- Adopt upstream in common/file-search and add TUI popup/types
- Preserve fork invariants in core (browser/agent/web_fetch gating, UA/version)
- Keep our TUI and CLI flows; resolve conflicts per policy
- Protocol: align mcp_protocol to upstream; add TS for Verbosity
- file-search: provide run_streaming shim to satisfy TUI usage
- common: make sandbox summary robust to new fields
Verification:
- scripts/upstream-merge/verify.sh: PASS (build-fast + API checks)
This adds `SetDefaultModel`, which takes `model` and `reasoning_effort`
as optional fields. If set, the field will overwrite what is in the
user's `config.toml`.
This reuses logic that was added to support the `/model` command in the
TUI: https://github.com/openai/codex/pull/2799.
- Treat Left/Right as Up/Down across Theme/Spinner views, including Create flows.\n- In review screens, Left focuses preview toggle (themes) and cycles buttons; Right moves to Save/Retry.\n- Update title hint to display '▲ ▼ ◀ ▶ select'.\n\nAlso includes other local TUI/core adjustments present in the working tree. Verified with ./build-fast.sh.
`ClientRequest::NewConversation` picks up the reasoning level from the user's defaults in `config.toml`, so it should be reported in `NewConversationResponse`.
## Summary
Handle timeouts the same way, regardless of approval mode. There's more
to do here, but this is simple and should be zero-regret
## Testing
- [x] existing tests pass
- [x] test locally and verify rollout
Created this PR by:
- adding `redundant_clone` to `[workspace.lints.clippy]` in
`cargo-rs/Cargol.toml`
- running `cargo clippy --tests --fix`
- running `just fmt`
Though I had to clean up one instance of the following that resulted:
```rust
let codex = codex;
```
This PR does the following:
* Adds the ability to paste or type an API key.
* Removes the `preferred_auth_method` config option. The last login
method is always persisted in auth.json, so this isn't needed.
* If OPENAI_API_KEY env variable is defined, the value is used to
prepopulate the new UI. The env variable is otherwise ignored by the
CLI.
* Adds a new MCP server entry point "login_api_key" so we can implement
this same API key behavior for the VS Code extension.
<img width="473" height="140" alt="Screenshot 2025-09-04 at 3 51 04 PM"
src="https://github.com/user-attachments/assets/c11bbd5b-8a4d-4d71-90fd-34130460f9d9"
/>
<img width="726" height="254" alt="Screenshot 2025-09-04 at 3 51 32 PM"
src="https://github.com/user-attachments/assets/6cc76b34-309a-4387-acbc-15ee5c756db9"
/>
- Add to and parse/write in config
- Apply per-server timeout to and initial
- Treat per-server errors as non-fatal; record and skip those servers
- Keep manager creation successful even if some servers time out
- Export so local smoke tool can exercise it
- Add (stdio JSON-RPC) and binary for manual validation
- Update TUI to set by default
This resolves GitHub issue #91 where a slow MCP server caused manager creation to time out and fail entirely.
- Restore browser_*/agent_* tool exposure and web_fetch (openai_tools.rs)
- Reintroduce browser gating and screenshot handling in codex.rs; remove obsolete image 'detail' field; adapt RolloutRecorder::new to params API
- Keep upstream TS model changes (protocol/models.rs) to satisfy protocol-ts while preserving our semantics
- Reinstate UA helpers for MCP server (USER_AGENT_SUFFIX, get_codex_user_agent_default) in default_client.rs
Build: ./build-fast.sh clean on upstream-merge
This PR changes get history op to get path. Then, forking will use a
path. This will help us have one unified codepath for resuming/forking
conversations. Will also help in having rollout history in order. It
also fixes a bug where you won't see the UI when resuming after forking.
## Unified PTY-Based Exec Tool
Note: this requires to have this flag in the config:
`use_experimental_unified_exec_tool=true`
- Adds a PTY-backed interactive exec feature (“unified_exec”) with
session reuse via
session_id, bounded output (128 KiB), and timeout clamping (≤ 60 s).
- Protocol: introduces ResponseItem::UnifiedExec { session_id,
arguments, timeout_ms }.
- Tools: exposes unified_exec as a function tool (Responses API);
excluded from Chat
Completions payload while still supported in tool lists.
- Path handling: resolves commands via PATH (or explicit paths), with
UTF‑8/newline‑aware
truncation (truncate_middle).
- Tests: cover command parsing, path resolution, session
persistence/cleanup, multi‑session
isolation, timeouts, and truncation behavior.
https://github.com/openai/codex/pull/3395 updated `mcp-types/src/lib.rs`
by hand, but that file is generated code that is produced by
`mcp-types/generate_mcp_types.py`. Unfortunately, we do not have
anything in CI to verify this right now, but I will address that in a
subsequent PR.
#3395 ended up introducing a change that added a required field when
deserializing `InitializeResult`, breaking Codex when used as an MCP
client, so the quick fix in #3436 was to make the new field `Optional`
with `skip_serializing_if = "Option::is_none"`, but that did not address
the problem that `mcp-types/generate_mcp_types.py` and
`mcp-types/src/lib.rs` are out of sync.
This PR gets things back to where they are in sync. It removes the
custom `mcp_types::McpClientInfo` type that was added to
`mcp-types/src/lib.rs` and forces us to use the generated
`mcp_types::Implementation` type. Though this PR also updates
`generate_mcp_types.py` to generate the additional `user_agent:
Optional<String>` field on `Implementation` so that we can continue to
specify it when Codex operates as an MCP server.
However, this also requires us to specify `user_agent: None` when Codex
operates as an MCP client.
We may want to introduce our own `InitializeResult` type that is
specific to when we run as a server to avoid this in the future, but my
immediate goal is just to get things back in sync.
- Default to upstream outside protected paths
- Preserve codex-core public re-exports and models alias
- Purge-globs unchanged
Build: ./build-fast.sh ok; verify.sh ok
This PR adds an `images` field to the existing `UserMessageEvent` so we
can encode zero or more images associated with a user message. This
allows images to be restored when conversations are restored.
- Adopt upstream MCP user-agent handling in core/mcp; keep workspace-compatible wrappers
- Prefer theirs in core/protocol; preserve ours in TUI/CLI and workflows
- Purged any reintroduced codex-cli images per policy
verify: scripts/upstream-merge/verify.sh ok; build-fast.sh ok (no warnings)
James Peter