mirror of
https://github.com/openai/codex.git
synced 2026-02-03 07:23:39 +00:00
Compare commits
4 Commits
pr8959
...
dev/cc/tmp
| Author | SHA1 | Date | |
|---|---|---|---|
|
50437ca302 | ||
|
|
e591cde2d5 | ||
|
|
c1162dedca | ||
|
|
303ea308bc |
@@ -14,26 +14,6 @@ RUN apt-get update && \
|
||||
pkg-config clang musl-tools libssl-dev just && \
|
||||
rm -rf /var/lib/apt/lists/*
|
||||
|
||||
# Install Bazel via Bazelisk (mirrors bazelbuild/setup-bazelisk@v3).
|
||||
ARG BAZELISK_VERSION=latest
|
||||
RUN arch="$(uname -m)" && \
|
||||
case "$arch" in \
|
||||
x86_64) arch="amd64" ;; \
|
||||
aarch64) arch="arm64" ;; \
|
||||
*) echo "Unsupported architecture: $arch" >&2; exit 1 ;; \
|
||||
esac && \
|
||||
if [ "$BAZELISK_VERSION" = "latest" ]; then \
|
||||
url="https://github.com/bazelbuild/bazelisk/releases/latest/download/bazelisk-linux-${arch}"; \
|
||||
else \
|
||||
url="https://github.com/bazelbuild/bazelisk/releases/download/v${BAZELISK_VERSION}/bazelisk-linux-${arch}"; \
|
||||
fi && \
|
||||
curl -fsSL "$url" -o /usr/local/bin/bazelisk && \
|
||||
chmod +x /usr/local/bin/bazelisk && \
|
||||
ln -s /usr/local/bin/bazelisk /usr/local/bin/bazel
|
||||
|
||||
# Install dotslash.
|
||||
RUN curl -LSfs "https://github.com/facebook/dotslash/releases/download/v0.5.8/dotslash-ubuntu-22.04.$(uname -m).tar.gz" | tar fxz - -C /usr/local/bin
|
||||
|
||||
# Ubuntu 24.04 ships with user 'ubuntu' already created with UID 1000.
|
||||
USER ubuntu
|
||||
|
||||
|
||||
21
.github/workflows/rust-release.yml
vendored
21
.github/workflows/rust-release.yml
vendored
@@ -323,26 +323,6 @@ jobs:
|
||||
- name: Checkout repository
|
||||
uses: actions/checkout@v6
|
||||
|
||||
- name: Generate release notes from tag commit message
|
||||
id: release_notes
|
||||
shell: bash
|
||||
run: |
|
||||
set -euo pipefail
|
||||
|
||||
# On tag pushes, GITHUB_SHA may be a tag object for annotated tags;
|
||||
# peel it to the underlying commit.
|
||||
commit="$(git rev-parse "${GITHUB_SHA}^{commit}")"
|
||||
notes_path="${RUNNER_TEMP}/release-notes.md"
|
||||
|
||||
# Use the commit message for the commit the tag points at (not the
|
||||
# annotated tag message).
|
||||
git log -1 --format=%B "${commit}" > "${notes_path}"
|
||||
# Ensure trailing newline so GitHub's markdown renderer doesn't
|
||||
# occasionally run the last line into subsequent content.
|
||||
echo >> "${notes_path}"
|
||||
|
||||
echo "path=${notes_path}" >> "${GITHUB_OUTPUT}"
|
||||
|
||||
- uses: actions/download-artifact@v7
|
||||
with:
|
||||
path: dist
|
||||
@@ -415,7 +395,6 @@ jobs:
|
||||
with:
|
||||
name: ${{ steps.release_name.outputs.name }}
|
||||
tag_name: ${{ github.ref_name }}
|
||||
body_path: ${{ steps.release_notes.outputs.path }}
|
||||
files: dist/**
|
||||
# Mark as prerelease only when the version has a suffix after x.y.z
|
||||
# (e.g. -alpha, -beta). Otherwise publish a normal release.
|
||||
|
||||
1
.gitignore
vendored
1
.gitignore
vendored
@@ -9,7 +9,6 @@ node_modules
|
||||
|
||||
# build
|
||||
dist/
|
||||
bazel-*
|
||||
build/
|
||||
out/
|
||||
storybook-static/
|
||||
|
||||
@@ -77,11 +77,11 @@ If you don’t have the tool:
|
||||
- Prefer deep equals comparisons whenever possible. Perform `assert_eq!()` on entire objects, rather than individual fields.
|
||||
- Avoid mutating process environment in tests; prefer passing environment-derived flags or dependencies from above.
|
||||
|
||||
### Spawning workspace binaries in tests (Cargo vs Bazel)
|
||||
### Spawning workspace binaries in tests (Cargo vs Buck2)
|
||||
|
||||
- Prefer `codex_utils_cargo_bin::cargo_bin("...")` over `assert_cmd::Command::cargo_bin(...)` or `escargot` when tests need to spawn first-party binaries.
|
||||
- Under Bazel, binaries and resources may live under runfiles; use `codex_utils_cargo_bin::cargo_bin` to resolve absolute paths that remain stable after `chdir`.
|
||||
- When locating fixture files or test resources under Bazel, avoid `env!("CARGO_MANIFEST_DIR")`. Prefer `codex_utils_cargo_bin::find_resource!` so paths resolve correctly under both Cargo and Bazel runfiles.
|
||||
- Under Buck2, `CARGO_BIN_EXE_*` may be project-relative (e.g. `buck-out/...`), which breaks if a test changes its working directory. `codex_utils_cargo_bin::cargo_bin` resolves to an absolute path first.
|
||||
- When locating fixture files under Buck2, avoid `env!("CARGO_MANIFEST_DIR")` (Buck codegen sets it to `"."`). Prefer deriving paths from `codex_utils_cargo_bin::buck_project_root()` when needed.
|
||||
|
||||
### Integration tests (core)
|
||||
|
||||
|
||||
@@ -1,16 +0,0 @@
|
||||
# Example announcement tips for Codex TUI.
|
||||
# Each [[announcements]] entry is evaluated in order; the last matching one is shown.
|
||||
# Dates are UTC, formatted as YYYY-MM-DD. The from_date is inclusive and the to_date is exclusive.
|
||||
# version_regex matches against the CLI version (env!("CARGO_PKG_VERSION")); omit to apply to all versions.
|
||||
# target_app specify which app should display the announcement (cli, vsce, ...).
|
||||
|
||||
[[announcements]]
|
||||
content = "Welcome to Codex! Check out the new onboarding flow."
|
||||
from_date = "2024-10-01"
|
||||
to_date = "2024-10-15"
|
||||
target_app = "cli"
|
||||
|
||||
[[announcements]]
|
||||
content = "This is a test announcement"
|
||||
version_regex = "^0\\.0\\.0$"
|
||||
to_date = "2026-01-10"
|
||||
96
codex-rs/Cargo.lock
generated
96
codex-rs/Cargo.lock
generated
@@ -360,7 +360,7 @@ dependencies = [
|
||||
"objc2-foundation",
|
||||
"parking_lot",
|
||||
"percent-encoding",
|
||||
"windows-sys 0.60.2",
|
||||
"windows-sys 0.52.0",
|
||||
"wl-clipboard-rs",
|
||||
"x11rb",
|
||||
]
|
||||
@@ -819,8 +819,6 @@ version = "1.2.30"
|
||||
source = "registry+https://github.com/rust-lang/crates.io-index"
|
||||
checksum = "deec109607ca693028562ed836a5f1c4b8bd77755c4e132fc5ce11b0b6211ae7"
|
||||
dependencies = [
|
||||
"jobserver",
|
||||
"libc",
|
||||
"shlex",
|
||||
]
|
||||
|
||||
@@ -1129,7 +1127,6 @@ dependencies = [
|
||||
"codex-common",
|
||||
"codex-core",
|
||||
"codex-git",
|
||||
"codex-utils-cargo-bin",
|
||||
"serde",
|
||||
"serde_json",
|
||||
"tempfile",
|
||||
@@ -1156,6 +1153,7 @@ dependencies = [
|
||||
"codex-execpolicy",
|
||||
"codex-login",
|
||||
"codex-mcp-server",
|
||||
"codex-process-hardening",
|
||||
"codex-protocol",
|
||||
"codex-responses-api-proxy",
|
||||
"codex-rmcp-client",
|
||||
@@ -1165,6 +1163,7 @@ dependencies = [
|
||||
"codex-utils-absolute-path",
|
||||
"codex-utils-cargo-bin",
|
||||
"codex-windows-sandbox",
|
||||
"ctor 0.5.0",
|
||||
"libc",
|
||||
"owo-colors",
|
||||
"predicates",
|
||||
@@ -1198,7 +1197,6 @@ dependencies = [
|
||||
"tracing",
|
||||
"tracing-opentelemetry",
|
||||
"tracing-subscriber",
|
||||
"zstd",
|
||||
]
|
||||
|
||||
[[package]]
|
||||
@@ -1300,6 +1298,7 @@ dependencies = [
|
||||
"dunce",
|
||||
"encoding_rs",
|
||||
"env-flags",
|
||||
"escargot",
|
||||
"eventsource-stream",
|
||||
"futures",
|
||||
"http 1.3.1",
|
||||
@@ -1349,19 +1348,6 @@ dependencies = [
|
||||
"which",
|
||||
"wildmatch",
|
||||
"wiremock",
|
||||
"zstd",
|
||||
]
|
||||
|
||||
[[package]]
|
||||
name = "codex-debug-client"
|
||||
version = "0.0.0"
|
||||
dependencies = [
|
||||
"anyhow",
|
||||
"clap",
|
||||
"codex-app-server-protocol",
|
||||
"pretty_assertions",
|
||||
"serde",
|
||||
"serde_json",
|
||||
]
|
||||
|
||||
[[package]]
|
||||
@@ -1619,12 +1605,10 @@ dependencies = [
|
||||
"opentelemetry-otlp",
|
||||
"opentelemetry-semantic-conventions",
|
||||
"opentelemetry_sdk",
|
||||
"pretty_assertions",
|
||||
"reqwest",
|
||||
"serde",
|
||||
"serde_json",
|
||||
"strum_macros 0.27.2",
|
||||
"thiserror 2.0.17",
|
||||
"tokio",
|
||||
"tracing",
|
||||
"tracing-opentelemetry",
|
||||
@@ -1882,7 +1866,7 @@ dependencies = [
|
||||
name = "codex-utils-cache"
|
||||
version = "0.0.0"
|
||||
dependencies = [
|
||||
"lru 0.16.3",
|
||||
"lru 0.16.2",
|
||||
"sha1",
|
||||
"tokio",
|
||||
]
|
||||
@@ -1892,7 +1876,6 @@ name = "codex-utils-cargo-bin"
|
||||
version = "0.0.0"
|
||||
dependencies = [
|
||||
"assert_cmd",
|
||||
"path-absolutize",
|
||||
"thiserror 2.0.17",
|
||||
]
|
||||
|
||||
@@ -2798,7 +2781,7 @@ source = "registry+https://github.com/rust-lang/crates.io-index"
|
||||
checksum = "778e2ac28f6c47af28e4907f13ffd1e1ddbd400980a9abd7c8df189bf578a5ad"
|
||||
dependencies = [
|
||||
"libc",
|
||||
"windows-sys 0.60.2",
|
||||
"windows-sys 0.52.0",
|
||||
]
|
||||
|
||||
[[package]]
|
||||
@@ -2807,6 +2790,17 @@ version = "3.3.2"
|
||||
source = "registry+https://github.com/rust-lang/crates.io-index"
|
||||
checksum = "dea2df4cf52843e0452895c455a1a2cfbb842a1e7329671acf418fdc53ed4c59"
|
||||
|
||||
[[package]]
|
||||
name = "escargot"
|
||||
version = "0.5.15"
|
||||
source = "registry+https://github.com/rust-lang/crates.io-index"
|
||||
checksum = "11c3aea32bc97b500c9ca6a72b768a26e558264303d101d3409cf6d57a9ed0cf"
|
||||
dependencies = [
|
||||
"log",
|
||||
"serde",
|
||||
"serde_json",
|
||||
]
|
||||
|
||||
[[package]]
|
||||
name = "event-listener"
|
||||
version = "5.4.0"
|
||||
@@ -2895,7 +2889,7 @@ checksum = "0ce92ff622d6dadf7349484f42c93271a0d49b7cc4d466a936405bacbe10aa78"
|
||||
dependencies = [
|
||||
"cfg-if",
|
||||
"rustix 1.0.8",
|
||||
"windows-sys 0.59.0",
|
||||
"windows-sys 0.52.0",
|
||||
]
|
||||
|
||||
[[package]]
|
||||
@@ -3836,7 +3830,7 @@ checksum = "e04d7f318608d35d4b61ddd75cbdaee86b023ebe2bd5a66ee0915f0bf93095a9"
|
||||
dependencies = [
|
||||
"hermit-abi",
|
||||
"libc",
|
||||
"windows-sys 0.59.0",
|
||||
"windows-sys 0.52.0",
|
||||
]
|
||||
|
||||
[[package]]
|
||||
@@ -3930,16 +3924,6 @@ version = "0.3.0"
|
||||
source = "registry+https://github.com/rust-lang/crates.io-index"
|
||||
checksum = "8eaf4bc02d17cbdd7ff4c7438cafcdf7fb9a4613313ad11b4f8fefe7d3fa0130"
|
||||
|
||||
[[package]]
|
||||
name = "jobserver"
|
||||
version = "0.1.34"
|
||||
source = "registry+https://github.com/rust-lang/crates.io-index"
|
||||
checksum = "9afb3de4395d6b3e67a780b6de64b51c978ecf11cb9a462c66be7d4ca9039d33"
|
||||
dependencies = [
|
||||
"getrandom 0.3.3",
|
||||
"libc",
|
||||
]
|
||||
|
||||
[[package]]
|
||||
name = "js-sys"
|
||||
version = "0.3.77"
|
||||
@@ -4167,9 +4151,9 @@ dependencies = [
|
||||
|
||||
[[package]]
|
||||
name = "lru"
|
||||
version = "0.16.3"
|
||||
version = "0.16.2"
|
||||
source = "registry+https://github.com/rust-lang/crates.io-index"
|
||||
checksum = "a1dc47f592c06f33f8e3aea9591776ec7c9f9e4124778ff8a3c3b87159f7e593"
|
||||
checksum = "96051b46fc183dc9cd4a223960ef37b9af631b55191852a8274bfef064cda20f"
|
||||
dependencies = [
|
||||
"hashbrown 0.16.0",
|
||||
]
|
||||
@@ -5347,7 +5331,7 @@ dependencies = [
|
||||
"once_cell",
|
||||
"socket2 0.6.1",
|
||||
"tracing",
|
||||
"windows-sys 0.60.2",
|
||||
"windows-sys 0.52.0",
|
||||
]
|
||||
|
||||
[[package]]
|
||||
@@ -5475,7 +5459,7 @@ dependencies = [
|
||||
"indoc",
|
||||
"itertools 0.14.0",
|
||||
"kasuari",
|
||||
"lru 0.16.3",
|
||||
"lru 0.16.2",
|
||||
"strum 0.27.2",
|
||||
"thiserror 2.0.17",
|
||||
"unicode-segmentation",
|
||||
@@ -5726,7 +5710,7 @@ dependencies = [
|
||||
"errno",
|
||||
"libc",
|
||||
"linux-raw-sys 0.4.15",
|
||||
"windows-sys 0.59.0",
|
||||
"windows-sys 0.52.0",
|
||||
]
|
||||
|
||||
[[package]]
|
||||
@@ -5739,7 +5723,7 @@ dependencies = [
|
||||
"errno",
|
||||
"libc",
|
||||
"linux-raw-sys 0.9.4",
|
||||
"windows-sys 0.60.2",
|
||||
"windows-sys 0.52.0",
|
||||
]
|
||||
|
||||
[[package]]
|
||||
@@ -8027,7 +8011,7 @@ version = "0.1.9"
|
||||
source = "registry+https://github.com/rust-lang/crates.io-index"
|
||||
checksum = "cf221c93e13a30d793f7645a0e7762c55d169dbb0a49671918a2319d289b10bb"
|
||||
dependencies = [
|
||||
"windows-sys 0.59.0",
|
||||
"windows-sys 0.52.0",
|
||||
]
|
||||
|
||||
[[package]]
|
||||
@@ -8825,34 +8809,6 @@ dependencies = [
|
||||
"syn 2.0.104",
|
||||
]
|
||||
|
||||
[[package]]
|
||||
name = "zstd"
|
||||
version = "0.13.3"
|
||||
source = "registry+https://github.com/rust-lang/crates.io-index"
|
||||
checksum = "e91ee311a569c327171651566e07972200e76fcfe2242a4fa446149a3881c08a"
|
||||
dependencies = [
|
||||
"zstd-safe",
|
||||
]
|
||||
|
||||
[[package]]
|
||||
name = "zstd-safe"
|
||||
version = "7.2.4"
|
||||
source = "registry+https://github.com/rust-lang/crates.io-index"
|
||||
checksum = "8f49c4d5f0abb602a93fb8736af2a4f4dd9512e36f7f570d66e65ff867ed3b9d"
|
||||
dependencies = [
|
||||
"zstd-sys",
|
||||
]
|
||||
|
||||
[[package]]
|
||||
name = "zstd-sys"
|
||||
version = "2.0.16+zstd.1.5.7"
|
||||
source = "registry+https://github.com/rust-lang/crates.io-index"
|
||||
checksum = "91e19ebc2adc8f83e43039e79776e3fda8ca919132d68a1fed6a5faca2683748"
|
||||
dependencies = [
|
||||
"cc",
|
||||
"pkg-config",
|
||||
]
|
||||
|
||||
[[package]]
|
||||
name = "zune-core"
|
||||
version = "0.4.12"
|
||||
|
||||
@@ -6,7 +6,6 @@ members = [
|
||||
"app-server",
|
||||
"app-server-protocol",
|
||||
"app-server-test-client",
|
||||
"debug-client",
|
||||
"apply-patch",
|
||||
"arg0",
|
||||
"feedback",
|
||||
@@ -135,6 +134,7 @@ dunce = "1.0.4"
|
||||
encoding_rs = "0.8.35"
|
||||
env-flags = "0.1.1"
|
||||
env_logger = "0.11.5"
|
||||
escargot = "0.5"
|
||||
eventsource-stream = "0.2.3"
|
||||
futures = { version = "0.3", default-features = false }
|
||||
http = "1.3.1"
|
||||
@@ -152,7 +152,7 @@ landlock = "0.4.4"
|
||||
lazy_static = "1"
|
||||
libc = "0.2.177"
|
||||
log = "0.4"
|
||||
lru = "0.16.3"
|
||||
lru = "0.16.2"
|
||||
maplit = "1.0.2"
|
||||
mime_guess = "2.0.5"
|
||||
multimap = "0.10.0"
|
||||
@@ -218,7 +218,6 @@ tracing-subscriber = "0.3.22"
|
||||
tracing-test = "0.2.5"
|
||||
tree-sitter = "0.25.10"
|
||||
tree-sitter-bash = "0.25"
|
||||
zstd = "0.13"
|
||||
tree-sitter-highlight = "0.25.10"
|
||||
ts-rs = "11"
|
||||
tui-scrollbar = "0.2.1"
|
||||
|
||||
@@ -109,26 +109,14 @@ client_request_definitions! {
|
||||
params: v2::ThreadResumeParams,
|
||||
response: v2::ThreadResumeResponse,
|
||||
},
|
||||
ThreadFork => "thread/fork" {
|
||||
params: v2::ThreadForkParams,
|
||||
response: v2::ThreadForkResponse,
|
||||
},
|
||||
ThreadArchive => "thread/archive" {
|
||||
params: v2::ThreadArchiveParams,
|
||||
response: v2::ThreadArchiveResponse,
|
||||
},
|
||||
ThreadRollback => "thread/rollback" {
|
||||
params: v2::ThreadRollbackParams,
|
||||
response: v2::ThreadRollbackResponse,
|
||||
},
|
||||
ThreadList => "thread/list" {
|
||||
params: v2::ThreadListParams,
|
||||
response: v2::ThreadListResponse,
|
||||
},
|
||||
ThreadLoadedList => "thread/loaded/list" {
|
||||
params: v2::ThreadLoadedListParams,
|
||||
response: v2::ThreadLoadedListResponse,
|
||||
},
|
||||
SkillsList => "skills/list" {
|
||||
params: v2::SkillsListParams,
|
||||
response: v2::SkillsListResponse,
|
||||
@@ -205,11 +193,6 @@ client_request_definitions! {
|
||||
response: v2::ConfigWriteResponse,
|
||||
},
|
||||
|
||||
ConfigRequirementsRead => "configRequirements/read" {
|
||||
params: #[ts(type = "undefined")] #[serde(skip_serializing_if = "Option::is_none")] Option<()>,
|
||||
response: v2::ConfigRequirementsReadResponse,
|
||||
},
|
||||
|
||||
GetAccount => "account/read" {
|
||||
params: v2::GetAccountParams,
|
||||
response: v2::GetAccountResponse,
|
||||
@@ -234,11 +217,6 @@ client_request_definitions! {
|
||||
params: v1::ResumeConversationParams,
|
||||
response: v1::ResumeConversationResponse,
|
||||
},
|
||||
/// Fork a recorded Codex conversation into a new session.
|
||||
ForkConversation {
|
||||
params: v1::ForkConversationParams,
|
||||
response: v1::ForkConversationResponse,
|
||||
},
|
||||
ArchiveConversation {
|
||||
params: v1::ArchiveConversationParams,
|
||||
response: v1::ArchiveConversationResponse,
|
||||
@@ -587,7 +565,7 @@ client_notification_definitions! {
|
||||
mod tests {
|
||||
use super::*;
|
||||
use anyhow::Result;
|
||||
use codex_protocol::ThreadId;
|
||||
use codex_protocol::ConversationId;
|
||||
use codex_protocol::account::PlanType;
|
||||
use codex_protocol::parse_command::ParsedCommand;
|
||||
use codex_protocol::protocol::AskForApproval;
|
||||
@@ -636,7 +614,7 @@ mod tests {
|
||||
|
||||
#[test]
|
||||
fn conversation_id_serializes_as_plain_string() -> Result<()> {
|
||||
let id = ThreadId::from_string("67e55044-10b1-426f-9247-bb680e5fe0c8")?;
|
||||
let id = ConversationId::from_string("67e55044-10b1-426f-9247-bb680e5fe0c8")?;
|
||||
|
||||
assert_eq!(
|
||||
json!("67e55044-10b1-426f-9247-bb680e5fe0c8"),
|
||||
@@ -647,10 +625,11 @@ mod tests {
|
||||
|
||||
#[test]
|
||||
fn conversation_id_deserializes_from_plain_string() -> Result<()> {
|
||||
let id: ThreadId = serde_json::from_value(json!("67e55044-10b1-426f-9247-bb680e5fe0c8"))?;
|
||||
let id: ConversationId =
|
||||
serde_json::from_value(json!("67e55044-10b1-426f-9247-bb680e5fe0c8"))?;
|
||||
|
||||
assert_eq!(
|
||||
ThreadId::from_string("67e55044-10b1-426f-9247-bb680e5fe0c8")?,
|
||||
ConversationId::from_string("67e55044-10b1-426f-9247-bb680e5fe0c8")?,
|
||||
id,
|
||||
);
|
||||
Ok(())
|
||||
@@ -671,7 +650,7 @@ mod tests {
|
||||
|
||||
#[test]
|
||||
fn serialize_server_request() -> Result<()> {
|
||||
let conversation_id = ThreadId::from_string("67e55044-10b1-426f-9247-bb680e5fe0c8")?;
|
||||
let conversation_id = ConversationId::from_string("67e55044-10b1-426f-9247-bb680e5fe0c8")?;
|
||||
let params = v1::ExecCommandApprovalParams {
|
||||
conversation_id,
|
||||
call_id: "call-42".to_string(),
|
||||
@@ -729,22 +708,6 @@ mod tests {
|
||||
Ok(())
|
||||
}
|
||||
|
||||
#[test]
|
||||
fn serialize_config_requirements_read() -> Result<()> {
|
||||
let request = ClientRequest::ConfigRequirementsRead {
|
||||
request_id: RequestId::Integer(1),
|
||||
params: None,
|
||||
};
|
||||
assert_eq!(
|
||||
json!({
|
||||
"method": "configRequirements/read",
|
||||
"id": 1,
|
||||
}),
|
||||
serde_json::to_value(&request)?,
|
||||
);
|
||||
Ok(())
|
||||
}
|
||||
|
||||
#[test]
|
||||
fn serialize_account_login_api_key() -> Result<()> {
|
||||
let request = ClientRequest::LoginAccount {
|
||||
|
||||
@@ -6,7 +6,6 @@ use crate::protocol::v2::UserInput;
|
||||
use codex_protocol::protocol::AgentReasoningEvent;
|
||||
use codex_protocol::protocol::AgentReasoningRawContentEvent;
|
||||
use codex_protocol::protocol::EventMsg;
|
||||
use codex_protocol::protocol::ThreadRolledBackEvent;
|
||||
use codex_protocol::protocol::TurnAbortedEvent;
|
||||
use codex_protocol::protocol::UserMessageEvent;
|
||||
|
||||
@@ -58,7 +57,6 @@ impl ThreadHistoryBuilder {
|
||||
EventMsg::TokenCount(_) => {}
|
||||
EventMsg::EnteredReviewMode(_) => {}
|
||||
EventMsg::ExitedReviewMode(_) => {}
|
||||
EventMsg::ThreadRolledBack(payload) => self.handle_thread_rollback(payload),
|
||||
EventMsg::UndoCompleted(_) => {}
|
||||
EventMsg::TurnAborted(payload) => self.handle_turn_aborted(payload),
|
||||
_ => {}
|
||||
@@ -132,23 +130,6 @@ impl ThreadHistoryBuilder {
|
||||
turn.status = TurnStatus::Interrupted;
|
||||
}
|
||||
|
||||
fn handle_thread_rollback(&mut self, payload: &ThreadRolledBackEvent) {
|
||||
self.finish_current_turn();
|
||||
|
||||
let n = usize::try_from(payload.num_turns).unwrap_or(usize::MAX);
|
||||
if n >= self.turns.len() {
|
||||
self.turns.clear();
|
||||
} else {
|
||||
self.turns.truncate(self.turns.len().saturating_sub(n));
|
||||
}
|
||||
|
||||
// Re-number subsequent synthetic ids so the pruned history is consistent.
|
||||
self.next_turn_index =
|
||||
i64::try_from(self.turns.len().saturating_add(1)).unwrap_or(i64::MAX);
|
||||
let item_count: usize = self.turns.iter().map(|t| t.items.len()).sum();
|
||||
self.next_item_index = i64::try_from(item_count.saturating_add(1)).unwrap_or(i64::MAX);
|
||||
}
|
||||
|
||||
fn finish_current_turn(&mut self) {
|
||||
if let Some(turn) = self.current_turn.take() {
|
||||
if turn.items.is_empty() {
|
||||
@@ -232,7 +213,6 @@ mod tests {
|
||||
use codex_protocol::protocol::AgentMessageEvent;
|
||||
use codex_protocol::protocol::AgentReasoningEvent;
|
||||
use codex_protocol::protocol::AgentReasoningRawContentEvent;
|
||||
use codex_protocol::protocol::ThreadRolledBackEvent;
|
||||
use codex_protocol::protocol::TurnAbortReason;
|
||||
use codex_protocol::protocol::TurnAbortedEvent;
|
||||
use codex_protocol::protocol::UserMessageEvent;
|
||||
@@ -430,95 +410,4 @@ mod tests {
|
||||
}
|
||||
);
|
||||
}
|
||||
|
||||
#[test]
|
||||
fn drops_last_turns_on_thread_rollback() {
|
||||
let events = vec![
|
||||
EventMsg::UserMessage(UserMessageEvent {
|
||||
message: "First".into(),
|
||||
images: None,
|
||||
}),
|
||||
EventMsg::AgentMessage(AgentMessageEvent {
|
||||
message: "A1".into(),
|
||||
}),
|
||||
EventMsg::UserMessage(UserMessageEvent {
|
||||
message: "Second".into(),
|
||||
images: None,
|
||||
}),
|
||||
EventMsg::AgentMessage(AgentMessageEvent {
|
||||
message: "A2".into(),
|
||||
}),
|
||||
EventMsg::ThreadRolledBack(ThreadRolledBackEvent { num_turns: 1 }),
|
||||
EventMsg::UserMessage(UserMessageEvent {
|
||||
message: "Third".into(),
|
||||
images: None,
|
||||
}),
|
||||
EventMsg::AgentMessage(AgentMessageEvent {
|
||||
message: "A3".into(),
|
||||
}),
|
||||
];
|
||||
|
||||
let turns = build_turns_from_event_msgs(&events);
|
||||
let expected = vec![
|
||||
Turn {
|
||||
id: "turn-1".into(),
|
||||
status: TurnStatus::Completed,
|
||||
error: None,
|
||||
items: vec![
|
||||
ThreadItem::UserMessage {
|
||||
id: "item-1".into(),
|
||||
content: vec![UserInput::Text {
|
||||
text: "First".into(),
|
||||
}],
|
||||
},
|
||||
ThreadItem::AgentMessage {
|
||||
id: "item-2".into(),
|
||||
text: "A1".into(),
|
||||
},
|
||||
],
|
||||
},
|
||||
Turn {
|
||||
id: "turn-2".into(),
|
||||
status: TurnStatus::Completed,
|
||||
error: None,
|
||||
items: vec![
|
||||
ThreadItem::UserMessage {
|
||||
id: "item-3".into(),
|
||||
content: vec![UserInput::Text {
|
||||
text: "Third".into(),
|
||||
}],
|
||||
},
|
||||
ThreadItem::AgentMessage {
|
||||
id: "item-4".into(),
|
||||
text: "A3".into(),
|
||||
},
|
||||
],
|
||||
},
|
||||
];
|
||||
assert_eq!(turns, expected);
|
||||
}
|
||||
|
||||
#[test]
|
||||
fn thread_rollback_clears_all_turns_when_num_turns_exceeds_history() {
|
||||
let events = vec![
|
||||
EventMsg::UserMessage(UserMessageEvent {
|
||||
message: "One".into(),
|
||||
images: None,
|
||||
}),
|
||||
EventMsg::AgentMessage(AgentMessageEvent {
|
||||
message: "A1".into(),
|
||||
}),
|
||||
EventMsg::UserMessage(UserMessageEvent {
|
||||
message: "Two".into(),
|
||||
images: None,
|
||||
}),
|
||||
EventMsg::AgentMessage(AgentMessageEvent {
|
||||
message: "A2".into(),
|
||||
}),
|
||||
EventMsg::ThreadRolledBack(ThreadRolledBackEvent { num_turns: 99 }),
|
||||
];
|
||||
|
||||
let turns = build_turns_from_event_msgs(&events);
|
||||
assert_eq!(turns, Vec::<Turn>::new());
|
||||
}
|
||||
}
|
||||
|
||||
@@ -1,7 +1,7 @@
|
||||
use std::collections::HashMap;
|
||||
use std::path::PathBuf;
|
||||
|
||||
use codex_protocol::ThreadId;
|
||||
use codex_protocol::ConversationId;
|
||||
use codex_protocol::config_types::ForcedLoginMethod;
|
||||
use codex_protocol::config_types::ReasoningSummary;
|
||||
use codex_protocol::config_types::SandboxMode;
|
||||
@@ -68,7 +68,7 @@ pub struct NewConversationParams {
|
||||
#[derive(Serialize, Deserialize, Debug, Clone, PartialEq, JsonSchema, TS)]
|
||||
#[serde(rename_all = "camelCase")]
|
||||
pub struct NewConversationResponse {
|
||||
pub conversation_id: ThreadId,
|
||||
pub conversation_id: ConversationId,
|
||||
pub model: String,
|
||||
pub reasoning_effort: Option<ReasoningEffort>,
|
||||
pub rollout_path: PathBuf,
|
||||
@@ -77,16 +77,7 @@ pub struct NewConversationResponse {
|
||||
#[derive(Serialize, Deserialize, Debug, Clone, JsonSchema, TS)]
|
||||
#[serde(rename_all = "camelCase")]
|
||||
pub struct ResumeConversationResponse {
|
||||
pub conversation_id: ThreadId,
|
||||
pub model: String,
|
||||
pub initial_messages: Option<Vec<EventMsg>>,
|
||||
pub rollout_path: PathBuf,
|
||||
}
|
||||
|
||||
#[derive(Serialize, Deserialize, Debug, Clone, JsonSchema, TS)]
|
||||
#[serde(rename_all = "camelCase")]
|
||||
pub struct ForkConversationResponse {
|
||||
pub conversation_id: ThreadId,
|
||||
pub conversation_id: ConversationId,
|
||||
pub model: String,
|
||||
pub initial_messages: Option<Vec<EventMsg>>,
|
||||
pub rollout_path: PathBuf,
|
||||
@@ -99,9 +90,9 @@ pub enum GetConversationSummaryParams {
|
||||
#[serde(rename = "rolloutPath")]
|
||||
rollout_path: PathBuf,
|
||||
},
|
||||
ThreadId {
|
||||
ConversationId {
|
||||
#[serde(rename = "conversationId")]
|
||||
conversation_id: ThreadId,
|
||||
conversation_id: ConversationId,
|
||||
},
|
||||
}
|
||||
|
||||
@@ -122,7 +113,7 @@ pub struct ListConversationsParams {
|
||||
#[derive(Serialize, Deserialize, Debug, Clone, PartialEq, JsonSchema, TS)]
|
||||
#[serde(rename_all = "camelCase")]
|
||||
pub struct ConversationSummary {
|
||||
pub conversation_id: ThreadId,
|
||||
pub conversation_id: ConversationId,
|
||||
pub path: PathBuf,
|
||||
pub preview: String,
|
||||
pub timestamp: Option<String>,
|
||||
@@ -152,19 +143,11 @@ pub struct ListConversationsResponse {
|
||||
#[serde(rename_all = "camelCase")]
|
||||
pub struct ResumeConversationParams {
|
||||
pub path: Option<PathBuf>,
|
||||
pub conversation_id: Option<ThreadId>,
|
||||
pub conversation_id: Option<ConversationId>,
|
||||
pub history: Option<Vec<ResponseItem>>,
|
||||
pub overrides: Option<NewConversationParams>,
|
||||
}
|
||||
|
||||
#[derive(Serialize, Deserialize, Debug, Clone, PartialEq, JsonSchema, TS)]
|
||||
#[serde(rename_all = "camelCase")]
|
||||
pub struct ForkConversationParams {
|
||||
pub path: Option<PathBuf>,
|
||||
pub conversation_id: Option<ThreadId>,
|
||||
pub overrides: Option<NewConversationParams>,
|
||||
}
|
||||
|
||||
#[derive(Serialize, Deserialize, Debug, Clone, PartialEq, JsonSchema, TS)]
|
||||
#[serde(rename_all = "camelCase")]
|
||||
pub struct AddConversationSubscriptionResponse {
|
||||
@@ -175,7 +158,7 @@ pub struct AddConversationSubscriptionResponse {
|
||||
#[derive(Serialize, Deserialize, Debug, Clone, PartialEq, JsonSchema, TS)]
|
||||
#[serde(rename_all = "camelCase")]
|
||||
pub struct ArchiveConversationParams {
|
||||
pub conversation_id: ThreadId,
|
||||
pub conversation_id: ConversationId,
|
||||
pub rollout_path: PathBuf,
|
||||
}
|
||||
|
||||
@@ -215,7 +198,7 @@ pub struct GitDiffToRemoteResponse {
|
||||
#[derive(Serialize, Deserialize, Debug, Clone, PartialEq, JsonSchema, TS)]
|
||||
#[serde(rename_all = "camelCase")]
|
||||
pub struct ApplyPatchApprovalParams {
|
||||
pub conversation_id: ThreadId,
|
||||
pub conversation_id: ConversationId,
|
||||
/// Use to correlate this with [codex_core::protocol::PatchApplyBeginEvent]
|
||||
/// and [codex_core::protocol::PatchApplyEndEvent].
|
||||
pub call_id: String,
|
||||
@@ -236,7 +219,7 @@ pub struct ApplyPatchApprovalResponse {
|
||||
#[derive(Serialize, Deserialize, Debug, Clone, PartialEq, JsonSchema, TS)]
|
||||
#[serde(rename_all = "camelCase")]
|
||||
pub struct ExecCommandApprovalParams {
|
||||
pub conversation_id: ThreadId,
|
||||
pub conversation_id: ConversationId,
|
||||
/// Use to correlate this with [codex_core::protocol::ExecCommandBeginEvent]
|
||||
/// and [codex_core::protocol::ExecCommandEndEvent].
|
||||
pub call_id: String,
|
||||
@@ -386,14 +369,14 @@ pub struct SandboxSettings {
|
||||
#[derive(Serialize, Deserialize, Debug, Clone, PartialEq, JsonSchema, TS)]
|
||||
#[serde(rename_all = "camelCase")]
|
||||
pub struct SendUserMessageParams {
|
||||
pub conversation_id: ThreadId,
|
||||
pub conversation_id: ConversationId,
|
||||
pub items: Vec<InputItem>,
|
||||
}
|
||||
|
||||
#[derive(Serialize, Deserialize, Debug, Clone, PartialEq, JsonSchema, TS)]
|
||||
#[serde(rename_all = "camelCase")]
|
||||
pub struct SendUserTurnParams {
|
||||
pub conversation_id: ThreadId,
|
||||
pub conversation_id: ConversationId,
|
||||
pub items: Vec<InputItem>,
|
||||
pub cwd: PathBuf,
|
||||
pub approval_policy: AskForApproval,
|
||||
@@ -412,7 +395,7 @@ pub struct SendUserTurnResponse {}
|
||||
#[derive(Serialize, Deserialize, Debug, Clone, PartialEq, JsonSchema, TS)]
|
||||
#[serde(rename_all = "camelCase")]
|
||||
pub struct InterruptConversationParams {
|
||||
pub conversation_id: ThreadId,
|
||||
pub conversation_id: ConversationId,
|
||||
}
|
||||
|
||||
#[derive(Serialize, Deserialize, Debug, Clone, JsonSchema, TS)]
|
||||
@@ -428,7 +411,7 @@ pub struct SendUserMessageResponse {}
|
||||
#[derive(Serialize, Deserialize, Debug, Clone, PartialEq, JsonSchema, TS)]
|
||||
#[serde(rename_all = "camelCase")]
|
||||
pub struct AddConversationListenerParams {
|
||||
pub conversation_id: ThreadId,
|
||||
pub conversation_id: ConversationId,
|
||||
#[serde(default)]
|
||||
pub experimental_raw_events: bool,
|
||||
}
|
||||
@@ -462,7 +445,7 @@ pub struct LoginChatGptCompleteNotification {
|
||||
#[derive(Serialize, Deserialize, Debug, Clone, JsonSchema, TS)]
|
||||
#[serde(rename_all = "camelCase")]
|
||||
pub struct SessionConfiguredNotification {
|
||||
pub session_id: ThreadId,
|
||||
pub session_id: ConversationId,
|
||||
pub model: String,
|
||||
pub reasoning_effort: Option<ReasoningEffort>,
|
||||
pub history_log_id: u64,
|
||||
|
||||
@@ -89,7 +89,6 @@ pub enum CodexErrorInfo {
|
||||
InternalServerError,
|
||||
Unauthorized,
|
||||
BadRequest,
|
||||
ThreadRollbackFailed,
|
||||
SandboxError,
|
||||
/// The response SSE stream disconnected in the middle of a turn before completion.
|
||||
ResponseStreamDisconnected {
|
||||
@@ -120,7 +119,6 @@ impl From<CoreCodexErrorInfo> for CodexErrorInfo {
|
||||
CoreCodexErrorInfo::InternalServerError => CodexErrorInfo::InternalServerError,
|
||||
CoreCodexErrorInfo::Unauthorized => CodexErrorInfo::Unauthorized,
|
||||
CoreCodexErrorInfo::BadRequest => CodexErrorInfo::BadRequest,
|
||||
CoreCodexErrorInfo::ThreadRollbackFailed => CodexErrorInfo::ThreadRollbackFailed,
|
||||
CoreCodexErrorInfo::SandboxError => CodexErrorInfo::SandboxError,
|
||||
CoreCodexErrorInfo::ResponseStreamDisconnected { http_status_code } => {
|
||||
CodexErrorInfo::ResponseStreamDisconnected { http_status_code }
|
||||
@@ -332,15 +330,6 @@ pub struct ProfileV2 {
|
||||
pub additional: HashMap<String, JsonValue>,
|
||||
}
|
||||
|
||||
#[derive(Serialize, Deserialize, Debug, Clone, PartialEq, JsonSchema, TS)]
|
||||
#[serde(rename_all = "snake_case")]
|
||||
#[ts(export_to = "v2/")]
|
||||
pub struct AnalyticsConfig {
|
||||
pub enabled: Option<bool>,
|
||||
#[serde(default, flatten)]
|
||||
pub additional: HashMap<String, JsonValue>,
|
||||
}
|
||||
|
||||
#[derive(Serialize, Deserialize, Debug, Clone, PartialEq, JsonSchema, TS)]
|
||||
#[serde(rename_all = "snake_case")]
|
||||
#[ts(export_to = "v2/")]
|
||||
@@ -365,7 +354,6 @@ pub struct Config {
|
||||
pub model_reasoning_effort: Option<ReasoningEffort>,
|
||||
pub model_reasoning_summary: Option<ReasoningSummary>,
|
||||
pub model_verbosity: Option<Verbosity>,
|
||||
pub analytics: Option<AnalyticsConfig>,
|
||||
#[serde(default, flatten)]
|
||||
pub additional: HashMap<String, JsonValue>,
|
||||
}
|
||||
@@ -453,22 +441,6 @@ pub struct ConfigReadResponse {
|
||||
pub layers: Option<Vec<ConfigLayer>>,
|
||||
}
|
||||
|
||||
#[derive(Serialize, Deserialize, Debug, Clone, PartialEq, JsonSchema, TS)]
|
||||
#[serde(rename_all = "camelCase")]
|
||||
#[ts(export_to = "v2/")]
|
||||
pub struct ConfigRequirements {
|
||||
pub allowed_approval_policies: Option<Vec<AskForApproval>>,
|
||||
pub allowed_sandbox_modes: Option<Vec<SandboxMode>>,
|
||||
}
|
||||
|
||||
#[derive(Serialize, Deserialize, Debug, Clone, PartialEq, JsonSchema, TS)]
|
||||
#[serde(rename_all = "camelCase")]
|
||||
#[ts(export_to = "v2/")]
|
||||
pub struct ConfigRequirementsReadResponse {
|
||||
/// Null if no requirements are configured (e.g. no requirements.toml/MDM entries).
|
||||
pub requirements: Option<ConfigRequirements>,
|
||||
}
|
||||
|
||||
#[derive(Serialize, Deserialize, Debug, Clone, PartialEq, JsonSchema, TS)]
|
||||
#[serde(rename_all = "camelCase")]
|
||||
#[ts(export_to = "v2/")]
|
||||
@@ -503,33 +475,14 @@ pub struct ConfigEdit {
|
||||
#[derive(Serialize, Deserialize, Debug, Clone, PartialEq, Eq, JsonSchema, TS)]
|
||||
#[serde(rename_all = "camelCase")]
|
||||
#[ts(export_to = "v2/")]
|
||||
pub enum CommandExecutionApprovalDecision {
|
||||
/// User approved the command.
|
||||
pub enum ApprovalDecision {
|
||||
Accept,
|
||||
/// User approved the command and future identical commands should run without prompting.
|
||||
/// Approve and remember the approval for the session.
|
||||
AcceptForSession,
|
||||
/// User approved the command, and wants to apply the proposed execpolicy amendment so future
|
||||
/// matching commands can run without prompting.
|
||||
AcceptWithExecpolicyAmendment {
|
||||
execpolicy_amendment: ExecPolicyAmendment,
|
||||
},
|
||||
/// User denied the command. The agent will continue the turn.
|
||||
Decline,
|
||||
/// User denied the command. The turn will also be immediately interrupted.
|
||||
Cancel,
|
||||
}
|
||||
|
||||
#[derive(Serialize, Deserialize, Debug, Clone, PartialEq, Eq, JsonSchema, TS)]
|
||||
#[serde(rename_all = "camelCase")]
|
||||
#[ts(export_to = "v2/")]
|
||||
pub enum FileChangeApprovalDecision {
|
||||
/// User approved the file changes.
|
||||
Accept,
|
||||
/// User approved the file changes and future changes to the same files should run without prompting.
|
||||
AcceptForSession,
|
||||
/// User denied the file changes. The agent will continue the turn.
|
||||
Decline,
|
||||
/// User denied the file changes. The turn will also be immediately interrupted.
|
||||
Cancel,
|
||||
}
|
||||
|
||||
@@ -1080,47 +1033,6 @@ pub struct ThreadResumeResponse {
|
||||
pub reasoning_effort: Option<ReasoningEffort>,
|
||||
}
|
||||
|
||||
#[derive(Serialize, Deserialize, Debug, Default, Clone, PartialEq, JsonSchema, TS)]
|
||||
#[serde(rename_all = "camelCase")]
|
||||
#[ts(export_to = "v2/")]
|
||||
/// There are two ways to fork a thread:
|
||||
/// 1. By thread_id: load the thread from disk by thread_id and fork it into a new thread.
|
||||
/// 2. By path: load the thread from disk by path and fork it into a new thread.
|
||||
///
|
||||
/// If using path, the thread_id param will be ignored.
|
||||
///
|
||||
/// Prefer using thread_id whenever possible.
|
||||
pub struct ThreadForkParams {
|
||||
pub thread_id: String,
|
||||
|
||||
/// [UNSTABLE] Specify the rollout path to fork from.
|
||||
/// If specified, the thread_id param will be ignored.
|
||||
pub path: Option<PathBuf>,
|
||||
|
||||
/// Configuration overrides for the forked thread, if any.
|
||||
pub model: Option<String>,
|
||||
pub model_provider: Option<String>,
|
||||
pub cwd: Option<String>,
|
||||
pub approval_policy: Option<AskForApproval>,
|
||||
pub sandbox: Option<SandboxMode>,
|
||||
pub config: Option<HashMap<String, serde_json::Value>>,
|
||||
pub base_instructions: Option<String>,
|
||||
pub developer_instructions: Option<String>,
|
||||
}
|
||||
|
||||
#[derive(Serialize, Deserialize, Debug, Clone, PartialEq, JsonSchema, TS)]
|
||||
#[serde(rename_all = "camelCase")]
|
||||
#[ts(export_to = "v2/")]
|
||||
pub struct ThreadForkResponse {
|
||||
pub thread: Thread,
|
||||
pub model: String,
|
||||
pub model_provider: String,
|
||||
pub cwd: PathBuf,
|
||||
pub approval_policy: AskForApproval,
|
||||
pub sandbox: SandboxPolicy,
|
||||
pub reasoning_effort: Option<ReasoningEffort>,
|
||||
}
|
||||
|
||||
#[derive(Serialize, Deserialize, Debug, Clone, PartialEq, JsonSchema, TS)]
|
||||
#[serde(rename_all = "camelCase")]
|
||||
#[ts(export_to = "v2/")]
|
||||
@@ -1133,30 +1045,6 @@ pub struct ThreadArchiveParams {
|
||||
#[ts(export_to = "v2/")]
|
||||
pub struct ThreadArchiveResponse {}
|
||||
|
||||
#[derive(Serialize, Deserialize, Debug, Clone, PartialEq, JsonSchema, TS)]
|
||||
#[serde(rename_all = "camelCase")]
|
||||
#[ts(export_to = "v2/")]
|
||||
pub struct ThreadRollbackParams {
|
||||
pub thread_id: String,
|
||||
/// The number of turns to drop from the end of the thread. Must be >= 1.
|
||||
///
|
||||
/// This only modifies the thread's history and does not revert local file changes
|
||||
/// that have been made by the agent. Clients are responsible for reverting these changes.
|
||||
pub num_turns: u32,
|
||||
}
|
||||
|
||||
#[derive(Serialize, Deserialize, Debug, Clone, PartialEq, JsonSchema, TS)]
|
||||
#[serde(rename_all = "camelCase")]
|
||||
#[ts(export_to = "v2/")]
|
||||
pub struct ThreadRollbackResponse {
|
||||
/// The updated thread after applying the rollback, with `turns` populated.
|
||||
///
|
||||
/// The ThreadItems stored in each Turn are lossy since we explicitly do not
|
||||
/// persist all agent interactions, such as command executions. This is the same
|
||||
/// behavior as `thread/resume`.
|
||||
pub thread: Thread,
|
||||
}
|
||||
|
||||
#[derive(Serialize, Deserialize, Debug, Clone, PartialEq, JsonSchema, TS)]
|
||||
#[serde(rename_all = "camelCase")]
|
||||
#[ts(export_to = "v2/")]
|
||||
@@ -1180,27 +1068,6 @@ pub struct ThreadListResponse {
|
||||
pub next_cursor: Option<String>,
|
||||
}
|
||||
|
||||
#[derive(Serialize, Deserialize, Debug, Clone, PartialEq, Default, JsonSchema, TS)]
|
||||
#[serde(rename_all = "camelCase")]
|
||||
#[ts(export_to = "v2/")]
|
||||
pub struct ThreadLoadedListParams {
|
||||
/// Opaque pagination cursor returned by a previous call.
|
||||
pub cursor: Option<String>,
|
||||
/// Optional page size; defaults to no limit.
|
||||
pub limit: Option<u32>,
|
||||
}
|
||||
|
||||
#[derive(Serialize, Deserialize, Debug, Clone, PartialEq, JsonSchema, TS)]
|
||||
#[serde(rename_all = "camelCase")]
|
||||
#[ts(export_to = "v2/")]
|
||||
pub struct ThreadLoadedListResponse {
|
||||
/// Thread ids for sessions currently loaded in memory.
|
||||
pub data: Vec<String>,
|
||||
/// Opaque cursor to pass to the next call to continue after the last item.
|
||||
/// if None, there are no more items to return.
|
||||
pub next_cursor: Option<String>,
|
||||
}
|
||||
|
||||
#[derive(Serialize, Deserialize, Debug, Clone, PartialEq, JsonSchema, TS)]
|
||||
#[serde(rename_all = "camelCase")]
|
||||
#[ts(export_to = "v2/")]
|
||||
@@ -1316,7 +1183,7 @@ pub struct Thread {
|
||||
pub source: SessionSource,
|
||||
/// Optional Git metadata captured when the thread was created.
|
||||
pub git_info: Option<GitInfo>,
|
||||
/// Only populated on `thread/resume`, `thread/rollback`, `thread/fork` responses.
|
||||
/// Only populated on a `thread/resume` response.
|
||||
/// For all other responses and notifications returning a Thread,
|
||||
/// the turns field will be an empty list.
|
||||
pub turns: Vec<Turn>,
|
||||
@@ -1344,7 +1211,6 @@ pub struct ThreadTokenUsageUpdatedNotification {
|
||||
pub struct ThreadTokenUsage {
|
||||
pub total: TokenUsageBreakdown,
|
||||
pub last: TokenUsageBreakdown,
|
||||
// TODO(aibrahim): make this not optional
|
||||
#[ts(type = "number | null")]
|
||||
pub model_context_window: Option<i64>,
|
||||
}
|
||||
@@ -1392,7 +1258,7 @@ impl From<CoreTokenUsage> for TokenUsageBreakdown {
|
||||
#[ts(export_to = "v2/")]
|
||||
pub struct Turn {
|
||||
pub id: String,
|
||||
/// Only populated on a `thread/resume` or `thread/fork` response.
|
||||
/// Only populated on a `thread/resume` response.
|
||||
/// For all other responses and notifications returning a Turn,
|
||||
/// the items field will be an empty list.
|
||||
pub items: Vec<ThreadItem>,
|
||||
@@ -1538,7 +1404,6 @@ pub enum UserInput {
|
||||
Text { text: String },
|
||||
Image { url: String },
|
||||
LocalImage { path: PathBuf },
|
||||
Skill { name: String, path: PathBuf },
|
||||
}
|
||||
|
||||
impl UserInput {
|
||||
@@ -1547,7 +1412,6 @@ impl UserInput {
|
||||
UserInput::Text { text } => CoreUserInput::Text { text },
|
||||
UserInput::Image { url } => CoreUserInput::Image { image_url: url },
|
||||
UserInput::LocalImage { path } => CoreUserInput::LocalImage { path },
|
||||
UserInput::Skill { name, path } => CoreUserInput::Skill { name, path },
|
||||
}
|
||||
}
|
||||
}
|
||||
@@ -1558,7 +1422,6 @@ impl From<CoreUserInput> for UserInput {
|
||||
CoreUserInput::Text { text } => UserInput::Text { text },
|
||||
CoreUserInput::Image { image_url } => UserInput::Image { url: image_url },
|
||||
CoreUserInput::LocalImage { path } => UserInput::LocalImage { path },
|
||||
CoreUserInput::Skill { name, path } => UserInput::Skill { name, path },
|
||||
_ => unreachable!("unsupported user input variant"),
|
||||
}
|
||||
}
|
||||
@@ -1985,7 +1848,7 @@ pub struct CommandExecutionRequestApprovalParams {
|
||||
#[serde(rename_all = "camelCase")]
|
||||
#[ts(export_to = "v2/")]
|
||||
pub struct CommandExecutionRequestApprovalResponse {
|
||||
pub decision: CommandExecutionApprovalDecision,
|
||||
pub decision: ApprovalDecision,
|
||||
}
|
||||
|
||||
#[derive(Serialize, Deserialize, Debug, Clone, PartialEq, JsonSchema, TS)]
|
||||
@@ -2005,7 +1868,7 @@ pub struct FileChangeRequestApprovalParams {
|
||||
#[derive(Serialize, Deserialize, Debug, Clone, PartialEq, JsonSchema, TS)]
|
||||
#[ts(export_to = "v2/")]
|
||||
pub struct FileChangeRequestApprovalResponse {
|
||||
pub decision: FileChangeApprovalDecision,
|
||||
pub decision: ApprovalDecision,
|
||||
}
|
||||
|
||||
#[derive(Serialize, Deserialize, Debug, Clone, PartialEq, JsonSchema, TS)]
|
||||
@@ -2144,10 +2007,6 @@ mod tests {
|
||||
CoreUserInput::LocalImage {
|
||||
path: PathBuf::from("local/image.png"),
|
||||
},
|
||||
CoreUserInput::Skill {
|
||||
name: "skill-creator".to_string(),
|
||||
path: PathBuf::from("/repo/.codex/skills/skill-creator/SKILL.md"),
|
||||
},
|
||||
],
|
||||
});
|
||||
|
||||
@@ -2165,10 +2024,6 @@ mod tests {
|
||||
UserInput::LocalImage {
|
||||
path: PathBuf::from("local/image.png"),
|
||||
},
|
||||
UserInput::Skill {
|
||||
name: "skill-creator".to_string(),
|
||||
path: PathBuf::from("/repo/.codex/skills/skill-creator/SKILL.md"),
|
||||
},
|
||||
],
|
||||
}
|
||||
);
|
||||
|
||||
@@ -18,13 +18,12 @@ use clap::Parser;
|
||||
use clap::Subcommand;
|
||||
use codex_app_server_protocol::AddConversationListenerParams;
|
||||
use codex_app_server_protocol::AddConversationSubscriptionResponse;
|
||||
use codex_app_server_protocol::ApprovalDecision;
|
||||
use codex_app_server_protocol::AskForApproval;
|
||||
use codex_app_server_protocol::ClientInfo;
|
||||
use codex_app_server_protocol::ClientRequest;
|
||||
use codex_app_server_protocol::CommandExecutionApprovalDecision;
|
||||
use codex_app_server_protocol::CommandExecutionRequestApprovalParams;
|
||||
use codex_app_server_protocol::CommandExecutionRequestApprovalResponse;
|
||||
use codex_app_server_protocol::FileChangeApprovalDecision;
|
||||
use codex_app_server_protocol::FileChangeRequestApprovalParams;
|
||||
use codex_app_server_protocol::FileChangeRequestApprovalResponse;
|
||||
use codex_app_server_protocol::GetAccountRateLimitsResponse;
|
||||
@@ -37,8 +36,6 @@ use codex_app_server_protocol::JSONRPCRequest;
|
||||
use codex_app_server_protocol::JSONRPCResponse;
|
||||
use codex_app_server_protocol::LoginChatGptCompleteNotification;
|
||||
use codex_app_server_protocol::LoginChatGptResponse;
|
||||
use codex_app_server_protocol::ModelListParams;
|
||||
use codex_app_server_protocol::ModelListResponse;
|
||||
use codex_app_server_protocol::NewConversationParams;
|
||||
use codex_app_server_protocol::NewConversationResponse;
|
||||
use codex_app_server_protocol::RequestId;
|
||||
@@ -53,7 +50,7 @@ use codex_app_server_protocol::TurnStartParams;
|
||||
use codex_app_server_protocol::TurnStartResponse;
|
||||
use codex_app_server_protocol::TurnStatus;
|
||||
use codex_app_server_protocol::UserInput as V2UserInput;
|
||||
use codex_protocol::ThreadId;
|
||||
use codex_protocol::ConversationId;
|
||||
use codex_protocol::protocol::Event;
|
||||
use codex_protocol::protocol::EventMsg;
|
||||
use serde::Serialize;
|
||||
@@ -130,9 +127,6 @@ enum CliCommand {
|
||||
TestLogin,
|
||||
/// Fetch the current account rate limits from the Codex app-server.
|
||||
GetAccountRateLimits,
|
||||
/// List the available models from the Codex app-server.
|
||||
#[command(name = "model-list")]
|
||||
ModelList,
|
||||
}
|
||||
|
||||
fn main() -> Result<()> {
|
||||
@@ -167,7 +161,6 @@ fn main() -> Result<()> {
|
||||
),
|
||||
CliCommand::TestLogin => test_login(&codex_bin, &config_overrides),
|
||||
CliCommand::GetAccountRateLimits => get_account_rate_limits(&codex_bin, &config_overrides),
|
||||
CliCommand::ModelList => model_list(&codex_bin, &config_overrides),
|
||||
}
|
||||
}
|
||||
|
||||
@@ -177,7 +170,7 @@ fn send_message(codex_bin: &str, config_overrides: &[String], user_message: Stri
|
||||
let initialize = client.initialize()?;
|
||||
println!("< initialize response: {initialize:?}");
|
||||
|
||||
let conversation = client.start_thread()?;
|
||||
let conversation = client.new_conversation()?;
|
||||
println!("< newConversation response: {conversation:?}");
|
||||
|
||||
let subscription = client.add_conversation_listener(&conversation.conversation_id)?;
|
||||
@@ -188,7 +181,7 @@ fn send_message(codex_bin: &str, config_overrides: &[String], user_message: Stri
|
||||
|
||||
client.stream_conversation(&conversation.conversation_id)?;
|
||||
|
||||
client.remove_thread_listener(subscription.subscription_id)?;
|
||||
client.remove_conversation_listener(subscription.subscription_id)?;
|
||||
|
||||
Ok(())
|
||||
}
|
||||
@@ -351,18 +344,6 @@ fn get_account_rate_limits(codex_bin: &str, config_overrides: &[String]) -> Resu
|
||||
Ok(())
|
||||
}
|
||||
|
||||
fn model_list(codex_bin: &str, config_overrides: &[String]) -> Result<()> {
|
||||
let mut client = CodexClient::spawn(codex_bin, config_overrides)?;
|
||||
|
||||
let initialize = client.initialize()?;
|
||||
println!("< initialize response: {initialize:?}");
|
||||
|
||||
let response = client.model_list(ModelListParams::default())?;
|
||||
println!("< model/list response: {response:?}");
|
||||
|
||||
Ok(())
|
||||
}
|
||||
|
||||
struct CodexClient {
|
||||
child: Child,
|
||||
stdin: Option<ChildStdin>,
|
||||
@@ -417,7 +398,7 @@ impl CodexClient {
|
||||
self.send_request(request, request_id, "initialize")
|
||||
}
|
||||
|
||||
fn start_thread(&mut self) -> Result<NewConversationResponse> {
|
||||
fn new_conversation(&mut self) -> Result<NewConversationResponse> {
|
||||
let request_id = self.request_id();
|
||||
let request = ClientRequest::NewConversation {
|
||||
request_id: request_id.clone(),
|
||||
@@ -429,7 +410,7 @@ impl CodexClient {
|
||||
|
||||
fn add_conversation_listener(
|
||||
&mut self,
|
||||
conversation_id: &ThreadId,
|
||||
conversation_id: &ConversationId,
|
||||
) -> Result<AddConversationSubscriptionResponse> {
|
||||
let request_id = self.request_id();
|
||||
let request = ClientRequest::AddConversationListener {
|
||||
@@ -443,7 +424,7 @@ impl CodexClient {
|
||||
self.send_request(request, request_id, "addConversationListener")
|
||||
}
|
||||
|
||||
fn remove_thread_listener(&mut self, subscription_id: Uuid) -> Result<()> {
|
||||
fn remove_conversation_listener(&mut self, subscription_id: Uuid) -> Result<()> {
|
||||
let request_id = self.request_id();
|
||||
let request = ClientRequest::RemoveConversationListener {
|
||||
request_id: request_id.clone(),
|
||||
@@ -461,7 +442,7 @@ impl CodexClient {
|
||||
|
||||
fn send_user_message(
|
||||
&mut self,
|
||||
conversation_id: &ThreadId,
|
||||
conversation_id: &ConversationId,
|
||||
message: &str,
|
||||
) -> Result<SendUserMessageResponse> {
|
||||
let request_id = self.request_id();
|
||||
@@ -518,17 +499,7 @@ impl CodexClient {
|
||||
self.send_request(request, request_id, "account/rateLimits/read")
|
||||
}
|
||||
|
||||
fn model_list(&mut self, params: ModelListParams) -> Result<ModelListResponse> {
|
||||
let request_id = self.request_id();
|
||||
let request = ClientRequest::ModelList {
|
||||
request_id: request_id.clone(),
|
||||
params,
|
||||
};
|
||||
|
||||
self.send_request(request, request_id, "model/list")
|
||||
}
|
||||
|
||||
fn stream_conversation(&mut self, conversation_id: &ThreadId) -> Result<()> {
|
||||
fn stream_conversation(&mut self, conversation_id: &ConversationId) -> Result<()> {
|
||||
loop {
|
||||
let notification = self.next_notification()?;
|
||||
|
||||
@@ -665,7 +636,7 @@ impl CodexClient {
|
||||
fn extract_event(
|
||||
&self,
|
||||
notification: JSONRPCNotification,
|
||||
conversation_id: &ThreadId,
|
||||
conversation_id: &ConversationId,
|
||||
) -> Result<Option<Event>> {
|
||||
let params = notification
|
||||
.params
|
||||
@@ -679,7 +650,7 @@ impl CodexClient {
|
||||
let conversation_value = map
|
||||
.remove("conversationId")
|
||||
.context("event missing conversationId")?;
|
||||
let notification_conversation: ThreadId = serde_json::from_value(conversation_value)
|
||||
let notification_conversation: ConversationId = serde_json::from_value(conversation_value)
|
||||
.context("conversationId was not a valid UUID")?;
|
||||
|
||||
if ¬ification_conversation != conversation_id {
|
||||
@@ -846,7 +817,7 @@ impl CodexClient {
|
||||
}
|
||||
|
||||
let response = CommandExecutionRequestApprovalResponse {
|
||||
decision: CommandExecutionApprovalDecision::Accept,
|
||||
decision: ApprovalDecision::Accept,
|
||||
};
|
||||
self.send_server_request_response(request_id, &response)?;
|
||||
println!("< approved commandExecution request for item {item_id}");
|
||||
@@ -877,7 +848,7 @@ impl CodexClient {
|
||||
}
|
||||
|
||||
let response = FileChangeRequestApprovalResponse {
|
||||
decision: FileChangeApprovalDecision::Accept,
|
||||
decision: ApprovalDecision::Accept,
|
||||
};
|
||||
self.send_server_request_response(request_id, &response)?;
|
||||
println!("< approved fileChange request for item {item_id}");
|
||||
|
||||
@@ -11,8 +11,6 @@
|
||||
- [Initialization](#initialization)
|
||||
- [API Overview](#api-overview)
|
||||
- [Events](#events)
|
||||
- [Approvals](#approvals)
|
||||
- [Skills](#skills)
|
||||
- [Auth endpoints](#auth-endpoints)
|
||||
|
||||
## Protocol
|
||||
@@ -41,7 +39,7 @@ Use the thread APIs to create, list, or archive conversations. Drive a conversat
|
||||
## Lifecycle Overview
|
||||
|
||||
- Initialize once: Immediately after launching the codex app-server process, send an `initialize` request with your client metadata, then emit an `initialized` notification. Any other request before this handshake gets rejected.
|
||||
- Start (or resume) a thread: Call `thread/start` to open a fresh conversation. The response returns the thread object and you’ll also get a `thread/started` notification. If you’re continuing an existing conversation, call `thread/resume` with its ID instead. If you want to branch from an existing conversation, call `thread/fork` to create a new thread id with copied history.
|
||||
- Start (or resume) a thread: Call `thread/start` to open a fresh conversation. The response returns the thread object and you’ll also get a `thread/started` notification. If you’re continuing an existing conversation, call `thread/resume` with its ID instead.
|
||||
- Begin a turn: To send user input, call `turn/start` with the target `threadId` and the user's input. Optional fields let you override model, cwd, sandbox policy, etc. This immediately returns the new turn object and triggers a `turn/started` notification.
|
||||
- Stream events: After `turn/start`, keep reading JSON-RPC notifications on stdout. You’ll see `item/started`, `item/completed`, deltas like `item/agentMessage/delta`, tool progress, etc. These represent streaming model output plus any side effects (commands, tool calls, reasoning notes).
|
||||
- Finish the turn: When the model is done (or the turn is interrupted via making the `turn/interrupt` call), the server sends `turn/completed` with the final turn state and token usage.
|
||||
@@ -72,11 +70,8 @@ Example (from OpenAI's official VSCode extension):
|
||||
|
||||
- `thread/start` — create a new thread; emits `thread/started` and auto-subscribes you to turn/item events for that thread.
|
||||
- `thread/resume` — reopen an existing thread by id so subsequent `turn/start` calls append to it.
|
||||
- `thread/fork` — fork an existing thread into a new thread id by copying the stored history; emits `thread/started` and auto-subscribes you to turn/item events for the new thread.
|
||||
- `thread/list` — page through stored rollouts; supports cursor-based pagination and optional `modelProviders` filtering.
|
||||
- `thread/loaded/list` — list the thread ids currently loaded in memory.
|
||||
- `thread/archive` — move a thread’s rollout file into the archived directory; returns `{}` on success.
|
||||
- `thread/rollback` — drop the last N turns from the agent’s in-memory context and persist a rollback marker in the rollout so future resumes see the pruned history; returns the updated `thread` (with `turns` populated) on success.
|
||||
- `turn/start` — add user input to a thread and begin Codex generation; responds with the initial `turn` object and streams `turn/started`, `item/*`, and `turn/completed` notifications.
|
||||
- `turn/interrupt` — request cancellation of an in-flight turn by `(thread_id, turn_id)`; success is an empty `{}` response and the turn finishes with `status: "interrupted"`.
|
||||
- `review/start` — kick off Codex’s automated reviewer for a thread; responds like `turn/start` and emits `item/started`/`item/completed` notifications with `enteredReviewMode` and `exitedReviewMode` items, plus a final assistant `agentMessage` containing the review.
|
||||
@@ -87,10 +82,9 @@ Example (from OpenAI's official VSCode extension):
|
||||
- `mcpServerStatus/list` — enumerate configured MCP servers with their tools, resources, resource templates, and auth status; supports cursor+limit pagination.
|
||||
- `feedback/upload` — submit a feedback report (classification + optional reason/logs and conversation_id); returns the tracking thread id.
|
||||
- `command/exec` — run a single command under the server sandbox without starting a thread/turn (handy for utilities and validation).
|
||||
- `config/read` — fetch the effective config on disk after resolving config layering.
|
||||
- `config/read` — fetch the effective config on disk after resolving config layering (thread-agnostic; does not include in-repo `.codex/` layers).
|
||||
- `config/value/write` — write a single config key/value to the user's config.toml on disk.
|
||||
- `config/batchWrite` — apply multiple config edits atomically to the user's config.toml on disk.
|
||||
- `configRequirements/read` — fetch the loaded requirements allow-lists from `requirements.toml` and/or MDM (or `null` if none are configured).
|
||||
|
||||
### Example: Start or resume a thread
|
||||
|
||||
@@ -123,14 +117,6 @@ To continue a stored session, call `thread/resume` with the `thread.id` you prev
|
||||
{ "id": 11, "result": { "thread": { "id": "thr_123", … } } }
|
||||
```
|
||||
|
||||
To branch from a stored session, call `thread/fork` with the `thread.id`. This creates a new thread id and emits a `thread/started` notification for it:
|
||||
|
||||
```json
|
||||
{ "method": "thread/fork", "id": 12, "params": { "threadId": "thr_123" } }
|
||||
{ "id": 12, "result": { "thread": { "id": "thr_456", … } } }
|
||||
{ "method": "thread/started", "params": { "thread": { … } } }
|
||||
```
|
||||
|
||||
### Example: List threads (with pagination & filters)
|
||||
|
||||
`thread/list` lets you render a history UI. Pass any combination of:
|
||||
@@ -157,17 +143,6 @@ Example:
|
||||
|
||||
When `nextCursor` is `null`, you’ve reached the final page.
|
||||
|
||||
### Example: List loaded threads
|
||||
|
||||
`thread/loaded/list` returns thread ids currently loaded in memory. This is useful when you want to check which sessions are active without scanning rollouts on disk.
|
||||
|
||||
```json
|
||||
{ "method": "thread/loaded/list", "id": 21 }
|
||||
{ "id": 21, "result": {
|
||||
"data": ["thr_123", "thr_456"]
|
||||
} }
|
||||
```
|
||||
|
||||
### Example: Archive a thread
|
||||
|
||||
Use `thread/archive` to move the persisted rollout (stored as a JSONL file on disk) into the archived sessions directory.
|
||||
@@ -220,26 +195,6 @@ You can optionally specify config overrides on the new turn. If specified, these
|
||||
} } }
|
||||
```
|
||||
|
||||
### Example: Start a turn (invoke a skill)
|
||||
|
||||
Invoke a skill explicitly by including `$<skill-name>` in the text input and adding a `skill` input item alongside it.
|
||||
|
||||
```json
|
||||
{ "method": "turn/start", "id": 33, "params": {
|
||||
"threadId": "thr_123",
|
||||
"input": [
|
||||
{ "type": "text", "text": "$skill-creator Add a new skill for triaging flaky CI and include step-by-step usage." },
|
||||
{ "type": "skill", "name": "skill-creator", "path": "/Users/me/.codex/skills/skill-creator/SKILL.md" }
|
||||
]
|
||||
} }
|
||||
{ "id": 33, "result": { "turn": {
|
||||
"id": "turn_457",
|
||||
"status": "inProgress",
|
||||
"items": [],
|
||||
"error": null
|
||||
} } }
|
||||
```
|
||||
|
||||
### Example: Interrupt an active turn
|
||||
|
||||
You can cancel a running Turn with `turn/interrupt`.
|
||||
@@ -449,46 +404,6 @@ Order of messages:
|
||||
|
||||
UI guidance for IDEs: surface an approval dialog as soon as the request arrives. The turn will proceed after the server receives a response to the approval request. The terminal `item/completed` notification will be sent with the appropriate status.
|
||||
|
||||
## Skills
|
||||
|
||||
Invoke a skill by including `$<skill-name>` in the text input. Add a `skill` input item (recommended) so the backend injects full skill instructions instead of relying on the model to resolve the name.
|
||||
|
||||
```json
|
||||
{
|
||||
"method": "turn/start",
|
||||
"id": 101,
|
||||
"params": {
|
||||
"threadId": "thread-1",
|
||||
"input": [
|
||||
{ "type": "text", "text": "$skill-creator Add a new skill for triaging flaky CI." },
|
||||
{ "type": "skill", "name": "skill-creator", "path": "/Users/me/.codex/skills/skill-creator/SKILL.md" }
|
||||
]
|
||||
}
|
||||
}
|
||||
```
|
||||
|
||||
If you omit the `skill` item, the model will still parse the `$<skill-name>` marker and try to locate the skill, which can add latency.
|
||||
|
||||
Example:
|
||||
|
||||
```
|
||||
$skill-creator Add a new skill for triaging flaky CI and include step-by-step usage.
|
||||
```
|
||||
|
||||
Use `skills/list` to fetch the available skills (optionally scoped by `cwd` and/or with `forceReload`).
|
||||
|
||||
```json
|
||||
{ "method": "skills/list", "id": 25, "params": {
|
||||
"cwd": "/Users/me/project",
|
||||
"forceReload": false
|
||||
} }
|
||||
{ "id": 25, "result": {
|
||||
"skills": [
|
||||
{ "name": "skill-creator", "description": "Create or update a Codex skill" }
|
||||
]
|
||||
} }
|
||||
```
|
||||
|
||||
## Auth endpoints
|
||||
|
||||
The JSON-RPC auth/account surface exposes request/response methods plus server-initiated notifications (no `id`). Use these to determine auth state, start or cancel logins, logout, and inspect ChatGPT rate limits.
|
||||
|
||||
@@ -1,21 +1,15 @@
|
||||
use crate::codex_message_processor::ApiVersion;
|
||||
use crate::codex_message_processor::PendingInterrupts;
|
||||
use crate::codex_message_processor::PendingRollbacks;
|
||||
use crate::codex_message_processor::TurnSummary;
|
||||
use crate::codex_message_processor::TurnSummaryStore;
|
||||
use crate::codex_message_processor::read_event_msgs_from_rollout;
|
||||
use crate::codex_message_processor::read_summary_from_rollout;
|
||||
use crate::codex_message_processor::summary_to_thread;
|
||||
use crate::error_code::INTERNAL_ERROR_CODE;
|
||||
use crate::error_code::INVALID_REQUEST_ERROR_CODE;
|
||||
use crate::outgoing_message::OutgoingMessageSender;
|
||||
use codex_app_server_protocol::AccountRateLimitsUpdatedNotification;
|
||||
use codex_app_server_protocol::AgentMessageDeltaNotification;
|
||||
use codex_app_server_protocol::ApplyPatchApprovalParams;
|
||||
use codex_app_server_protocol::ApplyPatchApprovalResponse;
|
||||
use codex_app_server_protocol::ApprovalDecision;
|
||||
use codex_app_server_protocol::CodexErrorInfo as V2CodexErrorInfo;
|
||||
use codex_app_server_protocol::CommandAction as V2ParsedCommand;
|
||||
use codex_app_server_protocol::CommandExecutionApprovalDecision;
|
||||
use codex_app_server_protocol::CommandExecutionOutputDeltaNotification;
|
||||
use codex_app_server_protocol::CommandExecutionRequestApprovalParams;
|
||||
use codex_app_server_protocol::CommandExecutionRequestApprovalResponse;
|
||||
@@ -26,7 +20,6 @@ use codex_app_server_protocol::ErrorNotification;
|
||||
use codex_app_server_protocol::ExecCommandApprovalParams;
|
||||
use codex_app_server_protocol::ExecCommandApprovalResponse;
|
||||
use codex_app_server_protocol::ExecPolicyAmendment as V2ExecPolicyAmendment;
|
||||
use codex_app_server_protocol::FileChangeApprovalDecision;
|
||||
use codex_app_server_protocol::FileChangeOutputDeltaNotification;
|
||||
use codex_app_server_protocol::FileChangeRequestApprovalParams;
|
||||
use codex_app_server_protocol::FileChangeRequestApprovalResponse;
|
||||
@@ -34,7 +27,6 @@ use codex_app_server_protocol::FileUpdateChange;
|
||||
use codex_app_server_protocol::InterruptConversationResponse;
|
||||
use codex_app_server_protocol::ItemCompletedNotification;
|
||||
use codex_app_server_protocol::ItemStartedNotification;
|
||||
use codex_app_server_protocol::JSONRPCErrorError;
|
||||
use codex_app_server_protocol::McpToolCallError;
|
||||
use codex_app_server_protocol::McpToolCallResult;
|
||||
use codex_app_server_protocol::McpToolCallStatus;
|
||||
@@ -48,7 +40,6 @@ use codex_app_server_protocol::ServerNotification;
|
||||
use codex_app_server_protocol::ServerRequestPayload;
|
||||
use codex_app_server_protocol::TerminalInteractionNotification;
|
||||
use codex_app_server_protocol::ThreadItem;
|
||||
use codex_app_server_protocol::ThreadRollbackResponse;
|
||||
use codex_app_server_protocol::ThreadTokenUsage;
|
||||
use codex_app_server_protocol::ThreadTokenUsageUpdatedNotification;
|
||||
use codex_app_server_protocol::Turn;
|
||||
@@ -59,11 +50,9 @@ use codex_app_server_protocol::TurnInterruptResponse;
|
||||
use codex_app_server_protocol::TurnPlanStep;
|
||||
use codex_app_server_protocol::TurnPlanUpdatedNotification;
|
||||
use codex_app_server_protocol::TurnStatus;
|
||||
use codex_app_server_protocol::build_turns_from_event_msgs;
|
||||
use codex_core::CodexThread;
|
||||
use codex_core::CodexConversation;
|
||||
use codex_core::parse_command::shlex_join;
|
||||
use codex_core::protocol::ApplyPatchApprovalRequestEvent;
|
||||
use codex_core::protocol::CodexErrorInfo as CoreCodexErrorInfo;
|
||||
use codex_core::protocol::Event;
|
||||
use codex_core::protocol::EventMsg;
|
||||
use codex_core::protocol::ExecApprovalRequestEvent;
|
||||
@@ -77,7 +66,7 @@ use codex_core::protocol::TokenCountEvent;
|
||||
use codex_core::protocol::TurnDiffEvent;
|
||||
use codex_core::review_format::format_review_findings_block;
|
||||
use codex_core::review_prompts;
|
||||
use codex_protocol::ThreadId;
|
||||
use codex_protocol::ConversationId;
|
||||
use codex_protocol::plan_tool::UpdatePlanArgs;
|
||||
use codex_protocol::protocol::ReviewOutputEvent;
|
||||
use std::collections::HashMap;
|
||||
@@ -89,17 +78,14 @@ use tracing::error;
|
||||
|
||||
type JsonValue = serde_json::Value;
|
||||
|
||||
#[allow(clippy::too_many_arguments)]
|
||||
pub(crate) async fn apply_bespoke_event_handling(
|
||||
event: Event,
|
||||
conversation_id: ThreadId,
|
||||
conversation: Arc<CodexThread>,
|
||||
conversation_id: ConversationId,
|
||||
conversation: Arc<CodexConversation>,
|
||||
outgoing: Arc<OutgoingMessageSender>,
|
||||
pending_interrupts: PendingInterrupts,
|
||||
pending_rollbacks: PendingRollbacks,
|
||||
turn_summary_store: TurnSummaryStore,
|
||||
api_version: ApiVersion,
|
||||
fallback_model_provider: String,
|
||||
) {
|
||||
let Event {
|
||||
id: event_turn_id,
|
||||
@@ -351,26 +337,6 @@ pub(crate) async fn apply_bespoke_event_handling(
|
||||
.await;
|
||||
}
|
||||
EventMsg::Error(ev) => {
|
||||
let message = ev.message.clone();
|
||||
let codex_error_info = ev.codex_error_info.clone();
|
||||
|
||||
// If this error belongs to an in-flight `thread/rollback` request, fail that request
|
||||
// (and clear pending state) so subsequent rollbacks are unblocked.
|
||||
//
|
||||
// Don't send a notification for this error.
|
||||
if matches!(
|
||||
codex_error_info,
|
||||
Some(CoreCodexErrorInfo::ThreadRollbackFailed)
|
||||
) {
|
||||
return handle_thread_rollback_failed(
|
||||
conversation_id,
|
||||
message,
|
||||
&pending_rollbacks,
|
||||
&outgoing,
|
||||
)
|
||||
.await;
|
||||
};
|
||||
|
||||
let turn_error = TurnError {
|
||||
message: ev.message,
|
||||
codex_error_info: ev.codex_error_info.map(V2CodexErrorInfo::from),
|
||||
@@ -379,7 +345,7 @@ pub(crate) async fn apply_bespoke_event_handling(
|
||||
handle_error(conversation_id, turn_error.clone(), &turn_summary_store).await;
|
||||
outgoing
|
||||
.send_server_notification(ServerNotification::Error(ErrorNotification {
|
||||
error: turn_error.clone(),
|
||||
error: turn_error,
|
||||
will_retry: false,
|
||||
thread_id: conversation_id.to_string(),
|
||||
turn_id: event_turn_id.clone(),
|
||||
@@ -724,58 +690,6 @@ pub(crate) async fn apply_bespoke_event_handling(
|
||||
)
|
||||
.await;
|
||||
}
|
||||
EventMsg::ThreadRolledBack(_rollback_event) => {
|
||||
let pending = {
|
||||
let mut map = pending_rollbacks.lock().await;
|
||||
map.remove(&conversation_id)
|
||||
};
|
||||
|
||||
if let Some(request_id) = pending {
|
||||
let rollout_path = conversation.rollout_path();
|
||||
let response = match read_summary_from_rollout(
|
||||
rollout_path.as_path(),
|
||||
fallback_model_provider.as_str(),
|
||||
)
|
||||
.await
|
||||
{
|
||||
Ok(summary) => {
|
||||
let mut thread = summary_to_thread(summary);
|
||||
match read_event_msgs_from_rollout(rollout_path.as_path()).await {
|
||||
Ok(events) => {
|
||||
thread.turns = build_turns_from_event_msgs(&events);
|
||||
ThreadRollbackResponse { thread }
|
||||
}
|
||||
Err(err) => {
|
||||
let error = JSONRPCErrorError {
|
||||
code: INTERNAL_ERROR_CODE,
|
||||
message: format!(
|
||||
"failed to load rollout `{}`: {err}",
|
||||
rollout_path.display()
|
||||
),
|
||||
data: None,
|
||||
};
|
||||
outgoing.send_error(request_id, error).await;
|
||||
return;
|
||||
}
|
||||
}
|
||||
}
|
||||
Err(err) => {
|
||||
let error = JSONRPCErrorError {
|
||||
code: INTERNAL_ERROR_CODE,
|
||||
message: format!(
|
||||
"failed to load rollout `{}`: {err}",
|
||||
rollout_path.display()
|
||||
),
|
||||
data: None,
|
||||
};
|
||||
outgoing.send_error(request_id, error).await;
|
||||
return;
|
||||
}
|
||||
};
|
||||
|
||||
outgoing.send_response(request_id, response).await;
|
||||
}
|
||||
}
|
||||
EventMsg::TurnDiff(turn_diff_event) => {
|
||||
handle_turn_diff(
|
||||
conversation_id,
|
||||
@@ -802,7 +716,7 @@ pub(crate) async fn apply_bespoke_event_handling(
|
||||
}
|
||||
|
||||
async fn handle_turn_diff(
|
||||
conversation_id: ThreadId,
|
||||
conversation_id: ConversationId,
|
||||
event_turn_id: &str,
|
||||
turn_diff_event: TurnDiffEvent,
|
||||
api_version: ApiVersion,
|
||||
@@ -821,7 +735,7 @@ async fn handle_turn_diff(
|
||||
}
|
||||
|
||||
async fn handle_turn_plan_update(
|
||||
conversation_id: ThreadId,
|
||||
conversation_id: ConversationId,
|
||||
event_turn_id: &str,
|
||||
plan_update_event: UpdatePlanArgs,
|
||||
api_version: ApiVersion,
|
||||
@@ -845,7 +759,7 @@ async fn handle_turn_plan_update(
|
||||
}
|
||||
|
||||
async fn emit_turn_completed_with_status(
|
||||
conversation_id: ThreadId,
|
||||
conversation_id: ConversationId,
|
||||
event_turn_id: String,
|
||||
status: TurnStatus,
|
||||
error: Option<TurnError>,
|
||||
@@ -866,7 +780,7 @@ async fn emit_turn_completed_with_status(
|
||||
}
|
||||
|
||||
async fn complete_file_change_item(
|
||||
conversation_id: ThreadId,
|
||||
conversation_id: ConversationId,
|
||||
item_id: String,
|
||||
changes: Vec<FileUpdateChange>,
|
||||
status: PatchApplyStatus,
|
||||
@@ -898,7 +812,7 @@ async fn complete_file_change_item(
|
||||
|
||||
#[allow(clippy::too_many_arguments)]
|
||||
async fn complete_command_execution_item(
|
||||
conversation_id: ThreadId,
|
||||
conversation_id: ConversationId,
|
||||
turn_id: String,
|
||||
item_id: String,
|
||||
command: String,
|
||||
@@ -931,7 +845,7 @@ async fn complete_command_execution_item(
|
||||
|
||||
async fn maybe_emit_raw_response_item_completed(
|
||||
api_version: ApiVersion,
|
||||
conversation_id: ThreadId,
|
||||
conversation_id: ConversationId,
|
||||
turn_id: &str,
|
||||
item: codex_protocol::models::ResponseItem,
|
||||
outgoing: &OutgoingMessageSender,
|
||||
@@ -951,7 +865,7 @@ async fn maybe_emit_raw_response_item_completed(
|
||||
}
|
||||
|
||||
async fn find_and_remove_turn_summary(
|
||||
conversation_id: ThreadId,
|
||||
conversation_id: ConversationId,
|
||||
turn_summary_store: &TurnSummaryStore,
|
||||
) -> TurnSummary {
|
||||
let mut map = turn_summary_store.lock().await;
|
||||
@@ -959,7 +873,7 @@ async fn find_and_remove_turn_summary(
|
||||
}
|
||||
|
||||
async fn handle_turn_complete(
|
||||
conversation_id: ThreadId,
|
||||
conversation_id: ConversationId,
|
||||
event_turn_id: String,
|
||||
outgoing: &OutgoingMessageSender,
|
||||
turn_summary_store: &TurnSummaryStore,
|
||||
@@ -975,7 +889,7 @@ async fn handle_turn_complete(
|
||||
}
|
||||
|
||||
async fn handle_turn_interrupted(
|
||||
conversation_id: ThreadId,
|
||||
conversation_id: ConversationId,
|
||||
event_turn_id: String,
|
||||
outgoing: &OutgoingMessageSender,
|
||||
turn_summary_store: &TurnSummaryStore,
|
||||
@@ -992,33 +906,8 @@ async fn handle_turn_interrupted(
|
||||
.await;
|
||||
}
|
||||
|
||||
async fn handle_thread_rollback_failed(
|
||||
conversation_id: ThreadId,
|
||||
message: String,
|
||||
pending_rollbacks: &PendingRollbacks,
|
||||
outgoing: &OutgoingMessageSender,
|
||||
) {
|
||||
let pending_rollback = {
|
||||
let mut map = pending_rollbacks.lock().await;
|
||||
map.remove(&conversation_id)
|
||||
};
|
||||
|
||||
if let Some(request_id) = pending_rollback {
|
||||
outgoing
|
||||
.send_error(
|
||||
request_id,
|
||||
JSONRPCErrorError {
|
||||
code: INVALID_REQUEST_ERROR_CODE,
|
||||
message: message.clone(),
|
||||
data: None,
|
||||
},
|
||||
)
|
||||
.await;
|
||||
}
|
||||
}
|
||||
|
||||
async fn handle_token_count_event(
|
||||
conversation_id: ThreadId,
|
||||
conversation_id: ConversationId,
|
||||
turn_id: String,
|
||||
token_count_event: TokenCountEvent,
|
||||
outgoing: &OutgoingMessageSender,
|
||||
@@ -1046,7 +935,7 @@ async fn handle_token_count_event(
|
||||
}
|
||||
|
||||
async fn handle_error(
|
||||
conversation_id: ThreadId,
|
||||
conversation_id: ConversationId,
|
||||
error: TurnError,
|
||||
turn_summary_store: &TurnSummaryStore,
|
||||
) {
|
||||
@@ -1057,7 +946,7 @@ async fn handle_error(
|
||||
async fn on_patch_approval_response(
|
||||
event_turn_id: String,
|
||||
receiver: oneshot::Receiver<JsonValue>,
|
||||
codex: Arc<CodexThread>,
|
||||
codex: Arc<CodexConversation>,
|
||||
) {
|
||||
let response = receiver.await;
|
||||
let value = match response {
|
||||
@@ -1099,7 +988,7 @@ async fn on_patch_approval_response(
|
||||
async fn on_exec_approval_response(
|
||||
event_turn_id: String,
|
||||
receiver: oneshot::Receiver<JsonValue>,
|
||||
conversation: Arc<CodexThread>,
|
||||
conversation: Arc<CodexConversation>,
|
||||
) {
|
||||
let response = receiver.await;
|
||||
let value = match response {
|
||||
@@ -1194,29 +1083,14 @@ fn format_file_change_diff(change: &CoreFileChange) -> String {
|
||||
}
|
||||
}
|
||||
|
||||
fn map_file_change_approval_decision(
|
||||
decision: FileChangeApprovalDecision,
|
||||
) -> (ReviewDecision, Option<PatchApplyStatus>) {
|
||||
match decision {
|
||||
FileChangeApprovalDecision::Accept => (ReviewDecision::Approved, None),
|
||||
FileChangeApprovalDecision::AcceptForSession => (ReviewDecision::ApprovedForSession, None),
|
||||
FileChangeApprovalDecision::Decline => {
|
||||
(ReviewDecision::Denied, Some(PatchApplyStatus::Declined))
|
||||
}
|
||||
FileChangeApprovalDecision::Cancel => {
|
||||
(ReviewDecision::Abort, Some(PatchApplyStatus::Declined))
|
||||
}
|
||||
}
|
||||
}
|
||||
|
||||
#[allow(clippy::too_many_arguments)]
|
||||
async fn on_file_change_request_approval_response(
|
||||
event_turn_id: String,
|
||||
conversation_id: ThreadId,
|
||||
conversation_id: ConversationId,
|
||||
item_id: String,
|
||||
changes: Vec<FileUpdateChange>,
|
||||
receiver: oneshot::Receiver<JsonValue>,
|
||||
codex: Arc<CodexThread>,
|
||||
codex: Arc<CodexConversation>,
|
||||
outgoing: Arc<OutgoingMessageSender>,
|
||||
turn_summary_store: TurnSummaryStore,
|
||||
) {
|
||||
@@ -1227,12 +1101,23 @@ async fn on_file_change_request_approval_response(
|
||||
.unwrap_or_else(|err| {
|
||||
error!("failed to deserialize FileChangeRequestApprovalResponse: {err}");
|
||||
FileChangeRequestApprovalResponse {
|
||||
decision: FileChangeApprovalDecision::Decline,
|
||||
decision: ApprovalDecision::Decline,
|
||||
}
|
||||
});
|
||||
|
||||
let (decision, completion_status) =
|
||||
map_file_change_approval_decision(response.decision);
|
||||
let (decision, completion_status) = match response.decision {
|
||||
ApprovalDecision::Accept
|
||||
| ApprovalDecision::AcceptForSession
|
||||
| ApprovalDecision::AcceptWithExecpolicyAmendment { .. } => {
|
||||
(ReviewDecision::Approved, None)
|
||||
}
|
||||
ApprovalDecision::Decline => {
|
||||
(ReviewDecision::Denied, Some(PatchApplyStatus::Declined))
|
||||
}
|
||||
ApprovalDecision::Cancel => {
|
||||
(ReviewDecision::Abort, Some(PatchApplyStatus::Declined))
|
||||
}
|
||||
};
|
||||
// Allow EventMsg::PatchApplyEnd to emit ItemCompleted for accepted patches.
|
||||
// Only short-circuit on declines/cancels/failures.
|
||||
(decision, completion_status)
|
||||
@@ -1270,13 +1155,13 @@ async fn on_file_change_request_approval_response(
|
||||
#[allow(clippy::too_many_arguments)]
|
||||
async fn on_command_execution_request_approval_response(
|
||||
event_turn_id: String,
|
||||
conversation_id: ThreadId,
|
||||
conversation_id: ConversationId,
|
||||
item_id: String,
|
||||
command: String,
|
||||
cwd: PathBuf,
|
||||
command_actions: Vec<V2ParsedCommand>,
|
||||
receiver: oneshot::Receiver<JsonValue>,
|
||||
conversation: Arc<CodexThread>,
|
||||
conversation: Arc<CodexConversation>,
|
||||
outgoing: Arc<OutgoingMessageSender>,
|
||||
) {
|
||||
let response = receiver.await;
|
||||
@@ -1286,18 +1171,16 @@ async fn on_command_execution_request_approval_response(
|
||||
.unwrap_or_else(|err| {
|
||||
error!("failed to deserialize CommandExecutionRequestApprovalResponse: {err}");
|
||||
CommandExecutionRequestApprovalResponse {
|
||||
decision: CommandExecutionApprovalDecision::Decline,
|
||||
decision: ApprovalDecision::Decline,
|
||||
}
|
||||
});
|
||||
|
||||
let decision = response.decision;
|
||||
|
||||
let (decision, completion_status) = match decision {
|
||||
CommandExecutionApprovalDecision::Accept => (ReviewDecision::Approved, None),
|
||||
CommandExecutionApprovalDecision::AcceptForSession => {
|
||||
(ReviewDecision::ApprovedForSession, None)
|
||||
}
|
||||
CommandExecutionApprovalDecision::AcceptWithExecpolicyAmendment {
|
||||
ApprovalDecision::Accept => (ReviewDecision::Approved, None),
|
||||
ApprovalDecision::AcceptForSession => (ReviewDecision::ApprovedForSession, None),
|
||||
ApprovalDecision::AcceptWithExecpolicyAmendment {
|
||||
execpolicy_amendment,
|
||||
} => (
|
||||
ReviewDecision::ApprovedExecpolicyAmendment {
|
||||
@@ -1305,11 +1188,11 @@ async fn on_command_execution_request_approval_response(
|
||||
},
|
||||
None,
|
||||
),
|
||||
CommandExecutionApprovalDecision::Decline => (
|
||||
ApprovalDecision::Decline => (
|
||||
ReviewDecision::Denied,
|
||||
Some(CommandExecutionStatus::Declined),
|
||||
),
|
||||
CommandExecutionApprovalDecision::Cancel => (
|
||||
ApprovalDecision::Cancel => (
|
||||
ReviewDecision::Abort,
|
||||
Some(CommandExecutionStatus::Declined),
|
||||
),
|
||||
@@ -1449,17 +1332,9 @@ mod tests {
|
||||
Arc::new(Mutex::new(HashMap::new()))
|
||||
}
|
||||
|
||||
#[test]
|
||||
fn file_change_accept_for_session_maps_to_approved_for_session() {
|
||||
let (decision, completion_status) =
|
||||
map_file_change_approval_decision(FileChangeApprovalDecision::AcceptForSession);
|
||||
assert_eq!(decision, ReviewDecision::ApprovedForSession);
|
||||
assert_eq!(completion_status, None);
|
||||
}
|
||||
|
||||
#[tokio::test]
|
||||
async fn test_handle_error_records_message() -> Result<()> {
|
||||
let conversation_id = ThreadId::new();
|
||||
let conversation_id = ConversationId::new();
|
||||
let turn_summary_store = new_turn_summary_store();
|
||||
|
||||
handle_error(
|
||||
@@ -1487,7 +1362,7 @@ mod tests {
|
||||
|
||||
#[tokio::test]
|
||||
async fn test_handle_turn_complete_emits_completed_without_error() -> Result<()> {
|
||||
let conversation_id = ThreadId::new();
|
||||
let conversation_id = ConversationId::new();
|
||||
let event_turn_id = "complete1".to_string();
|
||||
let (tx, mut rx) = mpsc::channel(CHANNEL_CAPACITY);
|
||||
let outgoing = Arc::new(OutgoingMessageSender::new(tx));
|
||||
@@ -1519,7 +1394,7 @@ mod tests {
|
||||
|
||||
#[tokio::test]
|
||||
async fn test_handle_turn_interrupted_emits_interrupted_with_error() -> Result<()> {
|
||||
let conversation_id = ThreadId::new();
|
||||
let conversation_id = ConversationId::new();
|
||||
let event_turn_id = "interrupt1".to_string();
|
||||
let turn_summary_store = new_turn_summary_store();
|
||||
handle_error(
|
||||
@@ -1561,7 +1436,7 @@ mod tests {
|
||||
|
||||
#[tokio::test]
|
||||
async fn test_handle_turn_complete_emits_failed_with_error() -> Result<()> {
|
||||
let conversation_id = ThreadId::new();
|
||||
let conversation_id = ConversationId::new();
|
||||
let event_turn_id = "complete_err1".to_string();
|
||||
let turn_summary_store = new_turn_summary_store();
|
||||
handle_error(
|
||||
@@ -1626,7 +1501,7 @@ mod tests {
|
||||
],
|
||||
};
|
||||
|
||||
let conversation_id = ThreadId::new();
|
||||
let conversation_id = ConversationId::new();
|
||||
|
||||
handle_turn_plan_update(
|
||||
conversation_id,
|
||||
@@ -1660,7 +1535,7 @@ mod tests {
|
||||
|
||||
#[tokio::test]
|
||||
async fn test_handle_token_count_event_emits_usage_and_rate_limits() -> Result<()> {
|
||||
let conversation_id = ThreadId::new();
|
||||
let conversation_id = ConversationId::new();
|
||||
let turn_id = "turn-123".to_string();
|
||||
let (tx, mut rx) = mpsc::channel(CHANNEL_CAPACITY);
|
||||
let outgoing = Arc::new(OutgoingMessageSender::new(tx));
|
||||
@@ -1745,7 +1620,7 @@ mod tests {
|
||||
|
||||
#[tokio::test]
|
||||
async fn test_handle_token_count_event_without_usage_info() -> Result<()> {
|
||||
let conversation_id = ThreadId::new();
|
||||
let conversation_id = ConversationId::new();
|
||||
let turn_id = "turn-456".to_string();
|
||||
let (tx, mut rx) = mpsc::channel(CHANNEL_CAPACITY);
|
||||
let outgoing = Arc::new(OutgoingMessageSender::new(tx));
|
||||
@@ -1779,7 +1654,7 @@ mod tests {
|
||||
},
|
||||
};
|
||||
|
||||
let thread_id = ThreadId::new().to_string();
|
||||
let thread_id = ConversationId::new().to_string();
|
||||
let turn_id = "turn_1".to_string();
|
||||
let notification = construct_mcp_tool_call_notification(
|
||||
begin_event.clone(),
|
||||
@@ -1809,8 +1684,8 @@ mod tests {
|
||||
#[tokio::test]
|
||||
async fn test_handle_turn_complete_emits_error_multiple_turns() -> Result<()> {
|
||||
// Conversation A will have two turns; Conversation B will have one turn.
|
||||
let conversation_a = ThreadId::new();
|
||||
let conversation_b = ThreadId::new();
|
||||
let conversation_a = ConversationId::new();
|
||||
let conversation_b = ConversationId::new();
|
||||
let turn_summary_store = new_turn_summary_store();
|
||||
|
||||
let (tx, mut rx) = mpsc::channel(CHANNEL_CAPACITY);
|
||||
@@ -1937,7 +1812,7 @@ mod tests {
|
||||
},
|
||||
};
|
||||
|
||||
let thread_id = ThreadId::new().to_string();
|
||||
let thread_id = ConversationId::new().to_string();
|
||||
let turn_id = "turn_2".to_string();
|
||||
let notification = construct_mcp_tool_call_notification(
|
||||
begin_event.clone(),
|
||||
@@ -1988,7 +1863,7 @@ mod tests {
|
||||
result: Ok(result),
|
||||
};
|
||||
|
||||
let thread_id = ThreadId::new().to_string();
|
||||
let thread_id = ConversationId::new().to_string();
|
||||
let turn_id = "turn_3".to_string();
|
||||
let notification = construct_mcp_tool_call_end_notification(
|
||||
end_event.clone(),
|
||||
@@ -2031,7 +1906,7 @@ mod tests {
|
||||
result: Err("boom".to_string()),
|
||||
};
|
||||
|
||||
let thread_id = ThreadId::new().to_string();
|
||||
let thread_id = ConversationId::new().to_string();
|
||||
let turn_id = "turn_4".to_string();
|
||||
let notification = construct_mcp_tool_call_end_notification(
|
||||
end_event.clone(),
|
||||
@@ -2065,7 +1940,7 @@ mod tests {
|
||||
let (tx, mut rx) = mpsc::channel(CHANNEL_CAPACITY);
|
||||
let outgoing = OutgoingMessageSender::new(tx);
|
||||
let unified_diff = "--- a\n+++ b\n".to_string();
|
||||
let conversation_id = ThreadId::new();
|
||||
let conversation_id = ConversationId::new();
|
||||
|
||||
handle_turn_diff(
|
||||
conversation_id,
|
||||
@@ -2100,7 +1975,7 @@ mod tests {
|
||||
async fn test_handle_turn_diff_is_noop_for_v1() -> Result<()> {
|
||||
let (tx, mut rx) = mpsc::channel(CHANNEL_CAPACITY);
|
||||
let outgoing = OutgoingMessageSender::new(tx);
|
||||
let conversation_id = ThreadId::new();
|
||||
let conversation_id = ConversationId::new();
|
||||
|
||||
handle_turn_diff(
|
||||
conversation_id,
|
||||
|
||||
File diff suppressed because it is too large
Load Diff
@@ -3,35 +3,32 @@ use crate::error_code::INVALID_REQUEST_ERROR_CODE;
|
||||
use codex_app_server_protocol::ConfigBatchWriteParams;
|
||||
use codex_app_server_protocol::ConfigReadParams;
|
||||
use codex_app_server_protocol::ConfigReadResponse;
|
||||
use codex_app_server_protocol::ConfigRequirements;
|
||||
use codex_app_server_protocol::ConfigRequirementsReadResponse;
|
||||
use codex_app_server_protocol::ConfigValueWriteParams;
|
||||
use codex_app_server_protocol::ConfigWriteErrorCode;
|
||||
use codex_app_server_protocol::ConfigWriteResponse;
|
||||
use codex_app_server_protocol::JSONRPCErrorError;
|
||||
use codex_app_server_protocol::SandboxMode;
|
||||
use codex_core::config::Config;
|
||||
use codex_core::config::ConfigBuilder;
|
||||
use codex_core::config::ConfigService;
|
||||
use codex_core::config::ConfigServiceError;
|
||||
use codex_core::config_loader::ConfigRequirementsToml;
|
||||
use codex_core::config_loader::LoaderOverrides;
|
||||
use codex_core::config_loader::SandboxModeRequirement as CoreSandboxModeRequirement;
|
||||
use codex_utils_json_to_toml::json_to_toml;
|
||||
use serde_json::json;
|
||||
use std::path::PathBuf;
|
||||
use toml::Value as TomlValue;
|
||||
|
||||
#[derive(Clone)]
|
||||
pub(crate) struct ConfigApi {
|
||||
codex_home: PathBuf,
|
||||
cli_overrides: Vec<(String, TomlValue)>,
|
||||
service: ConfigService,
|
||||
}
|
||||
|
||||
impl ConfigApi {
|
||||
pub(crate) fn new(
|
||||
codex_home: PathBuf,
|
||||
cli_overrides: Vec<(String, TomlValue)>,
|
||||
loader_overrides: LoaderOverrides,
|
||||
) -> Self {
|
||||
pub(crate) fn new(codex_home: PathBuf, cli_overrides: Vec<(String, TomlValue)>) -> Self {
|
||||
Self {
|
||||
service: ConfigService::new(codex_home, cli_overrides, loader_overrides),
|
||||
service: ConfigService::new(codex_home.clone(), cli_overrides.clone()),
|
||||
codex_home,
|
||||
cli_overrides,
|
||||
}
|
||||
}
|
||||
|
||||
@@ -42,17 +39,28 @@ impl ConfigApi {
|
||||
self.service.read(params).await.map_err(map_error)
|
||||
}
|
||||
|
||||
pub(crate) async fn config_requirements_read(
|
||||
pub(crate) async fn load_thread_agnostic_config(
|
||||
&self,
|
||||
) -> Result<ConfigRequirementsReadResponse, JSONRPCErrorError> {
|
||||
let requirements = self
|
||||
.service
|
||||
.read_requirements()
|
||||
.await
|
||||
.map_err(map_error)?
|
||||
.map(map_requirements_toml_to_api);
|
||||
overrides: codex_core::config::ConfigOverrides,
|
||||
request_cli_overrides: Option<std::collections::HashMap<String, serde_json::Value>>,
|
||||
) -> std::io::Result<Config> {
|
||||
// Apply the app server's startup `--config` overrides, then apply request-scoped overrides
|
||||
// with higher precedence.
|
||||
let mut merged_cli_overrides = self.cli_overrides.clone();
|
||||
merged_cli_overrides.extend(
|
||||
request_cli_overrides
|
||||
.unwrap_or_default()
|
||||
.into_iter()
|
||||
.map(|(k, v)| (k, json_to_toml(v))),
|
||||
);
|
||||
|
||||
Ok(ConfigRequirementsReadResponse { requirements })
|
||||
ConfigBuilder::default()
|
||||
.codex_home(self.codex_home.clone())
|
||||
.cli_overrides(merged_cli_overrides)
|
||||
.harness_overrides(overrides)
|
||||
.thread_agnostic()
|
||||
.build()
|
||||
.await
|
||||
}
|
||||
|
||||
pub(crate) async fn write_value(
|
||||
@@ -68,31 +76,17 @@ impl ConfigApi {
|
||||
) -> Result<ConfigWriteResponse, JSONRPCErrorError> {
|
||||
self.service.batch_write(params).await.map_err(map_error)
|
||||
}
|
||||
}
|
||||
|
||||
fn map_requirements_toml_to_api(requirements: ConfigRequirementsToml) -> ConfigRequirements {
|
||||
ConfigRequirements {
|
||||
allowed_approval_policies: requirements.allowed_approval_policies.map(|policies| {
|
||||
policies
|
||||
.into_iter()
|
||||
.map(codex_app_server_protocol::AskForApproval::from)
|
||||
.collect()
|
||||
}),
|
||||
allowed_sandbox_modes: requirements.allowed_sandbox_modes.map(|modes| {
|
||||
modes
|
||||
.into_iter()
|
||||
.filter_map(map_sandbox_mode_requirement_to_api)
|
||||
.collect()
|
||||
}),
|
||||
}
|
||||
}
|
||||
|
||||
fn map_sandbox_mode_requirement_to_api(mode: CoreSandboxModeRequirement) -> Option<SandboxMode> {
|
||||
match mode {
|
||||
CoreSandboxModeRequirement::ReadOnly => Some(SandboxMode::ReadOnly),
|
||||
CoreSandboxModeRequirement::WorkspaceWrite => Some(SandboxMode::WorkspaceWrite),
|
||||
CoreSandboxModeRequirement::DangerFullAccess => Some(SandboxMode::DangerFullAccess),
|
||||
CoreSandboxModeRequirement::ExternalSandbox => None,
|
||||
pub(crate) async fn load_latest_thread_agnostic_config(
|
||||
&self,
|
||||
) -> Result<Config, JSONRPCErrorError> {
|
||||
self.load_thread_agnostic_config(codex_core::config::ConfigOverrides::default(), None)
|
||||
.await
|
||||
.map_err(|err| JSONRPCErrorError {
|
||||
code: INTERNAL_ERROR_CODE,
|
||||
message: format!("failed to reload config: {err}"),
|
||||
data: None,
|
||||
})
|
||||
}
|
||||
}
|
||||
|
||||
@@ -117,38 +111,3 @@ fn config_write_error(code: ConfigWriteErrorCode, message: impl Into<String>) ->
|
||||
})),
|
||||
}
|
||||
}
|
||||
|
||||
#[cfg(test)]
|
||||
mod tests {
|
||||
use super::*;
|
||||
use codex_protocol::protocol::AskForApproval as CoreAskForApproval;
|
||||
use pretty_assertions::assert_eq;
|
||||
|
||||
#[test]
|
||||
fn map_requirements_toml_to_api_converts_core_enums() {
|
||||
let requirements = ConfigRequirementsToml {
|
||||
allowed_approval_policies: Some(vec![
|
||||
CoreAskForApproval::Never,
|
||||
CoreAskForApproval::OnRequest,
|
||||
]),
|
||||
allowed_sandbox_modes: Some(vec![
|
||||
CoreSandboxModeRequirement::ReadOnly,
|
||||
CoreSandboxModeRequirement::ExternalSandbox,
|
||||
]),
|
||||
};
|
||||
|
||||
let mapped = map_requirements_toml_to_api(requirements);
|
||||
|
||||
assert_eq!(
|
||||
mapped.allowed_approval_policies,
|
||||
Some(vec![
|
||||
codex_app_server_protocol::AskForApproval::Never,
|
||||
codex_app_server_protocol::AskForApproval::OnRequest,
|
||||
])
|
||||
);
|
||||
assert_eq!(
|
||||
mapped.allowed_sandbox_modes,
|
||||
Some(vec![SandboxMode::ReadOnly]),
|
||||
);
|
||||
}
|
||||
}
|
||||
|
||||
@@ -1,8 +1,7 @@
|
||||
#![deny(clippy::print_stdout, clippy::print_stderr)]
|
||||
|
||||
use codex_common::CliConfigOverrides;
|
||||
use codex_core::config::ConfigBuilder;
|
||||
use codex_core::config_loader::LoaderOverrides;
|
||||
use codex_core::config::Config;
|
||||
use std::io::ErrorKind;
|
||||
use std::io::Result as IoResult;
|
||||
use std::path::PathBuf;
|
||||
@@ -43,7 +42,6 @@ const CHANNEL_CAPACITY: usize = 128;
|
||||
pub async fn run_main(
|
||||
codex_linux_sandbox_exe: Option<PathBuf>,
|
||||
cli_config_overrides: CliConfigOverrides,
|
||||
loader_overrides: LoaderOverrides,
|
||||
) -> IoResult<()> {
|
||||
// Set up channels.
|
||||
let (incoming_tx, mut incoming_rx) = mpsc::channel::<JSONRPCMessage>(CHANNEL_CAPACITY);
|
||||
@@ -80,11 +78,7 @@ pub async fn run_main(
|
||||
format!("error parsing -c overrides: {e}"),
|
||||
)
|
||||
})?;
|
||||
let loader_overrides_for_config_api = loader_overrides.clone();
|
||||
let config = ConfigBuilder::default()
|
||||
.cli_overrides(cli_kv_overrides.clone())
|
||||
.loader_overrides(loader_overrides)
|
||||
.build()
|
||||
let config = Config::load_with_cli_overrides(cli_kv_overrides.clone())
|
||||
.await
|
||||
.map_err(|e| {
|
||||
std::io::Error::new(ErrorKind::InvalidData, format!("error loading config: {e}"))
|
||||
@@ -126,13 +120,11 @@ pub async fn run_main(
|
||||
let processor_handle = tokio::spawn({
|
||||
let outgoing_message_sender = OutgoingMessageSender::new(outgoing_tx);
|
||||
let cli_overrides: Vec<(String, TomlValue)> = cli_kv_overrides.clone();
|
||||
let loader_overrides = loader_overrides_for_config_api;
|
||||
let mut processor = MessageProcessor::new(
|
||||
outgoing_message_sender,
|
||||
codex_linux_sandbox_exe,
|
||||
std::sync::Arc::new(config),
|
||||
cli_overrides,
|
||||
loader_overrides,
|
||||
feedback.clone(),
|
||||
);
|
||||
async move {
|
||||
|
||||
@@ -1,42 +1,10 @@
|
||||
use codex_app_server::run_main;
|
||||
use codex_arg0::arg0_dispatch_or_else;
|
||||
use codex_common::CliConfigOverrides;
|
||||
use codex_core::config_loader::LoaderOverrides;
|
||||
use std::path::PathBuf;
|
||||
|
||||
// Debug-only test hook: lets integration tests point the server at a temporary
|
||||
// managed config file without writing to /etc.
|
||||
const MANAGED_CONFIG_PATH_ENV_VAR: &str = "CODEX_APP_SERVER_MANAGED_CONFIG_PATH";
|
||||
|
||||
fn main() -> anyhow::Result<()> {
|
||||
arg0_dispatch_or_else(|codex_linux_sandbox_exe| async move {
|
||||
let managed_config_path = managed_config_path_from_debug_env();
|
||||
let loader_overrides = LoaderOverrides {
|
||||
managed_config_path,
|
||||
..Default::default()
|
||||
};
|
||||
|
||||
run_main(
|
||||
codex_linux_sandbox_exe,
|
||||
CliConfigOverrides::default(),
|
||||
loader_overrides,
|
||||
)
|
||||
.await?;
|
||||
run_main(codex_linux_sandbox_exe, CliConfigOverrides::default()).await?;
|
||||
Ok(())
|
||||
})
|
||||
}
|
||||
|
||||
fn managed_config_path_from_debug_env() -> Option<PathBuf> {
|
||||
#[cfg(debug_assertions)]
|
||||
{
|
||||
if let Ok(value) = std::env::var(MANAGED_CONFIG_PATH_ENV_VAR) {
|
||||
return if value.is_empty() {
|
||||
None
|
||||
} else {
|
||||
Some(PathBuf::from(value))
|
||||
};
|
||||
}
|
||||
}
|
||||
|
||||
None
|
||||
}
|
||||
|
||||
@@ -18,9 +18,8 @@ use codex_app_server_protocol::JSONRPCRequest;
|
||||
use codex_app_server_protocol::JSONRPCResponse;
|
||||
use codex_app_server_protocol::RequestId;
|
||||
use codex_core::AuthManager;
|
||||
use codex_core::ThreadManager;
|
||||
use codex_core::ConversationManager;
|
||||
use codex_core::config::Config;
|
||||
use codex_core::config_loader::LoaderOverrides;
|
||||
use codex_core::default_client::USER_AGENT_SUFFIX;
|
||||
use codex_core::default_client::get_codex_user_agent;
|
||||
use codex_feedback::CodexFeedback;
|
||||
@@ -42,7 +41,6 @@ impl MessageProcessor {
|
||||
codex_linux_sandbox_exe: Option<PathBuf>,
|
||||
config: Arc<Config>,
|
||||
cli_overrides: Vec<(String, TomlValue)>,
|
||||
loader_overrides: LoaderOverrides,
|
||||
feedback: CodexFeedback,
|
||||
) -> Self {
|
||||
let outgoing = Arc::new(outgoing);
|
||||
@@ -51,21 +49,20 @@ impl MessageProcessor {
|
||||
false,
|
||||
config.cli_auth_credentials_store_mode,
|
||||
);
|
||||
let thread_manager = Arc::new(ThreadManager::new(
|
||||
config.codex_home.clone(),
|
||||
let conversation_manager = Arc::new(ConversationManager::new(
|
||||
auth_manager.clone(),
|
||||
SessionSource::VSCode,
|
||||
));
|
||||
let codex_message_processor = CodexMessageProcessor::new(
|
||||
auth_manager,
|
||||
thread_manager,
|
||||
conversation_manager,
|
||||
outgoing.clone(),
|
||||
codex_linux_sandbox_exe,
|
||||
Arc::clone(&config),
|
||||
cli_overrides.clone(),
|
||||
feedback,
|
||||
);
|
||||
let config_api = ConfigApi::new(config.codex_home.clone(), cli_overrides, loader_overrides);
|
||||
let config_api = ConfigApi::new(config.codex_home.clone(), cli_overrides);
|
||||
|
||||
Self {
|
||||
outgoing,
|
||||
@@ -158,12 +155,6 @@ impl MessageProcessor {
|
||||
ClientRequest::ConfigBatchWrite { request_id, params } => {
|
||||
self.handle_config_batch_write(request_id, params).await;
|
||||
}
|
||||
ClientRequest::ConfigRequirementsRead {
|
||||
request_id,
|
||||
params: _,
|
||||
} => {
|
||||
self.handle_config_requirements_read(request_id).await;
|
||||
}
|
||||
other => {
|
||||
self.codex_message_processor.process_request(other).await;
|
||||
}
|
||||
@@ -216,11 +207,4 @@ impl MessageProcessor {
|
||||
Err(error) => self.outgoing.send_error(request_id, error).await,
|
||||
}
|
||||
}
|
||||
|
||||
async fn handle_config_requirements_read(&self, request_id: RequestId) {
|
||||
match self.config_api.config_requirements_read().await {
|
||||
Ok(response) => self.outgoing.send_response(request_id, response).await,
|
||||
Err(error) => self.outgoing.send_error(request_id, error).await,
|
||||
}
|
||||
}
|
||||
}
|
||||
|
||||
@@ -2,17 +2,19 @@ use std::sync::Arc;
|
||||
|
||||
use codex_app_server_protocol::Model;
|
||||
use codex_app_server_protocol::ReasoningEffortOption;
|
||||
use codex_core::ThreadManager;
|
||||
use codex_core::ConversationManager;
|
||||
use codex_core::config::Config;
|
||||
use codex_protocol::openai_models::ModelPreset;
|
||||
use codex_protocol::openai_models::ReasoningEffortPreset;
|
||||
|
||||
pub async fn supported_models(thread_manager: Arc<ThreadManager>, config: &Config) -> Vec<Model> {
|
||||
thread_manager
|
||||
pub async fn supported_models(
|
||||
conversation_manager: Arc<ConversationManager>,
|
||||
config: &Config,
|
||||
) -> Vec<Model> {
|
||||
conversation_manager
|
||||
.list_models(config)
|
||||
.await
|
||||
.into_iter()
|
||||
.filter(|preset| preset.show_in_picker)
|
||||
.map(model_from_preset)
|
||||
.collect()
|
||||
}
|
||||
|
||||
@@ -18,9 +18,8 @@ pub use core_test_support::test_path_buf_with_windows;
|
||||
pub use core_test_support::test_tmp_path;
|
||||
pub use core_test_support::test_tmp_path_buf;
|
||||
pub use mcp_process::McpProcess;
|
||||
pub use mock_model_server::create_mock_responses_server_repeating_assistant;
|
||||
pub use mock_model_server::create_mock_responses_server_sequence;
|
||||
pub use mock_model_server::create_mock_responses_server_sequence_unchecked;
|
||||
pub use mock_model_server::create_mock_chat_completions_server;
|
||||
pub use mock_model_server::create_mock_chat_completions_server_unchecked;
|
||||
pub use models_cache::write_models_cache;
|
||||
pub use models_cache::write_models_cache_with_models;
|
||||
pub use responses::create_apply_patch_sse_response;
|
||||
|
||||
@@ -21,7 +21,6 @@ use codex_app_server_protocol::ConfigBatchWriteParams;
|
||||
use codex_app_server_protocol::ConfigReadParams;
|
||||
use codex_app_server_protocol::ConfigValueWriteParams;
|
||||
use codex_app_server_protocol::FeedbackUploadParams;
|
||||
use codex_app_server_protocol::ForkConversationParams;
|
||||
use codex_app_server_protocol::GetAccountParams;
|
||||
use codex_app_server_protocol::GetAuthStatusParams;
|
||||
use codex_app_server_protocol::InitializeParams;
|
||||
@@ -44,11 +43,8 @@ use codex_app_server_protocol::SendUserTurnParams;
|
||||
use codex_app_server_protocol::ServerRequest;
|
||||
use codex_app_server_protocol::SetDefaultModelParams;
|
||||
use codex_app_server_protocol::ThreadArchiveParams;
|
||||
use codex_app_server_protocol::ThreadForkParams;
|
||||
use codex_app_server_protocol::ThreadListParams;
|
||||
use codex_app_server_protocol::ThreadLoadedListParams;
|
||||
use codex_app_server_protocol::ThreadResumeParams;
|
||||
use codex_app_server_protocol::ThreadRollbackParams;
|
||||
use codex_app_server_protocol::ThreadStartParams;
|
||||
use codex_app_server_protocol::TurnInterruptParams;
|
||||
use codex_app_server_protocol::TurnStartParams;
|
||||
@@ -63,7 +59,7 @@ pub struct McpProcess {
|
||||
process: Child,
|
||||
stdin: ChildStdin,
|
||||
stdout: BufReader<ChildStdout>,
|
||||
pending_messages: VecDeque<JSONRPCMessage>,
|
||||
pending_user_messages: VecDeque<JSONRPCNotification>,
|
||||
}
|
||||
|
||||
impl McpProcess {
|
||||
@@ -130,7 +126,7 @@ impl McpProcess {
|
||||
process,
|
||||
stdin,
|
||||
stdout,
|
||||
pending_messages: VecDeque::new(),
|
||||
pending_user_messages: VecDeque::new(),
|
||||
})
|
||||
}
|
||||
|
||||
@@ -201,7 +197,7 @@ impl McpProcess {
|
||||
}
|
||||
|
||||
/// Send a `removeConversationListener` JSON-RPC request.
|
||||
pub async fn send_remove_thread_listener_request(
|
||||
pub async fn send_remove_conversation_listener_request(
|
||||
&mut self,
|
||||
params: RemoveConversationListenerParams,
|
||||
) -> anyhow::Result<i64> {
|
||||
@@ -311,15 +307,6 @@ impl McpProcess {
|
||||
self.send_request("thread/resume", params).await
|
||||
}
|
||||
|
||||
/// Send a `thread/fork` JSON-RPC request.
|
||||
pub async fn send_thread_fork_request(
|
||||
&mut self,
|
||||
params: ThreadForkParams,
|
||||
) -> anyhow::Result<i64> {
|
||||
let params = Some(serde_json::to_value(params)?);
|
||||
self.send_request("thread/fork", params).await
|
||||
}
|
||||
|
||||
/// Send a `thread/archive` JSON-RPC request.
|
||||
pub async fn send_thread_archive_request(
|
||||
&mut self,
|
||||
@@ -329,15 +316,6 @@ impl McpProcess {
|
||||
self.send_request("thread/archive", params).await
|
||||
}
|
||||
|
||||
/// Send a `thread/rollback` JSON-RPC request.
|
||||
pub async fn send_thread_rollback_request(
|
||||
&mut self,
|
||||
params: ThreadRollbackParams,
|
||||
) -> anyhow::Result<i64> {
|
||||
let params = Some(serde_json::to_value(params)?);
|
||||
self.send_request("thread/rollback", params).await
|
||||
}
|
||||
|
||||
/// Send a `thread/list` JSON-RPC request.
|
||||
pub async fn send_thread_list_request(
|
||||
&mut self,
|
||||
@@ -347,15 +325,6 @@ impl McpProcess {
|
||||
self.send_request("thread/list", params).await
|
||||
}
|
||||
|
||||
/// Send a `thread/loaded/list` JSON-RPC request.
|
||||
pub async fn send_thread_loaded_list_request(
|
||||
&mut self,
|
||||
params: ThreadLoadedListParams,
|
||||
) -> anyhow::Result<i64> {
|
||||
let params = Some(serde_json::to_value(params)?);
|
||||
self.send_request("thread/loaded/list", params).await
|
||||
}
|
||||
|
||||
/// Send a `model/list` JSON-RPC request.
|
||||
pub async fn send_list_models_request(
|
||||
&mut self,
|
||||
@@ -374,15 +343,6 @@ impl McpProcess {
|
||||
self.send_request("resumeConversation", params).await
|
||||
}
|
||||
|
||||
/// Send a `forkConversation` JSON-RPC request.
|
||||
pub async fn send_fork_conversation_request(
|
||||
&mut self,
|
||||
params: ForkConversationParams,
|
||||
) -> anyhow::Result<i64> {
|
||||
let params = Some(serde_json::to_value(params)?);
|
||||
self.send_request("forkConversation", params).await
|
||||
}
|
||||
|
||||
/// Send a `loginApiKey` JSON-RPC request.
|
||||
pub async fn send_login_api_key_request(
|
||||
&mut self,
|
||||
@@ -574,16 +534,27 @@ impl McpProcess {
|
||||
pub async fn read_stream_until_request_message(&mut self) -> anyhow::Result<ServerRequest> {
|
||||
eprintln!("in read_stream_until_request_message()");
|
||||
|
||||
let message = self
|
||||
.read_stream_until_message(|message| matches!(message, JSONRPCMessage::Request(_)))
|
||||
.await?;
|
||||
loop {
|
||||
let message = self.read_jsonrpc_message().await?;
|
||||
|
||||
let JSONRPCMessage::Request(jsonrpc_request) = message else {
|
||||
unreachable!("expected JSONRPCMessage::Request, got {message:?}");
|
||||
};
|
||||
jsonrpc_request
|
||||
.try_into()
|
||||
.with_context(|| "failed to deserialize ServerRequest from JSONRPCRequest")
|
||||
match message {
|
||||
JSONRPCMessage::Notification(notification) => {
|
||||
eprintln!("notification: {notification:?}");
|
||||
self.enqueue_user_message(notification);
|
||||
}
|
||||
JSONRPCMessage::Request(jsonrpc_request) => {
|
||||
return jsonrpc_request.try_into().with_context(
|
||||
|| "failed to deserialize ServerRequest from JSONRPCRequest",
|
||||
);
|
||||
}
|
||||
JSONRPCMessage::Error(_) => {
|
||||
anyhow::bail!("unexpected JSONRPCMessage::Error: {message:?}");
|
||||
}
|
||||
JSONRPCMessage::Response(_) => {
|
||||
anyhow::bail!("unexpected JSONRPCMessage::Response: {message:?}");
|
||||
}
|
||||
}
|
||||
}
|
||||
}
|
||||
|
||||
pub async fn read_stream_until_response_message(
|
||||
@@ -592,32 +563,52 @@ impl McpProcess {
|
||||
) -> anyhow::Result<JSONRPCResponse> {
|
||||
eprintln!("in read_stream_until_response_message({request_id:?})");
|
||||
|
||||
let message = self
|
||||
.read_stream_until_message(|message| {
|
||||
Self::message_request_id(message) == Some(&request_id)
|
||||
})
|
||||
.await?;
|
||||
|
||||
let JSONRPCMessage::Response(response) = message else {
|
||||
unreachable!("expected JSONRPCMessage::Response, got {message:?}");
|
||||
};
|
||||
Ok(response)
|
||||
loop {
|
||||
let message = self.read_jsonrpc_message().await?;
|
||||
match message {
|
||||
JSONRPCMessage::Notification(notification) => {
|
||||
eprintln!("notification: {notification:?}");
|
||||
self.enqueue_user_message(notification);
|
||||
}
|
||||
JSONRPCMessage::Request(_) => {
|
||||
anyhow::bail!("unexpected JSONRPCMessage::Request: {message:?}");
|
||||
}
|
||||
JSONRPCMessage::Error(_) => {
|
||||
anyhow::bail!("unexpected JSONRPCMessage::Error: {message:?}");
|
||||
}
|
||||
JSONRPCMessage::Response(jsonrpc_response) => {
|
||||
if jsonrpc_response.id == request_id {
|
||||
return Ok(jsonrpc_response);
|
||||
}
|
||||
}
|
||||
}
|
||||
}
|
||||
}
|
||||
|
||||
pub async fn read_stream_until_error_message(
|
||||
&mut self,
|
||||
request_id: RequestId,
|
||||
) -> anyhow::Result<JSONRPCError> {
|
||||
let message = self
|
||||
.read_stream_until_message(|message| {
|
||||
Self::message_request_id(message) == Some(&request_id)
|
||||
})
|
||||
.await?;
|
||||
|
||||
let JSONRPCMessage::Error(err) = message else {
|
||||
unreachable!("expected JSONRPCMessage::Error, got {message:?}");
|
||||
};
|
||||
Ok(err)
|
||||
loop {
|
||||
let message = self.read_jsonrpc_message().await?;
|
||||
match message {
|
||||
JSONRPCMessage::Notification(notification) => {
|
||||
eprintln!("notification: {notification:?}");
|
||||
self.enqueue_user_message(notification);
|
||||
}
|
||||
JSONRPCMessage::Request(_) => {
|
||||
anyhow::bail!("unexpected JSONRPCMessage::Request: {message:?}");
|
||||
}
|
||||
JSONRPCMessage::Response(_) => {
|
||||
// Keep scanning; we're waiting for an error with matching id.
|
||||
}
|
||||
JSONRPCMessage::Error(err) => {
|
||||
if err.id == request_id {
|
||||
return Ok(err);
|
||||
}
|
||||
}
|
||||
}
|
||||
}
|
||||
}
|
||||
|
||||
pub async fn read_stream_until_notification_message(
|
||||
@@ -626,64 +617,46 @@ impl McpProcess {
|
||||
) -> anyhow::Result<JSONRPCNotification> {
|
||||
eprintln!("in read_stream_until_notification_message({method})");
|
||||
|
||||
let message = self
|
||||
.read_stream_until_message(|message| {
|
||||
matches!(
|
||||
message,
|
||||
JSONRPCMessage::Notification(notification) if notification.method == method
|
||||
)
|
||||
})
|
||||
.await?;
|
||||
|
||||
let JSONRPCMessage::Notification(notification) = message else {
|
||||
unreachable!("expected JSONRPCMessage::Notification, got {message:?}");
|
||||
};
|
||||
Ok(notification)
|
||||
}
|
||||
|
||||
/// Clears any buffered messages so future reads only consider new stream items.
|
||||
///
|
||||
/// We call this when e.g. we want to validate against the next turn and no longer care about
|
||||
/// messages buffered from the prior turn.
|
||||
pub fn clear_message_buffer(&mut self) {
|
||||
self.pending_messages.clear();
|
||||
}
|
||||
|
||||
/// Reads the stream until a message matches `predicate`, buffering any non-matching messages
|
||||
/// for later reads.
|
||||
async fn read_stream_until_message<F>(&mut self, predicate: F) -> anyhow::Result<JSONRPCMessage>
|
||||
where
|
||||
F: Fn(&JSONRPCMessage) -> bool,
|
||||
{
|
||||
if let Some(message) = self.take_pending_message(&predicate) {
|
||||
return Ok(message);
|
||||
if let Some(notification) = self.take_pending_notification_by_method(method) {
|
||||
return Ok(notification);
|
||||
}
|
||||
|
||||
loop {
|
||||
let message = self.read_jsonrpc_message().await?;
|
||||
if predicate(&message) {
|
||||
return Ok(message);
|
||||
match message {
|
||||
JSONRPCMessage::Notification(notification) => {
|
||||
if notification.method == method {
|
||||
return Ok(notification);
|
||||
}
|
||||
self.enqueue_user_message(notification);
|
||||
}
|
||||
JSONRPCMessage::Request(_) => {
|
||||
anyhow::bail!("unexpected JSONRPCMessage::Request: {message:?}");
|
||||
}
|
||||
JSONRPCMessage::Error(_) => {
|
||||
anyhow::bail!("unexpected JSONRPCMessage::Error: {message:?}");
|
||||
}
|
||||
JSONRPCMessage::Response(_) => {
|
||||
anyhow::bail!("unexpected JSONRPCMessage::Response: {message:?}");
|
||||
}
|
||||
}
|
||||
self.pending_messages.push_back(message);
|
||||
}
|
||||
}
|
||||
|
||||
fn take_pending_message<F>(&mut self, predicate: &F) -> Option<JSONRPCMessage>
|
||||
where
|
||||
F: Fn(&JSONRPCMessage) -> bool,
|
||||
{
|
||||
if let Some(pos) = self.pending_messages.iter().position(predicate) {
|
||||
return self.pending_messages.remove(pos);
|
||||
fn take_pending_notification_by_method(&mut self, method: &str) -> Option<JSONRPCNotification> {
|
||||
if let Some(pos) = self
|
||||
.pending_user_messages
|
||||
.iter()
|
||||
.position(|notification| notification.method == method)
|
||||
{
|
||||
return self.pending_user_messages.remove(pos);
|
||||
}
|
||||
None
|
||||
}
|
||||
|
||||
fn message_request_id(message: &JSONRPCMessage) -> Option<&RequestId> {
|
||||
match message {
|
||||
JSONRPCMessage::Request(request) => Some(&request.id),
|
||||
JSONRPCMessage::Response(response) => Some(&response.id),
|
||||
JSONRPCMessage::Error(err) => Some(&err.id),
|
||||
JSONRPCMessage::Notification(_) => None,
|
||||
fn enqueue_user_message(&mut self, notification: JSONRPCNotification) {
|
||||
if notification.method == "codex/event/user_message" {
|
||||
self.pending_user_messages.push_back(notification);
|
||||
}
|
||||
}
|
||||
}
|
||||
|
||||
@@ -1,18 +1,17 @@
|
||||
use std::sync::atomic::AtomicUsize;
|
||||
use std::sync::atomic::Ordering;
|
||||
|
||||
use core_test_support::responses;
|
||||
use wiremock::Mock;
|
||||
use wiremock::MockServer;
|
||||
use wiremock::Respond;
|
||||
use wiremock::ResponseTemplate;
|
||||
use wiremock::matchers::method;
|
||||
use wiremock::matchers::path_regex;
|
||||
use wiremock::matchers::path;
|
||||
|
||||
/// Create a mock server that will provide the responses, in order, for
|
||||
/// requests to the `/v1/responses` endpoint.
|
||||
pub async fn create_mock_responses_server_sequence(responses: Vec<String>) -> MockServer {
|
||||
let server = responses::start_mock_server().await;
|
||||
/// requests to the `/v1/chat/completions` endpoint.
|
||||
pub async fn create_mock_chat_completions_server(responses: Vec<String>) -> MockServer {
|
||||
let server = MockServer::start().await;
|
||||
|
||||
let num_calls = responses.len();
|
||||
let seq_responder = SeqResponder {
|
||||
@@ -21,7 +20,7 @@ pub async fn create_mock_responses_server_sequence(responses: Vec<String>) -> Mo
|
||||
};
|
||||
|
||||
Mock::given(method("POST"))
|
||||
.and(path_regex(".*/responses$"))
|
||||
.and(path("/v1/chat/completions"))
|
||||
.respond_with(seq_responder)
|
||||
.expect(num_calls as u64)
|
||||
.mount(&server)
|
||||
@@ -30,10 +29,10 @@ pub async fn create_mock_responses_server_sequence(responses: Vec<String>) -> Mo
|
||||
server
|
||||
}
|
||||
|
||||
/// Same as `create_mock_responses_server_sequence` but does not enforce an
|
||||
/// Same as `create_mock_chat_completions_server` but does not enforce an
|
||||
/// expectation on the number of calls.
|
||||
pub async fn create_mock_responses_server_sequence_unchecked(responses: Vec<String>) -> MockServer {
|
||||
let server = responses::start_mock_server().await;
|
||||
pub async fn create_mock_chat_completions_server_unchecked(responses: Vec<String>) -> MockServer {
|
||||
let server = MockServer::start().await;
|
||||
|
||||
let seq_responder = SeqResponder {
|
||||
num_calls: AtomicUsize::new(0),
|
||||
@@ -41,7 +40,7 @@ pub async fn create_mock_responses_server_sequence_unchecked(responses: Vec<Stri
|
||||
};
|
||||
|
||||
Mock::given(method("POST"))
|
||||
.and(path_regex(".*/responses$"))
|
||||
.and(path("/v1/chat/completions"))
|
||||
.respond_with(seq_responder)
|
||||
.mount(&server)
|
||||
.await;
|
||||
@@ -58,24 +57,10 @@ impl Respond for SeqResponder {
|
||||
fn respond(&self, _: &wiremock::Request) -> ResponseTemplate {
|
||||
let call_num = self.num_calls.fetch_add(1, Ordering::SeqCst);
|
||||
match self.responses.get(call_num) {
|
||||
Some(response) => responses::sse_response(response.clone()),
|
||||
Some(response) => ResponseTemplate::new(200)
|
||||
.insert_header("content-type", "text/event-stream")
|
||||
.set_body_raw(response.clone(), "text/event-stream"),
|
||||
None => panic!("no response for {call_num}"),
|
||||
}
|
||||
}
|
||||
}
|
||||
|
||||
/// Create a mock responses API server that returns the same assistant message for every request.
|
||||
pub async fn create_mock_responses_server_repeating_assistant(message: &str) -> MockServer {
|
||||
let server = responses::start_mock_server().await;
|
||||
let body = responses::sse(vec![
|
||||
responses::ev_response_created("resp-1"),
|
||||
responses::ev_assistant_message("msg-1", message),
|
||||
responses::ev_completed("resp-1"),
|
||||
]);
|
||||
Mock::given(method("POST"))
|
||||
.and(path_regex(".*/responses$"))
|
||||
.respond_with(responses::sse_response(body))
|
||||
.mount(&server)
|
||||
.await;
|
||||
server
|
||||
}
|
||||
|
||||
@@ -15,7 +15,7 @@ fn preset_to_info(preset: &ModelPreset, priority: i32) -> ModelInfo {
|
||||
slug: preset.id.clone(),
|
||||
display_name: preset.display_name.clone(),
|
||||
description: Some(preset.description.clone()),
|
||||
default_reasoning_level: Some(preset.default_reasoning_effort),
|
||||
default_reasoning_level: preset.default_reasoning_effort,
|
||||
supported_reasoning_levels: preset.supported_reasoning_efforts.clone(),
|
||||
shell_type: ConfigShellToolType::ShellCommand,
|
||||
visibility: if preset.show_in_picker {
|
||||
@@ -26,20 +26,19 @@ fn preset_to_info(preset: &ModelPreset, priority: i32) -> ModelInfo {
|
||||
supported_in_api: true,
|
||||
priority,
|
||||
upgrade: preset.upgrade.as_ref().map(|u| u.id.clone()),
|
||||
base_instructions: "base instructions".to_string(),
|
||||
base_instructions: None,
|
||||
supports_reasoning_summaries: false,
|
||||
support_verbosity: false,
|
||||
default_verbosity: None,
|
||||
apply_patch_tool_type: None,
|
||||
truncation_policy: TruncationPolicyConfig::bytes(10_000),
|
||||
supports_parallel_tool_calls: false,
|
||||
context_window: Some(272_000),
|
||||
auto_compact_token_limit: None,
|
||||
effective_context_window_percent: 95,
|
||||
context_window: None,
|
||||
experimental_supported_tools: Vec::new(),
|
||||
}
|
||||
}
|
||||
|
||||
// todo(aibrahim): fix the priorities to be the opposite here.
|
||||
/// Write a models_cache.json file to the codex home directory.
|
||||
/// This prevents ModelsManager from making network requests to refresh models.
|
||||
/// The cache will be treated as fresh (within TTL) and used instead of fetching from the network.
|
||||
@@ -50,14 +49,14 @@ pub fn write_models_cache(codex_home: &Path) -> std::io::Result<()> {
|
||||
.iter()
|
||||
.filter(|preset| preset.show_in_picker)
|
||||
.collect();
|
||||
// Convert presets to ModelInfo, assigning priorities (lower = earlier in list).
|
||||
// Priority is used for sorting, so the first model gets the lowest priority.
|
||||
// Convert presets to ModelInfo, assigning priorities (higher = earlier in list)
|
||||
// Priority is used for sorting, so first model gets highest priority
|
||||
let models: Vec<ModelInfo> = presets
|
||||
.iter()
|
||||
.enumerate()
|
||||
.map(|(idx, preset)| {
|
||||
// Lower priority = earlier in list.
|
||||
let priority = idx as i32;
|
||||
// Higher priority = earlier in list, so reverse the index
|
||||
let priority = (presets.len() - idx) as i32;
|
||||
preset_to_info(preset, priority)
|
||||
})
|
||||
.collect();
|
||||
|
||||
@@ -1,4 +1,3 @@
|
||||
use core_test_support::responses;
|
||||
use serde_json::json;
|
||||
use std::path::Path;
|
||||
|
||||
@@ -15,30 +14,85 @@ pub fn create_shell_command_sse_response(
|
||||
"workdir": workdir.map(|w| w.to_string_lossy()),
|
||||
"timeout_ms": timeout_ms
|
||||
}))?;
|
||||
Ok(responses::sse(vec![
|
||||
responses::ev_response_created("resp-1"),
|
||||
responses::ev_function_call(call_id, "shell_command", &tool_call_arguments),
|
||||
responses::ev_completed("resp-1"),
|
||||
]))
|
||||
let tool_call = json!({
|
||||
"choices": [
|
||||
{
|
||||
"delta": {
|
||||
"tool_calls": [
|
||||
{
|
||||
"id": call_id,
|
||||
"function": {
|
||||
"name": "shell_command",
|
||||
"arguments": tool_call_arguments
|
||||
}
|
||||
}
|
||||
]
|
||||
},
|
||||
"finish_reason": "tool_calls"
|
||||
}
|
||||
]
|
||||
});
|
||||
|
||||
let sse = format!(
|
||||
"data: {}\n\ndata: DONE\n\n",
|
||||
serde_json::to_string(&tool_call)?
|
||||
);
|
||||
Ok(sse)
|
||||
}
|
||||
|
||||
pub fn create_final_assistant_message_sse_response(message: &str) -> anyhow::Result<String> {
|
||||
Ok(responses::sse(vec![
|
||||
responses::ev_response_created("resp-1"),
|
||||
responses::ev_assistant_message("msg-1", message),
|
||||
responses::ev_completed("resp-1"),
|
||||
]))
|
||||
let assistant_message = json!({
|
||||
"choices": [
|
||||
{
|
||||
"delta": {
|
||||
"content": message
|
||||
},
|
||||
"finish_reason": "stop"
|
||||
}
|
||||
]
|
||||
});
|
||||
|
||||
let sse = format!(
|
||||
"data: {}\n\ndata: DONE\n\n",
|
||||
serde_json::to_string(&assistant_message)?
|
||||
);
|
||||
Ok(sse)
|
||||
}
|
||||
|
||||
pub fn create_apply_patch_sse_response(
|
||||
patch_content: &str,
|
||||
call_id: &str,
|
||||
) -> anyhow::Result<String> {
|
||||
Ok(responses::sse(vec![
|
||||
responses::ev_response_created("resp-1"),
|
||||
responses::ev_apply_patch_shell_command_call_via_heredoc(call_id, patch_content),
|
||||
responses::ev_completed("resp-1"),
|
||||
]))
|
||||
// Use shell_command to call apply_patch with heredoc format
|
||||
let command = format!("apply_patch <<'EOF'\n{patch_content}\nEOF");
|
||||
let tool_call_arguments = serde_json::to_string(&json!({
|
||||
"command": command
|
||||
}))?;
|
||||
|
||||
let tool_call = json!({
|
||||
"choices": [
|
||||
{
|
||||
"delta": {
|
||||
"tool_calls": [
|
||||
{
|
||||
"id": call_id,
|
||||
"function": {
|
||||
"name": "shell_command",
|
||||
"arguments": tool_call_arguments
|
||||
}
|
||||
}
|
||||
]
|
||||
},
|
||||
"finish_reason": "tool_calls"
|
||||
}
|
||||
]
|
||||
});
|
||||
|
||||
let sse = format!(
|
||||
"data: {}\n\ndata: DONE\n\n",
|
||||
serde_json::to_string(&tool_call)?
|
||||
);
|
||||
Ok(sse)
|
||||
}
|
||||
|
||||
pub fn create_exec_command_sse_response(call_id: &str) -> anyhow::Result<String> {
|
||||
@@ -54,9 +108,28 @@ pub fn create_exec_command_sse_response(call_id: &str) -> anyhow::Result<String>
|
||||
"cmd": command.join(" "),
|
||||
"yield_time_ms": 500
|
||||
}))?;
|
||||
Ok(responses::sse(vec![
|
||||
responses::ev_response_created("resp-1"),
|
||||
responses::ev_function_call(call_id, "exec_command", &tool_call_arguments),
|
||||
responses::ev_completed("resp-1"),
|
||||
]))
|
||||
let tool_call = json!({
|
||||
"choices": [
|
||||
{
|
||||
"delta": {
|
||||
"tool_calls": [
|
||||
{
|
||||
"id": call_id,
|
||||
"function": {
|
||||
"name": "exec_command",
|
||||
"arguments": tool_call_arguments
|
||||
}
|
||||
}
|
||||
]
|
||||
},
|
||||
"finish_reason": "tool_calls"
|
||||
}
|
||||
]
|
||||
});
|
||||
|
||||
let sse = format!(
|
||||
"data: {}\n\ndata: DONE\n\n",
|
||||
serde_json::to_string(&tool_call)?
|
||||
);
|
||||
Ok(sse)
|
||||
}
|
||||
|
||||
@@ -1,5 +1,5 @@
|
||||
use anyhow::Result;
|
||||
use codex_protocol::ThreadId;
|
||||
use codex_protocol::ConversationId;
|
||||
use codex_protocol::protocol::GitInfo;
|
||||
use codex_protocol::protocol::SessionMeta;
|
||||
use codex_protocol::protocol::SessionMetaLine;
|
||||
@@ -28,7 +28,7 @@ pub fn create_fake_rollout(
|
||||
) -> Result<String> {
|
||||
let uuid = Uuid::new_v4();
|
||||
let uuid_str = uuid.to_string();
|
||||
let conversation_id = ThreadId::from_string(&uuid_str)?;
|
||||
let conversation_id = ConversationId::from_string(&uuid_str)?;
|
||||
|
||||
// sessions/YYYY/MM/DD derived from filename_ts (YYYY-MM-DDThh-mm-ss)
|
||||
let year = &filename_ts[0..4];
|
||||
|
||||
@@ -37,7 +37,7 @@ model_provider = "mock_provider"
|
||||
[model_providers.mock_provider]
|
||||
name = "Mock provider for test"
|
||||
base_url = "http://127.0.0.1:0/v1"
|
||||
wire_api = "responses"
|
||||
wire_api = "chat"
|
||||
request_max_retries = 0
|
||||
stream_max_retries = 0
|
||||
{requires_line}
|
||||
|
||||
@@ -1,7 +1,7 @@
|
||||
use anyhow::Result;
|
||||
use app_test_support::McpProcess;
|
||||
use app_test_support::create_final_assistant_message_sse_response;
|
||||
use app_test_support::create_mock_responses_server_sequence;
|
||||
use app_test_support::create_mock_chat_completions_server;
|
||||
use app_test_support::create_shell_command_sse_response;
|
||||
use app_test_support::format_with_current_shell;
|
||||
use app_test_support::to_response;
|
||||
@@ -65,7 +65,7 @@ async fn test_codex_jsonrpc_conversation_flow() -> Result<()> {
|
||||
)?,
|
||||
create_final_assistant_message_sse_response("Enjoy your new git repo!")?,
|
||||
];
|
||||
let server = create_mock_responses_server_sequence(responses).await;
|
||||
let server = create_mock_chat_completions_server(responses).await;
|
||||
create_config_toml(&codex_home, &server.uri())?;
|
||||
|
||||
// Start MCP server and initialize.
|
||||
@@ -145,7 +145,9 @@ async fn test_codex_jsonrpc_conversation_flow() -> Result<()> {
|
||||
|
||||
// 4) removeConversationListener
|
||||
let remove_listener_id = mcp
|
||||
.send_remove_thread_listener_request(RemoveConversationListenerParams { subscription_id })
|
||||
.send_remove_conversation_listener_request(RemoveConversationListenerParams {
|
||||
subscription_id,
|
||||
})
|
||||
.await?;
|
||||
let remove_listener_resp: JSONRPCResponse = timeout(
|
||||
DEFAULT_READ_TIMEOUT,
|
||||
@@ -197,7 +199,7 @@ async fn test_send_user_turn_changes_approval_policy_behavior() -> Result<()> {
|
||||
)?,
|
||||
create_final_assistant_message_sse_response("done 2")?,
|
||||
];
|
||||
let server = create_mock_responses_server_sequence(responses).await;
|
||||
let server = create_mock_chat_completions_server(responses).await;
|
||||
create_config_toml(&codex_home, &server.uri())?;
|
||||
|
||||
// Start MCP server and initialize.
|
||||
@@ -363,7 +365,7 @@ async fn test_send_user_turn_updates_sandbox_and_cwd_between_turns() -> Result<(
|
||||
)?,
|
||||
create_final_assistant_message_sse_response("done second")?,
|
||||
];
|
||||
let server = create_mock_responses_server_sequence(responses).await;
|
||||
let server = create_mock_chat_completions_server(responses).await;
|
||||
create_config_toml(&codex_home, &server.uri())?;
|
||||
|
||||
let mut mcp = McpProcess::new(&codex_home).await?;
|
||||
@@ -430,7 +432,6 @@ async fn test_send_user_turn_updates_sandbox_and_cwd_between_turns() -> Result<(
|
||||
mcp.read_stream_until_notification_message("codex/event/task_complete"),
|
||||
)
|
||||
.await??;
|
||||
mcp.clear_message_buffer();
|
||||
|
||||
let second_turn_id = mcp
|
||||
.send_send_user_turn_request(SendUserTurnParams {
|
||||
@@ -500,7 +501,7 @@ model_provider = "mock_provider"
|
||||
[model_providers.mock_provider]
|
||||
name = "Mock provider for test"
|
||||
base_url = "{server_uri}/v1"
|
||||
wire_api = "responses"
|
||||
wire_api = "chat"
|
||||
request_max_retries = 0
|
||||
stream_max_retries = 0
|
||||
"#
|
||||
|
||||
@@ -1,6 +1,7 @@
|
||||
use anyhow::Result;
|
||||
use app_test_support::McpProcess;
|
||||
use app_test_support::create_final_assistant_message_sse_response;
|
||||
use app_test_support::create_mock_chat_completions_server;
|
||||
use app_test_support::to_response;
|
||||
use codex_app_server_protocol::AddConversationListenerParams;
|
||||
use codex_app_server_protocol::AddConversationSubscriptionResponse;
|
||||
@@ -11,7 +12,6 @@ use codex_app_server_protocol::NewConversationResponse;
|
||||
use codex_app_server_protocol::RequestId;
|
||||
use codex_app_server_protocol::SendUserMessageParams;
|
||||
use codex_app_server_protocol::SendUserMessageResponse;
|
||||
use core_test_support::responses;
|
||||
use pretty_assertions::assert_eq;
|
||||
use serde_json::json;
|
||||
use std::path::Path;
|
||||
@@ -23,9 +23,8 @@ const DEFAULT_READ_TIMEOUT: std::time::Duration = std::time::Duration::from_secs
|
||||
#[tokio::test(flavor = "multi_thread", worker_threads = 2)]
|
||||
async fn test_conversation_create_and_send_message_ok() -> Result<()> {
|
||||
// Mock server – we won't strictly rely on it, but provide one to satisfy any model wiring.
|
||||
let response_body = create_final_assistant_message_sse_response("Done")?;
|
||||
let server = responses::start_mock_server().await;
|
||||
let response_mock = responses::mount_sse_sequence(&server, vec![response_body]).await;
|
||||
let responses = vec![create_final_assistant_message_sse_response("Done")?];
|
||||
let server = create_mock_chat_completions_server(responses).await;
|
||||
|
||||
// Temporary Codex home with config pointing at the mock server.
|
||||
let codex_home = TempDir::new()?;
|
||||
@@ -87,30 +86,32 @@ async fn test_conversation_create_and_send_message_ok() -> Result<()> {
|
||||
.await??;
|
||||
let _ok: SendUserMessageResponse = to_response::<SendUserMessageResponse>(send_resp)?;
|
||||
|
||||
// Avoid race condition by waiting for the mock server to receive the responses request.
|
||||
// avoid race condition by waiting for the mock server to receive the chat.completions request
|
||||
let deadline = std::time::Instant::now() + DEFAULT_READ_TIMEOUT;
|
||||
let requests = loop {
|
||||
let requests = response_mock.requests();
|
||||
let requests = server.received_requests().await.unwrap_or_default();
|
||||
if !requests.is_empty() {
|
||||
break requests;
|
||||
}
|
||||
if std::time::Instant::now() >= deadline {
|
||||
panic!("mock server did not receive the responses request in time");
|
||||
panic!("mock server did not receive the chat.completions request in time");
|
||||
}
|
||||
tokio::time::sleep(std::time::Duration::from_millis(10)).await;
|
||||
};
|
||||
|
||||
// Verify the outbound request body matches expectations for Responses.
|
||||
// Verify the outbound request body matches expectations for Chat Completions.
|
||||
let request = requests
|
||||
.first()
|
||||
.expect("mock server should have received at least one request");
|
||||
let body = request.body_json();
|
||||
let body = request.body_json::<serde_json::Value>()?;
|
||||
assert_eq!(body["model"], json!("o3"));
|
||||
let user_texts = request.message_input_texts("user");
|
||||
assert!(
|
||||
user_texts.iter().any(|text| text == "Hello"),
|
||||
"expected user input to include Hello, got {user_texts:?}"
|
||||
);
|
||||
assert!(body["stream"].as_bool().unwrap_or(false));
|
||||
let messages = body["messages"]
|
||||
.as_array()
|
||||
.expect("messages should be array");
|
||||
let last = messages.last().expect("at least one message");
|
||||
assert_eq!(last["role"], json!("user"));
|
||||
assert_eq!(last["content"], json!("Hello"));
|
||||
|
||||
drop(server);
|
||||
Ok(())
|
||||
@@ -132,7 +133,7 @@ model_provider = "mock_provider"
|
||||
[model_providers.mock_provider]
|
||||
name = "Mock provider for test"
|
||||
base_url = "{server_uri}/v1"
|
||||
wire_api = "responses"
|
||||
wire_api = "chat"
|
||||
request_max_retries = 0
|
||||
stream_max_retries = 0
|
||||
"#
|
||||
@@ -1,140 +0,0 @@
|
||||
use anyhow::Result;
|
||||
use app_test_support::McpProcess;
|
||||
use app_test_support::create_fake_rollout;
|
||||
use app_test_support::to_response;
|
||||
use codex_app_server_protocol::ForkConversationParams;
|
||||
use codex_app_server_protocol::ForkConversationResponse;
|
||||
use codex_app_server_protocol::JSONRPCNotification;
|
||||
use codex_app_server_protocol::JSONRPCResponse;
|
||||
use codex_app_server_protocol::NewConversationParams; // reused for overrides shape
|
||||
use codex_app_server_protocol::RequestId;
|
||||
use codex_app_server_protocol::ServerNotification;
|
||||
use codex_app_server_protocol::SessionConfiguredNotification;
|
||||
use codex_core::protocol::EventMsg;
|
||||
use pretty_assertions::assert_eq;
|
||||
use tempfile::TempDir;
|
||||
use tokio::time::timeout;
|
||||
|
||||
const DEFAULT_READ_TIMEOUT: std::time::Duration = std::time::Duration::from_secs(10);
|
||||
|
||||
#[tokio::test(flavor = "multi_thread", worker_threads = 2)]
|
||||
async fn fork_conversation_creates_new_rollout() -> Result<()> {
|
||||
let codex_home = TempDir::new()?;
|
||||
|
||||
let preview = "Hello A";
|
||||
let conversation_id = create_fake_rollout(
|
||||
codex_home.path(),
|
||||
"2025-01-02T12-00-00",
|
||||
"2025-01-02T12:00:00Z",
|
||||
preview,
|
||||
Some("openai"),
|
||||
None,
|
||||
)?;
|
||||
|
||||
let original_path = codex_home
|
||||
.path()
|
||||
.join("sessions")
|
||||
.join("2025")
|
||||
.join("01")
|
||||
.join("02")
|
||||
.join(format!(
|
||||
"rollout-2025-01-02T12-00-00-{conversation_id}.jsonl"
|
||||
));
|
||||
assert!(
|
||||
original_path.exists(),
|
||||
"expected original rollout to exist at {}",
|
||||
original_path.display()
|
||||
);
|
||||
let original_contents = std::fs::read_to_string(&original_path)?;
|
||||
|
||||
let mut mcp = McpProcess::new(codex_home.path()).await?;
|
||||
timeout(DEFAULT_READ_TIMEOUT, mcp.initialize()).await??;
|
||||
|
||||
let fork_req_id = mcp
|
||||
.send_fork_conversation_request(ForkConversationParams {
|
||||
path: Some(original_path.clone()),
|
||||
conversation_id: None,
|
||||
overrides: Some(NewConversationParams {
|
||||
model: Some("o3".to_string()),
|
||||
..Default::default()
|
||||
}),
|
||||
})
|
||||
.await?;
|
||||
|
||||
// Expect a sessionConfigured notification for the forked session.
|
||||
let notification: JSONRPCNotification = timeout(
|
||||
DEFAULT_READ_TIMEOUT,
|
||||
mcp.read_stream_until_notification_message("sessionConfigured"),
|
||||
)
|
||||
.await??;
|
||||
let session_configured: ServerNotification = notification.try_into()?;
|
||||
let ServerNotification::SessionConfigured(SessionConfiguredNotification {
|
||||
model,
|
||||
session_id,
|
||||
rollout_path,
|
||||
initial_messages: session_initial_messages,
|
||||
..
|
||||
}) = session_configured
|
||||
else {
|
||||
unreachable!("expected sessionConfigured notification");
|
||||
};
|
||||
|
||||
assert_eq!(model, "o3");
|
||||
assert_ne!(
|
||||
session_id.to_string(),
|
||||
conversation_id,
|
||||
"expected a new conversation id when forking"
|
||||
);
|
||||
assert_ne!(
|
||||
rollout_path, original_path,
|
||||
"expected a new rollout path when forking"
|
||||
);
|
||||
assert!(
|
||||
rollout_path.exists(),
|
||||
"expected forked rollout to exist at {}",
|
||||
rollout_path.display()
|
||||
);
|
||||
|
||||
let session_initial_messages =
|
||||
session_initial_messages.expect("expected initial messages when forking from rollout");
|
||||
match session_initial_messages.as_slice() {
|
||||
[EventMsg::UserMessage(message)] => {
|
||||
assert_eq!(message.message, preview);
|
||||
}
|
||||
other => panic!("unexpected initial messages from rollout fork: {other:#?}"),
|
||||
}
|
||||
|
||||
// Then the response for forkConversation.
|
||||
let fork_resp: JSONRPCResponse = timeout(
|
||||
DEFAULT_READ_TIMEOUT,
|
||||
mcp.read_stream_until_response_message(RequestId::Integer(fork_req_id)),
|
||||
)
|
||||
.await??;
|
||||
let ForkConversationResponse {
|
||||
conversation_id: forked_id,
|
||||
model: forked_model,
|
||||
initial_messages: response_initial_messages,
|
||||
rollout_path: response_rollout_path,
|
||||
} = to_response::<ForkConversationResponse>(fork_resp)?;
|
||||
|
||||
assert_eq!(forked_model, "o3");
|
||||
assert_eq!(response_rollout_path, rollout_path);
|
||||
assert_ne!(forked_id.to_string(), conversation_id);
|
||||
|
||||
let response_initial_messages =
|
||||
response_initial_messages.expect("expected initial messages in fork response");
|
||||
match response_initial_messages.as_slice() {
|
||||
[EventMsg::UserMessage(message)] => {
|
||||
assert_eq!(message.message, preview);
|
||||
}
|
||||
other => panic!("unexpected initial messages in fork response: {other:#?}"),
|
||||
}
|
||||
|
||||
let after_contents = std::fs::read_to_string(&original_path)?;
|
||||
assert_eq!(
|
||||
after_contents, original_contents,
|
||||
"fork should not mutate the original rollout file"
|
||||
);
|
||||
|
||||
Ok(())
|
||||
}
|
||||
@@ -18,7 +18,7 @@ use tempfile::TempDir;
|
||||
use tokio::time::timeout;
|
||||
|
||||
use app_test_support::McpProcess;
|
||||
use app_test_support::create_mock_responses_server_sequence;
|
||||
use app_test_support::create_mock_chat_completions_server;
|
||||
use app_test_support::create_shell_command_sse_response;
|
||||
use app_test_support::to_response;
|
||||
|
||||
@@ -56,7 +56,7 @@ async fn shell_command_interruption() -> anyhow::Result<()> {
|
||||
std::fs::create_dir(&working_directory)?;
|
||||
|
||||
// Create mock server with a single SSE response: the long sleep command
|
||||
let server = create_mock_responses_server_sequence(vec![create_shell_command_sse_response(
|
||||
let server = create_mock_chat_completions_server(vec![create_shell_command_sse_response(
|
||||
shell_command.clone(),
|
||||
Some(&working_directory),
|
||||
Some(10_000), // 10 seconds timeout in ms
|
||||
@@ -153,7 +153,7 @@ model_provider = "mock_provider"
|
||||
[model_providers.mock_provider]
|
||||
name = "Mock provider for test"
|
||||
base_url = "{server_uri}/v1"
|
||||
wire_api = "responses"
|
||||
wire_api = "chat"
|
||||
request_max_retries = 0
|
||||
stream_max_retries = 0
|
||||
"#
|
||||
|
||||
@@ -6,7 +6,7 @@ use codex_app_server_protocol::JSONRPCNotification;
|
||||
use codex_app_server_protocol::JSONRPCResponse;
|
||||
use codex_app_server_protocol::ListConversationsParams;
|
||||
use codex_app_server_protocol::ListConversationsResponse;
|
||||
use codex_app_server_protocol::NewConversationParams;
|
||||
use codex_app_server_protocol::NewConversationParams; // reused for overrides shape
|
||||
use codex_app_server_protocol::RequestId;
|
||||
use codex_app_server_protocol::ResumeConversationParams;
|
||||
use codex_app_server_protocol::ResumeConversationResponse;
|
||||
|
||||
@@ -32,7 +32,7 @@ model_provider = "mock_provider"
|
||||
[model_providers.mock_provider]
|
||||
name = "Mock provider for test"
|
||||
base_url = "http://127.0.0.1:0/v1"
|
||||
wire_api = "responses"
|
||||
wire_api = "chat"
|
||||
request_max_retries = 0
|
||||
stream_max_retries = 0
|
||||
"#,
|
||||
|
||||
@@ -1,9 +1,8 @@
|
||||
mod archive_thread;
|
||||
mod archive_conversation;
|
||||
mod auth;
|
||||
mod codex_message_processor_flow;
|
||||
mod config;
|
||||
mod create_thread;
|
||||
mod fork_thread;
|
||||
mod create_conversation;
|
||||
mod fuzzy_file_search;
|
||||
mod interrupt;
|
||||
mod list_resume;
|
||||
|
||||
@@ -1,5 +1,7 @@
|
||||
use anyhow::Result;
|
||||
use app_test_support::McpProcess;
|
||||
use app_test_support::create_final_assistant_message_sse_response;
|
||||
use app_test_support::create_mock_chat_completions_server;
|
||||
use app_test_support::to_response;
|
||||
use codex_app_server_protocol::AddConversationListenerParams;
|
||||
use codex_app_server_protocol::AddConversationSubscriptionResponse;
|
||||
@@ -11,11 +13,10 @@ use codex_app_server_protocol::NewConversationResponse;
|
||||
use codex_app_server_protocol::RequestId;
|
||||
use codex_app_server_protocol::SendUserMessageParams;
|
||||
use codex_app_server_protocol::SendUserMessageResponse;
|
||||
use codex_protocol::ThreadId;
|
||||
use codex_protocol::ConversationId;
|
||||
use codex_protocol::models::ContentItem;
|
||||
use codex_protocol::models::ResponseItem;
|
||||
use codex_protocol::protocol::RawResponseItemEvent;
|
||||
use core_test_support::responses;
|
||||
use pretty_assertions::assert_eq;
|
||||
use std::path::Path;
|
||||
use tempfile::TempDir;
|
||||
@@ -25,21 +26,13 @@ const DEFAULT_READ_TIMEOUT: std::time::Duration = std::time::Duration::from_secs
|
||||
|
||||
#[tokio::test]
|
||||
async fn test_send_message_success() -> Result<()> {
|
||||
// Spin up a mock responses server that immediately ends the Codex turn.
|
||||
// Spin up a mock completions server that immediately ends the Codex turn.
|
||||
// Two Codex turns hit the mock model (session start + send-user-message). Provide two SSE responses.
|
||||
let server = responses::start_mock_server().await;
|
||||
let body1 = responses::sse(vec![
|
||||
responses::ev_response_created("resp-1"),
|
||||
responses::ev_assistant_message("msg-1", "Done"),
|
||||
responses::ev_completed("resp-1"),
|
||||
]);
|
||||
let body2 = responses::sse(vec![
|
||||
responses::ev_response_created("resp-2"),
|
||||
responses::ev_assistant_message("msg-2", "Done"),
|
||||
responses::ev_completed("resp-2"),
|
||||
]);
|
||||
let _response_mock1 = responses::mount_sse_once(&server, body1).await;
|
||||
let _response_mock2 = responses::mount_sse_once(&server, body2).await;
|
||||
let responses = vec![
|
||||
create_final_assistant_message_sse_response("Done")?,
|
||||
create_final_assistant_message_sse_response("Done")?,
|
||||
];
|
||||
let server = create_mock_chat_completions_server(responses).await;
|
||||
|
||||
// Create a temporary Codex home with config pointing at the mock server.
|
||||
let codex_home = TempDir::new()?;
|
||||
@@ -88,7 +81,7 @@ async fn test_send_message_success() -> Result<()> {
|
||||
#[expect(clippy::expect_used)]
|
||||
async fn send_message(
|
||||
message: &str,
|
||||
conversation_id: ThreadId,
|
||||
conversation_id: ConversationId,
|
||||
mcp: &mut McpProcess,
|
||||
) -> Result<()> {
|
||||
// Now exercise sendUserMessage.
|
||||
@@ -142,13 +135,8 @@ async fn send_message(
|
||||
|
||||
#[tokio::test]
|
||||
async fn test_send_message_raw_notifications_opt_in() -> Result<()> {
|
||||
let server = responses::start_mock_server().await;
|
||||
let body = responses::sse(vec![
|
||||
responses::ev_response_created("resp-1"),
|
||||
responses::ev_assistant_message("msg-1", "Done"),
|
||||
responses::ev_completed("resp-1"),
|
||||
]);
|
||||
let _response_mock = responses::mount_sse_once(&server, body).await;
|
||||
let responses = vec![create_final_assistant_message_sse_response("Done")?];
|
||||
let server = create_mock_chat_completions_server(responses).await;
|
||||
|
||||
let codex_home = TempDir::new()?;
|
||||
create_config_toml(codex_home.path(), &server.uri())?;
|
||||
@@ -232,7 +220,7 @@ async fn test_send_message_session_not_found() -> Result<()> {
|
||||
let mut mcp = McpProcess::new(codex_home.path()).await?;
|
||||
timeout(DEFAULT_READ_TIMEOUT, mcp.initialize()).await??;
|
||||
|
||||
let unknown = ThreadId::new();
|
||||
let unknown = ConversationId::new();
|
||||
let req_id = mcp
|
||||
.send_send_user_message_request(SendUserMessageParams {
|
||||
conversation_id: unknown,
|
||||
@@ -271,7 +259,7 @@ model_provider = "mock_provider"
|
||||
[model_providers.mock_provider]
|
||||
name = "Mock provider for test"
|
||||
base_url = "{server_uri}/v1"
|
||||
wire_api = "responses"
|
||||
wire_api = "chat"
|
||||
request_max_retries = 0
|
||||
stream_max_retries = 0
|
||||
"#
|
||||
@@ -280,8 +268,10 @@ stream_max_retries = 0
|
||||
}
|
||||
|
||||
#[expect(clippy::expect_used)]
|
||||
async fn read_raw_response_item(mcp: &mut McpProcess, conversation_id: ThreadId) -> ResponseItem {
|
||||
// TODO: Switch to rawResponseItem/completed once we migrate to app server v2 in codex web.
|
||||
async fn read_raw_response_item(
|
||||
mcp: &mut McpProcess,
|
||||
conversation_id: ConversationId,
|
||||
) -> ResponseItem {
|
||||
loop {
|
||||
let raw_notification: JSONRPCNotification = timeout(
|
||||
DEFAULT_READ_TIMEOUT,
|
||||
|
||||
@@ -67,7 +67,7 @@ model_provider = "mock_provider"
|
||||
[model_providers.mock_provider]
|
||||
name = "Mock provider for test"
|
||||
base_url = "http://127.0.0.1:0/v1"
|
||||
wire_api = "responses"
|
||||
wire_api = "chat"
|
||||
request_max_retries = 0
|
||||
stream_max_retries = 0
|
||||
{requires_line}
|
||||
|
||||
@@ -184,10 +184,7 @@ writable_roots = [{}]
|
||||
|
||||
let mut mcp = McpProcess::new_with_env(
|
||||
codex_home.path(),
|
||||
&[(
|
||||
"CODEX_APP_SERVER_MANAGED_CONFIG_PATH",
|
||||
Some(&managed_path_str),
|
||||
)],
|
||||
&[("CODEX_MANAGED_CONFIG_PATH", Some(&managed_path_str))],
|
||||
)
|
||||
.await?;
|
||||
timeout(DEFAULT_READ_TIMEOUT, mcp.initialize()).await??;
|
||||
|
||||
@@ -5,11 +5,8 @@ mod output_schema;
|
||||
mod rate_limits;
|
||||
mod review;
|
||||
mod thread_archive;
|
||||
mod thread_fork;
|
||||
mod thread_list;
|
||||
mod thread_loaded_list;
|
||||
mod thread_resume;
|
||||
mod thread_rollback;
|
||||
mod thread_start;
|
||||
mod turn_interrupt;
|
||||
mod turn_start;
|
||||
|
||||
@@ -48,32 +48,57 @@ async fn list_models_returns_all_models_with_large_limit() -> Result<()> {
|
||||
|
||||
let expected_models = vec![
|
||||
Model {
|
||||
id: "gpt-5.2-codex".to_string(),
|
||||
model: "gpt-5.2-codex".to_string(),
|
||||
display_name: "gpt-5.2-codex".to_string(),
|
||||
description: "Latest frontier agentic coding model.".to_string(),
|
||||
id: "gpt-5.2".to_string(),
|
||||
model: "gpt-5.2".to_string(),
|
||||
display_name: "gpt-5.2".to_string(),
|
||||
description:
|
||||
"Latest frontier model with improvements across knowledge, reasoning and coding"
|
||||
.to_string(),
|
||||
supported_reasoning_efforts: vec![
|
||||
ReasoningEffortOption {
|
||||
reasoning_effort: ReasoningEffort::Low,
|
||||
description: "Fast responses with lighter reasoning".to_string(),
|
||||
description: "Balances speed with some reasoning; useful for straightforward \
|
||||
queries and short explanations"
|
||||
.to_string(),
|
||||
},
|
||||
ReasoningEffortOption {
|
||||
reasoning_effort: ReasoningEffort::Medium,
|
||||
description: "Balances speed and reasoning depth for everyday tasks"
|
||||
description: "Provides a solid balance of reasoning depth and latency for \
|
||||
general-purpose tasks"
|
||||
.to_string(),
|
||||
},
|
||||
ReasoningEffortOption {
|
||||
reasoning_effort: ReasoningEffort::High,
|
||||
description: "Greater reasoning depth for complex problems".to_string(),
|
||||
description: "Maximizes reasoning depth for complex or ambiguous problems"
|
||||
.to_string(),
|
||||
},
|
||||
ReasoningEffortOption {
|
||||
reasoning_effort: ReasoningEffort::XHigh,
|
||||
description: "Extra high reasoning depth for complex problems".to_string(),
|
||||
description: "Extra high reasoning for complex problems".to_string(),
|
||||
},
|
||||
],
|
||||
default_reasoning_effort: ReasoningEffort::Medium,
|
||||
is_default: true,
|
||||
},
|
||||
Model {
|
||||
id: "gpt-5.1-codex-mini".to_string(),
|
||||
model: "gpt-5.1-codex-mini".to_string(),
|
||||
display_name: "gpt-5.1-codex-mini".to_string(),
|
||||
description: "Optimized for codex. Cheaper, faster, but less capable.".to_string(),
|
||||
supported_reasoning_efforts: vec![
|
||||
ReasoningEffortOption {
|
||||
reasoning_effort: ReasoningEffort::Medium,
|
||||
description: "Dynamically adjusts reasoning based on the task".to_string(),
|
||||
},
|
||||
ReasoningEffortOption {
|
||||
reasoning_effort: ReasoningEffort::High,
|
||||
description: "Maximizes reasoning depth for complex or ambiguous problems"
|
||||
.to_string(),
|
||||
},
|
||||
],
|
||||
default_reasoning_effort: ReasoningEffort::Medium,
|
||||
is_default: false,
|
||||
},
|
||||
Model {
|
||||
id: "gpt-5.1-codex-max".to_string(),
|
||||
model: "gpt-5.1-codex-max".to_string(),
|
||||
@@ -102,48 +127,23 @@ async fn list_models_returns_all_models_with_large_limit() -> Result<()> {
|
||||
is_default: false,
|
||||
},
|
||||
Model {
|
||||
id: "gpt-5.1-codex-mini".to_string(),
|
||||
model: "gpt-5.1-codex-mini".to_string(),
|
||||
display_name: "gpt-5.1-codex-mini".to_string(),
|
||||
description: "Optimized for codex. Cheaper, faster, but less capable.".to_string(),
|
||||
supported_reasoning_efforts: vec![
|
||||
ReasoningEffortOption {
|
||||
reasoning_effort: ReasoningEffort::Medium,
|
||||
description: "Dynamically adjusts reasoning based on the task".to_string(),
|
||||
},
|
||||
ReasoningEffortOption {
|
||||
reasoning_effort: ReasoningEffort::High,
|
||||
description: "Maximizes reasoning depth for complex or ambiguous problems"
|
||||
.to_string(),
|
||||
},
|
||||
],
|
||||
default_reasoning_effort: ReasoningEffort::Medium,
|
||||
is_default: false,
|
||||
},
|
||||
Model {
|
||||
id: "gpt-5.2".to_string(),
|
||||
model: "gpt-5.2".to_string(),
|
||||
display_name: "gpt-5.2".to_string(),
|
||||
description:
|
||||
"Latest frontier model with improvements across knowledge, reasoning and coding"
|
||||
.to_string(),
|
||||
id: "gpt-5.2-codex".to_string(),
|
||||
model: "gpt-5.2-codex".to_string(),
|
||||
display_name: "gpt-5.2-codex".to_string(),
|
||||
description: "Latest frontier agentic coding model.".to_string(),
|
||||
supported_reasoning_efforts: vec![
|
||||
ReasoningEffortOption {
|
||||
reasoning_effort: ReasoningEffort::Low,
|
||||
description: "Balances speed with some reasoning; useful for straightforward \
|
||||
queries and short explanations"
|
||||
.to_string(),
|
||||
description: "Fast responses with lighter reasoning".to_string(),
|
||||
},
|
||||
ReasoningEffortOption {
|
||||
reasoning_effort: ReasoningEffort::Medium,
|
||||
description: "Provides a solid balance of reasoning depth and latency for \
|
||||
general-purpose tasks"
|
||||
description: "Balances speed and reasoning depth for everyday tasks"
|
||||
.to_string(),
|
||||
},
|
||||
ReasoningEffortOption {
|
||||
reasoning_effort: ReasoningEffort::High,
|
||||
description: "Maximizes reasoning depth for complex or ambiguous problems"
|
||||
.to_string(),
|
||||
description: "Greater reasoning depth for complex problems".to_string(),
|
||||
},
|
||||
ReasoningEffortOption {
|
||||
reasoning_effort: ReasoningEffort::XHigh,
|
||||
@@ -187,7 +187,7 @@ async fn list_models_pagination_works() -> Result<()> {
|
||||
} = to_response::<ModelListResponse>(first_response)?;
|
||||
|
||||
assert_eq!(first_items.len(), 1);
|
||||
assert_eq!(first_items[0].id, "gpt-5.2-codex");
|
||||
assert_eq!(first_items[0].id, "gpt-5.2");
|
||||
let next_cursor = first_cursor.ok_or_else(|| anyhow!("cursor for second page"))?;
|
||||
|
||||
let second_request = mcp
|
||||
@@ -209,7 +209,7 @@ async fn list_models_pagination_works() -> Result<()> {
|
||||
} = to_response::<ModelListResponse>(second_response)?;
|
||||
|
||||
assert_eq!(second_items.len(), 1);
|
||||
assert_eq!(second_items[0].id, "gpt-5.1-codex-max");
|
||||
assert_eq!(second_items[0].id, "gpt-5.1-codex-mini");
|
||||
let third_cursor = second_cursor.ok_or_else(|| anyhow!("cursor for third page"))?;
|
||||
|
||||
let third_request = mcp
|
||||
@@ -231,7 +231,7 @@ async fn list_models_pagination_works() -> Result<()> {
|
||||
} = to_response::<ModelListResponse>(third_response)?;
|
||||
|
||||
assert_eq!(third_items.len(), 1);
|
||||
assert_eq!(third_items[0].id, "gpt-5.1-codex-mini");
|
||||
assert_eq!(third_items[0].id, "gpt-5.1-codex-max");
|
||||
let fourth_cursor = third_cursor.ok_or_else(|| anyhow!("cursor for fourth page"))?;
|
||||
|
||||
let fourth_request = mcp
|
||||
@@ -253,7 +253,7 @@ async fn list_models_pagination_works() -> Result<()> {
|
||||
} = to_response::<ModelListResponse>(fourth_response)?;
|
||||
|
||||
assert_eq!(fourth_items.len(), 1);
|
||||
assert_eq!(fourth_items[0].id, "gpt-5.2");
|
||||
assert_eq!(fourth_items[0].id, "gpt-5.2-codex");
|
||||
assert!(fourth_cursor.is_none());
|
||||
Ok(())
|
||||
}
|
||||
|
||||
@@ -1,6 +1,7 @@
|
||||
use anyhow::Result;
|
||||
use app_test_support::McpProcess;
|
||||
use app_test_support::create_mock_responses_server_repeating_assistant;
|
||||
use app_test_support::create_final_assistant_message_sse_response;
|
||||
use app_test_support::create_mock_chat_completions_server_unchecked;
|
||||
use app_test_support::to_response;
|
||||
use codex_app_server_protocol::ItemCompletedNotification;
|
||||
use codex_app_server_protocol::ItemStartedNotification;
|
||||
@@ -43,7 +44,10 @@ async fn review_start_runs_review_turn_and_emits_code_review_item() -> Result<()
|
||||
"overall_confidence_score": 0.75
|
||||
})
|
||||
.to_string();
|
||||
let server = create_mock_responses_server_repeating_assistant(&review_payload).await;
|
||||
let responses = vec![create_final_assistant_message_sse_response(
|
||||
&review_payload,
|
||||
)?];
|
||||
let server = create_mock_chat_completions_server_unchecked(responses).await;
|
||||
|
||||
let codex_home = TempDir::new()?;
|
||||
create_config_toml(codex_home.path(), &server.uri())?;
|
||||
@@ -131,7 +135,7 @@ async fn review_start_runs_review_turn_and_emits_code_review_item() -> Result<()
|
||||
|
||||
#[tokio::test]
|
||||
async fn review_start_rejects_empty_base_branch() -> Result<()> {
|
||||
let server = create_mock_responses_server_repeating_assistant("Done").await;
|
||||
let server = create_mock_chat_completions_server_unchecked(vec![]).await;
|
||||
let codex_home = TempDir::new()?;
|
||||
create_config_toml(codex_home.path(), &server.uri())?;
|
||||
|
||||
@@ -172,7 +176,10 @@ async fn review_start_with_detached_delivery_returns_new_thread_id() -> Result<(
|
||||
"overall_confidence_score": 0.5
|
||||
})
|
||||
.to_string();
|
||||
let server = create_mock_responses_server_repeating_assistant(&review_payload).await;
|
||||
let responses = vec![create_final_assistant_message_sse_response(
|
||||
&review_payload,
|
||||
)?];
|
||||
let server = create_mock_chat_completions_server_unchecked(responses).await;
|
||||
|
||||
let codex_home = TempDir::new()?;
|
||||
create_config_toml(codex_home.path(), &server.uri())?;
|
||||
@@ -212,7 +219,7 @@ async fn review_start_with_detached_delivery_returns_new_thread_id() -> Result<(
|
||||
|
||||
#[tokio::test]
|
||||
async fn review_start_rejects_empty_commit_sha() -> Result<()> {
|
||||
let server = create_mock_responses_server_repeating_assistant("Done").await;
|
||||
let server = create_mock_chat_completions_server_unchecked(vec![]).await;
|
||||
let codex_home = TempDir::new()?;
|
||||
create_config_toml(codex_home.path(), &server.uri())?;
|
||||
|
||||
@@ -247,7 +254,7 @@ async fn review_start_rejects_empty_commit_sha() -> Result<()> {
|
||||
|
||||
#[tokio::test]
|
||||
async fn review_start_rejects_empty_custom_instructions() -> Result<()> {
|
||||
let server = create_mock_responses_server_repeating_assistant("Done").await;
|
||||
let server = create_mock_chat_completions_server_unchecked(vec![]).await;
|
||||
let codex_home = TempDir::new()?;
|
||||
create_config_toml(codex_home.path(), &server.uri())?;
|
||||
|
||||
@@ -313,7 +320,7 @@ model_provider = "mock_provider"
|
||||
[model_providers.mock_provider]
|
||||
name = "Mock provider"
|
||||
base_url = "{server_uri}/v1"
|
||||
wire_api = "responses"
|
||||
wire_api = "chat"
|
||||
request_max_retries = 0
|
||||
stream_max_retries = 0
|
||||
"#
|
||||
|
||||
@@ -8,7 +8,7 @@ use codex_app_server_protocol::ThreadArchiveResponse;
|
||||
use codex_app_server_protocol::ThreadStartParams;
|
||||
use codex_app_server_protocol::ThreadStartResponse;
|
||||
use codex_core::ARCHIVED_SESSIONS_SUBDIR;
|
||||
use codex_core::find_thread_path_by_id_str;
|
||||
use codex_core::find_conversation_path_by_id_str;
|
||||
use std::path::Path;
|
||||
use tempfile::TempDir;
|
||||
use tokio::time::timeout;
|
||||
@@ -39,7 +39,7 @@ async fn thread_archive_moves_rollout_into_archived_directory() -> Result<()> {
|
||||
assert!(!thread.id.is_empty());
|
||||
|
||||
// Locate the rollout path recorded for this thread id.
|
||||
let rollout_path = find_thread_path_by_id_str(codex_home.path(), &thread.id)
|
||||
let rollout_path = find_conversation_path_by_id_str(codex_home.path(), &thread.id)
|
||||
.await?
|
||||
.expect("expected rollout path for thread id to exist");
|
||||
assert!(
|
||||
|
||||
@@ -1,140 +0,0 @@
|
||||
use anyhow::Result;
|
||||
use app_test_support::McpProcess;
|
||||
use app_test_support::create_fake_rollout;
|
||||
use app_test_support::create_mock_responses_server_repeating_assistant;
|
||||
use app_test_support::to_response;
|
||||
use codex_app_server_protocol::JSONRPCNotification;
|
||||
use codex_app_server_protocol::JSONRPCResponse;
|
||||
use codex_app_server_protocol::RequestId;
|
||||
use codex_app_server_protocol::SessionSource;
|
||||
use codex_app_server_protocol::ThreadForkParams;
|
||||
use codex_app_server_protocol::ThreadForkResponse;
|
||||
use codex_app_server_protocol::ThreadItem;
|
||||
use codex_app_server_protocol::ThreadStartedNotification;
|
||||
use codex_app_server_protocol::TurnStatus;
|
||||
use codex_app_server_protocol::UserInput;
|
||||
use pretty_assertions::assert_eq;
|
||||
use std::path::Path;
|
||||
use tempfile::TempDir;
|
||||
use tokio::time::timeout;
|
||||
|
||||
const DEFAULT_READ_TIMEOUT: std::time::Duration = std::time::Duration::from_secs(10);
|
||||
|
||||
#[tokio::test]
|
||||
async fn thread_fork_creates_new_thread_and_emits_started() -> Result<()> {
|
||||
let server = create_mock_responses_server_repeating_assistant("Done").await;
|
||||
let codex_home = TempDir::new()?;
|
||||
create_config_toml(codex_home.path(), &server.uri())?;
|
||||
|
||||
let preview = "Saved user message";
|
||||
let conversation_id = create_fake_rollout(
|
||||
codex_home.path(),
|
||||
"2025-01-05T12-00-00",
|
||||
"2025-01-05T12:00:00Z",
|
||||
preview,
|
||||
Some("mock_provider"),
|
||||
None,
|
||||
)?;
|
||||
|
||||
let original_path = codex_home
|
||||
.path()
|
||||
.join("sessions")
|
||||
.join("2025")
|
||||
.join("01")
|
||||
.join("05")
|
||||
.join(format!(
|
||||
"rollout-2025-01-05T12-00-00-{conversation_id}.jsonl"
|
||||
));
|
||||
assert!(
|
||||
original_path.exists(),
|
||||
"expected original rollout to exist at {}",
|
||||
original_path.display()
|
||||
);
|
||||
let original_contents = std::fs::read_to_string(&original_path)?;
|
||||
|
||||
let mut mcp = McpProcess::new(codex_home.path()).await?;
|
||||
timeout(DEFAULT_READ_TIMEOUT, mcp.initialize()).await??;
|
||||
|
||||
let fork_id = mcp
|
||||
.send_thread_fork_request(ThreadForkParams {
|
||||
thread_id: conversation_id.clone(),
|
||||
..Default::default()
|
||||
})
|
||||
.await?;
|
||||
let fork_resp: JSONRPCResponse = timeout(
|
||||
DEFAULT_READ_TIMEOUT,
|
||||
mcp.read_stream_until_response_message(RequestId::Integer(fork_id)),
|
||||
)
|
||||
.await??;
|
||||
let ThreadForkResponse { thread, .. } = to_response::<ThreadForkResponse>(fork_resp)?;
|
||||
|
||||
let after_contents = std::fs::read_to_string(&original_path)?;
|
||||
assert_eq!(
|
||||
after_contents, original_contents,
|
||||
"fork should not mutate the original rollout file"
|
||||
);
|
||||
|
||||
assert_ne!(thread.id, conversation_id);
|
||||
assert_eq!(thread.preview, preview);
|
||||
assert_eq!(thread.model_provider, "mock_provider");
|
||||
assert!(thread.path.is_absolute());
|
||||
assert_ne!(thread.path, original_path);
|
||||
assert!(thread.cwd.is_absolute());
|
||||
assert_eq!(thread.source, SessionSource::VsCode);
|
||||
|
||||
assert_eq!(
|
||||
thread.turns.len(),
|
||||
1,
|
||||
"expected forked thread to include one turn"
|
||||
);
|
||||
let turn = &thread.turns[0];
|
||||
assert_eq!(turn.status, TurnStatus::Completed);
|
||||
assert_eq!(turn.items.len(), 1, "expected user message item");
|
||||
match &turn.items[0] {
|
||||
ThreadItem::UserMessage { content, .. } => {
|
||||
assert_eq!(
|
||||
content,
|
||||
&vec![UserInput::Text {
|
||||
text: preview.to_string()
|
||||
}]
|
||||
);
|
||||
}
|
||||
other => panic!("expected user message item, got {other:?}"),
|
||||
}
|
||||
|
||||
// A corresponding thread/started notification should arrive.
|
||||
let notif: JSONRPCNotification = timeout(
|
||||
DEFAULT_READ_TIMEOUT,
|
||||
mcp.read_stream_until_notification_message("thread/started"),
|
||||
)
|
||||
.await??;
|
||||
let started: ThreadStartedNotification =
|
||||
serde_json::from_value(notif.params.expect("params must be present"))?;
|
||||
assert_eq!(started.thread, thread);
|
||||
|
||||
Ok(())
|
||||
}
|
||||
|
||||
// Helper to create a config.toml pointing at the mock model server.
|
||||
fn create_config_toml(codex_home: &Path, server_uri: &str) -> std::io::Result<()> {
|
||||
let config_toml = codex_home.join("config.toml");
|
||||
std::fs::write(
|
||||
config_toml,
|
||||
format!(
|
||||
r#"
|
||||
model = "mock-model"
|
||||
approval_policy = "never"
|
||||
sandbox_mode = "read-only"
|
||||
|
||||
model_provider = "mock_provider"
|
||||
|
||||
[model_providers.mock_provider]
|
||||
name = "Mock provider for test"
|
||||
base_url = "{server_uri}/v1"
|
||||
wire_api = "responses"
|
||||
request_max_retries = 0
|
||||
stream_max_retries = 0
|
||||
"#
|
||||
),
|
||||
)
|
||||
}
|
||||
@@ -1,139 +0,0 @@
|
||||
use anyhow::Result;
|
||||
use app_test_support::McpProcess;
|
||||
use app_test_support::create_mock_responses_server_repeating_assistant;
|
||||
use app_test_support::to_response;
|
||||
use codex_app_server_protocol::JSONRPCResponse;
|
||||
use codex_app_server_protocol::RequestId;
|
||||
use codex_app_server_protocol::ThreadLoadedListParams;
|
||||
use codex_app_server_protocol::ThreadLoadedListResponse;
|
||||
use codex_app_server_protocol::ThreadStartParams;
|
||||
use codex_app_server_protocol::ThreadStartResponse;
|
||||
use pretty_assertions::assert_eq;
|
||||
use std::path::Path;
|
||||
use tempfile::TempDir;
|
||||
use tokio::time::timeout;
|
||||
|
||||
const DEFAULT_READ_TIMEOUT: std::time::Duration = std::time::Duration::from_secs(10);
|
||||
|
||||
#[tokio::test]
|
||||
async fn thread_loaded_list_returns_loaded_thread_ids() -> Result<()> {
|
||||
let server = create_mock_responses_server_repeating_assistant("Done").await;
|
||||
let codex_home = TempDir::new()?;
|
||||
create_config_toml(codex_home.path(), &server.uri())?;
|
||||
|
||||
let mut mcp = McpProcess::new(codex_home.path()).await?;
|
||||
timeout(DEFAULT_READ_TIMEOUT, mcp.initialize()).await??;
|
||||
|
||||
let thread_id = start_thread(&mut mcp).await?;
|
||||
|
||||
let list_id = mcp
|
||||
.send_thread_loaded_list_request(ThreadLoadedListParams::default())
|
||||
.await?;
|
||||
let resp: JSONRPCResponse = timeout(
|
||||
DEFAULT_READ_TIMEOUT,
|
||||
mcp.read_stream_until_response_message(RequestId::Integer(list_id)),
|
||||
)
|
||||
.await??;
|
||||
let ThreadLoadedListResponse {
|
||||
mut data,
|
||||
next_cursor,
|
||||
} = to_response::<ThreadLoadedListResponse>(resp)?;
|
||||
data.sort();
|
||||
assert_eq!(data, vec![thread_id]);
|
||||
assert_eq!(next_cursor, None);
|
||||
|
||||
Ok(())
|
||||
}
|
||||
|
||||
#[tokio::test]
|
||||
async fn thread_loaded_list_paginates() -> Result<()> {
|
||||
let server = create_mock_responses_server_repeating_assistant("Done").await;
|
||||
let codex_home = TempDir::new()?;
|
||||
create_config_toml(codex_home.path(), &server.uri())?;
|
||||
|
||||
let mut mcp = McpProcess::new(codex_home.path()).await?;
|
||||
timeout(DEFAULT_READ_TIMEOUT, mcp.initialize()).await??;
|
||||
|
||||
let first = start_thread(&mut mcp).await?;
|
||||
let second = start_thread(&mut mcp).await?;
|
||||
|
||||
let mut expected = [first, second];
|
||||
expected.sort();
|
||||
|
||||
let list_id = mcp
|
||||
.send_thread_loaded_list_request(ThreadLoadedListParams {
|
||||
cursor: None,
|
||||
limit: Some(1),
|
||||
})
|
||||
.await?;
|
||||
let resp: JSONRPCResponse = timeout(
|
||||
DEFAULT_READ_TIMEOUT,
|
||||
mcp.read_stream_until_response_message(RequestId::Integer(list_id)),
|
||||
)
|
||||
.await??;
|
||||
let ThreadLoadedListResponse {
|
||||
data: first_page,
|
||||
next_cursor,
|
||||
} = to_response::<ThreadLoadedListResponse>(resp)?;
|
||||
assert_eq!(first_page, vec![expected[0].clone()]);
|
||||
assert_eq!(next_cursor, Some(expected[0].clone()));
|
||||
|
||||
let list_id = mcp
|
||||
.send_thread_loaded_list_request(ThreadLoadedListParams {
|
||||
cursor: next_cursor,
|
||||
limit: Some(1),
|
||||
})
|
||||
.await?;
|
||||
let resp: JSONRPCResponse = timeout(
|
||||
DEFAULT_READ_TIMEOUT,
|
||||
mcp.read_stream_until_response_message(RequestId::Integer(list_id)),
|
||||
)
|
||||
.await??;
|
||||
let ThreadLoadedListResponse {
|
||||
data: second_page,
|
||||
next_cursor,
|
||||
} = to_response::<ThreadLoadedListResponse>(resp)?;
|
||||
assert_eq!(second_page, vec![expected[1].clone()]);
|
||||
assert_eq!(next_cursor, None);
|
||||
|
||||
Ok(())
|
||||
}
|
||||
|
||||
fn create_config_toml(codex_home: &Path, server_uri: &str) -> std::io::Result<()> {
|
||||
let config_toml = codex_home.join("config.toml");
|
||||
std::fs::write(
|
||||
config_toml,
|
||||
format!(
|
||||
r#"
|
||||
model = "mock-model"
|
||||
approval_policy = "never"
|
||||
sandbox_mode = "read-only"
|
||||
|
||||
model_provider = "mock_provider"
|
||||
|
||||
[model_providers.mock_provider]
|
||||
name = "Mock provider for test"
|
||||
base_url = "{server_uri}/v1"
|
||||
wire_api = "responses"
|
||||
request_max_retries = 0
|
||||
stream_max_retries = 0
|
||||
"#
|
||||
),
|
||||
)
|
||||
}
|
||||
|
||||
async fn start_thread(mcp: &mut McpProcess) -> Result<String> {
|
||||
let req_id = mcp
|
||||
.send_thread_start_request(ThreadStartParams {
|
||||
model: Some("gpt-5.1".to_string()),
|
||||
..Default::default()
|
||||
})
|
||||
.await?;
|
||||
let resp: JSONRPCResponse = timeout(
|
||||
DEFAULT_READ_TIMEOUT,
|
||||
mcp.read_stream_until_response_message(RequestId::Integer(req_id)),
|
||||
)
|
||||
.await??;
|
||||
let ThreadStartResponse { thread, .. } = to_response::<ThreadStartResponse>(resp)?;
|
||||
Ok(thread.id)
|
||||
}
|
||||
@@ -1,7 +1,7 @@
|
||||
use anyhow::Result;
|
||||
use app_test_support::McpProcess;
|
||||
use app_test_support::create_fake_rollout;
|
||||
use app_test_support::create_mock_responses_server_repeating_assistant;
|
||||
use app_test_support::create_mock_chat_completions_server;
|
||||
use app_test_support::to_response;
|
||||
use codex_app_server_protocol::JSONRPCResponse;
|
||||
use codex_app_server_protocol::RequestId;
|
||||
@@ -23,7 +23,7 @@ const DEFAULT_READ_TIMEOUT: std::time::Duration = std::time::Duration::from_secs
|
||||
|
||||
#[tokio::test]
|
||||
async fn thread_resume_returns_original_thread() -> Result<()> {
|
||||
let server = create_mock_responses_server_repeating_assistant("Done").await;
|
||||
let server = create_mock_chat_completions_server(vec![]).await;
|
||||
let codex_home = TempDir::new()?;
|
||||
create_config_toml(codex_home.path(), &server.uri())?;
|
||||
|
||||
@@ -66,7 +66,7 @@ async fn thread_resume_returns_original_thread() -> Result<()> {
|
||||
|
||||
#[tokio::test]
|
||||
async fn thread_resume_returns_rollout_history() -> Result<()> {
|
||||
let server = create_mock_responses_server_repeating_assistant("Done").await;
|
||||
let server = create_mock_chat_completions_server(vec![]).await;
|
||||
let codex_home = TempDir::new()?;
|
||||
create_config_toml(codex_home.path(), &server.uri())?;
|
||||
|
||||
@@ -130,7 +130,7 @@ async fn thread_resume_returns_rollout_history() -> Result<()> {
|
||||
|
||||
#[tokio::test]
|
||||
async fn thread_resume_prefers_path_over_thread_id() -> Result<()> {
|
||||
let server = create_mock_responses_server_repeating_assistant("Done").await;
|
||||
let server = create_mock_chat_completions_server(vec![]).await;
|
||||
let codex_home = TempDir::new()?;
|
||||
create_config_toml(codex_home.path(), &server.uri())?;
|
||||
|
||||
@@ -174,7 +174,7 @@ async fn thread_resume_prefers_path_over_thread_id() -> Result<()> {
|
||||
|
||||
#[tokio::test]
|
||||
async fn thread_resume_supports_history_and_overrides() -> Result<()> {
|
||||
let server = create_mock_responses_server_repeating_assistant("Done").await;
|
||||
let server = create_mock_chat_completions_server(vec![]).await;
|
||||
let codex_home = TempDir::new()?;
|
||||
create_config_toml(codex_home.path(), &server.uri())?;
|
||||
|
||||
@@ -247,7 +247,7 @@ model_provider = "mock_provider"
|
||||
[model_providers.mock_provider]
|
||||
name = "Mock provider for test"
|
||||
base_url = "{server_uri}/v1"
|
||||
wire_api = "responses"
|
||||
wire_api = "chat"
|
||||
request_max_retries = 0
|
||||
stream_max_retries = 0
|
||||
"#
|
||||
|
||||
@@ -1,177 +0,0 @@
|
||||
use anyhow::Result;
|
||||
use app_test_support::McpProcess;
|
||||
use app_test_support::create_final_assistant_message_sse_response;
|
||||
use app_test_support::create_mock_responses_server_sequence_unchecked;
|
||||
use app_test_support::to_response;
|
||||
use codex_app_server_protocol::JSONRPCResponse;
|
||||
use codex_app_server_protocol::RequestId;
|
||||
use codex_app_server_protocol::ThreadItem;
|
||||
use codex_app_server_protocol::ThreadResumeParams;
|
||||
use codex_app_server_protocol::ThreadResumeResponse;
|
||||
use codex_app_server_protocol::ThreadRollbackParams;
|
||||
use codex_app_server_protocol::ThreadRollbackResponse;
|
||||
use codex_app_server_protocol::ThreadStartParams;
|
||||
use codex_app_server_protocol::ThreadStartResponse;
|
||||
use codex_app_server_protocol::TurnStartParams;
|
||||
use codex_app_server_protocol::UserInput as V2UserInput;
|
||||
use pretty_assertions::assert_eq;
|
||||
use tempfile::TempDir;
|
||||
use tokio::time::timeout;
|
||||
|
||||
const DEFAULT_READ_TIMEOUT: std::time::Duration = std::time::Duration::from_secs(10);
|
||||
|
||||
#[tokio::test]
|
||||
async fn thread_rollback_drops_last_turns_and_persists_to_rollout() -> Result<()> {
|
||||
// Three Codex turns hit the mock model (session start + two turn/start calls).
|
||||
let responses = vec![
|
||||
create_final_assistant_message_sse_response("Done")?,
|
||||
create_final_assistant_message_sse_response("Done")?,
|
||||
create_final_assistant_message_sse_response("Done")?,
|
||||
];
|
||||
let server = create_mock_responses_server_sequence_unchecked(responses).await;
|
||||
|
||||
let codex_home = TempDir::new()?;
|
||||
create_config_toml(codex_home.path(), &server.uri())?;
|
||||
|
||||
let mut mcp = McpProcess::new(codex_home.path()).await?;
|
||||
timeout(DEFAULT_READ_TIMEOUT, mcp.initialize()).await??;
|
||||
|
||||
// Start a thread.
|
||||
let start_id = mcp
|
||||
.send_thread_start_request(ThreadStartParams {
|
||||
model: Some("mock-model".to_string()),
|
||||
..Default::default()
|
||||
})
|
||||
.await?;
|
||||
let start_resp: JSONRPCResponse = timeout(
|
||||
DEFAULT_READ_TIMEOUT,
|
||||
mcp.read_stream_until_response_message(RequestId::Integer(start_id)),
|
||||
)
|
||||
.await??;
|
||||
let ThreadStartResponse { thread, .. } = to_response::<ThreadStartResponse>(start_resp)?;
|
||||
|
||||
// Two turns.
|
||||
let first_text = "First";
|
||||
let turn1_id = mcp
|
||||
.send_turn_start_request(TurnStartParams {
|
||||
thread_id: thread.id.clone(),
|
||||
input: vec![V2UserInput::Text {
|
||||
text: first_text.to_string(),
|
||||
}],
|
||||
..Default::default()
|
||||
})
|
||||
.await?;
|
||||
let _turn1_resp: JSONRPCResponse = timeout(
|
||||
DEFAULT_READ_TIMEOUT,
|
||||
mcp.read_stream_until_response_message(RequestId::Integer(turn1_id)),
|
||||
)
|
||||
.await??;
|
||||
let _completed1 = timeout(
|
||||
DEFAULT_READ_TIMEOUT,
|
||||
mcp.read_stream_until_notification_message("turn/completed"),
|
||||
)
|
||||
.await??;
|
||||
|
||||
let turn2_id = mcp
|
||||
.send_turn_start_request(TurnStartParams {
|
||||
thread_id: thread.id.clone(),
|
||||
input: vec![V2UserInput::Text {
|
||||
text: "Second".to_string(),
|
||||
}],
|
||||
..Default::default()
|
||||
})
|
||||
.await?;
|
||||
let _turn2_resp: JSONRPCResponse = timeout(
|
||||
DEFAULT_READ_TIMEOUT,
|
||||
mcp.read_stream_until_response_message(RequestId::Integer(turn2_id)),
|
||||
)
|
||||
.await??;
|
||||
let _completed2 = timeout(
|
||||
DEFAULT_READ_TIMEOUT,
|
||||
mcp.read_stream_until_notification_message("turn/completed"),
|
||||
)
|
||||
.await??;
|
||||
|
||||
// Roll back the last turn.
|
||||
let rollback_id = mcp
|
||||
.send_thread_rollback_request(ThreadRollbackParams {
|
||||
thread_id: thread.id.clone(),
|
||||
num_turns: 1,
|
||||
})
|
||||
.await?;
|
||||
let rollback_resp: JSONRPCResponse = timeout(
|
||||
DEFAULT_READ_TIMEOUT,
|
||||
mcp.read_stream_until_response_message(RequestId::Integer(rollback_id)),
|
||||
)
|
||||
.await??;
|
||||
let ThreadRollbackResponse {
|
||||
thread: rolled_back_thread,
|
||||
} = to_response::<ThreadRollbackResponse>(rollback_resp)?;
|
||||
|
||||
assert_eq!(rolled_back_thread.turns.len(), 1);
|
||||
assert_eq!(rolled_back_thread.turns[0].items.len(), 2);
|
||||
match &rolled_back_thread.turns[0].items[0] {
|
||||
ThreadItem::UserMessage { content, .. } => {
|
||||
assert_eq!(
|
||||
content,
|
||||
&vec![V2UserInput::Text {
|
||||
text: first_text.to_string()
|
||||
}]
|
||||
);
|
||||
}
|
||||
other => panic!("expected user message item, got {other:?}"),
|
||||
}
|
||||
|
||||
// Resume and confirm the history is pruned.
|
||||
let resume_id = mcp
|
||||
.send_thread_resume_request(ThreadResumeParams {
|
||||
thread_id: thread.id,
|
||||
..Default::default()
|
||||
})
|
||||
.await?;
|
||||
let resume_resp: JSONRPCResponse = timeout(
|
||||
DEFAULT_READ_TIMEOUT,
|
||||
mcp.read_stream_until_response_message(RequestId::Integer(resume_id)),
|
||||
)
|
||||
.await??;
|
||||
let ThreadResumeResponse { thread, .. } = to_response::<ThreadResumeResponse>(resume_resp)?;
|
||||
|
||||
assert_eq!(thread.turns.len(), 1);
|
||||
assert_eq!(thread.turns[0].items.len(), 2);
|
||||
match &thread.turns[0].items[0] {
|
||||
ThreadItem::UserMessage { content, .. } => {
|
||||
assert_eq!(
|
||||
content,
|
||||
&vec![V2UserInput::Text {
|
||||
text: first_text.to_string()
|
||||
}]
|
||||
);
|
||||
}
|
||||
other => panic!("expected user message item, got {other:?}"),
|
||||
}
|
||||
|
||||
Ok(())
|
||||
}
|
||||
|
||||
fn create_config_toml(codex_home: &std::path::Path, server_uri: &str) -> std::io::Result<()> {
|
||||
let config_toml = codex_home.join("config.toml");
|
||||
std::fs::write(
|
||||
config_toml,
|
||||
format!(
|
||||
r#"
|
||||
model = "mock-model"
|
||||
approval_policy = "never"
|
||||
sandbox_mode = "read-only"
|
||||
|
||||
model_provider = "mock_provider"
|
||||
|
||||
[model_providers.mock_provider]
|
||||
name = "Mock provider for test"
|
||||
base_url = "{server_uri}/v1"
|
||||
wire_api = "responses"
|
||||
request_max_retries = 0
|
||||
stream_max_retries = 0
|
||||
"#
|
||||
),
|
||||
)
|
||||
}
|
||||
@@ -1,6 +1,6 @@
|
||||
use anyhow::Result;
|
||||
use app_test_support::McpProcess;
|
||||
use app_test_support::create_mock_responses_server_repeating_assistant;
|
||||
use app_test_support::create_mock_chat_completions_server;
|
||||
use app_test_support::to_response;
|
||||
use codex_app_server_protocol::JSONRPCNotification;
|
||||
use codex_app_server_protocol::JSONRPCResponse;
|
||||
@@ -17,7 +17,7 @@ const DEFAULT_READ_TIMEOUT: std::time::Duration = std::time::Duration::from_secs
|
||||
#[tokio::test]
|
||||
async fn thread_start_creates_thread_and_emits_started() -> Result<()> {
|
||||
// Provide a mock server and config so model wiring is valid.
|
||||
let server = create_mock_responses_server_repeating_assistant("Done").await;
|
||||
let server = create_mock_chat_completions_server(vec![]).await;
|
||||
|
||||
let codex_home = TempDir::new()?;
|
||||
create_config_toml(codex_home.path(), &server.uri())?;
|
||||
@@ -85,7 +85,7 @@ model_provider = "mock_provider"
|
||||
[model_providers.mock_provider]
|
||||
name = "Mock provider for test"
|
||||
base_url = "{server_uri}/v1"
|
||||
wire_api = "responses"
|
||||
wire_api = "chat"
|
||||
request_max_retries = 0
|
||||
stream_max_retries = 0
|
||||
"#
|
||||
|
||||
@@ -2,7 +2,7 @@
|
||||
|
||||
use anyhow::Result;
|
||||
use app_test_support::McpProcess;
|
||||
use app_test_support::create_mock_responses_server_sequence;
|
||||
use app_test_support::create_mock_chat_completions_server;
|
||||
use app_test_support::create_shell_command_sse_response;
|
||||
use app_test_support::to_response;
|
||||
use codex_app_server_protocol::JSONRPCNotification;
|
||||
@@ -41,7 +41,7 @@ async fn turn_interrupt_aborts_running_turn() -> Result<()> {
|
||||
std::fs::create_dir(&working_directory)?;
|
||||
|
||||
// Mock server: long-running shell command then (after abort) nothing else needed.
|
||||
let server = create_mock_responses_server_sequence(vec![create_shell_command_sse_response(
|
||||
let server = create_mock_chat_completions_server(vec![create_shell_command_sse_response(
|
||||
shell_command.clone(),
|
||||
Some(&working_directory),
|
||||
Some(10_000),
|
||||
@@ -135,7 +135,7 @@ model_provider = "mock_provider"
|
||||
[model_providers.mock_provider]
|
||||
name = "Mock provider for test"
|
||||
base_url = "{server_uri}/v1"
|
||||
wire_api = "responses"
|
||||
wire_api = "chat"
|
||||
request_max_retries = 0
|
||||
stream_max_retries = 0
|
||||
"#
|
||||
|
||||
@@ -3,15 +3,14 @@ use app_test_support::McpProcess;
|
||||
use app_test_support::create_apply_patch_sse_response;
|
||||
use app_test_support::create_exec_command_sse_response;
|
||||
use app_test_support::create_final_assistant_message_sse_response;
|
||||
use app_test_support::create_mock_responses_server_sequence;
|
||||
use app_test_support::create_mock_responses_server_sequence_unchecked;
|
||||
use app_test_support::create_mock_chat_completions_server;
|
||||
use app_test_support::create_mock_chat_completions_server_unchecked;
|
||||
use app_test_support::create_shell_command_sse_response;
|
||||
use app_test_support::format_with_current_shell_display;
|
||||
use app_test_support::to_response;
|
||||
use codex_app_server_protocol::CommandExecutionApprovalDecision;
|
||||
use codex_app_server_protocol::ApprovalDecision;
|
||||
use codex_app_server_protocol::CommandExecutionRequestApprovalResponse;
|
||||
use codex_app_server_protocol::CommandExecutionStatus;
|
||||
use codex_app_server_protocol::FileChangeApprovalDecision;
|
||||
use codex_app_server_protocol::FileChangeOutputDeltaNotification;
|
||||
use codex_app_server_protocol::FileChangeRequestApprovalResponse;
|
||||
use codex_app_server_protocol::ItemCompletedNotification;
|
||||
@@ -50,7 +49,7 @@ async fn turn_start_emits_notifications_and_accepts_model_override() -> Result<(
|
||||
create_final_assistant_message_sse_response("Done")?,
|
||||
create_final_assistant_message_sse_response("Done")?,
|
||||
];
|
||||
let server = create_mock_responses_server_sequence_unchecked(responses).await;
|
||||
let server = create_mock_chat_completions_server_unchecked(responses).await;
|
||||
|
||||
let codex_home = TempDir::new()?;
|
||||
create_config_toml(codex_home.path(), &server.uri(), "never")?;
|
||||
@@ -157,7 +156,7 @@ async fn turn_start_accepts_local_image_input() -> Result<()> {
|
||||
];
|
||||
// Use the unchecked variant because the request payload includes a LocalImage
|
||||
// which the strict matcher does not currently cover.
|
||||
let server = create_mock_responses_server_sequence_unchecked(responses).await;
|
||||
let server = create_mock_chat_completions_server_unchecked(responses).await;
|
||||
|
||||
let codex_home = TempDir::new()?;
|
||||
create_config_toml(codex_home.path(), &server.uri(), "never")?;
|
||||
@@ -233,7 +232,7 @@ async fn turn_start_exec_approval_toggle_v2() -> Result<()> {
|
||||
)?,
|
||||
create_final_assistant_message_sse_response("done 2")?,
|
||||
];
|
||||
let server = create_mock_responses_server_sequence(responses).await;
|
||||
let server = create_mock_chat_completions_server(responses).await;
|
||||
// Default approval is untrusted to force elicitation on first turn.
|
||||
create_config_toml(codex_home.as_path(), &server.uri(), "untrusted")?;
|
||||
|
||||
@@ -357,7 +356,7 @@ async fn turn_start_exec_approval_decline_v2() -> Result<()> {
|
||||
)?,
|
||||
create_final_assistant_message_sse_response("done")?,
|
||||
];
|
||||
let server = create_mock_responses_server_sequence(responses).await;
|
||||
let server = create_mock_chat_completions_server(responses).await;
|
||||
create_config_toml(codex_home.as_path(), &server.uri(), "untrusted")?;
|
||||
|
||||
let mut mcp = McpProcess::new(codex_home.as_path()).await?;
|
||||
@@ -427,7 +426,7 @@ async fn turn_start_exec_approval_decline_v2() -> Result<()> {
|
||||
mcp.send_response(
|
||||
request_id,
|
||||
serde_json::to_value(CommandExecutionRequestApprovalResponse {
|
||||
decision: CommandExecutionApprovalDecision::Decline,
|
||||
decision: ApprovalDecision::Decline,
|
||||
})?,
|
||||
)
|
||||
.await?;
|
||||
@@ -503,7 +502,7 @@ async fn turn_start_updates_sandbox_and_cwd_between_turns_v2() -> Result<()> {
|
||||
)?,
|
||||
create_final_assistant_message_sse_response("done second")?,
|
||||
];
|
||||
let server = create_mock_responses_server_sequence(responses).await;
|
||||
let server = create_mock_chat_completions_server(responses).await;
|
||||
create_config_toml(&codex_home, &server.uri(), "untrusted")?;
|
||||
|
||||
let mut mcp = McpProcess::new(&codex_home).await?;
|
||||
@@ -554,7 +553,6 @@ async fn turn_start_updates_sandbox_and_cwd_between_turns_v2() -> Result<()> {
|
||||
mcp.read_stream_until_notification_message("codex/event/task_complete"),
|
||||
)
|
||||
.await??;
|
||||
mcp.clear_message_buffer();
|
||||
|
||||
// second turn with workspace-write and second_cwd, ensure exec begins in second_cwd
|
||||
let second_turn = mcp
|
||||
@@ -637,7 +635,7 @@ async fn turn_start_file_change_approval_v2() -> Result<()> {
|
||||
create_apply_patch_sse_response(patch, "patch-call")?,
|
||||
create_final_assistant_message_sse_response("patch applied")?,
|
||||
];
|
||||
let server = create_mock_responses_server_sequence(responses).await;
|
||||
let server = create_mock_chat_completions_server(responses).await;
|
||||
create_config_toml(&codex_home, &server.uri(), "untrusted")?;
|
||||
|
||||
let mut mcp = McpProcess::new(&codex_home).await?;
|
||||
@@ -724,7 +722,7 @@ async fn turn_start_file_change_approval_v2() -> Result<()> {
|
||||
mcp.send_response(
|
||||
request_id,
|
||||
serde_json::to_value(FileChangeRequestApprovalResponse {
|
||||
decision: FileChangeApprovalDecision::Accept,
|
||||
decision: ApprovalDecision::Accept,
|
||||
})?,
|
||||
)
|
||||
.await?;
|
||||
@@ -784,190 +782,6 @@ async fn turn_start_file_change_approval_v2() -> Result<()> {
|
||||
Ok(())
|
||||
}
|
||||
|
||||
#[tokio::test]
|
||||
async fn turn_start_file_change_approval_accept_for_session_persists_v2() -> Result<()> {
|
||||
skip_if_no_network!(Ok(()));
|
||||
|
||||
let tmp = TempDir::new()?;
|
||||
let codex_home = tmp.path().join("codex_home");
|
||||
std::fs::create_dir(&codex_home)?;
|
||||
let workspace = tmp.path().join("workspace");
|
||||
std::fs::create_dir(&workspace)?;
|
||||
|
||||
let patch_1 = r#"*** Begin Patch
|
||||
*** Add File: README.md
|
||||
+new line
|
||||
*** End Patch
|
||||
"#;
|
||||
let patch_2 = r#"*** Begin Patch
|
||||
*** Update File: README.md
|
||||
@@
|
||||
-new line
|
||||
+updated line
|
||||
*** End Patch
|
||||
"#;
|
||||
|
||||
let responses = vec![
|
||||
create_apply_patch_sse_response(patch_1, "patch-call-1")?,
|
||||
create_final_assistant_message_sse_response("patch 1 applied")?,
|
||||
create_apply_patch_sse_response(patch_2, "patch-call-2")?,
|
||||
create_final_assistant_message_sse_response("patch 2 applied")?,
|
||||
];
|
||||
let server = create_mock_responses_server_sequence(responses).await;
|
||||
create_config_toml(&codex_home, &server.uri(), "untrusted")?;
|
||||
|
||||
let mut mcp = McpProcess::new(&codex_home).await?;
|
||||
timeout(DEFAULT_READ_TIMEOUT, mcp.initialize()).await??;
|
||||
|
||||
let start_req = mcp
|
||||
.send_thread_start_request(ThreadStartParams {
|
||||
model: Some("mock-model".to_string()),
|
||||
cwd: Some(workspace.to_string_lossy().into_owned()),
|
||||
..Default::default()
|
||||
})
|
||||
.await?;
|
||||
let start_resp: JSONRPCResponse = timeout(
|
||||
DEFAULT_READ_TIMEOUT,
|
||||
mcp.read_stream_until_response_message(RequestId::Integer(start_req)),
|
||||
)
|
||||
.await??;
|
||||
let ThreadStartResponse { thread, .. } = to_response::<ThreadStartResponse>(start_resp)?;
|
||||
|
||||
// First turn: expect FileChangeRequestApproval, respond with AcceptForSession, and verify the file exists.
|
||||
let turn_1_req = mcp
|
||||
.send_turn_start_request(TurnStartParams {
|
||||
thread_id: thread.id.clone(),
|
||||
input: vec![V2UserInput::Text {
|
||||
text: "apply patch 1".into(),
|
||||
}],
|
||||
cwd: Some(workspace.clone()),
|
||||
..Default::default()
|
||||
})
|
||||
.await?;
|
||||
let turn_1_resp: JSONRPCResponse = timeout(
|
||||
DEFAULT_READ_TIMEOUT,
|
||||
mcp.read_stream_until_response_message(RequestId::Integer(turn_1_req)),
|
||||
)
|
||||
.await??;
|
||||
let TurnStartResponse { turn: turn_1 } = to_response::<TurnStartResponse>(turn_1_resp)?;
|
||||
|
||||
let started_file_change_1 = timeout(DEFAULT_READ_TIMEOUT, async {
|
||||
loop {
|
||||
let started_notif = mcp
|
||||
.read_stream_until_notification_message("item/started")
|
||||
.await?;
|
||||
let started: ItemStartedNotification =
|
||||
serde_json::from_value(started_notif.params.clone().expect("item/started params"))?;
|
||||
if let ThreadItem::FileChange { .. } = started.item {
|
||||
return Ok::<ThreadItem, anyhow::Error>(started.item);
|
||||
}
|
||||
}
|
||||
})
|
||||
.await??;
|
||||
let ThreadItem::FileChange { id, status, .. } = started_file_change_1 else {
|
||||
unreachable!("loop ensures we break on file change items");
|
||||
};
|
||||
assert_eq!(id, "patch-call-1");
|
||||
assert_eq!(status, PatchApplyStatus::InProgress);
|
||||
|
||||
let server_req = timeout(
|
||||
DEFAULT_READ_TIMEOUT,
|
||||
mcp.read_stream_until_request_message(),
|
||||
)
|
||||
.await??;
|
||||
let ServerRequest::FileChangeRequestApproval { request_id, params } = server_req else {
|
||||
panic!("expected FileChangeRequestApproval request")
|
||||
};
|
||||
assert_eq!(params.item_id, "patch-call-1");
|
||||
assert_eq!(params.thread_id, thread.id);
|
||||
assert_eq!(params.turn_id, turn_1.id);
|
||||
|
||||
mcp.send_response(
|
||||
request_id,
|
||||
serde_json::to_value(FileChangeRequestApprovalResponse {
|
||||
decision: FileChangeApprovalDecision::AcceptForSession,
|
||||
})?,
|
||||
)
|
||||
.await?;
|
||||
|
||||
timeout(
|
||||
DEFAULT_READ_TIMEOUT,
|
||||
mcp.read_stream_until_notification_message("item/fileChange/outputDelta"),
|
||||
)
|
||||
.await??;
|
||||
timeout(
|
||||
DEFAULT_READ_TIMEOUT,
|
||||
mcp.read_stream_until_notification_message("item/completed"),
|
||||
)
|
||||
.await??;
|
||||
timeout(
|
||||
DEFAULT_READ_TIMEOUT,
|
||||
mcp.read_stream_until_notification_message("codex/event/task_complete"),
|
||||
)
|
||||
.await??;
|
||||
|
||||
let readme_path = workspace.join("README.md");
|
||||
assert_eq!(std::fs::read_to_string(&readme_path)?, "new line\n");
|
||||
|
||||
// Second turn: apply a patch to the same file. Approval should be skipped due to AcceptForSession.
|
||||
let turn_2_req = mcp
|
||||
.send_turn_start_request(TurnStartParams {
|
||||
thread_id: thread.id.clone(),
|
||||
input: vec![V2UserInput::Text {
|
||||
text: "apply patch 2".into(),
|
||||
}],
|
||||
cwd: Some(workspace.clone()),
|
||||
..Default::default()
|
||||
})
|
||||
.await?;
|
||||
timeout(
|
||||
DEFAULT_READ_TIMEOUT,
|
||||
mcp.read_stream_until_response_message(RequestId::Integer(turn_2_req)),
|
||||
)
|
||||
.await??;
|
||||
|
||||
let started_file_change_2 = timeout(DEFAULT_READ_TIMEOUT, async {
|
||||
loop {
|
||||
let started_notif = mcp
|
||||
.read_stream_until_notification_message("item/started")
|
||||
.await?;
|
||||
let started: ItemStartedNotification =
|
||||
serde_json::from_value(started_notif.params.clone().expect("item/started params"))?;
|
||||
if let ThreadItem::FileChange { .. } = started.item {
|
||||
return Ok::<ThreadItem, anyhow::Error>(started.item);
|
||||
}
|
||||
}
|
||||
})
|
||||
.await??;
|
||||
let ThreadItem::FileChange { id, status, .. } = started_file_change_2 else {
|
||||
unreachable!("loop ensures we break on file change items");
|
||||
};
|
||||
assert_eq!(id, "patch-call-2");
|
||||
assert_eq!(status, PatchApplyStatus::InProgress);
|
||||
|
||||
// If the server incorrectly emits FileChangeRequestApproval, the helper below will error
|
||||
// (it bails on unexpected JSONRPCMessage::Request), causing the test to fail.
|
||||
timeout(
|
||||
DEFAULT_READ_TIMEOUT,
|
||||
mcp.read_stream_until_notification_message("item/fileChange/outputDelta"),
|
||||
)
|
||||
.await??;
|
||||
timeout(
|
||||
DEFAULT_READ_TIMEOUT,
|
||||
mcp.read_stream_until_notification_message("item/completed"),
|
||||
)
|
||||
.await??;
|
||||
timeout(
|
||||
DEFAULT_READ_TIMEOUT,
|
||||
mcp.read_stream_until_notification_message("codex/event/task_complete"),
|
||||
)
|
||||
.await??;
|
||||
|
||||
assert_eq!(std::fs::read_to_string(readme_path)?, "updated line\n");
|
||||
|
||||
Ok(())
|
||||
}
|
||||
|
||||
#[tokio::test]
|
||||
async fn turn_start_file_change_approval_decline_v2() -> Result<()> {
|
||||
skip_if_no_network!(Ok(()));
|
||||
@@ -987,7 +801,7 @@ async fn turn_start_file_change_approval_decline_v2() -> Result<()> {
|
||||
create_apply_patch_sse_response(patch, "patch-call")?,
|
||||
create_final_assistant_message_sse_response("patch declined")?,
|
||||
];
|
||||
let server = create_mock_responses_server_sequence(responses).await;
|
||||
let server = create_mock_chat_completions_server(responses).await;
|
||||
create_config_toml(&codex_home, &server.uri(), "untrusted")?;
|
||||
|
||||
let mut mcp = McpProcess::new(&codex_home).await?;
|
||||
@@ -1074,7 +888,7 @@ async fn turn_start_file_change_approval_decline_v2() -> Result<()> {
|
||||
mcp.send_response(
|
||||
request_id,
|
||||
serde_json::to_value(FileChangeRequestApprovalResponse {
|
||||
decision: FileChangeApprovalDecision::Decline,
|
||||
decision: ApprovalDecision::Decline,
|
||||
})?,
|
||||
)
|
||||
.await?;
|
||||
@@ -1125,7 +939,7 @@ async fn command_execution_notifications_include_process_id() -> Result<()> {
|
||||
create_exec_command_sse_response("uexec-1")?,
|
||||
create_final_assistant_message_sse_response("done")?,
|
||||
];
|
||||
let server = create_mock_responses_server_sequence(responses).await;
|
||||
let server = create_mock_chat_completions_server(responses).await;
|
||||
let codex_home = TempDir::new()?;
|
||||
create_config_toml(codex_home.path(), &server.uri(), "never")?;
|
||||
let config_toml = codex_home.path().join("config.toml");
|
||||
@@ -1264,7 +1078,7 @@ model_provider = "mock_provider"
|
||||
[model_providers.mock_provider]
|
||||
name = "Mock provider for test"
|
||||
base_url = "{server_uri}/v1"
|
||||
wire_api = "responses"
|
||||
wire_api = "chat"
|
||||
request_max_retries = 0
|
||||
stream_max_retries = 0
|
||||
"#
|
||||
|
||||
@@ -227,14 +227,11 @@ fn check_start_and_end_lines_strict(
|
||||
first_line: Option<&&str>,
|
||||
last_line: Option<&&str>,
|
||||
) -> Result<(), ParseError> {
|
||||
let first_line = first_line.map(|line| line.trim());
|
||||
let last_line = last_line.map(|line| line.trim());
|
||||
|
||||
match (first_line, last_line) {
|
||||
(Some(first), Some(last)) if first == BEGIN_PATCH_MARKER && last == END_PATCH_MARKER => {
|
||||
(Some(&first), Some(&last)) if first == BEGIN_PATCH_MARKER && last == END_PATCH_MARKER => {
|
||||
Ok(())
|
||||
}
|
||||
(Some(first), _) if first != BEGIN_PATCH_MARKER => Err(InvalidPatchError(String::from(
|
||||
(Some(&first), _) if first != BEGIN_PATCH_MARKER => Err(InvalidPatchError(String::from(
|
||||
"The first line of the patch must be '*** Begin Patch'",
|
||||
))),
|
||||
_ => Err(InvalidPatchError(String::from(
|
||||
@@ -447,25 +444,6 @@ fn test_parse_patch() {
|
||||
"The last line of the patch must be '*** End Patch'".to_string()
|
||||
))
|
||||
);
|
||||
|
||||
assert_eq!(
|
||||
parse_patch_text(
|
||||
concat!(
|
||||
"*** Begin Patch",
|
||||
" ",
|
||||
"\n*** Add File: foo\n+hi\n",
|
||||
" ",
|
||||
"*** End Patch"
|
||||
),
|
||||
ParseMode::Strict
|
||||
)
|
||||
.unwrap()
|
||||
.hunks,
|
||||
vec![AddFile {
|
||||
path: PathBuf::from("foo"),
|
||||
contents: "hi\n".to_string()
|
||||
}]
|
||||
);
|
||||
assert_eq!(
|
||||
parse_patch_text(
|
||||
"*** Begin Patch\n\
|
||||
|
||||
@@ -1 +0,0 @@
|
||||
keep
|
||||
@@ -1 +0,0 @@
|
||||
keep
|
||||
@@ -1 +0,0 @@
|
||||
obsolete
|
||||
@@ -1,3 +0,0 @@
|
||||
*** Begin Patch
|
||||
*** Delete File: obsolete.txt
|
||||
*** End Patch
|
||||
@@ -1 +0,0 @@
|
||||
two
|
||||
@@ -1 +0,0 @@
|
||||
one
|
||||
@@ -1,6 +0,0 @@
|
||||
*** Begin Patch
|
||||
*** Update File: file.txt
|
||||
@@
|
||||
-one
|
||||
+two
|
||||
*** End Patch
|
||||
@@ -1,2 +0,0 @@
|
||||
line1
|
||||
line3
|
||||
@@ -1,3 +0,0 @@
|
||||
line1
|
||||
line2
|
||||
line3
|
||||
@@ -1,7 +0,0 @@
|
||||
*** Begin Patch
|
||||
*** Update File: lines.txt
|
||||
@@
|
||||
line1
|
||||
-line2
|
||||
line3
|
||||
*** End Patch
|
||||
@@ -1,2 +0,0 @@
|
||||
first
|
||||
second updated
|
||||
@@ -1,2 +0,0 @@
|
||||
first
|
||||
second
|
||||
@@ -1,8 +0,0 @@
|
||||
*** Begin Patch
|
||||
*** Update File: tail.txt
|
||||
@@
|
||||
first
|
||||
-second
|
||||
+second updated
|
||||
*** End of File
|
||||
*** End Patch
|
||||
@@ -1,4 +1,3 @@
|
||||
use codex_utils_cargo_bin::find_resource;
|
||||
use pretty_assertions::assert_eq;
|
||||
use std::collections::BTreeMap;
|
||||
use std::fs;
|
||||
@@ -9,7 +8,7 @@ use tempfile::tempdir;
|
||||
|
||||
#[test]
|
||||
fn test_apply_patch_scenarios() -> anyhow::Result<()> {
|
||||
let scenarios_dir = find_resource!("tests/fixtures/scenarios")?;
|
||||
let scenarios_dir = Path::new(env!("CARGO_MANIFEST_DIR")).join("tests/fixtures/scenarios");
|
||||
for scenario in fs::read_dir(scenarios_dir)? {
|
||||
let scenario = scenario?;
|
||||
let path = scenario.path();
|
||||
|
||||
@@ -73,8 +73,8 @@ impl Client {
|
||||
})
|
||||
}
|
||||
|
||||
pub fn from_auth(base_url: impl Into<String>, auth: &CodexAuth) -> Result<Self> {
|
||||
let token = auth.get_token().map_err(anyhow::Error::from)?;
|
||||
pub async fn from_auth(base_url: impl Into<String>, auth: &CodexAuth) -> Result<Self> {
|
||||
let token = auth.get_token().await.map_err(anyhow::Error::from)?;
|
||||
let mut client = Self::new(base_url)?
|
||||
.with_user_agent(get_codex_user_agent())
|
||||
.with_bearer_token(token);
|
||||
|
||||
@@ -12,7 +12,6 @@ anyhow = { workspace = true }
|
||||
clap = { workspace = true, features = ["derive"] }
|
||||
codex-common = { workspace = true, features = ["cli"] }
|
||||
codex-core = { workspace = true }
|
||||
codex-utils-cargo-bin = { workspace = true }
|
||||
serde = { workspace = true, features = ["derive"] }
|
||||
serde_json = { workspace = true }
|
||||
tokio = { workspace = true, features = ["full"] }
|
||||
|
||||
@@ -1,4 +1,4 @@
|
||||
use codex_core::AuthManager;
|
||||
use codex_core::CodexAuth;
|
||||
use std::path::Path;
|
||||
use std::sync::LazyLock;
|
||||
use std::sync::RwLock;
|
||||
@@ -23,10 +23,9 @@ pub async fn init_chatgpt_token_from_auth(
|
||||
codex_home: &Path,
|
||||
auth_credentials_store_mode: AuthCredentialsStoreMode,
|
||||
) -> std::io::Result<()> {
|
||||
let auth_manager =
|
||||
AuthManager::new(codex_home.to_path_buf(), false, auth_credentials_store_mode);
|
||||
if let Some(auth) = auth_manager.auth().await {
|
||||
let token_data = auth.get_token_data()?;
|
||||
let auth = CodexAuth::from_auth_storage(codex_home, auth_credentials_store_mode)?;
|
||||
if let Some(auth) = auth {
|
||||
let token_data = auth.get_token_data().await?;
|
||||
set_chatgpt_token_data(token_data);
|
||||
}
|
||||
Ok(())
|
||||
|
||||
@@ -1,6 +1,6 @@
|
||||
use codex_chatgpt::apply_command::apply_diff_from_task;
|
||||
use codex_chatgpt::get_task::GetTaskResponse;
|
||||
use codex_utils_cargo_bin::find_resource;
|
||||
use std::path::Path;
|
||||
use tempfile::TempDir;
|
||||
use tokio::process::Command;
|
||||
|
||||
@@ -68,8 +68,8 @@ async fn create_temp_git_repo() -> anyhow::Result<TempDir> {
|
||||
}
|
||||
|
||||
async fn mock_get_task_with_fixture() -> anyhow::Result<GetTaskResponse> {
|
||||
let fixture_path = find_resource!("tests/task_turn_fixture.json")?;
|
||||
let fixture_content = tokio::fs::read_to_string(fixture_path).await?;
|
||||
let fixture_path = Path::new(env!("CARGO_MANIFEST_DIR")).join("tests/task_turn_fixture.json");
|
||||
let fixture_content = std::fs::read_to_string(fixture_path)?;
|
||||
let response: GetTaskResponse = serde_json::from_str(&fixture_content)?;
|
||||
Ok(response)
|
||||
}
|
||||
|
||||
@@ -30,6 +30,7 @@ codex-exec = { workspace = true }
|
||||
codex-execpolicy = { workspace = true }
|
||||
codex-login = { workspace = true }
|
||||
codex-mcp-server = { workspace = true }
|
||||
codex-process-hardening = { workspace = true }
|
||||
codex-protocol = { workspace = true }
|
||||
codex-responses-api-proxy = { workspace = true }
|
||||
codex-rmcp-client = { workspace = true }
|
||||
@@ -37,6 +38,7 @@ codex-stdio-to-uds = { workspace = true }
|
||||
codex-tui = { workspace = true }
|
||||
codex-tui2 = { workspace = true }
|
||||
codex-utils-absolute-path = { workspace = true }
|
||||
ctor = { workspace = true }
|
||||
libc = { workspace = true }
|
||||
owo-colors = { workspace = true }
|
||||
regex-lite = { workspace = true }
|
||||
|
||||
@@ -155,7 +155,7 @@ pub async fn run_login_status(cli_config_overrides: CliConfigOverrides) -> ! {
|
||||
|
||||
match CodexAuth::from_auth_storage(&config.codex_home, config.cli_auth_credentials_store_mode) {
|
||||
Ok(Some(auth)) => match auth.mode {
|
||||
AuthMode::ApiKey => match auth.get_token() {
|
||||
AuthMode::ApiKey => match auth.get_token().await {
|
||||
Ok(api_key) => {
|
||||
eprintln!("Logged in using an API key - {}", safe_format_key(&api_key));
|
||||
std::process::exit(0);
|
||||
|
||||
@@ -283,7 +283,7 @@ struct StdioToUdsCommand {
|
||||
fn format_exit_messages(exit_info: AppExitInfo, color_enabled: bool) -> Vec<String> {
|
||||
let AppExitInfo {
|
||||
token_usage,
|
||||
thread_id: conversation_id,
|
||||
conversation_id,
|
||||
..
|
||||
} = exit_info;
|
||||
|
||||
@@ -418,6 +418,14 @@ fn stage_str(stage: codex_core::features::Stage) -> &'static str {
|
||||
}
|
||||
}
|
||||
|
||||
/// As early as possible in the process lifecycle, apply hardening measures. We
|
||||
/// skip this in debug builds to avoid interfering with debugging.
|
||||
#[ctor::ctor]
|
||||
#[cfg(not(debug_assertions))]
|
||||
fn pre_main_hardening() {
|
||||
codex_process_hardening::pre_main_hardening();
|
||||
}
|
||||
|
||||
fn main() -> anyhow::Result<()> {
|
||||
arg0_dispatch_or_else(|codex_linux_sandbox_exe| async move {
|
||||
cli_main(codex_linux_sandbox_exe).await?;
|
||||
@@ -472,12 +480,7 @@ async fn cli_main(codex_linux_sandbox_exe: Option<PathBuf>) -> anyhow::Result<()
|
||||
}
|
||||
Some(Subcommand::AppServer(app_server_cli)) => match app_server_cli.subcommand {
|
||||
None => {
|
||||
codex_app_server::run_main(
|
||||
codex_linux_sandbox_exe,
|
||||
root_config_overrides,
|
||||
codex_core::config_loader::LoaderOverrides::default(),
|
||||
)
|
||||
.await?;
|
||||
codex_app_server::run_main(codex_linux_sandbox_exe, root_config_overrides).await?;
|
||||
}
|
||||
Some(AppServerSubcommand::GenerateTs(gen_cli)) => {
|
||||
codex_app_server_protocol::generate_ts(
|
||||
@@ -782,7 +785,7 @@ mod tests {
|
||||
use super::*;
|
||||
use assert_matches::assert_matches;
|
||||
use codex_core::protocol::TokenUsage;
|
||||
use codex_protocol::ThreadId;
|
||||
use codex_protocol::ConversationId;
|
||||
use pretty_assertions::assert_eq;
|
||||
|
||||
fn finalize_from_args(args: &[&str]) -> TuiCli {
|
||||
@@ -822,7 +825,9 @@ mod tests {
|
||||
};
|
||||
AppExitInfo {
|
||||
token_usage,
|
||||
thread_id: conversation.map(ThreadId::from_string).map(Result::unwrap),
|
||||
conversation_id: conversation
|
||||
.map(ConversationId::from_string)
|
||||
.map(Result::unwrap),
|
||||
update_action: None,
|
||||
}
|
||||
}
|
||||
@@ -831,7 +836,7 @@ mod tests {
|
||||
fn format_exit_messages_skips_zero_usage() {
|
||||
let exit_info = AppExitInfo {
|
||||
token_usage: TokenUsage::default(),
|
||||
thread_id: None,
|
||||
conversation_id: None,
|
||||
update_action: None,
|
||||
};
|
||||
let lines = format_exit_messages(exit_info, false);
|
||||
|
||||
@@ -59,61 +59,3 @@ prefix_rule(
|
||||
|
||||
Ok(())
|
||||
}
|
||||
|
||||
#[test]
|
||||
fn execpolicy_check_includes_justification_when_present() -> Result<(), Box<dyn std::error::Error>>
|
||||
{
|
||||
let codex_home = TempDir::new()?;
|
||||
let policy_path = codex_home.path().join("rules").join("policy.rules");
|
||||
fs::create_dir_all(
|
||||
policy_path
|
||||
.parent()
|
||||
.expect("policy path should have a parent"),
|
||||
)?;
|
||||
fs::write(
|
||||
&policy_path,
|
||||
r#"
|
||||
prefix_rule(
|
||||
pattern = ["git", "push"],
|
||||
decision = "forbidden",
|
||||
justification = "pushing is blocked in this repo",
|
||||
)
|
||||
"#,
|
||||
)?;
|
||||
|
||||
let output = Command::new(codex_utils_cargo_bin::cargo_bin("codex")?)
|
||||
.env("CODEX_HOME", codex_home.path())
|
||||
.args([
|
||||
"execpolicy",
|
||||
"check",
|
||||
"--rules",
|
||||
policy_path
|
||||
.to_str()
|
||||
.expect("policy path should be valid UTF-8"),
|
||||
"git",
|
||||
"push",
|
||||
"origin",
|
||||
"main",
|
||||
])
|
||||
.output()?;
|
||||
|
||||
assert!(output.status.success());
|
||||
let result: serde_json::Value = serde_json::from_slice(&output.stdout)?;
|
||||
assert_eq!(
|
||||
result,
|
||||
json!({
|
||||
"decision": "forbidden",
|
||||
"matchedRules": [
|
||||
{
|
||||
"prefixRuleMatch": {
|
||||
"matchedPrefix": ["git", "push"],
|
||||
"decision": "forbidden",
|
||||
"justification": "pushing is blocked in this repo"
|
||||
}
|
||||
}
|
||||
]
|
||||
})
|
||||
);
|
||||
|
||||
Ok(())
|
||||
}
|
||||
|
||||
@@ -10,6 +10,7 @@ pub use cli::Cli;
|
||||
use anyhow::anyhow;
|
||||
use chrono::Utc;
|
||||
use codex_cloud_tasks_client::TaskStatus;
|
||||
use codex_login::AuthManager;
|
||||
use owo_colors::OwoColorize;
|
||||
use owo_colors::Stream;
|
||||
use std::cmp::Ordering;
|
||||
@@ -64,11 +65,7 @@ async fn init_backend(user_agent_suffix: &str) -> anyhow::Result<BackendContext>
|
||||
append_error_log(format!("startup: base_url={base_url} path_style={style}"));
|
||||
|
||||
let auth_manager = util::load_auth_manager().await;
|
||||
let auth = match auth_manager.as_ref() {
|
||||
Some(manager) => manager.auth().await,
|
||||
None => None,
|
||||
};
|
||||
let auth = match auth {
|
||||
let auth = match auth_manager.as_ref().and_then(AuthManager::auth) {
|
||||
Some(auth) => auth,
|
||||
None => {
|
||||
eprintln!(
|
||||
@@ -82,7 +79,7 @@ async fn init_backend(user_agent_suffix: &str) -> anyhow::Result<BackendContext>
|
||||
append_error_log(format!("auth: mode=ChatGPT account_id={acc}"));
|
||||
}
|
||||
|
||||
let token = match auth.get_token() {
|
||||
let token = match auth.get_token().await {
|
||||
Ok(t) if !t.is_empty() => t,
|
||||
_ => {
|
||||
eprintln!(
|
||||
|
||||
@@ -85,8 +85,8 @@ pub async fn build_chatgpt_headers() -> HeaderMap {
|
||||
HeaderValue::from_str(&ua).unwrap_or(HeaderValue::from_static("codex-cli")),
|
||||
);
|
||||
if let Some(am) = load_auth_manager().await
|
||||
&& let Some(auth) = am.auth().await
|
||||
&& let Ok(tok) = auth.get_token()
|
||||
&& let Some(auth) = am.auth()
|
||||
&& let Ok(tok) = auth.get_token().await
|
||||
&& !tok.is_empty()
|
||||
{
|
||||
let v = format!("Bearer {tok}");
|
||||
|
||||
@@ -10,7 +10,6 @@ use crate::provider::WireApi;
|
||||
use crate::sse::chat::spawn_chat_stream;
|
||||
use crate::telemetry::SseTelemetry;
|
||||
use codex_client::HttpTransport;
|
||||
use codex_client::RequestCompression;
|
||||
use codex_client::RequestTelemetry;
|
||||
use codex_protocol::models::ContentItem;
|
||||
use codex_protocol::models::ReasoningItemContent;
|
||||
@@ -81,13 +80,7 @@ impl<T: HttpTransport, A: AuthProvider> ChatClient<T, A> {
|
||||
extra_headers: HeaderMap,
|
||||
) -> Result<ResponseStream, ApiError> {
|
||||
self.streaming
|
||||
.stream(
|
||||
self.path(),
|
||||
body,
|
||||
extra_headers,
|
||||
RequestCompression::None,
|
||||
spawn_chat_stream,
|
||||
)
|
||||
.stream(self.path(), body, extra_headers, spawn_chat_stream)
|
||||
.await
|
||||
}
|
||||
}
|
||||
|
||||
@@ -215,14 +215,14 @@ mod tests {
|
||||
"supported_in_api": true,
|
||||
"priority": 1,
|
||||
"upgrade": null,
|
||||
"base_instructions": "base instructions",
|
||||
"base_instructions": null,
|
||||
"supports_reasoning_summaries": false,
|
||||
"support_verbosity": false,
|
||||
"default_verbosity": null,
|
||||
"apply_patch_tool_type": null,
|
||||
"truncation_policy": {"mode": "bytes", "limit": 10_000},
|
||||
"supports_parallel_tool_calls": false,
|
||||
"context_window": 272_000,
|
||||
"context_window": null,
|
||||
"experimental_supported_tools": [],
|
||||
}))
|
||||
.unwrap(),
|
||||
|
||||
@@ -9,11 +9,9 @@ use crate::provider::Provider;
|
||||
use crate::provider::WireApi;
|
||||
use crate::requests::ResponsesRequest;
|
||||
use crate::requests::ResponsesRequestBuilder;
|
||||
use crate::requests::responses::Compression;
|
||||
use crate::sse::spawn_response_stream;
|
||||
use crate::telemetry::SseTelemetry;
|
||||
use codex_client::HttpTransport;
|
||||
use codex_client::RequestCompression;
|
||||
use codex_client::RequestTelemetry;
|
||||
use codex_protocol::protocol::SessionSource;
|
||||
use http::HeaderMap;
|
||||
@@ -35,7 +33,6 @@ pub struct ResponsesOptions {
|
||||
pub conversation_id: Option<String>,
|
||||
pub session_source: Option<SessionSource>,
|
||||
pub extra_headers: HeaderMap,
|
||||
pub compression: Compression,
|
||||
}
|
||||
|
||||
impl<T: HttpTransport, A: AuthProvider> ResponsesClient<T, A> {
|
||||
@@ -59,8 +56,7 @@ impl<T: HttpTransport, A: AuthProvider> ResponsesClient<T, A> {
|
||||
&self,
|
||||
request: ResponsesRequest,
|
||||
) -> Result<ResponseStream, ApiError> {
|
||||
self.stream(request.body, request.headers, request.compression)
|
||||
.await
|
||||
self.stream(request.body, request.headers).await
|
||||
}
|
||||
|
||||
#[instrument(level = "trace", skip_all, err)]
|
||||
@@ -79,7 +75,6 @@ impl<T: HttpTransport, A: AuthProvider> ResponsesClient<T, A> {
|
||||
conversation_id,
|
||||
session_source,
|
||||
extra_headers,
|
||||
compression,
|
||||
} = options;
|
||||
|
||||
let request = ResponsesRequestBuilder::new(model, &prompt.instructions, &prompt.input)
|
||||
@@ -93,7 +88,6 @@ impl<T: HttpTransport, A: AuthProvider> ResponsesClient<T, A> {
|
||||
.session_source(session_source)
|
||||
.store_override(store_override)
|
||||
.extra_headers(extra_headers)
|
||||
.compression(compression)
|
||||
.build(self.streaming.provider())?;
|
||||
|
||||
self.stream_request(request).await
|
||||
@@ -110,21 +104,9 @@ impl<T: HttpTransport, A: AuthProvider> ResponsesClient<T, A> {
|
||||
&self,
|
||||
body: Value,
|
||||
extra_headers: HeaderMap,
|
||||
compression: Compression,
|
||||
) -> Result<ResponseStream, ApiError> {
|
||||
let compression = match compression {
|
||||
Compression::None => RequestCompression::None,
|
||||
Compression::Zstd => RequestCompression::Zstd,
|
||||
};
|
||||
|
||||
self.streaming
|
||||
.stream(
|
||||
self.path(),
|
||||
body,
|
||||
extra_headers,
|
||||
compression,
|
||||
spawn_response_stream,
|
||||
)
|
||||
.stream(self.path(), body, extra_headers, spawn_response_stream)
|
||||
.await
|
||||
}
|
||||
}
|
||||
|
||||
@@ -6,7 +6,6 @@ use crate::provider::Provider;
|
||||
use crate::telemetry::SseTelemetry;
|
||||
use crate::telemetry::run_with_request_telemetry;
|
||||
use codex_client::HttpTransport;
|
||||
use codex_client::RequestCompression;
|
||||
use codex_client::RequestTelemetry;
|
||||
use codex_client::StreamResponse;
|
||||
use http::HeaderMap;
|
||||
@@ -53,7 +52,6 @@ impl<T: HttpTransport, A: AuthProvider> StreamingClient<T, A> {
|
||||
path: &str,
|
||||
body: Value,
|
||||
extra_headers: HeaderMap,
|
||||
compression: RequestCompression,
|
||||
spawner: fn(StreamResponse, Duration, Option<Arc<dyn SseTelemetry>>) -> ResponseStream,
|
||||
) -> Result<ResponseStream, ApiError> {
|
||||
let builder = || {
|
||||
@@ -64,7 +62,6 @@ impl<T: HttpTransport, A: AuthProvider> StreamingClient<T, A> {
|
||||
http::HeaderValue::from_static("text/event-stream"),
|
||||
);
|
||||
req.body = Some(body.clone());
|
||||
req.compression = compression;
|
||||
add_auth_headers(&self.auth, req)
|
||||
};
|
||||
|
||||
|
||||
@@ -1,5 +1,4 @@
|
||||
use codex_client::Request;
|
||||
use codex_client::RequestCompression;
|
||||
use codex_client::RetryOn;
|
||||
use codex_client::RetryPolicy;
|
||||
use http::Method;
|
||||
@@ -88,7 +87,6 @@ impl Provider {
|
||||
url: self.url_for_path(path),
|
||||
headers: self.headers.clone(),
|
||||
body: None,
|
||||
compression: RequestCompression::None,
|
||||
timeout: None,
|
||||
}
|
||||
}
|
||||
|
||||
@@ -11,18 +11,10 @@ use codex_protocol::protocol::SessionSource;
|
||||
use http::HeaderMap;
|
||||
use serde_json::Value;
|
||||
|
||||
#[derive(Debug, Clone, Copy, Default, PartialEq, Eq)]
|
||||
pub enum Compression {
|
||||
#[default]
|
||||
None,
|
||||
Zstd,
|
||||
}
|
||||
|
||||
/// Assembled request body plus headers for a Responses stream request.
|
||||
pub struct ResponsesRequest {
|
||||
pub body: Value,
|
||||
pub headers: HeaderMap,
|
||||
pub compression: Compression,
|
||||
}
|
||||
|
||||
#[derive(Default)]
|
||||
@@ -40,7 +32,6 @@ pub struct ResponsesRequestBuilder<'a> {
|
||||
session_source: Option<SessionSource>,
|
||||
store_override: Option<bool>,
|
||||
headers: HeaderMap,
|
||||
compression: Compression,
|
||||
}
|
||||
|
||||
impl<'a> ResponsesRequestBuilder<'a> {
|
||||
@@ -103,11 +94,6 @@ impl<'a> ResponsesRequestBuilder<'a> {
|
||||
self
|
||||
}
|
||||
|
||||
pub fn compression(mut self, compression: Compression) -> Self {
|
||||
self.compression = compression;
|
||||
self
|
||||
}
|
||||
|
||||
pub fn build(self, provider: &Provider) -> Result<ResponsesRequest, ApiError> {
|
||||
let model = self
|
||||
.model
|
||||
@@ -152,11 +138,7 @@ impl<'a> ResponsesRequestBuilder<'a> {
|
||||
insert_header(&mut headers, "x-openai-subagent", &subagent);
|
||||
}
|
||||
|
||||
Ok(ResponsesRequest {
|
||||
body,
|
||||
headers,
|
||||
compression: self.compression,
|
||||
})
|
||||
Ok(ResponsesRequest { body, headers })
|
||||
}
|
||||
}
|
||||
|
||||
|
||||
@@ -11,7 +11,6 @@ use codex_api::Provider;
|
||||
use codex_api::ResponsesClient;
|
||||
use codex_api::ResponsesOptions;
|
||||
use codex_api::WireApi;
|
||||
use codex_api::requests::responses::Compression;
|
||||
use codex_client::HttpTransport;
|
||||
use codex_client::Request;
|
||||
use codex_client::Response;
|
||||
@@ -230,9 +229,7 @@ async fn responses_client_uses_responses_path_for_responses_wire() -> Result<()>
|
||||
let client = ResponsesClient::new(transport, provider("openai", WireApi::Responses), NoAuth);
|
||||
|
||||
let body = serde_json::json!({ "echo": true });
|
||||
let _stream = client
|
||||
.stream(body, HeaderMap::new(), Compression::None)
|
||||
.await?;
|
||||
let _stream = client.stream(body, HeaderMap::new()).await?;
|
||||
|
||||
let requests = state.take_stream_requests();
|
||||
assert_path_ends_with(&requests, "/responses");
|
||||
@@ -246,9 +243,7 @@ async fn responses_client_uses_chat_path_for_chat_wire() -> Result<()> {
|
||||
let client = ResponsesClient::new(transport, provider("openai", WireApi::Chat), NoAuth);
|
||||
|
||||
let body = serde_json::json!({ "echo": true });
|
||||
let _stream = client
|
||||
.stream(body, HeaderMap::new(), Compression::None)
|
||||
.await?;
|
||||
let _stream = client.stream(body, HeaderMap::new()).await?;
|
||||
|
||||
let requests = state.take_stream_requests();
|
||||
assert_path_ends_with(&requests, "/chat/completions");
|
||||
@@ -263,9 +258,7 @@ async fn streaming_client_adds_auth_headers() -> Result<()> {
|
||||
let client = ResponsesClient::new(transport, provider("openai", WireApi::Responses), auth);
|
||||
|
||||
let body = serde_json::json!({ "model": "gpt-test" });
|
||||
let _stream = client
|
||||
.stream(body, HeaderMap::new(), Compression::None)
|
||||
.await?;
|
||||
let _stream = client.stream(body, HeaderMap::new()).await?;
|
||||
|
||||
let requests = state.take_stream_requests();
|
||||
assert_eq!(requests.len(), 1);
|
||||
|
||||
@@ -56,7 +56,7 @@ async fn models_client_hits_models_endpoint() {
|
||||
slug: "gpt-test".to_string(),
|
||||
display_name: "gpt-test".to_string(),
|
||||
description: Some("desc".to_string()),
|
||||
default_reasoning_level: Some(ReasoningEffort::Medium),
|
||||
default_reasoning_level: ReasoningEffort::Medium,
|
||||
supported_reasoning_levels: vec![
|
||||
ReasoningEffortPreset {
|
||||
effort: ReasoningEffort::Low,
|
||||
@@ -76,16 +76,14 @@ async fn models_client_hits_models_endpoint() {
|
||||
supported_in_api: true,
|
||||
priority: 1,
|
||||
upgrade: None,
|
||||
base_instructions: "base instructions".to_string(),
|
||||
base_instructions: None,
|
||||
supports_reasoning_summaries: false,
|
||||
support_verbosity: false,
|
||||
default_verbosity: None,
|
||||
apply_patch_tool_type: None,
|
||||
truncation_policy: TruncationPolicyConfig::bytes(10_000),
|
||||
supports_parallel_tool_calls: false,
|
||||
context_window: Some(272_000),
|
||||
auto_compact_token_limit: None,
|
||||
effective_context_window_percent: 95,
|
||||
context_window: None,
|
||||
experimental_supported_tools: Vec::new(),
|
||||
}],
|
||||
};
|
||||
|
||||
@@ -9,7 +9,6 @@ use codex_api::Provider;
|
||||
use codex_api::ResponseEvent;
|
||||
use codex_api::ResponsesClient;
|
||||
use codex_api::WireApi;
|
||||
use codex_api::requests::responses::Compression;
|
||||
use codex_client::HttpTransport;
|
||||
use codex_client::Request;
|
||||
use codex_client::Response;
|
||||
@@ -125,11 +124,7 @@ async fn responses_stream_parses_items_and_completed_end_to_end() -> Result<()>
|
||||
let client = ResponsesClient::new(transport, provider("openai", WireApi::Responses), NoAuth);
|
||||
|
||||
let mut stream = client
|
||||
.stream(
|
||||
serde_json::json!({"echo": true}),
|
||||
HeaderMap::new(),
|
||||
Compression::None,
|
||||
)
|
||||
.stream(serde_json::json!({"echo": true}), HeaderMap::new())
|
||||
.await?;
|
||||
|
||||
let mut events = Vec::new();
|
||||
@@ -194,11 +189,7 @@ async fn responses_stream_aggregates_output_text_deltas() -> Result<()> {
|
||||
let client = ResponsesClient::new(transport, provider("openai", WireApi::Responses), NoAuth);
|
||||
|
||||
let stream = client
|
||||
.stream(
|
||||
serde_json::json!({"echo": true}),
|
||||
HeaderMap::new(),
|
||||
Compression::None,
|
||||
)
|
||||
.stream(serde_json::json!({"echo": true}), HeaderMap::new())
|
||||
.await?;
|
||||
|
||||
let mut stream = stream.aggregate();
|
||||
|
||||
@@ -19,7 +19,6 @@ thiserror = { workspace = true }
|
||||
tokio = { workspace = true, features = ["macros", "rt", "time", "sync"] }
|
||||
tracing = { workspace = true }
|
||||
tracing-opentelemetry = { workspace = true }
|
||||
zstd = { workspace = true }
|
||||
|
||||
[lints]
|
||||
workspace = true
|
||||
|
||||
@@ -104,13 +104,6 @@ impl CodexRequestBuilder {
|
||||
self.map(|builder| builder.json(value))
|
||||
}
|
||||
|
||||
pub fn body<B>(self, body: B) -> Self
|
||||
where
|
||||
B: Into<reqwest::Body>,
|
||||
{
|
||||
self.map(|builder| builder.body(body))
|
||||
}
|
||||
|
||||
pub async fn send(self) -> Result<Response, reqwest::Error> {
|
||||
let headers = trace_headers();
|
||||
|
||||
|
||||
@@ -11,7 +11,6 @@ pub use crate::default_client::CodexRequestBuilder;
|
||||
pub use crate::error::StreamError;
|
||||
pub use crate::error::TransportError;
|
||||
pub use crate::request::Request;
|
||||
pub use crate::request::RequestCompression;
|
||||
pub use crate::request::Response;
|
||||
pub use crate::retry::RetryOn;
|
||||
pub use crate::retry::RetryPolicy;
|
||||
|
||||
@@ -5,20 +5,12 @@ use serde::Serialize;
|
||||
use serde_json::Value;
|
||||
use std::time::Duration;
|
||||
|
||||
#[derive(Debug, Clone, Copy, Default, PartialEq, Eq)]
|
||||
pub enum RequestCompression {
|
||||
#[default]
|
||||
None,
|
||||
Zstd,
|
||||
}
|
||||
|
||||
#[derive(Debug, Clone)]
|
||||
pub struct Request {
|
||||
pub method: Method,
|
||||
pub url: String,
|
||||
pub headers: HeaderMap,
|
||||
pub body: Option<Value>,
|
||||
pub compression: RequestCompression,
|
||||
pub timeout: Option<Duration>,
|
||||
}
|
||||
|
||||
@@ -29,7 +21,6 @@ impl Request {
|
||||
url,
|
||||
headers: HeaderMap::new(),
|
||||
body: None,
|
||||
compression: RequestCompression::None,
|
||||
timeout: None,
|
||||
}
|
||||
}
|
||||
@@ -38,11 +29,6 @@ impl Request {
|
||||
self.body = serde_json::to_value(body).ok();
|
||||
self
|
||||
}
|
||||
|
||||
pub fn with_compression(mut self, compression: RequestCompression) -> Self {
|
||||
self.compression = compression;
|
||||
self
|
||||
}
|
||||
}
|
||||
|
||||
#[derive(Debug, Clone)]
|
||||
|
||||
@@ -2,7 +2,6 @@ use crate::default_client::CodexHttpClient;
|
||||
use crate::default_client::CodexRequestBuilder;
|
||||
use crate::error::TransportError;
|
||||
use crate::request::Request;
|
||||
use crate::request::RequestCompression;
|
||||
use crate::request::Response;
|
||||
use async_trait::async_trait;
|
||||
use bytes::Bytes;
|
||||
@@ -42,70 +41,18 @@ impl ReqwestTransport {
|
||||
}
|
||||
|
||||
fn build(&self, req: Request) -> Result<CodexRequestBuilder, TransportError> {
|
||||
let Request {
|
||||
method,
|
||||
url,
|
||||
mut headers,
|
||||
body,
|
||||
compression,
|
||||
timeout,
|
||||
} = req;
|
||||
|
||||
let mut builder = self.client.request(
|
||||
Method::from_bytes(method.as_str().as_bytes()).unwrap_or(Method::GET),
|
||||
&url,
|
||||
);
|
||||
|
||||
if let Some(timeout) = timeout {
|
||||
let mut builder = self
|
||||
.client
|
||||
.request(
|
||||
Method::from_bytes(req.method.as_str().as_bytes()).unwrap_or(Method::GET),
|
||||
&req.url,
|
||||
)
|
||||
.headers(req.headers);
|
||||
if let Some(timeout) = req.timeout {
|
||||
builder = builder.timeout(timeout);
|
||||
}
|
||||
|
||||
if let Some(body) = body {
|
||||
if compression != RequestCompression::None {
|
||||
if headers.contains_key(http::header::CONTENT_ENCODING) {
|
||||
return Err(TransportError::Build(
|
||||
"request compression was requested but content-encoding is already set"
|
||||
.to_string(),
|
||||
));
|
||||
}
|
||||
|
||||
let json = serde_json::to_vec(&body)
|
||||
.map_err(|err| TransportError::Build(err.to_string()))?;
|
||||
let pre_compression_bytes = json.len();
|
||||
let compression_start = std::time::Instant::now();
|
||||
let (compressed, content_encoding) = match compression {
|
||||
RequestCompression::None => unreachable!("guarded by compression != None"),
|
||||
RequestCompression::Zstd => (
|
||||
zstd::stream::encode_all(std::io::Cursor::new(json), 3)
|
||||
.map_err(|err| TransportError::Build(err.to_string()))?,
|
||||
http::HeaderValue::from_static("zstd"),
|
||||
),
|
||||
};
|
||||
let post_compression_bytes = compressed.len();
|
||||
let compression_duration = compression_start.elapsed();
|
||||
|
||||
// Ensure the server knows to unpack the request body.
|
||||
headers.insert(http::header::CONTENT_ENCODING, content_encoding);
|
||||
if !headers.contains_key(http::header::CONTENT_TYPE) {
|
||||
headers.insert(
|
||||
http::header::CONTENT_TYPE,
|
||||
http::HeaderValue::from_static("application/json"),
|
||||
);
|
||||
}
|
||||
|
||||
tracing::info!(
|
||||
pre_compression_bytes,
|
||||
post_compression_bytes,
|
||||
compression_duration_ms = compression_duration.as_millis(),
|
||||
"Compressed request body with zstd"
|
||||
);
|
||||
|
||||
builder = builder.headers(headers).body(compressed);
|
||||
} else {
|
||||
builder = builder.headers(headers).json(&body);
|
||||
}
|
||||
} else {
|
||||
builder = builder.headers(headers);
|
||||
if let Some(body) = req.body {
|
||||
builder = builder.json(&body);
|
||||
}
|
||||
Ok(builder)
|
||||
}
|
||||
|
||||
@@ -122,11 +122,11 @@ keyring = { workspace = true, features = ["sync-secret-service"] }
|
||||
assert_cmd = { workspace = true }
|
||||
assert_matches = { workspace = true }
|
||||
codex-arg0 = { workspace = true }
|
||||
codex-core = { path = ".", default-features = false, features = ["deterministic_process_ids"] }
|
||||
codex-otel = { workspace = true, features = ["disable-default-metrics-exporter"] }
|
||||
codex-core = { path = ".", features = ["deterministic_process_ids"] }
|
||||
codex-utils-cargo-bin = { workspace = true }
|
||||
core_test_support = { workspace = true }
|
||||
ctor = { workspace = true }
|
||||
escargot = { workspace = true }
|
||||
image = { workspace = true, features = ["jpeg", "png"] }
|
||||
maplit = { workspace = true }
|
||||
predicates = { workspace = true }
|
||||
@@ -137,7 +137,6 @@ tracing-subscriber = { workspace = true }
|
||||
tracing-test = { workspace = true, features = ["no-env-filter"] }
|
||||
walkdir = { workspace = true }
|
||||
wiremock = { workspace = true }
|
||||
zstd = { workspace = true }
|
||||
|
||||
[package.metadata.cargo-shear]
|
||||
ignored = ["openssl-sys"]
|
||||
|
||||
File diff suppressed because one or more lines are too long
@@ -1,386 +0,0 @@
|
||||
You are a coding agent running in the Codex CLI, a terminal-based coding assistant. Codex CLI is an open source project led by OpenAI. You are expected to be precise, safe, and helpful.
|
||||
|
||||
Your capabilities:
|
||||
|
||||
- Receive user prompts and other context provided by the harness, such as files in the workspace.
|
||||
- Communicate with the user by streaming thinking & responses, and by making & updating plans.
|
||||
- Emit function calls to run terminal commands and apply patches. Depending on how this specific run is configured, you can request that these function calls be escalated to the user for approval before running. More on this in the "Sandbox and approvals" section.
|
||||
|
||||
Within this context, Codex refers to the open-source agentic coding interface (not the old Codex language model built by OpenAI).
|
||||
|
||||
# How you work
|
||||
|
||||
## Personality
|
||||
|
||||
Your default personality and tone is concise, direct, and friendly. You communicate efficiently, always keeping the user clearly informed about ongoing actions without unnecessary detail. You always prioritize actionable guidance, clearly stating assumptions, environment prerequisites, and next steps. Unless explicitly asked, you avoid excessively verbose explanations about your work.
|
||||
|
||||
# AGENTS.md spec
|
||||
- Repos often contain AGENTS.md files. These files can appear anywhere within the repository.
|
||||
- These files are a way for humans to give you (the agent) instructions or tips for working within the container.
|
||||
- Some examples might be: coding conventions, info about how code is organized, or instructions for how to run or test code.
|
||||
- Instructions in AGENTS.md files:
|
||||
- The scope of an AGENTS.md file is the entire directory tree rooted at the folder that contains it.
|
||||
- For every file you touch in the final patch, you must obey instructions in any AGENTS.md file whose scope includes that file.
|
||||
- Instructions about code style, structure, naming, etc. apply only to code within the AGENTS.md file's scope, unless the file states otherwise.
|
||||
- More-deeply-nested AGENTS.md files take precedence in the case of conflicting instructions.
|
||||
- Direct system/developer/user instructions (as part of a prompt) take precedence over AGENTS.md instructions.
|
||||
- The contents of the AGENTS.md file at the root of the repo and any directories from the CWD up to the root are included with the developer message and don't need to be re-read. When working in a subdirectory of CWD, or a directory outside the CWD, check for any AGENTS.md files that may be applicable.
|
||||
|
||||
## Responsiveness
|
||||
|
||||
### Preamble messages
|
||||
|
||||
Before making tool calls, send a brief preamble to the user explaining what you’re about to do. When sending preamble messages, follow these principles and examples:
|
||||
|
||||
- **Logically group related actions**: if you’re about to run several related commands, describe them together in one preamble rather than sending a separate note for each.
|
||||
- **Keep it concise**: be no more than 1-2 sentences, focused on immediate, tangible next steps. (8–12 words for quick updates).
|
||||
- **Build on prior context**: if this is not your first tool call, use the preamble message to connect the dots with what’s been done so far and create a sense of momentum and clarity for the user to understand your next actions.
|
||||
- **Keep your tone light, friendly and curious**: add small touches of personality in preambles feel collaborative and engaging.
|
||||
- **Exception**: Avoid adding a preamble for every trivial read (e.g., `cat` a single file) unless it’s part of a larger grouped action.
|
||||
|
||||
**Examples:**
|
||||
|
||||
- “I’ve explored the repo; now checking the API route definitions.”
|
||||
- “Next, I’ll patch the config and update the related tests.”
|
||||
- “I’m about to scaffold the CLI commands and helper functions.”
|
||||
- “Ok cool, so I’ve wrapped my head around the repo. Now digging into the API routes.”
|
||||
- “Config’s looking tidy. Next up is patching helpers to keep things in sync.”
|
||||
- “Finished poking at the DB gateway. I will now chase down error handling.”
|
||||
- “Alright, build pipeline order is interesting. Checking how it reports failures.”
|
||||
- “Spotted a clever caching util; now hunting where it gets used.”
|
||||
|
||||
## Planning
|
||||
|
||||
You have access to an `update_plan` tool which tracks steps and progress and renders them to the user. Using the tool helps demonstrate that you've understood the task and convey how you're approaching it. Plans can help to make complex, ambiguous, or multi-phase work clearer and more collaborative for the user. A good plan should break the task into meaningful, logically ordered steps that are easy to verify as you go.
|
||||
|
||||
Note that plans are not for padding out simple work with filler steps or stating the obvious. The content of your plan should not involve doing anything that you aren't capable of doing (i.e. don't try to test things that you can't test). Do not use plans for simple or single-step queries that you can just do or answer immediately.
|
||||
|
||||
Do not repeat the full contents of the plan after an `update_plan` call — the harness already displays it. Instead, summarize the change made and highlight any important context or next step.
|
||||
|
||||
Before running a command, consider whether or not you have completed the previous step, and make sure to mark it as completed before moving on to the next step. It may be the case that you complete all steps in your plan after a single pass of implementation. If this is the case, you can simply mark all the planned steps as completed. Sometimes, you may need to change plans in the middle of a task: call `update_plan` with the updated plan and make sure to provide an `explanation` of the rationale when doing so.
|
||||
|
||||
Use a plan when:
|
||||
|
||||
- The task is non-trivial and will require multiple actions over a long time horizon.
|
||||
- There are logical phases or dependencies where sequencing matters.
|
||||
- The work has ambiguity that benefits from outlining high-level goals.
|
||||
- You want intermediate checkpoints for feedback and validation.
|
||||
- When the user asked you to do more than one thing in a single prompt
|
||||
- The user has asked you to use the plan tool (aka "TODOs")
|
||||
- You generate additional steps while working, and plan to do them before yielding to the user
|
||||
|
||||
### Examples
|
||||
|
||||
**High-quality plans**
|
||||
|
||||
Example 1:
|
||||
|
||||
1. Add CLI entry with file args
|
||||
2. Parse Markdown via CommonMark library
|
||||
3. Apply semantic HTML template
|
||||
4. Handle code blocks, images, links
|
||||
5. Add error handling for invalid files
|
||||
|
||||
Example 2:
|
||||
|
||||
1. Define CSS variables for colors
|
||||
2. Add toggle with localStorage state
|
||||
3. Refactor components to use variables
|
||||
4. Verify all views for readability
|
||||
5. Add smooth theme-change transition
|
||||
|
||||
Example 3:
|
||||
|
||||
1. Set up Node.js + WebSocket server
|
||||
2. Add join/leave broadcast events
|
||||
3. Implement messaging with timestamps
|
||||
4. Add usernames + mention highlighting
|
||||
5. Persist messages in lightweight DB
|
||||
6. Add typing indicators + unread count
|
||||
|
||||
**Low-quality plans**
|
||||
|
||||
Example 1:
|
||||
|
||||
1. Create CLI tool
|
||||
2. Add Markdown parser
|
||||
3. Convert to HTML
|
||||
|
||||
Example 2:
|
||||
|
||||
1. Add dark mode toggle
|
||||
2. Save preference
|
||||
3. Make styles look good
|
||||
|
||||
Example 3:
|
||||
|
||||
1. Create single-file HTML game
|
||||
2. Run quick sanity check
|
||||
3. Summarize usage instructions
|
||||
|
||||
If you need to write a plan, only write high quality plans, not low quality ones.
|
||||
|
||||
## Task execution
|
||||
|
||||
You are a coding agent. Please keep going until the query is completely resolved, before ending your turn and yielding back to the user. Only terminate your turn when you are sure that the problem is solved. Autonomously resolve the query to the best of your ability, using the tools available to you, before coming back to the user. Do NOT guess or make up an answer.
|
||||
|
||||
You MUST adhere to the following criteria when solving queries:
|
||||
|
||||
- Working on the repo(s) in the current environment is allowed, even if they are proprietary.
|
||||
- Analyzing code for vulnerabilities is allowed.
|
||||
- Showing user code and tool call details is allowed.
|
||||
- Use the `apply_patch` tool to edit files (NEVER try `applypatch` or `apply-patch`, only `apply_patch`): {"command":["apply_patch","*** Begin Patch\\n*** Update File: path/to/file.py\\n@@ def example():\\n- pass\\n+ return 123\\n*** End Patch"]}
|
||||
|
||||
If completing the user's task requires writing or modifying files, your code and final answer should follow these coding guidelines, though user instructions (i.e. AGENTS.md) may override these guidelines:
|
||||
|
||||
- Fix the problem at the root cause rather than applying surface-level patches, when possible.
|
||||
- Avoid unneeded complexity in your solution.
|
||||
- Do not attempt to fix unrelated bugs or broken tests. It is not your responsibility to fix them. (You may mention them to the user in your final message though.)
|
||||
- Update documentation as necessary.
|
||||
- Keep changes consistent with the style of the existing codebase. Changes should be minimal and focused on the task.
|
||||
- Use `git log` and `git blame` to search the history of the codebase if additional context is required.
|
||||
- NEVER add copyright or license headers unless specifically requested.
|
||||
- Do not waste tokens by re-reading files after calling `apply_patch` on them. The tool call will fail if it didn't work. The same goes for making folders, deleting folders, etc.
|
||||
- Do not `git commit` your changes or create new git branches unless explicitly requested.
|
||||
- Do not add inline comments within code unless explicitly requested.
|
||||
- Do not use one-letter variable names unless explicitly requested.
|
||||
- NEVER output inline citations like "【F:README.md†L5-L14】" in your outputs. The CLI is not able to render these so they will just be broken in the UI. Instead, if you output valid filepaths, users will be able to click on them to open the files in their editor.
|
||||
|
||||
## Sandbox and approvals
|
||||
|
||||
The Codex CLI harness supports several different sandboxing, and approval configurations that the user can choose from.
|
||||
|
||||
Filesystem sandboxing prevents you from editing files without user approval. The options are:
|
||||
|
||||
- **read-only**: You can only read files.
|
||||
- **workspace-write**: You can read files. You can write to files in your workspace folder, but not outside it.
|
||||
- **danger-full-access**: No filesystem sandboxing.
|
||||
|
||||
Network sandboxing prevents you from accessing network without approval. Options are
|
||||
|
||||
- **restricted**
|
||||
- **enabled**
|
||||
|
||||
Approvals are your mechanism to get user consent to perform more privileged actions. Although they introduce friction to the user because your work is paused until the user responds, you should leverage them to accomplish your important work. Do not let these settings or the sandbox deter you from attempting to accomplish the user's task. Approval options are
|
||||
|
||||
- **untrusted**: The harness will escalate most commands for user approval, apart from a limited allowlist of safe "read" commands.
|
||||
- **on-failure**: The harness will allow all commands to run in the sandbox (if enabled), and failures will be escalated to the user for approval to run again without the sandbox.
|
||||
- **on-request**: Commands will be run in the sandbox by default, and you can specify in your tool call if you want to escalate a command to run without sandboxing. (Note that this mode is not always available. If it is, you'll see parameters for it in the `shell` command description.)
|
||||
- **never**: This is a non-interactive mode where you may NEVER ask the user for approval to run commands. Instead, you must always persist and work around constraints to solve the task for the user. You MUST do your utmost best to finish the task and validate your work before yielding. If this mode is pared with `danger-full-access`, take advantage of it to deliver the best outcome for the user. Further, in this mode, your default testing philosophy is overridden: Even if you don't see local patterns for testing, you may add tests and scripts to validate your work. Just remove them before yielding.
|
||||
|
||||
When you are running with approvals `on-request`, and sandboxing enabled, here are scenarios where you'll need to request approval:
|
||||
|
||||
- You need to run a command that writes to a directory that requires it (e.g. running tests that write to /tmp)
|
||||
- You need to run a GUI app (e.g., open/xdg-open/osascript) to open browsers or files.
|
||||
- You are running sandboxed and need to run a command that requires network access (e.g. installing packages)
|
||||
- If you run a command that is important to solving the user's query, but it fails because of sandboxing, rerun the command with approval.
|
||||
- You are about to take a potentially destructive action such as an `rm` or `git reset` that the user did not explicitly ask for
|
||||
- (For all of these, you should weigh alternative paths that do not require approval.)
|
||||
|
||||
Note that when sandboxing is set to read-only, you'll need to request approval for any command that isn't a read.
|
||||
|
||||
You will be told what filesystem sandboxing, network sandboxing, and approval mode are active in a developer or user message. If you are not told about this, assume that you are running with workspace-write, network sandboxing ON, and approval on-failure.
|
||||
|
||||
## Validating your work
|
||||
|
||||
If the codebase has tests or the ability to build or run, consider using them to verify that your work is complete.
|
||||
|
||||
When testing, your philosophy should be to start as specific as possible to the code you changed so that you can catch issues efficiently, then make your way to broader tests as you build confidence. If there's no test for the code you changed, and if the adjacent patterns in the codebases show that there's a logical place for you to add a test, you may do so. However, do not add tests to codebases with no tests.
|
||||
|
||||
Similarly, once you're confident in correctness, you can suggest or use formatting commands to ensure that your code is well formatted. If there are issues you can iterate up to 3 times to get formatting right, but if you still can't manage it's better to save the user time and present them a correct solution where you call out the formatting in your final message. If the codebase does not have a formatter configured, do not add one.
|
||||
|
||||
For all of testing, running, building, and formatting, do not attempt to fix unrelated bugs. It is not your responsibility to fix them. (You may mention them to the user in your final message though.)
|
||||
|
||||
Be mindful of whether to run validation commands proactively. In the absence of behavioral guidance:
|
||||
|
||||
- When running in non-interactive approval modes like **never** or **on-failure**, proactively run tests, lint and do whatever you need to ensure you've completed the task.
|
||||
- When working in interactive approval modes like **untrusted**, or **on-request**, hold off on running tests or lint commands until the user is ready for you to finalize your output, because these commands take time to run and slow down iteration. Instead suggest what you want to do next, and let the user confirm first.
|
||||
- When working on test-related tasks, such as adding tests, fixing tests, or reproducing a bug to verify behavior, you may proactively run tests regardless of approval mode. Use your judgement to decide whether this is a test-related task.
|
||||
|
||||
## Ambition vs. precision
|
||||
|
||||
For tasks that have no prior context (i.e. the user is starting something brand new), you should feel free to be ambitious and demonstrate creativity with your implementation.
|
||||
|
||||
If you're operating in an existing codebase, you should make sure you do exactly what the user asks with surgical precision. Treat the surrounding codebase with respect, and don't overstep (i.e. changing filenames or variables unnecessarily). You should balance being sufficiently ambitious and proactive when completing tasks of this nature.
|
||||
|
||||
You should use judicious initiative to decide on the right level of detail and complexity to deliver based on the user's needs. This means showing good judgment that you're capable of doing the right extras without gold-plating. This might be demonstrated by high-value, creative touches when scope of the task is vague; while being surgical and targeted when scope is tightly specified.
|
||||
|
||||
## Sharing progress updates
|
||||
|
||||
For especially longer tasks that you work on (i.e. requiring many tool calls, or a plan with multiple steps), you should provide progress updates back to the user at reasonable intervals. These updates should be structured as a concise sentence or two (no more than 8-10 words long) recapping progress so far in plain language: this update demonstrates your understanding of what needs to be done, progress so far (i.e. files explores, subtasks complete), and where you're going next.
|
||||
|
||||
Before doing large chunks of work that may incur latency as experienced by the user (i.e. writing a new file), you should send a concise message to the user with an update indicating what you're about to do to ensure they know what you're spending time on. Don't start editing or writing large files before informing the user what you are doing and why.
|
||||
|
||||
The messages you send before tool calls should describe what is immediately about to be done next in very concise language. If there was previous work done, this preamble message should also include a note about the work done so far to bring the user along.
|
||||
|
||||
## Presenting your work and final message
|
||||
|
||||
Your final message should read naturally, like an update from a concise teammate. For casual conversation, brainstorming tasks, or quick questions from the user, respond in a friendly, conversational tone. You should ask questions, suggest ideas, and adapt to the user’s style. If you've finished a large amount of work, when describing what you've done to the user, you should follow the final answer formatting guidelines to communicate substantive changes. You don't need to add structured formatting for one-word answers, greetings, or purely conversational exchanges.
|
||||
|
||||
You can skip heavy formatting for single, simple actions or confirmations. In these cases, respond in plain sentences with any relevant next step or quick option. Reserve multi-section structured responses for results that need grouping or explanation.
|
||||
|
||||
The user is working on the same computer as you, and has access to your work. As such there's no need to show the full contents of large files you have already written unless the user explicitly asks for them. Similarly, if you've created or modified files using `apply_patch`, there's no need to tell users to "save the file" or "copy the code into a file"—just reference the file path.
|
||||
|
||||
If there's something that you think you could help with as a logical next step, concisely ask the user if they want you to do so. Good examples of this are running tests, committing changes, or building out the next logical component. If there’s something that you couldn't do (even with approval) but that the user might want to do (such as verifying changes by running the app), include those instructions succinctly.
|
||||
|
||||
Brevity is very important as a default. You should be very concise (i.e. no more than 10 lines), but can relax this requirement for tasks where additional detail and comprehensiveness is important for the user's understanding.
|
||||
|
||||
### Final answer structure and style guidelines
|
||||
|
||||
You are producing plain text that will later be styled by the CLI. Follow these rules exactly. Formatting should make results easy to scan, but not feel mechanical. Use judgment to decide how much structure adds value.
|
||||
|
||||
**Section Headers**
|
||||
|
||||
- Use only when they improve clarity — they are not mandatory for every answer.
|
||||
- Choose descriptive names that fit the content
|
||||
- Keep headers short (1–3 words) and in `**Title Case**`. Always start headers with `**` and end with `**`
|
||||
- Leave no blank line before the first bullet under a header.
|
||||
- Section headers should only be used where they genuinely improve scanability; avoid fragmenting the answer.
|
||||
|
||||
**Bullets**
|
||||
|
||||
- Use `-` followed by a space for every bullet.
|
||||
- Merge related points when possible; avoid a bullet for every trivial detail.
|
||||
- Keep bullets to one line unless breaking for clarity is unavoidable.
|
||||
- Group into short lists (4–6 bullets) ordered by importance.
|
||||
- Use consistent keyword phrasing and formatting across sections.
|
||||
|
||||
**Monospace**
|
||||
|
||||
- Wrap all commands, file paths, env vars, and code identifiers in backticks (`` `...` ``).
|
||||
- Apply to inline examples and to bullet keywords if the keyword itself is a literal file/command.
|
||||
- Never mix monospace and bold markers; choose one based on whether it’s a keyword (`**`) or inline code/path (`` ` ``).
|
||||
|
||||
**File References**
|
||||
When referencing files in your response, make sure to include the relevant start line and always follow the below rules:
|
||||
* Use inline code to make file paths clickable.
|
||||
* Each reference should have a stand alone path. Even if it's the same file.
|
||||
* Accepted: absolute, workspace‑relative, a/ or b/ diff prefixes, or bare filename/suffix.
|
||||
* Line/column (1‑based, optional): :line[:column] or #Lline[Ccolumn] (column defaults to 1).
|
||||
* Do not use URIs like file://, vscode://, or https://.
|
||||
* Do not provide range of lines
|
||||
* Examples: src/app.ts, src/app.ts:42, b/server/index.js#L10, C:\repo\project\main.rs:12:5
|
||||
|
||||
**Structure**
|
||||
|
||||
- Place related bullets together; don’t mix unrelated concepts in the same section.
|
||||
- Order sections from general → specific → supporting info.
|
||||
- For subsections (e.g., “Binaries” under “Rust Workspace”), introduce with a bolded keyword bullet, then list items under it.
|
||||
- Match structure to complexity:
|
||||
- Multi-part or detailed results → use clear headers and grouped bullets.
|
||||
- Simple results → minimal headers, possibly just a short list or paragraph.
|
||||
|
||||
**Tone**
|
||||
|
||||
- Keep the voice collaborative and natural, like a coding partner handing off work.
|
||||
- Be concise and factual — no filler or conversational commentary and avoid unnecessary repetition
|
||||
- Use present tense and active voice (e.g., “Runs tests” not “This will run tests”).
|
||||
- Keep descriptions self-contained; don’t refer to “above” or “below”.
|
||||
- Use parallel structure in lists for consistency.
|
||||
|
||||
**Don’t**
|
||||
|
||||
- Don’t use literal words “bold” or “monospace” in the content.
|
||||
- Don’t nest bullets or create deep hierarchies.
|
||||
- Don’t output ANSI escape codes directly — the CLI renderer applies them.
|
||||
- Don’t cram unrelated keywords into a single bullet; split for clarity.
|
||||
- Don’t let keyword lists run long — wrap or reformat for scanability.
|
||||
|
||||
Generally, ensure your final answers adapt their shape and depth to the request. For example, answers to code explanations should have a precise, structured explanation with code references that answer the question directly. For tasks with a simple implementation, lead with the outcome and supplement only with what’s needed for clarity. Larger changes can be presented as a logical walkthrough of your approach, grouping related steps, explaining rationale where it adds value, and highlighting next actions to accelerate the user. Your answers should provide the right level of detail while being easily scannable.
|
||||
|
||||
For casual greetings, acknowledgements, or other one-off conversational messages that are not delivering substantive information or structured results, respond naturally without section headers or bullet formatting.
|
||||
|
||||
# Tool Guidelines
|
||||
|
||||
## Shell commands
|
||||
|
||||
When using the shell, you must adhere to the following guidelines:
|
||||
|
||||
- When searching for text or files, prefer using `rg` or `rg --files` respectively because `rg` is much faster than alternatives like `grep`. (If the `rg` command is not found, then use alternatives.)
|
||||
- Do not use python scripts to attempt to output larger chunks of a file.
|
||||
|
||||
## `update_plan`
|
||||
|
||||
A tool named `update_plan` is available to you. You can use it to keep an up‑to‑date, step‑by‑step plan for the task.
|
||||
|
||||
To create a new plan, call `update_plan` with a short list of 1‑sentence steps (no more than 5-7 words each) with a `status` for each step (`pending`, `in_progress`, or `completed`).
|
||||
|
||||
When steps have been completed, use `update_plan` to mark each finished step as `completed` and the next step you are working on as `in_progress`. There should always be exactly one `in_progress` step until everything is done. You can mark multiple items as complete in a single `update_plan` call.
|
||||
|
||||
If all steps are complete, ensure you call `update_plan` to mark all steps as `completed`.
|
||||
|
||||
## `apply_patch`
|
||||
|
||||
Use the `apply_patch` shell command to edit files.
|
||||
Your patch language is a stripped‑down, file‑oriented diff format designed to be easy to parse and safe to apply. You can think of it as a high‑level envelope:
|
||||
|
||||
*** Begin Patch
|
||||
[ one or more file sections ]
|
||||
*** End Patch
|
||||
|
||||
Within that envelope, you get a sequence of file operations.
|
||||
You MUST include a header to specify the action you are taking.
|
||||
Each operation starts with one of three headers:
|
||||
|
||||
*** Add File: <path> - create a new file. Every following line is a + line (the initial contents).
|
||||
*** Delete File: <path> - remove an existing file. Nothing follows.
|
||||
*** Update File: <path> - patch an existing file in place (optionally with a rename).
|
||||
|
||||
May be immediately followed by *** Move to: <new path> if you want to rename the file.
|
||||
Then one or more “hunks”, each introduced by @@ (optionally followed by a hunk header).
|
||||
Within a hunk each line starts with:
|
||||
|
||||
For instructions on [context_before] and [context_after]:
|
||||
- By default, show 3 lines of code immediately above and 3 lines immediately below each change. If a change is within 3 lines of a previous change, do NOT duplicate the first change’s [context_after] lines in the second change’s [context_before] lines.
|
||||
- If 3 lines of context is insufficient to uniquely identify the snippet of code within the file, use the @@ operator to indicate the class or function to which the snippet belongs. For instance, we might have:
|
||||
@@ class BaseClass
|
||||
[3 lines of pre-context]
|
||||
- [old_code]
|
||||
+ [new_code]
|
||||
[3 lines of post-context]
|
||||
|
||||
- If a code block is repeated so many times in a class or function such that even a single `@@` statement and 3 lines of context cannot uniquely identify the snippet of code, you can use multiple `@@` statements to jump to the right context. For instance:
|
||||
|
||||
@@ class BaseClass
|
||||
@@ def method():
|
||||
[3 lines of pre-context]
|
||||
- [old_code]
|
||||
+ [new_code]
|
||||
[3 lines of post-context]
|
||||
|
||||
The full grammar definition is below:
|
||||
Patch := Begin { FileOp } End
|
||||
Begin := "*** Begin Patch" NEWLINE
|
||||
End := "*** End Patch" NEWLINE
|
||||
FileOp := AddFile | DeleteFile | UpdateFile
|
||||
AddFile := "*** Add File: " path NEWLINE { "+" line NEWLINE }
|
||||
DeleteFile := "*** Delete File: " path NEWLINE
|
||||
UpdateFile := "*** Update File: " path NEWLINE [ MoveTo ] { Hunk }
|
||||
MoveTo := "*** Move to: " newPath NEWLINE
|
||||
Hunk := "@@" [ header ] NEWLINE { HunkLine } [ "*** End of File" NEWLINE ]
|
||||
HunkLine := (" " | "-" | "+") text NEWLINE
|
||||
|
||||
A full patch can combine several operations:
|
||||
|
||||
*** Begin Patch
|
||||
*** Add File: hello.txt
|
||||
+Hello world
|
||||
*** Update File: src/app.py
|
||||
*** Move to: src/main.py
|
||||
@@ def greet():
|
||||
-print("Hi")
|
||||
+print("Hello, world!")
|
||||
*** Delete File: obsolete.txt
|
||||
*** End Patch
|
||||
|
||||
It is important to remember:
|
||||
|
||||
- You must include a header with your intended action (Add/Delete/Update)
|
||||
- You must prefix new lines with `+` even when creating a new file
|
||||
- File references can only be relative, NEVER ABSOLUTE.
|
||||
|
||||
You can invoke apply_patch like:
|
||||
|
||||
```
|
||||
shell {"command":["apply_patch","*** Begin Patch\n*** Add File: hello.txt\n+Hello, world!\n*** End Patch\n"]}
|
||||
```
|
||||
@@ -1,188 +0,0 @@
|
||||
use crate::CodexThread;
|
||||
use crate::agent::AgentStatus;
|
||||
use crate::error::CodexErr;
|
||||
use crate::error::Result as CodexResult;
|
||||
use crate::thread_manager::ThreadManagerState;
|
||||
use codex_protocol::ThreadId;
|
||||
use codex_protocol::protocol::EventMsg;
|
||||
use codex_protocol::protocol::Op;
|
||||
use codex_protocol::user_input::UserInput;
|
||||
use std::sync::Arc;
|
||||
use std::sync::Weak;
|
||||
|
||||
/// Control-plane handle for multi-agent operations.
|
||||
/// `AgentControl` is held by each session (via `SessionServices`). It provides capability to
|
||||
/// spawn new agents and the inter-agent communication layer.
|
||||
#[derive(Clone, Default)]
|
||||
pub(crate) struct AgentControl {
|
||||
/// Weak handle back to the global thread registry/state.
|
||||
/// This is `Weak` to avoid reference cycles and shadow persistence of the form
|
||||
/// `ThreadManagerState -> CodexThread -> Session -> SessionServices -> ThreadManagerState`.
|
||||
manager: Weak<ThreadManagerState>,
|
||||
}
|
||||
|
||||
impl AgentControl {
|
||||
/// Construct a new `AgentControl` that can spawn/message agents via the given manager state.
|
||||
pub(crate) fn new(manager: Weak<ThreadManagerState>) -> Self {
|
||||
Self { manager }
|
||||
}
|
||||
|
||||
#[allow(dead_code)] // Used by upcoming multi-agent tooling.
|
||||
/// Spawn a new agent thread and submit the initial prompt.
|
||||
///
|
||||
/// If `headless` is true, a background drain task is spawned to prevent unbounded event growth
|
||||
/// of the channel queue when there is no client actively reading the thread events.
|
||||
pub(crate) async fn spawn_agent(
|
||||
&self,
|
||||
config: crate::config::Config,
|
||||
prompt: String,
|
||||
headless: bool,
|
||||
) -> CodexResult<ThreadId> {
|
||||
let state = self.upgrade()?;
|
||||
let new_thread = state.spawn_new_thread(config, self.clone()).await?;
|
||||
|
||||
if headless {
|
||||
spawn_headless_drain(Arc::clone(&new_thread.thread));
|
||||
}
|
||||
|
||||
self.send_prompt(new_thread.thread_id, prompt).await?;
|
||||
|
||||
Ok(new_thread.thread_id)
|
||||
}
|
||||
|
||||
#[allow(dead_code)] // Used by upcoming multi-agent tooling.
|
||||
/// Send a `user` prompt to an existing agent thread.
|
||||
pub(crate) async fn send_prompt(
|
||||
&self,
|
||||
agent_id: ThreadId,
|
||||
prompt: String,
|
||||
) -> CodexResult<String> {
|
||||
let state = self.upgrade()?;
|
||||
state
|
||||
.send_op(
|
||||
agent_id,
|
||||
Op::UserInput {
|
||||
items: vec![UserInput::Text { text: prompt }],
|
||||
final_output_json_schema: None,
|
||||
},
|
||||
)
|
||||
.await
|
||||
}
|
||||
|
||||
#[allow(dead_code)] // Used by upcoming multi-agent tooling.
|
||||
/// Fetch the last known status for `agent_id`, returning `NotFound` when unavailable.
|
||||
pub(crate) async fn get_status(&self, agent_id: ThreadId) -> AgentStatus {
|
||||
let Ok(state) = self.upgrade() else {
|
||||
// No agent available if upgrade fails.
|
||||
return AgentStatus::NotFound;
|
||||
};
|
||||
let Ok(thread) = state.get_thread(agent_id).await else {
|
||||
return AgentStatus::NotFound;
|
||||
};
|
||||
thread.agent_status().await
|
||||
}
|
||||
|
||||
fn upgrade(&self) -> CodexResult<Arc<ThreadManagerState>> {
|
||||
self.manager
|
||||
.upgrade()
|
||||
.ok_or_else(|| CodexErr::UnsupportedOperation("thread manager dropped".to_string()))
|
||||
}
|
||||
}
|
||||
|
||||
/// When an agent is spawned "headless" (no UI/view attached), there may be no consumer polling
|
||||
/// `CodexThread::next_event()`. The underlying event channel is unbounded, so the producer can
|
||||
/// accumulate events indefinitely. This drain task prevents that memory growth by polling and
|
||||
/// discarding events until shutdown.
|
||||
fn spawn_headless_drain(thread: Arc<CodexThread>) {
|
||||
tokio::spawn(async move {
|
||||
loop {
|
||||
match thread.next_event().await {
|
||||
Ok(event) => {
|
||||
if matches!(event.msg, EventMsg::ShutdownComplete) {
|
||||
break;
|
||||
}
|
||||
}
|
||||
Err(err) => {
|
||||
tracing::warn!("failed to receive event from agent: {err:?}");
|
||||
break;
|
||||
}
|
||||
}
|
||||
}
|
||||
});
|
||||
}
|
||||
|
||||
#[cfg(test)]
|
||||
mod tests {
|
||||
use super::*;
|
||||
use crate::agent::agent_status_from_event;
|
||||
use codex_protocol::protocol::ErrorEvent;
|
||||
use codex_protocol::protocol::TaskCompleteEvent;
|
||||
use codex_protocol::protocol::TaskStartedEvent;
|
||||
use codex_protocol::protocol::TurnAbortReason;
|
||||
use codex_protocol::protocol::TurnAbortedEvent;
|
||||
use pretty_assertions::assert_eq;
|
||||
|
||||
#[tokio::test]
|
||||
async fn send_prompt_errors_when_manager_dropped() {
|
||||
let control = AgentControl::default();
|
||||
let err = control
|
||||
.send_prompt(ThreadId::new(), "hello".to_string())
|
||||
.await
|
||||
.expect_err("send_prompt should fail without a manager");
|
||||
assert_eq!(
|
||||
err.to_string(),
|
||||
"unsupported operation: thread manager dropped"
|
||||
);
|
||||
}
|
||||
|
||||
#[tokio::test]
|
||||
async fn get_status_returns_not_found_without_manager() {
|
||||
let control = AgentControl::default();
|
||||
let got = control.get_status(ThreadId::new()).await;
|
||||
assert_eq!(got, AgentStatus::NotFound);
|
||||
}
|
||||
|
||||
#[tokio::test]
|
||||
async fn on_event_updates_status_from_task_started() {
|
||||
let status = agent_status_from_event(&EventMsg::TaskStarted(TaskStartedEvent {
|
||||
model_context_window: None,
|
||||
}));
|
||||
assert_eq!(status, Some(AgentStatus::Running));
|
||||
}
|
||||
|
||||
#[tokio::test]
|
||||
async fn on_event_updates_status_from_task_complete() {
|
||||
let status = agent_status_from_event(&EventMsg::TaskComplete(TaskCompleteEvent {
|
||||
last_agent_message: Some("done".to_string()),
|
||||
}));
|
||||
let expected = AgentStatus::Completed(Some("done".to_string()));
|
||||
assert_eq!(status, Some(expected));
|
||||
}
|
||||
|
||||
#[tokio::test]
|
||||
async fn on_event_updates_status_from_error() {
|
||||
let status = agent_status_from_event(&EventMsg::Error(ErrorEvent {
|
||||
message: "boom".to_string(),
|
||||
codex_error_info: None,
|
||||
}));
|
||||
|
||||
let expected = AgentStatus::Errored("boom".to_string());
|
||||
assert_eq!(status, Some(expected));
|
||||
}
|
||||
|
||||
#[tokio::test]
|
||||
async fn on_event_updates_status_from_turn_aborted() {
|
||||
let status = agent_status_from_event(&EventMsg::TurnAborted(TurnAbortedEvent {
|
||||
reason: TurnAbortReason::Interrupted,
|
||||
}));
|
||||
|
||||
let expected = AgentStatus::Errored("Interrupted".to_string());
|
||||
assert_eq!(status, Some(expected));
|
||||
}
|
||||
|
||||
#[tokio::test]
|
||||
async fn on_event_updates_status_from_shutdown_complete() {
|
||||
let status = agent_status_from_event(&EventMsg::ShutdownComplete);
|
||||
assert_eq!(status, Some(AgentStatus::Shutdown));
|
||||
}
|
||||
}
|
||||
@@ -1,6 +0,0 @@
|
||||
pub(crate) mod control;
|
||||
pub(crate) mod status;
|
||||
|
||||
pub(crate) use codex_protocol::protocol::AgentStatus;
|
||||
pub(crate) use control::AgentControl;
|
||||
pub(crate) use status::agent_status_from_event;
|
||||
@@ -1,15 +0,0 @@
|
||||
use codex_protocol::protocol::AgentStatus;
|
||||
use codex_protocol::protocol::EventMsg;
|
||||
|
||||
/// Derive the next agent status from a single emitted event.
|
||||
/// Returns `None` when the event does not affect status tracking.
|
||||
pub(crate) fn agent_status_from_event(msg: &EventMsg) -> Option<AgentStatus> {
|
||||
match msg {
|
||||
EventMsg::TaskStarted(_) => Some(AgentStatus::Running),
|
||||
EventMsg::TaskComplete(ev) => Some(AgentStatus::Completed(ev.last_agent_message.clone())),
|
||||
EventMsg::TurnAborted(ev) => Some(AgentStatus::Errored(format!("{:?}", ev.reason))),
|
||||
EventMsg::Error(ev) => Some(AgentStatus::Errored(ev.message.clone())),
|
||||
EventMsg::ShutdownComplete => Some(AgentStatus::Shutdown),
|
||||
_ => None,
|
||||
}
|
||||
}
|
||||
@@ -100,7 +100,7 @@ fn extract_request_id(headers: Option<&HeaderMap>) -> Option<String> {
|
||||
})
|
||||
}
|
||||
|
||||
pub(crate) fn auth_provider_from_auth(
|
||||
pub(crate) async fn auth_provider_from_auth(
|
||||
auth: Option<CodexAuth>,
|
||||
provider: &ModelProviderInfo,
|
||||
) -> crate::error::Result<CoreAuthProvider> {
|
||||
@@ -119,7 +119,7 @@ pub(crate) fn auth_provider_from_auth(
|
||||
}
|
||||
|
||||
if let Some(auth) = auth {
|
||||
let token = auth.get_token()?;
|
||||
let token = auth.get_token().await?;
|
||||
Ok(CoreAuthProvider {
|
||||
token: Some(token),
|
||||
account_id: auth.get_account_id(),
|
||||
|
||||
@@ -1,9 +1,10 @@
|
||||
use crate::codex::Session;
|
||||
use crate::codex::TurnContext;
|
||||
use crate::function_tool::FunctionCallError;
|
||||
use crate::protocol::FileChange;
|
||||
use crate::protocol::ReviewDecision;
|
||||
use crate::safety::SafetyCheck;
|
||||
use crate::safety::assess_patch_safety;
|
||||
use crate::tools::sandboxing::ExecApprovalRequirement;
|
||||
use codex_apply_patch::ApplyPatchAction;
|
||||
use codex_apply_patch::ApplyPatchFileChange;
|
||||
use std::collections::HashMap;
|
||||
@@ -29,12 +30,13 @@ pub(crate) enum InternalApplyPatchInvocation {
|
||||
#[derive(Debug)]
|
||||
pub(crate) struct ApplyPatchExec {
|
||||
pub(crate) action: ApplyPatchAction,
|
||||
pub(crate) auto_approved: bool,
|
||||
pub(crate) exec_approval_requirement: ExecApprovalRequirement,
|
||||
pub(crate) user_explicitly_approved_this_action: bool,
|
||||
}
|
||||
|
||||
pub(crate) async fn apply_patch(
|
||||
sess: &Session,
|
||||
turn_context: &TurnContext,
|
||||
call_id: &str,
|
||||
action: ApplyPatchAction,
|
||||
) -> InternalApplyPatchInvocation {
|
||||
match assess_patch_safety(
|
||||
@@ -48,24 +50,40 @@ pub(crate) async fn apply_patch(
|
||||
..
|
||||
} => InternalApplyPatchInvocation::DelegateToExec(ApplyPatchExec {
|
||||
action,
|
||||
auto_approved: !user_explicitly_approved,
|
||||
exec_approval_requirement: ExecApprovalRequirement::Skip {
|
||||
bypass_sandbox: false,
|
||||
proposed_execpolicy_amendment: None,
|
||||
},
|
||||
user_explicitly_approved_this_action: user_explicitly_approved,
|
||||
}),
|
||||
SafetyCheck::AskUser => {
|
||||
// Delegate the approval prompt (including cached approvals) to the
|
||||
// tool runtime, consistent with how shell/unified_exec approvals
|
||||
// are orchestrator-driven.
|
||||
InternalApplyPatchInvocation::DelegateToExec(ApplyPatchExec {
|
||||
action,
|
||||
auto_approved: false,
|
||||
exec_approval_requirement: ExecApprovalRequirement::NeedsApproval {
|
||||
reason: None,
|
||||
proposed_execpolicy_amendment: None,
|
||||
},
|
||||
})
|
||||
// Compute a readable summary of path changes to include in the
|
||||
// approval request so the user can make an informed decision.
|
||||
//
|
||||
// Note that it might be worth expanding this approval request to
|
||||
// give the user the option to expand the set of writable roots so
|
||||
// that similar patches can be auto-approved in the future during
|
||||
// this session.
|
||||
let rx_approve = sess
|
||||
.request_patch_approval(
|
||||
turn_context,
|
||||
call_id.to_owned(),
|
||||
convert_apply_patch_to_protocol(&action),
|
||||
None,
|
||||
None,
|
||||
)
|
||||
.await;
|
||||
match rx_approve.await.unwrap_or_default() {
|
||||
ReviewDecision::Approved
|
||||
| ReviewDecision::ApprovedExecpolicyAmendment { .. }
|
||||
| ReviewDecision::ApprovedForSession => {
|
||||
InternalApplyPatchInvocation::DelegateToExec(ApplyPatchExec {
|
||||
action,
|
||||
user_explicitly_approved_this_action: true,
|
||||
})
|
||||
}
|
||||
ReviewDecision::Denied | ReviewDecision::Abort => {
|
||||
InternalApplyPatchInvocation::Output(Err(FunctionCallError::RespondToModel(
|
||||
"patch rejected by user".to_string(),
|
||||
)))
|
||||
}
|
||||
}
|
||||
}
|
||||
SafetyCheck::Reject { reason } => InternalApplyPatchInvocation::Output(Err(
|
||||
FunctionCallError::RespondToModel(format!("patch rejected: {reason}")),
|
||||
|
||||
@@ -8,10 +8,12 @@ use serde::Serialize;
|
||||
use serial_test::serial;
|
||||
use std::env;
|
||||
use std::fmt::Debug;
|
||||
use std::io::ErrorKind;
|
||||
use std::path::Path;
|
||||
use std::path::PathBuf;
|
||||
use std::sync::Arc;
|
||||
use std::sync::Mutex;
|
||||
use std::time::Duration;
|
||||
|
||||
use codex_app_server_protocol::AuthMode;
|
||||
use codex_protocol::config_types::ForcedLoginMethod;
|
||||
@@ -30,7 +32,11 @@ use crate::token_data::parse_id_token;
|
||||
use crate::util::try_parse_error_message;
|
||||
use codex_client::CodexHttpClient;
|
||||
use codex_protocol::account::PlanType as AccountPlanType;
|
||||
#[cfg(any(test, feature = "test-support"))]
|
||||
use once_cell::sync::Lazy;
|
||||
use serde_json::Value;
|
||||
#[cfg(any(test, feature = "test-support"))]
|
||||
use tempfile::TempDir;
|
||||
use thiserror::Error;
|
||||
|
||||
#[derive(Debug, Clone)]
|
||||
@@ -60,6 +66,9 @@ const REFRESH_TOKEN_UNKNOWN_MESSAGE: &str =
|
||||
const REFRESH_TOKEN_URL: &str = "https://auth.openai.com/oauth/token";
|
||||
pub const REFRESH_TOKEN_URL_OVERRIDE_ENV_VAR: &str = "CODEX_REFRESH_TOKEN_URL_OVERRIDE";
|
||||
|
||||
#[cfg(any(test, feature = "test-support"))]
|
||||
static TEST_AUTH_TEMP_DIRS: Lazy<Mutex<Vec<TempDir>>> = Lazy::new(|| Mutex::new(Vec::new()));
|
||||
|
||||
#[derive(Debug, Error)]
|
||||
pub enum RefreshTokenError {
|
||||
#[error("{0}")]
|
||||
@@ -75,6 +84,10 @@ impl RefreshTokenError {
|
||||
Self::Transient(_) => None,
|
||||
}
|
||||
}
|
||||
|
||||
fn other_with_message(message: impl Into<String>) -> Self {
|
||||
Self::Transient(std::io::Error::other(message.into()))
|
||||
}
|
||||
}
|
||||
|
||||
impl From<RefreshTokenError> for std::io::Error {
|
||||
@@ -87,6 +100,40 @@ impl From<RefreshTokenError> for std::io::Error {
|
||||
}
|
||||
|
||||
impl CodexAuth {
|
||||
pub async fn refresh_token(&self) -> Result<String, RefreshTokenError> {
|
||||
tracing::info!("Refreshing token");
|
||||
|
||||
let token_data = self.get_current_token_data().ok_or_else(|| {
|
||||
RefreshTokenError::Transient(std::io::Error::other("Token data is not available."))
|
||||
})?;
|
||||
let token = token_data.refresh_token;
|
||||
|
||||
let refresh_response = try_refresh_token(token, &self.client).await?;
|
||||
|
||||
let updated = update_tokens(
|
||||
&self.storage,
|
||||
refresh_response.id_token,
|
||||
refresh_response.access_token,
|
||||
refresh_response.refresh_token,
|
||||
)
|
||||
.await
|
||||
.map_err(RefreshTokenError::from)?;
|
||||
|
||||
if let Ok(mut auth_lock) = self.auth_dot_json.lock() {
|
||||
*auth_lock = Some(updated.clone());
|
||||
}
|
||||
|
||||
let access = match updated.tokens {
|
||||
Some(t) => t.access_token,
|
||||
None => {
|
||||
return Err(RefreshTokenError::other_with_message(
|
||||
"Token data is not available after refresh.",
|
||||
));
|
||||
}
|
||||
};
|
||||
Ok(access)
|
||||
}
|
||||
|
||||
/// Loads the available auth information from auth storage.
|
||||
pub fn from_auth_storage(
|
||||
codex_home: &Path,
|
||||
@@ -95,23 +142,62 @@ impl CodexAuth {
|
||||
load_auth(codex_home, false, auth_credentials_store_mode)
|
||||
}
|
||||
|
||||
pub fn get_token_data(&self) -> Result<TokenData, std::io::Error> {
|
||||
pub async fn get_token_data(&self) -> Result<TokenData, std::io::Error> {
|
||||
let auth_dot_json: Option<AuthDotJson> = self.get_current_auth_json();
|
||||
match auth_dot_json {
|
||||
Some(AuthDotJson {
|
||||
tokens: Some(tokens),
|
||||
last_refresh: Some(_),
|
||||
tokens: Some(mut tokens),
|
||||
last_refresh: Some(last_refresh),
|
||||
..
|
||||
}) => Ok(tokens),
|
||||
}) => {
|
||||
if last_refresh < Utc::now() - chrono::Duration::days(TOKEN_REFRESH_INTERVAL) {
|
||||
let refresh_result = tokio::time::timeout(
|
||||
Duration::from_secs(60),
|
||||
try_refresh_token(tokens.refresh_token.clone(), &self.client),
|
||||
)
|
||||
.await;
|
||||
let refresh_response = match refresh_result {
|
||||
Ok(Ok(response)) => response,
|
||||
Ok(Err(err)) => return Err(err.into()),
|
||||
Err(_) => {
|
||||
return Err(std::io::Error::new(
|
||||
ErrorKind::TimedOut,
|
||||
"timed out while refreshing OpenAI API key",
|
||||
));
|
||||
}
|
||||
};
|
||||
|
||||
let updated_auth_dot_json = update_tokens(
|
||||
&self.storage,
|
||||
refresh_response.id_token,
|
||||
refresh_response.access_token,
|
||||
refresh_response.refresh_token,
|
||||
)
|
||||
.await?;
|
||||
|
||||
tokens = updated_auth_dot_json
|
||||
.tokens
|
||||
.clone()
|
||||
.ok_or(std::io::Error::other(
|
||||
"Token data is not available after refresh.",
|
||||
))?;
|
||||
|
||||
#[expect(clippy::unwrap_used)]
|
||||
let mut auth_lock = self.auth_dot_json.lock().unwrap();
|
||||
*auth_lock = Some(updated_auth_dot_json);
|
||||
}
|
||||
|
||||
Ok(tokens)
|
||||
}
|
||||
_ => Err(std::io::Error::other("Token data is not available.")),
|
||||
}
|
||||
}
|
||||
|
||||
pub fn get_token(&self) -> Result<String, std::io::Error> {
|
||||
pub async fn get_token(&self) -> Result<String, std::io::Error> {
|
||||
match self.mode {
|
||||
AuthMode::ApiKey => Ok(self.api_key.clone().unwrap_or_default()),
|
||||
AuthMode::ChatGPT => {
|
||||
let id_token = self.get_token_data()?.access_token;
|
||||
let id_token = self.get_token_data().await?.access_token;
|
||||
Ok(id_token)
|
||||
}
|
||||
}
|
||||
@@ -259,7 +345,7 @@ pub fn load_auth_dot_json(
|
||||
storage.load()
|
||||
}
|
||||
|
||||
pub fn enforce_login_restrictions(config: &Config) -> std::io::Result<()> {
|
||||
pub async fn enforce_login_restrictions(config: &Config) -> std::io::Result<()> {
|
||||
let Some(auth) = load_auth(
|
||||
&config.codex_home,
|
||||
true,
|
||||
@@ -297,7 +383,7 @@ pub fn enforce_login_restrictions(config: &Config) -> std::io::Result<()> {
|
||||
return Ok(());
|
||||
}
|
||||
|
||||
let token_data = match auth.get_token_data() {
|
||||
let token_data = match auth.get_token_data().await {
|
||||
Ok(data) => data,
|
||||
Err(err) => {
|
||||
return logout_with_message(
|
||||
@@ -446,7 +532,6 @@ async fn try_refresh_token(
|
||||
Ok(refresh_response)
|
||||
} else {
|
||||
let body = response.text().await.unwrap_or_default();
|
||||
tracing::error!("Failed to refresh token: {status}: {body}");
|
||||
if status == StatusCode::UNAUTHORIZED {
|
||||
let failed = classify_refresh_token_failure(&body);
|
||||
Err(RefreshTokenError::Permanent(failed))
|
||||
@@ -545,329 +630,6 @@ struct CachedAuth {
|
||||
auth: Option<CodexAuth>,
|
||||
}
|
||||
|
||||
enum UnauthorizedRecoveryStep {
|
||||
Reload,
|
||||
RefreshToken,
|
||||
Done,
|
||||
}
|
||||
|
||||
enum ReloadOutcome {
|
||||
Reloaded,
|
||||
Skipped,
|
||||
}
|
||||
|
||||
// UnauthorizedRecovery is a state machine that handles an attempt to refresh the authentication when requests
|
||||
// to API fail with 401 status code.
|
||||
// The client calls next() every time it encounters a 401 error, one time per retry.
|
||||
// For API key based authentication, we don't do anything and let the error bubble to the user.
|
||||
// For ChatGPT based authentication, we:
|
||||
// 1. Attempt to reload the auth data from disk. We only reload if the account id matches the one the current process is running as.
|
||||
// 2. Attempt to refresh the token using OAuth token refresh flow.
|
||||
// If after both steps the server still responds with 401 we let the error bubble to the user.
|
||||
pub struct UnauthorizedRecovery {
|
||||
manager: Arc<AuthManager>,
|
||||
step: UnauthorizedRecoveryStep,
|
||||
expected_account_id: Option<String>,
|
||||
}
|
||||
|
||||
impl UnauthorizedRecovery {
|
||||
fn new(manager: Arc<AuthManager>) -> Self {
|
||||
let expected_account_id = manager
|
||||
.auth_cached()
|
||||
.as_ref()
|
||||
.and_then(CodexAuth::get_account_id);
|
||||
Self {
|
||||
manager,
|
||||
step: UnauthorizedRecoveryStep::Reload,
|
||||
expected_account_id,
|
||||
}
|
||||
}
|
||||
|
||||
pub fn has_next(&self) -> bool {
|
||||
if !self
|
||||
.manager
|
||||
.auth_cached()
|
||||
.is_some_and(|auth| auth.mode == AuthMode::ChatGPT)
|
||||
{
|
||||
return false;
|
||||
}
|
||||
|
||||
!matches!(self.step, UnauthorizedRecoveryStep::Done)
|
||||
}
|
||||
|
||||
pub async fn next(&mut self) -> Result<(), RefreshTokenError> {
|
||||
if !self.has_next() {
|
||||
return Err(RefreshTokenError::Permanent(RefreshTokenFailedError::new(
|
||||
RefreshTokenFailedReason::Other,
|
||||
"No more recovery steps available.",
|
||||
)));
|
||||
}
|
||||
|
||||
match self.step {
|
||||
UnauthorizedRecoveryStep::Reload => {
|
||||
match self
|
||||
.manager
|
||||
.reload_if_account_id_matches(self.expected_account_id.as_deref())
|
||||
{
|
||||
ReloadOutcome::Reloaded => {
|
||||
self.step = UnauthorizedRecoveryStep::RefreshToken;
|
||||
}
|
||||
ReloadOutcome::Skipped => {
|
||||
self.manager.refresh_token().await?;
|
||||
self.step = UnauthorizedRecoveryStep::Done;
|
||||
}
|
||||
}
|
||||
}
|
||||
UnauthorizedRecoveryStep::RefreshToken => {
|
||||
self.manager.refresh_token().await?;
|
||||
self.step = UnauthorizedRecoveryStep::Done;
|
||||
}
|
||||
UnauthorizedRecoveryStep::Done => {}
|
||||
}
|
||||
Ok(())
|
||||
}
|
||||
}
|
||||
|
||||
/// Central manager providing a single source of truth for auth.json derived
|
||||
/// authentication data. It loads once (or on preference change) and then
|
||||
/// hands out cloned `CodexAuth` values so the rest of the program has a
|
||||
/// consistent snapshot.
|
||||
///
|
||||
/// External modifications to `auth.json` will NOT be observed until
|
||||
/// `reload()` is called explicitly. This matches the design goal of avoiding
|
||||
/// different parts of the program seeing inconsistent auth data mid‑run.
|
||||
#[derive(Debug)]
|
||||
pub struct AuthManager {
|
||||
codex_home: PathBuf,
|
||||
inner: RwLock<CachedAuth>,
|
||||
enable_codex_api_key_env: bool,
|
||||
auth_credentials_store_mode: AuthCredentialsStoreMode,
|
||||
}
|
||||
|
||||
impl AuthManager {
|
||||
/// Create a new manager loading the initial auth using the provided
|
||||
/// preferred auth method. Errors loading auth are swallowed; `auth()` will
|
||||
/// simply return `None` in that case so callers can treat it as an
|
||||
/// unauthenticated state.
|
||||
pub fn new(
|
||||
codex_home: PathBuf,
|
||||
enable_codex_api_key_env: bool,
|
||||
auth_credentials_store_mode: AuthCredentialsStoreMode,
|
||||
) -> Self {
|
||||
let auth = load_auth(
|
||||
&codex_home,
|
||||
enable_codex_api_key_env,
|
||||
auth_credentials_store_mode,
|
||||
)
|
||||
.ok()
|
||||
.flatten();
|
||||
Self {
|
||||
codex_home,
|
||||
inner: RwLock::new(CachedAuth { auth }),
|
||||
enable_codex_api_key_env,
|
||||
auth_credentials_store_mode,
|
||||
}
|
||||
}
|
||||
|
||||
#[cfg(any(test, feature = "test-support"))]
|
||||
/// Create an AuthManager with a specific CodexAuth, for testing only.
|
||||
pub fn from_auth_for_testing(auth: CodexAuth) -> Arc<Self> {
|
||||
let cached = CachedAuth { auth: Some(auth) };
|
||||
|
||||
Arc::new(Self {
|
||||
codex_home: PathBuf::from("non-existent"),
|
||||
inner: RwLock::new(cached),
|
||||
enable_codex_api_key_env: false,
|
||||
auth_credentials_store_mode: AuthCredentialsStoreMode::File,
|
||||
})
|
||||
}
|
||||
|
||||
#[cfg(any(test, feature = "test-support"))]
|
||||
/// Create an AuthManager with a specific CodexAuth and codex home, for testing only.
|
||||
pub fn from_auth_for_testing_with_home(auth: CodexAuth, codex_home: PathBuf) -> Arc<Self> {
|
||||
let cached = CachedAuth { auth: Some(auth) };
|
||||
Arc::new(Self {
|
||||
codex_home,
|
||||
inner: RwLock::new(cached),
|
||||
enable_codex_api_key_env: false,
|
||||
auth_credentials_store_mode: AuthCredentialsStoreMode::File,
|
||||
})
|
||||
}
|
||||
|
||||
/// Current cached auth (clone) without attempting a refresh.
|
||||
pub fn auth_cached(&self) -> Option<CodexAuth> {
|
||||
self.inner.read().ok().and_then(|c| c.auth.clone())
|
||||
}
|
||||
|
||||
/// Current cached auth (clone). May be `None` if not logged in or load failed.
|
||||
/// Refreshes cached ChatGPT tokens if they are stale before returning.
|
||||
pub async fn auth(&self) -> Option<CodexAuth> {
|
||||
let auth = self.auth_cached()?;
|
||||
if let Err(err) = self.refresh_if_stale(&auth).await {
|
||||
tracing::error!("Failed to refresh token: {}", err);
|
||||
return Some(auth);
|
||||
}
|
||||
self.auth_cached()
|
||||
}
|
||||
|
||||
/// Force a reload of the auth information from auth.json. Returns
|
||||
/// whether the auth value changed.
|
||||
pub fn reload(&self) -> bool {
|
||||
tracing::info!("Reloading auth");
|
||||
let new_auth = self.load_auth_from_storage();
|
||||
self.set_auth(new_auth)
|
||||
}
|
||||
|
||||
fn reload_if_account_id_matches(&self, expected_account_id: Option<&str>) -> ReloadOutcome {
|
||||
let expected_account_id = match expected_account_id {
|
||||
Some(account_id) => account_id,
|
||||
None => {
|
||||
tracing::info!("Skipping auth reload because no account id is available.");
|
||||
return ReloadOutcome::Skipped;
|
||||
}
|
||||
};
|
||||
|
||||
let new_auth = self.load_auth_from_storage();
|
||||
let new_account_id = new_auth.as_ref().and_then(CodexAuth::get_account_id);
|
||||
|
||||
if new_account_id.as_deref() != Some(expected_account_id) {
|
||||
let found_account_id = new_account_id.as_deref().unwrap_or("unknown");
|
||||
tracing::info!(
|
||||
"Skipping auth reload due to account id mismatch (expected: {expected_account_id}, found: {found_account_id})"
|
||||
);
|
||||
return ReloadOutcome::Skipped;
|
||||
}
|
||||
|
||||
tracing::info!("Reloading auth for account {expected_account_id}");
|
||||
self.set_auth(new_auth);
|
||||
ReloadOutcome::Reloaded
|
||||
}
|
||||
|
||||
fn auths_equal(a: &Option<CodexAuth>, b: &Option<CodexAuth>) -> bool {
|
||||
match (a, b) {
|
||||
(None, None) => true,
|
||||
(Some(a), Some(b)) => a == b,
|
||||
_ => false,
|
||||
}
|
||||
}
|
||||
|
||||
fn load_auth_from_storage(&self) -> Option<CodexAuth> {
|
||||
load_auth(
|
||||
&self.codex_home,
|
||||
self.enable_codex_api_key_env,
|
||||
self.auth_credentials_store_mode,
|
||||
)
|
||||
.ok()
|
||||
.flatten()
|
||||
}
|
||||
|
||||
fn set_auth(&self, new_auth: Option<CodexAuth>) -> bool {
|
||||
if let Ok(mut guard) = self.inner.write() {
|
||||
let changed = !AuthManager::auths_equal(&guard.auth, &new_auth);
|
||||
tracing::info!("Reloaded auth, changed: {changed}");
|
||||
guard.auth = new_auth;
|
||||
changed
|
||||
} else {
|
||||
false
|
||||
}
|
||||
}
|
||||
|
||||
/// Convenience constructor returning an `Arc` wrapper.
|
||||
pub fn shared(
|
||||
codex_home: PathBuf,
|
||||
enable_codex_api_key_env: bool,
|
||||
auth_credentials_store_mode: AuthCredentialsStoreMode,
|
||||
) -> Arc<Self> {
|
||||
Arc::new(Self::new(
|
||||
codex_home,
|
||||
enable_codex_api_key_env,
|
||||
auth_credentials_store_mode,
|
||||
))
|
||||
}
|
||||
|
||||
pub fn unauthorized_recovery(self: &Arc<Self>) -> UnauthorizedRecovery {
|
||||
UnauthorizedRecovery::new(Arc::clone(self))
|
||||
}
|
||||
|
||||
/// Attempt to refresh the current auth token (if any). On success, reload
|
||||
/// the auth state from disk so other components observe refreshed token.
|
||||
/// If the token refresh fails, returns the error to the caller.
|
||||
pub async fn refresh_token(&self) -> Result<(), RefreshTokenError> {
|
||||
tracing::info!("Refreshing token");
|
||||
|
||||
let auth = match self.auth_cached() {
|
||||
Some(auth) => auth,
|
||||
None => return Ok(()),
|
||||
};
|
||||
let token_data = auth.get_current_token_data().ok_or_else(|| {
|
||||
RefreshTokenError::Transient(std::io::Error::other("Token data is not available."))
|
||||
})?;
|
||||
self.refresh_tokens(&auth, token_data.refresh_token).await?;
|
||||
// Reload to pick up persisted changes.
|
||||
self.reload();
|
||||
Ok(())
|
||||
}
|
||||
|
||||
/// Log out by deleting the on‑disk auth.json (if present). Returns Ok(true)
|
||||
/// if a file was removed, Ok(false) if no auth file existed. On success,
|
||||
/// reloads the in‑memory auth cache so callers immediately observe the
|
||||
/// unauthenticated state.
|
||||
pub fn logout(&self) -> std::io::Result<bool> {
|
||||
let removed = super::auth::logout(&self.codex_home, self.auth_credentials_store_mode)?;
|
||||
// Always reload to clear any cached auth (even if file absent).
|
||||
self.reload();
|
||||
Ok(removed)
|
||||
}
|
||||
|
||||
pub fn get_auth_mode(&self) -> Option<AuthMode> {
|
||||
self.auth_cached().map(|a| a.mode)
|
||||
}
|
||||
|
||||
async fn refresh_if_stale(&self, auth: &CodexAuth) -> Result<bool, RefreshTokenError> {
|
||||
if auth.mode != AuthMode::ChatGPT {
|
||||
return Ok(false);
|
||||
}
|
||||
|
||||
let auth_dot_json = match auth.get_current_auth_json() {
|
||||
Some(auth_dot_json) => auth_dot_json,
|
||||
None => return Ok(false),
|
||||
};
|
||||
let tokens = match auth_dot_json.tokens {
|
||||
Some(tokens) => tokens,
|
||||
None => return Ok(false),
|
||||
};
|
||||
let last_refresh = match auth_dot_json.last_refresh {
|
||||
Some(last_refresh) => last_refresh,
|
||||
None => return Ok(false),
|
||||
};
|
||||
if last_refresh >= Utc::now() - chrono::Duration::days(TOKEN_REFRESH_INTERVAL) {
|
||||
return Ok(false);
|
||||
}
|
||||
self.refresh_tokens(auth, tokens.refresh_token).await?;
|
||||
self.reload();
|
||||
Ok(true)
|
||||
}
|
||||
|
||||
async fn refresh_tokens(
|
||||
&self,
|
||||
auth: &CodexAuth,
|
||||
refresh_token: String,
|
||||
) -> Result<(), RefreshTokenError> {
|
||||
let refresh_response = try_refresh_token(refresh_token, &auth.client).await?;
|
||||
|
||||
update_tokens(
|
||||
&auth.storage,
|
||||
refresh_response.id_token,
|
||||
refresh_response.access_token,
|
||||
refresh_response.refresh_token,
|
||||
)
|
||||
.await
|
||||
.map_err(RefreshTokenError::from)?;
|
||||
|
||||
Ok(())
|
||||
}
|
||||
}
|
||||
|
||||
#[cfg(test)]
|
||||
mod tests {
|
||||
use super::*;
|
||||
@@ -1026,7 +788,7 @@ mod tests {
|
||||
assert_eq!(auth.mode, AuthMode::ApiKey);
|
||||
assert_eq!(auth.api_key, Some("sk-test-key".to_string()));
|
||||
|
||||
assert!(auth.get_token_data().is_err());
|
||||
assert!(auth.get_token_data().await.is_err());
|
||||
}
|
||||
|
||||
#[test]
|
||||
@@ -1154,6 +916,7 @@ mod tests {
|
||||
let config = build_config(codex_home.path(), Some(ForcedLoginMethod::Chatgpt), None).await;
|
||||
|
||||
let err = super::enforce_login_restrictions(&config)
|
||||
.await
|
||||
.expect_err("expected method mismatch to error");
|
||||
assert!(err.to_string().contains("ChatGPT login is required"));
|
||||
assert!(
|
||||
@@ -1179,6 +942,7 @@ mod tests {
|
||||
let config = build_config(codex_home.path(), None, Some("org_mine".to_string())).await;
|
||||
|
||||
let err = super::enforce_login_restrictions(&config)
|
||||
.await
|
||||
.expect_err("expected workspace mismatch to error");
|
||||
assert!(err.to_string().contains("workspace org_mine"));
|
||||
assert!(
|
||||
@@ -1203,7 +967,9 @@ mod tests {
|
||||
|
||||
let config = build_config(codex_home.path(), None, Some("org_mine".to_string())).await;
|
||||
|
||||
super::enforce_login_restrictions(&config).expect("matching workspace should succeed");
|
||||
super::enforce_login_restrictions(&config)
|
||||
.await
|
||||
.expect("matching workspace should succeed");
|
||||
assert!(
|
||||
codex_home.path().join("auth.json").exists(),
|
||||
"auth.json should remain when restrictions pass"
|
||||
@@ -1219,7 +985,9 @@ mod tests {
|
||||
|
||||
let config = build_config(codex_home.path(), None, Some("org_mine".to_string())).await;
|
||||
|
||||
super::enforce_login_restrictions(&config).expect("matching workspace should succeed");
|
||||
super::enforce_login_restrictions(&config)
|
||||
.await
|
||||
.expect("matching workspace should succeed");
|
||||
assert!(
|
||||
codex_home.path().join("auth.json").exists(),
|
||||
"auth.json should remain when restrictions pass"
|
||||
@@ -1235,6 +1003,7 @@ mod tests {
|
||||
let config = build_config(codex_home.path(), Some(ForcedLoginMethod::Chatgpt), None).await;
|
||||
|
||||
let err = super::enforce_login_restrictions(&config)
|
||||
.await
|
||||
.expect_err("environment API key should not satisfy forced ChatGPT login");
|
||||
assert!(
|
||||
err.to_string()
|
||||
@@ -1282,3 +1051,162 @@ mod tests {
|
||||
pretty_assertions::assert_eq!(auth.account_plan_type(), Some(AccountPlanType::Unknown));
|
||||
}
|
||||
}
|
||||
|
||||
/// Central manager providing a single source of truth for auth.json derived
|
||||
/// authentication data. It loads once (or on preference change) and then
|
||||
/// hands out cloned `CodexAuth` values so the rest of the program has a
|
||||
/// consistent snapshot.
|
||||
///
|
||||
/// External modifications to `auth.json` will NOT be observed until
|
||||
/// `reload()` is called explicitly. This matches the design goal of avoiding
|
||||
/// different parts of the program seeing inconsistent auth data mid‑run.
|
||||
#[derive(Debug)]
|
||||
pub struct AuthManager {
|
||||
codex_home: PathBuf,
|
||||
inner: RwLock<CachedAuth>,
|
||||
enable_codex_api_key_env: bool,
|
||||
auth_credentials_store_mode: AuthCredentialsStoreMode,
|
||||
}
|
||||
|
||||
impl AuthManager {
|
||||
/// Create a new manager loading the initial auth using the provided
|
||||
/// preferred auth method. Errors loading auth are swallowed; `auth()` will
|
||||
/// simply return `None` in that case so callers can treat it as an
|
||||
/// unauthenticated state.
|
||||
pub fn new(
|
||||
codex_home: PathBuf,
|
||||
enable_codex_api_key_env: bool,
|
||||
auth_credentials_store_mode: AuthCredentialsStoreMode,
|
||||
) -> Self {
|
||||
let auth = load_auth(
|
||||
&codex_home,
|
||||
enable_codex_api_key_env,
|
||||
auth_credentials_store_mode,
|
||||
)
|
||||
.ok()
|
||||
.flatten();
|
||||
Self {
|
||||
codex_home,
|
||||
inner: RwLock::new(CachedAuth { auth }),
|
||||
enable_codex_api_key_env,
|
||||
auth_credentials_store_mode,
|
||||
}
|
||||
}
|
||||
|
||||
#[cfg(any(test, feature = "test-support"))]
|
||||
#[expect(clippy::expect_used)]
|
||||
/// Create an AuthManager with a specific CodexAuth, for testing only.
|
||||
pub fn from_auth_for_testing(auth: CodexAuth) -> Arc<Self> {
|
||||
let cached = CachedAuth { auth: Some(auth) };
|
||||
let temp_dir = tempfile::tempdir().expect("temp codex home");
|
||||
let codex_home = temp_dir.path().to_path_buf();
|
||||
TEST_AUTH_TEMP_DIRS
|
||||
.lock()
|
||||
.expect("lock test codex homes")
|
||||
.push(temp_dir);
|
||||
Arc::new(Self {
|
||||
codex_home,
|
||||
inner: RwLock::new(cached),
|
||||
enable_codex_api_key_env: false,
|
||||
auth_credentials_store_mode: AuthCredentialsStoreMode::File,
|
||||
})
|
||||
}
|
||||
|
||||
#[cfg(any(test, feature = "test-support"))]
|
||||
/// Create an AuthManager with a specific CodexAuth and codex home, for testing only.
|
||||
pub fn from_auth_for_testing_with_home(auth: CodexAuth, codex_home: PathBuf) -> Arc<Self> {
|
||||
let cached = CachedAuth { auth: Some(auth) };
|
||||
Arc::new(Self {
|
||||
codex_home,
|
||||
inner: RwLock::new(cached),
|
||||
enable_codex_api_key_env: false,
|
||||
auth_credentials_store_mode: AuthCredentialsStoreMode::File,
|
||||
})
|
||||
}
|
||||
|
||||
/// Current cached auth (clone). May be `None` if not logged in or load failed.
|
||||
pub fn auth(&self) -> Option<CodexAuth> {
|
||||
self.inner.read().ok().and_then(|c| c.auth.clone())
|
||||
}
|
||||
|
||||
pub fn codex_home(&self) -> &Path {
|
||||
&self.codex_home
|
||||
}
|
||||
|
||||
/// Force a reload of the auth information from auth.json. Returns
|
||||
/// whether the auth value changed.
|
||||
pub fn reload(&self) -> bool {
|
||||
let new_auth = load_auth(
|
||||
&self.codex_home,
|
||||
self.enable_codex_api_key_env,
|
||||
self.auth_credentials_store_mode,
|
||||
)
|
||||
.ok()
|
||||
.flatten();
|
||||
if let Ok(mut guard) = self.inner.write() {
|
||||
let changed = !AuthManager::auths_equal(&guard.auth, &new_auth);
|
||||
guard.auth = new_auth;
|
||||
changed
|
||||
} else {
|
||||
false
|
||||
}
|
||||
}
|
||||
|
||||
fn auths_equal(a: &Option<CodexAuth>, b: &Option<CodexAuth>) -> bool {
|
||||
match (a, b) {
|
||||
(None, None) => true,
|
||||
(Some(a), Some(b)) => a == b,
|
||||
_ => false,
|
||||
}
|
||||
}
|
||||
|
||||
/// Convenience constructor returning an `Arc` wrapper.
|
||||
pub fn shared(
|
||||
codex_home: PathBuf,
|
||||
enable_codex_api_key_env: bool,
|
||||
auth_credentials_store_mode: AuthCredentialsStoreMode,
|
||||
) -> Arc<Self> {
|
||||
Arc::new(Self::new(
|
||||
codex_home,
|
||||
enable_codex_api_key_env,
|
||||
auth_credentials_store_mode,
|
||||
))
|
||||
}
|
||||
|
||||
/// Attempt to refresh the current auth token (if any). On success, reload
|
||||
/// the auth state from disk so other components observe refreshed token.
|
||||
/// If the token refresh fails in a permanent (non‑transient) way, logs out
|
||||
/// to clear invalid auth state.
|
||||
pub async fn refresh_token(&self) -> Result<Option<String>, RefreshTokenError> {
|
||||
let auth = match self.auth() {
|
||||
Some(a) => a,
|
||||
None => return Ok(None),
|
||||
};
|
||||
match auth.refresh_token().await {
|
||||
Ok(token) => {
|
||||
// Reload to pick up persisted changes.
|
||||
self.reload();
|
||||
Ok(Some(token))
|
||||
}
|
||||
Err(e) => {
|
||||
tracing::error!("Failed to refresh token: {}", e);
|
||||
Err(e)
|
||||
}
|
||||
}
|
||||
}
|
||||
|
||||
/// Log out by deleting the on‑disk auth.json (if present). Returns Ok(true)
|
||||
/// if a file was removed, Ok(false) if no auth file existed. On success,
|
||||
/// reloads the in‑memory auth cache so callers immediately observe the
|
||||
/// unauthenticated state.
|
||||
pub fn logout(&self) -> std::io::Result<bool> {
|
||||
let removed = super::auth::logout(&self.codex_home, self.auth_credentials_store_mode)?;
|
||||
// Always reload to clear any cached auth (even if file absent).
|
||||
self.reload();
|
||||
Ok(removed)
|
||||
}
|
||||
|
||||
pub fn get_auth_mode(&self) -> Option<AuthMode> {
|
||||
self.auth().map(|a| a.mode)
|
||||
}
|
||||
}
|
||||
|
||||
@@ -2,7 +2,6 @@ use std::sync::Arc;
|
||||
|
||||
use crate::api_bridge::auth_provider_from_auth;
|
||||
use crate::api_bridge::map_api_error;
|
||||
use crate::auth::UnauthorizedRecovery;
|
||||
use codex_api::AggregateStreamExt;
|
||||
use codex_api::ChatClient as ApiChatClient;
|
||||
use codex_api::CompactClient as ApiCompactClient;
|
||||
@@ -18,14 +17,11 @@ use codex_api::TransportError;
|
||||
use codex_api::common::Reasoning;
|
||||
use codex_api::create_text_param_for_request;
|
||||
use codex_api::error::ApiError;
|
||||
use codex_api::requests::responses::Compression;
|
||||
use codex_app_server_protocol::AuthMode;
|
||||
use codex_otel::OtelManager;
|
||||
|
||||
use codex_protocol::ThreadId;
|
||||
use codex_otel::otel_manager::OtelManager;
|
||||
use codex_protocol::ConversationId;
|
||||
use codex_protocol::config_types::ReasoningSummary as ReasoningSummaryConfig;
|
||||
use codex_protocol::models::ResponseItem;
|
||||
use codex_protocol::openai_models::ModelInfo;
|
||||
use codex_protocol::openai_models::ReasoningEffort as ReasoningEffortConfig;
|
||||
use codex_protocol::protocol::SessionSource;
|
||||
use eventsource_stream::Event;
|
||||
@@ -50,10 +46,10 @@ use crate::default_client::build_reqwest_client;
|
||||
use crate::error::CodexErr;
|
||||
use crate::error::Result;
|
||||
use crate::features::FEATURES;
|
||||
use crate::features::Feature;
|
||||
use crate::flags::CODEX_RS_SSE_FIXTURE;
|
||||
use crate::model_provider_info::ModelProviderInfo;
|
||||
use crate::model_provider_info::WireApi;
|
||||
use crate::models_manager::model_family::ModelFamily;
|
||||
use crate::tools::spec::create_tools_json_for_chat_completions_api;
|
||||
use crate::tools::spec::create_tools_json_for_responses_api;
|
||||
|
||||
@@ -61,10 +57,10 @@ use crate::tools::spec::create_tools_json_for_responses_api;
|
||||
pub struct ModelClient {
|
||||
config: Arc<Config>,
|
||||
auth_manager: Option<Arc<AuthManager>>,
|
||||
model_info: ModelInfo,
|
||||
model_family: ModelFamily,
|
||||
otel_manager: OtelManager,
|
||||
provider: ModelProviderInfo,
|
||||
conversation_id: ThreadId,
|
||||
conversation_id: ConversationId,
|
||||
effort: Option<ReasoningEffortConfig>,
|
||||
summary: ReasoningSummaryConfig,
|
||||
session_source: SessionSource,
|
||||
@@ -75,18 +71,18 @@ impl ModelClient {
|
||||
pub fn new(
|
||||
config: Arc<Config>,
|
||||
auth_manager: Option<Arc<AuthManager>>,
|
||||
model_info: ModelInfo,
|
||||
model_family: ModelFamily,
|
||||
otel_manager: OtelManager,
|
||||
provider: ModelProviderInfo,
|
||||
effort: Option<ReasoningEffortConfig>,
|
||||
summary: ReasoningSummaryConfig,
|
||||
conversation_id: ThreadId,
|
||||
conversation_id: ConversationId,
|
||||
session_source: SessionSource,
|
||||
) -> Self {
|
||||
Self {
|
||||
config,
|
||||
auth_manager,
|
||||
model_info,
|
||||
model_family,
|
||||
otel_manager,
|
||||
provider,
|
||||
conversation_id,
|
||||
@@ -97,11 +93,11 @@ impl ModelClient {
|
||||
}
|
||||
|
||||
pub fn get_model_context_window(&self) -> Option<i64> {
|
||||
let model_info = self.get_model_info();
|
||||
let effective_context_window_percent = model_info.effective_context_window_percent;
|
||||
model_info.context_window.map(|context_window| {
|
||||
context_window.saturating_mul(effective_context_window_percent) / 100
|
||||
})
|
||||
let model_family = self.get_model_family();
|
||||
let effective_context_window_percent = model_family.effective_context_window_percent;
|
||||
model_family
|
||||
.context_window
|
||||
.map(|w| w.saturating_mul(effective_context_window_percent) / 100)
|
||||
}
|
||||
|
||||
pub fn config(&self) -> Arc<Config> {
|
||||
@@ -150,25 +146,20 @@ impl ModelClient {
|
||||
}
|
||||
|
||||
let auth_manager = self.auth_manager.clone();
|
||||
let model_info = self.get_model_info();
|
||||
let instructions = prompt.get_full_instructions(&model_info).into_owned();
|
||||
let model_family = self.get_model_family();
|
||||
let instructions = prompt.get_full_instructions(&model_family).into_owned();
|
||||
let tools_json = create_tools_json_for_chat_completions_api(&prompt.tools)?;
|
||||
let api_prompt = build_api_prompt(prompt, instructions, tools_json);
|
||||
let conversation_id = self.conversation_id.to_string();
|
||||
let session_source = self.session_source.clone();
|
||||
|
||||
let mut auth_recovery = auth_manager
|
||||
.as_ref()
|
||||
.map(super::auth::AuthManager::unauthorized_recovery);
|
||||
let mut refreshed = false;
|
||||
loop {
|
||||
let auth = match auth_manager.as_ref() {
|
||||
Some(manager) => manager.auth().await,
|
||||
None => None,
|
||||
};
|
||||
let auth = auth_manager.as_ref().and_then(|m| m.auth());
|
||||
let api_provider = self
|
||||
.provider
|
||||
.to_api_provider(auth.as_ref().map(|a| a.mode))?;
|
||||
let api_auth = auth_provider_from_auth(auth.clone(), &self.provider)?;
|
||||
let api_auth = auth_provider_from_auth(auth.clone(), &self.provider).await?;
|
||||
let transport = ReqwestTransport::new(build_reqwest_client());
|
||||
let (request_telemetry, sse_telemetry) = self.build_streaming_telemetry();
|
||||
let client = ApiChatClient::new(transport, api_provider, api_auth)
|
||||
@@ -188,7 +179,7 @@ impl ModelClient {
|
||||
Err(ApiError::Transport(TransportError::Http { status, .. }))
|
||||
if status == StatusCode::UNAUTHORIZED =>
|
||||
{
|
||||
handle_unauthorized(status, &mut auth_recovery).await?;
|
||||
handle_unauthorized(status, &mut refreshed, &auth_manager, &auth).await?;
|
||||
continue;
|
||||
}
|
||||
Err(err) => return Err(map_api_error(err)),
|
||||
@@ -209,14 +200,13 @@ impl ModelClient {
|
||||
}
|
||||
|
||||
let auth_manager = self.auth_manager.clone();
|
||||
let model_info = self.get_model_info();
|
||||
let instructions = prompt.get_full_instructions(&model_info).into_owned();
|
||||
let model_family = self.get_model_family();
|
||||
let instructions = prompt.get_full_instructions(&model_family).into_owned();
|
||||
let tools_json: Vec<Value> = create_tools_json_for_responses_api(&prompt.tools)?;
|
||||
|
||||
let default_reasoning_effort = model_info.default_reasoning_level;
|
||||
let reasoning = if model_info.supports_reasoning_summaries {
|
||||
let reasoning = if model_family.supports_reasoning_summaries {
|
||||
Some(Reasoning {
|
||||
effort: self.effort.or(default_reasoning_effort),
|
||||
effort: self.effort.or(model_family.default_reasoning_effort),
|
||||
summary: if self.summary == ReasoningSummaryConfig::None {
|
||||
None
|
||||
} else {
|
||||
@@ -233,13 +223,15 @@ impl ModelClient {
|
||||
vec![]
|
||||
};
|
||||
|
||||
let verbosity = if model_info.support_verbosity {
|
||||
self.config.model_verbosity.or(model_info.default_verbosity)
|
||||
let verbosity = if model_family.support_verbosity {
|
||||
self.config
|
||||
.model_verbosity
|
||||
.or(model_family.default_verbosity)
|
||||
} else {
|
||||
if self.config.model_verbosity.is_some() {
|
||||
warn!(
|
||||
"model_verbosity is set but ignored as the model does not support verbosity: {}",
|
||||
model_info.slug
|
||||
model_family.family
|
||||
);
|
||||
}
|
||||
None
|
||||
@@ -250,34 +242,15 @@ impl ModelClient {
|
||||
let conversation_id = self.conversation_id.to_string();
|
||||
let session_source = self.session_source.clone();
|
||||
|
||||
let mut auth_recovery = auth_manager
|
||||
.as_ref()
|
||||
.map(super::auth::AuthManager::unauthorized_recovery);
|
||||
let mut refreshed = false;
|
||||
loop {
|
||||
let auth = match auth_manager.as_ref() {
|
||||
Some(manager) => manager.auth().await,
|
||||
None => None,
|
||||
};
|
||||
let auth = auth_manager.as_ref().and_then(|m| m.auth());
|
||||
let api_provider = self
|
||||
.provider
|
||||
.to_api_provider(auth.as_ref().map(|a| a.mode))?;
|
||||
let api_auth = auth_provider_from_auth(auth.clone(), &self.provider)?;
|
||||
let api_auth = auth_provider_from_auth(auth.clone(), &self.provider).await?;
|
||||
let transport = ReqwestTransport::new(build_reqwest_client());
|
||||
let (request_telemetry, sse_telemetry) = self.build_streaming_telemetry();
|
||||
let compression = if self
|
||||
.config
|
||||
.features
|
||||
.enabled(Feature::EnableRequestCompression)
|
||||
&& auth
|
||||
.as_ref()
|
||||
.is_some_and(|auth| auth.mode == AuthMode::ChatGPT)
|
||||
&& self.provider.is_openai()
|
||||
{
|
||||
Compression::Zstd
|
||||
} else {
|
||||
Compression::None
|
||||
};
|
||||
|
||||
let client = ApiResponsesClient::new(transport, api_provider, api_auth)
|
||||
.with_telemetry(Some(request_telemetry), Some(sse_telemetry));
|
||||
|
||||
@@ -290,7 +263,6 @@ impl ModelClient {
|
||||
conversation_id: Some(conversation_id.clone()),
|
||||
session_source: Some(session_source.clone()),
|
||||
extra_headers: beta_feature_headers(&self.config),
|
||||
compression,
|
||||
};
|
||||
|
||||
let stream_result = client
|
||||
@@ -304,7 +276,7 @@ impl ModelClient {
|
||||
Err(ApiError::Transport(TransportError::Http { status, .. }))
|
||||
if status == StatusCode::UNAUTHORIZED =>
|
||||
{
|
||||
handle_unauthorized(status, &mut auth_recovery).await?;
|
||||
handle_unauthorized(status, &mut refreshed, &auth_manager, &auth).await?;
|
||||
continue;
|
||||
}
|
||||
Err(err) => return Err(map_api_error(err)),
|
||||
@@ -326,11 +298,12 @@ impl ModelClient {
|
||||
|
||||
/// Returns the currently configured model slug.
|
||||
pub fn get_model(&self) -> String {
|
||||
self.model_info.slug.clone()
|
||||
self.get_model_family().get_model_slug().to_string()
|
||||
}
|
||||
|
||||
pub fn get_model_info(&self) -> ModelInfo {
|
||||
self.model_info.clone()
|
||||
/// Returns the currently configured model family.
|
||||
pub fn get_model_family(&self) -> ModelFamily {
|
||||
self.model_family.clone()
|
||||
}
|
||||
|
||||
/// Returns the current reasoning effort setting.
|
||||
@@ -356,21 +329,18 @@ impl ModelClient {
|
||||
return Ok(Vec::new());
|
||||
}
|
||||
let auth_manager = self.auth_manager.clone();
|
||||
let auth = match auth_manager.as_ref() {
|
||||
Some(manager) => manager.auth().await,
|
||||
None => None,
|
||||
};
|
||||
let auth = auth_manager.as_ref().and_then(|m| m.auth());
|
||||
let api_provider = self
|
||||
.provider
|
||||
.to_api_provider(auth.as_ref().map(|a| a.mode))?;
|
||||
let api_auth = auth_provider_from_auth(auth.clone(), &self.provider)?;
|
||||
let api_auth = auth_provider_from_auth(auth.clone(), &self.provider).await?;
|
||||
let transport = ReqwestTransport::new(build_reqwest_client());
|
||||
let request_telemetry = self.build_request_telemetry();
|
||||
let client = ApiCompactClient::new(transport, api_provider, api_auth)
|
||||
.with_telemetry(Some(request_telemetry));
|
||||
|
||||
let instructions = prompt
|
||||
.get_full_instructions(&self.get_model_info())
|
||||
.get_full_instructions(&self.get_model_family())
|
||||
.into_owned();
|
||||
let payload = ApiCompactionInput {
|
||||
model: &self.get_model(),
|
||||
@@ -515,19 +485,29 @@ where
|
||||
/// the mapped `CodexErr` is returned to the caller.
|
||||
async fn handle_unauthorized(
|
||||
status: StatusCode,
|
||||
auth_recovery: &mut Option<UnauthorizedRecovery>,
|
||||
refreshed: &mut bool,
|
||||
auth_manager: &Option<Arc<AuthManager>>,
|
||||
auth: &Option<crate::auth::CodexAuth>,
|
||||
) -> Result<()> {
|
||||
if let Some(recovery) = auth_recovery
|
||||
&& recovery.has_next()
|
||||
{
|
||||
return match recovery.next().await {
|
||||
Ok(_) => Ok(()),
|
||||
Err(RefreshTokenError::Permanent(failed)) => Err(CodexErr::RefreshTokenFailed(failed)),
|
||||
Err(RefreshTokenError::Transient(other)) => Err(CodexErr::Io(other)),
|
||||
};
|
||||
if *refreshed {
|
||||
return Err(map_unauthorized_status(status));
|
||||
}
|
||||
|
||||
Err(map_unauthorized_status(status))
|
||||
if let Some(manager) = auth_manager.as_ref()
|
||||
&& let Some(auth) = auth.as_ref()
|
||||
&& auth.mode == AuthMode::ChatGPT
|
||||
{
|
||||
match manager.refresh_token().await {
|
||||
Ok(_) => {
|
||||
*refreshed = true;
|
||||
Ok(())
|
||||
}
|
||||
Err(RefreshTokenError::Permanent(failed)) => Err(CodexErr::RefreshTokenFailed(failed)),
|
||||
Err(RefreshTokenError::Transient(other)) => Err(CodexErr::Io(other)),
|
||||
}
|
||||
} else {
|
||||
Err(map_unauthorized_status(status))
|
||||
}
|
||||
}
|
||||
|
||||
fn map_unauthorized_status(status: StatusCode) -> CodexErr {
|
||||
|
||||
@@ -1,13 +1,15 @@
|
||||
use crate::client_common::tools::ToolSpec;
|
||||
use crate::error::Result;
|
||||
use crate::models_manager::model_family::ModelFamily;
|
||||
pub use codex_api::common::ResponseEvent;
|
||||
use codex_apply_patch::APPLY_PATCH_TOOL_INSTRUCTIONS;
|
||||
use codex_protocol::models::ResponseItem;
|
||||
use codex_protocol::openai_models::ModelInfo;
|
||||
use futures::Stream;
|
||||
use serde::Deserialize;
|
||||
use serde_json::Value;
|
||||
use std::borrow::Cow;
|
||||
use std::collections::HashSet;
|
||||
use std::ops::Deref;
|
||||
use std::pin::Pin;
|
||||
use std::task::Context;
|
||||
use std::task::Poll;
|
||||
@@ -42,12 +44,28 @@ pub struct Prompt {
|
||||
}
|
||||
|
||||
impl Prompt {
|
||||
pub(crate) fn get_full_instructions<'a>(&'a self, model: &'a ModelInfo) -> Cow<'a, str> {
|
||||
Cow::Borrowed(
|
||||
self.base_instructions_override
|
||||
.as_deref()
|
||||
.unwrap_or(model.base_instructions.as_str()),
|
||||
)
|
||||
pub(crate) fn get_full_instructions<'a>(&'a self, model: &'a ModelFamily) -> Cow<'a, str> {
|
||||
let base = self
|
||||
.base_instructions_override
|
||||
.as_deref()
|
||||
.unwrap_or(model.base_instructions.deref());
|
||||
// When there are no custom instructions, add apply_patch_tool_instructions if:
|
||||
// - the model needs special instructions (4.1)
|
||||
// AND
|
||||
// - there is no apply_patch tool present
|
||||
let is_apply_patch_tool_present = self.tools.iter().any(|tool| match tool {
|
||||
ToolSpec::Function(f) => f.name == "apply_patch",
|
||||
ToolSpec::Freeform(f) => f.name == "apply_patch",
|
||||
_ => false,
|
||||
});
|
||||
if self.base_instructions_override.is_none()
|
||||
&& model.needs_special_apply_patch_instructions
|
||||
&& !is_apply_patch_tool_present
|
||||
{
|
||||
Cow::Owned(format!("{base}\n{APPLY_PATCH_TOOL_INSTRUCTIONS}"))
|
||||
} else {
|
||||
Cow::Borrowed(base)
|
||||
}
|
||||
}
|
||||
|
||||
pub(crate) fn get_formatted_input(&self) -> Vec<ResponseItem> {
|
||||
@@ -177,13 +195,8 @@ pub(crate) mod tools {
|
||||
LocalShell {},
|
||||
// TODO: Understand why we get an error on web_search although the API docs say it's supported.
|
||||
// https://platform.openai.com/docs/guides/tools-web-search?api-mode=responses#:~:text=%7B%20type%3A%20%22web_search%22%20%7D%2C
|
||||
// The `external_web_access` field determines whether the web search is over cached or live content.
|
||||
// https://platform.openai.com/docs/guides/tools-web-search#live-internet-access
|
||||
#[serde(rename = "web_search")]
|
||||
WebSearch {
|
||||
#[serde(skip_serializing_if = "Option::is_none")]
|
||||
external_web_access: Option<bool>,
|
||||
},
|
||||
WebSearch {},
|
||||
#[serde(rename = "custom")]
|
||||
Freeform(FreeformTool),
|
||||
}
|
||||
@@ -193,7 +206,7 @@ pub(crate) mod tools {
|
||||
match self {
|
||||
ToolSpec::Function(tool) => tool.name.as_str(),
|
||||
ToolSpec::LocalShell {} => "local_shell",
|
||||
ToolSpec::WebSearch { .. } => "web_search",
|
||||
ToolSpec::WebSearch {} => "web_search",
|
||||
ToolSpec::Freeform(tool) => tool.name.as_str(),
|
||||
}
|
||||
}
|
||||
@@ -259,8 +272,6 @@ mod tests {
|
||||
let prompt = Prompt {
|
||||
..Default::default()
|
||||
};
|
||||
let prompt_with_apply_patch_instructions =
|
||||
include_str!("../prompt_with_apply_patch_instructions.md");
|
||||
let test_cases = vec![
|
||||
InstructionsTestCase {
|
||||
slug: "gpt-3.5",
|
||||
@@ -301,16 +312,19 @@ mod tests {
|
||||
];
|
||||
for test_case in test_cases {
|
||||
let config = test_config();
|
||||
let model_info = ModelsManager::construct_model_info_offline(test_case.slug, &config);
|
||||
if test_case.expects_apply_patch_instructions {
|
||||
assert_eq!(
|
||||
model_info.base_instructions.as_str(),
|
||||
prompt_with_apply_patch_instructions
|
||||
);
|
||||
}
|
||||
let model_family =
|
||||
ModelsManager::construct_model_family_offline(test_case.slug, &config);
|
||||
let expected = if test_case.expects_apply_patch_instructions {
|
||||
format!(
|
||||
"{}\n{}",
|
||||
model_family.clone().base_instructions,
|
||||
APPLY_PATCH_TOOL_INSTRUCTIONS
|
||||
)
|
||||
} else {
|
||||
model_family.clone().base_instructions
|
||||
};
|
||||
|
||||
let expected = model_info.base_instructions.as_str();
|
||||
let full = prompt.get_full_instructions(&model_info);
|
||||
let full = prompt.get_full_instructions(&model_family);
|
||||
assert_eq!(full, expected);
|
||||
}
|
||||
}
|
||||
|
||||
File diff suppressed because it is too large
Load Diff
Some files were not shown because too many files have changed in this diff Show More
Reference in New Issue
Block a user