实现RAG参考文献显示模式

This commit is contained in:
吉鑫升 committed 2026-05-27 17:40:10 +08:00
1 parent eda0ccffdb
commit c56db15a03
22 files changed
+1733 -192

No files matched your search

@@ -100,7 +100,14 @@ _DEFAULT_ASSISTANT_ID = "lead_agent"
# Built-in LangGraph graph IDs registered in langgraph.json.
# These are NOT stored in the agents DB and must bypass the custom-agent access check.
_BUILTIN_GRAPH_IDS: frozenset[str] = frozenset({"lead_agent", "canvas_agent", "ai_writing"})
_BUILTIN_GRAPH_IDS: frozenset[str] = frozenset({"lead_agent", "canvas_agent", "ai_writing"})
_RAG_CITATION_PROMPT = """当前对话已开启参考文献模式。
如果本轮调用了搜索、知识库、检索类技能或工具,请基于本轮所有检索结果整体回答。
你必须把同一轮内多次检索得到的资料视为同一批参考文献,按出现顺序从 [1] 开始连续编号,不要让每个检索词各自从 [1] 重新编号。
回答正文中的关键结论必须标注对应编号,例如 [1]、[2],多个来源可写为 [1][3][5]。
不要引用不存在的编号,不要使用技能内部自带的编号,不要把参考文献完整列表堆在正文末尾。
如果没有任何可用检索结果,请直接说明未检索到可靠参考资料。"""
def _prepend_prompt_prefix(graph_input: dict[str, Any], prefix: str) -> dict[str, Any]:
@@ -129,7 +136,7 @@ def _prepend_prompt_prefix(graph_input: dict[str, Any], prefix: str) -> dict[str
return {**graph_input, "messages": new_messages}
def _prompt_prefix_opted_in(body: Any) -> bool:
def _prompt_prefix_opted_in(body: Any) -> bool:
"""Detect whether the caller asked for the prompt prefix to be applied."""
context = getattr(body, "context", None)
if isinstance(context, Mapping) and context.get("prompt_prefix_enabled"):
@@ -137,7 +144,44 @@ def _prompt_prefix_opted_in(body: Any) -> bool:
metadata = getattr(body, "metadata", None)
if isinstance(metadata, Mapping) and metadata.get("prompt_prefix_enabled"):
return True
return False
return False
def _rag_mode_requested(body: Any) -> bool:
context = getattr(body, "context", None)
if isinstance(context, Mapping) and context.get("rag_mode_enabled"):
return True
metadata = getattr(body, "metadata", None)
if isinstance(metadata, Mapping) and (
metadata.get("rag_mode_enabled") or metadata.get("rag_mode")
):
return True
return False
def _thread_rag_mode_enabled(record: Any) -> bool:
if not isinstance(record, Mapping):
return False
metadata = record.get("metadata")
return isinstance(metadata, Mapping) and bool(
metadata.get("rag_mode_enabled") or metadata.get("rag_mode")
)
def _append_invisible_prompt(graph_input: dict[str, Any], prompt: str) -> dict[str, Any]:
messages = graph_input.get("messages")
if not isinstance(messages, list) or not messages:
return graph_input
new_messages = list(messages)
for idx, msg in enumerate(new_messages):
if not isinstance(msg, HumanMessage):
continue
extra = dict(getattr(msg, "additional_kwargs", None) or {})
existing = str(extra.get("prompt_prefix") or "").strip()
extra["prompt_prefix"] = f"{existing}\n\n{prompt}".strip() if existing else prompt
new_messages[idx] = msg.model_copy(update={"additional_kwargs": extra})
break
return {**graph_input, "messages": new_messages}
# Whitelist of run-context keys that the langgraph-compat layer forwards from
@@ -399,16 +443,29 @@ async def start_run(
# Upsert thread metadata so the thread appears in /threads/search,
# even for threads that were never explicitly created via POST /threads
# (e.g. stateless runs).
try:
existing = await run_ctx.thread_store.get(thread_id)
if existing is None:
await run_ctx.thread_store.create(
thread_id,
assistant_id=body.assistant_id,
metadata=body.metadata,
)
else:
await run_ctx.thread_store.update_status(thread_id, "running")
requested_rag_mode = _rag_mode_requested(body)
effective_rag_mode = requested_rag_mode
try:
existing = await run_ctx.thread_store.get(thread_id)
effective_rag_mode = requested_rag_mode or _thread_rag_mode_enabled(existing)
if existing is None:
metadata = dict(body.metadata or {})
if effective_rag_mode:
metadata["rag_mode_enabled"] = True
metadata["rag_mode"] = True
await run_ctx.thread_store.create(
thread_id,
assistant_id=body.assistant_id,
metadata=metadata,
)
else:
await run_ctx.thread_store.update_status(thread_id, "running")
if requested_rag_mode and not _thread_rag_mode_enabled(existing):
await run_ctx.thread_store.update_metadata(
thread_id,
{"rag_mode_enabled": True, "rag_mode": True},
)
effective_rag_mode = True
# SDK 的 ``client.threads.create()`` 不传 assistant_id —— 先建出来空的 thread,
# 真正提交 run 时才知道用哪个 assistant。这里回填一次,避免历史列表 / 按
# assistant 筛选时拿不到关联。
@@ -428,17 +485,21 @@ async def start_run(
# applies once. We intentionally do NOT gate on thread-row existence: the
# thread_meta row is frequently pre-created, which previously skipped the
# prefix for genuine first turns.
if _prompt_prefix_opted_in(body):
prefix_settings = load_system_settings().prompt_prefix
if prefix_settings.enabled and prefix_settings.prompt_prefix.strip():
graph_input = _prepend_prompt_prefix(graph_input, prefix_settings.prompt_prefix.strip())
config = build_run_config(thread_id, body.config, body.metadata, assistant_id=body.assistant_id)
if _prompt_prefix_opted_in(body):
prefix_settings = load_system_settings().prompt_prefix
if prefix_settings.enabled and prefix_settings.prompt_prefix.strip():
graph_input = _prepend_prompt_prefix(graph_input, prefix_settings.prompt_prefix.strip())
if effective_rag_mode:
graph_input = _append_invisible_prompt(graph_input, _RAG_CITATION_PROMPT)
config = build_run_config(thread_id, body.config, body.metadata, assistant_id=body.assistant_id)
# Merge DeerFlow-specific context overrides into both ``configurable`` and ``context``.
# The ``context`` field is a custom extension for the langgraph-compat layer
# that carries agent configuration (model_name, thinking_enabled, etc.).
# Only agent-relevant keys are forwarded; unknown keys (e.g. thread_id) are ignored.
body_context = dict(getattr(body, "context", None) or {})
body_context = dict(getattr(body, "context", None) or {})
if effective_rag_mode:
body_context["rag_mode_enabled"] = True
# Promote whitelisted top-level body fields into the context map so
# callers can pass them either nested under ``context`` or as flat
# top-level fields (``excluded_tools``, ``skill_stop_names``, …).