fe517158a0
- Introduce scripts/test_documentation_generator.py: scans test files, adds module docstrings (explaining what is tested) and function docstrings (explaining verification purpose) without altering logic. - Applies documentation to 11 previously-undocumented test files: * tests/test_ci_config.py — added module-level docstring * tests/test_dedup.py — 30 function docstrings * tests/test_knowledge_gap_identifier.py — 10 function docstrings * tests/test_perf_bottleneck_finder.py — 25 function docstrings * tests/test_quality_gate.py — 14 function docstrings * scripts/test_diff_analyzer.py — 10 function docstrings * scripts/test_gitea_issue_parser.py — 6 function docstrings * scripts/test_harvest_prompt_comprehensive.py — 5 function docstrings * scripts/test_improvement_proposals.py — 2 function docstrings * scripts/test_knowledge_staleness.py — 8 function docstrings * scripts/test_session_pair_harvester.py — 5 function docstrings - Idempotent: re-running detects all 19 test files as up-to-date. - Processes up to 25 files per run (meets 20+ capacity requirement). Closes #88
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)