| name | morphy-ax |
| description | Use when changing Morphy AX shared agent-experience state, semantic assessment presentation, performance budgets, or cross-modal compatibility. |
Morphy AX
Purpose and Trigger
- Primary scope:
morphy-agent-experience
- Trigger on Morphy AX snapshots, active interaction layers, presentation derivation, semantic-assessment validation, compatibility projections, or AX performance budgets.
- Avoid overlap with
frontend-design-system, kai-voice-governance, and backend-agents-operons.
Coverage and Ownership
- Role:
spoke
- Owner family:
frontend
Owned repo surfaces:
hushh-webapp/lib/morphy-ax
docs/reference/quality/morphy-agent-experience.md
Non-owned surfaces:
hushh-webapp/lib/voice
consent-protocol/hushh_mcp/agents
hushh-webapp/lib/morphy-ux
Do Use
- Shared, redacted agent-experience snapshot, active-layer composition, and presentation contracts.
- Intelligence-assessment validation and compatibility/non-regression budgets.
- Cross-modal AX behavior that reuses the existing runtime owner and action gateway.
Do Not Use
- Voice action authoring, generated gateway changes, or ADK orchestration ownership.
- Visual primitive work owned by Morphy UX.
- A second React provider, store, router, action registry, DOM observer, or model-facing route tool.
Read First
docs/reference/quality/design.md
docs/reference/quality/morphy-agent-experience.md
docs/reference/one/one-voice-runtime-architecture.md
docs/reference/quality/frontend-ui-architecture-map.md
docs/reference/kai/kai-action-gateway-vnext.md
Workflow
- Verify the existing runtime, voice FSM, route playbook, and generated action authority before changing AX.
- Keep Morphy AX pure, redacted, memoizable, and hosted by
AgentRuntimeStateProvider.
- Let intelligence assess meaning; deterministic code may validate, reject, normalize, and enforce authority only.
- Compose authored
route, chrome, and interaction_layer publishers; expose only the top effective inventory and remove stale owner leases on route change.
- Require exact generated dismiss/cancel actions, focus-restored settlement, and declared Agent continuity; never synthesize click or Escape behavior.
- Treat
trusted_activation_required browser actions as exact Agent Bar continuations over mounted handlers, not redirect or popup-broker fallbacks.
- Preserve
OneVoiceContextSnapshot through an explicit compatibility projection while migration is active.
- Benchmark the same fixtures flag-off and flag-on; block wrong-layer actions, unsafe fallbacks, or budget regressions.
- Route voice, backend-agent, design-system, docs, or quality changes to their owning skills.
Handoff Rules
- Broad frontend work routes to
frontend.
- Voice/action contracts route to
kai-voice-governance.
- ADK or product-agent changes route to
backend-agents-operons.
- Visual primitives route to
frontend-design-system; verification policy routes to quality-contracts.
Required Checks
cd hushh-webapp && npm run verify:morphy-ax
cd hushh-webapp && npm run typecheck
cd hushh-webapp && npm run verify:voice-gateway
cd hushh-webapp && npm run verify:design-system
cd consent-protocol && python3 -m pytest tests/test_onboarding_goal_agent.py tests/test_one_adk_agent_tree.py -q
./bin/hushh docs verify