Mario Zechner d7868b0998 feat(ai): add reasoning token counts to Usage ...

Add optional reasoning?: number to Usage as a subset of output. Populate
for Anthropic (output_tokens_details.thinking_tokens), OpenAI
Responses/Codex/Azure (output_tokens_details.reasoning_tokens), OpenAI
Completions (completion_tokens_details.reasoning_tokens), and Google
Generative AI / Vertex (thoughtsTokenCount). Bedrock Converse and Mistral
do not return a reasoning breakdown, so they stay unset.

closes #6057

2026-06-25 10:35:02 +02:00

..

agent

docs(agent): update models phase 9 plan

2026-06-24 14:46:13 +02:00

ai

feat(ai): add reasoning token counts to Usage

2026-06-25 10:35:02 +02:00

coding-agent

fix(coding-agent): drain startup benchmark replies

2026-06-25 02:08:29 -05:00

tui

Add [Unreleased] section for next cycle

2026-06-23 23:45:39 +02:00