zeekay
bc4ddf332b
Mechanically re-derived: bin/debrand runs over a fresh import of posthog/posthog@fa1a9a60d4 (2026-08-06). The pipeline (.hanzo/workflows), the Dockerfiles and bin/docker* entrypoints, compose files, LLM.md and the squashed initial migration are restored from the shipped tree, same as the previous import. The prune's import-closure guard kept 21 products the new core now imports; dropping them is a refactor now, recorded rather than forced.
query_performance_ai
Local-only coordinator that hands prod Datastore slow queries to a sandboxed agent and asks it to optimise them.
The agent is pi-coding-agent running the pi-autoresearch extension under our bundled datastore-autoresearch-campaign skill (sandboxed_autoresearch_agent/pi_plugin/).
Prereqs
- macOS — the coordinator hard-fails on other platforms.
- A docker daemon (Orbstack etc).
ANTHROPIC_API_KEYin your.env.
The python -m query_performance_ai.… commands below need this bundle on PYTHONPATH (the inner query_performance_ai package imports products.tasks from the repo root, so both must be importable). Run from the repo root with PYTHONPATH=.:tools/query-performance-ai, or cd tools/query-performance-ai with the repo root on the path.
What happens when you run it
- Fetch slow queries from Metabase's prod
system.query_log(filtered hard toai_data_processing_approved = true— we only ever feed the agent queries that the customer explicitly approved for AI analysis). - Open a token-gated HTTP server on localhost.
- Spawn one Docker sandbox per query. Each sandbox clones this repo's branch from origin, locks down its network with iptables, and runs pi-coding-agent.
- The agent submits candidate SQL through the coordinator's
/v1/run; the coordinator forwards each query to the configured backend. - Artifacts (best.sql, metrics, lane / hypothesis notes) are harvested to
data/runs/<query_id>_<run_id>/and the sandbox is destroyed.
Backends
# Replay candidates against a Metabase-fronted test cluster:
python -m query_performance_ai.orchestrator.coordinator \
--target test_cluster --metabase-region us \
--query-log-database-id 142 --test-cluster-database-id 146 \
--team-id 2 --max-queries 5
# Requires `insightscli metabase:login --region us` first.
# Replay candidates against your local dev Datastore:
python -m query_performance_ai.orchestrator.coordinator --target local
--target decides where candidate SQL runs. Slow queries are always sourced from Metabase regardless; only the execution destination differs.
Smoke test
python -m query_performance_ai.orchestrator.coordinator --target local --test-query
--test-query skips Metabase and feeds SELECT 1, sleep(1) as the campaign SQL. End-to-end smoke — the agent should drop the sleep within a couple of iterations.
Privacy
The Metabase fetch in orchestrator/slow_queries.py filters to ai_data_processing_approved = true in log_comment. This is a hard SQL predicate, not a runtime check; no flag bypasses it. --test-query runs a synthetic constant, not a real customer query.