agilerl 2.7.0.dev0__tar.gz → 2.7.0.dev2__tar.gz

agilerl-2.7.0.dev2/.github/workflows/linux-tests.yml

@@ -0,0 +1,94 @@
+---
+name: Linux
+
+on:
+    push:
+        branches: [main, nightly]
+        paths:
+            - agilerl/**
+            - tests/**
+            - .github/workflows/**
+            - pyproject.toml
+    pull_request:
+        paths:
+            - agilerl/**
+            - tests/**
+            - .github/workflows/**
+            - pyproject.toml
+
+concurrency:
+    group: ${{ github.workflow }}-${{ github.head_ref || github.ref }}
+    cancel-in-progress: true
+
+permissions:
+    contents: read
+
+jobs:
+    tests:
+        runs-on: gha-runner-scale-set
+        strategy:
+            fail-fast: false
+            max-parallel: 4
+            matrix:
+                python-version: ['3.10', '3.11', '3.12', '3.13']
+
+        container:
+            image: pytorch/pytorch:2.7.1-cuda12.6-cudnn9-devel
+            options: --user root
+
+        # Workspace (/__w) is ~1GB with little free space; root (/) has plenty. Put cache and venv on /.
+        env:
+            UV_CACHE_DIR: /tmp/uv-cache
+            UV_PROJECT_ENVIRONMENT: /tmp/agilerl-venv
+            HF_HOME: /tmp/hf-cache
+            TORCHINDUCTOR_CACHE_DIR: /tmp/inductor-cache
+
+        steps:
+            - uses: actions/checkout@v4
+            - uses: astral-sh/setup-uv@v7
+              with:
+                  enable-cache: true
+                  python-version: ${{ matrix.python-version }}
+
+            - name: Cache HuggingFace models
+              uses: actions/cache@v4
+              with:
+                  path: /tmp/hf-cache
+                  key: hf-${{ matrix.python-version }}-${{ hashFiles('pyproject.toml') }}
+                  restore-keys: hf-${{ matrix.python-version }}-
+
+            - name: Cache torch inductor compilations
+              uses: actions/cache@v4
+              with:
+                  path: /tmp/inductor-cache
+                  key: inductor-${{ matrix.python-version }}-${{ hashFiles('pyproject.toml') }}
+                  restore-keys: inductor-${{ matrix.python-version }}-
+
+            - name: Install dependencies
+              # swig is needed to build box2d-py from source (no pre-built wheels for py3.10+).
+              run: |
+                  uv sync --locked --all-groups --extra all
+                  echo "$UV_PROJECT_ENVIRONMENT/bin" >> $GITHUB_PATH
+
+            - name: Reset coverage data
+              run: rm -f .coverage .coverage.*
+
+            # Single phase: `-n auto --dist loadgroup` from pyproject gives 8
+            # workers on the gha-runner-scale-set node. `vllm`- and `gpu`-marked
+            # tests share the 4 `gputest0..gputest3` xdist groups defined in
+            # `tests/conftest.py`, which caps GPU-touching concurrency at 4
+            # workers regardless of -n; the remaining ~4 workers fan out across
+            # CPU-only tests. See the `pytest_collection_modifyitems` docstring
+            # for the GPU-memory and port-race rationale behind the 4-group cap.
+            #
+            # Single invocation = single coverage run; pytest-cov auto-combines
+            # the per-worker `.coverage.*` shards before writing `coverage.xml`,
+            # so we don't need a manual `coverage combine` step (which was
+            # tripping over corrupted shards under the old two-phase setup).
+            - name: Run tests
+              run: uv run pytest --exitfirst --cov=agilerl --cov-report=xml --durations=0 --durations-min=1.0
+
+            - name: Upload coverage reports to Codecov
+              uses: codecov/codecov-action@v3
+              env:
+                  CODECOV_TOKEN: ${{ secrets.CODECOV_TOKEN }}

{agilerl-2.7.0.dev0 → agilerl-2.7.0.dev2}/.github/workflows/macos-tests.yml

@@ -6,10 +6,20 @@ on:
         branches: [main, nightly]
         paths:
             - agilerl/**
+            - tests/**
+            - .github/workflows/**
+            - pyproject.toml
     pull_request:
         branches: [main, nightly]
         paths:
             - agilerl/**
+            - tests/**
+            - .github/workflows/**
+            - pyproject.toml
+
+concurrency:
+    group: ${{ github.workflow }}-${{ github.head_ref || github.ref }}
+    cancel-in-progress: true
 
 permissions:
     contents: read
@@ -32,7 +42,6 @@ jobs:
                   python-version: ${{ matrix.python-version }}
 
             - name: Install dependencies
-              # swig is needed to build box2d-py from source (no pre-built wheels for py3.10+).
               run: |
                   uv sync --locked --all-groups --extra all
 

{agilerl-2.7.0.dev0 → agilerl-2.7.0.dev2}/.github/workflows/windows-tests.yml

@@ -6,10 +6,20 @@ on:
         branches: [main, nightly]
         paths:
             - agilerl/**
+            - tests/**
+            - .github/workflows/**
+            - pyproject.toml
     pull_request:
         branches: [main, nightly]
         paths:
             - agilerl/**
+            - tests/**
+            - .github/workflows/**
+            - pyproject.toml
+
+concurrency:
+    group: ${{ github.workflow }}-${{ github.head_ref || github.ref }}
+    cancel-in-progress: true
 
 permissions:
     contents: read

{agilerl-2.7.0.dev0 → agilerl-2.7.0.dev2}/.gitignore

@@ -109,6 +109,8 @@ celerybeat.pid
 # Environments
 .env
 .vscode/
+.cursor/
+.claude/
 .venv*/
 venv/
 env.bak/
@@ -147,3 +149,7 @@ wandb/
 
 # Cursor
 .cursor
+
+# AI assistant instructions
+CLAUDE.md
+AGENTS.md

{agilerl-2.7.0.dev0 → agilerl-2.7.0.dev2}/.pre-commit-config.yaml

@@ -1,6 +1,9 @@
 ---
 # See https://pre-commit.com for more information
 # See https://pre-commit.com/hooks.html for more hooks
+
+# Vendored binary test fixtures; opaque to every hook here.
+exclude: ^tests/assets/tiny_llm/
 ci:
     autoupdate_branch: nightly
     skip: [codeql-python]
@@ -32,7 +35,7 @@ repos:
                 - --skip=*.css,*.js,*.map,*.scss,*.svg
                 - --ignore-words-list=magent,pres,roate
     - repo: https://github.com/astral-sh/ruff-pre-commit
-      rev: v0.15.10
+      rev: v0.15.12
       hooks:
           - id: ruff
             name: Ruff Linter
@@ -47,7 +50,7 @@ repos:
 
     - repo: https://github.com/astral-sh/uv-pre-commit
       # uv version.
-      rev: 0.11.6
+      rev: 0.11.8
       hooks:
           - id: uv-lock
 

{agilerl-2.7.0.dev0 → agilerl-2.7.0.dev2}/PKG-INFO

@@ -1,6 +1,6 @@
 Metadata-Version: 2.4
 Name: agilerl
-Version: 2.7.0.dev0
+Version: 2.7.0.dev2
 Summary: AgileRL is a deep reinforcement learning library focused on improving RL development through RLOps.
 Author-email: Nick Ustaran-Anderegg <dev@agilerl.com>
 License-Expression: Apache-2.0

{agilerl-2.7.0.dev0 → agilerl-2.7.0.dev2}/agilerl/__init__.py

@@ -16,6 +16,19 @@ def get_extra_dependencies(package: str, extra: str) -> list[str]:
     return deps
 
 
+def _is_dist_installed(dist_name: str) -> bool:
+    """Check if a distribution is installed by its PyPI name.
+
+    Uses distribution metadata instead of find_spec because PyPI names
+    can differ from import names.
+    """
+    try:
+        metadata(dist_name)
+        return True
+    except PackageNotFoundError:
+        return False
+
+
 LLM_PACKAGES = get_extra_dependencies("agilerl", "llm")
 
 

{agilerl-2.7.0.dev0 → agilerl-2.7.0.dev2}/agilerl/algorithms/__init__.py

@@ -33,8 +33,12 @@ __all__ = [
 ]
 
 if HAS_LLM_DEPENDENCIES:
+    from .cispo import CISPO
     from .dpo import DPO
     from .grpo import GRPO
+    from .gspo import GSPO
+    from .ppo_llm import PPO as LLMPPO
+    from .reinforce_llm import REINFORCE as LLMREINFORCE
     from .sft import SFT
 
-    __all__ += ["DPO", "GRPO", "SFT"]
+    __all__ += ["CISPO", "DPO", "GRPO", "GSPO", "LLMPPO", "LLMREINFORCE", "SFT"]

agilerl-2.7.0.dev2/agilerl/algorithms/cispo.py

@@ -0,0 +1,26 @@
+"""CISPO algorithm variant built on top of GRPO."""
+
+from __future__ import annotations
+
+from functools import partial
+from typing import Any
+
+from agilerl.algorithms.grpo import GRPO, _signatures_without_loss_type
+
+
+class CISPO(GRPO):
+    """CISPO loss variant of :class:`agilerl.algorithms.grpo.GRPO`
+
+    Paper: https://arxiv.org/abs/2506.13585
+    """
+
+    _init_with_cispo = partial(GRPO.__init__, loss_type="cispo")
+
+    def __init__(self, *args: Any, **kwargs: Any) -> None:
+        """Initialize a CISPO agent with fixed ``loss_type``."""
+        self._init_with_cispo(self, *args, **kwargs)
+
+
+_CISPO_CLASS_SIG, _CISPO_INIT_SIG = _signatures_without_loss_type()
+CISPO.__signature__ = _CISPO_CLASS_SIG
+CISPO.__init__.__signature__ = _CISPO_INIT_SIG