Enable local image prompts without breaking text-only CLI flows

The Rust CLI now recognizes explicit local image references in prompt text,
encodes supported image files as base64, and serializes mixed text/image
content blocks for the API. The request conversion path was kept narrow so
existing runtime/session structures remain stable while prompt mode and user
text conversion gain multimodal support.

Constraint: Must support PNG, JPG/JPEG, GIF, and WebP without adding broad runtime abstractions
Constraint: Existing text-only prompt behavior and API tool flows must keep working unchanged
Rejected: Add only explicit --image CLI flags | does not satisfy auto-detect image refs in prompt text
Rejected: Persist native image blocks in runtime session model | broader refactor than needed for prompt support
Confidence: high
Scope-risk: moderate
Reversibility: clean
Directive: Keep image parsing scoped to outbound user prompt adaptation unless session persistence truly needs multimodal history
Tested: cargo fmt --all; cargo clippy --workspace --all-targets -- -D warnings; cargo test --workspace
Not-tested: Live remote multimodal request against Anthropic API

rust/crates/api/src/lib.rs

@@ -11,7 +11,7 @@ pub use error::ApiError;
 pub use sse::{parse_frame, SseParser};
 pub use types::{
     ContentBlockDelta, ContentBlockDeltaEvent, ContentBlockStartEvent, ContentBlockStopEvent,
-    InputContentBlock, InputMessage, MessageDelta, MessageDeltaEvent, MessageRequest,
+    ImageSource, InputContentBlock, InputMessage, MessageDelta, MessageDeltaEvent, MessageRequest,
     MessageResponse, MessageStartEvent, MessageStopEvent, OutputContentBlock, StreamEvent,
     ToolChoice, ToolDefinition, ToolResultContentBlock, Usage,
 };

rust/crates/api/src/types.rs

@@ -64,6 +64,9 @@ pub enum InputContentBlock {
     Text {
         text: String,
     },
+    Image {
+        source: ImageSource,
+    },
     ToolUse {
         id: String,
         name: String,
@@ -77,6 +80,14 @@ pub enum InputContentBlock {
     },
 }
 
+#[derive(Debug, Clone, PartialEq, Eq, Serialize, Deserialize)]
+pub struct ImageSource {
+    #[serde(rename = "type")]
+    pub kind: String,
+    pub media_type: String,
+    pub data: String,
+}
+
 #[derive(Debug, Clone, PartialEq, Serialize, Deserialize)]
 #[serde(tag = "type", rename_all = "snake_case")]
 pub enum ToolResultContentBlock {