8f705b0702
## Summary - keep pending steered input buffered until the active user prompt has received a model response - keep steering pending across auto-compact when there is real model/tool continuation to resume - allow queued steering to follow compaction immediately when the prior model response was already final - keep pending-input follow-up owned by `run_turn` instead of folding it into `SamplingRequestResult` - add regression coverage for mid-turn compaction, final-response compaction, and compaction triggered before the next request after tool output ## Root Cause Steered input was drained at the top of every `run_turn` loop. After auto-compaction, the loop continued and immediately appended any pending steer after the compact summary, making a queued prompt look like the newest task instead of letting the model first resume interrupted model/tool work. ## Implementation Notes This patch keeps the follow-up signals separated: - `SamplingRequestResult.needs_follow_up` means model/tool continuation is needed - `sess.has_pending_input().await` means queued user steering exists - `run_turn` computes the combined loop condition from those two signals In `run_turn`: ```rust let has_pending_input = sess.has_pending_input().await; let needs_follow_up = model_needs_follow_up || has_pending_input; ``` After auto-compact we choose whether the next request may drain steering: ```rust can_drain_pending_input = !model_needs_follow_up; ``` That means: - model/tool continuation + pending steer: compact -> resume once without draining steer - completed model answer + pending steer: compact -> drain/send the steer immediately - fresh user prompt: do not drain steering before the model has answered the prompt once The drain is still only `sess.get_pending_input().await`; when `can_drain_pending_input` is false, core uses an empty local vec and leaves the steer pending in session state. ## Validation - PASS `cargo test -p codex-core --test all steered_user_input -- --nocapture` - PASS `just fmt` - PASS `git diff --check` - NOT PASSING HERE `just fix -p codex-core` currently stops before linting this change on an unrelated mainline test-build error: `core/src/tools/spec_tests.rs` initializes `ToolsConfigParams` without `image_generation_tool_auth_allowed`; this PR does not touch that file.
codex-core
This crate implements the business logic for Codex. It is designed to be used by the various Codex UIs written in Rust.
Dependencies
Note that codex-core makes some assumptions about certain helper utilities being available in the environment. Currently, this support matrix is:
macOS
Expects /usr/bin/sandbox-exec to be present.
When using the workspace-write sandbox policy, the Seatbelt profile allows
writes under the configured writable roots while keeping .git (directory or
pointer file), the resolved gitdir: target, and .codex read-only.
Network access and filesystem read/write roots are controlled by
SandboxPolicy. Seatbelt consumes the resolved policy and enforces it.
Seatbelt also keeps the legacy default preferences read access
(user-preference-read) needed for cfprefs-backed macOS behavior.
Linux
Expects the binary containing codex-core to run the equivalent of codex sandbox linux (legacy alias: codex debug landlock) when arg0 is codex-linux-sandbox. See the codex-arg0 crate for details.
Legacy SandboxPolicy / sandbox_mode configs are still supported on Linux.
They can continue to use the legacy Landlock path when the split filesystem
policy is sandbox-equivalent to the legacy model after cwd resolution.
Split filesystem policies that need direct FileSystemSandboxPolicy
enforcement, such as read-only or denied carveouts under a broader writable
root, automatically route through bubblewrap. The legacy Landlock path is used
only when the split filesystem policy round-trips through the legacy
SandboxPolicy model without changing semantics. That includes overlapping
cases like /repo = write, /repo/a = none, /repo/a/b = write, where the
more specific writable child must reopen under a denied parent.
The Linux sandbox helper prefers the first bwrap found on PATH outside the
current working directory whenever it is available. If bwrap is present but
too old to support --argv0, the helper keeps using system bubblewrap and
switches to a no---argv0 compatibility path for the inner re-exec. If
bwrap is missing, it falls back to the vendored bubblewrap path compiled into
the binary and Codex surfaces a startup warning through its normal notification
path instead of printing directly from the sandbox helper. Codex also surfaces
a startup warning when bubblewrap cannot create user namespaces.
Windows
Legacy SandboxPolicy / sandbox_mode configs are still supported on
Windows.
The elevated setup/runner backend supports legacy ReadOnlyAccess::Restricted
for read-only and workspace-write policies. Restricted read access honors
explicit readable roots plus the command cwd, and keeps writable roots
readable when workspace-write is used.
When include_platform_defaults = true, the elevated Windows backend adds
backend-managed system read roots required for basic execution, such as
C:\Windows, C:\Program Files, C:\Program Files (x86), and
C:\ProgramData. When it is false, those extra system roots are omitted.
The unelevated restricted-token backend still supports the legacy full-read
Windows model for legacy ReadOnly and WorkspaceWrite behavior. It also
supports a narrow split-filesystem subset: full-read split policies whose
writable roots still match the legacy WorkspaceWrite root set, but add extra
read-only carveouts under those writable roots.
New [permissions] / split filesystem policies remain supported on Windows
only when they round-trip through the legacy SandboxPolicy model without
changing semantics. Policies that would require direct read restriction,
explicit unreadable carveouts, reopened writable descendants under read-only
carveouts, different writable root sets, or split carveout support in the
elevated setup/runner backend still fail closed instead of running with weaker
enforcement.
All Platforms
Expects the binary containing codex-core to simulate the virtual apply_patch CLI when arg1 is --codex-run-as-apply-patch. See the codex-arg0 crate for details.