core-agent-ide/codex-rs/app-server-test-client
Channing Conger c6343e0649
Implemented thread-level atomic elicitation counter for stopwatch pausing (#12296)
### Purpose
While trying to build out CLI-Tools for the agent to use under skills we
have found that those tools sometimes need to invoke a user elicitation.
These elicitations are handled out of band of the codex app-server but
need to indicate to the exec manager that the command running is not
going to progress on the usual timeout horizon.

### Example
Model calls universal exec:
`$ download-credit-card-history --start-date 2026-01-19 --end-date
2026-02-19 > credit_history.jsonl`

download-cred-card-history might hit a hosted/preauthenticated service
to fetch data. That service might decide that the request requires an
end user approval the access to the personal data. It should be able to
signal to the running thread that the command in question is blocked on
user elicitation. In that case we want the exec to continue, but the
timeout to not expire on the tool call, essentially freezing time until
the user approves or rejects the command at which point the tool would
signal the app-server to decrement the outstanding elicitation count.
Now timeouts would proceed as normal.

### What's Added

- New v2 RPC methods:
    - thread/increment_elicitation
    - thread/decrement_elicitation
- Protocol updates in:
    - codex-rs/app-server-protocol/src/protocol/common.rs
    - codex-rs/app-server-protocol/src/protocol/v2.rs
- App-server handlers wired in:
    - codex-rs/app-server/src/codex_message_processor.rs

### Behavior

- Counter starts at 0 per thread.
- increment atomically increases the counter.
- decrement atomically decreases the counter; decrement at 0 returns
invalid request.
- Transition rules:
- 0 -> 1: broadcast pause state, pausing all active stopwatches
immediately.
    - \>0 -> >0: remain paused.
    - 1 -> 0: broadcast unpause state, resuming stopwatches.
- Core thread/session logic:
    - codex-rs/core/src/codex_thread.rs
    - codex-rs/core/src/codex.rs
    - codex-rs/core/src/mcp_connection_manager.rs

### Exec-server stopwatch integration

- Added centralized stopwatch tracking/controller:
    - codex-rs/exec-server/src/posix/stopwatch_controller.rs
- Hooked pause/unpause broadcast handling + stopwatch registration:
    - codex-rs/exec-server/src/posix/mcp.rs
    - codex-rs/exec-server/src/posix/stopwatch.rs
    - codex-rs/exec-server/src/posix.rs
2026-03-09 22:29:26 -07:00
..
scripts Implemented thread-level atomic elicitation counter for stopwatch pausing (#12296) 2026-03-09 22:29:26 -07:00
src Implemented thread-level atomic elicitation counter for stopwatch pausing (#12296) 2026-03-09 22:29:26 -07:00
BUILD.bazel chore: add codex debug app-server tooling (#10367) 2026-02-03 23:17:34 +00:00
Cargo.toml feat(app-server-test-client): OTEL setup for tracing (#13493) 2026-03-04 13:30:09 -08:00
README.md app-server: Add an ability to watch events in the test client (#13080) 2026-02-27 17:19:53 -08:00

App Server Test Client

Quickstart for running and hitting codex app-server.

Quickstart

Run from <reporoot>/codex-rs.

# 1) Build debug codex binary
cargo build -p codex-cli --bin codex

# 2) Start websocket app-server in background
cargo run -p codex-app-server-test-client -- \
  --codex-bin ./target/debug/codex \
  serve --listen ws://127.0.0.1:4222 --kill

# 3) Call app-server (defaults to ws://127.0.0.1:4222)
cargo run -p codex-app-server-test-client -- model-list

Watching Raw Inbound Traffic

Initialize a connection, then print every inbound JSON-RPC message until you stop it with Ctrl+C:

cargo run -p codex-app-server-test-client -- watch

Testing Thread Rejoin Behavior

Build and start an app server using commands above. The app-server log is written to /tmp/codex-app-server-test-client/app-server.log

1) Get a thread id

Create at least one thread, then list threads:

cargo run -p codex-app-server-test-client -- send-message-v2 "seed thread for rejoin test"
cargo run -p codex-app-server-test-client -- thread-list --limit 5

Copy a thread id from the thread-list output.

2) Rejoin while a turn is in progress (two terminals)

Terminal A:

cargo run --bin codex-app-server-test-client -- \
  resume-message-v2 <THREAD_ID> "respond with thorough docs on the rust core"

Terminal B (while Terminal A is still streaming):

cargo run --bin codex-app-server-test-client -- thread-resume <THREAD_ID>