Cohere /v2/chat native transport adapter.

 Cohere is OpenAI-compat-ish but differs enough to need its own
 adapter: it has a typed message-content array, a documents field,
 a citation_options control, citations on the response, and a
 streaming event taxonomy with separate content-start /
 content-delta / content-end plus tool-plan-delta and citation-*
 events.

Reference: litellm-ref/llms/cohere/chat/v2_transformation.py.

Cohere embed adapter — POST {base}/embed.

 Cohere's wire shape diverges from OpenAI's in three places:
- Request uses :texts (vector) instead of :input.
- Request carries a required :input_type
     (search_document / search_query / classification / clustering)
     which lives in canonical request as
     :embed/provider-options :input-type. Defaults to
     "search_document" when omitted — that's the safest fallback
     for general-purpose retrieval.
- Response embeddings live under :embeddings.float (newer API
     with multi-format support) or :embeddings (legacy single
     format). Usage is in :meta.billed_units.input_tokens.

 Live smoke is env-gated under COHERE_API_KEY.

Cohere /rerank transport. Jina uses the same core wire shape while also
supporting structured returned documents and optional returned embeddings.

Cohere additionally returns :meta.billed_units.search_units for
usage; Jina returns :usage {total_tokens}. Both are surfaced
through the canonical :response/usage where possible.