feat: OLLAMA_* settings for an existing Ollama server

[TheBlackSide243]

Description

Adds a shorthand for pointing Wardrowbe at an Ollama server that already runs elsewhere, such as another container on the same host or another machine.

Variable	Fills in
OLLAMA_BASE_URL	AI_BASE_URL, with /v1 added for the OpenAI-compatible API
OLLAMA_MODEL	both AI_VISION_MODEL and AI_TEXT_MODEL
OLLAMA_VISION_MODEL / OLLAMA_TEXT_MODEL	only one of the two
OLLAMA_TIMEOUT	AI_TIMEOUT

• Ollama stays a separate service: Wardrowbe only calls its HTTP API and never runs or downloads a model itself.
• Endpoints a user adds in Settings > AI still take precedence. These variables only set the server default.
• docker-compose.yml passes the variables through, and .env.example documents them.

The change is small and independent. It branches from main and touches only config.py, the compose file and .env.example.

Type of Change

• Bug fix (non-breaking change that fixes an issue)
• New feature (non-breaking change that adds functionality)
• Breaking change (fix or feature that would cause existing functionality to change)
• Documentation update
• Refactoring (no functional changes)
• CI/CD or build changes

Checklist

• I have read the CONTRIBUTING guide
• My code follows the project's coding style
• I have added tests that prove my fix/feature works
• New and existing tests pass locally
• I have updated documentation as needed
• My changes don't introduce new warnings or errors

Testing

• Backend: ruff check, ruff format --check and the full pytest suite, including the compose-to-settings checks in test_deploy_env.py.
• By hand: running against the Ollama app on my TrueNAS (OLLAMA_BASE_URL=http://<nas>:30068).

Test Environment

• Docker Compose
• Kubernetes
• Local development

🤖 Generated with Claude Code

Summary by Sourcery

Enable Wardrowbe to use an existing external Ollama server through environment-based configuration.

New Features:

• Add OLLAMA_* configuration shorthand for connecting to an externally hosted Ollama server and populating the corresponding AI endpoint, model, and timeout settings.

Enhancements:

• Preserve existing AI configuration behavior when Ollama-specific variables are not provided, including support for explicit /v1 endpoints and separate vision/text models.

Build:

• Pass OLLAMA_* variables through Docker Compose backend configuration.

Tests:

• Add coverage for Ollama configuration mapping, endpoint normalization, model overrides, and compatibility with existing AI settings.

[sourcery-ai]

Sorry @TheBlackSide243, you've used your own review budget of 250,000 diff characters for the last 7 days.

You can request another review in 6 days and 22 hours by commenting @sourcery-ai review. Upgrade to get a review now.

[sourcery-ai]

Reviewer's Guide

Introduces an external-Ollama configuration shorthand: Pydantic post-validation maps OLLAMA_* variables into the existing AI settings, Compose forwards them to the backend, and tests cover URL/model/timeout mapping and fallback behavior.

Flow diagram for external Ollama settings mapping

flowchart LR
    Env[OLLAMA_* environment variables] --> Compose[docker-compose.yml backend environment]
    Compose --> Settings[Settings.apply_ollama_settings]
    Settings --> AI[AI_BASE_URL and AI_* settings]
    AI --> Client[Wardrowbe HTTP client]
    Client --> Ollama[External Ollama server]
    User[User AI endpoints] --> AI
    User -->|takes precedence| Client

Loading

File-Level Changes

Change	Details	Files
Added OLLAMA_* settings that are translated into the existing AI configuration during Pydantic settings validation.	Added optional server URL, shared/per-modality model, and timeout fields. Normalized the Ollama URL to include a single trailing /v1 API path. Applied shared model values to both modalities, with modality-specific values taking precedence. Mapped the timeout and preserved existing AI settings when Ollama variables are absent. Added coverage for mappings, URL normalization, modality override behavior, and fallback behavior.	backend/app/config.py backend/tests/test_ollama_settings.py
Exposed the Ollama shorthand variables through the backend Docker Compose environment.	Passed all five OLLAMA_* variables into the backend container with empty defaults.	docker-compose.yml
Documented the new Ollama environment variables and their purpose for external Ollama deployments.	Added variable descriptions and default/override behavior to the example environment configuration.	.env.example

---

Tips and commands

Interacting with Sourcery

• Trigger a new review: Comment @sourcery-ai review on the pull request.
• Continue discussions: Reply directly to Sourcery's review comments.
• Generate a GitHub issue from a review comment: Ask Sourcery to create an
  issue from a review comment by replying to it. You can also reply to a
  review comment with @sourcery-ai issue to create an issue from it.
• Generate a pull request title: Write @sourcery-ai anywhere in the pull
  request title to generate a title at any time. You can also comment
  @sourcery-ai title on the pull request to (re-)generate the title at any time.
• Generate a pull request summary: Write @sourcery-ai summary anywhere in
  the pull request body to generate a PR summary at any time exactly where you
  want it. You can also comment @sourcery-ai summary on the pull request to
  (re-)generate the summary at any time.
• Generate reviewer's guide: Comment @sourcery-ai guide on the pull
  request to (re-)generate the reviewer's guide at any time.
• Resolve all Sourcery comments: Comment @sourcery-ai resolve on the
  pull request to resolve all Sourcery comments. Useful if you've already
  addressed all the comments and don't want to see them anymore.
• Dismiss all Sourcery reviews: Comment @sourcery-ai dismiss on the pull
  request to dismiss all existing Sourcery reviews. Especially useful if you
  want to start fresh with a new review - don't forget to comment
  @sourcery-ai review to trigger a new review!

Customizing Your Experience

Access your dashboard to:

• Enable or disable review features such as the Sourcery-generated pull request
  summary, the reviewer's guide, and others.
• Change the review language.
• Add, remove or edit custom review instructions.
• Adjust other review settings.

Getting Help

• Contact our support team for questions or feedback.
• Visit our documentation for detailed guides and information.
• Keep in touch with the Sourcery team by following us on X/Twitter, LinkedIn or GitHub.