fix: retry transient Guardian reviewer failures#26334
Open
viyatb-oai wants to merge 11 commits into
Open
Conversation
Co-authored-by: Codex noreply@openai.com
Contributor
There was a problem hiding this comment.
💡 Codex Review
Here are some automated review suggestions for this pull request.
Reviewed commit: e014da9666
ℹ️ About Codex in GitHub
Your team has set up Codex to review pull requests in this repo. Reviews are triggered when you
- Open a pull request for review
- Mark a draft as ready
- Comment "@codex review".
If Codex has suggestions, it will comment; otherwise it will react with 👍.
Codex can also answer questions or update the PR. Try commenting "@codex address that feedback".
This was referenced Jun 4, 2026
viyatb-oai
added a commit
that referenced
this pull request
Jun 8, 2026
## Why Auto Review should remain the effective approval reviewer when settings cross runtime boundaries. A config or app-server round trip must not change the reviewer identity, and delegated work must not silently fall back to user review. This requires both a stable canonical serialized value and propagation of the effective setting. `auto_review` is the canonical value across protocol and app-server output, while `guardian_subagent` remains accepted as backward-compatible input. ## What changed - serialize `ApprovalsReviewer::AutoReview` consistently as `auto_review` across core protocol and app-server v2 - continue accepting `guardian_subagent` when reading existing config or client requests - carry the active turn's approval reviewer into spawned agents - update config/debug expectations and add delegated-task regression coverage ## Scope This does not change Guardian policy or remove compatibility with existing `guardian_subagent` inputs. It preserves the selected reviewer across serialization, config reloads, app-server settings, and delegated task setup. Related Guardian changes are split independently: - #26231 adds denials and soft denials - #26334 retries transient reviewer failures - #26333 reuses narrowly scoped low-risk approvals - #26232 adds TUI denial recovery ## Validation - `just test -p codex-app-server-protocol` (224 passed) - regression coverage for delegated task reviewer propagation - serialization coverage for canonical `auto_review` output and legacy `guardian_subagent` input --------- Co-authored-by: saud-oai <saud@openai.com>
Co-authored-by: Codex noreply@openai.com
dkropachev
pushed a commit
to dkropachev/codex
that referenced
this pull request
Jun 9, 2026
## Why Auto Review should remain the effective approval reviewer when settings cross runtime boundaries. A config or app-server round trip must not change the reviewer identity, and delegated work must not silently fall back to user review. This requires both a stable canonical serialized value and propagation of the effective setting. `auto_review` is the canonical value across protocol and app-server output, while `guardian_subagent` remains accepted as backward-compatible input. ## What changed - serialize `ApprovalsReviewer::AutoReview` consistently as `auto_review` across core protocol and app-server v2 - continue accepting `guardian_subagent` when reading existing config or client requests - carry the active turn's approval reviewer into spawned agents - update config/debug expectations and add delegated-task regression coverage ## Scope This does not change Guardian policy or remove compatibility with existing `guardian_subagent` inputs. It preserves the selected reviewer across serialization, config reloads, app-server settings, and delegated task setup. Related Guardian changes are split independently: - openai#26231 adds denials and soft denials - openai#26334 retries transient reviewer failures - openai#26333 reuses narrowly scoped low-risk approvals - openai#26232 adds TUI denial recovery ## Validation - `just test -p codex-app-server-protocol` (224 passed) - regression coverage for delegated task reviewer propagation - serialization coverage for canonical `auto_review` output and legacy `guardian_subagent` input --------- Co-authored-by: saud-oai <saud@openai.com>
…-reviewer-retries
Co-authored-by: Codex noreply@openai.com
Co-authored-by: Codex noreply@openai.com
Co-authored-by: Codex noreply@openai.com
dkropachev
pushed a commit
to dkropachev/codex
that referenced
this pull request
Jun 9, 2026
## Why Auto Review should remain the effective approval reviewer when settings cross runtime boundaries. A config or app-server round trip must not change the reviewer identity, and delegated work must not silently fall back to user review. This requires both a stable canonical serialized value and propagation of the effective setting. `auto_review` is the canonical value across protocol and app-server output, while `guardian_subagent` remains accepted as backward-compatible input. ## What changed - serialize `ApprovalsReviewer::AutoReview` consistently as `auto_review` across core protocol and app-server v2 - continue accepting `guardian_subagent` when reading existing config or client requests - carry the active turn's approval reviewer into spawned agents - update config/debug expectations and add delegated-task regression coverage ## Scope This does not change Guardian policy or remove compatibility with existing `guardian_subagent` inputs. It preserves the selected reviewer across serialization, config reloads, app-server settings, and delegated task setup. Related Guardian changes are split independently: - openai#26231 adds denials and soft denials - openai#26334 retries transient reviewer failures - openai#26333 reuses narrowly scoped low-risk approvals - openai#26232 adds TUI denial recovery ## Validation - `just test -p codex-app-server-protocol` (224 passed) - regression coverage for delegated task reviewer propagation - serialization coverage for canonical `auto_review` output and legacy `guardian_subagent` input --------- Co-authored-by: saud-oai <saud@openai.com>
Co-authored-by: Codex noreply@openai.com
Co-authored-by: Codex noreply@openai.com
Co-authored-by: Codex noreply@openai.com
dkropachev
pushed a commit
to dkropachev/codex
that referenced
this pull request
Jun 9, 2026
## Why Auto Review should remain the effective approval reviewer when settings cross runtime boundaries. A config or app-server round trip must not change the reviewer identity, and delegated work must not silently fall back to user review. This requires both a stable canonical serialized value and propagation of the effective setting. `auto_review` is the canonical value across protocol and app-server output, while `guardian_subagent` remains accepted as backward-compatible input. ## What changed - serialize `ApprovalsReviewer::AutoReview` consistently as `auto_review` across core protocol and app-server v2 - continue accepting `guardian_subagent` when reading existing config or client requests - carry the active turn's approval reviewer into spawned agents - update config/debug expectations and add delegated-task regression coverage ## Scope This does not change Guardian policy or remove compatibility with existing `guardian_subagent` inputs. It preserves the selected reviewer across serialization, config reloads, app-server settings, and delegated task setup. Related Guardian changes are split independently: - openai#26231 adds denials and soft denials - openai#26334 retries transient reviewer failures - openai#26333 reuses narrowly scoped low-risk approvals - openai#26232 adds TUI denial recovery ## Validation - `just test -p codex-app-server-protocol` (224 passed) - regression coverage for delegated task reviewer propagation - serialization coverage for canonical `auto_review` output and legacy `guardian_subagent` input --------- Co-authored-by: saud-oai <saud@openai.com>
dkropachev
pushed a commit
to dkropachev/codex
that referenced
this pull request
Jun 9, 2026
## Why Auto Review should remain the effective approval reviewer when settings cross runtime boundaries. A config or app-server round trip must not change the reviewer identity, and delegated work must not silently fall back to user review. This requires both a stable canonical serialized value and propagation of the effective setting. `auto_review` is the canonical value across protocol and app-server output, while `guardian_subagent` remains accepted as backward-compatible input. ## What changed - serialize `ApprovalsReviewer::AutoReview` consistently as `auto_review` across core protocol and app-server v2 - continue accepting `guardian_subagent` when reading existing config or client requests - carry the active turn's approval reviewer into spawned agents - update config/debug expectations and add delegated-task regression coverage ## Scope This does not change Guardian policy or remove compatibility with existing `guardian_subagent` inputs. It preserves the selected reviewer across serialization, config reloads, app-server settings, and delegated task setup. Related Guardian changes are split independently: - openai#26231 adds denials and soft denials - openai#26334 retries transient reviewer failures - openai#26333 reuses narrowly scoped low-risk approvals - openai#26232 adds TUI denial recovery ## Validation - `just test -p codex-app-server-protocol` (224 passed) - regression coverage for delegated task reviewer propagation - serialization coverage for canonical `auto_review` output and legacy `guardian_subagent` input --------- Co-authored-by: saud-oai <saud@openai.com>
dkropachev
pushed a commit
to dkropachev/codex
that referenced
this pull request
Jun 9, 2026
## Why Auto Review should remain the effective approval reviewer when settings cross runtime boundaries. A config or app-server round trip must not change the reviewer identity, and delegated work must not silently fall back to user review. This requires both a stable canonical serialized value and propagation of the effective setting. `auto_review` is the canonical value across protocol and app-server output, while `guardian_subagent` remains accepted as backward-compatible input. ## What changed - serialize `ApprovalsReviewer::AutoReview` consistently as `auto_review` across core protocol and app-server v2 - continue accepting `guardian_subagent` when reading existing config or client requests - carry the active turn's approval reviewer into spawned agents - update config/debug expectations and add delegated-task regression coverage ## Scope This does not change Guardian policy or remove compatibility with existing `guardian_subagent` inputs. It preserves the selected reviewer across serialization, config reloads, app-server settings, and delegated task setup. Related Guardian changes are split independently: - openai#26231 adds denials and soft denials - openai#26334 retries transient reviewer failures - openai#26333 reuses narrowly scoped low-risk approvals - openai#26232 adds TUI denial recovery ## Validation - `just test -p codex-app-server-protocol` (224 passed) - regression coverage for delegated task reviewer propagation - serialization coverage for canonical `auto_review` output and legacy `guardian_subagent` input --------- Co-authored-by: saud-oai <saud@openai.com>
dkropachev
pushed a commit
to dkropachev/codex
that referenced
this pull request
Jun 9, 2026
## Why Auto Review should remain the effective approval reviewer when settings cross runtime boundaries. A config or app-server round trip must not change the reviewer identity, and delegated work must not silently fall back to user review. This requires both a stable canonical serialized value and propagation of the effective setting. `auto_review` is the canonical value across protocol and app-server output, while `guardian_subagent` remains accepted as backward-compatible input. ## What changed - serialize `ApprovalsReviewer::AutoReview` consistently as `auto_review` across core protocol and app-server v2 - continue accepting `guardian_subagent` when reading existing config or client requests - carry the active turn's approval reviewer into spawned agents - update config/debug expectations and add delegated-task regression coverage ## Scope This does not change Guardian policy or remove compatibility with existing `guardian_subagent` inputs. It preserves the selected reviewer across serialization, config reloads, app-server settings, and delegated task setup. Related Guardian changes are split independently: - openai#26231 adds denials and soft denials - openai#26334 retries transient reviewer failures - openai#26333 reuses narrowly scoped low-risk approvals - openai#26232 adds TUI denial recovery ## Validation - `just test -p codex-app-server-protocol` (224 passed) - regression coverage for delegated task reviewer propagation - serialization coverage for canonical `auto_review` output and legacy `guardian_subagent` input --------- Co-authored-by: saud-oai <saud@openai.com>
Co-authored-by: Codex noreply@openai.com
Co-authored-by: Codex noreply@openai.com
dkropachev
pushed a commit
to dkropachev/codex
that referenced
this pull request
Jun 9, 2026
## Why Auto Review should remain the effective approval reviewer when settings cross runtime boundaries. A config or app-server round trip must not change the reviewer identity, and delegated work must not silently fall back to user review. This requires both a stable canonical serialized value and propagation of the effective setting. `auto_review` is the canonical value across protocol and app-server output, while `guardian_subagent` remains accepted as backward-compatible input. ## What changed - serialize `ApprovalsReviewer::AutoReview` consistently as `auto_review` across core protocol and app-server v2 - continue accepting `guardian_subagent` when reading existing config or client requests - carry the active turn's approval reviewer into spawned agents - update config/debug expectations and add delegated-task regression coverage ## Scope This does not change Guardian policy or remove compatibility with existing `guardian_subagent` inputs. It preserves the selected reviewer across serialization, config reloads, app-server settings, and delegated task setup. Related Guardian changes are split independently: - openai#26231 adds denials and soft denials - openai#26334 retries transient reviewer failures - openai#26333 reuses narrowly scoped low-risk approvals - openai#26232 adds TUI denial recovery ## Validation - `just test -p codex-app-server-protocol` (224 passed) - regression coverage for delegated task reviewer propagation - serialization coverage for canonical `auto_review` output and legacy `guardian_subagent` input --------- Co-authored-by: saud-oai <saud@openai.com>
dkropachev
pushed a commit
to dkropachev/codex
that referenced
this pull request
Jun 9, 2026
## Why Auto Review should remain the effective approval reviewer when settings cross runtime boundaries. A config or app-server round trip must not change the reviewer identity, and delegated work must not silently fall back to user review. This requires both a stable canonical serialized value and propagation of the effective setting. `auto_review` is the canonical value across protocol and app-server output, while `guardian_subagent` remains accepted as backward-compatible input. ## What changed - serialize `ApprovalsReviewer::AutoReview` consistently as `auto_review` across core protocol and app-server v2 - continue accepting `guardian_subagent` when reading existing config or client requests - carry the active turn's approval reviewer into spawned agents - update config/debug expectations and add delegated-task regression coverage ## Scope This does not change Guardian policy or remove compatibility with existing `guardian_subagent` inputs. It preserves the selected reviewer across serialization, config reloads, app-server settings, and delegated task setup. Related Guardian changes are split independently: - openai#26231 adds denials and soft denials - openai#26334 retries transient reviewer failures - openai#26333 reuses narrowly scoped low-risk approvals - openai#26232 adds TUI denial recovery ## Validation - `just test -p codex-app-server-protocol` (224 passed) - regression coverage for delegated task reviewer propagation - serialization coverage for canonical `auto_review` output and legacy `guardian_subagent` input --------- Co-authored-by: saud-oai <saud@openai.com>
dkropachev
pushed a commit
to dkropachev/codex
that referenced
this pull request
Jun 9, 2026
## Why Auto Review should remain the effective approval reviewer when settings cross runtime boundaries. A config or app-server round trip must not change the reviewer identity, and delegated work must not silently fall back to user review. This requires both a stable canonical serialized value and propagation of the effective setting. `auto_review` is the canonical value across protocol and app-server output, while `guardian_subagent` remains accepted as backward-compatible input. ## What changed - serialize `ApprovalsReviewer::AutoReview` consistently as `auto_review` across core protocol and app-server v2 - continue accepting `guardian_subagent` when reading existing config or client requests - carry the active turn's approval reviewer into spawned agents - update config/debug expectations and add delegated-task regression coverage ## Scope This does not change Guardian policy or remove compatibility with existing `guardian_subagent` inputs. It preserves the selected reviewer across serialization, config reloads, app-server settings, and delegated task setup. Related Guardian changes are split independently: - openai#26231 adds denials and soft denials - openai#26334 retries transient reviewer failures - openai#26333 reuses narrowly scoped low-risk approvals - openai#26232 adds TUI denial recovery ## Validation - `just test -p codex-app-server-protocol` (224 passed) - regression coverage for delegated task reviewer propagation - serialization coverage for canonical `auto_review` output and legacy `guardian_subagent` input --------- Co-authored-by: saud-oai <saud@openai.com>
This file contains hidden or bidirectional Unicode text that may be interpreted or compiled differently than what appears below. To review, open the file in an editor that reveals hidden Unicode characters.
Learn more about bidirectional Unicode characters
Sign up for free
to join this conversation on GitHub.
Already have an account?
Sign in to comment
1 participant
Add this suggestion to a batch that can be applied as a single commit.This suggestion is invalid because no changes were made to the code.Suggestions cannot be applied while the pull request is closed.Suggestions cannot be applied while viewing a subset of changes.Only one suggestion per line can be applied in a batch.Add this suggestion to a batch that can be applied as a single commit.Applying suggestions on deleted lines is not supported.You must change the existing code in this line in order to create a valid suggestion.Outdated suggestions cannot be applied.This suggestion has been applied or marked resolved.Suggestions cannot be applied from pending reviews.Suggestions cannot be applied on multi-line comments.Suggestions cannot be applied while the pull request is queued to merge.Suggestion cannot be applied right now. Please check back later.
Why
A Guardian review can fail because the reviewer is temporarily unavailable, not because the requested action violates policy. Treating capacity, rate-limit, timeout, transport, or retryable server failures as immediate denials conflates infrastructure health with a safety decision, blocks otherwise valid work after one transient error, and presents misleading risk language to the user.
What changed
5xxfailuresGuardianWarningbefore retrying so clients can distinguish reviewer availability from a policy denialScope
This is the reviewer-availability slice split from #26128. It intentionally does not add denial kinds, approval reuse, or new TUI/app UX.
Related independent slices: #26231, #26333, and #26232.
Validation
test_codexscenario covering a transient reviewer failure followed by a successful review