This commit is contained in:
许海洋 committed 2026-06-01 07:56:34 +08:00
commit dadb0bbe68
782 files changed
+160067 -3424

No files matched your search

@@ -9,6 +9,7 @@ from deerflow.agents.middlewares.clarification_middleware import ClarificationMi
from deerflow.agents.middlewares.loop_detection_middleware import LoopDetectionMiddleware
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.subagent_limit_middleware import SubagentLimitMiddleware
from deerflow.agents.middlewares.summarization_middleware import BeforeSummarizationHook, DeerFlowSummarizationMiddleware
@@ -254,11 +255,14 @@ def _build_middlewares(
List of middleware instances.
"""
resolved_app_config = app_config or get_app_config()
cfg = _get_runtime_config(config)
middlewares = build_lead_runtime_middlewares(app_config=resolved_app_config, lazy_init=True)
# Inject the admin prompt prefix into the model request (kept out of the
# persisted/displayed message so the user never sees it).
middlewares.append(PromptPrefixMiddleware())
if cfg.get("rag_mode_enabled", False):
middlewares.append(RagCitationMiddleware())
# Add summarization middleware if enabled
summarization_middleware = _create_summarization_middleware(app_config=resolved_app_config)
@@ -266,7 +270,6 @@ def _build_middlewares(
middlewares.append(summarization_middleware)
# Add TodoList middleware if plan mode is enabled
cfg = _get_runtime_config(config)
is_plan_mode = cfg.get("is_plan_mode", False)
is_bootstrap = cfg.get("is_bootstrap", False)
todo_list_middleware = _create_todo_list_middleware(is_plan_mode)
@@ -370,6 +373,7 @@ def _make_lead_agent(config: RunnableConfig, *, app_config: AppConfig):
max_concurrent_subagents = cfg.get("max_concurrent_subagents", 3)
is_bootstrap = cfg.get("is_bootstrap", 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))
writing_artifact_path = cfg.get("writing_artifact_path") if writing_mode else None
if not isinstance(writing_artifact_path, str) or not writing_artifact_path.strip():
@@ -497,24 +501,30 @@ def _make_lead_agent(config: RunnableConfig, *, app_config: AppConfig):
is_bootstrap=True,
app_config=resolved_app_config,
memory_injection_enabled=memory_injection_enabled,
rag_mode_enabled=rag_mode_enabled,
),
state_schema=ThreadState,
)
# Default lead agent (unchanged behavior)
# Use subagent tool groups if in subagent mode, otherwise use parent agent config
effective_tool_groups = subagent_tool_groups if subagent_mode else (agent_config.tool_groups if agent_config else None)
is_notebook_mode = bool(cfg.get("notebook_search_space_id"))
notebook_source_ids: list[int] = cfg.get("notebook_source_ids") or []
default_tools = get_available_tools(
model_name=model_name,
groups=agent_config.tool_groups if agent_config else None,
subagent_enabled=subagent_enabled,
is_scheduled_run=cfg.get("is_scheduled_run", False),
excluded_tools=requested_excluded_tools,
app_config=resolved_app_config,
)
if is_notebook_mode:
from deerflow.tools.builtins.notebook_search_tool import notebook_search_tool
default_tools = [notebook_search_tool] + default_tools
return create_agent(
model=create_chat_model(name=model_name, thinking_enabled=thinking_enabled, reasoning_effort=reasoning_effort, app_config=resolved_app_config),
tools=get_available_tools(
model_name=model_name,
groups=effective_tool_groups,
subagent_enabled=subagent_enabled,
is_scheduled_run=cfg.get("is_scheduled_run", False),
excluded_tools=requested_excluded_tools,
app_config=resolved_app_config,
),
tools=default_tools,
middleware=_build_middlewares(config, model_name=model_name, agent_name=agent_id, app_config=resolved_app_config),
system_prompt=apply_prompt_template(
subagent_enabled=subagent_enabled,
@@ -526,6 +536,9 @@ def _make_lead_agent(config: RunnableConfig, *, app_config: AppConfig):
available_skills=(set(agent_config.skills or []) if agent_config else None),
app_config=resolved_app_config,
memory_injection_enabled=memory_injection_enabled,
rag_mode_enabled=rag_mode_enabled,
is_notebook_mode=is_notebook_mode,
notebook_source_ids=notebook_source_ids,
),
state_schema=ThreadState,
)
@@ -667,17 +667,25 @@ def _get_memory_context(agent_name: str | None = None, *, app_config: AppConfig
@lru_cache(maxsize=32)
def _get_cached_skills_prompt_section(
skill_signature: tuple[tuple[str, str, str, str], ...],
display_signature: tuple[tuple[str, str, str], ...],
available_skills_key: tuple[str, ...] | None,
container_base_path: str,
skill_evolution_section: str,
) -> str:
display_by_skill = {name: (mode, custom_instruction) for name, mode, custom_instruction in display_signature}
filtered = [(name, description, category, location) for name, description, category, location in skill_signature if available_skills_key is None or name in available_skills_key]
skills_list = ""
if filtered:
skill_items = "\n".join(
f" <skill>\n <name>{name}</name>\n <description>{description} {_skill_mutability_label(category)}</description>\n <location>{location}</location>\n </skill>"
for name, description, category, location in filtered
)
items = []
for name, description, category, location in filtered:
display_mode, custom_instruction = display_by_skill.get(name, ("", ""))
display_hint = ""
if display_mode:
display_hint = f"\n <display mode=\"{display_mode}\">{custom_instruction}</display>"
items.append(
f" <skill>\n <name>{name}</name>\n <description>{description} {_skill_mutability_label(category)}</description>\n <location>{location}</location>{display_hint}\n </skill>"
)
skill_items = "\n".join(items)
skills_list = f"<available_skills>\n{skill_items}\n</available_skills>"
# Restricted mode: agent has an explicit skill allowlist.
@@ -693,6 +701,21 @@ def _get_cached_skills_prompt_section(
else:
scope_note = ""
display_pattern = (
"""
**Skill Result Display Pattern:**
- If RAG/reference display mode is enabled, do not number each skill result independently. Treat all retrieval results from the same user turn as one combined `referenceBatch` and cite with `[1]`, `[2]`, etc. from the system-provided reference prompt.
- In RAG/reference display mode, do not output `<skill-display .../>`; the frontend renders cards, tables, lists, and citation details in the right reference panel.
- If RAG/reference display mode is not enabled and a skill has `<display mode="citation">`, use the skill's returned result order as reference numbers. Cite facts from the first result as `[1]`, the second as `[2]`, and so on. Use only numbers that correspond to returned results.
- If a skill has `<display mode="list">`, summarize the returned items as a concise list and keep item order stable.
- If a skill has `<display mode="table">`, summarize the result and output `<skill-display tool="SKILL_OR_TOOL_NAME" mode="table" />` where the frontend should render the real table. Do not hand-write the table rows yourself.
- If a skill has `<display mode="card">`, summarize the result and output `<skill-display tool="SKILL_OR_TOOL_NAME" mode="card" />` where the frontend should render the cards.
- If a skill has `<display mode="custom">`, follow the custom display instruction in the `<display>` tag when presenting the skill result.
"""
if display_signature
else ""
)
return f"""<skill_system>
You have access to skills that provide optimized workflows for specific tasks. Each skill contains best practices, frameworks, and references to additional resources.
{scope_note}
@@ -702,13 +725,19 @@ You have access to skills that provide optimized workflows for specific tasks. E
3. The skill file contains references to external resources under the same folder
4. Load referenced resources only when needed during execution
5. Follow the skill's instructions precisely
{display_pattern}
{location_hint}{evolution_block}
{skills_list}
</skill_system>"""
def get_skills_prompt_section(available_skills: set[str] | None = None, *, app_config: AppConfig | None = None) -> str:
def get_skills_prompt_section(
available_skills: set[str] | None = None,
*,
app_config: AppConfig | None = None,
display_enabled: bool = False,
) -> str:
"""Generate the skills prompt section with available skills list."""
skills = _get_enabled_skills_for_config(app_config)
@@ -739,11 +768,30 @@ def get_skills_prompt_section(available_skills: set[str] | None = None, *, app_c
return ""
skill_signature = tuple((skill.name, skill.description, skill.category, skill.get_container_file_path(container_base_path)) for skill in skills)
display_signature: tuple[tuple[str, str, str], ...] = ()
if display_enabled:
try:
from deerflow.config.extensions_config import get_extensions_config
extensions = get_extensions_config()
display_signature = tuple(
(
name,
skill_config.display.mode,
skill_config.display.custom_instruction,
)
for name, skill_config in sorted(extensions.skills.items())
if skill_config.display is not None
and skill_config.display.enabled
and skill_config.display.mode != "none"
)
except Exception:
logger.debug("Failed to load skill display configs for prompt injection", exc_info=True)
available_key = tuple(sorted(available_skills)) if available_skills is not None else None
if not skill_signature and available_key is not None:
return ""
skill_evolution_section = _build_skill_evolution_section(effective_skill_evolution_enabled)
return _get_cached_skills_prompt_section(skill_signature, available_key, container_base_path, skill_evolution_section)
return _get_cached_skills_prompt_section(skill_signature, display_signature, available_key, container_base_path, skill_evolution_section)
def get_agent_soul(agent_id: str | None) -> str:
@@ -869,6 +917,9 @@ def apply_prompt_template(
app_config: AppConfig | None = None,
soul_override: str | None = None,
memory_injection_enabled: bool = True,
rag_mode_enabled: bool = False,
is_notebook_mode: bool = False,
notebook_source_ids: list[int] | None = None,
) -> str:
storage_agent_id = agent_id if agent_id is not None else agent_name
@@ -901,7 +952,11 @@ def apply_prompt_template(
bootstrap_section = _build_bootstrap_section() if is_bootstrap else ""
# Get skills section
skills_section = get_skills_prompt_section(available_skills, app_config=app_config)
skills_section = get_skills_prompt_section(
available_skills,
app_config=app_config,
display_enabled=rag_mode_enabled,
)
# Get deferred tools section (tool_search)
deferred_tools_section = get_deferred_tools_prompt_section(app_config=app_config)
@@ -939,6 +994,21 @@ Writing mode is enabled for this run.
# Build the offline-network policy block (empty unless DEER_FLOW_OFFLINE_MODE is set).
network_policy_section = _build_network_policy_section()
rag_mode_section = (
"""
<rag_citation_mode>
RAG/reference display mode is enabled.
When a search, knowledge, skill, or MCP tool returns a result list:
- If multiple search terms are needed, prefer calling the retrieval tools for all known terms in the same step, then answer after the tool results are returned.
- Treat every retrieval result from the same user turn as one combined `referenceBatch`; do not restart numbering for each search term, tool call, skill, or display adapter.
- Use only the system-provided merged reference numbers in the final answer, formatted as `[1]`, `[2]`, `[1][3][5]`.
- Do not output `<skill-display .../>` in RAG/reference mode. The frontend renders configured cards, tables, lists, and citation details in the right reference panel.
- If no display adapter exists, the frontend defaults the right reference panel to numbered citations.
</rag_citation_mode>
"""
if rag_mode_enabled
else ""
)
# Format the prompt with dynamic skills and memory
prompt = SYSTEM_PROMPT_TEMPLATE.format(
@@ -956,4 +1026,46 @@ Writing mode is enabled for this run.
acp_section=acp_and_mounts_section,
)
return prompt + f"\n<current_date>{datetime.now().strftime('%Y-%m-%d, %A')}</current_date>"
prompt = prompt + rag_mode_section + f"\n<current_date>{datetime.now().strftime('%Y-%m-%d, %A')}</current_date>"
if is_notebook_mode:
source_ids = notebook_source_ids or []
if source_ids:
source_line = f"当前检索范围:{len(source_ids)} 个来源(IDs: {', '.join(str(i) for i in source_ids)})"
else:
source_line = "当前检索范围:全部来源"
prompt += f"""
<notebook_mode>
## 角色
你是一个笔记本 AI 助手,**只能**基于笔记本文档来源回答用户问题,禁止使用任何其他知识。
## 可用知识来源
{source_line}
## 强制工作流程(每次用户提问都必须严格执行,无例外)
1. **第一步(必须)**:立即调用 `search_notebook_sources` 工具,`query` 填写用户问题或精炼的检索关键词。
- 无论问题多简单,都必须先检索,不得跳过。
- 若检索结果不足,可再次调用不同 query 补充检索。
2. **第二步**:仅基于检索到的内容组织回答,**不得使用训练知识或推断**。
3. **第三步**:若检索结果中确实无相关内容,明确告知用户"暂未在来源中找到相关信息"。
## 引用格式(强制)
- 每个事实/句子后立即插入 `[[cite:<chunk_id>]]` 标记,chunk_id 来自检索结果中每个文本块的 id 字段。
- 多个来源支持同一句话时连续插入:`[[cite:101]][[cite:102]]`
- 引用标记紧跟被引用内容末尾,不加空格,不单独成行。
## 示例
用户:合同中违约金是多少?
(调用 search_notebook_sources query="违约金",返回 chunk_id=101 的结果)
回答:根据合同第五条,违约金为合同总额的 0.5%[[cite:101]],乙方拒绝收货视为违约[[cite:101]]。
## 绝对禁止
- 未调用 `search_notebook_sources` 就直接回答
- 引用不在检索结果中的 chunk_id
- 省略引用标记
- 使用笔记本来源之外的知识
</notebook_mode>"""
return prompt