@roo-code/types 1.74.0 → 1.75.0

package/dist/index.js

@@ -98,6 +98,7 @@ var clineMessageSchema = z.object({
   contextCondense: contextCondenseSchema.optional(),
   isProtected: z.boolean().optional(),
   apiProtocol: z.union([z.literal("openai"), z.literal("anthropic")]).optional(),
+  isAnswered: z.boolean().optional(),
   metadata: z.object({
     gpt5: z.object({
       previous_response_id: z.string().optional(),
@@ -357,6 +358,8 @@ var reasoningEffortsSchema = z5.enum(reasoningEfforts);
 var reasoningEffortWithMinimalSchema = z5.union([reasoningEffortsSchema, z5.literal("minimal")]);
 var verbosityLevels = ["low", "medium", "high"];
 var verbosityLevelsSchema = z5.enum(verbosityLevels);
+var serviceTiers = ["default", "flex", "priority"];
+var serviceTierSchema = z5.enum(serviceTiers);
 var modelParameters = ["max_tokens", "temperature", "reasoning", "include_reasoning"];
 var modelParametersSchema = z5.enum(modelParameters);
 var isModelParameter = (value) => modelParameters.includes(value);
@@ -384,8 +387,15 @@ var modelInfoSchema = z5.object({
   minTokensPerCachePoint: z5.number().optional(),
   maxCachePoints: z5.number().optional(),
   cachableFields: z5.array(z5.string()).optional(),
+  /**
+   * Service tiers with pricing information.
+   * Each tier can have a name (for OpenAI service tiers) and pricing overrides.
+   * The top-level input/output/cache* fields represent the default/standard tier.
+   */
   tiers: z5.array(
     z5.object({
+      name: serviceTierSchema.optional(),
+      // Service tier name (flex, priority, etc.)
       contextWindow: z5.number(),
       inputPrice: z5.number().optional(),
       outputPrice: z5.number().optional(),
@@ -1348,6 +1358,15 @@ var chutesModels = {
     outputPrice: 0.5926,
     description: "Moonshot AI Kimi K2 Instruct model with 75k context window."
   },
+  "moonshotai/Kimi-K2-Instruct-0905": {
+    maxTokens: 32768,
+    contextWindow: 262144,
+    supportsImages: false,
+    supportsPromptCache: false,
+    inputPrice: 0.1999,
+    outputPrice: 0.8001,
+    description: "Moonshot AI Kimi K2 Instruct 0905 model with 256k context window."
+  },
   "Qwen/Qwen3-235B-A22B-Thinking-2507": {
     maxTokens: 32768,
     contextWindow: 262144,
@@ -1435,14 +1454,14 @@ var deepSeekModels = {
     contextWindow: 128e3,
     supportsImages: false,
     supportsPromptCache: true,
-    inputPrice: 0.27,
-    // $0.27 per million tokens (cache miss)
-    outputPrice: 1.1,
-    // $1.10 per million tokens
-    cacheWritesPrice: 0.27,
-    // $0.27 per million tokens (cache miss)
+    inputPrice: 0.56,
+    // $0.56 per million tokens (cache miss) - Updated Sept 5, 2025
+    outputPrice: 1.68,
+    // $1.68 per million tokens - Updated Sept 5, 2025
+    cacheWritesPrice: 0.56,
+    // $0.56 per million tokens (cache miss) - Updated Sept 5, 2025
     cacheReadsPrice: 0.07,
-    // $0.07 per million tokens (cache hit).
+    // $0.07 per million tokens (cache hit) - Updated Sept 5, 2025
     description: `DeepSeek-V3 achieves a significant breakthrough in inference speed over previous models. It tops the leaderboard among open-source models and rivals the most advanced closed-source models globally.`
   },
   "deepseek-reasoner": {
@@ -1451,14 +1470,14 @@ var deepSeekModels = {
     contextWindow: 128e3,
     supportsImages: false,
     supportsPromptCache: true,
-    inputPrice: 0.55,
-    // $0.55 per million tokens (cache miss)
-    outputPrice: 2.19,
-    // $2.19 per million tokens
-    cacheWritesPrice: 0.55,
-    // $0.55 per million tokens (cache miss)
-    cacheReadsPrice: 0.14,
-    // $0.14 per million tokens (cache hit)
+    inputPrice: 0.56,
+    // $0.56 per million tokens (cache miss) - Updated Sept 5, 2025
+    outputPrice: 1.68,
+    // $1.68 per million tokens - Updated Sept 5, 2025
+    cacheWritesPrice: 0.56,
+    // $0.56 per million tokens (cache miss) - Updated Sept 5, 2025
+    cacheReadsPrice: 0.07,
+    // $0.07 per million tokens (cache hit) - Updated Sept 5, 2025
     description: `DeepSeek-R1 achieves performance comparable to OpenAI-o1 across math, code, and reasoning tasks. Supports Chain of Thought reasoning with up to 64K output tokens.`
   }
 };
@@ -1568,8 +1587,18 @@ var featherlessModels = {
 var featherlessDefaultModelId = "deepseek-ai/DeepSeek-R1-0528";
 
 // src/providers/fireworks.ts
-var fireworksDefaultModelId = "accounts/fireworks/models/kimi-k2-instruct";
+var fireworksDefaultModelId = "accounts/fireworks/models/kimi-k2-instruct-0905";
 var fireworksModels = {
+  "accounts/fireworks/models/kimi-k2-instruct-0905": {
+    maxTokens: 16384,
+    contextWindow: 262144,
+    supportsImages: false,
+    supportsPromptCache: true,
+    inputPrice: 0.6,
+    outputPrice: 2.5,
+    cacheReadsPrice: 0.15,
+    description: "Kimi K2 model gets a new version update: Agentic coding: more accurate, better generalization across scaffolds. Frontend coding: improved aesthetics and functionalities on web, 3d, and other tasks. Context length: extended from 128k to 256k, providing better long-horizon support."
+  },
   "accounts/fireworks/models/kimi-k2-instruct": {
     maxTokens: 16384,
     contextWindow: 128e3,
@@ -1978,7 +2007,7 @@ var glamaDefaultModelInfo = {
 var GLAMA_DEFAULT_TEMPERATURE = 0;
 
 // src/providers/groq.ts
-var groqDefaultModelId = "llama-3.3-70b-versatile";
+var groqDefaultModelId = "moonshotai/kimi-k2-instruct-0905";
 var groqModels = {
   // Models based on API response: https://api.groq.com/openai/v1/models
   "llama-3.1-8b-instant": {
@@ -2064,6 +2093,16 @@ var groqModels = {
     // 50% discount for cached input tokens
     description: "Moonshot AI Kimi K2 Instruct 1T model, 128K context."
   },
+  "moonshotai/kimi-k2-instruct-0905": {
+    maxTokens: 16384,
+    contextWindow: 262144,
+    supportsImages: false,
+    supportsPromptCache: true,
+    inputPrice: 0.6,
+    outputPrice: 2.5,
+    cacheReadsPrice: 0.15,
+    description: "Kimi K2 model gets a new version update: Agentic coding: more accurate, better generalization across scaffolds. Frontend coding: improved aesthetics and functionalities on web, 3d, and other tasks. Context length: extended from 128k to 256k, providing better long-horizon support."
+  },
   "openai/gpt-oss-120b": {
     maxTokens: 32766,
     contextWindow: 131072,
@@ -2274,7 +2313,7 @@ var mistralModels = {
 var MISTRAL_DEFAULT_TEMPERATURE = 0;
 
 // src/providers/moonshot.ts
-var moonshotDefaultModelId = "kimi-k2-0711-preview";
+var moonshotDefaultModelId = "kimi-k2-0905-preview";
 var moonshotModels = {
   "kimi-k2-0711-preview": {
     maxTokens: 32e3,
@@ -2290,6 +2329,31 @@ var moonshotModels = {
     cacheReadsPrice: 0.15,
     // $0.15 per million tokens (cache hit)
     description: `Kimi K2 is a state-of-the-art mixture-of-experts (MoE) language model with 32 billion activated parameters and 1 trillion total parameters.`
+  },
+  "kimi-k2-0905-preview": {
+    maxTokens: 16384,
+    contextWindow: 262144,
+    supportsImages: false,
+    supportsPromptCache: true,
+    inputPrice: 0.6,
+    outputPrice: 2.5,
+    cacheReadsPrice: 0.15,
+    description: "Kimi K2 model gets a new version update: Agentic coding: more accurate, better generalization across scaffolds. Frontend coding: improved aesthetics and functionalities on web, 3d, and other tasks. Context length: extended from 128k to 256k, providing better long-horizon support."
+  },
+  "kimi-k2-turbo-preview": {
+    maxTokens: 32e3,
+    contextWindow: 262144,
+    supportsImages: false,
+    supportsPromptCache: true,
+    inputPrice: 2.4,
+    // $2.40 per million tokens (cache miss)
+    outputPrice: 10,
+    // $10.00 per million tokens
+    cacheWritesPrice: 0,
+    // $0 per million tokens (cache miss)
+    cacheReadsPrice: 0.6,
+    // $0.60 per million tokens (cache hit)
+    description: `Kimi K2 Turbo is a high-speed version of the state-of-the-art Kimi K2 mixture-of-experts (MoE) language model, with the same 32 billion activated parameters and 1 trillion total parameters, optimized for output speeds of up to 60 tokens per second, peaking at 100 tokens per second.`
   }
 };
 var MOONSHOT_DEFAULT_TEMPERATURE = 0.6;
@@ -2337,7 +2401,11 @@ var openAiNativeModels = {
     description: "GPT-5: The best model for coding and agentic tasks across domains",
     // supportsVerbosity is a new capability; ensure ModelInfo includes it
     supportsVerbosity: true,
-    supportsTemperature: false
+    supportsTemperature: false,
+    tiers: [
+      { name: "flex", contextWindow: 4e5, inputPrice: 0.625, outputPrice: 5, cacheReadsPrice: 0.0625 },
+      { name: "priority", contextWindow: 4e5, inputPrice: 2.5, outputPrice: 20, cacheReadsPrice: 0.25 }
+    ]
   },
   "gpt-5-mini-2025-08-07": {
     maxTokens: 128e3,
@@ -2351,7 +2419,11 @@ var openAiNativeModels = {
     cacheReadsPrice: 0.03,
     description: "GPT-5 Mini: A faster, more cost-efficient version of GPT-5 for well-defined tasks",
     supportsVerbosity: true,
-    supportsTemperature: false
+    supportsTemperature: false,
+    tiers: [
+      { name: "flex", contextWindow: 4e5, inputPrice: 0.125, outputPrice: 1, cacheReadsPrice: 0.0125 },
+      { name: "priority", contextWindow: 4e5, inputPrice: 0.45, outputPrice: 3.6, cacheReadsPrice: 0.045 }
+    ]
   },
   "gpt-5-nano-2025-08-07": {
     maxTokens: 128e3,
@@ -2365,7 +2437,8 @@ var openAiNativeModels = {
     cacheReadsPrice: 0.01,
     description: "GPT-5 Nano: Fastest, most cost-efficient version of GPT-5",
     supportsVerbosity: true,
-    supportsTemperature: false
+    supportsTemperature: false,
+    tiers: [{ name: "flex", contextWindow: 4e5, inputPrice: 0.025, outputPrice: 0.2, cacheReadsPrice: 25e-4 }]
   },
   "gpt-4.1": {
     maxTokens: 32768,
@@ -2375,7 +2448,10 @@ var openAiNativeModels = {
     inputPrice: 2,
     outputPrice: 8,
     cacheReadsPrice: 0.5,
-    supportsTemperature: true
+    supportsTemperature: true,
+    tiers: [
+      { name: "priority", contextWindow: 1047576, inputPrice: 3.5, outputPrice: 14, cacheReadsPrice: 0.875 }
+    ]
   },
   "gpt-4.1-mini": {
     maxTokens: 32768,
@@ -2385,7 +2461,10 @@ var openAiNativeModels = {
     inputPrice: 0.4,
     outputPrice: 1.6,
     cacheReadsPrice: 0.1,
-    supportsTemperature: true
+    supportsTemperature: true,
+    tiers: [
+      { name: "priority", contextWindow: 1047576, inputPrice: 0.7, outputPrice: 2.8, cacheReadsPrice: 0.175 }
+    ]
   },
   "gpt-4.1-nano": {
     maxTokens: 32768,
@@ -2395,7 +2474,10 @@ var openAiNativeModels = {
     inputPrice: 0.1,
     outputPrice: 0.4,
     cacheReadsPrice: 0.025,
-    supportsTemperature: true
+    supportsTemperature: true,
+    tiers: [
+      { name: "priority", contextWindow: 1047576, inputPrice: 0.2, outputPrice: 0.8, cacheReadsPrice: 0.05 }
+    ]
   },
   o3: {
     maxTokens: 1e5,
@@ -2407,7 +2489,11 @@ var openAiNativeModels = {
     cacheReadsPrice: 0.5,
     supportsReasoningEffort: true,
     reasoningEffort: "medium",
-    supportsTemperature: false
+    supportsTemperature: false,
+    tiers: [
+      { name: "flex", contextWindow: 2e5, inputPrice: 1, outputPrice: 4, cacheReadsPrice: 0.25 },
+      { name: "priority", contextWindow: 2e5, inputPrice: 3.5, outputPrice: 14, cacheReadsPrice: 0.875 }
+    ]
   },
   "o3-high": {
     maxTokens: 1e5,
@@ -2441,7 +2527,11 @@ var openAiNativeModels = {
     cacheReadsPrice: 0.275,
     supportsReasoningEffort: true,
     reasoningEffort: "medium",
-    supportsTemperature: false
+    supportsTemperature: false,
+    tiers: [
+      { name: "flex", contextWindow: 2e5, inputPrice: 0.55, outputPrice: 2.2, cacheReadsPrice: 0.138 },
+      { name: "priority", contextWindow: 2e5, inputPrice: 2, outputPrice: 8, cacheReadsPrice: 0.5 }
+    ]
   },
   "o4-mini-high": {
     maxTokens: 1e5,
@@ -2537,7 +2627,10 @@ var openAiNativeModels = {
     inputPrice: 2.5,
     outputPrice: 10,
     cacheReadsPrice: 1.25,
-    supportsTemperature: true
+    supportsTemperature: true,
+    tiers: [
+      { name: "priority", contextWindow: 128e3, inputPrice: 4.25, outputPrice: 17, cacheReadsPrice: 2.125 }
+    ]
   },
   "gpt-4o-mini": {
     maxTokens: 16384,
@@ -2547,7 +2640,10 @@ var openAiNativeModels = {
     inputPrice: 0.15,
     outputPrice: 0.6,
     cacheReadsPrice: 0.075,
-    supportsTemperature: true
+    supportsTemperature: true,
+    tiers: [
+      { name: "priority", contextWindow: 128e3, inputPrice: 0.25, outputPrice: 1, cacheReadsPrice: 0.125 }
+    ]
   },
   "codex-mini-latest": {
     maxTokens: 16384,
@@ -3088,6 +3184,60 @@ var vertexModels = {
     inputPrice: 0.35,
     outputPrice: 1.15,
     description: "Meta Llama 4 Maverick 17B Instruct model, 128K context."
+  },
+  "deepseek-r1-0528-maas": {
+    maxTokens: 32768,
+    contextWindow: 163840,
+    supportsImages: false,
+    supportsPromptCache: false,
+    inputPrice: 1.35,
+    outputPrice: 5.4,
+    description: "DeepSeek R1 (0528). Available in us-central1"
+  },
+  "deepseek-v3.1-maas": {
+    maxTokens: 32768,
+    contextWindow: 163840,
+    supportsImages: false,
+    supportsPromptCache: false,
+    inputPrice: 0.6,
+    outputPrice: 1.7,
+    description: "DeepSeek V3.1. Available in us-west2"
+  },
+  "gpt-oss-120b-maas": {
+    maxTokens: 32768,
+    contextWindow: 131072,
+    supportsImages: false,
+    supportsPromptCache: false,
+    inputPrice: 0.15,
+    outputPrice: 0.6,
+    description: "OpenAI gpt-oss 120B. Available in us-central1"
+  },
+  "gpt-oss-20b-maas": {
+    maxTokens: 32768,
+    contextWindow: 131072,
+    supportsImages: false,
+    supportsPromptCache: false,
+    inputPrice: 0.075,
+    outputPrice: 0.3,
+    description: "OpenAI gpt-oss 20B. Available in us-central1"
+  },
+  "qwen3-coder-480b-a35b-instruct-maas": {
+    maxTokens: 32768,
+    contextWindow: 262144,
+    supportsImages: false,
+    supportsPromptCache: false,
+    inputPrice: 1,
+    outputPrice: 4,
+    description: "Qwen3 Coder 480B A35B Instruct. Available in us-south1"
+  },
+  "qwen3-235b-a22b-instruct-2507-maas": {
+    maxTokens: 16384,
+    contextWindow: 262144,
+    supportsImages: false,
+    supportsPromptCache: false,
+    inputPrice: 0.25,
+    outputPrice: 1,
+    description: "Qwen3 235B A22B Instruct. Available in us-south1"
   }
 };
 var VERTEX_REGIONS = [
@@ -3096,6 +3246,7 @@ var VERTEX_REGIONS = [
   { value: "us-east1", label: "us-east1" },
   { value: "us-east4", label: "us-east4" },
   { value: "us-east5", label: "us-east5" },
+  { value: "us-south1", label: "us-south1" },
   { value: "us-west1", label: "us-west1" },
   { value: "us-west2", label: "us-west2" },
   { value: "us-west3", label: "us-west3" },
@@ -3589,6 +3740,18 @@ var mainlandZAiModels = {
 };
 var ZAI_DEFAULT_TEMPERATURE = 0;
 
+// src/providers/deepinfra.ts
+var deepInfraDefaultModelId = "Qwen/Qwen3-Coder-480B-A35B-Instruct-Turbo";
+var deepInfraDefaultModelInfo = {
+  maxTokens: 16384,
+  contextWindow: 262144,
+  supportsImages: false,
+  supportsPromptCache: false,
+  inputPrice: 0.3,
+  outputPrice: 1.2,
+  description: "Qwen 3 Coder 480B A35B Instruct Turbo model, 256K context."
+};
+
 // src/provider-settings.ts
 var providerNames = [
   "anthropic",
@@ -3607,6 +3770,7 @@ var providerNames = [
   "mistral",
   "moonshot",
   "deepseek",
+  "deepinfra",
   "doubao",
   "qwen-code",
   "unbound",
@@ -3747,7 +3911,10 @@ var geminiCliSchema = apiModelIdProviderModelSchema.extend({
 });
 var openAiNativeSchema = apiModelIdProviderModelSchema.extend({
   openAiNativeApiKey: z7.string().optional(),
-  openAiNativeBaseUrl: z7.string().optional()
+  openAiNativeBaseUrl: z7.string().optional(),
+  // OpenAI Responses API service tier for openai-native provider only.
+  // UI should only expose this when the selected model supports flex/priority.
+  openAiNativeServiceTier: serviceTierSchema.optional()
 });
 var mistralSchema = apiModelIdProviderModelSchema.extend({
   mistralApiKey: z7.string().optional(),
@@ -3757,6 +3924,11 @@ var deepSeekSchema = apiModelIdProviderModelSchema.extend({
   deepSeekBaseUrl: z7.string().optional(),
   deepSeekApiKey: z7.string().optional()
 });
+var deepInfraSchema = apiModelIdProviderModelSchema.extend({
+  deepInfraBaseUrl: z7.string().optional(),
+  deepInfraApiKey: z7.string().optional(),
+  deepInfraModelId: z7.string().optional()
+});
 var doubaoSchema = apiModelIdProviderModelSchema.extend({
   doubaoBaseUrl: z7.string().optional(),
   doubaoApiKey: z7.string().optional()
@@ -3847,6 +4019,7 @@ var providerSettingsSchemaDiscriminated = z7.discriminatedUnion("apiProvider", [
   openAiNativeSchema.merge(z7.object({ apiProvider: z7.literal("openai-native") })),
   mistralSchema.merge(z7.object({ apiProvider: z7.literal("mistral") })),
   deepSeekSchema.merge(z7.object({ apiProvider: z7.literal("deepseek") })),
+  deepInfraSchema.merge(z7.object({ apiProvider: z7.literal("deepinfra") })),
   doubaoSchema.merge(z7.object({ apiProvider: z7.literal("doubao") })),
   moonshotSchema.merge(z7.object({ apiProvider: z7.literal("moonshot") })),
   unboundSchema.merge(z7.object({ apiProvider: z7.literal("unbound") })),
@@ -3886,6 +4059,7 @@ var providerSettingsSchema = z7.object({
   ...openAiNativeSchema.shape,
   ...mistralSchema.shape,
   ...deepSeekSchema.shape,
+  ...deepInfraSchema.shape,
   ...doubaoSchema.shape,
   ...moonshotSchema.shape,
   ...unboundSchema.shape,
@@ -3926,7 +4100,8 @@ var MODEL_ID_KEYS = [
   "litellmModelId",
   "huggingFaceModelId",
   "ioIntelligenceModelId",
-  "vercelAiGatewayModelId"
+  "vercelAiGatewayModelId",
+  "deepInfraModelId"
 ];
 var getModelId = (settings) => {
   const modelIdKey = MODEL_ID_KEYS.find((key) => settings[key]);
@@ -4035,6 +4210,7 @@ var MODELS_BY_PROVIDER = {
   openrouter: { id: "openrouter", label: "OpenRouter", models: [] },
   requesty: { id: "requesty", label: "Requesty", models: [] },
   unbound: { id: "unbound", label: "Unbound", models: [] },
+  deepinfra: { id: "deepinfra", label: "DeepInfra", models: [] },
   "vercel-ai-gateway": { id: "vercel-ai-gateway", label: "Vercel AI Gateway", models: [] }
 };
 var dynamicProviders = [
@@ -4044,6 +4220,7 @@ var dynamicProviders = [
   "openrouter",
   "requesty",
   "unbound",
+  "deepinfra",
   "vercel-ai-gateway"
 ];
 var isDynamicProvider = (key) => dynamicProviders.includes(key);
@@ -4531,6 +4708,7 @@ var SECRET_STATE_KEYS = [
   "groqApiKey",
   "chutesApiKey",
   "litellmApiKey",
+  "deepInfraApiKey",
   "codeIndexOpenAiKey",
   "codeIndexQdrantApiKey",
   "codebaseIndexOpenAiCompatibleApiKey",
@@ -4724,7 +4902,8 @@ var userFeaturesSchema = z15.object({
   roomoteControlEnabled: z15.boolean().optional()
 });
 var userSettingsConfigSchema = z15.object({
-  extensionBridgeEnabled: z15.boolean().optional()
+  extensionBridgeEnabled: z15.boolean().optional(),
+  taskSyncEnabled: z15.boolean().optional()
 });
 var userSettingsDataSchema = z15.object({
   features: userFeaturesSchema,
@@ -5279,6 +5458,8 @@ export {
   customModePromptsSchema,
   customModesSettingsSchema,
   customSupportPromptsSchema,
+  deepInfraDefaultModelId,
+  deepInfraDefaultModelInfo,
   deepSeekDefaultModelId,
   deepSeekModels,
   discriminatedProviderSettingsWithIdSchema,
@@ -5386,6 +5567,8 @@ export {
   rooModels,
   sambaNovaDefaultModelId,
   sambaNovaModels,
+  serviceTierSchema,
+  serviceTiers,
   shareResponseSchema,
   shouldUseSingleFileRead,
   staticAppPropertiesSchema,