feat(web): add Qwen native search adapter (rescue of #5684)

CHANGELOG.md

@@ -9,6 +9,9 @@ and this project adheres to [Semantic Versioning](https://semver.org/spec/v2.0.0
 
 ### Added
 
+- Add provider-native web search for documented Qwen models on ModelStudio
+  Token Plan's Responses Harness, without enabling Coding Plan or Anthropic
+  routes.
 - Add provider-native web search for documented DeepSeek V4 routes through the
   Responses API, with fail-closed capability gating for compatible custom
   endpoints.

crates/config/src/route/capabilities.rs

@@ -50,6 +50,7 @@ impl CapabilityState {
 /// - OpenAI Responses web search: <https://developers.openai.com/api/docs/guides/tools-web-search>
 /// - Anthropic web search tool: <https://platform.claude.com/docs/en/agents-and-tools/tool-use/web-search-tool>
 /// - xAI web search tool: <https://docs.x.ai/developers/tools/web-search>
+/// - Alibaba Model Studio Token Plan Harness tools: <https://help.aliyun.com/en/model-studio/token-plan-harness-tool>
 /// - DeepSeek Responses web search: <https://api-docs.deepseek.com/api/create-response/>
 #[must_use]
 pub(crate) fn documented_server_side_web_search(
@@ -75,6 +76,10 @@ pub(crate) fn documented_server_side_web_search(
                 | "claude-sonnet-4-6"
         ),
         "xai" => matches!(wire_model_id.as_str(), "grok-4.6" | "grok-4.5"),
+        "modelstudio-token-plan" => matches!(
+            wire_model_id.as_str(),
+            "qwen3.8-max" | "qwen3.7-plus" | "qwen3.7-max"
+        ),
         "deepseek" => matches!(
             wire_model_id.as_str(),
             "deepseek-v4-flash" | "deepseek-v4-pro" | "deepseek-v4-flash-vision-exp"
@@ -164,6 +169,10 @@ mod tests {
             documented_server_side_web_search("anthropic", "claude-sonnet-4-6"),
             CapabilityState::Supported
         );
+        assert_eq!(
+            documented_server_side_web_search("modelstudio-token-plan", "qwen3.8-max"),
+            CapabilityState::Supported
+        );
         assert_eq!(
             documented_server_side_web_search("deepseek", "deepseek-v4-flash"),
             CapabilityState::Supported
@@ -177,6 +186,8 @@ mod tests {
             ("xai", "grok-4.6-latest"),
             ("xai", "grok-4.5-fast"),
             ("anthropic", "claude-haiku-4-5"),
+            ("modelstudio-coding-plan", "qwen3.8-max"),
+            ("modelstudio-token-plan", "qwen3.8-max-preview"),
             ("deepseek", "deepseek-v4-flash-preview"),
         ] {
             assert_eq!(

crates/config/src/route/offering.rs

@@ -310,6 +310,10 @@ pub fn bundled_offerings() -> Vec<ProviderModelOffering> {
             structured_output: CapabilityState::Supported,
             streaming: CapabilityState::Supported,
             image_input,
+            server_side_web_search: super::documented_server_side_web_search(
+                "modelstudio-token-plan",
+                model,
+            ),
             ..RouteCapabilities::default()
         }
     }

crates/config/src/route/tests.rs

@@ -1433,6 +1433,55 @@ fn provider_native_web_search_requires_exact_direct_endpoint_offering() {
     );
 }
 
+#[test]
+fn qwen_native_search_is_exact_to_token_plan_responses_routes() {
+    use crate::route::CapabilityState;
+
+    let resolver = RouteResolver::new();
+    let direct = resolver
+        .resolve(&req(
+            Some(ProviderKind::ModelstudioTokenPlan),
+            Some("qwen3.8-max"),
+        ))
+        .expect("Token Plan Qwen route resolves");
+    assert_eq!(
+        direct.capabilities().server_side_web_search,
+        CapabilityState::Supported
+    );
+
+    let preview = resolver
+        .resolve(&req(
+            Some(ProviderKind::ModelstudioTokenPlan),
+            Some("qwen3.8-max-preview"),
+        ))
+        .expect("neighboring preview route resolves");
+    assert_eq!(
+        preview.capabilities().server_side_web_search,
+        CapabilityState::Unknown
+    );
+
+    for base_url in [
+        "https://coding-intl.dashscope.aliyuncs.com/v1",
+        "https://token-plan.ap-southeast-1.maas.aliyuncs.com/apps/anthropic",
+        "https://compatible.example.test/v1",
+    ] {
+        let alternate = resolver
+            .resolve(&RouteRequest {
+                explicit_provider: Some(ProviderKind::ModelstudioTokenPlan),
+                model_selector: Some(LogicalModelRef::from("qwen3.8-max")),
+                saved_provider_model: None,
+                base_url_override: Some(base_url.to_string()),
+                limit_overrides: Vec::new(),
+            })
+            .expect("alternate product route resolves");
+        assert_eq!(
+            alternate.capabilities().server_side_web_search,
+            CapabilityState::Unknown,
+            "{base_url} must not inherit Token Plan Responses search"
+        );
+    }
+}
+
 #[test]
 fn priced_offering_yields_token_pricing_sku() {
     use super::candidate::PricingSku;

crates/tui/CHANGELOG.md

@@ -9,6 +9,9 @@ and this project adheres to [Semantic Versioning](https://semver.org/spec/v2.0.0
 
 ### Added
 
+- Add provider-native web search for documented Qwen models on ModelStudio
+  Token Plan's Responses Harness, without enabling Coding Plan or Anthropic
+  routes.
 - Add provider-native web search for documented DeepSeek V4 routes through the
   Responses API, with fail-closed capability gating for compatible custom
   endpoints.

crates/tui/src/client/provider_native_search.rs

@@ -48,6 +48,7 @@ impl ProviderNativeSearchClient {
             ApiProvider::Openai
                 | ApiProvider::Anthropic
                 | ApiProvider::Xai
+                | ApiProvider::ModelstudioTokenPlan
                 | ApiProvider::Deepseek
                 | ApiProvider::DeepseekCN
         )
@@ -117,6 +118,11 @@ impl ProviderNativeSearchClient {
                 request,
                 ResponsesSearchDialect::Xai,
             ),
+            ApiProvider::ModelstudioTokenPlan => build_responses_search_body(
+                &self.inner.default_model,
+                request,
+                ResponsesSearchDialect::ModelStudio,
+            ),
             ApiProvider::Deepseek | ApiProvider::DeepseekCN => build_responses_search_body(
                 &self.inner.default_model,
                 request,
@@ -135,7 +141,9 @@ impl ProviderNativeSearchClient {
             _ => bail!("active provider has no native web-search adapter"),
         };
         let url = match self.inner.api_provider {
-            ApiProvider::Openai | ApiProvider::Xai => api_url(&self.inner.base_url, "responses"),
+            ApiProvider::Openai | ApiProvider::Xai | ApiProvider::ModelstudioTokenPlan => {
+                api_url(&self.inner.base_url, "responses")
+            }
             ApiProvider::Deepseek | ApiProvider::DeepseekCN => {
                 responses_api_url(&self.inner.base_url, self.inner.api_provider)
             }
@@ -162,6 +170,7 @@ impl ProviderNativeSearchClient {
         let mut parsed = match self.inner.api_provider {
             ApiProvider::Openai
             | ApiProvider::Xai
+            | ApiProvider::ModelstudioTokenPlan
             | ApiProvider::Deepseek
             | ApiProvider::DeepseekCN => parse_responses_search(&payload),
             ApiProvider::Anthropic => parse_anthropic_search(&payload),
@@ -176,6 +185,7 @@ impl ProviderNativeSearchClient {
 enum ResponsesSearchDialect {
     Openai,
     Xai,
+    ModelStudio,
     Deepseek,
 }
 
@@ -215,6 +225,9 @@ fn build_responses_search_body(
         ResponsesSearchDialect::Xai => {
             body["tool_choice"] = json!("required");
         }
+        ResponsesSearchDialect::ModelStudio => {
+            body["tool_choice"] = json!("required");
+        }
         ResponsesSearchDialect::Deepseek => {
             body["tool_choice"] = json!({ "type": "web_search" });
         }
@@ -537,6 +550,20 @@ mod tests {
         assert_eq!(body["include"][0], "web_search_call.action.sources");
     }
 
+    #[test]
+    fn modelstudio_payload_uses_required_harness_search_without_filters() {
+        let body = build_responses_search_body(
+            "qwen3.8-max",
+            &request(),
+            ResponsesSearchDialect::ModelStudio,
+        );
+        assert_eq!(body["tools"][0]["type"], "web_search");
+        assert!(body["tools"][0].get("filters").is_none());
+        assert_eq!(body["tool_choice"], "required");
+        assert!(body.get("include").is_none());
+        assert!(body.get("store").is_none());
+    }
+
     #[test]
     fn deepseek_payload_uses_its_responses_search_contract() {
         let body = build_responses_search_body(
@@ -736,6 +763,52 @@ mod tests {
         assert_eq!(response.citations[0].url, "https://example.com/source");
     }
 
+    #[tokio::test]
+    async fn modelstudio_adapter_uses_token_plan_responses_contract() {
+        let server = MockServer::start().await;
+        Mock::given(method("POST"))
+            .and(path("/v1/responses"))
+            .and(header("authorization", "Bearer modelstudio-test-key"))
+            .and(body_partial_json(json!({
+                "model": "qwen3.8-max",
+                "tools": [{ "type": "web_search" }],
+                "tool_choice": "required"
+            })))
+            .respond_with(ResponseTemplate::new(200).set_body_json(json!({
+                "output": [{
+                    "type": "web_search_call",
+                    "action": {
+                        "sources": [{
+                            "url": "https://example.com/qwen",
+                            "title": "Qwen source"
+                        }]
+                    }
+                }]
+            })))
+            .expect(1)
+            .mount(&server)
+            .await;
+        let config = Config {
+            provider: Some("modelstudio-token-plan".to_string()),
+            providers: Some(ProvidersConfig {
+                modelstudio_token_plan: ProviderConfig {
+                    api_key: Some("modelstudio-test-key".to_string()),
+                    base_url: Some(format!("{}/v1", server.uri())),
+                    model: Some("qwen3.8-max".to_string()),
+                    ..ProviderConfig::default()
+                },
+                ..ProvidersConfig::default()
+            }),
+            ..Config::default()
+        };
+        let inner = DeepSeekClient::new(&config).expect("test ModelStudio client");
+        let client = ProviderNativeSearchClient::new(inner).expect("Qwen native adapter");
+
+        let response = client.search(&request()).await.expect("native search");
+
+        assert_eq!(response.citations.len(), 1);
+        assert_eq!(response.citations[0].url, "https://example.com/qwen");
+    }
     #[tokio::test]
     async fn deepseek_adapter_uses_authenticated_responses_endpoint() {
         let server = MockServer::start().await;

docs/PROVIDERS.md

@@ -605,7 +605,7 @@ overlay and lets DSH resolve its own keys.
 | `mistral` | `[providers.mistral]` | `MISTRAL_API_KEY` | `MISTRAL_BASE_URL`; default `https://api.mistral.ai/v1` | `mistral-code-latest` (default; `codestral-latest` accepted as alias), `mistral-medium-latest` (aliases: `mistral-medium-3-5`), `mistral-small-latest` (aliases: `mistral-small-2603`), `mistral-large-latest` | Mistral AI (la Plateforme) OpenAI-compatible Chat route. On the documented first-party HTTPS `/v1` hosts, Medium and Small send adjustable `reasoning_effort` (`none` or `high` only), parse Mistral's polymorphic thinking/text blocks, and replay stored thinking in that same wire shape. Deprecated native Magistral IDs remain explicit-configuration compatibility routes: they are always-reasoning and never receive the adjustable effort field. Code and Large are non-reasoning. A custom `MISTRAL_BASE_URL` keeps generic Chat semantics unless it is one of the documented first-party hosts. `MISTRAL_MODEL` is accepted. Provider aliases: `mistral-ai`, `mistralai`, `la-plateforme`. |
 | `edenai` | `[providers.edenai]` | `EDENAI_API_KEY` | `EDENAI_BASE_URL`; default `https://api.edenai.run/v3`; EU `https://api.eu.edenai.run/v3` | `deepseek/deepseek-v4-pro` (default); live `/models` catalog of `provider/model` ids | Eden AI OpenAI-compatible aggregation gateway. Catalog rows remain provider-scoped; generic reasoning controls are omitted because supported fields depend on the selected upstream family. `EDENAI_MODEL` is accepted. The default `deepseek/deepseek-v4-pro` is listed on the global catalog only; on the EU endpoint set `EDENAI_MODEL` (or `model`) to a row from the EU `/models` list, for example `qwen/deepseek-v4-pro`. Provider aliases: `eden-ai`, `eden_ai`. |
 | `xai` | `[providers.xai]` | `XAI_API_KEY`, Codewhale-owned device OAuth, or explicit read-only Grok CLI consent | `XAI_BASE_URL`; default `https://api.x.ai/v1` | `grok-4.6` (default), `grok-4.5`, `grok-4.3`, `grok-build`, `grok-composer-2.5-fast`, `grok-4.20-0309-reasoning`, `grok-4.20-0309-non-reasoning` | xAI/Grok OpenAI-compatible Chat Completions route. Grok 4.6 has a 500K context window, text/image input, function calls, structured output, server-side web search, and `low`/`medium`/`high`/`xhigh` reasoning (default `high`). Its standard rates double when the prompt reaches 200K tokens; the same 2x long-context rule applies to `grok-4.5` (500K context, $2.00 / $0.30 cached / $6.00) and `grok-4.3` (1M context, $1.25 / $0.20 cached / $2.50) per their [model pages](https://docs.x.ai/docs/models/grok-4.5). There is no documented `latest`/`fast` alias and no published numeric output limit. **API-key** (default): Bearer token from console.x.ai via `XAI_API_KEY` / keyring / `api_key`. **OAuth**: `codewhale auth xai-device` uses SSH-friendly device login and Codewhale-owned storage, which may refresh itself. Existing Grok CLI credentials require `codewhale auth external-consent --provider xai --mode read-only`; the granted external file is never refreshed or rewritten. OAuth may return HTTP 403 on some SuperGrok tiers — keep API-key as the reliable fallback. `XAI_MODEL` is accepted. Provider aliases: `x-ai`, `x_ai`, `grok`. |
-| `modelstudio-token-plan` | `[providers.modelstudio_token_plan]` | `MODELSTUDIO_API_KEY`, `DASHSCOPE_API_KEY` | `MODELSTUDIO_TOKEN_PLAN_BASE_URL`; default `https://token-plan.ap-southeast-1.maas.aliyuncs.com/compatible-mode/v1` | `qwen3.8-max` (default), `qwen3.8-max-preview`, `qwen3.7-plus`, `qwen3.7-max`, `qwen3.6-flash`, `deepseek-v4-pro`, `deepseek-v4-flash-0731`, `glm-5.2` | Alibaba Cloud Model Studio Token Plan OpenAI-compatible Chat Completions route. Token Plan Personal and Team share this endpoint. All listed models are reasoning-capable text/coding models. DeepSeek and GLM entries are provider-scoped and do not collide with first-party routes. `MODELSTUDIO_TOKEN_PLAN_MODEL` is accepted. Provider aliases: `modelstudio-token-plan`, `alibaba-token-plan`, `dashscope-token-plan`. |
+| `modelstudio-token-plan` | `[providers.modelstudio_token_plan]` | `MODELSTUDIO_API_KEY`, `DASHSCOPE_API_KEY` | `MODELSTUDIO_TOKEN_PLAN_BASE_URL`; default `https://token-plan.ap-southeast-1.maas.aliyuncs.com/compatible-mode/v1` | `qwen3.8-max` (default), `qwen3.8-max-preview`, `qwen3.7-plus`, `qwen3.7-max`, `qwen3.6-flash`, `deepseek-v4-pro`, `deepseek-v4-flash-0731`, `glm-5.2` | Alibaba Cloud Model Studio Token Plan OpenAI-compatible Chat Completions route. Token Plan Personal and Team share this endpoint. `qwen3.8-max`, `qwen3.7-plus`, and `qwen3.7-max` can use provider-native web search through the Token Plan Responses Harness; the preview, Coding Plan, and Anthropic routes do not inherit that capability. All listed models are reasoning-capable text/coding models. DeepSeek and GLM entries are provider-scoped and do not collide with first-party routes. `MODELSTUDIO_TOKEN_PLAN_MODEL` is accepted. Provider aliases: `modelstudio-token-plan`, `alibaba-token-plan`, `dashscope-token-plan`. |
 | `modelstudio-token-plan-anthropic` | `[providers.modelstudio_token_plan_anthropic]` | `MODELSTUDIO_API_KEY`, `DASHSCOPE_API_KEY` | default `https://token-plan.ap-southeast-1.maas.aliyuncs.com/apps/anthropic` | Same model catalog as `modelstudio-token-plan` | Token Plan Anthropic-compatible Messages route (`/apps/anthropic`). Same API key as the OpenAI dialect. Provider aliases: `modelstudio-token-plan-anthropic`, `alibaba-token-plan-anthropic`. |
 | `modelstudio-coding-plan` | `[providers.modelstudio_coding_plan]` | `MODELSTUDIO_API_KEY`, `DASHSCOPE_API_KEY` | `MODELSTUDIO_CODING_PLAN_BASE_URL`; default `https://coding-intl.dashscope.aliyuncs.com/v1` | `qwen3.8-max` (default); same catalog as Token Plan | Alibaba Cloud Model Studio Coding Plan OpenAI-compatible Chat Completions route. `MODELSTUDIO_CODING_PLAN_MODEL` is accepted. Provider aliases: `modelstudio-coding-plan`, `alibaba-coding-plan`, `dashscope-coding-plan`. |
 | `modelstudio-coding-plan-anthropic` | `[providers.modelstudio_coding_plan_anthropic]` | `MODELSTUDIO_API_KEY`, `DASHSCOPE_API_KEY` | default `https://coding-intl.dashscope.aliyuncs.com/apps/anthropic` | Same model catalog as `modelstudio-coding-plan` | Coding Plan Anthropic-compatible Messages route (`/apps/anthropic`). Provider aliases: `modelstudio-coding-plan-anthropic`, `alibaba-coding-plan-anthropic`. |