fix(agent): honor configured model max tokens

2026-05-04 09:36:43 +08:00
parent 52e2777821
commit a78e622dfe
4 changed files with 102 additions and 2 deletions
--- a/gateway/run.py
+++ b/gateway/run.py
@@ -12251,6 +12251,7 @@ class GatewayRunner:
    # Add more here as new baked-at-construction config settings are added.
    _CACHE_BUSTING_CONFIG_KEYS: tuple = (
        ("model", "context_length"),
+        ("model", "max_tokens"),
        ("compression", "enabled"),
        ("compression", "threshold"),
        ("compression", "target_ratio"),