## Why
Runtime decisions should not infer permissions from the lossy legacy
sandbox projection once `PermissionProfile` is available. In particular,
`Disabled` and `External` need to remain distinct, and managed profiles
with split filesystem or deny-read rules should not be collapsed before
approval, network, safety, or analytics code makes decisions.
## What Changed
- Changes managed network proxy setup and network approval logic to use
`PermissionProfile` when deciding whether a managed sandbox is active.
- Migrates patch safety, Guardian/user-shell approval paths, Landlock
helper setup, analytics sandbox classification, and selected
turn/session code to profile-backed permissions.
- Validates command-level profile overrides against the constrained
`PermissionProfile` rather than a strict `SandboxPolicy` round trip.
- Preserves configured deny-read restrictions when command profiles are
narrowed.
- Adds coverage for profile-backed trust, network proxy/approval
behavior, patch safety, analytics classification, and command-profile
narrowing.
## Verification
- `cargo test -p codex-core direct_write_roots`
- `cargo test -p codex-core runtime_roots_to_legacy_projection`
- `cargo test -p codex-app-server
requested_permissions_trust_project_uses_permission_profile_intent`
---
[//]: # (BEGIN SAPLING FOOTER)
Stack created with [Sapling](https://sapling-scm.com). Best reviewed
with [ReviewStack](https://reviewstack.dev/openai/codex/pull/19393).
* #19395
* #19394
* __->__ #19393
## Why
Config loading had become split across crates: `codex-config` owned the
config types and merge logic, while `codex-core` still owned the loader
that assembled the layer stack. This change consolidates that
responsibility in `codex-config`, so the crate that defines config
behavior also owns how configs are discovered and loaded.
To make that move possible without reintroducing the old dependency
cycle, the shell-environment policy types and helpers that
`codex-exec-server` needs now live in `codex-protocol` instead of
flowing through `codex-config`.
This also makes the migrated loader tests more deterministic on machines
that already have managed or system Codex config installed by letting
tests override the system config and requirements paths instead of
reading the host's `/etc/codex`.
## What Changed
- moved the config loader implementation from `codex-core` into
`codex-config::loader` and deleted the old `core::config_loader` module
instead of leaving a compatibility shim
- moved shell-environment policy types and helpers into
`codex-protocol`, then updated `codex-exec-server` and other downstream
crates to import them from their new home
- updated downstream callers to use loader/config APIs from
`codex-config`
- added test-only loader overrides for system config and requirements
paths so loader-focused tests do not depend on host-managed config state
- cleaned up now-unused dependency entries and platform-specific cfgs
that were surfaced by post-push CI
## Testing
- `cargo test -p codex-config`
- `cargo test -p codex-core config_loader_tests::`
- `cargo test -p codex-protocol -p codex-exec-server -p
codex-cloud-requirements -p codex-rmcp-client --lib`
- `cargo test --lib -p codex-app-server-client -p codex-exec`
- `cargo test --no-run --lib -p codex-app-server`
- `cargo test -p codex-linux-sandbox --lib`
- `cargo shear`
- `just bazel-lock-check`
## Notes
- I did not chase unrelated full-suite failures outside the migrated
loader surface.
- `cargo test -p codex-core --lib` still hits unrelated proxy-sensitive
failures on this machine, and Windows CI still shows unrelated
long-running/timeouting test noise outside the loader migration itself.
## Why
After #19391, `PermissionProfile` and the split filesystem/network
policies could still be stored in parallel. That creates drift risk: a
profile can preserve deny globs, external enforcement, or split
filesystem entries while a cached projection silently loses those
details. This PR makes the profile the runtime source and derives
compatibility views from it.
## What Changed
- Removes stored filesystem/network sandbox projections from
`Permissions` and `SessionConfiguration`; their accessors now derive
from the canonical `PermissionProfile`.
- Derives legacy `SandboxPolicy` snapshots from profiles only where an
older API still needs that field.
- Updates MCP connection and elicitation state to track
`PermissionProfile` instead of `SandboxPolicy` for auto-approval
decisions.
- Adds semantic filesystem-policy comparison so cwd changes can preserve
richer profiles while still recognizing equivalent legacy projections
independent of entry ordering.
- Updates config/session tests to assert profile-derived projections
instead of parallel stored fields.
## Verification
- `cargo test -p codex-core direct_write_roots`
- `cargo test -p codex-core runtime_roots_to_legacy_projection`
- `cargo test -p codex-app-server
requested_permissions_trust_project_uses_permission_profile_intent`
---
[//]: # (BEGIN SAPLING FOOTER)
Stack created with [Sapling](https://sapling-scm.com). Best reviewed
with [ReviewStack](https://reviewstack.dev/openai/codex/pull/19392).
* #19395
* #19394
* #19393
* __->__ #19392
## Why
This supersedes #19391. During stack repair, GitHub marked #19391 as
merged into a temporary stack branch rather than into `main`, so the
runtime-config change needed a fresh PR.
`PermissionProfile` is now the canonical permissions shape after #19231
because it can distinguish `Managed`, `Disabled`, and `External`
enforcement while also carrying filesystem rules that legacy
`SandboxPolicy` cannot represent cleanly. Core config and session state
still needed to accept profile-backed permissions without forcing every
profile through the strict legacy bridge, which rejected valid runtime
profiles such as direct write roots.
The unrelated CI/test hardening that previously rode along with this PR
has been split into #19683 so this PR stays focused on the permissions
model migration.
## What Changed
- Adds `Permissions.permission_profile` and
`SessionConfiguration.permission_profile` as constrained runtime state,
while keeping `sandbox_policy` as a legacy compatibility projection.
- Introduces profile setters that keep `PermissionProfile`, split
filesystem/network policies, and legacy `SandboxPolicy` projections
synchronized.
- Uses a compatibility projection for requirement checks and legacy
consumers instead of rejecting profiles that cannot round-trip through
`SandboxPolicy` exactly.
- Updates config loading, config overrides, session updates, turn
context plumbing, prompt permission text, sandbox tags, and exec request
construction to carry profile-backed runtime permissions.
- Preserves configured deny-read entries and `glob_scan_max_depth` when
command/session profiles are narrowed.
- Adds `PermissionProfile::read_only()` and
`PermissionProfile::workspace_write()` presets that match legacy
defaults.
## Verification
- `cargo test -p codex-core direct_write_roots`
- `cargo test -p codex-core runtime_roots_to_legacy_projection`
- `cargo test -p codex-app-server
requested_permissions_trust_project_uses_permission_profile_intent`
---
[//]: # (BEGIN SAPLING FOOTER)
Stack created with [Sapling](https://sapling-scm.com). Best reviewed
with [ReviewStack](https://reviewstack.dev/openai/codex/pull/19606).
* #19395
* #19394
* #19393
* #19392
* __->__ #19606
## Why
Windows Bazel runs in the permissions stack exposed that app-server
integration tests were launching normal plugin startup warmups in every
subprocess. Those warmups can call
`https://chatgpt.com/backend-api/plugins/featured` when a test is not
specifically exercising plugin startup, which adds slow background work,
noisy stderr, and dependence on external network state. The relevant
startup/featured-plugin behavior was introduced across #15042 and
#15264.
A few app-server tests also had long optional waits or unbounded cleanup
paths, making failures expensive to diagnose and contributing to slow
Windows shards. One external-agent config test from #18246 used a
GitHub-style marketplace source, which was enough to exercise the
pending remote-import path but also meant the background completion task
could attempt a real clone.
## What Changed
- Adds explicit `AppServerRuntimeOptions` / `PluginStartupTasks`
plumbing and a hidden debug-only
`--disable-plugin-startup-tasks-for-tests` app-server flag, so
integration tests can suppress startup plugin warmups without adding a
production env-var gate.
- Has the app-server test harness pass that hidden flag by default,
while opting plugin-startup coverage back in for tests that
intentionally exercise startup sync and featured-plugin warmup behavior.
- Lowers normal app-server subprocess logging from `info`/`debug` to
`warn` to avoid multi-megabyte stderr output in Bazel logs.
- Prevents the external-agent config test from attempting a real
marketplace clone by using an invalid non-local source while still
exercising the pending-import completion path.
- Bounds optional filesystem/realtime waits and fake WebSocket
test-server shutdown so failures produce targeted timeouts instead of
hanging a shard.
- Fixes the Unix script-resolution test in `rmcp-client` to exercise
PATH resolution directly and include the actual spawn error in failures.
## Verification
- `cargo check -p codex-app-server`
- `cargo clippy -p codex-app-server --tests -- -D warnings`
- `cargo test -p codex-rmcp-client
program_resolver::tests::test_unix_executes_script_without_extension`
- `cargo test -p codex-app-server --test all
external_agent_config_import_sends_completion_notification_after_pending_plugins_finish
-- --nocapture`
- `cargo test -p codex-app-server --test all
plugin_list_uses_warmed_featured_plugin_ids_cache_on_first_request --
--nocapture`
- Windows Local Bazel passed with this test-hardening bundle before it
was extracted from #19606.
---
[//]: # (BEGIN SAPLING FOOTER)
Stack created with [Sapling](https://sapling-scm.com). Best reviewed
with [ReviewStack](https://reviewstack.dev/openai/codex/pull/19683).
* #19395
* #19394
* #19393
* #19392
* #19606
* __->__ #19683
Some providers of Responses API forward a model-defined `end_turn`
boolean indicating explicitly the model's indication of whether it would
like to end the turn or to be inferenced again. In this PR, we update
the sampling loop to use this field correctly if it's set. If the field
is not set by the provider, we fall back to the existing sampling logic.
Fixes multiple scrollback and terminal resize issues: #5538, #5576,
#8352, #12223, #16165, and #15380.
## Why
Codex writes finalized transcript output into terminal scrollback after
wrapping it for the current viewport width. A later terminal resize
could leave that scrollback shaped for the old width, so wider windows
kept narrow output and narrower windows could show stale wrapping
artifacts until enough new output replaced the visible area.
This is also the foundation PR for responsive markdown tables. Table
rendering needs finalized transcript content to be width-sensitive after
insertion, not only while content is first streaming. Markdown table
rendering itself stays in #18576.
## Stack
- PR1: resize backlog reflow and interrupt cleanup
- #18576: markdown table support
## What Changed
- Rebuild source-backed transcript history when the terminal width
changes. `terminal_resize_reflow` is introduced through the experimental
feature system, but is enabled by default for this rollout so we can
validate behavior across real terminals.
- Preserve assistant and plan stream source so finalized streaming
output can participate in resize reflow after consolidation.
- Debounce resize work, but force a final source-backed reflow when a
resize happened during active or unconsolidated streaming output.
- Clear stale pending history lines on resize so old-width wrapped
output is not emitted just before rebuilt scrollback.
- Bound replay work with `[tui.terminal_resize_reflow].max_rows`:
omitted uses terminal-specific defaults, `0` keeps all rendered rows,
and a positive value sets an explicit cap. The cap applies both while
initially replaying a resumed transcript into scrollback and when
rebuilding scrollback after terminal resize.
- Consolidate interrupted assistant streams before cleanup, then clear
pending stream output and active-tail state consistently.
- Move resize reflow and thread event buffering helpers out of `app.rs`
into dedicated TUI modules.
- Add focused coverage for resize reflow, feature-gated behavior,
streaming source preservation, interrupted output cleanup,
unicode-neutral text, terminal-specific row caps, and composer/layout
stability.
## Runtime Bounds
Resize reflow keeps only the most recent rendered rows when a row cap is
active. The default is `auto`, which maps to the detected terminal's
default scrollback size where Codex can identify it: VS Code `1000`,
Windows Terminal `9001`, WezTerm `3500`, and Alacritty `10000`.
Terminals without a dedicated mapping use the conservative fallback of
`1000` rows. Users can override this with `[tui.terminal_resize_reflow]
max_rows = N`, or set `max_rows = 0` to disable row limiting.
## Validation
- `just fmt`
- `git diff --check`
- `cargo test --manifest-path codex-rs/Cargo.toml -p codex-tui reflow`
- `cargo test --manifest-path codex-rs/Cargo.toml -p codex-tui
transcript_reflow`
- `just fix -p codex-tui`
- PR CI in progress on the squashed branch
## Why
`sandbox_permissions = "require_escalated"` is treated as an explicit
request to approve the command and run it outside the
filesystem/platform sandbox. Before this change, shell and unified exec
still registered managed network approval context and could inject
Codex-managed proxy state into the child process, which meant an
approved escalated command could still hit a second network approval
path.
This PR makes that escalation boundary consistent: once a command is
explicitly approved to run outside the sandbox, Codex does not also
route that process through the managed network proxy.
## Security impact
Command/filesystem sandbox approval now implies network approval for
that command. If an untrusted command or script is allowed to run with
`require_escalated`, its network calls are unsandboxed: Codex-managed
network allowlists and denylists are not respected for that process, so
the command can exfiltrate any data it can read.
## What changed
- Skip managed network approval specs for
`SandboxPermissions::RequireEscalated`.
- Pass `network: None` into shell, zsh-fork shell, and unified exec
sandbox preparation for explicitly escalated requests.
- Strip Codex-managed proxy environment variables when
`CODEX_NETWORK_PROXY_ACTIVE` is present, while preserving user proxy env
when the Codex marker is absent.
- Add regression coverage for the prepared exec request so the old
behavior cannot silently reappear.
## Verification
- `cargo test -p codex-core explicit_escalation`
- `cargo clippy -p codex-core --all-targets -- -D warnings`
## Why
Recent `main` CI repeatedly timed out in:
- `codex-core::all suite::approvals::approval_matrix_covers_all_modes`
It failed in runs
[24909500958](https://github.com/openai/codex/actions/runs/24909500958),
[24908076251](https://github.com/openai/codex/actions/runs/24908076251),
[24906197645](https://github.com/openai/codex/actions/runs/24906197645),
[24905823212](https://github.com/openai/codex/actions/runs/24905823212),
[24903439629](https://github.com/openai/codex/actions/runs/24903439629),
[24903336028](https://github.com/openai/codex/actions/runs/24903336028),
and
[24898949647](https://github.com/openai/codex/actions/runs/24898949647).
The failure pattern was a 60s Linux remote timeout. Logs showed many
approval scenarios completing before the single matrix test timed out.
## Root Cause
`approval_matrix_covers_all_modes` packed every approval/sandbox/tool
scenario into one test case. That made the test vulnerable to normal CI
variance: one slow scenario or a slow process startup could push the
whole monolithic case past the 60s per-test timeout. It also hid which
part of the matrix was slow because the runner only reported the one
large matrix test.
## What Changed
- Keep the shared `scenarios()` table as the single source of approval
matrix coverage.
- Use one `#[test_case]` per `ScenarioGroup` to generate five async
Tokio tests: danger/full-access, read-only, workspace-write,
apply-patch, and unified-exec.
- Keep the group runner small and add per-scenario error context so a
failure still reports the specific scenario name.
## Why This Should Be Reliable
Each scenario group now has its own test harness timeout instead of
sharing one timeout window with the full matrix. That removes the long
sequential loop from a single test while keeping the implementation
compact and easy to scan.
The tests still run through the same scenario definitions and runner, so
this preserves coverage. `test-case` already composes with
`#[tokio::test]` in this crate and is already available for test code.
## Verification
- `cargo test -p codex-core --test all approval_matrix_ -- --list`
- `cargo test -p codex-core --test all approval_matrix_`
Adds the core runtime behavior for active goals on top of the model
tools from PR 3.
## Why
A long-running goal should be a core runtime concern, not something
every client has to implement. Core owns the turn lifecycle, tool
completion boundaries, interruptions, resume behavior, and token usage,
so it is the right place to account progress, enforce budgets, and
decide when to continue work.
## What changed
- Centralized goal lifecycle side effects behind
`Session::goal_runtime_apply(GoalRuntimeEvent::...)`.
- Starts goal continuation turns only when the session is idle; pending
user input and mailbox work take priority.
- Accounts token and wall-clock usage at turn, tool, mutation,
interrupt, and resume boundaries; `get_thread_goal` remains read-only.
- Preserves sub-second wall-clock remainder across accounting boundaries
so long-running goals do not drift downward over time.
- Treats token budget exhaustion as a soft stop by marking the goal
`budget_limited` and injecting wrap-up steering instead of aborting the
active turn.
- Suppresses budget steering when `update_goal` marks a goal complete.
- Pauses active goals on interrupt and auto-reactivates paused goals
when a thread resumes outside plan mode.
- Suppresses repeated automatic continuation when a continuation turn
makes no tool calls.
- Added continuation and budget-limit prompt templates.
## Verification
- Added focused core coverage for continuation scheduling, accounting
boundaries, budget-limit steering, completion accounting, interrupt
pause behavior, resume auto-activation, and wall-clock remainder
accounting.
Adds the model-facing goal tools on top of the app-server API from PR 2.
## Why
Once goals are persisted and exposed to clients, the model needs a
small, constrained tool surface for goal workflows. The tool contract
should let the model inspect goals, create them only when explicitly
requested, and mark them complete without giving it broad control over
user/runtime-owned state.
## What changed
- Added `get_goal`, `create_goal`, and `update_goal` tool specs behind
the `goals` feature flag.
- Added core goal tool handlers that validate objectives and token
budgets before mutating persisted state.
- Constrained `create_goal` to create only when no goal exists, with
optional `token_budget` only when a budget is explicitly provided.
- Tightened the `create_goal` instructions so the model does not infer
goals from ordinary task requests.
- Constrained `update_goal` to expose only goal completion; pause,
resume, clear, and budget-limited transitions remain user- or
runtime-controlled.
- Registered the goal tools in the tool registry and kept them out of
review contexts where they should not appear.
## Verification
- Added tool-registry coverage for feature gating and tool availability.
- Added core session tests for create/get/update behavior, duplicate
goal rejection, budget validation, and completion-only updates.
Adds the app-server v2 goal API on top of the persisted goal state from
PR 1.
## Why
Clients need a stable app-server surface for reading and controlling
materialized thread goals before the model tools and TUI can use them.
Goal changes also need to be observable by app-server clients, including
clients that resume an existing thread.
## What changed
- Added v2 `thread/goal/get`, `thread/goal/set`, and `thread/goal/clear`
RPCs for materialized threads.
- Added `thread/goal/updated` and `thread/goal/cleared` notifications so
clients can keep local goal state in sync.
- Added resume/snapshot wiring so reconnecting clients see the current
goal state for a thread.
- Added app-server handlers that reconcile persisted rollout state
before direct goal mutations.
- Updated the app-server README plus generated JSON and TypeScript
schema fixtures for the new API surface.
## Verification
- Added app-server v2 coverage for goal get/set/clear behavior,
notification emission, resume snapshots, and non-local thread-store
interactions.
Adds the persisted goal foundation for the rest of the stack. This PR is
intentionally limited to feature flag and state-layer behavior;
app-server APIs, model tools, runtime continuation, and TUI UX are
layered in later PRs.
## Why
Goal mode needs durable thread-level state before clients or model tools
can safely build on it. The state layer needs to know whether a goal
exists, what objective it tracks, whether it is active, paused,
budget-limited, or complete, and how much time/token usage has already
been accounted.
## What changed
- Added the `goals` feature flag and generated config schema entry.
- Added the `thread_goals` state table and Rust model for persisted
thread goals.
- Added state runtime APIs for creating, replacing, updating, deleting,
and accounting goal usage.
- Added `goal_id`-based stale update protection so an old goal update
cannot overwrite a replacement.
- Kept this PR scoped to persistence and state runtime behavior, with no
app-server, model-facing, continuation, or TUI behavior yet.
## Verification
- Added state runtime coverage for goal creation, replacement, stale
update protection, status transitions, token-budget behavior, and usage
accounting.
## Why
`ReadOnlyAccess` was a transitional legacy shape on `SandboxPolicy`:
`FullAccess` meant the historical read-only/workspace-write modes could
read the full filesystem, while `Restricted` tried to carry partial
readable roots. The partial-read model now belongs in
`FileSystemSandboxPolicy` and `PermissionProfile`, so keeping it on
`SandboxPolicy` makes every legacy projection reintroduce lossy
read-root bookkeeping and creates unnecessary noise in the rest of the
permissions migration.
This PR makes the legacy policy model narrower and explicit:
`SandboxPolicy::ReadOnly` and `SandboxPolicy::WorkspaceWrite` represent
the old full-read sandbox modes only. Split readable roots, deny-read
globs, and platform-default/minimal read behavior stay in the runtime
permissions model.
## What changed
- Removes `ReadOnlyAccess` from
`codex_protocol::protocol::SandboxPolicy`, including the generated
`access` and `readOnlyAccess` API fields.
- Updates legacy policy/profile conversions so restricted filesystem
reads are represented only by `FileSystemSandboxPolicy` /
`PermissionProfile` entries.
- Keeps app-server v2 compatible with legacy `fullAccess` read-access
payloads by accepting and ignoring that no-op shape, while rejecting
legacy `restricted` read-access payloads instead of silently widening
them to full-read legacy policies.
- Carries Windows sandbox platform-default read behavior with an
explicit override flag instead of depending on
`ReadOnlyAccess::Restricted`.
- Refreshes generated app-server schema/types and updates tests/docs for
the simplified legacy policy shape.
## Verification
- `cargo check -p codex-app-server-protocol --tests`
- `cargo check -p codex-windows-sandbox --tests`
- `cargo test -p codex-app-server-protocol sandbox_policy_`
---
[//]: # (BEGIN SAPLING FOOTER)
Stack created with [Sapling](https://sapling-scm.com). Best reviewed
with [ReviewStack](https://reviewstack.dev/openai/codex/pull/19449).
* #19395
* #19394
* #19393
* #19392
* #19391
* __->__ #19449
## Summary
- include the outer tool `call_id` in Codex Apps MCP request metadata
under `_meta._codex_apps.call_id`
- preserve existing Codex Apps metadata like `resource_uri` and
`contains_mcp_source`
- add request metadata coverage for both the existing-metadata and
no-existing-metadata cases
## Why
The paired backend change in
[openai/openai#850796](https://github.com/openai/openai/pull/850796)
updates MCP compliance logging to prefer `_meta._codex_apps.call_id`
instead of the JSON-RPC request id. This client change sends that outer
tool call id so the backend can record the model/tool call identifier
when it is available.
This is wire-compatible with older backends because `_meta._codex_apps`
is already reserved backend-only metadata. Backends that do not read
`call_id` will ignore the extra field.
## Testing
- `cargo test -p codex-core request_meta`
- `just fmt`
- `just fix -p codex-core`
- Add an integration test that guarantees nothing gets written to codex
home dir or sqlite when running a rollout with a non-local ThreadStore
- Add an in-memory "spy" ThreadStore for tests like this
Note I could not find a good way to also ensure there were no filesystem
_reads_ that didn't go through threadstore. I explored a more elaborate
sandboxed-subprocess approach but it isn't platform portable and felt
like it wasn't (yet) worth it.
- Route cold thread/resume and thread/fork source loading through
ThreadStore reads instead of direct rollout path operations
- Keep lookups that explicitly specify a rollout-path using the local
thread store methods but return an invalid-request error for remote
ThreadStore configurations
- Add some additional unit tests for code path coverage
## Why
The profile conversion path still required a `cwd` even when it was only
translating a legacy `SandboxPolicy` into a `PermissionProfile`. That
made profile producers invent an ambient `cwd`, which is exactly the
anchoring we are trying to remove from permission-profile data. A legacy
workspace-write policy can be represented symbolically instead: `:cwd =
write` plus read-only `:project_roots` metadata subpaths.
This PR creates that cwd-free base so the rest of the stack can stop
threading cwd through profile construction. Callers that actually need a
concrete runtime filesystem policy for a specific cwd still have an
explicitly named cwd-bound conversion.
## What Changed
- `PermissionProfile::from_legacy_sandbox_policy` now takes only
`&SandboxPolicy`.
- `FileSystemSandboxPolicy::from_legacy_sandbox_policy` is now the
symbolic, cwd-free projection for profiles.
- The old concrete projection is retained as
`FileSystemSandboxPolicy::from_legacy_sandbox_policy_for_cwd` for
runtime/boundary code that must materialize legacy cwd behavior.
- Workspace-write profiles preserve `CurrentWorkingDirectory` and
`ProjectRoots` special entries instead of materializing cwd into
absolute paths.
## Verification
- `cargo check -p codex-protocol -p codex-core -p
codex-app-server-protocol -p codex-app-server -p codex-exec -p
codex-exec-server -p codex-tui -p codex-sandboxing -p
codex-linux-sandbox -p codex-analytics --tests`
- `just fix -p codex-protocol -p codex-core -p codex-app-server-protocol
-p codex-app-server -p codex-exec -p codex-exec-server -p codex-tui -p
codex-sandboxing -p codex-linux-sandbox -p codex-analytics`
---
[//]: # (BEGIN SAPLING FOOTER)
Stack created with [Sapling](https://sapling-scm.com). Best reviewed
with [ReviewStack](https://reviewstack.dev/openai/codex/pull/19414).
* #19395
* #19394
* #19393
* #19392
* #19391
* __->__ #19414
## Why
Agent interruptions currently always persist a model-visible
interrupted-turn marker before emitting `TurnAborted`. That marker is
useful by default because it gives the next model turn context about a
deliberately interrupted task, but some deployments need to suppress
that history injection entirely while still keeping the client-visible
interruption event.
## What changed
- Add `[agents] interrupt_message = false` to disable the model-visible
interrupted-turn marker.
- Resolve the setting into `Config::agent_interrupt_message_enabled`,
defaulting to `true` so existing behavior is unchanged.
- Apply the setting to both live interrupted turns and interrupted fork
snapshots.
- Keep emitting `TurnAborted` even when the history marker is disabled.
- Regenerate `core/config.schema.json` for the new
`agents.interrupt_message` field.
## Testing
- `cargo test -p codex-core load_config_resolves_agent_interrupt_message
-- --nocapture`
- `cargo test -p codex-core
disabled_interrupted_fork_snapshot_appends_only_interrupt_event --
--nocapture`
- `cargo test -p codex-core
multi_agent_v2_interrupted_marker_uses_developer_input_message --
--nocapture`
- `cargo test -p codex-core
multi_agent_v2_followup_task_can_disable_interrupted_marker --
--nocapture`
- `cargo test -p codex-core
multi_agent_v2_followup_task_interrupts_busy_child_without_losing_message
-- --nocapture`
- `cargo check -p codex-core`
## Summary
- Thread `agent_max_threads` into `ToolsConfig` and
`SpawnAgentToolOptions`.
- Render the configured `max_concurrent_threads_per_session` value in
the MultiAgentV2 `spawn_agent` description.
- Cover the description text in `codex-tools` unit tests and
`codex-core` tool spec tests.
## Validation
- `just fmt`
- `cargo test -p codex-tools`
- `cargo test -p codex-core spawn_agent_description`
- `git diff --check`
## Notes
- `cargo test -p codex-core` was also attempted, but unrelated
environment-sensitive tests failed with the active local environment.
Examples: approvals reviewer defaults observed `AutoReview` instead of
`User`, request-permissions event tests did not emit events, and
proxy-env tests saw `http://127.0.0.1:50604` from the active proxy
environment.
Co-authored-by: Codex <noreply@openai.com>
## Why
`MultiAgentV2` follow-up messages are delivered to agents as
assistant-authored `InterAgentCommunication` envelopes. When
`followup_task` used `interrupt: true`, the interrupted-turn guidance
was still persisted as a contextual user message, so model-visible
history made a system-generated interruption boundary look
user-authored.
This keeps interruption guidance consistent with the rest of the v2
inter-agent message stream while preserving the legacy marker shape for
non-v2 sessions.
## What changed
- Make `interrupted_turn_history_marker` feature-aware.
- Record the interrupted-turn marker as an assistant `OutputText`
message when `Feature::MultiAgentV2` is enabled.
- Keep the existing user contextual fragment for non-v2 sessions.
- Apply the same feature-aware marker to interrupted fork snapshots.
- Add coverage for the live `followup_task` interrupt path and the
helper-level v2 marker shape.
## Testing
- `cargo test -p codex-core
multi_agent_v2_followup_task_interrupts_busy_child_without_losing_message
-- --nocapture`
- `cargo test -p codex-core
multi_agent_v2_interrupted_marker_uses_assistant_output_message --
--nocapture`
- `cargo test -p codex-core interrupted_fork_snapshot -- --nocapture`
Supersedes #18735.
The scheduled rust-release-prepare workflow force-pushed
`bot/update-models-json` back to the generated models.json-only diff,
which dropped the test and snapshot updates needed for CI.
This PR keeps the latest generated `models.json` from #18735 and adds
the corresponding fixture updates:
- preserve model availability NUX in the app-server model cache fixture
- update core/TUI expectations for the new `gpt-5.4` `xhigh` default
reasoning
- refresh affected TUI chatwidget snapshots for the `gpt-5.5`
default/model copy changes
Validation run locally while preparing the fix:
- `just fmt`
- `cargo test -p codex-app-server model_list`
- `cargo test -p codex-core includes_no_effort_in_request`
- `cargo test -p codex-core
includes_default_reasoning_effort_in_request_when_defined_by_model_info`
- `cargo test -p codex-tui --lib chatwidget::tests`
- `cargo insta pending-snapshots`
---------
Co-authored-by: aibrahim-oai <219906144+aibrahim-oai@users.noreply.github.com>
## Summary
Fixes#19275.
Codex runtime rejects inline MCP `bearer_token` config entries and asks
users to configure `bearer_token_env_var` instead, but the generated
config schema still advertised `mcp_servers.<name>.bearer_token` as a
supported field. That made editor/schema validation disagree with
runtime validation.
This keeps `bearer_token` in `RawMcpServerConfig` so Codex can continue
producing the targeted runtime error for recent or existing configs, but
skips the field during schemars generation. The checked-in
`core/config.schema.json` fixture now exposes `bearer_token_env_var`
without exposing unsupported inline `bearer_token`.
## Verification
- Added `config_schema_hides_unsupported_inline_mcp_bearer_token` to
assert the generated schema hides `bearer_token` while preserving
`bearer_token_env_var`.
- Ran `cargo test -p codex-config`.
- Ran `cargo test -p codex-core config_schema`.
we were not respecting turn's `truncation_policy` to clamp output tokens
for `unified_exec` and `write_stdin`.
this meant truncation was only being applied by `ContextManager` before
the output was stored in-memory (so it _was_ being truncated from
model-visible context), but the full output was persisted to rollout on
disk.
now we respect that `truncation_policy` and `ContextManager`-level
truncation remains a backup.
### Tests
added tests, tested locally.
## Summary
`codex.emitImage` accepted arbitrary image MIME types for byte payloads
and data URLs. That allowed a value like `image/rgba` to be wrapped as
an `input_image`, even though it is not a supported encoded image
format, so the invalid image could reach the model-input path and
trigger output sanitization.
This results in a panic in debug builds because the output sanitization
is meant as a final safety net, not a primary means of rejecting invalid
image types. I've hit this case multiple times when executing certain
long-running tasks.
This PR rejects unsupported image MIME types before they are emitted
from `js_repl`.
## Changes
- Validate `codex.emitImage({ bytes, mimeType })` in the JS kernel so
only encoded PNG, JPEG, WebP, or GIF payloads are accepted.
- Apply the same MIME allowlist to direct image data URLs, including the
Rust host-side validation path.
- Clarify the JS REPL instructions so agents know byte payloads must
already be encoded as PNG/JPEG/WebP/GIF.
Fixes#19257.
## Summary
Agent roles declared in config layers can set `config_file` to a
relative path, but deserializing the layer-local `[agents.*]` table
happened without an `AbsolutePathBuf` base path. That caused configs
like `config_file = "agents/my-role.toml"` to fail with `AbsolutePathBuf
deserialized without a base path`.
This updates agent role layer loading to deserialize `[agents.*]` while
the layer config folder is active as the path base, matching the
behavior documented for `AgentRoleToml.config_file`. It also adds
coverage for a user config layer with a relative agent role
`config_file`.
## Why
`PermissionProfile` is becoming the canonical permissions abstraction,
but the old shape only carried optional filesystem and network fields.
It could describe allowed access, but not who is responsible for
enforcing it. That made `DangerFullAccess` and `ExternalSandbox` lossy
when profiles were exported, cached, or round-tripped through app-server
APIs.
The important model change is that active permissions are now a disjoint
union over the enforcement mode. Conceptually:
```rust
pub enum PermissionProfile {
Managed {
file_system: FileSystemSandboxPolicy,
network: NetworkSandboxPolicy,
},
Disabled,
External {
network: NetworkSandboxPolicy,
},
}
```
This distinction matters because `Disabled` means Codex should apply no
outer sandbox at all, while `External` means filesystem isolation is
owned by an outside caller. Those are not equivalent to a broad managed
sandbox. For example, macOS cannot nest Seatbelt inside Seatbelt, so an
inner sandbox may require the outer Codex layer to use no sandbox rather
than a permissive one.
## How Existing Modeling Maps
Legacy `SandboxPolicy` remains a boundary projection, but it now maps
into the higher-fidelity profile model:
- `ReadOnly` and `WorkspaceWrite` map to `PermissionProfile::Managed`
with restricted filesystem entries plus the corresponding network
policy.
- `DangerFullAccess` maps to `PermissionProfile::Disabled`, preserving
the “no outer sandbox” intent instead of treating it as a lax managed
sandbox.
- `ExternalSandbox { network_access }` maps to
`PermissionProfile::External { network }`, preserving external
filesystem enforcement while still carrying the active network policy.
- Split runtime policies that legacy `SandboxPolicy` cannot faithfully
express, such as managed unrestricted filesystem plus restricted
network, stay `Managed` instead of being collapsed into
`ExternalSandbox`.
- Per-command/session/turn grants remain partial overlays via
`AdditionalPermissionProfile`; full `PermissionProfile` is reserved for
complete active runtime permissions.
## What Changed
- Change active `PermissionProfile` into a tagged union: `managed`,
`disabled`, and `external`.
- Keep partial permission grants separate with
`AdditionalPermissionProfile` for command/session/turn overlays.
- Represent managed filesystem permissions as either `restricted`
entries or `unrestricted`; `glob_scan_max_depth` is non-zero when
present.
- Preserve old rollout compatibility by accepting the pre-tagged `{
network, file_system }` profile shape during deserialization.
- Preserve fidelity for important edge cases: `DangerFullAccess`
round-trips as `disabled`, `ExternalSandbox` round-trips as `external`,
and managed unrestricted filesystem + restricted network stays managed
instead of being mistaken for external enforcement.
- Preserve configured deny-read entries and bounded glob scan depth when
full profiles are projected back into runtime policies, including
unrestricted replacements that now become `:root = write` plus deny
entries.
- Regenerate the experimental app-server v2 JSON/TypeScript schema and
update the `command/exec` README example for the tagged
`permissionProfile` shape.
## Compatibility
Legacy `SandboxPolicy` remains available at config/API boundaries as the
compatibility projection. Existing rollout lines with the old
`PermissionProfile` shape continue to load. The app-server
`permissionProfile` field is experimental, so its v2 wire shape is
intentionally updated to match the higher-fidelity model.
## Verification
- `just write-app-server-schema`
- `cargo check --tests`
- `cargo test -p codex-protocol permission_profile`
- `cargo test -p codex-protocol
preserving_deny_entries_keeps_unrestricted_policy_enforceable`
- `cargo test -p codex-app-server-protocol
permission_profile_file_system_permissions`
- `cargo test -p codex-app-server-protocol serialize_client_response`
- `cargo test -p codex-core
session_configured_reports_permission_profile_for_external_sandbox`
- `just fix`
- `just fix -p codex-protocol`
- `just fix -p codex-app-server-protocol`
- `just fix -p codex-core`
- `just fix -p codex-app-server`
## Why
`codex-models-manager` had grown to own provider-specific concerns:
constructing OpenAI-compatible `/models` requests, resolving provider
auth, emitting request telemetry, and deciding how provider catalogs
should be sourced. That made the manager harder to reuse for providers
whose model catalog is not fetched from the OpenAI `/models` endpoint,
such as Amazon Bedrock.
This change moves provider-specific model discovery behind
provider-owned implementations, so the models manager can focus on
refresh policy, cache behavior, picker ordering, and model metadata
merging.
## What Changed
- Introduced a `ModelsManager` trait with separate `OpenAiModelsManager`
and `StaticModelsManager` implementations.
- Added `ModelsEndpointClient` so OpenAI-compatible HTTP fetching lives
outside `codex-models-manager`.
- Moved `/models` request construction, provider auth resolution,
timeout handling, and request telemetry into `codex-model-provider` via
`OpenAiModelsEndpoint`.
- Added provider-owned `models_manager(...)` construction so configured
OpenAI-compatible providers use `OpenAiModelsManager`, while
static/catalog-backed providers can return `StaticModelsManager`.
- Added an Amazon Bedrock static model catalog for the GPT OSS Bedrock
model IDs.
- Updated core/session/thread manager code and tests to depend on
`Arc<dyn ModelsManager>`.
- Moved offline model test helpers into
`codex_models_manager::test_support`.
## Metadata References
The Bedrock catalog metadata is based on the official Amazon Bedrock
OpenAI model documentation:
- [Amazon Bedrock OpenAI
models](https://docs.aws.amazon.com/bedrock/latest/userguide/model-parameters-openai.html)
lists the Bedrock model IDs, text input/output modalities, and `128,000`
token context window for `gpt-oss-20b` and `gpt-oss-120b`.
- [Amazon Bedrock `gpt-oss-120b` model
card](https://docs.aws.amazon.com/bedrock/latest/userguide/model-card-openai-gpt-oss-120b.html)
lists the `bedrock-runtime` model ID `openai.gpt-oss-120b-1:0`, the
`bedrock-mantle` model ID `openai.gpt-oss-120b`, text-only modalities,
and `128K` context window.
- [OpenAI `gpt-oss-120b` model
docs](https://developers.openai.com/api/docs/models/gpt-oss-120b)
document configurable reasoning effort with `low`, `medium`, and `high`,
plus text input/output modality.
The display names, default reasoning effort, and priority ordering are
Codex-local catalog choices.
## Test Plan
- Manually verified app-server model listing with an AWS profile:
```shell
CODEX_HOME="$(mktemp -d)" cargo run -p codex-app-server-test-client -- \
--codex-bin ./target/debug/codex \
-c 'model_provider="amazon-bedrock"' \
-c 'model_providers.amazon-bedrock.aws.profile="codex-bedrock"' \
-c 'model_providers.amazon-bedrock.aws.region="us-west-2"' \
model-list
```
The response returned the Bedrock catalog with `openai.gpt-oss-120b-1:0`
as the default model and `openai.gpt-oss-20b-1:0` as the second listed
model, both text-only and supporting low/medium/high reasoning effort.
## Summary
Adds the debug CLI entry point for reducing recorded rollout traces.
This gives developers a direct way to inspect whether the emitted trace
stream reduces into the expected conversation/runtime model.
## Stack
This is PR 5/5 in the rollout trace stack.
- [#18876](https://github.com/openai/codex/pull/18876): Add rollout
trace crate
- [#18877](https://github.com/openai/codex/pull/18877): Record core
session rollout traces
- [#18878](https://github.com/openai/codex/pull/18878): Trace tool and
code-mode boundaries
- [#18879](https://github.com/openai/codex/pull/18879): Trace sessions
and multi-agent edges
- [#18880](https://github.com/openai/codex/pull/18880): Add debug trace
reduction command
## Review Notes
This PR is intentionally last: it depends on the trace crate, core
recorder, runtime/tool events, and session/agent edge data all existing.
The command should remain a debug/developer tool and avoid adding new
runtime behavior.
The useful review question is whether the CLI exposes the reducer in the
smallest practical way for local inspection without turning the debug
command into a supported user-facing workflow.
## Why
Several approval-focused tests were unintentionally sensitive to
host-level rule files. On machines with broader allowed command
prefixes, commonly allowed commands such as `/bin/date` could bypass the
approval path these tests were meant to exercise, making the fixtures
depend on the developer or CI host configuration.
## What changed
- Pins the approval matrix fixture to the explicit user reviewer so it
does not inherit a host reviewer.
- Changes OTel approval fixtures to request `/usr/bin/touch
codex-otel-approval-test`, avoiding a command that may be pre-approved
by local rules.
- Clears the config layer stack for the permissions-message assertion
that needs to compare only the permissions text under test.
## Verification
- `env -u CODEX_SANDBOX_NETWORK_DISABLED cargo test -p codex-core --test
all approval_matrix_covers_all_modes -- --nocapture`
- `env -u CODEX_SANDBOX_NETWORK_DISABLED cargo test -p codex-core --test
all permissions_messages -- --nocapture`
## Summary
The plugin MCP tool-listing test could hide MCP startup failures by
polling `ListMcpTools` until its own 30s deadline. If the plugin MCP
server startup had already failed or timed out, the session-owned MCP
manager would keep returning an empty tool list, so CI only reported
`discovered tools: []` instead of the startup state that mattered.
This makes the test synchronize on `McpStartupComplete` for the sample
plugin MCP server before asserting listed tools, and gives the
Bazel-launched test server a larger startup window.
## Notes
Confidence is about 80%. The source path strongly supports the RCA: a
failed MCP startup is represented as an empty tool list through
`ListMcpTools`, so the old polling contract could not distinguish "not
ready yet" from "startup already failed." I could not retrieve the CI
execution-log artifact to confirm the exact hidden startup error, but
the observed Ubuntu Bazel failure matches this path: repeated
`ListMcpTools` responses with no tools until the test-local timeout
fired.
I think this is the right solution because it keeps plugin behavior
unchanged and fixes only the test contract. Future startup failures
should now report the `McpStartupComplete` failure/cancellation instead
of timing out on an empty tool snapshot.
This test was introduced in https://github.com/openai/codex/pull/12864.
Addresses #11267
## Summary
`/review` can be interrupted while it is still spawning the review
sub-agent. That spawn path lives in `codex-core` and did not observe the
task cancellation token until after `Codex::spawn` returned, so an
interrupted review could keep building a child session and leave the TUI
in a wedged state.
The TUI exit path also waited indefinitely for app-server
`thread/unsubscribe`, which made Ctrl+C look broken if the app-server
was already stuck. This makes interactive delegate startup
cancellation-aware and bounds the TUI shutdown-first unsubscribe wait
with a short UI escape-hatch timeout.
## Testing
I reproed the hang using the steps in the bug report. Confirmed hang no
longer exists after fix.
## Why
Shell escalation still has adapter code that expects a legacy sandbox
policy, but command approvals should carry the resolved
`PermissionProfile` so callers can reason about the granted permissions
canonically.
## What changed
This introduces profile-shaped resolved escalation permissions while
retaining the derived legacy sandbox policy for the Unix escalation
adapter. It updates approval types, the escalation server protocol, and
tests that inspect escalated command permissions.
## Verification
- `cargo test -p codex-core --test all handle_container_exec_ --
--nocapture`
- `cargo test -p codex-core --test all handle_sandbox_ -- --nocapture`
---
[//]: # (BEGIN SAPLING FOOTER)
Stack created with [Sapling](https://sapling-scm.com). Best reviewed
with [ReviewStack](https://reviewstack.dev/openai/codex/pull/18287).
* #18288
* __->__ #18287
## Summary
Extends rollout tracing across tool dispatch and code-mode runtime
boundaries. This records canonical tool-call lifecycle events and links
code-mode execution/wait operations back to the model-visible calls that
caused them.
## Stack
This is PR 3/5 in the rollout trace stack.
- [#18876](https://github.com/openai/codex/pull/18876): Add rollout
trace crate
- [#18877](https://github.com/openai/codex/pull/18877): Record core
session rollout traces
- [#18878](https://github.com/openai/codex/pull/18878): Trace tool and
code-mode boundaries
- [#18879](https://github.com/openai/codex/pull/18879): Trace sessions
and multi-agent edges
- [#18880](https://github.com/openai/codex/pull/18880): Add debug trace
reduction command
## Review Notes
This PR is about attribution. Reviewers should focus on whether direct
tool calls, code-mode-originated tool calls, waits, outputs, and
cancellation boundaries are recorded with enough source information for
deterministic reduction without coupling the reducer to live runtime
internals.
The stack remains valid after this layer: tool and code-mode traces
reduce through the existing crate model, while the broader session and
multi-agent relationships are added in the next PR.
## Why
MCP tool calls can receive a serialized `SandboxState` when a server
declares the sandbox-state capability. That state is one of the places
MCP runtimes learn what permissions Codex is operating under. As the
permissions migration makes `PermissionProfile` the canonical
representation, MCP consumers should be able to read that profile
directly instead of reconstructing permissions from the legacy
`SandboxPolicy`.
## What changed
- Adds optional `permissionProfile` to `codex_mcp::SandboxState`, while
keeping `sandboxPolicy` for existing MCP consumers.
- Populates `permissionProfile` from the current `TurnContext` when
serializing sandbox state for MCP tool calls.
## Verification
- Current GitHub Actions for this PR are passing.
---
[//]: # (BEGIN SAPLING FOOTER)
Stack created with [Sapling](https://sapling-scm.com). Best reviewed
with [ReviewStack](https://reviewstack.dev/openai/codex/pull/18286).
* #18288
* #18287
* __->__ #18286
## Why
Per-turn permission overrides should use the same canonical profile
abstraction as session configuration. That lets TUI submissions preserve
exact configured permissions without round-tripping through legacy
sandbox fields.
## What changed
This adds `permission_profile` to user-turn operations, threads it
through TUI/app-server submission paths, fills the new field in existing
test fixtures, and adds coverage that composer submission includes the
configured profile.
## Verification
- `cargo test -p codex-tui permissions -- --nocapture`
- `cargo test -p codex-core --test all permissions_messages --
--nocapture`
---
[//]: # (BEGIN SAPLING FOOTER)
Stack created with [Sapling](https://sapling-scm.com). Best reviewed
with [ReviewStack](https://reviewstack.dev/openai/codex/pull/18285).
* #18288
* #18287
* #18286
* __->__ #18285
## Why
App-server needs a way to fetch thread-scoped config from the remote
thread config service when the user config opts into that behavior. This
mirrors the existing experimental remote thread store endpoint while
keeping local/noop behavior as the default.
Startup paths also need to avoid silently dropping the remote config
endpoint after the first config load. The stdio app-server path
discovers the endpoint from the initial config and installs the real
thread config loader for later config builds, while in-process clients
used by TUI/exec now select the same remote loader directly from their
provided config.
## What changed
- Added `experimental_thread_config_endpoint` to `ConfigToml`, `Config`,
and `core/config.schema.json`.
- Added config parsing coverage for the new setting.
- Updated app-server startup to select `RemoteThreadConfigLoader` from
the initially loaded config, falling back to `NoopThreadConfigLoader`
when unset.
- Let `ConfigManager` replace its thread config loader after startup
discovery so later config loads use the selected loader.
- Updated in-process app-server client startup to pass
`RemoteThreadConfigLoader` when its config has
`experimental_thread_config_endpoint` set.
## Verification
- Added `experimental_thread_config_endpoint_loads_from_config_toml`.
- Added
`runtime_start_args_use_remote_thread_config_loader_when_configured`.
- Ran `cargo check -p codex-app-server --lib`.
- Ran `cargo test -p codex-app-server-client`.
## Why
PR #18797 currently surfaces fallback rationale text that names Guardian
directly.
## What changed
- Updated the bare allow and bare deny fallback rationales in
`codex-rs/core/src/guardian/prompt.rs` from Guardian to Auto-review.
- Updated the existing bare allow parser test and added explicit bare
deny parser coverage.
## Verification
- `cargo test -p codex-core parse_guardian_assessment_treats_bare`
Begin migrating the thread write codepaths to ThreadStore.
This starts using ThreadStore inside of core session code, not only in
the app server code.
Rework the interfaces around thread recording/persistence. We're left
with the following:
* `ThreadManager`: owns the process-level registry of loaded threads and
handles cross-thread orchestration: start, resume, fork, lookup, remove,
and route ops to running CodexThreads.
* `CodexThread`: represents one loaded/running thread from the outside.
It is the handle app-server and callers use to submit ops, inspect
session metadata, and shut the thread down.
* `LiveThread`: session-owned persistence lifecycle handle for one
active thread. Core session code uses it to append rollout items,
materialize lazy persistence, flush, shutdown, discard init-failed
writers, and load that thread’s persisted history.
* `ThreadStore`: storage backend abstraction. It answers “how are
threads persisted, read, listed, updated, archived?” Local and remote
implementations live behind this trait.
* `LocalThreadStore`: local ThreadStore implementation. It owns the
file/sqlite-specific details and keeps RolloutRecorder as a local
implementation detail.
This is a few too many Thread abstractions for my liking, but they do
all represent different concepts / needs / layers.
Migration note: in places where the core code explicitly requires a
path, rather than a thread ID, throw an error if we're running with a
remote store.
Cover the new local live-writer lifecycle with focused tests and
preserve app-server thread-start behavior, including ephemeral pathless
sessions.
## Why
MultiAgentV2 children should not receive an extra model-visible
developer fragment just because they were spawned. The parent/configured
developer instructions should carry through normally, but the dedicated
`<spawned_agent_context>` block is no longer desired.
## What changed
- Removed the `SpawnAgentInstructions` context fragment and its
`<spawned_agent_context>` wrapper.
- Stopped appending spawned-agent instructions in
`codex-rs/core/src/tools/handlers/multi_agents_v2/spawn.rs`.
- Updated subagent notification coverage to assert inherited parent
developer instructions without expecting the spawned-agent wrapper.
## Verification
- `cargo test -p codex-core --test all
spawned_multi_agent_v2_child_inherits_parent_developer_context --
--nocapture`
- `cargo test -p codex-core --test all
skills_toggle_skips_instructions_for_parent_and_spawned_child --
--nocapture`
- `cargo test -p codex-core --test all subagent_notifications --
--nocapture`
