feat: 报告结构支持检索方向/来源与智能新增，并修复协助卡停轮与宿主跳转

为深度研究报告结构增加检索方向与技能来源、对话式智能新增页与详情排版；澄清中间件在 after_model 可靠结束本轮，避免弱模型出卡后继续生成；任务按钮补充 host 跳转与相关深链能力。 Co-authored-by: Cursor <cursoragent@cursor.com>
2026-08-22 17:46:06 +08:00
1 parent a5a9c952e8
commit 51afebb394
@@ -11,11 +11,12 @@ from deerflow.agents.middlewares.memory_middleware import MemoryMiddleware
 from deerflow.agents.middlewares.prompt_prefix_middleware import PromptPrefixMiddleware
 from deerflow.agents.middlewares.rag_citation_middleware import RagCitationMiddleware
 from deerflow.agents.middlewares.setup_agent_approval_middleware import SetupAgentApprovalMiddleware
+from deerflow.agents.middlewares.setup_report_structure_approval_middleware import SetupReportStructureApprovalMiddleware
 from deerflow.agents.middlewares.setup_writing_approval_middleware import SetupWritingApprovalMiddleware
-from deerflow.agents.middlewares.subagent_limit_middleware import SubagentLimitMiddleware
-from deerflow.agents.middlewares.summarization_middleware import BeforeSummarizationHook, DeerFlowSummarizationMiddleware
-from deerflow.agents.middlewares.task_external_context_middleware import TaskExternalContextMiddleware
-from deerflow.agents.middlewares.title_middleware import TitleMiddleware
+from deerflow.agents.middlewares.subagent_limit_middleware import SubagentLimitMiddleware
+from deerflow.agents.middlewares.summarization_middleware import BeforeSummarizationHook, DeerFlowSummarizationMiddleware
+from deerflow.agents.middlewares.task_external_context_middleware import TaskExternalContextMiddleware
+from deerflow.agents.middlewares.title_middleware import TitleMiddleware
 from deerflow.agents.middlewares.todo_middleware import TodoMiddleware
 from deerflow.agents.middlewares.token_usage_middleware import TokenUsageMiddleware
 from deerflow.agents.middlewares.tool_error_handling_middleware import build_lead_runtime_middlewares
@@ -31,6 +32,7 @@ logger = logging.getLogger(__name__)
 # 写作配置 Q&A 现在「先生成大纲并与用户多轮确认 → 再提交配置」，需要更多来回，故上限放宽。
 # 仍是兜底安全阀：到顶才用 tool_choice 强制提交，正常流程由用户确认大纲后自然提交。
 WRITING_SETUP_MAX_ROUNDS = 8
+REPORT_STRUCTURE_SETUP_MAX_ROUNDS = 8


 def _get_runtime_config(config: RunnableConfig) -> dict:
@@ -292,6 +294,7 @@ def _build_middlewares(
    is_plan_mode = cfg.get("is_plan_mode", False)
    is_bootstrap = cfg.get("is_bootstrap", False)
    is_writing_setup = cfg.get("is_writing_setup", False)
+    is_report_structure_setup = cfg.get("is_report_structure_setup", False)
    todo_list_middleware = _create_todo_list_middleware(is_plan_mode)
    if todo_list_middleware is not None:
        middlewares.append(todo_list_middleware)
@@ -319,7 +322,7 @@ def _build_middlewares(

    # Add MemoryMiddleware (after TitleMiddleware) — skip in bootstrap mode (agent creation flow) and ephemeral runs
    memory_injection_enabled = cfg.get("memory_injection_enabled", True)
-    if not is_bootstrap and not is_writing_setup and not is_ephemeral:
+    if not is_bootstrap and not is_writing_setup and not is_report_structure_setup and not is_ephemeral:
        middlewares.append(MemoryMiddleware(agent_name=agent_name, memory_config=resolved_app_config.memory, injection_enabled=memory_injection_enabled))

    # KnowledgeRagMiddleware — inject knowledge-base recall (phase 2). Gated
@@ -327,16 +330,16 @@ def _build_middlewares(
    # to the global ``knowledge.rag_enabled`` config. No-op when knowledge is
    # disabled. Skipped in bootstrap/writing-setup/ephemeral like MemoryMiddleware.
    knowledge_cfg = getattr(resolved_app_config, "knowledge", None)
-    if not is_bootstrap and not is_writing_setup and not is_ephemeral and knowledge_cfg is not None and knowledge_cfg.enabled:
-        from deerflow.agents.middlewares.knowledge_rag_middleware import KnowledgeRagMiddleware
-
-        middlewares.append(KnowledgeRagMiddleware(limit=knowledge_cfg.rag_limit, default_enabled=knowledge_cfg.rag_enabled))
-
-    # TaskExternalContextMiddleware — inject hidden per-run business context
-    # (for example rwfx's completed 3q report) into the model request only.
-    middlewares.append(TaskExternalContextMiddleware())
-
-    # Add ViewImageMiddleware only for the NATIVE-vision path (main model
+    if not is_bootstrap and not is_writing_setup and not is_report_structure_setup and not is_ephemeral and knowledge_cfg is not None and knowledge_cfg.enabled:
+        from deerflow.agents.middlewares.knowledge_rag_middleware import KnowledgeRagMiddleware
+
+        middlewares.append(KnowledgeRagMiddleware(limit=knowledge_cfg.rag_limit, default_enabled=knowledge_cfg.rag_enabled))
+
+    # TaskExternalContextMiddleware — inject hidden per-run business context
+    # (for example rwfx's completed 3q report) into the model request only.
+    middlewares.append(TaskExternalContextMiddleware())
+
+    # Add ViewImageMiddleware only for the NATIVE-vision path (main model
    # ingests raw image data). In delegated mode the view_image tool already
    # returns a text description and stores nothing in `viewed_images`, so the
    # middleware would otherwise inject a spurious "No images have been viewed."
@@ -374,6 +377,7 @@ def _build_middlewares(

    middlewares.append(SetupAgentApprovalMiddleware())
    middlewares.append(SetupWritingApprovalMiddleware())
+    middlewares.append(SetupReportStructureApprovalMiddleware())

    # SkillStopMiddleware — intercepts skill invocations and halts execution
    # when a configured skill is about to run. Request-level options
@@ -421,7 +425,7 @@ def make_lead_agent(config: RunnableConfig):
 def _make_lead_agent(config: RunnableConfig, *, app_config: AppConfig):
    # Lazy import to avoid circular dependency
    from deerflow.tools import get_available_tools
-    from deerflow.tools.builtins import ask_clarification_tool, setup_agent, setup_writing
+    from deerflow.tools.builtins import ask_clarification_tool, setup_agent, setup_report_structure, setup_writing

    cfg = _get_runtime_config(config)
    resolved_app_config = app_config
@@ -443,8 +447,12 @@ def _make_lead_agent(config: RunnableConfig, *, app_config: AppConfig):
    is_writing_setup = cfg.get("is_writing_setup", False)
    writing_setup_article_types = cfg.get("valid_article_types") if is_writing_setup else None
    # 快捷模式：跳过逐项选项澄清，给标题直接出大纲（见 build_writing_setup_prompt）。
-    writing_setup_quick = bool(cfg.get("writing_setup_quick", False)) if is_writing_setup else False
-    writing_sample_context = cfg.get("writing_sample_context") if is_writing_setup else None
+    writing_setup_quick = bool(cfg.get("writing_setup_quick", False)) if is_writing_setup else False
+    writing_sample_context = cfg.get("writing_sample_context") if is_writing_setup else None
+    # 报告结构智能新增：与 is_writing_setup 同构的最小化 bootstrap。
+    is_report_structure_setup = cfg.get("is_report_structure_setup", False)
+    report_structure_setup_skills = cfg.get("valid_retrieval_skills") if is_report_structure_setup else None
+    report_structure_setup_quick = bool(cfg.get("writing_setup_quick", False)) if is_report_structure_setup else False
    memory_injection_enabled = bool(cfg.get("memory_injection_enabled", True))
    rag_mode_enabled = bool(cfg.get("rag_mode_enabled", False))
    writing_mode = bool(cfg.get("writing_mode", False))
@@ -455,7 +463,7 @@ def _make_lead_agent(config: RunnableConfig, *, app_config: AppConfig):
    requested_excluded_tools = cfg.get("excluded_tools") or None

    try:
-        agent_config = load_agent_config(agent_id) if not is_bootstrap and not is_writing_setup else None
+        agent_config = load_agent_config(agent_id) if not is_bootstrap and not is_writing_setup and not is_report_structure_setup else None
    except FileNotFoundError:
        logger.warning("Agent directory not found for '%s'; running with default config", agent_id)
        agent_config = None
@@ -499,6 +507,13 @@ def _make_lead_agent(config: RunnableConfig, *, app_config: AppConfig):
        # Default lead agent keeps existing behavior (all enabled skills).
        runtime_available_skills = None

+    from deerflow.agents.deep_research.retrieval import merge_collector_skill_allowlist, runtime_extra_skills
+
+    runtime_available_skills = merge_collector_skill_allowlist(
+        agent_id, runtime_available_skills, runtime_extra_skills(cfg)
+    )
+    prompt_available_skills = set(runtime_available_skills) if runtime_available_skills is not None else None
+
    config["metadata"].update(
        {
            "agent_id": agent_id,
@@ -533,13 +548,46 @@ def _make_lead_agent(config: RunnableConfig, *, app_config: AppConfig):
                *_build_middlewares(config, model_name=model_name, app_config=resolved_app_config),
                WritingSetupRoundCapMiddleware(max_rounds=WRITING_SETUP_MAX_ROUNDS),
            ],
-            system_prompt=build_writing_setup_prompt(
-                writing_setup_article_types,
-                quick_mode=writing_setup_quick,
-                sample_context=writing_sample_context,
-            ),
-            state_schema=ThreadState,
-        )
+            system_prompt=build_writing_setup_prompt(
+                writing_setup_article_types,
+                quick_mode=writing_setup_quick,
+                sample_context=writing_sample_context,
+            ),
+            state_schema=ThreadState,
+        )
+
+    if is_report_structure_setup:
+        from deerflow.agents.lead_agent.prompt import build_report_structure_setup_prompt
+        from deerflow.agents.middlewares.writing_setup_round_cap_middleware import WritingSetupRoundCapMiddleware
+
+        setup_tools = (
+            [setup_report_structure]
+            if report_structure_setup_quick
+            else [setup_report_structure, ask_clarification_tool]
+        )
+        return create_agent(
+            model=create_chat_model(name=model_name, thinking_enabled=thinking_enabled, force_disable_thinking=thinking_force_disabled, app_config=resolved_app_config),
+            tools=setup_tools,
+            middleware=[
+                *_build_middlewares(config, model_name=model_name, app_config=resolved_app_config),
+                WritingSetupRoundCapMiddleware(
+                    max_rounds=REPORT_STRUCTURE_SETUP_MAX_ROUNDS,
+                    tool_name="setup_report_structure",
+                    force_instruction=(
+                        f"【系统强制】意图澄清已达 {REPORT_STRUCTURE_SETUP_MAX_ROUNDS} 轮上限。"
+                        "现在必须立即调用 setup_report_structure 提交报告结构配置，禁止再向用户提任何问题。"
+                        "缺失或不确定的字段一律用合理默认值："
+                        "title 根据对话主题拟一个短标题、name 用一句话描述、structure_mode 默认 adaptive、"
+                        "retrieval_directions / retrieval_skills 不确定就留空、content 必须给出一份 Markdown 大纲。"
+                    ),
+                ),
+            ],
+            system_prompt=build_report_structure_setup_prompt(
+                report_structure_setup_skills,
+                quick_mode=report_structure_setup_quick,
+            ),
+            state_schema=ThreadState,
+        )

    if is_bootstrap:
        # Special bootstrap agent with minimal prompt for initial custom agent creation flow
@@ -600,7 +648,7 @@ def _make_lead_agent(config: RunnableConfig, *, app_config: AppConfig):
            agent_name=agent_display_name,
            subagent_enabled=subagent_enabled,
            max_concurrent_subagents=max_concurrent_subagents,
-            available_skills=(set(agent_config.skills or []) if agent_config else None),
+            available_skills=prompt_available_skills,
            app_config=resolved_app_config,
            rag_mode_enabled=rag_mode_enabled,
            writing_mode=writing_mode,
@@ -614,7 +662,7 @@ def _make_lead_agent(config: RunnableConfig, *, app_config: AppConfig):
            agent_name=agent_display_name,
            writing_mode=writing_mode,
            writing_artifact_path=writing_artifact_path,
-            available_skills=(set(agent_config.skills or []) if agent_config else None),
+            available_skills=prompt_available_skills,
            app_config=resolved_app_config,
            memory_injection_enabled=memory_injection_enabled,
            rag_mode_enabled=rag_mode_enabled,