Merge branch 'ji' into master
合并 ji 的功能:开放问答接口(/api/open/chat[/stream] 回传生成文件 + 临时不留存)、 技能地址管理、智能体详情「最近对话」等。 冲突 frontend StrategyRoutes.tsx 已解决:同时保留 admin/roundtable-diagnostics(master) 与 admin/skill-addresses(ji) 两个管理员路由。 Co-Authored-By: Claude Opus 4.8 (1M context) <noreply@anthropic.com>
This commit is contained in:
commit
fbec222eb4
38 files changed
+3365
-94
No files matched your search
+20
-7
@@ -306,17 +306,25 @@ def _build_middlewares(
|
||||
if not cfg.get("is_scheduled_run", False):
|
||||
middlewares.append(TitleMiddleware(app_config=resolved_app_config))
|
||||
|
||||
# Add MemoryMiddleware (after TitleMiddleware) — skip in bootstrap mode (agent creation flow)
|
||||
# Ephemeral runs (e.g. the open Q&A API /api/open/chat) must NOT touch any
|
||||
# server-side per-user state: no memory recall/retain, no knowledge-base
|
||||
# recall/auto-ingest. Those runs use the shared "default" user bucket, so
|
||||
# persisting their conversations there would both store records the caller
|
||||
# explicitly asked NOT to keep and leak content across unrelated callers.
|
||||
# Skip both write-capable middlewares entirely.
|
||||
is_ephemeral = cfg.get("ephemeral", False)
|
||||
|
||||
# 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:
|
||||
if not is_bootstrap and not is_writing_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
|
||||
# per-conversation by the ``knowledge_rag_enabled`` runtime flag, defaulting
|
||||
# to the global ``knowledge.rag_enabled`` config. No-op when knowledge is
|
||||
# disabled. Skipped in bootstrap/writing-setup like MemoryMiddleware.
|
||||
# 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 knowledge_cfg is not None and knowledge_cfg.enabled:
|
||||
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))
|
||||
@@ -412,6 +420,11 @@ def _make_lead_agent(config: RunnableConfig, *, app_config: AppConfig):
|
||||
resolved_app_config = app_config
|
||||
|
||||
thinking_enabled = cfg.get("thinking_enabled", True)
|
||||
# Hard "thinking off" switch for internal vLLM/Qwen models whose config only
|
||||
# declares `supports_thinking: true` (no disable shape) — passes through to
|
||||
# create_chat_model(force_disable_thinking=...) so enable_thinking=false is
|
||||
# actually injected. Default off → no behavior change for normal chats.
|
||||
thinking_force_disabled = bool(cfg.get("thinking_force_disabled", False))
|
||||
reasoning_effort = cfg.get("reasoning_effort", None)
|
||||
requested_model_name: str | None = cfg.get("model_name") or cfg.get("model")
|
||||
is_plan_mode = cfg.get("is_plan_mode", False)
|
||||
@@ -501,7 +514,7 @@ def _make_lead_agent(config: RunnableConfig, *, app_config: AppConfig):
|
||||
from deerflow.agents.middlewares.writing_setup_round_cap_middleware import WritingSetupRoundCapMiddleware
|
||||
|
||||
return create_agent(
|
||||
model=create_chat_model(name=model_name, thinking_enabled=thinking_enabled, app_config=resolved_app_config),
|
||||
model=create_chat_model(name=model_name, thinking_enabled=thinking_enabled, force_disable_thinking=thinking_force_disabled, app_config=resolved_app_config),
|
||||
tools=[setup_writing, ask_clarification_tool],
|
||||
middleware=[
|
||||
*_build_middlewares(config, model_name=model_name, app_config=resolved_app_config),
|
||||
@@ -514,7 +527,7 @@ def _make_lead_agent(config: RunnableConfig, *, app_config: AppConfig):
|
||||
if is_bootstrap:
|
||||
# Special bootstrap agent with minimal prompt for initial custom agent creation flow
|
||||
return create_agent(
|
||||
model=create_chat_model(name=model_name, thinking_enabled=thinking_enabled, app_config=resolved_app_config),
|
||||
model=create_chat_model(name=model_name, thinking_enabled=thinking_enabled, force_disable_thinking=thinking_force_disabled, app_config=resolved_app_config),
|
||||
tools=get_available_tools(
|
||||
model_name=model_name,
|
||||
subagent_enabled=subagent_enabled,
|
||||
@@ -593,7 +606,7 @@ def _make_lead_agent(config: RunnableConfig, *, app_config: AppConfig):
|
||||
)
|
||||
|
||||
return create_agent(
|
||||
model=create_chat_model(name=model_name, thinking_enabled=thinking_enabled, reasoning_effort=reasoning_effort, app_config=resolved_app_config),
|
||||
model=create_chat_model(name=model_name, thinking_enabled=thinking_enabled, reasoning_effort=reasoning_effort, force_disable_thinking=thinking_force_disabled, 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=system_prompt,
|
||||
|
||||
Reference in new issue
Block a user