Add commercial LLM provider support (OpenAI, Anthropic) for AI suggestions#331
Merged
vincentmakes merged 5 commits intomainfrom Feb 27, 2026
Merged
Conversation
…tions Extend the AI description suggestion feature to support commercial LLM providers alongside the existing Ollama self-hosted option. Users can now choose between Ollama, OpenAI-compatible APIs (GPT, Gemini, Azure, OpenRouter, LM Studio, vLLM), and Anthropic Claude. DuckDuckGo web search is always used automatically for all providers to supply up-to-date context. API keys are encrypted at rest using Fernet. - Add multi-provider LLM dispatch (_call_openai_compatible, _call_anthropic) - Add provider_type and encrypted api_key to AI settings - Update admin UI with provider type dropdown and conditional fields - Add 71 backend tests covering all provider paths - Add translations for all 7 locales - Bump version to 0.22.0 https://claude.ai/code/session_01MpBvi4agFzqY6AL38D7BPK
![github-advanced-security[bot]](https://avatars.githubusercontent.com/in/57789?s=60&v=4){kind=small}
Remove provider_url from logger.info and logger.debug calls in ai_service.py to avoid clear-text logging of potentially sensitive endpoint information. The model name and provider type are sufficient for observability. https://claude.ai/code/session_01MpBvi4agFzqY6AL38D7BPK
Add explicit type annotation for json.loads() result to satisfy mypy's no-any-return check in _parse_llm_content(). https://claude.ai/code/session_01MpBvi4agFzqY6AL38D7BPK
httpx exceptions can include request headers (containing API keys) in their string representation. Replace `%s` exception logging and error messages with `type(exc).__name__` to prevent clear-text logging of sensitive credentials. Fixes CodeQL high-severity alerts. https://claude.ai/code/session_01MpBvi4agFzqY6AL38D7BPK
CodeQL traces taint from decrypt_value() through the ai_cfg dict, marking model and provider_type as sensitive since they originate from the same dict that holds the decrypted API key. Remove these variables from the log call to satisfy the clear-text logging check. https://claude.ai/code/session_01MpBvi4agFzqY6AL38D7BPK
This file contains hidden or bidirectional Unicode text that may be interpreted or compiled differently than what appears below. To review, open the file in an editor that reveals hidden Unicode characters.
Learn more about bidirectional Unicode characters
Sign up for free
to join this conversation on GitHub.
Already have an account?
Sign in to comment
2 participants
Add this suggestion to a batch that can be applied as a single commit.This suggestion is invalid because no changes were made to the code.Suggestions cannot be applied while the pull request is closed.Suggestions cannot be applied while viewing a subset of changes.Only one suggestion per line can be applied in a batch.Add this suggestion to a batch that can be applied as a single commit.Applying suggestions on deleted lines is not supported.You must change the existing code in this line in order to create a valid suggestion.Outdated suggestions cannot be applied.This suggestion has been applied or marked resolved.Suggestions cannot be applied from pending reviews.Suggestions cannot be applied on multi-line comments.Suggestions cannot be applied while the pull request is queued to merge.Suggestion cannot be applied right now. Please check back later.
Extend the AI description suggestion feature to support commercial LLM providers
alongside the existing Ollama self-hosted option. Users can now choose between
Ollama, OpenAI-compatible APIs (GPT, Gemini, Azure, OpenRouter, LM Studio, vLLM),
and Anthropic Claude. DuckDuckGo web search is always used automatically for all
providers to supply up-to-date context. API keys are encrypted at rest using Fernet.
https://claude.ai/code/session_01MpBvi4agFzqY6AL38D7BPK