litellm/tests/e2e
jaideeppyne ab78459097 fix(cohere): handle multimodal inputs in token counting and guardrails
Response transformation crashed with TypeError when counting tokens for
multimodal (dict-shaped) embedding inputs, since encoding.encode() was
called directly on the dict instead of its text parts. Also removed a
dead, equally-buggy duplicate of the same loop in _transform_response.

Separately, the embeddings guardrail handler silently skipped multimodal
dict inputs instead of scanning them, letting prohibited text/image
content bypass the configured guardrail. It now extracts and scans the
text parts while leaving image parts untouched.
2026-08-13 09:01:47 +05:30
..
a2a fix(cohere): handle multimodal inputs in token counting and guardrails 2026-08-13 09:01:47 +05:30
access_control fix(cohere): handle multimodal inputs in token counting and guardrails 2026-08-13 09:01:47 +05:30
batches fix(cohere): handle multimodal inputs in token counting and guardrails 2026-08-13 09:01:47 +05:30
claude_code fix(cohere): handle multimodal inputs in token counting and guardrails 2026-08-13 09:01:47 +05:30
coverage_registry fix(cohere): handle multimodal inputs in token counting and guardrails 2026-08-13 09:01:47 +05:30
guardrails fix(cohere): handle multimodal inputs in token counting and guardrails 2026-08-13 09:01:47 +05:30
llm_translation fix(cohere): handle multimodal inputs in token counting and guardrails 2026-08-13 09:01:47 +05:30
load fix(cohere): handle multimodal inputs in token counting and guardrails 2026-08-13 09:01:47 +05:30
logging fix(cohere): handle multimodal inputs in token counting and guardrails 2026-08-13 09:01:47 +05:30
management fix(cohere): handle multimodal inputs in token counting and guardrails 2026-08-13 09:01:47 +05:30
mcp fix(cohere): handle multimodal inputs in token counting and guardrails 2026-08-13 09:01:47 +05:30
other fix(cohere): handle multimodal inputs in token counting and guardrails 2026-08-13 09:01:47 +05:30
quota_management fix(cohere): handle multimodal inputs in token counting and guardrails 2026-08-13 09:01:47 +05:30
router fix(cohere): handle multimodal inputs in token counting and guardrails 2026-08-13 09:01:47 +05:30
ui fix(cohere): handle multimodal inputs in token counting and guardrails 2026-08-13 09:01:47 +05:30
CLAUDE.md fix(cohere): handle multimodal inputs in token counting and guardrails 2026-08-13 09:01:47 +05:30
conftest.py fix(cohere): handle multimodal inputs in token counting and guardrails 2026-08-13 09:01:47 +05:30
CONTRIBUTING.md fix(cohere): handle multimodal inputs in token counting and guardrails 2026-08-13 09:01:47 +05:30
e2e_config.py fix(cohere): handle multimodal inputs in token counting and guardrails 2026-08-13 09:01:47 +05:30
e2e_db.py fix(cohere): handle multimodal inputs in token counting and guardrails 2026-08-13 09:01:47 +05:30
e2e_http.py fix(cohere): handle multimodal inputs in token counting and guardrails 2026-08-13 09:01:47 +05:30
junit_properties.py fix(cohere): handle multimodal inputs in token counting and guardrails 2026-08-13 09:01:47 +05:30
lifecycle.py fix(cohere): handle multimodal inputs in token counting and guardrails 2026-08-13 09:01:47 +05:30
models.py fix(cohere): handle multimodal inputs in token counting and guardrails 2026-08-13 09:01:47 +05:30
otel_client.py fix(cohere): handle multimodal inputs in token counting and guardrails 2026-08-13 09:01:47 +05:30
proxy_client.py fix(cohere): handle multimodal inputs in token counting and guardrails 2026-08-13 09:01:47 +05:30
pytest.ini fix(cohere): handle multimodal inputs in token counting and guardrails 2026-08-13 09:01:47 +05:30
test_e2e_http.py fix(cohere): handle multimodal inputs in token counting and guardrails 2026-08-13 09:01:47 +05:30
transport.py fix(cohere): handle multimodal inputs in token counting and guardrails 2026-08-13 09:01:47 +05:30