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
17 lines
665 B
Plaintext
17 lines
665 B
Plaintext
# What is actually in the chain
|
|
|
|
one custom advisor at HIGHEST_PRECEDENCE + 100; the chain a call runs through:
|
|
Dump HIGHEST_PRECEDENCE + 100
|
|
Tool Calling Advisor HIGHEST_PRECEDENCE + 300
|
|
call LOWEST_PRECEDENCE
|
|
|
|
and the chain a stream runs through:
|
|
Dump HIGHEST_PRECEDENCE + 100
|
|
Tool Calling Advisor HIGHEST_PRECEDENCE + 300
|
|
stream LOWEST_PRECEDENCE
|
|
|
|
the same, with ToolCallingAdvisor.builder().build() added by hand:
|
|
Dump HIGHEST_PRECEDENCE + 100
|
|
Tool Calling Advisor HIGHEST_PRECEDENCE + 300
|
|
call LOWEST_PRECEDENCE
|