Ladder-aware Cline Anthropic caching — verify the rolling read/write ladder on the wire, then add the tools breakpoint and tune TTL. Updated for the 2026-08 AI-SDK monorepo.
原文语言:英语
菜单
SkillsMP 已收集 OnlyTerp/prompt-cache-skills 中的 14 个 Skill。打开任一 Skill 可查看来源和详情。
已展示 14 / 14 个已收集 Skill。
Ladder-aware Cline Anthropic caching — verify the rolling read/write ladder on the wire, then add the tools breakpoint and tune TTL. Updated for the 2026-08 AI-SDK monorepo.
原文语言:英语
Ladder-aware Roo Code Anthropic caching — verify the rolling read/write ladder on the wire, then close the real gaps (Vertex 4-block budget, MiniMax path).
原文语言:英语
Ladder-aware Continue Anthropic caching — verify the rolling ladder on the wire, then enable it by default and add TTL coverage.
原文语言:英语
Aider uses 5min TTL by default and works around long pauses with keepalive pings. Wire up the 1h TTL beta instead.
原文语言:英语
Aider's --cache-prompts is off by default. Flip it on for supported models.
原文语言:英语
Cline OpenAI native provider sends no prompt_cache_key. Add a stable per-task key so cached_tokens stops being zero.
原文语言:英语
Cline's system prompt includes a timestamp that may be recomputed per request, invalidating the system-prompt cache.
原文语言:英语
Continue's prompt caching is opt-in via config and off by default. Flip the default to systemAndTools.
原文语言:英语
Continue's Gemini provider doesn't use the cachedContents API at all. Add explicit caching for sessions over the minimum token threshold.
原文语言:英语
OpenCode places cachePoint on Bedrock messages containing DocumentBlocks, which produces a "nothing available to cache" error.
原文语言:英语
OpenCode's caching detection misses OpenAI-compatible proxies routing to Anthropic/Bedrock. Broaden the predicate.
原文语言:英语
OpenCode doesn't set prompt_cache_key for Mistral models, missing the documented 10% cached-token discount.
原文语言:英语
Roo Code's Bedrock provider silently disables caching for custom ARNs. Populate cachableFields to fix.
原文语言:英语
One-line description of what this fix does and why it matters.
原文语言:英语