da073ad7cf
Main harvester module that chains: session_reader → extraction prompt → LLM → validate → deduplicate → store Includes: - scripts/harvester.py — main module (reader + prompt + storage pipeline) - scripts/session_reader.py — JSONL transcript parser - scripts/test_harvester_pipeline.py — smoke tests (all passing) Pipeline: 1. Read session JSONL via session_reader 2. Truncate long sessions (first 50 + last 50 messages) 3. Send transcript + extraction prompt to LLM (mimo-v2-pro) 4. Parse structured JSON response (facts/pitfalls/patterns/quirks/questions) 5. Validate fields + confidence threshold 6. Deduplicate against knowledge/index.json (fingerprint + word overlap) 7. Write to knowledge store (index.json + per-repo markdown) CLI: Single: python3 harvester.py --session <path> --output knowledge/ Batch: python3 harvester.py --batch --since 2026-04-01 --limit 100 Dry-run: python3 harvester.py --session <path> --dry-run
Compounding Intelligence
Turn 1B+ daily tokens into durable, compounding fleet intelligence.
The Problem
20,991 sessions on disk. Each one starts at zero. Every agent rediscover the same HTTP 405 is a branch protection issue. The intelligence from a million tokens of work evaporates when the session ends.
The Solution
Three pipelines that form a compounding loop:
SESSION ENDS → HARVESTER → KNOWLEDGE STORE → BOOTSTRAPPER → NEW SESSION STARTS SMARTER
↓
MEASURER → Prove it's working
Architecture
Pipeline 1: Harvester
Reads finished session transcripts. Extracts durable knowledge: facts, pitfalls, patterns, tool quirks. Stores in knowledge/.
Pipeline 2: Bootstrap
Before a session starts, queries knowledge store for relevant facts. Assembles compact 2k-token context. Injects into session so it starts with full situational awareness.
Pipeline 3: Measure
Tracks whether compounding is happening. Knowledge velocity, error reduction, hit rate, task completion. Daily report proves the loop works.
Directory Structure
├── knowledge/
│ ├── index.json # Machine-readable fact index
│ ├── global/ # Cross-repo knowledge
│ ├── repos/{repo}.md # Per-repo knowledge
│ └── agents/{agent}.md # Agent-type notes
├── scripts/
│ ├── harvester.py # Post-session knowledge extractor
│ ├── bootstrapper.py # Pre-session context loader
│ ├── measurer.py # Compounding metrics
│ └── session_reader.py # JSONL parser
├── metrics/
│ └── dashboard.md # Human-readable status
└── templates/
├── bootstrap-context.md
└── harvest-prompt.md
The 100x Path
Month 1: 15,000 facts, sessions 20% faster
Month 2: 45,000 facts, sessions 40% faster, first-try success up 30%
Month 3: 90,000 facts, fleet measurably smarter per token
Each new session is better than the last. The intelligence compounds.
Issues
See all issues for the full roadmap.
Epics:
- EPIC 1: Session Harvester (#2)
- EPIC 2: Knowledge Store & Bootstrap (#3)
- EPIC 3: Compounding Measurement (#4)
- EPIC 4: Retroactive Harvest (#5)