## What changed
- Centralize `windows-sys` at version `0.61.2` in the workspace and migrate dependent crates to it.
- Adapt Windows API calls to the updated handle, boolean, and type definitions. Replace custom handle owners with `OwnedHandle` and use `BorrowedHandle` where ownership stays with the caller.
- Add explicit wrappers for non-owning Windows handles passed between threads.
## Testing
Enable the MCP refresh cleanup test on Windows. Retain process handles to verify that a superseded MCP server stays alive during an in-flight call, exits after cancellation, and leaves the replacement running until shutdown.
GitOrigin-RevId: 86f53d9b300d13edff7154f4a7c32e34dacd2919
## Why
Concurrent Linux test spawns can inherit writable descriptors for executable fixtures, preventing those fixtures from being executed even after the writing test closes its descriptor.
## What changed
Replace direct executable fixture writes and copies across the Rust tests with `codex_utils_cargo_bin::write_executable` and `copy_executable`. These existing helpers complete writes and copies in separate processes on Linux.
Remove the empty temporary inode before creating fake bubblewrap executables, and stage tampered bubblewrap bytes in a separate data file before copying them into the executable fixture. Add the required test dependencies.
GitOrigin-RevId: c875c83088731a4933ef1574e8d79d8cecc12f54
## Why
Token-budget truncation uses byte counts to estimate tokens, but previously scanned the entire string to count characters, including the discarded middle.
## What changed
Use UTF-8 boundary lookups to select the retained prefix and suffix for token-budget truncation. Skip character counting for a zero-token budget and defer it to paths that need character counts.
## Testing
Add regression coverage for multibyte characters crossing both retained boundaries, checking the truncated output and original token estimate.
GitOrigin-RevId: 37fee0c8d4ede8e74b491d3d641b0ea0e9003dd4
## Why
`LegacyAppPathString` treated `//server/share/project` as POSIX, losing its UNC interpretation when inferring a `PathUri`.
## What changed
Infer Windows syntax whenever an API path starts with two separators, including forward and mixed slashes, independently of the host. For example, `//server/share/project` now converts to `file://server/share/project`. Double-slash POSIX paths require an explicit `PathConvention::Posix`; inferred paths still undergo validation.
## Testing
Add regression tests for UNC and namespace paths, mixed separators, URI serialization round trips, explicit POSIX conversion, convention mismatches, and malformed UNC paths.
GitOrigin-RevId: 720893de517addb7a938e6784d1ed0f05df3ec0d
## Why
Opaque Windows paths encoded as UTF-16LE could be mistaken for POSIX paths when they began with `/`, or fail Windows convention inference when their leading separators mixed `/` and `\`. This prevented them from retaining the Windows path convention across URI serialization.
## What changed
Distinguish a UTF-16LE slash from a POSIX root and recognize either Windows separator in both positions of an opaque UNC prefix.
## Testing
Add round-trip coverage for Windows drive, UNC, device, and namespace paths, including forward and mixed separators. Cover JSON serialization, absolute-path joins, relative-path separator handling, and Windows-only host-native conversions.
GitOrigin-RevId: d4e8a40a314cfc030c30fa8c124bfdd1e565076d
## Why
Parsing multiple tag delimiters in a chunk repeatedly drained the pending
buffer, shifting its remaining contents after each delimiter.
## What changed
Track a consumed offset in `InlineHiddenTagParser::push_str` and drain the
buffer once after processing the chunk, preserving partial delimiters for
the next chunk.
## Testing
Add a regression test comparing visible text and extracted tags against
single-chunk parsing at every UTF-8 character boundary. The input covers
non-ASCII text and delimiters, adjacent tags, an empty tag, and an unfinished
tag at end of input.
GitOrigin-RevId: 18bfbfdb81060ffda30901d5cb82ee5804878b09
## Why
Background helpers launched from a detached Windows process can allocate console windows. Job Object launches and containment fallbacks need to preserve console suppression as well.
## What changed
- Add `codex_utils_process::background_command` to set `CREATE_NO_WINDOW` on Windows, and use it across background subprocess launches, including Git, plugins, authentication, diagnostics, and sandbox helpers.
- Centralize console suppression in Job Object launches. Keep `CREATE_NO_WINDOW` when retrying without containment, and clear `CREATE_SUSPENDED` so the fallback child can run.
- Preserve console inheritance for interactive shell launches and interactive AWS authentication refreshes.
## Testing
Add Windows regression tests covering console-free launches from detached parents through standard and Tokio commands, stdout/stderr capture, successful containment, Job Object creation and assignment failures, and sandbox setup refresh helpers.
GitOrigin-RevId: b2c238fa7d4f9fbd868e5adf7d4be9958ff01e6c
## Why
Concurrent tests can inherit writable descriptors for executable fixtures, causing `ETXTBSY` when those fixtures launch on Linux.
## What changed
Expose shared `write_executable` and `copy_executable` helpers from `codex_utils_cargo_bin` and adopt them in CLI, exec-server, and MCP tests. On Linux, writes and copies complete in separate processes so sibling test spawns cannot inherit the writable descriptors. Script fixtures receive mode `0o755`, and copied executables retain their source permissions.
Remove the executable-busy retry loop from the program resolver test now that its script uses the shared helper.
GitOrigin-RevId: 61624158190bb1e75c27d9eb9c87a2defc147fb7
## Why
Piped child processes launched from a detached Windows process should not allocate a console window.
## What changed
Set `CREATE_NO_WINDOW` by default for `codex-rs/utils/pty` child commands. Preserve it alongside `CREATE_SUSPENDED` when preparing a child for Job Object containment, since Tokio's `creation_flags` replaces existing flags.
## Testing
Add a Windows regression test that runs from a detached process and verifies that children have no console window and retain working piped stdin and stdout, both with and without Job Object containment.
GitOrigin-RevId: 990386032d74fa783a66bb20faff769539ea41c1
## What changed
Expose Windows process creation flags on the shared command wrapper and use
`CREATE_NO_WINDOW` when launching local stdio MCP servers, including fallback
launches without Job Object containment. Preserve `CREATE_SUSPENDED` when
assigning the server to a Job Object before execution.
## Testing
Add a Windows regression test covering direct launches and launches through
`cmd.exe`. Verify that the server has no console, initializes successfully,
returns tools, and exits after shutdown.
GitOrigin-RevId: 84475e82999d91a431e09327d4f5639b59c01427
## Why
Local `apply_patch` permission checks can treat a macOS system alias and its canonical spelling as different locations, sending writes covered by temporary-directory grants for unnecessary approval.
## What changed
- Normalize trusted top-level aliases in local policy roots and patch targets, reusing a prepared matcher for permission requests and patch safety checks.
- Share alias normalization with Seatbelt and the macOS executor sandbox while preserving mutable symlinks and missing descendants.
- Preserve read-only and deny precedence, protected metadata restrictions, and remote URI matching. Propagate normalization failures from fallible permission checks.
## Testing
Add macOS regressions for multi-file patches with missing parent directories through both direct `apply_patch` calls and shell interception, asserting automatic approval and file contents. Add unit coverage for alias restriction precedence, mutable symlink preservation, missing descendants, and remote permission isolation.
GitOrigin-RevId: 0822ff951eaab728cb1ad91281745fa1b8809f15
## Why
Image and audio estimate cache misses computed values while holding the cache mutex, blocking access to unrelated keys during initialization.
## What changed
Add `BlockingLruCache::get_or_init` using `Arc<OnceLock<V>>` and migrate the image and audio estimate caches to it. Initialization and same-key waits run in a Tokio blocking region after releasing the cache mutex. Callers share initialization while an entry remains cached; eviction can allow another initialization, so factories must be deterministic.
## Testing
Add a concurrency test covering access to other keys during initialization, eviction of an in-flight entry, and successful completion of both the evicted initializer and its replacement.
GitOrigin-RevId: 079226a58828b854eddc2b501079527bcbe5e603
## Why
Passing extra descriptors to a PTY previously selected behavior intended for inherited escalation sockets: no EOF on stdin close, different signal exit statuses, and no default `SHELL`. Launch attachments need ordinary PTY behavior and must survive execution even when marked `FD_CLOEXEC`.
## What changed
- Add `ChildFds::Attached` alongside `ChildFds::Inherited` to distinguish launch attachments from legacy inherited descriptors.
- Preserve ordinary EOF, default `SHELL`, and signal exit status behavior for PTY attachments.
- Allow explicitly supplied close-on-exec descriptors through pipe and PTY launches without changing the parent's descriptor flags, using child-side flag updates and macOS spawn inheritance actions.
- Update existing callers to use `ChildFds::Inherited`.
## Testing
Add Unix coverage for attachment accessibility, unchanged parent descriptor flags, default `SHELL`, and signal exit statuses. Extend the PTY stdin-draining test to cover attachments and EOF delivery.
GitOrigin-RevId: 864aedc6c5717d8b43c9d71057c9f54409834509
## What changed
- Move `Provider` and `RetryConfig` into `codex-client`, retaining re-exports from `codex-api`, and switch `codex-model-provider-info` to depend on `codex-client`.
- Move feature-state metric emission into `codex-core`, preserving its behavior while removing the `codex-features` dependency on `codex-otel`.
- Explicitly enable TLS features for `tonic` in `codex-config` and `reqwest` in `codex-http-client`.
- Enable `png`'s `zlib-rs` feature directly in `codex-utils-image` to keep encoded PNG bytes stable when WebSocket dependencies are absent.
GitOrigin-RevId: 91fd63ab01b55d516b3e80e3644d06af8d5a01f6
## What changed
- Cast `POSIX_SPAWN_SETSID` to the inferred flag type in the `ProcessMode::NewSession` branch.
- Use `LoaderOverrides::without_managed_config_for_tests()` for both cases in `project_layers_disabled_when_untrusted_or_unknown` so host-managed configuration does not affect the test.
GitOrigin-RevId: 1b27ac3ea139507d3f9402f4c2e3e63933c4d05c
## Why
Linux descriptor cleanup used allocating directory enumeration after `fork`. The child needs allocation-free cleanup while preserving Rust's spawn-error channel until `exec` succeeds.
## What changed
- Mark unrelated descriptors close-on-exec with `close_range(CLOSE_RANGE_CLOEXEC)`, leaving stdio and explicitly preserved descriptors' flags untouched.
- Fall back to stack-backed `getdents64` enumeration of the child's descriptor table when `close_range` fails.
- Document best-effort cleanup: failures allow launch to proceed and may leave unrelated descriptors inherited.
## Testing
Add Linux tests for descriptor inheritance, unsorted and duplicate allowlists, unchanged parent descriptors, fallback cleanup above a lowered descriptor limit, preserved exec-error reporting, and successful launch when both cleanup paths fail. Retain MCP coverage for descriptor exclusion in servers and descendants.
GitOrigin-RevId: 13abb95f82557324c7b40feb36bd6f806d60674e
## Why
PTY launches need to establish a controlling terminal and reset signal state. Extend the Linux process setup helper to perform this work in a fresh, single-threaded process image without forking the application when the native helper is available.
## What changed
- Add a PTY setup mode and support caller-owned stdout and stderr descriptors so all three standard streams use the PTY slave.
- Use the helper for eligible Linux PTY launches, including launches with explicitly preserved descriptors, and wait for child exit asynchronously.
- Preserve portable PTY behavior for `PATH` lookup, custom `argv[0]`, missing working directories, default `SHELL`, stdin EOF, and signal exit status.
- Retain compatibility fallbacks and release the initial PTY descriptors before allocating a portable replacement.
## Testing
Add regression tests for controlling-terminal setup without forking, portable signal exit status, and successful fallback under file-descriptor pressure. Resolve the Python test executable to an absolute path to exercise the helper path.
GitOrigin-RevId: 4b07ce68aa33c5b79548581e221caf5953b0eda1
## What changed
Add real-child tests for parent-death signaling, large environment transfers, explicit file descriptor inheritance, and fallback when the helper exits before acknowledgement.
Introduce test-only pause points during environment transfer, reporting, and exec to verify that cancelling startup kills and reaps the helper. Cover cancellation after runtime shutdown and verify that the fallback reaper can reap an exited child while an earlier child remains alive.
Probe an actual helper launch before asserting native-helper behavior, and skip fixtures when their required procfs or pidfd support is unavailable.
GitOrigin-RevId: 5136dc242a91efd0596171266965f29903c6c970
## Why
Linux pipe launches need session, parent-death signal, and descriptor setup. Move this work into a fresh, single-threaded executable image to avoid forking the app-server for child setup.
## What changed
- Register an early setup helper and launch it through `posix_spawn` for Linux pipe processes.
- Start the helper with an empty environment, then transfer the target environment over a control socket so loader settings cannot interfere with helper startup.
- Await target execution asynchronously, propagate setup and execution errors, and kill incomplete launches on cancellation.
- Preserve direct spawning as a fallback when the helper is unavailable or fails before target execution.
## Testing
Add coverage for launch semantics, avoiding fork, loader environment isolation, early argument dispatch, closed standard descriptors, and fallback under bootstrap failure or descriptor pressure. Add an app-server regression test that reuses a process handle after an execution failure.
GitOrigin-RevId: 079c673f0f22ebd531f8c57e5338095cc98acfdc
## Why
Unix command hooks use a `pre_exec` callback to detach from the controlling terminal, forcing the launcher to fork. Native spawn attributes can create the detached session without that callback.
## What changed
- Route Unix hooks through `codex_utils_pty::Command` with `ProcessMode::NewSession`.
- Extend the native `posix_spawn` launcher to detached Linux sessions, retaining compatibility fallbacks for unsupported libc features and executable handling.
- Preserve the session environment snapshot, hook overrides, and restricted-variable filtering.
## Testing
Add regression coverage for launches without parent forks, terminal detachment, environment and argument handling, Linux `PATH` lookup, and executable compatibility. Cover process-group cleanup on cancellation and timeout, including descendants holding output pipes open, and preservation of background descendants after completed hooks.
GitOrigin-RevId: dbe2cf12d84aa79868cfb55ace40c7d5b5282703
## Why
Pipe spawning installs Unix `pre_exec` hooks, forcing a fork on macOS even though the shared child launcher supports native spawning.
## What changed
- Use the shared `Command` for pipe processes, enabling native macOS spawning while preserving session isolation, explicit descriptor inheritance, and Linux parent-death handling.
- Select `ReapOnly` so the pipe adapter retains ownership of process-tree termination.
- Track embedded NUL bytes in original Unix command inputs and reject them before spawning, including when invalid `current_dir` or `arg0` values are later replaced.
## Testing
Add macOS integration coverage verifying fork avoidance, executable path lookup, pipe I/O, session isolation, and descriptor inheritance. Add Unix regression tests for pipe and PTY fallback under descriptor pressure and for rejecting NUL inputs without running the child.
GitOrigin-RevId: f4fa2c1d3c1aee2c4ffa1dc2ff946f9f0b08eb20
## What changed
- Add `ProcessMode::NewSession`, null stdin, and opt-in Linux parent-death termination to the shared child command API.
- Replace `DescriptorPolicy::StdioOnly` with `Explicit` and add `preserve_fds` to allow selected inheritable Unix descriptors alongside stdio. Preserve descriptor numbers without duplicating or closing the parent's descriptors, keeping POSIX record locks intact.
- Support session creation and preserved descriptors in the native macOS backend, with a compatible fallback for high descriptor numbers rejected by native file actions.
## Testing
Add regression coverage for process groups and sessions, descriptor preservation across native and executable-text launches, the last descriptor slot below the file limit, and retention of parent record locks.
GitOrigin-RevId: 29ecd859d3b673da6ae6412cc06a32fa10d11346
## What changed
Add a crate-private `ChildDropPolicy` to choose whether dropping a child kills it or only reaps it after exit. Keep `KillAndReap` as the default.
For `ReapOnly` on Unix, transfer dropped children to a shared reaper thread that operates independently of the Tokio runtime. Support both Tokio children and native macOS children, without blocking drop or letting a live child delay reaping others.
## Testing
Add an isolated regression test verifying that reap-only children survive handle drop after runtime shutdown, are reaped after exit, and do not prevent other exited children from being reaped.
GitOrigin-RevId: 5ec639597dba7f3b61694d6d465991e054ae3397
## What changed
- Record each MCP source and its first turn, including connector and plugin identifiers when available. Cover direct and Code Mode calls, including returned errors and results that are not printed.
- Persist cumulative attribution checkpoints and restore them across compaction, resume, and forks, including forks limited to recent turns.
- Attach fresh attribution to Responses API `client_metadata` under `mcp_attribution`, outside model-visible content. Restrict transmission to allowed OpenAI HTTPS destinations for both HTTP and WebSocket requests.
- Report `attribution_error` for legacy history without checkpoints, malformed or conflicting attribution, and serialized attribution exceeding 16 KiB.
## Testing
Add coverage for source deduplication, checkpoint persistence and restoration, recent-turn forks, direct and Code Mode calls, destination filtering, and the serialized size limit.
GitOrigin-RevId: fd285e152ca9e24bfa000debb20013709d67a86e
## Why
Filesystem helpers use a `pre_exec` callback to close inherited descriptors on macOS, forcing a fork before execution. Native spawning needs to preserve that isolation and support the socket used for file descriptor transfer.
## What changed
- Launch filesystem helpers through `codex_utils_pty::Command`, using `posix_spawn` with `POSIX_SPAWN_CLOEXEC_DEFAULT` on macOS and returning native launch errors without a fork fallback.
- Extend the shared command wrapper with explicit descriptor and fallback policies, socket-backed stdin, and custom `argv[0]` support.
- Add `Child::wait_with_output` to drain stdout and stderr concurrently, retain kill-on-drop behavior on cancellation, and keep output pipes open until the child exits.
## Testing
Add regression tests for fork-free sandboxed reads, writes, and file descriptor transfers; sandbox denial of outside paths and symlink escapes; descriptor isolation; bidirectional socket stdin; custom `argv[0]`; executable-format errors; and output-pipe lifetimes.
GitOrigin-RevId: d49c00787f30ec0bc196f9e066a0770fc8151152
## Why
The native macOS backend cannot inspect every setting or callback on a Tokio command. A shared, constrained launch API makes the supported settings explicit for both backends.
## What changed
- Replace `spawn_child` with `codex_utils_pty::Command`, enforcing an explicitly supplied environment, piped stdio, and kill-on-drop behavior.
- Add `ProcessMode::Inherit` and `ProcessMode::NewGroup`, honoring the selected mode in native macOS and Tokio spawning.
- Share the `Child` wrapper across platforms and migrate local MCP server launching to the new API, retaining its new process group and Windows suspended-spawn support.
## Testing
Adapt the existing macOS spawn compatibility and child lifecycle tests to the new API. Add a regression test that checks inherited and new process groups with both backends.
GitOrigin-RevId: 3e7a401659e3a8a94a13c4ff58d67bdcd2eea33d
## What changed
Expose the shared `Child` type and `spawn_child` function from `codex-utils-pty`, and update the MCP stdio transport to use them. Move the existing macOS spawning implementation and its tests into the utility crate, preserving platform-specific spawning, piped stdio, and kill-on-drop behavior.
GitOrigin-RevId: 26c2fb2f22cdba907aa9d18cab7dc8c4ac1c909e
## Why
On macOS, process-group signals can be denied even when individual members can be signalled. Core execution cleanup used helpers that did not retry those signals against group members.
## What changed
- Make `terminate_process_group` and `kill_process_group` use the existing member fallback on macOS, and simplify MCP and pipe callers to use the shared helpers.
- Use the saved process-group ID when escalating cancellation after the termination grace period, so this path also uses the fallback.
- Update the unsafe process-group ID test to exercise `terminate_process_group`.
GitOrigin-RevId: 1bab28d3d53cd401b51ffe71d41fbece12aed66d
## What changed
- Add `Platform` to `codex-utils-path-uri` with metadata parsing, native platform detection, and path convention mapping. Preserve missing or unrecognized metadata as `Unknown`.
- Replace `NetworkProxyExecutorOs` with the shared type and keep executor-specific socket path validation in the network proxy.
- Extract `effective_sandbox_mode` with explicit platform and Windows sandbox level inputs, preserving the native Windows fallback from `workspace-write` to `read-only` when the sandbox is disabled.
## Testing
Add unit tests for platform metadata, path conventions, native platform detection, and sandbox mode selection across platforms and Windows sandbox levels.
GitOrigin-RevId: 4fe0972e3a91040e35f2a6dfa5bcdf6c9a29be88
## What changed
Use `EnvironmentAccess` for skill discovery, environment skill loading, and plugin namespace resolution, replacing direct `ExecutorFileSystem` calls with explicit `None` sandbox arguments.
Wrap existing host and executor filesystems with `FileSystemEnvironmentAccessor::unrestricted` to preserve their current access behavior. Update discovery, loading, and namespace tests to use the same adapter.
GitOrigin-RevId: d68168cc0ee19dc303ef4ee726cf1de1a8db81e0
## Why
Permission summaries must preserve executor paths without interpreting them in the host's filesystem namespace.
## What changed
Accept `PathUri` values and summarize permission profiles directly instead of converting them to a legacy sandbox policy. Render additional workspace roots using their inferred native path convention, and update the exec and TUI callers.
Keep workspace subpath writes and writes outside the working directory classified as `custom permissions` when the working directory itself is not writable.
## Testing
Add coverage for POSIX, Windows drive, and UNC workspace paths, including encoded spaces and case-distinct roots, plus opaque workspace subpath writes.
GitOrigin-RevId: ff2c456e2a720e7216f13e0241b3a935cc925d00
## What changed
- Accept `fileId` alongside the existing `url` form for app-server image inputs, and forward file references to the Responses API as `file_id`. Update generated schemas and client types.
- Preserve file references, image detail hints, and mixed inline/file image ordering through user-message events, thread history, and rollout migration. Retain file images when truncating tool output.
- Pass file references through image preparation without resolving them, while keeping resize-notice numbering correct. Omit them from unsupported TUI display and Guardian image context.
- Reject image-edit requests whose recent-image window includes a file reference, preventing selection of an older inline image instead.
## Testing
Add coverage for serialization, request and rollout preservation, mixed-image history ordering, incomplete ordering metadata, tool-output truncation, and rejection of unsupported image-edit selections.
GitOrigin-RevId: 6ca20a8577155cc934b720803c3b7b3bffdf972a
## What changed
Represent images in `ContentItem` and `FunctionCallOutputContentItem` with `ImageReference::Inline`, flattened to preserve the existing `image_url` wire format. Update image producers and consumers and regenerate app-server schemas and SDK artifacts.
Preserve the Python SDK's `InputImageContentItem` and `InputImageFunctionCallOutputContentItem` class names during generation.
## Testing
Add a regression test for stable Python image class names and adapt existing image tests to the shared representation.
GitOrigin-RevId: c38a780ac3314c2ac2deb3afc1b93b94b6f93fec
## Why
Retaining the pseudoconsole's creation pipe handles prevents output readers from seeing EOF while the session remains alive.
## What changed
Drop the creation handles after a successful process spawn and call `ReleasePseudoConsole` when available on Windows 11 24H2 or newer. This lets output close after the last attached client exits while preserving I/O for surviving console descendants. Older Windows versions retain the `ClosePseudoConsole` cleanup path on drop.
## Testing
Add Windows lifecycle tests for output closure after normal exit and termination while retaining the session, plus continued input and output for a surviving console child. These tests skip when `ReleasePseudoConsole` is unavailable.
GitOrigin-RevId: fb1094fb2a570e6fec0cc80d6356f5d7eb1edcbf
## Why
Matches starting inside a lowercase expansion such as `İ` → `i̇` could receive an incorrect prefix bonus or gap penalty, causing strings that lowercase identically to rank differently.
## What changed
Track the first matched position in the lowercased text directly when calculating scores. Preserve original character indices for highlighting.
## Testing
Add a skill popup regression test and snapshot covering ranking and highlighting for matches beginning at the combining dot in expanded and already-lowercase names.
GitOrigin-RevId: 78a8b79f1defca9f76fde5df945b0b1ff4af25da
## Why
A persistent tmux session can gain remote clients after Codex starts, so successful native copying must not skip terminal forwarding. Terminal sends also lack delivery acknowledgement and cannot replace native copying reliably.
## What changed
- Attempt native copying first, then independently forward through tmux or OSC 52 in tmux and SSH sessions. Preserve existing native clipboard leases when a later copy returns no new lease.
- Target the most recently active client in the current pane's tmux session, checking that client's clipboard capability before sending. Retain OSC 52 fallback when tmux forwarding fails.
- Reject empty selections without touching clipboards and apply the 100,000-byte terminal payload limit to tmux copies.
- Resolve tmux and PowerShell through trusted system locations, adding Nix system profiles and the WSL PowerShell directory to helper discovery.
## Testing
Add regression coverage for native-before-terminal ordering, fallback routing, clipboard lease retention, empty and oversized payloads, tmux client selection, capability checks, and combined backend errors.
GitOrigin-RevId: df4b66fa4368a3cf19b4d07fde6c76ea96a8fef5
## Why
The 900-byte recap prompt limit leaves little room for completed progress, unresolved caveats, and recent corrections. Recaps need this context to distinguish completed work from pending requests.
## What changed
- Introduce a shared `RecapPrompt` with a 32 KiB ceiling for instructions and history, using an 8,192-token estimate. Instruct summaries to retain the broader goal, completed outcomes, and unresolved availability or validation caveats.
- Select up to eight answered exchanges plus a pending request, preserving adjacent steering and progress messages. Drop older whole exchanges before excerpting both ends of oversized messages, while retaining the newest answer and pending correction.
- Require a `summary` and nullable `next_action`, bounded to 700 and 200 characters respectively. Reject malformed or oversized responses and display an optional, separately styled `Next:` line.
## Testing
Add coverage for UTF-8 prompt bounds, exchange selection, pending corrections, excerpt boundaries, strict response parsing, and next-action rendering. Extend the recap generation integration test to verify bounded history and the structured response schema.
GitOrigin-RevId: 6c6a84bc602a168418c1952feb1d286ec0cb9e28
## Why
Permission paths need to follow the execution host's path conventions and home directory. Literal directory names containing glob syntax must not change the meaning of deny patterns, and profile availability checks need to account for configured workspace roots.
## What changed
- Use `ConfigPathContext` to compile built-in and custom profiles, returning the resolved profile and deduplicated `PathUri` workspace roots. Materialize configured roots while retaining runtime workspace symbols.
- Use the same compiler for configuration loading, persisted profile validation, and profile catalogs. Resolve roots against the requested `cwd` when listing profiles.
- Resolve home-relative scoped rules using the supplied home directory and reject unsafe directory prefixes when constructing globs.
- Share workspace-root materialization across native paths and URIs. Deny the affected root when a workspace glob cannot be safely resolved, and clear grants for legacy home-relative workspace denials whose target is unknown.
## Testing
Add coverage for POSIX, Windows, and UNC path resolution, inherited workspace roots, scoped home denials, missing home context, and conservative denial behavior for unsafe globs. Add an app-server test verifying that profile availability reflects the requested `cwd`.
GitOrigin-RevId: ca259434742365c16d0b72629cabfbab41513a80
## Why
Filesystem denial paths need to use the owning environment's path syntax, base directory, and home directory. Host-native resolution cannot supply those facts for another platform, and invalid denials must not be silently skipped when building the sandbox policy.
## What changed
- Add `ConfigPathContext` to requirements layers so `permissions.filesystem.deny_read` can resolve using explicit POSIX or Windows path facts, with native defaults when no context is supplied.
- Share URI-based resolution and validation for literal paths and glob prefixes. Reject ambiguous or lossy paths, including NUL bytes, Windows stream syntax, and unsupported UNC spellings.
- Move denial conversion into `FilesystemConstraints::apply_to_policy`, preserving glob patterns and deduplicating entries. Validate all denials before modifying the policy and propagate failures through configuration loading.
## Testing
Add tests for per-layer base and home resolution, Windows drives and globs, nested context restoration, missing home directories, and policy conversion without partial mutation. Add a configuration-loading regression test for a required denial glob containing a NUL byte.
GitOrigin-RevId: fa0da0d149407958e39897a39fe7b87edd6f1644
## Why
Replaying tool outputs under a different model can expand or shrink the history shown to the model if truncation uses the new model's budget.
## What changed
Save the originating history truncation budget on function and custom tool outputs and reuse it during replay, preserving existing tool-specific overrides. Include the existing 20% serialization allowance once, before converting byte budgets to tokens.
Rename the metadata field to `history_truncation_token_limit` while retaining `fallback_token_limit_override` as its serialized name for compatibility.
## Testing
Add regression coverage for resume and fork with different model budgets, including custom tool outputs. Extend unit coverage for existing overrides and byte-budget conversion.
GitOrigin-RevId: a62c8fd3e43198e2252b150fba72f022939c1070
Return `AudioPreparationError::InvalidDataUrl` with the reason
`audio payload is empty` when the decoded base64 payload is empty.
GitOrigin-RevId: e886dab5f49ebb1a363dbc1c292813b2b52698d4
## Why
Resuming a thread should retain its selected workspace folders, including additional roots and explicit empty selections. Resume overrides also need to survive a subsequent resume when no turn has run.
## What changed
- Persist `runtime_workspace_roots` in startup metadata and thread settings snapshots, separately from explicit environment selections and permission-profile roots.
- Restore roots from the latest snapshot owned by the resumed thread, falling back to owned startup metadata only when no snapshot exists. Honor explicit `runtimeWorkspaceRoots` overrides, retarget the old `cwd` root when `cwd` changes, deduplicate roots, and validate restored paths for the current host.
- Checkpoint effective settings on resume and restored settings after revert. Reload resume configuration if saved workspace roots change during loading.
- Normalize Windows rollout path spellings when matching thread search results, preserving selection of the correct rollout after revert, including compressed rollouts.
## Testing
Add regression coverage for workspace restoration, empty and explicit overrides, foreign paths, compaction and revert, resume checkpoints without recency changes, concurrent settings persistence, and rollout search path matching.
GitOrigin-RevId: d98d9d34dd63934d441120916c61c12b69e7f062
## What changed
- Add the experimental `worktrees` feature and a shared `--worktree` flag for new and forked `codex exec` sessions.
- Create each enabled session in a managed Git worktree, use that checkout as the session working directory, and bind the checkout to the new thread.
- Share the configured worktree pool with Desktop while leaving automatic cleanup disabled for CLI allocations.
- Reject unsupported commands, remote execution, ignored user configuration, ephemeral sessions, and use without the feature enabled before allocating a worktree.
## Testing
- Cover flag placement and inheritance, supported and rejected command combinations, worktree allocation and thread ownership, configuration gating, and compatibility with existing worktree-backed sessions.
GitOrigin-RevId: 011ff4639b09e8992c50d7b823df23e71798670e
## What changed
- Add `PromptImageMode::HIGH_DETAIL` and `PromptImageMode::ORIGINAL_DETAIL`
constants with the standard resize limits.
- Use the shared modes during core image preparation instead of defining the
limits locally.
- Cover the dimension and patch budgets for both detail modes in the image
utility tests.
GitOrigin-RevId: 27fdc77719f23d2e8f1060886576b3be843a8491
## Why
Reasoning configuration changes need to retain their position and trusted provenance when model history is persisted and replayed. Client-injected history must not be able to forge these controls.
## What changed
- Add a typed `configuration_update` response item carrying reasoning effort, including custom model-defined values.
- Persist harness-authored updates with provenance and preserve them across history reconstruction, thread resume, raw response notifications, and agent forks.
- Exclude untrusted configuration updates from model history, strip client-supplied provenance metadata, and reject configuration updates supplied as turn input.
- Export the new item through the JSON and TypeScript app-server schemas and classify it in telemetry and persistence metrics.
## Testing
- Cover serialization, provenance persistence, history filtering and rollback, resume reconstruction, and injection attempts before and after restart.
GitOrigin-RevId: eb5559d2b52b7a931621e7c9812f009ff9fb8939
## Why
Automatic startup work and `codex doctor` can run before a workspace is
trusted. A repository-controlled `PATH` must not be able to make those flows
execute workspace-provided helpers.
## What changed
- Resolve helpers used by automatic startup from trusted system installation
directories, and give plugin-sync Git subprocesses a sanitized environment.
- Make terminal detection environment-only and have doctor inspect executable
locations without running them. Fetch update metadata with the HTTP client
instead of `curl`.
- Fall back conservatively when trusted terminal helpers are unavailable,
including for tmux keyboard enhancement flags.
## Testing
Add black-box coverage with hostile workspace `PATH` entries for startup,
interactive tmux startup, support log collection, doctor, and curated plugin
sync. Add unit coverage for trusted executable resolution and bounded update
HTTP responses.
GitOrigin-RevId: 3b8995eb422b60ed53b0386951de59e8f9bfc542
## Why
`request_permissions` paths and grants need to be evaluated against the selected executor environment, including its path convention, home directory, workspace roots, and temporary directories.
## What changed
- Resolve relative and home-relative permission paths using the executor context, reject mismatched path conventions and lossy paths, and support legacy `read` and `write` path lists.
- Move grant intersection into core so requested and granted permissions use the originating environment's sandbox context. Preserve deny entries conservatively when a special path cannot be resolved.
- Keep the full originating environment with pending permission requests so delayed responses are normalized against the same context.
## Testing
- Cover POSIX, Windows, UNC, relative, and home-relative path resolution and invalid path contexts.
- Verify end-to-end app-server grants are limited to the requested workspace scope and unresolved temporary-directory denies are preserved.
GitOrigin-RevId: 730a2aacd391262e92a6314f3a5b6c262e3dca10
## Why
Git root discovery is optional metadata work, but filesystem probes can block. They should not exhaust Tokio's blocking pool, delay runtime shutdown, or prevent later turns from observing repository changes.
## What changed
- Add a shared `GitRootDiscovery` service that coalesces concurrent lookups for the same working directory and limits probes across directories.
- Run probes on detached threads, retain in-flight work across caller cancellation, and discard completed results instead of caching them.
- Use the service for turn and memory metadata enrichment, abort unused turn enrichment when its state is dropped, and limit memory metadata waits to one second.
## Testing
Add coverage for probe sharing, capacity limits, cancellation, fresh discovery, runtime shutdown, memory timeouts, and repositories restored after startup prewarming.
GitOrigin-RevId: bca46fc263e7a12a2f69146d8a0b3e7c7e0846cb
## What changed
- Add `VoiceHost` to resolve the packaged voice helper, launch it with an
allowlisted environment, perform the protocol handshake, and enforce bounded
shutdown and process cleanup.
- Preserve native executable path encoding in the pipe process APIs.
- Add `third_party/voice/assemble_package.py` to create a fresh package copy
containing a target-compatible helper and a provenance manifest with file
hashes.
## Testing
- Cover installed helper lifecycle, build matching, missing and symlinked
helpers, non-UTF-8 package paths, environment filtering, package validation,
target pairing, and failure cleanup.
GitOrigin-RevId: f893074b36ae6bb9bcedc00fbe7af6bb72745f4c
## What changed
- Add a positive `output_token_limit` setting to each entry under an MCP server's `tools` configuration.
- Apply the most restrictive limit when plugin and user policies overlap, while keeping approval policy independent.
- Carry the effective MCP output budget in conversation history so tool output, post-tool hook responses, and resumed sessions use the same truncation limit.
## Testing
- Cover configuration parsing, serialization, schema validation, and plugin policy merging.
- Cover MCP output below and above the configured limit, post-tool hook responses, and session resume.
GitOrigin-RevId: d0beb4fca9ba6055d9e1d31c137373b465d50d61
Tamir Duberstein