## What changed
- Inherit paginated history mode when spawning or forking a subagent from a paginated parent.
- Load the parent's model context when forking and persist it as an inherited rollout prefix, while excluding that prefix from the child's projected turns, items, and metadata.
- Record the boundary between inherited context and child history, and reject partially initialized paginated subagent rollouts on resume.
- Resume paginated subagents from their stored model context instead of legacy rollout history.
## Testing
Added coverage for fresh and forked paginated subagents, compacted-history forks, model-context resume, inherited-prefix projection, metadata isolation, and incomplete-prefix detection.
GitOrigin-RevId: e57dc37c29aa4aaaf57b052b991be591d730e5ba
## Why
Elevated Windows sandbox setup could turn the built-in read-only protections
for workspace metadata into deny-write paths, creating metadata directories
that did not already exist.
## What changed
- Track whether filesystem permission entries come from a built-in profile or
were explicitly configured.
- Exclude generated metadata defaults from direct Windows deny-write overrides
while continuing to enforce explicit read-only carveouts for the same paths.
- Preserve the distinction while materializing and normalizing permission
paths, without exposing generated defaults as user configuration.
## Testing
Added Windows coverage confirming that elevated sandbox setup leaves missing
workspace metadata absent and still produces overrides for explicit metadata
carveouts.
GitOrigin-RevId: 701bcb229f631b18ab5ced22f3edf6f303d932f3
## What changed
- Let deferred environments provide selected capability roots with their ready signal.
- Validate that those roots have unique, non-empty IDs, belong to the registering environment, and stay within the root limit.
- Include roots from ready turn environments when resolving MCP contributions, and refresh the MCP runtime when the selected root set changes.
- Expose the exact ready root set to MCP contributors so executor plugins become available with their environment.
## Testing
- Cover ready-root propagation, validation failures, replacement isolation, reconnection, and MCP plugin availability refresh.
GitOrigin-RevId: ec3498aab1164824025094e96a9b1063b7b731ad
## Why
Queue-only child-agent updates that arrive around a final answer should not
restart sampling, but they must remain available to the next turn. Explicitly
injected response items still need to reopen the current turn.
## What changed
- Defer queue-only inter-agent mail after a final answer without treating it as
same-turn pending input.
- Re-enable current-turn mailbox delivery when the model requests a follow-up,
a stop hook continues the turn, or a response item is explicitly injected.
- Check for turn-triggering mailbox work after clearing the completed active
turn so pending work can start safely.
## Testing
Added coverage that queued child mail waits for the next user turn and that an
injected response item after a final answer triggers a follow-up request.
GitOrigin-RevId: aa81d00707943284b7ab069b60970e547908c895
## Why
Cached MCP tool catalogs must not substitute stale session state for the live
server connection.
## What changed
- Verify `mcpServerStatus/list` waits for replacement stdio server metadata
before combining it with cached tools.
- Verify configurations with remotely sourced environment variables bypass the
tool catalog cache.
- Assert that calls made from cached definitions return output from the live
replacement process.
- Make the stdio test server available to Windows Bazel integration tests.
GitOrigin-RevId: 0e518cd46f0d89af28e3a4e256023b5872e6e2fb
## Why
Token-budget sessions need a final opportunity to preserve important state before the current context is compacted.
## What changed
- When `auto_compact_fallback_prompt` is configured, reserve `auto_compact_fallback_buffer_tokens` beyond the base auto-compaction limit.
- At the base limit, inject the fallback prompt once as a developer message while keeping the normal tool surface available. Continue reporting zero base-window tokens during this reserve.
- Roll over when the reserve or full model context is exhausted, and skip the fallback when a new context was already requested.
## Testing
Added coverage for using the fallback reserve, rolling over after it is exhausted, and bypassing the fallback for an explicit `new_context` request.
GitOrigin-RevId: 32983ecadc5cb4927e15ecd7b1e896cb52a9ad3b
## Why
Core filesystem permission models operate on native absolute paths, while exec
sandbox contexts must serialize paths as portable URIs.
## What changed
- Make the core filesystem permission and profile types concrete over
`AbsolutePathBuf` instead of generic over their path representation.
- Add exec-specific permission types that convert native permission paths to
`PathUri` values at the sandbox protocol boundary.
- Replace the legacy read/write-roots tuple with a named
`LegacyReadWriteRoots` struct.
## Testing
- Add coverage that exec sandbox permission paths serialize as URIs and round
trip through the filesystem protocol.
GitOrigin-RevId: a0ef5f8aba9bbfdf00a00fcc4f199314836bc85d
## Why
Sparse and out-of-order rate-limit updates can omit account metadata or let an
older full read overwrite a newer workspace hard stop. Credit availability also
does not always include a displayable balance.
## What changed
- Propagate the backend's `spendControlReached` state through rate-limit
snapshots and the app-server protocol, preserving it across sparse updates.
- Keep workspace hard-stop classifications for error routing and ignore stale
full-read results after a newer hard-stop notification.
- Base TUI warnings and model-switch prompts on credit availability and hard-stop
state, and show `Credits: Available` when a finite balance is hidden.
## Testing
Added coverage for spend-control mapping, snapshot merging, out-of-order reads,
workspace error routing, warning and prompt behavior, and credit status display.
GitOrigin-RevId: 18b09d493d5a620a7c079fb721ec50b38dd5b04c
## What changed
Resolve approval test targets outside the workspace relative to the test's
temporary home instead of the process working directory. This keeps the targets
outside the test workspace while containing them in the test environment.
GitOrigin-RevId: 871e840d658468c56d603afc10cc226f918bba5a
## Why
Starting a new session should not have to wait for an unchanged stdio MCP
server to initialize before its tools can be presented to the model.
## What changed
- Cache recent tool catalogs for matching stdio MCP server configurations and
use them while a new live connection starts in the background.
- Bound the process-wide cache to 32 entries with a 30-minute TTL, and key
entries by the server configuration, environment, working directory, and
elicitation capabilities that affect the catalog.
- Keep connection-specific instructions and tool annotations out of cached
catalogs. Resolve tool calls against the live connection so tools that are
unavailable or hidden in the new session cannot be invoked from stale data.
- Publish only the newest completed catalog fetch and do not cache HTTP servers
or stdio configurations that depend on remotely sourced environment values.
## Testing
- Add coverage for cache expiration, environment changes, catalog sanitization,
and out-of-order refreshes.
- Add an end-to-end test that starts inference from cached definitions while a
replacement MCP process initializes, then verifies calls and visibility
against the live process.
GitOrigin-RevId: 2ed0f29ba53ace12532730f951b175c588aa3ae7
## What changed
- Add an optional `policy_template` field to auto-review model messages.
- Build Guardian instructions from the catalog template when present, while
preserving the existing precedence for managed and catalog policy content.
- Fall back independently to the bundled template and bundled policy, and
preserve explicit empty catalog values.
## Testing
- Cover missing and empty template deserialization, policy precedence, bundled
fallbacks, and Guardian prewarm instructions.
GitOrigin-RevId: 93116dadbc9bf40527882844a428caed4159fff6
## What changed
- Replace pending WebSocket URL registration with deferred Noise environment
registration that gates connection attempts on an explicit readiness signal.
- Reuse the Noise rendezvous transport after readiness so reconnects request a
fresh connection bundle.
- Preserve terminal errors for failed or dropped registrations and keep late
completion isolated from replacement environments.
## Testing
- Add coverage for readiness gating, registration failure and replacement,
eager Noise connections, and reconnection through a fresh rendezvous bundle.
GitOrigin-RevId: 83e23fa03a02e3b2bdf1a83fe26d7ac461f55cf3
## What changed
- Define `SleepItem` in `codex-extension-items` and carry `clock.sleep` events through `TurnItem::Extension`.
- Preserve sleep persistence, thread-history reconstruction, and the app-server's `type: "sleep"` schema while reusing the extension-owned type.
## Testing
- Add serialization coverage for the `clock.sleep` extension wire shape and its protocol wrapper.
- Update sleep lifecycle and thread-history tests to exercise the extension-owned item.
GitOrigin-RevId: 34bb33ed9b90a09bf4744aafdb56e019c717a168
## What changed
- Add per-sandbox-mode permission messages to `ModelMessages` and preserve them when applying model configuration overrides.
- Use the selected catalog message in permission instructions, substituting `{{ network_access }}` with the active network policy. Fall back to the existing sandbox text when no override is provided, and allow an empty override to omit only the sandbox section.
- Apply catalog permission messages when a session starts and when its model changes.
## Testing
- Cover catalog deserialization, mode selection, network substitution, fallback and empty-message behavior, remote model catalogs, and model changes.
GitOrigin-RevId: cd5ed3aee3155dca0e7b2358c0f09bae73236856
## What changed
- Accept a caller-provided `CodexAppsToolsCache` when constructing a `ThreadManager` and pass it through to the MCP manager.
- Add `ConnectorRuntimeManager::new_without_cache()` for an in-memory runtime that neither loads nor persists connector state on disk.
- Re-export `CodexAppsToolsCache` from `codex-core` and `codex-core-api` for embedders.
## Testing
- Verify that a cache-disabled connector runtime ignores existing disk state and publishes live tools without creating cache files.
GitOrigin-RevId: f52f4f27c425a8d84ad0d0987b30a6fc3c14d702
## What changed
- Default `prompt_cache_key` to the session ID from response metadata instead of the thread ID.
- Preserve explicit prompt cache key overrides.
- Verify that API-key-authenticated root and subagent requests use the same session-based cache key even though they have different thread IDs.
GitOrigin-RevId: cb1bf21a3cb8fa2c5083c5c6afd4829ff2adcf1f
## Why
Multi-environment turns can run against different filesystems, so a single
thread-wide workspace-root list cannot accurately describe every selected
environment.
## What changed
- Add optional `runtimeWorkspaceRoots` to each app-server environment selection.
Omitted roots default to that environment's `cwd`, while an empty list selects
no roots.
- Carry environment-native roots through turn selection, model-visible context,
permission materialization, and tool sandboxing.
- Keep the top-level `runtimeWorkspaceRoots` field as a compatibility input when
constructing default environment selections; explicit selections use their
own roots.
## Testing
- Cover thread and turn API defaults, overrides, empty roots, and schema
round-tripping.
- Verify foreign roots remain model-visible and remote execution applies the
target environment's roots before sandbox selection.
GitOrigin-RevId: c6e7a62883c45c676c153055f46a55ee15a323a4
## Why
Embedding callers need to control whether model catalogs are persisted to disk.
## What changed
- Accept a shared models manager when constructing `ThreadManager` instead of always creating a cached manager internally.
- Add provider APIs for creating uncached model managers. OpenAI-compatible providers fetch on each `OnlineIfUncached` refresh without reading or writing `models_cache.json`.
- Keep existing app server, MCP server, sample, and test callers on the standard cached manager.
## Testing
- Verify an uncached manager fetches on every refresh.
- Verify an injected uncached manager controls thread refresh behavior and does not create `models_cache.json`.
GitOrigin-RevId: 8bb646054ecec4ccb865b2bf56249384916ea9db
## Why
Policy-blocked proxy requests must terminate the corresponding active tool call and preserve the correct approval result, including when multiple calls are running concurrently.
## What changed
- Resolve a blocked request's execution ID to its registered active network call before recording the policy denial.
- Preserve an outcome already recorded for that call, and cancel the owning call after storing a new denial.
## Testing
Expand network approval integration coverage for Guardian and user decisions, permission hooks, persisted policy amendments, concurrent calls, timeouts, cancellations, and unattributed proxy requests.
GitOrigin-RevId: 961901bbc07cc498309453ec78cda1a56ab00a4b
## Why
Compacting a resumed conversation can fail when its previous model is no longer
available. Some model-specific failures, such as a model-not-found response, are
not represented as invalid requests and therefore did not trigger the existing
fallback to the currently selected model.
## What changed
- Share a retry predicate between both remote compaction implementations.
- Fall back to the current model for invalid requests, unexpected statuses,
context-window and usage-limit errors, server failures, and exhausted retries.
## Testing
Add an integration test that resumes a conversation whose previous model returns
model-not-found and verifies that compaction and the next turn use the renamed
model.
GitOrigin-RevId: c3857beae2ce79b50589deb13c2e59710ce14725
## What changed
- Add an `auto_review.policy` field to model catalog messages.
- Use the selected Guardian model's catalog policy for review-session instructions, while preserving the precedence of `guardian_policy_config` and falling back to the built-in policy when neither is present.
- Preserve auto-review messages when model instruction overrides remove catalog instruction templates.
## Testing
- Cover configured-policy precedence, explicit empty catalog policies, catalog-message preservation, and propagation of the catalog policy into a prewarmed Guardian session.
GitOrigin-RevId: 26b61ae2958ea8325a64834dcf91f47e140d74b3
## Why
Network proxy enforcement on Windows requires the elevated sandbox backend. Silently selecting that backend for an unelevated configuration makes the effective sandbox differ from the configured mode.
## What changed
- Reject enabled network proxy configurations on Windows unless managed requirements allow only the elevated sandbox and `windows.sandbox` resolves to `"elevated"`.
- Preserve the configured sandbox backend during execution and validate proxy compatibility at config loading, sandbox setup, and process launch boundaries.
- Defer this validation during cloud-config bootstrap so authoritative managed requirements can be loaded first.
- Do not start or expose disabled Windows proxies, and render transitions to disabled networking as `<network enabled="false"></network>`.
## Testing
- Cover Windows requirement and sandbox compatibility matrices, bootstrap behavior, backend selection, disabled proxy handling, and environment-context updates.
GitOrigin-RevId: bfa1dda98594e0db61883f8e7f65bd560e3453e6
## Why
After a cold resume, a Multi-Agent V2 root thread must still be able to
address its persisted descendants even though their runtimes are not reopened
eagerly.
## What changed
- Restore metadata for open descendant agents when resuming a V2 root thread.
- Preserve each descendant's path, nickname, and role while leaving its runtime
unloaded until a message targets it.
- Reuse the spawn metadata preparation path so restored identities retain the
same reservation and naming checks as newly spawned agents.
## Testing
Added an end-to-end cold-resume test that follows up with a persisted agent by
name and verifies that the original agent thread is loaded on demand.
GitOrigin-RevId: a1663c1ae60eefadb948cd39f933cd3bbb49a492
## Why
OAuth metadata discovery for an optional HTTP MCP server can stall, delaying
`thread/start` even though that server is not required.
## What changed
- Remove eager MCP authentication-status discovery from session and connection
manager startup.
- When an MCP connection reports an authentication error, inspect configured and
stored credentials locally to preserve login and reauthentication failure
reasons without making another discovery request.
- Continue using server configuration directly for startup error messages and
timeout hints.
## Testing
Add an app-server regression test with an optional HTTP MCP endpoint that accepts
a connection but never responds, and verify that `thread/start` completes without
waiting for its configured startup timeout.
GitOrigin-RevId: 56fe0188cc1ceaf746b0b65e8b7dd1fd2e13420d
## Why
After switching from proactive delegation to explicit-request-only mode, an
earlier proactive instruction can remain in the conversation context. The new
mode must clearly supersede that instruction.
## What changed
Update the explicit-request-only developer message to cancel earlier proactive
delegation instructions before requiring delegation to be explicitly requested
by the user, `AGENTS.md`, or a skill.
## Testing
Update the multi-agent mode integration test expectation for the explicit-mode
instruction emitted after a cold resume.
GitOrigin-RevId: 0a6d18f38ef82d29cf4f3bfcfd4ac84738a39598
## Why
Paginated thread history needs durable ordering so consumers can process a rollout suffix without rebuilding all earlier history.
## What changed
- Add optional, zero-based ordinals to `RolloutLine` records in paginated rollouts while leaving legacy rollout serialization unchanged.
- Continue ordinals from the last valid record when appending or resuming, including after gaps or an incomplete tail, and reject overflow without appending.
- Add a stateless `project_rollout_line` helper that maps canonical turn lifecycle and completed-item records into thread-history change sets.
## Testing
- Cover ordinal assignment, legacy compatibility, resume and tail recovery, overflow handling, and thread-history projection for completed, failed, and interrupted turns.
GitOrigin-RevId: 3a9bb6cd2a1f674a9f154342e96e9aa3d8330781
## What changed
- Add a `ResponseItemId` type that generates item-specific prefixes with UUIDv7 suffixes and use it across response items.
- Keep deserialization permissive for legacy histories, but omit empty or unprefixed item IDs from HTTP and WebSocket requests.
- Export the new type in the generated TypeScript protocol schema.
## Testing
- Cover prefixed ID generation, legacy deserialization, prefix recognition, and outbound request filtering.
GitOrigin-RevId: 0209fe430c826d0ae88bc4648652c4ebf390c4a4
## What changed
- Add `supports_reasoning_summary_parameter` to model metadata, defaulting to
`true` for backward compatibility.
- Omit `reasoning.summary` and its summary-delivery stream option when the
selected model does not support the parameter.
- Apply the capability of the final selected model when a spawned agent uses a
different model.
## Testing
- Cover unsupported models in regular requests and spawned-agent model
overrides.
GitOrigin-RevId: 72b783799fc0685cef1501ef2dbf62d1308ceead
## What changed
- Add an optional `error` payload to `TurnCompleteEvent` and omit it when a turn completes without an error.
- Preserve the full terminal `ErrorEvent` through the turn lifecycle so the completion event includes the same error details emitted separately by `EventMsg::Error`.
## Testing
- Extend the stream-error integration test to verify that `TurnCompleteEvent` contains the emitted error and that the next turn can still proceed.
GitOrigin-RevId: 8d32942a44132763076130102d8b89ab356d59d0
## Why
Model catalog instructions can include a baked-in `# Personality` section. An
explicit `none` setting should omit that section instead of sending it as part
of the model's base instructions.
## What changed
- Pass the configured personality into the models manager.
- When personality support is enabled and the setting is explicitly `none`,
remove the `# Personality` section through the next level-one heading from
catalog base instructions and instruction templates.
- Preserve explicit `base_instructions` overrides and avoid warning when no
personality was requested.
## Testing
Added unit and integration coverage for section removal, heading boundaries,
CRLF input, preserved configurations, and explicit base instructions.
GitOrigin-RevId: 452c88d3ac6001c2ac7d4fef269cd75dc239fa61
## What changed
- Stop the TUI and app server from inspecting existing sessions at startup to
set `personality = "pragmatic"` automatically.
- Remove the migration marker, helper APIs, and associated tests.
GitOrigin-RevId: 9e963bf113aff21651696bbc463f2749ac0f510a
## What changed
- Add an optional `started_at` Unix timestamp to `TurnCompleteEvent` and
`TurnAbortedEvent`.
- Populate the timestamp from turn timing state when a turn completes or is
aborted.
- Preserve the timestamp when synthesizing interrupted fork history and when
importing external sessions.
## Testing
- Verify that interrupting a turn emits a `TurnAbortedEvent` with a start
timestamp.
GitOrigin-RevId: 75b3911b95c060e5fc1843a5e293d8fe47377186
## What changed
- Emit `responsesapi.websocket_timing` payloads as opt-in trace events with request context, while excluding them from diagnostic uploads and persisted logs by default.
- Preserve fractional-millisecond TBT values in telemetry histograms and runtime summaries, rounding only when formatting the TUI label.
## Testing
- Cover timing-log filtering, fractional TBT collection and display, and existing whole-millisecond duration behavior.
GitOrigin-RevId: 5f0a1c60c237abed17cc8b2d569ca77fbbc6ec41
## What changed
- Run permission-request hooks before routing approvals to the automated reviewer or user, including when `strict_auto_review` is enabled.
- Centralize approval resolution so hook, automated-reviewer, and user decisions share rejection handling and report the correct telemetry source.
## Testing
- Add an integration test showing that an allow hook can approve a shell command during strict auto-review without invoking the automated reviewer.
GitOrigin-RevId: 18e9d76baee6cbae9d35ae517250f2f82270a9d2
## Why
Remote environment provisioning can finish after a thread starts, before an
exec-server WebSocket URL is available.
## What changed
- Add `EnvironmentManager::register_pending_environment` and a one-shot
`PendingEnvironmentRegistration` handle that resolves to either a validated
WebSocket URL or a terminal provisioning error.
- Let lazy remote exec-server clients wait for that result, while preserving
reconnection behavior after a successful registration.
- Keep replacement registrations isolated so completing an older handle does
not resolve the current environment with the same ID.
## Testing
Add coverage for successful connection and reconnection, provisioning and
dropped-registration failures, invalid URLs, replacement isolation, and the
deferred-executor startup flow.
GitOrigin-RevId: 5c05be2b72291b77a1f71176d7075b1ad63332a5
## What changed
- Pass configured workspace roots from core to the exec server so filesystem and process sandbox permissions are materialized against the intended roots.
- Preserve an explicitly empty workspace-root list instead of treating the sandbox working directory as an implicit root.
- Initialize filesystem sandbox contexts with their working directory as the default workspace root.
## Testing
- Add end-to-end coverage for patch and command writes inside and outside workspace roots.
- Verify remote filesystem and process sandboxes do not grant access through an empty workspace-root list.
GitOrigin-RevId: 6684c8f7de50970b45a29e2a6323df954c96f9f6
## What changed
- Build a reasoning payload for every Responses request and always include `reasoning.encrypted_content`.
- Remove `supports_reasoning_summaries` from model metadata and retire the `model_supports_reasoning_summaries` configuration override.
- Use configured or model-default reasoning effort without a capability gate, including for guardian reviews and tracing.
GitOrigin-RevId: 2c9f194a5d2d4d688a2235299e6358f82ab8e1ea
## Why
Unified exec can drain process output multiple times while waiting for a command. Collecting those drains into an uncapped buffer allows large commands to exceed the output collection limit.
## What changed
- Accumulate drained output through the capped head/tail buffer so collection remains bounded while preserving the beginning and end of the stream.
- Include a `... N bytes omitted ...` marker when the collection cap drops output.
- Calculate the original token estimate from all observed bytes and preserve omission metadata through truncation and sandbox-denial responses.
## Testing
- Cover repeated drains, previously omitted output, omission markers, and large-output summaries.
GitOrigin-RevId: c6e2efeb875ed8f35914365eab7431f25fd3484c
## Why
Not every Codex distribution currently includes the
`codex-code-mode-host` companion binary. Enabling the process-host
feature should not make code mode unavailable on those surfaces while
packaging support is being completed.
## What changed
- Fall back to an in-process code-mode session only when spawning the
companion binary returns `io::ErrorKind::NotFound`.
- Keep permission, handshake, timeout, and other host failures visible
instead of silently falling back.
- Store the provider's owned-process/in-process choice as one
enum-backed state so later sessions reuse the fallback decision.
- Preserve the underlying spawn `io::Error` while retaining the host
path in the displayed error.
- Update provider, `CodeModeService`, and end-to-end coverage to verify
successful fallback execution.
## Test plan
- `just test -p codex-code-mode`
- `just test -p codex-core missing_process_host`
## Summary
Codex Apps file parameters are exposed to the model as local paths,
uploaded at execution time, and rewritten into provided-file payloads
before the MCP tool call.
The rewrite currently includes the documented optional fields
`mime_type` and `file_name` for every file parameter. Apps with strict
schemas can reject those fields when they are not declared.
## Changes
- Derive the supported optional file fields from each
`openai/fileParams` parameter's raw input schema before replacing it
with the model-visible local-path schema.
- Always include `download_url` and `file_id`.
- Include `mime_type` and `file_name` only when that specific file
parameter's schema accepts them, including schemas that allow additional
properties.
- Handle scalar and array file parameters, including items-only arrays,
composed schemas, and local JSON Schema references.
- Preserve the existing restriction that only the host-owned Codex Apps
MCP server can use this upload path.
This supports tools with different file contracts in the same app: one
parameter can accept the optional fields while another remains strict.
## Validation
- `just test -p codex-mcp`
- `just test -p codex-core mcp_openai_file`
- `just test -p codex-core codex_apps_file_params_`
- `just fix -p codex-mcp`
- `just fix -p codex-core`
- `just fmt`
- `git diff --check`
- Manually verified in the Codex Electron app that:
- a strict file schema receives only `download_url` and `file_id`
- a rich file schema also receives `mime_type` and `file_name`
Related: #31330
## Summary
- Forward Codexs canonical `originator` header on ChatGPT-hosted Apps
and plugin-runtime MCP requests.
- Preserve the configured `X-OpenAI-Product-Sku` header.
- Cover originator-only and originator-plus-SKU configurations.
## Why
Sites project creation is logged downstream of Apps MCP. Production
validation found `CODEX_UNKNOWN_DEFAULT` project-created threads that
matched `codex_surface=desktop_app` and `originator=Codex Desktop` in
`fact_codex_cli`
([query](https://kepler.gateway.data-1.internal.api.openai.org/permalink/H_mVoVPqLQ0)).
The hosted Apps MCP configuration forwarded the product SKU but not
Codexs canonical originator, so codex-backend could not derive
`CODEX_DESKTOP_APP` for those tool calls.
## Validation
- `just fmt`
- `CARGO_HOME=/private/tmp/codex-cargo-home
CARGO_TARGET_DIR=/private/tmp/codex-target just test -p codex-mcp` (106
passed)
- `CARGO_HOME=/private/tmp/codex-cargo-home
CARGO_TARGET_DIR=/private/tmp/codex-target just fix -p codex-mcp`
## Why
When MCP tools are deferred behind `tool_search`, Code mode keeps them
callable but omits their individual declarations from the initial `exec`
description. The shared MCP `CallToolResult` types were derived only
from directly rendered tools, so deferring every MCP tool also removed
the common response contract that models need to interpret MCP results.
This restores that contract without undoing the context savings from
deferred tool definitions. This is a follow-up to #29486.
## What changed
- Track deferred Code-mode tool definitions separately from directly
rendered definitions.
- Render the shared MCP type preamble when either direct or deferred MCP
tools are available.
- Keep deferred tool declarations out of the initial prompt.
- Add unit and integration coverage for deferred MCP tools.
## Testing
- `just test -p codex-code-mode-protocol`
- `just test -p codex-core
code_mode_only_guides_all_tools_search_and_calls_deferred_app_tools`
## Why
CCA thread startup loads repository skills through the primary remote
environment. This still used the older host skill loader, which
recursively issued directory and metadata requests over the exec-server
connection. On a high-latency connection, one skill scan could turn into
hundreds of round trips.
Executor-selected skill roots already avoid this pattern: they use one
bounded filesystem walk, reuse the returned inventory, and overlap
independent reads.
## What changed
- Extract the URI-native walk inventory into a shared private discovery
module.
- Use that discovery path for both environment-owned and host/repository
skill roots.
- Reuse the walk inventory to avoid per-skill metadata existence checks
when the inventory is complete.
- Canonicalize host skill identities and parse skill files with bounded
concurrency.
- Prune hidden host directories during traversal, preserving visible
aliases and walk limits.
- Cache namespace probes by ancestor and keep all remote namespace reads
under the same concurrency bound.
- Keep safe metadata probes for incomplete walks, file symlinks, and
case aliases.
## Dependency
#31570 is now merged. It provides the optional `pruneHiddenDirectories`
walk flag used here. That flag defaults to false and is omitted when
disabled.
No other exec-server API changes are introduced.
## Description
This PR makes new threads with `history_mode = "paginated"` persist
`ItemCompleted(item: <turn_item>)` in their rollout JSONL file.
Legacy threads keep persisting the existing legacy events. Because the
format is selected per thread, a rollout is either legacy or paginated;
we do not need to support mixed rollouts containing both
representations.
This PR depends on [#31473](https://github.com/openai/codex/pull/31473).
## Why
Paginated thread history needs stable turn/item IDs and completed item
snapshots so the later SQLite projector can materialize appended rollout
JSONL without rebuilding the whole thread.
Keeping the legacy persistence policy unchanged avoids changing
historical rollouts or the readers that still consume them.
## What changed
- Made rollout filtering history-mode aware. Paginated threads keep
completed canonical `ItemCompleted` events and drop their redundant
legacy projections; legacy threads keep the existing event set.
- Made forks inherit the source thread history mode, so copied legacy
history is never filtered as paginated.
- Made paginated threads assign IDs to locally-created response items
even when `Feature::ItemIds` is off, and reject streamed output items
that arrive without server IDs.
- Updated legacy turn replay, rollout list/search, and SQLite metadata
extraction to understand completed canonical user-message items.
[Codex Thread
019f2408-dc59-79f2-b245-4c11debd1a61](https://codex-thread-link.openai.chatgpt-team.site/thread/019f2408-dc59-79f2-b245-4c11debd1a61)
## Why
Long-lived Codex sessions can outlive the ChatGPT bearer token that was
present when the MCP runtime started.
The Responses path already recovers from token expiration by refreshing
or reloading the shared `AuthManager`. The reserved `codex_apps`
hosted-plugin client did not observe that update: `McpConnectionManager`
built its `/ps/mcp` HTTP auth once from a `CodexAuth` snapshot, and
`auth_provider_from_auth` copied that snapshot bearer into a static
`BearerAuthProvider`.
After the copied bearer expired, `/ps/mcp` kept sending it even though
Responses had a newer token in the same `AuthManager`. The failure
occurred before downstream connector execution, so unrelated apps such
as Gmail, Slack, and Google Calendar could all fail with the same
transport-level `401 token_expired`.
This replaces
[openai/codex#29474](https://github.com/openai/codex/pull/29474), which
was closed for inactivity without being merged. A new long-lived-session
report reproduced the same simultaneous `/ps/mcp` expiry pattern across
unrelated apps.
## What changed
- Add an `AuthManager`-backed request-header provider in
`codex-model-provider`. It keeps an `Arc<AuthManager>` and reads
`auth_cached()` for each outbound request, so the next `/ps/mcp` call
sees a token refreshed by the existing Responses/auth-recovery flow.
- Scope that provider to the startup account, ChatGPT user, and
workspace identity. Same-identity token reloads are followed; an account
switch emits no ambient auth until account-scoped MCP state is rebuilt.
- Have `McpConnectionManager` construct the dynamic provider only for
the reserved `codex_apps` registration used by the hosted-plugin
`/ps/mcp` path.
| MCP path | Auth behavior after this change |
| --- | --- |
| Reserved `codex_apps` hosted-plugin `/ps/mcp` | Read current
same-identity auth from the shared `AuthManager` per request |
| `codex_apps` with `CODEX_CONNECTORS_TOKEN` | Keep the environment
bearer-token override |
| User-configured/direct MCP registrations | Keep their existing
configured auth path |
## Non-goals
- No plugin-service changes.
- No downstream Slack, Gmail, Calendar, or other connector
OAuth/link-refresh changes.
- No auth UI changes.
- No behavior change for user-configured/direct MCP registrations.
- No new `/ps/mcp`-initiated token refresh; this makes `/ps/mcp` observe
refreshes already performed through the shared `AuthManager`.
## Tests
- `just test -p codex-model-provider`
- Covers same-identity token reloads and refuses a changed startup
identity.
- `just test -p codex-mcp`
- `just test -p codex-core mcp_auth_refresh`
- Creates the reserved hosted-plugin `codex_apps` `/ps/mcp` client
before the shared `AuthManager` changes, updates that same manager
through its public external-auth path, performs a real `tools/call`, and
asserts the request uses the current bearer.
## Why
A thread resumed without an explicit reviewer could pick up the reviewer
from the current config instead of preserving the reviewer already in
use by the thread. After an app restart, this meant a thread running
with auto review could silently switch back to user review, and the next
turn could continue under the wrong reviewer.
## What changed
Persist the effective reviewer with each turn and restore the latest
persisted value when the thread resumes. If the resume request
explicitly provides a reviewer, that value still takes precedence.
## Test plan
- Added a regression test that starts a thread with auto review, records
a turn, restarts with user review in config, resumes without an
override, and verifies that auto review is preserved.
- `just test -p codex-protocol`
- `just test -p codex-state`
- `just test -p codex-rollout`
- `just test -p codex-app-server
thread_resume_preserves_persisted_approvals_reviewer`
- Clippy for the affected crates
## Why
Macrobenchmarks benefit from having a way to exercise remote-executor
latency without depending on Docker.
This is a very minimal first cut, if we find that simulating network
conditions is useful we can always expand this scope or switch to a more
robust network shaping approach.
## What
- add a package-local exec-server binary for Cargo and Bazel test
fixtures
- add a host-local WebSocket exec-server fixture and fixed-delay
interposer
- let TestAppServer route its auto environment through that delayed
WebSocket transport
- cover the delayed thread/start path through the public app-server API
## Stack
1. [#31425 test: add TestAppServer
builder](https://github.com/openai/codex/pull/31425)
2. [#31427 test: add delayed exec-server
transport](https://github.com/openai/codex/pull/31427)
3. [#31295 bench: add cold skill load
macrobenchmark](https://github.com/openai/codex/pull/31295)
4. [#31428 bench: add e2e benchmark
entrypoints](https://github.com/openai/codex/pull/31428)
5. [#31429 ci: smoke Bazel e2e
benchmarks](https://github.com/openai/codex/pull/31429)
Owen Lin