Agents

Update agent observer-rollout flags

Partial update — include only the fields to change. MNE-556 P4: the former behavioral toggles (aap_enabled, aip_enabled, proof_enabled, proof_rate, nudge_strategy, ddr_mode, analyze_output) were removed; that config is now authored on the composed alignment card (PUT /agents/{id}/alignment-card). Only the observer-rollout flags are accepted here.

put/agents/{agent_id}/settings

Request

  • Base URL: https://api.mnemom.ai/v1
  • URL: https://api.mnemom.ai/v1/agents/{agent_id}/settings
  • Auth: one of:
    • HTTP bearer
    • API key in header X-Mnemom-Api-Key
    • API key in cookie mnemom_session

Path parameters

agent_idstring required

Agent identifier (e.g. smolt-abc123)

Request body

observer_v2_primary_enabledboolean

Whether the V2 observer retune is authoritative for this agent (default true).

observer_v1_shadow_enabledboolean

Whether the V1 observer runs in parallel shadow for this agent (default false).

Response

Settings updated.

agent_idstring required
observer_v2_primary_enabledboolean required

Whether the V2 observer retune is authoritative for this agent (default true).

observer_v1_shadow_enabledboolean required

Whether the V1 observer runs in parallel shadow for this agent (default false).

updatedboolean

Changes

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