@molecule/api-resource-ai-models 1.2.6 → 1.2.7

package/README.md

@@ -3,7 +3,7 @@ AUTO-GENERATED — DO NOT EDIT THIS FILE.
 Generated by `mlcl sync-docs` from the package's src/index.ts JSDoc + mlcl/registry.json.
 Edits here are overwritten on the next commit (molecule's pre-commit hook regenerates).
 To change this document, edit the module-level JSDoc in src/index.ts.
-Generated: 2026-08-27T00:37:24.634Z
+Generated: 2026-08-28T08:14:50.991Z
 -->
 
 # @molecule/api-resource-ai-models
@@ -728,6 +728,16 @@ All available AI models, grouped by provider, ordered from most to least capable
 To add or remove a model, edit this array. Both the server-side validation
 and the public discovery endpoint will update automatically.
 
+EVERY entry field that shapes the outbound request (`webSearchToolType`,
+`supportedEffortLevels`/`defaultEffortLevel`/`effortBudgetTokens`,
+`maxOutputTokens`, `regions`) must hold for the model's ACTUAL serving
+host(s) in every region — not just look right in a docs table. The
+pre-commit hook enforces this with a LIVE Synthase-shaped probe of each
+added/changed entry (molecule-dev `verify:model-dispatch --staged-catalog`);
+a value the host rejects fails the whole request for every user
+(glm-5.3-flash 2026-08-28: a `webSearchToolType` both zhipu hosts reject
+made every Synthase turn 400/422 while the model itself worked fine).
+
 Effort is each model's OWN native value — there is no abstract scale (see
 {@link ModelDefinition.supportedEffortLevels}):
 

package/dist/models.d.ts

@@ -14,6 +14,16 @@ import type { ModelDefinition } from './types.js';
  * To add or remove a model, edit this array. Both the server-side validation
  * and the public discovery endpoint will update automatically.
  *
+ * EVERY entry field that shapes the outbound request (`webSearchToolType`,
+ * `supportedEffortLevels`/`defaultEffortLevel`/`effortBudgetTokens`,
+ * `maxOutputTokens`, `regions`) must hold for the model's ACTUAL serving
+ * host(s) in every region — not just look right in a docs table. The
+ * pre-commit hook enforces this with a LIVE Synthase-shaped probe of each
+ * added/changed entry (molecule-dev `verify:model-dispatch --staged-catalog`);
+ * a value the host rejects fails the whole request for every user
+ * (glm-5.3-flash 2026-08-28: a `webSearchToolType` both zhipu hosts reject
+ * made every Synthase turn 400/422 while the model itself worked fine).
+ *
  * Effort is each model's OWN native value — there is no abstract scale (see
  * {@link ModelDefinition.supportedEffortLevels}):
  * - A model driven by a provider-native effort/level param lists its provider

package/dist/models.d.ts.map

@@ -1 +1 @@
-{"version":3,"file":"models.d.ts","sourceRoot":"","sources":["../src/models.ts"],"names":[],"mappings":"AAAA;;;;;;;;GAQG;AAEH,OAAO,KAAK,EAAE,eAAe,EAAE,MAAM,YAAY,CAAA;AAEjD;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;GAyIG;AACH,eAAO,MAAM,MAAM,EAAE,SAAS,eAAe,EAm/CnC,CAAA"}
+{"version":3,"file":"models.d.ts","sourceRoot":"","sources":["../src/models.ts"],"names":[],"mappings":"AAAA;;;;;;;;GAQG;AAEH,OAAO,KAAK,EAAE,eAAe,EAAE,MAAM,YAAY,CAAA;AAEjD;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;GAmJG;AACH,eAAO,MAAM,MAAM,EAAE,SAAS,eAAe,EAsjDnC,CAAA"}

package/dist/models.js

@@ -13,6 +13,16 @@
  * To add or remove a model, edit this array. Both the server-side validation
  * and the public discovery endpoint will update automatically.
  *
+ * EVERY entry field that shapes the outbound request (`webSearchToolType`,
+ * `supportedEffortLevels`/`defaultEffortLevel`/`effortBudgetTokens`,
+ * `maxOutputTokens`, `regions`) must hold for the model's ACTUAL serving
+ * host(s) in every region — not just look right in a docs table. The
+ * pre-commit hook enforces this with a LIVE Synthase-shaped probe of each
+ * added/changed entry (molecule-dev `verify:model-dispatch --staged-catalog`);
+ * a value the host rejects fails the whole request for every user
+ * (glm-5.3-flash 2026-08-28: a `webSearchToolType` both zhipu hosts reject
+ * made every Synthase turn 400/422 while the model itself worked fine).
+ *
  * Effort is each model's OWN native value — there is no abstract scale (see
  * {@link ModelDefinition.supportedEffortLevels}):
  * - A model driven by a provider-native effort/level param lists its provider
@@ -174,7 +184,11 @@ export const MODELS = [
         supportsPromptCaching: true,
         supportsTools: true,
         webSearchToolType: 'web_search_20260209',
-        codeExecutionToolType: 'code_execution_20250825',
+        // Current server-tool type per the API reference (verified 2026-08-28);
+        // 'code_execution_20250825' was the BETA HEADER date (code-execution-2025-08-25),
+        // not a tool type — sending it as one is a 400. Not currently sent by
+        // Synthase (request-shape.ts forwards only webSearchToolType).
+        codeExecutionToolType: 'code_execution_20260521',
         webFetchToolType: 'web_fetch_20260209',
         inputPricePerMTok: 10,
         outputPricePerMTok: 50,
@@ -214,7 +228,11 @@ export const MODELS = [
         supportsPromptCaching: true,
         supportsTools: true,
         webSearchToolType: 'web_search_20260209',
-        codeExecutionToolType: 'code_execution_20250825',
+        // Current server-tool type per the API reference (verified 2026-08-28);
+        // 'code_execution_20250825' was the BETA HEADER date (code-execution-2025-08-25),
+        // not a tool type — sending it as one is a 400. Not currently sent by
+        // Synthase (request-shape.ts forwards only webSearchToolType).
+        codeExecutionToolType: 'code_execution_20260521',
         webFetchToolType: 'web_fetch_20260209',
         // Drop-in successor to Opus 4.8 at identical pricing.
         inputPricePerMTok: 5,
@@ -243,7 +261,11 @@ export const MODELS = [
         supportsPromptCaching: true,
         supportsTools: true,
         webSearchToolType: 'web_search_20260209',
-        codeExecutionToolType: 'code_execution_20250825',
+        // Current server-tool type per the API reference (verified 2026-08-28);
+        // 'code_execution_20250825' was the BETA HEADER date (code-execution-2025-08-25),
+        // not a tool type — sending it as one is a 400. Not currently sent by
+        // Synthase (request-shape.ts forwards only webSearchToolType).
+        codeExecutionToolType: 'code_execution_20260521',
         webFetchToolType: 'web_fetch_20260209',
         inputPricePerMTok: 5,
         outputPricePerMTok: 25,
@@ -276,7 +298,11 @@ export const MODELS = [
         supportsPromptCaching: true,
         supportsTools: true,
         webSearchToolType: 'web_search_20260209',
-        codeExecutionToolType: 'code_execution_20250825',
+        // Current server-tool type per the API reference (verified 2026-08-28);
+        // 'code_execution_20250825' was the BETA HEADER date (code-execution-2025-08-25),
+        // not a tool type — sending it as one is a 400. Not currently sent by
+        // Synthase (request-shape.ts forwards only webSearchToolType).
+        codeExecutionToolType: 'code_execution_20260521',
         webFetchToolType: 'web_fetch_20260209',
         // Standard pricing. Intro pricing ($2/$10) applies through 2026-08-31 —
         // billed here at standard so metering never under-charges; revisit after.
@@ -307,7 +333,11 @@ export const MODELS = [
         supportsPromptCaching: true,
         supportsTools: true,
         webSearchToolType: 'web_search_20260209',
-        codeExecutionToolType: 'code_execution_20250825',
+        // Current server-tool type per the API reference (verified 2026-08-28);
+        // 'code_execution_20250825' was the BETA HEADER date (code-execution-2025-08-25),
+        // not a tool type — sending it as one is a 400. Not currently sent by
+        // Synthase (request-shape.ts forwards only webSearchToolType).
+        codeExecutionToolType: 'code_execution_20260521',
         webFetchToolType: 'web_fetch_20260209',
         inputPricePerMTok: 5,
         outputPricePerMTok: 25,
@@ -342,7 +372,11 @@ export const MODELS = [
         supportsPromptCaching: true,
         supportsTools: true,
         webSearchToolType: 'web_search_20260209',
-        codeExecutionToolType: 'code_execution_20250825',
+        // Current server-tool type per the API reference (verified 2026-08-28);
+        // 'code_execution_20250825' was the BETA HEADER date (code-execution-2025-08-25),
+        // not a tool type — sending it as one is a 400. Not currently sent by
+        // Synthase (request-shape.ts forwards only webSearchToolType).
+        codeExecutionToolType: 'code_execution_20260521',
         webFetchToolType: 'web_fetch_20260209',
         inputPricePerMTok: 5,
         outputPricePerMTok: 25,
@@ -373,7 +407,11 @@ export const MODELS = [
         supportsPromptCaching: true,
         supportsTools: true,
         webSearchToolType: 'web_search_20260209',
-        codeExecutionToolType: 'code_execution_20250825',
+        // Current server-tool type per the API reference (verified 2026-08-28);
+        // 'code_execution_20250825' was the BETA HEADER date (code-execution-2025-08-25),
+        // not a tool type — sending it as one is a 400. Not currently sent by
+        // Synthase (request-shape.ts forwards only webSearchToolType).
+        codeExecutionToolType: 'code_execution_20260521',
         webFetchToolType: 'web_fetch_20260209',
         inputPricePerMTok: 3,
         outputPricePerMTok: 15,
@@ -446,7 +484,11 @@ export const MODELS = [
         supportsTools: true,
         // Tools + ANY reasoning is a 400 on /v1/chat/completions for this family.
         toolsRequireReasoningOff: true,
-        webSearchToolType: 'web_search',
+        // NO webSearchToolType: the OpenAI bond calls /v1/chat/completions, which
+        // has no web_search tool type (it is a Responses-API construct), and the
+        // bond deliberately forwards no server tools. Advertising one here surfaced
+        // web search in the system prompt while it could never work. Re-add when
+        // the bond moves to /v1/responses (verified 2026-08-28).
         codeExecutionToolType: 'code_interpreter',
         // LIST price. OpenAI ran a >20% PROMO from 2026-08-22 ($4/$20, cache read
         // $0.40, cache write $5) — "GPT-5.6 Sol's promotional pricing is available
@@ -479,7 +521,11 @@ export const MODELS = [
         supportsTools: true,
         // Tools + ANY reasoning is a 400 on /v1/chat/completions for this family.
         toolsRequireReasoningOff: true,
-        webSearchToolType: 'web_search',
+        // NO webSearchToolType: the OpenAI bond calls /v1/chat/completions, which
+        // has no web_search tool type (it is a Responses-API construct), and the
+        // bond deliberately forwards no server tools. Advertising one here surfaced
+        // web search in the system prompt while it could never work. Re-add when
+        // the bond moves to /v1/responses (verified 2026-08-28).
         codeExecutionToolType: 'code_interpreter',
         // Repriced 2026-07-30 (20% cut from $2.50/$15).
         inputPricePerMTok: 2,
@@ -507,7 +553,11 @@ export const MODELS = [
         supportsTools: true,
         // Tools + ANY reasoning is a 400 on /v1/chat/completions for this family.
         toolsRequireReasoningOff: true,
-        webSearchToolType: 'web_search',
+        // NO webSearchToolType: the OpenAI bond calls /v1/chat/completions, which
+        // has no web_search tool type (it is a Responses-API construct), and the
+        // bond deliberately forwards no server tools. Advertising one here surfaced
+        // web search in the system prompt while it could never work. Re-add when
+        // the bond moves to /v1/responses (verified 2026-08-28).
         codeExecutionToolType: 'code_interpreter',
         // Repriced 2026-07-30 (80% cut from $1/$6).
         inputPricePerMTok: 0.2,
@@ -542,7 +592,11 @@ export const MODELS = [
         supportsTools: true,
         // Tools + ANY reasoning is a 400 on /v1/chat/completions for this family.
         toolsRequireReasoningOff: true,
-        webSearchToolType: 'web_search',
+        // NO webSearchToolType: the OpenAI bond calls /v1/chat/completions, which
+        // has no web_search tool type (it is a Responses-API construct), and the
+        // bond deliberately forwards no server tools. Advertising one here surfaced
+        // web search in the system prompt while it could never work. Re-add when
+        // the bond moves to /v1/responses (verified 2026-08-28).
         codeExecutionToolType: 'code_interpreter',
         inputPricePerMTok: 5,
         outputPricePerMTok: 30,
@@ -572,7 +626,11 @@ export const MODELS = [
         supportsTools: true,
         // Tools + ANY reasoning is a 400 on /v1/chat/completions for this family.
         toolsRequireReasoningOff: true,
-        webSearchToolType: 'web_search',
+        // NO webSearchToolType: the OpenAI bond calls /v1/chat/completions, which
+        // has no web_search tool type (it is a Responses-API construct), and the
+        // bond deliberately forwards no server tools. Advertising one here surfaced
+        // web search in the system prompt while it could never work. Re-add when
+        // the bond moves to /v1/responses (verified 2026-08-28).
         codeExecutionToolType: 'code_interpreter',
         inputPricePerMTok: 2.5,
         outputPricePerMTok: 15,
@@ -604,7 +662,11 @@ export const MODELS = [
         supportsTools: true,
         // Tools + ANY reasoning is a 400 on /v1/chat/completions for this family.
         toolsRequireReasoningOff: true,
-        webSearchToolType: 'web_search',
+        // NO webSearchToolType: the OpenAI bond calls /v1/chat/completions, which
+        // has no web_search tool type (it is a Responses-API construct), and the
+        // bond deliberately forwards no server tools. Advertising one here surfaced
+        // web search in the system prompt while it could never work. Re-add when
+        // the bond moves to /v1/responses (verified 2026-08-28).
         codeExecutionToolType: 'code_interpreter',
         inputPricePerMTok: 0.75,
         outputPricePerMTok: 4.5,
@@ -1583,6 +1645,11 @@ export const MODELS = [
         // US default: DeepInfra (zai-org/GLM-5.3-Flash) bills exactly the list
         // card — $0.15/$0.50, cache read 0.2× = $0.03. Verified live 2026-08-27.
         regions: ['us', 'cn'],
+        // NB: DeepInfra returns NO cached-token usage (verified live 2026-08-28:
+        // an identical ~2.6k-token prefix twice reported full input both passes,
+        // no prompt_tokens_details) — the us cacheRead rate below is informational
+        // only; metering always bills full input there. Native z.ai reports and
+        // discounts cached tokens correctly.
         regionPricing: {
             us: { inputPricePerMTok: 0.15, outputPricePerMTok: 0.5, cacheReadPricePerMTok: 0.03 },
         },
@@ -1614,6 +1681,11 @@ export const MODELS = [
         cacheWritePricePerMTok: 1.4,
         // US default (DeepInfra bills ~half native). Verified 2026-08-01.
         regions: ['us', 'cn'],
+        // NB: DeepInfra returns NO cached-token usage (verified live 2026-08-28:
+        // an identical ~2.6k-token prefix twice reported full input both passes,
+        // no prompt_tokens_details) — the us cacheRead rate below is informational
+        // only; metering always bills full input there. Native z.ai reports and
+        // discounts cached tokens correctly.
         regionPricing: {
             us: { inputPricePerMTok: 0.75, outputPricePerMTok: 2.4, cacheReadPricePerMTok: 0.14 },
         },
@@ -1650,6 +1722,11 @@ export const MODELS = [
         cacheWritePricePerMTok: 1,
         // US default (DeepInfra bills below native). Verified 2026-08-01.
         regions: ['us', 'cn'],
+        // NB: DeepInfra returns NO cached-token usage (verified live 2026-08-28:
+        // an identical ~2.6k-token prefix twice reported full input both passes,
+        // no prompt_tokens_details) — the us cacheRead rate below is informational
+        // only; metering always bills full input there. Native z.ai reports and
+        // discounts cached tokens correctly.
         regionPricing: {
             us: { inputPricePerMTok: 0.6, outputPricePerMTok: 2.08, cacheReadPricePerMTok: 0.12 },
         },

package/package.json

@@ -1,6 +1,6 @@
 {
   "name": "@molecule/api-resource-ai-models",
-  "version": "1.2.6",
+  "version": "1.2.7",
   "description": "AI model catalog — server-side source of truth plus an authentication-gated discovery endpoint",
   "type": "module",
   "main": "dist/index.js",