chore: re-enable the prefer-const ESLint rule

prefer-const was disabled in src/eslint.config.mjs under a "TODO: re-enable" comment. Re-enabled with { destructuring: "all" } so it only flags a destructuring declaration when every binding can be const. Most violations were auto-fixed (let -> const); five declare-then-assign cases were merged by hand into a single const declaration. No behavior change — tsc and the tests for the touched modules pass.

Author: 0xMink

src/api/providers/anthropic-vertex.ts

@@ -68,7 +68,7 @@ export class AnthropicVertexHandler extends BaseProvider implements SingleComple
 		messages: Anthropic.Messages.MessageParam[],
 		metadata?: ApiHandlerCreateMessageMetadata,
 	): ApiStream {
-		let { id, info, temperature, maxTokens, reasoning: thinking, betas } = this.getModel()
+		const { id, info, temperature, maxTokens, reasoning: thinking, betas } = this.getModel()
 
 		const { supportsPromptCache } = info
 
@@ -207,7 +207,7 @@ export class AnthropicVertexHandler extends BaseProvider implements SingleComple
 
 	getModel() {
 		const modelId = this.options.apiModelId
-		let id = modelId && modelId in vertexModels ? (modelId as VertexModelId) : vertexDefaultModelId
+		const id = modelId && modelId in vertexModels ? (modelId as VertexModelId) : vertexDefaultModelId
 		let info: ModelInfo = vertexModels[id]
 
 		// Check if 1M context beta should be enabled for supported models
@@ -261,7 +261,7 @@ export class AnthropicVertexHandler extends BaseProvider implements SingleComple
 
 	async completePrompt(prompt: string) {
 		try {
-			let {
+			const {
 				id,
 				info: { supportsPromptCache },
 				temperature,

src/api/providers/anthropic.ts

@@ -54,7 +54,7 @@ export class AnthropicHandler extends BaseProvider implements SingleCompletionHa
 	): ApiStream {
 		let stream: AnthropicStream<Anthropic.Messages.RawMessageStreamEvent>
 		const cacheControl: CacheControlEphemeral = { type: "ephemeral" }
-		let {
+		const {
 			id: modelId,
 			betas = ["fine-grained-tool-streaming-2025-05-14"],
 			maxTokens,
@@ -348,7 +348,7 @@ export class AnthropicHandler extends BaseProvider implements SingleCompletionHa
 
 	getModel() {
 		const modelId = this.options.apiModelId
-		let id = modelId && modelId in anthropicModels ? (modelId as AnthropicModelId) : anthropicDefaultModelId
+		const id = modelId && modelId in anthropicModels ? (modelId as AnthropicModelId) : anthropicDefaultModelId
 		let info: ModelInfo = anthropicModels[id]
 
 		// If 1M context beta is enabled for supported models, update the model info
@@ -394,7 +394,7 @@ export class AnthropicHandler extends BaseProvider implements SingleCompletionHa
 	}
 
 	async completePrompt(prompt: string) {
-		let { id: model, temperature } = this.getModel()
+		const { id: model, temperature } = this.getModel()
 
 		let message
 		try {

src/api/providers/bedrock.ts

@@ -205,7 +205,7 @@ export class AwsBedrockHandler extends BaseProvider implements SingleCompletionH
 	constructor(options: ProviderSettings) {
 		super()
 		this.options = options
-		let region = this.options.awsRegion
+		const region = this.options.awsRegion
 
 		// process the various user input options, be opinionated about the intent of the options
 		// and determine the model to use during inference and for cost calculations
@@ -532,8 +532,11 @@ export class AwsBedrockHandler extends BaseProvider implements SingleCompletionH
 						//so that pricing, context window, caching etc have values that can be used
 						//However, we want to keep the id of the model to be the ID for the router for
 						//subsequent requests so they are sent back through the router
-						let invokedArnInfo = this.parseArn(streamEvent.trace.promptRouter.invokedModelId)
-						let invokedModel = this.getModelById(invokedArnInfo.modelId as string, invokedArnInfo.modelType)
+						const invokedArnInfo = this.parseArn(streamEvent.trace.promptRouter.invokedModelId)
+						const invokedModel = this.getModelById(
+							invokedArnInfo.modelId as string,
+							invokedArnInfo.modelType,
+						)
 						if (invokedModel) {
 							invokedModel.id = modelConfig.id
 							this.costModelConfig = invokedModel
@@ -870,7 +873,7 @@ export class AwsBedrockHandler extends BaseProvider implements SingleCompletionH
 		}
 
 		// Get cache point placements
-		let strategy = new MultiPointStrategy(config)
+		const strategy = new MultiPointStrategy(config)
 		const cacheResult = strategy.determineOptimalCachePoints()
 
 		// Store cache point placements for future use if conversation ID is provided
@@ -934,7 +937,7 @@ export class AwsBedrockHandler extends BaseProvider implements SingleCompletionH
 		 */
 
 		const arnRegex = /^arn:[^:]+:(?:bedrock|sagemaker):([^:]+):([^:]*):(?:([^\/]+)\/([\w\.\-:]+)|([^\/]+))$/
-		let match = arn.match(arnRegex)
+		const match = arn.match(arnRegex)
 
 		if (match && match[1] && match[3] && match[4]) {
 			// Create the result object
@@ -961,7 +964,7 @@ export class AwsBedrockHandler extends BaseProvider implements SingleCompletionH
 			// Check if the original model ID had a region prefix
 			if (originalModelId && result.modelId !== originalModelId) {
 				// If the model ID changed after parsing, it had a region prefix
-				let prefix = originalModelId.replace(result.modelId, "")
+				const prefix = originalModelId.replace(result.modelId, "")
 				result.crossRegionInference = AwsBedrockHandler.isSystemInferenceProfile(prefix)
 			}
 

src/api/providers/fake-ai.ts

@@ -38,7 +38,7 @@ interface FakeAI {
  *
  * We use the ID to lookup the original FakeAI object in the mapping.
  */
-let fakeAiMap: Map<string, FakeAI> = new Map()
+const fakeAiMap: Map<string, FakeAI> = new Map()
 
 export class FakeAIHandler implements ApiHandler, SingleCompletionHandler {
 	private ai: FakeAI

src/api/providers/fetchers/ollama.ts

@@ -81,7 +81,7 @@ export async function getOllamaModels(
 
 		const response = await axios.get<OllamaModelsResponse>(`${baseUrl}/api/tags`, { headers })
 		const parsedResponse = OllamaModelsResponseSchema.safeParse(response.data)
-		let modelInfoPromises = []
+		const modelInfoPromises = []
 
 		if (parsedResponse.success) {
 			for (const ollamaModel of parsedResponse.data.models) {

src/api/providers/gemini.ts

@@ -348,7 +348,7 @@ export class GeminiHandler extends BaseProvider implements SingleCompletionHandl
 
 	override getModel() {
 		const modelId = this.options.apiModelId
-		let id = modelId && modelId in geminiModels ? (modelId as GeminiModelId) : geminiDefaultModelId
+		const id = modelId && modelId in geminiModels ? (modelId as GeminiModelId) : geminiDefaultModelId
 		let info: ModelInfo = geminiModels[id]
 
 		const params = getModelParams({
@@ -509,7 +509,7 @@ export class GeminiHandler extends BaseProvider implements SingleCompletionHandl
 		// Bill both completion and reasoning ("thoughts") tokens as output.
 		const billedOutputTokens = outputTokens + reasoningTokens
 
-		let cacheReadCost = cacheReadTokens > 0 ? cacheReadsPrice * (cacheReadTokens / 1_000_000) : 0
+		const cacheReadCost = cacheReadTokens > 0 ? cacheReadsPrice * (cacheReadTokens / 1_000_000) : 0
 
 		const inputTokensCost = inputPrice * (uncachedInputTokens / 1_000_000)
 		const outputTokensCost = outputPrice * (billedOutputTokens / 1_000_000)

src/api/providers/lite-llm.ts

@@ -184,7 +184,7 @@ export class LiteLLMHandler extends RouterProvider implements SingleCompletionHa
 		}
 
 		// Required by some providers; others default to max tokens allowed
-		let maxTokens: number | undefined = info.maxTokens ?? undefined
+		const maxTokens: number | undefined = info.maxTokens ?? undefined
 
 		// Check if this is a GPT-5 model that requires max_completion_tokens instead of max_tokens
 		const isGPT5Model = this.isGpt5(modelId)

src/api/providers/minimax.ts

@@ -81,7 +81,6 @@ export class MiniMaxHandler extends BaseProvider implements SingleCompletionHand
 		messages: Anthropic.Messages.MessageParam[],
 		metadata?: ApiHandlerCreateMessageMetadata,
 	): ApiStream {
-		let stream: AnthropicStream<Anthropic.Messages.RawMessageStreamEvent>
 		const cacheControl: CacheControlEphemeral = { type: "ephemeral" }
 		const { id: modelId, info, maxTokens, temperature } = this.getModel()
 
@@ -113,7 +112,7 @@ export class MiniMaxHandler extends BaseProvider implements SingleCompletionHand
 			tool_choice: convertOpenAIToolChoice(metadata?.tool_choice),
 		}
 
-		stream = await this.client.messages.create(requestParams)
+		const stream = await this.client.messages.create(requestParams)
 
 		let inputTokens = 0
 		let outputTokens = 0

src/api/providers/openai-codex.ts

@@ -1117,7 +1117,7 @@ export class OpenAiCodexHandler extends BaseProvider implements SingleCompletion
 	override getModel() {
 		const modelId = this.options.apiModelId
 
-		let id = modelId && modelId in openAiCodexModels ? (modelId as OpenAiCodexModelId) : openAiCodexDefaultModelId
+		const id = modelId && modelId in openAiCodexModels ? (modelId as OpenAiCodexModelId) : openAiCodexDefaultModelId
 
 		const info: ModelInfo = openAiCodexModels[id]
 

src/api/providers/openai-native.ts

@@ -674,8 +674,8 @@ export class OpenAiNativeHandler extends BaseProvider implements SingleCompletio
 		const decoder = new TextDecoder()
 		let buffer = ""
 		let hasContent = false
-		let totalInputTokens = 0
-		let totalOutputTokens = 0
+		const totalInputTokens = 0
+		const totalOutputTokens = 0
 
 		try {
 			while (true) {
@@ -1435,7 +1435,7 @@ export class OpenAiNativeHandler extends BaseProvider implements SingleCompletio
 	override getModel() {
 		const modelId = this.options.apiModelId
 
-		let id =
+		const id =
 			modelId && modelId in openAiNativeModels ? (modelId as OpenAiNativeModelId) : openAiNativeDefaultModelId
 
 		const info: ModelInfo = openAiNativeModels[id]