## What changed
- Detect readable symbolic `:root` entries separately from effective full-disk access so narrower deny-read rules do not disable the Windows sandbox's broad-read setup.
- Add explicit readable roots to that setup while omitting the filesystem root itself, and prevent read roots at or below denied paths from being granted access.
## Testing
- Extend the elevated Windows sandbox integration test to verify that an allowed bundled skill under the user profile remains readable while exact and glob-based secrets stay denied.
GitOrigin-RevId: 8f6f267b78718b9e8609a9205c489f253f478491
## Why
A Multi-Agent V2 child can finish after the parent turn that spawned it, so its
successful completion needs to remain associated with that parent turn in
notifications and history.
## What changed
- Add `completed` to `SubAgentActivityKind` and emit the corresponding started
and completed item events on the spawning parent turn when a child succeeds.
- Persist completed activity as a canonical turn item in both legacy and
paginated history, and expose it through app-server history and schemas.
- Render completed activity as terminal in the TUI without counting it as a
separate tool call or tool-runtime event.
## Testing
- Cover successful completion in legacy and paginated history, late updates to
completed parent turns, TUI rendering, analytics, and rollout tracing.
- Verify that terminal child errors do not emit completed activity.
GitOrigin-RevId: 6c71eb8b10e7327611c6af84f70e294e27d94d02
## What changed
- Register the stable, requirements-only `in_app_local_automation` feature for desktop apps.
- Add the feature to the configuration schema.
- Verify that an enterprise requirement can disable local automation.
GitOrigin-RevId: 939f7f3ee15f662dc85589cd1bcc3838e4cd1287
## What changed
- Retain completed synchronous Guardian reviews as structured records until the async scorer builds its classification input.
- Render and bound review correlation, action, rationale, and full evidence body with the async scorer's transcript truncation marker.
- Extend the Guardian V2 integration test to verify oversized action and rationale content is truncated and the resulting review evidence remains bounded.
GitOrigin-RevId: 0000ba77b810748e34254dd00df4a69f8492e175
## What changed
- Recognize percent-encoded drive colons when inferring Windows paths, rendering
native path strings, and resolving same-drive relative joins.
- Reject Windows file URIs with percent-encoded `/` or `\` separators before
converting them to native absolute paths, so decoding cannot reinterpret URI
segment boundaries.
## Testing
- Cover uppercase and lowercase encodings for drive colons and path separators,
including local-drive and UNC file URIs.
GitOrigin-RevId: ecb6c92f4ef1af73f85e57a135abf6bc5bb968dc
## Why
Windows update commands could be influenced by the current project through
relative `PATH` entries or project-local package-manager configuration.
## What changed
- Resolve package-manager commands and `powershell.exe` using only absolute
`PATH` entries before starting an update.
- Run the resolved command from a temporary directory so the current project
does not affect the update, while retaining Windows `.cmd` and `.bat`
handling.
- Reject a relative-only `PATH` with guidance to update manually.
## Testing
Added a Windows regression test that verifies relative `PATH` entries and
current-directory command decoys are ignored.
GitOrigin-RevId: 15303165af42718244b99786f939f400dc6cbd07
## What changed
- Add a `GuardianPolicy` contextual fragment that renders as a standalone
developer message with the `guardian.policy` content kind.
- Use the fragment when rebuilding Guardian context and verify that its content
kind remains attached after history compaction.
GitOrigin-RevId: f7028fb29a48ad2453437f3d3a4405fcab7a2fd7
## What changed
- Build `skills.list` pages against the current tool-call response-byte budget.
- Skip entries that cannot fit, preserve pagination across retained entries, and report oversized metadata without repeating the warning for the same budget.
- Keep existing cursors compatible while encoding the response budget in new cursors.
## Testing
- Cover direct and Code Mode listing, budget changes between pages, provider and omission warnings, oversized entries, legacy cursors, and budgets too small to return discovery warnings.
GitOrigin-RevId: 4b34cd2714e4849fe9155ce3f0021b218763c395
## What changed
- Cover forwarding a legacy `env_vars` entry when the portable MCP server has no `env` map.
- Use the test workspace variable instead of `PATH` in the stdio round-trip test, keeping overlay forwarding distinct from portable environment expansion.
GitOrigin-RevId: c5cfb333e553581fc856d43a04e5be0abd9f65ef
## What changed
- Increase the Guardian sampler's initial WebSocket pool from 2 connections to 8.
- Keep pool growth and recovery tests focused on the two-connection scenarios they exercise while making the remaining tests derive their expectations from the initial pool size.
GitOrigin-RevId: e2eabcdde5828ac7df333271f3253e74d696f396
## Why
Yielding once after spawning the test executor does not guarantee that its TCP
listener is ready, so the environment can race the server during setup.
## What changed
Poll the executor address until it accepts a TCP connection, with a five-second
timeout and a clear error if startup does not complete.
GitOrigin-RevId: b44b5bbef666a97da1299d05790f5e9c976d914f
## What changed
- Replace structured numeric classifier output with a single `high` or `low`
token and map those classifications to `1.0` and `0.0` risk scores.
- Require the classification contract in both default and overridden prompts,
including when classifier instructions are truncated.
- Return the first streamed classification immediately while draining the
remaining response for connection reuse and token accounting.
## Testing
- Cover prompt rendering and truncation, classification parsing, early streamed
results, conflicting later output, WebSocket reuse, and approval routing.
GitOrigin-RevId: 31a57e4eb9bf8df2a161b84aa3d5b16ab8f2937b
## What changed
- Add `ToolCallSource` to extension `ToolCall`s and propagate direct or Code Mode
invocation metadata, including the runtime cell and nested tool-call IDs.
- Add `ToolCall::response_byte_budget` so extension tools can bound direct-call
responses by the host truncation policy while allowing Code Mode responses up
to the tool's own limit.
- Share the skills extension's response-size limit between its `list` and `read`
tools.
## Testing
- Verify that Code Mode source metadata is preserved when core constructs an
extension tool call.
GitOrigin-RevId: b10aef01be30d35b67bee3af24a1a4175c9ee112
## Why
On macOS, rejecting a symlinked writable root during sandbox setup could be
misreported as corrupt session data because both paths surfaced an
`InvalidInput` I/O error.
## What changed
- Treat only `InvalidData` errors as evidence of corrupt session storage.
- Preserve `InvalidInput` failures so the original sandbox preparation error
and its actionable details reach the user.
## Testing
Add a macOS regression test that configures a symlinked writable root and
verifies thread creation reports the sandbox failure without suggesting that
session data is corrupt.
GitOrigin-RevId: 2b83d9f92a517407b88c21b471fa8bff5fd20d1d
## What changed
Set the local exec server's `shellSnapshotV2` capability on Unix, while
continuing to report it as unsupported on other platforms.
GitOrigin-RevId: 5e60cfb459c9312a3c56f020c11f7eece6643ab2
## What changed
Pass the session source associated with each MCP configuration snapshot into
selected-environment server projection. This keeps Guardian reviewer isolation
decisions aligned with the snapshot being projected instead of rereading the
session's mutable configuration.
GitOrigin-RevId: 61fd891fec13f62cfea9886d13e2f94f6f60922f
## What changed
- Apply local `env_vars` declarations from `.codex-plugin/plugin.json` to matching stdio servers loaded from an Agent Plugin manifest.
- Replace matching `${NAME}` entries in the portable server environment with host environment forwarding while preserving the portable command, arguments, and unrelated servers.
- Ignore remote-sourced environment variables and support both inline and file-based Codex MCP declarations.
## Testing
- Cover matching-server filtering, local and remote sources, inline declarations, and an end-to-end `PATH` forwarding round trip.
GitOrigin-RevId: 843e1232a084fa5f571fe56e07266995b87fd53d
## What changed
- Include `environmentInfo` in the exec-server `initialize` response and seed the Rust client's metadata cache from it.
- Fall back to one lazy `environment/info` request when connecting to older servers that omit initialization metadata, then share the cached result across client clones and session recovery.
- Keep app-server `environment/info` requests uncached so they continue to probe the executor.
## Testing
- Cover initialization metadata, the legacy-server fallback, shared caching, accepted WebSocket environments, and repeated uncached app-server probes.
GitOrigin-RevId: 380132d9db183998d73e8c6b0954e4d70c7e8406
## What changed
- Use `gpt-live-1-codex` as the default model for frameless realtime sessions.
- Preserve an explicitly supplied per-session model override.
## Testing
- Cover both default and explicit model selection in the WebRTC frameless conversation test.
- Update the app-server live session request expectation for the new default.
GitOrigin-RevId: ce5dc978911ff0289d677b60fae2dd8cb1058d22
## What changed
- Include matching Codex tasks in the `@` mention popup when the active thread supports task tools, prioritizing tasks from the current working directory.
- Submit selected tasks as bounded live thread references so Codex can load their contents with `read_thread`.
- Preserve task mentions across composer history and thread start, resume, and fork flows.
## Testing
- Add coverage for task search and capability propagation, popup selection and rendering, submission encoding, history round-trips, and reference validation and limits.
GitOrigin-RevId: 17502be91bf6d4b01745668829eb69fb318cb5b9
## Why
The TUI rejected app-server dynamic tool calls as unsupported, so agents could
not inspect or manage other Codex tasks through a TUI session.
## What changed
- Add the `codex_tui` tool namespace for listing, reading, waiting on, creating,
forking, messaging, renaming, archiving, and restoring tasks.
- Handle tool calls through existing app-server thread operations, with bounded
inputs and responses and cleanup when calls complete or the TUI disconnects.
- Route delegation tools through an authenticated local MCP server with explicit
approval prompts, while respecting configured and managed MCP policies.
- Fall back to starting threads without dynamic tools when connected to an older
app server that does not support them.
## Testing
Add coverage for tool schemas and response bounds, task lifecycle operations,
approval-gated MCP transport, namespace dispatch, cancellation, and legacy
app-server fallback behavior.
GitOrigin-RevId: c782c11f0a3edceb3fa6909a4b92d6ce01a6eed3
## Why
The synthetic mount registry must remain private to the sandbox helper. A
writable bind overlapping its temporary directory could expose the registry,
and a pre-existing registry symlink could redirect bookkeeping into a writable
location.
## What changed
- Add the registry's read-only bind while constructing filesystem mounts, but
only when a writable bind exposes it and before applying deny masks.
- Reject a symlinked registry path before registering mounts or starting the
sandboxed command.
## Testing
Add coverage for symlink rejection and for denied temporary directories under
both full-root and minimal filesystem policies.
GitOrigin-RevId: 3adff28998f0ef8c8ec26a73e5a1183b4931c0e8
## What changed
- Show `SelfServeBusinessProLite` as `Business Premium` in TUI account displays instead of grouping it under `Business`.
- Update the display-name and app-server session tests for the new label.
GitOrigin-RevId: aac5c7abe9543f5d49f4e9dc9cbe20e7e3b41e5b
## What changed
- Add a dedicated contextual fragment for developer instructions that emits the
`generic.developer_instructions` content kind.
- Use the fragment when adding child-specific developer instructions to a
full-history subagent fork, preserving their classification and ensuring they
reach the child exactly once without appearing in the parent request.
## Testing
- Extend full-history subagent coverage to verify the child-only instructions'
annotation, placement, and count.
GitOrigin-RevId: 82589d311535225fed76d500a19458fda72f40f2
## What changed
- Build Responses Lite base instructions through a dedicated context fragment so the developer message carries the `model.base_instructions` content kind.
- Apply provider metadata cleanup after adding the base-instructions message, preserving the existing behavior for non-OpenAI providers.
## Testing
- Extend Responses Lite request coverage to verify the annotation is present for OpenAI requests and omitted for a third-party provider.
GitOrigin-RevId: b0317f92dfb9570860688b49e3a7668da516ee8c
## What changed
- Change the permission prompt content kind from
`generic.permissions_instructions` to `permissions.instructions`.
- Update request annotation tests to expect the new content kind.
GitOrigin-RevId: e1e39c74ac24668ac1f3467bb0cc1335a9408712
## What changed
- Derive each `InternalModelContextFragment` content kind from its source as
`<source>.internal_context` instead of using a shared generic kind.
- Cover the source-specific kind in the contextual user fragment test.
GitOrigin-RevId: 2075d558265fc1ae1ce394e9a865210d1bc270af
## Why
Image preparation can rewrite message content, including replacing images that
cannot be processed with model-visible error text. The positional content-kind
metadata must stay aligned with those rewrites.
## What changed
- Process message images together with their content-kind annotations.
- Preserve existing kinds for unchanged and resized content.
- Classify failed-image placeholders as `images.preparation_error`.
## Testing
- Cover metadata preservation across successful, resized, and failed images.
- Verify Responses Lite sends `user.image` and `images.preparation_error` kinds.
GitOrigin-RevId: 1be7bcbe47014251019bfff0d826c9dfe3239dec
## Why
Remote compaction's retained-message budget counted text but not images, so
image-heavy history could retain more context than the budget represented.
## What changed
- Add the opt-in `compaction_image_budget` feature to charge retained images
using the existing image size estimate.
- Keep images and their adjacent labels atomic when truncating a boundary
message, while preserving existing text, audio, metadata, and
client-authored developer-message behavior.
- Stop backfilling older messages when an image at the truncation boundary
does not fit.
## Testing
- Add unit coverage for image boundaries, annotations, audio, text-only
messages, and client-authored developer messages.
- Add an integration test covering repeated remote compaction with the feature
enabled, disabled, and left at its default.
GitOrigin-RevId: 88868bbd09d2858939dbae3f8402e1f497b4e3c6
## What changed
- Render omitted image and audio inputs as contextual fragments tagged with
`images.unsupported` and `audio.unsupported` content kinds.
- Normalize message media through annotated content so metadata for surrounding
content remains intact when switching to a model without media support.
## Testing
- Extend history and model-switching tests to verify content-kind annotations
before and after unsupported media is replaced.
GitOrigin-RevId: 4ee6577f8b78bd5a850ee01ea9d4590c20272850
## What changed
- Represent compaction summaries and Guardian-approved actions as typed contextual fragments.
- Inject subagent notifications through the same fragment path.
- Annotate the resulting request items with `compaction.summary`, `guardian.approved_action`, and `multi_agent.subagent_notification` content kinds while preserving their existing roles and text.
## Testing
- Verify the content-kind metadata on compacted summaries, approved actions, and subagent notifications.
GitOrigin-RevId: 01c93e7f08b2dc1c1e85ba69e82bfb5f56e6cca5
## Why
Local compaction rebuilds preserved user input as a single text item. Carrying
over the original per-item content kinds can leave its annotation metadata out
of sync with the rebuilt content.
## What changed
- Set the rebuilt item's content kind to `user.text` when the original message
had content-kind metadata.
- Preserve the remaining message and harness metadata.
## Testing
- Cover metadata normalization in compacted history.
- Verify persisted replacement history contains the merged text and a matching
`user.text` content kind.
GitOrigin-RevId: cd10b8ec68ef8ec2a272a90182e69875b60dc35c
## What changed
- Filter rolled-back model-switch instructions through annotated content so the
surviving developer fragments retain their matching content-kind metadata.
- Add regression coverage for annotation preservation and request-level metadata
alignment after rolling back a first-turn model change.
GitOrigin-RevId: 42a3c0cf4c5727bc6fe40990254467f40f4686f9
## Why
Developer-message content and its positional `content_item_kinds` metadata must stay aligned when parent history is prepared for a spawned agent.
## What changed
- Filter and rewrite developer-message content as annotated content so each retained item keeps its matching kind.
- Rebuild both message content and annotation metadata together after removing parent-only instructions and multi-agent usage hints.
## Testing
- Extend forked-history coverage to verify retained annotation kinds.
- Assert that spawned child requests contain the same number of content items and annotation kinds.
GitOrigin-RevId: 59748d9e8c4fc06ef8e5b90389bcf40465589f90
## Why
Rebuilding a truncated message from its content fields can drop passthrough
metadata and leave positional content classifications out of sync with the
items that remain.
## What changed
- Convert message content and its classifications into `AnnotatedContent`
before applying the token budget, then write both back together.
- Preserve other message and envelope metadata during truncation.
- Assign the `unknown` classification to content from legacy messages that do
not provide classifications.
## Testing
Expanded truncation coverage to verify that retained text and image items keep
their matching classifications and that unrelated passthrough metadata is
preserved.
GitOrigin-RevId: f84e2ebc3e97392e45f321dec3c171713864bdcd
## What changed
- Recognize `cua_repl` alongside `node_repl` when collecting Guardian review evidence, applying computer-use policy, and capturing transcript images.
- Render `cua_repl.js` results with the compact REPL history and transcript views.
- Preserve failed MCP call status and result content when replaying app-server history.
## Testing
- Cover both REPL server names across Guardian policy, evidence, image capture, history rendering, and failed-call replay tests.
GitOrigin-RevId: 8c13a721f718add403b07e727c1634b59203c51a
## Why
Guardian reviews were reported with the generic `subagent` thread source, making them indistinguishable from other delegated threads in persisted metadata and analytics.
## What changed
- Add the `guardian_review` thread source to the core protocol and app-server schema.
- Assign it to Guardian reviewer sessions and propagate the configured source through turn metadata, rollouts, and analytics.
- Continue treating Guardian reviews like subagents for paginated history and trusted-provenance checks.
## Testing
- Cover protocol round trips, delegate source selection, emitted analytics, request metadata, and persisted rollout metadata.
GitOrigin-RevId: 07480c122715812874c9d3b48bb39fc5c86b2367
## What changed
- Keep the normal composer footer visible when a draft contains the word `plan`.
- Remove the contextual “Create a plan?” prompt, its Escape dismissal behavior, and its per-thread dismissal state.
## Testing
- Update wide and narrow composer snapshots to cover the standard footer for plan-related drafts.
GitOrigin-RevId: 1a3c8cfce9d4effa2149790975133f652aa7c914
## What changed
- Preserve each contextual fragment's `ContentItemKind` when converting it to a response message.
- Classify user text, image, and audio content as `user.text`, `user.image`, and `user.audio` in their original order.
- Give additional context key-specific `additional_content.<key>` kinds and retain annotations on generated messages such as image resize notices and interrupted-turn markers.
## Testing
- Expand request-level coverage to verify content-kind annotations across mixed-modality turns, additional context, reminders, budgets, skills, model switching, subagents, and image resizing.
GitOrigin-RevId: 671e4545f39b335525c60d2a5df4608e8068cafc
## What changed
- Set `thread_source` to `memory_consolidation` in turn metadata for detached memory requests.
- Verify that startup requests carry matching turn metadata in the request header and nested `client_metadata`.
GitOrigin-RevId: 318d6f097e07463ac7a1c52b35a926532e67b83d
## What changed
- Carry each contextual fragment's `ContentItemKind` through initial context assembly and world-state updates.
- Attach the classifications to merged response messages through `content_item_kinds`, preserving their order alongside the message content.
- Convert extension prompt fragments into annotated developer fragments and classify built-in developer and guardian instructions.
## Testing
- Add an integration test covering roles and content annotations in the first request.
- Update world-state and persisted-history tests to account for annotation metadata.
GitOrigin-RevId: 71c48dad5b17bffd47ba03263e3eb6d5e74fbf4b
## What changed
- Require each `ContextualUserFragment` to provide a stable `<feature>.<name>`
`ContentItemKind`.
- Add `AnnotatedContent` and `RenderedFragment` so rendered text, its role, and
its classification can travel together to API boundaries.
- Derive extension-owned world-state classifications from the extension ID and
keep the skills catalog classification with its fragment implementation.
## Testing
- Verify that an extension-owned world-state section renders with an
`<extension-id>.instructions` content kind.
GitOrigin-RevId: e46b74a0bb41e0b6112667c9d36bc9e7f2714451
## Why
Collaboration can resume an archived descendant without unarchiving its
rollout. Archiving the parent again previously skipped shutdown for that
descendant because only rollouts newly marked as archived were prepared.
## What changed
Prepare every loaded thread in the spawn subtree for archival, including
descendants whose rollouts are already archived, before updating archive
state.
## Testing
Add an app-server integration test that resumes an archived child through its
parent and verifies that archiving the parent unloads the entire subtree.
GitOrigin-RevId: aca8c0d6ddb8900aad16becbeb594426cea1e3a6
## What changed
- Require each `PromptFragment` to include a producer-owned `ContentItemKind`.
- Re-export `ContentItemKind` from `codex_extension_api` and assign stable kinds to skills, memories, examples, and test contributors.
- Limit prompt slots to developer policy and developer capabilities, and combine contributed fragments into a single developer update.
## Testing
- Update extension registry tests to verify fragment ordering with the new content-kind metadata.
GitOrigin-RevId: ef8624a9b4ae9dce025bca9c0954d91dd8075e85
## What changed
- Add `ContentItemKind` as an open-ended string classification and carry an
optional list of kinds in `InternalChatMessageMetadataPassthrough`.
- Keep unknown classification values intact during round trips, while treating
a malformed `content_item_kinds` value as absent so the response item can
still be loaded.
## Testing
- Cover round trips for future classification values and deserialization of
malformed metadata.
GitOrigin-RevId: 5398cae5bb294a9f71ddd192e297177fab54a576
## What changed
- Cover live and replayed patch approvals recovering their file changes for the full-screen pager.
- Verify scrolling, resizing, dismissing and reopening the pager, and accepting or canceling a request exactly once.
- Document why approval requests recover diff contents from the matching stored item.
GitOrigin-RevId: 0b1ef25998aa466409ea79731e2c913a6d42388a
## Why
Showing the cursor before moving it can briefly expose it at its previous
position during a draw.
## What changed
Reorder terminal cursor updates so the cursor is positioned before it is made
visible.
## Testing
Add a regression test that verifies the cursor move escape sequence is emitted
before the show-cursor sequence.
GitOrigin-RevId: 2df277ba315bef4a7a56c11ecb78fcd52c354ac5
## What changed
- Add a global `codex exec --thread-source <SOURCE>` option and propagate it to newly created and forked threads.
- Default the source to `user` when the option is omitted.
- Expose the classification as `threadSource` in the TypeScript SDK. It applies when a thread is first created and does not override the source when resuming an existing thread.
## Testing
- Cover CLI parsing and persisted metadata for new, resumed, and forked threads.
- Verify that the TypeScript SDK forwards `threadSource` only for new threads.
GitOrigin-RevId: 67a55a2b1f91b3a88f946c2af1c2a0989abb3130
## What changed
- Mark Guardian classifier requests with `thread_source: guardian_classifier` in turn metadata.
- Remove the classifier-specific `request_kind` and `is_guardian_mode` fields.
- Update sampler and extension tests to expect the new metadata shape.
GitOrigin-RevId: 1654389ea538b7bd879045634816cbace4bd8f5c
## Why
MCP inventory can be cached or collected separately from a thread's live
connections, so tool availability alone does not describe the current runtime
state.
## What changed
- Add a nullable `runtimeStatus` to `mcpServerStatus/list` for thread-scoped
requests, covering not-started, starting, connected, authentication-required,
failed, cancelled, and disabled connections.
- Observe published connection state without starting or reconnecting servers,
and return an unknown status when no thread is supplied or the active
configuration no longer matches the published registration.
- Show connection state and tool counts in the compact `/mcp` view while
retaining the detailed inventory in `/mcp verbose` and compatibility with
servers that omit `runtimeStatus`.
## Testing
- Cover runtime status transitions, deferred and disabled servers, closed
transports, configuration changes, protocol compatibility, and TUI rendering.
GitOrigin-RevId: e3bb6efe652f0fa8b3c97d5c53e4729b3a87cd91
zm-oai