## 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`.
## Why
`argument-comment-lint` was green in CI even though the repo still had
many uncommented literal arguments. The main gap was target coverage:
the repo wrapper did not force Cargo to inspect test-only call sites, so
examples like the `latest_session_lookup_params(true, ...)` tests in
`codex-rs/tui_app_server/src/lib.rs` never entered the blocking CI path.
This change cleans up the existing backlog, makes the default repo lint
path cover all Cargo targets, and starts rolling that stricter CI
enforcement out on the platform where it is currently validated.
## What changed
- mechanically fixed existing `argument-comment-lint` violations across
the `codex-rs` workspace, including tests, examples, and benches
- updated `tools/argument-comment-lint/run-prebuilt-linter.sh` and
`tools/argument-comment-lint/run.sh` so non-`--fix` runs default to
`--all-targets` unless the caller explicitly narrows the target set
- fixed both wrappers so forwarded cargo arguments after `--` are
preserved with a single separator
- documented the new default behavior in
`tools/argument-comment-lint/README.md`
- updated `rust-ci` so the macOS lint lane keeps the plain wrapper
invocation and therefore enforces `--all-targets`, while Linux and
Windows temporarily pass `-- --lib --bins`
That temporary CI split keeps the stricter all-targets check where it is
already cleaned up, while leaving room to finish the remaining Linux-
and Windows-specific target-gated cleanup before enabling
`--all-targets` on those runners. The Linux and Windows failures on the
intermediate revision were caused by the wrapper forwarding bug, not by
additional lint findings in those lanes.
## Validation
- `bash -n tools/argument-comment-lint/run.sh`
- `bash -n tools/argument-comment-lint/run-prebuilt-linter.sh`
- shell-level wrapper forwarding check for `-- --lib --bins`
- shell-level wrapper forwarding check for `-- --tests`
- `just argument-comment-lint`
- `cargo test` in `tools/argument-comment-lint`
- `cargo test -p codex-terminal-detection`
## Follow-up
- Clean up remaining Linux-only target-gated callsites, then switch the
Linux lint lane back to the plain wrapper invocation.
- Clean up remaining Windows-only target-gated callsites, then switch
the Windows lint lane back to the plain wrapper invocation.
Migrate `cwd` and related session/config state to `AbsolutePathBuf` so
downstream consumers consistently see absolute working directories.
Add test-only `.abs()` helpers for `Path`, `PathBuf`, and `TempDir`, and
update branch-local tests to use them instead of
`AbsolutePathBuf::try_from(...)`.
For the remaining TUI/app-server snapshot coverage that renders absolute
cwd values, keep the snapshots unchanged and skip the Windows-only cases
where the platform-specific absolute path layout differs.
## Summary
This PR keeps app-server RPC request trace context alive for the full
lifetime of the work that request kicks off (e.g. for `thread/start`,
this is `app-server rpc handler -> tokio background task -> core op
submissions`). Previously we lose trace lineage once the request handler
returns or hands work off to background tasks.
This approach is especially relevant for `thread/start` and other RPC
handlers that run in a non-blocking way. In the near future we'll most
likely want to make all app-server handlers run in a non-blocking way by
default, and only queue operations that must operate in order (e.g.
thread RPCs per thread?), so we want to make sure tracing in app-server
just generally works.
Depends on https://github.com/openai/codex/pull/14300
**Before**
<img width="155" height="207" alt="image"
src="https://github.com/user-attachments/assets/c9487459-36f1-436c-beb7-fafeb40737af"
/>
**After**
<img width="299" height="337" alt="image"
src="https://github.com/user-attachments/assets/727392b2-d072-4427-9dc4-0502d8652dea"
/>
## What changed
- Keep request-scoped trace context around until we send the final
response or error, or the connection closes.
- Thread that trace context through detached `thread/start` work so
background startup stays attached to the originating request.
- Pass request trace context through to downstream core operations,
including:
- thread creation
- resume/fork flows
- turn submission
- review
- interrupt
- realtime conversation operations
- Add tracing tests that verify:
- remote W3C trace context is preserved for `thread/start`
- remote W3C trace context is preserved for `turn/start`
- downstream core spans stay under the originating request span
- request-scoped tracing state is cleaned up correctly
- Clean up shutdown behavior so detached background tasks and spawned
threads are drained before process exit.
This PR adds a durable trace linkage for each turn by storing the active
trace ID on the rollout TurnContext record stored in session rollout
files.
Before this change, we propagated trace context at runtime but didn’t
persist a stable per-turn trace key in rollout history. That made
after-the-fact debugging harder (for example, mapping a historical turn
to the corresponding trace in datadog). This sets us up for much easier
debugging in the future.
### What changed
- Added an optional `trace_id` to TurnContextItem (rollout schema).
- Added a small OTEL helper to read the current span trace ID.
- Captured `trace_id` when creating `TurnContext` and included it in
`to_turn_context_item()`.
- Updated tests and fixtures that construct TurnContextItem so
older/no-trace cases still work.
### Why this approach
TurnContext is already the canonical durable per-turn metadata in
rollout. This keeps ownership clean: trace linkage lives with other
persisted turn metadata.
## Summary
- record a realtime close developer message when a new realtime session
replaces an active one
- assert the replacement marker through the mocked responses request
path
---------
Co-authored-by: Codex <noreply@openai.com>
Co-authored-by: Charles Cunningham <ccunningham@openai.com>
## Summary
This PR includes the session's local date and timezone in the
model-visible environment context and persists that data in
`TurnContextItem`.
## What changed
- captures the current local date and IANA timezone when building a turn
context, with a UTC fallback if the timezone lookup fails
- includes current_date and timezone in the serialized
<environment_context> payload
- stores those fields on TurnContextItem so they survive rollout/history
handling, subagent review threads, and resume flows
- treats date/timezone changes as environment updates, so prompt caching
and context refresh logic do not silently reuse stale time context
- updates tests to validate the new environment fields without depending
on a single hardcoded environment-context string
## test
built a local build and saw it in the rollout file:
```
{"timestamp":"2026-02-26T21:39:50.737Z","type":"response_item","payload":{"type":"message","role":"user","content":[{"type":"input_text","text":"<environment_context>\n <shell>zsh</shell>\n <current_date>2026-02-26</current_date>\n <timezone>America/Los_Angeles</timezone>\n</environment_context>"}]}}
```
## Summary
- make `Config.model_reasoning_summary` optional so unset means use
model default
- resolve the optional config value to a concrete summary when building
`TurnContext`
- add protocol support for `default_reasoning_summary` in model metadata
## Validation
- `cargo test -p codex-core --lib client::tests -- --nocapture`
---------
Co-authored-by: Codex <noreply@openai.com>
## Why
`codex-rs/core/src/lib.rs` re-exported a broad set of types and modules
from `codex-protocol` and `codex-shell-command`. That made it easy for
workspace crates to import those APIs through `codex-core`, which in
turn hides dependency edges and makes it harder to reduce compile-time
coupling over time.
This change removes those public re-exports so call sites must import
from the source crates directly. Even when a crate still depends on
`codex-core` today, this makes dependency boundaries explicit and
unblocks future work to drop `codex-core` dependencies where possible.
## What Changed
- Removed public re-exports from `codex-rs/core/src/lib.rs` for:
- `codex_protocol::protocol` and related protocol/model types (including
`InitialHistory`)
- `codex_protocol::config_types` (`protocol_config_types`)
- `codex_shell_command::{bash, is_dangerous_command, is_safe_command,
parse_command, powershell}`
- Migrated workspace Rust call sites to import directly from:
- `codex_protocol::protocol`
- `codex_protocol::config_types`
- `codex_protocol::models`
- `codex_shell_command`
- Added explicit `Cargo.toml` dependencies (`codex-protocol` /
`codex-shell-command`) in crates that now import those crates directly.
- Kept `codex-core` internal modules compiling by using `pub(crate)`
aliases in `core/src/lib.rs` (internal-only, not part of the public
API).
- Updated the two utility crates that can already drop a `codex-core`
dependency edge entirely:
- `codex-utils-approval-presets`
- `codex-utils-cli`
## Verification
- `cargo test -p codex-utils-approval-presets`
- `cargo test -p codex-utils-cli`
- `cargo check --workspace --all-targets`
- `just clippy`
## Summary
- move regular-turn context diff/full-context persistence into
`run_turn` so pre-turn compaction runs before incoming context updates
are recorded
- after successful pre-turn compaction, rely on a cleared
`reference_context_item` to trigger full context reinjection on the
follow-up regular turn (manual `/compact` keeps replacement history
summary-only and also clears the baseline)
- preserve `<model_switch>` when full context is reinjected, and inject
it *before* the rest of the full-context items
- scope `reference_context_item` and `previous_model` to regular user
turns only so standalone tasks (`/compact`, shell, review, undo) cannot
suppress future reinjection or `<model_switch>` behavior
- make context-diff persistence + `reference_context_item` updates
explicit in the regular-turn path, with clearer docs/comments around the
invariant
- stop persisting local `/compact` `RolloutItem::TurnContext` snapshots
(only regular turns persist `TurnContextItem` now)
- simplify resume/fork previous-model/reference-baseline hydration by
looking up the last surviving turn context from rollout lifecycle
events, including rollback and compaction-crossing handling
- remove the legacy fallback that guessed from bare `TurnContext`
rollouts without lifecycle events
- update compaction/remote-compaction/model-visible snapshots and
compact test assertions (including remote compaction mock response
shape)
## Why
We were persisting incoming context items before spawning the regular
turn task, which let pre-turn compaction requests accidentally include
incoming context diffs without the new user message. Fixing that exposed
follow-on baseline issues around `/compact`, resume/fork, and standalone
tasks that could cause duplicate context injection or suppress
`<model_switch>` instructions.
This PR re-centers the invariants around regular turns:
- regular turns persist model-visible context diffs/full reinjection and
update the `reference_context_item`
- standalone tasks do not advance those regular-turn baselines
- compaction clears the baseline when replacement history may have
stripped the referenced context diffs
## Follow-ups (TODOs left in code)
- `TODO(ccunningham)`: fix rollback/backtracking baseline handling more
comprehensively
- `TODO(ccunningham)`: include pending incoming context items in
pre-turn compaction threshold estimation
- `TODO(ccunningham)`: inject updated personality spec alongside
`<model_switch>` so some model-switch paths can avoid forced full
reinjection
- `TODO(ccunningham)`: review task turn lifecycle
(`TurnStarted`/`TurnComplete`) behavior and emit task-start context
diffs for task types that should have them (excluding `/compact`)
## Validation
- `just fmt`
- CI should cover the updated compaction/resume/model-visible snapshot
expectations and rollout-hydration behavior
- I did **not** rerun the full local test suite after the latest
resume-lookup / rollout-persistence simplifications
### What
It's currently unclear when the harness falls back to the default,
generic `ModelInfo`. This happens when the `remote_models` feature is
disabled or the model is truly unknown, and can lead to bad performance
and issues in the harness.
Add a user-facing warning when this happens so they are aware when their
setup is broken.
### Tests
Added tests, tested locally.
## Summary
This PR delivers the first small, shippable step toward model-visible
state diffing by making
`TurnContextItem` more complete and standardizing how it is built.
Specifically, it:
- Adds persisted network context to `TurnContextItem`.
- Introduces a single canonical `TurnContext -> TurnContextItem`
conversion path.
- Routes existing rollout write sites through that canonical conversion
helper.
No context injection/diff behavior changes are included in this PR.
## Why this change
The design goal is to make `TurnContextItem` the canonical source of
truth for context-diff
decisions.
Before this PR:
- `TurnContextItem` did not include all TurnContext-derived environment
inputs needed for v1
completeness.
- Construction was duplicated at multiple write sites.
This PR addresses both with a minimal, reviewable change.
## Changes
### 1) Extend `TurnContextItem` with network state
- Added `TurnContextNetworkItem { allowed_domains, denied_domains }`.
- Added `network: Option<TurnContextNetworkItem>` to `TurnContextItem`.
- Kept backward compatibility by making the new field optional and
skipped when absent.
Files:
- `codex-rs/protocol/src/protocol.rs`
### 2) Canonical conversion helper
- Added `TurnContext::to_turn_context_item(collaboration_mode)` in core.
- Added internal helper to derive network fields from
`config_layer_stack.requirements().network`.
Files:
- `codex-rs/core/src/codex.rs`
### 3) Use canonical conversion at rollout write sites
- Replaced ad hoc `TurnContextItem { ... }` construction with
`to_turn_context_item(...)` in:
- sampling request path
- compaction path
Files:
- `codex-rs/core/src/codex.rs`
- `codex-rs/core/src/compact.rs`
### 4) Update fixtures/tests for new optional field
- Updated existing `TurnContextItem` literals in tests to include
`network: None`.
- Added protocol tests for:
- deserializing old payloads with no `network`
- serializing when `network` is present
Files:
- `codex-rs/core/tests/suite/resume_warning.rs`
- No replay/diff logic changes.
- Persisted rollout `TurnContextItem` now carries additional network
context when available.
- Older rollout lines without `network` remain readable.
## Why
We currently carry multiple permission-related concepts directly on
`Config` for shell/unified-exec behavior (`approval_policy`,
`sandbox_policy`, `network`, `shell_environment_policy`,
`windows_sandbox_mode`).
Consolidating these into one in-memory struct makes permission handling
easier to reason about and sets up the next step: supporting named
permission profiles (`[permissions.PROFILE_NAME]`) without changing
behavior now.
This change is mostly mechanical: it updates existing callsites to go
through `config.permissions`, but it does not yet refactor those
callsites to take a single `Permissions` value in places where multiple
permission fields are still threaded separately.
This PR intentionally **does not** change the on-disk `config.toml`
format yet and keeps compatibility with legacy config keys.
## What Changed
- Introduced `Permissions` in `core/src/config/mod.rs`.
- Added `Config::permissions` and moved effective runtime permission
fields under it:
- `approval_policy`
- `sandbox_policy`
- `network`
- `shell_environment_policy`
- `windows_sandbox_mode`
- Updated config loading/building so these effective values are still
derived from the same existing config inputs and constraints.
- Updated Windows sandbox helpers/resolution to read/write via
`permissions`.
- Threaded the new field through all permission consumers across core
runtime, app-server, CLI/exec, TUI, and sandbox summary code.
- Updated affected tests to reference `config.permissions.*`.
- Renamed the struct/field from
`EffectivePermissions`/`effective_permissions` to
`Permissions`/`permissions` and aligned variable naming accordingly.
## Verification
- `just fix -p codex-core -p codex-tui -p codex-cli -p codex-app-server
-p codex-exec -p codex-utils-sandbox-summary`
- `cargo build -p codex-core -p codex-tui -p codex-cli -p
codex-app-server -p codex-exec -p codex-utils-sandbox-summary`
This PR adds an experimental `persist_extended_history` bool flag to
app-server thread APIs so rollout logs can retain a richer set of
EventMsgs for non-lossy Thread > Turn > ThreadItems reconstruction (i.e.
on `thread/resume`).
### Motivation
Today, our rollout recorder only persists a small subset (e.g. user
message, reasoning, assistant message) of `EventMsg` types, dropping a
good number (like command exec, file change, etc.) that are important
for reconstructing full item history for `thread/resume`, `thread/read`,
and `thread/fork`.
Some clients want to be able to resume a thread without lossiness. This
lossiness is primarily a UI thing, since what the model sees are
`ResponseItem` and not `EventMsg`.
### Approach
This change introduces an opt-in `persist_full_history` flag to preserve
those events when you start/resume/fork a thread (defaults to `false`).
This is done by adding an `EventPersistenceMode` to the rollout
recorder:
- `Limited` (existing behavior, default)
- `Extended` (new opt-in behavior)
In `Extended` mode, persist additional `EventMsg` variants needed for
non-lossy app-server `ThreadItem` reconstruction. We now store the
following ThreadItems that we didn't before:
- web search
- command execution
- patch/file changes
- MCP tool calls
- image view calls
- collab tool outcomes
- context compaction
- review mode enter/exit
For **command executions** in particular, we truncate the output using
the existing `truncate_text` from core to store an upper bound of 10,000
bytes, which is also the default value for truncating tool outputs shown
to the model. This keeps the size of the rollout file and command
execution items returned over the wire reasonable.
And we also persist `EventMsg::Error` which we can now map back to the
Turn's status and populates the Turn's error metadata.
#### Updates to EventMsgs
To truly make `thread/resume` non-lossy, we also needed to persist the
`status` on `EventMsg::CommandExecutionEndEvent` and
`EventMsg::PatchApplyEndEvent`. Previously it was not obvious whether a
command failed or was declined (similar for apply_patch). These
EventMsgs were never persisted before so I made it a required field.
## Why
`codex-core` was being built in multiple feature-resolved permutations
because test-only behavior was modeled as crate features. For a large
crate, those permutations increase compile cost and reduce cache reuse.
## Net Change
- Removed the `test-support` crate feature and related feature wiring so
`codex-core` no longer needs separate feature shapes for test consumers.
- Standardized cross-crate test-only access behind
`codex_core::test_support`.
- External test code now imports helpers from
`codex_core::test_support`.
- Underlying implementation hooks are kept internal (`pub(crate)`)
instead of broadly public.
## Outcome
- Fewer `codex-core` build permutations.
- Better incremental cache reuse across test targets.
- No intended production behavior change.
Problem:
1. turn id is constructed in-memory;
2. on resuming threads, turn_id might not be unique;
3. client cannot no the boundary of a turn from rollout files easily.
This PR does three things:
1. persist `task_started` and `task_complete` events;
1. persist `turn_id` in rollout turn events;
5. generate turn_id as unique uuids instead of incrementing it in
memory.
This helps us resolve the issue of clients wanting to have unique turn
ids for resuming a thread, and knowing the boundry of each turn in
rollout files.
example debug logs
```
2026-02-11T00:32:10.746876Z DEBUG codex_app_server_protocol::protocol::thread_history: built turn from rollout items turn_index=8 turn=Turn { id: "019c4a07-d809-74c3-bc4b-fd9618487b4b", items: [UserMessage { id: "item-24", content: [Text { text: "hi", text_elements: [] }] }, AgentMessage { id: "item-25", text: "Hi. I’m in the workspace with your current changes loaded and ready. Send the next task and I’ll execute it end-to-end." }], status: Completed, error: None }
2026-02-11T00:32:10.746888Z DEBUG codex_app_server_protocol::protocol::thread_history: built turn from rollout items turn_index=9 turn=Turn { id: "019c4a18-1004-76c0-a0fb-a77610f6a9b8", items: [UserMessage { id: "item-26", content: [Text { text: "hello", text_elements: [] }] }, AgentMessage { id: "item-27", text: "Hello. Ready for the next change in `codex-rs`; I can continue from the current in-progress diff or start a new task." }], status: Completed, error: None }
2026-02-11T00:32:10.746899Z DEBUG codex_app_server_protocol::protocol::thread_history: built turn from rollout items turn_index=10 turn=Turn { id: "019c4a19-41f0-7db0-ad78-74f1503baeb8", items: [UserMessage { id: "item-28", content: [Text { text: "hello", text_elements: [] }] }, AgentMessage { id: "item-29", text: "Hello. Send the specific change you want in `codex-rs`, and I’ll implement it and run the required checks." }], status: Completed, error: None }
```
backward compatibility:
if you try to resume an old session without task_started and
task_complete event populated, the following happens:
- If you resume and do nothing: those reconstructed historical IDs can
differ next time you resume.
- If you resume and send a new turn: the new turn gets a fresh UUID from
live submission flow and is persisted, so that new turn’s ID is stable
on later resumes.
I think this behavior is fine, because we only care about deterministic
turn id once a turn is triggered.
## Summary
Support updating Personality mid-Thread via UserTurn/OverwriteTurn. This
is explicitly unused by the clients so far, to simplify PRs - app-server
and tui implementations will be follow-ups.
## Testing
- [x] added integration tests
## 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
## 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
### Motivation
- Persist richer per-turn configuration in rollouts so resumed/forked
sessions and tooling can reason about the exact instruction inputs and
output constraints used for a turn.
### Description
- Extend `TurnContextItem` to include optional `base_instructions`,
`user_instructions`, and `developer_instructions`.
- Record the optional `final_output_json_schema` associated with a turn.
- Add an optional `truncation_policy` to `TurnContextItem` and populate
it when writing turn-context rollout items.
- Introduce a protocol-level `TruncationPolicy` representation and
convert from core truncation policy when recording.
### Testing
- `cargo test -p codex-protocol` (pass)
This adds support for `allowed_sandbox_modes` in `requirements.toml` and
provides legacy support for constraining sandbox modes in
`managed_config.toml`. This is converted to `Constrained<SandboxPolicy>`
in `ConfigRequirements` and applied to `Config` such that constraints
are enforced throughout the harness.
Note that, because `managed_config.toml` is deprecated, we do not add
support for the new `external-sandbox` variant recently introduced in
https://github.com/openai/codex/pull/8290. As noted, that variant is not
supported in `config.toml` today, but can be configured programmatically
via app server.
https://github.com/openai/codex/pull/8235 introduced `ConfigBuilder` and
this PR updates all call non-test call sites to use it instead of
`Config::load_from_base_config_with_overrides()`.
This is important because `load_from_base_config_with_overrides()` uses
an empty `ConfigRequirements`, which is a reasonable default for testing
so the tests are not influenced by the settings on the host. This method
is now guarded by `#[cfg(test)]` so it cannot be used by business logic.
Because `ConfigBuilder::build()` is `async`, many of the test methods
had to be migrated to be `async`, as well. On the bright side, this made
it possible to eliminate a bunch of `block_on_future()` stuff.
Constrain `approval_policy` through new `admin_policy` config.
This PR will:
1. Add a `admin_policy` section to config, with a single field (for now)
`allowed_approval_policies`. This list constrains the set of
user-settable `approval_policy`s.
2. Introduce a new `Constrained<T>` type, which combines a current value
and a validator function. The validator function ensures disallowed
values are not set.
3. Change the type of `approval_policy` on `Config` and
`SessionConfiguration` from `AskForApproval` to
`Constrained<AskForApproval>`. The validator function is set by the
values passed into `allowed_approval_policies`.
4. `GenericDisplayRow`: add a `disabled_reason: Option<String>`. When
set, it disables selection of the value and indicates as such in the
menu. This also makes it unselectable with arrow keys or numbers. This
is used in the `/approvals` menu.
Follow ups are:
1. Do the same thing to `sandbox_policy`.
2. Propagate the allowed set of values through app-server for the
extension (though already this should prevent app-server from setting
this values, it's just that we want to disable UI elements that are
unsettable).
Happy to split this PR up if you prefer, into the logical numbered areas
above. Especially if there are parts we want to gavel on separately
(e.g. admin_policy).
Disabled full access:
<img width="1680" height="380" alt="image"
src="https://github.com/user-attachments/assets/1fb61c8c-1fcb-4dc4-8355-2293edb52ba0"
/>
Disabled `--yolo` on startup:
<img width="749" height="76" alt="image"
src="https://github.com/user-attachments/assets/0a1211a0-6eb1-40d6-a1d7-439c41e94ddb"
/>
CODEX-4087
- Make Config.model optional and centralize default-selection logic in
ModelsManager, including a default_model helper (with
codex-auto-balanced when available) so sessions now carry an explicit
chosen model separate from the base config.
- Resolve `model` once in `core` and `tui` from config. Then store the
state of it on other structs.
- Move refreshing models to be before resolving the default model
