mirror of
https://github.com/openai/codex.git
synced 2026-04-25 07:05:38 +00:00
fix(guardian, app-server): introduce guardian review ids (#17298)
## Description This PR introduces `review_id` as the stable identifier for guardian reviews and exposes it in app-server `item/autoApprovalReview/started` and `item/autoApprovalReview/completed` events. Internally, guardian rejection state is now keyed by `review_id` instead of the reviewed tool item ID. `target_item_id` is still included when a review maps to a concrete thread item, but it is no longer overloaded as the review lifecycle identifier. ## Motivation We'd like to give users the ability to preempt a guardian review while it's running (approve or decline). However, we can't implement the API that allows the user to override a running guardian review because we didn't have a unique `review_id` per guardian review. Using `target_item_id` is not correct since: - with execve reviews, there can be multiple execve calls (and therefore guardian reviews) per shell command - with network policy reviews, there is no target item ID The PR that actually implements user overrides will use `review_id` as the stable identifier.
This commit is contained in:
@@ -802,6 +802,13 @@
|
||||
}
|
||||
]
|
||||
},
|
||||
"AutoReviewDecisionSource": {
|
||||
"description": "[UNSTABLE] Source that produced a terminal guardian approval review decision.",
|
||||
"enum": [
|
||||
"agent"
|
||||
],
|
||||
"type": "string"
|
||||
},
|
||||
"ByteRange": {
|
||||
"properties": {
|
||||
"end": {
|
||||
@@ -5502,17 +5509,28 @@
|
||||
},
|
||||
"ItemGuardianApprovalReviewCompletedNotification": {
|
||||
"$schema": "http://json-schema.org/draft-07/schema#",
|
||||
"description": "[UNSTABLE] Temporary notification payload for guardian automatic approval review. This shape is expected to change soon.\n\nTODO(ccunningham): Attach guardian review state to the reviewed tool item's lifecycle instead of sending separate standalone review notifications so the app-server API can persist and replay review state via `thread/read`.",
|
||||
"description": "[UNSTABLE] Temporary notification payload for guardian automatic approval review. This shape is expected to change soon.",
|
||||
"properties": {
|
||||
"action": {
|
||||
"$ref": "#/definitions/GuardianApprovalReviewAction"
|
||||
},
|
||||
"decisionSource": {
|
||||
"$ref": "#/definitions/AutoReviewDecisionSource"
|
||||
},
|
||||
"review": {
|
||||
"$ref": "#/definitions/GuardianApprovalReview"
|
||||
},
|
||||
"targetItemId": {
|
||||
"reviewId": {
|
||||
"description": "Stable identifier for this review.",
|
||||
"type": "string"
|
||||
},
|
||||
"targetItemId": {
|
||||
"description": "Identifier for the reviewed item or tool call when one exists.\n\nIn most cases, one review maps to one target item. The exceptions are - execve reviews, where a single command may contain multiple execve calls to review (only possible when using the shell_zsh_fork feature) - network policy reviews, where there is no target item\n\nA network call is triggered by a CommandExecution item, so having a target_item_id set to the CommandExecution item would be misleading because the review is about the network call, not the command execution. Therefore, target_item_id is set to None for network policy reviews.",
|
||||
"type": [
|
||||
"string",
|
||||
"null"
|
||||
]
|
||||
},
|
||||
"threadId": {
|
||||
"type": "string"
|
||||
},
|
||||
@@ -5522,8 +5540,9 @@
|
||||
},
|
||||
"required": [
|
||||
"action",
|
||||
"decisionSource",
|
||||
"review",
|
||||
"targetItemId",
|
||||
"reviewId",
|
||||
"threadId",
|
||||
"turnId"
|
||||
],
|
||||
@@ -5532,7 +5551,7 @@
|
||||
},
|
||||
"ItemGuardianApprovalReviewStartedNotification": {
|
||||
"$schema": "http://json-schema.org/draft-07/schema#",
|
||||
"description": "[UNSTABLE] Temporary notification payload for guardian automatic approval review. This shape is expected to change soon.\n\nTODO(ccunningham): Attach guardian review state to the reviewed tool item's lifecycle instead of sending separate standalone review notifications so the app-server API can persist and replay review state via `thread/read`.",
|
||||
"description": "[UNSTABLE] Temporary notification payload for guardian automatic approval review. This shape is expected to change soon.",
|
||||
"properties": {
|
||||
"action": {
|
||||
"$ref": "#/definitions/GuardianApprovalReviewAction"
|
||||
@@ -5540,9 +5559,17 @@
|
||||
"review": {
|
||||
"$ref": "#/definitions/GuardianApprovalReview"
|
||||
},
|
||||
"targetItemId": {
|
||||
"reviewId": {
|
||||
"description": "Stable identifier for this review.",
|
||||
"type": "string"
|
||||
},
|
||||
"targetItemId": {
|
||||
"description": "Identifier for the reviewed item or tool call when one exists.\n\nIn most cases, one review maps to one target item. The exceptions are - execve reviews, where a single command may contain multiple execve calls to review (only possible when using the shell_zsh_fork feature) - network policy reviews, where there is no target item\n\nA network call is triggered by a CommandExecution item, so having a target_item_id set to the CommandExecution item would be misleading because the review is about the network call, not the command execution. Therefore, target_item_id is set to None for network policy reviews.",
|
||||
"type": [
|
||||
"string",
|
||||
"null"
|
||||
]
|
||||
},
|
||||
"threadId": {
|
||||
"type": "string"
|
||||
},
|
||||
@@ -5553,7 +5580,7 @@
|
||||
"required": [
|
||||
"action",
|
||||
"review",
|
||||
"targetItemId",
|
||||
"reviewId",
|
||||
"threadId",
|
||||
"turnId"
|
||||
],
|
||||
|
||||
Reference in New Issue
Block a user