Commit Graph
1595 Commits
Author SHA1 Message Date
jif 851d9e95f1 Bind Guardian reviews to the action's target environment (#47630)
## Why

Actions targeting a secondary environment could be reviewed with the primary environment's denied-read restrictions. Each review needs the permission context of the environment that owns the action, including when a Guardian session is reused across environments.

## What changed

- Carry `environment_id` through environment-scoped approval requests and their planned-action JSON.
- Select and label permission context using the target environment, explicitly stating when it has no denied-read paths or globs.
- Reject reviews for unavailable target environments and reject environment IDs longer than 256 bytes before Guardian inference, while preserving manual approval routing for oversized IDs.

## Testing

Add coverage for `exec_command`, `apply_patch`, and `request_permissions` reviews switching environments while preserving the existing review prefix. Extend tests for environment-specific restrictions, unavailable environments, action serialization, and the 256-byte ID boundary.

GitOrigin-RevId: ad3292edddb1c6f5b180142c6857cba6f1308328
2026-09-23 19:03:12 +00:00
Ankush Gupta f07b26c9c9 Recognize user_message tools in Guardian authorization context (#47624)
## Why

Messages sent through the singular `user_message` connector were omitted from Guardian's delivered assistant message evidence because only `user_messaging` tool names were recognized.

## What changed

Accept both namespaced and flat `user_message` forms of `send_message` alongside the existing `user_messaging` forms.

## Testing

Extend Guardian subagent authorization tests to cover the singular connector and flat tool names, including blocked post-tool hooks and cancellation before confirmation. Add a negative case ensuring `send_message_to_thread` is not treated as delivered message evidence.

GitOrigin-RevId: 68495642ef4b78eec71df4fee2bacfda407adc47
2026-09-23 18:53:38 +00:00
iceweasel-oai 6f6af0fce4 Record sandbox backends in command execution analytics (#47568)
## Why

Command execution analytics lack the observed sandbox backend. Older execution servers may omit this information, so an unknown backend must remain distinguishable from an explicitly unsandboxed process.

## What changed

- Carry optional `sandbox_type` metadata through command execution items and emit its metric tag as `sandbox_backend` in analytics.
- Propagate the observed backend through unified execution completion and failure events, including asynchronous exits.
- Preserve missing backend information as `None` and mark executed user shell commands as `Some(SandboxType::None)`.
- Exclude the metadata from serialized command items and generated schemas and TypeScript types.

## Testing

Extend tests for missing and explicit executor backends, backend propagation on failed execution, and analytics payloads, including platform-specific backend tags in app-server integration coverage.

GitOrigin-RevId: 178fe46824a6194910802ec02168ed40ee0b2019
2026-09-23 15:05:59 +00:00
jif 30fc6864cc Add an option to disable multi-agent v2 direct messaging (#47540)
## What changed

Add `features.multi_agent_v2.disable_direct_message`, defaulting to `false`. When enabled, omit `send_message` and `followup_task` while preserving spawning, automatic child results, and the remaining agent management tools.

Require an available message-board `post` tool when this option is enabled for sessions using multi-agent v2 collaboration tools, exempting internal worker sessions.

## Testing

Extend configuration parsing tests and run the message-board subscription/resume scenario with direct messaging both enabled and disabled. Verify post search, subscription behavior, and which collaboration tools are exposed.

GitOrigin-RevId: 72ec22ef0b92fa81e02cdeb058d8b4f93aca3be6
2026-09-23 12:09:05 +00:00
jif 0b23f365f8 Route agent lookups and V2 context through AgentControl (#47536)
## Why

V2 tools and model context need to use the controller's agent tree even when the session's local runtime has no registry entries.

## What changed

- Add target resolution and direct-child path lookup to `AgentControl`.
- Move lazy root registration into the controller's resolution and listing methods.
- Build V2 subagent context from controller-provided paths, keeping formatting and size limits in the session layer and preserving loaded-first ordering.

## Testing

Extend the V2 spawn and messaging test with an empty session-local registry to cover relative-path resolution, message delivery, and subagent environment context through the controller.

GitOrigin-RevId: c935b34a6d3314e968ba451ff981cf2a223bbfa8
2026-09-23 11:07:41 +00:00
Peter Steinberger a69d757cd8 Emit command lifecycle events for unified exec launch failures (#47529)
## Why

When unified exec cannot create a process, command lifecycle events are missing, leaving clients without a command failure notification.

## What changed

Emit start and failure events for terminal process-creation errors in both regular and zsh-fork execution. Report no process ID, an exit code of `-1`, zero duration, and the launch diagnostic, while retaining plugin attribution. Once event publication starts, let it finish even if the caller is cancelled.

Preserve approval rejection handling and retryable sandbox denials.

## Testing

Extend app-server tests to cover pipe and PTY launch failures, plugin attribution on failed launches, and zsh-fork launch failures after approval. Assert failure metadata and check for duplicate lifecycle notifications while retaining approval-decline coverage.

GitOrigin-RevId: 26ed191fc69b903ea4710dd1a6c3b031e8caa4eb
2026-09-23 10:18:21 +00:00
jif 27969c0ae9 Route session agent operations through AgentControl (#47520)
## What changed

- Store `Arc<dyn AgentControl>` in session services and route agent tools, turn admission, usage accounting, completion notifications, and shared settings through the trait.
- Add `AgentControlInit` so delegated and guardian sessions inherit the parent's controller and local runtime.
- Move local registry and context helpers to `LocalAgentRuntime`, keep resume, close, inspection, and status subscriptions on the local controller, and simplify synchronous and infallible trait methods.

GitOrigin-RevId: ad3f213eb483ac524bde56d769f20a78f20989a0
2026-09-23 09:39:30 +00:00
sayan-oai 370cd7cba8 Allow environment selection updates during an active turn (#47435)
## What changed

- Add `environments` to `TurnSettingsUpdate` to replace the selection for subsequent steps without changing future turns.
- Capture model settings and environments together so combined updates apply or reject atomically, while existing steps retain their captured selection.
- Validate environment IDs, working directories, configuration ownership, and permission requirements against the running turn's selections.
- Preserve executor startup behavior when switching environments and use the step's local working directory for tool hooks.

## Testing

Add coverage for workspace switching and restoration on the next turn, atomic model and environment updates, permission validation, executor connection waits, and replacement of pending environment selections.

GitOrigin-RevId: 02b5c57a78fd594b2aed84fc09d9e99eb97be28c
2026-09-23 03:12:33 +00:00
Owen Lin 286d4ecf44 Persist resume metadata in compaction checkpoints (#47323)
## Why

Compaction companion records do not represent all resume state, including the last started turn and previous turn settings. The selected multi-agent runtime also needs a persisted value when no companion turn context is present.

## What changed

- Add optional `resume_metadata` to `CompactedItem`, recording the multi-agent version, last started turn ID, and previous turn settings. Preserve the distinction between absent metadata and explicitly empty values while retaining compatibility with older records.
- Capture this metadata under the settings persistence lock alongside the compaction checkpoint.
- Rewrite inherited metadata to use the child agent's runtime, and clear previous turn settings when the child must rebuild context.
- Clear pending continuation state before delivering acceptance of standalone settings updates, while holding the persistence lock.

## Testing

Add coverage for metadata round trips with empty values, legacy reader compatibility, checkpoint companion records, inherited fork metadata, and continuation invalidation while settings event delivery is blocked.

GitOrigin-RevId: f30b7feaa7e2fdb5b65fc3c53b37fd7a7fe27903
2026-09-22 16:35:30 +00:00
jif 5c07856e25 Separate local agent runtime state from controller handles (#47301)
## What changed

Extract `LocalAgentRuntime` from `LocalAgentControl` to hold the shared registry, residency state, execution limiter, rollout budget, service tier, instruction provider, and thread-manager bindings. Keep session identity on the controller handle.

Store the runtime in `SessionServices` and use it to bind controllers for child startup, resume, delegation, and guardian reviews. Route ownership checks and residency handling through the shared runtime, preserving registry identity across handles. Update existing test fixtures to keep the controller and runtime paired.

GitOrigin-RevId: 846094657cbdf736da3149f0a1c96b4e01423dfe
2026-09-22 14:48:28 +00:00
jif c6c09fe29f Consolidate agent operations in the AgentControl implementation (#47292)
## What changed

Move `spawn`, `send`, and `inspect` into the `AgentControl` implementation for `LocalAgentControl`, removing the forwarding methods and the `spawn_request` module. Update tool handlers and existing tests to use the trait methods, and remove redundant boxing at spawn call sites.

Preserve spawn validation, message attribution, runtime loading, and queue-only delivery semantics.

GitOrigin-RevId: 6027d4d97d0dfb6763dc97ef92a2d7ef58de945d
2026-09-22 13:47:56 +00:00
jif ac7634b9f7 Stream agent snapshots from local status subscriptions (#47267)
## What changed

- Return `StatusSubscription` streams of `AgentInfo` snapshots from local status subscriptions, including agent metadata and configuration.
- Emit the initial snapshot before subsequent coalesced updates. Use a weak thread reference and retain the last observed configuration so published final updates remain available after the runtime is dropped.
- Update completion notifications and `wait_agent` to consume snapshot streams, propagate subscription errors from `wait_agent`, and fall back to the latest status when a stream ends.

## Testing

Update the shutdown subscription test to verify that shutdown before the first poll preserves the initial `PendingInit` snapshot followed by `Shutdown`.

GitOrigin-RevId: beb46952cbcc9bddf65a4d6603fea939d5ace8b9
2026-09-22 11:44:00 +00:00
jif fdd89e78ac Return agent snapshots from close_agent (#47252)
## What changed

Return an `AgentInfo` snapshot captured before shutdown, including metadata for known unloaded agents. Use the snapshot's status and metadata in the tool's completion event and its status in `previous_status`, replacing the separate status subscription.

Preserve the pre-close status for error reporting when shutdown removes the target before a descendant fails to close. Propagate unexpected thread lookup errors before attempting shutdown.

GitOrigin-RevId: bdbd877aaf0389e830d6a7e84a5e14bb7d47277a
2026-09-22 10:58:32 +00:00
jif c46aa58a7b Centralize agent resume handling in LocalAgentControl (#47244)
## What changed

Add `LocalAgentControl::resume_agent` to reuse an existing thread or restore it from its rollout when lookup returns `ThreadNotFound`. Return the agent's current status, metadata, and configuration snapshot.

Route the `resume_agent` tool through this method, replacing its status-based resume check and separate restoration helper.

GitOrigin-RevId: 2ae0572a030f169eca1760ba0aff1fb9e2ab6651
2026-09-22 10:27:19 +00:00
jif f908e5a968 Route multi-agent spawning through SpawnRequest (#47235)
## What changed

- Route both multi-agent spawn handlers through `LocalAgentControl::spawn`, accepting user input or an agent message.
- Centralize spawn message attribution and canonical path validation, and require message input to use `TriggerTurn`.
- Return the child's configuration snapshot alongside `LiveAgent`, so handlers obtain effective settings directly from spawning without a separate lookup.
- Update child test fixtures to use the shared spawn entry point.

GitOrigin-RevId: 9f9278df08041a62215f9ec3d38688c78fc5e0e2
2026-09-22 09:32:22 +00:00
ningyi-oai a37f260dc6 Preserve empty cell metadata under pending tool-call pressure (#47174)
## 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
2026-09-22 03:03:52 +00:00
Adam Perry @ OpenAI 69759baefd Preserve foreign working directories in extension tool environments (#47129)
## Why

Extension calls omitted environments whose working directories could not be converted to host-native paths, preventing extensions from receiving those environments.

## What changed

Store `ToolEnvironment.cwd` as `PathUri` and pass all turn environments to extension tools without requiring host-native path conversion. Keep image generation's existing path requirements by selecting the first environment with a convertible working directory when reading referenced images or saving generated images.

GitOrigin-RevId: b4320c6e07d27ef59885cd0013e5d1c535f69659
2026-09-21 23:27:42 +00:00
rhan-oai 5aa4939be4 Support model-catalog overrides for Code Mode tool messages (#47118)
## What changed

- Add `tools.code_mode` catalog messages for `exec`, `wait`, deferred-tool guidance, and shared MCP TypeScript definitions.
- Render `{{ default_exec_yield_time_ms }}` and `{{ image_helper }}` in `exec` descriptions while preserving runtime tool declarations and the freeform grammar.
- Resolve `wait` descriptions and parameter schemas independently, falling back to bundled parameters for invalid or unsupported schemas.
- Use the active model's Code Mode messages, including after mid-turn model changes. Missing overrides retain bundled defaults; empty text overrides suppress the corresponding text.

## Testing

Add coverage for literal template substitution, runtime section preservation, independent `wait` overrides and fallback behavior, mid-turn model changes, and a yielded cell completing through `wait` with catalog messages.

GitOrigin-RevId: e542a0cd47a7138a414871192cee47790ed1214e
2026-09-21 22:49:17 +00:00
Eddie Chen 6a601c00da Preserve originating turn metadata for yielded skill calls (#47106)
## Why

Code Mode callbacks can retain skill tools after another turn becomes active. Looking up the active turn when a delayed skill invocation completes can lose access to the originating turn's metrics and metadata.

## What changed

- Capture and retain the originating `SkillTurnMetrics` when constructing skill analytics.
- Expose turn analytics metadata through the turn extension store and carry it into skill telemetry.
- Add optional turn metadata to `TrackEventsContext` and pass it from app, skill, and plugin usage call sites.

## Testing

Add a regression test that yields a Code Mode cell, starts another turn, and releases both skill reads through a shared barrier. Assert that each `skill_invocation` event retains its originating `turn_id`.

GitOrigin-RevId: aa629dd5f84563d558aa6a86bfbdfc356f1b98e4
2026-09-21 20:34:46 +00:00
peilin-openai ac98537678 Track cumulative MCP attribution across requests and thread history (#47081)
## 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
2026-09-21 18:19:07 +00:00
felixxia-oai 3483294596 Preserve delivered messages through post-tool hook failures (#47039)
## Why

Guardian can lose a confirmed User Messaging message from its parent context when a `PostToolUse` hook blocks the result or is cancelled. The message has already been sent and remains relevant to interpreting the user's authorization.

## What changed

Capture confirmed message text after input-rewriting hooks in shared per-call state before awaiting post-tool processing. Attach that evidence to the response metadata even when dispatch returns a blocked or aborted result, while keeping post-tool hooks cancellable. Calls cancelled before delivery confirmation contribute no message evidence.

## Testing

Extend Guardian subagent authorization coverage to verify retained messages after post-tool hook blocking and cancellation, and their absence when cancellation precedes delivery confirmation.

GitOrigin-RevId: 9abb7959980eada20d0fb5c0b3a4a8669e4cd0a3
2026-09-21 14:14:21 +00:00
Charlie Marsh 3ead673946 Defer extension tool history materialization until first access (#47035)
## Why

Extension tool calls eagerly copied and converted conversation history even when the tool never read it.

## What changed

Retain a shared invocation-time snapshot and defer conversion to raw response items until `ConversationHistory::items()` is called. Cache the result across clones with `LazyLock`, and keep debug formatting from triggering materialization. Release unrelated history metadata when capturing the shared items.

## Testing

Extend the extension executor test to verify that history first read after a later turn still reflects the invocation-time snapshot, in both legacy and paginated history modes. Update the history API test to check that shared items preserve their envelopes.

GitOrigin-RevId: c737b765b7e4889735dc78e12d685d36e854570b
2026-09-21 13:56:17 +00:00
felixxia-oai f585f13a12 Preserve ordered assistant context in Guardian reviews (#47030)
## Why

Guardian's retained root context appended assistant messages after user evidence and omitted questions sent through User Messaging. This could leave subagent authorization reviews with missing or misplaced conversational context.

## What changed

- Record assistant messages and function calls in the same order sequence as accepted user inputs, then merge retained review context by recorded position while prioritizing user evidence within the message budget.
- Capture bounded User Messaging text after input hooks when a send succeeds, and match it to the original call for assistant context.
- Label assistant context without a recorded position explicitly and clear parent assistant and tool positions when forking agent history.
- Clarify that recorded order does not establish delivery order or pair ordinary replies with questions; assistant messages remain untrusted context.

## Testing

Add coverage for hook-rewritten messages, failed or unconfirmed sends, queued replies with delayed tool results, ordering across resume, and removal of inherited assistant positions from forked history.

GitOrigin-RevId: ac717cf0f5efe4b05c18f2d8370dd48453ac4e35
2026-09-21 13:30:55 +00:00
jif 8a62cc4dc1 Align message-board tools with the multi-agent namespace (#47028)
## Why

Message-board tools hardcoded the `collaboration` namespace and used a different namespace description from the multi-agent tools. This ignored custom namespace configuration and caused conflicts under strict tool collision checking.

## What changed

- Use `multi_agent_v2.tool_namespace` and the shared multi-agent namespace description for message-board tools, resolving the namespace at runtime startup.
- Support unnamespaced tool specifications when no namespace is supplied.
- Remove hardcoded `collaboration` prefixes from message-board notifications.

## Testing

Add app-server integration coverage for the default `collaboration` namespace and a configured `agents` namespace with strict collision checking enabled. Verify that both tool families are advertised together and that `get_channels` executes through the installed extension.

GitOrigin-RevId: fef7be51ea2a84bbdb6d3491606db442ed4e6ea3
2026-09-21 13:27:39 +00:00
jif 7d99ee82d7 Add agent inspection without restoring unloaded runtimes (#47010)
## Why

Agent inspection needs to distinguish registered but unloaded agents from missing identities and backend failures without restoring a runtime.

## What changed

- Add inspection returning `AgentInfo` with metadata, status, and configuration for loaded agents, or metadata for unloaded agents.
- Use inspection for configuration snapshots and to capture an agent's state before interruption.
- Add `AgentInfo` accessors and share V2 error mapping between interruption and messaging tools, preserving the distinction between invalid requests and a dropped thread manager.

## Testing

Extend the V2 reload test helper to assert that inspecting a registered, unloaded agent returns `AgentInfo::Unloaded` and leaves its runtime unloaded.

GitOrigin-RevId: fa897264ff3ff3ec6cc76259d8482be55dec0c0a
2026-09-21 11:50:27 +00:00
felixxia-oai ebc05da3bd Decouple tool restrictions from session identity with ToolPolicy (#46999)
## Why

Tool allowlists alone cannot express the reviewer's sandbox and shell restrictions, which previously depended on session identity. Threads need to supply these restrictions explicitly at startup.

## What changed

- Replace `AllowedTools` with `ToolPolicy`, combining an optional allowlist with managed-sandbox requirements, unified-exec requirements, and control over additional-permission arguments.
- Capture the policy once at startup and apply it during tool registration and construction, including hosted tool filtering. Later extension-state changes cannot relax it.
- Supply the reviewer policy explicitly while retaining the fallback for reviewer sessions without a supplied policy. Explicit policies take precedence over session identity; ordinary defaults preserve existing tool setup.

## Testing

Update tool-planning tests to use explicit policies and add startup coverage for additional-permission schemas, ordinary defaults, reviewer fallbacks, explicit-policy precedence, and policy capture despite later extension-state changes.

GitOrigin-RevId: 71e561d76ea24d961f5b29c7c619bdb1356c216a
2026-09-21 10:40:40 +00:00
jif 3938a27c1d Route agent delivery through captured send requests (#46994)
## What changed

Replace `LocalAgentControl::deliver_message` with `send(SendRequest)`, accepting both user input and agent messages with captured resume configuration and turn options. Resolve target references relative to the caller's registered identity and return recipient metadata and a submission ID in `DeliveryReceipt`.

Migrate the V2 messaging tools to the new entry point and use receipt metadata for activity events. Preserve recipient reload behavior, non-waking queue-only messages, and rejection of follow-up tasks targeting the root agent.

## Testing

Update the cold-resume and sibling-reload tests to exercise `SendRequest` while checking instruction inheritance.

GitOrigin-RevId: 8fd330b8a9c3510483110ed05c4c9d3d616db237
2026-09-21 10:11:53 +00:00
Rennie c45ea25ffb Allow subagents to request MCP elicitation input (#46877)
## Why

MCP requests requiring user input previously failed in subagents with guidance to ask the parent agent, blocking browser sign-in, form input, and interactive tool approval in the child thread.

## What changed

Remove the root-only MCP elicitation guard and `allow_user_interaction` plumbing so subagents can surface prompts and wait for responses under the existing approval policy and automatic review rules. Connector authentication can now return retry guidance after acceptance or preserve the original failure when declined.

Keep legacy tool approvals through `request_user_input` restricted to the root thread.

## Testing

Update unit and integration coverage for subagent prompt resolution, form responses, connector authentication acceptance and decline, automatic approval, strict review, and approval-policy updates on reused connections. Update the browser sign-in scenario snapshot to show the subagent continuing after an accepted response.

GitOrigin-RevId: c226fc6dfde724ed22b91dc04dd32bbc15245bee
2026-09-20 19:42:18 +00:00
ningyi-oai ed0ee704b4 Recover executed tool call metadata under recorder capacity pressure (#46712)
## 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
2026-09-19 20:31:30 +00:00
sayan-oai c7828dd010 Keep step settings and approval environments consistent (#46556)
## Why

Background processes can outlive their launching turn. Their approval reviews need the originating environment's filesystem restrictions, even when the active turn uses a different environment. Remote restrictions must also be resolved using executor paths rather than the local filesystem.

## What changed

- Capture settings and environment selections together in `StepInputs`. Preserve the captured selection during active model updates while allowing environment startup to finish.
- Carry environment IDs into Guardian network and `execve` requests, and use the owning process's environment with current review settings. Refresh environment readiness for network requests that fall back to the active turn.
- Resolve remote denied paths and globs using the executor's policy context. Decline automatic approval when the request's environment is unavailable or an explicitly denied temporary directory cannot be resolved.

## Testing

Add regression coverage for active model updates retaining their environment while the next turn adopts a new selection, background approvals using their owning environment, newly ready network environments, and remote denied paths and globs, including Windows paths and missing temporary-directory metadata.

GitOrigin-RevId: b620d4b030c597a4f430fe0500864fa5469db3d4
2026-09-19 01:27:26 +00:00
iceweasel-oai a633ebc124 Always use private desktops for legacy Windows sandboxes (#46554)
## What changed

- Remove the private-desktop opt-out from elevated and unelevated Windows sandbox launches.
- Remove `windows.sandbox_private_desktop` and its managed requirement and API fields. Warn users to remove the obsolete setting.
- Require a private desktop name when launching through the Windows sandbox wrapper and command runner.

## Testing

Add coverage for the obsolete-setting migration warning and update wrapper tests to verify a live private desktop is passed and a missing desktop name is rejected.

GitOrigin-RevId: c7135f8d211aac8d812180691c2c1e433d77cde4
2026-09-19 01:21:32 +00:00
jif c6f5d9e9b5 Return LiveAgent records from agent listing (#46553)
## What changed

Return thread IDs, metadata, and status from `LocalAgentControl::list_agents` using the shared `LiveAgent` type. Move conversion to `ListedAgent` into the tool handler, preserving the `list_agents` response fields and the thread ID fallback for agents without a path.

GitOrigin-RevId: c935cf96ab2a370645a4b74e3306540fc2d168a5
2026-09-19 01:21:09 +00:00
jif c026e7a622 Expose a backend-independent agent control contract (#46547)
## What changed

Add a public, object-safe `AgentControl` trait and request/response types for coordinating an agent tree independently of where its threads run. Define contracts for lifecycle operations, message delivery, status observation, execution admission, usage accounting, shared configuration, and guardian evidence.

Move shared agent types out of the local controller and export them from `codex-core`. Let `AgentExecutionGuard` own a backend-provided reservation while preserving the local limiter's release-on-drop behavior. Include `root_thread_id` in `GuardianRootSnapshot` to identify the source of authorization evidence.

## Testing

Add tests for reservation release when a guard is dropped or a turn is cancelled, and extend the guardian authorization test to assert the root thread identity. Check trait object safety at compile time.

GitOrigin-RevId: 9385c9fbfd189f08429539fd89061ef8c9efe0d9
2026-09-19 01:03:55 +00:00
papayo-oai b244e9bafe Add a command-start callback for tool lifecycle extensions (#46539)
## What changed

Add `ToolLifecycleContributor::on_command_start` with `CommandStartInput` carrying the resolved command, working directory, selected executor's filesystem, and lifecycle context. Await contributors after command hooks and environment resolution so they can prepare the filesystem before `exec_command` runs, including calls from code mode.

Reserve process IDs only after preparation completes so cancelled preparation does not consume an ID. Keep deterministic process IDs from being reused after removal.

## Testing

Add tests for direct and code-mode calls that verify callbacks receive hook-rewritten commands and the executor's working directory, filesystem preparation completes before execution, and interrupted preparation prevents execution without consuming a process ID. Add a regression test for deterministic process ID reuse after removal.

GitOrigin-RevId: d10bcafcc583a6e3e8b5924d004806727e3763bb
2026-09-19 00:46:06 +00:00
iceweasel-oai 74af2496c9 Default local binding to true for MXC managed networking (#46523)
## Why

MXC's native host-loopback access is bidirectional, so it cannot enforce `allow_local_binding = false`. Treating an omitted setting as `false` prevents managed networking from working with the default configuration.

## What changed

- Preserve an omitted `allow_local_binding` until the executor's sandbox policy is known. Default to `true` for Windows MXC and `false` elsewhere, including remote execution.
- Reject an effective `false` for MXC managed networking after applying policy restrictions, without enabling disabled networking.
- Use the executor's resolved value for remote network approval decisions while preserving explicit controller restrictions.
- Document that local binding permits local servers and direct host-loopback connections and skips additional private-network destination checks; proxy domain rules still apply.

## Testing

Add coverage for per-executor defaults, explicit values, MXC rejection of `false`, and remote network review cleanup with the resolved policy.

GitOrigin-RevId: 0fa7c1eaec68bebada2b8f7af45688315eea70a9
2026-09-19 00:00:01 +00:00
jif 7fb599de8c Rename AgentControl to LocalAgentControl (#46513)
GitOrigin-RevId: a8e8a5c818a1751c5d2667f5af87e481482fc7db
2026-09-18 23:39:30 +00:00
rhan-oai cc7591646e Support catalog parameter schemas for Multi-Agent V2 tools (#46505)
## What changed

Add optional JSON-encoded `parameters` to catalog tool messages and apply them to all six Multi-Agent V2 tools, including plain, namespaced, and code-mode exposure. Schema selection follows the active model, including mid-turn model changes.

Require an object schema supported by the existing `JsonSchema` subset and preserve bundled encryption annotations. Fall back to bundled parameters when overrides are missing, invalid, unsupported, or omit encrypted properties. Tool execution and argument handling remain unchanged.

## Testing

Extend integration coverage for schema overrides, fallback behavior, encryption annotations, exposure modes, and mid-turn model changes. Add a snapshot scenario exercising `list_agents` with a catalog parameter schema.

GitOrigin-RevId: 978be6d5f7e6a6865969922be5483bc697b20aca
2026-09-18 23:16:56 +00:00
sayan-oai e0f05de6e0 Allow approved escalation with environment-owned network policies (#46499)
## Why

Environment-owned network policies rejected explicit sandbox escalation before command approval, and retained terminals that bypassed or no longer matched those policies required a new terminal.

## What changed

- Allow `require_escalated` commands through the normal approval flow and bypass managed network proxies when full escalation is permitted.
- Preserve denied-read restrictions, including the sandbox and network proxy needed to enforce them.
- Track the network restrictions bypassed at launch and require escalation review for terminal input when launch permissions or network settings warrant it, instead of rejecting input outright.

## Testing

Extend network approval coverage for approved and denied escalation, unproxied remote execution, and preserved denied-read restrictions. Add retained-terminal coverage verifying command and `write_stdin` approvals with restricted and unrestricted filesystems, and update the unit test for changed environment network policies to expect escalation review.

GitOrigin-RevId: 50524b1bc4e3df58447c3c92fb9e50e69ed50cf8
2026-09-18 23:06:48 +00:00
Sean Huang 3724dc8361 Share platform identity across path, network, and sandbox configuration (#46334)
## What changed

- Add `Platform` to `codex-utils-path-uri` with metadata parsing, native platform detection, and path convention mapping. Preserve missing or unrecognized metadata as `Unknown`.
- Replace `NetworkProxyExecutorOs` with the shared type and keep executor-specific socket path validation in the network proxy.
- Extract `effective_sandbox_mode` with explicit platform and Windows sandbox level inputs, preserving the native Windows fallback from `workspace-write` to `read-only` when the sandbox is disabled.

## Testing

Add unit tests for platform metadata, path conventions, native platform detection, and sandbox mode selection across platforms and Windows sandbox levels.

GitOrigin-RevId: 4fe0972e3a91040e35f2a6dfa5bcdf6c9a29be88
2026-09-18 00:51:34 +00:00
Sean Huang ea218f5cd8 Validate network socket policies using the executor OS (#46302)
## Why

A controller and its executor can run different operating systems. Validating socket paths against the controller's OS can reject absolute paths that are valid on the executor, such as Windows paths on a Linux controller.

## What changed

- Thread `NetworkProxyExecutorOs` through network policy validation, proxy construction, and policy updates.
- Require allowed socket paths to be NUL-free and absolute for the executor OS, while preserving deny entries unchanged.
- Accept either Unix or Windows absolute syntax when executor metadata omits the OS, then validate against the executor's own OS at launch.
- Keep native path normalization and socket support checks at execution time.

## Testing

Add coverage for cross-platform absolute path syntax, invalid allow entries, preserved deny entries, and remote policy round trips that retain executor semantics through domain edits and proxy construction.

GitOrigin-RevId: 1ebc09cbce7138f60ec5fd62875591a3df52d067
2026-09-17 20:59:55 +00:00
rhan-oai 3e581ebca8 Support catalog descriptions for all multi-agent V2 tools (#46297)
## Why

Model catalog description overrides only covered `spawn_agent`, leaving the other multi-agent V2 tools with fixed descriptions.

## What changed

Extend `model_messages.tools.multi_agent` description overrides to `send_message`, `followup_task`, `wait_agent`, `interrupt_agent`, and `list_agents`. Resolve each override by tool name across namespaced, plain, and Code Mode exposure.

Missing or null descriptions retain bundled text; empty strings suppress static text without disabling tools. Preserve `spawn_agent` runtime guidance, tool schemas, and execution behavior. Descriptions follow mid-turn model changes.

## Testing

Expand integration coverage to all six tools, including missing, null, empty, and sparse overrides; plain, namespaced, and Code Mode exposure; unchanged V1 behavior; and mid-turn model changes.

GitOrigin-RevId: a2c47eb8efb28c3eeebcc6482e36c188c38a6dd1
2026-09-17 20:05:47 +00:00
cassirer-openai 0fd1cd8d99 Add opt-in overhead timing to code-mode responses (#46288)
## Why

Code-mode responses show host duration without exposing time spent outside the host, including app-server waiting.

## What changed

- Add `features.code_mode.experimental_show_cell_overhead`, disabled by default, to show handler duration, host duration, and their difference in `exec` and `wait` response headers.
- Reuse the completed handler measurement from tool-call logging, excluding dispatch waiting, and capture it even when logging is disabled.
- Preserve the existing timing format when the option is disabled or host timing is unavailable, and preserve boolean feature toggles when merging nested code-mode configuration.

## Testing

Add coverage for timing headers, zero and missing host measurements, negative rounding differences, content preservation, and configuration merging. Extend app-server tests across gRPC and stdio to verify timing includes post-host elicitation waiting, and add a response snapshot for successful execution and a failed wait.

GitOrigin-RevId: 929b84784d9c6077cf2b5927a90bd2d5f3870078
2026-09-17 19:34:45 +00:00
iceweasel-oai 8b78600dc8 Enable MXC selection through Windows sandbox configuration (#46271)
## What changed

- Accept `windows.sandbox = "mxc"` and preserve the selected backend through environment configuration, command execution, patch writes, and sandbox metadata.
- Treat MXC as enabled in the TUI and report Windows sandbox readiness as `ready`, avoiding legacy setup prompts.
- Keep `allowed_sandbox_implementations` scoped to the legacy elevated and unelevated backends without restricting MXC.
- Default `windows.sandbox_private_desktop` to `false` for MXC while retaining `true` for legacy sandboxes.

## Testing

Add coverage for MXC configuration precedence, legacy requirement handling, sandbox selection, and TUI state. Add a Wine integration test that verifies command and patch routing fails when native MXC is unavailable and reports `windows_mxc` in turn metadata.

GitOrigin-RevId: e2162447d0750f60753864c92a20e02a7f297bca
2026-09-17 18:20:28 +00:00
surajs-oai 16f49ccd7f Relax delegation guidance in the v2 spawn_agent description (#46264)
Remove the default description's instruction to spawn agents only for concrete,
bounded subtasks that can run independently alongside useful local work.

GitOrigin-RevId: cbceed13c738b0f84fb90c053fa9285f541d578b
2026-09-17 17:36:51 +00:00
rhan-oai c5d079470e Allow model catalogs to override the V2 spawn_agent description (#46123)
## What changed

Read the static V2 `spawn_agent` description from `model_messages.tools.multi_agent.spawn_agent.description`, independently of the runtime tool namespace. Missing or null values retain the bundled description; an empty string suppresses it.

Preserve generated model guidance, local usage hints, and tool parameters when applying an override. Resolve the description from the active model so it follows mid-turn model changes.

## Testing

Add coverage for sparse and empty catalog values, preservation of generated context and outbound tool schemas, and description updates after mid-turn model changes.

GitOrigin-RevId: 96cfa180f8f374dc868e4fabc337e49380e405da
2026-09-17 05:17:31 +00:00
Adam Perry @ OpenAI a4ee536f01 Route filesystem reads and writes by their own sandbox permissions (#46122)
## Why

Filesystem reads previously required a sandbox whenever writes were restricted, even with full-disk read permission. This made permitted reads depend on sandbox availability.

## What changed

- Select sandboxing independently for reads and writes, allowing full-disk reads directly while keeping restricted operations sandboxed.
- Use the executor's path convention when evaluating full-disk access, including `:slash_tmp` denials.
- Apply read-specific checks to capability discovery and skill resource reads, allowing unrestricted reads on executors without sandboxed discovery support.

## Testing

Add regression tests for direct read APIs, restricted writes and reads, executor-specific permission rules, and capability discovery without sandbox support. Update Windows tests to verify sandbox enforcement through writes.

GitOrigin-RevId: a03844bd1f0ea583bb54326683cddbfdd050119f
2026-09-17 05:09:03 +00:00
Adam Perry @ OpenAI 841b5490b2 Preserve filesystem sandbox policy context when the cwd disappears (#46112)
## Why

Removing the selected working directory can prevent filesystem sandbox helpers from launching, even when the requested absolute paths remain accessible. Permission rules must stay anchored to the selected directory while those operations continue.

## What changed

- Require a policy `cwd` in `FileSystemSandboxContext` and launch filesystem helpers from the filesystem root while preserving the policy directory and workspace roots.
- Carry explicit `policyContext` in filesystem RPCs, preserving legacy wire fields and resolving omitted directories from older clients at executor ingress.
- Keep permission paths as executor file URIs and validate host compatibility where they are enforced.
- Bind Windows relative denial globs to the policy directory before changing the helper's launch directory, preserving home-relative patterns.

## Testing

Add regression coverage for `apply_patch` after working-directory removal, legacy RPC directory fallbacks, cross-platform permission URI transport, and Windows relative read denials. The patch regression verifies that an allowed file is updated while an explicitly denied file remains unreadable and unchanged.

GitOrigin-RevId: b0f4db722b27cb72ec129fc297c85732afac11f7
2026-09-17 04:37:54 +00:00
Jiwon Kim 108e6a6dbe Replace Sites migration state with a runtime compatibility guard (#46108)
## Why

Older Desktop clients can still provide bundled Sites to an independently updated SSH app-server. A cached remote Sites install must take precedence, even when disabled, while a missing remote bundle must preserve the bundled fallback.

## What changed

- Remove persisted bundled-plugin exclusions, Sites migration checks, and the migration wait when loading local plugin configuration.
- Suppress `sites@openai-bundled` during plugin loading when the remote global catalog is active and a cached remote Sites install is available.
- Remove exclusion-based catalog filtering and read/install guards, and simplify `install_plugin` to accept `ConfigLayerStack`.

## Testing

Expand the agent-turn Sites test to cover enabled remote precedence, disabled remote suppression of bundled Sites, and fallback when the remote bundle is missing.

GitOrigin-RevId: e2758596e5493ccee051cdfbf6b4afbe4f98948c
2026-09-17 04:23:45 +00:00
Nick Felt 8452164c76 Mark finished empty Code Mode tool inventories as complete (#46081)
## 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
2026-09-17 02:18:05 +00:00
rhan-oai 800d183e2d Use captured step settings when spawning subagents (#46075)
## Why

After a settings update during an active turn, spawned agents could inherit the turn's initial model and reasoning settings. Effort-only overrides could also be validated against the wrong model.

## What changed

Build child configuration from the invoking step's captured model, effective reasoning effort, and reasoning summary in both multi-agent versions. Validate effort-only overrides against that captured model's supported reasoning levels.

## Testing

Add regression coverage for spawning after an active-turn settings update in both multi-agent versions, including effort-only overrides. Update configuration tests to check captured settings and the model's default reasoning effort.

GitOrigin-RevId: 068bdb744149048829cdaa68d254b62e96e6e6af
2026-09-17 01:51:14 +00:00