Our token estimation heuristic (chars/3 * 1.1 for code, chars/4 * 1.1 for text)
slightly undercounts over long sessions with hundreds of tool calls. This
accumulated drift of ~89 tokens caused Anthropic API 400 errors:
'prompt is too long: 200089 tokens > 200000 maximum'
Fix: ContextWindow::new() now applies a 1% buffer, setting total_tokens to 99%
of the provider-reported limit. For a 200k window this gives 198k, providing a
2000-token safety margin that absorbs estimation drift.
All percentage calculations, compaction thresholds, and thinning triggers
operate against the buffered limit, so compaction fires earlier and we never
send a request the API will reject.
Dhanji R. Prasanna
0410efd41b