Sync models.json with current Command Code registry (55 models) - #19
Open
RigaOnTheRocks wants to merge 1 commit into
Open
Sync models.json with current Command Code registry (55 models)#19RigaOnTheRocks wants to merge 1 commit into
RigaOnTheRocks wants to merge 1 commit into
Conversation
Updates the model catalog to match Command Code's current registry: - Adds Qwen3.7-Flash, Qwen3.8-Max, Qwen3.7-Plus - Adds Gemini 3.6/3.7 Flash, GLM-5.2/5.2-Fast/5.3, Grok 4.5/4.6 - Adds Kimi-K2.7-Code/Highspeed, K3, Muse Spark 1.1/1.2, Inkling - Adds MiniMax-M3, MiMo V2.5/Pro, Step-3.7-Flash, Hy3, Laguna S 2.1, Fugu - Fixes case-sensitive ids verified against api.commandcode.ai (e.g. Qwen/Qwen3.7-Flash)
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
1 participant
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Outdated suggestions cannot be applied.This suggestion has been applied or marked resolved.Suggestions cannot be applied from pending reviews.Suggestions cannot be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.
Summary
Syncs
models.jsonwith Command Code's current model registry. The bundled catalog was stale at 21 models and missing several models the Command Code API serves (notablyQwen/Qwen3.7-Flash, which users keep hitting as "not recognized").What changed
Qwen/Qwen3.7-Flash,Qwen/Qwen3.7-Plus,Qwen/Qwen3.8-Maxgoogle/gemini-3.6-flash,google/gemini-3.7-flash,google/gemini-3.5-flash-litezai-org/GLM-5.2,zai-org/GLM-5.2-Fast,zai-org/GLM-5.3moonshotai/Kimi-K2.7-Code,moonshotai/Kimi-K2.7-Code-Highspeed,moonshotai/Kimi-K3MiniMaxAI/MiniMax-M3xai/grok-4.5,xai/grok-4.6meta/muse-spark-1.1,meta/muse-spark-1.2,meta/muse-spark-1.2-contributorthinkingmachines/inkling,thinkingmachines/inkling-smallxiaomi/mimo-v2.5,xiaomi/mimo-v2.5-prostepfun/Step-3.7-Flashtencent/hy3-paidpoolside/laguna-s-2.1-freesakana/fugu-ultraclaude-sonnet-5,claude-opus-5,claude-fable-5,claude-opus-4-8Important detail
Command Code's
/alpha/generateAPI is case-sensitive on model ids. The ids in this PR were verified live againsthttps://api.commandcode.ai/alpha/generate— e.g.Qwen/Qwen3.7-Flashworks butqwen/qwen3.7-flashreturns403 Model/provider not recognized. This is why the previousQwen/Qwen3.7-Maxentry used the exact capitalized form.Verification
Each of the 55 ids was POSTed to
api.commandcode.ai/alpha/generatewith the plugin's request shape and confirmed to return a stream ({"type":"start"}). The resultingprovider.commandcode.modelsblock also loads correctly in opencode 1.18.x — all 55 show inopencode models commandcode.