♊ fix: Sanitize MCP Tool Schemas for Gemini/Vertex Compatibility (#13623)

* 🧰 fix: Flatten union schemas for Gemini/Vertex MCP tool compatibility

`@langchain/google-common`'s `zod_to_gemini_parameters` throws "Gemini cannot
handle union types" on any genuine `anyOf`/`oneOf` (e.g. discriminated unions),
so MCP tools shipping union-typed schemas crash on the Google endpoint while
working fine on OpenAI/Claude.

Add `flattenJsonSchemaUnions` (packages/api) to collapse unions to their first
non-null member and multi-entry `type` arrays to a single nullable type, and
apply it in `createToolInstance`'s existing `isGoogle` branch so only the
Google/Vertex path is affected. Lossy by design, mirroring the existing
empty-object fallback.

Closes #13612

* 🩹 fix: Address Codex review — preserve fields, strip null enums, cover definitions path

- Preserve parent-level `properties`/`required` when collapsing a union: merge the
  chosen branch into the parent instead of overwriting, so args declared outside the
  union (e.g. always-required fields) still reach Gemini.
- Drop the `null` member from `enum` when a union/type-array makes a field nullable,
  keeping Gemini's required homogeneous-enum invariant.
- Propagate the Google-flattened schema to the definitions/deferred-tool path:
  thread `provider` into `loadToolDefinitions` and flatten there, and store the
  flattened schema on `mcpJsonSchema` so `extractMCPToolDefinition` no longer emits
  raw unions on Google/Vertex.

* 🎨 style: Sort imports in tools/definitions per import-order check

* ♊ feat: Broaden union flatten into a full Gemini schema sanitizer

The union flatten alone wasn't enough — real GitHub MCP tools on Gemini also 400
with `Invalid value ... (TYPE_STRING), true`, because Gemini's function-calling
Schema (https://ai.google.dev/api/caching#Schema) accepts only a restricted JSON
Schema subset, and `enum` is `Type.STRING`-only.

Rename `flattenJsonSchemaUnions` → `sanitizeGeminiSchema` and broaden it (one pass,
Gemini-gated) to cover the documented subset:

- Keep only string `enum` values; drop the keyword for non-string types (fixes the
  reported boolean-enum 400, incl. boolean `const` normalized to `enum: [true]`).
- `const` → single-value string enum, or drop if non-string.
- Merge `allOf` intersections; fold `exclusiveMinimum`/`exclusiveMaximum` into
  `minimum`/`maximum`.
- Strip unsupported keywords: `additionalProperties`, `default`, `$schema`, `$id`.
- (Existing) collapse `anyOf`/`oneOf`, multi-entry `type` arrays, nullable.

Grounded in Google's Schema docs rather than reverse-engineered from 400s. Verified
end-to-end against the real `@langchain/google-common` converter. Complements
danny-avila/agents#232 (langchain bump), which defers schema flattening to LibreChat.

* 🩹 fix: Gate enum retention on the effective (collapsed) type

Codex review: a mixed-type enum like `type: ['integer','string'], enum: [1,'auto']`
collapsed the type to `integer` but still kept the string value `'auto'`, yielding
`{type:'integer', enum:['auto']}` — a non-string type with an enum, which Gemini
rejects. Keep `enum` only when the effective collapsed type is string (or unset),
and stamp `type: 'string'` on a surviving typeless enum (e.g. a string `const`
discriminator) so it satisfies Gemini's Type.STRING enum requirement.

api/server/services/MCP.js

@@ -9,6 +9,7 @@ const {
   normalizeJsonSchema,
   GenerationJobManager,
   resolveJsonSchemaRefs,
+  sanitizeGeminiSchema,
   buildMCPAuthStepId,
   buildMCPAuthToolCall,
   buildMCPAuthRunStepEvent,
@@ -648,6 +649,12 @@ function createToolInstance({
 
   let schema = parameters ? normalizeJsonSchema(resolveJsonSchemaRefs(parameters)) : null;
 
+  if (schema && isGoogle) {
+    // Gemini/Vertex AI accept only a subset of JSON Schema; sanitize so MCP tools with
+    // unions, non-string enums, etc. don't 400 (they work as-is on OpenAI/Claude).
+    schema = sanitizeGeminiSchema(schema);
+  }
+
   if (!schema || (isGoogle && isEmptyObjectSchema(schema))) {
     schema = {
       type: 'object',
@@ -779,7 +786,9 @@ function createToolInstance({
   });
   toolInstance.mcp = true;
   toolInstance.mcpRawServerName = serverName;
-  toolInstance.mcpJsonSchema = parameters;
+  // On Google/Vertex, propagate the union-flattened schema so definitions extracted
+  // from this instance don't reach the Gemini converter with unsupported unions.
+  toolInstance.mcpJsonSchema = isGoogle ? schema : parameters;
   return toolInstance;
 }
 

api/server/services/ToolService.js

@@ -840,6 +840,7 @@ async function loadToolDefinitionsWrapper({ req, res, agent, streamId = null, to
       deferredToolsEnabled,
       programmaticToolsEnabled,
       codeExecutionEnabled,
+      provider: agent.provider,
     },
     {
       isBuiltInTool,
@@ -919,6 +920,7 @@ async function loadToolDefinitionsWrapper({ req, res, agent, streamId = null, to
           deferredToolsEnabled,
           programmaticToolsEnabled,
           codeExecutionEnabled,
+          provider: agent.provider,
         },
         {
           isBuiltInTool,