## Why
Fixed retention limits could discard long user instructions or leave
older sender messages out of Guardian review even when the configured
elastic budget had room for them.
## What changed
- Apply the configured retained-instruction entry limit when capturing
and restoring user messages. Fixed-budget reviewers use the fixed
retention window for both user and assistant messages.
- Build elastic sender snapshots at delivery using the receiver's sender
evidence budget. Give recent user messages first claim on space, then
include preceding assistant context where it fits. Mark omitted
evidence and save the snapshot for review and rollback.
## Testing
Add coverage for cross-host delivery after compaction, large sender
snapshots through checkpoint restore and rollback, and how synchronous
and asynchronous reviewers read saved or empty sender snapshots.
GitOrigin-RevId: f0b01a2d558e3286335efac85a4f8645dd9b954b
## Why
The fixed retention window can discard assistant messages before elastic
Guardian reviews can use them as context for a user's reply.
## What changed
Apply the thread's Guardian retention policy when recording assistant messages,
including confirmed messages sent through the user messaging tool. Keep full
text within the configured record limit and the overall assistant history byte
budget. Preserve an incomplete marker when a confirmed delivery exceeds the
record limit.
Recover the thread's retention settings from saved history and compaction
checkpoints. Fixed-budget reviews continue to use the fixed retention window.
## Testing
Add coverage for record limits during capture and restore, thread-owned
settings recovery, and replay of oversized confirmed deliveries.
GitOrigin-RevId: e828f06824ce6712910a9cc5ef42a438d1ddf27e
## What changed
At session startup, derive `assistant_record_bytes` from the Sync Elastic
per-entry token limit for retained user instructions. Use the default
section limit when the configuration omits that section.
Store the resolved byte limit in the optional `guardian_retention` field
of `ThreadSettingsSnapshot` and update the app-server schema. Fixed-mode
snapshots omit the field, and older snapshots can still be read.
GitOrigin-RevId: a8de88c5bd0e35c4a114577e70fb0c858acb13c9
## Why
Config servers that publish OAuth metadata still required administrators
to configure OAuth endpoints explicitly for Codex to use them.
## What changed
- Discover OAuth metadata when `config_server.oauth` is omitted. Use
explicit settings when provided, and fetch managed configuration
anonymously when discovery finds no metadata.
- Have the Git credential helper resolve the config server before
fetching managed configuration. It refuses explicit or discovered
OAuth so it can apply workspace policy without opening the OS keyring.
- Apply local network policy to discovery during `codex logout`.
## Testing
Cover app-server recovery after a discovery failure, Git credential
helper rejection of explicit OAuth without a network request, and
logout discovery blocked by local network policy.
GitOrigin-RevId: 1ad84effef48fd9b56371ee177bd53c54f3e87b8
## Why
When a turn incurs usage priced directly in USD, reporting only the
credit-converted estimate understates its cost.
## What changed
Sum `estimated_usage_usd_micros` and `native_usage_usd_micros` for
settled turns. Default an omitted native USD field to zero for legacy
responses. Suppress the total when either component is unavailable
(including explicit null), either is negative, or their sum overflows.
## Testing
Cover omitted and null native USD values, zero costs, negative amounts,
and overflow in backend client tests. Verify that the combined amount
reaches the OTLP exporter in the app-server integration test.
GitOrigin-RevId: 8709e48329db813cd66baf270ee3f1bcfd87cb03
## What changed
Use the turn's effective `web_search` mode for standalone and hosted
web search. Remove model-selected Search MCP discovery, fallback, and
provider tracking across thread resumes.
Remove `web_search_provider` from model metadata, the
`tools.client_search_provider` hint from configuration, and the
`hosted_search_policy` feature flag. Update the app-server schemas and
generated SDK types to match.
GitOrigin-RevId: 59e3371f4a43d532a484db52d5998f6770292028
## Why
Reconnect replaces the app event queue, so queued thread-switch events can be
discarded while their resets are still counted as pending.
## What changed
- Clear the pending thread-switch reset count when replacing the event queue
and use a shared accessor for the displayed thread during reconnect.
- Box the app event dispatch future and extract helpers for choosing the side
conversation target and rendering the composer pane.
GitOrigin-RevId: 6bb14443952262b6a0df7fdf05db053038c7ce2d
## Why
When a server stops reading a request, the client's WebSocket write can
stall. If the server sends a Ping or rejects the request while the write
is blocked, the client can leave that message unread until the write
fails or times out.
## What changed
Poll for incoming messages before each outgoing frame and while a write
is pending. On subsequent polls, give the pending write first use of
Tokio's cooperative budget and cap read-ahead across the entire upload.
## Testing
Add regression tests for Pong delivery before upload completion, early
size-limit closes, and bounded read-ahead without write starvation.
Cover error precedence for buffered peer replies, local send failures,
and network policy revocation, plus token usage when a close arrives
before an interrupt can be sent.
GitOrigin-RevId: c018c25dcdc70b64835b07935caede5e34dfa8f2
## Why
A server can reject an oversized request after reading just the first
frame header. If the upload then fails with a broken pipe, the write
error can hide the server's message-too-large close.
## What changed
After a write fails partway through an upload, drain immediately
readable replies within the send deadline and a bounded read budget.
Use those replies to surface server errors, including
`WebsocketMessageTooLarge`. Treat a close seen before the first frame
as belonging to the idle connection, and retire the socket after a
failed send.
## Testing
Add regression tests for size-limit closes on an idle socket, just
before the first frame, and after a partial first-frame write fails
with pings and pongs ahead of the close.
GitOrigin-RevId: 2feeb1961992b425dbec06129015dbe4c44ff3f2
## Why
An idle Responses WebSocket still needs to answer server pings when the
write buffer is full. The pong must finish flushing once the peer drains
the socket, even if no further messages or requests arrive.
## What changed
Have the WebSocket pump flush automatically queued pongs and retry pending
flushes as the socket becomes writable. Bound incoming polling and the
number of pongs tracked while a flush is pending.
## Testing
Add an in-memory WebSocket test that forces a partial pong write and
checks that the peer receives the full heartbeat reply without further
traffic.
GitOrigin-RevId: 12865842c80a8a25a5e107be690f9c3962ce9775
## Why
Matching messages by text can link a tool call to an earlier message
with the same content. A recipient can also accept a message without
ever including it in a model request.
## What changed
Record the originating tool call ID when the recipient adds a spawn,
task assignment, or message to its history. On replay, use that ID to
link the accepted message to its sender even if the recipient records
it before the sender tool finishes.
Keep the interaction edge pointed at the recipient thread until the
message appears in a model request. Track distinct conversation items
across history resets and count repeated prompt prefixes only once.
## Testing
Replay tests cover identical message text, receipt before tool
completion, and messages observed again after compaction.
GitOrigin-RevId: ccab7c33993ba5fce7fceb733dc90c9d428ec78f
## What changed
Use state database-backed `thread/list` requests for task mentions without
searching conversation contents. Merge title-filtered results with recent
threads by thread ID so a full filtered page cannot crowd out recent
candidates. Native Cloud uses the recent list because it lacks a title filter.
Fuzzy-match the displayed title in the picker. Keep the working directory
visible as a description and exclude it from matching.
## Testing
Cover remote listing, retention of recent candidates when the filtered page
is full, and fallback when the filtered request times out. Check that a
directory-only match stays out of the picker.
GitOrigin-RevId: ec2a5ae9f046e533104251fd82f6683343854ee0
## Why
The daemon's automatic update preference still permits manual updates.
Administrators need a policy that covers both paths.
## What changed
Set `features.daemon_updates = false` in managed `requirements.toml` or
local MDM policy to block scheduled updates and manual daemon package
replacements. Updates are allowed by default. User configuration cannot
override the policy, and cloud-delivered requirements reject the setting.
When policy blocks updates, the TUI hides update actions in `/daemon`,
suppresses update offers in version notices, and directs users to their
administrator where a newer daemon is required.
## Testing
Add coverage for the default, disabled, and invalid policy cases,
rejection of the setting in cloud requirements, and the TUI with daemon
updates disabled.
GitOrigin-RevId: de9e50c4acc4dc8e83bbd2b9a5e902deb8c6f477
## Why
A pasted image path could become unreadable before submission if the
original file was moved or deleted.
## What changed
Copy the image into a private temporary file at paste time and use that
copy as the attachment. Apply a 1 GiB limit when saving image files and
clipboard PNGs. If copying a pasted image path fails, show an error and
preserve the draft.
## Testing
Cover attachment readability after deleting the original file and verify
that an oversized image paste reports an error and preserves the draft.
GitOrigin-RevId: 5f797979f36173fb3355345e0f124b81fcf86d01
## Why
The analytics client sends eligible events through HTTP. Hosts that
embed Codex need a way to deliver specific event types themselves while
keeping HTTP delivery for the rest of the batch.
## What changed
Add `AnalyticsEventsClient::new_with_event_transport` so hosts can opt
in and select eligible events by wire type. The transport receives the
complete wire payload and the event's product SKU, when available.
Events stay on the HTTP path unless the transport returns `Handled`,
which suppresses a duplicate HTTP send.
Disabled analytics and local file capture bypass the transport.
Rebinding the client to a new auth context restores HTTP delivery.
## Testing
Add tests for mixed batches that verify HTTP payloads and product
attribution, plus coverage for auth eligibility, local capture,
analytics opt-out, and auth rebinding.
GitOrigin-RevId: 27ba3fe54050754b5f844f00e7e761a4d7bcb8c0
## Why
Discovery could retry transport failures on successive lookups while
caching server errors until invalidation. That could repeat requests
against an unhealthy executor or leave a session without an inventory
after the server recovered.
## What changed
Cache failed discovery loads per context and return the cached error
during cooldown. The first lookup after cooldown retries, with delays
doubling from 1 second up to 30 seconds on consecutive failures.
Successful inventories are reused, canceled loads add no cooldown, and
explicit refresh clears the cooldown for the next lookup without
interrupting in-flight readers.
Compare discovery snapshots to detect inventory changes so recovered
plugins and MCP capabilities can become available without an explicit
refresh.
## Testing
Cover backoff timing, shared results for concurrent callers,
cancellation, and refresh bypassing cooldown. Exercise recovery after
failed prewarming and verify that MCP inventory updates after recovery.
GitOrigin-RevId: 6de34bb8957a0b24ee874e2447157bd3af562430
## Why
An exhausted carryover budget could drop explicitly pinned items, and an
oversized pin could crowd out ordinary user messages during local compaction.
## What changed
Preserve eligible pins in full and in their original order for the current
thread, child threads, or both, according to their retention policy. Apply
the carryover budget to the remaining history, including items retained by
features without an explicit pin.
## Testing
Add regression tests for destination-specific pins at zero budget and for
keeping an ordinary user message alongside an oversized pin during local
compaction.
GitOrigin-RevId: fc8529bcc254d8e7a4a010337ce760e94daa4bef
## Why
Invalidating Codex's discovery cache could still return stale inventory
if the executor reused its cached snapshot before its file watcher
reported a change.
## What changed
Add an optional `forceReload` flag to `capabilities/discoverV2` that
makes the executor rescan its files. Codex sends it on the next lookup
of each invalidated context. Explicit reloads also replace the matching
cache entry so subsequent ordinary requests can reuse the fresh result.
## Testing
Add coverage for discovering a newly added skill before the watcher
runs, forwarding the reload flag after invalidation, and reusing
refreshed results.
GitOrigin-RevId: c98f2b8d4772e10b74ff09dd382ad8386857158f
## Why
Step-time discovery can make the first step that needs a remote executor
inventory wait for a discovery round trip. Starting discovery during
environment setup lets deferred turns begin sampling while the inventory
is being fetched.
## What changed
When executor capability discovery V2 is enabled, prewarm the thread's
discovery cache for supported remote executors before marking their
environments ready. Reserve cache capacity for all selected environments
so the first step can reuse their inventories.
Give each prewarm up to five seconds and let environment startup proceed
after discovery errors or a timeout. Step-time discovery reuses cached
successes and permanent errors and can retry transient failures and
timed-out loads.
## Testing
Add integration coverage for deferred readiness and cache reuse after
success, permanent errors, transient failures, and timeouts. Also cover
cache retention across multiple environments and session startup when
discovery receives no reply.
GitOrigin-RevId: d07fc78bd42953a4caf9e4b39528db8a254eb2b8
## Why
The `always` policy ties retention across context windows to inheritance by
spawned agents. Callers need to control those behaviors independently.
## What changed
- `alwaysInThread` carries items across context windows in the current thread
and excludes them from spawned agents, including full-history forks.
- `alwaysInChildren` passes items still in the parent's context to spawned
agents and leaves each thread's context-window retention to the usual rules.
- `always` continues to apply in both scopes, including for items saved by
older versions. Retained tool calls and outputs must be adjacent, with the
call first and the same retention policy on both items.
## Testing
Extend integration coverage for retention across remote compaction, inheritance
by spawned agents, and injection through the app server.
GitOrigin-RevId: aafede69cfbe149aa52292e6029d248d4bdf6401
## What changed
Add `sizeBytes` to the app server's metadata response so clients can
read a file's size in bytes from its metadata. The field reports the
target file's size for symlinks to regular files and is `null` for
paths that resolve to directories or other non-regular files. The
protocol schemas and generated Python SDK model accept responses from
older servers that omit the field.
## Testing
Cover byte counts for regular files and symlinks to files, explicit
`null` for directories, and decoding responses that omit `sizeBytes`.
GitOrigin-RevId: fcc7bda9e55bd0584c1eff4af059422af282da9f
## What changed
Add `InheritedHistoryVisibility` to `CreateThreadParams` and pass it through
prepared forks. `Full` is the default and remains the mode used by app-server
forks. `ModelContextOnly` requests that `list_turns` and `list_items` omit
inherited history. The local thread store rejects that mode as unsupported.
## Testing
Add a regression test that requests `ModelContextOnly` through a prepared fork
and checks that the local store's unsupported-operation error reaches the caller.
GitOrigin-RevId: de675d6b83ca610eca5a304b9622b312d64828f6
Show the TUI warning navigation hint only when there are multiple
warnings to browse. Update the single-warning snapshots to reflect the
shorter footer.
GitOrigin-RevId: 8bcea7841d9fd84e037f59a6afa3e4ef2de6f01e
## Why
Active turns in paginated threads retain completed MCP tool results in
memory even when history can supply the same payloads. History can also
store a truncated preview, so dropping a result requires checking that
the full payload is recoverable.
## What changed
For persisted paginated threads, check successful MCP calls in batches
and release an active-turn result only when the stored result matches
it exactly. When resuming with full history, fetch released results by
item ID so a stale history page cannot supply an older result.
## Testing
Add a regression test that restores the latest result despite a stale
page and checks that truncated, metadata-mismatched, missing, and failed
results remain in memory.
GitOrigin-RevId: 49f6f1414201e4327433043050d65a1f4adc9720
## Why
Starting a turn discarded the discovery cache and forced MCP to rebuild
from a fresh inventory even when the executor context was unchanged.
An MCP refresh could also discover a different inventory from the one
the step had already captured.
## What changed
Keep a per-thread cache keyed by environment, executor session, working
directory, and sandbox. Explicit invalidation reloads discovery on the
next lookup and lets in-flight readers finish with their captured results.
Use the step's captured inventory for MCP reconciliation and bind it
with the current MCP policy. Apply the binding's plugin policy when
selecting skills and hooks.
## Testing
Cover cache reuse across turns, lazy invalidation during in-flight
discovery, and MCP refresh with a captured inventory after a server
has been revoked.
GitOrigin-RevId: 8d4087dffdb3d6feef2456918a08ae7724cf18e4
## Why
A WebSocket response can still complete with a final answer while Codex drains it after a mailbox interrupt. Treating the interrupt alone as a reason to resample reopens the turn even when the pending mail can wait.
## What changed
Recheck whether pending mail requires preemption after the drain. When the drain retains a final answer, queue-only mail waits for the next turn's sampling boundary. User steering can still reopen the current turn.
## Testing
Add WebSocket regression cases for queue-only mail after both empty and nonempty final answers, and for user steering received during the drain.
GitOrigin-RevId: 914b51f2de1afc91311667cc05718507717aaaa0
## Why
Status line authors can start rows at the leading edge or distribute
extra space between items. They also need to center or right-align a
group while keeping its configured gaps.
## What changed
Add `justify: "center"` and `justify: "end"` to the row renderer and
TypeScript contract. Align each wrapped line independently within its
available width.
Leading padding uses the row background, stays outside hyperlink
targets, and leaves blank lines unpainted. When the last visible line
fills the width and more lines follow, the renderer can reclaim a
padding cell for the overflow ellipsis.
## Testing
Add rendering coverage for wrapped and nested rows, wide characters,
blank lines, hyperlink boundaries, and overflow. Extend the TypeScript
contract check to cover both new values.
GitOrigin-RevId: 85dd907fe60b5d2cfb759b32058d0876430dd9e6
## Why
Thread summaries need the first session metadata and preview events. Reading
each line asynchronously and parsing unrelated records adds work to every
rollout scanned.
## What changed
Use the buffered rollout reader to scan each plain or compressed rollout in
one blocking task. After reading the first session metadata, skip JSON
parsing for lines without an `event_msg` marker or a Unicode escape that
could encode the event tag.
## Testing
Extend coverage for delayed user messages with escaped or numeric event
tags, preview reads that stop before invalid UTF-8 in plain and compressed
rollouts, and provider filtering for archived threads sorted by update time.
GitOrigin-RevId: 06c996ad3bcc290102f3ecab992e40364cb4dee9
## What changed
Move ID derivation for base instructions and Responses Lite tool definitions
into `ThreadContextIds`. These items keep the same thread-scoped,
content-derived UUIDs when rebuilt for a request.
Invoke prefix ID assignment for newly rendered items during history
replacement and when publishing initial context into empty history.
The UUID allocator leaves these items to ordinary response item ID
allocation.
GitOrigin-RevId: f230a58e3264894bddfd5a250a4b6d1baeabecf0
## Why
Response item IDs and context window IDs use separate generator callbacks.
A shared allocator gives history and inference a single API for both.
## What changed
Use `ThreadContextIds` to allocate response item IDs, retained-context
revisions, and compaction window IDs. Move initial window selection into
`InitialHistory` so resumed threads reuse a valid window ID from their
rollout. Give rollout reconstruction its own allocator.
Assign hook prompt IDs through the session's normal response item
recording path.
## Testing
Move the prefixed UUIDv7 item ID test to the allocator crate and add
coverage for JSON escaping in Guardian's item ID token budget.
GitOrigin-RevId: 31232f50648382033506d1f86815ce7c1de78378
## Why
A failed catalog fetch can leave an explicitly configured Guardian provider
without a classifier. Waiting for another fetch during tool dispatch would
delay the tool call.
## What changed
When a tool call is observed and background scoring is allowed, retry
initializing the Guardian catalog without blocking dispatch. Allow only one
background retry at a time. Check catalog readiness against the current
credentials and schedule initialization if auth needs to be resolved first.
## Testing
Add a regression test that holds the catalog retry open while the first tool
call completes, then verifies that a later call is scored once discovery
succeeds. Cover full-access sessions and mandatory review requirements, where
background recovery is skipped.
GitOrigin-RevId: 2f07bb6bdcfbf22e512f0bd223845f149fa186b5
## What changed
Use `slash_args_elements` in both the chat composer and slash command
dispatch. The shared helper converts text element byte ranges to offsets
relative to the command arguments and clips them to the argument bounds.
GitOrigin-RevId: 72e2fa42bf0d3fc385a58cc13fb6741c896db900
Pass `SamplingUsage` into numeric usage accounting and let the host and
controller paths apply their budget decisions directly. Host-wide
exhaustion stops new work, while turn-only exhaustion returns
`SessionBudgetExceeded`. The controller still stops new work on budget
exhaustion when there is no native rollout budget.
GitOrigin-RevId: 544b9a49a23e2becc68d9cecae347e4d00bbdea0
## Why
Configuration, protocol, and prompt code use in-memory policies and
previously pulled in the Starlark parser through `codex-execpolicy`.
## What changed
Move policy construction, rule validation, and evaluation into
`codex-execpolicy-rules` and use it directly from those crates. Keep
Starlark policy loading and file updates in `codex-execpolicy`, which
re-exports the shared rule types and wraps rule validation errors while
preserving their source locations.
GitOrigin-RevId: 5bc70d3cd387b43a3ad1fcc56af96ad169ac8b13
## Why
Running threads need to pick up changes to approval requirements and
Guardian policy when users reload configuration, sign in, or sign out.
## What changed
Refresh Guardian policy after publishing local config layers so the first
reload uses updated policy fallbacks. Attempt the refresh even if unrelated
user configuration fails to load.
Refresh policy after login while the account owner is still current, and
after logout. If reading account details fails after login, report the
error in the login completion notification and still send the account
update.
## Testing
Extend coverage for changing and removing Guardian policy requirements,
applying requirements despite a config load error, and picking up local
fallbacks on the first reload. Verify that a late low-risk score cannot
release a pending adaptive approval while stricter requirements apply.
GitOrigin-RevId: 95453807a06a0d3c39dcfd9a0f66fd63f41294b9
## Why
Recommendation lookups poll the plugin service for a tooling-state marker even when the cached catalog can still be reused. Install flows and installed-plugin snapshots already give Codex signals to refresh recommendations.
## What changed
Remove tooling-state polling and refresh recommendations on the next lookup after a known install event or a change to the installed plugin inventory or enabled state. Invalidate all product SKUs for the affected plugin service and account scope. If the account changes while a remote install prompt is open, invalidate both account scopes when the user accepts.
Concurrent lookups share a catalog fetch. If a refresh fails, keep serving the last successful result when available and retry on the next lookup.
## Testing
Cover invalidation across accounts, backends, and product SKUs, retention of the last catalog after a failed refresh, and isolation from fetches that complete after invalidation. Update the remote install integration test to exercise the next turn without waiting for the poll interval.
GitOrigin-RevId: 5d2ba84d1118e9346308bf6225543e0e174f8125
## Why
When a client resumes a thread with many pending server requests, replay
can fill the connection's bounded outbound queue if the client reads
slowly. Replaying inline can also stall the thread listener.
## What changed
Replay pending requests in a background task after sending the
`thread/resume` response. Allow one outstanding replay write per
connection and wait for its write receipt to complete or be dropped
before sending the next request. This extends the write-receipt
backpressure used by `command/exec`.
https://github.com/openai/codex/pull/15547
A new resume replaces the previous replay for the same thread and
connection while honoring any outstanding write receipt. Unsubscribing
or disconnecting stops the replay. Before sending each request, check
that it is still pending and apply the human approval eligibility check
where required.
## Testing
Add a regression test with more pending requests than the outbound queue
can hold. It checks that a second resume succeeds while a replay write is
stalled, dropped write receipts let replay advance, and unsubscribe and
disconnect stop replay.
GitOrigin-RevId: 77fc415be0e7b50744f5ccfcaa09857359dd5c55
## Why
An explicit Guardian provider could handle approval reviews, but configuring it
disabled Guardian V2 scoring. This prevented automatic reviews from using
background scores from that provider.
## What changed
Route classification through the configured Guardian provider and use its
classifier catalog for instructions, reasoning effort, review thresholds, and
input limits. Apply the Guardian provider's API-key access policy to classifier
requests and ignore assessments from the actor's response stream when a
Guardian provider is configured.
Keep mandatory review requirements in force and skip background scoring in
User approval mode and Full Access.
## Testing
Extend coverage for separate actor and Guardian providers at startup and after
cold resume, including when both use the same model name. Cover catalog
settings, scoring restrictions, and provider-specific API-key policy.
GitOrigin-RevId: 5f83d1704bacc63033e144bba0d78752283cb590
## Why
A thread can reserve a turn slot and assign a turn ID while it still
waits for host admission. Callers need to distinguish a pending turn
from one cleared to execute.
## What changed
Add `turn_admission_state()` to report `Idle`, `Pending` with an optional
turn ID, or `Admitted` with a turn ID in a single snapshot. Host-managed
turns become admitted after a grant is installed. Native turns are
admitted synchronously, including when no execution guard is needed.
The current slot retains its admitted state through finishing.
Reject superseded submissions before they can overwrite an owned slot,
and verify that a host grant still belongs to the current turn and task
before recording admission.
## Testing
Cover the admission state while a host decision is pending, after an
interrupt, during execution after a grant, and after the slot returns
to idle. Cover native admission without a host guard.
GitOrigin-RevId: 0633dc036aef99433505559c92b0b1b26a023352
## Why
Applying client context at submission time lets input stopped by a hook
affect the conversation. A queued prompt that is later blocked can also
supersede the context attached to an earlier accepted prompt.
## What changed
Keep each context update with its submitted input and apply updates in
delivery order after the input passes its hooks. Preserve context-only
submissions when a turn is suspended for host handoff before inference.
For experimental `additionalContext` on `turn/start` and `turn/steer`,
omission or `null` keeps the current set. A supplied map replaces it on
delivery, and `{}` clears it while preserving conversation history.
## Testing
Add regression coverage for context on prompts stopped by hooks, context
on accepted queued prompts, context-only host handoff, and context
delivery when continuing an idle thread.
GitOrigin-RevId: 160f4f90d9aebf5eb3ea4a939c67265a1c6422da
## Why
A remote exec-server connection could fail during setup if the transport
closed before the client received the initialization response. Callers
waiting for readiness received the failure even if a new connection
could succeed moments later.
## What changed
Share retries among callers during startup, reconnect, and connection
refresh. After a retryable transport or initialization failure, use
backoff and allow new attempts for up to five seconds. Attempts already
underway can finish after that window.
Keep the registry's existing retry policy and reuse the provisioning
deadline across transport retries.
## Testing
Add regression coverage for shared startup recovery after a WebSocket
closes during initialization, registry retry limits and authentication
failures, and child-process cleanup when stdio initialization is
cancelled.
GitOrigin-RevId: 56004badb67f4e5df8d939f2bc6cdfa46246fdb0
## Why
Large file reads over stdio previously allocated both a base64 string
and a complete JSON response before writing to stdout.
## What changed
Keep file contents as bytes until the stdio writer encodes them
directly into the newline-delimited JSON response through a bounded
buffer. Clients still receive the same `dataBase64` field.
## Testing
Compare streamed output byte for byte with the eagerly encoded
response for empty files, inputs that require base64 padding, and
files larger than the write buffer. Check that JSON-RPC conversion
preserves the request ID and base64 payload.
GitOrigin-RevId: 730f201f0905fd15e32b6e9c5b2ef02ca21c7532
## Why
When Windows security policy blocks the sandbox account from signing in,
commands cannot start. The runner error previously gave users only the
failing API call and the numeric error code.
## What changed
For `ERROR_LOGON_TYPE_NOT_GRANTED` (1385), explain the policy denial and
point users to the “Allow log on locally” and “Deny log on locally” settings.
Advise users on managed PCs to contact their administrator.
## Testing
Add a regression test that checks the error explanation and verifies that
the denial does not trigger a sandbox credential refresh.
GitOrigin-RevId: b638bf3d103dc4aec72f2f9c13cb2c8825594e96
## What changed
Stop collecting cumulative MCP tool attribution, sending it in Responses
API request metadata, and writing it to rollout checkpoints.
Use `model_search_state` for search provider history in new rollouts. When
reading older rollouts, decode `mcp_attribution` only to determine whether
Search MCP may have been used. Treat malformed or error attribution as
possible Search MCP use so native search fallback stays disabled.
## Testing
Add a history test that distinguishes legacy Search MCP use, an explicit
record of no use, and missing attribution.
GitOrigin-RevId: a145b5b6b7d2f423d989af10623ef21120f49d4d
## Why
Guardian inherits the actor's inference provider by default. Hosts that run
actors on a different provider need to route Guardian reviews independently
and resolve reviewer policy and model capabilities from the Guardian provider.
## What changed
- Share the selected provider and its model catalog between asynchronous
scoring and blocking approval reviews. Use the provider's preferred
reviewer and resolve policy from managed requirements or reviewer model
metadata.
- Keep Guardian review history independent of actor compaction when the
host selects a provider. Preserve inherited routing when no provider is
selected.
## Testing
Add integration coverage for separate actor and Guardian endpoints, catalog
isolation when both share an endpoint, and routing after resuming a compacted
thread.
GitOrigin-RevId: 1eb15421f746a58eefe27257e86d948de31bcf86
## What changed
Choose the full config or shell environment filter schema inside the
diagnostics module. Config loaders call the helper for the validation
that failed without passing a deserialization type or the
`config.toml` filename. Both helpers use the same layer traversal and
source location reporting.
GitOrigin-RevId: 5dcc7984b907e3769904c303cd08577c6faf4769
## Why
A Guardian policy refresh could leave a thread using its previous restrictions
if the new policy disallowed its current model. A refresh could also report
success after its managed policy source changed before publication.
## What changed
- Use the app server's configuration manager to load Guardian policy from
current local and managed configuration. Report an error when the policy
source changes before publication or a live thread rejects the update.
- Apply updated reviewer and model restrictions even when they block the
current model. Keep automatic work queued while the model is blocked and
wake it when a later refresh permits it. Allow a new turn to supply a
compliant replacement model.
## Testing
Regression tests cover policy changes during thread startup and live refresh,
queued work resuming after a blocking policy is lifted, and updated policy
text reaching Guardian reviews without reconnecting MCP.
GitOrigin-RevId: c7d3e119aa409342cc2fa18946ce2b6a4392e0e3
## Why
Sidebar previews load a snapshot of the file when opened, so edits on disk
leave the open tab showing stale content.
## What changed
Watch each previewed file’s parent directory through the app server so the
preview refreshes even when an editor saves by atomically replacing the file.
Poll every three seconds when a watch cannot be registered, and resubscribe
when reconnecting to the same backend.
Preserve the text preview’s reading position across reloads, including when
the file temporarily becomes unreadable and then returns.
## Testing
The sidebar test covers atomic saves and recovery after moving a directory
away and back. It checks that the tab shows updated content at the existing
reading position.
GitOrigin-RevId: d5f7507d1a81a118fb10a0febf5e274c18f19d81
## Why
An unsupported `\underbrace` leaves the display equation as LaTeX source,
so readers have to interpret which terms each label groups.
## What changed
Render `\underbrace{expression}_{label}` with a Unicode brace that spans
the expression's terminal columns and a label centered below it. Keep
surrounding math aligned with the expression. Inline math, unsupported
arguments, and layouts that exceed the available width still use the
existing fallback.
## Testing
Add a snapshot for labeled Boolean clauses, short expressions, and labels
wider than their expressions. Check fallback for inline, malformed,
nested, multiline, and over-width cases.
GitOrigin-RevId: 8fbe92d512d06c73cf21247343ad869743bebd0c
## What changed
Request emoji presentation for the cloud marker in thread labels.
Preserve the emoji variation selector immediately after the cloud
symbol in Unicode terminal titles and keep GNU Screen titles ASCII.
## Testing
Update rendering snapshots for the task overview, side panes, mentions,
resume picker, and thread identity displays. Extend the terminal title
test to cover the cloud marker in both title encodings.
GitOrigin-RevId: 15959a0760f63a45d8fff917df2e008cda7536a5