Files
compounding-intelligence/knowledge/SCHEMA.md

115 lines
3.0 KiB
Markdown
Raw Normal View History

# Knowledge File Format Specification
**Version:** 1
**Issue:** #10
**Status:** Draft
---
## Overview
The knowledge system has two layers:
1. **index.json** — Machine-readable fact index. Fast lookups by ID, category, repo, tags.
2. **Knowledge files** (YAML) — Human-readable, editable facts organized by domain.
The harvester writes to both. The bootstrapper reads from index.json. Humans edit the YAML files directly.
---
## index.json Schema
```json
{
"version": 1,
"last_updated": "ISO-8601 timestamp",
"total_facts": 0,
"facts": []
}
```
### Fact Object
| Field | Type | Required | Description |
|-------|------|----------|-------------|
| `id` | string | yes | Unique identifier: `{domain}:{category}:{sequence}` |
| `fact` | string | yes | One-sentence description of the knowledge |
| `category` | enum | yes | One of: `fact`, `pitfall`, `pattern`, `tool-quirk`, `question` |
| `domain` | string | yes | Where this applies: repo name, `global`, or agent name |
| `confidence` | float | yes | 0.01.0. How certain is this knowledge? |
| `tags` | string[] | no | Searchable labels |
| `source_count` | int | no | How many sessions confirmed this fact |
| `first_seen` | date | no | ISO-8601 date first extracted |
| `last_confirmed` | date | no | ISO-8601 date last seen in a session |
| `expires` | date | no | Optional. After this date, fact is stale |
| `related` | string[] | no | IDs of related facts |
### ID Format: `{domain}:{category}:{sequence}`
### Categories
| Category | Definition |
|----------|------------|
| `fact` | Concrete, verifiable information |
| `pitfall` | Errors, wrong assumptions, time-wasters |
| `pattern` | Successful sequences of actions |
| `tool-quirk` | Environment-specific behaviors |
| `question` | Identified but unanswered |
### Confidence Scoring
| Range | Meaning |
|-------|---------|
| 0.91.0 | Explicitly stated and verified |
| 0.70.8 | Clearly implied by multiple data points |
| 0.50.6 | Suggested but not fully verified |
| 0.30.4 | Inferred from limited data |
| 0.10.2 | Speculative or uncertain |
---
## Directory Structure
```
knowledge/
├── index.json # Machine-readable fact index
├── SCHEMA.md # This file
├── global/ # Cross-repo knowledge
│ ├── pitfalls.yaml
│ ├── patterns.yaml
│ └── tool-quirks.yaml
├── repos/ # Per-repo knowledge
│ ├── {repo-name}.yaml
│ └── ...
└── agents/ # Agent-type knowledge
└── {agent-type}.yaml
```
## YAML File Format
YAML files use frontmatter for metadata, then markdown sections with fact entries:
```yaml
---
domain: global
category: tool-quirk
version: 1
last_updated: "2026-04-13"
---
# Title
## Section
- id: global:tool-quirk:001
fact: "Description"
confidence: 0.95
tags: [tag1, tag2]
source_count: 5
first_seen: "2026-03-27"
```
## Validation
Run `python scripts/validate_knowledge.py` to validate index.json.