Your lightweight open-source personal agent.
Python agent-frameworkai-agentai-agentschatbotchatopsdiscord-botllm-agentsllmslocal-llmmcpmodel-context-protocolmulti-agentopenai-compatibleopenclawpersonal-ai-assistantpythonself-hostedtelegram-bot-ai-assistantwebuiworkflow-automation
fix(providers): remove obsolete DeepSeek hosted search
chengyongrud808dbdb443a
diff --git a/docs/configuration.md b/docs/configuration.mdindex c6f0615fa..42b7d3de9 100644--- a/docs/configuration.md+++ b/docs/configuration.md@@ -352,32 +352,6 @@ The WebUI's OpenAI web-search switch selects Responses without Chat fallback. Pr</details>-<details>-<summary><b>DeepSeek native web search</b></summary>--DeepSeek V4 Flash and Pro use DeepSeek's native Responses API. Their provider-hosted web search is-enabled by default because it does not require a separate paid add-on. Turn it off from the-WebUI provider settings, or with:--```json-{- "providers": {- "deepseek": {- "apiKey": "${DEEPSEEK_API_KEY}",- "extraBody": {- "tools": []- }- }- }-}-```--The switch applies to `deepseek-v4-flash` and `deepseek-v4-pro`; DeepSeek models that remain on-Chat Completions cannot use this Responses tool. Native search calls appear in the WebUI activity-stream, and their opaque output items are preserved for multi-turn Responses state replay.--</details>-<a id="responses-state-and-compaction"></a>### Responses conversation state and compaction@@ -1458,6 +1432,8 @@ In `config.json`, set `providers.<name>.api` for the built-in `custom` providerIf your configuration uses `providers.openai.apiType` (or `api_type`), save it with a version that supports the migration before upgrading further. Saving replaces the old field with `api`: `chat_completions` or `responses` becomes a single-API declaration, while `auto` keeps automatic selection. If both fields are present, `api` takes precedence, including `api: null`.+The migration also accepts the `NANOBOT_PROVIDERS__OPENAI__API_TYPE` and `NANOBOT_PROVIDERS__OPENAI__APITYPE` environment variables.+The old field is accepted in the first release containing this migration and the immediately following release. The third release will require the current `api` format.### Preset request APIdiff --git a/docs/providers.md b/docs/providers.mdindex 62ff6c20c..3d3e24ae3 100644--- a/docs/providers.md+++ b/docs/providers.md@@ -355,11 +355,11 @@ For a named custom provider serving Anthropic Messages, set `providers.<name>.apReplace the model with a model ID available to your account. Leave API selection on Auto unless you need to choose Chat Completions or Responses in the preset's **Advanced options**. See [preset API settings](./configuration.md#preset-request-api) for WebUI and JSON configuration. `providers.openai.api` sets the connection default; explicit presets override it. If your configuration still uses `apiType`, follow the [migration instructions](./configuration.md#legacy-openai-api-selector-migration).-Direct OpenAI Responses, OpenAI Codex, Azure OpenAI Responses, and eligible GitHub Copilot models can retain server-provided conversation state; [native context compaction](./configuration.md#responses-state-and-compaction) depends on provider support. The WebUI offers switches for OpenAI web search, Codex Fast mode, DeepSeek web search, and Grok X Search.+Direct OpenAI Responses, OpenAI Codex, Azure OpenAI Responses, and eligible GitHub Copilot models can retain server-provided conversation state; [native context compaction](./configuration.md#responses-state-and-compaction) depends on provider support. The WebUI offers switches for OpenAI web search, Codex Fast mode, and Grok X Search.-DeepSeek's `deepseek-v4-flash`, `deepseek-v4-pro`, and `deepseek-v4-flash-vision-exp` automatically use its native Responses API. Its native `web_search` tool is enabled by default and shows its lifecycle in WebUI chat activity; set `providers.deepseek.extraBody.tools` to `[]` to disable it. OpenCode Go's `muse-spark-1.2-contributor` and `muse-spark-1.3-contributor` also use Responses by default.+DeepSeek's `deepseek-v4-flash`, `deepseek-v4-pro`, and `deepseek-v4-flash-vision-exp` automatically use its native Responses API. For web search, use nanobot's [web search tool](./configuration.md#web-search). OpenCode Go's `muse-spark-1.2-contributor` and `muse-spark-1.3-contributor` also use Responses by default.-The `deepseek-flash` alias uses Responses automatically at `https://api.deepseek.com`, including the `/v1` form. With a different `providers.deepseek.apiBase`, Auto uses Chat Completions for this alias. Select Responses in the preset if the proxy supports it. The V4 model names listed above use Responses with either endpoint configuration. Explicitly enabling native web search for this alias also selects Responses.+The `deepseek-flash` alias uses Responses automatically at `https://api.deepseek.com`, including the `/v1` form. With a different `providers.deepseek.apiBase`, Auto uses Chat Completions for this alias. Select Responses in the preset if the proxy supports it. The V4 model names listed above use Responses with either endpoint configuration.### Custom OpenAI-Compatible Endpointdiff --git a/nanobot/config/provider_api_migration.py b/nanobot/config/provider_api_migration.pyindex e272a79dc..b5f50f06e 100644--- a/nanobot/config/provider_api_migration.py+++ b/nanobot/config/provider_api_migration.py@@ -11,11 +11,13 @@ def migrate_legacy_provider_api(values: dict[str, Any], *, provider_name: str,) -> dict[str, Any]:"""Consume old input keys; all callers receive the current API declaration."""- if "apiType" not in values and "api_type" not in values:+ if "apiType" not in values and "api_type" not in values and "apitype" not in values:return valuesmigrated = dict(values)- legacy = migrated.pop("apiType", migrated.get("api_type", "auto"))+ # Case-insensitive settings sources normalize the former apiType env alias.+ legacy = migrated.pop("apiType", migrated.get("api_type", migrated.get("apitype", "auto")))migrated.pop("api_type", None)+ migrated.pop("apitype", None)if "api" in migrated:return migratedif legacy not in ("auto", "chat_completions", "responses"):diff --git a/nanobot/providers/model_api.py b/nanobot/providers/model_api.pyindex 2736ac153..e4eb2ef5e 100644--- a/nanobot/providers/model_api.py+++ b/nanobot/providers/model_api.py@@ -44,15 +44,11 @@ def is_hosted_web_search_tool(tool: object) -> bool:return is_hosted_web_search_type(cast(dict[object, object], tool).get("type"))-def hosted_web_search_enabled(- extra_body: dict[str, Any], default_tools: tuple[str, ...] = (),-) -> bool:- if "tools" in extra_body:- tools = extra_body["tools"]- return isinstance(tools, list) and any(- is_hosted_web_search_tool(tool) for tool in cast(list[object], tools)- )- return any(is_hosted_web_search_type(value) for value in default_tools)+def hosted_web_search_enabled(extra_body: dict[str, Any]) -> bool:+ tools = extra_body.get("tools")+ return isinstance(tools, list) and any(+ is_hosted_web_search_tool(tool) for tool in cast(list[object], tools)+ )@dataclass(frozen=True)@@ -79,9 +75,20 @@ class ResponsesCapabilities:requires_direct_openai_base: bool = Falsereasoning_replay: Literal["none", "encrypted", "plaintext"] = "none"supports_native_compaction: bool = False+ supports_hosted_web_search: bool = Trueallows_chat_fallback: bool = Trueendpoint_models: tuple[tuple[str, tuple[str, ...]], ...] = ()+ def request_extra_body(self, extra_body: dict[str, Any] | None) -> dict[str, Any]:+ """Omit hosted search settings when the endpoint ignores that tool type."""+ body = dict(extra_body or {})+ tools = body.get("tools")+ if not self.supports_hosted_web_search and isinstance(tools, list):+ body["tools"] = [+ tool for tool in cast(list[object], tools) if not is_hosted_web_search_tool(tool)+ ]+ return body+def matches_model(self, model: str, *, api_base: str | None = None) -> bool:"""Match curated models, restricting endpoint defaults when a base is supplied."""model_name = model.lower()@@ -120,14 +127,12 @@ class ResponsesCapabilities:api_base: str | None = None,default_api_base: str = "",extra_body: dict[str, Any] | None = None,- default_tools: tuple[str, ...] = (),) -> ModelAPICapabilities:"""Apply endpoint, reasoning, and hosted-tool rules to automatic selection."""- body = extra_body or {}+ body = self.request_extra_body(extra_body)effective_base = api_base or default_api_base or None- # Explicit hosted tools require Responses; defaults follow the endpoint's model rules.search_model_base = None if hosted_web_search_enabled(body) else effective_base- if hosted_web_search_enabled(body, default_tools) and (+ if hosted_web_search_enabled(body) and (self.route_reasoning or self.matches_model(model, api_base=search_model_base)):return ModelAPICapabilities(("responses",), "responses")diff --git a/nanobot/providers/openai_compat_provider.py b/nanobot/providers/openai_compat_provider.pyindex 20f22d29d..0eebcb8e8 100644--- a/nanobot/providers/openai_compat_provider.py+++ b/nanobot/providers/openai_compat_provider.py@@ -502,7 +502,10 @@ class OpenAICompatProvider(LLMProvider):self.extra_headers = extra_headers or {}self._spec = specself._preset_model_api = model_api- self._extra_body = dict(extra_body or {})+ self._extra_body = (+ spec.responses.request_extra_body(extra_body)+ if spec and spec.responses is not None else dict(extra_body or {})+ )self._extra_query = extra_query or {}self._proxy = proxy or Noneself._responses = ResponsesBackend()@@ -1099,9 +1102,7 @@ class OpenAICompatProvider(LLMProvider):return "chat_completions" not in api.supported_apis or self._hosted_web_search_enabled()def _hosted_web_search_enabled(self) -> bool:- return hosted_web_search_enabled(- self._extra_body, self._spec.responses_default_tools if self._spec else (),- )+ return hosted_web_search_enabled(self._extra_body)def _responses_capabilities(self) -> ResponsesCapabilities | None:capabilities = self._spec.responses if self._spec is not None else None@@ -1276,12 +1277,6 @@ class OpenAICompatProvider(LLMProvider):body.setdefault("reasoning", {})["context"] = "all_turns"extra_body = getattr(self, "_extra_body", {})- default_tools = getattr(self._spec, "responses_default_tools", ())- if "tools" not in extra_body and default_tools:- body["tools"] = [- *cast(list[object], body.get("tools", [])),- *({"type": tool_type} for tool_type in default_tools),- ]if extra_body:body = _merge_responses_extra_body(body, extra_body)diff --git a/nanobot/providers/registry.py b/nanobot/providers/registry.pyindex 6cf125429..cd4a277e4 100644--- a/nanobot/providers/registry.py+++ b/nanobot/providers/registry.py@@ -130,10 +130,6 @@ class ProviderSpec:# Capabilities for providers/models served through the shared Responses path.responses: ResponsesCapabilities | None = None- # Provider-hosted Responses tools sent unless extraBody.tools explicitly- # supplies the hosted-tool selection. Values are raw Responses tool types.- responses_default_tools: tuple[str, ...] = ()-# When the model returns content as a list of {"type":"thinking",...} +# {"type":"text",...} blocks, extract the thinking text into# reasoning_content. Mistral's Magistral / reasoning-enabled responses use@@ -179,7 +175,7 @@ class ProviderSpec:return self.responses.default_model_api(self.request_model_name(model), reasoning_effort,api_base=api_base, default_api_base=self.default_api_base,- extra_body=extra_body, default_tools=self.responses_default_tools,+ extra_body=extra_body,)@property@@ -637,8 +633,8 @@ PROVIDERS: tuple[ProviderSpec, ...] = (),endpoint_models=(("https://api.deepseek.com", ("deepseek-flash",)),),reasoning_replay="plaintext",+ supports_hosted_web_search=False,),- responses_default_tools=("web_search",),),# Gemini: Google's OpenAI-compatible endpointProviderSpec(diff --git a/tests/providers/test_extra_body_config.py b/tests/providers/test_extra_body_config.pyindex 3ea952f99..4bc5e419d 100644--- a/tests/providers/test_extra_body_config.py+++ b/tests/providers/test_extra_body_config.py@@ -3,7 +3,8 @@from __future__ import annotationsfrom typing import Any-from unittest.mock import MagicMock++import pytestfrom nanobot.providers.openai_compat_provider import (OpenAICompatProvider,@@ -145,17 +146,11 @@ class TestBuildKwargsExtraBody:"""Config extra_body should merge with (and override) thinking params."""from nanobot.providers.registry import ProviderSpec- spec = MagicMock(spec=ProviderSpec)- spec.thinking_style = "deepseek"- spec.supports_prompt_caching = False- spec.strip_model_prefix = False- spec.model_overrides = []- spec.name = "custom"- spec.supports_max_completion_tokens = False- spec.env_key = None- spec.default_api_base = None- spec.is_local = True- spec.detect_by_base_keyword = None+ spec = ProviderSpec(+ name="custom", keywords=(), env_key="",+ request_apis=("chat_completions", "responses"),+ thinking_style="thinking_type", is_local=True,+ )provider = OpenAICompatProvider(api_key="test",@@ -171,6 +166,7 @@ class TestBuildKwargsExtraBody:body = kwargs.get("extra_body", {})# Config param should be presentassert body.get("custom_param") == "value"+ assert body["thinking"] == {"type": "enabled"}def test_nested_extra_body_does_not_clobber_siblings(self) -> None:"""Nested dict merge should preserve sibling keys."""@@ -314,39 +310,13 @@ class TestBuildResponsesBodyExtraBody:assert body["include"] == ["web_search_call.action.sources"]assert provider._should_use_responses_api(None, None) is True- def test_deepseek_default_search_replaces_the_local_search_function(self) -> None:- provider = OpenAICompatProvider(- api_key="test-key",- default_model="deepseek-v4-flash",- spec=find_by_name("deepseek"),- )-- body = provider._build_responses_body(- messages=_simple_messages(),- tools=[{- "type": "function",- "function": {- "name": "web_search",- "description": "Search with nanobot's configured backend",- "parameters": {"type": "object"},- },- }],- model=None,- max_tokens=100,- temperature=0.1,- reasoning_effort=None,- tool_choice=None,- )-- assert body["tools"] == [{"type": "web_search"}]- assert "include" not in body-- def test_explicit_empty_tools_disables_deepseek_default_search(self) -> None:+ @pytest.mark.parametrize("extra_body", [None, {"tools": []}, {"tools": [{"type": "web_search"}]}])+ def test_deepseek_preserves_the_local_search_function(self, extra_body) -> None:provider = OpenAICompatProvider(api_key="test-key",default_model="deepseek-v4-flash",spec=find_by_name("deepseek"),- extra_body={"tools": []},+ extra_body=extra_body,)body = provider._build_responses_body(diff --git a/tests/providers/test_litellm_kwargs.py b/tests/providers/test_litellm_kwargs.pyindex 6e1506008..00d93aa8a 100644--- a/tests/providers/test_litellm_kwargs.py+++ b/tests/providers/test_litellm_kwargs.py@@ -364,7 +364,7 @@ async def test_deepseek_v4_pro_uses_responses_api() -> None:call_kwargs = mock_responses.call_args.kwargsassert call_kwargs["model"] == "deepseek-v4-pro"assert call_kwargs["reasoning"] == {"effort": "none"}- assert call_kwargs["tools"] == [{"type": "web_search"}]+ assert "tools" not in call_kwargsassert "include" not in call_kwargsdiff --git a/tests/providers/test_model_api_presets.py b/tests/providers/test_model_api_presets.pyindex dd56fe8f0..e8438f961 100644--- a/tests/providers/test_model_api_presets.py+++ b/tests/providers/test_model_api_presets.py@@ -8,6 +8,7 @@ from anthropic import AsyncAnthropicfrom openai import AsyncOpenAIfrom pydantic import ValidationError+from nanobot.agent.tools.web import WebSearchToolfrom nanobot.config.schema import (Config,InlineFallbackConfig,@@ -178,12 +179,16 @@ async def test_deepseek_automatic_api_preserves_endpoint_routing(provider = bind_transport(make_provider(config), handler, api_base=api_base)invoke = provider.chat_stream if stream else provider.chat- result = await invoke([{"role": "user", "content": "hello"}])+ result = await invoke(+ [{"role": "user", "content": "hello"}], tools=[WebSearchTool().to_schema()],+ )assert result.content == "ok"assert [request.url.path for request in requests] == [expected_path]assert resolve_automatic_model_api(config, preset=config.resolve_preset()) == ("deepseek", api)body = json.loads(requests[0].content)- assert body.get("tools", []) == ([{"type": "web_search"}] if api == "responses" else [])+ search_tool = body["tools"][0]+ assert search_tool["type"] == "function"+ assert (search_tool if api == "responses" else search_tool["function"])["name"] == "web_search"@pytest.mark.parametrize("stream", [False, True])@@ -213,12 +218,15 @@ async def test_deepseek_proxy_accepts_explicit_responses_and_chat_fallback(invoke = provider.chat_stream if stream else provider.chatresult = await invoke([{"role": "user", "content": "hello"}])assert result.content == "ok"- expected_paths = ["/v1/responses"] if response_supported else ["/v1/responses", "/v1/chat/completions"]+ expected_paths = (+ ["/v1/chat/completions"] if api is None+ else ["/v1/responses"] if response_supported+ else ["/v1/responses", "/v1/chat/completions"]+ )assert [request.url.path for request in requests] == expected_paths- expected_tools = [{"type": "web_search"}] if response_supported else []- assert json.loads(requests[0].content).get("tools", []) == expected_tools+ assert json.loads(requests[0].content).get("tools", []) == []if api is None:- assert resolve_automatic_model_api(config, preset=preset) == ("deepseek", "responses")+ assert resolve_automatic_model_api(config, preset=preset) == ("deepseek", "chat_completions")@pytest.mark.parametrize("stream", [False, True])@@ -566,3 +574,32 @@ async def test_migrated_openai_default_routes_and_allows_model_override(bind_traoverride = bind_transport(make_provider(config, preset_name="override"), handler)assert (await override.chat([{"role": "user", "content": "hello"}])).content == "ok"assert requests[-1] == ("/v1/responses" if opposite == "responses" else "/v1/chat/completions")++[email protected]("env_field", ["API_TYPE", "APITYPE"])[email protected]("legacy,path", [+ ("auto", "/v1/chat/completions"),+ ("chat_completions", "/v1/chat/completions"),+ ("responses", "/v1/responses"),+])+async def test_legacy_openai_environment_selector_keeps_request_api(+ bind_transport, tmp_path, monkeypatch, env_field, legacy, path,+):+ from nanobot.config.loader import load_config++ monkeypatch.setenv(f"NANOBOT_PROVIDERS__OPENAI__{env_field}", legacy)+ config_path = tmp_path / "config.json"+ config_path.write_text(json.dumps({+ "providers": {"openai": {"apiKey": "fixture", "apiBase": "https://tenant.test/v1"}},+ "agents": {"defaults": {"model": "gpt-4o", "provider": "openai"}},+ }), encoding="utf-8")+ config = load_config(config_path)+ requests = []++ def handler(request):+ requests.append(request.url.path)+ return _answer(request)++ provider = bind_transport(make_provider(config), handler)+ assert (await provider.chat([{"role": "user", "content": "hello"}])).content == "ok"+ assert requests == [path]diff --git a/webui/src/components/settings/models/ProviderSettings.tsx b/webui/src/components/settings/models/ProviderSettings.tsxindex 66c04821d..36bd6ca03 100644--- a/webui/src/components/settings/models/ProviderSettings.tsx+++ b/webui/src/components/settings/models/ProviderSettings.tsx@@ -106,15 +106,6 @@ const PROVIDER_REQUEST_OPTIONS: Partial<Record<string, ProviderRequestOption[]>>toolType: "web_search",forceResponses: true,}],- deepseek: [{- kind: "hosted_tool",- titleKey: "settings.providers.capabilityDeepSeekSearch",- title: "DeepSeek web search",- helpKey: "settings.providers.capabilityDeepSeekSearchHelp",- help: "Let DeepSeek V4 Flash search the web through its Responses API. Search activity appears in chat.",- toolType: "web_search",- defaultEnabled: true,- }],xai_grok: [{kind: "hosted_tool",titleKey: "settings.providers.capabilityXSearch",diff --git a/webui/src/i18n/locales/en/common.json b/webui/src/i18n/locales/en/common.jsonindex 78614c459..7758b06d2 100644--- a/webui/src/i18n/locales/en/common.json+++ b/webui/src/i18n/locales/en/common.json@@ -1212,8 +1212,6 @@"extraQuery": "Query parameters","capabilityFastMode": "Fast mode","capabilityFastModeHelp": "Faster replies use credits faster.\n\nUse OpenAI's priority service tier for faster responses. This consumes credits faster.",- "capabilityDeepSeekSearch": "DeepSeek web search",- "capabilityDeepSeekSearchHelp": "Supported DeepSeek models can search the web.\n\nLet DeepSeek V4 Flash search the web through its Responses API. Search activity appears in chat.","capabilityXSearch": "X Search","capabilityXSearchHelp": "Supported Grok models can search X.\n\nAllow supported Grok models to use xAI-hosted X Search. Search activity appears in chat.","capabilityOpenAISearch": "OpenAI web search",diff --git a/webui/src/i18n/locales/es/common.json b/webui/src/i18n/locales/es/common.jsonindex be222b03b..aebe17991 100644--- a/webui/src/i18n/locales/es/common.json+++ b/webui/src/i18n/locales/es/common.json@@ -789,8 +789,6 @@"extraQuery": "Parámetros de consulta","capabilityFastMode": "Modo rápido","capabilityFastModeHelp": "Las respuestas más rápidas consumen créditos más rápido.\n\nUsa el nivel de servicio prioritario de OpenAI para responder más rápido. Esto consume créditos más deprisa.",- "capabilityDeepSeekSearch": "Búsqueda web de DeepSeek",- "capabilityDeepSeekSearchHelp": "Los modelos DeepSeek compatibles pueden buscar en la web.\n\nPermite que DeepSeek V4 Flash busque en la web mediante Responses API. La actividad de búsqueda aparece en el chat.","capabilityXSearch": "Búsqueda en X","capabilityXSearchHelp": "Los modelos Grok compatibles pueden buscar en X.\n\nPermite que los modelos Grok compatibles usen X Search alojado por xAI. La actividad de búsqueda aparece en el chat.","capabilityOpenAISearch": "Búsqueda web de OpenAI",diff --git a/webui/src/i18n/locales/fr/common.json b/webui/src/i18n/locales/fr/common.jsonindex 6f2e7583b..e0ef61d70 100644--- a/webui/src/i18n/locales/fr/common.json+++ b/webui/src/i18n/locales/fr/common.json@@ -789,8 +789,6 @@"extraQuery": "Paramètres de requête","capabilityFastMode": "Mode rapide","capabilityFastModeHelp": "Des réponses plus rapides consomment les crédits plus vite.\n\nUtilise le niveau de service prioritaire d’OpenAI pour accélérer les réponses. Les crédits sont consommés plus rapidement.",- "capabilityDeepSeekSearch": "Recherche web DeepSeek",- "capabilityDeepSeekSearchHelp": "Les modèles DeepSeek compatibles peuvent rechercher sur le web.\n\nPermet à DeepSeek V4 Flash de rechercher sur le web via l’API Responses. L’activité de recherche apparaît dans le chat.","capabilityXSearch": "Recherche sur X","capabilityXSearchHelp": "Les modèles Grok compatibles peuvent rechercher sur X.\n\nPermet aux modèles Grok compatibles d’utiliser X Search hébergé par xAI. L’activité de recherche apparaît dans le chat.","capabilityOpenAISearch": "Recherche web OpenAI",diff --git a/webui/src/i18n/locales/id/common.json b/webui/src/i18n/locales/id/common.jsonindex 8a617c516..c8123762d 100644--- a/webui/src/i18n/locales/id/common.json+++ b/webui/src/i18n/locales/id/common.json@@ -789,8 +789,6 @@"extraQuery": "Parameter kueri","capabilityFastMode": "Mode cepat","capabilityFastModeHelp": "Balasan lebih cepat menghabiskan kredit lebih cepat.\n\nGunakan tingkat layanan prioritas OpenAI agar respons lebih cepat. Kredit akan terpakai lebih cepat.",- "capabilityDeepSeekSearch": "Pencarian web DeepSeek",- "capabilityDeepSeekSearchHelp": "Model DeepSeek yang didukung dapat mencari di web.\n\nIzinkan DeepSeek V4 Flash mencari di web melalui Responses API. Aktivitas pencarian ditampilkan di chat.","capabilityXSearch": "Pencarian X","capabilityXSearchHelp": "Model Grok yang didukung dapat mencari di X.\n\nIzinkan model Grok yang didukung menggunakan X Search yang dihosting xAI. Aktivitas pencarian ditampilkan di chat.","capabilityOpenAISearch": "Pencarian web OpenAI",diff --git a/webui/src/i18n/locales/ja/common.json b/webui/src/i18n/locales/ja/common.jsonindex 6e26c2803..60d92d54e 100644--- a/webui/src/i18n/locales/ja/common.json+++ b/webui/src/i18n/locales/ja/common.json@@ -789,8 +789,6 @@"extraQuery": "クエリパラメーター","capabilityFastMode": "高速モード","capabilityFastModeHelp": "応答が速くなり、クレジットの消費も速くなります。\n\nOpenAI の優先サービス階層を使用して応答を高速化します。クレジットの消費も速くなります。",- "capabilityDeepSeekSearch": "DeepSeek ウェブ検索",- "capabilityDeepSeekSearchHelp": "対応する DeepSeek モデルがウェブ検索を使えます。\n\nDeepSeek V4 Flash が Responses API 経由でウェブを検索できるようにします。検索状況はチャットに表示されます。","capabilityXSearch": "X 検索","capabilityXSearchHelp": "対応する Grok モデルが X を検索できます。\n\n対応する Grok モデルが xAI ホストの X Search を使用できるようにします。検索状況はチャットに表示されます。","capabilityOpenAISearch": "OpenAI ウェブ検索",diff --git a/webui/src/i18n/locales/ko/common.json b/webui/src/i18n/locales/ko/common.jsonindex ef4e20084..07a5a168a 100644--- a/webui/src/i18n/locales/ko/common.json+++ b/webui/src/i18n/locales/ko/common.json@@ -789,8 +789,6 @@"extraQuery": "쿼리 매개변수","capabilityFastMode": "고속 모드","capabilityFastModeHelp": "더 빠른 답변은 크레딧도 더 빨리 소모합니다.\n\nOpenAI 우선 서비스 등급을 사용해 더 빠르게 응답합니다. 크레딧도 더 빠르게 소모됩니다.",- "capabilityDeepSeekSearch": "DeepSeek 웹 검색",- "capabilityDeepSeekSearchHelp": "지원되는 DeepSeek 모델은 웹을 검색할 수 있습니다.\n\nDeepSeek V4 Flash가 Responses API를 통해 웹을 검색하도록 허용합니다. 검색 활동은 채팅에 표시됩니다.","capabilityXSearch": "X 검색","capabilityXSearchHelp": "지원되는 Grok 모델은 X를 검색할 수 있습니다.\n\n지원되는 Grok 모델이 xAI 호스팅 X Search를 사용하도록 허용합니다. 검색 활동은 채팅에 표시됩니다.","capabilityOpenAISearch": "OpenAI 웹 검색",diff --git a/webui/src/i18n/locales/pt-BR/common.json b/webui/src/i18n/locales/pt-BR/common.jsonindex edb76040d..d1a117a92 100644--- a/webui/src/i18n/locales/pt-BR/common.json+++ b/webui/src/i18n/locales/pt-BR/common.json@@ -1026,8 +1026,6 @@"extraQuery": "Parâmetros de consulta","capabilityFastMode": "Modo rápido","capabilityFastModeHelp": "Respostas mais rápidas consomem créditos mais rápido.\n\nUsa o nível de serviço prioritário da OpenAI para respostas mais rápidas. Isso consome créditos mais rapidamente.",- "capabilityDeepSeekSearch": "Pesquisa web do DeepSeek",- "capabilityDeepSeekSearchHelp": "Modelos DeepSeek compatíveis podem pesquisar na web.\n\nPermite que o DeepSeek V4 Flash pesquise na web pela Responses API. A atividade de pesquisa aparece no chat.","capabilityXSearch": "Pesquisa no X","capabilityXSearchHelp": "Modelos Grok compatíveis podem pesquisar no X.\n\nPermite que modelos Grok compatíveis usem o X Search hospedado pela xAI. A atividade de pesquisa aparece no chat.","capabilityOpenAISearch": "Pesquisa web da OpenAI",diff --git a/webui/src/i18n/locales/vi/common.json b/webui/src/i18n/locales/vi/common.jsonindex ccfa4f347..4d8369b88 100644--- a/webui/src/i18n/locales/vi/common.json+++ b/webui/src/i18n/locales/vi/common.json@@ -789,8 +789,6 @@"extraQuery": "Tham số truy vấn","capabilityFastMode": "Chế độ nhanh","capabilityFastModeHelp": "Trả lời nhanh hơn cũng tiêu hao hạn mức nhanh hơn.\n\nDùng tầng dịch vụ ưu tiên của OpenAI để phản hồi nhanh hơn. Tín dụng cũng sẽ được tiêu thụ nhanh hơn.",- "capabilityDeepSeekSearch": "Tìm kiếm web DeepSeek",- "capabilityDeepSeekSearchHelp": "Mô hình DeepSeek được hỗ trợ có thể tìm kiếm web.\n\nCho phép DeepSeek V4 Flash tìm kiếm trên web qua Responses API. Hoạt động tìm kiếm được hiển thị trong cuộc trò chuyện.","capabilityXSearch": "Tìm kiếm X","capabilityXSearchHelp": "Mô hình Grok được hỗ trợ có thể tìm kiếm X.\n\nCho phép các mô hình Grok được hỗ trợ dùng X Search do xAI lưu trữ. Hoạt động tìm kiếm được hiển thị trong cuộc trò chuyện.","capabilityOpenAISearch": "Tìm kiếm web OpenAI",diff --git a/webui/src/i18n/locales/zh-CN/common.json b/webui/src/i18n/locales/zh-CN/common.jsonindex 3780f6f56..206b6617c 100644--- a/webui/src/i18n/locales/zh-CN/common.json+++ b/webui/src/i18n/locales/zh-CN/common.json@@ -1212,8 +1212,6 @@"extraQuery": "查询参数","capabilityFastMode": "快速模式","capabilityFastModeHelp": "回复更快,额度消耗也更快\n\n通过 OpenAI 优先服务层获取更快响应,会更快消耗额度。",- "capabilityDeepSeekSearch": "DeepSeek 联网搜索",- "capabilityDeepSeekSearchHelp": "支持的 DeepSeek 模型可联网搜索\n\n允许 DeepSeek V4 Flash 通过 Responses API 搜索网络,并在对话中展示搜索过程。","capabilityXSearch": "X 搜索","capabilityXSearchHelp": "支持的 Grok 模型可搜索 X\n\n允许受支持的 Grok 模型使用 xAI 托管的 X Search,并在对话中展示搜索过程。","capabilityOpenAISearch": "OpenAI 联网搜索",diff --git a/webui/src/i18n/locales/zh-TW/common.json b/webui/src/i18n/locales/zh-TW/common.jsonindex 9daf84206..8791ffa51 100644--- a/webui/src/i18n/locales/zh-TW/common.json+++ b/webui/src/i18n/locales/zh-TW/common.json@@ -789,8 +789,6 @@"extraQuery": "查詢引數","capabilityFastMode": "快速模式","capabilityFastModeHelp": "回覆更快,額度消耗也更快\n\n透過 OpenAI 優先服務層獲取更快響應,會更快消耗額度。",- "capabilityDeepSeekSearch": "DeepSeek 網路搜尋",- "capabilityDeepSeekSearchHelp": "支援的 DeepSeek 模型可聯網搜尋\n\n允許 DeepSeek V4 Flash 透過 Responses API 搜尋網路,並在對話中展示搜尋過程。","capabilityXSearch": "X 搜尋","capabilityXSearchHelp": "支援的 Grok 模型可搜尋 X\n\n允許受支援的 Grok 模型使用 xAI 託管的 X Search,並在對話中展示搜尋過程。","capabilityOpenAISearch": "OpenAI 網路搜尋",diff --git a/webui/src/tests/settings-providers.test.tsx b/webui/src/tests/settings-providers.test.tsxindex 4c885ed0e..fcd1c5d45 100644--- a/webui/src/tests/settings-providers.test.tsx+++ b/webui/src/tests/settings-providers.test.tsx@@ -748,15 +748,8 @@ describe("Settings providers", () => {fireEvent.click(screen.getByRole("button", { name: "Close", exact: true }));fireEvent.click(screen.getByRole("button", { name: /^DeepSeek/ }));- expect(screen.getByText(/DeepSeek V4 Flash/)).toBeInTheDocument();- const deepSeekSearch = screen.getByRole("switch", { name: "DeepSeek web search" });- expect(deepSeekSearch).toHaveAttribute("aria-checked", "true");- fireEvent.click(deepSeekSearch);- fireEvent.click(screen.getByRole("button", { name: "Save provider" }));- await waitFor(() => expect(- screen.getByRole("button", { name: "DeepSeek", exact: true }),- ).toBeVisible());-+ expect(screen.queryByRole("switch")).not.toBeInTheDocument();+ fireEvent.click(screen.getByRole("button", { name: "Close", exact: true }));fireEvent.click(screen.getByRole("button", { name: "OpenAI", exact: true }));fireEvent.click(screen.getByRole("switch", { name: "OpenAI web search" }));fireEvent.click(screen.getByRole("button", { name: "Save provider" }));@@ -781,7 +774,6 @@ describe("Settings providers", () => {expect(requestUpdates).toEqual([["xai_grok", { extraBody: { tools: [] } }],["openai_codex", { extraBody: { service_tier: "priority" } }],- ["deepseek", { extraBody: { tools: [] } }],["openai", {api: { supported_apis: ["responses"], preferred_api: "responses" },extraBody: { tools: [{ type: "web_search" }] },