kit/internal/app at 2de98d32be6f98b328497f53391e3262ed293c21 - kit

mirror of https://github.com/mark3labs/kit.git synced 2026-06-14 03:30:26 +00:00

Files

T

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

app_test.go

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

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

app.go

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

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

events.go

fix(ui): show MCP tools in /tools and status bar after async loading

2026-04-07 16:29:09 +03:00

messages_test.go

refactor(pkg/kit): use fantasy type aliases for LLM types with clean SDK names