Metadata-Version: 2.4
Name: summitsdk
Version: 0.1.0
Summary: Instrumentation layer for multi-agent AI pipelines
Home-page: https://cronys.xyz/summit
Author: Shaz Hussain
Author-email: shaz@cronys.xyz
Classifier: Programming Language :: Python :: 3
Classifier: License :: OSI Approved :: MIT License
Classifier: Operating System :: OS Independent
Requires-Python: >=3.8
Description-Content-Type: text/markdown
License-File: LICENSE
Requires-Dist: anthropic
Provides-Extra: openai
Requires-Dist: openai; extra == "openai"
Dynamic: author
Dynamic: author-email
Dynamic: classifier
Dynamic: description
Dynamic: description-content-type
Dynamic: home-page
Dynamic: license-file
Dynamic: provides-extra
Dynamic: requires-dist
Dynamic: requires-python
Dynamic: summary

# MARL

Simulation and evaluation environment for
Summit by Cronys.

## Structure

sim/        Planner, Worker, Judge agents
eval/       Reward model evaluator
improve.py  Single-pass improvement loop
cycle.py    Automated multi-cycle runner
marlsdk/    summitsdk package source
data/       Traces and evaluation results

## Usage

```python
from anthropic import Anthropic
from marlsdk.tracer import Tracer
from marlsdk.exporters.local import LocalExporter

exporter = LocalExporter(output_dir="traces/")
tracer = Tracer(exporter=exporter)

client = Anthropic()
wrapped = tracer.wrap_anthropic(
    client,
    from_agent="planner",
    to_agent="worker",
    task_id="task-001",
    round_trip=1
)

response = wrapped.messages.create(
    model="claude-sonnet-4-20250514",
    max_tokens=1024,
    messages=[{"role": "user", "content": "your prompt"}]
)
# trace written automatically to traces/
```

OpenAI: use tracer.wrap_openai(client, ...)
with the same arguments.
