@index9/mcp 6.0.0 → 6.1.0

package/dist/cli.js

@@ -43,6 +43,11 @@ var Index9MetaSchema = z.object({
   retryAfterSeconds: z.number().optional(),
   rateLimit: RateLimitMetaSchema.optional()
 });
+var MissingModelDiagnosticSchema = z.object({
+  reason: z.enum(["unknown_provider", "no_match", "suggestions_available", "ambiguous_alias"]),
+  provider: z.string().optional(),
+  message: z.string()
+});
 var UserContentTextPartSchema = z.strictObject({
   type: z.literal("text"),
   text: z.string().trim().min(1)
@@ -101,8 +106,9 @@ Typical workflow:
 Key rules:
 - find_models requires \`q\` when \`sortBy=relevance\` (the default). Omit \`q\` only with \`sortBy=created\` or \`sortBy=price\`.
 - find_models price-asc tends to be dominated by free preview models \u2014 pass \`excludeFree=true\` when you want a paid SLA.
-- find_models flags \`meta.confidence: "low"\` when no candidate matched on keyword (BM25). When that fires, prefer \`meta.suggestion\` over the returned scores; weak hits are capped at score=30 so they don't masquerade as strong matches.
-- get_models accepts aliases (display names, short names) \u2014 not just full IDs. Unknown ids return in missingIds with \`suggestions\` (token-fuzzy or recency-anchored newest-from-provider). Retry with one of the suggested ids.
+- find_models always emits \`meta.confidence\` ("high" | "low") on semantic queries. Low means no candidate matched on keyword (BM25); \`meta.lowConfidenceReason\` is "no_keyword_matches" or "no_results" and \`meta.suggestion\` carries an actionable hint. Weak hits are capped at score=30 so they don't masquerade as strong matches. Pass \`requireKeywordMatch: true\` to get an empty page instead of weak vector-only neighbors.
+- find_models with sortBy=price exposes \`pricing.effectivePromptPerMillion\` and \`pageInfo.priceSortBasis\` \u2014 sort order may diverge from displayed promptPerMillion for models with per-request fees.
+- get_models accepts aliases (display names, short names) \u2014 not just full IDs. Unknown ids return in missingIds with \`suggestions\` (token-fuzzy or recency-anchored newest-from-provider) and \`missingDiagnostics\` keyed by id with \`reason\` ("unknown_provider" | "no_match" | "suggestions_available" | "ambiguous_alias") so retry strategy is explicit. Retry with one of the suggested ids.
 - compare_models accepts the same alias formats as get_models. Use it instead of N parallel get_models calls when the user is comparing finalists.
 - Use test_model with \`dryRun=true\` to estimate cost before live testing. Pass \`expectedPromptTokens\` for capacity planning at sizes you don't want to paste in full.
 - test_model with \`dryRun=false\` (default) requires OPENROUTER_API_KEY and incurs real usage costs.
@@ -129,11 +135,11 @@ Examples:
 
 Valid capabilities: ${CAPABILITIES.join(", ")}.
 
-Each result: id, name, description, created (unix seconds), createdAt (ISO 8601), contextLength, maxOutputTokens, pricing.{promptPerMillion, completionPerMillion} (numbers, USD per million tokens), inputModalities[] / outputModalities[] (e.g. ["text","image"] \u2014 check at a glance to spot text-only vs multimodal models), capabilities[], score.
+Each result: id, name, description, created (unix seconds), createdAt (ISO 8601), contextLength, maxOutputTokens, pricing.{promptPerMillion, completionPerMillion} (rounded display $/M), pricing.{promptPerToken, completionPerToken, requestUsd} (exact, use for cost math), inputModalities[] / outputModalities[], capabilities[], score. With sortBy=price, results also expose pricing.effectivePromptPerMillion and pageInfo.priceSortBasis \u2014 sort order may diverge from displayed promptPerMillion for models with per-request fees.
 
 \`score\` is 0-100: the best match per page scores 100; others scale proportionally. Combines semantic similarity and keyword matching. Null when sorting by price or date.
 
-\`q\` must be at least 2 characters when provided. \`meta.confidence\` is "low" when no candidate matched on keyword (BM25), meaning the ranker fell back to vector similarity alone \u2014 typo, gibberish, or a query the catalog can't answer. When low, \`meta.suggestion\` carries an actionable hint and \`score\` values are capped at 30 so weak hits don't masquerade as strong ones.
+\`q\` must be at least 2 characters when provided. For semantic queries, \`meta.confidence\` is always emitted as "high" or "low". Low means no candidate matched on keyword (BM25); \`meta.lowConfidenceReason\` is "no_keyword_matches" or "no_results" and \`meta.suggestion\` carries an actionable hint. Pass \`requireKeywordMatch: true\` to suppress weak hits and get an empty page on low confidence.
 
 Pass result.id to get_models for full specs or to test_model for live testing.`,
     requiresKey: false
@@ -150,12 +156,14 @@ Response: { results: (Model | null)[], missingIds: string[], resolvedAliases?: R
 - id, canonicalSlug, name, description
 - created (unix seconds), createdAt (ISO 8601), knowledgeCutoff (ISO date or null)
 - contextLength (tokens), maxOutputTokens, isModerated
-- pricing: { promptPerMillion, completionPerMillion, requestUsd, imageUsd } \u2014 all USD, all numbers. Token prices are per million tokens; request/image are per unit.
+- pricing: { promptPerMillion, completionPerMillion, promptPerToken, completionPerToken, requestUsd, imageUsd } \u2014 *PerMillion is rounded display, *PerToken is exact (use for cost math). request/image are flat per-unit fees.
 - architecture: { inputModalities[], outputModalities[], tokenizer, instructType }
 - capabilities[]: normalized capability flags (same values as find_models and capabilitiesAll/Any)
 - supportedParameters[]: OpenRouter parameters the model accepts (e.g., "temperature", "tools", "response_format")
 
-Entries in results are null when the id is unknown; those ids appear in missingIds. Ambiguous aliases appear in ambiguousAliases with candidate canonical ids \u2014 pass a canonical id to disambiguate. Unknown ids that partially match (e.g. "sonnet" \u2192 all Claude Sonnet variants) appear in suggestions with up to 5 candidate ids. When token-overlap finds nothing but the id is shaped like \`provider/<unknown>\` and the provider exists, suggestions falls back to the 5 newest models from that provider (real created timestamps, no hardcoded "popular" list). Retry with one of the suggested ids.`,
+Entries in results are null when the id is unknown; those ids appear in missingIds. Ambiguous aliases appear in ambiguousAliases with candidate canonical ids \u2014 pass a canonical id to disambiguate. Unknown ids that partially match (e.g. "sonnet" \u2192 all Claude Sonnet variants) appear in suggestions with up to 5 candidate ids. When token-overlap finds nothing but the id is shaped like \`provider/<unknown>\` and the provider exists, suggestions falls back to the 5 newest models from that provider (real created timestamps, no hardcoded "popular" list). Retry with one of the suggested ids.
+
+\`missingDiagnostics\` (when present) gives a machine-readable reason per missing id: \`unknown_provider\` (the prefix before / isn't in the catalog \u2014 fix the provider, not the model name), \`ambiguous_alias\`, \`suggestions_available\` (mirrors suggestions[id]), or \`no_match\`.`,
     requiresKey: false
   },
   compare_models: {
@@ -170,9 +178,9 @@ Response: { models: ModelResponse[], diff: { contextLength, maxOutputTokens, pro
 
 Each numeric/string diff field has { allEqual: boolean, values: Record<id, value|null> }. Capability/parameter diffs have { commonAll: string[], uniquePerModel: Record<id, string[]> }. cheapestForPromptPerMillion / largestContext are convenience picks across the supplied models \u2014 null when the field is missing on every model.
 
-Optional: pass \`expectedPromptTokens\` AND \`expectedCompletionTokens\` to also receive \`workloadCosts\` (per-model totalCostUsd) and \`cheapestForRealisticWorkload\` \u2014 the actual cheapest given the user's expected token mix. This matters when prompt:completion price ratios diverge across models (e.g., a model with cheap prompt but expensive completion can lose against a flatter-priced sibling under heavy completions).
+Optional: pass \`expectedPromptTokens\` AND \`expectedCompletionTokens\` to also receive \`workloadCosts\` and \`cheapestForRealisticWorkload\` \u2014 the actual cheapest given the user's expected token mix. Each \`workloadCosts[i]\` carries \`tokenCostUsd\` (token-only), \`requestCostUsd\` (per-request fee), \`totalCostUsd\` (sum, includes request fees), and \`pricingBasis\` ("exact_per_token" | "rounded_per_million" | "unavailable"). This matters when prompt:completion price ratios diverge across models, or when a model has a per-request fee.
 
-Accepts the same alias formats as get_models. Unknown ids are returned in missingIds (with suggestions when partial matches exist).`,
+Accepts the same alias formats as get_models. Unknown ids are returned in missingIds (with suggestions when partial matches exist, plus \`missingDiagnostics\` carrying a machine-readable reason per id).`,
     requiresKey: false
   },
   list_facets: {
@@ -206,7 +214,9 @@ Parameters:
 - expectedCompletionTokens: Optional completion token estimate used by dryRun
 - maxTokens, systemPrompt, temperature, topP, seed, responseFormat, enforceJson, retries: Live-testing controls (ignored when dryRun=true)
 
-Results (live): each result carries modelId (the id you passed), resolvedModelId (canonical id, present when the input was an alias), ok, response, latencyMs, tokens { prompt, completion }, cost (USD; live from OpenRouter when available, else estimated from cached pricing), and truncated=true when finish_reason is "length". Use find_models or get_models first to identify model ids.`,
+Results (live): each result carries modelId (the id you passed), resolvedModelId (canonical id, present when the input was an alias), ok, response, latencyMs, tokens { prompt, completion }, cost (USD; live from OpenRouter when available, else estimated from cached pricing), and truncated=true when finish_reason is "length". On failure, results include \`error\` (free-form) plus \`failureReason\` ("insufficient_credits" | "model_unavailable" | "rate_limited" | "timeout" | "invalid_request" | "unknown") so callers can pick a retry strategy without parsing the error string.
+
+Results (dryRun): each entry carries \`tokenCostUsd\`, \`requestCostUsd\`, \`totalCostUsd\` (matches \`estimatedCost\`, includes per-request fees), and \`estimatedCostBasis\` (same enum as compare_models.workloadCosts). Use find_models or get_models first to identify model ids.`,
     requiresKey: true
   }
 };
@@ -219,6 +229,7 @@ var PARAM_DESCRIPTIONS = {
   modality: `Required output modality. Filters on the model's output modalities, not input capabilities. For example, "image" finds image-generation models, while capabilitiesAll=["vision"] finds models that accept image input. Valid values: ${OUTPUT_MODALITIES.join(", ")}.`,
   provider: `Provider prefix filter. Array of provider slugs \u2014 a model matches if its ID starts with any of them (e.g., ['openai'] matches 'openai/gpt-4o'; ['openai','anthropic'] matches both). Pass a single-element array for one provider. Common providers: ${COMMON_PROVIDERS.join(", ")}.`,
   excludeFree: `When true, exclude models with id ending in ':free'. Useful for sortBy=price (which would otherwise be dominated by free-tier preview models) and when you want a paid SLA. Default false.`,
+  requireKeywordMatch: `When true, suppress weak vector-only results from semantic queries. If no candidate has a BM25 keyword hit, returns an empty page with meta.confidence='low' and meta.lowConfidenceReason \u2014 instead of returning misleading nearest-neighbor matches. Filter-only queries (sortBy=created or sortBy=price without q) ignore this flag. Default false.`,
   expectedPromptTokens: `Expected number of prompt tokens for dryRun cost estimation. When set, overrides the heuristic that counts characters from the literal \`prompt\` string \u2014 use this for capacity planning ("what would 6000-token reviews cost?") without pasting filler. If both are omitted, the prompt string is tokenized at ~4 chars/token.`,
   expectedCompletionTokens: `Expected number of completion tokens for cost estimation (default: 256). Typical ranges: 100-500 for quick tests, 1000-2000 for code generation, 4000+ for long-form content. This is a heuristic \u2014 actual billed tokens may differ.`
 };
@@ -556,7 +567,8 @@ var SearchQuerySchema = z2.object({
   capabilitiesAny: z2.array(z2.enum(CAPABILITIES)).optional(),
   modality: z2.enum(OUTPUT_MODALITIES).optional(),
   provider: z2.array(z2.string().min(1)).optional(),
-  excludeFree: z2.boolean().optional()
+  excludeFree: z2.boolean().optional(),
+  requireKeywordMatch: z2.boolean().optional()
 }).strict();
 var SearchResultSchema = z2.object({
   id: z2.string(),
@@ -568,7 +580,11 @@ var SearchResultSchema = z2.object({
   maxOutputTokens: z2.number().nullable(),
   pricing: z2.object({
     promptPerMillion: z2.number().nullable(),
-    completionPerMillion: z2.number().nullable()
+    completionPerMillion: z2.number().nullable(),
+    promptPerToken: z2.number().nullable().optional(),
+    completionPerToken: z2.number().nullable().optional(),
+    requestUsd: z2.number().nullable().optional(),
+    effectivePromptPerMillion: z2.number().nullable().optional()
   }),
   inputModalities: z2.array(z2.string()),
   outputModalities: z2.array(z2.string()),
@@ -582,13 +598,15 @@ var SearchResponseSchema = z2.object({
     limit: z2.number(),
     hasMore: z2.boolean(),
     sortBy: SearchSortBySchema,
-    sortOrder: SearchSortOrderSchema
+    sortOrder: SearchSortOrderSchema,
+    priceSortBasis: z2.literal("effective_prompt_per_million").optional()
   }),
   meta: z2.object({
     queryMode: z2.enum(["semantic", "filter_only"]),
     ranking: z2.literal("hybrid_rrf"),
     confidence: z2.enum(["high", "low"]).optional(),
-    suggestion: z2.string().optional()
+    suggestion: z2.string().optional(),
+    lowConfidenceReason: z2.enum(["no_keyword_matches", "no_results"]).optional()
   })
 });
 var FindModelsToolResultSchema = SearchResponseSchema.extend({
@@ -604,6 +622,8 @@ var BatchModelLookupRequestSchema = z3.object({
 var ModelPricingSchema = z3.object({
   promptPerMillion: z3.number().nullable(),
   completionPerMillion: z3.number().nullable(),
+  promptPerToken: z3.number().nullable().optional(),
+  completionPerToken: z3.number().nullable().optional(),
   requestUsd: z3.number().nullable(),
   imageUsd: z3.number().nullable()
 });
@@ -634,7 +654,8 @@ var BatchModelLookupResponseSchema = z3.object({
   missingIds: z3.array(z3.string()),
   resolvedAliases: z3.record(z3.string(), z3.string()).optional(),
   ambiguousAliases: z3.record(z3.string(), z3.array(z3.string())).optional(),
-  suggestions: z3.record(z3.string(), z3.array(z3.string())).optional()
+  suggestions: z3.record(z3.string(), z3.array(z3.string())).optional(),
+  missingDiagnostics: z3.record(z3.string(), MissingModelDiagnosticSchema).optional()
 }).strict();
 var GetModelsToolResultSchema = z3.object({
   results: z3.array(ModelResponseSchema.nullable()),
@@ -642,11 +663,13 @@ var GetModelsToolResultSchema = z3.object({
   resolvedAliases: z3.record(z3.string(), z3.string()).optional(),
   ambiguousAliases: z3.record(z3.string(), z3.array(z3.string())).optional(),
   suggestions: z3.record(z3.string(), z3.array(z3.string())).optional(),
+  missingDiagnostics: z3.record(z3.string(), MissingModelDiagnosticSchema).optional(),
   _index9: Index9MetaSchema
 });
 
 // ../core/dist/schemas/compare.js
 import { z as z4 } from "zod";
+var PricingBasisSchema = z4.enum(["exact_per_token", "rounded_per_million", "unavailable"]);
 var CompareRequestSchema = z4.object({
   ids: z4.array(z4.string().min(1)).min(2, "compare requires at least 2 ids").max(LIMITS.compareModelsMax, `ids must contain between 2 and ${LIMITS.compareModelsMax} model IDs`),
   expectedPromptTokens: z4.number().int().positive().optional(),
@@ -683,7 +706,10 @@ var CompareWorkloadCostSchema = z4.object({
   modelId: z4.string(),
   promptTokens: z4.number().int().nonnegative(),
   completionTokens: z4.number().int().nonnegative(),
-  totalCostUsd: z4.number().nullable()
+  totalCostUsd: z4.number().nullable(),
+  tokenCostUsd: z4.number().nullable().optional(),
+  requestCostUsd: z4.number().nullable().optional(),
+  pricingBasis: PricingBasisSchema.optional()
 });
 var CompareResponseSchema = z4.object({
   models: z4.array(ModelResponseSchema),
@@ -695,7 +721,8 @@ var CompareResponseSchema = z4.object({
   resolvedAliases: z4.record(z4.string(), z4.string()).optional(),
   missingIds: z4.array(z4.string()),
   suggestions: z4.record(z4.string(), z4.array(z4.string())).optional(),
-  ambiguousAliases: z4.record(z4.string(), z4.array(z4.string())).optional()
+  ambiguousAliases: z4.record(z4.string(), z4.array(z4.string())).optional(),
+  missingDiagnostics: z4.record(z4.string(), MissingModelDiagnosticSchema).optional()
 }).strict();
 var CompareModelsToolResultSchema = CompareResponseSchema.extend({
   _index9: Index9MetaSchema
@@ -770,8 +797,17 @@ var TestPricingUsedSchema = z6.object({
   promptPerToken: z6.number().nullable().optional(),
   completionPerToken: z6.number().nullable().optional(),
   promptPerMillion: z6.number().nullable().optional(),
-  completionPerMillion: z6.number().nullable().optional()
+  completionPerMillion: z6.number().nullable().optional(),
+  requestUsd: z6.number().nullable().optional()
 });
+var TestFailureReasonSchema = z6.enum([
+  "insufficient_credits",
+  "model_unavailable",
+  "rate_limited",
+  "timeout",
+  "invalid_request",
+  "unknown"
+]);
 var TestModelMetadataSchema = z6.object({
   id: z6.string(),
   name: z6.string(),
@@ -796,6 +832,7 @@ var TestResultFailureSchema = z6.object({
   ok: z6.literal(false),
   model: TestModelMetadataSchema,
   error: z6.string(),
+  failureReason: TestFailureReasonSchema.optional(),
   latencyMs: z6.number().min(0)
 });
 var TestResultSchema = z6.discriminatedUnion("ok", [
@@ -807,7 +844,11 @@ var TestEstimateResultSchema = z6.object({
   resolvedModelId: z6.string().optional(),
   model: TestModelMetadataSchema,
   tokens: UsageTokensSchema,
-  estimatedCost: z6.number().nullable().optional()
+  estimatedCost: z6.number().nullable().optional(),
+  tokenCostUsd: z6.number().nullable().optional(),
+  requestCostUsd: z6.number().nullable().optional(),
+  totalCostUsd: z6.number().nullable().optional(),
+  estimatedCostBasis: PricingBasisSchema.optional()
 });
 var TestDryRunResponseSchema = z6.object({
   dryRun: z6.literal(true),
@@ -1005,6 +1046,7 @@ async function handleSearchModels(ctx, args) {
   if (q.modality) params.modality = q.modality;
   if (q.provider?.length) params.provider = q.provider.join(",");
   if (q.excludeFree === true) params.excludeFree = "true";
+  if (q.requireKeywordMatch === true) params.requireKeywordMatch = "true";
   return callApi(
     ctx,
     buildUrl(ctx.baseUrl, API_PATHS.search, params),
@@ -1096,7 +1138,8 @@ async function createServer() {
         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)
+        excludeFree: z7.boolean().optional().describe(PARAM_DESCRIPTIONS.excludeFree),
+        requireKeywordMatch: z7.boolean().optional().describe(PARAM_DESCRIPTIONS.requireKeywordMatch)
       },
       outputSchema: FindModelsToolResultSchema.shape,
       annotations: { readOnlyHint: true }

package/manifest.json

@@ -1,7 +1,7 @@
 {
   "manifest_version": "0.3",
   "name": "index9",
-  "version": "5.3.0",
+  "version": "6.0.0",
   "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": "6.0.0",
+  "version": "6.1.0",
   "license": "MIT",
   "repository": {
     "type": "git",
@@ -28,7 +28,7 @@
     "tsup": "^8.5.1",
     "typescript": "6.0.3",
     "vitest": "^4.1.5",
-    "@index9/core": "2.3.2"
+    "@index9/core": "2.4.0"
   },
   "engines": {
     "node": ">=20"