@documentation-robotics/cli 0.1.13 → 0.3.0

package/dist/integrations/github_copilot/skills/dr_12_apm_layer/SKILL.md

@@ -13,13 +13,13 @@ triggers:
     "OpenTelemetry",
     "telemetry"
   ]
-version: 0.8.1
+version: 0.8.3
 ---
 
 # APM Layer Skill
 
 **Layer Number:** 11
-**Specification:** Metadata Model Spec v0.8.1
+**Specification:** Metadata Model Spec v0.8.3
 **Purpose:** Defines observability using OpenTelemetry 1.0+, specifying traces, metrics, logs, and instrumentation.
 
 ---
@@ -33,7 +33,7 @@ The APM Layer captures **application performance monitoring**:
 - **LOGS** - Structured logging
 - **INSTRUMENTATION** - Code instrumentation configuration
 - **RESOURCES** - Telemetry resource attributes
-- **SLOs/SLAs** - Service level objectives and agreements
+- **ALERTING** - Alert rules and monitoring dashboards
 
 This layer uses **OpenTelemetry 1.0+** (industry standard for observability).
 
@@ -41,29 +41,93 @@ This layer uses **OpenTelemetry 1.0+** (industry standard for observability).
 
 ---
 
+## Pre-Extraction Verification
+
+Before extracting APM elements, verify what level of observability the codebase ACTUALLY implements. Do not model aspirational instrumentation.
+
+### Step 1: Check for OTel SDK
+
+```bash
+grep "@opentelemetry" package.json
+```
+
+**If NO OTel SDK found:**
+
+- Do NOT add `MetricInstrument`, `Span`, `TraceConfiguration`, or `ExporterConfig` elements as if they are implemented
+- ONLY model what exists: browser console logging (`LogConfiguration`), UI-displayed metrics (describe in element description that export is absent)
+- Mark all elements `provenance: inferred` and add a note in the description: "Metric concept identified; no OTel export implemented."
+
+**If OTel SDK IS found:**
+
+- Proceed with full extraction of all APM types
+
+### Step 2: Identify what observability actually exists
+
+Even without OTel, codebases may have:
+
+- Browser console error logging → `apm.logconfiguration`
+- UI-visible token/usage counters → `apm.metricinstrument` (with note: display-only, not exported)
+- Error tracking utilities → `apm.instrumentationconfig` (type: manual)
+- In-memory state tracking → `apm.metricinstrument` (inferred, note: in-memory only)
+
+### In-UI Observability vs. OTel Instrumentation
+
+| Pattern                         | Model as                                  | provenance |
+| ------------------------------- | ----------------------------------------- | ---------- |
+| `console.error()` logging       | `logconfiguration`                        | extracted  |
+| UI badge showing token count    | `metricinstrument` (note: display-only)   | inferred   |
+| Store tracks reconnection count | `metricinstrument` (note: in-memory only) | inferred   |
+| `opentelemetry.createCounter()` | `metricinstrument`                        | extracted  |
+| Prometheus export endpoint      | `exporterconfig`                          | extracted  |
+
+---
+
 ## Entity Types
 
 > **CLI Introspection:** Run `dr schema types apm` for the authoritative, always-current list of node types.
 > Run `dr schema node <type-id>` for full attribute details on any type.
 
-### Core APM Entities (14 entities)
-
-| Entity Type              | Description                                   |
-| ------------------------ | --------------------------------------------- |
-| **APMConfiguration**     | Root configuration for observability          |
-| **TraceConfiguration**   | Distributed tracing configuration             |
-| **Span**                 | Unit of work in distributed trace             |
-| **SpanEvent**            | Timestamped event within span                 |
-| **MetricConfiguration**  | Metrics collection configuration              |
-| **MeterConfig**          | Meter for metric instruments                  |
-| **InstrumentConfig**     | Metric instrument (counter, gauge, histogram) |
-| **LogConfiguration**     | Structured logging configuration              |
-| **LogRecord**            | Individual log record                         |
-| **Resource**             | Telemetry resource attributes                 |
-| **Attribute**            | Key-value telemetry attribute                 |
-| **InstrumentationScope** | Scope of instrumentation                      |
-| **DataQualityMetric**    | Data quality metrics                          |
-| **DataQualityMetrics**   | Collection of data quality metrics            |
+### Core APM Entities (15 entities)
+
+| Entity Type               | Description                                                       |
+| ------------------------- | ----------------------------------------------------------------- |
+| **TraceConfiguration**    | Distributed tracing configuration                                 |
+| **Span**                  | Unit of work in distributed trace                                 |
+| **SpanEvent**             | Timestamped event within span                                     |
+| **SpanLink**              | Link between spans from different traces                          |
+| **MetricConfiguration**   | Metrics collection configuration                                  |
+| **MetricInstrument**      | Specific metric instrument (Counter, Gauge, Histogram, etc.)      |
+| **LogConfiguration**      | Structured logging configuration                                  |
+| **LogRecord**             | Individual log record                                             |
+| **LogProcessor**          | Log processing pipeline step (simple, batch, custom)              |
+| **Resource**              | Telemetry resource attributes                                     |
+| **InstrumentationScope**  | Scope of instrumentation                                          |
+| **InstrumentationConfig** | Code instrumentation configuration (library, auto/manual type)    |
+| **ExporterConfig**        | Telemetry exporter configuration (OTLP, Jaeger, Prometheus, etc.) |
+| **Alert**                 | Alert rule with severity, condition, and notification channels    |
+| **Dashboard**             | Monitoring dashboard definition (Grafana, Datadog, etc.)          |
+
+---
+
+## Type Decision Tree
+
+Use this decision tree **before assigning a type** to any APM element.
+
+- Is this an alert rule with severity and condition? → `apm.alert`
+- Is this a monitoring dashboard definition (Grafana, Datadog, etc.)? → `apm.dashboard`
+- Is this an exporter configuration (OTLP, Jaeger, Prometheus endpoint)? → `apm.exporterconfig`
+- Is this a code instrumentation configuration (library name, auto/manual)? → `apm.instrumentationconfig`
+- Is this the instrumentation scope (library version, schema URL)? → `apm.instrumentationscope`
+- Is this logging pipeline configuration (service name, minimum severity)? → `apm.logconfiguration`
+- Is this a log processor step (batch, simple, custom)? → `apm.logprocessor`
+- Is this an individual structured log record with body and severity? → `apm.logrecord`
+- Is this a metrics collection configuration (export interval, cardinality limit)? → `apm.metricconfiguration`
+- Is this a specific metric instrument (counter, gauge, histogram, observable)? → `apm.metricinstrument`
+- Is this a telemetry resource (service name, deployment environment attributes)? → `apm.resource`
+- Is this a unit of work/operation in a distributed trace? → `apm.span`
+- Is this an event that occurred within a span? → `apm.spanevent`
+- Is this a link between spans from different traces? → `apm.spanlink`
+- Is this distributed tracing configuration (sampler type, propagators)? → `apm.traceconfiguration`
 
 ---
 
@@ -79,20 +143,65 @@ Activate when the user:
 
 ---
 
-## Cross-Layer Relationships
-
-**Outgoing (APM → Other Layers):**
+## Intra-Layer Relationships
+
+A resource aggregates the instrumentation scopes running in it, and a scope aggregates the spans,
+metric instruments and log records emitted under it. Providers (trace, metric, log configurations)
+depend on their resource and aggregate processors and exporters. Each signal flows through its own
+processors to exporters; signals are correlated by `references`. Only signals and instrumentation
+configurations `monitors` elements in other layers; alerts and dashboards monitor signals.
+
+| Source Type           | Predicate  | Target Type          | Example                                                          |
+| --------------------- | ---------- | -------------------- | ---------------------------------------------------------------- |
+| Span                  | composes   | SpanEvent            | "Process Order" composes "Payment Authorized"                    |
+| Span                  | aggregates | SpanLink             | "Process Order Batch" aggregates "Link To Enqueue Trace"         |
+| SpanLink              | references | Span                 | "Link To Enqueue Trace" references "Enqueue Order"               |
+| Span                  | references | Span                 | "Charge Card" references "Process Order" (parent span)           |
+| Resource              | aggregates | InstrumentationScope | "order-service Resource" aggregates "orders-tracer"              |
+| Span                  | flows-to   | ExporterConfig       | "Process Order" flows-to "OTLP Trace Exporter"                   |
+| InstrumentationScope  | aggregates | LogRecord            | "orders-logger" aggregates "Payment Error Log"                   |
+| MetricInstrument      | flows-to   | ExporterConfig       | "order_rate" flows-to "Prometheus Exporter"                      |
+| LogRecord             | references | Span                 | "Payment Error Log" references "Charge Card"                     |
+| LogRecord             | flows-to   | LogProcessor         | "Payment Error Log" flows-to "PII Redaction Processor"           |
+| LogProcessor          | flows-to   | ExporterConfig       | "PII Redaction Processor" flows-to "OTLP Log Exporter"           |
+| InstrumentationScope  | aggregates | Span                 | "orders-tracer" aggregates "Process Order"                       |
+| InstrumentationScope  | aggregates | MetricInstrument     | "orders-meter" aggregates "order_rate"                           |
+| InstrumentationConfig | references | InstrumentationScope | "Node Auto-Instrumentation" references "express instrumentation" |
+| TraceConfiguration    | depends-on | Resource             | "Order Service Tracing" depends-on "order-service Resource"      |
+| MetricConfiguration   | aggregates | MetricInstrument     | "Order Service Metrics" aggregates "order_rate"                  |
+| LogConfiguration      | aggregates | LogProcessor         | "Order Service Logging" aggregates "PII Redaction Processor"     |
+| Alert                 | monitors   | MetricInstrument     | "High Order Error Rate" monitors "order_errors_total"            |
+| Dashboard             | monitors   | MetricInstrument     | "Order Operations Dashboard" monitors "order_rate"               |
+| Dashboard             | references | Alert                | "Order Operations Dashboard" references "High Order Error Rate"  |
 
-- `instrumented-service` → Application Layer (which service is being monitored?)
-- `business-metrics` → Business Layer (business KPIs)
-
-**Incoming (Other Layers → APM):**
+---
 
-- Application Layer → APM (services reference metrics)
-- API Layer → APM (operations set SLA targets)
-- Business Layer → APM (processes reference business metrics)
-- Data Model Layer → APM (data quality metrics)
-- Data Store Layer → APM (query performance metrics)
+## Cross-Layer References
+
+### Outgoing References (APM → Other Layers)
+
+| Source Type           | Predicate        | Target Type                        | Example                                                        |
+| --------------------- | ---------------- | ---------------------------------- | -------------------------------------------------------------- |
+| Span                  | monitors         | `application.applicationservice`   | "Process Order" monitors "Order Service"                       |
+| Span                  | monitors         | `api.operation`                    | "POST /orders" span monitors "Create Order"                    |
+| Span                  | monitors         | `navigation.route`                 | "Route Change" monitors "Checkout Route"                       |
+| Span                  | monitors         | `data-store.collection`            | "Insert Order" monitors "orders table"                         |
+| MetricInstrument      | monitors         | `api.operation`                    | "http_server_duration" monitors "Create Order"                 |
+| MetricInstrument      | monitors         | `business.businessprocess`         | "order_rate" monitors "Order Fulfillment"                      |
+| MetricInstrument      | monitors         | `data-store.database`              | "db_pool_connections" monitors "Orders Database"               |
+| MetricInstrument      | measures-outcome | `motivation.outcome`               | "order_rate" measures "Higher Order Throughput"                |
+| MetricInstrument      | satisfies        | `motivation.requirement`           | "http_server_duration" satisfies "p95 Latency Under 300ms"     |
+| Resource              | maps-to          | `application.applicationcomponent` | "order-service Resource" maps-to "Order Service Component"     |
+| Resource              | references       | `technology.node`                  | "order-service Resource" references "EKS Production Cluster"   |
+| InstrumentationConfig | monitors         | `application.applicationcomponent` | "Node Auto-Instrumentation" monitors "Order Service Component" |
+| LogConfiguration      | satisfies        | `security.auditconfig`             | "Order Service Logging" satisfies "Order Audit Logging"        |
+
+### Incoming References (Other Layers → APM)
+
+| Source Type                      | Predicate  | Target Type        | Example                                            |
+| -------------------------------- | ---------- | ------------------ | -------------------------------------------------- |
+| `application.applicationservice` | references | TraceConfiguration | "Order Service" references "Order Service Tracing" |
+| `testing.testcasesketch`         | tests      | MetricInstrument   | "Order Counter Increments" tests "order_rate"      |
 
 ---
 
@@ -113,22 +222,22 @@ Activate when the user:
 
 ```bash
 # Add span
-dr add apm span --name "Process Order"
+dr add apm span "Process Order"
 
-# Add metric
-dr add apm instrument-config --name "order_rate" --property type=counter
+# Add metric instrument
+dr add apm metricinstrument "order_rate" --description "Order processing rate counter"
 
 # Add log record
-dr add apm log-record --name "Error Log"
+dr add apm logrecord "Error Log"
 
 # List APM elements
-dr list apm span
+dr list apm --type span
 
 # Validate APM layer
-dr validate --layer apm
+dr validate --layers apm
 
 # Export APM configuration
-dr export --layer apm --format json
+dr export markdown --layers apm
 ```
 
 ---
@@ -140,28 +249,21 @@ id: apm.span.process-order
 name: "Process Order Span"
 type: span
 properties:
+  traceId: "4bf92f3577b34da6a3ce929d0e0e4736"
+  spanId: "00f067aa0ba902b7"
+  traceState: ""
+  parentSpanId: "b9c7c989f97918e1"
   spanKind: INTERNAL
-  operationName: process_order
+  startTimeUnixNano: "1544712660000000000"
+  endTimeUnixNano: "1544712661000000000"
+  droppedAttributesCount: 0
+  droppedEventsCount: 0
+  droppedLinksCount: 0
+  statusCode: OK
   attributes:
-    - key: order.id
-      type: string
-    - key: order.total
-      type: double
-    - key: customer.id
-      type: string
-  events:
-    - name: order_validated
-      timestamp: relative
-    - name: payment_processed
-      timestamp: relative
-    - name: inventory_reserved
-      timestamp: relative
-  instrumented-service: application.service.order-processing
-  business-metrics:
-    - apm.metric.orders-processed
-    - apm.metric.order-processing-time
-  sla-target-latency: 500ms
-  sla-target-availability: 99.9%
+    order.id: "ord-12345"
+    order.total: 99.99
+    customer.id: "cust-67890"
 ```
 
 ---
@@ -169,58 +271,40 @@ properties:
 ## Example: Business Metrics
 
 ```yaml
-id: apm.metric.order-rate
+id: apm.metricinstrument.order-rate
 name: "Order Rate Metric"
-type: instrument-config
+type: metricinstrument
 properties:
-  instrumentType: counter
+  type: Counter
   unit: orders
-  description: "Number of orders processed"
-  attributes:
-    - key: order.type
-      type: string
-      values: [standard, express, subscription]
-    - key: payment.method
-      type: string
-      values: [credit_card, paypal, bank_transfer]
-  business-context:
-    kpi: true
-    dashboard: revenue-dashboard
-    alerts:
-      - threshold: 100
-        condition: less-than
-        severity: warning
-        message: "Order rate below threshold"
+  description: "Number of orders processed per minute"
+  enabled: true
 ```
 
 ---
 
-## Example: Data Quality Metrics
-
-```yaml
-id: apm.data-quality-metrics.user-data
-name: "User Data Quality Metrics"
-type: data-quality-metrics
-properties:
-  entity: data_model.object-schema.user
-  metrics:
-    - name: completeness
-      type: gauge
-      description: "Percentage of non-null required fields"
-      target: 95%
-    - name: validity
-      type: gauge
-      description: "Percentage of records passing validation"
-      target: 99%
-    - name: uniqueness
-      type: gauge
-      description: "Percentage of unique email addresses"
-      target: 100%
-    - name: freshness
-      type: histogram
-      description: "Time since last update"
-      target: 24h
-```
+## Coverage Completeness Checklist
+
+Before declaring APM layer extraction complete, verify each type was considered:
+
+- [ ] `apm.alert` — Alert rule with severity and notification channels
+- [ ] `apm.dashboard` — Monitoring dashboard (Grafana, Datadog, etc.)
+- [ ] `apm.exporterconfig` — Telemetry exporter configuration (OTLP, Prometheus, etc.)
+- [ ] `apm.instrumentationconfig` — Code instrumentation configuration
+- [ ] `apm.instrumentationscope` — Instrumentation scope (library version and schema URL)
+- [ ] `apm.logconfiguration` — Logging configuration per service
+- [ ] `apm.logprocessor` — Log processing pipeline step
+- [ ] `apm.logrecord` — Individual structured log record
+- [ ] `apm.metricconfiguration` — Metrics collection configuration per service
+- [ ] `apm.metricinstrument` — Specific metric instrument (Counter, Gauge, Histogram, etc.)
+- [ ] `apm.resource` — Telemetry resource attributes (service name, environment)
+- [ ] `apm.span` — Unit of work in a distributed trace
+- [ ] `apm.spanevent` — Timestamped event within a span
+- [ ] `apm.spanlink` — Link between spans from different traces
+- [ ] `apm.traceconfiguration` — Distributed tracing configuration
+
+If any type has ZERO elements, explicitly decide:
+"This type doesn't apply to this codebase" with reasoning.
 
 ---