Files
codex/codex-rs/app-server-protocol/schema/json/v1/SendUserTurnParams.json
Michael Bolin dc092a644d Make sandbox read access configurable with ReadOnlyAccess
## What

This change introduces a new `ReadOnlyAccess` model and threads it through
sandbox policy consumers so read access is explicit instead of implicit.

- Added `ReadOnlyAccess` to protocol:
  - `Restricted { include_platform_defaults, readable_roots }`
  - `FullAccess`
- Changed `SandboxPolicy` shape:
  - `ReadOnly` is now `ReadOnly { access: ReadOnlyAccess }`
  - `WorkspaceWrite` now carries `read_only_access: ReadOnlyAccess`
- Kept existing behavior for now by defaulting to `ReadOnlyAccess::FullAccess`
  in constructors and current config/app-server mappings.
- Added helper methods to compute effective readable roots (including optional
  platform defaults + cwd) and to detect full read access.
- Updated seatbelt policy generation to honor restricted read roots by emitting
  scoped `(allow file-read* ...)` entries when full read access is not granted.
- Updated Linux backends (`bwrap`, legacy landlock path) to fail closed with an
  explicit `UnsupportedOperation` when restricted read access is requested but
  not yet implemented there.
- Updated Windows sandbox backends (standard, elevated, and runner paths) to
  fail closed in the same way for restricted read access.
- Updated all call sites/tests/pattern matches for the new structured variants
  and regenerated app-server protocol schema/types.

## Why

The previous `SandboxPolicy::ReadOnly` implied full-disk read access and left
no way to express a narrower read surface.

This refactor establishes the policy model needed to support user-configurable
read restrictions in a follow-up without changing current runtime behavior.

It also ensures we do not silently ignore future restricted-read policies on
platform backends that do not support them yet. Failing closed keeps sandbox
semantics predictable and avoids accidental over-permission.

## Compatibility and rollout notes

- Existing behavior is preserved by default (`FullAccess`).
- Existing config/app-server flows continue to serialize/deserialize cleanly.
- New schema artifacts are included to keep generated protocol outputs in sync.

## Validation

- `just fmt`
- `just fix -p codex-protocol -p codex-core -p codex-linux-sandbox -p codex-windows-sandbox -p codex-app-server-protocol`
- `cargo check -p codex-windows-sandbox`
- Targeted crate/test runs were executed during development for protocol/core/
  sandbox-related crates.
2026-02-11 11:12:51 -08:00

446 lines
13 KiB
JSON
Raw Blame History

This file contains ambiguous Unicode characters
This file contains Unicode characters that might be confused with other characters. If you think that this is intentional, you can safely ignore this warning. Use the Escape button to reveal them.
{
"$schema": "http://json-schema.org/draft-07/schema#",
"definitions": {
"AbsolutePathBuf": {
"description": "A path that is guaranteed to be absolute and normalized (though it is not guaranteed to be canonicalized or exist on the filesystem).\n\nIMPORTANT: When deserializing an `AbsolutePathBuf`, a base path must be set using [AbsolutePathBufGuard::new]. If no base path is set, the deserialization will fail unless the path being deserialized is already absolute.",
"type": "string"
},
"AskForApproval": {
"description": "Determines the conditions under which the user is consulted to approve running the command proposed by Codex.",
"oneOf": [
{
"description": "Under this policy, only \"known safe\" commands—as determined by `is_safe_command()`—that **only read files** are autoapproved. Everything else will ask the user to approve.",
"enum": [
"untrusted"
],
"type": "string"
},
{
"description": "*All* commands are autoapproved, but they are expected to run inside a sandbox where network access is disabled and writes are confined to a specific set of paths. If the command fails, it will be escalated to the user to approve execution without a sandbox.",
"enum": [
"on-failure"
],
"type": "string"
},
{
"description": "The model decides when to ask the user for approval.",
"enum": [
"on-request"
],
"type": "string"
},
{
"description": "Never ask the user to approve commands. Failures are immediately returned to the model, and never escalated to the user for approval.",
"enum": [
"never"
],
"type": "string"
}
]
},
"InputItem": {
"oneOf": [
{
"properties": {
"data": {
"properties": {
"text": {
"type": "string"
},
"text_elements": {
"default": [],
"description": "UI-defined spans within `text` used to render or persist special elements.",
"items": {
"$ref": "#/definitions/V1TextElement"
},
"type": "array"
}
},
"required": [
"text"
],
"type": "object"
},
"type": {
"enum": [
"text"
],
"title": "TextInputItemType",
"type": "string"
}
},
"required": [
"data",
"type"
],
"title": "TextInputItem",
"type": "object"
},
{
"properties": {
"data": {
"properties": {
"image_url": {
"type": "string"
}
},
"required": [
"image_url"
],
"type": "object"
},
"type": {
"enum": [
"image"
],
"title": "ImageInputItemType",
"type": "string"
}
},
"required": [
"data",
"type"
],
"title": "ImageInputItem",
"type": "object"
},
{
"properties": {
"data": {
"properties": {
"path": {
"type": "string"
}
},
"required": [
"path"
],
"type": "object"
},
"type": {
"enum": [
"localImage"
],
"title": "LocalImageInputItemType",
"type": "string"
}
},
"required": [
"data",
"type"
],
"title": "LocalImageInputItem",
"type": "object"
}
]
},
"NetworkAccess": {
"description": "Represents whether outbound network access is available to the agent.",
"enum": [
"restricted",
"enabled"
],
"type": "string"
},
"ReadOnlyAccess": {
"description": "Determines how read-only file access is granted inside a restricted sandbox.",
"oneOf": [
{
"description": "Restrict reads to an explicit set of roots.\n\nWhen `include_platform_defaults` is `true`, platform defaults required for basic execution are included in addition to `readable_roots`.",
"properties": {
"include_platform_defaults": {
"default": true,
"description": "Include built-in platform read roots required for basic process execution.",
"type": "boolean"
},
"readable_roots": {
"description": "Additional absolute roots that should be readable.",
"items": {
"$ref": "#/definitions/AbsolutePathBuf"
},
"type": "array"
},
"type": {
"enum": [
"restricted"
],
"title": "RestrictedReadOnlyAccessType",
"type": "string"
}
},
"required": [
"type"
],
"title": "RestrictedReadOnlyAccess",
"type": "object"
},
{
"description": "Allow unrestricted file reads.",
"properties": {
"type": {
"enum": [
"full-access"
],
"title": "FullAccessReadOnlyAccessType",
"type": "string"
}
},
"required": [
"type"
],
"title": "FullAccessReadOnlyAccess",
"type": "object"
}
]
},
"ReasoningEffort": {
"description": "See https://platform.openai.com/docs/guides/reasoning?api-mode=responses#get-started-with-reasoning",
"enum": [
"none",
"minimal",
"low",
"medium",
"high",
"xhigh"
],
"type": "string"
},
"ReasoningSummary": {
"description": "A summary of the reasoning performed by the model. This can be useful for debugging and understanding the model's reasoning process. See https://platform.openai.com/docs/guides/reasoning?api-mode=responses#reasoning-summaries",
"oneOf": [
{
"enum": [
"auto",
"concise",
"detailed"
],
"type": "string"
},
{
"description": "Option to disable reasoning summaries.",
"enum": [
"none"
],
"type": "string"
}
]
},
"SandboxPolicy": {
"description": "Determines execution restrictions for model shell commands.",
"oneOf": [
{
"description": "No restrictions whatsoever. Use with caution.",
"properties": {
"type": {
"enum": [
"danger-full-access"
],
"title": "DangerFullAccessSandboxPolicyType",
"type": "string"
}
},
"required": [
"type"
],
"title": "DangerFullAccessSandboxPolicy",
"type": "object"
},
{
"description": "Read-only access configuration.",
"properties": {
"access": {
"allOf": [
{
"$ref": "#/definitions/ReadOnlyAccess"
}
],
"description": "Read access granted while running under this policy."
},
"type": {
"enum": [
"read-only"
],
"title": "ReadOnlySandboxPolicyType",
"type": "string"
}
},
"required": [
"type"
],
"title": "ReadOnlySandboxPolicy",
"type": "object"
},
{
"description": "Indicates the process is already in an external sandbox. Allows full disk access while honoring the provided network setting.",
"properties": {
"network_access": {
"allOf": [
{
"$ref": "#/definitions/NetworkAccess"
}
],
"default": "restricted",
"description": "Whether the external sandbox permits outbound network traffic."
},
"type": {
"enum": [
"external-sandbox"
],
"title": "ExternalSandboxSandboxPolicyType",
"type": "string"
}
},
"required": [
"type"
],
"title": "ExternalSandboxSandboxPolicy",
"type": "object"
},
{
"description": "Same as `ReadOnly` but additionally grants write access to the current working directory (\"workspace\").",
"properties": {
"exclude_slash_tmp": {
"default": false,
"description": "When set to `true`, will NOT include the `/tmp` among the default writable roots on UNIX. Defaults to `false`.",
"type": "boolean"
},
"exclude_tmpdir_env_var": {
"default": false,
"description": "When set to `true`, will NOT include the per-user `TMPDIR` environment variable among the default writable roots. Defaults to `false`.",
"type": "boolean"
},
"network_access": {
"default": false,
"description": "When set to `true`, outbound network access is allowed. `false` by default.",
"type": "boolean"
},
"read_only_access": {
"allOf": [
{
"$ref": "#/definitions/ReadOnlyAccess"
}
],
"description": "Read access granted while running under this policy."
},
"type": {
"enum": [
"workspace-write"
],
"title": "WorkspaceWriteSandboxPolicyType",
"type": "string"
},
"writable_roots": {
"description": "Additional folders (beyond cwd and possibly TMPDIR) that should be writable from within the sandbox.",
"items": {
"$ref": "#/definitions/AbsolutePathBuf"
},
"type": "array"
}
},
"required": [
"type"
],
"title": "WorkspaceWriteSandboxPolicy",
"type": "object"
}
]
},
"ThreadId": {
"type": "string"
},
"V1ByteRange": {
"properties": {
"end": {
"description": "End byte offset (exclusive) within the UTF-8 text buffer.",
"format": "uint",
"minimum": 0.0,
"type": "integer"
},
"start": {
"description": "Start byte offset (inclusive) within the UTF-8 text buffer.",
"format": "uint",
"minimum": 0.0,
"type": "integer"
}
},
"required": [
"end",
"start"
],
"type": "object"
},
"V1TextElement": {
"properties": {
"byteRange": {
"allOf": [
{
"$ref": "#/definitions/V1ByteRange"
}
],
"description": "Byte range in the parent `text` buffer that this element occupies."
},
"placeholder": {
"description": "Optional human-readable placeholder for the element, displayed in the UI.",
"type": [
"string",
"null"
]
}
},
"required": [
"byteRange"
],
"type": "object"
}
},
"properties": {
"approvalPolicy": {
"$ref": "#/definitions/AskForApproval"
},
"conversationId": {
"$ref": "#/definitions/ThreadId"
},
"cwd": {
"type": "string"
},
"effort": {
"anyOf": [
{
"$ref": "#/definitions/ReasoningEffort"
},
{
"type": "null"
}
]
},
"items": {
"items": {
"$ref": "#/definitions/InputItem"
},
"type": "array"
},
"model": {
"type": "string"
},
"outputSchema": {
"description": "Optional JSON Schema used to constrain the final assistant message for this turn."
},
"sandboxPolicy": {
"$ref": "#/definitions/SandboxPolicy"
},
"summary": {
"$ref": "#/definitions/ReasoningSummary"
}
},
"required": [
"approvalPolicy",
"conversationId",
"cwd",
"items",
"model",
"sandboxPolicy",
"summary"
],
"title": "SendUserTurnParams",
"type": "object"
}