fix: queue concurrent subagents (#5566)

* fix: queue concurrent subagents

* chore: keep spawn schema concise

nanobot/agent/subagent.py

@@ -55,7 +55,8 @@ class SubagentStatus:
     label: str
     task_description: str
     started_at: float          # time.monotonic()
-    phase: str = "initializing"  # initializing | awaiting_tools | tools_completed | final_response | done | error
+    # queued | initializing | awaiting_tools | tools_completed | final_response | done | error
+    phase: str = "initializing"
     iteration: int = 0
     tool_events: list[dict[str, str]] = field(default_factory=list)
     usage: LLMUsage | None = None
@@ -147,6 +148,7 @@ class SubagentManager:
             if max_concurrent_subagents is not None
             else defaults.max_concurrent_subagents
         )
+        self._run_slots = asyncio.Semaphore(self.max_concurrent_subagents)
         self.runner = AgentRunner()
         self._exec_session_manager = ExecSessionManager()
         self._llm_wall_timeout_for_session = llm_wall_timeout_for_session
@@ -363,6 +365,35 @@ class SubagentManager:
         workspace_scope: WorkspaceScope | None = None,
         *,
         announce: bool = True,
+    ) -> str:
+        """Wait for capacity, then execute one subagent task."""
+        status.phase = "queued"
+        async with self._run_slots:
+            status.phase = "initializing"
+            return await self._run_admitted_subagent(
+                task_id,
+                task,
+                label,
+                origin,
+                status,
+                runtime,
+                origin_message_id,
+                workspace_scope,
+                announce=announce,
+            )
+
+    async def _run_admitted_subagent(
+        self,
+        task_id: str,
+        task: str,
+        label: str,
+        origin: _SubagentOrigin,
+        status: SubagentStatus,
+        runtime: LLMRuntime,
+        origin_message_id: str | None = None,
+        workspace_scope: WorkspaceScope | None = None,
+        *,
+        announce: bool = True,
     ) -> str:
         """Execute the subagent task and announce the result."""
         logger.info("Subagent [{}] starting task: {}", task_id, label)

nanobot/agent/tools/spawn.py

@@ -73,6 +73,11 @@ class SpawnTool(Tool):
             "and use a dedicated subdirectory when helpful."
         )
 
+    @property
+    def concurrency_safe(self) -> bool:
+        """Each call owns its task state; the manager serializes capacity admission."""
+        return True
+
     async def execute(
         self,
         task: str,
@@ -82,14 +87,6 @@ class SpawnTool(Tool):
         **kwargs: Any,
     ) -> str:
         """Spawn a subagent to execute the given task."""
-        running = self._manager.get_running_count()
-        limit = self._manager.max_concurrent_subagents
-        if running >= limit:
-            return (
-                f"Cannot spawn subagent: concurrency limit reached "
-                f"({running}/{limit} running). Wait for a running subagent "
-                f"to complete before spawning a new one."
-            )
         request_ctx = current_request_context()
         if request_ctx is None or request_ctx.runtime is None:
             return ToolResult.error("Error: spawn requires an active model runtime")

nanobot/config/schema.py

@@ -128,7 +128,7 @@ class AgentDefaults(Base):
     temperature: float = 0.1
     fallback_models: list[FallbackCandidate] = Field(default_factory=list)
     max_tool_iterations: int = 200
-    max_concurrent_subagents: int = Field(default=1, ge=1)
+    max_concurrent_subagents: int = Field(default=4, ge=1)
     max_tool_result_chars: int = 16_000
     provider_retry_mode: Literal["standard", "persistent"] = "standard"
     tool_hint_max_length: int = Field(