langsmith-tracing

LangSmith Tracing Plugin for Claude Code

A Claude Code plugin that traces conversations, tool calls, subagent executions, and context compaction to LangSmith.

Prerequisites

• Node.js v18+

Installation

As a Claude Code plugin

From within Claude Code, run:

/plugin marketplace add langchain-ai/langsmith-claude-code-plugins
/plugin install langsmith-tracing@langsmith-claude-code-plugins
/reload-plugins

To update, run:

/plugin marketplace update langsmith-claude-code-plugins
/reload-plugins

As a Claude Cowork plugin

Claude Cowork runs Claude Code in a sandboxed VM, thus the plugin needs to be added separately.

1. Allow network egress for LANGSMITH_CC_ENDPOINT (eg. https://api.smith.langchain.com) or for all domains
2. Add langchain-ai/langsmith-claude-code-plugins marketplace in Customize > Personal Plugins (+) > Create Plugin > Add Marketplace
3. Edit each of the Claude Code hooks by prepending LangSmith Claude Code environment variables to command of every hook. Watch video to see step-by-step.

https://github.com/user-attachments/assets/1d44b30f-e0a8-4173-b60b-97a2d1fb95c5

[!IMPORTANT] Make sure that 'Allow network egress' is either enabled for all domains or enabled for LANGSMITH_CC_ENDPOINT, otherwise Cowork might freeze.

From source (development)

pnpm install
pnpm build
claude --plugin-dir /path/to/langsmith-claude-code-plugins

Setting environment variables

Option 1: Claude Code settings file (recommended)

Add the following to a .claude/settings.local.json file in your project folder or ~/.claude/settings.json globally:

{
  "env": {
    "TRACE_TO_LANGSMITH": "true",
    "CC_LANGSMITH_API_KEY": "lsv2_pt_...",
    "CC_LANGSMITH_PROJECT": "my-project"
  }
}

Option 2: Export to shell

Add to your ~/.zshrc, ~/.bashrc, or ~/.bash_profile:

export TRACE_TO_LANGSMITH="true"
export CC_LANGSMITH_API_KEY="lsv2_pt_..."
export CC_LANGSMITH_PROJECT="my-project"

Getting your LangSmith API key

1. Go to smith.langchain.com
2. Sign in or create an account
3. Navigate to Settings → API Keys
4. Click Create API Key
5. Copy the key (starts with lsv2_pt_...)

What gets traced

Each LLM run includes:

• Inputs: accumulated conversation messages
• Outputs: assistant response content
• Metadata: ls_provider: "anthropic", ls_model_name, ls_invocation_params (model, stop reason), token usage

All runs (LLM, tool, turn, subagent) automatically include identity metadata so you can attribute traces in LangSmith:

• anthropic_user_id — read from the userID field in ~/.claude.json (the Claude Code installation's stable hashed user ID). Omitted if the file is missing or unreadable.
• local_username — the local OS username from os.userInfo().

To override either field, supply your own value via CC_LANGSMITH_METADATA — user-supplied keys always win.

Tool runs include the tool name, inputs, and output content.

Interrupted turns (where the user cancels mid-response) are marked with status "interrupted" in LangSmith.

Environment variables

The plugin respects the following environment variables: