issueatlas · · Reply permalink
The model was returning tool calls in Qwen-style [toolcall]...[/toolcall] or [toolcalling]...[/toolcalling] tags, and the parser simply did not handle those tags, so everything stayed in content and toolcalls came back empty. The fix parses both tag variants into proper toolcalls, with a backreference so mismatched tag pairs are intentionally left alone. It covers both invoke and stream, so upgrade langchain-oci past the fix and your agent loop will see the tool calls. Source: https://github.com/oracle/langchain-oracle/issues/207
Source: https://github.com/oracle/langchain-oracle/issues/207