Three final-review deviations closed:
I1 (session-end release): mcp SDK 1.28.1 exposes no per-session
shutdown callback (only a server-level lifespan). Lower the
McpBusyTracker default TTL from 60s to 20s and update spec §6.5,
Q5/R3, D9, and docs/MCP_INTEGRATION.md concurrency section to
document the TTL-only recovery path. 20s is short enough to recover
within one 30s heartbeat interval but long enough that an active
session does not lose its lease during normal operator pauses.
I2 (JSON-RPC error shape): FastMCP Tool.run wraps every non-
UrlElicitationRequiredError exception (including McpError with typed
ErrorData) into ToolError, which the lowlevel call_tool handler
serializes as CallToolResult(isError=true, content=[TextContent(...)]).
There is no public path that surfaces JSON-RPC -32000 with structured
data.busy_owner from a tool call site. Update spec §7 error matrix
and docs/MCP_INTEGRATION.md error table to document the actual wire
shape; busy_owner now lives in the text content.
I3 (typing): mcp_server: Any = None -> FastMCP | None = None via
TYPE_CHECKING, keeping the mcp import lazy (matches precedent
elsewhere in the codebase) while adding static type checking at the
create_console_app boundary.
Tests added (4):
- test_default_ttl_is_20_seconds — locks I1's new default TTL
- test_default_ttl_recovers_dead_session_within_one_window — locks
I1's recovery semantics (lease sweeped on next read after 20s)
- test_busy_error_wire_shape_is_calltoolresult_iserror — pins I2's
wire envelope via Tool.run + lowlevel Server._make_error_result
- test_busy_error_text_includes_cloud_assignment_owner — same for
the cloud_assignment busy_owner branch
Full non-integration suite: 697 passed / 54 deselected (was 693 / 54).
Co-Authored-By: Claude Opus 4.6 <noreply@anthropic.com>
Reformat the files touched by Tasks 1-14 of the host-agent MCP server
plan. No semantic changes; pre-existing format issues in unrelated
files (test_templates, test_skill_sync_wiring, 0010_skill_management,
test_skill_catalog_mcp) left untouched for a separate housekeeping
pass.
Co-Authored-By: Claude Opus 4.6 <noreply@anthropic.com>
The previous _current_session_id() implementation tried to import a
non-existent get_context() helper, so the production code path always
fell through to the empty _TEST_SESSION_ID ContextVar — meaning every
MCP client shared the empty-string identity and there was no per-session
isolation in production.
Use Context.session (the long-lived ServerSession object) as the source
of identity. id(ctx.session) is stable across every tool call the same
client makes within a Streamable HTTP session, which is exactly what the
busy tracker needs to renew leases.
Wire FastMCP to inject the Context into the wrapper by setting
tool.context_kwarg = "ctx" after swapping tool.fn; wrap the swap in a
defensive try/except that surfaces a FastMcpSdkIncompatibilityError on
future SDK layout drift.
Add 4 tests covering the production path: stability across calls in the
same session, isolation between sessions, fallback to _TEST_SESSION_ID
when no Context is supplied, and verification that the registered tool
declares context_kwarg="ctx".
Co-Authored-By: Claude Opus 4.6 <noreply@anthropic.com>
The root tests/conftest.py fixture disables APEX_HUMANIZE_ENABLED by default for deterministic assertions, but apps/device-host-agent/tests/ was outside its scope. test_e2e.py::test_public_sdk_reports_fake_device_success_and_runtime_failure failed because tap coordinates were jittered (2.67..., 3.37...) instead of exact (2, 3).
Add the same autouse fixture to apps/device-host-agent/tests/conftest.py so all tests in that directory inherit the deterministic behavior.
Adds long_press/double_tap atomic gestures, a centralized humanize layer
(coordinate jitter, curved W3C-Actions swipe, timing jitter) gated by
APEX_HUMANIZE_ENABLED, and planner integration. 651 non-integration tests
pass on the branch.
Co-Authored-By: Claude Opus 4.6 <noreply@anthropic.com>
- New internal API route POST /internal/v1/hosts/{host_id}/tasks/{task_id}/cancel,
authenticated via the host's own bearer credential (authorize_host) with an
ownership check, since host tokens carry no scopes and cannot reach the
public SDK's tasks:submit-scoped cancel endpoint.
- HostAgentClient.cancel_task() calls the new internal route directly.
- create_console_app() gains a cancel_task callable with automatic default
wiring from host_client, so production app.py needs no changes.
- Local console: POST /tasks/{task_id}/cancel route resolves the local
execution id to its Cloud source_task_id before cancelling, and the task
detail page/template show a Cancel button plus notice/error banners.
- Tests across all three layers: internal API route, Jinja2 template
rendering, and FastAPI console route behavior.
- LeaseGuard gains an is_cancellation convenience property
- ActiveAssignmentRunner marks the lease lost with a cancellation
reason when a renewal response reports cancel_requested
- AssignmentExecutor threads stop_reason through to TaskRunner/
WorkflowRunner and maps a cancellation-flavored stop to
AssignmentExecutionResult.status = "cancelled" instead of "failed"
- AssignmentProcessor forwards a three-way done/cancelled/failed
status when reporting the terminal result
- Add/extend tests across lease, assignment, processor, and client
Fixes issue 3: the host-agent console showed OCR results but never real
UI-tree data, because _ui_tree_nodes() checked for a get_ui_tree/ui_tree
tool action that has never existed anywhere in the codebase.
- storage/timeline.py: add a ui_tree_results field to TimelineRecord and
Timeline.append(), mirroring the existing ocr_results field.
- runtime/task.py: _append_timeline() now extracts scene.elements with
source == "ui" into ui_tree_results (scene_builder.build_scene() already
preserved these; they were just never persisted).
- host_agent/web/app.py: _ui_tree_nodes() reads the new field directly
instead of the dead tool-action check. New _overlay_payload() exposes
each step's scene dimensions and fused element list for client-side
rendering.
- task_detail.html: adds a toggle to overlay OCR (orange) and UI-tree
(blue) bounding boxes on the before-action screenshot, plus a visual
marker for the actually executed action (tap circle, or an animated
swipe path) using an SVG viewBox so no manual coordinate-scaling JS is
needed. Legacy/incomplete records degrade to no overlay, never an error.
Also corrects openspec/specs/runtime-task-evidence and
host-agent-console-task-pages, which had encoded the same nonexistent-tool
assumption, via the new host-agent-console-visual-evidence change.
600 tests passing; ruff/compileall/openspec validate all clean.
Documents Skill Management in CLOUD_DEPLOYMENT.md (cloud-skill store,
per-host entitlement, incremental sync, local authoring/override,
inventory report, skills:admin scope) and applies ruff check/format to
all touched modules. All tasks complete; full non-integration suite
green (593 passed) and openspec validate --strict passes.
Co-Authored-By: Claude Opus 4.6 <noreply@anthropic.com>
Adds host_agent/skill_sync.py (HostAgentSkillSync) which constructs the
synced + local skill stores, the Cloud API sync client, and the runner,
then drives them on the host-agent lifecycle: incremental per-host pull
into the synced catalog, fork-on-revocation, and a best-effort local-
skill inventory report to the Cloud (design D7). Wired into
create_application + run_async start/stop. Host-agent suite green
(219 passed).
Co-Authored-By: Claude Opus 4.6 <noreply@anthropic.com>
Adds the skills:admin router (cloud/sdk/skill_api.py) for cloud-skill CRUD
and per-host entitlement grant/revoke with CSRF/scope/audit, and a
host-scoped router serving incremental per-host sync deltas plus the
agent local-skill inventory report/readback. Both composed into the
Cloud API app. cloud-api suite green (46 passed).
Co-Authored-By: Claude Opus 4.6 <noreply@anthropic.com>
Adds cloud/skills.py (domain + service), SQLAlchemy models and Alembic
migration 0010_skill_management (cloud_skills, cloud_skill_entitlements,
cloud_skill_sync_state, a per-host changelog, and host_skill_inventory),
and repository methods with a monotonic per-host entitlement_version that
drives correct incremental fetch_host_delta. cloud-api suite green (41
passed); HEAD_REVISION bumped to 0010.
Co-Authored-By: Claude Opus 4.6 <noreply@anthropic.com>
paddlepaddle has no Python 3.14 (cp314) wheel on PyPI, so host-agent
deployments on 3.14 can never install it, causing OCR to fail at
runtime with RuntimeError. Pin the workspace to Python 3.13 across
all pyproject.toml files, the Docker base image, and the Jenkins CI
image; regenerate uv.lock against 3.13.
Also fixes a pre-existing Python-2-style `except X, Y:` syntax error
(invalid in all Python 3.x) in runtime/task.py and
packages/cloud-platform/cloud/{sql_repository,internal_api/api}.py,
introduced in 22d37ca9 and unrelated to this change's scope, which
blocked the full test suite from collecting on any interpreter
version.
openspec change: downgrade-python-3-13-paddleocr
create_task_runner() built TaskRunner's observer/screenshot_provider by
calling describe_screen(device_id)/take_screenshot(device_id) without
manager=, so both silently fell back to the process-global DEFAULT_MANAGER
singleton instead of the Host Agent's real, device-populated DeviceManager.
DEFAULT_MANAGER never has any device registered, so every task's first step
raised DeviceNotFoundError even though the console (which does pass
manager=) showed the same device as connected. Deterministic on every task,
independent of process count.
Add regression tests confirming both lambdas now resolve devices via the
configured manager; verified each fails with the original DeviceNotFoundError
symptom when the fix is reverted.
Co-Authored-By: Claude Sonnet 5 <noreply@anthropic.com>
Acquire an exclusive, non-blocking filelock on the identity state directory
as the first action of create_application(), before resolve_host_identity()
or any enrollment/heartbeat side effect. A second process against the same
identity_path exits immediately with InstanceAlreadyRunningError naming the
lock path; the lock releases automatically on any process exit (including
SIGKILL) via OS-level advisory locking, and explicitly during run_async()'s
shutdown finally block. filelock is promoted from transitive to direct
dependency (version unchanged at 3.29.7).
Co-Authored-By: Claude Opus 4.6 <noreply@anthropic.com>
Replace hand-written f-string + html.escape() rendering in the Host Agent
local console with a module-level Jinja2 Environment configured with
select_autoescape(["html","xml"]). XSS safety now holds by mechanism
rather than per-call discipline — every operator-controlled field
(device name, connection_info, task summary, etc.) is escaped by the
engine uniformly.
Eight templates under host_agent/web/templates/ replace the former
_chrome(), _CSS, escape(), and per-page _xxx_body() helpers: base.html
(header/nav/CSS + {% block body %}), login, dashboard (with the polling
<script> preserved byte-identically inside {% raw %}), devices, account,
history, tasks_list, and task_detail. The task-list and task-detail
templates — added by the just-landed task-execution-progress-visibility
change — were also migrated here rather than left in f-string form,
since this change removes the shared helpers they depended on.
URLs, auth/session/CSRF semantics, redirects, and /api/status JSON are
unchanged. 15 new template tests cover render-smoke, XSS probing, script
byte-identity, and no-autoescape-bypass guards. Tasks 8.1-8.6 (manual
browser verification) remain.
Co-Authored-By: Claude Opus 4.6 <noreply@anthropic.com>
Host Agent now persists step-level execution detail locally (via a real
TaskMetadataStore/Timeline wired into TaskRunner) and reports a bounded
in-progress snapshot piggybacked on lease renewal. Cloud persists that
snapshot per active assignment and exposes it through the existing task
list/detail query path; Cloud Console renders it as a live badge. Host
Agent's local console gains authenticated, read-only task list and
detail/timeline pages (same-origin, server-rendered) with inlined
screenshots.
Also fixes a pre-existing gap in the shared Timeline: the actual
per-step LLM prompt is now recorded instead of the task goal, benefiting
both Runtime and Host Agent consoles. When a host uses the cloud planner
transport, each decide call's prompt and resulting tool decision are
durably logged in a new planner_decision_log table (with bounded
retention) and browsable from Cloud Console; direct-transport hosts
explicitly surface a "not reported" state.
Includes Alembic migrations 0008 (progress columns on scheduled_tasks)
and 0009 (planner_decision_log), bounded Host-Agent-local retention,
dual-backend repository parity, and Vitest + pytest coverage. Task 6.5
(manual end-to-end device verification) remains.
Co-Authored-By: Claude Opus 4.6 <noreply@anthropic.com>
DeviceManager marks a device "busy" as soon as an Appium/WDA session is
connected, which is unrelated to whether a task is currently executing on
it. The Host Agent's local console displayed this raw status, making
connected-but-idle devices look permanently busy. Cross-reference the
device id against AgentStatusTracker's current_assignment (already
tracked via mark_assignment_started/finished) to show "connected" unless
a task is actually running on that device.
Adds an opt-in dependency supervisor inside the Host Agent that probes,
spawns, and restarts the two local processes the macOS single-machine
real-device workflow depends on: the Appium server (gates Driver.connect())
and the local Runtime API (local inspection). Default-off; gated by
HOST_AGENT_DEPENDENCY_SUPERVISOR_ENABLED plus per-dependency *_SUPERVISED
flags.
Mitigates the live-incident failure mode where forgetting to start Appium
silently keeps devices offline and tasks queued forever with no error
surfaced in Host Agent logs.
Behavior (per openspec change):
- Adopt-don't-fight: probe (TCP + dependency-specific HTTP health check)
before spawn. Healthy listener → adopted (never killed/restarted).
Unhealthy listener → port-conflict error, skip. No listener → spawn.
- Only supervisor-spawned processes are restarted on crash, with capped
exponential backoff (1s/2s/4s/8s, capped at 30s) and a per-process-lifetime
attempt ceiling (HOST_AGENT_DEPENDENCY_RESTART_MAX_ATTEMPTS, default 5).
- Spawn failures (e.g. missing executable) logged distinctly from crashes.
- Graceful stop terminates only spawned children; adopted processes untouched.
- Supervisor starts before the heartbeat loop's first connect_devices() pass
and stops alongside existing heartbeat/console teardown.
Validation: ruff check + format clean, compileall clean, openspec validate
--strict valid. Non-integration suite 503 passed / 44 deselected / 2 failed
(both failures pre-existing from unrelated 03c7c30 LLM_PROVIDER_ENC_KEY;
verified by stashing this change). macOS real-device manual verification
(task 6.4) deferred to a macOS host.
Co-Authored-By: Claude Opus 4.6 <noreply@anthropic.com>
showtan001
q792602257andClaude Opus 4.6