matrix-agent-validated/ops/systemd/lakehouse.service
profit ac01fffd9a checkpoint: matrix-agent-validated (2026-04-25)
Architectural snapshot of the lakehouse codebase at the point where the
full matrix-driven agent loop with Mem0 versioning + deletion was
validated end-to-end.

WHAT THIS REPO IS
A clean single-commit snapshot of the lakehouse code. Heavy test data
(.parquet datasets, vector indexes) excluded — see REPLICATION.md for
regen path. Full lakehouse history at git.agentview.dev/profit/lakehouse.

WHAT WAS PROVEN
- Vector retrieval across multi-corpora matrix (chicago_permits + entity
  briefs + sec_tickers + distilled procedural + llm_team runs)
- Observer hand-review (cloud + heuristic fallback) gating each candidate
- Local-model agent loop (qwen3.5:latest) with tool use + scratchpad
- Playbook seal on success → next-iter retrieval surfaces it as preamble
- Mem0 versioning + deletion in pathway_memory:
    * UPSERT: ADD on new workflow, UPDATE bumps replay_count on identical
    * REVISE: chains versions, parent.superseded_at + superseded_by stamped
    * RETIRE: marks specific trace retired with reason, excluded from retrieval
    * HISTORY: walks chain root→tip, cycle-safe

KEY DIRECTORIES
- crates/vectord/src/pathway_memory.rs — Mem0 ops live here
- crates/vectord/src/playbook_memory.rs — original Mem0 reference
- tests/agent_test/ — local-model agent harness + PRD + session archives
- scripts/dump_raw_corpus.sh — MinIO bucket dump (raw test corpus)
- scripts/vectorize_raw_corpus.ts — corpus → vector indexes
- scripts/analyze_chicago_contracts.ts — real inference pipeline
- scripts/seal_agent_playbook.ts — Mem0 upsert from agent traces

Replication: see REPLICATION.md for Debian 13 clean install + cloud-only
adaptation (no local Ollama).

Co-Authored-By: Claude Opus 4.7 (1M context) <noreply@anthropic.com>
2026-04-25 19:43:27 -05:00

27 lines
944 B
Desktop File

[Unit]
Description=Lakehouse Gateway
After=network.target ollama.service
[Service]
Type=simple
WorkingDirectory=/home/profit/lakehouse
ExecStart=/home/profit/lakehouse/target/release/gateway
Restart=always
RestartSec=5
Environment=RUST_LOG=info
# Lance S3 support — connects to MinIO via the AWS SDK env vars.
# AWS_ALLOW_HTTP required for non-TLS MinIO endpoints.
Environment=AWS_ACCESS_KEY_ID=profit
Environment=AWS_SECRET_ACCESS_KEY=29IgevhKQjE2WHg088ieI1wP
Environment=AWS_ENDPOINT=http://localhost:9000
Environment=AWS_ALLOW_HTTP=true
Environment=AWS_DEFAULT_REGION=us-east-1
# Langfuse keys — shared with lakehouse-langfuse-bridge.service so the
# gateway-side emitter (`/v1/chat`, `/v1/respond`) and the observer
# ingest path see the same project. Leading `-` makes missing-file a
# warn-not-fatal so gateway still starts if Langfuse is torn down.
EnvironmentFile=-/etc/lakehouse/langfuse.env
[Install]
WantedBy=multi-user.target