@roo-code/types 1.44.0 → 1.45.0

package/dist/index.js

@@ -11,6 +11,8 @@ import { z as z3 } from "zod";
 import { z } from "zod";
 var reasoningEfforts = ["low", "medium", "high"];
 var reasoningEffortsSchema = z.enum(reasoningEfforts);
+var verbosityLevels = ["low", "medium", "high"];
+var verbosityLevelsSchema = z.enum(verbosityLevels);
 var modelParameters = ["max_tokens", "temperature", "reasoning", "include_reasoning"];
 var modelParametersSchema = z.enum(modelParameters);
 var isModelParameter = (value) => modelParameters.includes(value);
@@ -21,6 +23,8 @@ var modelInfoSchema = z.object({
   supportsImages: z.boolean().optional(),
   supportsComputerUse: z.boolean().optional(),
   supportsPromptCache: z.boolean(),
+  // Capability flag to indicate whether the model supports an output verbosity parameter
+  supportsVerbosity: z.boolean().optional(),
   supportsReasoningBudget: z.boolean().optional(),
   requiredReasoningBudget: z.boolean().optional(),
   supportsReasoningEffort: z.boolean().optional(),
@@ -88,6 +92,7 @@ var codebaseIndexProviderSchema = z2.object({
 });
 
 // src/provider-settings.ts
+var extendedReasoningEffortsSchema = z3.union([reasoningEffortsSchema, z3.literal("minimal")]);
 var providerNames = [
   "anthropic",
   "claude-code",
@@ -117,7 +122,8 @@ var providerNames = [
   "huggingface",
   "cerebras",
   "sambanova",
-  "zai"
+  "zai",
+  "fireworks"
 ];
 var providerNamesSchema = z3.enum(providerNames);
 var providerSettingsEntrySchema = z3.object({
@@ -136,9 +142,11 @@ var baseProviderSettingsSchema = z3.object({
   consecutiveMistakeLimit: z3.number().min(0).optional(),
   // Model reasoning.
   enableReasoningEffort: z3.boolean().optional(),
-  reasoningEffort: reasoningEffortsSchema.optional(),
+  reasoningEffort: extendedReasoningEffortsSchema.optional(),
   modelMaxTokens: z3.number().optional(),
-  modelMaxThinkingTokens: z3.number().optional()
+  modelMaxThinkingTokens: z3.number().optional(),
+  // Model verbosity.
+  verbosity: verbosityLevelsSchema.optional()
 });
 var apiModelIdProviderModelSchema = baseProviderSettingsSchema.extend({
   apiModelId: z3.string().optional()
@@ -289,6 +297,9 @@ var zaiSchema = apiModelIdProviderModelSchema.extend({
   zaiApiKey: z3.string().optional(),
   zaiApiLine: z3.union([z3.literal("china"), z3.literal("international")]).optional()
 });
+var fireworksSchema = apiModelIdProviderModelSchema.extend({
+  fireworksApiKey: z3.string().optional()
+});
 var defaultSchema = z3.object({
   apiProvider: z3.undefined()
 });
@@ -322,6 +333,7 @@ var providerSettingsSchemaDiscriminated = z3.discriminatedUnion("apiProvider", [
   cerebrasSchema.merge(z3.object({ apiProvider: z3.literal("cerebras") })),
   sambaNovaSchema.merge(z3.object({ apiProvider: z3.literal("sambanova") })),
   zaiSchema.merge(z3.object({ apiProvider: z3.literal("zai") })),
+  fireworksSchema.merge(z3.object({ apiProvider: z3.literal("fireworks") })),
   defaultSchema
 ]);
 var providerSettingsSchema = z3.object({
@@ -355,6 +367,7 @@ var providerSettingsSchema = z3.object({
   ...cerebrasSchema.shape,
   ...sambaNovaSchema.shape,
   ...zaiSchema.shape,
+  ...fireworksSchema.shape,
   ...codebaseIndexProviderSchema.shape
 });
 var providerSettingsWithIdSchema = providerSettingsSchema.extend({ id: z3.string().optional() });
@@ -502,7 +515,14 @@ var clineMessageSchema = z6.object({
   progressStatus: toolProgressStatusSchema.optional(),
   contextCondense: contextCondenseSchema.optional(),
   isProtected: z6.boolean().optional(),
-  apiProtocol: z6.union([z6.literal("openai"), z6.literal("anthropic")]).optional()
+  apiProtocol: z6.union([z6.literal("openai"), z6.literal("anthropic")]).optional(),
+  metadata: z6.object({
+    gpt5: z6.object({
+      previous_response_id: z6.string().optional(),
+      instructions: z6.string().optional(),
+      reasoning_summary: z6.string().optional()
+    }).optional()
+  }).optional()
 });
 var tokenUsageSchema = z6.object({
   totalTokensIn: z6.number(),
@@ -985,7 +1005,8 @@ var SECRET_STATE_KEYS = [
   "codebaseIndexGeminiApiKey",
   "codebaseIndexMistralApiKey",
   "huggingFaceApiKey",
-  "sambaNovaApiKey"
+  "sambaNovaApiKey",
+  "fireworksApiKey"
 ];
 var isSecretStateKey = (key) => SECRET_STATE_KEYS.includes(key);
 var GLOBAL_STATE_KEYS = [...GLOBAL_SETTINGS_KEYS, ...PROVIDER_SETTINGS_KEYS].filter(
@@ -1494,6 +1515,22 @@ var anthropicModels = {
     // $0.30 per million tokens
     supportsReasoningBudget: true
   },
+  "claude-opus-4-1-20250805": {
+    maxTokens: 8192,
+    contextWindow: 2e5,
+    supportsImages: true,
+    supportsComputerUse: true,
+    supportsPromptCache: true,
+    inputPrice: 15,
+    // $15 per million input tokens
+    outputPrice: 75,
+    // $75 per million output tokens
+    cacheWritesPrice: 18.75,
+    // $18.75 per million tokens
+    cacheReadsPrice: 1.5,
+    // $1.50 per million tokens
+    supportsReasoningBudget: true
+  },
   "claude-opus-4-20250514": {
     maxTokens: 32e3,
     // Overridden to 8k if `enableReasoningEffort` is false.
@@ -1674,6 +1711,21 @@ var bedrockModels = {
     maxCachePoints: 4,
     cachableFields: ["system", "messages", "tools"]
   },
+  "anthropic.claude-opus-4-1-20250805-v1:0": {
+    maxTokens: 8192,
+    contextWindow: 2e5,
+    supportsImages: true,
+    supportsComputerUse: true,
+    supportsPromptCache: true,
+    supportsReasoningBudget: true,
+    inputPrice: 15,
+    outputPrice: 75,
+    cacheWritesPrice: 18.75,
+    cacheReadsPrice: 1.5,
+    minTokensPerCachePoint: 1024,
+    maxCachePoints: 4,
+    cachableFields: ["system", "messages", "tools"]
+  },
   "anthropic.claude-opus-4-20250514-v1:0": {
     maxTokens: 8192,
     contextWindow: 2e5,
@@ -2046,6 +2098,15 @@ var cerebrasModels = {
     outputPrice: 0,
     description: "SOTA performance with ~1500 tokens/s",
     supportsReasoningEffort: true
+  },
+  "gpt-oss-120b": {
+    maxTokens: 8e3,
+    contextWindow: 64e3,
+    supportsImages: false,
+    supportsPromptCache: false,
+    inputPrice: 0,
+    outputPrice: 0,
+    description: "OpenAI GPT OSS model with ~2800 tokens/s\n\n\u2022 64K context window\n\u2022 Excels at efficient reasoning across science, math, and coding"
   }
 };
 
@@ -2301,6 +2362,15 @@ var claudeCodeModels = {
     supportsReasoningBudget: false,
     requiredReasoningBudget: false
   },
+  "claude-opus-4-1-20250805": {
+    ...anthropicModels["claude-opus-4-1-20250805"],
+    supportsImages: false,
+    supportsPromptCache: true,
+    // Claude Code does report cache tokens
+    supportsReasoningEffort: false,
+    supportsReasoningBudget: false,
+    requiredReasoningBudget: false
+  },
   "claude-opus-4-20250514": {
     ...anthropicModels["claude-opus-4-20250514"],
     supportsImages: false,
@@ -2774,6 +2844,24 @@ var groqModels = {
     inputPrice: 1,
     outputPrice: 3,
     description: "Moonshot AI Kimi K2 Instruct 1T model, 128K context."
+  },
+  "openai/gpt-oss-120b": {
+    maxTokens: 32766,
+    contextWindow: 131072,
+    supportsImages: false,
+    supportsPromptCache: false,
+    inputPrice: 0.15,
+    outputPrice: 0.75,
+    description: "GPT-OSS 120B is OpenAI's flagship open source model, built on a Mixture-of-Experts (MoE) architecture with 20 billion parameters and 128 experts."
+  },
+  "openai/gpt-oss-20b": {
+    maxTokens: 32768,
+    contextWindow: 131072,
+    supportsImages: false,
+    supportsPromptCache: false,
+    inputPrice: 0.1,
+    outputPrice: 0.5,
+    description: "GPT-OSS 20B is OpenAI's flagship open source model, built on a Mixture-of-Experts (MoE) architecture with 20 billion parameters and 32 experts."
   }
 };
 
@@ -2802,6 +2890,7 @@ var litellmDefaultModelInfo = {
 };
 var LITELLM_COMPUTER_USE_MODELS = /* @__PURE__ */ new Set([
   "claude-3-5-sonnet-latest",
+  "claude-opus-4-1-20250805",
   "claude-opus-4-20250514",
   "claude-sonnet-4-20250514",
   "claude-3-7-sonnet-latest",
@@ -2811,22 +2900,26 @@ var LITELLM_COMPUTER_USE_MODELS = /* @__PURE__ */ new Set([
   "vertex_ai/claude-3-5-sonnet-v2",
   "vertex_ai/claude-3-5-sonnet-v2@20241022",
   "vertex_ai/claude-3-7-sonnet@20250219",
+  "vertex_ai/claude-opus-4-1@20250805",
   "vertex_ai/claude-opus-4@20250514",
   "vertex_ai/claude-sonnet-4@20250514",
   "openrouter/anthropic/claude-3.5-sonnet",
   "openrouter/anthropic/claude-3.5-sonnet:beta",
   "openrouter/anthropic/claude-3.7-sonnet",
   "openrouter/anthropic/claude-3.7-sonnet:beta",
+  "anthropic.claude-opus-4-1-20250805-v1:0",
   "anthropic.claude-opus-4-20250514-v1:0",
   "anthropic.claude-sonnet-4-20250514-v1:0",
   "anthropic.claude-3-7-sonnet-20250219-v1:0",
   "anthropic.claude-3-5-sonnet-20241022-v2:0",
   "us.anthropic.claude-3-5-sonnet-20241022-v2:0",
   "us.anthropic.claude-3-7-sonnet-20250219-v1:0",
+  "us.anthropic.claude-opus-4-1-20250805-v1:0",
   "us.anthropic.claude-opus-4-20250514-v1:0",
   "us.anthropic.claude-sonnet-4-20250514-v1:0",
   "eu.anthropic.claude-3-5-sonnet-20241022-v2:0",
   "eu.anthropic.claude-3-7-sonnet-20250219-v1:0",
+  "eu.anthropic.claude-opus-4-1-20250805-v1:0",
   "eu.anthropic.claude-opus-4-20250514-v1:0",
   "eu.anthropic.claude-sonnet-4-20250514-v1:0",
   "snowflake/claude-3-5-sonnet"
@@ -2963,8 +3056,48 @@ var ollamaDefaultModelInfo = {
 };
 
 // src/providers/openai.ts
-var openAiNativeDefaultModelId = "gpt-4.1";
+var openAiNativeDefaultModelId = "gpt-5-2025-08-07";
 var openAiNativeModels = {
+  "gpt-5-2025-08-07": {
+    maxTokens: 128e3,
+    contextWindow: 4e5,
+    supportsImages: true,
+    supportsPromptCache: true,
+    supportsReasoningEffort: true,
+    reasoningEffort: "medium",
+    inputPrice: 1.25,
+    outputPrice: 10,
+    cacheReadsPrice: 0.13,
+    description: "GPT-5: The best model for coding and agentic tasks across domains",
+    // supportsVerbosity is a new capability; ensure ModelInfo includes it
+    supportsVerbosity: true
+  },
+  "gpt-5-mini-2025-08-07": {
+    maxTokens: 128e3,
+    contextWindow: 4e5,
+    supportsImages: true,
+    supportsPromptCache: true,
+    supportsReasoningEffort: true,
+    reasoningEffort: "medium",
+    inputPrice: 0.25,
+    outputPrice: 2,
+    cacheReadsPrice: 0.03,
+    description: "GPT-5 Mini: A faster, more cost-efficient version of GPT-5 for well-defined tasks",
+    supportsVerbosity: true
+  },
+  "gpt-5-nano-2025-08-07": {
+    maxTokens: 128e3,
+    contextWindow: 4e5,
+    supportsImages: true,
+    supportsPromptCache: true,
+    supportsReasoningEffort: true,
+    reasoningEffort: "medium",
+    inputPrice: 0.05,
+    outputPrice: 0.4,
+    cacheReadsPrice: 0.01,
+    description: "GPT-5 Nano: Fastest, most cost-efficient version of GPT-5",
+    supportsVerbosity: true
+  },
   "gpt-4.1": {
     maxTokens: 32768,
     contextWindow: 1047576,
@@ -3150,6 +3283,7 @@ var openAiModelInfoSaneDefaults = {
 };
 var azureOpenAiDefaultApiVersion = "2024-08-01-preview";
 var OPENAI_NATIVE_DEFAULT_TEMPERATURE = 0;
+var GPT5_DEFAULT_TEMPERATURE = 1;
 var OPENAI_AZURE_AI_INFERENCE_PATH = "/models/chat/completions";
 
 // src/providers/openrouter.ts
@@ -3187,6 +3321,7 @@ var OPEN_ROUTER_PROMPT_CACHING_MODELS = /* @__PURE__ */ new Set([
   "anthropic/claude-3.7-sonnet:thinking",
   "anthropic/claude-sonnet-4",
   "anthropic/claude-opus-4",
+  "anthropic/claude-opus-4.1",
   "google/gemini-2.5-flash-preview",
   "google/gemini-2.5-flash-preview:thinking",
   "google/gemini-2.5-flash-preview-05-20",
@@ -3204,7 +3339,8 @@ var OPEN_ROUTER_COMPUTER_USE_MODELS = /* @__PURE__ */ new Set([
   "anthropic/claude-3.7-sonnet:beta",
   "anthropic/claude-3.7-sonnet:thinking",
   "anthropic/claude-sonnet-4",
-  "anthropic/claude-opus-4"
+  "anthropic/claude-opus-4",
+  "anthropic/claude-opus-4.1"
 ]);
 var OPEN_ROUTER_REQUIRED_REASONING_BUDGET_MODELS = /* @__PURE__ */ new Set([
   "anthropic/claude-3.7-sonnet:thinking",
@@ -3214,6 +3350,7 @@ var OPEN_ROUTER_REQUIRED_REASONING_BUDGET_MODELS = /* @__PURE__ */ new Set([
 var OPEN_ROUTER_REASONING_BUDGET_MODELS = /* @__PURE__ */ new Set([
   "anthropic/claude-3.7-sonnet:beta",
   "anthropic/claude-opus-4",
+  "anthropic/claude-opus-4.1",
   "anthropic/claude-sonnet-4",
   "google/gemini-2.5-pro-preview",
   "google/gemini-2.5-pro",
@@ -3504,6 +3641,18 @@ var vertexModels = {
     cacheReadsPrice: 0.3,
     supportsReasoningBudget: true
   },
+  "claude-opus-4-1@20250805": {
+    maxTokens: 8192,
+    contextWindow: 2e5,
+    supportsImages: true,
+    supportsComputerUse: true,
+    supportsPromptCache: true,
+    inputPrice: 15,
+    outputPrice: 75,
+    cacheWritesPrice: 18.75,
+    cacheReadsPrice: 1.5,
+    supportsReasoningBudget: true
+  },
   "claude-opus-4@20250514": {
     maxTokens: 8192,
     contextWindow: 2e5,
@@ -4021,6 +4170,92 @@ var mainlandZAiModels = {
   }
 };
 var ZAI_DEFAULT_TEMPERATURE = 0;
+
+// src/providers/fireworks.ts
+var fireworksDefaultModelId = "accounts/fireworks/models/kimi-k2-instruct";
+var fireworksModels = {
+  "accounts/fireworks/models/kimi-k2-instruct": {
+    maxTokens: 16384,
+    contextWindow: 128e3,
+    supportsImages: false,
+    supportsPromptCache: false,
+    inputPrice: 0.6,
+    outputPrice: 2.5,
+    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. Trained with the Muon optimizer, Kimi K2 achieves exceptional performance across frontier knowledge, reasoning, and coding tasks while being meticulously optimized for agentic capabilities."
+  },
+  "accounts/fireworks/models/qwen3-235b-a22b-instruct-2507": {
+    maxTokens: 32768,
+    contextWindow: 256e3,
+    supportsImages: false,
+    supportsPromptCache: false,
+    inputPrice: 0.22,
+    outputPrice: 0.88,
+    description: "Latest Qwen3 thinking model, competitive against the best closed source models in Jul 2025."
+  },
+  "accounts/fireworks/models/qwen3-coder-480b-a35b-instruct": {
+    maxTokens: 32768,
+    contextWindow: 256e3,
+    supportsImages: false,
+    supportsPromptCache: false,
+    inputPrice: 0.45,
+    outputPrice: 1.8,
+    description: "Qwen3's most agentic code model to date."
+  },
+  "accounts/fireworks/models/deepseek-r1-0528": {
+    maxTokens: 20480,
+    contextWindow: 16e4,
+    supportsImages: false,
+    supportsPromptCache: false,
+    inputPrice: 3,
+    outputPrice: 8,
+    description: "05/28 updated checkpoint of Deepseek R1. Its overall performance is now approaching that of leading models, such as O3 and Gemini 2.5 Pro. Compared to the previous version, the upgraded model shows significant improvements in handling complex reasoning tasks, and this version also offers a reduced hallucination rate, enhanced support for function calling, and better experience for vibe coding. Note that fine-tuning for this model is only available through contacting fireworks at https://fireworks.ai/company/contact-us."
+  },
+  "accounts/fireworks/models/deepseek-v3": {
+    maxTokens: 16384,
+    contextWindow: 128e3,
+    supportsImages: false,
+    supportsPromptCache: false,
+    inputPrice: 0.9,
+    outputPrice: 0.9,
+    description: "A strong Mixture-of-Experts (MoE) language model with 671B total parameters with 37B activated for each token from Deepseek. Note that fine-tuning for this model is only available through contacting fireworks at https://fireworks.ai/company/contact-us."
+  },
+  "accounts/fireworks/models/glm-4p5": {
+    maxTokens: 16384,
+    contextWindow: 128e3,
+    supportsImages: false,
+    supportsPromptCache: false,
+    inputPrice: 0.55,
+    outputPrice: 2.19,
+    description: "Z.ai GLM-4.5 with 355B total parameters and 32B active parameters. Features unified reasoning, coding, and intelligent agent capabilities."
+  },
+  "accounts/fireworks/models/glm-4p5-air": {
+    maxTokens: 16384,
+    contextWindow: 128e3,
+    supportsImages: false,
+    supportsPromptCache: false,
+    inputPrice: 0.55,
+    outputPrice: 2.19,
+    description: "Z.ai GLM-4.5-Air with 106B total parameters and 12B active parameters. Features unified reasoning, coding, and intelligent agent capabilities."
+  },
+  "accounts/fireworks/models/gpt-oss-20b": {
+    maxTokens: 16384,
+    contextWindow: 128e3,
+    supportsImages: false,
+    supportsPromptCache: false,
+    inputPrice: 0.07,
+    outputPrice: 0.3,
+    description: "OpenAI gpt-oss-20b: Compact model for local/edge deployments. Optimized for low-latency and resource-constrained environments with chain-of-thought output, adjustable reasoning, and agentic workflows."
+  },
+  "accounts/fireworks/models/gpt-oss-120b": {
+    maxTokens: 16384,
+    contextWindow: 128e3,
+    supportsImages: false,
+    supportsPromptCache: false,
+    inputPrice: 0.15,
+    outputPrice: 0.6,
+    description: "OpenAI gpt-oss-120b: Production-grade, general-purpose model that fits on a single H100 GPU. Features complex reasoning, configurable effort, full chain-of-thought transparency, and supports function calling, tool use, and structured outputs."
+  }
+};
 export {
   ANTHROPIC_DEFAULT_MAX_TOKENS,
   ANTHROPIC_STYLE_PROVIDERS,
@@ -4043,6 +4278,7 @@ export {
   GLAMA_DEFAULT_TEMPERATURE,
   GLOBAL_SETTINGS_KEYS,
   GLOBAL_STATE_KEYS,
+  GPT5_DEFAULT_TEMPERATURE,
   HUGGINGFACE_API_URL,
   HUGGINGFACE_CACHE_DURATION,
   HUGGINGFACE_DEFAULT_CONTEXT_WINDOW,
@@ -4114,6 +4350,9 @@ export {
   experimentIds,
   experimentIdsSchema,
   experimentsSchema,
+  extendedReasoningEffortsSchema,
+  fireworksDefaultModelId,
+  fireworksModels,
   followUpDataSchema,
   geminiDefaultModelId,
   geminiModels,
@@ -4208,6 +4447,8 @@ export {
   toolUsageSchema,
   unboundDefaultModelId,
   unboundDefaultModelInfo,
+  verbosityLevels,
+  verbosityLevelsSchema,
   vertexDefaultModelId,
   vertexModels,
   vscodeLlmDefaultModelId,