@roo-code/types 1.88.0 → 1.90.0
This diff represents the content of publicly available package versions that have been released to one of the supported registries. The information contained in this diff is provided for informational purposes only and reflects changes between package versions as they appear in their respective public registries.
- package/dist/index.cjs +358 -147
- package/dist/index.cjs.map +1 -1
- package/dist/index.d.cts +5268 -1395
- package/dist/index.d.ts +5268 -1395
- package/dist/index.js +348 -144
- package/dist/index.js.map +1 -1
- package/package.json +1 -1
package/dist/index.cjs
CHANGED
|
@@ -23,6 +23,7 @@ __export(index_exports, {
|
|
|
23
23
|
ANTHROPIC_DEFAULT_MAX_TOKENS: () => ANTHROPIC_DEFAULT_MAX_TOKENS,
|
|
24
24
|
ANTHROPIC_STYLE_PROVIDERS: () => ANTHROPIC_STYLE_PROVIDERS,
|
|
25
25
|
AWS_INFERENCE_PROFILE_MAPPING: () => AWS_INFERENCE_PROFILE_MAPPING,
|
|
26
|
+
ApiProviderError: () => ApiProviderError,
|
|
26
27
|
BEDROCK_1M_CONTEXT_MODEL_IDS: () => BEDROCK_1M_CONTEXT_MODEL_IDS,
|
|
27
28
|
BEDROCK_DEFAULT_CONTEXT: () => BEDROCK_DEFAULT_CONTEXT,
|
|
28
29
|
BEDROCK_DEFAULT_TEMPERATURE: () => BEDROCK_DEFAULT_TEMPERATURE,
|
|
@@ -32,6 +33,7 @@ __export(index_exports, {
|
|
|
32
33
|
CLAUDE_CODE_DEFAULT_MAX_OUTPUT_TOKENS: () => CLAUDE_CODE_DEFAULT_MAX_OUTPUT_TOKENS,
|
|
33
34
|
CODEBASE_INDEX_DEFAULTS: () => CODEBASE_INDEX_DEFAULTS,
|
|
34
35
|
CONSENT_COOKIE_NAME: () => CONSENT_COOKIE_NAME,
|
|
36
|
+
CONTEXT_MANAGEMENT_EVENTS: () => CONTEXT_MANAGEMENT_EVENTS,
|
|
35
37
|
COOKIE_CONSENT_EVENTS: () => COOKIE_CONSENT_EVENTS,
|
|
36
38
|
ConnectionState: () => ConnectionState,
|
|
37
39
|
DEEP_SEEK_DEFAULT_TEMPERATURE: () => DEEP_SEEK_DEFAULT_TEMPERATURE,
|
|
@@ -44,10 +46,10 @@ __export(index_exports, {
|
|
|
44
46
|
DOUBAO_API_CHAT_PATH: () => DOUBAO_API_CHAT_PATH,
|
|
45
47
|
EVALS_SETTINGS: () => EVALS_SETTINGS,
|
|
46
48
|
EVALS_TIMEOUT: () => EVALS_TIMEOUT,
|
|
49
|
+
EXPECTED_API_ERROR_CODES: () => EXPECTED_API_ERROR_CODES,
|
|
47
50
|
ExtensionBridgeCommandName: () => ExtensionBridgeCommandName,
|
|
48
51
|
ExtensionBridgeEventName: () => ExtensionBridgeEventName,
|
|
49
52
|
ExtensionSocketEvents: () => ExtensionSocketEvents,
|
|
50
|
-
GLAMA_DEFAULT_TEMPERATURE: () => GLAMA_DEFAULT_TEMPERATURE,
|
|
51
53
|
GLOBAL_SECRET_KEYS: () => GLOBAL_SECRET_KEYS,
|
|
52
54
|
GLOBAL_SETTINGS_KEYS: () => GLOBAL_SETTINGS_KEYS,
|
|
53
55
|
GLOBAL_STATE_KEYS: () => GLOBAL_STATE_KEYS,
|
|
@@ -131,6 +133,7 @@ __export(index_exports, {
|
|
|
131
133
|
commandExecutionStatusSchema: () => commandExecutionStatusSchema,
|
|
132
134
|
commandIds: () => commandIds,
|
|
133
135
|
contextCondenseSchema: () => contextCondenseSchema,
|
|
136
|
+
contextTruncationSchema: () => contextTruncationSchema,
|
|
134
137
|
convertModelNameForVertex: () => convertModelNameForVertex,
|
|
135
138
|
customModePromptsSchema: () => customModePromptsSchema,
|
|
136
139
|
customModesSettingsSchema: () => customModesSettingsSchema,
|
|
@@ -152,6 +155,7 @@ __export(index_exports, {
|
|
|
152
155
|
extensionBridgeCommandSchema: () => extensionBridgeCommandSchema,
|
|
153
156
|
extensionBridgeEventSchema: () => extensionBridgeEventSchema,
|
|
154
157
|
extensionInstanceSchema: () => extensionInstanceSchema,
|
|
158
|
+
extractApiProviderErrorProperties: () => extractApiProviderErrorProperties,
|
|
155
159
|
fauxProviders: () => fauxProviders,
|
|
156
160
|
featherlessDefaultModelId: () => featherlessDefaultModelId,
|
|
157
161
|
featherlessModels: () => featherlessModels,
|
|
@@ -163,12 +167,12 @@ __export(index_exports, {
|
|
|
163
167
|
getApiProtocol: () => getApiProtocol,
|
|
164
168
|
getClaudeCodeModelId: () => getClaudeCodeModelId,
|
|
165
169
|
getEffectiveProtocol: () => getEffectiveProtocol,
|
|
170
|
+
getErrorMessage: () => getErrorMessage,
|
|
171
|
+
getErrorStatusCode: () => getErrorStatusCode,
|
|
166
172
|
getImageGenerationProvider: () => getImageGenerationProvider,
|
|
167
173
|
getModelId: () => getModelId,
|
|
168
174
|
getProviderDefaultModelId: () => getProviderDefaultModelId,
|
|
169
175
|
gitPropertiesSchema: () => gitPropertiesSchema,
|
|
170
|
-
glamaDefaultModelId: () => glamaDefaultModelId,
|
|
171
|
-
glamaDefaultModelInfo: () => glamaDefaultModelInfo,
|
|
172
176
|
globalSettingsSchema: () => globalSettingsSchema,
|
|
173
177
|
groqDefaultModelId: () => groqDefaultModelId,
|
|
174
178
|
groqModels: () => groqModels,
|
|
@@ -185,6 +189,8 @@ __export(index_exports, {
|
|
|
185
189
|
ioIntelligenceDefaultModelId: () => ioIntelligenceDefaultModelId,
|
|
186
190
|
ioIntelligenceModels: () => ioIntelligenceModels,
|
|
187
191
|
ipcMessageSchema: () => ipcMessageSchema,
|
|
192
|
+
isApiProviderError: () => isApiProviderError,
|
|
193
|
+
isContextManagementEvent: () => isContextManagementEvent,
|
|
188
194
|
isCustomProvider: () => isCustomProvider,
|
|
189
195
|
isDynamicProvider: () => isDynamicProvider,
|
|
190
196
|
isFauxProvider: () => isFauxProvider,
|
|
@@ -273,6 +279,7 @@ __export(index_exports, {
|
|
|
273
279
|
serviceTierSchema: () => serviceTierSchema,
|
|
274
280
|
serviceTiers: () => serviceTiers,
|
|
275
281
|
shareResponseSchema: () => shareResponseSchema,
|
|
282
|
+
shouldReportApiErrorToTelemetry: () => shouldReportApiErrorToTelemetry,
|
|
276
283
|
shouldUseSingleFileRead: () => shouldUseSingleFileRead,
|
|
277
284
|
staticAppPropertiesSchema: () => staticAppPropertiesSchema,
|
|
278
285
|
suggestionItemSchema: () => suggestionItemSchema,
|
|
@@ -393,6 +400,7 @@ var clineSays = [
|
|
|
393
400
|
"diff_error",
|
|
394
401
|
"condense_context",
|
|
395
402
|
"condense_context_error",
|
|
403
|
+
"sliding_window_truncation",
|
|
396
404
|
"codebase_search_result",
|
|
397
405
|
"user_edit_todos"
|
|
398
406
|
];
|
|
@@ -405,7 +413,14 @@ var contextCondenseSchema = import_zod.z.object({
|
|
|
405
413
|
cost: import_zod.z.number(),
|
|
406
414
|
prevContextTokens: import_zod.z.number(),
|
|
407
415
|
newContextTokens: import_zod.z.number(),
|
|
408
|
-
summary: import_zod.z.string()
|
|
416
|
+
summary: import_zod.z.string(),
|
|
417
|
+
condenseId: import_zod.z.string().optional()
|
|
418
|
+
});
|
|
419
|
+
var contextTruncationSchema = import_zod.z.object({
|
|
420
|
+
truncationId: import_zod.z.string(),
|
|
421
|
+
messagesRemoved: import_zod.z.number(),
|
|
422
|
+
prevContextTokens: import_zod.z.number(),
|
|
423
|
+
newContextTokens: import_zod.z.number()
|
|
409
424
|
});
|
|
410
425
|
var clineMessageSchema = import_zod.z.object({
|
|
411
426
|
ts: import_zod.z.number(),
|
|
@@ -419,7 +434,16 @@ var clineMessageSchema = import_zod.z.object({
|
|
|
419
434
|
conversationHistoryIndex: import_zod.z.number().optional(),
|
|
420
435
|
checkpoint: import_zod.z.record(import_zod.z.string(), import_zod.z.unknown()).optional(),
|
|
421
436
|
progressStatus: toolProgressStatusSchema.optional(),
|
|
437
|
+
/**
|
|
438
|
+
* Data for successful context condensation.
|
|
439
|
+
* Present when `say: "condense_context"` and `partial: false`.
|
|
440
|
+
*/
|
|
422
441
|
contextCondense: contextCondenseSchema.optional(),
|
|
442
|
+
/**
|
|
443
|
+
* Data for sliding window truncation.
|
|
444
|
+
* Present when `say: "sliding_window_truncation"`.
|
|
445
|
+
*/
|
|
446
|
+
contextTruncation: contextTruncationSchema.optional(),
|
|
423
447
|
isProtected: import_zod.z.boolean().optional(),
|
|
424
448
|
apiProtocol: import_zod.z.union([import_zod.z.literal("openai"), import_zod.z.literal("anthropic")]).optional(),
|
|
425
449
|
isAnswered: import_zod.z.boolean().optional()
|
|
@@ -448,8 +472,8 @@ var toolNames = [
|
|
|
448
472
|
"read_file",
|
|
449
473
|
"write_to_file",
|
|
450
474
|
"apply_diff",
|
|
451
|
-
"insert_content",
|
|
452
475
|
"search_and_replace",
|
|
476
|
+
"search_replace",
|
|
453
477
|
"apply_patch",
|
|
454
478
|
"search_files",
|
|
455
479
|
"list_files",
|
|
@@ -568,7 +592,7 @@ var rooCodeEventsSchema = import_zod3.z.object({
|
|
|
568
592
|
["taskAskResponded" /* TaskAskResponded */]: import_zod3.z.tuple([import_zod3.z.string()]),
|
|
569
593
|
["taskUserMessage" /* TaskUserMessage */]: import_zod3.z.tuple([import_zod3.z.string()]),
|
|
570
594
|
["taskToolFailed" /* TaskToolFailed */]: import_zod3.z.tuple([import_zod3.z.string(), toolNamesSchema, import_zod3.z.string()]),
|
|
571
|
-
["taskTokenUsageUpdated" /* TaskTokenUsageUpdated */]: import_zod3.z.tuple([import_zod3.z.string(), tokenUsageSchema]),
|
|
595
|
+
["taskTokenUsageUpdated" /* TaskTokenUsageUpdated */]: import_zod3.z.tuple([import_zod3.z.string(), tokenUsageSchema, toolUsageSchema]),
|
|
572
596
|
["modeChanged" /* ModeChanged */]: import_zod3.z.tuple([import_zod3.z.string()]),
|
|
573
597
|
["providerProfileChanged" /* ProviderProfileChanged */]: import_zod3.z.tuple([import_zod3.z.object({ name: import_zod3.z.string(), provider: import_zod3.z.string() })])
|
|
574
598
|
});
|
|
@@ -722,9 +746,9 @@ var import_zod5 = require("zod");
|
|
|
722
746
|
var reasoningEfforts = ["low", "medium", "high"];
|
|
723
747
|
var reasoningEffortsSchema = import_zod5.z.enum(reasoningEfforts);
|
|
724
748
|
var reasoningEffortWithMinimalSchema = import_zod5.z.union([reasoningEffortsSchema, import_zod5.z.literal("minimal")]);
|
|
725
|
-
var reasoningEffortsExtended = ["none", "minimal", "low", "medium", "high"];
|
|
749
|
+
var reasoningEffortsExtended = ["none", "minimal", "low", "medium", "high", "xhigh"];
|
|
726
750
|
var reasoningEffortExtendedSchema = import_zod5.z.enum(reasoningEffortsExtended);
|
|
727
|
-
var reasoningEffortSettingValues = ["disable", "none", "minimal", "low", "medium", "high"];
|
|
751
|
+
var reasoningEffortSettingValues = ["disable", "none", "minimal", "low", "medium", "high", "xhigh"];
|
|
728
752
|
var reasoningEffortSettingSchema = import_zod5.z.enum(reasoningEffortSettingValues);
|
|
729
753
|
var verbosityLevels = ["low", "medium", "high"];
|
|
730
754
|
var verbosityLevelsSchema = import_zod5.z.enum(verbosityLevels);
|
|
@@ -752,7 +776,7 @@ var modelInfoSchema = import_zod5.z.object({
|
|
|
752
776
|
supportsTemperature: import_zod5.z.boolean().optional(),
|
|
753
777
|
defaultTemperature: import_zod5.z.number().optional(),
|
|
754
778
|
requiredReasoningBudget: import_zod5.z.boolean().optional(),
|
|
755
|
-
supportsReasoningEffort: import_zod5.z.union([import_zod5.z.boolean(), import_zod5.z.array(import_zod5.z.enum(["disable", "none", "minimal", "low", "medium", "high"]))]).optional(),
|
|
779
|
+
supportsReasoningEffort: import_zod5.z.union([import_zod5.z.boolean(), import_zod5.z.array(import_zod5.z.enum(["disable", "none", "minimal", "low", "medium", "high", "xhigh"]))]).optional(),
|
|
756
780
|
requiredReasoningEffort: import_zod5.z.boolean().optional(),
|
|
757
781
|
preserveReasoning: import_zod5.z.boolean().optional(),
|
|
758
782
|
supportedParameters: import_zod5.z.array(modelParametersSchema).optional(),
|
|
@@ -768,6 +792,8 @@ var modelInfoSchema = import_zod5.z.object({
|
|
|
768
792
|
cachableFields: import_zod5.z.array(import_zod5.z.string()).optional(),
|
|
769
793
|
// Flag to indicate if the model is deprecated and should not be used
|
|
770
794
|
deprecated: import_zod5.z.boolean().optional(),
|
|
795
|
+
// Flag to indicate if the model should hide vendor/company identity in responses
|
|
796
|
+
isStealthModel: import_zod5.z.boolean().optional(),
|
|
771
797
|
// Flag to indicate if the model is free (no cost)
|
|
772
798
|
isFree: import_zod5.z.boolean().optional(),
|
|
773
799
|
// Flag to indicate if the model supports native tool calling (OpenAI-style function calling)
|
|
@@ -834,7 +860,9 @@ var codebaseIndexConfigSchema = import_zod6.z.object({
|
|
|
834
860
|
codebaseIndexOpenAiCompatibleModelDimension: import_zod6.z.number().optional(),
|
|
835
861
|
// Bedrock specific fields
|
|
836
862
|
codebaseIndexBedrockRegion: import_zod6.z.string().optional(),
|
|
837
|
-
codebaseIndexBedrockProfile: import_zod6.z.string().optional()
|
|
863
|
+
codebaseIndexBedrockProfile: import_zod6.z.string().optional(),
|
|
864
|
+
// OpenRouter specific fields
|
|
865
|
+
codebaseIndexOpenRouterSpecificProvider: import_zod6.z.string().optional()
|
|
838
866
|
});
|
|
839
867
|
var codebaseIndexModelsSchema = import_zod6.z.object({
|
|
840
868
|
openai: import_zod6.z.record(import_zod6.z.string(), import_zod6.z.object({ dimension: import_zod6.z.number() })).optional(),
|
|
@@ -1079,7 +1107,7 @@ var ANTHROPIC_DEFAULT_MAX_TOKENS = 8192;
|
|
|
1079
1107
|
// src/providers/baseten.ts
|
|
1080
1108
|
var basetenModels = {
|
|
1081
1109
|
"moonshotai/Kimi-K2-Thinking": {
|
|
1082
|
-
maxTokens:
|
|
1110
|
+
maxTokens: 16384,
|
|
1083
1111
|
contextWindow: 262e3,
|
|
1084
1112
|
supportsImages: false,
|
|
1085
1113
|
supportsPromptCache: false,
|
|
@@ -1091,7 +1119,7 @@ var basetenModels = {
|
|
|
1091
1119
|
description: "Kimi K2 Thinking - A model with enhanced reasoning capabilities from Kimi K2"
|
|
1092
1120
|
},
|
|
1093
1121
|
"zai-org/GLM-4.6": {
|
|
1094
|
-
maxTokens:
|
|
1122
|
+
maxTokens: 16384,
|
|
1095
1123
|
contextWindow: 2e5,
|
|
1096
1124
|
supportsImages: false,
|
|
1097
1125
|
supportsPromptCache: false,
|
|
@@ -1103,7 +1131,7 @@ var basetenModels = {
|
|
|
1103
1131
|
description: "Frontier open model with advanced agentic, reasoning and coding capabilities"
|
|
1104
1132
|
},
|
|
1105
1133
|
"deepseek-ai/DeepSeek-R1": {
|
|
1106
|
-
maxTokens:
|
|
1134
|
+
maxTokens: 16384,
|
|
1107
1135
|
contextWindow: 163840,
|
|
1108
1136
|
supportsImages: false,
|
|
1109
1137
|
supportsPromptCache: false,
|
|
@@ -1114,7 +1142,7 @@ var basetenModels = {
|
|
|
1114
1142
|
description: "DeepSeek's first-generation reasoning model"
|
|
1115
1143
|
},
|
|
1116
1144
|
"deepseek-ai/DeepSeek-R1-0528": {
|
|
1117
|
-
maxTokens:
|
|
1145
|
+
maxTokens: 16384,
|
|
1118
1146
|
contextWindow: 163840,
|
|
1119
1147
|
supportsImages: false,
|
|
1120
1148
|
supportsPromptCache: false,
|
|
@@ -1125,7 +1153,7 @@ var basetenModels = {
|
|
|
1125
1153
|
description: "The latest revision of DeepSeek's first-generation reasoning model"
|
|
1126
1154
|
},
|
|
1127
1155
|
"deepseek-ai/DeepSeek-V3-0324": {
|
|
1128
|
-
maxTokens:
|
|
1156
|
+
maxTokens: 16384,
|
|
1129
1157
|
contextWindow: 163840,
|
|
1130
1158
|
supportsImages: false,
|
|
1131
1159
|
supportsPromptCache: false,
|
|
@@ -1136,7 +1164,7 @@ var basetenModels = {
|
|
|
1136
1164
|
description: "Fast general-purpose LLM with enhanced reasoning capabilities"
|
|
1137
1165
|
},
|
|
1138
1166
|
"deepseek-ai/DeepSeek-V3.1": {
|
|
1139
|
-
maxTokens:
|
|
1167
|
+
maxTokens: 16384,
|
|
1140
1168
|
contextWindow: 163840,
|
|
1141
1169
|
supportsImages: false,
|
|
1142
1170
|
supportsPromptCache: false,
|
|
@@ -1146,8 +1174,20 @@ var basetenModels = {
|
|
|
1146
1174
|
cacheReadsPrice: 0,
|
|
1147
1175
|
description: "Extremely capable general-purpose LLM with hybrid reasoning capabilities and advanced tool calling"
|
|
1148
1176
|
},
|
|
1177
|
+
"deepseek-ai/DeepSeek-V3.2": {
|
|
1178
|
+
maxTokens: 16384,
|
|
1179
|
+
contextWindow: 163840,
|
|
1180
|
+
supportsImages: false,
|
|
1181
|
+
supportsPromptCache: false,
|
|
1182
|
+
supportsNativeTools: true,
|
|
1183
|
+
inputPrice: 0.3,
|
|
1184
|
+
outputPrice: 0.45,
|
|
1185
|
+
cacheWritesPrice: 0,
|
|
1186
|
+
cacheReadsPrice: 0,
|
|
1187
|
+
description: "DeepSeek's hybrid reasoning model with efficient long context scaling with GPT-5 level performance"
|
|
1188
|
+
},
|
|
1149
1189
|
"Qwen/Qwen3-235B-A22B-Instruct-2507": {
|
|
1150
|
-
maxTokens:
|
|
1190
|
+
maxTokens: 16384,
|
|
1151
1191
|
contextWindow: 262144,
|
|
1152
1192
|
supportsImages: false,
|
|
1153
1193
|
supportsPromptCache: false,
|
|
@@ -1158,7 +1198,7 @@ var basetenModels = {
|
|
|
1158
1198
|
description: "Mixture-of-experts LLM with math and reasoning capabilities"
|
|
1159
1199
|
},
|
|
1160
1200
|
"Qwen/Qwen3-Coder-480B-A35B-Instruct": {
|
|
1161
|
-
maxTokens:
|
|
1201
|
+
maxTokens: 16384,
|
|
1162
1202
|
contextWindow: 262144,
|
|
1163
1203
|
supportsImages: false,
|
|
1164
1204
|
supportsPromptCache: false,
|
|
@@ -1169,7 +1209,7 @@ var basetenModels = {
|
|
|
1169
1209
|
description: "Mixture-of-experts LLM with advanced coding and reasoning capabilities"
|
|
1170
1210
|
},
|
|
1171
1211
|
"openai/gpt-oss-120b": {
|
|
1172
|
-
maxTokens:
|
|
1212
|
+
maxTokens: 16384,
|
|
1173
1213
|
contextWindow: 128072,
|
|
1174
1214
|
supportsImages: false,
|
|
1175
1215
|
supportsPromptCache: false,
|
|
@@ -1181,7 +1221,7 @@ var basetenModels = {
|
|
|
1181
1221
|
description: "Extremely capable general-purpose LLM with strong, controllable reasoning capabilities"
|
|
1182
1222
|
},
|
|
1183
1223
|
"moonshotai/Kimi-K2-Instruct-0905": {
|
|
1184
|
-
maxTokens:
|
|
1224
|
+
maxTokens: 16384,
|
|
1185
1225
|
contextWindow: 262e3,
|
|
1186
1226
|
supportsImages: false,
|
|
1187
1227
|
supportsPromptCache: false,
|
|
@@ -1205,6 +1245,7 @@ var bedrockModels = {
|
|
|
1205
1245
|
supportsImages: true,
|
|
1206
1246
|
supportsPromptCache: true,
|
|
1207
1247
|
supportsReasoningBudget: true,
|
|
1248
|
+
supportsNativeTools: true,
|
|
1208
1249
|
inputPrice: 3,
|
|
1209
1250
|
outputPrice: 15,
|
|
1210
1251
|
cacheWritesPrice: 3.75,
|
|
@@ -1218,6 +1259,7 @@ var bedrockModels = {
|
|
|
1218
1259
|
contextWindow: 3e5,
|
|
1219
1260
|
supportsImages: true,
|
|
1220
1261
|
supportsPromptCache: true,
|
|
1262
|
+
supportsNativeTools: true,
|
|
1221
1263
|
inputPrice: 0.8,
|
|
1222
1264
|
outputPrice: 3.2,
|
|
1223
1265
|
cacheWritesPrice: 0.8,
|
|
@@ -1233,6 +1275,7 @@ var bedrockModels = {
|
|
|
1233
1275
|
contextWindow: 3e5,
|
|
1234
1276
|
supportsImages: true,
|
|
1235
1277
|
supportsPromptCache: false,
|
|
1278
|
+
supportsNativeTools: true,
|
|
1236
1279
|
inputPrice: 1,
|
|
1237
1280
|
outputPrice: 4,
|
|
1238
1281
|
cacheWritesPrice: 1,
|
|
@@ -1246,6 +1289,7 @@ var bedrockModels = {
|
|
|
1246
1289
|
contextWindow: 3e5,
|
|
1247
1290
|
supportsImages: true,
|
|
1248
1291
|
supportsPromptCache: true,
|
|
1292
|
+
supportsNativeTools: true,
|
|
1249
1293
|
inputPrice: 0.06,
|
|
1250
1294
|
outputPrice: 0.24,
|
|
1251
1295
|
cacheWritesPrice: 0.06,
|
|
@@ -1261,6 +1305,7 @@ var bedrockModels = {
|
|
|
1261
1305
|
contextWindow: 128e3,
|
|
1262
1306
|
supportsImages: false,
|
|
1263
1307
|
supportsPromptCache: true,
|
|
1308
|
+
supportsNativeTools: true,
|
|
1264
1309
|
inputPrice: 0.035,
|
|
1265
1310
|
outputPrice: 0.14,
|
|
1266
1311
|
cacheWritesPrice: 0.035,
|
|
@@ -1277,6 +1322,7 @@ var bedrockModels = {
|
|
|
1277
1322
|
supportsImages: true,
|
|
1278
1323
|
supportsPromptCache: true,
|
|
1279
1324
|
supportsReasoningBudget: true,
|
|
1325
|
+
supportsNativeTools: true,
|
|
1280
1326
|
inputPrice: 3,
|
|
1281
1327
|
outputPrice: 15,
|
|
1282
1328
|
cacheWritesPrice: 3.75,
|
|
@@ -1291,6 +1337,7 @@ var bedrockModels = {
|
|
|
1291
1337
|
supportsImages: true,
|
|
1292
1338
|
supportsPromptCache: true,
|
|
1293
1339
|
supportsReasoningBudget: true,
|
|
1340
|
+
supportsNativeTools: true,
|
|
1294
1341
|
inputPrice: 15,
|
|
1295
1342
|
outputPrice: 75,
|
|
1296
1343
|
cacheWritesPrice: 18.75,
|
|
@@ -1305,6 +1352,7 @@ var bedrockModels = {
|
|
|
1305
1352
|
supportsImages: true,
|
|
1306
1353
|
supportsPromptCache: true,
|
|
1307
1354
|
supportsReasoningBudget: true,
|
|
1355
|
+
supportsNativeTools: true,
|
|
1308
1356
|
inputPrice: 5,
|
|
1309
1357
|
outputPrice: 25,
|
|
1310
1358
|
cacheWritesPrice: 6.25,
|
|
@@ -1319,6 +1367,7 @@ var bedrockModels = {
|
|
|
1319
1367
|
supportsImages: true,
|
|
1320
1368
|
supportsPromptCache: true,
|
|
1321
1369
|
supportsReasoningBudget: true,
|
|
1370
|
+
supportsNativeTools: true,
|
|
1322
1371
|
inputPrice: 15,
|
|
1323
1372
|
outputPrice: 75,
|
|
1324
1373
|
cacheWritesPrice: 18.75,
|
|
@@ -1333,6 +1382,7 @@ var bedrockModels = {
|
|
|
1333
1382
|
supportsImages: true,
|
|
1334
1383
|
supportsPromptCache: true,
|
|
1335
1384
|
supportsReasoningBudget: true,
|
|
1385
|
+
supportsNativeTools: true,
|
|
1336
1386
|
inputPrice: 3,
|
|
1337
1387
|
outputPrice: 15,
|
|
1338
1388
|
cacheWritesPrice: 3.75,
|
|
@@ -1346,6 +1396,7 @@ var bedrockModels = {
|
|
|
1346
1396
|
contextWindow: 2e5,
|
|
1347
1397
|
supportsImages: true,
|
|
1348
1398
|
supportsPromptCache: true,
|
|
1399
|
+
supportsNativeTools: true,
|
|
1349
1400
|
inputPrice: 3,
|
|
1350
1401
|
outputPrice: 15,
|
|
1351
1402
|
cacheWritesPrice: 3.75,
|
|
@@ -1359,6 +1410,7 @@ var bedrockModels = {
|
|
|
1359
1410
|
contextWindow: 2e5,
|
|
1360
1411
|
supportsImages: false,
|
|
1361
1412
|
supportsPromptCache: true,
|
|
1413
|
+
supportsNativeTools: true,
|
|
1362
1414
|
inputPrice: 0.8,
|
|
1363
1415
|
outputPrice: 4,
|
|
1364
1416
|
cacheWritesPrice: 1,
|
|
@@ -1373,6 +1425,7 @@ var bedrockModels = {
|
|
|
1373
1425
|
supportsImages: true,
|
|
1374
1426
|
supportsPromptCache: true,
|
|
1375
1427
|
supportsReasoningBudget: true,
|
|
1428
|
+
supportsNativeTools: true,
|
|
1376
1429
|
inputPrice: 1,
|
|
1377
1430
|
outputPrice: 5,
|
|
1378
1431
|
cacheWritesPrice: 1.25,
|
|
@@ -1388,6 +1441,7 @@ var bedrockModels = {
|
|
|
1388
1441
|
contextWindow: 2e5,
|
|
1389
1442
|
supportsImages: true,
|
|
1390
1443
|
supportsPromptCache: false,
|
|
1444
|
+
supportsNativeTools: true,
|
|
1391
1445
|
inputPrice: 3,
|
|
1392
1446
|
outputPrice: 15
|
|
1393
1447
|
},
|
|
@@ -1396,6 +1450,7 @@ var bedrockModels = {
|
|
|
1396
1450
|
contextWindow: 2e5,
|
|
1397
1451
|
supportsImages: true,
|
|
1398
1452
|
supportsPromptCache: false,
|
|
1453
|
+
supportsNativeTools: true,
|
|
1399
1454
|
inputPrice: 15,
|
|
1400
1455
|
outputPrice: 75
|
|
1401
1456
|
},
|
|
@@ -1404,6 +1459,7 @@ var bedrockModels = {
|
|
|
1404
1459
|
contextWindow: 2e5,
|
|
1405
1460
|
supportsImages: true,
|
|
1406
1461
|
supportsPromptCache: false,
|
|
1462
|
+
supportsNativeTools: true,
|
|
1407
1463
|
inputPrice: 3,
|
|
1408
1464
|
outputPrice: 15
|
|
1409
1465
|
},
|
|
@@ -1412,6 +1468,7 @@ var bedrockModels = {
|
|
|
1412
1468
|
contextWindow: 2e5,
|
|
1413
1469
|
supportsImages: true,
|
|
1414
1470
|
supportsPromptCache: false,
|
|
1471
|
+
supportsNativeTools: true,
|
|
1415
1472
|
inputPrice: 0.25,
|
|
1416
1473
|
outputPrice: 1.25
|
|
1417
1474
|
},
|
|
@@ -1420,6 +1477,7 @@ var bedrockModels = {
|
|
|
1420
1477
|
contextWindow: 1e5,
|
|
1421
1478
|
supportsImages: false,
|
|
1422
1479
|
supportsPromptCache: false,
|
|
1480
|
+
supportsNativeTools: true,
|
|
1423
1481
|
inputPrice: 8,
|
|
1424
1482
|
outputPrice: 24,
|
|
1425
1483
|
description: "Claude 2.1"
|
|
@@ -1429,6 +1487,7 @@ var bedrockModels = {
|
|
|
1429
1487
|
contextWindow: 1e5,
|
|
1430
1488
|
supportsImages: false,
|
|
1431
1489
|
supportsPromptCache: false,
|
|
1490
|
+
supportsNativeTools: true,
|
|
1432
1491
|
inputPrice: 8,
|
|
1433
1492
|
outputPrice: 24,
|
|
1434
1493
|
description: "Claude 2.0"
|
|
@@ -1438,6 +1497,7 @@ var bedrockModels = {
|
|
|
1438
1497
|
contextWindow: 1e5,
|
|
1439
1498
|
supportsImages: false,
|
|
1440
1499
|
supportsPromptCache: false,
|
|
1500
|
+
supportsNativeTools: true,
|
|
1441
1501
|
inputPrice: 0.8,
|
|
1442
1502
|
outputPrice: 2.4,
|
|
1443
1503
|
description: "Claude Instant"
|
|
@@ -1447,6 +1507,7 @@ var bedrockModels = {
|
|
|
1447
1507
|
contextWindow: 128e3,
|
|
1448
1508
|
supportsImages: false,
|
|
1449
1509
|
supportsPromptCache: false,
|
|
1510
|
+
supportsNativeTools: true,
|
|
1450
1511
|
inputPrice: 1.35,
|
|
1451
1512
|
outputPrice: 5.4
|
|
1452
1513
|
},
|
|
@@ -1455,6 +1516,7 @@ var bedrockModels = {
|
|
|
1455
1516
|
contextWindow: 128e3,
|
|
1456
1517
|
supportsImages: false,
|
|
1457
1518
|
supportsPromptCache: false,
|
|
1519
|
+
supportsNativeTools: true,
|
|
1458
1520
|
inputPrice: 0.5,
|
|
1459
1521
|
outputPrice: 1.5,
|
|
1460
1522
|
description: "GPT-OSS 20B - Optimized for low latency and local/specialized use cases"
|
|
@@ -1464,6 +1526,7 @@ var bedrockModels = {
|
|
|
1464
1526
|
contextWindow: 128e3,
|
|
1465
1527
|
supportsImages: false,
|
|
1466
1528
|
supportsPromptCache: false,
|
|
1529
|
+
supportsNativeTools: true,
|
|
1467
1530
|
inputPrice: 2,
|
|
1468
1531
|
outputPrice: 6,
|
|
1469
1532
|
description: "GPT-OSS 120B - Production-ready, general-purpose, high-reasoning model"
|
|
@@ -1473,6 +1536,7 @@ var bedrockModels = {
|
|
|
1473
1536
|
contextWindow: 128e3,
|
|
1474
1537
|
supportsImages: false,
|
|
1475
1538
|
supportsPromptCache: false,
|
|
1539
|
+
supportsNativeTools: true,
|
|
1476
1540
|
inputPrice: 0.72,
|
|
1477
1541
|
outputPrice: 0.72,
|
|
1478
1542
|
description: "Llama 3.3 Instruct (70B)"
|
|
@@ -1482,6 +1546,7 @@ var bedrockModels = {
|
|
|
1482
1546
|
contextWindow: 128e3,
|
|
1483
1547
|
supportsImages: true,
|
|
1484
1548
|
supportsPromptCache: false,
|
|
1549
|
+
supportsNativeTools: true,
|
|
1485
1550
|
inputPrice: 0.72,
|
|
1486
1551
|
outputPrice: 0.72,
|
|
1487
1552
|
description: "Llama 3.2 Instruct (90B)"
|
|
@@ -1491,6 +1556,7 @@ var bedrockModels = {
|
|
|
1491
1556
|
contextWindow: 128e3,
|
|
1492
1557
|
supportsImages: true,
|
|
1493
1558
|
supportsPromptCache: false,
|
|
1559
|
+
supportsNativeTools: true,
|
|
1494
1560
|
inputPrice: 0.16,
|
|
1495
1561
|
outputPrice: 0.16,
|
|
1496
1562
|
description: "Llama 3.2 Instruct (11B)"
|
|
@@ -1500,6 +1566,7 @@ var bedrockModels = {
|
|
|
1500
1566
|
contextWindow: 128e3,
|
|
1501
1567
|
supportsImages: false,
|
|
1502
1568
|
supportsPromptCache: false,
|
|
1569
|
+
supportsNativeTools: true,
|
|
1503
1570
|
inputPrice: 0.15,
|
|
1504
1571
|
outputPrice: 0.15,
|
|
1505
1572
|
description: "Llama 3.2 Instruct (3B)"
|
|
@@ -1509,6 +1576,7 @@ var bedrockModels = {
|
|
|
1509
1576
|
contextWindow: 128e3,
|
|
1510
1577
|
supportsImages: false,
|
|
1511
1578
|
supportsPromptCache: false,
|
|
1579
|
+
supportsNativeTools: true,
|
|
1512
1580
|
inputPrice: 0.1,
|
|
1513
1581
|
outputPrice: 0.1,
|
|
1514
1582
|
description: "Llama 3.2 Instruct (1B)"
|
|
@@ -1518,6 +1586,7 @@ var bedrockModels = {
|
|
|
1518
1586
|
contextWindow: 128e3,
|
|
1519
1587
|
supportsImages: false,
|
|
1520
1588
|
supportsPromptCache: false,
|
|
1589
|
+
supportsNativeTools: true,
|
|
1521
1590
|
inputPrice: 2.4,
|
|
1522
1591
|
outputPrice: 2.4,
|
|
1523
1592
|
description: "Llama 3.1 Instruct (405B)"
|
|
@@ -1527,6 +1596,7 @@ var bedrockModels = {
|
|
|
1527
1596
|
contextWindow: 128e3,
|
|
1528
1597
|
supportsImages: false,
|
|
1529
1598
|
supportsPromptCache: false,
|
|
1599
|
+
supportsNativeTools: true,
|
|
1530
1600
|
inputPrice: 0.72,
|
|
1531
1601
|
outputPrice: 0.72,
|
|
1532
1602
|
description: "Llama 3.1 Instruct (70B)"
|
|
@@ -1536,6 +1606,7 @@ var bedrockModels = {
|
|
|
1536
1606
|
contextWindow: 128e3,
|
|
1537
1607
|
supportsImages: false,
|
|
1538
1608
|
supportsPromptCache: false,
|
|
1609
|
+
supportsNativeTools: true,
|
|
1539
1610
|
inputPrice: 0.9,
|
|
1540
1611
|
outputPrice: 0.9,
|
|
1541
1612
|
description: "Llama 3.1 Instruct (70B) (w/ latency optimized inference)"
|
|
@@ -1545,6 +1616,7 @@ var bedrockModels = {
|
|
|
1545
1616
|
contextWindow: 8e3,
|
|
1546
1617
|
supportsImages: false,
|
|
1547
1618
|
supportsPromptCache: false,
|
|
1619
|
+
supportsNativeTools: true,
|
|
1548
1620
|
inputPrice: 0.22,
|
|
1549
1621
|
outputPrice: 0.22,
|
|
1550
1622
|
description: "Llama 3.1 Instruct (8B)"
|
|
@@ -1554,6 +1626,7 @@ var bedrockModels = {
|
|
|
1554
1626
|
contextWindow: 8e3,
|
|
1555
1627
|
supportsImages: false,
|
|
1556
1628
|
supportsPromptCache: false,
|
|
1629
|
+
supportsNativeTools: true,
|
|
1557
1630
|
inputPrice: 2.65,
|
|
1558
1631
|
outputPrice: 3.5
|
|
1559
1632
|
},
|
|
@@ -1562,6 +1635,7 @@ var bedrockModels = {
|
|
|
1562
1635
|
contextWindow: 4e3,
|
|
1563
1636
|
supportsImages: false,
|
|
1564
1637
|
supportsPromptCache: false,
|
|
1638
|
+
supportsNativeTools: true,
|
|
1565
1639
|
inputPrice: 0.3,
|
|
1566
1640
|
outputPrice: 0.6
|
|
1567
1641
|
},
|
|
@@ -1570,6 +1644,7 @@ var bedrockModels = {
|
|
|
1570
1644
|
contextWindow: 8e3,
|
|
1571
1645
|
supportsImages: false,
|
|
1572
1646
|
supportsPromptCache: false,
|
|
1647
|
+
supportsNativeTools: true,
|
|
1573
1648
|
inputPrice: 0.15,
|
|
1574
1649
|
outputPrice: 0.2,
|
|
1575
1650
|
description: "Amazon Titan Text Lite"
|
|
@@ -1579,6 +1654,7 @@ var bedrockModels = {
|
|
|
1579
1654
|
contextWindow: 8e3,
|
|
1580
1655
|
supportsImages: false,
|
|
1581
1656
|
supportsPromptCache: false,
|
|
1657
|
+
supportsNativeTools: true,
|
|
1582
1658
|
inputPrice: 0.2,
|
|
1583
1659
|
outputPrice: 0.6,
|
|
1584
1660
|
description: "Amazon Titan Text Express"
|
|
@@ -1598,6 +1674,52 @@ var bedrockModels = {
|
|
|
1598
1674
|
supportsPromptCache: false,
|
|
1599
1675
|
inputPrice: 0.02,
|
|
1600
1676
|
description: "Amazon Titan Text Embeddings V2"
|
|
1677
|
+
},
|
|
1678
|
+
"moonshot.kimi-k2-thinking": {
|
|
1679
|
+
maxTokens: 32e3,
|
|
1680
|
+
contextWindow: 262144,
|
|
1681
|
+
supportsImages: false,
|
|
1682
|
+
supportsPromptCache: false,
|
|
1683
|
+
supportsNativeTools: true,
|
|
1684
|
+
defaultToolProtocol: "native",
|
|
1685
|
+
preserveReasoning: true,
|
|
1686
|
+
inputPrice: 0.6,
|
|
1687
|
+
outputPrice: 2.5,
|
|
1688
|
+
description: "Kimi K2 Thinking (1T parameter MoE model with 32B active parameters)"
|
|
1689
|
+
},
|
|
1690
|
+
"minimax.minimax-m2": {
|
|
1691
|
+
maxTokens: 16384,
|
|
1692
|
+
contextWindow: 196608,
|
|
1693
|
+
supportsImages: false,
|
|
1694
|
+
supportsPromptCache: false,
|
|
1695
|
+
supportsNativeTools: true,
|
|
1696
|
+
defaultToolProtocol: "native",
|
|
1697
|
+
preserveReasoning: true,
|
|
1698
|
+
inputPrice: 0.3,
|
|
1699
|
+
outputPrice: 1.2,
|
|
1700
|
+
description: "MiniMax M2 (230B parameter MoE model with 10B active parameters)"
|
|
1701
|
+
},
|
|
1702
|
+
"qwen.qwen3-next-80b-a3b": {
|
|
1703
|
+
maxTokens: 8192,
|
|
1704
|
+
contextWindow: 262144,
|
|
1705
|
+
supportsImages: false,
|
|
1706
|
+
supportsPromptCache: false,
|
|
1707
|
+
supportsNativeTools: true,
|
|
1708
|
+
defaultToolProtocol: "native",
|
|
1709
|
+
inputPrice: 0.15,
|
|
1710
|
+
outputPrice: 1.2,
|
|
1711
|
+
description: "Qwen3 Next 80B (MoE model with 3B active parameters)"
|
|
1712
|
+
},
|
|
1713
|
+
"qwen.qwen3-coder-480b-a35b-v1:0": {
|
|
1714
|
+
maxTokens: 8192,
|
|
1715
|
+
contextWindow: 262144,
|
|
1716
|
+
supportsImages: false,
|
|
1717
|
+
supportsPromptCache: false,
|
|
1718
|
+
supportsNativeTools: true,
|
|
1719
|
+
defaultToolProtocol: "native",
|
|
1720
|
+
inputPrice: 0.45,
|
|
1721
|
+
outputPrice: 1.8,
|
|
1722
|
+
description: "Qwen3 Coder 480B (MoE model with 35B active parameters)"
|
|
1601
1723
|
}
|
|
1602
1724
|
};
|
|
1603
1725
|
var BEDROCK_DEFAULT_TEMPERATURE = 0.3;
|
|
@@ -1663,47 +1785,56 @@ var BEDROCK_GLOBAL_INFERENCE_MODEL_IDS = [
|
|
|
1663
1785
|
var cerebrasDefaultModelId = "gpt-oss-120b";
|
|
1664
1786
|
var cerebrasModels = {
|
|
1665
1787
|
"zai-glm-4.6": {
|
|
1666
|
-
maxTokens:
|
|
1667
|
-
//
|
|
1788
|
+
maxTokens: 8192,
|
|
1789
|
+
// Conservative default to avoid premature rate limiting (Cerebras reserves quota upfront)
|
|
1668
1790
|
contextWindow: 131072,
|
|
1669
1791
|
supportsImages: false,
|
|
1670
1792
|
supportsPromptCache: false,
|
|
1793
|
+
supportsNativeTools: true,
|
|
1671
1794
|
inputPrice: 0,
|
|
1672
1795
|
outputPrice: 0,
|
|
1673
1796
|
description: "Highly intelligent general purpose model with up to 1,000 tokens/s"
|
|
1674
1797
|
},
|
|
1675
1798
|
"qwen-3-235b-a22b-instruct-2507": {
|
|
1676
|
-
maxTokens:
|
|
1799
|
+
maxTokens: 8192,
|
|
1800
|
+
// Conservative default to avoid premature rate limiting
|
|
1677
1801
|
contextWindow: 64e3,
|
|
1678
1802
|
supportsImages: false,
|
|
1679
1803
|
supportsPromptCache: false,
|
|
1804
|
+
supportsNativeTools: true,
|
|
1680
1805
|
inputPrice: 0,
|
|
1681
1806
|
outputPrice: 0,
|
|
1682
1807
|
description: "Intelligent model with ~1400 tokens/s"
|
|
1683
1808
|
},
|
|
1684
1809
|
"llama-3.3-70b": {
|
|
1685
|
-
maxTokens:
|
|
1810
|
+
maxTokens: 8192,
|
|
1811
|
+
// Conservative default to avoid premature rate limiting
|
|
1686
1812
|
contextWindow: 64e3,
|
|
1687
1813
|
supportsImages: false,
|
|
1688
1814
|
supportsPromptCache: false,
|
|
1815
|
+
supportsNativeTools: true,
|
|
1689
1816
|
inputPrice: 0,
|
|
1690
1817
|
outputPrice: 0,
|
|
1691
1818
|
description: "Powerful model with ~2600 tokens/s"
|
|
1692
1819
|
},
|
|
1693
1820
|
"qwen-3-32b": {
|
|
1694
|
-
maxTokens:
|
|
1821
|
+
maxTokens: 8192,
|
|
1822
|
+
// Conservative default to avoid premature rate limiting
|
|
1695
1823
|
contextWindow: 64e3,
|
|
1696
1824
|
supportsImages: false,
|
|
1697
1825
|
supportsPromptCache: false,
|
|
1826
|
+
supportsNativeTools: true,
|
|
1698
1827
|
inputPrice: 0,
|
|
1699
1828
|
outputPrice: 0,
|
|
1700
1829
|
description: "SOTA coding performance with ~2500 tokens/s"
|
|
1701
1830
|
},
|
|
1702
1831
|
"gpt-oss-120b": {
|
|
1703
|
-
maxTokens:
|
|
1832
|
+
maxTokens: 8192,
|
|
1833
|
+
// Conservative default to avoid premature rate limiting
|
|
1704
1834
|
contextWindow: 64e3,
|
|
1705
1835
|
supportsImages: false,
|
|
1706
1836
|
supportsPromptCache: false,
|
|
1837
|
+
supportsNativeTools: true,
|
|
1707
1838
|
inputPrice: 0,
|
|
1708
1839
|
outputPrice: 0,
|
|
1709
1840
|
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"
|
|
@@ -2224,35 +2355,37 @@ var deepSeekModels = {
|
|
|
2224
2355
|
supportsImages: false,
|
|
2225
2356
|
supportsPromptCache: true,
|
|
2226
2357
|
supportsNativeTools: true,
|
|
2227
|
-
|
|
2228
|
-
|
|
2229
|
-
|
|
2230
|
-
|
|
2231
|
-
|
|
2232
|
-
|
|
2233
|
-
|
|
2234
|
-
|
|
2235
|
-
|
|
2358
|
+
defaultToolProtocol: "native",
|
|
2359
|
+
inputPrice: 0.28,
|
|
2360
|
+
// $0.28 per million tokens (cache miss) - Updated Dec 9, 2025
|
|
2361
|
+
outputPrice: 0.42,
|
|
2362
|
+
// $0.42 per million tokens - Updated Dec 9, 2025
|
|
2363
|
+
cacheWritesPrice: 0.28,
|
|
2364
|
+
// $0.28 per million tokens (cache miss) - Updated Dec 9, 2025
|
|
2365
|
+
cacheReadsPrice: 0.028,
|
|
2366
|
+
// $0.028 per million tokens (cache hit) - Updated Dec 9, 2025
|
|
2367
|
+
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).`
|
|
2236
2368
|
},
|
|
2237
2369
|
"deepseek-reasoner": {
|
|
2238
|
-
maxTokens:
|
|
2239
|
-
//
|
|
2370
|
+
maxTokens: 8192,
|
|
2371
|
+
// 8K max output
|
|
2240
2372
|
contextWindow: 128e3,
|
|
2241
2373
|
supportsImages: false,
|
|
2242
2374
|
supportsPromptCache: true,
|
|
2243
2375
|
supportsNativeTools: true,
|
|
2244
|
-
|
|
2245
|
-
|
|
2246
|
-
|
|
2247
|
-
|
|
2248
|
-
|
|
2249
|
-
|
|
2250
|
-
|
|
2251
|
-
|
|
2252
|
-
|
|
2376
|
+
defaultToolProtocol: "native",
|
|
2377
|
+
inputPrice: 0.28,
|
|
2378
|
+
// $0.28 per million tokens (cache miss) - Updated Dec 9, 2025
|
|
2379
|
+
outputPrice: 0.42,
|
|
2380
|
+
// $0.42 per million tokens - Updated Dec 9, 2025
|
|
2381
|
+
cacheWritesPrice: 0.28,
|
|
2382
|
+
// $0.28 per million tokens (cache miss) - Updated Dec 9, 2025
|
|
2383
|
+
cacheReadsPrice: 0.028,
|
|
2384
|
+
// $0.028 per million tokens (cache hit) - Updated Dec 9, 2025
|
|
2385
|
+
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).`
|
|
2253
2386
|
}
|
|
2254
2387
|
};
|
|
2255
|
-
var DEEP_SEEK_DEFAULT_TEMPERATURE = 0
|
|
2388
|
+
var DEEP_SEEK_DEFAULT_TEMPERATURE = 0;
|
|
2256
2389
|
|
|
2257
2390
|
// src/providers/doubao.ts
|
|
2258
2391
|
var doubaoDefaultModelId = "doubao-seed-1-6-250615";
|
|
@@ -2707,21 +2840,6 @@ var geminiModels = {
|
|
|
2707
2840
|
}
|
|
2708
2841
|
};
|
|
2709
2842
|
|
|
2710
|
-
// src/providers/glama.ts
|
|
2711
|
-
var glamaDefaultModelId = "anthropic/claude-3-7-sonnet";
|
|
2712
|
-
var glamaDefaultModelInfo = {
|
|
2713
|
-
maxTokens: 8192,
|
|
2714
|
-
contextWindow: 2e5,
|
|
2715
|
-
supportsImages: true,
|
|
2716
|
-
supportsPromptCache: true,
|
|
2717
|
-
inputPrice: 3,
|
|
2718
|
-
outputPrice: 15,
|
|
2719
|
-
cacheWritesPrice: 3.75,
|
|
2720
|
-
cacheReadsPrice: 0.3,
|
|
2721
|
-
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)"
|
|
2722
|
-
};
|
|
2723
|
-
var GLAMA_DEFAULT_TEMPERATURE = 0;
|
|
2724
|
-
|
|
2725
2843
|
// src/providers/groq.ts
|
|
2726
2844
|
var groqDefaultModelId = "moonshotai/kimi-k2-instruct-0905";
|
|
2727
2845
|
var groqModels = {
|
|
@@ -2902,6 +3020,7 @@ var litellmDefaultModelInfo = {
|
|
|
2902
3020
|
contextWindow: 2e5,
|
|
2903
3021
|
supportsImages: true,
|
|
2904
3022
|
supportsPromptCache: true,
|
|
3023
|
+
supportsNativeTools: true,
|
|
2905
3024
|
inputPrice: 3,
|
|
2906
3025
|
outputPrice: 15,
|
|
2907
3026
|
cacheWritesPrice: 3.75,
|
|
@@ -3089,6 +3208,7 @@ var ollamaDefaultModelInfo = {
|
|
|
3089
3208
|
contextWindow: 2e5,
|
|
3090
3209
|
supportsImages: true,
|
|
3091
3210
|
supportsPromptCache: true,
|
|
3211
|
+
supportsNativeTools: true,
|
|
3092
3212
|
inputPrice: 0,
|
|
3093
3213
|
outputPrice: 0,
|
|
3094
3214
|
cacheWritesPrice: 0,
|
|
@@ -3099,10 +3219,30 @@ var ollamaDefaultModelInfo = {
|
|
|
3099
3219
|
// src/providers/openai.ts
|
|
3100
3220
|
var openAiNativeDefaultModelId = "gpt-5.1";
|
|
3101
3221
|
var openAiNativeModels = {
|
|
3222
|
+
"gpt-5.1-codex-max": {
|
|
3223
|
+
maxTokens: 128e3,
|
|
3224
|
+
contextWindow: 4e5,
|
|
3225
|
+
supportsNativeTools: true,
|
|
3226
|
+
includedTools: ["apply_patch"],
|
|
3227
|
+
excludedTools: ["apply_diff", "write_to_file"],
|
|
3228
|
+
supportsImages: true,
|
|
3229
|
+
supportsPromptCache: true,
|
|
3230
|
+
promptCacheRetention: "24h",
|
|
3231
|
+
supportsReasoningEffort: ["low", "medium", "high", "xhigh"],
|
|
3232
|
+
reasoningEffort: "medium",
|
|
3233
|
+
inputPrice: 1.25,
|
|
3234
|
+
outputPrice: 10,
|
|
3235
|
+
cacheReadsPrice: 0.125,
|
|
3236
|
+
supportsTemperature: false,
|
|
3237
|
+
tiers: [{ name: "priority", contextWindow: 4e5, inputPrice: 2.5, outputPrice: 20, cacheReadsPrice: 0.25 }],
|
|
3238
|
+
description: "GPT-5.1 Codex Max: Our most intelligent coding model optimized for long-horizon, agentic coding tasks"
|
|
3239
|
+
},
|
|
3102
3240
|
"gpt-5.1": {
|
|
3103
3241
|
maxTokens: 128e3,
|
|
3104
3242
|
contextWindow: 4e5,
|
|
3105
3243
|
supportsNativeTools: true,
|
|
3244
|
+
includedTools: ["apply_patch"],
|
|
3245
|
+
excludedTools: ["apply_diff", "write_to_file"],
|
|
3106
3246
|
supportsImages: true,
|
|
3107
3247
|
supportsPromptCache: true,
|
|
3108
3248
|
promptCacheRetention: "24h",
|
|
@@ -3123,6 +3263,8 @@ var openAiNativeModels = {
|
|
|
3123
3263
|
maxTokens: 128e3,
|
|
3124
3264
|
contextWindow: 4e5,
|
|
3125
3265
|
supportsNativeTools: true,
|
|
3266
|
+
includedTools: ["apply_patch"],
|
|
3267
|
+
excludedTools: ["apply_diff", "write_to_file"],
|
|
3126
3268
|
supportsImages: true,
|
|
3127
3269
|
supportsPromptCache: true,
|
|
3128
3270
|
promptCacheRetention: "24h",
|
|
@@ -3139,6 +3281,8 @@ var openAiNativeModels = {
|
|
|
3139
3281
|
maxTokens: 128e3,
|
|
3140
3282
|
contextWindow: 4e5,
|
|
3141
3283
|
supportsNativeTools: true,
|
|
3284
|
+
includedTools: ["apply_patch"],
|
|
3285
|
+
excludedTools: ["apply_diff", "write_to_file"],
|
|
3142
3286
|
supportsImages: true,
|
|
3143
3287
|
supportsPromptCache: true,
|
|
3144
3288
|
promptCacheRetention: "24h",
|
|
@@ -3154,6 +3298,8 @@ var openAiNativeModels = {
|
|
|
3154
3298
|
maxTokens: 128e3,
|
|
3155
3299
|
contextWindow: 4e5,
|
|
3156
3300
|
supportsNativeTools: true,
|
|
3301
|
+
includedTools: ["apply_patch"],
|
|
3302
|
+
excludedTools: ["apply_diff", "write_to_file"],
|
|
3157
3303
|
supportsImages: true,
|
|
3158
3304
|
supportsPromptCache: true,
|
|
3159
3305
|
supportsReasoningEffort: ["minimal", "low", "medium", "high"],
|
|
@@ -3173,6 +3319,8 @@ var openAiNativeModels = {
|
|
|
3173
3319
|
maxTokens: 128e3,
|
|
3174
3320
|
contextWindow: 4e5,
|
|
3175
3321
|
supportsNativeTools: true,
|
|
3322
|
+
includedTools: ["apply_patch"],
|
|
3323
|
+
excludedTools: ["apply_diff", "write_to_file"],
|
|
3176
3324
|
supportsImages: true,
|
|
3177
3325
|
supportsPromptCache: true,
|
|
3178
3326
|
supportsReasoningEffort: ["minimal", "low", "medium", "high"],
|
|
@@ -3192,6 +3340,8 @@ var openAiNativeModels = {
|
|
|
3192
3340
|
maxTokens: 128e3,
|
|
3193
3341
|
contextWindow: 4e5,
|
|
3194
3342
|
supportsNativeTools: true,
|
|
3343
|
+
includedTools: ["apply_patch"],
|
|
3344
|
+
excludedTools: ["apply_diff", "write_to_file"],
|
|
3195
3345
|
supportsImages: true,
|
|
3196
3346
|
supportsPromptCache: true,
|
|
3197
3347
|
supportsReasoningEffort: ["low", "medium", "high"],
|
|
@@ -3207,6 +3357,8 @@ var openAiNativeModels = {
|
|
|
3207
3357
|
maxTokens: 128e3,
|
|
3208
3358
|
contextWindow: 4e5,
|
|
3209
3359
|
supportsNativeTools: true,
|
|
3360
|
+
includedTools: ["apply_patch"],
|
|
3361
|
+
excludedTools: ["apply_diff", "write_to_file"],
|
|
3210
3362
|
supportsImages: true,
|
|
3211
3363
|
supportsPromptCache: true,
|
|
3212
3364
|
supportsReasoningEffort: ["minimal", "low", "medium", "high"],
|
|
@@ -3223,6 +3375,8 @@ var openAiNativeModels = {
|
|
|
3223
3375
|
maxTokens: 128e3,
|
|
3224
3376
|
contextWindow: 4e5,
|
|
3225
3377
|
supportsNativeTools: true,
|
|
3378
|
+
includedTools: ["apply_patch"],
|
|
3379
|
+
excludedTools: ["apply_diff", "write_to_file"],
|
|
3226
3380
|
supportsImages: true,
|
|
3227
3381
|
supportsPromptCache: true,
|
|
3228
3382
|
inputPrice: 1.25,
|
|
@@ -3234,6 +3388,8 @@ var openAiNativeModels = {
|
|
|
3234
3388
|
maxTokens: 32768,
|
|
3235
3389
|
contextWindow: 1047576,
|
|
3236
3390
|
supportsNativeTools: true,
|
|
3391
|
+
includedTools: ["apply_patch"],
|
|
3392
|
+
excludedTools: ["apply_diff", "write_to_file"],
|
|
3237
3393
|
supportsImages: true,
|
|
3238
3394
|
supportsPromptCache: true,
|
|
3239
3395
|
inputPrice: 2,
|
|
@@ -3248,6 +3404,8 @@ var openAiNativeModels = {
|
|
|
3248
3404
|
maxTokens: 32768,
|
|
3249
3405
|
contextWindow: 1047576,
|
|
3250
3406
|
supportsNativeTools: true,
|
|
3407
|
+
includedTools: ["apply_patch"],
|
|
3408
|
+
excludedTools: ["apply_diff", "write_to_file"],
|
|
3251
3409
|
supportsImages: true,
|
|
3252
3410
|
supportsPromptCache: true,
|
|
3253
3411
|
inputPrice: 0.4,
|
|
@@ -3262,6 +3420,8 @@ var openAiNativeModels = {
|
|
|
3262
3420
|
maxTokens: 32768,
|
|
3263
3421
|
contextWindow: 1047576,
|
|
3264
3422
|
supportsNativeTools: true,
|
|
3423
|
+
includedTools: ["apply_patch"],
|
|
3424
|
+
excludedTools: ["apply_diff", "write_to_file"],
|
|
3265
3425
|
supportsImages: true,
|
|
3266
3426
|
supportsPromptCache: true,
|
|
3267
3427
|
inputPrice: 0.1,
|
|
@@ -3469,6 +3629,8 @@ var openAiNativeModels = {
|
|
|
3469
3629
|
maxTokens: 128e3,
|
|
3470
3630
|
contextWindow: 4e5,
|
|
3471
3631
|
supportsNativeTools: true,
|
|
3632
|
+
includedTools: ["apply_patch"],
|
|
3633
|
+
excludedTools: ["apply_diff", "write_to_file"],
|
|
3472
3634
|
supportsImages: true,
|
|
3473
3635
|
supportsPromptCache: true,
|
|
3474
3636
|
supportsReasoningEffort: ["minimal", "low", "medium", "high"],
|
|
@@ -3488,6 +3650,8 @@ var openAiNativeModels = {
|
|
|
3488
3650
|
maxTokens: 128e3,
|
|
3489
3651
|
contextWindow: 4e5,
|
|
3490
3652
|
supportsNativeTools: true,
|
|
3653
|
+
includedTools: ["apply_patch"],
|
|
3654
|
+
excludedTools: ["apply_diff", "write_to_file"],
|
|
3491
3655
|
supportsImages: true,
|
|
3492
3656
|
supportsPromptCache: true,
|
|
3493
3657
|
supportsReasoningEffort: ["minimal", "low", "medium", "high"],
|
|
@@ -3507,6 +3671,8 @@ var openAiNativeModels = {
|
|
|
3507
3671
|
maxTokens: 128e3,
|
|
3508
3672
|
contextWindow: 4e5,
|
|
3509
3673
|
supportsNativeTools: true,
|
|
3674
|
+
includedTools: ["apply_patch"],
|
|
3675
|
+
excludedTools: ["apply_diff", "write_to_file"],
|
|
3510
3676
|
supportsImages: true,
|
|
3511
3677
|
supportsPromptCache: true,
|
|
3512
3678
|
supportsReasoningEffort: ["minimal", "low", "medium", "high"],
|
|
@@ -3669,7 +3835,18 @@ var RooModelSchema = import_zod7.z.object({
|
|
|
3669
3835
|
type: import_zod7.z.literal("language"),
|
|
3670
3836
|
tags: import_zod7.z.array(import_zod7.z.string()).optional(),
|
|
3671
3837
|
pricing: RooPricingSchema,
|
|
3672
|
-
deprecated: import_zod7.z.boolean().optional()
|
|
3838
|
+
deprecated: import_zod7.z.boolean().optional(),
|
|
3839
|
+
default_temperature: import_zod7.z.number().optional(),
|
|
3840
|
+
// Dynamic settings that map directly to ModelInfo properties
|
|
3841
|
+
// Allows the API to configure model-specific defaults like includedTools, excludedTools, reasoningEffort, etc.
|
|
3842
|
+
// These are always direct values (e.g., includedTools: ['search_replace']) for backward compatibility with old clients.
|
|
3843
|
+
settings: import_zod7.z.record(import_zod7.z.string(), import_zod7.z.unknown()).optional(),
|
|
3844
|
+
// Versioned settings keyed by version number (e.g., '3.36.4').
|
|
3845
|
+
// Each version key maps to a settings object that is used when plugin version >= that version.
|
|
3846
|
+
// New clients find the highest version key <= current version and use those settings.
|
|
3847
|
+
// Old clients ignore this field and use plain values from `settings`.
|
|
3848
|
+
// Example: { '3.36.4': { includedTools: ['search_replace'] }, '3.35.0': { ... } }
|
|
3849
|
+
versionedSettings: import_zod7.z.record(import_zod7.z.string(), import_zod7.z.record(import_zod7.z.string(), import_zod7.z.unknown())).optional()
|
|
3673
3850
|
});
|
|
3674
3851
|
var RooModelsResponseSchema = import_zod7.z.object({
|
|
3675
3852
|
object: import_zod7.z.literal("list"),
|
|
@@ -3787,6 +3964,7 @@ var unboundDefaultModelInfo = {
|
|
|
3787
3964
|
contextWindow: 2e5,
|
|
3788
3965
|
supportsImages: true,
|
|
3789
3966
|
supportsPromptCache: true,
|
|
3967
|
+
supportsNativeTools: true,
|
|
3790
3968
|
inputPrice: 3,
|
|
3791
3969
|
outputPrice: 15,
|
|
3792
3970
|
cacheWritesPrice: 3.75,
|
|
@@ -4434,15 +4612,17 @@ var xaiDefaultModelId = "grok-code-fast-1";
|
|
|
4434
4612
|
var xaiModels = {
|
|
4435
4613
|
"grok-code-fast-1": {
|
|
4436
4614
|
maxTokens: 16384,
|
|
4437
|
-
contextWindow:
|
|
4438
|
-
supportsImages:
|
|
4615
|
+
contextWindow: 256e3,
|
|
4616
|
+
supportsImages: true,
|
|
4439
4617
|
supportsPromptCache: true,
|
|
4440
4618
|
supportsNativeTools: true,
|
|
4441
4619
|
inputPrice: 0.2,
|
|
4442
4620
|
outputPrice: 1.5,
|
|
4443
4621
|
cacheWritesPrice: 0.02,
|
|
4444
4622
|
cacheReadsPrice: 0.02,
|
|
4445
|
-
description: "xAI's Grok Code Fast model with 256K context window"
|
|
4623
|
+
description: "xAI's Grok Code Fast model with 256K context window",
|
|
4624
|
+
includedTools: ["search_replace"],
|
|
4625
|
+
excludedTools: ["apply_diff"]
|
|
4446
4626
|
},
|
|
4447
4627
|
"grok-4-1-fast-reasoning": {
|
|
4448
4628
|
maxTokens: 65536,
|
|
@@ -4454,7 +4634,9 @@ var xaiModels = {
|
|
|
4454
4634
|
outputPrice: 0.5,
|
|
4455
4635
|
cacheWritesPrice: 0.05,
|
|
4456
4636
|
cacheReadsPrice: 0.05,
|
|
4457
|
-
description: "xAI's Grok 4.1 Fast model with 2M context window, optimized for high-performance agentic tool calling with reasoning"
|
|
4637
|
+
description: "xAI's Grok 4.1 Fast model with 2M context window, optimized for high-performance agentic tool calling with reasoning",
|
|
4638
|
+
includedTools: ["search_replace"],
|
|
4639
|
+
excludedTools: ["apply_diff"]
|
|
4458
4640
|
},
|
|
4459
4641
|
"grok-4-1-fast-non-reasoning": {
|
|
4460
4642
|
maxTokens: 65536,
|
|
@@ -4466,7 +4648,9 @@ var xaiModels = {
|
|
|
4466
4648
|
outputPrice: 0.5,
|
|
4467
4649
|
cacheWritesPrice: 0.05,
|
|
4468
4650
|
cacheReadsPrice: 0.05,
|
|
4469
|
-
description: "xAI's Grok 4.1 Fast model with 2M context window, optimized for high-performance agentic tool calling"
|
|
4651
|
+
description: "xAI's Grok 4.1 Fast model with 2M context window, optimized for high-performance agentic tool calling",
|
|
4652
|
+
includedTools: ["search_replace"],
|
|
4653
|
+
excludedTools: ["apply_diff"]
|
|
4470
4654
|
},
|
|
4471
4655
|
"grok-4-fast-reasoning": {
|
|
4472
4656
|
maxTokens: 65536,
|
|
@@ -4478,7 +4662,9 @@ var xaiModels = {
|
|
|
4478
4662
|
outputPrice: 0.5,
|
|
4479
4663
|
cacheWritesPrice: 0.05,
|
|
4480
4664
|
cacheReadsPrice: 0.05,
|
|
4481
|
-
description: "xAI's Grok 4 Fast model with 2M context window, optimized for high-performance agentic tool calling with reasoning"
|
|
4665
|
+
description: "xAI's Grok 4 Fast model with 2M context window, optimized for high-performance agentic tool calling with reasoning",
|
|
4666
|
+
includedTools: ["search_replace"],
|
|
4667
|
+
excludedTools: ["apply_diff"]
|
|
4482
4668
|
},
|
|
4483
4669
|
"grok-4-fast-non-reasoning": {
|
|
4484
4670
|
maxTokens: 65536,
|
|
@@ -4490,9 +4676,11 @@ var xaiModels = {
|
|
|
4490
4676
|
outputPrice: 0.5,
|
|
4491
4677
|
cacheWritesPrice: 0.05,
|
|
4492
4678
|
cacheReadsPrice: 0.05,
|
|
4493
|
-
description: "xAI's Grok 4 Fast model with 2M context window, optimized for high-performance agentic tool calling"
|
|
4679
|
+
description: "xAI's Grok 4 Fast model with 2M context window, optimized for high-performance agentic tool calling",
|
|
4680
|
+
includedTools: ["search_replace"],
|
|
4681
|
+
excludedTools: ["apply_diff"]
|
|
4494
4682
|
},
|
|
4495
|
-
"grok-4": {
|
|
4683
|
+
"grok-4-0709": {
|
|
4496
4684
|
maxTokens: 8192,
|
|
4497
4685
|
contextWindow: 256e3,
|
|
4498
4686
|
supportsImages: true,
|
|
@@ -4502,36 +4690,14 @@ var xaiModels = {
|
|
|
4502
4690
|
outputPrice: 15,
|
|
4503
4691
|
cacheWritesPrice: 0.75,
|
|
4504
4692
|
cacheReadsPrice: 0.75,
|
|
4505
|
-
description: "xAI's Grok-4 model with 256K context window"
|
|
4506
|
-
|
|
4507
|
-
|
|
4508
|
-
maxTokens: 8192,
|
|
4509
|
-
contextWindow: 131072,
|
|
4510
|
-
supportsImages: false,
|
|
4511
|
-
supportsPromptCache: true,
|
|
4512
|
-
supportsNativeTools: true,
|
|
4513
|
-
inputPrice: 3,
|
|
4514
|
-
outputPrice: 15,
|
|
4515
|
-
cacheWritesPrice: 0.75,
|
|
4516
|
-
cacheReadsPrice: 0.75,
|
|
4517
|
-
description: "xAI's Grok-3 model with 128K context window"
|
|
4518
|
-
},
|
|
4519
|
-
"grok-3-fast": {
|
|
4520
|
-
maxTokens: 8192,
|
|
4521
|
-
contextWindow: 131072,
|
|
4522
|
-
supportsImages: false,
|
|
4523
|
-
supportsPromptCache: true,
|
|
4524
|
-
supportsNativeTools: true,
|
|
4525
|
-
inputPrice: 5,
|
|
4526
|
-
outputPrice: 25,
|
|
4527
|
-
cacheWritesPrice: 1.25,
|
|
4528
|
-
cacheReadsPrice: 1.25,
|
|
4529
|
-
description: "xAI's Grok-3 fast model with 128K context window"
|
|
4693
|
+
description: "xAI's Grok-4 model with 256K context window",
|
|
4694
|
+
includedTools: ["search_replace"],
|
|
4695
|
+
excludedTools: ["apply_diff"]
|
|
4530
4696
|
},
|
|
4531
4697
|
"grok-3-mini": {
|
|
4532
4698
|
maxTokens: 8192,
|
|
4533
4699
|
contextWindow: 131072,
|
|
4534
|
-
supportsImages:
|
|
4700
|
+
supportsImages: true,
|
|
4535
4701
|
supportsPromptCache: true,
|
|
4536
4702
|
supportsNativeTools: true,
|
|
4537
4703
|
inputPrice: 0.3,
|
|
@@ -4539,40 +4705,24 @@ var xaiModels = {
|
|
|
4539
4705
|
cacheWritesPrice: 0.07,
|
|
4540
4706
|
cacheReadsPrice: 0.07,
|
|
4541
4707
|
description: "xAI's Grok-3 mini model with 128K context window",
|
|
4542
|
-
supportsReasoningEffort:
|
|
4543
|
-
|
|
4544
|
-
|
|
4545
|
-
|
|
4546
|
-
contextWindow: 131072,
|
|
4547
|
-
supportsImages: false,
|
|
4548
|
-
supportsPromptCache: true,
|
|
4549
|
-
supportsNativeTools: true,
|
|
4550
|
-
inputPrice: 0.6,
|
|
4551
|
-
outputPrice: 4,
|
|
4552
|
-
cacheWritesPrice: 0.15,
|
|
4553
|
-
cacheReadsPrice: 0.15,
|
|
4554
|
-
description: "xAI's Grok-3 mini fast model with 128K context window",
|
|
4555
|
-
supportsReasoningEffort: true
|
|
4708
|
+
supportsReasoningEffort: ["low", "high"],
|
|
4709
|
+
reasoningEffort: "low",
|
|
4710
|
+
includedTools: ["search_replace"],
|
|
4711
|
+
excludedTools: ["apply_diff"]
|
|
4556
4712
|
},
|
|
4557
|
-
"grok-
|
|
4713
|
+
"grok-3": {
|
|
4558
4714
|
maxTokens: 8192,
|
|
4559
4715
|
contextWindow: 131072,
|
|
4560
|
-
supportsImages: false,
|
|
4561
|
-
supportsPromptCache: false,
|
|
4562
|
-
supportsNativeTools: true,
|
|
4563
|
-
inputPrice: 2,
|
|
4564
|
-
outputPrice: 10,
|
|
4565
|
-
description: "xAI's Grok-2 model (version 1212) with 128K context window"
|
|
4566
|
-
},
|
|
4567
|
-
"grok-2-vision-1212": {
|
|
4568
|
-
maxTokens: 8192,
|
|
4569
|
-
contextWindow: 32768,
|
|
4570
4716
|
supportsImages: true,
|
|
4571
|
-
supportsPromptCache:
|
|
4717
|
+
supportsPromptCache: true,
|
|
4572
4718
|
supportsNativeTools: true,
|
|
4573
|
-
inputPrice:
|
|
4574
|
-
outputPrice:
|
|
4575
|
-
|
|
4719
|
+
inputPrice: 3,
|
|
4720
|
+
outputPrice: 15,
|
|
4721
|
+
cacheWritesPrice: 0.75,
|
|
4722
|
+
cacheReadsPrice: 0.75,
|
|
4723
|
+
description: "xAI's Grok-3 model with 128K context window",
|
|
4724
|
+
includedTools: ["search_replace"],
|
|
4725
|
+
excludedTools: ["apply_diff"]
|
|
4576
4726
|
}
|
|
4577
4727
|
};
|
|
4578
4728
|
|
|
@@ -4679,7 +4829,6 @@ var internationalZAiModels = {
|
|
|
4679
4829
|
supportsImages: false,
|
|
4680
4830
|
supportsPromptCache: true,
|
|
4681
4831
|
supportsNativeTools: true,
|
|
4682
|
-
supportsReasoningBinary: true,
|
|
4683
4832
|
inputPrice: 0.6,
|
|
4684
4833
|
outputPrice: 2.2,
|
|
4685
4834
|
cacheWritesPrice: 0,
|
|
@@ -4752,7 +4901,6 @@ var internationalZAiModels = {
|
|
|
4752
4901
|
supportsImages: false,
|
|
4753
4902
|
supportsPromptCache: true,
|
|
4754
4903
|
supportsNativeTools: true,
|
|
4755
|
-
supportsReasoningBinary: true,
|
|
4756
4904
|
inputPrice: 0.6,
|
|
4757
4905
|
outputPrice: 2.2,
|
|
4758
4906
|
cacheWritesPrice: 0,
|
|
@@ -4780,7 +4928,6 @@ var mainlandZAiModels = {
|
|
|
4780
4928
|
supportsImages: false,
|
|
4781
4929
|
supportsPromptCache: true,
|
|
4782
4930
|
supportsNativeTools: true,
|
|
4783
|
-
supportsReasoningBinary: true,
|
|
4784
4931
|
inputPrice: 0.29,
|
|
4785
4932
|
outputPrice: 1.14,
|
|
4786
4933
|
cacheWritesPrice: 0,
|
|
@@ -4853,7 +5000,6 @@ var mainlandZAiModels = {
|
|
|
4853
5000
|
supportsImages: false,
|
|
4854
5001
|
supportsPromptCache: true,
|
|
4855
5002
|
supportsNativeTools: true,
|
|
4856
|
-
supportsReasoningBinary: true,
|
|
4857
5003
|
inputPrice: 0.29,
|
|
4858
5004
|
outputPrice: 1.14,
|
|
4859
5005
|
cacheWritesPrice: 0,
|
|
@@ -4929,8 +5075,6 @@ function getProviderDefaultModelId(provider, options = { isChina: false }) {
|
|
|
4929
5075
|
return openRouterDefaultModelId;
|
|
4930
5076
|
case "requesty":
|
|
4931
5077
|
return requestyDefaultModelId;
|
|
4932
|
-
case "glama":
|
|
4933
|
-
return glamaDefaultModelId;
|
|
4934
5078
|
case "unbound":
|
|
4935
5079
|
return unboundDefaultModelId;
|
|
4936
5080
|
case "litellm":
|
|
@@ -5017,7 +5161,6 @@ var dynamicProviders = [
|
|
|
5017
5161
|
"io-intelligence",
|
|
5018
5162
|
"requesty",
|
|
5019
5163
|
"unbound",
|
|
5020
|
-
"glama",
|
|
5021
5164
|
"roo",
|
|
5022
5165
|
"chutes"
|
|
5023
5166
|
];
|
|
@@ -5099,10 +5242,6 @@ var claudeCodeSchema = apiModelIdProviderModelSchema.extend({
|
|
|
5099
5242
|
claudeCodePath: import_zod8.z.string().optional(),
|
|
5100
5243
|
claudeCodeMaxOutputTokens: import_zod8.z.number().int().min(1).max(2e5).optional()
|
|
5101
5244
|
});
|
|
5102
|
-
var glamaSchema = baseProviderSettingsSchema.extend({
|
|
5103
|
-
glamaModelId: import_zod8.z.string().optional(),
|
|
5104
|
-
glamaApiKey: import_zod8.z.string().optional()
|
|
5105
|
-
});
|
|
5106
5245
|
var openRouterSchema = baseProviderSettingsSchema.extend({
|
|
5107
5246
|
openRouterApiKey: import_zod8.z.string().optional(),
|
|
5108
5247
|
openRouterModelId: import_zod8.z.string().optional(),
|
|
@@ -5287,7 +5426,6 @@ var defaultSchema = import_zod8.z.object({
|
|
|
5287
5426
|
var providerSettingsSchemaDiscriminated = import_zod8.z.discriminatedUnion("apiProvider", [
|
|
5288
5427
|
anthropicSchema.merge(import_zod8.z.object({ apiProvider: import_zod8.z.literal("anthropic") })),
|
|
5289
5428
|
claudeCodeSchema.merge(import_zod8.z.object({ apiProvider: import_zod8.z.literal("claude-code") })),
|
|
5290
|
-
glamaSchema.merge(import_zod8.z.object({ apiProvider: import_zod8.z.literal("glama") })),
|
|
5291
5429
|
openRouterSchema.merge(import_zod8.z.object({ apiProvider: import_zod8.z.literal("openrouter") })),
|
|
5292
5430
|
bedrockSchema.merge(import_zod8.z.object({ apiProvider: import_zod8.z.literal("bedrock") })),
|
|
5293
5431
|
vertexSchema.merge(import_zod8.z.object({ apiProvider: import_zod8.z.literal("vertex") })),
|
|
@@ -5329,7 +5467,6 @@ var providerSettingsSchema = import_zod8.z.object({
|
|
|
5329
5467
|
apiProvider: providerNamesSchema.optional(),
|
|
5330
5468
|
...anthropicSchema.shape,
|
|
5331
5469
|
...claudeCodeSchema.shape,
|
|
5332
|
-
...glamaSchema.shape,
|
|
5333
5470
|
...openRouterSchema.shape,
|
|
5334
5471
|
...bedrockSchema.shape,
|
|
5335
5472
|
...vertexSchema.shape,
|
|
@@ -5374,7 +5511,6 @@ var discriminatedProviderSettingsWithIdSchema = providerSettingsSchemaDiscrimina
|
|
|
5374
5511
|
var PROVIDER_SETTINGS_KEYS = providerSettingsSchema.keyof().options;
|
|
5375
5512
|
var modelIdKeys = [
|
|
5376
5513
|
"apiModelId",
|
|
5377
|
-
"glamaModelId",
|
|
5378
5514
|
"openRouterModelId",
|
|
5379
5515
|
"openAiModelId",
|
|
5380
5516
|
"ollamaModelId",
|
|
@@ -5396,7 +5532,6 @@ var isTypicalProvider = (key) => isProviderName(key) && !isInternalProvider(key)
|
|
|
5396
5532
|
var modelIdKeysByProvider = {
|
|
5397
5533
|
anthropic: "apiModelId",
|
|
5398
5534
|
"claude-code": "apiModelId",
|
|
5399
|
-
glama: "glamaModelId",
|
|
5400
5535
|
openrouter: "openRouterModelId",
|
|
5401
5536
|
bedrock: "apiModelId",
|
|
5402
5537
|
vertex: "apiModelId",
|
|
@@ -5527,7 +5662,6 @@ var MODELS_BY_PROVIDER = {
|
|
|
5527
5662
|
zai: { id: "zai", label: "Z.ai", models: Object.keys(internationalZAiModels) },
|
|
5528
5663
|
baseten: { id: "baseten", label: "Baseten", models: Object.keys(basetenModels) },
|
|
5529
5664
|
// Dynamic providers; models pulled from remote APIs.
|
|
5530
|
-
glama: { id: "glama", label: "Glama", models: [] },
|
|
5531
5665
|
huggingface: { id: "huggingface", label: "Hugging Face", models: [] },
|
|
5532
5666
|
litellm: { id: "litellm", label: "LiteLLM", models: [] },
|
|
5533
5667
|
openrouter: { id: "openrouter", label: "OpenRouter", models: [] },
|
|
@@ -5759,6 +5893,67 @@ var rooCodeTelemetryEventSchema = import_zod11.z.discriminatedUnion("type", [
|
|
|
5759
5893
|
})
|
|
5760
5894
|
})
|
|
5761
5895
|
]);
|
|
5896
|
+
var EXPECTED_API_ERROR_CODES = /* @__PURE__ */ new Set([
|
|
5897
|
+
402,
|
|
5898
|
+
// Payment required - billing issues
|
|
5899
|
+
429
|
|
5900
|
+
// Rate limit - expected when hitting API limits
|
|
5901
|
+
]);
|
|
5902
|
+
var EXPECTED_ERROR_MESSAGE_PATTERNS = [
|
|
5903
|
+
/^429\b/,
|
|
5904
|
+
// Message starts with "429"
|
|
5905
|
+
/rate limit/i
|
|
5906
|
+
// Contains "rate limit" (case insensitive)
|
|
5907
|
+
];
|
|
5908
|
+
function isOpenAISdkError(error) {
|
|
5909
|
+
return typeof error === "object" && error !== null && "status" in error && typeof error.status === "number";
|
|
5910
|
+
}
|
|
5911
|
+
function getErrorStatusCode(error) {
|
|
5912
|
+
if (isOpenAISdkError(error)) {
|
|
5913
|
+
return error.status;
|
|
5914
|
+
}
|
|
5915
|
+
return void 0;
|
|
5916
|
+
}
|
|
5917
|
+
function getErrorMessage(error) {
|
|
5918
|
+
if (isOpenAISdkError(error)) {
|
|
5919
|
+
return error.error?.metadata?.raw || error.error?.message || error.message;
|
|
5920
|
+
}
|
|
5921
|
+
return void 0;
|
|
5922
|
+
}
|
|
5923
|
+
function shouldReportApiErrorToTelemetry(errorCode, errorMessage) {
|
|
5924
|
+
if (errorCode !== void 0 && EXPECTED_API_ERROR_CODES.has(errorCode)) {
|
|
5925
|
+
return false;
|
|
5926
|
+
}
|
|
5927
|
+
if (errorMessage) {
|
|
5928
|
+
for (const pattern of EXPECTED_ERROR_MESSAGE_PATTERNS) {
|
|
5929
|
+
if (pattern.test(errorMessage)) {
|
|
5930
|
+
return false;
|
|
5931
|
+
}
|
|
5932
|
+
}
|
|
5933
|
+
}
|
|
5934
|
+
return true;
|
|
5935
|
+
}
|
|
5936
|
+
var ApiProviderError = class extends Error {
|
|
5937
|
+
constructor(message, provider, modelId, operation, errorCode) {
|
|
5938
|
+
super(message);
|
|
5939
|
+
this.provider = provider;
|
|
5940
|
+
this.modelId = modelId;
|
|
5941
|
+
this.operation = operation;
|
|
5942
|
+
this.errorCode = errorCode;
|
|
5943
|
+
this.name = "ApiProviderError";
|
|
5944
|
+
}
|
|
5945
|
+
};
|
|
5946
|
+
function isApiProviderError(error) {
|
|
5947
|
+
return error instanceof Error && error.name === "ApiProviderError" && "provider" in error && "modelId" in error && "operation" in error;
|
|
5948
|
+
}
|
|
5949
|
+
function extractApiProviderErrorProperties(error) {
|
|
5950
|
+
return {
|
|
5951
|
+
provider: error.provider,
|
|
5952
|
+
modelId: error.modelId,
|
|
5953
|
+
operation: error.operation,
|
|
5954
|
+
...error.errorCode !== void 0 && { errorCode: error.errorCode }
|
|
5955
|
+
};
|
|
5956
|
+
}
|
|
5762
5957
|
|
|
5763
5958
|
// src/mode.ts
|
|
5764
5959
|
var import_zod12 = require("zod");
|
|
@@ -5837,7 +6032,7 @@ var DEFAULT_MODES = [
|
|
|
5837
6032
|
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.",
|
|
5838
6033
|
description: "Plan and design before implementation",
|
|
5839
6034
|
groups: ["read", ["edit", { fileRegex: "\\.md$", description: "Markdown files only" }], "browser", "mcp"],
|
|
5840
|
-
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
|
|
6035
|
+
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"
|
|
5841
6036
|
},
|
|
5842
6037
|
{
|
|
5843
6038
|
slug: "code",
|
|
@@ -6055,7 +6250,6 @@ var GLOBAL_SETTINGS_KEYS = globalSettingsSchema.keyof().options;
|
|
|
6055
6250
|
var rooCodeSettingsSchema = providerSettingsSchema.merge(globalSettingsSchema);
|
|
6056
6251
|
var SECRET_STATE_KEYS = [
|
|
6057
6252
|
"apiKey",
|
|
6058
|
-
"glamaApiKey",
|
|
6059
6253
|
"openRouterApiKey",
|
|
6060
6254
|
"awsAccessKey",
|
|
6061
6255
|
"awsApiKey",
|
|
@@ -6621,6 +6815,16 @@ var usageStatsSchema = import_zod16.z.object({
|
|
|
6621
6815
|
// Period in days (e.g., 30)
|
|
6622
6816
|
});
|
|
6623
6817
|
|
|
6818
|
+
// src/context-management.ts
|
|
6819
|
+
var CONTEXT_MANAGEMENT_EVENTS = [
|
|
6820
|
+
"condense_context",
|
|
6821
|
+
"condense_context_error",
|
|
6822
|
+
"sliding_window_truncation"
|
|
6823
|
+
];
|
|
6824
|
+
function isContextManagementEvent(value) {
|
|
6825
|
+
return typeof value === "string" && CONTEXT_MANAGEMENT_EVENTS.includes(value);
|
|
6826
|
+
}
|
|
6827
|
+
|
|
6624
6828
|
// src/cookie-consent.ts
|
|
6625
6829
|
var CONSENT_COOKIE_NAME = "roo-code-cookie-consent";
|
|
6626
6830
|
var COOKIE_CONSENT_EVENTS = {
|
|
@@ -6813,6 +7017,7 @@ var commandExecutionStatusSchema = import_zod21.z.discriminatedUnion("status", [
|
|
|
6813
7017
|
ANTHROPIC_DEFAULT_MAX_TOKENS,
|
|
6814
7018
|
ANTHROPIC_STYLE_PROVIDERS,
|
|
6815
7019
|
AWS_INFERENCE_PROFILE_MAPPING,
|
|
7020
|
+
ApiProviderError,
|
|
6816
7021
|
BEDROCK_1M_CONTEXT_MODEL_IDS,
|
|
6817
7022
|
BEDROCK_DEFAULT_CONTEXT,
|
|
6818
7023
|
BEDROCK_DEFAULT_TEMPERATURE,
|
|
@@ -6822,6 +7027,7 @@ var commandExecutionStatusSchema = import_zod21.z.discriminatedUnion("status", [
|
|
|
6822
7027
|
CLAUDE_CODE_DEFAULT_MAX_OUTPUT_TOKENS,
|
|
6823
7028
|
CODEBASE_INDEX_DEFAULTS,
|
|
6824
7029
|
CONSENT_COOKIE_NAME,
|
|
7030
|
+
CONTEXT_MANAGEMENT_EVENTS,
|
|
6825
7031
|
COOKIE_CONSENT_EVENTS,
|
|
6826
7032
|
ConnectionState,
|
|
6827
7033
|
DEEP_SEEK_DEFAULT_TEMPERATURE,
|
|
@@ -6834,10 +7040,10 @@ var commandExecutionStatusSchema = import_zod21.z.discriminatedUnion("status", [
|
|
|
6834
7040
|
DOUBAO_API_CHAT_PATH,
|
|
6835
7041
|
EVALS_SETTINGS,
|
|
6836
7042
|
EVALS_TIMEOUT,
|
|
7043
|
+
EXPECTED_API_ERROR_CODES,
|
|
6837
7044
|
ExtensionBridgeCommandName,
|
|
6838
7045
|
ExtensionBridgeEventName,
|
|
6839
7046
|
ExtensionSocketEvents,
|
|
6840
|
-
GLAMA_DEFAULT_TEMPERATURE,
|
|
6841
7047
|
GLOBAL_SECRET_KEYS,
|
|
6842
7048
|
GLOBAL_SETTINGS_KEYS,
|
|
6843
7049
|
GLOBAL_STATE_KEYS,
|
|
@@ -6921,6 +7127,7 @@ var commandExecutionStatusSchema = import_zod21.z.discriminatedUnion("status", [
|
|
|
6921
7127
|
commandExecutionStatusSchema,
|
|
6922
7128
|
commandIds,
|
|
6923
7129
|
contextCondenseSchema,
|
|
7130
|
+
contextTruncationSchema,
|
|
6924
7131
|
convertModelNameForVertex,
|
|
6925
7132
|
customModePromptsSchema,
|
|
6926
7133
|
customModesSettingsSchema,
|
|
@@ -6942,6 +7149,7 @@ var commandExecutionStatusSchema = import_zod21.z.discriminatedUnion("status", [
|
|
|
6942
7149
|
extensionBridgeCommandSchema,
|
|
6943
7150
|
extensionBridgeEventSchema,
|
|
6944
7151
|
extensionInstanceSchema,
|
|
7152
|
+
extractApiProviderErrorProperties,
|
|
6945
7153
|
fauxProviders,
|
|
6946
7154
|
featherlessDefaultModelId,
|
|
6947
7155
|
featherlessModels,
|
|
@@ -6953,12 +7161,12 @@ var commandExecutionStatusSchema = import_zod21.z.discriminatedUnion("status", [
|
|
|
6953
7161
|
getApiProtocol,
|
|
6954
7162
|
getClaudeCodeModelId,
|
|
6955
7163
|
getEffectiveProtocol,
|
|
7164
|
+
getErrorMessage,
|
|
7165
|
+
getErrorStatusCode,
|
|
6956
7166
|
getImageGenerationProvider,
|
|
6957
7167
|
getModelId,
|
|
6958
7168
|
getProviderDefaultModelId,
|
|
6959
7169
|
gitPropertiesSchema,
|
|
6960
|
-
glamaDefaultModelId,
|
|
6961
|
-
glamaDefaultModelInfo,
|
|
6962
7170
|
globalSettingsSchema,
|
|
6963
7171
|
groqDefaultModelId,
|
|
6964
7172
|
groqModels,
|
|
@@ -6975,6 +7183,8 @@ var commandExecutionStatusSchema = import_zod21.z.discriminatedUnion("status", [
|
|
|
6975
7183
|
ioIntelligenceDefaultModelId,
|
|
6976
7184
|
ioIntelligenceModels,
|
|
6977
7185
|
ipcMessageSchema,
|
|
7186
|
+
isApiProviderError,
|
|
7187
|
+
isContextManagementEvent,
|
|
6978
7188
|
isCustomProvider,
|
|
6979
7189
|
isDynamicProvider,
|
|
6980
7190
|
isFauxProvider,
|
|
@@ -7063,6 +7273,7 @@ var commandExecutionStatusSchema = import_zod21.z.discriminatedUnion("status", [
|
|
|
7063
7273
|
serviceTierSchema,
|
|
7064
7274
|
serviceTiers,
|
|
7065
7275
|
shareResponseSchema,
|
|
7276
|
+
shouldReportApiErrorToTelemetry,
|
|
7066
7277
|
shouldUseSingleFileRead,
|
|
7067
7278
|
staticAppPropertiesSchema,
|
|
7068
7279
|
suggestionItemSchema,
|