Add GPT-5.1 models and clean up reasoning effort logic

packages/types/src/model.ts

@@ -18,6 +18,22 @@ export const reasoningEffortWithMinimalSchema = z.union([reasoningEffortsSchema,
 
 export type ReasoningEffortWithMinimal = z.infer<typeof reasoningEffortWithMinimalSchema>
 
+/**
+ * Extended Reasoning Effort (includes "none" and "minimal")
+ * Note: "disable" is a UI/control value, not a value sent as effort
+ */
+export const reasoningEffortsExtended = ["none", "minimal", "low", "medium", "high"] as const
+
+export const reasoningEffortExtendedSchema = z.enum(reasoningEffortsExtended)
+
+export type ReasoningEffortExtended = z.infer<typeof reasoningEffortExtendedSchema>
+
+/**
+ * Reasoning Effort user setting (includes "disable")
+ */
+export const reasoningEffortSettingValues = ["disable", "none", "minimal", "low", "medium", "high"] as const
+export const reasoningEffortSettingSchema = z.enum(reasoningEffortSettingValues)
+
 /**
  * Verbosity
  */
@@ -67,7 +83,9 @@ export const modelInfoSchema = z.object({
 	supportsTemperature: z.boolean().optional(),
 	defaultTemperature: z.number().optional(),
 	requiredReasoningBudget: z.boolean().optional(),
-	supportsReasoningEffort: z.boolean().optional(),
+	supportsReasoningEffort: z
+		.union([z.boolean(), z.array(z.enum(["disable", "none", "minimal", "low", "medium", "high"]))])
+		.optional(),
 	requiredReasoningEffort: z.boolean().optional(),
 	preserveReasoning: z.boolean().optional(),
 	supportedParameters: z.array(modelParametersSchema).optional(),
@@ -76,7 +94,8 @@ export const modelInfoSchema = z.object({
 	cacheWritesPrice: z.number().optional(),
 	cacheReadsPrice: z.number().optional(),
 	description: z.string().optional(),
-	reasoningEffort: reasoningEffortsSchema.optional(),
+	// Default effort value for models that support reasoning effort
+	reasoningEffort: reasoningEffortExtendedSchema.optional(),
 	minTokensPerCachePoint: z.number().optional(),
 	maxCachePoints: z.number().optional(),
 	cachableFields: z.array(z.string()).optional(),

packages/types/src/provider-settings.ts

@@ -1,6 +1,6 @@
 import { z } from "zod"
 
-import { modelInfoSchema, reasoningEffortWithMinimalSchema, verbosityLevelsSchema, serviceTierSchema } from "./model.js"
+import { modelInfoSchema, reasoningEffortSettingSchema, verbosityLevelsSchema, serviceTierSchema } from "./model.js"
 import { codebaseIndexProviderSchema } from "./codebase-index.js"
 import {
 	anthropicModels,
@@ -176,7 +176,7 @@ const baseProviderSettingsSchema = z.object({
 
 	// Model reasoning.
 	enableReasoningEffort: z.boolean().optional(),
-	reasoningEffort: reasoningEffortWithMinimalSchema.optional(),
+	reasoningEffort: reasoningEffortSettingSchema.optional(),
 	modelMaxTokens: z.number().optional(),
 	modelMaxThinkingTokens: z.number().optional(),
 

packages/types/src/providers/openai.ts

@@ -3,85 +3,128 @@ import type { ModelInfo } from "../model.js"
 // https://openai.com/api/pricing/
 export type OpenAiNativeModelId = keyof typeof openAiNativeModels
 
-export const openAiNativeDefaultModelId: OpenAiNativeModelId = "gpt-5-2025-08-07"
+export const openAiNativeDefaultModelId: OpenAiNativeModelId = "gpt-5.1"
 
 export const openAiNativeModels = {
-	"gpt-5-chat-latest": {
+	"gpt-5.1": {
 		maxTokens: 128000,
 		contextWindow: 400000,
 		supportsImages: true,
 		supportsPromptCache: true,
-		supportsReasoningEffort: false,
+		supportsReasoningEffort: ["none", "low", "medium", "high"],
+		reasoningEffort: "medium",
 		inputPrice: 1.25,
 		outputPrice: 10.0,
-		cacheReadsPrice: 0.13,
-		description: "GPT-5 Chat Latest: Optimized for conversational AI and non-reasoning tasks",
+		cacheReadsPrice: 0.125,
+		supportsVerbosity: true,
+		supportsTemperature: false,
+		tiers: [
+			{ name: "flex", contextWindow: 400000, inputPrice: 0.625, outputPrice: 5.0, cacheReadsPrice: 0.0625 },
+			{ name: "priority", contextWindow: 400000, inputPrice: 2.5, outputPrice: 20.0, cacheReadsPrice: 0.25 },
+		],
+		description: "GPT-5.1: The best model for coding and agentic tasks across domains",
 	},
-	"gpt-5-2025-08-07": {
+	"gpt-5.1-codex": {
 		maxTokens: 128000,
 		contextWindow: 400000,
 		supportsImages: true,
 		supportsPromptCache: true,
-		supportsReasoningEffort: true,
+		supportsReasoningEffort: ["low", "medium", "high"],
 		reasoningEffort: "medium",
 		inputPrice: 1.25,
 		outputPrice: 10.0,
-		cacheReadsPrice: 0.13,
-		description: "GPT-5: The best model for coding and agentic tasks across domains",
-		// supportsVerbosity is a new capability; ensure ModelInfo includes it
+		cacheReadsPrice: 0.125,
+		supportsTemperature: false,
+		tiers: [{ name: "priority", contextWindow: 400000, inputPrice: 2.5, outputPrice: 20.0, cacheReadsPrice: 0.25 }],
+		description: "GPT-5.1 Codex: A version of GPT-5.1 optimized for agentic coding in Codex",
+	},
+	"gpt-5.1-codex-mini": {
+		maxTokens: 128000,
+		contextWindow: 400000,
+		supportsImages: true,
+		supportsPromptCache: true,
+		supportsReasoningEffort: ["low", "medium", "high"],
+		reasoningEffort: "medium",
+		inputPrice: 0.25,
+		outputPrice: 2.0,
+		cacheReadsPrice: 0.025,
+		supportsTemperature: false,
+		description: "GPT-5.1 Codex mini: A version of GPT-5.1 optimized for agentic coding in Codex",
+	},
+	"gpt-5": {
+		maxTokens: 128000,
+		contextWindow: 400000,
+		supportsImages: true,
+		supportsPromptCache: true,
+		supportsReasoningEffort: ["minimal", "low", "medium", "high"],
+		reasoningEffort: "medium",
+		inputPrice: 1.25,
+		outputPrice: 10.0,
+		cacheReadsPrice: 0.125,
 		supportsVerbosity: true,
 		supportsTemperature: false,
 		tiers: [
 			{ name: "flex", contextWindow: 400000, inputPrice: 0.625, outputPrice: 5.0, cacheReadsPrice: 0.0625 },
 			{ name: "priority", contextWindow: 400000, inputPrice: 2.5, outputPrice: 20.0, cacheReadsPrice: 0.25 },
 		],
+		description: "GPT-5: The best model for coding and agentic tasks across domains",
 	},
-	"gpt-5-mini-2025-08-07": {
+	"gpt-5-mini": {
 		maxTokens: 128000,
 		contextWindow: 400000,
 		supportsImages: true,
 		supportsPromptCache: true,
-		supportsReasoningEffort: true,
+		supportsReasoningEffort: ["minimal", "low", "medium", "high"],
 		reasoningEffort: "medium",
 		inputPrice: 0.25,
 		outputPrice: 2.0,
-		cacheReadsPrice: 0.03,
-		description: "GPT-5 Mini: A faster, more cost-efficient version of GPT-5 for well-defined tasks",
+		cacheReadsPrice: 0.025,
 		supportsVerbosity: true,
 		supportsTemperature: false,
 		tiers: [
 			{ name: "flex", contextWindow: 400000, inputPrice: 0.125, outputPrice: 1.0, cacheReadsPrice: 0.0125 },
 			{ name: "priority", contextWindow: 400000, inputPrice: 0.45, outputPrice: 3.6, cacheReadsPrice: 0.045 },
 		],
+		description: "GPT-5 Mini: A faster, more cost-efficient version of GPT-5 for well-defined tasks",
 	},
-	"gpt-5-nano-2025-08-07": {
+	"gpt-5-codex": {
 		maxTokens: 128000,
 		contextWindow: 400000,
 		supportsImages: true,
 		supportsPromptCache: true,
-		supportsReasoningEffort: true,
+		supportsReasoningEffort: ["low", "medium", "high"],
+		reasoningEffort: "medium",
+		inputPrice: 1.25,
+		outputPrice: 10.0,
+		cacheReadsPrice: 0.125,
+		supportsTemperature: false,
+		tiers: [{ name: "priority", contextWindow: 400000, inputPrice: 2.5, outputPrice: 20.0, cacheReadsPrice: 0.25 }],
+		description: "GPT-5-Codex: A version of GPT-5 optimized for agentic coding in Codex",
+	},
+	"gpt-5-nano": {
+		maxTokens: 128000,
+		contextWindow: 400000,
+		supportsImages: true,
+		supportsPromptCache: true,
+		supportsReasoningEffort: ["minimal", "low", "medium", "high"],
 		reasoningEffort: "medium",
 		inputPrice: 0.05,
 		outputPrice: 0.4,
-		cacheReadsPrice: 0.01,
-		description: "GPT-5 Nano: Fastest, most cost-efficient version of GPT-5",
+		cacheReadsPrice: 0.005,
 		supportsVerbosity: true,
 		supportsTemperature: false,
 		tiers: [{ name: "flex", contextWindow: 400000, inputPrice: 0.025, outputPrice: 0.2, cacheReadsPrice: 0.0025 }],
+		description: "GPT-5 Nano: Fastest, most cost-efficient version of GPT-5",
 	},
-	"gpt-5-codex": {
+	"gpt-5-chat-latest": {
 		maxTokens: 128000,
 		contextWindow: 400000,
 		supportsImages: true,
 		supportsPromptCache: true,
-		supportsReasoningEffort: true,
-		reasoningEffort: "medium",
 		inputPrice: 1.25,
 		outputPrice: 10.0,
-		cacheReadsPrice: 0.13,
-		description: "GPT-5-Codex: A version of GPT-5 optimized for agentic coding in Codex",
-		supportsVerbosity: true,
-		supportsTemperature: false,
+		cacheReadsPrice: 0.125,
+		description: "GPT-5 Chat: Optimized for conversational AI and non-reasoning tasks",
 	},
 	"gpt-4.1": {
 		maxTokens: 32_768,
@@ -130,7 +173,7 @@ export const openAiNativeModels = {
 		inputPrice: 2.0,
 		outputPrice: 8.0,
 		cacheReadsPrice: 0.5,
-		supportsReasoningEffort: true,
+		supportsReasoningEffort: ["low", "medium", "high"],
 		reasoningEffort: "medium",
 		supportsTemperature: false,
 		tiers: [
@@ -168,7 +211,7 @@ export const openAiNativeModels = {
 		inputPrice: 1.1,
 		outputPrice: 4.4,
 		cacheReadsPrice: 0.275,
-		supportsReasoningEffort: true,
+		supportsReasoningEffort: ["low", "medium", "high"],
 		reasoningEffort: "medium",
 		supportsTemperature: false,
 		tiers: [
@@ -206,7 +249,7 @@ export const openAiNativeModels = {
 		inputPrice: 1.1,
 		outputPrice: 4.4,
 		cacheReadsPrice: 0.55,
-		supportsReasoningEffort: true,
+		supportsReasoningEffort: ["low", "medium", "high"],
 		reasoningEffort: "medium",
 		supportsTemperature: false,
 	},
@@ -295,11 +338,63 @@ export const openAiNativeModels = {
 		supportsPromptCache: false,
 		inputPrice: 1.5,
 		outputPrice: 6,
-		cacheReadsPrice: 0,
+		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. Trained with reinforcement learning to generate human-style code, adhere to instructions, and iteratively run tests.",
 	},
+	// Dated clones (snapshots) preserved for backward compatibility
+	"gpt-5-2025-08-07": {
+		maxTokens: 128000,
+		contextWindow: 400000,
+		supportsImages: true,
+		supportsPromptCache: true,
+		supportsReasoningEffort: ["minimal", "low", "medium", "high"],
+		reasoningEffort: "medium",
+		inputPrice: 1.25,
+		outputPrice: 10.0,
+		cacheReadsPrice: 0.125,
+		supportsVerbosity: true,
+		supportsTemperature: false,
+		tiers: [
+			{ name: "flex", contextWindow: 400000, inputPrice: 0.625, outputPrice: 5.0, cacheReadsPrice: 0.0625 },
+			{ name: "priority", contextWindow: 400000, inputPrice: 2.5, outputPrice: 20.0, cacheReadsPrice: 0.25 },
+		],
+		description: "GPT-5: The best model for coding and agentic tasks across domains",
+	},
+	"gpt-5-mini-2025-08-07": {
+		maxTokens: 128000,
+		contextWindow: 400000,
+		supportsImages: true,
+		supportsPromptCache: true,
+		supportsReasoningEffort: ["minimal", "low", "medium", "high"],
+		reasoningEffort: "medium",
+		inputPrice: 0.25,
+		outputPrice: 2.0,
+		cacheReadsPrice: 0.025,
+		supportsVerbosity: true,
+		supportsTemperature: false,
+		tiers: [
+			{ name: "flex", contextWindow: 400000, inputPrice: 0.125, outputPrice: 1.0, cacheReadsPrice: 0.0125 },
+			{ name: "priority", contextWindow: 400000, inputPrice: 0.45, outputPrice: 3.6, cacheReadsPrice: 0.045 },
+		],
+		description: "GPT-5 Mini: A faster, more cost-efficient version of GPT-5 for well-defined tasks",
+	},
+	"gpt-5-nano-2025-08-07": {
+		maxTokens: 128000,
+		contextWindow: 400000,
+		supportsImages: true,
+		supportsPromptCache: true,
+		supportsReasoningEffort: ["minimal", "low", "medium", "high"],
+		reasoningEffort: "medium",
+		inputPrice: 0.05,
+		outputPrice: 0.4,
+		cacheReadsPrice: 0.005,
+		supportsVerbosity: true,
+		supportsTemperature: false,
+		tiers: [{ name: "flex", contextWindow: 400000, inputPrice: 0.025, outputPrice: 0.2, cacheReadsPrice: 0.0025 }],
+		description: "GPT-5 Nano: Fastest, most cost-efficient version of GPT-5",
+	},
 } as const satisfies Record<string, ModelInfo>
 
 export const openAiModelInfoSaneDefaults: ModelInfo = {
@@ -316,6 +411,5 @@ export const openAiModelInfoSaneDefaults: ModelInfo = {
 export const azureOpenAiDefaultApiVersion = "2024-08-01-preview"
 
 export const OPENAI_NATIVE_DEFAULT_TEMPERATURE = 0
-export const GPT5_DEFAULT_TEMPERATURE = 1.0
 
 export const OPENAI_AZURE_AI_INFERENCE_PATH = "/models/chat/completions"