greatmengqi
3e6a34297d
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).
77 lines
2.8 KiB
Python
77 lines
2.8 KiB
Python
import json
|
|
|
|
from firecrawl import FirecrawlApp
|
|
from langchain.tools import ToolRuntime, tool
|
|
|
|
from deerflow.config.app_config import AppConfig
|
|
from deerflow.config.deer_flow_context import resolve_context
|
|
|
|
|
|
def _get_firecrawl_client(app_config: AppConfig, tool_name: str = "web_search") -> FirecrawlApp:
|
|
tool_config = app_config.get_tool_config(tool_name)
|
|
api_key = None
|
|
if tool_config is not None and "api_key" in tool_config.model_extra:
|
|
api_key = tool_config.model_extra.get("api_key")
|
|
return FirecrawlApp(api_key=api_key) # type: ignore[arg-type]
|
|
|
|
|
|
@tool("web_search", parse_docstring=True)
|
|
def web_search_tool(query: str, runtime: ToolRuntime) -> str:
|
|
"""Search the web.
|
|
|
|
Args:
|
|
query: The query to search for.
|
|
"""
|
|
try:
|
|
app_config = resolve_context(runtime).app_config
|
|
tool_config = app_config.get_tool_config("web_search")
|
|
max_results = 5
|
|
if tool_config is not None:
|
|
max_results = tool_config.model_extra.get("max_results", max_results)
|
|
|
|
client = _get_firecrawl_client(app_config, "web_search")
|
|
result = client.search(query, limit=max_results)
|
|
|
|
# result.web contains list of SearchResultWeb objects
|
|
web_results = result.web or []
|
|
normalized_results = [
|
|
{
|
|
"title": getattr(item, "title", "") or "",
|
|
"url": getattr(item, "url", "") or "",
|
|
"snippet": getattr(item, "description", "") or "",
|
|
}
|
|
for item in web_results
|
|
]
|
|
json_results = json.dumps(normalized_results, indent=2, ensure_ascii=False)
|
|
return json_results
|
|
except Exception as e:
|
|
return f"Error: {str(e)}"
|
|
|
|
|
|
@tool("web_fetch", parse_docstring=True)
|
|
def web_fetch_tool(url: str, runtime: ToolRuntime) -> str:
|
|
"""Fetch the contents of a web page at a given URL.
|
|
Only fetch EXACT URLs that have been provided directly by the user or have been returned in results from the web_search and web_fetch tools.
|
|
This tool can NOT access content that requires authentication, such as private Google Docs or pages behind login walls.
|
|
Do NOT add www. to URLs that do NOT have them.
|
|
URLs must include the schema: https://example.com is a valid URL while example.com is an invalid URL.
|
|
|
|
Args:
|
|
url: The URL to fetch the contents of.
|
|
"""
|
|
try:
|
|
app_config = resolve_context(runtime).app_config
|
|
client = _get_firecrawl_client(app_config, "web_fetch")
|
|
result = client.scrape(url, formats=["markdown"])
|
|
|
|
markdown_content = result.markdown or ""
|
|
metadata = result.metadata
|
|
title = metadata.title if metadata and metadata.title else "Untitled"
|
|
|
|
if not markdown_content:
|
|
return "Error: No content found"
|
|
except Exception as e:
|
|
return f"Error: {str(e)}"
|
|
|
|
return f"# {title}\n\n{markdown_content[:4096]}"
|