Agent wouldn't "see" attached images and would instead try to use the
view_file tool:
<img width="1516" height="504" alt="image"
src="https://github.com/user-attachments/assets/68a705bb-f962-4fc1-9087-e932a6859b12"
/>
In this PR, we wrap image content items in XML tags with the name of
each image (now just a numbered name like `[Image #1]`), so that the
model can understand inline image references (based on name). We also
put the image content items above the user message which the model seems
to prefer (maybe it's more used to definitions being before references).
We also tweak the view_file tool description which seemed to help a bit
Results on a simple eval set of images:
Before
<img width="980" height="310" alt="image"
src="https://github.com/user-attachments/assets/ba838651-2565-4684-a12e-81a36641bf86"
/>
After
<img width="918" height="322" alt="image"
src="https://github.com/user-attachments/assets/10a81951-7ee6-415e-a27e-e7a3fd0aee6f"
/>
```json
[
{
"id": "single_describe",
"prompt": "Describe the attached image in one sentence.",
"images": ["image_a.png"]
},
{
"id": "single_color",
"prompt": "What is the dominant color in the image? Answer with a single color word.",
"images": ["image_b.png"]
},
{
"id": "orientation_check",
"prompt": "Is the image portrait or landscape? Answer in one sentence.",
"images": ["image_c.png"]
},
{
"id": "detail_request",
"prompt": "Look closely at the image and call out any small details you notice.",
"images": ["image_d.png"]
},
{
"id": "two_images_compare",
"prompt": "I attached two images. Are they the same or different? Briefly explain.",
"images": ["image_a.png", "image_b.png"]
},
{
"id": "two_images_captions",
"prompt": "Provide a short caption for each image (Image 1, Image 2).",
"images": ["image_c.png", "image_d.png"]
},
{
"id": "multi_image_rank",
"prompt": "Rank the attached images from most colorful to least colorful.",
"images": ["image_a.png", "image_b.png", "image_c.png"]
},
{
"id": "multi_image_choice",
"prompt": "Which image looks more vibrant? Answer with 'Image 1' or 'Image 2'.",
"images": ["image_b.png", "image_d.png"]
}
]
```
Some enterprises do not want their users to be able to `/feedback`.
<img width="395" height="325" alt="image"
src="https://github.com/user-attachments/assets/2dae9c0b-20c3-4a15-bcd3-0187857ebbd8"
/>
Adds to `config.toml`:
```toml
[feedback]
enabled = false
```
I've deliberately decided to:
1. leave other references to `/feedback` (e.g. in the interrupt message,
tips of the day) unchanged. I think we should continue to promote the
feature even if it is not usable currently.
2. leave the `/feedback` menu item selectable and display an error
saying it's disabled, rather than remove the menu item (which I believe
would raise more questions).
but happy to discuss these.
This will be followed by a change to requirements.toml that admins can
use to force the value of feedback.enabled.
Add `ctrl+g` shortcut to enable opening current prompt in configured
editor (`$VISUAL` or `$EDITOR`).
- Prompt is updated with editor's content upon editor close.
- Paste placeholders are automatically expanded when opening the
external editor, and are not "recompressed" on close
- They could be preserved in the editor, but it would be hard to prevent
the user from modifying the placeholder text directly, which would drop
the mapping to the `pending_paste` value
- Image placeholders stay as-is
- `ctrl+g` explanation added to shortcuts menu, snapshot tests updated
https://github.com/user-attachments/assets/4ee05c81-fa49-4e99-8b07-fc9eef0bbfce
1. Skills load once in core at session start; the cached outcome is
reused across core and surfaced to TUI via SessionConfigured.
2. TUI detects explicit skill selections, and core injects the matching
SKILL.md content into the turn when a selected skill is present.
## Updating the `execpolicy` TUI flow
In the TUI, when going through the command approval flow, codex will now
ask the user if they would like to whitelist the FIRST unmatched command
among a chain of commands.
For example, let's say the agent wants to run `apple | pear` with an
empty `execpolicy`
Neither apple nor pear will match to an `execpolicy` rule. Thus, when
prompting the user, codex tui will ask the user if they would like to
whitelist `apple`.
If the agent wants to run `apple | pear` again, they would be prompted
again because pear is still unknown. when prompted, the user will now be
asked if they'd like to whitelist `pear`.
Here's a demo video of this flow:
https://github.com/user-attachments/assets/fd160717-f6cb-46b0-9f4a-f0a974d4e710
This PR also removed the `allow for this session` option from the TUI.
## Refactor of the `execpolicy` crate
To illustrate why we need this refactor, consider an agent attempting to
run `apple | rm -rf ./`. Suppose `apple` is allowed by `execpolicy`.
Before this PR, `execpolicy` would consider `apple` and `pear` and only
render one rule match: `Allow`. We would skip any heuristics checks on
`rm -rf ./` and immediately approve `apple | rm -rf ./` to run.
To fix this, we now thread a `fallback` evaluation function into
`execpolicy` that runs when no `execpolicy` rules match a given command.
In our example, we would run `fallback` on `rm -rf ./` and prevent
`apple | rm -rf ./` from being run without approval.
this PR enables TUI to approve commands and add their prefixes to an
allowlist:
<img width="708" height="605" alt="Screenshot 2025-11-21 at 4 18 07 PM"
src="https://github.com/user-attachments/assets/56a19893-4553-4770-a881-becf79eeda32"
/>
note: we only show the option to whitelist the command when
1) command is not multi-part (e.g `git add -A && git commit -m 'hello
world'`)
2) command is not already matched by an existing rule
This PR adds support for a new feature flag `tui.animations`. By
default, the TUI uses animations in its welcome screen, "working"
spinners, and "shimmer" effects. This animations can interfere with
screen readers, so it's good to provide a way to disable them.
This change is inspired by [a
PR](https://github.com/openai/codex/pull/4014) contributed by @Orinks.
That PR has faltered a bit, but I think the core idea is sound. This
version incorporates feedback from @aibrahim-oai. In particular:
1. It uses a feature flag (`tui.animations`) rather than the unqualified
CLI key `no-animations`. Feature flags are the preferred way to expose
boolean switches. They are also exposed via CLI command switches.
2. It includes more complete documentation.
3. It disables a few animations that the other PR omitted.
## Summary
- show live review token usage while `/review` runs and restore the main
session indicator afterward
- add regression coverage for the footer behavior
## Testing
- just fmt
- cargo test -p codex-tui
Fixes#5604
---------
Signed-off-by: Fahad <fahad@2doapp.com>
- introduce RenderableItem to support both owned and borrowed children
in composite Renderables
- refactor some of our gnarlier manual layouts, BottomPane and
ChatWidget, to use ColumnRenderable
- Renderable and friends now handle cursor_pos()
This fixes an issue where messages sent during the final response stream
would seem to disappear, because the "queued messages" UI wasn't shown
during streaming.
This PR adds support for a model-based summary and risk assessment for
commands that violate the sandbox policy and require user approval. This
aids the user in evaluating whether the command should be approved.
The feature works by taking a failed command and passing it back to the
model and asking it to summarize the command, give it a risk level (low,
medium, high) and a risk category (e.g. "data deletion" or "data
exfiltration"). It uses a new conversation thread so the context in the
existing thread doesn't influence the answer. If the call to the model
fails or takes longer than 5 seconds, it falls back to the current
behavior.
For now, this is an experimental feature and is gated by a config key
`experimental_sandbox_command_assessment`.
Here is a screen shot of the approval prompt showing the risk assessment
and summary.
<img width="723" height="282" alt="image"
src="https://github.com/user-attachments/assets/4597dd7c-d5a0-4e9f-9d13-414bd082fd6b"
/>
## Summary
- show the remaining context window percentage in `/status` alongside
existing token usage details
- replace the composer shortcut prompt with the context window
percentage (or an unavailable message) while a task is running
- update TUI snapshots to reflect the new context window line
## Testing
- cargo test -p codex-tui
------
https://chatgpt.com/codex/tasks/task_i_68dc6e7397ac8321909d7daff25a396c
Instead of overwriting the contents of the composer when pressing
<kbd>Esc</kbd> when there's a queued message, prepend the queued
message(s) to the composer draft.
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
Ahmed Ibrahim