@roo-code/types 1.110.0 → 1.111.0

package/dist/index.js

@@ -2,7 +2,7 @@
 import { z as z16 } from "zod";
 
 // src/events.ts
-import { z as z3 } from "zod";
+import { z as z4 } from "zod";
 
 // src/message.ts
 import { z } from "zod";
@@ -141,16 +141,97 @@ var queuedMessageSchema = z.object({
   images: z.array(z.string()).optional()
 });
 
-// src/tool.ts
+// src/model.ts
 import { z as z2 } from "zod";
+var reasoningEfforts = ["low", "medium", "high"];
+var reasoningEffortsSchema = z2.enum(reasoningEfforts);
+var reasoningEffortWithMinimalSchema = z2.union([reasoningEffortsSchema, z2.literal("minimal")]);
+var reasoningEffortsExtended = ["none", "minimal", "low", "medium", "high", "xhigh"];
+var reasoningEffortExtendedSchema = z2.enum(reasoningEffortsExtended);
+var reasoningEffortSettingValues = ["disable", "none", "minimal", "low", "medium", "high", "xhigh"];
+var reasoningEffortSettingSchema = z2.enum(reasoningEffortSettingValues);
+var verbosityLevels = ["low", "medium", "high"];
+var verbosityLevelsSchema = z2.enum(verbosityLevels);
+var serviceTiers = ["default", "flex", "priority"];
+var serviceTierSchema = z2.enum(serviceTiers);
+var modelParameters = ["max_tokens", "temperature", "reasoning", "include_reasoning"];
+var modelParametersSchema = z2.enum(modelParameters);
+var isModelParameter = (value) => modelParameters.includes(value);
+var modelInfoSchema = z2.object({
+  maxTokens: z2.number().nullish(),
+  maxThinkingTokens: z2.number().nullish(),
+  contextWindow: z2.number(),
+  supportsImages: z2.boolean().optional(),
+  supportsPromptCache: z2.boolean(),
+  // Optional default prompt cache retention policy for providers that support it.
+  // When set to "24h", extended prompt caching will be requested; when omitted
+  // or set to "in_memory", the default in‑memory cache is used.
+  promptCacheRetention: z2.enum(["in_memory", "24h"]).optional(),
+  // Capability flag to indicate whether the model supports an output verbosity parameter
+  supportsVerbosity: z2.boolean().optional(),
+  supportsReasoningBudget: z2.boolean().optional(),
+  // Capability flag to indicate whether the model supports simple on/off binary reasoning
+  supportsReasoningBinary: z2.boolean().optional(),
+  // Capability flag to indicate whether the model supports temperature parameter
+  supportsTemperature: z2.boolean().optional(),
+  defaultTemperature: z2.number().optional(),
+  requiredReasoningBudget: z2.boolean().optional(),
+  supportsReasoningEffort: z2.union([z2.boolean(), z2.array(z2.enum(["disable", "none", "minimal", "low", "medium", "high", "xhigh"]))]).optional(),
+  requiredReasoningEffort: z2.boolean().optional(),
+  preserveReasoning: z2.boolean().optional(),
+  supportedParameters: z2.array(modelParametersSchema).optional(),
+  inputPrice: z2.number().optional(),
+  outputPrice: z2.number().optional(),
+  cacheWritesPrice: z2.number().optional(),
+  cacheReadsPrice: z2.number().optional(),
+  description: z2.string().optional(),
+  // Default effort value for models that support reasoning effort
+  reasoningEffort: reasoningEffortExtendedSchema.optional(),
+  minTokensPerCachePoint: z2.number().optional(),
+  maxCachePoints: z2.number().optional(),
+  cachableFields: z2.array(z2.string()).optional(),
+  // Flag to indicate if the model is deprecated and should not be used
+  deprecated: z2.boolean().optional(),
+  // Flag to indicate if the model should hide vendor/company identity in responses
+  isStealthModel: z2.boolean().optional(),
+  // Flag to indicate if the model is free (no cost)
+  isFree: z2.boolean().optional(),
+  // Exclude specific native tools from being available (only applies to native protocol)
+  // These tools will be removed from the set of tools available to the model
+  excludedTools: z2.array(z2.string()).optional(),
+  // Include specific native tools (only applies to native protocol)
+  // These tools will be added if they belong to an allowed group in the current mode
+  // Cannot force-add tools from groups the mode doesn't allow
+  includedTools: z2.array(z2.string()).optional(),
+  /**
+   * Service tiers with pricing information.
+   * Each tier can have a name (for OpenAI service tiers) and pricing overrides.
+   * The top-level input/output/cache* fields represent the default/standard tier.
+   */
+  tiers: z2.array(
+    z2.object({
+      name: serviceTierSchema.optional(),
+      // Service tier name (flex, priority, etc.)
+      contextWindow: z2.number(),
+      inputPrice: z2.number().optional(),
+      outputPrice: z2.number().optional(),
+      cacheWritesPrice: z2.number().optional(),
+      cacheReadsPrice: z2.number().optional()
+    })
+  ).optional()
+});
+
+// src/tool.ts
+import { z as z3 } from "zod";
 var toolGroups = ["read", "edit", "browser", "command", "mcp", "modes"];
-var toolGroupsSchema = z2.enum(toolGroups);
+var toolGroupsSchema = z3.enum(toolGroups);
 var toolNames = [
   "execute_command",
   "read_file",
   "read_command_output",
   "write_to_file",
   "apply_diff",
+  "edit",
   "search_and_replace",
   "search_replace",
   "edit_file",
@@ -171,12 +252,12 @@ var toolNames = [
   "generate_image",
   "custom_tool"
 ];
-var toolNamesSchema = z2.enum(toolNames);
-var toolUsageSchema = z2.record(
+var toolNamesSchema = z3.enum(toolNames);
+var toolUsageSchema = z3.record(
   toolNamesSchema,
-  z2.object({
-    attempts: z2.number(),
-    failures: z2.number()
+  z3.object({
+    attempts: z3.number(),
+    failures: z3.number()
   })
 );
 
@@ -207,198 +288,230 @@ var RooCodeEventName = /* @__PURE__ */ ((RooCodeEventName2) => {
   RooCodeEventName2["TaskToolFailed"] = "taskToolFailed";
   RooCodeEventName2["ModeChanged"] = "modeChanged";
   RooCodeEventName2["ProviderProfileChanged"] = "providerProfileChanged";
+  RooCodeEventName2["CommandsResponse"] = "commandsResponse";
+  RooCodeEventName2["ModesResponse"] = "modesResponse";
+  RooCodeEventName2["ModelsResponse"] = "modelsResponse";
   RooCodeEventName2["EvalPass"] = "evalPass";
   RooCodeEventName2["EvalFail"] = "evalFail";
   return RooCodeEventName2;
 })(RooCodeEventName || {});
-var rooCodeEventsSchema = z3.object({
-  ["taskCreated" /* TaskCreated */]: z3.tuple([z3.string()]),
-  ["taskStarted" /* TaskStarted */]: z3.tuple([z3.string()]),
-  ["taskCompleted" /* TaskCompleted */]: z3.tuple([
-    z3.string(),
+var rooCodeEventsSchema = z4.object({
+  ["taskCreated" /* TaskCreated */]: z4.tuple([z4.string()]),
+  ["taskStarted" /* TaskStarted */]: z4.tuple([z4.string()]),
+  ["taskCompleted" /* TaskCompleted */]: z4.tuple([
+    z4.string(),
     tokenUsageSchema,
     toolUsageSchema,
-    z3.object({
-      isSubtask: z3.boolean()
+    z4.object({
+      isSubtask: z4.boolean()
     })
   ]),
-  ["taskAborted" /* TaskAborted */]: z3.tuple([z3.string()]),
-  ["taskFocused" /* TaskFocused */]: z3.tuple([z3.string()]),
-  ["taskUnfocused" /* TaskUnfocused */]: z3.tuple([z3.string()]),
-  ["taskActive" /* TaskActive */]: z3.tuple([z3.string()]),
-  ["taskInteractive" /* TaskInteractive */]: z3.tuple([z3.string()]),
-  ["taskResumable" /* TaskResumable */]: z3.tuple([z3.string()]),
-  ["taskIdle" /* TaskIdle */]: z3.tuple([z3.string()]),
-  ["taskPaused" /* TaskPaused */]: z3.tuple([z3.string()]),
-  ["taskUnpaused" /* TaskUnpaused */]: z3.tuple([z3.string()]),
-  ["taskSpawned" /* TaskSpawned */]: z3.tuple([z3.string(), z3.string()]),
-  ["taskDelegated" /* TaskDelegated */]: z3.tuple([
-    z3.string(),
+  ["taskAborted" /* TaskAborted */]: z4.tuple([z4.string()]),
+  ["taskFocused" /* TaskFocused */]: z4.tuple([z4.string()]),
+  ["taskUnfocused" /* TaskUnfocused */]: z4.tuple([z4.string()]),
+  ["taskActive" /* TaskActive */]: z4.tuple([z4.string()]),
+  ["taskInteractive" /* TaskInteractive */]: z4.tuple([z4.string()]),
+  ["taskResumable" /* TaskResumable */]: z4.tuple([z4.string()]),
+  ["taskIdle" /* TaskIdle */]: z4.tuple([z4.string()]),
+  ["taskPaused" /* TaskPaused */]: z4.tuple([z4.string()]),
+  ["taskUnpaused" /* TaskUnpaused */]: z4.tuple([z4.string()]),
+  ["taskSpawned" /* TaskSpawned */]: z4.tuple([z4.string(), z4.string()]),
+  ["taskDelegated" /* TaskDelegated */]: z4.tuple([
+    z4.string(),
     // parentTaskId
-    z3.string()
+    z4.string()
     // childTaskId
   ]),
-  ["taskDelegationCompleted" /* TaskDelegationCompleted */]: z3.tuple([
-    z3.string(),
+  ["taskDelegationCompleted" /* TaskDelegationCompleted */]: z4.tuple([
+    z4.string(),
     // parentTaskId
-    z3.string(),
+    z4.string(),
     // childTaskId
-    z3.string()
+    z4.string()
     // completionResultSummary
   ]),
-  ["taskDelegationResumed" /* TaskDelegationResumed */]: z3.tuple([
-    z3.string(),
+  ["taskDelegationResumed" /* TaskDelegationResumed */]: z4.tuple([
+    z4.string(),
     // parentTaskId
-    z3.string()
+    z4.string()
     // childTaskId
   ]),
-  ["message" /* Message */]: z3.tuple([
-    z3.object({
-      taskId: z3.string(),
-      action: z3.union([z3.literal("created"), z3.literal("updated")]),
+  ["message" /* Message */]: z4.tuple([
+    z4.object({
+      taskId: z4.string(),
+      action: z4.union([z4.literal("created"), z4.literal("updated")]),
       message: clineMessageSchema
     })
   ]),
-  ["taskModeSwitched" /* TaskModeSwitched */]: z3.tuple([z3.string(), z3.string()]),
-  ["taskAskResponded" /* TaskAskResponded */]: z3.tuple([z3.string()]),
-  ["taskUserMessage" /* TaskUserMessage */]: z3.tuple([z3.string()]),
-  ["queuedMessagesUpdated" /* QueuedMessagesUpdated */]: z3.tuple([z3.string(), z3.array(queuedMessageSchema)]),
-  ["taskToolFailed" /* TaskToolFailed */]: z3.tuple([z3.string(), toolNamesSchema, z3.string()]),
-  ["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() })])
+  ["taskModeSwitched" /* TaskModeSwitched */]: z4.tuple([z4.string(), z4.string()]),
+  ["taskAskResponded" /* TaskAskResponded */]: z4.tuple([z4.string()]),
+  ["taskUserMessage" /* TaskUserMessage */]: z4.tuple([z4.string()]),
+  ["queuedMessagesUpdated" /* QueuedMessagesUpdated */]: z4.tuple([z4.string(), z4.array(queuedMessageSchema)]),
+  ["taskToolFailed" /* TaskToolFailed */]: z4.tuple([z4.string(), toolNamesSchema, z4.string()]),
+  ["taskTokenUsageUpdated" /* TaskTokenUsageUpdated */]: z4.tuple([z4.string(), tokenUsageSchema, toolUsageSchema]),
+  ["modeChanged" /* ModeChanged */]: z4.tuple([z4.string()]),
+  ["providerProfileChanged" /* ProviderProfileChanged */]: z4.tuple([z4.object({ name: z4.string(), provider: z4.string() })]),
+  ["commandsResponse" /* CommandsResponse */]: z4.tuple([
+    z4.array(
+      z4.object({
+        name: z4.string(),
+        source: z4.enum(["global", "project", "built-in"]),
+        filePath: z4.string().optional(),
+        description: z4.string().optional(),
+        argumentHint: z4.string().optional()
+      })
+    )
+  ]),
+  ["modesResponse" /* ModesResponse */]: z4.tuple([z4.array(z4.object({ slug: z4.string(), name: z4.string() }))]),
+  ["modelsResponse" /* ModelsResponse */]: z4.tuple([z4.record(z4.string(), modelInfoSchema)])
 });
-var taskEventSchema = z3.discriminatedUnion("eventName", [
+var taskEventSchema = z4.discriminatedUnion("eventName", [
   // Task Provider Lifecycle
-  z3.object({
-    eventName: z3.literal("taskCreated" /* TaskCreated */),
+  z4.object({
+    eventName: z4.literal("taskCreated" /* TaskCreated */),
     payload: rooCodeEventsSchema.shape["taskCreated" /* TaskCreated */],
-    taskId: z3.number().optional()
+    taskId: z4.number().optional()
   }),
   // Task Lifecycle
-  z3.object({
-    eventName: z3.literal("taskStarted" /* TaskStarted */),
+  z4.object({
+    eventName: z4.literal("taskStarted" /* TaskStarted */),
     payload: rooCodeEventsSchema.shape["taskStarted" /* TaskStarted */],
-    taskId: z3.number().optional()
+    taskId: z4.number().optional()
   }),
-  z3.object({
-    eventName: z3.literal("taskCompleted" /* TaskCompleted */),
+  z4.object({
+    eventName: z4.literal("taskCompleted" /* TaskCompleted */),
     payload: rooCodeEventsSchema.shape["taskCompleted" /* TaskCompleted */],
-    taskId: z3.number().optional()
+    taskId: z4.number().optional()
   }),
-  z3.object({
-    eventName: z3.literal("taskAborted" /* TaskAborted */),
+  z4.object({
+    eventName: z4.literal("taskAborted" /* TaskAborted */),
     payload: rooCodeEventsSchema.shape["taskAborted" /* TaskAborted */],
-    taskId: z3.number().optional()
+    taskId: z4.number().optional()
   }),
-  z3.object({
-    eventName: z3.literal("taskFocused" /* TaskFocused */),
+  z4.object({
+    eventName: z4.literal("taskFocused" /* TaskFocused */),
     payload: rooCodeEventsSchema.shape["taskFocused" /* TaskFocused */],
-    taskId: z3.number().optional()
+    taskId: z4.number().optional()
   }),
-  z3.object({
-    eventName: z3.literal("taskUnfocused" /* TaskUnfocused */),
+  z4.object({
+    eventName: z4.literal("taskUnfocused" /* TaskUnfocused */),
     payload: rooCodeEventsSchema.shape["taskUnfocused" /* TaskUnfocused */],
-    taskId: z3.number().optional()
+    taskId: z4.number().optional()
   }),
-  z3.object({
-    eventName: z3.literal("taskActive" /* TaskActive */),
+  z4.object({
+    eventName: z4.literal("taskActive" /* TaskActive */),
     payload: rooCodeEventsSchema.shape["taskActive" /* TaskActive */],
-    taskId: z3.number().optional()
+    taskId: z4.number().optional()
   }),
-  z3.object({
-    eventName: z3.literal("taskInteractive" /* TaskInteractive */),
+  z4.object({
+    eventName: z4.literal("taskInteractive" /* TaskInteractive */),
     payload: rooCodeEventsSchema.shape["taskInteractive" /* TaskInteractive */],
-    taskId: z3.number().optional()
+    taskId: z4.number().optional()
   }),
-  z3.object({
-    eventName: z3.literal("taskResumable" /* TaskResumable */),
+  z4.object({
+    eventName: z4.literal("taskResumable" /* TaskResumable */),
     payload: rooCodeEventsSchema.shape["taskResumable" /* TaskResumable */],
-    taskId: z3.number().optional()
+    taskId: z4.number().optional()
   }),
-  z3.object({
-    eventName: z3.literal("taskIdle" /* TaskIdle */),
+  z4.object({
+    eventName: z4.literal("taskIdle" /* TaskIdle */),
     payload: rooCodeEventsSchema.shape["taskIdle" /* TaskIdle */],
-    taskId: z3.number().optional()
+    taskId: z4.number().optional()
   }),
   // Subtask Lifecycle
-  z3.object({
-    eventName: z3.literal("taskPaused" /* TaskPaused */),
+  z4.object({
+    eventName: z4.literal("taskPaused" /* TaskPaused */),
     payload: rooCodeEventsSchema.shape["taskPaused" /* TaskPaused */],
-    taskId: z3.number().optional()
+    taskId: z4.number().optional()
   }),
-  z3.object({
-    eventName: z3.literal("taskUnpaused" /* TaskUnpaused */),
+  z4.object({
+    eventName: z4.literal("taskUnpaused" /* TaskUnpaused */),
     payload: rooCodeEventsSchema.shape["taskUnpaused" /* TaskUnpaused */],
-    taskId: z3.number().optional()
+    taskId: z4.number().optional()
   }),
-  z3.object({
-    eventName: z3.literal("taskSpawned" /* TaskSpawned */),
+  z4.object({
+    eventName: z4.literal("taskSpawned" /* TaskSpawned */),
     payload: rooCodeEventsSchema.shape["taskSpawned" /* TaskSpawned */],
-    taskId: z3.number().optional()
+    taskId: z4.number().optional()
   }),
-  z3.object({
-    eventName: z3.literal("taskDelegated" /* TaskDelegated */),
+  z4.object({
+    eventName: z4.literal("taskDelegated" /* TaskDelegated */),
     payload: rooCodeEventsSchema.shape["taskDelegated" /* TaskDelegated */],
-    taskId: z3.number().optional()
+    taskId: z4.number().optional()
   }),
-  z3.object({
-    eventName: z3.literal("taskDelegationCompleted" /* TaskDelegationCompleted */),
+  z4.object({
+    eventName: z4.literal("taskDelegationCompleted" /* TaskDelegationCompleted */),
     payload: rooCodeEventsSchema.shape["taskDelegationCompleted" /* TaskDelegationCompleted */],
-    taskId: z3.number().optional()
+    taskId: z4.number().optional()
   }),
-  z3.object({
-    eventName: z3.literal("taskDelegationResumed" /* TaskDelegationResumed */),
+  z4.object({
+    eventName: z4.literal("taskDelegationResumed" /* TaskDelegationResumed */),
     payload: rooCodeEventsSchema.shape["taskDelegationResumed" /* TaskDelegationResumed */],
-    taskId: z3.number().optional()
+    taskId: z4.number().optional()
   }),
   // Task Execution
-  z3.object({
-    eventName: z3.literal("message" /* Message */),
+  z4.object({
+    eventName: z4.literal("message" /* Message */),
     payload: rooCodeEventsSchema.shape["message" /* Message */],
-    taskId: z3.number().optional()
+    taskId: z4.number().optional()
   }),
-  z3.object({
-    eventName: z3.literal("taskModeSwitched" /* TaskModeSwitched */),
+  z4.object({
+    eventName: z4.literal("taskModeSwitched" /* TaskModeSwitched */),
     payload: rooCodeEventsSchema.shape["taskModeSwitched" /* TaskModeSwitched */],
-    taskId: z3.number().optional()
+    taskId: z4.number().optional()
   }),
-  z3.object({
-    eventName: z3.literal("taskAskResponded" /* TaskAskResponded */),
+  z4.object({
+    eventName: z4.literal("taskAskResponded" /* TaskAskResponded */),
     payload: rooCodeEventsSchema.shape["taskAskResponded" /* TaskAskResponded */],
-    taskId: z3.number().optional()
+    taskId: z4.number().optional()
   }),
-  z3.object({
-    eventName: z3.literal("queuedMessagesUpdated" /* QueuedMessagesUpdated */),
+  z4.object({
+    eventName: z4.literal("queuedMessagesUpdated" /* QueuedMessagesUpdated */),
     payload: rooCodeEventsSchema.shape["queuedMessagesUpdated" /* QueuedMessagesUpdated */],
-    taskId: z3.number().optional()
+    taskId: z4.number().optional()
   }),
   // Task Analytics
-  z3.object({
-    eventName: z3.literal("taskToolFailed" /* TaskToolFailed */),
+  z4.object({
+    eventName: z4.literal("taskToolFailed" /* TaskToolFailed */),
     payload: rooCodeEventsSchema.shape["taskToolFailed" /* TaskToolFailed */],
-    taskId: z3.number().optional()
+    taskId: z4.number().optional()
   }),
-  z3.object({
-    eventName: z3.literal("taskTokenUsageUpdated" /* TaskTokenUsageUpdated */),
+  z4.object({
+    eventName: z4.literal("taskTokenUsageUpdated" /* TaskTokenUsageUpdated */),
     payload: rooCodeEventsSchema.shape["taskTokenUsageUpdated" /* TaskTokenUsageUpdated */],
-    taskId: z3.number().optional()
+    taskId: z4.number().optional()
+  }),
+  // Query Responses
+  z4.object({
+    eventName: z4.literal("commandsResponse" /* CommandsResponse */),
+    payload: rooCodeEventsSchema.shape["commandsResponse" /* CommandsResponse */],
+    taskId: z4.number().optional()
+  }),
+  z4.object({
+    eventName: z4.literal("modesResponse" /* ModesResponse */),
+    payload: rooCodeEventsSchema.shape["modesResponse" /* ModesResponse */],
+    taskId: z4.number().optional()
+  }),
+  z4.object({
+    eventName: z4.literal("modelsResponse" /* ModelsResponse */),
+    payload: rooCodeEventsSchema.shape["modelsResponse" /* ModelsResponse */],
+    taskId: z4.number().optional()
   }),
   // Evals
-  z3.object({
-    eventName: z3.literal("evalPass" /* EvalPass */),
-    payload: z3.undefined(),
-    taskId: z3.number()
+  z4.object({
+    eventName: z4.literal("evalPass" /* EvalPass */),
+    payload: z4.undefined(),
+    taskId: z4.number()
   }),
-  z3.object({
-    eventName: z3.literal("evalFail" /* EvalFail */),
-    payload: z3.undefined(),
-    taskId: z3.number()
+  z4.object({
+    eventName: z4.literal("evalFail" /* EvalFail */),
+    payload: z4.undefined(),
+    taskId: z4.number()
   })
 ]);
 
 // src/task.ts
-import { z as z4 } from "zod";
+import { z as z5 } from "zod";
 var TaskStatus = /* @__PURE__ */ ((TaskStatus2) => {
   TaskStatus2["Running"] = "running";
   TaskStatus2["Interactive"] = "interactive";
@@ -407,9 +520,9 @@ var TaskStatus = /* @__PURE__ */ ((TaskStatus2) => {
   TaskStatus2["None"] = "none";
   return TaskStatus2;
 })(TaskStatus || {});
-var taskMetadataSchema = z4.object({
-  task: z4.string().optional(),
-  images: z4.array(z4.string()).optional()
+var taskMetadataSchema = z5.object({
+  task: z5.string().optional(),
+  images: z5.array(z5.string()).optional()
 });
 
 // src/global-settings.ts
@@ -418,86 +531,6 @@ import { z as z14 } from "zod";
 // src/provider-settings.ts
 import { z as z8 } from "zod";
 
-// src/model.ts
-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", "xhigh"];
-var reasoningEffortExtendedSchema = z5.enum(reasoningEffortsExtended);
-var reasoningEffortSettingValues = ["disable", "none", "minimal", "low", "medium", "high", "xhigh"];
-var reasoningEffortSettingSchema = z5.enum(reasoningEffortSettingValues);
-var verbosityLevels = ["low", "medium", "high"];
-var verbosityLevelsSchema = z5.enum(verbosityLevels);
-var serviceTiers = ["default", "flex", "priority"];
-var serviceTierSchema = z5.enum(serviceTiers);
-var modelParameters = ["max_tokens", "temperature", "reasoning", "include_reasoning"];
-var modelParametersSchema = z5.enum(modelParameters);
-var isModelParameter = (value) => modelParameters.includes(value);
-var modelInfoSchema = z5.object({
-  maxTokens: z5.number().nullish(),
-  maxThinkingTokens: z5.number().nullish(),
-  contextWindow: z5.number(),
-  supportsImages: z5.boolean().optional(),
-  supportsPromptCache: z5.boolean(),
-  // Optional default prompt cache retention policy for providers that support it.
-  // When set to "24h", extended prompt caching will be requested; when omitted
-  // or set to "in_memory", the default in‑memory cache is used.
-  promptCacheRetention: z5.enum(["in_memory", "24h"]).optional(),
-  // Capability flag to indicate whether the model supports an output verbosity parameter
-  supportsVerbosity: z5.boolean().optional(),
-  supportsReasoningBudget: z5.boolean().optional(),
-  // Capability flag to indicate whether the model supports simple on/off binary reasoning
-  supportsReasoningBinary: z5.boolean().optional(),
-  // Capability flag to indicate whether the model supports temperature parameter
-  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", "xhigh"]))]).optional(),
-  requiredReasoningEffort: z5.boolean().optional(),
-  preserveReasoning: z5.boolean().optional(),
-  supportedParameters: z5.array(modelParametersSchema).optional(),
-  inputPrice: z5.number().optional(),
-  outputPrice: z5.number().optional(),
-  cacheWritesPrice: z5.number().optional(),
-  cacheReadsPrice: z5.number().optional(),
-  description: z5.string().optional(),
-  // Default effort value for models that support reasoning effort
-  reasoningEffort: reasoningEffortExtendedSchema.optional(),
-  minTokensPerCachePoint: z5.number().optional(),
-  maxCachePoints: z5.number().optional(),
-  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(),
-  // Exclude specific native tools from being available (only applies to native protocol)
-  // These tools will be removed from the set of tools available to the model
-  excludedTools: z5.array(z5.string()).optional(),
-  // Include specific native tools (only applies to native protocol)
-  // These tools will be added if they belong to an allowed group in the current mode
-  // Cannot force-add tools from groups the mode doesn't allow
-  includedTools: z5.array(z5.string()).optional(),
-  /**
-   * Service tiers with pricing information.
-   * Each tier can have a name (for OpenAI service tiers) and pricing overrides.
-   * The top-level input/output/cache* fields represent the default/standard tier.
-   */
-  tiers: z5.array(
-    z5.object({
-      name: serviceTierSchema.optional(),
-      // Service tier name (flex, priority, etc.)
-      contextWindow: z5.number(),
-      inputPrice: z5.number().optional(),
-      outputPrice: z5.number().optional(),
-      cacheWritesPrice: z5.number().optional(),
-      cacheReadsPrice: z5.number().optional()
-    })
-  ).optional()
-});
-
 // src/codebase-index.ts
 import { z as z6 } from "zod";
 var CODEBASE_INDEX_DEFAULTS = {
@@ -797,1090 +830,1051 @@ var anthropicModels = {
 };
 var ANTHROPIC_DEFAULT_MAX_TOKENS = 8192;
 
-// src/providers/baseten.ts
-var basetenModels = {
-  "moonshotai/Kimi-K2-Thinking": {
-    maxTokens: 16384,
-    contextWindow: 262e3,
-    supportsImages: false,
-    supportsPromptCache: false,
-    inputPrice: 0.6,
-    outputPrice: 2.5,
-    cacheWritesPrice: 0,
-    cacheReadsPrice: 0,
-    description: "Kimi K2 Thinking - A model with enhanced reasoning capabilities from Kimi K2"
-  },
-  "zai-org/GLM-4.6": {
-    maxTokens: 16384,
+// src/providers/azure.ts
+var azureModels = {
+  "codex-mini": {
+    maxTokens: 1e5,
     contextWindow: 2e5,
     supportsImages: false,
-    supportsPromptCache: false,
-    inputPrice: 0.6,
-    outputPrice: 2.2,
-    cacheWritesPrice: 0,
-    cacheReadsPrice: 0,
-    description: "Frontier open model with advanced agentic, reasoning and coding capabilities"
+    supportsPromptCache: true,
+    inputPrice: 1.5,
+    outputPrice: 6,
+    cacheReadsPrice: 0.375,
+    supportsTemperature: false,
+    description: "Codex Mini: Cloud-based software engineering agent powered by codex-1, a version of o3 optimized for coding tasks"
   },
-  "deepseek-ai/DeepSeek-R1": {
-    maxTokens: 16384,
-    contextWindow: 163840,
+  "gpt-4": {
+    maxTokens: 8192,
+    contextWindow: 8192,
     supportsImages: false,
     supportsPromptCache: false,
-    inputPrice: 2.55,
-    outputPrice: 5.95,
-    cacheWritesPrice: 0,
-    cacheReadsPrice: 0,
-    description: "DeepSeek's first-generation reasoning model"
+    inputPrice: 60,
+    outputPrice: 120,
+    supportsTemperature: true,
+    description: "GPT-4"
   },
-  "deepseek-ai/DeepSeek-R1-0528": {
-    maxTokens: 16384,
-    contextWindow: 163840,
+  "gpt-4-32k": {
+    maxTokens: 32768,
+    contextWindow: 32768,
     supportsImages: false,
     supportsPromptCache: false,
-    inputPrice: 2.55,
-    outputPrice: 5.95,
-    cacheWritesPrice: 0,
-    cacheReadsPrice: 0,
-    description: "The latest revision of DeepSeek's first-generation reasoning model"
+    inputPrice: 60,
+    outputPrice: 120,
+    supportsTemperature: true,
+    description: "GPT-4 32K"
   },
-  "deepseek-ai/DeepSeek-V3-0324": {
-    maxTokens: 16384,
-    contextWindow: 163840,
-    supportsImages: false,
+  "gpt-4-turbo": {
+    maxTokens: 4096,
+    contextWindow: 128e3,
+    supportsImages: true,
     supportsPromptCache: false,
-    inputPrice: 0.77,
-    outputPrice: 0.77,
-    cacheWritesPrice: 0,
-    cacheReadsPrice: 0,
-    description: "Fast general-purpose LLM with enhanced reasoning capabilities"
+    inputPrice: 10,
+    outputPrice: 30,
+    supportsTemperature: true,
+    description: "GPT-4 Turbo"
   },
-  "deepseek-ai/DeepSeek-V3.1": {
-    maxTokens: 16384,
-    contextWindow: 163840,
-    supportsImages: false,
+  "gpt-4-turbo-vision": {
+    maxTokens: 4096,
+    contextWindow: 128e3,
+    supportsImages: true,
     supportsPromptCache: false,
-    inputPrice: 0.5,
-    outputPrice: 1.5,
-    cacheWritesPrice: 0,
-    cacheReadsPrice: 0,
-    description: "Extremely capable general-purpose LLM with hybrid reasoning capabilities and advanced tool calling"
+    inputPrice: 10,
+    outputPrice: 30,
+    supportsTemperature: true,
+    description: "GPT-4 Turbo Vision"
   },
-  "deepseek-ai/DeepSeek-V3.2": {
-    maxTokens: 16384,
-    contextWindow: 163840,
-    supportsImages: false,
-    supportsPromptCache: false,
-    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"
+  "gpt-4.1": {
+    maxTokens: 32768,
+    contextWindow: 1047576,
+    supportsImages: true,
+    supportsPromptCache: true,
+    inputPrice: 2,
+    outputPrice: 8,
+    cacheReadsPrice: 0.5,
+    supportsTemperature: true,
+    description: "GPT-4.1"
   },
-  "openai/gpt-oss-120b": {
-    maxTokens: 16384,
-    contextWindow: 128072,
-    supportsImages: false,
-    supportsPromptCache: false,
+  "gpt-4.1-mini": {
+    maxTokens: 32768,
+    contextWindow: 1047576,
+    supportsImages: true,
+    supportsPromptCache: true,
+    inputPrice: 0.4,
+    outputPrice: 1.6,
+    cacheReadsPrice: 0.1,
+    supportsTemperature: true,
+    description: "GPT-4.1 mini"
+  },
+  "gpt-4.1-nano": {
+    maxTokens: 32768,
+    contextWindow: 1047576,
+    supportsImages: true,
+    supportsPromptCache: true,
     inputPrice: 0.1,
-    outputPrice: 0.5,
-    cacheWritesPrice: 0,
-    cacheReadsPrice: 0,
-    description: "Extremely capable general-purpose LLM with strong, controllable reasoning capabilities"
+    outputPrice: 0.4,
+    cacheReadsPrice: 0.03,
+    supportsTemperature: true,
+    description: "GPT-4.1 nano"
   },
-  "Qwen/Qwen3-235B-A22B-Instruct-2507": {
+  "gpt-4o": {
     maxTokens: 16384,
-    contextWindow: 262144,
-    supportsImages: false,
-    supportsPromptCache: false,
-    inputPrice: 0.22,
-    outputPrice: 0.8,
-    cacheWritesPrice: 0,
-    cacheReadsPrice: 0,
-    description: "Mixture-of-experts LLM with math and reasoning capabilities"
+    contextWindow: 128e3,
+    supportsImages: true,
+    supportsPromptCache: true,
+    inputPrice: 2.5,
+    outputPrice: 10,
+    cacheReadsPrice: 1.25,
+    supportsTemperature: true,
+    description: "GPT-4o"
   },
-  "Qwen/Qwen3-Coder-480B-A35B-Instruct": {
+  "gpt-4o-mini": {
     maxTokens: 16384,
-    contextWindow: 262144,
-    supportsImages: false,
-    supportsPromptCache: false,
-    inputPrice: 0.38,
-    outputPrice: 1.53,
-    cacheWritesPrice: 0,
-    cacheReadsPrice: 0,
-    description: "Mixture-of-experts LLM with advanced coding and reasoning capabilities"
-  },
-  "moonshotai/Kimi-K2-Instruct-0905": {
-    maxTokens: 16384,
-    contextWindow: 262e3,
-    supportsImages: false,
-    supportsPromptCache: false,
-    inputPrice: 0.6,
-    outputPrice: 2.5,
-    cacheWritesPrice: 0,
-    cacheReadsPrice: 0,
-    description: "State of the art language model for agentic and coding tasks. September Update."
-  }
-};
-var basetenDefaultModelId = "zai-org/GLM-4.6";
-
-// src/providers/bedrock.ts
-var bedrockDefaultModelId = "anthropic.claude-sonnet-4-5-20250929-v1:0";
-var bedrockDefaultPromptRouterModelId = "anthropic.claude-3-sonnet-20240229-v1:0";
-var bedrockModels = {
-  "anthropic.claude-sonnet-4-5-20250929-v1:0": {
-    maxTokens: 8192,
-    contextWindow: 2e5,
+    contextWindow: 128e3,
     supportsImages: true,
     supportsPromptCache: true,
-    supportsReasoningBudget: true,
-    inputPrice: 3,
-    outputPrice: 15,
-    cacheWritesPrice: 3.75,
-    cacheReadsPrice: 0.3,
-    minTokensPerCachePoint: 1024,
-    maxCachePoints: 4,
-    cachableFields: ["system", "messages", "tools"]
+    inputPrice: 0.15,
+    outputPrice: 0.6,
+    cacheReadsPrice: 0.08,
+    supportsTemperature: true,
+    description: "GPT-4o mini"
   },
-  "amazon.nova-pro-v1:0": {
-    maxTokens: 5e3,
-    contextWindow: 3e5,
+  "gpt-5": {
+    maxTokens: 128e3,
+    contextWindow: 272e3,
+    includedTools: ["apply_patch"],
+    excludedTools: ["apply_diff", "write_to_file"],
     supportsImages: true,
     supportsPromptCache: true,
-    inputPrice: 0.8,
-    outputPrice: 3.2,
-    cacheWritesPrice: 0.8,
-    // per million tokens
-    cacheReadsPrice: 0.2,
-    // per million tokens
-    minTokensPerCachePoint: 1,
-    maxCachePoints: 1,
-    cachableFields: ["system"]
-  },
-  "amazon.nova-pro-latency-optimized-v1:0": {
-    maxTokens: 5e3,
-    contextWindow: 3e5,
-    supportsImages: true,
-    supportsPromptCache: false,
-    inputPrice: 1,
-    outputPrice: 4,
-    cacheWritesPrice: 1,
-    // per million tokens
-    cacheReadsPrice: 0.25,
-    // per million tokens
-    description: "Amazon Nova Pro with latency optimized inference"
+    supportsReasoningEffort: ["minimal", "low", "medium", "high"],
+    reasoningEffort: "medium",
+    inputPrice: 1.25,
+    outputPrice: 10,
+    cacheReadsPrice: 0.13,
+    supportsVerbosity: true,
+    supportsTemperature: false,
+    description: "GPT-5: The best model for coding and agentic tasks across domains"
   },
-  "amazon.nova-lite-v1:0": {
-    maxTokens: 5e3,
-    contextWindow: 3e5,
+  "gpt-5-codex": {
+    maxTokens: 128e3,
+    contextWindow: 4e5,
+    includedTools: ["apply_patch"],
+    excludedTools: ["apply_diff", "write_to_file"],
     supportsImages: true,
     supportsPromptCache: true,
-    inputPrice: 0.06,
-    outputPrice: 0.24,
-    cacheWritesPrice: 0.06,
-    // per million tokens
-    cacheReadsPrice: 0.015,
-    // per million tokens
-    minTokensPerCachePoint: 1,
-    maxCachePoints: 1,
-    cachableFields: ["system"]
+    supportsReasoningEffort: ["low", "medium", "high"],
+    reasoningEffort: "medium",
+    inputPrice: 1.25,
+    outputPrice: 10,
+    cacheReadsPrice: 0.13,
+    supportsTemperature: false,
+    description: "GPT-5-Codex: A version of GPT-5 optimized for agentic coding in Codex"
   },
-  "amazon.nova-2-lite-v1:0": {
-    maxTokens: 65535,
-    contextWindow: 1e6,
+  "gpt-5-mini": {
+    maxTokens: 128e3,
+    contextWindow: 272e3,
+    includedTools: ["apply_patch"],
+    excludedTools: ["apply_diff", "write_to_file"],
     supportsImages: true,
     supportsPromptCache: true,
-    inputPrice: 0.33,
-    outputPrice: 2.75,
-    cacheWritesPrice: 0,
-    cacheReadsPrice: 0.0825,
-    // 75% less than input price
-    minTokensPerCachePoint: 1,
-    maxCachePoints: 1,
-    cachableFields: ["system"],
-    description: "Amazon Nova 2 Lite - Comparable to Claude Haiku 4.5"
-  },
-  "amazon.nova-micro-v1:0": {
-    maxTokens: 5e3,
-    contextWindow: 128e3,
-    supportsImages: false,
-    supportsPromptCache: true,
-    inputPrice: 0.035,
-    outputPrice: 0.14,
-    cacheWritesPrice: 0.035,
-    // per million tokens
-    cacheReadsPrice: 875e-5,
-    // per million tokens
-    minTokensPerCachePoint: 1,
-    maxCachePoints: 1,
-    cachableFields: ["system"]
+    supportsReasoningEffort: ["minimal", "low", "medium", "high"],
+    reasoningEffort: "medium",
+    inputPrice: 0.25,
+    outputPrice: 2,
+    cacheReadsPrice: 0.03,
+    supportsVerbosity: true,
+    supportsTemperature: false,
+    description: "GPT-5 Mini: A faster, more cost-efficient version of GPT-5 for well-defined tasks"
   },
-  "anthropic.claude-sonnet-4-20250514-v1:0": {
-    maxTokens: 8192,
-    contextWindow: 2e5,
+  "gpt-5-nano": {
+    maxTokens: 128e3,
+    contextWindow: 272e3,
+    includedTools: ["apply_patch"],
+    excludedTools: ["apply_diff", "write_to_file"],
     supportsImages: true,
     supportsPromptCache: true,
-    supportsReasoningBudget: true,
-    inputPrice: 3,
-    outputPrice: 15,
-    cacheWritesPrice: 3.75,
-    cacheReadsPrice: 0.3,
-    minTokensPerCachePoint: 1024,
-    maxCachePoints: 4,
-    cachableFields: ["system", "messages", "tools"]
+    supportsReasoningEffort: ["minimal", "low", "medium", "high"],
+    reasoningEffort: "medium",
+    inputPrice: 0.05,
+    outputPrice: 0.4,
+    cacheReadsPrice: 0.01,
+    supportsVerbosity: true,
+    supportsTemperature: false,
+    description: "GPT-5 Nano: Fastest, most cost-efficient version of GPT-5"
   },
-  "anthropic.claude-opus-4-1-20250805-v1:0": {
-    maxTokens: 8192,
-    contextWindow: 2e5,
+  "gpt-5-pro": {
+    maxTokens: 272e3,
+    contextWindow: 4e5,
+    includedTools: ["apply_patch"],
+    excludedTools: ["apply_diff", "write_to_file"],
     supportsImages: true,
-    supportsPromptCache: true,
-    supportsReasoningBudget: true,
+    supportsPromptCache: false,
+    supportsReasoningEffort: ["minimal", "low", "medium", "high"],
+    reasoningEffort: "medium",
     inputPrice: 15,
-    outputPrice: 75,
-    cacheWritesPrice: 18.75,
-    cacheReadsPrice: 1.5,
-    minTokensPerCachePoint: 1024,
-    maxCachePoints: 4,
-    cachableFields: ["system", "messages", "tools"]
+    outputPrice: 120,
+    supportsVerbosity: true,
+    supportsTemperature: false,
+    description: "GPT-5 Pro"
   },
-  "anthropic.claude-opus-4-6-v1": {
-    maxTokens: 8192,
-    contextWindow: 2e5,
-    // Default 200K, extendable to 1M with beta flag 'context-1m-2025-08-07'
+  "gpt-5.1": {
+    maxTokens: 128e3,
+    contextWindow: 272e3,
+    includedTools: ["apply_patch"],
+    excludedTools: ["apply_diff", "write_to_file"],
     supportsImages: true,
     supportsPromptCache: true,
-    supportsReasoningBudget: true,
-    inputPrice: 5,
-    // $5 per million input tokens (≤200K context)
-    outputPrice: 25,
-    // $25 per million output tokens (≤200K context)
-    cacheWritesPrice: 6.25,
-    // $6.25 per million tokens
-    cacheReadsPrice: 0.5,
-    // $0.50 per million tokens
-    minTokensPerCachePoint: 1024,
-    maxCachePoints: 4,
-    cachableFields: ["system", "messages", "tools"],
-    // Tiered pricing for extended context (requires beta flag 'context-1m-2025-08-07')
-    tiers: [
-      {
-        contextWindow: 1e6,
-        // 1M tokens with beta flag
-        inputPrice: 10,
-        // $10 per million input tokens (>200K context)
-        outputPrice: 37.5,
-        // $37.50 per million output tokens (>200K context)
-        cacheWritesPrice: 12.5,
-        // $12.50 per million tokens (>200K context)
-        cacheReadsPrice: 1
-        // $1.00 per million tokens (>200K context)
-      }
-    ]
+    promptCacheRetention: "24h",
+    supportsReasoningEffort: ["none", "low", "medium", "high"],
+    reasoningEffort: "medium",
+    inputPrice: 1.25,
+    outputPrice: 10,
+    cacheReadsPrice: 0.125,
+    supportsVerbosity: true,
+    supportsTemperature: false,
+    description: "GPT-5.1: The best model for coding and agentic tasks across domains"
   },
-  "anthropic.claude-opus-4-5-20251101-v1:0": {
-    maxTokens: 8192,
-    contextWindow: 2e5,
+  "gpt-5.1-chat": {
+    maxTokens: 16384,
+    contextWindow: 128e3,
+    includedTools: ["apply_patch"],
+    excludedTools: ["apply_diff", "write_to_file"],
     supportsImages: true,
     supportsPromptCache: true,
-    supportsReasoningBudget: true,
-    inputPrice: 5,
-    outputPrice: 25,
-    cacheWritesPrice: 6.25,
-    cacheReadsPrice: 0.5,
-    minTokensPerCachePoint: 1024,
-    maxCachePoints: 4,
-    cachableFields: ["system", "messages", "tools"]
+    promptCacheRetention: "24h",
+    inputPrice: 1.25,
+    outputPrice: 10,
+    cacheReadsPrice: 0.125,
+    supportsTemperature: false,
+    description: "GPT-5.1 Chat: Optimized for conversational AI and chat use cases"
   },
-  "anthropic.claude-opus-4-20250514-v1:0": {
-    maxTokens: 8192,
-    contextWindow: 2e5,
+  "gpt-5.1-codex": {
+    maxTokens: 128e3,
+    contextWindow: 4e5,
+    includedTools: ["apply_patch"],
+    excludedTools: ["apply_diff", "write_to_file"],
     supportsImages: true,
     supportsPromptCache: true,
-    supportsReasoningBudget: true,
-    inputPrice: 15,
-    outputPrice: 75,
-    cacheWritesPrice: 18.75,
-    cacheReadsPrice: 1.5,
-    minTokensPerCachePoint: 1024,
-    maxCachePoints: 4,
-    cachableFields: ["system", "messages", "tools"]
-  },
-  "anthropic.claude-3-7-sonnet-20250219-v1:0": {
-    maxTokens: 8192,
-    contextWindow: 2e5,
+    promptCacheRetention: "24h",
+    supportsReasoningEffort: ["low", "medium", "high"],
+    reasoningEffort: "medium",
+    inputPrice: 1.25,
+    outputPrice: 10,
+    cacheReadsPrice: 0.125,
+    supportsTemperature: false,
+    description: "GPT-5.1 Codex: A version of GPT-5.1 optimized for agentic coding in Codex"
+  },
+  "gpt-5.1-codex-max": {
+    maxTokens: 128e3,
+    contextWindow: 4e5,
+    includedTools: ["apply_patch"],
+    excludedTools: ["apply_diff", "write_to_file"],
     supportsImages: true,
     supportsPromptCache: true,
-    supportsReasoningBudget: true,
-    inputPrice: 3,
-    outputPrice: 15,
-    cacheWritesPrice: 3.75,
-    cacheReadsPrice: 0.3,
-    minTokensPerCachePoint: 1024,
-    maxCachePoints: 4,
-    cachableFields: ["system", "messages", "tools"]
+    promptCacheRetention: "24h",
+    supportsReasoningEffort: ["low", "medium", "high", "xhigh"],
+    reasoningEffort: "medium",
+    inputPrice: 1.25,
+    outputPrice: 10,
+    cacheReadsPrice: 0.125,
+    supportsTemperature: false,
+    description: "GPT-5.1 Codex Max: Our most intelligent coding model optimized for long-horizon, agentic coding tasks"
   },
-  "anthropic.claude-3-5-sonnet-20241022-v2:0": {
-    maxTokens: 8192,
-    contextWindow: 2e5,
+  "gpt-5.1-codex-mini": {
+    maxTokens: 128e3,
+    contextWindow: 4e5,
+    includedTools: ["apply_patch"],
+    excludedTools: ["apply_diff", "write_to_file"],
     supportsImages: true,
     supportsPromptCache: true,
-    inputPrice: 3,
-    outputPrice: 15,
-    cacheWritesPrice: 3.75,
-    cacheReadsPrice: 0.3,
-    minTokensPerCachePoint: 1024,
-    maxCachePoints: 4,
-    cachableFields: ["system", "messages", "tools"]
+    promptCacheRetention: "24h",
+    supportsReasoningEffort: ["low", "medium", "high"],
+    reasoningEffort: "medium",
+    inputPrice: 0.25,
+    outputPrice: 2,
+    cacheReadsPrice: 0.025,
+    supportsTemperature: false,
+    description: "GPT-5.1 Codex mini: A version of GPT-5.1 optimized for agentic coding in Codex"
   },
-  "anthropic.claude-3-5-haiku-20241022-v1:0": {
-    maxTokens: 8192,
-    contextWindow: 2e5,
-    supportsImages: false,
+  "gpt-5.2": {
+    maxTokens: 128e3,
+    contextWindow: 4e5,
+    includedTools: ["apply_patch"],
+    excludedTools: ["apply_diff", "write_to_file"],
+    supportsImages: true,
     supportsPromptCache: true,
-    inputPrice: 0.8,
-    outputPrice: 4,
-    cacheWritesPrice: 1,
-    cacheReadsPrice: 0.08,
-    minTokensPerCachePoint: 2048,
-    maxCachePoints: 4,
-    cachableFields: ["system", "messages", "tools"]
+    promptCacheRetention: "24h",
+    supportsReasoningEffort: ["none", "low", "medium", "high", "xhigh"],
+    reasoningEffort: "medium",
+    inputPrice: 1.75,
+    outputPrice: 14,
+    cacheReadsPrice: 0.125,
+    supportsVerbosity: true,
+    supportsTemperature: false,
+    description: "GPT-5.2: Our flagship model for coding and agentic tasks across industries"
   },
-  "anthropic.claude-haiku-4-5-20251001-v1:0": {
-    maxTokens: 8192,
-    contextWindow: 2e5,
+  "gpt-5.2-chat": {
+    maxTokens: 16384,
+    contextWindow: 128e3,
+    includedTools: ["apply_patch"],
+    excludedTools: ["apply_diff", "write_to_file"],
     supportsImages: true,
     supportsPromptCache: true,
-    supportsReasoningBudget: true,
-    inputPrice: 1,
-    outputPrice: 5,
-    cacheWritesPrice: 1.25,
-    // 5m cache writes
-    cacheReadsPrice: 0.1,
-    // cache hits / refreshes
-    minTokensPerCachePoint: 2048,
-    maxCachePoints: 4,
-    cachableFields: ["system", "messages", "tools"]
+    inputPrice: 1.75,
+    outputPrice: 14,
+    cacheReadsPrice: 0.175,
+    supportsTemperature: false,
+    description: "GPT-5.2 Chat: Optimized for conversational AI and chat use cases"
   },
-  "anthropic.claude-3-5-sonnet-20240620-v1:0": {
-    maxTokens: 8192,
-    contextWindow: 2e5,
+  "gpt-5.2-codex": {
+    maxTokens: 128e3,
+    contextWindow: 4e5,
+    includedTools: ["apply_patch"],
+    excludedTools: ["apply_diff", "write_to_file"],
     supportsImages: true,
-    supportsPromptCache: false,
-    inputPrice: 3,
-    outputPrice: 15
+    supportsPromptCache: true,
+    promptCacheRetention: "24h",
+    supportsReasoningEffort: ["low", "medium", "high", "xhigh"],
+    reasoningEffort: "medium",
+    inputPrice: 1.75,
+    outputPrice: 14,
+    cacheReadsPrice: 0.175,
+    supportsTemperature: false,
+    description: "GPT-5.2 Codex: Our most intelligent coding model optimized for long-horizon, agentic coding tasks"
   },
-  "anthropic.claude-3-opus-20240229-v1:0": {
-    maxTokens: 4096,
+  o1: {
+    maxTokens: 1e5,
     contextWindow: 2e5,
     supportsImages: true,
-    supportsPromptCache: false,
+    supportsPromptCache: true,
     inputPrice: 15,
-    outputPrice: 75
+    outputPrice: 60,
+    cacheReadsPrice: 7.5,
+    supportsTemperature: false,
+    description: "o1"
   },
-  "anthropic.claude-3-sonnet-20240229-v1:0": {
-    maxTokens: 4096,
+  "o1-mini": {
+    maxTokens: 65536,
+    contextWindow: 128e3,
+    supportsImages: true,
+    supportsPromptCache: true,
+    inputPrice: 1.1,
+    outputPrice: 4.4,
+    cacheReadsPrice: 0.55,
+    supportsTemperature: false,
+    description: "o1-mini"
+  },
+  "o1-preview": {
+    maxTokens: 32768,
+    contextWindow: 128e3,
+    supportsImages: true,
+    supportsPromptCache: true,
+    inputPrice: 16.5,
+    outputPrice: 66,
+    cacheReadsPrice: 8.25,
+    supportsTemperature: false,
+    description: "o1-preview"
+  },
+  o3: {
+    maxTokens: 1e5,
     contextWindow: 2e5,
     supportsImages: true,
-    supportsPromptCache: false,
-    inputPrice: 3,
-    outputPrice: 15
+    supportsPromptCache: true,
+    supportsReasoningEffort: ["low", "medium", "high"],
+    reasoningEffort: "medium",
+    inputPrice: 2,
+    outputPrice: 8,
+    cacheReadsPrice: 0.5,
+    supportsTemperature: false,
+    description: "o3"
   },
-  "anthropic.claude-3-haiku-20240307-v1:0": {
-    maxTokens: 4096,
+  "o3-mini": {
+    maxTokens: 1e5,
+    contextWindow: 2e5,
+    supportsImages: false,
+    supportsPromptCache: true,
+    supportsReasoningEffort: ["low", "medium", "high"],
+    reasoningEffort: "medium",
+    inputPrice: 1.1,
+    outputPrice: 4.4,
+    cacheReadsPrice: 0.55,
+    supportsTemperature: false,
+    description: "o3-mini"
+  },
+  "o4-mini": {
+    maxTokens: 1e5,
     contextWindow: 2e5,
     supportsImages: true,
+    supportsPromptCache: true,
+    supportsReasoningEffort: ["low", "medium", "high"],
+    reasoningEffort: "medium",
+    inputPrice: 1.1,
+    outputPrice: 4.4,
+    cacheReadsPrice: 0.28,
+    supportsTemperature: false,
+    description: "o4-mini"
+  }
+};
+var azureDefaultModelId = "gpt-4o";
+var azureDefaultModelInfo = azureModels[azureDefaultModelId];
+
+// src/providers/baseten.ts
+var basetenModels = {
+  "moonshotai/Kimi-K2-Thinking": {
+    maxTokens: 16384,
+    contextWindow: 262e3,
+    supportsImages: false,
     supportsPromptCache: false,
-    inputPrice: 0.25,
-    outputPrice: 1.25
+    inputPrice: 0.6,
+    outputPrice: 2.5,
+    cacheWritesPrice: 0,
+    cacheReadsPrice: 0,
+    description: "Kimi K2 Thinking - A model with enhanced reasoning capabilities from Kimi K2"
   },
-  "deepseek.r1-v1:0": {
-    maxTokens: 32768,
-    contextWindow: 128e3,
+  "zai-org/GLM-4.6": {
+    maxTokens: 16384,
+    contextWindow: 2e5,
     supportsImages: false,
     supportsPromptCache: false,
-    inputPrice: 1.35,
-    outputPrice: 5.4
+    inputPrice: 0.6,
+    outputPrice: 2.2,
+    cacheWritesPrice: 0,
+    cacheReadsPrice: 0,
+    description: "Frontier open model with advanced agentic, reasoning and coding capabilities"
   },
-  "openai.gpt-oss-20b-1:0": {
-    maxTokens: 8192,
-    contextWindow: 128e3,
+  "deepseek-ai/DeepSeek-R1": {
+    maxTokens: 16384,
+    contextWindow: 163840,
     supportsImages: false,
     supportsPromptCache: false,
-    inputPrice: 0.5,
-    outputPrice: 1.5,
-    description: "GPT-OSS 20B - Optimized for low latency and local/specialized use cases"
+    inputPrice: 2.55,
+    outputPrice: 5.95,
+    cacheWritesPrice: 0,
+    cacheReadsPrice: 0,
+    description: "DeepSeek's first-generation reasoning model"
   },
-  "openai.gpt-oss-120b-1:0": {
-    maxTokens: 8192,
-    contextWindow: 128e3,
+  "deepseek-ai/DeepSeek-R1-0528": {
+    maxTokens: 16384,
+    contextWindow: 163840,
     supportsImages: false,
     supportsPromptCache: false,
-    inputPrice: 2,
-    outputPrice: 6,
-    description: "GPT-OSS 120B - Production-ready, general-purpose, high-reasoning model"
+    inputPrice: 2.55,
+    outputPrice: 5.95,
+    cacheWritesPrice: 0,
+    cacheReadsPrice: 0,
+    description: "The latest revision of DeepSeek's first-generation reasoning model"
   },
-  "meta.llama3-3-70b-instruct-v1:0": {
-    maxTokens: 8192,
-    contextWindow: 128e3,
+  "deepseek-ai/DeepSeek-V3-0324": {
+    maxTokens: 16384,
+    contextWindow: 163840,
     supportsImages: false,
     supportsPromptCache: false,
-    inputPrice: 0.72,
-    outputPrice: 0.72,
-    description: "Llama 3.3 Instruct (70B)"
-  },
-  "meta.llama3-2-90b-instruct-v1:0": {
-    maxTokens: 8192,
-    contextWindow: 128e3,
-    supportsImages: true,
-    supportsPromptCache: false,
-    inputPrice: 0.72,
-    outputPrice: 0.72,
-    description: "Llama 3.2 Instruct (90B)"
+    inputPrice: 0.77,
+    outputPrice: 0.77,
+    cacheWritesPrice: 0,
+    cacheReadsPrice: 0,
+    description: "Fast general-purpose LLM with enhanced reasoning capabilities"
   },
-  "meta.llama3-2-11b-instruct-v1:0": {
-    maxTokens: 8192,
-    contextWindow: 128e3,
-    supportsImages: true,
+  "deepseek-ai/DeepSeek-V3.1": {
+    maxTokens: 16384,
+    contextWindow: 163840,
+    supportsImages: false,
     supportsPromptCache: false,
-    inputPrice: 0.16,
-    outputPrice: 0.16,
-    description: "Llama 3.2 Instruct (11B)"
+    inputPrice: 0.5,
+    outputPrice: 1.5,
+    cacheWritesPrice: 0,
+    cacheReadsPrice: 0,
+    description: "Extremely capable general-purpose LLM with hybrid reasoning capabilities and advanced tool calling"
   },
-  "meta.llama3-2-3b-instruct-v1:0": {
-    maxTokens: 8192,
-    contextWindow: 128e3,
+  "deepseek-ai/DeepSeek-V3.2": {
+    maxTokens: 16384,
+    contextWindow: 163840,
     supportsImages: false,
     supportsPromptCache: false,
-    inputPrice: 0.15,
-    outputPrice: 0.15,
-    description: "Llama 3.2 Instruct (3B)"
+    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"
   },
-  "meta.llama3-2-1b-instruct-v1:0": {
-    maxTokens: 8192,
-    contextWindow: 128e3,
+  "openai/gpt-oss-120b": {
+    maxTokens: 16384,
+    contextWindow: 128072,
     supportsImages: false,
     supportsPromptCache: false,
     inputPrice: 0.1,
-    outputPrice: 0.1,
-    description: "Llama 3.2 Instruct (1B)"
+    outputPrice: 0.5,
+    cacheWritesPrice: 0,
+    cacheReadsPrice: 0,
+    description: "Extremely capable general-purpose LLM with strong, controllable reasoning capabilities"
   },
-  "meta.llama3-1-405b-instruct-v1:0": {
-    maxTokens: 8192,
-    contextWindow: 128e3,
+  "Qwen/Qwen3-235B-A22B-Instruct-2507": {
+    maxTokens: 16384,
+    contextWindow: 262144,
     supportsImages: false,
     supportsPromptCache: false,
-    inputPrice: 2.4,
-    outputPrice: 2.4,
-    description: "Llama 3.1 Instruct (405B)"
+    inputPrice: 0.22,
+    outputPrice: 0.8,
+    cacheWritesPrice: 0,
+    cacheReadsPrice: 0,
+    description: "Mixture-of-experts LLM with math and reasoning capabilities"
   },
-  "meta.llama3-1-70b-instruct-v1:0": {
-    maxTokens: 8192,
-    contextWindow: 128e3,
+  "Qwen/Qwen3-Coder-480B-A35B-Instruct": {
+    maxTokens: 16384,
+    contextWindow: 262144,
     supportsImages: false,
     supportsPromptCache: false,
-    inputPrice: 0.72,
-    outputPrice: 0.72,
-    description: "Llama 3.1 Instruct (70B)"
+    inputPrice: 0.38,
+    outputPrice: 1.53,
+    cacheWritesPrice: 0,
+    cacheReadsPrice: 0,
+    description: "Mixture-of-experts LLM with advanced coding and reasoning capabilities"
   },
-  "meta.llama3-1-70b-instruct-latency-optimized-v1:0": {
-    maxTokens: 8192,
-    contextWindow: 128e3,
+  "moonshotai/Kimi-K2-Instruct-0905": {
+    maxTokens: 16384,
+    contextWindow: 262e3,
     supportsImages: false,
     supportsPromptCache: false,
-    inputPrice: 0.9,
-    outputPrice: 0.9,
-    description: "Llama 3.1 Instruct (70B) (w/ latency optimized inference)"
-  },
-  "meta.llama3-1-8b-instruct-v1:0": {
+    inputPrice: 0.6,
+    outputPrice: 2.5,
+    cacheWritesPrice: 0,
+    cacheReadsPrice: 0,
+    description: "State of the art language model for agentic and coding tasks. September Update."
+  }
+};
+var basetenDefaultModelId = "zai-org/GLM-4.6";
+
+// src/providers/bedrock.ts
+var bedrockDefaultModelId = "anthropic.claude-sonnet-4-5-20250929-v1:0";
+var bedrockDefaultPromptRouterModelId = "anthropic.claude-3-sonnet-20240229-v1:0";
+var bedrockModels = {
+  "anthropic.claude-sonnet-4-5-20250929-v1:0": {
     maxTokens: 8192,
-    contextWindow: 8e3,
-    supportsImages: false,
-    supportsPromptCache: false,
-    inputPrice: 0.22,
-    outputPrice: 0.22,
-    description: "Llama 3.1 Instruct (8B)"
-  },
-  "meta.llama3-70b-instruct-v1:0": {
-    maxTokens: 2048,
-    contextWindow: 8e3,
-    supportsImages: false,
-    supportsPromptCache: false,
-    inputPrice: 2.65,
-    outputPrice: 3.5
+    contextWindow: 2e5,
+    supportsImages: true,
+    supportsPromptCache: true,
+    supportsReasoningBudget: true,
+    inputPrice: 3,
+    outputPrice: 15,
+    cacheWritesPrice: 3.75,
+    cacheReadsPrice: 0.3,
+    minTokensPerCachePoint: 1024,
+    maxCachePoints: 4,
+    cachableFields: ["system", "messages", "tools"]
   },
-  "meta.llama3-8b-instruct-v1:0": {
-    maxTokens: 2048,
-    contextWindow: 4e3,
-    supportsImages: false,
-    supportsPromptCache: false,
-    inputPrice: 0.3,
-    outputPrice: 0.6
+  "amazon.nova-pro-v1:0": {
+    maxTokens: 5e3,
+    contextWindow: 3e5,
+    supportsImages: true,
+    supportsPromptCache: true,
+    inputPrice: 0.8,
+    outputPrice: 3.2,
+    cacheWritesPrice: 0.8,
+    // per million tokens
+    cacheReadsPrice: 0.2,
+    // per million tokens
+    minTokensPerCachePoint: 1,
+    maxCachePoints: 1,
+    cachableFields: ["system"]
   },
-  "amazon.titan-text-lite-v1:0": {
-    maxTokens: 4096,
-    contextWindow: 8e3,
-    supportsImages: false,
+  "amazon.nova-pro-latency-optimized-v1:0": {
+    maxTokens: 5e3,
+    contextWindow: 3e5,
+    supportsImages: true,
     supportsPromptCache: false,
-    inputPrice: 0.15,
-    outputPrice: 0.2,
-    description: "Amazon Titan Text Lite"
+    inputPrice: 1,
+    outputPrice: 4,
+    cacheWritesPrice: 1,
+    // per million tokens
+    cacheReadsPrice: 0.25,
+    // per million tokens
+    description: "Amazon Nova Pro with latency optimized inference"
   },
-  "amazon.titan-text-express-v1:0": {
-    maxTokens: 4096,
-    contextWindow: 8e3,
-    supportsImages: false,
-    supportsPromptCache: false,
-    inputPrice: 0.2,
-    outputPrice: 0.6,
-    description: "Amazon Titan Text Express"
+  "amazon.nova-lite-v1:0": {
+    maxTokens: 5e3,
+    contextWindow: 3e5,
+    supportsImages: true,
+    supportsPromptCache: true,
+    inputPrice: 0.06,
+    outputPrice: 0.24,
+    cacheWritesPrice: 0.06,
+    // per million tokens
+    cacheReadsPrice: 0.015,
+    // per million tokens
+    minTokensPerCachePoint: 1,
+    maxCachePoints: 1,
+    cachableFields: ["system"]
   },
-  "moonshot.kimi-k2-thinking": {
-    maxTokens: 32e3,
-    contextWindow: 262144,
-    supportsImages: false,
-    supportsPromptCache: false,
-    preserveReasoning: true,
-    inputPrice: 0.6,
-    outputPrice: 2.5,
-    description: "Kimi K2 Thinking (1T parameter MoE model with 32B active parameters)"
+  "amazon.nova-2-lite-v1:0": {
+    maxTokens: 65535,
+    contextWindow: 1e6,
+    supportsImages: true,
+    supportsPromptCache: true,
+    inputPrice: 0.33,
+    outputPrice: 2.75,
+    cacheWritesPrice: 0,
+    cacheReadsPrice: 0.0825,
+    // 75% less than input price
+    minTokensPerCachePoint: 1,
+    maxCachePoints: 1,
+    cachableFields: ["system"],
+    description: "Amazon Nova 2 Lite - Comparable to Claude Haiku 4.5"
   },
-  "minimax.minimax-m2": {
-    maxTokens: 16384,
-    contextWindow: 196608,
+  "amazon.nova-micro-v1:0": {
+    maxTokens: 5e3,
+    contextWindow: 128e3,
     supportsImages: false,
-    supportsPromptCache: false,
-    preserveReasoning: true,
-    inputPrice: 0.3,
-    outputPrice: 1.2,
-    description: "MiniMax M2 (230B parameter MoE model with 10B active parameters)"
+    supportsPromptCache: true,
+    inputPrice: 0.035,
+    outputPrice: 0.14,
+    cacheWritesPrice: 0.035,
+    // per million tokens
+    cacheReadsPrice: 875e-5,
+    // per million tokens
+    minTokensPerCachePoint: 1,
+    maxCachePoints: 1,
+    cachableFields: ["system"]
   },
-  "qwen.qwen3-next-80b-a3b": {
+  "anthropic.claude-sonnet-4-20250514-v1:0": {
     maxTokens: 8192,
-    contextWindow: 262144,
-    supportsImages: false,
-    supportsPromptCache: false,
-    inputPrice: 0.15,
-    outputPrice: 1.2,
-    description: "Qwen3 Next 80B (MoE model with 3B active parameters)"
+    contextWindow: 2e5,
+    supportsImages: true,
+    supportsPromptCache: true,
+    supportsReasoningBudget: true,
+    inputPrice: 3,
+    outputPrice: 15,
+    cacheWritesPrice: 3.75,
+    cacheReadsPrice: 0.3,
+    minTokensPerCachePoint: 1024,
+    maxCachePoints: 4,
+    cachableFields: ["system", "messages", "tools"]
   },
-  "qwen.qwen3-coder-480b-a35b-v1:0": {
+  "anthropic.claude-opus-4-1-20250805-v1:0": {
     maxTokens: 8192,
-    contextWindow: 262144,
-    supportsImages: false,
-    supportsPromptCache: false,
-    inputPrice: 0.45,
-    outputPrice: 1.8,
-    description: "Qwen3 Coder 480B (MoE model with 35B active parameters)"
-  }
-};
-var BEDROCK_DEFAULT_TEMPERATURE = 0.3;
-var BEDROCK_MAX_TOKENS = 4096;
-var BEDROCK_DEFAULT_CONTEXT = 128e3;
-var AWS_INFERENCE_PROFILE_MAPPING = [
-  // Australia regions (Sydney and Melbourne) → au. inference profile (most specific - 14 chars)
-  ["ap-southeast-2", "au."],
-  ["ap-southeast-4", "au."],
-  // Japan regions (Tokyo and Osaka) → jp. inference profile (13 chars)
-  ["ap-northeast-", "jp."],
-  // US Government Cloud → ug. inference profile (7 chars)
-  ["us-gov-", "ug."],
-  // Americas regions → us. inference profile (3 chars)
-  ["us-", "us."],
-  // Europe regions → eu. inference profile (3 chars)
-  ["eu-", "eu."],
-  // Asia Pacific regions → apac. inference profile (3 chars)
-  ["ap-", "apac."],
-  // Canada regions → ca. inference profile (3 chars)
-  ["ca-", "ca."],
-  // South America regions → sa. inference profile (3 chars)
-  ["sa-", "sa."]
-];
-var BEDROCK_REGIONS = [
-  { value: "us-east-1", label: "us-east-1" },
-  { value: "us-east-2", label: "us-east-2" },
-  { value: "us-west-1", label: "us-west-1" },
-  { value: "us-west-2", label: "us-west-2" },
-  { value: "ap-northeast-1", label: "ap-northeast-1" },
-  { value: "ap-northeast-2", label: "ap-northeast-2" },
-  { value: "ap-northeast-3", label: "ap-northeast-3" },
-  { value: "ap-south-1", label: "ap-south-1" },
-  { value: "ap-south-2", label: "ap-south-2" },
-  { value: "ap-southeast-1", label: "ap-southeast-1" },
-  { value: "ap-southeast-2", label: "ap-southeast-2" },
-  { value: "ap-east-1", label: "ap-east-1" },
-  { value: "eu-central-1", label: "eu-central-1" },
-  { value: "eu-central-2", label: "eu-central-2" },
-  { value: "eu-west-1", label: "eu-west-1" },
-  { value: "eu-west-2", label: "eu-west-2" },
-  { value: "eu-west-3", label: "eu-west-3" },
-  { value: "eu-north-1", label: "eu-north-1" },
-  { value: "eu-south-1", label: "eu-south-1" },
-  { value: "eu-south-2", label: "eu-south-2" },
-  { value: "ca-central-1", label: "ca-central-1" },
-  { value: "sa-east-1", label: "sa-east-1" },
-  { value: "us-gov-east-1", label: "us-gov-east-1" },
-  { value: "us-gov-west-1", label: "us-gov-west-1" }
-].sort((a, b) => a.value.localeCompare(b.value));
-var BEDROCK_1M_CONTEXT_MODEL_IDS = [
-  "anthropic.claude-sonnet-4-20250514-v1:0",
-  "anthropic.claude-sonnet-4-5-20250929-v1:0",
-  "anthropic.claude-opus-4-6-v1"
-];
-var BEDROCK_GLOBAL_INFERENCE_MODEL_IDS = [
-  "anthropic.claude-sonnet-4-20250514-v1:0",
-  "anthropic.claude-sonnet-4-5-20250929-v1:0",
-  "anthropic.claude-haiku-4-5-20251001-v1:0",
-  "anthropic.claude-opus-4-5-20251101-v1:0",
-  "anthropic.claude-opus-4-6-v1"
-];
-var BEDROCK_SERVICE_TIER_MODEL_IDS = [
-  // Amazon Nova models
-  "amazon.nova-lite-v1:0",
-  "amazon.nova-2-lite-v1:0",
-  "amazon.nova-pro-v1:0",
-  "amazon.nova-pro-latency-optimized-v1:0",
-  // DeepSeek models
-  "deepseek.r1-v1:0",
-  // Qwen models
-  "qwen.qwen3-next-80b-a3b",
-  "qwen.qwen3-coder-480b-a35b-v1:0",
-  // OpenAI GPT-OSS models
-  "openai.gpt-oss-20b-1:0",
-  "openai.gpt-oss-120b-1:0"
-];
-var BEDROCK_SERVICE_TIER_PRICING = {
-  STANDARD: 1,
-  // Base price
-  FLEX: 0.5,
-  // 50% discount from standard
-  PRIORITY: 1.75
-  // 75% premium over standard
-};
-
-// src/providers/cerebras.ts
-var cerebrasDefaultModelId = "gpt-oss-120b";
-var cerebrasModels = {
-  "zai-glm-4.7": {
-    maxTokens: 16384,
-    // Conservative default to avoid premature rate limiting (Cerebras reserves quota upfront)
-    contextWindow: 131072,
-    supportsImages: false,
+    contextWindow: 2e5,
+    supportsImages: true,
     supportsPromptCache: true,
-    supportsTemperature: true,
-    defaultTemperature: 1,
-    inputPrice: 0,
-    outputPrice: 0,
-    description: "Highly capable general-purpose model on Cerebras (up to 1,000 tokens/s), competitive with leading proprietary models on coding tasks."
-  },
-  "qwen-3-235b-a22b-instruct-2507": {
-    maxTokens: 16384,
-    // Conservative default to avoid premature rate limiting
-    contextWindow: 64e3,
-    supportsImages: false,
-    supportsPromptCache: false,
-    inputPrice: 0,
-    outputPrice: 0,
-    description: "Intelligent model with ~1400 tokens/s"
-  },
-  "llama-3.3-70b": {
-    maxTokens: 16384,
-    // Conservative default to avoid premature rate limiting
-    contextWindow: 64e3,
-    supportsImages: false,
-    supportsPromptCache: false,
-    inputPrice: 0,
-    outputPrice: 0,
-    description: "Powerful model with ~2600 tokens/s"
-  },
-  "qwen-3-32b": {
-    maxTokens: 16384,
-    // Conservative default to avoid premature rate limiting
-    contextWindow: 64e3,
-    supportsImages: false,
-    supportsPromptCache: false,
-    inputPrice: 0,
-    outputPrice: 0,
-    description: "SOTA coding performance with ~2500 tokens/s"
-  },
-  "gpt-oss-120b": {
-    maxTokens: 16384,
-    // Conservative default to avoid premature rate limiting
-    contextWindow: 64e3,
-    supportsImages: false,
-    supportsPromptCache: false,
-    inputPrice: 0,
-    outputPrice: 0,
-    description: "OpenAI GPT OSS model with ~2800 tokens/s\n\n\u2022 64K context window\n\u2022 Excels at efficient reasoning across science, math, and coding"
-  }
-};
-
-// src/providers/chutes.ts
-var chutesDefaultModelId = "deepseek-ai/DeepSeek-R1-0528";
-var chutesModels = {
-  "deepseek-ai/DeepSeek-R1-0528": {
-    maxTokens: 32768,
-    contextWindow: 163840,
-    supportsImages: false,
-    supportsPromptCache: false,
-    inputPrice: 0,
-    outputPrice: 0,
-    description: "DeepSeek R1 0528 model."
-  },
-  "deepseek-ai/DeepSeek-R1": {
-    maxTokens: 32768,
-    contextWindow: 163840,
-    supportsImages: false,
-    supportsPromptCache: false,
-    inputPrice: 0,
-    outputPrice: 0,
-    description: "DeepSeek R1 model."
-  },
-  "deepseek-ai/DeepSeek-V3": {
-    maxTokens: 32768,
-    contextWindow: 163840,
-    supportsImages: false,
-    supportsPromptCache: false,
-    inputPrice: 0,
-    outputPrice: 0,
-    description: "DeepSeek V3 model."
-  },
-  "deepseek-ai/DeepSeek-V3.1": {
-    maxTokens: 32768,
-    contextWindow: 163840,
-    supportsImages: false,
-    supportsPromptCache: false,
-    inputPrice: 0,
-    outputPrice: 0,
-    description: "DeepSeek V3.1 model."
-  },
-  "deepseek-ai/DeepSeek-V3.1-Terminus": {
-    maxTokens: 163840,
-    contextWindow: 163840,
-    supportsImages: false,
-    supportsPromptCache: false,
-    inputPrice: 0.23,
-    outputPrice: 0.9,
-    description: "DeepSeek\u2011V3.1\u2011Terminus is an update to V3.1 that improves language consistency by reducing CN/EN mix\u2011ups and eliminating random characters, while strengthening agent capabilities with notably better Code Agent and Search Agent performance."
-  },
-  "deepseek-ai/DeepSeek-V3.1-turbo": {
-    maxTokens: 32768,
-    contextWindow: 163840,
-    supportsImages: false,
-    supportsPromptCache: false,
-    inputPrice: 1,
-    outputPrice: 3,
-    description: "DeepSeek-V3.1-turbo is an FP8, speculative-decoding turbo variant optimized for ultra-fast single-shot queries (~200 TPS), with outputs close to the originals and solid function calling/reasoning/structured output, priced at $1/M input and $3/M output tokens, using 2\xD7 quota per request and not intended for bulk workloads."
+    supportsReasoningBudget: true,
+    inputPrice: 15,
+    outputPrice: 75,
+    cacheWritesPrice: 18.75,
+    cacheReadsPrice: 1.5,
+    minTokensPerCachePoint: 1024,
+    maxCachePoints: 4,
+    cachableFields: ["system", "messages", "tools"]
   },
-  "deepseek-ai/DeepSeek-V3.2-Exp": {
-    maxTokens: 163840,
-    contextWindow: 163840,
-    supportsImages: false,
-    supportsPromptCache: false,
-    inputPrice: 0.25,
-    outputPrice: 0.35,
-    description: "DeepSeek-V3.2-Exp is an experimental LLM that introduces DeepSeek Sparse Attention to improve long\u2011context training and inference efficiency while maintaining performance comparable to V3.1\u2011Terminus."
+  "anthropic.claude-opus-4-6-v1": {
+    maxTokens: 8192,
+    contextWindow: 2e5,
+    // Default 200K, extendable to 1M with beta flag 'context-1m-2025-08-07'
+    supportsImages: true,
+    supportsPromptCache: true,
+    supportsReasoningBudget: true,
+    inputPrice: 5,
+    // $5 per million input tokens (≤200K context)
+    outputPrice: 25,
+    // $25 per million output tokens (≤200K context)
+    cacheWritesPrice: 6.25,
+    // $6.25 per million tokens
+    cacheReadsPrice: 0.5,
+    // $0.50 per million tokens
+    minTokensPerCachePoint: 1024,
+    maxCachePoints: 4,
+    cachableFields: ["system", "messages", "tools"],
+    // Tiered pricing for extended context (requires beta flag 'context-1m-2025-08-07')
+    tiers: [
+      {
+        contextWindow: 1e6,
+        // 1M tokens with beta flag
+        inputPrice: 10,
+        // $10 per million input tokens (>200K context)
+        outputPrice: 37.5,
+        // $37.50 per million output tokens (>200K context)
+        cacheWritesPrice: 12.5,
+        // $12.50 per million tokens (>200K context)
+        cacheReadsPrice: 1
+        // $1.00 per million tokens (>200K context)
+      }
+    ]
   },
-  "unsloth/Llama-3.3-70B-Instruct": {
-    maxTokens: 32768,
-    // From Groq
-    contextWindow: 131072,
-    // From Groq
-    supportsImages: false,
-    supportsPromptCache: false,
-    inputPrice: 0,
-    outputPrice: 0,
-    description: "Unsloth Llama 3.3 70B Instruct model."
+  "anthropic.claude-opus-4-5-20251101-v1:0": {
+    maxTokens: 8192,
+    contextWindow: 2e5,
+    supportsImages: true,
+    supportsPromptCache: true,
+    supportsReasoningBudget: true,
+    inputPrice: 5,
+    outputPrice: 25,
+    cacheWritesPrice: 6.25,
+    cacheReadsPrice: 0.5,
+    minTokensPerCachePoint: 1024,
+    maxCachePoints: 4,
+    cachableFields: ["system", "messages", "tools"]
   },
-  "chutesai/Llama-4-Scout-17B-16E-Instruct": {
-    maxTokens: 32768,
-    contextWindow: 512e3,
-    supportsImages: false,
-    supportsPromptCache: false,
-    inputPrice: 0,
-    outputPrice: 0,
-    description: "ChutesAI Llama 4 Scout 17B Instruct model, 512K context."
+  "anthropic.claude-opus-4-20250514-v1:0": {
+    maxTokens: 8192,
+    contextWindow: 2e5,
+    supportsImages: true,
+    supportsPromptCache: true,
+    supportsReasoningBudget: true,
+    inputPrice: 15,
+    outputPrice: 75,
+    cacheWritesPrice: 18.75,
+    cacheReadsPrice: 1.5,
+    minTokensPerCachePoint: 1024,
+    maxCachePoints: 4,
+    cachableFields: ["system", "messages", "tools"]
   },
-  "unsloth/Mistral-Nemo-Instruct-2407": {
-    maxTokens: 32768,
-    contextWindow: 128e3,
-    supportsImages: false,
-    supportsPromptCache: false,
-    inputPrice: 0,
-    outputPrice: 0,
-    description: "Unsloth Mistral Nemo Instruct model."
+  "anthropic.claude-3-7-sonnet-20250219-v1:0": {
+    maxTokens: 8192,
+    contextWindow: 2e5,
+    supportsImages: true,
+    supportsPromptCache: true,
+    supportsReasoningBudget: true,
+    inputPrice: 3,
+    outputPrice: 15,
+    cacheWritesPrice: 3.75,
+    cacheReadsPrice: 0.3,
+    minTokensPerCachePoint: 1024,
+    maxCachePoints: 4,
+    cachableFields: ["system", "messages", "tools"]
   },
-  "unsloth/gemma-3-12b-it": {
-    maxTokens: 32768,
-    contextWindow: 131072,
-    supportsImages: false,
-    supportsPromptCache: false,
-    inputPrice: 0,
-    outputPrice: 0,
-    description: "Unsloth Gemma 3 12B IT model."
+  "anthropic.claude-3-5-sonnet-20241022-v2:0": {
+    maxTokens: 8192,
+    contextWindow: 2e5,
+    supportsImages: true,
+    supportsPromptCache: true,
+    inputPrice: 3,
+    outputPrice: 15,
+    cacheWritesPrice: 3.75,
+    cacheReadsPrice: 0.3,
+    minTokensPerCachePoint: 1024,
+    maxCachePoints: 4,
+    cachableFields: ["system", "messages", "tools"]
   },
-  "NousResearch/DeepHermes-3-Llama-3-8B-Preview": {
-    maxTokens: 32768,
-    contextWindow: 131072,
+  "anthropic.claude-3-5-haiku-20241022-v1:0": {
+    maxTokens: 8192,
+    contextWindow: 2e5,
     supportsImages: false,
-    supportsPromptCache: false,
-    inputPrice: 0,
-    outputPrice: 0,
-    description: "Nous DeepHermes 3 Llama 3 8B Preview model."
+    supportsPromptCache: true,
+    inputPrice: 0.8,
+    outputPrice: 4,
+    cacheWritesPrice: 1,
+    cacheReadsPrice: 0.08,
+    minTokensPerCachePoint: 2048,
+    maxCachePoints: 4,
+    cachableFields: ["system", "messages", "tools"]
   },
-  "unsloth/gemma-3-4b-it": {
-    maxTokens: 32768,
-    contextWindow: 131072,
-    supportsImages: false,
-    supportsPromptCache: false,
-    inputPrice: 0,
-    outputPrice: 0,
-    description: "Unsloth Gemma 3 4B IT model."
+  "anthropic.claude-haiku-4-5-20251001-v1:0": {
+    maxTokens: 8192,
+    contextWindow: 2e5,
+    supportsImages: true,
+    supportsPromptCache: true,
+    supportsReasoningBudget: true,
+    inputPrice: 1,
+    outputPrice: 5,
+    cacheWritesPrice: 1.25,
+    // 5m cache writes
+    cacheReadsPrice: 0.1,
+    // cache hits / refreshes
+    minTokensPerCachePoint: 2048,
+    maxCachePoints: 4,
+    cachableFields: ["system", "messages", "tools"]
   },
-  "nvidia/Llama-3_3-Nemotron-Super-49B-v1": {
-    maxTokens: 32768,
-    contextWindow: 131072,
-    supportsImages: false,
+  "anthropic.claude-3-5-sonnet-20240620-v1:0": {
+    maxTokens: 8192,
+    contextWindow: 2e5,
+    supportsImages: true,
     supportsPromptCache: false,
-    inputPrice: 0,
-    outputPrice: 0,
-    description: "Nvidia Llama 3.3 Nemotron Super 49B model."
+    inputPrice: 3,
+    outputPrice: 15
   },
-  "nvidia/Llama-3_1-Nemotron-Ultra-253B-v1": {
-    maxTokens: 32768,
-    contextWindow: 131072,
-    supportsImages: false,
+  "anthropic.claude-3-opus-20240229-v1:0": {
+    maxTokens: 4096,
+    contextWindow: 2e5,
+    supportsImages: true,
     supportsPromptCache: false,
-    inputPrice: 0,
-    outputPrice: 0,
-    description: "Nvidia Llama 3.1 Nemotron Ultra 253B model."
+    inputPrice: 15,
+    outputPrice: 75
   },
-  "chutesai/Llama-4-Maverick-17B-128E-Instruct-FP8": {
-    maxTokens: 32768,
-    contextWindow: 256e3,
-    supportsImages: false,
+  "anthropic.claude-3-sonnet-20240229-v1:0": {
+    maxTokens: 4096,
+    contextWindow: 2e5,
+    supportsImages: true,
     supportsPromptCache: false,
-    inputPrice: 0,
-    outputPrice: 0,
-    description: "ChutesAI Llama 4 Maverick 17B Instruct FP8 model."
+    inputPrice: 3,
+    outputPrice: 15
   },
-  "deepseek-ai/DeepSeek-V3-Base": {
-    maxTokens: 32768,
-    contextWindow: 163840,
-    supportsImages: false,
+  "anthropic.claude-3-haiku-20240307-v1:0": {
+    maxTokens: 4096,
+    contextWindow: 2e5,
+    supportsImages: true,
     supportsPromptCache: false,
-    inputPrice: 0,
-    outputPrice: 0,
-    description: "DeepSeek V3 Base model."
+    inputPrice: 0.25,
+    outputPrice: 1.25
   },
-  "deepseek-ai/DeepSeek-R1-Zero": {
+  "deepseek.r1-v1:0": {
     maxTokens: 32768,
-    contextWindow: 163840,
+    contextWindow: 128e3,
     supportsImages: false,
     supportsPromptCache: false,
-    inputPrice: 0,
-    outputPrice: 0,
-    description: "DeepSeek R1 Zero model."
+    inputPrice: 1.35,
+    outputPrice: 5.4
   },
-  "deepseek-ai/DeepSeek-V3-0324": {
-    maxTokens: 32768,
-    contextWindow: 163840,
+  "openai.gpt-oss-20b-1:0": {
+    maxTokens: 8192,
+    contextWindow: 128e3,
     supportsImages: false,
     supportsPromptCache: false,
-    inputPrice: 0,
-    outputPrice: 0,
-    description: "DeepSeek V3 (0324) model."
+    inputPrice: 0.5,
+    outputPrice: 1.5,
+    description: "GPT-OSS 20B - Optimized for low latency and local/specialized use cases"
   },
-  "Qwen/Qwen3-235B-A22B-Instruct-2507": {
-    maxTokens: 32768,
-    contextWindow: 262144,
+  "openai.gpt-oss-120b-1:0": {
+    maxTokens: 8192,
+    contextWindow: 128e3,
     supportsImages: false,
     supportsPromptCache: false,
-    inputPrice: 0,
-    outputPrice: 0,
-    description: "Qwen3 235B A22B Instruct 2507 model with 262K context window."
+    inputPrice: 2,
+    outputPrice: 6,
+    description: "GPT-OSS 120B - Production-ready, general-purpose, high-reasoning model"
   },
-  "Qwen/Qwen3-235B-A22B": {
-    maxTokens: 32768,
-    contextWindow: 40960,
+  "meta.llama3-3-70b-instruct-v1:0": {
+    maxTokens: 8192,
+    contextWindow: 128e3,
     supportsImages: false,
     supportsPromptCache: false,
-    inputPrice: 0,
-    outputPrice: 0,
-    description: "Qwen3 235B A22B model."
+    inputPrice: 0.72,
+    outputPrice: 0.72,
+    description: "Llama 3.3 Instruct (70B)"
   },
-  "Qwen/Qwen3-32B": {
-    maxTokens: 32768,
-    contextWindow: 40960,
-    supportsImages: false,
+  "meta.llama3-2-90b-instruct-v1:0": {
+    maxTokens: 8192,
+    contextWindow: 128e3,
+    supportsImages: true,
     supportsPromptCache: false,
-    inputPrice: 0,
-    outputPrice: 0,
-    description: "Qwen3 32B model."
+    inputPrice: 0.72,
+    outputPrice: 0.72,
+    description: "Llama 3.2 Instruct (90B)"
   },
-  "Qwen/Qwen3-30B-A3B": {
-    maxTokens: 32768,
-    contextWindow: 40960,
-    supportsImages: false,
+  "meta.llama3-2-11b-instruct-v1:0": {
+    maxTokens: 8192,
+    contextWindow: 128e3,
+    supportsImages: true,
     supportsPromptCache: false,
-    inputPrice: 0,
-    outputPrice: 0,
-    description: "Qwen3 30B A3B model."
+    inputPrice: 0.16,
+    outputPrice: 0.16,
+    description: "Llama 3.2 Instruct (11B)"
   },
-  "Qwen/Qwen3-14B": {
-    maxTokens: 32768,
-    contextWindow: 40960,
+  "meta.llama3-2-3b-instruct-v1:0": {
+    maxTokens: 8192,
+    contextWindow: 128e3,
     supportsImages: false,
     supportsPromptCache: false,
-    inputPrice: 0,
-    outputPrice: 0,
-    description: "Qwen3 14B model."
+    inputPrice: 0.15,
+    outputPrice: 0.15,
+    description: "Llama 3.2 Instruct (3B)"
   },
-  "Qwen/Qwen3-8B": {
-    maxTokens: 32768,
-    contextWindow: 40960,
+  "meta.llama3-2-1b-instruct-v1:0": {
+    maxTokens: 8192,
+    contextWindow: 128e3,
     supportsImages: false,
     supportsPromptCache: false,
-    inputPrice: 0,
-    outputPrice: 0,
-    description: "Qwen3 8B model."
+    inputPrice: 0.1,
+    outputPrice: 0.1,
+    description: "Llama 3.2 Instruct (1B)"
   },
-  "microsoft/MAI-DS-R1-FP8": {
-    maxTokens: 32768,
-    contextWindow: 163840,
+  "meta.llama3-1-405b-instruct-v1:0": {
+    maxTokens: 8192,
+    contextWindow: 128e3,
     supportsImages: false,
     supportsPromptCache: false,
-    inputPrice: 0,
-    outputPrice: 0,
-    description: "Microsoft MAI-DS-R1 FP8 model."
+    inputPrice: 2.4,
+    outputPrice: 2.4,
+    description: "Llama 3.1 Instruct (405B)"
   },
-  "tngtech/DeepSeek-R1T-Chimera": {
-    maxTokens: 32768,
-    contextWindow: 163840,
+  "meta.llama3-1-70b-instruct-v1:0": {
+    maxTokens: 8192,
+    contextWindow: 128e3,
     supportsImages: false,
     supportsPromptCache: false,
-    inputPrice: 0,
-    outputPrice: 0,
-    description: "TNGTech DeepSeek R1T Chimera model."
+    inputPrice: 0.72,
+    outputPrice: 0.72,
+    description: "Llama 3.1 Instruct (70B)"
   },
-  "zai-org/GLM-4.5-Air": {
-    maxTokens: 32768,
-    contextWindow: 151329,
+  "meta.llama3-1-70b-instruct-latency-optimized-v1:0": {
+    maxTokens: 8192,
+    contextWindow: 128e3,
     supportsImages: false,
     supportsPromptCache: false,
-    inputPrice: 0,
-    outputPrice: 0,
-    description: "GLM-4.5-Air model with 151,329 token context window and 106B total parameters with 12B activated."
+    inputPrice: 0.9,
+    outputPrice: 0.9,
+    description: "Llama 3.1 Instruct (70B) (w/ latency optimized inference)"
   },
-  "zai-org/GLM-4.5-FP8": {
-    maxTokens: 32768,
-    contextWindow: 131072,
+  "meta.llama3-1-8b-instruct-v1:0": {
+    maxTokens: 8192,
+    contextWindow: 8e3,
     supportsImages: false,
     supportsPromptCache: false,
-    inputPrice: 0,
-    outputPrice: 0,
-    description: "GLM-4.5-FP8 model with 128k token context window, optimized for agent-based applications with MoE architecture."
+    inputPrice: 0.22,
+    outputPrice: 0.22,
+    description: "Llama 3.1 Instruct (8B)"
   },
-  "zai-org/GLM-4.5-turbo": {
-    maxTokens: 32768,
-    contextWindow: 131072,
+  "meta.llama3-70b-instruct-v1:0": {
+    maxTokens: 2048,
+    contextWindow: 8e3,
     supportsImages: false,
     supportsPromptCache: false,
-    inputPrice: 1,
-    outputPrice: 3,
-    description: "GLM-4.5-turbo model with 128K token context window, optimized for fast inference."
+    inputPrice: 2.65,
+    outputPrice: 3.5
   },
-  "zai-org/GLM-4.6-FP8": {
-    maxTokens: 32768,
-    contextWindow: 202752,
+  "meta.llama3-8b-instruct-v1:0": {
+    maxTokens: 2048,
+    contextWindow: 4e3,
     supportsImages: false,
     supportsPromptCache: false,
-    inputPrice: 0,
-    outputPrice: 0,
-    description: "GLM-4.6 introduces major upgrades over GLM-4.5, including a longer 200K-token context window for complex tasks, stronger coding performance in benchmarks and real-world tools (such as Claude Code, Cline, Roo Code, and Kilo Code), improved reasoning with tool use during inference, more capable and efficient agent integration, and refined writing that better matches human style, readability, and natural role-play scenarios."
+    inputPrice: 0.3,
+    outputPrice: 0.6
   },
-  "zai-org/GLM-4.6-turbo": {
-    maxTokens: 202752,
-    // From Chutes /v1/models: max_output_length
-    contextWindow: 202752,
+  "amazon.titan-text-lite-v1:0": {
+    maxTokens: 4096,
+    contextWindow: 8e3,
     supportsImages: false,
     supportsPromptCache: false,
-    inputPrice: 1.15,
-    outputPrice: 3.25,
-    description: "GLM-4.6-turbo model with 200K-token context window, optimized for fast inference."
+    inputPrice: 0.15,
+    outputPrice: 0.2,
+    description: "Amazon Titan Text Lite"
   },
-  "meituan-longcat/LongCat-Flash-Thinking-FP8": {
-    maxTokens: 32768,
-    contextWindow: 128e3,
+  "amazon.titan-text-express-v1:0": {
+    maxTokens: 4096,
+    contextWindow: 8e3,
     supportsImages: false,
     supportsPromptCache: false,
-    inputPrice: 0,
-    outputPrice: 0,
-    description: "LongCat Flash Thinking FP8 model with 128K context window, optimized for complex reasoning and coding tasks."
+    inputPrice: 0.2,
+    outputPrice: 0.6,
+    description: "Amazon Titan Text Express"
   },
-  "Qwen/Qwen3-Coder-480B-A35B-Instruct-FP8": {
-    maxTokens: 32768,
+  "moonshot.kimi-k2-thinking": {
+    maxTokens: 32e3,
     contextWindow: 262144,
     supportsImages: false,
     supportsPromptCache: false,
-    inputPrice: 0,
-    outputPrice: 0,
-    description: "Qwen3 Coder 480B A35B Instruct FP8 model, optimized for coding tasks."
+    preserveReasoning: true,
+    inputPrice: 0.6,
+    outputPrice: 2.5,
+    description: "Kimi K2 Thinking (1T parameter MoE model with 32B active parameters)"
   },
-  "moonshotai/Kimi-K2-Instruct-75k": {
-    maxTokens: 32768,
-    contextWindow: 75e3,
+  "minimax.minimax-m2": {
+    maxTokens: 16384,
+    contextWindow: 196608,
     supportsImages: false,
     supportsPromptCache: false,
-    inputPrice: 0.1481,
-    outputPrice: 0.5926,
-    description: "Moonshot AI Kimi K2 Instruct model with 75k context window."
+    preserveReasoning: true,
+    inputPrice: 0.3,
+    outputPrice: 1.2,
+    description: "MiniMax M2 (230B parameter MoE model with 10B active parameters)"
   },
-  "moonshotai/Kimi-K2-Instruct-0905": {
-    maxTokens: 32768,
+  "qwen.qwen3-next-80b-a3b": {
+    maxTokens: 8192,
     contextWindow: 262144,
     supportsImages: false,
     supportsPromptCache: false,
-    inputPrice: 0.1999,
-    outputPrice: 0.8001,
-    description: "Moonshot AI Kimi K2 Instruct 0905 model with 256k context window."
+    inputPrice: 0.15,
+    outputPrice: 1.2,
+    description: "Qwen3 Next 80B (MoE model with 3B active parameters)"
   },
-  "Qwen/Qwen3-235B-A22B-Thinking-2507": {
-    maxTokens: 32768,
+  "qwen.qwen3-coder-480b-a35b-v1:0": {
+    maxTokens: 8192,
     contextWindow: 262144,
     supportsImages: false,
     supportsPromptCache: false,
-    inputPrice: 0.077968332,
-    outputPrice: 0.31202496,
-    description: "Qwen3 235B A22B Thinking 2507 model with 262K context window."
-  },
-  "Qwen/Qwen3-Next-80B-A3B-Instruct": {
-    maxTokens: 32768,
-    contextWindow: 131072,
-    supportsImages: false,
-    supportsPromptCache: false,
-    inputPrice: 0,
-    outputPrice: 0,
-    description: "Fast, stable instruction-tuned model optimized for complex tasks, RAG, and tool use without thinking traces."
-  },
-  "Qwen/Qwen3-Next-80B-A3B-Thinking": {
-    maxTokens: 32768,
-    contextWindow: 131072,
-    supportsImages: false,
-    supportsPromptCache: false,
-    inputPrice: 0,
-    outputPrice: 0,
-    description: "Reasoning-first model with structured thinking traces for multi-step problems, math proofs, and code synthesis."
-  },
-  "Qwen/Qwen3-VL-235B-A22B-Thinking": {
-    maxTokens: 262144,
-    contextWindow: 262144,
-    supportsImages: true,
-    supportsPromptCache: false,
-    inputPrice: 0.16,
-    outputPrice: 0.65,
-    description: "Qwen3\u2011VL\u2011235B\u2011A22B\u2011Thinking is an open\u2011weight MoE vision\u2011language model (235B total, ~22B activated) optimized for deliberate multi\u2011step reasoning with strong text\u2011image\u2011video understanding and long\u2011context capabilities."
+    inputPrice: 0.45,
+    outputPrice: 1.8,
+    description: "Qwen3 Coder 480B (MoE model with 35B active parameters)"
   }
 };
-var chutesDefaultModelInfo = chutesModels[chutesDefaultModelId];
+var BEDROCK_DEFAULT_TEMPERATURE = 0.3;
+var BEDROCK_MAX_TOKENS = 4096;
+var BEDROCK_DEFAULT_CONTEXT = 128e3;
+var AWS_INFERENCE_PROFILE_MAPPING = [
+  // Australia regions (Sydney and Melbourne) → au. inference profile (most specific - 14 chars)
+  ["ap-southeast-2", "au."],
+  ["ap-southeast-4", "au."],
+  // Japan regions (Tokyo and Osaka) → jp. inference profile (13 chars)
+  ["ap-northeast-", "jp."],
+  // US Government Cloud → ug. inference profile (7 chars)
+  ["us-gov-", "ug."],
+  // Americas regions → us. inference profile (3 chars)
+  ["us-", "us."],
+  // Europe regions → eu. inference profile (3 chars)
+  ["eu-", "eu."],
+  // Asia Pacific regions → apac. inference profile (3 chars)
+  ["ap-", "apac."],
+  // Canada regions → ca. inference profile (3 chars)
+  ["ca-", "ca."],
+  // South America regions → sa. inference profile (3 chars)
+  ["sa-", "sa."]
+];
+var BEDROCK_REGIONS = [
+  { value: "us-east-1", label: "us-east-1" },
+  { value: "us-east-2", label: "us-east-2" },
+  { value: "us-west-1", label: "us-west-1" },
+  { value: "us-west-2", label: "us-west-2" },
+  { value: "ap-northeast-1", label: "ap-northeast-1" },
+  { value: "ap-northeast-2", label: "ap-northeast-2" },
+  { value: "ap-northeast-3", label: "ap-northeast-3" },
+  { value: "ap-south-1", label: "ap-south-1" },
+  { value: "ap-south-2", label: "ap-south-2" },
+  { value: "ap-southeast-1", label: "ap-southeast-1" },
+  { value: "ap-southeast-2", label: "ap-southeast-2" },
+  { value: "ap-east-1", label: "ap-east-1" },
+  { value: "eu-central-1", label: "eu-central-1" },
+  { value: "eu-central-2", label: "eu-central-2" },
+  { value: "eu-west-1", label: "eu-west-1" },
+  { value: "eu-west-2", label: "eu-west-2" },
+  { value: "eu-west-3", label: "eu-west-3" },
+  { value: "eu-north-1", label: "eu-north-1" },
+  { value: "eu-south-1", label: "eu-south-1" },
+  { value: "eu-south-2", label: "eu-south-2" },
+  { value: "ca-central-1", label: "ca-central-1" },
+  { value: "sa-east-1", label: "sa-east-1" },
+  { value: "us-gov-east-1", label: "us-gov-east-1" },
+  { value: "us-gov-west-1", label: "us-gov-west-1" }
+].sort((a, b) => a.value.localeCompare(b.value));
+var BEDROCK_1M_CONTEXT_MODEL_IDS = [
+  "anthropic.claude-sonnet-4-20250514-v1:0",
+  "anthropic.claude-sonnet-4-5-20250929-v1:0",
+  "anthropic.claude-opus-4-6-v1"
+];
+var BEDROCK_GLOBAL_INFERENCE_MODEL_IDS = [
+  "anthropic.claude-sonnet-4-20250514-v1:0",
+  "anthropic.claude-sonnet-4-5-20250929-v1:0",
+  "anthropic.claude-haiku-4-5-20251001-v1:0",
+  "anthropic.claude-opus-4-5-20251101-v1:0",
+  "anthropic.claude-opus-4-6-v1"
+];
+var BEDROCK_SERVICE_TIER_MODEL_IDS = [
+  // Amazon Nova models
+  "amazon.nova-lite-v1:0",
+  "amazon.nova-2-lite-v1:0",
+  "amazon.nova-pro-v1:0",
+  "amazon.nova-pro-latency-optimized-v1:0",
+  // DeepSeek models
+  "deepseek.r1-v1:0",
+  // Qwen models
+  "qwen.qwen3-next-80b-a3b",
+  "qwen.qwen3-coder-480b-a35b-v1:0",
+  // OpenAI GPT-OSS models
+  "openai.gpt-oss-20b-1:0",
+  "openai.gpt-oss-120b-1:0"
+];
+var BEDROCK_SERVICE_TIER_PRICING = {
+  STANDARD: 1,
+  // Base price
+  FLEX: 0.5,
+  // 50% discount from standard
+  PRIORITY: 1.75
+  // 75% premium over standard
+};
 
 // src/providers/deepseek.ts
 var deepSeekDefaultModelId = "deepseek-chat";
@@ -1921,109 +1915,6 @@ var deepSeekModels = {
 };
 var DEEP_SEEK_DEFAULT_TEMPERATURE = 0.3;
 
-// src/providers/doubao.ts
-var doubaoDefaultModelId = "doubao-seed-1-6-250615";
-var doubaoModels = {
-  "doubao-seed-1-6-250615": {
-    maxTokens: 32768,
-    contextWindow: 128e3,
-    supportsImages: true,
-    supportsPromptCache: true,
-    inputPrice: 1e-4,
-    // $0.0001 per million tokens (cache miss)
-    outputPrice: 4e-4,
-    // $0.0004 per million tokens
-    cacheWritesPrice: 1e-4,
-    // $0.0001 per million tokens (cache miss)
-    cacheReadsPrice: 2e-5,
-    // $0.00002 per million tokens (cache hit)
-    description: `Doubao Seed 1.6 is a powerful model designed for high-performance tasks with extensive context handling.`
-  },
-  "doubao-seed-1-6-thinking-250715": {
-    maxTokens: 32768,
-    contextWindow: 128e3,
-    supportsImages: true,
-    supportsPromptCache: true,
-    inputPrice: 2e-4,
-    // $0.0002 per million tokens
-    outputPrice: 8e-4,
-    // $0.0008 per million tokens
-    cacheWritesPrice: 2e-4,
-    // $0.0002 per million
-    cacheReadsPrice: 4e-5,
-    // $0.00004 per million tokens (cache hit)
-    description: `Doubao Seed 1.6 Thinking is optimized for reasoning tasks, providing enhanced performance in complex problem-solving scenarios.`
-  },
-  "doubao-seed-1-6-flash-250715": {
-    maxTokens: 32768,
-    contextWindow: 128e3,
-    supportsImages: true,
-    supportsPromptCache: true,
-    inputPrice: 15e-5,
-    // $0.00015 per million tokens
-    outputPrice: 6e-4,
-    // $0.0006 per million tokens
-    cacheWritesPrice: 15e-5,
-    // $0.00015 per million
-    cacheReadsPrice: 3e-5,
-    // $0.00003 per million tokens (cache hit)
-    description: `Doubao Seed 1.6 Flash is tailored for speed and efficiency, making it ideal for applications requiring rapid responses.`
-  }
-};
-var doubaoDefaultModelInfo = doubaoModels[doubaoDefaultModelId];
-var DOUBAO_API_BASE_URL = "https://ark.cn-beijing.volces.com/api/v3";
-var DOUBAO_API_CHAT_PATH = "/chat/completions";
-
-// src/providers/featherless.ts
-var featherlessModels = {
-  "deepseek-ai/DeepSeek-V3-0324": {
-    maxTokens: 4096,
-    contextWindow: 32678,
-    supportsImages: false,
-    supportsPromptCache: false,
-    inputPrice: 0,
-    outputPrice: 0,
-    description: "DeepSeek V3 0324 model."
-  },
-  "deepseek-ai/DeepSeek-R1-0528": {
-    maxTokens: 4096,
-    contextWindow: 32678,
-    supportsImages: false,
-    supportsPromptCache: false,
-    inputPrice: 0,
-    outputPrice: 0,
-    description: "DeepSeek R1 0528 model."
-  },
-  "moonshotai/Kimi-K2-Instruct": {
-    maxTokens: 4096,
-    contextWindow: 32678,
-    supportsImages: false,
-    supportsPromptCache: false,
-    inputPrice: 0,
-    outputPrice: 0,
-    description: "Kimi K2 Instruct model."
-  },
-  "openai/gpt-oss-120b": {
-    maxTokens: 4096,
-    contextWindow: 32678,
-    supportsImages: false,
-    supportsPromptCache: false,
-    inputPrice: 0,
-    outputPrice: 0,
-    description: "GPT-OSS 120B model."
-  },
-  "Qwen/Qwen3-Coder-480B-A35B-Instruct": {
-    maxTokens: 4096,
-    contextWindow: 32678,
-    supportsImages: false,
-    supportsPromptCache: false,
-    inputPrice: 0,
-    outputPrice: 0,
-    description: "Qwen3 Coder 480B A35B Instruct model."
-  }
-};
-var featherlessDefaultModelId = "moonshotai/Kimi-K2-Instruct";
-
 // src/providers/fireworks.ts
 var fireworksDefaultModelId = "accounts/fireworks/models/kimi-k2-instruct-0905";
 var fireworksModels = {
@@ -2439,121 +2330,6 @@ var geminiModels = {
   }
 };
 
-// src/providers/groq.ts
-var groqDefaultModelId = "moonshotai/kimi-k2-instruct-0905";
-var groqModels = {
-  // Models based on API response: https://api.groq.com/openai/v1/models
-  "llama-3.1-8b-instant": {
-    maxTokens: 8192,
-    contextWindow: 131072,
-    supportsImages: false,
-    supportsPromptCache: false,
-    inputPrice: 0.05,
-    outputPrice: 0.08,
-    description: "Meta Llama 3.1 8B Instant model, 128K context."
-  },
-  "llama-3.3-70b-versatile": {
-    maxTokens: 8192,
-    contextWindow: 131072,
-    supportsImages: false,
-    supportsPromptCache: false,
-    inputPrice: 0.59,
-    outputPrice: 0.79,
-    description: "Meta Llama 3.3 70B Versatile model, 128K context."
-  },
-  "meta-llama/llama-4-scout-17b-16e-instruct": {
-    maxTokens: 8192,
-    contextWindow: 131072,
-    supportsImages: false,
-    supportsPromptCache: false,
-    inputPrice: 0.11,
-    outputPrice: 0.34,
-    description: "Meta Llama 4 Scout 17B Instruct model, 128K context."
-  },
-  "qwen/qwen3-32b": {
-    maxTokens: 8192,
-    contextWindow: 131072,
-    supportsImages: false,
-    supportsPromptCache: false,
-    inputPrice: 0.29,
-    outputPrice: 0.59,
-    description: "Alibaba Qwen 3 32B model, 128K context."
-  },
-  "moonshotai/kimi-k2-instruct-0905": {
-    maxTokens: 16384,
-    contextWindow: 262144,
-    supportsImages: false,
-    supportsPromptCache: true,
-    inputPrice: 0.6,
-    outputPrice: 2.5,
-    cacheReadsPrice: 0.15,
-    description: "Kimi K2 model gets a new version update: Agentic coding: more accurate, better generalization across scaffolds. Frontend coding: improved aesthetics and functionalities on web, 3d, and other tasks. Context length: extended from 128k to 256k, providing better long-horizon support."
-  },
-  "openai/gpt-oss-120b": {
-    maxTokens: 32766,
-    contextWindow: 131072,
-    supportsImages: false,
-    supportsPromptCache: false,
-    inputPrice: 0.15,
-    outputPrice: 0.75,
-    description: "GPT-OSS 120B is OpenAI's flagship open source model, built on a Mixture-of-Experts (MoE) architecture with 20 billion parameters and 128 experts."
-  },
-  "openai/gpt-oss-20b": {
-    maxTokens: 32768,
-    contextWindow: 131072,
-    supportsImages: false,
-    supportsPromptCache: false,
-    inputPrice: 0.1,
-    outputPrice: 0.5,
-    description: "GPT-OSS 20B is OpenAI's flagship open source model, built on a Mixture-of-Experts (MoE) architecture with 20 billion parameters and 32 experts."
-  }
-};
-
-// src/providers/huggingface.ts
-var HUGGINGFACE_DEFAULT_MAX_TOKENS = 2048;
-var HUGGINGFACE_MAX_TOKENS_FALLBACK = 8192;
-var HUGGINGFACE_DEFAULT_CONTEXT_WINDOW = 128e3;
-var HUGGINGFACE_SLIDER_STEP = 256;
-var HUGGINGFACE_SLIDER_MIN = 1;
-var HUGGINGFACE_TEMPERATURE_MAX_VALUE = 2;
-var HUGGINGFACE_API_URL = "https://router.huggingface.co/v1/models?collection=roocode";
-var HUGGINGFACE_CACHE_DURATION = 1e3 * 60 * 60;
-
-// src/providers/io-intelligence.ts
-var ioIntelligenceDefaultModelId = "meta-llama/Llama-4-Maverick-17B-128E-Instruct-FP8";
-var ioIntelligenceDefaultBaseUrl = "https://api.intelligence.io.solutions/api/v1";
-var IO_INTELLIGENCE_CACHE_DURATION = 1e3 * 60 * 60;
-var ioIntelligenceModels = {
-  "deepseek-ai/DeepSeek-R1-0528": {
-    maxTokens: 8192,
-    contextWindow: 128e3,
-    supportsImages: false,
-    supportsPromptCache: false,
-    description: "DeepSeek R1 reasoning model"
-  },
-  "meta-llama/Llama-4-Maverick-17B-128E-Instruct-FP8": {
-    maxTokens: 8192,
-    contextWindow: 43e4,
-    supportsImages: true,
-    supportsPromptCache: false,
-    description: "Llama 4 Maverick 17B model"
-  },
-  "Intel/Qwen3-Coder-480B-A35B-Instruct-int4-mixed-ar": {
-    maxTokens: 8192,
-    contextWindow: 106e3,
-    supportsImages: false,
-    supportsPromptCache: false,
-    description: "Qwen3 Coder 480B specialized for coding"
-  },
-  "openai/gpt-oss-120b": {
-    maxTokens: 8192,
-    contextWindow: 131072,
-    supportsImages: false,
-    supportsPromptCache: false,
-    description: "OpenAI GPT-OSS 120B model"
-  }
-};
-
 // src/providers/lite-llm.ts
 var litellmDefaultModelId = "claude-3-7-sonnet-20250219";
 var litellmDefaultModelInfo = {
@@ -3255,7 +3031,7 @@ var openAiModelInfoSaneDefaults = {
   inputPrice: 0,
   outputPrice: 0
 };
-var azureOpenAiDefaultApiVersion = "2024-08-01-preview";
+var azureOpenAiDefaultApiVersion = "2025-04-01-preview";
 var OPENAI_NATIVE_DEFAULT_TEMPERATURE = 0;
 var OPENAI_AZURE_AI_INFERENCE_PATH = "/models/chat/completions";
 
@@ -3645,19 +3421,6 @@ var sambaNovaModels = {
   }
 };
 
-// src/providers/unbound.ts
-var unboundDefaultModelId = "anthropic/claude-sonnet-4-5";
-var unboundDefaultModelInfo = {
-  maxTokens: 8192,
-  contextWindow: 2e5,
-  supportsImages: true,
-  supportsPromptCache: true,
-  inputPrice: 3,
-  outputPrice: 15,
-  cacheWritesPrice: 3.75,
-  cacheReadsPrice: 0.3
-};
-
 // src/providers/vertex.ts
 var vertexDefaultModelId = "claude-sonnet-4-5@20250929";
 var vertexModels = {
@@ -4924,18 +4687,6 @@ var zaiApiLineConfigs = {
   }
 };
 
-// src/providers/deepinfra.ts
-var deepInfraDefaultModelId = "Qwen/Qwen3-Coder-480B-A35B-Instruct-Turbo";
-var deepInfraDefaultModelInfo = {
-  maxTokens: 16384,
-  contextWindow: 262144,
-  supportsImages: false,
-  supportsPromptCache: false,
-  inputPrice: 0.3,
-  outputPrice: 1.2,
-  description: "Qwen 3 Coder 480B A35B Instruct Turbo model, 256K context."
-};
-
 // src/providers/minimax.ts
 var minimaxDefaultModelId = "MiniMax-M2";
 var minimaxModels = {
@@ -4993,18 +4744,10 @@ function getProviderDefaultModelId(provider, options = { isChina: false }) {
       return openRouterDefaultModelId;
     case "requesty":
       return requestyDefaultModelId;
-    case "unbound":
-      return unboundDefaultModelId;
     case "litellm":
       return litellmDefaultModelId;
     case "xai":
       return xaiDefaultModelId;
-    case "groq":
-      return groqDefaultModelId;
-    case "huggingface":
-      return "meta-llama/Llama-3.3-70B-Instruct";
-    case "chutes":
-      return chutesDefaultModelId;
     case "baseten":
       return basetenDefaultModelId;
     case "bedrock":
@@ -5015,8 +4758,6 @@ function getProviderDefaultModelId(provider, options = { isChina: false }) {
       return geminiDefaultModelId;
     case "deepseek":
       return deepSeekDefaultModelId;
-    case "doubao":
-      return doubaoDefaultModelId;
     case "moonshot":
       return moonshotDefaultModelId;
     case "minimax":
@@ -5039,26 +4780,20 @@ function getProviderDefaultModelId(provider, options = { isChina: false }) {
     case "lmstudio":
       return "";
     // LMStudio uses dynamic model selection
-    case "deepinfra":
-      return deepInfraDefaultModelId;
     case "vscode-lm":
       return vscodeLlmDefaultModelId;
-    case "cerebras":
-      return cerebrasDefaultModelId;
     case "sambanova":
       return sambaNovaDefaultModelId;
     case "fireworks":
       return fireworksDefaultModelId;
-    case "featherless":
-      return featherlessDefaultModelId;
-    case "io-intelligence":
-      return ioIntelligenceDefaultModelId;
     case "roo":
       return rooDefaultModelId;
     case "qwen-code":
       return qwenCodeDefaultModelId;
     case "vercel-ai-gateway":
       return vercelAiGatewayDefaultModelId;
+    case "azure":
+      return azureDefaultModelId;
     case "anthropic":
     case "gemini-cli":
     case "fake-ai":
@@ -5069,18 +4804,7 @@ function getProviderDefaultModelId(provider, options = { isChina: false }) {
 
 // src/provider-settings.ts
 var DEFAULT_CONSECUTIVE_MISTAKE_LIMIT = 3;
-var dynamicProviders = [
-  "openrouter",
-  "vercel-ai-gateway",
-  "huggingface",
-  "litellm",
-  "deepinfra",
-  "io-intelligence",
-  "requesty",
-  "unbound",
-  "roo",
-  "chutes"
-];
+var dynamicProviders = ["openrouter", "vercel-ai-gateway", "litellm", "requesty", "roo"];
 var isDynamicProvider = (key) => dynamicProviders.includes(key);
 var localProviders = ["ollama", "lmstudio"];
 var isLocalProvider = (key) => localProviders.includes(key);
@@ -5097,16 +4821,13 @@ var providerNames = [
   ...customProviders,
   ...fauxProviders,
   "anthropic",
+  "azure",
   "bedrock",
   "baseten",
-  "cerebras",
-  "doubao",
   "deepseek",
-  "featherless",
   "fireworks",
   "gemini",
   "gemini-cli",
-  "groq",
   "mistral",
   "moonshot",
   "minimax",
@@ -5121,10 +4842,24 @@ var providerNames = [
 ];
 var providerNamesSchema = z8.enum(providerNames);
 var isProviderName = (key) => typeof key === "string" && providerNames.includes(key);
+var retiredProviderNames = [
+  "cerebras",
+  "chutes",
+  "deepinfra",
+  "doubao",
+  "featherless",
+  "groq",
+  "huggingface",
+  "io-intelligence",
+  "unbound"
+];
+var retiredProviderNamesSchema = z8.enum(retiredProviderNames);
+var isRetiredProvider = (value) => retiredProviderNames.includes(value);
+var providerNamesWithRetiredSchema = z8.union([providerNamesSchema, retiredProviderNamesSchema]);
 var providerSettingsEntrySchema = z8.object({
   id: z8.string(),
   name: z8.string(),
-  apiProvider: providerNamesSchema.optional(),
+  apiProvider: providerNamesWithRetiredSchema.optional(),
   modelId: z8.string().optional()
 });
 var baseProviderSettingsSchema = z8.object({
@@ -5246,15 +4981,6 @@ var deepSeekSchema = apiModelIdProviderModelSchema.extend({
   deepSeekBaseUrl: z8.string().optional(),
   deepSeekApiKey: z8.string().optional()
 });
-var deepInfraSchema = apiModelIdProviderModelSchema.extend({
-  deepInfraBaseUrl: z8.string().optional(),
-  deepInfraApiKey: z8.string().optional(),
-  deepInfraModelId: z8.string().optional()
-});
-var doubaoSchema = apiModelIdProviderModelSchema.extend({
-  doubaoBaseUrl: z8.string().optional(),
-  doubaoApiKey: z8.string().optional()
-});
 var moonshotSchema = apiModelIdProviderModelSchema.extend({
   moonshotBaseUrl: z8.union([z8.literal("https://api.moonshot.ai/v1"), z8.literal("https://api.moonshot.cn/v1")]).optional(),
   moonshotApiKey: z8.string().optional()
@@ -5263,10 +4989,6 @@ var minimaxSchema = apiModelIdProviderModelSchema.extend({
   minimaxBaseUrl: z8.union([z8.literal("https://api.minimax.io/v1"), z8.literal("https://api.minimaxi.com/v1")]).optional(),
   minimaxApiKey: z8.string().optional()
 });
-var unboundSchema = baseProviderSettingsSchema.extend({
-  unboundApiKey: z8.string().optional(),
-  unboundModelId: z8.string().optional()
-});
 var requestySchema = baseProviderSettingsSchema.extend({
   requestyBaseUrl: z8.string().optional(),
   requestyApiKey: z8.string().optional(),
@@ -5278,26 +5000,12 @@ var fakeAiSchema = baseProviderSettingsSchema.extend({
 var xaiSchema = apiModelIdProviderModelSchema.extend({
   xaiApiKey: z8.string().optional()
 });
-var groqSchema = apiModelIdProviderModelSchema.extend({
-  groqApiKey: z8.string().optional()
-});
-var huggingFaceSchema = baseProviderSettingsSchema.extend({
-  huggingFaceApiKey: z8.string().optional(),
-  huggingFaceModelId: z8.string().optional(),
-  huggingFaceInferenceProvider: z8.string().optional()
-});
-var chutesSchema = apiModelIdProviderModelSchema.extend({
-  chutesApiKey: z8.string().optional()
-});
 var litellmSchema = baseProviderSettingsSchema.extend({
   litellmBaseUrl: z8.string().optional(),
   litellmApiKey: z8.string().optional(),
   litellmModelId: z8.string().optional(),
   litellmUsePromptCache: z8.boolean().optional()
 });
-var cerebrasSchema = apiModelIdProviderModelSchema.extend({
-  cerebrasApiKey: z8.string().optional()
-});
 var sambaNovaSchema = apiModelIdProviderModelSchema.extend({
   sambaNovaApiKey: z8.string().optional()
 });
@@ -5309,13 +5017,6 @@ var zaiSchema = apiModelIdProviderModelSchema.extend({
 var fireworksSchema = apiModelIdProviderModelSchema.extend({
   fireworksApiKey: z8.string().optional()
 });
-var featherlessSchema = apiModelIdProviderModelSchema.extend({
-  featherlessApiKey: z8.string().optional()
-});
-var ioIntelligenceSchema = apiModelIdProviderModelSchema.extend({
-  ioIntelligenceModelId: z8.string().optional(),
-  ioIntelligenceApiKey: z8.string().optional()
-});
 var qwenCodeSchema = apiModelIdProviderModelSchema.extend({
   qwenCodeOauthPath: z8.string().optional()
 });
@@ -5330,11 +5031,18 @@ var vercelAiGatewaySchema = baseProviderSettingsSchema.extend({
 var basetenSchema = apiModelIdProviderModelSchema.extend({
   basetenApiKey: z8.string().optional()
 });
+var azureSchema = apiModelIdProviderModelSchema.extend({
+  azureApiKey: z8.string().optional(),
+  azureResourceName: z8.string().optional(),
+  azureDeploymentName: z8.string().optional(),
+  azureApiVersion: z8.string().optional()
+});
 var defaultSchema = z8.object({
   apiProvider: z8.undefined()
 });
 var providerSettingsSchemaDiscriminated = z8.discriminatedUnion("apiProvider", [
   anthropicSchema.merge(z8.object({ apiProvider: z8.literal("anthropic") })),
+  azureSchema.merge(z8.object({ apiProvider: z8.literal("azure") })),
   openRouterSchema.merge(z8.object({ apiProvider: z8.literal("openrouter") })),
   bedrockSchema.merge(z8.object({ apiProvider: z8.literal("bedrock") })),
   vertexSchema.merge(z8.object({ apiProvider: z8.literal("vertex") })),
@@ -5348,33 +5056,25 @@ var providerSettingsSchemaDiscriminated = z8.discriminatedUnion("apiProvider", [
   openAiNativeSchema.merge(z8.object({ apiProvider: z8.literal("openai-native") })),
   mistralSchema.merge(z8.object({ apiProvider: z8.literal("mistral") })),
   deepSeekSchema.merge(z8.object({ apiProvider: z8.literal("deepseek") })),
-  deepInfraSchema.merge(z8.object({ apiProvider: z8.literal("deepinfra") })),
-  doubaoSchema.merge(z8.object({ apiProvider: z8.literal("doubao") })),
   moonshotSchema.merge(z8.object({ apiProvider: z8.literal("moonshot") })),
   minimaxSchema.merge(z8.object({ apiProvider: z8.literal("minimax") })),
-  unboundSchema.merge(z8.object({ apiProvider: z8.literal("unbound") })),
   requestySchema.merge(z8.object({ apiProvider: z8.literal("requesty") })),
   fakeAiSchema.merge(z8.object({ apiProvider: z8.literal("fake-ai") })),
   xaiSchema.merge(z8.object({ apiProvider: z8.literal("xai") })),
-  groqSchema.merge(z8.object({ apiProvider: z8.literal("groq") })),
   basetenSchema.merge(z8.object({ apiProvider: z8.literal("baseten") })),
-  huggingFaceSchema.merge(z8.object({ apiProvider: z8.literal("huggingface") })),
-  chutesSchema.merge(z8.object({ apiProvider: z8.literal("chutes") })),
   litellmSchema.merge(z8.object({ apiProvider: z8.literal("litellm") })),
-  cerebrasSchema.merge(z8.object({ apiProvider: z8.literal("cerebras") })),
   sambaNovaSchema.merge(z8.object({ apiProvider: z8.literal("sambanova") })),
   zaiSchema.merge(z8.object({ apiProvider: z8.literal("zai") })),
   fireworksSchema.merge(z8.object({ apiProvider: z8.literal("fireworks") })),
-  featherlessSchema.merge(z8.object({ apiProvider: z8.literal("featherless") })),
-  ioIntelligenceSchema.merge(z8.object({ apiProvider: z8.literal("io-intelligence") })),
   qwenCodeSchema.merge(z8.object({ apiProvider: z8.literal("qwen-code") })),
   rooSchema.merge(z8.object({ apiProvider: z8.literal("roo") })),
   vercelAiGatewaySchema.merge(z8.object({ apiProvider: z8.literal("vercel-ai-gateway") })),
   defaultSchema
 ]);
 var providerSettingsSchema = z8.object({
-  apiProvider: providerNamesSchema.optional(),
+  apiProvider: providerNamesWithRetiredSchema.optional(),
   ...anthropicSchema.shape,
+  ...azureSchema.shape,
   ...openRouterSchema.shape,
   ...bedrockSchema.shape,
   ...vertexSchema.shape,
@@ -5388,25 +5088,16 @@ var providerSettingsSchema = z8.object({
   ...openAiNativeSchema.shape,
   ...mistralSchema.shape,
   ...deepSeekSchema.shape,
-  ...deepInfraSchema.shape,
-  ...doubaoSchema.shape,
   ...moonshotSchema.shape,
   ...minimaxSchema.shape,
-  ...unboundSchema.shape,
   ...requestySchema.shape,
   ...fakeAiSchema.shape,
   ...xaiSchema.shape,
-  ...groqSchema.shape,
   ...basetenSchema.shape,
-  ...huggingFaceSchema.shape,
-  ...chutesSchema.shape,
   ...litellmSchema.shape,
-  ...cerebrasSchema.shape,
   ...sambaNovaSchema.shape,
   ...zaiSchema.shape,
   ...fireworksSchema.shape,
-  ...featherlessSchema.shape,
-  ...ioIntelligenceSchema.shape,
   ...qwenCodeSchema.shape,
   ...rooSchema.shape,
   ...vercelAiGatewaySchema.shape,
@@ -5424,13 +5115,9 @@ var modelIdKeys = [
   "ollamaModelId",
   "lmStudioModelId",
   "lmStudioDraftModelId",
-  "unboundModelId",
   "requestyModelId",
   "litellmModelId",
-  "huggingFaceModelId",
-  "ioIntelligenceModelId",
-  "vercelAiGatewayModelId",
-  "deepInfraModelId"
+  "vercelAiGatewayModelId"
 ];
 var getModelId = (settings) => {
   const modelIdKey = modelIdKeys.find((key) => settings[key]);
@@ -5439,6 +5126,7 @@ var getModelId = (settings) => {
 var isTypicalProvider = (key) => isProviderName(key) && !isInternalProvider(key) && !isCustomProvider(key) && !isFauxProvider(key);
 var modelIdKeysByProvider = {
   anthropic: "apiModelId",
+  azure: "apiModelId",
   openrouter: "openRouterModelId",
   bedrock: "apiModelId",
   vertex: "apiModelId",
@@ -5452,23 +5140,14 @@ var modelIdKeysByProvider = {
   moonshot: "apiModelId",
   minimax: "apiModelId",
   deepseek: "apiModelId",
-  deepinfra: "deepInfraModelId",
-  doubao: "apiModelId",
   "qwen-code": "apiModelId",
-  unbound: "unboundModelId",
   requesty: "requestyModelId",
   xai: "apiModelId",
-  groq: "apiModelId",
   baseten: "apiModelId",
-  chutes: "apiModelId",
   litellm: "litellmModelId",
-  huggingface: "huggingFaceModelId",
-  cerebras: "apiModelId",
   sambanova: "apiModelId",
   zai: "apiModelId",
   fireworks: "apiModelId",
-  featherless: "apiModelId",
-  "io-intelligence": "ioIntelligenceModelId",
   roo: "apiModelId",
   "vercel-ai-gateway": "vercelAiGatewayModelId"
 };
@@ -5491,27 +5170,22 @@ var MODELS_BY_PROVIDER = {
     label: "Anthropic",
     models: Object.keys(anthropicModels)
   },
+  azure: {
+    id: "azure",
+    label: "Azure AI Foundry",
+    // Azure uses deployment names configured by the user (not a fixed upstream model ID list)
+    models: []
+  },
   bedrock: {
     id: "bedrock",
     label: "Amazon Bedrock",
     models: Object.keys(bedrockModels)
   },
-  cerebras: {
-    id: "cerebras",
-    label: "Cerebras",
-    models: Object.keys(cerebrasModels)
-  },
   deepseek: {
     id: "deepseek",
     label: "DeepSeek",
     models: Object.keys(deepSeekModels)
   },
-  doubao: { id: "doubao", label: "Doubao", models: Object.keys(doubaoModels) },
-  featherless: {
-    id: "featherless",
-    label: "Featherless",
-    models: Object.keys(featherlessModels)
-  },
   fireworks: {
     id: "fireworks",
     label: "Fireworks",
@@ -5522,12 +5196,6 @@ var MODELS_BY_PROVIDER = {
     label: "Google Gemini",
     models: Object.keys(geminiModels)
   },
-  groq: { id: "groq", label: "Groq", models: Object.keys(groqModels) },
-  "io-intelligence": {
-    id: "io-intelligence",
-    label: "IO Intelligence",
-    models: Object.keys(ioIntelligenceModels)
-  },
   mistral: {
     id: "mistral",
     label: "Mistral",
@@ -5574,14 +5242,10 @@ 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.
-  huggingface: { id: "huggingface", label: "Hugging Face", models: [] },
   litellm: { id: "litellm", label: "LiteLLM", models: [] },
   openrouter: { id: "openrouter", label: "OpenRouter", models: [] },
   requesty: { id: "requesty", label: "Requesty", models: [] },
-  unbound: { id: "unbound", label: "Unbound", models: [] },
-  deepinfra: { id: "deepinfra", label: "DeepInfra", models: [] },
   "vercel-ai-gateway": { id: "vercel-ai-gateway", label: "Vercel AI Gateway", models: [] },
-  chutes: { id: "chutes", label: "Chutes AI", models: [] },
   // Local providers; models discovered from localhost endpoints.
   lmstudio: { id: "lmstudio", label: "LM Studio", models: [] },
   ollama: { id: "ollama", label: "Ollama", models: [] }
@@ -6244,19 +5908,13 @@ var SECRET_STATE_KEYS = [
   "ollamaApiKey",
   "geminiApiKey",
   "openAiNativeApiKey",
-  "cerebrasApiKey",
   "deepSeekApiKey",
-  "doubaoApiKey",
   "moonshotApiKey",
   "mistralApiKey",
   "minimaxApiKey",
-  "unboundApiKey",
   "requestyApiKey",
   "xaiApiKey",
-  "groqApiKey",
-  "chutesApiKey",
   "litellmApiKey",
-  "deepInfraApiKey",
   "codeIndexOpenAiKey",
   "codeIndexQdrantApiKey",
   "codebaseIndexOpenAiCompatibleApiKey",
@@ -6264,14 +5922,12 @@ var SECRET_STATE_KEYS = [
   "codebaseIndexMistralApiKey",
   "codebaseIndexVercelAiGatewayApiKey",
   "codebaseIndexOpenRouterApiKey",
-  "huggingFaceApiKey",
   "sambaNovaApiKey",
   "zaiApiKey",
   "fireworksApiKey",
-  "featherlessApiKey",
-  "ioIntelligenceApiKey",
   "vercelAiGatewayApiKey",
-  "basetenApiKey"
+  "basetenApiKey",
+  "azureApiKey"
 ];
 var GLOBAL_SECRET_KEYS = [
   "openRouterImageApiKey"
@@ -6875,6 +6531,9 @@ var TaskCommandName = /* @__PURE__ */ ((TaskCommandName2) => {
   TaskCommandName2["CloseTask"] = "CloseTask";
   TaskCommandName2["ResumeTask"] = "ResumeTask";
   TaskCommandName2["SendMessage"] = "SendMessage";
+  TaskCommandName2["GetCommands"] = "GetCommands";
+  TaskCommandName2["GetModes"] = "GetModes";
+  TaskCommandName2["GetModels"] = "GetModels";
   return TaskCommandName2;
 })(TaskCommandName || {});
 var taskCommandSchema = z19.discriminatedUnion("commandName", [
@@ -6903,6 +6562,15 @@ var taskCommandSchema = z19.discriminatedUnion("commandName", [
       text: z19.string().optional(),
       images: z19.array(z19.string()).optional()
     })
+  }),
+  z19.object({
+    commandName: z19.literal("GetCommands" /* GetCommands */)
+  }),
+  z19.object({
+    commandName: z19.literal("GetModes" /* GetModes */)
+  }),
+  z19.object({
+    commandName: z19.literal("GetModels" /* GetModels */)
   })
 ]);
 var ipcMessageSchema = z19.discriminatedUnion("type", [
@@ -7089,8 +6757,6 @@ export {
   DEFAULT_MODES,
   DEFAULT_TERMINAL_OUTPUT_PREVIEW_SIZE,
   DEFAULT_WRITE_DELAY_MS,
-  DOUBAO_API_BASE_URL,
-  DOUBAO_API_CHAT_PATH,
   EVALS_SETTINGS,
   EVALS_TIMEOUT,
   EXPECTED_API_ERROR_CODES,
@@ -7101,18 +6767,9 @@ export {
   GLOBAL_SETTINGS_KEYS,
   GLOBAL_STATE_KEYS,
   HEARTBEAT_INTERVAL_MS,
-  HUGGINGFACE_API_URL,
-  HUGGINGFACE_CACHE_DURATION,
-  HUGGINGFACE_DEFAULT_CONTEXT_WINDOW,
-  HUGGINGFACE_DEFAULT_MAX_TOKENS,
-  HUGGINGFACE_MAX_TOKENS_FALLBACK,
-  HUGGINGFACE_SLIDER_MIN,
-  HUGGINGFACE_SLIDER_STEP,
-  HUGGINGFACE_TEMPERATURE_MAX_VALUE,
   IMAGE_GENERATION_MODELS,
   IMAGE_GENERATION_MODEL_IDS,
   INSTANCE_TTL_SECONDS,
-  IO_INTELLIGENCE_CACHE_DURATION,
   IpcMessageType,
   IpcOrigin,
   LMSTUDIO_DEFAULT_TEMPERATURE,
@@ -7160,6 +6817,9 @@ export {
   anthropicDefaultModelId,
   anthropicModels,
   appPropertiesSchema,
+  azureDefaultModelId,
+  azureDefaultModelInfo,
+  azureModels,
   azureOpenAiDefaultApiVersion,
   basetenDefaultModelId,
   basetenModels,
@@ -7167,13 +6827,8 @@ export {
   bedrockDefaultPromptRouterModelId,
   bedrockModels,
   browserActions,
-  cerebrasDefaultModelId,
-  cerebrasModels,
   checkoutDiffPayloadSchema,
   checkoutRestorePayloadSchema,
-  chutesDefaultModelId,
-  chutesDefaultModelInfo,
-  chutesModels,
   clineAskSchema,
   clineAsks,
   clineMessageSchema,
@@ -7193,15 +6848,10 @@ export {
   customModesSettingsSchema,
   customProviders,
   customSupportPromptsSchema,
-  deepInfraDefaultModelId,
-  deepInfraDefaultModelInfo,
   deepSeekDefaultModelId,
   deepSeekModels,
   defineCustomTool,
   discriminatedProviderSettingsWithIdSchema,
-  doubaoDefaultModelId,
-  doubaoDefaultModelInfo,
-  doubaoModels,
   dynamicAppPropertiesSchema,
   dynamicProviders,
   experimentIds,
@@ -7214,8 +6864,6 @@ export {
   extractConsecutiveMistakeErrorProperties,
   extractMessageFromJsonPayload,
   fauxProviders,
-  featherlessDefaultModelId,
-  featherlessModels,
   fireworksDefaultModelId,
   fireworksModels,
   followUpDataSchema,
@@ -7229,8 +6877,6 @@ export {
   getProviderDefaultModelId,
   gitPropertiesSchema,
   globalSettingsSchema,
-  groqDefaultModelId,
-  groqModels,
   groupEntrySchema,
   groupOptionsSchema,
   historyItemSchema,
@@ -7241,9 +6887,6 @@ export {
   internalProviders,
   internationalZAiDefaultModelId,
   internationalZAiModels,
-  ioIntelligenceDefaultBaseUrl,
-  ioIntelligenceDefaultModelId,
-  ioIntelligenceModels,
   ipcMessageSchema,
   isApiProviderError,
   isConsecutiveMistakeError,
@@ -7262,6 +6905,7 @@ export {
   isNonBlockingAsk,
   isProviderName,
   isResumableAsk,
+  isRetiredProvider,
   isSecretStateKey,
   isTypicalProvider,
   lMStudioDefaultModelId,
@@ -7312,6 +6956,7 @@ export {
   promptComponentSchema,
   providerNames,
   providerNamesSchema,
+  providerNamesWithRetiredSchema,
   providerSettingsEntrySchema,
   providerSettingsSchema,
   providerSettingsSchemaDiscriminated,
@@ -7329,6 +6974,8 @@ export {
   requestyDefaultModelId,
   requestyDefaultModelInfo,
   resumableAsks,
+  retiredProviderNames,
+  retiredProviderNamesSchema,
   rooCodeEventsSchema,
   rooCodeSettingsSchema,
   rooCodeTelemetryEventSchema,
@@ -7361,8 +7008,6 @@ export {
   toolNamesSchema,
   toolProgressStatusSchema,
   toolUsageSchema,
-  unboundDefaultModelId,
-  unboundDefaultModelInfo,
   usageStatsSchema,
   userFeaturesSchema,
   userSettingsConfigSchema,