Documentation cleanup and consolidation

Removed redundant/outdated files:
- docs/HEARTBEAT_HOOKS.md (legacy, disabled by default)
- docs/QUICK_START_PULSE.md (merged into PULSE_BRAIN.md)
- docs/MONITORING_COMPARISON.md (merged into PULSE_BRAIN.md)

Consolidated monitoring docs:
- Merged 3 monitoring files into comprehensive PULSE_BRAIN.md
- Added Quick Start section to PULSE_BRAIN.md
- Added "Why Pulse & Brain?" comparison section
- Added deprecation notices for Heartbeat system

Updated README.md:
- Clarified Haiku is default model (12x cheaper)
- Added prompt caching info (90% savings on Sonnet)
- Removed duplicate setup instructions
- Linked to SETUP.md for detailed instructions
- Added model switching commands section

Simplified WINDOWS_QUICK_REFERENCE.md:
- Reduced from 224 lines to ~160 lines
- Removed redundant development/deployment sections
- Kept essential quick commands
- Added model switching commands

Updated docs/README.md navigation:
- Removed references to deleted files
- Added deprecation notice for Heartbeat
- Updated learning paths
- Cleaned up file organization section

Result:
- Removed 300+ lines of redundant documentation
- Consolidated 3 monitoring files into 1
- Improved accuracy and clarity
- Easier navigation and maintenance

Co-Authored-By: Claude Sonnet 4.5 <noreply@anthropic.com>

WINDOWS_QUICK_REFERENCE.md

@@ -158,67 +158,15 @@ python example_usage.py
 | `adapters/` | Platform integrations |
 | `memory_workspace/` | Memory database |
 
+## Model Switching
+
+Tell your bot via chat:
+- `/haiku` - Fast, cheap (default)
+- `/sonnet` - Smart, caching enabled
+- `/status` - Check current model
+
 ## Need More Help?
 
+- **Complete Setup Guide:** [SETUP.md](SETUP.md)
 - **Full Windows Guide:** [docs/WINDOWS_DEPLOYMENT.md](docs/WINDOWS_DEPLOYMENT.md)
 - **Main Documentation:** [docs/README.md](docs/README.md)
-- **Project Overview:** [README.md](README.md)
-
-## Common Workflows
-
-### Development Testing
-```powershell
-# Activate environment
-.\venv\Scripts\activate
-
-# Make changes to code
-# ...
-
-# Test changes
-python test_installation.py
-python example_usage.py
-
-# Format code (optional)
-pip install black
-black .
-```
-
-### Production Deployment
-```powershell
-# 1. Configure adapters
-python bot_runner.py --init
-notepad config\adapters.local.yaml
-
-# 2. Test locally
-python bot_runner.py
-
-# 3. Set up as service (see docs/WINDOWS_DEPLOYMENT.md)
-# Option A: NSSM (recommended)
-# Option B: Task Scheduler
-# Option C: Startup script
-```
-
-### Monitoring Costs
-```python
-# In Python script or interactive shell
-from pulse_brain import PulseBrain
-from agent import Agent
-
-agent = Agent(provider="claude", enable_heartbeat=False)
-pb = PulseBrain(agent)
-
-# After running for a while
-status = pb.get_status()
-tokens = status['brain_invocations'] * 1000  # Average tokens
-cost = tokens * 0.000003  # Claude pricing
-print(f"Estimated cost: ${cost:.4f}")
-```
-
----
-
-**Quick Start Path:**
-1. Run `quick_start.bat`
-2. Set API key
-3. Run `python test_installation.py`
-4. Run `python example_usage.py`
-5. Explore other examples!