Expose structured thinking without polluting normal assistant output

Extended thinking needed to travel end-to-end through the API,
runtime, and CLI so the client can request a thinking budget,
preserve streamed reasoning blocks, and present them in a
collapsed text-first form. The implementation keeps thinking
strictly opt-in, adds a session-local toggle, and reuses the
existing flag/slash-command/reporting surfaces instead of
introducing a new UI layer.

Constraint: Existing non-thinking text/tool flows had to remain backward compatible by default
Constraint: Terminal UX needed a lightweight collapsed representation rather than an interactive TUI widget
Rejected: Heuristic CLI-only parsing of reasoning text | brittle against structured stream payloads
Rejected: Expanded raw thinking output by default | too noisy for normal assistant responses
Confidence: medium
Scope-risk: moderate
Reversibility: clean
Directive: Keep thinking blocks structurally separate from answer text unless the upstream API contract changes
Tested: cargo fmt --all; cargo clippy --workspace --all-targets -- -D warnings; cargo test -q
Not-tested: Live upstream thinking payloads against the production API contract

rust/crates/api/src/client.rs

@@ -912,6 +912,7 @@ mod tests {
             system: None,
             tools: None,
             tool_choice: None,
+            thinking: None,
             stream: false,
         };
 

rust/crates/api/src/lib.rs

@@ -13,5 +13,5 @@ pub use types::{
     ContentBlockDelta, ContentBlockDeltaEvent, ContentBlockStartEvent, ContentBlockStopEvent,
     InputContentBlock, InputMessage, MessageDelta, MessageDeltaEvent, MessageRequest,
     MessageResponse, MessageStartEvent, MessageStopEvent, OutputContentBlock, StreamEvent,
-    ToolChoice, ToolDefinition, ToolResultContentBlock, Usage,
+    ThinkingConfig, ToolChoice, ToolDefinition, ToolResultContentBlock, Usage,
 };

rust/crates/api/src/types.rs

@@ -12,6 +12,8 @@ pub struct MessageRequest {
     pub tools: Option<Vec<ToolDefinition>>,
     #[serde(skip_serializing_if = "Option::is_none")]
     pub tool_choice: Option<ToolChoice>,
+    #[serde(skip_serializing_if = "Option::is_none")]
+    pub thinking: Option<ThinkingConfig>,
     #[serde(default, skip_serializing_if = "std::ops::Not::not")]
     pub stream: bool,
 }
@@ -24,6 +26,23 @@ impl MessageRequest {
     }
 }
 
+#[derive(Debug, Clone, PartialEq, Eq, Serialize, Deserialize)]
+pub struct ThinkingConfig {
+    #[serde(rename = "type")]
+    pub kind: String,
+    pub budget_tokens: u32,
+}
+
+impl ThinkingConfig {
+    #[must_use]
+    pub fn enabled(budget_tokens: u32) -> Self {
+        Self {
+            kind: "enabled".to_string(),
+            budget_tokens,
+        }
+    }
+}
+
 #[derive(Debug, Clone, PartialEq, Serialize, Deserialize)]
 pub struct InputMessage {
     pub role: String,
@@ -130,6 +149,11 @@ pub enum OutputContentBlock {
     Text {
         text: String,
     },
+    Thinking {
+        thinking: String,
+        #[serde(default, skip_serializing_if = "Option::is_none")]
+        signature: Option<String>,
+    },
     ToolUse {
         id: String,
         name: String,
@@ -189,6 +213,8 @@ pub struct ContentBlockDeltaEvent {
 #[serde(tag = "type", rename_all = "snake_case")]
 pub enum ContentBlockDelta {
     TextDelta { text: String },
+    ThinkingDelta { thinking: String },
+    SignatureDelta { signature: String },
     InputJsonDelta { partial_json: String },
 }
 

rust/crates/api/tests/client_integration.rs

@@ -258,6 +258,7 @@ async fn live_stream_smoke_test() {
             system: None,
             tools: None,
             tool_choice: None,
+            thinking: None,
             stream: false,
         })
         .await
@@ -438,6 +439,7 @@ fn sample_request(stream: bool) -> MessageRequest {
             }),
         }]),
         tool_choice: Some(ToolChoice::Auto),
+        thinking: None,
         stream,
     }
 }