scriptoriumadmin/litellm
1
0
Fork 0
mirror of https://github.com/BerriAI/litellm.git synced 2026-10-07 02:59:05 +00:00
Code Issues Projects Releases Packages Wiki Activity Actions 103

docs(complexity-router): state the reasoning boundary as inclusive

Browse source 
The mapping's last comparison is a strict 'score < complex_reasoning', so a score landing
exactly on the boundary falls through to REASONING. The table said greater than.
This commit is contained in:
Tin Chi Lo 2026-08-21 19:56:23 -07:00
parent 6ede2a2764
commit 41ffc87ed7
1 changed files with 1 additions and 1 deletions
Show stats Download patch file Download diff file Expand all files Collapse all files

2
litellm/router_strategy/complexity_router/README.md
View file

@ -32,7 +32,7 @@ The weighted sum is mapped to tiers using configurable boundaries:
| SIMPLE | < 0.10 | - | Basic questions, greetings |
| MEDIUM | 0.10 - 0.25 | `simple_medium` | Standard queries |
| COMPLEX | 0.25 - 0.50 | `medium_complex` | Technical, multi-part requests |
| REASONING | > 0.50 | `complex_reasoning` | Chain-of-thought, analysis |
| REASONING | >= 0.50 | `complex_reasoning` | Chain-of-thought, analysis |
The three boundaries must ascend, and any key you leave out is filled from the shipped default, so setting one boundary without the others can put them out of order. A set that decreases would strand the tier between the inverted pair and silently route its traffic to a costlier one, so it is rejected at config load with a message naming the resolved values. Set every boundary you need to move, not just one.