feat: parallel loop running based on asyncio (#932)

* refactor: split workflow into pkg, add WorkflowTracker & wait_retry

* feat: add async LoopBase with parallel workers and step semaphores

* fix: replace pickle with dill and run blocking tasks via joblib wrapper

* feat: add log format settings, dynamic parallelism & pickle-based snapshot

* fix: default step semaphore to 1 and avoid subprocess when single worker

* merge bowen's changes

* merge tim's changes

* refactor: extract component task mapping, add conditional logger setup

* lint

* refactor: add type hints and safer remain_time metric logging in workflow

* lint

* fix: allow BadRequestError to be pickled via custom copyreg reducer

* fix: stop loop when LoopTerminationError is raised in LoopBase

* lint

* refactor: make log tag context-local using ContextVar for thread safety

* feat: add subproc_step flag and helper to decide subprocess execution

* fix: use ./cache path and normalize relative volume bind paths

* fix: reset loop_idx to 0 on loop restart/resume to ensure correct flow

* fix: avoid chmod on cache and input dirs in Env timeout wrapper

* fix: skip chmod on 'cache' and 'input' dirs using find -prune

* fix: restrict chmod to immediate mount dirs excluding cache/input

* fix: chmod cache and input dirs alongside their contents after entry run

* fix: guard chmod with directory checks for cache and input

* fix: prefix mount_path in chmod command for cache/input dirs

* fix: drop quotes from find exclude patterns to ensure chmod executes

* fix: skip chmod on cache/input directories to avoid warning spam

* feat: support string volume mappings and poll subprocess stdout/stderr

* support remove symbolic link

* test: use dynamic home path and code volume in LocalEnv local_simple

* fix: skip trace and progress update when loop step is withdrawn

* refactor: add clean_workspace util and non-destructive workspace backup

* fix: preserve symlinks when backing up workspace with copytree

* fix: prevent AttributeError when _pbar not yet initialized in LoopBase

* perf: replace shutil.copytree with rsync for faster workspace backup

* fix: cast log directory Path to str in tar command of data science loop

* fix: use portable 'cp -r -P' instead of rsync for workspace backup

* fix: add retry and logging to workspace backup for robustness

* refactor: extract backup_folder helper and reuse in DataScienceRDLoop

* fix: propagate backup errors & default _pbar getattr to avoid error

* fix the division by zero bug

* refactor: execute RD loops via asyncio.run and add necessary imports

* lint

* lint

* lint

---------

Co-authored-by: Xu <v-xuminrui@microsoft.com>

rdagent/core/conf.py

@@ -78,5 +78,24 @@ class RDAgentSettings(ExtendedBaseSettings):
 
     initial_fator_library_size: int = 20
 
+    # parallel loop
+    step_semaphore: int | dict[str, int] = 1
+    """the semaphore for each step;  you can specify a overall semaphore
+    or a step-wise semaphore like {"coding": 3, "running": 2}"""
+
+    def get_max_parallel(self) -> int:
+        """Based on the setting of semaphore, return the maximum number of parallel loops"""
+        if isinstance(self.step_semaphore, int):
+            return self.step_semaphore
+        else:
+            return max(self.step_semaphore.values())
+
+    # NOTE: for debug
+    # the following function only serves as debugging and is necessary in main logic.
+    subproc_step: bool = False
+
+    def is_force_subproc(self) -> bool:
+        return self.subproc_step or self.get_max_parallel() > 1
+
 
 RD_AGENT_SETTINGS = RDAgentSettings()

rdagent/core/proposal.py

@@ -2,14 +2,19 @@
 
 from __future__ import annotations
 
+import asyncio
 from abc import ABC, abstractmethod
-from typing import Generic, List, Tuple, TypeVar
+from typing import TYPE_CHECKING, Generic, List, Tuple, TypeVar
 
+from rdagent.core.conf import RD_AGENT_SETTINGS
 from rdagent.core.evaluation import Feedback
 from rdagent.core.experiment import ASpecificExp, Experiment
 from rdagent.core.knowledge_base import KnowledgeBase
 from rdagent.core.scenario import Scenario
 
+if TYPE_CHECKING:
+    from rdagent.utils.workflow.loop import LoopBase
+
 
 class Hypothesis:
     """
@@ -248,6 +253,17 @@ class ExpGen(ABC):
             )
         """
 
+    async def async_gen(self, trace: Trace, loop: LoopBase) -> Experiment:
+        """
+        generate the experiment and decide whether to stop yield generation and give up control to other routines.
+        """
+        # we give a default implementation here.
+        # The proposal is set to try best to generate the experiment in max-parallel level.
+        while True:
+            if loop.get_unfinished_loop_cnt(loop.loop_idx) < RD_AGENT_SETTINGS.get_max_parallel():
+                return self.gen(trace)
+            await asyncio.sleep(1)
+
 
 class HypothesisGen(ABC):