@roo-code/types 1.89.0 → 1.90.0

package/dist/index.js

@@ -75,6 +75,7 @@ var clineSays = [
   "diff_error",
   "condense_context",
   "condense_context_error",
+  "sliding_window_truncation",
   "codebase_search_result",
   "user_edit_todos"
 ];
@@ -87,7 +88,14 @@ var contextCondenseSchema = z.object({
   cost: z.number(),
   prevContextTokens: z.number(),
   newContextTokens: z.number(),
-  summary: z.string()
+  summary: z.string(),
+  condenseId: z.string().optional()
+});
+var contextTruncationSchema = z.object({
+  truncationId: z.string(),
+  messagesRemoved: z.number(),
+  prevContextTokens: z.number(),
+  newContextTokens: z.number()
 });
 var clineMessageSchema = z.object({
   ts: z.number(),
@@ -101,7 +109,16 @@ var clineMessageSchema = z.object({
   conversationHistoryIndex: z.number().optional(),
   checkpoint: z.record(z.string(), z.unknown()).optional(),
   progressStatus: toolProgressStatusSchema.optional(),
+  /**
+   * Data for successful context condensation.
+   * Present when `say: "condense_context"` and `partial: false`.
+   */
   contextCondense: contextCondenseSchema.optional(),
+  /**
+   * Data for sliding window truncation.
+   * Present when `say: "sliding_window_truncation"`.
+   */
+  contextTruncation: contextTruncationSchema.optional(),
   isProtected: z.boolean().optional(),
   apiProtocol: z.union([z.literal("openai"), z.literal("anthropic")]).optional(),
   isAnswered: z.boolean().optional()
@@ -130,8 +147,8 @@ var toolNames = [
   "read_file",
   "write_to_file",
   "apply_diff",
-  "insert_content",
   "search_and_replace",
+  "search_replace",
   "apply_patch",
   "search_files",
   "list_files",
@@ -250,7 +267,7 @@ var rooCodeEventsSchema = z3.object({
   ["taskAskResponded" /* TaskAskResponded */]: z3.tuple([z3.string()]),
   ["taskUserMessage" /* TaskUserMessage */]: z3.tuple([z3.string()]),
   ["taskToolFailed" /* TaskToolFailed */]: z3.tuple([z3.string(), toolNamesSchema, z3.string()]),
-  ["taskTokenUsageUpdated" /* TaskTokenUsageUpdated */]: z3.tuple([z3.string(), tokenUsageSchema]),
+  ["taskTokenUsageUpdated" /* TaskTokenUsageUpdated */]: z3.tuple([z3.string(), tokenUsageSchema, toolUsageSchema]),
   ["modeChanged" /* ModeChanged */]: z3.tuple([z3.string()]),
   ["providerProfileChanged" /* ProviderProfileChanged */]: z3.tuple([z3.object({ name: z3.string(), provider: z3.string() })])
 });
@@ -404,9 +421,9 @@ import { z as z5 } from "zod";
 var reasoningEfforts = ["low", "medium", "high"];
 var reasoningEffortsSchema = z5.enum(reasoningEfforts);
 var reasoningEffortWithMinimalSchema = z5.union([reasoningEffortsSchema, z5.literal("minimal")]);
-var reasoningEffortsExtended = ["none", "minimal", "low", "medium", "high"];
+var reasoningEffortsExtended = ["none", "minimal", "low", "medium", "high", "xhigh"];
 var reasoningEffortExtendedSchema = z5.enum(reasoningEffortsExtended);
-var reasoningEffortSettingValues = ["disable", "none", "minimal", "low", "medium", "high"];
+var reasoningEffortSettingValues = ["disable", "none", "minimal", "low", "medium", "high", "xhigh"];
 var reasoningEffortSettingSchema = z5.enum(reasoningEffortSettingValues);
 var verbosityLevels = ["low", "medium", "high"];
 var verbosityLevelsSchema = z5.enum(verbosityLevels);
@@ -434,7 +451,7 @@ var modelInfoSchema = z5.object({
   supportsTemperature: z5.boolean().optional(),
   defaultTemperature: z5.number().optional(),
   requiredReasoningBudget: z5.boolean().optional(),
-  supportsReasoningEffort: z5.union([z5.boolean(), z5.array(z5.enum(["disable", "none", "minimal", "low", "medium", "high"]))]).optional(),
+  supportsReasoningEffort: z5.union([z5.boolean(), z5.array(z5.enum(["disable", "none", "minimal", "low", "medium", "high", "xhigh"]))]).optional(),
   requiredReasoningEffort: z5.boolean().optional(),
   preserveReasoning: z5.boolean().optional(),
   supportedParameters: z5.array(modelParametersSchema).optional(),
@@ -450,6 +467,8 @@ var modelInfoSchema = z5.object({
   cachableFields: z5.array(z5.string()).optional(),
   // Flag to indicate if the model is deprecated and should not be used
   deprecated: z5.boolean().optional(),
+  // Flag to indicate if the model should hide vendor/company identity in responses
+  isStealthModel: z5.boolean().optional(),
   // Flag to indicate if the model is free (no cost)
   isFree: z5.boolean().optional(),
   // Flag to indicate if the model supports native tool calling (OpenAI-style function calling)
@@ -516,7 +535,9 @@ var codebaseIndexConfigSchema = z6.object({
   codebaseIndexOpenAiCompatibleModelDimension: z6.number().optional(),
   // Bedrock specific fields
   codebaseIndexBedrockRegion: z6.string().optional(),
-  codebaseIndexBedrockProfile: z6.string().optional()
+  codebaseIndexBedrockProfile: z6.string().optional(),
+  // OpenRouter specific fields
+  codebaseIndexOpenRouterSpecificProvider: z6.string().optional()
 });
 var codebaseIndexModelsSchema = z6.object({
   openai: z6.record(z6.string(), z6.object({ dimension: z6.number() })).optional(),
@@ -761,7 +782,7 @@ var ANTHROPIC_DEFAULT_MAX_TOKENS = 8192;
 // src/providers/baseten.ts
 var basetenModels = {
   "moonshotai/Kimi-K2-Thinking": {
-    maxTokens: 163800,
+    maxTokens: 16384,
     contextWindow: 262e3,
     supportsImages: false,
     supportsPromptCache: false,
@@ -773,7 +794,7 @@ var basetenModels = {
     description: "Kimi K2 Thinking - A model with enhanced reasoning capabilities from Kimi K2"
   },
   "zai-org/GLM-4.6": {
-    maxTokens: 2e5,
+    maxTokens: 16384,
     contextWindow: 2e5,
     supportsImages: false,
     supportsPromptCache: false,
@@ -785,7 +806,7 @@ var basetenModels = {
     description: "Frontier open model with advanced agentic, reasoning and coding capabilities"
   },
   "deepseek-ai/DeepSeek-R1": {
-    maxTokens: 131072,
+    maxTokens: 16384,
     contextWindow: 163840,
     supportsImages: false,
     supportsPromptCache: false,
@@ -796,7 +817,7 @@ var basetenModels = {
     description: "DeepSeek's first-generation reasoning model"
   },
   "deepseek-ai/DeepSeek-R1-0528": {
-    maxTokens: 131072,
+    maxTokens: 16384,
     contextWindow: 163840,
     supportsImages: false,
     supportsPromptCache: false,
@@ -807,7 +828,7 @@ var basetenModels = {
     description: "The latest revision of DeepSeek's first-generation reasoning model"
   },
   "deepseek-ai/DeepSeek-V3-0324": {
-    maxTokens: 131072,
+    maxTokens: 16384,
     contextWindow: 163840,
     supportsImages: false,
     supportsPromptCache: false,
@@ -818,7 +839,7 @@ var basetenModels = {
     description: "Fast general-purpose LLM with enhanced reasoning capabilities"
   },
   "deepseek-ai/DeepSeek-V3.1": {
-    maxTokens: 131072,
+    maxTokens: 16384,
     contextWindow: 163840,
     supportsImages: false,
     supportsPromptCache: false,
@@ -828,8 +849,20 @@ var basetenModels = {
     cacheReadsPrice: 0,
     description: "Extremely capable general-purpose LLM with hybrid reasoning capabilities and advanced tool calling"
   },
+  "deepseek-ai/DeepSeek-V3.2": {
+    maxTokens: 16384,
+    contextWindow: 163840,
+    supportsImages: false,
+    supportsPromptCache: false,
+    supportsNativeTools: true,
+    inputPrice: 0.3,
+    outputPrice: 0.45,
+    cacheWritesPrice: 0,
+    cacheReadsPrice: 0,
+    description: "DeepSeek's hybrid reasoning model with efficient long context scaling with GPT-5 level performance"
+  },
   "Qwen/Qwen3-235B-A22B-Instruct-2507": {
-    maxTokens: 262144,
+    maxTokens: 16384,
     contextWindow: 262144,
     supportsImages: false,
     supportsPromptCache: false,
@@ -840,7 +873,7 @@ var basetenModels = {
     description: "Mixture-of-experts LLM with math and reasoning capabilities"
   },
   "Qwen/Qwen3-Coder-480B-A35B-Instruct": {
-    maxTokens: 262144,
+    maxTokens: 16384,
     contextWindow: 262144,
     supportsImages: false,
     supportsPromptCache: false,
@@ -851,7 +884,7 @@ var basetenModels = {
     description: "Mixture-of-experts LLM with advanced coding and reasoning capabilities"
   },
   "openai/gpt-oss-120b": {
-    maxTokens: 128072,
+    maxTokens: 16384,
     contextWindow: 128072,
     supportsImages: false,
     supportsPromptCache: false,
@@ -863,7 +896,7 @@ var basetenModels = {
     description: "Extremely capable general-purpose LLM with strong, controllable reasoning capabilities"
   },
   "moonshotai/Kimi-K2-Instruct-0905": {
-    maxTokens: 168e3,
+    maxTokens: 16384,
     contextWindow: 262e3,
     supportsImages: false,
     supportsPromptCache: false,
@@ -1316,6 +1349,52 @@ var bedrockModels = {
     supportsPromptCache: false,
     inputPrice: 0.02,
     description: "Amazon Titan Text Embeddings V2"
+  },
+  "moonshot.kimi-k2-thinking": {
+    maxTokens: 32e3,
+    contextWindow: 262144,
+    supportsImages: false,
+    supportsPromptCache: false,
+    supportsNativeTools: true,
+    defaultToolProtocol: "native",
+    preserveReasoning: true,
+    inputPrice: 0.6,
+    outputPrice: 2.5,
+    description: "Kimi K2 Thinking (1T parameter MoE model with 32B active parameters)"
+  },
+  "minimax.minimax-m2": {
+    maxTokens: 16384,
+    contextWindow: 196608,
+    supportsImages: false,
+    supportsPromptCache: false,
+    supportsNativeTools: true,
+    defaultToolProtocol: "native",
+    preserveReasoning: true,
+    inputPrice: 0.3,
+    outputPrice: 1.2,
+    description: "MiniMax M2 (230B parameter MoE model with 10B active parameters)"
+  },
+  "qwen.qwen3-next-80b-a3b": {
+    maxTokens: 8192,
+    contextWindow: 262144,
+    supportsImages: false,
+    supportsPromptCache: false,
+    supportsNativeTools: true,
+    defaultToolProtocol: "native",
+    inputPrice: 0.15,
+    outputPrice: 1.2,
+    description: "Qwen3 Next 80B (MoE model with 3B active parameters)"
+  },
+  "qwen.qwen3-coder-480b-a35b-v1:0": {
+    maxTokens: 8192,
+    contextWindow: 262144,
+    supportsImages: false,
+    supportsPromptCache: false,
+    supportsNativeTools: true,
+    defaultToolProtocol: "native",
+    inputPrice: 0.45,
+    outputPrice: 1.8,
+    description: "Qwen3 Coder 480B (MoE model with 35B active parameters)"
   }
 };
 var BEDROCK_DEFAULT_TEMPERATURE = 0.3;
@@ -1381,8 +1460,8 @@ var BEDROCK_GLOBAL_INFERENCE_MODEL_IDS = [
 var cerebrasDefaultModelId = "gpt-oss-120b";
 var cerebrasModels = {
   "zai-glm-4.6": {
-    maxTokens: 16384,
-    // consistent with their other models
+    maxTokens: 8192,
+    // Conservative default to avoid premature rate limiting (Cerebras reserves quota upfront)
     contextWindow: 131072,
     supportsImages: false,
     supportsPromptCache: false,
@@ -1392,7 +1471,8 @@ var cerebrasModels = {
     description: "Highly intelligent general purpose model with up to 1,000 tokens/s"
   },
   "qwen-3-235b-a22b-instruct-2507": {
-    maxTokens: 64e3,
+    maxTokens: 8192,
+    // Conservative default to avoid premature rate limiting
     contextWindow: 64e3,
     supportsImages: false,
     supportsPromptCache: false,
@@ -1402,7 +1482,8 @@ var cerebrasModels = {
     description: "Intelligent model with ~1400 tokens/s"
   },
   "llama-3.3-70b": {
-    maxTokens: 64e3,
+    maxTokens: 8192,
+    // Conservative default to avoid premature rate limiting
     contextWindow: 64e3,
     supportsImages: false,
     supportsPromptCache: false,
@@ -1412,7 +1493,8 @@ var cerebrasModels = {
     description: "Powerful model with ~2600 tokens/s"
   },
   "qwen-3-32b": {
-    maxTokens: 64e3,
+    maxTokens: 8192,
+    // Conservative default to avoid premature rate limiting
     contextWindow: 64e3,
     supportsImages: false,
     supportsPromptCache: false,
@@ -1422,7 +1504,8 @@ var cerebrasModels = {
     description: "SOTA coding performance with ~2500 tokens/s"
   },
   "gpt-oss-120b": {
-    maxTokens: 8e3,
+    maxTokens: 8192,
+    // Conservative default to avoid premature rate limiting
     contextWindow: 64e3,
     supportsImages: false,
     supportsPromptCache: false,
@@ -1947,35 +2030,37 @@ var deepSeekModels = {
     supportsImages: false,
     supportsPromptCache: true,
     supportsNativeTools: true,
-    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-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.`
+    defaultToolProtocol: "native",
+    inputPrice: 0.28,
+    // $0.28 per million tokens (cache miss) - Updated Dec 9, 2025
+    outputPrice: 0.42,
+    // $0.42 per million tokens - Updated Dec 9, 2025
+    cacheWritesPrice: 0.28,
+    // $0.28 per million tokens (cache miss) - Updated Dec 9, 2025
+    cacheReadsPrice: 0.028,
+    // $0.028 per million tokens (cache hit) - Updated Dec 9, 2025
+    description: `DeepSeek-V3.2 (Non-thinking Mode) 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. Supports JSON output, tool calls, chat prefix completion (beta), and FIM completion (beta).`
   },
   "deepseek-reasoner": {
-    maxTokens: 65536,
-    // 64K max output for reasoning mode
+    maxTokens: 8192,
+    // 8K max output
     contextWindow: 128e3,
     supportsImages: false,
     supportsPromptCache: true,
     supportsNativeTools: true,
-    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.`
+    defaultToolProtocol: "native",
+    inputPrice: 0.28,
+    // $0.28 per million tokens (cache miss) - Updated Dec 9, 2025
+    outputPrice: 0.42,
+    // $0.42 per million tokens - Updated Dec 9, 2025
+    cacheWritesPrice: 0.28,
+    // $0.28 per million tokens (cache miss) - Updated Dec 9, 2025
+    cacheReadsPrice: 0.028,
+    // $0.028 per million tokens (cache hit) - Updated Dec 9, 2025
+    description: `DeepSeek-V3.2 (Thinking Mode) achieves performance comparable to OpenAI-o1 across math, code, and reasoning tasks. Supports Chain of Thought reasoning with up to 8K output tokens. Supports JSON output, tool calls, and chat prefix completion (beta).`
   }
 };
-var DEEP_SEEK_DEFAULT_TEMPERATURE = 0.6;
+var DEEP_SEEK_DEFAULT_TEMPERATURE = 0;
 
 // src/providers/doubao.ts
 var doubaoDefaultModelId = "doubao-seed-1-6-250615";
@@ -2430,21 +2515,6 @@ var geminiModels = {
   }
 };
 
-// src/providers/glama.ts
-var glamaDefaultModelId = "anthropic/claude-3-7-sonnet";
-var glamaDefaultModelInfo = {
-  maxTokens: 8192,
-  contextWindow: 2e5,
-  supportsImages: true,
-  supportsPromptCache: true,
-  inputPrice: 3,
-  outputPrice: 15,
-  cacheWritesPrice: 3.75,
-  cacheReadsPrice: 0.3,
-  description: "Claude 3.7 Sonnet is an advanced large language model with improved reasoning, coding, and problem-solving capabilities. It introduces a hybrid reasoning approach, allowing users to choose between rapid responses and extended, step-by-step processing for complex tasks. The model demonstrates notable improvements in coding, particularly in front-end development and full-stack updates, and excels in agentic workflows, where it can autonomously navigate multi-step processes. Claude 3.7 Sonnet maintains performance parity with its predecessor in standard mode while offering an extended reasoning mode for enhanced accuracy in math, coding, and instruction-following tasks. Read more at the [blog post here](https://www.anthropic.com/news/claude-3-7-sonnet)"
-};
-var GLAMA_DEFAULT_TEMPERATURE = 0;
-
 // src/providers/groq.ts
 var groqDefaultModelId = "moonshotai/kimi-k2-instruct-0905";
 var groqModels = {
@@ -2625,6 +2695,7 @@ var litellmDefaultModelInfo = {
   contextWindow: 2e5,
   supportsImages: true,
   supportsPromptCache: true,
+  supportsNativeTools: true,
   inputPrice: 3,
   outputPrice: 15,
   cacheWritesPrice: 3.75,
@@ -2823,10 +2894,30 @@ var ollamaDefaultModelInfo = {
 // src/providers/openai.ts
 var openAiNativeDefaultModelId = "gpt-5.1";
 var openAiNativeModels = {
+  "gpt-5.1-codex-max": {
+    maxTokens: 128e3,
+    contextWindow: 4e5,
+    supportsNativeTools: true,
+    includedTools: ["apply_patch"],
+    excludedTools: ["apply_diff", "write_to_file"],
+    supportsImages: true,
+    supportsPromptCache: true,
+    promptCacheRetention: "24h",
+    supportsReasoningEffort: ["low", "medium", "high", "xhigh"],
+    reasoningEffort: "medium",
+    inputPrice: 1.25,
+    outputPrice: 10,
+    cacheReadsPrice: 0.125,
+    supportsTemperature: false,
+    tiers: [{ name: "priority", contextWindow: 4e5, inputPrice: 2.5, outputPrice: 20, cacheReadsPrice: 0.25 }],
+    description: "GPT-5.1 Codex Max: Our most intelligent coding model optimized for long-horizon, agentic coding tasks"
+  },
   "gpt-5.1": {
     maxTokens: 128e3,
     contextWindow: 4e5,
     supportsNativeTools: true,
+    includedTools: ["apply_patch"],
+    excludedTools: ["apply_diff", "write_to_file"],
     supportsImages: true,
     supportsPromptCache: true,
     promptCacheRetention: "24h",
@@ -2847,6 +2938,8 @@ var openAiNativeModels = {
     maxTokens: 128e3,
     contextWindow: 4e5,
     supportsNativeTools: true,
+    includedTools: ["apply_patch"],
+    excludedTools: ["apply_diff", "write_to_file"],
     supportsImages: true,
     supportsPromptCache: true,
     promptCacheRetention: "24h",
@@ -2863,6 +2956,8 @@ var openAiNativeModels = {
     maxTokens: 128e3,
     contextWindow: 4e5,
     supportsNativeTools: true,
+    includedTools: ["apply_patch"],
+    excludedTools: ["apply_diff", "write_to_file"],
     supportsImages: true,
     supportsPromptCache: true,
     promptCacheRetention: "24h",
@@ -2878,6 +2973,8 @@ var openAiNativeModels = {
     maxTokens: 128e3,
     contextWindow: 4e5,
     supportsNativeTools: true,
+    includedTools: ["apply_patch"],
+    excludedTools: ["apply_diff", "write_to_file"],
     supportsImages: true,
     supportsPromptCache: true,
     supportsReasoningEffort: ["minimal", "low", "medium", "high"],
@@ -2897,6 +2994,8 @@ var openAiNativeModels = {
     maxTokens: 128e3,
     contextWindow: 4e5,
     supportsNativeTools: true,
+    includedTools: ["apply_patch"],
+    excludedTools: ["apply_diff", "write_to_file"],
     supportsImages: true,
     supportsPromptCache: true,
     supportsReasoningEffort: ["minimal", "low", "medium", "high"],
@@ -2916,6 +3015,8 @@ var openAiNativeModels = {
     maxTokens: 128e3,
     contextWindow: 4e5,
     supportsNativeTools: true,
+    includedTools: ["apply_patch"],
+    excludedTools: ["apply_diff", "write_to_file"],
     supportsImages: true,
     supportsPromptCache: true,
     supportsReasoningEffort: ["low", "medium", "high"],
@@ -2931,6 +3032,8 @@ var openAiNativeModels = {
     maxTokens: 128e3,
     contextWindow: 4e5,
     supportsNativeTools: true,
+    includedTools: ["apply_patch"],
+    excludedTools: ["apply_diff", "write_to_file"],
     supportsImages: true,
     supportsPromptCache: true,
     supportsReasoningEffort: ["minimal", "low", "medium", "high"],
@@ -2947,6 +3050,8 @@ var openAiNativeModels = {
     maxTokens: 128e3,
     contextWindow: 4e5,
     supportsNativeTools: true,
+    includedTools: ["apply_patch"],
+    excludedTools: ["apply_diff", "write_to_file"],
     supportsImages: true,
     supportsPromptCache: true,
     inputPrice: 1.25,
@@ -2958,6 +3063,8 @@ var openAiNativeModels = {
     maxTokens: 32768,
     contextWindow: 1047576,
     supportsNativeTools: true,
+    includedTools: ["apply_patch"],
+    excludedTools: ["apply_diff", "write_to_file"],
     supportsImages: true,
     supportsPromptCache: true,
     inputPrice: 2,
@@ -2972,6 +3079,8 @@ var openAiNativeModels = {
     maxTokens: 32768,
     contextWindow: 1047576,
     supportsNativeTools: true,
+    includedTools: ["apply_patch"],
+    excludedTools: ["apply_diff", "write_to_file"],
     supportsImages: true,
     supportsPromptCache: true,
     inputPrice: 0.4,
@@ -2986,6 +3095,8 @@ var openAiNativeModels = {
     maxTokens: 32768,
     contextWindow: 1047576,
     supportsNativeTools: true,
+    includedTools: ["apply_patch"],
+    excludedTools: ["apply_diff", "write_to_file"],
     supportsImages: true,
     supportsPromptCache: true,
     inputPrice: 0.1,
@@ -3193,6 +3304,8 @@ var openAiNativeModels = {
     maxTokens: 128e3,
     contextWindow: 4e5,
     supportsNativeTools: true,
+    includedTools: ["apply_patch"],
+    excludedTools: ["apply_diff", "write_to_file"],
     supportsImages: true,
     supportsPromptCache: true,
     supportsReasoningEffort: ["minimal", "low", "medium", "high"],
@@ -3212,6 +3325,8 @@ var openAiNativeModels = {
     maxTokens: 128e3,
     contextWindow: 4e5,
     supportsNativeTools: true,
+    includedTools: ["apply_patch"],
+    excludedTools: ["apply_diff", "write_to_file"],
     supportsImages: true,
     supportsPromptCache: true,
     supportsReasoningEffort: ["minimal", "low", "medium", "high"],
@@ -3231,6 +3346,8 @@ var openAiNativeModels = {
     maxTokens: 128e3,
     contextWindow: 4e5,
     supportsNativeTools: true,
+    includedTools: ["apply_patch"],
+    excludedTools: ["apply_diff", "write_to_file"],
     supportsImages: true,
     supportsPromptCache: true,
     supportsReasoningEffort: ["minimal", "low", "medium", "high"],
@@ -3393,7 +3510,18 @@ var RooModelSchema = z7.object({
   type: z7.literal("language"),
   tags: z7.array(z7.string()).optional(),
   pricing: RooPricingSchema,
-  deprecated: z7.boolean().optional()
+  deprecated: z7.boolean().optional(),
+  default_temperature: z7.number().optional(),
+  // Dynamic settings that map directly to ModelInfo properties
+  // Allows the API to configure model-specific defaults like includedTools, excludedTools, reasoningEffort, etc.
+  // These are always direct values (e.g., includedTools: ['search_replace']) for backward compatibility with old clients.
+  settings: z7.record(z7.string(), z7.unknown()).optional(),
+  // Versioned settings keyed by version number (e.g., '3.36.4').
+  // Each version key maps to a settings object that is used when plugin version >= that version.
+  // New clients find the highest version key <= current version and use those settings.
+  // Old clients ignore this field and use plain values from `settings`.
+  // Example: { '3.36.4': { includedTools: ['search_replace'] }, '3.35.0': { ... } }
+  versionedSettings: z7.record(z7.string(), z7.record(z7.string(), z7.unknown())).optional()
 });
 var RooModelsResponseSchema = z7.object({
   object: z7.literal("list"),
@@ -4159,15 +4287,17 @@ var xaiDefaultModelId = "grok-code-fast-1";
 var xaiModels = {
   "grok-code-fast-1": {
     maxTokens: 16384,
-    contextWindow: 262144,
-    supportsImages: false,
+    contextWindow: 256e3,
+    supportsImages: true,
     supportsPromptCache: true,
     supportsNativeTools: true,
     inputPrice: 0.2,
     outputPrice: 1.5,
     cacheWritesPrice: 0.02,
     cacheReadsPrice: 0.02,
-    description: "xAI's Grok Code Fast model with 256K context window"
+    description: "xAI's Grok Code Fast model with 256K context window",
+    includedTools: ["search_replace"],
+    excludedTools: ["apply_diff"]
   },
   "grok-4-1-fast-reasoning": {
     maxTokens: 65536,
@@ -4179,7 +4309,9 @@ var xaiModels = {
     outputPrice: 0.5,
     cacheWritesPrice: 0.05,
     cacheReadsPrice: 0.05,
-    description: "xAI's Grok 4.1 Fast model with 2M context window, optimized for high-performance agentic tool calling with reasoning"
+    description: "xAI's Grok 4.1 Fast model with 2M context window, optimized for high-performance agentic tool calling with reasoning",
+    includedTools: ["search_replace"],
+    excludedTools: ["apply_diff"]
   },
   "grok-4-1-fast-non-reasoning": {
     maxTokens: 65536,
@@ -4191,7 +4323,9 @@ var xaiModels = {
     outputPrice: 0.5,
     cacheWritesPrice: 0.05,
     cacheReadsPrice: 0.05,
-    description: "xAI's Grok 4.1 Fast model with 2M context window, optimized for high-performance agentic tool calling"
+    description: "xAI's Grok 4.1 Fast model with 2M context window, optimized for high-performance agentic tool calling",
+    includedTools: ["search_replace"],
+    excludedTools: ["apply_diff"]
   },
   "grok-4-fast-reasoning": {
     maxTokens: 65536,
@@ -4203,7 +4337,9 @@ var xaiModels = {
     outputPrice: 0.5,
     cacheWritesPrice: 0.05,
     cacheReadsPrice: 0.05,
-    description: "xAI's Grok 4 Fast model with 2M context window, optimized for high-performance agentic tool calling with reasoning"
+    description: "xAI's Grok 4 Fast model with 2M context window, optimized for high-performance agentic tool calling with reasoning",
+    includedTools: ["search_replace"],
+    excludedTools: ["apply_diff"]
   },
   "grok-4-fast-non-reasoning": {
     maxTokens: 65536,
@@ -4215,9 +4351,11 @@ var xaiModels = {
     outputPrice: 0.5,
     cacheWritesPrice: 0.05,
     cacheReadsPrice: 0.05,
-    description: "xAI's Grok 4 Fast model with 2M context window, optimized for high-performance agentic tool calling"
+    description: "xAI's Grok 4 Fast model with 2M context window, optimized for high-performance agentic tool calling",
+    includedTools: ["search_replace"],
+    excludedTools: ["apply_diff"]
   },
-  "grok-4": {
+  "grok-4-0709": {
     maxTokens: 8192,
     contextWindow: 256e3,
     supportsImages: true,
@@ -4227,36 +4365,14 @@ var xaiModels = {
     outputPrice: 15,
     cacheWritesPrice: 0.75,
     cacheReadsPrice: 0.75,
-    description: "xAI's Grok-4 model with 256K context window"
-  },
-  "grok-3": {
-    maxTokens: 8192,
-    contextWindow: 131072,
-    supportsImages: false,
-    supportsPromptCache: true,
-    supportsNativeTools: true,
-    inputPrice: 3,
-    outputPrice: 15,
-    cacheWritesPrice: 0.75,
-    cacheReadsPrice: 0.75,
-    description: "xAI's Grok-3 model with 128K context window"
-  },
-  "grok-3-fast": {
-    maxTokens: 8192,
-    contextWindow: 131072,
-    supportsImages: false,
-    supportsPromptCache: true,
-    supportsNativeTools: true,
-    inputPrice: 5,
-    outputPrice: 25,
-    cacheWritesPrice: 1.25,
-    cacheReadsPrice: 1.25,
-    description: "xAI's Grok-3 fast model with 128K context window"
+    description: "xAI's Grok-4 model with 256K context window",
+    includedTools: ["search_replace"],
+    excludedTools: ["apply_diff"]
   },
   "grok-3-mini": {
     maxTokens: 8192,
     contextWindow: 131072,
-    supportsImages: false,
+    supportsImages: true,
     supportsPromptCache: true,
     supportsNativeTools: true,
     inputPrice: 0.3,
@@ -4264,40 +4380,24 @@ var xaiModels = {
     cacheWritesPrice: 0.07,
     cacheReadsPrice: 0.07,
     description: "xAI's Grok-3 mini model with 128K context window",
-    supportsReasoningEffort: true
-  },
-  "grok-3-mini-fast": {
-    maxTokens: 8192,
-    contextWindow: 131072,
-    supportsImages: false,
-    supportsPromptCache: true,
-    supportsNativeTools: true,
-    inputPrice: 0.6,
-    outputPrice: 4,
-    cacheWritesPrice: 0.15,
-    cacheReadsPrice: 0.15,
-    description: "xAI's Grok-3 mini fast model with 128K context window",
-    supportsReasoningEffort: true
+    supportsReasoningEffort: ["low", "high"],
+    reasoningEffort: "low",
+    includedTools: ["search_replace"],
+    excludedTools: ["apply_diff"]
   },
-  "grok-2-1212": {
+  "grok-3": {
     maxTokens: 8192,
     contextWindow: 131072,
-    supportsImages: false,
-    supportsPromptCache: false,
-    supportsNativeTools: true,
-    inputPrice: 2,
-    outputPrice: 10,
-    description: "xAI's Grok-2 model (version 1212) with 128K context window"
-  },
-  "grok-2-vision-1212": {
-    maxTokens: 8192,
-    contextWindow: 32768,
     supportsImages: true,
-    supportsPromptCache: false,
+    supportsPromptCache: true,
     supportsNativeTools: true,
-    inputPrice: 2,
-    outputPrice: 10,
-    description: "xAI's Grok-2 Vision model (version 1212) with image support and 32K context window"
+    inputPrice: 3,
+    outputPrice: 15,
+    cacheWritesPrice: 0.75,
+    cacheReadsPrice: 0.75,
+    description: "xAI's Grok-3 model with 128K context window",
+    includedTools: ["search_replace"],
+    excludedTools: ["apply_diff"]
   }
 };
 
@@ -4404,7 +4504,6 @@ var internationalZAiModels = {
     supportsImages: false,
     supportsPromptCache: true,
     supportsNativeTools: true,
-    supportsReasoningBinary: true,
     inputPrice: 0.6,
     outputPrice: 2.2,
     cacheWritesPrice: 0,
@@ -4477,7 +4576,6 @@ var internationalZAiModels = {
     supportsImages: false,
     supportsPromptCache: true,
     supportsNativeTools: true,
-    supportsReasoningBinary: true,
     inputPrice: 0.6,
     outputPrice: 2.2,
     cacheWritesPrice: 0,
@@ -4505,7 +4603,6 @@ var mainlandZAiModels = {
     supportsImages: false,
     supportsPromptCache: true,
     supportsNativeTools: true,
-    supportsReasoningBinary: true,
     inputPrice: 0.29,
     outputPrice: 1.14,
     cacheWritesPrice: 0,
@@ -4578,7 +4675,6 @@ var mainlandZAiModels = {
     supportsImages: false,
     supportsPromptCache: true,
     supportsNativeTools: true,
-    supportsReasoningBinary: true,
     inputPrice: 0.29,
     outputPrice: 1.14,
     cacheWritesPrice: 0,
@@ -4654,8 +4750,6 @@ function getProviderDefaultModelId(provider, options = { isChina: false }) {
       return openRouterDefaultModelId;
     case "requesty":
       return requestyDefaultModelId;
-    case "glama":
-      return glamaDefaultModelId;
     case "unbound":
       return unboundDefaultModelId;
     case "litellm":
@@ -4742,7 +4836,6 @@ var dynamicProviders = [
   "io-intelligence",
   "requesty",
   "unbound",
-  "glama",
   "roo",
   "chutes"
 ];
@@ -4824,10 +4917,6 @@ var claudeCodeSchema = apiModelIdProviderModelSchema.extend({
   claudeCodePath: z8.string().optional(),
   claudeCodeMaxOutputTokens: z8.number().int().min(1).max(2e5).optional()
 });
-var glamaSchema = baseProviderSettingsSchema.extend({
-  glamaModelId: z8.string().optional(),
-  glamaApiKey: z8.string().optional()
-});
 var openRouterSchema = baseProviderSettingsSchema.extend({
   openRouterApiKey: z8.string().optional(),
   openRouterModelId: z8.string().optional(),
@@ -5012,7 +5101,6 @@ var defaultSchema = z8.object({
 var providerSettingsSchemaDiscriminated = z8.discriminatedUnion("apiProvider", [
   anthropicSchema.merge(z8.object({ apiProvider: z8.literal("anthropic") })),
   claudeCodeSchema.merge(z8.object({ apiProvider: z8.literal("claude-code") })),
-  glamaSchema.merge(z8.object({ apiProvider: z8.literal("glama") })),
   openRouterSchema.merge(z8.object({ apiProvider: z8.literal("openrouter") })),
   bedrockSchema.merge(z8.object({ apiProvider: z8.literal("bedrock") })),
   vertexSchema.merge(z8.object({ apiProvider: z8.literal("vertex") })),
@@ -5054,7 +5142,6 @@ var providerSettingsSchema = z8.object({
   apiProvider: providerNamesSchema.optional(),
   ...anthropicSchema.shape,
   ...claudeCodeSchema.shape,
-  ...glamaSchema.shape,
   ...openRouterSchema.shape,
   ...bedrockSchema.shape,
   ...vertexSchema.shape,
@@ -5099,7 +5186,6 @@ var discriminatedProviderSettingsWithIdSchema = providerSettingsSchemaDiscrimina
 var PROVIDER_SETTINGS_KEYS = providerSettingsSchema.keyof().options;
 var modelIdKeys = [
   "apiModelId",
-  "glamaModelId",
   "openRouterModelId",
   "openAiModelId",
   "ollamaModelId",
@@ -5121,7 +5207,6 @@ var isTypicalProvider = (key) => isProviderName(key) && !isInternalProvider(key)
 var modelIdKeysByProvider = {
   anthropic: "apiModelId",
   "claude-code": "apiModelId",
-  glama: "glamaModelId",
   openrouter: "openRouterModelId",
   bedrock: "apiModelId",
   vertex: "apiModelId",
@@ -5252,7 +5337,6 @@ var MODELS_BY_PROVIDER = {
   zai: { id: "zai", label: "Z.ai", models: Object.keys(internationalZAiModels) },
   baseten: { id: "baseten", label: "Baseten", models: Object.keys(basetenModels) },
   // Dynamic providers; models pulled from remote APIs.
-  glama: { id: "glama", label: "Glama", models: [] },
   huggingface: { id: "huggingface", label: "Hugging Face", models: [] },
   litellm: { id: "litellm", label: "LiteLLM", models: [] },
   openrouter: { id: "openrouter", label: "OpenRouter", models: [] },
@@ -5484,6 +5568,67 @@ var rooCodeTelemetryEventSchema = z11.discriminatedUnion("type", [
     })
   })
 ]);
+var EXPECTED_API_ERROR_CODES = /* @__PURE__ */ new Set([
+  402,
+  // Payment required - billing issues
+  429
+  // Rate limit - expected when hitting API limits
+]);
+var EXPECTED_ERROR_MESSAGE_PATTERNS = [
+  /^429\b/,
+  // Message starts with "429"
+  /rate limit/i
+  // Contains "rate limit" (case insensitive)
+];
+function isOpenAISdkError(error) {
+  return typeof error === "object" && error !== null && "status" in error && typeof error.status === "number";
+}
+function getErrorStatusCode(error) {
+  if (isOpenAISdkError(error)) {
+    return error.status;
+  }
+  return void 0;
+}
+function getErrorMessage(error) {
+  if (isOpenAISdkError(error)) {
+    return error.error?.metadata?.raw || error.error?.message || error.message;
+  }
+  return void 0;
+}
+function shouldReportApiErrorToTelemetry(errorCode, errorMessage) {
+  if (errorCode !== void 0 && EXPECTED_API_ERROR_CODES.has(errorCode)) {
+    return false;
+  }
+  if (errorMessage) {
+    for (const pattern of EXPECTED_ERROR_MESSAGE_PATTERNS) {
+      if (pattern.test(errorMessage)) {
+        return false;
+      }
+    }
+  }
+  return true;
+}
+var ApiProviderError = class extends Error {
+  constructor(message, provider, modelId, operation, errorCode) {
+    super(message);
+    this.provider = provider;
+    this.modelId = modelId;
+    this.operation = operation;
+    this.errorCode = errorCode;
+    this.name = "ApiProviderError";
+  }
+};
+function isApiProviderError(error) {
+  return error instanceof Error && error.name === "ApiProviderError" && "provider" in error && "modelId" in error && "operation" in error;
+}
+function extractApiProviderErrorProperties(error) {
+  return {
+    provider: error.provider,
+    modelId: error.modelId,
+    operation: error.operation,
+    ...error.errorCode !== void 0 && { errorCode: error.errorCode }
+  };
+}
 
 // src/mode.ts
 import { z as z12 } from "zod";
@@ -5562,7 +5707,7 @@ var DEFAULT_MODES = [
     whenToUse: "Use this mode when you need to plan, design, or strategize before implementation. Perfect for breaking down complex problems, creating technical specifications, designing system architecture, or brainstorming solutions before coding.",
     description: "Plan and design before implementation",
     groups: ["read", ["edit", { fileRegex: "\\.md$", description: "Markdown files only" }], "browser", "mcp"],
-    customInstructions: "1. Do some information gathering (using provided tools) to get more context about the task.\n\n2. You should also ask the user clarifying questions to get a better understanding of the task.\n\n3. Once you've gained more context about the user's request, break down the task into clear, actionable steps and create a todo list using the `update_todo_list` tool. Each todo item should be:\n   - Specific and actionable\n   - Listed in logical execution order\n   - Focused on a single, well-defined outcome\n   - Clear enough that another mode could execute it independently\n\n   **Note:** If the `update_todo_list` tool is not available, write the plan to a markdown file (e.g., `plan.md` or `todo.md`) instead.\n\n4. As you gather more information or discover new requirements, update the todo list to reflect the current understanding of what needs to be accomplished.\n\n5. Ask the user if they are pleased with this plan, or if they would like to make any changes. Think of this as a brainstorming session where you can discuss the task and refine the todo list.\n\n6. Include Mermaid diagrams if they help clarify complex workflows or system architecture. Please avoid using double quotes (\"\") and parentheses () inside square brackets ([]) in Mermaid diagrams, as this can cause parsing errors.\n\n7. Use the switch_mode tool to request that the user switch to another mode to implement the solution.\n\n**IMPORTANT: Focus on creating clear, actionable todo lists rather than lengthy markdown documents. Use the todo list as your primary planning tool to track and organize the work that needs to be done.**"
+    customInstructions: "1. Do some information gathering (using provided tools) to get more context about the task.\n\n2. You should also ask the user clarifying questions to get a better understanding of the task.\n\n3. Once you've gained more context about the user's request, break down the task into clear, actionable steps and create a todo list using the `update_todo_list` tool. Each todo item should be:\n   - Specific and actionable\n   - Listed in logical execution order\n   - Focused on a single, well-defined outcome\n   - Clear enough that another mode could execute it independently\n\n   **Note:** If the `update_todo_list` tool is not available, write the plan to a markdown file (e.g., `plan.md` or `todo.md`) instead.\n\n4. As you gather more information or discover new requirements, update the todo list to reflect the current understanding of what needs to be accomplished.\n\n5. Ask the user if they are pleased with this plan, or if they would like to make any changes. Think of this as a brainstorming session where you can discuss the task and refine the todo list.\n\n6. Include Mermaid diagrams if they help clarify complex workflows or system architecture. Please avoid using double quotes (\"\") and parentheses () inside square brackets ([]) in Mermaid diagrams, as this can cause parsing errors.\n\n7. Use the switch_mode tool to request that the user switch to another mode to implement the solution.\n\n**IMPORTANT: Focus on creating clear, actionable todo lists rather than lengthy markdown documents. Use the todo list as your primary planning tool to track and organize the work that needs to be done.**\n\n**CRITICAL: Never provide level of effort time estimates (e.g., hours, days, weeks) for tasks. Focus solely on breaking down the work into clear, actionable steps without estimating how long they will take.**\n\nUnless told otherwise, if you want to save a plan file, put it in the /plans directory"
   },
   {
     slug: "code",
@@ -5780,7 +5925,6 @@ var GLOBAL_SETTINGS_KEYS = globalSettingsSchema.keyof().options;
 var rooCodeSettingsSchema = providerSettingsSchema.merge(globalSettingsSchema);
 var SECRET_STATE_KEYS = [
   "apiKey",
-  "glamaApiKey",
   "openRouterApiKey",
   "awsAccessKey",
   "awsApiKey",
@@ -6346,6 +6490,16 @@ var usageStatsSchema = z16.object({
   // Period in days (e.g., 30)
 });
 
+// src/context-management.ts
+var CONTEXT_MANAGEMENT_EVENTS = [
+  "condense_context",
+  "condense_context_error",
+  "sliding_window_truncation"
+];
+function isContextManagementEvent(value) {
+  return typeof value === "string" && CONTEXT_MANAGEMENT_EVENTS.includes(value);
+}
+
 // src/cookie-consent.ts
 var CONSENT_COOKIE_NAME = "roo-code-cookie-consent";
 var COOKIE_CONSENT_EVENTS = {
@@ -6537,6 +6691,7 @@ export {
   ANTHROPIC_DEFAULT_MAX_TOKENS,
   ANTHROPIC_STYLE_PROVIDERS,
   AWS_INFERENCE_PROFILE_MAPPING,
+  ApiProviderError,
   BEDROCK_1M_CONTEXT_MODEL_IDS,
   BEDROCK_DEFAULT_CONTEXT,
   BEDROCK_DEFAULT_TEMPERATURE,
@@ -6546,6 +6701,7 @@ export {
   CLAUDE_CODE_DEFAULT_MAX_OUTPUT_TOKENS,
   CODEBASE_INDEX_DEFAULTS,
   CONSENT_COOKIE_NAME,
+  CONTEXT_MANAGEMENT_EVENTS,
   COOKIE_CONSENT_EVENTS,
   ConnectionState,
   DEEP_SEEK_DEFAULT_TEMPERATURE,
@@ -6558,10 +6714,10 @@ export {
   DOUBAO_API_CHAT_PATH,
   EVALS_SETTINGS,
   EVALS_TIMEOUT,
+  EXPECTED_API_ERROR_CODES,
   ExtensionBridgeCommandName,
   ExtensionBridgeEventName,
   ExtensionSocketEvents,
-  GLAMA_DEFAULT_TEMPERATURE,
   GLOBAL_SECRET_KEYS,
   GLOBAL_SETTINGS_KEYS,
   GLOBAL_STATE_KEYS,
@@ -6645,6 +6801,7 @@ export {
   commandExecutionStatusSchema,
   commandIds,
   contextCondenseSchema,
+  contextTruncationSchema,
   convertModelNameForVertex,
   customModePromptsSchema,
   customModesSettingsSchema,
@@ -6666,6 +6823,7 @@ export {
   extensionBridgeCommandSchema,
   extensionBridgeEventSchema,
   extensionInstanceSchema,
+  extractApiProviderErrorProperties,
   fauxProviders,
   featherlessDefaultModelId,
   featherlessModels,
@@ -6677,12 +6835,12 @@ export {
   getApiProtocol,
   getClaudeCodeModelId,
   getEffectiveProtocol,
+  getErrorMessage,
+  getErrorStatusCode,
   getImageGenerationProvider,
   getModelId,
   getProviderDefaultModelId,
   gitPropertiesSchema,
-  glamaDefaultModelId,
-  glamaDefaultModelInfo,
   globalSettingsSchema,
   groqDefaultModelId,
   groqModels,
@@ -6699,6 +6857,8 @@ export {
   ioIntelligenceDefaultModelId,
   ioIntelligenceModels,
   ipcMessageSchema,
+  isApiProviderError,
+  isContextManagementEvent,
   isCustomProvider,
   isDynamicProvider,
   isFauxProvider,
@@ -6787,6 +6947,7 @@ export {
   serviceTierSchema,
   serviceTiers,
   shareResponseSchema,
+  shouldReportApiErrorToTelemetry,
   shouldUseSingleFileRead,
   staticAppPropertiesSchema,
   suggestionItemSchema,