代码提交
This commit is contained in:
1 parent
d93cc62806
commit
ddf83f7728
25 files changed
+4086
-424
No files matched your search
@@ -3,6 +3,7 @@
|
||||
from __future__ import annotations
|
||||
|
||||
import asyncio
|
||||
import json
|
||||
|
||||
import pytest
|
||||
import pytest_asyncio
|
||||
@@ -13,6 +14,8 @@ from app.maf_roundtable.conversation_service import MafConversationService
|
||||
from app.maf_roundtable.dispatch_contracts import (
|
||||
InvalidDispatchPlanError,
|
||||
MafDispatchAssignment,
|
||||
MafDispatchCandidateSet,
|
||||
MafDispatchCatalog,
|
||||
MafDispatchPlan,
|
||||
MafIntentDecision,
|
||||
resolve_intent,
|
||||
@@ -23,7 +26,6 @@ from deerflow.persistence.maf_roundtable import make_maf_roundtable_store
|
||||
from deerflow.persistence.maf_roundtable.model import (
|
||||
MafRoundtableConversationRow,
|
||||
MafRoundtableParticipantRow,
|
||||
MafRoundtableRunRow,
|
||||
MafRoundtableSessionRow,
|
||||
)
|
||||
|
||||
@@ -132,8 +134,8 @@ async def test_server_route_creates_participants_and_dispatches(store):
|
||||
.order_by(MafRoundtableParticipantRow.sort_order)
|
||||
)
|
||||
).scalars().all()
|
||||
assert session_row.task_payload_json["maf_v2"]["dispatch_plan"]["manager_agent_id"] == "manager-from-config"
|
||||
assert [p.agent_id for p in participants] == ["manager-from-config", "seat-a", "seat-b"]
|
||||
assert session_row.task_payload_json["maf_v2"]["manager_agent_id"] == "manager-from-config"
|
||||
assert [p.agent_id for p in participants] == ["manager-from-config"]
|
||||
assert all(p.thread_id is None for p in participants)
|
||||
|
||||
events = (
|
||||
@@ -146,15 +148,47 @@ async def test_server_route_creates_participants_and_dispatches(store):
|
||||
assert events.active_run_id == run["id"]
|
||||
|
||||
|
||||
@pytest.mark.asyncio
|
||||
async def test_direct_answer_persists_manager_only_participants(store):
|
||||
dispatcher = RecordingDispatcher()
|
||||
svc = MafConversationService(store, maf_config=FakeMafConfig(), dispatcher=dispatcher)
|
||||
conv = await svc.create_conversation(user_id="u1", title="Manager only")
|
||||
|
||||
await svc.send_message(
|
||||
conversation_id=conv["id"],
|
||||
user_id="u1",
|
||||
content="给我一个普通的直接答案",
|
||||
)
|
||||
assert len(dispatcher.calls) == 1
|
||||
session, _run, _owner = dispatcher.calls[0]
|
||||
|
||||
async with store.session_factory() as db:
|
||||
participants = (
|
||||
await db.execute(
|
||||
select(MafRoundtableParticipantRow)
|
||||
.where(MafRoundtableParticipantRow.session_id == session["id"])
|
||||
.order_by(MafRoundtableParticipantRow.sort_order)
|
||||
)
|
||||
).scalars().all()
|
||||
assert [participant.agent_id for participant in participants] == [
|
||||
"manager-from-config"
|
||||
]
|
||||
maf_v2 = session["task_payload"]["maf_v2"]
|
||||
assert maf_v2["manager_agent_id"] == "manager-from-config"
|
||||
assert maf_v2["candidate_seat_agent_ids"] == ["seat-a", "seat-b"]
|
||||
|
||||
|
||||
@pytest.mark.asyncio
|
||||
async def test_clarification_does_not_create_or_dispatch_run(store):
|
||||
"""Short / unclear content still creates a run — the manager workflow
|
||||
is responsible for detecting clarification needs, not the send path."""
|
||||
dispatcher = RecordingDispatcher()
|
||||
svc = MafConversationService(store, maf_config=FakeMafConfig(), dispatcher=dispatcher)
|
||||
conv = await svc.create_conversation(user_id="u1", title="Need detail")
|
||||
|
||||
result = await svc.send_message(conversation_id=conv["id"], user_id="u1", content="不清楚")
|
||||
result = await svc.send_message(conversation_id=conv["id"], user_id="u1", content="请分析这个任务")
|
||||
assert result["message_id"]
|
||||
assert dispatcher.calls == []
|
||||
assert len(dispatcher.calls) == 1
|
||||
|
||||
async with store.session_factory() as db:
|
||||
conv_row = (
|
||||
@@ -164,17 +198,8 @@ async def test_clarification_does_not_create_or_dispatch_run(store):
|
||||
)
|
||||
)
|
||||
).scalars().one()
|
||||
assert conv_row.safe_status == "waiting_input"
|
||||
assert conv_row.active_run_id is None
|
||||
runs = (
|
||||
await db.execute(select(MafRoundtableRunRow))
|
||||
).scalars().all()
|
||||
assert runs == []
|
||||
|
||||
# A clarification reply is allowed to claim the idle waiting-input
|
||||
# conversation and launch exactly one run.
|
||||
await svc.send_message(conversation_id=conv["id"], user_id="u1", content="请分析这个任务")
|
||||
assert len(dispatcher.calls) == 1
|
||||
assert conv_row.safe_status == "running"
|
||||
assert conv_row.active_run_id is not None
|
||||
|
||||
|
||||
@pytest.mark.asyncio
|
||||
@@ -228,7 +253,7 @@ async def test_workflow_projection_whitelists_user_visible_event_data(store):
|
||||
},
|
||||
},
|
||||
)
|
||||
events = await store.conversation_events.list_events(conv["id"], after_seq=3)
|
||||
events = await store.conversation_events.list_events(conv["id"], after_seq=1)
|
||||
tool = next(event for event in events if event["type"] == "tool.requested")
|
||||
assert tool["data"] == {"tool_name": "safe_tool", "agent_id": "seat-a", "turn_index": 1}
|
||||
complete = next(event for event in events if event["type"] == "agent.message.complete")
|
||||
@@ -244,6 +269,21 @@ def test_intent_resolution_is_deterministic_and_does_not_select_agents():
|
||||
assert resolve_intent("给我一个普通答案").intent_type == "direct_answer"
|
||||
|
||||
|
||||
def test_new_conversation_candidate_set_has_no_keyword_intent_decision():
|
||||
catalog = MafDispatchCatalog(FakeMafConfig())
|
||||
candidate_set = catalog.build_candidate_set(task_context=None)
|
||||
|
||||
assert candidate_set == MafDispatchCandidateSet(
|
||||
manager_agent_id="manager-from-config",
|
||||
candidate_seat_agent_ids=["seat-a", "seat-b"],
|
||||
mode="structured",
|
||||
max_rounds=8,
|
||||
)
|
||||
# The request wording cannot change this server-owned candidate set;
|
||||
# the manager JSON contract decides intent only after this point.
|
||||
assert catalog.build_candidate_set(task_context=None) == candidate_set
|
||||
|
||||
|
||||
def test_weak_model_cannot_expand_or_duplicate_dispatch_plan():
|
||||
with pytest.raises(ValueError):
|
||||
MafDispatchPlan(
|
||||
@@ -263,6 +303,7 @@ def test_weak_model_cannot_expand_or_duplicate_dispatch_plan():
|
||||
assignments=[MafDispatchAssignment(agent_id="seat-a", sort_order=1)],
|
||||
intent_type="single_seat",
|
||||
max_rounds=8,
|
||||
execution_mode="single",
|
||||
)
|
||||
with pytest.raises(InvalidDispatchPlanError):
|
||||
validate_dispatch_plan(plan, trusted_agent_ids={"manager", "seat-b"}, max_seats=4)
|
||||
@@ -284,3 +325,113 @@ def test_clarification_plan_is_not_constructible():
|
||||
confidence=0.9,
|
||||
reason_code="needs_detail",
|
||||
)
|
||||
|
||||
|
||||
def test_server_dispatch_plan_selects_the_correct_topology():
|
||||
catalog = MafDispatchCatalog(FakeMafConfig())
|
||||
cases = [
|
||||
("direct_answer", [], "manager_only"),
|
||||
("single_seat", ["seat-a"], "single"),
|
||||
("parallel_consultation", ["seat-a", "seat-b"], "parallel"),
|
||||
("chain_consultation", ["seat-a", "seat-b"], "chain"),
|
||||
("tool_write", ["seat-a"], "single"),
|
||||
]
|
||||
for intent_name, expected_seats, expected_mode in cases:
|
||||
plan = catalog.build_plan(
|
||||
intent=MafIntentDecision(
|
||||
intent_type=intent_name,
|
||||
confidence=1,
|
||||
reason_code="test",
|
||||
),
|
||||
task_context=None,
|
||||
)
|
||||
assert plan.seat_agent_ids == expected_seats
|
||||
assert plan.execution_mode == expected_mode
|
||||
assert plan.candidate_seat_agent_ids == ["seat-a", "seat-b"]
|
||||
|
||||
single_plan = catalog.build_plan(
|
||||
intent=MafIntentDecision(
|
||||
intent_type="single_seat",
|
||||
confidence=1,
|
||||
reason_code="test",
|
||||
),
|
||||
task_context=None,
|
||||
)
|
||||
participant_ids = [item["agent_id"] for item in catalog.participants(single_plan)]
|
||||
assert participant_ids == ["manager-from-config", "seat-a", "seat-b"]
|
||||
|
||||
|
||||
def test_manager_decision_selects_intent_only_within_trusted_candidates():
|
||||
candidate_set = MafDispatchCatalog(FakeMafConfig()).build_candidate_set(task_context=None)
|
||||
proposed, plan = MafDispatchCatalog.parse_manager_decision(
|
||||
json.dumps({
|
||||
"intent_type": "direct_answer",
|
||||
"selected_seat_agent_ids": [],
|
||||
"assignments": [],
|
||||
"execution_mode": "manager_only",
|
||||
"convergence_path": ["manager answer"],
|
||||
"reason": "manager can answer directly",
|
||||
}),
|
||||
candidate_set=candidate_set,
|
||||
max_seats=4,
|
||||
)
|
||||
assert proposed.intent_type == "direct_answer"
|
||||
assert plan is not None
|
||||
assert plan.execution_mode == "manager_only"
|
||||
assert plan.seat_agent_ids == []
|
||||
|
||||
|
||||
def test_manager_plan_is_schema_checked_and_allowlisted():
|
||||
catalog = MafDispatchCatalog(FakeMafConfig())
|
||||
server_plan = catalog.build_plan(
|
||||
intent=MafIntentDecision(
|
||||
intent_type="parallel_consultation",
|
||||
confidence=1,
|
||||
reason_code="test",
|
||||
),
|
||||
task_context=None,
|
||||
)
|
||||
raw = json.dumps({
|
||||
"intent_type": "parallel_consultation",
|
||||
"selected_seat_agent_ids": ["seat-a", "seat-b"],
|
||||
"assignments": [{
|
||||
"agent_id": "seat-a",
|
||||
"task_goal": "Collect the first evidence set",
|
||||
"delivery_requirements": ["cite evidence"],
|
||||
"order": 1,
|
||||
}, {
|
||||
"agent_id": "seat-b",
|
||||
"task_goal": "Compare the two evidence sets",
|
||||
"delivery_requirements": ["cite evidence"],
|
||||
"order": 2,
|
||||
}],
|
||||
"execution_mode": "parallel",
|
||||
"convergence_path": ["manager synthesis", "cross review", "final answer"],
|
||||
"reason": "seat-b has the relevant capability",
|
||||
})
|
||||
final_plan = catalog.parse_manager_plan(
|
||||
raw,
|
||||
expected_intent="parallel_consultation",
|
||||
server_plan=server_plan,
|
||||
max_seats=4,
|
||||
)
|
||||
assert final_plan.seat_agent_ids == ["seat-a", "seat-b"]
|
||||
assert final_plan.source == "manager"
|
||||
|
||||
for invalid in (
|
||||
raw.replace('"seat-b"', '"untrusted-seat"'),
|
||||
raw.replace('"selected_seat_agent_ids": ["seat-a", "seat-b"]', '"selected_seat_agent_ids": ["seat-b", "seat-b"]'),
|
||||
raw.replace('"execution_mode": "parallel"', '"execution_mode": "single"'),
|
||||
raw.replace('"delivery_requirements": ["cite evidence"]', '"delivery_requirements": []'),
|
||||
raw.replace(
|
||||
'"convergence_path": ["manager synthesis", "cross review", "final answer"]',
|
||||
'"convergence_path": []',
|
||||
),
|
||||
):
|
||||
with pytest.raises(InvalidDispatchPlanError):
|
||||
catalog.parse_manager_plan(
|
||||
invalid,
|
||||
expected_intent="parallel_consultation",
|
||||
server_plan=server_plan,
|
||||
max_seats=4,
|
||||
)
|
||||
Reference in new issue
Block a user