## Summary
- keep context injection on a single ContextContributor trait
- split context injection into thread-scoped and turn-scoped
contribution methods
- wire turn-scoped fragments into initial context assembly so extensions
can contribute context from turn-local state
## Why
`ResponseItem` variants do not have a consistent internal ID shape: some
variants carry required IDs, some carry optional IDs, and some cannot
represent an ID at all. The existing fields also use inconsistent serde,
TypeScript, and JSON-schema annotations. A single enum-level access path
is needed before history recording can assign and retain IDs.
This PR establishes that internal model only. It intentionally does not
generate or serialize IDs; allocation and wire persistence are isolated
in the stacked follow-up.
## What changed
- Give every concrete `ResponseItem` variant an `Option<String>` ID
field.
- Apply the same internal-only annotations to every ID field:
`#[serde(default, skip_serializing)]`, `#[ts(skip)]`, and
`#[schemars(skip)]`.
- Add `ResponseItem::id()` and `ResponseItem::set_id()` as the shared
accessors.
- Preserve IDs when history items are rewritten for truncation.
- Adapt consumers that previously assumed reasoning and image-generation
IDs were required.
- Regenerate app-server schemas so the hidden fields are represented
consistently.
The serde catch-all `ResponseItem::Other` remains ID-less because it
must remain a unit variant.
## Test plan
- `cargo check --tests -p codex-core -p codex-api -p codex-rollout-trace
-p codex-image-generation-extension`
- `just test -p codex-protocol`
- `just test -p codex-app-server-protocol`
- `just test -p codex-api -p codex-rollout-trace -p
codex-image-generation-extension`
- `just test -p codex-core event_mapping`
## Why
Host skill discovery was still exposed as a manager even though it is a
process-owned service shared by sessions, the app-server catalog, and
file-watcher invalidation. The skills extension also consumed an ad hoc
loaded-skills wrapper instead of a named immutable snapshot.
## What changed
- replace `SkillsManager` with concrete `SkillsService`
- make the service cache and return immutable `HostSkillsSnapshot`
values
- migrate the skills extension host provider to the snapshot boundary
- migrate app-server catalog, watcher, and invalidation paths to the
service
This keeps the service limited to host discovery, caching, roots, and
invalidation. Catalog rendering and invocation remain extension
responsibilities for the next stacked change.
## Why
app-server may run on a different OS from the selected exec-server
environment. Parsing that environment’s cwd with the Codex host’s path
rules prevents thread startup.
## What
Carry environment cwd values as `LegacyAppPathString` at the app-server
boundary and `PathUri` internally. Existing tool-call schemas and
relative-path behavior stay host-native; remaining local-only consumers
convert explicitly and leave follow-up TODOs.
The Wine integration test verifies app-server can start a thread and
complete an ordinary turn with a Windows environment cwd from Linux.
## Validation
- `bazel test //codex-rs/core/tests/remote_env_windows:smoke-test
--test_output=errors`
- focused app-server environment-selection and protocol schema tests
- scoped Clippy for `codex-core` and `codex-app-server-protocol`
## Why
Multi-agent v2 messages need a consistent, model-visible envelope that
identifies what kind of interaction occurred, who sent it, and which
agent it targets. Previously, encrypted deliveries exposed only
`encrypted_content`, while child completion used the legacy
`<subagent_notification>` shape. That meant the client could not
consistently present `NEW_TASK`, `MESSAGE`, and `FINAL_ANSWER` using the
same format.
This change adds the routing envelope as plaintext while keeping task
and message payloads encrypted. No new Responses API field is required:
an encrypted delivery is represented as an `input_text` header
immediately followed by its existing `encrypted_content` item.
Every envelope now follows this shape:
```text
Message Type: <NEW_TASK | MESSAGE | FINAL_ANSWER>
Task name: <recipient agent path>
Sender: <author agent path>
Payload:
<message payload>
```
## Message types
### `NEW_TASK`
`NEW_TASK` is used when the recipient should begin a new turn, including
an initial `spawn_agent` task and a later `followup_task`.
For a root agent spawning `/root/worker`, the request contains a
plaintext envelope followed by the encrypted task:
```json
{
"type": "agent_message",
"author": "/root",
"recipient": "/root/worker",
"content": [
{
"type": "input_text",
"text": "Message Type: NEW_TASK\nTask name: /root/worker\nSender: /root\nPayload:\n"
},
{
"type": "encrypted_content",
"encrypted_content": "<encrypted task payload>"
}
]
}
```
Conceptually, the model receives:
```text
Message Type: NEW_TASK
Task name: /root/worker
Sender: /root
Payload:
Review the authentication changes and report any regressions.
```
### `MESSAGE`
`MESSAGE` is used for a queued `send_message` delivery. It communicates
with an existing agent without starting a new turn.
For `/root/worker` reporting progress to the root agent, the request
contains:
```json
{
"type": "agent_message",
"author": "/root/worker",
"recipient": "/root",
"content": [
{
"type": "input_text",
"text": "Message Type: MESSAGE\nTask name: /root\nSender: /root/worker\nPayload:\n"
},
{
"type": "encrypted_content",
"encrypted_content": "<encrypted message payload>"
}
]
}
```
Conceptually, the model receives:
```text
Message Type: MESSAGE
Task name: /root
Sender: /root/worker
Payload:
The protocol tests pass; I am checking the resume path now.
```
### `FINAL_ANSWER`
`FINAL_ANSWER` is emitted when a child agent reaches a terminal state
and reports its result to its parent. Completion payloads are already
available locally, so the complete envelope is represented as plaintext
rather than as a plaintext header plus encrypted content.
For `/root/worker` completing work for the root agent, the request
contains:
```json
{
"type": "agent_message",
"author": "/root/worker",
"recipient": "/root",
"content": [
{
"type": "input_text",
"text": "Message Type: FINAL_ANSWER\nTask name: /root\nSender: /root/worker\nPayload:\nNo regressions found."
}
]
}
```
The model-visible form is:
```text
Message Type: FINAL_ANSWER
Task name: /root
Sender: /root/worker
Payload:
No regressions found.
```
Errored, shut down, and missing agents also use `FINAL_ANSWER`, with a
terminal-status description in the payload.
## What changed
- Render `NEW_TASK` or `MESSAGE` in
`InterAgentCommunication::to_model_input_item`, based on whether the
encrypted delivery starts a turn.
- Replace the multi-agent v2 `<subagent_notification>` completion
payload with a model-visible `FINAL_ANSWER` envelope.
- Document `Task name`, `Sender`, and `Payload` consistently in the
multi-agent developer instructions.
- Prevent local-only history projections from treating an encrypted
message's plaintext header as the complete assistant message.
- Preserve rollout-trace interaction edges when an agent message
contains both plaintext and encrypted content.
Legacy multi-agent behavior remains unchanged.
## Verification
- `just test -p codex-protocol`
- `just test -p codex-rollout-trace`
- `just test -p codex-web-search-extension`
- `just test -p codex-core
encrypted_multi_agent_v2_spawn_sends_agent_message_to_child`
- `just test -p codex-core
plaintext_multi_agent_v2_completion_sends_agent_message`
- `just test -p codex-core
multi_agent_v2_followup_task_completion_notifies_parent_on_every_turn`
- `just test -p codex-core
multi_agent_v2_completion_queues_message_for_direct_parent`
Summary
- Add the two missing `metadata: None` initializers after #28355 made
response-item metadata required.
- Restore test compilation for `codex-core` and `codex-api` on main.
Validation
- `git diff --check`
- `just fmt` (Rust formatting passed; unrelated Python formatter steps
could not use the sandboxed shared `uv` cache)
- Focused crate tests are running after PR creation.
## Description
This PR adds an optional `metadata` field to `ResponseItem` for
Responses API calls. Only mechanical plumbing, no actual values
populated and sent yet. Turns out just adding a new field to
`ResponseItem` has quite a large blast radius already.
This change is backwards compatible because `metadata` is optional and
omitted when absent, so existing response items and rollout history
without it still deserialize and requests that do not set it keep the
same wire shape. For provider compatibility, we strip out `metadata`
before non-OpenAI Responses requests so Azure and AWS Bedrock never see
this field.
My followup PR here will actually make use of it to start storing and
passing along `turn_id`: https://github.com/openai/codex/pull/28360
## What changed
- Added `ResponseItemMetadata` with optional `turn_id`, plus optional
`metadata` on Responses API item variants and inter-agent communication.
- Preserved item metadata through response-item rewrites such as
truncation, missing tool-output synthesis, compaction history
rebuilding, visible-history conversion, rollout/resume, and generated
app-server schemas/types.
- Strip item metadata from non-OpenAI Responses requests while
preserving it for OpenAI-shaped requests.
- Updated the mechanical fixture/test construction churn required by the
new optional field.
## Why
Guardian reviews embed the parent session transcript as untrusted
evidence. Skill or plugin mentions in that transcript must not be
interpreted as requests to inject more instructions into the Guardian
request, and memory context adds unrelated model-visible context to an
approval decision.
Keeping those sources out of the nested review session makes the request
smaller and preserves the trust boundary around the transcript being
assessed.
## What changed
- Skip skill and plugin discovery when building turns for Guardian
reviewer sessions.
- Disable memory context and dedicated memory tools in the derived
Guardian configuration.
- Extend the Guardian request-layout coverage to verify that a `$skill`
mention remains visible only as transcript evidence while neither the
skill body nor memory context is injected.
- Expand the Guardian configuration test to cover the disabled memory
settings.
## Testing
- Updated the Guardian review request snapshot and assertions for skill
and memory isolation.
- Extended the Guardian session configuration test to cover memories.
## Why
We need request-level evidence for Guardian cases where
`codex-auto-review` is missing from the client-side model catalog and
the review falls back to the parent model.
## What changed
- Add `guardian_catalog_contains_auto_review` to Guardian Responses API
client metadata.
- Add `guardian_model_provider_id` to Guardian Responses API client
metadata.
- Keep review-session metadata optional so callers without metadata
preserve the existing `None` path.
- Add tests for override, normal preferred-model, and
missing-auto-review-catalog behavior.
## Validation
- `just test -p codex-core
guardian_review_records_missing_auto_review_model_in_request_metadata`
- `just test -p codex-core
guardian_review_uses_model_catalog_override_when_preferred_review_model_exists`
- `just test -p codex-core
guardian_review_uses_preferred_review_model_without_model_catalog_override`
- `git diff --check origin/main`
## Why
Multi-agent v2 `send_message` deliveries already reach the receiving
model as typed `agent_message` items with encrypted content.
Child-completion notifications are generated by Codex itself, so their
content is plaintext and previously fell back to a serialized JSON
envelope inside an assistant message.
With plaintext `input_text` supported for `agent_message`, both delivery
paths can use the same model-visible type while preserving explicit
author and recipient metadata.
## What changed
- add plaintext `input_text` support to `AgentMessageInputContent` and
regenerate the affected app-server schemas
- preserve `InterAgentCommunication` as structured mailbox input instead
of converting it to assistant text
- record delivered communications as typed `agent_message` history items
- persist a dedicated rollout item so local delivery metadata such as
`trigger_turn` remains available without leaking into the Responses
request
- reconstruct typed agent messages on resume and preserve fork-turn
truncation behavior
- remove request-time assistant-content parsing
- preserve plaintext and encrypted inter-agent deliveries in stage-one
memory inputs
- normalize and link plaintext and encrypted agent messages in rollout
traces without treating inbound messages as child results
- cover the real MultiAgent V2 child-completion path end to end with
deterministic mailbox synchronization
## Verification
- `just test -p codex-core
plaintext_multi_agent_v2_completion_sends_agent_message`
- `just test -p codex-core input_queue_drains_mailbox_in_delivery_order
record_initial_history_reconstructs_typed_inter_agent_message
fork_turn_positions_use_inter_agent_delivery_metadata`
- `just test -p codex-memories-write
serializes_inter_agent_communications_for_memory`
- `just test -p codex-rollout-trace
agent_messages_preserve_routing_and_content
sub_agent_started_activity_creates_spawn_edge`
- `just test -p codex-rollout-trace
agent_result_edge_falls_back_to_child_thread_without_result_message`
- `just test -p codex-protocol -p codex-rollout -p
codex-app-server-protocol`
## Why
Sandbox cwd values can cross app-server and exec-server host boundaries.
They should retain URI semantics until the receiving host validates them
instead of being interpreted early as native paths.
## What
- Carry `PathUri` through filesystem sandbox contexts, sandbox commands,
and transform inputs.
- Convert command and policy cwd once in `SandboxManager::transform`,
then keep launch requests native.
- Preserve sandbox cwd over remote filesystem transport and reject
non-native URIs without fallback.
- Cache paired native/URI turn-environment cwd values during migration,
with immutable access to keep them synchronized.
- Extend existing protocol, forwarding, transform, and core runtime
tests.
## Why
We want to remove implicit use of `$CODEX_HOME` from `codex-core` and
make embedders responsible for supplying user-level instructions. This
also ensures user instructions load when no primary environment is
selected.
## What changed
Stacked on #27415, which makes `codex exec` surface thread-scoped
runtime warnings.
- Added `UserInstructionsProvider` to `codex-extension-api`, with
absolute source attribution and recoverable loading warnings.
- Added `codex-home` with the filesystem-backed provider for
`AGENTS.override.md` and `AGENTS.md`, preserving precedence, fallback,
trimming, lossy UTF-8 handling, and the existing uncapped global
instruction size.
- Removed global instruction loading from `Config` and require
`ThreadManager` callers to inject a provider.
- Load provider instructions once for each fresh root runtime, including
runtimes without a primary environment. Running sessions retain their
snapshot, while child agents inherit the parent snapshot without
invoking the provider.
- Keep provider instructions separate while loading project `AGENTS.md`,
then assemble the model-visible instructions with the existing ordering,
source attribution, warning, and turn-context behavior.
- Wired the Codex home provider through the CLI, app server, MCP server,
core facade, and thread-manager sample.
## Validation
- `just test -p codex-home -p codex-extension-api`
- `just test -p codex-core agents_md`
- `just test -p codex-core guardian`
- `just test -p codex-app-server
thread_start_without_selected_environment_includes_only_global_instruction_source`
- `just test -p codex-exec warning`
- `just bazel-lock-check`
## Background
Codex can use **Auto Review** for permission requests. Instead of asking
the user immediately, Codex starts a separate locked-down reviewer
session called **Guardian**, which returns a structured `allow` or
`deny` assessment.
The Guardian reviewer is itself a Codex session, so its model request
can fail for transient infrastructure reasons such as model overload,
HTTP connection failure, or response-stream disconnect. Today, any such
failure immediately ends the Auto Review attempt and blocks the action.
This PR adds bounded retries for failures that the existing protocol
explicitly identifies as transient.
Linear context:
[CA-539](https://linear.app/openai/issue/CA-539/retry-auto-review-infrastructure-failures-and-fall-back-to-manual)
## What changes
A Guardian review can now make at most **three total attempts**:
1. Run the review normally.
2. Retry after a jittered delay of roughly 180–220 ms if the first
attempt fails with an eligible error.
3. Retry after a jittered delay of roughly 360–440 ms if the second
attempt also fails with an eligible error.
All attempts share the original review deadline. Jitter spreads retries
from concurrent clients to reduce synchronized load during broader
outages. The retries do not reset the user's maximum wait time, and the
backoff waits terminate early if the review is cancelled or the deadline
expires.
Before retrying, the existing Guardian session lifecycle decides whether
the session remains usable. Healthy trunks are reused, broken trunks are
removed by the existing cleanup path, and ephemeral sessions continue to
clean themselves up.
The review still emits one logical lifecycle to clients. Recoverable
intermediate failures do not produce warnings or terminal events.
## Retry policy
### Retried up to twice
- model/server overload
- HTTP connection failure
- response-stream connection failure
- response-stream disconnect
- internal server error
- a final reviewer message that cannot be parsed as the required
Guardian assessment
### Not retried
- bad or invalid requests
- authentication failures
- usage limits
- cyber-policy failures
- errors without a structured category
- a request that already exhausted the lower-level Responses retry
budget
- a completed Guardian turn with no assessment payload
- prompt-construction failures
- Guardian review timeout
- cancellation or abort
- a valid `deny` assessment
The session-error classification uses `ErrorEvent.codex_error_info`; it
does not inspect error-message strings.
## Implementation notes
- `wait_for_guardian_review` preserves the complete `ErrorEvent`,
including structured `codex_error_info`.
- Guardian session failures preserve the original message and optional
structured `CodexErrorInfo`.
- The retry policy classifies the explicitly transient `CodexErrorInfo`
variants; unknown, absent, and deterministic categories are not retried.
- The Guardian session manager receives the caller's deadline rather
than creating a new timeout per attempt.
- Analytics record the final `attempt_count`.
- Retry orchestration does not add a separate session-cleanup protocol;
it relies on the existing trunk and ephemeral lifecycle decisions.
## Automated testing
Focused Guardian coverage verifies:
- every supported transient `CodexErrorInfo` is classified as retryable,
while absent and non-transient categories are not;
- structured transient session failure -> retry -> approval with the
healthy trunk reused;
- two invalid Guardian responses -> third attempt -> approval, with
exactly three requests;
- three invalid responses -> existing fail-closed result, with exactly
three requests and one terminal lifecycle;
- valid denial, missing payload, invalid request, timeout, cancellation,
and prompt/session construction failures are not retried;
- retry eligibility ends after the third attempt;
- retry delays use the shared exponential backoff helper and remain
within the expected jitter bounds;
- cancellation and deadline expiry interrupt the backoff wait;
- healthy trunks are reused across retryable failures;
- broken event streams remove the trunk through the existing lifecycle
cleanup;
- an ephemeral retry does not disturb a concurrent trunk review.
Validation performed:
- `just test -p codex-core guardian_review_
guardian_ephemeral_retry_preserves_parallel_trunk_and_fork_history
run_review_removes_trunk_when_event_stream_is_broken` — **42 passed**;
- `just test -p codex-analytics` — **71 passed**;
- scoped Clippy fixes for `codex-core` and `codex-analytics` passed.
A prior full `codex-core` run had unrelated environment-sensitive
failures outside Guardian coverage.
## Manual QA
The focused integration tests use the local mock Responses server to
inspect exact request counts and emitted lifecycle events. They confirm
that retries are internal, a successful later attempt supplies the final
decision, non-retryable failures issue only one request, and exhausted
retries emit only one terminal result.
## Why
Thread cwd and environment selections are a single logical setting in
core: updating one without the other can silently desynchronize the
next-turn execution context. This change makes that relationship
explicit in the internal thread settings flow while preserving the
existing app-server public API shape.
## What changed
- Moved the cwd/environment pair through internal
`ThreadSettingsOverrides.environment_settings` instead of a top-level
internal `cwd` field.
- Kept `thread/settings/update` public params unchanged, with app-server
translating top-level `cwd` into the paired internal settings shape.
- Moved `Op::UserInput` environment overrides into thread settings so
user turns and settings updates use the same core path.
- Updated core, app-server, MCP, memories, sample, and test callsites to
construct the paired settings shape.
## Verification
- `git diff --check`
- Local test run starting after PR creation.
## Why
Thread settings cwd overrides are expected to be resolved before they
enter core. Keeping this boundary as a plain `PathBuf` made it easy for
core/session code to keep fallback normalization and relative-path
resolution logic in places that should only receive an already-resolved
cwd.
This is intentionally the absolute-cwd-only slice: it does not change
environment selection stickiness or cwd-to-default-environment fallback
behavior.
## What changed
- Changes `ThreadSettingsOverrides.cwd`,
`CodexThreadSettingsOverrides.cwd`, and `SessionSettingsUpdate.cwd` to
use `AbsolutePathBuf`.
- Removes core-side cwd normalization/resolution from session settings
updates.
- Updates affected core/app-server test helpers and callsites to pass
existing absolute cwd values or use `abs()` helpers.
## Validation
Opening as draft so CI can start while local validation continues.
## Summary
- accept non-empty model-defined reasoning effort values while
preserving built-in effort behavior
- propagate the non-Copy effort type through core, app-server, TUI,
telemetry, and persistence call sites
- preserve string wire encoding and expose an open-string schema for
clients
- update model selection and shortcut behavior for model-advertised
effort values
## Root cause
`ReasoningEffort` gained a string-backed custom variant, so it could no
longer implement `Copy` or rely on derived closed-enum serialization.
Existing consumers still moved effort values from shared references and
assumed a fixed built-in value set.
## Validation
- `just fmt`
- Local tests and compilation were not run per request; relying on CI.
## Why
Workspace-specific `AGENTS.md` loading needs to use the selected
environment filesystem so remote workspaces and child agents read
instructions from their actual environment instead of the host
filesystem. The app-server should report the same instruction sources
the initialized thread actually loaded, rather than independently
rescanning configuration and filesystem state.
## What changed
- Introduce `LoadedAgentsMd` to retain ordered user, project, and
internal instructions with their provenance.
- Load and canonicalize workspace `AGENTS.md` paths through the primary
`EnvironmentManager` environment, then render the loaded instructions
when constructing turn context.
- Expose cached loaded instruction sources from initialized threads and
use them for app-server start, resume, and fork responses.
- Preserve global `CODEX_HOME` loading and separator behavior while
excluding empty project files that did not supply model-visible
instructions.
- Add integration coverage for CLI injection, selected-environment
provenance and rendering, empty environment selection, and cached
sources on loaded-thread resume.
## Validation
- `just test -p codex-core agents_md`
- `just test -p codex-core
selected_environment_sources_match_model_visible_instructions`
- `just test -p codex-exec agents_md`
- `just test -p codex-app-server instruction_sources`
- `just test -p codex-app-server --status-level fail`
## Why
Guardian review turns already submit a read-only `PermissionProfile`,
which is the permissions model the runtime should honor. Passing the
equivalent legacy `SandboxPolicy` through `ThreadSettingsOverrides`
keeps two representations of the same read-only constraint alive on this
path and makes the guardian flow depend on compatibility plumbing that
is being phased out.
## What Changed
- Set `sandbox_policy` to `None` when the guardian review session
submits its child `Op::UserInput`.
- Keep `permission_profile: Some(PermissionProfile::read_only())` and
`approval_policy: Some(AskForApproval::Never)`, so the guardian review
remains read-only and cannot request approvals.
- Remove the now-unused `SandboxPolicy` import and redundant comment
from `codex-rs/core/src/guardian/review_session.rs`.
## Verification
Not run locally; this is a narrow cleanup of redundant thread-settings
override state.
## Why
Guardian auto-review normally uses the provider-preferred review model
when one is available. Some parent models need model-catalog metadata to
select a different review model while keeping older `/models` payloads
compatible when that metadata is absent.
## What changed
- Added optional `ModelInfo::auto_review_model_override` metadata to the
public model payload as a review-model slug.
- Updated Guardian review model selection to prefer the catalog override
when present, while preserving the existing provider preferred-model
path and parent-model fallback when it is omitted.
- Added focused Guardian coverage for override and no-override model
selection.
- Added an `auto_review` core integration suite test that loads override
metadata from a remote model catalog path and asserts the strict
auto-review `/responses` request uses the catalog-selected review model.
- Updated existing `ModelInfo` fixtures and local catalog constructors
for the new optional field.
## Validation
- `cargo test -p codex-protocol
model_info_defaults_availability_nux_to_none_when_omitted`
- `cargo test -p codex-core guardian_review_uses_`
- `cargo test -p codex-core
remote_model_override_uses_catalog_model_for_strict_auto_review --test
all`
- `just fix -p codex-protocol`
- `just fix -p codex-core`
- `just fmt`
- `git diff --check`
## Why
This PR
https://github.com/openai/codex/pull/24161#discussion_r3325692763
revealed a subagent data modeling issue, where we overloaded
`forked_from_id` to also mean `parent_thread_id`. That's incorrect since
guardian and review subagents can be a subagent and NOT fork the main
thread's history.
The solution here is to explicitly store a new `parent_thread_id` on
`SessionMeta`, alongside `forked_from_id` which already exists. While
we're at it, also expose it in the app-server protocol on the `Thread`
object.
A thread->subagent relationship and a fork of thread history are
orthogonal concepts.
## What Changed
- Added top-level `parent_thread_id` persistence on `SessionMeta` and
runtime/session plumbing through `SessionConfiguredEvent`,
`CodexSpawnArgs`, `SessionConfiguration`, `ThreadConfigSnapshot`,
`TurnContext`, and `ModelClient`.
- Made turn metadata, request headers, analytics, and subagent-start
events read the separate runtime/top-level parent field instead of
deriving general parent lineage from `SessionSource` or
`forked_from_thread_id`.
- Passed parent lineage separately at delegated subagent, review,
guardian, agent-job, and multi-agent spawn construction sites;
copied-history fork lineage remains derived only from `InitialHistory`.
- Persisted and exposed parent lineage through rollout/thread-store
projections and app-server v2 `Thread.parentThreadId`.
- Updated app-server README text and regenerated app-server schema
fixtures for the additive `parentThreadId` response field.
## Summary
Some permission profiles can encode filesystem reads that should remain
unavailable to the agent. Before this change, the model-visible context
and automatic approval review prompt summarized the effective
permissions as a legacy sandbox mode, which can omit permission-profile
filesystem entries from escalation decisions.
For example, a profile can grant workspace access while denying a
private subtree across every workspace root:
```toml
default_permissions = "restricted-workspace"
[permissions.restricted-workspace.workspace_roots]
"/Users/alice/project" = true
"/Users/alice/other-project" = true
[permissions.restricted-workspace.filesystem]
":minimal" = "read"
[permissions.restricted-workspace.filesystem.":workspace_roots"]
"." = "write"
"private" = "deny"
"private/**" = "deny"
```
The context window now describes the workspace roots and effective
filesystem side of the `PermissionProfile` directly, with deny entries
marked as non-escalatable:
```xml
<environment_context>
<cwd>/Users/alice/project</cwd>
<shell>zsh</shell>
<filesystem><workspace_roots><root>/Users/alice/project</root><root>/Users/alice/other-project</root></workspace_roots><permission_profile type="managed"><file_system type="restricted"><entry access="read"><special>:minimal</special></entry><entry access="write"><path>/Users/alice/project</path></entry><entry access="write"><path>/Users/alice/other-project</path></entry><entry access="deny" escalatable="false"><path>/Users/alice/project/private</path></entry><entry access="deny" escalatable="false"><path>/Users/alice/other-project/private</path></entry><entry access="deny" escalatable="false"><glob>/Users/alice/project/private/**</glob></entry><entry access="deny" escalatable="false"><glob>/Users/alice/other-project/private/**</glob></entry></file_system></permission_profile></filesystem>
</environment_context>
```
Managed requirements can impose the same kind of deny-read restriction:
```toml
[permissions.filesystem]
deny_read = [
"/Users/alice/project/private",
"/Users/alice/project/private/**",
]
```
The automatic approval review prompt also receives the parent turn's
denied-read context, so review decisions can account for the active
permission profile.
## What Changed
- Render the effective filesystem profile in `<environment_context>`,
including profile type, filesystem entries, workspace roots, and
non-escalatable deny entries.
- Persist effective `workspace_roots` in `TurnContextItem` so
resumed/replayed context does not have to bind `:workspace_roots`
through legacy `cwd` fallback.
- Add explicit permission instructions that denied reads are policy
restrictions, not escalation targets.
- Pass the parent turn's denied-read context into automatic approval
reviews.
- Add targeted coverage for prompt rendering, workspace-root
materialization, replay context, and review prompt context.
- Keep the prompt-context test expectations platform-aware so the same
filesystem rendering assertions pass on Unix and Windows paths.
## Testing
- `just test -p codex-core
context::environment_context::tests::serialize_environment_context_with_full_filesystem_profile`
- `just test -p codex-core
context::environment_context::tests::turn_context_item_filesystem_uses_workspace_roots_instead_of_cwd`
- `just test -p codex-core
context::permissions_instructions::permissions_instructions_tests::builds_permissions_from_profile_with_denied_reads`
- `just fix -p codex-core`
I also attempted `just test -p codex-core`; the changed prompt-context
tests passed, but the full local run did not complete cleanly in this
sandboxed macOS environment due unrelated user-shell `CODEX_SANDBOX*`
expectations and integration-test timeouts.
## Why
Guardian reviews already emit analytics events, but we do not expose
aggregate OpenTelemetry metrics for review volume, latency, token usage,
or terminal outcomes. That makes it harder to monitor Guardian behavior
during rollouts and to compare review outcomes by source, action type,
session kind, model, and failure mode.
## What Changed
- Added Guardian review metric names for count, total duration, time to
first token, and token usage in `codex-rs/otel`.
- Added `core/src/guardian/metrics.rs` to convert
`GuardianReviewAnalyticsResult` into sanitized metric tags covering
decision, terminal status, failure reason, approval request source,
reviewed action, session kind, risk/outcome, model, reasoning effort,
and context/truncation state.
- Emitted the new metrics from `track_guardian_review` for each terminal
Guardian review result.
## Testing
- Added
`guardian_review_metrics_record_counts_durations_and_token_usage`, which
verifies the emitted count, duration, TTFT, token usage histograms, and
tag set through the in-memory metrics exporter.
## Summary
- Add the required `/*parent_thread_id*/` argument comment at the
Guardian review session test callsite flagged by CI.
## Validation
- `just fmt`
- Not run: clippy/tests, per request; CI will cover them.
Split from the Guardian prompt cache key change. This PR only updates
codex-rs/core/src/guardian/tests.rs. Validation was not run per request;
this branch is expected to rely on the companion split PRs.
Split from the Guardian prompt cache key change. This PR only updates
codex-rs/core/src/guardian/review_session.rs. Validation was not run per
request; this branch is expected to rely on the companion split PRs.
Split from the Guardian prompt cache key change. This PR only updates
codex-rs/core/src/guardian/mod.rs. Validation was not run per request;
this branch is expected to rely on the companion split PRs.
## Summary
Clear inherited legacy `notify` from Guardian review session config,
since we should not be passing auto review threads into `notify`
targets. Keeps legacy notify payload and hook runtime behavior unchanged
for normal user turns.
## Testing
- [x] add a Guardian config regression and dedicated Guardian
integration test so review sessions cannot inherit parent notify hooks
## Summary
Adds experimental `additionalContext` support to `turn/start` and
`turn/steer` so clients can provide ephemeral external context, such as
browser or automation state, without turning that plumbing into a
visible user prompt or triggering user-prompt lifecycle behavior.
## API Shape
The parameter shape is:
```ts
additionalContext?: Record<string, {
value: string
kind: "untrusted" | "application"
}> | null
```
Example:
```json
{
"additionalContext": {
"browser_info": {
"value": "Active tab is CI failures.",
"kind": "untrusted"
},
"automation_info": {
"value": "CI rerun is in progress.",
"kind": "application"
}
}
}
```
The keys are opaque and caller-defined.
## Context Injection
When provided, accepted entries are inserted into model context as
hidden contextual message items, not as visible thread user-message
items.
`kind: "untrusted"` entries are inserted with role `user`:
```text
<external_${key}>${value}</external_${key}>
```
`kind: "application"` entries are inserted with role `developer`:
```text
<${key}>${value}</${key}>
```
Values are not escaped. Each value is truncated to 1k approximate tokens
before wrapping.
For `turn/start`, accepted additional context is inserted before normal
user input. For `turn/steer`, additional context is merged only when the
steer includes non-empty user input; context-only steers still reject as
empty input.
## Dedupe Strategy
`AdditionalContextStore` lives on session state and stores the latest
complete additional-context map.
Each `turn/start` or non-empty `turn/steer` treats its
`additionalContext` as the current complete set of values. Entries are
injected only when the key is new or the exact entry for that key
changed, including `value` or `kind`. After merging, the store is
replaced with the provided map, so omitted keys are removed from the
retained set and can be injected again later if reintroduced.
Omitting `additionalContext`, passing `null`, or passing an empty object
resets the store to empty and injects nothing.
## What Changed
- Threads experimental v2 `additionalContext` through app-server into
core turn start and steer handling.
- Adds separate contextual fragment types for untrusted user-role
context and application developer-role context.
- Uses pending response input items so additional context can be
combined with normal user input without treating it as prompt text.
- Adds integration coverage for start/steer flow, role routing,
dedupe/reset behavior, deletion/re-add behavior, hook-blocked input
behavior, empty context-only steer rejection, external-fragment marker
matching, and truncation.
## Why
Once a named permission profile is selected, runtime state has to keep
that profile identity intact instead of collapsing back to anonymous
effective permissions. The session refresh path also needs to rebuild
profile-derived network proxy state so active profile switches take
effect consistently.
## What changed
- Preserve the active permission profile through session updates.
- Rebuild profile-derived runtime/network configuration when the active
profile changes.
- Keep the runtime path aligned with the current session configuration
APIs.
- Tighten the affected tests, including the Windows delete-pending
memory-file case that was intermittently tripping CI.
## Stack
1. **This PR**: runtime/session/network propagation for active
permission profiles.
2. [#23708](https://github.com/openai/codex/pull/23708): TUI selection
plumbing and guardrail flow.
3. [#21559](https://github.com/openai/codex/pull/21559): profile-aware
`/permissions` menu and custom profile display.
<img width="1296" height="906" alt="image"
src="https://github.com/user-attachments/assets/077fa3a7-80cb-4925-80b1-d2395018d90a"
/>
## Summary
- remove the unreachable ARC monitor path from MCP tool approval
handling
- delete the unused ARC monitor module/tests and trim the orphaned
safety-monitor decision plumbing
- keep `always allow` approvals on the existing auto-approval
short-circuit without a dead monitor hop
## Testing
- `cargo test -p codex-core mcp_tool_call`
- `just fmt`
- `just fix -p codex-core`
- `git diff --check`
## Additional validation
- Attempted `cargo test -p codex-core`; the library test target passed,
then the integration target failed in this local environment.
- The narrower MCP-focused rerun passed its unit coverage and only hit
missing local `test_stdio_server` binaries in filtered integration
cases.
## Why
`model_auto_compact_token_limit` has only been able to budget the full
active context. That makes it hard to set a small "growth since
compaction" budget for sessions that preserve a large carried window
prefix: the preserved prefix can consume the whole budget and force
immediate repeated compaction.
This PR adds an opt-in `body_after_prefix` scope so callers can apply
`model_auto_compact_token_limit` to sampled output and later growth
after the current carried prefix, while still forcing compaction before
the full model context window is exhausted.
## What changed
- Adds `AutoCompactTokenLimitScope` with the existing `total` behavior
as the default and a new `body_after_prefix` mode:
[`config_types.rs`](https://github.com/openai/codex/blob/973806b1cb35792555bead994cb3ed94656eb171/codex-rs/protocol/src/config_types.rs#L24-L37).
- Threads `model_auto_compact_token_limit_scope` through config loading,
`Config`, `core-api`, and app-server v2 schema/TypeScript generation.
- Records the first observed input-token count for a `body_after_prefix`
compaction window and uses it as the baseline when deciding whether the
scoped auto-compaction budget is exhausted:
[`turn.rs`](https://github.com/openai/codex/blob/973806b1cb35792555bead994cb3ed94656eb171/codex-rs/core/src/session/turn.rs#L743-L781).
- Keeps a hard context-window cap in `body_after_prefix`, so scoped
budgeting cannot let the active context overrun the usable window.
## Verification
Added compact-suite coverage for the two key behaviors:
`body_after_prefix` does not re-compact just because the carried prefix
is larger than the scoped budget, and it still compacts when the total
active context reaches the configured context window:
[`compact.rs`](https://github.com/openai/codex/blob/973806b1cb35792555bead994cb3ed94656eb171/codex-rs/core/tests/suite/compact.rs#L3003-L3128).
## Why
`SandboxPolicy` is now a legacy compatibility shape, but several tests
still built a `SandboxPolicy` only to immediately convert it into
`PermissionProfile` for APIs that already accept canonical runtime
permissions. Those detours make it harder to audit where legacy sandbox
policy is still required, because boundary-only usages are mixed
together with ordinary test setup.
## What Changed
- Updated tests in `codex-core`, `codex-exec`, `codex-analytics`, and
`codex-config` to construct `PermissionProfile` values directly when the
code under test takes a permission profile.
- Changed exec-policy, request-permissions, session, and sandbox test
helpers to pass `PermissionProfile` through instead of converting from
`SandboxPolicy` internally.
- Left `SandboxPolicy` in place where tests are explicitly exercising
legacy compatibility or request/response boundaries.
## Test Plan
- `cargo test -p codex-analytics -p codex-config`
- `cargo test -p codex-core --lib safety::tests`
- `cargo test -p codex-core --lib exec_policy::tests::`
- `cargo test -p codex-core --lib exec::tests`
- `cargo test -p codex-core --lib guardian_review_session_config`
- `cargo test -p codex-core --lib tools::network_approval::tests`
- `cargo test -p codex-core --lib
tools::runtimes::shell::unix_escalation::tests`
- `cargo test -p codex-core --lib managed_network`
- `cargo test -p codex-core --test all request_permissions::`
- `cargo test -p codex-exec sandbox`
---
[//]: # (BEGIN SAPLING FOOTER)
Stack created with [Sapling](https://sapling-scm.com). Best reviewed
with [ReviewStack](https://reviewstack.dev/openai/codex/pull/23030).
* #23036
* __->__ #23030
## Why
`SandboxPolicy` is being pushed back toward legacy config loading and
compatibility boundaries. Guardian review sessions already want the
built-in read-only permission behavior; carrying that as an active
`PermissionProfile` makes the review sandbox follow the new permissions
path instead of configuring the child session through the legacy policy
API.
## What Changed
- Configure the guardian review session with
`PermissionProfile::read_only()`.
- Send the read-only profile through the guardian child `Op::UserTurn`.
- Keep the legacy `sandbox_policy` field populated with
`SandboxPolicy::new_read_only_policy()` declared next to the profile so
the two remain visibly in sync until the compatibility field goes away.
## How To Review
Start in `codex-rs/core/src/guardian/review_session.rs`. The important
check is that both the guardian config and the child turn now use the
read-only permission profile, while the remaining
`SandboxPolicy::ReadOnly` assignment is only the compatibility field
required by the current turn protocol.
## Verification
- `cargo test -p codex-core
guardian_review_session_config_clears_parent_developer_instructions`
---
[//]: # (BEGIN SAPLING FOOTER)
Stack created with [Sapling](https://sapling-scm.com). Best reviewed
with [ReviewStack](https://reviewstack.dev/openai/codex/pull/22789).
* #22795
* #22792
* #22791
* #22790
* __->__ #22789
## Why
This PR is the invariant-cleanup layer that follows the workspace-roots
base merged in [#22610](https://github.com/openai/codex/pull/22610).
#22610 adds `[permissions.<id>.workspace_roots]` and keeps runtime
workspace roots separate from the raw permission profile, but its
in-memory representation is intentionally transitional: `Permissions`
still carries the selected profile identity next to a constrained
`PermissionProfile`. That makes APIs such as
`set_constrained_permission_profile_with_active_profile()` fragile
because the id and value only mean the right thing when every caller
keeps them in sync.
This PR introduces a single resolved profile state so profile identity,
`extends`, the profile value, and profile-declared workspace roots
travel together. The next PR,
[#22611](https://github.com/openai/codex/pull/22611), builds on this by
changing the app-server turn API to select permission profiles by id
plus runtime workspace roots.
## Stack Context
- #22610, now merged: adds profile-declared `workspace_roots`, runtime
workspace roots, and `:workspace_roots` materialization.
- This PR: replaces the parallel active-profile/profile-value fields
with `PermissionProfileState`.
- #22611: switches app-server turn updates toward profile ids plus
runtime workspace roots.
- #22612: updates TUI/exec summaries to show the effective workspace
roots.
Keeping this separate from #22611 is deliberate: reviewers can validate
the internal state invariant before reviewing the app-server protocol
migration.
## What Changed
- Added `ResolvedPermissionProfile::{Legacy, BuiltIn, Named}` and
`PermissionProfileState`.
- Typed built-in profile ids with `BuiltInPermissionProfileId`.
- Moved selected profile identity and profile-declared workspace roots
into the resolved state.
- Replaced `Permissions` parallel profile fields with one
`permission_profile_state`.
- Removed `set_constrained_permission_profile_with_active_profile()`
from session sync paths.
- Kept trusted session replay/`SessionConfigured` compatibility through
explicit session snapshot helpers.
- Updated session configuration, MCP initialization, app-server, exec,
TUI, and guardian call sites to consume `&PermissionProfile` directly.
## Review Guide
Start with `codex-rs/core/src/config/resolved_permission_profile.rs`; it
is the new invariant boundary. Then review
`codex-rs/core/src/config/mod.rs` to see how config loading records
active profile identity and profile workspace roots. The remaining
call-site changes are mostly mechanical fallout from
`Permissions::permission_profile()` returning `&PermissionProfile`
instead of `&Constrained<PermissionProfile>`.
## Verification
The existing config/session coverage now constructs and asserts through
`PermissionProfileState`. The workspace-root config test also asserts
that profile-declared roots are preserved in the resolved state, which
is the behavior #22611 relies on when runtime roots become mutable
through the app-server API.
---
[//]: # (BEGIN SAPLING FOOTER)
Stack created with [Sapling](https://sapling-scm.com). Best reviewed
with [ReviewStack](https://reviewstack.dev/openai/codex/pull/22683).
* #22612
* #22611
* __->__ #22683
## Why
This is the configuration/model half of the alternative permissions
migration we discussed as a comparison point for
[#22401](https://github.com/openai/codex/pull/22401) and
[#22402](https://github.com/openai/codex/pull/22402).
The old `workspace-write` model mixes three concerns that we want to
keep separate:
- reusable profile rules that should stay immutable once selected
- user/runtime workspace roots from `cwd`, `--add-dir`, and legacy
workspace-write config
- internal Codex writable roots such as memories, which should not be
shown as user workspace roots
This PR gives permission profiles first-class `workspace_roots` so users
can opt multiple repositories into the same `:workspace_roots` rules
without using broad absolute-path write grants. It also starts
separating the raw selected profile from the effective runtime profile
by making `Permissions` expose explicit accessors instead of public
mutable fields.
A representative `config.toml` looks like this:
```toml
default_permissions = "dev"
[permissions.dev.workspace_roots]
"~/code/openai" = true
"~/code/developers-website" = true
[permissions.dev.filesystem.":workspace_roots"]
"." = "write"
".codex" = "read"
".git" = "read"
".vscode" = "read"
```
If Codex starts in `~/code/codex` with that profile selected, the
effective workspace-root set becomes:
- `~/code/codex` from the runtime `cwd`
- `~/code/openai` from the profile
- `~/code/developers-website` from the profile
The `:workspace_roots` rules are materialized across each root, so
`.git`, `.codex`, and `.vscode` stay scoped the same way everywhere.
Runtime additions such as `--add-dir` can still layer on later stack
entries without mutating the selected profile.
## Stack Shape
This PR intentionally stops before the profile-identity cleanup in
[#22683](https://github.com/openai/codex/pull/22683) so the base review
stays focused on config loading, workspace-root materialization, and
compatibility with legacy `workspace-write`.
The representation in this PR is therefore transitional: `Permissions`
carries enough state to distinguish the raw constrained profile from the
effective runtime profile, and there are still call sites that must keep
the active profile identity and constrained profile value in sync. The
follow-up PR replaces that with a single resolved profile state
(`ResolvedPermissionProfile` / `PermissionProfileState`) that keeps the
profile id, immutable `PermissionProfile`, and profile-declared
workspace roots together. That follow-up removes APIs such as
`set_constrained_permission_profile_with_active_profile()` where
separate arguments could drift out of sync.
Downstream PRs then build on this base to switch app-server turn updates
to profile ids plus runtime workspace roots and to finish the
user-visible summary behavior. Reviewers should judge this PR as the
workspace-roots foundation, not as the final in-memory shape of selected
permission profiles.
## Review Guide
Suggested review order:
1. Start with `codex-rs/core/src/config/mod.rs`.
This is the main shape change in the base slice. `Permissions` now
stores a private raw `Constrained<PermissionProfile>` plus runtime
`workspace_roots`. Callers use `permission_profile()` when they need the
raw constrained value and `effective_permission_profile()` when they
need a materialized runtime profile. As noted above,
[#22683](https://github.com/openai/codex/pull/22683) replaces this
transitional shape with a resolved profile state that keeps identity and
profile data together.
2. Review `codex-rs/config/src/permissions_toml.rs` and
`codex-rs/core/src/config/permissions.rs`.
These add `[permissions.<id>.workspace_roots]`, resolve enabled entries
relative to the policy cwd, and keep `:workspace_roots` deny-read glob
patterns symbolic until the actual roots are known.
3. Review `codex-rs/protocol/src/permissions.rs` and
`codex-rs/protocol/src/models.rs`.
These add the policy/profile materialization helpers that expand exact
`:workspace_roots` entries and scoped deny-read globs over every
workspace root. This is also where `ActivePermissionProfileModification`
is removed from the core model.
4. Review the legacy bridge in
`Config::load_from_base_config_with_overrides` and
`Config::set_legacy_sandbox_policy`.
This is where legacy `workspace-write` roots become runtime workspace
roots, while Codex internal writable roots stay internal and do not
appear as user-facing workspace roots.
5. Then skim downstream call sites.
The interesting pattern is raw-vs-effective access: state/proxy/bwrap
paths keep the raw constrained profile, while execution, summaries, and
user-visible status use the effective profile and workspace-root list.
## What Changed
- added `[permissions.<id>.workspace_roots]` to the config model and
schema
- added runtime `workspace_roots` state to `Config`/`Permissions` and
`ConfigOverrides`
- made `Permissions` profile fields private and replaced direct mutation
with accessors/setters
- added `PermissionProfile` and `FileSystemSandboxPolicy` helpers for
materializing `:workspace_roots` exact paths and deny-read globs across
all roots
- moved legacy additional writable roots into runtime workspace-root
state instead of active profile modifications
- removed `ActivePermissionProfileModification` and its app-server
protocol/schema export
- updated sandbox/status summary paths so internal writable roots are
not reported as user workspace roots
## Verification Strategy
The targeted tests cover the behavior at the layers where regressions
are most likely:
- `codex-rs/core/src/config/config_tests.rs` verifies config loading,
legacy workspace-root seeding, effective profile materialization, and
memory-root handling.
- `codex-rs/core/src/config/permissions_tests.rs` verifies profile
`workspace_roots` parsing and `:workspace_roots` scoped/glob
compilation.
- `codex-rs/protocol/src/permissions.rs` unit tests verify exact and
glob materialization over multiple workspace roots.
- `codex-rs/tui/src/status/tests.rs` and
`codex-rs/utils/sandbox-summary/src/sandbox_summary.rs` verify the
user-facing summaries show effective workspace roots and hide internal
writes.
I also ran `cargo check --tests` locally after the latest stack refresh
to catch cross-crate API breakage from the private-field/accessor
changes.
---
[//]: # (BEGIN SAPLING FOOTER)
Stack created with [Sapling](https://sapling-scm.com). Best reviewed
with [ReviewStack](https://reviewstack.dev/openai/codex/pull/22610).
* #22612
* #22611
* #22683
* __->__ #22610
## Summary
Removes the feature since this is effectively on by default in all cases
where we should use it, or can be configured via models.json.
## Testing
- [x] unit tests pass
## Why
`TurnContext::cwd` and `TurnContext::resolve_path` are being phased out
in favor of using the selected turn environment cwd directly.
Deprecating both APIs makes any new direct dependency visible while
preserving the existing migration path for current callers.
## What Changed
- Marked `TurnContext::cwd` and `TurnContext::resolve_path` as
deprecated with guidance to use the selected turn environment cwd
instead.
- Added exact `#[allow(deprecated)]` suppressions at each existing
direct usage site, including tests, rather than adding crate-wide
suppression.
- Kept the change behavior-preserving: current cwd reads, writes, and
path resolution continue to use the same values.
## Verification
- `just fmt`
- `cargo check -p codex-core`
- `cargo check -p codex-core --tests`
- `git diff --check`
## Why
Guardian review selection was hard-coded in `core`, which worked for the
default OpenAI path but did not give provider implementations a way to
choose backend-specific reviewer model IDs. That matters for Amazon
Bedrock: guardian review should run through the Bedrock/Mantle provider
using Bedrock's `openai.gpt-5.4` model ID, instead of accidentally
selecting a reviewer model that implies the OpenAI backend.
## What Changed
- Added provider-owned approval review model selection via
`ModelProvider::approval_review_model_selection`.
- Moved the existing default selection policy into the provider
abstraction: prefer the requested reviewer model when it is available,
otherwise fall back to the active turn model, preferring `Low` reasoning
when supported.
- Added an Amazon Bedrock override that pins guardian review to
`openai.gpt-5.4` with `Low` reasoning.
## Why
Review telemetry should describe reviews as first-class events, not only
as counters denormalized onto terminal tool-item events. That lets us
analyze guardian and user reviews consistently across command execution,
file changes, permissions, and network access, while still preserving
the terminal item summaries that existing tool analytics need.
To make those review events accurate, analytics also needs the observed
completion time for each review and enough command metadata to
distinguish `shell` from `unified_exec` reviews.
## What changed
- emit generic `codex_review_event` rows for completed user and guardian
reviews, with review subjects, reviewer, trigger, terminal status,
resolution, and observed duration
- reduce approval request / response / abort facts into review events
for command execution, file change, and permissions flows
- keep denormalized review counts, final approval outcome, and
permission-request flags on terminal tool-item events for
item-associated reviews
- plumb review completion timing so user-review responses and aborts use
app-server-observed completion times, while guardian analytics reuse the
same terminal timestamps emitted on guardian assessment events
- carry command approval `source` through the protocol and app-server
layers so review analytics can distinguish `shell` from `unified_exec`
- add analytics coverage for user-review emission, guardian-review
emission, permission reviews that should not denormalize onto tool
items, item-summary isolation across threads, and the serialized
review-event shape
## Verification
- `cargo test -p codex-analytics`
---
[//]: # (BEGIN SAPLING FOOTER)
Stack created with [Sapling](https://sapling-scm.com). Best reviewed
with [ReviewStack](https://reviewstack.dev/openai/codex/pull/18748).
* __->__ #18748
* #21434
* #18747
* #17090
* #17089
* #20514
## Why
Long-running turns can accumulate enough denied auto-review decisions to
trip the global short-circuit even when those denials are spread far
apart. The breaker should still stop genuinely bad loops, but it should
judge recent behavior instead of lifetime turn history.
## What changed
- Replaced the lifetime `10 total denials` threshold with `10 denials in
the last 50 reviews`.
- Kept the existing `3 consecutive denials` interrupt behavior
unchanged.
- Tracked recent auto-review outcomes in the circuit breaker and updated
the warning copy to report the rolling-window count.
- Renamed the new rolling-window coverage to `auto_review_*` test names.
- Added coverage that confirms older denials fall out of the 50-review
window and no longer trigger the breaker.
## Validation
- `just fmt`
- `cargo test -p codex-core guardian_rejection_circuit_breaker --lib`
- `cargo test -p codex-core auto_review_rejection_circuit_breaker --lib`
## Why
We want terminal tool review analytics, but the reducer should not stamp
review timing from its own wall clock.
This PR plumbs review timing through the real protocol and app-server
seams so downstream analytics can consume the emitter's timestamps
directly. Guardian reviews keep their enriched `started_at` /
`completed_at` analytics fields by deriving those legacy second-based
values from the same protocol-native millisecond lifecycle timestamps,
rather than sampling a separate analytics clock.
## What changed
- add `started_at_ms` to user approval request payloads
- add `started_at_ms` / `completed_at_ms` to guardian review
notifications
- preserve Guardian review `started_at` / `completed_at` enrichment from
the protocol-native timing source
- stamp typed `ServerResponse` analytics facts with app-server-observed
`completed_at_ms`
- thread the new timing fields through core, protocol, app-server, TUI,
and analytics fixtures
## Verification
- `cargo test -p codex-app-server outgoing_message --manifest-path
codex-rs/Cargo.toml`
- `cargo test -p codex-app-server-protocol guardian --manifest-path
codex-rs/Cargo.toml`
- `cargo test -p codex-tui guardian --manifest-path codex-rs/Cargo.toml`
- `cargo test -p codex-analytics analytics_client_tests --manifest-path
codex-rs/Cargo.toml`
---
[//]: # (BEGIN SAPLING FOOTER)
Stack created with [Sapling](https://sapling-scm.com). Best reviewed
with [ReviewStack](https://reviewstack.dev/openai/codex/pull/21434).
* #18748
* __->__ #21434
* #18747
* #17090
* #17089
* #20514
- fork loaded parent threads from `ThreadStore` history in core agent
control paths
- migrate guardian review fork history to loaded session history instead
of rereading rollout files
## Verification
- `cargo test -p codex-core spawn_agent_fork`
## Why
`multi_agents_v2` is meant to be independently gated from the older
`collab` feature. The tool registry still treated the
collaboration-style agent tools as `collab`-only, so enabling
`multi_agents_v2` without `collab` omitted the v2 agent tools. Review
and guardian sub-sessions also need to keep agent spawning disabled even
when the outer session has `multi_agents_v2` enabled.
## What changed
- Include the collab-backed agent tools when either `multi_agents_v2` or
`collab` is enabled.
- Explicitly disable `multi_agents_v2` for review and guardian review
sub-sessions, matching the existing `spawn_csv` and `collab`
restrictions.
- Add a registry test that enables `multi_agents_v2`, disables `collab`,
and verifies the v2 agent tools are present while legacy `send_input`
and `resume_agent` remain hidden.
## Testing
- Added
`test_build_specs_multi_agent_v2_does_not_require_collab_feature`.
## Why
Reused Guardian review trunks can still have older child-turn events
queued when a later review starts. The review waiter currently accepts
the first terminal event it sees from the shared child session, so a
stale `TurnComplete` can be attributed to the new review. That produces
impossible analytics combinations such as non-null TTFT with sub-10 ms
completion latency and zero token deltas on `trunk_reused` reviews.
## What changed
- Preserve the child turn id returned by the Guardian review
`Op::UserTurn` submission.
- Restrict Guardian review waiting to events correlated with that
submitted child turn.
- Restrict timeout/abort draining to terminal events for the same child
turn.
- Add regression coverage for stale prior-turn completions, stale
prior-turn errors, and interrupt draining in
`codex-rs/core/src/guardian/review_session.rs`.
## Verification
- `cargo test -p codex-core guardian::review_session::tests::`
- `cargo clippy -p codex-core --tests -- -D warnings`
## Summary
- include the live auto-review trunk rollout when `/feedback` uploads
logs
- upload that attachment as
`auto-review-rollout-<parent-thread-id>.jsonl` so it is distinguishable
from the parent rollout
- show the same auto-review attachment name in the TUI consent popup
## Scope
- this only covers the live cached auto-review trunk for the current
parent thread
- it does not add durable historical parent->auto-review lookup
- it does not add persisted rollout support for ephemeral parallel
review forks
## UI
<img width="599" height="185" alt="Screenshot 2026-04-28 at 1 17 18 PM"
src="https://github.com/user-attachments/assets/6a0e79c2-5d21-4702-8a89-f765778bc9e9"
/>
## Validation
- `cargo test -p codex-core
cached_guardian_subagent_exposes_its_rollout_path`
- `cargo test -p codex-feedback`
- `cargo test -p codex-app-server`
- `cargo test -p codex-tui feedback_upload_consent_popup_snapshot`
- `cargo test -p codex-tui
feedback_good_result_consent_popup_includes_connectivity_diagnostics_filename`
## Known unrelated local failures
- `cargo test -p codex-core` currently fails in the pre-existing proxy
env snapshot test
`tools::runtimes::tests::maybe_wrap_shell_lc_with_snapshot_keeps_user_proxy_env_when_proxy_inactive`
- `cargo test -p codex-tui` currently hits pre-existing `status::*`
snapshot drift unrelated to this change
## Follow-Up
- persist parallel auto-review fork sessions so /feedback can include
their rollout history too
- attach each persisted fork as its own clearly named file, for example
auto-review-rollout-<parent-thread-id>-fork <n>.jsonl, instead of
merging multiple Guardian sessions into one attachment
- keep the same live-session-only scope initially; durable historical
parent -> auto-review lookup can remain a separate decision if we later
need feedback from resumed sessions
jifandGitHub
pakrym-oaiandGitHub
Adam Perry @ OpenAIandGitHub
Alex DaleyandGitHub
Owen LinandGitHub
Won ParkandGitHub
kbazziandGitHub
Ahmed IbrahimandGitHub
Michael BolinandGitHub
Dylan HurdandGitHub
viyatb-oaiandGitHub
Matthew ZengandGitHub
Eric TrautandGitHub
Celia ChenandGitHub
rhan-oaiandGitHub
TomandGitHub