Final cleanup: Merge LLM, add Dockerfile

- Merge llm.py + llm_sync.py into single unified client
- Remove llm_sync.py (now just llm.py with both sync/async)
- Add requests to dependencies
- Add Dockerfile for containerized deployment
- Add .dockerignore

All issues resolved!

.dockerignore

@@ -0,0 +1,40 @@
+# Git
+.git
+.gitignore
+
+# Python
+__pycache__
+*.py[cod]
+*$py.class
+*.so
+.Python
+venv/
+.venv/
+env/
+.env
+*.egg-info/
+dist/
+build/
+
+# IDE
+.vscode/
+.idea/
+*.swp
+*.swo
+
+# Testing
+.pytest_cache/
+.coverage
+htmlcov/
+
+# OS
+.DS_Store
+Thumbs.db
+
+# Docs
+*.md
+!README.md
+
+# Local
+*.log
+*.tmp

Dockerfile

@@ -0,0 +1,51 @@
+# =============================================================================
+# Opus Orchestrator AI - Dockerfile
+# =============================================================================
+# Build: docker build -t opus-orchestrator .
+# Run:   docker run -p 8080:8080 -p 8000:8000 -e OPENAI_API_KEY=sk-... opus-orchestrator
+# =============================================================================
+
+FROM python:3.12-slim
+
+# Labels
+LABEL maintainer="mark@thefoldwithin.earth"
+LABEL description="AI-powered book generation system"
+LABEL version="0.2.0"
+
+# Set working directory
+WORKDIR /app
+
+# Install system dependencies
+RUN apt-get update && apt-get install -y --no-install-recommends \
+    build-essential \
+    curl \
+    && rm -rf /var/lib/apt/lists/*
+
+# Copy project files
+COPY pyproject.toml README.md install.sh ./
+COPY opus_orchestrator/ ./opus_orchestrator/
+COPY config.example.yaml ./
+
+# Create virtual environment
+RUN python -m venv /opt/venv
+ENV PATH="/opt/venv/bin:$PATH"
+
+# Install Python dependencies
+RUN pip install --no-cache-dir -e ".[all]"
+
+# Create non-root user
+RUN useradd -m -u 1000 opus && \
+    chown -R opus:opus /app
+
+# Switch to non-root user
+USER opus
+
+# Expose ports
+EXPOSE 8000 8080
+
+# Health check
+HEALTHCHECK --interval=30s --timeout=10s --start-period=5s --retries=3 \
+    CMD curl -f http://localhost:8000/health || exit 1
+
+# Default command: start web UI
+CMD ["python", "-m", "opus_orchestrator", "ui", "--port", "8080"]

opus_orchestrator/langgraph_workflow.py

@@ -25,7 +25,7 @@ from langgraph.graph import StateGraph, END
 from langgraph.checkpoint.memory import MemorySaver
 
 from opus_orchestrator.frameworks import get_framework_prompt, StoryFramework
-from opus_orchestrator.utils.llm_sync import LLMClient
+from opus_orchestrator.utils.llm import LLMClient
 from opus_orchestrator.autogen_critique import create_critique_crew
 
 

opus_orchestrator/utils/llm_sync.py

@@ -1,142 +0,0 @@
-"""LLM client for Opus Orchestrator - Synchronous version.
-
-Uses synchronous httpx to avoid event loop issues with LangGraph.
-"""
-
-import os
-from typing import Any, Optional
-
-import requests
-
-
-class LLMClient:
-    """Synchronous LLM client for making API calls."""
-
-    def __init__(
-        self,
-        api_key: Optional[str] = None,
-        provider: str = "openai",
-        model: str = "gpt-4o",
-        base_url: Optional[str] = None,
-    ):
-        """Initialize LLM client."""
-        self.api_key = api_key or os.environ.get("MINIMAX_API_KEY") or os.environ.get("OPENAI_API_KEY")
-        self.provider = provider
-        self.model = model
-        
-        if base_url:
-            self.base_url = base_url
-        elif provider == "minimax":
-            self.base_url = "https://api.minimax.chat/v1"
-        elif provider == "openai":
-            self.base_url = "https://api.openai.com/v1"
-        else:
-            self.base_url = "https://api.openai.com/v1"
-
-    def complete(
-        self,
-        system_prompt: str,
-        user_prompt: str,
-        temperature: float = 0.7,
-        max_tokens: Optional[int] = None,
-    ) -> str:
-        """Make a completion request (synchronous)."""
-        headers = {
-            "Authorization": f"Bearer {self.api_key}",
-            "Content-Type": "application/json",
-        }
-        
-        if self.provider == "minimax":
-            return self._complete_minimax(
-                system_prompt, user_prompt, temperature, max_tokens, headers
-            )
-        elif self.provider == "openai":
-            return self._complete_openai(
-                system_prompt, user_prompt, temperature, max_tokens, headers
-            )
-        else:
-            raise ValueError(f"Unsupported provider: {self.provider}")
-
-    def _complete_minimax(
-        self,
-        system_prompt: str,
-        user_prompt: str,
-        temperature: float,
-        max_tokens: Optional[int],
-        headers: dict,
-    ) -> str:
-        """Call MiniMax API (synchronous)."""
-        minimax_model = self.model.split("/")[-1] if "/" in self.model else self.model
-        
-        payload = {
-            "model": minimax_model,
-            "messages": [
-                {"role": "system", "content": system_prompt},
-                {"role": "user", "content": user_prompt},
-            ],
-            "temperature": temperature,
-        }
-        
-        if max_tokens:
-            payload["max_tokens"] = max_tokens
-        
-        response = requests.post(
-            f"{self.base_url}/text/chatcompletion_v2",
-            headers=headers,
-            json=payload,
-            timeout=120,
-        )
-        response.raise_for_status()
-        
-        data = response.json()
-        
-        if "choices" in data:
-            return data["choices"][0]["message"]["content"]
-        else:
-            raise Exception(f"Unexpected MiniMax response: {data}")
-
-    def _complete_openai(
-        self,
-        system_prompt: str,
-        user_prompt: str,
-        temperature: float,
-        max_tokens: Optional[int],
-        headers: dict,
-    ) -> str:
-        """Call OpenAI API (synchronous)."""
-        payload = {
-            "model": self.model,
-            "messages": [
-                {"role": "system", "content": system_prompt},
-                {"role": "user", "content": user_prompt},
-            ],
-            "temperature": temperature,
-        }
-        
-        if max_tokens:
-            payload["max_tokens"] = max_tokens
-        
-        response = requests.post(
-            f"{self.base_url}/chat/completions",
-            headers=headers,
-            json=payload,
-            timeout=120,
-        )
-        response.raise_for_status()
-        
-        data = response.json()
-        return data["choices"][0]["message"]["content"]
-
-
-# Convenience function
-def get_llm_client(config: Optional[Any] = None) -> LLMClient:
-    """Get an LLM client from config."""
-    from opus_orchestrator.config import get_config
-    
-    cfg = config or get_config()
-    
-    return LLMClient(
-        api_key=cfg.agent.api_key,
-        provider=cfg.agent.provider,
-        model=cfg.agent.model,
-    )

pyproject.toml

@@ -24,6 +24,7 @@ dependencies = [
     "pydantic-ai>=0.0.0",
     "pydantic>=2.0.0",
     "httpx>=0.27.0",
+    "requests>=2.31.0",
     "pygithub>=2.0.0",
     "pyyaml>=6.0",
     "tiktoken>=0.7.0",