## Why
Managed command policies need to require a human decision independently of automatic review, hook allowances, and saved approvals.
## What changed
- Support `decision = "prompt-user"` in managed `requirements.toml` prefix rules, requiring a fresh, one-time human decision for matching commands.
- Add experimental `humanCommand` approval requests for clients advertising both `experimentalApi` and `requiredHumanApproval`. Accept only `accept`, `decline`, or `cancel`; reject commands when no capable client is available.
- Restrict responses to capable clients that received the request, and replay pending prompts to compatible clients on reconnect.
- Enable the capability in the TUI and update protocol schemas and client bindings.
## Testing
Add coverage for fresh decisions overriding saved allowances, hook allowances, and automatic review, plus child-thread approval routing and rejection of responses from incompatible or unrelated clients.
GitOrigin-RevId: 0b95ff6aab7f8a04b7298c8a4329d1fddf6a603e
## Why
MCP completion events can truncate large results and omit content removed for model consumption. Rollout traces need the original response, including content and metadata, as well as results for calls denied before reaching the backend.
## What changed
- Record MCP runtime results before callbacks, content filtering, and UI truncation, and record skipped calls as failures.
- Stop deriving MCP runtime completion records from protocol events to avoid duplicate records.
- Treat MCP runtime payloads as opaque results when reducing agent interactions.
- Buffer JSON trace writes and explicitly flush them.
## Testing
Extend app-server tests to verify that traces retain oversized MCP text, audio, structured content, and metadata while UI results remain truncated, and that denied calls produce exactly one failed runtime result with the denial reason.
GitOrigin-RevId: 57880770545eb5869420d7dc6fa4a15e481cae9d
## What changed
- Include ready environments' configured hooks in lifecycle events and execute command hooks using each owner's shell, working directory, shell environment policy, and managed network policy.
- Resolve tool environments before `PreToolUse` and use those targets for tool hooks, execution, and permission review. Route MCP hooks by server ownership and file-copy hooks to both endpoints.
- Preserve environment, MCP server, and terminal session selectors across hook input rewrites, rejecting attempts to switch targets.
## Testing
Add regression coverage for permission-request selector preservation, MCP resource hook ownership, and file-copy hooks that rewrite paths while preserving source and target environments.
GitOrigin-RevId: 31a3a6830523965285dab451cfc866c620ef6c83
## Why
MCP tool calls reported every aborted approval as "user cancelled MCP tool call", including interrupted requests and automatic cancellations in `exec` mode.
## What changed
Carry `user`, `interrupted`, or `non_interactive` cancellation reasons through MCP approval metadata and resolution. Mark explicit TUI cancellations as user actions, interrupted requests as interruptions, and automatic `exec` cancellations as non-interactive.
Use the reason to report when a call was cancelled before approval or because interactive approval is unavailable in `exec` mode. Preserve the existing cancellation message for clients that omit the reason.
## Testing
Update tests to verify that a closed approval response carries the interruption reason and that `exec` cancellation responses include the non-interactive reason.
GitOrigin-RevId: be2a5f7fef539b5db2add53b46aea27e2b8a66fc
## Why
MCP request failures and tool errors reported only through `codex/telemetry` metadata previously received an `unknown` error code, obscuring the failure category.
## What changed
- Classify typed request failures into bounded codes such as `request_timeout`, `transport_closed`, and `protocol_error`, and carry them into MCP call metrics and spans before errors become strings.
- Preserve typed timeouts when a prepared tool call exhausts its deadline during trusted access lookup.
- Accept allowlisted `error_code` values from `codex/telemetry` as a fallback after structured content and connector authentication metadata. Keep model output unchanged and ignore unrecognized metadata codes.
## Testing
Add coverage for typed errors wrapped in context, prepared-call timeout classification, metadata precedence and rejection, unchanged model output, and exported span error attributes.
GitOrigin-RevId: d7a440a6c9119b8a07a7f1fad697eb25af506f00
## What changed
- Preserve approval resolution sources through tool errors and tag cancelled MCP approvals with `error_type=approval`, `error_code=cancelled`, and `approval_source` (`guardian`, `user`, `hook`, or `unknown`). The source identifies the reviewer, not who caused cancellation.
- Record `context_changed` when validating a Guardian allow against changed authorization or review context, even when a concurrent stop or history reset determines the outcome. Retain the flag across retries and fresh-checkpoint recovery, and include it in the Guardian review counter.
GitOrigin-RevId: a19a986a7565f9a78a9bb2eaabdb5651834d28b8
## Why
MCP servers must forward sandbox policy unchanged to `codex sandbox --sandbox-state-json`, while interpreting launcher information to find the Codex CLI. Keep those contracts separate so consumers can preserve unknown policy fields.
## What changed
- Accept the experimental `codex/sandbox-state` capability alongside the deprecated `codex/sandbox-state-meta` capability, and send identical policy values under both `_meta` keys.
- Move `codexExecutable` out of the policy into `codex/sandbox-launcher`, supplied only when a verified CLI path is available for a local stdio server.
- Replace stale sandbox metadata while retaining unrelated entries, and remove stale launcher metadata when no launcher is available.
- Document the metadata contract and how servers should forward policy and retain authority for long-lived subprocesses.
## Testing
Update unit and integration coverage for policy serialization, identical state aliases, launcher availability across execution environments, and stale metadata replacement.
GitOrigin-RevId: e544c06e6e023953b1fc8069b7b1affa065262d1
## Why
MCP servers receiving sandbox state need a usable Codex executable to launch commands with the issuing call's policy. HTTP and remote servers cannot assume access to the host's filesystem.
## What changed
- Include optional `codexExecutable` metadata for local stdio servers when the host supplies an absolute, UTF-8 path to a CLI supporting `sandbox --sandbox-state-json`. Cache capability probes by executable path and bound them to five seconds.
- Document forwarding the sandbox state unchanged and requiring an explicit opt-out rather than silently falling back to PATH lookup or unsandboxed execution when the launcher is absent.
- Honor `useMxc` from forwarded sandbox state when selecting the Windows sandbox backend and network proxy policies, preserving a parent's selection made through CLI overrides.
## Testing
Add coverage for launcher eligibility across local, remote, and HTTP servers, invalid or missing executable paths, and binaries without sandbox-state support. Extend metadata integration and serialization tests to cover the optional launcher field, legacy state, and unknown future fields.
GitOrigin-RevId: ea8cd3770616e5a620b423a01052a7bc828bceb9
## What changed
Add the turn's `root_turn_id` to `_codex_apps` request metadata for host-owned Apps MCP calls. Remove any tool-supplied value before populating it from turn metadata, and omit the field for user-configured or extension-owned Apps servers.
## Testing
Extend unit coverage to verify that host-owned Apps calls replace an untrusted `root_turn_id` and user-configured Apps calls omit it. Update integration assertions for default and explicitly supplied root turn IDs, including approval flows, and verify that extension-owned calls omit the field.
GitOrigin-RevId: 754a642c2fff36a866b8cffa9fb3e161f232de08
## Why
MCP elicitation reviews used turn-start context, which could omit remote environments that became ready before the tool invocation and use stale environment permissions.
## What changed
Capture the issuing step's Guardian review context with each live MCP invocation and reuse it for elicitation reviews. Fall back to turn context when no matching live invocation is available, and preserve the captured context for in-flight actions.
## Testing
Extend the deferred-executor regression test to cover MCP elicitations, checking that Guardian receives the newly ready remote environment and its denied paths, excludes stale local denied paths, and returns the denial to the parent model.
GitOrigin-RevId: 0cc58b8f30543a9af87d53e1a90f574a8e6a2f84
## Why
Paginated thread history can persist large MCP results in completed tool-call items. Bound these stored results to avoid retaining multi-megabyte payloads.
## What changed
Apply a 64 KiB preview budget when persisting oversized MCP results in paginated history. Replace the result with a truncated text preview of its serialized JSON, preserving `is_error` and clearing `structuredContent` and `_meta`. Leave small results unchanged.
Share the truncation helper with the existing MCP tool-call event path.
## Testing
Add helper tests for unchanged small results and oversized results with structured content and metadata. Add a thread-history test verifying that persisted MCP results contain a bounded preview with the beginning, end, and truncation marker while preserving tool arguments.
GitOrigin-RevId: 09dce73c70bfd357c9b9630f456e9e5c1d8492cf
## 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
## What changed
Capture each environment's effective Windows sandbox backend in the MCP runtime and include it as `useMxc` in sandbox state metadata for supporting servers. Use the server's captured environment selection, including local fallback, so the local MXC preference does not leak into attached environments. Default missing backend information to `false`.
## Testing
Extend tests to cover MXC metadata handoff, attachment isolation, local fallback without a selected local environment, and preservation of captured backend settings across runtime refreshes.
GitOrigin-RevId: f559bffeff383838334e5a475b1eab608d571fa1
## Why
The transcript supplied to Guardian may omit earlier user instructions, restrictions, or revoked permissions. History retrieval lets the reviewer check relevant authorization before approving actions with side effects.
## What changed
- Add the disabled-by-default `guardian_conversation_history_tools` feature. With Apps enabled, expose `user_message.search_messages` and `user_message.read_messages` through the parent's live Apps connection and conversation identity.
- Recheck the parent's current app and tool policy on each call, rejecting disabled tools and calls requiring approval.
- Add retrieval instructions that distinguish user authorization from assistant context and account for later revocations and incomplete results. Allow overrides through `auto_review.experimental_conversation_history_prompt`.
- Limit history responses to an estimated 4,000 tokens by default, configurable through `auto_review.conversation_history_max_output_tokens`, while preserving stricter parent and reviewer limits.
- Allow explicit extension registries for isolated sessions and prevent those sessions from inheriting the implicit Apps connection.
## Testing
Add scenarios covering history tool exposure, parent connection and identity reuse, custom prompts, output truncation, stricter reviewer budgets, and live permission changes on a reused reviewer. Extend configuration coverage for blank prompt overrides.
GitOrigin-RevId: 055a69b113c8548bd58e7d5618ea026ba6d1ffb1
## Why
Defaulting missing or unsupported display preferences to `inline` prevents clients from applying resource display defaults.
## What changed
Populate `mcpAppUi` only when a tool descriptor has a resource URI and an explicit `inline` or `fullscreen` preference. Preserve `mcpAppResourceUri` independently in tool-call events, including when `mcpAppUi` is unset, and document the behavior.
## Testing
Update integration coverage for explicit display modes, missing and unsupported preferences, and legacy resource URIs, checking tool-call events and resumed history.
GitOrigin-RevId: 4876cced068d8e464adeb265abd053d8abe667ce
## Why
Guardian needs the assistant's delivered question to interpret a user's reply. Messages sent through nested Code Mode tools must remain available as review context, and approvals based on earlier context must become stale when a new delivery is confirmed. Assistant messages do not themselves grant authorization.
## What changed
- Capture successful hosted User Messaging sends after input rewriting and before result callbacks or post-tool hooks.
- Retain bounded delivery text in acceptance order, persist it through cancellation and shutdown, and preserve it across compaction and resume with an older-client-compatible rollout encoding.
- Track assistant review context separately from user authorization, invalidating pending and cached approvals for both local and worker reviews when that context changes.
- Associate retained deliveries with the correct instruction or communication boundary during rollback.
## Testing
Add coverage for nested messaging review context, fast replies and communication ordering, shutdown persistence, stale local and worker approvals, rollout compatibility, and rollback retention.
GitOrigin-RevId: 1bc1ec9e8947560b99f4b39a42ddb9f2099f519b
## Why
The Browser connector on `codex_apps` needs the computer-use policies and review handling already applied to `node_repl` and `cua_repl`.
## What changed
- Classify `connector_openai_browser` using registered tool metadata and preserve its computer-use scope through Guardian review.
- Extend confirmation-policy forwarding, review evidence capture, JavaScript execution tracking, and initial-call approval handling to the Browser connector.
- Correlate Browser elicitations with live invocations so nested actions retain their own review identity while assessments are attributed to the originating call. Require verified Browser identity for strict nested review.
- Include the Browser connector in computer-use policy prompts and bundled model messages.
## Testing
Add integration coverage for ordinary and strict Browser nested reviews, including policy injection and action attribution. Verify strict review declines requests with missing or unknown invocation correlation or a non-Browser registration.
GitOrigin-RevId: b04af6fb9db1bac2203dc4265913d210746df90b
## Why
Code Mode callbacks can retain skill tools after another turn becomes active. Looking up the active turn when a delayed skill invocation completes can lose access to the originating turn's metrics and metadata.
## What changed
- Capture and retain the originating `SkillTurnMetrics` when constructing skill analytics.
- Expose turn analytics metadata through the turn extension store and carry it into skill telemetry.
- Add optional turn metadata to `TrackEventsContext` and pass it from app, skill, and plugin usage call sites.
## Testing
Add a regression test that yields a Code Mode cell, starts another turn, and releases both skill reads through a shared barrier. Assert that each `skill_invocation` event retains its originating `turn_id`.
GitOrigin-RevId: aa629dd5f84563d558aa6a86bfbdfc356f1b98e4
## What changed
- Record each MCP source and its first turn, including connector and plugin identifiers when available. Cover direct and Code Mode calls, including returned errors and results that are not printed.
- Persist cumulative attribution checkpoints and restore them across compaction, resume, and forks, including forks limited to recent turns.
- Attach fresh attribution to Responses API `client_metadata` under `mcp_attribution`, outside model-visible content. Restrict transmission to allowed OpenAI HTTPS destinations for both HTTP and WebSocket requests.
- Report `attribution_error` for legacy history without checkpoints, malformed or conflicting attribution, and serialized attribution exceeding 16 KiB.
## Testing
Add coverage for source deduplication, checkpoint persistence and restoration, recent-turn forks, direct and Code Mode calls, destination filtering, and the serialized size limit.
GitOrigin-RevId: fd285e152ca9e24bfa000debb20013709d67a86e
## Why
MCP requests requiring user input previously failed in subagents with guidance to ask the parent agent, blocking browser sign-in, form input, and interactive tool approval in the child thread.
## What changed
Remove the root-only MCP elicitation guard and `allow_user_interaction` plumbing so subagents can surface prompts and wait for responses under the existing approval policy and automatic review rules. Connector authentication can now return retry guidance after acceptance or preserve the original failure when declined.
Keep legacy tool approvals through `request_user_input` restricted to the root thread.
## Testing
Update unit and integration coverage for subagent prompt resolution, form responses, connector authentication acceptance and decline, automatic approval, strict review, and approval-policy updates on reused connections. Update the browser sign-in scenario snapshot to show the subagent continuing after an accepted response.
GitOrigin-RevId: c226fc6dfde724ed22b91dc04dd32bbc15245bee
## Why
MCP requests that need human input, including browser sign-in, must be handled by the root thread. Subagents need guidance to hand these blockers to their parent without prompting the user or automatically accepting requests that require input.
## What changed
- Reject interactive MCP elicitations and tool approval prompts in subagents with guidance to ask the parent and wait before retrying.
- Recognize browser authentication and `codex_requires_user_input` metadata even when the form schema is empty, while preserving automatic permission approvals and review decisions.
- Carry user-interaction eligibility through MCP runtime creation and connection reuse, and guard prompt registration.
- Preserve connector authentication diagnostics alongside handoff guidance, subject to normal tool-output limits.
## Testing
Add unit and integration coverage for blocked subagent prompts, root browser authentication, automatic approval and review, connection reuse, and authentication diagnostic preservation and truncation. Add a request-history snapshot for browser-auth handoff guidance.
GitOrigin-RevId: 83e146b6e5c1a2a22a34681ad45615f504b3c96c
## What changed
- Add `ResolvedModelMessages` to resolve catalog text and bundled defaults while preserving explicit empty overrides and their source.
- Move base-instruction rendering, Guardian prompt composition, multi-agent role rendering, and `update_plan` guidance filtering into `codex-prompts`; migrate consumers to the shared APIs.
- Separate permission-profile resolution from prompt composition, and annotate Guardian policy and classifier instructions with content kinds.
## Testing
Add and update coverage for missing versus empty templates, literal overrides, multi-agent role composition, Guardian policy substitution and truncation, and preservation of permission path spellings and order.
GitOrigin-RevId: 52335bb7acec0f432d5c57acb2accd5f0276056e
## Why
Clients need widget presentation details to render MCP Apps without waiting for the full MCP catalog, including when replaying saved history.
## What changed
- Add `mcpToolCall.mcpAppUi` with the invoked descriptor's `resourceUri` and `preferredModelDisplayMode`, and carry it through tool-call events and saved history.
- Support `fullscreen` and default to `inline` when the display preference is missing or unsupported.
- Keep existing resource URI fields for compatibility. Leave `mcpAppUi` null for older history and tools that declare widgets only in result metadata, where clients still use catalog discovery.
- Update protocol schemas, TypeScript and Python types, and app-server documentation.
## Testing
Add parameterized integration coverage for fullscreen, missing and unsupported preferences, legacy URI metadata, and result-only widgets, verifying consistent tool events and preservation across session resume.
GitOrigin-RevId: 2a9bed804dcea8c2b4903b8406fa6710681f7f5e
## What changed
- Record `auth_or_link` for Codex app calls with trusted connector authentication failure metadata, capturing it before result callbacks or model-facing rewrites. Propagate the classification to MCP tool-call and app-usage analytics.
- Record `approval` when a dispatched approval request is denied, times out, or aborts, covering both MCP elicitation and legacy user-input approvals.
## Testing
Add unit and turn-level coverage for authentication failures, metadata removal by callbacks, successful and rejected approvals, and closed approval response channels. Verify event counts, classification, and exclusion of sensitive test values and authentication URLs from analytics payloads.
GitOrigin-RevId: 493df2a2923f346a0f644f1f26ab8b6b9b8888e0
## What changed
Add an optional `elicitation_type` to app-used and MCP tool-call events, with `auth_or_link` and `approval` classifications and `null` for unclassified calls. Existing core app-use tracking passes `None`.
Expose an API to queue MCP classifications by thread, turn, and item before completion. Preserve them across turn completion, consume them on item completion, and clear them on thread closure. Bound pending classifications to 256 entries, evicting the oldest when full.
## Testing
Add coverage for serialization, first-classification retention during app-use deduplication, per-call classification across turn completion, pending-state eviction and cleanup, and exclusion of tool arguments from emitted events.
GitOrigin-RevId: 185a2ccb38153e123fc731231edff0259a26bce3
## What changed
Include `sessionId` and the originating `windowId` alongside `threadId` and optional `itemId` in MCP request metadata. Retain the originating item and window for code-mode cells across waits and compaction, including the window when no matching history item is found.
## Testing
Extend metadata assertions for direct and nested MCP calls. Add a regression test verifying that a code-mode cell retains its original item and window IDs when it resumes after compaction.
GitOrigin-RevId: 5e3cf761f2bed4c16565334c94654496367325fd
## Why
Model and reasoning effort updates during a turn can leave request metadata and tool hooks reporting the turn's initial settings. Metadata should describe the step that issued the request or tool call.
## What changed
- Share captured execution metadata across Responses, MCP, and extension tool calls, including model, reasoning effort, and automatic review and Node REPL flags.
- Build Responses tool inventory metadata from the issuing step's finalized tool router. Attach the finalized inventory separately for remote compaction.
- Use captured step settings for pre- and post-tool hooks, and captured review settings for permission-request hooks.
## Testing
Add and extend regression tests for model and effort changes during a turn, MCP metadata, pre-tool hook model attribution, captured review flags, and tool inventory matching the issuing request.
GitOrigin-RevId: 9dee46a8b4839de8b434cdad4ed441cc0bb6ff9b
## Why
A code-mode cell can outlive its turn. Nested tool calls dispatched during a later turn need the original step's tools and context, while approval handling must still work across that turn boundary.
## What changed
- Retain each cell's originating `StepContext` for nested tool dispatch and cancel queued calls whose context has been released.
- Keep MCP approval metadata available for the lifetime of the running invocation, keyed by server and call ID.
- Apply Guardian denial accounting and interruption to the active turn, including reviews from an earlier cell.
- Carry `turn_id` in legacy MCP begin/end events so history reconstruction and rollout migration assign late completions to their original turn. Preserve the current-turn fallback for older records without it.
## Testing
Add regression coverage for originating tool selection across turns, callback and metadata cleanup, delayed MCP elicitation review, Guardian interruption of the active turn, and late MCP completion attribution with legacy compatibility.
GitOrigin-RevId: 4533379aae6e4ecb4aabe5a25e4aca5d65385d76
## What changed
- Apply `disabled_plugin_ids` to plugin skills, recommendations, hooks, and MCP servers without modifying shared plugin state.
- Activate selection changes when the next task starts, keeping pending settings from changing the active runtime.
- Hide app tools contributed only by disabled plugins from model tool catalogs and search. Preserve connectors shared with enabled plugins and existing direct Apps RPC behavior.
- Include plugin identity in MCP approval keys and use that identity when persisting plugin tool approvals.
## Testing
Add regression coverage for disabling and re-enabling plugin skills and tools, deferred activation of settings, shared connector ownership, selected plugin servers, executor hooks, and plugin-specific approval keys and persistence.
GitOrigin-RevId: 1153ff6aa7ab6953d50e838da05203904ecd2956
## 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
## Why
Queued prompts and `request_user_input` answers can be persisted in a different
order from when the host accepted them. Using persistence order can therefore
reorder retained instructions during replay or apply the wrong rollback
boundary.
## What changed
- Reserve an acceptance sequence for user prompts and elicitation responses
when retained thread context is enabled.
- Persist that sequence with user-message metadata and verified answers, and
use it when ordering, bounding, replaying, and rolling back retained context.
- Keep events without acceptance metadata compatible with legacy recording
order.
## Testing
- Cover delayed queued-input recording, rejected prompts, checkpoint replay,
compaction, rollback migration, and legacy retained-context behavior.
GitOrigin-RevId: 42d24465cc2033bc51c0c2da79d3c0884a8ad98a
## What changed
- Preserve the selected app account `link_id` when building native MCP tool
approval requests.
- Add `link_id` and `link_is_implicit` to the elicitation metadata, recognizing
IDs with the reserved `implicit_link::` prefix as implicit links.
## Testing
- Extend the app link policy integration test to verify elicitation metadata
for default, explicitly selected, and implicit account links.
GitOrigin-RevId: a76731d9f5f3640318187511ccdc0dc82967a9c5
## Why
Remembering an app tool approval by connector and tool alone could reuse an
approval when the same tool was called with a different selected account.
## What changed
Include the app `link_id` in MCP tool approval keys so remembered session
approvals apply only to the account link that was approved. Calls for another
link, or calls without a link selector, request their own approval.
## Testing
Add an integration test covering calls across two link IDs and the legacy
no-selector case.
GitOrigin-RevId: 7dd88330b75de312469020d5892dfb2fa5d5fada
## What changed
- Add `approvalsReviewer` to the experimental `turn/settings/update` API.
- Apply reviewer changes to subsequently captured steps and new background approval requests while preserving pending approvals and future-thread defaults.
- Allow reviewer-only updates without `step_model_switching`, while continuing to enforce managed reviewer restrictions and model-required auto review.
- Use an explicit live reviewer update for MCP approvals while retaining refreshed thread defaults for clients that have not set one.
## Testing
- Cover switching between user and automatic review during a live turn, future-turn isolation, and managed-authority rejection.
GitOrigin-RevId: e1216b09c6a7972c2c9eaf4955d8d57d60604ca1
## What changed
- Retain MCP invocation metadata for Node-backed REPL servers so nested
elicitations can resolve the enclosing tool call.
- Use a valid, same-server `callId` from the current turn as the Guardian
assessment target while continuing to review each nested action and connector
independently.
- Fall back to an elicitation-specific target when `callId` is missing,
malformed, unknown, from another server, or from an earlier turn.
## Testing
- Cover ordinary and strict reviews for `node_repl` and `cua_repl`, multiple
nested decisions, unrelated servers, and invalid or stale call IDs.
GitOrigin-RevId: adea4b5cff96726a540ff3b3ea902b0f5dd99299
## What changed
- Resolve `link_id` from tool-call arguments when Apps metadata sets
`requires_explicit_link_id` to `true`.
- Reject the call before approval or execution when the required selector is
missing, empty, or not a string.
- Preserve catalog-provided account metadata for legacy Apps tools and leave
non-Apps MCP tools unchanged.
## Testing
- Add unit coverage for required selectors, malformed values, legacy
fallbacks, and non-Apps tools.
- Add end-to-end coverage for execution, approval prompts, and rejection when
an Apps call omits `link_id`.
GitOrigin-RevId: 667fd04102a3934d53ded020da6d1bf68a1ca3e5
## What changed
- Add `ToolLifecycleContributor::on_mcp_tool_result` with access to the
executed MCP tool context, rewritten arguments, extension data stores, and
mutable server result.
- Run contributors before publishing MCP completion and before preparing the
result for the model, so extensions can inspect or replace successful and
error results.
## Testing
- Cover unchanged, replaced, and error results for direct MCP calls, plus
replaced and error results through Code Mode.
- Verify completion waits for result processing and the processed result flows
to both completion events and subsequent model input.
GitOrigin-RevId: ece7acfe9c5eed4778cb78a29c3ffd06a74e1bcf
## What changed
- Add optional Browser Use and Computer Use confirmation-policy Markdown to model catalog messages.
- Send the configured documents verbatim in `openai/confirmation_policies` metadata for `node_repl` and `cua_repl` tool calls. Send an empty object when the issuing model has no policies so runtime defaults are cleared.
- Use the issuing step's model snapshot across approval waits, and omit the metadata for other MCP servers and Guardian sessions.
## Testing
- Cover policy serialization, configuration overrides, model changes, approval waits, partial or empty policies, eligible server filtering, and Guardian exclusion.
GitOrigin-RevId: 038c4c262a31fc71986e4a2a947fe9bcbd407acc
## What changed
- Add optional `McpToolContext` metadata to `ToolStartInput`, exposing the
model-visible MCP tool details and its source classification without exposing
the executable client.
- Classify MCP calls as connectors, configured servers, plugin servers,
executor-selected plugins, or other registrations based on the prepared call.
- Prepare each MCP call before notifying tool lifecycle contributors and reuse
that same call for execution so the callback describes the call that runs.
## Testing
- Cover host-owned connector calls and extension-owned Apps server calls,
including their distinct provenance and executed tool names.
GitOrigin-RevId: efd23f511b1045ffdd96349d621ad62365569b2b
## What changed
- Add the originating Responses item ID to MCP tool request metadata as
`_meta.itemId`.
- Preserve the initiating `exec` item ID across code-mode cells so nested MCP
calls carry the same origin.
## Testing
- Cover metadata generation for direct and code-mode MCP tool calls.
GitOrigin-RevId: 1161cac64f1cc3a6d4dac4368e63804bd9d2c417
## Why
MCP tool calls can be issued by a model step whose settings differ from the
turn's initial settings. Request metadata must describe the issuing step.
## What changed
- Build MCP tool-call metadata from the captured `StepContext` model and its
effective reasoning effort.
- Populate `node_repl_disabled` from the issuing step while leaving turn-owned
Responses metadata unchanged.
- Apply the same step-scoped values to MCP requests emitted by stop hooks.
## Testing
Add coverage for configured and model-default reasoning effort, model changes,
Node REPL restrictions, and preservation of the original step and turn
metadata.
GitOrigin-RevId: f9cce52fbe559f15437bd19d699b657229c0d145
## Why
MCP servers attached to executor environments must retain their owner's
permission profile instead of inheriting the thread-wide sandbox authority.
## What changed
- Resolve and capture a permission profile for each enabled MCP server when
publishing the runtime, and reject calls or elicitations when that authority
is unavailable.
- Use the captured server profile for tool approval decisions, elicitation, and
sandbox metadata, including after runtime refreshes.
- Materialize `:workspace_roots` from `PathUri` values so permissions preserve
the path convention of remote executor environments.
- Give threadless app discovery and resource reads an explicit default
permission profile.
## Testing
Added coverage for per-server elicitation authority, unresolved attachments,
runtime refreshes, restricted tool calls, and foreign-platform workspace roots.
GitOrigin-RevId: 6b188d4b08b29e9971ff7aa68a7785a0cdf9e394
## Why
Thread settings can change while a turn is running, and delegated review or
compaction steps can select a different model. Each request needs a consistent
set of settings resolved against the model that will execute it.
## What changed
- Capture immutable resolved settings for each model step, including model
metadata, reasoning options, service tier, approvals, and personality.
- Keep in-flight steps on their captured settings while applying thread updates
to subsequent work.
- Resolve inherited reasoning summaries and filter service tiers against the
selected model and feature configuration for review and compaction steps.
## Testing
Added coverage for settings updates during paused turns, model changes,
previous-model compaction, review-model defaults, and service-tier filtering.
GitOrigin-RevId: fca4b3b305379f1bf26a5cac75ee0dd1747ac1f6
## What changed
- Add Windows sandbox mode, private-desktop behavior, and legacy Landlock selection to each `EnvironmentConfig`.
- Centralize sandbox context construction on `TurnEnvironment`, preserving environment-owned permissions, paths, and backend settings while applying additional permission grants.
- Use the environment-derived context for project instructions, capability discovery, file uploads, and filesystem-oriented tools.
## Testing
- Verify capability discovery uses the selected environment's permission profile and sandbox backends when they differ from the thread defaults.
GitOrigin-RevId: 7ae2fed90c8ada950f2e8431e571e9b2c793c291
## What changed
Propagate tool cancellation tokens into Guardian approval reviews so interrupting a tool also aborts its pending review. Apply the same cancellation behavior to server-initiated MCP approval elicitation.
## Testing
Add integration coverage for cancellation from direct tool calls, code-mode turns, background code-mode cells, and MCP elicitation.
GitOrigin-RevId: cbee4b422bbcbf6984e415ef6409cee705beebdc
## What changed
- Add `rejection_instructions` and `timeout_instructions` to catalog-provided auto-review messages.
- Use the acting model's instructions for denied and timed-out reviews across tool approvals, shell escalation, and MCP elicitation responses.
- Fall back to the existing instructions only when a catalog value is absent, while preserving explicit empty-string overrides.
## Testing
- Cover catalog overrides, legacy fallbacks, empty values, and separation between acting-model and reviewer-model messages.
GitOrigin-RevId: c5b2c2dbdaefd45d1d658651dd1abaeb6d8c93da
## 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
## What changed
- Give approval review contributors the first opportunity to resolve an action when automatic review is not required for the model.
- Return an extension's decision directly and fall back to Guardian when no extension claims the review.
- Update Guardian V2 to approve actions below its risk threshold through the review contributor API, and remove the extension approval-policy API.
## Testing
- Verify that an extension approval bypasses both the Guardian model call and the user approval prompt.
- Cover Guardian V2 review decisions for low-risk, high-risk, and disabled threads.
GitOrigin-RevId: 5be56941143aff6f358b75b5f8101b7c047147ae
## What changed
- Add a thread-scoped extension API for requesting automatic review, resolving
multiple contributors to the strongest requirement.
- Have Guardian v2 request automatic review when it is enabled and the latest
`action_risk` score is at least `0.8`.
- Honor extension review requirements across tool approvals, MCP elicitation,
and remote execution while preserving host configuration and managed-policy
constraints.
## Testing
- Cover contributor registration and requirement resolution.
- Verify Guardian v2 requests review at the threshold, returns to the default
below it, and does not affect threads where the extension is disabled.
- Exercise extension-requested strict review with a remote model override.
GitOrigin-RevId: 6329fc23585d5cc7173c39bb9952c3109ec3884b
jif