Skip to content

Merge upstream main; fix exec shutdown + inputs; refresh pnpm lockfile - #153

Merged
ScriptedAlchemy merged 670 commits into
mainfrom
merge-upstream-main-20260204
Feb 6, 2026
Merged

ScriptedAlchemy merged 670 commits into
mainfrom
merge-upstream-main-20260204

Conversation

@ScriptedAlchemy

@ScriptedAlchemy ScriptedAlchemy commented Feb 4, 2026 •

Copy link
Copy Markdown
Owner

Summary

  • Merge upstream main into the branch.
  • Ensure exec callback mode shuts down on TurnAborted and respects ShutdownComplete.
  • Honor structured inputItems for exec callers instead of prompting on stdin.
  • Restore programmatic TUI shutdown by wiring a cancellation token through codex_tui and the native SDK.
  • Refresh pnpm-lock.yaml to match sdk/native/package.json.

Testing

  • Not run locally (CI only)

charley-oai and others added 30 commits January 29, 2026 16:40
…0103)

## Summary
Adds a simple `/plan` slash command in the TUI that switches the active
collaboration mode to Plan mode. The command is only available when the
`collaboration_modes` feature is enabled.

## Changes
- Add `plan_mask` helper in `codex-rs/tui/src/collaboration_modes.rs`
- Add `SlashCommand::Plan` metadata in
`codex-rs/tui/src/slash_command.rs`
- Implement and hard-gate `/plan` dispatch in
`codex-rs/tui/src/chatwidget.rs`
- Hide `/plan` when collaboration modes are disabled in
`codex-rs/tui/src/bottom_pane/slash_commands.rs`
- Update command popup tests in
`codex-rs/tui/src/bottom_pane/command_popup.rs`
- Add a focused unit test for `/plan` in
`codex-rs/tui/src/chatwidget/tests.rs`

## Behavior notes
- `/plan` is now a no-op if `Feature::CollaborationModes` is disabled.
- When enabled, `/plan` switches directly to Plan mode without opening
the picker.

## Codex author
`codex resume 019c05da-d7c3-7322-ae2c-3ca38d0ef702`
Explain what this is and what it's used for.
Add dynamic tools to rollout file for persistence & read from rollout on
resume. Ran a real example and spotted the following in the rollout
file:
```
{"timestamp":"2026-01-29T01:27:57.468Z","type":"session_meta","payload":{"id":"019c075d-3f0b-77e3-894e-c1c159b04b1e","timestamp":"2026-01-29T01:27:57.451Z","...."dynamic_tools":[{"name":"demo_tool","description":"Demo dynamic tool","inputSchema":{"additionalProperties":false,"properties":{"city":{"type":"string"}},"required":["city"],"type":"object"}}],"git":{"commit_hash":"ebc573f15c01b8af158e060cfedd401f043e9dfa","branch":"dev/cc/dynamic-tools","repository_url":"https://github.com/openai/codex.git"}}}
```
Adds support for the Go plan type
Updates rate limit error messages to point to the usage page
## Problem
OpenAI employees were sent to the public GitHub issue flow after
`/feedback`, which is the wrong follow-up path internally.

## Mental model
After feedback upload completes, we render a follow-up link/message.
That link should be audience-aware but must not change the upload
pipeline itself.

## Non-goals
- Changing how feedback is captured or uploaded
- Changing external user behavior

## Tradeoffs
We detect employees via the authenticated account email suffix
(`@openai.com`). If the email is unavailable (e.g., API key auth), we
default to the external behavior.

## Architecture
- Introduce `FeedbackAudience` and thread it from `App` -> `ChatWidget`
-> `FeedbackNoteView`
- Gate internal messaging/links on `FeedbackAudience::OpenAiEmployee`
- Internal follow-up link is now `http://go/codex-feedback-internal`
- External GitHub URL remains byte-for-byte identical

## Observability
No new telemetry; this only changes rendered follow-up instructions.

## Tests
- `just fmt`
- `cargo test -p codex-tui --lib`
## Summary
Let's dial in this api contract in a bit more with more robust fallback
behavior when model_instructions_template is false.

Switches to a more explicit template / variables structure, with more
fallbacks.

## Testing
- [x] Adding unit tests
- [x] Tested locally
Add elicitation approval request for MCP tool call requests.
<img width="599" height="238" alt="Screenshot 2026-01-29 at 13 24 57"
src="https://github.com/user-attachments/assets/1e9a5af2-f649-476c-b310-ae4938814538"
/>
## Summary
- add startup tooltip for OpenAI community Discord
- add startup tooltip for Codex community forum

## Testing
- not run (text-only tooltip change)
… isOther (#10210)

We should never ask a freeform question when planning and we should
always include isOther as an escape hatch.
1. Add a metric to measure the backfill time
2. Add a unit to the timing histogram
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>
Load requirements from Codex Backend. It only does this for enterprise
customers signed in with ChatGPT.

Todo in follow-up PRs:
* Add to app-server and exec too
* Switch from fail-open to fail-closed on failure
Previously, `CodexAuth` was defined as follows:


https://github.com/openai/codex/blob/d550fbf41afc09d7d7b5ac813aea38de07b2a73f/codex-rs/core/src/auth.rs#L39-L46

But if you looked at its constructors, we had creation for
`AuthMode::ApiKey` where `storage` was built using a nonsensical path
(`PathBuf::new()`) and `auth_dot_json` was `None`:


https://github.com/openai/codex/blob/d550fbf41afc09d7d7b5ac813aea38de07b2a73f/codex-rs/core/src/auth.rs#L212-L220

By comparison, when `AuthMode::ChatGPT` was used, `api_key` was always
`None`:


https://github.com/openai/codex/blob/d550fbf41afc09d7d7b5ac813aea38de07b2a73f/codex-rs/core/src/auth.rs#L665-L671

openai/codex#10012 took things further because
it introduced a new `ChatgptAuthTokens` variant to `AuthMode`, which is
important in when invoking `account/login/start` via the app server, but
most logic _internal_ to the app server should just reason about two
`AuthMode` variants: `ApiKey` and `ChatGPT`.

This PR tries to clean things up as follows:

- `LoginAccountParams` and `AuthMode` in `codex-rs/app-server-protocol/`
both continue to have the `ChatgptAuthTokens` variant, though it is used
exclusively for the on-the-wire messaging.
- `codex-rs/core/src/auth.rs` now has its own `AuthMode` enum, which
only has two variants: `ApiKey` and `ChatGPT`.
- `CodexAuth` has been changed from a struct to an enum. It is a
disjoint union where each variant (`ApiKey`, `ChatGpt`, and
`ChatGptAuthTokens`) have only the associated fields that make sense for
that variant.

---
[//]: # (BEGIN SAPLING FOOTER)
Stack created with [Sapling](https://sapling-scm.com). Best reviewed
with [ReviewStack](https://reviewstack.dev/openai/codex/pull/10208).
* #10224
* __->__ #10208
## Summary
Let users start opting in to trying out personalities

## Testing
- [x] existing tests pass
## Summary
Let's start getting feedback on this feature 😅 

## Testing
- [x] existing tests pass
`requirements.toml` should be able to specify rules which always run. 

My intention here was that these rules could only ever be restrictive,
which means the decision can be "prompt" or "forbidden" but never
"allow". A requirement of "you must always allow this command" didn't
make sense to me, but happy to be gaveled otherwise.

Rules already applies the most restrictive decision, so we can safely
merge these with rules found in other config folders.
## Summary
- Tightens Plan Mode to encourage exploration-first behavior and more
back-and-forth alignment.
- Adds a required TL;DR checkpoint before drafting the full plan.
- Clarifies client behavior that can cause premature “Implement this
plan?” prompts.

## What changed
- Require at least one targeted non-mutating exploration pass before the
first user question.
- Insert a TL;DR checkpoint between Phase 2 (intent) and Phase 3
(implementation).
- TL;DR checkpoint guidance:
  - Label: “Proposed Plan (TL;DR)”
  - Format: 3–5 bullets using `- `
  - Options: exactly one option, “Approve”
- `isOther: true`, with explicit guidance that “None of the above” is
the edit path in the current UI.
- Require the final plan to include a TL;DR consistent with the approved
checkpoint.

## Why
- In Plan Mode, any normal assistant message at turn completion is
treated as plan content by the client. This can trigger premature
“Implement this plan?” prompts.
- The TL;DR checkpoint aligns on direction before Codex drafts a long,
decision-complete plan.

## Testing
- Manual: built the local CLI and verified the flow now explores first,
presents a TL;DR checkpoint, and only drafts the full plan after
approval.

---------

Co-authored-by: Nick Baumann <@openai.com>
…(#9786)

## Summary
- Stream proposed plans in Plan Mode using `<proposed_plan>` tags parsed
in core, emitting plan deltas plus a plan `ThreadItem`, while stripping
tags from normal assistant output.
- Persist plan items and rebuild them on resume so proposed plans show
in thread history.
- Wire plan items/deltas through app-server protocol v2 and render a
dedicated proposed-plan view in the TUI, including the “Implement this
plan?” prompt only when a plan item is present.

## Changes

### Core (`codex-rs/core`)
- Added a generic, line-based tag parser that buffers each line until it
can disprove a tag prefix; implements auto-close on `finish()` for
unterminated tags. `codex-rs/core/src/tagged_block_parser.rs`
- Refactored proposed plan parsing to wrap the generic parser.
`codex-rs/core/src/proposed_plan_parser.rs`
- In plan mode, stream assistant deltas as:
  - **Normal text** → `AgentMessageContentDelta`
  - **Plan text** → `PlanDelta` + `TurnItem::Plan` start/completion  
  (`codex-rs/core/src/codex.rs`)
- Final plan item content is derived from the completed assistant
message (authoritative), not necessarily the concatenated deltas.
- Strips `<proposed_plan>` blocks from assistant text in plan mode so
tags don’t appear in normal messages.
(`codex-rs/core/src/stream_events_utils.rs`)
- Persist `ItemCompleted` events only for plan items for rollout replay.
(`codex-rs/core/src/rollout/policy.rs`)
- Guard `update_plan` tool in Plan Mode with a clear error message.
(`codex-rs/core/src/tools/handlers/plan.rs`)
- Updated Plan Mode prompt to:  
  - keep `<proposed_plan>` out of non-final reasoning/preambles  
  - require exact tag formatting  
  - allow only one `<proposed_plan>` block per turn  
  (`codex-rs/core/templates/collaboration_mode/plan.md`)

### Protocol / App-server protocol
- Added `TurnItem::Plan` and `PlanDeltaEvent` to core protocol items.
(`codex-rs/protocol/src/items.rs`, `codex-rs/protocol/src/protocol.rs`)
- Added v2 `ThreadItem::Plan` and `PlanDeltaNotification` with
EXPERIMENTAL markers and note that deltas may not match the final plan
item. (`codex-rs/app-server-protocol/src/protocol/v2.rs`)
- Added plan delta route in app-server protocol common mapping.
(`codex-rs/app-server-protocol/src/protocol/common.rs`)
- Rebuild plan items from persisted `ItemCompleted` events on resume.
(`codex-rs/app-server-protocol/src/protocol/thread_history.rs`)

### App-server
- Forward plan deltas to v2 clients and map core plan items to v2 plan
items. (`codex-rs/app-server/src/bespoke_event_handling.rs`,
`codex-rs/app-server/src/codex_message_processor.rs`)
- Added v2 plan item tests.
(`codex-rs/app-server/tests/suite/v2/plan_item.rs`)

### TUI
- Added a dedicated proposed plan history cell with special background
and padding, and moved “• Proposed Plan” outside the highlighted block.
(`codex-rs/tui/src/history_cell.rs`, `codex-rs/tui/src/style.rs`)
- Only show “Implement this plan?” when a plan item exists.
(`codex-rs/tui/src/chatwidget.rs`,
`codex-rs/tui/src/chatwidget/tests.rs`)

<img width="831" height="847" alt="Screenshot 2026-01-29 at 7 06 24 PM"
src="https://github.com/user-attachments/assets/69794c8c-f96b-4d36-92ef-c1f5c3a8f286"
/>

### Docs / Misc
- Updated protocol docs to mention plan deltas.
(`codex-rs/docs/protocol_v1.md`)
- Minor plumbing updates in exec/debug clients to tolerate plan deltas.
(`codex-rs/debug-client/src/reader.rs`, `codex-rs/exec/...`)

## Tests
- Added core integration tests:
  - Plan mode strips plan from agent messages.
  - Missing `</proposed_plan>` closes at end-of-message.  
  (`codex-rs/core/tests/suite/items.rs`)
- Added unit tests for generic tag parser (prefix buffering, non-tag
lines, auto-close). (`codex-rs/core/src/tagged_block_parser.rs`)
- Existing app-server plan item tests in v2.
(`codex-rs/app-server/tests/suite/v2/plan_item.rs`)

## Notes / Behavior
- Plan output no longer appears in standard assistant text in Plan Mode;
it streams via `PlanDelta` and completes as a `TurnItem::Plan`.
- The final plan item content is authoritative and may diverge from
streamed deltas (documented as experimental).
- Reasoning summaries are not filtered; prompt instructs the model not
to include `<proposed_plan>` outside the final plan message.

## Codex Author
`codex fork 019bec2d-b09d-7450-b292-d7bcdddcdbfb`
Title
Hide Code mode footer label/cycle hint; add Plan footer-collapse
snapshots

Summary
- Keep Code mode internal naming but suppress the footer mode label +
cycle hint when Code is active.
- Only show the cycle hint when a non‑Code mode indicator is present.
- Add Plan-mode footer collapse snapshot coverage (empty + queued,
across widths) and update existing footer collapse snapshots for the new
Code behavior.

Notes
- The test run currently fails in codex-cloud-requirements on
origin/main due to a stale auth.mode field; no fix is included in this
PR to keep the diff minimal.

Codex author
`codex resume 019c0296-cfd4-7193-9b0a-6949048e4546`
owenlin0 and others added 28 commits February 5, 2026 10:46
…server (#10423)

So that the rest of the codebase (like TUI) don't need to be concerned
whether ChatGPT auth was handled by Codex itself or passed in via
app-server's external auth mode.
This will give visibility into the comparative success rate of the
Windows sandbox implementations compared to other platforms.
default-enablement of web_search is now client-side, no need to send
eligibility headers to backend.

Tested locally, headers no longer sent.

will wait for corresponding backend change to deploy before merging
- [x] Add a method to list experimental features.
seems like footgun if we forget to remove before releasing 0.99.0,
limited announcement to versions < 0.98.0
- Adds --listen <URL> to codex app-server with two listen modes:
      - stdio:// (default, existing behavior)
      - ws://IP:PORT (new websocket transport)
  - Refactors message routing to be connection-aware:
- Tracks per-connection session state (initialize/experimental
capability)
      - Routes responses/errors to the originating connection
- Broadcasts server notifications/requests to initialized connections
- Updates initialization semantics to be per connection (not
process-global), and updates app-server docs accordingly.
- Adds websocket accept/read/write handling (JSON-RPC per text frame,
ping/pong handling, connection lifecycle events).

Testing

- Unit tests for transport URL parsing and targeted response/error
routing.
  - New websocket integration test validating:
      - per-connection initialization requirements
      - no cross-connection response leakage
      - same request IDs on different connections route independently.
…-20260204

# Conflicts:
#	codex-rs/core/src/client.rs
#	codex-rs/core/src/codex.rs
#	codex-rs/core/src/compact.rs
#	codex-rs/core/src/state/service.rs
#	codex-rs/core/src/tools/registry.rs
#	codex-rs/core/tests/responses_headers.rs
#	codex-rs/core/tests/suite/client.rs
#	codex-rs/core/tests/suite/client_websockets.rs
#	codex-rs/core/tests/suite/mod.rs
#	codex-rs/core/tests/suite/personality.rs
#	codex-rs/state/src/runtime.rs
configRequirements/read now returns updated cloud requirements after
login.
###### What
Remove special-casing that prevented auto-enabling `web_search` for
Azure model provider users. Addresses #10071, #10257.

###### Why
Azure fixed their responsesapi implementation; `web_search` is now
supported on models it wasn't before (like `gpt-5.1-codex-max`).

This request now works:
```
curl "$AZURE_API_ENDPOINT" -H "Content-Type: application/json" -H "Authorization: Bearer $AZURE_API_KEY" -d '{
  "model": "gpt-5.1-codex-max",
  "tools": [
    { "type": "web_search" }
  ],
  "tool_choice": "auto",
  "input": "Find the sunrise time in Paris today and cite the source."
}'
```

###### Tests
Tested with above curl, removed Azure-specific tests.
## Problem

`codex` currently prompts you to update via `brew upgrade --cask codex`
but the brew api does not return the new version

> <img width="1500" height="822" alt="Screenshot 2026-02-05 at 12 36
09 PM"
src="https://github.com/user-attachments/assets/9e12929d-95e8-43f4-8fba-ab93f5f76e73"
/>

## Solution

`codex-rs/tui/src/updates.rs` was using the [latest cask in
github](https://github.com/Homebrew/homebrew-cask/blob/HEAD/Casks/c/codex.rb)
but this does not agree with the brew api, which leads to the issue
above. Instead we use the [brew api json
endpoint](https://github.com/Homebrew/homebrew-cask/blob/HEAD/Casks/c/codex.rb)
to ensure our version check agrees with the upgrade command.
- [x] Add stage field for experimental flags.
This PR adds a dedicated `turn/steer` API for appending user input to an
in-flight turn.

## Motivation
Currently, steering in the app is implemented by just calling
`turn/start` while a turn is running. This has some really weird quirks:
- Client gets back a new `turn.id`, even though streamed
events/approvals remained tied to the original active turn ID.
- All the various turn-level override params on `turn/start` do not
apply to the "steer", and would only apply to the next real turn.
- There can also be a race condition where the client thinks the turn is
active but the server has already completed it, so there might be bugs
if the client has baked in some client-specific behavior thinking it's a
steer when in fact the server kicked off a new turn. This is
particularly possible when running a client against a remote app-server.

Having a dedicated `turn/steer` API eliminates all those quirks.

`turn/steer` behavior:
- Requires an active turn on threadId. Returns a JSON-RPC error if there
is no active turn.
- If expectedTurnId is provided, it must match the active turn (more
useful when connecting to a remote app-server).
- Does not emit `turn/started`.
- Does not accept turn overrides (`cwd`, `model`, `sandbox`, etc.) or
`outputSchema` to accurately reflect that these are not applied when
steering.
@ScriptedAlchemy
ScriptedAlchemy merged commit 720039b into main Feb 6, 2026
13 checks passed
@ScriptedAlchemy
ScriptedAlchemy deleted the merge-upstream-main-20260204 branch February 6, 2026 05:11
Sign up for free to join this conversation on GitHub. Already have an account? Sign in to comment

Labels

None yet

Projects

None yet

Development

Successfully merging this pull request may close these issues.