## 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
## Why
Existing threads retain their model provider configuration, which can stop matching managed requirements after those requirements change.
## What changed
- Check retained providers against current managed `model_provider` and `model_providers` requirements before turn start/steer, review, compaction, manual queue start, and active goal updates. Reject requests when requirements cannot be loaded or no longer match; provider mismatches prompt users to restart Codex.
- Load managed requirements independently of user, project, system defaults, and thread configuration, and resolve Bedrock provider overrides before comparison.
- Keep interrupt, realtime stop, and goal pause/clear available. Realtime connections use separate routing and are outside these checks.
- Make detached reviews inherit their parent thread's configuration.
## Testing
Add unit and integration coverage for provider selection and definition changes, Bedrock overrides, requirement load failures, unchanged queue and goal state after rejection, and continued operation after local configuration changes. Extend detached review coverage to verify inheritance of the parent's provider route.
GitOrigin-RevId: 21abf08ad2bcc2ea4698209fa33a17485eed4740
## What changed
Replace the selectable personality templates in the bundled `gpt-5.4` and `gpt-5.5` definitions with fixed friendly instructions. Personality selection becomes unavailable for these models in the TUI, and submitted turns omit the personality override. Remove personality overrides from Python SDK examples and the walkthrough notebook.
## Testing
Update core and TUI tests to cover fixed friendly instructions, ignored pragmatic updates, unavailable personality selection, and omitted turn overrides. Preserve coverage for selectable personalities in legacy catalogs, and add coverage for resumed legacy sessions and explicit empty instruction overrides.
GitOrigin-RevId: 869a71445584272405fcbd1325efc31c224808c8
## 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
- Accept `disabledPluginIds` in `thread/settings/update` and `turn/start`. A supplied list replaces the saved selection; omission or `null` preserves it, and `[]` clears it.
- Return the selection in thread start, resume, and fork responses and `thread/settings/updated` notifications. Update generated schemas and client types.
- Restore disabled plugin IDs from the history retained at the requested fork boundary, preserving explicit overrides.
The selection persists across resume but does not yet filter plugin capabilities.
## Testing
Add coverage for replacing, preserving, and clearing selections without inference; turn-start notifications; resume; and fork boundaries across legacy and paginated history, with loaded and restarted parents. Add a core regression test for history restoration and explicit clearing.
GitOrigin-RevId: 654a8c2a0527228d422c0dd4919228447e2663db
## 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
## What changed
After resolving startup configuration and model defaults, reject `features.token_budget.use_history_notes_extension` when the starting model lacks `supports_experimental_context`. Return an error directing users to disable the option or select a compatible model.
## Testing
Add startup coverage for explicit configuration and model defaults, verifying rejection for unsupported models and successful activation for supported models and standalone token budgets. Update history-notes test fixtures to declare experimental context support.
GitOrigin-RevId: abf1a024efc5acf97cfc858fbb93821363769dc0
## Why
The trusted UI host needs the local credential's public metadata to complete backend registration. `userVerification/enroll` previously returned only `credentialId`.
## What changed
- Return `algorithm` and `publicKey` for newly created or reused credentials. The algorithm is `ecdsaP256Sha256X962`; the public key is unpadded base64url SPKI-DER.
- Keep both fields optional in the protocol for compatibility with older app-servers, while current servers populate both.
- Document caller-owned backend registration and revocation, including checking metadata, signing an enrollment challenge with `userVerification/verify`, matching credential IDs, and preserving the authenticated account throughout registration.
## Testing
Add protocol coverage for absent or null metadata and populated-response round trips. Add an RPC assertion for enrollment metadata and extend the local enrollment test to check metadata when creating and reusing a key.
GitOrigin-RevId: f0726e8c430e27559e1a01ba2ea635993cbeba09
## 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
Enterprise MCP authorization must remain controlled by host, user, or managed configuration. Project settings and plugin declarations must not redirect enterprise credentials or downgrade the selected authentication mode.
## What changed
- Add `auth = "ema_auth"`, shared `mcp_enterprise_managed_auth` IdP configuration, and per-plugin enterprise registration settings.
- Require enterprise registrations to come from one non-project configuration layer, preserve managed IdP precedence, and reject project overrides that change authorization or re-enable disabled enterprise servers.
- Add the disabled-by-default `use_xaa` feature flag and require non-project opt-in or a managed requirement.
- Reject plugin declarations that select `ema_auth`. Keep EMA connections unsupported and block ordinary MCP OAuth login and credential fallback for this mode.
- Extend the configuration schema and serialization for the new settings.
## Testing
Add coverage for IdP precedence, incomplete registrations, alternate credential validation, project-only opt-in, plugin self-declaration rejection, configuration round-tripping, and trusted-project attempts to downgrade enterprise auth to OAuth or ChatGPT auth.
GitOrigin-RevId: f193bdfda74208c98e496a23bf2916955b131a1c
## What changed
Add `serverCapabilities` to `mcpServerStatus/list` responses in both `full` and `toolsAndAuthOnly` modes, including thread-scoped reads. Return the initialized server's capabilities object, including its `extensions` map, or `null` when unavailable.
Capture capabilities during initialization so they remain available when tool discovery fails. Clear them on each new connection attempt and keep them independent of shared tool caches. Update the protocol schemas, generated TypeScript and Python types, and documentation.
## Testing
Add coverage for extension capabilities surviving tool-discovery failures in both detail modes. Extend existing tests to check advertised extensions, absent capabilities after initialization failure, and serialization of unavailable capabilities as `null`.
GitOrigin-RevId: 8e9d67c10fac3a54e82bef8be5d99caaf82597d1
## What changed
Add an app-server integration test for `requirements.toml` with `unified_exec = false` and `shell_tool = true`. Verify that:
- The model receives `exec_command` without `write_stdin`.
- Command approval carries the expected thread, item, and environment IDs.
- Accepting approval completes the command and turn successfully.
- The model receives command output without a running session ID.
GitOrigin-RevId: 67977c20b9b206e210807d0ce1e305259d25b7ba
## Why
Unrecognized settings can be silently ignored, leaving typos or deprecated configuration unnoticed.
## What changed
- Collect warnings for unrecognized fields in effective configuration and requirements layers, including unknown feature keys in configuration.
- Report sources and field names without configuration values, show up to three entries, and provide migration hints for `network_proxy`, `allowed_permissions`, and `include_view_image_tool`.
- Emit project-specific warnings when starting a thread and suppress repeated startup warnings in the app server and TUI.
## Testing
Add coverage for merged configuration, disabled layers, startup and project warning delivery, omission of configuration values, and warning deduplication.
GitOrigin-RevId: 464cef87882502b19865ae10b50b6f82defb7296
## 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
Running root threads retained their startup global instructions, so edits to global `AGENTS.md` files did not take effect during an active session.
## What changed
- Reload global instructions when capturing model-request context, including after tools within the same turn. Apply changes without repeating unchanged instructions or rediscovering repository instructions when the environment and trust level are unchanged.
- Preserve the last successful global instructions on read failures, suppress recurring warnings until recovery, and clear instructions when their source is removed or blank.
- Serialize refreshes and allow cancellation without blocking subsequent requests.
- Give new subagents the parent's applied instruction snapshot and update Guardian reviewer reuse to account for refreshed instructions.
## Testing
Add regression coverage for live edits and removal, read failures and recovery, warning suppression, cancellation, subagent inheritance, and Guardian reviewer reuse. Update resume, fork, and compaction tests to verify refreshed instructions.
GitOrigin-RevId: f7e9b399740fa4f45e482c070f6e901ee7cf85cd
## What changed
- Support `model_provider` and `model_providers` in managed requirements. Required selection overrides local and session configuration; each required provider definition replaces the corresponding local entry, including its authentication and headers.
- Merge provider requirement fragments before validation, preserving source-relative `auth.cwd` paths. Reject invalid cloud provider definitions before replacing the cached bundle, including unsupported Bedrock overrides.
- Expose `modelProvider` and `modelProviders` through the configuration requirements API and generated schemas. Reject writes to managed provider settings and omit their local origins, including for provider IDs containing dots.
## Testing
Add tests for requirement precedence, authentication fragment merging, path resolution, cloud cache preservation, and read-only configuration RPCs. Integration tests verify that model discovery and inference use the required gateway and ChatGPT authentication without leaking local headers, and that provider requirements survive configuration rebuilds.
GitOrigin-RevId: d1448604d4ef5662ebb5df7b693712d3b8ad6d54
## What changed
Allow app-server to advertise `openai/elicitation.userVerification` and route verification requests to local stdio clients named `Codex Desktop` when `experimentalApi` is enabled and the device supports verification. Preserve support for the in-process `codex-tui` client.
Document the experimental verification API, local credential lifecycle, transport restrictions, and GUI requirements for cancellation and late proofs.
## Testing
Extend activation tests to cover desktop capability advertisement and request eligibility, including rejection for other transports, unrecognized client names, missing opt-in, and unsupported devices.
GitOrigin-RevId: ba4fd4b83b9c24541df3a490396d6c715e7b7433
## 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
Truncating action arguments can leave approval reviewers evaluating incomplete actions. Large actions need complete review input and explicit handling when they exceed the review budget.
## What changed
- Remove action truncation and the fixed synchronous action byte limit. Admit complete actions against the whole-request budget, splitting long text losslessly into bounded transport parts and accounting for their framing.
- Route actions exceeding the asynchronous action budget to synchronous review. Prevent cached scores from covering oversized calls, including expanded approval arguments, while allowing later small actions to recover score reuse.
- Request user approval when optional review exhausts its local input budget. Keep required review and compaction service failures closed to approval, and retire exhausted review sessions.
## Testing
Add coverage for complete large-action delivery, optional user fallback, required-review denial, subsequent review recovery, async overflow through MCP approval routing, and lossless text splitting with budget accounting.
GitOrigin-RevId: 08f06e68a94b2f779480dd6b6cf5bc30b241f6dd
## What changed
- Add `thread/attachment/add`, `thread/attachment/list`, and `thread/attachment/remove` to manage durable resource references without loading the owning thread or changing conversation history.
- Identify attachments by thread, `attachmentType`, and `identityKey`. Repeated adds return the existing attachment; repeated removals succeed without emitting another update. Listing supports cursor pagination.
- Broadcast `thread/attachment/updated` after creation or deletion, after responding to the requester. Serialize attachment mutations with thread lifecycle operations and reject stores that do not support attachments.
- Update protocol schemas, TypeScript and Python bindings, documentation, and TUI notification handling so attachment updates do not add untracked threads to the agent picker.
## Testing
Add coverage for unloaded threads, pagination, idempotent addition and removal, reattachment, invalid inputs, unsupported stores, response-before-notification ordering across clients, and TUI notification routing.
GitOrigin-RevId: 0d29cf903afd4e931a70a9cf96300475213b34aa
## Why
Stdio shutdown can hang on open pipes or blocked I/O, and Unix `SIGTERM` needs to run connection cleanup so owned commands terminate and session-end hooks execute.
## What changed
- Handle `SIGTERM` on a dedicated signal thread and close the stdio connection through the existing cleanup path.
- Move blocking stdin and stdout operations to dedicated threads so they do not hold the Tokio runtime open. Cancel message forwarding on `SIGTERM` to release blocked producers.
- When shutdown signal handling is enabled on Unix, start a shared 45-second watchdog on EOF or `SIGTERM`. Preserve the first deadline and exit with status `1` if cleanup or runtime teardown stalls, even when logging is blocked.
## Testing
Add Unix integration coverage for shutdown with open pipes, blocked stdout, blocked stderr, and a stalled filesystem write. Verify command and child-process termination, preserve the EOF deadline when `SIGTERM` follows, and extend session-end hook coverage to `SIGTERM`.
GitOrigin-RevId: 43a80b8277eb50519cdc293eb3b5dc2cad00b3aa
## Why
Session isolation relied on Guardian source attribution. An explicit policy lets callers control inherited capabilities independently of how a session is attributed.
## What changed
- Add `SessionIsolation` with default `Inherit` and opt-in `Isolated` modes, captured at session startup through `ExtensionDataInit`.
- Use the policy to control inherited instructions, extensions, execution rules, and MCP resources. Isolated sessions retain managed execution rules and omit executor-discovered MCP servers.
- Explicitly isolate Guardian reviewers while preserving source-based fallback for older callers and saved reviewers.
## Testing
Extend delegate tests to cover isolation independently of attribution, update execution-policy coverage to supply the explicit policy, and assert that managed reviewers do not inherit the parent's configured MCP tools.
GitOrigin-RevId: f0ab42fa2f0237860ec661e72693ab191216afbf
## Why
MCP tool and connector descriptions were included in required action JSON, consuming review input budget even though they are optional metadata.
## What changed
Move `tool_description` and `connector_description` into an optional, explicitly untrusted `guardian_tool_descriptions` fragment. Limit each description to 400 estimated tokens, escape closing tags, and allow budget enforcement to omit the fragment while retaining the required action JSON. Preserve nested arguments such as `arguments.description` and mention tool descriptions in the budget omission notice.
## Testing
Add regression coverage for oversized descriptions, escaped closing markers, and budget eviction without changing action arguments. Update MCP approval and elicitation tests to verify descriptions appear separately from the action JSON.
GitOrigin-RevId: 30734567c2ebc4b180110276c83d79ddb315ceab
## Why
Transient rate limits can end automatic approval reviews prematurely, and review failures currently report high risk even when no assessment completed.
## What changed
- Retry rate limits and recoverable exhausted-stream errors, while excluding non-transient HTTP failures.
- Preserve server retry delays after stream retries are exhausted and honor them within the review deadline. Scope retry advice to the current turn so reused sessions cannot apply stale delays.
- Keep failed reviews denied, but leave risk and authorization unset and explain that the review could not complete without declaring the action unsafe.
## Testing
Add an integration test covering rate-limit recovery through approval and tool execution, asserting that the action executes exactly once after approval. Update failure assertions to check absent assessment fields and the review-failure explanation.
GitOrigin-RevId: 1163cfde35c6b8eb23b6f24f1f24461b86ded838
## What changed
Add the default-off `api_key_model_discovery` feature and expose it through app-server experimental feature enablement, respecting user configuration overrides.
When enabled, fetch OpenAI API-key model metadata from the Codex backend, honoring explicit provider base URLs. Treat remote catalogs containing visible models as authoritative. When disabled at startup, skip discovery requests and cached catalogs and retain bundled models.
## Testing
Add coverage for feature enablement and user overrides, cached catalogs across sessions, provider routing, and API-key `model/list` results. Extend coverage for remote instructions and auth-specific cache isolation.
GitOrigin-RevId: 4b189c37c615a7f808cb6ff5f0858a9a55f36ebc
## Why
Attachment mutations must coordinate with thread deletion so queued requests cannot use metadata belonging to a deleted thread.
## What changed
- Add typed `ThreadStore` operations for idempotent attachment creation, paginated listing, and removal, with capability detection and unsupported defaults.
- Implement attachment operations for SQLite-backed `LocalThreadStore`, including unloaded threads, and preserve invalid-request and missing-thread errors.
- Coordinate attachment mutations with lifecycle locks and move SQLite cleanup into thread-store deletion. Remove state rows only after rollout deletion, preserving retries after cleanup failures.
- Give the in-memory store ownership of its associated SQLite cleanup and remove duplicate cleanup from the app-server.
## Testing
Add coverage for attachment pagination and idempotency, unsupported stores, error categories, lifecycle exclusion, mutations queued behind single and batch deletion, cleanup failure retries, and in-memory state cleanup. Extend the app-server descendant deletion test to verify SQLite rows are removed.
GitOrigin-RevId: f0157538c7c5c2ee1362ce40eac157101c5d4505
## Why
Remote-control connections and queued operations must not carry over to a different signed-in user or account. Token refreshes for the same identity should preserve the live relay connection.
## What changed
- Scope relay state and authentication recovery to a login lifetime. Retire the session on logout or identity changes and leave remote control disabled until enabled again.
- Reject stale incoming messages and queued RPCs, and cancel pending remote-control operations when their authentication owner changes.
- Start replacement sessions with fresh client, replay, and enrollment state, and prevent retired sessions from publishing status into their replacements.
- Serialize enrollment and preference persistence across sessions, retaining write permits through caller cancellation and draining admitted writes on shutdown.
## Testing
Add regression coverage for same-owner refreshes, user and account changes, stale pairing and client-revocation work, unauthorized enrollment recovery after logging in again, and persistence during cancellation.
GitOrigin-RevId: 5e6ecd23588aab1e2e6168a21f575fb24bbb341c
## 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
## Why
The elevated Windows sandbox requires effective `:root` read access and cannot safely enforce policies that deny reads at the filesystem root.
## What changed
- Validate root read access before elevated setup, service provisioning, and setup refresh, rejecting root-denying globs before expansion.
- Reject filesystem-root deny-read ACL targets after canonicalization and check the opened handle before applying an ACL, so aliases cannot bypass the root guard.
- Read and update deny ACLs through the same handle, and allow an existing deny ACE to be recognized when write access to the ACL is unavailable.
## Testing
Add regression coverage for default root denial, root-denying globs, allowed root reads with narrower deny rules, handle-based root detection, and reading existing deny ACEs without `WRITE_DAC`.
GitOrigin-RevId: b904e7cdbc09ee0147e1818c898b0382b5820c1b
## What changed
Add nullable `promptHash` to the upload response, populated from the uploaded `prompt_hash` tag. It identifies the whitespace-normalized SHA-256 of the session base instructions, excludes later developer messages, and is `null` when the reported rollout has no prompt metadata.
Update the protocol schemas, precomputed exports, and generated TypeScript and Python types.
GitOrigin-RevId: 6fa70fbe7a06604ac1cd0ea363eb4f192083dad9
## Why
Automatic goal continuations can repeatedly return empty final answers without
making progress. Stop this loop by marking the goal as `blocked` after three
consecutive empty turns with no other activity.
## What changed
- Observe completed turn items through a new `on_item_completed` lifecycle hook.
- Track empty final answers only for automatically admitted goal turns, resetting
the streak on activity, user turns, or goal changes.
- Preserve normal turn completion and streamed message deltas when blocking a goal.
## Testing
Add accounting coverage for the three-turn threshold and streak resets, plus
app-server tests for empty continuations and recovery through final-answer text,
commentary, or tool activity.
GitOrigin-RevId: 4b9d2cb2e306b0adc316972429cc35000115b88b
## Why
Hosted Codex Apps shared the `mcp_2026_07_28` protocol setting with other MCP servers, preventing independent protocol selection.
## What changed
- Add `features.codex_apps_mcp_2026_07_28`, disabled by default, for the host-owned HTTP `codex_apps` server. Enabling it attempts 2026-07-28 discovery with Legacy fallback.
- Keep other servers, including third-party registrations with Apps-like names or URLs and local stdio servers, governed by `mcp_2026_07_28`.
- Support the new flag through `experimentalFeature/enablement/set` and refresh protocol settings in existing sessions. Track protocol mode per server when deciding whether to reuse connections.
## Testing
Add coverage for independent feature and protocol selection, hosted event-stream protocol selection, standalone Legacy defaults and discovery fallback, and runtime enablement refreshing an existing app-server thread.
GitOrigin-RevId: 640e8e251f0c45e5f4829cc2b73c3082cf42f715
## Why
Saved threads need to resume after a managed daemon restart so active goals can continue without waiting for a client to reconnect.
## What changed
- Consume the recovery snapshot at startup and restore threads in the background through the shared cold-resume path.
- Trigger idle lifecycle work without attaching a client subscription, and leave already-loaded threads untouched.
- Continue recovery after individual thread failures and abort background recovery during shutdown.
## Testing
Extend the daemon restart integration test to verify goal continuation before client reconnection, restored conversation history and tools, idle-thread restoration, and recovery snapshot consumption. Include malformed snapshots and an invalid thread ID.
GitOrigin-RevId: 90e7b8f74ddc0ae327bacde1b2108b9749c65f2a
## What changed
- Atomically save successfully persisted, loaded root thread IDs to `app-server-daemon/loaded-threads.json` during graceful managed shutdown, excluding ephemeral threads and threads pending unload.
- Clear stale recovery state at startup and around daemon lifecycle operations, including explicit stops and fresh starts.
- Probe support for `--managed-daemon` before launching managed app servers, and clear recovery state best-effort when launching older binaries.
- Keep forced shutdown responsive while saving the snapshot and log snapshot failures without preventing shutdown.
## Testing
Add coverage for snapshots after active turns finish, forced shutdown without a snapshot, excluded threads, snapshot write failures, and recovery-state cleanup for stops, fresh starts, and legacy launches.
GitOrigin-RevId: 422dc32b85355510f7e4c57b7540597b47d9f0b2
## Why
`update_goal` only accepted `complete` and `blocked`, preventing the agent from pausing a goal in response to an explicit user request.
## What changed
- Accept `paused` and account for final goal progress when pausing, with budget limits taking precedence.
- Update tool instructions and goal prompts to allow pauses only at the user's explicit request, report the returned status, and stop goal work. A later resume revokes the pause request.
## Testing
Extend coverage for pause accounting, budget-limit precedence, rejection of resume and system-limit statuses, and preservation of a tool-paused goal when resuming a thread.
GitOrigin-RevId: c3c15a51f848ce6eb65854d51b1a1bc75bb456a7
## Why
Loaded threads, including idle threads whose rollout files are still deferred, need to survive a managed daemon restart. Shutdown must also remain forceable when rollout I/O is blocked.
## What changed
- Add a hidden `--managed-daemon` option for app-server Unix socket transports. After active turns and admitted requests drain, save loaded persistent root threads before exiting.
- Skip ephemeral threads, non-root agent threads, and threads pending unload. Log persistence failures and continue saving other threads.
- Apply shutdown admission checks to thread and turn settings updates, thread deletion, and archiving.
- Keep force signals and daemon shutdown requests responsive during persistence. Return `AppServerExit::Forced` so executables can exit without waiting for runtime teardown.
## Testing
Add integration coverage for resuming active and idle threads after restart, forcing shutdown during active work, and forcing shutdown with a blocked rollout writer. Extend shutdown rejection coverage to deletion and settings updates.
GitOrigin-RevId: 4344e97d39f9f80c5d84c41c17300fd6aa99b4cc
## 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
## What changed
Move the synchronous review loop, outcome mapping, deadline helpers, and session pool into `codex-guardian-reviewer`. Core supplies adapters for evidence capture, authorization checks, session creation, and event publication through the new host interfaces.
Have `guardian-v2` initialize the reviewer pool and host separately, with the pool managing prewarming, session reuse, concurrent forks, invalidation, and shutdown.
## Testing
Extend the app-server reviewer lifecycle test to cover interrupted concurrent reviews as well as completed reviews, including resuming a reviewer after parent shutdown. Adapt core reviewer tests to use the pool and factory interfaces.
GitOrigin-RevId: 2d69bd20c169b20534764b98cbdb63f38564a530
## 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
## What changed
- Let higher-priority providers in `features.network_proxy.credentials` displace lower-priority providers with overlapping `env` sources, including in profiles. Preserve inherited settings when providers swap sources, and compare environment names case-insensitively on Windows.
- Preserve provider definitions across ordered batch remaps and persist displaced-provider removals without overwriting unrelated sibling updates.
- Validate remapped providers using the credential broker's compilation rules before persisting writes, while allowing incomplete drafts and explicit deletions.
- Omit displaced providers from config origins and report writes overridden by another provider's source ownership.
- Build trusted credential-broker configuration before merging managed layers for project discovery, preserving remapped providers' environment protections.
## Testing
Add unit and config RPC regression tests for source precedence, source swaps, ordered edits, concurrent sibling updates, atomic rejection of invalid remaps, persistence, and override reporting. Add a macOS managed-config regression test for remapped provider bindings during project discovery.
GitOrigin-RevId: b7d402727acf4e5b0f25946db1cf18811f5e2679
## Why
Guardian request and section cost distributions need shared bucket boundaries across synchronous and asynchronous reviewers so their measurements align.
## What changed
- Add `histogram_with_boundaries` to session telemetry and extension metrics while preserving session attribution.
- Use shared request-token buckets up to 2,000,000 tokens and section-cost buckets up to 16,777,216 for both review paths.
## Testing
Extend telemetry tests to verify explicit bucket boundaries and sample counts, and Guardian integration coverage to check exported request and section metric bounds for both synchronous and asynchronous reviews.
GitOrigin-RevId: e34f6972b3418bac3b061939b62eeeccaec5a299
## Why
Diagnostic attachment reads assume the queued file path still exists and contains plain bytes. Compressed rollouts can therefore be omitted when only the logical `.jsonl` path is available, or attached as compressed data when a `.jsonl.zst` path is supplied.
## What changed
- Read rollout attachments through a bounded decoder that resolves plain or compressed representations without materializing a durable JSONL file.
- Use canonical `.jsonl` filenames for attachments and app-server report metadata, while preserving filename overrides.
- Apply size limits to decoded bytes and preserve JSONL prefix truncation.
## Testing
Add regression tests for compressed attachments, representation changes after queuing, plain-sibling preference, filename overrides, decoded size limits, truncation, nonregular files, and unrelated `.zst` attachments.
GitOrigin-RevId: b30f7dd08a741b0c99283460a1ce8933d2920ddf
## What changed
- Record per-section text bytes, estimated text tokens, image bytes, and image counts for synchronous reviews and asynchronous scoring without logging evidence payloads.
- Emit estimated request tokens through `codex.guardian.context.request_tokens`. Synchronous estimates include assembled history, instructions, tool definitions, and output format, and measure the full logical request before WebSocket delta generation. Asynchronous estimates cover the assembled input.
- Add shared context budgeting helpers, including conservative image token reservations independent of encoded payload size and model-aware input limit calculation.
## Testing
Add coverage for separate text and image accounting, image estimates independent of encoded size, and section estimates that bound delivered messages. Extend asynchronous scorer and app-server tests to verify cost metric emission.
GitOrigin-RevId: aed45ecd9c23706f88caa51f2a4f2c77872d3bdb
## 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
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
## 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
New client requests and automatic continuations can start more work while the app-server is draining. Shutdown also needs to account for requests still preparing or submitting work before they appear as running turns.
## What changed
- Close a shared admission gate when shutdown begins, rejecting new turn work and thread lifecycle changes with the server-draining error.
- Apply the gate to automatic turn starts, including queued work and goal continuations, and recheck serialized turn requests before execution.
- Wait for admitted requests and running turns to finish, while preserving forced shutdown. Keep reads and `turn/interrupt` available during drain.
## Testing
Add coverage for admission permit tracking, discarded queued requests, forced shutdown, and WebSocket drain behavior, including request rejection, interruption, and suppression of automatic continuations.
GitOrigin-RevId: 1bc108aa00a427cfa41974fa9ec60754c2b968c2
