mirror of
https://github.com/agent0ai/agent-zero.git
synced 2026-05-17 04:01:13 +00:00
f67564a8ae
Create a generic OAuth Connections plugin with Codex/ChatGPT Account as the first provider, using OpenAI's device-code flow to persist Codex-compatible account tokens. Expose a loopback OpenAI-compatible wrapper for models, responses, and chat completions, and point LiteLLM at the container-local Agent Zero origin. Add a dummy API-key extension and focused tests so the account-backed provider appears configured without requiring a user-entered key. docs: add Codex plan OAuth callout Highlight that Agent Zero can use an existing OpenAI Codex plan through the new OAuth flow. Add the account-backed LLM plans image and surface the section from the README navigation, while pointing toward future Gemini CLI and Claude Code integrations. Handle Codex account SSE chat chunks Teach the Codex/ChatGPT account bridge to extract text from OpenAI-style SSE chat completion deltas and fall back to a normal output_text response when upstream only streams chunks. Strip user-supplied stream kwargs before LiteLLM calls so Agent Zero owns streaming mode and custom parameters cannot pass stream twice. Add targeted tests for streamed delta extraction and reconstructed responses. update README.md with LLM plans mention
33 lines
947 B
YAML
33 lines
947 B
YAML
# Generic OAuth connection settings. Only Codex is implemented for now.
|
|
codex:
|
|
enabled: true
|
|
|
|
# Empty means auto-discover CODEX_HOME/auth.json, ~/.codex/auth.json,
|
|
# CHATGPT_LOCAL_HOME/auth.json, then ~/.chatgpt-local/auth.json.
|
|
auth_file_path: ""
|
|
|
|
issuer: "https://auth.openai.com"
|
|
token_url: "https://auth.openai.com/oauth/token"
|
|
client_id: "app_EMoamEEZ73f0CkXaXp7hrann"
|
|
scopes:
|
|
- openid
|
|
- profile
|
|
- email
|
|
- offline_access
|
|
- api.connectors.read
|
|
- api.connectors.invoke
|
|
|
|
open_browser_from_server: false
|
|
forced_workspace_id: ""
|
|
|
|
upstream_base_url: "https://chatgpt.com/backend-api/codex"
|
|
codex_version: ""
|
|
models: []
|
|
request_timeout_seconds: 120
|
|
|
|
# The OpenAI-compatible wrapper is mounted at /oauth/codex/v1.
|
|
# It is loopback-only by default and does not emit CORS headers.
|
|
proxy_base_path: "/oauth/codex"
|
|
callback_path: "/auth/callback"
|
|
require_proxy_token: false
|
|
proxy_token: ""
|