rob thijssen
df0abfe4d4
All checks were successful
build-prerelease / Resolve version stamps (push) Successful in 34s
CI / Format (push) Successful in 37s
CI / Clippy (push) Successful in 2m33s
CI / Test (push) Successful in 5m4s
CI / Build cortex SRPM (push) Has been skipped
CI / Build neuron SRPM (push) Has been skipped
CI / Publish cortex to COPR (push) Has been skipped
CI / Publish neuron to COPR (push) Has been skipped
CI / Bump version in source (push) Has been skipped
build-prerelease / Build neuron-blackwell (push) Successful in 6m2s
build-prerelease / Build neuron-ampere (push) Successful in 7m49s
build-prerelease / Build neuron-ada (push) Successful in 5m27s
build-prerelease / Build cortex binary (push) Successful in 4m16s
build-prerelease / Package cortex RPM (push) Successful in 1m19s
build-prerelease / Package helexa-neuron-ampere RPM (push) Successful in 3m2s
build-prerelease / Package helexa-neuron-ada RPM (push) Successful in 3m10s
build-prerelease / Package helexa-neuron-blackwell RPM (push) Successful in 3m47s
build-prerelease / Publish to rpm.lair.cafe (unstable) (push) Successful in 1m2s
Stage 5. Zed clipboard/DnD images get forwarded as OpenAI
content-array messages on user turns.
- New MessageContent::MultiPart variant + MessagePart (Text|Image)
+ ImageData struct (mime_type, base64 data, optional uri).
- flatten_prompt now produces structured content: collapses to
Text when every block is text (some upstreams treat array-form
as vision-only and refuse on text-only models), otherwise
produces MultiPart preserving block order.
- OpenAI encoder emits `[{type:"text",text:…}, {type:"image_url",
image_url:{url:"data:{mime};base64,{data}"}}]` for MultiPart user
messages. Data URIs are used over remote `uri` because they
round-trip through every upstream we care about.
- prompt_capabilities.image = true at initialize so Zed actually
sends image blocks.
- compaction estimates ~512 tokens per image (the middle of the
Qwen3-VL / OpenAI detail range) so the budget tracker doesn't
pretend images are free.
- session/load replays image-bearing user turns by surfacing the
text parts verbatim and rendering each image as a "[image: {mime}
({n} bytes)]" placeholder chunk — Zed can show the prior text
context even though re-uploading the bytes through ACP isn't
meaningful for resume.
- 4 new tests: flatten produces MultiPart in block order, image-only
prompts still flatten to MultiPart, encoder emits the correct
array shape, text-only encoding stays as the string form.
Co-Authored-By: Claude Opus 4.7 <noreply@anthropic.com>