Function create_fallback_models

codewiki/src/be/llm_services.py:133–137

Create fallback models chain from configuration.

(config: Config)

    and extends it). OpenAI-compatible proxies such as LiteLLM forward the
    markers to providers that support prompt caching; providers that don't
    either ignore the field or reject the request with a 4xx, in which case the
    request is retried once without markers and the (base_url, model) pair is
    remembered so later calls skip injection entirely.
    """

    # Plain class attributes (not dataclass fields) so instances copied without
    # __init__ still resolve them.
    _prompt_caching_enabled = False