Ollama v0.40.14-rc0 发布

What's Changed

• ci: pin buildx to workaround deadlock by @dhiltgen in #19373
• openai: preserve readable Responses input content by @hoyyeva in #19192
• mlx: sort long top-k rows in chunks by @dhiltgen in #19392
• app: make ChatGPT disconnect failures retryable by @hoyyeva in #19336
• launch: use model output limits for Claude Code by @ParthSareen in #19410
• openai: don't override model sampler defaults by @dhiltgen in #19432
• launch: check ChatGPT routing before configuring by @hoyyeva in #19470
• server: decode cloud web search responses by @ParthSareen in #19476

Full Changelog: v0.40.13...v0.40.14-rc0