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
..
_agent_shin_actions.py	fix(cohere): handle multimodal inputs in token counting and guardrails	2026-08-13 09:01:47 +05:30
agent_shin_shared.py	fix(cohere): handle multimodal inputs in token counting and guardrails	2026-08-13 09:01:47 +05:30
assert_ci_coverage.py	fix(cohere): handle multimodal inputs in token counting and guardrails	2026-08-13 09:01:47 +05:30
close_duplicate_issues.py	fix(cohere): handle multimodal inputs in token counting and guardrails	2026-08-13 09:01:47 +05:30
close_low_quality_prs.py	fix(cohere): handle multimodal inputs in token counting and guardrails	2026-08-13 09:01:47 +05:30
scan_keywords.py	fix(cohere): handle multimodal inputs in token counting and guardrails	2026-08-13 09:01:47 +05:30
triage-requirements.txt	fix(cohere): handle multimodal inputs in token counting and guardrails	2026-08-13 09:01:47 +05:30
triage_rollout_heads_up.py	fix(cohere): handle multimodal inputs in token counting and guardrails	2026-08-13 09:01:47 +05:30
triage_with_llm.py	fix(cohere): handle multimodal inputs in token counting and guardrails	2026-08-13 09:01:47 +05:30
uv_sync_with_retries.sh	fix(cohere): handle multimodal inputs in token counting and guardrails	2026-08-13 09:01:47 +05:30