## Why
Refreshing installed Apps without a thread should update the tools available to existing threads on their next turn.
## What changed
- Publish live tool catalogs to clients with matching transport, auth, protocol, and listing settings within the same account and home directory. Ignore the thread attribution header when matching scopes.
- Adopt updated tools before catalog reads and new calls, preserving running calls and rejecting calls prepared against an outdated catalog revision.
- Keep the newest successful fetch per scope so older refreshes cannot overwrite newer tools, and exclude disk snapshots from live updates.
## Testing
Add regression coverage for refresh propagation to an existing thread without another tools listing, scope and account isolation, out-of-order refreshes, late client startup, and running versus stale prepared calls.
GitOrigin-RevId: 7a5ee34e23742ce374c6647dc8928b76ea622448
## 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
Allow v2 memories to build in the background while the selected memory version continues supplying context, and let clients check whether v2 has enough consolidated data and a valid summary to use.
## What changed
- Add `memories.dual_write`, disabled by default, to run v1 and v2 extraction and consolidation concurrently with separate stores and directories.
- Add the experimental `memory/status` endpoint, returning `v2ConsolidatedThreads` and `v2Ready`. Readiness requires a valid v2 summary and a consolidation thread count meeting `minConsolidatedThreads` (default 20, supported range 1–4096).
- Persist the largest thread count from a successful consolidation across pruning and clear it on memory reset.
- Share v2 summary validation between consolidation and status reporting, and tag memory metrics with `memory_version`.
## Testing
Add tests for independent dual-write outputs, preserving existing notes without importing them into v2, and readiness behavior across consolidation ownership checks, missing summaries, configurable thresholds, thread deletion, and memory reset.
GitOrigin-RevId: 54417cc60bf419062401355c0da8c79119995f61
## What changed
- Consolidate v2 rollout summaries into `memory_summary.md` without generating `raw_memories.md` or requiring `MEMORY.md`. Validate the summary's required sections and size below 10,000 UTF-8 bytes.
- Add v2 read instructions for selective history retrieval, evidence-grounded preferences, citations, and explicit memory edits. Split injected instructions into fragments to preserve the complete summary within fragment byte limits.
- Record memory citation usage in the store selected by `memories.version`.
## Testing
Add coverage for v2 consolidation without a handbook, summary validation, version-isolated memory reads, and resetting both memory versions while preserving threads.
GitOrigin-RevId: 1d895fb4a23a973f1a45ba03be07a1f480c10227
## Why
Synchronous approval reviews and asynchronous scoring assemble Guardian evidence separately, duplicating transcript framing and section placement.
## What changed
- Move evidence ordering, framing, and delivery into `codex-guardian-context`, while keeping transcript retention, budgets, and delta cursors with their callers.
- Pass composed messages directly to the asynchronous sampler, preserving roles, annotations, trusted message boundaries, and image placement.
- Reject unsupported synchronous delivery with `SectionError::UnsupportedDelivery` instead of silently dropping content.
## Testing
Add composition coverage for preserving separate messages and rejecting them for synchronous delivery. Extend Guardian integration coverage to check trusted tool and skill messages, mixed text and image evidence ordering, and full and delta review framing.
GitOrigin-RevId: efc06695ee4e2b7400b123b77ef2a21c8bf40646
## What changed
Add `is_worktree` to thread initialization analytics and the `codex.thread.started` metric using validated Git repository metadata. Classify linked worktrees as `true` and primary checkouts as `false`; report an unavailable classification as `null` in analytics and `unknown` in metrics. Subagent initialization analytics leave the field unset (`null`).
## Testing
Add analytics coverage for primary checkouts, linked worktrees, unknown repositories, and event serialization. Extend the account-switch telemetry test to check that the `is_worktree` tag reaches the next account's collector.
GitOrigin-RevId: bc9bcd3c0212c0a123e4bcfed0c7020eef17dda6
## What changed
Represent host-verified tool metadata as `TrustedTool` in `codex-guardian-context` and collect it through an async-only context section. Route Guardian v2 sampling through that section while preserving separate developer-message delivery and the 512-token rendering budget. Omit tool metadata from debug output.
## Testing
Move the rendering-budget test into the shared crate, extend registry coverage for async-only collection and debug redaction, and narrow the scoped approval test to messages tagged `guardian.trusted_tool`.
GitOrigin-RevId: ee7cb4e9b9ceced70438cb58060d1a2973e1dc6a
## What changed
- Store the shared `GuardianReviewSessionManager` in thread extension data and let the Guardian extension spawn and fork reviewers through `ThreadManager`, independently of async scorer startup.
- Preserve reviewer reuse, concurrent forks, cancellation, inherited environments, and user instructions. Gate managed reviewer startup on parent registration and remove terminated reviewers from the manager.
- Retain the `guardian` subagent identity in saved conversations. Reject resume of live Guardian reviewers and reject client archive or delete of live owner-managed workers with JSON-RPC error `-32600`; allow normal access after the owner releases them.
- Keep standalone reviewer support for inline delegates and remove duplicated extension prompt and configuration code.
## Testing
Add app-server tests covering reviewer reuse and concurrent forks, inherited instructions and prompt cache keys, live resume and removal rejection, saved reviewer discovery and resume after parent shutdown, and strict Guardian assessment inside an inline review.
GitOrigin-RevId: 4f9893c1ade151eacb4c11ffeae3d9e9ec019187
## Why
The existing `userVerification/*` handlers always returned unavailability, leaving local clients unable to use the native verification provider.
## What changed
- Dispatch status, enrollment, deletion, and challenge signing through an account-scoped provider. Enrollment creates or reuses a local key; it does not register credentials with a server.
- Restrict enrollment, deletion, and signing to stdio and in-process connections, rejecting WebSocket and remote-control callers before parameter validation.
- Bound native work to one operation per service with a 120-second timeout, and propagate in-process caller cancellation. Recheck connection, cancellation, and authentication state before delivering results, including after waiting for response queue capacity.
- Add device-gated verification capability wiring for the experimental in-process `codex-tui` client, with automatic activation still disabled by default.
## Testing
Add tests for local key reuse and deletion, decoded challenge signing, cancellation, authentication changes during verification and response queuing, concurrent worker rejection, and stdio/WebSocket RPC behavior.
GitOrigin-RevId: 7eac15a5ffb049d27bf8fedcfbae19a49a3f6a3d
## What changed
- Introduce `codex-user-verification` with a provider interface for credential status, creation, deletion, and challenge signing. Include typed errors, shared cancellation guards, and hashed account-user key namespaces.
- Add P-256 public-key encoding as unpadded base64url SPKI DER, derive credential IDs from its SHA-256 digest, and redact proof fields in debug output.
- Add app-server helpers to validate challenge and display-text bounds and map provider errors to typed RPC errors without exposing provider diagnostics.
The platform implementation reports verification as unsupported. App-server requests still return typed unavailability, with the message updated to mention build or account availability.
## Testing
Add tests for credential encoding and signature verification, invalid curve points, cancellation across guard clones, stable and distinct account namespaces, and invalid challenge or display values. Update the app-server unavailability test for the revised message.
GitOrigin-RevId: fe4a4eb37c68d7fdc547704e76aa257abf3e9c81
## Why
A fork cutoff can remove the only `TurnContext` recording the source thread's selected multi-agent version. Forking before the first turn must preserve that version, including when the child is resumed before its first turn.
## What changed
Recover the version from the untrimmed source history or loaded parent, independently of permission overrides, and carry it into the fork's session metadata for `last_turn_id` and `before_turn_id` cutoffs.
## Testing
Add regression coverage for forks before the first turn across legacy and paginated history modes, with loaded and unloaded parents and explicit permission overrides. Verify that the child persists `MultiAgentVersion::V2` and still uses the `collaboration` tools after restarting and resuming.
GitOrigin-RevId: d7e30cf8bfdeb4f755fefab3d1d0884964d7c977
## 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
## 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
Route `gpt-5.6-luna` POST requests through `luna_response` using the shared
classifier state in the guardian compaction and rollback test. This gives
HTTP classifier requests the configured mock score instead of treating them
as guardian review or parent requests.
GitOrigin-RevId: 3841705c7ed1ec564662c33f71e1c78e9b960c68
## 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
## What changed
Route managed Windows app-server shutdown through `/daemon/shutdown` on the local control socket. Require the server's PID and acknowledge it before triggering shutdown through the existing drain logic. Enable the endpoint only for managed Windows launches via `CODEX_DAEMON_SHUTDOWN_SOCKET`.
Watch running-turn changes whenever shutdown is requested so socket-triggered shutdown can finish draining. Keep the updater's file-based shutdown mechanism and retain forced termination as the manager's timeout fallback.
## Testing
Add a transport test covering rejection of unmanaged shutdown requests and mismatched PIDs, plus acknowledgment before emitting the shutdown event.
GitOrigin-RevId: 3e95dc1914f61e8a131f9b6fd56b6c63688d1744
## What changed
Add `userVerification/status`, `userVerification/enroll`, `userVerification/delete`, and `userVerification/verify` behind the `experimentalApi` capability. Define request, response, proof, and typed error contracts, export their schemas, and document the API.
All four methods currently return `unavailable` with reason `providerUnavailable`; native verification operations are not implemented by this change.
## Testing
Add tests for experimental opt-in, typed provider unavailability, readiness serialization, and rejection of mismatched error reasons and native diagnostic payloads.
GitOrigin-RevId: a858ab41523c5acec7dbf3cfa7fcab693ac44a8c
## Why
Experimental context activation previously checked the provider and account eligibility without checking model support. Child sessions also inherited token-budget activation from their parent, even when starting fresh with a different model.
## What changed
- Add `ModelInfo.supports_experimental_context`, defaulting to `false`, and enable it for the bundled `gpt-6-astra` model. Require this capability when activating experimental context.
- Snapshot configured token-budget preferences before startup activation. Restore them for fresh child sessions before applying their starting model's defaults, while history forks retain their parent's activation.
- Pass unresolved token-budget preferences to child sessions so they can use their own model's prompts.
## Testing
Extend coverage for unsupported models, model-switch guidance under explicit and experimental activation, and child configuration from both active and inactive parents. Verify that omitted capability metadata defaults to `false`.
GitOrigin-RevId: 02df9e171682267232fa923d5ea3f7af36527808
## What changed
Replace `features.guardian_thread_context` with `features.guardianv2.thread_context` and update the configuration schema. The setting controls thread-owned context for synchronous and asynchronous Guardian, defaults to `false`, and remains independent of `features.guardianv2.enabled`.
## Testing
Update configuration tests to cover the nested setting, profile overrides, and enabling thread context while Guardian v2 is disabled. Migrate Guardian approval, history, and async scorer tests to the new configuration key.
GitOrigin-RevId: 54a91555eb68001e0adedc8a07bdbc5ea2273f9b
## Why
Calling `app/installed` with `threadId` and `forceRefresh: true` refreshed a separate runtime snapshot without updating the thread's tools for subsequent turns.
## What changed
Use the thread's current configuration and refresh its live app tools when a thread is specified. Account for the refreshed snapshot's model-visible tools when reporting `callable`. Requests without `threadId` continue to use a separate runtime for refreshes.
## Testing
Add integration coverage verifying that refreshed tools replace previous tools in subsequent model requests and can be called, and that a failed refresh preserves the last working tools. Extend thread configuration coverage to include forced refreshes.
GitOrigin-RevId: fc13e28a59da00af470cf25c0cde356504e1575b
## What changed
Capture the ID from `response.created` and pass it as `parent_response_id` in Guardian review and classifier request metadata. Clear the current response ID before sampling retries so tool reviews cannot inherit a failed response's ID.
Request Guardian credits with `guardian_credits_requested` on eligible parent requests. Remove the ticket protocol, transport attachment, and ticket-specific body redaction. Keep ordinary app-server client `parent_response_id` values inside `x-codex-turn-metadata` rather than promoting them to Guardian request metadata.
## Testing
Update coverage for HTTP fallback, WebSocket review reuse, missing response IDs, classifier transport retries, and code-mode yield/resume attribution. Extend app-server tests to verify client metadata placement over HTTP and WebSocket.
GitOrigin-RevId: c1665e56382ecec8d260fc2ca0ecd5e20b0b2391
## Why
Reverting a paginated thread can remove the turn context that records its resolved multi-agent version. Preserve that version so a model-selected V2 thread keeps its collaboration tools after reload or a server restart.
## What changed
Pass the live thread's `multi_agent_version` into the thread store and persist it in the replacement rollout's session metadata. When no live version is supplied, retain the existing metadata value. Document this guarantee for `thread/revert`.
## Testing
Add regression tests for model-selected V2 across live reload and cold resume, plus metadata preservation for `V1`, `V2`, and `Disabled` across repeated reverts.
GitOrigin-RevId: bd7d4d76a50d23da16caa2a0631acf10bfa49629
## What changed
Remove the `codex mcp-server` subcommand and the standalone `codex-mcp-server` crate, including its tests, interface documentation, build dependencies, and run recipe.
## Testing
Update the strict configuration test to use `codex exec hello`, preserving coverage for rejecting unknown configuration overrides.
GitOrigin-RevId: 8688b1f41862d7c2073ea2812a257c0087c55d9c
## Why
Plugin updates made by another process do not notify a loaded session's hook runtime, leaving it with stale hooks.
## What changed
Compare the current plugin hook sources and load warnings with those retained by the hook runtime during turn construction. Refresh hooks when either differs so existing sessions pick up external plugin updates.
## Testing
Add an app-server regression test that updates the shared plugin store without notifying the server and verifies that successive turns in the same thread run the installed hooks across an upgrade and a rollback.
GitOrigin-RevId: d3a2653ac4c069d9d8a02f30e21e4506d76a091c
In `guardian_v2_routes_scoped_tool_approvals`, wait for the reviewed
thread's `codex_turn_event` before shutting down the app server. Use the
returned event for assertions instead of looking it up in the
post-shutdown analytics snapshot.
GitOrigin-RevId: 3ba4d37838852842c6caf7701d3abf7c89166a98
## Why
Background and empty-input turns could lack a `root_turn_id`, and detached memory requests omitted turn identity entirely. Tasks without a root could also adopt one from coalesced mailbox input.
## What changed
- Set `root_turn_id` to the task's turn ID at task start unless an inherited or recovered root is already present.
- Stop assigning roots from mailbox input or steering an active turn.
- Give detached memory requests a fresh UUID for both `turn_id` and `root_turn_id`, included in turn headers and client metadata while still omitting session and thread identity.
## Testing
Extend assertions for background turns, empty input, goal continuations, manual compaction, and detached memory requests. Exercise mailbox coalescing with both independent and inherited roots to verify the task keeps its established root.
GitOrigin-RevId: ee0f2f1b43542a9f5884f694c1d94341b476779c
## Why
Clients need a per-thread Daybreak toggle that survives restarts and can be
restored on resume without changing the access program of an active or future
turn.
## What changed
- Add experimental `daybreakEnabled` support to `thread/metadata/update` and
expose the saved value on thread responses.
- Store the preference in SQLite, including for threads without a first turn,
and preserve it through reads, resumes, reconciliation, and restarts.
- Copy the preference when forking a thread while keeping subsequent updates
independent.
- Keep `daybreakEnabled` separate from the per-turn `cyberAccessProgram` field;
app-server does not derive one from the other.
## Testing
- Cover persistence across restarts, cold reads, reconciliation, and forks.
- Verify metadata updates do not alter the access program of active or later
turns.
GitOrigin-RevId: bcf987a9fcd7b0ac8a88b1c8f0df06b33ed8ad6e
## Why
Guardian reviews must not lose user authorization constraints or reuse an
unreadable or incompatible parent checkpoint after compaction.
## What changed
- Retain bounded excerpts of oversized root user messages across compaction,
resume, and rollback, and recover excerpts from legacy Guardian history when
available.
- Require thread-owned Guardian review sessions and asynchronous scoring to
reuse only non-empty checkpoints produced by a compatible review model.
- Fail closed instead of reviewing without the required checkpoint when reuse
is disabled, compatibility is unknown, or checkpoint content is unusable.
## Testing
Expanded retained-context, review-session, asynchronous-scoring, and app-server
coverage for oversized instructions, legacy recovery, model incompatibility,
missing content, resume, rollback, and disabled checkpoint reuse.
GitOrigin-RevId: f30d837197e0d838e656a632109f490c38208f5e
## Why
Guardian reviews need the original user instructions even when compaction or
transcript selection removes them from the active conversation window.
## What changed
- Capture complete user messages in host-owned retained context and include them
as ordered authorization evidence alongside verified answers.
- Omit oversized instructions atomically and emit an explicit incomplete-evidence
notice instead of exposing a potentially misleading partial permission.
- Mark user messages inherited by forked agents so they remain model-visible
without becoming child-local authorization.
## Testing
- Cover retained instructions across compaction, resume, rollback, and agent
forks, including oversized evidence and legacy context behavior.
GitOrigin-RevId: 97122509d818c90d2f87c6a1b29c99c05ad0316e
## Why
Guardian reviews for delegated workers need the current root instructions and verified answers even after the parent context is compacted. Approvals must also become stale when that root authorization changes.
## What changed
- Build bounded root review evidence from retained context, preserving source order and answer scope while prioritizing user instructions over optional assistant context.
- Recover retained instructions from Guardian history after compaction and mark authorization incomplete when required instructions or answers are unavailable.
- Version root authorization in synchronous and reusable review sessions so an allow result is cancelled when its evidence changes.
- Strip parent-only Guardian approvals when forking worker history in retained-context mode.
## Testing
- Cover retained and legacy context modes, oversized evidence, message limits, parent compaction, and authorization changes during review.
GitOrigin-RevId: 658219b7cee08f2752adcea9966268fd21727976
## What changed
- Parse the optional `[browser_use].allow_webmcp` boolean from managed requirements and preserve requirement-layer precedence.
- Return the policy as `browserUse.allowWebmcp` from `configRequirements/read`, including explicit `true`, explicit `false`, and `null` when omitted.
- Update the generated JSON and TypeScript protocol schemas.
## Testing
- Cover parsing, invalid values, layered overrides, and app-server response serialization.
GitOrigin-RevId: a3fd7d1a6f838bb3ab0ac2a644409101a2338ca6
## Why
Packaged clients need to pair a staging OAuth client ID with the matching
issuer. The issuer override was previously limited to debug builds.
## What changed
- Apply `CODEX_APP_SERVER_LOGIN_ISSUER` in all builds when it contains a
non-empty value.
- Keep `CODEX_APP_SERVER_DEV_OPEN_APP_URL` debug-only.
## Testing
Exercise the complete app-server OAuth flow with the issuer and client ID
overrides, including authorization, token exchange, and login completion.
GitOrigin-RevId: 13d290b9dae689cd811361b1b549953a3b52db42
## Why
Cold `thread/resume` configuration loading can call back into the host. Holding the global metadata permit during that work blocks unrelated thread metadata updates and MCP requests.
## What changed
- Release the metadata permit while loading configuration for a cold resume.
- Reacquire the permit and reload the resolved thread history before startup.
- Reload configuration when persisted metadata, settings, or the history working directory changed during the unlocked interval.
- Rejoin a thread that another request resumed concurrently, and avoid reopening threads that were archived or deleted.
## Testing
Add coverage for unrelated metadata and MCP requests during a blocked config load, concurrent resume mutations, and the extra history read required for non-local thread stores.
GitOrigin-RevId: 8cbd3868eeff84968765b1e3dbc7590ebe5fa892
## What changed
- Add optional per-model Guardian modes for computer use, shell, code mode,
file changes, MCP, network, and permission requests.
- Apply disabled, synchronous, or adaptive review by action category while
preserving legacy configuration when model policy is absent.
- Bind cached risk scores to the active model policy, thread settings, and
environment selections so outdated scores cannot approve later actions.
- Keep unknown review modes on the synchronous path and ignore unknown policy
fields for forward compatibility.
## Testing
- Cover policy serialization, legacy fallback, scoped tool classification,
disabled categories, and score invalidation after policy changes.
GitOrigin-RevId: f334a5f4fffb198da66cde3a400233e0df650516
## Why
A pending remote control enrollment could prevent the app server from exiting
after stdio EOF, leaving resources such as thread writers held by the process.
## What changed
- Give remote control its own child shutdown token and cancel it before draining
RPCs when the stdio connection closes.
- Interrupt enrollment requests that require network access after shutdown has
begun, while still allowing in-memory or persisted enrollments to be enabled
and durably saved.
## Testing
- Cover stdio shutdown during a blocked enrollment and verify that another app
server can acquire the released thread writer.
- Cover durable enablement after shutdown with in-memory, persisted, and missing
enrollments.
GitOrigin-RevId: ef9ab49672f273a4cf8257188454a154c03088bd
## What changed
- Emit a connection-scoped `deprecationNotice` when `review/start` uses
`delivery: "detached"`, including when validation later rejects the request.
- Preserve detached review behavior while directing callers to use `thread/start`
followed by an inline review for a separate review thread.
- Document the deprecation and migration options in the app-server protocol and
README.
## Testing
- Cover the notice for accepted and rejected detached reviews.
- Verify that omitted, null, and inline delivery do not emit the notice.
GitOrigin-RevId: 4234a09d2bb7ef8053091580175dc8cbe8d7512c
## Why
An empty tool map does not distinguish a successfully returned empty catalog from a server whose startup or tool discovery failed.
## What changed
- Add nullable `toolsError` to each `mcpServerStatus/list` entry when no catalog is available because startup or tool discovery failed.
- Keep `toolsError` null for returned catalogs, including cached and empty catalogs, and continue returning healthy servers when another server fails.
- Update the protocol schemas and generated TypeScript type.
## Testing
- Extend the app-server status integration test with a broken MCP server and verify its error without losing the healthy server's inventory.
GitOrigin-RevId: 30b4ca4d9a45cec6998f5f626d3fddbee90a525d
## Why
Loaded threads can retain their previous configuration after a local plugin is
installed, preventing the plugin's bundled MCP servers and pending user-config
changes from taking effect in the current session.
## What changed
- Reload user configuration for loaded threads after installing a local plugin.
- Refresh MCP and hook runtimes only after the new configuration is applied.
- Keep installation successful if configuration reload fails, while logging the
failure.
## Testing
- Verify an installed plugin's MCP tool can be called from a thread that was
started before installation.
- Update the hook runtime test to verify installation applies a staged hook
configuration change to the loaded session.
GitOrigin-RevId: 63f5a5c7f16303e51cf940e8d9dc3b45c50ae2a9
## Why
Guardian can reuse an opaque parent compaction only when the checkpoint's
recorded producer hash matches the scoring model. Missing or incompatible
provenance must not allow an asynchronous score or cached approval to omit
compacted context.
## What changed
- Record the producing model's compatibility hash on compaction history items
and expose the latest checkpoint hash through conversation snapshots.
- In thread-owned context mode, fail closed and require synchronous review when
checkpoint reuse is enabled but the latest checkpoint is incompatible or has
unknown provenance.
- Reject incompatible checkpoints in the sampler while preserving the legacy
context behavior.
## Testing
Add coverage for local, remote, resumed, compacted, and rolled-back histories,
including matching, mismatched, missing, and empty compatibility hashes.
GitOrigin-RevId: 1ce959cb276edc602fd7dfa442133c7fe5e53857
## Why
Guardian authorization reviews need host-verified `request_user_input` answers to
remain aligned with thread history across compaction, resume, and rollback.
## What changed
- Record verified question-and-answer pairs in retained thread context when
`GuardianThreadContext` is enabled, and source both local and delegated Guardian
review evidence from that context.
- Preserve complete answer records within the evidence budget. Mark authorization
context incomplete when records are unavailable or oversized, and defer cached
fast approvals in that case.
- Keep the existing runtime-only answer path for threads that do not enable the
thread-owned context.
## Testing
- Cover answer retention through compaction and resume, removal after rollback,
source-call eviction, oversized answers, delegated review evidence, and legacy
behavior.
GitOrigin-RevId: 01f6f4541515434a0d00fdde318ff59f2f8bd2eb
## What changed
- Add the creation-time `originator` to app-server thread responses and `thread/started` notifications.
- Persist originators in thread metadata and preserve the first recorded value across list, read, resume, rollout, and SQLite paths.
- Add an `originators` allowlist to `thread/list` for hosted backends. The local app-server accepts omitted or empty values but rejects nonempty filters.
## Testing
- Cover originator persistence across server restarts and list, read, and resume requests.
- Verify local `thread/list` handling for nonempty, omitted, null, and empty originator filters.
- Heap-allocate large TUI dispatcher futures in affected tests to keep them within the Windows test-thread stack.
GitOrigin-RevId: 73ad6e61b8fdd2d93a22d1f971723a19ec7be3fc
## What changed
- Add `originator` to plugin measurement inputs and emitted analytics events.
- Populate it from the turn originator when recording plugin measurements.
- Extend analytics tests to verify the originator is preserved in event payloads.
GitOrigin-RevId: 9998f829760222fc690dc8a10324794b5da27220
## Why
Computer-use-only Guardian scoring should follow the active model's REPL
auto-review requirement, including when the model changes within a live thread.
## What changed
- Run computer-use scoring and fast approval decisions only when the active
model sets `node_repl_auto_review_required`.
- Invalidate prior or in-flight scores when a model switch skips scoring, so
switching back to a reviewed model cannot revive a stale decision.
## Testing
- Cover model switches for both `node_repl` and `cua_repl` MCP servers.
- Verify skipped scoring and stale-score rejection across requirement changes.
GitOrigin-RevId: 46aec4d017bea8f135b435bcd769b87369b8ce95
## What changed
- Add `application.network` managed requirements with exact-domain allow/deny
rules, default-enabled behavior, domain normalization, and normal managed TOML
precedence.
- Return the policy separately from agent network requirements through the
experimental `configRequirements/read` API. The endpoint reports the policy
but does not enforce it.
- Export the new protocol types and schemas, and document the TOML format.
## Testing
- Cover parsing, validation, normalization, layered precedence, and cloud
requirement composition.
- Verify app-server responses, defaults, separation from agent policy, and
rejection of invalid domains.
GitOrigin-RevId: 563eeed296d9748430b819797204a44a8db92f3b
## Why
Selected plugin MCP servers may be skipped after the optional startup grace
period. When a user explicitly mentions a plugin or MCP server, the turn should
continue waiting so the requested tools are available to the model.
## What changed
- Track explicitly mentioned plugin IDs and MCP servers across later samples,
steered input, and same-turn restarts.
- Require matching selected-plugin MCP servers to finish startup before
capturing the tool catalog, while leaving unmentioned servers optional.
- Match `plugin://` identities independently of display names and ignore
targeting query parameters such as `app` and `browserFamily`.
## Testing
Added coverage for linked and structured plugin mentions, direct and batched
capability discovery, delayed environment attachment, steering, and same-turn
restarts.
GitOrigin-RevId: c509ef8df45df1a7edb0da6afdb2682dc53a4de8
## What changed
- Add the experimental `Thread.environments` field with each selected environment's ID, working directory, and runtime workspace roots.
- Populate the field from live thread state in start, resume, read, list, and unarchive responses. Use `null` for unloaded threads and an empty list when a loaded thread has no environment selection.
- Document that the field reports selection rather than connection status and does not affect executor selection or resume behavior.
## Testing
- Cover selection updates, unloaded and resumed threads, loaded pathless unarchives, and clients that subscribe after environment connection notifications.
GitOrigin-RevId: a6daa06aff7089d7c5a1e4c7d03109b41f12fa3c
## Why
Directly deserializing the flattened `RolloutLine` envelope can reject nested
decimal values, preventing affected paginated sessions from resuming.
## What changed
- Add canonical string, byte, and reverse-scanner helpers that decode rollout
records through `serde_json::Value` before decoding the flattened item.
- Route rollout readers across session discovery, history, migration, search,
thread storage, and transcript previews through those helpers.
- Remove `Deserialize` from `RolloutLine` so new readers cannot bypass the
canonical persistence decoder.
## Testing
Add coverage that resumes a paginated rollout after a token-count record with
a decimal rate-limit value and verifies that ordinal sequencing continues.
GitOrigin-RevId: 49abac1e0751c073daa5a93a840d8a483fd2d013
## What changed
- Remove the per-thread `RealtimeConversation` feature check when starting a realtime session.
- Retain `features.realtime_conversation` as a removed compatibility setting that has no effect, even when set to `false`.
- Document the always-available behavior for `thread/realtime/start`.
## Testing
- Cover realtime startup on forked and cold-resumed threads with the legacy setting absent, disabled, or enabled.
GitOrigin-RevId: d9cd9aa3898d1c2efb9414a8f40c86be8951e210
## Why
When ordinary included usage is exhausted, eligible users need a way to keep working with the backend-provided Luna Reserve quota and return to their previous model once ordinary usage recovers.
## What changed
- Automatically switch eligible TUI tasks to Luna Reserve after an authoritative account usage read, preserving the prior model and reasoning effort per task.
- Restrict model selection while on Reserve to its supported reasoning levels, keep queued turns on the accepted model, and restore the saved model after a fresh read confirms recovery.
- Surface Reserve usage in the composer and `/status`, and expose `normalModelSlug` in app-server rate-limit snapshots so clients can use the associated model's display metadata without changing the request model.
- Poll account limits more frequently near exhaustion and retain compatibility with app servers that only accept the legacy null request parameters.
## Testing
- Added coverage for Reserve entry, queued-turn handling, task reconstruction, recovery authorization, account changes, model selection, usage rendering, and banner dismissal.
GitOrigin-RevId: 46a435e9531051f8cec3f6a46c4b9f7cfa479747
## Why
Detached Windows processes cannot receive console signals, so app-server daemons
need another way to enter the existing graceful and forced shutdown flow.
## What changed
- Watch the path in `CODEX_DAEMON_SHUTDOWN_FILE` for a request addressed to the
current process, and consume only a matching PID.
- Race daemon shutdown requests with Ctrl-C on Windows while leaving unmanaged
launches on the existing console-signal path.
- Exercise the SIGTERM-equivalent graceful and forced WebSocket shutdown cases
on Windows.
## Testing
Added unit coverage ensuring inherited control paths and malformed requests
cannot consume another process's shutdown request.
GitOrigin-RevId: 426a3c12edc344802395d4d26288f2bb015c484f
