Allow OpenAI-compatible services without API key when base URL is set

[Copilot]

Application fails to start with OpenAI-compatible services (LM Studio, local inference servers) because it enforces OPENAI_API_KEY requirement even when OPENAI_BASE_URL is configured. These services typically don't require authentication.

Changes

Validation Logic

• Modified startup validation to allow empty OPENAI_API_KEY when OPENAI_BASE_URL is set
• Updated error message to indicate both authentication paths
• Azure OpenAI still requires both key and URL (unchanged)

Client Creation

• createLLM(), createVisionLLM(), and ocr.createOpenAIClient() now inject dummy token when base URL is set but key is empty
• Dummy token defined in internal/constants package to avoid duplication

Testing

• Added test coverage for OpenAI-compatible configurations (with/without API key)
• Verified Azure and standard OpenAI flows remain unchanged

Usage

# LM Studio / OpenAI-compatible services (no key needed)
export OPENAI_BASE_URL="http://localhost:1234/v1"
export LLM_PROVIDER="openai"
export LLM_MODEL="model-name"
# OPENAI_API_KEY not required

# Standard OpenAI (key required)
export OPENAI_API_KEY="sk-..."
export LLM_PROVIDER="openai"

# Azure OpenAI (both required)
export OPENAI_API_KEY="..."
export OPENAI_BASE_URL="https://resource.openai.azure.com"
export OPENAI_API_TYPE="azure"

Warning

Firewall rules blocked me from connecting to one or more addresses (expand for details)

I tried to connect to the following addresses, but was blocked by firewall rules:

• openaipublic.blob.core.windows.net
  • Triggering command: /tmp/go-build1520700788/b001/paperless-gpt.test -test.testlogfile=/tmp/go-build1520700788/b001/testlog.txt -test.paniconexit0 -test.timeout=10m0s -test.v=true (dns block)
  • Triggering command: /tmp/go-build1391058986/b001/paperless-gpt.test -test.testlogfile=/tmp/go-build1391058986/b001/testlog.txt -test.paniconexit0 -test.timeout=10m0s (dns block)

If you need me to access, download, or install something from one of these locations, you can either:

• Configure Actions setup steps to set up my environment, which run before the firewall is enabled
• Add the appropriate URLs or hosts to the custom allowlist in this repository's Copilot coding agent settings (admins only)

Original prompt

---

This section details on the original issue you should resolve

<issue_title>Cannot use LM Studio despite OpenAI API compatibility – requires OPENAI_API_KEY</issue_title>
<issue_description>I'm trying to use LM Studio as an OpenAI-compatible backend, but the application still requires an API key for OpenAI, even though I'm setting the OPENAI_BASE_URL to the LM Studio URL.

Steps to reproduce:

1. Set environment variables as follows:
   OPENAI_BASE_URL=http://localhost:1234/v1

2. Run the application without setting OPENAI_API_KEY (since LM Studio doesn’t require one).

Expected behavior:
The app should connect to LM Studio successfully without needing an OpenAI API key.

Actual behavior:
The application immediately fails with the following error message in the log:
level=fatal msg="Please set the OPENAI_API_KEY environment variable for OpenAI provider."

Additional context:
Even when providing a dummy API key, the same error occurs.
It seems the application enforces OPENAI_API_KEY presence regardless of the base URL or provider.</issue_description>

Comments on the Issue (you are @copilot in this section)

• Fixes Cannot use LM Studio despite OpenAI API compatibility – requires OPENAI_API_KEY #767

---

💬 We'd love your input! Share your thoughts on Copilot coding agent in our 2 minute survey.

[coderabbitai]

Important

Review skipped

Bot user detected.

To trigger a single review, invoke the @coderabbitai review command.

You can disable this status message by setting the reviews.review_status to false in the CodeRabbit configuration file.

---

_{Comment @coderabbitai help to get the list of available commands and usage tips.}