Commit Graph
156 Commits
Author SHA1 Message Date
Won Park 550eb50545 Keep environment-backed tools exposed across readiness changes (#50741)
## Why

Environment readiness previously changed which tools and command parameters were advertised to the model, even when the selected environments stayed the same.

## What changed

- Keep enabled command, patch, image, and permission tools exposed when environments are absent, starting, or failed.
- Return a consistent message asking the model to wait when no usable execution environment is available, while preserving distinct errors for unknown environment IDs.
- Derive environment selectors from all selected environments rather than only ready ones.
- Always advertise `exec_command`'s `shell` and `login` parameters while continuing to enforce login policy at execution time.

## Testing

Expand integration coverage for empty, pending, failed, ready, and recovered environments, including stable command parameters and login-policy rejection. Update subagent and skill-catalog snapshots, with separate Windows expectations.

GitOrigin-RevId: bb08084066896a9f14b3b568c081c3eaac981db7
2026-10-03 23:22:59 +00:00
Ahmed Ibrahim 58ae3ba611 Keep third-party tools deferred in strict Code Mode Only (#50687)
## Why

Third-party exposure settings can eagerly expose tool schemas or exclude tools from `exec`. Keeping eligible tools deferred lets MCP catalogs change between turns without changing the model's eager tool prefix.

## What changed

Add the disabled-by-default `code_mode_only_strict_3p_tools` feature, applied only when the effective model tool mode is Code Mode Only.

- Defer eligible MCP, app, and client-supplied dynamic tools while keeping them discoverable and callable through `exec`.
- Override `deferLoading`, MCP/app `omit_tools_from`, and direct-only or excluded namespace settings. Log conflicts without adding prompt warnings.
- Preserve disabled, app-only, policy-denied, and over-budget tool restrictions. Keep built-in tool exposure unchanged, including when a dynamic tool has the same name.

## Testing

Add unit and integration coverage for exposure overrides, effective model modes, tool eligibility, and app discovery and dispatch. Add an MCP refresh scenario that verifies the eager tool prefix stays unchanged as tools are added, replaced, and removed while `exec` tracks the current catalog.

GitOrigin-RevId: a6a8e401214119bb02ea4711473c8fa3ec85c81a
2026-10-03 18:15:13 +00:00
Ahmed Ibrahim 55b6f282a8 Keep MCP resource helpers available in code mode (#50546)
## Why

In `CodeModeOnly`, MCP resource helper definitions changed when the first server was added or the last server was removed.

## What changed

Always register `list_mcp_resources`, `list_mcp_resource_templates`, and `read_mcp_resource` in `CodeModeOnly`, even without configured MCP servers. This keeps their definitions stable across server configuration changes.

## Testing

Add a regression scenario that calls all three helpers before adding a server, with a server registered, and after removing it. Assert identical tool definitions across requests, empty resource and template lists, and the expected error when reading from an unknown server.

GitOrigin-RevId: c5777efac250b83dd4bb1c9100a6b6169470556f
2026-10-03 06:42:48 +00:00
pakrym-oai fd75aa116c Remove the provider capability gate for tool namespaces (#50447)
## What changed

- Remove `namespace_tools` from `ProviderCapabilities` and `namespaceTools` from `ModelProviderCapabilitiesReadResponse`, updating generated schemas and SDK types.
- Preserve tool namespaces and configured collaboration tool namespaces without a provider capability check, and always use Responses Lite tool serialization for Responses Lite requests.
- Gate tool search on `supports_search_tool` and retain the existing image generation and web search checks without requiring a namespace capability.

GitOrigin-RevId: ae1843563736765a40e03a02c41ff5e470018a93
2026-10-02 22:55:08 +00:00
jif 2e5fea64ee Add an opt-in model catalog to multi-agent context (#49560)
## Why

Refreshing available model descriptions changes the `spawn_agent` tool schema. Keep model choices current while preserving tool definitions and earlier conversation input.

## What changed

- Add the disabled-by-default `model_catalog_in_context` feature for multi-agent V1 and V2. When enabled and model overrides are available, move model listings from tool descriptions into developer `<model_catalog>` messages.
- Include picker-visible, compatible models with descriptions, reasoning efforts, and service tiers in a listing bounded to 1,000 bytes. Point `spawn_agent` guidance to the latest catalog.
- Append updated listings only when their rendered content changes, restore missing listings, and invalidate retained catalogs when they no longer apply.

## Testing

Extend integration coverage for V1 and V2 with the feature enabled and disabled. Verify that catalog refreshes preserve tool definitions and prior input when enabled, append the updated listing once, and retain the existing tool-description behavior when disabled. Add a request-history snapshot for the V1 opt-in path.

GitOrigin-RevId: 67b11b4ad6c35f00d0e29edf6343bb0b4804d797
2026-09-30 10:03:09 +00:00
Vivian Fang 339e981ba7 Make MCP and Code Mode input schema budgets configurable (#47936)
## 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
2026-09-24 20:39:37 +00:00
rhan-oai 29f056c26c Honor catalog schemas for asynchronous user input (#47773)
## 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
2026-09-24 07:21:20 +00:00
rhan-oai b2aa42e6f1 Support model catalog overrides for MCP resource tool specs (#47677)
## 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
2026-09-23 22:09:18 +00:00
rhan-oai 8c66a5a243 Add model-specific prefixes to indirect tool descriptions (#47642)
## 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
2026-09-23 19:54:07 +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
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
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
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
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
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
ptiet-oai a6d4741d39 Add per-app tool exposure configuration (#46035)
## Why

Server-level tool exposure settings apply to every connector on the apps server. Individual connectors need a way to opt out of deferred discovery without changing exposure for other apps.

## What changed

Add `apps.<connector_id>.omit_tools_from` with support for `code_mode`, `deferred`, and `direct`. Combine connector omissions with server omissions so app settings preserve server restrictions.

For example, `omit_tools_from = ["deferred"]` makes a connector's tools available without tool search, through direct calls or Code Mode as permitted by the active tool mode and remaining restrictions.

Expose the setting in the app-server protocol, JSON schemas, and generated TypeScript and Python types.

## Testing

Add integration coverage for connector-specific exposure and MCP dispatch across tool modes, server restrictions, and direct-only namespaces. Extend config tests to cover populated, absent, and empty omission lists, and add a Code Mode request-history snapshot.

GitOrigin-RevId: cc99ab290c8a878d06d8d7ccf2d1dbd7c46bfa8a
2026-09-16 21:50:07 +00:00
rhan-oai a8c36ca6d2 Centralize model-message resolution and rendering in codex-prompts (#46026)
## What changed

- Add `ResolvedModelMessages` to resolve catalog text and bundled defaults while preserving explicit empty overrides and their source.
- Move base-instruction rendering, Guardian prompt composition, multi-agent role rendering, and `update_plan` guidance filtering into `codex-prompts`; migrate consumers to the shared APIs.
- Separate permission-profile resolution from prompt composition, and annotate Guardian policy and classifier instructions with content kinds.

## Testing

Add and update coverage for missing versus empty templates, literal overrides, multi-agent role composition, Guardian policy substitution and truncation, and preservation of permission path spellings and order.

GitOrigin-RevId: 52335bb7acec0f432d5c57acb2accd5f0276056e
2026-09-16 21:01:13 +00:00
jif 2fdcdeaf0e Add startup tool allowlists for threads (#45711)
## What changed

- Add `AllowedTools` to the extension API, captured once at thread startup to restrict which tools can be advertised or executed. An empty list disables all tools; an absent value preserves ordinary tool setup. Callers must supply the list again when resuming a thread.
- Filter tool registration and hosted tool specifications before Code Mode and discovery. Match names with their namespaces and require generated tools such as `exec` and `wait` to be explicitly allowed.
- Move Guardian reviewer tool selection into the allowlist while retaining feature and sandbox restrictions, with a fallback for older reviewer sessions.

## Testing

Add coverage for selected, empty, and absent allowlists across tool sources and Code Mode. Add managed-thread tests verifying advertised tools, rejection of excluded calls, and that replacing extension state after startup cannot change the captured allowlist.

GitOrigin-RevId: 33c1722c4241f368963d8385fa0415112e16a72d
2026-09-15 14:45:35 +00:00
alishobeiri-oai b979d4f1f0 Add a feature flag for asynchronous user messages (#45124)
## What changed

Add the disabled-by-default `send_message_to_user_async` feature flag so root agents can use the tool without model catalog support. Preserve catalog-based opt-in and keep the tool unavailable to subagents. Register the flag as under development and expose it in the configuration schema.

## Testing

Extend integration tests to cover feature and catalog opt-ins, deduplication when both are enabled, subagent exclusion, and the retired `send_async_message` flag. Check that either opt-in allows messages to be emitted without ending the turn.

GitOrigin-RevId: 3f53181ab074b0432c795550de73a9b1da7caf15
2026-09-12 22:28:41 +00:00
jif 3c837e568c Gate unified exec TTY support behind a feature flag (#42718)
## What changed

- Add the stable, default-on `unified_exec_tty` feature.
- When disabled, omit `tty` from the `exec_command` tool schema and reject calls that explicitly request a TTY.
- Continue to support commands that omit `tty` or set it to `false`.

## Testing

- Add unified exec coverage for the disabled tool schema, explicit TTY rejection, and non-TTY command execution.

GitOrigin-RevId: c5934fe9db1423170b891c7ecd0188792cd03f42
2026-09-04 10:22:43 +00:00
rka-oai d6350e24be Add free-form asynchronous user messages (#42354)
## What changed

- Add the `send_message_to_user_async` control tool for concise questions and updates during ongoing work.
- Emit messages as asynchronous agent items without ending the turn, and reject empty message text.
- Expose the tool only to root agents when the model catalog explicitly opts in, independently of `request_user_input_async`.

## Testing

- Cover catalog gating for root agents and subagents.
- Verify asynchronous item emission, tool output, empty-message validation, and continued turn execution.

GitOrigin-RevId: 8c6a7988a502f3dbc9eff7000913e85f0c596550
2026-09-02 20:41:14 +00:00
rka-oai 2c79ee6dac Add structured asynchronous user input requests (#42178)
## What changed

- Replace `send_user_message_async` with `request_user_input_async`, accepting one or more questions with optional suggested answers while allowing the turn to continue.
- Attach structured question metadata to asynchronous agent messages while retaining readable fallback text, and preserve it through app-server events, thread history, and generated schemas.
- Continue enabling the new tool for model catalogs that advertise either the old or new tool name.

## Testing

- Cover tool registration, question validation, emitted items, continued turn execution, history preservation, and backwards-compatible deserialization.

GitOrigin-RevId: ffc49aebde2e854c3c50a122aa52805fec3fc6b3
2026-09-02 02:09:35 +00:00
jif 2c8cfbf44f Keep history extension tools out of Guardian reviews (#41861)
## What changed

- Initialize Guardian reviewer subthreads with empty extension data.
- Remove the special registration that exposed inherited read-only `history`
  tools in the Guardian tool plan.

GitOrigin-RevId: 7700f033faab125d59d11bc2d82955c67689e3c3
2026-08-31 15:19:38 +00:00
rhan-oai 3c062df036 Source async user message descriptions from the model catalog (#41461)
## What changed

- Add model message metadata for built-in tool descriptions.
- Use the active step model's catalog description for `send_user_message_async`, including after a mid-turn model change.
- Fall back to the built-in description when catalog metadata is absent, while preserving an explicitly empty description.

## Testing

- Cover catalog serialization, fallback and empty-value behavior, and model changes within a turn.

GitOrigin-RevId: 72b953214ab9708931065321debf12133f8d2d40
2026-08-29 03:44:01 +00:00
jif b836aecd4d Preserve one-shot exec when unified exec is disabled (#41393)
## Why

Managed configuration can disable resumable unified execution while leaving shell tools enabled. This should not remove command execution entirely or grant access to retained processes.

## What changed

- Keep `exec_command` available in completion-only mode when `unified_exec` is disabled.
- Remove `tty`, `yield_time_ms`, `session_id`, and `write_stdin` from that mode, and add a `timeout_ms` argument.
- Terminate one-shot commands on timeout or turn cancellation, reporting timed-out commands with exit code 124.

## Testing

Added integration coverage for tool availability, timeout cleanup, and interruption cleanup under managed configuration.

GitOrigin-RevId: a382d34f922fdc4ba52889272c6db985abd42e47
2026-08-28 19:04:54 +00:00
iceweasel-oai 5ed294d49d Match Windows shell guidance to the executor platform (#41368)
## What changed

- Include Windows safety guidance in the `exec_command` tool description when a
  single ready environment reports Windows as its executor platform.
- Omit that guidance when the selected executor reports a non-Windows platform.
- Preserve the host-based behavior when platform information is unavailable or
  the tool can target multiple environments.

## Testing

- Cover Windows, non-Windows, unknown-platform, and multi-environment tool plans.
- Verify remote environments expose guidance that matches their target OS.

GitOrigin-RevId: 95e09790446c684ffaff2a0be077db426fff4618
2026-08-28 17:09:22 +00:00
rka-oai ec9620c231 Add configurable gating for the sleep tool (#41243)
## What changed

- Add a stable `sleep_tool` feature that can enable or disable registration of the built-in sleep tool independently of the clock tool.
- Support structured `features.sleep_tool` configuration with `model_driven` and `always_on` modes. The default `model_driven` mode preserves the existing model and `current_time_reminder` behavior, while `always_on` registers sleep whenever the feature is enabled.
- Preserve nested sleep-tool configuration across CLI overrides, config merges, and feature toggles, and expose the settings in the generated config schema.

## Testing

- Cover feature-map overrides, both selection modes, legacy clock settings, config merging and editing, and invalid mode rejection.

GitOrigin-RevId: 18eadc582f8a4445958c29d063e5be495276703e
2026-08-28 02:09:07 +00:00
rka-oai f6494dc8f5 Enable clock tools from model metadata (#41210)
## What changed

- Register both `clock.curr_time` and `clock.sleep` when a model lists `clock` in `experimental_supported_tools`.
- Keep current-time reminder injection controlled separately by the `current_time_reminder` feature.

## Testing

- Cover a model-advertised clock with reminders disabled, verifying that both tools are available and no reminder is added.

GitOrigin-RevId: c39b5cb6e2da397daaaa4e0ad81f0763b8dd91e9
2026-08-27 21:46:20 +00:00
Abhinav 0182ff3480 Finalize model-specific tool plans in ToolRouter (#41195)
## Why

Planning tools for a candidate model must not change the selected model or its
Responses Lite tool inventory. Otherwise, preparing a fallback can overwrite
metadata before the current model's request is sent.

## What changed

- Build tool registries and visible specs from an explicit `ModelInfo`.
- Store the finalized tool mode, code-mode names, namespace inventory, and
  terminal and child-management capabilities on `ToolRouter`.
- Publish namespace inventory only after selecting the step's router, and use
  that router's mode when dispatching and recording tool calls.

## Testing

Added coverage for candidate-model isolation, fallback compaction metadata,
code-mode worker selection, normalized tool names, and router capabilities.

GitOrigin-RevId: 56df2de8f42c7e93a4c4dcd117720e40a0cca3db
2026-08-27 20:01:39 +00:00
Adam Perry @ OpenAI 81e180044d Scope extension capabilities to invocation lifetimes (#41020)
## 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
2026-08-27 02:00:31 +00:00
jif 039eb58a0b Give Guardian reviewers read-only access to parent history (#40848)
## Why

Guardian approval reviews may need the original user instructions to decide
whether a command is authorized.

## What changed

- Forward the parent thread's `history.list_windows`, `history.list_items`,
  `history.read_item`, and `history.search_contents` executors to Guardian
  reviewer sessions.
- Keep other parent extension tools, including the `notes` namespace, isolated
  from Guardian reviewers.

## Testing

Add an app-server integration test that reads parent history during a Guardian
review and verifies that `notes` tools are not exposed.

GitOrigin-RevId: 65a90036577050adfa23b1d98f862233c994d9d7
2026-08-26 09:23:41 +00:00
joeflorencio-openai 68301fa45f Snapshot resolved settings for each model step (#40651)
## Why

Thread settings can change while a turn is running, and delegated review or
compaction steps can select a different model. Each request needs a consistent
set of settings resolved against the model that will execute it.

## What changed

- Capture immutable resolved settings for each model step, including model
  metadata, reasoning options, service tier, approvals, and personality.
- Keep in-flight steps on their captured settings while applying thread updates
  to subsequent work.
- Resolve inherited reasoning summaries and filter service tiers against the
  selected model and feature configuration for review and compaction steps.

## Testing

Added coverage for settings updates during paused turns, model changes,
previous-model compaction, review-model defaults, and service-tier filtering.

GitOrigin-RevId: fca4b3b305379f1bf26a5cac75ee0dd1747ac1f6
2026-08-25 17:41:22 +00:00
Won Park 8476434a97 Harden internal Guardian session isolation (#40497)
## Why

Internal Guardian reviews must remain independent of parent-session customization while still honoring managed execution and environment restrictions.

## What changed

- Apply the restricted Guardian session path to both internal and subagent review sources.
- Start internal reviews without inherited user instructions, extensions, MCP servers, or multi-agent behavior.
- Preserve managed execution policy and selected environment constraints while exposing only the allowed review tools. Honor shell feature restrictions across every selected environment and retain code mode when enabled.

## Testing

- Cover internal review isolation from parent state and managed instructions.
- Cover optional tool filtering, managed shell restrictions, code mode, and secondary environment profiles.

GitOrigin-RevId: edbf7d8a6fe3ee8213a1c75bc8ec331a1cf49006
2026-08-24 23:23:18 +00:00
jif bce5f2fcfc Standardize shell execution on unified exec (#39772)
## What changed

- Use `exec_command` and `write_stdin` as the shell tool surface.
- Treat legacy `default`, `local`, and `shell_command` model metadata as `unified_exec`.
- Remove obsolete shell-selection configuration and runtime paths while preserving the feature and policy gates for zsh fork execution.

GitOrigin-RevId: d743cbe598630d73052f1fecad680c4cde17977d
2026-08-20 18:29:35 +00:00
jif 8a40095ea3 Standardize shell execution on unified exec (#39757)
## What changed

- Remove the legacy `shell_command` handler and runtime, leaving `exec_command`
  and `write_stdin` as the shell execution tools.
- Treat legacy `shell_command` model metadata as `unified_exec`, and normalize
  legacy user opt-outs so they do not disable command execution. Managed feature
  requirements and `shell_tool` can still disable it.
- Preserve shell approvals, sandboxing, zsh-fork support, and output truncation
  through the unified execution path.

## Testing

- Cover legacy configuration and model-metadata compatibility.
- Exercise unified shell execution, approvals, truncation, and `apply_patch`
  serialization across the app-server and core test suites.

GitOrigin-RevId: 5c2fd6164fc3519cdae4944cb9db276b8467311c
2026-08-20 17:46:05 +00:00
rka-oai 198f42067a Keep async user messages on the direct tool surface (#39601)
## What changed

- Register `send_user_message_async` as `DirectModelOnly` so supported models can call it directly without exposing it through code mode.
- Exercise the async message flow with a code-mode-only model configuration and verify that the tool remains directly visible.

GitOrigin-RevId: ce22d5f63471ce90ac55ae2f3d0048f6cda57e01
2026-08-20 05:42:20 +00:00
rka-oai f5a3dc5540 Remove the feature gate for async user messages (#39452)
## What changed

- Expose `send_user_message_async` to root agents whenever the selected model advertises support for it.
- Retain `send_async_message` as a removed compatibility flag so existing configuration is accepted without controlling tool availability.
- Update the async message test to cover model-driven tool exposure without enabling the legacy flag.

GitOrigin-RevId: 558b427c2b203a057dd7c836e0ec702ae6134346
2026-08-19 09:01:23 +00:00
rka-oai 71dbf72b05 Add the async user message tool (#39319)
## What changed

- Add `send_user_message_async` for root agents when the async-message feature is enabled and the model advertises tool support.
- Emit the supplied text as an asynchronous agent message and immediately return an accepted result so the turn can continue.
- Keep the user-visible update out of the model's input context.

## Testing

- Add an integration test covering tool registration, item events, continued turn execution, and model context.

GitOrigin-RevId: 13d5168cb8cd6742db17bb74a15c910994e9c98b
2026-08-18 23:59:19 +00:00
sayan-oai 22bf16a37e Preserve environment configuration ownership (#38678)
## Why

Environment attachments can either inherit configuration from their thread or
provide their own. Later thread setting updates must refresh inherited
configuration without overwriting attachment-owned permissions and capability
roots.

## What changed

- Resolve each attachment's configuration when it is selected and retain
  whether it came from the thread or the attachment owner.
- Apply subsequent thread configuration updates only to thread-owned
  attachments, while preserving ownership across snapshots and child threads.
- Keep the resolved configuration with the environment selection so runtime
  consumers use a single canonical value.

## Testing

- Extend remote-environment coverage to verify that thread-owned permissions
  follow thread updates while owner-provided read-only permissions remain in
  effect.
- Cover configuration inheritance, attachment replacement, and owner-configured
  capability roots.

GitOrigin-RevId: fe70c4be5f151432b69bf4b141e316faa89036ae
2026-08-15 00:43:44 +00:00
jif a7e9fb5480 Constrain Guardian reviews to parent filesystem permissions (#38377)
## Why

Guardian review sessions must not gain access to paths that the parent turn is
not allowed to read.

## What changed

- Derive Guardian permissions by intersecting managed parent filesystem rules
  with read-only access, preserving denied paths and restricting network access.
- Offer Guardian execution tools only when a managed sandbox can enforce those
  rules.
- Include the selected environment IDs in the review-session reuse key so a
  session is not reused across different environment sets.

## Testing

Update the Guardian reuse integration test to verify that a review cannot read
a parent-denied file or write a local file while consecutive reviews still
reuse the same session.

GitOrigin-RevId: 20f17a6c379f1eda651e8508459d642a51e4ce94
2026-08-13 13:41:08 +00:00
rka-oai 8e4b10446e Remove the legacy code-mode tool metadata inventory (#37500)
## What changed

- Stop adding `code_mode_tool_names` to Responses Lite turn metadata.
- Keep `code_mode_tool_names` reserved so client metadata cannot reintroduce the removed, unbounded inventory.
- Use the opt-in `tool_namespaces_info` metadata, including each function's `code_mode_name`, when authoritative tool details are requested.

## Testing

- Update Responses Lite and code-mode tests to verify the opt-in namespace metadata and normalized code-mode names.

GitOrigin-RevId: cbfb9af984de71c7cc175d0cd47ae799a5275309
2026-08-07 20:26:08 +00:00
rka-oai 2b1811e562 Include tool namespace inventory in turn metadata (#37492)
## What changed

- Add opt-in `tool_namespaces_info` metadata for Responses Lite turns when
  `tool_registry.turn_metadata_includes_tool_info` is enabled.
- Describe each model-visible function's namespace, direct and deferred
  exposure, Code Mode name, and harness or MCP ownership.
- Reject visible namespaces shared by different owners when strict collision
  checking and tool inventory metadata are enabled.
- Keep tool inventories out of compatibility headers and metadata sent to MCP
  servers.

## Testing

- Cover opt-in behavior, MCP exposure details, namespace ownership collisions,
  reserved metadata handling, and Responses Lite request serialization.

GitOrigin-RevId: 6a6965d2ba98e29444fdfbb4ccec6aafcf0391e6
2026-08-07 19:32:15 +00:00
pakrym-oai d0c8f422ea Configure the default code-mode exec yield timeout (#37352)
## What changed

- Add `features.code_mode.default_exec_yield_time_ms`, defaulting to 30 seconds.
- Apply the configured default to code-mode `exec` calls that omit `yield_time_ms` and reflect it in the tool description.
- Remove the `code_mode_buffered_exec` compatibility feature flag.

## Testing

- Cover config loading and tool descriptions for both default and custom yield timeouts.

GitOrigin-RevId: 581ffc737b04721c7b5fc81260b1da1cf7d87523
2026-08-07 01:41:54 +00:00
jif 57f42a8113 Avoid cloning immutable metadata on tool search cache hits (#37279)
## Why

Checking the tool search cache currently rebuilds search metadata for every deferred tool, even when an immutable tool runtime has not changed.

## What changed

- Track immutable deferred tools by runtime identity and dynamic tools by their current search metadata.
- Rebuild the search handler when the deferred registry, dynamic metadata, or source-listing mode changes.
- Keep only weak references to immutable runtimes in the cache.

## Testing

Added unit coverage for immutable handler reuse, registry and exposure changes, source-listing changes, and refreshed dynamic tool metadata.

GitOrigin-RevId: 024c6f4498d431e7bbfaecde420f77fcf8c0dba7
2026-08-06 14:11:35 +00:00
jif e1831db7c3 Reuse MCP handlers across sampling steps (#37273)
## Why

MCP tool handlers and their Code Mode definitions are immutable for the lifetime
of a stable MCP binding, so rebuilding them for every sampling step repeats schema
construction unnecessarily.

## What changed

- Cache MCP handlers per session and reuse them while the same binding remains
  active, invalidating the cache when the binding changes.
- Lazily cache schema-free Code Mode definitions on MCP handlers while continuing
  to rebuild definitions for step-local tools whose specifications may change.
- Reapply current app enablement, tool policy, exposure, and plugin schema budgets
  whenever cached handlers are registered for a step.

## Testing

- Cover handler and Code Mode definition reuse, binding invalidation, changing app
  policy, stable continuation schemas, and step-local custom tool updates.

GitOrigin-RevId: 69c5011fb97c08580ac476e7fb2286b1e92e0359
2026-08-06 13:37:07 +00:00
Curtis 'Fjord' Hawthorne 0a0ebb8535 Add a unified image budget (#37206)
## What changed

- Add the gated `unified_image_budget` feature for models that support original image detail or Responses Lite.
- Apply one 6,000-pixel, 10,000-patch preprocessing limit regardless of legacy image detail hints.
- Hide detail controls from `view_image` and code mode while continuing to accept existing hints for compatibility.
- Preserve detail-based resizing and tool contracts for unsupported models.

## Testing

- Cover unified resizing limits, Responses Lite, legacy detail hints, unsupported models, and `view_image` integration in code mode.

GitOrigin-RevId: cb07bff1669a96599fdfd076b3d9ec80f2b6fff7
2026-08-06 03:15:08 +00:00
tongzhou wang 98da2c4499 Reserve the tool_search namespace for the search tool (#37188)
## What changed

- Remove namespace tools named `tool_search` before registering the built-in
  search tool, preventing them from sharing its model-visible surface.
- Record removed namespace tools as collisions so strict collision handling
  reports their qualified tool names.

## Testing

- Cover direct and deferred MCP tools that use the reserved namespace.
- Cover strict collision errors for both direct and deferred conflicts.

GitOrigin-RevId: 28fff918b4358a67b167467d92728fa545b951d7
2026-08-06 00:16:57 +00:00
rka-oai 3171166881 Reject conflicting namespace descriptions in strict tool mode (#37053)
## What changed

- Treat different non-empty descriptions for the same tool namespace as a
  collision when `error_on_tool_collisions` is enabled, including deferred
  tools.
- Continue allowing multiple tools to share a namespace when their descriptions
  match or are empty.
- Preserve the first non-empty namespace description when strict collision
  checking is disabled.

## Testing

- Cover strict collisions across direct and deferred tools, valid shared
  namespaces, relaxed description merging, and failure before model sampling.

GitOrigin-RevId: 788a2ae0eccb64c97995af7a208d9abb79edf2d0
2026-08-05 08:01:47 +00:00
jacobzhou-oai 56b82e676c Enforce Agent Plugin runtime boundaries (#37027)
## What changed

- Track Agent Plugin manifests through plugin, skill, and MCP loading so their capabilities use format-specific behavior without changing legacy plugins.
- Discover only direct-child skills, exclude app and hook capabilities, isolate MCP data, and reject MCP configuration files that are non-regular or resolve outside the plugin root.
- Bound model-visible skill instructions, plugin instructions, MCP descriptions, schemas, individual tools, and the aggregate Agent Plugin MCP tool set.
- Stop MCP and OAuth redirects when Agent Plugins send configured or authorization headers, while retaining existing redirect behavior for legacy MCP servers.

## Testing

- Add coverage for capability filtering, skill discovery, isolated MCP data and reserved-path expansion, unsafe MCP configuration files, context limits, and redirect handling.

GitOrigin-RevId: c9af66b051269f3226628ca280a58d32c808c38f
2026-08-05 04:54:33 +00:00
rka-oai f21dc46388 Canonicalize default tools under the functions namespace (#37022)
## What changed

- Group top-level function and custom tool definitions into a single `functions` namespace for Responses Lite providers that support namespaced tools.
- Normalize missing, empty, and explicit `functions` namespaces to the same tool identity across registration, routing, lifecycle hooks, configuration, and tool search.
- Keep default tool names unprefixed in code mode, display output, and dispatch traces while preserving explicit non-default namespaces.

## Testing

- Add coverage for Responses Lite serialization, tool search results, namespace normalization and collision handling, routing, lifecycle events, and code-mode namespace policies.

GitOrigin-RevId: d48414005b5d22d39b11a198e19c47814d3a19f2
2026-08-05 04:07:59 +00:00