Module common 

Shared provider helpers, grouped by responsibility behind stable imports.

Functions

execute_token_count_request

Execute an exact token-count request when provider endpoint is available. Returns Ok(None) when endpoint appears unsupported.

extract_reasoning_text_from_detail_values

extract_reasoning_text_from_serialized_details

forward_prompt_cache_with_state

make_anthropic_thinking_config

Generates the interleaved thinking configuration for Anthropic models. This provides consistent thinking configuration across all Anthropic provider implementations.

parse_prompt_tokens_from_count_response

Parse prompt/input token counts from common response shapes.

strip_generation_controls_for_token_count

Remove generation-only controls from a payload before exact prompt-token counting. Token-count endpoints generally require only prompt-side fields.