@smthrs/observability 0.34.0 → 1.0.0-rc.3

package/grafana/dashboards/smithers-dashboard.json

@@ -1,453 +0,0 @@
-{
-  "uid": "smithers-overview",
-  "title": "Smithers Overview",
-  "tags": ["smithers", "ai", "orchestration"],
-  "timezone": "browser",
-  "schemaVersion": 39,
-  "version": 1,
-  "refresh": "10s",
-  "time": { "from": "now-1h", "to": "now" },
-  "editable": true,
-  "panels": [
-    {
-      "type": "row",
-      "title": "Overview",
-      "collapsed": false,
-      "gridPos": { "h": 1, "w": 24, "x": 0, "y": 0 },
-      "id": 1
-    },
-    {
-      "type": "stat",
-      "title": "Active Runs",
-      "id": 2,
-      "gridPos": { "h": 4, "w": 4, "x": 0, "y": 1 },
-      "datasource": { "type": "prometheus", "uid": "prometheus" },
-      "targets": [{ "expr": "smithers_smithers_runs_active", "refId": "A" }],
-      "fieldConfig": {
-        "defaults": {
-          "thresholds": {
-            "mode": "absolute",
-            "steps": [
-              { "color": "green", "value": null },
-              { "color": "yellow", "value": 5 },
-              { "color": "red", "value": 10 }
-            ]
-          },
-          "color": { "mode": "thresholds" }
-        }
-      },
-      "options": {
-        "reduceOptions": { "calcs": ["lastNotNull"] },
-        "colorMode": "background",
-        "graphMode": "area"
-      }
-    },
-    {
-      "type": "stat",
-      "title": "Total Runs",
-      "id": 3,
-      "gridPos": { "h": 4, "w": 4, "x": 4, "y": 1 },
-      "datasource": { "type": "prometheus", "uid": "prometheus" },
-      "targets": [{ "expr": "smithers_smithers_runs_total", "refId": "A" }],
-      "fieldConfig": { "defaults": { "color": { "mode": "fixed", "fixedColor": "blue" } } },
-      "options": {
-        "reduceOptions": { "calcs": ["lastNotNull"] },
-        "colorMode": "value",
-        "graphMode": "area"
-      }
-    },
-    {
-      "type": "stat",
-      "title": "Active Nodes",
-      "id": 4,
-      "gridPos": { "h": 4, "w": 4, "x": 8, "y": 1 },
-      "datasource": { "type": "prometheus", "uid": "prometheus" },
-      "targets": [{ "expr": "smithers_smithers_nodes_active", "refId": "A" }],
-      "fieldConfig": {
-        "defaults": {
-          "thresholds": {
-            "mode": "absolute",
-            "steps": [
-              { "color": "green", "value": null },
-              { "color": "yellow", "value": 10 },
-              { "color": "red", "value": 20 }
-            ]
-          },
-          "color": { "mode": "thresholds" }
-        }
-      },
-      "options": {
-        "reduceOptions": { "calcs": ["lastNotNull"] },
-        "colorMode": "background",
-        "graphMode": "area"
-      }
-    },
-    {
-      "type": "stat",
-      "title": "Node Success Rate",
-      "id": 5,
-      "gridPos": { "h": 4, "w": 4, "x": 12, "y": 1 },
-      "datasource": { "type": "prometheus", "uid": "prometheus" },
-      "targets": [{
-        "expr": "(smithers_smithers_nodes_finished / (smithers_smithers_nodes_finished + smithers_smithers_nodes_failed > 0)) * 100 or vector(100)",
-        "refId": "A"
-      }],
-      "fieldConfig": {
-        "defaults": {
-          "unit": "percent",
-          "thresholds": {
-            "mode": "absolute",
-            "steps": [
-              { "color": "red", "value": null },
-              { "color": "yellow", "value": 90 },
-              { "color": "green", "value": 99 }
-            ]
-          },
-          "color": { "mode": "thresholds" },
-          "min": 0,
-          "max": 100
-        }
-      },
-      "options": {
-        "reduceOptions": { "calcs": ["lastNotNull"] },
-        "colorMode": "background",
-        "graphMode": "none"
-      }
-    },
-    {
-      "type": "stat",
-      "title": "Cache Hit Rate",
-      "id": 6,
-      "gridPos": { "h": 4, "w": 4, "x": 16, "y": 1 },
-      "datasource": { "type": "prometheus", "uid": "prometheus" },
-      "targets": [{
-        "expr": "(smithers_smithers_cache_hits / (smithers_smithers_cache_hits + smithers_smithers_cache_misses > 0)) * 100 or vector(0)",
-        "refId": "A"
-      }],
-      "fieldConfig": {
-        "defaults": {
-          "unit": "percent",
-          "thresholds": {
-            "mode": "absolute",
-            "steps": [
-              { "color": "red", "value": null },
-              { "color": "yellow", "value": 30 },
-              { "color": "green", "value": 70 }
-            ]
-          },
-          "color": { "mode": "thresholds" },
-          "min": 0,
-          "max": 100
-        }
-      },
-      "options": {
-        "reduceOptions": { "calcs": ["lastNotNull"] },
-        "colorMode": "background",
-        "graphMode": "none"
-      }
-    },
-    {
-      "type": "stat",
-      "title": "DB Retries",
-      "id": 7,
-      "gridPos": { "h": 4, "w": 4, "x": 20, "y": 1 },
-      "datasource": { "type": "prometheus", "uid": "prometheus" },
-      "targets": [{ "expr": "smithers_smithers_db_retries", "refId": "A" }],
-      "fieldConfig": {
-        "defaults": {
-          "thresholds": {
-            "mode": "absolute",
-            "steps": [
-              { "color": "green", "value": null },
-              { "color": "yellow", "value": 5 },
-              { "color": "red", "value": 20 }
-            ]
-          },
-          "color": { "mode": "thresholds" }
-        }
-      },
-      "options": {
-        "reduceOptions": { "calcs": ["lastNotNull"] },
-        "colorMode": "value",
-        "graphMode": "area"
-      }
-    },
-
-    {
-      "type": "row",
-      "title": "Runs & Nodes",
-      "collapsed": false,
-      "gridPos": { "h": 1, "w": 24, "x": 0, "y": 5 },
-      "id": 10
-    },
-    {
-      "type": "timeseries",
-      "title": "Node Throughput",
-      "id": 11,
-      "gridPos": { "h": 8, "w": 12, "x": 0, "y": 6 },
-      "datasource": { "type": "prometheus", "uid": "prometheus" },
-      "targets": [
-        { "expr": "rate(smithers_smithers_nodes_started[5m])", "legendFormat": "Started", "refId": "A" },
-        { "expr": "rate(smithers_smithers_nodes_finished[5m])", "legendFormat": "Finished", "refId": "B" },
-        { "expr": "rate(smithers_smithers_nodes_failed[5m])", "legendFormat": "Failed", "refId": "C" }
-      ],
-      "fieldConfig": {
-        "defaults": {
-          "custom": { "drawStyle": "line", "lineWidth": 2, "fillOpacity": 10, "gradientMode": "scheme" },
-          "color": { "mode": "palette-classic" },
-          "unit": "ops"
-        }
-      },
-      "options": {
-        "tooltip": { "mode": "multi", "sort": "desc" },
-        "legend": { "displayMode": "list", "placement": "bottom", "calcs": ["mean", "max"] }
-      }
-    },
-    {
-      "type": "heatmap",
-      "title": "Node Duration",
-      "id": 12,
-      "gridPos": { "h": 8, "w": 12, "x": 12, "y": 6 },
-      "datasource": { "type": "prometheus", "uid": "prometheus" },
-      "targets": [{
-        "expr": "sum(increase(smithers_smithers_node_duration_ms_bucket[5m])) by (le)",
-        "legendFormat": "{{le}}",
-        "refId": "A",
-        "format": "heatmap"
-      }],
-      "options": {
-        "calculate": false,
-        "yAxis": { "unit": "ms" },
-        "color": { "mode": "scheme", "scheme": "Oranges", "steps": 64 },
-        "cellGap": 1
-      }
-    },
-
-    {
-      "type": "row",
-      "title": "Tools",
-      "collapsed": false,
-      "gridPos": { "h": 1, "w": 24, "x": 0, "y": 14 },
-      "id": 20
-    },
-    {
-      "type": "timeseries",
-      "title": "Tool Call Rate",
-      "id": 21,
-      "gridPos": { "h": 8, "w": 12, "x": 0, "y": 15 },
-      "datasource": { "type": "prometheus", "uid": "prometheus" },
-      "targets": [{
-        "expr": "rate(smithers_smithers_tool_calls_total[5m])",
-        "legendFormat": "Tool Calls / sec",
-        "refId": "A"
-      }],
-      "fieldConfig": {
-        "defaults": {
-          "custom": { "drawStyle": "line", "lineWidth": 2, "fillOpacity": 10 },
-          "color": { "mode": "fixed", "fixedColor": "purple" },
-          "unit": "ops"
-        }
-      },
-      "options": {
-        "tooltip": { "mode": "single" },
-        "legend": { "displayMode": "list", "placement": "bottom" }
-      }
-    },
-    {
-      "type": "heatmap",
-      "title": "Tool Duration",
-      "id": 22,
-      "gridPos": { "h": 8, "w": 12, "x": 12, "y": 15 },
-      "datasource": { "type": "prometheus", "uid": "prometheus" },
-      "targets": [{
-        "expr": "sum(increase(smithers_smithers_tool_duration_ms_bucket[5m])) by (le)",
-        "legendFormat": "{{le}}",
-        "refId": "A",
-        "format": "heatmap"
-      }],
-      "options": {
-        "calculate": false,
-        "yAxis": { "unit": "ms" },
-        "color": { "mode": "scheme", "scheme": "Blues", "steps": 64 },
-        "cellGap": 1
-      }
-    },
-
-    {
-      "type": "row",
-      "title": "Infrastructure",
-      "collapsed": false,
-      "gridPos": { "h": 1, "w": 24, "x": 0, "y": 23 },
-      "id": 30
-    },
-    {
-      "type": "timeseries",
-      "title": "HTTP Request Latency",
-      "id": 31,
-      "gridPos": { "h": 8, "w": 8, "x": 0, "y": 24 },
-      "datasource": { "type": "prometheus", "uid": "prometheus" },
-      "targets": [
-        {
-          "expr": "histogram_quantile(0.50, sum(rate(smithers_smithers_http_request_duration_ms_bucket[5m])) by (le))",
-          "legendFormat": "p50",
-          "refId": "A"
-        },
-        {
-          "expr": "histogram_quantile(0.95, sum(rate(smithers_smithers_http_request_duration_ms_bucket[5m])) by (le))",
-          "legendFormat": "p95",
-          "refId": "B"
-        },
-        {
-          "expr": "histogram_quantile(0.99, sum(rate(smithers_smithers_http_request_duration_ms_bucket[5m])) by (le))",
-          "legendFormat": "p99",
-          "refId": "C"
-        }
-      ],
-      "fieldConfig": {
-        "defaults": {
-          "custom": { "drawStyle": "line", "lineWidth": 2, "fillOpacity": 5 },
-          "color": { "mode": "palette-classic" },
-          "unit": "ms"
-        }
-      },
-      "options": {
-        "tooltip": { "mode": "multi", "sort": "desc" },
-        "legend": { "displayMode": "list", "placement": "bottom" }
-      }
-    },
-    {
-      "type": "heatmap",
-      "title": "DB Query Duration",
-      "id": 32,
-      "gridPos": { "h": 8, "w": 8, "x": 8, "y": 24 },
-      "datasource": { "type": "prometheus", "uid": "prometheus" },
-      "targets": [{
-        "expr": "sum(increase(smithers_smithers_db_query_ms_bucket[5m])) by (le)",
-        "legendFormat": "{{le}}",
-        "refId": "A",
-        "format": "heatmap"
-      }],
-      "options": {
-        "calculate": false,
-        "yAxis": { "unit": "ms" },
-        "color": { "mode": "scheme", "scheme": "Greens", "steps": 64 },
-        "cellGap": 1
-      }
-    },
-    {
-      "type": "timeseries",
-      "title": "VCS & Hot Reload",
-      "id": 33,
-      "gridPos": { "h": 8, "w": 8, "x": 16, "y": 24 },
-      "datasource": { "type": "prometheus", "uid": "prometheus" },
-      "targets": [
-        {
-          "expr": "rate(smithers_smithers_hot_reloads[5m])",
-          "legendFormat": "Hot Reloads / sec",
-          "refId": "A"
-        },
-        {
-          "expr": "rate(smithers_smithers_hot_reload_failures[5m])",
-          "legendFormat": "Reload Failures / sec",
-          "refId": "B"
-        },
-        {
-          "expr": "histogram_quantile(0.95, sum(rate(smithers_smithers_vcs_duration_ms_bucket[5m])) by (le))",
-          "legendFormat": "VCS p95 (ms)",
-          "refId": "C"
-        }
-      ],
-      "fieldConfig": {
-        "defaults": {
-          "custom": { "drawStyle": "line", "lineWidth": 2, "fillOpacity": 10 },
-          "color": { "mode": "palette-classic" }
-        }
-      },
-      "options": {
-        "tooltip": { "mode": "multi", "sort": "desc" },
-        "legend": { "displayMode": "list", "placement": "bottom" }
-      }
-    },
-
-    {
-      "type": "row",
-      "title": "Approvals",
-      "collapsed": false,
-      "gridPos": { "h": 1, "w": 24, "x": 0, "y": 32 },
-      "id": 40
-    },
-    {
-      "type": "timeseries",
-      "title": "Approval Flow",
-      "id": 41,
-      "gridPos": { "h": 8, "w": 12, "x": 0, "y": 33 },
-      "datasource": { "type": "prometheus", "uid": "prometheus" },
-      "targets": [
-        { "expr": "rate(smithers_smithers_approvals_requested[5m])", "legendFormat": "Requested", "refId": "A" },
-        { "expr": "rate(smithers_smithers_approvals_granted[5m])", "legendFormat": "Granted", "refId": "B" },
-        { "expr": "rate(smithers_smithers_approvals_denied[5m])", "legendFormat": "Denied", "refId": "C" }
-      ],
-      "fieldConfig": {
-        "defaults": {
-          "custom": { "drawStyle": "bars", "lineWidth": 1, "fillOpacity": 50 },
-          "color": { "mode": "palette-classic" },
-          "unit": "ops"
-        }
-      },
-      "options": {
-        "tooltip": { "mode": "multi" },
-        "legend": { "displayMode": "list", "placement": "bottom" }
-      }
-    },
-    {
-      "type": "timeseries",
-      "title": "HTTP Request Rate",
-      "id": 42,
-      "gridPos": { "h": 8, "w": 12, "x": 12, "y": 33 },
-      "datasource": { "type": "prometheus", "uid": "prometheus" },
-      "targets": [{
-        "expr": "rate(smithers_smithers_http_requests[5m])",
-        "legendFormat": "Requests / sec",
-        "refId": "A"
-      }],
-      "fieldConfig": {
-        "defaults": {
-          "custom": { "drawStyle": "line", "lineWidth": 2, "fillOpacity": 15, "gradientMode": "scheme" },
-          "color": { "mode": "fixed", "fixedColor": "green" },
-          "unit": "reqps"
-        }
-      },
-      "options": {
-        "tooltip": { "mode": "single" },
-        "legend": { "displayMode": "list", "placement": "bottom" }
-      }
-    },
-
-    {
-      "type": "row",
-      "title": "Traces",
-      "collapsed": true,
-      "gridPos": { "h": 1, "w": 24, "x": 0, "y": 41 },
-      "id": 50,
-      "panels": [
-        {
-          "type": "traces",
-          "title": "Recent Traces",
-          "id": 51,
-          "gridPos": { "h": 12, "w": 24, "x": 0, "y": 42 },
-          "datasource": { "type": "tempo", "uid": "tempo" },
-          "targets": [{
-            "datasource": { "type": "tempo", "uid": "tempo" },
-            "queryType": "traceqlSearch",
-            "limit": 20,
-            "tableType": "traces",
-            "filters": [
-              { "id": "service-name", "tag": "service.name", "operator": "=", "value": ["smithers"], "scope": "resource" }
-            ],
-            "refId": "A"
-          }]
-        }
-      ]
-    }
-  ]
-}

package/grafana/provisioning/dashboards/dashboards.yml

@@ -1,12 +0,0 @@
-apiVersion: 1
-
-providers:
-  - name: default
-    orgId: 1
-    folder: ""
-    type: file
-    disableDeletion: false
-    updateIntervalSeconds: 30
-    allowUiUpdates: true
-    options:
-      path: /var/lib/grafana/dashboards

package/grafana/provisioning/datasources/datasources.yml

@@ -1,49 +0,0 @@
-apiVersion: 1
-
-datasources:
-  - name: Prometheus
-    type: prometheus
-    uid: prometheus
-    access: proxy
-    url: http://prometheus:9090
-    isDefault: true
-    editable: false
-    jsonData:
-      httpMethod: POST
-      exemplarTraceIdDestinations:
-        - name: traceID
-          datasourceUid: tempo
-
-  - name: Loki
-    type: loki
-    uid: loki
-    access: proxy
-    url: http://loki:3100
-    editable: false
-    jsonData:
-      maxLines: 1000
-
-  - name: Tempo
-    type: tempo
-    uid: tempo
-    access: proxy
-    url: http://tempo:3200
-    editable: false
-    jsonData:
-      tracesToLogs:
-        datasourceUid: loki
-        tags: ["service.name"]
-        mappedTags:
-          - key: service.name
-            value: service.name
-        mapTagNamesEnabled: false
-        spanStartTimeShift: "-1h"
-        spanEndTimeShift: "1h"
-        filterByTraceID: false
-        filterBySpanID: false
-      tracesToMetrics:
-        datasourceUid: prometheus
-        spanStartTimeShift: "-1h"
-        spanEndTimeShift: "1h"
-      nodeGraph:
-        enabled: true

package/loki/loki-config.yaml

@@ -1,35 +0,0 @@
-auth_enabled: false
-
-server:
-  http_listen_port: 3100
-
-common:
-  instance_addr: 127.0.0.1
-  path_prefix: /loki
-  storage:
-    filesystem:
-      chunks_directory: /loki/chunks
-      rules_directory: /loki/rules
-  replication_factor: 1
-  ring:
-    kvstore:
-      store: inmemory
-
-schema_config:
-  configs:
-    - from: 2020-10-24
-      store: tsdb
-      object_store: filesystem
-      schema: v13
-      index:
-        prefix: index_
-        period: 24h
-
-limits_config:
-  allow_structured_metadata: true
-
-ruler:
-  alertmanager_url: http://localhost:9093
-
-analytics:
-  reporting_enabled: false

package/otel-collector-config.yml

@@ -1,38 +0,0 @@
-receivers:
-  otlp:
-    protocols:
-      grpc:
-        endpoint: "0.0.0.0:4317"
-      http:
-        endpoint: "0.0.0.0:4318"
-
-exporters:
-  prometheus:
-    endpoint: "0.0.0.0:8889"
-    namespace: smithers
-  otlp_grpc/tempo:
-    endpoint: "tempo:4317"
-    tls:
-      insecure: true
-  otlp_http/loki:
-    endpoint: "http://loki:3100/otlp"
-
-processors:
-  batch:
-    timeout: 5s
-    send_batch_size: 1024
-
-service:
-  pipelines:
-    metrics:
-      receivers: [otlp]
-      processors: [batch]
-      exporters: [prometheus]
-    traces:
-      receivers: [otlp]
-      processors: [batch]
-      exporters: [otlp_grpc/tempo]
-    logs:
-      receivers: [otlp]
-      processors: [batch]
-      exporters: [otlp_http/loki]

package/prometheus/prometheus.yml

@@ -1,8 +0,0 @@
-global:
-  scrape_interval: 15s
-  evaluation_interval: 15s
-
-scrape_configs:
-  - job_name: "otel-collector"
-    static_configs:
-      - targets: ["otel-collector:8889"]

package/src/MetricName.ts

@@ -1 +0,0 @@
-export type MetricName = string;

package/src/MetricsServiceLive.js

@@ -1,9 +0,0 @@
-import { MetricsService } from "./_coreMetrics.js";
-import { Effect, Layer } from "effect";
-import { metricsServiceAdapter } from "./metrics/index.js";
-import { renderPrometheusMetrics } from "./renderPrometheusMetrics.js";
-/** @type {Layer.Layer<MetricsService, never, never>} */
-export const MetricsServiceLive = Layer.succeed(MetricsService, {
-  ...metricsServiceAdapter,
-  renderPrometheus: () => Effect.sync(renderPrometheusMetrics),
-});

package/src/README.md

@@ -1,28 +0,0 @@
-# @smthrs/observability — src
-
-The concrete observability implementation: Effect-based metrics, logging, and
-tracing services, OTLP layer wiring (`createSmithersObservabilityLayer`,
-`createSmithersOtelLayer`, `createSmithersRuntimeLayer`), the agent-trace
-pipeline (`detectAgentFamily`, `detectCaptureMode`, `_traceEventNormalizers`,
-`_traceRedaction`, the `*ToOtelLogRecord` builders, `_sessionFileResolvers`),
-and Prometheus text rendering.
-
-Conventions: one export per file, with type-only `.ts` sidecars next to the
-`.js` implementations. `package.json` exposes a `./*` wildcard onto `src/`, so
-EVERY file here is an importable public subpath — `packages/engine` imports the
-underscore modules directly (e.g. `observability/_traceEventNormalizers`). Do
-not rename, move, or delete files. `_core*` modules hold shared implementations
-behind the root shim files that `index.js` re-exports. The correlation context
-is dual-tracked (AsyncLocalStorage for imperative reads, FiberRef for Effect
-code) under `_coreCorrelation/`.
-
-Entry points: `index.js` (main export), `metrics/index.js` (the `./metrics`
-subpath), `createSmithersObservabilityLayer.js` (layer composition), and
-`logging.js` (fire-and-forget logs with a pluggable runtime via
-`setSmithersLogRunner`).
-
-Gotchas: `index.d.ts`, `metrics/index.d.ts`, and the hash-suffixed `*-*.d.ts`
-chunks are build artifacts of `tsup --dts-only` (the build script `rm`s them
-first) — never edit them. `correlation.js`'s `updateCurrentCorrelationContext`
-is a deliberately mutating legacy shim, distinct from the Effect version in
-`_coreCorrelation/`.

package/src/ResolvedSmithersObservabilityOptions.ts

@@ -1,12 +0,0 @@
-import type { LogLevel } from "effect";
-import type { SmithersLogFormat } from "./SmithersLogFormat";
-
-export type ResolvedSmithersObservabilityOptions = {
-  readonly enabled: boolean;
-  readonly endpoint: string;
-  readonly headers: Record<string, string> | undefined;
-  readonly serviceName: string;
-  readonly logFormat: SmithersLogFormat;
-  readonly logLevel: LogLevel.LogLevel;
-  readonly installLogger: boolean;
-};