feat: add image support across all endpoints (responses, completions, gemini)

src/api/util.rs

@@ -4,9 +4,12 @@ use axum::{
     http::StatusCode,
     response::{sse::Event, IntoResponse, Json},
 };
+use base64::Engine;
 use std::time::{SystemTime, UNIX_EPOCH};
+use tracing::warn;
 
 use super::types::{ErrorDetail, ErrorResponse};
+use crate::proto::ImageData;
 
 pub(crate) fn err_response(
     status: StatusCode,
@@ -34,3 +37,55 @@ pub(crate) fn responses_sse_event(event_type: &str, data: serde_json::Value) ->
         .event(event_type)
         .data(serde_json::to_string(&data).unwrap())
 }
+
+// ─── Image extraction ────────────────────────────────────────────────────────
+
+/// Parse a base64 data URI like `data:image/png;base64,iVBOR...` into ImageData.
+/// Also accepts plain URLs (returns None — we only support inline base64).
+pub(crate) fn parse_data_uri(url: &str) -> Option<ImageData> {
+    // data:image/png;base64,<data>
+    let rest = url.strip_prefix("data:")?;
+    let (header, b64) = rest.split_once(";base64,")?;
+    let mime_type = header.to_string();
+
+    match base64::engine::general_purpose::STANDARD.decode(b64) {
+        Ok(data) => {
+            tracing::info!(mime = %mime_type, size = data.len(), "Decoded inline image");
+            Some(ImageData { mime_type, data })
+        }
+        Err(e) => {
+            warn!(error = %e, "Failed to decode base64 image data");
+            None
+        }
+    }
+}
+
+/// Extract an image from an OpenAI content array item.
+///
+/// Supports:
+/// - Chat Completions: `{"type": "image_url", "image_url": {"url": "data:..."}}`
+/// - Responses API:    `{"type": "input_image", "image_url": "data:..."}` or
+///                     `{"type": "input_image", "url": "data:..."}`
+pub(crate) fn extract_image_from_content(item: &serde_json::Value) -> Option<ImageData> {
+    let item_type = item["type"].as_str().unwrap_or("");
+
+    match item_type {
+        // OpenAI Chat Completions format
+        "image_url" => {
+            let url = item["image_url"]["url"].as_str()?;
+            parse_data_uri(url)
+        }
+        // OpenAI Responses API format
+        "input_image" => {
+            let url = item["image_url"].as_str()
+                .or_else(|| item["url"].as_str())?;
+            parse_data_uri(url)
+        }
+        _ => None,
+    }
+}
+
+/// Extract the first image from a content array (Value::Array of content parts).
+pub(crate) fn extract_first_image(content: &serde_json::Value) -> Option<ImageData> {
+    content.as_array()?.iter().find_map(extract_image_from_content)
+}