## Stack
1. [#26547](https://github.com/openai/codex/pull/26547) - [1 of 2] Align
goal extension with core behavior
2. [#26548](https://github.com/openai/codex/pull/26548) - [2 of 2] Move
goal runtime to extension
## Why
This PR completes the switch of the goal behavior to the
extension-backed runtime and removes the old core goal implementation.
## What Changed
- Installs the goal extension for app-server `ThreadManager` sessions.
- Routes app-server thread goal `get`, `set`, and `clear` through
`GoalService`.
- Uses thread-idle lifecycle emission after goal resume and snapshot
ordering so the extension can decide whether to continue the goal.
- Forwards extension goal updates through a FIFO async app-server
notification path so backpressure does not drop them or reorder updates.
- Keeps review turns from enabling goal runtime behavior.
- Plans extension tools before dynamic tools so built-in goal tool names
keep their old precedence when goals are enabled.
- Removes the old core goal runtime, core goal tool handlers, and core
goal tool specs.
- Updates tests that were coupled to the core-owned goal runtime while
leaving the legacy `<goal_context>` compatibility path in core for old
threads.
- Removes the stale cargo-shear ignore now that `codex-goal-extension`
is used by the workspace.
- Keeps realtime event matching exhaustive after removing the old
goal-specific realtime text path.
## Validation
- Ran manual `/goal` runs in TUI. Validated time accounting matched
wall-clock time and goal lifecycle state transitions.
Stacked on #26532.
## Why
#26532 moves cwd normalization to the app-server/core boundary.
`runtimeWorkspaceRoots` still accepted raw paths in v2 requests and in
`ConfigOverrides`, which left core responsible for interpreting those
roots later. This makes runtime workspace roots follow the same
absolute-path boundary as cwd.
## What
- Change v2 `runtimeWorkspaceRoots` request fields for `thread/start`,
`thread/resume`, `thread/fork`, and `turn/start` to `AbsolutePathBuf`.
- Deduplicate already-absolute runtime roots in app-server handlers and
pass them through `ConfigOverrides.workspace_roots` as
`AbsolutePathBuf`.
- Update TUI and exec client request builders to pass absolute runtime
roots directly.
- Update app-server docs, schema fixtures, and focused tests for
absolute runtime roots.
## Testing
- `just test -p codex-app-server-protocol`
- `just test -p codex-app-server runtime_workspace_roots`
- `just test -p codex-core
session_permission_profile_rebinds_runtime_workspace_roots`
- `just test -p codex-tui app_server_session`
- `just test -p codex-exec`
## Summary
Add flat profiling fields to `codex_turn_event` so analytics can explain
where turn wall-clock time is spent without changing tool execution
behavior.
The profile reports:
- time before the first sampling request
- sampling time across all attempts and follow-ups
- overhead between sampling requests
- time blocked in the post-sampling tool drain
- time after the final sampling request
- sampling request and retry counts
## Implementation
- Extend the existing turn timing state with constant-memory phase
accounting and one RAII phase guard.
- Observe sampling and the existing post-sampling drain only at turn
orchestration boundaries.
- Keep tool runtime, tool futures, response item handling, and turn
lifecycle values unchanged.
- Add the profiling fields directly to the existing analytics turn event
without changing app-server protocol or rollout persistence.
- Use the existing turn `status` to distinguish completed, failed, and
interrupted profiles.
Exact sampling/tool overlap is intentionally omitted because measuring
tool completion accurately would require hooks in the tool execution
path.
## Validation
- Add app-server end-to-end coverage for a single-sampling turn with no
blocking tool work.
- Add app-server end-to-end coverage for `request_user_input` blocking
followed by a second sampling request.
- CI is running on the PR; tests were not executed locally per
repository guidance.
## Why
Windows managed filesystem permissions can now be backed by a real
Windows sandbox. `exec-policy` was still treating the managed read-only
policy shape as if there were never a sandbox backend, so benign
unmatched commands such as PowerShell directory listings could be
rejected with `blocked by policy` even when `windows.sandbox` was
enabled.
The inverse case still needs to stay conservative: when the Windows
sandbox backend is disabled, managed filesystem restrictions are only
configuration intent, not an enforced filesystem boundary. That applies
to writable-root restricted profiles too, not just read-only profiles.
## What Changed
- Thread the effective `WindowsSandboxLevel` into exec-policy approval
decisions for shell, unified exec, and intercepted shell exec paths.
- Treat managed restricted filesystem profiles as lacking sandbox
protection only on Windows when `WindowsSandboxLevel::Disabled`.
- Exclude full-disk-write profiles from that no-backend path because
they do not rely on filesystem sandbox enforcement.
- Remove the cwd-sensitive read-only heuristic and the now-stale cwd
plumbing from exec-policy approval contexts.
- Add Windows coverage for both enabled-sandbox and disabled-backend
behavior, including a writable-root managed profile.
## Validation
- Added/updated `exec_policy` coverage for managed filesystem
restrictions, full-disk-write exclusion, enabled Windows sandbox
behavior, and disabled-backend read-only/writable-root behavior.
- `just test -p codex-core exec_policy` — 100 passed, 10 leaky
- Empirical local `codex exec` probe with `--sandbox read-only -c
'windows.sandbox="unelevated"'`: PowerShell directory listing completed
successfully.
- Disabled-backend control with Windows sandbox cleared: the same
command was rejected with `blocked by policy`.
## Why
Turn diffs were tracked as one flat set of absolute paths. In
multi-environment turns, local and remote environments can report the
same path while representing different filesystems, so a single path key
can collapse distinct changes or attribute them to the wrong
environment.
The environment name is **NOT** included in the generated unified diff.
This can come later.
## 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
This is the first small step toward making multi-agent v2 agents durable
logical agents whose `ThreadManager` residency is only an implementation
detail.
This PR adds a narrow v2 reload-on-delivery hook:
- If a known v2 agent target is already loaded, delivery is unchanged.
- If the target is still registered but missing from `ThreadManager`,
delivery reloads that exact v2 thread from durable rollout history
before submitting the message.
- If the target is unknown, closed, missing from storage, or not a v2
thread, delivery still fails as not found.
The reload is wired only into existing-agent delivery paths: v2
`send_message` / `followup_task`, and legacy `send_input` when its
target is a known v2 agent.
## Stack
1. **Reload on delivery**: load known unloaded v2 agents before
`followup_task`, `send_message`, or `send_input` delivery. This PR.
2. **Residency LRU**: unload idle resident v2 agents from
`ThreadManager` without making them closed or unreachable.
3. **Execution concurrency**: count active non-root turns, not logical
agents or resident idle threads.
4. **Close semantics**: make v2 close interrupt-only and leave durable
agent identity intact.
5. **Resume cleanup**: remove user-facing v2 resume semantics;
addressing an unloaded durable agent reloads it implicitly.
## Validation
- Ran `just fmt`.
- Left broader tests and clippy to CI.
## Summary
Mechanically splits `AgentControl` into focused modules so later agent
runtime changes are easier to review. The shared lookup, messaging, and
completion logic remains in `control.rs`, while spawn-specific code and
V1 legacy close/resume behavior move into dedicated files.
## Changes
- Extract spawn-agent code into `agent/control/spawn.rs`.
- Extract V1-only legacy close/resume behavior into
`agent/control/legacy.rs`.
- Keep shared control-plane behavior in `agent/control.rs`.
- Preserve existing behavior; this PR is intended to be mechanical.
## Stack
1. This PR - Mechanical `AgentControl` split: extracts spawn and V1
legacy code without behavior changes.
2. #26614 - Execution slot accounting: separates logical agents from
active execution slots.
3. #26611 - Residency and reload runtime: adds resident-agent LRU,
eviction/reload, durable lookup, and V2 delivery through reload.
4. #26612 - V2 tool semantics: narrows `close_agent` to interrupt-only
and updates V2 tool coverage.
## Summary
- keep the legacy v1 `spawn_agent` role and model selectors visible
- add regression coverage for the default v1 tool plan
## Why
`hide_spawn_agent_metadata` is a multi-agent v2 setting, but the v1
planning branch also consumed it. After the default changed to `true`,
v1 stopped advertising `agent_type`, `model`, `reasoning_effort`, and
`service_tier`, preventing configured agents from being selected.
This keeps the hidden-metadata default for v2 while opting v1 out of
that behavior.
Fixes#26363.
## Validation
Not run locally, per request; CI will validate the change.
## Why
First-party backends can supply turn-scoped moderation metadata that
app-server clients need for client-side presentation. Exposing this as
an experimental typed notification lets opted-in clients consume it
without interpreting raw Responses API events.
## What changed
- forward `response.metadata.openai_chatgpt_moderation_metadata` from
Responses API SSE and WebSocket streams as turn-scoped moderation
metadata
- emit the experimental app-server v2 `turn/moderationMetadata`
notification with `{ threadId, turnId, metadata }`
- add app-server integration coverage for the typed moderation metadata
notification
## Testing
- `just test -p codex-core
build_ws_client_metadata_includes_window_lineage_and_turn_metadata`
- `just test -p codex-core` (fails locally: 46 failures and 1 timeout,
primarily missing `test_stdio_server` and shell snapshot timeouts)
- `just test -p codex-app-server-protocol`
- `just test -p codex-app-server
turn_moderation_metadata_emits_typed_notification_v2`
- `just test -p codex-app-server` (fails locally: 792 passed, 10 failed,
and 5 timed out; failures are in existing environment-sensitive tests,
primarily because nested macOS `sandbox-exec` is not permitted)
- `just write-app-server-schema --experimental --schema-root
/tmp/codex-app-server-schema-experimental`
## Why
Multi-agent v2 currently routes agent instructions through normal tool
arguments and inter-agent context. That means the parent model can emit
plaintext task text, Codex can persist it in history/rollouts, and the
recipient can receive it as ordinary assistant-message JSON.
This changes the v2 path so agent instructions stay encrypted between
model calls: Responses encrypts the `message` argument returned by the
model, Codex forwards only that ciphertext, and Responses decrypts it
internally for the recipient model.
## What changed
- Mark the v2 `message` parameter as encrypted for `spawn_agent`,
`send_message`, and `followup_task`.
- Treat multi-agent v2 tool `message` values as ciphertext
unconditionally.
- Store v2 inter-agent task text in
`InterAgentCommunication.encrypted_content` with empty plaintext
`content`.
- Convert encrypted inter-agent communications into the Responses
`agent_message` input item before sending the child request.
- Preserve `agent_message` items across history, rollout, compaction,
telemetry, and app-server schema paths.
- Leave multi-agent v1 unchanged.
## Message shape
The model still calls the v2 tools with a `message` argument, but that
value is now ciphertext:
```json
{
"name": "spawn_agent",
"arguments": {
"task_name": "worker",
"message": "<ciphertext>"
}
}
```
Codex stores the task as encrypted inter-agent communication:
```json
{
"author": "/root",
"recipient": "/root/worker",
"content": "",
"encrypted_content": "<ciphertext>",
"trigger_turn": true
}
```
When Codex builds the recipient request, it forwards the ciphertext
using the new Responses input item:
```json
{
"type": "agent_message",
"author": "/root",
"recipient": "/root/worker",
"content": [
{
"type": "encrypted_content",
"encrypted_content": "<ciphertext>"
}
]
}
```
Responses decrypts that item internally for the recipient model.
## Context impact
- Parent context no longer carries plaintext v2 agent task instructions
from these tool arguments.
- Codex rollout/history stores ciphertext for v2 agent instructions.
- Recipient requests receive an `agent_message` item instead of
assistant commentary JSON for encrypted task delivery.
- Plaintext completion/status notifications are still plaintext because
they are Codex-generated status messages, not encrypted model tool
arguments.
## Validation
- `just test -p codex-tools`
- `just test -p codex-protocol`
- `just test -p codex-rollout`
- `just test -p codex-rollout-trace`
- `just test -p codex-otel`
- `just write-app-server-schema`
## Why
Shell detection needs to be available through the `Environment`
abstraction so callers can ask the selected local or remote environment
for shell metadata without adding a separate HTTP endpoint or parallel
info-source path. This keeps shell metadata shaped like the existing
environment-owned filesystem capability and lets remote environments
answer through exec-server JSON-RPC.
## What changed
- Added `environment/info` to the exec-server protocol/client/server and
exposed `Environment::info()`.
- Added local and remote environment info providers on `Environment`,
following the existing capability-provider pattern used for filesystem
access.
- Moved the shared shell detection logic into `codex-shell-command` and
kept core shell APIs as wrappers around that implementation.
- Returned shell metadata as `EnvironmentInfo { shell: ShellInfo }`
using the existing shell detection path.
- Added a remote environment test that calls `Environment::info()`
through an exec-server-backed environment.
## Validation
- `git diff --check`
- `just test -p codex-shell-command`
- `just test -p codex-core -E 'test(/shell::tests::/)'`\n- `just test -p
codex-exec-server environment`
## Why
`PermissionProfile` already owns the runtime filesystem sandbox policy
through `file_system_sandbox_policy()`. Keeping a separate
`FileSystemSandboxPolicy` on exec-policy fallback contexts made it
possible for callers and tests to construct split states that the
production permission model should not rely on.
## What changed
- Removed `file_system_sandbox_policy` from `UnmatchedCommandContext`,
`ExecApprovalRequest`, and the intercepted Unix exec-policy context.
- Derived filesystem sandbox policy inside unmatched-command decision
logic from `PermissionProfile::file_system_sandbox_policy()`.
- Simplified shell/unified-exec callers and tests that were only
plumbing the duplicate policy through.
## Testing
Local tests not run per request; relying on remote CI.
## Summary
- add a defaulted `ModelInfo.use_responses_lite` catalog field
- support serializing `reasoning.context` while preserving the existing
effort and summary path
- has not been turned on for any models yet
I've added an override to parallel tools if responses_lite is on. I've
also forced persistent reasoning when using responses_lite. It would be
ideal if we could centralize all the responses_lite plumbing, but I
think this is best for now to keep the plumbing & diffs small.
## Testing
- `cargo test -p codex-protocol
model_info_defaults_availability_nux_to_none_when_omitted`
- `RUST_MIN_STACK=8388608 cargo test -p codex-core
responses_lite_sets_all_turns_context_and_disables_parallel_tool_calls`
- `RUST_MIN_STACK=8388608 cargo test -p codex-core
configured_reasoning_summary_is_sent`
- `cargo check -p codex-core --tests`
- `RUST_MIN_STACK=8388608 cargo clippy -p codex-core --tests` (passes
with pre-existing warnings in `codex-code-mode` and
`codex-core-plugins`)
## Summary
Adds a dedicated `codex.sandbox_outcome` telemetry event so we can query
sandbox edge outcomes without threading sandbox metadata through
tool-result output types.
This is meant to make sandbox failures and approved escalation retries
visible in OTEL while keeping the existing `codex.tool_result` event
shape focused on tool completion data.
## What changed
- Adds `SessionTelemetry::sandbox_outcome(...)`, which emits
`codex.sandbox_outcome` as both a log and trace event.
- Records the tool name, call id, sandbox outcome, initial attempt
duration, and escalated attempt duration when a retry runs.
- Emits `denied` when the sandbox blocks execution and no retry is run.
- Emits `timed_out` and `signal` when those sandbox errors surface from
tool execution.
- Emits `escalated` when the initial sandboxed attempt fails and the
approved unsandboxed retry succeeds.
- Adds OTEL coverage for the new event payload, including timing fields.
## Validation
- `RUST_MIN_STACK=8388608 just test -p codex-core
sandbox_outcome_event_records_outcome
handle_sandbox_error_user_approves_retry_records_tool_decision`
- `just test -p codex-otel
otel_export_routing_policy_routes_tool_result_log_and_trace_events
runtime_metrics_summary_collects_tool_api_and_streaming_metrics`
- `just fix -p codex-core`
- `just fix -p codex-otel`
We cross build when using bazel for windows. This causes a couple
hiccups in that v8 does a mksnapshot step that is expecting to snapshot
on the host arch which wasn't matching when we were doing the
crossbuild. This was causing segfault failiures when starting up
codemode from a cross built artifact.
This changes things such that we cross build the library and then run
and link a snapshot on the host machine/arch which is windows. This
gives us a functional snapshot and library that can start code-mode on
windows.
This fixes the build and then fixes two test regressions we had.
## Intent
Follow up on #26205 by avoiding unnecessary filesystem canonicalization
during `AGENTS.md` discovery. The configured working directory is
already absolute, and canonicalization incorrectly switches symlinked
workspaces from their logical parent hierarchy to the target's
hierarchy.
## User-facing behavior
For a symlinked working directory such as:
```text
test-root/
|-- logical-repo/
| |-- AGENTS.md ("logical parent doc")
| `-- workspace ------------> physical-repo/workspace/
`-- physical-repo/
|-- AGENTS.md ("physical parent doc")
`-- workspace/
`-- AGENTS.md ("workspace doc")
```
Before this change, Codex canonicalized `logical-repo/workspace` to
`physical-repo/workspace` before discovery. It therefore loaded
`physical-repo/AGENTS.md` and `physical-repo/workspace/AGENTS.md`,
ignoring the instructions from the repository through which the user
entered the workspace.
After this change, ancestor discovery walks the configured logical path,
so Codex loads `logical-repo/AGENTS.md`. Opening
`logical-repo/workspace/AGENTS.md` still follows the symlink through the
host filesystem, so the workspace document is also loaded.
`physical-repo/AGENTS.md` is not loaded.
## Implementation
Use the logical absolute working directory when discovering project
instructions and reporting instruction sources. Filesystem reads still
follow the working-directory symlink, so an `AGENTS.md` in the target
workspace continues to load while ancestor discovery uses the symlink's
parents.
## Validation
Added integration coverage proving that discovery loads the logical
parent's instructions and the target workspace's instructions, but not
the target parent's instructions.
## 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
The Responses websocket client no longer needs to send a follow-up
`response.processed` request after a turn response has already been
recorded. Keeping that extra acknowledgement path adds feature-gated
control flow and a second websocket request shape that no longer carries
useful behavior.
## What Changed
- Removed the `response.processed` websocket request type and sender.
- Removed the `responses_websocket_response_processed` feature flag and
schema entry.
- Removed turn and remote-compaction plumbing that only tracked response
IDs to send the acknowledgement.
- Removed tests that existed solely to cover the deleted feature path.
## Validation
- `just fix -p codex-core -p codex-api -p codex-features`
## 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
Research and training setups need to control which tool namespaces
appear inside code mode's nested `tools` surface without disabling those
tools entirely. This makes it possible to train against a deliberately
reduced nested-tool setup while preserving the normal direct and
deferred tool paths.
## What
- Extend `features.code_mode` to accept structured configuration while
preserving the existing boolean syntax.
- Add an exact `excluded_tool_namespaces` list under
`[features.code_mode]`:
```toml
[features.code_mode]
enabled = true
excluded_tool_namespaces = ["mcp__codex_apps", "multi_agent_v1"]
```
- Filter matching canonical `ToolName` namespaces when constructing code
mode's nested router and code-mode-specific direct tool descriptions.
- Keep excluded tools registered, directly exposed in mixed code mode,
and discoverable through top-level `tool_search` when otherwise
eligible.
- Derive deferred nested-tool guidance after namespace filtering so the
`exec` description does not advertise excluded-only deferred tools.
- Preserve the boolean/table representation when materializing config
locks and update the generated config schema.
## Testing
- `just test -p codex-features`
- `just test -p codex-config`
- `just test -p codex-core load_config_resolves_code_mode_config`
- `just test -p codex-core
lock_contains_prompts_and_materializes_features`
- `just test -p codex-core
excluded_deferred_namespaces_do_not_enable_nested_tool_guidance`
- `just test -p codex-core
code_mode_excludes_configured_nested_tool_namespaces`
- `cargo check -p codex-thread-manager-sample`
## Why
- Thread initialization analytics do not identify the source thread for
forked threads.
- The session viewer needs this lineage to construct thread trees.
- Depends on openai/openai#987854. Do not release this change before
that backend schema change is deployed.
## What Changed
- Adds optional `forked_from_thread_id` to `codex_thread_initialized`.
- Populates it from the existing thread fork lineage for app-server and
in-process subagent initialization paths.
- Keeps it null for non-forked threads.
## Verification
- `just fmt`
- `just test -p codex-analytics`
- `just test -p codex-app-server
thread_fork_tracks_thread_initialized_analytics`
## Why
Standalone image generation returns image bytes to the model, but the
model also needs the host artifact path to reference the generated file
in follow-up work.
## What changed
- Append the default saved-image path hint alongside the generated image
tool output.
- Reuse the existing core image-generation hint text.
- Pass the thread ID and Codex home directory needed to compute the
artifact path.
- Add app-server and extension coverage for the model-visible hint.
## Validation
- `just fmt`
- `just bazel-lock-check`
- `just test -p codex-app-server
standalone_image_generation_returns_saved_path_hint_to_model`
## Why
The skills extension needs to become the path that exposes local host
skills without losing the behavior already owned by core skill loading.
Host skill discovery is not just `$CODEX_HOME/skills`: it also includes
config layers, bundled-skill settings, plugin roots, runtime extra
roots, and the filesystem for the selected primary environment.
Rather than making the extension reload host skills and risk drifting
from that authoritative load, this PR bridges the already-loaded
per-turn skills outcome into the extension. That lets the extension
advertise host skills and inject explicit `$skill` prompts while
preserving the same roots, disabled/hidden state, rendered paths, and
environment-backed file reads that the legacy path uses.
## What Changed
- Adds `HostLoadedSkills` in `core-skills` to wrap the turn's
`SkillLoadOutcome` and read `SKILL.md` through the filesystem that
loaded that skill.
- Stores `HostLoadedSkills` in turn extension data for normal turns and
review turns, so the skills extension can consume the loaded host
catalog without reloading it.
- Adds `HostSkillProvider` under `ext/skills/src/provider/host.rs`,
mapping host-loaded skill metadata into the skills-extension
catalog/read contract.
- Registers the host provider by default from
`codex_skills_extension::install()`.
- Preserves host skill metadata such as dependencies, disabled state,
hidden-from-prompt policy, and slash-normalized display paths.
- Passes host-loaded skills through `SkillListQuery` and
`SkillReadRequest` so explicit skill invocation reads only resources
from the loaded host catalog.
- Adds integration coverage for a real legacy
`$CODEX_HOME/skills/.../SKILL.md` skill being listed and injected
through the installed extension.
## Testing
- Added `installed_extension_loads_host_skills_from_legacy_roots` in
`ext/skills/tests/skills_extension.rs`.
- `just test -p codex-skills-extension`
## Why
Goal idle continuation is extension-triggered model-visible work, so it
should follow one core-owned rule for when automatic work may start. In
particular, it should not jump ahead of queued user/client work, start
while another task is active, or inject a continuation turn while the
thread is in Plan mode.
Keeping this policy in `try_start_turn_if_idle` avoids passing
`collaboration_mode` or review-specific state through
`ThreadLifecycleContributor::on_thread_idle`. Active `/review` is
covered by the same active-task gate because Review turns are not
steerable.
## What Changed
- Teach `Session::try_start_turn_if_idle` to reject automatic idle turns
in Plan mode, both before reserving an idle turn and after building the
turn context.
- Document `CodexThread::try_start_turn_if_idle` as the extension-facing
gate for automatic idle work, including Plan-mode and active Review-task
behavior.
- Add focused coverage for Plan-mode rejection and active Review-task
rejection without queuing synthetic input.
## Testing
- `just test -p codex-core try_start_turn_if_idle`
## Why
Compaction analytics need token counts that better represent the request
being compacted. The existing session snapshot can diverge from the
actual remote compaction request after output rewriting, and remote v2
can use server-side Responses usage when available.
## What changed
- Add an optional `active_context_tokens_before` override to
`CompactionAnalyticsAttempt::track(...)` for remote compaction when it
has a better before-token value than the begin-time session snapshot.
The local `/compact` path passes no override.
- For remote v1 `responses_compact`, subtract the estimated token delta
from pre-compaction output rewriting from the session snapshot, capped
by locally-added tokens since the last successful API response.
- For remote v2 `responses_compaction_v2`, use the same bounded
output-rewrite fallback as remote v1, then overwrite
`active_context_tokens_before` with server `token_usage.input_tokens`
from the `response.completed` event when present.
- Keep the existing v2 compaction-output validation while carrying the
completed response token usage through `collect_compaction_output`.
## Verification
- `just fmt`
- `just test -p codex-core
collect_compaction_output_accepts_additional_output_items`
- `git diff --check`
## Why
Codex package installs include helper binaries in `codex-path`, such as
the bundled `rg`. Package-layout launches should add that directory
before user commands run, but standalone launches were missing it while
npm launches only worked because `codex.js` had its own legacy `PATH`
rewrite. That made npm and standalone package behavior diverge.
Shell snapshot restoration can also reset `PATH` after runtime setup.
Any package-owned `PATH` prepend has to be recorded as an explicit
runtime override so shells, unified exec, and user-shell commands keep
access to `codex-path` after a snapshot is sourced.
## Repro
Before this change, a curl-installed package could contain `rg` under
`codex-path` but still fail to put it on `PATH`:
```shell
mkdir /tmp/test-codex-curl
curl -fsSL https://chatgpt.com/codex/install.sh \
| CODEX_HOME=/tmp/test-codex-curl CODEX_NON_INTERACTIVE=1 sh
/tmp/test-codex-curl/packages/standalone/current/bin/codex exec \
--skip-git-repo-check 'print `which -a rg`'
find /tmp/test-codex-curl -name rg
```
The `which -a rg` output omitted the packaged helper even though `find`
showed it under
`/tmp/test-codex-curl/packages/standalone/releases/.../codex-path/rg`.
The npm install path behaved differently only because
`codex-cli/bin/codex.js` had legacy `PATH` rewriting:
```shell
mkdir /tmp/test-codex-npm
cd /tmp/test-codex-npm
npm install @openai/codex
./node_modules/.bin/codex exec --skip-git-repo-check 'print `which -a rg`'
```
That printed the npm package's `vendor/<target>/codex-path/rg` first.
This PR moves that behavior into Rust-side package launch setup so
curl/standalone and npm/bun launches agree without JS rewriting `PATH`.
## What Changed
- `codex-rs/arg0` now uses
`InstallContext::current().package_layout.path_dir` to prepend the
package helper directory before any threads are created.
- Package helper `PATH` setup is independent from the temporary arg0
alias setup, so `codex-path` is still added even if CODEX_HOME tempdir,
lock, or symlink setup fails.
- `codex-rs/install-context` detects the canonical package layout we
ship: `bin/`, `codex-resources/`, and `codex-path/` next to
`codex-package.json`.
- Shell, local unified exec, and user-shell runtimes now record package
`codex-path` prepends in `explicit_env_overrides`, matching the existing
zsh-fork behavior so shell snapshots cannot restore over the package
helper path.
- Remote unified exec requests do not receive the local app-server
package path overlay.
- `codex-cli/bin/codex.js` no longer computes or overrides `PATH`; it
only locates the native binary in the canonical package layout and
passes npm/bun management metadata.
- Added regression tests for `PATH` ordering, package layout detection,
and shell snapshot preservation of package path prepends.
## Verification
- `node --check codex-cli/bin/codex.js`
- `just test -p codex-install-context -p codex-arg0`
- `just test -p codex-core
user_shell_snapshot_preserves_package_path_prepend`
- `just test -p codex-core tools::runtimes::tests`
- `just bazel-lock-update`
- `just bazel-lock-check`
- `just fix -p codex-install-context -p codex-arg0 -p codex-core`
# Why
When an organization requires the elevated Windows sandbox, Codex
launches an elevated helper to provision users, configure firewall and
ACL rules, and lock persistent sandbox directories.
We observed that closing the helper after setup started could leave the
machine partially initialized while the TUI still announced **Sandbox
ready**. Model-only turns continued to work, but the first shell command
retried setup and failed with Windows cancellation error `1223`.
This was not an enforcement bypass; command execution continued to fail
closed. The issue was a false readiness signal: `setup_marker.json` was
written during user provisioning, before the remaining setup stages had
completed.
# What
Treat `setup_marker.json` as the commit record for Windows sandbox
setup:
1. Before full or provisioning setup begins, remove the existing marker
and create the final marker path with a protected ACL.
2. Keep the marker empty and therefore invalid while setup is in
progress. Sandbox users cannot read, modify, or replace it.
3. Run every synchronous setup stage.
4. After setup succeeds, write the valid marker contents without
changing its ACL.
5. After the helper exits successfully, verify the existing readiness
check before enabling the sandbox.
If setup is canceled or fails, the marker remains invalid and Codex
reports setup as incomplete instead of announcing readiness.
Refresh-only and read-ACL-only helper runs continue to leave the marker
untouched. The setup version remains `5` to avoid forcing all existing
Windows users through elevated setup again.
# Verification
- Added coverage confirming sandbox users cannot read or modify the
setup marker after elevated setup.
- Added coverage confirming a successful helper exit without complete
setup artifacts is rejected.
- Ran `just test -p codex-windows-sandbox`.
## Why
When trying to fit history under compaction limit rewrite output items
instead of removing them entirely. Otherwise we're breaking
incrementality in relation to the previous response.
## Why
Model metadata can now select multi-agent v2 even when a user has not
enabled `features.multi_agent_v2` in their config. Some existing configs
still set the legacy `agents.max_threads` knob for v1 multi-agent
behavior, so treating every v2 runtime as incompatible with
`agents.max_threads` would break users whose only v2 signal came from
the model catalog.
The incompatible configuration is specifically enabling
`features.multi_agent_v2` while also setting `agents.max_threads`.
Catalog-forced v2 should use the v2 concurrency setting and ignore the
legacy v1 cap instead of rejecting the config.
## What changed
- Split config validation from runtime concurrency calculation:
`effective_agent_max_threads` now just returns the effective cap for the
resolved multi-agent runtime.
- Added explicit validation for `features.multi_agent_v2` +
`agents.max_threads` at session startup.
- Preserved catalog-selected v2 behavior when `features.multi_agent_v2`
is disabled, so existing configs with `agents.max_threads` keep
starting.
- Updated model-runtime selector coverage so a catalog v2 model still
exposes v2 tools even when `agents.max_threads` is set and the config
flag is disabled.
## Validation
- `cargo check -p codex-core --lib`
- `just test -p codex-core --lib -E
"test(multi_agent_v2_feature_rejects_agents_max_threads) |
test(catalog_v2_allows_agents_max_threads_when_feature_disabled)"`
## Why
Local image attachments include image bytes, but the adjacent
model-visible label omits the source path. Exposing the path lets
model-selected workflows refer back to the intended local image
explicitly.
## What changed
- Include an escaped `path` attribute in model-visible local image
opening tags.
- Reuse the path-aware marker generator in rollout coverage.
- Update protocol, replay, and rollout coverage for the new request
shape.
## Validation
- `just fmt`
- `just test -p codex-protocol`
- `just test -p codex-core skips_local_image_label_text`
- `just test -p codex-core
copy_paste_local_image_persists_rollout_request_shape`
- `git diff --check`
## Why
#25450 attempts a broad `SandboxPolicy` removal across several unrelated
surfaces, which makes it hard to review and still leaves new helper code
moving legacy policies around. This PR is a narrower alternative:
migrate only the exec-side Windows sandbox plumbing so the review can
focus on one production path and one compatibility boundary.
The goal is to stop threading `SandboxPolicy` through exec code without
expanding the migration into app-server, protocol, telemetry, config, or
session behavior.
## What changed
- Removed `ExecRequest::compatibility_sandbox_policy()`.
- Changed the Windows restricted-token and elevated filesystem override
helpers to accept `PermissionProfile` plus the split filesystem/network
policies instead of a `SandboxPolicy`.
- Kept the remaining legacy projection local to the writable-root
comparison that still needs to compare split policy behavior against the
legacy Windows backend model.
- Rejected restricted split filesystem policies that still grant
full-disk writes before using the Windows restricted-token backend,
preserving the previous clear-failure behavior for profiles that project
to `ExternalSandbox`.
- Updated the Windows sandbox override tests to exercise the new call
shape and cover the full-write split-profile regression.
## Verification
- `just test -p codex-core windows_restricted_token`
- `just test -p codex-core windows_elevated`
Skip turn git metadata enrichment when a turn has remote or multiple
executors, so we do not report the orchestrator checkout as executor
workspace metadata.
Test: `just test -p codex-core` (blocked by existing
`Session::conversation_id` compile error in `close_agent.rs`).
## Why
The skills extension needs the resolved turn environments to build a
real per-turn `SkillListQuery`. The previous `TurnLifecycleContributor`
hook only had a turn id, so it could only seed a placeholder query and
never carry the executor authorities that executor-scoped skill routing
will need.
Moving catalog resolution onto `TurnInputContributor` puts the skills
extension on the same turn-preparation path that already has the
environment ids and working directories for the submitted turn, while
keeping the actual prompt injection work for follow-up changes.
## What changed
- switch `ext/skills` from `TurnLifecycleContributor` to
`TurnInputContributor`
- build `executor_authorities` from `TurnInputContext.environments` and
pass them through `SkillListQuery`
- keep storing the resolved catalog in `SkillsTurnState`, but drop the
placeholder query helper that no longer matches the real data flow
- update the extension TODOs to reflect that per-turn catalog resolution
now happens in the turn-input contributor, and that prompt/context
injection still needs to move later
## Testing
- Not run locally.
## Why
`close_agent` is a parent-owned coordination tool: a worker should
return its result, then let its parent decide when to close it. Before
this change, if an MAv2 worker targeted itself, the resolved target
could flow through the normal close path and ask the agent control layer
to close the current conversation.
## What changed
- Reject `close_agent` when the resolved target is the current session's
`conversation_id`, returning a model-visible error that tells the worker
to return its result instead.
- Keep the guard after target resolution so it covers both thread-id
targets and task-path targets.
- Add coverage for self-targeting by thread id and by task name in
`multi_agents_tests.rs`.
Relevant code:
-
[`handle_close_agent`](https://github.com/openai/codex/blob/7c24e6641b693a3eed933dd376ce8f424ab6ea5f/codex-rs/core/src/tools/handlers/multi_agents_v2/close_agent.rs#L39-L57)
- [`multi_agent_v2_close_agent_rejects_self_target_by_id` /
`multi_agent_v2_close_agent_rejects_self_target_by_task_name`](https://github.com/openai/codex/blob/7c24e6641b693a3eed933dd376ce8f424ab6ea5f/codex-rs/core/src/tools/handlers/multi_agents_tests.rs#L3936-L4070)
## Testing
Not run locally.
## Why
`codex-core` currently owns the generic contextual-fragment trait and
several reusable fragment implementations. That makes it harder for
other crates to share the same host-owned model-input abstraction
without depending on all of `codex-core`.
This change extracts the reusable fragment machinery into a small
`codex-context-fragments` crate so future extension and skills work can
depend on the fragment abstraction directly.
## What Changed
- Added the `codex-context-fragments` crate with:
- `ContextualUserFragment`
- `FragmentRegistration` / `FragmentRegistrationProxy`
- additional-context fragment types
- Moved `SkillInstructions` into `codex-core-skills`, since
skill-specific rendering belongs with skills rather than generic core
context machinery.
- Kept `codex-core` re-exporting the fragment types it still uses
internally, so existing call sites keep the same shape.
- Updated Cargo and Bazel workspace metadata for the new crate.
## Verification
- `cargo metadata --locked --format-version 1 --no-deps`
- `just bazel-lock-update`
- `just bazel-lock-check`
## Disclaimer
Do not use for now
## Why
Extensions can already contribute prompt fragments and request same-turn
item injection, but there was no host-owned hook for contributing
structured `ResponseItem`s while Codex is assembling a new turn's
initial model input. This change adds that seam so extensions can attach
turn-local input that depends on the submitted user input and resolved
turn environments without routing through prompt text or late injection.
## What changed
- add `TurnInputContributor` to `codex_extension_api` and export the new
`TurnInputContext` / `TurnInputEnvironment` types it receives
- teach `ExtensionRegistry` to register and expose turn-input
contributors alongside the existing extension hooks
- call registered turn-input contributors from
`core/src/session/turn.rs` while building the initial injected input for
a turn, then append their returned `ResponseItem`s after the skill and
plugin injections
## Why
`PermissionProfile` is becoming the default way to represent Codex
permissions, but the implicit default behavior should stay the same for
now:
- trusted projects use `:workspace`
- untrusted projects also use `:workspace`
- roots without a trust decision use `:read-only`
- unsandboxed Windows falls back to `:read-only`
This keeps the existing sandbox semantics while making silent config
defaults observable as built-in permission profiles instead of treating
the legacy `SandboxPolicy` projection as the primary shape.
## What Changed
- Refactored legacy sandbox derivation to resolve the configured sandbox
mode once, then apply the implicit project fallback only when no sandbox
mode was configured.
- Preserved the existing trust-decision fallback: trusted and untrusted
projects default to workspace-write where supported.
- Added empty-config coverage asserting that an untrusted project
resolves to the built-in active permission profile (`:workspace` outside
unsandboxed Windows).
## Verification
- `just fmt`
- `just test -p codex-core 'config::'`
- `just test -p codex-config`
---
[//]: # (BEGIN SAPLING FOOTER)
Stack created with [Sapling](https://sapling-scm.com). Best reviewed
with [ReviewStack](https://reviewstack.dev/openai/codex/pull/25926).
* __->__ #25926
## Why
`profile_sandbox_mode` was left over from the old selected legacy
profile path. Production now always derives permissions without that
value, and legacy profile contents are ignored, so keeping a parameter
that is always `None` makes `derive_permission_profile` look like it
still supports a fallback that no longer exists.
## What Changed
- Removed the `profile_sandbox_mode` argument from
`ConfigToml::derive_permission_profile`.
- Updated the production caller and legacy sandbox-policy test helper to
match.
- Dropped the stale unselected legacy-profile sandbox test that only
protected the removed fallback shape.
## Verification
- `just test -p codex-config`
- `just test -p codex-core 'config::'`
---
[//]: # (BEGIN SAPLING FOOTER)
Stack created with [Sapling](https://sapling-scm.com). Best reviewed
with [ReviewStack](https://reviewstack.dev/openai/codex/pull/25943).
* #25926
* __->__ #25943
## Stack
1. #25850 - Key request-permission grants by environment: stores and
applies sticky permission grants per environment id.
2. #25858 - Add `environmentId` to `request_permissions`: lets the model
target a selected environment and resolves relative permission paths
against it.
3. #25862 - Propagate permission approval environment id: carries the
selected environment id through approval events, app-server requests,
TUI prompts, and delegate forwarding.
4. This PR (#25867) - Add remote request permissions integration
coverage: verifies the selected remote environment across request,
approval, grant reuse, and exec.
This PR is stacked on #25862 and should be reviewed after #25850,
#25858, and #25862.
## Why
The environment-scoped permission stack needs one end-to-end check that
exercises the CCA-shaped path, not only unit-level parsing. This
verifies that a model-sent `environmentId` on `request_permissions`
reaches the approval event, stores the grant under the selected
environment, and is reused by a later tool call in that same
environment.
## What Changed
- Adds a remote executor integration test for `request_permissions` with
`environmentId: remote` and a relative write root.
- Asserts the permission event reports the remote environment and cwd,
and that the normalized grant resolves under the remote cwd.
- Approves the grant, then runs a remote `exec_command` without explicit
per-call permissions and verifies it completes without another exec
approval and writes only in the remote filesystem.
## Verification
- Not run locally per instruction.
- `git diff --check`
## Why
`code_mode_only` moved ordinary runtime tools behind `exec`, but it also
hid hosted Responses tools. Hosted `web_search` and `image_generation`
do not have a nested `exec` runtime path, so code-only sessions lost
those capabilities entirely even when their existing provider, auth,
model, and configuration gates passed.
## What changed
- Keep hosted Responses tools top-level in `code_mode_only` sessions
after their existing gates pass.
- Preserve the existing nested-tool behavior for ordinary runtimes and
the direct-only behavior for multi-agent v2 tools.
- Add planner coverage for `code_mode_only` with default multi-agent v2
settings, hosted live web search, and hosted image generation.
## Verification
- Added focused regression coverage in
`codex-rs/core/src/tools/spec_plan_tests.rs`.
- Left execution to CI per repository workflow.
## 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.
## Summary
- Adapts the moved `codex-cloud-config` crate from the legacy cloud
requirements endpoint to the new config bundle endpoint.
- Switches runtime consumers from `CloudRequirementsLoader` to
`CloudConfigBundleLoader` so one shared bundle supplies cloud-delivered
config and requirements.
- Removes the legacy cloud requirements domain loader path.
## Details
This intentionally keeps `codex-cloud-config` monolithic for review
lineage: the previous PR establishes the crate move, and this PR shows
the behavior change against that moved implementation. A follow-up PR
splits the module back into focused files.
The new bundle path preserves the important cloud requirements loader
semantics where intended: account-scoped signed cache, 30 minute TTL, 5
minute refresh cadence, retry/backoff, auth recovery, and fail-closed
startup loading. The cached payload changes from a single requirements
TOML string to the backend-delivered bundle, and validation rejects
malformed config or requirements fragments before cache write/use.
Eric TrautandGitHub
pakrym-oaiandGitHub
Ahmed IbrahimandGitHub
iceweasel-oaiandGitHub
jifandGitHub
carlc-oaiandGitHub
Michael BolinandGitHub
rka-oaiandGitHub
rreichel3-oaiandGitHub
Channing CongerandGitHub
Adam Perry @ OpenAIandGitHub
sayan-oaiandGitHub
kbazziandGitHub
Won ParkandGitHub
rhan-oaiandGitHub
Chris DongandGitHub
AbhinavandGitHub
joeflorencio-openaiandGitHub