@blockrun/llm 3.8.0 → 3.8.1

package/dist/index.cjs

@@ -38,6 +38,7 @@ __export(index_exports, {
   ImageClient: () => ImageClient,
   KNOWN_PROVIDERS: () => KNOWN_PROVIDERS,
   LLMClient: () => LLMClient,
+  MAX_TOKENS_SANITY_LIMIT: () => MAX_TOKENS_SANITY_LIMIT,
   MusicClient: () => MusicClient,
   NETWORK_ALIASES: () => NETWORK_ALIASES,
   OpenAI: () => OpenAI,
@@ -355,6 +356,7 @@ function validateModel(model) {
     throw new Error("Model must be a non-empty string");
   }
 }
+var MAX_TOKENS_SANITY_LIMIT = 1e6;
 function validateMaxTokens(maxTokens) {
   if (maxTokens === void 0 || maxTokens === null) {
     return;
@@ -365,8 +367,13 @@ function validateMaxTokens(maxTokens) {
   if (maxTokens < 1) {
     throw new Error("maxTokens must be positive (minimum: 1)");
   }
-  if (maxTokens > 1e5) {
-    throw new Error("maxTokens too large (maximum: 100000)");
+  if (maxTokens > MAX_TOKENS_SANITY_LIMIT) {
+    throw Object.assign(
+      new Error(
+        `maxTokens implausibly large (client-side sanity limit: ${MAX_TOKENS_SANITY_LIMIT}). This is not a model limit \u2014 the gateway enforces the real per-model ceiling and reports it.`
+      ),
+      { code: "MAX_TOKENS_SANITY_LIMIT", limit: MAX_TOKENS_SANITY_LIMIT }
+    );
   }
 }
 function validateTemperature(temperature) {
@@ -766,6 +773,7 @@ var LLMClient = class _LLMClient {
    * @returns ChatResponse object with choices and usage
    */
   async chatCompletion(model, messages, options) {
+    validateMaxTokens(options?.maxTokens);
     const buildBody = (m) => {
       const body = {
         model: m,
@@ -1036,6 +1044,7 @@ var LLMClient = class _LLMClient {
    * @returns Raw fetch Response with a streaming SSE body.
    */
   async chatCompletionStream(model, messages, options) {
+    validateMaxTokens(options?.maxTokens);
     const url = `${this.apiUrl}/v1/chat/completions`;
     const body = {
       model,
@@ -5087,6 +5096,7 @@ var SolanaLLMClient = class {
   }
   /** Full chat completion (OpenAI-compatible). */
   async chatCompletion(model, messages, options) {
+    validateMaxTokens(options?.maxTokens);
     const body = {
       model,
       messages,
@@ -6129,6 +6139,7 @@ var AnthropicClient = class {
   ImageClient,
   KNOWN_PROVIDERS,
   LLMClient,
+  MAX_TOKENS_SANITY_LIMIT,
   MusicClient,
   NETWORK_ALIASES,
   OpenAI,

package/dist/index.d.cts

@@ -3161,7 +3161,34 @@ declare const KNOWN_PROVIDERS: Set<string>;
  */
 declare function validateModel(model: string): void;
 /**
- * Validates that max_tokens is an integer between 1 and 100,000.
+ * Client-side typo guard, NOT a model limit. The gateway already enforces the
+ * real per-model ceiling and rejects with that model's own number, so anything
+ * hardcoded here can only be wrong in one direction: too low.
+ *
+ * This was 100000. Note what it was and was not doing: until this change no
+ * client called `validateMaxTokens` at all, so the bound bound nothing on a
+ * real request — it only rejected callers who imported the validator directly
+ * off the package's public surface. The guard is now wired into
+ * `LLMClient.chatCompletion`, `LLMClient.chatCompletionStream`, and
+ * `SolanaLLMClient.chatCompletion`, which is exactly why the number had to go
+ * up first: at 100000 it would have started rejecting real requests.
+ *
+ * Verified against the live gateway 2026-07-21
+ * with the guard bypassed: zai/glm-5.2 accepted 262144, and the whole 128000
+ * class accepted 128000 (claude-opus-4.8, claude-sonnet-5, claude-fable-5,
+ * gpt-5.6-sol/terra/luna, gpt-5.5, gpt-5.4, gpt-5.3-codex, glm-5/5.1/5-turbo).
+ * 19 models advertised above 100000; all 19 accepted their ceiling. Those are
+ * as-of-date probe results, not a maintained invariant — nothing in this repo
+ * ships a model catalog, so CI cannot detect when they go stale.
+ *
+ * Keep a bound so an obvious mistake (1e9, a byte count, a timestamp) fails
+ * fast locally instead of becoming a payment quote. Set it far above any real
+ * model so it can never be the binding constraint again.
+ */
+declare const MAX_TOKENS_SANITY_LIMIT = 1000000;
+/**
+ * Validates that max_tokens is a positive integer no larger than
+ * {@link MAX_TOKENS_SANITY_LIMIT}.
  *
  * @param maxTokens - Maximum number of tokens to generate
  * @throws {Error} If maxTokens is invalid
@@ -3191,4 +3218,4 @@ declare function validateTemperature(temperature?: number): void;
  */
 declare function validateTopP(topP?: number): void;
 
-export { APIError, AnthropicClient, type AudioModel, type AudioTrack, BASE_CHAIN_ID, type BarResolution, type BlockRunAnthropicOptions, BlockrunClient, type BlockrunClientOptions, BlockrunError, type CallInitiatedResponse, type CallModel, type CallOptions, type CallStatusResponse, type ChatChoice, type ChatCompletionOptions, type ChatMessage, type ChatOptions, type ChatResponse, type ChatResponseWithCost, type ChatUsage, type CostEntry, type CostEstimate, type CreatePaymentOptions, type FunctionCall, type FunctionDefinition, type HistoryOptions, ImageClient, type ImageClientOptions, type ImageData, type ImageEditOptions, type ImageGenerateOptions, type ImageModel, type ImageResponse, KNOWN_PROVIDERS, LLMClient, type LLMClientOptions, type ListOptions, type MarketSession, type Model, MusicClient, type MusicClientOptions, type MusicGenerateOptions, type MusicResponse, NETWORK_ALIASES, type NewsSearchSource, OpenAI, type OpenAIChatCompletionChoice, type OpenAIChatCompletionChunk, type OpenAIChatCompletionParams, type OpenAIChatCompletionResponse, type OpenAIClientOptions, PHONE_PRICES, PORTRAIT_ENROLLMENT_PRICE_USD, PaymentError, type PaymentLinks, type PhoneBuyOptions, type PhoneBuyResponse, PhoneClient, type PhoneClientOptions, type PhoneListResponse, type PhoneLookupResponse, type PhoneNumberRecord, type PhoneReleaseResponse, type PhoneRenewResponse, type PollOptions, PortraitClient, type PortraitClientOptions, type PortraitEnrollOptions, type PortraitEnrollResponse, type PriceBar, type PriceCategory, PriceClient, type PriceClientOptions, type PriceHistoryResponse, type PriceOptions, type PricePoint, RPC_PRICE_USD, type ResponseFormat, type RoutingDecision, type RoutingProfile, type RoutingTier, type RpcBatchRequest, RpcClient, type RpcClientOptions, type RpcError, type RpcNetwork, type RpcResponse, type RssSearchSource, SOLANA_NETWORK, SOLANA_WALLET_FILE as SOLANA_WALLET_FILE_PATH, SUPPORTED_NETWORKS, SearchClient, type SearchClientOptions, type SearchOptions, type SearchParameters, type SearchResult, type SearchSource, type SearchUsage, type SmartChatOptions, type SmartChatResponse, SolanaLLMClient, type SolanaLLMClientOptions, type SolanaWalletInfo, type SoundEffectOptions, type SpeechAudio, SpeechClient, type SpeechClientOptions, type SpeechGenerateOptions, type SpeechModel, type SpeechResponse, type SpeechVoice, type Spending, type SpendingReport, type StockMarket, SurfClient, type SurfClientOptions, type SymbolListResponse, type Tool, type ToolCall, type ToolChoice, USDC_BASE, USDC_BASE_CONTRACT, USDC_SOLANA, VideoClient, type VideoClientOptions, type VideoClip, type VideoGenerateOptions, type VideoModel, type VideoResponse, VoiceClient, type VoiceClientOptions, type VoiceInfo, type VoicePreset, WALLET_DIR_PATH, WALLET_FILE_PATH, type WalletInfo, type WebSearchSource, type XSearchSource, clearCache, createPaymentPayload, createSolanaPaymentPayload, createSolanaWallet, createWallet, LLMClient as default, extractPaymentDetails, formatFundingMessageCompact, formatNeedsFundingMessage, formatSolanaWalletMigrationNotice, formatWalletCreatedMessage, formatWalletMigrationNotice, getCached, getCachedByRequest, getCostLogSummary, getCostSummary, getEip681Uri, getOrCreateSolanaWallet, getOrCreateWallet, getPaymentLinks, getWalletAddress, importSolanaWallet, importWallet, listDiscoveredSolanaWallets, listDiscoveredWallets, loadSolanaWallet, loadWallet, logCost, parsePaymentRequired, saveSolanaWallet, saveToCache, saveWallet, scanSolanaWallets, scanWallets, setCache, setupAgentSolanaWallet, setupAgentWallet, solanaClient, solanaKeyToBytes, solanaPublicKey, status, validateMaxTokens, validateModel, validateTemperature, validateTopP };
+export { APIError, AnthropicClient, type AudioModel, type AudioTrack, BASE_CHAIN_ID, type BarResolution, type BlockRunAnthropicOptions, BlockrunClient, type BlockrunClientOptions, BlockrunError, type CallInitiatedResponse, type CallModel, type CallOptions, type CallStatusResponse, type ChatChoice, type ChatCompletionOptions, type ChatMessage, type ChatOptions, type ChatResponse, type ChatResponseWithCost, type ChatUsage, type CostEntry, type CostEstimate, type CreatePaymentOptions, type FunctionCall, type FunctionDefinition, type HistoryOptions, ImageClient, type ImageClientOptions, type ImageData, type ImageEditOptions, type ImageGenerateOptions, type ImageModel, type ImageResponse, KNOWN_PROVIDERS, LLMClient, type LLMClientOptions, type ListOptions, MAX_TOKENS_SANITY_LIMIT, type MarketSession, type Model, MusicClient, type MusicClientOptions, type MusicGenerateOptions, type MusicResponse, NETWORK_ALIASES, type NewsSearchSource, OpenAI, type OpenAIChatCompletionChoice, type OpenAIChatCompletionChunk, type OpenAIChatCompletionParams, type OpenAIChatCompletionResponse, type OpenAIClientOptions, PHONE_PRICES, PORTRAIT_ENROLLMENT_PRICE_USD, PaymentError, type PaymentLinks, type PhoneBuyOptions, type PhoneBuyResponse, PhoneClient, type PhoneClientOptions, type PhoneListResponse, type PhoneLookupResponse, type PhoneNumberRecord, type PhoneReleaseResponse, type PhoneRenewResponse, type PollOptions, PortraitClient, type PortraitClientOptions, type PortraitEnrollOptions, type PortraitEnrollResponse, type PriceBar, type PriceCategory, PriceClient, type PriceClientOptions, type PriceHistoryResponse, type PriceOptions, type PricePoint, RPC_PRICE_USD, type ResponseFormat, type RoutingDecision, type RoutingProfile, type RoutingTier, type RpcBatchRequest, RpcClient, type RpcClientOptions, type RpcError, type RpcNetwork, type RpcResponse, type RssSearchSource, SOLANA_NETWORK, SOLANA_WALLET_FILE as SOLANA_WALLET_FILE_PATH, SUPPORTED_NETWORKS, SearchClient, type SearchClientOptions, type SearchOptions, type SearchParameters, type SearchResult, type SearchSource, type SearchUsage, type SmartChatOptions, type SmartChatResponse, SolanaLLMClient, type SolanaLLMClientOptions, type SolanaWalletInfo, type SoundEffectOptions, type SpeechAudio, SpeechClient, type SpeechClientOptions, type SpeechGenerateOptions, type SpeechModel, type SpeechResponse, type SpeechVoice, type Spending, type SpendingReport, type StockMarket, SurfClient, type SurfClientOptions, type SymbolListResponse, type Tool, type ToolCall, type ToolChoice, USDC_BASE, USDC_BASE_CONTRACT, USDC_SOLANA, VideoClient, type VideoClientOptions, type VideoClip, type VideoGenerateOptions, type VideoModel, type VideoResponse, VoiceClient, type VoiceClientOptions, type VoiceInfo, type VoicePreset, WALLET_DIR_PATH, WALLET_FILE_PATH, type WalletInfo, type WebSearchSource, type XSearchSource, clearCache, createPaymentPayload, createSolanaPaymentPayload, createSolanaWallet, createWallet, LLMClient as default, extractPaymentDetails, formatFundingMessageCompact, formatNeedsFundingMessage, formatSolanaWalletMigrationNotice, formatWalletCreatedMessage, formatWalletMigrationNotice, getCached, getCachedByRequest, getCostLogSummary, getCostSummary, getEip681Uri, getOrCreateSolanaWallet, getOrCreateWallet, getPaymentLinks, getWalletAddress, importSolanaWallet, importWallet, listDiscoveredSolanaWallets, listDiscoveredWallets, loadSolanaWallet, loadWallet, logCost, parsePaymentRequired, saveSolanaWallet, saveToCache, saveWallet, scanSolanaWallets, scanWallets, setCache, setupAgentSolanaWallet, setupAgentWallet, solanaClient, solanaKeyToBytes, solanaPublicKey, status, validateMaxTokens, validateModel, validateTemperature, validateTopP };

package/dist/index.d.ts

@@ -3161,7 +3161,34 @@ declare const KNOWN_PROVIDERS: Set<string>;
  */
 declare function validateModel(model: string): void;
 /**
- * Validates that max_tokens is an integer between 1 and 100,000.
+ * Client-side typo guard, NOT a model limit. The gateway already enforces the
+ * real per-model ceiling and rejects with that model's own number, so anything
+ * hardcoded here can only be wrong in one direction: too low.
+ *
+ * This was 100000. Note what it was and was not doing: until this change no
+ * client called `validateMaxTokens` at all, so the bound bound nothing on a
+ * real request — it only rejected callers who imported the validator directly
+ * off the package's public surface. The guard is now wired into
+ * `LLMClient.chatCompletion`, `LLMClient.chatCompletionStream`, and
+ * `SolanaLLMClient.chatCompletion`, which is exactly why the number had to go
+ * up first: at 100000 it would have started rejecting real requests.
+ *
+ * Verified against the live gateway 2026-07-21
+ * with the guard bypassed: zai/glm-5.2 accepted 262144, and the whole 128000
+ * class accepted 128000 (claude-opus-4.8, claude-sonnet-5, claude-fable-5,
+ * gpt-5.6-sol/terra/luna, gpt-5.5, gpt-5.4, gpt-5.3-codex, glm-5/5.1/5-turbo).
+ * 19 models advertised above 100000; all 19 accepted their ceiling. Those are
+ * as-of-date probe results, not a maintained invariant — nothing in this repo
+ * ships a model catalog, so CI cannot detect when they go stale.
+ *
+ * Keep a bound so an obvious mistake (1e9, a byte count, a timestamp) fails
+ * fast locally instead of becoming a payment quote. Set it far above any real
+ * model so it can never be the binding constraint again.
+ */
+declare const MAX_TOKENS_SANITY_LIMIT = 1000000;
+/**
+ * Validates that max_tokens is a positive integer no larger than
+ * {@link MAX_TOKENS_SANITY_LIMIT}.
  *
  * @param maxTokens - Maximum number of tokens to generate
  * @throws {Error} If maxTokens is invalid
@@ -3191,4 +3218,4 @@ declare function validateTemperature(temperature?: number): void;
  */
 declare function validateTopP(topP?: number): void;
 
-export { APIError, AnthropicClient, type AudioModel, type AudioTrack, BASE_CHAIN_ID, type BarResolution, type BlockRunAnthropicOptions, BlockrunClient, type BlockrunClientOptions, BlockrunError, type CallInitiatedResponse, type CallModel, type CallOptions, type CallStatusResponse, type ChatChoice, type ChatCompletionOptions, type ChatMessage, type ChatOptions, type ChatResponse, type ChatResponseWithCost, type ChatUsage, type CostEntry, type CostEstimate, type CreatePaymentOptions, type FunctionCall, type FunctionDefinition, type HistoryOptions, ImageClient, type ImageClientOptions, type ImageData, type ImageEditOptions, type ImageGenerateOptions, type ImageModel, type ImageResponse, KNOWN_PROVIDERS, LLMClient, type LLMClientOptions, type ListOptions, type MarketSession, type Model, MusicClient, type MusicClientOptions, type MusicGenerateOptions, type MusicResponse, NETWORK_ALIASES, type NewsSearchSource, OpenAI, type OpenAIChatCompletionChoice, type OpenAIChatCompletionChunk, type OpenAIChatCompletionParams, type OpenAIChatCompletionResponse, type OpenAIClientOptions, PHONE_PRICES, PORTRAIT_ENROLLMENT_PRICE_USD, PaymentError, type PaymentLinks, type PhoneBuyOptions, type PhoneBuyResponse, PhoneClient, type PhoneClientOptions, type PhoneListResponse, type PhoneLookupResponse, type PhoneNumberRecord, type PhoneReleaseResponse, type PhoneRenewResponse, type PollOptions, PortraitClient, type PortraitClientOptions, type PortraitEnrollOptions, type PortraitEnrollResponse, type PriceBar, type PriceCategory, PriceClient, type PriceClientOptions, type PriceHistoryResponse, type PriceOptions, type PricePoint, RPC_PRICE_USD, type ResponseFormat, type RoutingDecision, type RoutingProfile, type RoutingTier, type RpcBatchRequest, RpcClient, type RpcClientOptions, type RpcError, type RpcNetwork, type RpcResponse, type RssSearchSource, SOLANA_NETWORK, SOLANA_WALLET_FILE as SOLANA_WALLET_FILE_PATH, SUPPORTED_NETWORKS, SearchClient, type SearchClientOptions, type SearchOptions, type SearchParameters, type SearchResult, type SearchSource, type SearchUsage, type SmartChatOptions, type SmartChatResponse, SolanaLLMClient, type SolanaLLMClientOptions, type SolanaWalletInfo, type SoundEffectOptions, type SpeechAudio, SpeechClient, type SpeechClientOptions, type SpeechGenerateOptions, type SpeechModel, type SpeechResponse, type SpeechVoice, type Spending, type SpendingReport, type StockMarket, SurfClient, type SurfClientOptions, type SymbolListResponse, type Tool, type ToolCall, type ToolChoice, USDC_BASE, USDC_BASE_CONTRACT, USDC_SOLANA, VideoClient, type VideoClientOptions, type VideoClip, type VideoGenerateOptions, type VideoModel, type VideoResponse, VoiceClient, type VoiceClientOptions, type VoiceInfo, type VoicePreset, WALLET_DIR_PATH, WALLET_FILE_PATH, type WalletInfo, type WebSearchSource, type XSearchSource, clearCache, createPaymentPayload, createSolanaPaymentPayload, createSolanaWallet, createWallet, LLMClient as default, extractPaymentDetails, formatFundingMessageCompact, formatNeedsFundingMessage, formatSolanaWalletMigrationNotice, formatWalletCreatedMessage, formatWalletMigrationNotice, getCached, getCachedByRequest, getCostLogSummary, getCostSummary, getEip681Uri, getOrCreateSolanaWallet, getOrCreateWallet, getPaymentLinks, getWalletAddress, importSolanaWallet, importWallet, listDiscoveredSolanaWallets, listDiscoveredWallets, loadSolanaWallet, loadWallet, logCost, parsePaymentRequired, saveSolanaWallet, saveToCache, saveWallet, scanSolanaWallets, scanWallets, setCache, setupAgentSolanaWallet, setupAgentWallet, solanaClient, solanaKeyToBytes, solanaPublicKey, status, validateMaxTokens, validateModel, validateTemperature, validateTopP };
+export { APIError, AnthropicClient, type AudioModel, type AudioTrack, BASE_CHAIN_ID, type BarResolution, type BlockRunAnthropicOptions, BlockrunClient, type BlockrunClientOptions, BlockrunError, type CallInitiatedResponse, type CallModel, type CallOptions, type CallStatusResponse, type ChatChoice, type ChatCompletionOptions, type ChatMessage, type ChatOptions, type ChatResponse, type ChatResponseWithCost, type ChatUsage, type CostEntry, type CostEstimate, type CreatePaymentOptions, type FunctionCall, type FunctionDefinition, type HistoryOptions, ImageClient, type ImageClientOptions, type ImageData, type ImageEditOptions, type ImageGenerateOptions, type ImageModel, type ImageResponse, KNOWN_PROVIDERS, LLMClient, type LLMClientOptions, type ListOptions, MAX_TOKENS_SANITY_LIMIT, type MarketSession, type Model, MusicClient, type MusicClientOptions, type MusicGenerateOptions, type MusicResponse, NETWORK_ALIASES, type NewsSearchSource, OpenAI, type OpenAIChatCompletionChoice, type OpenAIChatCompletionChunk, type OpenAIChatCompletionParams, type OpenAIChatCompletionResponse, type OpenAIClientOptions, PHONE_PRICES, PORTRAIT_ENROLLMENT_PRICE_USD, PaymentError, type PaymentLinks, type PhoneBuyOptions, type PhoneBuyResponse, PhoneClient, type PhoneClientOptions, type PhoneListResponse, type PhoneLookupResponse, type PhoneNumberRecord, type PhoneReleaseResponse, type PhoneRenewResponse, type PollOptions, PortraitClient, type PortraitClientOptions, type PortraitEnrollOptions, type PortraitEnrollResponse, type PriceBar, type PriceCategory, PriceClient, type PriceClientOptions, type PriceHistoryResponse, type PriceOptions, type PricePoint, RPC_PRICE_USD, type ResponseFormat, type RoutingDecision, type RoutingProfile, type RoutingTier, type RpcBatchRequest, RpcClient, type RpcClientOptions, type RpcError, type RpcNetwork, type RpcResponse, type RssSearchSource, SOLANA_NETWORK, SOLANA_WALLET_FILE as SOLANA_WALLET_FILE_PATH, SUPPORTED_NETWORKS, SearchClient, type SearchClientOptions, type SearchOptions, type SearchParameters, type SearchResult, type SearchSource, type SearchUsage, type SmartChatOptions, type SmartChatResponse, SolanaLLMClient, type SolanaLLMClientOptions, type SolanaWalletInfo, type SoundEffectOptions, type SpeechAudio, SpeechClient, type SpeechClientOptions, type SpeechGenerateOptions, type SpeechModel, type SpeechResponse, type SpeechVoice, type Spending, type SpendingReport, type StockMarket, SurfClient, type SurfClientOptions, type SymbolListResponse, type Tool, type ToolCall, type ToolChoice, USDC_BASE, USDC_BASE_CONTRACT, USDC_SOLANA, VideoClient, type VideoClientOptions, type VideoClip, type VideoGenerateOptions, type VideoModel, type VideoResponse, VoiceClient, type VoiceClientOptions, type VoiceInfo, type VoicePreset, WALLET_DIR_PATH, WALLET_FILE_PATH, type WalletInfo, type WebSearchSource, type XSearchSource, clearCache, createPaymentPayload, createSolanaPaymentPayload, createSolanaWallet, createWallet, LLMClient as default, extractPaymentDetails, formatFundingMessageCompact, formatNeedsFundingMessage, formatSolanaWalletMigrationNotice, formatWalletCreatedMessage, formatWalletMigrationNotice, getCached, getCachedByRequest, getCostLogSummary, getCostSummary, getEip681Uri, getOrCreateSolanaWallet, getOrCreateWallet, getPaymentLinks, getWalletAddress, importSolanaWallet, importWallet, listDiscoveredSolanaWallets, listDiscoveredWallets, loadSolanaWallet, loadWallet, logCost, parsePaymentRequired, saveSolanaWallet, saveToCache, saveWallet, scanSolanaWallets, scanWallets, setCache, setupAgentSolanaWallet, setupAgentWallet, solanaClient, solanaKeyToBytes, solanaPublicKey, status, validateMaxTokens, validateModel, validateTemperature, validateTopP };

package/dist/index.js

@@ -242,6 +242,7 @@ function validateModel(model) {
     throw new Error("Model must be a non-empty string");
   }
 }
+var MAX_TOKENS_SANITY_LIMIT = 1e6;
 function validateMaxTokens(maxTokens) {
   if (maxTokens === void 0 || maxTokens === null) {
     return;
@@ -252,8 +253,13 @@ function validateMaxTokens(maxTokens) {
   if (maxTokens < 1) {
     throw new Error("maxTokens must be positive (minimum: 1)");
   }
-  if (maxTokens > 1e5) {
-    throw new Error("maxTokens too large (maximum: 100000)");
+  if (maxTokens > MAX_TOKENS_SANITY_LIMIT) {
+    throw Object.assign(
+      new Error(
+        `maxTokens implausibly large (client-side sanity limit: ${MAX_TOKENS_SANITY_LIMIT}). This is not a model limit \u2014 the gateway enforces the real per-model ceiling and reports it.`
+      ),
+      { code: "MAX_TOKENS_SANITY_LIMIT", limit: MAX_TOKENS_SANITY_LIMIT }
+    );
   }
 }
 function validateTemperature(temperature) {
@@ -653,6 +659,7 @@ var LLMClient = class _LLMClient {
    * @returns ChatResponse object with choices and usage
    */
   async chatCompletion(model, messages, options) {
+    validateMaxTokens(options?.maxTokens);
     const buildBody = (m) => {
       const body = {
         model: m,
@@ -923,6 +930,7 @@ var LLMClient = class _LLMClient {
    * @returns Raw fetch Response with a streaming SSE body.
    */
   async chatCompletionStream(model, messages, options) {
+    validateMaxTokens(options?.maxTokens);
     const url = `${this.apiUrl}/v1/chat/completions`;
     const body = {
       model,
@@ -4974,6 +4982,7 @@ var SolanaLLMClient = class {
   }
   /** Full chat completion (OpenAI-compatible). */
   async chatCompletion(model, messages, options) {
+    validateMaxTokens(options?.maxTokens);
     const body = {
       model,
       messages,
@@ -6015,6 +6024,7 @@ export {
   ImageClient,
   KNOWN_PROVIDERS,
   LLMClient,
+  MAX_TOKENS_SANITY_LIMIT,
   MusicClient,
   NETWORK_ALIASES,
   OpenAI,

package/package.json

@@ -1,6 +1,6 @@
 {
   "name": "@blockrun/llm",
-  "version": "3.8.0",
+  "version": "3.8.1",
   "type": "module",
   "description": "BlockRun SDK - Pay-per-request AI (LLM, Image, Video, Music, Voice) via x402 on Base and Solana",
   "main": "dist/index.cjs",