Commit Graph
256 Commits
Author SHA1 Message Date
jif b043762f9e Preserve remote exec output until it is collected (#53622)
## Why

Remote process exit can arrive before the final output, and inherited pipes can keep the output stream open after exit. Removing the session at exit can lose output that should remain available to `write_stdin` polls.

## What changed

- Retain remote sessions with open or unread output after exit, including early exits and cancelled initial collection.
- Collect pending output when `write_stdin` races with exit, skipping stdin writes once remote exit is known.
- After initial collection finishes and the process exits, allow a five-second grace period before a final background read. Respect active polling deadlines and keep later polls available while that read recovers retained output.
- Let explicit termination stop output collection even when the process has already exited, and install the exit watcher before cancellable cleanup.

## Testing

Extend remote process event tests to cover output arriving after the initial yield, polling during a delayed final read, active polls exceeding the background grace period, resumable cancellation, and termination before the initial yield.

GitOrigin-RevId: b1671fad8b61a2cdecf7cf9fdf92e57c028c7af8
2026-10-13 09:34:17 +00:00
jif 7e9c061ceb Finish remote exec cleanup when output streams remain open (#53331)
## Why

A remote process can exit while its output stream remains open, leaving the exit watcher waiting and delaying `ExecCommandEnd` even after output collection finishes.

## What changed

Cancel the process output token after final collection or polling, on one-shot cancellation, and after confirmed termination. This releases the exit watcher while allowing delayed output to be collected before the final poll completes.

## Testing

Add remote process event tests for output streams that remain open at the collection deadline, during interruption, and during explicit termination. Assert that `ExecCommandEnd` preserves the exit code and aggregated output, background terminals are cleared, and interruption and termination require no extra `process/read` requests.

GitOrigin-RevId: 8346e5ce446280915b6e2ffa362fcfd79280bfff
2026-10-12 09:29:11 +00:00
jif 89c8759d8c Bound local exec-server output draining after process exit (#52652)
## Why

A local command can exit while a descendant keeps its inherited output pipes open, delaying `exec_command` completion and turn completion.

## What changed

Start the bounded output drain when a local exec-server process exits, whether exit is reported by an event or recovered through `process/read`. Remote execution continues waiting for output closure so buffered or delayed output is retained.

## Testing

Add regression coverage for local shell snapshot execution completing before a descendant releases stdout, preserving the foreground output and exit code. Add remote event-stream cases that retain output arriving after both reported and recovered process exit.

GitOrigin-RevId: d38bcd394be42cf48d2af02733e883b02d1dd62f
2026-10-09 17:32:27 +00:00
jif cd85a26cae Remove the patched zsh shell execution backend (#52160)
## What changed

- Use the standard shell executor and remove the zsh fork escalation runtime, `codex-execve-wrapper`, and `shell-escalation` crate.
- Ignore `shell_zsh_fork` and `unified_exec_zsh_fork`, emit migration notices for legacy configuration, and warn when ignoring managed requirements for these flags.
- Keep the active session's `apply_patch` alias directory readable under restricted filesystem permissions.

## Testing

Add coverage for legacy configuration startup and shell execution, migration notice rendering, active alias directory selection, and nested `apply_patch` execution while other files in `CODEX_HOME` remain unreadable.

GitOrigin-RevId: 43af461fea32b4980550ee7237effd2bc0646ed8
2026-10-08 16:19:09 +00:00
Leonardo Di Donato 9b738582b1 Expose originating tool call metadata in command environments (#52119)
## Why

Command processes need thread and tool call labels for correlation, without stale values from inherited environments or cached shell snapshots.

## What changed

- Export the originating `exec_command` call ID as `CODEX_TOOL_CALL_ID`; later `write_stdin` calls leave it unchanged.
- Apply executor metadata as `CODEX_THREAD_ID` and `CODEX_TOOL_CALL_ID` after environment policies, overlays, and snapshot replay. Clear omitted fields when metadata is present; without metadata, preserve thread context and remove the call ID.
- Exclude both IDs from newly captured snapshots and omit the call ID from capture and validation helpers.
- Preserve empty call IDs, omit NUL-containing IDs, and handle case-insensitive environment names on Windows. Document that these labels support correlation, not authorization.

## Testing

Add regression coverage for metadata precedence, missing and invalid IDs, snapshot capture and replay, local and remote execution with pipes and TTYs, sandboxed remote execution, and preservation of the originating call ID across later input.

GitOrigin-RevId: 1027212b5d495d8e7cfac0f498c3134e060aa897
2026-10-08 13:45:19 +00:00
tongzhou wang e974aad3b1 Support model-specific function description prefixes (#51930)
## What changed

Add `functions_namespace_functions_description_prefixes` to model tool messages, keyed by unqualified tool name. Prepend this guidance to descriptions in the `functions` namespace across direct declarations, Code Mode documentation, and tool-search results, including custom tools.

Trim prefixes, ignore empty values and unavailable functions, and enforce a combined 256-byte UTF-8 limit including separators for reachable tools. Keep overrides local to each step, preserve search ranking text, and retain runtime caches for unaffected tools.

## Testing

Extend coverage for direct and indirect descriptions, clearing prefixes when switching models, namespace scoping for deferred dynamic tools, and tool-search cache reuse and reset.

GitOrigin-RevId: f434e37cec010764fe3e09fb12c339e933b3c21c
2026-10-08 03:20:54 +00:00
iceweasel-oai cba716c0f1 Run sandbox integrity checks before commands and filesystem operations (#51843)
## What changed

Wire existing sandbox integrity checks into local command preparation, exec-server process preparation, and sandboxed filesystem helper and file-open operations. Make execution request preparation asynchronous so callers can await the checks.

The checks remain observational: failures and timeouts do not prevent command execution.

## Testing

Add regression tests that launch a real command after checker preparation fails or exceeds its timeout, verifying successful output and exit status.

GitOrigin-RevId: a82399f8aeb8b08f9965e6121b4c7f460552af3f
2026-10-07 21:52:43 +00:00
iceweasel-oai 622e9e3696 Preserve sandbox overrides across execution requests (#51786)
## What changed

Move `SandboxOverride` into the shared protocol and carry the controller's selection through tool attempts, execution requests, and exec-server process and filesystem sandbox preparation. Include it as `sandboxOverride` in filesystem sandbox contexts for observation without granting broader permissions or altering sandbox commands.

Default missing values to `NoOverride` and omit that value when serializing to preserve compatibility with existing requests.

## Testing

Extend tests to cover override propagation, wire round-trips for all three variants, and deserialization of requests without `sandboxOverride`.

GitOrigin-RevId: 2f438cf4aef1134e3149959d14aa731682168ae5
2026-10-07 17:59:22 +00:00
Charlie Marsh 685270a56a Make apply_patch preserve line endings unconditionally (#51203)
## Why

Updating a CRLF file with `apply_patch` previously normalized its line endings to LF unless preservation was explicitly enabled. Preserve the file's existing line endings without requiring an opt-in.

## What changed

- Use line-ending-preserving updates for both tool calls and standalone `apply_patch` invocations, removing the legacy normalization mode.
- Mark `apply_patch_preserve_line_endings` as removed.
- Always set `CODEX_APPLY_PATCH_PRESERVE_LINE_ENDINGS=1` in child environments for compatibility with older patch executables, overriding stale values.

## Testing

Update CLI, tool-call, shell-heredoc, and app-server tests to check CRLF preservation by default. Keep coverage for overriding stale compatibility environment values.

GitOrigin-RevId: 96d0b0e5350faa3fc7a45d63627a132657b44523
2026-10-05 23:52:06 +00:00
Owen Lin c5d242fa79 Consolidate command execution output into aggregated_output (#50402)
## What changed

- Remove `stdout`, `stderr`, and `formatted_output` from `CommandExecutionItem` and `ExecCommandEndEvent`, retaining `aggregated_output` as the output field.
- Update command event producers, legacy conversion, rollout traces, and the precomputed schema. Use aggregated output for terminal trace results.
- Clear `interaction_input` in emitted and migrated command completion items.

## Testing

Update command execution and trace tests to use aggregated output, and assert that legacy rollout migration preserves `aggregatedOutput`.

GitOrigin-RevId: ed59827d4a5ec9a767084ee4feac72c2042440f2
2026-10-02 18:48:49 +00:00
Adam Perry @ OpenAI 1f52d40704 Bind permission grants to the originating turn (#49880)
## Why

Background code-mode cells can continue running after a new turn starts. Looking up grants and strict review requirements through the active turn can make those cells lose their approved access or use another turn's permissions.

## What changed

- Keep turn-scoped grants and strict review state in `TurnContext`, retained by captured steps and background cells.
- Record permission responses against the requesting turn, including requests made after a later turn starts.
- Share live session-scoped grants across turns while keeping turn-scoped grants isolated.
- Use the originating turn's permissions and review requirements for tool execution, patches, MCP calls, file uploads, and terminal input.

## Testing

Add regression coverage for background cells retaining grants across turn changes, turn versus session scope, permission requests after the next turn starts, and strict review enabled while `write_stdin` is queued.

GitOrigin-RevId: 641502fbfd43553c2c42424d4aaa53ae8020c850
2026-10-01 05:33:36 +00:00
Adam Perry @ OpenAI 995138d71a Carry shell invocation metadata and report executor PATH directories (#49360)
## What changed

- Carry the selected shell and login mode through unified exec using `ShellInvocation`. Use this metadata for shell snapshots and credential brokerage instead of inferring it from command arguments.
- Add `prependPathDirs` to exec-server environment metadata, populated from the executor's package PATH directory. Default to an empty list for older servers and omit empty lists from serialized output.

## Testing

Extend environment metadata round-trip coverage for `prependPathDirs` and the remote exec-server integration test to verify the packaged `codex-path` directory is reported.

GitOrigin-RevId: c571c068effcb305d196a701ad9a335ec7a3f5a2
2026-09-29 20:40:21 +00:00
viyatb-oai 804d6306e8 Allow approved filesystem escalation while preserving denied reads (#49353)
## Why

Denied-read policies previously kept explicitly approved commands within their original filesystem restrictions, preventing operations that need broader write access, such as updating Git metadata.

## What changed

- Apply broader filesystem permissions after approval of explicit escalation while retaining the sandbox, denied reads, and network policy. Command allow rules alone do not widen filesystem access.
- Reject escalation when the required local sandbox is unavailable or a remote exec server lacks support for preserving the restrictions.
- Track escalated terminal access so subsequent `write_stdin` calls still require review when stdin approval is enabled.

## Testing

Add coverage for approved and denied escalation, allow rules, remote server compatibility, and stdin approval before input delivery. Add a Windows integration test verifying that an approved `git pull` updates Git metadata while exact-path and glob-based read denials remain enforced. Serialize Windows sandbox integration tests across processes to protect shared test account credentials.

GitOrigin-RevId: 5dce6d41487ee4d39bd795c8d086398ab9794d5b
2026-09-29 19:50:50 +00:00
Steve Coffey f6a4bd81e3 Generate unique exec-server process IDs for every request (#48168)
## Why

Threads sharing an executor and sandbox retries can reuse a public process handle while the executor still retains the previous process.

## What changed

Always append a fresh UUID to the exec-server process ID, including requests without sandbox or shell snapshot settings, to avoid collisions when handles are reused.

## Testing

Update the request-parameter test to check the UUID-suffixed format and verify that repeated calls with the same handle produce distinct process IDs.

GitOrigin-RevId: bd1fc9af3e7d5ea99fdf88382df09afa7dc9f72b
2026-09-25 18:56:32 +00:00
jif 60713126ee Avoid stdin approval for runtime-only permission grants (#48073)
## Why

Runtime filesystem grants, such as those used for plugin metrics, could trigger unnecessary approval for `write_stdin` and prevent input when sandbox approval was disabled.

## What changed

Include retained runtime grants in the baseline permission comparison for stdin review. Continue requiring review for additional agent permissions, sandbox bypasses, and policy changes. Update the approval description to report current permissions when only runtime grants are present.

## Testing

Extend unit coverage to ensure runtime grants do not require review or mask agent filesystem and network grants, and that sandbox bypasses still require review. Add local and remote plugin regression cases that send stdin and verify metric emission with sandbox approval disabled.

GitOrigin-RevId: 989098bdc7fbf839786c01f11cbf02999bae1cc1
2026-09-25 11:43:35 +00:00
jif 61e23bc6a1 Bind Guardian async scores to target environment permissions (#47830)
## Why

Asynchronous Guardian scoring omitted the target environment's denied-read restrictions, and cached score authorization did not include that permission context. A score from one environment could therefore be reused for an action in another environment with different restrictions.

## What changed

- Share permission resolution between synchronous review and asynchronous scoring, including resolving `write_stdin` targets from the owning terminal session.
- Include environment identity and denied-read paths/globs in async scoring context and cached score authorization.
- Fall back to synchronous review when permission evidence cannot be resolved or exceeds the async limit of 3,000 bytes, rather than omitting restrictions.

## Testing

Add regression coverage for rejecting cached scores with different environments or denied paths, passing the target environment's restrictions to the classifier, and rejecting oversized async permission evidence.

GitOrigin-RevId: 14b6f3454bbea458be037560eb1da47d22874df1
2026-09-24 12:34:04 +00:00
felixxia-oai 869b5527cd Fix a lost wakeup in the unified exec termination test (#47814)
Use `notify_one()` instead of `notify_waiters()` in
`terminating_initial_exec_command_rechecks_initial_response_state` to retain
the release notification if the termination waiter has not registered yet.
This prevents the test from timing out due to a missed notification.

GitOrigin-RevId: d233ffc50e016eb75752fd360a4d846de0063683
2026-09-24 10:56:24 +00:00
jif 51d4562070 Support close-on-exec attachments without changing PTY semantics (#47797)
## 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
2026-09-24 09:25:19 +00:00
Steve Coffey 4891c4e35f Update unified exec output buffers atomically (#47712)
## Why

Appending output to the completion transcript and pending polling buffer under separate locks allows cancellation to interrupt a chunk update between the two buffers.

## What changed

Store both buffers in `OutputBuffers` behind a shared mutex and append each chunk to both while holding that lock. Polling drains only the pending buffer, while completion events read the retained transcript. Apply this to both local and exec-server output handling.

## Testing

Extend the repeated-drain test to verify that the completion transcript preserves the expected bounded output after polling drains the pending buffer.

GitOrigin-RevId: ef8519582937b0d8c42e46375226501338df4a01
2026-09-24 01:41:14 +00:00
Steve Coffey d47b9a8c00 Preserve early unified exec output in completion events (#47665)
## Why

Output produced before the streaming subscriber attaches can be missing from command completion events, even when it was returned to the model.

## What changed

Record the bounded completion transcript directly in `UnifiedExecProcess` as local and exec-server output arrives. Keep it independent of output polling and streaming delta delivery, and use it for completion events.

## Testing

Add regression coverage for output collected before subscription, both with and without later output. Strengthen the lifecycle test to assert that `aggregated_output` includes both early and late output.

GitOrigin-RevId: 9825acbd706dc4845837c8b4ab1347d8267ce0af
2026-09-23 20:56:32 +00:00
iceweasel-oai 6f6af0fce4 Record sandbox backends in command execution analytics (#47568)
## Why

Command execution analytics lack the observed sandbox backend. Older execution servers may omit this information, so an unknown backend must remain distinguishable from an explicitly unsandboxed process.

## What changed

- Carry optional `sandbox_type` metadata through command execution items and emit its metric tag as `sandbox_backend` in analytics.
- Propagate the observed backend through unified execution completion and failure events, including asynchronous exits.
- Preserve missing backend information as `None` and mark executed user shell commands as `Some(SandboxType::None)`.
- Exclude the metadata from serialized command items and generated schemas and TypeScript types.

## Testing

Extend tests for missing and explicit executor backends, backend propagation on failed execution, and analytics payloads, including platform-specific backend tags in app-server integration coverage.

GitOrigin-RevId: 178fe46824a6194910802ec02168ed40ee0b2019
2026-09-23 15:05:59 +00:00
sayan-oai 370cd7cba8 Allow environment selection updates during an active turn (#47435)
## What changed

- Add `environments` to `TurnSettingsUpdate` to replace the selection for subsequent steps without changing future turns.
- Capture model settings and environments together so combined updates apply or reject atomically, while existing steps retain their captured selection.
- Validate environment IDs, working directories, configuration ownership, and permission requirements against the running turn's selections.
- Preserve executor startup behavior when switching environments and use the step's local working directory for tool hooks.

## Testing

Add coverage for workspace switching and restoration on the next turn, atomic model and environment updates, permission validation, executor connection waits, and replacement of pending environment selections.

GitOrigin-RevId: 02b5c57a78fd594b2aed84fc09d9e99eb97be28c
2026-09-23 03:12:33 +00:00
sayan-oai c7828dd010 Keep step settings and approval environments consistent (#46556)
## Why

Background processes can outlive their launching turn. Their approval reviews need the originating environment's filesystem restrictions, even when the active turn uses a different environment. Remote restrictions must also be resolved using executor paths rather than the local filesystem.

## What changed

- Capture settings and environment selections together in `StepInputs`. Preserve the captured selection during active model updates while allowing environment startup to finish.
- Carry environment IDs into Guardian network and `execve` requests, and use the owning process's environment with current review settings. Refresh environment readiness for network requests that fall back to the active turn.
- Resolve remote denied paths and globs using the executor's policy context. Decline automatic approval when the request's environment is unavailable or an explicitly denied temporary directory cannot be resolved.

## Testing

Add regression coverage for active model updates retaining their environment while the next turn adopts a new selection, background approvals using their owning environment, newly ready network environments, and remote denied paths and globs, including Windows paths and missing temporary-directory metadata.

GitOrigin-RevId: b620d4b030c597a4f430fe0500864fa5469db3d4
2026-09-19 01:27:26 +00:00
iceweasel-oai a633ebc124 Always use private desktops for legacy Windows sandboxes (#46554)
## What changed

- Remove the private-desktop opt-out from elevated and unelevated Windows sandbox launches.
- Remove `windows.sandbox_private_desktop` and its managed requirement and API fields. Warn users to remove the obsolete setting.
- Require a private desktop name when launching through the Windows sandbox wrapper and command runner.

## Testing

Add coverage for the obsolete-setting migration warning and update wrapper tests to verify a live private desktop is passed and a missing desktop name is rejected.

GitOrigin-RevId: c7135f8d211aac8d812180691c2c1e433d77cde4
2026-09-19 01:21:32 +00:00
papayo-oai b244e9bafe Add a command-start callback for tool lifecycle extensions (#46539)
## What changed

Add `ToolLifecycleContributor::on_command_start` with `CommandStartInput` carrying the resolved command, working directory, selected executor's filesystem, and lifecycle context. Await contributors after command hooks and environment resolution so they can prepare the filesystem before `exec_command` runs, including calls from code mode.

Reserve process IDs only after preparation completes so cancelled preparation does not consume an ID. Keep deterministic process IDs from being reused after removal.

## Testing

Add tests for direct and code-mode calls that verify callbacks receive hook-rewritten commands and the executor's working directory, filesystem preparation completes before execution, and interrupted preparation prevents execution without consuming a process ID. Add a regression test for deterministic process ID reuse after removal.

GitOrigin-RevId: d10bcafcc583a6e3e8b5924d004806727e3763bb
2026-09-19 00:46:06 +00:00
iceweasel-oai 74af2496c9 Default local binding to true for MXC managed networking (#46523)
## Why

MXC's native host-loopback access is bidirectional, so it cannot enforce `allow_local_binding = false`. Treating an omitted setting as `false` prevents managed networking from working with the default configuration.

## What changed

- Preserve an omitted `allow_local_binding` until the executor's sandbox policy is known. Default to `true` for Windows MXC and `false` elsewhere, including remote execution.
- Reject an effective `false` for MXC managed networking after applying policy restrictions, without enabling disabled networking.
- Use the executor's resolved value for remote network approval decisions while preserving explicit controller restrictions.
- Document that local binding permits local servers and direct host-loopback connections and skips additional private-network destination checks; proxy domain rules still apply.

## Testing

Add coverage for per-executor defaults, explicit values, MXC rejection of `false`, and remote network review cleanup with the resolved policy.

GitOrigin-RevId: 0fa7c1eaec68bebada2b8f7af45688315eea70a9
2026-09-19 00:00:01 +00:00
sayan-oai e0f05de6e0 Allow approved escalation with environment-owned network policies (#46499)
## Why

Environment-owned network policies rejected explicit sandbox escalation before command approval, and retained terminals that bypassed or no longer matched those policies required a new terminal.

## What changed

- Allow `require_escalated` commands through the normal approval flow and bypass managed network proxies when full escalation is permitted.
- Preserve denied-read restrictions, including the sandbox and network proxy needed to enforce them.
- Track the network restrictions bypassed at launch and require escalation review for terminal input when launch permissions or network settings warrant it, instead of rejecting input outright.

## Testing

Extend network approval coverage for approved and denied escalation, unproxied remote execution, and preserved denied-read restrictions. Add retained-terminal coverage verifying command and `write_stdin` approvals with restricted and unrestricted filesystems, and update the unit test for changed environment network policies to expect escalation review.

GitOrigin-RevId: 50524b1bc4e3df58447c3c92fb9e50e69ed50cf8
2026-09-18 23:06:48 +00:00
iceweasel-oai 8b78600dc8 Enable MXC selection through Windows sandbox configuration (#46271)
## What changed

- Accept `windows.sandbox = "mxc"` and preserve the selected backend through environment configuration, command execution, patch writes, and sandbox metadata.
- Treat MXC as enabled in the TUI and report Windows sandbox readiness as `ready`, avoiding legacy setup prompts.
- Keep `allowed_sandbox_implementations` scoped to the legacy elevated and unelevated backends without restricting MXC.
- Default `windows.sandbox_private_desktop` to `false` for MXC while retaining `true` for legacy sandboxes.

## Testing

Add coverage for MXC configuration precedence, legacy requirement handling, sandbox selection, and TUI state. Add a Wine integration test that verifies command and patch routing fails when native MXC is unavailable and reports `windows_mxc` in turn metadata.

GitOrigin-RevId: e2162447d0750f60753864c92a20e02a7f297bca
2026-09-17 18:20:28 +00:00
Adam Perry @ OpenAI 841b5490b2 Preserve filesystem sandbox policy context when the cwd disappears (#46112)
## Why

Removing the selected working directory can prevent filesystem sandbox helpers from launching, even when the requested absolute paths remain accessible. Permission rules must stay anchored to the selected directory while those operations continue.

## What changed

- Require a policy `cwd` in `FileSystemSandboxContext` and launch filesystem helpers from the filesystem root while preserving the policy directory and workspace roots.
- Carry explicit `policyContext` in filesystem RPCs, preserving legacy wire fields and resolving omitted directories from older clients at executor ingress.
- Keep permission paths as executor file URIs and validate host compatibility where they are enforced.
- Bind Windows relative denial globs to the policy directory before changing the helper's launch directory, preserving home-relative patterns.

## Testing

Add regression coverage for `apply_patch` after working-directory removal, legacy RPC directory fallbacks, cross-platform permission URI transport, and Windows relative read denials. The patch regression verifies that an allowed file is updated while an explicitly denied file remains unreadable and unchanged.

GitOrigin-RevId: b0f4db722b27cb72ec129fc297c85732afac11f7
2026-09-17 04:37:54 +00:00
Sean Huang 83dc7d11e8 Preserve executor path URIs in permission profile workspace roots (#45863)
## Why

Executor profile roots can use path conventions that are not native to the current host. Converting them to host paths during configuration or turn reconstruction can reject or drop those roots, while case-insensitive comparison can hide Windows path spelling changes.

## What changed

- Store profile roots as URI-backed `ProfileWorkspaceRoot` values throughout permission snapshots and thread settings, preserving spelling in equality and deduplication.
- Keep effective workspace roots as `PathUri` values for permission materialization and status summaries. Convert Windows sandbox root hints to native paths only at native Windows sandbox boundaries, rejecting incompatible roots.
- Omit the legacy rollout `workspace_roots` field when profile roots cannot be represented as host paths, retaining the compiled permission profile.

## Testing

Add regression coverage for Windows and UNC root spelling changes, settings restoration and turn recording with foreign roots, executor-root status display, and backend-specific Windows root conversion.

GitOrigin-RevId: 903c068fd74959bdd10e7cb1141aa42b953a59a4
2026-09-16 04:23:46 +00:00
iceweasel-oai d4e11a9b97 Separate executor sandbox selection from Windows sandbox levels (#45730)
## Why

MXC is a sandbox implementation, not a restricted-token sandbox level. Executor requests need to represent that choice separately from `WindowsSandboxLevel`.

## What changed

- Introduce `WindowsSandboxSelection` for executor sandbox contexts and remove `Mxc` from `WindowsSandboxLevel`.
- Preserve the `windowsSandboxLevel` wire field and its serialized values for compatibility.
- Share sandbox selection between executor process launches and filesystem helpers, and use the new selection in capability discovery and skill reads.
- Disable Windows sandbox selection for executor paths that do not use Windows path conventions.

## Testing

Extend coverage for MXC wire serialization, Windows skill-read sandbox checks, and capability discovery with distinct permissions. Exercise remote filesystem write restrictions with both restricted-token and MXC sandboxes, including rejection when native MXC is unavailable.

GitOrigin-RevId: 266211377bcb138a0dc75861e9ff2225fa37a53d
2026-09-15 16:40:06 +00:00
viyatb-oai 99914f4950 Honor explicit Unix socket grants in the Linux managed sandbox (#45534)
## Why

Linux proxy-routed sandboxing denied standalone Unix sockets even when the effective network policy enabled `dangerously_allow_all_unix_sockets`.

## What changed

- Carry Unix socket permissions in `ManagedNetworkSandboxContext` and pass the prepared context through Linux sandbox launches with `--managed-network`.
- Allow `AF_UNIX` socket creation in proxy-routed mode when `dangerously_allow_all_unix_sockets` is enabled, while preserving network namespace isolation and restrictions on other socket families.
- Keep standalone Unix sockets denied by default and for path-only grants. Default missing fields in older serialized contexts to restrictive values.

## Testing

Add coverage for policy preparation and transport, legacy deserialization, and malformed policy rejection. Add a Linux integration test covering default denial, path-only denial, and explicit allow-all access, while checking that direct TCP access and `AF_NETLINK`/`AF_VSOCK` sockets remain blocked.

GitOrigin-RevId: 2695b945ad3e59fcb3faf7662d852a26650af16c
2026-09-14 22:40:20 +00:00
Adam Perry @ OpenAI 4d5d37c5f8 Add lifecycle tracing for unified exec (#45505)
## What changed

- Add spans for one-shot and resumable `exec_command`, `write_stdin`, session creation, and output collection, recording outcomes and output collection stop reasons.
- Correlate calls with conversations, turns, and processes; link stdin interactions to the original exec call and process start requests to executor process IDs. Omit empty turn and call IDs and those longer than 256 bytes.
- Propagate the current tracing span into the spawned one-shot execution task and distinguish timeouts, cancellations, and failures.

GitOrigin-RevId: 722728dc3f5b624e7a4da69fc867c3c672465af0
2026-09-14 19:39:08 +00:00
jwang-openai 4d8eca1ff3 Attribute command and plugin analytics to the invoking model (#45445)
## Why

Command execution and plugin measurement events lack model and reasoning-effort labels. Attribution needs to reflect the step that invoked the command, even when model settings change before a background process finishes.

## What changed

- Add `model_slug` and `reasoning_effort` to command execution and plugin measurement analytics.
- Capture model context from resolved step settings and carry it through execution, approval, Guardian review, and plugin metrics collection.
- Preserve the first command-start model context when subsequent start notifications arrive.
- Keep the carried context out of serialized protocol items and generated schemas.

## Testing

Extend analytics tests to cover model switches before invocation and during background execution, default reasoning effort, Guardian-denied commands, and repeated start notifications retaining the original model context.

GitOrigin-RevId: af90e1c0d39bab625f2e89786085b61a9b96c0ce
2026-09-14 15:30:22 +00:00
felixxia-oai 9c4879f3a5 Preserve complete actions in Guardian approval reviews (#44569)
## Why

Truncating action arguments can leave approval reviewers evaluating incomplete actions. Large actions need complete review input and explicit handling when they exceed the review budget.

## What changed

- Remove action truncation and the fixed synchronous action byte limit. Admit complete actions against the whole-request budget, splitting long text losslessly into bounded transport parts and accounting for their framing.
- Route actions exceeding the asynchronous action budget to synchronous review. Prevent cached scores from covering oversized calls, including expanded approval arguments, while allowing later small actions to recover score reuse.
- Request user approval when optional review exhausts its local input budget. Keep required review and compaction service failures closed to approval, and retire exhausted review sessions.

## Testing

Add coverage for complete large-action delivery, optional user fallback, required-review denial, subsequent review recovery, async overflow through MCP approval routing, and lossless text splitting with budget accounting.

GitOrigin-RevId: 08f06e68a94b2f779480dd6b6cf5bc30b241f6dd
2026-09-10 16:01:02 +00:00
Abhinav 205f3671e1 Use captured step settings for tool planning and execution (#44242)
## Why

After a model change within a turn, tools could still use the turn's original model capabilities, output limits, and telemetry attribution.

## What changed

- Build each step's tool plan from its captured model settings.
- Use those settings for image support and detail, command and MCP output truncation, extension metadata, and tool telemetry.
- Preserve the issuing step's model for delayed command completion events while allowing later `write_stdin` calls to use their own step's output limits.

## Testing

Add regression coverage for model changes within a turn, including tool replanning, Code Mode execution, image handling, MCP tool and resource output limits, extension settings, and delayed command completion.

GitOrigin-RevId: ef991598e89a846889baf770a0c9e12e56886d5d
2026-09-09 17:45:37 +00:00
Won Park 3d3df0a0ca Raise Guardian's action review limit to 200,000 bytes (#44060)
## What changed

Increase `GUARDIAN_MAX_ACTION_BYTES` from 8,000 to 200,000 bytes to allow larger actions to be reviewed. Keep unified exec stdin approvals capped at 8,000 bytes with a separate `MAX_STDIN_APPROVAL_BYTES` constant.

## Testing

Update aggregate payload rejection coverage for the new limit and exercise MCP elicitation reviews with tool descriptions exceeding the previous 8,000-byte limit.

GitOrigin-RevId: fd4b97980803a7a687449043931e6f1e57e260d3
2026-09-09 05:07:22 +00:00
Winston Howes 2e220af1f6 Protect shell snapshots when credential brokerage is enabled (#43909)
## Why

Shell startup files can introduce credentials or overwrite brokered dummy values. Snapshot capture and replay need to respect the command's sandbox and environment policy without persisting real credentials.

## What changed

- Capture and validate brokered snapshots per command using its requested shell, working directory, login mode, sandbox, and environment policy.
- Discover shell-initialized credentials and prepare snapshot exports for brokered replay. Preserve shell functions and aliases while preventing startup files from overwriting dummy credentials during replay.
- Rebuild snapshots as credential broker state changes and retain each command's snapshot for the lifetime of its process.
- Reject brokered POSIX shell execution when a protected snapshot cannot be created, and reject brokerage with `shell_zsh_fork`. Restore real credentials and remove brokerage markers for unsupported PowerShell and Cmd execution; escalated commands bypass protected snapshots.

## Testing

Add regression coverage for credential discovery and redaction, environment filtering, readonly exports, shell function and heredoc replay, command working directories and login modes, sandbox enforcement, and missing or disabled snapshots.

GitOrigin-RevId: 685356cb9e80f11cf69d053e4d239ee6ccf43a9e
2026-09-08 20:59:50 +00:00
Nick Steele b090e901f8 Add staged enterprise OIDC login and coordinated logout (#43844)
## Why

Enterprise sign-in needs to keep browser completion separate from credential storage so callers can recheck the active account and configuration before saving a grant. Logout must also prevent an earlier sign-in from restoring credentials, including from another process sharing `CODEX_HOME`.

## What changed

- Add enterprise login APIs in `rmcp-client` that return an authorization URL and stage validated credentials for an explicit `commit_if` call. Store grants only in the keyring after rechecking caller authority under the credential lock.
- Require a registered client ID, published metadata matching the configured issuer, HTTP loopback callbacks, a refresh token, and a valid OIDC identity assertion. Request `openid` and `offline_access` with `prompt=consent`, and omit MCP resource indicators from authorization and code exchange.
- Persist a login generation under the credential lock so logout invalidates pending and staged sign-ins across processes, even when no grant is stored.
- Keep credentials and account identifiers out of enterprise error chains and logs, and avoid logging callback payloads when the receiver has closed.

## Testing

Add coverage for discovery validation, loopback callbacks, PKCE, staged keyring storage, cancellation, stale attempts, cross-process logout, and error/log privacy. Preserve ordinary MCP OAuth login without a refresh token, and adjust the terminal polling test deadline to include the minimum empty-poll wait.

GitOrigin-RevId: 2a27b9a26505a2f6fdecce8877f6e2c21e148f72
2026-09-08 16:07:38 +00:00
iceweasel-oai 773f0b081d Preserve executor paths in Guardian approval reviews (#42838)
## Why

Guardian approval actions can contain paths from a remote executor whose path convention differs from the host, such as Windows paths reviewed on a POSIX host. Converting those paths to host-native absolute paths prevents the action from being reviewed.

## What changed

- Render command working directories using the executor's reported path convention, and preserve URI-backed paths for attribution.
- Carry foreign command and patch paths through Guardian events and app-server schemas as legacy path strings.
- Bound remote plugin attribution within the overall review deadline and reject Guardian action payloads that exceed the review byte limit.

## Testing

- Cover Windows and POSIX executor path rendering, foreign patch paths, protocol round trips, oversized payload rejection, and remote Guardian review context.

GitOrigin-RevId: 38be0fcdac897139519e74e077eb5cb4f8f8017e
2026-09-04 19:56:31 +00:00
jif 9bb1ea035f Expose the Codex version to commands and turn metadata (#42395)
## What changed

- Set `CODEX_VERSION` to the running package version in user shell and unified
  exec environments, overriding stale shell-policy or snapshot values.
- Add the reserved `codex_version` field to MCP turn metadata.

## Testing

- Cover version propagation through shell policies, shell snapshots, unified
  exec, and MCP metadata.

GitOrigin-RevId: 7846c70d668176530b1f467293b749dc9ddd79a0
2026-09-03 00:17:19 +00:00
viyatb-oai f53c91be2c Add attributed exec process lifecycle telemetry (#42373)
## Why

Exec-server process and network-policy events need stable attribution to the
launching tool call and executor without recording process payloads.

## What changed

- Add optional `ExecMetadata` to `ExecParams` and propagate the thread and tool
  call IDs from unified exec.
- Emit bounded OpenTelemetry events for process start, spawn failure, sandbox
  denial, and exit. Correlate them with the launch trace and registry-issued
  executor identity while excluding arguments, paths, environment values,
  output, and error text.
- Preserve launch attribution across long-running processes and reconnects, and
  attach the same metadata to network-policy audit events.
- Keep the protocol backward compatible when metadata is omitted, and prevent
  invalid trace headers from inheriting an unrelated active span.

## Testing

Add coverage for metadata serialization and propagation, lifecycle event
fields, trace relationships, reconnect behavior, spawn failures, sandbox
denials, and network-policy attribution.

GitOrigin-RevId: 7aa480a7289c73cb95e2c124c35500bb6f0d5084
2026-09-02 21:58:58 +00:00
jif 612e6491d5 Prewarm shell snapshots for eligible turns (#42137)
## Why

Shell Snapshot V2 previously captured the login-shell environment lazily when a
command started, adding that work to the command path.

## What changed

- Start one asynchronous snapshot capture after turn hooks accept the turn, so
  eligible local `exec_command` calls can reuse it without blocking the model.
- Use the turn's resolved tools, permissions, sandbox, environment, and shell
  configuration, and skip prewarming for unsupported or network-managed cases.
- Cancel outstanding prewarming during shutdown. Keep failed speculative
  captures retryable by real commands without consuming their retry budget.

## Testing

Added coverage for non-blocking capture and reuse, failure recovery, sandbox and
permission isolation, shutdown cancellation, hook-stopped turns, eligibility
gates, and concurrent capture retries.

GitOrigin-RevId: ff24a4f0328c06653e09d03fd0a3db1eccd65030
2026-09-01 21:16:12 +00:00
iceweasel-oai 1f4c47343a Apply remote platform semantics to exec safety checks (#42113)
## Why

Unified exec can run commands on an OS that differs from the Codex host. Using
host path and shell semantics for approval checks can therefore miss dangerous
Windows and PowerShell commands sent to a remote executor.

## What changed

- Thread the executor platform through command parsing, executable-name
  normalization, and dangerous-command classification. Legacy executors fall
  back to the host platform, while unknown reported platforms use Windows rules
  conservatively.
- Bound model-facing `exec_command` rejection messages and avoid echoing the
  rejected command into the error.
- Keep deterministic process IDs reserved after release so rejected test
  commands cannot reuse an earlier ID.

## Testing

- Add coverage that a long dangerous PowerShell command targeting a remote
  Windows executor is rejected with a bounded response.
- Verify deterministic process IDs advance after release.

GitOrigin-RevId: a26b4a63ea3d6df7140032b88b3e7aec0b85b948
2026-09-01 18:24:56 +00:00
jif b836aecd4d Preserve one-shot exec when unified exec is disabled (#41393)
## Why

Managed configuration can disable resumable unified execution while leaving shell tools enabled. This should not remove command execution entirely or grant access to retained processes.

## What changed

- Keep `exec_command` available in completion-only mode when `unified_exec` is disabled.
- Remove `tty`, `yield_time_ms`, `session_id`, and `write_stdin` from that mode, and add a `timeout_ms` argument.
- Terminate one-shot commands on timeout or turn cancellation, reporting timed-out commands with exit code 124.

## Testing

Added integration coverage for tool availability, timeout cleanup, and interruption cleanup under managed configuration.

GitOrigin-RevId: a382d34f922fdc4ba52889272c6db985abd42e47
2026-08-28 19:04:54 +00:00
jif 39507eea53 Reject NUL bytes in reviewed terminal input (#41354)
## Why

Manual terminal-input approvals shell-quote the proposed input, which cannot
preserve NUL bytes for an accurate review.

## What changed

Reject terminal input containing a NUL byte before creating an approval request
or sending any of the input to the terminal.

## Testing

Extend the unreviewable-input integration test to cover both oversized input
and NUL-containing input, and verify that rejected input is not executed.

GitOrigin-RevId: e738c59ba5570012663bf6168ad052be237ca226
2026-08-28 15:44:48 +00:00
jif 5eea8d0dd3 Review terminal input against retained permissions (#41328)
## Why

An existing terminal keeps the sandbox, network settings, and grants it had at launch. Later `write_stdin` calls must account for that retained authority, including when permissions change between turns.

## What changed

- Capture each terminal's effective launch permissions and compare them with the current environment before accepting non-empty input.
- Request approval when the terminal bypassed the sandbox, retains additional grants, strict auto-review is active, or its sandbox or network settings differ from the current policy.
- Reject input when current denied-read or environment-owned network restrictions cannot be enforced by the existing terminal, while keeping empty polls and non-TTY interrupts available without review.
- Include the effective sandbox mode and user-visible additional grants in `write_stdin` approval actions without exposing host-owned grant paths.

## Testing

Added unit and end-to-end coverage for retained cross-turn grants, strict auto-review, sandbox and network policy changes, denied reads, Windows sandbox backends, and private grant redaction.

GitOrigin-RevId: e2d71daf9358474c885998786c4928069100711c
2026-08-28 11:38:03 +00:00
jif efc020d224 Instrument stdin review size checks (#41189)
## What changed

Emit a `codex.unified_exec.stdin_review.size_check` counter when reviewing
input for an escalated terminal. Tag each check with:

- the result: `formatter_truncated`, `over_limit`, or `within_limit`;
- whether the submitted input is control-only or text.

Preserve the existing rejection behavior for truncated or oversized reviews.

GitOrigin-RevId: 6556beb2121cfaf91d572a26822b50442391c95f
2026-08-27 19:44:11 +00:00
jif bce96bcb43 Reject oversized reviewed terminal input (#41159)
## Why

Reviewing a shortened `write_stdin` action while sending the complete input could allow unreviewed bytes to reach an escalated terminal.

## What changed

- Require the fully formatted action and approval reason to fit within 8,000 bytes.
- Reject truncated or oversized actions before requesting approval or writing any bytes to the terminal.
- Document the reviewed stdin size limit in the app-server protocol.

## Testing

Add an integration test that uses JSON escaping to push a formatted action over the limit and verifies that it is neither offered for approval nor executed, while a subsequent valid write still succeeds.

GitOrigin-RevId: f6c96a78a65a136366c8119a7d242dfc2ec05fe6
2026-08-27 14:54:13 +00:00
Dylan Hurd a57b398351 Require approval for input to escalated terminals (#40978)
## What changed

- Add the `write_stdin_approval` feature flag, disabled by default, to require a fresh approval before sending non-empty input to an escalated unified-exec terminal.
- Route these reviews through hooks, Guardian, app-server, and the TUI as `writeStdin` approvals while keeping the parent command item unchanged.
- Preserve the terminal environment, launch directory, and escalation state across turns, and revalidate the process identity after approval before writing input.

## Testing

- Cover approval routing, policy decisions, process reuse, terminal identity preservation, app-server events, analytics, and TUI rendering.

GitOrigin-RevId: 4ba29eaae6208e934737ba078c96e589c7c2164d
2026-08-26 21:39:05 +00:00