Ed Zynda 2de98d32be fix(ui): accurate context token tracking including cache tokens ...

- Include all token categories in context fill calculation:
  InputTokens + CacheReadTokens + CacheCreationTokens + OutputTokens
- With Anthropic/kimi prompt caching, InputTokens can be near-zero
  while CacheReadTokens holds the bulk of the context
- Include OutputTokens since assistant output becomes context next turn
- Remove max-only guard in SetContextTokens so context shrinks after
  compaction instead of staying stuck at the high-water mark
- Reset context tokens to 0 after compaction in both SDK and UI layers
- Use real API-reported token counts in ShouldCompact() instead of
  the chars/4 text heuristic which misses system prompts and tool defs

2026-04-10 17:05:47 +03:00

..

extensions/test

fix(test): add return after t.Fatal to silence SA5011 nil-deref warnings

2026-04-01 21:24:02 +03:00

kit

fix(ui): accurate context token tracking including cache tokens

2026-04-10 17:05:47 +03:00