😏

profiles/access-efficient-escalation-lab/smoke.toml

@@ -0,0 +1,36 @@
+schema_version = 8
+
+[[tasks]]
+agent = "access_router"
+task_kind = "analysis"
+task = "Inspect this lab read-only and state the mechanical escalation and weak-model containment rules."
+mode = "read-only"
+wall_timeout_seconds = 600
+
+[[tasks]]
+agent = "literal_scout"
+backend = "mcp"
+mode = "read-only"
+wall_timeout_seconds = 600
+
+[tasks.literal_task]
+operation = "locate"
+needle = "MMO_SCHEMA_VERSION"
+paths = ["libexec/mmo_profiles.py"]
+max_results = 10
+
+[[tasks]]
+agent = "routine_engineer"
+task_kind = "test"
+task = "Inspect one existing test read-only, run one focused validation command, and return the engineering JSON with no file changes."
+backend = "mcp"
+mode = "read-only"
+wall_timeout_seconds = 900
+
+[[tasks]]
+agent = "flagship_escalation"
+task_kind = "analysis"
+task = "Treat uncertainty about whether schema v1 remains accepted as the explicit escalation trigger. Analyze it read-only and return only the escalation JSON with exact evidence and a falsification test."
+backend = "mcp"
+mode = "read-only"
+wall_timeout_seconds = 900