fix: read lead agent options from context (#2515)

* fix: read lead agent options from context

* fix: validate runtime context config

backend/app/gateway/services.py

@@ -12,6 +12,7 @@ import json
 import logging
 import re
 import time
+from collections.abc import Mapping
 from typing import Any
 
 from fastapi import HTTPException, Request
@@ -101,9 +102,10 @@ def resolve_agent_factory(assistant_id: str | None):
     """Resolve the agent factory callable from config.
 
     Custom agents are implemented as ``lead_agent`` + an ``agent_name``
-    injected into ``configurable`` — see :func:`build_run_config`.  All
-    ``assistant_id`` values therefore map to the same factory; the routing
-    happens inside ``make_lead_agent`` when it reads ``cfg["agent_name"]``.
+    injected into ``configurable`` or ``context`` — see
+    :func:`build_run_config`.  All ``assistant_id`` values therefore map to the
+    same factory; the routing happens inside ``make_lead_agent`` when it reads
+    ``cfg["agent_name"]``.
     """
     from deerflow.agents.lead_agent.agent import make_lead_agent
 
@@ -120,10 +122,12 @@ def build_run_config(
     """Build a RunnableConfig dict for the agent.
 
     When *assistant_id* refers to a custom agent (anything other than
-    ``"lead_agent"`` / ``None``), the name is forwarded as
-    ``configurable["agent_name"]``.  ``make_lead_agent`` reads this key to
-    load the matching ``agents/<name>/SOUL.md`` and per-agent config —
-    without it the agent silently runs as the default lead agent.
+    ``"lead_agent"`` / ``None``), the name is forwarded as ``agent_name`` in
+    whichever runtime options container is active: ``context`` for
+    LangGraph >= 0.6.0 requests, otherwise ``configurable``.
+    ``make_lead_agent`` reads this key to load the matching
+    ``agents/<name>/SOUL.md`` and per-agent config — without it the agent
+    silently runs as the default lead agent.
 
     This mirrors the channel manager's ``_resolve_run_params`` logic so that
     the LangGraph Platform-compatible HTTP API and the IM channel path behave
@@ -142,7 +146,14 @@ def build_run_config(
                     thread_id,
                     list(request_config.get("configurable", {}).keys()),
                 )
-            config["context"] = request_config["context"]
+            context_value = request_config["context"]
+            if context_value is None:
+                context = {}
+            elif isinstance(context_value, Mapping):
+                context = dict(context_value)
+            else:
+                raise ValueError("request config 'context' must be a mapping or null.")
+            config["context"] = context
         else:
             configurable = {"thread_id": thread_id}
             configurable.update(request_config.get("configurable", {}))
@@ -154,13 +165,19 @@ def build_run_config(
         config["configurable"] = {"thread_id": thread_id}
 
     # Inject custom agent name when the caller specified a non-default assistant.
-    # Honour an explicit configurable["agent_name"] in the request if already set.
-    if assistant_id and assistant_id != _DEFAULT_ASSISTANT_ID and "configurable" in config:
-        if "agent_name" not in config["configurable"]:
-            normalized = assistant_id.strip().lower().replace("_", "-")
-            if not normalized or not re.fullmatch(r"[a-z0-9-]+", normalized):
-                raise ValueError(f"Invalid assistant_id {assistant_id!r}: must contain only letters, digits, and hyphens after normalization.")
-            config["configurable"]["agent_name"] = normalized
+    # Honour an explicit agent_name in the active runtime options container.
+    if assistant_id and assistant_id != _DEFAULT_ASSISTANT_ID:
+        normalized = assistant_id.strip().lower().replace("_", "-")
+        if not normalized or not re.fullmatch(r"[a-z0-9-]+", normalized):
+            raise ValueError(f"Invalid assistant_id {assistant_id!r}: must contain only letters, digits, and hyphens after normalization.")
+        if "configurable" in config:
+            target = config["configurable"]
+        elif "context" in config:
+            target = config["context"]
+        else:
+            target = config.setdefault("configurable", {})
+        if target is not None and "agent_name" not in target:
+            target["agent_name"] = normalized
     if metadata:
         config.setdefault("metadata", {}).update(metadata)
     return config

backend/packages/harness/deerflow/agents/lead_agent/agent.py

@@ -26,6 +26,15 @@ from deerflow.models import create_chat_model
 logger = logging.getLogger(__name__)
 
 
+def _get_runtime_config(config: RunnableConfig) -> dict:
+    """Merge legacy configurable options with LangGraph runtime context."""
+    cfg = dict(config.get("configurable", {}) or {})
+    context = config.get("context", {}) or {}
+    if isinstance(context, dict):
+        cfg.update(context)
+    return cfg
+
+
 def _resolve_model_name(requested_model_name: str | None = None) -> str:
     """Resolve a runtime model name safely, falling back to default if invalid. Returns None if no models are configured."""
     app_config = get_app_config()
@@ -248,7 +257,8 @@ def _build_middlewares(config: RunnableConfig, model_name: str | None, agent_nam
         middlewares.append(summarization_middleware)
 
     # Add TodoList middleware if plan mode is enabled
-    is_plan_mode = config.get("configurable", {}).get("is_plan_mode", False)
+    cfg = _get_runtime_config(config)
+    is_plan_mode = cfg.get("is_plan_mode", False)
     todo_list_middleware = _create_todo_list_middleware(is_plan_mode)
     if todo_list_middleware is not None:
         middlewares.append(todo_list_middleware)
@@ -277,9 +287,9 @@ def _build_middlewares(config: RunnableConfig, model_name: str | None, agent_nam
         middlewares.append(DeferredToolFilterMiddleware())
 
     # Add SubagentLimitMiddleware to truncate excess parallel task calls
-    subagent_enabled = config.get("configurable", {}).get("subagent_enabled", False)
+    subagent_enabled = cfg.get("subagent_enabled", False)
     if subagent_enabled:
-        max_concurrent_subagents = config.get("configurable", {}).get("max_concurrent_subagents", 3)
+        max_concurrent_subagents = cfg.get("max_concurrent_subagents", 3)
         middlewares.append(SubagentLimitMiddleware(max_concurrent=max_concurrent_subagents))
 
     # LoopDetectionMiddleware — detect and break repetitive tool call loops
@@ -299,7 +309,7 @@ def make_lead_agent(config: RunnableConfig):
     from deerflow.tools import get_available_tools
     from deerflow.tools.builtins import setup_agent
 
-    cfg = config.get("configurable", {})
+    cfg = _get_runtime_config(config)
 
     thinking_enabled = cfg.get("thinking_enabled", True)
     reasoning_effort = cfg.get("reasoning_effort", None)

backend/tests/test_gateway_services.py

@@ -145,6 +145,21 @@ def test_build_run_config_explicit_agent_name_not_overwritten():
     assert config["configurable"]["agent_name"] == "explicit-agent"
 
 
+def test_build_run_config_context_custom_agent_injects_agent_name():
+    """Custom assistant_id must be forwarded as context['agent_name'] in context mode."""
+    from app.gateway.services import build_run_config
+
+    config = build_run_config(
+        "thread-1",
+        {"context": {"model_name": "deepseek-v3"}},
+        None,
+        assistant_id="finalis",
+    )
+
+    assert config["context"]["agent_name"] == "finalis"
+    assert "configurable" not in config
+
+
 def test_resolve_agent_factory_returns_make_lead_agent():
     """resolve_agent_factory always returns make_lead_agent regardless of assistant_id."""
     from app.gateway.services import resolve_agent_factory
@@ -298,6 +313,36 @@ def test_build_run_config_with_context():
     assert config["recursion_limit"] == 100
 
 
+def test_build_run_config_null_context_becomes_empty_context():
+    """When caller sends context=null, treat it as an empty context object."""
+    from app.gateway.services import build_run_config
+
+    config = build_run_config("thread-1", {"context": None}, None)
+
+    assert config["context"] == {}
+    assert "configurable" not in config
+
+
+def test_build_run_config_rejects_non_mapping_context():
+    """When caller sends a non-object context, raise a clear error instead of a TypeError."""
+    import pytest
+
+    from app.gateway.services import build_run_config
+
+    with pytest.raises(ValueError, match="context"):
+        build_run_config("thread-1", {"context": "bad-context"}, None)
+
+
+def test_build_run_config_null_context_custom_agent_injects_agent_name():
+    """Custom assistant_id can still be injected when context=null starts context mode."""
+    from app.gateway.services import build_run_config
+
+    config = build_run_config("thread-1", {"context": None}, None, assistant_id="finalis")
+
+    assert config["context"] == {"agent_name": "finalis"}
+    assert "configurable" not in config
+
+
 def test_build_run_config_context_plus_configurable_warns(caplog):
     """When caller sends both 'context' and 'configurable', prefer 'context' and log a warning."""
     import logging

backend/tests/test_lead_agent_model_resolution.py

@@ -113,6 +113,54 @@ def test_make_lead_agent_disables_thinking_when_model_does_not_support_it(monkey
     assert result["model"] is not None
 
 
+def test_make_lead_agent_reads_runtime_options_from_context(monkeypatch):
+    app_config = _make_app_config(
+        [
+            _make_model("default-model", supports_thinking=False),
+            _make_model("context-model", supports_thinking=True),
+        ]
+    )
+
+    import deerflow.tools as tools_module
+
+    get_available_tools = MagicMock(return_value=[])
+    monkeypatch.setattr(lead_agent_module, "get_app_config", lambda: app_config)
+    monkeypatch.setattr(tools_module, "get_available_tools", get_available_tools)
+    monkeypatch.setattr(lead_agent_module, "_build_middlewares", lambda config, model_name, agent_name=None: [])
+
+    captured: dict[str, object] = {}
+
+    def _fake_create_chat_model(*, name, thinking_enabled, reasoning_effort=None):
+        captured["name"] = name
+        captured["thinking_enabled"] = thinking_enabled
+        captured["reasoning_effort"] = reasoning_effort
+        return object()
+
+    monkeypatch.setattr(lead_agent_module, "create_chat_model", _fake_create_chat_model)
+    monkeypatch.setattr(lead_agent_module, "create_agent", lambda **kwargs: kwargs)
+
+    result = lead_agent_module.make_lead_agent(
+        {
+            "context": {
+                "model_name": "context-model",
+                "thinking_enabled": False,
+                "reasoning_effort": "high",
+                "is_plan_mode": True,
+                "subagent_enabled": True,
+                "max_concurrent_subagents": 7,
+            }
+        }
+    )
+
+    assert captured == {
+        "name": "context-model",
+        "thinking_enabled": False,
+        "reasoning_effort": "high",
+    }
+    get_available_tools.assert_called_once_with(model_name="context-model", groups=None, subagent_enabled=True)
+    assert result["model"] is not None
+
+
 def test_make_lead_agent_rejects_invalid_bootstrap_agent_name(monkeypatch):
     app_config = _make_app_config([_make_model("safe-model", supports_thinking=False)])