wanwu/deer-flow
1
0
Fork 0
mirror of https://gitee.com/wanwujie/deer-flow synced 2026-04-25 07:04:44 +08:00
Code Issues Packages Projects Releases Wiki Activity

feat: make max concurrent subagents configurable via runtime config

Browse Source 
Support configuring max_concurrent_subagents (2-4, default 3) through
config.configurable, with automatic clamping and dynamic prompt generation.

Co-Authored-By: Claude Opus 4.6 <noreply@anthropic.com>
This commit is contained in:
hetao
2026-02-11 11:41:30 +08:00
parent 4a85c5de7b
commit 770d92fe36
5 changed files with 75 additions and 52 deletions
Download Patch File Download Diff File Expand all files Collapse all files

30
backend/src/agents/middlewares/subagent_limit_middleware.py
View File

@@ -11,15 +11,32 @@ from src.subagents.executor import MAX_CONCURRENT_SUBAGENTS
logger = logging.getLogger(__name__)
# Valid range for max_concurrent_subagents
MIN_SUBAGENT_LIMIT = 2
MAX_SUBAGENT_LIMIT = 4
def _clamp_subagent_limit(value: int) -> int:
"""Clamp subagent limit to valid range [2, 4]."""
return max(MIN_SUBAGENT_LIMIT, min(MAX_SUBAGENT_LIMIT, value))
class SubagentLimitMiddleware(AgentMiddleware[AgentState]):
"""Truncates excess 'task' tool calls from a single model response.
When an LLM generates more than MAX_CONCURRENT_SUBAGENTS parallel task tool calls
in one response, this middleware keeps only the first MAX_CONCURRENT_SUBAGENTS and
When an LLM generates more than max_concurrent parallel task tool calls
in one response, this middleware keeps only the first max_concurrent and
discards the rest. This is more reliable than prompt-based limits.
Args:
max_concurrent: Maximum number of concurrent subagent calls allowed.
Defaults to MAX_CONCURRENT_SUBAGENTS (3). Clamped to [2, 4].
"""
def __init__(self, max_concurrent: int = MAX_CONCURRENT_SUBAGENTS):
super().__init__()
self.max_concurrent = _clamp_subagent_limit(max_concurrent)
def _truncate_task_calls(self, state: AgentState) -> dict | None:
messages = state.get("messages", [])
if not messages:
@@ -35,18 +52,15 @@ class SubagentLimitMiddleware(AgentMiddleware[AgentState]):
# Count task tool calls
task_indices = [i for i, tc in enumerate(tool_calls) if tc.get("name") == "task"]
if len(task_indices) <= MAX_CONCURRENT_SUBAGENTS:
if len(task_indices) <= self.max_concurrent:
return None
# Build set of indices to drop (excess task calls beyond the limit)
indices_to_drop = set(task_indices[MAX_CONCURRENT_SUBAGENTS:])
indices_to_drop = set(task_indices[self.max_concurrent :])
truncated_tool_calls = [tc for i, tc in enumerate(tool_calls) if i not in indices_to_drop]
dropped_count = len(indices_to_drop)
logger.warning(
f"Truncated {dropped_count} excess task tool call(s) from model response "
f"(limit: {MAX_CONCURRENT_SUBAGENTS})"
)
logger.warning(f"Truncated {dropped_count} excess task tool call(s) from model response (limit: {self.max_concurrent})")
# Replace the AIMessage with truncated tool_calls (same id triggers replacement)
updated_msg = last_msg.model_copy(update={"tool_calls": truncated_tool_calls})