/ 
App-Greple-xlate-2.03
⭐ Starred 0 / App::Greple::xlate::llm::gpt6

NAME

App::Greple::xlate::llm::gpt6 - GPT-6 Astra translation engine (llm backend) for greple xlate module

SYNOPSIS

greple -Mxlate --xlate-engine=gpt6 --xlate=ja file.txt

DESCRIPTION

This module provides GPT-6 Astra translation support for the App::Greple::xlate module, calling the model through the llm command line tool (https://llm.datasette.io/). Select it with xlate -e gpt6 -t JA file.txt. Its cache files use the separate *.xlate-gpt6-*.json namespace.

The llm command must be installed and must know the gpt-6-astra model (check with llm models | grep gpt-6-astra). If the call fails, this module inspects the environment and reports what is missing.

This engine is context-aware: when re-translating changed blocks it receives the surrounding source text, neighboring translation pairs, and the previous version of the changed text, controlled by the --xlate-context-window option of App::Greple::xlate.

CONFIGURATION

This engine uses the following defaults:

  • model: gpt-6-astra

  • reasoning_effort: low (lowest effort supported by llm for GPT-6 Astra)

  • max_length: 3000 characters per batch

No temperature option is sent: GPT-6 Astra does not support this parameter, and llm only sends it when specified.

No max_tokens option is sent either. Omitting the cap leaves the translation output naturally bounded by the input size and avoids endpoint-specific output-token option differences.

No verbosity option is sent. The shared prompt requires a JSON array with no commentary; omitting this option also supports custom Responses models registered with llm 0.33.

MODEL REGISTRATION

If llm models does not list gpt-6-astra, add the following entry to extra-openai-models.yaml in the llm user directory (the directory containing the path printed by llm logs path). Preserve any existing entries.

- model_id: gpt-6-astra
  model_name: gpt-6-astra
  responses: true
  reasoning: true
  supports_schema: true

Check registration with llm models -m gpt-6-astra --options. Model registration does not grant API access; the API key must have access to GPT-6 Astra.

ENVIRONMENT VARIABLES

  • OPENAI_API_KEY - OpenAI API key, read by the llm command. Alternatively use llm keys set openai.

RELATED OPTIONS

  • --xlate-maxlen=chars - Maximum characters sent per request (defaults to this engine's value of 3000 when unset)

  • --xlate-maxline=n - Maximum lines sent per request (default 0 = unlimited); useful as a safety valve if a large batch causes a response element-count mismatch

  • --xlate-debug - Dump the llm command and parameters

DEPENDENCIES

SEE ALSO

AUTHOR

Kazumasa Utashiro

LICENSE

Copyright 2026 Kazumasa Utashiro.

This library is free software; you can redistribute it and/or modify it under the same terms as Perl itself.