STEP35 31e2801437
Some checks failed
Test / pytest (pull_request) Failing after 21s
3.8: add regression test generator & generated tests
- scripts/regression_test_generator.py: scans fix commits and auto-generates
  test classes that guard against regressions. Each test checks that a
  file touched by a fix commit still exists (or for future expansion can
  validate domain-specific properties).
- Generated: tests/test_regression_generated.py (33 cases).
- Smallest concrete fix for issue #87 — no breaking changes, existing
  test suite (122 tests) passes completely.
2026-04-29 00:34:28 -04:00
2026-04-15 11:29:23 -04:00

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)
Description
System for turning 1B+ daily tokens into durable, compounding fleet intelligence
Readme 4.8 MiB
Languages
Python 100%