Merge remote-tracking branch 'upstream/main' into worktree-api-timeout-retry-v2

# Conflicts:
#	rust/crates/runtime/src/config.rs
#	rust/crates/runtime/src/lib.rs

rust/crates/api/src/client.rs

@@ -161,7 +161,7 @@ mod tests {
 
     #[test]
     fn resolves_existing_and_grok_aliases() {
-        assert_eq!(resolve_model_alias("opus"), "claude-opus-4-6");
+        assert_eq!(resolve_model_alias("opus"), "claude-opus-4-7");
         assert_eq!(resolve_model_alias("grok"), "grok-3");
         assert_eq!(resolve_model_alias("grok-mini"), "grok-3-mini");
     }
@@ -235,4 +235,22 @@ mod tests {
             other => panic!("Expected ProviderClient::OpenAi for qwen-plus, got: {other:?}"),
         }
     }
+
+    #[test]
+    fn local_openai_base_url_routes_authless_ollama_models() {
+        let _lock = env_lock();
+        let _base_url = EnvVarGuard::set("OPENAI_BASE_URL", Some("http://127.0.0.1:11434/v1"));
+        let _openai_key = EnvVarGuard::set("OPENAI_API_KEY", None);
+        let _anthropic_key = EnvVarGuard::set("ANTHROPIC_API_KEY", Some("test-anthropic-key"));
+        let _anthropic_token = EnvVarGuard::set("ANTHROPIC_AUTH_TOKEN", None);
+
+        let client = ProviderClient::from_model("qwen2.5-coder:7b")
+            .expect("local model should route to OpenAI-compatible client without auth");
+        match client {
+            ProviderClient::OpenAi(openai_client) => {
+                assert_eq!(openai_client.base_url(), "http://127.0.0.1:11434/v1")
+            }
+            other => panic!("Expected ProviderClient::OpenAi for local model, got: {other:?}"),
+        }
+    }
 }

rust/crates/api/src/providers/anthropic.rs

@@ -487,8 +487,7 @@ impl AnthropicClient {
         request: &MessageRequest,
     ) -> Result<reqwest::Response, ApiError> {
         let request_url = format!("{}/v1/messages", self.base_url.trim_end_matches('/'));
-        let mut request_body = self.request_profile.render_json_body(request)?;
-        strip_unsupported_beta_body_fields(&mut request_body);
+        let request_body = render_standard_messages_body(&self.request_profile, request)?;
         let request_builder = self.build_request(&request_url).json(&request_body);
         request_builder.send().await.map_err(ApiError::from)
     }
@@ -548,8 +547,7 @@ impl AnthropicClient {
             "{}/v1/messages/count_tokens",
             self.base_url.trim_end_matches('/')
         );
-        let mut request_body = self.request_profile.render_json_body(request)?;
-        strip_unsupported_beta_body_fields(&mut request_body);
+        let request_body = render_standard_messages_body(&self.request_profile, request)?;
         let response = self
             .build_request(&request_url)
             .json(&request_body)
@@ -1036,6 +1034,21 @@ fn enrich_bearer_auth_error(error: ApiError, auth: &AuthSource) -> ApiError {
     }
 }
 
+fn anthropic_wire_model(model: &str) -> &str {
+    model.strip_prefix("anthropic/").unwrap_or(model)
+}
+
+fn render_standard_messages_body(
+    request_profile: &AnthropicRequestProfile,
+    request: &MessageRequest,
+) -> Result<Value, serde_json::Error> {
+    let mut wire_request = request.clone();
+    wire_request.model = anthropic_wire_model(&request.model).to_string();
+    let mut body = request_profile.render_json_body(&wire_request)?;
+    strip_unsupported_beta_body_fields(&mut body);
+    Ok(body)
+}
+
 /// Remove beta-only body fields that the standard `/v1/messages` and
 /// `/v1/messages/count_tokens` endpoints reject as `Extra inputs are not
 /// permitted`. The `betas` opt-in is communicated via the `anthropic-beta`
@@ -1609,6 +1622,27 @@ mod tests {
         );
     }
 
+    #[test]
+    fn standard_messages_body_strips_anthropic_routing_prefix() {
+        let client = AnthropicClient::new("test-key");
+        let request = MessageRequest {
+            model: "anthropic/claude-opus-4-6".to_string(),
+            max_tokens: 64,
+            messages: vec![],
+            system: None,
+            tools: None,
+            tool_choice: None,
+            stream: false,
+            ..Default::default()
+        };
+
+        let rendered = super::render_standard_messages_body(client.request_profile(), &request)
+            .expect("body should render");
+
+        assert_eq!(rendered["model"], serde_json::json!("claude-opus-4-6"));
+        assert!(rendered.get("betas").is_none());
+    }
+
     #[test]
     fn enrich_bearer_auth_error_appends_sk_ant_hint_on_401_with_pure_bearer_token() {
         // given

rust/crates/api/src/providers/mod.rs

@@ -211,7 +211,7 @@ pub fn resolve_model_alias(model: &str) -> String {
         .find_map(|(alias, metadata)| {
             (*alias == lower).then_some(match metadata.provider {
                 ProviderKind::Anthropic => match *alias {
-                    "opus" => "claude-opus-4-6",
+                    "opus" => "claude-opus-4-7",
                     "sonnet" => "claude-sonnet-4-6",
                     "haiku" => "claude-haiku-4-5-20251213",
                     _ => trimmed,
@@ -262,6 +262,14 @@ pub fn metadata_for_model(model: &str) -> Option<ProviderMetadata> {
             default_base_url: openai_compat::DEFAULT_OPENAI_BASE_URL,
         });
     }
+    if canonical.starts_with("local/") {
+        return Some(ProviderMetadata {
+            provider: ProviderKind::OpenAi,
+            auth_env: "OPENAI_API_KEY",
+            base_url_env: "OPENAI_BASE_URL",
+            default_base_url: openai_compat::DEFAULT_OPENAI_BASE_URL,
+        });
+    }
     // Alibaba DashScope compatible-mode endpoint. Routes qwen/* and bare
     // qwen-* model names (qwen-max, qwen-plus, qwen-turbo, qwen-qwq, etc.)
     // to the OpenAI-compat client pointed at DashScope's /compatible-mode/v1.
@@ -337,17 +345,21 @@ pub fn provider_diagnostics_for_model(model: &str) -> ProviderDiagnostics {
     }
 }
 
+fn looks_like_local_openai_model(model: &str) -> bool {
+    model.contains(':') || model.contains('.')
+}
+
 #[must_use]
 pub fn detect_provider_kind(model: &str) -> ProviderKind {
-    if let Some(metadata) = metadata_for_model(model) {
+    let resolved_model = resolve_model_alias(model);
+    if let Some(metadata) = metadata_for_model(&resolved_model) {
         return metadata.provider;
     }
-    // When OPENAI_BASE_URL is set, the user explicitly configured an
-    // OpenAI-compatible endpoint. Prefer it over the Anthropic fallback
-    // even when the model name has no recognized prefix — this is the
-    // common case for local providers (Ollama, LM Studio, vLLM, etc.)
-    // where model names like "qwen2.5-coder:7b" don't match any prefix.
-    if std::env::var_os("OPENAI_BASE_URL").is_some() && openai_compat::has_api_key("OPENAI_API_KEY")
+    // When OPENAI_BASE_URL is set and the unknown model name looks like a
+    // local server tag (for example `llama3.2` or `qwen2.5-coder:7b`), prefer
+    // the OpenAI-compatible endpoint over ambient Anthropic credentials.
+    if std::env::var_os("OPENAI_BASE_URL").is_some()
+        && looks_like_local_openai_model(&resolved_model)
     {
         return ProviderKind::OpenAi;
     }
@@ -608,7 +620,7 @@ pub fn model_token_limit(model: &str) -> Option<ModelTokenLimit> {
     let canonical = resolve_model_alias(model);
     let base_model = canonical.rsplit('/').next().unwrap_or(canonical.as_str());
     match base_model {
-        "claude-opus-4-6" => Some(ModelTokenLimit {
+        "claude-opus-4-7" | "claude-opus-4-6" => Some(ModelTokenLimit {
             max_output_tokens: 32_000,
             context_window_tokens: 200_000,
         }),
@@ -1042,6 +1054,18 @@ mod tests {
         assert_eq!(kind2, ProviderKind::OpenAi);
     }
 
+    #[test]
+    fn local_prefix_routes_to_openai_not_anthropic() {
+        let meta = super::metadata_for_model("local/Qwen/Qwen3.6-27B-FP8")
+            .expect("local/ prefix must resolve to OpenAI-compatible metadata");
+        assert_eq!(meta.provider, ProviderKind::OpenAi);
+        assert_eq!(meta.auth_env, "OPENAI_API_KEY");
+        assert_eq!(meta.base_url_env, "OPENAI_BASE_URL");
+
+        let kind = detect_provider_kind("local/Qwen/Qwen3.6-27B-FP8");
+        assert_eq!(kind, ProviderKind::OpenAi);
+    }
+
     #[test]
     fn qwen_prefix_routes_to_dashscope_not_anthropic() {
         // User request from Discord #clawcode-get-help: web3g wants to use

rust/crates/api/src/providers/openai_compat.rs

@@ -1,5 +1,6 @@
 use std::borrow::Cow;
 use std::collections::{BTreeMap, VecDeque};
+use std::net::Ipv4Addr;
 use std::sync::atomic::{AtomicU64, Ordering};
 use std::time::{Duration, SystemTime, UNIX_EPOCH};
 
@@ -131,13 +132,22 @@ impl OpenAiCompatClient {
     }
 
     pub fn from_env(config: OpenAiCompatConfig) -> Result<Self, ApiError> {
-        let Some(api_key) = read_env_non_empty(config.api_key_env)? else {
-            return Err(ApiError::missing_credentials(
-                config.provider_name,
-                config.credential_env_vars(),
-            ));
+        let base_url = read_base_url(config);
+        let api_key = match read_env_non_empty(config.api_key_env)? {
+            Some(api_key) => api_key,
+            None if config.provider_name == "OpenAI"
+                && is_local_openai_compatible_base_url(&base_url) =>
+            {
+                "local-dev-token".to_string()
+            }
+            None => {
+                return Err(ApiError::missing_credentials(
+                    config.provider_name,
+                    config.credential_env_vars(),
+                ));
+            }
         };
-        Ok(Self::new(api_key, config))
+        Ok(Self::new(api_key, config).with_base_url(base_url))
     }
 
     #[must_use]
@@ -933,14 +943,18 @@ pub fn model_requires_reasoning_content_in_history(model: &str) -> bool {
 
 /// Strip routing prefix (e.g., "openai/gpt-4" → "gpt-4") for the wire.
 /// The prefix is used only to select transport; the backend expects the
-/// bare model id.
+/// bare model id. Use `local/` to force OpenAI-compatible routing while
+/// preserving any slashes that follow the prefix.
 #[allow(dead_code)]
 fn strip_routing_prefix(model: &str) -> &str {
     if let Some(pos) = model.find('/') {
         let prefix = &model[..pos];
         // Only strip if the prefix before "/" is a known routing prefix,
         // not if "/" appears in the middle of the model name for other reasons.
-        if matches!(prefix, "openai" | "xai" | "grok" | "qwen" | "kimi") {
+        if matches!(
+            prefix,
+            "openai" | "xai" | "grok" | "qwen" | "kimi" | "local"
+        ) {
             &model[pos + 1..]
         } else {
             model
@@ -950,6 +964,44 @@ fn strip_routing_prefix(model: &str) -> &str {
     }
 }
 
+fn normalize_base_url_for_model_routing(url: &str) -> &str {
+    let trimmed = url.trim_end_matches('/');
+    trimmed
+        .strip_suffix("/chat/completions")
+        .map(|value| value.trim_end_matches('/'))
+        .unwrap_or(trimmed)
+}
+
+fn url_host(url: &str) -> &str {
+    let after_scheme = url.split_once("://").map_or(url, |(_, rest)| rest);
+    let authority = after_scheme.split(['/', '?', '#']).next().unwrap_or("");
+    let host_port = authority
+        .rsplit_once('@')
+        .map_or(authority, |(_, host_port)| host_port);
+    if host_port.starts_with('[') {
+        return host_port
+            .split(']')
+            .next()
+            .unwrap_or("")
+            .trim_start_matches('[');
+    }
+    host_port.split(':').next().unwrap_or("")
+}
+
+fn is_local_openai_compatible_base_url(url: &str) -> bool {
+    let host = url_host(url.trim());
+    if host.eq_ignore_ascii_case("localhost") || host == "::1" {
+        return true;
+    }
+    let Ok(address) = host.parse::<Ipv4Addr>() else {
+        return false;
+    };
+    let [first, second, ..] = address.octets();
+    matches!(first, 10 | 127)
+        || first == 192 && second == 168
+        || first == 172 && (16..=31).contains(&second)
+}
+
 fn wire_model_for_base_url<'a>(
     model: &'a str,
     config: OpenAiCompatConfig,
@@ -962,26 +1014,22 @@ fn wire_model_for_base_url<'a>(
     let lowered_prefix = prefix.to_ascii_lowercase();
 
     if lowered_prefix == "openai" {
-        let trimmed_base_url = base_url.trim_end_matches('/');
-        let default_openai = DEFAULT_OPENAI_BASE_URL.trim_end_matches('/');
-        if matches!(
-            lowered_prefix.as_str(),
-            "xai" | "grok" | "kimi" | "gemini" | "gemma"
-        ) {
+        let normalized_base_url = normalize_base_url_for_model_routing(base_url);
+        let default_base_url = normalize_base_url_for_model_routing(config.default_base_url);
+        if normalized_base_url.eq_ignore_ascii_case(default_base_url)
+            || is_local_openai_compatible_base_url(base_url)
+        {
             return Cow::Borrowed(&model[pos + 1..]);
         }
-        if config.provider_name == "OpenAI" && trimmed_base_url != default_openai {
-            // Only preserve the full slug if it's NOT a model we want to strip
-            if !model.contains("gemini") && !model.contains("gemma") {
-                return Cow::Borrowed(model);
-            }
-        }
-        return Cow::Borrowed(&model[pos + 1..]);
+        return Cow::Borrowed(model);
     }
 
     if matches!(lowered_prefix.as_str(), "xai" | "grok" | "qwen" | "kimi") {
         return Cow::Borrowed(&model[pos + 1..]);
     }
+    if lowered_prefix == "local" {
+        return Cow::Borrowed(&model[pos + 1..]);
+    }
 
     Cow::Borrowed(model)
 }
@@ -1133,6 +1181,13 @@ fn build_chat_completion_request_for_base_url(
         payload[key] = value.clone();
     }
 
+    // DeepSeek V4 Pro/Flash thinking mode requires this provider-specific opt-in
+    // and also requires assistant reasoning history to be echoed as `reasoning_content`.
+    // Apply it after extra_body so callers cannot accidentally override the required shape.
+    if model_requires_reasoning_content_in_history(wire_model) {
+        payload["thinking"] = json!({"type": "enabled"});
+    }
+
     payload
 }
 
@@ -1190,16 +1245,19 @@ pub fn translate_message(message: &InputMessage, model: &str) -> Vec<Value> {
                     InputContentBlock::ToolResult { .. } => {}
                 }
             }
-            let include_reasoning =
-                model_requires_reasoning_content_in_history(model) && !reasoning.is_empty();
-            if text.is_empty() && tool_calls.is_empty() && !include_reasoning {
+            let needs_reasoning = model_requires_reasoning_content_in_history(model);
+            if text.is_empty() && tool_calls.is_empty() && reasoning.is_empty() {
                 Vec::new()
             } else {
                 let mut msg = serde_json::json!({
                     "role": "assistant",
-                    "content": (!text.is_empty()).then_some(text),
                 });
-                if include_reasoning {
+                if !text.is_empty() {
+                    msg["content"] = json!(text);
+                } else if !needs_reasoning {
+                    msg["content"] = Value::Null;
+                }
+                if needs_reasoning {
                     msg["reasoning_content"] = json!(reasoning);
                 }
                 // Only include tool_calls when non-empty: some providers reject
@@ -1752,6 +1810,7 @@ mod tests {
         ToolChoice, ToolDefinition, ToolResultContentBlock,
     };
     use serde_json::json;
+    use std::borrow::Cow;
     use std::collections::BTreeMap;
     use std::sync::{Mutex, OnceLock};
 
@@ -1850,6 +1909,31 @@ mod tests {
         assert_eq!(assistant["content"], json!("answer"));
     }
 
+    #[test]
+    fn deepseek_v4_assistant_with_only_tool_calls_omits_content_and_includes_reasoning() {
+        let request = MessageRequest {
+            model: "deepseek-v4-pro".to_string(),
+            max_tokens: 100,
+            messages: vec![InputMessage {
+                role: "assistant".to_string(),
+                content: vec![InputContentBlock::ToolUse {
+                    id: "call_1".to_string(),
+                    name: "get_weather".to_string(),
+                    input: json!({"city": "Paris"}),
+                }],
+            }],
+            stream: false,
+            ..Default::default()
+        };
+
+        let payload = build_chat_completion_request(&request, OpenAiCompatConfig::openai());
+        let assistant = &payload["messages"][0];
+
+        assert!(assistant.get("content").is_none());
+        assert_eq!(assistant["reasoning_content"], json!(""));
+        assert_eq!(assistant["tool_calls"].as_array().map(Vec::len), Some(1));
+    }
+
     #[test]
     fn deepseek_v4_flash_request_includes_reasoning_content_for_assistant_history() {
         // Given an assistant history turn containing thinking.
@@ -2036,6 +2120,49 @@ mod tests {
         assert_eq!(payload["reasoning_effort"], json!("high"));
     }
 
+    #[test]
+    fn deepseek_v4_request_includes_thinking_parameter() {
+        let payload = build_chat_completion_request(
+            &MessageRequest {
+                model: "deepseek-v4-pro".to_string(),
+                max_tokens: 1024,
+                messages: vec![InputMessage::user_text("hello")],
+                ..Default::default()
+            },
+            OpenAiCompatConfig::openai(),
+        );
+        assert_eq!(payload["thinking"], json!({"type": "enabled"}));
+        assert_eq!(payload["model"], json!("deepseek-v4-pro"));
+
+        let mut extra_body = BTreeMap::new();
+        extra_body.insert("thinking".to_string(), json!({"type": "disabled"}));
+        let payload_with_override = build_chat_completion_request(
+            &MessageRequest {
+                model: "openai/deepseek-v4-flash".to_string(),
+                max_tokens: 1024,
+                messages: vec![InputMessage::user_text("hello")],
+                extra_body,
+                ..Default::default()
+            },
+            OpenAiCompatConfig::openai(),
+        );
+        assert_eq!(
+            payload_with_override["thinking"],
+            json!({"type": "enabled"})
+        );
+
+        let non_deepseek_payload = build_chat_completion_request(
+            &MessageRequest {
+                model: "gpt-4o".to_string(),
+                max_tokens: 64,
+                messages: vec![InputMessage::user_text("hello")],
+                ..Default::default()
+            },
+            OpenAiCompatConfig::openai(),
+        );
+        assert!(non_deepseek_payload.get("thinking").is_none());
+    }
+
     #[test]
     fn reasoning_effort_omitted_when_not_set() {
         let payload = build_chat_completion_request(
@@ -2123,6 +2250,28 @@ mod tests {
         ));
     }
 
+    #[test]
+    fn local_openai_base_url_does_not_require_api_key() {
+        let _lock = env_lock();
+        let original_base_url = std::env::var_os("OPENAI_BASE_URL");
+        let original_api_key = std::env::var_os("OPENAI_API_KEY");
+        std::env::set_var("OPENAI_BASE_URL", "http://127.0.0.1:11434/v1");
+        std::env::remove_var("OPENAI_API_KEY");
+
+        let client = OpenAiCompatClient::from_env(OpenAiCompatConfig::openai())
+            .expect("local OpenAI-compatible endpoint should not require an API key");
+        assert_eq!(client.base_url(), "http://127.0.0.1:11434/v1");
+
+        match original_base_url {
+            Some(value) => std::env::set_var("OPENAI_BASE_URL", value),
+            None => std::env::remove_var("OPENAI_BASE_URL"),
+        }
+        match original_api_key {
+            Some(value) => std::env::set_var("OPENAI_API_KEY", value),
+            None => std::env::remove_var("OPENAI_API_KEY"),
+        }
+    }
+
     #[test]
     fn endpoint_builder_accepts_base_urls_and_full_endpoints() {
         assert_eq!(
@@ -2738,6 +2887,66 @@ mod tests {
         }
     }
 
+    #[test]
+    fn wire_model_strips_openai_prefix_for_default_and_local_preserves_custom_gateways() {
+        assert_eq!(
+            super::wire_model_for_base_url(
+                "openai/gpt-4o",
+                OpenAiCompatConfig::openai(),
+                super::DEFAULT_OPENAI_BASE_URL,
+            ),
+            Cow::Borrowed("gpt-4o")
+        );
+        assert_eq!(
+            super::wire_model_for_base_url(
+                "openai/qwen2.5-coder:7b",
+                OpenAiCompatConfig::openai(),
+                "http://127.0.0.1:11434/v1",
+            ),
+            Cow::Borrowed("qwen2.5-coder:7b")
+        );
+        assert_eq!(
+            super::wire_model_for_base_url(
+                "openai/llama3.2",
+                OpenAiCompatConfig::openai(),
+                "http://localhost:11434/v1/chat/completions",
+            ),
+            Cow::Borrowed("llama3.2")
+        );
+        assert_eq!(
+            super::wire_model_for_base_url(
+                "openai/gpt-4.1-mini",
+                OpenAiCompatConfig::openai(),
+                "https://openrouter.ai/api/v1",
+            ),
+            Cow::Borrowed("openai/gpt-4.1-mini")
+        );
+        assert_eq!(
+            super::wire_model_for_base_url(
+                "openai/gpt-4.1-mini",
+                OpenAiCompatConfig::openai(),
+                "https://not-localhost.example.com/v1",
+            ),
+            Cow::Borrowed("openai/gpt-4.1-mini")
+        );
+    }
+
+    #[test]
+    fn local_routing_prefix_strips_only_escape_hatch() {
+        assert_eq!(
+            super::strip_routing_prefix("local/Qwen/Qwen3.6-27B-FP8"),
+            "Qwen/Qwen3.6-27B-FP8"
+        );
+        assert_eq!(
+            super::wire_model_for_base_url(
+                "local/Qwen/Qwen3.6-27B-FP8",
+                OpenAiCompatConfig::openai(),
+                "http://127.0.0.1:8000/v1",
+            ),
+            Cow::Borrowed("Qwen/Qwen3.6-27B-FP8")
+        );
+    }
+
     #[test]
     fn check_request_body_size_allows_large_requests_for_openai() {
         // Create a request that exceeds DashScope's limit but is under OpenAI's 100MB limit

rust/crates/api/tests/client_integration.rs

@@ -103,6 +103,58 @@ async fn send_message_posts_json_and_parses_response() {
     );
 }
 
+#[tokio::test]
+async fn send_message_strips_anthropic_routing_prefix_on_wire() {
+    let state = Arc::new(Mutex::new(Vec::<CapturedRequest>::new()));
+    let server = spawn_server(
+        state.clone(),
+        vec![
+            http_response("200 OK", "application/json", "{\"input_tokens\":1}"),
+            http_response(
+                "200 OK",
+                "application/json",
+                concat!(
+                    "{",
+                    "\"id\":\"msg_prefixed\",",
+                    "\"type\":\"message\",",
+                    "\"role\":\"assistant\",",
+                    "\"content\":[{\"type\":\"text\",\"text\":\"ok\"}],",
+                    "\"model\":\"claude-opus-4-6\",",
+                    "\"stop_reason\":\"end_turn\",",
+                    "\"stop_sequence\":null,",
+                    "\"usage\":{\"input_tokens\":1,\"output_tokens\":1}",
+                    "}"
+                ),
+            ),
+        ],
+    )
+    .await;
+
+    let client = AnthropicClient::new("test-key").with_base_url(server.base_url());
+    client
+        .send_message(&MessageRequest {
+            model: "anthropic/claude-opus-4-6".to_string(),
+            ..sample_request(false)
+        })
+        .await
+        .expect("request should succeed");
+
+    let captured = state.lock().await;
+    assert_eq!(
+        captured.len(),
+        2,
+        "count_tokens and messages requests should be captured"
+    );
+    let count_tokens_body: serde_json::Value =
+        serde_json::from_str(&captured[0].body).expect("count_tokens body should be json");
+    let messages_body: serde_json::Value =
+        serde_json::from_str(&captured[1].body).expect("request body should be json");
+    assert_eq!(captured[0].path, "/v1/messages/count_tokens");
+    assert_eq!(captured[1].path, "/v1/messages");
+    assert_eq!(count_tokens_body["model"], json!("claude-opus-4-6"));
+    assert_eq!(messages_body["model"], json!("claude-opus-4-6"));
+}
+
 #[tokio::test]
 async fn send_message_blocks_oversized_requests_before_the_http_call() {
     let state = Arc::new(Mutex::new(Vec::<CapturedRequest>::new()));

rust/crates/api/tests/openai_compat_integration.rs

@@ -159,10 +159,15 @@ async fn send_message_preserves_deepseek_reasoning_content_before_text() {
             },
         ]
     );
+
+    let captured = state.lock().await;
+    let request = captured.first().expect("server should capture request");
+    let body: serde_json::Value = serde_json::from_str(&request.body).expect("json body");
+    assert_eq!(body["thinking"], json!({"type": "enabled"}));
 }
 
 #[tokio::test]
-async fn custom_openai_gateway_preserves_slash_model_ids_and_extra_body_params() {
+async fn local_openai_gateway_strips_routing_prefix_and_preserves_extra_body_params() {
     let state = Arc::new(Mutex::new(Vec::<CapturedRequest>::new()));
     let body = concat!(
         "{",
@@ -206,7 +211,7 @@ async fn custom_openai_gateway_preserves_slash_model_ids_and_extra_body_params()
     let captured = state.lock().await;
     let request = captured.first().expect("captured request");
     let body: serde_json::Value = serde_json::from_str(&request.body).expect("json body");
-    assert_eq!(body["model"], json!("openai/gpt-4.1-mini"));
+    assert_eq!(body["model"], json!("gpt-4.1-mini"));
     assert_eq!(
         body["web_search_options"],
         json!({"search_context_size": "low"})