test: extend smoke tests for v0.4.0 features and missing API coverage

README.md

@@ -179,9 +179,9 @@ Each demo has automated smoke tests that verify the gateway starts and the REST
 
 ```bash
 # Run smoke tests against a running demo (default: http://localhost:8080)
-./tests/smoke_test.sh              # Sensor diagnostics (21 tests, incl. fault injection)
-./tests/smoke_test_turtlebot3.sh   # TurtleBot3 (entity discovery)
-./tests/smoke_test_moveit.sh       # MoveIt pick-and-place (entity discovery)
+./tests/smoke_test.sh              # Sensor diagnostics (full API coverage + fault injection + beacons)
+./tests/smoke_test_turtlebot3.sh   # TurtleBot3 (discovery, data, operations, scripts, triggers, logs)
+./tests/smoke_test_moveit.sh       # MoveIt pick-and-place (discovery, data, operations, scripts, triggers, logs)
 ```
 
 CI runs all 3 demos in parallel - each job builds the Docker image, starts the container, and runs the smoke tests against it. See [CI workflow](.github/workflows/ci.yml).

tests/smoke_lib.sh

@@ -144,12 +144,23 @@ test_entity_discovery() {
     local entity_type="$1"
     shift
     local entity_ids=("$@")
+    local expected_count=${#entity_ids[@]}
     local label
     label="${entity_type^}"
 
     section "Entity Discovery - ${label}"
 
     if api_get "/${entity_type}"; then
+        # Verify exact count - catches duplicate/synthetic entities leaking through
+        local actual_count
+        actual_count=$(echo "$RESPONSE" | jq '.items | length')
+        if [ "$actual_count" = "$expected_count" ]; then
+            pass "${entity_type} count is ${expected_count}"
+        else
+            local actual_ids
+            actual_ids=$(echo "$RESPONSE" | jq -r '[.items[].id] | sort | join(", ")')
+            fail "${entity_type} count is ${expected_count}" "got ${actual_count}: ${actual_ids}"
+        fi
         for entity_id in "${entity_ids[@]}"; do
             if echo "$RESPONSE" | items_contain_id "$entity_id"; then
                 pass "${entity_type} contains '${entity_id}'"
@@ -162,8 +173,190 @@ test_entity_discovery() {
     fi
 }
 
-# Print test summary and exit with appropriate code
+# Test that procfs introspection data is available for an app
+# Usage: assert_procfs_introspection "lidar-sim"
+assert_procfs_introspection() {
+    local app_id="$1"
+    local endpoint="/apps/${app_id}/x-medkit-procfs"
+    if api_get "$endpoint"; then
+        if echo "$RESPONSE" | jq -e '.pid' > /dev/null 2>&1; then
+            pass "GET ${endpoint} returns procfs data with pid"
+        else
+            fail "GET ${endpoint} returns procfs data with pid" "pid field missing"
+        fi
+    else
+        fail "GET ${endpoint} returns 200" "unexpected status code"
+    fi
+}
+
+# Test that scripts are listed for a component
+# Usage: assert_scripts_list "compute-unit" "run-diagnostics"
+assert_scripts_list() {
+    local component_id="$1"
+    local expected_script="$2"
+    local endpoint="/components/${component_id}/scripts"
+    if api_get "$endpoint"; then
+        if echo "$RESPONSE" | jq -e '.items | length > 0' > /dev/null 2>&1; then
+            pass "GET ${endpoint} returns non-empty items"
+        else
+            fail "GET ${endpoint} returns non-empty items" "items is empty"
+        fi
+        if echo "$RESPONSE" | jq -e --arg s "$expected_script" '.items[] | select(.id == $s)' > /dev/null 2>&1; then
+            pass "scripts contains '${expected_script}'"
+        else
+            fail "scripts contains '${expected_script}'" "not found in response"
+        fi
+    else
+        fail "GET ${endpoint} returns 200" "unexpected status code"
+    fi
+}
+
+# Execute a script and verify it completes
+# Usage: assert_script_execution "compute-unit" "run-diagnostics" [max_wait]
+assert_script_execution() {
+    local component_id="$1"
+    local script_id="$2"
+    local max_wait="${3:-30}"
+    local exec_endpoint="/components/${component_id}/scripts/${script_id}/executions"
+
+    # Start execution
+    local exec_response
+    exec_response=$(curl -s -w "\n%{http_code}" -X POST "${API_BASE}${exec_endpoint}" \
+        -H "Content-Type: application/json" \
+        -d '{"execution_type": "now"}' 2>/dev/null) || true
+    local exec_http
+    exec_http=$(echo "$exec_response" | tail -1)
+    local exec_body
+    exec_body=$(echo "$exec_response" | sed '$d')
+
+    if [ "$exec_http" != "201" ] && [ "$exec_http" != "200" ] && [ "$exec_http" != "202" ]; then
+        fail "POST ${exec_endpoint} starts execution" "got HTTP ${exec_http}"
+        return
+    fi
+    pass "POST ${exec_endpoint} starts execution"
+
+    local exec_id
+    exec_id=$(echo "$exec_body" | jq -r '.id')
+    if [ -z "$exec_id" ] || [ "$exec_id" = "null" ]; then
+        fail "script execution returns valid id" "id is null or empty"
+        return
+    fi
+    pass "script execution returns valid id"
+
+    # Poll until completed
+    echo "  Waiting for script '${script_id}' to complete (max ${max_wait}s)..."
+    local elapsed=0
+    while [ $elapsed -lt "$max_wait" ]; do
+        if api_get "${exec_endpoint}/${exec_id}"; then
+            local status
+            status=$(echo "$RESPONSE" | jq -r '.status')
+            case "$status" in
+                completed)
+                    pass "script '${script_id}' completed successfully"
+                    return
+                    ;;
+                failed|terminated)
+                    fail "script '${script_id}' completed successfully" "status: ${status}"
+                    return
+                    ;;
+            esac
+        fi
+        sleep 1
+        elapsed=$((elapsed + 1))
+    done
+    fail "script '${script_id}' completed successfully" "timed out after ${max_wait}s"
+}
+
+# Test trigger CRUD lifecycle on an entity
+# Usage: assert_triggers_crud "apps" "diagnostic-bridge" "/api/v1/apps/diagnostic-bridge/faults"
+assert_triggers_crud() {
+    local entity_type="$1"
+    local entity_id="$2"
+    local resource_uri="$3"
+    local triggers_endpoint="/${entity_type}/${entity_id}/triggers"
+
+    # Create trigger
+    echo "  Creating OnChange trigger on ${entity_type}/${entity_id}..."
+    local payload
+    payload=$(jq -n --arg resource "$resource_uri" \
+        '{resource: $resource, trigger_condition: {condition_type: "OnChange"}, multishot: true, lifetime: 60}')
+    local create_response
+    create_response=$(curl -s -w "\n%{http_code}" -X POST "${API_BASE}${triggers_endpoint}" \
+        -H "Content-Type: application/json" \
+        -d "$payload" 2>/dev/null) || true
+
+    local create_http
+    create_http=$(echo "$create_response" | tail -1)
+    local create_body
+    create_body=$(echo "$create_response" | sed '$d')
+
+    if [ "$create_http" = "201" ]; then
+        pass "POST ${triggers_endpoint} returns 201"
+    else
+        fail "POST ${triggers_endpoint} returns 201" "got HTTP ${create_http}"
+        return
+    fi
+
+    local trigger_id
+    trigger_id=$(echo "$create_body" | jq -r '.id')
+    if [ -n "$trigger_id" ] && [ "$trigger_id" != "null" ]; then
+        pass "trigger response contains valid id"
+    else
+        fail "trigger response contains valid id" "id is null or empty"
+        return
+    fi
+
+    local trigger_status
+    trigger_status=$(echo "$create_body" | jq -r '.status')
+    if [ "$trigger_status" = "active" ]; then
+        pass "trigger status is 'active'"
+    else
+        fail "trigger status is 'active'" "got '${trigger_status}'"
+    fi
+
+    # List triggers - verify it appears
+    if api_get "${triggers_endpoint}"; then
+        if echo "$RESPONSE" | jq -e --arg id "$trigger_id" '.items[] | select(.id == $id)' > /dev/null 2>&1; then
+            pass "GET ${triggers_endpoint} lists created trigger"
+        else
+            fail "GET ${triggers_endpoint} lists created trigger" "trigger ${trigger_id} not found"
+        fi
+    else
+        fail "GET ${triggers_endpoint} returns 200" "unexpected status code"
+    fi
+
+    # Delete trigger
+    local delete_status
+    delete_status=$(curl -s -o /dev/null -w "%{http_code}" -X DELETE \
+        "${API_BASE}${triggers_endpoint}/${trigger_id}" 2>/dev/null) || true
+
+    if [ "$delete_status" = "204" ]; then
+        pass "DELETE trigger ${trigger_id} returns 204"
+    else
+        fail "DELETE trigger ${trigger_id} returns 204" "got HTTP ${delete_status}"
+    fi
+
+    # Verify trigger is gone
+    if api_get "${triggers_endpoint}"; then
+        if ! echo "$RESPONSE" | jq -e --arg id "$trigger_id" '.items[] | select(.id == $id)' > /dev/null 2>&1; then
+            pass "trigger no longer listed after deletion"
+        else
+            fail "trigger no longer listed after deletion" "still found in list"
+        fi
+    else
+        fail "GET ${triggers_endpoint} returns 200 after delete" "unexpected status code"
+    fi
+}
+
+# Print test summary (called via EXIT trap - do not call exit here)
+SUMMARY_PRINTED=false
 print_summary() {
+    # Guard against double-printing when called as both trap and explicit call
+    if [ "$SUMMARY_PRINTED" = true ]; then
+        return
+    fi
+    SUMMARY_PRINTED=true
+
     echo ""
     echo -e "${BLUE}================================${NC}"
     local total=$((PASS_COUNT + FAIL_COUNT))
@@ -172,7 +365,7 @@ print_summary() {
     if [ "$FAIL_COUNT" -gt 0 ]; then
         echo -e "\n  ${RED}Failed tests:${FAILED_TESTS}${NC}"
         echo -e "${BLUE}================================${NC}"
-        exit 1
+        return
     fi
 
     echo -e "${BLUE}================================${NC}"

tests/smoke_test.sh

@@ -12,6 +12,8 @@ SCRIPT_DIR="$(cd "$(dirname "${BASH_SOURCE[0]}")" && pwd)"
 # shellcheck source=tests/smoke_lib.sh
 source "${SCRIPT_DIR}/smoke_lib.sh"
 
+trap print_summary EXIT
+
 # --- Wait for gateway startup ---
 
 wait_for_gateway 90
@@ -31,9 +33,18 @@ else
     fail "GET /health returns 200" "unexpected status code"
 fi
 
-test_entity_discovery "areas" sensors processing diagnostics
-test_entity_discovery "components" lidar-unit imu-unit gps-unit camera-unit
-test_entity_discovery "apps" lidar-sim imu-sim gps-sim camera-sim anomaly-detector
+test_entity_discovery "areas" sensors processing diagnostics bridge
+test_entity_discovery "components" lidar-unit imu-unit gps-unit camera-unit compute-unit gateway fault-manager diagnostic-bridge-unit
+test_entity_discovery "apps" lidar-sim imu-sim gps-sim camera-sim anomaly-detector medkit-gateway medkit-fault-manager diagnostic-bridge
+test_entity_discovery "functions" sensor-monitoring anomaly-detection fault-management
+
+section "Discovery Relationships"
+
+assert_non_empty_items "/areas/sensors/components"
+
+section "Linux Introspection"
+
+assert_procfs_introspection "lidar-sim"
 
 section "Data Access"
 
@@ -49,6 +60,30 @@ else
     fail "configurations contains 'noise_stddev' parameter" "not found in response"
 fi
 
+section "Operations"
+
+# fault_manager services may take extra time to be discovered via runtime graph introspection
+echo "  Waiting for fault-manager operations to appear (max 30s)..."
+if poll_until "/apps/medkit-fault-manager/operations" '.items | length > 0' 30; then
+    pass "GET /apps/medkit-fault-manager/operations returns non-empty items"
+else
+    fail "GET /apps/medkit-fault-manager/operations returns non-empty items" "items still empty after 30s"
+fi
+
+section "Scripts"
+
+assert_scripts_list "compute-unit" "run-diagnostics"
+assert_script_execution "compute-unit" "run-diagnostics" 30
+
+section "Bulk Data"
+
+# Bulk data endpoint should return 200 with categories list (may be empty without faults)
+if api_get "/apps/diagnostic-bridge/bulk-data"; then
+    pass "GET /apps/diagnostic-bridge/bulk-data returns 200"
+else
+    fail "GET /apps/diagnostic-bridge/bulk-data returns 200" "unexpected status code"
+fi
+
 section "Logs"
 
 assert_non_empty_items "/apps/medkit-gateway/logs"
@@ -116,67 +151,38 @@ fi
 
 section "Triggers"
 
-# Create a trigger on diagnostic-bridge faults
-echo "  Creating OnChange fault trigger..."
-TRIGGER_RESPONSE=$(curl -s -w "\n%{http_code}" -X POST "${API_BASE}/apps/diagnostic-bridge/triggers" \
-    -H "Content-Type: application/json" \
-    -d '{"resource":"/api/v1/apps/diagnostic-bridge/faults","trigger_condition":{"condition_type":"OnChange"},"multishot":true,"lifetime":60}' 2>/dev/null) || true
-
-TRIGGER_HTTP=$(echo "$TRIGGER_RESPONSE" | tail -1)
-TRIGGER_BODY=$(echo "$TRIGGER_RESPONSE" | sed '$d')
-
-if [ "$TRIGGER_HTTP" = "201" ]; then
-    pass "POST /apps/diagnostic-bridge/triggers returns 201"
-else
-    fail "POST /apps/diagnostic-bridge/triggers returns 201" "got HTTP $TRIGGER_HTTP"
-fi
-
-TRIGGER_ID=$(echo "$TRIGGER_BODY" | jq -r '.id')
-if [ -n "$TRIGGER_ID" ] && [ "$TRIGGER_ID" != "null" ]; then
-    pass "trigger response contains valid id"
-else
-    fail "trigger response contains valid id" "id is null or empty"
-fi
-
-TRIGGER_STATUS=$(echo "$TRIGGER_BODY" | jq -r '.status')
-if [ "$TRIGGER_STATUS" = "active" ]; then
-    pass "trigger status is 'active'"
-else
-    fail "trigger status is 'active'" "got '$TRIGGER_STATUS'"
-fi
-
-# List triggers - verify it appears
-if api_get "/apps/diagnostic-bridge/triggers"; then
-    if echo "$RESPONSE" | jq -e --arg id "$TRIGGER_ID" '.items[] | select(.id == $id)' > /dev/null 2>&1; then
-        pass "GET /apps/diagnostic-bridge/triggers lists created trigger"
-    else
-        fail "GET /apps/diagnostic-bridge/triggers lists created trigger" "trigger $TRIGGER_ID not found"
-    fi
-else
-    fail "GET /apps/diagnostic-bridge/triggers returns 200" "unexpected status code"
-fi
-
-# Delete trigger
-TRIGGER_DELETE_STATUS=$(curl -s -o /dev/null -w "%{http_code}" -X DELETE \
-    "${API_BASE}/apps/diagnostic-bridge/triggers/${TRIGGER_ID}" 2>/dev/null) || true
-
-if [ "$TRIGGER_DELETE_STATUS" = "204" ]; then
-    pass "DELETE /apps/diagnostic-bridge/triggers/$TRIGGER_ID returns 204"
-else
-    fail "DELETE /apps/diagnostic-bridge/triggers/$TRIGGER_ID returns 204" "got HTTP $TRIGGER_DELETE_STATUS"
-fi
-
-# Verify trigger is gone
-if api_get "/apps/diagnostic-bridge/triggers"; then
-    if ! echo "$RESPONSE" | jq -e --arg id "$TRIGGER_ID" '.items[] | select(.id == $id)' > /dev/null 2>&1; then
-        pass "trigger no longer listed after deletion"
-    else
-        fail "trigger no longer listed after deletion" "still found in list"
+assert_triggers_crud "apps" "diagnostic-bridge" "/api/v1/apps/diagnostic-bridge/faults"
+
+section "Beacon Discovery"
+
+# Beacon data is exposed at vendor extension endpoints:
+#   /apps/{id}/x-medkit-topic-beacon  (BEACON_MODE=topic)
+#   /apps/{id}/x-medkit-param-beacon  (BEACON_MODE=param)
+# When BEACON_MODE=none (CI default), these endpoints return 404.
+beacon_found=false
+for beacon_type in topic-beacon param-beacon; do
+    if api_get "/apps/lidar-sim/x-medkit-${beacon_type}"; then
+        beacon_found=true
+        pass "GET /apps/lidar-sim/x-medkit-${beacon_type} returns 200"
+        if echo "$RESPONSE" | jq -e '.status' > /dev/null 2>&1; then
+            pass "beacon response contains 'status' field"
+        else
+            fail "beacon response contains 'status' field" "field missing"
+        fi
+        if echo "$RESPONSE" | jq -e '.entity_id' > /dev/null 2>&1; then
+            pass "beacon response contains 'entity_id' field"
+        else
+            fail "beacon response contains 'entity_id' field" "field missing"
+        fi
+        break
     fi
-else
-    fail "GET /apps/diagnostic-bridge/triggers returns 200 after delete" "unexpected status code"
+done
+if [ "$beacon_found" = false ]; then
+    # Not a failure - beacons are optional depending on BEACON_MODE
+    echo -e "  ${BLUE}SKIP${NC} beacon not active (BEACON_MODE=none or plugin not loaded)"
 fi
 
 # --- Summary ---
 
-print_summary
+# print_summary runs via EXIT trap; exit code reflects test results
+[ "$FAIL_COUNT" -eq 0 ]