## 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
Add an optional `protocol_mode` to `McpServerContribution::HostedApps` and apply it when registering the server. Preserve the hosted Apps default when no override is provided.
## Testing
Add an integration test that selects MCP `2026-07-28` with the global feature disabled and completes a native user verification flow, including resuming the tool call with the verification response. Extend capability tests to confirm that the override preserves hosted Apps user verification without granting it to ordinary extension registrations.
GitOrigin-RevId: e8662c45f964c00b0bb4503bbcfd8432d7e2fa70
## 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
Add `codex_history::CompactionCheckpoint` to keep a checkpoint and its recorded producer model hash together, with shared checks for usability and reviewer compatibility.
Replace `ConversationHistorySnapshot::latest_compaction_model_hash()` with `latest_compaction()` and use the shared abstraction in Guardian context selection, review sessions, and parent compaction reuse. Preserve selection of the latest checkpoint even when unusable, and leave missing producer metadata unknown.
## Testing
Add coverage showing that the latest checkpoint retains its own provenance even with missing or empty encrypted content, and that compatibility requires matching producer and reviewer hashes. Adapt existing history, migration, and parent compaction tests to the new API.
GitOrigin-RevId: 98e794644edf979c98fcc8294baa48ff82ea0ed0
## Why
With `NonfatalClockReadErrors` enabled, a clock failure after a successful read could be suppressed if an earlier failure had already been reported in the same turn and context window. This left the model without a fresh notice that the clock was unavailable again.
## What changed
Clear `last_clock_failure` after a successful clock read so a subsequent outage produces a new notice while consecutive failures remain deduplicated.
## Testing
Add a regression test that scripts two failures, a successful read, and another failure within one turn. It verifies that the consecutive failures share one notice, recovery delivers a time reminder, and the later failure adds a new notice.
GitOrigin-RevId: f2a9c4d7b63f2e8408a47b1803b0bc4577f23f32
## Why
An omitted controller socket policy was treated as an explicit denial, preventing execution environments from supplying their own Unix socket grants.
## What changed
- Preserve omission of `dangerously_allow_all_unix_sockets` separately from `false`, and retain explicitly empty `unix_sockets` maps.
- Defer to attachment socket permissions when the controller supplies neither setting. Continue enforcing explicit restrictions, socket denials, and managed requirements.
- Resolve omitted values to `false` for ordinary execution and remote configuration, preserving the default for commands without attachment grants.
- Add debug logging for effective environment and remote execution network policies.
## Testing
Add regression coverage for omitted, explicit, finite, empty, and managed socket policies through remote launch configuration, including live policy replacement and serialization round trips. Adjust remote environment tests to tolerate child-completion ordering and box large cold-resume test futures to reduce Windows stack usage.
GitOrigin-RevId: 98a88d01cbb91aea1faaa03b3c414ef3be7af398
## What changed
Move duplicated action preparation into `codex_guardian_context::action_for_review`, shared by approval rendering and cached-evidence size checks. Preserve the existing behavior: omit top-level `tool_description` and `connector_description` metadata from MCP tool calls while keeping tool arguments intact.
## Testing
Add unit tests verifying that MCP arguments retain description fields, including nested fields, and that other action types remain unchanged.
GitOrigin-RevId: 8e890fb263556596f695177f917750377c04d43c
## What changed
Introduce `ReviewTurnResult` and `ReviewSessionResult` to carry review outcomes, session disposition, and completion or analytics data. Propagate `SessionDisposition` directly through review execution and pooling, replacing boolean reuse flags and positional tuple access while preserving existing behavior.
Update existing review-session tests to assert the named fields and explicit session dispositions.
GitOrigin-RevId: 93eea8b482cd592167956444042becc1ef5f2eb5
## Why
Memory usage telemetry identifies artifact kinds but does not distinguish reads from `memories` and `memories_v2`.
## What changed
Return each artifact's memory version from shell command classification and add a `memory_version` tag (`v1` or `v2`) to usage counters. Normalize Windows path separators before classifying memory paths.
## Testing
Extend regression coverage for both memory versions with Unix and PowerShell reads, and add a test for commands that read artifacts from both roots.
GitOrigin-RevId: 68eaab3af0317613e4969e8c4e5478b18255ca52
## Why
Reusing a Guardian reviewer could trigger a model catalog refresh during the previous-model compaction check, even when the model was unchanged and no compaction compatibility change required compaction.
## What changed
Return early from the previous-model compaction check for Guardian sessions when the model slug is unchanged and the compaction compatibility hashes do not require compaction.
## Testing
Add a regression test with an expired model catalog cache that verifies two approvals reuse the same Guardian reviewer, both reviews and the parent turn complete, and no additional model catalog request occurs.
GitOrigin-RevId: cc1cdc5f89c6f9ec03f1bedfb78cad9780825733
## Why
Probing Windows network paths can send ambient credentials, even during metadata checks. Entries in `project_doc_fallback_filenames` must be validated before filesystem probes.
## What changed
Ignore entries containing path syntax according to the executor's OS, rather than the host's. Reject `.` and `..`, slashes, and NUL characters on all executors; also reject backslashes and colons on Windows. Log a warning for rejected entries and continue considering valid filenames.
## Testing
Add tests that verify invalid entries never reach metadata probes under POSIX and Windows path conventions, preserve backslashes and colons in POSIX filenames, and confirm valid fallback instructions still load alongside invalid entries.
GitOrigin-RevId: 4369e9b97ae6a3560d09e79efd8c85adac3d1d90
## 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
Clock provider failures can abort a turn while preparing time context or running clock tools. Allow turns to continue with an explicit indication that the current time is unavailable.
## What changed
- Add `features.nonfatal_clock_read_errors`, disabled by default, to report clock failures to the model without failing the turn.
- Emit a generic `failed to read current time` notice for context reads and tool errors, without exposing provider error details. Deduplicate context notices per turn and compaction window, and remove inherited notices from forked subagent context.
- Omit unavailable environment dates and explicitly clear previously visible dates with `<current_date status="unavailable" />`.
- Return external sleep clock failures to the model when the feature is enabled, preserving sleep item completion notifications.
## Testing
Add coverage for continued inference after clock failures, notice deduplication across compaction, subagent notice filtering, environment date removal and recovery, and sleep failures during initial and polling reads.
GitOrigin-RevId: a39c3723c06a6f786d8ad59d667e8b9f626c973e
## 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
- Add an optional `WorkspaceRoutingResolver` to `AuthManager` and pass session configuration into routing lookups. Callers without a resolver retain existing routing behavior.
- Apply resolved backend origins and account routing overrides to eligible ChatGPT Responses HTTP requests and WebSocket handshakes. Preserve endpoint paths, validate routing values, and reject HTTP redirects for routed requests, including `NO_CONSTRAINT` routes.
- Key cached WebSocket connections by destination, routing header, and auth revision. Rebuild request setup after credential refreshes and reject account changes during setup or routing discovery.
- Serialize routing lookups per session and retain whether the session has previously been routed.
## Testing
Add tests for path preservation, provider exclusions, concurrent routing lookups, unavailable resolvers, workspace mismatches, redirect rejection, and credential refresh or account changes during request setup.
GitOrigin-RevId: 2b6609019e84a315745c94858955f3f16426fe7f
## 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
Managed daemon recovery snapshots previously saved only loaded thread IDs, without identifying active turns or preserving their turn-specific options.
## What changed
- Capture regular, uncanceled turns after their input is recorded, saving the turn ID, output schema, service tier, and cyber access program alongside persisted thread IDs.
- Store interruption metadata atomically in the existing candidate array format so older servers can still read thread candidates.
- Begin snapshotting once admitted operations drain, while turns may still be running. Run snapshot collection and thread listener attachment independently of the event loop to keep forced shutdown responsive.
## Testing
Add coverage for running, completed, canceled, and compacting turns; recovery readiness for automatic and user turns; admitted resumes during shutdown; forced shutdown with a blocked rollout writer and child listener attachment; and legacy candidate-array compatibility.
GitOrigin-RevId: ed46342c3a5c71b09c48fa9acece2f15ae748e2f
## What changed
Reject `request_plugin_install` calls from non-root agents with an error returned to the model before parsing arguments or prompting for installation. Apply the restriction to both legacy install requests and recommended plugin requests.
## Testing
Add unit and integration tests for both request formats, verifying that subagent calls return the root-only error and emit no installation elicitation request.
GitOrigin-RevId: f23bbc6dd34d69366b81e4033bd554bba1fb816a
## 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
A checkpoint produced by a previous model may be incompatible with the selected Guardian reviewer. Legacy review must retain user restrictions and verified answers across compaction and restart until a compatible checkpoint is available.
## What changed
- Expose retained user evidence independently of whether Guardian reviews the legacy transcript or parent context.
- Resolve the selected reviewer's compaction compatibility hash during resume and remote compaction. Preserve the legacy transcript when checkpoint compatibility is unknown or mismatched.
- Activate parent-context review immediately after compatible compaction and invalidate pending reviews bound to the previous evidence policy. Ordinary compaction preserves pending reviews.
- Keep strict compatibility checks for previously migrated checkpoints whose complete legacy transcript is no longer available.
## Testing
Add coverage for mismatched checkpoint hashes, retained evidence during legacy review, and pending-review cancellation on migration. Add a request-history scenario covering a model switch, incompatible automatic compaction, restart, and compatible manual compaction with preserved user restrictions and verified answers.
GitOrigin-RevId: b52bfd7c21ce7ebed482174c8d7c327e50b1ada8
## Why
Older compaction checkpoints can lack a producer model hash. Enabling thread-owned Guardian context must accommodate those checkpoints without losing user instructions or verified answers.
## What changed
- Select review policy from each history snapshot independently of the session's evidence capture policy.
- Keep legacy review for checkpoints with missing or empty producer hashes when the transcript preserves the evidence. Preserve strict compatibility checks when review depends on retained-only evidence.
- Continue capturing retained instructions and answers during migration, while supplying legacy reviews with runtime answers and subagent reviews with root authorization evidence.
- Record producer model hashes on new compactions regardless of context mode.
## Testing
Add coverage for checkpoint migration across compaction and resume in both history storage modes, snapshot policy stability, retained-evidence preservation, and authorization revalidation for owning sessions and subagents.
GitOrigin-RevId: ec72b4a51d40729173e24ac1b53b7d516ddaa825
## What changed
- Track the Windows sandbox implementation separately from its legacy setup level.
- Select dedicated proxy listeners for `WindowsMxc` on Windows across sessions, app-server command execution, and the sandbox CLI.
- Rebuild the session proxy when routing changes, retaining its network policy decider.
- Add a sandbox CLI execution path through the MXC sandbox transform when `WindowsMxc` is selected.
## Testing
Extend configuration assertions for the selected sandbox type and the session refresh test to verify dedicated routing and policy decider retention on Windows.
GitOrigin-RevId: 2a22192636c542022ec81a378a16c1bb6867e145
## Why
Disabling a connector's canonical plugin could leave its tools available when another enabled plugin contributed the same connector.
## What changed
Retain `canonical_app_id` in the remote installed-plugin cache and use ownership metadata for the current account when building connector snapshots. A disabled canonical owner now excludes its connector even when another plugin contributes it or the owner's bundle is absent from the host. Match owners by plugin name and marketplace, and ignore ownership metadata when the cache no longer matches the current authentication.
Build these snapshots through `PluginsManager` when the plugins feature is enabled; otherwise use an empty snapshot.
## Testing
Add manager coverage for combined local and canonical exclusions, marketplace matching, and authentication changes. Add an integration test showing that disabling a noncanonical contributor preserves shared calendar tools, disabling the canonical owner hides them, and clearing the exclusion restores them.
GitOrigin-RevId: ee2981d1277825fefb671dd7d1078cd7ea5c0ea5
## What changed
- Replace dedicated Guardian endpoints with `/responses`, sending `x-codex-guardian: reviewer` or `x-codex-guardian: classifier` for eligible Codex backend requests over HTTP and WebSocket.
- Add model-scoped thread headers, recheck backend authentication on each request attempt, and reconnect WebSockets when the applicable headers change.
- Retain `features.guardianv2.free_guardian` for configuration compatibility while removing its routing gate; the backend now controls Guardian billing.
## Testing
Update tests for reviewer and classifier headers, model and authentication scoping, HTTP fallback, WebSocket reuse, and parent-response metadata across retries.
GitOrigin-RevId: 1c2b3c458ab77fb40aae4ee6784f6d827c60e76c
## 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
Move concrete reviewer settings into `guardian-v2` and replace `ReviewerConfigOverrides` with a `ReviewerConfig` callback stored in thread extension data. Apply the callback to each captured parent configuration before preparing context and checking session reuse.
Keep model selection, policy prompt construction, and live network state in the core adapter. Preserve the existing read-only reviewer settings and share `reviewer_permission_profile` with inherited environment configuration.
## Testing
Update existing Guardian configuration, session reuse, and prewarming tests to use the extension's actual configuration builder, including compiling the shared source in core's test host.
GitOrigin-RevId: dfa1dae9f8d4469f2e4f6e64ab842cc662970898
## 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 `AllowedTools` to the extension API, captured once at thread startup to restrict which tools can be advertised or executed. An empty list disables all tools; an absent value preserves ordinary tool setup. Callers must supply the list again when resuming a thread.
- Filter tool registration and hosted tool specifications before Code Mode and discovery. Match names with their namespaces and require generated tools such as `exec` and `wait` to be explicitly allowed.
- Move Guardian reviewer tool selection into the allowlist while retaining feature and sandbox restrictions, with a fallback for older reviewer sessions.
## Testing
Add coverage for selected, empty, and absent allowlists across tool sources and Code Mode. Add managed-thread tests verifying advertised tools, rejection of excluded calls, and that replacing extension state after startup cannot change the captured allowlist.
GitOrigin-RevId: 33c1722c4241f368963d8385fa0415112e16a72d
## What changed
Introduce `ReviewRequest` in `codex-guardian-reviewer` to own contributor routing, cached approvals, synchronous fallback, and review cancellation. Keep action validation and session-specific preparation in the host.
Track the complete approval operation through parent shutdown, driving cancellation through reporting and reviewer cleanup before releasing it. Preserve fresh-review requirements and validate cached approvals before recording their outcome.
## Testing
Extend coverage for cancellation before routing and during cached approval, parent shutdown cleanup, and required fresh review overriding a cached allow result with matching assessment events and a denial warning.
GitOrigin-RevId: 8dcf26cc3660e91ef94e28e0bee7327ebe34ae6c
## What changed
Replace duplicated model-selection fields in `GuardianReviewSessionConfig` and `GuardianReviewSessionParams` with the existing `ReviewModel` struct. Read model settings and selection metadata from that struct for session execution, analytics, and failed-review records, and update the existing test fixtures accordingly.
GitOrigin-RevId: 1da2001e68168ec40a3d726694eb5fd0445aa3d7
## What changed
Remove core guardian tests for transcript numbering and unpaired tool outputs. Extend `guardian-context` coverage to assert that named image-only tool outputs retain their source and use `[non-text output]` for both sync and async contexts, with tool calls included or excluded.
GitOrigin-RevId: ba483e8f6e335697106a987051687a12ad2fde01
## What changed
- Mark `guardian_ext` as a removed compatibility flag.
- Remove `InternalSessionSpawner`, `InternalSessionSpawnFuture`, `ApprovalReviewInput`, and `ApprovalReviewError` from the extension API, along with the spawner test.
- Remove `NodeReplReviewEvidence::review_inputs` and make the core re-exports of `NodeReplReviewEvidenceMode` crate-private.
GitOrigin-RevId: 1c532bc57264644cf521ef8077285a9b8ed67391
## What changed
- Make `SynchronousReview` own assessment events, telemetry, warnings, evidence-recording decisions, and consecutive-denial accounting.
- Keep action preparation, stale-approval validation, evidence storage, and event publication in the host adapter.
- Extract `Session::interrupt_turn_with_warning` to apply extension-requested interruptions to the selected active turn and emit the interrupted thread-idle lifecycle event.
## Testing
Adapt session tests to verify that extension interruptions emit the thread-idle lifecycle event and survive shutdown of the calling runtime.
GitOrigin-RevId: b234ad86206fedc2434f48fc44dc57679443c69f
## What changed
Extract V2 interruption validation and dispatch into `AgentControl::interrupt_spawned_agent`, returning the agent path and previous status with typed validation and runtime errors. Update the `interrupt_agent` tool handler to delegate to it while retaining tool error mapping and activity emission.
Preserve rejection of root and self targets and successful handling of unloaded or already-dead runtimes without reloading them.
GitOrigin-RevId: 893bbc4f464596d0fee032a71702a4a4f6becf5c
## What changed
- Use cancellation guards to tie reusable reviewers and temporary forks to their lifetimes, including when a review future is dropped. Replace cancelled reusable reviewers before reuse.
- Share `ReviewerTasks` between the pool and `ThreadManager`, and wait for tracked cleanup during pool shutdown. Remove the separate session shutdown protocol.
- Move denial cleanup from core task handling into Guardian's turn start, stop, and abort hooks. Expose `install_reviewer` to register both thread and turn lifecycle contributors together.
## Testing
Add an integration test that exercises stale denial cleanup at turn start, completion, and interruption, including starting another turn after interruption.
GitOrigin-RevId: 85badb235309c1e1576547d1746f7ee9fc66d545
## What changed
Extract target validation, runtime reloading, and message delivery from the V2 tool handler into `AgentControl::deliver_message`. Keep target resolution, analytics, and tool-facing error mapping in the handler.
Represent plaintext and encrypted payloads with `AgentMessage`, sharing communication construction with agent spawning. Preserve queue-only and follow-up turn semantics, target checks before reload, and turn metadata propagation.
GitOrigin-RevId: a88bcede015a17f6c11c7cad95ee58add5dc2820
## What changed
Move shared spawn and resume configuration helpers into `agent::child_config` and route both multi-agent versions through `prepare_agent_spawn_config`.
Preserve each version's role and model precedence, full-history inheritance, service-tier selection, runtime policy, and default-role metadata for reloads. Return configuration errors as strings and convert them to `FunctionCallError::RespondToModel` at tool-handler boundaries.
GitOrigin-RevId: 9d539050aa44f94043a6487f1f6f1037de1d15ca
## 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
Copy the source thread's current attachments when creating a non-ephemeral fork, including forks at an earlier turn. Copies receive new attachment IDs and creation timestamps while preserving resource identities and payloads. Attachment membership can then change independently on either thread; referenced resources are not copied.
Await the atomic copy before publishing the fork. If copying fails, log the error and allow the conversation fork to succeed without attachments. Resuming a fork does not copy attachments again.
Document that clients should use `forkedFromId` on `thread/started` and fetch the fork's attachments with `thread/attachment/list`; copying does not emit per-attachment updates.
## Testing
Add coverage for atomic rollback, independent attachment membership, inheritance across history cutoffs, successful conversation forks after copy failures, and resuming without restoring removed attachments.
GitOrigin-RevId: 939d2c6a3073ccfcd922380c6beda45d3deac606
## What changed
Replace `AttachmentStore::persist` with `upload` and `resolve`. Uploads return inline bytes or a file ID; resolution returns optional file metadata and a download URL only when a minimum URL lifetime is requested. Add image dimensions, digest, size, MIME type, and categorized errors to the API.
Make `InlineAttachmentStore` return the original bytes and report `NotFound` when resolving file IDs. Redact attachment bytes and file URLs in debug output.
Pass the configured image store from the thread manager into sessions and inherit it in delegated sessions. Allow `TestCodexBuilder` to accept a custom image store.
## Testing
Update unit coverage for preserving PNG and JPEG bytes, redacting bytes and URLs in debug output, and rejecting file resolution in the inline store.
GitOrigin-RevId: f313e0048925998d84394c7e5a278e0d39d86a45
## 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
Guardian reviews must stop when their parent shuts down or their history is reset. Shutdown must also finish reviewer cleanup before closing the parent's persistent history, including when a review is waiting to retry after a rate limit.
## What changed
- Let the Guardian extension own reviewer startup, prewarming, and shutdown through `ThreadManager`, tracking and joining outstanding work during teardown.
- Cancel reviews on history reset or parent shutdown and reject decisions returned after cancellation, including cached extension decisions.
- Keep background prewarm previews from overwriting the active turn's model metadata.
## Testing
Extend regression coverage to verify reviewer cleanup after parent shutdown, prompt shutdown during a 60-second Guardian retry with the network request denied, and preservation of active model review requirements during prewarming.
GitOrigin-RevId: 05efc369b9a1642a10365eac8a09da77f3f6e28c
## Why
Linux proxy-routed sandboxing denied standalone Unix sockets even when the effective network policy enabled `dangerously_allow_all_unix_sockets`.
## What changed
- Carry Unix socket permissions in `ManagedNetworkSandboxContext` and pass the prepared context through Linux sandbox launches with `--managed-network`.
- Allow `AF_UNIX` socket creation in proxy-routed mode when `dangerously_allow_all_unix_sockets` is enabled, while preserving network namespace isolation and restrictions on other socket families.
- Keep standalone Unix sockets denied by default and for path-only grants. Default missing fields in older serialized contexts to restrictive values.
## Testing
Add coverage for policy preparation and transport, legacy deserialization, and malformed policy rejection. Add a Linux integration test covering default denial, path-only denial, and explicit allow-all access, while checking that direct TCP access and `AF_NETLINK`/`AF_VSOCK` sockets remain blocked.
GitOrigin-RevId: 2695b945ad3e59fcb3faf7662d852a26650af16c
## What changed
Replace `ReviewerSessionFactory` with a startup callback installed through
`ReviewerPool::new`. Review requests supply shared setup data and reuse context,
while the pool uses its callback to create both reusable and forked reviewers.
Update Guardian session setup, prewarming, and existing test fixtures to use the
new pool API.
GitOrigin-RevId: fa171503afcee8bdbdf6822573bea8ded50ce117
## Why
Resuming a thread initialized its collaboration mode to Default, losing the saved Plan mode and its developer instructions. Reconnecting clients also lacked a server-reported mode to reconcile changes made by another client.
## What changed
- Restore the saved collaboration mode from the latest matching `ThreadSettingsApplied` event, falling back to the last legacy `TurnContext`. Apply the effective model and reasoning effort while retaining the saved mode and developer instructions.
- Include `collaborationMode` in `thread/resume` responses and update the generated schemas and bindings.
- Use the restored mode in the TUI, including the first prompt after resume. Prefer the server's mode when restoring disconnected input, while preserving the local selection for older servers that omit it.
## Testing
Add regression coverage for persisted and legacy collaboration modes, model and reasoning-effort overrides, the resumed Plan mode display and first prompt, and reconnect behavior with and without a server-reported mode.
GitOrigin-RevId: ed064516e7fae1c1668152ab448f510cbcacfe06
## Why
Inline delegates have no entry in the thread registry, so reviewer creation cannot depend on looking up the parent or waiting for its thread-ready notification.
## What changed
- Capture parent identity, authentication, shared agent control, originator, and inherited instructions in `StartThreadOptions` so `ThreadManager` can start a child without a registered parent.
- Route Guardian reviewer creation through this path, remove the standalone fallback and readiness gate, and require a Guardian extension host.
- Install explicit reviewer hosts in unit tests and the Guardian reviewer extension in the integration test harness, using `ExtensionRegistry::to_builder()` to preserve existing contributors.
## Testing
Extend the thread-manager regression test to remove the parent from the registry before starting a child, then verify inherited lineage, originator, session identity, and authentication, and exclusion from the public thread list.
GitOrigin-RevId: 468ded6fdce7520cb39d55c1a884dcfa5aaea2d9
## What changed
Add `auto_review.experimental_policy_template` to override the Guardian prompt template in `config.toml`. Trim the configured value and ignore it when empty. Prefer the override over the model catalog template, retaining the bundled template as the final fallback.
The template's `{{ tenant_policy_config }}` placeholder is replaced with the resolved Guardian policy.
## Testing
Extend tests to cover template deserialization, trimming, precedence over the catalog template, and rendered policy text in Guardian inference requests.
GitOrigin-RevId: 85b4a8fc193a42735354894203ccbd1f738a3b58
## Why
Building MCP search entries eagerly cloned tool specs and normalized schemas even for tools that were never selected.
## What changed
Store search specs in `Arc<ToolSpec>` and let MCP search entries share the handler's spec. Materialize and normalize loadable specs only for selected results, preserving existing result formatting and dynamic-tool cache equality behavior.
## Testing
Add coverage for function, freeform, and namespace specs that verifies shared specs produce equivalent results, retain the source while needed, and release it when the search entry is dropped.
GitOrigin-RevId: 4260f2e2527834d8a856b1528654c6951aab8a7d
## Why
Persisting user input received during an active turn currently blocks the next model request. Stores that support background persistence can overlap this checkpoint with inference.
## What changed
- Add `PersistContext::SteeredUserInput` and `allows_background_persistence()` so stores may enqueue these checkpoints, with durability and error reporting enforced by later flush or shutdown operations.
- Use the new context for accepted steered user input and apply the same metadata handling as turn-start persistence.
- Keep tool outputs synchronous, including in mixed input batches, and allow stores to retain synchronous persistence for all contexts.
## Testing
Add gated-store integration tests covering background user-input persistence, synchronous stores, and synchronous tool-output checkpoints. Verify that the next request includes the steered input and waits for persistence when required.
GitOrigin-RevId: c60b7b6c9b483245fd3169306bcf0de248ccdf35
