feat(search): harvest custom DuckDuckGo endpoint

CHANGELOG.md

@@ -41,6 +41,11 @@ and this project adheres to [Semantic Versioning](https://semver.org/spec/v2.0.0
   were previously unpriced: `mimo-v2.5-pro` / `xiaomi/mimo-v2.5-pro` reuse the
   DeepSeek V4-Pro rate table and `mimo-v2.5` / `xiaomi/mimo-v2.5` reuse the
   DeepSeek V4-Flash rates. Existing DeepSeek pricing is unchanged (#2731, #2750).
+- Added optional `[search].base_url` / `CODEWHALE_SEARCH_BASE_URL` support for
+  DuckDuckGo-compatible private search endpoints, while keeping
+  `DEEPSEEK_SEARCH_BASE_URL` as a legacy alias. Custom endpoints are gated by
+  their configured host, do not fall back to public Bing, and report the custom
+  host as the result source for diagnostics (#2436, #2510).
 
 ### Changed
 
@@ -154,8 +159,10 @@ and this project adheres to [Semantic Versioning](https://semver.org/spec/v2.0.0
 ### Community
 
 Thanks to **@sximelon** for reporting and fixing the saved-session resume
-footer hint (#2758, #2760), **@cyq1017** for the restore-listing implementation
-(#2513) and pending-input delivery-mode label work (#2532, #2054),
+footer hint (#2758, #2760), **@cyq1017** for the custom
+DuckDuckGo-compatible search endpoint, restore-listing implementation, and
+pending-input delivery-mode label work (#2510, #2513, #2532, #2054),
+**@Artenx** for the private-search endpoint report (#2436),
 **@wywsoor** for the broader macOS/iTerm rollback UX report (#2494),
 **@HUQIANTAO** for the `web_run` lock-splitting work (#2502), turn-metadata
 prefix-cache stability work (#2517), and project-context cache direction

config.example.toml

@@ -409,13 +409,16 @@ max_subagents = 10 # optional (1-20)
 #                            # baidu:      百度 AI Search via qianfan.baidubce.com，需 api_key
 #                            # volcengine: 火山引擎 Ark web_search (免费 2 万次/月), 需 api_key
 #                            #             也回退到 VOLCENGINE_API_KEY / VOLCENGINE_ARK_API_KEY / ARK_API_KEY 环境变量
+# base_url = "https://search.example/html/" # optional DuckDuckGo-compatible HTML endpoint
 # api_key = "YOUR_SEARCH_KEY" # required for tavily, bocha, and baidu; optional for metaso
 #                             # WARNING: treat config.toml like a secret file when
 #                             # storing API keys. Prefer env vars for local smoke tests.
 #
 # Env-var overrides:
 #   DEEPSEEK_SEARCH_PROVIDER → search.provider
 #   DEEPSEEK_SEARCH_API_KEY  → search.api_key
+#   CODEWHALE_SEARCH_BASE_URL → search.base_url
+#   DEEPSEEK_SEARCH_BASE_URL  → search.base_url (legacy alias)
 #   METASO_API_KEY           → metaso key fallback
 #   BAIDU_SEARCH_API_KEY     → baidu key fallback
 

crates/tui/CHANGELOG.md

@@ -41,6 +41,11 @@ and this project adheres to [Semantic Versioning](https://semver.org/spec/v2.0.0
   were previously unpriced: `mimo-v2.5-pro` / `xiaomi/mimo-v2.5-pro` reuse the
   DeepSeek V4-Pro rate table and `mimo-v2.5` / `xiaomi/mimo-v2.5` reuse the
   DeepSeek V4-Flash rates. Existing DeepSeek pricing is unchanged (#2731, #2750).
+- Added optional `[search].base_url` / `CODEWHALE_SEARCH_BASE_URL` support for
+  DuckDuckGo-compatible private search endpoints, while keeping
+  `DEEPSEEK_SEARCH_BASE_URL` as a legacy alias. Custom endpoints are gated by
+  their configured host, do not fall back to public Bing, and report the custom
+  host as the result source for diagnostics (#2436, #2510).
 
 ### Changed
 
@@ -154,8 +159,10 @@ and this project adheres to [Semantic Versioning](https://semver.org/spec/v2.0.0
 ### Community
 
 Thanks to **@sximelon** for reporting and fixing the saved-session resume
-footer hint (#2758, #2760), **@cyq1017** for the restore-listing implementation
-(#2513) and pending-input delivery-mode label work (#2532, #2054),
+footer hint (#2758, #2760), **@cyq1017** for the custom
+DuckDuckGo-compatible search endpoint, restore-listing implementation, and
+pending-input delivery-mode label work (#2510, #2513, #2532, #2054),
+**@Artenx** for the private-search endpoint report (#2436),
 **@wywsoor** for the broader macOS/iTerm rollback UX report (#2494),
 **@HUQIANTAO** for the `web_run` lock-splitting work (#2502), turn-metadata
 prefix-cache stability work (#2517), and project-context cache direction

crates/tui/src/config.rs

@@ -1116,6 +1116,11 @@ pub struct SearchConfig {
     /// Search provider: `bing` | `duckduckgo` | `tavily` | `bocha` | `metaso` | `baidu` | `volcengine`. Default: `duckduckgo`.
     #[serde(default)]
     pub provider: Option<SearchProvider>,
+    /// Optional DuckDuckGo-compatible HTML endpoint. When set with the
+    /// DuckDuckGo provider, `web_search` appends the `q` query parameter to
+    /// this URL instead of using `https://html.duckduckgo.com/html/`.
+    #[serde(default)]
+    pub base_url: Option<String>,
     /// API key for Tavily, Bocha, Metaso, Baidu, or Volcengine. Not required for Bing or DuckDuckGo.
     /// Metaso also falls back to `METASO_API_KEY` env var, then a built-in default.
     /// Baidu also falls back to `BAIDU_SEARCH_API_KEY` env var.
@@ -3803,6 +3808,12 @@ fn apply_env_overrides(config: &mut Config) {
             .get_or_insert_with(SearchConfig::default)
             .api_key = Some(value);
     }
+    if let Ok(value) = codewhale_env_var("CODEWHALE_SEARCH_BASE_URL", "DEEPSEEK_SEARCH_BASE_URL") {
+        config
+            .search
+            .get_or_insert_with(SearchConfig::default)
+            .base_url = Some(value);
+    }
     if let Ok(value) = std::env::var("DEEPSEEK_REQUIREMENTS_PATH") {
         config.requirements_path = Some(value);
     }
@@ -5524,6 +5535,25 @@ mod tests {
         );
     }
 
+    #[test]
+    fn search_config_preserves_custom_base_url() {
+        let config: Config = toml::from_str(
+            r#"
+            [search]
+            provider = "duckduckgo"
+            base_url = "https://search.internal.example/html/"
+            "#,
+        )
+        .expect("search config");
+
+        let search = config.search.expect("search table");
+        assert_eq!(search.provider, Some(SearchProvider::DuckDuckGo));
+        assert_eq!(
+            search.base_url.as_deref(),
+            Some("https://search.internal.example/html/")
+        );
+    }
+
     #[test]
     fn explicit_baidu_search_provider_is_preserved() {
         let config: Config = toml::from_str(
@@ -5667,6 +5697,61 @@ mod tests {
         );
     }
 
+    #[test]
+    fn apply_env_overrides_sets_search_base_url() {
+        let _guard = lock_test_env();
+        let prev_codewhale = env::var_os("CODEWHALE_SEARCH_BASE_URL");
+        let prev_deepseek = env::var_os("DEEPSEEK_SEARCH_BASE_URL");
+        unsafe {
+            env::remove_var("CODEWHALE_SEARCH_BASE_URL");
+            env::set_var(
+                "DEEPSEEK_SEARCH_BASE_URL",
+                "https://search.internal.example/html/",
+            )
+        };
+        let mut config = Config::default();
+
+        apply_env_overrides(&mut config);
+
+        unsafe {
+            EnvGuard::restore_var("CODEWHALE_SEARCH_BASE_URL", prev_codewhale);
+            EnvGuard::restore_var("DEEPSEEK_SEARCH_BASE_URL", prev_deepseek);
+        }
+        assert_eq!(
+            config.search.and_then(|search| search.base_url),
+            Some("https://search.internal.example/html/".to_string())
+        );
+    }
+
+    #[test]
+    fn codewhale_search_base_url_env_wins_over_legacy_alias() {
+        let _guard = lock_test_env();
+        let prev_codewhale = env::var_os("CODEWHALE_SEARCH_BASE_URL");
+        let prev_deepseek = env::var_os("DEEPSEEK_SEARCH_BASE_URL");
+        unsafe {
+            env::set_var(
+                "CODEWHALE_SEARCH_BASE_URL",
+                "https://codewhale-search.example/html/",
+            );
+            env::set_var(
+                "DEEPSEEK_SEARCH_BASE_URL",
+                "https://legacy-search.example/html/",
+            );
+        }
+        let mut config = Config::default();
+
+        apply_env_overrides(&mut config);
+
+        unsafe {
+            EnvGuard::restore_var("CODEWHALE_SEARCH_BASE_URL", prev_codewhale);
+            EnvGuard::restore_var("DEEPSEEK_SEARCH_BASE_URL", prev_deepseek);
+        }
+        assert_eq!(
+            config.search.and_then(|search| search.base_url),
+            Some("https://codewhale-search.example/html/".to_string())
+        );
+    }
+
     #[test]
     fn search_provider_resolution_ignores_invalid_env_override() {
         let _guard = lock_test_env();

crates/tui/src/core/engine.rs

@@ -344,6 +344,8 @@ pub struct EngineConfig {
     /// Metaso also falls back to `METASO_API_KEY` env var, then a built-in key.
     /// Baidu also falls back to `BAIDU_SEARCH_API_KEY`.
     pub search_api_key: Option<String>,
+    /// Optional DuckDuckGo-compatible HTML endpoint override.
+    pub search_base_url: Option<String>,
     /// Per-step DeepSeek API timeout for sub-agent `create_message` requests.
     /// Resolved from `[subagents] api_timeout_secs` (clamped to 1..=1800)
     /// once at engine construction, then threaded onto every
@@ -408,6 +410,7 @@ impl Default for EngineConfig {
             workshop: None,
             search_provider: crate::config::SearchProvider::default(),
             search_api_key: None,
+            search_base_url: None,
             subagent_api_timeout: Duration::from_secs(
                 crate::config::DEFAULT_SUBAGENT_API_TIMEOUT_SECS,
             ),
@@ -2251,6 +2254,7 @@ In {new} mode: {policy}\n\n\
         // Wire search provider config.
         ctx.search_provider = self.config.search_provider;
         ctx.search_api_key = self.config.search_api_key.clone();
+        ctx.search_base_url = self.config.search_base_url.clone();
 
         let policy = sandbox_policy_for_mode(mode, &self.session.workspace);
         let mut ctx = ctx.with_elevated_sandbox_policy(policy);

crates/tui/src/main.rs

@@ -5745,6 +5745,7 @@ async fn run_exec_agent(
         workshop: config.workshop.clone(),
         search_provider: config.search_provider(),
         search_api_key: config.search.as_ref().and_then(|s| s.api_key.clone()),
+        search_base_url: config.search.as_ref().and_then(|s| s.base_url.clone()),
         tools_always_load: config.tools_always_load(),
         tools: config.tools.clone(),
     };
@@ -6317,6 +6318,7 @@ mod doctor_endpoint_tests {
         let config = Config {
             search: Some(crate::config::SearchConfig {
                 provider: Some(crate::config::SearchProvider::DuckDuckGo),
+                base_url: None,
                 api_key: None,
             }),
             ..Default::default()
@@ -6356,6 +6358,7 @@ mod doctor_endpoint_tests {
         let config = Config {
             search: Some(crate::config::SearchConfig {
                 provider: Some(crate::config::SearchProvider::Bing),
+                base_url: None,
                 api_key: None,
             }),
             ..Default::default()

crates/tui/src/runtime_threads.rs

@@ -2083,6 +2083,7 @@ impl RuntimeThreadManager {
             workshop: self.config.workshop.clone(),
             search_provider: self.config.search_provider(),
             search_api_key: self.config.search.as_ref().and_then(|s| s.api_key.clone()),
+            search_base_url: self.config.search.as_ref().and_then(|s| s.base_url.clone()),
             tools_always_load: self.config.tools_always_load(),
             tools: self.config.tools.clone(),
         };

crates/tui/src/tools/spec.rs

@@ -169,6 +169,8 @@ pub struct ToolContext {
     /// Metaso also falls back to `METASO_API_KEY` env var, then a built-in key.
     /// Baidu also falls back to `BAIDU_SEARCH_API_KEY`.
     pub search_api_key: Option<String>,
+    /// Optional DuckDuckGo-compatible HTML endpoint override for `web_search`.
+    pub search_base_url: Option<String>,
 
     /// Per-session workshop variable store (#548). Holds the raw content of
     /// the most recent large-tool routing event so the parent can call
@@ -210,6 +212,7 @@ impl ToolContext {
             large_output_router: None,
             search_provider: crate::config::SearchProvider::default(),
             search_api_key: None,
+            search_base_url: None,
             workshop_vars: None,
         }
     }
@@ -247,6 +250,7 @@ impl ToolContext {
             large_output_router: None,
             search_provider: crate::config::SearchProvider::default(),
             search_api_key: None,
+            search_base_url: None,
             workshop_vars: None,
         }
     }
@@ -284,6 +288,7 @@ impl ToolContext {
             large_output_router: None,
             search_provider: crate::config::SearchProvider::default(),
             search_api_key: None,
+            search_base_url: None,
             workshop_vars: None,
         }
     }