v0.1.1: Enhance Tool Parsing Logic
Added
-
Model Info Getter: Native
get_model_info()for SGLang client. -
Think Block Exclusion:
HermesToolCallParserexcludes tool calls inside<think>blocks by default, preventing parsing of draft tool calls from reasoning models (Qwen3, DeepSeek-R1). Configurable viathink_start_token/think_end_token. -
Tool Result Ordering: Tool results are now sorted by sequential IDs (
call_0000,call_0001, ...) before tokenization. Fixes ordering issues when Strands executes tools concurrently and returns results in completion order.
Full Changelog: v0.1.0...v0.1.1