habemus-papadum-codex-launcher
Import: pdum.codex_launcher. CLI: pdum-codex.
Self-contained Codex profiles, async foreground app-server ownership, PID-aware cleanup, a thin browser-compatible WebSocket relay, inspection processors and optional upstream MITM. Uses your selected installed Codex; no binary is bundled.
uv run pdum-codex launch --temp --model gpt-6-luna
Connect the ordinary CLI using codex --remote ENDPOINT, with the printed
endpoint. Temporary profiles can snapshot available file-backed credentials with
a warning; submitting prompts can incur model usage. Default operation trusts
the operator's network: sandbox/approvals off and all-interface TCP listeners.
Persistent profiles:
uv run pdum-codex profile create research --model gpt-6-luna
uv run pdum-codex --profile research profile configure
uv run pdum-codex --profile research auth login
uv run pdum-codex --profile research launch
uv run pdum-codex --profile research status
uv run pdum-codex --profile research stop
On a terminal, create/configure use Rich previews and Questionary selections.
New profiles default to importing your native Codex home; use --clean for fresh
settings or --no-interview for scripts. Select all/none/individual marketplaces,
plugins, MCP servers and skills, then accept or edit the remaining native TOML.
Imports are experimental and preserve unknown settings. Configure starts from
that profile, not your ordinary developer configuration.
Authentication can preserve native settings, use ChatGPT login, refer to an API-key
environment variable, or use AWS → OpenAI API federation. Configuration and login
are separate, with --login for a post-save login action. The federation extra
adds the exchange dependency; live AWS mapping/login/renewal qualification remains
pending. See the profile guide.
The Python API accepts a directory. async with launch(directory, LaunchOptions(...))
owns the process and yields its endpoint, PID and async status/stop operations.
pdum.codex_launcher.cli.create_app() returns a mountable Typer command tree.
MITM is absent by default. Install the mitm extra and use
--mitm --capture-dir PATH --capture to record upstream traffic, or omit
--capture and toggle it later with capture on/off.
--record NEW_FILE records the independent client-protocol stream.
JsonlRecorder, UsageObserver and explicit processors run independently
of forwarding; missing usage stays unknown and repeated totals are not summed.
The management extra provides pdum.codex_launcher.management.create_app(server)
for optional FastAPI status/capture/stop routes over the existing process owner.
It neither starts another server process nor adds a second lifecycle.
The first implementation passes real local tests and a small live Luna turn through the vanilla remote CLI, relay and MITM. See current capabilities and limitations and the testing guide. The wider architecture includes further unimplemented conveniences and unqualified federation renewal; it is not a promise that every proposed feature ships now.
From the repository root:
./scripts/setup.sh
uv run --frozen pytest packages/codex-launcher/tests
uv build --package habemus-papadum-codex-launcher
Follow AGENTS.md. Never commit profiles/captures or modify the operator's ordinary Codex state in tests.
Metadata
Release files for habemus-papadum-codex-launcher 0.1.0
For a detailed explanation of source distributions (sdists) and built distributions (wheels), please see the package formats documentation.
Source distribution (sdist)
| File | Size | Uploaded | Provenance | Actions |
|---|---|---|---|---|
| habemus_papadum_codex_launcher-0.1.0.tar.gz | 70.4 kB | Without provenance | Details for habemus_papadum_codex_launcher-0.1.0.tar.gz |
Built distribution (wheel)
| File | Interpreter | ABI | Platform | Actions Reset |
|---|---|---|---|---|
| habemus_papadum_codex_launcher-0.1.0-py3-none-any.whl | Python 3 | none | any | Details for habemus_papadum_codex_launcher-0.1.0-py3-none-any.whl |
Total release size: 126.1 kB
Release files / habemus_papadum_codex_launcher-0.1.0.tar.gz
| Download URL | habemus_papadum_codex_launcher-0.1.0.tar.gz |
|---|---|
| Size | 70.4 kB |
| Tags | Source |
|
SHA-256 checksum How to use checksums |
9e3fd0405e02bc582ea0f17810271cb883cf252e0de99611e22a7d9901f0e0b5
|
|
BLAKE2b-256 checksum How to use checksums |
d2f225ac145f8d38c05d3bf41cf505786200b6ebe7e8269003f73f6a6b654847
|
| Upload date | |
|
Uploaded using Trusted Publishing? What is trusted publishing? |
No |
| Uploaded via |
twine/7.0.0 CPython/3.13.14
|
Release files / habemus_papadum_codex_launcher-0.1.0-py3-none-any.whl
| Download URL | habemus_papadum_codex_launcher-0.1.0-py3-none-any.whl |
|---|---|
| Size | 55.7 kB |
| Tags | Python 3 |
|
SHA-256 checksum How to use checksums |
e96a0574fc3e00655dfd7ba15c7a02a491ee22278ba792a2823895a26fd5df88
|
|
BLAKE2b-256 checksum How to use checksums |
15908b924e6992e81cf52a09f68e4d6082782142767d746514c906bd18a8f454
|
| Upload date | |
|
Uploaded using Trusted Publishing? What is trusted publishing? |
No |
| Uploaded via |
twine/7.0.0 CPython/3.13.14
|
Security for habemus-papadum-codex-launcher 0.1.0
Provenance
Provenance describes where a file came from. On PyPI, provenance is shared via attestations, which provide a verifiable record of the build or publishing details. View details, limitations and caveats.
No provenance found
None of the files in this release were uploaded with provenance metadata.
A note on package security
PyPI is a repository for distributing packages, not a service for auditing them. While third-party security researchers and our staff do their best to detect and remove malicious packages, PyPI cannot guarantee the quality, security or suitability of any given package.
To learn more about protecting yourself from malicious actors, visit our package security documentation.