feat: improve task execution, verification and packaging

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.

README.md

@@ -220,7 +220,7 @@ async def main():
     client = ArtemisClient(
         "http://artemis-host:8000",
         device_serial="emulator-5554",  # optional: target specific device serial
-        default_profile="flash",        # "flash" (fast reactive) or "pro" (deep reasoning)
+        default_profile="flash",  # "flash" (fast reactive) or "pro" (deep reasoning)
     )
 
     result = await client.run(
@@ -273,8 +273,8 @@ Evaluated on [AndroidWorld](https://github.com/google-research/android_world)
 
 ARTEMIS supports two execution profiles tailored for different automation requirements:
 
-* **Flash Profile (`--profile flash`)**: Fast and token-efficient reactive loop (~3–5s per step). Ideal for routine, deterministic UI tasks within 25–30 steps. *Limitations*: Does not support long-term state monitoring, video stream analysis, or multi-step failure self-healing.
-* **Pro Profile (`--profile pro`)**: Our most capable model architecture (~15–40s per step). Powered by a multi-agent graph with planning, visual verification, and automated recovery. Capable of handling 100+ step long-horizon workflows, continuous device state monitoring, and multimedia video analysis.
+* **Flash Profile (`--profile flash`)**: Fast and token-efficient reactive loop (~3–5s per step): one model observes the live screen, thinks, and acts, with no graph orchestration. Ideal for routine, deterministic UI tasks. The loop is unbounded by default (`agent.flash.max_turns`, 0 = unlimited) because history is compressed rather than capped: Flash shares the Pro session transcript ledger (session-relative `T+mm:ss` clock, screenshots folded into visual summaries, older steps chunked into eras and recallable on demand via `recall_history`) and can query the session recording through `video_analyzer`. Transient UI (auto-fading control bars, toasts) is handled by chaining taps into one `click_sequence`. *Limitations*: No task plan or notes, no pre-execution safety net, no checkpoint verification or final report, and no ADB shell.
+* **Pro Profile (`--profile pro`)**: Our most capable architecture (~15–40s per step), built as a multi-agent graph. A **Planner** maintains a living Markdown task plan with milestones and `verify` / `assert` check items; the **Operator** executes it with the full toolset (Explorer grounding whose `flash` / `pro` / `ultra` tier is a user setting per profile — `pro.explorer.mode` / `flash.explorer_mode` in `config/artemis.jsonc` or `--explorer-pro-mode` — never chosen by the agent; notes, history recall, video analysis, ADB diagnostics). Every single action passes a pre-execution **Safety Net** (XML-first, pixel fallback), while multi-action **fast-action bursts** fire back to back to beat turn latency on transient UI. A blocked or failed action opens an **execution incident** that stays in the Operator's context until a later action succeeds, so recovery is handled by the Operator itself with no separate repair agent. A read-only **Checker** verifies plan checkpoints and runs an exit final review against the original goal (`--verification-level`: `off` / `final` (default) / `checkpoints` / `strict`), and plan milestone edits get an advisory review. Handles 100+ step long-horizon workflows, `[Loop:continuous]` monitoring, and an optional written report.
 
 ## Roadmap