## Why
Initial history replay and rollback before the first turn could clear the reasoning-effort baseline established by startup prewarm, preventing the first request from preserving that baseline when the selected effort changes.
## What changed
Preserve the reasoning-effort pin during history reconstruction. Clear it on rollback only after startup prewarm has been consumed. With reasoning-effort overrides enabled, a prewarmed `medium` baseline remains on the request while a subsequent `high` selection is sent as a `configuration_update`.
## Testing
Add regression coverage for prewarm completing before initial replay on resume and fork. Expand WebSocket tests to cover resumed and forked threads with overrides enabled and disabled, plus rollback before the first turn.
GitOrigin-RevId: 2e2d0e8a06b24f01b717458ca0576d63107c7697
## Why
Review evidence can fit its own limits while exceeding the reviewer context window once history, tools, output format, and reminders are included. Tool continuations can also push an existing review over budget.
## What changed
- Select evidence after tools and turn context are resolved, reserving request overhead and a 256-token margin. Omit optional evidence while preserving required sections, and reject required evidence that cannot fit.
- Keep incoming evidence pending until budget selection succeeds so cancellation and compaction cannot record unselected input in reusable history.
- Check the assembled prompt before sampling, including retries and tool continuations. Retry budget failures with summary compaction once per model step, and retire reviewers whose budgets remain exhausted. Avoid history-resetting token-budget compaction for this recovery.
- Record section costs after budget selection.
## Testing
Add unit and integration coverage for required-evidence rejection, optional-evidence omission, reminder overhead, cancellation safety, incoming-review and tool-continuation compaction, and reviewer retirement after ineffective compaction.
GitOrigin-RevId: 2f7ef191b3f46032d295ad363eb7debf9d7a9684
## Why
Failed environments were omitted from environment context, and `wait_for_environment` returned a generic failure or treated an already-failed environment as unselected. The model needs the failure reason to explain problems such as an empty repository.
## What changed
- Preserve the selected environment and error when startup or configuration fails.
- Include failed status and XML-escaped error details in environment context, and return the reason from `wait_for_environment` for failures detected before or during a wait.
- Limit error details to 256 bytes per environment and 512 bytes total in context, preserving UTF-8 boundaries. Limit wait failure details to 256 bytes.
## Testing
Add coverage for failures before a turn and while waiting, verifying that the model receives the reason and the turn completes. Add unit tests for XML escaping, incremental context updates, clearing errors on recovery, and UTF-8-safe truncation.
GitOrigin-RevId: 093ab9b447c7b3243fbb53b665180db95479f2a7
## Why
Recovering a suspended turn can append a duplicate reasoning effort update when history already ends with a matching trusted update but the runtime has not established its effort pin.
## What changed
Reuse a matching harness-authored `ConfigurationUpdate` at the end of history even when the runtime effort pin is unset.
## Testing
Add a regression test that suspends and recovers a turn without WebSocket prewarming, then verifies the recovered request contains exactly one effort update and retains `high` reasoning effort.
GitOrigin-RevId: 2e49073eb5e8d4fae39a8dc1d9d2b07f77802adb
## Why
Remote compaction already uses the normal Responses API, leaving the legacy `/responses/compact` runner unused.
## What changed
- Remove the legacy runner, endpoint client, request types, analytics variant, and obsolete test helpers and snapshots.
- Move tool-output trimming and its metadata tests into `compact_remote_history` for reuse by remote compaction v2.
- Consolidate retained-history filtering in the v2 implementation and remove redundant `RemoteCompactionV2` settings from tests.
## Testing
Extend the retained-history unit test to explicitly check that hook prompts survive compaction.
GitOrigin-RevId: 999bb1391aa22c3c281d6a96f98817d6c9e46ed9
## What changed
- Route manual and automatic remote compaction through the v2 implementation.
- Retire the `remote_compaction_v2` feature toggle while continuing to advertise it in the model client beta features header.
- Migrate compaction tests from `/responses/compact` to streamed `/responses` requests with `compaction_trigger` items and remove legacy parity coverage.
## Testing
Add streamed compaction coverage for tool search output trimming and session base instruction token estimates. Update app-server tests to verify started/completed notifications for both local and streamed remote compaction.
GitOrigin-RevId: cea392a6166a9b116ff83708fd9126d5546476e4
## Why
Saved model selections can outlive their bundled catalog entries and still need migration guidance.
## What changed
- Remove `gpt-5.2` and `gpt-5.4-mini` from the bundled model catalog.
- Preserve migration from saved `gpt-5.4-mini` selections to `gpt-5.6-luna` when the old model is absent, while respecting catalog-provided migration metadata.
- Update tests and snapshots to use current models or explicit test fixtures, and remove the obsolete prompt fixture.
## Testing
Extend migration tests to cover catalog metadata precedence, saved selections, replacement model and reasoning-effort persistence, acknowledged prompts, and missing or hidden migration targets.
GitOrigin-RevId: 82beea504cc4a15699677c28a61ec0939af3069c
## Why
Switching models can send images from conversation history with `detail: original` to a model that does not support it.
## What changed
Normalize image details on request copies using the receiving model's capabilities. Downgrade `original` to `high` when unsupported, covering user messages and function and custom tool outputs. Preserve stored image details so switching back to a supporting model retains `original`, and continue stripping details for Responses Lite.
## Testing
Expand unit coverage across image detail values and model capabilities. Extend integration coverage for model switches within and between turns, text-only models, and resumed and forked threads, including assertions that persisted tool outputs remain unchanged.
GitOrigin-RevId: 2561651ea74f045e00f708ae53771a41dcd49c94
## Why
Replaying tool outputs under a different model can expand or shrink the history shown to the model if truncation uses the new model's budget.
## What changed
Save the originating history truncation budget on function and custom tool outputs and reuse it during replay, preserving existing tool-specific overrides. Include the existing 20% serialization allowance once, before converting byte budgets to tokens.
Rename the metadata field to `history_truncation_token_limit` while retaining `fallback_token_limit_override` as its serialized name for compatibility.
## Testing
Add regression coverage for resume and fork with different model budgets, including custom tool outputs. Extend unit coverage for existing overrides and byte-budget conversion.
GitOrigin-RevId: a62c8fd3e43198e2252b150fba72f022939c1070
## Why
History recording used the model captured at turn start, so switching models within a turn could apply stale image preparation and tool-output truncation rules.
## What changed
Pass explicit model metadata through conversation recording. Record model responses and tool results using their originating step's settings, and capture the current model for pending input recorded during startup interruption or task completion.
## Testing
Add regression coverage for tool results across a model switch, explicit model selection for plain and annotated history, and image input retained during interruption and completion. Extend model-switching tests to verify that prepared media and item identity survive switching back to a multimodal model in live, resumed, and forked threads.
GitOrigin-RevId: 5bc750c30c334acb9b802cb80fdea01daffa84a1
## 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
Model switches within a turn can leave extension context using stale model metadata. Skill catalogs, context windows, and metric attribution need to match the model captured for each sampling step.
## What changed
- Pass captured model metadata and step-specific telemetry to world-state contributors.
- Use that metadata for skill catalog budgets and usage instructions, preserving configured budget overrides.
- Supply the captured model's usable context window to turn-context contributors, including when rebuilding context.
## Testing
Add regression coverage for model switches during skill discovery, catalog budgets and metric attribution, and extension context windows after `new_context` and retained-step context rebuilds.
GitOrigin-RevId: c51b40b739a380b9767a54ea8c8ee6de45bf01c8
## Why
Model changes during an active turn could leave context using the turn's initial model and settings, even after requests switched to the new model.
## What changed
- Build model, personality, approval, collaboration, app, plugin, and multi-agent instructions from captured step settings.
- Resolve multi-agent policy from the step's effective reasoning effort.
- Use the captured step's context window for full-context metadata and retain that step when rebuilding initial context for compaction.
## Testing
Add regression coverage for model switches updating context without duplicating updates, delegation policy following selected or model-default reasoning effort, and compaction preserving retained context after a model change.
GitOrigin-RevId: 3615c7a3f13f15fdcce9ad13d23311340e0aea88
## Why
Cancelling a session after persistence opens but while MCP startup is still pending can leave its writer held, blocking a subsequent resume.
## What changed
Create `LiveThreadInitGuard` inside the persistence startup future so it protects the live thread while `tokio::join!` waits for other startup work. Dropping the startup future then schedules writer cleanup.
## Testing
Add a regression test that cancels a resume while MCP startup is blocked, verifies the local writer is released, and resumes the same thread successfully.
GitOrigin-RevId: 57d8624e783a7b993579a6386aea35ba845da0e3
## Why
Dormant MCP servers with usable cached tool catalogs prevented binding reuse, causing each model step to capture a new binding even when the catalog was unchanged.
## What changed
Track dormant catalog revisions alongside ready client revisions so bindings can be reused until the catalog changes or the server starts. Explicit server and plugin requirements still trigger binding capture and startup. Check cached catalog availability without cloning tool definitions.
## Testing
Extend the lazy-startup integration test to verify that two model steps share one binding while the server stays dormant, and that starting the server invalidates that binding.
GitOrigin-RevId: ef0469a85000f84a928946c24350e3bda1522fb5
## Why
Credential brokerage must retain trusted destination hints even when shell environment policy hides them from child processes. Snapshot replay also needs to preserve credential aliases when tokens are short or captured dummy values change.
## What changed
- Add `features.network_proxy.credentials` and preserve provider settings when toggling the proxy. Prevent project configuration from overriding providers or their credential and destination environment variables.
- Use provider metadata throughout snapshot capture and replay, and pass hidden destination context to the broker without exposing it in the child environment.
- Rewrite aliases containing short credentials or previously captured dummies, respecting environment filters and explicit overrides.
- Preserve case-distinct `shell_environment_policy.set` keys so Windows credential ambiguity checks survive configuration merging and permission profile changes.
- Restore independent MITM settings when credential brokerage is disabled.
## Testing
Add regression coverage for custom providers, hidden destination hints, Bash and Zsh alias replay, configuration edits and merging, Windows ambiguity handling, and credential protection during approved execution.
GitOrigin-RevId: b2bd935d2d8555be56baf8feb1a8e5b3a0c666bc
## What changed
Increase `GUARDIAN_MAX_ACTION_BYTES` from 8,000 to 200,000 bytes to allow larger actions to be reviewed. Keep unified exec stdin approvals capped at 8,000 bytes with a separate `MAX_STDIN_APPROVAL_BYTES` constant.
## Testing
Update aggregate payload rejection coverage for the new limit and exercise MCP elicitation reviews with tool descriptions exceeding the previous 8,000-byte limit.
GitOrigin-RevId: fd4b97980803a7a687449043931e6f1e57e260d3
## What changed
Pass `StartThreadOptions` through rollout, loaded-history, and prepared forks instead of separate configuration and startup arguments. Replace `options.initial_history` with the fork snapshot while preserving the other supplied startup options, and update app-server and test callers.
Box the app-server's `thread_fork_inner` future to keep the large fork future out of the shared request dispatcher's stack frame.
GitOrigin-RevId: d54eb8b212dedabaf2c5d99d155637cefd7deb7a
## Why
Shell quoting can hide credentials from raw-text checks, and startup files can restore real credentials after the broker replaces them with dummy values.
## What changed
- Decode shell literals without evaluating them and reject snapshots containing credentials in executable source, including aliases, functions, and heredocs.
- Preserve credential policy overrides, explicit unsets, and aliases whose source variables were removed. Support credential aliases in Zsh tied arrays while rejecting credentials that span array elements.
- Guard snapshot replay against credential restoration through shell startup files and preserve unrelated `ENV` settings.
- Apply Windows environment-key casing rules to credential overrides, suppress unredacted sandbox diagnostics during snapshot capture, and clear inherited environment variables before launching escalated commands.
## Testing
Add regression coverage for shell quoting and escaped credentials, Zsh tied arrays, startup-file replay, readonly credentials, policy overrides, and sensitive capture timeout and cancellation handling.
GitOrigin-RevId: 58274c07c715423241d26ce6dd2c2b4230cf0f64
## What changed
Support `model_providers.amazon-bedrock.aws.credential_export` with `command`, `args`, and `timeout_ms` to supply SigV4 signing credentials from a command's JSON output. Accept both flat credential-process output and nested STS `Credentials` objects.
Cache credentials in memory, refresh before expiration, and share exports across sessions with matching AWS configuration. On recoverable authentication failures, run the optional `aws.auth_refresh` command before exporting fresh credentials, coalescing concurrent recovery attempts.
Bound command execution time and output size, and keep credential values out of errors. Reject combining `aws.credential_export` with `aws.profile`. Bedrock setup and login reject changes while an exporter is configured, preserving configuration and saved credentials.
## Testing
Add coverage for output formats, expiration, credential precedence, caching, concurrent recovery, command failures, and secret redaction. Integration tests verify request signing with rotated credentials, bounded recovery attempts, and setup/login rejection across configuration layers.
GitOrigin-RevId: 4ef799f88ab5e3b2578f8f41a5e56e4f30e2cd81
## Why
Credential-brokered commands rebuild shell snapshots on every invocation. Snapshot capture failures can also include credential-bearing startup output, and descendants holding output pipes need cleanup even after the shell exits.
## What changed
- Cache successful protected snapshots per environment, keyed by working directory, shell, login mode, and sandbox configuration. Rebuild missing or stale snapshots while keeping concurrent captures independently cancellable.
- Invalidate snapshots when shell settings or credential broker configuration change, and retry capture once if broker configuration changes during startup.
- Restore credentials and associated provider context while respecting environment policy filters and explicit overrides.
- Keep full-buffer capture subject to timeout and cancellation through output draining, clean up descendants on capture expiration or drain failure, and omit startup output from snapshot errors.
## Testing
Add regression coverage for snapshot reuse, invalidation, recovery after storage failure, concurrent cancellation, credential-safe errors, and descendant cleanup. Verify that successful background startup and output beyond the shell output cap remain supported.
GitOrigin-RevId: 7c7c8455bf6e3b9ca173dbb4277783469f0b45e6
## 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
## What changed
- Match parent follow-up responses by tool call IDs in the grandchild context baseline test, and assert that the grandchild completes with `done`.
- Drive delayed terminal output with newline-delimited stdin instead of sleeps, keeping the process alive across three `write_stdin` calls and updating the expected stdin events.
GitOrigin-RevId: 433954e5ed5ecce920cf198d1bf1264e58178ba6
## What changed
- Update the status heading from the latest usable reasoning line and retain it through tool activity and empty reasoning items. Keep completed reasoning in the expanded transcript only.
- Restore active reasoning after resume, thread switches, and session refreshes, including when earlier events have left the replay buffer.
- Default new embedded TUI threads to `model_reasoning_summary = "detailed"`, honoring explicit summary settings. Keep `concurrent_reasoning_summaries` opt-in and disable it when summaries are `none`.
- Persist the request's captured reasoning summary setting in context updates and local and remote compaction checkpoints.
- Animate status text with a smooth, grapheme-aware shimmer that respects terminal colors and reduced motion.
## Testing
Add regression coverage for reasoning status updates, transcript visibility, resume and buffered replay, outbound summary configuration, and summary settings across all three compaction modes. Add shimmer snapshots and checks for smooth brightness changes and Unicode grapheme preservation.
GitOrigin-RevId: 725c7de20f23166d7a3da6daeca617add5cbc600
## Why
Guardian reviewers can inherit token-budget mode from the parent session or model defaults, causing context rollover instead of summary-based compaction.
## What changed
Clear inherited token-budget startup activation, set an explicit default `TokenBudgetConfig`, and disable `Feature::TokenBudget` and `Feature::ContextManagement` for Guardian review sessions.
## Testing
Update regression coverage to verify that reviewers compact with a summary even when the parent and model enable token budgets. Cover both transcript modes and browser evidence, checking that review requests omit `token_budget.context_window` and retain the compaction summary.
GitOrigin-RevId: e1a84f9c7752a712399cd749c3834b2a7bb4a7e6
## Why
Shell startup files can introduce credentials or overwrite brokered dummy values. Snapshot capture and replay need to respect the command's sandbox and environment policy without persisting real credentials.
## What changed
- Capture and validate brokered snapshots per command using its requested shell, working directory, login mode, sandbox, and environment policy.
- Discover shell-initialized credentials and prepare snapshot exports for brokered replay. Preserve shell functions and aliases while preventing startup files from overwriting dummy credentials during replay.
- Rebuild snapshots as credential broker state changes and retain each command's snapshot for the lifetime of its process.
- Reject brokered POSIX shell execution when a protected snapshot cannot be created, and reject brokerage with `shell_zsh_fork`. Restore real credentials and remove brokerage markers for unsupported PowerShell and Cmd execution; escalated commands bypass protected snapshots.
## Testing
Add regression coverage for credential discovery and redaction, environment filtering, readonly exports, shell function and heredoc replay, command working directories and login modes, sandbox enforcement, and missing or disabled snapshots.
GitOrigin-RevId: 685356cb9e80f11cf69d053e4d239ee6ccf43a9e
## Why
Switching providers or authentication could reuse a previous identity's model catalog, including its default service tier. An in-flight refresh could also overwrite a newer account's catalog after cache storage completed.
## What changed
- Require a matching provider and auth identity for disk and in-memory catalog reuse. Treat legacy entries without an identity as cache misses and fall back to bundled metadata when the in-memory identity no longer matches.
- Recheck identity after fetching and storing a catalog before publishing it.
- Renew cache freshness only when the client version, identity, and ETag match the stored entry.
- Update cache fixtures to include the configured provider and auth identity.
## Testing
Add regression coverage for provider and auth switches, credential rotation, legacy and mismatched cache entries, conditional TTL renewal, and an account switch during cache storage. Verify that API-key requests do not inherit a ChatGPT catalog's default `service_tier`, while explicit tier selection still works.
GitOrigin-RevId: e15d7ffff238d951d7a1c6a68381cbb479994146
## What changed
Add a SHA-256 identity derived from provider routing, headers, and authentication scope. Return it with each model catalog response and persist it in `ModelsCacheEntry`. ChatGPT credentials with stable account and user metadata retain the same identity across token refreshes; opaque API credentials contribute to the digest.
## Testing
Add identity tests covering account, user, email, plan, auth mode, provider routing, headers, and API credential changes, plus stability across ChatGPT token refreshes. Update cache tests to include the persisted identity.
GitOrigin-RevId: 3f51c6cabcb01bc03505150a768a61dfe5d6569f
## Why
Stopping proxy listeners could leave accepted connections and half-closed tunnels alive after their owning thread was unloaded.
## What changed
Tie HTTP and SOCKS5 connection work, including HTTP CONNECT upgrades, to the lifetime of the proxy listeners. Cancel connections across the main and environment proxies when the handle is dropped, shutdown is requested, or `wait()` is canceled. Explicit shutdown waits for connection cleanup.
## Testing
Add live TCP regression tests for HTTP keep-alive connections and open or half-closed HTTP CONNECT and SOCKS5 tunnels across shutdown, handle drop, and canceled waits. Verify that half-closed tunnels still carry return traffic while the proxy is running, and that repeated thread creation and unloading closes managed proxy tunnels.
GitOrigin-RevId: b523f3b08d73e9ae368f6932952cc930c7b038c9
## Why
Passing `undefined` to a tool could fail JSON parsing because V8 stringifies it as the non-JSON text `undefined`.
## What changed
Return no JSON value for JavaScript `undefined`, so explicit `undefined` tool arguments behave like omitted arguments. Attempts to `store` an undefined value report the existing serializability error and preserve the previous stored value.
## Testing
Add regression coverage for storing `undefined` over an existing `null` value, and extend the current-time tool test to cover `{}`, omitted arguments, and explicit `undefined`.
GitOrigin-RevId: 071050ebb2ecc44c8f08453cf8523b4d21728c7e
## 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
## Why
`TurnComplete` precedes active-turn cleanup, so waiting for it alone can race with rollback in the guardian retained-context fork test.
## What changed
Wait for a thread-scoped idle notification after each parent turn, including optional compaction, before checking rollback boundaries. Consume notifications separately so earlier turns or child completion cannot satisfy the wait. Fail immediately on rollback errors to expose the failure directly.
GitOrigin-RevId: 3caabee45e4e6eb6b2618d84ab68dff7de2a1196
## Why
Evicting entries on every append once history fills invalidates Guardian's transcript cursor, forcing repeated full transcripts instead of deltas.
## What changed
On non-user history overflow, evict at least the oldest half of existing non-user entries, removing more if needed to meet the byte limit. This leaves room for subsequent appends without invalidating the cursor. Preserve the separate user-message retention limits.
## Testing
Update retention assertions and add a regression test that verifies a full transcript after eviction, followed by a delta on the same Guardian thread, while retaining the user's earlier restriction.
GitOrigin-RevId: 7ba18f01e2962d3de35488d981b667ccbb8995c7
## Why
With reasoning effort overrides enabled, compaction used the selected effort even when sampling requests still used an earlier pinned effort. Successful compaction also left that old pin active in the new context window.
## What changed
- Use the pinned request effort for local and remote compaction when it matches the model.
- Resolve fallback models' effort without mutating the live pin, preserving it if compaction fails.
- Reset the pin after successful compaction so the next sampling request establishes the selected effort as its baseline without a redundant `configuration_update`.
## Testing
Add regression coverage for remote compaction success and failure, fallback model effort selection, pin preservation during fallback lookup, and compaction after resuming with overrides disabled.
GitOrigin-RevId: 35e666b0c8026553500715ddbe7bef02cd759f4a
## Why
Reasoning-effort changes should preserve the request baseline while trusted `configuration_update` items carry the selected effort.
## What changed
- Pin request-level reasoning effort for the current model when reasoning-effort overrides are available, including during WebSocket prewarm.
- Re-establish the selected effort after rollback, resume, or a model switch, refreshing the trusted override even when the selection is unchanged.
- Continue using the selected request effort when overrides are unavailable.
## Testing
Add regression coverage for WebSocket prewarm and reconnect, rollback, resume, and model switches. Update transition tests to assert that request-level effort stays pinned while configuration updates change.
GitOrigin-RevId: 89cfee6289543230347b0488d1388190b4da7216
## What changed
- Add feature-gated `/voice`, `/voice mute`, and `/voice stop` commands with local WebRTC audio and app-server signaling.
- Show live transcripts, conversation status, and microphone and speaker levels. Preserve captions and undelivered answers across thread switches.
- Speak final answers from voice handoffs while keeping delegated reasoning and commentary hidden and typed answers unspoken.
- Retry eligible startup failures once and clean up voice sessions on thread switches and disconnects.
- Stop voice and block late handoffs after a misalignment policy violation. Remove realtime event payloads and spoken text from receipt and debug logs.
## Testing
Add coverage for voice command mapping, rejected starts, disconnect cleanup, delegated final-answer speech, late handoff rejection, and transcript and footer rendering.
GitOrigin-RevId: 11def1f86b0e023b21d0d92072d6636ccad89815
## What changed
Represent denied read paths and globs with `PermissionContext` and render them through a sync-only section in `codex-guardian-context`. Keep policy resolution in the host and preserve the existing permission warning in Guardian review prompts.
## Testing
Extend registry tests to verify permission sections appear only for synchronous reviews. Extend the session reuse test to check that resolved denied paths and globs appear in both the initial review request and the next review's delta.
GitOrigin-RevId: a966a14b367f1eedb5a577f7ed74a869559ae646
## Why
A code-mode `exec` wrapper and its nested tool calls each advance Guardian's score lag. Counting the unscored wrapper against its own nested approval can trigger a synchronous review sooner than needed.
## What changed
Track originating response items and approval tool-call IDs so cached approvals discount their own wrapper when it is newer than the latest score. Preserve wrapper identity across yields and waits, and retain the full lag when provenance is missing or evicted. Other wrappers and scoring failures still count.
Use the current `write_stdin` call's identity for approval freshness, and omit tool-call identity for `execve` intercepts that only retain the launch ID.
## Testing
Add coverage for wrapper-specific discounts, already-scored wrappers, missing and evicted provenance, identity across code-mode resumes, and approval identities for stdin writes and `execve` intercepts.
GitOrigin-RevId: 4002a06d64c4e1e0a13c072303503d6ddfacad09
## Why
Configured MCP servers must not be able to request user verification, even when they reuse the hosted apps server name. Local verification identity selection also needs to distinguish a user's workspace memberships.
## What changed
- Advertise `userVerification` only to the host-owned apps MCP server and cancel verification requests from other servers before prompting the client.
- Add `CodexAuth::get_chatgpt_account_user_id()` to read the access token's opaque `chatgpt_account_user_id` only when its workspace matches the selected account. Missing or malformed claims return no identity, without falling back to another user ID or breaking ordinary authentication.
## Testing
Add coverage for capability filtering, rejection of configured servers including those using the hosted apps name, and account-user identity selection with malformed or mismatched claims. Add an MCP round-trip test showing that verification waits for a client response even in full access mode, returns the supplied proof, and discards response metadata.
GitOrigin-RevId: 156e83d5a0302c013b85e564b46b4bfe858cbdb0
## Why
After a cold resume and compaction, the subagent roster omitted children whose threads had not been loaded.
## What changed
Build the multi-agent v2 roster from registered direct children and render their full agent paths. Prioritize loaded children, sort alphabetically within each group, and cap the rendered roster at eight agents and 1,024 bytes. Preserve the existing behavior for other multi-agent versions.
## Testing
Extend the cold-resume integration test to check that post-compaction context includes unloaded children, excludes grandchildren, and lists a loaded child before an alphabetically earlier unloaded sibling.
GitOrigin-RevId: 745c1622133b9c01e61f4702e4b2ef6255417f39
## Why
A standalone root forked from a worker needs its inherited user instructions for Guardian review, including after compaction. Parent input counters belong to a different thread, and omitted parent answers may have restricted an inherited authorization.
## What changed
- Adopt inherited user instructions into thread-owned retained context for standalone roots, recovering surviving checkpoint messages when needed.
- Keep inherited instructions before local evidence without sharing local acceptance counters, and preserve that distinction during reconciliation and rollback.
- Mark parent verified answers as incomplete and treat recovered checkpoint instructions as incomplete excerpts.
## Testing
Add coverage for standalone forks from copied history and truncated checkpoints, retention through compaction and resume, inherited/local ordering collisions, and rollback scope.
GitOrigin-RevId: bf716e224a1d29d6c528ef0dd7cdb118a413a08c
## Why
Incomplete retained checkpoints can omit root user instructions that still survive in live history. Queued input can also reach model history after a later-accepted answer, so recording order cannot reliably order grants and restrictions for subagent authorization reviews.
## What changed
- Reconcile retained evidence with surviving local user messages using source identity and persisted acceptance order, including answers present only in the checkpoint.
- Preserve checkpoint gaps and mark evidence incomplete when recovered instructions lack an order or conflict with an existing order.
- Restore the input-order counter from surviving local metadata so new instructions sort after recovered evidence, even without a retained checkpoint.
## Testing
Add unit coverage for source matching, acceptance ordering, persistent gaps, conflicting orders, and counter restoration. Extend subagent authorization tests to cover checkpoint resume, queued approvals, missing sources, and a subsequent revocation.
GitOrigin-RevId: 8bfbfd2c797d725796187e5cecf7f3f11a5f3380
## Why
`TurnComplete` arrives before the active turn is cleared, so submitting a
rollback immediately can race with turn cleanup.
## What changed
Wait for the thread-idle callback with a 10-second timeout before rolling back
in the first-turn model-change and generated-image tests. Fail immediately on
an error event while waiting for `ThreadRolledBack`.
GitOrigin-RevId: c17b35d709b2c74361dd7933506ae192464ea4e8
## What changed
- Use `decide_approval` for MCP elicitations, carrying the effective approval policy, reviewer, and synchronous-review requirement into the decision.
- Preserve unsupported form and URL elicitations for user review.
- Use `computer_use_review_required()` for review evidence, session policy, and turn metadata so model policy takes precedence over the legacy flag.
- Derive strict-review notifications from each assessment's review reason.
## Testing
Add coverage for model policy precedence, user and full-access modes, sensitive elicitations, independent code-mode and nested-tool policies, cached score reuse, and user review of unsupported elicitations.
GitOrigin-RevId: d0a9c40572dca7b3dbf876230d2162b72728084d
## Why
Concurrent parent compaction can remove evidence between Guardian checkpoint selection and prompt construction. New user instructions or answers received during a review can also invalidate an approval based on earlier authorization.
## What changed
- With `GuardianThreadContext` enabled, use the same parent history snapshot for checkpoint selection and prompt evidence.
- Cancel completed allow decisions if the owning session's user-message revision or root authorization version changed during the review, even without cacheable review evidence.
## Testing
Add regression coverage for evidence preservation during concurrent compaction and aborted approvals after new user instructions or verified answers. Extend reviewer context rollover coverage to exercise `GuardianThreadContext`.
GitOrigin-RevId: 1c2c82197a27c0d3d45b6fe08d200a835d80cc30
## 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
When no healthy pooled WebSocket is available, classification waits for a new connection to open and can stall on its handshake.
## What changed
- Use HTTP streaming when no healthy idle WebSocket is ready, and replenish the pool in the background with a five-minute cooldown after connection timeouts.
- Share concurrency limits and the sampling retry budget across both transports, and bound the wait for HTTP response headers.
- Cancel superseded requests while awaiting response headers and stop SSE polling when the consumer closes.
## Testing
Add coverage for HTTP fallback and recovery after cooldown, shared transport capacity, stalled response headers, and cancellation before headers or during body draining. Update sampler and extension tests to cover fallback after socket expiry, authentication changes, and transient failures.
GitOrigin-RevId: 0b23ccc1bfb2dfdbc8d2791d097706cd4dd44f39
## 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
## What changed
- Handle `openai/userVerification` requests through `openai/elicitation/create` when the client advertises `userVerification` support.
- Validate request fields, size limits, and base64url encoding. Require a correctly shaped, bounded proof for acceptance; cancel invalid acceptance responses and discard proof material on decline or cancellation.
- Handle request and service cancellation, including cancellation received before request dispatch. Bound early-cancellation storage and cancel new verifications when capacity is exceeded.
- Keep verification inactive in Codex: cancel requests without prompting until the typed app-server and UI path is available.
## Testing
Add tests for request and proof validation, malformed modes, cancellation races and capacity limits, timeout-pause cleanup, and independent concurrent requests. Add integration coverage showing that verification does not prompt or prevent tool and turn completion before activation.
GitOrigin-RevId: 6313c1be40fae0b33cc3ce0f8fe025b4124ed2ef
## 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
