This is a first cut at a GitHub Action that lets you define prompt
templates in `.md` files under `.github/codex/labels` that will run
Codex with the associated prompt when the label is added to a GitHub
pull request.
For example, this PR includes these files:
```
.github/codex/labels/codex-attempt.md
.github/codex/labels/codex-code-review.md
.github/codex/labels/codex-investigate-issue.md
```
And the new `.github/workflows/codex.yml` workflow declares the
following triggers:
```yaml
on:
issues:
types: [opened, labeled]
pull_request:
branches: [main]
types: [labeled]
```
as well as the following expression to gate the action:
```
jobs:
codex:
if: |
(github.event_name == 'issues' && (
(github.event.action == 'labeled' && (github.event.label.name == 'codex-attempt' || github.event.label.name == 'codex-investigate-issue'))
)) ||
(github.event_name == 'pull_request' && github.event.action == 'labeled' && github.event.label.name == 'codex-code-review')
```
Note the "actor" who added the label must have write access to the repo
for the action to take effect.
After adding a label, the action will "ack" the request by replacing the
original label (e.g., `codex-review`) with an `-in-progress` suffix
(e.g., `codex-review-in-progress`). When it is finished, it will swap
the `-in-progress` label with a `-completed` one (e.g.,
`codex-review-completed`).
Users of the action are responsible for providing an `OPENAI_API_KEY`
and making it available as a secret to the action.
The way these definitions worked before, they did not handle quoted args
with spaces properly.
For example, if you had `/tmp/test-just/printlen.py` as:
```python
#!/usr/bin/env python3
import sys
print(len(sys.argv))
```
and your `justfile` was:
```
printlen *args:
/tmp/test-just/printlen.py {{args}}
```
Then:
```shell
$ just printlen foo bar
3
$ just printlen 'foo bar'
3
```
which is not what we want: `'foo bar'` should be treated as one
argument.
The fix is to use
[positional-arguments](https://github.com/casey/just/blob/515e806b5121a4696113ef15b5f0b12e69854570/README.md#L1131):
```
set positional-arguments
printlen *args:
/tmp/test-just/printlen.py "$@"
```
The output of an MCP server tool call can be one of several types, but
to date, we treated all outputs as text by showing the serialized JSON
as the "tool output" in Codex:
https://github.com/openai/codex/blob/25a9949c49194d5a64de54a11bcc5b4724ac9bd5/codex-rs/mcp-types/src/lib.rs#L96-L101
This PR adds support for the `ImageContent` variant so we can now
display an image output from an MCP tool call.
In making this change, we introduce a new
`ResponseInputItem::McpToolCallOutput` variant so that we can work with
the `mcp_types::CallToolResult` directly when the function call is made
to an MCP server.
Though arguably the more significant change is the introduction of
`HistoryCell::CompletedMcpToolCallWithImageOutput`, which is a cell that
uses `ratatui_image` to render an image into the terminal. To support
this, we introduce `ImageRenderCache`, cache a
`ratatui_image::picker::Picker`, and `ensure_image_cache()` to cache the
appropriate scaled image data and dimensions based on the current
terminal size.
To test, I created a minimal `package.json`:
```json
{
"name": "kitty-mcp",
"version": "1.0.0",
"type": "module",
"description": "MCP that returns image of kitty",
"main": "index.js",
"dependencies": {
"@modelcontextprotocol/sdk": "^1.12.0"
}
}
```
with the following `index.js` to define the MCP server:
```js
#!/usr/bin/env node
import { McpServer } from "@modelcontextprotocol/sdk/server/mcp.js";
import { StdioServerTransport } from "@modelcontextprotocol/sdk/server/stdio.js";
import { readFile } from "node:fs/promises";
import { join } from "node:path";
const IMAGE_URI = "image://Ada.png";
const server = new McpServer({
name: "Demo",
version: "1.0.0",
});
server.tool(
"get-cat-image",
"If you need a cat image, this tool will provide one.",
async () => ({
content: [
{ type: "image", data: await getAdaPngBase64(), mimeType: "image/png" },
],
})
);
server.resource("Ada the Cat", IMAGE_URI, async (uri) => {
const base64Image = await getAdaPngBase64();
return {
contents: [
{
uri: uri.href,
mimeType: "image/png",
blob: base64Image,
},
],
};
});
async function getAdaPngBase64() {
const __dirname = new URL(".", import.meta.url).pathname;
// From https://github.com/benjajaja/ratatui-image/blob/9705ce2c59ec669abbce2924cbfd1f5ae22c9860/assets/Ada.png
const filePath = join(__dirname, "Ada.png");
const imageData = await readFile(filePath);
const base64Image = imageData.toString("base64");
return base64Image;
}
const transport = new StdioServerTransport();
await server.connect(transport);
```
With the local changes from this PR, I added the following to my
`config.toml`:
```toml
[mcp_servers.kitty]
command = "node"
args = ["/Users/mbolin/code/kitty-mcp/index.js"]
```
Running the TUI from source:
```
cargo run --bin codex -- --model o3 'I need a picture of a cat'
```
I get:
<img width="732" alt="image"
src="https://github.com/user-attachments/assets/bf80b721-9ca0-4d81-aec7-77d6899e2869"
/>
Now, that said, I have only tested in iTerm and there is definitely some
funny business with getting an accurate character-to-pixel ratio
(sometimes the `CompletedMcpToolCallWithImageOutput` thinks it needs 10
rows to render instead of 4), so there is still work to be done here.
Michael Bolin
