fix: streaming robustness — OpenAI parsing, error detection, reasoning content

Improves SSE parsing with raw JSON error detection, HTML response detection (for misconfigured endpoints), thinking/reasoning content from provider-specific delta fields, #[serde(default)] on streaming types for lenient deserialization, compact session boundary guard, and /team slash command. Adds install.sh convenience script.

Author: TheArchitectit

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

@@ -505,10 +505,12 @@ impl StreamState {
         }
 
         for choice in chunk.choices {
+            // Handle reasoning/thinking from various provider fields
             if let Some(reasoning) = choice
                 .delta
                 .reasoning_content
                 .filter(|value| !value.is_empty())
+                .or(choice.delta.thinking.and_then(|t| t.content).filter(|value| !value.is_empty()))
             {
                 if !self.thinking_started {
                     self.thinking_started = true;
@@ -736,6 +738,7 @@ impl ToolCallState {
 
 #[derive(Debug, Deserialize)]
 struct ChatCompletionResponse {
+    #[serde(default)]
     id: String,
     model: String,
     choices: Vec<ChatChoice>,
@@ -806,6 +809,7 @@ impl OpenAiUsage {
 
 #[derive(Debug, Deserialize)]
 struct ChatCompletionChunk {
+    #[serde(default)]
     id: String,
     #[serde(default)]
     model: Option<String>,
@@ -817,6 +821,7 @@ struct ChatCompletionChunk {
 
 #[derive(Debug, Deserialize)]
 struct ChunkChoice {
+    #[serde(default)]
     delta: ChunkDelta,
     #[serde(default)]
     finish_reason: Option<String>,
@@ -826,12 +831,21 @@ struct ChunkChoice {
 struct ChunkDelta {
     #[serde(default)]
     content: Option<String>,
+    /// Some providers (GLM, DeepSeek) emit reasoning in `reasoning_content`
     #[serde(default)]
     reasoning_content: Option<String>,
+    #[serde(default)]
+    thinking: Option<ThinkingDelta>,
     #[serde(default, deserialize_with = "deserialize_null_as_empty_vec")]
     tool_calls: Vec<DeltaToolCall>,
 }
 
+#[derive(Debug, Default, Deserialize)]
+struct ThinkingDelta {
+    #[serde(default)]
+    content: Option<String>,
+}
+
 #[derive(Debug, Deserialize)]
 struct DeltaToolCall {
     #[serde(default)]
@@ -1455,7 +1469,50 @@ fn parse_sse_frame(
             data_lines.push(data.trim_start());
         }
     }
+    // If no SSE data lines found, check if the entire frame is raw JSON (error or otherwise)
     if data_lines.is_empty() {
+        // Detect raw JSON error response (not SSE-framed)
+        if let Ok(raw) = serde_json::from_str::<serde_json::Value>(trimmed) {
+            if let Some(err_obj) = raw.get("error") {
+                let msg = err_obj
+                    .get("message")
+                    .and_then(|m| m.as_str())
+                    .unwrap_or("provider returned an error")
+                    .to_string();
+                let code = err_obj
+                    .get("code")
+                    .and_then(serde_json::Value::as_u64)
+                    .map(|c| c as u16);
+                let status = reqwest::StatusCode::from_u16(code.unwrap_or(500))
+                    .unwrap_or(reqwest::StatusCode::INTERNAL_SERVER_ERROR);
+                return Err(ApiError::Api {
+                    status,
+                    error_type: err_obj
+                        .get("type")
+                        .and_then(|t| t.as_str())
+                        .map(str::to_owned),
+                    message: Some(msg),
+                    request_id: None,
+                    body: trimmed.chars().take(500).collect(),
+                    retryable: false,
+                    suggested_action: suggested_action_for_status(status),
+                    retry_after: None,
+                });
+            }
+        }
+        // Detect HTML responses
+        if trimmed.starts_with('<') || trimmed.starts_with("<!") {
+            return Err(ApiError::Api {
+                status: reqwest::StatusCode::BAD_REQUEST,
+                error_type: Some("invalid_response".to_string()),
+                message: Some("provider returned HTML instead of JSON (check endpoint URL)".to_string()),
+                request_id: None,
+                body: trimmed.chars().take(200).collect(),
+                retryable: false,
+                suggested_action: Some("verify the API endpoint URL is correct".to_string()),
+                retry_after: None,
+            });
+        }
         return Ok(None);
     }
     let payload = data_lines.join("\n");
@@ -1492,6 +1549,20 @@ fn parse_sse_frame(
             });
         }
     }
+    // Detect HTML or other non-JSON responses early for better error messages
+    let trimmed_payload = payload.trim();
+    if trimmed_payload.starts_with('<') || trimmed_payload.starts_with("<!") {
+        return Err(ApiError::Api {
+            status: reqwest::StatusCode::BAD_REQUEST,
+            error_type: Some("invalid_response".to_string()),
+            message: Some("provider returned HTML instead of JSON (check endpoint URL)".to_string()),
+            request_id: None,
+            body: payload.chars().take(200).collect(),
+            retryable: false,
+            suggested_action: Some("verify the API endpoint URL is correct".to_string()),
+            retry_after: None,
+        });
+    }
     serde_json::from_str::<ChatCompletionChunk>(&payload)
         .map(Some)
         .map_err(|error| ApiError::json_deserialize(provider, model, &payload, error))

rust/crates/commands/src/lib.rs

@@ -1472,6 +1472,7 @@ pub fn validate_slash_command_input(
         }
         "plan" => SlashCommand::Plan { mode: remainder },
         "review" => SlashCommand::Review { scope: remainder },
+        "team" => SlashCommand::Team { action: remainder },
         "tasks" => SlashCommand::Tasks { args: remainder },
         "theme" => SlashCommand::Theme { name: remainder },
         "voice" => SlashCommand::Voice { mode: remainder },

rust/crates/runtime/src/compact.rs

@@ -128,7 +128,7 @@ pub fn compact_session(session: &Session, config: CompactionConfig) -> Compactio
         // is NOT an assistant message that contains a ToolUse block (i.e. the
         // pair is actually broken at the boundary).
         loop {
-            if k == 0 || k <= compacted_prefix_len {
+            if k == 0 || k <= compacted_prefix_len || k >= session.messages.len() {
                 break;
             }
             let first_preserved = &session.messages[k];

rust/scripts/install.sh

@@ -0,0 +1,11 @@
+#!/bin/bash
+set -e
+
+# Build the release binary
+cargo build --release
+
+# Link to ~/.local/bin
+mkdir -p "$HOME/.local/bin"
+ln -sf "$(pwd)/target/release/claw" "$HOME/.local/bin/claw"
+
+echo "✓ Claw installed to ~/.local/bin/claw"