feat: add LangSmith tracing integration (#878)

* feat: add LangSmith tracing integration

Add optional LangSmith tracing support that can be enabled via environment
variables (LANGSMITH_TRACING, LANGSMITH_API_KEY, LANGSMITH_PROJECT,
LANGSMITH_ENDPOINT). When enabled, a LangChainTracer callback is attached
to chat models and run metadata is injected for trace tagging.

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

* Update backend/src/config/tracing_config.py

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

* Update backend/src/agents/lead_agent/agent.py

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

* Update backend/src/agents/lead_agent/agent.py

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

* Update backend/src/models/factory.py

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

* Add threading lock to ensure thread-safe access to tracing configuration

---------

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

backend/src/agents/lead_agent/agent.py

@@ -245,6 +245,17 @@ def make_lead_agent(config: RunnableConfig):
     subagent_enabled = config.get("configurable", {}).get("subagent_enabled", False)
     max_concurrent_subagents = config.get("configurable", {}).get("max_concurrent_subagents", 3)
     print(f"thinking_enabled: {thinking_enabled}, model_name: {model_name}, is_plan_mode: {is_plan_mode}, subagent_enabled: {subagent_enabled}, max_concurrent_subagents: {max_concurrent_subagents}")
+    
+    # Inject run metadata for LangSmith trace tagging
+    if "metadata" not in config:
+        config["metadata"] = {}
+    config["metadata"].update({
+        "model_name": model_name or "default",
+        "thinking_enabled": thinking_enabled,
+        "is_plan_mode": is_plan_mode,
+        "subagent_enabled": subagent_enabled,
+    })
+    
     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),

backend/src/config/__init__.py

@@ -2,6 +2,7 @@ from .app_config import get_app_config
 from .extensions_config import ExtensionsConfig, get_extensions_config
 from .memory_config import MemoryConfig, get_memory_config
 from .skills_config import SkillsConfig
+from .tracing_config import get_tracing_config, is_tracing_enabled
 
 __all__ = [
     "get_app_config",
@@ -10,4 +11,6 @@ __all__ = [
     "get_extensions_config",
     "MemoryConfig",
     "get_memory_config",
+    "get_tracing_config",
+    "is_tracing_enabled",
 ]

backend/src/config/tracing_config.py

@@ -0,0 +1,51 @@
+import logging
+import os
+from pydantic import BaseModel, Field
+import threading
+
+logger = logging.getLogger(__name__)
+_config_lock = threading.Lock()
+
+class TracingConfig(BaseModel):
+    """Configuration for LangSmith tracing."""
+
+    enabled: bool = Field(...)
+    api_key: str | None = Field(...)
+    project: str = Field(...)
+    endpoint: str = Field(...)
+
+    @property
+    def is_configured(self) -> bool:
+        """Check if tracing is fully configured (enabled and has API key)."""
+        return self.enabled and bool(self.api_key)
+
+
+_tracing_config: TracingConfig | None = None
+
+
+def get_tracing_config() -> TracingConfig:
+    """Get the current tracing configuration from environment variables.
+    Returns:
+        TracingConfig with current settings.
+    """
+    global _tracing_config
+    if _tracing_config is not None:
+        return _tracing_config
+    with _config_lock:
+        if _tracing_config is not None:  # Double-check after acquiring lock
+            return _tracing_config
+        _tracing_config = TracingConfig(
+            enabled=os.environ.get("LANGSMITH_TRACING", "").lower() == "true",
+            api_key=os.environ.get("LANGSMITH_API_KEY"),
+            project=os.environ.get("LANGSMITH_PROJECT", "deer-flow"),
+            endpoint=os.environ.get("LANGSMITH_ENDPOINT", "https://api.smith.langchain.com"),
+        )
+        return _tracing_config
+    
+def is_tracing_enabled() -> bool:
+    """Check if LangSmith tracing is enabled and configured.
+    Returns:
+        True if tracing is enabled and has an API key.
+    """
+    return get_tracing_config().is_configured
+

backend/src/models/factory.py

@@ -1,8 +1,10 @@
+import logging
 from langchain.chat_models import BaseChatModel
 
-from src.config import get_app_config
+from src.config import get_app_config, get_tracing_config, is_tracing_enabled
 from src.reflection import resolve_class
 
+logger = logging.getLogger(__name__)
 
 def create_chat_model(name: str | None = None, thinking_enabled: bool = False, **kwargs) -> BaseChatModel:
     """Create a chat model instance from the config.
@@ -37,4 +39,20 @@ def create_chat_model(name: str | None = None, thinking_enabled: bool = False, *
             raise ValueError(f"Model {name} does not support thinking. Set `supports_thinking` to true in the `config.yaml` to enable thinking.") from None
         model_settings_from_config.update(model_config.when_thinking_enabled)
     model_instance = model_class(**kwargs, **model_settings_from_config)
+
+    if is_tracing_enabled():
+        try:
+            from langchain_core.tracers.langchain import LangChainTracer
+
+            tracing_config = get_tracing_config()
+            tracer = LangChainTracer(
+                project_name=tracing_config.project,
+            )
+            existing_callbacks = model_instance.callbacks or []
+            model_instance.callbacks = [*existing_callbacks, tracer]
+            logger.debug(
+                f"LangSmith tracing attached to model '{name}' (project='{tracing_config.project}')"
+            )
+        except Exception as e:
+            logger.warning(f"Failed to attach LangSmith tracing to model '{name}': {e}")
     return model_instance