Observability overhaul + traces support

api-contracts/openapi/components/schemas/_index.yaml

@@ -400,3 +400,11 @@ V1CELDebugResponse:
   $ref: "./v1/cel.yaml#/V1CELDebugResponse"
 V1CELDebugResponseStatus:
   $ref: "./v1/cel.yaml#/V1CELDebugResponseStatus"
+OtelSpan:
+  $ref: "./v1/otel.yaml#/OtelSpan"
+OtelSpanKind:
+  $ref: "./v1/otel.yaml#/OtelSpanKind"
+OtelStatusCode:
+  $ref: "./v1/otel.yaml#/OtelStatusCode"
+OtelSpanList:
+  $ref: "./v1/otel.yaml#/OtelSpanList"

api-contracts/openapi/components/schemas/v1/otel.yaml

@@ -0,0 +1,73 @@
+OtelSpan:
+  type: object
+  properties:
+    trace_id:
+      type: string
+    span_id:
+      type: string
+    parent_span_id:
+      type: string
+    span_name:
+      type: string
+    span_kind:
+      $ref: "#/OtelSpanKind"
+    service_name:
+      type: string
+    status_code:
+      $ref: "#/OtelStatusCode"
+    status_message:
+      type: string
+    duration:
+      type: integer
+      format: int64
+    created_at:
+      type: string
+      format: date-time
+    resource_attributes:
+      type: object
+      additionalProperties:
+        type: string
+    span_attributes:
+      type: object
+      additionalProperties:
+        type: string
+    scope_name:
+      type: string
+    scope_version:
+      type: string
+  required:
+    - trace_id
+    - span_id
+    - span_name
+    - span_kind
+    - service_name
+    - status_code
+    - duration
+    - created_at
+
+OtelSpanKind:
+  type: string
+  enum:
+    - UNSPECIFIED
+    - INTERNAL
+    - SERVER
+    - CLIENT
+    - PRODUCER
+    - CONSUMER
+
+OtelStatusCode:
+  type: string
+  enum:
+    - UNSET
+    - OK
+    - ERROR
+
+OtelSpanList:
+  type: object
+  properties:
+    pagination:
+      $ref: "../metadata.yaml#/PaginationResponse"
+    rows:
+      type: array
+      items:
+        $ref: "#/OtelSpan"

api-contracts/openapi/openapi.yaml

@@ -29,6 +29,8 @@ paths:
     $ref: "./paths/v1/tasks/tasks.yaml#/listTaskEvents"
   /api/v1/stable/tasks/{task}/logs:
     $ref: "./paths/v1/tasks/tasks.yaml#/listLogs"
+  /api/v1/stable/tasks/{task}/trace:
+    $ref: "./paths/v1/tasks/tasks.yaml#/getTrace"
   /api/v1/stable/tenants/{tenant}/tasks/cancel:
     $ref: "./paths/v1/tasks/tasks.yaml#/cancelTasks"
   /api/v1/stable/tenants/{tenant}/tasks/replay:

api-contracts/openapi/paths/v1/tasks/tasks.yaml

@@ -441,6 +441,64 @@ replayTasks:
     tags:
       - Task
 
+getTrace:
+  get:
+    x-resources: ["tenant", "task"]
+    description: Get OTel trace for a task run
+    operationId: v1-task:get:trace
+    parameters:
+      - description: The task id
+        in: path
+        name: task
+        required: true
+        schema:
+          type: string
+          format: uuid
+          minLength: 36
+          maxLength: 36
+      - description: The number to skip
+        in: query
+        name: offset
+        required: false
+        schema:
+          type: integer
+          format: int64
+      - description: The number to limit by
+        in: query
+        name: limit
+        required: false
+        schema:
+          type: integer
+          format: int64
+    responses:
+      "200":
+        content:
+          application/json:
+            schema:
+              $ref: "../../../components/schemas/_index.yaml#/OtelSpanList"
+        description: Successfully retrieved the OTel trace
+      "400":
+        content:
+          application/json:
+            schema:
+              $ref: "../../../components/schemas/_index.yaml#/APIErrors"
+        description: A malformed or bad request
+      "403":
+        content:
+          application/json:
+            schema:
+              $ref: "../../../components/schemas/_index.yaml#/APIErrors"
+        description: Forbidden
+      "404":
+        content:
+          application/json:
+            schema:
+              $ref: "../../../components/schemas/_index.yaml#/APIErrors"
+        description: The task was not found
+    summary: Get OTel trace
+    tags:
+      - Task
+
 listLogs:
   get:
     x-resources: ["tenant", "task"]

api/v1/server/handlers/v1/tasks/trace.go

@@ -0,0 +1,31 @@
+package tasks
+
+import (
+	"github.com/labstack/echo/v4"
+
+	"github.com/hatchet-dev/hatchet/api/v1/server/oas/gen"
+	transformers "github.com/hatchet-dev/hatchet/api/v1/server/oas/transformers/v1"
+	"github.com/hatchet-dev/hatchet/pkg/repository/sqlcv1"
+)
+
+func (t *TasksService) V1TaskGetTrace(ctx echo.Context, request gen.V1TaskGetTraceRequestObject) (gen.V1TaskGetTraceResponseObject, error) {
+	task := ctx.Get("task").(*sqlcv1.V1TasksOlap)
+
+	limit := int64(1000)
+	offset := int64(0)
+
+	if request.Params.Limit != nil {
+		limit = *request.Params.Limit
+	}
+
+	if request.Params.Offset != nil {
+		offset = *request.Params.Offset
+	}
+
+	result, err := t.config.V1.OTelCollector().ListSpansByTaskExternalID(ctx.Request().Context(), task.TenantID, task.ExternalID, offset, limit)
+	if err != nil {
+		return nil, err
+	}
+
+	return gen.V1TaskGetTrace200JSONResponse(transformers.ToV1OtelSpanList(result.Rows, limit, offset, result.Total)), nil
+}