v0.21 alpha add research brief and compressed findings

scripts/runtime/assembly.py

@@ -41,8 +41,41 @@ def validate_chapter_brief(brief: dict) -> None:
         raise ValueError("chapter brief requires counter_evidence")
 
 
+def validate_compressed_finding(finding: dict) -> None:
+    required = {
+        "chapter_id",
+        "chapter_title",
+        "packet_ids",
+        "chapter_thesis",
+        "key_findings",
+        "evidence_landings",
+        "counter_evidence",
+        "source_ids",
+        "open_questions",
+        "writing_plan",
+    }
+    missing = sorted(required - set(finding))
+    if missing:
+        raise ValueError(f"compressed finding missing fields: {missing}")
+    if not finding["chapter_id"]:
+        raise ValueError("chapter_id required")
+    if not finding["packet_ids"]:
+        raise ValueError("compressed finding requires packet_ids")
+    if not finding["chapter_thesis"]:
+        raise ValueError("compressed finding requires chapter_thesis")
+    if not finding["key_findings"]:
+        raise ValueError("compressed finding requires key_findings")
+    if not finding["evidence_landings"]:
+        raise ValueError("compressed finding requires evidence_landings")
+    if not finding["counter_evidence"]:
+        raise ValueError("compressed finding requires counter_evidence")
+
+
 def validate_chapter_markdown_citations(markdown: str, brief: dict) -> None:
-    validate_chapter_brief(brief)
+    if "key_findings" in brief:
+        validate_compressed_finding(brief)
+    else:
+        validate_chapter_brief(brief)
     cited = set(re.findall(r"\[(src_[A-Za-z0-9_-]+)\]", markdown))
     allowed = set(brief.get("source_ids") or [])
     unknown = sorted(cited - allowed)
@@ -103,9 +136,79 @@ def build_chapter_briefs(project_root: Path) -> list[dict]:
     return briefs
 
 
+def _source_ids_from_item(item: dict) -> list[str]:
+    if item.get("source_ids"):
+        return list(item.get("source_ids") or [])
+    if item.get("source_id"):
+        return [item["source_id"]]
+    return []
+
+
+def build_compressed_findings(project_root: Path) -> list[dict]:
+    """Compress packet-level evidence into chapter-level writing inputs.
+
+    This is intentionally deterministic: it does not invent a better narrative,
+    but it forces a chapter-level evidence map before any model writes prose.
+    """
+    brief_dir = project_root / "phase2" / "chapter_briefs"
+    if not brief_dir.exists() or not list(brief_dir.glob("ch*.json")):
+        briefs = build_chapter_briefs(project_root)
+    else:
+        briefs = [
+            json.loads(path.read_text(encoding="utf-8"))
+            for path in sorted(brief_dir.glob("ch*.json"))
+        ]
+    out_dir = project_root / "phase2" / "compressed_findings"
+    out_dir.mkdir(parents=True, exist_ok=True)
+    findings: list[dict] = []
+    for brief in briefs:
+        validate_chapter_brief(brief)
+        core_claims = brief.get("core_claims") or []
+        evidence_items = brief.get("evidence_items") or []
+        first_claim = core_claims[0] if core_claims else {}
+        chapter_thesis = first_claim.get("claim") or f"{brief['chapter_title']} 需要以证据为中心重写。"
+        finding = {
+            "chapter_id": brief["chapter_id"],
+            "chapter_title": brief["chapter_title"],
+            "packet_ids": brief["packet_ids"],
+            "chapter_thesis": chapter_thesis,
+            "key_findings": [
+                {
+                    "finding": claim.get("claim") or claim.get("summary") or str(claim),
+                    "source_ids": _source_ids_from_item(claim),
+                    "confidence": claim.get("confidence", "medium"),
+                }
+                for claim in core_claims
+            ],
+            "evidence_landings": [
+                {
+                    "evidence": item.get("summary") or item.get("finding") or item.get("quote") or str(item),
+                    "source_ids": _source_ids_from_item(item),
+                    "landing_hint": item.get("landing_hint", "用于支撑本章关键判断或整改动作。"),
+                }
+                for item in evidence_items
+            ],
+            "counter_evidence": brief["counter_evidence"],
+            "source_ids": brief["source_ids"],
+            "open_questions": brief["open_questions"],
+            "writing_plan": [
+                "先写本章判断，不按 packet 顺序堆砌。",
+                "每个二级小节至少落下具体审计发现、法规要求、记录/参数或整改证据。",
+                "正文末尾必须保留“证据落点与待补证据”表。",
+            ],
+        }
+        validate_compressed_finding(finding)
+        (out_dir / f"{brief['chapter_id']}.json").write_text(
+            json.dumps(finding, ensure_ascii=False, indent=2) + "\n",
+            encoding="utf-8",
+        )
+        findings.append(finding)
+    return findings
+
+
 def build_chapter_user_prompt(brief: dict) -> str:
     return (
-        "请根据以下 chapter brief 写一章正式中文 Markdown 正文。\n"
+        "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"
         "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"
@@ -142,7 +245,10 @@ class ChapterAssemblyWorker:
         )
 
     def write_chapter(self, *, project_root: Path, brief: dict) -> Path:
-        validate_chapter_brief(brief)
+        if "key_findings" in brief:
+            validate_compressed_finding(brief)
+        else:
+            validate_chapter_brief(brief)
         markdown = self.client.chat_complete(
             model=self.role.model,
             system=self._system_prompt(),