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

2026-05-07 08:21:28 +08:00
parent 0644a68ecc
commit 68e45bcf41
45 changed files with 3005 additions and 157 deletions
@@ -1,4 +1,4 @@
-"""Deterministic Phase 3 review checks for the Python core."""
+"""Phase 3 review checks for the Python core."""

 from __future__ import annotations

@@ -52,6 +52,24 @@ def _ready_packet_stems(project_root: Path) -> set[str]:
    return ready


+def _read_text_if_exists(path: Path, *, max_chars: int | None = None) -> str:
+    if not path.exists():
+        return ""
+    text = path.read_text(encoding="utf-8", errors="ignore")
+    return text[:max_chars] if max_chars is not None else text
+
+
+def _json_if_exists(path: Path, *, max_chars: int | None = None) -> str:
+    if not path.exists():
+        return ""
+    try:
+        data = json.loads(path.read_text(encoding="utf-8"))
+        text = json.dumps(data, ensure_ascii=False, indent=2)
+    except Exception:
+        text = path.read_text(encoding="utf-8", errors="ignore")
+    return text[:max_chars] if max_chars is not None else text
+
+
 def _draft_quality_findings(drafts: list[Path]) -> list[dict[str, Any]]:
    findings: list[dict[str, Any]] = []
    generic_markers = [
@@ -77,6 +95,159 @@ def _draft_quality_findings(drafts: list[Path]) -> list[dict[str, Any]]:
    return findings


+def build_phase3_model_review_context(project_root: Path, *, max_chars: int = 650_000) -> str:
+    """Build a structured, bounded context packet for an independent model review."""
+    deterministic_path = build_phase3_critique(project_root)
+    deterministic_copy = project_root / "phase3" / "critique_deterministic.md"
+    deterministic_copy.write_text(deterministic_path.read_text(encoding="utf-8"), encoding="utf-8")
+
+    manifest = load_manifest(project_root)
+    parts: list[str] = [
+        f"# Phase 3 Model Review Context: {manifest.get('topic', project_root.name)}",
+        "",
+        "## Review Contract",
+        "",
+        "- 这是给非 Codex 模型的独立总编审校上下文，不要求重写正文。",
+        "- 请判断 Phase2 草稿能否进入 Phase4，或必须回炉补证据/重写。",
+        "- 重点关注：证据是否落纸面、并发 packet 是否造成碎片化、法规/最佳实践覆盖是否足够、整改建议是否具体可执行。",
+        "",
+        "## Manifest",
+        "",
+        "```json",
+        json.dumps(manifest, ensure_ascii=False, indent=2),
+        "```",
+        "",
+        "## Deterministic Review Baseline",
+        "",
+        _read_text_if_exists(deterministic_copy),
+        "",
+        "## Phase 1 Framework",
+        "",
+        _read_text_if_exists(project_root / "phase1" / "framework.md", max_chars=50_000),
+        "",
+        "## Phase 1 Research Brief",
+        "",
+        _read_text_if_exists(project_root / "phase1" / "research_brief.md", max_chars=30_000),
+        "",
+        "## Phase 2 Brief Warnings",
+        "",
+        _json_if_exists(project_root / "phase2" / "brief_warnings.json", max_chars=30_000) or "无",
+        "",
+        "## Phase 2 Packet Errors",
+        "",
+    ]
+    errors = sorted((project_root / "phase2" / "packet_errors").glob("*.json"))
+    if errors:
+        for path in errors[:40]:
+            parts.extend([f"### {path.name}", "", _json_if_exists(path, max_chars=2_000), ""])
+    else:
+        parts.append("无")
+
+    parts.extend(["", "## Source Registry Summary", ""])
+    source_lines = []
+    sources_path = project_root / "phase2" / "sources.jsonl"
+    if sources_path.exists():
+        for line in sources_path.read_text(encoding="utf-8").splitlines()[:260]:
+            if not line.strip():
+                continue
+            try:
+                source = json.loads(line)
+            except json.JSONDecodeError:
+                continue
+            source_lines.append(
+                "- {id} | {tier} | {title} | {url} | cached={cached}".format(
+                    id=source.get("id", ""),
+                    tier=source.get("tier", ""),
+                    title=str(source.get("title", ""))[:120],
+                    url=source.get("url", ""),
+                    cached=source.get("cached_text_path", ""),
+                )
+            )
+    parts.append("\n".join(source_lines) or "无")
+
+    parts.extend(["", "## Compressed Findings", ""])
+    for path in sorted((project_root / "phase2" / "compressed_findings").glob("ch*.json")):
+        parts.extend([f"### {path.name}", "", "```json", _json_if_exists(path, max_chars=35_000), "```", ""])
+
+    parts.extend(["", "## Chapter Drafts", ""])
+    for path in sorted((project_root / "phase2" / "drafts").glob("ch*.md")):
+        parts.extend([f"### {path.name}", "", _read_text_if_exists(path, max_chars=55_000), ""])
+
+    context = "\n".join(parts)
+    if len(context) > max_chars:
+        context = context[:max_chars] + "\n\n[Context truncated by max_chars; review should flag if truncation limits confidence.]\n"
+
+    out = project_root / "phase3" / "review_context_opus_4_7.md"
+    out.parent.mkdir(parents=True, exist_ok=True)
+    out.write_text(context, encoding="utf-8")
+    return context
+
+
+def phase3_model_review_system_prompt() -> str:
+    return (
+        "你是 Deep Research Phase 3 的独立总编审校模型，本次由 ZenMux Claude Opus 4.7 执行，用于避免 Codex/OpenAI 模型偏见。\n"
+        "你的任务是审校，不是润色或重写。必须用中文输出，英文仅可保留 source title、URL、法规缩写和原文短摘录。\n"
+        "请严格检查：1) 研究目标与 Phase1 框架是否契合；2) Phase2 并发 evidence packets 是否被章节真正吸收，还是造成碎片化；"
+        "3) FDA/NMPA/EMA/ICH/WHO/EU GMP 等权威来源是否足以支撑关键判断；4) 用户材料是否被正确作为起点且被权威来源交叉验证；"
+        "5) 运营管理与团队能力章节是否具体，不得泛泛咨询腔；6) CAPA 建议是否包含 owner、期限、关闭证据、QA verification、复核窗口和升级阈值；"
+        "7) 引用链和 source_id 是否可追踪；8) 是否仍有明显 AI 味、中英文混杂或空泛表达。\n\n"
+        "输出必须使用以下 Markdown 结构：\n"
+        "# Phase 3 Opus 4.7 独立审校\n"
+        "## 总体判定\n"
+        "给出：通过 / 有条件通过 / 回炉 Phase2，并说明最核心理由。\n"
+        "## P0/P1 阻断问题\n"
+        "列出必须修复的问题；每条写明章节/文件、问题、为什么阻断、建议动作。\n"
+        "## 章节级审校表\n"
+        "用表格覆盖 ch01-ch11：主线质量、证据密度、法规覆盖、整改可执行性、是否需要回炉。\n"
+        "## 证据与信源质量\n"
+        "单独评价 FDA warning letters、ICH Q9/Q10、EU GMP Annex 1、本地缓存信源、第三方低质信源的使用情况。\n"
+        "## 碎片化与叙事连贯性\n"
+        "判断并发研究是否造成割裂，并给出具体整合建议。\n"
+        "## Phase2 回炉任务清单\n"
+        "如果需要回炉，列出可执行任务卡级别的补证据/重写要求。\n"
+        "## Phase4 准入条件\n"
+        "明确进入 final 前必须满足的条件。\n"
+    )
+
+
+def build_phase3_model_critique(
+    project_root: Path,
+    *,
+    client: Any,
+    model: str = "zenmux-anthropic/claude-opus-4-7",
+    max_context_chars: int = 650_000,
+) -> Path:
+    context = build_phase3_model_review_context(project_root, max_chars=max_context_chars)
+    content = client.chat_complete(
+        model=model,
+        system=phase3_model_review_system_prompt(),
+        user=context,
+        temperature=0.2,
+        max_tokens=20_000,
+        tag="phase3:opus-review",
+    )
+    out = project_root / "phase3" / "critique.md"
+    out.parent.mkdir(parents=True, exist_ok=True)
+    out.write_text(content.rstrip() + "\n", encoding="utf-8")
+
+    manifest = load_manifest(project_root)
+    phase3 = manifest.setdefault("phase3", {})
+    phase3.update(
+        {
+            "status": "completed",
+            "review_mode": "model",
+            "review_model": model,
+            "critique_path": "phase3/critique.md",
+            "context_path": "phase3/review_context_opus_4_7.md",
+            "deterministic_critique_path": "phase3/critique_deterministic.md",
+            "updated_at": utc_now_iso(),
+        }
+    )
+    manifest["updated_at"] = utc_now_iso()
+    write_manifest(project_root, manifest)
+    return out
+
+
 def build_phase3_critique(project_root: Path) -> Path:
    manifest = load_manifest(project_root)
    drafts = sorted((project_root / "phase2" / "drafts").glob("ch*.md"))