Victor Vargas e6830161bc fix(llamacpp,anthropic): SSE headroom, no-choices guard, real context window ... - llamacpp: 4MB SSE scanner buffer (the 64KB bufio.Scanner default killed streams whose single line exceeded it, e.g. a write tool call carrying a whole file) and an empty-choices guard in toResponse instead of a panic; request payload now uses bytes.NewReader (drops a full string copy). - anthropic: Capabilities() reported a 1M-token context window for any non-haiku model. Callers use that number to decide when to compact, so compaction would have fired far too late and requests overflowed the real window. Default is now the standard 200k, configurable via Config.ContextWindow for extended-window models/plans. Co-Authored-By: Claude Fable 5 <noreply@anthropic.com>		2026-07-12 16:14:15 -07:00
..
anthropic	fix(llamacpp,anthropic): SSE headroom, no-choices guard, real context window	2026-07-12 16:14:15 -07:00
llamacpp	fix(llamacpp,anthropic): SSE headroom, no-choices guard, real context window	2026-07-12 16:14:15 -07:00
openai	fix(openai): make streaming actually work; honor configured model	2026-07-12 16:14:01 -07:00