opensource/n8n
3
0
Fork 0
mirror of https://github.com/n8n-io/n8n.git synced 2026-08-29 01:39:24 +08:00
Code Issues Packages Projects Releases Wiki Activity

fix(core): Support bare models for custom AI Assistant endpoints (#34016)

Browse Source
This commit is contained in:
oleg
2026-07-13 11:52:39 +02:00
committed by GitHub
parent f54893f0b4
commit 0fee78b7fc
4 changed files with 19 additions and 2 deletions
Download Patch File Download Diff File Expand all files Collapse all files
packages/@n8n/agents/src/runtime/model/model-factory.ts
+13
View File
@@ -82,6 +82,19 @@ const LANGUAGE_PROVIDERS: ProviderRegistry = {
return creds.baseURL ? provider.chat(model) : provider(model);
},
},
custom: {
build: (creds, model, fetch) => {
const { createOpenAICompatible } =
require('@ai-sdk/openai-compatible') as typeof import('@ai-sdk/openai-compatible');
return createOpenAICompatible({
name: 'custom',
baseURL: creds.baseURL,
apiKey: creds.apiKey,
headers: creds.headers,
fetch,
})(model);
},
},
anthropic: {
build: (creds, model, fetch) => {
const { createAnthropic } =
packages/@n8n/agents/src/runtime/model/provider-credentials.ts
+3
View File
@@ -12,6 +12,9 @@ const apiKeyCreds = z.object({
*/
export const PROVIDER_CREDENTIAL_SCHEMAS = {
openai: apiKeyCreds,
custom: apiKeyCreds.extend({
baseURL: z.string().min(1, 'baseURL is required'),
}),
anthropic: apiKeyCreds,
google: apiKeyCreds,
xai: apiKeyCreds,
packages/@n8n/config/src/configs/instance-ai.config.ts
+1 -1
View File
@@ -4,7 +4,7 @@ import { Config, Env } from '../decorators';
@Config
export class InstanceAiConfig {
/** LLM model in provider/model format (e.g. "anthropic/claude-opus-4-8"). */
/** LLM model in provider/model format, or a bare model name for a custom endpoint. */
@Env('N8N_INSTANCE_AI_MODEL')
model: string = 'anthropic/claude-opus-4-8';
packages/@n8n/instance-ai/docs/configuration.md
+2 -1
View File
@@ -8,7 +8,7 @@ All Instance AI configuration is done via environment variables.
| Variable | Type | Default | Description |
|----------|------|---------|-------------|
| `N8N_INSTANCE_AI_MODEL` | string | `anthropic/claude-opus-4-8` | LLM model in `provider/model` format. Must be set for the module to enable. |
| `N8N_INSTANCE_AI_MODEL` | string | `anthropic/claude-opus-4-8` | LLM model in `provider/model` format for built-in providers, or a bare model name when `N8N_INSTANCE_AI_MODEL_URL` is set. Must be set for the module to enable. |
| `N8N_INSTANCE_AI_MODEL_URL` | string | `''` | Base URL for an OpenAI-compatible endpoint (e.g. `http://localhost:1234/v1` for LM Studio). When set, model requests go to this URL instead of the built-in provider. |
| `N8N_INSTANCE_AI_MODEL_API_KEY` | string | `''` | API key for the custom model endpoint. Optional — some local servers don't require one. |
| `N8N_INSTANCE_AI_MCP_SERVERS` | string | `''` | Comma-separated MCP server configs. Format: `name=url,name=url` |
@@ -208,6 +208,7 @@ N8N_INSTANCE_AI_GATEWAY_API_KEY=my-secret-key
# User runs: npx @n8n/computer-use
# With custom OpenAI-compatible endpoint (e.g. LM Studio, Ollama)
N8N_INSTANCE_AI_MODEL=your-tool-capable-model
N8N_INSTANCE_AI_MODEL_URL=http://localhost:1234/v1
# Output filtering — secrets + email only, with a custom placeholder