mirror of
https://github.com/open-thought/reasoning-gym.git
synced 2026-04-19 12:58:07 +00:00
e2702092f4
* 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
84 lines
1.7 KiB
TOML
84 lines
1.7 KiB
TOML
[build-system]
|
|
requires = ["hatchling"]
|
|
build-backend = "hatchling.build"
|
|
|
|
[project]
|
|
name = "reasoning_gym"
|
|
version = "0.1.8"
|
|
authors = [
|
|
{ name = "Open-Thought community", email = "andreas.koepf@xamla.com" },
|
|
]
|
|
description = "A library of procedural dataset generators for training reasoning models"
|
|
readme = "README.md"
|
|
requires-python = ">=3.11"
|
|
dependencies = [
|
|
"bfi==1.0.4",
|
|
"cellpylib==2.4.0",
|
|
"sympy>=1.13.1",
|
|
"magiccube==0.3.0",
|
|
"pycosat==0.6.6",
|
|
"pyfiglet==1.0.2",
|
|
"pytz>=2024.1",
|
|
"tabulate==0.9.0",
|
|
"pyyaml>=6.0.2",
|
|
"arckit==0.1.0",
|
|
]
|
|
classifiers = [
|
|
"Programming Language :: Python :: 3",
|
|
"License :: OSI Approved :: Apache Software License",
|
|
"Operating System :: OS Independent",
|
|
]
|
|
license = "Apache-2.0"
|
|
license-files = ["LICENSE*"]
|
|
|
|
[project.optional-dependencies]
|
|
test = [
|
|
"pytest>=7.0.0",
|
|
"pytest-cov>=4.0.0",
|
|
"httpx>=0.27.0"
|
|
]
|
|
server = [
|
|
"fastapi>=0.109.0",
|
|
"uvicorn>=0.27.0",
|
|
"pydantic-settings>=2.1.0",
|
|
]
|
|
cli = [
|
|
"typer>=0.9.0",
|
|
"rich>=13.7.0",
|
|
"pyyaml>=6.0.1",
|
|
"httpx>=0.27.0",
|
|
]
|
|
|
|
[project.urls]
|
|
"Homepage" = "https://github.com/open-thought/reasoning-gym"
|
|
"Bug Tracker" = "https://github.com/open-thought/reasoning-gym/issues"
|
|
|
|
|
|
[tool.hatch.build]
|
|
packages = [
|
|
"reasoning_gym",
|
|
"tools.cli.rgc"
|
|
]
|
|
include = [
|
|
"reasoning_gym/**/*.py",
|
|
"reasoning_gym/**/*.txt",
|
|
"reasoning_gym/**/levels/*",
|
|
"tools/cli/rgc/**/*.py"
|
|
]
|
|
|
|
[project.scripts]
|
|
rgc = "tools.cli.rgc.main:main"
|
|
|
|
[tool.black]
|
|
line-length = 120
|
|
target-version = ['py312']
|
|
include = '\.pyi?$'
|
|
|
|
[tool.isort]
|
|
profile = "black"
|
|
multi_line_output = 3
|
|
line_length = 120
|
|
|
|
[tool.pytest.ini_options]
|
|
addopts = "-ra -q"
|
|
testpaths = ["tests"]
|