## Summary
- Moves the existing `codex-cloud-requirements` crate to
`codex-cloud-config`.
- Updates workspace dependencies and imports to the new crate name.
- Intentionally keeps runtime behavior unchanged: this still fetches the
legacy cloud requirements endpoint.
## Details
This PR exists to make the lineage obvious before the bundle migration.
GitHub should show the old `codex-rs/cloud-requirements/src/lib.rs`
implementation as moved to `codex-rs/cloud-config/src/lib.rs`, rather
than as unrelated new code.
The follow-up PR adapts this moved crate to the new config bundle API
and switches runtime consumers over.
## Why
This is the configuration/model half of the alternative permissions
migration we discussed as a comparison point for
[#22401](https://github.com/openai/codex/pull/22401) and
[#22402](https://github.com/openai/codex/pull/22402).
The old `workspace-write` model mixes three concerns that we want to
keep separate:
- reusable profile rules that should stay immutable once selected
- user/runtime workspace roots from `cwd`, `--add-dir`, and legacy
workspace-write config
- internal Codex writable roots such as memories, which should not be
shown as user workspace roots
This PR gives permission profiles first-class `workspace_roots` so users
can opt multiple repositories into the same `:workspace_roots` rules
without using broad absolute-path write grants. It also starts
separating the raw selected profile from the effective runtime profile
by making `Permissions` expose explicit accessors instead of public
mutable fields.
A representative `config.toml` looks like this:
```toml
default_permissions = "dev"
[permissions.dev.workspace_roots]
"~/code/openai" = true
"~/code/developers-website" = true
[permissions.dev.filesystem.":workspace_roots"]
"." = "write"
".codex" = "read"
".git" = "read"
".vscode" = "read"
```
If Codex starts in `~/code/codex` with that profile selected, the
effective workspace-root set becomes:
- `~/code/codex` from the runtime `cwd`
- `~/code/openai` from the profile
- `~/code/developers-website` from the profile
The `:workspace_roots` rules are materialized across each root, so
`.git`, `.codex`, and `.vscode` stay scoped the same way everywhere.
Runtime additions such as `--add-dir` can still layer on later stack
entries without mutating the selected profile.
## Stack Shape
This PR intentionally stops before the profile-identity cleanup in
[#22683](https://github.com/openai/codex/pull/22683) so the base review
stays focused on config loading, workspace-root materialization, and
compatibility with legacy `workspace-write`.
The representation in this PR is therefore transitional: `Permissions`
carries enough state to distinguish the raw constrained profile from the
effective runtime profile, and there are still call sites that must keep
the active profile identity and constrained profile value in sync. The
follow-up PR replaces that with a single resolved profile state
(`ResolvedPermissionProfile` / `PermissionProfileState`) that keeps the
profile id, immutable `PermissionProfile`, and profile-declared
workspace roots together. That follow-up removes APIs such as
`set_constrained_permission_profile_with_active_profile()` where
separate arguments could drift out of sync.
Downstream PRs then build on this base to switch app-server turn updates
to profile ids plus runtime workspace roots and to finish the
user-visible summary behavior. Reviewers should judge this PR as the
workspace-roots foundation, not as the final in-memory shape of selected
permission profiles.
## Review Guide
Suggested review order:
1. Start with `codex-rs/core/src/config/mod.rs`.
This is the main shape change in the base slice. `Permissions` now
stores a private raw `Constrained<PermissionProfile>` plus runtime
`workspace_roots`. Callers use `permission_profile()` when they need the
raw constrained value and `effective_permission_profile()` when they
need a materialized runtime profile. As noted above,
[#22683](https://github.com/openai/codex/pull/22683) replaces this
transitional shape with a resolved profile state that keeps identity and
profile data together.
2. Review `codex-rs/config/src/permissions_toml.rs` and
`codex-rs/core/src/config/permissions.rs`.
These add `[permissions.<id>.workspace_roots]`, resolve enabled entries
relative to the policy cwd, and keep `:workspace_roots` deny-read glob
patterns symbolic until the actual roots are known.
3. Review `codex-rs/protocol/src/permissions.rs` and
`codex-rs/protocol/src/models.rs`.
These add the policy/profile materialization helpers that expand exact
`:workspace_roots` entries and scoped deny-read globs over every
workspace root. This is also where `ActivePermissionProfileModification`
is removed from the core model.
4. Review the legacy bridge in
`Config::load_from_base_config_with_overrides` and
`Config::set_legacy_sandbox_policy`.
This is where legacy `workspace-write` roots become runtime workspace
roots, while Codex internal writable roots stay internal and do not
appear as user-facing workspace roots.
5. Then skim downstream call sites.
The interesting pattern is raw-vs-effective access: state/proxy/bwrap
paths keep the raw constrained profile, while execution, summaries, and
user-visible status use the effective profile and workspace-root list.
## What Changed
- added `[permissions.<id>.workspace_roots]` to the config model and
schema
- added runtime `workspace_roots` state to `Config`/`Permissions` and
`ConfigOverrides`
- made `Permissions` profile fields private and replaced direct mutation
with accessors/setters
- added `PermissionProfile` and `FileSystemSandboxPolicy` helpers for
materializing `:workspace_roots` exact paths and deny-read globs across
all roots
- moved legacy additional writable roots into runtime workspace-root
state instead of active profile modifications
- removed `ActivePermissionProfileModification` and its app-server
protocol/schema export
- updated sandbox/status summary paths so internal writable roots are
not reported as user workspace roots
## Verification Strategy
The targeted tests cover the behavior at the layers where regressions
are most likely:
- `codex-rs/core/src/config/config_tests.rs` verifies config loading,
legacy workspace-root seeding, effective profile materialization, and
memory-root handling.
- `codex-rs/core/src/config/permissions_tests.rs` verifies profile
`workspace_roots` parsing and `:workspace_roots` scoped/glob
compilation.
- `codex-rs/protocol/src/permissions.rs` unit tests verify exact and
glob materialization over multiple workspace roots.
- `codex-rs/tui/src/status/tests.rs` and
`codex-rs/utils/sandbox-summary/src/sandbox_summary.rs` verify the
user-facing summaries show effective workspace roots and hide internal
writes.
I also ran `cargo check --tests` locally after the latest stack refresh
to catch cross-crate API breakage from the private-field/accessor
changes.
---
[//]: # (BEGIN SAPLING FOOTER)
Stack created with [Sapling](https://sapling-scm.com). Best reviewed
with [ReviewStack](https://reviewstack.dev/openai/codex/pull/22610).
* #22612
* #22611
* #22683
* __->__ #22610
## Summary
`cargo test` has entails both running standard Rust tests and doctests.
It turns out that the doctest discovery is fairly slow, and it's a cost
you pay even for crates that don't include any doctests.
This PR disables doctests with `doctest = false` for crates that lack
any doctests.
For the collection of crates below, this speeds up test execution by
>4x.
E.g., before this PR:
```
Benchmark 1: cargo test -p codex-utils-absolute-path -p codex-utils-cache -p codex-utils-cli -p codex-utils-home-dir -p codex-utils-output-truncation -p codex-utils-path -p codex-utils-string -p codex-utils-template -p codex-utils-elapsed -p codex-utils-json-to-toml
Time (mean ± σ): 1.849 s ± 4.455 s [User: 0.752 s, System: 1.367 s]
Range (min … max): 0.418 s … 14.529 s 10 runs
```
And after:
```
Benchmark 1: cargo test -p codex-utils-absolute-path -p codex-utils-cache -p codex-utils-cli -p codex-utils-home-dir -p codex-utils-output-truncation -p codex-utils-path -p codex-utils-string -p codex-utils-template -p codex-utils-elapsed -p codex-utils-json-to-toml
Time (mean ± σ): 428.6 ms ± 6.9 ms [User: 187.7 ms, System: 219.7 ms]
Range (min … max): 418.0 ms … 436.8 ms 10 runs
```
For a single crate, with >2x speedup, before:
```
Benchmark 1: cargo test -p codex-utils-string
Time (mean ± σ): 491.1 ms ± 9.0 ms [User: 229.8 ms, System: 234.9 ms]
Range (min … max): 480.9 ms … 512.0 ms 10 runs
```
And after:
```
Benchmark 1: cargo test -p codex-utils-string
Time (mean ± σ): 213.9 ms ± 4.3 ms [User: 112.8 ms, System: 84.0 ms]
Range (min … max): 206.8 ms … 221.0 ms 13 runs
```
Co-authored-by: Codex <noreply@openai.com>
## 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.
Stacked on #16508.
This removes the temporary `codex-core` / `codex-login` re-export shims
from the ownership split and rewrites callsites to import directly from
`codex-model-provider-info`, `codex-models-manager`, `codex-api`,
`codex-protocol`, `codex-feedback`, and `codex-response-debug-context`.
No behavior change intended; this is the mechanical import cleanup layer
split out from the ownership move.
---------
Co-authored-by: Codex <noreply@openai.com>
## Why
`codex-core` was re-exporting APIs owned by sibling `codex-*` crates,
which made downstream crates depend on `codex-core` as a proxy module
instead of the actual owner crate.
Removing those forwards makes crate boundaries explicit and lets leaf
crates drop unnecessary `codex-core` dependencies. In this PR, this
reduces the dependency on `codex-core` to `codex-login` in the following
files:
```
codex-rs/backend-client/Cargo.toml
codex-rs/mcp-server/tests/common/Cargo.toml
```
## What
- Remove `codex-rs/core/src/lib.rs` re-exports for symbols owned by
`codex-login`, `codex-mcp`, `codex-rollout`, `codex-analytics`,
`codex-protocol`, `codex-shell-command`, `codex-sandboxing`,
`codex-tools`, and `codex-utils-path`.
- Delete the `default_client` forwarding shim in `codex-rs/core`.
- Update in-crate and downstream callsites to import directly from the
owning `codex-*` crate.
- Add direct Cargo dependencies where callsites now target the owner
crate, and remove `codex-core` from `codex-rs/backend-client`.
- create `codex-git-utils` and move the shared git helpers into it with
file moves preserved for diff readability
- move the `GitInfo` helpers out of `core` so stacked rollout work can
depend on the shared crate without carrying its own git info module
---------
Co-authored-by: Ahmed Ibrahim <219906144+aibrahim-oai@users.noreply.github.com>
Co-authored-by: Codex <noreply@openai.com>
This PR completes the conversion of non-interactive `codex exec` to use
app server rather than directly using core events and methods.
### Summary
- move `codex-exec` off exec-owned `AuthManager` and `ThreadManager`
state
- route exec bootstrap, resume, and auth refresh through existing
app-server paths
- replace legacy `codex/event/*` decoding in exec with typed app-server
notification handling
- update human and JSONL exec output adapters to translate existing
app-server notifications only
- clean up "app server client" layer by eliminating support for legacy
notifications; this is no longer needed
- remove exposure of `authManager` and `threadManager` from "app server
client" layer
### Testing
- `exec` has pretty extensive unit and integration tests already, and
these all pass
- In addition, I asked Codex to put together a comprehensive manual set
of tests to cover all of the `codex exec` functionality (including
command-line options), and it successfully generated and ran these tests
This is a subset of PR #13636. See that PR for a full overview of the
architectural change.
This PR implements the in-process app server and modifies the
non-interactive "exec" entry point to use the app server.
---------
Co-authored-by: Felipe Coury <felipe.coury@gmail.com>
### Summary
Propagate trace context originating at app-server RPC method handlers ->
codex core submission loop (so this includes spans such as `run_turn`!).
This implements PR 2 of the app-server tracing rollout.
This also removes the old lower-level env-based reparenting in core so
explicit request/submission ancestry wins instead of being overridden by
ambient `TRACEPARENT` state.
### What changed
- Added `trace: Option<W3cTraceContext>` to codex_protocol::Submission
- Taught `Codex::submit()` / `submit_with_id()` to automatically capture
the current span context when constructing or forwarding a submission
- Wrapped the core submission loop in a submission_dispatch span
parented from Submission.trace
- Warn on invalid submission trace carriers and ignore them cleanly
- Removed the old env-based downstream reparenting path in core task
execution
- Stopped OTEL provider init from implicitly attaching env trace context
process-wide
- Updated mcp-server Submission call sites for the new field
Added focused unit tests for:
- capturing trace context into Submission
- preferring `Submission.trace` when building the core dispatch span
### Why
PR 1 gave us consistent inbound request spans in app-server, but that
only covered the transport boundary. For long-running work like turns
and reviews, the important missing piece was preserving ancestry after
the request handler returns and core continues work on a different async
path.
This change makes that handoff explicit and keeps the parentage rules
simple:
- app-server request span sets the current context
- `Submission.trace` snapshots that context
- core restores it once, at the submission boundary
- deeper core spans inherit naturally
That also lets us stop relying on env-based reparenting for this path,
which was too ambient and could override explicit ancestry.
## Why
`codex-rs/arg0` only needed two things from `codex-core`:
- the `find_codex_home()` wrapper
- the special argv flag used for the internal `apply_patch`
self-invocation path
That made `codex-arg0` depend on `codex-core` for a very small surface
area. This change removes that dependency edge and moves the shared
`apply_patch` invocation flag to a more natural boundary
(`codex-apply-patch`) while keeping the contract explicitly documented.
## What Changed
- Moved the internal `apply_patch` argv[1] flag constant out of
`codex-core` and into `codex-apply-patch`.
- Renamed the constant to `CODEX_CORE_APPLY_PATCH_ARG1` and documented
that it is part of the Codex core process-invocation contract (even
though it now lives in `codex-apply-patch`).
- Updated `arg0`, the core apply-patch runtime, and the `codex-exec`
apply-patch test to import the constant from `codex-apply-patch`.
- Updated `codex-rs/arg0` to call
`codex_utils_home_dir::find_codex_home()` directly instead of
`codex_core::config::find_codex_home()`.
- Removed the `codex-core` dependency from `codex-rs/arg0` and added the
needed direct dependency on `codex-utils-home-dir`.
- Added `codex-apply-patch` as a dev-dependency for `codex-rs/exec`
tests (the apply-patch test now imports the moved constant directly).
## Verification
- `cargo test -p codex-apply-patch`
- `cargo test -p codex-arg0`
- `cargo test -p codex-core --lib apply_patch`
- `cargo test -p codex-exec
test_standalone_exec_cli_can_use_apply_patch`
- `cargo shear`
We are removing feature-gated shared crates from the `codex-rs`
workspace. `codex-common` grouped several unrelated utilities behind
`[features]`, which made dependency boundaries harder to reason about
and worked against the ongoing effort to eliminate feature flags from
workspace crates.
Splitting these utilities into dedicated crates under `utils/` aligns
this area with existing workspace structure and keeps each dependency
explicit at the crate boundary.
## What changed
- Removed `codex-rs/common` (`codex-common`) from workspace members and
workspace dependencies.
- Added six new utility crates under `codex-rs/utils/`:
- `codex-utils-cli`
- `codex-utils-elapsed`
- `codex-utils-sandbox-summary`
- `codex-utils-approval-presets`
- `codex-utils-oss`
- `codex-utils-fuzzy-match`
- Migrated the corresponding modules out of `codex-common` into these
crates (with tests), and added matching `BUILD.bazel` targets.
- Updated direct consumers to use the new crates instead of
`codex-common`:
- `codex-rs/cli`
- `codex-rs/tui`
- `codex-rs/exec`
- `codex-rs/app-server`
- `codex-rs/mcp-server`
- `codex-rs/chatgpt`
- `codex-rs/cloud-tasks`
- Updated workspace lockfile entries to reflect the new dependency graph
and removal of `codex-common`.
We started working with MCP in Codex before
https://crates.io/crates/rmcp was mature, so we had our own crate for
MCP types that was generated from the MCP schema:
https://github.com/openai/codex/blob/8b95d3e082376f4cb23e92641705a22afb28a9da/codex-rs/mcp-types/README.md
Now that `rmcp` is more mature, it makes more sense to use their MCP
types in Rust, as they handle details (like the `_meta` field) that our
custom version ignored. Though one advantage that our custom types had
is that our generated types implemented `JsonSchema` and `ts_rs::TS`,
whereas the types in `rmcp` do not. As such, part of the work of this PR
is leveraging the adapters between `rmcp` types and the serializable
types that are API for us (app server and MCP) introduced in #10356.
Note this PR results in a number of changes to
`codex-rs/app-server-protocol/schema`, which merit special attention
during review. We must ensure that these changes are still
backwards-compatible, which is possible because we have:
```diff
- export type CallToolResult = { content: Array<ContentBlock>, isError?: boolean, structuredContent?: JsonValue, };
+ export type CallToolResult = { content: Array<JsonValue>, structuredContent?: JsonValue, isError?: boolean, _meta?: JsonValue, };
```
so `ContentBlock` has been replaced with the more general `JsonValue`.
Note that `ContentBlock` was defined as:
```typescript
export type ContentBlock = TextContent | ImageContent | AudioContent | ResourceLink | EmbeddedResource;
```
so the deletion of those individual variants should not be a cause of
great concern.
Similarly, we have the following change in
`codex-rs/app-server-protocol/schema/typescript/Tool.ts`:
```
- export type Tool = { annotations?: ToolAnnotations, description?: string, inputSchema: ToolInputSchema, name: string, outputSchema?: ToolOutputSchema, title?: string, };
+ export type Tool = { name: string, title?: string, description?: string, inputSchema: JsonValue, outputSchema?: JsonValue, annotations?: JsonValue, icons?: Array<JsonValue>, _meta?: JsonValue, };
```
so:
- `annotations?: ToolAnnotations` ➡️ `JsonValue`
- `inputSchema: ToolInputSchema` ➡️ `JsonValue`
- `outputSchema?: ToolOutputSchema` ➡️ `JsonValue`
and two new fields: `icons?: Array<JsonValue>, _meta?: JsonValue`
---
[//]: # (BEGIN SAPLING FOOTER)
Stack created with [Sapling](https://sapling-scm.com). Best reviewed
with [ReviewStack](https://reviewstack.dev/openai/codex/pull/10349).
* #10357
* __->__ #10349
* #10356
Session renaming:
- `/rename my_session`
- `/rename` without arg and passing an argument in `customViewPrompt`
- AppExitInfo shows resume hint using the session name if set instead of
uuid, defaults to uuid if not set
- Names are stored in `CODEX_HOME/sessions.jsonl`
Session resuming:
- codex resume <name> lookup for `CODEX_HOME/sessions.jsonl` first entry
matching the name and resumes the session
---------
Co-authored-by: jif-oai <jif@openai.com>
This PR introduces a `codex-utils-cargo-bin` utility crate that
wraps/replaces our use of `assert_cmd::Command` and
`escargot::CargoBuild`.
As you can infer from the introduction of `buck_project_root()` in this
PR, I am attempting to make it possible to build Codex under
[Buck2](https://buck2.build) as well as `cargo`. With Buck2, I hope to
achieve faster incremental local builds (largely due to Buck2's
[dice](https://buck2.build/docs/insights_and_knowledge/modern_dice/)
build strategy, as well as benefits from its local build daemon) as well
as faster CI builds if we invest in remote execution and caching.
See
https://buck2.build/docs/getting_started/what_is_buck2/#why-use-buck2-key-advantages
for more details about the performance advantages of Buck2.
Buck2 enforces stronger requirements in terms of build and test
isolation. It discourages assumptions about absolute paths (which is key
to enabling remote execution). Because the `CARGO_BIN_EXE_*` environment
variables that Cargo provides are absolute paths (which
`assert_cmd::Command` reads), this is a problem for Buck2, which is why
we need this `codex-utils-cargo-bin` utility.
My WIP-Buck2 setup sets the `CARGO_BIN_EXE_*` environment variables
passed to a `rust_test()` build rule as relative paths.
`codex-utils-cargo-bin` will resolve these values to absolute paths,
when necessary.
---
[//]: # (BEGIN SAPLING FOOTER)
Stack created with [Sapling](https://sapling-scm.com). Best reviewed
with [ReviewStack](https://reviewstack.dev/openai/codex/pull/8496).
* #8498
* __->__ #8496
Changes the `writable_roots` field of the `WorkspaceWrite` variant of
the `SandboxPolicy` enum from `Vec<PathBuf>` to `Vec<AbsolutePathBuf>`.
This is helpful because now callers can be sure the value is an absolute
path rather than a relative one. (Though when using an absolute path in
a Seatbelt config policy, we still have to _canonicalize_ it first.)
Because `writable_roots` can be read from a config file, it is important
that we are able to resolve relative paths properly using the parent
folder of the config file as the base path.
## Overview
Adds LM Studio OSS support. Closes#1883
### Changes
This PR enhances the behavior of `--oss` flag to support LM Studio as a
provider. Additionally, it introduces a new flag`--local-provider` which
can take in `lmstudio` or `ollama` as values if the user wants to
explicitly choose which one to use.
If no provider is specified `codex --oss` will auto-select the provider
based on whichever is running.
#### Additional enhancements
The default can be set using `oss-provider` in config like:
```
oss_provider = "lmstudio"
```
For non-interactive users, they will need to either provide the provider
as an arg or have it in their `config.toml`
### Notes
For best performance, [set the default context
length](https://lmstudio.ai/docs/app/advanced/per-model) for gpt-oss to
the maximum your machine can support
---------
Co-authored-by: Matt Clayton <matt@lmstudio.ai>
Co-authored-by: Eric Traut <etraut@openai.com>
### Title
## otel
Codex can emit [OpenTelemetry](https://opentelemetry.io/) **log events**
that
describe each run: outbound API requests, streamed responses, user
input,
tool-approval decisions, and the result of every tool invocation. Export
is
**disabled by default** so local runs remain self-contained. Opt in by
adding an
`[otel]` table and choosing an exporter.
```toml
[otel]
environment = "staging" # defaults to "dev"
exporter = "none" # defaults to "none"; set to otlp-http or otlp-grpc to send events
log_user_prompt = false # defaults to false; redact prompt text unless explicitly enabled
```
Codex tags every exported event with `service.name = "codex-cli"`, the
CLI
version, and an `env` attribute so downstream collectors can distinguish
dev/staging/prod traffic. Only telemetry produced inside the
`codex_otel`
crate—the events listed below—is forwarded to the exporter.
### Event catalog
Every event shares a common set of metadata fields: `event.timestamp`,
`conversation.id`, `app.version`, `auth_mode` (when available),
`user.account_id` (when available), `terminal.type`, `model`, and
`slug`.
With OTEL enabled Codex emits the following event types (in addition to
the
metadata above):
- `codex.api_request`
- `cf_ray` (optional)
- `attempt`
- `duration_ms`
- `http.response.status_code` (optional)
- `error.message` (failures)
- `codex.sse_event`
- `event.kind`
- `duration_ms`
- `error.message` (failures)
- `input_token_count` (completion only)
- `output_token_count` (completion only)
- `cached_token_count` (completion only, optional)
- `reasoning_token_count` (completion only, optional)
- `tool_token_count` (completion only)
- `codex.user_prompt`
- `prompt_length`
- `prompt` (redacted unless `log_user_prompt = true`)
- `codex.tool_decision`
- `tool_name`
- `call_id`
- `decision` (`approved`, `approved_for_session`, `denied`, or `abort`)
- `source` (`config` or `user`)
- `codex.tool_result`
- `tool_name`
- `call_id`
- `arguments`
- `duration_ms` (execution time for the tool)
- `success` (`"true"` or `"false"`)
- `output`
### Choosing an exporter
Set `otel.exporter` to control where events go:
- `none` – leaves instrumentation active but skips exporting. This is
the
default.
- `otlp-http` – posts OTLP log records to an OTLP/HTTP collector.
Specify the
endpoint, protocol, and headers your collector expects:
```toml
[otel]
exporter = { otlp-http = {
endpoint = "https://otel.example.com/v1/logs",
protocol = "binary",
headers = { "x-otlp-api-key" = "${OTLP_TOKEN}" }
}}
```
- `otlp-grpc` – streams OTLP log records over gRPC. Provide the endpoint
and any
metadata headers:
```toml
[otel]
exporter = { otlp-grpc = {
endpoint = "https://otel.example.com:4317",
headers = { "x-otlp-meta" = "abc123" }
}}
```
If the exporter is `none` nothing is written anywhere; otherwise you
must run or point to your
own collector. All exporters run on a background batch worker that is
flushed on
shutdown.
If you build Codex from source the OTEL crate is still behind an `otel`
feature
flag; the official prebuilt binaries ship with the feature enabled. When
the
feature is disabled the telemetry hooks become no-ops so the CLI
continues to
function without the extra dependencies.
---------
Co-authored-by: Anton Panasenko <apanasenko@openai.com>
This pull request add a new experimental format of JSON output.
You can try it using `codex exec --experimental-json`.
Design takes a lot of inspiration from Responses API items and stream
format.
# Session and items
Each invocation of `codex exec` starts or resumes a session.
Session contains multiple high-level item types:
1. Assistant message
2. Assistant thinking
3. Command execution
4. File changes
5. To-do lists
6. etc.
# Events
Session and items are going through their life cycles which is
represented by events.
Session is `session.created` or `session.resumed`
Items are `item.added`, `item.updated`, `item.completed`,
`item.require_approval` (or other item types like `item.output_delta`
when we need streaming).
So a typical session can look like:
<details>
```
{
"type": "session.created",
"session_id": "01997dac-9581-7de3-b6a0-1df8256f2752"
}
{
"type": "item.completed",
"item": {
"id": "itm_0",
"item_type": "assistant_message",
"text": "I’ll locate the top-level README and remove its first line. Then I’ll show a quick summary of what changed."
}
}
{
"type": "item.completed",
"item": {
"id": "itm_1",
"item_type": "command_execution",
"command": "bash -lc ls -la | sed -n '1,200p'",
"aggregated_output": "pyenv: cannot rehash: /Users/pakrym/.pyenv/shims isn't writable\ntotal 192\ndrwxr-xr-x@ 33 pakrym staff 1056 Sep 24 14:36 .\ndrwxr-xr-x 41 pakrym staff 1312 Sep 24 09:17 ..\n-rw-r--r--@ 1 pakrym staff 6 Jul 9 16:16 .codespellignore\n-rw-r--r--@ 1 pakrym staff 258 Aug 13 09:40 .codespellrc\ndrwxr-xr-x@ 5 pakrym staff 160 Jul 23 08:26 .devcontainer\n-rw-r--r--@ 1 pakrym staff 6148 Jul 22 10:03 .DS_Store\ndrwxr-xr-x@ 15 pakrym staff 480 Sep 24 14:38 .git\ndrwxr-xr-x@ 12 pakrym staff 384 Sep 2 16:00 .github\n-rw-r--r--@ 1 pakrym staff 778 Jul 9 16:16 .gitignore\ndrwxr-xr-x@ 3 pakrym staff 96 Aug 11 09:37 .husky\n-rw-r--r--@ 1 pakrym staff 104 Jul 9 16:16 .npmrc\n-rw-r--r--@ 1 pakrym staff 96 Sep 2 08:52 .prettierignore\n-rw-r--r--@ 1 pakrym staff 170 Jul 9 16:16 .prettierrc.toml\ndrwxr-xr-x@ 5 pakrym staff 160 Sep 14 17:43 .vscode\ndrwxr-xr-x@ 2 pakrym staff 64 Sep 11 11:37 2025-09-11\n-rw-r--r--@ 1 pakrym staff 5505 Sep 18 09:28 AGENTS.md\n-rw-r--r--@ 1 pakrym staff 92 Sep 2 08:52 CHANGELOG.md\n-rw-r--r--@ 1 pakrym staff 1145 Jul 9 16:16 cliff.toml\ndrwxr-xr-x@ 11 pakrym staff 352 Sep 24 13:03 codex-cli\ndrwxr-xr-x@ 38 pakrym staff 1216 Sep 24 14:38 codex-rs\ndrwxr-xr-x@ 18 pakrym staff 576 Sep 23 11:01 docs\n-rw-r--r--@ 1 pakrym staff 2038 Jul 9 16:16 flake.lock\n-rw-r--r--@ 1 pakrym staff 1434 Jul 9 16:16 flake.nix\n-rw-r--r--@ 1 pakrym staff 10926 Jul 9 16:16 LICENSE\ndrwxr-xr-x@ 465 pakrym staff 14880 Jul 15 07:36 node_modules\n-rw-r--r--@ 1 pakrym staff 242 Aug 5 08:25 NOTICE\n-rw-r--r--@ 1 pakrym staff 578 Aug 14 12:31 package.json\n-rw-r--r--@ 1 pakrym staff 498 Aug 11 09:37 pnpm-lock.yaml\n-rw-r--r--@ 1 pakrym staff 58 Aug 11 09:37 pnpm-workspace.yaml\n-rw-r--r--@ 1 pakrym staff 2402 Jul 9 16:16 PNPM.md\n-rw-r--r--@ 1 pakrym staff 4393 Sep 12 14:36 README.md\ndrwxr-xr-x@ 4 pakrym staff 128 Sep 18 09:28 scripts\ndrwxr-xr-x@ 2 pakrym staff 64 Sep 11 11:34 tmp\n",
"exit_code": 0,
"status": "completed"
}
}
{
"type": "item.completed",
"item": {
"id": "itm_2",
"item_type": "reasoning",
"text": "**Reviewing README.md file**\n\nI've located the README.md file at the root, and it’s 4393 bytes. Now, I need to remove the first line, but first, I should check its content to make sure I’m patching it correctly. I’ll use sed to display the first 20 lines. By reviewing those lines, I can determine exactly what needs to be removed before I proceed with the editing. Let's do this carefully!"
}
}
{
"type": "item.completed",
"item": {
"id": "itm_3",
"item_type": "command_execution",
"command": "bash -lc sed -n '1,40p' README.md",
"aggregated_output": "<h1 align=\"center\">OpenAI Codex CLI</h1>\n\n<p align=\"center\"><code>npm i -g @openai/codex</code><br />or <code>brew install codex</code></p>\n\n<p align=\"center\"><strong>Codex CLI</strong> is a coding agent from OpenAI that runs locally on your computer.\n</br>\n</br>If you want Codex in your code editor (VS Code, Cursor, Windsurf), <a href=\"https://developers.openai.com/codex/ide\">install in your IDE</a>\n</br>If you are looking for the <em>cloud-based agent</em> from OpenAI, <strong>Codex Web</strong>, go to <a href=\"https://chatgpt.com/codex\">chatgpt.com/codex</a></p>\n\n<p align=\"center\">\n <img src=\"./.github/codex-cli-splash.png\" alt=\"Codex CLI splash\" width=\"80%\" />\n </p>\n\n---\n\n## Quickstart\n\n### Installing and running Codex CLI\n\nInstall globally with your preferred package manager. If you use npm:\n\n```shell\nnpm install -g @openai/codex\n```\n\nAlternatively, if you use Homebrew:\n\n```shell\nbrew install codex\n```\n\nThen simply run `codex` to get started:\n\n```shell\ncodex\n```\n\n<details>\n<summary>You can also go to the <a href=\"https://github.com/openai/codex/releases/latest\">latest GitHub Release</a> and download the appropriate binary for your platform.</summary>\n\n",
"exit_code": 0,
"status": "completed"
}
}
{
"type": "item.completed",
"item": {
"id": "itm_4",
"item_type": "reasoning",
"text": "**Updating README file**\n\nThe user wants to update the README by removing the first line, which is an HTML h1 tag. I'll proceed to delete that line while keeping the rest intact. To do this, I need to use the apply_patch tool and create a patch in the diff format. I’ll take care to include context lines around the change. After removing the header, I’m considering whether to delete the following blank line as well to keep it tidy."
}
}
{
"type": "item.completed",
"item": {
"id": "itm_5",
"item_type": "reasoning",
"text": "**Crafting the patch**\n\nThe user has asked to remove just the first line, without mentioning the blank lines. Technically, leaving a blank line at the start is acceptable, but it's not ideal. Ideally, I'd prefer to remove the first line while maintaining the subsequent blank line. However, if I can also remove that blank line, it could tidy things up even more. Still, since the user's request is strictly to remove only the first line, I'll stick to that and craft the patch accordingly."
}
}
{
"type": "item.completed",
"item": {
"id": "itm_6",
"item_type": "assistant_message",
"text": "Applying the change by removing the first line from `README.md`."
}
}
{
"type": "item.completed",
"item": {
"id": "itm_7",
"item_type": "file_change",
"changes": [
{
"path": "/Users/pakrym/code/codex/README.md",
"kind": "update"
}
],
"status": "completed"
}
}
{
"type": "item.completed",
"item": {
"id": "itm_8",
"item_type": "reasoning",
"text": "**Validating README Update**\n\nI updated the README.md and now I need to validate that the first line has been successfully removed. To do this, I'll check the first 10 lines of the document to ensure everything looks correct. It’s always good to double-check these kinds of changes, so I’m going to take that extra step to make sure the update was executed properly. Let's see what those initial lines say!"
}
}
{
"type": "item.completed",
"item": {
"id": "itm_9",
"item_type": "command_execution",
"command": "bash -lc sed -n '1,20p' README.md",
"aggregated_output": "\n<p align=\"center\"><code>npm i -g @openai/codex</code><br />or <code>brew install codex</code></p>\n\n<p align=\"center\"><strong>Codex CLI</strong> is a coding agent from OpenAI that runs locally on your computer.\n</br>\n</br>If you want Codex in your code editor (VS Code, Cursor, Windsurf), <a href=\"https://developers.openai.com/codex/ide\">install in your IDE</a>\n</br>If you are looking for the <em>cloud-based agent</em> from OpenAI, <strong>Codex Web</strong>, go to <a href=\"https://chatgpt.com/codex\">chatgpt.com/codex</a></p>\n\n<p align=\"center\">\n <img src=\"./.github/codex-cli-splash.png\" alt=\"Codex CLI splash\" width=\"80%\" />\n </p>\n\n---\n\n## Quickstart\n\n### Installing and running Codex CLI\n\nInstall globally with your preferred package manager. If you use npm:\n\n",
"exit_code": 0,
"status": "completed"
}
}
{
"type": "item.completed",
"item": {
"id": "itm_10",
"item_type": "assistant_message",
"text": "- Updated `README.md:1` by removing the opening H1 line.\n- The README now starts with the install instructions paragraph.\n\nWant me to also remove the leading blank line at the top?"
}
}
```
</details>
The idea is to give users fully formatted items they can use directly in
their rendering/application logic and avoid having them building up
items manually based on events (unless they want to for streaming).
This PR implements only the `item.completed` payload for some event
types, more event types and item types to come.
---------
Co-authored-by: Michael Bolin <mbolin@openai.com>
Adding the ability to resume conversations.
we have one verb `resume`.
Behavior:
`tui`:
`codex resume`: opens session picker
`codex resume --last`: continue last message
`codex resume <session id>`: continue conversation with `session id`
`exec`:
`codex resume --last`: continue last conversation
`codex resume <session id>`: continue conversation with `session id`
Implementation:
- I added a function to find the path in `~/.codex/sessions/` with a
`UUID`. This is helpful in resuming with session id.
- Added the above mentioned flags
- Added lots of testing
This PR adds a central `AuthManager` struct that manages the auth
information used across conversations and the MCP server. Prior to this,
each conversation and the MCP server got their own private snapshots of
the auth information, and changes to one (such as a logout or token
refresh) were not seen by others.
This is especially problematic when multiple instances of the CLI are
run. For example, consider the case where you start CLI 1 and log in to
ChatGPT account X and then start CLI 2 and log out and then log in to
ChatGPT account Y. The conversation in CLI 1 is still using account X,
but if you create a new conversation, it will suddenly (and
unexpectedly) switch to account Y.
With the `AuthManager`, auth information is read from disk at the time
the `ConversationManager` is constructed, and it is cached in memory.
All new conversations use this same auth information, as do any token
refreshes.
The `AuthManager` is also used by the MCP server's GetAuthStatus
command, which now returns the auth method currently used by the MCP
server.
This PR also includes an enhancement to the GetAuthStatus command. It
now accepts two new (optional) input parameters: `include_token` and
`refresh_token`. Callers can use this to request the in-use auth token
and can optionally request to refresh the token.
The PR also adds tests for the login and auth APIs that I recently added
to the MCP server.
The existing `wire_format.rs` should share more types with the
`codex-protocol` crate (like `AskForApproval` instead of maintaining a
parallel `CodexToolCallApprovalPolicy` enum), so this PR moves
`wire_format.rs` into `codex-protocol`, renaming it as
`mcp-protocol.rs`. We also de-dupe types, where appropriate.
---
[//]: # (BEGIN SAPLING FOOTER)
Stack created with [Sapling](https://sapling-scm.com). Best reviewed
with [ReviewStack](https://reviewstack.dev/openai/codex/pull/2423).
* #2424
* __->__ #2423
## Summary
We've been seeing a number of issues and reports with our synthetic
`apply_patch` tool, e.g. #802. Let's make this a real tool - in my
anecdotal testing, it's critical for GPT-OSS models, but I'd like to
make it the standard across GPT-5 and codex models as well.
## Testing
- [x] Tested locally
- [x] Integration test
When using codex-tui on a linux system I was unable to run `cargo
clippy` inside of codex due to:
```
[pid 3548377] socketpair(AF_UNIX, SOCK_SEQPACKET|SOCK_CLOEXEC, 0, <unfinished ...>
[pid 3548370] close(8 <unfinished ...>
[pid 3548377] <... socketpair resumed>0x7ffb97f4ed60) = -1 EPERM (Operation not permitted)
```
And
```
3611300 <... recvfrom resumed>0x708b8b5cffe0, 8, 0, NULL, NULL) = -1 EPERM (Operation not permitted)
```
This PR:
* Fixes a bug that disallowed AF_UNIX to allow it on `socket()`
* Adds recvfrom() to the syscall allow list, this should be fine since
we disable opening new sockets. But we should validate there is not a
open socket inheritance issue.
* Allow socketpair to be called for AF_UNIX
* Adds tests for AF_UNIX components
* All of which allows running `cargo clippy` within the sandbox on
linux, and possibly other tooling using a fork server model + AF_UNIX
comms.
This adds support for easily running Codex backed by a local Ollama
instance running our new open source models. See
https://github.com/openai/gpt-oss for details.
If you pass in `--oss` you'll be prompted to install/launch ollama, and
it will automatically download the 20b model and attempt to use it.
We'll likely want to expand this with some options later to make the
experience smoother for users who can't run the 20b or want to run the
120b.
Co-authored-by: Michael Bolin <mbolin@openai.com>
This introduces some special behavior to the CLIs that are using the
`codex-arg0` crate where if `arg1` is `--codex-run-as-apply-patch`, then
it will run as if `apply_patch arg2` were invoked. This is important
because it means we can do things like:
```
SANDBOX_TYPE=landlock # or seatbelt for macOS
codex debug "${SANDBOX_TYPE}" -- codex --codex-run-as-apply-patch PATCH
```
which gives us a way to run `apply_patch` while ensuring it adheres to
the sandbox the user specified.
While it would be nice to use the `arg0` trick like we are currently
doing for `codex-linux-sandbox`, there is no way to specify the `arg0`
for the underlying command when running under `/usr/bin/sandbox-exec`,
so it will not work for us in this case.
Admittedly, we could have also supported this via a custom environment
variable (e.g., `CODEX_ARG0`), but since environment variables are
inherited by child processes, that seemed like a potentially leakier
abstraction.
This change, as well as our existing reliance on checking `arg0`, place
additional requirements on those who include `codex-core`. Its
`README.md` has been updated to reflect this.
While we could have just added an `apply-patch` subcommand to the
`codex` multitool CLI, that would not be sufficient for the standalone
`codex-exec` CLI, which is something that we distribute as part of our
GitHub releases for those who know they will not be using the TUI and
therefore prefer to use a slightly smaller executable:
https://github.com/openai/codex/releases/tag/rust-v0.10.0
To that end, this PR adds an integration test to ensure that the
`--codex-run-as-apply-patch` option works with the standalone
`codex-exec` CLI.
---
[//]: # (BEGIN SAPLING FOOTER)
Stack created with [Sapling](https://sapling-scm.com). Best reviewed
with [ReviewStack](https://reviewstack.dev/openai/codex/pull/1702).
* #1705
* #1703
* __->__ #1702
* #1698
* #1697
Historically, we spawned the Seatbelt and Landlock sandboxes in
substantially different ways:
For **Seatbelt**, we would run `/usr/bin/sandbox-exec` with our policy
specified as an arg followed by the original command:
https://github.com/openai/codex/blob/d1de7bb383552e8fadd94be79d65d188e00fd562/codex-rs/core/src/exec.rs#L147-L219
For **Landlock/Seccomp**, we would do
`tokio::runtime::Builder::new_current_thread()`, _invoke
Landlock/Seccomp APIs to modify the permissions of that new thread_, and
then spawn the command:
https://github.com/openai/codex/blob/d1de7bb383552e8fadd94be79d65d188e00fd562/codex-rs/core/src/exec_linux.rs#L28-L49
While it is neat that Landlock/Seccomp supports applying a policy to
only one thread without having to apply it to the entire process, it
requires us to maintain two different codepaths and is a bit harder to
reason about. The tipping point was
https://github.com/openai/codex/pull/1061, in which we had to start
building up the `env` in an unexpected way for the existing
Landlock/Seccomp approach to continue to work.
This PR overhauls things so that we do similar things for Mac and Linux.
It turned out that we were already building our own "helper binary"
comparable to Mac's `sandbox-exec` as part of the `cli` crate:
https://github.com/openai/codex/blob/d1de7bb383552e8fadd94be79d65d188e00fd562/codex-rs/cli/Cargo.toml#L10-L12
We originally created this to build a small binary to include with the
Node.js version of the Codex CLI to provide support for Linux
sandboxing.
Though the sticky bit is that, at this point, we still want to deploy
the Rust version of Codex as a single, standalone binary rather than a
CLI and a supporting sandboxing binary. To satisfy this goal, we use
"the arg0 trick," in which we:
* use `std::env::current_exe()` to get the path to the CLI that is
currently running
* use the CLI as the `program` for the `Command`
* set `"codex-linux-sandbox"` as arg0 for the `Command`
A CLI that supports sandboxing should check arg0 at the start of the
program. If it is `"codex-linux-sandbox"`, it must invoke
`codex_linux_sandbox::run_main()`, which runs the CLI as if it were
`codex-linux-sandbox`. When acting as `codex-linux-sandbox`, we make the
appropriate Landlock/Seccomp API calls and then use `execvp(3)` to spawn
the original command, so do _replace_ the process rather than spawn a
subprocess. Incidentally, we do this before starting the Tokio runtime,
so the process should only have one thread when `execvp(3)` is called.
Because the `core` crate that needs to spawn the Linux sandboxing is not
a CLI in its own right, this means that every CLI that includes `core`
and relies on this behavior has to (1) implement it and (2) provide the
path to the sandboxing executable. While the path is almost always
`std::env::current_exe()`, we needed to make this configurable for
integration tests, so `Config` now has a `codex_linux_sandbox_exe:
Option<PathBuf>` property to facilitate threading this through,
introduced in https://github.com/openai/codex/pull/1089.
This common pattern is now captured in
`codex_linux_sandbox::run_with_sandbox()` and all of the `main.rs`
functions that should use it have been updated as part of this PR.
The `codex-linux-sandbox` crate added to the Cargo workspace as part of
this PR now has the bulk of the Landlock/Seccomp logic, which makes
`core` a bit simpler. Indeed, `core/src/exec_linux.rs` and
`core/src/landlock.rs` were removed/ported as part of this PR. I also
moved the unit tests for this code into an integration test,
`linux-sandbox/tests/landlock.rs`, in which I use
`env!("CARGO_BIN_EXE_codex-linux-sandbox")` as the value for
`codex_linux_sandbox_exe` since `std::env::current_exe()` is not
appropriate in that case.
Sets submodules to use workspace lints. Added denying unwrap as a
workspace level lint, which found a couple of cases where we could have
propagated errors. Also manually labeled ones that were fine by my eye.
Some effects of this change:
- New formatting changes across many files. No functionality changes
should occur from that.
- Calls to `set_env` are considered unsafe, since this only happens in
tests we wrap them in `unsafe` blocks
I started this PR because I wanted to share the `format_duration()`
utility function in `codex-rs/exec/src/event_processor.rs` with the TUI.
The question was: where to put it?
`core` should have as few dependencies as possible, so moving it there
would introduce a dependency on `chrono`, which seemed undesirable.
`core` already had this `cli` feature to deal with a similar situation
around sharing common utility functions, so I decided to:
* make `core` feature-free
* introduce `common`
* `common` can have as many "special interest" features as it needs,
each of which can declare their own deps
* the first two features of common are `cli` and `elapsed`
In practice, this meant updating a number of `Cargo.toml` files,
replacing this line:
```toml
codex-core = { path = "../core", features = ["cli"] }
```
with these:
```toml
codex-core = { path = "../core" }
codex-common = { path = "../common", features = ["cli"] }
```
Moving `format_duration()` into its own file gave it some "breathing
room" to add a unit test, so I had Codex generate some tests and new
support for durations over 1 minute.
Taking a pass at building artifacts per platform so we can consider
different distribution strategies that don't require users to install
the full `cargo` toolchain.
Right now this grabs just the `codex-repl` and `codex-tui` bins for 5
different targets and bundles them into a draft release. I think a
clearly marked pre-release set of artifacts will unblock the next step
of testing.
This changes how instantiating `Config` works and also adds
`approval_policy` and `sandbox_policy` as fields. The idea is:
* All fields of `Config` have appropriate default values.
* `Config` is initially loaded from `~/.codex/config.toml`, so values in
`config.toml` will override those defaults.
* Clients must instantiate `Config` via
`Config::load_with_overrides(ConfigOverrides)` where `ConfigOverrides`
has optional overrides that are expected to be settable based on CLI
flags.
The `Config` should be defined early in the program and then passed
down. Now functions like `init_codex()` take fewer individual parameters
because they can just take a `Config`.
Also, `Config::load()` used to fail silently if `~/.codex/config.toml`
had a parse error and fell back to the default config. This seemed
really bad because it wasn't clear why the values in my `config.toml`
weren't getting picked up. I changed things so that
`load_with_overrides()` returns `Result<Config>` and verified that the
various CLIs print a reasonable error if `config.toml` is malformed.
Finally, I also updated the TUI to show which **sandbox** value is being
used, as we do for other key values like **model** and **approval**.
This was also a reminder that the various values of `--sandbox` are
honored on Linux but not macOS today, so I added some TODOs about fixing
that.
As stated in `codex-rs/README.md`:
Today, Codex CLI is written in TypeScript and requires Node.js 22+ to
run it. For a number of users, this runtime requirement inhibits
adoption: they would be better served by a standalone executable. As
maintainers, we want Codex to run efficiently in a wide range of
environments with minimal overhead. We also want to take advantage of
operating system-specific APIs to provide better sandboxing, where
possible.
To that end, we are moving forward with a Rust implementation of Codex
CLI contained in this folder, which has the following benefits:
- The CLI compiles to small, standalone, platform-specific binaries.
- Can make direct, native calls to
[seccomp](https://man7.org/linux/man-pages/man2/seccomp.2.html) and
[landlock](https://man7.org/linux/man-pages/man7/landlock.7.html) in
order to support sandboxing on Linux.
- No runtime garbage collection, resulting in lower memory consumption
and better, more predictable performance.
Currently, the Rust implementation is materially behind the TypeScript
implementation in functionality, so continue to use the TypeScript
implmentation for the time being. We will publish native executables via
GitHub Releases as soon as we feel the Rust version is usable.
joeflorencio-openai ·
Michael Bolin ·
Charlie Marsh ·
pakrym-oai ·
Ahmed Ibrahim ·
Eric Traut ·
Owen Lin ·
gt-oai ·
pap-openai ·
Anton Panasenko ·
Josh McKinney ·
rugvedS07 ·
vishnu-oai ·
jif-oai ·
dependabot[bot] ·
Dylan ·
Parker Thompson ·
easong-openai ·
Rene Leonhardt ·
jcoens-openai ·
oai-ragona ·
Fouad Matin ·