lmstudio: Fix context wheel by including token usage in streaming responses - #57861
Merged
bennetbo merged 4 commits intoJul 10, 2026
Conversation
…ponses Add stream_options with include_usage: true to the ChatCompletionRequest so LM Studio returns token usage in streaming responses. Previously, without this field, the API never included usage data, so the context wheel had nothing to display. Also move usage handling in the event mapper to run before the empty-choices guard. OpenAI-compatible servers send the final usage summary as a chunk with an empty choices array, so the old guard was discarding usage data instead of emitting a UsageUpdate event. Fixes zed-industries#53790
…ponses Add stream_options with include_usage: true to the ChatCompletionRequest so LM Studio returns token usage in streaming responses. Previously, without this field, the API never included usage data, so the context wheel had nothing to display. Also move usage handling in the event mapper to run before the empty-choices guard. OpenAI-compatible servers send the final usage summary as a chunk with an empty choices array, so the old guard was discarding usage data instead of emitting a UsageUpdate event. Fixes zed-industries#53790
…ub.com/GabrieleAncillai/zed into lmstudio-fix-context-wheel-token-usage
|
We require contributors to sign our Contributor License Agreement, and we don't have @gancillai-sofka on file. You can sign our CLA at https://zed.dev/cla. Once you've signed, post a comment here that says '@cla-bot check'. |
zed-community-bot
Bot
added
the
first contribution
Contributor
Author
|
@cla-bot check |
|
We require contributors to sign our Contributor License Agreement, and we don't have @gancillai-sofka on file. You can sign our CLA at https://zed.dev/cla. Once you've signed, post a comment here that says '@cla-bot check'. |
|
The cla-bot has been summoned, and re-checked this pull request! |
Contributor
Author
|
@cla-bot check |
|
We require contributors to sign our Contributor License Agreement, and we don't have @gancillai-sofka on file. You can sign our CLA at https://zed.dev/cla. Once you've signed, post a comment here that says '@cla-bot check'. |
|
The cla-bot has been summoned, and re-checked this pull request! |
Contributor
Author
|
@cla-bot check |
cla-bot
Bot
added
the
cla-signed
|
The cla-bot has been summoned, and re-checked this pull request! |
|
This is a needed feature. When will it be available? Any updates? |
|
Hey, any updates here? This fix would come very handy |
|
YES! Please make it happen. |
bennetbo
added
the
area:ai
Contributor
|
Thank you @bennetbo !!! 🙏🙌 |
|
thanks a lot! |
This was referenced Jul 31, 2026
jolutz
pushed a commit
to jolutz/zed
that referenced
this pull request
Aug 8, 2026
…ponses (zed-industries#57861) LM Studio doesn't show the context token wheel (zed-industries#53790) because token usage is never reported in streaming responses. Causes: 1. `stream_options` was missing from the request. Without `stream_options: { include_usage: true }`, the LM Studio API omits `usage` from every streaming chunk entirely. 2. The event mapper discarded usage data in the final chunk. OpenAI-compatible servers send the usage summary in a trailing chunk that has an empty `choices` array. The old guard treated that as an error, so even when usage was present it was thrown away before emitting a `UsageUpdate` event. Fix: - Add `StreamOptions { include_usage: bool }` and `stream_options` to `ChatCompletionRequest`, and always set it to `true` for streaming requests. - Move usage handling in `LmStudioEventMapper::map_event` to run *before* the empty-choices guard, mirroring the OpenAI provider's approach. - Add four unit tests for `map_event` covering the fixed behavior. Release Notes: - Fixed LM Studio not showing the context window usage wheel. <img width="1184" height="1080" alt="Screenshot_20260527_130449" src="https://github.com/user-attachments/assets/97eb8500-39dd-4824-aaf8-f0422b62119d" /> --------- Co-authored-by: Gabriele Ancillai <gabriele.ancillai@sofka.com.co> Co-authored-by: Bennet Bo Fenner <bennetbo@gmx.de>
playdohface
pushed a commit
to playdohface/zed
that referenced
this pull request
Aug 29, 2026
…ponses (zed-industries#57861) LM Studio doesn't show the context token wheel (zed-industries#53790) because token usage is never reported in streaming responses. Causes: 1. `stream_options` was missing from the request. Without `stream_options: { include_usage: true }`, the LM Studio API omits `usage` from every streaming chunk entirely. 2. The event mapper discarded usage data in the final chunk. OpenAI-compatible servers send the usage summary in a trailing chunk that has an empty `choices` array. The old guard treated that as an error, so even when usage was present it was thrown away before emitting a `UsageUpdate` event. Fix: - Add `StreamOptions { include_usage: bool }` and `stream_options` to `ChatCompletionRequest`, and always set it to `true` for streaming requests. - Move usage handling in `LmStudioEventMapper::map_event` to run *before* the empty-choices guard, mirroring the OpenAI provider's approach. - Add four unit tests for `map_event` covering the fixed behavior. Release Notes: - Fixed LM Studio not showing the context window usage wheel. <img width="1184" height="1080" alt="Screenshot_20260527_130449" src="https://github.com/user-attachments/assets/97eb8500-39dd-4824-aaf8-f0422b62119d" /> --------- Co-authored-by: Gabriele Ancillai <gabriele.ancillai@sofka.com.co> Co-authored-by: Bennet Bo Fenner <bennetbo@gmx.de>
This file contains hidden or bidirectional Unicode text that may be interpreted or compiled differently than what appears below. To review, open the file in an editor that reveals hidden Unicode characters.
Learn more about bidirectional Unicode characters
Sign up for free
to join this conversation on GitHub.
Already have an account?
Sign in to comment
7 participants
Add this suggestion to a batch that can be applied as a single commit.This suggestion is invalid because no changes were made to the code.Suggestions cannot be applied while the pull request is closed.Suggestions cannot be applied while viewing a subset of changes.Only one suggestion per line can be applied in a batch.Add this suggestion to a batch that can be applied as a single commit.Applying suggestions on deleted lines is not supported.You must change the existing code in this line in order to create a valid suggestion.Outdated suggestions cannot be applied.This suggestion has been applied or marked resolved.Suggestions cannot be applied from pending reviews.Suggestions cannot be applied on multi-line comments.Suggestions cannot be applied while the pull request is queued to merge.Suggestion cannot be applied right now. Please check back later.
LM Studio doesn't show the context token wheel (#53790) because token usage is
never reported in streaming responses.
Causes:
stream_optionswas missing from the request. Withoutstream_options: { include_usage: true }, the LM Studio API omitsusagefrom every streaming chunk entirely.
The event mapper discarded usage data in the final chunk. OpenAI-compatible
servers send the usage summary in a trailing chunk that has an empty
choicesarray. The old guard treated that as an error, so even when usage was present
it was thrown away before emitting a
UsageUpdateevent.Fix:
StreamOptions { include_usage: bool }andstream_optionstoChatCompletionRequest, and always set it totruefor streaming requests.LmStudioEventMapper::map_eventto run before theempty-choices guard, mirroring the OpenAI provider's approach.
map_eventcovering the fixed behavior.Release Notes: