NAME
Langertha::Role::HermesTools - Hermes-style tool calling via XML tags
VERSION
version 0.304
SYNOPSIS
package Langertha::Engine::MyEngine;
use Moose;
extends 'Langertha::Engine::Remote';
with 'Langertha::Role::Tools';
with 'Langertha::Role::HermesTools';DESCRIPTION
This role implements tool calling via Hermes-style XML tags. Instead of using an API's native tools parameter, tool definitions are injected into the system prompt as <tools> XML and the model responds with <tool_call> XML tags containing JSON. This works with any chat model regardless of native tool API support.
Engines composing this role get implementations of the five methods required by Langertha::Role::Tools: "format_tools", "response_tool_calls", "extract_tool_call", "format_tool_results", and "response_text_content". It also provides "build_tool_chat_request" to inject tools into the system prompt instead of passing them as an API parameter.
hermes_call_tag
hermes_call_tag => 'function_call'The XML tag name used for tool calls in the model's output. Both the prompt template and the response parser use this tag. Defaults to tool_call.
hermes_response_tag
hermes_response_tag => 'function_response'The XML tag name used when sending tool results back to the model. Defaults to tool_response.
hermes_tool_instructions
hermes_tool_instructions => 'You are a helpful assistant that can call functions.'The instruction text prepended to the Hermes tool system prompt. Customize this to change the model's behavior without altering the structural XML template. The default instructs the model to call functions without making assumptions about argument values.
hermes_tool_prompt
The full system prompt template used for Hermes tool calling. Must contain a %s placeholder where the tools JSON will be inserted. Built automatically from "hermes_tool_instructions" and "hermes_call_tag". Override this only if you need full control over the prompt structure.
hermes_extract_content
my $content = $self->hermes_extract_content($data);Extracts raw text content from a parsed LLM response for Hermes tool call parsing. Defaults to OpenAI response format (choices[0].message.content). Override this method in engines with non-OpenAI response structures.
format_tools
Returns the MCP tool definitions as-is for JSON encoding into the Hermes system prompt.
build_tool_chat_request
Builds a chat request with tool definitions injected into the system prompt as XML, rather than passing them as an API parameter.
response_tool_calls
Parses <tool_call> XML tags from the model's text output and returns an ArrayRef of tool call HashRefs with name and arguments.
extract_tool_call
Extracts tool name and arguments from a Hermes tool call HashRef.
response_text_content
Extracts the final text content from the response, stripping any <tool_call> XML tags.
format_tool_results
Formats tool execution results as <tool_response> XML messages for the next conversation turn.
SEE ALSO
Langertha::Role::Tools - Base tool calling role
Langertha::Engine::NousResearch - Hermes model engine
Langertha::Engine::AKI - AKI.IO engine using Hermes tools
SUPPORT
Issues
Please report bugs and feature requests on GitHub at https://github.com/Getty/langertha/issues.
CONTRIBUTING
Contributions are welcome! Please fork the repository and submit a pull request.
AUTHOR
Torsten Raudssus <torsten@raudssus.de> https://raudss.us/
COPYRIGHT AND LICENSE
This software is copyright (c) 2026 by Torsten Raudssus.
This is free software; you can redistribute it and/or modify it under the same terms as the Perl 5 programming language system itself.