## Summary
#9555 is the start of a rename, so I'm starting to standardize here.
Sets up `model_instructions` templating with a strongly-typed object for
injecting a personality block into the model instructions.
## Testing
- [x] Added tests
- [x] Ran locally
## Summary
- Retire the experimental TUI2 implementation and its feature flag.
- Remove TUI2-only config/schema/docs so the CLI stays on the
terminal-native path.
- Keep docs aligned with the legacy TUI while we focus on redraw-based
improvements.
## Customer impact
- Retires the TUI2 experiment and keeps Codex on the proven
terminal-native UI while we invest in redraw-based improvements to the
existing experience.
## Migration / compatibility
- If you previously set tui2-related options in config.toml, they are
now ignored and Codex continues using the existing terminal-native TUI
(no action required).
## Context
- What worked: a transcript-owned viewport delivered excellent resize
rewrap and high-fidelity copy (especially for code).
- Why stop: making that experience feel fully native across the
environment matrix (terminal emulator, OS, input modality, multiplexer,
font/theme, alt-screen behavior) creates a combinatorial explosion of
edge cases.
- What next: we are focusing on redraw-based improvements to the
existing terminal-native TUI so scrolling, selection, and copy remain
native while resize/redraw correctness improves.
## Testing
- just write-config-schema
- just fmt
- cargo clippy --fix --all-features --tests --allow-dirty --allow-no-vcs
-p codex-core
- cargo clippy --fix --all-features --tests --allow-dirty --allow-no-vcs
-p codex-cli
- cargo check
- cargo test -p codex-core
- cargo test -p codex-cli
## Summary
- make paste-burst tests deterministic by injecting explicit timestamps
instead of relying on wall clock timing
- add time-aware helpers for input/submission paths so tests can drive
the burst heuristic precisely
- update burst-related tests to flush using computed timeouts while
preserving behavior assertions
- increase timeout slack in
shell_tools_start_before_response_completed_when_stream_delayed to
reduce flakiness
Follow up to #8956; publish schema on new release to stable URL.
Also canonicalize schema (sort keys) when writing. This avoids reliance
on default `schema_rs` behavior and makes the schema easier to read.
This PR adds support for chained (layered) config.toml file merging for
clients that use the app server interface. This feature already exists
for the TUI, but it does not work for GUI clients.
It does the following:
* Changes code paths for new thread, resume thread, and fork thread to
use the effective config based on the cwd.
* Updates the `config/read` API to accept an optional `cwd` parameter.
If specified, the API returns the effective config based on that cwd
path. Also optionally includes all layers including project config
files. If cwd is not specified, the API falls back on its older behavior
where it considers only the global (non-project) config files when
computing the effective config.
The changes in codex_message_processor.rs look deceptively large. They
mostly just involve moving existing blocks of code to a later point in
some functions so it can use the cwd to calculate the config.
This PR builds upon #9509 and should be reviewed and merged after that
PR.
Tested:
* Verified change with (dependent, as-yet-uncommitted) changes to IDE
Extension and confirmed correct behavior
The full fix requires additional changes in the IDE Extension code base,
but they depend on this PR.
## Summary
- add optional `collaboration_mode` to `TurnContextItem` in rollouts
- persist the current collaboration mode when recording turn context
(sampling + compaction)
## Rationale
We already persist turn context data for resume logic. Capturing
collaboration mode in the rollout gives us the mode context for each
turn, enabling follow‑up work to diff mode instructions correctly on
resume.
## Changes
- protocol: add optional `collaboration_mode` field to `TurnContextItem`
- core: persist collaboration mode alongside other turn context settings
in rollouts
This PR adds 2 defensive mechanisms for shell snapshotting:
* Filter out invalid env variables (containing `-` for example) without
dropping the whole snapshot
* Validate the snapshot before considering it as valid by running a mock
command with a shell snapshot
# 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.
## Summary
- Keep `request_user_input` in the tool list but reject it at runtime in
Execute/Custom modes with a clear model-facing error.
- Add a session accessor for current collaboration mode and enforce the
gate in the request_user_input handler.
- Update core/app-server tests to use Plan mode for success and add
Execute/Custom rejection coverage.
Using terminal with TERM=dumb specifically mean that TUIs and the like
don't work. Ensure that codex doesn't run in these environments and exit
with odd errors like crossterm's "Error: The cursor position could not
be read within a normal duration"
---------
Co-authored-by: Josh McKinney <joshka@openai.com>
### What
Implemented detection for dangerous "force delete" commands on Windows
to trigger the user approval prompt when `--ask-for-approval on-request`
is set. This aligns Windows behavior with the existing safety checks for
`rm -rf` on Linux.
### Why
Fixes#8567 - a critical safety gap where destructive Windows commands
could bypass the approval prompt. This prevents accidental data loss by
ensuring the user explicitly confirms operations that would otherwise
suppress the OS's native confirmation prompts.
### How
Updated the Windows command safety module to identify and flag the
following patterns as dangerous:
* **PowerShell**:
* Detects `Remove-Item` (and aliases `rm`, `ri`, `del`, `erase`, `rd`,
`rmdir`) when used with the `-Force` flag.
* Uses token-based analysis to robustly detect these patterns even
inside script blocks (`{...}`), sub-expression `(...)`, or
semicolon-chained sequences.
* **CMD**:
* Detects `del /f` (force delete files).
* Detects `rd /s /q` (recursive delete quiet).
* **Command Chaining**: Added support for analyzing chained commands
(using `&`, `&&`, `|`, `||`) to separate and check individual commands
(e.g., catching `del /f` hidden in `echo log & del /f data`).
### Testing
Added comprehensive unit tests covering:
* **PowerShell**: `Remove-Item -Path 'test' -Recurse -Force` (Exact
reproduction case).
* **Complex Syntax**: Verified detection inside blocks (e.g., `if
($true) { rm -Force }`) and with trailing punctuation.
* **CMD**:
* `del /f` (Flagged).
* `rd /s /q` (Flagged).
* Chained commands: `echo hi & del /f file` (Flagged).
* **False Positives**:
* `rd /s` (Not flagged - relies on native prompt).
* Standard deletions without force flags.
Verified with `cargo test` and `cargo clippy`.
---------
Co-authored-by: Eric Traut <etraut@openai.com>
## Summary
- Make `TextElement` placeholders private and add a text-backed accessor
to avoid assuming `Some`.
- Since they are optional in the protocol, we want to make sure any
accessors properly handle the None case (getting the placeholder using
the byte range in the text)
- Preserve placeholders during protocol/app-server conversions using the
accessor fallback.
- Update TUI composer/remap logic and tests to use the new
constructor/accessor.
We have `models.json` and `/models` response
Behavior:
1. New models from models endpoint gets added
2. Shared models get replaced by remote ones
3. Existing models in `models.json` but not `/models` are kept
4. Mark highest priority as default
Remove `FileTimes::new().set_modified(SystemTime::now())` when resuming
a thread.
Context: It's awkward in UI built on top of app-server that resuming a
thread bumps the `updated_at` timestamp, even if no message is sent. So
if you open a thread (perhaps to just view its contents), it
automatically reorders it to the top which is almost certainly not what
you want.
## What
Record a model-visible `<turn_aborted>` marker in history when a turn is
interrupted, and treat it as a session prefix.
## Why
When a turn is interrupted, Codex emits `TurnAborted` but previously did
not persist anything model-visible in the conversation history. On the
next user turn, the model can’t tell the previous work was aborted and
may resume/repeat earlier actions (including duplicated side effects
like re-opening PRs).
Fixes: https://github.com/openai/codex/issues/9042
## How
On `TurnAbortReason::Interrupted`, append a hidden user message
containing a `<turn_aborted>…</turn_aborted>` marker and flush.
Treat `<turn_aborted>` like `<environment_context>` for session-prefix
filtering.
Add a regression test to ensure follow-up turns don’t repeat side
effects from an aborted turn.
## Testing
`just fmt`
`just fix -p codex-core`
`cargo test -p codex-core -- --test-threads=1`
`cargo test --all-features -- --test-threads=1`
---------
Co-authored-by: Skylar Graika <sgraika127@gmail.com>
Co-authored-by: jif-oai <jif@openai.com>
Co-authored-by: Eric Traut <etraut@openai.com>
This PR fixes a small issue with chained (layered) config.toml file
merging. The old logic didn't properly handle profiles.
In particular, if a lower-layer config overrides a profile defined in a
higher-layer config, the override did not take effect. This prevents
users from having project-specific profile overrides and contradicts the
(soon-to-be) documented behavior of config merging.
The change adds a unit test for this case. It also exposes a function
from the config crate that is needed by the app server code paths to
implement support for layered configs.
## Summary
Introduces the concept of a config model_personality. I would consider
this an MVP for testing out the feature. There are a number of
follow-ups to this PR:
- More sophisticated templating with validation
- In-product experience to manage this
## Testing
- [x] Testing locally
Config includes multiple code execution entrypoints.
Now, we load the config from predetermined locations first
(~/.codex/config.toml etc), use those to learn which folders are
'trusted', and only load additional config from the CWD if it is
trusted.
Continuation of breaking up this PR
https://github.com/openai/codex/pull/9116
## Summary
- Thread user text element ranges through TUI/TUI2 input, submission,
queueing, and history so placeholders survive resume/edit flows.
- Preserve local image attachments alongside text elements and rehydrate
placeholders when restoring drafts.
- Keep model-facing content shapes clean by attaching UI metadata only
to user input/events (no API content changes).
## Key Changes
- TUI/TUI2 composer now captures text element ranges, trims them with
text edits, and restores them when submission is suppressed.
- User history cells render styled spans for text elements and keep
local image paths for future rehydration.
- Initial chat widget bootstraps accept empty `initial_text_elements` to
keep initialization uniform.
- Protocol/core helpers updated to tolerate the new InputText field
shape without changing payloads sent to the API.
## Summary
This PR consolidates base_instructions onto SessionMeta /
SessionConfiguration, so we ensure `base_instructions` is set once per
session and should be (mostly) immutable, unless:
- overridden by config on resume / fork
- sub-agent tasks, like review or collab
In a future PR, we should convert all references to `base_instructions`
to consistently used the typed struct, so it's less likely that we put
other strings there. See #9423. However, this PR is already quite
complex, so I'm deferring that to a follow-up.
## Testing
- [x] Added a resume test to assert that instructions are preserved. In
particular, `resume_switches_models_preserves_base_instructions` fails
against main.
Existing test coverage thats assert base instructions are preserved
across multiple requests in a session:
- Manual compact keeps baseline instructions:
core/tests/suite/compact.rs:199
- Auto-compact keeps baseline instructions:
core/tests/suite/compact.rs:1142
- Prompt caching reuses the same instructions across two requests:
core/tests/suite/prompt_caching.rs:150 and
core/tests/suite/prompt_caching.rs:157
- Prompt caching with explicit expected string across two requests:
core/tests/suite/prompt_caching.rs:213 and
core/tests/suite/prompt_caching.rs:222
- Resume with model switch keeps original instructions:
core/tests/suite/resume.rs:136
- Compact/resume/fork uses request 0 instructions for later expected
payloads: core/tests/suite/compact_resume_fork.rs:215
### Summary
* Added instruction on using `request_user_input`
* Added the output to be json with `plan` key and the actual plan as the
value.
* Remove `PLAN.md` write because that gets into sandbox issue. We can
add it back later.
Users of Azure endpoints are reporting that when they use `/review`,
they sometimes see an error "Invalid 'input[3].id". I suspect this is
specific to the Azure implementation of the `responses` API. The Azure
team generally copies the OpenAI code for this endpoint, but they do
have minor differences and sometimes lag in rolling out bug fixes or
updates.
The error appears to be triggered because the `/review` implementation
is using a user ID with a colon in it.
Addresses #9360
We already support reading from `config.toml` through a symlink, but the
code was not properly handling updates to a symlinked config file. This
PR generalizes safe symlink-chain resolution and atomic writes into
path_utils, updating all config write paths to use the shared logic
(including set_default_oss_provider, which previously didn't use the
common path), and adds tests for symlink chains and cycles.
This resolves#6646.
Notes:
* Symlink cycles or resolution failures replace the top-level symlink
with a real file.
* Shared config write path now handles symlinks consistently across
edits, defaults, and empty-user-layer creation.
This PR was inspired by https://github.com/openai/codex/pull/9437, which
was contributed by @ryoppippi
# 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.
### Description
- Remove the now-unused `instructions` field from the session metadata
to simplify SessionMeta and stop propagating transient instruction text
through the rollout recorder API. This was only saving
user_instructions, and was never being read.
- Stop passing user instructions into the rollout writer at session
creation so the rollout header only contains canonical session metadata.
### Testing
- Ran `just fmt` which completed successfully.
- Ran `just fix -p codex-protocol`, `just fix -p codex-core`, `just fix
-p codex-app-server`, `just fix -p codex-tui`, and `just fix -p
codex-tui2` which completed (Clippy fixes applied) as part of
verification.
- Ran `cargo test -p codex-protocol` which passed (28 tests).
- Ran `cargo test -p codex-core` which showed failures in a small set of
tests (not caused by the protocol type change directly):
`default_client::tests::test_create_client_sets_default_headers`,
several `models_manager::manager::tests::refresh_available_models_*`,
and `shell_snapshot::tests::linux_sh_snapshot_includes_sections` (these
tests failed in this CI run).
- Ran `cargo test -p codex-app-server` which reported several failing
integration tests (including
`suite::codex_message_processor_flow::test_codex_jsonrpc_conversation_flow`,
`suite::output_schema::send_user_turn_*`, and
`suite::user_agent::get_user_agent_returns_current_codex_user_agent`).
- `cargo test -p codex-tui` and `cargo test -p codex-tui2` were
attempted but aborted due to disk space exhaustion (`No space left on
device`).
------
[Codex
Task](https://chatgpt.com/codex/tasks/task_i_696bd8ce632483228d298cf07c7eb41c)
xl-openaiandGitHub
Dylan HurdandGitHub
Josh McKinneyandGitHub
charley-oaiandGitHub
sayan-oaiandGitHub
Eric TrautandGitHub
Shijie RaoandGitHub
jif-oaiandGitHub
pakrym-oaiandGitHub
alexsong-oaiandGitHub
Michael BolinandGitHub
Ahmed IbrahimandGitHub
Owen LinandGitHub
Simon WillisonandGitHub
Anton PanasenkoandGitHub
gt-oaiandGitHub
