feat: Add OpenAI-compatible API support to AI Writer operation by aurkinet · Pull Request #250 · directus-labs/extensions

aurkinet · 2025-09-22T23:43:40Z

Adds support for any OpenAI-compatible API to the AI Writer operation, allowing users to use local models, cloud providers, and any service that implements the OpenAI Chat completions API format.

To test :

Select "OpenAI Compatible (Custom)" as AI Provider
Enter custom endpoint (e.g., https://router.huggingface.co/v1)
Provide API key
Choose model or enter custom model name (e.g., Qwen/Qwen3-Next-80B-A3B-Instruct:novita)

NemeZZiZZ · 2025-10-05T21:41:25Z

You can use field AI Model with meta.options: {.., allowOther: true} without any special custom field, so user can enter any desired model that is not hardcoded

Copilot

Pull request overview

Adds an “OpenAI Compatible (Custom)” provider option to the AI Writer operation so users can target OpenAI Chat Completions–compatible endpoints beyond OpenAI itself.

Changes:

Add new UI options for “OpenAI Compatible (Custom)”, including custom endpoint, API key, and custom model name input.
Extend provider selection + OpenAI provider implementation to support custom endpoints and custom model names.
Expand Directus sandbox request scopes and update README documentation for the new provider.

Reviewed changes

Copilot reviewed 6 out of 6 changed files in this pull request and generated 6 comments.

Show a summary per file

File	Description
packages/ai-writer-operation/src/app.ts	Adds “OpenAI Compatible (Custom)” provider choice and related config fields in the operation UI.
packages/ai-writer-operation/src/api.ts	Extends operation options interface with custom endpoint/key/model fields.
packages/ai-writer-operation/src/Provider/ProviderFactory.ts	Routes `openai-compatible` provider to the OpenAI provider and fixes a typo in error text.
packages/ai-writer-operation/src/Provider/OpenAi.ts	Adds custom endpoint + API key handling and allows custom model name substitution.
packages/ai-writer-operation/package.json	Broadens sandbox `request` URL scopes to allow arbitrary OpenAI-compatible endpoints.
packages/ai-writer-operation/README.md	Updates docs and adds guidance for OpenAI-compatible providers.

💡 Add Copilot custom instructions for smarter, more guided reviews. Learn how to get started.

Copilot · 2026-03-10T20:57:40Z

-			throw new InvalidPayloadError({ reason: 'OpenAI API Key is missing' });
-		}
+		// Determine if this is a custom OpenAI-compatible provider or standard OpenAI
+		const isCustomProvider = options.aiProvider === 'openai-compatible';


isCustomProvider is checked with a case-sensitive equality (options.aiProvider === 'openai-compatible'), but getProvider() routes here using a case-insensitive comparison. If aiProvider ever comes through with different casing (e.g., via API/DB), this will incorrectly treat it as standard OpenAI and require apiKeyOpenAi / use the OpenAI endpoint. Normalize casing here (e.g., compare options.aiProvider?.toLowerCase()), or pass a canonical provider value into the provider classes.

Suggested change

const isCustomProvider = options.aiProvider === 'openai-compatible';

const isCustomProvider = options.aiProvider?.toLowerCase() === 'openai-compatible';

Copilot · 2026-03-10T20:57:40Z

+			const endpoint = options.customEndpoint.endsWith('/chat/completions') 
+				? options.customEndpoint 
+				: `${options.customEndpoint.replace(/\/$/, '')}/chat/completions`;


The endpoint normalization can produce a duplicated path when the user provides a full /chat/completions/ URL with a trailing slash (e.g., .../chat/completions/ becomes .../chat/completions/chat/completions). Consider trimming trailing slashes before the endsWith('/chat/completions') check (or using new URL() path joining) to make this robust.

Suggested change

const endpoint = options.customEndpoint.endsWith('/chat/completions')

? options.customEndpoint

: `${options.customEndpoint.replace(/\/$/, '')}/chat/completions`;

const baseEndpoint = options.customEndpoint.replace(/\/+$/, '');

const endpoint = baseEndpoint.endsWith('/chat/completions')

? baseEndpoint

: `${baseEndpoint}/chat/completions`;

Copilot · 2026-03-10T20:57:40Z

+		// Use custom model name if provided, otherwise use the selected model
+		const modelName = this.options.model === 'custom' && this.options.customModelName 
+			? this.options.customModelName 


When model is set to 'custom' but customModelName is missing/empty, the request will be sent with model: 'custom'. Add server-side validation to require a non-empty customModelName when model === 'custom' (don’t rely on the app UI’s conditional required field).

Suggested change

// Use custom model name if provided, otherwise use the selected model

const modelName = this.options.model === 'custom' && this.options.customModelName

? this.options.customModelName

// Validate that a custom model name is provided when using a custom model

if (this.options.model === 'custom' && !this.options.customModelName) {

throw new InvalidPayloadError({

reason: 'Custom Model Name is missing',

});

}

// Use custom model name if provided, otherwise use the selected model

const modelName = this.options.model === 'custom' && this.options.customModelName

? this.options.customModelName

Copilot · 2026-03-10T20:57:41Z

 					],
 					"urls": [


The new request scope patterns (https://**/v1/** and especially http://**/v1/**) allow this operation to make network calls to essentially any host, including over plaintext HTTP. If custom endpoints are required, consider restricting to HTTPS-only and/or limiting HTTP to localhost, and validate customEndpoint to reject localhost/private IP ranges by default to reduce SSRF risk.

Suggested change

"urls": [

"https://**/v1/**"

Copilot · 2026-03-10T20:57:41Z

 	}

-	throw new Error(`Unsoported AI Provider ${options.aiProvider}`);
+	throw new Error(`Unsupported AI Provider ${options.aiProvider}`);


For unsupported providers, this throws a generic Error while other validation errors use InvalidPayloadError. Consider throwing InvalidPayloadError here as well (with a clear reason) so API consumers get consistent error types/status codes.

Suggested change

throw new Error(`Unsupported AI Provider ${options.aiProvider}`);

throw new InvalidPayloadError({ reason: `Unsupported AI Provider: ${options.aiProvider}` });

Copilot · 2026-03-10T20:57:41Z

+The extension now supports any OpenAI-compatible API by selecting "OpenAI Compatible (Custom)" as the AI Provider. This allows you to use services like:
+- Local models (Ollama, LM Studio, etc.)
+- Cloud providers (Azure OpenAI, Google Vertex AI, etc.)
+- Other OpenAI-compatible services (Groq, Together AI, etc.)
+
+When using a custom provider, you'll need to:
+1. Select "OpenAI Compatible (Custom)" as the AI Provider
+2. Enter your custom API endpoint (e.g., `https://api.example.com/v1`)
+3. Provide your API key
+4. Choose a model from the dropdown or select "Custom Model" to enter a specific model name
+


The README implies Azure OpenAI / Vertex AI work directly as “OpenAI-compatible APIs”, but Azure’s endpoints/auth (api-key header + api-version + deployments path) and Vertex AI are not Chat Completions-compatible by default. Please clarify that this works with services that expose the OpenAI Chat Completions-compatible endpoint + Bearer auth (or mention that Azure/Vertex require a compatibility/proxy layer).

Suggested change

The extension now supports any OpenAI-compatible API by selecting "OpenAI Compatible (Custom)" as the AI Provider. This allows you to use services like:

- Local models (Ollama, LM Studio, etc.)

- Cloud providers (Azure OpenAI, Google Vertex AI, etc.)

- Other OpenAI-compatible services (Groq, Together AI, etc.)

When using a custom provider, you'll need to:

1. Select "OpenAI Compatible (Custom)" as the AI Provider

2. Enter your custom API endpoint (e.g., `https://api.example.com/v1`)

3. Provide your API key

4. Choose a model from the dropdown or select "Custom Model" to enter a specific model name

The extension supports providers that expose an **OpenAI Chat Completions-compatible HTTP API** (OpenAI-style paths and request/response format, using `Authorization: Bearer <api-key>`), by selecting "OpenAI Compatible (Custom)" as the AI Provider. This allows you to use services like:

- Local models (Ollama, LM Studio, etc.) when configured to expose an OpenAI-compatible endpoint

- Cloud providers (Azure OpenAI, Google Vertex AI, etc.) **via an OpenAI-compatible/translation layer or proxy** that normalizes their endpoints and auth to the OpenAI Chat Completions format

- Other OpenAI-compatible services (Groq, Together AI, etc.) that implement the Chat Completions API

When using a custom provider, you'll need to:

1. Select "OpenAI Compatible (Custom)" as the AI Provider

2. Enter your custom API endpoint (e.g., `https://api.example.com/v1`) that implements the OpenAI Chat Completions-compatible interface

3. Provide your API key (sent as a Bearer token)

4. Choose a model from the dropdown or select "Custom Model" to enter a specific model name

> Note: Azure OpenAI and Google Vertex AI do **not** use the OpenAI Chat Completions URL structure or authentication scheme by default. To use them here, you must either:

> - Use a compatibility/proxy layer that exposes an OpenAI Chat Completions-compatible endpoint, or

> - Use a provider-managed endpoint explicitly documented as OpenAI Chat Completions-compatible.

feat: Add OpenAI-compatible API support to AI Writer operation

2737c0b

aurkinet mentioned this pull request Sep 22, 2025

OpenAI API compatible endpoint Custom Base URL / Model Name for AI directus extensions? #236

Open

bryantgillespie requested a review from Copilot March 10, 2026 20:53

Copilot started reviewing on behalf of bryantgillespie March 10, 2026 20:53 View session

Merge branch 'main' into feature/openai-compatible-support

597b6fd

Copilot AI reviewed Mar 10, 2026

View reviewed changes

Provide feedback

Saved searches

Use saved searches to filter your results more quickly

Uh oh!

feat: Add OpenAI-compatible API support to AI Writer operation#250

feat: Add OpenAI-compatible API support to AI Writer operation#250
aurkinet wants to merge 2 commits into
directus-labs:mainfrom
aurkinet:feature/openai-compatible-support

aurkinet commented Sep 22, 2025

Uh oh!

NemeZZiZZ commented Oct 5, 2025

Uh oh!

Copilot AI left a comment

Uh oh!

Copilot AI Mar 10, 2026

Uh oh!

Copilot AI Mar 10, 2026

Uh oh!

Copilot AI Mar 10, 2026

Uh oh!

Copilot AI Mar 10, 2026

Uh oh!

Copilot AI Mar 10, 2026

Uh oh!

Copilot AI Mar 10, 2026

Uh oh!

Reviewers

Assignees

Labels

Projects

Milestone

Development

Uh oh!

4 participants

	const isCustomProvider = options.aiProvider === 'openai-compatible';
	const isCustomProvider = options.aiProvider?.toLowerCase() === 'openai-compatible';

-			const endpoint = options.customEndpoint.endsWith('/chat/completions')
-				? options.customEndpoint
-				: `${options.customEndpoint.replace(/\/$/, '')}/chat/completions`;
+			const baseEndpoint = options.customEndpoint.replace(/\/+$/, '');
+			const endpoint = baseEndpoint.endsWith('/chat/completions')
+				? baseEndpoint
+				: `${baseEndpoint}/chat/completions`;

	throw new Error(`Unsupported AI Provider ${options.aiProvider}`);
	throw new InvalidPayloadError({ reason: `Unsupported AI Provider: ${options.aiProvider}` });

Uh oh!

Conversation

aurkinet commented Sep 22, 2025

Uh oh!

NemeZZiZZ commented Oct 5, 2025

Uh oh!

Copilot AI left a comment

Choose a reason for hiding this comment

Pull request overview

Reviewed changes

Uh oh!

Copilot AI Mar 10, 2026

Choose a reason for hiding this comment

Uh oh!

Copilot AI Mar 10, 2026

Choose a reason for hiding this comment

Uh oh!

Copilot AI Mar 10, 2026

Choose a reason for hiding this comment

Uh oh!

Copilot AI Mar 10, 2026

Choose a reason for hiding this comment

Uh oh!

Copilot AI Mar 10, 2026

Choose a reason for hiding this comment

Uh oh!

Copilot AI Mar 10, 2026

Choose a reason for hiding this comment

Uh oh!

Reviewers

Assignees

Labels

Projects

Milestone

Development

Uh oh!

4 participants