Compare commits
1 Commits
feat/93-de
...
fix/10-kno
| Author | SHA1 | Date | |
|---|---|---|---|
|
b32d316023 |
114
knowledge/SCHEMA.md
Normal file
114
knowledge/SCHEMA.md
Normal file
@@ -0,0 +1,114 @@
|
||||
# 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 | 0.0–1.0. 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 |
|
||||
|-------|---------|
|
||||
| 0.9–1.0 | Explicitly stated and verified |
|
||||
| 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 |
|
||||
|
||||
---
|
||||
|
||||
## 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.
|
||||
80
knowledge/global/pitfalls.yaml
Normal file
80
knowledge/global/pitfalls.yaml
Normal file
@@ -0,0 +1,80 @@
|
||||
---
|
||||
domain: global
|
||||
category: pitfall
|
||||
version: 1
|
||||
last_updated: "2026-04-13"
|
||||
---
|
||||
|
||||
# Pitfalls (Global)
|
||||
|
||||
Cross-repo traps that waste time across the fleet.
|
||||
|
||||
## Git & Forge
|
||||
|
||||
- id: global:pitfall:001
|
||||
fact: "Branch protection requires 1 approval on main - API merges fail with 405 without it"
|
||||
confidence: 0.95
|
||||
tags: [git, merge, branch-protection, gitea]
|
||||
source_count: 12
|
||||
first_seen: "2026-04-05"
|
||||
last_confirmed: "2026-04-13"
|
||||
related: [the-nexus:pitfall:001]
|
||||
|
||||
- id: global:pitfall:002
|
||||
fact: "Never use --no-verify on git commits - it bypasses all hooks including safety checks"
|
||||
confidence: 0.95
|
||||
tags: [git, hooks, safety]
|
||||
source_count: 5
|
||||
first_seen: "2026-03-28"
|
||||
last_confirmed: "2026-04-13"
|
||||
|
||||
- id: global:pitfall:003
|
||||
fact: "Gitea PR creation workaround needed on the-nexus - direct API call fails, use alternative endpoint"
|
||||
confidence: 0.9
|
||||
tags: [gitea, pr, api, workaround]
|
||||
source_count: 4
|
||||
first_seen: "2026-04-06"
|
||||
last_confirmed: "2026-04-12"
|
||||
|
||||
## Agent Operations
|
||||
|
||||
- id: global:pitfall:004
|
||||
fact: "Anthropic is BANNED from fallback chain - if fallback triggers to Anthropic, something is wrong"
|
||||
confidence: 0.95
|
||||
tags: [provider, anthropic, fallback]
|
||||
source_count: 7
|
||||
first_seen: "2026-03-30"
|
||||
last_confirmed: "2026-04-13"
|
||||
|
||||
- id: global:pitfall:005
|
||||
fact: "Telegram tokens expired - don't assume Telegram notifications work without checking"
|
||||
confidence: 0.85
|
||||
tags: [telegram, notifications, token]
|
||||
source_count: 3
|
||||
first_seen: "2026-04-02"
|
||||
|
||||
- id: global:pitfall:006
|
||||
fact: "Multiple gateways = 'cannot schedule futures' error - only one gateway process should run"
|
||||
confidence: 0.9
|
||||
tags: [gateway, cron, process]
|
||||
source_count: 4
|
||||
first_seen: "2026-04-04"
|
||||
last_confirmed: "2026-04-11"
|
||||
|
||||
## Testing
|
||||
|
||||
- id: global:pitfall:007
|
||||
fact: "pytest root collection picks up operational *_test.py scripts - restrict to tests/ directory"
|
||||
confidence: 0.9
|
||||
tags: [pytest, test, collection]
|
||||
source_count: 3
|
||||
first_seen: "2026-04-07"
|
||||
last_confirmed: "2026-04-13"
|
||||
|
||||
- id: global:pitfall:008
|
||||
fact: "TDD: test 1 before building 55 - verify the cycle works before scaling"
|
||||
confidence: 0.95
|
||||
tags: [tdd, testing, methodology]
|
||||
source_count: 8
|
||||
first_seen: "2026-03-25"
|
||||
last_confirmed: "2026-04-13"
|
||||
71
knowledge/global/tool-quirks.yaml
Normal file
71
knowledge/global/tool-quirks.yaml
Normal file
@@ -0,0 +1,71 @@
|
||||
---
|
||||
domain: global
|
||||
category: tool-quirk
|
||||
version: 1
|
||||
last_updated: "2026-04-13"
|
||||
---
|
||||
|
||||
# Tool Quirks (Global)
|
||||
|
||||
## Authentication
|
||||
|
||||
- id: global:tool-quirk:001
|
||||
fact: "Gitea token stored at ~/.config/gitea/token, not env var GITEA_TOKEN"
|
||||
confidence: 0.95
|
||||
tags: [git, auth, gitea, token]
|
||||
source_count: 23
|
||||
first_seen: "2026-03-27"
|
||||
last_confirmed: "2026-04-13"
|
||||
related: [global:pitfall:001]
|
||||
|
||||
- id: global:tool-quirk:002
|
||||
fact: "Gitea API uses 'Authorization: token TOKEN' header format, not Bearer"
|
||||
confidence: 0.9
|
||||
tags: [git, api, gitea]
|
||||
source_count: 8
|
||||
first_seen: "2026-03-28"
|
||||
last_confirmed: "2026-04-12"
|
||||
|
||||
- id: global:tool-quirk:003
|
||||
fact: "Gitea Issues API type=issues param does NOT filter PRs - use truthiness check on pull_request field"
|
||||
confidence: 0.95
|
||||
tags: [gitea, api, issues, pr]
|
||||
source_count: 6
|
||||
first_seen: "2026-04-01"
|
||||
last_confirmed: "2026-04-13"
|
||||
|
||||
## Paths & Environment
|
||||
|
||||
- id: global:tool-quirk:004
|
||||
fact: "~/.hermes is the default hermes home - check get_hermes_home() not the path literal"
|
||||
confidence: 0.9
|
||||
tags: [paths, hermes, env]
|
||||
source_count: 10
|
||||
first_seen: "2026-03-30"
|
||||
last_confirmed: "2026-04-13"
|
||||
related: [hermes-agent:pitfall:005]
|
||||
|
||||
- id: global:tool-quirk:005
|
||||
fact: "Ansible vault-encrypted vars in YAML require vault_inline_vars plugin"
|
||||
confidence: 0.85
|
||||
tags: [ansible, vault, config]
|
||||
source_count: 3
|
||||
first_seen: "2026-04-02"
|
||||
|
||||
## Model & Inference
|
||||
|
||||
- id: global:tool-quirk:006
|
||||
fact: "mimo-v2-pro via Nous Research is the default model - don't assume Anthropic is available"
|
||||
confidence: 0.95
|
||||
tags: [model, provider, nous, default]
|
||||
source_count: 15
|
||||
first_seen: "2026-03-25"
|
||||
last_confirmed: "2026-04-13"
|
||||
|
||||
- id: global:tool-quirk:007
|
||||
fact: "Kill + restart with 'hermes chat' preserves old model state - NEVER use --resume"
|
||||
confidence: 0.95
|
||||
tags: [hermes, model, restart, session]
|
||||
source_count: 8
|
||||
first_seen: "2026-03-29"
|
||||
last_confirmed: "2026-04-12"
|
||||
@@ -1,6 +1,472 @@
|
||||
{
|
||||
"version": 1,
|
||||
"last_updated": "2026-04-13T20:00:00Z",
|
||||
"total_facts": 0,
|
||||
"facts": []
|
||||
"total_facts": 29,
|
||||
"facts": [
|
||||
{
|
||||
"id": "hermes-agent:pitfall:001",
|
||||
"fact": "deploy-crons.py leaves jobs in mixed model format",
|
||||
"category": "pitfall",
|
||||
"domain": "hermes-agent",
|
||||
"confidence": 0.95,
|
||||
"tags": [
|
||||
"cron",
|
||||
"deploy",
|
||||
"model",
|
||||
"config"
|
||||
],
|
||||
"source_count": 5,
|
||||
"first_seen": "2026-04-08",
|
||||
"last_confirmed": "2026-04-13",
|
||||
"related": [
|
||||
"hermes-agent:pitfall:002",
|
||||
"hermes-agent:pitfall:003"
|
||||
]
|
||||
},
|
||||
{
|
||||
"id": "hermes-agent:pitfall:002",
|
||||
"fact": "deploy-crons.py --deploy doesn't set legacy skill field from skills list",
|
||||
"category": "pitfall",
|
||||
"domain": "hermes-agent",
|
||||
"confidence": 0.9,
|
||||
"tags": [
|
||||
"cron",
|
||||
"deploy",
|
||||
"skills"
|
||||
],
|
||||
"source_count": 3,
|
||||
"first_seen": "2026-04-09",
|
||||
"last_confirmed": "2026-04-13",
|
||||
"related": [
|
||||
"hermes-agent:pitfall:001"
|
||||
]
|
||||
},
|
||||
{
|
||||
"id": "hermes-agent:pitfall:003",
|
||||
"fact": "Cron jobs with blank fallback_model fields trigger spurious gateway warnings",
|
||||
"category": "pitfall",
|
||||
"domain": "hermes-agent",
|
||||
"confidence": 0.9,
|
||||
"tags": [
|
||||
"cron",
|
||||
"model",
|
||||
"fallback"
|
||||
],
|
||||
"source_count": 4,
|
||||
"first_seen": "2026-04-07",
|
||||
"last_confirmed": "2026-04-12",
|
||||
"related": [
|
||||
"hermes-agent:pitfall:001"
|
||||
]
|
||||
},
|
||||
{
|
||||
"id": "hermes-agent:pitfall:004",
|
||||
"fact": "model-watchdog.py checks first provider line, not model.provider - causes false drift alarms",
|
||||
"category": "pitfall",
|
||||
"domain": "hermes-agent",
|
||||
"confidence": 0.9,
|
||||
"tags": [
|
||||
"watchdog",
|
||||
"model",
|
||||
"config"
|
||||
],
|
||||
"source_count": 3,
|
||||
"first_seen": "2026-04-08",
|
||||
"last_confirmed": "2026-04-13"
|
||||
},
|
||||
{
|
||||
"id": "hermes-agent:pitfall:005",
|
||||
"fact": "10+ files read HERMES_HOME directly instead of get_hermes_home()",
|
||||
"category": "pitfall",
|
||||
"domain": "hermes-agent",
|
||||
"confidence": 0.85,
|
||||
"tags": [
|
||||
"paths",
|
||||
"env",
|
||||
"hermes-home"
|
||||
],
|
||||
"source_count": 6,
|
||||
"first_seen": "2026-04-06",
|
||||
"last_confirmed": "2026-04-12",
|
||||
"related": [
|
||||
"global:pitfall:002"
|
||||
]
|
||||
},
|
||||
{
|
||||
"id": "hermes-agent:pitfall:006",
|
||||
"fact": "get_hermes_home() doesn't expand tilde when HERMES_HOME=~/... is set",
|
||||
"category": "pitfall",
|
||||
"domain": "hermes-agent",
|
||||
"confidence": 0.8,
|
||||
"tags": [
|
||||
"paths",
|
||||
"env",
|
||||
"bug"
|
||||
],
|
||||
"source_count": 2,
|
||||
"first_seen": "2026-04-05"
|
||||
},
|
||||
{
|
||||
"id": "hermes-agent:pitfall:007",
|
||||
"fact": "vps-agent-dispatch reports OK while remote hermes binary path is broken",
|
||||
"category": "pitfall",
|
||||
"domain": "hermes-agent",
|
||||
"confidence": 0.9,
|
||||
"tags": [
|
||||
"ssh",
|
||||
"dispatch",
|
||||
"vps"
|
||||
],
|
||||
"source_count": 4,
|
||||
"first_seen": "2026-04-07",
|
||||
"last_confirmed": "2026-04-11"
|
||||
},
|
||||
{
|
||||
"id": "hermes-agent:pitfall:008",
|
||||
"fact": "nightwatch-health-monitor SSH check fails on cloud-model-only deployments",
|
||||
"category": "pitfall",
|
||||
"domain": "hermes-agent",
|
||||
"confidence": 0.85,
|
||||
"tags": [
|
||||
"ssh",
|
||||
"health",
|
||||
"cloud"
|
||||
],
|
||||
"source_count": 2,
|
||||
"first_seen": "2026-04-10"
|
||||
},
|
||||
{
|
||||
"id": "the-nexus:pitfall:001",
|
||||
"fact": "Merges fail with HTTP 405 due to branch protection",
|
||||
"category": "pitfall",
|
||||
"domain": "the-nexus",
|
||||
"confidence": 0.95,
|
||||
"tags": [
|
||||
"git",
|
||||
"merge",
|
||||
"branch-protection",
|
||||
"gitea"
|
||||
],
|
||||
"source_count": 12,
|
||||
"first_seen": "2026-04-05",
|
||||
"last_confirmed": "2026-04-13",
|
||||
"related": [
|
||||
"global:pitfall:001"
|
||||
]
|
||||
},
|
||||
{
|
||||
"id": "the-nexus:pitfall:002",
|
||||
"fact": "ThreadingHTTPServer required for multi-user bridge - standard HTTPServer blocks on concurrent requests",
|
||||
"category": "pitfall",
|
||||
"domain": "the-nexus",
|
||||
"confidence": 0.95,
|
||||
"tags": [
|
||||
"server",
|
||||
"concurrency",
|
||||
"bridge"
|
||||
],
|
||||
"source_count": 5,
|
||||
"first_seen": "2026-04-10",
|
||||
"last_confirmed": "2026-04-13"
|
||||
},
|
||||
{
|
||||
"id": "the-nexus:pitfall:003",
|
||||
"fact": "ChatLog.log() crashes on message persistence when index.html has orphaned button tags",
|
||||
"category": "pitfall",
|
||||
"domain": "the-nexus",
|
||||
"confidence": 0.9,
|
||||
"tags": [
|
||||
"html",
|
||||
"crash",
|
||||
"chatlog"
|
||||
],
|
||||
"source_count": 3,
|
||||
"first_seen": "2026-04-12",
|
||||
"last_confirmed": "2026-04-13"
|
||||
},
|
||||
{
|
||||
"id": "the-nexus:pitfall:004",
|
||||
"fact": "Three.js LOD not implemented - local hardware struggles with full scene",
|
||||
"category": "pitfall",
|
||||
"domain": "the-nexus",
|
||||
"confidence": 0.85,
|
||||
"tags": [
|
||||
"threejs",
|
||||
"performance",
|
||||
"lod"
|
||||
],
|
||||
"source_count": 4,
|
||||
"first_seen": "2026-04-09",
|
||||
"last_confirmed": "2026-04-13"
|
||||
},
|
||||
{
|
||||
"id": "the-nexus:pitfall:005",
|
||||
"fact": "Duplicate content blocks appear in index.html when PR merges conflict silently",
|
||||
"category": "pitfall",
|
||||
"domain": "the-nexus",
|
||||
"confidence": 0.8,
|
||||
"tags": [
|
||||
"html",
|
||||
"merge-conflict",
|
||||
"duplicate"
|
||||
],
|
||||
"source_count": 3,
|
||||
"first_seen": "2026-04-11",
|
||||
"last_confirmed": "2026-04-13"
|
||||
},
|
||||
{
|
||||
"id": "the-nexus:pitfall:006",
|
||||
"fact": "Unified HTTP + WebSocket server required for proper URL deployment - separate servers break CORS",
|
||||
"category": "pitfall",
|
||||
"domain": "the-nexus",
|
||||
"confidence": 0.9,
|
||||
"tags": [
|
||||
"deploy",
|
||||
"websocket",
|
||||
"http",
|
||||
"cors"
|
||||
],
|
||||
"source_count": 4,
|
||||
"first_seen": "2026-04-10",
|
||||
"last_confirmed": "2026-04-13"
|
||||
},
|
||||
{
|
||||
"id": "global:tool-quirk:001",
|
||||
"fact": "Gitea token stored at ~/.config/gitea/token, not env var GITEA_TOKEN",
|
||||
"category": "tool-quirk",
|
||||
"domain": "global",
|
||||
"confidence": 0.95,
|
||||
"tags": [
|
||||
"git",
|
||||
"auth",
|
||||
"gitea",
|
||||
"token"
|
||||
],
|
||||
"source_count": 23,
|
||||
"first_seen": "2026-03-27",
|
||||
"last_confirmed": "2026-04-13",
|
||||
"related": [
|
||||
"global:pitfall:001"
|
||||
]
|
||||
},
|
||||
{
|
||||
"id": "global:tool-quirk:002",
|
||||
"fact": "Gitea API uses 'Authorization: token TOKEN' header format, not Bearer",
|
||||
"category": "tool-quirk",
|
||||
"domain": "global",
|
||||
"confidence": 0.9,
|
||||
"tags": [
|
||||
"git",
|
||||
"api",
|
||||
"gitea"
|
||||
],
|
||||
"source_count": 8,
|
||||
"first_seen": "2026-03-28",
|
||||
"last_confirmed": "2026-04-12"
|
||||
},
|
||||
{
|
||||
"id": "global:tool-quirk:003",
|
||||
"fact": "Gitea Issues API type=issues param does NOT filter PRs",
|
||||
"category": "tool-quirk",
|
||||
"domain": "global",
|
||||
"confidence": 0.95,
|
||||
"tags": [
|
||||
"gitea",
|
||||
"api",
|
||||
"issues",
|
||||
"pr"
|
||||
],
|
||||
"source_count": 6,
|
||||
"first_seen": "2026-04-01",
|
||||
"last_confirmed": "2026-04-13"
|
||||
},
|
||||
{
|
||||
"id": "global:tool-quirk:004",
|
||||
"fact": "~/.hermes is the default hermes home - check get_hermes_home() not the path literal",
|
||||
"category": "tool-quirk",
|
||||
"domain": "global",
|
||||
"confidence": 0.9,
|
||||
"tags": [
|
||||
"paths",
|
||||
"hermes",
|
||||
"env"
|
||||
],
|
||||
"source_count": 10,
|
||||
"first_seen": "2026-03-30",
|
||||
"last_confirmed": "2026-04-13",
|
||||
"related": [
|
||||
"hermes-agent:pitfall:005"
|
||||
]
|
||||
},
|
||||
{
|
||||
"id": "global:tool-quirk:005",
|
||||
"fact": "Ansible vault-encrypted vars in YAML require vault_inline_vars plugin",
|
||||
"category": "tool-quirk",
|
||||
"domain": "global",
|
||||
"confidence": 0.85,
|
||||
"tags": [
|
||||
"ansible",
|
||||
"vault",
|
||||
"config"
|
||||
],
|
||||
"source_count": 3,
|
||||
"first_seen": "2026-04-02"
|
||||
},
|
||||
{
|
||||
"id": "global:tool-quirk:006",
|
||||
"fact": "mimo-v2-pro via Nous Research is the default model - don't assume Anthropic is available",
|
||||
"category": "tool-quirk",
|
||||
"domain": "global",
|
||||
"confidence": 0.95,
|
||||
"tags": [
|
||||
"model",
|
||||
"provider",
|
||||
"nous",
|
||||
"default"
|
||||
],
|
||||
"source_count": 15,
|
||||
"first_seen": "2026-03-25",
|
||||
"last_confirmed": "2026-04-13"
|
||||
},
|
||||
{
|
||||
"id": "global:tool-quirk:007",
|
||||
"fact": "Kill + restart with 'hermes chat' preserves old model state - NEVER use --resume",
|
||||
"category": "tool-quirk",
|
||||
"domain": "global",
|
||||
"confidence": 0.95,
|
||||
"tags": [
|
||||
"hermes",
|
||||
"model",
|
||||
"restart",
|
||||
"session"
|
||||
],
|
||||
"source_count": 8,
|
||||
"first_seen": "2026-03-29",
|
||||
"last_confirmed": "2026-04-12"
|
||||
},
|
||||
{
|
||||
"id": "global:pitfall:001",
|
||||
"fact": "Branch protection requires 1 approval on main - API merges fail with 405 without it",
|
||||
"category": "pitfall",
|
||||
"domain": "global",
|
||||
"confidence": 0.95,
|
||||
"tags": [
|
||||
"git",
|
||||
"merge",
|
||||
"branch-protection",
|
||||
"gitea"
|
||||
],
|
||||
"source_count": 12,
|
||||
"first_seen": "2026-04-05",
|
||||
"last_confirmed": "2026-04-13",
|
||||
"related": [
|
||||
"the-nexus:pitfall:001"
|
||||
]
|
||||
},
|
||||
{
|
||||
"id": "global:pitfall:002",
|
||||
"fact": "Never use --no-verify on git commits",
|
||||
"category": "pitfall",
|
||||
"domain": "global",
|
||||
"confidence": 0.95,
|
||||
"tags": [
|
||||
"git",
|
||||
"hooks",
|
||||
"safety"
|
||||
],
|
||||
"source_count": 5,
|
||||
"first_seen": "2026-03-28",
|
||||
"last_confirmed": "2026-04-13"
|
||||
},
|
||||
{
|
||||
"id": "global:pitfall:003",
|
||||
"fact": "Gitea PR creation workaround needed on the-nexus - direct API call fails",
|
||||
"category": "pitfall",
|
||||
"domain": "global",
|
||||
"confidence": 0.9,
|
||||
"tags": [
|
||||
"gitea",
|
||||
"pr",
|
||||
"api",
|
||||
"workaround"
|
||||
],
|
||||
"source_count": 4,
|
||||
"first_seen": "2026-04-06",
|
||||
"last_confirmed": "2026-04-12"
|
||||
},
|
||||
{
|
||||
"id": "global:pitfall:004",
|
||||
"fact": "Anthropic is BANNED from fallback chain",
|
||||
"category": "pitfall",
|
||||
"domain": "global",
|
||||
"confidence": 0.95,
|
||||
"tags": [
|
||||
"provider",
|
||||
"anthropic",
|
||||
"fallback"
|
||||
],
|
||||
"source_count": 7,
|
||||
"first_seen": "2026-03-30",
|
||||
"last_confirmed": "2026-04-13"
|
||||
},
|
||||
{
|
||||
"id": "global:pitfall:005",
|
||||
"fact": "Telegram tokens expired - don't assume Telegram notifications work",
|
||||
"category": "pitfall",
|
||||
"domain": "global",
|
||||
"confidence": 0.85,
|
||||
"tags": [
|
||||
"telegram",
|
||||
"notifications",
|
||||
"token"
|
||||
],
|
||||
"source_count": 3,
|
||||
"first_seen": "2026-04-02"
|
||||
},
|
||||
{
|
||||
"id": "global:pitfall:006",
|
||||
"fact": "Multiple gateways = 'cannot schedule futures' error - only one gateway process should run",
|
||||
"category": "pitfall",
|
||||
"domain": "global",
|
||||
"confidence": 0.9,
|
||||
"tags": [
|
||||
"gateway",
|
||||
"cron",
|
||||
"process"
|
||||
],
|
||||
"source_count": 4,
|
||||
"first_seen": "2026-04-04",
|
||||
"last_confirmed": "2026-04-11"
|
||||
},
|
||||
{
|
||||
"id": "global:pitfall:007",
|
||||
"fact": "pytest root collection picks up operational *_test.py scripts - restrict to tests/ directory",
|
||||
"category": "pitfall",
|
||||
"domain": "global",
|
||||
"confidence": 0.9,
|
||||
"tags": [
|
||||
"pytest",
|
||||
"test",
|
||||
"collection"
|
||||
],
|
||||
"source_count": 3,
|
||||
"first_seen": "2026-04-07",
|
||||
"last_confirmed": "2026-04-13"
|
||||
},
|
||||
{
|
||||
"id": "global:pitfall:008",
|
||||
"fact": "TDD: test 1 before building 55",
|
||||
"category": "pitfall",
|
||||
"domain": "global",
|
||||
"confidence": 0.95,
|
||||
"tags": [
|
||||
"tdd",
|
||||
"testing",
|
||||
"methodology"
|
||||
],
|
||||
"source_count": 8,
|
||||
"first_seen": "2026-03-25",
|
||||
"last_confirmed": "2026-04-13"
|
||||
}
|
||||
]
|
||||
}
|
||||
80
knowledge/repos/hermes-agent.yaml
Normal file
80
knowledge/repos/hermes-agent.yaml
Normal file
@@ -0,0 +1,80 @@
|
||||
---
|
||||
domain: hermes-agent
|
||||
category: pitfall
|
||||
version: 1
|
||||
last_updated: "2026-04-13"
|
||||
---
|
||||
|
||||
# Pitfalls (hermes-agent)
|
||||
|
||||
## Cron & Deployment
|
||||
|
||||
- id: hermes-agent:pitfall:001
|
||||
fact: "deploy-crons.py leaves jobs in mixed model format - some have provider/model, some just model"
|
||||
confidence: 0.95
|
||||
tags: [cron, deploy, model, config]
|
||||
source_count: 5
|
||||
first_seen: "2026-04-08"
|
||||
last_confirmed: "2026-04-13"
|
||||
related: [hermes-agent:pitfall:002, hermes-agent:pitfall:003]
|
||||
|
||||
- id: hermes-agent:pitfall:002
|
||||
fact: "deploy-crons.py --deploy doesn't set legacy skill field from skills list"
|
||||
confidence: 0.9
|
||||
tags: [cron, deploy, skills]
|
||||
source_count: 3
|
||||
first_seen: "2026-04-09"
|
||||
last_confirmed: "2026-04-13"
|
||||
related: [hermes-agent:pitfall:001]
|
||||
|
||||
- id: hermes-agent:pitfall:003
|
||||
fact: "Cron jobs with blank fallback_model fields trigger spurious gateway warnings"
|
||||
confidence: 0.9
|
||||
tags: [cron, model, fallback]
|
||||
source_count: 4
|
||||
first_seen: "2026-04-07"
|
||||
last_confirmed: "2026-04-12"
|
||||
related: [hermes-agent:pitfall:001]
|
||||
|
||||
- id: hermes-agent:pitfall:004
|
||||
fact: "model-watchdog.py checks first provider line, not model.provider - causes false drift alarms"
|
||||
confidence: 0.9
|
||||
tags: [watchdog, model, config]
|
||||
source_count: 3
|
||||
first_seen: "2026-04-08"
|
||||
last_confirmed: "2026-04-13"
|
||||
|
||||
## Path & Environment
|
||||
|
||||
- id: hermes-agent:pitfall:005
|
||||
fact: "10+ files read HERMES_HOME directly instead of get_hermes_home() - breaks on custom paths"
|
||||
confidence: 0.85
|
||||
tags: [paths, env, hermes-home]
|
||||
source_count: 6
|
||||
first_seen: "2026-04-06"
|
||||
last_confirmed: "2026-04-12"
|
||||
related: [global:pitfall:002]
|
||||
|
||||
- id: hermes-agent:pitfall:006
|
||||
fact: "get_hermes_home() doesn't expand tilde when HERMES_HOME=~/... is set"
|
||||
confidence: 0.8
|
||||
tags: [paths, env, bug]
|
||||
source_count: 2
|
||||
first_seen: "2026-04-05"
|
||||
|
||||
## SSH & Dispatch
|
||||
|
||||
- id: hermes-agent:pitfall:007
|
||||
fact: "vps-agent-dispatch reports OK while remote hermes binary path is broken"
|
||||
confidence: 0.9
|
||||
tags: [ssh, dispatch, vps]
|
||||
source_count: 4
|
||||
first_seen: "2026-04-07"
|
||||
last_confirmed: "2026-04-11"
|
||||
|
||||
- id: hermes-agent:pitfall:008
|
||||
fact: "nightwatch-health-monitor SSH check fails on cloud-model-only deployments"
|
||||
confidence: 0.85
|
||||
tags: [ssh, health, cloud]
|
||||
source_count: 2
|
||||
first_seen: "2026-04-10"
|
||||
63
knowledge/repos/the-nexus.yaml
Normal file
63
knowledge/repos/the-nexus.yaml
Normal file
@@ -0,0 +1,63 @@
|
||||
---
|
||||
domain: the-nexus
|
||||
category: pitfall
|
||||
version: 1
|
||||
last_updated: "2026-04-13"
|
||||
---
|
||||
|
||||
# Pitfalls (the-nexus)
|
||||
|
||||
## Git & Merging
|
||||
|
||||
- id: the-nexus:pitfall:001
|
||||
fact: "Merges fail with HTTP 405 due to branch protection - must use merge API with 1 approval"
|
||||
confidence: 0.95
|
||||
tags: [git, merge, branch-protection, gitea]
|
||||
source_count: 12
|
||||
first_seen: "2026-04-05"
|
||||
last_confirmed: "2026-04-13"
|
||||
related: [global:pitfall:001]
|
||||
|
||||
- id: the-nexus:pitfall:002
|
||||
fact: "ThreadingHTTPServer required for multi-user bridge - standard HTTPServer blocks on concurrent requests"
|
||||
confidence: 0.95
|
||||
tags: [server, concurrency, bridge]
|
||||
source_count: 5
|
||||
first_seen: "2026-04-10"
|
||||
last_confirmed: "2026-04-13"
|
||||
|
||||
- id: the-nexus:pitfall:003
|
||||
fact: "ChatLog.log() crashes on message persistence when index.html has orphaned button tags"
|
||||
confidence: 0.9
|
||||
tags: [html, crash, chatlog]
|
||||
source_count: 3
|
||||
first_seen: "2026-04-12"
|
||||
last_confirmed: "2026-04-13"
|
||||
|
||||
## Three.js & Performance
|
||||
|
||||
- id: the-nexus:pitfall:004
|
||||
fact: "Three.js LOD not implemented - local hardware struggles with full scene without texture optimization"
|
||||
confidence: 0.85
|
||||
tags: [threejs, performance, lod]
|
||||
source_count: 4
|
||||
first_seen: "2026-04-09"
|
||||
last_confirmed: "2026-04-13"
|
||||
|
||||
- id: the-nexus:pitfall:005
|
||||
fact: "Duplicate content blocks appear in index.html when PR merges conflict silently"
|
||||
confidence: 0.8
|
||||
tags: [html, merge-conflict, duplicate]
|
||||
source_count: 3
|
||||
first_seen: "2026-04-11"
|
||||
last_confirmed: "2026-04-13"
|
||||
|
||||
## Deployment
|
||||
|
||||
- id: the-nexus:pitfall:006
|
||||
fact: "Unified HTTP + WebSocket server required for proper URL deployment - separate servers break CORS"
|
||||
confidence: 0.9
|
||||
tags: [deploy, websocket, http, cors]
|
||||
source_count: 4
|
||||
first_seen: "2026-04-10"
|
||||
last_confirmed: "2026-04-13"
|
||||
@@ -1,249 +0,0 @@
|
||||
#!/usr/bin/env python3
|
||||
"""
|
||||
Cross-Repo Dependency Graph Builder
|
||||
|
||||
Scans repos for import/require/reference patterns and builds a directed
|
||||
dependency graph. Detects circular dependencies. Outputs DOT and Mermaid.
|
||||
|
||||
Usage:
|
||||
python3 scripts/dependency_graph.py /path/to/repos/
|
||||
python3 scripts/dependency_graph.py --repos repo1,repo2,repo3 --format mermaid
|
||||
python3 scripts/dependency_graph.py --repos-dir /path/to/ --format dot --output deps.dot
|
||||
|
||||
Patterns detected:
|
||||
- Python: import X, from X import Y
|
||||
- JavaScript: require("X"), import ... from "X"
|
||||
- Go: import "X"
|
||||
- Ansible: include_role, import_role
|
||||
- Docker/Compose: image: X, depends_on
|
||||
- Config references: repo-name in YAML/TOML/JSON
|
||||
"""
|
||||
|
||||
import argparse
|
||||
import json
|
||||
import os
|
||||
import re
|
||||
import sys
|
||||
from collections import defaultdict
|
||||
from pathlib import Path
|
||||
|
||||
|
||||
# Known repo names for matching
|
||||
KNOWN_REPOS = [
|
||||
"hermes-agent", "timmy-config", "timmy-home", "the-nexus", "the-door",
|
||||
"the-beacon", "fleet-ops", "burn-fleet", "timmy-dispatch", "turboquant",
|
||||
"compounding-intelligence", "the-playground", "second-son-of-timmy",
|
||||
"ai-safety-review", "the-echo-pattern", "timmy-academy", "wolf",
|
||||
"the-testament",
|
||||
]
|
||||
|
||||
|
||||
def normalize_repo_name(name: str) -> str:
|
||||
"""Normalize a repo name for comparison."""
|
||||
return name.lower().replace("_", "-").replace(".git", "").strip()
|
||||
|
||||
|
||||
def scan_file_for_deps(filepath: str, content: str, own_repo: str) -> set:
|
||||
"""Scan a file's content for references to other repos."""
|
||||
deps = set()
|
||||
own_norm = normalize_repo_name(own_repo)
|
||||
|
||||
for repo in KNOWN_REPOS:
|
||||
repo_norm = normalize_repo_name(repo)
|
||||
if repo_norm == own_norm:
|
||||
continue
|
||||
|
||||
# Direct name references
|
||||
patterns = [
|
||||
repo, # exact name
|
||||
repo.replace("-", "_"), # underscore variant
|
||||
repo.replace("-", ""), # no separator
|
||||
f"/{repo}/", # path reference
|
||||
f'"{repo}"', # quoted
|
||||
f"'{repo}'", # single quoted
|
||||
f"Timmy_Foundation/{repo}", # full Gitea path
|
||||
f"Timmy_Foundation.{repo}", # Python module path
|
||||
]
|
||||
|
||||
for pattern in patterns:
|
||||
if pattern in content:
|
||||
deps.add(repo)
|
||||
break
|
||||
|
||||
return deps
|
||||
|
||||
|
||||
def scan_repo(repo_path: str, repo_name: str = None) -> dict:
|
||||
"""Scan a repo directory for dependencies."""
|
||||
path = Path(repo_path)
|
||||
if not path.is_dir():
|
||||
return {"error": f"Not a directory: {repo_path}"}
|
||||
|
||||
if not repo_name:
|
||||
repo_name = path.name
|
||||
|
||||
deps = set()
|
||||
files_scanned = 0
|
||||
exts = {".py", ".js", ".ts", ".go", ".yaml", ".yml", ".toml", ".json",
|
||||
".md", ".sh", ".bash", ".Dockerfile", ".tf", ".hcl"}
|
||||
|
||||
for fpath in path.rglob("*"):
|
||||
if not fpath.is_file():
|
||||
continue
|
||||
if fpath.suffix not in exts:
|
||||
continue
|
||||
# Skip common non-source dirs
|
||||
parts = fpath.parts
|
||||
if any(p in (".git", "node_modules", "__pycache__", ".venv", "venv",
|
||||
"vendor", "dist", "build", ".tox") for p in parts):
|
||||
continue
|
||||
|
||||
try:
|
||||
content = fpath.read_text(errors="ignore")
|
||||
except:
|
||||
continue
|
||||
|
||||
file_deps = scan_file_for_deps(str(fpath), content, repo_name)
|
||||
deps.update(file_deps)
|
||||
files_scanned += 1
|
||||
|
||||
return {
|
||||
"repo": repo_name,
|
||||
"dependencies": sorted(deps),
|
||||
"files_scanned": files_scanned,
|
||||
}
|
||||
|
||||
|
||||
def detect_cycles(graph: dict) -> list:
|
||||
"""Detect circular dependencies using DFS."""
|
||||
cycles = []
|
||||
visited = set()
|
||||
rec_stack = set()
|
||||
|
||||
def dfs(node, path):
|
||||
visited.add(node)
|
||||
rec_stack.add(node)
|
||||
|
||||
for neighbor in graph.get(node, {}).get("dependencies", []):
|
||||
if neighbor not in visited:
|
||||
result = dfs(neighbor, path + [neighbor])
|
||||
if result:
|
||||
return result
|
||||
elif neighbor in rec_stack:
|
||||
cycle_start = path.index(neighbor)
|
||||
return path[cycle_start:] + [neighbor]
|
||||
|
||||
rec_stack.remove(node)
|
||||
return None
|
||||
|
||||
for node in graph:
|
||||
if node not in visited:
|
||||
cycle = dfs(node, [node])
|
||||
if cycle:
|
||||
cycles.append(cycle)
|
||||
|
||||
return cycles
|
||||
|
||||
|
||||
def to_dot(graph: dict) -> str:
|
||||
"""Generate DOT format output."""
|
||||
lines = ["digraph dependencies {"]
|
||||
lines.append(" rankdir=LR;")
|
||||
lines.append(" node [shape=box, style=filled, fillcolor="#1a1a2e", fontcolor="#e6edf3"];")
|
||||
lines.append(" edge [color="#4a4a6a"];")
|
||||
lines.append("")
|
||||
|
||||
for repo, data in sorted(graph.items()):
|
||||
dep_count = len(data.get("dependencies", []))
|
||||
fill = "#2d1b69" if dep_count > 2 else "#16213e"
|
||||
lines.append(f' "{repo}" [fillcolor="{fill}"];')
|
||||
for dep in data.get("dependencies", []):
|
||||
lines.append(f' "{repo}" -> "{dep}";')
|
||||
|
||||
lines.append("}")
|
||||
return "\n".join(lines)
|
||||
|
||||
|
||||
def to_mermaid(graph: dict) -> str:
|
||||
"""Generate Mermaid format output."""
|
||||
lines = ["graph LR"]
|
||||
|
||||
for repo, data in sorted(graph.items()):
|
||||
for dep in data.get("dependencies", []):
|
||||
lines.append(f" {repo.replace('-','_')} --> {dep.replace('-','_')}")
|
||||
|
||||
# Add node labels
|
||||
lines.append("")
|
||||
for repo in sorted(graph.keys()):
|
||||
lines.append(f" {repo.replace('-','_')}[{repo}]")
|
||||
|
||||
return "\n".join(lines)
|
||||
|
||||
|
||||
def main():
|
||||
parser = argparse.ArgumentParser(description="Build cross-repo dependency graph")
|
||||
parser.add_argument("repos_dir", nargs="?", help="Directory containing repos")
|
||||
parser.add_argument("--repos", help="Comma-separated list of repo paths")
|
||||
parser.add_argument("--format", choices=["dot", "mermaid", "json"], default="json")
|
||||
parser.add_argument("--output", "-o", help="Output file (default: stdout)")
|
||||
parser.add_argument("--cycles-only", action="store_true", help="Only report cycles")
|
||||
args = parser.parse_args()
|
||||
|
||||
results = {}
|
||||
repo_paths = []
|
||||
|
||||
if args.repos:
|
||||
repo_paths = [p.strip() for p in args.repos.split(",")]
|
||||
elif args.repos_dir:
|
||||
base = Path(args.repos_dir)
|
||||
repo_paths = [str(p) for p in base.iterdir() if p.is_dir() and not p.name.startswith(".")]
|
||||
else:
|
||||
parser.print_help()
|
||||
sys.exit(1)
|
||||
|
||||
for rpath in repo_paths:
|
||||
name = Path(rpath).name
|
||||
print(f"Scanning {name}...", file=sys.stderr)
|
||||
result = scan_repo(rpath, name)
|
||||
if "error" not in result:
|
||||
results[name] = result
|
||||
|
||||
# Detect cycles
|
||||
cycles = detect_cycles(results)
|
||||
|
||||
if args.cycles_only:
|
||||
if cycles:
|
||||
print("CIRCULAR DEPENDENCIES DETECTED:")
|
||||
for cycle in cycles:
|
||||
print(f" {' -> '.join(cycle)}")
|
||||
sys.exit(1)
|
||||
else:
|
||||
print("No circular dependencies found.")
|
||||
sys.exit(0)
|
||||
|
||||
# Output
|
||||
output = {}
|
||||
if args.format == "dot":
|
||||
output = to_dot(results)
|
||||
elif args.format == "mermaid":
|
||||
output = to_mermaid(results)
|
||||
else:
|
||||
output = json.dumps({
|
||||
"repos": results,
|
||||
"cycles": cycles,
|
||||
"summary": {
|
||||
"total_repos": len(results),
|
||||
"total_deps": sum(len(r["dependencies"]) for r in results.values()),
|
||||
"cycles_found": len(cycles),
|
||||
}
|
||||
}, indent=2)
|
||||
|
||||
if args.output:
|
||||
Path(args.output).write_text(output)
|
||||
print(f"Written to {args.output}", file=sys.stderr)
|
||||
else:
|
||||
print(output)
|
||||
|
||||
|
||||
if __name__ == "__main__":
|
||||
main()
|
||||
@@ -1,212 +0,0 @@
|
||||
#!/usr/bin/env python3
|
||||
"""
|
||||
Comprehensive test script for knowledge extraction prompt.
|
||||
Validates prompt structure, requirements, and consistency.
|
||||
"""
|
||||
|
||||
import json
|
||||
import re
|
||||
from pathlib import Path
|
||||
|
||||
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 test_confidence_scoring():
|
||||
"""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():
|
||||
"""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():
|
||||
"""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():
|
||||
"""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__":
|
||||
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)
|
||||
38
scripts/validate_knowledge.py
Normal file
38
scripts/validate_knowledge.py
Normal file
@@ -0,0 +1,38 @@
|
||||
#!/usr/bin/env python3
|
||||
"""Validate knowledge files and index.json against the schema."""
|
||||
import json, sys
|
||||
from pathlib import Path
|
||||
|
||||
VALID_CATEGORIES = {"fact", "pitfall", "pattern", "tool-quirk", "question"}
|
||||
REQUIRED = {"id", "fact", "category", "domain", "confidence"}
|
||||
|
||||
def validate_fact(fact, src=""):
|
||||
errs = []
|
||||
for f in REQUIRED:
|
||||
if f not in fact: errs.append(f"{src}: missing '{f}'")
|
||||
if "category" in fact and fact["category"] not in VALID_CATEGORIES:
|
||||
errs.append(f"{src}: invalid category '{fact['category']}'")
|
||||
if "confidence" in fact:
|
||||
if not isinstance(fact["confidence"], (int, float)) or not (0 <= fact["confidence"] <= 1):
|
||||
errs.append(f"{src}: confidence must be 0.0-1.0")
|
||||
if "id" in fact:
|
||||
parts = fact["id"].split(":")
|
||||
if len(parts) != 3: errs.append(f"{src}: id must be domain:category:sequence")
|
||||
return errs
|
||||
|
||||
def main():
|
||||
idx = Path(__file__).parent.parent / "knowledge" / "index.json"
|
||||
if not idx.exists(): print(f"FAILED: {idx} not found"); sys.exit(1)
|
||||
data = json.load(open(idx))
|
||||
errs = []
|
||||
seen = set()
|
||||
for i, f in enumerate(data.get("facts", [])):
|
||||
errs.extend(validate_fact(f, f"[{i}]"))
|
||||
if "id" in f:
|
||||
if f["id"] in seen: errs.append(f"duplicate id '{f['id']}'")
|
||||
seen.add(f["id"])
|
||||
if errs:
|
||||
print(f"FAILED - {len(errs)} errors:"); [print(f" x {e}") for e in errs]; sys.exit(1)
|
||||
print(f"PASSED - {len(data.get('facts', []))} facts")
|
||||
|
||||
if __name__ == "__main__": main()
|
||||
@@ -1,18 +0,0 @@
|
||||
{"role": "user", "content": "Deploy the application to production"}
|
||||
{"role": "assistant", "content": "I'll deploy the application to production.", "tool_calls": [{"function": "terminal", "arguments": {"command": "ssh deploy@prod-server 'cd /app && git pull && docker-compose up -d'"}}]}
|
||||
{"role": "tool", "content": "ssh: connect to host prod-server port 22: Connection refused"}
|
||||
{"role": "assistant", "content": "Connection refused. Let me check the server status.", "tool_calls": [{"function": "terminal", "arguments": {"command": "ping -c 3 prod-server"}}]}
|
||||
{"role": "tool", "content": "PING prod-server (192.168.1.100): 56 data bytes\nRequest timeout for icmp_seq 0\nRequest timeout for icmp_seq 1\nRequest timeout for icmp_seq 2\n--- prod-server ping statistics ---\n3 packets transmitted, 0 packets received, 100.0% packet loss"}
|
||||
{"role": "assistant", "content": "The server appears to be down. Let me check if there's an alternative deployment method."}
|
||||
{"role": "user", "content": "Try using the VPS instead"}
|
||||
{"role": "assistant", "content": "I'll try deploying to the VPS.", "tool_calls": [{"function": "terminal", "arguments": {"command": "ssh deploy@vps-server 'cd /app && git pull && docker-compose up -d'"}}]}
|
||||
{"role": "tool", "content": "Permission denied (publickey)."}
|
||||
{"role": "assistant", "content": "Permission denied. The SSH key might not be set up correctly. Let me check the SSH configuration.", "tool_calls": [{"function": "terminal", "arguments": {"command": "cat ~/.ssh/config"}}]}
|
||||
{"role": "tool", "content": "Host vps-server\n HostName 167.99.126.228\n User deploy\n IdentityFile ~/.ssh/id_rsa_vps"}
|
||||
{"role": "assistant", "content": "The SSH config looks correct. Let me check if the key exists.", "tool_calls": [{"function": "terminal", "arguments": {"command": "ls -la ~/.ssh/id_rsa_vps"}}]}
|
||||
{"role": "tool", "content": "ls: /Users/user/.ssh/id_rsa_vps: No such file or directory"}
|
||||
{"role": "assistant", "content": "The SSH key doesn't exist. This is a pitfall - we need to generate the SSH key first."}
|
||||
{"role": "user", "content": "Generate a new SSH key for the VPS"}
|
||||
{"role": "assistant", "content": "I'll generate a new SSH key.", "tool_calls": [{"function": "terminal", "arguments": {"command": "ssh-keygen -t rsa -b 4096 -f ~/.ssh/id_rsa_vps -N ''"}}]}
|
||||
{"role": "tool", "content": "Generating public/private rsa key pair.\nYour identification has been saved in /Users/user/.ssh/id_rsa_vps\nYour public key has been saved in /Users/user/.ssh/id_rsa_vps.pub\nThe key fingerprint is:\nSHA256:abc123... user@machine"}
|
||||
{"role": "assistant", "content": "SSH key generated. Now I need to add it to the VPS."}
|
||||
@@ -1,14 +0,0 @@
|
||||
{"role": "user", "content": "Check the Gitea API for open issues"}
|
||||
{"role": "assistant", "content": "I'll check the Gitea API for open issues.", "tool_calls": [{"function": "terminal", "arguments": {"command": "curl -H 'Authorization: token $GITEA_TOKEN' https://forge.alexanderwhitestone.com/api/v1/repos/Timmy_Foundation/compounding-intelligence/issues?state=open"}}]}
|
||||
{"role": "tool", "content": "curl: (6) Could not resolve host: forge.alexanderwhitestone.com"}
|
||||
{"role": "assistant", "content": "DNS resolution failed. Let me check the network connectivity.", "tool_calls": [{"function": "terminal", "arguments": {"command": "nslookup forge.alexanderwhitestone.com"}}]}
|
||||
{"role": "tool", "content": "Server: 8.8.8.8\nAddress: 8.8.8.8#53\n\n** server can't find forge.alexanderwhitestone.com: NXDOMAIN"}
|
||||
{"role": "assistant", "content": "The domain doesn't resolve. This might be a DNS issue. Let me try using the IP address directly.", "tool_calls": [{"function": "terminal", "arguments": {"command": "curl -H 'Authorization: token $GITEA_TOKEN' https://167.99.126.228/api/v1/repos/Timmy_Foundation/compounding-intelligence/issues?state=open"}}]}
|
||||
{"role": "tool", "content": "curl: (60) SSL certificate problem: self signed certificate"}
|
||||
{"role": "assistant", "content": "SSL certificate issue. The server is using a self-signed certificate. Let me try with -k flag to skip SSL verification.", "tool_calls": [{"function": "terminal", "arguments": {"command": "curl -k -H 'Authorization: token $GITEA_TOKEN' https://167.99.126.228/api/v1/repos/Timmy_Foundation/compounding-intelligence/issues?state=open"}}]}
|
||||
{"role": "tool", "content": "[]"}
|
||||
{"role": "assistant", "content": "No open issues found. The API returned an empty array."}
|
||||
{"role": "user", "content": "Check if there are any pull requests"}
|
||||
{"role": "assistant", "content": "Let me check for pull requests.", "tool_calls": [{"function": "terminal", "arguments": {"command": "curl -k -H 'Authorization: token $GITEA_TOKEN' https://167.99.126.228/api/v1/repos/Timmy_Foundation/compounding-intelligence/pulls?state=open"}}]}
|
||||
{"role": "tool", "content": "[{"id": 20, "title": "feat: add harvester.py + session_reader.py — session knowledge extractor (closes #8)", "state": "open", "user": {"login": "Rockachopa"}, "created_at": "2026-04-14T17:28:20Z"}]"}
|
||||
{"role": "assistant", "content": "Found 1 open pull request: PR #20 - "feat: add harvester.py + session_reader.py — session knowledge extractor (closes #8)" by Rockachopa."}
|
||||
@@ -1,10 +0,0 @@
|
||||
{"role": "user", "content": "How do I deploy a new version of the application?"}
|
||||
{"role": "assistant", "content": "Here's the deployment process:\n1. Run tests: pytest\n2. Build Docker image: docker build -t app:latest .\n3. Push to registry: docker push registry.example.com/app:latest\n4. Update production: ssh prod 'cd /app && docker-compose pull && docker-compose up -d'\n5. Verify: curl https://app.example.com/health"}
|
||||
{"role": "user", "content": "What if tests fail?"}
|
||||
{"role": "assistant", "content": "If tests fail:\n1. Check the error logs: pytest -v\n2. Fix the failing tests\n3. Re-run tests: pytest\n4. If still failing, check recent changes: git log --oneline -10\n5. Consider reverting: git revert HEAD"}
|
||||
{"role": "user", "content": "What if the Docker build fails?"}
|
||||
{"role": "assistant", "content": "If Docker build fails:\n1. Check Dockerfile syntax: docker build --no-cache -t app:latest .\n2. Check for missing dependencies: cat requirements.txt\n3. Check disk space: df -h\n4. Clean up Docker: docker system prune -f\n5. Try building with verbose output: docker build --progress=plain -t app:latest ."}
|
||||
{"role": "user", "content": "What if the push to registry fails?"}
|
||||
{"role": "assistant", "content": "If push to registry fails:\n1. Check registry credentials: docker login registry.example.com\n2. Check registry space: curl https://registry.example.com/v2/_catalog\n3. Check image size: docker images app:latest\n4. Try tagging with version: docker tag app:latest registry.example.com/app:v1.0.0\n5. Push with version tag: docker push registry.example.com/app:v1.0.0"}
|
||||
{"role": "user", "content": "What if the production update fails?"}
|
||||
{"role": "assistant", "content": "If production update fails:\n1. Check SSH connection: ssh prod 'echo connected'\n2. Check disk space on prod: ssh prod 'df -h'\n3. Check Docker status: ssh prod 'docker ps -a'\n4. Check logs: ssh prod 'docker-compose logs --tail=100'\n5. Rollback: ssh prod 'cd /app && git checkout HEAD~1 && docker-compose up -d'"}
|
||||
@@ -1,12 +0,0 @@
|
||||
{"role": "user", "content": "I need to implement a new feature for the application"}
|
||||
{"role": "assistant", "content": "I can help you implement a new feature. What feature would you like to add?"}
|
||||
{"role": "user", "content": "I want to add user authentication"}
|
||||
{"role": "assistant", "content": "User authentication is a good feature. I have a few questions:\n1. What authentication method do you prefer? (JWT, OAuth, Session-based)\n2. Do you need social login? (Google, GitHub, etc.)\n3. What user data do you need to store?\n4. Do you need role-based access control?\n5. What's your database? (PostgreSQL, MySQL, SQLite)"}
|
||||
{"role": "user", "content": "I prefer JWT, no social login, just email and password, no roles, PostgreSQL"}
|
||||
{"role": "assistant", "content": "Great choices. Here's the implementation plan:\n1. Create user model with email and password hash\n2. Create JWT token generation and validation\n3. Create login endpoint: POST /api/auth/login\n4. Create register endpoint: POST /api/auth/register\n5. Create middleware for protected routes\n6. Add password hashing with bcrypt\n7. Add rate limiting for login attempts\n8. Add password reset functionality\n9. Add email verification\n10. Test all endpoints"}
|
||||
{"role": "user", "content": "What about password reset?"}
|
||||
{"role": "assistant", "content": "For password reset:\n1. Create reset token table\n2. Create forgot password endpoint: POST /api/auth/forgot-password\n3. Send reset email with token\n4. Create reset password endpoint: POST /api/auth/reset-password\n5. Validate reset token and expiration\n6. Update password and delete token\n7. Send confirmation email"}
|
||||
{"role": "user", "content": "What about email verification?"}
|
||||
{"role": "assistant", "content": "For email verification:\n1. Add email_verified field to user model\n2. Create verification token table\n3. Send verification email on registration\n4. Create verify email endpoint: GET /api/auth/verify-email?token=...\n5. Validate token and update email_verified\n6. Add middleware to check email_verified for certain routes\n7. Add resend verification email endpoint"}
|
||||
{"role": "user", "content": "What about rate limiting?"}
|
||||
{"role": "assistant", "content": "For rate limiting:\n1. Use Redis for rate limit storage\n2. Create rate limit middleware\n3. Set limits: 5 login attempts per minute, 3 password resets per hour\n4. Return 429 Too Many Requests when limit exceeded\n5. Add X-RateLimit headers to responses\n6. Log rate limit violations\n7. Add whitelist for trusted IPs"}
|
||||
@@ -1,13 +0,0 @@
|
||||
{"role": "user", "content": "Clone the repo at forge.alexanderwhitestone.com/Timmy_Foundation/compounding-intelligence"}
|
||||
{"role": "assistant", "content": "I'll clone the repository for you.", "tool_calls": [{"function": "terminal", "arguments": {"command": "git clone https://forge.alexanderwhitestone.com/Timmy_Foundation/compounding-intelligence.git"}}]}
|
||||
{"role": "tool", "content": "Cloning into 'compounding-intelligence'...\nremote: Enumerating objects: 15, done.\nremote: Counting objects: 100% (15/15), done.\nremote: Compressing objects: 100% (12/12), done.\nremote: Total 15 (delta 2), reused 0 (delta 0), pack-reused 0\nReceiving objects: 100% (15/15), done.\nResolving deltas: 100% (2/2), done."}
|
||||
{"role": "assistant", "content": "Repository cloned successfully. Let me check the structure.", "tool_calls": [{"function": "terminal", "arguments": {"command": "ls -la compounding-intelligence/"}}]}
|
||||
{"role": "tool", "content": "total 8\ndrwxr-xr-x 5 user staff 160 Apr 14 17:21 .\ndrwxr-xr-x 12 user staff 384 Apr 14 17:21 ..\ndrwxr-xr-x 13 user staff 416 Apr 14 17:21 .git\n-rw-r--r-- 1 user staff 1234 Apr 14 17:21 README.md\ndrwxr-xr-x 3 user staff 96 Apr 14 17:21 knowledge\n-rw-r--r-- 1 user staff 456 Apr 14 17:21 metrics\ndrwxr-xr-x 4 user staff 128 Apr 14 17:21 scripts\ndrwxr-xr-x 3 user staff 96 Apr 14 17:21 templates"}
|
||||
{"role": "user", "content": "What files are in the templates directory?"}
|
||||
{"role": "assistant", "content": "Let me check the templates directory.", "tool_calls": [{"function": "terminal", "arguments": {"command": "ls -la compounding-intelligence/templates/"}}]}
|
||||
{"role": "tool", "content": "total 0\ndrwxr-xr-x 3 user staff 96 Apr 14 17:21 .\ndrwxr-xr-x 5 user staff 160 Apr 14 17:21 ..\n-rw-r--r-- 1 user staff 0 Apr 14 17:21 .gitkeep"}
|
||||
{"role": "assistant", "content": "The templates directory currently only contains a .gitkeep file. No templates have been added yet."}
|
||||
{"role": "user", "content": "Create a harvest-prompt.md template in the templates directory."}
|
||||
{"role": "assistant", "content": "I'll create the harvest-prompt.md template for you.", "tool_calls": [{"function": "terminal", "arguments": {"command": "cat > compounding-intelligence/templates/harvest-prompt.md << 'EOF'\n# Knowledge Extraction Prompt\n\nExtract knowledge from session transcripts.\nEOF"}}]}
|
||||
{"role": "tool", "content": ""}
|
||||
{"role": "assistant", "content": "Template created successfully. The harvest-prompt.md file is now in the templates directory."}
|
||||
Reference in New Issue
Block a user