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
10 lines
385 B
Plaintext
10 lines
385 B
Plaintext
# Token accounting on a stream
|
|
|
|
same question, same answer:
|
|
call, usage from the response: 9 tokens
|
|
stream, usage on the last chunk: 9 tokens
|
|
stream, no usage reported (estimated): 9 tokens
|
|
|
|
A stream that reports no usage is billed by the provider all the same. The estimate above
|
|
matches only because this scripted model and the advisor use the same tokenizer.
|