feat(evolution): evolve.py per-target evolution — skill/system/tool (#9)

tests/unit/test_evolve.py

@@ -6,8 +6,9 @@
 
 from __future__ import annotations
 
+import asyncio
 import json
-from unittest.mock import AsyncMock
+from unittest.mock import AsyncMock, MagicMock
 
 import pytest
 
@@ -27,7 +28,11 @@ from core.evolution.evolve import (
     _strip_protected_regions,
     _system_protected_spans,
     _tool_protected_spans,
+    consolidate_appendix,
     edit_budget_at,
+    evolve_single_skill,
+    evolve_single_tool,
+    evolve_system_prompt,
     rank_and_clip,
     resolve_skill_file,
     validate_skill,
@@ -40,7 +45,14 @@ from core.evolution.patch import (
     MOMENTUM_END,
     MOMENTUM_START,
 )
-from core.evolution.types import RejectedEdit
+from core.evolution.types import (
+    EvolvePrompts,
+    RejectedEdit,
+    SkillCasePack,
+    SystemCasePack,
+    ToolCasePack,
+)
+from core.types import LLMResponse
 
 # =========================================================================
 # A. 内部辅助函数
@@ -657,3 +669,109 @@ class TestFormatRejectedEdits:
         assert "skill.md" in result
         assert "changed X" in result
         assert "W=" not in result
+
+
+# =========================================================================
+# I. 进化入口函数测试（Task 8）
+# =========================================================================
+
+
+_PROMPTS = EvolvePrompts(
+    evolve_skill="sk",
+    evolve_system="sys",
+    evolve_tool="tool",
+    evolve_rank="rank",
+    consolidate_system="cons",
+)
+
+
+def _make_fake_llm(response_content: str) -> AsyncMock:
+    """构造返回固定 LLMResponse 的模拟 LLM。"""
+    mock = AsyncMock()
+    mock.chat.return_value = LLMResponse(
+        content=response_content,
+        thinking="",
+        model="test",
+        provider="test",
+        prompt_tokens=0,
+        completion_tokens=0,
+        latency_ms=0,
+        ttft_ms=None,
+        max_inter_token_ms=None,
+        cache_hit=False,
+        call_id="test-id",
+    )
+    return mock
+
+
+class TestEvolveSingleSkill:
+    """evolve_single_skill 测试。"""
+
+    def test_empty_pack_skipped(self) -> None:
+        """空案例包（无失败、无 lapse）导致无 applied edits → rejected。"""
+        pack = SkillCasePack(
+            task_type="test",
+            target_file="test.md",
+            stats={},
+            failure_cases=[],
+            success_cases=[],
+            lapse_notes=[],
+        )
+        store = MagicMock()
+        store.read_skill.return_value = "---\nname: t\ndescription: d\ntask_type: t\n---\nbody"
+        store.list_skill_files.return_value = ["test.md"]
+        llm = _make_fake_llm('{"suggestions":[],"edits":[]}')
+        record = asyncio.run(evolve_single_skill(llm, pack, store, _PROMPTS, "v1", 5, 6))
+        assert record.status in ("rejected", "skipped")
+
+
+class TestEvolveSystemPrompt:
+    """evolve_system_prompt 测试。"""
+
+    def test_no_failures_returns_skipped(self) -> None:
+        """空 failure_cases + 空 edits → 无 applied → rejected。"""
+        pack = SystemCasePack(stats={}, failure_cases=[], success_cases=[])
+        store = MagicMock()
+        store.read_prompt.return_value = (
+            "## 能力边界\nfixed\n## 输出格式\nfixed\n## 视频树结构\nfixed\nbody"
+        )
+        llm = _make_fake_llm('{"suggestions":[],"edits":[]}')
+        record = asyncio.run(evolve_system_prompt(llm, pack, store, _PROMPTS, "v1", 5))
+        assert record.status in ("rejected", "skipped")
+
+
+class TestEvolveSingleTool:
+    """evolve_single_tool 测试。"""
+
+    def test_evolved_content_is_json(self) -> None:
+        """即使 rejected，evolved_content 仍是合法 JSON 含 extract/verify。"""
+        pack = ToolCasePack(
+            tool_name="view_node",
+            target_files=["view_node_extract.md", "view_node_verify.md"],
+            stats={},
+            failure_spans=[],
+            success_spans=[],
+        )
+        store = MagicMock()
+        store.read_prompt.return_value = "## 输出格式\nfixed\nbody"
+        llm = _make_fake_llm('{"suggestions":[],"edits":[]}')
+        record = asyncio.run(evolve_single_tool(llm, pack, store, _PROMPTS, "v1", 5))
+        parsed = json.loads(record.evolved_content)
+        assert "extract" in parsed and "verify" in parsed
+
+
+class TestConsolidateAppendix:
+    """consolidate_appendix 测试。"""
+
+    def test_single_note_passthrough(self) -> None:
+        """G1 守卫：单条 note 直接返回，不调 LLM。"""
+        llm = _make_fake_llm("")
+        result = asyncio.run(consolidate_appendix(llm, ["note1"]))
+        assert result == ["note1"]
+
+    def test_exception_returns_original(self) -> None:
+        """G3 守卫：LLM 异常时降级返回原 notes。"""
+        llm = AsyncMock()
+        llm.chat.side_effect = RuntimeError("boom")
+        result = asyncio.run(consolidate_appendix(llm, ["a", "b", "c"]))
+        assert result == ["a", "b", "c"]