Lakebase-backed persistent memory for CODA sessions

[dgokeeffe]

Summary

Adds Lakebase-backed persistent memory to CODA. Migrating from datasciencemonkey PR #145.

At session end, a Stop hook extracts 3–8 structured memories from the Claude transcript via the Databricks Claude Haiku serving endpoint, persists them to a coda_memories Postgres table, and regenerates coda_memory.md so the next session opens with the accumulated context already loaded.

Components

• memory/extractor.py — Stop hook: parses the JSONL transcript, calls Haiku, writes to Lakebase, regenerates the local memory file.
• memory/store.py — psycopg 3 + psycopg_pool with an OAuthConnection subclass that mints a fresh Lakebase OAuth credential on every pool recycle (45 min, ahead of the 1h token expiry). Follows the canonical Databricks Apps + Lakebase Autoscaling pattern.
• memory/injector.py — Regenerates ~/.claude/memory/coda_memory.md (or project-scoped variant) from Lakebase.
• memory/searcher.py — FTS-ranked search CLI used by the memory-recall subagent.
• memory/hooks/user_prompt_submit.py — Zero-cost nudge so Claude knows to invoke the subagent when historical context would help.
• setup_memory.py — Per-session schema init, memory-file warm-up, idempotent hook registration.

Schema

coda_memories: content_hash UNIQUE for dedup, content_tsv generated column + GIN index for FTS, nullable vector(1536) + HNSW (kept off by default — semantic search comes later).

Branch

feat/lakebase-memory — about to be pushed.

Diff scope

+6581 / -10, 36 files. Tests in tests/test_memory_*.py.

Follow-ups

• Embedding ingestion + MMR retrieval (vector column is in place, query side isn't yet).
• Memory decay / TTL.
• Multi-tenant scoping (currently single-user).