mirror of
https://github.com/BerriAI/litellm.git
synced 2026-09-09 22:31:41 +00:00
31a67561ab
The LLM classifier capped every prior turn at 200 characters independently, so a 785 character turn was cut even when the whole block it belonged to was 353 characters. A character budget now bounds the block: turns are taken newest first and quoted whole while they fit, older turns are dropped whole once it runs out, and only the turn straddling the boundary is cut. The per-turn cap stays as an optional clamp for operators who set it deliberately, defaulting to unset. |
||
|---|---|---|
| .. | ||
| adaptive_router | ||
| test_auto_router.py | ||
| test_base_routing_strategy.py | ||
| test_budget_limiter_hotpath.py | ||
| test_complexity_router.py | ||
| test_lar1_routing.py | ||
| test_litellm_encoder.py | ||
| test_lowest_latency.py | ||
| test_quality_router.py | ||
| test_router_routing_groups.py | ||
| test_router_routing_plugins.py | ||
| test_router_tag_regex_routing.py | ||
| test_router_tag_routing.py | ||
| test_savings_baseline.py | ||