max_tokens defaults to 32k (compat servers were capping at ~2k, truncating file
writes); a below-limit model 400 drops the param and retries on the server default.
claude/ ids use Anthropic's native Bedrock client; everything else goes via Converse.
Credentials: explicit keys, named profile (incl. SSO), or the ambient AWS chain.
New reasoning_delta event; traces persist as a display sidecar stripped from provider feeds.
Sources: compat vendors' reasoning_content and Gemini thought summaries (include_thoughts).
Live-verified on GLM via Together and Gemini 3; Gemini tool loops stay healthy.
Signatures ride the assistant message as a _gemini sidecar and are reattached in tool loops.
Thought-flagged parts are filtered from answer text; foreign sidecars stripped on the OpenAI wire.
Live-verified both Gemini 3 models end-to-end; without the echo they 400 on every tool loop.
Imported from andrewyng/aisuite@1b4bbf303e
(contents of its platform/ directory, hoisted to the repo root).
Development history prior to this commit lives in that repository.
Co-authored-by: Devika <devikaverma11@gmail.com>
Rohit C Prasad