AI & LLM Engineering · By OnlyTerp

Patches Aider to request Anthropic's one-hour prompt cache lifetime, so long pauses between turns no longer expire the cache or need paid keepalive pings.

OnlyTerp/prompt-cache-skills

Patch recipe that turns on Aider's --cache-prompts by default for models that support caching, with a verification procedure against the wire request.

OnlyTerp/prompt-cache-skills

Verifies how Cline marks Anthropic prompt-cache breakpoints on the wire, then adds a tools breakpoint and tunes the cache TTL in its AI SDK code.

OnlyTerp/prompt-cache-skills

Patch guide for adding a stable per-task prompt_cache_key to Cline's OpenAI native provider so cached token counts stop reading as zero.

OnlyTerp/prompt-cache-skills

Cline's system prompt includes a timestamp that may be recomputed per request, invalidating the system-prompt cache.

OnlyTerp/prompt-cache-skills

Continue's prompt caching is opt-in via config and off by default.

OnlyTerp/prompt-cache-skills

Continue's Gemini provider doesn't use the cachedContents API at all.

OnlyTerp/prompt-cache-skills

OpenCode places cachePoint on Bedrock messages containing DocumentBlocks, which produces a "nothing available to cache" error.

OnlyTerp/prompt-cache-skills

OpenCode's caching detection misses OpenAI-compatible proxies routing to Anthropic/Bedrock.

OnlyTerp/prompt-cache-skills

OpenCode doesn't set promptcachekey for Mistral models, missing the documented 10% cached-token discount.

OnlyTerp/prompt-cache-skills

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).

OnlyTerp/prompt-cache-skills