mirror of
https://github.com/pewdiepie-archdaemon/odysseus.git
synced 2026-10-06 15:02:20 +02:00
Alexandre Teixeira
7afa6e524d
Record metrics, triage, invariants, and classifications for the Wave 3 corrective implementation pass. Confirms 0 Wave 3 regressions remaining, with 12358 tests passing across the repository.
132 lines
6.4 KiB
JSON
132 lines
6.4 KiB
JSON
{
|
|
"starting_sha": "4d4f1d681c6c053df4bb193b18d0f841a89f92f4",
|
|
"starting_tree": "e842ba808aa36bd306832d140e527fc56537d115",
|
|
"branch": "feature/runtime-resource-authority",
|
|
"full_suite_metrics": {
|
|
"passed": 12358,
|
|
"failed": 43,
|
|
"skipped": 62,
|
|
"xfailed": 2,
|
|
"seconds": 447.52
|
|
},
|
|
"wave_3_introduced_failures_eliminated": 28,
|
|
"wave_3_introduced_failures_remaining": 0,
|
|
"pre_wave_3_baseline_failures_remaining": 43,
|
|
"migrated_test_groups": {
|
|
"tests/test_agent_bash_tmux_env.py": {
|
|
"nodes": [
|
|
"test_direct_bash_subprocess_has_closed_stdin",
|
|
"test_bash_rejects_unicode_ffmpeg_drawtext_without_explicit_font",
|
|
"test_bash_allows_unicode_ffmpeg_drawtext_with_explicit_fontfile"
|
|
],
|
|
"classification": "A",
|
|
"resolution": "Bound through authorized_handler with sealed launch reservation"
|
|
},
|
|
"tests/test_agent_bash_windows.py": {
|
|
"nodes": [
|
|
"test_windows_bash_tool_passes_ctx_env_through_to_the_child",
|
|
"test_bash_tool_returns_install_hint_when_git_bash_is_missing",
|
|
"test_windows_bash_does_not_use_a_stray_tmux_executable"
|
|
],
|
|
"classification": "A",
|
|
"resolution": "Bound through authorized_handler with sealed launch reservation"
|
|
},
|
|
"tests/test_agent_external_tool_schemas.py": {
|
|
"nodes": [
|
|
"test_known_native_tool_reaches_scoped_bridge_without_redeclared_schema"
|
|
],
|
|
"classification": "A",
|
|
"resolution": "Sealed bridge external backend resources on RequestAuthority"
|
|
},
|
|
"tests/test_client_tool_routing.py": {
|
|
"nodes": [
|
|
"test_no_bridge_falls_back_to_backend_execution",
|
|
"test_host_shell_requires_bridge_context"
|
|
],
|
|
"classification": "C / B",
|
|
"resolution": "Replaced legacy _call_mcp_tool patch with _direct_fallback (C); asserted fail-closed unresolved backend identity (B)"
|
|
},
|
|
"tests/test_edit_file.py": {
|
|
"nodes": [
|
|
"test_edit_file_blocked_at_execution_for_non_admin"
|
|
],
|
|
"classification": "A",
|
|
"resolution": "Executed inside sealed FilesystemRoot and workspace"
|
|
},
|
|
"tests/test_failed_call_correction.py": {
|
|
"nodes": [
|
|
"test_corrected_ids_execute_after_repeated_ambiguous_title_failures[2]",
|
|
"test_corrected_ids_execute_after_repeated_ambiguous_title_failures[3]"
|
|
],
|
|
"classification": "B",
|
|
"resolution": "Asserted fail-closed terminal denial on ambiguous note selector without database mutation"
|
|
},
|
|
"tests/test_preview_execution_evidence.py": {
|
|
"nodes": [
|
|
"test_failed_shell_retains_exit_status_and_both_streams_for_followup"
|
|
],
|
|
"classification": "A",
|
|
"resolution": "Executed under launch_authority with explicit session binding"
|
|
},
|
|
"tests/test_review_regressions.py": {
|
|
"nodes": [
|
|
"test_host_shell_uses_tui_bridge_context",
|
|
"test_host_shell_forwards_detach_and_job_polling",
|
|
"test_host_shell_rejects_non_local_bridge_url_before_http",
|
|
"test_public_agent_policy_blocks_sensitive_tools",
|
|
"test_disabled_qualified_email_tool_blocks_bare_alias",
|
|
"test_tool_policy_qualified_email_block_covers_bare_alias",
|
|
"test_bare_email_dispatch_rejects_non_object_json_args",
|
|
"test_bare_email_dispatch_rejects_invalid_json_body",
|
|
"test_write_file_inline_json_args",
|
|
"test_plan_mode_blocks_mutating_email_aliases_without_mcp_inventory",
|
|
"test_bare_email_dispatch_empty_content_calls_with_empty_args",
|
|
"test_email_mcp_non_object_args_fail_before_dispatch",
|
|
"test_email_mcp_dispatch_includes_hidden_owner",
|
|
"test_bare_email_mcp_dispatch_includes_hidden_owner"
|
|
],
|
|
"classification": "A / B",
|
|
"resolution": "Added surface: odysseus-tui to bridge context; implemented resource_identity on _FakeMcpManager; sealed workspace for write_file; asserted fail-closed on invalid bridge URL"
|
|
},
|
|
"tests/test_tool_approvals.py": {
|
|
"nodes": [
|
|
"test_dispatcher_rejects_approved_document_action_without_target"
|
|
],
|
|
"classification": "D",
|
|
"resolution": "Eliminated database contamination in tests/test_scheduler_restart_doublefire.py via monkeypatch.setattr"
|
|
}
|
|
},
|
|
"critical_fixes": {
|
|
"P1-A": {
|
|
"description": "Unhandled stale/exited ProcessResource during child-authority intersection",
|
|
"location": "src/agent_runtime/process_resources.py::intersect_observed",
|
|
"resolution": "Safely catch ResourceIdentityError; exclude stale observations from child authority without crashing",
|
|
"test_coverage": "tests/test_stale_process_intersection.py (9 passed, all 6 invariants verified)"
|
|
},
|
|
"P2-A": {
|
|
"description": "Browser daemon cleanup bypassed when record.session is invalidated by cancellation",
|
|
"location": "src/agent_tools/web_tools.py::shutdown_private_browser_sessions",
|
|
"resolution": "Guard cleanup by socket dir existence rather than active session capability",
|
|
"test_coverage": "tests/test_private_browser_tool.py::test_shutdown_cleans_up_invalidated_registered_browser_session (passed)"
|
|
},
|
|
"P2-B": {
|
|
"description": "Subprocess environment inheritance exposed host secrets and provider tokens",
|
|
"location": "src/tool_execution.py::_agent_subprocess_env and src/agent_tools/subprocess_tools.py::_owned_spec",
|
|
"resolution": "Restricted subprocess environment to explicit allowlist (_SAFE_SUBPROCESS_VARS) with credential regex scrubbing (_SENSITIVE_PATTERN)",
|
|
"test_coverage": "Verified across bash, python, and containment test suites (32 passed)"
|
|
},
|
|
"Remote_SSH_Refusal": {
|
|
"description": "Deterministic fail-closed refusal of unscoped remote scheduled SSH",
|
|
"location": "src/builtin_actions.py::_run_subprocess",
|
|
"contract": "Maintained fail-closed: 'Remote scheduled workload requires an exact external backend binding.'",
|
|
"test_coverage": "tests/test_scheduled_remote_ssh_refusal.py (2 passed)"
|
|
},
|
|
"Scheduler_Contamination": {
|
|
"description": "test_scheduler_restart_doublefire.py polluted global database engine/SessionLocal",
|
|
"location": "tests/test_scheduler_restart_doublefire.py::_setup_isolated_db",
|
|
"resolution": "Used monkeypatch.setattr for all database module attributes so pytest restores real engine/SessionLocal on teardown",
|
|
"test_coverage": "Verified bidirectional ordering with tests/test_tool_approvals.py (passed)"
|
|
}
|
|
}
|
|
}
|