Merge pull request #30 from Dark-Alex-17/feat/PLAN-responses-api

PLAN-responses-api: OpenAI Responses API as the default wire format

assets/config-template.yaml

@@ -302,4 +302,28 @@ sync_models_ttl_hours: 24        # Hours before the synced model catalog is cons
 #
 # The claude, bedrock, and vertexai clients also support:
 #   prompt_cache: true                              # Enable Anthropic prompt caching (default: true)
+#
+# The openai and openai-compatible clients also support:
+#   wire_api: responses                             # Which OpenAI wire protocol to use; Possible values: responses and chat
+#                                                   # Defaults when unset: stock openai (no api_base) -> responses;
+#                                                   # openai with a custom api_base -> chat; openai-compatible -> chat.
+#                                                   # Codex OAuth always uses responses (`wire_api: chat` there is a config error)
+#
+# Patches are selected per wire: `chat_completions` patches only ever touch chat bodies. To patch
+# requests on the responses wire, use the `responses` key on the client `patch` block (same
+# <regex> -> url/body/headers shape as chat_completions):
+#   patch:
+#     responses:
+#       <regex>:
+#         body:
+#           <json>
+# Model patches likewise: the top-level `patch` keys apply to the chat wire only, and a
+# `responses:` sub-key applies to the responses wire only:
+#   models:
+#     - name: xxxx
+#       patch:
+#         responses:
+#           body:
+#             <json>
+# Env override per wire: COYOTE_PATCH_<client>_RESPONSES / COYOTE_PATCH_<client>_CHAT_COMPLETIONS
 __CLIENTS_BLOCK__

assets/functions/tools/web_search_coyote.sh

@@ -23,10 +23,16 @@ set -e
 #   - perplexity:*
 #   - ernie:*
 #   - claude:*                       (Anthropic native web_search server tool)
-#   - openai:gpt-4o-search-preview   (and -mini-; requires an api-key openai
+#   - openai:gpt-4o*/gpt-4.1*/gpt-5*/o3*/o4*
-#                                     client — the codex OAuth path uses the
+#     OpenAI serves web search through two different mechanisms depending on
-#                                     Responses API where this parameter
+#     the wire API the client resolves (the script cannot pick the wire):
-#                                     does not exist)
+#     Chat Completions serves it via `web_search_options` on the chat-only
+#     *-search-preview models, while the Responses API serves it via its
+#     native `web_search` tool on regular models. Both request patches are
+#     exported (request patching is wire-aware, so the resolved wire applies
+#     exactly one) and openai searches run as an attempt chain: the
+#     chat-completions mechanism first, then the Responses mechanism, and
+#     the search fails only when both attempts fail.
 # @env WEB_SEARCH_USE_CURRENT_MODEL=true Prefer the running session's model when it natively supports web search.
 # @env LLM_OUTPUT=/dev/stdout The output path
 
@@ -34,7 +40,7 @@ set -e
 supports_native_search() {
     case "$1" in
     gemini:* | vertexai:gemini-* | perplexity:* | ernie:* | claude:*) return 0 ;;
-    openai:gpt-4o*search-preview*) return 0 ;;
+    openai:gpt-4o* | openai:gpt-4.1* | openai:gpt-5* | openai:o3* | openai:o4*) return 0 ;;
     *) return 1 ;;
     esac
 }
@@ -46,7 +52,8 @@ export_search_patch() {
         COYOTE_PATCH_VERTEXAI_CHAT_COMPLETIONS \
         COYOTE_PATCH_ERNIE_CHAT_COMPLETIONS \
         COYOTE_PATCH_CLAUDE_CHAT_COMPLETIONS \
-        COYOTE_PATCH_OPENAI_CHAT_COMPLETIONS
+        COYOTE_PATCH_OPENAI_CHAT_COMPLETIONS \
+        COYOTE_PATCH_OPENAI_RESPONSES
 
     case "${1%%:*}" in
     gemini)
@@ -65,18 +72,67 @@ export_search_patch() {
         export COYOTE_PATCH_CLAUDE_CHAT_COMPLETIONS='{".*":{"body":{"tools":[{"type":"web_search_20250305","name":"web_search","max_uses":5}]}}}'
         ;;
     openai)
-        # Chat Completions native search exists only on the search-preview
+        # Both patches are exported; request patching is wire-aware, so the
-        # models; the regex scopes the patch so other OpenAI models run
+        # client's resolved wire applies exactly one of them. Each regex
-        # unpatched instead of erroring on an unsupported parameter.
+        # scopes its patch to the models that actually support that
+        # mechanism, so other OpenAI models run unpatched instead of
+        # erroring on an unsupported parameter:
+        #   - Chat Completions native search exists only on the chat-only
+        #     *-search-preview models (`web_search_options`).
+        #   - The Responses API serves search through its native
+        #     `web_search` tool, which only some model families support.
         export COYOTE_PATCH_OPENAI_CHAT_COMPLETIONS='{"gpt-4o.*search-preview.*":{"body":{"web_search_options":{}}}}'
+        export COYOTE_PATCH_OPENAI_RESPONSES='{"(gpt-4o|gpt-4\\.1|gpt-5|o3|o4).*":{"body":{"tools":[{"type":"web_search"}]}}}'
         ;;
     esac
 }
 
+# Maps an openai model to the one used for the chat-completions attempt:
+# Chat Completions web search is served only by the *-search-preview models.
+openai_chat_search_model() {
+    case "${1#openai:}" in
+    gpt-4o*search-preview*) echo "$1" ;;
+    gpt-4o-mini*) echo "openai:gpt-4o-mini-search-preview" ;;
+    *) echo "openai:gpt-4o-search-preview" ;;
+    esac
+}
+
+# Maps an openai model to the one used for the Responses attempt: the
+# *-search-preview models are chat-only and do not exist on /v1/responses,
+# so they map back to their base models.
+openai_responses_search_model() {
+    case "${1#openai:}" in
+    gpt-4o-mini-search-preview*) echo "openai:gpt-4o-mini" ;;
+    gpt-4o*search-preview*) echo "openai:gpt-4o" ;;
+    *) echo "$1" ;;
+    esac
+}
+
+# OpenAI attempt chain: try the chat-completions mechanism first (works when
+# the client's wire is chat); if that fails — e.g. the client resolved the
+# responses wire, where the search-preview models do not exist — retry with
+# the Responses mechanism on a responses-capable model. Fails when both
+# attempts fail.
+# shellcheck disable=SC2154
+run_openai_search() {
+    if coyote -m "$(openai_chat_search_model "$1")" "$argc_query" >>"$LLM_OUTPUT"; then
+        return 0
+    fi
+    echo "web_search: openai chat-completions attempt failed; retrying via the Responses API" >&2
+    coyote -m "$(openai_responses_search_model "$1")" "$argc_query" >>"$LLM_OUTPUT"
+}
+
 # shellcheck disable=SC2154
 run_search() {
     export_search_patch "$1"
+    case "$1" in
+    openai:*)
+        run_openai_search "$1"
+        ;;
+    *)
         coyote -m "$1" "$argc_query" >>"$LLM_OUTPUT"
+        ;;
+    esac
 }
 
 main() {

models.yaml

@@ -351,6 +351,10 @@
         max_tokens: null
         temperature: null
         top_p: null
+      responses:
+        body:
+          temperature: null
+          top_p: null
     max_output_tokens: 100000
     supports_vision: true
     supports_function_calling: true
@@ -370,6 +374,10 @@
         max_tokens: null
         temperature: null
         top_p: null
+      responses:
+        body:
+          temperature: null
+          top_p: null
     max_output_tokens: 100000
     supports_vision: true
     supports_function_calling: true
@@ -429,6 +437,10 @@
         max_tokens: null
         temperature: null
         top_p: null
+      responses:
+        body:
+          temperature: null
+          top_p: null
     max_output_tokens: 100000
     supports_function_calling: true
     reasoning_levels:
@@ -540,6 +552,12 @@
         max_tokens: null
         temperature: null
         top_p: null
+      responses:
+        body:
+          temperature: null
+          top_p: null
+          reasoning:
+            effort: high
     max_output_tokens: 100000
     supports_vision: true
     supports_function_calling: true
@@ -556,6 +574,12 @@
         max_tokens: null
         temperature: null
         top_p: null
+      responses:
+        body:
+          temperature: null
+          top_p: null
+          reasoning:
+            effort: high
     supports_vision: true
     supports_function_calling: true
     system_prompt_prefix: Formatting re-enabled
@@ -571,6 +595,12 @@
         max_tokens: null
         temperature: null
         top_p: null
+      responses:
+        body:
+          temperature: null
+          top_p: null
+          reasoning:
+            effort: high
     max_output_tokens: 100000
     supports_vision: true
     supports_function_calling: true
@@ -6947,9 +6977,9 @@
   - name: deepseek/deepseek-v4-flash
     type: chat
     max_input_tokens: 1048576
-    input_price: 0.0886
+    input_price: 0.084
-    output_price: 0.1772
+    output_price: 0.168
-    cache_read_price: 0.0177
+    cache_read_price: 0.0168
     max_output_tokens: 384000
     supports_function_calling: true
   - name: deepseek/deepseek-v4-flash-0731
@@ -6997,10 +7027,10 @@
   - name: deepseek/deepseek-v4-pro-0813
     type: chat
     max_input_tokens: 1048576
-    input_price: 0.9834
+    input_price: 0.5795
-    output_price: 2.9502
+    output_price: 1.7384
-    cache_read_price: 0.0328
+    cache_read_price: 0.0184
-    max_output_tokens: 384000
+    max_output_tokens: 393216
     supports_function_calling: true
   - name: deepseek/deepseek-v4-pro-0813:batch
     type: chat
@@ -8022,9 +8052,9 @@
   - name: moonshotai/kimi-k3
     type: chat
     max_input_tokens: 1048576
-    input_price: 2.6481
+    input_price: 3.0
-    output_price: 13.2827
+    output_price: 15.0
-    cache_read_price: 0.3026
+    cache_read_price: 0.3
     max_output_tokens: 943718
     supports_vision: true
     supports_function_calling: true
@@ -9405,9 +9435,9 @@
   - name: qwen/qwen3-vl-30b-a3b-instruct
     type: chat
     max_input_tokens: 262144
-    input_price: 0.15
+    input_price: 0.13
-    output_price: 0.6
+    output_price: 0.52
-    max_output_tokens: 16384
+    max_output_tokens: 32768
     supports_vision: true
     supports_function_calling: true
   - name: qwen/qwen3-vl-30b-a3b-thinking
@@ -9716,6 +9746,14 @@
     input_price: 0.65
     output_price: 0.75
     max_output_tokens: 16384
+  - name: stealth/union-alpha
+    type: chat
+    max_input_tokens: 262144
+    input_price: 0.0
+    output_price: 0.0
+    max_output_tokens: 131072
+    supports_vision: true
+    supports_function_calling: true
   - name: stepfun/step-3.5-flash
     type: chat
     max_input_tokens: 262144
@@ -9759,9 +9797,9 @@
   - name: tencent/hy3
     type: chat
     max_input_tokens: 262144
-    input_price: 0.132
+    input_price: 0.0825
-    output_price: 0.528
+    output_price: 0.33
-    cache_read_price: 0.033
+    cache_read_price: 0.0206
     max_output_tokens: 128000
     supports_function_calling: true
   - name: tencent/hy3-preview
@@ -10037,7 +10075,7 @@
     input_price: 1.4
     output_price: 4.4
     cache_read_price: 0.14
-    max_output_tokens: 128000
+    max_output_tokens: 131072
     supports_function_calling: true
   - name: z-ai/glm-5.2:batch
     type: chat
@@ -10142,16 +10180,16 @@
     input_price: 0.15
     output_price: 0.6
     cache_read_price: 0.015
-    max_output_tokens: 943718
+    max_output_tokens: 393216
     supports_vision: true
     supports_function_calling: true
   - name: ~deepseek/deepseek-pro-latest
     type: chat
     max_input_tokens: 1048576
-    input_price: 0.66
+    input_price: 0.5795
-    output_price: 1.98
+    output_price: 1.7384
-    cache_read_price: 0.022
+    cache_read_price: 0.0184
-    max_output_tokens: 384000
+    max_output_tokens: 393216
     supports_function_calling: true
   - name: ~deepseek/deepseek-v4-flash-latest
     type: chat
@@ -10184,9 +10222,9 @@
   - name: ~moonshotai/kimi-latest
     type: chat
     max_input_tokens: 1048576
-    input_price: 2.1
+    input_price: 2.0
-    output_price: 10.95
+    output_price: 11.2
-    cache_read_price: 0.23
+    cache_read_price: 0.232
     max_output_tokens: 943718
     supports_vision: true
     supports_function_calling: true

quirks.yaml

@@ -51,6 +51,10 @@
           max_tokens: null
           temperature: null
           top_p: null
+        responses:
+          body:
+            temperature: null
+            top_p: null
     - match: "o3"
       system_prompt_prefix: Formatting re-enabled
       patch:
@@ -58,6 +62,10 @@
           max_tokens: null
           temperature: null
           top_p: null
+        responses:
+          body:
+            temperature: null
+            top_p: null
     - match: "o3-mini"
       system_prompt_prefix: Formatting re-enabled
       patch:
@@ -65,6 +73,10 @@
           max_tokens: null
           temperature: null
           top_p: null
+        responses:
+          body:
+            temperature: null
+            top_p: null
   models:
     - name: text-embedding-3-large
       type: embedding
@@ -94,6 +106,12 @@
           max_tokens: null
           temperature: null
           top_p: null
+        responses:
+          body:
+            temperature: null
+            top_p: null
+            reasoning:
+              effort: high
     - name: o3-high
       real_name: o3
       max_input_tokens: 200000
@@ -108,6 +126,12 @@
           max_tokens: null
           temperature: null
           top_p: null
+        responses:
+          body:
+            temperature: null
+            top_p: null
+            reasoning:
+              effort: high
     - name: o3-mini-high
       max_output_tokens: 100000
       real_name: o3-mini
@@ -123,6 +147,12 @@
           max_tokens: null
           temperature: null
           top_p: null
+        responses:
+          body:
+            temperature: null
+            top_p: null
+            reasoning:
+              effort: high
     - name: chat-latest
       max_input_tokens: 400000
       max_output_tokens: 128000

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(
@@ -427,7 +429,9 @@ fn build_chat_completions_body(
                         let mut user_parts = vec![];
                         for (index, tool_result) in tool_results.iter().enumerate() {
                             for block in &tool_result.thinking {
-                                assistant_parts.push(converse_reasoning_block(block));
+                                if let Some(part) = converse_reasoning_block(block) {
+                                    assistant_parts.push(part);
+                                }
                             }
                             let round_text = if index == 0 && !text.is_empty() {
                                 Some(text.as_str())
@@ -496,7 +500,9 @@ fn build_chat_completions_body(
                                 chunk_ids.insert(id);
                             }
                             for block in &tool_result.thinking {
-                                assistant_parts.push(converse_reasoning_block(block));
+                                if let Some(part) = converse_reasoning_block(block) {
+                                    assistant_parts.push(part);
+                                }
                             }
                             let round_text = if index == 0 && !text.is_empty() {
                                 Some(text.as_str())
@@ -661,23 +667,26 @@ fn bedrock_tool_result_content(output: &Value) -> Value {
 }
 
 /// Maps a ThinkingBlock (Anthropic tagged shape) to the Converse
-/// reasoningContent union so signed blocks replay verbatim.
+/// reasoningContent union so signed blocks replay verbatim. OpenAI Responses
-fn converse_reasoning_block(block: &ThinkingBlock) -> Value {
+/// reasoning items have no Converse encoding, so they are dropped when the
+/// session moves to Bedrock.
+fn converse_reasoning_block(block: &ThinkingBlock) -> Option<Value> {
     match block {
         ThinkingBlock::Thinking {
             thinking,
             signature,
-        } => json!({
+        } => Some(json!({
             "reasoningContent": {
                 "reasoningText": {
                     "text": thinking,
                     "signature": signature,
                 }
             }
-        }),
+        })),
-        ThinkingBlock::RedactedThinking { data } => json!({
+        ThinkingBlock::RedactedThinking { data } => Some(json!({
             "reasoningContent": { "redactedContent": data }
-        }),
+        })),
+        ThinkingBlock::Reasoning { .. } => None,
     }
 }
 
@@ -1185,6 +1194,32 @@ mod tests {
         }
     }
 
+    #[test]
+    fn skips_openai_reasoning_blocks_in_converse_shape() {
+        let reasoning = ToolResult {
+            call: ToolCall::new(
+                "fs_read".into(),
+                json!({"path": "x"}),
+                Some("tool_A".into()),
+            ),
+            output: json!("ok"),
+            text: None,
+            thinking: vec![ThinkingBlock::Reasoning {
+                id: "rs_1".into(),
+                summary: json!([{ "type": "summary_text", "text": "thinking" }]),
+                encrypted_content: Some("enc123".into()),
+            }],
+        };
+
+        for sequence in [false, true] {
+            let body = build_body_with(vec![reasoning.clone()], "", sequence);
+
+            let content = body["messages"][1]["content"].as_array().unwrap();
+            assert_eq!(content.len(), 1, "body: {body}");
+            assert!(content[0].get("toolUse").is_some(), "body: {body}");
+        }
+    }
+
     #[test]
     fn extract_chat_completions_captures_reasoning_content() {
         let data = json!({

src/client/claude.rs

@@ -407,8 +407,17 @@ pub fn claude_build_chat_completions_body(
                         let mut user_parts = vec![];
                         for (index, tool_result) in tool_results.iter().enumerate() {
                             for block in &tool_result.thinking {
+                                // Only Anthropic thinking blocks replay here;
+                                // Responses reasoning items (and any future
+                                // variant) are dropped.
+                                if matches!(
+                                    block,
+                                    ThinkingBlock::Thinking { .. }
+                                        | ThinkingBlock::RedactedThinking { .. }
+                                ) {
                                     assistant_parts.push(json!(block));
                                 }
+                            }
                             let round_text = if index == 0 && !text.is_empty() {
                                 Some(text.as_str())
                             } else {
@@ -475,8 +484,17 @@ pub fn claude_build_chat_completions_body(
                                 chunk_ids.insert(id);
                             }
                             for block in &tool_result.thinking {
+                                // Only Anthropic thinking blocks replay here;
+                                // Responses reasoning items (and any future
+                                // variant) are dropped.
+                                if matches!(
+                                    block,
+                                    ThinkingBlock::Thinking { .. }
+                                        | ThinkingBlock::RedactedThinking { .. }
+                                ) {
                                     assistant_parts.push(json!(block));
                                 }
+                            }
                             let round_text = if index == 0 && !text.is_empty() {
                                 Some(text.as_str())
                             } else {
@@ -875,6 +893,48 @@ mod tests {
         assert_eq!(messages.len(), 1, "body: {body}");
     }
 
+    #[test]
+    fn replays_only_anthropic_thinking_blocks() {
+        let mixed = ToolResult {
+            call: ToolCall::new(
+                "fs_read".into(),
+                json!({"path": "x"}),
+                Some("toolu_A".into()),
+            ),
+            output: json!("ok"),
+            text: None,
+            thinking: vec![
+                ThinkingBlock::Thinking {
+                    thinking: "hmm".into(),
+                    signature: "sig123".into(),
+                },
+                ThinkingBlock::RedactedThinking {
+                    data: "b64data".into(),
+                },
+                ThinkingBlock::Reasoning {
+                    id: "rs_1".into(),
+                    summary: json!([{ "type": "summary_text", "text": "thinking" }]),
+                    encrypted_content: Some("enc123".into()),
+                },
+            ],
+        };
+
+        for sequence in [false, true] {
+            let body = build_body_with(vec![mixed.clone()], "", sequence, false);
+
+            let content = body["messages"][1]["content"].as_array().unwrap();
+            let types: Vec<_> = content
+                .iter()
+                .map(|block| block["type"].as_str().unwrap())
+                .collect();
+            assert_eq!(
+                types,
+                ["thinking", "redacted_thinking", "tool_use"],
+                "body: {body}"
+            );
+        }
+    }
+
     #[test]
     fn prompt_cache_places_breakpoints() {
         let functions = vec![function_declaration("a"), function_declaration("b")];

src/client/common.rs

@@ -222,23 +222,39 @@ 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,
@@ -272,16 +288,26 @@ 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 {
@@ -293,9 +319,15 @@ 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,
@@ -313,7 +345,9 @@ 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);
@@ -2012,4 +2046,263 @@ mod tests {
             Some("500")
         );
     }
+
+    /// 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 non_map_request_patch_responses_section_is_rejected() {
+        let err = serde_json::from_value::<RequestPatch>(json!({"responses": "bogus"}))
+            .unwrap_err()
+            .to_string();
+
+        assert!(err.contains("expected a map"), "unexpected error: {err}");
+    }
+
+    #[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());
+    }
+
+    /// Pins the silent-ignore contract for a malformed `responses` sub-key:
+    /// model patches are untyped JSON maps and the whole patch layer is
+    /// deliberately lenient — `apply_patch` only reads object-shaped
+    /// `url`/`body`/`headers` keys — so a non-object `responses` sub-key
+    /// degrades to a no-op on the Responses wire (never a request-time
+    /// error, never a partial merge) and stays inert on the Chat wire,
+    /// where the patch's top-level keys still apply normally.
+    #[test]
+    fn malformed_model_patch_responses_subkey_is_silently_ignored() {
+        for malformed in [json!("oops"), json!([{"body": {"store": true}}])] {
+            let model_patch = json!({
+                "body": {"temperature": 0.2},
+                "responses": malformed,
+            });
+            let client = patch_probe("patchprobemalformed", Some(model_patch), None);
+
+            let mut responses_request = wire_request(WireApi::Responses);
+            let before_url = responses_request.url.clone();
+            let before_body = responses_request.body.clone();
+            let before_headers = responses_request.headers.clone();
+            client.patch_request_data(&mut responses_request);
+            assert_eq!(responses_request.url, before_url);
+            assert_eq!(responses_request.body, before_body);
+            assert_eq!(responses_request.headers, before_headers);
+
+            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/message.rs

@@ -188,15 +188,27 @@ pub struct ImageUrl {
     pub url: String,
 }
 
-/// An extended-thinking block returned by Anthropic-protocol models.
+/// An extended-thinking block returned by Anthropic-protocol models or an
-/// Serialized to match the API wire format (`type: thinking` / `type: redacted_thinking`)
+/// OpenAI Responses reasoning item. Serialized to match each API's wire
+/// format (`type: thinking` / `type: redacted_thinking` / `type: reasoning`)
 /// so blocks can be replayed verbatim, signature intact, in subsequent
-/// tool-loop rounds as the API requires.
+/// tool-loop rounds as the APIs require.
 #[derive(Debug, Clone, Deserialize, Serialize)]
 #[serde(tag = "type", rename_all = "snake_case")]
 pub enum ThinkingBlock {
-    Thinking { thinking: String, signature: String },
+    Thinking {
-    RedactedThinking { data: String },
+        thinking: String,
+        signature: String,
+    },
+    RedactedThinking {
+        data: String,
+    },
+    Reasoning {
+        id: String,
+        summary: serde_json::Value,
+        #[serde(default, skip_serializing_if = "Option::is_none")]
+        encrypted_content: Option<String>,
+    },
 }
 
 #[derive(Debug, Clone, Deserialize, Serialize)]
@@ -263,3 +275,87 @@ pub fn extract_system_message(messages: &mut Vec<Message>) -> Option<String> {
 
     None
 }
+
+#[cfg(test)]
+mod tests {
+    use super::*;
+    use serde_json::json;
+
+    #[test]
+    fn old_session_thinking_blocks_still_deserialize() {
+        let json = json!([
+            { "type": "thinking", "thinking": "hmm", "signature": "sig123" },
+            { "type": "redacted_thinking", "data": "b64data" },
+        ]);
+
+        let blocks: Vec<ThinkingBlock> = serde_json::from_value(json.clone()).unwrap();
+
+        assert!(
+            matches!(&blocks[0], ThinkingBlock::Thinking { thinking, signature } if thinking == "hmm" && signature == "sig123")
+        );
+        assert!(
+            matches!(&blocks[1], ThinkingBlock::RedactedThinking { data } if data == "b64data")
+        );
+        assert_eq!(serde_json::to_value(&blocks).unwrap(), json);
+    }
+
+    #[test]
+    fn reasoning_block_round_trips() {
+        let json = json!({
+            "type": "reasoning",
+            "id": "rs_1",
+            "summary": [{ "type": "summary_text", "text": "thinking about it" }],
+            "encrypted_content": "enc123",
+        });
+
+        let block: ThinkingBlock = serde_json::from_value(json.clone()).unwrap();
+
+        assert!(
+            matches!(&block, ThinkingBlock::Reasoning { id, encrypted_content, .. } if id == "rs_1" && encrypted_content.as_deref() == Some("enc123"))
+        );
+        assert_eq!(serde_json::to_value(&block).unwrap(), json);
+    }
+
+    #[test]
+    fn reasoning_block_without_encrypted_content_round_trips() {
+        let json = json!({
+            "type": "reasoning",
+            "id": "rs_1",
+            "summary": [],
+        });
+
+        let block: ThinkingBlock = serde_json::from_value(json.clone()).unwrap();
+
+        assert!(
+            matches!(&block, ThinkingBlock::Reasoning { encrypted_content, .. } if encrypted_content.is_none())
+        );
+        assert_eq!(serde_json::to_value(&block).unwrap(), json);
+    }
+
+    #[test]
+    fn thinking_blocks_round_trip_through_yaml() {
+        let json = json!([
+            { "type": "thinking", "thinking": "hmm", "signature": "sig123" },
+            { "type": "redacted_thinking", "data": "b64data" },
+            {
+                "type": "reasoning",
+                "id": "rs_1",
+                "summary": [{ "type": "summary_text", "text": "thinking about it" }],
+                "encrypted_content": "enc123",
+            },
+            {
+                "type": "reasoning",
+                "id": "rs_2",
+                "summary": [],
+            },
+        ]);
+
+        let blocks: Vec<ThinkingBlock> = serde_json::from_value(json.clone()).unwrap();
+
+        let yaml = serde_yaml::to_string(&blocks).unwrap();
+        assert!(!yaml.contains("encrypted_content: null"));
+
+        let restored: Vec<ThinkingBlock> = serde_yaml::from_str(&yaml).unwrap();
+        assert_eq!(serde_json::to_value(&restored).unwrap(), json);
+    }
+}

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_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"
+        );
+    }
+}

src/client/stream.rs

@@ -215,6 +215,14 @@ impl SseHandler {
         !self.buffer.is_empty() || !self.tool_calls.is_empty() || !self.thinking.is_empty()
     }
 
+    /// Whether visible output (text or tool calls) has been accumulated.
+    /// Unlike [`Self::has_received_content`], thinking blocks do not count:
+    /// a stream truncated before any visible output is still an empty
+    /// response to the caller.
+    pub fn has_received_visible_output(&self) -> bool {
+        !self.buffer.is_empty() || !self.tool_calls.is_empty()
+    }
+
     pub fn abort(&self) -> AbortSignal {
         self.abort_signal.clone()
     }
@@ -544,6 +552,23 @@ mod tests {
         assert!(handler.has_received_content());
     }
 
+    /// Pins the deliberate exclusion: thinking blocks count as received
+    /// content but not as visible output, so a thinking-only stream is
+    /// still an empty response to the caller.
+    #[test]
+    fn thinking_blocks_do_not_count_as_visible_output() {
+        let (mut handler, _rx) = new_handler();
+        handler.thinking_block(ThinkingBlock::Thinking {
+            thinking: "hmm".to_string(),
+            signature: "sig".to_string(),
+        });
+        assert!(handler.has_received_content());
+        assert!(!handler.has_received_visible_output());
+
+        handler.text("hello").unwrap();
+        assert!(handler.has_received_visible_output());
+    }
+
     /// Claude splits usage across events: `message_start` carries the input
     /// and cache counts with a provisional output count, `message_delta`
     /// carries only the final output count. Later non-None fields must win.

src/function/mod.rs

@@ -2576,13 +2576,16 @@ fn polyfill_cmd_name<T: AsRef<Path>>(cmd_name: &str, bin_dir: &[T]) -> String {
     cmd_name
 }
 
-// Polling tools are expected to repeat; recording them would also let them
+// Polling tools are expected to repeat with identical arguments (status probes,
-// break up detection of a real loop in the calls they interleave with.
+// list views, inbox checks); recording them would also let them break up
-const LOOP_TRACKER_EXEMPT_TOOLS: [&str; 4] = [
+// detection of a real loop in the calls they interleave with.
+const LOOP_TRACKER_EXEMPT_TOOLS: [&str; 6] = [
     "job__check",
     "job__list",
     "agent__check",
     "agent__list_running",
+    "agent__task_list",
+    "agent__check_inbox",
 ];
 
 fn is_loop_tracker_exempt(name: &str) -> bool {
@@ -3386,10 +3389,12 @@ mod tests {
             "job__list",
             "agent__check",
             "agent__list_running",
+            "agent__task_list",
+            "agent__check_inbox",
         ]
         .into_iter()
         .collect();
-        assert_eq!(LOOP_TRACKER_EXEMPT_TOOLS.len(), 4);
+        assert_eq!(LOOP_TRACKER_EXEMPT_TOOLS.len(), 6);
         assert_eq!(actual, expected);
     }
 
@@ -3426,6 +3431,29 @@ mod tests {
         assert!(tracker.check_loop(&x).is_some());
     }
 
+    /// Zero-argument polls (`agent__check_inbox`, `agent__task_list`) are
+    /// byte-identical on every call, so the protocol-mandated "check your inbox
+    /// after each round" cadence must never read as a loop — even when the
+    /// polls are back-to-back and well past the repeat threshold.
+    #[test]
+    fn tracker_zero_arg_polls_never_trip_even_when_consecutive() {
+        for name in ["agent__check_inbox", "agent__task_list"] {
+            let mut tracker = ToolCallTracker::default();
+            let poll = call_with_args(name, json!({}));
+            for _ in 0..10 {
+                assert!(
+                    tracker.check_loop(&poll).is_none(),
+                    "{name} must never trip the loop tracker"
+                );
+                tracker.record_call(poll.clone());
+            }
+            assert!(
+                tracker.last_calls.is_empty(),
+                "{name} must not be recorded in the call history"
+            );
+        }
+    }
+
     #[test]
     fn tracker_non_exempt_behavior_unchanged() {
         let mut tracker = ToolCallTracker::default();