## Why
Model catalog description overrides only covered `spawn_agent`, leaving the other multi-agent V2 tools with fixed descriptions.
## What changed
Extend `model_messages.tools.multi_agent` description overrides to `send_message`, `followup_task`, `wait_agent`, `interrupt_agent`, and `list_agents`. Resolve each override by tool name across namespaced, plain, and Code Mode exposure.
Missing or null descriptions retain bundled text; empty strings suppress static text without disabling tools. Preserve `spawn_agent` runtime guidance, tool schemas, and execution behavior. Descriptions follow mid-turn model changes.
## Testing
Expand integration coverage to all six tools, including missing, null, empty, and sparse overrides; plain, namespaced, and Code Mode exposure; unchanged V1 behavior; and mid-turn model changes.
GitOrigin-RevId: a2c47eb8efb28c3eeebcc6482e36c188c38a6dd1
## What changed
- Accept `windows.sandbox = "mxc"` and preserve the selected backend through environment configuration, command execution, patch writes, and sandbox metadata.
- Treat MXC as enabled in the TUI and report Windows sandbox readiness as `ready`, avoiding legacy setup prompts.
- Keep `allowed_sandbox_implementations` scoped to the legacy elevated and unelevated backends without restricting MXC.
- Default `windows.sandbox_private_desktop` to `false` for MXC while retaining `true` for legacy sandboxes.
## Testing
Add coverage for MXC configuration precedence, legacy requirement handling, sandbox selection, and TUI state. Add a Wine integration test that verifies command and patch routing fails when native MXC is unavailable and reports `windows_mxc` in turn metadata.
GitOrigin-RevId: e2162447d0750f60753864c92a20e02a7f297bca
## Why
Image preparation replaces uploaded images with file references in model history, but user message events still retain the original local paths or inline image URLs. Live and persisted display history should carry the prepared file IDs as well.
## What changed
- Prepare images before emitting user message events, and copy uploaded file IDs into the corresponding user inputs.
- Track original input positions through content expansion so failed image reads, omitted inputs, and duplicate URLs do not misassociate images.
- Preserve text spans, image detail settings, and inputs without a prepared file reference.
## Testing
Add a protocol test for image position mapping and an integration test covering file IDs in model requests, live user message events, and persisted display history, including failed images and duplicate URLs.
GitOrigin-RevId: 55e7ab97925b5db049c5c2403d90349635eee740
## Why
An explicit `service_tier = "flex"` could be dropped when fast mode was disabled or the model catalog did not advertise Flex, even though Flex is an API request option.
## What changed
- Preserve configured `flex` through core session settings, TUI tier resolution, and request construction regardless of fast-mode or catalog support.
- Omit `service_tier` from Amazon Bedrock requests, including with custom catalogs, because Bedrock only supports the implicit default tier.
## Testing
Add regression coverage for Flex configured at startup or through thread settings, connected thread startup, and TUI turn submission. Update review coverage to expect Flex with fast mode disabled, and verify that both Bedrock providers omit `service_tier`.
GitOrigin-RevId: 98f2761bdd780603839ebfec75cb983a5d55e554
## What changed
Read the static V2 `spawn_agent` description from `model_messages.tools.multi_agent.spawn_agent.description`, independently of the runtime tool namespace. Missing or null values retain the bundled description; an empty string suppresses it.
Preserve generated model guidance, local usage hints, and tool parameters when applying an override. Resolve the description from the active model so it follows mid-turn model changes.
## Testing
Add coverage for sparse and empty catalog values, preservation of generated context and outbound tool schemas, and description updates after mid-turn model changes.
GitOrigin-RevId: 96cfa180f8f374dc868e4fabc337e49380e405da
## Why
Filesystem reads previously required a sandbox whenever writes were restricted, even with full-disk read permission. This made permitted reads depend on sandbox availability.
## What changed
- Select sandboxing independently for reads and writes, allowing full-disk reads directly while keeping restricted operations sandboxed.
- Use the executor's path convention when evaluating full-disk access, including `:slash_tmp` denials.
- Apply read-specific checks to capability discovery and skill resource reads, allowing unrestricted reads on executors without sandboxed discovery support.
## Testing
Add regression tests for direct read APIs, restricted writes and reads, executor-specific permission rules, and capability discovery without sandbox support. Update Windows tests to verify sandbox enforcement through writes.
GitOrigin-RevId: a03844bd1f0ea583bb54326683cddbfdd050119f
## Why
Code Mode cells that finish without invoking tools omit completeness metadata, leaving a verified empty inventory indistinguishable from an unverified one.
## What changed
- Retain completed, losslessly recorded cells even when they contain no tool calls.
- Always include `executed_tool_calls` when setting `tool_calls_complete`, using `[]` for empty inventories or terminal waits with no new calls.
- Preserve completeness across request retries while revalidating history and rejecting late calls or ambiguous output mappings.
## Testing
Add regression coverage for empty tool discovery, errors, termination, feature gating, retries, and fresh-session requirements for waits. Update protocol assertions to require an explicit empty call list with completeness metadata.
GitOrigin-RevId: 24affe47f46068b6559d04a0103958ae83a00b92
## 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
## What changed
Capture result metadata for host-owned app calls when analytics and executed tool call metadata recording are enabled. Respect both `analytics.enabled = false` and host-disabled analytics, using the prepared call's ownership to determine eligibility.
Disable incremental WebSocket request reuse when raw result metadata or its call binding changes, so late results attached to an already-sent output are included in the next request. Continue allowing reuse when only other metadata changes or result metadata is filtered out for the endpoint.
## Testing
Extend coverage for direct and code-mode calls, analytics settings and host overrides, runtime recording changes, and prepared call ownership. Add metadata comparison and WebSocket reuse tests, and verify that raw response item notifications continue to omit result metadata.
GitOrigin-RevId: 411843fbff3749ee96fd6f0ebc591362942a4555
## What changed
- Extend `GuardianModelPolicy` with controls for uncategorized tools, unscored actions, the initial computer-use call allowance, and sandboxed command coverage.
- Add `GuardianPolicyLoader` in `codex-config` to translate legacy settings, preserve catalog policy precedence, and enforce reviewer requirements. Apply live model review requirements through `ConfigRequirements::constrain_guardian_policy`.
- Use the shared model policy for Guardian scoring and approval, replacing the extension-local policy wrapper while retaining legacy defaults.
## Testing
Add configuration tests for catalog precedence, legacy scope fallback, required-model constraints, and legacy computer-use opt-in and feature gating. Adapt existing extension tests to consume the shared policy.
GitOrigin-RevId: 6fed1c3a831964ad28ea7de5cb19e74e323c1204
## Why
Code Mode wrappers should preserve cached scores for nested actions so adaptive review can reuse them across cells.
## What changed
Remove `code_mode` from `GuardianModelPolicy` and its approval scopes. Skip scoring and cache invalidation for direct Code Mode `exec` wrappers under model policies, leaving nested tools governed by their own categories. Preserve legacy wrapper scoring behavior.
## Testing
Expand app-server coverage for score reuse across cells, synchronous nested reviews, required model policies, and legacy configurations. Retain checks that ordinary tools named `exec` or MCP tools named `wait` invalidate cached scores.
GitOrigin-RevId: 7a0692e5330f3d4b4bda988ecbe7061bc8b2318c
## Why
Executor profile roots can use path conventions that are not native to the current host. Converting them to host paths during configuration or turn reconstruction can reject or drop those roots, while case-insensitive comparison can hide Windows path spelling changes.
## What changed
- Store profile roots as URI-backed `ProfileWorkspaceRoot` values throughout permission snapshots and thread settings, preserving spelling in equality and deduplication.
- Keep effective workspace roots as `PathUri` values for permission materialization and status summaries. Convert Windows sandbox root hints to native paths only at native Windows sandbox boundaries, rejecting incompatible roots.
- Omit the legacy rollout `workspace_roots` field when profile roots cannot be represented as host paths, retaining the compiled permission profile.
## Testing
Add regression coverage for Windows and UNC root spelling changes, settings restoration and turn recording with foreign roots, executor-root status display, and backend-specific Windows root conversion.
GitOrigin-RevId: 903c068fd74959bdd10e7cb1141aa42b953a59a4
## Why
Daemon recovery reloads threads but leaves interrupted work unfinished. Resume eligible work automatically from the saved conversation, even without a connected client.
## What changed
- Attempt one new continuation turn immediately after restoration, including in Plan mode. Mark the old turn interrupted and supply recovery context without creating a user message or granting new authorization.
- Require an idle thread, matching permissions, and the same single local environment configured by the thread. Skip completed, aborted, or superseded work and snapshots without environment identity.
- Add `continue_turn_if_idle` with an atomic previous-turn check so newer tasks or standalone settings changes invalidate pending continuation.
- Preserve the output schema, service tier, and root turn ID, and emit a “Resuming interrupted work” warning when continuation starts.
## Testing
Add daemon restart coverage for continuation without a client, Plan mode, permission and environment mismatches, and legacy snapshots. Add core coverage for preserved continuation metadata, absence of user-message events, rejection of superseded continuations, and exclusion of remote execution from recovery snapshots.
GitOrigin-RevId: 2b290b75d9399fc58258bcda2e85c74e9b5b3b09
## What changed
- Accept and ignore `features.personality` in user configuration, profiles, and managed requirements.
- Remove feature gating from `personality = "none"`, which strips the literal `# Personality` section when preparing model catalog instructions. Preserve explicit base instructions and existing thread instructions.
- Document deprecated personality fields in configuration, app-server schemas, and the Python SDK: `friendly` and `pragmatic` no longer select a style, and `supportsPersonality` is always `false`.
## Testing
Add regression coverage for ignored legacy flag values and managed requirements, personality opt-out behavior with the flag absent or set to either value, role overrides, and preservation of explicit base instructions, including empty strings.
GitOrigin-RevId: 4e12c66b42bfc59d6f151a5b3c28fadc6654ae99
## 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
- Accept `fileId` alongside the existing `url` form for app-server image inputs, and forward file references to the Responses API as `file_id`. Update generated schemas and client types.
- Preserve file references, image detail hints, and mixed inline/file image ordering through user-message events, thread history, and rollout migration. Retain file images when truncating tool output.
- Pass file references through image preparation without resolving them, while keeping resize-notice numbering correct. Omit them from unsupported TUI display and Guardian image context.
- Reject image-edit requests whose recent-image window includes a file reference, preventing selection of an older inline image instead.
## Testing
Add coverage for serialization, request and rollout preservation, mixed-image history ordering, incomplete ordering metadata, tool-output truncation, and rejection of unsupported image-edit selections.
GitOrigin-RevId: 6ca20a8577155cc934b720803c3b7b3bffdf972a
## Why
MXC is a sandbox implementation, not a restricted-token sandbox level. Executor requests need to represent that choice separately from `WindowsSandboxLevel`.
## What changed
- Introduce `WindowsSandboxSelection` for executor sandbox contexts and remove `Mxc` from `WindowsSandboxLevel`.
- Preserve the `windowsSandboxLevel` wire field and its serialized values for compatibility.
- Share sandbox selection between executor process launches and filesystem helpers, and use the new selection in capability discovery and skill reads.
- Disable Windows sandbox selection for executor paths that do not use Windows path conventions.
## Testing
Extend coverage for MXC wire serialization, Windows skill-read sandbox checks, and capability discovery with distinct permissions. Exercise remote filesystem write restrictions with both restricted-token and MXC sandboxes, including rejection when native MXC is unavailable.
GitOrigin-RevId: 266211377bcb138a0dc75861e9ff2225fa37a53d
## What changed
Represent images in `ContentItem` and `FunctionCallOutputContentItem` with `ImageReference::Inline`, flattened to preserve the existing `image_url` wire format. Update image producers and consumers and regenerate app-server schemas and SDK artifacts.
Preserve the Python SDK's `InputImageContentItem` and `InputImageFunctionCallOutputContentItem` class names during generation.
## Testing
Add a regression test for stable Python image class names and adapt existing image tests to the shared representation.
GitOrigin-RevId: c38a780ac3314c2ac2deb3afc1b93b94b6f93fec
## Why
Command execution and plugin measurement events lack model and reasoning-effort labels. Attribution needs to reflect the step that invoked the command, even when model settings change before a background process finishes.
## What changed
- Add `model_slug` and `reasoning_effort` to command execution and plugin measurement analytics.
- Capture model context from resolved step settings and carry it through execution, approval, Guardian review, and plugin metrics collection.
- Preserve the first command-start model context when subsequent start notifications arrive.
- Keep the carried context out of serialized protocol items and generated schemas.
## Testing
Extend analytics tests to cover model switches before invocation and during background execution, default reasoning effort, Guardian-denied commands, and repeated start notifications retaining the original model context.
GitOrigin-RevId: af90e1c0d39bab625f2e89786085b61a9b96c0ce
## Why
Direct tool-call records need to stay associated with the invocation that produced each output, including when call IDs are reused. Completeness must describe the recorded call inventory, independently of tool success.
## What changed
- Attach direct-call records to outputs before they enter history, and set `tool_calls_complete` when the invocation's arguments are fully recorded.
- Bound pending recordings and retained metadata, release reservations on completion or cancellation, and invalidate pending records when capture is disabled.
- Apply request budgets to direct metadata and strip it from inference and compaction inputs when capture is disabled.
- Remove executed-call metadata from app-server raw response notifications and exclude its size from Guardian history retention budgets.
- Track call IDs that bypass dispatch so their reuse cannot incorrectly establish Code Mode completeness.
## Testing
Add regression coverage for direct-call attribution, malformed calls, metadata budgets, cancellation, configuration changes, compaction, notification filtering, and Guardian context isolation.
GitOrigin-RevId: 2ebd39c7f141d04788736491495109841656b4c0
## What changed
- Add explicit MXC backend selection and carry its identity through exec-server process reporting and sandbox violation classification.
- Launch MXC through the Codex executable with the effective permission profile and command environment.
- Reject exec-server MXC requests when native MXC is unavailable or when they request a TTY, an `arg0` override, or managed networking. Reject private desktop isolation during MXC preparation.
- Allow an explicitly empty child environment and avoid exposing request payload values in launcher decode errors.
## Testing
Add coverage for sandbox selection and unsupported-request rejection, plus Windows RPC tests for stdin writes and temporary-directory permissions derived from the command environment. Native MXC tests skip when MXC is unavailable.
GitOrigin-RevId: 3626ff0f9ad7f9b812ce09b68c31ea9a5a9c72b1
## What changed
- Use literal model instruction templates and the standard fallback prompt, ignoring legacy personality variables. Retain catalog decoding compatibility and report `supports_personality` as `false` for generated model presets.
- Stop emitting `<personality_spec>` developer messages and assigning an implicit Pragmatic configuration default.
- Filter Friendly/Pragmatic overrides from TUI requests while preserving explicit `personality = "none"`. With `features.personality` enabled, this opt-out still strips the model's personality section.
- Refresh inherited model instructions for agent roles only when the personality opt-out changes, preserving custom instructions.
## Testing
Update coverage for literal legacy templates, deprecated overrides on turn start and resume, role instruction refresh, and forwarding the explicit opt-out through thread start, resume, and fork requests.
GitOrigin-RevId: 1391db4e565e010569f0885f80013d1f86b45825
## What changed
Remove `thread/rollback`, its request and response types, generated bindings, and the core `Op::ThreadRollback` operation. Requests now follow the generic unknown-method rejection path. Document `thread/revert` as the alternative for paginated threads.
Keep historical `ThreadRolledBack` markers and legacy error deserialization so existing rollouts remain compatible with replay and migration.
## Testing
Adapt retained-context and Guardian history tests to append legacy rollback markers and resume threads, preserving coverage of surviving instructions, answers, and review history.
GitOrigin-RevId: b3da1becdf86b1869275aacb0ffc2817cee5af2e
## What changed
Carry optional `available_access_programs` metadata through model information, presets, caches, and the TUI, and expose it as `availableAccessPrograms` in app-server `model/list` responses. Update the generated JSON schemas, TypeScript types, and Python models.
Preserve the distinction between missing metadata and an empty `cyber` list. Ignore unknown cyber program names when reading the catalog so new server programs do not prevent older clients from loading it. Discovery metadata does not grant access; inference still enforces authorization.
## Testing
Add coverage for absent, null, empty, and populated metadata, unknown program names, and app-server serialization. Extend cache tests and verify that online refreshes persist changed access metadata even when the catalog ETag stays unchanged.
GitOrigin-RevId: b3ef5805c1c61b8d64b9b896c9c0a79120143667
## 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
## Why
Permission paths need to follow the execution host's path conventions and home directory. Literal directory names containing glob syntax must not change the meaning of deny patterns, and profile availability checks need to account for configured workspace roots.
## What changed
- Use `ConfigPathContext` to compile built-in and custom profiles, returning the resolved profile and deduplicated `PathUri` workspace roots. Materialize configured roots while retaining runtime workspace symbols.
- Use the same compiler for configuration loading, persisted profile validation, and profile catalogs. Resolve roots against the requested `cwd` when listing profiles.
- Resolve home-relative scoped rules using the supplied home directory and reject unsafe directory prefixes when constructing globs.
- Share workspace-root materialization across native paths and URIs. Deny the affected root when a workspace glob cannot be safely resolved, and clear grants for legacy home-relative workspace denials whose target is unknown.
## Testing
Add coverage for POSIX, Windows, and UNC path resolution, inherited workspace roots, scoped home denials, missing home context, and conservative denial behavior for unsafe globs. Add an app-server test verifying that profile availability reflects the requested `cwd`.
GitOrigin-RevId: ca259434742365c16d0b72629cabfbab41513a80
## Why
Persisted turn-start events lack the originating root turn ID, so they cannot directly associate child turns with the root turn that initiated them.
## What changed
- Add optional `root_turn_id` to `TurnStartedEvent`. Use the inherited root turn ID when available, otherwise the turn's own ID.
- Centralize turn-start emission for regular turns, shell commands, and manual compaction so they record attribution consistently.
- Carry attribution into `ThreadHistoryTurnChange` when processing turn-start events and retain it through completion in the history builder.
- Keep older records compatible by defaulting missing attribution to `None`.
## Testing
Add coverage for root and child turn attribution, persistence when tool collisions fail a turn before sampling, history change propagation, and deserialization of older turn-start records.
GitOrigin-RevId: 54a80b828ca7d1c4c19f13d468c01d052e1b9130
## Why
Reused call IDs, ambiguous exec/wait associations, and missing history can make tool-call completeness claims unreliable. Truncating one cell's recorded calls should also preserve completeness for unrelated cells.
## What changed
- Track observed call and runtime cell IDs with bounded memory, including call IDs from initial history, and withhold completeness when evidence is missing or ambiguous.
- Validate exec/wait input-output associations and keep invalidated completeness from returning on retries. Withhold wait completeness after resume or fork, where runtime cell IDs can be reused.
- Keep truncation markers and omission counts local to each output, clearing completeness across the affected cell while preserving unrelated cells within the metadata budget.
- Refresh recording enablement from runtime configuration without changing execution features, and preserve the live recorder during legacy configuration reloads.
## Testing
Add regression coverage for reused IDs, compaction, resumed waits, mismatched wrappers, runtime recording changes, and metadata budgeting that preserves unrelated complete calls.
GitOrigin-RevId: 0bc85964bee079879620ec0664eea530a13b61fb
## What changed
- Add host-recorded `tool_result_metadata` snapshots with size limits, redacted debug output, and protection against deserialization from untrusted input. MCP capture remains disabled.
- Preserve accepted metadata across retries and delayed Code Mode results. Shed raw metadata before source evidence, calls, or completion markers when the request budget is exceeded.
- Send raw metadata only to allowed OpenAI and ChatGPT HTTPS endpoints, filtering by the resolved destination for HTTP and WebSocket requests.
- Encode source parse failures as an array entry with type `parse_failed` and an empty ID.
## Testing
Add coverage for metadata bounds and redaction, retained-call updates, budget shedding, disabled MCP capture, and HTTP/WebSocket destination filtering.
GitOrigin-RevId: b1a396323ad0623167cdd9e20ff9453f0d01bbf7
## What changed
- Add `disabled_plugin_ids` to thread startup options, settings overrides, snapshots, and persisted turn contexts. Omitted overrides preserve the current list; an empty list clears it.
- Restore the selection on resume and capture it before truncating history for a fork. Prefer the owning thread's latest settings snapshot, falling back only to the latest turn context so stale history cannot resurrect an older selection.
- Freeze the selection at turn admission and retain compatibility with histories that lack the new fields.
## Testing
Add coverage for owned settings, explicit clears, latest-turn fallback, and legacy snapshots. Extend settings tests to cover plugin selection during runtime restoration and compaction, and verify initial turn persistence without extra settings checkpoints in both history modes.
GitOrigin-RevId: 75ffbff5763cd93cc5ac69d73b08b237f59bc009
## What changed
Replace straight apostrophes with curly apostrophes in usage-limit and high-demand error messages, and update usage-limit test expectations. Document that the context-window error's ASCII prefix is matched by the iOS input-limit classifier.
GitOrigin-RevId: 93484aaf805b9e6f8785fd1b43fe6ff9f1a13efa
## Why
Hosts need to stop new turn-input work during shutdown without consuming pending input or preventing already-running delegated work from finishing.
## What changed
- Add an optional `TurnStartAdmission` extension gate, checked before reserving or starting a new turn. Hosts without a gate retain existing behavior.
- Return `NotSubmittedReason::ServerDraining` for refused starts and surface an app-server error instructing clients to reconnect and retry.
- Keep steering, parent-delegated subagent input, and memory-only mailbox wakeups available during drain, while gating automatic starts.
- Close realtime conversations with an ordered handoff, error, and close event sequence when a handoff is refused during drain.
## Testing
Add regression coverage for rejected input staying out of subsequent requests, persisted queue items remaining available for later starts, delegated agent and review work completing during drain, mailbox wakeups, and realtime handoff error ordering.
GitOrigin-RevId: 03dbdcd71eab200e597c0649e6eb39bd92dbc82f
## Why
Filesystem policies for remote execution need to interpret paths, home directories, and temporary directories using the execution host's context.
## What changed
- Add context-based read-denial matching, read-access checks, glob resolution, and `PathUri` workspace-write constructors without consulting local paths or environment variables.
- Share managed read-denial validation through `DenyReadValidator` and use it in core configuration, preserving required-entry checks, concrete grant validation, and constraint diagnostics.
- Reject invalid or unresolvable denial paths when constructing a context-based matcher, and apply `/tmp` denials according to the execution host's path convention.
- Preserve workspace-root symbols and protected metadata entries when materializing URI-based writable roots.
## Testing
Add regression tests for POSIX, Windows, and UNC path matching; conflicting read and write grants; malformed or unresolvable denials; `/tmp` handling; and workspace metadata protection.
GitOrigin-RevId: aa2b174288d1172ab52ff485f58d306236d27652
Move lexical scan-bound calculation into `codex_protocol::permissions` and
expose `windows_deny_read_glob_scan` with its `WindowsDenyReadGlobScan` result.
Have the Windows sandbox resolver use the shared helper, preserving literal
scan roots, glob suffixes, and traversal depth limits without filesystem access
in the planner.
GitOrigin-RevId: 748a12b45f89c6e045e9123c055453ec39c202b1
## Why
Resuming a thread should retain its selected workspace folders, including additional roots and explicit empty selections. Resume overrides also need to survive a subsequent resume when no turn has run.
## What changed
- Persist `runtime_workspace_roots` in startup metadata and thread settings snapshots, separately from explicit environment selections and permission-profile roots.
- Restore roots from the latest snapshot owned by the resumed thread, falling back to owned startup metadata only when no snapshot exists. Honor explicit `runtimeWorkspaceRoots` overrides, retarget the old `cwd` root when `cwd` changes, deduplicate roots, and validate restored paths for the current host.
- Checkpoint effective settings on resume and restored settings after revert. Reload resume configuration if saved workspace roots change during loading.
- Normalize Windows rollout path spellings when matching thread search results, preserving selection of the correct rollout after revert, including compressed rollouts.
## Testing
Add regression coverage for workspace restoration, empty and explicit overrides, foreign paths, compaction and revert, resume checkpoints without recency changes, concurrent settings persistence, and rollout search path matching.
GitOrigin-RevId: d98d9d34dd63934d441120916c61c12b69e7f062
## What changed
- Add `memories.version` with `v1` as the default and `v2` as an opt-in selection.
- Route memory generation, summaries, and retrieval tools through the selected version. Store `v2` artifacts in `memories_v2` and lazily create a separate SQLite database, keeping jobs and outputs isolated while sharing the thread catalog.
- Preserve the initial memory version across extension config updates so summaries and retrieval tools use the same namespace.
- Clear both versions on memory reset and remove thread memory from both stores on thread deletion. Recognize both artifact roots in shell usage telemetry.
## Testing
Add regression coverage for version defaults and validation, independent job claims and outputs, deletion and reset across versions, and shell usage classification for both memory roots.
GitOrigin-RevId: aa799bf87ab6ec10c8f5668213931e57547d080b
## What changed
- Let approval extensions choose between cached approval, synchronous review, and a user prompt for tool and permission requests, while core enforces mandatory Guardian and fresh-review requirements.
- Carry an optional `review_reason` on Guardian assessment events and use it to trigger strict-review notifications, retaining the fallback for older events.
- Require synchronous review when cached evidence has an unusable encrypted parent compaction.
## Testing
Add regression coverage for manual prompts and cached approvals with non-UTF-8 working directories. Update approval contributors in existing tests to use the decision API.
GitOrigin-RevId: a4e66416070bdaa881daa41429c49021629f44c1
## Why
Device-authenticated verification needs an app response outside automated approval and review. Previously, MCP user-verification requests were always cancelled.
## What changed
- Add typed `openai/userVerification` elicitations carrying a title, description, and challenge through core and app-server.
- Route verification to one connection enabled by trusted host activation. Restrict responses to that owner, exclude requests from replay, and cancel on disconnect or authentication changes, including account switches away and back.
- Return proofs in `content`, discard response metadata, and cancel malformed acceptances. Suppress verification response logging and analytics, and send only a generic verification notice to realtime.
- Keep the mode experimental and exclude it from stable schema exports. Capability advertisement remains disabled, and the TUI cancels verification requests.
## Testing
Add coverage for owner isolation, disconnect and authentication races, proof response handling, automated-review bypass, inactive-host cancellation, stable schema filtering, and realtime payload exclusion. Update the MCP integration test to verify that an activated request holds the tool until the client responds.
GitOrigin-RevId: c8c7b6691a3f7756682bbcca9def1df0d1feb906
## Why
Experimental context activation previously checked the provider and account eligibility without checking model support. Child sessions also inherited token-budget activation from their parent, even when starting fresh with a different model.
## What changed
- Add `ModelInfo.supports_experimental_context`, defaulting to `false`, and enable it for the bundled `gpt-6-astra` model. Require this capability when activating experimental context.
- Snapshot configured token-budget preferences before startup activation. Restore them for fresh child sessions before applying their starting model's defaults, while history forks retain their parent's activation.
- Pass unresolved token-budget preferences to child sessions so they can use their own model's prompts.
## Testing
Extend coverage for unsupported models, model-switch guidance under explicit and experimental activation, and child configuration from both active and inactive parents. Verify that omitted capability metadata defaults to `false`.
GitOrigin-RevId: 02df9e171682267232fa923d5ea3f7af36527808
## What changed
Add the disabled-by-default `reasoning_effort_override` feature for OpenAI models with `use_responses_lite` enabled. Append a trusted `configuration_update` after accepted input when no effort is established in surviving history or the resolved effort changes. Preserve the existing history prefix and continue sending the request-level reasoning effort.
Share effort normalization through `ModelInfo::resolve_reasoning_effort` so requests and history updates resolve `ultra` consistently and translate `persistent` to `disabled`. Exclude other custom effort values from history updates, and compare only against harness-authored configuration items.
## Testing
Add integration coverage for effort transitions, deduplication, history prefix and cache-key preservation, alias normalization, and feature/provider/model gating. Add unit coverage for model-specific `ultra` resolution, fallbacks, and `persistent` translation.
GitOrigin-RevId: c3fe7050058076454d8ea20054a618bca9d48c7c
## What changed
Capture the ID from `response.created` and pass it as `parent_response_id` in Guardian review and classifier request metadata. Clear the current response ID before sampling retries so tool reviews cannot inherit a failed response's ID.
Request Guardian credits with `guardian_credits_requested` on eligible parent requests. Remove the ticket protocol, transport attachment, and ticket-specific body redaction. Keep ordinary app-server client `parent_response_id` values inside `x-codex-turn-metadata` rather than promoting them to Guardian request metadata.
## Testing
Update coverage for HTTP fallback, WebSocket review reuse, missing response IDs, classifier transport retries, and code-mode yield/resume attribution. Extend app-server tests to verify client metadata placement over HTTP and WebSocket.
GitOrigin-RevId: c1665e56382ecec8d260fc2ca0ecd5e20b0b2391
## Why
Preparing a filesystem sandbox could synchronously probe unrelated permission
roots on the executor runtime thread and repeatedly resolve the same filesystem
aliases while deriving writable roots.
## What changed
- On Linux, leave permission-root alias resolution to the sandbox helper.
- Filter effective permission entries once and cache their resolved paths for
writable-root and read-only carveout construction.
- Return early when the policy has no effective writable entries.
GitOrigin-RevId: 305364173ca55f967c1701aad94d2374f78999d3
## Why
Guardian approval actions can contain paths from a remote executor whose path convention differs from the host, such as Windows paths reviewed on a POSIX host. Converting those paths to host-native absolute paths prevents the action from being reviewed.
## What changed
- Render command working directories using the executor's reported path convention, and preserve URI-backed paths for attribution.
- Carry foreign command and patch paths through Guardian events and app-server schemas as legacy path strings.
- Bound remote plugin attribution within the overall review deadline and reject Guardian action payloads that exceed the review byte limit.
## Testing
- Cover Windows and POSIX executor path rendering, foreign patch paths, protocol round trips, oversized payload rejection, and remote Guardian review context.
GitOrigin-RevId: 38be0fcdac897139519e74e077eb5cb4f8f8017e
## What changed
- Extend `ApprovalReviewContributor` with a `decide` hook that can allow an
action, return a synchronous review result, or hand the request to the user.
- Pass contributors the request's approval state and a callback bound to the
existing synchronous reviewer. Review results satisfy the review gate while
the host continues to enforce permissions.
- Add structured reasons for requesting a fresh Guardian review and select the
first contributor decision in registration order.
GitOrigin-RevId: ec84474b3fcbcf1027c8502aa1c2947c10149f9d
## What changed
- Request and parse server-issued Guardian tickets for eligible Codex backend responses.
- Scope each ticket to the response that produced a Guardian review or classifier request, including HTTP and WebSocket retries, without adding it to model-visible or persisted context.
- Validate ticket shape, reserve its metadata keys, redact it from debug and request-body logging, and attach it only at the Guardian transport boundary.
## Testing
- Cover ticket parsing, endpoint and authentication routing, retry scoping, classifier retries, and redaction for compressed and uncompressed requests.
GitOrigin-RevId: 6219dd15c9f19ed3387de516aac1b8e7c9cdb0e3
## What changed
- Add optional per-model Guardian modes for computer use, shell, code mode,
file changes, MCP, network, and permission requests.
- Apply disabled, synchronous, or adaptive review by action category while
preserving legacy configuration when model policy is absent.
- Bind cached risk scores to the active model policy, thread settings, and
environment selections so outdated scores cannot approve later actions.
- Keep unknown review modes on the synchronous path and ignore unknown policy
fields for forward compatibility.
## Testing
- Cover policy serialization, legacy fallback, scoped tool classification,
disabled categories, and score invalidation after policy changes.
GitOrigin-RevId: f334a5f4fffb198da66cde3a400233e0df650516
## What changed
- Pass the selected executor's `PathUri` through user command approval requests instead of converting the working directory to a host-native path.
- Make native-path permission helpers explicitly local and require executor-aware permission transforms to receive a `FileSystemSandboxPolicyContext`.
- Cover approved remote commands to verify that the approval request reports the selected remote working directory and execution resumes after approval.
GitOrigin-RevId: 0aa3042f2d7594af6c7d0abf31d7f99cf67d5556
## Why
Patch targets can use a different path convention from the Codex host, so
host-native path conversion can misclassify writable roots and requested
permissions.
## What changed
- Evaluate patch targets as `PathUri` values with the active filesystem policy
context, including workspace roots and the executor's path convention.
- Distinguish executor-managed sandboxing from local platform sandboxing when
deciding whether a patch can be auto-approved and how to normalize additional
write permissions.
- Make full-disk and special-path policy checks honor the selected executor's
Windows or POSIX convention.
## Testing
Add coverage for Windows executor URIs, full-disk policy aliases, remote patch
permission requests, sandbox availability, and owner-provided workspace roots.
GitOrigin-RevId: 1a054ea443efd342623c67432762f85c53d20c15
## Why
When ordinary included usage is exhausted, eligible users need a way to keep working with the backend-provided Luna Reserve quota and return to their previous model once ordinary usage recovers.
## What changed
- Automatically switch eligible TUI tasks to Luna Reserve after an authoritative account usage read, preserving the prior model and reasoning effort per task.
- Restrict model selection while on Reserve to its supported reasoning levels, keep queued turns on the accepted model, and restore the saved model after a fresh read confirms recovery.
- Surface Reserve usage in the composer and `/status`, and expose `normalModelSlug` in app-server rate-limit snapshots so clients can use the associated model's display metadata without changing the request model.
- Poll account limits more frequently near exhaustion and retain compatibility with app servers that only accept the legacy null request parameters.
## Testing
- Added coverage for Reserve entry, queued-turn handling, task reconstruction, recovery authorization, account changes, model selection, usage rendering, and banner dismissal.
GitOrigin-RevId: 46a435e9531051f8cec3f6a46c4b9f7cfa479747
