Autonomous App Walker

Autonomous walker explores bounded portion of web application UI in managed tester VM. Records states, transitions, screenshots, console und network diagnostics, und deduplicated findings. Useful für discovery; kein Nachweis every route or behavior was tested.

Verfügbarkeit: walker data plane, reports, authenticated profiles, bounded mechanical/AI/hybrid/task modes, safety controls und scenario mining implemented. Walk can still miss behavior because of limits, dynamic UI, inaccessible labels, unavailable credentials oder model/parser error. Review coverage before relying on result.

Start safely

Non-production environment und dedicated test account. Tester VM obtain, then start with default mechanical policy:


ensure_tester_vm(app="my-app", app_url="https://staging.example.com")

walk_app(
  app_name="my-app",
  app_url="https://staging.example.com",
  vm_name="<tester-vm>",
  max_states=40,
  max_depth=5,
  max_wall_seconds=600,
  destructive_allowed=false
)

walk_app returns immediately. Keep walk_id, then poll get_app_walk(walk_id=...); call stop_app_walk if run should end early.

Exploration modes

Mode	Behavior
`mechanical`	Bounded DOM-order traversal; no model ranking
`ai`	Model ranks candidate actions, falls back when call cap reached
`hybrid`	Model ranking for first configured states, then mechanical traversal
`cot`	Task-directed search with decision cap und optional output schema

AI und hybrid modes fall back to mechanical when no supported model backend available. Task-directed mode fails instead. Model-ranked actions remain subject to same origin und destructive-action policy.

Safety controls

Destructive actions skipped by default.
destructive_allowed=true permits only guarded class; high-stakes labels remain blocked unless explicitly allowlisted.
Task-directed mode never accepts destructive_allowed=true.
Form filling avoids sensitive fields und blocks transactional submits.
Navigation origin-limited; task mode may add explicit bounded origin allowlist.
Authentication configuration contains secret variable names, not literal credentials. Scenario runner resolves values from owner keystore.

Allowlist ist operator authorization decision. Use narrow literal labels, review target environment, prefer test data discardable.

Reading the result

Completed walk reports what actually observed:

visited UI states und transitions;
screenshots und interactive-element fingerprints;
console und meaningful network errors;
findings with severity, category, evidence und deduplication key; und
configured state, depth, action, time, model und safety limits.

completed means frontier ended or configured limit reached without internal error. Does not mean application passed. Review blocker und major findings, skipped actions, authentication status und coverage totals.

Authenticated walks

Prefer encrypted browser profile when available. Legacy username/password flow accepts only keystore variable names. If sign-in fails or expected post-login content absent, run records authentication failure; interpret walk of login page not as coverage of product.

Turn discovery into regression tests

After reviewing finding, save deterministic app scenario for affected flow. Mined scenario can be low-confidence unless verification checkpoint passed, inspect steps before adopting as release gate.