## Why
The `<current_date>` in environment context could diverge from the clock used by current-time features, especially when a host provides an external clock.
## What changed
- Read the current time from the session's time provider whenever world state is built, and render its local date in environment context.
- Use each session's own thread ID for clock reads, including guardian sessions.
- Propagate clock-read failures through turn error events and stop before model inference.
## Testing
- Cover date updates across turns and app-server requests.
- Verify guardian clock reads use the corresponding root or guardian thread ID and do not run during prewarm.
- Verify clock failures emit an error without sending an inference request.
GitOrigin-RevId: bb7f32ccc0229b7bc6f14d7356db00bcce78066d
## What changed
- Pass the canonical `PermissionProfile` through execution requests, sandbox
selection, escalation, and the exec server instead of carrying separate
derived filesystem and network policies.
- Derive runtime sandbox policies from the effective profile at their points of
use, including after applying additional permissions.
- Update sandbox and escalation tests to inspect policies through the profile.
GitOrigin-RevId: 695b82ea94f5289516b0933bb23074cb2dcce8ac
## What changed
- Add the opt-in `executed_tool_call_metadata` feature to record model-attempted direct and code-mode tool calls.
- Attach recorded names and arguments to the matching tool output in the next Responses request, preserving the metadata across sampling retries.
- Bound pending calls and argument sizes, and emit truncation metadata when limits are exceeded.
## Testing
- Cover disabled-by-default behavior, namespaced and nested calls, blocked or failed attempts, retry handling, and recorder limits.
GitOrigin-RevId: 5ce917b73e797b0f6904d46477b9d2cf8ea71bf2
## Why
External MCP, extension, and dynamic tools can collide with host-owned tool
names. In particular, a dynamic `tool_search` definition must not replace the
host implementation used to discover and route deferred tools.
## What changed
- Build each turn's tools through a single ordered `ToolRegistry` that retains
the first runtime registered for a name.
- Treat duplicate external tools as skippable collisions while preserving
strict duplicate checks for trusted host tools.
- Reserve host-owned code-mode and `tool_search` runtimes before producing the
model-visible tool list.
- Base hosted web-search fallback behavior on the extension runtime that
actually won registration.
## Testing
- Cover ordered registry mutation and duplicate handling.
- Verify a client-provided `tool_search` cannot shadow the host tool.
- Verify hosted web-search fallback follows the registered browser runtime.
GitOrigin-RevId: acebe360de8ec69ad7da2f684cc2542cbf18a984
## Why
Executor capability discovery can traverse plugin and skill roots, including
symlinks. Under restricted filesystem permissions, discovery must not expose
files outside the permitted paths.
## What changed
- Pass each environment's filesystem sandbox context through capability root
discovery and apply it to metadata, directory walks, and file reads.
- Enable discovery for restricted sessions so permitted executor skills remain
available while inaccessible roots and symlink targets are omitted.
- Key discovery caches by sandbox context and reject sandboxed discovery on
executors that do not advertise support for it.
- Split requests with more than 128 roots into supported-size batches.
## Testing
- Cover permitted and denied external symlink targets.
- Verify restricted skill listing excludes inaccessible skills.
- Verify cache separation across permission contexts and discovery of 129 roots.
GitOrigin-RevId: 44d16468ca003403bdb8b71a04ae8c9ff94ed494
## Why
Executor-backed skill resources must honor the active filesystem permission profile instead of reading outside its allowed roots.
## What changed
- Propagate each environment's filesystem sandbox context into `skills.read` calls.
- Apply turn-scoped permission grants when reading executor skill resources.
- Fail closed when no matching sandbox context exists or a restricted Windows read cannot be sandboxed.
- Preserve the existing resource size limit for both sandboxed and streamed reads.
## Testing
- Cover reads within permitted roots and reads that succeed after a permission grant.
- Verify denied references do not expose their contents and disabled Windows sandboxing is rejected.
GitOrigin-RevId: 5cc679b9385b0621665ff20cf5848863cc6396a4
## What changed
- Split core tool planning from the assembly of MCP, extension, and dynamic tool runtimes.
- Build `ToolRouter` from a single ordered runtime list plus hosted tool specs.
- Centralize whether each `ToolExposure` variant is available in code mode.
- Preserve core, MCP, extension, and dynamic source ordering and existing name-collision priority.
## Testing
- Add coverage for unified source ordering and collisions, code-mode exposure, and standalone web search alongside MCP and dynamic `web.run` tools.
GitOrigin-RevId: b010c2e9728b92b75a35325ca9b2ec465c3bac12
## What changed
- Add `EnvironmentManager::publish_ready_info` to update the selected capability
roots for an existing environment without replacing it.
- Store readiness as an atomically replaceable snapshot so repeated publications
expose the latest roots while deferred completion still controls connection
readiness.
- Validate published roots and reject updates for missing environments.
## Testing
- Cover publication, replacement, repeated and invalid updates, and interaction
with deferred environment completion.
GitOrigin-RevId: 1477f60e1319f840e6b33703ef2af052713779fd
## What changed
- Preserve `encrypted_function_args` on function calls so an empty list can mark plaintext collaboration arguments across request replay.
- Deliver `spawn_agent`, `send_message`, and `followup_task` payloads as structured plaintext agent messages when that marker is present; retain encrypted delivery otherwise.
- Redact plaintext collaboration arguments from tool and communication logs, and omit the metadata when sending requests to non-OpenAI providers.
## Testing
- Cover serialization of empty encrypted-argument metadata and plaintext versus encrypted subagent message delivery.
- Verify plaintext tool arguments are redacted and provider-specific metadata is removed from non-OpenAI requests.
GitOrigin-RevId: 64db98ff0b61a3af2f04ed609292363f2e2362a8
## What changed
- Add the stable, disabled-by-default `recommended_plugins` feature flag.
- Load recommended plugin candidates when apps and plugins are enabled and
either `tool_suggest` or `recommended_plugins` is active.
- Keep the `request_plugin_install` tool gated by `tool_suggest`.
## Testing
- Cover the first turn after external login with `tool_suggest` both enabled
and disabled, including the expected install-tool availability.
GitOrigin-RevId: 06d9a1c2e8dd2498a47796d833eb6d25ba528351
## What changed
- Propagate the initiating turn ID through agent spawns, follow-up tasks, reviews, and delegated Codex sessions.
- Add `parent_turn_id` to Responses client and turn metadata while keeping it out of external MCP metadata.
- Preserve parent-turn provenance across queued agent messages when their triggering parent is unambiguous.
## Testing
- Cover spawned, resumed, nested, reviewed, delegated, and WebSocket request metadata.
- Verify queued messages do not claim ambiguous or queue-only parent turns.
GitOrigin-RevId: 481fdebbe7df2031880fe259509273cce50b20a8
## What changed
Run the thread-title lookup alongside instruction refresh and plugin and skill
warmup, avoiding an additional sequential wait during session initialization.
GitOrigin-RevId: 021f48abeac249c5d3fe526d026bf031acf1bed9
## Why
Host skill catalogs supplied through extension world state should report budget warnings only when their catalog update is actually rendered.
## What changed
- Stop rebuilding an extension-owned host catalog in core.
- Emit host catalog budget warnings when the corresponding world-state fragment is rendered, and deduplicate them with executor catalog warnings.
- Cover full, shortened, and omitted host and executor catalogs, including repeated turns and resumed persisted snapshots.
GitOrigin-RevId: ba28b6e337281b49ed4da2175c193fd4a6898ab7
## Why
A pending optional MCP server can delay the first model request even when the
turn does not need that server.
## What changed
- Give optional MCP servers a shared one-second startup grace, then omit servers
that are still pending from the captured tool catalog.
- Continue waiting when the turn explicitly requires a server through a plugin,
skill dependency, or `mcp://` mention, and preserve this behavior for input
received between sampling steps.
- Route direct resource requests to the live connection set when a pending
server was omitted from the binding, while keeping all-server resource
discovery non-blocking.
## Testing
- Cover the shared grace period and resource behavior for pending optional
servers.
- Verify plugin, plugin-skill, and direct MCP mentions wait for startup.
- Verify an Apps-enabled turn proceeds without tools from an unrelated pending
optional server.
GitOrigin-RevId: b5f895c5a5362fe73f7d33250367662d4a217e4d
## What changed
- Add protocol types and `ResponseItem` helpers for attaching and clearing
locally recorded tool-call names and arguments.
- Bound serialized metadata across a prompt, replacing oversized arguments and
omitted calls with trusted truncation details.
- Prevent deserialized response items or model-provided arguments from forging
locally generated tool-call and truncation metadata.
## Testing
- Cover prompt-wide size limits, omission accounting, idempotent bounding, and
forged truncation markers.
GitOrigin-RevId: 960a223437ce81fe6b4cbb5fc7a9774408b2755b
## What changed
- Update the `rmcp` model and transport integrations for `3.0.0-beta.3`.
- Preserve legacy `elicitation/create` form requests, schema defaults, metadata, and wire-format compatibility while adopting the new elicitation types.
- Harden OAuth discovery by using GET-first discovery without starting an MCP session, preventing cross-origin header redirects, validating authorization-server and callback issuers, and retaining compatibility with metadata that omits an issuer.
- Keep stored OAuth credentials readable and avoid requiring reauthorization after transient refresh failures.
## Testing
- Add coverage for legacy elicitation round trips, OAuth discovery variants, callback issuer validation, credential migration, and refresh failures.
GitOrigin-RevId: 756197d26f3fd347c28c400228f6b3d06ed493b7
## What changed
- Store a request-logging-disabled `RouteAwareClientPool` in session services and use it for file creation, blob upload, and finalization requests.
- Preserve the existing system-root fallback for transport-default proxy routes, and emit a warning event when that fallback is used.
- Remove the direct `reqwest` dependency from `codex-api` now that uploads use the shared HTTP abstraction.
## Testing
- Add coverage for completing multiple uploads through a shared client pool.
GitOrigin-RevId: 01842415cad2d349a6bd3869abb3332e8110ebce
## What changed
- Add `features.multi_agent_v2.subagent_developer_instructions` to override inherited developer instructions for subagents that do not define role-specific instructions.
- Preserve role-specific instructions as the higher-precedence setting, and carry the effective instructions through full and bounded forks, compacted histories, and cold resume without duplication.
- Treat an unset override as inheritance and a blank override as clearing inherited instructions.
## Testing
- Cover configuration parsing and materialization, instruction precedence, fork modes, compaction, role application, and resumed subagents.
GitOrigin-RevId: 32321e61abc59b14a1be5f31e6bd6570bb1cd89d
## Why
Turn preparation waited for MCP discovery before requesting endpoint plugin
recommendations, adding their latencies together.
## What changed
- Prepare the MCP runtime and endpoint plugin recommendations concurrently.
- Wait for both results before building tools and starting model sampling.
- Cancel the combined preparation when the turn is interrupted.
## Testing
- Add coverage that gates MCP initialization and verifies recommendation fetching
overlaps it while the final request includes both results.
- Verify interrupting concurrent preparation prevents model sampling.
GitOrigin-RevId: 295ec268331bf05304e6b313925fd2b6c2ae4190
## What changed
- Add token-budget settings to model catalog messages and apply them when the
feature is enabled without explicit token-budget configuration.
- Keep explicit user settings authoritative, reject invalid catalog defaults,
and preserve resolved defaults in exported config locks.
- Manage context-window guidance through world state so it updates once when
the active model changes while retaining prior conversation history.
## Testing
- Cover catalog defaults, explicit overrides, disabled features, invalid
values, config-lock replay, and model switching.
GitOrigin-RevId: 54544fefaa14b09f5ef5bad9967a13c52b87b0fe
## What changed
- Add an optional `ExtensionMetrics` capability to thread, turn-input, and world-state contributors, backed by session telemetry in the host.
- Record skill counts, omissions, and truncated description characters for extension-rendered catalogs, tagged by the catalog surface.
- Preserve host session attribution on extension metrics, including the effective model for each turn, and prevent extension tags from overriding host metadata.
- Avoid duplicate host-catalog samples by recording world-state metrics only when the section is published or changes.
## Testing
- Cover metric values and surface tags, session metadata preservation, turn-level model changes, and host world-state publication behavior.
GitOrigin-RevId: 9059e521943a8f81df25a38b03692eddbc1d990d
## What changed
- Add model and personality sections to the persisted world-state snapshot.
- Generate model-switch and personality instructions through world-state diffs, including when prior state must be inferred during replay.
- Keep those instruction fragments in standalone developer messages instead of merging them with adjacent context updates.
## Testing
- Cover initial, unchanged, and changed model and personality states.
- Verify that model changes are recorded in rollout world-state items.
GitOrigin-RevId: 497e29cf38cac08e992e546df900f6f8b01120f9
## What changed
- Add an optional `started_at_ms` field to `ItemCompletedEvent`, retaining
compatibility with older persisted events that lack it.
- Track the first start timestamp for each in-flight item and attach it when
emitting and persisting the completion event. If no start was recorded, use
the completion timestamp as a fallback.
- Emit a complete start/completion lifecycle for subagent activity items.
## Testing
- Cover concurrent item timing, repeated starts, turn-boundary cleanup, the
missing-start fallback, subagent activity, and persisted web-search events.
GitOrigin-RevId: e7cec9c4f1ef6ba67f287e81fb4d7d856fcf87a7
## What changed
- Scope pending network approvals to a turn and execution while still coalescing duplicate requests within one execution.
- Fail abandoned approval owners closed, cancel denied executions, resolve any waiting requests, and cancel in-flight Guardian reviews when their owner is dropped.
- Serialize session policy updates with approval caches so concurrent allow and deny decisions cannot leave enforcement and cached decisions inconsistent.
- Give user approval requests and permission hooks unique per-execution identifiers.
## Testing
- Cover approval deduplication boundaries, abandoned-owner cleanup, cancellation outcomes, replacement requests, and Guardian cancellation events.
GitOrigin-RevId: 11e184dd1c70294a99581b6ff0d4b6607d9ea1d9
## What changed
- Carry a plugin's local and remote identities together from plugin loading into
`SkillMetadata`.
- Resolve remote IDs from the installed-plugin snapshot when available, falling
back to persisted install metadata only when no snapshot exists.
- Include plugin identity in skill cache keys so identity changes refresh cached
skill metadata.
## Testing
- Cover snapshot and persisted identity resolution, local marketplace isolation,
cached skill refreshes, and propagation through plugin skill snapshots.
GitOrigin-RevId: aabeeb631a43361fe817358ace7f1ea8ba5db708
## Why
Hooks can only consume a transcript path when the thread has a local rollout.
## What changed
- Resolve the local rollout path before materializing the transcript.
- Return no transcript path for non-local thread stores without persisting them.
- Continue materializing lazy local rollouts before passing their path to hooks.
## Testing
Added session and hook tests covering both non-local thread stores and lazy local rollouts.
GitOrigin-RevId: c742984d146f7a3e1048b848198198fc7a64f4de
## Why
`thread/fork` rejected threads using paginated history, so they could not use the same fork workflow as legacy threads.
## What changed
- Create paginated forks by referencing a frozen source-history prefix while persisting only child-owned records in the new rollout.
- Support latest, `lastTurnId`, and `beforeTurnId` boundaries, including inherited lineage, model-context reconstruction, interruption markers, and approval-reviewer inheritance.
- Make paginated reads and occurrence search traverse referenced history while excluding source records added after the fork.
- Coordinate fork preparation with archive and delete operations, and materialize compressed rollouts before they become fork references.
## Testing
Added app-server and thread-store coverage for boundary selection, active turns, inherited reads and search, compressed lineage, and concurrent source lifecycle operations.
GitOrigin-RevId: 66052d69517d7fb97a3b7817ab77a39c5ad995fd
## Why
MCP config reloads updated resolved server and authentication values, but did not
carry managed server constraints or plugin requirements into active threads.
## What changed
- Refresh MCP state from the typed thread config, including its managed
requirements, while retaining the thread's user layer and unrelated settings.
- Apply the refreshed config directly through `CodexThread` instead of encoding it
as a protocol operation.
- Re-evaluate effective plugins immediately after account changes so their MCP
requirements reach existing threads.
## Testing
- Cover replacement and enforcement of managed server and plugin requirements.
- Verify refreshed MCP settings are installed without changing the active model.
GitOrigin-RevId: 3cf0d69f51ef4893a4d722ee803fcbfdf1cd959e
## Why
MCP elicitation reviewers are reused across runtime refreshes, while an active
turn can retain the approval settings it started with. Reviewing against that
turn could therefore apply stale authority after session settings changed.
## What changed
- Read the latest published MCP runtime configuration when reviewing an
elicitation, including the approval policy, permission profile, configuration
layers, and reviewer selection.
- Apply `never` and granular MCP-elicitation policy decisions before routing an
eligible request to Guardian.
- Keep MCP runtime startup registered for refresh invalidation through session
creation.
## Testing
Added coverage that refreshes a running session and verifies the same reviewer
uses the latest authority for Guardian routing, denial, and empty-form
auto-approval.
GitOrigin-RevId: 826a157aa70fc8e3a9e3a14ecb0261bf7b63f63a
## Why
MCP configuration can change while a thread is still starting, before it appears in the thread manager's loaded-thread list. In that window, invalidation could miss the new thread and leave it with a stale MCP runtime.
## What changed
- Centralize MCP runtime invalidation in `ThreadManager` so it refreshes loaded threads and marks in-progress thread startups for refresh after publication.
- Use the centralized invalidation path for account and plugin changes.
- Invalidate MCP runtimes after successful server and plugin OAuth logins.
## Testing
- Add a regression test that pauses thread startup, invalidates MCP runtimes, and verifies that the newly published thread refreshes its MCP projection.
GitOrigin-RevId: 8944f5a21816a1405e038a0d4c08b66362ea9368
## What changed
- Add executor authority support to `skills.list` and `skills.read` for skills from selected capability roots.
- Allow `skills.read` to load package-relative resources referenced by an executor skill while keeping reads within the selected package.
- Paginate skill listings and resource contents with bounded response sizes and stale-cursor validation.
- Resolve executor filesystems per sampling step so skill tools use the active selected capability roots.
## Testing
- Extend the app-server executor skill test to list an executor skill, read its main `SKILL.md`, and read a paginated reference resource.
- Cover visibility filtering, metadata bounds, pagination, invalid cursors, package boundaries, and resource size limits.
GitOrigin-RevId: 1b5de95d5d1b9f79c34d2879d6e67f24401e9c29
## What changed
- Add `McpRefresh` to own the pending invalidation state and serialize MCP runtime refreshes.
- Keep cancellation recovery alongside the refresh state so a claimed refresh is marked pending again if publication does not complete.
- Update session initialization, shutdown, refresh paths, and tests to use the new abstraction.
GitOrigin-RevId: 915b28fa8b98a4f4c87ce8f2aa0d0ff99b57577d
## Why
Runtime updates reuse unchanged MCP connections, so an explicit
`RefreshMcpServers` operation could leave existing server connections intact.
## What changed
- Mark explicit MCP refreshes to rebuild connections for every configured
server on the next runtime replacement.
- Preserve the reconnect request if that replacement is cancelled before it
finishes.
- Continue reusing connections for ordinary runtime updates.
## Testing
Update the transient Apps startup recovery test to wait for both turn
completion and the MCP server's ready event before checking the recovered tool.
GitOrigin-RevId: cb9fd978b3c07543058a2393a154fb70911531de
## What changed
- Track the authentication state used by each published MCP runtime and mark the runtime dirty when the auth mode, account details, or token changes.
- Refresh plugin auth mode before evaluating pending MCP work, and rebuild the initial MCP projection if authentication changes during session startup.
- Carry one auth snapshot through runtime construction so plugin discovery and MCP connections use consistent credentials.
## Testing
- Add a regression test that replaces an API key, reloads authentication, and verifies that MCP refresh publishes a runtime using the new credentials.
GitOrigin-RevId: 219c2f7a157f53b5467116e18bfe70a8c3dca695
## Why
Changes to MCP inputs can require rebuilding the runtime before the next model
step. Start that work eagerly so the step is less likely to wait for it.
## What changed
- Add a per-session worker that prewarms dirty MCP state after configuration,
authentication, or explicit refresh changes.
- Coalesce queued refreshes and always rebuild from the latest session state,
while keeping exact model-step refreshes as the correctness path.
- Stop and join the worker during session shutdown.
## Testing
- Verify rapid refreshes skip superseded configuration and publish the latest
state.
- Verify MCP-relevant policy changes mark the runtime for refresh.
GitOrigin-RevId: 045ed406caff97dcbb483bc183fd16eae0c7d7ad
## What changed
- Add `WaitForEnvironmentToolConfig` as thread extension data for overriding the
model-visible tool and `environment_id` descriptions.
- Preserve the default descriptions when no override is provided or when the
configured descriptions exceed the input or serialized tool-spec limits.
- Keep `wait_for_environment` availability gated by the deferred executor
feature independently of whether a host override is present.
## Testing
- Cover default, custom, oversized, and feature-disabled tool configurations.
- Verify the custom descriptions in the deferred-environment integration flow.
GitOrigin-RevId: 6b49a73a434becd99ea5df911be53f3706a17c0a
## What changed
- Add the disabled-by-default `deferred_tool_world_state` feature, which exposes deferred tool namespaces and their descriptions to the model in a `<tools>` world-state section.
- Emit added and removed namespace updates as tool availability changes, bound the rendered context size, and persist nonempty state across thread resumes.
- Omit empty tool state while retaining deferred tool discovery through `tool_search`.
## Testing
- Cover initial, unchanged, removed, recovered, empty, and resumed namespace state, along with description truncation and rendered-size limits.
GitOrigin-RevId: 867e599666dc3569eb0789ba78aaa40254253a6f
## Why
Guardian review commands can run without the proxy-port environment used to
configure the parent session. Reconciling persistent Windows sandbox settings
for those commands can discard the parent's proxy configuration.
## What changed
- Add a session-level Windows sandbox proxy-settings mode and use `Preserve`
for guardian review sessions while keeping `Reconcile` as the default.
- Carry the mode through unified exec and the exec-server sandbox context to
Windows process launches.
- In preserve mode, reuse the proxy settings recorded by the existing sandbox
setup marker.
## Testing
Added coverage for guardian session configuration, exec-server transport, and
preserving an existing setup marker when proxy-port environment variables are
absent.
GitOrigin-RevId: 214655c6e6d97360906431773dc0de0fdda2db6e
## What changed
- Add optional `plugin_id` and `script_path` fields to execution approval and guardian assessment events.
- Propagate validated plugin attribution through delegated approvals, guardian-reviewed command items, app-server notifications, thread history, and rollout traces.
- Preserve attribution on both started and completed command items, including declined commands.
## Testing
- Extend core, app-server, thread-history, and rollout-trace tests to cover plugin attribution propagation and serialization.
GitOrigin-RevId: 723684d010cab04142918d7a95e06ed95d008da1
## Why
After a remote plugin install refreshes the Apps tool catalog, a later MCP
runtime publication must not restore the catalog from the previous connection.
## What changed
- Rebuild the MCP runtime with fresh connections when hard-refreshing Apps
tools, using the latest desired runtime configuration.
- Refresh the Apps catalog on the newly published connection so subsequent
runtime updates retain it.
## Testing
Extend the remote plugin install test to verify that both newly available and
missing Apps tools remain consistent after an unrelated runtime configuration
refresh.
GitOrigin-RevId: 5b675d53d56379ab67fab09512fc2ad0ffcb8535
## What changed
- Resolve shell and unified-exec commands against the trusted plugin roots loaded for each turn.
- Add optional `pluginId` and safe plugin-relative `scriptPath` fields to command execution items and legacy execution events, and propagate them through app-server notifications.
- Include the attribution in command execution analytics while rejecting absolute, unsafe, and unattributed script paths.
## Testing
- Cover attribution for cached curated and remote plugin scripts from command execution through core and app-server events.
- Verify analytics serialization and unsafe-path filtering.
GitOrigin-RevId: 02fac3a233284ccfc6642fa502a95f1881dba83d
## What changed
- Wrap `CodexErrorDetails` and an optional retry delay in `CodexErr`, allowing any mapped error to preserve server-provided retry timing.
- Generate the payload-free `CodexErrKind` classification alongside the error details and reuse it for analytics.
- Update error handling sites to inspect `CodexErr::details()` while preserving existing display, debug, protocol mapping, and retryability behavior.
## Testing
- Add coverage for legacy debug formatting, error-specific retryability, and retry-delay propagation through API error mapping.
GitOrigin-RevId: d3ab8a305f2a2ee21d0c0a8c8c388b06dda9c59a
## Why
Codex and SQLite data can use separate home directories, but state consumers
could reconstruct database paths from the Codex home instead of consistently
using the resolved SQLite configuration.
## What changed
- Pass `SqliteConfig` through the core, rollout, state runtime, and thread store
instead of passing a directory and rebuilding the configuration downstream.
- Use that shared configuration for state, logs, memories, goals, and paginated
thread-history database access, including integrity checks and cleanup.
- Reject state database handles whose SQLite configuration does not match the
requesting store.
## Testing
Add coverage with separate Codex and SQLite homes that verifies startup
backfill, thread listing, and paginated history all use the configured SQLite
directory.
GitOrigin-RevId: 1de1cdd1d6ff1d70bbb6c360c8352e6543fb8ebf
## Why
Refreshing MCP runtime state should not restart an unchanged, ready server or
relist its tools.
## What changed
- Reconcile refreshed MCP configuration against the published connection set
and reuse connections whose transport, environment, authentication, OAuth
credentials, and client capabilities are unchanged.
- Keep tool filters, timeouts, metadata, and plugin provenance in the published
server view so those settings can change without reconnecting.
- Update elicitation authority in place for reused connections, and reconnect
when connection-defining inputs or live OAuth credentials change.
## Testing
Added coverage for unchanged-server reuse, view-only and elicitation-policy
updates, connection identity changes, OAuth credential changes, and avoiding
redundant tool listing.
GitOrigin-RevId: f04f5db5fbdde127b6a14f6aa9673112c0b557e7
## What changed
- Treat batch writes containing only `model`, `model_reasoning_effort`,
`plan_mode_reasoning_effort`, `service_tier`, or `personality` as defaults for
future sessions, even when `reloadUserConfig` is requested.
- Keep runtime config reloads and skill/plugin cache invalidation for other
config changes, and document which settings remain session-static.
- Preserve cached skill listings after session-default writes until a forced
reload, with test coverage for each supported default.
GitOrigin-RevId: 6d988014cf4758ceb9422a11f7c2bd5fc6b9f90a
## What changed
- Make `McpRuntime` own the published MCP configuration, connections, elicitation routing, and selected capability roots for a thread.
- Capture immutable MCP bindings for model steps and tool calls so in-flight work keeps a consistent connection set and approval authority while refreshed state is published atomically.
- Mark MCP state dirty when relevant configuration, plugins, environments, authentication, or elicitation capabilities change, then rebuild it before the next sampling request or out-of-band MCP operation.
- Separate config reloads from server invalidation: `ReloadMcpConfig` applies resolved MCP inputs, while `RefreshMcpServers` requests reinitialization from the thread's latest state.
## Testing
- Cover refreshed state visibility for existing turns, stable step bindings, current approval authority, cancelled refresh retries, resource-client reconciliation, and Apps recovery between sampling requests.
GitOrigin-RevId: 59eabb1aa8dc083426bd18ef4d3630508f376401
## Why
An idle thread with an outstanding durable sleep must resume when agent work
arrives, even when that message would normally remain queued without triggering a
turn.
## What changed
- Treat any pending mailbox message as wake-up work while a durable sleep is
attached to the thread.
- Keep requiring `trigger_turn` for idle threads that are not durably asleep.
- Cover waking a sleeping root thread from queue-only agent mail and persisting
the message in thread history.
GitOrigin-RevId: e361ac1b104436d4d63aebfe5e2422691a1cc139
## Why
Multi-agent mode instructions are durable model context and need to survive
history changes without re-emitting unrelated setup hints.
## What changed
- Add a `multi_agent_mode` world-state section that diffs, retains, and restores
the effective mode instructions.
- Persist mode changes in world-state snapshots while keeping the legacy
`TurnContextItem.multi_agent_mode` field for reading older rollouts.
- Keep initial mode instructions after the root-agent usage hint so the active
mode takes precedence, and bound custom mode text before snapshotting it.
## Testing
- Add snapshot coverage for mode transitions, retained history, and custom-text
truncation.
- Verify live mode changes preserve instruction ordering, avoid duplicating the
usage hint, and record both modes in world state.
GitOrigin-RevId: 96b9964d6e5299b07a011c559b68e3d948a49226
## Why
Interrupting a turn while MCP tools were still starting could abort before the
submitted user input was recorded in conversation history.
## What changed
- Build and retain the MCP tool list and tool router as part of each step
snapshot, using the turn cancellation token during tool discovery.
- Record turn hooks and submitted input when cancellation occurs during startup
prewarming, pre-sampling compaction, or first-step capture.
- Reuse the captured router for sampling, compaction, and prompt debugging so
advertised and executable tools share the same request-scoped view.
## Testing
Add coverage that interrupts each affected MCP startup phase and verifies that
the user prompt remains in history before the turn-aborted marker.
GitOrigin-RevId: 6e96c6814357a55545d69b580e28f35933cfadf7
## What changed
- Add `compaction_ms` to turn profile facts and turn analytics events.
- Measure manual and automatic compaction as an exclusive profile phase instead of including it in surrounding idle time.
- Complete the profile and total turn duration from the same instant so their elapsed times remain consistent.
## Testing
- Cover compaction phase accounting and profile-duration consistency.
- Update turn event serialization coverage for `compaction_ms`.
GitOrigin-RevId: 50f0e1cf19789a807f9f56c2ef763c620a5d641c
rka-oai