mirror of
https://github.com/bytedance/deer-flow.git
synced 2026-11-13 06:31:47 +00:00
53c5195e5d
* fix(gateway): name the agent problem when run admission rejects agent_name Since #5238, run admission loads the named custom agent's config for every run, with or without a knowledge scope, and folded every failure into "knowledge_scope assistant configuration could not be resolved". Messaging a chat whose custom agent was deleted, or passing a malformed agent_name, pointed callers at the knowledge base instead of the agent. The 422 status is unchanged; the detail now says which problem it is: - Agent '<name>' not found - Invalid agent_name '<value>': must contain only letters, digits, and hyphens after normalization. (shared with custom_agent_name(), which gains a field= argument; existing callers keep the default) - Invalid agent_name: expected a string, got <type>. - Agent '<name>' configuration could not be loaded * docs(changelog): reference #8087 for the run admission agent_name detail * fix(gateway): bound the agent name echoed in run admission errors Address review on #8087: admission now echoes the caller's raw agent_name, which start_run merges from config/context without a size check, so an oversized value was reflected verbatim into the 422 detail and any log line that records it. Cap the echoed name at 200 characters in the invalid-name message (shared with assistant_id validation) and in the not-found / unreadable-config messages. --------- Co-authored-by: Willem Jiang <willem.jiang@gmail.com>
313 lines
10 KiB
Python
313 lines
10 KiB
Python
from types import SimpleNamespace
|
|
|
|
import pytest
|
|
from fastapi import HTTPException
|
|
from langchain_core.messages import AIMessage, HumanMessage
|
|
|
|
from app.gateway.knowledge_scope_admission import admit_message_knowledge_scope
|
|
from app.gateway.services import strip_internal_context_keys
|
|
from deerflow.config.tool_config import ToolConfig
|
|
from deerflow.knowledge_scope import KNOWLEDGE_SCOPE_KEY, KNOWLEDGE_SCOPE_RUNTIME_KEY
|
|
|
|
|
|
def _app_config(provider: str = "deerflow.community.ragflow.tools:knowledge_search_tool"):
|
|
tool_config = ToolConfig(
|
|
name="knowledge_search",
|
|
group="knowledge",
|
|
use=provider,
|
|
)
|
|
return SimpleNamespace(
|
|
knowledge_base=SimpleNamespace(enabled=True),
|
|
get_tool_config=lambda name: tool_config if name == "knowledge_search" else None,
|
|
)
|
|
|
|
|
|
def _agent_config(tool_groups=None):
|
|
return SimpleNamespace(tool_groups=tool_groups)
|
|
|
|
|
|
def _input(message):
|
|
return {"messages": [message]}
|
|
|
|
|
|
def test_admission_canonicalizes_custom_agent_human_message() -> None:
|
|
graph_input = _input(
|
|
HumanMessage(
|
|
content="question",
|
|
additional_kwargs={
|
|
KNOWLEDGE_SCOPE_KEY: {
|
|
"version": 1,
|
|
"mode": "selected",
|
|
"dataset_ids": [" dataset-a ", "dataset-a"],
|
|
}
|
|
},
|
|
)
|
|
)
|
|
|
|
admitted = admit_message_knowledge_scope(
|
|
graph_input,
|
|
assistant_id="agriculture-agent",
|
|
app_config=_app_config(),
|
|
agent_config=_agent_config(None),
|
|
)
|
|
|
|
assert admitted == {
|
|
"version": 1,
|
|
"mode": "selected",
|
|
"dataset_ids": ["dataset-a"],
|
|
}
|
|
assert graph_input["messages"][0].additional_kwargs[KNOWLEDGE_SCOPE_KEY] == admitted
|
|
|
|
|
|
@pytest.mark.parametrize(
|
|
("assistant_id", "provider", "tool_groups"),
|
|
[
|
|
(None, "deerflow.community.ragflow.tools:knowledge_search_tool", None),
|
|
("agent", "unknown:knowledge_search_tool", None),
|
|
("agent", "deerflow.community.ragflow.tools:knowledge_search_tool", []),
|
|
("agent", "deerflow.community.ragflow.tools:knowledge_search_tool", ["web"]),
|
|
],
|
|
)
|
|
def test_scope_is_rejected_outside_supported_custom_agent(
|
|
assistant_id: str | None,
|
|
provider: str,
|
|
tool_groups: list[str] | None,
|
|
) -> None:
|
|
graph_input = _input(
|
|
HumanMessage(
|
|
content="question",
|
|
additional_kwargs={KNOWLEDGE_SCOPE_KEY: {"version": 1, "mode": "all"}},
|
|
)
|
|
)
|
|
|
|
with pytest.raises(HTTPException) as exc_info:
|
|
admit_message_knowledge_scope(
|
|
graph_input,
|
|
assistant_id=assistant_id,
|
|
app_config=_app_config(provider),
|
|
agent_config=_agent_config(tool_groups) if assistant_id not in {None, "lead_agent"} else None,
|
|
)
|
|
|
|
assert exc_info.value.status_code == 422
|
|
|
|
|
|
def test_admission_accepts_main_agent_with_configured_ragflow_provider() -> None:
|
|
graph_input = _input(
|
|
HumanMessage(
|
|
content="question",
|
|
additional_kwargs={KNOWLEDGE_SCOPE_KEY: {"version": 1, "mode": "all"}},
|
|
)
|
|
)
|
|
|
|
admitted = admit_message_knowledge_scope(
|
|
graph_input,
|
|
assistant_id="lead_agent",
|
|
app_config=_app_config(),
|
|
agent_config=None,
|
|
)
|
|
|
|
assert admitted == {"version": 1, "mode": "all"}
|
|
|
|
|
|
def test_scope_on_non_human_or_multiple_humans_is_rejected() -> None:
|
|
invalid_ai = _input(
|
|
AIMessage(
|
|
content="answer",
|
|
additional_kwargs={KNOWLEDGE_SCOPE_KEY: {"version": 1, "mode": "all"}},
|
|
)
|
|
)
|
|
with pytest.raises(HTTPException, match="HumanMessage"):
|
|
admit_message_knowledge_scope(
|
|
invalid_ai,
|
|
assistant_id="agent",
|
|
app_config=_app_config(),
|
|
agent_config=_agent_config(),
|
|
)
|
|
|
|
duplicate = {
|
|
"messages": [
|
|
HumanMessage(
|
|
content="one",
|
|
additional_kwargs={KNOWLEDGE_SCOPE_KEY: {"version": 1, "mode": "all"}},
|
|
),
|
|
HumanMessage(
|
|
content="two",
|
|
additional_kwargs={KNOWLEDGE_SCOPE_KEY: {"version": 1, "mode": "all"}},
|
|
),
|
|
]
|
|
}
|
|
with pytest.raises(HTTPException, match="one new HumanMessage"):
|
|
admit_message_knowledge_scope(
|
|
duplicate,
|
|
assistant_id="agent",
|
|
app_config=_app_config(),
|
|
agent_config=_agent_config(),
|
|
)
|
|
|
|
|
|
def test_scope_on_an_earlier_human_message_is_rejected() -> None:
|
|
graph_input = {
|
|
"messages": [
|
|
HumanMessage(
|
|
content="historical",
|
|
additional_kwargs={KNOWLEDGE_SCOPE_KEY: {"version": 1, "mode": "all"}},
|
|
),
|
|
HumanMessage(content="current"),
|
|
]
|
|
}
|
|
|
|
with pytest.raises(HTTPException, match="current HumanMessage"):
|
|
admit_message_knowledge_scope(
|
|
graph_input,
|
|
assistant_id="agent",
|
|
app_config=_app_config(),
|
|
agent_config=_agent_config(),
|
|
)
|
|
|
|
|
|
def test_recovery_scope_replaces_client_forgery_and_legacy_removes_it() -> None:
|
|
graph_input = _input(
|
|
HumanMessage(
|
|
content="question",
|
|
additional_kwargs={KNOWLEDGE_SCOPE_KEY: {"version": 1, "mode": "all"}},
|
|
)
|
|
)
|
|
recovered = admit_message_knowledge_scope(
|
|
graph_input,
|
|
assistant_id="agent",
|
|
app_config=_app_config(),
|
|
agent_config=_agent_config(),
|
|
recovery_scope={"version": 1, "mode": "disabled"},
|
|
recovery=True,
|
|
)
|
|
assert recovered == {"version": 1, "mode": "disabled"}
|
|
assert graph_input["messages"][0].additional_kwargs[KNOWLEDGE_SCOPE_KEY] == recovered
|
|
|
|
admitted = admit_message_knowledge_scope(
|
|
graph_input,
|
|
assistant_id="agent",
|
|
app_config=_app_config(),
|
|
agent_config=_agent_config(),
|
|
recovery_scope=None,
|
|
recovery=True,
|
|
)
|
|
assert admitted is None
|
|
assert KNOWLEDGE_SCOPE_KEY not in graph_input["messages"][0].additional_kwargs
|
|
|
|
|
|
def test_free_form_runtime_scope_fields_are_scrubbed() -> None:
|
|
config = {
|
|
"context": {
|
|
KNOWLEDGE_SCOPE_KEY: {"version": 1, "mode": "all"},
|
|
KNOWLEDGE_SCOPE_RUNTIME_KEY: {"version": 1, "mode": "disabled"},
|
|
},
|
|
"configurable": {
|
|
KNOWLEDGE_SCOPE_KEY: {"version": 1, "mode": "all"},
|
|
KNOWLEDGE_SCOPE_RUNTIME_KEY: {"version": 1, "mode": "disabled"},
|
|
},
|
|
}
|
|
|
|
strip_internal_context_keys(config)
|
|
|
|
assert config == {"context": {}, "configurable": {}}
|
|
|
|
|
|
# -- agent config loading during run admission ------------------------------
|
|
# Every run that names a custom agent loads its config here, with or without a
|
|
# knowledge scope, so the 422 detail must say what is wrong with the agent.
|
|
|
|
|
|
@pytest.mark.anyio
|
|
async def test_scope_agent_lookup_reports_a_missing_agent(monkeypatch) -> None:
|
|
from app.gateway import services
|
|
|
|
def _missing(name, *, user_id=None):
|
|
raise FileNotFoundError(name)
|
|
|
|
monkeypatch.setattr(services, "load_agent_config", _missing)
|
|
|
|
with pytest.raises(HTTPException) as excinfo:
|
|
await services._load_scope_agent_config(assistant_id="Ghost_Agent", user_id="u1")
|
|
|
|
assert excinfo.value.status_code == 422
|
|
assert excinfo.value.detail == "Agent 'ghost-agent' not found"
|
|
|
|
|
|
@pytest.mark.anyio
|
|
async def test_scope_agent_lookup_reports_an_unreadable_agent_config(monkeypatch) -> None:
|
|
from app.gateway import services
|
|
|
|
def _corrupt(name, *, user_id=None):
|
|
raise ValueError("bad yaml")
|
|
|
|
monkeypatch.setattr(services, "load_agent_config", _corrupt)
|
|
|
|
with pytest.raises(HTTPException) as excinfo:
|
|
await services._load_scope_agent_config(assistant_id="broken-agent", user_id="u1")
|
|
|
|
assert excinfo.value.status_code == 422
|
|
assert excinfo.value.detail == "Agent 'broken-agent' configuration could not be loaded"
|
|
|
|
|
|
@pytest.mark.anyio
|
|
@pytest.mark.parametrize(
|
|
("agent_name", "detail"),
|
|
[
|
|
("Bad Name!", "Invalid agent_name 'Bad Name!': must contain only letters, digits, and hyphens after normalization."),
|
|
(" ", "Invalid agent_name ' ': must contain only letters, digits, and hyphens after normalization."),
|
|
(1, "Invalid agent_name: expected a string, got int."),
|
|
],
|
|
)
|
|
async def test_scope_agent_lookup_rejects_an_invalid_agent_name_without_loading(monkeypatch, agent_name, detail) -> None:
|
|
from app.gateway import services
|
|
|
|
def _unexpected(name, *, user_id=None):
|
|
raise AssertionError("an invalid agent name must not reach the agent store")
|
|
|
|
monkeypatch.setattr(services, "load_agent_config", _unexpected)
|
|
|
|
with pytest.raises(HTTPException) as excinfo:
|
|
await services._load_scope_agent_config(assistant_id=agent_name, user_id="u1")
|
|
|
|
assert excinfo.value.status_code == 422
|
|
assert excinfo.value.detail == detail
|
|
|
|
|
|
@pytest.mark.anyio
|
|
async def test_scope_agent_lookup_bounds_an_oversized_invalid_agent_name(monkeypatch) -> None:
|
|
"""Admission echoes the caller's raw ``agent_name``; a huge value must not bloat the 422 or logs."""
|
|
from app.gateway import services
|
|
|
|
def _unexpected(name, *, user_id=None):
|
|
raise AssertionError("an invalid agent name must not reach the agent store")
|
|
|
|
monkeypatch.setattr(services, "load_agent_config", _unexpected)
|
|
oversized = "Bad Name!" + "x" * 100_000
|
|
|
|
with pytest.raises(HTTPException) as excinfo:
|
|
await services._load_scope_agent_config(assistant_id=oversized, user_id="u1")
|
|
|
|
assert excinfo.value.status_code == 422
|
|
assert excinfo.value.detail.startswith("Invalid agent_name 'Bad Name!xxx")
|
|
assert excinfo.value.detail.endswith(": must contain only letters, digits, and hyphens after normalization.")
|
|
assert len(excinfo.value.detail) < 400
|
|
|
|
|
|
@pytest.mark.anyio
|
|
async def test_scope_agent_lookup_bounds_an_oversized_missing_agent_name(monkeypatch) -> None:
|
|
"""A syntactically valid name has no length cap either, so the not-found detail is bounded too."""
|
|
from app.gateway import services
|
|
|
|
def _missing(name, *, user_id=None):
|
|
raise FileNotFoundError(name)
|
|
|
|
monkeypatch.setattr(services, "load_agent_config", _missing)
|
|
|
|
with pytest.raises(HTTPException) as excinfo:
|
|
await services._load_scope_agent_config(assistant_id="a" * 100_000, user_id="u1")
|
|
|
|
assert excinfo.value.status_code == 422
|
|
assert excinfo.value.detail.startswith("Agent 'aaa")
|
|
assert excinfo.value.detail.endswith("' not found")
|
|
assert len(excinfo.value.detail) < 400
|