Fresh start - excluded large ROM JSON files

2026-04-11 09:45:12 -05:00
commit 5deb387aa6
395 changed files with 47744 additions and 0 deletions
--- a/memory/projects/coding-workflow.md
+++ b/memory/projects/coding-workflow.md
@@ -0,0 +1,25 @@
+# Coding Setup & Workflow
+
+## Environment
+- **Primary Channel:** Discord #coding (1468627455656067074)
+- **Repo:** whoisfrost/controls-web
+- **Model:** kimi-k2.5:cloud (switched from deepseek-v3.2 for less token bloat)
+
+## Git Workflow
+- **main:** Stable/production branch
+- **dev:** Testing/playground branch
+- **Feature branches:** Create → merge to dev → merge dev to main
+- **Process:** Work PC pushes to dev → Dev server pulls dev → Live server pulls main
+
+## LAMP Stack
+- **Dashboard:** `C:\web\htdocs\dashboard` (active)
+- **Web Root:** `C:\web\htdocs\`
+- **Old Dashboard:** `/var/www/html/dashboardv2/` (ignore)
+
+## Tools
+- Shell: Bash
+- SSH, curl, jq
+
+---
+
+*Trigger words: coding, git, repo, workflow, lamp, dashboard, controls-web*
--- a/memory/projects/discord-reminder-system.md
+++ b/memory/projects/discord-reminder-system.md
@@ -0,0 +1,59 @@
+# Discord Reminder System
+
+**Status:** ✅ Live  
+**Channel:** #schedule (1474636036905631867)  
+**Created:** 2026-02-25  
+**Files:**
+- `tools/reminder-manager.py` - Core Python logic
+- `tools/reminder-handler.ps1` - PowerShell wrapper
+- `skills/discord-reminder/SKILL.md` - Documentation
+- `data/reminders.db` - SQLite database
+
+## How It Works
+
+1. User says: `remind me 20m Call John`
+2. I parse natural language time (20m, 2h, tomorrow 9am, etc.)
+3. Create OpenClaw cron job for exact time
+4. At trigger time, cron fires → sends Discord message
+5. One-shot jobs auto-delete after firing
+
+## Supported Time Formats
+
+| Format | Example |
+|--------|---------|
+| Minutes | `20m`, `5m` |
+| Hours | `2h`, `1h30m` |
+| Today time | `9am`, `2:30pm`, `15:00` |
+| Tomorrow | `tomorrow`, `tomorrow 9am` |
+
+## Commands
+
+- `remind me [time] [message]` - Add reminder
+- `list reminders` - Show active reminders
+- `cancel reminder #[id]` - Cancel by ID
+
+## Technical Details
+
+- **Backend:** OpenClaw cron + SQLite
+- **Delivery:** systemEvent → Discord channel
+- **Timezone:** America/Chicago (automatic DST handling)
+- **Cleanup:** Old reminders auto-delete via Daily Cron Cleanup job
+
+## Testing History
+
+- ✅ 2026-02-25 - Basic 5m reminders working
+- ✅ 2026-02-25 - 3pm same-day reminders working
+- ✅ 2026-02-27 - Confirmed still working after 2 days
+
+## Known Quirks
+
+- Must say "remind me" — "remind 4 minutes" won't work (by design)
+- One-shot reminders don't show in `list` after firing (auto-deleted)
+- All times are America/Chicago
+
+## Future Ideas
+
+- [ ] Recurring reminders (daily, weekly)
+- [ ] Snooze functionality
+- [ ] Reminder categories/tags
+- [ ] DM reminders (vs channel-only)
--- a/memory/projects/discord-voice-bot.md
+++ b/memory/projects/discord-voice-bot.md
@@ -0,0 +1,31 @@
+# Discord Voice Bot (GLaDOS)
+
+## Overview
+Voice-controlled Discord bot with conversational AI
+
+## Location
+`/home/admin/.openclaw/workspace/discord-voice-bot/`
+
+## Architecture (v2 - 2026-02-08)
+- **TTS:** HTTP endpoint at 192.168.0.17:5050 ("glados" voice)
+- **STT:** Whisper on 192.168.0.17:10300 (Wyoming protocol)
+- **LLM:** Ollama at 192.168.0.17:11434 (qwen3-coder-next:cloud)
+- **Auto-join:** Bot auto-joins #coding voice channel on startup
+
+## Commands
+- `!join` - Join voice channel
+- `!leave` - Leave voice channel
+- `!test [text]` - Test TTS
+
+## MCP Integration
+- `list_projects()` - "What am I working on?"
+- `create_project()` - Start new project
+- `add_task()` - Add tasks via voice
+- `update_task_status()` - Mark complete
+
+## Status
+✅ **Completed** — Operational and always available in #coding voice channel
+
+---
+
+*Trigger words: voice bot, glados, discord bot, TTS, STT, wyoming, voice control*
--- a/memory/projects/home-assistant.md
+++ b/memory/projects/home-assistant.md
@@ -0,0 +1,26 @@
+# Home Assistant
+
+## Environment
+- **URL:** http://192.168.0.39:8123
+- **Auth Token:** eyJhbGciOiJIUzI1NiIsInR5cCI6IkpXVCJ9.eyJpc3MiOiI0ZTcyMGRjZDkzODg0ZTFiOTE5YzkyMDVkZmNlMTY5NSIsImlhdCI6MTc3MzI1NTM5MiwiZXhwIjoyMDg4NjE1MzkyfQ.t7QYwdOP7w2s0tilu9A4zh5saezNRhveuXEJdz4ILKM
+- **MQTT Broker:** 192.168.0.39:1883 (corey/41945549)
+- **Status:** In Progress (entity cleanup ongoing)
+
+## Room-Assistant (Bluetooth Presence)
+- **Host:** 192.168.0.95 (livingroom-pi)
+- **SSH Key:** ~/.ssh/id_ed25519 (ed25519)
+- **Config:** `/home/admin/config/local.yml`
+- **Phone MAC:** b0:c2:c7:07:28:b5
+- **Entities:** sensor.livingroom_cluster_size, sensor.livingroom_cluster_leader
+- **Note:** mdns module needed for cluster discovery (not critical)
+
+## Channel
+Discord #home-assistant (1466074219829006599)
+
+## Current Tasks
+- [ ] Entity cleanup (972 devices in spreadsheet)
+- [ ] Fix hallway sensor battery (1%)
+
+---
+
+*Trigger words: home assistant, HA, mqtt, room-assistant, presence, sensor*
--- a/memory/projects/memory-system.md
+++ b/memory/projects/memory-system.md
@@ -0,0 +1,38 @@
+# Memory System
+
+## Architecture
+Hybrid system: File-based (human-readable) + SQLite (structured)
+
+## Components
+
+### File-Based Memory
+- **Daily Notes:** `memory/YYYY-MM-DD.md`
+- **Curated Memory:** `MEMORY.md` (index + always-load info)
+- **Workspace Context:** `workspace-context.md` (temp state)
+
+### SQLite Database
+- **Location:** `~/.openclaw/memory.db`
+- **Tables:** memory_cells, scenes, memory_fts
+- **Extraction:** Memory Worker agent (3 AM daily)
+
+### Cloud Backup
+- **Service:** Supermemory.ai
+- **Schedule:** Daily 2 AM
+- **Script:** `scripts/backup-memory.py`
+
+## Workers
+- **Memory Worker:** Extracts structured data daily at 3 AM
+- **Job Verifier:** Checks all overnight jobs at 9 AM
+
+## Status
+✅ **Complete** — Hierarchical restructure finished (Feb 25, 2026)
+- Daily notes automation working
+- MEMORY.md as curated index
+- SQLite database with FTS
+- Supermemory backups daily
+- Memory worker extracting nightly
+- Obsidian integration with Dataview
+
+---
+
+*Trigger words: memory, database, sqlite, supermemory, backup, extraction*
--- a/memory/projects/memory-vector-system.md
+++ b/memory/projects/memory-vector-system.md
@@ -0,0 +1,240 @@
+# Memory Vector System
+
+**Status:** ✅ Supermonkey-Powered  
+**Created:** 2026-03-02  
+**Replaces:** Supermemory cloud embedding API
+
+---
+
+## Overview
+
+Local semantic memory search using SQLite + Ollama embeddings. No cloud dependency, no API limits, works offline.
+
+## Architecture
+
+### File-Based Pipeline
+```
+Memory Files (markdown)
+    ↓
+memory_embedding_worker.py
+    ↓
+Ollama (nomic-embed-text) → 768-dim vectors
+    ↓
+SQLite + sqlite-vector extension
+    ↓
+Cosine similarity search
+```
+
+### Real-Time Session Pipeline (NEW)
+```
+Discord/Chat Messages
+    ↓
+OpenClaw Session Transcript (.jsonl)
+    ↓
+session_monitor.py (cron every 2 min)
+    ↓
+Count messages → At 15: summarize
+    ↓
+Ollama (nomic-embed-text)
+    ↓
+SQLite + sqlite-vector
+```
+
+**Innovation:** We read OpenClaw's own session transcripts to auto-capture conversations without manual tracking!
+
+## Components
+
+### Core Module
+**File:** `memory_vector.py`
+- `MemoryVectorDB` class — database wrapper
+- `store_memory()` — save embedding
+- `search_memories()` — semantic search
+- `setup_memory_vectors()` — one-time init
+
+### Worker Scripts
+**File:** `tools/memory_embedding_worker.py`
+- Daily/batch processing for memory.md files
+- Processes section-by-section
+- Called by cron at 3 AM
+
+**File:** `tools/session_monitor.py` ⭐ NEW
+- Reads OpenClaw session transcripts live
+- Tracks message counts automatically
+- Creates snapshots every 15 messages
+- Cron: every 2 minutes
+- Database: `session_tracking` table
+
+**File:** `tools/session_snapshotter.py`
+- Manual session capture (legacy)
+- Use session_monitor.py for auto-tracking
+
+**File:** `tools/search_memories.py`
+- CLI tool for manual searches
+- Interactive or one-shot mode
+
+**File:** `tools/bulk_memory_loader.py`
+- One-time historical import
+- Processed 1,186 embeddings on first run
+
+**File:** `scripts/memory-embeddings-cron.ps1`
+- PowerShell wrapper for daily cron
+- Checks Ollama availability
+
+## Database Schema
+
+### memory_embeddings
+| Column | Type | Description |
+|--------|------|-------------|
+| id | INTEGER | Primary key |
+| source_type | TEXT | "daily", "memory_md", "project", "session_snapshot", "auto_session" |
+| source_path | TEXT | File path + section or timestamp |
+| content_text | TEXT | First 500 chars (searchable preview) |
+| embedding | BLOB | 768-dim Float32 vector (3,072 bytes) |
+| created_at | TIMESTAMP | Auto-set |
+
+### session_tracking ⭐ NEW
+| Column | Type | Description |
+|--------|------|-------------|
+| session_id | TEXT | OpenClaw session UUID |
+| channel_key | TEXT | discord:channel_id |
+| transcript_path | TEXT | Path to .jsonl file |
+| last_message_index | INTEGER | Last processed line |
+| messages_since_snapshot | INTEGER | Counter since last embed |
+| last_checkpoint_time | TIMESTAMP | Last check |
+| is_active | BOOLEAN | Session still exists? |
+
+## Cron Schedule
+
+| Job | Schedule | What It Does |
+|-----|----------|--------------|
+| **Memory Embeddings Daily** | 3:00 AM | Process yesterday's memory file |
+| **Session Monitor** ⭐ NEW | Every 2 min | Reads transcripts, auto-snapshots at 15 msgs |
+| Session Snapshots (legacy) | Manual | Manual capture via script |
+
+**How Session Monitor Works:**
+1. Reads `.openclaw/agents/main/sessions/*.jsonl`
+2. Tracks `last_message_index` per session
+3. Counts new user messages
+4. At 15 messages: summarize → embed → store
+5. Updates checkpoint in `session_tracking` table
+
+## Usage
+
+### Search
+```powershell
+# Search by query
+python tools/search_memories.py "home assistant automation"
+
+# Interactive mode
+python tools/search_memories.py --interactive
+```
+
+### Manual Snapshot
+```powershell
+python tools/session_snapshotter.py "Summary of important discussion"
+```
+
+### From Python
+```python
+from memory_vector import search_memories
+
+# Generate query embedding with Ollama
+# Then search
+results = search_memories(query_embedding, k=5)
+# Returns: [(source_path, content_text, distance), ...]
+```
+
+## Stats
+
+| Metric | Value |
+|--------|-------|
+| Total embeddings | **1,623** |
+| Daily notes | 818 |
+| Project files | 332 |
+| MEMORY.md | 33 |
+| Manual session snapshots | 2 |
+| **Auto session snapshots** ⭐ | **27** |
+| Tracked sessions | 245 |
+| Active sessions | 243 |
+| Database size | ~5 MB |
+
+**Live Stats Query:**
+```powershell
+python -c "import sqlite3; db=sqlite3.connect(r'C:\Users\admin\.openclaw\memory.db'); c=db.cursor(); c.execute('SELECT COUNT(*) FROM memory_embeddings'); print('Total:', c.fetchone()[0]); c.execute('SELECT COUNT(*) FROM memory_embeddings WHERE source_type=\'auto_session\''); print('Auto snapshots:', c.fetchone()[0]); c.execute('SELECT COUNT(*) FROM session_tracking WHERE is_active=1'); print('Active sessions:', c.fetchone()[0]); db.close()"
+```
+
+**Check Session Monitor Status:**
+```powershell
+# See last run
+python tools/session_monitor.py
+
+# Check if cron is running
+openclaw cron list | findstr "Session Monitor"
+```
+
+## The Innovation ⭐
+
+**Problem:** How to automatically capture live conversations without manual tracking?
+
+**Solution:** Read OpenClaw's own session transcripts!
+
+OpenClaw stores every session in `.openclaw/agents/main/sessions/[session-id].jsonl`. We discovered we can:
+
+1. **Monitor these files live** — cron job every 2 minutes
+2. **Track line position** — `last_message_index` checkpoint
+3. **Count user messages** — parse JSONL for `role: "user"`
+4. **Auto-snapshot at threshold** — 15 messages → summarize → embed
+
+**Why this matters:**
+- ✅ No manual message counting
+- ✅ Survives session restarts
+- ✅ Multi-channel aware (each channel = separate session file)
+- ✅ No OpenClaw hooks required (we read their existing data)
+
+**Credit:** Corey's genius idea 💡 *(Corey, 2026-03-03)*
+
+---
+
+## Comparison: Old vs New
+
+| Feature | Supermemory | SQLite-Vector |
+|---------|-------------|---------------|
+| Cloud dependency | Required | None |
+| API limits | Yes | No |
+| Offline use | No | Yes |
+| Embeddings stored | Cloud | Local |
+| Search speed | Network latency | <100ms local |
+| Reliability | Crashing | Stable |
+| Cost | API-based | Free |
+
+## Troubleshooting
+
+### Ollama not running
+```powershell
+# Check status
+Invoke-RestMethod -Uri "http://localhost:11434/api/tags"
+
+# Start Ollama
+ollama serve
+```
+
+### Missing model
+```powershell
+ollama pull nomic-embed-text
+```
+
+### Database locked
+Close any GUI tools (DB Browser) before running scripts.
+
+## Future Enhancements
+
+- [ ] Keyword filtering alongside vector search
+- [ ] Date range queries
+- [ ] Source type filtering (e.g., only projects)
+- [ ] Embedding quality scoring
+- [ ] Auto-summarization improvements
+
+---
+
+**Status:** Fully operational  
+**Last updated:** 2026-03-02
--- a/memory/projects/mission-control-dashboard-tlc.md
+++ b/memory/projects/mission-control-dashboard-tlc.md
@@ -0,0 +1,120 @@
+# Mission Control Dashboard — TLC Project
+
+**Status: Parked (awaiting direction decision) — Needs Consolidation & Refresh  
+**Created: 2026-02-17 (Next.js) / 2026-02-20 (Python)
+**Goal:** Combine both dashboards into one unified system
+
+---
+
+## Current State
+
+We have **TWO** Mission Control dashboards:
+
+### 1. Next.js Dashboard
+| Attribute | Value |
+|-----------|-------|
+| **Location** | `C:\web\htdocs\mission-control` |
+| **URL** | http://localhost:3000 |
+| **Tech** | Next.js 14, TypeScript, Tailwind |
+| **Status** | ✅ Running but needs updates |
+| **Features** | Project cards, Kanban boards, Status widgets, Themes |
+
+### 2. Python/Flask Dashboard
+| Attribute | Value |
+|-----------|-------|
+| **Location** | `C:\web\htdocs\mission-control-py` |
+| **URL** | http://localhost:5050 |
+| **Tech** | Python/Flask, MySQL, HA API |
+| **Status** | ✅ Running but needs updates |
+| **Features** | Admin CRUD, Weather, Gateway status, Projects |
+
+---
+
+## The Problem
+
+Two dashboards doing similar things. Need to:
+
+| Decision | Status |
+|----------|--------|
+| **Pick one as primary?** | Undecided |
+| **Merge features?** | Undecided |
+| **Start fresh?** | Option on table |
+
+---
+
+## Features to Preserve (From Both)
+
+### From Next.js Version:
+- ✅ Project cards with Kanban boards
+- ✅ Drag-and-drop task management
+- ✅ Real-time status widgets (Gateway, Discord, Cron)
+- ✅ 4 themes (NASA Retro, Luxury Commander, Cyberpunk, Organic)
+- ✅ Knowledge base reference cards
+- ✅ GLaDOS voice control integration
+
+### From Python Version:
+- ✅ MySQL persistence (vs JSON files)
+- ✅ Home Assistant API integration
+- ✅ Weather widget
+- ✅ Admin CRUD interface
+- ✅ News tracking
+- ✅ Gateway status with real endpoints
+
+---
+
+## Known Issues / TLC Needed
+
+| Issue | Dashboard | Priority |
+|-------|-----------|----------|
+| Status widgets outdated | Both | High |
+| Memory system not integrated | Both | High |
+| Mobile responsiveness | Next.js | Medium |
+| Theme switching flaky | Next.js | Low |
+| No unified data source | Both | High |
+
+---
+
+## Possible Directions
+
+### Option A: Refactor Next.js
+- Keep Next.js as frontend
+- Add MySQL backend (like Python version)
+- Port Python features over
+- Add memory system widgets
+
+### Option B: Enhance Python
+- Keep Python as primary
+- Add theme system from Next.js
+- Better UI/UX polish
+- Mobile responsiveness
+
+### Option C: Start Fresh
+- New tech stack (Svelte? Vue?)
+- Learn from both versions
+- Design unified architecture
+- Full rebuild
+
+### Option D: Hybrid API
+- Python as backend API
+- Next.js as frontend
+- Separate concerns properly
+
+---
+
+## Next Steps (When We Pick This Up)
+
+1. **Audit both dashboards** — what works, what doesn't
+2. **Decide architecture** — A, B, C, or D
+3. **Design unified schema** — data models, APIs
+4. **Migrate/merge features** — one dashboard to rule them all
+
+---
+
+**Notes:**
+- Frigate is ✅ working (Docker)
+- UniFi is 🟡 parked (auth issues later)
+- This project is on hold until direction decided
+
+---
+
+*Trigger words: dashboard tlc, mission control refresh, combine dashboards, dashboard v2*
--- a/memory/projects/mission-control-dashboard.md
+++ b/memory/projects/mission-control-dashboard.md
@@ -0,0 +1,95 @@
+# Mission Control Dashboard
+
+## Overview
+Next.js 14 dashboard for project management and system monitoring
+
+## Location
+`C:\web\htdocs\mission-control`
+**URL:** http://localhost:3000
+
+## Status
+🔄 **Consolidating** — Combined with Python version  
+**See:** `mission-control-dashboard-tlc.md` for unified project plan
+
+**Note:** Both dashboards running feature-complete but need refresh/merge.
+
+## Features
+
+### Project Management
+- Project cards with status (Planning, In Progress, Completed)
+- Kanban task boards
+- Drag-and-drop task management
+
+### Status Widgets (Real-Time)
+- OpenClaw gateway status
+- Home Assistant connectivity
+- Discord bot status
+- GLaDOS MCP health
+- Cron job monitoring
+
+### Quick Actions
+- Common operation buttons
+- One-click system checks
+
+### Knowledge Base
+- Reference cards with commands
+- API endpoint documentation
+- Path references
+
+## Tech Stack
+- **Framework:** Next.js 14+ with App Router
+- **Language:** TypeScript
+- **Styling:** Tailwind CSS + shadcn/ui
+- **Data:** Real-time polling APIs
+
+## API Endpoints
+
+### System Status
+- `GET /api/gateway` — Live OpenClaw status (30s refresh)
+- `GET /api/cron` — All cron jobs with status indicators
+- `GET /api/backup` — Supermemory backup status
+
+### Project Management
+- `GET /api/projects` — List all projects
+- `POST /api/projects` — Create new project
+- `PUT /api/projects/[id]` — Update project
+- `POST /api/projects/[id]/tasks` — Add task
+- `PUT /api/projects/[id]/tasks/[taskId]` — Update task status
+
+## Voice Control (GLaDOS Integration)
+
+**MCP Tools:**
+- `list_projects()` — "What am I working on?"
+- `create_project(name)` — Start new project
+- `add_task(project, task)` — Add task via voice
+- `update_task_status(taskId, status)` — Mark complete
+- `get_project_status()` — Check overall progress
+
+## Themes
+4 distinct themes created:
+1. **NASA Retro** — 1969 CRT monitor aesthetic
+2. **Luxury Commander** — Swiss editorial, watch brand quality
+3. **Cyberpunk Terminal** — Neon dystopian tech
+4. **Organic Living** — Biomorphic, natural flows
+
+Switch via: `themes\switch-theme.bat [1-4]`
+
+## Data Storage
+- **Projects:** `data/projects.json` (dynamic read/write)
+- **Data Store:** `data/data-store.ts` (read/write utilities)
+
+## Usage
+```bash
+cd C:\web\htdocs\mission-control
+npm run dev
+# Open http://localhost:3000
+```
+
+## Next Steps
+- Add Home Assistant real-time data (once HA cleanup complete)
+- Mobile responsiveness tweaks
+- PTT key binding (Spacebar hold)
+
+---
+
+*Trigger words: dashboard, mission control, nextjs, projects, kanban, status*
--- a/memory/projects/mission-control-python.md
+++ b/memory/projects/mission-control-python.md
@@ -0,0 +1,189 @@
+---
+## Mission Control Dashboard (Python) — Consolidating
+
+**Status:** 🔄 Combined with Next.js version — See TLC project  
+**Location:** `C:\web\htdocs\mission-control-py`
+**URL:** http://localhost:5050
+**URL (network):** http://192.168.0.34:5050  
+**Tech:** Python/Flask + MySQL + Home Assistant API
+
+---
+
+### Quick Reference
+
+| Command | Where |
+|---------|-------|
+| Run server | `cd C:\web\htdocs\mission-control-py && python app.py` |
+| Restart | Server auto-reloads on file changes |
+| Port | 5050 (Frigate-safe) |
+
+---
+
+### Pages
+
+| Route | File | Purpose |
+|-------|------|---------|
+| `/` | `dashboard.html` | Home: Gateway status, Cron jobs, Weather, Projects, Tasks |
+| `/admin` | `admin.html` | CRUD for Projects/Tasks in MySQL |
+| `/news` | `news.html` | Last 10 news briefs (JSON archive) |
+| `/alerts` | `alerts.html` | System alerts from Job Verifier cron |
+| `/calendar` | `calendar.html` | HA calendar + 24 F1 races |
+| `/memory` | `memory.html` | Memory file stats, cleanup candidates |
+
+---
+
+### File Structure
+
+```
+mission-control-py/
+├── app.py              # Main Flask app, routes
+├── api/
+│   ├── gateway.py      # get_gateway_status(), get_cron_jobs()
+│   ├── ha_calendar.py  # HA calendar API wrapper
+│   └── memory_files.py # Memory file scanner
+├── templates/
+│   ├── base.html       # Master template
+│   ├── dashboard.html  # Home page
+│   ├── admin.html      # Admin CRUD
+│   ├── news.html       # News briefs archive
+│   ├── alerts.html     # System alerts
+│   ├── calendar.html   # HA calendar
+│   └── memory.html     # Memory file stats
+├── static/
+│   └── style.css       # All styles
+├── outputs/
+│   ├── news/           # YYYY-MM-DD.json, latest.json
+│   └── alerts/         # latest.json
+└── models/
+    └── models.py       # Project, Task (MySQL)
+```
+
+---
+
+### Features
+
+#### Caching (5-minute TTL)
+- Gateway status cached in `_cache` dict
+- Cron jobs cached
+- Weather cached
+- Location: `app.py` → `_CACHE_TTL = timedelta(minutes=5)`
+
+#### Weather
+- Source: `weather.home` HA entity
+- API: `GET /api/states/weather.home`
+- Location: `get_weather()` in `app.py`
+- Fallback: Shows "--" if HA unavailable
+
+#### Calendar
+- Source: HA `calendar.appointments` entity
+- Fetch API: `GET /api/calendars/calendar.appointments?start=...&end=...`
+- Add API: `POST /api/services/calendar/create_event`
+- Location: `api/ha_calendar.py`
+- **Known Issue:** Date range filter may not work correctly (March 3 event not showing)
+
+#### News Briefs
+- Source: Cron job output JSON
+- Files: `outputs/news/latest.json` + `outputs/news/YYYY-MM-DD.json`
+- Format: `{title, date, generated_at, content, sources, summary}`
+- Crontab: Daily 8 AM → `openclaw cron run 3cf50074-...`
+
+#### Alerts
+- Source: Job Verifier cron output JSON
+- File: `outputs/alerts/latest.json`
+- Format: `{date, generated_at, alerts: [{level, message, time, ...}]}`
+- Crontab: Daily 9 AM → `openclaw cron run 8e2b06ee-...`
+
+#### Memory Files
+- Source: `C:\Users\admin\.openclaw\workspace\memory\*.md`
+- Features: Line count, TODO count, cleanup scoring
+- Location: `api/memory_files.py`
+
+---
+
+### Known Issues & Fixes
+
+| Issue | Status | Fix |
+|-------|--------|-----|
+| Calendar events beyond 10 days not showing | **KNOWN** | Date range filter bug — March 3 event (11 days out) not displaying |
+| Double "°F" in weather | FIXED | Strip HA unit before adding; `get_weather()` in `app.py` |
+| Calendar agent creates cron jobs instead of calendar events | **KNOWN** | Agent using `cron.add` instead of `ha_calendar.add()` — needs fix |
+
+---
+
+### HA API Reference
+
+**Base URL:** `http://192.168.0.39:8123`
+**Token:** See `TOOLS.md` or `api/ha_calendar.py`
+
+| Endpoint | Method | Description |
+|----------|--------|-------------|
+| `/api/states/weather.home` | GET | Current weather state |
+| `/api/calendars` | GET | List calendars |
+| `/api/calendars/calendar.appointments` | GET | Get appointments (params: `start`, `end`) |
+| `/api/services/calendar/create_event` | POST | Add event (body: `entity_id`, `summary`, `start_date_time`, `end_date_time`) |
+
+**Auth:** Header `Authorization: Bearer <token>`
+
+---
+
+### Cron Jobs Integrated
+
+| Job Name | ID | Schedule | Output |
+|----------|-----|----------|--------|
+| Daily News Brief | `3cf50074-8736-423e-ac41-6e6fb807bfee` | 0 8 * * * (8 AM) | JSON + Discord + /news |
+| Job Verifier Daily | `8e2b06ee-f2ea-4b33-ae39-23cf04b1a657` | 0 9 * * * (9 AM) | JSON + /alerts |
+
+---
+
+### Configuration
+
+**MySQL Connection:**
+- Database: `alexai`
+- Tables: `projects`, `tasks`
+- Config: `config.py` → `SQLALCHEMY_DATABASE_URI`
+
+**HA Token:**
+- In `api/ha_calendar.py` and `app.py`
+- Falls back to env var `HA_TOKEN`
+
+---
+
+### Debugging Tips
+
+1. **Check HA directly:**
+   ```bash
+   python -c "
+   import requests
+   r = requests.get('http://192.168.0.39:8123/api/calendars/calendar.appointments',
+                    params={'start': '2026-03-03T00:00:00', 'end': '2026-03-04T00:00:00'},
+                    headers={'Authorization': 'Bearer <token>'})
+   print(r.json())
+   "
+   ```
+
+2. **Test API directly:**
+   ```python
+   from api.ha_calendar import get_calendar_events, add_calendar_event
+   events = get_calendar_events('calendar.appointments', days=14)
+   print([e['summary'] for e in events])
+   ```
+
+3. **Clear cache:** Restart server (auto-reloads)
+
+4. **Check logs:** Terminal output shows "Starting Mission Control..."
+
+---
+
+### Changes Log
+
+| Date | Change |
+|------|--------|
+| 2026-02-19 | Initial build, 5 pages |
+| 2026-02-20 | Added weather, calendar, memory, F1 races (24 races added) |
+| 2026-02-20 | Fixed double °F in weather |
+| 2026-02-20 | Calendar agent created (has bug - creates cron instead of events) |
+
+---
+
+**Last Updated:** 2026-02-20
+**Maintainer:** Corey's Agent
--- a/memory/projects/nzb-download-system.md
+++ b/memory/projects/nzb-download-system.md
@@ -0,0 +1,51 @@
+# NZB Download System
+
+**Status:** Operational
+**Added:** 2026-03-09
+
+## Overview
+
+Automated NZB download pipeline via NZBGeek API + SABnzbd.
+
+## Workflow
+
+OpenClaw -> pirate/ -> SABnzbd -> VPN -> downloads
+
+## Components
+
+- **NZBGeek API** (api.nzbgeek.info) - Source index
+- **OpenClaw** (AIAgents) - Search, grab NZBs
+- **pirate/** (workspace/pirate/) - Watch folder
+- **SABnzbd** (VPN box 192.168.0.17) - Download client
+- **VPN** - Routes traffic
+
+## Download Preferences
+
+1. English only
+2. Under 10GB (default)
+3. Atmos preferred
+
+## API Key
+
+ueQEr7DGNzdtit3AYCP3snwduLtJPaeD
+
+## First Download
+
+Tron (1982) - 2160p DSNP WEB-DL, DD+ 5.1 Atmos, 9.9 GB
+
+---
+
+## Future: Torrent Support
+
+Same pirate/ folder for .torrent files via qBittorrent.
+## Note
+
+Once NZB is dropped in pirate/, SABnzbd auto-picks it up. No manual intervention needed.
+
+## Downloads
+
+| Date | Title | Quality | Size | Status |
+|------|-------|---------|------|--------|
+| 2026-03-09 | Tron (1982) | 2160p DSNP WEB-DL DD+ 5.1 Atmos | 9.9 GB | Downloaded |
+| 2026-03-13 | Good Luck Have Fun Don't Die | 1080p WEBRip x265 DDP5.1 | 2.2 GB | Queued |
+| 2026-03-20 | We Bury the Dead (2024) | 1080p WebRip YTS x264 AAC5.1 | 1.84 GB | Queued |
--- a/memory/projects/obsidian-workflow.md
+++ b/memory/projects/obsidian-workflow.md
@@ -0,0 +1,126 @@
+# Obsidian Workflow Rules
+
+**Purpose**: Define where and how to save content to Obsidian vault.
+
+When user says "save this to Obsidian" or "save to vault", **READ THIS FILE FIRST**.
+
+---
+
+## Vault Location
+
+```
+C:\Users\admin\Documents\Corey
+```
+
+CLI: `notesmd-cli` (default vault set)
+
+---
+
+## Folder Structure & Rules
+
+### Daily Notes/
+**Purpose**: Daily journal / log
+**Naming**: YYYY-MM-DD.md (auto-generated)
+**Use for**: Daily logs, quick notes, "save to today"
+
+### Projects/
+**Purpose**: Active project documentation
+**Naming**: `[Project Name]/[Topic].md`
+**Use for**: Ongoing work, project-specific notes
+
+#### Sub-folders:
+- `Projects/ROM Library/` - ROM organization notes
+- `Projects/Home Assistant/` - HA automations, configs
+- `Projects/Coding/` - Code snippets, workflows
+
+### Summaries/
+**Purpose**: Content summaries (articles, videos, etc.)
+**Naming**: `[Source] - [Title].md`
+**Use for**: `/summarize` output, web article summaries
+
+### Personal Notes/
+**Purpose**: Non-work personal notes
+**Naming**: Freeform
+**Use for**: Ideas, thoughts, personal references
+
+### Guides/
+**Purpose**: How-to guides, references
+**Naming**: `[Topic] Guide.md`
+**Use for**: Tutorials, step-by-step instructions
+
+### Home Assistant/
+**Purpose**: Home Assistant specific
+**Naming**: Device/automation specific
+**Use for**: HA configs, automations, device notes
+
+### OpenClaw/
+**Purpose**: OpenClaw agent notes
+**Naming**: Freeform
+**Use for**: Agent configuration, workflow notes
+
+### News Briefs/
+**Purpose**: Daily/weekly news summaries
+**Naming**: `News YYYY-MM-DD.md`
+**Use for**: Daily news brief output
+
+### Tasks/
+**Purpose**: Task tracking
+**Naming**: Freeform or by project
+**Use for**: TODOs, action items
+
+### UniFi/
+**Purpose**: UniFi network notes
+**Naming**: Device/issue specific
+**Use for**: Network config, device inventory
+
+### WORK/
+**Purpose**: Work-related notes
+**Naming**: By client/project
+**Use for**: Work projects, client notes
+
+---
+
+## File Naming Conventions
+
+- Use Title Case: `ROM Library Inventory.md`
+- Date prefix for dated content: `2026-03-10 Event Log.md`
+- No special characters except `-` and spaces
+- Keep names readable, avoid abbreviations unless obvious
+
+---
+
+## Default Behaviors
+
+| Content Type | Default Location |
+|--------------|------------------|
+| Daily log entry | Daily Notes/today |
+| Project note | Projects/[Project]/ |
+| Article summary | Summaries/ |
+| How-to guide | Guides/ |
+| Personal note | Personal Notes/ |
+| Work note | WORK/ |
+
+---
+
+## Workflow Checklist
+
+When saving to Obsidian:
+
+1. ✅ Read this file first (obsidian-workflow.md)
+2. ✅ Identify content type
+3. ✅ Choose appropriate folder
+4. ✅ Apply naming convention
+5. ✅ Create note with `notesmd-cli create "[folder]/[name]" --content "..."`
+
+---
+
+## Tags
+
+Default tags to include in frontmatter:
+- `#project/[name]` - Project association
+- `#status/active` or `#status/completed`
+- `#type/[note/guide/summary/log]`
+
+---
+
+*Last Updated: 2026-03-10*
--- a/memory/projects/proton-mail-bridge.md
+++ b/memory/projects/proton-mail-bridge.md
@@ -0,0 +1,57 @@
+# Proton Mail Bridge Integration
+
+## Overview
+Email integration via Proton Mail Bridge for IMAP/SMTP access
+
+## Connection Details
+- **IMAP Server:** 127.0.0.1:1143
+- **SMTP Server:** 127.0.0.1:1025
+- **Username:** alexthenerdyai@proton.me
+- **Security:** AUTH=PLAIN (local connection only)
+- **Bridge Version:** Proton Mail Bridge 03.22.00 - gluon
+
+## Test Results (2026-02-18)
+✅ Connected successfully to Bridge IMAP
+✅ Authenticated with Bridge password
+✅ Retrieved folder list (10 folders found)
+✅ INBOX has 3 messages, all unread
+
+## Available Folders
+- INBOX
+- Sent
+- Drafts
+- Starred
+- Archive
+- Spam
+- Trash
+- All Mail
+- Folders
+- Labels
+
+## Capabilities
+- Read emails from INBOX
+- Search, mark read/unread, move messages
+- Send emails via SMTP
+- Full folder management
+
+## Potential Uses
+- Daily email digest
+- Notifications
+- Automated responses
+- Email-based triggers
+
+## Files Created
+- `tools/proton_imap_test.py` — Initial test script
+- `tools/proton_imap_simple.py` — Working IMAP test script
+
+## Status
+✅ **Functional** — Bridge connected and tested
+
+## Next Steps
+- [ ] Integrate with cron jobs for email-based actions
+- [ ] Create email notification system
+- [ ] Set up email-to-Discord forwarding if desired
+
+---
+
+*Trigger words: proton, email, imap, smtp, bridge, mail*
--- a/memory/projects/research-agents.md
+++ b/memory/projects/research-agents.md
@@ -0,0 +1,51 @@
+# Research Agent Spawning
+
+## Overview
+System for spawning isolated sub-agents to handle research tasks asynchronously
+
+## Status
+🔄 **In Progress** — Designing spawn and report workflows
+
+## Goals
+- Spawn sub-agents for independent research tasks
+- Parallel execution for multiple research queries
+- Automatic summarization and reporting back
+- Resource management (don't overwhelm system)
+
+## Architecture Ideas
+
+### Option 1: Cron-Based Research
+- Spawn agents via cron jobs
+- Results delivered via Discord
+- Good for: scheduled research, news monitoring
+
+### Option 2: On-Demand Spawning
+- User triggers: "/research [topic]"
+- Spawns isolated session
+- Reports back when complete
+- Good for: deep dives, ad-hoc questions
+
+### Option 3: Persistent Research Channel
+- Dedicated Discord channel
+- All research requests go there
+- Agent monitors and spawns workers
+- Good for: continuous research, collaborative
+
+## Current Exploration
+Testing in #projects channel (1468257895152881796)
+
+## Questions to Answer
+- [ ] How many concurrent agents?
+- [ ] How to handle long-running research?
+- [ ] Where to store results? (Obsidian? SQLite?)
+- [ ] How to prevent spawn loops?
+- [ ] Cost tracking per agent?
+
+## Related
+- [[Multi-User Agent Architecture]] — multi-user considerations
+- [[Memory System]] — where research results might go
+
+---
+
+*Created: 2026-02-25*
+*Next: Test spawning mechanisms*
--- a/memory/projects/rom-library.md
+++ b/memory/projects/rom-library.md
@@ -0,0 +1,59 @@
+# ROM Library Organization
+
+**Status**: In Progress
+**Started**: 2026-03-09
+**Location**: R:\ (38.8 TB)
+
+## Goal
+Phase 1: Inventory all ROMs across multiple gaming systems
+Phase 2: Detect duplicates via MD5 hashing
+Phase 3: Identify missing ROMs from No-Intro/Redump sets (future)
+
+## Library Structure
+```
+R:/
+├── Rom Sets (Organized)/
+│   ├── Nintendo/
+│   ├── Sony/
+│   ├── Sega/
+│   ├── Microsoft/
+│   ├── Atari/
+│   ├── Arcade/
+│   ├── Computers/
+│   └── Misc Consoles/
+└── Rom Sets (Somewhat Organized)/
+```
+
+## Quick Scan Results (2026-03-09)
+- **Total**: 98,601 items, 1,701 GB
+- **Top by count**: Commodore 64 (24,349), Atari (10,935), MAME (8,651)
+- **Top by size**: PSN ISO Pack (672 GB), Nintendo 3DS (412 GB), TurboGrafx-CD (234 GB)
+
+## By Manufacturer
+| Manufacturer | Items | Size |
+|--------------|-------|------|
+| Computers | 47,327 | 61.89 GB |
+| Arcade | 12,951 | 32.97 GB |
+| Atari | 12,399 | 2.56 GB |
+| Nintendo | 12,017 | 467.24 GB |
+| Sony | 3,106 | 672.40 GB |
+| Sega | 2,747 | 3.54 GB |
+| Microsoft | 1,661 | 0.05 GB |
+
+## Disc vs Cartridge Systems
+- **Disc systems** (count folders): PSX (1,516), PS3 (77), PS VITA (6), Saturn (3)
+- **Cartridge systems** (count files): NES (1,592), SNES, Genesis, GBA, etc.
+
+## Scripts
+- `tools/rom-quick-scan.py` - Quick count (completed)
+- `tools/rom-full-scan.py` - Duplicate detection (overnight scan)
+
+## Output Files
+- `rom-inventory/rom-inventory.json` - Quick scan
+- `rom-inventory/rom-full-*.json` - Full scan with duplicates
+
+## Notes
+- Hash only files under 50MB (speed vs coverage tradeoff)
+- Node gateway has 30s timeout - use background processes for long scans
+- No-Intro DAT files available at https://datomatic.no-intro.org/
+\n## Full Scan Results (2026-04-09)\n\n**Status:** Complete\n\n| Metric | Value |\n|--------|-------|\n| Total files | 773,442 |\n| Total size | 21.9 TB |\n| Files hashed | 756,454 |\n| Skipped (too large) | 16,987 |\n| **Duplicates found** | **44,844** |\n\n**Runtime:** 13 hours\n\n**Output:** `rom-inventory/rom-full-scan.json`\n\n**Next steps:**\n1. Analyze JSON to identify duplicate clusters\n2. Determine which systems have most duplicates\n3. Create cleanup plan (manual review vs auto-delete)\n
--- a/memory/projects/supermonkey-memory-system.md
+++ b/memory/projects/supermonkey-memory-system.md
@@ -0,0 +1,158 @@
+# Supermonkey Memory System
+
+**Status:** ✅ Production  
+**Created:** 2026-03-02  
+**Location:** `~/.openclaw/memory.db`
+
+---
+
+## Overview
+
+Local semantic memory search using SQLite + Ollama embeddings. Replaces flaky Supermemory cloud API.
+
+**Why "Supermonkey"?**
+- Works offline (like a monkey with a typewriter)
+- No cloud dependency
+- Just keeps going
+
+---
+
+## Architecture
+
+### File-Based Pipeline (Daily)
+```
+Memory Files (markdown)
+    ↓
+memory_embedding_worker.py
+    ↓
+Ollama (nomic-embed-text) → 768-dim vectors
+    ↓
+SQLite + sqlite-vector extension
+    ↓
+Cosine similarity search
+```
+
+### Real-Time Session Pipeline (Live)
+```
+Discord/Chat Messages
+    ↓
+OpenClaw Session Transcript (.jsonl)
+    ↓
+session_monitor.py (cron every 2 min)
+    ↓
+Count messages → At 15: summarize → embed → store
+    ↓
+Ollama (nomic-embed-text)
+    ↓
+SQLite + sqlite-vector
+```
+
+**The Innovation:** Read OpenClaw's own session transcripts to auto-capture conversations without manual tracking or hooks!
+
+---
+
+## Components
+
+| File | Purpose |
+|------|---------|
+| `memory_vector.py` | Core SQLite-vector wrapper |
+| `memory_embedding_worker.py` | Daily memory file processor |
+| `session_monitor.py` | Real-time transcript capture |
+| `session_snapshotter.py` | Manual session capture |
+| `search_memories.py` | CLI search tool |
+| `bulk_memory_loader.py` | One-time historical import |
+
+---
+
+## Quick Commands
+
+```powershell
+# Search memories
+python tools/search_memories.py "home assistant automation"
+
+# Check stats
+python -c "import sqlite3; db=sqlite3.connect(r'C:\Users\admin\.openclaw\memory.db'); c=db.cursor(); c.execute('SELECT COUNT(*) FROM memory_embeddings'); print('Total:', c.fetchone()[0]); c.execute('SELECT COUNT(*) FROM memory_embeddings WHERE source_type=\'auto_session\''); print('Auto snapshots:', c.fetchone()[0]); db.close()"
+
+# Run daily worker manually
+python tools/memory_embedding_worker.py --date 2026-03-03
+
+# Run session monitor manually
+python tools/session_monitor.py
+```
+
+---
+
+## Current Stats
+
+| Metric | Value |
+|--------|-------|
+| Total embeddings | ~1,623 |
+| Daily notes processed | 818 |
+| Project files | 332 |
+| MEMORY.md sections | 33 |
+| Manual session snapshots | 2 |
+| **Auto session snapshots** | **27** |
+| Tracked sessions | 245 |
+| Active sessions | 243 |
+| Database size | ~5 MB |
+
+---
+
+## Database Schema
+
+### memory_embeddings
+| Column | Type | Description |
+|--------|------|-------------|
+| id | INTEGER | Primary key |
+| source_type | TEXT | daily, memory_md, project, auto_session |
+| source_path | TEXT | File path + section |
+| content_text | TEXT | First 500 chars |
+| embedding | BLOB | 768-dim vector |
+| created_at | TIMESTAMP | Auto-set |
+
+### session_tracking
+| Column | Type | Description |
+|--------|------|-------------|
+| session_id | TEXT | OpenClaw UUID |
+| transcript_path | TEXT | Path to .jsonl |
+| last_message_index | INTEGER | Checkpoint |
+| messages_since_snapshot | INTEGER | Counter |
+| is_active | BOOLEAN | Active? |
+
+---
+
+## Cron Schedule
+
+| Job | Schedule | Purpose |
+|-----|----------|---------|
+| Memory Embeddings Daily | 3:00 AM | Process yesterday's memory files |
+| Session Monitor | Every 2 min | Auto-snapshot live conversations |
+
+---
+
+## Troubleshooting
+
+**Ollama not running:**
+```powershell
+ollama serve
+```
+
+**Database locked:**
+Close DB Browser for SQLite
+
+**Unicode errors in cron:**
+All emojis replaced with ASCII-safe markers
+
+---
+
+## Future Enhancements
+
+- [ ] Keyword filtering alongside vector search
+- [ ] Date range queries
+- [ ] Source type filtering
+- [ ] Embedding quality scoring
+
+---
+
+**Credit:** Corey's genius idea to read session.json files 💡  
+**System:** Operational and self-managing
--- a/memory/projects/unifi-monitoring.md
+++ b/memory/projects/unifi-monitoring.md
@@ -0,0 +1,66 @@
+# UniFi Network Monitoring
+
+**Status:** 🔄 In Progress  
+**Location:** `~/.openclaw/workspace/skills/unifi/`  
+**Added:** 2026-02-27
+
+## Overview
+
+Network monitoring via UniFi Controller API. Read-only access to:
+- Device status (APs, switches, USG)
+- Connected clients
+- Network health
+- DPI traffic stats
+- Alerts/alarms
+
+## Hardware
+
+- **Gateway:** UniFi USG
+- **Controller:** Running on Home Assistant box (192.168.0.39:8123)
+- **API URL:** `https://192.168.0.39:8443` (standard controller port)
+
+## Setup Status
+
+- [x] Skill files installed
+- [ ] Credentials configured
+- [ ] Connection tested
+- [ ] Commands verified working
+
+## Commands
+
+| Script | Purpose |
+|--------|---------|
+| `bash scripts/devices.sh` | List UniFi devices |
+| `bash scripts/clients.sh` | List connected clients |
+| `bash scripts/health.sh` | Network health |
+| `bash scripts/top-apps.sh` | Top bandwidth consumers |
+| `bash scripts/alerts.sh` | Recent alarms |
+| `bash scripts/dashboard.sh` | Full dashboard |
+
+All support `json` argument for raw output.
+
+## Configuration
+
+File: `~/.clawdbot/credentials/unifi/config.json`
+
+```json
+{
+  "url": "https://192.168.0.39:8443",
+  "username": "admin",
+  "password": "YOUR_PASSWORD",
+  "site": "default"
+}
+```
+
+## Notes
+
+- Requires local admin account (not UniFi SSO)
+- Scripts use `curl -k` for self-signed controller certs
+- DPI must be enabled in UniFi for bandwidth stats
+- Read-only API access (safe for monitoring)
+
+## Related
+
+- **Skill Docs:** `skills/unifi/README.md`
+- **API Reference:** `skills/unifi/references/unifi-readonly-endpoints.md`
+- **Source:** OpenClaw official skills repo