Remove deepseek, add flash, llama and qwen.#44
Remove deepseek, add flash, llama and qwen.#44JudahZF wants to merge 2 commits intoT3-Content:mainfrom
Conversation
📝 WalkthroughWalkthroughThe PR updates Changes
Estimated code review effort🎯 2 (Simple) | ⏱️ ~5 minutes Poem
🚥 Pre-merge checks | ✅ 3✅ Passed checks (3 passed)
✏️ Tip: You can configure your own custom pre-merge checks in the settings. ✨ Finishing Touches
🧪 Generate unit tests (beta)
Thanks for using CodeRabbit! It's free for OSS, and your support helps us grow. If you like it, consider giving us a shout-out. Comment |
![coderabbitai[bot]](https://avatars.githubusercontent.com/in/347564?s=60&v=4){kind=small}
There was a problem hiding this comment.
Actionable comments posted: 2
🤖 Prompt for all review comments with AI agents
Verify each finding against the current code and only fix it if needed.
Inline comments:
In `@game.ts`:
- Line 15: The MODEL_COLORS map contains a stale commented-out entry for
"DeepSeek 3.2" that no longer corresponds to any active model in MODELS; remove
the dead entry from MODEL_COLORS (or restore the model in MODELS if it should be
used) so lookups are consistent—search for the commented line referencing
"deepseek/deepseek-v3.2" and either delete that entry from MODEL_COLORS or
re-add the matching model to the MODELS array/object to keep the sets in sync.
- Around line 10-12: The MODEL_COLORS map is missing entries for the new model
names added ({ id: "google/gemini-3-flash-preview", name: "Gemini 3 Flash" }, {
id: "meta-llama/llama-4-maverick", name: "Llama 4 Maverick" }, { id:
"qwen/qwen3.5-plus-02-15", name: "Qwen 3.5 Plus" }); add string color values for
the keys "Gemini 3 Flash", "Llama 4 Maverick", and "Qwen 3.5 Plus" to the
MODEL_COLORS Record<string,string> (the same map referenced where MODEL_COLORS
is declared) so lookups return valid hex/ansi color strings used by the ink UI
renderer. Ensure the key names exactly match the name fields and choose distinct
colors consistent with existing palette.
There was a problem hiding this comment.
Pull request overview
This PR replaces the DeepSeek model with three new AI models to improve performance. DeepSeek was removed because it was too slow, and the new models (Gemini Flash, Llama 4 Maverick, and Qwen 3.5 Plus) are added to provide more variety and better performance.
Changes:
- Removed DeepSeek 3.2 model from active use (commented out)
- Added Gemini 3 Flash, Llama 4 Maverick, and Qwen 3.5 Plus models
💡 Add Copilot custom instructions for smarter, more guided reviews. Learn how to get started.
| { id: "google/gemini-3-flash-preview", name: "Gemini 3 Flash" }, | ||
| { id: "meta-llama/llama-4-maverick", name: "Llama 4 Maverick" }, | ||
| { id: "qwen/qwen3.5-plus-02-15", name: "Qwen 3.5 Plus" }, |
There was a problem hiding this comment.
The newly added models "Gemini 3 Flash", "Llama 4 Maverick", and "Qwen 3.5 Plus" are missing from the MODEL_COLORS object (lines 26-37). Each active model in the MODELS array should have a corresponding color entry in MODEL_COLORS to ensure consistent styling. Add color entries for these three models.
Add color entries for Gemini 3 Flash, Llama 4 Maverick, and Qwen 3.5 Plus, and remove the stale DeepSeek 3.2 entry that no longer has an active model. Co-Authored-By: Claude Sonnet 4.6 <[email protected]>
There was a problem hiding this comment.
♻️ Duplicate comments (1)
game.ts (1)
10-15: LGTM — all three model IDs confirmed valid on OpenRouter.Gemini 3 Flash Preview is confirmed on OpenRouter, Llama 4 Maverick is a valid OpenRouter model, and Qwen3.5 Plus 2026-02-15 is also available.
Both issues from the previous review cycle have been addressed in this commit:
- The
MODEL_COLORSentries for all three new models are now present (lines 28–30).- The stale
"DeepSeek 3.2"entry has been removed fromMODEL_COLORS.🤖 Prompt for AI Agents
Verify each finding against the current code and only fix it if needed. In `@game.ts` around lines 10 - 15, No code changes required; the new model entries ("google/gemini-3-flash-preview", "meta-llama/llama-4-maverick", "qwen/qwen3.5-plus-02-15") are valid and the related MODEL_COLORS entries have been added while the stale "deepseek/deepseek-v3.2" entry was removed—proceed to approve/merge the changes as-is (no edits to functions or classes needed).
🤖 Prompt for all review comments with AI agents
Verify each finding against the current code and only fix it if needed.
Duplicate comments:
In `@game.ts`:
- Around line 10-15: No code changes required; the new model entries
("google/gemini-3-flash-preview", "meta-llama/llama-4-maverick",
"qwen/qwen3.5-plus-02-15") are valid and the related MODEL_COLORS entries have
been added while the stale "deepseek/deepseek-v3.2" entry was removed—proceed to
approve/merge the changes as-is (no edits to functions or classes needed).
Deepseek is slow, swap it for some new models.
Note
Update
game.tsto remove DeepSeek 3.2 and add Gemini 3 Flash, Llama 4 Maverick, and Qwen 3.5 Plus toMODELSandMODEL_COLORSAdd three model entries and corresponding color mappings in game.ts and remove the DeepSeek 3.2 entry and mapping.
📍Where to Start
Start with the
MODELSandMODEL_COLORSconstants in game.ts.Macroscope summarized ea95fdf.
Summary by CodeRabbit
New Features
Updates