OnlyTerp@Prompt Cache Skills

One-line description of what this fix does and why it matters.

Aider uses 5min TTL by default and works around long pauses with keepalive pings. Wire up the 1h TTL beta instead.

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

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).

Aider's --cache-prompts is off by default. Flip it on for supported models.

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.

Cline OpenAI native provider sends no prompt_cache_key. Add a stable per-task key so cached_tokens stops being zero.

Roo Code's Bedrock provider silently disables caching for custom ARNs. Populate cachableFields to fix.

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

Continue's Gemini provider doesn't use the cachedContents API at all. Add explicit caching for sessions over the minimum token threshold.

Ladder-aware Continue Anthropic caching — verify the rolling ladder on the wire, then enable it by default and add TTL coverage.

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

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

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