## Why
Fixed argument limits truncated recorded tool calls even when their metadata fit within the available message budget.
## What changed
- Remove the 8 KiB per-call and 32 KiB per-output argument limits for direct calls and Code Mode.
- Preserve full recorded arguments while retaining message metadata budgets, pending-call limits, and the direct metadata retention limit.
- Rename the normalization helper to `normalize_executed_tool_call_completeness`; it now only clears completeness when calls or tool names were lost.
## Testing
Update regression coverage for large arguments, escaped inputs, reserved-key wrappers, and argument and result metadata preservation across Code Mode waits.
GitOrigin-RevId: 8c199ccf39191d5d44eef02d28b1773654735b43
## What changed
Add `functions_namespace_functions_description_prefixes` to model tool messages, keyed by unqualified tool name. Prepend this guidance to descriptions in the `functions` namespace across direct declarations, Code Mode documentation, and tool-search results, including custom tools.
Trim prefixes, ignore empty values and unavailable functions, and enforce a combined 256-byte UTF-8 limit including separators for reachable tools. Keep overrides local to each step, preserve search ranking text, and retain runtime caches for unaffected tools.
## Testing
Extend coverage for direct and indirect descriptions, clearing prefixes when switching models, namespace scoping for deferred dynamic tools, and tool-search cache reuse and reset.
GitOrigin-RevId: f434e37cec010764fe3e09fb12c339e933b3c21c
## Why
Truncating recorded arguments does not lose the call inventory. Clearing `tool_calls_complete` in that case incorrectly treats retained calls and tool names as incomplete.
## What changed
Define `tool_calls_complete` as completeness of the ordered call inventory, independent of recorded arguments. Preserve it for direct tool outputs and Code Mode cells when argument limits or message budgets truncate arguments, including across later waits. Continue clearing completeness when calls are omitted or tool names are truncated.
## Testing
Update protocol, recorder, and integration tests to verify completeness survives argument truncation and message budgeting. Add coverage confirming that omitted calls and truncated tool names still clear completeness.
GitOrigin-RevId: 1534dbfabbd1291b840dd6fb6738ed51bcd4c0c4
## What changed
Mark `code_mode_interrupt` as stable and enable it by default, so interrupting a turn terminates active code mode cells and nested tool calls.
## Testing
Update the existing interruption test to use the feature default instead of explicitly enabling `CodeModeInterrupt`. It verifies that active cells and nested tools are aborted while stored session values remain available.
GitOrigin-RevId: 17be94f208713bc232e2292feb48261938254db3
## What changed
Apply `code_mode_tool_description_first` when preparing nested tool definitions for Code Mode execution and tool search. When enabled, place each tool's description before its namespace description; otherwise, preserve namespace-first ordering.
Reuse cached MCP definitions only when both the input schema budget and description-order setting match.
## Testing
Extend deferred app tool integration tests to cover both description orders with and without ranked search, including consistency between search results and `ALL_TOOLS`. Extend the MCP cache test to reject reuse when the description-order setting changes.
GitOrigin-RevId: 1e3f84d2d95c200aef21ad710d367274b2169b4b
## What changed
Add `TurnEnvironmentRequests` to carry environment requests together with their fallback working directory. Update thread settings overrides and active turn settings to accept requests, constructing `TurnEnvironmentSelection` values in the receiving thread before validation and runtime use.
Adapt app-server callers, reviewer settings, and existing tests to supply requests or explicitly convert runtime selections back into requests.
GitOrigin-RevId: 8028f804bebe3fde553f57bb450f6dca3970cc4a
## What changed
- Add the default-disabled `code_mode_tool_search` feature to expose `await tools.tool_search({query: "...", limit: 8})` in code mode when the model supports tool search.
- Return BM25-ranked deferred tools as `{tools: [{name, description}]}`, including callable names and TypeScript declarations for use in later code cells.
- Filter results through the current step's nested-tool policy before applying the limit, preserving namespace restrictions, normalized identities, description prefixes, and schema budgets.
- Add ranked-search guidance while retaining `ALL_TOOLS` catalog discovery and description overrides.
## Testing
Add coverage for feature and model-capability gating, namespace restrictions, argument validation, schema budgets, and discovery followed by deferred MCP and dynamic tool calls. Extend the scenario snapshot to cover search, invocation, yielding, and completion through `wait`.
GitOrigin-RevId: 092a29dd5f0773c518f53a001b9cafb917422f13
## What changed
Move base instructions from the top-level `instructions` field into a prefixed `developer` message in `input` for standard Responses requests, matching Responses Lite. Remove the field from HTTP and WebSocket request types and assign instruction messages stable IDs derived from the thread and instruction text.
## Testing
Extend standard and Responses Lite tests to cover instruction message serialization, stable IDs, and resume consistency. Update WebSocket tests to verify that changed instructions trigger a full request without `previous_response_id`.
GitOrigin-RevId: e2de4b8e30a9339377fac133ceda981abd1a112b
## Why
Persistence and aggregate metadata budgets can omit tool-call observations that are still relevant to the current request, including tool result metadata needed during compaction.
## What changed
- Retain live direct-call observations separately from bounded persisted outputs, keyed by response item ID so reused call IDs cannot mix results.
- Restore those observations for sampling and compaction, pruning them only when sampling confirms they have left the history window. Preserve observations across shortened compaction retries.
- Remove aggregate prompt metadata caps while retaining per-call argument limits and the outgoing message size limit. Invalidate cell completeness when argument normalization truncates a recorded call.
## Testing
Add regression coverage for exhausted persistence budgets, reused call IDs and reversed completion order, shortened compaction retries, and completeness after argument truncation. Extend integration coverage for large Code Mode metadata, provider metadata support, and fork/resume behavior.
GitOrigin-RevId: 004082b69bff9cc8b05f36d1052057f163c67f07
## Why
Configuration reloads must honor current managed restrictions without granting new enterprise MCP authority to existing sessions or overwriting newer configuration with stale snapshots.
## What changed
- Allow enterprise managed authentication only for configured MCP servers. Remove plugin `ema_auth` overlays from the schema and disable servers that still use them.
- Refresh ordinary MCP settings while preserving session settings and initially admitted enterprise registrations. Disable enterprise MCP when its registration changes, policy revokes access, or configuration loading or resolution fails; require a new session to restore enterprise authority.
- Publish refreshes only when their captured configuration is still current, with bounded retries in app-server reloads. Preserve updated managed restrictions even when a refresh is rejected.
- Finish processing other thread refreshes before `config/mcpServer/reload` reports a rejection, and document that an error can accompany partially applied changes.
## Testing
Add regression coverage for stale refreshes, bounded retries, managed-policy revocation, persistent enterprise disablement, ordinary MCP transport changes, and rejection of plugin enterprise authentication. Verify that denied enterprise servers receive no requests.
GitOrigin-RevId: 34429cd339c1ec152a2ee8697cb29f0cff5d9e5f
## Why
Destination-only filtering stripped raw tool result metadata and MCP attribution when the built-in OpenAI provider used a custom endpoint.
## What changed
Add a runtime-only `include_internal_metadata` grant to `ModelProviderInfo` and enable it for the built-in OpenAI provider. Apply the provider grant or the existing first-party HTTPS destination check to both HTTP and WebSocket Responses requests.
Keep the grant out of serialized configuration and schemas, and default it to false for providers received through remote configuration. Providers without the grant retain the existing destination filtering.
## Testing
Update HTTP and WebSocket tests to expect metadata at overridden OpenAI endpoints. Cover provider grants, destination filtering, MCP attribution on requests, and the grant's exclusion from TOML serialization and configuration.
GitOrigin-RevId: 53aad6fb4d52cdfa9c79c6d92fe87383e1d0d1ef
## Why
When a nested code-mode call's recorded arguments were truncated and attached to an output before its result arrived, the recorder could no longer attach the result metadata to that call.
## What changed
Retain validated call bindings so late result metadata updates the original output across retries and subsequent waits. Keep truncated arguments and incomplete call inventories intact, and apply existing metadata budgets.
Invalidate late metadata bindings when duplicate IDs, reused cells, conflicting outputs, or changed call inventories make attribution ambiguous. Clear stale pending calls when a cell ID is reused, and avoid counting duplicate pending IDs against capacity more than once.
## Testing
Add recorder regression tests for late metadata across retries, compaction, waits, and cell closure, plus ambiguous bindings and budget limits. Add a code-mode integration test that delays a tool result until its truncated call has been recorded and verifies metadata remains attached to the original output across later waits.
GitOrigin-RevId: 7398beaaa1a513147deebdea7aa841513a79d06b
## 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
## 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
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
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
## 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
## What changed
Add `model_messages.tools.indirect_description_prefixes` with selectors for exact namespaces and configured MCP server names. Apply the selected model's guidance to namespace documentation embedded in `CodeModeOnly` prompts, `ALL_TOOLS` descriptions, and namespaces returned by tool search.
Trim prefix values, treat empty values as no prefix, and reject conflicting selectors for the same namespace. Apply prefixes during rendering so model changes take effect without altering direct tool specifications, search ranking, or tool dispatch.
## Testing
Add unit tests for prefix normalization, namespace grouping, MCP server mapping, and conflicts. Add scenarios covering both Code Mode variants, clearing prefixes on model changes, unchanged tool dispatch, and conflict rejection before a model request.
GitOrigin-RevId: 0c7ce6d418c775945c2ccfdab3c605fa4d431b55
## Why
Reaching the pending tool-call limit could evict finished empty cells even though removing them frees no pending-call capacity. This loses the metadata needed to certify an empty tool-call inventory on a later `wait`.
## What changed
Only evict cells with pending calls when reclaiming pending-call capacity. Keep empty cells eligible for eviction when a cell slot is needed.
## Testing
Extend recorder coverage to check empty inventories under pending-call pressure in fresh and resumed sessions. Add a code-mode integration test verifying that `wait` serializes an empty inventory with `tool_calls_complete: true` while another cell has filled the pending-call budget.
GitOrigin-RevId: 559d0b4fdc9864c42a90b7d087eb2a3327272d5c
## What changed
- Record each MCP source and its first turn, including connector and plugin identifiers when available. Cover direct and Code Mode calls, including returned errors and results that are not printed.
- Persist cumulative attribution checkpoints and restore them across compaction, resume, and forks, including forks limited to recent turns.
- Attach fresh attribution to Responses API `client_metadata` under `mcp_attribution`, outside model-visible content. Restrict transmission to allowed OpenAI HTTPS destinations for both HTTP and WebSocket requests.
- Report `attribution_error` for legacy history without checkpoints, malformed or conflicting attribution, and serialized attribution exceeding 16 KiB.
## Testing
Add coverage for source deduplication, checkpoint persistence and restoration, recent-turn forks, direct and Code Mode calls, destination filtering, and the serialized size limit.
GitOrigin-RevId: fd285e152ca9e24bfa000debb20013709d67a86e
## Why
Orphaned output mappings and pending calls from finished cells can exhaust recorder capacity, preventing fresh code mode calls from attaching complete executed tool call metadata.
## What changed
Reclaim output mappings without remaining cells when the mapping limit is reached. Under cell or pending-call pressure, evict finished cells without output mappings, invalidate their retained completion markers, and release their pending-call count. Preserve the cell being registered and keep late records until capacity pressure requires cleanup.
## Testing
Add regression coverage for preserving existing cells and late partial records under mapping pressure, and an integration test verifying that a fresh code mode call carries its executed calls, cell ID, and completion marker after orphaned mappings fill the recorder.
GitOrigin-RevId: 8894d1283a962088fbf8cad60078cc0cd07aaf17
## Why
Code Mode cells that finish without invoking tools omit completeness metadata, leaving a verified empty inventory indistinguishable from an unverified one.
## What changed
- Retain completed, losslessly recorded cells even when they contain no tool calls.
- Always include `executed_tool_calls` when setting `tool_calls_complete`, using `[]` for empty inventories or terminal waits with no new calls.
- Preserve completeness across request retries while revalidating history and rejecting late calls or ambiguous output mappings.
## Testing
Add regression coverage for empty tool discovery, errors, termination, feature gating, retries, and fresh-session requirements for waits. Update protocol assertions to require an explicit empty call list with completeness metadata.
GitOrigin-RevId: 24affe47f46068b6559d04a0103958ae83a00b92
## Why
Compaction prompts omitted recorded Code Mode tool calls, leaving them without the nested tool inventory available to normal sampling requests.
## What changed
- Attach pending and retained Code Mode tool metadata to local and remote v2 compaction prompts, including updated result metadata and completeness markers.
- Bound Code Mode metadata separately while preserving captured direct tool records.
- Keep observations omitted from shortened compaction retries available if compaction fails and normal sampling resumes.
## Testing
Add regression coverage for metadata attachment, retry retention, independent budgeting, and binding validation. Extend local and remote compaction tests to check tool inventories with metadata enabled and disabled.
GitOrigin-RevId: 1dc012bd5838797c605d981a8fc1b0378a142227
## What changed
Add an optional `protocol_mode` to `McpServerContribution::HostedApps` and apply it when registering the server. Preserve the hosted Apps default when no override is provided.
## Testing
Add an integration test that selects MCP `2026-07-28` with the global feature disabled and completes a native user verification flow, including resuming the tool call with the verification response. Extend capability tests to confirm that the override preserves hosted Apps user verification without granting it to ordinary extension registrations.
GitOrigin-RevId: e8662c45f964c00b0bb4503bbcfd8432d7e2fa70
## What changed
Capture result metadata for host-owned app calls when analytics and executed tool call metadata recording are enabled. Respect both `analytics.enabled = false` and host-disabled analytics, using the prepared call's ownership to determine eligibility.
Disable incremental WebSocket request reuse when raw result metadata or its call binding changes, so late results attached to an already-sent output are included in the next request. Continue allowing reuse when only other metadata changes or result metadata is filtered out for the endpoint.
## Testing
Extend coverage for direct and code-mode calls, analytics settings and host overrides, runtime recording changes, and prepared call ownership. Add metadata comparison and WebSocket reuse tests, and verify that raw response item notifications continue to omit result metadata.
GitOrigin-RevId: 411843fbff3749ee96fd6f0ebc591362942a4555
## What changed
Represent images in `ContentItem` and `FunctionCallOutputContentItem` with `ImageReference::Inline`, flattened to preserve the existing `image_url` wire format. Update image producers and consumers and regenerate app-server schemas and SDK artifacts.
Preserve the Python SDK's `InputImageContentItem` and `InputImageFunctionCallOutputContentItem` class names during generation.
## Testing
Add a regression test for stable Python image class names and adapt existing image tests to the shared representation.
GitOrigin-RevId: c38a780ac3314c2ac2deb3afc1b93b94b6f93fec
## What changed
Include `sessionId` and the originating `windowId` alongside `threadId` and optional `itemId` in MCP request metadata. Retain the originating item and window for code-mode cells across waits and compaction, including the window when no matching history item is found.
## Testing
Extend metadata assertions for direct and nested MCP calls. Add a regression test verifying that a code-mode cell retains its original item and window IDs when it resumes after compaction.
GitOrigin-RevId: 5e3cf761f2bed4c16565334c94654496367325fd
## Why
Direct tool-call records need to stay associated with the invocation that produced each output, including when call IDs are reused. Completeness must describe the recorded call inventory, independently of tool success.
## What changed
- Attach direct-call records to outputs before they enter history, and set `tool_calls_complete` when the invocation's arguments are fully recorded.
- Bound pending recordings and retained metadata, release reservations on completion or cancellation, and invalidate pending records when capture is disabled.
- Apply request budgets to direct metadata and strip it from inference and compaction inputs when capture is disabled.
- Remove executed-call metadata from app-server raw response notifications and exclude its size from Guardian history retention budgets.
- Track call IDs that bypass dispatch so their reuse cannot incorrectly establish Code Mode completeness.
## Testing
Add regression coverage for direct-call attribution, malformed calls, metadata budgets, cancellation, configuration changes, compaction, notification filtering, and Guardian context isolation.
GitOrigin-RevId: 2ebd39c7f141d04788736491495109841656b4c0
## Why
A code-mode cell can outlive its turn. Nested tool calls dispatched during a later turn need the original step's tools and context, while approval handling must still work across that turn boundary.
## What changed
- Retain each cell's originating `StepContext` for nested tool dispatch and cancel queued calls whose context has been released.
- Keep MCP approval metadata available for the lifetime of the running invocation, keyed by server and call ID.
- Apply Guardian denial accounting and interruption to the active turn, including reviews from an earlier cell.
- Carry `turn_id` in legacy MCP begin/end events so history reconstruction and rollout migration assign late completions to their original turn. Preserve the current-turn fallback for older records without it.
## Testing
Add regression coverage for originating tool selection across turns, callback and metadata cleanup, delayed MCP elicitation review, Guardian interruption of the active turn, and late MCP completion attribution with legacy compatibility.
GitOrigin-RevId: 4533379aae6e4ecb4aabe5a25e4aca5d65385d76
## Why
Reused call IDs, ambiguous exec/wait associations, and missing history can make tool-call completeness claims unreliable. Truncating one cell's recorded calls should also preserve completeness for unrelated cells.
## What changed
- Track observed call and runtime cell IDs with bounded memory, including call IDs from initial history, and withhold completeness when evidence is missing or ambiguous.
- Validate exec/wait input-output associations and keep invalidated completeness from returning on retries. Withhold wait completeness after resume or fork, where runtime cell IDs can be reused.
- Keep truncation markers and omission counts local to each output, clearing completeness across the affected cell while preserving unrelated cells within the metadata budget.
- Refresh recording enablement from runtime configuration without changing execution features, and preserve the live recorder during legacy configuration reloads.
## Testing
Add regression coverage for reused IDs, compaction, resumed waits, mismatched wrappers, runtime recording changes, and metadata budgeting that preserves unrelated complete calls.
GitOrigin-RevId: 0bc85964bee079879620ec0664eea530a13b61fb
## What changed
- Add host-recorded `tool_result_metadata` snapshots with size limits, redacted debug output, and protection against deserialization from untrusted input. MCP capture remains disabled.
- Preserve accepted metadata across retries and delayed Code Mode results. Shed raw metadata before source evidence, calls, or completion markers when the request budget is exceeded.
- Send raw metadata only to allowed OpenAI and ChatGPT HTTPS endpoints, filtering by the resolved destination for HTTP and WebSocket requests.
- Encode source parse failures as an array entry with type `parse_failed` and an empty ID.
## Testing
Add coverage for metadata bounds and redaction, retained-call updates, budget shedding, disabled MCP capture, and HTTP/WebSocket destination filtering.
GitOrigin-RevId: b1a396323ad0623167cdd9e20ff9453f0d01bbf7
## What changed
- Add `disabled_plugin_ids` to thread startup options, settings overrides, snapshots, and persisted turn contexts. Omitted overrides preserve the current list; an empty list clears it.
- Restore the selection on resume and capture it before truncating history for a fork. Prefer the owning thread's latest settings snapshot, falling back only to the latest turn context so stale history cannot resurrect an older selection.
- Freeze the selection at turn admission and retain compatibility with histories that lack the new fields.
## Testing
Add coverage for owned settings, explicit clears, latest-turn fallback, and legacy snapshots. Extend settings tests to cover plugin selection during runtime restoration and compaction, and verify initial turn persistence without extra settings checkpoints in both history modes.
GitOrigin-RevId: 75ffbff5763cd93cc5ac69d73b08b237f59bc009
## Why
Review evidence can fit its own limits while exceeding the reviewer context window once history, tools, output format, and reminders are included. Tool continuations can also push an existing review over budget.
## What changed
- Select evidence after tools and turn context are resolved, reserving request overhead and a 256-token margin. Omit optional evidence while preserving required sections, and reject required evidence that cannot fit.
- Keep incoming evidence pending until budget selection succeeds so cancellation and compaction cannot record unselected input in reusable history.
- Check the assembled prompt before sampling, including retries and tool continuations. Retry budget failures with summary compaction once per model step, and retire reviewers whose budgets remain exhausted. Avoid history-resetting token-budget compaction for this recovery.
- Record section costs after budget selection.
## Testing
Add unit and integration coverage for required-evidence rejection, optional-evidence omission, reminder overhead, cancellation safety, incoming-review and tool-continuation compaction, and reviewer retirement after ineffective compaction.
GitOrigin-RevId: 2f7ef191b3f46032d295ad363eb7debf9d7a9684
## What changed
- Route manual and automatic remote compaction through the v2 implementation.
- Retire the `remote_compaction_v2` feature toggle while continuing to advertise it in the model client beta features header.
- Migrate compaction tests from `/responses/compact` to streamed `/responses` requests with `compaction_trigger` items and remove legacy parity coverage.
## Testing
Add streamed compaction coverage for tool search output trimming and session base instruction token estimates. Update app-server tests to verify started/completed notifications for both local and streamed remote compaction.
GitOrigin-RevId: cea392a6166a9b116ff83708fd9126d5546476e4
## Why
Saved model selections can outlive their bundled catalog entries and still need migration guidance.
## What changed
- Remove `gpt-5.2` and `gpt-5.4-mini` from the bundled model catalog.
- Preserve migration from saved `gpt-5.4-mini` selections to `gpt-5.6-luna` when the old model is absent, while respecting catalog-provided migration metadata.
- Update tests and snapshots to use current models or explicit test fixtures, and remove the obsolete prompt fixture.
## Testing
Extend migration tests to cover catalog metadata precedence, saved selections, replacement model and reasoning-effort persistence, acknowledged prompts, and missing or hidden migration targets.
GitOrigin-RevId: 82beea504cc4a15699677c28a61ec0939af3069c
## Why
Guardian reviewers can inherit token-budget mode from the parent session or model defaults, causing context rollover instead of summary-based compaction.
## What changed
Clear inherited token-budget startup activation, set an explicit default `TokenBudgetConfig`, and disable `Feature::TokenBudget` and `Feature::ContextManagement` for Guardian review sessions.
## Testing
Update regression coverage to verify that reviewers compact with a summary even when the parent and model enable token budgets. Cover both transcript modes and browser evidence, checking that review requests omit `token_budget.context_window` and retain the compaction summary.
GitOrigin-RevId: e1a84f9c7752a712399cd749c3834b2a7bb4a7e6
## Why
Passing `undefined` to a tool could fail JSON parsing because V8 stringifies it as the non-JSON text `undefined`.
## What changed
Return no JSON value for JavaScript `undefined`, so explicit `undefined` tool arguments behave like omitted arguments. Attempts to `store` an undefined value report the existing serializability error and preserve the previous stored value.
## Testing
Add regression coverage for storing `undefined` over an existing `null` value, and extend the current-time tool test to cover `{}`, omitted arguments, and explicit `undefined`.
GitOrigin-RevId: 071050ebb2ecc44c8f08453cf8523b4d21728c7e
## Why
A code-mode `exec` wrapper and its nested tool calls each advance Guardian's score lag. Counting the unscored wrapper against its own nested approval can trigger a synchronous review sooner than needed.
## What changed
Track originating response items and approval tool-call IDs so cached approvals discount their own wrapper when it is newer than the latest score. Preserve wrapper identity across yields and waits, and retain the full lag when provenance is missing or evicted. Other wrappers and scoring failures still count.
Use the current `write_stdin` call's identity for approval freshness, and omit tool-call identity for `execve` intercepts that only retain the launch ID.
## Testing
Add coverage for wrapper-specific discounts, already-scored wrappers, missing and evicted provenance, identity across code-mode resumes, and approval identities for stdin writes and `execve` intercepts.
GitOrigin-RevId: 4002a06d64c4e1e0a13c072303503d6ddfacad09
## What changed
Capture the ID from `response.created` and pass it as `parent_response_id` in Guardian review and classifier request metadata. Clear the current response ID before sampling retries so tool reviews cannot inherit a failed response's ID.
Request Guardian credits with `guardian_credits_requested` on eligible parent requests. Remove the ticket protocol, transport attachment, and ticket-specific body redaction. Keep ordinary app-server client `parent_response_id` values inside `x-codex-turn-metadata` rather than promoting them to Guardian request metadata.
## Testing
Update coverage for HTTP fallback, WebSocket review reuse, missing response IDs, classifier transport retries, and code-mode yield/resume attribution. Extend app-server tests to verify client metadata placement over HTTP and WebSocket.
GitOrigin-RevId: c1665e56382ecec8d260fc2ca0ecd5e20b0b2391
## What changed
- Request and parse server-issued Guardian tickets for eligible Codex backend responses.
- Scope each ticket to the response that produced a Guardian review or classifier request, including HTTP and WebSocket retries, without adding it to model-visible or persisted context.
- Validate ticket shape, reserve its metadata keys, redact it from debug and request-body logging, and attach it only at the Guardian transport boundary.
## Testing
- Cover ticket parsing, endpoint and authentication routing, retry scoping, classifier retries, and redaction for compressed and uncompressed requests.
GitOrigin-RevId: 6219dd15c9f19ed3387de516aac1b8e7c9cdb0e3
## Why
Audio models cannot reliably encode tool-generated clips shorter than 25 ms.
## What changed
- Measure the available audio frames in base64-encoded PCM and IEEE float WAV outputs.
- Replace clips under 25 ms with explanatory text while preserving surrounding Code Mode output.
- Leave clips at or above the threshold and unrecognized audio formats unchanged.
## Testing
- Cover the duration boundary across multiple sample rates and all supported `audio()` input forms.
- Verify bounded and truncated WAV chunks, output after `yield_control()`, and end-to-end mixed text and audio output.
GitOrigin-RevId: 342b4bdbc65db4238580f9cdc372763c2576eca5
## What changed
- Default `tools.update_plan.enabled` to `false`; users can explicitly enable it to expose `update_plan`.
- Remove bundled `update_plan` guidance from model, collaboration-mode, multi-agent, compaction, prewarm, and goal-continuation prompts when the tool is disabled.
- Preserve custom base instructions, model catalog instructions, collaboration policies, and user goal text even when they mention planning or `update_plan`.
## Testing
- Cover default and explicitly enabled tool registration, prompt consistency across request paths, and preservation of custom instructions.
GitOrigin-RevId: a53964e6e72f98e2557dd3090fdb7caccb956527
## Why
Environment-backed stdio MCP servers have no host-local working-directory
fallback, so their test fixtures must provide a workspace explicitly.
## What changed
- Set the fixture workspace as `cwd` for environment-backed MCP servers across
the core integration tests.
- Reuse the same test environment when configuring MCP servers and building
fixtures that need an explicit working directory.
GitOrigin-RevId: e38f2029e01fc1377cdc34d01a392ad310419766
## What changed
- Cover the default, explicitly enabled, and explicitly disabled states of
`tools.update_plan.enabled`.
- Verify prompt tool lists remain consistent across requests, including when
custom base and developer instructions are configured.
- Explicitly enable `update_plan` in existing fixtures that depend on the tool.
GitOrigin-RevId: 3be279cb5195dfc5892c2c8ff6a1461fac879309
## Why
Long-lived Guardian sessions can exhaust the review model's context window. After
a rollover, a transcript delta is insufficient because the new window no longer
contains the original transcript or persistent review instructions.
## What changed
- Compact an exhausted Guardian session before submitting the next review while
respecting the review model's token-budget configuration.
- Detect whether the full transcript remains in the reviewer history. If it does
not, reset transcript and Node REPL evidence cursors so the next review replays
the complete transcript and associated image evidence.
- Restore the follow-up reminder and Node REPL policy when compaction removes
them.
## Testing
- Cover rollover both when the reviewer window is already exhausted and when a
follow-up reminder crosses the limit.
- Verify that multimodal reviews preserve the fallback buffer and replay browser
evidence after rollover.
GitOrigin-RevId: f2a02a84e1f25d15c6e2b8eddb93e2d1805449f5
## Why
Executed-tool metadata for a Code Mode cell can span its `exec` and `wait`
outputs. Consumers need to know whether that metadata contains the cell's full
tool call inventory or only a partial record.
## What changed
- Associate recorded tool calls with the originating Code Mode cell across
`exec` and `wait` outputs.
- Add a host-owned `tool_calls_complete` marker when recording finishes without
dropped or truncated calls. The marker describes inventory completeness, not
tool success.
- Preserve the cell metadata through replay and pruning, and clear the
completeness marker when prompt budgeting makes the record incomplete.
## Testing
Add coverage for multi-wait cells, retries, interruptions, recording limits,
argument truncation, prompt budgeting, and rejection of input-forged metadata.
GitOrigin-RevId: 377014edec06aab42aadab78b8b5dccc0a1c83ba
## What changed
- Add callback lifetimes to extension `ToolCall`, `ToolEnvironment`, turn-input context, and skill-read request types.
- Require extension tool executors to handle calls for any invocation lifetime and tie their returned futures to that lifetime.
- Update built-in extensions, adapters, and tests to use the lifetime-scoped APIs without retaining host-owned environment capabilities.
GitOrigin-RevId: aca9ce3a1b6870df550bc84ec9308cc65533f161
## What changed
- Add the originating Responses item ID to MCP tool request metadata as
`_meta.itemId`.
- Preserve the initiating `exec` item ID across code-mode cells so nested MCP
calls carry the same origin.
## Testing
- Cover metadata generation for direct and code-mode MCP tool calls.
GitOrigin-RevId: 1161cac64f1cc3a6d4dac4368e63804bd9d2c417
## What changed
- Recognize `cua_repl` alongside `node_repl` when collecting Guardian review evidence, applying computer-use policy, and capturing transcript images.
- Render `cua_repl.js` results with the compact REPL history and transcript views.
- Preserve failed MCP call status and result content when replaying app-server history.
## Testing
- Cover both REPL server names across Guardian policy, evidence, image capture, history rendering, and failed-call replay tests.
GitOrigin-RevId: 8c13a721f718add403b07e727c1634b59203c51a
ningyi-oai