langchain-debug-bundle

# LangChain Debug Bundle

## Overview
Collect comprehensive debug information for LangChain issues including traces, versions, and reproduction steps.

## Prerequisites
- LangChain installed
- Reproducible error condition
- Access to logs and environment

## Instructions

### Step 1: Collect Environment Info
```python
# debug_bundle.py
import sys
import platform
import subprocess

def collect_environment():
    """Collect system and package information."""
    info = {
        "python_version": sys.version,
        "platform": platform.platform(),
        "packages": {}
    }

    # Get LangChain package versions
    packages = [
        "langchain",
        "langchain-core",
        "langchain-community",
        "langchain-openai",
        "langchain-anthropic",
        "openai",
        "anthropic"
    ]

    for pkg in packages:
        try:
            result = subprocess.run(
                [sys.executable, "-m", "pip", "show", pkg],
                capture_output=True, text=True
            )
            for line in result.stdout.split("\n"):
                if line.startswith("Version:"):
                    info["packages"][pkg] = line.split(":")[1].strip()
        except:
            info["packages"][pkg] = "not installed"

    return info

print(collect_environment())
```

### Step 2: Enable Full Tracing
```python
import os
import langchain

# Enable debug mode
langchain.debug = True

# Enable LangSmith tracing (if available)
os.environ["LANGCHAIN_TRACING_V2"] = "true"
os.environ["LANGCHAIN_PROJECT"] = "debug-session"

# Custom callback for logging
from langchain_core.callbacks import BaseCallbackHandler
from datetime import datetime

class DebugCallback(BaseCallbackHandler):
    def __init__(self):
        self.logs = []

    def on_llm_start(self, serialized, prompts, **kwargs):
        self.logs.append({
            "event": "llm_start",
            "time": datetime.now().isoformat(),
            "prompts": prompts
        })

    def on_llm_end(self,