release: v0.20 Codex-ready skill-driven core

scripts/runtime/assembly.py

@@ -91,34 +91,82 @@ def _chapter_title_from_id(chapter_id: str) -> str:
         return chapter_id
 
 
+def _load_source_registry(sources_path: Path, source_ids: list[str]) -> list[dict]:
+    wanted = set(source_ids)
+    if not sources_path.exists() or not wanted:
+        return []
+    rows: list[dict] = []
+    for line in sources_path.read_text(encoding="utf-8").splitlines():
+        if not line.strip():
+            continue
+        try:
+            row = json.loads(line)
+        except json.JSONDecodeError:
+            continue
+        if row.get("id") in wanted:
+            rows.append(row)
+    return rows
+
+
+def _cached_source_excerpts(project_root: Path, cached_paths: list[str], *, max_sources: int = 5, max_chars: int = 1400) -> list[dict]:
+    excerpts: list[dict] = []
+    for rel in cached_paths[:max_sources]:
+        path = project_root / rel
+        if not path.exists():
+            continue
+        text = path.read_text(encoding="utf-8", errors="ignore").strip()
+        excerpts.append({"path": rel, "excerpt": text[:max_chars]})
+    return excerpts
+
+
 def build_chapter_briefs(project_root: Path) -> list[dict]:
     cards = load_task_cards(project_root / "phase2" / "task_cards.json")
     grouped: dict[str, list[tuple[str, dict]]] = {}
+    skipped_packets: list[dict[str, str]] = []
     for card in cards:
         packet_path = project_root / card.output_packet
         if not packet_path.exists():
+            skipped_packets.append({"task_id": card.task_id, "reason": "packet file missing"})
             continue
         packet = json.loads(packet_path.read_text(encoding="utf-8"))
-        validate_packet(packet)
+        try:
+            validate_packet(packet)
+        except Exception as exc:
+            skipped_packets.append({"task_id": card.task_id, "reason": str(exc)})
+            continue
         for chapter_id in card.chapter_ids:
             grouped.setdefault(chapter_id, []).append((card.task_id, packet))
 
     briefs: list[dict] = []
     out_dir = project_root / "phase2" / "chapter_briefs"
     out_dir.mkdir(parents=True, exist_ok=True)
+    if skipped_packets:
+        (project_root / "phase2" / "brief_warnings.json").write_text(
+            json.dumps(skipped_packets, ensure_ascii=False, indent=2) + "\n",
+            encoding="utf-8",
+        )
     for chapter_id in sorted(grouped):
-        packet_pairs = sorted(grouped[chapter_id], key=lambda item: item[0])
+        packet_pairs = grouped[chapter_id]
         packet_ids = [item[0] for item in packet_pairs]
         packets = [item[1] for item in packet_pairs]
         source_ids = sorted({sid for packet in packets for sid in packet.get("source_ids", [])})
+        source_registry = _load_source_registry(project_root / "phase2" / "sources.jsonl", source_ids)
+        cached_paths = [
+            source["cached_text_path"]
+            for source in source_registry
+            if source.get("cached_text_path")
+        ]
+        chapter_title = next((card.chapter_title for card in cards if chapter_id in card.chapter_ids and card.chapter_title), None)
         brief = {
             "chapter_id": chapter_id,
-            "chapter_title": _chapter_title_from_id(chapter_id),
+            "chapter_title": chapter_title or _chapter_title_from_id(chapter_id),
             "packet_ids": packet_ids,
             "core_claims": [claim for packet in packets for claim in packet.get("claims", [])],
             "evidence_items": [item for packet in packets for item in packet.get("evidence_items", [])],
             "counter_evidence": [item for packet in packets for item in packet.get("counter_evidence", [])],
             "source_ids": source_ids,
+            "cached_source_paths": cached_paths,
+            "cached_source_excerpts": _cached_source_excerpts(project_root, cached_paths),
             "open_questions": [q for packet in packets for q in packet.get("open_questions", [])],
             "assembly_notes": [
                 "用中文写正式章节，英文仅保留在必要的来源标题、原文摘录、DOI/URL 中。",
@@ -190,6 +238,8 @@ def build_compressed_findings(project_root: Path) -> list[dict]:
             ],
             "counter_evidence": brief["counter_evidence"],
             "source_ids": brief["source_ids"],
+            "cached_source_paths": brief.get("cached_source_paths", []),
+            "cached_source_excerpts": brief.get("cached_source_excerpts", []),
             "open_questions": brief["open_questions"],
             "writing_plan": [
                 "先写本章判断，不按 packet 顺序堆砌。",
@@ -211,6 +261,7 @@ def build_chapter_user_prompt(brief: dict) -> str:
         "请根据以下 compressed finding / chapter brief 写一章正式中文 Markdown 正文。\n"
         "目标是形成一个完整章节，而不是 packet 摘要。避免碎片化，按金字塔结构组织：章首先给结论，再用证据支撑。\n"
         "要求：标题必须是观点型判断；每个数字和事实保留 [src_xxx]；纳入反方证据；不要出现调度元数据。\n"
+        "如 brief 中包含 cached_source_paths，说明这些是已抓取到本地的核心一手/权威信源快照；优先使用 packet 已摘录的原文，并在证据不足时标记需要从本地快照补摘录，不要重新联网检索。\n"
         "禁止写空泛咨询腔。每个二级小节都必须至少落下 2 个具体审计发现、法规要求、SOP/记录/参数/现场观察或整改证据；不要只写原则。\n"
         "正文末尾必须增加“证据落点与待补证据”小节，用表格列出：关键判断、已使用证据 source_id、已落地整改动作、仍缺证据。若证据不足，直接标注需回炉 Phase 2，不要用泛泛表述补齐。\n"
         "只输出 Markdown，不要输出解释。\n\n"
@@ -238,6 +289,7 @@ class ChapterAssemblyWorker:
             except FileNotFoundError:
                 skill_texts.append(f"# Skill: {name}\n\n[missing skill: {name}]")
         return (
+            f"{self.role.identity}\n\n"
             "你是 Deep Research v0.20 的中文章节组装 worker。\n"
             "你的职责是把结构化证据包收束成连贯章节，解决并发研究造成的碎片化。\n"
             "不得编造来源，不得删除关键反方证据。\n\n"