v0.21 alpha add research brief and compressed findings

AGENTS.md

@@ -64,14 +64,16 @@
 ### Phase 1：框架规划
 - **驱动命令**：`uv run python scripts/dr.py init <topic>` → `uv run python scripts/dr.py frame <slug>`（`/dr-init`、`/dr-frame` 只是薄封装）
 - **主导入口**：Python core 生成项目骨架与 framework；dr-plan 可作为表层访谈增强
-- **产出**：`projects/<slug>/phase1/framework.md`（记录 research_method、8-15 章大纲，每 section 带研究思路与字数配额）
-- **暂停点**：用户确认框架
+- **产出**：`phase1/material_brief.md` + `phase1/framework.md` + `phase1/research_brief.md/json`
+- **暂停点**：用户确认材料解读、研究方法、任务切分、检索策略和章节框架
+- **硬规则**：clarification 不只是问范围；必须固化报告用途、基调、成功标准、任务拆分、每个任务轴的 prompt/skills/search route，让低成本 worker 也能独立执行
 
 ### Phase 2：深度研究
 - **驱动命令**：`uv run python scripts/dr.py research <slug> --workers 6`
 - **主导入口**：Python core 生成 task cards 并控制并发
-- **产出**：`projects/<slug>/phase2/task_cards.json` + `packets/*.json` + `drafts/chXX.md` + `evidence/chXX-evidence.md` + `sources.jsonl`
+- **产出**：`phase2/task_cards.json` + `packets/*.json` + `sources.jsonl` + `chapter_briefs/*.json` + `compressed_findings/*.json` + `drafts/chXX.md`
 - **不暂停**：全自动跑完
+- **防碎片化规则**：并发 worker 只写 evidence packet；`--build-briefs` 必须先收束为 chapter brief 和 compressed finding；章节正文必须从 compressed finding 写，不得把 packet 按顺序拼贴成报告
 
 ### Phase 3：总编审校
 - **驱动命令**：`uv run python scripts/dr.py review <slug>`（`/dr-review` 只是薄封装）
@@ -190,6 +192,7 @@ uv run python scripts/dr.py methods list
 - 不把平台 subagent 当默认并发机制。
 - 真实并发由 `scripts/runtime/workers.py` 的 worker pool 执行。
 - 真实模型选择由 `configs/models.yaml` 和 `scripts/runtime/roles.py` 执行。
+- 信息检索默认走 `scripts/search.py` / `SearchClient` / `search-gateway` skill；不得把 Tavily MCP、browser MCP 或平台 web search 作为默认路径，除非用户明确授权。
 
 ---
 
@@ -215,10 +218,11 @@ uv run python scripts/dr.py methods list
 
 1. `uv run python scripts/dr.py status <slug>` 能看到 phase 状态。
 2. Phase 2 存在 `phase2/task_cards.json`。
-3. `--execute-packets` 后存在 `phase2/packets/*.json` 和必要时的 `phase2/packet_errors/*.json`。
-4. `--build-briefs` 后存在 `phase2/chapter_briefs/*.json`。
-5. `--assemble-chapters` 后存在 `phase2/drafts/chXX.md` 和必要时的 `phase2/chapter_errors/*.json`。
-6. `scripts/v020_regression.py` 输出 `v0.20 regression PASS`。
+3. Phase 1 存在 `phase1/research_brief.md` 和 `phase1/research_brief.json`。
+4. `--execute-packets` 后存在 `phase2/packets/*.json` 和必要时的 `phase2/packet_errors/*.json`。
+5. `--build-briefs` 后存在 `phase2/chapter_briefs/*.json` 与 `phase2/compressed_findings/*.json`。
+6. `--assemble-chapters` 后存在 `phase2/drafts/chXX.md` 和必要时的 `phase2/chapter_errors/*.json`。
+7. `scripts/v020_regression.py` 输出 `v0.20 regression PASS`。
 
 ---
 

PLAN.md

@@ -686,3 +686,18 @@ OpenCode 的坑：如果只是在主会话里装样子地写"让 X agent 做"，
   - fixture 项目必须覆盖：material brief -> research brief -> task cards -> enrichment round -> compressed findings -> chapter draft -> Phase3 score gate。
   - 搜索测试必须验证 subagent prompt 中包含 `search-gateway`，且不会提及 Tavily MCP 作为默认路径。
   - 质量测试必须能让“泛泛咨询腔但有引用”的章节失败，让“具体审计发现+法规条款+整改动作+待补证据”的章节通过。
+
+- 2026-05-06 v0.21-alpha implementation：**Research Brief 与压缩发现先行落地**
+
+  **已落地**：
+  - `scripts/runtime/phase1.py` 新增 `phase1/research_brief.md` 与 `phase1/research_brief.json`，在 `frame` 阶段把材料简报、研究方法、工作语言、写作基调、成功标准、任务切分原则、每个任务轴的 prompt brief / search route / required skills / stop conditions 固化为文件。
+  - `scripts/runtime/orchestrator.py` 生成 Phase2 task cards 时优先读取 `research_brief.json`，不再只依赖章节标题和 method axes。
+  - `scripts/runtime/tasks.py` 扩展 `TaskCard` schema：`research_goal`、`research_method`、`prompt_brief`、`required_skills`、`allowed_materials`、`expected_evidence`、`stop_conditions`、`model_hint`；旧 task card 会自动补默认字段，保持 fixture 兼容。
+  - `scripts/runtime/assembly.py` 新增 `build_compressed_findings()` 与 `validate_compressed_finding()`，`--build-briefs` 会同步写入 `phase2/compressed_findings/chXX.json`。
+  - `--assemble-chapters` 改为从 `compressed_findings` 写中文章节，减少并发 packet 直接拼接造成的碎片化。
+  - `AGENTS.md` 已同步更新 Phase1/2 真实产物、search-gateway 默认路径、Python core 验证锚点。
+
+  **仍未完成**：
+  - `phase2/enrichment_rounds/roundXX/coverage_gap.json` 还未实现；下一步应先做 deterministic coverage evaluator，再让补充 task cards 从 gap 生成。
+  - Phase3 evaluator rubrics 仍是计划项；当前 deterministic review 已能抓部分 draft 质量问题，但还没有分维度评分与 finalize gate。
+  - DOCX/PPTX/图片批量 OCR、表格抽取、材料 source registry 仍放入后续资料导入增强。

README.md

@@ -183,7 +183,7 @@ uv run python scripts/search.py "dual-target siRNA GalNAc" --route patents
 ```
 deep_research/
 ├── PLAN.md                      # 完整方案（中断续接从此读起）
-├── AGENTS.md                    # 研究方法论与规则（OpenCode 自动加载）
+├── AGENTS.md                    # 跨平台研究方法论与运行规则
 ├── README.md                    # 本文件
 ├── secrets.env.example          # 密钥模板
 ├── secrets.env                  # 你的密钥（gitignore）
@@ -224,7 +224,7 @@ deep_research/
 
 ### 1. Python core 防止上下文污染
 
-OpenCode/Codex/Claude Code/Antigravity/Gemini CLI 的 subagent 或 agent thread 都可能把大上下文带入子会话。v0.20 起，默认并发由 Python runtime 的任务卡执行层控制：先生成 `phase2/task_cards.json`，再按任务卡产出 `phase2/packets/*.json`，最后组装中文章节。平台 agent 只负责调用 CLI 和展示状态。
+OpenCode/Codex/Claude Code/Antigravity/Gemini CLI 的 subagent 或 agent thread 都可能把大上下文带入子会话。v0.20 起，默认并发由 Python runtime 的任务卡执行层控制：先生成 `phase1/research_brief.json` 固化研究意图和任务切分，再生成 `phase2/task_cards.json`，按任务卡产出 `phase2/packets/*.json`，经 `phase2/compressed_findings/*.json` 收束后再组装中文章节。平台 agent 只负责调用 CLI 和展示状态。
 
 ### 2. 信源分级（Tier 1-4 + 黑名单）
 

scripts/dr.py

@@ -26,7 +26,7 @@ from scripts.lib.model_config import (
     parse_model_overrides,
     resolve_model_profile,
 )
-from scripts.runtime.assembly import build_chapter_briefs, run_chapter_assembly_workers
+from scripts.runtime.assembly import build_chapter_briefs, build_compressed_findings, run_chapter_assembly_workers
 from scripts.runtime.orchestrator import create_phase2_task_cards, write_placeholder_packets
 from scripts.runtime.methods import ResearchMethodRegistry
 from scripts.runtime.phase1 import create_project, render_framework, write_material_brief
@@ -258,11 +258,14 @@ def cmd_research(args: argparse.Namespace) -> int:
         packet_count = len(list((project_root / "phase2" / "packets").glob("*.json")))
     brief_count = 0
     chapter_count = 0
+    compressed_count = 0
     source_count = None
     if args.build_briefs or args.assemble_chapters:
         source_count = rebuild_sources_from_packets(project_root)
         briefs = build_chapter_briefs(project_root)
         brief_count = len(briefs)
+        compressed_findings = build_compressed_findings(project_root)
+        compressed_count = len(compressed_findings)
         if args.assemble_chapters:
             from scripts.lib.zenmux_client import ZenMuxClient, load_secrets
 
@@ -273,7 +276,7 @@ def cmd_research(args: argparse.Namespace) -> int:
 
             chapter_count = run_chapter_assembly_workers(
                 project_root=project_root,
-                briefs=briefs,
+                briefs=compressed_findings,
                 runtime=runtime,
                 client_factory=chapter_client_factory,
                 workers=args.workers,
@@ -288,6 +291,7 @@ def cmd_research(args: argparse.Namespace) -> int:
         print(f"Sources rebuilt: {source_count}")
     if args.build_briefs or args.assemble_chapters:
         print(f"Chapter briefs: {brief_count}")
+        print(f"Compressed findings: {compressed_count}")
     if args.assemble_chapters:
         print(f"Chapter drafts: {chapter_count}")
     if args.dry_run:
@@ -298,7 +302,7 @@ def cmd_research(args: argparse.Namespace) -> int:
         print("Wrote: phase2/task_cards.json and validated phase2/packets/*.json")
         print("Next: rerun with --build-briefs to aggregate packets into chapter briefs.")
     elif args.build_briefs:
-        print("Wrote: phase2/chapter_briefs/*.json")
+        print("Wrote: phase2/chapter_briefs/*.json and phase2/compressed_findings/*.json")
         print("Next: rerun with --assemble-chapters to write Chinese chapter drafts.")
     else:
         print("Wrote: phase2/task_cards.json and phase2/packets/*.json")
@@ -373,6 +377,8 @@ def cmd_status(args: argparse.Namespace) -> int:
     drafts = sorted((project_root / "phase2" / "drafts").glob("ch*.md"))
     evidence = sorted((project_root / "phase2" / "evidence").glob("ch*-evidence.md"))
     task_cards = project_root / "phase2" / "task_cards.json"
+    research_brief = project_root / "phase1" / "research_brief.json"
+    compressed_findings = sorted((project_root / "phase2" / "compressed_findings").glob("ch*.json"))
     packet_counts = packet_state_counts(project_root)
     sources = project_root / "phase2" / "sources.jsonl"
     final_en = project_root / "phase4" / "final_en.md"
@@ -399,6 +405,7 @@ def cmd_status(args: argparse.Namespace) -> int:
     print()
     print("Artifacts:")
     print(f"  framework: {file_state(project_root / 'phase1' / 'framework.md')}")
+    print(f"  research_brief.json: {file_state(research_brief)}")
     print(f"  task_cards.json: {file_state(task_cards)}")
     print(
         "  packets: "
@@ -410,6 +417,7 @@ def cmd_status(args: argparse.Namespace) -> int:
         f"total={packet_counts['total']}"
     )
     print(f"  drafts: {len(drafts)}")
+    print(f"  compressed findings: {len(compressed_findings)}")
     print(f"  evidence files: {len(evidence)}")
     print(f"  sources: {source_count}")
     print(f"  final_en.md: {file_state(final_en)} ({en_words:,} words)")

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(),

scripts/runtime/orchestrator.py

@@ -8,7 +8,7 @@ from pathlib import Path
 
 from scripts.runtime.artifacts import ensure_phase_dirs, load_manifest, write_manifest
 from scripts.runtime.methods import ResearchMethodRegistry
-from scripts.runtime.tasks import generate_task_cards, write_task_cards
+from scripts.runtime.tasks import generate_task_cards, generate_task_cards_from_research_brief, write_task_cards
 
 
 def utc_now_iso() -> str:
@@ -28,7 +28,19 @@ def create_phase2_task_cards(
     if (project_root / "manifest.json").exists():
         method_key = load_manifest(project_root).get("research_method")
     method = ResearchMethodRegistry().get(method_key)
-    cards = generate_task_cards(project_root.name, framework.read_text(encoding="utf-8"), axes=axes, method=method)
+    research_brief_path = project_root / "phase1" / "research_brief.json"
+    framework_text = framework.read_text(encoding="utf-8")
+    if research_brief_path.exists():
+        research_brief = json.loads(research_brief_path.read_text(encoding="utf-8"))
+        cards = generate_task_cards_from_research_brief(
+            project_root.name,
+            framework_text,
+            research_brief,
+            axes=axes,
+            method=method,
+        )
+    else:
+        cards = generate_task_cards(project_root.name, framework_text, axes=axes, method=method)
     if not dry_run:
         ensure_phase_dirs(project_root)
         write_task_cards(project_root / "phase2" / "task_cards.json", cards)

scripts/runtime/phase1.py

@@ -3,6 +3,7 @@
 from __future__ import annotations
 
 import hashlib
+import json
 import re
 from datetime import datetime, timezone
 from pathlib import Path
@@ -11,6 +12,7 @@ from typing import Any
 from scripts.runtime.artifacts import PROJECTS_DIR, ensure_phase_dirs, load_manifest, write_manifest
 from scripts.runtime.materials import ingest_input_materials, render_material_inventory
 from scripts.runtime.methods import ResearchMethod, ResearchMethodRegistry
+from scripts.runtime.tasks import AXIS_ROUTES
 
 
 def utc_now_iso() -> str:
@@ -187,6 +189,132 @@ def write_material_brief(
     return out
 
 
+def _axis_prompt_brief(axis: str, method: ResearchMethod) -> str:
+    prompts = {
+        "input_material_findings": "从用户材料中提取现场事实、审计发现、复盘记录和内部答复，并标注原始材料位置。",
+        "nmpa_fda_ema_ich_who_baseline": "把 NMPA、FDA、EMA、ICH、WHO、药典或 Annex 1 等要求转化为可核验的法规基线。",
+        "quality_system_gap": "把现场发现映射到质量体系流程缺口，覆盖偏差、变更、CAPA、文件、培训和数据完整性。",
+        "manufacturing_process_risk": "围绕生产工艺、设施、公用系统、CPP/CQA、验证和无菌保障识别系统性风险。",
+        "operations_management_gap": "诊断运营管理、跨部门协同、会议机制、指标体系和交付节奏的结构性问题。",
+        "team_capability": "识别人员能力、岗位职责、质量文化和管理梯队方面的缺口与建设路径。",
+        "capa_roadmap": "把差距转化为短中长期 CAPA 组合，要求绑定 owner、期限、优先级、关闭证据和复核机制。",
+        "verification_evidence": "定义整改完成后可被审计接受的验证证据，包括记录、报告、趋势和管理评审输入。",
+        "counter": "主动寻找反方证据、限制条件和可能降低严重度或改变优先级的解释，避免单向论证。",
+    }
+    return prompts.get(axis, f"按照 `{method.key}` 方法，对 {axis} 轴进行证据收集、证伪和结构化归纳。")
+
+
+def _material_paths(manifest: dict[str, Any]) -> list[dict[str, str]]:
+    materials: list[dict[str, str]] = []
+    for item in manifest.get("material_inventory") or []:
+        rel = item.get("ocr_extracted_to") or item.get("extracted_to") or item.get("copied_to")
+        if rel:
+            materials.append({"path": rel, "role": "input_material"})
+    return materials
+
+
+def build_research_brief_payload(
+    project_root: Path,
+    manifest: dict[str, Any],
+    method: ResearchMethod,
+) -> dict[str, Any]:
+    """Create the file-backed Phase 1 research brief used by task-card generation."""
+    axes = list(method.task_axes)
+    return {
+        "version": "0.21-alpha",
+        "topic": manifest.get("topic", project_root.name),
+        "research_method": method.key,
+        "method_name": method.name,
+        "work_language": "zh",
+        "tone": "事实型、整改导向、面向管理层和质量/生产负责人；避免空泛咨询腔。",
+        "central_question": f"如何基于已提供材料和权威法规/最佳实践，系统诊断“{manifest.get('topic', project_root.name)}”并形成可执行整改路线图？",
+        "success_criteria": [
+            "每个核心判断都能回到用户材料、权威法规、最佳实践或反方证据。",
+            "短中长期整改建议必须绑定优先级、责任、关闭证据和复核机制。",
+            "章节写作必须先收束主线，再使用 evidence packet；不得按 packet 机械拼贴。",
+        ],
+        "phase2_inputs": {
+            "material_brief_path": "phase1/material_brief.md",
+            "framework_path": "phase1/framework.md",
+            "research_brief_path": "phase1/research_brief.json",
+        },
+        "materials": _material_paths(manifest),
+        "task_planning": {
+            "chapter_source": "phase1/framework.md",
+            "axes": axes,
+            "required_skills": [
+                "deep-research",
+                "search-gateway",
+                "search-strategy",
+                "source-quality",
+                "evidence-table",
+                "citation-manager",
+            ],
+            "search_routes_by_axis": {axis: AXIS_ROUTES.get(axis, ["general"]) for axis in axes},
+            "axis_prompt_briefs": {axis: _axis_prompt_brief(axis, method) for axis in axes},
+            "stop_conditions": [
+                "每张任务卡至少形成 3 条可追溯 evidence_items，且不得编造 candidate_sources 以外来源。",
+                "关键 claim 不足 2 个独立 Tier 1-2 信源时，必须写入 open_questions 和证据缺口。",
+                "必须包含 counter_evidence；找不到反方证据时记录检索路径和限制。",
+            ],
+            "fragmentation_guard": "并发 worker 只生产 evidence packet；章节主线由 compressed_findings 收束，禁止直接把 packet 堆成正文。",
+        },
+        "clarification_notes": {
+            "requires_user_review": True,
+            "questions_source": "phase1/material_brief.md",
+            "decision_items": [
+                "确认报告用途、受众和脱敏边界。",
+                "确认研究方法是否适配当前场景；MECE 只是可选方法之一。",
+                "确认任务切分和检索策略是否足以让低成本模型独立执行。",
+            ],
+        },
+    }
+
+
+def write_research_brief(
+    project_root: Path,
+    manifest: dict[str, Any] | None = None,
+    method: ResearchMethod | None = None,
+) -> tuple[Path, Path]:
+    manifest = manifest or load_manifest(project_root)
+    method = method or ResearchMethodRegistry().get(manifest.get("research_method"))
+    payload = build_research_brief_payload(project_root, manifest, method)
+    json_path = project_root / "phase1" / "research_brief.json"
+    md_path = project_root / "phase1" / "research_brief.md"
+    json_path.parent.mkdir(parents=True, exist_ok=True)
+    json_path.write_text(json.dumps(payload, ensure_ascii=False, indent=2) + "\n", encoding="utf-8")
+    lines = [
+        f"# Phase 1 Research Brief：{payload['topic']}",
+        "",
+        f"- research_method: {payload['research_method']}",
+        f"- work_language: {payload['work_language']}",
+        f"- tone: {payload['tone']}",
+        "",
+        "## 中心问题",
+        "",
+        payload["central_question"],
+        "",
+        "## 成功标准",
+        "",
+    ]
+    lines.extend(f"- {item}" for item in payload["success_criteria"])
+    lines.extend(["", "## 任务切分原则", ""])
+    planning = payload["task_planning"]
+    lines.append(planning["fragmentation_guard"])
+    lines.append("")
+    for axis in planning["axes"]:
+        routes = "、".join(planning["search_routes_by_axis"].get(axis, []))
+        prompt = planning["axis_prompt_briefs"].get(axis, "")
+        lines.append(f"- `{axis}`：{prompt} 检索路径：{routes}")
+    lines.extend(["", "## 必读 Skills", ""])
+    lines.extend(f"- {name}" for name in planning["required_skills"])
+    lines.extend(["", "## 停止条件", ""])
+    lines.extend(f"- {item}" for item in planning["stop_conditions"])
+    lines.append("")
+    md_path.write_text("\n".join(lines), encoding="utf-8")
+    return md_path, json_path
+
+
 CHAPTER_TEMPLATES: dict[str, list[str]] = {
     "mckinsey_market": [
         "核心结论先行界定市场机会与约束",
@@ -329,10 +457,14 @@ def render_framework(project_root: Path, *, method_key: str | None = None, chapt
     out = project_root / "phase1" / "framework.md"
     out.parent.mkdir(parents=True, exist_ok=True)
     out.write_text("\n".join(lines), encoding="utf-8")
+    research_brief_md, research_brief_json = write_research_brief(project_root, manifest, method)
     manifest["phase1"] = {
         "status": "completed",
         "approved": False,
         "framework_path": "phase1/framework.md",
+        "research_brief_path": str(research_brief_md.relative_to(project_root)),
+        "research_brief_json_path": str(research_brief_json.relative_to(project_root)),
+        "requires_user_interview": True,
         "research_method": method.key,
         "updated_at": utc_now_iso(),
     }

scripts/runtime/tasks.py

@@ -63,6 +63,14 @@ class TaskCard:
     preferred_model_role: str = "dr_analyst"
     status: str = "pending"
     dependencies: list[str] = field(default_factory=list)
+    research_goal: str = ""
+    research_method: str = ""
+    prompt_brief: str = ""
+    required_skills: list[str] = field(default_factory=list)
+    allowed_materials: list[str] = field(default_factory=list)
+    expected_evidence: dict[str, Any] = field(default_factory=dict)
+    stop_conditions: list[str] = field(default_factory=list)
+    model_hint: str = ""
 
     def to_dict(self) -> dict[str, Any]:
         return asdict(self)
@@ -105,6 +113,66 @@ def _questions_for_axis(chapter: Chapter, axis: str) -> list[str]:
     ]
 
 
+def _default_required_skills(axis: str) -> list[str]:
+    skills = ["search-gateway", "search-strategy", "source-quality", "evidence-table"]
+    if axis == "counter":
+        skills.append("mckinsey-method")
+    return skills
+
+
+def _default_expected_evidence(axis: str) -> dict[str, Any]:
+    return {
+        "min_tier_1_2_sources": 2,
+        "must_include_counter_evidence": True,
+        "must_include_source_metadata": True,
+        "preferred_evidence_types": [
+            "regulatory_or_best_practice_requirement",
+            "site_or_material_finding",
+            "quantitative_fact_or_record",
+            "implementation_or_verification_evidence",
+        ],
+        "axis": axis,
+    }
+
+
+def _default_stop_conditions() -> list[str]:
+    return [
+        "已形成至少 3 条可追溯 evidence_items，且每条关键 claim 有 source_id。",
+        "已主动记录 counter_evidence 或明确说明未找到反方证据的检索路径。",
+        "candidate_sources 不足以支撑结论时停止写作，并把缺口写入 open_questions。",
+    ]
+
+
+def _task_card_for_chapter_axis(
+    *,
+    chapter: Chapter,
+    axis: str,
+    routes: list[str],
+    method_key: str,
+    required_skills: list[str] | None = None,
+    allowed_materials: list[str] | None = None,
+    prompt_brief: str | None = None,
+    stop_conditions: list[str] | None = None,
+) -> TaskCard:
+    return TaskCard(
+        task_id=f"{chapter.chapter_id}-{axis}",
+        chapter_ids=[chapter.chapter_id],
+        topic_axis=axis,
+        questions=_questions_for_axis(chapter, axis),
+        search_routes=routes,
+        output_packet=f"phase2/packets/{chapter.chapter_id}-{axis}.json",
+        preferred_model_role="dr_verifier" if axis == "counter" else "dr_analyst",
+        research_goal=f"为《{chapter.title}》收集并验证 {axis} 轴证据，形成可写入章节的具体判断与证据落点。",
+        research_method=method_key,
+        prompt_brief=prompt_brief or f"围绕《{chapter.title}》的 {axis} 轴，优先形成可证伪、可引用、可落地的证据包。",
+        required_skills=required_skills or _default_required_skills(axis),
+        allowed_materials=allowed_materials or [],
+        expected_evidence=_default_expected_evidence(axis),
+        stop_conditions=stop_conditions or _default_stop_conditions(),
+        model_hint="use_cross_model_verifier" if axis == "counter" else "use_cost_effective_research_worker",
+    )
+
+
 def generate_task_cards(
     slug: str,
     framework_text: str,
@@ -120,14 +188,56 @@ def generate_task_cards(
         for axis in selected_axes:
             routes = AXIS_ROUTES.get(axis, ["general"])
             cards.append(
-                TaskCard(
-                    task_id=f"{chapter.chapter_id}-{axis}",
-                    chapter_ids=[chapter.chapter_id],
-                    topic_axis=axis,
-                    questions=_questions_for_axis(chapter, axis),
-                    search_routes=routes,
-                    output_packet=f"phase2/packets/{chapter.chapter_id}-{axis}.json",
-                    preferred_model_role="dr_verifier" if axis == "counter" else "dr_analyst",
+                _task_card_for_chapter_axis(
+                    chapter=chapter,
+                    axis=axis,
+                    routes=routes,
+                    method_key=method.key if method else "",
+                )
+            )
+    validate_task_cards(cards)
+    return cards
+
+
+def generate_task_cards_from_research_brief(
+    slug: str,
+    framework_text: str,
+    research_brief: dict[str, Any],
+    *,
+    axes: list[str] | None = None,
+    method: ResearchMethod | None = None,
+) -> list[TaskCard]:
+    del slug
+    chapters = parse_framework_chapters(framework_text)
+    planning = research_brief.get("task_planning") or {}
+    method_key = research_brief.get("research_method") or (method.key if method else "")
+    selected_axes = axes or (method.task_axes if method else None) or list(planning.get("search_routes_by_axis") or []) or DEFAULT_AXES
+    routes_by_axis = planning.get("search_routes_by_axis") or {}
+    prompt_by_axis = planning.get("axis_prompt_briefs") or {}
+    base_skills = list(planning.get("required_skills") or [])
+    stop_conditions = list(planning.get("stop_conditions") or [])
+    allowed_materials = [
+        str(item.get("path"))
+        for item in research_brief.get("materials", [])
+        if item.get("path")
+    ]
+    cards: list[TaskCard] = []
+    for chapter in chapters:
+        for axis in selected_axes:
+            routes = list(routes_by_axis.get(axis) or AXIS_ROUTES.get(axis, ["general"]))
+            skills = base_skills or _default_required_skills(axis)
+            if "search-gateway" not in skills:
+                skills = ["search-gateway", *skills]
+            cards.append(
+                _task_card_for_chapter_axis(
+                    chapter=chapter,
+                    axis=axis,
+                    routes=routes,
+                    method_key=method_key,
+                    required_skills=skills,
+                    allowed_materials=allowed_materials,
+                    prompt_brief=prompt_by_axis.get(axis),
+                    stop_conditions=stop_conditions or None,
                 )
             )
     validate_task_cards(cards)
@@ -157,6 +267,18 @@ def detect_dependency_cycles(cards: list[TaskCard]) -> None:
 def validate_task_cards(cards: list[TaskCard]) -> None:
     seen: set[str] = set()
     for card in cards:
+        if not card.research_goal:
+            card.research_goal = f"围绕 {card.topic_axis} 轴收集并验证结构化证据。"
+        if not card.prompt_brief:
+            card.prompt_brief = f"按 {card.topic_axis} 轴形成证据包，避免泛泛结论。"
+        if not card.required_skills:
+            card.required_skills = _default_required_skills(card.topic_axis)
+        if "search-gateway" not in card.required_skills:
+            card.required_skills = ["search-gateway", *card.required_skills]
+        if not card.expected_evidence:
+            card.expected_evidence = _default_expected_evidence(card.topic_axis)
+        if not card.stop_conditions:
+            card.stop_conditions = _default_stop_conditions()
         if card.task_id in seen:
             raise ValueError(f"duplicate task_id: {card.task_id}")
         seen.add(card.task_id)

scripts/v020_regression.py

@@ -34,6 +34,29 @@ def make_fixture(root: Path) -> Path:
     return project
 
 
+def write_fixture_packet(project: Path) -> None:
+    cards = json.loads((project / "phase2" / "task_cards.json").read_text(encoding="utf-8"))
+    for index, card in enumerate(cards, start=1):
+        source_a = f"src_{index:03d}_a"
+        source_b = f"src_{index:03d}_b"
+        packet = {
+            "task_id": card["task_id"],
+            "claims": [{"claim": f"{card['task_id']} 回归证据支持章节主线", "source_ids": [source_a]}],
+            "evidence_items": [{"source_id": source_a, "summary": "权威来源支持该判断"}],
+            "counter_evidence": [{"claim": "证据仍需更多来源交叉验证", "source_ids": [source_b]}],
+            "source_ids": [source_a, source_b],
+            "source_quality_notes": [f"{source_a} Tier 1", f"{source_b} Tier 2"],
+            "open_questions": ["需要在真实项目中补充更多来源。"],
+            "raw_quotes_or_notes": ["English raw note can remain here."],
+            "sources": [
+                {"id": source_a, "title": f"Regression Source {index}A", "url": f"https://example.com/source-{index}-a", "tier": 1},
+                {"id": source_b, "title": f"Regression Source {index}B", "url": f"https://example.com/source-{index}-b", "tier": 2},
+            ],
+        }
+        packet_path = project / card["output_packet"]
+        packet_path.write_text(json.dumps(packet, ensure_ascii=False, indent=2) + "\n", encoding="utf-8")
+
+
 def main() -> int:
     python = sys.executable
     run([python, "scripts/dr.py", "skills", "validate"])
@@ -56,9 +79,13 @@ def main() -> int:
         )
         project = make_fixture(tmp_root)
         run([python, "scripts/dr.py", "frame", str(project)])
+        assert (project / "phase1" / "research_brief.json").exists()
         run([python, "scripts/dr.py", "approve", str(project)])
-        run([python, "scripts/dr.py", "research", str(project), "--workers", "2", "--dry-run"])
-        run([python, "scripts/dr.py", "research", str(project), "--workers", "2"])
+        run([python, "scripts/dr.py", "research", str(project), "--workers", "2", "--axis", "literature", "--dry-run"])
+        run([python, "scripts/dr.py", "research", str(project), "--workers", "2", "--axis", "literature"])
+        write_fixture_packet(project)
+        run([python, "scripts/dr.py", "research", str(project), "--workers", "2", "--axis", "literature", "--build-briefs"])
+        assert (project / "phase2" / "compressed_findings" / "ch01.json").exists()
         run([python, "scripts/dr.py", "review", str(project)])
         run([python, "scripts/dr.py", "finalize", str(project), "--dry-run"])
     print("v0.20 regression PASS")

tests/test_chapter_assembly.py

@@ -11,10 +11,12 @@ if str(REPO_ROOT) not in sys.path:
 from scripts.runtime.assembly import (
     ChapterAssemblyWorker,
     build_chapter_briefs,
+    build_compressed_findings,
     build_chapter_user_prompt,
     run_chapter_assembly_workers,
     validate_chapter_markdown_citations,
     validate_chapter_brief,
+    validate_compressed_finding,
 )
 from scripts.runtime.roles import resolve_runtime_profile
 
@@ -104,6 +106,17 @@ def test_build_chapter_briefs_aggregates_packets_by_chapter(tmp_path: Path) -> N
     assert "src_002" in brief["source_ids"]
     assert (project / "phase2/chapter_briefs/ch01.json").exists()
 
+    compressed = build_compressed_findings(project)
+
+    assert len(compressed) == 1
+    finding = compressed[0]
+    validate_compressed_finding(finding)
+    assert finding["chapter_id"] == "ch01"
+    assert "chapter_thesis" in finding
+    assert "evidence_landings" in finding
+    assert "src_001" in finding["source_ids"]
+    assert (project / "phase2/compressed_findings/ch01.json").exists()
+
 
 def test_chapter_prompt_contains_brief_and_fragmentation_guard() -> None:
     brief = {
@@ -122,6 +135,7 @@ def test_chapter_prompt_contains_brief_and_fragmentation_guard() -> None:
 
     assert "临床证据正在重塑需求判断" in prompt
     assert "避免碎片化" in prompt
+    assert "compressed finding" in prompt
     assert "只输出 Markdown" in prompt
 
 

tests/test_phase0_materials.py

@@ -62,9 +62,20 @@ def test_framework_mentions_ingested_materials(tmp_path: Path) -> None:
     render_framework(project, method_key="gmp_quality_operations_diagnosis")
 
     framework = (project / "phase1/framework.md").read_text(encoding="utf-8")
+    research_brief_md = project / "phase1" / "research_brief.md"
+    research_brief_json = project / "phase1" / "research_brief.json"
+    brief = json.loads(research_brief_json.read_text(encoding="utf-8"))
+
     assert "phase0/extracted/audit.md" in framework
     assert "NMPA、FDA、EMA、ICH、WHO" in framework
     assert "请先确认 `phase1/material_brief.md`" in framework
+    assert research_brief_md.exists()
+    assert "任务切分原则" in research_brief_md.read_text(encoding="utf-8")
+    assert brief["research_method"] == "gmp_quality_operations_diagnosis"
+    assert brief["work_language"] == "zh"
+    assert brief["task_planning"]["required_skills"]
+    assert brief["task_planning"]["search_routes_by_axis"]["counter"] == ["scholar", "general"]
+    assert brief["phase2_inputs"]["framework_path"] == "phase1/framework.md"
 
 
 def test_pdf_requiring_ocr_uses_firered_and_records_result(tmp_path: Path, monkeypatch) -> None:

tests/test_research_methods.py

@@ -45,6 +45,23 @@ def test_orchestrator_reads_research_method_from_manifest(tmp_path: Path) -> Non
         "## 第1章 GMP 体系差距需要按法规和风险双轴定位\n\n研究思路。",
         encoding="utf-8",
     )
+    (project / "phase1" / "research_brief.json").write_text(
+        json.dumps(
+            {
+                "research_method": "gmp_gap_assessment",
+                "work_language": "zh",
+                "task_planning": {
+                    "required_skills": ["search-gateway", "evidence-table"],
+                    "search_routes_by_axis": {"regulatory_gap": ["general", "news"]},
+                    "axis_prompt_briefs": {"regulatory_gap": "逐条映射法规基线与审计差距。"},
+                    "stop_conditions": ["证据不足则回炉补证。"],
+                },
+                "materials": [{"path": "phase0/extracted/audit.md"}],
+            },
+            ensure_ascii=False,
+        ),
+        encoding="utf-8",
+    )
 
     cards = create_phase2_task_cards(project, dry_run=True)
 
@@ -53,3 +70,5 @@ def test_orchestrator_reads_research_method_from_manifest(tmp_path: Path) -> Non
         "risk_classification",
         "capa_design",
     ]
+    assert cards[0]["prompt_brief"] == "逐条映射法规基线与审计差距。"
+    assert cards[0]["allowed_materials"] == ["phase0/extracted/audit.md"]

tests/test_v020_runtime.py

@@ -17,6 +17,7 @@ from scripts.runtime.tasks import (
     TaskCard,
     detect_dependency_cycles,
     generate_task_cards,
+    generate_task_cards_from_research_brief,
     validate_packet,
     validate_task_cards,
 )
@@ -77,6 +78,47 @@ def test_generate_task_cards_from_chinese_framework() -> None:
         "ch02-regulatory",
     ]
     assert cards[0].output_packet == "phase2/packets/ch01-clinical.json"
+    assert cards[0].research_goal
+    assert "search-gateway" in cards[0].required_skills
+    assert cards[0].expected_evidence["min_tier_1_2_sources"] == 2
+    assert cards[0].stop_conditions
+
+
+def test_generate_task_cards_from_research_brief_carries_prompt_and_skills() -> None:
+    brief = {
+        "research_method": "gmp_quality_operations_diagnosis",
+        "work_language": "zh",
+        "tone": "面向管理层的事实型整改诊断",
+        "task_planning": {
+            "required_skills": ["search-gateway", "evidence-table", "source-quality"],
+            "search_routes_by_axis": {
+                "quality_system_gap": ["general", "news"],
+                "counter": ["scholar", "general"],
+            },
+            "axis_prompt_briefs": {
+                "quality_system_gap": "把现场发现映射到质量体系流程缺口和法规要求。",
+                "counter": "主动寻找能削弱或限定结论的反方证据。",
+            },
+            "stop_conditions": ["每张卡至少形成 3 条可追溯证据。"],
+        },
+        "materials": [{"path": "phase0/extracted/audit.md", "role": "site_evidence"}],
+    }
+    framework = "## 第1章 质量体系闭环能力决定整改可信度\n\n研究思路。"
+
+    cards = generate_task_cards_from_research_brief(
+        "baifan-test",
+        framework,
+        brief,
+        axes=["quality_system_gap", "counter"],
+    )
+
+    assert [card.task_id for card in cards] == ["ch01-quality_system_gap", "ch01-counter"]
+    assert cards[0].prompt_brief == "把现场发现映射到质量体系流程缺口和法规要求。"
+    assert cards[0].research_method == "gmp_quality_operations_diagnosis"
+    assert cards[0].allowed_materials == ["phase0/extracted/audit.md"]
+    assert cards[0].preferred_model_role == "dr_analyst"
+    assert cards[1].preferred_model_role == "dr_verifier"
+    assert "search-gateway" in cards[0].required_skills
 
 
 def test_task_card_validation_rejects_duplicates_and_cycles() -> None: