Commit Graph

1989 Commits

Author SHA1 Message Date
pakrym-oai
e3e5ad2847 Harden unsandboxed patch filesystem access (#39659)
## Why

An `apply_patch` path can be replaced with a symlink after verification, allowing an unsandboxed patch operation to reach a different file than the one that was approved.

## What changed

- Add `follow_symlinks` options to executor filesystem reads, writes, metadata lookups, directory creation, and removal, including the corresponding `followSymlinks` protocol fields.
- Implement no-follow filesystem operations on Unix and Windows that reject links in any path component and restrict file access to regular files.
- Run `apply_patch` with symlink traversal disabled when an otherwise-required sandbox is bypassed, while retaining the existing follow-symlink default for standalone callers.

## Testing

- Cover leaf and ancestor symlinks across patch add, update, delete, and move operations, including a path swap after verification.
- Exercise local and remote no-follow filesystem behavior, concurrent directory creation, special-file rejection, and Windows reparse points.

GitOrigin-RevId: 43fd479084891493ce13564fbd894b98f329c6dd
2026-08-20 08:10:08 +00:00
Ankush Gupta
4e1a772a7d Let Guardian V2 satisfy required model reviews (#39658)
## What changed

- Allow the Guardian V2 approval monitor to handle reviews for models that require automatic review.
- Preserve full Guardian review when Guardian V2 is disabled by configuration or managed requirements.
- Cover required-model routing for low- and high-risk actions, plus both Guardian V2 disable paths.

GitOrigin-RevId: d1201cc3dbd7c4a07de633388b14f17ada9feb39
2026-08-20 08:07:06 +00:00
pakrym-oai
1802a65571 Make core integration test permissions explicit (#39655)
## What changed

- Run local and remote compaction test turns with approvals disabled and an unrestricted permission profile.
- Keep the full test harness available where compaction turns need the configured model and working directory.
- Enable the Windows sandbox for managed-network unified exec process-event coverage.
- Update request snapshots to reflect the resulting `danger-full-access` sandbox metadata.

GitOrigin-RevId: 38eb46ca6ab28246d738e31eab900b2825072c7d
2026-08-20 07:52:35 +00:00
Adam Perry @ OpenAI
7ece061767 Enforce filesystem permissions when loading AGENTS.md (#39653)
## Why

Project instructions must respect the selected environment's filesystem read
permissions. Tightening those permissions for a later turn must not allow
previously cached instructions to reach the model.

## What changed

- Apply each environment's filesystem sandbox while discovering and reading
  `AGENTS.md` files.
- Fail thread or turn setup when sandboxing blocks a discovered instruction
  file, while allowing a restricted project with no instructions to start.
- Clear cached instructions before refresh and include the Windows sandbox
  level in the cache key.
- Ignore inaccessible ancestor marker probes so readable instructions in the
  selected working directory can still load.

## Testing

Added coverage for restricted projects, denied instruction files, cache
invalidation after permissions tighten, and unreadable ancestor markers.

GitOrigin-RevId: 6ea1a27b9c873a6260e4f87d42ae1317a6a4ae4b
2026-08-20 07:48:46 +00:00
evanz-oai
663da53823 Sanitize developer context in full-history agent forks (#39641)
## Why

Developer messages can contain both inherited agent policy and unrelated context. Full-history forks need to replace the parent policy without dropping the unrelated content that shares its message.

## What changed

- Filter fork-specific developer instructions by content item instead of excluding an entire developer message.
- Remove inherited multi-agent mode instructions before applying the child agent's current mode.
- Preserve unrelated content items and discard developer messages only when filtering leaves them empty.

## Testing

Extend agent-control and subagent notification tests to cover compound compacted messages, multi-agent mode instructions, and proactive-to-explicit mode transitions.

GitOrigin-RevId: 028834e237d8636c13b17a724574bc8eb09a55ba
2026-08-20 07:29:43 +00:00
jif
942af8447b Retire the untrusted approval policy (#39630)
## What changed

- Remove `untrusted` from the CLI, configuration schema, and MCP tool interface. Explicit `approval_policy = "untrusted"` settings now fail with an actionable error.
- Remove the known-safe command allowlist. Projects marked untrusted now request approval for every command unless an explicit exec policy rule allows it.
- Keep command parsing conservative by treating in-place `sed` forms as mutating and ignoring unrecognized commands when recording memory usage.

## Testing

- Cover rejection of the retired configuration value and approval requests for commands in untrusted projects.

GitOrigin-RevId: d6bf425edddfffbb325eee6acf383434af5fd33b
2026-08-20 07:03:02 +00:00
philn-oai
e396ef3fc1 Add cwd-relative turn diff paths (#39625)
## What changed

- Add the opt-in `cwd_relative_turn_diffs` feature.
- When enabled, render turn diff paths relative to each selected environment's
  working directory instead of the detected Git root.
- Preserve repository-root-relative paths when the feature is disabled.

## Testing

- Cover enabled and disabled behavior for nested working directories across
  supported originators.

GitOrigin-RevId: 8b4908706a82b01f33ccd035b0945f9a29fce26f
2026-08-20 06:52:01 +00:00
Jeremy Rose
bc3545b805 Validate linked worktrees before inheriting project trust (#39616)
## Why

A checkout could point its `.git` file at a trusted repository's worktree
directory without proving that the repository had registered that checkout.
This could cause project configuration from an unrelated checkout to be treated
as trusted.

## What changed

- Verify the linked worktree's `gitdir` backlink, `commondir`, registered
  checkout, and main checkout ownership before resolving the main repository's
  trust key.
- Reject missing, oversized, symlinked, mismatched, or swapped Git metadata.
- Preserve valid linked worktrees that use path aliases, separate Git
  directories, or non-UTF-8 POSIX paths.

## Testing

Add resolver and config-loading coverage for forged worktrees, metadata races,
case-sensitive paths, moved worktrees, and host MCP startup from project config.

GitOrigin-RevId: 6052a7d10ad2d613436f20175c356abdef8c758e
2026-08-20 06:29:32 +00:00
Jeremy Rose
250b5ea2bf Bind MCP OAuth refresh tokens to their issuer (#39615)
## Why

An authorization server discovered for an MCP server can change. A stored refresh token must not be sent to a different issuer than the one that originally granted it.

## What changed

- Persist the discovered authorization server issuer with new OAuth credentials and preserve it across refreshes.
- Validate that issuer against a single pinned metadata snapshot before refreshing or adopting stored refresh credentials.
- Require reauthentication when refresh credentials have no issuer or the issuer changed. An unexpired access token can still be used without exposing its refresh token.

## Testing

Add coverage for issuer persistence, missing and changed issuers, metadata changes during startup, and refresh-token preservation.

GitOrigin-RevId: 07e48ba892f627428a28bbed5cca4ad703e2a5fd
2026-08-20 06:25:17 +00:00
sayan-oai
530c1aed58 Prevent apply_patch from widening write permissions (#39614)
## Why

Deriving permissions from the parent of an already-writable patch target can
unnecessarily grant write access outside the intended workspace.

## What changed

Skip targets already covered by the active filesystem sandbox policy before
deriving additional parent-directory permissions. Targets outside the writable
area continue to request the required parent access.

## Testing

Added unit and CLI regression coverage for workspace-directory targets,
already-writable parents, and symlink escapes outside the workspace.

GitOrigin-RevId: 187109ff0b56a1a399cb8a9981b7e822977025d5
2026-08-20 06:21:54 +00:00
pakrym-oai
186b449bc2 Resolve model-provided shells by type (#39607)
## Why

A model-provided shell path should select the requested shell type without
allowing that path to determine which executable Codex runs.

## What changed

- Resolve model-provided shells through Codex's normal shell discovery and
  fallback logic after detecting their type.
- Keep the configured packaged zsh executable when the zsh-fork feature is
  enabled and the file exists.
- Update shell, unified exec, and network approval expectations to use the
  resolved local executable and arguments.

GitOrigin-RevId: ebe6f7eec2cfd1c0548d5bf1a26b7a30dba02cc2
2026-08-20 06:03:25 +00:00
rka-oai
198f42067a Keep async user messages on the direct tool surface (#39601)
## What changed

- Register `send_user_message_async` as `DirectModelOnly` so supported models can call it directly without exposing it through code mode.
- Exercise the async message flow with a code-mode-only model configuration and verify that the tool remains directly visible.

GitOrigin-RevId: ce22d5f63471ce90ac55ae2f3d0048f6cda57e01
2026-08-20 05:42:20 +00:00
sayan-oai
d75c85f651 Separate thread settings from environment configuration (#39597)
## Why

Environment-owned permission profiles and workspace roots must remain effective
without being persisted or restored as thread-owned settings.

## What changed

- Keep thread settings snapshots and restore data separate from the effective
  configuration supplied by the primary environment.
- Use resolved environment permissions, active profiles, workspace roots, and
  network policy when building turn context and session events.
- Preserve environment selections when agents are evicted, resumed, or spawned,
  and validate owner configuration when it becomes ready.
- Start memory initialization only after the primary environment is configured.

## Testing

- Extend remote-environment and multi-agent tests to cover settings persistence,
  owner permission profiles, workspace roots, spawning, eviction, and resume.

GitOrigin-RevId: d82f126981cd0190233020bbdd61d96c70558868
2026-08-20 05:29:12 +00:00
Dylan Hurd
4b450d2f1b Preserve unparsed shell wrappers in exec policy (#39588)
## Why

Reducing a heredoc shell script to its inner executable lets a prefix rule for
that executable apply to the entire wrapper, even though the full script was
not parsed as a plain command.

## What changed

- Fall back to evaluating the complete shell wrapper when plain-command parsing
  fails, including for heredoc scripts.
- Keep these commands sandboxed when only the inner executable is allowed.
- Propose the full wrapper as the exec policy amendment when approval is needed.

## Testing

Added exec policy, Unix escalation, and approval scenario coverage for unparsed
and heredoc shell wrappers.

GitOrigin-RevId: 8f65133acb6b7c638263917e1d9137e45990772c
2026-08-20 05:07:17 +00:00
iceweasel-oai
3b45c29062 Stop treating Git commands as inherently safe (#39524)
## Why

Repository configuration can cause even read-only Git commands to execute
helpers, so Git command arguments alone are not enough to establish trust.

## What changed

- Remove Git commands from the known-safe command classification on Unix and
  Windows, including commands nested in supported shells.
- Under the `unless-trusted` approval policy, require approval for commands such
  as `git status` unless an explicit execution policy rule allows them.

## Testing

- Cover direct, shell-wrapped, absolute-path, and PowerShell Git commands.
- Verify `git status` approval behavior with and without an explicit allow rule.

GitOrigin-RevId: dd04e0ddca0c56ba64ae64abe6e658bae7bf5a4d
2026-08-19 18:01:14 +00:00
jif
6972c57c78 Test disabled enhanced Node REPL transcript images separately (#39509)
## What changed

- Add a focused Code Mode integration test with Guardian transcript images enabled and enhanced Node REPL transcripts disabled.
- Verify that the Guardian request and parent request omit both the screenshot and its surrounding transcript markers.
- Remove this configuration from the broader parameterized transcript-evidence test.

GitOrigin-RevId: 1309de12337a28a7e1d49eca509ba73207d4d9be
2026-08-19 15:47:56 +00:00
jif
eb5a25aaa2 Test code mode notifications without a sync tool call (#39506)
GitOrigin-RevId: 9ee4dfb93fee83737fa555bb6111101991417a4d
2026-08-19 15:42:22 +00:00
jif
b0cdcce616 Test text stringify errors in the code mode runtime (#39505)
## What changed

Move circular-value coverage for the `text()` helper from the core integration
suite to the in-process code mode runtime tests. Verify that stringification
returns no content and surfaces the V8 circular-structure error without needing
a mock server or network access.

GitOrigin-RevId: d506591af5ae8ce0a8c7305d633a7b0f2e458335
2026-08-19 15:37:26 +00:00
jif
36268f177f Use a narrow fixture for the unified image resize test (#39501)
## What changed

Update the unified image budget integration test to resize a `6401x1` image to
`6000x1` and verify that the model receives the corresponding resize notice.

GitOrigin-RevId: 401e9728dc4bd6f0122bbc62f996a0b961e22b3a
2026-08-19 15:32:59 +00:00
jif
83915c7ca1 Correct normalized dynamic tool coverage across response modes (#39497)
## What changed

- Keep validating normalized dynamic tool visibility for both Responses and Responses Lite.
- Exercise the normalized dynamic tool call and its returned metadata only for Responses Lite.
- Let the standard Responses case complete in a single mocked response without expecting a dynamic tool request.

GitOrigin-RevId: 7793e6f6df07fc58c2976a773a1198496af08dfd
2026-08-19 15:26:15 +00:00
jif
af70018080 Use default timeouts in cyber exec policy tests (#39496)
## What changed

Stop setting explicit one-second `timeout_ms` and `yield_time_ms` values in the
mock command calls. The shell command and unified exec variants now use their
default timing behavior while testing cyber exec policy.

GitOrigin-RevId: b1c25304ca47e7b08f023fe678467fc00330158b
2026-08-19 15:21:11 +00:00
jif
94a831d9dd Test panoramic Guardian transcript image resizing (#39494)
## What changed

Use a 2049-by-32 image in the Guardian transcript evidence test and verify that
it is resized to 2048-by-32 while preserving its aspect ratio.

GitOrigin-RevId: 4b1b404c0fc76c46739379ef154e629bf8d669f3
2026-08-19 15:17:02 +00:00
rka-oai
f5a3dc5540 Remove the feature gate for async user messages (#39452)
## What changed

- Expose `send_user_message_async` to root agents whenever the selected model advertises support for it.
- Retain `send_async_message` as a removed compatibility flag so existing configuration is accepted without controlling tool availability.
- Update the async message test to cover model-driven tool exposure without enabling the legacy flag.

GitOrigin-RevId: 558b427c2b203a057dd7c836e0ec702ae6134346
2026-08-19 09:01:23 +00:00
alexsong-oai
3929c99a97 Refresh expired AWS credentials for Bedrock (#39410)
## Why

Bedrock sessions that use the AWS SDK credential chain need a way to recover when credentials expire during a request.

## What changed

- Add `aws.auth_refresh` provider configuration with an `aws` command, arguments, and a configurable timeout.
- Run the command for refreshable Bedrock authentication failures, reload the SDK credentials, re-sign the request, and retry it.
- Share refresh state across matching provider configurations so concurrent failures invoke the command only once. Bearer tokens, command auth, and static environment credentials do not use this recovery path.

## Testing

- Add coverage for configuration validation, refreshable error classification, concurrent refresh sharing, and an end-to-end retry signed with refreshed credentials.

GitOrigin-RevId: 0302fe3aabdbc1097e7bd62a74d407ba38a3cc57
2026-08-19 04:46:58 +00:00
sayan-oai
fde2156057 Enforce environment MCP policies (#39335)
## What changed

- Add environment-provided MCP restrictions for configured and plugin-provided servers.
- Disable attachment-scoped servers while their environment configuration is pending, failed, or unselected, while preserving selected-plugin access and the controller-owned Apps server.
- Apply the resolved policy to runtime startup, model tool exposure, telemetry, OAuth flows, and skill dependency installation.

## Testing

- Cover policy filtering for configured and plugin servers, environment state transitions, Apps ownership, and managed OAuth rejection.

GitOrigin-RevId: 7ca5d4dda14068e758497f88835d5cba685e159e
2026-08-19 01:26:16 +00:00
Abhinav
d35e5495f9 Route hook MCP calls through current connections (#39331)
## What changed

- Execute hook-triggered MCP calls through the runtime's latest connection set instead of preparing a separate catalog-bound call.
- Keep hook calls from waiting for server startup or reconnecting, and reject disconnected servers immediately.
- Apply the shorter of the hook-requested timeout and the server's configured tool timeout.

## Testing

- Update connection manager tests to cover non-waiting calls and disabled tool filters.

GitOrigin-RevId: 3166b2d1e26d9ae2b8b3a648b4d0897cc260eb93
2026-08-19 01:15:10 +00:00
rka-oai
71dbf72b05 Add the async user message tool (#39319)
## What changed

- Add `send_user_message_async` for root agents when the async-message feature is enabled and the model advertises tool support.
- Emit the supplied text as an asynchronous agent message and immediately return an accepted result so the turn can continue.
- Keep the user-visible update out of the model's input context.

## Testing

- Add an integration test covering tool registration, item events, continued turn execution, and model context.

GitOrigin-RevId: 13d5168cb8cd6742db17bb74a15c910994e9c98b
2026-08-18 23:59:19 +00:00
jif
7d9990fa30 Bind unified exec approvals to shell executables (#39311)
## Why

An unfamiliar executable can ignore its arguments, so trust in an apparent
inner command must not implicitly trust the executable that runs it.

## What changed

- Evaluate unfamiliar shell executables alongside their parsed commands when
  determining unified exec approval requirements. Inner commands can add
  restrictions, but cannot grant trust to the executable.
- Include the executable in reusable approval keys so approval for one custom
  shell does not apply to another.
- Parse literal PowerShell scripts without launching the requested executable,
  preserving command policy checks before approval.

## Testing

Add cross-platform coverage for spoofed shell paths, allowed and forbidden
inner commands, explicit custom-shell approval, and session approval isolation.

GitOrigin-RevId: 0dd2c7e9a2ac30965ef5fe5de1a8d2968bb5f9d0
2026-08-18 23:00:53 +00:00
jif
1a6e07a4fe Restrict agent roles to bounded configuration overrides (#39299)
## Why

Agent roles should customize a child agent without expanding the authority or changing the provider configuration inherited from its parent session.

## What changed

- Apply only supported role overrides for model behavior, developer instructions, personality, service tier, and capability reductions.
- Preserve parent-owned permissions, model providers, endpoints, MCP servers, notifications, and other unrestricted configuration.
- Keep managed feature requirements effective when a role disables capabilities, and reject symlinked user role files.
- Use the same bounded role application path for both multi-agent implementations and resumed agents.

## Testing

Add coverage for authority preservation, managed feature requirements, symlink rejection, provider inheritance, and provider routing after resume.

GitOrigin-RevId: c528d615b691f9c02bfbc21154d514ea07743010
2026-08-18 22:20:32 +00:00
Abhinav
87070a7792 Enable MCP tool hooks in Codex sessions (#39296)
## What changed

- Execute `mcp_tool` hook handlers through the session's shared MCP runtime, including managed hook configurations.
- Restrict hook calls to already-connected, cataloged, and policy-allowed tools. Unavailable servers fail immediately without starting or reconnecting them.
- Pass session metadata to hook tools, cap hook timeouts by the server timeout, and invoke hooks without model-tool approval or recursive hook dispatch.
- Record handler type and execution mode in hook telemetry, and mark memory as externally influenced after successful or blocking MCP hooks when configured.

## Testing

- Added end-to-end coverage for prompt interpolation, hidden tools, blocking decisions, unavailable servers, thread metadata, approval bypass, and memory-mode handling.
- Added MCP runtime coverage for startup readiness, tool filters, catalog revisions, and managed connector policy.

GitOrigin-RevId: 1647cb801ebc5fa385c7bda9d9c266a389c611b8
2026-08-18 22:10:43 +00:00
Dylan Hurd
ba37d0c45b Report network disconnects during approval (#39284)
## Why

When a local proxy request disconnects before network approval completes, the
owning tool call needs a model-visible explanation instead of remaining tied to
the abandoned request.

## What changed

- Track disconnect timing while plain HTTP and CONNECT requests await policy
  decisions.
- Cancel the owning execution and report how long the request waited when it
  disconnects before approval completes.
- Preserve an explicit approval outcome when disconnect cleanup runs afterward.

## Testing

Added unit coverage for disconnect tracking and outcome precedence, plus
end-to-end coverage for plain HTTP and CONNECT requests.

GitOrigin-RevId: b354b29bbe86f38e252fcaf529541f177480136b
2026-08-18 21:30:45 +00:00
sayan-oai
392328ed5d Preserve owner-provided environment configuration (#39278)
## Why

Thread settings could replace an owner-provided environment configuration with
`FromThread`, allowing the thread to take ownership of that configuration.

## What changed

Reject environment settings updates that change an existing owner-provided
configuration to `FromThread`.

## Testing

Cover preview and turn settings updates for pending, ready, and failed
owner-provided environments.

GitOrigin-RevId: c516954819447ceb29e2ff9f29fe781ca101ae54
2026-08-18 20:49:36 +00:00
olliem-oai
4a3e829c56 Inject Node REPL policy into Guardian review sessions (#39267)
## What changed

- Add a dedicated developer policy for Guardian reviews of Node REPL browser and computer-use actions.
- Inject the policy once before the first eligible Node REPL approval and retain it when the reviewer session is reused.
- Include Node REPL policy eligibility in the reviewer reuse key so sessions are not reused across incompatible model settings.
- Keep the approval request itself on the generic planned-action format.

## Testing

- Cover first-action injection, reuse after a shell review, repeated Node REPL reviews, and ineligible parent models through the production approval path.

GitOrigin-RevId: bfce190ff8599788aa85e388cc6a959d27fb489c
2026-08-18 19:22:31 +00:00
Dylan Hurd
d68b85a097 Require fresh approval beneath denied permission paths (#39266)
## Why

A stored permission grant may allow access to a parent while explicitly denying
a child path. A later request for that child must not be treated as already
approved by the broader parent grant.

## What changed

- Compare materialized permission profiles without intersecting away denied or
  reopened paths before deciding that a request is preapproved.
- Execute preapproved commands with the stored grant itself so its denied paths
  remain enforced.
- Fail closed when permission profiles cannot be materialized.

## Testing

Added unit and integration coverage for turn and session grants across
`exec_command`, `shell_command`, and `apply_patch`, including approval-disabled
and `Never` approval modes.

GitOrigin-RevId: 5455880328a89c7958f859c7ce87805dff9704fb
2026-08-18 19:17:09 +00:00
Peter Bakkum
ecb8013dfa Reconnect WebRTC Realtime sideband transports (#39257)
## What changed

- Reconnect frameless bidirectional WebRTC sideband sockets after unexpected transport loss with capped exponential backoff.
- Preserve pending text or handoff output and bounded transcript state across reconnects.
- Treat `404 Not Found` and `410 Gone` handshake responses as terminal session completion, and preserve HTTP status information from failed WebSocket handshakes.
- Bound Realtime delegation input and transcript fields while retaining the most relevant portion of each.

## Testing

- Add unit coverage for reconnect backoff, terminal status handling, transport error classification, transcript continuity and truncation, and pending outbound messages.
- Add an end-to-end WebRTC conversation test covering an unclean disconnect, reconnect, transcript reconciliation, outbound progress during sustained inbound traffic, and terminal session completion.

GitOrigin-RevId: 544fd7e542c3434d0bb42cfbcc7143604419a037
2026-08-18 18:41:40 +00:00
victor-openai
a1dc95d5af Scope MCP resource reads by connector (#39244)
## What changed

- Add an optional `connectorId` to `mcpServer/resource/read`.
- Forward the selected connector through `x-codex-turn-metadata` for threaded and threadless resource reads, restricting hosted app resources to that connector.
- Update the generated protocol schemas and app-server documentation.

GitOrigin-RevId: 5cc94d703abbbb6086665910c1c9ed5dc7075210
2026-08-18 18:01:39 +00:00
jif
9b9b614b02 Include node_repl screenshots in Guardian v2 reviews (#39227)
## Why

`node_repl` screenshots are nested tool results and do not appear in the parent
conversation history, so Guardian v2 transcript image collection could miss
them.

## What changed

- Allow Guardian v2 to enable bounded, thread-scoped `node_repl` image capture
  when transcript images are configured.
- Add retained `node_repl` screenshots to review requests when transcript
  sources include tool outputs, while deduplicating images and keeping them out
  of the parent turn input.

## Testing

- Add an integration test covering screenshot capture without the synchronous
  Guardian transcript feature flags and verifying that screenshots stay out of
  the parent request.

GitOrigin-RevId: 5f70c5f2e80389aa8b2a286c3b7f9b1104865486
2026-08-18 16:38:52 +00:00
Dylan Hurd
e7e13c68e2 Add Guardian v2 approval review metrics (#39224)
## What changed

- Pass metrics bound to the active turn's model to approval-review contributors.
- Add counter support to `ExtensionMetrics` while preserving host session attribution.
- Record Guardian v2 tool-call score lag and count stale-score fallbacks with the `score_lag` reason.

## Testing

- Cover counter forwarding and session metadata tags.
- Verify Guardian v2 metric samples for current and stale scores.

GitOrigin-RevId: 0ec34736d29d2e37ed217a27e773b4f6230ae38a
2026-08-18 16:27:54 +00:00
viyatb-oai
e13c1d569d Prevent custom providers from inheriting ambient auth (#39214)
## Why

Custom model providers that do not require OpenAI authentication could inherit
ambient authentication headers, including the bearer token and
`ChatGPT-Account-ID`, and send them to the custom provider endpoint.

## What changed

- Resolve providers without `requires_openai_auth` or configured `auth` as
  unauthenticated.
- Continue to honor an explicit `experimental_bearer_token` or command-resolved
  provider authentication.
- Preserve ambient authentication for OpenAI providers.

## Testing

Added unit and request-level coverage for custom, explicitly authenticated, and
OpenAI provider authentication behavior.

GitOrigin-RevId: d89a79604338bc660a3edb2af0068cfa9b694fa2
2026-08-18 15:06:09 +00:00
jif
711a5f8b3a Drop descendant progress updates after remote compaction (#39176)
## What changed

- Exclude descendant-authored `MESSAGE` progress updates from the history retained after remote compaction v2.
- Continue retaining descendant-authored tasks while omitting progress updates and final answers from subsequent requests.

## Testing

- Extend the remote compaction follow-up test to cover descendant progress updates and descendant-authored tasks.

GitOrigin-RevId: 3e3e60bb108d27e99e2a4c222eed4b9d02fd3829
2026-08-18 09:38:27 +00:00
rhan-oai
e2eea07140 Refresh collaboration instructions when their content changes (#39163)
## Why

Collaboration guidance can change without changing the active mode or model, such as after a model catalog refresh. Tracking only the mode and model leaves the earlier guidance in retained history.

## What changed

- Include a hash of the rendered collaboration instructions in the world-state snapshot so changed guidance is appended to retained history once.
- Emit one empty collaboration fragment when guidance is removed, preventing stale instructions from remaining active without repeatedly clearing them.
- Refresh legacy snapshots that lack an instruction hash once on resume.

## Testing

Cover same-mode catalog updates, clearing missing or explicitly empty guidance, retained-history behavior, and cold resume from legacy snapshots.

GitOrigin-RevId: 69f690adeccd1fb9794a6b15647e6efae3fec4f6
2026-08-18 07:32:03 +00:00
Dylan Hurd
4216123b3d Require approval for commands with dynamic shell words (#39159)
## Why

Tree-sitter can represent brace expansions, globs, and escaped text as plain
words even though the shell changes them at runtime. Treating their source text
as literal argv could let a command match a safe-command check or allow rule
that does not match what will actually execute.

## What changed

- Reject unquoted Bash and Zsh words containing expansion, glob, or escape
  syntax from literal command parsing, including heredoc command prefixes.
- Reject double-quoted escape sequences that the shell removes or interprets,
  while continuing to accept quoted metacharacters that remain literal.
- Require approval for affected commands under `UnlessTrusted`, even when a
  policy contains an allow rule for the unexpanded source text.

## Testing

Add parser and approval scenarios covering brace expansion, globs, escapes,
Zsh-specific syntax, heredocs, and quoted literals.

GitOrigin-RevId: 31f2c6062680c42ac65362e3f3eebfaaf4eb71da
2026-08-18 07:26:21 +00:00
Shijie Rao
230791fd1f Persist active permission profiles in turn context (#39145)
## What changed

- Add the optional `active_permission_profile` field to `TurnContextItem` to record the built-in or named profile that produced the effective permission profile.
- Populate the field when serializing a turn context while preserving compatibility with records where it is absent.

## Testing

- Add coverage verifying that turn-context serialization stores the active permission profile.

GitOrigin-RevId: d69142ab1b26595ab406235f89818ef41370e963
2026-08-18 05:46:08 +00:00
Matthew Zeng
de7bbb0481 Hydrate recommended plugin metadata on selection (#39143)
## What changed

- Fetch recommendations from the Codex-specific `/ps/plugins/suggested/codex` endpoint and parse its compact response shape.
- Fetch the selected plugin's details before presenting an install request, using them to verify availability and populate connector metadata.
- Skip install elicitation when the selected recommendation is no longer available, and return a retryable response when its metadata cannot be verified.

## Testing

- Cover the new recommendation route and response shape.
- Cover metadata hydration for available plugins and rejection of unavailable plugins.

GitOrigin-RevId: 2b0e2d70572aae2b7cd8e458b42e9dd14be3dbaf
2026-08-18 05:42:39 +00:00
Charlie Marsh
f97e775693 Fail closed on deeply nested command wrappers (#39122)
## Why

Dangerous-command inspection has a bounded wrapper depth. Returning no match
after that limit could let a nested dangerous payload escape policy detection.

## What changed

- Classify commands beyond the wrapper-depth limit as dangerous.
- Cover the boundary and overflow cases in the command-safety unit tests.
- Verify that exec policy rejects a deeply `env`-wrapped forced `rm` before it
  can delete a sentinel file when approvals are disabled.

GitOrigin-RevId: a6cdbbb7bdc6274a62745f668189fabaaf46745f
2026-08-18 02:23:57 +00:00
willwang-openai
fc6268ad38 Read plugin authentication state from AuthManager (#39087)
## What changed

- Give `PluginsManager` a shared `AuthManager` instead of a separately mutable authentication-mode snapshot.
- Read the current authentication mode and credentials from that shared manager for plugin discovery, startup tasks, CLI commands, MCP setup, and external-agent migration.
- Update test helpers and coverage to exercise plugin projections and curated marketplace selection as authentication changes.

GitOrigin-RevId: 600c94de5130eda2da5727e1a0b4d39083fefc56
2026-08-17 22:26:27 +00:00
iceweasel-oai
2013e04354 Preserve filesystem permission path conventions (#39084)
## Why

Filesystem permission paths can use a convention that differs from the host
running Codex. Converting them immediately to native absolute paths can change
the meaning of ambiguous paths such as `/C:/secret` or Windows UNC paths.

## What changed

- Store literal filesystem permission paths as `PathUri` values through the
  runtime policy and execution protocol.
- Keep legacy string-based serialization at explicit protocol boundaries and
  reject conversions that cannot be represented losslessly.
- Encode native paths as opaque URIs when a normal file URI would imply the
  wrong path convention.

## Testing

Added coverage for cross-platform and ambiguous path round trips, UNC path
variants, permission-profile serialization, and deny-policy enforcement.

GitOrigin-RevId: 5247713796d1f2bb4e02f94eb9fc82d4698060f0
2026-08-17 21:49:30 +00:00
Andrew Wilkes
682f57254f Persist generated images through turn executors (#39072)
## Why

Image generation did not save its result when the extension host did not provide a host-local save root.

## What changed

- Save generated images under the turn environment's `generated_images` directory through its sandboxed filesystem executor when no host save root is configured.
- Limit executor-written images to 32 MiB, reject symlinked output directories and existing destinations, and continue returning the image if persistence fails.
- Include the saved workspace path in the tool output hint while preserving host-managed persistence when a save root is available.

## Testing

- Extend the granted-turn-permissions integration test to verify the image and path hint are written to the turn workspace without creating a host-local artifact.

GitOrigin-RevId: 3d24381a75fe4595641b5250e19fac8ed473b2cd
2026-08-17 20:32:41 +00:00
sayan-oai
4a7b51c560 Add network policy metadata to environment configuration (#39055)
## What changed

- Add `EnvironmentNetworkPolicy` as a serializable view of portable domain,
  Unix-socket, upstream-proxy, and local-binding restrictions without exposing
  controller-owned proxy runtime settings.
- Add an optional `network_policy` field to `EnvironmentConfig` and re-export
  the policy and related permission types through the core APIs.
- Reject owner-provided network policies during environment preview and
  readiness until runtime enforcement is implemented, while preserving the
  existing controller policy when the field is absent.

## Testing

- Cover rejection through both environment preview and readiness, including
  preservation of the existing environment selection.

GitOrigin-RevId: 80ad4cf4d4a45632daa7a823e6cf568eb0e8bb80
2026-08-17 19:22:45 +00:00
iceweasel-oai
d0fd4e830a Preserve foreign paths in managed network approvals (#39040)
## Why

Unified exec could drop network approval registration when a selected environment used a Windows working directory on a non-Windows host because the trigger path could not be converted to a host absolute path.

## What changed

- Keep network approval trigger working directories as `PathUri` values and render them with their inferred native path syntax for Guardian requests.
- Fall back to the selected turn environment only when a trigger path can be converted to a host absolute path.
- Reject selected environment working directories larger than 8 KiB at the thread-manager validation boundary.

## Testing

- Cover managed-network approval registration for a foreign Windows working directory.
- Verify that oversized working directories are rejected as invalid `thread/start` requests.

GitOrigin-RevId: 646fbf12115a35a7e5cb04b511464797bee6647b
2026-08-17 18:15:56 +00:00