Files
LibreChat/api/server/services/Config/loadDefaultModels.js
Danny Avila 2350ebb24a 📨 feat: Custom Headers on Built-in Provider Endpoints (#13742)
* 📨 feat: Custom Headers on Built-in Provider Endpoints

Add a `headers` config option to the built-in `openAI`, `anthropic`, and
`google` endpoints (incl. Anthropic/Google Vertex), mirroring the custom
endpoint header mechanism. Values support the same placeholder resolution
(env vars, `{{LIBRECHAT_USER_*}}`, `{{LIBRECHAT_BODY_CONVERSATIONID}}`) and
are resolved at request time so dynamic values like conversationId resolve
against the live request — without losing provider-native request shaping.

Closes #13082. Covers #13713: forwarding conversationId to a reverse proxy
is now `X-Conversation-Id: '{{LIBRECHAT_BODY_CONVERSATIONID}}'` — an unknown
header is ignored by the native Anthropic API, so no 400 and no metadata
gating needed.

- Schema: `headers` on `baseEndpointSchema` (openAI/google/anthropic/all).
- New `mergeHeaders`/`resolveConfigHeaders` utils centralize the per-provider
  header locations (`configuration.defaultHeaders`, Anthropic
  `clientOptions.defaultHeaders`, Google `customHeaders`); provider-managed
  headers (auth, `anthropic-beta`) always win on collision.
- Each initializer threads configured headers (endpoint over `all`) into the
  right place; request-time resolution runs across all locations in the main
  and title flows.

* 🩹 fix: Cast endpoints.all to TEndpoint for headers DeepPartial widening

Adding `headers` (a Record) to `baseEndpointSchema` makes `DeepPartial<TCustomConfig>`
widen its value type to `string | undefined`, which is not assignable to the
concrete `TEndpoint['headers']: Record<string, string>` at the `loadedEndpoints.all`
assignment. Cast at the assignment site, mirroring the existing
`anthropicConfig as TAnthropicEndpoint` cast in the same function.

* 🛡️ fix: Harden built-in endpoint custom headers (Codex review)

Address Codex P2 findings on the custom-headers feature:

- Anthropic title requests: `omitTitleOptions` strips the `clientOptions`
  carrier, which dropped its `defaultHeaders`. Preserve just the header carrier
  so gateway/reverse-proxy metadata still reaches title generation.
- mergeHeaders: match header names case-insensitively so an override (e.g. a
  provider-managed `Authorization`/`anthropic-beta`) replaces/uniones a
  case-variant from the base instead of emitting two names a client may collapse.
- OpenAI: withhold admin-configured headers when the user supplies the base URL
  (`user_provided`), since values may carry `${SECRET}`/token placeholders that
  must not reach a user-controlled endpoint — mirrors the custom-endpoint guard.
- Azure: honor global `endpoints.all` headers (same OpenAI carrier) while keeping
  Azure-managed `api-key`/version headers authoritative.

Adds tests for each.

* 🔐 fix: Resolve-once + provider-managed header safety (Codex review round 2)

Address Codex P2 findings:

- Azure: keep global `endpoints.all` headers unresolved at init and let
  request-time `resolveConfigHeaders` resolve them once, avoiding a
  second-order env expansion of already-substituted user values.
- Google: `resolveConfigHeaders` no longer template-resolves the
  provider-managed `Authorization` header (built from a possibly user-provided
  key), so a user key like `${ENV}` can't leak server environment values.
- Model fetches: thread configured headers (endpoint over `all`) + user object
  through `getOpenAIModels`/`getAnthropicModels` → `fetchModels`, so a
  gateway-fronted built-in provider receives the header on `/models` too. Fixed
  `fetchModels` to merge custom headers for Anthropic instead of overwriting
  them (managed `x-api-key`/version still win).

Adds/updates tests for each.

* 🧯 fix: Header provenance, memory/title coverage, idempotency (Codex round 3)

Address Codex P2 findings, including two regressions from the prior round:

- Google auth (findings 6 & 8): move native Google header resolution to init
  (`initializeGoogle`), resolving admin templates BEFORE the key-derived auth
  header is built. resolveConfigHeaders no longer touches Google `customHeaders`,
  so admin `Authorization` templates resolve again (fixes the round-2 regression)
  while the SDK auth header (possibly a user-provided key) is never env-expanded.
- Memory runs: memory extraction now calls `resolveConfigHeaders`, so native
  Anthropic (and OpenAI) headers resolve for memory requests too.
- Vertex titles: restore the ORIGINAL `clientOptions` object reference (not a
  copy) when preserving headers across `omitTitleOptions`, so the Vertex
  `createClient` closure and the resolved headers stay on the same object.
- Reuse: `resolveConfigHeaders` is now idempotent (resolve-once per header map),
  preventing a second pass from env-expanding values already substituted with
  user/body data when an agent object flows through buildAgentInput twice.

Adds/updates tests for each.
2026-06-14 17:02:04 -04:00

96 lines
3.2 KiB
JavaScript

const { logger } = require('@librechat/data-schemas');
const { EModelEndpoint } = require('librechat-data-provider');
const {
mergeHeaders,
getAnthropicModels,
getBedrockModels,
getOpenAIModels,
getGoogleModels,
} = require('@librechat/api');
const { getAppConfig } = require('./app');
/**
* Loads the default models for the application.
* @async
* @function
* @param {ServerRequest} req - The Express request object.
*/
async function loadDefaultModels(req) {
try {
const appConfig =
req.config ??
(await getAppConfig({
role: req.user?.role,
userId: req.user?.id,
tenantId: req.user?.tenantId,
}));
const vertexConfig = appConfig?.endpoints?.[EModelEndpoint.anthropic]?.vertexConfig;
/** Forward configured custom headers (endpoint over global `all`) so model
* fetches reach a gateway-fronted provider the same as chat requests. */
const allHeaders = appConfig?.endpoints?.all?.headers;
const openAIHeaders = mergeHeaders(
allHeaders,
appConfig?.endpoints?.[EModelEndpoint.openAI]?.headers,
);
const anthropicHeaders = mergeHeaders(
allHeaders,
appConfig?.endpoints?.[EModelEndpoint.anthropic]?.headers,
);
const [openAI, anthropic, azureOpenAI, assistants, azureAssistants, google, bedrock] =
await Promise.all([
getOpenAIModels({ user: req.user.id, headers: openAIHeaders, userObject: req.user }).catch(
(error) => {
logger.error('Error fetching OpenAI models:', error);
return [];
},
),
getAnthropicModels({
user: req.user.id,
vertexModels: vertexConfig?.modelNames,
headers: anthropicHeaders,
userObject: req.user,
}).catch((error) => {
logger.error('Error fetching Anthropic models:', error);
return [];
}),
getOpenAIModels({ user: req.user.id, azure: true }).catch((error) => {
logger.error('Error fetching Azure OpenAI models:', error);
return [];
}),
getOpenAIModels({ assistants: true }).catch((error) => {
logger.error('Error fetching OpenAI Assistants API models:', error);
return [];
}),
getOpenAIModels({ azureAssistants: true }).catch((error) => {
logger.error('Error fetching Azure OpenAI Assistants API models:', error);
return [];
}),
Promise.resolve(getGoogleModels()).catch((error) => {
logger.error('Error getting Google models:', error);
return [];
}),
Promise.resolve(getBedrockModels()).catch((error) => {
logger.error('Error getting Bedrock models:', error);
return [];
}),
]);
return {
[EModelEndpoint.openAI]: openAI,
[EModelEndpoint.google]: google,
[EModelEndpoint.anthropic]: anthropic,
[EModelEndpoint.azureOpenAI]: azureOpenAI,
[EModelEndpoint.assistants]: assistants,
[EModelEndpoint.azureAssistants]: azureAssistants,
[EModelEndpoint.bedrock]: bedrock,
};
} catch (error) {
logger.error('Error fetching default models:', error);
throw new Error(`Failed to load default models: ${error.message}`);
}
}
module.exports = loadDefaultModels;