LLM Agent Orchestrator Documentation
Web-deployed multi-agent AI system for autonomous software development with role-based orchestration and self-healing agent outputs.
OVERVIEW
ARCHITECTURE
AGENTS
CONFIGURATION
WORKFLOW
TROUBLESHOOTING
What is the LLM Agent Orchestrator?
A sophisticated multi-agent system for autonomous software development. Built with Python, supporting both Django web interface and CustomTkinter desktop application, it enables teams of specialized AI agents to collaborate on complex coding tasks through a persistent virtual file system.
🎯 Design Philosophy: This system bridges the gap between simple chatbots and
complex multi-agent architectures. Each agent has a distinct persona, role, and expertise area,
working together through structured communication protocols to produce complete, executable software
projects.
Core Capabilities
- Multi-Agent Collaboration: 6+ specialized agents (Strategist, PM, Architect, Programmer, Bug-Hunter, Consensus Finder)
- Multi-Provider Support: Google Gemini, OpenAI GPT, Anthropic Claude, and Local LLMs (LM Studio)
- Virtual File System: Persistent code storage with automatic versioning and history tracking
- Self-Healing JSON: Automatic retry logic with syntax error recovery for code generation
- Context Injection: Full codebase automatically loaded into agent context before each response
- Project Resume: Load existing projects and continue from any checkpoint
System Components
Agent Layer
Specialized AI personas with distinct system prompts
Temperature and token limits per agent
Orchestration Engine
Round-robin speaker rotation
Question-based delegation (QUESTION TO syntax)
Approval-based progression (APPROVAL trigger)
File System Layer
current/ - Active codebase (executable)
versions/ - Historical snapshots
logs/ - Conversation and configuration history
Use Cases
✅ Ideal For
• Proof-of-concept prototypes
• CLI tools and automation scripts
• Small web applications (Flask, FastAPI)
• Educational code examples
• Single-file utilities
❌ Not Recommended For
• Production-critical systems
• Projects requiring compiled languages (C++, Rust)
• Complex GUI applications
• Projects needing binary assets (images, audio)
• Real-time systems with hard deadlines
Technical Stack
Backend
Python 3.10+
Threading & Queue for async
Frontend
CustomTkinter (desktop)
Django (web)
LLM Integration
google-generativeai, openai, anthropic SDKs
Local OpenAI-compatible API
Storage
File-based (no database)
JSON for logs/config
System Architecture
Core Components
1. AgentSimulation (agent_logic.py)
Central orchestration engine managing conversation state, chat history, retry logic, JSON validation, and file system operations.
2. LLM Provider Layer (llm_providers.py)
GeminiProvider
google-generativeai SDK
1M+ token context
OpenAIProvider
openai SDK v1.0+
Most reliable API
AnthropicProvider
anthropic SDK
Extended context windows
LocalProvider
OpenAI-compatible REST
http://localhost:1234/v1
Data Flow
1. User Input → Prompt
2. Select Agent (Round-Robin / QUESTION TO)
3. Load Context (Architect plan + current/ files)
4. LLM API Call (with 3-attempt retry)
5. Parse Response (validate JSON if Programmer)
6. Save Files (current/ + versions/)
7. Update UI → Next Turn
File System Structure
output/project_name_20240115_143022/
├── logs/
│ ├── conversation.log # JSON-lines
│ └── agents.json # Config snapshot
├── current/ # EXECUTABLE
│ ├── run.py
│ └── src/
│ ├── __init__.py # Auto-generated
│ └── main.py
└── versions/ # HISTORY
├── run.py.v001
└── run.py.v002
Communication Protocols
APPROVAL
Consensus Finder signals completion
Advances round or ends simulation
QUESTION TO [Role]
Delegates to specific agent
Example: QUESTION TO Programmer: Fix import
AGENT_FAILURE
Retry exhaustion signal
Halts after 3 failed attempts
JSON Self-Healing
- Parser detects syntax error in Programmer response
- Error message constructed with original attempt
- Correction prompt sent back to Programmer (no turn increment)
- Loop until valid JSON or retry exhaustion
- Valid JSON → Files saved → Flow continues
⚠️ Critical Detail: JSON healing loop does NOT increment turn counter, preventing
infinite loops where downstream agents get called before code is saved.
Agent System
1. Strategist (Konrad) - Optional
Role
Strategic planning and requirement interpretation
Creates task checklists with role assignments
Config
Temp: 0.8 | Tokens: 8K | Enabled: False
Color: #9a9fa0 (gray)
2. Project Manager (Klaus)
Role
Converts plan into User Stories
Defines domain-specific minimal features
Makes fundamental technical decisions
Config
Temp: 0.7 | Tokens: 8K | Enabled: True
Color: #bb8fcd (purple)
3. Software Architect (Eva)
Role
Creates definitive technical design (pure spec, no code)
Defines file structure and API signatures
Enforces Two-Stage Bootstrap pattern
Config
Temp: 0.6 | Tokens: 30K | Enabled: True
Color: #c6e1f4 (light blue)
💡 Two-Stage Bootstrap:
run.py sets sys.path and calls
src.main. All imports use src. prefix. Prevents ImportError.
4. Programmer (Ben)
Role
1:1 implementation of Architect's design
Strict JSON output format (enforced)
Config
Temp: 0.2 | Tokens: 30K | Enabled: True
Color: #53ff79 (green)
JSON Format:
{"files": [
{"file_path": "run.py", "content": "..."},
{"file_path": "src/main.py", "content": "..."}
]}
5. Bug-Hunter (Findus)
Role
Deep code analysis for logical errors
Circular dependency detection
Logic cohesion verification
Config
Temp: 0.1 | Tokens: 8K | Enabled: True
Color: #8cb4df (blue)
6. Consensus Finder (Judge)
Role
Final completeness verification
Compares planned vs. actual files
Blocks approval until 100% complete
Config
Temp: 0.7 | Tokens: 8K | Enabled: True
Color: #27e0bb (cyan)
Communication Patterns
Round-Robin:
PM → Architect → Programmer → Bug-Hunter → Consensus
Question-Based:
Bug-Hunter finds error → QUESTION TO Programmer
Programmer fixes → Back to Bug-Hunter
Bug-Hunter approves → Continue to Consensus
Configuration System
Agent Parameters
name
Display name in UI
internal_name
Persona nickname
system_prompt
Complete role definition
color
Hex code (#RRGGBB)
enabled
Boolean toggle
temperature
0.0-1.0 randomness
max_output_tokens
256-32768 max length
Recommended Configs by Role
Creative
Strategist, PM
Temp: 0.7-0.8 | Tokens: 4K-8K
Design
Architect
Temp: 0.5-0.6 | Tokens: 16K-30K
Implementation
Programmer
Temp: 0.1-0.3 | Tokens: 16K-30K
Analysis
Bug-Hunter, Consensus
Temp: 0.1-0.2 | Tokens: 4K-8K
Environment Variables
GEMINI_API_KEY
ai.google.dev
OPENAI_API_KEY
platform.openai.com
ANTHROPIC_API_KEY
console.anthropic.com
Best Practices
- System Prompts: Use ALL-CAPS for critical rules (NEVER, MUST, ALWAYS)
- Temperature: Code generation: 0.1-0.3, Design: 0.5-0.7, Brainstorming: 0.8-1.0
- Tokens: 1 token ≈ 4 characters. Account for context overhead
- Ordering: Architect MUST come before Programmer (plan cached for context injection)
⚠️ Critical: Architect must precede Programmer. System caches Architect's plan as
last_architect_plan for injection into Programmer/Bug-Hunter/Consensus contexts.
Simulation Workflow
1. Initialization
- Launch application (desktop/web)
- Load default agent config
- Check API key environment variables
- Detect available LLM providers
2. Configuration
User
Select provider/model
Enter API key
Adjust agents
Set rounds (1-10)
System
Validate API key
Update UI dropdowns
Initialize logs
Prepare queue
3. Orchestration Loop
Round N:
Turn 1-5: Agents respond in sequence
If APPROVAL → Advance Round / End
If QUESTION TO → Jump to target agent
Else → Next agent
4. Multi-Pass Refinement
Pass 1: Programmer delivers → Bug-Hunter finds issue
Pass 2: Programmer fixes → Bug-Hunter approves
Pass 3: Consensus checks → Missing file found
Pass 4: Programmer adds → Consensus → APPROVAL
5. Completion
Success
APPROVAL + round limit reached
Pause
User clicks Stop
Failure
3 retries exhausted
Error
Critical exception
Project Resume
- Select existing project folder
- System creates backup:
backup_pre_resume_TIMESTAMP/ - Load
logs/conversation.loginto histories - Inject all files from
current/ - Add continuity mandate to prompts
- Enter new task or "Continue"
💡 Continuity Mandate: When resuming, prompts include: "This is continuation of
existing project. Provided files represent current state. Continue work on this basis. Do NOT
reinvent. Respect existing code as Ground Truth."
Troubleshooting Guide
API Issues
Immediate Red Error
Symptom
Error immediately on start
No agent responses
Solution
1. Verify API key (copy-paste)
2. Check model dropdown
3. Test connection
4. Try different model
Gemini 400 Error
Symptom
App freezes mid-simulation
Chat stops updating
Solution
Desktop: Restart (Ctrl+C)
Django: Restart server
Prevention: Use OpenAI/Anthropic
Local LLM Refused
Cause
LM Studio not running
Wrong port (need 1234)
Solution
1. Start LM Studio
2. Verify port 1234
3. Test: curl localhost:1234/v1/models
4. Enter "local" as API key
JSON Errors
Infinite Healing Loop
Cause
Model doesn't understand correction
Temperature too high
Solution
1. Lower Programmer temp to 0.1
2. Use stronger model (GPT-4, Opus)
3. Simplify project scope
Import Errors
ModuleNotFoundError
Symptom
ModuleNotFoundError: No module named 'src'
Solution
1. Check run.py has sys.path setup
2. Verify imports: from src.module import X
3. Check __init__.py exists
4. Run from project root
Circular Import
Cause
Module A imports B, B imports A
Solution
1. Trace import chain
2. Use forward refs: def foo(x: 'Class')
3. Move imports inside functions
4. Extract shared code to 3rd module
Known Limitations
- Binary Assets: Cannot generate images/audio. Workaround: URLs or manual placeholders
- Large Projects: 50+ files may exceed context. Workaround: Split into modules
- Complex GUIs: Often incomplete. Workaround: Explicit feature list in prompt
⚠️ Critical Recovery: If broken beyond repair:
- Close app/stop server
- Delete output/ directory
- Verify API key
- Start minimal (PM, Architect, Programmer, Consensus)
- Test: "Create hello world script"
Copyright © 2026 Dr. Felix Sébastien Bourier. All rights reserved.