### Description
- codex exec --json resume --last "<prompt>" bailed out because clap
treated the prompt as SESSION_ID. I removed the conflicts_with flag and
reinterpret that positional as a prompt when
--last is set, so the flow now keeps working in JSON mode.
(codex-rs/exec/src/cli.rs:84-104, codex-rs/exec/src/lib.rs:75-130)
- Added a regression test that exercises resume --last in JSON mode to
ensure the prompt is accepted and the rollout file is updated.
(codex-rs/exec/tests/suite/resume.rs:126-178)
### Testing
- just fmt
- cargo test -p codex-exec
- just fix -p codex-exec
- cargo test -p codex-exec
#6717
Signed-off-by: Dmitri Khokhlov <dkhokhlov@cribl.io>
This PR adds the API V2 version of the apply_patch approval flow, which
centers around `ThreadItem::FileChange`.
This PR wires the new RPC (`item/fileChange/requestApproval`, V2 only)
and related events (`item/started`, `item/completed` for
`ThreadItem::FileChange`, which are emitted in both V1 and V2) through
the app-server
protocol. The new approval RPC is only sent when the user initiates a
turn with the new `turn/start` API so we don't break backwards
compatibility with VSCE.
Similar to https://github.com/openai/codex/pull/6758, the approach I
took was to make as few changes to the Codex core as possible,
leveraging existing `EventMsg` core events, and translating those in
app-server. I did have to add a few additional fields to
`EventMsg::PatchApplyBegin` and `EventMsg::PatchApplyEnd`, but those
were fairly lightweight.
However, the `EventMsg`s emitted by core are the following:
```
1) Auto-approved (no request for approval)
- EventMsg::PatchApplyBegin
- EventMsg::PatchApplyEnd
2) Approved by user
- EventMsg::ApplyPatchApprovalRequest
- EventMsg::PatchApplyBegin
- EventMsg::PatchApplyEnd
3) Declined by user
- EventMsg::ApplyPatchApprovalRequest
- EventMsg::PatchApplyBegin
- EventMsg::PatchApplyEnd
```
For a request triggering an approval, this would result in:
```
item/fileChange/requestApproval
item/started
item/completed
```
which is different from the `ThreadItem::CommandExecution` flow
introduced in https://github.com/openai/codex/pull/6758, which does the
below and is preferable:
```
item/started
item/commandExecution/requestApproval
item/completed
```
To fix this, we leverage `TurnSummaryStore` on codex_message_processor
to store a little bit of state, allowing us to fire `item/started` and
`item/fileChange/requestApproval` whenever we receive the underlying
`EventMsg::ApplyPatchApprovalRequest`, and no-oping when we receive the
`EventMsg::PatchApplyBegin` later.
This is much less invasive than modifying the order of EventMsg within
core (I tried).
The resulting payloads:
```
{
"method": "item/started",
"params": {
"item": {
"changes": [
{
"diff": "Hello from Codex!\n",
"kind": "add",
"path": "/Users/owen/repos/codex/codex-rs/APPROVAL_DEMO.txt"
}
],
"id": "call_Nxnwj7B3YXigfV6Mwh03d686",
"status": "inProgress",
"type": "fileChange"
}
}
}
```
```
{
"id": 0,
"method": "item/fileChange/requestApproval",
"params": {
"grantRoot": null,
"itemId": "call_Nxnwj7B3YXigfV6Mwh03d686",
"reason": null,
"threadId": "019a9e11-8295-7883-a283-779e06502c6f",
"turnId": "1"
}
}
```
```
{
"id": 0,
"result": {
"decision": "accept"
}
}
```
```
{
"method": "item/completed",
"params": {
"item": {
"changes": [
{
"diff": "Hello from Codex!\n",
"kind": "add",
"path": "/Users/owen/repos/codex/codex-rs/APPROVAL_DEMO.txt"
}
],
"id": "call_Nxnwj7B3YXigfV6Mwh03d686",
"status": "completed",
"type": "fileChange"
}
}
}
```
This reverts commit c2ec477d93.
# External (non-OpenAI) Pull Request Requirements
Before opening this Pull Request, please read the dedicated
"Contributing" markdown file or your PR may be closed:
https://github.com/openai/codex/blob/main/docs/contributing.md
If your PR conforms to our contribution guidelines, replace this text
with a detailed and high quality description of your changes.
Include a link to a bug report or enhancement request.
This adds the following fields to `ThreadStartResponse` and
`ThreadResumeResponse`:
```rust
pub model: String,
pub model_provider: String,
pub cwd: PathBuf,
pub approval_policy: AskForApproval,
pub sandbox: SandboxPolicy,
pub reasoning_effort: Option<ReasoningEffort>,
```
This is important because these fields are optional in
`ThreadStartParams` and `ThreadResumeParams`, so the caller needs to be
able to determine what values were ultimately used to start/resume the
conversation. (Though note that any of these could be changed later
between turns in the conversation.)
Though to get this information reliably, it must be read from the
internal `SessionConfiguredEvent` that is created in response to the
start of a conversation. Because `SessionConfiguredEvent` (as defined in
`codex-rs/protocol/src/protocol.rs`) did not have all of these fields, a
number of them had to be added as part of this PR.
Because `SessionConfiguredEvent` is referenced in many tests, test
instances of `SessionConfiguredEvent` had to be updated, as well, which
is why this PR touches so many files.
## Summary
- update documentation, example configs, and automation defaults to
reference gpt-5.1 / gpt-5.1-codex
- bump the CLI and core configuration defaults, model presets, and error
messaging to the new models while keeping the model-family/tool coverage
for legacy slugs
- refresh tests, fixtures, and TUI snapshots so they expect the upgraded
defaults
## Testing
- `cargo test -p codex-core
config::tests::test_precedence_fixture_with_gpt5_profile`
------
[Codex
Task](https://chatgpt.com/codex/tasks/task_i_6916c5b3c2b08321ace04ee38604fc6b)
This PR adds the API V2 version of the command‑execution approval flow
for the shell tool.
This PR wires the new RPC (`item/commandExecution/requestApproval`, V2
only) and related events (`item/started`, `item/completed`, and
`item/commandExecution/delta`, which are emitted in both V1 and V2)
through the app-server
protocol. The new approval RPC is only sent when the user initiates a
turn with the new `turn/start` API so we don't break backwards
compatibility with VSCE.
The approach I took was to make as few changes to the Codex core as
possible, leveraging existing `EventMsg` core events, and translating
those in app-server. I did have to add additional fields to
`EventMsg::ExecCommandEndEvent` to capture the command's input so that
app-server can statelessly transform these events to a
`ThreadItem::CommandExecution` item for the `item/completed` event.
Once we stabilize the API and it's complete enough for our partners, we
can work on migrating the core to be aware of command execution items as
a first-class concept.
**Note**: We'll need followup work to make sure these APIs work for the
unified exec tool, but will wait til that's stable and landed before
doing a pass on app-server.
Example payloads below:
```
{
"method": "item/started",
"params": {
"item": {
"aggregatedOutput": null,
"command": "/bin/zsh -lc 'touch /tmp/should-trigger-approval'",
"cwd": "/Users/owen/repos/codex/codex-rs",
"durationMs": null,
"exitCode": null,
"id": "call_lNWWsbXl1e47qNaYjFRs0dyU",
"parsedCmd": [
{
"cmd": "touch /tmp/should-trigger-approval",
"type": "unknown"
}
],
"status": "inProgress",
"type": "commandExecution"
}
}
}
```
```
{
"id": 0,
"method": "item/commandExecution/requestApproval",
"params": {
"itemId": "call_lNWWsbXl1e47qNaYjFRs0dyU",
"parsedCmd": [
{
"cmd": "touch /tmp/should-trigger-approval",
"type": "unknown"
}
],
"reason": "Need to create file in /tmp which is outside workspace sandbox",
"risk": null,
"threadId": "019a93e8-0a52-7fe3-9808-b6bc40c0989a",
"turnId": "1"
}
}
```
```
{
"id": 0,
"result": {
"acceptSettings": {
"forSession": false
},
"decision": "accept"
}
}
```
```
{
"params": {
"item": {
"aggregatedOutput": null,
"command": "/bin/zsh -lc 'touch /tmp/should-trigger-approval'",
"cwd": "/Users/owen/repos/codex/codex-rs",
"durationMs": 224,
"exitCode": 0,
"id": "call_lNWWsbXl1e47qNaYjFRs0dyU",
"parsedCmd": [
{
"cmd": "touch /tmp/should-trigger-approval",
"type": "unknown"
}
],
"status": "completed",
"type": "commandExecution"
}
}
}
```
## Summary
Adds support for specifying additional directories in the TypeScript SDK
through a new `additionalDirectories` option in `ThreadOptions`.
## Changes
- Added `additionalDirectories` parameter to `ThreadOptions` interface
- Updated `CodexExec` to accept and pass through additional directories
via the `--config` flag for `sandbox_workspace_write.writable_roots`
- Added comprehensive test coverage for the new functionality
## Test plan
- Added test case that verifies `additionalDirectories` is correctly
passed as repeated flags
- Existing tests continue to pass
---------
Co-authored-by: Claude <noreply@anthropic.com>
feature: Add "!cmd" user shell execution
This change lets users run local shell commands directly from the TUI by
prefixing their input with ! (e.g. !ls). Output is truncated to keep the
exec cell usable, and Ctrl-C cleanly
interrupts long-running commands (e.g. !sleep 10000).
**Summary of changes**
- Route Op::RunUserShellCommand through a dedicated UserShellCommandTask
(core/src/tasks/user_shell.rs), keeping the task logic out of codex.rs.
- Reuse the existing tool router: the task constructs a ToolCall for the
local_shell tool and relies on ShellHandler, so no manual MCP tool
lookup is required.
- Emit exec lifecycle events (ExecCommandBegin/ExecCommandEnd) so the
TUI can show command metadata, live output, and exit status.
**End-to-end flow**
**TUI handling**
1. ChatWidget::submit_user_message (TUI) intercepts messages starting
with !.
2. Non-empty commands dispatch Op::RunUserShellCommand { command };
empty commands surface a help hint.
3. No UserInput items are created, so nothing is enqueued for the model.
**Core submission loop**
4. The submission loop routes the op to handlers::run_user_shell_command
(core/src/codex.rs).
5. A fresh TurnContext is created and Session::spawn_user_shell_command
enqueues UserShellCommandTask.
**Task execution**
6. UserShellCommandTask::run emits TaskStartedEvent, formats the
command, and prepares a ToolCall targeting local_shell.
7. ToolCallRuntime::handle_tool_call dispatches to ShellHandler.
**Shell tool runtime**
8. ShellHandler::run_exec_like launches the process via the unified exec
runtime, honoring sandbox and shell policies, and emits
ExecCommandBegin/End.
9. Stdout/stderr are captured for the UI, but the task does not turn the
resulting ToolOutput into a model response.
**Completion**
10. After ExecCommandEnd, the task finishes without an assistant
message; the session marks it complete and the exec cell displays the
final output.
**Conversation context**
- The command and its output never enter the conversation history or the
model prompt; the flow is local-only.
- Only exec/task events are emitted for UI rendering.
**Demo video**
https://github.com/user-attachments/assets/fcd114b0-4304-4448-a367-a04c43e0b996
## Summary
- Coerce Windows `workspace-write` configs back to read-only, surface
the forced downgrade in the approvals popup,
and funnel users toward WSL or Full Access.
- Add WSL installation instructions to the Auto preset on Windows while
keeping the preset available for other
platforms.
- Skip the trust-on-first-run prompt on native Windows so new folders
remain read-only without additional
confirmation.
- Expose a structured sandbox policy resolution from config to flag
Windows downgrades and adjust tests (core,
exec, TUI) to reflect the new behavior; provide a Windows-only approvals
snapshot.
## Testing
- cargo fmt
- cargo test -p codex-core
config::tests::add_dir_override_extends_workspace_writable_roots
- cargo test -p codex-exec
suite::resume::exec_resume_preserves_cli_configuration_overrides
- cargo test -p codex-tui
chatwidget::tests::approvals_selection_popup_snapshot
- cargo test -p codex-tui
approvals_popup_includes_wsl_note_for_auto_mode
- cargo test -p codex-tui windows_skips_trust_prompt
- just fix -p codex-core
- just fix -p codex-tui
## Summary
- ensure the TypeScript SDK sets CODEX_INTERNAL_ORIGINATOR_OVERRIDE to
codex_sdk_ts when spawning the Codex CLI
- extend the responses proxy test helper to capture request headers for
assertions
- add coverage that verifies Codex threads launched from the TypeScript
SDK send the codex_sdk_ts originator header
## Testing
- Not Run (not requested)
------
https://chatgpt.com/codex/tasks/task_i_68e561b125248320a487f129093d16e7
## Summary
- replace manual wiremock SSE mounts in the compact suite with the
shared response helpers
- simplify the exec auth_env integration test by using the
mount_sse_once_match helper
- rely on mount_sse_sequence plus server request collection to replace
the bespoke SeqResponder utility in tests
## Testing
- just fmt
------
https://chatgpt.com/codex/tasks/task_i_68e2e238f2a88320a337f0b9e4098093
## Summary
- add a reusable `ev_response_created` helper that builds
`response.created` SSE events for integration tests
- update the exec and core integration suites to use the new helper
instead of repeating manual JSON literals
- keep the streaming fixtures consistent by relying on the shared helper
in every touched test
## Testing
- `just fmt`
------
https://chatgpt.com/codex/tasks/task_i_68e1fe885bb883208aafffb94218da61
This updates `codex exec` so that, by default, most of the agent's
activity is written to stderr so that only the final agent message is
written to stdout. This makes it easier to pipe `codex exec` into
another tool without extra filtering.
I introduced `#![deny(clippy::print_stdout)]` to help enforce this
change and renamed the `ts_println!()` macro to `ts_msg()` because (1)
it no longer calls `println!()` and (2), `ts_eprintln!()` seemed too
long of a name.
While here, this also adds `-o` as an alias for `--output-last-message`.
Fixes https://github.com/openai/codex/issues/1670
# Tool System Refactor
- Centralizes tool definitions and execution in `core/src/tools/*`:
specs (`spec.rs`), handlers (`handlers/*`), router (`router.rs`),
registry/dispatch (`registry.rs`), and shared context (`context.rs`).
One registry now builds the model-visible tool list and binds handlers.
- Router converts model responses to tool calls; Registry dispatches
with consistent telemetry via `codex-rs/otel` and unified error
handling. Function, Local Shell, MCP, and experimental `unified_exec`
all flow through this path; legacy shell aliases still work.
- Rationale: reduce per‑tool boilerplate, keep spec/handler in sync, and
make adding tools predictable and testable.
Example: `read_file`
- Spec: `core/src/tools/spec.rs` (see `create_read_file_tool`,
registered by `build_specs`).
- Handler: `core/src/tools/handlers/read_file.rs` (absolute `file_path`,
1‑indexed `offset`, `limit`, `L#: ` prefixes, safe truncation).
- E2E test: `core/tests/suite/read_file.rs` validates the tool returns
the requested lines.
## Next steps:
- Decompose `handle_container_exec_with_params`
- Add parallel tool calls
We continue the separation between `codex app-server` and `codex
mcp-server`.
In particular, we introduce a new crate, `codex-app-server-protocol`,
and migrate `codex-rs/protocol/src/mcp_protocol.rs` into it, renaming it
`codex-rs/app-server-protocol/src/protocol.rs`.
Because `ConversationId` was defined in `mcp_protocol.rs`, we move it
into its own file, `codex-rs/protocol/src/conversation_id.rs`, and
because it is referenced in a ton of places, we have to touch a lot of
files as part of this PR.
We also decide to get away from proper JSON-RPC 2.0 semantics, so we
also introduce `codex-rs/app-server-protocol/src/jsonrpc_lite.rs`, which
is basically the same `JSONRPCMessage` type defined in `mcp-types`
except with all of the `"jsonrpc": "2.0"` removed.
Getting rid of `"jsonrpc": "2.0"` makes our serialization logic
considerably simpler, as we can lean heavier on serde to serialize
directly into the wire format that we use now.
### Title
## otel
Codex can emit [OpenTelemetry](https://opentelemetry.io/) **log events**
that
describe each run: outbound API requests, streamed responses, user
input,
tool-approval decisions, and the result of every tool invocation. Export
is
**disabled by default** so local runs remain self-contained. Opt in by
adding an
`[otel]` table and choosing an exporter.
```toml
[otel]
environment = "staging" # defaults to "dev"
exporter = "none" # defaults to "none"; set to otlp-http or otlp-grpc to send events
log_user_prompt = false # defaults to false; redact prompt text unless explicitly enabled
```
Codex tags every exported event with `service.name = "codex-cli"`, the
CLI
version, and an `env` attribute so downstream collectors can distinguish
dev/staging/prod traffic. Only telemetry produced inside the
`codex_otel`
crate—the events listed below—is forwarded to the exporter.
### Event catalog
Every event shares a common set of metadata fields: `event.timestamp`,
`conversation.id`, `app.version`, `auth_mode` (when available),
`user.account_id` (when available), `terminal.type`, `model`, and
`slug`.
With OTEL enabled Codex emits the following event types (in addition to
the
metadata above):
- `codex.api_request`
- `cf_ray` (optional)
- `attempt`
- `duration_ms`
- `http.response.status_code` (optional)
- `error.message` (failures)
- `codex.sse_event`
- `event.kind`
- `duration_ms`
- `error.message` (failures)
- `input_token_count` (completion only)
- `output_token_count` (completion only)
- `cached_token_count` (completion only, optional)
- `reasoning_token_count` (completion only, optional)
- `tool_token_count` (completion only)
- `codex.user_prompt`
- `prompt_length`
- `prompt` (redacted unless `log_user_prompt = true`)
- `codex.tool_decision`
- `tool_name`
- `call_id`
- `decision` (`approved`, `approved_for_session`, `denied`, or `abort`)
- `source` (`config` or `user`)
- `codex.tool_result`
- `tool_name`
- `call_id`
- `arguments`
- `duration_ms` (execution time for the tool)
- `success` (`"true"` or `"false"`)
- `output`
### Choosing an exporter
Set `otel.exporter` to control where events go:
- `none` – leaves instrumentation active but skips exporting. This is
the
default.
- `otlp-http` – posts OTLP log records to an OTLP/HTTP collector.
Specify the
endpoint, protocol, and headers your collector expects:
```toml
[otel]
exporter = { otlp-http = {
endpoint = "https://otel.example.com/v1/logs",
protocol = "binary",
headers = { "x-otlp-api-key" = "${OTLP_TOKEN}" }
}}
```
- `otlp-grpc` – streams OTLP log records over gRPC. Provide the endpoint
and any
metadata headers:
```toml
[otel]
exporter = { otlp-grpc = {
endpoint = "https://otel.example.com:4317",
headers = { "x-otlp-meta" = "abc123" }
}}
```
If the exporter is `none` nothing is written anywhere; otherwise you
must run or point to your
own collector. All exporters run on a background batch worker that is
flushed on
shutdown.
If you build Codex from source the OTEL crate is still behind an `otel`
feature
flag; the official prebuilt binaries ship with the feature enabled. When
the
feature is disabled the telemetry hooks become no-ops so the CLI
continues to
function without the extra dependencies.
---------
Co-authored-by: Anton Panasenko <apanasenko@openai.com>
Adds a 1-per-turn todo-list item and item.updated event
```jsonl
{"type":"item.started","item":{"id":"item_6","item_type":"todo_list","items":[{"text":"Record initial two-step plan now","completed":false},{"text":"Update progress to next step","completed":false}]}}
{"type":"item.updated","item":{"id":"item_6","item_type":"todo_list","items":[{"text":"Record initial two-step plan now","completed":true},{"text":"Update progress to next step","completed":false}]}}
{"type":"item.completed","item":{"id":"item_6","item_type":"todo_list","items":[{"text":"Record initial two-step plan now","completed":true},{"text":"Update progress to next step","completed":false}]}}
```
Adds a new `item.started` event to `codex exec` and implements it for
command_execution item type.
```jsonl
{"type":"session.created","session_id":"019982d1-75f0-7920-b051-e0d3731a5ed8"}
{"type":"item.completed","item":{"id":"item_0","item_type":"reasoning","text":"**Executing commands securely**\n\nI'm thinking about how the default harness typically uses \"bash -lc,\" while historically \"bash\" is what we've been using. The command should be executed as a string in our CLI, so using \"bash -lc 'echo hello'\" is optimal but calling \"echo hello\" directly feels safer. The sandbox makes sure environment variables like CODEX_SANDBOX_NETWORK_DISABLED=1 are set, so I won't ask for approval. I just need to run \"echo hello\" and correctly present the output."}}
{"type":"item.completed","item":{"id":"item_1","item_type":"reasoning","text":"**Preparing for tool calls**\n\nI realize that I need to include a preamble before making any tool calls. So, I'll first state the preamble in the commentary channel, then proceed with the tool call. After that, I need to present the final message along with the output. It's possible that the CLI will show the output inline, but I must ensure that I present the result clearly regardless. Let's move forward and get this organized!"}}
{"type":"item.completed","item":{"id":"item_2","item_type":"assistant_message","text":"Running `echo` to confirm shell access and print output."}}
{"type":"item.started","item":{"id":"item_3","item_type":"command_execution","command":"bash -lc echo hello","aggregated_output":"","exit_code":null,"status":"in_progress"}}
{"type":"item.completed","item":{"id":"item_3","item_type":"command_execution","command":"bash -lc echo hello","aggregated_output":"hello\n","exit_code":0,"status":"completed"}}
{"type":"item.completed","item":{"id":"item_4","item_type":"assistant_message","text":"hello"}}
```
This changes the reqwest client used in tests to be sandbox-friendly,
and skips a bunch of other tests that don't work inside the
sandbox/without network.
This pull request add a new experimental format of JSON output.
You can try it using `codex exec --experimental-json`.
Design takes a lot of inspiration from Responses API items and stream
format.
# Session and items
Each invocation of `codex exec` starts or resumes a session.
Session contains multiple high-level item types:
1. Assistant message
2. Assistant thinking
3. Command execution
4. File changes
5. To-do lists
6. etc.
# Events
Session and items are going through their life cycles which is
represented by events.
Session is `session.created` or `session.resumed`
Items are `item.added`, `item.updated`, `item.completed`,
`item.require_approval` (or other item types like `item.output_delta`
when we need streaming).
So a typical session can look like:
<details>
```
{
"type": "session.created",
"session_id": "01997dac-9581-7de3-b6a0-1df8256f2752"
}
{
"type": "item.completed",
"item": {
"id": "itm_0",
"item_type": "assistant_message",
"text": "I’ll locate the top-level README and remove its first line. Then I’ll show a quick summary of what changed."
}
}
{
"type": "item.completed",
"item": {
"id": "itm_1",
"item_type": "command_execution",
"command": "bash -lc ls -la | sed -n '1,200p'",
"aggregated_output": "pyenv: cannot rehash: /Users/pakrym/.pyenv/shims isn't writable\ntotal 192\ndrwxr-xr-x@ 33 pakrym staff 1056 Sep 24 14:36 .\ndrwxr-xr-x 41 pakrym staff 1312 Sep 24 09:17 ..\n-rw-r--r--@ 1 pakrym staff 6 Jul 9 16:16 .codespellignore\n-rw-r--r--@ 1 pakrym staff 258 Aug 13 09:40 .codespellrc\ndrwxr-xr-x@ 5 pakrym staff 160 Jul 23 08:26 .devcontainer\n-rw-r--r--@ 1 pakrym staff 6148 Jul 22 10:03 .DS_Store\ndrwxr-xr-x@ 15 pakrym staff 480 Sep 24 14:38 .git\ndrwxr-xr-x@ 12 pakrym staff 384 Sep 2 16:00 .github\n-rw-r--r--@ 1 pakrym staff 778 Jul 9 16:16 .gitignore\ndrwxr-xr-x@ 3 pakrym staff 96 Aug 11 09:37 .husky\n-rw-r--r--@ 1 pakrym staff 104 Jul 9 16:16 .npmrc\n-rw-r--r--@ 1 pakrym staff 96 Sep 2 08:52 .prettierignore\n-rw-r--r--@ 1 pakrym staff 170 Jul 9 16:16 .prettierrc.toml\ndrwxr-xr-x@ 5 pakrym staff 160 Sep 14 17:43 .vscode\ndrwxr-xr-x@ 2 pakrym staff 64 Sep 11 11:37 2025-09-11\n-rw-r--r--@ 1 pakrym staff 5505 Sep 18 09:28 AGENTS.md\n-rw-r--r--@ 1 pakrym staff 92 Sep 2 08:52 CHANGELOG.md\n-rw-r--r--@ 1 pakrym staff 1145 Jul 9 16:16 cliff.toml\ndrwxr-xr-x@ 11 pakrym staff 352 Sep 24 13:03 codex-cli\ndrwxr-xr-x@ 38 pakrym staff 1216 Sep 24 14:38 codex-rs\ndrwxr-xr-x@ 18 pakrym staff 576 Sep 23 11:01 docs\n-rw-r--r--@ 1 pakrym staff 2038 Jul 9 16:16 flake.lock\n-rw-r--r--@ 1 pakrym staff 1434 Jul 9 16:16 flake.nix\n-rw-r--r--@ 1 pakrym staff 10926 Jul 9 16:16 LICENSE\ndrwxr-xr-x@ 465 pakrym staff 14880 Jul 15 07:36 node_modules\n-rw-r--r--@ 1 pakrym staff 242 Aug 5 08:25 NOTICE\n-rw-r--r--@ 1 pakrym staff 578 Aug 14 12:31 package.json\n-rw-r--r--@ 1 pakrym staff 498 Aug 11 09:37 pnpm-lock.yaml\n-rw-r--r--@ 1 pakrym staff 58 Aug 11 09:37 pnpm-workspace.yaml\n-rw-r--r--@ 1 pakrym staff 2402 Jul 9 16:16 PNPM.md\n-rw-r--r--@ 1 pakrym staff 4393 Sep 12 14:36 README.md\ndrwxr-xr-x@ 4 pakrym staff 128 Sep 18 09:28 scripts\ndrwxr-xr-x@ 2 pakrym staff 64 Sep 11 11:34 tmp\n",
"exit_code": 0,
"status": "completed"
}
}
{
"type": "item.completed",
"item": {
"id": "itm_2",
"item_type": "reasoning",
"text": "**Reviewing README.md file**\n\nI've located the README.md file at the root, and it’s 4393 bytes. Now, I need to remove the first line, but first, I should check its content to make sure I’m patching it correctly. I’ll use sed to display the first 20 lines. By reviewing those lines, I can determine exactly what needs to be removed before I proceed with the editing. Let's do this carefully!"
}
}
{
"type": "item.completed",
"item": {
"id": "itm_3",
"item_type": "command_execution",
"command": "bash -lc sed -n '1,40p' README.md",
"aggregated_output": "<h1 align=\"center\">OpenAI Codex CLI</h1>\n\n<p align=\"center\"><code>npm i -g @openai/codex</code><br />or <code>brew install codex</code></p>\n\n<p align=\"center\"><strong>Codex CLI</strong> is a coding agent from OpenAI that runs locally on your computer.\n</br>\n</br>If you want Codex in your code editor (VS Code, Cursor, Windsurf), <a href=\"https://developers.openai.com/codex/ide\">install in your IDE</a>\n</br>If you are looking for the <em>cloud-based agent</em> from OpenAI, <strong>Codex Web</strong>, go to <a href=\"https://chatgpt.com/codex\">chatgpt.com/codex</a></p>\n\n<p align=\"center\">\n <img src=\"./.github/codex-cli-splash.png\" alt=\"Codex CLI splash\" width=\"80%\" />\n </p>\n\n---\n\n## Quickstart\n\n### Installing and running Codex CLI\n\nInstall globally with your preferred package manager. If you use npm:\n\n```shell\nnpm install -g @openai/codex\n```\n\nAlternatively, if you use Homebrew:\n\n```shell\nbrew install codex\n```\n\nThen simply run `codex` to get started:\n\n```shell\ncodex\n```\n\n<details>\n<summary>You can also go to the <a href=\"https://github.com/openai/codex/releases/latest\">latest GitHub Release</a> and download the appropriate binary for your platform.</summary>\n\n",
"exit_code": 0,
"status": "completed"
}
}
{
"type": "item.completed",
"item": {
"id": "itm_4",
"item_type": "reasoning",
"text": "**Updating README file**\n\nThe user wants to update the README by removing the first line, which is an HTML h1 tag. I'll proceed to delete that line while keeping the rest intact. To do this, I need to use the apply_patch tool and create a patch in the diff format. I’ll take care to include context lines around the change. After removing the header, I’m considering whether to delete the following blank line as well to keep it tidy."
}
}
{
"type": "item.completed",
"item": {
"id": "itm_5",
"item_type": "reasoning",
"text": "**Crafting the patch**\n\nThe user has asked to remove just the first line, without mentioning the blank lines. Technically, leaving a blank line at the start is acceptable, but it's not ideal. Ideally, I'd prefer to remove the first line while maintaining the subsequent blank line. However, if I can also remove that blank line, it could tidy things up even more. Still, since the user's request is strictly to remove only the first line, I'll stick to that and craft the patch accordingly."
}
}
{
"type": "item.completed",
"item": {
"id": "itm_6",
"item_type": "assistant_message",
"text": "Applying the change by removing the first line from `README.md`."
}
}
{
"type": "item.completed",
"item": {
"id": "itm_7",
"item_type": "file_change",
"changes": [
{
"path": "/Users/pakrym/code/codex/README.md",
"kind": "update"
}
],
"status": "completed"
}
}
{
"type": "item.completed",
"item": {
"id": "itm_8",
"item_type": "reasoning",
"text": "**Validating README Update**\n\nI updated the README.md and now I need to validate that the first line has been successfully removed. To do this, I'll check the first 10 lines of the document to ensure everything looks correct. It’s always good to double-check these kinds of changes, so I’m going to take that extra step to make sure the update was executed properly. Let's see what those initial lines say!"
}
}
{
"type": "item.completed",
"item": {
"id": "itm_9",
"item_type": "command_execution",
"command": "bash -lc sed -n '1,20p' README.md",
"aggregated_output": "\n<p align=\"center\"><code>npm i -g @openai/codex</code><br />or <code>brew install codex</code></p>\n\n<p align=\"center\"><strong>Codex CLI</strong> is a coding agent from OpenAI that runs locally on your computer.\n</br>\n</br>If you want Codex in your code editor (VS Code, Cursor, Windsurf), <a href=\"https://developers.openai.com/codex/ide\">install in your IDE</a>\n</br>If you are looking for the <em>cloud-based agent</em> from OpenAI, <strong>Codex Web</strong>, go to <a href=\"https://chatgpt.com/codex\">chatgpt.com/codex</a></p>\n\n<p align=\"center\">\n <img src=\"./.github/codex-cli-splash.png\" alt=\"Codex CLI splash\" width=\"80%\" />\n </p>\n\n---\n\n## Quickstart\n\n### Installing and running Codex CLI\n\nInstall globally with your preferred package manager. If you use npm:\n\n",
"exit_code": 0,
"status": "completed"
}
}
{
"type": "item.completed",
"item": {
"id": "itm_10",
"item_type": "assistant_message",
"text": "- Updated `README.md:1` by removing the opening H1 line.\n- The README now starts with the install instructions paragraph.\n\nWant me to also remove the leading blank line at the top?"
}
}
```
</details>
The idea is to give users fully formatted items they can use directly in
their rendering/application logic and avoid having them building up
items manually based on events (unless they want to for streaming).
This PR implements only the `item.completed` payload for some event
types, more event types and item types to come.
---------
Co-authored-by: Michael Bolin <mbolin@openai.com>
Adding the ability to resume conversations.
we have one verb `resume`.
Behavior:
`tui`:
`codex resume`: opens session picker
`codex resume --last`: continue last message
`codex resume <session id>`: continue conversation with `session id`
`exec`:
`codex resume --last`: continue last conversation
`codex resume <session id>`: continue conversation with `session id`
Implementation:
- I added a function to find the path in `~/.codex/sessions/` with a
`UUID`. This is helpful in resuming with session id.
- Added the above mentioned flags
- Added lots of testing
Created this PR by:
- adding `redundant_clone` to `[workspace.lints.clippy]` in
`cargo-rs/Cargol.toml`
- running `cargo clippy --tests --fix`
- running `just fmt`
Though I had to clean up one instance of the following that resulted:
```rust
let codex = codex;
```
