fix: make schema sanitization provider-specific

src/services/api/openaiSchemaSanitizer.ts

@@ -1,216 +1 @@
-function isSchemaRecord(value: unknown): value is Record<string, unknown> {
-  return value !== null && typeof value === 'object' && !Array.isArray(value)
-}
-
-function deepEqualJsonValue(a: unknown, b: unknown): boolean {
-  if (Object.is(a, b)) return true
-  if (typeof a !== typeof b) return false
-
-  if (Array.isArray(a) && Array.isArray(b)) {
-    return (
-      a.length === b.length &&
-      a.every((value, index) => deepEqualJsonValue(value, b[index]))
-    )
-  }
-
-  if (isSchemaRecord(a) && isSchemaRecord(b)) {
-    const aKeys = Object.keys(a)
-    const bKeys = Object.keys(b)
-    return (
-      aKeys.length === bKeys.length &&
-      aKeys.every(key => key in b && deepEqualJsonValue(a[key], b[key]))
-    )
-  }
-
-  return false
-}
-
-function matchesJsonSchemaType(type: string, value: unknown): boolean {
-  switch (type) {
-    case 'string':
-      return typeof value === 'string'
-    case 'number':
-      return typeof value === 'number' && Number.isFinite(value)
-    case 'integer':
-      return typeof value === 'number' && Number.isInteger(value)
-    case 'boolean':
-      return typeof value === 'boolean'
-    case 'object':
-      return value !== null && typeof value === 'object' && !Array.isArray(value)
-    case 'array':
-      return Array.isArray(value)
-    case 'null':
-      return value === null
-    default:
-      return true
-  }
-}
-
-function getJsonSchemaTypes(record: Record<string, unknown>): string[] {
-  const raw = record.type
-  if (typeof raw === 'string') {
-    return [raw]
-  }
-  if (Array.isArray(raw)) {
-    return raw.filter((value): value is string => typeof value === 'string')
-  }
-  return []
-}
-
-function schemaAllowsValue(schema: Record<string, unknown>, value: unknown): boolean {
-  if (Array.isArray(schema.anyOf)) {
-    return schema.anyOf.some(item =>
-      schemaAllowsValue(sanitizeSchemaForOpenAICompat(item), value),
-    )
-  }
-
-  if (Array.isArray(schema.oneOf)) {
-    return (
-      schema.oneOf.filter(item =>
-        schemaAllowsValue(sanitizeSchemaForOpenAICompat(item), value),
-      ).length === 1
-    )
-  }
-
-  if (Array.isArray(schema.allOf)) {
-    return schema.allOf.every(item =>
-      schemaAllowsValue(sanitizeSchemaForOpenAICompat(item), value),
-    )
-  }
-
-  if ('const' in schema && !deepEqualJsonValue(schema.const, value)) {
-    return false
-  }
-
-  if (Array.isArray(schema.enum)) {
-    if (!schema.enum.some(item => deepEqualJsonValue(item, value))) {
-      return false
-    }
-  }
-
-  const types = getJsonSchemaTypes(schema)
-  if (types.length > 0 && !types.some(type => matchesJsonSchemaType(type, value))) {
-    return false
-  }
-
-  return true
-}
-
-function sanitizeTypeField(record: Record<string, unknown>): void {
-  const allowed = new Set([
-    'string',
-    'number',
-    'integer',
-    'boolean',
-    'object',
-    'array',
-    'null',
-  ])
-
-  const raw = record.type
-  if (typeof raw === 'string') {
-    if (!allowed.has(raw)) delete record.type
-    return
-  }
-
-  if (!Array.isArray(raw)) return
-
-  const filtered = raw.filter(
-    (value, index): value is string =>
-      typeof value === 'string' &&
-      allowed.has(value) &&
-      raw.indexOf(value) === index,
-  )
-
-  if (filtered.length === 0) {
-    delete record.type
-  } else if (filtered.length === 1) {
-    record.type = filtered[0]
-  } else {
-    record.type = filtered
-  }
-}
-
-/**
- * Sanitize loose/invalid JSON Schema into a form OpenAI-compatible providers
- * are more likely to accept. This is intentionally defensive for external MCP
- * servers that may advertise imperfect schemas.
- */
-export function sanitizeSchemaForOpenAICompat(
-  schema: unknown,
-): Record<string, unknown> {
-  if (!isSchemaRecord(schema)) {
-    return {}
-  }
-
-  const record = { ...schema }
-
-  delete record.$schema
-  delete record.propertyNames
-
-  sanitizeTypeField(record)
-
-  if (isSchemaRecord(record.properties)) {
-    const sanitizedProps: Record<string, unknown> = {}
-    for (const [key, value] of Object.entries(record.properties)) {
-      sanitizedProps[key] = sanitizeSchemaForOpenAICompat(value)
-    }
-    record.properties = sanitizedProps
-  }
-
-  if ('items' in record) {
-    if (Array.isArray(record.items)) {
-      record.items = record.items.map(item =>
-        sanitizeSchemaForOpenAICompat(item),
-      )
-    } else {
-      record.items = sanitizeSchemaForOpenAICompat(record.items)
-    }
-  }
-
-  for (const key of ['anyOf', 'oneOf', 'allOf'] as const) {
-    if (Array.isArray(record[key])) {
-      record[key] = record[key].map(item =>
-        sanitizeSchemaForOpenAICompat(item),
-      )
-    }
-  }
-
-  if (Array.isArray(record.required) && isSchemaRecord(record.properties)) {
-    record.required = record.required.filter(
-      (value): value is string =>
-        typeof value === 'string' && value in record.properties,
-    )
-  }
-
-  const schemaWithoutEnum = { ...record }
-  delete schemaWithoutEnum.enum
-
-  if (Array.isArray(record.enum)) {
-    const filteredEnum = record.enum.filter(value =>
-      schemaAllowsValue(schemaWithoutEnum, value),
-    )
-    if (filteredEnum.length > 0) {
-      record.enum = filteredEnum
-    } else {
-      delete record.enum
-    }
-  }
-
-  const schemaWithoutConst = { ...record }
-  delete schemaWithoutConst.const
-  if ('const' in record && !schemaAllowsValue(schemaWithoutConst, record.const)) {
-    delete record.const
-  }
-
-  const schemaWithoutDefault = { ...record }
-  delete schemaWithoutDefault.default
-  if (
-    'default' in record &&
-    !schemaAllowsValue(schemaWithoutDefault, record.default)
-  ) {
-    delete record.default
-  }
-
-  return record
-}
+export { sanitizeSchemaForOpenAICompat } from '../../utils/schemaSanitizer.js'

src/services/api/openaiShim.ts

@@ -38,9 +38,8 @@ import {
   resolveCodexApiCredentials,
   resolveProviderRequest,
 } from './providerConfig.js'
-import { stripIncompatibleSchemaKeywords } from '../../utils/schemaSanitizer.js'
+import { sanitizeSchemaForOpenAICompat } from '../../utils/schemaSanitizer.js'
 import { redactSecretValueForDisplay } from '../../utils/providerProfile.js'
-import { sanitizeSchemaForOpenAICompat } from './openaiSchemaSanitizer.js'
 
 const GITHUB_MODELS_DEFAULT_BASE = 'https://models.github.ai/inference'
 const GITHUB_API_VERSION = '2022-11-28'

src/utils/api.test.ts

@@ -3,7 +3,7 @@ import { z } from 'zod/v4'
 import { getEmptyToolPermissionContext, type Tool, type Tools } from '../Tool.js'
 import { toolToAPISchema } from './api.js'
 
-test('toolToAPISchema strips incompatible schema keywords from input_schema', async () => {
+test('toolToAPISchema preserves provider-specific schema keywords in input_schema', async () => {
   const schema = await toolToAPISchema(
     {
       name: 'WebFetch',
@@ -18,6 +18,9 @@ test('toolToAPISchema strips incompatible schema keywords from input_schema', as
           },
           metadata: {
             type: 'object',
+            propertyNames: {
+              pattern: '^[a-z]+$',
+            },
             properties: {
               callback: {
                 type: 'string',
@@ -42,26 +45,22 @@ test('toolToAPISchema strips incompatible schema keywords from input_schema', as
       properties: {
         url: {
           type: 'string',
+          format: 'uri',
           description: 'Public HTTP or HTTPS URL',
         },
         metadata: {
           type: 'object',
+          propertyNames: {
+            pattern: '^[a-z]+$',
+          },
           properties: {
             callback: {
               type: 'string',
+              format: 'uri-reference',
             },
           },
         },
       },
     },
   })
-
-  const inputSchema = (schema as { input_schema: Record<string, unknown> }).input_schema
-  const properties = inputSchema.properties as Record<string, Record<string, unknown>>
-  expect(properties.url?.format).toBeUndefined()
-  expect(
-    (
-      properties.metadata?.properties as Record<string, Record<string, unknown>>
-    )?.callback?.format,
-  ).toBeUndefined()
 })

src/utils/api.ts

@@ -60,7 +60,6 @@ import {
 import { getPlatform } from './platform.js'
 import { countFilesRoundedRg } from './ripgrep.js'
 import { jsonStringify } from './slowOperations.js'
-import { stripIncompatibleSchemaKeywords } from './schemaSanitizer.js'
 import type { SystemPrompt } from './systemPromptType.js'
 import { getToolSchemaCache } from './toolSchemaCache.js'
 import { windowsPathToPosixPath } from './windowsPaths.js'
@@ -166,7 +165,6 @@ export async function toolToAPISchema(
     if (!isAgentSwarmsEnabled()) {
       input_schema = filterSwarmFieldsFromSchema(tool.name, input_schema)
     }
-    input_schema = stripIncompatibleSchemaKeywords(input_schema)
 
     base = {
       name: tool.name,

src/utils/schemaSanitizer.ts

@@ -1,30 +1,246 @@
-/**
- * Anthropic-compatible tool schemas reject several JSON Schema keywords that
- * Zod commonly emits, especially string `format` validators like `uri`.
- * Strip those fields recursively before sending tool schemas to providers.
- */
-export function stripIncompatibleSchemaKeywords<T>(
-  schema: T,
-): T {
-  if (Array.isArray(schema)) {
-    return schema.map(item => stripIncompatibleSchemaKeywords(item)) as T
+const OPENAI_INCOMPATIBLE_SCHEMA_KEYWORDS = new Set([
+  '$comment',
+  '$schema',
+  'default',
+  'else',
+  'examples',
+  'format',
+  'if',
+  'maxLength',
+  'maximum',
+  'minLength',
+  'minimum',
+  'multipleOf',
+  'pattern',
+  'patternProperties',
+  'propertyNames',
+  'then',
+  'unevaluatedProperties',
+])
+
+function isSchemaRecord(value: unknown): value is Record<string, unknown> {
+  return value !== null && typeof value === 'object' && !Array.isArray(value)
 }
 
-  if (!schema || typeof schema !== 'object') {
+function stripSchemaKeywords(schema: unknown, keywords: Set<string>): unknown {
+  if (Array.isArray(schema)) {
+    return schema.map(item => stripSchemaKeywords(item, keywords))
+  }
+
+  if (!isSchemaRecord(schema)) {
     return schema
   }
 
   const result: Record<string, unknown> = {}
-  for (const [key, value] of Object.entries(schema as Record<string, unknown>)) {
-    if (key === '$schema' || key === 'format' || key === 'propertyNames') {
+  for (const [key, value] of Object.entries(schema)) {
+    if (keywords.has(key)) {
       continue
     }
 
-    result[key] =
-      value && typeof value === 'object'
-        ? stripIncompatibleSchemaKeywords(value)
-        : value
+    result[key] = stripSchemaKeywords(value, keywords)
   }
 
-  return result as T
+  return result
+}
+
+function deepEqualJsonValue(a: unknown, b: unknown): boolean {
+  if (Object.is(a, b)) return true
+  if (typeof a !== typeof b) return false
+
+  if (Array.isArray(a) && Array.isArray(b)) {
+    return (
+      a.length === b.length &&
+      a.every((value, index) => deepEqualJsonValue(value, b[index]))
+    )
+  }
+
+  if (isSchemaRecord(a) && isSchemaRecord(b)) {
+    const aKeys = Object.keys(a)
+    const bKeys = Object.keys(b)
+    return (
+      aKeys.length === bKeys.length &&
+      aKeys.every(key => key in b && deepEqualJsonValue(a[key], b[key]))
+    )
+  }
+
+  return false
+}
+
+function matchesJsonSchemaType(type: string, value: unknown): boolean {
+  switch (type) {
+    case 'string':
+      return typeof value === 'string'
+    case 'number':
+      return typeof value === 'number' && Number.isFinite(value)
+    case 'integer':
+      return typeof value === 'number' && Number.isInteger(value)
+    case 'boolean':
+      return typeof value === 'boolean'
+    case 'object':
+      return value !== null && typeof value === 'object' && !Array.isArray(value)
+    case 'array':
+      return Array.isArray(value)
+    case 'null':
+      return value === null
+    default:
+      return true
+  }
+}
+
+function getJsonSchemaTypes(record: Record<string, unknown>): string[] {
+  const raw = record.type
+  if (typeof raw === 'string') {
+    return [raw]
+  }
+  if (Array.isArray(raw)) {
+    return raw.filter((value): value is string => typeof value === 'string')
+  }
+  return []
+}
+
+function schemaAllowsValue(schema: Record<string, unknown>, value: unknown): boolean {
+  if (Array.isArray(schema.anyOf)) {
+    return schema.anyOf.some(item =>
+      schemaAllowsValue(sanitizeSchemaForOpenAICompat(item), value),
+    )
+  }
+
+  if (Array.isArray(schema.oneOf)) {
+    return (
+      schema.oneOf.filter(item =>
+        schemaAllowsValue(sanitizeSchemaForOpenAICompat(item), value),
+      ).length === 1
+    )
+  }
+
+  if (Array.isArray(schema.allOf)) {
+    return schema.allOf.every(item =>
+      schemaAllowsValue(sanitizeSchemaForOpenAICompat(item), value),
+    )
+  }
+
+  if ('const' in schema && !deepEqualJsonValue(schema.const, value)) {
+    return false
+  }
+
+  if (Array.isArray(schema.enum)) {
+    if (!schema.enum.some(item => deepEqualJsonValue(item, value))) {
+      return false
+    }
+  }
+
+  const types = getJsonSchemaTypes(schema)
+  if (types.length > 0 && !types.some(type => matchesJsonSchemaType(type, value))) {
+    return false
+  }
+
+  return true
+}
+
+function sanitizeTypeField(record: Record<string, unknown>): void {
+  const allowed = new Set([
+    'string',
+    'number',
+    'integer',
+    'boolean',
+    'object',
+    'array',
+    'null',
+  ])
+
+  const raw = record.type
+  if (typeof raw === 'string') {
+    if (!allowed.has(raw)) delete record.type
+    return
+  }
+
+  if (!Array.isArray(raw)) return
+
+  const filtered = raw.filter(
+    (value, index): value is string =>
+      typeof value === 'string' &&
+      allowed.has(value) &&
+      raw.indexOf(value) === index,
+  )
+
+  if (filtered.length === 0) {
+    delete record.type
+  } else if (filtered.length === 1) {
+    record.type = filtered[0]
+  } else {
+    record.type = filtered
+  }
+}
+
+/**
+ * Sanitize JSON Schema into a shape OpenAI-compatible providers and Codex
+ * strict-mode tooling are more likely to accept. This strips provider-rejected
+ * keywords while keeping enum/const cleanup defensive for imperfect MCP schemas.
+ */
+export function sanitizeSchemaForOpenAICompat(
+  schema: unknown,
+): Record<string, unknown> {
+  const stripped = stripSchemaKeywords(schema, OPENAI_INCOMPATIBLE_SCHEMA_KEYWORDS)
+  if (!isSchemaRecord(stripped)) {
+    return {}
+  }
+
+  const record = { ...stripped }
+
+  sanitizeTypeField(record)
+
+  if (isSchemaRecord(record.properties)) {
+    const sanitizedProps: Record<string, unknown> = {}
+    for (const [key, value] of Object.entries(record.properties)) {
+      sanitizedProps[key] = sanitizeSchemaForOpenAICompat(value)
+    }
+    record.properties = sanitizedProps
+  }
+
+  if ('items' in record) {
+    if (Array.isArray(record.items)) {
+      record.items = record.items.map(item =>
+        sanitizeSchemaForOpenAICompat(item),
+      )
+    } else {
+      record.items = sanitizeSchemaForOpenAICompat(record.items)
+    }
+  }
+
+  for (const key of ['anyOf', 'oneOf', 'allOf'] as const) {
+    if (Array.isArray(record[key])) {
+      record[key] = record[key].map(item =>
+        sanitizeSchemaForOpenAICompat(item),
+      )
+    }
+  }
+
+  if (Array.isArray(record.required) && isSchemaRecord(record.properties)) {
+    record.required = record.required.filter(
+      (value): value is string =>
+        typeof value === 'string' && value in record.properties,
+    )
+  }
+
+  const schemaWithoutEnum = { ...record }
+  delete schemaWithoutEnum.enum
+
+  if (Array.isArray(record.enum)) {
+    const filteredEnum = record.enum.filter(value =>
+      schemaAllowsValue(schemaWithoutEnum, value),
+    )
+    if (filteredEnum.length > 0) {
+      record.enum = filteredEnum
+    } else {
+      delete record.enum
+    }
+  }
+
+  const schemaWithoutConst = { ...record }
+  delete schemaWithoutConst.const
+  if ('const' in record && !schemaAllowsValue(schemaWithoutConst, record.const)) {
+    delete record.const
+  }
+
+  return record
 }