Sydney Runkle 4cd09d39ae test(langchain): fix benchmark quality issues from code review ...

- Move middleware construction inside benchmarked lambdas for fresh instances
- Rework memory test to observation-only with print output (no hard assertion)
- Add deeply-nested Pydantic schema tool (RouteSchema) to LARGE_TOOLS (15 tools)
- Update docstrings to document '10 accesses per iteration' in schema benchmarks
- Fix bare `_ =` pattern in schema benchmarks (bare expressions)
- Mark memory test with @pytest.mark.benchmark to exclude from normal runs

Co-Authored-By: Claude Sonnet 4.6 <noreply@anthropic.com>

2026-04-27 13:37:51 -04:00

..

benchmarks

test(langchain): fix benchmark quality issues from code review

2026-04-27 13:37:51 -04:00

cassettes

fix(openai): add type: message to Responses API input items (#35693)

2026-03-15 12:43:16 -04:00

integration_tests

refactor(langchain): rename _SUPPORTED_PROVIDERS -> _BUILTIN_PROVIDERS (#35100)

2026-02-09 15:26:01 -05:00

unit_tests

feat(langchain): ls_agent_type tag on create_agent calls (#36774)

2026-04-17 15:39:22 -07:00

__init__.py

…