Sydney Runkle 7af79039fc fix: only increment thread count on successful executions (#33837) ...

* for run count + thread count overflow we should warn model not to call
again
* don't tally mocked tool calls in thread limit -- consider the
following
  * run limit is 1 
  * thread limit is 3
  * first run calls the tool 2 times, 1 executes, 1 is blocked
* we should only count the successful execution above towards the total
thread count
* raise more helpful warnings on invalid config

2025-11-05 10:00:07 -05:00

..

integration_tests

chore: use model IDs, latest anthropic models (#33747)

2025-10-30 16:13:28 -04:00

unit_tests

fix: only increment thread count on successful executions (#33837)

2025-11-05 10:00:07 -05:00

__init__.py

feat(langchain): v1 scaffolding (#32166)

2025-07-24 09:47:48 -04:00