misc

Request a human judgment (L3 layer) by attaching evidence — approval, evidence, or verdict. This is the ONLY door an agent has into the judgment queue.

Request a human judgment (L3 layer) by attaching evidence — approval, evidence, or verdict. This is the ONLY door an agent has into the judgment queue.

🔴 decision is REJECTED with an error if passed — judgments are always created with decision='pending'. Only a human decides them (from the /command queue). Use judgment_list afterwards to check whether this judgment has since been decided.

risk_tier controls urgency: 1=destructive (blocks execution until decided), 2=reversible (may auto-proceed after a wait window), 3=informational (auto-expires after 24h).

post/api/mcp/tools/judgment_submit

Request

  • Base URL: https://api.ainote.dev
  • URL: https://api.ainote.dev/api/mcp/tools/judgment_submit
  • Auth: API key in header Authorization

Request body

kind'approval' | 'evidence' | 'verdict' required

approval | evidence | verdict.

risk_tier1 | 2 | 3

1=destructive 2=reversible 3=informational. Default: 2.

summarystring required

One sentence: what is being judged (required).

evidenceobject

Free-form evidence attached to the request — links, numbers, diff summaries.

project_idstring

Optional project this judgment relates to.

subject_type'Assumption' | 'Task'

Optional. Pair with subject_id. Only Assumption or Task are allowed.

subject_idstring

Optional. UUID of the Assumption or Task this judgment is about.

Response

Tool executed successfully

Changes

No recorded changes to this operation across all 1 revision of this API.