/ 
Langertha-0.305
River stage one • 1 direct dependent • 1 total dependent
/ Langertha::Engine::AnthropicBase

NAME

Langertha::Engine::AnthropicBase - Base class for Anthropic-compatible engines

VERSION

version 0.305

SYNOPSIS

package My::AnthropicCompatible;
use Moose;

extends 'Langertha::Engine::AnthropicBase';

has '+url' => ( default => sub { 'https://api.example.com' } );

sub _build_api_key { $ENV{MY_API_KEY} || die "MY_API_KEY required" }
sub default_model { 'my-model-v1' }

__PACKAGE__->meta->make_immutable;

DESCRIPTION

Intermediate base class for engines speaking the Anthropic-compatible /v1/messages format. Extends Langertha::Engine::Remote and composes models/chat/streaming plus Anthropic-style tool calling and response parsing.

Concrete engines extending this class include Langertha::Engine::Anthropic, Langertha::Engine::MiniMax, and Langertha::Engine::LMStudioAnthropic.

THIS API IS WORK IN PROGRESS

api_key

Anthropic-compatible API key sent as x-api-key. Subclasses typically override _build_api_key to read a provider-specific environment variable.

api_version

The Anthropic API version header sent with every request. Defaults to 2023-06-01.

effort

Controls the depth of thinking for reasoning models. Values: low, medium, high. When set, passed as the effort parameter in the API request.

my $claude = Langertha::Engine::Anthropic->new(
    api_key => $ENV{ANTHROPIC_API_KEY},
    model   => 'claude-opus-4-6',
    effort  => 'high',
);

inference_geo

Controls data residency for inference. Values: us, eu. When set, passed as the inference_geo parameter to keep processing in the specified region.

my $claude = Langertha::Engine::Anthropic->new(
    api_key       => $ENV{ANTHROPIC_API_KEY},
    inference_geo => 'eu',
);

list_models

my $model_ids = $engine->list_models;
my $models    = $engine->list_models(full => 1);
my $models    = $engine->list_models(force_refresh => 1);

Fetches available models from the Anthropic API using cursor pagination. Returns an ArrayRef of model ID strings by default, or full model objects when full = 1> is passed. Results are cached for models_cache_ttl seconds (default: 3600). Pass force_refresh = 1> to bypass the cache.

_parse_rate_limit_headers

Parses anthropic-ratelimit-* headers from the HTTP response into a Langertha::RateLimit object. The raw hash captures extras like input-tokens-limit and output-tokens-limit.

SEE ALSO

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.