tessen 0.1.0

Drop-in runtime capture for AI agents. Two lines to install. Logs every LLM call (Anthropic, OpenAI, Google Gemini, Cohere, Mistral) to local JSONL. MIT.

tessen

Drop-in runtime capture for AI agents. Two lines to install. Every LLM call your agent makes — full request, full response with thinking decoded, cache-token usage, call site, timing — written as JSONL to local disk.

import tessen
tessen.init(agent_name="my_agent")

That's the entire integration. Drop it before you construct your LLM client. Every call from every supported SDK is intercepted.

Install

pip install tessen
# or, if you want the optional log viewer
pip install "tessen[viewer]"

The core install has zero hard dependencies. Tessen only patches vendor SDKs that are already importable in your process — install whichever you actually use.

What gets captured

SDK	what's intercepted
Anthropic (anthropic)	messages.create, messages.stream, async equivalents, batches API, and stream=True iterator returns (tee'd transparently)
OpenAI (openai)	chat.completions.create, responses.create, legacy completions.create, sync + async
Google Gemini	both google.generativeai (legacy) and google.genai (current), sync + async, streaming
Cohere (cohere)	chat, chat_stream, async
Mistral (mistralai)	chat.complete, chat.stream, async

Streaming responses (both messages.stream(...) context managers and messages.create(..., stream=True) iterators) are tee'd transparently — your code does not change. The captured event records the assembled final message and chunk count.

What an event looks like

{
  "event_id": "...",
  "agent_name": "my_agent",
  "ts": 1715630400.123,
  "provider": "anthropic",
  "surface": "create",
  "duration_ms": 842.1,
  "request": { "model": "claude-...", "system": "...", "messages": [...], "tools": [...] },
  "response": { "content": [ {"type": "thinking", ...}, {"type": "tool_use", ...} ],
                "stop_reason": "tool_use",
                "usage": { "input_tokens": 512, "output_tokens": 128,
                           "cache_read_input_tokens": 256,
                           "cache_creation_input_tokens": 64 } },
  "call_site": { "file": "/path/to/your/agent.py", "line": 84, "func": "step" },
  "status": "ok"
}

Why

You cannot debug an agent you cannot see. Most observability tools capture the model call as a span on a metrics pipeline. Tessen captures the call as a forensic record — thinking deltas, tool blocks, stop reasons, cache hits, retries — at the depth needed to actually investigate why an agent failed.

• request: model, system, full messages, full tools schema, max_tokens, thinking config, sampling params
• response: every content block (text, thinking, tool_use, tool_result), stop_reason, stop_sequence, message id, model returned
• usage: input_tokens, output_tokens, cache_read_input_tokens, cache_creation_input_tokens — so you can see what the model actually paid for
• call_site: file path + line number + function name of the caller, with /tessen/ and vendor-SDK frames skipped so you land on your code
• timing: duration_ms wall-clock
• errors: exception type, message, and full traceback if the call raised
• streaming: streamed: true + chunks_captured + assembled final message

Where logs live

~/.tessen/logs/{agent_name}/{YYYY-MM-DD}.jsonl. Override with tessen.init(log_dir=...). Files rotate at 100 MB.

python -m tessen.viewer ~/.tessen/logs/my_agent/2026-05-13.jsonl

Overhead

The wrapper is a thin function call around the original SDK method. The write goes through a thread-locked append + fsync(). Real-world overhead is well under 1 ms per call.

Frameworks

Tessen patches at the resource-class level (anthropic.resources.messages.Messages.create, etc.), so framework wrappers — LangChain ChatAnthropic, LangGraph nodes, deepagents, OpenAI Agents SDK with an Anthropic adapter — all flow through Tessen automatically.

Privacy

The SDK runs in your process. There is no network call from Tessen. You bring your own API keys; we never see them. Your code, your data, your machine.

License

MIT. Vendor it, ship it, modify it.

---

tessen.dev · [e-mail]