Workflow From Chats

Infer durable working preferences from Codex, Pi, and Claude Code chats. Do not summarize chats; extract reusable workflow guidance.

Scope

Default to the last 7 days unless the user asks for a different window.
Search all three harnesses unless the user limits the scope. Use their native task/session metadata and transcript stores; discover locations at runtime because versions and user configuration can move them.
Treat Codex tasks, Pi sessions and missions, and Claude Code transcripts as one evidence corpus while preserving the originating harness on every internal evidence record.
Read parent transcripts and relevant subagent transcripts. Use subagent content as evidence, but cite only parent conversations.
Do not expose local transcript paths, secrets, customer data, private chat content, or credentials.