torina 0.1.2

Trace ingestion client for Torina — captures LLM agent traces and forwards them over HTTP.

torina

Captures LLM agent traces and forwards them to Torina. LangChain is the only supported integration for now — more are planned.

Quickstart

1. Create an API key

Create one at app.torina.io/profile?section=api-keys.

2. Install

uv add torina
# or
pip install torina

3. Add instrumentation

import os
import torina

torina.auto_instrument()
torina.init_logger(
    api_key=os.environ["TORINA_API_KEY"],
    project="My Project (Python)",
)

auto_instrument() patches LangChain automatically if it's installed, so every agent.invoke()/.stream() call anywhere in your app gets captured with no per-call-site changes.

Traces go to https://app.torina.io/api/traces by default. Pass endpoint= or set TORINA_ENDPOINT to point at a self-hosted or dev instance instead.

Capturing conversations, agent names, and metadata

These all come from LangChain's own config/create_agent(name=...), no Torina-specific code needed:

agent = create_agent(..., name="weather-agent")  # -> payload["agent_name"]

agent.invoke(
    {"messages": [...]},
    config={
        "configurable": {"thread_id": thread_id},  # -> payload["conversation_id"]
        "metadata": {"user_id": "u_123", "plan": "enterprise"},  # -> payload["metadata"]
    },
)

Manual instrumentation

For control over a specific call site instead of the global patch, TorinaCallbackHandler is available directly (requires langchain-core):

from torina.langchain import TorinaCallbackHandler

agent.invoke({"messages": [...]}, config={"callbacks": [TorinaCallbackHandler()]})

dry_run

torina.init_logger(dry_run=True)  # no api_key or endpoint needed

Traces are logged instead of sent — useful for local testing before you have a real endpoint. Same code path either way; dry_run only swaps the network call for a log line.

Contributing

See CONTRIBUTING.md for local development, the release process, and notes on how traces are structured internally.