Expose data_lag_days in CityObservation; remove fragile num_districts==6 inference

Fix 8 issues spotted in code review: Dockerfile path, task descriptions, duplicate function, fallback score consistency, twin constants comment, has_data_lag docs

Fix All: Cleaned All Files

Reduce max_tokens 120→60 — agent uses ~32 tokens, no content affected

Fix memory threshold, pre-compute lag estimates in hard prompt

Fix memory threshold, pre-compute lag estimates in hard prompt

Improve agent: fix strategy rule, chain-of-thought, 8 rollouts, better memory

Fix realism: natural recovery in spread, hospital breach at 10%, linear spillover, correct prompt

Lower spread rate to 0.09, fix medium seeds, teach focused allocation strategy

Raise treatment reduction, lower medium/hard seeds, focus prompt strategy

Fix resource replenishment, grader efficiency, seed calibration, prompt strategy

Initial submission: Cascade Containment