openai_subscribed: Use full context windows for subscription models - #62502
Merged
Conversation
cla-bot
Bot
added
the
cla-signed
zed-community-bot
Bot
added
the
staff
eholk
force-pushed
the
increase-openai-subscription-context-window
branch
from
August 11, 2026 21:28
cffe8f1 to
5f20877
Compare
mikayla-maki
approved these changes
Aug 11, 2026
eholk
enabled auto-merge
August 11, 2026 21:34
pull Bot
pushed a commit
to Mu-L/zed
that referenced
this pull request
Aug 12, 2026
PR zed-industries#62502 changed the ChatGPT subscription models to report the corresponding public API context windows. That was based on a mistaken assumption: subscription requests go through the separate Codex backend, which still rejects requests around the previous context limit. Because the advertised context window also determines when Zed compacts a conversation, reporting 1.05M tokens delays compaction until after the Codex backend rejects the request. This reverts zed-industries#62502 and restores the previous conservative limits. Longer term, we should load the account-specific model metadata from the Codex `/models` endpoint rather than maintaining this list by hand. Release Notes: - Fixed automatic context compaction for GPT models accessed through a ChatGPT subscription.
playdohface
pushed a commit
to playdohface/zed
that referenced
this pull request
Aug 29, 2026
…ed-industries#62502) ChatGPT subscription models currently report the short-context billing thresholds (272k or 372k tokens) as their maximum context windows. Those thresholds matter when Zed is paying metered API costs, but subscription requests are billed directly by OpenAI. This updates the subscribed models to report the full context windows supported by the corresponding public API models: 1.05M tokens for GPT-5.4, GPT-5.5, and GPT-5.6, and 400k tokens for GPT-5.4 Mini. It also reports the 128k output limit so context accounting reserves capacity for the response. Request serialization is unchanged; the unsupported `max_output_tokens` parameter is still omitted from requests to the Codex backend. Release Notes: - Improved context window usage for GPT models accessed through a ChatGPT subscription.
playdohface
pushed a commit
to playdohface/zed
that referenced
this pull request
Aug 29, 2026
PR zed-industries#62502 changed the ChatGPT subscription models to report the corresponding public API context windows. That was based on a mistaken assumption: subscription requests go through the separate Codex backend, which still rejects requests around the previous context limit. Because the advertised context window also determines when Zed compacts a conversation, reporting 1.05M tokens delays compaction until after the Codex backend rejects the request. This reverts zed-industries#62502 and restores the previous conservative limits. Longer term, we should load the account-specific model metadata from the Codex `/models` endpoint rather than maintaining this list by hand. Release Notes: - Fixed automatic context compaction for GPT models accessed through a ChatGPT subscription.
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
2 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.
ChatGPT subscription models currently report the short-context billing thresholds (272k or 372k tokens) as their maximum context windows. Those thresholds matter when Zed is paying metered API costs, but subscription requests are billed directly by OpenAI.
This updates the subscribed models to report the full context windows supported by the corresponding public API models: 1.05M tokens for GPT-5.4, GPT-5.5, and GPT-5.6, and 400k tokens for GPT-5.4 Mini. It also reports the 128k output limit so context accounting reserves capacity for the response. Request serialization is unchanged; the unsupported
max_output_tokensparameter is still omitted from requests to the Codex backend.Release Notes: