Fix chat template turn closure after tool-call-only turns

Add canonical header to chat template

fix: scope preserve_thinking to tool-call turns, remove extra newline in continuation turns

fix: scope preserve_thinking to tool-call turns only

fix: update stale comment — thinking channel no longer tool-call-only

fix: render thinking channel regardless of tool_calls presence

fix: revert add_generation_prompt regression + preserve_thinking default

fix: prevent extra <turn|> when assistant has content + tool_calls + continuation

fix: restore model turn + thinking cue after tool responses

fix: chat template — null handling, reasoning preservation, turn-tag balance, input validation

Update README.md

Update README.md

fix(chat_template): Emit multimodal placeholders in tool response content-parts (#28)

Fix lineage (#31)

fix(chat_template): update SI and tool call handling (#26)

Update response schema (#15)

fix: prefix-preserving tool calls + dialog compliance (#13)

Preparing for release!