records status='draft' by default (or pass status explicitly). Pass idempotency_key to make retries safe — a repeat call with the same key returns the existing correction unchanged rather than duplicating it. Pass regenerate=true to ALSO, in this same call: re-resolve every added pointer live (repair), mark the source handoff invalidated/non-executable (its body is left untouched, for audit), and produce a new deterministic handoff revision (new body hash + provenance token) via the normal generate_handoff renderer. Idempotent: a correction that already produced a revision returns that same result again instead of regenerating a second time. A receiving executor should load the result via load_handoff (its 'correction' field) or a direct get_sprint — not by reconstructing the correction from log_task/note text. No DOCX or canonical project mutation is implied by recording a correction. 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 Destructive tool in the Meridian MCP Server, which means it can permanently delete or destroy data. Block by default and require explicit approval.
record_handoff_correction accepts 12 parameters: mode, status, version, output_dir, project_id, regenerate, session_id, project_name, source_token, added_pointers, idempotency_key, requested_scope. 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 record_handoff_correction: 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.
record_handoff_correction 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 record_handoff_correction 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 record_handoff_correction. 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.
record_handoff_correction 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.
Across the catalogue