## Summary
Introduces a “ghost commit” workflow that snapshots the tree without
touching refs.
1. git commit-tree writes an unreferenced commit object from the current
index, optionally pointing to the current HEAD as its parent.
2. We then stash that commit id and use git restore --source <ghost> to
roll the worktree (and index) back to the recorded snapshot later on.
## Details
- Ghost commits live only as loose objects—we never update branches or
tags—so the repo history stays untouched while still giving us a full
tree snapshot.
- Force-included paths let us stage otherwise ignored files before
capturing the tree.
- Restoration rehydrates both tracked and force-included files while
leaving untracked/ignored files alone.
Adds a "View Stack" to the bottom pane to allow for pushing/popping
bottom panels.
`esc` will go back instead of dismissing.
Benefit: We retain the "selection state" of a parent panel (e.g. the
review panel).
Adds the following options:
1. Review current changes
2. Review a specific commit
3. Review against a base branch (PR style)
4. Custom instructions
<img width="487" height="330" alt="Screenshot 2025-09-20 at 2 11 36 PM"
src="https://github.com/user-attachments/assets/edb0aaa5-5747-47fa-881f-cc4c4f7fe8bc"
/>
---
\+ Adds the following UI helpers:
1. Makes list selection searchable
2. Adds navigation to the bottom pane, so you could add a stack of
popups
3. Basic custom prompt view
## 📝 Review Mode -- Core
This PR introduces the Core implementation for Review mode:
- New op `Op::Review { prompt: String }:` spawns a child review task
with isolated context, a review‑specific system prompt, and a
`Config.review_model`.
- `EnteredReviewMode`: emitted when the child review session starts.
Every event from this point onwards reflects the review session.
- `ExitedReviewMode(Option<ReviewOutputEvent>)`: emitted when the review
finishes or is interrupted, with optional structured findings:
```json
{
"findings": [
{
"title": "<≤ 80 chars, imperative>",
"body": "<valid Markdown explaining *why* this is a problem; cite files/lines/functions>",
"confidence_score": <float 0.0-1.0>,
"priority": <int 0-3>,
"code_location": {
"absolute_file_path": "<file path>",
"line_range": {"start": <int>, "end": <int>}
}
}
],
"overall_correctness": "patch is correct" | "patch is incorrect",
"overall_explanation": "<1-3 sentence explanation justifying the overall_correctness verdict>",
"overall_confidence_score": <float 0.0-1.0>
}
```
## Questions
### Why separate out its own message history?
We want the review thread to match the training of our review models as
much as possible -- that means using a custom prompt, removing user
instructions, and starting a clean chat history.
We also want to make sure the review thread doesn't leak into the parent
thread.
### Why do this as a mode, vs. sub-agents?
1. We want review to be a synchronous task, so it's fine for now to do a
bespoke implementation.
2. We're still unclear about the final structure for sub-agents. We'd
prefer to land this quickly and then refactor into sub-agents without
rushing that implementation.
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;
```
This PR changes get history op to get path. Then, forking will use a
path. This will help us have one unified codepath for resuming/forking
conversations. Will also help in having rollout history in order. It
also fixes a bug where you won't see the UI when resuming after forking.
We're trying to migrate from `session_id: Uuid` to `conversation_id:
ConversationId`. Not only does this give us more type safety but it
unifies our terminology across Codex and with the implementation of
session resuming, a conversation (which can span multiple sessions) is
more appropriate.
I started this impl on https://github.com/openai/codex/pull/3219 as part
of getting resume working in the extension but it's big enough that it
should be broken out.
This updates the ctrl + c behavior to clear the current prompt if there
is text and you press ctrl + c.
I also updated the ctrl + c hint text to show `^c to interrupt` instead
of `^c to quit` if there is an active conversation.
Two things I don't love:
1. You can currently interrupt a conversation with escape or ctrl + c
(not related to this PR and maybe fine)
2. The bottom row hint text always says `^c to quit` but this PR doesn't
really make that worse.
https://github.com/user-attachments/assets/6eddadec-0d84-4fa7-abcb-d6f5a04e5748
Fixes https://github.com/openai/codex/issues/3126
TuiEvent is supposed to be purely events that come from the "driver",
i.e. events from the terminal. Everything app-specific should be an
AppEvent. In this case, it didn't need to be an event at all.
#### Summary
- Emit a “Proposed Command” history cell when an ExecApprovalRequest
arrives (parity with proposed patches).
- Simplify the approval dialog: show only the reason/instructions; move
the command preview into history.
- Make approval/abort decision history concise:
- Single line snippet; if multiline, show first line + " ...".
- Truncate to 80 graphemes with ellipsis for very long commands.
#### Details
- History
- Add `new_proposed_command` to render a header and indented command
preview.
- Use shared `prefix_lines` helper for first/subsequent line prefixes.
- Approval UI
- `UserApprovalWidget` no longer renders the command in the modal; shows
optional `reason` text only.
- Decision history renders an inline, dimmed snippet per rules above.
- Tests (snapshot-based)
- Proposed/decision flow for short command.
- Proposed multi-line + aborted decision snippet with “ ...”.
- Very long one-line command -> truncated snippet with “…”.
- Updated existing exec approval snapshots and test reasons.
<img width="1053" height="704" alt="Screenshot 2025-09-03 at 11 57
35 AM"
src="https://github.com/user-attachments/assets/9ed4c316-9daf-4ac1-80ff-7ae1f481dd10"
/>
after approving:
<img width="1053" height="704" alt="Screenshot 2025-09-03 at 11 58
18 AM"
src="https://github.com/user-attachments/assets/a44e243f-eb9d-42ea-87f4-171b3fb481e7"
/>
rejection:
<img width="1053" height="207" alt="Screenshot 2025-09-03 at 11 58
45 AM"
src="https://github.com/user-attachments/assets/a022664b-ae0e-4b70-a388-509208707934"
/>
big command:
https://github.com/user-attachments/assets/2dd976e5-799f-4af7-9682-a046e66cc494
#### Summary
Avoid a potential panic when rendering the active execution cell when
the allocated area has zero height.
#### Changes
- Guard rendering with `active_cell_area.height > 0` and presence of
`active_exec_cell`.
- Use `saturating_add(1)` for the Y offset to avoid overflow.
- Render via `active_exec_cell.as_ref().unwrap().render_ref(...)` after
the explicit `is_some` check.
Adds a TUI resume flow with an interactive picker and quick resume.
- CLI:
- --resume / -r: open picker to resume a prior session
- --continue / -l: resume the most recent session (no picker)
- Behavior on resume: initial history is replayed, welcome banner
hidden, and the first redraw is suppressed to avoid flicker.
- Implementation:
- New tui/src/resume_picker.rs (paginated listing via
RolloutRecorder::list_conversations)
- App::run accepts ResumeSelection; resumes from disk when requested
- ChatWidget refactor with ChatWidgetInit and new_from_existing; replays
initial messages
- Tests: cover picker sorting/preview extraction and resumed-history
rendering.
- Docs: getting-started updated with flags and picker usage.
https://github.com/user-attachments/assets/1bb6469b-e5d1-42f6-bec6-b1ae6debda3b
This PR does the following:
- divides user msgs into 3 categories: plain, user instructions, and
environment context
- Centralizes adding user instructions and environment context to a
degree
- Improve the integration testing
Building on top of #3123
Specifically this
[comment](https://github.com/openai/codex/pull/3123#discussion_r2319885089).
We need to send the user message while ignoring the User Instructions
and Environment Context we attach.
- Introduce websearch end to complement the begin
- Moves the logic of adding the sebsearch tool to
create_tools_json_for_responses_api
- Making it the client responsibility to toggle the tool on or off
- Other misc in #2371 post commit feedback
- Show the query:
<img width="1392" height="151" alt="image"
src="https://github.com/user-attachments/assets/8457f1a6-f851-44cf-bcca-0d4fe460ce89"
/>
Adds custom `/prompts` to `~/.codex/prompts/<command>.md`.
<img width="239" height="107" alt="Screenshot 2025-08-25 at 6 22 42 PM"
src="https://github.com/user-attachments/assets/fe6ebbaa-1bf6-49d3-95f9-fdc53b752679"
/>
---
Details:
1. Adds `Op::ListCustomPrompts` to core.
2. Returns `ListCustomPromptsResponse` with list of `CustomPrompt`
(name, content).
3. TUI calls the operation on load, and populates the custom prompts
(excluding prompts that collide with builtins).
4. Selecting the custom prompt automatically sends the prompt to the
agent.
This PR fixes two edge cases in managing burst paste (mainly on power
shell).
Bugs:
- Needs an event key after paste to render the pasted items
> ChatComposer::flush_paste_burst_if_due() flushes on timeout. Called:
> - Pre-render in App on TuiEvent::Draw.
> - Via a delayed frame
>
BottomPane::request_redraw_in(ChatComposer::recommended_paste_flush_delay()).
- Parses two key events separately before starting parsing burst paste
> When threshold is crossed, pull preceding burst chars out of the
textarea and prepend to paste_burst_buffer, then keep buffering.
- Integrates with #2567 to bring image pasting to windows.
Esc and Ctrl+C while a task is running should do the same thing. There
were some cases where pressing Esc would leave a "stuck" widget in the
history; this fixes that and cleans up the logic so there's just one
path for interrupting the task. Also clean up some subtly mishandled key
events (e.g. Ctrl+D would quit the app while an approval modal was
showing if the textarea was empty).
---------
Co-authored-by: Ahmed Ibrahim <aibrahim@openai.com>
