Repository navigation
fix(plugin): keep Fast mode for live-synced OpenAI models - #6120
Merged
Merged
Conversation
Live provider sync builds v2 models in the bundled plugin, which only translated a catalog model's reasoning efforts. The managed engine config it replaced also turns an OpenAI catalog model's priority-processing mode into Fast variants (default plus one per effort), so Fast mode disappeared from the picker for those models once live sync took over. Mirror the shared rule (packages/types cloud-model-fast): same variant ids, same conditions (provider @ai-sdk/openai, unchanged model package, exact service_tier priority mode, no catalog-declared Fast variants). Signed-off-by: Benjamin Shafii <ben@prologe.io>
Contributor
|
The latest updates on your projects. Learn more about Vercel for GitHub. 4 Skipped Deployments
|
benjaminshafii
temporarily deployed
to
pr-internal-specs
October 17, 2026 16:02 — with
GitHub Actions
Inactive
Contributor
OpenWork evidence
Run details · Open the preview to inspect evidence and sandbox options. |
Contributor
There was a problem hiding this comment.
Warden clearance. Complete security and confidentiality review of 7134e65e7f0416f5844e59452ea35e7a02ebb119 found no high or medium security findings and no confidentiality findings. Any new push dismisses this approval. Analysis run
Contributor
Warden: approvedNo high or medium security findings and no confidentiality findings. Reviewed |
This branch was successfully deployed
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
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Outdated suggestions cannot be applied.This suggestion has been applied or marked resolved.Suggestions cannot be applied from pending reviews.Suggestions cannot be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.
What is this about?
Desktop on OpenCode v2 with live provider sync: Fast mode is offered again for organization OpenAI models that support it.
What problem does it solve?
After live provider sync took over the organization's models, the Fast mode toggle disappeared from the model picker for those models.
What was the situation before?
Picking a supported organization OpenAI model showed Effort but no Fast mode row; with live sync off it was there.
How is this implemented?
packages/opencode-plugin/src/providers.ts:toModelInfonow appends Fast variants via a newfastVariants, next to the existing effort variants.packages/types/src/cloud-model-fast.ts(used by the managed engine config this path replaced): the same variant ids (__openwork_fast_v1/defaultand one per effort) and the same conditions — provider package@ai-sdk/openai, the model not overriding it, an exactservice_tier: "priority"fast mode, and no Fast variants already declared.What else changed?
none
Release note
Fast mode is available again for supported organization models when live model updates are on.
Evidence
No E2E.
packages/opencode-plugin/src/providers.test.ts— before: the new test fails; after: an OpenAI model with priority mode gets the Fast variants, and models without it, non-OpenAI providers or a different service tier do not. Plugin suite 132/132,apps/server/test/live-provider-sync.test.ts12/12.