v0.21 alpha add research brief and compressed findings

2026-05-06 19:23:30 +08:00
parent db626f1d58
commit 0644a68ecc
13 changed files with 539 additions and 27 deletions
@@ -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)