feat(runtime): bind browser resources to authority

docs/runtime-decomposition/validation/wave-3-browser-final-results.json

@@ -0,0 +1,136 @@
+{
+  "starting_sha": "bc5e1ee6922000a290371f8c2aa18802a03ffcad",
+  "starting_tree": "8e09cc2560f50a3472e06ec614d6ada028b7eb18",
+  "resource_focused": {
+    "passed": 1425
+  },
+  "integrated": {
+    "files": 149,
+    "passed": 3776,
+    "skipped": 7,
+    "xfailed": 2
+  },
+  "index_schema_config_focused": {
+    "passed": 40
+  },
+  "release_docker_live": {
+    "passed": 4,
+    "version": "0.35.0",
+    "architecture": "linux-x64",
+    "page_execution_enabled": false,
+    "pin_contract_proven": false
+  },
+  "full": {
+    "passed": 12310,
+    "failed": 76,
+    "skipped": 65,
+    "xfailed": 2,
+    "subtests_passed": 6,
+    "seconds": 403.66
+  },
+  "failure_classification": {
+    "initial_failing_cases": 82,
+    "frozen_a_replay_failed": 79,
+    "frozen_a_replay_passed": 3,
+    "corrected_browser_regressions": [
+      "tests/test_execution_bridge.py::test_registry_dispatch_preserves_session_id_for_native_handlers",
+      "tests/test_tool_index_schema_parity.py::test_every_schema_tool_has_an_index_description"
+    ],
+    "remaining_order_failure_reproduced_on_frozen_a": {
+      "command": "python -m pytest -q tests/test_scheduler_restart_doublefire.py tests/test_tool_approvals.py::test_dispatcher_rejects_approved_document_action_without_target",
+      "passed": 4,
+      "failed": 1
+    },
+    "all_final_failed_nodes_reproduced_on_frozen_a": true,
+    "final_failed_nodes": [
+      "tests/test_agent_bash_tmux_env.py::test_direct_bash_subprocess_has_closed_stdin",
+      "tests/test_agent_bash_tmux_env.py::test_bash_rejects_unicode_ffmpeg_drawtext_without_explicit_font",
+      "tests/test_agent_bash_tmux_env.py::test_bash_allows_unicode_ffmpeg_drawtext_with_explicit_fontfile",
+      "tests/test_agent_bash_windows.py::test_windows_bash_tool_passes_ctx_env_through_to_the_child",
+      "tests/test_agent_bash_windows.py::test_bash_tool_returns_install_hint_when_git_bash_is_missing",
+      "tests/test_agent_bash_windows.py::test_windows_bash_does_not_use_a_stray_tmux_executable",
+      "tests/test_agent_external_tool_schemas.py::test_known_native_tool_reaches_scoped_bridge_without_redeclared_schema",
+      "tests/test_client_tool_routing.py::test_no_bridge_falls_back_to_backend_execution",
+      "tests/test_client_tool_routing.py::test_host_shell_requires_bridge_context",
+      "tests/test_doc_library_open_orphaned.py::test_mobile_explicit_load_restores_full_editor_from_bottom_dock",
+      "tests/test_document_history_controls.py::test_mobile_rich_text_history_state_and_document_switch",
+      "tests/test_document_library_mobile_footer.py::test_mobile_open_in_new_chat_copies_to_materialized_session",
+      "tests/test_document_module_api.py::test_default_export_surface_is_complete_and_callable",
+      "tests/test_document_module_api.py::test_named_exports_survive_and_stay_callable",
+      "tests/test_document_module_api.py::test_window_bridge_is_the_default_export",
+      "tests/test_document_outline.py::test_outline_jumps_in_markdown_and_rich_text_and_fits_mobile",
+      "tests/test_document_rich_checklist_enter.py::test_enter_creates_unchecked_task_and_empty_enter_exits_cleanly",
+      "tests/test_document_rich_color_reset_and_contrast.py::test_rich_colors_follow_theme_and_undo_as_one_edit",
+      "tests/test_document_rich_docx_export.py::test_browser_word_export_contains_native_rich_docx_ooxml",
+      "tests/test_document_rich_docx_export.py::test_browser_markdown_word_export_keeps_heading_and_inline_formatting",
+      "tests/test_document_rich_find_boundaries.py::test_find_rejects_cross_block_matches_but_supports_inline_matches_and_replacement",
+      "tests/test_document_rich_font_color_controls.py::test_numeric_font_size_and_custom_colors_work_on_desktop_and_mobile",
+      "tests/test_document_rich_heading_enter.py::test_mobile_heading_enter_exits_cleanly_and_is_one_step_undoable",
+      "tests/test_document_rich_heading_enter.py::test_heading_enter_preserves_shift_middle_and_empty_heading_semantics",
+      "tests/test_document_rich_image_caption.py::test_mobile_image_caption_survives_resize_history_and_empty_removal",
+      "tests/test_document_rich_input_rules.py::test_typing_markers_converts_blocks_and_preserves_following_text",
+      "tests/test_document_rich_keyboard_shortcuts.py::test_rich_document_shortcuts_work_at_desktop_and_mobile_widths",
+      "tests/test_document_rich_selection_toolbar.py::test_selection_toolbar_formats_and_stays_inside_desktop_and_mobile_viewports",
+      "tests/test_document_rich_slash_menu.py::test_slash_menu_filters_converts_blocks_inserts_tables_and_fits_mobile",
+      "tests/test_document_rich_smart_link_paste.py::test_rich_url_paste_links_selections_and_plain_urls_without_unsafe_autolinks",
+      "tests/test_document_rich_structure_tools.py::test_mobile_headings_page_break_history_and_persistence",
+      "tests/test_document_rich_table_cell_alignment.py::test_mobile_table_cell_alignment_tracks_state_and_native_history",
+      "tests/test_document_rich_table_header_preservation.py::test_mobile_structural_edits_preserve_header_modes_and_history",
+      "tests/test_document_rich_table_headers.py::test_mobile_header_row_and_column_toggle_independently_with_undo",
+      "tests/test_document_rich_table_merge_split.py::test_mobile_merge_split_round_trip_preserves_headers_formatting_and_history",
+      "tests/test_document_rich_table_tab_history.py::test_mobile_table_tab_navigation_row_creation_and_history",
+      "tests/test_document_rich_toolbar_menus.py::test_mobile_toolbar_uses_native_momentum_and_distinct_activation_tokens",
+      "tests/test_document_rich_toolbar_menus.py::test_mobile_toolbar_menu_preserves_selection_and_restores_focus",
+      "tests/test_document_rich_toolbar_menus.py::test_rich_toolbar_menus_track_live_formatting_values",
+      "tests/test_document_save_shortcut.py::test_ctrl_s_saves_rich_text_immediately_once_and_updates_status",
+      "tests/test_document_save_status.py::test_save_status_is_dirty_race_safe_and_reports_failures",
+      "tests/test_document_toolbar_order.py::test_rich_toolbar_rendered_order_is_stable_on_desktop_and_mobile",
+      "tests/test_edit_file.py::test_edit_file_blocked_at_execution_for_non_admin",
+      "tests/test_email_library_module_graph_js.py::test_every_package_module_evaluates_on_its_own_in_a_browser",
+      "tests/test_email_library_module_graph_js.py::test_wrapper_and_entry_module_hand_out_the_same_functions",
+      "tests/test_escape_inner_layers.py::test_rich_escape_closes_toolbar_then_selection_badge",
+      "tests/test_escape_inner_layers.py::test_email_escape_closes_inner_states_without_closing_library",
+      "tests/test_failed_call_correction.py::test_corrected_ids_execute_after_repeated_ambiguous_title_failures[2]",
+      "tests/test_failed_call_correction.py::test_corrected_ids_execute_after_repeated_ambiguous_title_failures[3]",
+      "tests/test_history_resume_rendering_js.py::test_history_resume_rendering_browser_suite",
+      "tests/test_live_fallback_round_attribution.py::test_detached_resume_reconciles_canonical_terminal_failures",
+      "tests/test_live_fallback_round_attribution.py::test_detached_resume_surfaces_fallback_then_provider_alias_without_reload",
+      "tests/test_live_fallback_round_attribution.py::test_detached_resume_renders_preoutput_error_without_empty_reload",
+      "tests/test_manage_tasks_cron.py::test_cron_create_edit_resume_and_invalid_edit_rollback",
+      "tests/test_manage_tasks_cron.py::test_named_weekdays_create_and_edit_preserve_actual_clock",
+      "tests/test_manage_tasks_cron.py::test_time_only_edit_changes_cron_clock_not_calendar_fields[15 9 * * 1,3,5]",
+      "tests/test_manage_tasks_cron.py::test_time_only_edit_changes_cron_clock_not_calendar_fields[15 9 15 * *]",
+      "tests/test_manage_tasks_cron.py::test_time_only_edit_changes_cron_clock_not_calendar_fields[0,30 8-10 * * 2,4]",
+      "tests/test_manage_tasks_cron.py::test_invalid_cron_retime_rolls_back_all_edits",
+      "tests/test_preview_execution_evidence.py::test_failed_shell_retains_exit_status_and_both_streams_for_followup",
+      "tests/test_review_regressions.py::test_host_shell_uses_tui_bridge_context",
+      "tests/test_review_regressions.py::test_host_shell_forwards_detach_and_job_polling",
+      "tests/test_review_regressions.py::test_host_shell_rejects_non_local_bridge_url_before_http",
+      "tests/test_review_regressions.py::test_public_agent_policy_blocks_sensitive_tools",
+      "tests/test_review_regressions.py::test_disabled_qualified_email_tool_blocks_bare_alias",
+      "tests/test_review_regressions.py::test_tool_policy_qualified_email_block_covers_bare_alias",
+      "tests/test_review_regressions.py::test_bare_email_dispatch_rejects_non_object_json_args",
+      "tests/test_review_regressions.py::test_bare_email_dispatch_rejects_invalid_json_body",
+      "tests/test_review_regressions.py::test_write_file_inline_json_args",
+      "tests/test_review_regressions.py::test_plan_mode_blocks_mutating_email_aliases_without_mcp_inventory",
+      "tests/test_review_regressions.py::test_bare_email_dispatch_empty_content_calls_with_empty_args",
+      "tests/test_review_regressions.py::test_email_mcp_non_object_args_fail_before_dispatch",
+      "tests/test_review_regressions.py::test_email_mcp_dispatch_includes_hidden_owner",
+      "tests/test_review_regressions.py::test_bare_email_mcp_dispatch_includes_hidden_owner",
+      "tests/test_tool_approvals.py::test_dispatcher_rejects_approved_document_action_without_target",
+      "tests/test_turn_rendering_js.py::test_turn_rendering_browser_suite"
+    ]
+  },
+  "static": {
+    "compileall": "passed",
+    "diff_check": "passed",
+    "conflict_markers": "none",
+    "unmerged_index": "none"
+  },
+  "limitations": [
+    "page/document reads and effects unconditionally unavailable",
+    "arm64 producer execution not live tested",
+    "18-case positive producer enabling gate remains blocked on atomic expected-identity operation support",
+    "full repository suite is not green; failures reproduced on frozen A"
+  ]
+}

docs/runtime-decomposition/wave-3-browser-authority.md

@@ -0,0 +1,282 @@
+# Wave 3 browser authority: observations with page execution disabled
+
+Starting Checkpoint A: `bc5e1ee6922000a290371f8c2aa18802a03ffcad`, tree
+`8e09cc2560f50a3472e06ec614d6ada028b7eb18`. Branch, cleanliness, both A
+commits and canonical Wave 5B ancestry were verified before edits. Existing
+145-file Checkpoint A baseline passed 3369 tests, with 3 platform skips
+and 2 existing xfails.
+
+## Producer decision and live evidence
+
+The actual release Docker image was available locally:
+`sha256:cc2d47e2327d573af01c6b027f23d2ab0f2ee9b85d658e9eb8065bd02b9c3515`
+(Linux amd64). Its native binary reports exactly `agent-browser 0.35.0`.
+
+The isolated local-launch probe performed:
+
+1. Fresh local browser launch with the first `--pin-tab` request.
+2. Create a sibling tab; capture and select an exact producer targetId.
+3. `session info --no-pin-tab`, then `session info --pin-tab`.
+4. Destroy the captured target using an external **test fixture**.
+5. `snapshot --pin-tab`.
+
+Both re-arm calls succeeded. The snapshot also succeeded, a replacement target
+became active, and there was no `tab_gone`. Lifecycle metadata reported
+`relaunchedBrowser=false`, `restartedBackground=false`, `launched=false`.
+The CLI's special `session info` path does not attach the pin fields to its
+daemon request. Successful flags therefore cannot establish `pin_armed_for`.
+The producer audit's proposed re-arm sequence is not valid in this mode.
+
+`tests/test_browser_producer_live_contract.py` reproduces this defect against
+the actual binary, rather than treating the defect as a passing pin contract.
+The four live tests also validate target/loader stability, reload/navigation,
+same-document history change, distinct same-URL pages, and exact target switch
+responses. Four passed in the actual release image. Raw GUIDs/CDP capability URLs
+are neither printed nor saved by the tests or production adapter.
+
+Page/document reads and effects are **unconditionally disabled before producer
+dispatch**. Observations, matching preconditions, matching postconditions,
+successful pin flags, exact approval and child scope never override this gate.
+
+## Identity architecture
+
+`src/browser_identity.py` owns producer validation, private configuration,
+registration, observations, metadata execution, resource binding and CDP
+observation. `src/agent_runtime/resources.py` supplies immutable types:
+
+- `BrowserSessionObservation`: trusted namespace, version, platform, binary
+  digest, configuration digest, selector-only session key, one nested Wave 5B
+  `ProcessIdentity`, domain-separated browser GUID digest, and deterministic
+  session-incarnation digest. No duplicated start-token abstraction.
+- `BrowserSessionResource`: the observation plus mandatory owner/thread binding.
+- `BrowserPageResource`: exact parent session, producer targetId, opaque loaderId,
+  explicit page/document scope, and alias/URL audit metadata. Page authority is
+  session + target; document authority additionally includes loader. Metadata
+  does not participate in the authority key.
+
+Registration is server-only, checks the installed producer and creates private
+owned configuration. It does not spawn or adopt a daemon/browser. Model-facing
+lookup never creates a session. Legacy lifecycle records are not authority.
+There is currently no model-facing launch/enrolment operation; default/legacy
+sessions without a registered observation fail closed.
+
+An explicit trusted observation checks active producer state, captures the
+daemon incarnation around exact executable observation, obtains the local CDP
+capability, rejects lifecycle launch/replacement, validates tab schema and the
+absence of labels, cross-checks CDP target type, captures main-frame loaderId,
+detaches and rechecks daemon/browser identity. A changed session invalidates
+every earlier page/document observation. A changed loader invalidates document
+scope; a same-URL or same-alias replacement never inherits target scope.
+
+The proposed pin re-arm is **not implemented as an authority-establishing
+action**. `pin_armed_for` stays unset; even modifying this field cannot enable
+page execution. No alternate pin workaround or producer fork is introduced.
+
+## Trusted producer and observation transport
+
+Only explicit glibc Linux release binaries are allowlisted:
+
+| Platform | Version | Native binary SHA-256 |
+| --- | --- | --- |
+| linux-x64 | 0.35.0 | b7a28c3a43a7008dd02585e2e60c391c08983f7a099149caed63c9f13f57b752 |
+| linux-arm64 | 0.35.0 | 92cd7d0897837ac648b9a6ab1965c69c5920e0f54df57e4295cdb1143b0541c8 |
+
+These digests were observed from the release image's installed package. x64 was
+executed live; arm64 execution remains a separate architecture gate. Selection
+uses `/usr/local/lib/node_modules/agent-browser/bin/agent-browser-<platform>`.
+Version, hash, ownership, permissions and schema are checked. No PATH search,
+npx execution/download, cache glob, mtime selection or replacement download.
+0.27.0, unknown versions, platforms and hashes fail closed.
+
+The CDP sidecar accepts only loopback browser websocket capability URLs and
+only `Target.getTargets`, `Target.getTargetInfo`, `Target.attachToTarget`,
+`Page.getFrameTree`, `Target.detachFromTarget`. It does not enable domains,
+evaluate, navigate, close targets or expose arbitrary CDP to tools. Frame identity
+must equal the captured target and loaderId must be nonempty. Requests have
+3-second bounds and bounded frame/message sizes. This is producer identity
+observation, not semantic evidence or trust elevation.
+
+The capability URL stays in a non-serializable, non-repr memory field. Metadata
+revalidation connects to that captured browser endpoint, rather than calling
+`get cdp-url` again: that getter can auto-launch a replacement. Failed or changed
+daemon/CDP observations invalidate the registered session; no rediscovery/retry.
+
+Configuration is exactly `{}` in an owned private cwd, with observed inode and
+permissions checked. Client environment is constructed from an explicit fixed
+allowlist: owned HOME/TMPDIR/socket directory, system PATH, Chromium path and
+idle timeout. Ambient AGENT_BROWSER/CDP/provider/profile/state/config/proxy/XDG
+settings and model subprocess environment are not inherited. Configuration is
+part of the incarnation digest; credentials are not serialized.
+
+## Operation and approval boundaries
+
+| Operation | Binding | Current execution |
+| --- | --- | --- |
+| `session_info` | Exact registered session + caller/request | Supported metadata only; no URL/title/content, target selection or launch |
+| New page, initial open, tab list, whole-session close | Session/creation producer guarantee | Disabled; no trustworthy atomic creation/control contract admitted |
+| Select/close page, navigate/reload/back/forward, time wait, viewport scroll, page network/console | Exact session + target | Disabled before dispatch |
+| Click/fill/press/evaluate, selector/ref interactions and waits | Exact session + target + loader | Disabled before dispatch |
+| Snapshot/read/find/screenshot | Exact page, loader sandwich for any future read | Disabled before dispatch; no replacement-page read |
+
+Failure is structured: `failure_kind=browser_page_authority_unavailable`,
+`executed=false`, `retryable=false`, `producer_capability_unavailable=true`.
+Missing session authority produces a separate session-unavailable failure.
+No timeout or post-check can authorize execution against a replacement.
+
+RequestAuthority version 5 carries explicit session/page ceilings. Old snapshots
+restore empty browser scopes. Exact proposal capture binds normalized operation,
+request/owner/thread and the exact session/page/document observation. Metadata
+execution revalidates before one-use claim and at producer entry. Restoration
+adds no general scope. Unsupported page approvals are never claimed/executed.
+
+Child scopes validate parent observations before intersection. Session ceilings
+require exact incarnation; page ceilings require exact parent + target; document
+ceilings also require loader. A page child cannot acquire session control, and a
+document child cannot renew a replaced document. Discovery adds no authority.
+
+Model batches, raw tab/window/frame/connect commands, labels, raw targetIds,
+configuration/session/CDP/provider/profile/state flags and flag-like positional
+values are rejected. `page: tN` is strictly validated. The preview's automatic
+open/snapshot batch rewrite and native read/post-click batches/recovery engine
+are removed. Raw global Playwright browser control calls fail closed as well;
+remote backend/stdio identity is not page authority. Other remote/MCP transport
+mechanics remain unchanged and external.
+
+Client invocations are bounded at 20 seconds, below the source-verified 30-second
+read/resend floor, with held-handle kill/wait on timeout/cancellation and no
+Odysseus retries. Immediate producer EOF/reset retries cannot be eliminated by
+this wrapper. **No exactly-once claim is made; all effects remain disabled.**
+
+## Control state and prior unsupported paths
+
+Private browser runtime/configuration is protected by central control-plane
+resolution and native launch workspace guards, including actual configured
+directories. Direct, symlink and hardlink tests cover it. These are pathname/
+inode observations, not race-freedom claims or a new containment policy.
+Service-owned Wave 5B cleanup remains independent of model authority; shutdown
+does not discover/download/run an untrusted producer binary.
+
+Re-audit of Checkpoint A seams found:
+
+| Path | Remaining enforcement |
+| --- | --- |
+| PTY/native manager routes | `routes/shell_routes.py:setup_shell_routes.shell_exec/shell_stream` call `_require_admin` before `_exec_shell/_generate_pty/_generate_tmux`; internal/anonymous controls denied, authenticated human administration separate |
+| Additional process producers | `resources.ProcessResource.__post_init__` admits only frozen native producer/role combinations; `process_resources.resolve_process_operation` requires sealed observations |
+| Raw scheduled SSH | `TaskScheduler._execute_action` → `builtin_actions.action_ssh_command` → `_run_subprocess` refuses SSH without an external workload adapter |
+| Local Cookbook scheduled auto-stop | `routes/cookbook_routes.py:setup_cookbook_routes.protect_native_control` applies shell admin boundary to local mutation; `tools/cookbook._cookbook_kill_session` refuses registry-less local control; legacy internal shell route cannot gain administration |
+| Legacy/unscoped tasks | `authority.restore_task_authority` → `process_resources.resolve_process_operation` admits no missing creation scope |
+| Anonymous administration / generic app_api | `owned_resources.needs_owned_binding` rejects shell/model/Cookbook namespaces; `_require_admin` also rejects unlabelled loopback when anonymous or unauthenticated |
+
+No model-reachable page producer entry remains in the native/research wrapper.
+Trusted observation/setup methods are not tools or routes. Native arbitrary
+program/network effects and remote workload effects retain their existing
+explicit launch/backend boundaries; this checkpoint adds no general network
+egress/provenance policy (Wave 4).
+
+## Validation and remaining release gates
+
+`wave-3-final-tests.txt` contains 149 files, retaining all 145 Checkpoint A files
+and the exact prior 88-file selection. Legacy positive page/batch/recovery tests
+are replaced by explicit unsupported-before-dispatch tests; formatting,
+filesystem, YouTube, Wave 5B ownership/cleanup and research fallback tests remain.
+
+Final resource/authority/approval focused run: **1,425 passed**. Final 149-file
+integrated gate: **3,776 passed, 7 skipped, 2 xfailed**. The exact old 88-file
+selection and all 145 Checkpoint A files were verified as subsets of this gate.
+The 7 skips are `/tmp` not being a symlink, applicable RLIMIT_AS already
+available, the Windows Ollama startup guard, and four explicit Docker-only
+producer probes. Those four probes ran separately: **4 passed** on the actual
+release x64 image. Index/schema/configuration checks separately passed 40 tests.
+
+Full-suite failure classification was performed against an isolated archive of
+the frozen Checkpoint A (no checkout/rewrite): replay of the initial 82 failing
+cases reproduced 79. Two browser/schema regressions were corrected. The third
+case, `test_dispatcher_rejects_approved_document_action_without_target`, passed
+alone but failed identically on the frozen archive when preceded by
+`test_scheduler_restart_doublefire.py`. That fixture permanently replaces
+`core.database.SessionLocal/engine` with a task-only database. This is an
+existing suite-order issue, not a browser authority regression. Missing Node
+Playwright dependencies and legacy fixtures that expect unscoped execution
+also remain explicit full-suite limitations; they are not skipped or counted
+as passes. New browser test environment documentation also records the existing
+memory backend owner settings required to regenerate the configuration page.
+
+Final full repository run: **12,310 passed, 76 failed, 65 skipped, 2 xfailed,
+6 subtests passed** (403.66 seconds). Every final failed node was reproduced on
+frozen Checkpoint A, using the scheduler-order reproduction for the document
+case. This is **not a green full-suite gate**. Exact failed node IDs and totals
+are in `validation/wave-3-browser-final-results.json`.
+
+Full-suite skips include smoke/live endpoints without an instance or opt-in,
+the four separately executed release producer probes, the three platform cases,
+missing caldav/chromadb/fitz/openpyxl/markitdown/libmagic/Node Playwright,
+ffmpeg format limitations and missing rsvg-convert. Nothing was silently
+converted into a pass. The two existing strict xfails remain the inferred single-file deletion and inferred CSV overwrite path cases in `test_runtime_behavior_regressions.py`.
+
+Compileall, whitespace, conflict-marker and unmerged-index checks pass.
+The coherent fail-closed implementation is available for independent review;
+full-suite cleanup remains outstanding and page enabling is not merge-ready.
+
+## Exact production changes since Checkpoint A
+
+```text
+src/browser_identity.py
+src/agent_runtime/resources.py
+src/agent_runtime/authority.py
+src/agent_runtime/process_resources.py
+src/agent_tools/web_tools.py
+src/tool_execution.py
+src/tool_approvals.py
+src/tool_schemas.py
+src/tool_index.py
+src/clean_agent_preview.py
+src/agent_loop.py
+src/constants.py
+scripts/generate_env_reference.py
+```
+
+`website/configuration-reference.md` is regenerated documentation. Runtime
+instructions/schema/index no longer advertise executable page interactions.
+The agent loop change is only the browser prompt snippet; it is not decomposed.
+Wave 5B lifecycle mechanics and MCP transport are not modified.
+
+```sh
+python3 -m pytest -q -rs $(cat docs/runtime-decomposition/wave-3-final-tests.txt)
+python3 -m pytest -q -rs
+python3 -m compileall -q app.py core routes services src tests scripts
+git diff --check
+git grep -n -E '^(<<<<<<< |=======$|>>>>>>> )' || true
+git ls-files -u
+```
+
+Live release probe (source checkout mounted read-only, isolated container state):
+
+```sh
+docker run --rm --network none \
+  -e ODYSSEUS_BROWSER_LIVE_CONTRACT=1 -e ODYSSEUS_DATA_DIR=/tmp/w3-data \
+  -e DATABASE_URL=sqlite:///:memory: -v "$PWD:/app:ro" \
+  --entrypoint python odysseus-maintainer-preview-odysseus:latest \
+  -m pytest -q -rs -o cache_dir=/tmp/w3-pytest-cache \
+  tests/test_browser_producer_live_contract.py
+```
+
+The x64 probes pass by proving observation contracts **and the known defect**.
+They are not a positive merge gate for enabling page effects. Re-enabling needs
+a separately audited/allowlisted producer that executes only while expected
+browser incarnation, targetId and optional loaderId still match, rejects stale
+state atomically before reading/effect, and does not resend an indeterminate
+effect. No producer changes are implemented here.
+
+The original positive 18-case Docker gate remains mandatory before re-enabling:
+stable/repeated targets; reload; cross-/same-document navigation; identical URLs;
+close/recreate; browser and daemon replacement; popup races; destroyed targets;
+local-launch pin/atomic binding; exact target switch; A-F label collision;
+lifecycle metadata; timeout/duplicate effects; bfcache; prerender/frame invariant;
+strict schema. It must run per supported release architecture. Pin success and
+pre/post checking alone can never substitute for atomic binding.
+
+P1: producer page/document capability unavailable; unregistered sessions and
+Checkpoint A compatibility paths intentionally denied. P2: private-runtime scan
+cost/retention, filesystem observation races and architecture-specific live
+coverage. Wave 4 remains responsible for effects/provenance/egress and truthful
+completion evidence; no Wave 4 journal or lifecycle redesign is introduced.

docs/runtime-decomposition/wave-3-final-tests.txt

@@ -0,0 +1,149 @@
+tests/test_resource_identity.py
+tests/test_owned_resource_identity.py
+tests/test_remote_resource_identity.py
+tests/test_request_authority.py
+tests/test_tool_approvals.py
+tests/test_tool_approval_single_action_scope.py
+tests/test_tool_approval_task_scope.py
+tests/test_workspace_confine.py
+tests/test_tool_path_confinement.py
+tests/test_path_confinement_boundary.py
+tests/test_filesystem_tool_argument_validation.py
+tests/test_code_nav_tools.py
+tests/test_apply_patch_transaction.py
+tests/test_execution_bridge.py
+tests/test_production_external_bridge.py
+tests/test_turn_contract.py
+tests/test_turn_contract_read_operations.py
+tests/test_turn_contract_integration.py
+tests/test_agent_turn_contract_boundaries.py
+tests/test_explicit_personal_turn_contract.py
+tests/test_nested_invocation_ownership.py
+tests/test_containment_contract.py
+tests/test_containment_enforcement.py
+tests/test_containment_process_tree.py
+tests/test_native_execution_containment.py
+tests/test_background_containment.py
+tests/test_process_ownership.py
+tests/test_bg_jobs_store.py
+tests/test_bg_job_tools.py
+tests/test_execution_filesystem_boundary.py
+tests/test_mcp_manager.py
+tests/test_mcp_reconnect_args.py
+tests/test_mcp_text_error_normalization.py
+tests/test_mcp_param_hint_hardening.py
+tests/test_mcp_tool_params_in_prompt.py
+tests/test_mcp_memory_owner_scope.py
+tests/test_mcp_cache_invalidation.py
+tests/test_multiple_mcp_servers_timeout.py
+tests/test_mcp_dependency_compatibility.py
+tests/test_builtin_mcp_bg_tasks.py
+tests/test_builtin_mcp_pythonpath.py
+tests/test_builtin_mcp_npx_cache.py
+tests/test_mcp_add_server_args_validation.py
+tests/test_manage_mcp_command_allowlist.py
+tests/test_document_tool_owner_scope.py
+tests/test_owned_document_query.py
+tests/test_document_session_owner_scope.py
+tests/test_active_document_mutation_guard.py
+tests/test_native_document_stream.py
+tests/test_document_followup_integrity.py
+tests/test_document_active_restore.py
+tests/test_attachment_refs.py
+tests/test_upload_handler_atomicity.py
+tests/test_upload_handler_cleanup.py
+tests/test_upload_handler_rename_owner.py
+tests/test_upload_routes_owner_scope.py
+tests/test_resolve_upload_path_nondict.py
+tests/test_personal_upload_isolation.py
+tests/test_personal_upload_privilege.py
+tests/test_extract_text_tool.py
+tests/test_media_ingress.py
+tests/test_session_tools_registry.py
+tests/test_session_owner_attribution.py
+tests/test_session_list_owner_scope.py
+tests/test_session_endpoint_owner_scope.py
+tests/test_session_search.py
+tests/test_session_search_batch_fetch.py
+tests/test_history_topics_owner_scope.py
+tests/test_history_order_by_timestamp_regression.py
+tests/test_history_db_fallback_hidden.py
+tests/test_memory_owner_isolation.py
+tests/test_memory_routes_session_owner.py
+tests/test_manage_memory_json_contract.py
+tests/test_manage_memory_list.py
+tests/test_memory_store_unreadable_no_wipe.py
+tests/test_manage_notes_search_contract.py
+tests/test_notes_fail_closed_auth.py
+tests/test_notes_checklist_state.py
+tests/test_vault_password_not_in_argv.py
+tests/test_vault_routes_shim.py
+tests/test_external_context_tool_gate.py
+tests/test_chat_route_tool_policy.py
+tests/test_product_turn_contract_route.py
+tests/test_native_tool_result_threading.py
+tests/test_host_shell_polling.py
+tests/test_integrations_url_join.py
+tests/test_integration_api_call_ssrf.py
+tests/test_integrations_api_call_truncation.py
+tests/test_process_resource_identity.py
+tests/test_background_resource_identity.py
+tests/test_runtime_resource_integration.py
+tests/test_process_lifecycle.py
+tests/test_browser_lifecycle.py
+tests/test_private_browser_tool.py
+tests/test_browser_transport_recovery.py
+tests/test_shell_routes.py
+tests/test_agent_tmux_retirement.py
+tests/test_cookbook_stop_without_procfs.py
+tests/test_cookbook_serve_lifecycle.py
+tests/test_task_scheduler_cancel.py
+tests/test_task_shell_tools.py
+tests/test_runtime_behavior_regressions.py
+tests/test_workspace_artifact_tool_floor.py
+tests/test_bg_monitor_stream.py
+tests/test_orphan_reaping.py
+tests/test_cookbook_agent_tool_ssh_validation.py
+tests/test_codex_cookbook_admin_gate.py
+tests/test_task_cookbook_admin_gate.py
+tests/test_builtin_actions_cookbook_serve_state.py
+tests/test_cookbook_local_serve_pid_winpid.py
+tests/test_scheduler_restart_doublefire.py
+tests/test_task_scheduler_session_delivery.py
+tests/test_cookbook_cache_scan_isolation.py
+tests/test_cookbook_cached_scan_refresh.py
+tests/test_cookbook_chat_deeplinks_static.py
+tests/test_cookbook_cpu_only_serve.py
+tests/test_cookbook_dead_download_status.py
+tests/test_cookbook_dependency_completion_regression.py
+tests/test_cookbook_deps_recipes.py
+tests/test_cookbook_diagnosis.py
+tests/test_cookbook_diagnosis_js.py
+tests/test_cookbook_docker_access.py
+tests/test_cookbook_download_toast_duration.py
+tests/test_cookbook_endpoint_registration.py
+tests/test_cookbook_error_feedback.py
+tests/test_cookbook_error_tail_lines.py
+tests/test_cookbook_finished_download_label.py
+tests/test_cookbook_gemma4_thinking_template.py
+tests/test_cookbook_helpers.py
+tests/test_cookbook_hf_token.py
+tests/test_cookbook_official_trending_filter.py
+tests/test_cookbook_package_detection.py
+tests/test_cookbook_port_parsing_js.py
+tests/test_cookbook_progress_signal_js.py
+tests/test_cookbook_remote_windows_diffusers.py
+tests/test_cookbook_same_host_server_profiles_js.py
+tests/test_cookbook_tool_dry_run.py
+tests/test_cookbook_windows_stop_tree_js.py
+tests/test_scheduler_prompt_cache_time.py
+tests/test_scheduler_scheduled_time_validation.py
+tests/test_task_scheduler_cache.py
+tests/test_task_scheduler_fixture_isolation.py
+tests/test_tool_task_cancelled_on_disconnect.py
+tests/test_background_tool_jobs.py
+tests/test_deep_research_browser_fallback.py
+tests/test_browser_resource_identity.py
+tests/test_browser_identity_transport.py
+tests/test_browser_producer_live_contract.py
+tests/test_clean_agent_preview.py