Files
beaver_project/app-instance/backend/tests/unit/test_task_skill_resolver.py
steven_li 8a12c30141 feat(beaver): 完成Task Team功能v1实现,重构后端架构支持统一内核
新增内部Task系统,包括验证、反馈门控机制,实现自动质量验证
(通过率>=0.75)和用户反馈闭环(satisfied/revise/abandon)。

实现Agent Team v1协调器,支持sequence/parallel/dag执行策略,
sub-agent复用主AgentLoop,每个run使用独立memory snapshot。

建立Skill学习pipeline,包含draft/审核/发布/回滚完整生命周期,
通过Task验证通过且用户满意才生成学习候选。

重构目录结构,移除third_party依赖,建立统一engine内核,
所有agent共享运行时基础组件。

更新ContextBuilder清理provider消息字段,增强SkillContext版本管理,
集成TaskExecutionPlanner和TaskSkillResolver实现技能解析机制。
2026-05-08 17:14:14 +08:00

176 lines
6.0 KiB
Python

from __future__ import annotations
import asyncio
from pathlib import Path
from types import SimpleNamespace
from beaver.coordinator import AgentDescriptor, ExecutionGraph, ExecutionNode
from beaver.engine.context import SkillContext
from beaver.engine.providers.base import LLMProvider, LLMResponse
from beaver.engine.providers.factory import ProviderBundle
from beaver.skills.drafts import DraftService
from beaver.skills.learning import MissingSkillSynthesizer
from beaver.skills.publisher import SkillPublisher
from beaver.skills.reviews import ReviewService
from beaver.skills.specs import SkillSpecStore
from beaver.skills import SkillsLoader
from beaver.tasks import TaskRecord, TaskSkillResolver
class RecordingProvider(LLMProvider):
def __init__(self, responses: list[str]) -> None:
super().__init__()
self.responses = list(responses)
self.calls: list[list[dict]] = []
async def chat(
self,
messages: list[dict],
tools: list[dict] | None = None,
model: str | None = None,
max_tokens: int = 4096,
temperature: float = 0.7,
) -> LLMResponse:
self.calls.append(messages)
content = self.responses.pop(0) if self.responses else "[]"
return LLMResponse(content=content, finish_reason="stop", provider_name="stub", model="stub-model")
def get_default_model(self) -> str:
return "stub-model"
def _bundle(provider: RecordingProvider) -> ProviderBundle:
return ProviderBundle(
main_runtime=SimpleNamespace(model="stub-model", provider_name="stub"),
main_provider=provider,
)
def _task() -> TaskRecord:
return TaskRecord(
task_id="task-1",
session_id="session-1",
description="review api compatibility",
goal="review api compatibility",
constraints=[],
priority=0,
status="open",
creator="test",
created_at="now",
updated_at="now",
)
def _publish_skill(workspace: Path, *, skill_name: str) -> None:
store = SkillSpecStore(workspace)
draft = DraftService(store).create_new_skill_draft(
skill_name=skill_name,
proposed_content="# API Contract Review\n\nCheck schema compatibility and breaking changes.",
proposed_frontmatter={"description": "API contract compatibility review", "tools": []},
created_by="tester",
reason="test",
)
ReviewService(store).approve(skill_name, draft.draft_id, reviewer="tester")
SkillPublisher(store).publish(skill_name, draft.draft_id, publisher="tester")
def test_task_skill_resolver_pins_matching_published_skill(tmp_path: Path) -> None:
_publish_skill(tmp_path, skill_name="api-contract-review")
provider = RecordingProvider(['["api-contract-review"]'])
resolver = TaskSkillResolver(
skills_loader=SkillsLoader(tmp_path),
draft_service=DraftService(SkillSpecStore(tmp_path)),
)
graph = ExecutionGraph(
strategy="sequence",
nodes=[
ExecutionNode(
"api_review",
"review API compatibility",
AgentDescriptor(
name="api_review",
metadata={
"skill_query": "API contract compatibility review",
"required_capabilities": ["schema compatibility"],
},
),
)
],
)
resolved, reports = asyncio.run(
resolver.resolve_graph(
graph,
task=_task(),
user_message="review api",
attempt_index=1,
provider_bundle=_bundle(provider),
)
)
assert resolved.nodes[0].agent.name == "api_review"
assert resolved.nodes[0].agent.role == ""
assert resolved.nodes[0].inherited_pinned_skills == ["api-contract-review"]
assert resolved.nodes[0].inherited_pinned_skill_contexts == []
assert reports[0].selected_skill_names == ["api-contract-review"]
assert reports[0].ephemeral_used is False
def test_task_skill_resolver_generates_draft_only_ephemeral_skill_when_missing(tmp_path: Path) -> None:
provider = RecordingProvider(
[
"""
{
"skill_name": "api-compatibility-review",
"description": "Review API compatibility",
"content": "# API Compatibility Review\\n\\nCheck schema compatibility.",
"tags": ["api", "review"]
}
"""
]
)
store = SkillSpecStore(tmp_path)
resolver = TaskSkillResolver(
skills_loader=SkillsLoader(tmp_path),
draft_service=DraftService(store),
missing_skill_synthesizer=MissingSkillSynthesizer(),
)
graph = ExecutionGraph(
strategy="sequence",
nodes=[
ExecutionNode(
"api_review",
"review API compatibility",
AgentDescriptor(
name="api_review",
metadata={
"skill_query": "API compatibility review",
"required_capabilities": ["schema compatibility"],
},
),
)
],
)
resolved, reports = asyncio.run(
resolver.resolve_graph(
graph,
task=_task(),
user_message="review api",
attempt_index=1,
provider_bundle=_bundle(provider),
)
)
drafts = store.list_drafts("api-compatibility-review")
assert len(drafts) == 1
assert store.list_published_skill_names() == []
assert resolved.nodes[0].inherited_pinned_skills == []
assert len(resolved.nodes[0].inherited_pinned_skill_contexts) == 1
context: SkillContext = resolved.nodes[0].inherited_pinned_skill_contexts[0]
assert context.name == "draft:api-compatibility-review"
assert context.version == f"draft:{drafts[0].draft_id}"
assert context.activation_reason == "generated_missing_skill"
assert reports[0].generated_skill_draft_id == drafts[0].draft_id
assert reports[0].ephemeral_used is True