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>
Implements all 19 tasks of the cloud-planner-proxy OpenSpec change:
- Cloud API: cloud.planner_config (CloudPlannerConfig, load/build helpers)
reusing runtime.tool_calling_client provider clients (no new dependency
needed -- device-cloud-platform already depends on device-agent-runtime).
- Cloud API: new host-scoped POST /internal/v1/hosts/{host_id}/planner/decide
internal endpoint, reusing existing bearer auth; logs only metadata
(host id, tool name, latency, error class), never prompt/screenshot
content.
- Host Agent: new AI_PLANNER_TRANSPORT config (direct default | cloud) and
host_agent/cloud_planner_client.py::CloudProxyToolCallingClient, a
synchronous ToolCallingClient implementation (structural, not importing
runtime) that calls the new endpoint via its own httpx.Client -- avoids
bridging the async HostAgentClient across the worker-thread boundary
that AIPlanner.plan() runs in (asyncio.to_thread in lease.py).
- Host Agent wiring: create_execution_factories()/_host_agent_planner()
select the cloud-proxy client only when AI_PLANNER_TRANSPORT=cloud;
direct/unset transport is unchanged (still the default).
- Tests: 22 new tests across Cloud API config, the new endpoint, the new
client, and transport-selection wiring; full non-integration suite
(492 tests) passes with no regressions.
- Docs: docs/CLOUD_DEPLOYMENT.md documents the cloud transport, its
trade-offs, and the credential split between Host Agent and Cloud API.
proposal.md/design.md were corrected during implementation to reflect two
findings: no new anthropic/openai dependency is actually needed, and
CloudProxyToolCallingClient uses its own sync httpx.Client rather than a
new HostAgentClient method, per the thread-boundary reasoning above.
Host Agent:
- One-time local operator account bootstrap (PBKDF2-HMAC-SHA256, atomic
0600-permission write) gating the daemon's first unattended start via a
new `setup` CLI subcommand.
- Default control-plane URL now https://amcp.home.jerryyan.top (env var
override unchanged).
- Enrollment no longer requires a pre-issued token; falls back to
zero-token self-service enrollment when none is configured.
Cloud control plane:
- CLOUD_SELF_SERVICE_ENROLLMENT_ENABLED (default false) opt-in flag.
- SelfServiceEnrollmentAuthProvider + ChainedEnrollmentAuthProvider:
configured tokens still take priority; self-service only applies when
no token matches, preserving edge-host-enrollment's token-bound path.
- Fixed a latent bug in sql_repository.py::enroll_host: the token-conflict
lookup used `== enrollment_token_digest`, which SQLAlchemy compiles to
`IS NULL` when the value is None, so every self-service enrollment after
the first would have falsely collided with an existing NULL-digest host.
Skipped that lookup entirely when the digest is None.
Docs/deploy: .env.example, compose.yaml, compose.deploy.yaml,
CLOUD_DEPLOYMENT.md, MACOS_IPHONE_SETUP.md updated for the new flag,
URL default, and required `device-host-agent setup` step.
Verification: 494 non-integration tests pass; openspec validate --strict
passes. PostgreSQL-backed contract tests and full manual end-to-end
verification were not run (no Postgres/Docker or reachable cloud-api in
this environment); noted as unchecked in tasks.md 7.2/7.4.
Register `SUPPORTED_DRIVER_TYPES["uiautomator2"]` backed by the new
`AndroidDriver`, mirroring `WDADriver` method-for-method. tap/swipe/home use
the confirmed UiAutomator2 mobile commands (`clickGesture`, `dragGesture`,
`pressKey`); swipe converts `duration_ms` to a drag speed with a zero-distance
guard. Adds 34 mocked unit tests, an env-var-gated integration test, and
corrects the outdated "Android not registered" note in the iPhone setup doc.
Co-Authored-By: Claude Opus 4.6 <noreply@anthropic.com>
Implements the cloud-console OpenSpec change: adds GET /v1/tasks (filterable,
bounded pagination, tasks:read) and GET /v1/tasks/{id}/attempts (404 on unknown
task) to the platform SDK, with matching CloudClient methods and a closed-by-
default CLOUD_CONSOLE_CORS_ORIGINS allow-list wired through CloudControlConfig.
Ships an independent Vue 3 + Vite SPA at cloud-console/ that authenticates with
an operator-supplied bearer token held in sessionStorage, renders tasks with
attempt history, device pool, host registry, and the plugin registry with a
registration form.
Backend test suite: 438 passed (-m "not integration"); cloud-console typecheck
and production build both succeed. PostgreSQL-backed repository tests and
manual end-to-end verification remain pending external infrastructure.
Co-Authored-By: Claude Opus 4.6 <noreply@anthropic.com>
Replaces the stub Planner's fixed describe_screen/[] behavior with a real
decision-maker: AIPlanner uses native tool/function calling (Anthropic or
OpenAI, pluggable via AI_PLANNER_PROVIDER) to select exactly one grounded
action per turn, with an explicit finish_task(success, reason) tool for
completion/failure instead of an ambiguous "no tool call" signal. Default
disabled (AI_PLANNER_ENABLED=false) and additive; TaskRunner falls back to
the existing stub Planner unchanged when disabled.
Amends CONSTITUTION.md's Perception Boundary with one narrow exception:
only the AI Planner may receive the current step's raw screenshot bytes
alongside Scene, for vision-grounded coordinate grounding. Also fixes a
latent gap in TaskRunner.run(): observe/plan exceptions are now caught per
iteration and turned into a failed task with a failure_reason, instead of
propagating uncaught.
openspec change: ai-planner-runtime.
Co-Authored-By: Claude Sonnet 5 <noreply@anthropic.com>
q792602257andClaude Opus 4.6