mirror of
https://github.com/docker/docker-agent.git
synced 2026-11-04 10:02:15 +00:00
Arnaud Héritier
99a3c80532
Make GPT-5.6 easier and more efficient to use by updating provider defaults, model-specific reasoning levels, built-in agents, examples, and the embedded models.dev catalog. References: - https://developers.openai.com/api/docs/guides/latest-model - https://developers.openai.com/api/docs/guides/reasoning - https://developers.openai.com/api/docs/models/gpt-5.6 - https://developers.openai.com/api/docs/models/gpt-5.6-sol - https://developers.openai.com/api/docs/models/gpt-5.6-terra - https://developers.openai.com/api/docs/models/gpt-5.6-luna - https://developers.openai.com/codex/models - https://models.dev/models/openai/gpt-5.6-sol - https://models.dev/models/openai/gpt-5.6-terra - https://models.dev/models/openai/gpt-5.6-luna
29 lines
784 B
YAML
29 lines
784 B
YAML
# Example: ChatGPT account (subscription) provider
|
|
#
|
|
# Use your ChatGPT Plus/Pro/Business subscription instead of an
|
|
# OPENAI_API_KEY. Sign in once with (pick chatgpt in the provider list):
|
|
#
|
|
# docker agent setup
|
|
#
|
|
# The browser sign-in stores an OAuth credential that docker-agent refreshes
|
|
# automatically; check it anytime with `docker agent doctor`. Requests go to
|
|
# the ChatGPT Codex backend, which serves the gpt-5 model family over the
|
|
# Responses API.
|
|
#
|
|
# Run with:
|
|
#
|
|
# docker agent run examples/chatgpt.yaml
|
|
|
|
models:
|
|
gpt:
|
|
provider: chatgpt
|
|
model: gpt-5.6
|
|
thinking_budget: medium
|
|
|
|
agents:
|
|
root:
|
|
model: gpt
|
|
description: A helpful assistant running on your ChatGPT subscription
|
|
instruction: |
|
|
You are a helpful assistant. Answer concisely.
|