feat: initial llm-connect package scaffold

Copy markitect.llm module into standalone llm_connect package.
All markitect.* imports replaced with llm_connect.* equivalents.
LLMError base class inlined (no markitect.exceptions dependency).
Verified: from llm_connect import create_adapter works.

Co-Authored-By: Claude Sonnet 4.6 <noreply@anthropic.com>

llm_connect/models.py

@@ -0,0 +1,86 @@
+"""
+Shared data models for LLM execution.
+
+These classes are the canonical definitions; they are re-exported by
+markitect.prompts.execution.models for backward compatibility.
+"""
+
+from dataclasses import dataclass, field
+from typing import Dict, Any
+
+
+@dataclass
+class RunConfig:
+    """
+    Configuration for prompt execution.
+
+    Attributes:
+        model_name: LLM model to use
+        temperature: Model temperature (0.0-1.0)
+        max_tokens: Maximum tokens to generate
+        model_params: Additional model parameters
+        max_depth: Maximum generation depth for nested runs
+        skip_if_exists: Skip if identical InputBundleHash exists
+        timeout_seconds: Execution timeout
+    """
+    model_name: str = "gpt-4"
+    temperature: float = 0.7
+    max_tokens: int = 2000
+    model_params: Dict[str, Any] = field(default_factory=dict)
+    max_depth: int = 3
+    skip_if_exists: bool = True
+    timeout_seconds: int = 300
+
+    def to_dict(self) -> Dict[str, Any]:
+        """Convert to dictionary."""
+        return {
+            "model_name": self.model_name,
+            "temperature": self.temperature,
+            "max_tokens": self.max_tokens,
+            "model_params": self.model_params,
+            "max_depth": self.max_depth,
+            "skip_if_exists": self.skip_if_exists,
+            "timeout_seconds": self.timeout_seconds,
+        }
+
+    @classmethod
+    def from_dict(cls, data: Dict[str, Any]) -> "RunConfig":
+        """Create from dictionary."""
+        return cls(
+            model_name=data.get("model_name", "gpt-4"),
+            temperature=data.get("temperature", 0.7),
+            max_tokens=data.get("max_tokens", 2000),
+            model_params=data.get("model_params", {}),
+            max_depth=data.get("max_depth", 3),
+            skip_if_exists=data.get("skip_if_exists", True),
+            timeout_seconds=data.get("timeout_seconds", 300),
+        )
+
+
+@dataclass
+class LLMResponse:
+    """
+    Response from LLM execution.
+
+    Attributes:
+        content: Generated content
+        model: Model used
+        usage: Token usage statistics
+        finish_reason: Why generation stopped
+        metadata: Additional response metadata
+    """
+    content: str
+    model: str
+    usage: Dict[str, int] = field(default_factory=dict)
+    finish_reason: str = "stop"
+    metadata: Dict[str, Any] = field(default_factory=dict)
+
+    def to_dict(self) -> Dict[str, Any]:
+        """Convert to dictionary."""
+        return {
+            "content": self.content,
+            "model": self.model,
+            "usage": self.usage,
+            "finish_reason": self.finish_reason,
+            "metadata": self.metadata,
+        }