mirror of
https://github.com/openai/codex.git
synced 2026-09-10 20:26:47 +00:00
## Why Python SDK CI needs to exercise the checkout's CLI while retaining coverage of the wheel installation and its default runtime. ## What changed - Run the Python SDK test suite against the same Bazel-built CLI as the TypeScript SDK tests. Build and stage `codex-code-mode-host` alongside the CLI so it can be discovered. - Make the Python test harness prefer `CODEX_EXEC_PATH`, then a local debug build, then the installed runtime. Exclude optional turn-cost probes from recorded model requests. - Add a separate installation job that builds the Python SDK wheel and installs it in a fresh environment. ## Testing The installation smoke test verifies that imports resolve to the installed SDK and that its default runtime completes a mocked turn with the expected user input and final response. GitOrigin-RevId: 8e3126742a014e2cf042afe799bc657e1ea2a282
OpenAI Codex Python SDK
Build Python applications that start Codex threads, run turns, stream progress, and control workspace access.
Install
Install the SDK:
pip install openai-codex
Quickstart
The SDK reuses your existing Codex authentication when one is already available:
from openai_codex import Codex
with Codex() as codex:
thread = codex.thread_start()
result = thread.run("Explain this repository in three bullets.")
print(result.final_response)
thread.run(...) returns a TurnResult containing the final response,
collected items, and token usage.
Authentication
Existing Codex authentication is reused automatically. To start ChatGPT browser login explicitly:
from openai_codex import Codex
with Codex() as codex:
login = codex.login_chatgpt()
print(login.auth_url)
print(login.wait().success)
For device-code login:
with Codex() as codex:
login = codex.login_chatgpt_device_code()
print(login.verification_url, login.user_code)
login.wait()
For API-key login:
with Codex() as codex:
codex.login_api_key("sk-...")
Built-In Help
Use Python's standard help(openai_codex), help(Codex), or
python -m pydoc openai_codex documentation tools.
Documentation
The package is licensed under the repository Apache License 2.0.