## Why
Runtime filesystem grants, such as those used for plugin metrics, could trigger unnecessary approval for `write_stdin` and prevent input when sandbox approval was disabled.
## What changed
Include retained runtime grants in the baseline permission comparison for stdin review. Continue requiring review for additional agent permissions, sandbox bypasses, and policy changes. Update the approval description to report current permissions when only runtime grants are present.
## Testing
Extend unit coverage to ensure runtime grants do not require review or mask agent filesystem and network grants, and that sandbox bypasses still require review. Add local and remote plugin regression cases that send stdin and verify metric emission with sandbox approval disabled.
GitOrigin-RevId: 989098bdc7fbf839786c01f11cbf02999bae1cc1
## What changed
Return post metadata from the in-memory message board after updating board state when no notification recipients remain. This avoids constructing an unused notification preview, including when the author is the only requested recipient.
## Testing
Run the existing post-and-search model-context scenario against both disk and in-memory message boards, checking that post metadata and search results reach the model without self-notifications.
GitOrigin-RevId: dcf07a5fd55738fbcd6edd3dce3f6fb8fc910eaf
## Why
The network command can yield before its request reaches Guardian, allowing a parent request to consume the mock response intended for Guardian.
## What changed
Update `guardian_receives_exact_trigger_for_single_network_request` to match parent and Guardian requests separately. Have the parent poll running processes with `write_stdin` until they exit, and bound the wait for turn completion to 30 seconds. Preserve the assertion that Guardian receives exactly the original call ID and command.
GitOrigin-RevId: f39e9461c3628fbab00ba241f828d318b17975b5
## Why
Reused Guardian sessions already contain previously delivered instructions. Follow-up reviews can avoid repeating that evidence, but must deliver it again if it changes or compaction removes it.
## What changed
- Track retained source identity, revision, and completeness in host-owned history metadata, preserving revisions during replay.
- Omit retained instructions from synchronous review inputs only when the same complete revision remains in reviewer history.
- Restore missing evidence after reviewer compaction, enforcing the request budget before persisting additions. Classify restored evidence as context rather than new user authorization.
- Keep source-order labels stable across eviction and retain full delivery for legacy records without reliable provenance.
## Testing
Add coverage for consecutive-review deduplication, changed revisions, missing or incomplete metadata, and restoring compacted evidence exactly once. Extend compaction and resume coverage to verify retained revisions.
GitOrigin-RevId: e90fca16cde0a0970da36dd873af2ca1dbaaf4d3
## Why
When a container denies fresh `/proc` mounts, the existing sandbox fallback retains the caller's `/proc` while creating a new PID namespace. Process IDs inside the sandbox can then differ from those exposed by `/proc`, breaking process lookups.
## What changed
- Add `codex exec-server --linux-sandbox-pid-namespace=inherit` to reuse the caller's PID namespace and `/proc` for both process and filesystem helpers. Repository config and command environment variables cannot enable it.
- Keep `isolate` as the default, preserving the existing mount fallback and compatibility with older helpers. Inheritance requires an updated helper and omits `--unshare-pid` and `--as-pid-1`.
- Preserve other sandbox restrictions. With `:minimal`, bind the inherited `/proc` read-only with its container masks and apply explicit filesystem denials afterward.
Inheritance is intended for dedicated environments: it allows sandboxed commands to signal other same-UID processes, including the executor.
## Testing
Add unit and integration coverage for namespace flags, denied proc mounts, consistent process IDs, retained sandbox restrictions, and startup-only selection across process and filesystem helpers.
GitOrigin-RevId: dd13f2b9286d7edcf366b3a42a455f4d78daaf27
## Why
Refreshing the MCP catalog with unchanged tool metadata recreated handlers and forced the tool search index to rebuild.
## What changed
Cache handlers by canonical tool name and reuse them when tool metadata, agent plugin status, and the input schema size limit are unchanged. Replace handlers when those inputs change and evict tools removed from the catalog, preserving search index reuse across equivalent bindings.
## Testing
Extend the deferred tool world state test to verify that an unchanged catalog refresh captures a new binding without rebuilding the search index, and that removing all deferred tools stops advertising `tool_search`.
GitOrigin-RevId: 150866f635e9ee817d7ca44fb76e724a3f7608a5
## Why
`active_turn_environment_selections()` returns the selections captured at turn start, so it does not reflect later environment settings updates.
## What changed
Add `CodexThread::current_turn_environment_selections(expected_turn_id)` to read the running turn's current selections, including environments that are still starting or have failed. Return `None` when the requested turn is no longer active or has been cancelled.
## Testing
Add a regression test covering selection updates, mismatched turn IDs, and completed turns, while verifying that the initial selection snapshot remains unchanged.
GitOrigin-RevId: bb526a686d549209142150ffde99ad1444add205
## What changed
- Recognize `flex_unavailable` in HTTP 429 responses and streamed `error` and `response.failed` events. End normal turns without retries and report `Flex capacity unavailable.`
- Expose `flexUnavailable` through the core and app-server protocols and generated schemas and SDK types.
- Keep Flex capacity failures eligible for Guardian review and sampler retries, with a distinct telemetry classification.
- Map unexpected HTTP responses to `HttpConnectionFailed`, preserving their status codes.
## Testing
Add regression coverage for terminal Flex failures over HTTP, SSE, and WebSocket, HTTP 504 status preservation after a stream retry, and protocol serialization. Update Guardian retry and sampler recovery tests to cover Flex failures.
GitOrigin-RevId: f2e03a6d2d36a6d9748c35952e40397f8670d121
## Why
Removing tool-result metadata alone can leave requests above the 15 MiB message budget when recorded tool calls and arguments occupy the remaining space. If trimming loses calls or arguments from a Code Mode cell, later waits must not report its call inventory as complete.
## What changed
- Bound all optional tool-call observations against the serialized HTTP or WebSocket message size, preserving ordinary tool outputs and continuation history.
- Shed generic result metadata, sources, and recorded arguments before resource-access evidence, retaining tool names and smaller metadata where possible.
- Invalidate completeness across affected cell outputs and later waits when the outgoing copy loses calls or arguments.
- Preserve size-limit omission markers for direct tool-result metadata when they fit, while continuing to exclude that metadata from custom providers.
## Testing
Add regression coverage for HTTP and WebSocket message budgets, unchanged tool results and history, resource-evidence retention, direct-call omission markers, and Code Mode waits after argument truncation.
GitOrigin-RevId: 538dc9d8c11b0830ec70327422f98a1803122e85
## What changed
Increase `MAX_ROOT_MESSAGES` from 8 to 16 so Guardian subagent authorization reviews can include more root conversation context.
## Testing
Update authorization integration tests to exercise the larger message limit, preserve late user authorization and question context, and expect incomplete root instructions when retained user messages exceed the cap.
GitOrigin-RevId: facc55f424a4d7e29626f4161ecfe031021b30c2
## Why
Ephemeral sessions cannot use the SQLite-backed agent message board. An in-memory backend lets agents share discussions without creating durable board storage.
## What changed
- Add the opt-in `message_board_in_memory` setting to the multi-agent v2 configuration, allowing the board to run in ephemeral sessions when both required features are enabled.
- Share board state across agents in the same tree and release it when the last handle is dropped.
- Implement channels, posts, subscriptions, notifications, search, and paginated reads through the existing `AgentMessageBoard` interface, including request deduplication.
## Testing
Add coverage for shared handles, concurrent request deduplication, tree isolation, and state release. Run existing query and tool test cases against both backends, and extend the parent/child scenario to verify ephemeral board sharing without creating a board database.
GitOrigin-RevId: d0b2083f8ea5b1c5a3a70f258ef738b87ea74cef
## Why
Callers need to await acceptance or rejection of thread settings without consuming the thread event stream. Acceptance must precede event delivery because the caller may hold a lock needed by the event consumer.
## What changed
- Add `CodexThread::update_thread_settings` and re-export `ThreadSettingsOverrides` from `core-api`.
- Add an optional reply channel to `Op::ThreadSettings`. Return validation failures as `InvalidRequest` through that channel, retaining error events for callers without a reply channel.
- Reply to successful updates before emitting `ThreadSettingsApplied`, while holding the settings persistence lock through notification.
## Testing
Extend settings constraint coverage to direct replies, including rejection without an error event and successful notification. Verify that acceptance and continuation invalidation precede blocked event delivery, while checkpointing waits for notification.
GitOrigin-RevId: e09b0d3cc4b6750709c173371632f19619e5c250
## Why
Fixed schema budgets can strip parameter descriptions from large MCP tools or render their Code Mode input types as `unknown`. Allow larger budgets to preserve that guidance.
## What changed
- Add `mcp_servers.<name>.tool_input_schema_max_bytes` to configure the UTF-8 byte threshold for best-effort input schema compaction, retaining the 5,000-byte default.
- Add `features.code_mode.tool_input_schema_max_bytes` for rendered input types. Use the largest of the 16,000-byte default, the Code Mode setting, and the ordinary MCP server's explicit setting.
- Apply rendering budgets to prompt declarations and the runtime tool catalog, and avoid reusing cached declarations after the Code Mode budget changes.
## Testing
Add coverage for UTF-8 compaction thresholds, budget precedence, configuration round trips, and preservation of parameter guidance in both the Code Mode prompt and `ALL_TOOLS`.
GitOrigin-RevId: 0ef2823a614d4794e636f518b09c0b03a5239b45
## Why
Required MCP servers can block startup while establishing a live connection even when a usable tool catalog is already cached.
## What changed
- Add per-server `startup_readiness = "catalog"` to expose cached tools while the connection starts, retaining `"connection"` as the default.
- Allow an eligible cached catalog to satisfy required-server startup validation and model binding capture. Explicit server or plugin requirements still wait for a live connection, and tool execution still requires the current connection.
- Check tool filters and model visibility when accepting cached catalogs, and preserve cached catalog revisions for binding reuse.
- Serialize the new setting, expose it in the configuration schema, and trace startup readiness at validation and model binding gates.
GitOrigin-RevId: a1cbdf1757ebb5824cffe2cc56408be49711c422
## Why
Saved model selections can outlive their catalog entries. Removing GPT-5.4 needs to preserve a migration path without applying it to other providers that may still support the same model slug.
## What changed
- Remove `gpt-5.4` from the bundled catalog and `openai.gpt-5.4` from the Bedrock catalogs, including GovCloud.
- Add fallback migration prompts to GPT-6 Sol for saved GPT-5.4 selections on OpenAI and Amazon Bedrock. Scope fallback migrations, including the existing GPT-5.4 Mini migration, to their owning providers while honoring catalog metadata.
- Update tests that depend on bundled GPT-5.4 metadata to use GPT-5.5 or explicit model overrides.
## Testing
Extend migration tests to cover catalog metadata precedence, acknowledged targets, missing or hidden replacements, and preserving the provider while saving the replacement model and its default reasoning effort. Update Bedrock catalog assertions and picker snapshots.
GitOrigin-RevId: f739795da423b9622db2a416be6c52b01b8e7a71
## Why
Expanded recursive deny lists can exceed the Windows command-line limit, preventing sandbox wrappers and setup helpers from launching.
## What changed
- Use chunked environment transport for wrapper and non-elevating setup payloads above 24,000 UTF-16 code units, preserving the existing argument protocol for smaller requests.
- Share the transport with the MXC launcher, supporting payloads up to 16 MiB with Unicode-safe chunking and validation.
- Keep transport variables out of the workload environment and remove inherited chunks before launching setup helpers.
## Testing
Add coverage for transport boundaries, Unicode round trips, malformed payload rejection, environment cleanup, and large payloads crossing Windows process creation. Extend the elevated sandbox integration test with 1,000 nested denied files to verify read restrictions and `AGENTS.md` discovery with a payload exceeding the command-line limit.
GitOrigin-RevId: 8ef92fdc7d534143f0eac76036a2173a6f585d08
## Why
Agent messages arriving during a response can interrupt sampling at reasoning or commentary boundaries, cutting off remaining tool calls.
## What changed
Add the disabled-by-default `defer_mailbox_preemption` feature flag. When enabled, sampling continues past these boundaries and queued agent messages reach the next model request alongside completed tool results.
## Testing
Add streaming scenarios and snapshots for reasoning and commentary boundaries with deferral enabled and disabled. Verify that deferral preserves the planned tool call and that both queued messages arrive in order in the next request.
GitOrigin-RevId: d6846dd73b3afb47e7293f3b1aa2abcd04e37853
## What changed
- Make `LocalThreadStore` default to paginated history while retaining explicit legacy mode.
- Explicitly use paginated history for Guardian review sessions and allow in-memory stores to create paginated threads.
- Rename full-history resume, fork, and subagent helpers to identify them as legacy APIs, and document the paginated alternatives.
- Reject `thread/revert` for ephemeral threads and prevent the TUI from replaying or attaching to ephemeral agent threads.
## Testing
Add coverage for preserving the default and explicitly selected history modes and conversation context across restart, and for retaining context after rejected ephemeral reverts. Extend Guardian checkpoint coverage across both history modes and verify that saved reviews use paginated history.
GitOrigin-RevId: 870239eb3757018159ee4f230a009c97d38ac5b7
## Why
Treating an omitted `allow_local_binding` setting as `false` prevents environment policies from inheriting local-binding permissions.
## What changed
Keep `allow_local_binding` optional when composing controller and environment policies. Preserve explicit denials from either policy and resolve executor defaults after composition. Without a controller, default to denying local binding unless the environment explicitly allows it.
## Testing
Add coverage for omitted, allowed, and denied settings, managed constraints, executor defaults, and remote launch rejection when local-binding restrictions cannot be enforced. Extend remote network approval tests with loopback requests to verify controller and environment policy composition.
GitOrigin-RevId: aa0d15e8be87a2741255cd3a5a2cabffa03214ac
## Why
SQLite write failures can leave persisted logs incomplete, while log snapshots taken before collection miss errors raised during that collection.
## What changed
- Report SQLite flush failures directly to the in-memory log buffer without re-entering tracing, using an error category and batch size instead of raw error details.
- Track whether the log writer has lost a batch and make app-server diagnostic uploads use the memory buffer when SQLite logs are incomplete.
- Refresh log bytes after flushing and querying SQLite so the same submission includes collection failures, while preserving captured metadata and thread identity.
## Testing
Add regression tests for failure reporting without recursion, subsequent write recovery, metadata preservation, and healthy and failing SQLite collection. Add an upload integration test that captures attachments locally and checks failure diagnostics, memory-buffer fallback, and omission of raw SQLite error details.
GitOrigin-RevId: 51b0c4b69c977d9f4e74f2f245a9fd90fdb13761
## Why
Local `apply_patch` permission checks can treat a macOS system alias and its canonical spelling as different locations, sending writes covered by temporary-directory grants for unnecessary approval.
## What changed
- Normalize trusted top-level aliases in local policy roots and patch targets, reusing a prepared matcher for permission requests and patch safety checks.
- Share alias normalization with Seatbelt and the macOS executor sandbox while preserving mutable symlinks and missing descendants.
- Preserve read-only and deny precedence, protected metadata restrictions, and remote URI matching. Propagate normalization failures from fallible permission checks.
## Testing
Add macOS regressions for multi-file patches with missing parent directories through both direct `apply_patch` calls and shell interception, asserting automatic approval and file contents. Add unit coverage for alias restriction precedence, mutable symlink preservation, missing descendants, and remote permission isolation.
GitOrigin-RevId: 0822ff951eaab728cb1ad91281745fa1b8809f15
## Why
The PID reservation test could race with the backend's read on Windows by deleting the PID file from its cleanup task. The guardian heartbeat snapshot and environment normalization also needed to match the current permission-context wording.
## What changed
- Release the reservation lock and let `stop()` remove the stale PID file, then assert that the file is gone.
- Update the guardian heartbeat snapshot and normalization pattern to use `The active permission profile for environment`.
GitOrigin-RevId: d9cadae0e5d36cb2e1ab0517e2d7121cf2d0715d
## What changed
Add `otel.log_guardian_assessments`, disabled by default and requiring an OTLP HTTP or gRPC log exporter. Emit `codex.guardian_assessment` when a synchronous Guardian review finishes, including review identifiers, status, risk level, user authorization, and rationale. Include `allow` or `deny` outcomes only for completed model assessments, not review errors, timeouts, or cancellations.
Cap exported rationales at 64 KiB on a UTF-8 character boundary and record their original byte length and truncation status. Use the log-only route to exclude assessment payloads from trace export, local state logs, and bug-report log buffers. Cached V2 approvals are not included.
## Testing
Add coverage for configuration gating, enabled and disabled denial logging, terminal statuses and outcomes, UTF-8 rationale truncation, export routing, and bug-report log buffer exclusion.
GitOrigin-RevId: dcbb5b429c8726a5a5c80ff82f9d625e81796ede
## What changed
- Resolve remote sandbox modes, writable roots, and denied read paths/globs using the executor's filesystem context, displaying paths in its native format. Preserve local filesystem resolution for local environments.
- Resolve remote read denials individually so missing executor facts omit only the unresolved entries.
- Apply a shared 32 KiB budget to displayed permission paths/globs, omitting whole entries and warning that all restrictions still apply, including omitted read denials.
## Testing
Add coverage for remote Windows writable roots and read denials, missing executor path facts, and whole-entry omission with multibyte paths under the shared budget.
GitOrigin-RevId: c61e7ddc8fa569dbc25e9990d90357c42315188f
## Why
Unchanged scheduled heartbeat instructions should not become fresh authorization evidence that supersedes a later human override or floods Guardian review context.
## What changed
- Capture heartbeat provenance per input, including when steering an active turn, and persist it in history and retained context.
- Coalesce unchanged instructions for each automation at their original acceptance order. Preserve changed instruction versions and ordinary human messages.
- Represent repeated heartbeats as references to earlier instructions in Guardian transcripts, while tracking the latest input turn separately for trusted skill selection.
- Limit coalescing to recognized, bounded heartbeat envelopes with host-provided provenance.
## Testing
Add regression coverage for human overrides across repeated and steered heartbeats, instruction changes, checkpoint restoration, transcript references, envelope parsing, and latest-turn trusted skills in delegated reviews.
GitOrigin-RevId: 31e444ddb685a1a618be26d3cc32fb562296946b
## Why
Cold Rosetta translation and cache invalidation from hard-linked executables can interfere with timed CLI tests. Sampling the clock twice also makes local retry telemetry report a delay shorter than the selected backoff.
## What changed
- Warm CLI fixtures with `--version` on macOS x86_64 before timed checks, and use copies or Unix symlinks to avoid invalidating the shared executable's Rosetta cache.
- Use one clock sample to calculate the response retry deadline and recorded delay.
- Include the retry telemetry event in delay-range assertion failures for the headerless rate-limit stream test.
GitOrigin-RevId: fc573bfff912e999cf74b94a1c6e7ae1be07974b
## Why
Asynchronous Guardian scoring omitted the target environment's denied-read restrictions, and cached score authorization did not include that permission context. A score from one environment could therefore be reused for an action in another environment with different restrictions.
## What changed
- Share permission resolution between synchronous review and asynchronous scoring, including resolving `write_stdin` targets from the owning terminal session.
- Include environment identity and denied-read paths/globs in async scoring context and cached score authorization.
- Fall back to synchronous review when permission evidence cannot be resolved or exceeds the async limit of 3,000 bytes, rather than omitting restrictions.
## Testing
Add regression coverage for rejecting cached scores with different environments or denied paths, passing the target environment's restrictions to the classifier, and rejecting oversized async permission evidence.
GitOrigin-RevId: 14b6f3454bbea458be037560eb1da47d22874df1
Raise `max_concurrent_threads_per_session` from 3 to 4 in the test
configuration so the root, worker, grandchild, and sibling can all remain
resident until explicit shutdown.
GitOrigin-RevId: 564fd7bd64d2a91c160437f7346c7e17a30a5f2a
## What changed
Add a `TestCodexBuilder::with_thread_manager` hook for configuring the thread manager before test threads start, and register an integration suite using a test `AgentControl` implementation.
The tests verify:
- Controller factory calls for new roots, forks, and cold resumes, with reuse for warm resumes and shared session identity for internal sessions.
- Child session identity, persisted parent lineage, message-board authorship, and routing of child reloads through the host controller.
- Preservation of the controller's service tier when child threads start or root starts are rejected.
- Dispatch of `spawn_agent`, `send_message`, and `list_agents` to the host controller, including propagation of its errors to tool results.
GitOrigin-RevId: bc6a6c6dbcde9ecc3ce15456aaf7a0610a14eceb
## Why
New user input during a Guardian review invalidated an in-flight approval and aborted the pending action, even when the input was only a status inquiry. Review the action again against the latest authorization evidence so it can proceed or be denied based on the updated instructions.
## What changed
- Treat stale authorization as a retryable review error within the existing attempt budget and shared deadline.
- Refresh authorization evidence for each attempt while keeping the pending action fixed, and record evidence from the completed attempt.
- Preserve cancellation and history-reset aborts, and deny approval if stale authorization exhausts the retry budget.
## Testing
Add and update coverage for parent status updates, authorization revocation, repeated updates, cancellation, history resets, and retry deadlines. Verify that refreshed reviews see the latest input and that the pending action executes exactly once only after approval.
GitOrigin-RevId: c683e2efb6f07840b99d0d34acf0d38c9ddfe9bd
## Why
The list-voices barrier can consume the sleep completion event that `any_new_input_interrupts_sleep` needs to observe.
## What changed
Enqueue agent mail directly in the test so the subsequent wait can observe sleep completion. Keep the `TestCodex` fixture alive for the duration of the test by cloning its `codex` handle instead of moving it out.
GitOrigin-RevId: 957165c2f20cc4d76df763cd41fd99816b477be3
## Why
Explicit user goal edits can restrict permitted actions, such as “Inspect only; do not publish.” Guardian needs these edits as authorization evidence even though they are recorded as contextual messages.
## What changed
- Add `UserGoalUpdate` and a recording API for objective, status, and clear updates without scheduling a model response.
- Use host annotations to retain goal updates in Guardian review history and root authorization evidence, and invalidate cached authorization when updates are recorded.
- Omit oversized objectives whole and mark their evidence incomplete so truncation cannot turn a restriction into a grant.
- Keep item injection from updating shared model and multi-agent metadata.
## Testing
Extend authorization, retained-context, and review snapshot tests to cover goal-edit cache invalidation, root goal visibility from child threads, and restrictive goals reaching Guardian alongside managed policies.
GitOrigin-RevId: 17b99d9fa8c1620840d6f408d79b405a78a778f8
## What changed
Promote `write_stdin_approval` to stable and enable it by default.
## Testing
Update the stdin approval suite to rely on the default feature setting. Adjust the background network approval test to account for terminal input review before network access and explicitly wait for the network assessment.
GitOrigin-RevId: 1bb449f6d9ecf4ee451e84f95f839a6744877e8b
## What changed
Use the model catalog's `send_user_message_async.parameters` override for the `request_user_input_async` tool schema. Fall back to the bundled schema when the override is absent or invalid, logging a warning for invalid overrides while preserving the catalog description.
## Testing
Extend integration coverage for catalog schemas, empty and invalid overrides, and schema updates during mid-turn model changes. Update the asynchronous question-and-answer scenario to verify that requests carry the catalog schema while work continues and the user's answer arrives.
GitOrigin-RevId: c51a90d3266daaba1e7001aa4026964f84dfb206
## Why
The 32 KiB per-result cap and 128 KiB aggregate budget discard tool metadata even when the outgoing request has room to retain it.
## What changed
- Remove the per-result capture cap and raise the aggregate executed-tool metadata budget to 2 MiB.
- Apply a 15 MiB soft budget to serialized HTTP requests and WebSocket messages, using the actual WebSocket delta. Trim optional result metadata on the wire copy while preserving ordinary content and logical history.
- Prioritize `openai/resource_access` metadata during trimming, and include `overage_bytes` in omission markers.
- Record bytes removed by metadata budgets in `codex.tool_metadata.shed_bytes`, tagged by stage.
## Testing
Add coverage for HTTP and WebSocket message boundaries, resource preservation, residual marker removal, unchanged history, and shedding metrics. Update direct-tool and code-mode tests to verify metadata survives beyond the previous limits.
GitOrigin-RevId: ed00996b77945300f60db1e52eff22b4de2707c1
## Why
Repeated prewarm calls still prepared instructions, tools, and a prompt even when an existing WebSocket connection was already warm.
## What changed
Check for a previous request and a connection that is not known to be closed before startup prewarm preparation. Reuse this readiness check in `prewarm_websocket`, and record `ready` or `needs_prewarm` in the `codex.startup_prewarm.websocket_check` counter before preparation can fail.
## Testing
Extend the WebSocket resume test to verify that repeated prewarm calls skip instruction loading on a healthy connection, while a closed connection triggers preparation again.
GitOrigin-RevId: 6a1b361b36b4e7f16fb283e48a8ce4d4fb996ceb
## Why
History notes and image generation requests used default HTTP clients that did not carry the configured application network policy.
## What changed
Pass `Config::http_client_factory()` into both extension backends and create transports with `ClientRouteClass::Api`, so their requests honor application network restrictions and configured proxy behavior.
## Testing
Add regression coverage verifying that denied image requests never reach the server and that history notes context requests stop after the network policy becomes restrictive. Retain coverage for image file access restrictions.
GitOrigin-RevId: 7ba61fdc60fa1afe1842d869da9ccd744ab7d82f
## Why
Exceeding the aggregate metadata budget previously replaced all tool result metadata with omission markers, discarding small results unnecessarily. Oversized results also lost resource-access evidence even when that evidence alone would fit.
## What changed
- Raise the executed-tool-call metadata budget per request from 32 KiB to 128 KiB while retaining the 32 KiB per-result limit.
- Reduce the largest result metadata first and stop once the request fits, preserving smaller results.
- Retain `openai/resource_access` when full metadata exceeds capture, request, or direct-call retained-history limits. Keep resource lists intact, and discard optional result metadata before sacrificing call records, source evidence, or completion markers.
## Testing
Add regression coverage for selective reduction, resource-access retention, serialized request size, and direct-call and Code Mode behavior. Update compaction and truncation tests for the larger request budget.
GitOrigin-RevId: 698e47dcbdd3351e9a031e45ea39053608a5a0e4
## What changed
Return completed startup prewarm sessions to the client cache and schedule resume prewarm through the normal session setup path. Keep in-flight warmups shared, remove the separate nonblocking prewarmed checks, and simplify the prewarm handle to own a single task.
## Testing
Update the resume prewarm integration test to assert `User-Agent` and `x-codex-window-id` handshake headers while retaining coverage for connection reuse, response continuation, and reconnection after closure. Remove the assertion that healthy resumes skip instruction preparation.
GitOrigin-RevId: a9b6d4810aca9aba2e6e41df181b7d9d90474230
## Why
A previously used WebSocket can close while a thread is idle. Hosts need a way to prepare the connection before the next turn without repeating warmup on a healthy connection.
## What changed
- Expose `CodexThread::prewarm()` using the existing startup warmup and next-turn handoff.
- Reuse healthy connections and pending warmups, retry failed warmups, and repair closed connections. Treat a finished WebSocket reader task as a closed connection.
- Skip scheduling during an active turn or shutdown, and stop warmup admission before shutdown takes the pending task.
- Expose `active_turn_environment_selections()` so hosts can inspect the environments captured by the active turn, including those still starting or failed, when authorizing steering.
## Testing
Add regression coverage for repeated idle prewarm calls, healthy connection reuse with preserved response continuation, reconnection with `generate: false`, and warmup rejection after shutdown. Update delayed MCP discovery coverage to verify prewarm repairs an eagerly closed socket and the first turn reuses it.
GitOrigin-RevId: aa164b91a399de2375eda3bf28397725439fce93
Use `tokio::select!` to listen for shutdown alongside `ws_stream.next()`
in the test server's request loop, allowing the server task to exit when
shutdown is requested while waiting for the next client message.
GitOrigin-RevId: ef77ae64322ab3bdf9b624645a9062a2a9f827cc
## What changed
Call `ensure_rollout_materialized` after recording pending inter-agent communication, using the supplied persistence context. This also triggers the first execution checkpoint when an agent message starts the first turn.
## Testing
Extend the first-input persistence test to cover inter-agent communication, checking that the checkpoint is requested and sampling proceeds while durable metadata is blocked. Verify that prepared context precedes the agent message and that its author and recipient reach the model.
GitOrigin-RevId: 55779edb1a38fcf4d1c1cff24c09f5a810460c3d
## What changed
Always use `GuardianContextMode::ThreadOwned` for session capture and subagent history forks, regardless of `guardianv2.thread_context`. Continue selecting reviewer policy from saved checkpoints, preserving legacy review for incompatible checkpoints and removing the feature gate from reviewer compaction compatibility checks.
## Testing
Update coverage for unconditional retained context across compaction, resume, and subagent forks. Exercise legacy review with saved checkpoints, and verify that local and managed opt-outs do not disable sender context capture or checkpoint migration.
GitOrigin-RevId: cd74e2029c83f12bc655b6563242d06f29dd46af
## What changed
Use retained root context for subagent authorization reviews, removing the separate legacy history path. Remove the runtime `request_user_input` answer buffer and its response counter; authorization versions now track the user-message revision and retained-context completeness.
## Testing
Update authorization and input-handler tests to exercise retained context, and add coverage for the `user_messaging` connector in subagent reviews.
GitOrigin-RevId: 00ad151cf71b843af0e82ae90cbcf559d0c65f89
## What changed
- Deprecate and ignore `features.guardianv2.thread_context`, including profile overrides, with a migration notice. Ignore managed requirements for the removed flag with a warning.
- Preserve surviving legacy root instructions across compaction and resume when retained instructions are incomplete. Include unmatched instructions in worker authorization context with an explicit unknown-ordering notice, without replacing newer retained facts or expanding the reviewer's model window.
- Use surviving source calls to roll back verified answers from older checkpoints that lack acceptance-order metadata.
## Testing
Add regression coverage for legacy instruction recovery, compaction and resume, source matching, and answer rollback around same-turn user input. Update configuration and Guardian review tests to verify that the deprecated opt-out still uses thread-owned context and rejects incompatible compaction evidence.
GitOrigin-RevId: a65936c9e0b912e7667d1385a2ec53df726565de
## What changed
Add `ModelRequestContributor` and `ModelResponseInterceptor` to the extension API. Contributors can add filtered `client_metadata` without overwriting existing or reserved fields and create interceptors for individual requests.
Wire contributors into HTTP and WebSocket requests, distinguishing generation from warmup. Apply response interceptors in registration order before tracing and response bookkeeping so transformed output is recorded consistently. Interceptors can inspect, buffer, or transform events, with stream ownership carrying request state and cancellation.
## Testing
Add tests for metadata protection, incremental event transformation, interceptor ordering, upstream cancellation, and consistency between delivered output, traces, and WebSocket bookkeeping. Integration tests cover output gating and interruption over HTTP and WebSocket, including a contributor that bypasses gating for warmup requests.
GitOrigin-RevId: d4bc1745d2cacf8636728dbc0a58ab9f250e9392
## Why
MCP resource helpers use fixed descriptions and parameter schemas, preventing the model catalog from supplying model-specific guidance.
## What changed
Add `model_messages.tools.mcp_resources` entries for `list_mcp_resources`, `list_mcp_resource_templates`, and `read_mcp_resource`. Resolve these entries for the current model when constructing tool specs for direct calls and Code Mode.
Descriptions and parameter schemas override independently. Preserve bundled defaults for missing fields and fall back to bundled parameters with a warning when a supplied schema is invalid. MCP resource execution remains unchanged.
## Testing
Add unit coverage for independent overrides, literal descriptions, and invalid-schema fallback. Add integration coverage for resource discovery and reading through direct calls and Code Mode, plus assertions that resource tool specs follow model changes between steps.
GitOrigin-RevId: 40b5beddb38b2b61c19dc9cd6013d6ba5d756dbc
## Why
Channel tools use bundled descriptions even when the model catalog supplies tool messages. Let their descriptions follow the active model, including model changes within a turn.
## What changed
- Add channel tool entries to `MultiAgentToolMessages` and pass them to the message board extension for each step.
- Apply catalog descriptions while retaining bundled text for missing or null values and honoring empty strings. Ignore parameter overrides with a warning and keep bundled schemas.
- Clarify bundled descriptions for channel discovery, thread reading, posting, and subscription notifications.
## Testing
Add coverage for full and partial overrides in namespaced and Code Mode tools, preserving Code Mode declarations and parameter schemas. Extend the mid-turn model-change test to verify that the `post` description follows the active model.
GitOrigin-RevId: fca20bed1203d5214713f82cb16a91eeebb38f56
## Why
Output produced before the streaming subscriber attaches can be missing from command completion events, even when it was returned to the model.
## What changed
Record the bounded completion transcript directly in `UnifiedExecProcess` as local and exec-server output arrives. Keep it independent of output polling and streaming delta delivery, and use it for completion events.
## Testing
Add regression coverage for output collected before subscription, both with and without later output. Strengthen the lifecycle test to assert that `aggregated_output` includes both early and late output.
GitOrigin-RevId: 9825acbd706dc4845837c8b4ab1347d8267ce0af
## Why
The default transport fallback bypassed managed application network policy when using `ReqwestDefault` proxy handling or running inside the Codex sandbox.
## What changed
Use a `RouteAwareClientPool` whenever application network policy is managed, retaining policy enforcement for requests and redirects while preserving legacy proxy behavior and custom CA fallback.
## Testing
Add code mode web search regression cases for denied initial requests and denied redirect destinations, verifying that policy errors reach tool output and no requests reach the denied destination.
GitOrigin-RevId: 74ba0e6e4dcad03f3e83c0450b8b17bcefcc267c
jif