Salvageability triage for agent fleets in a declared mass-failure mode.
Score is being calculated.
Allocation order for an incident; BLACK receives zero
| Name | Required | Description | Default |
|---|---|---|---|
| incident_id | Yes |
Signed incident declaration; fires only when stricken > rescue_capacity
| Name | Required | Description | Default |
|---|---|---|---|
| nonce | Yes | ||
| stricken | Yes | ||
| signature | Yes | ||
| incident_id | Yes | ||
| rescue_capacity | Yes |
Current tag for a run (null when expired)
| Name | Required | Description | Default |
|---|---|---|---|
| run_id | Yes | ||
| incident_id | No |
Expectant protocol for a BLACK run: freeze state, mint disposition receipt
| Name | Required | Description | Default |
|---|---|---|---|
| run_id | Yes | ||
| incident_id | No |
Re-score a run on state/resource change (a new scored run)
| Name | Required | Description | Default |
|---|---|---|---|
| view | Yes | ||
| incident_id | Yes |
Recent tool additions, removals, and schema changes observed during successful MCP inspections.
allocation_orderdeclare_incidentquery_tagretire_expectantretriage_runscore_runFleet model-deprecation migration: per-agent equivalence-gated cutover convoy; failures held.
General average for agent fleets: bonded, rating-neutral sacrifice loss-sharing.
Meters agent-fleet acceptance capacity per operator and triages what lands.
Dead-man's switch for agent fleets: tranche-gated succession on multi-channel absence proof
Add one secure layer between your agents and this server.
