R Observatory: Metrics for ellmercodex version 0.2.0

Balamuta, James Joseph

doi:10.5281/zenodo.21843040

ellmercodex

0.2.0Package record

'ChatGPT' Plan Provider for 'ellmer'

0packages depend

107downloads / year

40.2%test coverage

12/12flavors OK

Overview

About

Maintained by Simon HerreraCRAN page ↗GitHub ↗Issues ↗

Connects 'ellmer' chats to a 'ChatGPT' subscription through 'OpenAI''s documented "Sign in with ChatGPT" flow for open-source, locally hosted apps https://developers.openai.com/siwc/token-sharing-open-source. Provides a stable, explicitly bounded core of the public 'ellmer' (>= 0.5.0) Chat object, including browser sign-in with dynamic client registration, package-scoped credential storage, redacted diagnostics, multi-turn text, streaming, structured-output, function-tool, asynchronous, cancellation, cloning, metadata, multimodal chat, account-specific model discovery, and reasoning-effort selection through the public 'Responses' API. Parallel and batch helper functions are explicitly unsupported because 'ChatGPT' plan usage is stream-only. This independent third-party integration is not endorsed by 'OpenAI'.

Changes in 0.2.0

Breaking changes: documented "Sign in with ChatGPT" flow

Authentication now follows OpenAI's documented "Sign in with ChatGPT" flow for open-source, locally hosted apps (<https://developers.openai.com/siwc/token-sharing-open-source>). The package no longer reuses the Codex CLI OAuth client or calls the undocumented chatgpt.com/backend-api/codex endpoints. **Existing credentials cannot be migrated: run codex_login() again.**
codex_login() registers dynamically with client_id=dynamic_agent_client, stores the client ID that OpenAI issues for the chosen account and workspace, and reauthorizes that registration on later sign-ins. It sends a stable ext_agent_host_id, created once per host, and uses PKCE and a nonce. The ID token is verified against OpenAI's published keys, and sign-in fails with the new codex_plan_scope_error when ChatGPT plan usage (chatgpt.tokens.use.direct) is not granted. The package now imports jose for ID token verification.

Show all changes in 0.2.0Hide the rest of the changes in 0.2.0

The OAuth callback moved from http://localhost:1455/auth/callback to http://127.0.0.1:1455/callback, as the documentation requires. Set ELLMERCODEX_CALLBACK_PORT to use another port.
Credentials moved from httr2's OAuth cache to a package-owned credentials.json (mode 0600, atomic writes) in tools::R_user_dir("ellmercodex", "config"), or in the directory named by ELLMERCODEX_HOME. HTTR2_OAUTH_CACHE no longer applies. Refreshes are serialized across R processes because refresh tokens rotate.
codex_logout() gains revoke = TRUE and now revokes the refresh token with OpenAI before deleting the local credential. It also removes the old httr2 cache entry. To switch account or workspace, log out and sign in again.
Chats and codex_models() use the public https://api.openai.com/v1 Responses and Models endpoints with only the bearer token; the ChatGPT-Account-Id, OpenAI-Beta, and originator headers are gone. codex_models() keeps models with visibility: "list", and its client_version argument is deprecated and ignored (ELLMERCODEX_CLIENT_VERSION is no longer read).
Requests follow the ChatGPT plan usage preview limits: system prompts are sent as developer messages, function tools are grouped in an ellmer namespace, and temperature, top_p, max_tokens, metadata, previous_response_id, and the other excluded Responses arguments now fail with codex_chat_argument_error before a request is sent.
A response.incomplete event now fails a Chat turn with codex_incomplete_error instead of returning a truncated turn.
Documented plan error codes map to new subclasses that keep the existing parents: codex_usage_limit_error (a codex_rate_limit_error), codex_usage_unavailable_error (a codex_server_error), codex_plan_ineligible_error (a codex_authentication_error), and codex_unsupported_capability_error (a codex_malformed_request_error). Synchronous chats now raise these package conditions, rather than httr2 errors, for HTTP failures before the stream opens.

Other changes

Codex generation requests no longer inherit ellmer's automatic retries, as documented in the technical design: a retried request could duplicate a generation the service already accepted.
Codex requests and turn costs are now built without five unexported ellmer helpers, reducing the private ellmer surface ahead of a CRAN submission.
chat_codex() now accepts explicitly selected models omitted from the account catalog. The service validates those model IDs and reasoning efforts.

From NEWS.md in the release

Install

R (CRAN)pak (dev)Fedora (COPR)openSUSE (OBS)

install.packages("ellmercodex", repos = "https://cloud.r-project.org/")

Installs the current CRAN release. Prebuilt binaries on Windows and macOS.

if (!requireNamespace("pak", quietly = TRUE))
  install.packages("pak", repos = "https://cloud.r-project.org/")
pak::pak("simxnherrera/ellmercodex")

Development version from simxnherrera/ellmercodex. Installs pak first if it is not already available.

# enable the iucar/cran COPR if it is not already present, then install
ls /etc/yum.repos.d/*iucar*cran*.repo >/dev/null 2>&1 \
  || sudo dnf copr enable -y iucar/cran
sudo dnf install -y R-CRAN-ellmercodex

RPMs from the iucar/cran COPR, rebuilt from CRAN.

For install.packages() integration in R, also: sudo dnf install R-CoprManager

# add the autoCRAN OBS repo (Tumbleweed) if it is missing, then install
zypper -q lr | grep -qi autoCRAN \
  || sudo zypper addrepo https://download.opensuse.org/repositories/devel:/languages:/R:/autoCRAN/openSUSE_Tumbleweed/devel:languages:R:autoCRAN.repo
sudo zypper install -y R-ellmercodex

RPMs auto-built from CRAN on openSUSE OBS (Tumbleweed). We list this channel from recorded autoCRAN download activity rather than from a live index of the repository, so treat it as last known rather than guaranteed.

Health

CRAN checks

12OK

CRAN check page ↗

Slowest check: 2.3 min · r-release-macos-x86_64

Status changes

OK12 OKNow
OK7 OK2026-10-17

Advisories

none known

How this is measured·How advisories are found

Documentation

In release 0.2.0

READMEYes · 1,581 wordsVignettesYes · 1 · dynamicNEWSYes · 100% structured · mentions 0.2.0Citation fileNoWebsitenot declared in DESCRIPTION

Help pages: 9 (1 internal)includes a package overview page
Examples that run: 100%7 run in a plain check (5 of them under a condition)
Exported functions with examples: 100%
Documented parameters: 100%
Return-value docs: 100%
Help pages citing references: 0%

Vignettes (1)

Getting started with ellmercodex HTML

How these are measured

Downloads

107

CRAN downloads in the past year

Rank #25,547 · ~0/day · ~9/mo

ellmercodex Releases R versions

Daily download trend is not available in this view yet.

10730 days

10790 days

1071 year

Compare downloads with other packages →

How downloads are counted

Repository

simxnherrera/ellmercodex ↗Account: simxnherrera

3Stars

0Forks

0Open issues

0Open PRs

12Releases

43Commits

1Commit identities

43 commits · Last activity 2026-10-18

Responsiveness

How these are sampled

PRs merged (all time): 100%
Median days to close, 50 most recently updated closed issues: 2
Median days to close, 50 most recently updated closed PRs: 0

Commits over time

2026-10-18 · 372026-10-20 · 43

How these are measured

PracticesBeta

5 development-tooling and community-health practices detected across 4 families in the upstream repository

Checks run against github.com/simxnherrera/ellmercodex on 2026-10-18.

Continuous integration (2)

GitHub ActionsR CMD check workflow

The R CMD check workflow runs on Linux, macOS and Windows, and on R-devel

CRAN release process (1)

cran-comments.md

Lint, format, editor (1)

lintr

Git structural (1)

.gitattributes

How this is detected·Detection ruleset v3 (2026-09-26)

AI coding toolsBeta

This repository shows signs of AI coding tools.

Claude Codefirst seen 2026-10-06
Pull request it wrote: opened by a project member
Commits: at least 10 crediting it in the message

Models named in its commits

Claude Opus 5.510 commits · Oct 2026

Counts are commits, not lines of code. Commits by a tool's accounts count once across all of its accounts. Commits crediting it are the largest count among its credit lines, a minimum.How this is detected·Detection ruleset v4 (updated 2026-09-27)

Dependencies

Declared dependencies

16 external dependencies (excludes base and recommended)

Installing ellmercodex adds 28 packages (17 with compiled code, 18 MB of source tarballs). Heaviest: promises 3.1 MB, ellmer 3.0 MB, Rcpp 1.8 MB.

Depends (1)

R >= 4.1.0

Imports (10)

coro ellmer httr2 httpuv jose jsonlite openssl promises rlang S7

LinkingTo (0)

none

Suggests (6)

callr knitr later pkgload rmarkdown testthat

Enhances (0)

none

Dependency license breakdown →

Reverse dependencies

0direct

0indirect

Nothing depends on this yet.

How these are counted

Code & Tests

People & History

People (1)

Simon Herrera

Releases (1)

0.2.0Latest
record
2026-10-16 · current release ·
9 days in CRAN's queue
Listed in CRAN's incoming queue from 2026-10-06 20:42 to 2026-10-16 07:45 UTC, in 44 readings.
R
R 4.6.0 released · 2026-04-24

Across CRAN, the median accepted release of the past year spent 23 hours in the queue, 90% under 11 days.How queue time is measured

Package metadata

First published: 2026-10-16
Total releases: 1 / 1 yrs
License: MIT + file LICENSE OSI
Minimum R: ≥ 4.1.0
Download size: 446 KB

Cite

Cite this package

Run in R for the authors' preferred citation:

citation("ellmercodex")

Format

Herrera, S. (2026). ellmercodex: 'ChatGPT' Plan Provider for 'ellmer' (Version 0.2.0) [Computer software]. https://doi.org/10.32614/CRAN.package.ellmercodex

This package has no citation file, so citation() returns this entry built from DESCRIPTION.

Cite the R Observatory

For a number measured here: a download total, a coverage figure, an archival date.

Format

APA

Balamuta, J. J. (2026). R Observatory: Metrics for ellmercodex version 0.2.0 [Data set]. HJJB, LLC. Data release v2026-10-21. https://doi.org/10.5281/zenodo.21843040

From data release v2026-10-21, which the citation names so these numbers can be found later. More on citing and the projects behind them.

Report a problem with this page →