zed/crates/language_models/Cargo.toml
morgankrey 37f6d7a15c
Add ChatGPT subscription provider via OAuth 2.0 PKCE (#53166)
Adds a new language model provider that lets users authenticate with
their ChatGPT Plus/Pro subscription and use OpenAI models
(codex-mini-latest, o4-mini, o3) directly in the Zed agent — without
needing a separate API key.

## How it works

1. **OAuth 2.0 + PKCE sign-in**: Uses OpenAI's official Codex CLI client
ID to run an authorization code flow. A local HTTP server on
`127.0.0.1:1455` captures the callback, exchanges the code for tokens,
and stores them in the system keychain.

2. **Token refresh**: Access tokens are automatically refreshed when
they're within 5 minutes of expiry, using the stored refresh token.

3. **Responses API**: Requests go to
`https://chatgpt.com/backend-api/codex/responses` using the existing
`open_ai::responses` client (Responses API format, not Chat Completions
which was deprecated for this endpoint in Feb 2026).

4. **Required headers**: `originator: zed`, `OpenAI-Beta:
responses=experimental`, `ChatGPT-Account-Id` (extracted from JWT),
`store: false` in the body.

## Files changed

- `crates/open_ai/src/responses.rs`: Add `store: Option<bool>` field to
`Request`; add `extra_headers` param to `stream_response` for
per-provider header injection
- `crates/language_models/src/provider/openai_subscribed.rs`: New
provider (sign-in UI, OAuth flow, token storage/refresh, model list)
- `crates/language_models/src/provider/open_ai.rs`,
`open_ai_compatible.rs`, `opencode.rs`: Pass `vec![]` for new
`extra_headers` param
- `crates/language_models/src/language_models.rs`: Register the new
provider
- `crates/language_models/Cargo.toml`: Add `rand` and `sha2` deps for
PKCE

## Open questions / known gaps

- [ ] **Terms of service**: Usage appears to be within OpenAI's ToS
(interactive use via their official CLI client ID), but needs legal
sign-off before shipping
- [ ] **Redirect URI**: Currently `http://localhost:1455/auth/callback`
— may need to match exactly what OpenAI's Codex CLI uses
- [ ] **UI polish**: The sign-in card is functional but minimal; needs
design review
- [ ] **Error messages**: OAuth error responses from the callback URL
aren't surfaced to the user yet
- [ ] **`o3` availability**: o3 may require a higher subscription tier;
consider gating it

## Testing

Sign-in flow was designed to match the Copilot Chat provider pattern.
Manual testing against the live OAuth endpoint is needed.

Release Notes:

- Added ChatGPT subscription provider, allowing users to use their
ChatGPT Plus/Pro subscription with the Zed agent

---------

Co-authored-by: Zed Zippy <234243425+zed-zippy[bot]@users.noreply.github.com>
Co-authored-by: Richard Feldman <richard@zed.dev>
Co-authored-by: Richard Feldman <oss@rtfeldman.com>
Co-authored-by: Agus Zubiaga <agus@zed.dev>
2026-05-14 21:03:56 +00:00

81 lines
2.6 KiB
TOML

[package]
name = "language_models"
version = "0.1.0"
edition.workspace = true
publish.workspace = true
license = "GPL-3.0-or-later"
[lints]
workspace = true
[lib]
path = "src/language_models.rs"
[dependencies]
ai_onboarding.workspace = true
async-lock.workspace = true
anthropic = { workspace = true, features = ["schemars"] }
anyhow.workspace = true
aws-config = { workspace = true, features = ["behavior-version-latest"] }
aws-credential-types = { workspace = true, features = ["hardcoded-credentials"] }
aws_http_client.workspace = true
base64.workspace = true
bedrock = { workspace = true, features = ["schemars"] }
client.workspace = true
cloud_api_client.workspace = true
cloud_api_types.workspace = true
collections.workspace = true
component.workspace = true
convert_case.workspace = true
copilot.workspace = true
copilot_chat.workspace = true
copilot_ui.workspace = true
credentials_provider.workspace = true
deepseek = { workspace = true, features = ["schemars"] }
extension.workspace = true
extension_host.workspace = true
fs.workspace = true
futures.workspace = true
google_ai = { workspace = true, features = ["schemars"] }
gpui.workspace = true
gpui_tokio.workspace = true
http_client.workspace = true
language.workspace = true
language_model.workspace = true
language_models_cloud.workspace = true
lmstudio = { workspace = true, features = ["schemars"] }
log.workspace = true
menu.workspace = true
mistral = { workspace = true, features = ["schemars"] }
oauth_callback_server.workspace = true
ollama = { workspace = true, features = ["schemars"] }
open_ai = { workspace = true, features = ["schemars"] }
opencode = { workspace = true, features = ["schemars"] }
open_router = { workspace = true, features = ["schemars"] }
rand.workspace = true
release_channel.workspace = true
schemars.workspace = true
sha2.workspace = true
serde.workspace = true
serde_json.workspace = true
settings.workspace = true
smol.workspace = true
strum.workspace = true
tokio = { workspace = true, features = ["rt", "rt-multi-thread"] }
ui.workspace = true
ui_input.workspace = true
url.workspace = true
util.workspace = true
x_ai = { workspace = true, features = ["schemars"] }
[dev-dependencies]
client = { workspace = true, features = ["test-support"] }
clock = { workspace = true, features = ["test-support"] }
db = { workspace = true, features = ["test-support"] }
feature_flags.workspace = true
gpui = { workspace = true, features = ["test-support"] }
http_client = { workspace = true, features = ["test-support"] }
language_model = { workspace = true, features = ["test-support"] }
parking_lot.workspace = true
pretty_assertions.workspace = true
settings = { workspace = true, features = ["test-support"] }