@index9/mcp 6.5.3 → 6.5.4

package/dist/cli.js

@@ -262,8 +262,8 @@ var SITE = {
     installCta: "Install"
   },
   hero: {
-    title: "Index9 helps coding assistants pick models from live data.",
-    subtitle: "MCP tools for Claude Code, Cursor, VS Code, and Codex. Search, compare, cost-model, and live-test 300+ models.",
+    title: "Index9 helps coding assistants pick from live model data.",
+    subtitle: "MCP tools for Claude Code, Cursor, VS Code, and Codex to search, compare, cost-model, and live-test 300+ models.",
     pricingNote: "Free to install. Live tests use your OpenRouter key.",
     seeHowItWorks: "See a real session",
     updatedBadge: "OpenRouter data \xB7 refreshed ",
@@ -279,9 +279,9 @@ var SITE = {
     label: "Why this exists",
     heading: "Your assistant's model knowledge is stale",
     body: [
-      'New models ship every week. Pricing changes. "Use GPT-4" or "use Claude 3.5" is usually months behind reality.',
-      "Without live data, your assistant defaults to whatever it learned in training. Usually a model superseded by something cheaper or better-suited to your task.",
-      "Index9 gives it the data, and the tools to compare."
+      "New models ship every week. Prices, aliases, and capabilities change with them.",
+      "Without live data, your assistant falls back to training-time memory \u2014 usually a model that's been superseded by something cheaper or better-suited.",
+      "Index9 lets it check the live catalog before recommending."
     ]
   },
   howItWorks: {
@@ -309,76 +309,13 @@ var SITE = {
   caseStudy: {
     label: "Real session",
     heading: "A real session, not a mockup",
-    subheading: "Claude Sonnet 4.6 using Index9 to pick a model for a TypeScript code-review bot. Real prompt, tool calls, and verdict.",
-    prompt: {
-      title: "The prompt",
-      body: "Pick a model for a TypeScript code-review bot that runs on every PR. I want real quality without paying frontier rates. Quote model ids verbatim from the tool responses."
-    },
-    toolCalls: {
-      title: "What the assistant did",
-      subtitle: "4 calls, 42s",
-      calls: [
-        {
-          tool: "find_models",
-          params: "sortBy=created, function_calling + structured_output",
-          note: "skip stale training picks"
-        },
-        {
-          tool: "find_models",
-          params: "code review, maxPrice=$5/M, minContext=64K",
-          note: "task fit"
-        },
-        {
-          tool: "compare_models",
-          params: "4 finalists, 3,000 prompt + 800 completion",
-          note: "per-PR cost diff"
-        },
-        {
-          tool: "test_model",
-          params: "dry-run \xD7 4, same token budget",
-          note: "cost confirmation"
-        }
-      ]
-    },
+    subheading: "A real eval run picking a model for a TypeScript code-review bot. Real prompt, real tool calls, real verdict.",
+    promptTitle: "The prompt",
+    toolCallsTitle: "What the assistant did",
     consideredTitle: "Candidates evaluated",
-    consideredSubtitle: "5 evaluated, 1 pick",
-    consideredRows: [
-      {
-        id: "anthropic/claude-opus-4.7-fast",
-        age: "5d ago",
-        decision: "skip",
-        reason: "$30/M input, above the maxPrice filter"
-      },
-      {
-        id: "mistralai/devstral-medium",
-        age: "10mo ago",
-        decision: "tested",
-        reason: "$0.40/M input, $2/M output, $0.0028 per PR"
-      },
-      {
-        id: "qwen/qwen3-coder",
-        age: "10mo ago",
-        decision: "tested",
-        reason: "$0.22/M input, 1M context, no file_input, $0.0021 per PR"
-      },
-      {
-        id: "google/gemini-3.1-flash-lite",
-        age: "1w ago",
-        decision: "tested",
-        reason: "$0.25/M input, newest finalist, reasoning + vision, $0.00195 per PR"
-      },
-      {
-        id: "mistralai/codestral-2508",
-        age: "9mo ago",
-        decision: "shortlisted",
-        reason: "$0.30/M input, coding-specific, $0.00162 per PR"
-      }
-    ],
-    verdict: {
-      title: "The pick",
-      model: "mistralai/codestral-2508",
-      body: "$0.00162 per PR (3K diff + 800 review, dry-run). Coding-specific, structured output, file input, 256K context. About 100\xD7 cheaper on input than claude-opus-4.7-fast."
-    }
+    verdictTitle: "The pick",
+    capturedPrefix: "Captured ",
+    sourcePrefix: " \xB7 source "
   },
   toolsSection: {
     label: "Tools",
@@ -767,56 +704,92 @@ var ListFacetsToolResultSchema = FacetsResponseSchema.extend({
   _index9: Index9MetaSchema
 });
 
-// ../core/dist/schemas/test.js
+// ../core/dist/schemas/case-study.js
 import { z as z6 } from "zod";
-var ResponseFormatSchema = z6.object({
-  type: z6.string().min(1)
-}).catchall(z6.unknown()).optional();
-var ProviderSortSchema = z6.enum(["throughput", "price", "latency"]);
-var TestRequestSchema = z6.object({
-  prompt: z6.string().min(1).optional(),
-  userContent: z6.array(UserContentPartSchema).min(1).optional(),
-  dryRun: z6.boolean().optional(),
-  expectedPromptTokens: z6.number().int().positive().optional(),
-  expectedCompletionTokens: z6.number().int().positive().optional(),
-  models: z6.array(z6.string().min(1)).min(1, "Models are required").max(LIMITS.testModelsMax, `Models must contain between 1 and ${LIMITS.testModelsMax} model IDs`),
-  timeoutMs: z6.number().int().positive().optional(),
-  maxTokens: z6.number().int().positive().optional(),
-  systemPrompt: z6.string().min(1).optional(),
-  temperature: z6.number().min(0).max(2).optional(),
-  topP: z6.number().gt(0).lte(1).optional(),
-  seed: z6.number().int().optional(),
+var CaseStudyDecisionSchema = z6.enum(["shortlisted", "tested"]);
+var CaseStudyToolCallSchema = z6.object({
+  tool: z6.string(),
+  params: z6.string()
+}).strict();
+var CaseStudyCandidateSchema = z6.object({
+  id: z6.string(),
+  createdAt: z6.string().nullable(),
+  decision: CaseStudyDecisionSchema,
+  promptPerMillion: z6.number().nullable(),
+  completionPerMillion: z6.number().nullable(),
+  perPromptCostUsd: z6.number().nullable()
+}).strict();
+var CaseStudyVerdictSchema = z6.object({
+  model: z6.string().nullable(),
+  body: z6.string()
+}).strict();
+var CaseStudySchema = z6.object({
+  capturedAt: z6.string(),
+  generatedAt: z6.string(),
+  sourceRun: z6.string(),
+  evaluatorModelId: z6.string(),
+  promptId: z6.string(),
+  promptBody: z6.string(),
+  totalLatencyMs: z6.number().int(),
+  totalCostUsd: z6.number().nullable(),
+  toolCallCount: z6.number().int(),
+  candidateCount: z6.number().int(),
+  selectedModelId: z6.string().nullable(),
+  toolCalls: z6.array(CaseStudyToolCallSchema),
+  candidates: z6.array(CaseStudyCandidateSchema),
+  verdict: CaseStudyVerdictSchema
+}).strict();
+
+// ../core/dist/schemas/test.js
+import { z as z7 } from "zod";
+var ResponseFormatSchema = z7.object({
+  type: z7.string().min(1)
+}).catchall(z7.unknown()).optional();
+var ProviderSortSchema = z7.enum(["throughput", "price", "latency"]);
+var TestRequestSchema = z7.object({
+  prompt: z7.string().min(1).optional(),
+  userContent: z7.array(UserContentPartSchema).min(1).optional(),
+  dryRun: z7.boolean().optional(),
+  expectedPromptTokens: z7.number().int().positive().optional(),
+  expectedCompletionTokens: z7.number().int().positive().optional(),
+  models: z7.array(z7.string().min(1)).min(1, "Models are required").max(LIMITS.testModelsMax, `Models must contain between 1 and ${LIMITS.testModelsMax} model IDs`),
+  timeoutMs: z7.number().int().positive().optional(),
+  maxTokens: z7.number().int().positive().optional(),
+  systemPrompt: z7.string().min(1).optional(),
+  temperature: z7.number().min(0).max(2).optional(),
+  topP: z7.number().gt(0).lte(1).optional(),
+  seed: z7.number().int().optional(),
   responseFormat: ResponseFormatSchema,
-  enforceJson: z6.boolean().optional(),
-  retries: z6.number().int().min(0).max(3).optional(),
+  enforceJson: z7.boolean().optional(),
+  retries: z7.number().int().min(0).max(3).optional(),
   // Use OpenRouter's SSE streaming endpoint so capacity/refusal errors
   // surface in ~1s instead of waiting the full per-model timeout for an
   // empty 200 OK. Cost/tokens are still returned via stream_options.
-  stream: z6.boolean().optional(),
+  stream: z7.boolean().optional(),
   // First-token deadline (streaming only). If the upstream sends no
   // delta within this window, abort the request. Defaults to 10s when
   // streaming. Ignored when stream=false.
-  firstTokenTimeoutMs: z6.number().int().positive().optional(),
+  firstTokenTimeoutMs: z7.number().int().positive().optional(),
   // Forwards as `provider.sort` to OpenRouter — opt into routing toward
   // higher-throughput providers when running benchmarks.
   providerSort: ProviderSortSchema.optional(),
   // Forwards as `provider.order` — try these provider slugs first in the
   // given order before falling back. Capped to stay within reasonable
   // limits and prevent abuse.
-  providerOrder: z6.array(z6.string().min(1)).min(1).max(8).optional(),
+  providerOrder: z7.array(z7.string().min(1)).min(1).max(8).optional(),
   // Forwards as the top-level `models` array (NOT `model`). OpenRouter
   // tries each in order if the primary is unavailable. Different intent
   // from providerOrder, which routes within a single model.
-  fallbackModels: z6.array(z6.string().min(1)).min(1).max(5).optional(),
+  fallbackModels: z7.array(z7.string().min(1)).min(1).max(5).optional(),
   // When true, attach a `debug` field on each result with the raw
   // upstream finish_reason, error message, provider name, refusal, and
   // usage. Used to diagnose "missing assistant text" without re-running.
-  debug: z6.boolean().optional()
+  debug: z7.boolean().optional()
 }).strict().superRefine((data, ctx) => {
   if (data.dryRun === true) {
     if (!data.prompt && data.expectedPromptTokens === void 0) {
       ctx.addIssue({
-        code: z6.ZodIssueCode.custom,
+        code: z7.ZodIssueCode.custom,
         message: "dryRun requires either prompt or expectedPromptTokens",
         path: ["prompt"]
       });
@@ -825,24 +798,24 @@ var TestRequestSchema = z6.object({
   }
   if (!data.prompt && !data.userContent?.length) {
     ctx.addIssue({
-      code: z6.ZodIssueCode.custom,
+      code: z7.ZodIssueCode.custom,
       message: "Prompt or userContent is required",
       path: ["prompt"]
     });
   }
 });
-var UsageTokensSchema = z6.object({
-  prompt: z6.number().min(0),
-  completion: z6.number().min(0)
+var UsageTokensSchema = z7.object({
+  prompt: z7.number().min(0),
+  completion: z7.number().min(0)
 });
-var TestPricingUsedSchema = z6.object({
-  promptPerToken: z6.number().nullable().optional(),
-  completionPerToken: z6.number().nullable().optional(),
-  promptPerMillion: z6.number().nullable().optional(),
-  completionPerMillion: z6.number().nullable().optional(),
-  requestUsd: z6.number().nullable().optional()
+var TestPricingUsedSchema = z7.object({
+  promptPerToken: z7.number().nullable().optional(),
+  completionPerToken: z7.number().nullable().optional(),
+  promptPerMillion: z7.number().nullable().optional(),
+  completionPerMillion: z7.number().nullable().optional(),
+  requestUsd: z7.number().nullable().optional()
 });
-var TestFailureReasonSchema = z6.enum([
+var TestFailureReasonSchema = z7.enum([
   "insufficient_credits",
   "model_unavailable",
   "rate_limited",
@@ -854,86 +827,86 @@ var TestFailureReasonSchema = z6.enum([
   "invalid_request",
   "unknown"
 ]);
-var TestDebugInfoSchema = z6.object({
-  upstreamId: z6.string().optional(),
-  providerName: z6.string().optional(),
-  modelPublisher: z6.string().optional(),
-  finishReason: z6.string().optional(),
-  upstreamError: z6.string().optional(),
-  refusal: z6.string().optional(),
-  hasToolCalls: z6.boolean().optional(),
-  usage: z6.object({
-    promptTokens: z6.number().optional(),
-    completionTokens: z6.number().optional(),
-    totalTokens: z6.number().optional()
+var TestDebugInfoSchema = z7.object({
+  upstreamId: z7.string().optional(),
+  providerName: z7.string().optional(),
+  modelPublisher: z7.string().optional(),
+  finishReason: z7.string().optional(),
+  upstreamError: z7.string().optional(),
+  refusal: z7.string().optional(),
+  hasToolCalls: z7.boolean().optional(),
+  usage: z7.object({
+    promptTokens: z7.number().optional(),
+    completionTokens: z7.number().optional(),
+    totalTokens: z7.number().optional()
   }).optional()
 });
-var TestModelMetadataSchema = z6.object({
-  id: z6.string(),
-  name: z6.string(),
-  created: z6.number().nullable().optional(),
-  createdAt: z6.string().nullable().optional(),
+var TestModelMetadataSchema = z7.object({
+  id: z7.string(),
+  name: z7.string(),
+  created: z7.number().nullable().optional(),
+  createdAt: z7.string().nullable().optional(),
   pricingUsed: TestPricingUsedSchema.optional()
 });
-var TestResultSuccessSchema = z6.object({
-  modelId: z6.string(),
-  resolvedModelId: z6.string().optional(),
-  ok: z6.literal(true),
+var TestResultSuccessSchema = z7.object({
+  modelId: z7.string(),
+  resolvedModelId: z7.string().optional(),
+  ok: z7.literal(true),
   model: TestModelMetadataSchema,
-  response: z6.string(),
-  latencyMs: z6.number().min(0),
+  response: z7.string(),
+  latencyMs: z7.number().min(0),
   tokens: UsageTokensSchema,
-  cost: z6.number().nullable().optional(),
-  truncated: z6.boolean().optional(),
+  cost: z7.number().nullable().optional(),
+  truncated: z7.boolean().optional(),
   debug: TestDebugInfoSchema.optional()
 });
-var TestResultFailureSchema = z6.object({
-  modelId: z6.string(),
-  resolvedModelId: z6.string().optional(),
-  ok: z6.literal(false),
+var TestResultFailureSchema = z7.object({
+  modelId: z7.string(),
+  resolvedModelId: z7.string().optional(),
+  ok: z7.literal(false),
   model: TestModelMetadataSchema,
-  error: z6.string(),
+  error: z7.string(),
   failureReason: TestFailureReasonSchema.optional(),
-  latencyMs: z6.number().min(0),
+  latencyMs: z7.number().min(0),
   debug: TestDebugInfoSchema.optional()
 });
-var TestResultSchema = z6.discriminatedUnion("ok", [
+var TestResultSchema = z7.discriminatedUnion("ok", [
   TestResultSuccessSchema,
   TestResultFailureSchema
 ]);
-var TestEstimateResultSchema = z6.object({
-  modelId: z6.string(),
-  resolvedModelId: z6.string().optional(),
+var TestEstimateResultSchema = z7.object({
+  modelId: z7.string(),
+  resolvedModelId: z7.string().optional(),
   model: TestModelMetadataSchema,
   tokens: UsageTokensSchema,
-  estimatedCost: z6.number().nullable().optional(),
-  tokenCostUsd: z6.number().nullable().optional(),
-  requestCostUsd: z6.number().nullable().optional(),
-  totalCostUsd: z6.number().nullable().optional(),
+  estimatedCost: z7.number().nullable().optional(),
+  tokenCostUsd: z7.number().nullable().optional(),
+  requestCostUsd: z7.number().nullable().optional(),
+  totalCostUsd: z7.number().nullable().optional(),
   estimatedCostBasis: PricingBasisSchema.optional()
 });
 var TestResolutionFieldsSchema = {
-  missingIds: z6.array(z6.string()).optional(),
-  resolvedAliases: z6.record(z6.string(), z6.string()).optional(),
-  ambiguousAliases: z6.record(z6.string(), z6.array(z6.string())).optional(),
-  suggestions: z6.record(z6.string(), z6.array(SuggestionEntrySchema)).optional(),
-  missingDiagnostics: z6.record(z6.string(), MissingModelDiagnosticSchema).optional()
+  missingIds: z7.array(z7.string()).optional(),
+  resolvedAliases: z7.record(z7.string(), z7.string()).optional(),
+  ambiguousAliases: z7.record(z7.string(), z7.array(z7.string())).optional(),
+  suggestions: z7.record(z7.string(), z7.array(SuggestionEntrySchema)).optional(),
+  missingDiagnostics: z7.record(z7.string(), MissingModelDiagnosticSchema).optional()
 };
-var TestDryRunResponseSchema = z6.object({
-  dryRun: z6.literal(true),
-  results: z6.array(TestEstimateResultSchema),
-  disclaimer: z6.string(),
+var TestDryRunResponseSchema = z7.object({
+  dryRun: z7.literal(true),
+  results: z7.array(TestEstimateResultSchema),
+  disclaimer: z7.string(),
   ...TestResolutionFieldsSchema
 });
-var TestLiveResponseSchema = z6.object({
-  results: z6.array(TestResultSchema),
+var TestLiveResponseSchema = z7.object({
+  results: z7.array(TestResultSchema),
   ...TestResolutionFieldsSchema
 });
-var TestResponseSchema = z6.union([TestDryRunResponseSchema, TestLiveResponseSchema]);
+var TestResponseSchema = z7.union([TestDryRunResponseSchema, TestLiveResponseSchema]);
 
 // src/server.ts
 import { McpServer } from "@modelcontextprotocol/sdk/server/mcp.js";
-import { z as z7 } from "zod";
+import { z as z8 } from "zod";
 
 // src/config.ts
 var DEFAULT_BASE_URL = "https://index9.dev";
@@ -1230,22 +1203,22 @@ async function createServer() {
       title: TOOLS.find_models.title,
       description: TOOLS.find_models.description,
       inputSchema: {
-        q: z7.string().min(1).optional().describe(PARAM_DESCRIPTIONS.q),
-        limit: z7.number().int().min(1).max(100).default(20).describe("Page size (1-100, default 20)."),
-        cursor: z7.string().min(1).optional().describe(PARAM_DESCRIPTIONS.cursor),
-        sortBy: z7.enum(["relevance", "created", "price"]).default("relevance").describe(PARAM_DESCRIPTIONS.sortBy),
-        sortOrder: z7.enum(["asc", "desc"]).optional().describe("Sort order. Defaults by sortBy."),
-        createdAfter: z7.string().optional().describe("Lower bound for model created timestamp."),
-        createdBefore: z7.string().optional().describe("Upper bound for model created timestamp."),
-        minPrice: z7.number().min(0).optional().describe(PARAM_DESCRIPTIONS.minPrice),
-        maxPrice: z7.number().min(0).optional().describe(PARAM_DESCRIPTIONS.maxPrice),
-        minContext: z7.number().int().min(1).optional().describe("Minimum context window in tokens."),
-        capabilitiesAll: z7.array(z7.enum(CAPABILITIES)).optional().describe(PARAM_DESCRIPTIONS.capabilitiesAll),
-        capabilitiesAny: z7.array(z7.enum(CAPABILITIES)).optional().describe(PARAM_DESCRIPTIONS.capabilitiesAny),
-        modality: z7.enum(OUTPUT_MODALITIES).optional().describe(PARAM_DESCRIPTIONS.modality),
-        provider: z7.array(z7.string().min(1)).optional().describe(PARAM_DESCRIPTIONS.provider),
-        excludeFree: z7.boolean().optional().describe(PARAM_DESCRIPTIONS.excludeFree),
-        requireKeywordMatch: z7.boolean().optional().describe(PARAM_DESCRIPTIONS.requireKeywordMatch)
+        q: z8.string().min(1).optional().describe(PARAM_DESCRIPTIONS.q),
+        limit: z8.number().int().min(1).max(100).default(20).describe("Page size (1-100, default 20)."),
+        cursor: z8.string().min(1).optional().describe(PARAM_DESCRIPTIONS.cursor),
+        sortBy: z8.enum(["relevance", "created", "price"]).default("relevance").describe(PARAM_DESCRIPTIONS.sortBy),
+        sortOrder: z8.enum(["asc", "desc"]).optional().describe("Sort order. Defaults by sortBy."),
+        createdAfter: z8.string().optional().describe("Lower bound for model created timestamp."),
+        createdBefore: z8.string().optional().describe("Upper bound for model created timestamp."),
+        minPrice: z8.number().min(0).optional().describe(PARAM_DESCRIPTIONS.minPrice),
+        maxPrice: z8.number().min(0).optional().describe(PARAM_DESCRIPTIONS.maxPrice),
+        minContext: z8.number().int().min(1).optional().describe("Minimum context window in tokens."),
+        capabilitiesAll: z8.array(z8.enum(CAPABILITIES)).optional().describe(PARAM_DESCRIPTIONS.capabilitiesAll),
+        capabilitiesAny: z8.array(z8.enum(CAPABILITIES)).optional().describe(PARAM_DESCRIPTIONS.capabilitiesAny),
+        modality: z8.enum(OUTPUT_MODALITIES).optional().describe(PARAM_DESCRIPTIONS.modality),
+        provider: z8.array(z8.string().min(1)).optional().describe(PARAM_DESCRIPTIONS.provider),
+        excludeFree: z8.boolean().optional().describe(PARAM_DESCRIPTIONS.excludeFree),
+        requireKeywordMatch: z8.boolean().optional().describe(PARAM_DESCRIPTIONS.requireKeywordMatch)
       },
       outputSchema: FindModelsToolResultSchema.shape,
       annotations: { readOnlyHint: true }
@@ -1258,8 +1231,8 @@ async function createServer() {
       title: TOOLS.get_models.title,
       description: TOOLS.get_models.description,
       inputSchema: {
-        ids: z7.array(z7.string().min(1)).min(1).max(100).describe("Model identifiers or aliases. Up to 100."),
-        maxDescriptionChars: z7.number().int().min(0).max(2e3).optional().describe("Truncate descriptions to this many characters.")
+        ids: z8.array(z8.string().min(1)).min(1).max(100).describe("Model identifiers or aliases. Up to 100."),
+        maxDescriptionChars: z8.number().int().min(0).max(2e3).optional().describe("Truncate descriptions to this many characters.")
       },
       outputSchema: GetModelsToolResultSchema.shape,
       annotations: { readOnlyHint: true }
@@ -1272,13 +1245,13 @@ async function createServer() {
       title: TOOLS.compare_models.title,
       description: TOOLS.compare_models.description,
       inputSchema: {
-        ids: z7.array(z7.string().min(1)).min(2).max(LIMITS.compareModelsMax).describe(
+        ids: z8.array(z8.string().min(1)).min(2).max(LIMITS.compareModelsMax).describe(
           `Model identifiers or aliases to compare (2-${LIMITS.compareModelsMax}). Same alias formats as get_models.`
         ),
-        expectedPromptTokens: z7.number().int().min(1).optional().describe(
+        expectedPromptTokens: z8.number().int().min(1).optional().describe(
           "Optional. When set with expectedCompletionTokens, computes total per-call cost for each model and picks cheapestForRealisticWorkload \u2014 closes the gap where promptPerMillion alone misleads when prompt:completion price ratios diverge."
         ),
-        expectedCompletionTokens: z7.number().int().min(1).optional().describe(
+        expectedCompletionTokens: z8.number().int().min(1).optional().describe(
           "Optional. Pair with expectedPromptTokens to surface workloadCosts and cheapestForRealisticWorkload. Both must be set to enable workload costing."
         )
       },
@@ -1304,39 +1277,39 @@ async function createServer() {
       title: TOOLS.test_model.title,
       description: TOOLS.test_model.description,
       inputSchema: {
-        prompt: z7.string().min(1).optional().describe("Prompt sent to each model."),
-        userContent: z7.array(UserContentPartSchema).min(1).optional().describe("Multimodal user content. At least one of prompt or userContent required."),
-        dryRun: z7.boolean().optional().describe(
+        prompt: z8.string().min(1).optional().describe("Prompt sent to each model."),
+        userContent: z8.array(UserContentPartSchema).min(1).optional().describe("Multimodal user content. At least one of prompt or userContent required."),
+        dryRun: z8.boolean().optional().describe(
           "When true, returns estimated token usage and cost without calling OpenRouter (no API key required)."
         ),
-        expectedPromptTokens: z7.number().int().min(1).optional().describe(PARAM_DESCRIPTIONS.expectedPromptTokens),
-        expectedCompletionTokens: z7.number().int().min(1).optional().describe(PARAM_DESCRIPTIONS.expectedCompletionTokens),
-        models: z7.array(z7.string().min(1)).min(1).max(LIMITS.testModelsMax).describe(`Model IDs to evaluate (1-${LIMITS.testModelsMax}).`),
-        timeoutMs: z7.number().int().min(1).optional().describe("Per-model timeout in ms (default 15000, max 60000)."),
-        maxTokens: z7.number().int().min(1).optional().describe(
+        expectedPromptTokens: z8.number().int().min(1).optional().describe(PARAM_DESCRIPTIONS.expectedPromptTokens),
+        expectedCompletionTokens: z8.number().int().min(1).optional().describe(PARAM_DESCRIPTIONS.expectedCompletionTokens),
+        models: z8.array(z8.string().min(1)).min(1).max(LIMITS.testModelsMax).describe(`Model IDs to evaluate (1-${LIMITS.testModelsMax}).`),
+        timeoutMs: z8.number().int().min(1).optional().describe("Per-model timeout in ms (default 15000, max 60000)."),
+        maxTokens: z8.number().int().min(1).optional().describe(
           "Completion token cap. For reasoning-capable models, set \u2265 2000 (or omit) \u2014 reasoning tokens count against this before visible output, and too-low caps cause finish_reason=length."
         ),
-        systemPrompt: z7.string().min(1).optional().describe("System instruction prepended to prompt."),
-        temperature: z7.number().min(0).max(2).optional().describe("Sampling temperature (0-2)."),
-        topP: z7.number().gt(0).max(1).optional().describe("Nucleus sampling (0-1]."),
-        seed: z7.number().int().optional().describe("Seed for repeatable outputs."),
+        systemPrompt: z8.string().min(1).optional().describe("System instruction prepended to prompt."),
+        temperature: z8.number().min(0).max(2).optional().describe("Sampling temperature (0-2)."),
+        topP: z8.number().gt(0).max(1).optional().describe("Nucleus sampling (0-1]."),
+        seed: z8.number().int().optional().describe("Seed for repeatable outputs."),
         responseFormat: ResponseFormatSchema.describe(
           "Structured output shape request forwarded to OpenRouter (e.g., { type: 'json_object' })."
         ),
-        enforceJson: z7.boolean().optional().describe("When true, output must parse as JSON."),
-        retries: z7.number().int().min(0).max(3).optional().describe("Retries for transient failures."),
-        stream: z7.boolean().optional().describe(
+        enforceJson: z8.boolean().optional().describe("When true, output must parse as JSON."),
+        retries: z8.number().int().min(0).max(3).optional().describe("Retries for transient failures."),
+        stream: z8.boolean().optional().describe(
           "Use OpenRouter SSE streaming so capacity/refusal errors surface quickly. Defaults to false."
         ),
-        firstTokenTimeoutMs: z7.number().int().min(1).optional().describe("Streaming-only first-token deadline in ms. Defaults to 10000."),
+        firstTokenTimeoutMs: z8.number().int().min(1).optional().describe("Streaming-only first-token deadline in ms. Defaults to 10000."),
         providerSort: ProviderSortSchema.optional().describe(
           'OpenRouter provider routing sort: "throughput", "price", or "latency".'
         ),
-        providerOrder: z7.array(z7.string().min(1)).min(1).max(8).optional().describe("Provider slugs to try first, in order. Up to 8."),
-        fallbackModels: z7.array(z7.string().min(1)).min(1).max(5).optional().describe(
+        providerOrder: z8.array(z8.string().min(1)).min(1).max(8).optional().describe("Provider slugs to try first, in order. Up to 8."),
+        fallbackModels: z8.array(z8.string().min(1)).min(1).max(5).optional().describe(
           "Fallback model IDs OpenRouter may try if the primary is unavailable. Up to 5."
         ),
-        debug: z7.boolean().optional().describe(
+        debug: z8.boolean().optional().describe(
           "When true, include upstream finish_reason, provider, error, refusal, and usage."
         )
       },

package/manifest.json

@@ -1,7 +1,7 @@
 {
   "manifest_version": "0.3",
   "name": "index9",
-  "version": "6.5.3",
+  "version": "6.5.4",
   "description": "Discover, shortlist, compare, cost-model, and live-test 300+ AI models from your editor",
   "author": {
     "name": "Index9"

package/package.json

@@ -1,6 +1,6 @@
 {
   "name": "@index9/mcp",
-  "version": "6.5.3",
+  "version": "6.5.4",
   "description": "Discover, shortlist, compare, cost-model, and live-test 300+ AI models from your editor",
   "license": "MIT",
   "repository": {

package/server.json

@@ -7,13 +7,13 @@
     "url": "https://github.com/index9-org/mcp",
     "source": "github"
   },
-  "version": "6.5.3",
+  "version": "6.5.4",
   "packages": [
     {
       "registryType": "npm",
       "registryBaseUrl": "https://registry.npmjs.org",
       "identifier": "@index9/mcp",
-      "version": "6.5.3",
+      "version": "6.5.4",
       "transport": {
         "type": "stdio"
       },