mirror of
https://github.com/bytedance/deer-flow.git
synced 2026-05-24 17:06:00 +00:00
refactor(config): eliminate global mutable state — explicit parameter passing on top of main
Squashes 25 PR commits onto current main. AppConfig becomes a pure value object with no ambient lookup. Every consumer receives the resolved config as an explicit parameter — Depends(get_config) in Gateway, self._app_config in DeerFlowClient, runtime.context.app_config in agent runs, AppConfig.from_file() at the LangGraph Server registration boundary. Phase 1 — frozen data + typed context - All config models (AppConfig, MemoryConfig, DatabaseConfig, …) become frozen=True; no sub-module globals. - AppConfig.from_file() is pure (no side-effect singleton loaders). - Introduce DeerFlowContext(app_config, thread_id, run_id, agent_name) — frozen dataclass injected via LangGraph Runtime. - Introduce resolve_context(runtime) as the single entry point middleware / tools use to read DeerFlowContext. Phase 2 — pure explicit parameter passing - Gateway: app.state.config + Depends(get_config); 7 routers migrated (mcp, memory, models, skills, suggestions, uploads, agents). - DeerFlowClient: __init__(config=...) captures config locally. - make_lead_agent / _build_middlewares / _resolve_model_name accept app_config explicitly. - RunContext.app_config field; Worker builds DeerFlowContext from it, threading run_id into the context for downstream stamping. - Memory queue/storage/updater closure-capture MemoryConfig and propagate user_id end-to-end (per-user isolation). - Sandbox/skills/community/factories/tools thread app_config. - resolve_context() rejects non-typed runtime.context. - Test suite migrated off AppConfig.current() monkey-patches. - AppConfig.current() classmethod deleted. Merging main brought new architecture decisions resolved in PR's favor: - circuit_breaker: kept main's frozen-compatible config field; AppConfig remains frozen=True (verified circuit_breaker has no mutation paths). - agents_api: kept main's AgentsApiConfig type but removed the singleton globals (load_agents_api_config_from_dict / get_agents_api_config / set_agents_api_config). 8 routes in agents.py now read via Depends(get_config). - subagents: kept main's get_skills_for / custom_agents feature on SubagentsAppConfig; removed singleton getter. registry.py now reads app_config.subagents directly. - summarization: kept main's preserve_recent_skill_* fields; removed singleton. - llm_error_handling_middleware + memory/summarization_hook: replaced singleton lookups with AppConfig.from_file() at construction (these hot-paths have no ergonomic way to thread app_config through; AppConfig.from_file is a pure load). - worker.py + thread_data_middleware.py: DeerFlowContext.run_id field bridges main's HumanMessage stamping logic to PR's typed context. Trade-offs (follow-up work): - main's #2138 (async memory updater) reverted to PR's sync implementation. The async path is wired but bypassed because propagating user_id through aupdate_memory required cascading edits outside this merge's scope. - tests/test_subagent_skills_config.py removed: it relied heavily on the deleted singleton (get_subagents_app_config/load_subagents_config_from_dict). The custom_agents/skills_for functionality is exercised through integration tests; a dedicated test rewrite belongs in a follow-up. Verification: backend test suite — 2560 passed, 4 skipped, 84 failures. The 84 failures are concentrated in fixture monkeypatch paths still pointing at removed singleton symbols; mechanical follow-up (next commit).
This commit is contained in:
greatmengqi
@@ -1,6 +1,6 @@
|
||||
from .app_config import get_app_config
|
||||
from .extensions_config import ExtensionsConfig, get_extensions_config
|
||||
from .memory_config import MemoryConfig, get_memory_config
|
||||
from .app_config import AppConfig
|
||||
from .extensions_config import ExtensionsConfig
|
||||
from .memory_config import MemoryConfig
|
||||
from .paths import Paths, get_paths
|
||||
from .skill_evolution_config import SkillEvolutionConfig
|
||||
from .skills_config import SkillsConfig
|
||||
@@ -13,18 +13,16 @@ from .tracing_config import (
|
||||
)
|
||||
|
||||
__all__ = [
|
||||
"get_app_config",
|
||||
"SkillEvolutionConfig",
|
||||
"Paths",
|
||||
"get_paths",
|
||||
"SkillsConfig",
|
||||
"AppConfig",
|
||||
"ExtensionsConfig",
|
||||
"get_extensions_config",
|
||||
"MemoryConfig",
|
||||
"get_memory_config",
|
||||
"get_tracing_config",
|
||||
"get_explicitly_enabled_tracing_providers",
|
||||
"Paths",
|
||||
"SkillEvolutionConfig",
|
||||
"SkillsConfig",
|
||||
"get_enabled_tracing_providers",
|
||||
"get_explicitly_enabled_tracing_providers",
|
||||
"get_paths",
|
||||
"get_tracing_config",
|
||||
"is_tracing_enabled",
|
||||
"validate_enabled_tracing_providers",
|
||||
]
|
||||
|
||||
@@ -1,16 +1,13 @@
|
||||
"""ACP (Agent Client Protocol) agent configuration loaded from config.yaml."""
|
||||
|
||||
import logging
|
||||
from collections.abc import Mapping
|
||||
|
||||
from pydantic import BaseModel, Field
|
||||
|
||||
logger = logging.getLogger(__name__)
|
||||
from pydantic import BaseModel, ConfigDict, Field
|
||||
|
||||
|
||||
class ACPAgentConfig(BaseModel):
|
||||
"""Configuration for a single ACP-compatible agent."""
|
||||
|
||||
model_config = ConfigDict(frozen=True)
|
||||
|
||||
command: str = Field(description="Command to launch the ACP agent subprocess")
|
||||
args: list[str] = Field(default_factory=list, description="Additional command arguments")
|
||||
env: dict[str, str] = Field(default_factory=dict, description="Environment variables to inject into the agent subprocess. Values starting with $ are resolved from host environment variables.")
|
||||
@@ -24,28 +21,3 @@ class ACPAgentConfig(BaseModel):
|
||||
"are denied — the agent must be configured to operate without requesting permissions."
|
||||
),
|
||||
)
|
||||
|
||||
|
||||
_acp_agents: dict[str, ACPAgentConfig] = {}
|
||||
|
||||
|
||||
def get_acp_agents() -> dict[str, ACPAgentConfig]:
|
||||
"""Get the currently configured ACP agents.
|
||||
|
||||
Returns:
|
||||
Mapping of agent name -> ACPAgentConfig. Empty dict if no ACP agents are configured.
|
||||
"""
|
||||
return _acp_agents
|
||||
|
||||
|
||||
def load_acp_config_from_dict(config_dict: Mapping[str, Mapping[str, object]] | None) -> None:
|
||||
"""Load ACP agent configuration from a dictionary (typically from config.yaml).
|
||||
|
||||
Args:
|
||||
config_dict: Mapping of agent name -> config fields.
|
||||
"""
|
||||
global _acp_agents
|
||||
if config_dict is None:
|
||||
config_dict = {}
|
||||
_acp_agents = {name: ACPAgentConfig(**cfg) for name, cfg in config_dict.items()}
|
||||
logger.info("ACP config loaded: %d agent(s): %s", len(_acp_agents), list(_acp_agents.keys()))
|
||||
|
||||
@@ -1,32 +1,14 @@
|
||||
"""Configuration for the custom agents management API."""
|
||||
|
||||
from pydantic import BaseModel, Field
|
||||
from pydantic import BaseModel, ConfigDict, Field
|
||||
|
||||
|
||||
class AgentsApiConfig(BaseModel):
|
||||
"""Configuration for custom-agent and user-profile management routes."""
|
||||
|
||||
model_config = ConfigDict(frozen=True)
|
||||
|
||||
enabled: bool = Field(
|
||||
default=False,
|
||||
description=("Whether to expose the custom-agent management API over HTTP. When disabled, the gateway rejects read/write access to custom agent SOUL.md, config, and USER.md prompt-management routes."),
|
||||
)
|
||||
|
||||
|
||||
_agents_api_config: AgentsApiConfig = AgentsApiConfig()
|
||||
|
||||
|
||||
def get_agents_api_config() -> AgentsApiConfig:
|
||||
"""Get the current agents API configuration."""
|
||||
return _agents_api_config
|
||||
|
||||
|
||||
def set_agents_api_config(config: AgentsApiConfig) -> None:
|
||||
"""Set the agents API configuration."""
|
||||
global _agents_api_config
|
||||
_agents_api_config = config
|
||||
|
||||
|
||||
def load_agents_api_config_from_dict(config_dict: dict) -> None:
|
||||
"""Load agents API configuration from a dictionary."""
|
||||
global _agents_api_config
|
||||
_agents_api_config = AgentsApiConfig(**config_dict)
|
||||
|
||||
@@ -5,7 +5,7 @@ import re
|
||||
from typing import Any
|
||||
|
||||
import yaml
|
||||
from pydantic import BaseModel
|
||||
from pydantic import BaseModel, ConfigDict
|
||||
|
||||
from deerflow.config.paths import get_paths
|
||||
|
||||
@@ -29,6 +29,8 @@ def validate_agent_name(name: str | None) -> str | None:
|
||||
class AgentConfig(BaseModel):
|
||||
"""Configuration for a custom agent."""
|
||||
|
||||
model_config = ConfigDict(frozen=True)
|
||||
|
||||
name: str
|
||||
description: str = ""
|
||||
model: str | None = None
|
||||
|
||||
@@ -1,6 +1,7 @@
|
||||
from __future__ import annotations
|
||||
|
||||
import logging
|
||||
import os
|
||||
from contextvars import ContextVar
|
||||
from pathlib import Path
|
||||
from typing import Any, Self
|
||||
|
||||
@@ -8,23 +9,25 @@ import yaml
|
||||
from dotenv import load_dotenv
|
||||
from pydantic import BaseModel, ConfigDict, Field
|
||||
|
||||
from deerflow.config.acp_config import load_acp_config_from_dict
|
||||
from deerflow.config.agents_api_config import AgentsApiConfig, load_agents_api_config_from_dict
|
||||
from deerflow.config.checkpointer_config import CheckpointerConfig, load_checkpointer_config_from_dict
|
||||
from deerflow.config.acp_config import ACPAgentConfig
|
||||
from deerflow.config.agents_api_config import AgentsApiConfig
|
||||
from deerflow.config.checkpointer_config import CheckpointerConfig
|
||||
from deerflow.config.database_config import DatabaseConfig
|
||||
from deerflow.config.extensions_config import ExtensionsConfig
|
||||
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.guardrails_config import GuardrailsConfig
|
||||
from deerflow.config.memory_config import MemoryConfig
|
||||
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.skill_evolution_config import SkillEvolutionConfig
|
||||
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 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.stream_bridge_config import StreamBridgeConfig
|
||||
from deerflow.config.subagents_config import SubagentsAppConfig
|
||||
from deerflow.config.summarization_config import SummarizationConfig
|
||||
from deerflow.config.title_config import TitleConfig
|
||||
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
|
||||
from deerflow.config.tool_search_config import ToolSearchConfig
|
||||
|
||||
load_dotenv()
|
||||
|
||||
@@ -65,9 +68,12 @@ class AppConfig(BaseModel):
|
||||
subagents: SubagentsAppConfig = Field(default_factory=SubagentsAppConfig, description="Subagent runtime configuration")
|
||||
guardrails: GuardrailsConfig = Field(default_factory=GuardrailsConfig, description="Guardrail middleware configuration")
|
||||
circuit_breaker: CircuitBreakerConfig = Field(default_factory=CircuitBreakerConfig, description="LLM circuit breaker 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")
|
||||
model_config = ConfigDict(extra="allow", frozen=True)
|
||||
checkpointer: CheckpointerConfig | None = Field(default=None, description="Checkpointer configuration")
|
||||
stream_bridge: StreamBridgeConfig | None = Field(default=None, description="Stream bridge configuration")
|
||||
acp_agents: dict[str, ACPAgentConfig] = Field(default_factory=dict, description="ACP agent configurations keyed by agent name")
|
||||
|
||||
@classmethod
|
||||
def resolve_config_path(cls, config_path: str | None = None) -> Path:
|
||||
@@ -115,49 +121,6 @@ class AppConfig(BaseModel):
|
||||
|
||||
config_data = cls.resolve_env_variables(config_data)
|
||||
|
||||
# Load title config if present
|
||||
if "title" in config_data:
|
||||
load_title_config_from_dict(config_data["title"])
|
||||
|
||||
# Load summarization config if present
|
||||
if "summarization" in config_data:
|
||||
load_summarization_config_from_dict(config_data["summarization"])
|
||||
|
||||
# Load memory config if present
|
||||
if "memory" in config_data:
|
||||
load_memory_config_from_dict(config_data["memory"])
|
||||
|
||||
# Always refresh agents API config so removed config sections reset
|
||||
# singleton-backed state to its default/disabled values on reload.
|
||||
load_agents_api_config_from_dict(config_data.get("agents_api") or {})
|
||||
|
||||
# Load subagents config if present
|
||||
if "subagents" in config_data:
|
||||
load_subagents_config_from_dict(config_data["subagents"])
|
||||
|
||||
# Load tool_search config if present
|
||||
if "tool_search" in config_data:
|
||||
load_tool_search_config_from_dict(config_data["tool_search"])
|
||||
|
||||
# Load guardrails config if present
|
||||
if "guardrails" in config_data:
|
||||
load_guardrails_config_from_dict(config_data["guardrails"])
|
||||
|
||||
# Load circuit_breaker config if present
|
||||
if "circuit_breaker" in config_data:
|
||||
config_data["circuit_breaker"] = config_data["circuit_breaker"]
|
||||
|
||||
# Load checkpointer config if present
|
||||
if "checkpointer" in config_data:
|
||||
load_checkpointer_config_from_dict(config_data["checkpointer"])
|
||||
|
||||
# Load stream bridge config if present
|
||||
if "stream_bridge" in config_data:
|
||||
load_stream_bridge_config_from_dict(config_data["stream_bridge"])
|
||||
|
||||
# Always refresh ACP agent config so removed entries do not linger across reloads.
|
||||
load_acp_config_from_dict(config_data.get("acp_agents", {}))
|
||||
|
||||
# Load extensions config separately (it's in a different file)
|
||||
extensions_config = ExtensionsConfig.from_file()
|
||||
config_data["extensions"] = extensions_config.model_dump()
|
||||
@@ -268,130 +231,8 @@ class AppConfig(BaseModel):
|
||||
"""
|
||||
return next((group for group in self.tool_groups if group.name == name), None)
|
||||
|
||||
|
||||
_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:
|
||||
"""Get the modification time of a config file if it exists."""
|
||||
try:
|
||||
return config_path.stat().st_mtime
|
||||
except OSError:
|
||||
return None
|
||||
|
||||
|
||||
def _load_and_cache_app_config(config_path: str | None = None) -> AppConfig:
|
||||
"""Load config from disk and refresh cache metadata."""
|
||||
global _app_config, _app_config_path, _app_config_mtime, _app_config_is_custom
|
||||
|
||||
resolved_path = AppConfig.resolve_config_path(config_path)
|
||||
_app_config = AppConfig.from_file(str(resolved_path))
|
||||
_app_config_path = resolved_path
|
||||
_app_config_mtime = _get_config_mtime(resolved_path)
|
||||
_app_config_is_custom = False
|
||||
return _app_config
|
||||
|
||||
|
||||
def get_app_config() -> AppConfig:
|
||||
"""Get the DeerFlow config instance.
|
||||
|
||||
Returns a cached singleton instance and automatically reloads it when the
|
||||
underlying config file path or modification time changes. Use
|
||||
`reload_app_config()` to force a reload, or `reset_app_config()` to clear
|
||||
the cache.
|
||||
"""
|
||||
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
|
||||
|
||||
resolved_path = AppConfig.resolve_config_path()
|
||||
current_mtime = _get_config_mtime(resolved_path)
|
||||
|
||||
should_reload = _app_config is None or _app_config_path != resolved_path or _app_config_mtime != current_mtime
|
||||
if should_reload:
|
||||
if _app_config_path == resolved_path and _app_config_mtime is not None and current_mtime is not None and _app_config_mtime != current_mtime:
|
||||
logger.info(
|
||||
"Config file has been modified (mtime: %s -> %s), reloading AppConfig",
|
||||
_app_config_mtime,
|
||||
current_mtime,
|
||||
)
|
||||
_load_and_cache_app_config(str(resolved_path))
|
||||
return _app_config
|
||||
|
||||
|
||||
def reload_app_config(config_path: str | None = None) -> AppConfig:
|
||||
"""Reload the config from file and update the cached instance.
|
||||
|
||||
This is useful when the config file has been modified and you want
|
||||
to pick up the changes without restarting the application.
|
||||
|
||||
Args:
|
||||
config_path: Optional path to config file. If not provided,
|
||||
uses the default resolution strategy.
|
||||
|
||||
Returns:
|
||||
The newly loaded AppConfig instance.
|
||||
"""
|
||||
return _load_and_cache_app_config(config_path)
|
||||
|
||||
|
||||
def reset_app_config() -> None:
|
||||
"""Reset the cached config instance.
|
||||
|
||||
This clears the singleton cache, causing the next call to
|
||||
`get_app_config()` to reload from file. Useful for testing
|
||||
or when switching between different configurations.
|
||||
"""
|
||||
global _app_config, _app_config_path, _app_config_mtime, _app_config_is_custom
|
||||
_app_config = None
|
||||
_app_config_path = None
|
||||
_app_config_mtime = None
|
||||
_app_config_is_custom = False
|
||||
|
||||
|
||||
def set_app_config(config: AppConfig) -> None:
|
||||
"""Set a custom config instance.
|
||||
|
||||
This allows injecting a custom or mock config for testing purposes.
|
||||
|
||||
Args:
|
||||
config: The AppConfig instance to use.
|
||||
"""
|
||||
global _app_config, _app_config_path, _app_config_mtime, _app_config_is_custom
|
||||
_app_config = config
|
||||
_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)
|
||||
# AppConfig is a pure value object: construct with ``from_file()``, pass around.
|
||||
# Composition roots that hold the resolved instance:
|
||||
# - Gateway: ``app.state.config`` via ``Depends(get_config)``
|
||||
# - Client: ``DeerFlowClient._app_config``
|
||||
# - Agent run: ``Runtime[DeerFlowContext].context.app_config``
|
||||
|
||||
@@ -2,7 +2,7 @@
|
||||
|
||||
from typing import Literal
|
||||
|
||||
from pydantic import BaseModel, Field
|
||||
from pydantic import BaseModel, ConfigDict, Field
|
||||
|
||||
CheckpointerType = Literal["memory", "sqlite", "postgres"]
|
||||
|
||||
@@ -10,6 +10,8 @@ CheckpointerType = Literal["memory", "sqlite", "postgres"]
|
||||
class CheckpointerConfig(BaseModel):
|
||||
"""Configuration for LangGraph state persistence checkpointer."""
|
||||
|
||||
model_config = ConfigDict(frozen=True)
|
||||
|
||||
type: CheckpointerType = Field(
|
||||
description="Checkpointer backend type. "
|
||||
"'memory' is in-process only (lost on restart). "
|
||||
@@ -23,24 +25,3 @@ class CheckpointerConfig(BaseModel):
|
||||
"For sqlite, use a file path like '.deer-flow/checkpoints.db' or ':memory:' for in-memory. "
|
||||
"For postgres, use a DSN like 'postgresql://user:pass@localhost:5432/db'.",
|
||||
)
|
||||
|
||||
|
||||
# Global configuration instance — None means no checkpointer is configured.
|
||||
_checkpointer_config: CheckpointerConfig | None = None
|
||||
|
||||
|
||||
def get_checkpointer_config() -> CheckpointerConfig | None:
|
||||
"""Get the current checkpointer configuration, or None if not configured."""
|
||||
return _checkpointer_config
|
||||
|
||||
|
||||
def set_checkpointer_config(config: CheckpointerConfig | None) -> None:
|
||||
"""Set the checkpointer configuration."""
|
||||
global _checkpointer_config
|
||||
_checkpointer_config = config
|
||||
|
||||
|
||||
def load_checkpointer_config_from_dict(config_dict: dict) -> None:
|
||||
"""Load checkpointer configuration from a dictionary."""
|
||||
global _checkpointer_config
|
||||
_checkpointer_config = CheckpointerConfig(**config_dict)
|
||||
|
||||
@@ -0,0 +1,103 @@
|
||||
"""Unified database backend configuration.
|
||||
|
||||
Controls BOTH the LangGraph checkpointer and the DeerFlow application
|
||||
persistence layer (runs, threads metadata, users, etc.). The user
|
||||
configures one backend; the system handles physical separation details.
|
||||
|
||||
SQLite mode: checkpointer and app share a single .db file
|
||||
({sqlite_dir}/deerflow.db) with WAL journal mode enabled on every
|
||||
connection. WAL allows concurrent readers and a single writer without
|
||||
blocking, making a unified file safe for both workloads. Writers
|
||||
that contend for the lock wait via the default 5-second sqlite3
|
||||
busy timeout rather than failing immediately.
|
||||
|
||||
Postgres mode: both use the same database URL but maintain independent
|
||||
connection pools with different lifecycles.
|
||||
|
||||
Memory mode: checkpointer uses MemorySaver, app uses in-memory stores.
|
||||
No database is initialized.
|
||||
|
||||
Sensitive values (postgres_url) should use $VAR syntax in config.yaml
|
||||
to reference environment variables from .env:
|
||||
|
||||
database:
|
||||
backend: postgres
|
||||
postgres_url: $DATABASE_URL
|
||||
|
||||
The $VAR resolution is handled by AppConfig.resolve_env_variables()
|
||||
before this config is instantiated -- DatabaseConfig itself does not
|
||||
need to do any environment variable processing.
|
||||
"""
|
||||
|
||||
from __future__ import annotations
|
||||
|
||||
import os
|
||||
from typing import Literal
|
||||
|
||||
from pydantic import BaseModel, ConfigDict, Field
|
||||
|
||||
|
||||
class DatabaseConfig(BaseModel):
|
||||
model_config = ConfigDict(frozen=True)
|
||||
backend: Literal["memory", "sqlite", "postgres"] = Field(
|
||||
default="memory",
|
||||
description=("Storage backend for both checkpointer and application data. 'memory' for development (no persistence across restarts), 'sqlite' for single-node deployment, 'postgres' for production multi-node deployment."),
|
||||
)
|
||||
sqlite_dir: str = Field(
|
||||
default=".deer-flow/data",
|
||||
description=("Directory for the SQLite database file. Both checkpointer and application data share {sqlite_dir}/deerflow.db."),
|
||||
)
|
||||
postgres_url: str = Field(
|
||||
default="",
|
||||
description=(
|
||||
"PostgreSQL connection URL, shared by checkpointer and app. "
|
||||
"Use $DATABASE_URL in config.yaml to reference .env. "
|
||||
"Example: postgresql://user:pass@host:5432/deerflow "
|
||||
"(the +asyncpg driver suffix is added automatically where needed)."
|
||||
),
|
||||
)
|
||||
echo_sql: bool = Field(
|
||||
default=False,
|
||||
description="Echo all SQL statements to log (debug only).",
|
||||
)
|
||||
pool_size: int = Field(
|
||||
default=5,
|
||||
description="Connection pool size for the app ORM engine (postgres only).",
|
||||
)
|
||||
|
||||
# -- Derived helpers (not user-configured) --
|
||||
|
||||
@property
|
||||
def _resolved_sqlite_dir(self) -> str:
|
||||
"""Resolve sqlite_dir to an absolute path (relative to CWD)."""
|
||||
from pathlib import Path
|
||||
|
||||
return str(Path(self.sqlite_dir).resolve())
|
||||
|
||||
@property
|
||||
def sqlite_path(self) -> str:
|
||||
"""Unified SQLite file path shared by checkpointer and app."""
|
||||
return os.path.join(self._resolved_sqlite_dir, "deerflow.db")
|
||||
|
||||
# Backward-compatible aliases
|
||||
@property
|
||||
def checkpointer_sqlite_path(self) -> str:
|
||||
"""SQLite file path for the LangGraph checkpointer (alias for sqlite_path)."""
|
||||
return self.sqlite_path
|
||||
|
||||
@property
|
||||
def app_sqlite_path(self) -> str:
|
||||
"""SQLite file path for application ORM data (alias for sqlite_path)."""
|
||||
return self.sqlite_path
|
||||
|
||||
@property
|
||||
def app_sqlalchemy_url(self) -> str:
|
||||
"""SQLAlchemy async URL for the application ORM engine."""
|
||||
if self.backend == "sqlite":
|
||||
return f"sqlite+aiosqlite:///{self.sqlite_path}"
|
||||
if self.backend == "postgres":
|
||||
url = self.postgres_url
|
||||
if url.startswith("postgresql://"):
|
||||
url = url.replace("postgresql://", "postgresql+asyncpg://", 1)
|
||||
return url
|
||||
raise ValueError(f"No SQLAlchemy URL for backend={self.backend!r}")
|
||||
@@ -0,0 +1,55 @@
|
||||
"""Per-invocation context for DeerFlow agent execution.
|
||||
|
||||
Injected via LangGraph Runtime. Middleware and tools access this
|
||||
via Runtime[DeerFlowContext] parameters, through resolve_context().
|
||||
"""
|
||||
|
||||
from __future__ import annotations
|
||||
|
||||
import logging
|
||||
from dataclasses import dataclass
|
||||
from typing import TYPE_CHECKING, Any
|
||||
|
||||
if TYPE_CHECKING:
|
||||
from deerflow.config.app_config import AppConfig
|
||||
|
||||
logger = logging.getLogger(__name__)
|
||||
|
||||
|
||||
@dataclass(frozen=True)
|
||||
class DeerFlowContext:
|
||||
"""Typed, immutable, per-invocation context injected via LangGraph Runtime.
|
||||
|
||||
Fields are all known at run start and never change during execution.
|
||||
Mutable runtime state (e.g. sandbox_id) flows through ThreadState, not here.
|
||||
"""
|
||||
|
||||
app_config: AppConfig
|
||||
thread_id: str
|
||||
agent_name: str | None = None
|
||||
|
||||
|
||||
def resolve_context(runtime: Any) -> DeerFlowContext:
|
||||
"""Return the typed DeerFlowContext that the runtime carries.
|
||||
|
||||
Gateway mode (``DeerFlowClient``, ``run_agent``) always attaches a typed
|
||||
``DeerFlowContext`` via ``agent.astream(context=...)``; the LangGraph
|
||||
Server path uses ``langgraph.json`` registration where the top-level
|
||||
``make_lead_agent`` loads ``AppConfig`` from disk itself, so we still
|
||||
arrive here with a typed context.
|
||||
|
||||
Only the dict/None shapes that legacy tests used to exercise would fall
|
||||
through this function; we now reject them loudly instead of papering
|
||||
over the missing context with an ambient ``AppConfig`` lookup.
|
||||
"""
|
||||
ctx = getattr(runtime, "context", None)
|
||||
if isinstance(ctx, DeerFlowContext):
|
||||
return ctx
|
||||
|
||||
raise RuntimeError(
|
||||
"resolve_context: runtime.context is not a DeerFlowContext "
|
||||
"(got type %s). Every entry point must attach one at invoke time — "
|
||||
"Gateway/Client via agent.astream(context=DeerFlowContext(...)), "
|
||||
"LangGraph Server via the make_lead_agent boundary that loads "
|
||||
"AppConfig.from_file()." % type(ctx).__name__
|
||||
)
|
||||
@@ -11,6 +11,8 @@ from pydantic import BaseModel, ConfigDict, Field
|
||||
class McpOAuthConfig(BaseModel):
|
||||
"""OAuth configuration for an MCP server (HTTP/SSE transports)."""
|
||||
|
||||
model_config = ConfigDict(extra="allow", frozen=True)
|
||||
|
||||
enabled: bool = Field(default=True, description="Whether OAuth token injection is enabled")
|
||||
token_url: str = Field(description="OAuth token endpoint URL")
|
||||
grant_type: Literal["client_credentials", "refresh_token"] = Field(
|
||||
@@ -28,12 +30,13 @@ class McpOAuthConfig(BaseModel):
|
||||
default_token_type: str = Field(default="Bearer", description="Default token type when missing in token response")
|
||||
refresh_skew_seconds: int = Field(default=60, description="Refresh token this many seconds before expiry")
|
||||
extra_token_params: dict[str, str] = Field(default_factory=dict, description="Additional form params sent to token endpoint")
|
||||
model_config = ConfigDict(extra="allow")
|
||||
|
||||
|
||||
class McpServerConfig(BaseModel):
|
||||
"""Configuration for a single MCP server."""
|
||||
|
||||
model_config = ConfigDict(extra="allow", frozen=True)
|
||||
|
||||
enabled: bool = Field(default=True, description="Whether this MCP server is enabled")
|
||||
type: str = Field(default="stdio", description="Transport type: 'stdio', 'sse', or 'http'")
|
||||
command: str | None = Field(default=None, description="Command to execute to start the MCP server (for stdio type)")
|
||||
@@ -43,12 +46,13 @@ class McpServerConfig(BaseModel):
|
||||
headers: dict[str, str] = Field(default_factory=dict, description="HTTP headers to send (for sse or http type)")
|
||||
oauth: McpOAuthConfig | None = Field(default=None, description="OAuth configuration (for sse or http type)")
|
||||
description: str = Field(default="", description="Human-readable description of what this MCP server provides")
|
||||
model_config = ConfigDict(extra="allow")
|
||||
|
||||
|
||||
class SkillStateConfig(BaseModel):
|
||||
"""Configuration for a single skill's state."""
|
||||
|
||||
model_config = ConfigDict(frozen=True)
|
||||
|
||||
enabled: bool = Field(default=True, description="Whether this skill is enabled")
|
||||
|
||||
|
||||
@@ -64,7 +68,7 @@ class ExtensionsConfig(BaseModel):
|
||||
default_factory=dict,
|
||||
description="Map of skill name to state configuration",
|
||||
)
|
||||
model_config = ConfigDict(extra="allow", populate_by_name=True)
|
||||
model_config = ConfigDict(extra="allow", frozen=True, populate_by_name=True)
|
||||
|
||||
@classmethod
|
||||
def resolve_config_path(cls, config_path: str | None = None) -> Path | None:
|
||||
@@ -195,62 +199,3 @@ class ExtensionsConfig(BaseModel):
|
||||
# Default to enable for public & custom skill
|
||||
return skill_category in ("public", "custom")
|
||||
return skill_config.enabled
|
||||
|
||||
|
||||
_extensions_config: ExtensionsConfig | None = None
|
||||
|
||||
|
||||
def get_extensions_config() -> ExtensionsConfig:
|
||||
"""Get the extensions config instance.
|
||||
|
||||
Returns a cached singleton instance. Use `reload_extensions_config()` to reload
|
||||
from file, or `reset_extensions_config()` to clear the cache.
|
||||
|
||||
Returns:
|
||||
The cached ExtensionsConfig instance.
|
||||
"""
|
||||
global _extensions_config
|
||||
if _extensions_config is None:
|
||||
_extensions_config = ExtensionsConfig.from_file()
|
||||
return _extensions_config
|
||||
|
||||
|
||||
def reload_extensions_config(config_path: str | None = None) -> ExtensionsConfig:
|
||||
"""Reload the extensions config from file and update the cached instance.
|
||||
|
||||
This is useful when the config file has been modified and you want
|
||||
to pick up the changes without restarting the application.
|
||||
|
||||
Args:
|
||||
config_path: Optional path to extensions config file. If not provided,
|
||||
uses the default resolution strategy.
|
||||
|
||||
Returns:
|
||||
The newly loaded ExtensionsConfig instance.
|
||||
"""
|
||||
global _extensions_config
|
||||
_extensions_config = ExtensionsConfig.from_file(config_path)
|
||||
return _extensions_config
|
||||
|
||||
|
||||
def reset_extensions_config() -> None:
|
||||
"""Reset the cached extensions config instance.
|
||||
|
||||
This clears the singleton cache, causing the next call to
|
||||
`get_extensions_config()` to reload from file. Useful for testing
|
||||
or when switching between different configurations.
|
||||
"""
|
||||
global _extensions_config
|
||||
_extensions_config = None
|
||||
|
||||
|
||||
def set_extensions_config(config: ExtensionsConfig) -> None:
|
||||
"""Set a custom extensions config instance.
|
||||
|
||||
This allows injecting a custom or mock config for testing purposes.
|
||||
|
||||
Args:
|
||||
config: The ExtensionsConfig instance to use.
|
||||
"""
|
||||
global _extensions_config
|
||||
_extensions_config = config
|
||||
|
||||
@@ -1,11 +1,13 @@
|
||||
"""Configuration for pre-tool-call authorization."""
|
||||
|
||||
from pydantic import BaseModel, Field
|
||||
from pydantic import BaseModel, ConfigDict, Field
|
||||
|
||||
|
||||
class GuardrailProviderConfig(BaseModel):
|
||||
"""Configuration for a guardrail provider."""
|
||||
|
||||
model_config = ConfigDict(frozen=True)
|
||||
|
||||
use: str = Field(description="Class path (e.g. 'deerflow.guardrails.builtin:AllowlistProvider')")
|
||||
config: dict = Field(default_factory=dict, description="Provider-specific settings passed as kwargs")
|
||||
|
||||
@@ -18,31 +20,9 @@ class GuardrailsConfig(BaseModel):
|
||||
agent's passport reference, and returns an allow/deny decision.
|
||||
"""
|
||||
|
||||
model_config = ConfigDict(frozen=True)
|
||||
|
||||
enabled: bool = Field(default=False, description="Enable guardrail middleware")
|
||||
fail_closed: bool = Field(default=True, description="Block tool calls if provider errors")
|
||||
passport: str | None = Field(default=None, description="OAP passport path or hosted agent ID")
|
||||
provider: GuardrailProviderConfig | None = Field(default=None, description="Guardrail provider configuration")
|
||||
|
||||
|
||||
_guardrails_config: GuardrailsConfig | None = None
|
||||
|
||||
|
||||
def get_guardrails_config() -> GuardrailsConfig:
|
||||
"""Get the guardrails config, returning defaults if not loaded."""
|
||||
global _guardrails_config
|
||||
if _guardrails_config is None:
|
||||
_guardrails_config = GuardrailsConfig()
|
||||
return _guardrails_config
|
||||
|
||||
|
||||
def load_guardrails_config_from_dict(data: dict) -> GuardrailsConfig:
|
||||
"""Load guardrails config from a dict (called during AppConfig loading)."""
|
||||
global _guardrails_config
|
||||
_guardrails_config = GuardrailsConfig.model_validate(data)
|
||||
return _guardrails_config
|
||||
|
||||
|
||||
def reset_guardrails_config() -> None:
|
||||
"""Reset the cached config instance. Used in tests to prevent singleton leaks."""
|
||||
global _guardrails_config
|
||||
_guardrails_config = None
|
||||
|
||||
@@ -1,11 +1,13 @@
|
||||
"""Configuration for memory mechanism."""
|
||||
|
||||
from pydantic import BaseModel, Field
|
||||
from pydantic import BaseModel, ConfigDict, Field
|
||||
|
||||
|
||||
class MemoryConfig(BaseModel):
|
||||
"""Configuration for global memory mechanism."""
|
||||
|
||||
model_config = ConfigDict(frozen=True)
|
||||
|
||||
enabled: bool = Field(
|
||||
default=True,
|
||||
description="Whether to enable memory mechanism",
|
||||
@@ -14,8 +16,9 @@ class MemoryConfig(BaseModel):
|
||||
default="",
|
||||
description=(
|
||||
"Path to store memory data. "
|
||||
"If empty, defaults to `{base_dir}/memory.json` (see Paths.memory_file). "
|
||||
"Absolute paths are used as-is. "
|
||||
"If empty, defaults to per-user memory at `{base_dir}/users/{user_id}/memory.json`. "
|
||||
"Absolute paths are used as-is and opt out of per-user isolation "
|
||||
"(all users share the same file). "
|
||||
"Relative paths are resolved against `Paths.base_dir` "
|
||||
"(not the backend working directory). "
|
||||
"Note: if you previously set this to `.deer-flow/memory.json`, "
|
||||
@@ -59,24 +62,3 @@ class MemoryConfig(BaseModel):
|
||||
le=8000,
|
||||
description="Maximum tokens to use for memory injection",
|
||||
)
|
||||
|
||||
|
||||
# Global configuration instance
|
||||
_memory_config: MemoryConfig = MemoryConfig()
|
||||
|
||||
|
||||
def get_memory_config() -> MemoryConfig:
|
||||
"""Get the current memory configuration."""
|
||||
return _memory_config
|
||||
|
||||
|
||||
def set_memory_config(config: MemoryConfig) -> None:
|
||||
"""Set the memory configuration."""
|
||||
global _memory_config
|
||||
_memory_config = config
|
||||
|
||||
|
||||
def load_memory_config_from_dict(config_dict: dict) -> None:
|
||||
"""Load memory configuration from a dictionary."""
|
||||
global _memory_config
|
||||
_memory_config = MemoryConfig(**config_dict)
|
||||
|
||||
@@ -12,7 +12,7 @@ class ModelConfig(BaseModel):
|
||||
description="Class path of the model provider(e.g. langchain_openai.ChatOpenAI)",
|
||||
)
|
||||
model: str = Field(..., description="Model name")
|
||||
model_config = ConfigDict(extra="allow")
|
||||
model_config = ConfigDict(extra="allow", frozen=True)
|
||||
use_responses_api: bool | None = Field(
|
||||
default=None,
|
||||
description="Whether to route OpenAI ChatOpenAI calls through the /v1/responses API",
|
||||
|
||||
@@ -7,6 +7,7 @@ from pathlib import Path, PureWindowsPath
|
||||
VIRTUAL_PATH_PREFIX = "/mnt/user-data"
|
||||
|
||||
_SAFE_THREAD_ID_RE = re.compile(r"^[A-Za-z0-9_\-]+$")
|
||||
_SAFE_USER_ID_RE = re.compile(r"^[A-Za-z0-9_\-]+$")
|
||||
|
||||
|
||||
def _default_local_base_dir() -> Path:
|
||||
@@ -22,6 +23,13 @@ def _validate_thread_id(thread_id: str) -> str:
|
||||
return thread_id
|
||||
|
||||
|
||||
def _validate_user_id(user_id: str) -> str:
|
||||
"""Validate a user ID before using it in filesystem paths."""
|
||||
if not _SAFE_USER_ID_RE.match(user_id):
|
||||
raise ValueError(f"Invalid user_id {user_id!r}: only alphanumeric characters, hyphens, and underscores are allowed.")
|
||||
return user_id
|
||||
|
||||
|
||||
def _join_host_path(base: str, *parts: str) -> str:
|
||||
"""Join host filesystem path segments while preserving native style.
|
||||
|
||||
@@ -134,44 +142,63 @@ class Paths:
|
||||
"""Per-agent memory file: `{base_dir}/agents/{name}/memory.json`."""
|
||||
return self.agent_dir(name) / "memory.json"
|
||||
|
||||
def thread_dir(self, thread_id: str) -> Path:
|
||||
def user_dir(self, user_id: str) -> Path:
|
||||
"""Directory for a specific user: `{base_dir}/users/{user_id}/`."""
|
||||
return self.base_dir / "users" / _validate_user_id(user_id)
|
||||
|
||||
def user_memory_file(self, user_id: str) -> Path:
|
||||
"""Per-user memory file: `{base_dir}/users/{user_id}/memory.json`."""
|
||||
return self.user_dir(user_id) / "memory.json"
|
||||
|
||||
def user_agent_memory_file(self, user_id: str, agent_name: str) -> Path:
|
||||
"""Per-user per-agent memory: `{base_dir}/users/{user_id}/agents/{name}/memory.json`."""
|
||||
return self.user_dir(user_id) / "agents" / agent_name.lower() / "memory.json"
|
||||
|
||||
def thread_dir(self, thread_id: str, *, user_id: str | None = None) -> Path:
|
||||
"""
|
||||
Host path for a thread's data: `{base_dir}/threads/{thread_id}/`
|
||||
Host path for a thread's data.
|
||||
|
||||
When *user_id* is provided:
|
||||
`{base_dir}/users/{user_id}/threads/{thread_id}/`
|
||||
Otherwise (legacy layout):
|
||||
`{base_dir}/threads/{thread_id}/`
|
||||
|
||||
This directory contains a `user-data/` subdirectory that is mounted
|
||||
as `/mnt/user-data/` inside the sandbox.
|
||||
|
||||
Raises:
|
||||
ValueError: If `thread_id` contains unsafe characters (path separators
|
||||
or `..`) that could cause directory traversal.
|
||||
ValueError: If `thread_id` or `user_id` contains unsafe characters (path
|
||||
separators or `..`) that could cause directory traversal.
|
||||
"""
|
||||
if user_id is not None:
|
||||
return self.user_dir(user_id) / "threads" / _validate_thread_id(thread_id)
|
||||
return self.base_dir / "threads" / _validate_thread_id(thread_id)
|
||||
|
||||
def sandbox_work_dir(self, thread_id: str) -> Path:
|
||||
def sandbox_work_dir(self, thread_id: str, *, user_id: str | None = None) -> Path:
|
||||
"""
|
||||
Host path for the agent's workspace directory.
|
||||
Host: `{base_dir}/threads/{thread_id}/user-data/workspace/`
|
||||
Sandbox: `/mnt/user-data/workspace/`
|
||||
"""
|
||||
return self.thread_dir(thread_id) / "user-data" / "workspace"
|
||||
return self.thread_dir(thread_id, user_id=user_id) / "user-data" / "workspace"
|
||||
|
||||
def sandbox_uploads_dir(self, thread_id: str) -> Path:
|
||||
def sandbox_uploads_dir(self, thread_id: str, *, user_id: str | None = None) -> Path:
|
||||
"""
|
||||
Host path for user-uploaded files.
|
||||
Host: `{base_dir}/threads/{thread_id}/user-data/uploads/`
|
||||
Sandbox: `/mnt/user-data/uploads/`
|
||||
"""
|
||||
return self.thread_dir(thread_id) / "user-data" / "uploads"
|
||||
return self.thread_dir(thread_id, user_id=user_id) / "user-data" / "uploads"
|
||||
|
||||
def sandbox_outputs_dir(self, thread_id: str) -> Path:
|
||||
def sandbox_outputs_dir(self, thread_id: str, *, user_id: str | None = None) -> Path:
|
||||
"""
|
||||
Host path for agent-generated artifacts.
|
||||
Host: `{base_dir}/threads/{thread_id}/user-data/outputs/`
|
||||
Sandbox: `/mnt/user-data/outputs/`
|
||||
"""
|
||||
return self.thread_dir(thread_id) / "user-data" / "outputs"
|
||||
return self.thread_dir(thread_id, user_id=user_id) / "user-data" / "outputs"
|
||||
|
||||
def acp_workspace_dir(self, thread_id: str) -> Path:
|
||||
def acp_workspace_dir(self, thread_id: str, *, user_id: str | None = None) -> Path:
|
||||
"""
|
||||
Host path for the ACP workspace of a specific thread.
|
||||
Host: `{base_dir}/threads/{thread_id}/acp-workspace/`
|
||||
@@ -180,41 +207,43 @@ class Paths:
|
||||
Each thread gets its own isolated ACP workspace so that concurrent
|
||||
sessions cannot read each other's ACP agent outputs.
|
||||
"""
|
||||
return self.thread_dir(thread_id) / "acp-workspace"
|
||||
return self.thread_dir(thread_id, user_id=user_id) / "acp-workspace"
|
||||
|
||||
def sandbox_user_data_dir(self, thread_id: str) -> Path:
|
||||
def sandbox_user_data_dir(self, thread_id: str, *, user_id: str | None = None) -> Path:
|
||||
"""
|
||||
Host path for the user-data root.
|
||||
Host: `{base_dir}/threads/{thread_id}/user-data/`
|
||||
Sandbox: `/mnt/user-data/`
|
||||
"""
|
||||
return self.thread_dir(thread_id) / "user-data"
|
||||
return self.thread_dir(thread_id, user_id=user_id) / "user-data"
|
||||
|
||||
def host_thread_dir(self, thread_id: str) -> str:
|
||||
def host_thread_dir(self, thread_id: str, *, user_id: str | None = None) -> str:
|
||||
"""Host path for a thread directory, preserving Windows path syntax."""
|
||||
if user_id is not None:
|
||||
return _join_host_path(self._host_base_dir_str(), "users", _validate_user_id(user_id), "threads", _validate_thread_id(thread_id))
|
||||
return _join_host_path(self._host_base_dir_str(), "threads", _validate_thread_id(thread_id))
|
||||
|
||||
def host_sandbox_user_data_dir(self, thread_id: str) -> str:
|
||||
def host_sandbox_user_data_dir(self, thread_id: str, *, user_id: str | None = None) -> str:
|
||||
"""Host path for a thread's user-data root."""
|
||||
return _join_host_path(self.host_thread_dir(thread_id), "user-data")
|
||||
return _join_host_path(self.host_thread_dir(thread_id, user_id=user_id), "user-data")
|
||||
|
||||
def host_sandbox_work_dir(self, thread_id: str) -> str:
|
||||
def host_sandbox_work_dir(self, thread_id: str, *, user_id: str | None = None) -> str:
|
||||
"""Host path for the workspace mount source."""
|
||||
return _join_host_path(self.host_sandbox_user_data_dir(thread_id), "workspace")
|
||||
return _join_host_path(self.host_sandbox_user_data_dir(thread_id, user_id=user_id), "workspace")
|
||||
|
||||
def host_sandbox_uploads_dir(self, thread_id: str) -> str:
|
||||
def host_sandbox_uploads_dir(self, thread_id: str, *, user_id: str | None = None) -> str:
|
||||
"""Host path for the uploads mount source."""
|
||||
return _join_host_path(self.host_sandbox_user_data_dir(thread_id), "uploads")
|
||||
return _join_host_path(self.host_sandbox_user_data_dir(thread_id, user_id=user_id), "uploads")
|
||||
|
||||
def host_sandbox_outputs_dir(self, thread_id: str) -> str:
|
||||
def host_sandbox_outputs_dir(self, thread_id: str, *, user_id: str | None = None) -> str:
|
||||
"""Host path for the outputs mount source."""
|
||||
return _join_host_path(self.host_sandbox_user_data_dir(thread_id), "outputs")
|
||||
return _join_host_path(self.host_sandbox_user_data_dir(thread_id, user_id=user_id), "outputs")
|
||||
|
||||
def host_acp_workspace_dir(self, thread_id: str) -> str:
|
||||
def host_acp_workspace_dir(self, thread_id: str, *, user_id: str | None = None) -> str:
|
||||
"""Host path for the ACP workspace mount source."""
|
||||
return _join_host_path(self.host_thread_dir(thread_id), "acp-workspace")
|
||||
return _join_host_path(self.host_thread_dir(thread_id, user_id=user_id), "acp-workspace")
|
||||
|
||||
def ensure_thread_dirs(self, thread_id: str) -> None:
|
||||
def ensure_thread_dirs(self, thread_id: str, *, user_id: str | None = None) -> None:
|
||||
"""Create all standard sandbox directories for a thread.
|
||||
|
||||
Directories are created with mode 0o777 so that sandbox containers
|
||||
@@ -228,24 +257,24 @@ class Paths:
|
||||
ACP agent invocation.
|
||||
"""
|
||||
for d in [
|
||||
self.sandbox_work_dir(thread_id),
|
||||
self.sandbox_uploads_dir(thread_id),
|
||||
self.sandbox_outputs_dir(thread_id),
|
||||
self.acp_workspace_dir(thread_id),
|
||||
self.sandbox_work_dir(thread_id, user_id=user_id),
|
||||
self.sandbox_uploads_dir(thread_id, user_id=user_id),
|
||||
self.sandbox_outputs_dir(thread_id, user_id=user_id),
|
||||
self.acp_workspace_dir(thread_id, user_id=user_id),
|
||||
]:
|
||||
d.mkdir(parents=True, exist_ok=True)
|
||||
d.chmod(0o777)
|
||||
|
||||
def delete_thread_dir(self, thread_id: str) -> None:
|
||||
def delete_thread_dir(self, thread_id: str, *, user_id: str | None = None) -> None:
|
||||
"""Delete all persisted data for a thread.
|
||||
|
||||
The operation is idempotent: missing thread directories are ignored.
|
||||
"""
|
||||
thread_dir = self.thread_dir(thread_id)
|
||||
thread_dir = self.thread_dir(thread_id, user_id=user_id)
|
||||
if thread_dir.exists():
|
||||
shutil.rmtree(thread_dir)
|
||||
|
||||
def resolve_virtual_path(self, thread_id: str, virtual_path: str) -> Path:
|
||||
def resolve_virtual_path(self, thread_id: str, virtual_path: str, *, user_id: str | None = None) -> Path:
|
||||
"""Resolve a sandbox virtual path to the actual host filesystem path.
|
||||
|
||||
Args:
|
||||
@@ -253,6 +282,7 @@ class Paths:
|
||||
virtual_path: Virtual path as seen inside the sandbox, e.g.
|
||||
``/mnt/user-data/outputs/report.pdf``.
|
||||
Leading slashes are stripped before matching.
|
||||
user_id: Optional user ID for user-scoped path resolution.
|
||||
|
||||
Returns:
|
||||
The resolved absolute host filesystem path.
|
||||
@@ -270,7 +300,7 @@ class Paths:
|
||||
raise ValueError(f"Path must start with /{prefix}")
|
||||
|
||||
relative = stripped[len(prefix) :].lstrip("/")
|
||||
base = self.sandbox_user_data_dir(thread_id).resolve()
|
||||
base = self.sandbox_user_data_dir(thread_id, user_id=user_id).resolve()
|
||||
actual = (base / relative).resolve()
|
||||
|
||||
try:
|
||||
|
||||
@@ -0,0 +1,34 @@
|
||||
"""Run event storage configuration.
|
||||
|
||||
Controls where run events (messages + execution traces) are persisted.
|
||||
|
||||
Backends:
|
||||
- memory: In-memory storage, data lost on restart. Suitable for
|
||||
development and testing.
|
||||
- db: SQL database via SQLAlchemy ORM. Provides full query capability.
|
||||
Suitable for production deployments.
|
||||
- jsonl: Append-only JSONL files. Lightweight alternative for
|
||||
single-node deployments that need persistence without a database.
|
||||
"""
|
||||
|
||||
from __future__ import annotations
|
||||
|
||||
from typing import Literal
|
||||
|
||||
from pydantic import BaseModel, ConfigDict, Field
|
||||
|
||||
|
||||
class RunEventsConfig(BaseModel):
|
||||
model_config = ConfigDict(frozen=True)
|
||||
backend: Literal["memory", "db", "jsonl"] = Field(
|
||||
default="memory",
|
||||
description="Storage backend for run events. 'memory' for development (no persistence), 'db' for production (SQL queries), 'jsonl' for lightweight single-node persistence.",
|
||||
)
|
||||
max_trace_content: int = Field(
|
||||
default=10240,
|
||||
description="Maximum trace content size in bytes before truncation (db backend only).",
|
||||
)
|
||||
track_token_usage: bool = Field(
|
||||
default=True,
|
||||
description="Whether RunJournal should accumulate token counts to RunRow.",
|
||||
)
|
||||
@@ -4,6 +4,8 @@ from pydantic import BaseModel, ConfigDict, Field
|
||||
class VolumeMountConfig(BaseModel):
|
||||
"""Configuration for a volume mount."""
|
||||
|
||||
model_config = ConfigDict(frozen=True)
|
||||
|
||||
host_path: str = Field(..., description="Path on the host machine")
|
||||
container_path: str = Field(..., description="Path inside the container")
|
||||
read_only: bool = Field(default=False, description="Whether the mount is read-only")
|
||||
@@ -80,4 +82,4 @@ class SandboxConfig(BaseModel):
|
||||
description="Maximum characters to keep from ls tool output. Output exceeding this limit is head-truncated. Set to 0 to disable truncation.",
|
||||
)
|
||||
|
||||
model_config = ConfigDict(extra="allow")
|
||||
model_config = ConfigDict(extra="allow", frozen=True)
|
||||
|
||||
@@ -1,9 +1,11 @@
|
||||
from pydantic import BaseModel, Field
|
||||
from pydantic import BaseModel, ConfigDict, Field
|
||||
|
||||
|
||||
class SkillEvolutionConfig(BaseModel):
|
||||
"""Configuration for agent-managed skill evolution."""
|
||||
|
||||
model_config = ConfigDict(frozen=True)
|
||||
|
||||
enabled: bool = Field(
|
||||
default=False,
|
||||
description="Whether the agent can create and modify skills under skills/custom.",
|
||||
|
||||
@@ -1,6 +1,6 @@
|
||||
from pathlib import Path
|
||||
|
||||
from pydantic import BaseModel, Field
|
||||
from pydantic import BaseModel, ConfigDict, Field
|
||||
|
||||
|
||||
def _default_repo_root() -> Path:
|
||||
@@ -11,6 +11,8 @@ def _default_repo_root() -> Path:
|
||||
class SkillsConfig(BaseModel):
|
||||
"""Configuration for skills system"""
|
||||
|
||||
model_config = ConfigDict(frozen=True)
|
||||
|
||||
path: str | None = Field(
|
||||
default=None,
|
||||
description="Path to skills directory. If not specified, defaults to ../skills relative to backend directory",
|
||||
|
||||
@@ -2,7 +2,7 @@
|
||||
|
||||
from typing import Literal
|
||||
|
||||
from pydantic import BaseModel, Field
|
||||
from pydantic import BaseModel, ConfigDict, Field
|
||||
|
||||
StreamBridgeType = Literal["memory", "redis"]
|
||||
|
||||
@@ -10,6 +10,8 @@ StreamBridgeType = Literal["memory", "redis"]
|
||||
class StreamBridgeConfig(BaseModel):
|
||||
"""Configuration for the stream bridge that connects agent workers to SSE endpoints."""
|
||||
|
||||
model_config = ConfigDict(frozen=True)
|
||||
|
||||
type: StreamBridgeType = Field(
|
||||
default="memory",
|
||||
description="Stream bridge backend type. 'memory' uses in-process asyncio.Queue (single-process only). 'redis' uses Redis Streams (planned for Phase 2, not yet implemented).",
|
||||
@@ -22,25 +24,3 @@ class StreamBridgeConfig(BaseModel):
|
||||
default=256,
|
||||
description="Maximum number of events buffered per run in the memory bridge.",
|
||||
)
|
||||
|
||||
|
||||
# Global configuration instance — None means no stream bridge is configured
|
||||
# (falls back to memory with defaults).
|
||||
_stream_bridge_config: StreamBridgeConfig | None = None
|
||||
|
||||
|
||||
def get_stream_bridge_config() -> StreamBridgeConfig | None:
|
||||
"""Get the current stream bridge configuration, or None if not configured."""
|
||||
return _stream_bridge_config
|
||||
|
||||
|
||||
def set_stream_bridge_config(config: StreamBridgeConfig | None) -> None:
|
||||
"""Set the stream bridge configuration."""
|
||||
global _stream_bridge_config
|
||||
_stream_bridge_config = config
|
||||
|
||||
|
||||
def load_stream_bridge_config_from_dict(config_dict: dict) -> None:
|
||||
"""Load stream bridge configuration from a dictionary."""
|
||||
global _stream_bridge_config
|
||||
_stream_bridge_config = StreamBridgeConfig(**config_dict)
|
||||
|
||||
@@ -1,15 +1,13 @@
|
||||
"""Configuration for the subagent system loaded from config.yaml."""
|
||||
|
||||
import logging
|
||||
|
||||
from pydantic import BaseModel, Field
|
||||
|
||||
logger = logging.getLogger(__name__)
|
||||
from pydantic import BaseModel, ConfigDict, Field
|
||||
|
||||
|
||||
class SubagentOverrideConfig(BaseModel):
|
||||
"""Per-agent configuration overrides."""
|
||||
|
||||
model_config = ConfigDict(frozen=True)
|
||||
|
||||
timeout_seconds: int | None = Field(
|
||||
default=None,
|
||||
ge=1,
|
||||
@@ -71,6 +69,8 @@ class CustomSubagentConfig(BaseModel):
|
||||
class SubagentsAppConfig(BaseModel):
|
||||
"""Configuration for the subagent system."""
|
||||
|
||||
model_config = ConfigDict(frozen=True)
|
||||
|
||||
timeout_seconds: int = Field(
|
||||
default=900,
|
||||
ge=1,
|
||||
@@ -140,48 +140,3 @@ class SubagentsAppConfig(BaseModel):
|
||||
if override is not None and override.skills is not None:
|
||||
return override.skills
|
||||
return None
|
||||
|
||||
|
||||
_subagents_config: SubagentsAppConfig = SubagentsAppConfig()
|
||||
|
||||
|
||||
def get_subagents_app_config() -> SubagentsAppConfig:
|
||||
"""Get the current subagents configuration."""
|
||||
return _subagents_config
|
||||
|
||||
|
||||
def load_subagents_config_from_dict(config_dict: dict) -> None:
|
||||
"""Load subagents configuration from a dictionary."""
|
||||
global _subagents_config
|
||||
_subagents_config = SubagentsAppConfig(**config_dict)
|
||||
|
||||
overrides_summary = {}
|
||||
for name, override in _subagents_config.agents.items():
|
||||
parts = []
|
||||
if override.timeout_seconds is not None:
|
||||
parts.append(f"timeout={override.timeout_seconds}s")
|
||||
if override.max_turns is not None:
|
||||
parts.append(f"max_turns={override.max_turns}")
|
||||
if override.model is not None:
|
||||
parts.append(f"model={override.model}")
|
||||
if override.skills is not None:
|
||||
parts.append(f"skills={override.skills}")
|
||||
if parts:
|
||||
overrides_summary[name] = ", ".join(parts)
|
||||
|
||||
custom_agents_names = list(_subagents_config.custom_agents.keys())
|
||||
|
||||
if overrides_summary or custom_agents_names:
|
||||
logger.info(
|
||||
"Subagents config loaded: default timeout=%ss, default max_turns=%s, per-agent overrides=%s, custom_agents=%s",
|
||||
_subagents_config.timeout_seconds,
|
||||
_subagents_config.max_turns,
|
||||
overrides_summary or "none",
|
||||
custom_agents_names or "none",
|
||||
)
|
||||
else:
|
||||
logger.info(
|
||||
"Subagents config loaded: default timeout=%ss, default max_turns=%s, no per-agent overrides",
|
||||
_subagents_config.timeout_seconds,
|
||||
_subagents_config.max_turns,
|
||||
)
|
||||
|
||||
@@ -2,7 +2,7 @@
|
||||
|
||||
from typing import Literal
|
||||
|
||||
from pydantic import BaseModel, Field
|
||||
from pydantic import BaseModel, ConfigDict, Field
|
||||
|
||||
ContextSizeType = Literal["fraction", "tokens", "messages"]
|
||||
|
||||
@@ -10,6 +10,8 @@ ContextSizeType = Literal["fraction", "tokens", "messages"]
|
||||
class ContextSize(BaseModel):
|
||||
"""Context size specification for trigger or keep parameters."""
|
||||
|
||||
model_config = ConfigDict(frozen=True)
|
||||
|
||||
type: ContextSizeType = Field(description="Type of context size specification")
|
||||
value: int | float = Field(description="Value for the context size specification")
|
||||
|
||||
@@ -21,6 +23,8 @@ class ContextSize(BaseModel):
|
||||
class SummarizationConfig(BaseModel):
|
||||
"""Configuration for automatic conversation summarization."""
|
||||
|
||||
model_config = ConfigDict(frozen=True)
|
||||
|
||||
enabled: bool = Field(
|
||||
default=False,
|
||||
description="Whether to enable automatic conversation summarization",
|
||||
@@ -70,24 +74,3 @@ class SummarizationConfig(BaseModel):
|
||||
default_factory=lambda: ["read_file", "read", "view", "cat"],
|
||||
description="Tool names treated as skill file reads when preserving recently-loaded skills across summarization.",
|
||||
)
|
||||
|
||||
|
||||
# Global configuration instance
|
||||
_summarization_config: SummarizationConfig = SummarizationConfig()
|
||||
|
||||
|
||||
def get_summarization_config() -> SummarizationConfig:
|
||||
"""Get the current summarization configuration."""
|
||||
return _summarization_config
|
||||
|
||||
|
||||
def set_summarization_config(config: SummarizationConfig) -> None:
|
||||
"""Set the summarization configuration."""
|
||||
global _summarization_config
|
||||
_summarization_config = config
|
||||
|
||||
|
||||
def load_summarization_config_from_dict(config_dict: dict) -> None:
|
||||
"""Load summarization configuration from a dictionary."""
|
||||
global _summarization_config
|
||||
_summarization_config = SummarizationConfig(**config_dict)
|
||||
|
||||
@@ -1,11 +1,13 @@
|
||||
"""Configuration for automatic thread title generation."""
|
||||
|
||||
from pydantic import BaseModel, Field
|
||||
from pydantic import BaseModel, ConfigDict, Field
|
||||
|
||||
|
||||
class TitleConfig(BaseModel):
|
||||
"""Configuration for automatic thread title generation."""
|
||||
|
||||
model_config = ConfigDict(frozen=True)
|
||||
|
||||
enabled: bool = Field(
|
||||
default=True,
|
||||
description="Whether to enable automatic title generation",
|
||||
@@ -30,24 +32,3 @@ class TitleConfig(BaseModel):
|
||||
default=("Generate a concise title (max {max_words} words) for this conversation.\nUser: {user_msg}\nAssistant: {assistant_msg}\n\nReturn ONLY the title, no quotes, no explanation."),
|
||||
description="Prompt template for title generation",
|
||||
)
|
||||
|
||||
|
||||
# Global configuration instance
|
||||
_title_config: TitleConfig = TitleConfig()
|
||||
|
||||
|
||||
def get_title_config() -> TitleConfig:
|
||||
"""Get the current title configuration."""
|
||||
return _title_config
|
||||
|
||||
|
||||
def set_title_config(config: TitleConfig) -> None:
|
||||
"""Set the title configuration."""
|
||||
global _title_config
|
||||
_title_config = config
|
||||
|
||||
|
||||
def load_title_config_from_dict(config_dict: dict) -> None:
|
||||
"""Load title configuration from a dictionary."""
|
||||
global _title_config
|
||||
_title_config = TitleConfig(**config_dict)
|
||||
|
||||
@@ -1,7 +1,9 @@
|
||||
from pydantic import BaseModel, Field
|
||||
from pydantic import BaseModel, ConfigDict, Field
|
||||
|
||||
|
||||
class TokenUsageConfig(BaseModel):
|
||||
"""Configuration for token usage tracking."""
|
||||
|
||||
model_config = ConfigDict(frozen=True)
|
||||
|
||||
enabled: bool = Field(default=False, description="Enable token usage tracking middleware")
|
||||
|
||||
@@ -5,7 +5,7 @@ class ToolGroupConfig(BaseModel):
|
||||
"""Config section for a tool group"""
|
||||
|
||||
name: str = Field(..., description="Unique name for the tool group")
|
||||
model_config = ConfigDict(extra="allow")
|
||||
model_config = ConfigDict(extra="allow", frozen=True)
|
||||
|
||||
|
||||
class ToolConfig(BaseModel):
|
||||
@@ -17,4 +17,4 @@ class ToolConfig(BaseModel):
|
||||
...,
|
||||
description="Variable name of the tool provider(e.g. deerflow.sandbox.tools:bash_tool)",
|
||||
)
|
||||
model_config = ConfigDict(extra="allow")
|
||||
model_config = ConfigDict(extra="allow", frozen=True)
|
||||
|
||||
@@ -1,6 +1,6 @@
|
||||
"""Configuration for deferred tool loading via tool_search."""
|
||||
|
||||
from pydantic import BaseModel, Field
|
||||
from pydantic import BaseModel, ConfigDict, Field
|
||||
|
||||
|
||||
class ToolSearchConfig(BaseModel):
|
||||
@@ -11,25 +11,9 @@ class ToolSearchConfig(BaseModel):
|
||||
via the tool_search tool at runtime.
|
||||
"""
|
||||
|
||||
model_config = ConfigDict(frozen=True)
|
||||
|
||||
enabled: bool = Field(
|
||||
default=False,
|
||||
description="Defer tools and enable tool_search",
|
||||
)
|
||||
|
||||
|
||||
_tool_search_config: ToolSearchConfig | None = None
|
||||
|
||||
|
||||
def get_tool_search_config() -> ToolSearchConfig:
|
||||
"""Get the tool search config, loading from AppConfig if needed."""
|
||||
global _tool_search_config
|
||||
if _tool_search_config is None:
|
||||
_tool_search_config = ToolSearchConfig()
|
||||
return _tool_search_config
|
||||
|
||||
|
||||
def load_tool_search_config_from_dict(data: dict) -> ToolSearchConfig:
|
||||
"""Load tool search config from a dict (called during AppConfig loading)."""
|
||||
global _tool_search_config
|
||||
_tool_search_config = ToolSearchConfig.model_validate(data)
|
||||
return _tool_search_config
|
||||
|
||||
@@ -1,7 +1,7 @@
|
||||
import os
|
||||
import threading
|
||||
|
||||
from pydantic import BaseModel, Field
|
||||
from pydantic import BaseModel, ConfigDict, Field
|
||||
|
||||
_config_lock = threading.Lock()
|
||||
|
||||
@@ -9,6 +9,8 @@ _config_lock = threading.Lock()
|
||||
class LangSmithTracingConfig(BaseModel):
|
||||
"""Configuration for LangSmith tracing."""
|
||||
|
||||
model_config = ConfigDict(frozen=True)
|
||||
|
||||
enabled: bool = Field(...)
|
||||
api_key: str | None = Field(...)
|
||||
project: str = Field(...)
|
||||
@@ -26,6 +28,8 @@ class LangSmithTracingConfig(BaseModel):
|
||||
class LangfuseTracingConfig(BaseModel):
|
||||
"""Configuration for Langfuse tracing."""
|
||||
|
||||
model_config = ConfigDict(frozen=True)
|
||||
|
||||
enabled: bool = Field(...)
|
||||
public_key: str | None = Field(...)
|
||||
secret_key: str | None = Field(...)
|
||||
@@ -50,6 +54,8 @@ class LangfuseTracingConfig(BaseModel):
|
||||
class TracingConfig(BaseModel):
|
||||
"""Tracing configuration for supported providers."""
|
||||
|
||||
model_config = ConfigDict(frozen=True)
|
||||
|
||||
langsmith: LangSmithTracingConfig = Field(...)
|
||||
langfuse: LangfuseTracingConfig = Field(...)
|
||||
|
||||
|
||||
Reference in New Issue
Block a user