feat: list all Codex models in /orch and add Qwen 3.8 Cerebras row - #188
Merged
Conversation
The /orch Codex section offered only Codex default and GPT 6 Astra while the runner allowlist supports eight models. Expose all of them, guarded by a test that keeps the picker in sync with codexrunner.SupportedModels() in both directions. Also adds a coming-soon Qwen 3.8 row to the Cerebras section with a qwen-3.8 model ID (qwen/qwen3.8 aliases); confirm the ID against the live Cerebras API at launch.
|
Phase: Synth Sigilix is reviewing this pull request. A structured overview will replace this note when retrieval and specialist review complete. |
QualityMax ReviewReviewing Max's current mission: Max is reviewing the diff from his tiny laptop. The completed review will replace this message. |
Merged
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Outdated suggestions cannot be applied.This suggestion has been applied or marked resolved.Suggestions cannot be applied from pending reviews.Suggestions cannot be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.
Why
After v1.31.0, the /orch picker's Codex section offered only two entries (Codex default, GPT 6 Astra) even though the runner allowlist supports eight models. This PR exposes all of them and pre-adds Qwen 3.8 to the Cerebras section.
Changes
codexModelsnow lists everycodexrunner.SupportedModels()entry (GPT 6 Astra, 5.6 Sol/Terra/Luna, 5.5, 5.4, 5.4 Mini, 5.3 Codex Spark) withexternalbadges; Codex default keeps ⭐/shortcut 6.TestPickerOffersEverySupportedCodexModelfails when the picker and the runner allowlist drift in either direction.CerebrasQwen38Model = "qwen-3.8"constant plusqwen/qwen3.8/qwen-3-8alias resolution (unknown IDs still pass through).The Cerebras model catalog page was not reachable at authoring time, so
qwen-3.8follows Cerebras naming (zai-glm-4.7,gemma-4-31b) but is unconfirmed against the live API — per AGENTS.md the model is not live yet. The picker row is labeledcoming soon; verify the real ID before launch.Verification
Risk: LOW — additive picker rows and alias cases; persisted
codex_modelvalues are validated against the same allowlist on startup.