mirror of
https://gitee.com/wanwujie/deer-flow
synced 2026-04-18 20:14:44 +08:00
* refactor: extract shared utils to break harness→app cross-layer imports Move _validate_skill_frontmatter to src/skills/validation.py and CONVERTIBLE_EXTENSIONS + convert_file_to_markdown to src/utils/file_conversion.py. This eliminates the two reverse dependencies from client.py (harness layer) into gateway/routers/ (app layer), preparing for the harness/app package split. Co-Authored-By: Claude Opus 4.6 <noreply@anthropic.com> * refactor: split backend/src into harness (deerflow.*) and app (app.*) Physically split the monolithic backend/src/ package into two layers: - **Harness** (`packages/harness/deerflow/`): publishable agent framework package with import prefix `deerflow.*`. Contains agents, sandbox, tools, models, MCP, skills, config, and all core infrastructure. - **App** (`app/`): unpublished application code with import prefix `app.*`. Contains gateway (FastAPI REST API) and channels (IM integrations). Key changes: - Move 13 harness modules to packages/harness/deerflow/ via git mv - Move gateway + channels to app/ via git mv - Rename all imports: src.* → deerflow.* (harness) / app.* (app layer) - Set up uv workspace with deerflow-harness as workspace member - Update langgraph.json, config.example.yaml, all scripts, Docker files - Add build-system (hatchling) to harness pyproject.toml - Add PYTHONPATH=. to gateway startup commands for app.* resolution - Update ruff.toml with known-first-party for import sorting - Update all documentation to reflect new directory structure Boundary rule enforced: harness code never imports from app. All 429 tests pass. Lint clean. Co-Authored-By: Claude Opus 4.6 <noreply@anthropic.com> * chore: add harness→app boundary check test and update docs Add test_harness_boundary.py that scans all Python files in packages/harness/deerflow/ and fails if any `from app.*` or `import app.*` statement is found. This enforces the architectural rule that the harness layer never depends on the app layer. Update CLAUDE.md to document the harness/app split architecture, import conventions, and the boundary enforcement test. Co-Authored-By: Claude Opus 4.6 <noreply@anthropic.com> * feat: add config versioning with auto-upgrade on startup When config.example.yaml schema changes, developers' local config.yaml files can silently become outdated. This adds a config_version field and auto-upgrade mechanism so breaking changes (like src.* → deerflow.* renames) are applied automatically before services start. - Add config_version: 1 to config.example.yaml - Add startup version check warning in AppConfig.from_file() - Add scripts/config-upgrade.sh with migration registry for value replacements - Add `make config-upgrade` target - Auto-run config-upgrade in serve.sh and start-daemon.sh before starting services - Add config error hints in service failure messages Co-Authored-By: Claude Opus 4.6 <noreply@anthropic.com> * fix comments * fix: update src.* import in test_sandbox_tools_security to deerflow.* Co-Authored-By: Claude Opus 4.6 <noreply@anthropic.com> * fix: handle empty config and search parent dirs for config.example.yaml Address Copilot review comments on PR #1131: - Guard against yaml.safe_load() returning None for empty config files - Search parent directories for config.example.yaml instead of only looking next to config.yaml, fixing detection in common setups Co-Authored-By: Claude Opus 4.6 <noreply@anthropic.com> * fix: correct skills root path depth and config_version type coercion - loader.py: fix get_skills_root_path() to use 5 parent levels (was 3) after harness split, file lives at packages/harness/deerflow/skills/ so parent×3 resolved to backend/packages/harness/ instead of backend/ - app_config.py: coerce config_version to int() before comparison in _check_config_version() to prevent TypeError when YAML stores value as string (e.g. config_version: "1") - tests: add regression tests for both fixes Co-Authored-By: Claude Sonnet 4.6 <noreply@anthropic.com> * fix: update test imports from src.* to deerflow.*/app.* after harness refactor Co-Authored-By: Claude Sonnet 4.6 <noreply@anthropic.com> --------- Co-authored-by: Claude Opus 4.6 <noreply@anthropic.com>
95 lines
3.4 KiB
Python
95 lines
3.4 KiB
Python
import logging
|
||
import os
|
||
import threading
|
||
|
||
from pydantic import BaseModel, Field
|
||
|
||
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
|
||
|
||
|
||
_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``.
|
||
"""
|
||
for name in names:
|
||
value = os.environ.get(name)
|
||
if value is not None and value.strip():
|
||
return value.strip().lower() in _TRUTHY_VALUES
|
||
return False
|
||
|
||
|
||
def _first_env_value(*names: str) -> str | None:
|
||
"""Return the first non-empty environment value from candidate names."""
|
||
for name in names:
|
||
value = os.environ.get(name)
|
||
if value and value.strip():
|
||
return value.strip()
|
||
return 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.
|
||
"""
|
||
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(
|
||
# 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",
|
||
)
|
||
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
|