databrickslabs / databrickslabs/coding-agents-databricks-apps

Lakebase-backed persistent memory for CODA sessions

Open
#14 0 comments 0 reactions 0 assignees View on GitHub

Nobody has claimed this yet.

Dominant language
Python
Stars
40
Forks
11
Avg merge
1m
Merged PRs (30d)
1

Description

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.pypsycopg 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).

Contributor guide

Open the contributing guide

First steps

  1. Read the whole issue, then the project's contributing guide.
  2. Comment on the issue to say you are picking it up — it saves two people doing the same work.
  3. Fork the repository and make your change on a branch.
  4. Open a pull request that references the issue number.

Research direction

Start with setup_memory.py and the tests in tests/test_memory_*.py, then read memory/extractor.py, memory/store.py, memory/injector.py, and memory/searcher.py to understand the session flow. Done means the Stop hook extracts structured memories, persists them in coda_memories, regenerates coda_memory.md, and the documented tests pass without breaking hook registration.

Written by the indexing model from the issue text.

Assessment

Tech stack
postgres, python
Domain
ai, backend, cloud, databases
Issue type
Feature
Difficulty
5/5
Estimated time
Over a week
Activity status
Quiet
Clarity
Mostly clear
Newbie friendliness
25/100

Get new issues in your inbox

A short digest of beginner-friendly GitHub issues.