| Filename | Latest commit message | Latest commit date |
|---|---|---|
5eacc99146
/api/dashboard-state reported ctx_tokens from raw ctx_usage.input_tokens, which is only the *uncached* input. With prompt caching the bulk of the prompt is cache-read, so input_tokens is ~0 and every SW4RM card showed 'ctx·0k'. Use ctx_usage.context_tokens() (input + cache-read + cache-creation = the real window size) to match the agent page (ships the full ctx_usage) and turn.rs's cache-TTL check. Doc comment updated. |
||
| .. | ||
| prompts | ||
| src | ||
| Cargo.toml | ||