mirror of
https://github.com/lukaszraczylo/llm-testbench.git
synced 2026-10-12 00:45:19 +00:00
lukaszraczylo
6ad9dfbe42
An error row with zero latency reads as an instant rejection when it can be three exhausted request timeouts. A 651-second thinking-model generation looked instant in the 2026-08-30 run and misdirected the diagnosis toward gateway rejection. The error path now records the wall clock across all attempts.
12 lines
536 B
YAML
12 lines
536 B
YAML
endpoint: https://llm-gateway.example.com/v1
|
|
api_key: "" # optional; env LLMTB_API_KEY wins
|
|
models:
|
|
- uni/deepseek-v4-flash-0731
|
|
- uni/qwen3.6-27b
|
|
- uni/btl-4
|
|
concurrency: 8 # default when omitted; matches internal/config's default
|
|
request_timeout: 900s # default when omitted
|
|
max_tokens_default: 12000 # default when omitted; a reasoning model can spend
|
|
# thousands of tokens on reasoning_content before
|
|
# writing an answer, so this must stay generous
|