Commit Graph
10 Commits
Author SHA1 Message Date
Felipe Coury 5f03ec622b feat(app-server): add permission request capabilities
Add the `supportedServerRequests` initialize capability across the
app-server protocol, clients, and connection session state. This lets
surfaces explicitly advertise which conversational permission approval
requests they know how to receive.

Keep this branch limited to the opt-in contract and the bookkeeping
needed to store that capability per connection. Delivery and UI handling
stay in later stacked PRs so existing clients remain backward
compatible and the review surface stays small.
2026-04-12 21:43:09 -03:00
Ahmed Ibrahim 2f9090be62 Add realtime voice selection (#17176)
- Add realtime voice selection for realtime/start.
- Expose the supported v1/v2 voice lists and cover explicit, configured,
default, and invalid voice paths.
2026-04-08 20:19:15 -07:00
Ahmed IbrahimandCodex 4c2a1ae31b Move default realtime prompt into core (#17165)
- Adds a core-owned realtime backend prompt template and preparation
path.
- Makes omitted realtime start prompts use the core default, while null
or empty prompts intentionally send empty instructions.
- Covers the core realtime path and app-server v2 path with integration
coverage.

---------

Co-authored-by: Codex <noreply@openai.com>
2026-04-08 19:34:40 -07:00
Ahmed IbrahimandCodex fb3dcfde1d Add WebRTC transport to realtime start (#16960)
Adds WebRTC startup to the experimental app-server
`thread/realtime/start` method with an optional transport enum. The
websocket path remains the default; WebRTC offers create the realtime
session through the shared start flow and emit the answer SDP via
`thread/realtime/sdp`.

---------

Co-authored-by: Codex <noreply@openai.com>
2026-04-07 15:43:38 -07:00
Jack Mousseau b7dba72dbd Rename reject approval policy to granular (#14516) 2026-03-12 16:38:04 -07:00
Celia Chen c1a424691f chore: add a separate reject-policy flag for skill approvals (#14271)
## Summary
- add `skill_approval` to `RejectConfig` and the app-server v2
`AskForApproval::Reject` payload so skill-script prompts can be
configured independently from sandbox and rule-based prompts
- update Unix shell escalation to reject prompts based on the actual
decision source, keeping prefix rules tied to `rules`, unmatched command
fallbacks tied to `sandbox_approval`, and skill scripts tied to
`skill_approval`
- regenerate the affected protocol/config schemas and expand
unit/integration coverage for the new flag and skill approval behavior
2026-03-11 12:33:09 -07:00
Dylan Hurdandcelia-oai d5694529ca app-server: propagate nested experimental gating for AskForApproval::Reject (#14191)
## Summary
This change makes `AskForApproval::Reject` gate correctly anywhere it
appears inside otherwise-stable app-server protocol types.

Previously, experimental gating for `approval_policy: Reject` was
handled with request-specific logic in `ClientRequest` detection. That
covered a few request params types, but it did not generalize to other
nested uses such as `ProfileV2`, `Config`, `ConfigReadResponse`, or
`ConfigRequirements`.

This PR replaces that ad hoc handling with a generic nested experimental
propagation mechanism.

## Testing

seeing this when run app-server-test-client without experimental api
enabled:
```
 initialize response: InitializeResponse { user_agent: "codex-toy-app-server/0.0.0 (Mac OS 26.3.1; arm64) vscode/2.4.36 (codex-toy-app-server; 0.0.0)" }
> {
>   "id": "50244f6a-270a-425d-ace0-e9e98205bde7",
>   "method": "thread/start",
>   "params": {
>     "approvalPolicy": {
>       "reject": {
>         "mcp_elicitations": false,
>         "request_permissions": true,
>         "rules": false,
>         "sandbox_approval": true
>       }
>     },
>     "baseInstructions": null,
>     "config": null,
>     "cwd": null,
>     "developerInstructions": null,
>     "dynamicTools": null,
>     "ephemeral": null,
>     "experimentalRawEvents": false,
>     "mockExperimentalField": null,
>     "model": null,
>     "modelProvider": null,
>     "persistExtendedHistory": false,
>     "personality": null,
>     "sandbox": null,
>     "serviceName": null
>   }
> }
< {
<   "error": {
<     "code": -32600,
<     "message": "askForApproval.reject requires experimentalApi capability"
<   },
<   "id": "50244f6a-270a-425d-ace0-e9e98205bde7"
< }
[verified] thread/start rejected approvalPolicy=Reject without experimentalApi
```

---------

Co-authored-by: celia-oai <celia@openai.com>
2026-03-11 12:33:08 -07:00
Ahmed IbrahimandCodex 947092283a Add app-server v2 thread realtime API (#12715)
Add experimental `thread/realtime/*` v2 requests and notifications, then
route app-server realtime events through that thread-scoped surface with
integration coverage.

---------

Co-authored-by: Codex <noreply@openai.com>
2026-02-25 09:59:10 -08:00
jif-oai a364dd8b56 feat: opt-out of events in the app-server (#11319)
Add `optOutNotificationMethods` in the app-server to opt-out events
based on exact method matching
2026-02-10 18:04:52 +00:00
jif-oai 3cc9122ee2 feat: experimental flags (#10231)
## Problem being solved
- We need a single, reliable way to mark app-server API surface as
experimental so that:
  1. the runtime can reject experimental usage unless the client opts in
2. generated TS/JSON schemas can exclude experimental methods/fields for
stable clients.

Right now that’s easy to drift or miss when done ad-hoc.

## How to declare experimental methods and fields
- **Experimental method**: add `#[experimental("method/name")]` to the
`ClientRequest` variant in `client_request_definitions!`.
- **Experimental field**: on the params struct, derive `ExperimentalApi`
and annotate the field with `#[experimental("method/name.field")]` + set
`inspect_params: true` for the method variant so
`ClientRequest::experimental_reason()` inspects params for experimental
fields.

## How the macro solves it
- The new derive macro lives in
`codex-rs/codex-experimental-api-macros/src/lib.rs` and is used via
`#[derive(ExperimentalApi)]` plus `#[experimental("reason")]`
attributes.
- **Structs**:
- Generates `ExperimentalApi::experimental_reason(&self)` that checks
only annotated fields.
  - The “presence” check is type-aware:
    - `Option<T>`: `is_some_and(...)` recursively checks inner.
    - `Vec`/`HashMap`/`BTreeMap`: must be non-empty.
    - `bool`: must be `true`.
    - Other types: considered present (returns `true`).
- Registers each experimental field in an `inventory` with `(type_name,
serialized field name, reason)` and exposes `EXPERIMENTAL_FIELDS` for
that type. Field names are converted from `snake_case` to `camelCase`
for schema/TS filtering.
- **Enums**:
- Generates an exhaustive `match` returning `Some(reason)` for annotated
variants and `None` otherwise (no wildcard arm).
- **Wiring**:
- Runtime gating uses `ExperimentalApi::experimental_reason()` in
`codex-rs/app-server/src/message_processor.rs` to reject requests unless
`InitializeParams.capabilities.experimental_api == true`.
- Schema/TS export filters use the inventory list and
`EXPERIMENTAL_CLIENT_METHODS` from `client_request_definitions!` to
strip experimental methods/fields when `experimental_api` is false.
2026-02-02 11:06:50 +00:00