## Why
`codex-shell-escalation` exposed a `codex-core`-specific adapter layer
(`ShellActionProvider`, `ShellPolicyFactory`, and `run_escalate_server`)
that existed only to bridge `codex-core` to `EscalateServer`. That
indirection increased API surface and obscured crate ownership without
adding behavior.
This change moves orchestration into `codex-core` so boundaries are
clearer: `codex-shell-escalation` provides reusable escalation
primitives, and `codex-core` provides shell-tool policy decisions.
Admittedly, @pakrym rightfully requested this sort of cleanup as part of
https://github.com/openai/codex/pull/12649, though this avoids moving
all of `codex-shell-escalation` into `codex-core`.
## What changed
- Made `EscalateServer` public and exported it from `shell-escalation`.
- Removed the adapter layer from `shell-escalation`:
- deleted `shell-escalation/src/unix/core_shell_escalation.rs`
- removed exports for `ShellActionProvider`, `ShellPolicyFactory`,
`EscalationPolicyFactory`, and `run_escalate_server`
- Updated `core/src/tools/runtimes/shell/unix_escalation.rs` to:
- create `Stopwatch`/cancellation in `codex-core`
- instantiate `EscalateServer` directly
- implement `EscalationPolicy` directly on `CoreShellActionProvider`
Net effect: same escalation flow with fewer wrappers and a smaller
public API.
## Verification
- Manually reviewed the old vs. new escalation call flow to confirm
timeout/cancellation behavior and approval policy decisions are
preserved while removing wrapper types.
Increase `IMAGE_BYTES_ESTIMATE` from 340 bytes to 7,373 bytes so the
existing 4-bytes/token heuristic yields an image estimate of ~1,844
tokens instead of ~85. This makes auto-compaction more conservative for
image-heavy transcripts and avoids underestimating context usage, which
can otherwise cause compaction to fail when there is not enough free
context remaining. The new value was chosen because that's the image
resolution cap used for our latest models.
Follow-up to [#12419](https://github.com/openai/codex/pull/12419).
Refs [#11845](https://github.com/openai/codex/issues/11845).
Fixes#12128
The docs indicates that `project_root_markers` are used to discover the
project root for local config as well as `AGENTS.md`. It looks like it
was never wired up to support the latter.
Summary
- resolve project docs by walking to the configured
`project_root_markers` (or defaults) instead of assuming the Git root,
while honoring CLI overrides and handling malformed configs
- fall back to the project’s canonical path chain and add a test that
makes sure custom markers upstream of `.git` are respected
- Add a hidden `realtime_conversation` feature flag and `/realtime`
slash command for start/stop live voice sessions.
- Reuse transcription composer/footer UI for live metering, stream mic
audio, play assistant audio, render realtime user text events, and
force-close on feature disable.
---------
Co-authored-by: Codex <noreply@openai.com>
Summary
- detect skill-invoking shell commands based on the original command
string, request approvals when needed, and cache positive decisions per
session
- keep implicit skill invocation emitted after approval and keep skill
approval decline messaging centralized to the shell handler
- expand and adjust skill approval tests to cover shell-based skill
scripts while matching the new detection expectations
Testing
- Not run (not requested)
## Problem
Diff lines used only foreground colors (green/red) with no background
tinting, making them hard to scan. The gutter (line numbers) also had no
theme awareness — dimmed text was fine on dark terminals but unreadable
on light ones.
## Mental model
Each diff line now has four styled layers: **gutter** (line number),
**sign** (`+`/`-`), **content** (text), and **line background** (full
terminal width). A `DiffTheme` enum (`Dark` / `Light`) is selected once
per render by probing the terminal's queried background via
`default_bg()`. A companion `DiffColorLevel` enum (`TrueColor` /
`Ansi256` / `Ansi16`) is derived from `stdout_color_level()` and gates
which palette is used. All style helpers dispatch on `(theme,
DiffLineType, color_level)` to pick the right colors.
| Theme Picker Wide | Theme Picker Narrow |
|---|---|
| <img width="1552" height="1012" alt="image"
src="https://github.com/user-attachments/assets/231b21b7-32d4-4727-80ed-7d01924954be"
/> | <img width="795" height="1012" alt="image"
src="https://github.com/user-attachments/assets/549cacdf-daec-43c9-ad64-2a28d16d140e"
/> |
| Dark BG - 16 colors | Dark BG - 256 colors | Dark BG - True Colors |
|---|---|---|
| <img width="1552" height="1012" alt="dark-16colors"
src="https://github.com/user-attachments/assets/fba36de3-c101-47d4-9e63-88cdd00410d0"
/> | <img width="1552" height="1012" alt="dark-256colors"
src="https://github.com/user-attachments/assets/f39e4307-c6b0-49c4-b4fe-bd26d3d8e41c"
/> | <img width="1552" height="1012" alt="dark-truecolor"
src="https://github.com/user-attachments/assets/1af4ec57-04bf-4dfb-8a44-0ab5e5aaaf18"
/> |
| Light BG - 16 colors | Light BG - 256 colors | Light BG - True Colors
|
|---|---|---|
| <img width="1552" height="1012" alt="light-16colors"
src="https://github.com/user-attachments/assets/2b5423d1-74b4-4b1e-8123-7c2488ff436b"
/> | <img width="1552" height="1012" alt="light-256colors"
src="https://github.com/user-attachments/assets/c94cff9a-8d3e-42c9-bbe7-079da39953a8"
/> | <img width="1552" height="1012" alt="light-truecolor"
src="https://github.com/user-attachments/assets/f73da626-725f-4452-99ee-69ef706df2c6"
/> |
## Non-goals
- No runtime theme switching beyond what `default_bg()` already
provides.
- No change to syntax highlighting theme selection or the highlight
module.
## Tradeoffs
- Three fixed palettes (truecolor RGB, 256-color indexed, 16-color
named) are maintained rather than using `best_color` nearest-match. This
is deliberate: `supports_color::on_cached(Stream::Stdout)` can misreport
capabilities once crossterm enters the alternate screen, so hand-picked
palette entries give better visual results than automatic quantization.
- Delete lines in the syntax-highlighted path get `Modifier::DIM` to
visually recede compared to insert lines. This trades some readability
of deleted code for scan-ability of additions.
- The theme picker's diff preview sets `preserve_side_content_bg: true`
on `ListSelectionView` so diff background tints survive into the side
panel. Other popups keep the default (`false`) to preserve their
reset-background look.
## Architecture
- **Color constants** are module-level `const` items grouped by palette
tier: `DARK_TC_*` / `LIGHT_TC_*` (truecolor RGB tuples), `DARK_256_*` /
`LIGHT_256_*` (xterm indexed), with named `Color` variants used for the
16-color tier.
- **`DiffTheme`** is a private enum; `diff_theme()` probes the terminal
and `diff_theme_for_bg()` is the testable pure-function version.
- **`DiffColorLevel`** is a private enum derived from `StdoutColorLevel`
via `diff_color_level()`.
- **Palette helpers** (`add_line_bg`, `del_line_bg`, `light_gutter_fg`,
`light_add_num_bg`, `light_del_num_bg`) each take `(DiffTheme,
DiffColorLevel)` or just `DiffColorLevel` and return a `Color`.
- **Style helpers** (`style_line_bg_for`, `style_gutter_for`,
`style_sign_add`, `style_sign_del`, `style_add`, `style_del`) each take
`(DiffLineType, DiffTheme, DiffColorLevel)` or `(DiffTheme,
DiffColorLevel)` and return a `Style`.
- **`push_wrapped_diff_line_inner_with_theme_and_color_level`** is the
innermost renderer, accepting both theme and color level so tests can
exercise any combination without depending on the terminal.
- **Line-level background** is applied via
`RtLine::from(...).style(line_bg)` so the tint extends across the full
terminal width, not just the text content.
- **Theme picker integration**: `ListSelectionView` gained a
`preserve_side_content_bg` flag. When `true`, the side panel skips
`force_bg_to_terminal_bg`, letting diff preview backgrounds render
faithfully.
## Observability
No new logging. Theme selection is deterministic from `default_bg()`,
which is already queried and cached at TUI startup.
## Tests
1. **`DiffTheme` is determined per `render_change` call** — if
`default_bg()` changes mid-render (e.g. `requery_default_colors()`
fires), different file chunks could render with different themes. Low
risk in practice since re-query only happens on explicit user action.
2. **16-color tier uses named `Color` variants** (`Color::Green`,
`Color::Red`, etc.) which the terminal maps to its own palette. On
unusual terminal themes these could clash with the background.
Acceptable since 16-color terminals already have unpredictable color
rendering.
3. **Light-theme `style_add` / `style_del` set bg but no fg** — on light
terminals, non-syntax-highlighted content uses the terminal's default
foreground against a pastel background. If the terminal's default fg
happens to be very light, contrast could suffer. This is an edge case
since light-terminal users typically have dark default fg.
4. **`preserve_side_content_bg` is a general-purpose flag but only used
by the theme picker** — if other popups start using side content with
intentional backgrounds they'll need to opt in explicitly. Not a real
risk today, just a note for future callers.
#### What
Try matching `\w+`-namespaced model after `longest prefix` as heuristic
to match `ModelInfo` from list of candidates.
This shouldn't regress existing behavior:
- `gpt-5.2-codex` -> `gpt-5.2` if `gpt-5.2-codex` not present
- `gpt-5.3` -> `gpt-5` if `gpt-5.3` not present
- `gpt-9` still doesn't match anything
while being more forgiving for custom prefixes:
- `oai/gpt-5.3-codex` -> `gpt-5.3-codex`
#### Tests
Added unit test.
Fixes#12175
If a user types an npm package name with multiple `@` symbols like `npx
-y @foo/bar@latest`, the TUI currently treats this as though it's
attempting to invoke the file picker.
### What changed
- **Generalized `@` token parsing**
- `current_prefixed_token(...)` now treats `@` as a token start **only
at a whitespace boundary** (or start-of-line).
- If the cursor is on a nested `@` inside an existing
whitespace-delimited token (for example `@scope/pkg@latest`), it keeps
the surrounding token active instead of starting a new token at the
second `@`.
- It also avoids misclassifying mid-word usages like `foo@bar` as an `@`
file token.
- **Enter behavior with file popup**
- If the file-search popup is open but has **no selected match**,
pressing `Enter` now closes the popup and falls through to normal submit
behavior.
- This prevents pasted strings containing `@...` from blocking
submission just because file-search was active with no actionable
selection.
### Testing
I manually built and tested the scenarios involved with the bug report
and related use of `@` mentions to verify no regressions
## Why
This PR switches the `shell_command` zsh-fork path over to
`codex-shell-escalation` so the new shell tool can use the shared
exec-wrapper/escalation protocol instead of the `zsh_exec_bridge`
implementation that was introduced in
https://github.com/openai/codex/pull/12052. `zsh_exec_bridge` relied on
UNIX domain sockets, which is not as tamper-proof as the FD-based
approach in `codex-shell-escalation`.
## What Changed
- Added a Unix zsh-fork runtime adapter in `core`
(`core/src/tools/runtimes/shell/unix_escalation.rs`) that:
- runs zsh-fork commands through
`codex_shell_escalation::run_escalate_server`
- bridges exec-policy / approval decisions into `ShellActionProvider`
- executes escalated commands via a `ShellCommandExecutor` that calls
`process_exec_tool_call`
- Updated `ShellRuntime` / `ShellCommandHandler` / tool spec wiring to
select a `shell_command` backend (`classic` vs `zsh-fork`) while leaving
the generic `shell` tool path unchanged.
- Removed the `zsh_exec_bridge`-based session service and deleted
`core/src/zsh_exec_bridge/mod.rs`.
- Moved exec-wrapper entrypoint dispatch to `arg0` by handling the
`codex-execve-wrapper` arg0 alias there, and removed the old
`codex_core::maybe_run_zsh_exec_wrapper_mode()` hooks from `cli` and
`app-server` mains.
- Added the needed `codex-shell-escalation` dependencies for `core` and
`arg0`.
## Tests
- `cargo test -p codex-core
shell_zsh_fork_prefers_shell_command_over_unified_exec`
- `cargo test -p codex-app-server turn_start_shell_zsh_fork --
--nocapture`
- verifies zsh-fork command execution and approval flows through the new
backend
- includes subcommand approve/decline coverage using the shared zsh
DotSlash fixture in `app-server/tests/suite/zsh`
- To test manually, I added the following to `~/.codex/config.toml`:
```toml
zsh_path = "/Users/mbolin/code/codex3/codex-rs/app-server/tests/suite/zsh"
[features]
shell_zsh_fork = true
```
Then I ran `just c` to run the dev build of Codex with these changes and
sent it the message:
```
run `echo $0`
```
And it replied with:
```
echo $0 printed:
/Users/mbolin/code/codex3/codex-rs/app-server/tests/suite/zsh
In this tool context, $0 reflects the script path used to invoke the shell, not just zsh.
```
so the tool appears to be wired up correctly.
## Notes
- The zsh subcommand-decline integration test now uses `rm` under a
`WorkspaceWrite` sandbox. The previous `/usr/bin/true` scenario is
auto-allowed by the new `shell-escalation` policy path, which no longer
produces subcommand approval prompts.
## Summary
Introduces the initial implementation of Feature::RequestPermissions.
RequestPermissions allows the model to request that a command be run
inside the sandbox, with additional permissions, like writing to a
specific folder. Eventually this will include other rules as well, and
the ability to persist these permissions, but this PR is already quite
large - let's get the core flow working and go from there!
<img width="1279" height="541" alt="Screenshot 2026-02-15 at 2 26 22 PM"
src="https://github.com/user-attachments/assets/0ee3ec0f-02ec-4509-91a2-809ac80be368"
/>
## Testing
- [x] Added tests
- [x] Tested locally
- [x] Feature
Send a request with `generate: falls` but a full set of tools and
instructions to pre-warm inference.
---------
Co-authored-by: Codex <noreply@openai.com>
## Summary
- tighten the memory-use decision boundary so agents skip memory only
for clearly self-contained asks
- make the quick memory pass more explicit and bounded (including a
lightweight search budget)
- add structured `<memory_citation>` requirements and examples for final
replies
- clarify memory update guidance and end-state wording for memory lookup
## Why
The previous template was directionally correct, but still left room for
inconsistent memory lookup behavior and citation formatting. This change
makes the default behavior, quick-pass scope, and citation output
contract much more explicit.
## Testing
- not run (prompt/template text change only)
Co-authored-by: jif-oai <jif@openai.com>
Michael Bolin