openai/codex
1
0
Fork 0
mirror of https://github.com/openai/codex.git synced 2026-11-08 20:40:33 +00:00
Code Issues Packages Projects Releases Wiki Activity
Files
df38cb3b2af40dd413d0af7f000fe5cb3f077aad
codex/codex-rs/core/tests/suite/snapshots
T
History
swastik-oai 3934ae926a Support direct Guardian review of recorded MCP calls (#59735) 
## What changed

Extend `guardian_review` to assess recorded MCP tool calls using the current tool catalog, bindings, and approval policy without executing the call or remembering an approval. Return no assessment when policy or a remembered approval skips review, and reject tools blocked by app configuration.

## Testing

Add a scenario test that compares direct and live MCP review inputs, verifies that neither dispatches the tool, and checks that the current app approval policy can skip review.

GitOrigin-RevId: 05746dd0804a0f96d7946468701d5222171ff64f
2026-11-05 20:55:46 +00:00
..
all__suite__additional_context__additional_context_simple_input.snap
Enable deferred tool world state by default (#58410)
2026-10-30 18:33:14 +00:00
all__suite__compact__compaction_cold_resume_after_completion.snap
Preserve running turn recovery across thread settings updates (#53879)
2026-10-14 06:03:02 +00:00
all__suite__compact__manual_compact_with_history_shapes.snap
Preserve pending agent messages across compaction (#59404)
2026-11-04 13:03:01 +00:00
all__suite__compact__manual_compact_without_prev_user_shapes.snap
Enable deferred tool world state by default (#58410)
2026-10-30 18:33:14 +00:00
all__suite__compact__mid_turn_compaction_shapes.snap
Enable deferred tool world state by default (#58410)
2026-10-30 18:33:14 +00:00
all__suite__compact__pre_sampling_model_switch_compaction_shapes.snap
Enable deferred tool world state by default (#58410)
2026-10-30 18:33:14 +00:00
all__suite__compact__pre_turn_compaction_context_window_exceeded_shapes.snap
Enable deferred tool world state by default (#58410)
2026-10-30 18:33:14 +00:00
all__suite__compact__pre_turn_compaction_including_incoming_shapes.snap
Enable deferred tool world state by default (#58410)
2026-10-30 18:33:14 +00:00
all__suite__compact__pre_turn_compaction_strips_incoming_model_switch_shapes.snap
Enable deferred tool world state by default (#58410)
2026-10-30 18:33:14 +00:00
all__suite__executor_discovery_v2__plugin_acceptance_auth_refresh.snap
Enable deferred tool world state by default (#58410)
2026-10-30 18:33:14 +00:00
all__suite__gcp__gcp_model_picker.snap
Add GPT-6.1 Terra to model catalogs (#57293)
2026-10-26 22:13:14 +00:00
all__suite__mcp_tool_exposure__deferred_tools_initial_unchanged_and_removed.snap
Send base instructions as Responses input messages (#51156)
2026-10-05 18:52:51 +00:00
all__suite__mcp_tool_exposure__deferred_tools_recover_during_sampling.snap
Send base instructions as Responses input messages (#51156)
2026-10-05 18:52:51 +00:00
all__suite__mcp_tool_exposure__deferred_tools_resume_without_duplicate_update.snap
Send base instructions as Responses input messages (#51156)
2026-10-05 18:52:51 +00:00
all__suite__model_provider_requirements__provider_selection_override_warning.snap
Enforce managed model provider selection and definitions (#44650)
2026-09-10 21:41:39 +00:00
all__suite__model_visible_layout__model_visible_layout_cwd_change_refreshes_agents.snap
Enable deferred tool world state by default (#58410)
2026-10-30 18:33:14 +00:00
all__suite__model_visible_layout__model_visible_layout_environment_context_includes_one_subagent.snap
Make context snapshot text rendering consistent (#44976)
2026-09-12 05:04:11 +00:00
all__suite__model_visible_layout__model_visible_layout_environment_context_includes_two_subagents.snap
Make context snapshot text rendering consistent (#44976)
2026-09-12 05:04:11 +00:00
all__suite__model_visible_layout__model_visible_layout_resume_override_matches_rollout_model.snap
Send base instructions as Responses input messages (#51156)
2026-10-05 18:52:51 +00:00
all__suite__model_visible_layout__model_visible_layout_resume_with_personality_change.snap
Enable deferred tool world state by default (#58410)
2026-10-30 18:33:14 +00:00
all__suite__model_visible_layout__model_visible_layout_turn_overrides.snap
Enable deferred tool world state by default (#58410)
2026-10-30 18:33:14 +00:00
all__suite__pending_input__pending_input_queued_mail_after_commentary.snap
Send base instructions as Responses input messages (#51156)
2026-10-05 18:52:51 +00:00
all__suite__pending_input__pending_input_queued_mail_after_reasoning.snap
Send base instructions as Responses input messages (#51156)
2026-10-05 18:52:51 +00:00
all__suite__pending_input__pending_input_user_input_no_preempt_after_reasoning.snap
Send base instructions as Responses input messages (#51156)
2026-10-05 18:52:51 +00:00
all__suite__realtime_conversation__conversation_startup_context_current_thread_selects_many_turns_by_budget.snap
Budget realtime current thread context (#17519)
2026-04-12 11:59:09 -07:00
all__suite__request_plugin_install__catalog_plugin_recommendations_absent.snap
Enable unified image budgeting by default (#59282)
2026-11-04 01:24:36 +00:00
all__suite__request_plugin_install__catalog_plugin_recommendations_blank.snap
Enable unified image budgeting by default (#59282)
2026-11-04 01:24:36 +00:00
all__suite__request_plugin_install__catalog_plugin_recommendations_custom.snap
Enable unified image budgeting by default (#59282)
2026-11-04 01:24:36 +00:00
all__suite__request_plugin_install__catalog_plugin_recommendations_disabled.snap
Enable unified image budgeting by default (#59282)
2026-11-04 01:24:36 +00:00
all__suite__request_plugin_install__catalog_plugin_recommendations_empty.snap
Enable unified image budgeting by default (#59282)
2026-11-04 01:24:36 +00:00
all__suite__request_plugin_install__catalog_plugin_recommendations_null.snap
Enable unified image budgeting by default (#59282)
2026-11-04 01:24:36 +00:00
all__suite__request_plugin_install__catalog_plugin_recommendations_oversized.snap
Enable unified image budgeting by default (#59282)
2026-11-04 01:24:36 +00:00
all__suite__request_plugin_install__startup_recommendations_developer_context.snap
Send base instructions as Responses input messages (#51156)
2026-10-05 18:52:51 +00:00
all__suite__scenarios__additional_context_legacy_messages.snap
Enable deferred tool world state by default (#58410)
2026-10-30 18:33:14 +00:00
all__suite__scenarios__additional_context_tool_outputs.snap
Enable deferred tool world state by default (#58410)
2026-10-30 18:33:14 +00:00
all__suite__scenarios__admitted_prompt_id_reaches_responses.snap
Enable deferred tool world state by default (#58410)
2026-10-30 18:33:14 +00:00
all__suite__scenarios__agent_eviction__idle_eviction_followup.snap
Enable unified image budgeting by default (#59282)
2026-11-04 01:24:36 +00:00
all__suite__scenarios__agent_message_board__agent_message_board_context.snap
Add optional descriptions to agent message board channels (#52183)
2026-10-08 17:25:39 +00:00
all__suite__scenarios__agent_message_board__board_connections.snap
Route message-board notifications through agent mailboxes (#59139)
2026-11-03 12:33:26 +00:00
all__suite__scenarios__agent_message_board__http__agent_message_board_mcp_context.snap
Add a standalone HTTP MCP server for the agent message board (#58904)
2026-11-02 15:09:22 +00:00
all__suite__scenarios__agent_message_board__http__agent_message_board_mcp_feature_context.snap
Route message-board notifications through agent mailboxes (#59139)
2026-11-03 12:33:26 +00:00
all__suite__scenarios__agent_message_board__http__agent_message_board_plugin_context.snap
Package the message board MCP connection as a plugin (#58908)
2026-11-02 15:28:37 +00:00
all__suite__scenarios__agent_message_board__remote__remote_board_notification.snap
Deliver remote message board notifications to active turns (#49686)
2026-09-30 17:33:59 +00:00
all__suite__scenarios__agent_message_board__remote__remote_board_permissions_direct.snap
Enable unified image budgeting by default (#59282)
2026-11-04 01:24:36 +00:00
all__suite__scenarios__agent_message_board__remote__remote_board_tools.snap
Remove partial-history subagent forks (#51329)
2026-10-06 10:39:16 +00:00
all__suite__scenarios__app_tool_exposure_CodeModeOnly.snap
Enable unified image budgeting by default (#59282)
2026-11-04 01:24:36 +00:00
all__suite__scenarios__astra_active_environment_selection.snap
Enable unified image budgeting by default (#59282)
2026-11-04 01:24:36 +00:00
all__suite__scenarios__astra_async_compaction_with_live_suffix.snap
Enable unified image budgeting by default (#59282)
2026-11-04 01:24:36 +00:00
all__suite__scenarios__astra_async_question_and_answer.snap
Enable unified image budgeting by default (#59282)
2026-11-04 01:24:36 +00:00
all__suite__scenarios__astra_code_mode_call_timing.snap
Enable unified image budgeting by default (#59282)
2026-11-04 01:24:36 +00:00
all__suite__scenarios__astra_disabled_executor_skills.snap
Enable unified image budgeting by default (#59282)
2026-11-04 01:24:36 +00:00
all__suite__scenarios__astra_executor_plugin_policy_refresh.snap
Enable unified image budgeting by default (#59282)
2026-11-04 01:24:36 +00:00
all__suite__scenarios__astra_input_interrupts_response.snap
Enable unified image budgeting by default (#59282)
2026-11-04 01:24:36 +00:00
all__suite__scenarios__astra_input_yields_code_mode_cell.snap
Enable unified image budgeting by default (#59282)
2026-11-04 01:24:36 +00:00
all__suite__scenarios__astra_kickoff_remote_compaction_windows.snap
Enable unified image budgeting by default (#59282)
2026-11-04 01:24:36 +00:00
all__suite__scenarios__astra_plugin_policy_limits_visible_skills.snap
Enable unified image budgeting by default (#59282)
2026-11-04 01:24:36 +00:00
all__suite__scenarios__astra_plugin_policy_without_skill_descriptions.snap
Enable unified image budgeting by default (#59282)
2026-11-04 01:24:36 +00:00
all__suite__scenarios__astra_plugin_refresh_simplified_selection_hints_off.snap
Enable unified image budgeting by default (#59282)
2026-11-04 01:24:36 +00:00
all__suite__scenarios__astra_plugin_refresh_simplified_selection_hints_on.snap
Enable unified image budgeting by default (#59282)
2026-11-04 01:24:36 +00:00
all__suite__scenarios__astra_settings_release_check_tool_shapes.snap
Enable unified image budgeting by default (#59282)
2026-11-04 01:24:36 +00:00
all__suite__scenarios__audio_file__measured_audio_compaction_and_cold_resume.snap
Use measured durations to budget uploaded audio (#59268)
2026-11-04 00:19:12 +00:00
all__suite__scenarios__audio_file__rejected_uploaded_audio_follow_up_and_resume.snap
Enable uploaded audio with durable rejection recovery (#59234)
2026-11-03 21:24:16 +00:00
all__suite__scenarios__audio_file__unsupported_steered_audio_follow_up_and_resume.snap
Add audio file references with explicit runtime rejection (#58430)
2026-10-30 20:53:25 +00:00
all__suite__scenarios__audio_file__uploaded_audio_compaction_and_cold_resume.snap
Enable uploaded audio with durable rejection recovery (#59234)
2026-11-03 21:24:16 +00:00
all__suite__scenarios__audio_file__uploaded_audio_survives_follow_up.snap
Enable uploaded audio with durable rejection recovery (#59234)
2026-11-03 21:24:16 +00:00
all__suite__scenarios__budget_context__host_budget_context_after_compaction.snap
Render host-owned V2 subagent rosters in environment context (#59531)
2026-11-05 00:39:39 +00:00
all__suite__scenarios__catalog_approval_instructions__catalog_approval_headings_follow_selected_model.snap
Allow model catalogs to customize approval instruction headings (#57581)
2026-10-27 22:26:12 +00:00
all__suite__scenarios__catalog_denied_reads_follow_selected_model.snap
Support model-catalog wording for permission path warnings (#57263)
2026-10-26 21:20:52 +00:00
all__suite__scenarios__catalog_plugin_guidance_follows_model_and_survives_resume.snap
Enable unified image budgeting by default (#59282)
2026-11-04 01:24:36 +00:00
all__suite__scenarios__catalog_selected_plugin_omission_bounds_runtime_capabilities.snap
Enable unified image budgeting by default (#59282)
2026-11-04 01:24:36 +00:00
all__suite__scenarios__catalog_selected_plugin_wording_apps_false_simplified_false.snap
Enable unified image budgeting by default (#59282)
2026-11-04 01:24:36 +00:00
all__suite__scenarios__catalog_selected_plugin_wording_apps_true_simplified_false.snap
Enable unified image budgeting by default (#59282)
2026-11-04 01:24:36 +00:00
all__suite__scenarios__catalog_selected_plugin_wording_apps_true_simplified_true.snap
Enable unified image budgeting by default (#59282)
2026-11-04 01:24:36 +00:00
all__suite__scenarios__catalog_writable_roots_follow_selected_model.snap
Support model-catalog wording for permission path warnings (#57263)
2026-10-26 21:20:52 +00:00
all__suite__scenarios__child_completion_wakes_parent_after_final_answer.snap
Enable unified image budgeting by default (#59282)
2026-11-04 01:24:36 +00:00
all__suite__scenarios__code_mode_catalog_messages_ranked_search.snap
Enable unified image budgeting by default (#59282)
2026-11-04 01:24:36 +00:00
all__suite__scenarios__code_mode_catalog_messages.snap
Enable unified image budgeting by default (#59282)
2026-11-04 01:24:36 +00:00
all__suite__scenarios__code_mode_mcp_schema_limits.snap
Enable unified image budgeting by default (#59282)
2026-11-04 01:24:36 +00:00
all__suite__scenarios__code_mode_settled_helpers__code_mode_settled_helpers.snap
Enable unified image budgeting by default (#59282)
2026-11-04 01:24:36 +00:00
all__suite__scenarios__command_sessions__command_sessions_world_state.snap
Expose retained command sessions in incremental world state (#59633)
2026-11-05 11:14:26 +00:00
all__suite__scenarios__compaction__remote_slash_compact.snap
Preserve pending agent messages across compaction (#59404)
2026-11-04 13:03:01 +00:00
all__suite__scenarios__content_filter__content_filter_guidance.snap
Enable deferred tool world state by default (#58410)
2026-10-30 18:33:14 +00:00
all__suite__scenarios__context_management_tools__catalog_context_tool_definitions_follow_captured_models.snap
Enable unified image budgeting by default (#59282)
2026-11-04 01:24:36 +00:00
all__suite__scenarios__credential_masking__remote_credential_masking_zsh.snap
Enable deferred tool world state by default (#58410)
2026-10-30 18:33:14 +00:00
all__suite__scenarios__credential_masking__remote_credential_masking.snap
Enable deferred tool world state by default (#58410)
2026-10-30 18:33:14 +00:00
all__suite__scenarios__dynamic_tools__dynamic_tools_update_preserves_pending_calls_and_survives_resume.snap
Enable unified image budgeting by default (#59282)
2026-11-04 01:24:36 +00:00
all__suite__scenarios__frozen_cloud_skills__frozen_cloud_skills_with_named_executor_request_history.snap
Enable unified image budgeting by default (#59282)
2026-11-04 01:24:36 +00:00
all__suite__scenarios__gif_generation_preserves_animation_and_replays_a_still_preview.snap
Enable unified image budgeting by default (#59282)
2026-11-04 01:24:36 +00:00
all__suite__scenarios__guardian_agent_messages__encrypted_native_history_custom_namespace.snap
Enable unified image budgeting by default (#59282)
2026-11-04 01:24:36 +00:00
all__suite__scenarios__guardian_agent_messages__encrypted_native_history_default_namespace.snap
Enable unified image budgeting by default (#59282)
2026-11-04 01:24:36 +00:00
all__suite__scenarios__guardian_agent_messages__encrypted_parent_reply_survives_incremental_guardian_reviews.snap
Enable unified image budgeting by default (#59282)
2026-11-04 01:24:36 +00:00
all__suite__scenarios__guardian_checkpoint_migration.snap
Enable unified image budgeting by default (#59282)
2026-11-04 01:24:36 +00:00
all__suite__scenarios__guardian_code_mode_messaging.snap
Enable unified image budgeting by default (#59282)
2026-11-04 01:24:36 +00:00
all__suite__scenarios__guardian_direct_mcp__guardian_direct_mcp.snap
Support direct Guardian review of recorded MCP calls (#59735)
2026-11-05 20:55:46 +00:00
all__suite__scenarios__guardian_direct_review__guardian_direct_exec_patch.snap
Enable unified image budgeting by default (#59282)
2026-11-04 01:24:36 +00:00
all__suite__scenarios__guardian_direct_review__guardian_direct_exec.snap
Enable unified image budgeting by default (#59282)
2026-11-04 01:24:36 +00:00
all__suite__scenarios__guardian_direct_review__guardian_direct_patch.snap
Enable unified image budgeting by default (#59282)
2026-11-04 01:24:36 +00:00
all__suite__scenarios__guardian_direct_review__guardian_direct_permissions.snap
Enable unified image budgeting by default (#59282)
2026-11-04 01:24:36 +00:00
all__suite__scenarios__guardian_direct_review__guardian_direct_pre_tool_use_rewrite.snap
Enable unified image budgeting by default (#59282)
2026-11-04 01:24:36 +00:00
all__suite__scenarios__guardian_elastic_budgeting.snap
Add opt-in elastic budgeting for synchronous Guardian reviews (#59444)
2026-11-04 16:33:22 +00:00
all__suite__scenarios__guardian_extra_policy__extra_policy_reaches_guardian_review.snap
Enable unified image budgeting by default (#59282)
2026-11-04 01:24:36 +00:00
all__suite__scenarios__guardian_handoff__guardian_handoff_delegation_native.snap
Enable unified image budgeting by default (#59282)
2026-11-04 01:24:36 +00:00
all__suite__scenarios__guardian_handoff__guardian_handoff_delegation.snap
Enable unified image budgeting by default (#59282)
2026-11-04 01:24:36 +00:00
all__suite__scenarios__guardian_heartbeat__heartbeat_repetitions_keep_later_human_authorization.snap
Enable unified image budgeting by default (#59282)
2026-11-04 01:24:36 +00:00
all__suite__scenarios__guardian_orchestrator_connector__host_owned_orchestrator_connector_request_history.snap
Enable deferred tool world state by default (#58410)
2026-10-30 18:33:14 +00:00
all__suite__scenarios__guardian_reconsideration__guardian_denial_reconsideration.snap
Resample Guardian denials with the original request (#59659)
2026-11-05 13:38:12 +00:00
all__suite__scenarios__guardian_sender_context__cross_host_sender_context.snap
Enable unified image budgeting by default (#59282)
2026-11-04 01:24:36 +00:00
all__suite__scenarios__host_turn_admission__retained_input_after_admission.snap
Add host-owned turn admission to the agent runtime (#58963)
2026-11-02 20:10:37 +00:00
all__suite__scenarios__incremental_tools__incremental_tool_removals.snap
Enable unified image budgeting by default (#59282)
2026-11-04 01:24:36 +00:00
all__suite__scenarios__incremental_tools__incremental_tools_catalog_messages.snap
Enable unified image budgeting by default (#59282)
2026-11-04 01:24:36 +00:00
all__suite__scenarios__incremental_tools__incremental_tools_responses_api.snap
Enable unified image budgeting by default (#59282)
2026-11-04 01:24:36 +00:00
all__suite__scenarios__incremental_tools__incremental_tools_suppressed_announcements.snap
Enable unified image budgeting by default (#59282)
2026-11-04 01:24:36 +00:00
all__suite__scenarios__incremental_tools__incremental_tools.snap
Enable unified image budgeting by default (#59282)
2026-11-04 01:24:36 +00:00
all__suite__scenarios__incremental_tools__prediction_fork_inherited_tools.snap
Enable unified image budgeting by default (#59282)
2026-11-04 01:24:36 +00:00
all__suite__scenarios__incremental_tools_resume__disable_incremental_tools.snap
Enable unified image budgeting by default (#59282)
2026-11-04 01:24:36 +00:00
all__suite__scenarios__incremental_tools_resume__legacy_resume_remote_compaction.snap
Enable unified image budgeting by default (#59282)
2026-11-04 01:24:36 +00:00
all__suite__scenarios__incremental_tools_resume__legacy_resume_window_reset.snap
Enable unified image budgeting by default (#59282)
2026-11-04 01:24:36 +00:00
all__suite__scenarios__indirect_namespace_prefixes__catalog_indirect_namespace_prefixes.snap
Enable unified image budgeting by default (#59282)
2026-11-04 01:24:36 +00:00
all__suite__scenarios__injected_agent_mail__injected_agent_message_interrupting_sampling_survives_mid_turn_compaction.snap
Preserve pending agent messages across compaction (#59404)
2026-11-04 13:03:01 +00:00
all__suite__scenarios__injected_agent_mail__injected_mail_respects_delivery_boundaries.snap
Respect delivery boundaries for injected agent messages (#58988)
2026-11-02 21:35:56 +00:00
all__suite__scenarios__mailbox_preemption__mailbox_preemption_commentary_deferred_false.snap
Send base instructions as Responses input messages (#51156)
2026-10-05 18:52:51 +00:00
all__suite__scenarios__mailbox_preemption__mailbox_preemption_commentary_deferred_true.snap
Send base instructions as Responses input messages (#51156)
2026-10-05 18:52:51 +00:00
all__suite__scenarios__mailbox_preemption__mailbox_preemption_partial_answer_deferred_false.snap
Handle partial answers consistently across agent workflows (#51249)
2026-10-06 03:27:04 +00:00
all__suite__scenarios__mailbox_preemption__mailbox_preemption_partial_answer_deferred_true.snap
Handle partial answers consistently across agent workflows (#51249)
2026-10-06 03:27:04 +00:00
all__suite__scenarios__mailbox_preemption__mailbox_preemption_reasoning_deferred_false.snap
Send base instructions as Responses input messages (#51156)
2026-10-05 18:52:51 +00:00
all__suite__scenarios__mailbox_preemption__mailbox_preemption_reasoning_deferred_true.snap
Send base instructions as Responses input messages (#51156)
2026-10-05 18:52:51 +00:00
all__suite__scenarios__managed_human_approval__managed_checkpoint_requires_fresh_human_decisions.snap
Enable deferred tool world state by default (#58410)
2026-10-30 18:33:14 +00:00
all__suite__scenarios__mcp_ema__enterprise_failure_preserves_ordinary_mcp_history.snap
Enable unified image budgeting by default (#59282)
2026-11-04 01:24:36 +00:00
all__suite__scenarios__mcp_ema__enterprise_revocation_preserves_history_and_ordinary_tools.snap
Enable unified image budgeting by default (#59282)
2026-11-04 01:24:36 +00:00
all__suite__scenarios__mcp_ema__enterprise_sign_in_required.snap
Fix enterprise MCP credential selection and reauthentication (#55859)
2026-10-21 10:40:59 +00:00
all__suite__scenarios__mcp_resource_messages__mcp_resource_messages.snap
Enable unified image budgeting by default (#59282)
2026-11-04 01:24:36 +00:00
all__suite__scenarios__mcp_sharing__shared_mcp_keeps_tools_and_model_requested_input_per_chat.snap
Enable unified image budgeting by default (#59282)
2026-11-04 01:24:36 +00:00
all__suite__scenarios__mcp_tool_discovery_CodeModeOnly.snap
Enable unified image budgeting by default (#59282)
2026-11-04 01:24:36 +00:00
all__suite__scenarios__mcp_tool_discovery_Direct.snap
Enable unified image budgeting by default (#59282)
2026-11-04 01:24:36 +00:00
all__suite__scenarios__model_catalog_refresh_preserves_tools_and_history.snap
Send base instructions as Responses input messages (#51156)
2026-10-05 18:52:51 +00:00
all__suite__scenarios__model_instructions__incremental_model_instructions.snap
Refresh model instructions in incremental-tool context windows (#53872)
2026-10-14 05:36:44 +00:00
all__suite__scenarios__model_instructions__originator_catalog_instructions_and_tools.snap
Scope model catalogs and caches by thread originator (#56284)
2026-10-22 22:44:48 +00:00
all__suite__scenarios__multi_agent_catalog_parameters.snap
Enable unified image budgeting by default (#59282)
2026-11-04 01:24:36 +00:00
all__suite__scenarios__multi_agent_native_tools_hidden.snap
Omit native multi-agent guidance when native tools are disabled (#59732)
2026-11-05 20:43:36 +00:00
all__suite__scenarios__mxc__preferred_mxc_permissions.snap
Enable deferred tool world state by default (#58410)
2026-10-30 18:33:14 +00:00
all__suite__scenarios__partial_answers__partial_answer_continuation.snap
Enable deferred tool world state by default (#58410)
2026-10-30 18:33:14 +00:00
all__suite__scenarios__partial_answers__partial_answer_fork.snap
Update collaboration snapshots for full-history fork instructions (#51335)
2026-10-06 10:56:45 +00:00
all__suite__scenarios__partial_answers__preserved_answer_fork.snap
Enable unified image budgeting by default (#59282)
2026-11-04 01:24:36 +00:00
all__suite__scenarios__prediction_fork_inherits_parent_context.snap
Enable unified image budgeting by default (#59282)
2026-11-04 01:24:36 +00:00
all__suite__scenarios__prediction_fork_preserves_context_above_compaction_threshold.snap
Enable unified image budgeting by default (#59282)
2026-11-04 01:24:36 +00:00
all__suite__scenarios__provider_capabilities__custom_provider_capabilities.snap
Enable unified image budgeting by default (#59282)
2026-11-04 01:24:36 +00:00
all__suite__scenarios__realtime_attachment_replacement.snap
Enable deferred tool world state by default (#58410)
2026-10-30 18:33:14 +00:00
all__suite__scenarios__retained_tool_outputs__retained_tool_output_retention_disabled.snap
Enable unified image budgeting by default (#59282)
2026-11-04 01:24:36 +00:00
all__suite__scenarios__retained_tool_outputs__retained_tool_output_survives_compaction_and_resume.snap
Enable unified image budgeting by default (#59282)
2026-11-04 01:24:36 +00:00
all__suite__scenarios__shared_instructions__shared_instructions_update_running_descendants.snap
Add audio file references with explicit runtime rejection (#58430)
2026-10-30 20:53:25 +00:00
all__suite__scenarios__skill_catalog_dedup__dedup_before_budgeting.snap
Enable unified image budgeting by default (#59282)
2026-11-04 01:24:36 +00:00
all__suite__scenarios__skill_catalog_dedup__dedup_without_descriptions.snap
Enable unified image budgeting by default (#59282)
2026-11-04 01:24:36 +00:00
all__suite__scenarios__skill_catalog_dedup__repository_skill_turn_grant.snap
Stabilize cross-platform tests and directory-change fork permissions (#59369)
2026-11-04 09:51:28 +00:00
all__suite__scenarios__skill_catalog_dedup__skill_catalog_deltas.snap
Enable unified image budgeting by default (#59282)
2026-11-04 01:24:36 +00:00
all__suite__scenarios__skill_read_installation_recovery_request_history.snap
Enable unified image budgeting by default (#59282)
2026-11-04 01:24:36 +00:00
all__suite__scenarios__strict_3p_cache__strict_3p_mcp_catalog_cache.snap
Enforce strict third-party tool deferral in Code Mode Only (#59071)
2026-11-03 06:05:55 +00:00
all__suite__scenarios__subagent_browser_auth.snap
Enable unified image budgeting by default (#59282)
2026-11-04 01:24:36 +00:00
all__suite__scenarios__subagent_inherits_pending_environment_windows.snap
Send base instructions as Responses input messages (#51156)
2026-10-05 18:52:51 +00:00
all__suite__scenarios__subagent_inherits_pending_environment.snap
Send base instructions as Responses input messages (#51156)
2026-10-05 18:52:51 +00:00
all__suite__scenarios__tools_namespace_budget__names_before_descriptions.snap
Send base instructions as Responses input messages (#51156)
2026-10-05 18:52:51 +00:00
all__suite__scenarios__turn_input_agent_message__agent_followup_AfterFinalAnswer.snap
Accept agent follow-ups through native turn input delivery (#58829)
2026-11-02 07:27:49 +00:00
all__suite__scenarios__turn_input_agent_message__agent_followup_BeforeFinalAnswer.snap
Accept agent follow-ups through native turn input delivery (#58829)
2026-11-02 07:27:49 +00:00
all__suite__scenarios__unavailable_images_are_rechecked_without_rewriting_history.snap
Enable unified image budgeting by default (#59282)
2026-11-04 01:24:36 +00:00
all__suite__scenarios__unshared_apps_catalog_across_turns.snap
Enable unified image budgeting by default (#59282)
2026-11-04 01:24:36 +00:00
all__suite__scenarios__web_search__literature_search_and_open.snap
Enable unified image budgeting by default (#59282)
2026-11-04 01:24:36 +00:00
all__suite__scenarios__web_search__literature_search_web_run_schema.snap
Add model-gated literature search to standalone web search (#57542)
2026-10-27 19:11:56 +00:00
all__suite__scenarios__web_search__model_selected_search_preserves_discovery_and_call_history.snap
Enable unified image budgeting by default (#59282)
2026-11-04 01:24:36 +00:00
all__suite__scenarios__world_state_prefix__extension_window_prefix_local.snap
Enable unified image budgeting by default (#59282)
2026-11-04 01:24:36 +00:00
all__suite__scenarios__world_state_prefix__extension_window_prefix_remote.snap
Enable unified image budgeting by default (#59282)
2026-11-04 01:24:36 +00:00
all__suite__skills_extension__cloud_skills_across_executor_readiness_windows.snap
Enable unified image budgeting by default (#59282)
2026-11-04 01:24:36 +00:00
all__suite__skills_extension__cloud_skills_across_executor_readiness.snap
Enable unified image budgeting by default (#59282)
2026-11-04 01:24:36 +00:00
all__suite__token_budget__token_budget_new_context_window_tool_full_context.snap
Enable deferred tool world state by default (#58410)
2026-10-30 18:33:14 +00:00
all__suite__unified_exec__exec_command_tty_disabled.snap
Gate unified exec TTY support behind a feature flag (#42718)
2026-09-04 10:22:43 +00:00