feat(TASK-041): add WireApi enum and wire-aware Responses dispatch

Introduce a WireApi enum (responses|chat) with an optional wire_api
config field on the openai and openai-compatible clients, resolved
through a single resolve_wire_api fn: codex forces the responses wire
(an explicit wire_api: chat there is a hard config error), an explicit
wire_api wins everywhere else, and the default stays chat for now.
The openai dispatch generalizes from (RequestData, bool) to
(RequestData, WireApi), and the openai-compatible client gains opt-in
Responses dispatch (URL, body, extractor, and streaming forks).

Both patch layers are now wire-aware: RequestData carries its wire,
RequestPatch gains a responses section, and patch_request_data selects
patches per wire. This deliberately FIXES a codex bug: chat-shaped
model patches (e.g. o3-high's max_tokens/temperature/top_p/
reasoning_effort tweaks) previously merged wire-blind into codex
responses bodies, poisoning them with chat-only keys. On the responses
wire only an explicit responses sub-patch applies; chat-wire patching
is byte-identical to before (pinned by a regression test).

src/client/bedrock.rs

@@ -73,6 +73,7 @@ impl BedrockClient {
             url: _,
             headers,
             body,
+            ..
         } = request_data;
 
         let builder = aws_fetch(
@@ -126,6 +127,7 @@ impl BedrockClient {
             url: _,
             headers,
             body,
+            ..
         } = request_data;
 
         let builder = aws_fetch(

src/client/common.rs

@@ -221,23 +221,39 @@ pub trait Client: Sync + Send {
         request_data.into_builder(client)
     }
 
+    /// Patches are chat-shaped unless keyed otherwise: on the Responses wire
+    /// only the `responses` sub-patch of a model patch and the `responses`
+    /// section of a client patch apply, so chat-only keys never leak into a
+    /// responses body.
     fn patch_request_data(&self, request_data: &mut RequestData) {
         let model_type = self.model().model_type();
+        let wire = request_data.wire;
         if let Some(patch) = self.model().patch() {
+            match wire {
+                WireApi::Chat => request_data.apply_patch(patch.clone()),
+                WireApi::Responses => {
+                    if let Some(patch) = patch.get("responses") {
                         request_data.apply_patch(patch.clone());
                     }
+                }
+            }
+        }
 
+        let api_name = match wire {
+            WireApi::Responses => "responses",
+            WireApi::Chat => model_type.api_name(),
+        };
         let patch_map = std::env::var(get_env_name(&format!(
-            "patch_{}_{}",
+            "patch_{}_{api_name}",
             self.model().client_name(),
-            model_type.api_name(),
         )))
         .ok()
         .and_then(|v| serde_json::from_str(&v).ok())
         .or_else(|| {
-            self.patch_config()
+            self.patch_config().and_then(|v| match wire {
-                .and_then(|v| model_type.extract_patch(v))
+                WireApi::Responses => v.responses.clone(),
-                .cloned()
+                WireApi::Chat => model_type.extract_patch(v).cloned(),
+            })
         });
         let patch_map = match patch_map {
             Some(v) => v,
@@ -271,16 +287,26 @@ pub struct ExtraConfig {
 #[derive(Debug, Clone, Deserialize, Default)]
 pub struct RequestPatch {
     pub chat_completions: Option<ApiPatch>,
+    pub responses: Option<ApiPatch>,
     pub embeddings: Option<ApiPatch>,
     pub rerank: Option<ApiPatch>,
 }
 
 pub type ApiPatch = IndexMap<String, Value>;
 
+#[derive(Debug, Clone, Copy, PartialEq, Eq, Deserialize, Serialize)]
+#[serde(rename_all = "lowercase")]
+pub enum WireApi {
+    Responses,
+    Chat,
+}
+
+#[derive(Debug)]
 pub struct RequestData {
     pub url: String,
     pub headers: IndexMap<String, String>,
     pub body: Value,
+    pub wire: WireApi,
 }
 
 impl RequestData {
@@ -292,9 +318,15 @@ impl RequestData {
             url: url.to_string(),
             headers: Default::default(),
             body,
+            wire: WireApi::Chat,
         }
     }
 
+    pub fn wire(mut self, wire: WireApi) -> Self {
+        self.wire = wire;
+        self
+    }
+
     pub fn bearer_auth<T>(&mut self, auth: T)
     where
         T: std::fmt::Display,
@@ -312,7 +344,9 @@ impl RequestData {
     }
 
     pub fn into_builder(self, client: &ReqwestClient) -> RequestBuilder {
-        let RequestData { url, headers, body } = self;
+        let RequestData {
+            url, headers, body, ..
+        } = self;
         debug!("Request {url} {body}");
 
         let mut builder = client.post(url);
@@ -1524,4 +1558,222 @@ mod tests {
         assert_eq!(client.streaming_calls.load(Ordering::SeqCst), 1);
         assert_paced_reply(&text, &results);
     }
+
+    /// Minimal client for exercising `patch_request_data`: only the model
+    /// and the client-level patch config matter.
+    struct PatchProbeClient {
+        config: AppConfig,
+        model: Model,
+        patch: Option<RequestPatch>,
+    }
+
+    #[async_trait::async_trait]
+    impl Client for PatchProbeClient {
+        fn app_config(&self) -> &AppConfig {
+            &self.config
+        }
+
+        fn extra_config(&self) -> Option<&ExtraConfig> {
+            None
+        }
+
+        fn patch_config(&self) -> Option<&RequestPatch> {
+            self.patch.as_ref()
+        }
+
+        fn name(&self) -> &str {
+            self.model.client_name()
+        }
+
+        fn model(&self) -> &Model {
+            &self.model
+        }
+
+        async fn chat_completions_inner(
+            &self,
+            _client: &ReqwestClient,
+            _data: ChatCompletionsData,
+        ) -> Result<ChatCompletionsOutput> {
+            bail!("the patch probe makes no requests")
+        }
+
+        async fn chat_completions_streaming_inner(
+            &self,
+            _client: &ReqwestClient,
+            _handler: &mut SseHandler,
+            _data: ChatCompletionsData,
+        ) -> Result<()> {
+            bail!("the patch probe makes no requests")
+        }
+    }
+
+    fn patch_probe(
+        client_name: &str,
+        model_patch: Option<Value>,
+        patch: Option<RequestPatch>,
+    ) -> PatchProbeClient {
+        let mut data = ModelData::new("gpt-test");
+        data.patch = model_patch;
+        PatchProbeClient {
+            config: AppConfig::default(),
+            model: Model::from_config(client_name, &[data]).remove(0),
+            patch,
+        }
+    }
+
+    fn client_patch(json: Value) -> RequestPatch {
+        serde_json::from_value(json).unwrap()
+    }
+
+    fn wire_request(wire: WireApi) -> RequestData {
+        RequestData::new("https://example.test/v1", json!({"model": "gpt-test"})).wire(wire)
+    }
+
+    #[test]
+    fn request_patch_accepts_a_responses_section() {
+        let patch = client_patch(json!({
+            "responses": {".*": {"body": {"store": true}}},
+            "chat_completions": {".*": {"body": {"temperature": 0.5}}},
+        }));
+
+        assert!(patch.responses.is_some());
+        assert!(patch.chat_completions.is_some());
+    }
+
+    #[test]
+    fn chat_client_patch_never_touches_the_responses_wire() {
+        let client = patch_probe(
+            "patchprobechatiso",
+            None,
+            Some(client_patch(json!({
+                "chat_completions": {".*": {"body": {"temperature": 0.5}}}
+            }))),
+        );
+        let mut request_data = wire_request(WireApi::Responses);
+        let before = request_data.body.clone();
+
+        client.patch_request_data(&mut request_data);
+
+        assert_eq!(request_data.body, before);
+    }
+
+    #[test]
+    fn responses_client_patch_never_touches_the_chat_wire() {
+        let patch = Some(client_patch(json!({
+            "responses": {".*": {"body": {"store": true}}}
+        })));
+        let client = patch_probe("patchproberespiso", None, patch);
+
+        let mut chat_request = wire_request(WireApi::Chat);
+        let before = chat_request.body.clone();
+        client.patch_request_data(&mut chat_request);
+        assert_eq!(chat_request.body, before);
+
+        let mut responses_request = wire_request(WireApi::Responses);
+        client.patch_request_data(&mut responses_request);
+        assert_eq!(responses_request.body["store"], json!(true));
+    }
+
+    #[test]
+    fn chat_shaped_model_patch_never_touches_the_responses_wire() {
+        let client = patch_probe(
+            "patchprobemodeliso",
+            Some(json!({"body": {"reasoning_effort": "high"}})),
+            None,
+        );
+        let mut request_data = wire_request(WireApi::Responses);
+        let before = request_data.body.clone();
+
+        client.patch_request_data(&mut request_data);
+
+        assert_eq!(request_data.body, before);
+    }
+
+    #[test]
+    fn model_patch_responses_subkey_is_selected_per_wire() {
+        let model_patch = json!({
+            "body": {"temperature": 0.2},
+            "responses": {"body": {"store": true}},
+        });
+        let client = patch_probe("patchprobesubkey", Some(model_patch), None);
+
+        let mut responses_request = wire_request(WireApi::Responses);
+        client.patch_request_data(&mut responses_request);
+        assert_eq!(responses_request.body["store"], json!(true));
+        assert!(responses_request.body.get("temperature").is_none());
+
+        let mut chat_request = wire_request(WireApi::Chat);
+        client.patch_request_data(&mut chat_request);
+        assert_eq!(chat_request.body["temperature"], json!(0.2));
+        assert!(chat_request.body.get("store").is_none());
+    }
+
+    #[test]
+    fn env_patch_override_is_selected_per_wire() {
+        // Unique client name so the env vars cannot race parallel tests.
+        let client_name = "patchprobeenvwire";
+        let responses_env = get_env_name(&format!("patch_{client_name}_responses"));
+        let chat_env = get_env_name(&format!("patch_{client_name}_chat_completions"));
+        unsafe {
+            std::env::set_var(&responses_env, r#"{".*": {"body": {"store": true}}}"#);
+            std::env::set_var(&chat_env, r#"{".*": {"body": {"temperature": 0.7}}}"#);
+        }
+
+        let client = patch_probe(client_name, None, None);
+        let mut responses_request = wire_request(WireApi::Responses);
+        client.patch_request_data(&mut responses_request);
+        let mut chat_request = wire_request(WireApi::Chat);
+        client.patch_request_data(&mut chat_request);
+
+        unsafe {
+            std::env::remove_var(&responses_env);
+            std::env::remove_var(&chat_env);
+        }
+
+        assert_eq!(responses_request.body["store"], json!(true));
+        assert!(responses_request.body.get("temperature").is_none());
+        assert_eq!(chat_request.body["temperature"], json!(0.7));
+        assert!(chat_request.body.get("store").is_none());
+    }
+
+    #[test]
+    fn chat_wire_patching_is_unchanged_by_wire_awareness() {
+        let client = patch_probe(
+            "patchproberegress",
+            Some(json!({"body": {"max_tokens": null}, "headers": {"x-model": "m"}})),
+            Some(client_patch(json!({
+                "chat_completions": {".*": {
+                    "url": "https://patched.example/v1/chat/completions",
+                    "body": {"temperature": 0.9},
+                }}
+            }))),
+        );
+        let mut request_data = RequestData::new(
+            "https://example.test/v1/chat/completions",
+            json!({"model": "gpt-test", "max_tokens": 100}),
+        );
+        request_data.bearer_auth("sk-test");
+
+        client.patch_request_data(&mut request_data);
+
+        assert_eq!(
+            request_data.url,
+            "https://patched.example/v1/chat/completions"
+        );
+        assert_eq!(
+            request_data.body,
+            json!({"model": "gpt-test", "temperature": 0.9})
+        );
+        assert_eq!(
+            request_data.headers.get("x-model").map(String::as_str),
+            Some("m")
+        );
+        assert_eq!(
+            request_data
+                .headers
+                .get("authorization")
+                .map(String::as_str),
+            Some("Bearer sk-test")
+        );
+    }
 }

src/client/oauth.rs

@@ -1460,6 +1460,7 @@ echo_pkce_in_token_exchange: true
             api_key: None,
             auth: auth.map(str::to_string),
             oauth: oauth.map(Box::new),
+            wire_api: None,
             models: vec![],
             patch: None,
             extra: None,
@@ -1496,6 +1497,7 @@ echo_pkce_in_token_exchange: true
             organization_id: None,
             auth: auth.map(str::to_string),
             oauth: oauth.map(Box::new),
+            wire_api: None,
             models: vec![],
             patch: None,
             extra: None,

src/client/openai.rs

@@ -21,6 +21,7 @@ pub struct OpenAIConfig {
     pub organization_id: Option<String>,
     pub auth: Option<String>,
     pub oauth: Option<Box<OAuthConfig>>,
+    pub wire_api: Option<WireApi>,
     #[serde(default)]
     pub models: Vec<ModelData>,
     pub patch: Option<RequestPatch>,
@@ -47,12 +48,11 @@ impl Client for OpenAIClient {
         client: &ReqwestClient,
         data: ChatCompletionsData,
     ) -> Result<ChatCompletionsOutput> {
-        let (request_data, uses_codex) = prepare_chat_completions(self, client, data).await?;
+        let (request_data, wire) = prepare_chat_completions(self, client, data).await?;
         let builder = self.request_builder(client, request_data);
-        if uses_codex {
+        match wire {
-            openai_responses_chat_completions(builder, self.model()).await
+            WireApi::Responses => openai_responses_chat_completions(builder, self.model()).await,
-        } else {
+            WireApi::Chat => openai_chat_completions(builder, self.model()).await,
-            openai_chat_completions(builder, self.model()).await
         }
     }
 
@@ -62,15 +62,16 @@ impl Client for OpenAIClient {
         handler: &mut SseHandler,
         data: ChatCompletionsData,
     ) -> Result<()> {
-        let (request_data, uses_codex) = prepare_chat_completions(self, client, data).await?;
+        let (request_data, wire) = prepare_chat_completions(self, client, data).await?;
         let builder = self.request_builder(client, request_data);
 
-        if uses_codex {
+        match wire {
-            openai_responses_streaming(builder, handler).await
+            WireApi::Responses => openai_responses_streaming(builder, handler).await,
-        } else {
+            WireApi::Chat => {
                 openai_chat_completions_streaming(builder, handler, self.model()).await
             }
         }
+    }
 
     async fn embeddings_inner(
         &self,
@@ -93,11 +94,29 @@ impl Client for OpenAIClient {
     }
 }
 
+/// Codex only speaks the Responses API, so it forces the responses wire and
+/// rejects an explicit `wire_api: chat`. Anywhere else an explicit `wire_api`
+/// wins and the default is chat.
+pub fn resolve_wire_api(
+    explicit: Option<WireApi>,
+    uses_codex: bool,
+    _stock_openai_without_api_base: bool,
+) -> Result<WireApi> {
+    match (uses_codex, explicit) {
+        (true, Some(WireApi::Chat)) => bail!(
+            "the Codex backend only speaks the Responses API; remove `wire_api: chat` or configure an `api_base`"
+        ),
+        (true, _) => Ok(WireApi::Responses),
+        (false, Some(wire)) => Ok(wire),
+        (false, None) => Ok(WireApi::Chat),
+    }
+}
+
 async fn prepare_chat_completions(
     self_: &OpenAIClient,
     client: &ReqwestClient,
     data: ChatCompletionsData,
-) -> Result<(RequestData, bool)> {
+) -> Result<(RequestData, WireApi)> {
     let uses_oauth = self_.config.auth.as_deref() == Some("oauth");
 
     if !uses_oauth && self_.config.oauth.is_some() {
@@ -116,21 +135,28 @@ async fn prepare_chat_completions(
     let uses_stock_provider = matches!(oauth_provider, Some((_, true)));
     // Stock oauth with no `api_base` routes to the ChatGPT codex backend (Responses API).
     let uses_codex = uses_stock_provider && self_.get_api_base().is_err();
+    let wire = resolve_wire_api(
+        self_.config.wire_api,
+        uses_codex,
+        self_.get_api_base().is_err(),
+    )?;
 
     let url = if uses_codex {
         CODEX_API_ENDPOINT.to_string()
     } else {
         let api_base = resolve_api_base(self_)?;
-        format!("{}/chat/completions", api_base.trim_end_matches('/'))
+        match wire {
+            WireApi::Responses => format!("{}/responses", api_base.trim_end_matches('/')),
+            WireApi::Chat => format!("{}/chat/completions", api_base.trim_end_matches('/')),
+        }
     };
 
-    let body = if uses_codex {
+    let body = match wire {
-        openai_build_responses_body(data, &self_.model)
+        WireApi::Responses => openai_build_responses_body(data, &self_.model),
-    } else {
+        WireApi::Chat => openai_build_chat_completions_body(data, &self_.model),
-        openai_build_chat_completions_body(data, &self_.model)
     };
 
-    let mut request_data = RequestData::new(url, body);
+    let mut request_data = RequestData::new(url, body).wire(wire);
 
     if let Some((provider, _)) = oauth_provider {
         let ready = oauth::prepare_oauth_access_token(client, &*provider, self_.name()).await?;
@@ -167,7 +193,7 @@ async fn prepare_chat_completions(
         request_data.header("OpenAI-Organization", organization_id);
     }
 
-    Ok((request_data, uses_codex))
+    Ok((request_data, wire))
 }
 
 async fn prepare_embeddings(
@@ -909,7 +935,11 @@ mod tests {
             .unwrap()
     }
 
-    fn prepare(client: &OpenAIClient) -> Result<(RequestData, bool)> {
+    fn prepare(client: &OpenAIClient) -> Result<(RequestData, WireApi)> {
+        prepare_with_stream(client, false)
+    }
+
+    fn prepare_with_stream(client: &OpenAIClient, stream: bool) -> Result<(RequestData, WireApi)> {
         let data = ChatCompletionsData {
             messages: vec![Message::new(
                 MessageRole::User,
@@ -919,7 +949,7 @@ mod tests {
             top_p: None,
             reasoning_effort: None,
             functions: None,
-            stream: false,
+            stream,
         };
         tokio::runtime::Builder::new_current_thread()
             .enable_all()
@@ -1006,9 +1036,9 @@ mod tests {
         let client = make_client(config.clone(), vec![ClientConfig::OpenAIConfig(config)]);
         set_access_token(name, "codex-at".into(), Utc::now().timestamp() + 3600, None);
 
-        let (request_data, uses_codex) = prepare(&client).unwrap();
+        let (request_data, wire) = prepare(&client).unwrap();
 
-        assert!(uses_codex);
+        assert_eq!(wire, WireApi::Responses);
         assert_eq!(request_data.url, CODEX_API_ENDPOINT);
     }
 
@@ -1024,9 +1054,9 @@ mod tests {
             None,
         );
 
-        let (request_data, uses_codex) = prepare(&client).unwrap();
+        let (request_data, wire) = prepare(&client).unwrap();
 
-        assert!(!uses_codex);
+        assert_eq!(wire, WireApi::Chat);
         assert_eq!(
             request_data.url,
             "https://gateway.example/v1/chat/completions"
@@ -1243,4 +1273,170 @@ mod tests {
             "bundled models.yaml must not carry an openai oauth block: it would silently disable codex routing for stock ChatGPT oauth users"
         );
     }
+
+    #[test]
+    fn wire_api_deserializes_on_openai_config() {
+        let config: OpenAIConfig = serde_yaml::from_str("wire_api: responses").unwrap();
+        assert_eq!(config.wire_api, Some(WireApi::Responses));
+
+        let config: OpenAIConfig = serde_yaml::from_str("wire_api: chat").unwrap();
+        assert_eq!(config.wire_api, Some(WireApi::Chat));
+    }
+
+    #[test]
+    fn bogus_wire_api_is_a_config_error() {
+        let err = serde_yaml::from_str::<OpenAIConfig>("wire_api: bogus")
+            .unwrap_err()
+            .to_string();
+
+        assert!(
+            err.contains("responses") && err.contains("chat"),
+            "unexpected error: {err}"
+        );
+    }
+
+    #[test]
+    fn resolver_codex_defaults_to_responses() {
+        assert_eq!(
+            resolve_wire_api(None, true, false).unwrap(),
+            WireApi::Responses
+        );
+        assert_eq!(
+            resolve_wire_api(Some(WireApi::Responses), true, false).unwrap(),
+            WireApi::Responses
+        );
+    }
+
+    #[test]
+    fn resolver_rejects_explicit_chat_on_codex() {
+        let err = resolve_wire_api(Some(WireApi::Chat), true, false)
+            .unwrap_err()
+            .to_string();
+
+        assert!(
+            err.contains("only speaks the Responses API"),
+            "unexpected error: {err}"
+        );
+    }
+
+    #[test]
+    fn resolver_explicit_wins_off_codex() {
+        for stock in [false, true] {
+            assert_eq!(
+                resolve_wire_api(Some(WireApi::Responses), false, stock).unwrap(),
+                WireApi::Responses
+            );
+            assert_eq!(
+                resolve_wire_api(Some(WireApi::Chat), false, stock).unwrap(),
+                WireApi::Chat
+            );
+        }
+    }
+
+    #[test]
+    fn resolver_defaults_to_chat_this_milestone() {
+        for stock in [false, true] {
+            assert_eq!(resolve_wire_api(None, false, stock).unwrap(), WireApi::Chat);
+        }
+    }
+
+    fn api_key_config(name: &str, wire_api: Option<WireApi>) -> OpenAIConfig {
+        OpenAIConfig {
+            name: Some(name.into()),
+            api_key: Some("sk-test".into()),
+            wire_api,
+            ..Default::default()
+        }
+    }
+
+    #[test]
+    fn api_key_openai_defaults_to_the_chat_wire() {
+        let config = api_key_config("openai-wire-default-test", None);
+        let client = make_client(config.clone(), vec![ClientConfig::OpenAIConfig(config)]);
+
+        let (request_data, wire) = prepare(&client).unwrap();
+
+        assert_eq!(wire, WireApi::Chat);
+        assert_eq!(request_data.url, format!("{API_BASE}/chat/completions"));
+        assert!(
+            request_data.body.get("messages").is_some(),
+            "body: {}",
+            request_data.body
+        );
+    }
+
+    #[test]
+    fn explicit_responses_wire_posts_a_responses_body_to_the_responses_endpoint() {
+        let config = api_key_config("openai-wire-responses-test", Some(WireApi::Responses));
+        let client = make_client(config.clone(), vec![ClientConfig::OpenAIConfig(config)]);
+
+        let (request_data, wire) = prepare(&client).unwrap();
+
+        assert_eq!(wire, WireApi::Responses);
+        assert_eq!(request_data.url, format!("{API_BASE}/responses"));
+        assert_eq!(request_data.body["store"], json!(false));
+        assert!(
+            request_data.body.get("input").is_some() && request_data.body.get("messages").is_none(),
+            "body: {}",
+            request_data.body
+        );
+    }
+
+    #[test]
+    fn explicit_responses_wire_forks_the_streaming_path_too() {
+        let config = api_key_config("openai-wire-responses-stream-test", Some(WireApi::Responses));
+        let client = make_client(config.clone(), vec![ClientConfig::OpenAIConfig(config)]);
+
+        let (request_data, wire) = prepare_with_stream(&client, true).unwrap();
+
+        assert_eq!(wire, WireApi::Responses);
+        assert_eq!(request_data.url, format!("{API_BASE}/responses"));
+        assert_eq!(request_data.body["stream"], json!(true));
+        assert!(
+            request_data.body.get("input").is_some(),
+            "body: {}",
+            request_data.body
+        );
+    }
+
+    #[test]
+    fn codex_with_explicit_chat_wire_is_rejected() {
+        let name = "openai-codex-chat-wire-test";
+        let mut config = openai_config(name, Some("oauth"), None);
+        config.wire_api = Some(WireApi::Chat);
+        let client = make_client(config.clone(), vec![ClientConfig::OpenAIConfig(config)]);
+
+        let err = prepare(&client).unwrap_err().to_string();
+
+        assert!(
+            err.contains("only speaks the Responses API"),
+            "unexpected error: {err}"
+        );
+    }
+
+    #[test]
+    fn codex_responses_body_ignores_a_chat_shaped_model_patch() {
+        let name = "openai-codex-chat-patch-test";
+        let config = openai_config(name, Some("oauth"), None);
+        let mut model_data = ModelData::new("gpt-test");
+        model_data.patch = Some(json!({
+            "body": {
+                "max_tokens": null,
+                "temperature": null,
+                "top_p": null,
+                "reasoning_effort": "high",
+            }
+        }));
+        let mut client = make_client(config.clone(), vec![ClientConfig::OpenAIConfig(config)]);
+        client.model = Model::from_config("openai", &[model_data]).remove(0);
+        set_access_token(name, "codex-at".into(), Utc::now().timestamp() + 3600, None);
+
+        let (mut request_data, wire) = prepare(&client).unwrap();
+        assert_eq!(wire, WireApi::Responses);
+        let body_before = request_data.body.clone();
+
+        client.patch_request_data(&mut request_data);
+
+        assert_eq!(request_data.body, body_before, "a chat-shaped model patch must not merge into a responses body");
+    }
 }

src/client/openai_compatible.rs

@@ -16,6 +16,7 @@ pub struct OpenAICompatibleConfig {
     pub api_key: Option<String>,
     pub auth: Option<String>,
     pub oauth: Option<Box<OAuthConfig>>,
+    pub wire_api: Option<WireApi>,
     #[serde(default)]
     pub models: Vec<ModelData>,
     pub patch: Option<RequestPatch>,
@@ -42,10 +43,13 @@ impl Client for OpenAICompatibleClient {
         client: &ReqwestClient,
         data: ChatCompletionsData,
     ) -> Result<ChatCompletionsOutput> {
-        let request_data = prepare_chat_completions(self, client, data).await?;
+        let (request_data, wire) = prepare_chat_completions(self, client, data).await?;
         let builder = self.request_builder(client, request_data);
 
-        openai_chat_completions(builder, self.model()).await
+        match wire {
+            WireApi::Responses => openai_responses_chat_completions(builder, self.model()).await,
+            WireApi::Chat => openai_chat_completions(builder, self.model()).await,
+        }
     }
 
     async fn chat_completions_streaming_inner(
@@ -54,11 +58,16 @@ impl Client for OpenAICompatibleClient {
         handler: &mut SseHandler,
         data: ChatCompletionsData,
     ) -> Result<()> {
-        let request_data = prepare_chat_completions(self, client, data).await?;
+        let (request_data, wire) = prepare_chat_completions(self, client, data).await?;
         let builder = self.request_builder(client, request_data);
 
+        match wire {
+            WireApi::Responses => openai_responses_streaming(builder, handler).await,
+            WireApi::Chat => {
                 openai_chat_completions_streaming(builder, handler, self.model()).await
             }
+        }
+    }
 
     async fn embeddings_inner(
         &self,
@@ -87,15 +96,22 @@ async fn prepare_chat_completions(
     self_: &OpenAICompatibleClient,
     client: &ReqwestClient,
     data: ChatCompletionsData,
-) -> Result<RequestData> {
+) -> Result<(RequestData, WireApi)> {
+    let wire = resolve_wire_api(self_.config.wire_api, false, false)?;
     let api_base = get_api_base_ext(self_)?;
-    let url = format!("{api_base}/chat/completions");
+    let url = match wire {
-    let body = openai_build_chat_completions_body(data, &self_.model);
+        WireApi::Responses => format!("{api_base}/responses"),
-    let mut request_data = RequestData::new(url, body);
+        WireApi::Chat => format!("{api_base}/chat/completions"),
+    };
+    let body = match wire {
+        WireApi::Responses => openai_build_responses_body(data, &self_.model),
+        WireApi::Chat => openai_build_chat_completions_body(data, &self_.model),
+    };
+    let mut request_data = RequestData::new(url, body).wire(wire);
 
     apply_auth(self_, client, &mut request_data).await?;
 
-    Ok(request_data)
+    Ok((request_data, wire))
 }
 
 async fn prepare_embeddings(
@@ -246,3 +262,137 @@ pub fn generic_build_rerank_body(data: &RerankData, model: &Model) -> Value {
     }
     body
 }
+
+#[cfg(test)]
+mod tests {
+    use super::*;
+    use crate::config::AppConfig;
+    use std::sync::Arc;
+
+    fn compat_config(wire_api: Option<WireApi>) -> OpenAICompatibleConfig {
+        OpenAICompatibleConfig {
+            name: Some("compat-test".into()),
+            api_base: Some("https://compat.example/v1".into()),
+            api_key: Some("sk-test".into()),
+            auth: None,
+            oauth: None,
+            wire_api,
+            models: vec![],
+            patch: None,
+            extra: None,
+        }
+    }
+
+    fn make_client(config: OpenAICompatibleConfig) -> OpenAICompatibleClient {
+        OpenAICompatibleClient {
+            app_config: Arc::new(AppConfig::default()),
+            config,
+            model: Model::new("compat-test", "gpt-test"),
+        }
+    }
+
+    fn prepare(
+        client: &OpenAICompatibleClient,
+        stream: bool,
+    ) -> Result<(RequestData, WireApi)> {
+        let data = ChatCompletionsData {
+            messages: vec![Message::new(
+                MessageRole::User,
+                MessageContent::Text("hello".to_string()),
+            )],
+            temperature: None,
+            top_p: None,
+            reasoning_effort: None,
+            functions: None,
+            stream,
+        };
+        tokio::runtime::Builder::new_current_thread()
+            .enable_all()
+            .build()
+            .unwrap()
+            .block_on(prepare_chat_completions(
+                client,
+                &ReqwestClient::new(),
+                data,
+            ))
+    }
+
+    #[test]
+    fn wire_api_deserializes_on_openai_compatible_config() {
+        let config: OpenAICompatibleConfig = serde_yaml::from_str("wire_api: responses").unwrap();
+        assert_eq!(config.wire_api, Some(WireApi::Responses));
+
+        let config: OpenAICompatibleConfig = serde_yaml::from_str("wire_api: chat").unwrap();
+        assert_eq!(config.wire_api, Some(WireApi::Chat));
+    }
+
+    #[test]
+    fn bogus_wire_api_is_a_config_error() {
+        let err = serde_yaml::from_str::<OpenAICompatibleConfig>("wire_api: bogus")
+            .unwrap_err()
+            .to_string();
+
+        assert!(
+            err.contains("responses") && err.contains("chat"),
+            "unexpected error: {err}"
+        );
+    }
+
+    #[test]
+    fn default_wire_is_chat() {
+        let client = make_client(compat_config(None));
+
+        let (request_data, wire) = prepare(&client, false).unwrap();
+
+        assert_eq!(wire, WireApi::Chat);
+        assert_eq!(
+            request_data.url,
+            "https://compat.example/v1/chat/completions"
+        );
+        assert!(
+            request_data.body.get("messages").is_some(),
+            "body: {}",
+            request_data.body
+        );
+    }
+
+    #[test]
+    fn explicit_responses_wire_posts_a_responses_body_to_the_responses_endpoint() {
+        let client = make_client(compat_config(Some(WireApi::Responses)));
+
+        let (request_data, wire) = prepare(&client, false).unwrap();
+
+        assert_eq!(wire, WireApi::Responses);
+        assert_eq!(request_data.url, "https://compat.example/v1/responses");
+        assert_eq!(request_data.body["store"], json!(false));
+        assert!(
+            request_data.body.get("input").is_some() && request_data.body.get("messages").is_none(),
+            "body: {}",
+            request_data.body
+        );
+    }
+
+    #[test]
+    fn explicit_responses_wire_forks_the_streaming_path_too() {
+        let client = make_client(compat_config(Some(WireApi::Responses)));
+
+        let (request_data, wire) = prepare(&client, true).unwrap();
+
+        assert_eq!(wire, WireApi::Responses);
+        assert_eq!(request_data.url, "https://compat.example/v1/responses");
+        assert_eq!(request_data.body["stream"], json!(true));
+    }
+
+    #[test]
+    fn explicit_chat_wire_keeps_the_chat_endpoint() {
+        let client = make_client(compat_config(Some(WireApi::Chat)));
+
+        let (request_data, wire) = prepare(&client, false).unwrap();
+
+        assert_eq!(wire, WireApi::Chat);
+        assert_eq!(
+            request_data.url,
+            "https://compat.example/v1/chat/completions"
+        );
+    }
+}