## Summary
- track user-like input and tool-output boundaries in current-time
reminder state
- gate reminder injection when delivery_mode is
after_user_or_tool_output
- preserve interval debounce and forced reminders after context-window
changes
## Why
Training can request reminders only after user or tool-output items
while keeping the existing canonical pre-inference history-injection
path.
## Validation
- just test -p codex-core
current_time_reminders_can_follow_only_user_or_tool_outputs
- just test -p codex-core
current_time_reminders_follow_time_interval_and_persist_in_history
- just test -p codex-core
current_time_reminder_is_refreshed_after_compaction
- just fix -p codex-core
## Summary
- retry ERS `409 environment_offline` responses inside the existing
exec-server recovery loop
- keep all other registry conflicts terminal
- add focused coverage for both cases
## Root cause
When an exec server disconnects and reconnects, the client already
starts recovery and calls ERS `/connect`. During the transient executor
presence gap, ERS can return `409 environment_offline`. The retry
classifier treated every 409 as terminal, so the first response aborted
the existing 25-second recovery window before the executor came back
online. That then caused active processes to be marked lost.
This change classifies only the structured `environment_offline`
conflict as retryable. Recovery continues with the existing bounded
deadline, exponential backoff, and jitter.
## Validation
- `just test -p codex-exec-server client::recovery::tests` — 4 passed
- `just fix -p codex-exec-server` — passed
- `just fmt` — passed
- Full `just test -p codex-exec-server` reached unrelated macOS
filesystem-sandbox integration failures because nested
`/usr/bin/sandbox-exec` is denied in this environment (`sandbox_apply:
Operation not permitted`).
## tl;dr
Inject a `CODEX_PERMISSION_PROFILE` environment variable with the name
of the current permission profile when invoking a shell tool.
## Why
Shell tool owners may need to launch nested commands under the same
named permission profile, including through `codex sandbox -P PROFILE
--include-managed-config`. Until now, child processes could observe
sandbox and network metadata but could not identify the active named
permission profile.
The `--include-managed-config` flag is essential when a helper
reconstructs the sandbox from a profile name: it ensures the nested
sandbox also loads managed enterprise requirements. Without it, using
the inherited profile could unintentionally create a sandbox that does
not enforce the organization's managed restrictions.
The new environment value is intentionally informational and **must not
be treated as trusted input**. Any process in the ancestry can overwrite
an environment variable, so a consumer that passes this value to `codex
sandbox -P` must first validate it against the profiles that helper is
authorized to use.
## Example Use Case
Suppose an organization provides a trusted `remote-bash` wrapper that
lets Codex run a command on an approved build host. The local shell
command uses the named `:workspace` permission profile:
```toml
default_permissions = ":workspace"
```
The command exposed to the model is a small zsh wrapper. It deliberately
delegates with `exec`, preserving the original arguments and process
environment:
```zsh
#!/usr/bin/env zsh
exec /opt/codex-tools/remote_bash.py "$@"
```
The model invokes the public wrapper, not its Python implementation:
```sh
/opt/codex-tools/remote-bash \
--host builder.example.com \
-- printf '%s' 'hello world'
```
Only the inner implementation is authorized to escape the local sandbox:
```starlark
prefix_rule(
pattern=["/opt/codex-tools/remote_bash.py"],
decision="allow",
)
```
With zsh-fork, execution begins with `remote-bash` inside the
`:workspace` sandbox. When the wrapper calls `exec`, the exact prefix
rule matches `remote_bash.py`, so that inner script is restarted
unsandboxed. The escalated process inherits:
```text
CODEX_PERMISSION_PROFILE=:workspace
```
Inheritance does not make the value trustworthy. `remote_bash.py`
independently allowlists both the remote host and the permission profile
before using either value. In particular, a forged value such as
`:danger-full-access` is rejected before it can reach `codex sandbox
-P`:
```python
import argparse
import os
import shlex
import sys
ALLOWED_HOSTS = {"builder.example.com"}
ALLOWED_PROFILES = {":workspace"}
parser = argparse.ArgumentParser()
parser.add_argument("--host", required=True)
separator = sys.argv.index("--")
args = parser.parse_args(sys.argv[1:separator])
command = sys.argv[separator + 1:]
if args.host not in ALLOWED_HOSTS:
parser.error("host is not allowlisted")
if not command:
parser.error("the remote command must not be empty")
profile = os.environ.get("CODEX_PERMISSION_PROFILE")
if not profile:
raise SystemExit("CODEX_PERMISSION_PROFILE must not be empty")
if profile not in ALLOWED_PROFILES:
raise SystemExit("CODEX_PERMISSION_PROFILE is not allowlisted")
remote_command = shlex.join(command)
sandbox_command = shlex.join([
"codex", "sandbox", "-P", profile,
"--include-managed-config", "--",
"bash", "-lc", remote_command,
])
print(shlex.join(["ssh", args.host, sandbox_command]))
```
This builds each command layer as an argument vector and uses
`shlex.join()` at the boundary, rather than interpolating untrusted
shell text. After validation and parsing, the nested command has this
structure:
```text
ssh argv:
["ssh", "builder.example.com", SANDBOX_COMMAND]
SANDBOX_COMMAND argv:
["codex", "sandbox", "-P", ":workspace",
"--include-managed-config", "--",
"bash", "-lc", "printf %s 'hello world'"]
bash -lc payload argv:
["printf", "%s", "hello world"]
```
A production implementation could execute that SSH command. The
integration fixture prints it and parses the result back into arguments,
verifying the complete flow:
```text
model invokes outer wrapper
-> zsh-fork starts wrapper under :workspace
-> wrapper execs allowlisted Python script
-> prefix rule restarts Python script unsandboxed
-> Python script inherits CODEX_PERMISSION_PROFILE=:workspace
-> Python script verifies :workspace is allowlisted
-> remote command runs codex sandbox -P :workspace
with --include-managed-config
-> nested sandbox honors managed enterprise requirements
```
This gives the trusted helper access to resources outside the local
sandbox—such as SSH credentials—while ensuring that it can select only
an explicitly authorized profile and that work on the remote host
remains subject to the organization's managed requirements.
## What changed
- Inject `CODEX_PERMISSION_PROFILE` after shell environment policy
evaluation so the active profile wins over inherited or configured stale
values.
- Apply the variable to both `shell_command` and unified `exec_command`,
including local, zsh-fork, and remote exec-server paths.
- Remove stale values when the session has no active named profile.
- Preserve the current profile value when loading a shell snapshot so a
parent snapshot cannot restore an older profile.
## Testing
- Added classic-shell integration coverage proving an exact prefix rule
can run a `require_escalated` script outside the `:workspace` sandbox
while preserving `CODEX_PERMISSION_PROFILE=:workspace`.
- Added zsh-fork integration coverage in which the model invokes an
outer zsh wrapper, an inner allowlisted `remote_bash.py` runs
unsandboxed, and its printed SSH command reconstructs the inherited
`:workspace` sandbox with `--include-managed-config` while preserving
every argument after `--`.
- The example helper treats `CODEX_PERMISSION_PROFILE` as untrusted and
validates it against `ALLOWED_PROFILES` before constructing the nested
command.
- Assert that the reconstructed sandbox command includes
`--include-managed-config` so nested use of the inherited profile cannot
bypass managed enterprise requirements.
- Added coverage for overriding and removing stale profile values.
- Verified `shell_command` receives the selected active profile.
- Added shell snapshot coverage using `printenv
CODEX_PERMISSION_PROFILE`.
A zero interval lets callers request a reminder at every
otherwise-eligible inference boundary.
## Validation
- just test -p codex-core load_config_resolves_current_time_reminder
## Why
`codex sandbox` accepts a single named permissions profile, so the
existing plural `--permissions-profile` spelling is misleading. The
canonical flag and its help text should use the singular form without
breaking scripts that already use the old spelling.
## What changed
- Make `--permission-profile` the canonical flag for all sandbox
backends.
- Keep `--permissions-profile` as a hidden backwards-compatible alias.
- Cover the canonical spelling, legacy alias, and help visibility with
regression tests.
## Testing
Ran `just c sandbox --help` and verified I saw:
```shell
-P, --permission-profile <NAME>
Named permissions profile to apply from the active configuration stack
```
## Why
Helper threads such as task title generation can request a model ID that
is valid for the default OpenAI provider but unavailable from the active
provider. With Amazon Bedrock, `gpt-5.4-mini` is rejected while the
provider static catalog exposes Bedrock model IDs such as
`openai.gpt-5.5` and `openai.gpt-5.4`. This causes repeated background
404s and can surface a misleading turn error even when the main turn
succeeds.
Clients need an explicit way to ask app-server to resolve an unavailable
helper model to the active provider default. That fallback must remain
limited to providers with an authoritative static catalog so custom or
dynamically discovered model IDs are not rewritten based on an
incomplete catalog.
Fixes#28741.
## What changed
- Add the experimental `allowProviderModelFallback` option to
`thread/start`, defaulting to `false` to preserve existing behavior.
- Thread the option through thread creation and model selection.
- When enabled for a static model manager, preserve requested models
present in the catalog and replace unavailable models with the provider
default.
- Continue preserving explicit model IDs for dynamic model managers
without fetching a catalog solely to validate them.
- Document the new `thread/start` behavior in the app-server API
overview.
## Test
Temporary test-client harness:
```
ThreadStartParams {
model: Some("gpt-5.4-mini".to_string()),
allow_provider_model_fallback: true,
..Default::default()
}
```
Command:
```
CODEX_HOME=/tmp/codex-bedrock-thread-start-home \
CODEX_E2E_BEDROCK_THREAD_START_ONLY=1 \
./target/debug/codex-app-server-test-client \
--codex-bin ./target/debug/codex \
-c 'model_provider="amazon-bedrock"' \
send-message-v2 --experimental-api ignored
```
Relevant output:
```
> "method": "thread/start",
> "params": {
> "model": "gpt-5.4-mini",
> "modelProvider": null,
> "allowProviderModelFallback": true,
> ...
> }
< "result": {
< "model": "openai.gpt-5.5",
< "modelProvider": "amazon-bedrock",
< ...
< }
```
## Summary
- Record bounded connection, request, and process lifecycle metrics.
- Report active gauges from callbacks on every collection, including
delta exports.
- Serialize active-count updates so concurrent starts and finishes
cannot publish stale values.
- Serialize process exit, explicit termination, and shutdown through the
process registry so exactly one completion result wins.
- Keep the implementation small with single-owner RAII guards and one
real OTLP/HTTP integration test using the existing `wiremock`
dependency.
## Root cause
Process exit and session shutdown previously used cloned completion
state. That avoided duplicate emission, but it duplicated lifecycle
ownership and made the ordering harder to reason about. The process
registry mutex already defines the lifecycle ordering, so the final
implementation stores the metric guard and termination flag directly on
the process entry. Whichever path claims the entry first owns the
completion result.
Production metric export uses delta temporality. Event-only synchronous
gauge recordings disappear after the next collection when no count
changes, so active counts now use observable callbacks that report
current state on every collection.
The cleanup also removes the constant `result="accepted"` connection
tag, redundant route and response assertions, a custom HTTP collector,
and fallback initialization machinery that did not add behavior.
## Stack
Review and land this stack in order:
1. #27466 — trace exec-server JSON-RPC requests
2. #27467 — record bounded connection, request, and process lifecycle
metrics **(this PR)**
3. #27470 — observe remote registration and Noise rendezvous lifecycle
## Validation
- `just test -p codex-exec-server --lib` (158 passed)
- `just test -p codex-cli --test exec_server` (3 passed)
- `just test -p codex-otel
observable_gauge_is_collected_on_every_delta_snapshot` (1 passed)
- `CARGO_BUILD_JOBS=1 just fix -p codex-otel -p codex-exec-server`
- `just fmt`
- `git diff --check`
## Why
`selectedCapabilityRoots` is durable thread intent: “use this capability
root from environment `worker`.”
The important product assumption is:
> One environment ID always names the same logical executor and stable
contents.
`worker` does not silently change from executor A to an unrelated
executor B. The process-local connection handle for `worker` can still
be replaced while Codex is running, though, for example when
`environment/add` registers a fresh handle for the same logical
environment.
The thread should persist only the stable selection. Each model step
should pair that selection with the exact ready handle captured for that
step.
## The boundary
```text
persisted thread intent
plugin@1 -> environment "worker"
|
| capture the current step
v
model-step view
unavailable, or
plugin@1 + worker's exact captured ready handle
```
The environment ID is the stable identity and cache key. The
`Arc<Environment>` is only a process-local handle retained so consumers
of one model step use the same captured environment. It is never
persisted and it does not imply different environment contents.
## What changes
### Persist the stable selection
Selected roots are written into `SessionMeta` and restored with the
thread. Forked subagents inherit the same selections, including
bounded-history forks.
Only stable data is persisted: root ID, environment ID, and root path.
### Capture readiness together with the exact handle
The environment snapshot records:
```rust
environment_id -> Some(Arc<Environment>) // ready in this step
environment_id -> None // still starting in this step
```
This prevents readiness and execution from coming from different
registry snapshots.
For example:
```text
step snapshot: worker -> handle A, ready
environment/add: worker -> fresh handle B for the same logical environment
current step: plugin@1 still uses captured handle A
```
Without carrying handle A in the snapshot, the resolver could combine “A
was ready” with handle B and treat B as ready before it had finished
starting.
This does not change cache invalidation. Stable capability metadata
remains identified by environment ID and capability root. Replacing a
process-local handle under the same stable environment ID does not
invalidate or rediscover that metadata.
### Resolve availability per model step
- A ready captured environment produces resolved roots using its
captured handle.
- A starting, missing, or failed environment is omitted from that step.
- A selected lazy environment that is outside the turn's captured
environment set is asked to start, and a later step can observe it as
ready.
- No capability files are scanned here.
Transient transport disconnects remain the remote client's reconnect
concern. This PR models initial attachment/readiness; it does not add
live socket-connectivity state.
## Example
```text
thread selection: plugin@1 -> environment "worker"
step 1: worker is starting -> plugin@1 unavailable
step 2: worker is ready -> plugin@1 resolves through worker's captured handle
step 3: fresh local handle -> current step remains pinned; a later step captures its own view
```
Temporary unavailability does not discard the durable selection. Later
PRs can retain stable metadata caches while projecting only currently
available capabilities into model-visible World State.
## Compatibility
The app-server request shape does not change. Older rollouts without
`selected_capability_roots` deserialize to an empty list.
## Stack
1. **This PR:** persist stable selected roots and resolve them through
an exact model-step handle.
2. #29960: cache stable skill metadata and project available skills into
World State.
3. #29946: cache stable plugin declarations and manage the separate live
MCP runtime.
## Why
#28529 proves OAuth discovery uses the selected executor, but its
end-to-end test stops before the callback and token exchange.
## What changed
- add an executor-only mock token endpoint
- complete the OAuth callback using the authorization URL's `state` and
`redirect_uri`
- assert the PKCE token exchange reaches the executor-only endpoint
- assert the completion notification reports the selected thread and
succeeds
Depends on #28529.
## Why
#28522 routes selected-plugin HTTP MCP traffic through the owning
executor, but OAuth bootstrap and refresh still used host-local clients.
Executor-only servers therefore cannot complete discovery or login
through the same network boundary as the MCP connection.
## What changed
- adapt `codex_exec_server::HttpClient` to RMCP 1.8's `OAuthHttpClient`
contract
- let RMCP own discovery, dynamic registration, PKCE, token exchange,
and refresh
- route auth status, persisted-token startup, and app-server login
through the server runtime while preserving the existing local discovery
path
- add optional `threadId` to `mcpServer/oauth/login` and echo it in the
completion notification
- implement RMCP's redirect policy and 1 MiB OAuth response limit over
executor HTTP
- cover selected-thread OAuth discovery and login through an
executor-only route
Depends on #28522.
## Why
Selected executor plugins can declare both stdio and Streamable HTTP MCP
servers, but only stdio registrations were retained. That silently drops
part of the plugin's tool surface and prevents HTTP traffic from using
the owning executor's network.
## What changed
- retain selected-plugin Streamable HTTP MCP declarations alongside
stdio declarations
- route their HTTP clients through the owning executor environment
- preserve local auth-header environment references while rejecting them
for executor-hosted declarations
- cover thread isolation, refresh, and an executor-only HTTP route end
to end
## Why
Avoid a request waterfall for loading lots of skills at once by hiding
latency in concurrent tasks.
## What changed
Poll the per-skill parse futures concurrently with an order-preserving
stream capped at 64 in-flight loads. Results retain discovery order, and
the existing filtering, warnings, and final catalog sorting are
unchanged.
## Why
Older rollouts can retain model-visible context for a WorldState section
without having a persisted snapshot for that section. Treating the
missing snapshot as definitely absent can duplicate old context or fail
to tell the model that it was replaced or removed.
This provides a generic migration path for sections moving into
WorldState, beginning with AGENTS.md.
Builds on #29810.
## What changed
- distinguish section state that is absent, known from a persisted
snapshot, or unknown because matching legacy context remains in history
- let WorldState sections identify their own legacy fragments while
`ContextManager` owns history reconciliation and baseline persistence
- make AGENTS.md emit one conservative replacement or removal update for
legacy history, then deduplicate from the newly persisted baseline
- preserve existing environment rendering when persisted section data is
missing or malformed
## Testing
- `just test -p codex-core world_state`
- `just test -p codex-core
cold_resume_invalidates_deleted_legacy_agents_md_once -- --exact`
## Why
With deferred executors, a turn can begin before a remote environment
attaches. AGENTS.md discovery previously ran only during session setup,
so instructions from a later environment never reached the model or the
session instruction sources.
WorldState persistence has now landed, so this uses the durable
model-visible baseline directly instead of carrying a temporary
resume/fork compatibility path.
## What
- Add an `AgentsMdManager` in `SessionServices` to own host
instructions, loaded state, and refresh caching.
- When `DeferredExecutor` is enabled, refresh AGENTS.md when attached
environment selections change and freeze the result in the corresponding
`StepContext`.
- Represent AGENTS.md as a persisted WorldState section for every
session, with bounded initial, replacement, and removal updates.
- Remove duplicate AGENTS.md state and rendering from
`SessionConfiguration` and `TurnContext`.
- Build initial context, per-request updates, and compaction context
from the same step-scoped value.
- On resume and fork, compare current instructions with the restored
WorldState baseline and inject a replacement exactly once when they
differ.
Builds on #29833, #29835, and #29837.
## Tests
- Covers a remote environment becoming ready mid-turn, with AGENTS.md
appearing on the next request exactly once and updating canonical
instruction sources.
- Covers full, unchanged, replaced, and removed AGENTS.md WorldState
rendering.
- Covers changed instructions across cold resume and fork without
duplicate reinjection.
- Covers remote-v2 compaction retaining creation-time instructions in
the live session and cold resume appending one replacement when the
source changed.
- Ran focused `codex-core` AGENTS.md, WorldState, and context-update
test suites.
## Stack
This is PR 3 of the simplified HAI single-run-task stack:
- [#19047](https://github.com/openai/codex/pull/19047) Agent Identity
assertion and task-registration primitives, including the shared
run-task helper used by existing Agent Identity JWT auth.
- [#19049](https://github.com/openai/codex/pull/19049)
Disabled-by-default ChatGPT auth opt-in that provisions/reuses persisted
Agent Identity runtime auth and its single run task.
- [#19051](https://github.com/openai/codex/pull/19051) Run-scoped
provider auth that uses one backend-owned task id for first-party
inference and compaction requests.
[#19054](https://github.com/openai/codex/pull/19054) collapsed out of
the active stack because the simplified design no longer needs a
separate background/control-plane task helper.
## Summary
This PR moves Agent Identity usage into provider auth resolution. That
keeps `AgentAssertion` auth tied to first-party OpenAI provider requests
instead of applying a late session-wide override that could affect
local, custom, Bedrock, API-key, or external-bearer providers.
What changed:
- adds a small `ProviderAuthScope` struct carrying the run auth policy
and session source needed by provider-scoped auth resolution
- lets `Session` opt the existing `ModelClient` into `ChatGptAuth`
policy when `use_agent_identity` is enabled, without adding a second
model-client constructor
- resolves Agent Identity only for first-party OpenAI provider auth
paths
- uses the persisted run task id from the `AgentIdentityAuth` record to
build `AgentAssertion` auth for Responses requests
- routes shared request setup through scoped provider auth so unary
compact requests use the same run-task assertion path as inference turns
- keeps local/custom/Bedrock/env-key/external-bearer provider auth
unchanged
- lets missing run-task state surface through the existing model-request
error path instead of silently falling back to bearer auth
This PR intentionally does not create thread-scoped, target-scoped, or
background-scoped task identities. The run task is the only task Codex
registers in this POC shape.
## Testing
- `just test -p codex-model-provider`
- `just test -p codex-core client::tests::provider_auth_scope_uses`
- `just test -p codex-core remote_compact_uses_agent_identity_assertion`
## Summary
- add a cancellable sleep operation to `TimeProvider`
- route `clock.sleep` through the configured provider
- extend the supported sleep duration to 12 hours
- complete the sleep turn item before propagating provider failures
## Why
This isolates the core clock abstraction needed by external clock
integrations. Existing system and app-server behavior remains wall-clock
based in this PR; the stacked follow-up supplies app-server sleeps from
an external clock.
## Why
Token-budget reminder and guidance messages can require more than 1,000
bytes to provide useful model-facing instructions. At the same time,
these strings are injected into model-visible context, so their size
must remain tightly bounded in response to the P0 context-growth
concern. A 2,000-byte runtime cap provides additional room without
allowing the substantially larger context growth of a 4 KiB limit.
## What changed
- raises the runtime byte limits for token-budget reminder templates and
guidance messages from 1,000 to 2,000
- raises the corresponding JSON Schema `maxLength` values to 2,000
- regenerates `codex-rs/core/config.schema.json`
## Testing
- `just test -p codex-features`
- `just test -p codex-core load_config_resolves_token_budget_config
load_config_rejects_invalid_token_budget_reminder_template`
The full `codex-core` test run completed 2,858 tests successfully and
encountered seven unrelated environment-sensitive failures involving
Seatbelt/network environment assertions, MCP capability setup, and abort
timing.
## Why
MCP error-code telemetry special-cased Codex Apps: its reported error
codes were retained, while codes from every other MCP server were
replaced with `unknown`. Error reporting should behave consistently for
every MCP server. The server name already identifies where an error came
from, so telemetry does not need a separate Codex Apps classification.
This follows up on [#28976](https://github.com/openai/codex/pull/28976),
which introduced MCP error-code telemetry.
## What changed
- Add the MCP server name to call, duration, and error metrics.
- Retain bounded, sanitized tool error codes from every MCP server.
- Remove `McpErrorCodeSource` and the Codex Apps ownership lookup from
telemetry collection.
- Use the same metric-tagging path for blocked, rejected, and executed
MCP calls.
## Test plan
- Verify the complete metric tag set includes the sanitized MCP server
name.
- Verify error codes from ordinary MCP servers are retained, bounded,
and sanitized.
- Preserve coverage for request failures, tool-result failures, nested
auth failures, and span attributes.
## Why
Persisting `WorldState` snapshots and patches is only useful if resume
and fork restore that exact comparison baseline. Rebuilding it from
`TurnContextItem` loses section state and can either repeat or suppress
model-visible updates.
This is the third PR in the WorldState persistence stack, built on
#29835.
## What
- Replay full WorldState snapshots and RFC 7386 patches through the
existing rollout reconstruction segments.
- Discard state from rolled-back turns and treat compaction as a
baseline reset.
- Hydrate `ContextManager` from the reconstructed snapshot on resume and
fork.
- Remove the synthetic `TurnContextItem` to WorldState conversion path.
- Leave legacy or malformed rollouts without a baseline so the next
update safely emits a full snapshot.
## Testing
- `just test -p codex-core world_state`
- `just test -p codex-core rollout_reconstruction_tests`
- `just fix -p codex-core`
- `just test -p codex-core` *(the changed tests passed; the full run
also hit unrelated existing/test-environment failures, primarily a
missing `test_stdio_server` binary)*
