llm-anthropic 0.31

Anthropic released Fable 5.2 and Mythos 5.2, and the author added both to llm-anthropic, so prompts can now be run through Fable 5.2 via the llm CLI. Testing pelican SVG generation at all five reasoning levels (low, medium, high, xhigh, max), the best result came from xhigh, while max failed to return an image at all after spending 128,000 tokens thinking. The author notes this is the same bug seen with Opus 5.5 but new for the Fable series, since Fable 5 and Fable 5.1 returned max effort pelicans fine.