refactor: thread release config through lead path (#2612)

Co-authored-by: greatmengqi <chenmengqi.0376@bytedance.com>

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

@@ -18,7 +18,7 @@ from deerflow.agents.middlewares.tool_error_handling_middleware import build_lea
 from deerflow.agents.middlewares.view_image_middleware import ViewImageMiddleware
 from deerflow.agents.thread_state import ThreadState
 from deerflow.config.agents_config import load_agent_config, validate_agent_name
-from deerflow.config.app_config import get_app_config
+from deerflow.config.app_config import AppConfig, get_app_config
 from deerflow.config.memory_config import get_memory_config
 from deerflow.config.summarization_config import get_summarization_config
 from deerflow.models import create_chat_model
@@ -35,9 +35,9 @@ def _get_runtime_config(config: RunnableConfig) -> dict:
     return cfg
 
 
-def _resolve_model_name(requested_model_name: str | None = None) -> str:
+def _resolve_model_name(requested_model_name: str | None = None, *, app_config: AppConfig | 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()
+    app_config = app_config or get_app_config()
     default_model_name = app_config.models[0].name if app_config.models else None
     if default_model_name is None:
         raise ValueError("No chat models are configured. Please configure at least one model in config.yaml.")
@@ -50,7 +50,7 @@ def _resolve_model_name(requested_model_name: str | None = None) -> str:
     return default_model_name
 
 
-def _create_summarization_middleware() -> DeerFlowSummarizationMiddleware | None:
+def _create_summarization_middleware(*, app_config: AppConfig | None = None) -> DeerFlowSummarizationMiddleware | None:
     """Create and configure the summarization middleware from config."""
     config = get_summarization_config()
 
@@ -73,9 +73,9 @@ def _create_summarization_middleware() -> DeerFlowSummarizationMiddleware | None
     # as middleware rather than lead_agent (SummarizationMiddleware is a
     # LangChain built-in, so we tag the model at creation time).
     if config.model_name:
-        model = create_chat_model(name=config.model_name, thinking_enabled=False)
+        model = create_chat_model(name=config.model_name, thinking_enabled=False, app_config=app_config)
     else:
-        model = create_chat_model(thinking_enabled=False)
+        model = create_chat_model(thinking_enabled=False, app_config=app_config)
     model = model.with_config(tags=["middleware:summarize"])
 
     # Prepare kwargs
@@ -99,7 +99,8 @@ def _create_summarization_middleware() -> DeerFlowSummarizationMiddleware | None
     # the sole entry point for DeerFlowSummarizationMiddleware, and the runtime
     # config is not expected to change after startup.
     try:
-        skills_container_path = get_app_config().skills.container_path or "/mnt/skills"
+        resolved_app_config = app_config or get_app_config()
+        skills_container_path = resolved_app_config.skills.container_path or "/mnt/skills"
     except Exception:
         logger.exception("Failed to resolve skills container path; falling back to default")
         skills_container_path = "/mnt/skills"
@@ -240,7 +241,14 @@ Being proactive with task management demonstrates thoroughness and ensures all r
 # ViewImageMiddleware should be before ClarificationMiddleware to inject image details before LLM
 # ToolErrorHandlingMiddleware should be before ClarificationMiddleware to convert tool exceptions to ToolMessages
 # ClarificationMiddleware should be last to intercept clarification requests after model calls
-def _build_middlewares(config: RunnableConfig, model_name: str | None, agent_name: str | None = None, custom_middlewares: list[AgentMiddleware] | None = None):
+def _build_middlewares(
+    config: RunnableConfig,
+    model_name: str | None,
+    agent_name: str | None = None,
+    custom_middlewares: list[AgentMiddleware] | None = None,
+    *,
+    app_config: AppConfig | None = None,
+):
     """Build middleware chain based on runtime configuration.
 
     Args:
@@ -252,9 +260,10 @@ def _build_middlewares(config: RunnableConfig, model_name: str | None, agent_nam
         List of middleware instances.
     """
     middlewares = build_lead_runtime_middlewares(lazy_init=True)
+    resolved_app_config = app_config or get_app_config()
 
     # Add summarization middleware if enabled
-    summarization_middleware = _create_summarization_middleware()
+    summarization_middleware = _create_summarization_middleware(app_config=resolved_app_config)
     if summarization_middleware is not None:
         middlewares.append(summarization_middleware)
 
@@ -266,7 +275,7 @@ def _build_middlewares(config: RunnableConfig, model_name: str | None, agent_nam
         middlewares.append(todo_list_middleware)
 
     # Add TokenUsageMiddleware when token_usage tracking is enabled
-    if get_app_config().token_usage.enabled:
+    if resolved_app_config.token_usage.enabled:
         middlewares.append(TokenUsageMiddleware())
 
     # Add TitleMiddleware
@@ -277,13 +286,12 @@ def _build_middlewares(config: RunnableConfig, model_name: str | None, agent_nam
 
     # Add ViewImageMiddleware only if the current model supports vision.
     # Use the resolved runtime model_name from make_lead_agent to avoid stale config values.
-    app_config = get_app_config()
-    model_config = app_config.get_model_config(model_name) if model_name else None
+    model_config = resolved_app_config.get_model_config(model_name) if model_name else None
     if model_config is not None and model_config.supports_vision:
         middlewares.append(ViewImageMiddleware())
 
     # Add DeferredToolFilterMiddleware to hide deferred tool schemas from model binding
-    if app_config.tool_search.enabled:
+    if resolved_app_config.tool_search.enabled:
         from deerflow.agents.middlewares.deferred_tool_filter_middleware import DeferredToolFilterMiddleware
 
         middlewares.append(DeferredToolFilterMiddleware())
@@ -306,12 +314,13 @@ def _build_middlewares(config: RunnableConfig, model_name: str | None, agent_nam
     return middlewares
 
 
-def make_lead_agent(config: RunnableConfig):
+def make_lead_agent(config: RunnableConfig, app_config: AppConfig | None = None):
     # Lazy import to avoid circular dependency
     from deerflow.tools import get_available_tools
     from deerflow.tools.builtins import setup_agent
 
     cfg = _get_runtime_config(config)
+    resolved_app_config = app_config or get_app_config()
 
     thinking_enabled = cfg.get("thinking_enabled", True)
     reasoning_effort = cfg.get("reasoning_effort", None)
@@ -327,10 +336,9 @@ def make_lead_agent(config: RunnableConfig):
     agent_model_name = agent_config.model if agent_config and agent_config.model else None
 
     # Final model name resolution: request → agent config → global default, with fallback for unknown names
-    model_name = _resolve_model_name(requested_model_name or agent_model_name)
+    model_name = _resolve_model_name(requested_model_name or agent_model_name, app_config=resolved_app_config)
 
-    app_config = get_app_config()
-    model_config = app_config.get_model_config(model_name)
+    model_config = resolved_app_config.get_model_config(model_name)
 
     if model_config is None:
         raise ValueError("No chat model could be resolved. Please configure at least one model in config.yaml or provide a valid 'model_name'/'model' in the request.")
@@ -369,20 +377,34 @@ def make_lead_agent(config: RunnableConfig):
     if is_bootstrap:
         # Special bootstrap agent with minimal prompt for initial custom agent creation flow
         return create_agent(
-            model=create_chat_model(name=model_name, thinking_enabled=thinking_enabled),
-            tools=get_available_tools(model_name=model_name, subagent_enabled=subagent_enabled) + [setup_agent],
-            middleware=_build_middlewares(config, model_name=model_name),
-            system_prompt=apply_prompt_template(subagent_enabled=subagent_enabled, max_concurrent_subagents=max_concurrent_subagents, available_skills=set(["bootstrap"])),
+            model=create_chat_model(name=model_name, thinking_enabled=thinking_enabled, app_config=resolved_app_config),
+            tools=get_available_tools(model_name=model_name, subagent_enabled=subagent_enabled, app_config=resolved_app_config) + [setup_agent],
+            middleware=_build_middlewares(config, model_name=model_name, app_config=resolved_app_config),
+            system_prompt=apply_prompt_template(
+                subagent_enabled=subagent_enabled,
+                max_concurrent_subagents=max_concurrent_subagents,
+                available_skills=set(["bootstrap"]),
+                app_config=resolved_app_config,
+            ),
             state_schema=ThreadState,
         )
 
     # Default lead agent (unchanged behavior)
     return create_agent(
-        model=create_chat_model(name=model_name, thinking_enabled=thinking_enabled, reasoning_effort=reasoning_effort),
-        tools=get_available_tools(model_name=model_name, groups=agent_config.tool_groups if agent_config else None, subagent_enabled=subagent_enabled),
-        middleware=_build_middlewares(config, model_name=model_name, agent_name=agent_name),
+        model=create_chat_model(name=model_name, thinking_enabled=thinking_enabled, reasoning_effort=reasoning_effort, app_config=resolved_app_config),
+        tools=get_available_tools(
+            model_name=model_name,
+            groups=agent_config.tool_groups if agent_config else None,
+            subagent_enabled=subagent_enabled,
+            app_config=resolved_app_config,
+        ),
+        middleware=_build_middlewares(config, model_name=model_name, agent_name=agent_name, app_config=resolved_app_config),
         system_prompt=apply_prompt_template(
-            subagent_enabled=subagent_enabled, max_concurrent_subagents=max_concurrent_subagents, agent_name=agent_name, available_skills=set(agent_config.skills) if agent_config and agent_config.skills is not None else None
+            subagent_enabled=subagent_enabled,
+            max_concurrent_subagents=max_concurrent_subagents,
+            agent_name=agent_name,
+            available_skills=set(agent_config.skills) if agent_config and agent_config.skills is not None else None,
+            app_config=resolved_app_config,
         ),
         state_schema=ThreadState,
     )

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

@@ -1,14 +1,20 @@
+from __future__ import annotations
+
 import asyncio
 import logging
 import threading
 from datetime import datetime
 from functools import lru_cache
+from typing import TYPE_CHECKING
 
 from deerflow.config.agents_config import load_agent_soul
 from deerflow.skills import load_skills
 from deerflow.skills.types import Skill
 from deerflow.subagents import get_available_subagent_names
 
+if TYPE_CHECKING:
+    from deerflow.config.app_config import AppConfig
+
 logger = logging.getLogger(__name__)
 
 _ENABLED_SKILLS_REFRESH_WAIT_TIMEOUT_SECONDS = 5.0
@@ -111,6 +117,19 @@ def _get_enabled_skills():
     return []
 
 
+def _get_enabled_skills_for_config(app_config: AppConfig | None = None) -> list[Skill]:
+    """Return enabled skills using the caller's config source.
+
+    When a concrete ``app_config`` is supplied, bypass the global enabled-skills
+    cache so the skill list and skill paths are resolved from the same config
+    object. This keeps request-scoped config injection consistent even while the
+    release branch still supports global fallback paths.
+    """
+    if app_config is None:
+        return _get_enabled_skills()
+    return list(load_skills(enabled_only=True, app_config=app_config))
+
+
 def _skill_mutability_label(category: str) -> str:
     return "[custom, editable]" if category == "custom" else "[built-in]"
 
@@ -576,14 +595,14 @@ You have access to skills that provide optimized workflows for specific tasks. E
 </skill_system>"""
 
 
-def get_skills_prompt_section(available_skills: set[str] | None = None) -> str:
+def get_skills_prompt_section(available_skills: set[str] | None = None, *, app_config: AppConfig | None = None) -> str:
     """Generate the skills prompt section with available skills list."""
-    skills = _get_enabled_skills()
+    skills = _get_enabled_skills_for_config(app_config)
 
     try:
         from deerflow.config import get_app_config
 
-        config = get_app_config()
+        config = app_config or get_app_config()
         container_base_path = config.skills.container_path
         skill_evolution_enabled = config.skill_evolution.enabled
     except Exception:
@@ -612,7 +631,7 @@ def get_agent_soul(agent_name: str | None) -> str:
     return ""
 
 
-def get_deferred_tools_prompt_section() -> str:
+def get_deferred_tools_prompt_section(*, app_config: AppConfig | None = None) -> str:
     """Generate <available-deferred-tools> block for the system prompt.
 
     Lists only deferred tool names so the agent knows what exists
@@ -624,7 +643,8 @@ def get_deferred_tools_prompt_section() -> str:
     try:
         from deerflow.config import get_app_config
 
-        if not get_app_config().tool_search.enabled:
+        config = app_config or get_app_config()
+        if not config.tool_search.enabled:
             return ""
     except Exception:
         return ""
@@ -657,12 +677,13 @@ def _build_acp_section() -> str:
     )
 
 
-def _build_custom_mounts_section() -> str:
+def _build_custom_mounts_section(*, app_config: AppConfig | None = None) -> str:
     """Build a prompt section for explicitly configured sandbox mounts."""
     try:
         from deerflow.config import get_app_config
 
-        mounts = get_app_config().sandbox.mounts or []
+        config = app_config or get_app_config()
+        mounts = config.sandbox.mounts or []
     except Exception:
         logger.exception("Failed to load configured sandbox mounts for the lead-agent prompt")
         return ""
@@ -679,7 +700,14 @@ def _build_custom_mounts_section() -> str:
     return f"\n**Custom Mounted Directories:**\n{mounts_list}\n- If the user needs files outside `/mnt/user-data`, use these absolute container paths directly when they match the requested directory"
 
 
-def apply_prompt_template(subagent_enabled: bool = False, max_concurrent_subagents: int = 3, *, agent_name: str | None = None, available_skills: set[str] | None = None) -> str:
+def apply_prompt_template(
+    subagent_enabled: bool = False,
+    max_concurrent_subagents: int = 3,
+    *,
+    agent_name: str | None = None,
+    available_skills: set[str] | None = None,
+    app_config: AppConfig | None = None,
+) -> str:
     # Get memory context
     memory_context = _get_memory_context(agent_name)
 
@@ -706,14 +734,14 @@ def apply_prompt_template(subagent_enabled: bool = False, max_concurrent_subagen
     )
 
     # Get skills section
-    skills_section = get_skills_prompt_section(available_skills)
+    skills_section = get_skills_prompt_section(available_skills, app_config=app_config)
 
     # Get deferred tools section (tool_search)
-    deferred_tools_section = get_deferred_tools_prompt_section()
+    deferred_tools_section = get_deferred_tools_prompt_section(app_config=app_config)
 
     # Build ACP agent section only if ACP agents are configured
     acp_section = _build_acp_section()
-    custom_mounts_section = _build_custom_mounts_section()
+    custom_mounts_section = _build_custom_mounts_section(app_config=app_config)
     acp_and_mounts_section = "\n".join(section for section in (acp_section, custom_mounts_section) if section)
 
     # Format the prompt with dynamic skills and memory