Compare commits
1 Commits
fix/201-py
...
fix/676
| Author | SHA1 | Date | |
|---|---|---|---|
| c203010e3a |
374
GENOME.md
374
GENOME.md
@@ -1,16 +1,16 @@
|
||||
# GENOME.md — compounding-intelligence
|
||||
|
||||
*Auto-generated codebase genome. Addresses timmy-home#676.*
|
||||
**Generated:** 2026-04-17
|
||||
**Repo:** Timmy_Foundation/compounding-intelligence
|
||||
**Description:** Turn 1B+ daily agent tokens into durable, compounding fleet intelligence.
|
||||
|
||||
---
|
||||
|
||||
## Project Overview
|
||||
|
||||
**What:** A system that turns 1B+ daily agent tokens into durable, compounding fleet intelligence.
|
||||
Every agent session starts at zero. The same HTTP 405 gets rediscovered as a branch protection issue. The same token path gets searched from scratch. Intelligence evaporates when the session ends.
|
||||
|
||||
**Why:** Every agent session starts at zero. The same mistakes get made repeatedly — the same HTTP 405 is rediscovered as a branch protection issue, the same token path is searched for from scratch. Intelligence evaporates when the session ends.
|
||||
|
||||
**How:** Three pipelines form a compounding loop:
|
||||
Compounding-intelligence solves this with three pipelines forming a loop:
|
||||
|
||||
```
|
||||
SESSION ENDS → HARVESTER → KNOWLEDGE STORE → BOOTSTRAPPER → NEW SESSION STARTS SMARTER
|
||||
@@ -18,222 +18,234 @@ SESSION ENDS → HARVESTER → KNOWLEDGE STORE → BOOTSTRAPPER → NEW SESSION
|
||||
MEASURER → Prove it's working
|
||||
```
|
||||
|
||||
**Status:** Early stage. Template and test scaffolding exist. Core pipeline scripts (harvester.py, bootstrapper.py, measurer.py, session_reader.py) are planned but not yet implemented. The knowledge extraction prompt is complete and validated.
|
||||
|
||||
---
|
||||
**Status:** Active development. Core pipelines implemented. 20+ scripts, 14 test files, knowledge store populated with real data.
|
||||
|
||||
## Architecture
|
||||
|
||||
```mermaid
|
||||
graph TD
|
||||
A[Session Transcript<br/>.jsonl] --> B[Harvester]
|
||||
B --> C{Extract Knowledge}
|
||||
C --> D[knowledge/index.json]
|
||||
C --> E[knowledge/global/*.md]
|
||||
C --> F[knowledge/repos/{repo}.md]
|
||||
C --> G[knowledge/agents/{agent}.md]
|
||||
D --> H[Bootstrapper]
|
||||
H --> I[Bootstrap Context<br/>2k token injection]
|
||||
I --> J[New Session<br/>starts smarter]
|
||||
J --> A
|
||||
D --> K[Measurer]
|
||||
K --> L[metrics/dashboard.md]
|
||||
K --> M[Velocity / Hit Rate<br/>Error Reduction]
|
||||
TRANS[Session Transcripts<br/>~/.hermes/sessions/*.jsonl] --> READER[session_reader.py]
|
||||
READER --> HARVESTER[harvester.py]
|
||||
HARVESTER -->|LLM extraction| PROMPT[harvest-prompt.md]
|
||||
HARVESTER --> DEDUP[deduplicate()]
|
||||
DEDUP --> INDEX[knowledge/index.json]
|
||||
DEDUP --> GLOBAL[knowledge/global/*.yaml]
|
||||
DEDUP --> REPO[knowledge/repos/*.yaml]
|
||||
|
||||
INDEX --> BOOTSTRAPPER[bootstrapper.py]
|
||||
BOOTSTRAPPER -->|filter + rank + truncate| CONTEXT[Bootstrap Context<br/>2k token injection]
|
||||
CONTEXT --> SESSION[New Session starts smarter]
|
||||
|
||||
INDEX --> VALIDATOR[validate_knowledge.py]
|
||||
INDEX --> STALENESS[knowledge_staleness_check.py]
|
||||
INDEX --> GAPS[knowledge_gap_identifier.py]
|
||||
|
||||
TRANS --> SAMPLER[sampler.py]
|
||||
SAMPLER -->|score + rank| BEST[High-value sessions]
|
||||
BEST --> HARVESTER
|
||||
|
||||
TRANS --> METADATA[session_metadata.py]
|
||||
METADATA --> SUMMARY[SessionSummary objects]
|
||||
|
||||
KNOWLEDGE --> DIFF[diff_analyzer.py]
|
||||
DIFF --> PROPOSALS[improvement_proposals.py]
|
||||
PROPOSALS --> PRIORITIES[priority_rebalancer.py]
|
||||
```
|
||||
|
||||
### Pipeline 1: Harvester
|
||||
## Entry Points
|
||||
|
||||
**Status:** Prompt designed. Script not implemented.
|
||||
### Core Pipelines
|
||||
|
||||
Reads finished session transcripts (JSONL). Uses `templates/harvest-prompt.md` to extract durable knowledge into five categories:
|
||||
| Script | Purpose | Key Functions |
|
||||
|--------|---------|---------------|
|
||||
| `harvester.py` | Extract knowledge from session transcripts | `harvest_session()`, `call_llm()`, `deduplicate()`, `validate_fact()` |
|
||||
| `bootstrapper.py` | Build pre-session context from knowledge store | `build_bootstrap_context()`, `filter_facts()`, `sort_facts()`, `truncate_to_tokens()` |
|
||||
| `session_reader.py` | Parse JSONL session transcripts | `read_session()`, `extract_conversation()`, `messages_to_text()` |
|
||||
| `sampler.py` | Score and rank sessions for harvesting value | `scan_session_fast()`, `score_session()` |
|
||||
| `session_metadata.py` | Extract structured metadata from sessions | `extract_session_metadata()`, `SessionSummary` |
|
||||
|
||||
| Category | Description | Example |
|
||||
|----------|-------------|---------|
|
||||
| `fact` | Concrete, verifiable information | "Repository X has 5 files" |
|
||||
| `pitfall` | Errors encountered, wrong assumptions | "Token is at ~/.config/gitea/token, not env var" |
|
||||
| `pattern` | Successful action sequences | "Deploy: test → build → push → webhook" |
|
||||
| `tool-quirk` | Environment-specific behaviors | "URL format requires trailing slash" |
|
||||
| `question` | Identified but unanswered | "Need optimal batch size for harvesting" |
|
||||
### Analysis & Quality
|
||||
|
||||
Output schema per knowledge item:
|
||||
```json
|
||||
{
|
||||
"fact": "One sentence description",
|
||||
"category": "fact|pitfall|pattern|tool-quirk|question",
|
||||
"repo": "repo-name or 'global'",
|
||||
"confidence": 0.0-1.0
|
||||
}
|
||||
```
|
||||
| Script | Purpose |
|
||||
|--------|---------|
|
||||
| `validate_knowledge.py` | Validate knowledge index schema compliance |
|
||||
| `knowledge_staleness_check.py` | Detect stale knowledge (source changed since extraction) |
|
||||
| `knowledge_gap_identifier.py` | Find untested functions, undocumented APIs, missing tests |
|
||||
| `diff_analyzer.py` | Analyze code diffs for improvement signals |
|
||||
| `improvement_proposals.py` | Generate ranked improvement proposals |
|
||||
| `priority_rebalancer.py` | Rebalance priorities across proposals |
|
||||
| `automation_opportunity_finder.py` | Find manual steps that can be automated |
|
||||
| `dead_code_detector.py` | Detect unused code |
|
||||
| `dependency_graph.py` | Map dependency relationships |
|
||||
| `perf_bottleneck_finder.py` | Find performance bottlenecks |
|
||||
| `refactoring_opportunity_finder.py` | Identify refactoring targets |
|
||||
| `gitea_issue_parser.py` | Parse Gitea issues for knowledge extraction |
|
||||
|
||||
### Pipeline 2: Bootstrapper
|
||||
### Automation
|
||||
|
||||
**Status:** Not implemented.
|
||||
| Script | Purpose |
|
||||
|--------|---------|
|
||||
| `session_pair_harvester.py` | Extract training pairs from sessions |
|
||||
|
||||
Queries knowledge store before session start. Assembles a compact 2k-token context from relevant facts. Injects into session startup so the agent begins with full situational awareness.
|
||||
|
||||
### Pipeline 3: Measurer
|
||||
|
||||
**Status:** Not implemented.
|
||||
|
||||
Tracks compounding metrics: knowledge velocity (facts/day), error reduction (%), hit rate (knowledge used / knowledge available), task completion improvement.
|
||||
|
||||
---
|
||||
|
||||
## Directory Structure
|
||||
## Data Flow
|
||||
|
||||
```
|
||||
compounding-intelligence/
|
||||
├── README.md # Project overview and architecture
|
||||
├── GENOME.md # This file (codebase genome)
|
||||
├── knowledge/ # [PLANNED] Knowledge store
|
||||
│ ├── index.json # Machine-readable fact index
|
||||
│ ├── global/ # Cross-repo knowledge
|
||||
│ ├── repos/{repo}.md # Per-repo knowledge
|
||||
│ └── agents/{agent}.md # Agent-type notes
|
||||
├── scripts/
|
||||
│ ├── test_harvest_prompt.py # Basic prompt validation (2.5KB)
|
||||
│ └── test_harvest_prompt_comprehensive.py # Full prompt structure test (6.8KB)
|
||||
├── templates/
|
||||
│ └── harvest-prompt.md # Knowledge extraction prompt (3.5KB)
|
||||
├── test_sessions/
|
||||
│ ├── session_success.jsonl # Happy path test data
|
||||
│ ├── session_failure.jsonl # Failure path test data
|
||||
│ ├── session_partial.jsonl # Incomplete session test data
|
||||
│ ├── session_patterns.jsonl # Pattern extraction test data
|
||||
│ └── session_questions.jsonl # Question identification test data
|
||||
└── metrics/ # [PLANNED] Compounding metrics
|
||||
└── dashboard.md
|
||||
1. Session ends → .jsonl written to ~/.hermes/sessions/
|
||||
2. sampler.py scores sessions by age, recency, repo coverage
|
||||
3. harvester.py reads top sessions, calls LLM with harvest-prompt.md
|
||||
4. LLM extracts facts/pitfalls/patterns/quirks/questions
|
||||
5. deduplicate() checks against existing index via fact_fingerprint()
|
||||
6. validate_fact() checks schema compliance
|
||||
7. write_knowledge() appends to knowledge/index.json + per-repo YAML
|
||||
8. On next session start, bootstrapper.py:
|
||||
a. Loads knowledge/index.json
|
||||
b. Filters by session's repo and agent type
|
||||
c. Sorts by confidence (high first), then recency
|
||||
d. Truncates to 2k token budget
|
||||
e. Injects as pre-context
|
||||
9. Agent starts with full situational awareness instead of zero
|
||||
```
|
||||
|
||||
---
|
||||
|
||||
## Entry Points and Data Flow
|
||||
|
||||
### Entry Point 1: Knowledge Extraction (Harvester)
|
||||
|
||||
```
|
||||
Input: Session transcript (JSONL)
|
||||
↓
|
||||
templates/harvest-prompt.md (LLM prompt)
|
||||
↓
|
||||
Knowledge items (JSON array)
|
||||
↓
|
||||
Output: knowledge/index.json + per-repo/per-agent markdown files
|
||||
```
|
||||
|
||||
### Entry Point 2: Session Bootstrap (Bootstrapper)
|
||||
|
||||
```
|
||||
Input: Session context (repo, agent type, task type)
|
||||
↓
|
||||
knowledge/index.json (query relevant facts)
|
||||
↓
|
||||
2k-token bootstrap context
|
||||
↓
|
||||
Output: Injected into session startup
|
||||
```
|
||||
|
||||
### Entry Point 3: Measurement (Measurer)
|
||||
|
||||
```
|
||||
Input: knowledge/index.json + session history
|
||||
↓
|
||||
Velocity, hit rate, error reduction calculations
|
||||
↓
|
||||
Output: metrics/dashboard.md
|
||||
```
|
||||
|
||||
---
|
||||
|
||||
## Key Abstractions
|
||||
|
||||
### Knowledge Item
|
||||
The atomic unit. One sentence, one category, one confidence score. Designed to be small enough that 1000 items fit in a 2k-token bootstrap context.
|
||||
### Knowledge Item (fact/pitfall/pattern/quirk/question)
|
||||
```json
|
||||
{
|
||||
"fact": "Gitea token is at ~/.config/gitea/token",
|
||||
"category": "tool-quirk",
|
||||
"repo": "global",
|
||||
"confidence": 0.9,
|
||||
"evidence": "Found during clone attempt",
|
||||
"source_session": "2026-04-13_abc123",
|
||||
"extracted_at": "2026-04-13T20:00:00Z"
|
||||
}
|
||||
```
|
||||
|
||||
### Knowledge Store
|
||||
A directory structure that mirrors the fleet's mental model:
|
||||
- `global/` — knowledge that applies everywhere (tool quirks, environment facts)
|
||||
- `repos/` — knowledge specific to each repo
|
||||
- `agents/` — knowledge specific to each agent type
|
||||
### SessionSummary (session_metadata.py)
|
||||
Extracted metadata per session: duration, token count, tools used, repos touched, error count, outcome.
|
||||
|
||||
### Confidence Score
|
||||
0.0–1.0 scale. Defines how certain the harvester is about each extracted fact:
|
||||
- 0.9–1.0: Explicitly stated with verification
|
||||
- 0.7–0.8: Clearly implied by multiple data points
|
||||
- 0.5–0.6: Suggested but not fully verified
|
||||
- 0.3–0.4: Inferred from limited data
|
||||
- 0.1–0.2: Speculative or uncertain
|
||||
### Gap / GapReport (knowledge_gap_identifier.py)
|
||||
Structured gap analysis: untested functions, undocumented APIs, missing tests. Severity: critical/high/medium/low.
|
||||
|
||||
### Bootstrap Context
|
||||
The 2k-token injection that a new session receives. Assembled from the most relevant knowledge items for the current task, filtered by confidence > 0.7, deduplicated, and compressed.
|
||||
### Knowledge Index (knowledge/index.json)
|
||||
Machine-readable fact store. 12KB, populated with real data. Categories: fact, pitfall, pattern, tool-quirk, question.
|
||||
|
||||
---
|
||||
## Knowledge Store
|
||||
|
||||
```
|
||||
knowledge/
|
||||
├── index.json # Master fact store (12KB, populated)
|
||||
├── SCHEMA.md # Schema documentation
|
||||
├── global/
|
||||
│ ├── pitfalls.yaml # Cross-repo pitfalls (2KB)
|
||||
│ └── tool-quirks.yaml # Tool-specific quirks (2KB)
|
||||
├── repos/
|
||||
│ ├── hermes-agent.yaml # hermes-agent knowledge (2KB)
|
||||
│ └── the-nexus.yaml # the-nexus knowledge (2KB)
|
||||
└── agents/ # Per-agent knowledge (empty)
|
||||
```
|
||||
|
||||
## API Surface
|
||||
|
||||
### Internal (scripts not yet implemented)
|
||||
### LLM API (consumed)
|
||||
| Provider | Endpoint | Usage |
|
||||
|----------|----------|-------|
|
||||
| Nous Research | `https://inference-api.nousresearch.com/v1` | Knowledge extraction |
|
||||
| Ollama | `http://localhost:11434/v1` | Local fallback |
|
||||
|
||||
| Script | Input | Output | Status |
|
||||
|--------|-------|--------|--------|
|
||||
| `harvester.py` | Session JSONL path | Knowledge items JSON | PLANNED |
|
||||
| `bootstrapper.py` | Repo + agent type | 2k-token context string | PLANNED |
|
||||
| `measurer.py` | Knowledge store path | Metrics JSON | PLANNED |
|
||||
| `session_reader.py` | Session JSONL path | Parsed transcript | PLANNED |
|
||||
|
||||
### Prompt (templates/harvest-prompt.md)
|
||||
|
||||
The extraction prompt is the core "API." It takes a session transcript and returns structured JSON. It defines:
|
||||
- Five extraction categories
|
||||
- Output format (JSON array of knowledge items)
|
||||
- Confidence scoring rubric
|
||||
- Constraints (no hallucination, specificity, relevance, brevity)
|
||||
- Example input/output pair
|
||||
|
||||
---
|
||||
### File API (consumed/produced)
|
||||
| Path | Format | Direction |
|
||||
|------|--------|-----------|
|
||||
| `~/.hermes/sessions/*.jsonl` | JSONL | Input (session transcripts) |
|
||||
| `knowledge/index.json` | JSON | Output (master fact store) |
|
||||
| `knowledge/global/*.yaml` | YAML | Output (cross-repo knowledge) |
|
||||
| `knowledge/repos/*.yaml` | YAML | Output (per-repo knowledge) |
|
||||
| `templates/harvest-prompt.md` | Markdown | Config (extraction prompt) |
|
||||
|
||||
## Test Coverage
|
||||
|
||||
### What Exists
|
||||
**14 test files** covering core pipelines:
|
||||
|
||||
| File | Tests | Coverage |
|
||||
|------|-------|----------|
|
||||
| `scripts/test_harvest_prompt.py` | 2 tests | Prompt file existence, sample transcript |
|
||||
| `scripts/test_harvest_prompt_comprehensive.py` | 5 tests | Prompt structure, categories, fields, confidence scoring, size limits |
|
||||
| `test_sessions/*.jsonl` | 5 sessions | Success, failure, partial, patterns, questions |
|
||||
| Test File | Covers |
|
||||
|-----------|--------|
|
||||
| `test_harvest_prompt.py` | Prompt validation, hallucination detection |
|
||||
| `test_harvest_prompt_comprehensive.py` | Extended prompt testing |
|
||||
| `test_harvester_pipeline.py` | Harvester extraction + dedup |
|
||||
| `test_bootstrapper.py` | Context building, filtering, truncation |
|
||||
| `test_session_pair_harvester.py` | Training pair extraction |
|
||||
| `test_improvement_proposals.py` | Proposal generation |
|
||||
| `test_priority_rebalancer.py` | Priority scoring |
|
||||
| `test_knowledge_staleness.py` | Staleness detection |
|
||||
| `test_automation_opportunity_finder.py` | Automation detection |
|
||||
| `test_diff_analyzer.py` | Diff analysis |
|
||||
| `test_gitea_issue_parser.py` | Issue parsing |
|
||||
| `test_refactoring_opportunity_finder.py` | Refactoring signals |
|
||||
| `test_knowledge_gap_identifier.py` | Gap analysis |
|
||||
| `test_perf_bottleneck_finder.py` | Perf bottleneck detection |
|
||||
|
||||
### What's Missing
|
||||
### Coverage Gaps
|
||||
|
||||
1. **Harvester integration test** — Does the prompt actually extract correct knowledge from real transcripts?
|
||||
2. **Bootstrapper test** — Does it assemble relevant context correctly?
|
||||
3. **Knowledge store test** — Does the index.json maintain consistency?
|
||||
4. **Confidence calibration test** — Do high-confidence facts actually prove true in later sessions?
|
||||
5. **Deduplication test** — Are duplicate facts across sessions handled?
|
||||
6. **Staleness test** — How does the system handle outdated knowledge?
|
||||
|
||||
---
|
||||
1. **session_reader.py** — No dedicated test file (tested indirectly)
|
||||
2. **sampler.py** — No test file (scoring logic untested)
|
||||
3. **session_metadata.py** — No test file
|
||||
4. **validate_knowledge.py** — No test file
|
||||
5. **knowledge_staleness_check.py** — Tested but limited
|
||||
|
||||
## Security Considerations
|
||||
|
||||
1. **No secrets in knowledge store** — The harvester must filter out API keys, tokens, and credentials from extracted facts. The prompt constraints mention this but there is no automated guard.
|
||||
### API Key Handling
|
||||
- `harvester.py` reads API key from `~/.hermes/auth.json` or env vars
|
||||
- Key passed to LLM API in request headers only
|
||||
- No key logging
|
||||
|
||||
2. **Knowledge poisoning** — A malicious or corrupted session could inject false facts. Confidence scoring partially mitigates this, but there is no verification step.
|
||||
### Knowledge Integrity
|
||||
- `validate_fact()` checks schema before writing
|
||||
- `deduplicate()` prevents duplicate entries via fingerprint
|
||||
- `knowledge_staleness_check.py` detects when source code changed but knowledge didn't
|
||||
- Confidence scores prevent low-quality knowledge from polluting the store
|
||||
|
||||
3. **Access control** — The knowledge store has no access control. Any process that can read the directory can read all facts. In a multi-tenant setup, this is a concern.
|
||||
### File Safety
|
||||
- Knowledge writes are append-only (never deletes)
|
||||
- Bootstrap context is truncated to budget (no prompt injection via knowledge)
|
||||
- Session reader handles malformed JSONL gracefully
|
||||
|
||||
4. **Transcript privacy** — Session transcripts may contain user data. The harvester must not extract personally identifiable information into the knowledge store.
|
||||
## File Index
|
||||
|
||||
```
|
||||
scripts/
|
||||
harvester.py (473 lines) — Core knowledge extraction
|
||||
bootstrapper.py (302 lines) — Pre-session context builder
|
||||
session_reader.py (137 lines) — JSONL session parser
|
||||
sampler.py (363 lines) — Session scoring + ranking
|
||||
session_metadata.py (271 lines) — Session metadata extraction
|
||||
validate_knowledge.py (44 lines) — Index validation
|
||||
knowledge_staleness_check.py (125 lines) — Staleness detection
|
||||
knowledge_gap_identifier.py (291 lines) — Gap analysis engine
|
||||
diff_analyzer.py (203 lines) — Diff analysis
|
||||
improvement_proposals.py (518 lines) — Proposal generation
|
||||
priority_rebalancer.py (745 lines) — Priority scoring
|
||||
automation_opportunity_finder.py (600 lines) — Automation detection
|
||||
dead_code_detector.py (270 lines) — Dead code detection
|
||||
dependency_graph.py (220 lines) — Dependency mapping
|
||||
perf_bottleneck_finder.py (635 lines) — Perf analysis
|
||||
refactoring_opportunity_finder.py (46 lines) — Refactoring signals
|
||||
gitea_issue_parser.py (140 lines) — Gitea issue parsing
|
||||
session_pair_harvester.py (224 lines) — Training pair extraction
|
||||
knowledge/
|
||||
index.json (12KB) — Master fact store
|
||||
SCHEMA.md (3KB) — Schema docs
|
||||
global/pitfalls.yaml (2KB) — Cross-repo pitfalls
|
||||
global/tool-quirks.yaml (2KB) — Tool quirks
|
||||
repos/hermes-agent.yaml (2KB) — Repo-specific knowledge
|
||||
repos/the-nexus.yaml (2KB) — Repo-specific knowledge
|
||||
templates/
|
||||
harvest-prompt.md (4KB) — Extraction prompt
|
||||
test_sessions/ (5 files) — Sample transcripts
|
||||
tests/ + scripts/test_* (14 files)— Test suite
|
||||
```
|
||||
|
||||
**Total:** ~6,500 lines of code across 18 scripts + 14 test files.
|
||||
|
||||
---
|
||||
|
||||
## The 100x Path (from README)
|
||||
|
||||
```
|
||||
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.
|
||||
|
||||
---
|
||||
|
||||
*Generated by codebase-genome pipeline. Ref: timmy-home#676.*
|
||||
*Generated by Codebase Genome pipeline — Issue #676*
|
||||
|
||||
@@ -1,72 +1,212 @@
|
||||
#!/usr/bin/env python3
|
||||
"""Comprehensive tests for knowledge extraction prompt."""
|
||||
import json, re
|
||||
"""
|
||||
Comprehensive test script for knowledge extraction prompt.
|
||||
Validates prompt structure, requirements, and consistency.
|
||||
"""
|
||||
|
||||
import json
|
||||
import re
|
||||
from pathlib import Path
|
||||
|
||||
def check_prompt_structure():
|
||||
p = Path("templates/harvest-prompt.md")
|
||||
if not p.exists(): return False, "harvest-prompt.md not found"
|
||||
c = p.read_text()
|
||||
for s in ["System Prompt","Instructions","Categories","Output Format","Confidence Scoring","Constraints","Example"]:
|
||||
if s.lower() not in c.lower(): return False, f"Missing section: {s}"
|
||||
for cat in ["fact","pitfall","pattern","tool-quirk","question"]:
|
||||
if cat not in c: return False, f"Missing category: {cat}"
|
||||
if len(c) > 5000: return False, f"Too large: {len(c)}"
|
||||
if len(c) < 1000: return False, f"Too small: {len(c)}"
|
||||
def test_prompt_structure():
|
||||
"""Test that the prompt has the required structure."""
|
||||
prompt_path = Path("templates/harvest-prompt.md")
|
||||
if not prompt_path.exists():
|
||||
return False, "harvest-prompt.md not found"
|
||||
|
||||
content = prompt_path.read_text()
|
||||
|
||||
# Check for required sections
|
||||
required_sections = [
|
||||
"System Prompt",
|
||||
"Instructions",
|
||||
"Categories",
|
||||
"Output Format",
|
||||
"Confidence Scoring",
|
||||
"Constraints",
|
||||
"Example"
|
||||
]
|
||||
|
||||
for section in required_sections:
|
||||
if section.lower() not in content.lower():
|
||||
return False, f"Missing required section: {section}"
|
||||
|
||||
# Check for required categories
|
||||
required_categories = ["fact", "pitfall", "pattern", "tool-quirk", "question"]
|
||||
for category in required_categories:
|
||||
if category not in content:
|
||||
return False, f"Missing required category: {category}"
|
||||
|
||||
# Check for required output fields
|
||||
required_fields = ["fact", "category", "repo", "confidence"]
|
||||
for field in required_fields:
|
||||
if field not in content:
|
||||
return False, f"Missing required output field: {field}"
|
||||
|
||||
# Check prompt size (should be ~1k tokens, roughly 4k chars)
|
||||
if len(content) > 5000:
|
||||
return False, f"Prompt too large: {len(content)} chars (max ~5000)"
|
||||
|
||||
if len(content) < 1000:
|
||||
return False, f"Prompt too small: {len(content)} chars (min ~1000)"
|
||||
|
||||
return True, "Prompt structure is valid"
|
||||
|
||||
def check_confidence_scoring():
|
||||
c = Path("templates/harvest-prompt.md").read_text()
|
||||
for l in ["0.9-1.0","0.7-0.8","0.5-0.6","0.3-0.4","0.1-0.2"]:
|
||||
if l not in c: return False, f"Missing level: {l}"
|
||||
return True, "Confidence scoring defined"
|
||||
|
||||
def check_example_quality():
|
||||
c = Path("templates/harvest-prompt.md").read_text()
|
||||
if "example" not in c.lower(): return False, "No examples"
|
||||
m = re.search(r'"knowledge"', c[c.lower().find("example"):])
|
||||
if not m: return False, "No JSON example"
|
||||
return True, "Examples present"
|
||||
|
||||
def check_constraint_coverage():
|
||||
c = Path("templates/harvest-prompt.md").read_text()
|
||||
for x in ["no hallucination","explicitly","partial","failed sessions"]:
|
||||
if x not in c.lower(): return False, f"Missing: {x}"
|
||||
return True, "Constraints covered"
|
||||
|
||||
def check_test_sessions():
|
||||
d = Path("test_sessions")
|
||||
if not d.exists(): return False, "test_sessions/ not found"
|
||||
files = list(d.glob("*.jsonl"))
|
||||
if len(files) < 5: return False, f"Only {len(files)} sessions"
|
||||
for f in files:
|
||||
for i, line in enumerate(f.read_text().strip().split("\n"), 1):
|
||||
try: json.loads(line)
|
||||
except json.JSONDecodeError as e: return False, f"{f.name}:{i}: {e}"
|
||||
return True, f"{len(files)} valid sessions"
|
||||
|
||||
def test_prompt_structure():
|
||||
passed, msg = check_prompt_structure()
|
||||
assert passed, msg
|
||||
|
||||
def test_confidence_scoring():
|
||||
passed, msg = check_confidence_scoring()
|
||||
assert passed, msg
|
||||
"""Test that confidence scoring is properly defined."""
|
||||
prompt_path = Path("templates/harvest-prompt.md")
|
||||
content = prompt_path.read_text()
|
||||
|
||||
# Check for confidence scale definitions
|
||||
confidence_levels = [
|
||||
("0.9-1.0", "explicitly stated"),
|
||||
("0.7-0.8", "clearly implied"),
|
||||
("0.5-0.6", "suggested"),
|
||||
("0.3-0.4", "inferred"),
|
||||
("0.1-0.2", "speculative")
|
||||
]
|
||||
|
||||
for level, description in confidence_levels:
|
||||
if level not in content:
|
||||
return False, f"Missing confidence level: {level}"
|
||||
if description.lower() not in content.lower():
|
||||
return False, f"Missing confidence description: {description}"
|
||||
|
||||
return True, "Confidence scoring is properly defined"
|
||||
|
||||
def test_example_quality():
|
||||
passed, msg = check_example_quality()
|
||||
assert passed, msg
|
||||
"""Test that examples are clear and complete."""
|
||||
prompt_path = Path("templates/harvest-prompt.md")
|
||||
content = prompt_path.read_text()
|
||||
|
||||
# Check for example input/output
|
||||
if "example" not in content.lower():
|
||||
return False, "No examples provided"
|
||||
|
||||
# Check that example includes all categories
|
||||
example_section = content[content.lower().find("example"):]
|
||||
|
||||
# Look for JSON example
|
||||
json_match = re.search(r'\{[\s\S]*"knowledge"[\s\S]*\}', example_section)
|
||||
if not json_match:
|
||||
return False, "No JSON example found"
|
||||
|
||||
example_json = json_match.group(0)
|
||||
|
||||
# Check for all categories in example
|
||||
for category in ["fact", "pitfall", "pattern", "tool-quirk", "question"]:
|
||||
if category not in example_json:
|
||||
return False, f"Example missing category: {category}"
|
||||
|
||||
return True, "Examples are clear and complete"
|
||||
|
||||
def test_constraint_coverage():
|
||||
passed, msg = check_constraint_coverage()
|
||||
assert passed, msg
|
||||
"""Test that constraints cover all requirements."""
|
||||
prompt_path = Path("templates/harvest-prompt.md")
|
||||
content = prompt_path.read_text()
|
||||
|
||||
required_constraints = [
|
||||
"No hallucination",
|
||||
"only extract",
|
||||
"explicitly",
|
||||
"partial",
|
||||
"failed sessions",
|
||||
"1k tokens"
|
||||
]
|
||||
|
||||
for constraint in required_constraints:
|
||||
if constraint.lower() not in content.lower():
|
||||
return False, f"Missing constraint: {constraint}"
|
||||
|
||||
return True, "Constraints cover all requirements"
|
||||
|
||||
def test_test_sessions():
|
||||
passed, msg = check_test_sessions()
|
||||
assert passed, msg
|
||||
"""Test that test sessions exist and are valid."""
|
||||
test_sessions_dir = Path("test_sessions")
|
||||
if not test_sessions_dir.exists():
|
||||
return False, "test_sessions directory not found"
|
||||
|
||||
session_files = list(test_sessions_dir.glob("*.jsonl"))
|
||||
if len(session_files) < 5:
|
||||
return False, f"Only {len(session_files)} test sessions found, need 5"
|
||||
|
||||
# Check each session file
|
||||
for session_file in session_files:
|
||||
content = session_file.read_text()
|
||||
lines = content.strip().split("\n")
|
||||
|
||||
# Check that each line is valid JSON
|
||||
for i, line in enumerate(lines, 1):
|
||||
try:
|
||||
json.loads(line)
|
||||
except json.JSONDecodeError as e:
|
||||
return False, f"Invalid JSON in {session_file.name}, line {i}: {e}"
|
||||
|
||||
return True, f"Found {len(session_files)} valid test sessions"
|
||||
|
||||
def run_all_tests():
|
||||
"""Run all tests and return results."""
|
||||
tests = [
|
||||
("Prompt Structure", test_prompt_structure),
|
||||
("Confidence Scoring", test_confidence_scoring),
|
||||
("Example Quality", test_example_quality),
|
||||
("Constraint Coverage", test_constraint_coverage),
|
||||
("Test Sessions", test_test_sessions)
|
||||
]
|
||||
|
||||
results = []
|
||||
all_passed = True
|
||||
|
||||
for test_name, test_func in tests:
|
||||
try:
|
||||
passed, message = test_func()
|
||||
results.append({
|
||||
"test": test_name,
|
||||
"passed": passed,
|
||||
"message": message
|
||||
})
|
||||
if not passed:
|
||||
all_passed = False
|
||||
except Exception as e:
|
||||
results.append({
|
||||
"test": test_name,
|
||||
"passed": False,
|
||||
"message": f"Error: {str(e)}"
|
||||
})
|
||||
all_passed = False
|
||||
|
||||
# Print results
|
||||
print("=" * 60)
|
||||
print("HARVEST PROMPT TEST RESULTS")
|
||||
print("=" * 60)
|
||||
|
||||
for result in results:
|
||||
status = "✓ PASS" if result["passed"] else "✗ FAIL"
|
||||
print(f"{status}: {result['test']}")
|
||||
print(f" {result['message']}")
|
||||
print()
|
||||
|
||||
print("=" * 60)
|
||||
if all_passed:
|
||||
print("ALL TESTS PASSED!")
|
||||
else:
|
||||
print("SOME TESTS FAILED!")
|
||||
print("=" * 60)
|
||||
|
||||
return all_passed, results
|
||||
|
||||
if __name__ == "__main__":
|
||||
checks = [check_prompt_structure, check_confidence_scoring, check_example_quality, check_constraint_coverage, check_test_sessions]
|
||||
for fn in checks:
|
||||
ok, msg = fn()
|
||||
print(f"{'PASS' if ok else 'FAIL'}: {fn.__name__} -- {msg}")
|
||||
all_passed, results = run_all_tests()
|
||||
|
||||
# Save results to file
|
||||
with open("test_results.json", "w") as f:
|
||||
json.dump({
|
||||
"all_passed": all_passed,
|
||||
"results": results,
|
||||
"timestamp": "2026-04-14T19:05:00Z"
|
||||
}, f, indent=2)
|
||||
|
||||
print(f"Results saved to test_results.json")
|
||||
|
||||
# Exit with appropriate code
|
||||
exit(0 if all_passed else 1)
|
||||
|
||||
Reference in New Issue
Block a user