mirror of
https://github.com/open-thought/reasoning-gym.git
synced 2025-10-09 13:40:09 +03:00
* feat: Add initial server structure with configuration, registry, and middleware * feat: Add chain_sum dataset to experiment registry test * fix: Update test_registry to use DatasetSpec for composite config validation * refactor: Update Pydantic config to use json_schema_extra and ConfigDict * feat: Add Pydantic models for API request/response data * feat: Implement basic experiment management endpoints with tests * feat: Implement composite configuration endpoints for experiments * fix: Add missing DatasetConfigUpdate import in server.py * refactor: Update dataset config update method to properly merge config updates * fix: Correctly retrieve current dataset config in composite endpoint * feat: Add basic CLI structure with experiments and config commands * feat: Add initial CLI tool with basic experiment management commands * refactor: Reorganize CLI package structure and fix import paths * refactor: Implement initial CLI commands for experiment management * feat: Implement HTTP client for Reasoning Gym server in RGC CLI tool * fix: Move print statements inside try block to resolve SyntaxError * fix: Resolve SyntaxError in edit_config function by adding missing except block * feat: Add default app instance in server module for easier uvicorn startup * docs: Add README.md with server and RGC tool documentation * remove unused files * refactor: Remove unsupported type annotation in registry.py * refactor: Move ExperimentRegistry to coaching module and add Experiment class * fix: Add missing CompositeDataset import in test_registry.py * refactor: Implement lazy ASGI app creation for server initialization * feat: Add health check command to RGC CLI for server connection * feat: Add version tracking support to CompositeDataset * feat: Add DatasetVersionManager for tracking dataset versions * feat: Add entry_id metadata and score_answer_with_id method to CompositeDataset * feat: Add entry_id metadata combining version and index * fix: Resolve undefined variable by storing version_id before use * test: Add comprehensive unit tests for score_answer_with_id() function * test: Add comprehensive version tracking test for dataset config updates * feat: Validate dataset weights are positive in CompositeDataset initialization * feat: Add weight update and normalization methods to CompositeDataset * refactor: Centralize weight normalization in CompositeDataset and allow zero-weight datasets * feat: Add negative weight validation to CompositeDataset constructor * feat: Add duplicate dataset name check in CompositeDataset and update test * refactor: Move duplicate dataset name check inside dataset iteration loop * refactor: Update CompositeDataset weight management to use config as source of truth * refactor: Move duplicate dataset name check to CompositeConfig.validate() * test: Update composite dataset weight test assertions and validation * feat: Add methods to add and remove datasets in CompositeDataset * refactor: Remove weight normalization and use unnormalized weights directly * refactor: Remove redundant total weight check in update_dataset_weights * feat: Add batch generation and scoring endpoints to server * fix: Import BatchEntry in server.py to resolve undefined name error * refactor: Update ReasoningGymDataset to use server for batch generation and scoring * fix: Add missing List and Dict type imports * feat: Add get_batch() and score_outputs() methods to RGClient * test: Add unit tests for generate_batch and score_outputs endpoints * refactor: Add DatasetVersionManager to Experiment class and CompositeDataset constructor * feat: Add validation for base_index and batch_size in generate_batch endpoint * refactor: Remove unused BatchRequest type from imports * refactor: Convert models to use Pydantic exclusively * test: Update scoring endpoint tests to use correct request model format * refactor: Rename ScoreItem to AnswerItem and update related code * feat: Update scoring endpoint to return ordered ScoringResponse with scores and entry_ids * fix: Add missing ScoringResponse import in server.py * move verl ppo sample with server into own file * refactor: Use Pydantic models for get_batch() and score_outputs() in RGClient * refactor: Update client methods to use Pydantic models for type safety * refactor: Use Pydantic models for experiment and dataset config operations * refactor: Clean up duplicate methods and improve error handling in main.py * first bits of rg server use for verl * refactor: Optimize scoring with single HTTP request in _score_output * fix: Correct experiment creation with ExperimentCreate object * grpo tests with server
1.5 KiB
1.5 KiB
Reasoning Gym Tools
This directory contains additional tools for working with Reasoning Gym:
Server
A FastAPI server that manages reasoning gym experiments, allowing runtime configuration and monitoring.
Starting the Server
- Install server dependencies:
pip install -e ".[server]"
- Set the API key environment variable:
export REASONING_GYM_API_KEY=your-secret-key
- Start the server:
uvicorn tools.server.server:app
The server will be available at http://localhost:8000. You can access the API documentation at http://localhost:8000/docs.
RGC (Reasoning Gym Client)
A command-line interface for interacting with the Reasoning Gym server.
Installation
pip install -e ".[cli]"
Usage
First, set the API key to match your server:
export REASONING_GYM_API_KEY=your-secret-key
Then you can use the CLI:
# List all commands
rgc --help
# List experiments
rgc experiments list
# Create a new experiment interactively
rgc experiments create my-experiment
# Create from config file
rgc experiments create my-experiment -f config.yaml
# Show experiment details
rgc experiments show my-experiment
# Edit dataset configuration
rgc config edit my-experiment chain_sum
Example Configuration File
Here's an example config.yaml for creating an experiment:
size: 500
seed: 42
datasets:
chain_sum:
weight: 1.0
config:
min_terms: 2
max_terms: 4
min_digits: 1
max_digits: 2
allow_negation: false