antigravity harness server - support streaming

[joycel-github]

Problem statement

Antigravity harness currently has slow TTFT for Text / Thought output.

The harness currently buffers contiguous text/thought chunks and only emits after the block completes. This makes the content boundary clear for downstream display code, but it also means AX cannot render the first token until the whole buffered block is done.

Desired behavior:

• emit the first visible output as soon as the model stream produces it
• preserve the difference between answer text and thought-summary text
• keep final/durable content semantics correct
• avoid a broad protocol redesign

Proposal

Add explicit streaming delta content types:

• TextDeltaContent
• ThoughtSummaryDeltaContent

These are modeled after the streaming primitives TextDelta and ThoughtSummaryDelta in google-genai.

Streaming semantics

The harness should not infer sentence boundaries.

Instead, deltas are ordered append-only chunks for the current contiguous output run. A delta run is complete when:

• the next delta has a different content kind
• the role changes
• a non-delta output arrives, such as tool call/tool result
• the stream ends

Responsibilities:

• Harness server emits deltas immediately and preserves order.
• Controller accumulates adjacent deltas with the same role/kind for durable logs/history.
• Display renders deltas immediately and switches formatting when role/kind changes.

Implementation tasks

1. Proto

   • Add TextDeltaContent and ThoughtSummaryDeltaContent, modeled after Antigravity SDK primitives.
   • Add text_delta and thought_summary_delta to Content.

2. Antigravity harness

   • Emit text_delta / thought_summary_delta as chunks arrive.
   • Stop waiting for the full contiguous text/thought block before yielding.

3. Controller

   • Accept delta content in stream handling.
   • Accumulate adjacent deltas into durable text/thought output where needed.
   • Flush accumulation on role change, kind change, non-delta output, or stream end.

4. Display / clients

   • Render text_delta as streamed assistant text.
   • Render thought_summary_delta as streamed thought-summary text.
   • Add handling for the new delta types wherever content variants are switched on.
     - Note Display / clients side are reasonable for formatting

[rakyll]

We can move this to v0.3.0 milestone.

[rakyll]

TextDeltaContent and ThoughtSummaryDeltaContent are not Interactions proto compatible. We need to come back at this issue in v0.3.0 after we introduce Interactions steps to the proto and make a cleanup.

[joycel-github]

discussed offline, we will re-base to Interactions proto when it's ready. Descoped from milestone 0.2.0