Some checks failed
CI Code / Check coding style (pull_request) Successful in 46s
CI Code / Linux (arch) (pull_request) Failing after 9m46s
CI Code / Code Coverage (pull_request) Failing after 14m8s
CI Code / Check spelling (pull_request) Failing after 14m16s
CI Code / Linux (ubuntu) (pull_request) Failing after 14m24s
CI Code / Linux (debian) (pull_request) Failing after 14m33s
Rewrote internal JSON parsing to correctly handle whitespace, escaped quotes, and strict field context extraction. This prevents incorrect field names or provider names from being added to the model list. Added `ai_parse_models_from_json` public API to facilitate testing. Changed `/ai models` default behavior to always fetch fresh models. Replaced `--refresh` flag with `--cached` to display local cache. Added comprehensive unit tests covering OpenAI and Perplexity formats, array format, empty/null JSON, escaped quotes, and whitespace handling.