Merge branch 'pettingzoo_shared_vf' of https://github.com/MatthewCWeston/rllib_current_attention into pettingzoo_shared_vf

Author: MatthewCWeston

ci/build/build-ray-docker.sh

@@ -14,15 +14,14 @@ CPU_TMP="$(mktemp -d)"
 
 cp -r .whl "${CPU_TMP}/.whl"
 cp docker/ray/Dockerfile "${CPU_TMP}/Dockerfile"
-cp python/requirements_compiled.txt "${CPU_TMP}/."
+cp python/"${CONSTRAINTS_FILE}" "${CPU_TMP}/requirements_compiled.txt"
 
 # Build the image.
 cd "${CPU_TMP}"
 tar --mtime="UTC 2020-01-01" -c -f - . \
     | docker build --progress=plain \
         --build-arg FULL_BASE_IMAGE="$SOURCE_IMAGE" \
         --build-arg WHEEL_PATH=".whl/${WHEEL_NAME}" \
-        --build-arg CONSTRAINTS_FILE="$CONSTRAINTS_FILE" \
         --label "io.ray.ray-version=$RAY_VERSION" \
         --label "io.ray.ray-commit=$RAY_COMMIT" \
         -t "$DEST_IMAGE" -f Dockerfile -

ci/lint/pydoclint-baseline.txt

@@ -192,8 +192,6 @@ python/ray/_private/services.py
     DOC101: Function `start_raylet`: Docstring contains fewer arguments than in function signature.
     DOC107: Function `start_raylet`: The option `--arg-type-hints-in-signature` is `True` but not all args in the signature have type hints
     DOC103: Function `start_raylet`: Docstring arguments are different from function arguments. (Or could be other formatting issues: https://jsh9.github.io/pydoclint/violation_codes.html#notes-on-doc103 ). Arguments in the function signature but not in the docstring: [cluster_id: str, socket_to_use: Optional[int]].
-    DOC101: Function `determine_plasma_store_config`: Docstring contains fewer arguments than in function signature.
-    DOC103: Function `determine_plasma_store_config`: Docstring arguments are different from function arguments. (Or could be other formatting issues: https://jsh9.github.io/pydoclint/violation_codes.html#notes-on-doc103 ). Arguments in the function signature but not in the docstring: [temp_dir: str].
     DOC101: Function `start_monitor`: Docstring contains fewer arguments than in function signature.
     DOC103: Function `start_monitor`: Docstring arguments are different from function arguments. (Or could be other formatting issues: https://jsh9.github.io/pydoclint/violation_codes.html#notes-on-doc103 ). Arguments in the function signature but not in the docstring: [autoscaler_v2: bool, fate_share: Optional[bool]].
     DOC101: Function `start_ray_client_server`: Docstring contains fewer arguments than in function signature.

ci/raydepsets/cli.py

@@ -96,6 +96,15 @@ def __init__(
         check: Optional[bool] = False,
         build_all_configs: Optional[bool] = False,
     ):
+        """Initialize the dependency set manager.
+
+        Args:
+            config_path: Path to the depsets config file.
+            workspace_dir: Path to the workspace directory.
+            uv_cache_dir: Directory to cache uv dependencies.
+            check: Whether to check if lock files are up to date.
+            build_all_configs: Whether to build all configs or just the specified one.
+        """
         self.workspace = Workspace(workspace_dir)
         self.config = self.workspace.load_configs(config_path)
         self.config_name = os.path.basename(config_path)
@@ -109,6 +118,7 @@ def __init__(
             self.copy_to_temp_dir()
 
     def get_output_paths(self) -> List[Path]:
+        """Get all output paths for depset nodes in topological order."""
         output_paths = []
         for node in topological_sort(self.build_graph):
             if self.build_graph.nodes[node]["node_type"] == "depset":
@@ -126,6 +136,7 @@ def copy_to_temp_dir(self):
             )
 
     def get_diffs(self) -> List[str]:
+        """Compare current lock files with previously saved copies and return unified diffs."""
         diffs = []
         for output_path in self.output_paths:
             new_lock_file_fp, old_lock_file_fp = self.get_source_and_dest(output_path)
@@ -142,6 +153,7 @@ def get_diffs(self) -> List[str]:
         return diffs
 
     def diff_lock_files(self):
+        """Check if lock files are up to date and raise an error if not."""
         diffs = self.get_diffs()
         if len(diffs) > 0:
             raise RuntimeError(
@@ -151,9 +163,11 @@ def diff_lock_files(self):
         click.echo("Lock files are up to date.")
 
     def get_source_and_dest(self, output_path: str) -> tuple[Path, Path]:
+        """Get the source workspace path and temporary destination path for a lock file."""
         return (self.get_path(output_path), (Path(self.temp_dir) / output_path))
 
     def _build(self, build_all_configs: Optional[bool] = False):
+        """Build the dependency graph from config depsets."""
         for depset in self.config.depsets:
             if depset.operation == "compile":
                 self.build_graph.add_node(
@@ -201,11 +215,13 @@ def _build(self, build_all_configs: Optional[bool] = False):
             self.subgraph_config_nodes()
 
     def subgraph_dependency_nodes(self, depset_name: str):
+        """Reduce the build graph to only include the specified depset and its ancestors."""
         dependency_nodes = networkx_ancestors(self.build_graph, depset_name)
         nodes = dependency_nodes | {depset_name}
         self.build_graph = self.build_graph.subgraph(nodes).copy()
 
     def subgraph_config_nodes(self):
+        """Reduce the build graph to nodes matching the current config and their ancestors."""
         # Get all nodes that have the target config name
         config_nodes = [
             node
@@ -224,6 +240,7 @@ def subgraph_config_nodes(self):
         self.build_graph = self.build_graph.subgraph(nodes).copy()
 
     def execute(self, single_depset_name: Optional[str] = None):
+        """Execute all depsets in topological order, optionally limited to a single depset."""
         if single_depset_name:
             # check if the depset exists
             _get_depset(self.config.depsets, single_depset_name)
@@ -240,6 +257,7 @@ def execute(self, single_depset_name: Optional[str] = None):
     def exec_uv_cmd(
         self, cmd: str, args: List[str], stdin: Optional[bytes] = None
     ) -> str:
+        """Execute a uv pip command with the given arguments."""
         cmd = [self._uv_binary, "pip", cmd, *args]
         click.echo(f"Executing command: {' '.join(cmd)}")
         status = subprocess.run(
@@ -252,6 +270,7 @@ def exec_uv_cmd(
         return status.stdout.decode("utf-8")
 
     def execute_pre_hook(self, pre_hook: str):
+        """Execute a pre-hook shell command."""
         status = subprocess.run(
             shlex.split(pre_hook),
             cwd=self.workspace.dir,
@@ -265,6 +284,7 @@ def execute_pre_hook(self, pre_hook: str):
         click.echo(f"Executed pre_hook {pre_hook} successfully")
 
     def execute_depset(self, depset: Depset):
+        """Execute a single depset based on its operation type (compile, subset, or expand)."""
         if depset.operation == "compile":
             self.compile(
                 constraints=depset.constraints,
@@ -389,15 +409,18 @@ def expand(
         )
 
     def read_lock_file(self, file_path: Path) -> List[str]:
+        """Read and return the contents of a lock file as a list of lines."""
         if not file_path.exists():
             raise RuntimeError(f"Lock file {file_path} does not exist")
         with open(file_path, "r") as f:
             return f.readlines()
 
     def get_path(self, path: str) -> Path:
+        """Convert a relative path to an absolute path within the workspace."""
         return Path(self.workspace.dir) / path
 
     def check_subset_exists(self, source_depset: Depset, requirements: List[str]):
+        """Verify that all requirements exist in the source depset."""
         for req in requirements:
             if req not in self.get_expanded_depset_requirements(source_depset.name, []):
                 raise RuntimeError(
@@ -424,15 +447,18 @@ def get_expanded_depset_requirements(
         return list(set(requirements_list))
 
     def cleanup(self):
+        """Remove the temporary directory used for lock file comparisons."""
         if self.temp_dir:
             shutil.rmtree(self.temp_dir)
 
 
 def _get_bytes(packages: List[str]) -> bytes:
+    """Convert a list of package names to newline-separated UTF-8 bytes."""
     return ("\n".join(packages) + "\n").encode("utf-8")
 
 
 def _get_depset(depsets: List[Depset], name: str) -> Depset:
+    """Find and return a depset by name from a list of depsets."""
     for depset in depsets:
         if depset.name == name:
             return depset
@@ -452,6 +478,7 @@ def _flatten_flags(flags: List[str]) -> List[str]:
 
 
 def _override_uv_flags(flags: List[str], args: List[str]) -> List[str]:
+    """Override existing uv flags in args with new values from flags."""
     flag_names = {f.split()[0] for f in flags if f.startswith("--")}
     new_args = []
     skip_next = False
@@ -468,6 +495,7 @@ def _override_uv_flags(flags: List[str], args: List[str]) -> List[str]:
 
 
 def _uv_binary():
+    """Get the path to the uv binary for the current platform."""
     r = runfiles.Create()
     system = platform.system()
     processor = platform.processor()

ci/raydepsets/configs/rayimg.depsets.yaml

@@ -8,13 +8,16 @@ build_arg_sets:
   py312:
     PYTHON_VERSION: "3.12"
     PYTHON_SHORT: "312"
+  py313:
+    PYTHON_VERSION: "3.13"
+    PYTHON_SHORT: "313"
 
 depsets:
   - name: ray_img_depset_${PYTHON_SHORT}
     requirements:
-      - release/ray_release/byod/ray_dev.in
+      - python/deplocks/ray_img/ray_dev.in
     constraints:
-      - /tmp/ray-deps/requirements_compiled.txt
+      - /tmp/ray-deps/requirements_compiled_py${PYTHON_VERSION}.txt
     output: python/deplocks/ray_img/ray_img_py${PYTHON_SHORT}.lock
     operation: compile
     append_flags:
@@ -25,9 +28,10 @@ depsets:
       - py310
       - py311
       - py312
+      - py313
     pre_hooks:
       - ci/raydepsets/pre_hooks/build-placeholder-wheel.sh
-      - ci/raydepsets/pre_hooks/remove-compiled-headers.sh
+      - ci/raydepsets/pre_hooks/remove-compiled-headers.sh ${PYTHON_VERSION}
 
   - name: ray_base_extra_testdeps_${PYTHON_SHORT}
     operation: expand
@@ -36,7 +40,7 @@ depsets:
       - docker/base-deps/requirements.in
       - docker/base-extra/requirements.in
     constraints:
-      - /tmp/ray-deps/requirements_compiled.txt
+      - /tmp/ray-deps/requirements_compiled_py${PYTHON_VERSION}.txt
     depsets:
       - ray_img_depset_${PYTHON_SHORT}
     output: release/ray_release/byod/ray_base_extra_testdeps_py${PYTHON_VERSION}.lock
@@ -48,6 +52,7 @@ depsets:
       - py310
       - py311
       - py312
+      - py313
 
   - name: ray_base_extra_testdeps_cuda_${PYTHON_SHORT}
     operation: expand
@@ -56,7 +61,7 @@ depsets:
       - docker/base-deps/requirements.in
       - docker/base-extra/requirements.in
     constraints:
-      - /tmp/ray-deps/requirements_compiled.txt
+      - /tmp/ray-deps/requirements_compiled_py${PYTHON_VERSION}.txt
     depsets:
       - ray_img_depset_${PYTHON_SHORT}
     output: release/ray_release/byod/ray_base_extra_testdeps_cuda_py${PYTHON_VERSION}.lock
@@ -69,6 +74,7 @@ depsets:
       - py310
       - py311
       - py312
+      - py313
 
   - name: ray_base_extra_testdeps_gpu_${PYTHON_SHORT}
     operation: expand
@@ -77,7 +83,7 @@ depsets:
       - docker/base-deps/requirements.in
       - docker/base-extra/requirements.in
     constraints:
-      - /tmp/ray-deps/requirements_compiled.txt
+      - /tmp/ray-deps/requirements_compiled_py${PYTHON_VERSION}.txt
     depsets:
       - ray_img_depset_${PYTHON_SHORT}
     output: release/ray_release/byod/ray_base_extra_testdeps_gpu_py${PYTHON_VERSION}.lock
@@ -96,7 +102,7 @@ depsets:
       - docker/base-deps/requirements.in
       - docker/base-extra/requirements.in
     constraints:
-      - /tmp/ray-deps/requirements_compiled.txt
+      - /tmp/ray-deps/requirements_compiled_py${PYTHON_VERSION}.txt
     depsets:
       - ray_img_depset_${PYTHON_SHORT}
     output: release/ray_release/byod/ray_ml_base_extra_testdeps_py${PYTHON_VERSION}.lock
@@ -114,7 +120,7 @@ depsets:
       - docker/base-deps/requirements.in
       - docker/base-extra/requirements.in
     constraints:
-      - /tmp/ray-deps/requirements_compiled.txt
+      - /tmp/ray-deps/requirements_compiled_py${PYTHON_VERSION}.txt
     depsets:
       - ray_img_depset_${PYTHON_SHORT}
     output: release/ray_release/byod/ray_ml_base_extra_testdeps_cuda_py${PYTHON_VERSION}.lock
@@ -142,6 +148,7 @@ depsets:
       - py310
       - py311
       - py312
+      - py313
     include_setuptools: true
 
     # Second layer of the ray release images. Contains anyscale cli deps (and others)
@@ -161,3 +168,4 @@ depsets:
       - py310
       - py311
       - py312
+      - py313

ci/raydepsets/pre_hooks/remove-compiled-headers.sh

@@ -2,9 +2,17 @@
 
 set -euo pipefail
 
+PYTHON_VERSION=${1:-}
+
+if [[ -z "${PYTHON_VERSION}" ]]; then
+    FILENAME="requirements_compiled.txt"
+else
+    FILENAME="requirements_compiled_py${PYTHON_VERSION}.txt"
+fi
+
 mkdir -p /tmp/ray-deps
 
 # Remove the GPU constraints
-cp python/requirements_compiled.txt /tmp/ray-deps/requirements_compiled.txt
-sed -e '/^--extra-index-url /d' -e '/^--find-links /d' /tmp/ray-deps/requirements_compiled.txt > /tmp/ray-deps/requirements_compiled.txt.tmp
-mv /tmp/ray-deps/requirements_compiled.txt.tmp /tmp/ray-deps/requirements_compiled.txt
+cp "python/${FILENAME}" "/tmp/ray-deps/${FILENAME}"
+sed -e '/^--extra-index-url /d' -e '/^--find-links /d' "/tmp/ray-deps/${FILENAME}" > "/tmp/ray-deps/${FILENAME}.tmp"
+mv "/tmp/ray-deps/${FILENAME}.tmp" "/tmp/ray-deps/${FILENAME}"

cpp/src/ray/runtime/object/native_object_store.cc

@@ -76,14 +76,37 @@ void NativeObjectStore::CheckException(const std::string &meta_str,
     throw RayWorkerException(std::move(data_str));
   } else if (meta_str == std::to_string(ray::rpc::ErrorType::ACTOR_DIED)) {
     throw RayActorException(std::move(data_str));
-  } else if (meta_str == std::to_string(ray::rpc::ErrorType::OBJECT_UNRECONSTRUCTABLE) ||
-             meta_str == std::to_string(ray::rpc::ErrorType::OBJECT_LOST) ||
-             meta_str == std::to_string(ray::rpc::ErrorType::OWNER_DIED) ||
-             meta_str == std::to_string(ray::rpc::ErrorType::OBJECT_DELETED)) {
-    // TODO: Differentiate object errors.
-    throw UnreconstructableException(std::move(data_str));
   } else if (meta_str == std::to_string(ray::rpc::ErrorType::TASK_EXECUTION_EXCEPTION)) {
     throw RayTaskException(std::move(data_str));
+  } else if (meta_str == std::to_string(ray::rpc::ErrorType::OBJECT_LOST) ||
+             meta_str == std::to_string(ray::rpc::ErrorType::OWNER_DIED) ||
+             meta_str == std::to_string(ray::rpc::ErrorType::OBJECT_DELETED) ||
+             meta_str ==
+                 std::to_string(ray::rpc::ErrorType::OBJECT_UNRECONSTRUCTABLE_PUT) ||
+             meta_str ==
+                 std::to_string(
+                     ray::rpc::ErrorType::OBJECT_UNRECONSTRUCTABLE_RETRIES_DISABLED) ||
+             meta_str ==
+                 std::to_string(
+                     ray::rpc::ErrorType::OBJECT_UNRECONSTRUCTABLE_LINEAGE_EVICTED) ||
+             meta_str ==
+                 std::to_string(ray::rpc::ErrorType::
+                                    OBJECT_UNRECONSTRUCTABLE_MAX_ATTEMPTS_EXCEEDED) ||
+             meta_str ==
+                 std::to_string(ray::rpc::ErrorType::OBJECT_UNRECONSTRUCTABLE_BORROWED) ||
+             meta_str == std::to_string(
+                             ray::rpc::ErrorType::OBJECT_UNRECONSTRUCTABLE_LOCAL_MODE) ||
+             meta_str ==
+                 std::to_string(
+                     ray::rpc::ErrorType::OBJECT_UNRECONSTRUCTABLE_REF_NOT_FOUND) ||
+             meta_str ==
+                 std::to_string(
+                     ray::rpc::ErrorType::OBJECT_UNRECONSTRUCTABLE_TASK_CANCELLED) ||
+             meta_str ==
+                 std::to_string(
+                     ray::rpc::ErrorType::OBJECT_UNRECONSTRUCTABLE_LINEAGE_DISABLED)) {
+    // TODO: Differentiate object error
+    throw UnreconstructableException(std::move(data_str));
   }
 }
 

cpp/src/ray/util/process_helper.cc

@@ -114,16 +114,12 @@ void ProcessHelper::RayStart(CoreWorkerOptions::TaskExecutionCallback callback)
     ConfigInternal::Instance().plasma_store_socket_name =
         node_info.object_store_socket_name();
     ConfigInternal::Instance().node_manager_port = node_info.node_manager_port();
+    ConfigInternal::Instance().UpdateSessionDir(node_info.session_dir());
   }
   RAY_CHECK(!ConfigInternal::Instance().raylet_socket_name.empty());
   RAY_CHECK(!ConfigInternal::Instance().plasma_store_socket_name.empty());
   RAY_CHECK(ConfigInternal::Instance().node_manager_port > 0);
 
-  if (ConfigInternal::Instance().worker_type == WorkerType::DRIVER) {
-    auto session_dir = *global_state_accessor->GetInternalKV("session", "session_dir");
-    ConfigInternal::Instance().UpdateSessionDir(session_dir);
-  }
-
   gcs::GcsClientOptions gcs_options =
       gcs::GcsClientOptions(bootstrap_ip,
                             bootstrap_port,