from __future__ import annotations import json import sys from pathlib import Path REPO_ROOT = Path(__file__).resolve().parents[1] if str(REPO_ROOT) not in sys.path: sys.path.insert(0, str(REPO_ROOT)) from scripts.runtime.assembly import ( ChapterAssemblyWorker, build_chapter_briefs, build_chapter_user_prompt, run_chapter_assembly_workers, validate_chapter_markdown_citations, validate_chapter_brief, ) from scripts.runtime.roles import resolve_runtime_profile class FakeClient: def __init__(self, response: str) -> None: self.response = response self.calls: list[dict[str, object]] = [] def chat_complete(self, **kwargs) -> str: self.calls.append(kwargs) return self.response class TaggedClient: def __init__(self, responses_by_tag: dict[str, str]) -> None: self.responses_by_tag = responses_by_tag self.calls: list[dict[str, object]] = [] def chat_complete(self, **kwargs) -> str: self.calls.append(kwargs) return self.responses_by_tag[str(kwargs["tag"])] def chapter_brief(chapter_id: str, source_ids: list[str]) -> dict: return { "chapter_id": chapter_id, "chapter_title": "临床证据正在重塑需求判断", "packet_ids": [f"{chapter_id}-clinical"], "core_claims": [{"claim": "临床证据支持核心判断", "source_ids": source_ids[:1]}], "evidence_items": [{"source_id": source_ids[0], "summary": "III 期数据支持主要终点"}], "counter_evidence": [{"claim": "长期安全性仍需随访", "source_ids": source_ids[-1:]}], "source_ids": source_ids, "open_questions": [], "assembly_notes": ["按金字塔结构组织。"], } def write_packet(path: Path, task_id: str, claim: str, source_id: str) -> None: packet = { "task_id": task_id, "claims": [{"claim": claim, "source_ids": [source_id]}], "evidence_items": [{"source_id": source_id, "summary": f"{claim} 的证据"}], "counter_evidence": [{"claim": "仍需关注样本量和外推限制", "source_ids": ["src_counter"]}], "source_ids": [source_id, "src_counter"], "source_quality_notes": [f"{source_id} Tier 1"], "open_questions": ["还需要补充中国市场数据"], "raw_quotes_or_notes": ["English note can remain as source material."], } path.parent.mkdir(parents=True, exist_ok=True) path.write_text(json.dumps(packet, ensure_ascii=False, indent=2) + "\n", encoding="utf-8") def test_build_chapter_briefs_aggregates_packets_by_chapter(tmp_path: Path) -> None: project = tmp_path / "project" cards = [ { "task_id": "ch01-clinical", "chapter_ids": ["ch01"], "topic_axis": "clinical", "questions": ["q"], "search_routes": ["scholar"], "output_packet": "phase2/packets/ch01-clinical.json", }, { "task_id": "ch01-market", "chapter_ids": ["ch01"], "topic_axis": "market", "questions": ["q"], "search_routes": ["news"], "output_packet": "phase2/packets/ch01-market.json", }, ] (project / "phase2").mkdir(parents=True) (project / "phase2" / "task_cards.json").write_text(json.dumps(cards, ensure_ascii=False), encoding="utf-8") write_packet(project / "phase2/packets/ch01-clinical.json", "ch01-clinical", "临床证据支持核心判断", "src_001") write_packet(project / "phase2/packets/ch01-market.json", "ch01-market", "市场数据支持需求增长", "src_002") briefs = build_chapter_briefs(project) assert len(briefs) == 1 brief = briefs[0] validate_chapter_brief(brief) assert brief["chapter_id"] == "ch01" assert brief["packet_ids"] == ["ch01-clinical", "ch01-market"] assert "src_001" in brief["source_ids"] assert "src_002" in brief["source_ids"] assert (project / "phase2/chapter_briefs/ch01.json").exists() def test_chapter_prompt_contains_brief_and_fragmentation_guard() -> None: brief = { "chapter_id": "ch01", "chapter_title": "临床证据正在重塑需求判断", "packet_ids": ["ch01-clinical"], "core_claims": [{"claim": "临床证据支持核心判断", "source_ids": ["src_001"]}], "evidence_items": [{"source_id": "src_001", "summary": "III 期数据支持主要终点"}], "counter_evidence": [{"claim": "长期安全性仍需随访", "source_ids": ["src_002"]}], "source_ids": ["src_001", "src_002"], "open_questions": [], "assembly_notes": ["避免重复 packet 原文；按金字塔结构组织。"], } prompt = build_chapter_user_prompt(brief) assert "临床证据正在重塑需求判断" in prompt assert "避免碎片化" in prompt assert "只输出 Markdown" in prompt def test_chapter_assembly_worker_writes_markdown(tmp_path: Path) -> None: runtime = resolve_runtime_profile(profile="medium") role = runtime.role_for_task("chapter_assembly") fake = FakeClient("# 第1章 临床证据正在重塑需求判断\n\n结论先行。[src_001]\n") worker = ChapterAssemblyWorker(role=role, client=fake) brief = { "chapter_id": "ch01", "chapter_title": "临床证据正在重塑需求判断", "packet_ids": ["ch01-clinical"], "core_claims": [{"claim": "临床证据支持核心判断", "source_ids": ["src_001"]}], "evidence_items": [{"source_id": "src_001", "summary": "III 期数据支持主要终点"}], "counter_evidence": [{"claim": "长期安全性仍需随访", "source_ids": ["src_002"]}], "source_ids": ["src_001", "src_002"], "open_questions": [], "assembly_notes": ["按金字塔结构组织。"], } output = worker.write_chapter(project_root=tmp_path, brief=brief) assert output == tmp_path / "phase2/drafts/ch01.md" assert "结论先行" in output.read_text(encoding="utf-8") assert fake.calls[0]["model"] == role.model def test_validate_chapter_markdown_rejects_unknown_source_ids() -> None: brief = { "chapter_id": "ch01", "chapter_title": "临床证据正在重塑需求判断", "packet_ids": ["ch01-clinical"], "core_claims": [{"claim": "临床证据支持核心判断", "source_ids": ["src_001"]}], "evidence_items": [{"source_id": "src_001", "summary": "III 期数据支持主要终点"}], "counter_evidence": [{"claim": "长期安全性仍需随访", "source_ids": ["src_002"]}], "source_ids": ["src_001", "src_002"], "open_questions": [], "assembly_notes": ["按金字塔结构组织。"], } try: validate_chapter_markdown_citations("结论引用了不存在的来源。[src_fake]", brief) except ValueError as exc: assert "unknown citation ids" in str(exc) assert "src_fake" in str(exc) else: raise AssertionError("unknown source id should fail validation") def test_chapter_assembly_worker_refuses_to_write_unknown_citations(tmp_path: Path) -> None: runtime = resolve_runtime_profile(profile="medium") role = runtime.role_for_task("chapter_assembly") fake = FakeClient("# 第1章 临床证据正在重塑需求判断\n\n结论先行。[src_fake]\n") worker = ChapterAssemblyWorker(role=role, client=fake) brief = { "chapter_id": "ch01", "chapter_title": "临床证据正在重塑需求判断", "packet_ids": ["ch01-clinical"], "core_claims": [{"claim": "临床证据支持核心判断", "source_ids": ["src_001"]}], "evidence_items": [{"source_id": "src_001", "summary": "III 期数据支持主要终点"}], "counter_evidence": [{"claim": "长期安全性仍需随访", "source_ids": ["src_002"]}], "source_ids": ["src_001", "src_002"], "open_questions": [], "assembly_notes": ["按金字塔结构组织。"], } try: worker.write_chapter(project_root=tmp_path, brief=brief) except ValueError as exc: assert "unknown citation ids" in str(exc) else: raise AssertionError("chapter with unknown citation should not be written") assert not (tmp_path / "phase2/drafts/ch01.md").exists() def test_run_chapter_assembly_workers_records_errors_without_aborting_batch(tmp_path: Path) -> None: runtime = resolve_runtime_profile(profile="medium") fake = TaggedClient( { "chapter:ch01": "# 第1章 临床证据正在重塑需求判断\n\n结论先行。[src_001]\n", "chapter:ch02": "# 第2章 临床证据存在不确定性\n\n错误引用。[src_fake]\n", } ) count = run_chapter_assembly_workers( project_root=tmp_path, briefs=[chapter_brief("ch01", ["src_001", "src_002"]), chapter_brief("ch02", ["src_003", "src_004"])], runtime=runtime, client_factory=lambda _role: fake, workers=2, ) assert count == 1 assert (tmp_path / "phase2/drafts/ch01.md").exists() assert not (tmp_path / "phase2/drafts/ch02.md").exists() error_path = tmp_path / "phase2/chapter_errors/ch02.json" assert error_path.exists() error = json.loads(error_path.read_text(encoding="utf-8")) assert error["chapter_id"] == "ch02" assert error["status"] == "failed" assert "src_fake" in error["error"]