Claude
527f4ba7ff
Tests pin down chain ordering (including ties), BaseAdvisor stream behaviour, redaction order versus memory and logging, the tool loop, and how a refusal surfaces on calls, streams and over HTTP. Co-Authored-By: Claude Sonnet 5 <[email protected]> Claude-Session: https://claude.ai/code/session_01Ja4jkzrbQ4LQZBNrb5mkZE
16 lines
659 B
Plaintext
16 lines
659 B
Plaintext
# TokenBudgetAdvisor: 40 tokens per request, 60 per user
|
|
|
|
alice asks short questions; "spent" is the usage the model reported:
|
|
call 1: answered, spent=13, model calls=1
|
|
call 2: answered, spent=26, model calls=2
|
|
call 3: answered, spent=39, model calls=3
|
|
call 4: answered, spent=52, model calls=4
|
|
call 5: answered, spent=65, model calls=5
|
|
call 6: refused (user alice has used 65 of 60 tokens), spent=65, model calls=5
|
|
|
|
bob pastes a stack trace of 103 estimated tokens:
|
|
refused: prompt is about 103 tokens, the limit per request is 40
|
|
model calls: 5 (was 5), bob's spent: 0
|
|
|
|
bob then asks a short question: answered, bob spent=13, alice spent=65
|