feat: show ETA on prefill progress bar

Track when prefill starts via performance.now() and extrapolate
remaining time from observed tokens/sec. Displays "~Xs remaining"
(or "~Xm Ys remaining" for longer prompts) next to the percentage.

Co-Authored-By: Claude Opus 4.6 <noreply@anthropic.com>

dashboard/src/lib/components/PrefillProgressBar.svelte

@@ -14,6 +14,21 @@
       : 0,
   );
 
+  const etaText = $derived.by(() => {
+    if (progress.processed <= 0 || progress.total <= 0) return null;
+    const elapsedMs = performance.now() - progress.startedAt;
+    if (elapsedMs < 200) return null; // need a minimum sample window
+    const tokensPerMs = progress.processed / elapsedMs;
+    const remainingTokens = progress.total - progress.processed;
+    const remainingMs = remainingTokens / tokensPerMs;
+    const remainingSec = Math.ceil(remainingMs / 1000);
+    if (remainingSec <= 0) return null;
+    if (remainingSec < 60) return `~${remainingSec}s remaining`;
+    const mins = Math.floor(remainingSec / 60);
+    const secs = remainingSec % 60;
+    return `~${mins}m ${secs}s remaining`;
+  });
+
   function formatTokenCount(count: number | undefined): string {
     if (count == null) return "0";
     if (count >= 1000) {
@@ -40,8 +55,11 @@
       style="width: {percentage}%"
     ></div>
   </div>
-  <div class="text-right text-xs text-exo-light-gray/70 mt-0.5 font-mono">
-    {percentage}%
+  <div
+    class="flex items-center justify-between text-xs text-exo-light-gray/70 mt-0.5 font-mono"
+  >
+    <span>{etaText ?? ""}</span>
+    <span>{percentage}%</span>
   </div>
 </div>
 

dashboard/src/lib/stores/app.svelte.ts

@@ -276,6 +276,8 @@ export interface TokenData {
 export interface PrefillProgress {
   processed: number;
   total: number;
+  /** Timestamp (performance.now()) when prefill started. */
+  startedAt: number;
 }
 
 export interface Message {
@@ -2420,6 +2422,7 @@ class AppStore {
             this.prefillProgress = {
               processed: inner.processed_tokens,
               total: inner.total_tokens,
+              startedAt: this.prefillProgress?.startedAt ?? performance.now(),
             };
           },
         },

src/exo/master/adapters/responses.py

@@ -31,6 +31,7 @@ from exo.shared.types.openai_responses import (
     ResponseOutputText,
     ResponsesRequest,
     ResponsesResponse,
+    ResponsesStreamEvent,
     ResponseTextDeltaEvent,
     ResponseTextDoneEvent,
     ResponseUsage,
@@ -38,6 +39,11 @@ from exo.shared.types.openai_responses import (
 from exo.shared.types.text_generation import InputMessage, TextGenerationTaskParams
 
 
+def _format_sse(event: ResponsesStreamEvent) -> str:
+    """Format a streaming event as an SSE message."""
+    return f"event: {event.type}\ndata: {event.model_dump_json()}\n\n"
+
+
 def _extract_content(content: str | list[ResponseContentPart]) -> str:
     """Extract plain text from a content field that may be a string or list of parts."""
     if isinstance(content, str):
@@ -219,13 +225,13 @@ async def generate_responses_stream(
     created_event = ResponseCreatedEvent(
         sequence_number=next(seq), response=initial_response
     )
-    yield f"event: response.created\ndata: {created_event.model_dump_json()}\n\n"
+    yield _format_sse(created_event)
 
     # response.in_progress
     in_progress_event = ResponseInProgressEvent(
         sequence_number=next(seq), response=initial_response
     )
-    yield f"event: response.in_progress\ndata: {in_progress_event.model_dump_json()}\n\n"
+    yield _format_sse(in_progress_event)
 
     # response.output_item.added
     initial_item = ResponseMessageItem(
@@ -236,7 +242,7 @@ async def generate_responses_stream(
     item_added = ResponseOutputItemAddedEvent(
         sequence_number=next(seq), output_index=0, item=initial_item
     )
-    yield f"event: response.output_item.added\ndata: {item_added.model_dump_json()}\n\n"
+    yield _format_sse(item_added)
 
     # response.content_part.added
     initial_part = ResponseOutputText(text="")
@@ -247,7 +253,7 @@ async def generate_responses_stream(
         content_index=0,
         part=initial_part,
     )
-    yield f"event: response.content_part.added\ndata: {part_added.model_dump_json()}\n\n"
+    yield _format_sse(part_added)
 
     accumulated_text = ""
     function_call_items: list[ResponseFunctionCallItem] = []
@@ -281,7 +287,7 @@ async def generate_responses_stream(
                     output_index=next_output_index,
                     item=fc_item,
                 )
-                yield f"event: response.output_item.added\ndata: {fc_added.model_dump_json()}\n\n"
+                yield _format_sse(fc_added)
 
                 # response.function_call_arguments.delta
                 args_delta = ResponseFunctionCallArgumentsDeltaEvent(
@@ -290,7 +296,7 @@ async def generate_responses_stream(
                     output_index=next_output_index,
                     delta=tool.arguments,
                 )
-                yield f"event: response.function_call_arguments.delta\ndata: {args_delta.model_dump_json()}\n\n"
+                yield _format_sse(args_delta)
 
                 # response.function_call_arguments.done
                 args_done = ResponseFunctionCallArgumentsDoneEvent(
@@ -300,7 +306,7 @@ async def generate_responses_stream(
                     name=tool.name,
                     arguments=tool.arguments,
                 )
-                yield f"event: response.function_call_arguments.done\ndata: {args_done.model_dump_json()}\n\n"
+                yield _format_sse(args_done)
 
                 # response.output_item.done
                 fc_done_item = ResponseFunctionCallItem(
@@ -315,7 +321,7 @@ async def generate_responses_stream(
                     output_index=next_output_index,
                     item=fc_done_item,
                 )
-                yield f"event: response.output_item.done\ndata: {fc_item_done.model_dump_json()}\n\n"
+                yield _format_sse(fc_item_done)
 
                 function_call_items.append(fc_done_item)
                 next_output_index += 1
@@ -331,7 +337,7 @@ async def generate_responses_stream(
             content_index=0,
             delta=chunk.text,
         )
-        yield f"event: response.output_text.delta\ndata: {delta_event.model_dump_json()}\n\n"
+        yield _format_sse(delta_event)
 
     # response.output_text.done
     text_done = ResponseTextDoneEvent(
@@ -341,7 +347,7 @@ async def generate_responses_stream(
         content_index=0,
         text=accumulated_text,
     )
-    yield f"event: response.output_text.done\ndata: {text_done.model_dump_json()}\n\n"
+    yield _format_sse(text_done)
 
     # response.content_part.done
     final_part = ResponseOutputText(text=accumulated_text)
@@ -352,7 +358,7 @@ async def generate_responses_stream(
         content_index=0,
         part=final_part,
     )
-    yield f"event: response.content_part.done\ndata: {part_done.model_dump_json()}\n\n"
+    yield _format_sse(part_done)
 
     # response.output_item.done
     final_message_item = ResponseMessageItem(
@@ -363,7 +369,7 @@ async def generate_responses_stream(
     item_done = ResponseOutputItemDoneEvent(
         sequence_number=next(seq), output_index=0, item=final_message_item
     )
-    yield f"event: response.output_item.done\ndata: {item_done.model_dump_json()}\n\n"
+    yield _format_sse(item_done)
 
     # Create usage from usage data if available
     usage = None
@@ -388,4 +394,4 @@ async def generate_responses_stream(
     completed_event = ResponseCompletedEvent(
         sequence_number=next(seq), response=final_response
     )
-    yield f"event: response.completed\ndata: {completed_event.model_dump_json()}\n\n"
+    yield _format_sse(completed_event)