Merge branch 'main' into rayhpeng/persistence-scaffold

# Conflicts:
#	.env.example
#	backend/packages/harness/deerflow/agents/middlewares/title_middleware.py

backend/packages/harness/deerflow/config/__init__.py

@@ -3,7 +3,13 @@ from .extensions_config import ExtensionsConfig, get_extensions_config
 from .memory_config import MemoryConfig, get_memory_config
 from .paths import Paths, get_paths
 from .skills_config import SkillsConfig
-from .tracing_config import get_tracing_config, is_tracing_enabled
+from .tracing_config import (
+    get_enabled_tracing_providers,
+    get_explicitly_enabled_tracing_providers,
+    get_tracing_config,
+    is_tracing_enabled,
+    validate_enabled_tracing_providers,
+)
 
 __all__ = [
     "get_app_config",
@@ -15,5 +21,8 @@ __all__ = [
     "MemoryConfig",
     "get_memory_config",
     "get_tracing_config",
+    "get_explicitly_enabled_tracing_providers",
+    "get_enabled_tracing_providers",
     "is_tracing_enabled",
+    "validate_enabled_tracing_providers",
 ]

backend/packages/harness/deerflow/config/agents_config.py

@@ -22,6 +22,11 @@ class AgentConfig(BaseModel):
     description: str = ""
     model: str | None = None
     tool_groups: list[str] | None = None
+    # skills controls which skills are loaded into the agent's prompt:
+    # - None (or omitted): load all enabled skills (default fallback behavior)
+    # - [] (explicit empty list): disable all skills
+    # - ["skill1", "skill2"]: load only the specified skills
+    skills: list[str] | None = None
 
 
 def load_agent_config(name: str | None) -> AgentConfig | None:

backend/packages/harness/deerflow/config/app_config.py

@@ -1,5 +1,6 @@
 import logging
 import os
+from contextvars import ContextVar
 from pathlib import Path
 from typing import Any, Self
 
@@ -11,16 +12,16 @@ from deerflow.config.acp_config import load_acp_config_from_dict
 from deerflow.config.checkpointer_config import CheckpointerConfig, load_checkpointer_config_from_dict
 from deerflow.config.database_config import DatabaseConfig
 from deerflow.config.extensions_config import ExtensionsConfig
-from deerflow.config.guardrails_config import load_guardrails_config_from_dict
-from deerflow.config.memory_config import load_memory_config_from_dict
+from deerflow.config.guardrails_config import GuardrailsConfig, load_guardrails_config_from_dict
+from deerflow.config.memory_config import MemoryConfig, load_memory_config_from_dict
 from deerflow.config.model_config import ModelConfig
 from deerflow.config.run_events_config import RunEventsConfig
 from deerflow.config.sandbox_config import SandboxConfig
 from deerflow.config.skills_config import SkillsConfig
 from deerflow.config.stream_bridge_config import StreamBridgeConfig, load_stream_bridge_config_from_dict
-from deerflow.config.subagents_config import load_subagents_config_from_dict
-from deerflow.config.summarization_config import load_summarization_config_from_dict
-from deerflow.config.title_config import load_title_config_from_dict
+from deerflow.config.subagents_config import SubagentsAppConfig, load_subagents_config_from_dict
+from deerflow.config.summarization_config import SummarizationConfig, load_summarization_config_from_dict
+from deerflow.config.title_config import TitleConfig, load_title_config_from_dict
 from deerflow.config.token_usage_config import TokenUsageConfig
 from deerflow.config.tool_config import ToolConfig, ToolGroupConfig
 from deerflow.config.tool_search_config import ToolSearchConfig, load_tool_search_config_from_dict
@@ -30,6 +31,13 @@ load_dotenv()
 logger = logging.getLogger(__name__)
 
 
+def _default_config_candidates() -> tuple[Path, ...]:
+    """Return deterministic config.yaml locations without relying on cwd."""
+    backend_dir = Path(__file__).resolve().parents[4]
+    repo_root = backend_dir.parent
+    return (backend_dir / "config.yaml", repo_root / "config.yaml")
+
+
 class AppConfig(BaseModel):
     """Config for the DeerFlow application"""
 
@@ -42,6 +50,11 @@ class AppConfig(BaseModel):
     skills: SkillsConfig = Field(default_factory=SkillsConfig, description="Skills configuration")
     extensions: ExtensionsConfig = Field(default_factory=ExtensionsConfig, description="Extensions configuration (MCP servers and skills state)")
     tool_search: ToolSearchConfig = Field(default_factory=ToolSearchConfig, description="Tool search / deferred loading configuration")
+    title: TitleConfig = Field(default_factory=TitleConfig, description="Automatic title generation configuration")
+    summarization: SummarizationConfig = Field(default_factory=SummarizationConfig, description="Conversation summarization configuration")
+    memory: MemoryConfig = Field(default_factory=MemoryConfig, description="Memory subsystem configuration")
+    subagents: SubagentsAppConfig = Field(default_factory=SubagentsAppConfig, description="Subagent runtime configuration")
+    guardrails: GuardrailsConfig = Field(default_factory=GuardrailsConfig, description="Guardrail middleware configuration")
     model_config = ConfigDict(extra="allow", frozen=False)
     database: DatabaseConfig = Field(default_factory=DatabaseConfig, description="Unified database backend configuration")
     run_events: RunEventsConfig = Field(default_factory=RunEventsConfig, description="Run event storage configuration")
@@ -55,7 +68,7 @@ class AppConfig(BaseModel):
         Priority:
         1. If provided `config_path` argument, use it.
         2. If provided `DEER_FLOW_CONFIG_PATH` environment variable, use it.
-        3. Otherwise, first check the `config.yaml` in the current directory, then fallback to `config.yaml` in the parent directory.
+        3. Otherwise, search deterministic backend/repository-root defaults from `_default_config_candidates()`.
         """
         if config_path:
             path = Path(config_path)
@@ -68,14 +81,10 @@ class AppConfig(BaseModel):
                 raise FileNotFoundError(f"Config file specified by environment variable `DEER_FLOW_CONFIG_PATH` not found at {path}")
             return path
         else:
-            # Check if the config.yaml is in the current directory
-            path = Path(os.getcwd()) / "config.yaml"
-            if not path.exists():
-                # Check if the config.yaml is in the parent directory of CWD
-                path = Path(os.getcwd()).parent / "config.yaml"
-                if not path.exists():
-                    raise FileNotFoundError("`config.yaml` file not found at the current directory nor its parent directory")
-            return path
+            for path in _default_config_candidates():
+                if path.exists():
+                    return path
+            raise FileNotFoundError("`config.yaml` file not found at the default backend or repository root locations")
 
     @classmethod
     def from_file(cls, config_path: str | None = None) -> Self:
@@ -248,6 +257,8 @@ _app_config: AppConfig | None = None
 _app_config_path: Path | None = None
 _app_config_mtime: float | None = None
 _app_config_is_custom = False
+_current_app_config: ContextVar[AppConfig | None] = ContextVar("deerflow_current_app_config", default=None)
+_current_app_config_stack: ContextVar[tuple[AppConfig | None, ...]] = ContextVar("deerflow_current_app_config_stack", default=())
 
 
 def _get_config_mtime(config_path: Path) -> float | None:
@@ -280,6 +291,10 @@ def get_app_config() -> AppConfig:
     """
     global _app_config, _app_config_path, _app_config_mtime
 
+    runtime_override = _current_app_config.get()
+    if runtime_override is not None:
+        return runtime_override
+
     if _app_config is not None and _app_config_is_custom:
         return _app_config
 
@@ -341,3 +356,26 @@ def set_app_config(config: AppConfig) -> None:
     _app_config_path = None
     _app_config_mtime = None
     _app_config_is_custom = True
+
+
+def peek_current_app_config() -> AppConfig | None:
+    """Return the runtime-scoped AppConfig override, if one is active."""
+    return _current_app_config.get()
+
+
+def push_current_app_config(config: AppConfig) -> None:
+    """Push a runtime-scoped AppConfig override for the current execution context."""
+    stack = _current_app_config_stack.get()
+    _current_app_config_stack.set(stack + (_current_app_config.get(),))
+    _current_app_config.set(config)
+
+
+def pop_current_app_config() -> None:
+    """Pop the latest runtime-scoped AppConfig override for the current execution context."""
+    stack = _current_app_config_stack.get()
+    if not stack:
+        _current_app_config.set(None)
+        return
+    previous = stack[-1]
+    _current_app_config_stack.set(stack[:-1])
+    _current_app_config.set(previous)

backend/packages/harness/deerflow/config/extensions_config.py

@@ -80,6 +80,12 @@ class ExtensionsConfig(BaseModel):
         Args:
             config_path: Optional path to extensions config file.
 
+        Resolution order:
+            1. If provided `config_path` argument, use it.
+            2. If provided `DEER_FLOW_EXTENSIONS_CONFIG_PATH` environment variable, use it.
+            3. Otherwise, search backend/repository-root defaults for
+               `extensions_config.json`, then legacy `mcp_config.json`.
+
         Returns:
             Path to the extensions config file if found, otherwise None.
         """
@@ -94,24 +100,16 @@ class ExtensionsConfig(BaseModel):
                 raise FileNotFoundError(f"Extensions config file specified by environment variable `DEER_FLOW_EXTENSIONS_CONFIG_PATH` not found at {path}")
             return path
         else:
-            # Check if the extensions_config.json is in the current directory
-            path = Path(os.getcwd()) / "extensions_config.json"
-            if path.exists():
-                return path
-
-            # Check if the extensions_config.json is in the parent directory of CWD
-            path = Path(os.getcwd()).parent / "extensions_config.json"
-            if path.exists():
-                return path
-
-            # Backward compatibility: check for mcp_config.json
-            path = Path(os.getcwd()) / "mcp_config.json"
-            if path.exists():
-                return path
-
-            path = Path(os.getcwd()).parent / "mcp_config.json"
-            if path.exists():
-                return path
+            backend_dir = Path(__file__).resolve().parents[4]
+            repo_root = backend_dir.parent
+            for path in (
+                backend_dir / "extensions_config.json",
+                repo_root / "extensions_config.json",
+                backend_dir / "mcp_config.json",
+                repo_root / "mcp_config.json",
+            ):
+                if path.exists():
+                    return path
 
             # Extensions are optional, so return None if not found
             return None

backend/packages/harness/deerflow/config/paths.py

@@ -9,6 +9,12 @@ VIRTUAL_PATH_PREFIX = "/mnt/user-data"
 _SAFE_THREAD_ID_RE = re.compile(r"^[A-Za-z0-9_\-]+$")
 
 
+def _default_local_base_dir() -> Path:
+    """Return the repo-local DeerFlow state directory without relying on cwd."""
+    backend_dir = Path(__file__).resolve().parents[4]
+    return backend_dir / ".deer-flow"
+
+
 def _validate_thread_id(thread_id: str) -> str:
     """Validate a thread ID before using it in filesystem paths."""
     if not _SAFE_THREAD_ID_RE.match(thread_id):
@@ -67,8 +73,7 @@ class Paths:
     BaseDir resolution (in priority order):
         1. Constructor argument `base_dir`
         2. DEER_FLOW_HOME environment variable
-        3. Local dev fallback: cwd/.deer-flow  (when cwd is the backend/ dir)
-        4. Default: $HOME/.deer-flow
+        3. Repo-local fallback derived from this module path: `{backend_dir}/.deer-flow`
     """
 
     def __init__(self, base_dir: str | Path | None = None) -> None:
@@ -104,11 +109,7 @@ class Paths:
         if env_home := os.getenv("DEER_FLOW_HOME"):
             return Path(env_home).resolve()
 
-        cwd = Path.cwd()
-        if cwd.name == "backend" or (cwd / "pyproject.toml").exists():
-            return cwd / ".deer-flow"
-
-        return Path.home() / ".deer-flow"
+        return _default_local_base_dir()
 
     @property
     def memory_file(self) -> Path:

backend/packages/harness/deerflow/config/sandbox_config.py

@@ -64,4 +64,15 @@ class SandboxConfig(BaseModel):
         description="Environment variables to inject into the sandbox container. Values starting with $ will be resolved from host environment variables.",
     )
 
+    bash_output_max_chars: int = Field(
+        default=20000,
+        ge=0,
+        description="Maximum characters to keep from bash tool output. Output exceeding this limit is middle-truncated (head + tail), preserving the first and last half. Set to 0 to disable truncation.",
+    )
+    read_file_output_max_chars: int = Field(
+        default=50000,
+        ge=0,
+        description="Maximum characters to keep from read_file tool output. Output exceeding this limit is head-truncated. Set to 0 to disable truncation.",
+    )
+
     model_config = ConfigDict(extra="allow")

backend/packages/harness/deerflow/config/skills_config.py

@@ -3,6 +3,11 @@ from pathlib import Path
 from pydantic import BaseModel, Field
 
 
+def _default_repo_root() -> Path:
+    """Resolve the repo root without relying on the current working directory."""
+    return Path(__file__).resolve().parents[5]
+
+
 class SkillsConfig(BaseModel):
     """Configuration for skills system"""
 
@@ -26,8 +31,8 @@ class SkillsConfig(BaseModel):
             # Use configured path (can be absolute or relative)
             path = Path(self.path)
             if not path.is_absolute():
-                # If relative, resolve from current working directory
-                path = Path.cwd() / path
+                # If relative, resolve from the repo root for deterministic behavior.
+                path = _default_repo_root() / path
             return path.resolve()
         else:
             # Default: ../skills relative to backend directory

backend/packages/harness/deerflow/config/tracing_config.py

@@ -1,14 +1,12 @@
-import logging
 import os
 import threading
 
 from pydantic import BaseModel, Field
 
-logger = logging.getLogger(__name__)
 _config_lock = threading.Lock()
 
 
-class TracingConfig(BaseModel):
+class LangSmithTracingConfig(BaseModel):
     """Configuration for LangSmith tracing."""
 
     enabled: bool = Field(...)
@@ -18,9 +16,69 @@ class TracingConfig(BaseModel):
 
     @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)
 
+    def validate(self) -> None:
+        if self.enabled and not self.api_key:
+            raise ValueError("LangSmith tracing is enabled but LANGSMITH_API_KEY (or LANGCHAIN_API_KEY) is not set.")
+
+
+class LangfuseTracingConfig(BaseModel):
+    """Configuration for Langfuse tracing."""
+
+    enabled: bool = Field(...)
+    public_key: str | None = Field(...)
+    secret_key: str | None = Field(...)
+    host: str = Field(...)
+
+    @property
+    def is_configured(self) -> bool:
+        return self.enabled and bool(self.public_key) and bool(self.secret_key)
+
+    def validate(self) -> None:
+        if not self.enabled:
+            return
+        missing: list[str] = []
+        if not self.public_key:
+            missing.append("LANGFUSE_PUBLIC_KEY")
+        if not self.secret_key:
+            missing.append("LANGFUSE_SECRET_KEY")
+        if missing:
+            raise ValueError(f"Langfuse tracing is enabled but required settings are missing: {', '.join(missing)}")
+
+
+class TracingConfig(BaseModel):
+    """Tracing configuration for supported providers."""
+
+    langsmith: LangSmithTracingConfig = Field(...)
+    langfuse: LangfuseTracingConfig = Field(...)
+
+    @property
+    def is_configured(self) -> bool:
+        return bool(self.enabled_providers)
+
+    @property
+    def explicitly_enabled_providers(self) -> list[str]:
+        enabled: list[str] = []
+        if self.langsmith.enabled:
+            enabled.append("langsmith")
+        if self.langfuse.enabled:
+            enabled.append("langfuse")
+        return enabled
+
+    @property
+    def enabled_providers(self) -> list[str]:
+        enabled: list[str] = []
+        if self.langsmith.is_configured:
+            enabled.append("langsmith")
+        if self.langfuse.is_configured:
+            enabled.append("langfuse")
+        return enabled
+
+    def validate_enabled(self) -> None:
+        self.langsmith.validate()
+        self.langfuse.validate()
+
 
 _tracing_config: TracingConfig | None = None
 
@@ -29,12 +87,7 @@ _TRUTHY_VALUES = {"1", "true", "yes", "on"}
 
 
 def _env_flag_preferred(*names: str) -> bool:
-    """Return the boolean value of the first env var that is present and non-empty.
-
-    Accepted truthy values (case-insensitive): ``1``, ``true``, ``yes``, ``on``.
-    Any other non-empty value is treated as falsy.  If none of the named
-    variables is set, returns ``False``.
-    """
+    """Return the boolean value of the first env var that is present and non-empty."""
     for name in names:
         value = os.environ.get(name)
         if value is not None and value.strip():
@@ -52,43 +105,45 @@ def _first_env_value(*names: str) -> str | None:
 
 
 def get_tracing_config() -> TracingConfig:
-    """Get the current tracing configuration from environment variables.
-
-    ``LANGSMITH_*`` variables take precedence over their legacy ``LANGCHAIN_*``
-    counterparts.  For boolean flags (``enabled``), the *first* variable that is
-    present and non-empty in the priority list is the sole authority – its value
-    is parsed and returned without consulting the remaining candidates.  Accepted
-    truthy values are ``1``, ``true``, ``yes``, and ``on`` (case-insensitive);
-    any other non-empty value is treated as falsy.
-
-    Priority order:
-        enabled  : LANGSMITH_TRACING > LANGCHAIN_TRACING_V2 > LANGCHAIN_TRACING
-        api_key  : LANGSMITH_API_KEY  > LANGCHAIN_API_KEY
-        project  : LANGSMITH_PROJECT  > LANGCHAIN_PROJECT   (default: "deer-flow")
-        endpoint : LANGSMITH_ENDPOINT > LANGCHAIN_ENDPOINT  (default: https://api.smith.langchain.com)
-
-    Returns:
-        TracingConfig with current settings.
-    """
+    """Get the current tracing configuration from environment variables."""
     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
+        if _tracing_config is not None:
             return _tracing_config
         _tracing_config = TracingConfig(
-            # Keep compatibility with both legacy LANGCHAIN_* and newer LANGSMITH_* variables.
-            enabled=_env_flag_preferred("LANGSMITH_TRACING", "LANGCHAIN_TRACING_V2", "LANGCHAIN_TRACING"),
-            api_key=_first_env_value("LANGSMITH_API_KEY", "LANGCHAIN_API_KEY"),
-            project=_first_env_value("LANGSMITH_PROJECT", "LANGCHAIN_PROJECT") or "deer-flow",
-            endpoint=_first_env_value("LANGSMITH_ENDPOINT", "LANGCHAIN_ENDPOINT") or "https://api.smith.langchain.com",
+            langsmith=LangSmithTracingConfig(
+                enabled=_env_flag_preferred("LANGSMITH_TRACING", "LANGCHAIN_TRACING_V2", "LANGCHAIN_TRACING"),
+                api_key=_first_env_value("LANGSMITH_API_KEY", "LANGCHAIN_API_KEY"),
+                project=_first_env_value("LANGSMITH_PROJECT", "LANGCHAIN_PROJECT") or "deer-flow",
+                endpoint=_first_env_value("LANGSMITH_ENDPOINT", "LANGCHAIN_ENDPOINT") or "https://api.smith.langchain.com",
+            ),
+            langfuse=LangfuseTracingConfig(
+                enabled=_env_flag_preferred("LANGFUSE_TRACING"),
+                public_key=_first_env_value("LANGFUSE_PUBLIC_KEY"),
+                secret_key=_first_env_value("LANGFUSE_SECRET_KEY"),
+                host=_first_env_value("LANGFUSE_BASE_URL") or "https://cloud.langfuse.com",
+            ),
         )
         return _tracing_config
 
 
+def get_enabled_tracing_providers() -> list[str]:
+    """Return the configured tracing providers that are enabled and complete."""
+    return get_tracing_config().enabled_providers
+
+
+def get_explicitly_enabled_tracing_providers() -> list[str]:
+    """Return tracing providers explicitly enabled by config, even if incomplete."""
+    return get_tracing_config().explicitly_enabled_providers
+
+
+def validate_enabled_tracing_providers() -> None:
+    """Validate that any explicitly enabled providers are fully configured."""
+    get_tracing_config().validate_enabled()
+
+
 def is_tracing_enabled() -> bool:
-    """Check if LangSmith tracing is enabled and configured.
-    Returns:
-        True if tracing is enabled and has an API key.
-    """
+    """Check if any tracing provider is enabled and fully configured."""
     return get_tracing_config().is_configured