fix(task): remove max_turns parameter from task tool interface (#2783)

* fix(task): remove max_turns parameter from task tool interface

Subagents should always use their configured max_turns value. Exposing
this parameter allowed callers to override the admin-configured limit,
which is undesirable. The value is now exclusively driven by subagent
config (per-agent overrides and global defaults in config.yaml).

Co-Authored-By: Claude Sonnet 4.6 <noreply@anthropic.com>

* Potential fix for pull request finding

Co-authored-by: Copilot Autofix powered by AI <175728472+Copilot@users.noreply.github.com>

---------

Co-authored-by: Claude Sonnet 4.6 <noreply@anthropic.com>
Co-authored-by: Willem Jiang <willem.jiang@gmail.com>
Co-authored-by: Copilot Autofix powered by AI <175728472+Copilot@users.noreply.github.com>

backend/CLAUDE.md

@@ -266,7 +266,7 @@ Proxied through nginx: `/api/langgraph/*` → LangGraph, all other `/api/*` →
    - `setup_agent` - Bootstrap-only: persist a brand-new custom agent's `SOUL.md` and `config.yaml`. Bound only when `is_bootstrap=True`.
    - `update_agent` - Custom-agent-only: persist self-updates to the current agent's `SOUL.md` / `config.yaml` from inside a normal chat (partial update + atomic write). Bound when `agent_name` is set and `is_bootstrap=False`.
 4. **Subagent tool** (if enabled):
-   - `task` - Delegate to subagent (description, prompt, subagent_type, max_turns)
+   - `task` - Delegate to subagent (description, prompt, subagent_type)
 
 **Community tools** (`packages/harness/deerflow/community/`):
 - `tavily/` - Web search (5 results default) and web fetch (4KB limit)

backend/packages/harness/deerflow/tools/builtins/task_tool.py

@@ -54,7 +54,6 @@ async def task_tool(
     prompt: str,
     subagent_type: str,
     tool_call_id: Annotated[str, InjectedToolCallId],
-    max_turns: int | None = None,
 ) -> str:
     """Delegate a task to a specialized subagent that runs in its own context.
 
@@ -90,7 +89,6 @@ async def task_tool(
         description: A short (3-5 word) description of the task for logging/display. ALWAYS PROVIDE THIS PARAMETER FIRST.
         prompt: The task description for the subagent. Be specific and clear about what needs to be done. ALWAYS PROVIDE THIS PARAMETER SECOND.
         subagent_type: The type of subagent to use. ALWAYS PROVIDE THIS PARAMETER THIRD.
-        max_turns: Optional maximum number of agent turns. Defaults to subagent's configured max.
     """
     runtime_app_config = _get_runtime_app_config(runtime)
     available_subagent_names = get_available_subagent_names(app_config=runtime_app_config) if runtime_app_config is not None else get_available_subagent_names()
@@ -112,9 +110,6 @@ async def task_tool(
     # each subagent loads its own skills based on config, injected as conversation items).
     # No longer appended to system_prompt here.
 
-    if max_turns is not None:
-        overrides["max_turns"] = max_turns
-
     # Extract parent context from runtime
     sandbox_state = None
     thread_data = None

backend/tests/test_task_tool_core_logic.py

@@ -221,7 +221,6 @@ def test_task_tool_emits_running_and_completed_events(monkeypatch):
         prompt="collect diagnostics",
         subagent_type="general-purpose",
         tool_call_id="tc-123",
-        max_turns=7,
     )
 
     assert output == "Task Succeeded. Result: all done"
@@ -229,7 +228,7 @@ def test_task_tool_emits_running_and_completed_events(monkeypatch):
     assert captured["task_id"] == "tc-123"
     assert captured["executor_kwargs"]["thread_id"] == "thread-1"
     assert captured["executor_kwargs"]["parent_model"] == "ark-model"
-    assert captured["executor_kwargs"]["config"].max_turns == 7
+    assert captured["executor_kwargs"]["config"].max_turns == config.max_turns
     # Skills are no longer appended to system_prompt; they are loaded per-session
     # by SubagentExecutor and injected as conversation items (Codex pattern).
     assert captured["executor_kwargs"]["config"].system_prompt == "Base system prompt"