Skip to content

feat: support using the action with Azure-hosted OpenAI models #47

New issue

Have a question about this project? Sign up for a free GitHub account to open an issue and contact its maintainers and the community.

Sign up for GitHub

By clicking “Sign up for GitHub”, you agree to our terms of service and privacy statement. We’ll occasionally send you account related emails.

Already on GitHub? Sign in to your account

Merged
pakrym-oai merged 1 commit into from
Nov 5, 2025
Merged

feat: support using the action with Azure-hosted OpenAI models #47

Show file tree
Hide file tree
Changes from all commits
Commits
Show all changes
1 commit
Select commit
File filter

Filter by extension

Filter by extension
Conversations
Failed to load comments.
Loading
Jump to
Jump to file
Failed to load files.
Loading
Diff view
Diff view
60 changes: 40 additions & 20 deletions README.md
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -2,7 +2,7 @@

Run [Codex](https://github.com/openai/codex#codex-exec) from a GitHub Actions workflow while keeping tight control over the privileges available to Codex. This action handles installing the Codex CLI and configuring it with a secure proxy to the [Responses API](https://platform.openai.com/docs/api-reference/responses).

Users must provide their [`OPENAI_API_KEY`](https://platform.openai.com/api-keys) as a [GitHub Actions secret](https://docs.github.com/en/actions/how-tos/write-workflows/choose-what-workflows-do/use-secrets) to use this action.
Users must provide an API key for their chosen provider (for example, [`OPENAI_API_KEY`](https://platform.openai.com/api-keys) or `AZURE_OPENAI_API_KEY` [if using Azure for OpenAI models](#azure)) as a [GitHub Actions secret](https://docs.github.com/en/actions/how-tos/write-workflows/choose-what-workflows-do/use-secrets) to use this action.

## Example: Create Your Own Pull Request Bot

Expand Down Expand Up @@ -90,25 +90,26 @@ jobs:

## Inputs

| Name | Description | Default |
| -------------------- | --------------------------------------------------------------------------------------------------------------------------------------- | ----------- |
| `openai-api-key` | Secret used to start the Responses API proxy. Required when starting the proxy (key-only or key+prompt). Store it in `secrets`. | `""` |
| `prompt` | Inline prompt text. Provide this or `prompt-file`. | `""` |
| `prompt-file` | Path (relative to the repository root) of a file that contains the prompt. Provide this or `prompt`. | `""` |
| `output-file` | File where the final Codex message is written. Leave empty to skip writing a file. | `""` |
| `working-directory` | Directory passed to `codex exec --cd`. Defaults to the repository root. | `""` |
| `sandbox` | Sandbox mode for Codex. One of `workspace-write` (default), `read-only` or `danger-full-access`. | `""` |
| `codex-version` | Version of `@openai/codex` to install. | `""` |
| `codex-args` | Extra arguments forwarded to `codex exec`. Accepts JSON arrays (`["--flag", "value"]`) or shell-style strings. | `""` |
| `output-schema` | Inline schema contents written to a temp file and passed to `codex exec --output-schema`. Mutually exclusive with `output-schema-file`. | `""` |
| `output-schema-file` | Schema file forwarded to `codex exec --output-schema`. Leave empty to skip passing the option. | `""` |
| `model` | Model the agent should use. Leave empty to let Codex pick its default. | `""` |
| `effort` | Reasoning effort the agent should use. Leave empty to let Codex pick its default. | `""` |
| `codex-home` | Directory to use as the Codex CLI home (config/cache). Uses the CLI default when empty. | `""` |
| `safety-strategy` | Controls how the action restricts Codex privileges. See [Safety strategy](#safety-strategy). | `drop-sudo` |
| `codex-user` | Username to run Codex as when `safety-strategy` is `unprivileged-user`. | `""` |
| `allow-users` | List of GitHub usernames who can trigger the action in addition to those who have write access to the repo. | "" |
| `allow-bots` | Allow runs triggered by GitHub Apps/bot accounts to bypass the write-access check. | "false" |
| Name | Description | Default |
| ------------------------ | ---------------------------------------------------------------------------------------------------------------------------------------------- | ----------- |
| `openai-api-key` | Secret used to start the Responses API proxy when you are using OpenAI (default). Store it in `secrets`. | `""` |
| `responses-api-endpoint` | Optional Responses API endpoint override, e.g. `https://example.openai.azure.com/openai/v1/responses`. Leave empty to use the proxy's default. | `""` |
| `prompt` | Inline prompt text. Provide this or `prompt-file`. | `""` |
| `prompt-file` | Path (relative to the repository root) of a file that contains the prompt. Provide this or `prompt`. | `""` |
| `output-file` | File where the final Codex message is written. Leave empty to skip writing a file. | `""` |
| `working-directory` | Directory passed to `codex exec --cd`. Defaults to the repository root. | `""` |
| `sandbox` | Sandbox mode for Codex. One of `workspace-write` (default), `read-only` or `danger-full-access`. | `""` |
| `codex-version` | Version of `@openai/codex` to install. | `""` |
| `codex-args` | Extra arguments forwarded to `codex exec`. Accepts JSON arrays (`["--flag", "value"]`) or shell-style strings. | `""` |
| `output-schema` | Inline schema contents written to a temp file and passed to `codex exec --output-schema`. Mutually exclusive with `output-schema-file`. | `""` |
| `output-schema-file` | Schema file forwarded to `codex exec --output-schema`. Leave empty to skip passing the option. | `""` |
| `model` | Model the agent should use. Leave empty to let Codex pick its default. | `""` |
| `effort` | Reasoning effort the agent should use. Leave empty to let Codex pick its default. | `""` |
| `codex-home` | Directory to use as the Codex CLI home (config/cache). Uses the CLI default when empty. | `""` |
| `safety-strategy` | Controls how the action restricts Codex privileges. See [Safety strategy](#safety-strategy). | `drop-sudo` |
| `codex-user` | Username to run Codex as when `safety-strategy` is `unprivileged-user`. | `""` |
| `allow-users` | List of GitHub usernames who can trigger the action in addition to those who have write access to the repo. | `""` |
| `allow-bots` | Allow runs triggered by GitHub Apps/bot accounts to bypass the write-access check. | `false` |

## Safety Strategy

Expand Down Expand Up @@ -145,10 +146,29 @@ jobs:
## Additional tips

- Run this action after `actions/checkout@v5` so Codex has access to your repository contents.
- To use a non-default Responses endpoint (for example Azure OpenAI), set `responses-api-endpoint` to the provider's URL while keeping `openai-api-key` populated; the proxy will still send `Authorization: Bearer <key>` upstream.
- If you want Codex to have access to a narrow set of privileged functionality, consider running a local MCP server that can perform these actions and configure Codex to use it.
- If you need more control over the CLI invocation, pass flags through `codex-args` or create a `config.toml` in `codex-home`.
- Once `openai/codex-action` is run once with `openai-api-key`, you can also call `codex` from subsequent scripts in your job. (You can omit `prompt` and `prompt-file` from the action in this case.)

## Azure

To configure the Action to use OpenAI models hosted on Azure, pay close attention to the following:

- The `responses-api-endpoint` must be set to the full URL (including any required query parameters) that Codex will `POST` to for a Responses API request. For Azure, this might look like `https://YOUR_PROJECT_NAME.openai.azure.com/openai/v1/responses`. Note that [unlike when customizing a model provider in Codex](https://github.com/openai/codex/blob/main/docs/config.md#azure-model-provider-example), you must include the `v1/responses` suffix to the URL yourself, if appropriate.
Copy link
Collaborator

@pakrym-oai pakrym-oai Nov 5, 2025

Choose a reason for hiding this comment

The reason will be displayed to describe this comment to others. Learn more.

Should we mention api-version query parameter?

- The `openai-api-key` input must be a valid key that can be used with the `Authorization: Bearer <KEY>` header when making a `POST` request to your Responses API endpoint. (This is also true for the value of the [`env_key`](https://github.com/openai/codex/blob/main/docs/config.md#azure-model-provider-example) when setting a custom provider using the Codex CLI.)

Ultimately, your configured Action might look something like the following:

```yaml
- name: Start Codex proxy
uses: openai/codex-action@v1
with:
openai-api-key: ${{ secrets.AZURE_OPENAI_API_KEY }}
responses-api-endpoint: "https://bolinfest-7804-resource.cognitiveservices.azure.com/openai/v1/responses"
prompt: "Debug all the things."
```

## License

This project is licensed under the [Apache License 2.0](./LICENSE).
26 changes: 21 additions & 5 deletions action.yml
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -18,6 +18,10 @@ inputs:
description: "OpenAI API key used by Codex."
required: false
default: ""
responses-api-endpoint:
description: "Optional Responses API endpoint override, e.g. https://example.openai.azure.com/openai/v1/responses. Defaults to the proxy's built-in endpoint when empty."
Copy link
Collaborator

@pakrym-oai pakrym-oai Nov 5, 2025

Choose a reason for hiding this comment

The reason will be displayed to describe this comment to others. Learn more.

Defaults to Responses API when empty?

required: false
default: ""
working-directory:
description: "Working directory that Codex should use. Defaults to the repository root."
required: false
Expand Down Expand Up @@ -165,17 +169,29 @@ runs:
fi

# This is its own step to minimize the runtime logic that has access to the
# API key. Note we use `env -u OPENAI_API_KEY` to ensure extra copies of the
# key do not end up in the memory of the `codex-responses-api-proxy` process
# where environment variables are stored.
# API key. Note we use `env -u PROXY_API_KEY` to ensure extra copies of the
# key do not end up in the memory of the `codex-responses-api-proxy`
# process where environment variables are stored.
- name: Start Responses API proxy
if: ${{ inputs['openai-api-key'] != '' && steps.start_proxy.outputs.server_info_file_exists == 'false' }}
env:
OPENAI_API_KEY: ${{ inputs['openai-api-key'] }}
PROXY_API_KEY: ${{ inputs['openai-api-key'] }}
shell: bash
run: |
upstream_url="${{ inputs['responses-api-endpoint'] }}"

args=(
codex-responses-api-proxy
--http-shutdown
--server-info "${{ steps.derive_server_info.outputs.server_info_file }}"
)

if [ -n "$upstream_url" ]; then
args+=(--upstream-url "$upstream_url")
fi

(
printenv OPENAI_API_KEY | env -u OPENAI_API_KEY codex-responses-api-proxy --http-shutdown --server-info "${{ steps.derive_server_info.outputs.server_info_file }}"
printenv PROXY_API_KEY | env -u PROXY_API_KEY "${args[@]}"
) &

- name: Wait for Responses API proxy
Expand Down
6 changes: 3 additions & 3 deletions dist/main.js
View file
Open in desktop

Large diffs are not rendered by default.

4 changes: 2 additions & 2 deletions src/writeProxyConfig.ts
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -4,7 +4,7 @@ import * as os from "node:os";
import { SafetyStrategy } from "./runCodexExec";
import { checkOutput } from "./checkOutput";

const MODEL_PROVIDER = "openai-proxy";
const MODEL_PROVIDER = "codex-action-responses-proxy";

export async function writeProxyConfig(
codexHome: string,
Expand All @@ -29,7 +29,7 @@ model_provider = "${MODEL_PROVIDER}"

# Added by codex-action.
[model_providers.${MODEL_PROVIDER}]
name = "OpenAI Proxy"
name = "Codex Action Responses Proxy"
base_url = "http://127.0.0.1:${port}/v1"
wire_api = "responses"
`;
Expand Down