feat(open-chat): 新增 /api/open/chat 开放问答接口

- 无需登录(/api/open/ 加入 auth 白名单 + CSRF 豁免),供外部系统直接调用本项目智能体做问答
- 可指定模型(model_name)与智能体(agent_name 中文名称,扫描 agents/*/config.yaml 解析为运行 id);GET /api/open/agents 列出可选名称
- 只返回最终结果(answer = 最后一段 markdown),不含中间过程/工具调用
- 可靠关闭思考:thinking_enabled=false 时下发 thinking_force_disabled,经 create_chat_model(force_disable_thinking=True) 强制注入 enable_thinking=false(及 GLM thinking.type=disabled),覆盖只声明 supports_thinking 的内网 vLLM/Qwen 模型(与生成标题关思考一致)
- 一次性问答设 is_scheduled_run 跳过自动起标题

Co-Authored-By: Claude Opus 4.8 (1M context) <noreply@anthropic.com>
This commit is contained in:
吉鑫升andClaude Opus 4.8 committed 2026-06-22 11:21:56 +08:00
1 parent 593daa91ec
commit 2b6424b3ff
9 files changed
+337 -4

No files matched your search

@@ -412,6 +412,11 @@ 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 +506,7 @@ 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 +519,7 @@ 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 +598,7 @@ 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,
@@ -47,11 +47,22 @@ def _enable_stream_usage_by_default(model_use_path: str, model_settings_from_con
model_settings_from_config["stream_usage"] = True
def create_chat_model(name: str | None = None, thinking_enabled: bool = False, *, app_config: AppConfig | None = None, **kwargs) -> BaseChatModel:
def create_chat_model(name: str | None = None, thinking_enabled: bool = False, *, app_config: AppConfig | None = None, force_disable_thinking: bool = False, **kwargs) -> BaseChatModel:
"""Create a chat model instance from the config.
Args:
name: The name of the model to create. If None, the first model in the config will be used.
thinking_enabled: Turn the model's extended thinking / reasoning on.
force_disable_thinking: Hard override that disables thinking even when the
per-model config declares no ``when_thinking_*`` shape. Many internal
vLLM / Qwen models only set ``supports_thinking: true`` (no disable
shape), so passing ``thinking_enabled=False`` alone injects nothing and
the model keeps reasoning on. When this flag is set (and thinking is
off) we additionally inject both common OpenAI-compatible disable shapes
— vLLM/Qwen ``chat_template_kwargs.enable_thinking=False`` and Zhipu GLM
``thinking.type="disabled"`` — mirroring
``TitleMiddleware._force_disable_thinking``. No effect when thinking is
enabled, and skipped for model classes that don't accept ``extra_body``.
Returns:
A chat model instance.
@@ -120,6 +131,15 @@ def create_chat_model(name: str | None = None, thinking_enabled: bool = False, *
kwargs.pop("reasoning_effort", None)
model_settings_from_config.pop("reasoning_effort", None)
# Hard override: force-disable thinking regardless of the per-model config shape.
# Injected only for OpenAI-compatible classes (those declaring `extra_body`);
# other providers would reject the kwarg, so they are skipped (they ignore it).
if force_disable_thinking and not thinking_enabled and "extra_body" in getattr(model_class, "model_fields", {}):
model_settings_from_config["extra_body"] = _deep_merge_dicts(
model_settings_from_config.get("extra_body"),
{"chat_template_kwargs": {"enable_thinking": False}, "thinking": {"type": "disabled"}},
)
_enable_stream_usage_by_default(model_config.use, model_settings_from_config)
# For Codex Responses API models: map thinking mode to reasoning_effort