Merge branch 'RooCodeInc:main' into main

Author: mohammad154

CHANGELOG.md

@@ -1,5 +1,23 @@
 # Roo Code Changelog
 
+## [3.28.15] - 2025-10-03
+
+![3.28.15 Release - Kangaroo Sliding Down a Chute](/releases/3.28.15-release.png)
+
+- Add new DeepSeek and GLM models with detailed descriptions to the Chutes provider (thanks @mohammad154!)
+- Fix: properly reset cost limit tracking when user clicks "Reset and Continue" (#6889 by @alecoot, PR by app/roomote)
+- Fix: improve save button activation in prompts settings (#5780 by @beccare, PR by app/roomote)
+- Fix: overeager 'there are unsaved changes' dialog in settings (thanks @brunobergher!)
+- Fix: show send button when only images are selected in chat textarea (thanks app/roomote!)
+- Fix: Claude Sonnet 4.5 compatibility improvements (thanks @mrubens!)
+- Add UsageStats schema and type for better analytics tracking (thanks app/roomote!)
+- Include reasoning messages in cloud tasks (thanks @mrubens!)
+- Security: update dependency vite to v6.3.6 (thanks app/renovate!)
+- Deprecate free grok 4 fast model (thanks @mrubens!)
+- Remove unsupported Gemini 2.5 Flash Image Preview free model (thanks @SannidhyaSah!)
+- Add structured data to the homepage for better SEO (thanks @mrubens!)
+- Update dependency glob to v11.0.3 (thanks app/renovate!)
+
 ## [3.28.14] - 2025-09-30
 
 ![3.28.14 Release - GLM-4.6 Model Support](/releases/3.28.14-release.png)

packages/types/src/model.ts

@@ -76,6 +76,8 @@ export const modelInfoSchema = z.object({
 	minTokensPerCachePoint: z.number().optional(),
 	maxCachePoints: z.number().optional(),
 	cachableFields: z.array(z.string()).optional(),
+	// Flag to indicate if the model is deprecated and should not be used
+	deprecated: z.boolean().optional(),
 	/**
 	 * Service tiers with pricing information.
 	 * Each tier can have a name (for OpenAI service tiers) and pricing overrides.

packages/types/src/providers/roo.ts

@@ -38,6 +38,7 @@ export const rooModels = {
 		outputPrice: 0,
 		description:
 			"Grok 4 Fast is xAI's latest multimodal model with SOTA cost-efficiency and a 2M token context window. (Note: prompts and completions are logged by xAI and used to improve the model.)",
+		deprecated: true,
 	},
 	"deepseek/deepseek-chat-v3.1": {
 		maxTokens: 16_384,