incident-postmortem

Close the learning loop after a rescue or incident — reconstruct the timeline from action_log, run root-cause analysis (platform / site / measurement / external), produce a structured postmortem document, distill reusable insights via /learn, and propose preventive guardrails. Use after a /rescue, a CPA spike, a conversion drop, or a runaway-spend event has been handled, or when the user asks for a postmortem,…