mirror of
https://github.com/openai/codex.git
synced 2026-05-28 15:00:16 +00:00
768848ab6f
## Summary
Adds experimental `additionalContext` support to `turn/start` and
`turn/steer` so clients can provide ephemeral external context, such as
browser or automation state, without turning that plumbing into a
visible user prompt or triggering user-prompt lifecycle behavior.
## API Shape
The parameter shape is:
```ts
additionalContext?: Record<string, {
value: string
kind: "untrusted" | "application"
}> | null
```
Example:
```json
{
"additionalContext": {
"browser_info": {
"value": "Active tab is CI failures.",
"kind": "untrusted"
},
"automation_info": {
"value": "CI rerun is in progress.",
"kind": "application"
}
}
}
```
The keys are opaque and caller-defined.
## Context Injection
When provided, accepted entries are inserted into model context as
hidden contextual message items, not as visible thread user-message
items.
`kind: "untrusted"` entries are inserted with role `user`:
```text
<external_${key}>${value}</external_${key}>
```
`kind: "application"` entries are inserted with role `developer`:
```text
<${key}>${value}</${key}>
```
Values are not escaped. Each value is truncated to 1k approximate tokens
before wrapping.
For `turn/start`, accepted additional context is inserted before normal
user input. For `turn/steer`, additional context is merged only when the
steer includes non-empty user input; context-only steers still reject as
empty input.
## Dedupe Strategy
`AdditionalContextStore` lives on session state and stores the latest
complete additional-context map.
Each `turn/start` or non-empty `turn/steer` treats its
`additionalContext` as the current complete set of values. Entries are
injected only when the key is new or the exact entry for that key
changed, including `value` or `kind`. After merging, the store is
replaced with the provided map, so omitted keys are removed from the
retained set and can be injected again later if reintroduced.
Omitting `additionalContext`, passing `null`, or passing an empty object
resets the store to empty and injects nothing.
## What Changed
- Threads experimental v2 `additionalContext` through app-server into
core turn start and steer handling.
- Adds separate contextual fragment types for untrusted user-role
context and application developer-role context.
- Uses pending response input items so additional context can be
combined with normal user input without treating it as prompt text.
- Adds integration coverage for start/steer flow, role routing,
dedupe/reset behavior, deletion/re-add behavior, hook-blocked input
behavior, empty context-only steer rejection, external-fragment marker
matching, and truncation.
84 lines
2.9 KiB
Rust
84 lines
2.9 KiB
Rust
#![cfg(not(target_os = "windows"))]
|
||
|
||
use std::os::unix::fs::PermissionsExt;
|
||
|
||
use codex_protocol::protocol::EventMsg;
|
||
use codex_protocol::protocol::Op;
|
||
use codex_protocol::user_input::UserInput;
|
||
use core_test_support::fs_wait;
|
||
use core_test_support::responses;
|
||
use core_test_support::skip_if_no_network;
|
||
use core_test_support::test_codex::TestCodex;
|
||
use core_test_support::test_codex::test_codex;
|
||
use core_test_support::wait_for_event;
|
||
use pretty_assertions::assert_eq;
|
||
use serde_json::Value;
|
||
use serde_json::json;
|
||
use tempfile::TempDir;
|
||
|
||
use responses::ev_assistant_message;
|
||
use responses::ev_completed;
|
||
use responses::sse;
|
||
use responses::start_mock_server;
|
||
use std::time::Duration;
|
||
|
||
#[tokio::test(flavor = "multi_thread", worker_threads = 2)]
|
||
async fn summarize_context_three_requests_and_instructions() -> anyhow::Result<()> {
|
||
skip_if_no_network!(Ok(()));
|
||
|
||
let server = start_mock_server().await;
|
||
|
||
let sse1 = sse(vec![ev_assistant_message("m1", "Done"), ev_completed("r1")]);
|
||
|
||
responses::mount_sse_once(&server, sse1).await;
|
||
|
||
let notify_dir = TempDir::new()?;
|
||
// write a script to the notify that touches a file next to it
|
||
let notify_script = notify_dir.path().join("notify.sh");
|
||
std::fs::write(
|
||
¬ify_script,
|
||
r#"#!/bin/bash
|
||
set -e
|
||
payload_path="$(dirname "${0}")/notify.txt"
|
||
tmp_path="${payload_path}.tmp"
|
||
echo -n "${@: -1}" > "${tmp_path}"
|
||
mv "${tmp_path}" "${payload_path}""#,
|
||
)?;
|
||
std::fs::set_permissions(¬ify_script, std::fs::Permissions::from_mode(0o755))?;
|
||
|
||
let notify_file = notify_dir.path().join("notify.txt");
|
||
let notify_script_str = notify_script.to_str().unwrap().to_string();
|
||
|
||
let TestCodex { codex, .. } = test_codex()
|
||
.with_config(move |cfg| cfg.notify = Some(vec![notify_script_str]))
|
||
.build(&server)
|
||
.await?;
|
||
|
||
// 1) Normal user input – should hit server once.
|
||
codex
|
||
.submit(Op::UserInput {
|
||
environments: None,
|
||
items: vec![UserInput::Text {
|
||
text: "hello world".into(),
|
||
text_elements: Vec::new(),
|
||
}],
|
||
final_output_json_schema: None,
|
||
responsesapi_client_metadata: None,
|
||
additional_context: Default::default(),
|
||
thread_settings: Default::default(),
|
||
})
|
||
.await?;
|
||
wait_for_event(&codex, |ev| matches!(ev, EventMsg::TurnComplete(_))).await;
|
||
|
||
// We fork the notify script, so we need to wait for it to write to the file.
|
||
fs_wait::wait_for_path_exists(¬ify_file, Duration::from_secs(5)).await?;
|
||
let notify_payload_raw = tokio::fs::read_to_string(¬ify_file).await?;
|
||
let payload: Value = serde_json::from_str(¬ify_payload_raw)?;
|
||
|
||
assert_eq!(payload["type"], json!("agent-turn-complete"));
|
||
assert_eq!(payload["input-messages"], json!(["hello world"]));
|
||
assert_eq!(payload["last-assistant-message"], json!("Done"));
|
||
|
||
Ok(())
|
||
}
|