Add dark theme, richer Markdown and readable plugin results.
Improve Android input evidence, response integrity and diagnostics.
Unify lifecycle, guidance receipts and evidence sources across clients.
Keep direct action dispatch without an added AI quota approval layer.
Align version metadata at 2.2.0 and bundle Helper 1.2.2.
Validation: 3063 backend tests before the version bump; 44 after.
Frontend: 317 tests and production build passed.
Preserve user guidance through history compression, stabilize Flash index targets, and retire withdrawn checks without applying stale verdicts.
Improve runtime diagnostics, tool responses, and history rendering. Simplify documentation and comments.
Validation: 2076 tests passed in the full suite; 381 affected tests and 26 frontend tests passed after cleanup. Ruff and the quality ratchet passed.
Report device actions as dispatched and preserve full failure details. Route
Flash through McpActionExecutor and use ToolFailure across helper tools and
agent loops instead of inferring failure from response text.
Require model-provided descriptions for coordinate targets. Keep observed
element metadata separate from those descriptions in safety checks, visual
summaries, history, and frontend labels.
Add Gemini Interactions API video analysis with configurable processing mode,
chunk size, and timeouts. Centralize Google provider capabilities and token
usage normalization, and update google-genai to 2.22.0.
Preserve system instructions on follow-up interactions, replan pending chunks
when falling back to static processing, and reject unanswered native video
and audio segments instead of caching placeholder results. Keep helper-tool
failure status intact through history tools and committee calls.
Validation: 1,762 Python unit tests passed (3 skipped), 40 frontend formatter
tests passed, and the production UI build completed. Ruff lint, formatting,
the quality ratchet, and git diff checks passed.
Add execution incidents, action bursts and shared Flash history.
Expose verification and Explorer settings with streamed check results.
Support graceful cancellation, recording recovery and bundled UI resources.
Add CI quality checks and clean up comments and documentation.
- Extract device action execution into artemis/mcp action layer:
typed ActionResult, capability manifest with startup validation,
AdbActuator as the single physical implementation, in-memory
ActionSession (replaces stdio subprocess MCP in validator), and
McpActionExecutor preserving the legacy executor contract.
adb_server keeps its external stdio/SSE surface unchanged and now
reuses the actuator implementation; import-time side effects moved
into configure_stdio_mode().
- Capability-gated prompt assembly (prompt_assembly.py): tool enums and
teaching segments render per available backend tools; full-set output
is byte-identical to the previous static text (locked by tests).
- Admin console task queue: serial worker replaced by a per-device
concurrent dispatcher (ARTEMIS_CONCURRENCY_MODE=global restores
serial semantics), per-session cancellation, strict device binding on
enqueue, unified stdio piping with tee to trace stdout.log, and
shutdown cleanup of all active runs. Fix _pid_exists exception order
so PermissionError is treated as alive.
- mcp_server reliability: spawn watchdog kills runners stuck before
interpreter startup and releases device reservations; task state
reconcile uses psutil liveness, prefers runner-reported pids, and
adds a 45s startup grace to stop false failure reports on Windows;
conversation_id is now optional end-to-end; explicit device_serial is
validated at submission.
- CLI install now writes ~/.claude/rules/artemis.md for Claude Code and
migrates/removes the legacy CLAUDE.md injection block; ~/.claude.json
is never rewritten when it fails to parse.
- Tests: Windows-portable stdio lifecycle and path assertions; new
suites for action layer, prompt assembly, spawn watchdog, and task
reconcile (895 passed, 3 skipped).
- Backend: maintain _step_number_cache in DataEngine and include step_number in all step_updated SSE events (summary, thinking, execution result)
- Admin console: query unassigned trace step_ids in stepless_rows to prevent orphan traces from being lost
- Showcase UI: implement dual-indexed entity deduplication (by step_id and step_number) in extractStepReplayFrames to eliminate phantom ghost steps
- Showcase UI: filter visual screenshot steps before generating sequential 1-based frame numbers, preventing step-4 start and index shift bugs
- Showcase UI: add rawStepNumber and summary properties to StepReplayFrame
- Showcase UI: update FloatingVideoPlayerComponent session reset effect to only reset playback on sessionId change rather than on every stepFrames mutation
- Showcase UI: add stepSeekRequest signal and stepIndex parameter to AgentService.openVideoPlayer
- Unit tests: add Karma and Pytest unit tests verifying step 1 start, dual-indexing, and SSE step_number payloads
- Unified configuration and paths under artemis.config as single source of truth
- Consolidated execution across CLI, SDK, MCP, and Admin Console to default to Artemis Daemon
- Fixed frontend step replay to preserve failure steps with proper sequential numbering
- Implemented task deduplication, debouncing, and multi-device lock isolation
- Added comprehensive end-to-end multi-port integration tests for live phone and emulator
Introduce complete test coverage for the ARTEMIS platform across multiple layers:
Unit tests: Add tests for agent nodes (Planner, Operator, Validator, Diagnoser, FlashRunner, Explorer), tools, utils (OCR/XML fusion, UI hierarchy), and data engine.
Integration tests: Add live tool verification, reactive runner, IME, and standalone workflow tests.
E2E tests: Add end-to-end scenario tests for media playback and failure recovery flows.
Fixtures & mocks: Add mock inputs (audio, video, screenshot) and test utilities.
chenmingxuan
somew1nd