mirror of
https://github.com/bytedance/deer-flow.git
synced 2026-11-09 04:20:34 +00:00
aaca3eeaeb
* refactor(agent): ground runtime decisions in structured evidence Use producer status and structured errors for tool recovery, preserve memory context without lexical confirmation, and remove predetermined receipt and skill conclusions. Require explicit MCP discovery and authenticated schedule trial actions. Preserve authorization, ownership, isolation, and bounded execution; update documentation and regression coverage. * test(sandbox): expect read_file initialization error callback * fix(agent): address evidence review follow-ups * fix(agent): preserve retry budgets for OpenAI transport errors * fix(agent): expose tool execution status in model requests Project validated execution metadata and exact tool text into request-only JSON so status survives provider serialization. Preserve stored results and receipt hashes, cover SDK and graph boundaries, and migrate replay input hashes without changing recorded responses. --------- Co-authored-by: Willem Jiang <willem.jiang@gmail.com>
55 lines
2.7 KiB
Python
55 lines
2.7 KiB
Python
"""Runtime decisions require structured evidence, not prose matches."""
|
|
|
|
import httpx
|
|
import pytest
|
|
from langchain_core.messages import HumanMessage
|
|
|
|
from deerflow.agents.middlewares.llm_error_handling_middleware import LLMErrorHandlingMiddleware, _extract_in_band_status
|
|
from deerflow.agents.middlewares.mcp_routing_middleware import McpRoutingMiddleware
|
|
from deerflow.config.app_config import AppConfig
|
|
from deerflow.config.sandbox_config import SandboxConfig
|
|
|
|
|
|
class ProviderError(Exception):
|
|
def __init__(self, text, status=None, code=None, body=None):
|
|
super().__init__(text)
|
|
self.status_code = status
|
|
self.code = code
|
|
self.body = body
|
|
|
|
|
|
@pytest.mark.parametrize("text", ["No billing or permission issue; unknown failure", "server busy is only a quoted example", "HTTP 503 is not the actual response", "余额不足只是示例"])
|
|
def test_provider_prose_does_not_establish_error_category(text):
|
|
middleware = LLMErrorHandlingMiddleware(app_config=AppConfig(sandbox=SandboxConfig(use="test")))
|
|
assert middleware._classify_error(ProviderError(text)) == (False, "generic")
|
|
|
|
|
|
@pytest.mark.parametrize(
|
|
("error", "expected"),
|
|
[
|
|
(ProviderError("quota billing permission", status=503), (True, "transient")),
|
|
(ProviderError("server busy", status=401), (False, "auth")),
|
|
(ProviderError("server busy", status=400), (False, "generic")),
|
|
(ProviderError("anything", status=429, code="insufficient_quota"), (False, "quota")),
|
|
(ProviderError("anything", status=429, code="limit_burst_rate"), (True, "burst_rate")),
|
|
(IndexError("list index out of range"), (False, "generic")),
|
|
(httpx.ReadError("peer closed"), (True, "transient")),
|
|
(ProviderError("not an HTTP status", status=True), (False, "generic")),
|
|
],
|
|
)
|
|
def test_provider_classification_uses_status_codes_and_real_types(error, expected):
|
|
middleware = LLMErrorHandlingMiddleware(app_config=AppConfig(sandbox=SandboxConfig(use="test")))
|
|
assert middleware._classify_error(error) == expected
|
|
|
|
|
|
def test_in_band_status_does_not_parse_numbers_from_prose():
|
|
assert _extract_in_band_status(ProviderError("Example [504], not an actual status")) is None
|
|
assert _extract_in_band_status(ProviderError("anything", body={"error": {"status": 504}})) == 504
|
|
|
|
|
|
@pytest.mark.parametrize("text", ["orders", "do not query orders", "订单只是引用", "What does orders mean?", "unrelated preorders text"])
|
|
def test_mcp_routing_keywords_never_promote_schemas(text):
|
|
middleware = McpRoutingMiddleware({"postgres_query": {"priority": 100, "keywords": ["orders", "订单"]}}, "hash", 3)
|
|
state = {"messages": [HumanMessage(content=text)]}
|
|
assert middleware.before_model(state, None) is None
|