codex

jif-oai · 2026-01-28 16:19:08 +01:00

231406bd04

feat: sqlite 1 (#10004 )

Add a `.sqlite` database to be used to store rollout metatdata (and
later logs)
This PR is phase 1:
* Add the database and the required infrastructure
* Add a backfill of the database
* Persist the newly created rollout both in files and in the DB
* When we need to get metadata or a rollout, consider the `JSONL` as the
source of truth but compare the results with the DB and show any errors

jif-oai · 2026-01-28 15:29:14 +01:00

3878c3dc7c

Add exec policy TOML representation (#10026 )

We'd like to represent these in `requirements.toml`. This just adds the
representation and the tests, doesn't wire it up anywhere yet.

gt-oai · 2026-01-28 12:00:10 +00:00

71b8d937ed

feat(core) RequestRule (#9489 )

## Summary
Instead of trying to derive the prefix_rule for a command mechanically,
let's let the model decide for us.

## Testing
- [x] tested locally

Dylan Hurd · 2026-01-28 08:43:17 +00:00

996e09ca24

error code/msg details for failed elevated setup (#9941 )

iceweasel-oai · 2026-01-27 23:06:10 -08:00

9f79365691

fix(core) info cleanup (#9986 )

## Summary
Simplify this logic a bit.

Dylan Hurd · 2026-01-27 21:15:15 -07:00

fef3e36f67

[skills] Auto install MCP dependencies when running skils with dependency specs. (#9982 )

Auto install MCP dependencies when running skils with dependency specs.

Matthew Zeng · 2026-01-27 19:02:45 -08:00

3bb8e69dd3

fix: allow unknown fields on Notice in schema (#10041 )

the `notice` field didn't allow unknown fields in the schema, leading to
issues where they shouldn't be.

Now we allow unknown fields.

<img width="2260" height="720" alt="image"
src="https://github.com/user-attachments/assets/1de43b60-0d50-4a96-9c9c-34419270d722"
/>

sayan-oai · 2026-01-27 18:24:24 -08:00

1609f6aa81

fix: enable per-turn updates to web search mode (#10040 )

web_search can now be updated per-turn, for things like changes to
sandbox policy.

`SandboxPolicy::DangerFullAccess` now sets web_search to `live`, and the
default is still `cached`.

Added integration tests.

sayan-oai · 2026-01-27 18:09:29 -08:00

a90ab789c2

enable live web search for DangerFullAccess sandbox policy (#10008 )

Auto-enable live `web_search` tool when sandbox policy is
`DangerFullAccess`.

Explicitly setting `web_search` (canonical setting), or enabling
`web_search_cached` or `web_search_request` still takes precedence over
this sandbox-policy-driven enablement.

sayan-oai · 2026-01-27 20:09:05 +00:00

28051d18c6

Remove load from SKILL.toml fallback (#10007 )

alexsong-oai · 2026-01-27 12:06:40 -08:00

2f8a44baea

remove sandbox globals. (#9797 )

Threads sandbox updates through OverrideTurnContext for active turn
Passes computed sandbox type into safety/exec

iceweasel-oai · 2026-01-27 11:04:23 -08:00

c40ad65bd8

fix(app-server, core): defer initial context write to rollout file until first turn (#9950 )

### Overview
Currently calling `thread/resume` will always bump the thread's
`updated_at` timestamp. This PR makes it the `updated_at` timestamp
changes only if a turn is triggered.

### Additonal context
What we typically do on resuming a thread is **always** writing “initial
context” to the rollout file immediately. This initial context includes:
- Developer instructions derived from sandbox/approval policy + cwd
- Optional developer instructions (if provided)
- Optional collaboration-mode instructions
- Optional user instructions (if provided)
- Environment context (cwd, shell, etc.)

This PR defers writing the “initial context” to the rollout file until
the first `turn/start`, so we don't inadvertently bump the thread's
`updated_at` timestamp until a turn is actually triggered.

This works even though both `thread/resume` and `turn/start` accept
overrides (such as `model`, `cwd`, etc.) because the initial context is
seeded from the effective `TurnContext` in memory, computed at
`turn/start` time, after both sets of overrides have been applied.

**NOTE**: This is a very short-lived solution until we introduce sqlite.
Then we can remove this.

Owen Lin · 2026-01-27 10:41:54 -08:00

fc0fd85349

description in role type (#9993 )

jif-oai · 2026-01-27 17:20:07 +00:00

067922a734

chore: clean orchestrator prompt (#9994 )

jif-oai · 2026-01-27 16:32:05 +00:00

3b726d9550

nit: better unused prompt (#9991 )

jif-oai · 2026-01-27 13:03:12 +00:00

74ffbbe7c1

nit: better tool description (#9988 )

jif-oai · 2026-01-27 12:46:51 +00:00

742f086ee6

Fix: cap aggregated exec output consistently (#9759 )

## WHAT?
- Bias aggregated output toward stderr under contention (2/3 stderr, 1/3
stdout) while keeping the 1 MiB cap.
- Rebalance unused stderr share back to stdout when stderr is tiny to
avoid underfilling.
- Add tests for contention, small-stderr rebalance, and under-cap
ordering (stdout then stderr).

## WHY?
- Review feedback requested stderr priority under contention.
- Avoid underfilled aggregated output when stderr is small while
preserving a consistent cap across exec paths.

## HOW?
- Update `aggregate_output` to compute stdout/stderr shares, then
reassign unused capacity to the other stream.
- Use the helper in both Windows and async exec paths.
- Add regression tests for contention/rebalance and under-cap ordering.

## BEFORE
```rust
// Best-effort aggregate: stdout then stderr (capped).
let mut aggregated = Vec::with_capacity(
    stdout
        .text
        .len()
        .saturating_add(stderr.text.len())
        .min(EXEC_OUTPUT_MAX_BYTES),
);
append_capped(&mut aggregated, &stdout.text, EXEC_OUTPUT_MAX_BYTES);
append_capped(&mut aggregated, &stderr.text, EXEC_OUTPUT_MAX_BYTES);
let aggregated_output = StreamOutput {
    text: aggregated,
    truncated_after_lines: None,
};
```

## AFTER
```rust
fn aggregate_output(
    stdout: &StreamOutput<Vec<u8>>,
    stderr: &StreamOutput<Vec<u8>>,
) -> StreamOutput<Vec<u8>> {
    let total_len = stdout.text.len().saturating_add(stderr.text.len());
    let max_bytes = EXEC_OUTPUT_MAX_BYTES;
    let mut aggregated = Vec::with_capacity(total_len.min(max_bytes));

    if total_len <= max_bytes {
        aggregated.extend_from_slice(&stdout.text);
        aggregated.extend_from_slice(&stderr.text);
        return StreamOutput {
            text: aggregated,
            truncated_after_lines: None,
        };
    }

    // Under contention, reserve 1/3 for stdout and 2/3 for stderr; rebalance unused stderr to stdout.
    let want_stdout = stdout.text.len().min(max_bytes / 3);
    let want_stderr = stderr.text.len();
    let stderr_take = want_stderr.min(max_bytes.saturating_sub(want_stdout));
    let remaining = max_bytes.saturating_sub(want_stdout + stderr_take);
    let stdout_take = want_stdout + remaining.min(stdout.text.len().saturating_sub(want_stdout));

    aggregated.extend_from_slice(&stdout.text[..stdout_take]);
    aggregated.extend_from_slice(&stderr.text[..stderr_take]);

    StreamOutput {
        text: aggregated,
        truncated_after_lines: None,
    }
}
```

## TESTS
- [x] `just fmt`
- [x] `just fix -p codex-core`
- [x] `cargo test -p codex-core aggregate_output_`
- [x] `cargo test -p codex-core`
- [x] `cargo test --all-features`

## FIXES
Fixes #9758

K Bediako · 2026-01-27 09:29:12 +00:00

ab99df0694

Fixing main and make plan mode reasoning effort medium (#9980 )

It's overthinking so much on high and going over the context window.

Ahmed Ibrahim · 2026-01-26 22:30:24 -08:00

509ff1c643

make plan prompt less detailed (#9977 )

This was too much to ask for

Ahmed Ibrahim · 2026-01-26 21:42:01 -08:00

cabb2085cc

tui: wrapping user input questions (#9971 )

Ahmed Ibrahim · 2026-01-26 21:30:09 -08:00

4db6da32a3

make cached web_search client-side default (#9974 )

[Experiment](https://console.statsig.com/50aWbk2p4R76rNX9lN5VUw/experiments/codex_web_search_rollout/summary)
for default cached `web_search` completed; cached chosen as default.

Update client to reflect that.

sayan-oai · 2026-01-26 21:25:40 -08:00

0adcd8aa86

plan prompt (#9975 )

# 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.

Ahmed Ibrahim · 2026-01-26 21:14:05 -08:00

28bd7db14a

prompt (#9970 )

# 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.

Ahmed Ibrahim · 2026-01-26 20:27:57 -08:00

0c72d8fd6e

prompt final (#9969 )

hopefully final this time (at least tonight) >_<

Ahmed Ibrahim · 2026-01-26 20:12:43 -08:00

f45a8733bf

Improve plan mode prompt (#9968 )

# 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.

Ahmed Ibrahim · 2026-01-26 19:56:16 -08:00

b655a092ba

plan prompt v7 (#9966 )

# 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.

Ahmed Ibrahim · 2026-01-26 19:34:18 -08:00

b7bba3614e

fix: handle all web_search actions and in progress invocations (#9960 )

### Summary
- Parse all `web_search` tool actions (`search`, `find_in_page`,
`open_page`).
- Previously we only parsed + displayed `search`, which made the TUI
appear to pause when the other actions were being used.
- Show in progress `web_search` calls as `Searching the web`
  - Previously we only showed completed tool calls

<img width="308" height="149" alt="image"
src="https://github.com/user-attachments/assets/90a4e8ff-b06a-48ff-a282-b57b31121845"
/>

### Tests
Added + updated tests, tested locally

### Follow ups
Update VSCode extension to display these as well

sayan-oai · 2026-01-27 03:33:48 +00:00

86adf53235

Use test_codex more (#9961 )

Reduces boilderplate.

pakrym-oai · 2026-01-26 18:52:10 -08:00

998e88b12a

Warn users on enabling underdevelopment features (#9954 )

<img width="938" height="73" alt="image"
src="https://github.com/user-attachments/assets/a2d5ac46-92c5-4828-b35e-0965c30cdf36"
/>

Ahmed Ibrahim · 2026-01-27 01:58:05 +00:00

c900de271a

feat: load interface metadata from SKILL.json (#9953 )

alexsong-oai · 2026-01-27 01:38:06 +00:00

a641a6427c

Reject request_user_input outside Plan/Pair (#9955 )

## Context

Previous work in https://github.com/openai/codex/pull/9560 only rejected
`request_user_input` in Execute and Custom modes. Since then, additional
modes
(e.g., Code) were added, so the guard should be mode-agnostic.

## What changed

- Switch the handler to an allowlist: only Plan and PairProgramming are
allowed
- Return the same error for any other mode (including Code)
- Add a Code-mode rejection test alongside the existing Execute/Custom
tests

## Why

This prevents `request_user_input` from being used in modes where it is
not
intended, even as new modes are introduced.

Charley Cunningham · 2026-01-26 17:12:17 -08:00

47aa1f3b6a

Add composer config and shared menu surface helpers (#9891 )

Centralize built-in slash-command gating and extract shared menu-surface
helpers.

- Add bottom_pane::slash_commands and reuse it from composer + command
popup.
- Introduce ChatComposerConfig + shared menu surface rendering without
changing default behavior.

Ahmed Ibrahim · 2026-01-26 23:16:29 +00:00

a8f195828b

plan prompt (#9943 )

# 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.

Ahmed Ibrahim · 2026-01-26 14:48:54 -08:00

159ff06281

Add MCP server scopes config and use it as fallback for OAuth login (#9647 )

### Motivation
- Allow MCP OAuth flows to request scopes defined in `config.toml`
instead of requiring users to always pass `--scopes` on the CLI.
CLI/remote parameters should still override config values.

### Description
- Add optional `scopes: Option<Vec<String>>` to `McpServerConfig` and
`RawMcpServerConfig`, and propagate it through deserialization and the
built config types.
- Serialize `scopes` into the MCP server TOML via
`serialize_mcp_server_table` in `core/src/config/edit.rs` and include
`scopes` in the generated config schema (`core/config.schema.json`).
- CLI: update `codex-rs/cli/src/mcp_cmd.rs` `run_login` to fall back to
`server.scopes` when the `--scopes` flag is empty, with explicit CLI
scopes still taking precedence.
- App server: update
`codex-rs/app-server/src/codex_message_processor.rs`
`mcp_server_oauth_login` to use `params.scopes.or_else(||
server.scopes.clone())` so the RPC path also respects configured scopes.
- Update many test fixtures to initialize the new `scopes` field (set to
`None`) so test code builds with the new struct field.

### Testing
- Ran config tooling and formatters: `just write-config-schema`
(succeeded), `just fmt` (succeeded), and `just fix -p codex-core`, `just
fix -p codex-cli`, `just fix -p codex-app-server` (succeeded where
applicable).
- Ran unit tests for the CLI: `cargo test -p codex-cli` (passed).
- Ran unit tests for core: `cargo test -p codex-core` (ran; many tests
passed but several failed, including model refresh/403-related tests,
shell snapshot/timeouts, and several `unified_exec` expectations).
- Ran app-server tests: `cargo test -p codex-app-server` (ran; many
integration-suite tests failed due to mocked/remote HTTP 401/403
responses and wiremock expectations).

If you want, I can split the tests into smaller focused runs or help
debug the failing integration tests (they appear to be unrelated to the
config change and stem from external HTTP/mocking behaviors encountered
during the test runs).

------
[Codex
Task](https://chatgpt.com/codex/tasks/task_i_69718f505914832ea1f334b3ba064553)

blevy-oai · 2026-01-26 14:13:04 -08:00

bdc4742bfc

Aligned feature stage names with public feature maturity stages (#9929 )

We've recently standardized a [feature maturity
model](https://developers.openai.com/codex/feature-maturity) that we're
using in our docs and support forums to communicate expectations to
users. This PR updates the internal stage names and descriptions to
match.

This change involves a simple internal rename and updates to a few
user-visible strings. No functional change.

Eric Traut · 2026-01-26 11:43:36 -08:00

b77bf4d36d

Add thread/unarchive to restore archived rollouts (#9843 )

## Summary
- Adds a new `thread/unarchive` RPC to move archived thread rollouts
back into the active `sessions/` tree.

## What changed
- **Protocol**
  - Adds `thread/unarchive` request/response types and wiring.
- **Server**
  - Implements `thread_unarchive` in the app server.
  - Validates the archived rollout path and thread ID.
- Restores the rollout to `sessions/YYYY/MM/DD/...` based on the rollout
filename timestamp.
- **Core**
- Adds `find_archived_thread_path_by_id_str` helper for archived
rollouts.
- **Docs**
  - Documents the new RPC and usage example.
- **Tests**
  - Adds an end-to-end server test that:
    1) starts a thread,
    2) archives it,
    3) unarchives it,
    4) asserts the file is restored to `sessions/`.

## How to use
```json
{ "method": "thread/unarchive", "id": 24, "params": { "threadId": "<thread-id>" } }
```

## Author Codex Session

`codex resume 019bf158-54b6-7960-a696-9d85df7e1bc1` (soon I'll make this
kind of session UUID forkable by anyone with the right
`session_object_storage_url` line in their config, but for now just
pasting it here for my reference)

Charley Cunningham · 2026-01-26 11:24:36 -08:00

62266b13f8

chore: update interrupt message (#9925 )

jif-oai · 2026-01-26 19:07:54 +00:00

09251387e0

prompt (#9928 )

# 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.

Ahmed Ibrahim · 2026-01-26 10:27:18 -08:00

e471ebc5d2

fix: attempt to reduce high cpu usage when using collab (#9776 )

Reproduce with a prompt like this with collab enabled:
```
Examine the code at <some subdirectory with a deeply nested project>.  Find the most urgent issue to resolve and describe it to me.
```

Existing behavior causes the top-level agent to busy wait on subagents.

Gene Oden · 2026-01-26 10:07:25 -08:00

375a5ef051

Fix flakey shell snapshot test (#9919 )

Sometimes fails with:

```
failures:

  ---- shell_snapshot::tests::timed_out_snapshot_shell_is_terminated stdout ----

  thread 'shell_snapshot::tests::timed_out_snapshot_shell_is_terminated' panicked at codex-rs/core/src/shell_snapshot.rs:588:9:
  expected timeout error, got Failed to execute sh

  Caused by:
      Text file busy (os error 26)


  failures:
      shell_snapshot::tests::timed_out_snapshot_shell_is_terminated

  test result: FAILED. 815 passed; 1 failed; 4 ignored; 0 measured; 0 filtered out; finished in 18.00s
```

gt-oai · 2026-01-26 18:05:30 +00:00

fdc69df454

Feat: add isOther to question returned by request user input tool (#9890 )

### Summary
Add `isOther` to question object from request_user_input tool input and
remove `other` option from the tool prompt to better handle tool input.

Shijie Rao · 2026-01-26 09:52:38 -08:00

3ba702c5b6

Fix up config disabled err msg (#9916 )

**Before:**
<img width="745" height="375" alt="image"
src="https://github.com/user-attachments/assets/d6c23562-b87f-4af9-8642-329aab8e594d"
/>

**After:**
<img width="1042" height="354" alt="image"
src="https://github.com/user-attachments/assets/c9a2413c-c945-4c34-8b7e-c6c9b8fbf762"
/>

Two changes:
1. only display if there is a `config.toml` that is skipped (i.e. if
there is just `.codex/skills` but no `.codex/config.toml` we do not
display the error)
2. clarify the implications and the fix in the error message.

gt-oai · 2026-01-26 17:49:31 +00:00

6316e57497

feat: disable collab at max depth (#9899 )

jif-oai · 2026-01-26 17:05:36 +00:00

70d5959398

feat: explorer collab (#9918 )

jif-oai · 2026-01-26 16:21:42 +00:00

3f338e4a6a

feat: dynamic tools injection (#9539 )

## Summary
Add dynamic tool injection to thread startup in API v2, wire dynamic
tool calls through the app server to clients, and plumb responses back
into the model tool pipeline.

### Flow (high level)
- Thread start injects `dynamic_tools` into the model tool list for that
thread (validation is done here).
- When the model emits a tool call for one of those names, core raises a
`DynamicToolCallRequest` event.
- The app server forwards it to the client as `item/tool/call`, waits
for the client’s response, then submits a `DynamicToolResponse` back to
core.
- Core turns that into a `function_call_output` in the next model
request so the model can continue.

### What changed
- Added dynamic tool specs to v2 thread start params and protocol types;
introduced `item/tool/call` (request/response) for dynamic tool
execution.
- Core now registers dynamic tool specs at request time and routes those
calls via a new dynamic tool handler.
- App server validates tool names/schemas, forwards dynamic tool call
requests to clients, and publishes tool outputs back into the session.
- Integration tests

jif-oai · 2026-01-26 10:06:44 +00:00

d594693d1a

chore(core) move model_instructions_template config (#9871 )

## Summary
Move `model_instructions_template` config to the experimental slug while
we iterate on this feature

## Testing
- [x] Tested locally, unit tests still pass

Dylan Hurd · 2026-01-26 07:02:11 +00:00

25fccc3d4d

feat(tui) /personality (#9718 )

## Summary
Adds /personality selector in the TUI, which leverages the new core
interface in #9644

Notes:
- We are doing some of our own state management for model_info loading
here, but not sure if that's ideal. open to opinions on simpler
approach, but would like to avoid blocking on a larger refactor
- Right now, the `/personality` selector just hides when the model
doesn't support it. we can update this behavior down the line

## Testing
- [x] Tested locally
- [x] Added snapshot tests

Dylan Hurd · 2026-01-25 21:59:42 -08:00

031bafd1fb

Plan prompt (#9877 )

# 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.

Ahmed Ibrahim · 2026-01-25 19:50:35 -08:00

d27f2533a9

Prompt (#9874 )

# 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.

Ahmed Ibrahim · 2026-01-25 18:24:25 -08:00

0f798173d7

1364 Commits