fix(#5626 #5832): handle multiple content chunks & images better (#5839)

Co-authored-by: Pradeepta Dash <pradeepta@exceeds.ai>

crates/goose/src/providers/formats/anthropic.rs

@@ -2,6 +2,7 @@ use crate::conversation::message::{Message, MessageContent};
 use crate::model::ModelConfig;
 use crate::providers::base::Usage;
 use crate::providers::errors::ProviderError;
+use crate::providers::utils::{convert_image, ImageFormat};
 use anyhow::{anyhow, Result};
 use rmcp::model::{object, CallToolRequestParam, ErrorCode, ErrorData, JsonObject, Role, Tool};
 use rmcp::object as json_object;
@@ -106,7 +107,9 @@ pub fn format_messages(messages: &[Message]) -> Vec<Value> {
                         DATA_FIELD: redacted.data
                     }));
                 }
-                MessageContent::Image(_) => continue, // Anthropic doesn't support image content yet
+                MessageContent::Image(image) => {
+                    content.push(convert_image(image, &ImageFormat::Anthropic));
+                }
                 MessageContent::FrontendToolRequest(tool_request) => {
                     if let Ok(tool_call) = &tool_request.tool_call {
                         content.push(json!({

crates/goose/src/providers/formats/openai.rs

@@ -63,25 +63,22 @@ pub fn format_messages(messages: &[Message], image_format: &ImageFormat) -> Vec<
         });
 
         let mut output = Vec::new();
+        let mut content_array = Vec::new();
+        let mut text_array = Vec::new();
 
         for content in &message.content {
             match content {
                 MessageContent::Text(text) => {
                     if !text.text.is_empty() {
-                        // Check for image paths in the text
                         if let Some(image_path) = detect_image_path(&text.text) {
-                            // Try to load and convert the image
                             if let Ok(image) = load_image_file(image_path) {
-                                converted["content"] = json!([
-                                    {"type": "text", "text": text.text},
-                                    convert_image(&image, image_format)
-                                ]);
+                                content_array.push(json!({"type": "text", "text": text.text}));
+                                content_array.push(convert_image(&image, image_format));
                             } else {
-                                // If image loading fails, just use the text
-                                converted["content"] = json!(text.text);
+                                text_array.push(text.text.clone());
                             }
                         } else {
-                            converted["content"] = json!(text.text);
+                            text_array.push(text.text.clone());
                         }
                     }
                 }
@@ -205,8 +202,7 @@ pub fn format_messages(messages: &[Message], image_format: &ImageFormat) -> Vec<
                     // Skip tool confirmation requests
                 }
                 MessageContent::Image(image) => {
-                    // Handle direct image content
-                    converted["content"] = json!([convert_image(image, image_format)]);
+                    content_array.push(convert_image(image, image_format));
                 }
                 MessageContent::FrontendToolRequest(request) => match &request.tool_call {
                     Ok(tool_call) => {
@@ -244,9 +240,16 @@ pub fn format_messages(messages: &[Message], image_format: &ImageFormat) -> Vec<
             }
         }
 
+        if !content_array.is_empty() {
+            converted["content"] = json!(content_array);
+        } else if !text_array.is_empty() {
+            converted["content"] = json!(text_array.join("\n"));
+        }
+
         if converted.get("content").is_some() || converted.get("tool_calls").is_some() {
             output.insert(0, converted);
         }
+
         messages_spec.extend(output);
     }
 
@@ -1230,6 +1233,23 @@ mod tests {
         Ok(())
     }
 
+    #[test]
+    fn test_format_messages_multiple_text_blocks() -> anyhow::Result<()> {
+        let message = Message::user()
+            .with_text("--- Resource: file:///test.md ---\n# Test\n\n---\n")
+            .with_text(" What is in the file?");
+
+        let spec = format_messages(&[message], &ImageFormat::OpenAi);
+
+        assert_eq!(spec.len(), 1);
+        assert_eq!(spec[0]["role"], "user");
+        assert_eq!(
+            spec[0]["content"],
+            "--- Resource: file:///test.md ---\n# Test\n\n---\n\n What is in the file?"
+        );
+        Ok(())
+    }
+
     #[test]
     fn test_create_request_gpt_4o() -> anyhow::Result<()> {
         // Test default medium reasoning effort for O3 model