The `TODO` in `core/src/seatbelt.rs` claimed that `apply_patch` still needed to honor `SandboxPolicy`. That was true when the comment was added, but it is no longer true.
Analysis:
- The TODO was introduced in #1762, when seatbelt code was split out of `exec.rs`.
- `apply_patch` sandboxing was later implemented in #1705.
- Today, `apply_patch` calls are routed through the tool orchestrator and delegated to `ApplyPatchRuntime`, which executes via `execute_env()` using the active sandbox attempt policy.
- On macOS, the sandbox transform path for that execution still builds seatbelt args with `create_seatbelt_command_args(command, policy, sandbox_policy_cwd)`, so the same `SandboxPolicy` gates `apply_patch` writes and network behavior.
Because this behavior is already enforced, the TODO is stale and removing it avoids implying missing sandbox coverage where none exists.
No functional behavior change; comment-only cleanup.
During thread/fork, the new rollout includes the fork’s own session_meta
plus copied history that can contain older session_meta entries from the
source thread. thread/list was overwriting metadata on later
session_meta lines, so a fork could be reported with the source thread’s
thread_id. This fix only uses the first session_meta, so the fork keeps
its own ID.
Summary
- move `core/src/hooks` implementation into a new `codex-hooks` crate
with its own manifest
- update `codex-rs` workspace and `codex-core` crate to depend on the
extracted `hooks` crate and wire up the shared APIs
- ensure references, modules, and lockfile reflect the new crate layout
Testing
- Not run (not requested)
## Align with the new phase-1 design
Basically we know run phase 1 in parallel by considering:
* Max 64 rollouts
* Max 1 month old
* Consider the most recent first
This PR also adds stronger parallelization capabilities by detecting
stale jobs, retry policies, ownership of computation to prevent double
computations etc etc
As of this PR, `SessionServices` retains a
`Option<StartedNetworkProxy>`, if appropriate.
Now the `network` field on `Config` is `Option<NetworkProxySpec>`
instead of `Option<NetworkProxy>`.
Over in `Session::new()`, we invoke `NetworkProxySpec::start_proxy()` to
create the `StartedNetworkProxy`, which is a new struct that retains the
`NetworkProxy` as well as the `NetworkProxyHandle`. (Note that `Drop` is
implemented for `NetworkProxyHandle` to ensure the proxies are shutdown
when it is dropped.)
The `NetworkProxy` from the `StartedNetworkProxy` is threaded through to
the appropriate places.
---
[//]: # (BEGIN SAPLING FOOTER)
Stack created with [Sapling](https://sapling-scm.com). Best reviewed
with [ReviewStack](https://reviewstack.dev/openai/codex/pull/11207).
* #11285
* __->__ #11207
The dynamic model refresh feature (`https://api.openai.com/v1/models`
endpoint) is currently gated on a runtime check for an auth method other
than API Key. It should be gated on a check specifically for ChatGPT
Auth because some custom model providers (e.g. for local models) use no
auth mechanism. A call to `self.auth_manager.auth_mode()` will return
`None` in this case.
Addresses #11213
…ount_id and chatgpt_plan_type
### Summary
Following up on external auth mode which was introduced here:
https://github.com/openai/codex/pull/10012
Turns out some clients have a differently shaped ID token and don't have
a chosen workspace (aka chatgpt_account_id) encoded in their ID token.
So, let's replace `id_token` param with `chatgpt_account_id` and
`chatgpt_plan_type` (optional) when initializing the external ChatGPT
auth mode (`account/login/start` with `chatgptAuthTokens`).
The client was able to test end-to-end with a Codex build from this
branch and verified it worked!
# External (non-OpenAI) Pull Request Requirements
Before opening this Pull Request, please read the dedicated
"Contributing" markdown file or your PR may be closed:
https://github.com/openai/codex/blob/main/docs/contributing.md
If your PR conforms to our contribution guidelines, replace this text
with a detailed and high quality description of your changes.
Include a link to a bug report or enhancement request.
Match model metadata by longest matching remote slug prefix before local
fallback.
- Update `get_model_info` to prefer the most specific remote slug prefix
for the requested model.
- Add an integration test to assert `gpt-5.3-codex-test` resolves to
`gpt-5.3-codex` over `gpt-5.3`.
**Why We Did This**
- The goal is to reduce MCP tool context pollution by not exposing the
full MCP tool list up front
- It forces an explicit discovery step (`search_tool_bm25`) so the model
narrows tool scope before making MCP calls, which helps relevance and
lowers prompt/tool clutter.
**What It Changed**
- Added a new experimental feature flag `search_tool` in
`core/src/features.rs:90` and `core/src/features.rs:430`.
- Added config/schema support for that flag in
`core/config.schema.json:214` and `core/config.schema.json:1235`.
- Added BM25 dependency (`bm25`) in `Cargo.toml:129` and
`core/Cargo.toml:23`.
- Added new tool handler `search_tool_bm25` in
`core/src/tools/handlers/search_tool_bm25.rs:18`.
- Registered the handler and tool spec in
`core/src/tools/handlers/mod.rs:11` and `core/src/tools/spec.rs:780` and
`core/src/tools/spec.rs:1344`.
- Extended `ToolsConfig` to carry `search_tool` enablement in
`core/src/tools/spec.rs:32` and `core/src/tools/spec.rs:56`.
- Injected dedicated developer instructions for tool-discovery workflow
in `core/src/codex.rs:483` and `core/src/codex.rs:1976`, using
`core/templates/search_tool/developer_instructions.md:1`.
- Added session state to store one-shot selected MCP tools in
`core/src/state/session.rs:27` and `core/src/state/session.rs:131`.
- Added filtering so when feature is enabled, only selected MCP tools
are exposed on the next request (then consumed) in
`core/src/codex.rs:3800` and `core/src/codex.rs:3843`.
- Added E2E suite coverage for
enablement/instructions/hide-until-search/one-turn-selection in
`core/tests/suite/search_tool.rs:72`,
`core/tests/suite/search_tool.rs:109`,
`core/tests/suite/search_tool.rs:147`, and
`core/tests/suite/search_tool.rs:218`.
- Refactored test helper utilities to support config-driven tool
collection in `core/tests/suite/tools.rs:281`.
**Net Behavioral Effect**
- With `search_tool` **off**: existing MCP behavior (tools exposed
normally).
- With `search_tool` **on**: MCP tools start hidden, model must call
`search_tool_bm25`, and only returned `selected_tools` are available for
the next model call.
## Summary
- add targeted remote-compaction failure diagnostics in compact_remote
logging
- log the specific values needed to explain overflow timing:
- last_api_response_total_tokens
- estimated_tokens_of_items_added_since_last_successful_api_response
- estimated_bytes_of_items_added_since_last_successful_api_response
- failing_compaction_request_body_bytes
- simplify breakdown naming and remove
last_api_response_total_bytes_estimate (it was an approximation and not
useful for debugging)
## Why
When compaction fails with context_length_exceeded, we need concrete,
low-ambiguity numbers that map directly to:
1) what the API most recently reported, and
2) what local history added since then.
This keeps the failure logs actionable without adding broad, noisy
metrics.
## Testing
- just fmt
- cargo test -p codex-core
Instead of storing a special connection on the client level make the
regular task responsible for establishing a normal client session and
open a connection on it.
Then when the turn is started we pass in a pre-established session.
On some platforms, the "notify" file watcher library emits events for
file opens and reads, not just file modifications or deletes. The
previous implementation didn't take this into account.
Furthermore, the `tracing.info!` call that I previously added was
emitting a lot of logs. I had assumed incorrectly that `info` level
logging was disabled by default, but it's apparently enabled for this
crate. This is resulting in large logs (hundreds of MB) for some users.
## Summary
- change compaction pre-check accounting to include all items added
after the last model-generated item, not only trailing codex-generated
outputs
- use that boundary consistently in get_total_token_usage() and
get_total_token_usage_breakdown()
- update history tests to cover user/tool-output items after the last
model item
## Why
last_token_usage.total_tokens is API-reported for the last successful
model response. After that point, local history may gain additional
items (user messages, injected context, tool outputs). Compaction
triggering must account for all of those items to avoid late compaction
attempts that can overflow context.
## Testing
- just fmt
- cargo test -p codex-core
We support requirements on Unix, loading from
`/etc/codex/requirements.toml`. On MacOS, we also support MDM.
Now, on Windows, we'll load requirements from
`%ProgramData%\OpenAI\Codex\requirements.toml`
With this PR we do not close the unified exec processes (i.e. background
terminals) at the end of a turn unless:
* The user interrupt the turn
* The user decide to clean the processes through `app-server` or
`/clean`
I made sure that `codex exec` correctly kill all the processes
This PR adds the following field to `Config`:
```rust
pub network: Option<NetworkProxy>,
```
Though for the moment, it will always be initialized as `None` (this
will be addressed in a subsequent PR).
This PR does the work to thread `network` through to `execute_exec_env()`, `process_exec_tool_call()`, and `UnifiedExecRuntime.run()` to ensure it is available whenever we span a process.
There are two concepts of apps that we load in the harness:
- Directory apps, which is all the apps that the user can install.
- Accessible apps, which is what the user actually installed and can be
$ inserted and be used by the model. These are extracted from the tools
that are loaded through the gateway MCP.
Previously we wait for both sets of apps before returning the full apps
list. Which causes many issues because accessible apps won't be
available to the UI or the model if directory apps aren't loaded or
failed to load.
In this PR we are separating them so that accessible apps can be loaded
separately and are instantly available to be shown in the UI and to be
provided in model context. We also added an app-server event so that
clients can subscribe to also get accessible apps without being blocked
on the full app list.
- [x] Separate accessible apps and directory apps loading.
- [x] `app/list` request will also emit `app/list/updated` notifications
that app-server clients can subscribe. Which allows clients to get
accessible apps list to render in the $ menu without being blocked by
directory apps.
- [x] Cache both accessible and directory apps with 1 hour TTL to avoid
reloading them when creating new threads.
- [x] TUI improvements to redraw $ menu and /apps menu when app list is
updated.
If `NetworkConstraints` is set, then include the relevant settings on `<environment_context>`. Example:
```xml
<environment_context>
<cwd>/repo</cwd>
<shell>bash</shell>
<network enabled="true">
<allowed>api.example.com</allowed>
<allowed>*.openai.com</allowed>
<denied>blocked.example.com</denied>
</network>
</environment_context>
```
- Plumb input modalities from model catalog through the openai model
protocol. Default to text and image.
- Conditionally add the view_image tool only if input modalities support
image.
- Defer rollout persistence for fresh threads (`InitialHistory::New`):
keep rollout events in memory and only materialize rollout file + state
DB row on first `EventMsg::UserMessage`.
- Keep precomputed rollout path available before materialization.
- Change `thread/start` to build thread response from live config
snapshot and optional precomputed path.
- Improve pre-materialization behavior in app-server/TUI: clearer
invalid-request errors for file-backed ops and a friendlier `/fork` “not
ready yet” UX.
- Update tests to match deferred semantics across
start/read/archive/unarchive/fork/resume/review flows.
- Improved resilience of user_shell test, which should be unrelated to
this change but must be affected by timing changes
For Reviewers:
* The primary change is in recorder.rs
* Most of the other changes were to fix up broken assumptions in
existing tests
Testing:
* Manually tested CLI
* Exercised app server paths by manually running IDE Extension with
rebuilt CLI binary
* Only user-visible change is that `/fork` in TUI generates visible
error if used prior to first turn
