Steward runtime text-input capability packet - 2026-06-10
Status: proposed adoption-run/v2 proof, not yet a passing runtime claim · Audience: maintainers and agents
Claim to prove
A fresh agent can use Flutter MCP Toolkit against the running flutter_test_app to discover the greeting field, enter text through the interaction tool, and prove runtime state changed.
This is the next harder Skill Steward adoption slice after the hosted dependency cutover gate because it exercises a live MCP/runtime path:
launch app -> discover VM service -> semantic_snapshot -> enter_text -> evaluate_dart_expression
It does not claim all interaction tools, fill_form, web/mobile parity, production app behavior, WebMCP dogfood, or broad repo H5 maturity.
Adoption-run/v2 classification
| Field | Value |
|---|---|
| Capability id | mcp_flutter.runtime.enter-text-greeting |
| Capability class | mcp_tool_runtime |
| Scope | adoption_run until runtime evidence passes; capability_level only after reviewed proof |
| User goal | Prove a real MCP toolkit interaction can fill a Flutter text input and verify state |
| Acceptance check | AgentState.instance.greeting equals the submitted text after enter_text |
| Native owner | flutter_test_app, flutter-mcp-toolkit, interaction command catalog, and flutter-mcp-toolkit-control skill |
| Review outcomes | continue, refactor, stop, abandon, or promote |
Target surface
Known target:
flutter_test_app/lib/showcase_screen.dartwraps the field with semantics identifiergreeting_input_field.semantic_snapshotshould return a ref for that field.enter_textshould submitsteward runtime proof.evaluate_dart_expression("AgentState.instance.greeting")should return the submitted text.flutter_test_app/lib/agent_state.dartowns the assertion state.
Use enter_text for this one-field proof. Reserve fill_form for a later batch-form capability proof.
Acceptance sequence
Run from this checkout:
cd flutter_test_app
flutter run --debug --machine --host-vmservice-port=8181 -d macos
Use the emitted app.debugPort.wsUri as $WS.
flutter-mcp-toolkit doctor --vm-service-uri "$WS" --json
flutter-mcp-toolkit exec --name semantic_snapshot \
--args "{\"connection\":{\"targetId\":\"$WS\"}}"
Find the node with semantics identifier greeting_input_field, capture its ref and snapshotId, then run:
flutter-mcp-toolkit exec --name enter_text \
--args "{\"ref\":\"<ref>\",\"snapshotId\":<snapshotId>,\"text\":\"steward runtime proof\",\"connection\":{\"targetId\":\"$WS\"}}"
flutter-mcp-toolkit exec --name evaluate_dart_expression \
--args "{\"expression\":\"AgentState.instance.greeting\",\"connection\":{\"targetId\":\"$WS\"}}"
The proof passes only when the final expression returns exactly steward runtime proof.
Detour budget
- If the field ref is stale, call
semantic_snapshotagain and retry once. - If app launch or VM service connection fails after two setup attempts, stop restoration and record an unknown case.
- Do not add a new MCP tool in this adoption run unless the existing toolkit path is proven unable to satisfy the acceptance check.
- If direct Dart expression can set the state but
enter_textfails, record fallback evidence only; that does not prove text-input interaction.
Promotion requirements
Promote to capability-level H5 only after:
- A clean runtime run proves
doctor,semantic_snapshot,enter_text, andevaluate_dart_expression. - Evidence records platform, VM service URI provenance, subject commit, and dirty state.
- The proof selects the field by semantics identifier, not by whichever ref appears first.
- A falsifier exists, such as asserting the expression is not the target value before entry or proving a wrong ref does not satisfy the acceptance check.
- A future-agent or held-out run repeats the path without hidden local context.