Commit Graph
706 Commits
Author SHA1 Message Date
ioanbudea-OAI 7fcb825b46 Persist Guardian retention limits in thread settings (#62827)
## 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
2026-11-20 20:08:33 +00:00
yitaoh-oai 4360c5f813 Remove model-selected Search MCP routing (#62808)
## 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
2026-11-20 17:46:32 +00:00
cassirer-openai 076ac7856b Link agent tool calls to delivered messages in rollout traces (#62709)
## 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
2026-11-20 08:49:07 +00:00
Anthony Tafoya ffa05c8bfb Prewarm executor capability discovery during remote startup (#62674)
## 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
2026-11-20 05:17:34 +00:00
Vivian Fang a0a30c40e8 Add thread and child retention policies for injected items (#62654)
## 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
2026-11-20 02:59:58 +00:00
Owen Lin 10ca17496f Pass inherited history visibility to the thread store (#62644)
## 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
2026-11-20 02:02:55 +00:00
Anthony Tafoya e720e6c80b Reuse executor Discovery V2 inventories across turns (#62640)
## 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
2026-11-20 01:48:00 +00:00
Ruslan Nigmatullin 30607648d9 Centralize request and prefix ID handling in ThreadContextIds (#62635)
## 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
2026-11-20 01:20:38 +00:00
Ruslan Nigmatullin 583ec348cf Centralize thread context ID allocation (#62633)
## 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
2026-11-20 00:44:31 +00:00
Dylan Hurd b16fddf9d0 Apply additional context when turn input is delivered (#62602)
## 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
2026-11-19 21:44:38 +00:00
Owen Lin 30c69e60a3 Remove cumulative MCP attribution from requests and rollouts (#62589)
## 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
2026-11-19 21:06:08 +00:00
XMLIU-oai 5f8c36e836 Support a host-selected inference provider for Guardian (#62588)
## 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
2026-11-19 20:43:32 +00:00
ioanbudea-OAI 90dd6cf9df Enforce refreshed Guardian policy on running threads (#62585)
## 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
2026-11-19 20:26:00 +00:00
jif 3869f396aa Keep async Guardian scoring active for serving probes (#62571)
## Why

A serving probe that reports no review needed can bypass async scoring.
Keeping the async path active lets Guardian compare the two signals
while using the existing approval policy.

## What changed

Treat streamed review flags as observations. Match each flag to its
response item, carry the enclosing item's flag into Code Mode tool
calls, and discard the flag when a pre-tool hook rewrites the payload.

Emit correlated `codex.guardian_probe_comparison` logs for tool calls,
async classification outcomes, and synchronous review results.

## Testing

Update integration tests to expect async scoring even when a probe
reports no review needed, and verify that Code Mode retains the probe
across yield and resume.

GitOrigin-RevId: 715f56ba4a82d544ce59f0291bcd1a84dd2daa51
2026-11-19 18:54:22 +00:00
Bryan Ashley 65454c7b99 Add OpenTelemetry for subagent lifecycles (#62567)
## Why

Correlating a subagent's creation, turn attempts, and stop requests
helps explain what happened when those actions span workers.

## What changed

- Emit structured events and counters for successful spawns and accepted
  `close_agent` and `interrupt_agent` calls. Count accepted stops even
  when the target is already idle or unloaded.
- Track initial, follow-up, and resumed turn attempts for spawned
  subagents. Record each start and at most one outcome per attempt:
  completed, failed, interrupted, or suspended.
- Use thread, turn, and call IDs to correlate structured events while
  keeping those IDs out of metric labels.

## Testing

Add coverage for lifecycle counts, duplicate outcomes, stop handling,
and event correlation across workers. Improve the Windows elevated
sandbox test for an approved `git pull` by provisioning the sandbox
before the turn and reporting setup or launch failures with diagnostics.

GitOrigin-RevId: bc1190302e1dffbdd79c7ac984b6debe1dac4a65
2026-11-19 18:39:32 +00:00
akak-oai ed9becd2fc Report why turn critical path capture is incomplete (#62357)
## Why

The `incomplete` status alone gives no indication of which timing dependency was missing or which operation prevented capture.

## What changed

Emit deduplicated `critical_path_incomplete_reasons` in turn analytics for incomplete captures. Reasons cover unsupported Code Mode and agent operations, unattributed reviews and user waits, missing turn starts, and forced teardown, with an `unclassified` fallback. External tools that share a built-in name can still invalidate capture without being classified as the built-in operation.

During interruption, use the task's join result to distinguish forced teardown from normal completion so a task that already finished can still report a complete path.

## Testing

Add coverage for analytics serialization, concurrent reason deduplication, tool name collisions, and interrupted tasks that finish normally or require forced teardown.

GitOrigin-RevId: fab9aa1ff881997a34dcf75adc5638133cedc7fe
2026-11-18 20:29:59 +00:00
bkotsopoulos 0ba514837d Measure plugin recommendation latency during initial context setup (#62326)
Record how long initial context assembly waits for prompt-only plugin
recommendations in `codex.initial_context.plugin_recommendations_wait_ms`.
Use named info-level spans for loading recommendations, reading the
tooling change marker, and fetching the recommendation catalog.

GitOrigin-RevId: 67b26f79252f8cba6e770f43df252ec1d73a569f
2026-11-18 17:57:12 +00:00
viyatb-oai 6257fbc4bd Move sandbox preparation into platform backends (#62317)
## What changed

Have `SandboxManager` handle backend selection and shared preparation, then
delegate command wrapping and session setup to the Linux, macOS Seatbelt,
Windows token, and Windows MXC backends.

Centralize Windows managed proxy routing in `codex-sandboxing` so the exec
server and other callers use the same rule for selecting dedicated MXC
listeners.

GitOrigin-RevId: a75886809aefebf6c267bb39dbc104f76bda3409
2026-11-18 17:09:03 +00:00
Zahan Malkani bd00a8a42e Preserve pending realtime speech when a call ends (#62299)
## Why

A realtime call can end with completed speech that has yet to reach a
Codex turn. The next turn needs that context even if the call's transport
has already disconnected.

## What changed

- For V3 calls with realtime frame history enabled, save pending speech
  as context for the next turn. Restore it on thread reload and exclude
  it from the turn count used by rollback.
- Drain already received transcript events and settle pending handoffs
  before saving the call's closing marker. Report recovery required if
  shutdown cannot confirm that history was saved.
- Keep transport detach separate from ending a call. Reattaching restores
  saved pending speech, and an open call can be ended from persisted
  history after a reload. Use the call ID for TUI attachments so successive
  calls on one thread have distinct history.

## Testing

Add coverage for queued speech at hangup, reconnect and stop after
reload, retries after an uncertain write, and rollback across saved
session-end context.

GitOrigin-RevId: 657491f1d7e446a1a48e22189758810c8bdd82cb
2026-11-18 15:24:29 +00:00
Zahan Malkani ad5dd4a110 Persist realtime handoffs before accepting turn input (#62288)
## Why

Realtime history needs to record which transcript frames reached the
coding agent and which turn received them. If a handoff fails or the
conversation reconnects, Codex needs to distinguish speech that was
already used from speech that is still available for the next input.

## What changed

- Route handoffs through normal turn admission to start or steer a turn.
  When realtime frame history is enabled, persist the transcript frames
  and the receiving turn's input before publishing acceptance or exposing
  the input to the model. Attribute only transcript frames represented
  in the rendered input.
- Reserve transcript frames across overlapping handoffs and release them
  on definite rejection. Retry an uncertain write with the same input
  and require history recovery if the write still cannot be confirmed.
- On V3 reconnect, restore persisted speech that has not been consumed
  and put it before newly captured speech.

## Testing

Add regression tests for attribution after transcript truncation,
overlapping handoffs, V3 reconnect ordering, and preservation of typed
input when a handoff in the same turn fails before model sampling.

GitOrigin-RevId: 432dd51971f7ced20344ebc7f0c7b007bb849f54
2026-11-18 14:26:53 +00:00
Zahan Malkani 6d9f0199ed Refactor realtime handoff and history access (#62245)
## What changed

Move realtime text routing into `realtime_handoff` and keep it on the shared start-or-steer path. Extract UTF-8-safe range selection for realtime delegation truncation.

Use `RolloutItem` accessors for realtime timestamps and items in recording, clock restoration, and thread history reads. Pass annotated response items to turn-boundary checks in core and migration rollback so callers can work directly with history envelopes.

GitOrigin-RevId: 3dd37cf91ee5abdca84e87b7d7e304749d9baf04
2026-11-18 09:55:30 +00:00
Ruslan Nigmatullin 86d0e458e3 Prevent duplicate initial context when injection races the first turn (#62206)
## Why

A first user turn and a concurrent raw response-item injection can both
observe that the session has no reference context. Both can then append
the initial prompt prefix and persist a full world-state snapshot.

## What changed

Allow context preparation to run concurrently, then serialize publication
of the initial prefix and its checkpoints. If injection publishes first,
the user turn computes its context updates against the published baseline.
If the user turn publishes first, injection appends only the
caller-provided items.

## Testing

Add an integration test that forces the overlap in both preparation
orders. It checks the first request's world-state updates, verifies that
the follow-up request contains the initial instructions and injected
content once each, and checks that history contains one full snapshot.

GitOrigin-RevId: b66f9c6ccc5d42a2be0e852b4d83b78adbc9e5b2
2026-11-18 06:35:41 +00:00
cassirer-openai c826ca1286 Preserve accepted tool outputs and local resets in rollout traces (#61973)
## Why

Accepted tool outputs may never appear in a later inference request, and request preparation can strip their history IDs. Replay needs to retain these outputs and match them to later snapshots, including trimmed results and outputs with identical wire bodies.

## What changed

- Capture accepted function and custom tool outputs, preserving their acceptance order, identity, and tool provenance during replay.
- Record stripped tool output IDs alongside inference requests so replay can restore identity without changing the captured wire payload. Reuse accepted items and adopt their first model-visible snapshot bodies.
- Record compaction checkpoints for local context-window resets using the selected input and frozen installed history, including goal edits retained during installation.
- Exclude `configuration_update` items from normalized conversation history.

## Testing

Add replay coverage for outputs accepted without subsequent inference, trimmed results, identical outputs with distinct IDs, and acceptance before or after a request snapshot. Extend checkpoint coverage to verify that retained goal edits are captured and later edits do not alter the checkpoint.

GitOrigin-RevId: 70f737782f5000812f389a4e01b9f9690e39549f
2026-11-17 05:35:07 +00:00
Adam Perry @ OpenAI d8d840d32a Capture local attachments before queuing turn input (#61962)
## Why

Queued input can outlive its local attachment files. Reading those files only when rendering a model message can lose media submitted while turn admission is pending.

## What changed

- Introduce `ResolvedUserInput` to carry captured image bytes, audio data URLs, or read errors through session queues and agent input.
- Resolve client attachments on the submitting host before queuing, using a blocking task for local file reads.
- Render messages from captured payloads while preserving original paths and text spans for display, along with image position mappings.

## Testing

Add coverage for rendering and serialization after source files are removed, steered audio retained during pending admission, and local audio errors and display content.

GitOrigin-RevId: 4bbb6bda44167439a8cfdae15d3c476a7b1d336b
2026-11-17 04:08:00 +00:00
Adam Perry @ OpenAI 5b3d2c7fce Extract user input preparation into codex-user-input (#61949)
## What changed

Move local attachment snapshotting and conversion from `UserInput` to model request content out of `codex-protocol` into a dedicated `codex-user-input` crate. Update core, the TUI, and the queue extension to use the new crate, replacing the `ResponseInputItem` conversion methods with `from_user_input`.

Move the associated attachment and message conversion tests alongside the implementation, preserving coverage for image positions, media labels, serialization, and error placeholders.

GitOrigin-RevId: 77d0f94a4cd4c2edc008b9e2e63a989995aab058
2026-11-17 02:43:52 +00:00
jif cff061fca9 Add opt-in item-boundary interrupts for subagents (#61909)
## What changed

Add the multi-agent v2 setting `interrupt_at_item_boundary`, disabled by default. When enabled, `interrupt_agent` lets a subagent finish and retain its current output item while cancelling tools immediately. Later output items are discarded, and retained tool calls that have not run receive an aborted result.

Wait for the interrupted turn's terminal event before starting follow-up input, and prevent idle contributors from restarting the interrupted child.

## Testing

Add streaming tests for retaining an assistant message or tool call, discarding later output, and preserving history and follow-up input when the child resumes. Update configuration and interrupt-routing tests.

GitOrigin-RevId: 8b2b9b1383bfb4eefea7369a40012bebc5fff07b
2026-11-16 23:26:07 +00:00
viyatb-oai effad7568c Allow network policy to enable transparent TCP capture (#61851)
## What changed

- Add `transparent_tcp` to network configuration and managed requirements, defaulting to off. When enabled, route outbound TCP from managed Linux sandbox commands through the managed SOCKS5 proxy without requiring an executor startup flag.
- Propagate the setting through local and remote execution, require an enabled SOCKS5 proxy, and check the executor's `networkProxyTransparentTcp` capability before remote launches.
- Refresh the live proxy when switching between permission profiles with different network settings.

## Testing

Add coverage for configuration-driven sandbox capture, rejection of unsupported launch contexts, execution parameter propagation, and live permission profile changes.

GitOrigin-RevId: c4db87056de116f433a128806bef673802f35397
2026-11-16 18:19:16 +00:00
tongzhou wang 92c1a4dc2e Add response processing after completion and usage accounting (#61577)
## Why

Streaming can dispatch tools before a response finishes and its usage is accounted for. Allow callers to wait for completion and synchronous post-hooks so budget enforcement can block tools from the response that exhausts the budget.

## What changed

- Add `responses.process_mode = "after_complete_response"` to buffer response items and release them in order after completion, synchronous post-hooks, and usage accounting. Keep `streaming` as the default and deliver safety-buffering notifications immediately.
- Track whether response usage has already been charged to avoid duplicate accounting, including during compaction.
- Stop new tools across the agent tree when the rollout budget is exhausted. Coordinate steering with accounting and prevent buffered tool calls from dispatching after steering or cancellation.
- Bound buffered responses to 65,535 events and reject overflow.

## Testing

Add configuration coverage and extend integration tests for buffered output ordering, synchronous hooks, interrupted responses and resume, steering, invalid usage, and budget exhaustion preventing tool dispatch.

GitOrigin-RevId: bd06811cfd50cb701babe6353465c57dfed2a37a
2026-11-14 23:50:12 +00:00
tongzhou wang 81b995a6c9 Unify model request hook lifecycles across sampling and compaction (#61562)
## What changed

- Pair `PreModelRequest` and `PostModelRequest` hooks per sampling or compaction attempt, with distinct lifecycle IDs and cancellation reporting.
- Add `thread_id` and `kind` to hook inputs, distinguishing `sampling`, `foreground_compaction`, and `background_compaction`. Include the provider's `response_id` in post-hook inputs when available.
- Wait for synchronous post-hooks before releasing terminal response events, accounting for usage, or installing compaction results. Allow streaming output and tool execution to proceed before the hook finishes, and cancel synchronous post-hooks when their owning request is interrupted.
- Preserve incomplete-response, budget-exceeded, and hook-denied outcomes across sampling retries and compaction model fallback.

## Testing

Add coverage for streaming and tool ordering, interrupted post-hooks, per-attempt metadata, and foreground and background compaction accounting and installation ordering.

GitOrigin-RevId: 3e808c5b3bf2d5a6a326d9f5be5bbd0359b2d16e
2026-11-14 19:40:12 +00:00
goodman-oai 65a5410f72 Add trusted request-country metadata to Responses requests (#61535)
## What changed

- Add `RequestCountry` for host-supplied country codes. Normalize two-letter ASCII codes to uppercase, omit the field by default, and serialize explicit unknown (`XX`) as `null` to prevent fallback to request provenance.
- Carry `request_country` through thread defaults and captured step settings into Codex backend HTTP and WebSocket requests. Allow live country updates without enabling `step_model_switching`, and preserve WebSocket continuation reuse when the country changes.
- Propagate the captured country to subagents, reviews, and compaction requests.

## Testing

Add coverage for country validation and serialization, thread and live-turn update lifetimes, prewarm settings capture, agent inheritance and reloads, compaction and reviews, WebSocket country changes, and HTTP fallback.

GitOrigin-RevId: 787cd1fa7ba5d465a4eb64a92f13c79e93d9bca7
2026-11-14 15:44:38 +00:00
Zahan Malkani 5943d7acdf Persist timestamped realtime frames before acknowledging completion (#61473)
## What changed

- Record voice transcripts as `frame` items with a `voice_transcript` channel for eligible threads, while retaining legacy transcript support and the existing app-server live and mixed timeline representation.
- Assign first-observed timestamps that never move backward, retain them through completion, and restore the clock floor from history and compaction checkpoints.
- Flush realtime records before completion notifications, including file and initial directory durability barriers for local rollouts.
- Generate a distinct default session ID for each new call, use the call ID when attaching to an existing call, and derive opening record IDs from session IDs.
- Add protocol types for turn-input acceptance and session-end input receipts, excluding those receipts from live notifications and mixed timelines. Update generated schemas and SDK types.

## Testing

Add coverage for frame serialization and required voice payloads, clock rollback and checkpoint restoration, durability barrier failures and retries, per-call session IDs, and persisted transcript availability immediately after completion.

GitOrigin-RevId: 3f6632b517d563861aee085b723475b8945c391c
2026-11-14 06:14:36 +00:00
Ruslan Nigmatullin ecf54824c6 Refactor session mail recording and compaction metadata capture (#61461)
## What changed

- Consume the optional delivery handle directly when recording inter-agent messages.
- Capture compaction resume metadata before constructing the `CompactedItem`.
- Move the existing inter-agent message rollout and resume test into `mail_publication_tests.rs`, preserving its assertions for turn IDs, timestamps, persisted metadata, and restored history.

GitOrigin-RevId: 761a837922377d5a72266d775622211e43fa87d3
2026-11-14 04:16:22 +00:00
Ruslan Nigmatullin c2c1ebba0a Add optional tool output rendering for context window hints (#61452)
## What changed

Add the token-budget setting `context_window_as_tool_output`, defaulting to `false`. When enabled, render agent identity, context window IDs, and associated hints as an `agent.thread_hint` tool output. Use the same format for agent identity updates in forked threads.

Preserve this setting when applying model token-budget defaults without treating it as an explicit budget override.

## Testing

Update fork scenario snapshots to cover tool output rendering, including a child agent's window hint after its inherited parent context and a prediction fork above the compaction threshold.

GitOrigin-RevId: e1a7089935bd0aed44ffd15f0ae3ec41a2607218
2026-11-14 02:55:41 +00:00
Anthony Tafoya d26406987e Add explicit cloud catalog refresh before turn admission (#61449)
## Why

Hosts need to refresh cloud plugin and skill catalogs without starting a turn or waiting for step preparation.

## What changed

- Add `CodexThread::refresh_cloud_plugins()` and a turn-independent extension callback that bypass cached catalog reuse and failure cooldowns.
- Run catalog contributors concurrently while serializing publication with step snapshot capture. Invalidate MCP resource caches before explicit discovery and schedule MCP reconciliation afterward.
- Accept complete and partial catalogs, report discovery errors, and keep failed or cancelled refreshes retryable.
- Allow hosts to gate cloud plugin discovery through effective configuration.

## Testing

Add coverage for discovery before turn admission, catalog replacement and reuse, immediate retry after failure, concurrent contributors, and cancellation-safe publication and invalidation.

GitOrigin-RevId: 83e847fcab6562581af2c9e831b1d2a310f2b270
2026-11-14 02:45:51 +00:00
dob-oai 8afe928a76 Avoid starting dormant REPL servers for cleanup hooks (#61437)
## Why

Bundled `turn_ended` hooks can start an unused REPL server solely to clean it up, even though its deferred startup means there is no process to clean up.

## What changed

Allow bundled cleanup calls for `node_repl` and `cua_repl` to return an empty successful result when startup has never been requested. Limit this behavior to configured, unshared local stdio connections using the legacy MCP protocol. Other calls continue to wait for server startup.

## Testing

Add coverage for the connection eligibility checks and extend subagent hook tests to verify that bundled cleanup leaves unused REPL servers dormant while ordinary hooks can still start cached tools hidden from the model.

GitOrigin-RevId: 0a07772fccd670c53348ff7a702b4bee353e263c
2026-11-14 01:34:12 +00:00
Hung 5158e9780e Add opt-in file-backed tool audio (#61394)
## What changed

- Add the disabled-by-default `file_backed_tool_audio` feature to prepare fresh function and custom tool audio through the attachment store before persistence. Store returned file IDs in history and preserve them on replay without uploading again.
- Validate and budget mixed text and audio output before uploading retained clips, preserving audio token charges and producer limits. Resolve tool audio durations before continuation compaction checks.
- Keep inline audio on backend upload failures and use text placeholders for invalid or rejected clips. Replace unavailable tool audio files with placeholders in prompts while retaining the original history, so restored files can be used again.
- Treat file-backed tool audio as a competing source when attributing audio or unknown-file errors to user uploads.

## Testing

Add coverage for direct tool and Code Mode audio across follow-up turns, file expiration, restoration, and resume in both legacy and paginated history. Extend tests for truncation before upload, upload failure handling, bounded error placeholders, and error attribution.

GitOrigin-RevId: 66c1e7699c7d92f98c3a2d0f5cecbbd63147eb6c
2026-11-13 23:02:16 +00:00
Dylan Hurd 347143f140 Preserve active additional context across compaction (#61390)
## Why

Compaction can drop active client context while deduplication prevents unchanged values from being sent again on subsequent turns.

## What changed

Track additional context by history item ID and restore active items when installing complete or prefix compaction results. Preserve their history order, refresh retained items with their original bounded payloads, and leave queued updates to arrive with their input.

## Testing

Add regression coverage for local compaction with message context and remote compaction with tool-output context. Verify that current context survives exactly once, stale values are absent, and restored context precedes the preserved user prompt.

GitOrigin-RevId: a3114f387c6a4ae1a2d1651993d0f7a101be7dd5
2026-11-13 22:19:12 +00:00
Charlie Marsh 1c76c0bc08 Reduce session submission channel memory with boxed payloads (#61389)
## Why

The bounded submission channel reserves all slots at session startup, including space for a full `Submission` in each slot.

## What changed

Send `Box<Submission>` through the channel so each slot reserves only pointer-sized payload storage, allocating full submissions as needed. Update submission producers, delegate forwarding, and test helpers to pass boxed submissions, and unbox them in the submission loop.

GitOrigin-RevId: d8d9c613683076d74fcb3e2f2cb6244c5857bca2
2026-11-13 22:18:34 +00:00
Alex Zamoshchin 42f950cd11 Refresh plugin recommendations when tooling state changes (#61387)
## Why

Cached recommendations can keep offering a plugin after installation. Refreshing the shared catalog during step preparation can also leave the recommendation prompt and install handler with different candidates.

## What changed

- Check `tooling_changed_at` before reusing recommendations, with a one-second reuse window and a 250 ms deadline that includes authentication. Refresh the catalog when the marker changes, preserving cached recommendations on failure and retrying on a later poll.
- Scope recommendation and featured-plugin caches by product, backend, and account identity, and share concurrent recommendation refreshes.
- Use the same recommendation snapshot for a step's prompt and install handler, while allowing later steps to observe updated recommendations.

## Testing

Add coverage for marker changes, missing markers, refresh failures, concurrent and cancelled requests, and the authentication deadline. Extend integration tests to verify consistent step candidates and stop offering an installed plugin while preserving the original recommendation block in conversation history.

GitOrigin-RevId: 44fa6723a623d9604f0c768118bc6889d2d3b693
2026-11-13 22:16:32 +00:00
Alex Zamoshchin a46c5be77e Delegate installed plugin recommendation filtering to the endpoint (#61374)
## What changed

Request plugin suggestions with `includeInstalled=false` and use the endpoint results without filtering against loaded plugins or the local installed-plugin cache. Retain disabled-tool and client eligibility filtering, and remove plugin loading that was only needed for recommendation filtering.

## Testing

Update tests to verify the query parameter and confirm that endpoint recommendations survive local installed-cache filtering while disabled tools remain excluded.

GitOrigin-RevId: a1b199f9ac8da7dae40abe46b6ccfaf1d8230a5c
2026-11-13 21:00:04 +00:00
Vivian Fang c33002259e Add per-item retention policies for injected history (#61344)
## What changed

Allow `thread/inject_items` to accept wrapped items with `retention: "default"` or `retention: "always"`, while preserving support for raw response items. Persist explicit policies separately from legacy client-authored metadata.

Carry explicitly retained items through local and remote compaction, context-window changes, and child-agent creation, subject to retention budgets. Preserve history order and keep retained tool exchanges together; require matching calls and outputs to be adjacent in the injection request and both marked `always`.

Update Quinn dependencies and record exceptions for additional Hickory DNSSEC advisories where DNSSEC is disabled.

## Testing

Update injection tests for explicit retention metadata and extend the compaction scenario to cover a retained tool exchange across repeated compaction and restart.

GitOrigin-RevId: 1195a4ed62dc162a62e58bc2ad733262fbabea27
2026-11-13 18:46:13 +00:00
Vivian Fang 7844815bd7 Add opt-in prompt image sanitization (#61341)
## What changed

- Add the disabled-by-default `safe_image_decoder` feature to decode and re-encode prompt images without source metadata, with byte and decoded-pixel limits.
- Apply JPEG orientation and supported ICC color conversion to sRGB, emitting PNG for PNG/GIF inputs and JPEG for JPEG/WebP inputs.
- Use the selected decoder for image preparation, `view_image` validation, and MCP image validation. Include the decoder in image cache keys.
- Preserve original inline images in history metadata so resume and fork can regenerate prepared images without repeated JPEG encoding changing their bytes.

## Testing

Add regression tests for identical JPEG replay after history serialization and for preventing legacy cache entries from bypassing sanitization.

GitOrigin-RevId: 718cd83d0a233e2eb8efd1a64c14d8944e44c350
2026-11-13 18:44:31 +00:00
Chris Dong 006911a313 Track dictation usage from accepted user inputs (#61215)
## What changed

Capture `codex_app_used_dictation` as per-input metadata, with patches taking precedence over replacements, and remove the key from metadata forwarded to Responses. Record attribution when user-origin input is accepted into turn history.

Add `used_dictation` to turn analytics: report `true` if any accepted input used dictation, `false` only when every accepted input has known non-dictation attribution, and omit the field otherwise.

## Testing

Add coverage for per-input extraction, patch precedence, and turn-level aggregation. Extend the app-server steering test to verify that dictation attribution reaches analytics while the metadata key is excluded from Responses requests.

GitOrigin-RevId: 0a55687a7dd61f00e9b188f89810e52bd941490b
2026-11-13 00:52:01 +00:00
Bryan Ashley fae87361f4 Add graceful agent-tree suspension and recovery (#61198)
## Why

Suspending a locally controlled agent tree must preserve unfinished turns and child results that arrive during teardown so they remain available after recovery.

## What changed

- Add `ThreadManager::suspend_agent_tree` to stop durable trees, close their writers, and return unfinished root and named V2 child turn IDs plus any pending root wake.
- Persist terminal child results before suspension succeeds, including results queued for evicted parents. Report failed or unconfirmed writes.
- Add `load_suspended_agent` to restore named V2 descendants through their recorded ancestors without starting model turns.
- Allow empty `continue_turn_if_idle` input to wake on saved results, guarded by the preceding turn ID. Keep mail queued until task registration so suspension can preserve it.

## Testing

Add coverage for completion and wake races, child errors, parent writer failures, evicted parents, descendant restoration, repeated suspension after caller cancellation, and ephemeral roots remaining active.

GitOrigin-RevId: 3041791f51bff2555210f6b2d2443f9f05f68330
2026-11-12 22:43:14 +00:00
Ruslan Nigmatullin 77cbcdb4a6 Preserve thread-local model ID state across replay and compaction (#60942)
## What changed

- Initialize item and context-window ID generators per thread, reuse the stored window on resume, and give history reconstruction a separate item generator.
- Recover item ordinals from checkpoint replacement history, guardian history, and retained context without lowering the cursor established by earlier records.
- Stamp compaction resume metadata with the next item ordinal in append order, tracking the cursor in local and in-memory thread stores.

## Testing

Extend the history ordinal test to verify that a checkpoint records the cursor at its position in a batch, excluding later allocations.

GitOrigin-RevId: 7121b747a039dc5477235078702137d1ff74e789
2026-11-12 00:27:01 +00:00
Ruslan Nigmatullin 9e6d1c5278 Preserve retained assistant revisions across rollout replay (#60839)
## Why

Replaying delivered assistant messages allocates new retained-source revisions instead of preserving those captured in live history.

## What changed

- Capture retained sources when recording assistant deliveries, persist them in rollout metadata, and reuse their revisions during replay.
- Add optional `next_item_ordinal` compaction metadata and a `next_model_id_ordinals` helper to recover item and window allocation positions from checkpoints and subsequent records. Ignore allocation metadata that refers to other threads.

## Testing

Extend tests to compare live and replayed delivery sources, preserve revisions through an older reader's rewrite, and verify ordinal recovery from checkpoints and subsequent local items.

GitOrigin-RevId: cfdeebe8e13b1700b34b9c98696880a90a99ace5
2026-11-11 18:56:47 +00:00
Dylan Hurd 3a89580f08 Hand off approved plans through attachments in fresh sessions (#60763)
## What changed

Make “Yes, clear context and implement” save the approved plan as an app-server attachment and submit a short prompt referencing it. Add the experimental `thread/prepareApprovedPlan` request to verify that the fresh thread's executor can read the file and that its contents match the approved plan.

If the attachment cannot be written or read, inject the complete plan as `proposed_plan` tool output within the model's context and truncation limits. If the complete plan cannot fit, report an error and keep the current session. Clear the UI and switch threads only after plan preparation succeeds.

## Testing

Add TUI tests covering a large plan read from its attachment, complete fallback context when attachment writes or reads fail, and preservation of the original session when the fallback is too large. Snapshot the fresh thread's initial request.

GitOrigin-RevId: b717f30359256994c6efb3f4fe7f87aabe8936af
2026-11-11 09:01:04 +00:00
Ruslan Nigmatullin 4f8205c808 Use typed context window IDs throughout thread persistence (#60757)
## What changed

Carry `ContextWindowId` through session metadata, compaction checkpoints, rollout recording, and thread creation instead of converting IDs to strings. Add deserialization and JSON schema support while preserving the serialized string format and legacy numeric compaction IDs.

Validate deserialized IDs as UUIDv7 values before restoring context windows, preserving the existing handling of unsupported IDs.

GitOrigin-RevId: fda329d0654f438171a955c9f75550817c32c047
2026-11-11 08:16:52 +00:00
felixxia-oai fad8b3d5bc Initialize Guardian evidence cursors from thread history state (#60670)
## What changed

Expose history initialization and the effective history mode to thread-ready contributors. Add `EvidenceCursor::at_thread_ready` with paginated-history validation:

- Start new or cleared threads at position zero without requiring an existing rollout.
- Start resumed, forked, or supplied-history threads at the durable tail to avoid backfilling existing evidence.
- Skip the initial `SessionMeta` header when capturing evidence from position zero.

## Testing

Extend evidence tests to cover initialization before a rollout exists, capture of the first original record, rejection of resume without a rollout, and exclusion of existing records on resume.

GitOrigin-RevId: 32aa8e2afb71eb4e882b5f1fb107ac8616b33c8e
2026-11-10 22:00:08 +00:00
rhan-oai 30b42cb802 Keep interrupts responsive during host service-tier updates (#60644)
## Why

Waiting for host acceptance of a service-tier update in the submission loop can block interrupts while the host receipt is pending.

## What changed

Move the host acceptance wait out of the submission loop while keeping explicit thread settings replies pending until acceptance completes. Report handoff failures to the caller while preserving the locally committed settings, and allow a subsequent explicit request for the same tier to retry a failed handoff.

## Testing

Add a WebSocket regression test covering interrupts with pending host receipts, failure reporting, same-tier retries, and continued thread operation after startup caller cancellation.

GitOrigin-RevId: 1b27d156eba3ebb47e717a987f41f4f595635be8
2026-11-10 19:13:55 +00:00