Teknium 60fdb58ce4 fix(agent): update context compressor limits after fallback activation (#3305) ...

When _try_activate_fallback() switches to the fallback model, it
updates the agent's model/provider/client but never touches
self.context_compressor. The compressor keeps the primary model's
context_length and threshold_tokens, so compression decisions use
wrong limits — a 200K primary → 32K fallback still uses 200K-based
thresholds, causing oversized sessions to overflow the fallback.

Update the compressor's model, credentials, context_length, and
threshold_tokens after fallback activation using get_model_context_length()
for the new model.

Cherry-picked from PR #3202 by binhnt92.

Co-authored-by: binhnt92 <binhnt.ht.92@gmail.com>

2026-03-26 18:10:50 -07:00

2.9 KiB

Raw Blame History

View Raw