feat(langchain): Broaden AI provider detection beyond OpenAI and Anthropic #5707
@sentry/warden / warden: find-bugs
completed
Mar 25, 2026 in 2m 50s
1 issue
find-bugs: Found 1 issue (1 medium)
Medium
Test filters for wrong span operation type, causing test to fail - `tests/integrations/langchain/test_langchain.py:2304-2307`
The test filters for spans with op == "gen_ai.pipeline" at lines 2304-2305, but on_llm_start creates spans with op=OP.GEN_AI_GENERATE_TEXT which equals "gen_ai.generate_text". This means llm_spans will always be empty and the assertion len(llm_spans) > 0 will fail, making this test non-functional for validating AI system detection.
Duration: 2m 48s · Tokens: 842.5k in / 7.9k out · Cost: $1.35 (+extraction: $0.00, +fix_gate: $0.00)
Annotations
Check warning on line 2307 in tests/integrations/langchain/test_langchain.py
sentry-warden / warden: find-bugs
Test filters for wrong span operation type, causing test to fail
The test filters for spans with `op == "gen_ai.pipeline"` at lines 2304-2305, but `on_llm_start` creates spans with `op=OP.GEN_AI_GENERATE_TEXT` which equals `"gen_ai.generate_text"`. This means `llm_spans` will always be empty and the assertion `len(llm_spans) > 0` will fail, making this test non-functional for validating AI system detection.
Loading