feat: add xatu-cbt seed data generator with S3 upload support

.github/typos.toml

@@ -1,2 +1,2 @@
 [files]
-extend-exclude = ["pkg/tui/view.go", "pkg/tui/logs.go"]
+extend-exclude = ["pkg/tui/view.go", "pkg/tui/logs.go", "pkg/seeddata/discovery.go"]

README.md

@@ -226,3 +226,36 @@ models:
 ```
 
 See [`.cbt-overrides.example.yaml`](.cbt-overrides.example.yaml) for more examples.
+
+## xatu-cbt Test Data
+
+Generate seed data parquet files for xatu-cbt tests:
+
+```bash
+# Interactive mode
+xcli lab xatu-cbt generate-seed-data
+
+# Scripted mode
+xcli lab xatu-cbt generate-seed-data \
+  --model consensus_engine_api_new_payload \
+  --network mainnet \
+  --spec fusaka \
+  --range-column slot \
+  --from 1000000 \
+  --to 1001000 \
+  --filter "status = VALID" \
+  --upload
+```
+
+Requires hybrid mode (`xcli lab mode hybrid`) for external ClickHouse access.
+
+### S3 Upload
+
+Set R2/S3 credentials for upload:
+
+```bash
+export AWS_ACCESS_KEY_ID="your-access-key"
+export AWS_SECRET_ACCESS_KEY="your-secret-key"
+```
+
+Defaults to ethpandaops R2 bucket. Override with `S3_ENDPOINT` and `S3_BUCKET` env vars.

go.mod

@@ -6,6 +6,10 @@ require (
 	dario.cat/mergo v1.0.2
 	github.com/ClickHouse/clickhouse-go/v2 v2.41.0
 	github.com/acarl005/stripansi v0.0.0-20180116102854-5a71ef0e047d
+	github.com/aws/aws-sdk-go-v2 v1.41.0
+	github.com/aws/aws-sdk-go-v2/config v1.32.5
+	github.com/aws/aws-sdk-go-v2/service/s3 v1.93.2
+	github.com/aws/smithy-go v1.24.0
 	github.com/charmbracelet/bubbletea v1.3.10
 	github.com/charmbracelet/lipgloss v1.1.0
 	github.com/docker/docker v28.5.2+incompatible
@@ -27,6 +31,21 @@ require (
 	github.com/ClickHouse/ch-go v0.69.0 // indirect
 	github.com/Microsoft/go-winio v0.6.2 // indirect
 	github.com/andybalholm/brotli v1.2.0 // indirect
+	github.com/aws/aws-sdk-go-v2/aws/protocol/eventstream v1.7.4 // indirect
+	github.com/aws/aws-sdk-go-v2/credentials v1.19.5 // indirect
+	github.com/aws/aws-sdk-go-v2/feature/ec2/imds v1.18.16 // indirect
+	github.com/aws/aws-sdk-go-v2/internal/configsources v1.4.16 // indirect
+	github.com/aws/aws-sdk-go-v2/internal/endpoints/v2 v2.7.16 // indirect
+	github.com/aws/aws-sdk-go-v2/internal/ini v1.8.4 // indirect
+	github.com/aws/aws-sdk-go-v2/internal/v4a v1.4.16 // indirect
+	github.com/aws/aws-sdk-go-v2/service/internal/accept-encoding v1.13.4 // indirect
+	github.com/aws/aws-sdk-go-v2/service/internal/checksum v1.9.7 // indirect
+	github.com/aws/aws-sdk-go-v2/service/internal/presigned-url v1.13.16 // indirect
+	github.com/aws/aws-sdk-go-v2/service/internal/s3shared v1.19.16 // indirect
+	github.com/aws/aws-sdk-go-v2/service/signin v1.0.4 // indirect
+	github.com/aws/aws-sdk-go-v2/service/sso v1.30.7 // indirect
+	github.com/aws/aws-sdk-go-v2/service/ssooidc v1.35.12 // indirect
+	github.com/aws/aws-sdk-go-v2/service/sts v1.41.5 // indirect
 	github.com/aymanbagabas/go-osc52/v2 v2.0.1 // indirect
 	github.com/charmbracelet/colorprofile v0.2.3-0.20250311203215-f60798e515dc // indirect
 	github.com/charmbracelet/x/ansi v0.10.1 // indirect

go.sum

@@ -32,6 +32,44 @@ github.com/acarl005/stripansi v0.0.0-20180116102854-5a71ef0e047d/go.mod h1:asat6
 github.com/andybalholm/brotli v1.2.0 h1:ukwgCxwYrmACq68yiUqwIWnGY0cTPox/M94sVwToPjQ=
 github.com/andybalholm/brotli v1.2.0/go.mod h1:rzTDkvFWvIrjDXZHkuS16NPggd91W3kUSvPlQ1pLaKY=
 github.com/atomicgo/cursor v0.0.1/go.mod h1:cBON2QmmrysudxNBFthvMtN32r3jxVRIvzkUiF/RuIk=
+github.com/aws/aws-sdk-go-v2 v1.41.0 h1:tNvqh1s+v0vFYdA1xq0aOJH+Y5cRyZ5upu6roPgPKd4=
+github.com/aws/aws-sdk-go-v2 v1.41.0/go.mod h1:MayyLB8y+buD9hZqkCW3kX1AKq07Y5pXxtgB+rRFhz0=
+github.com/aws/aws-sdk-go-v2/aws/protocol/eventstream v1.7.4 h1:489krEF9xIGkOaaX3CE/Be2uWjiXrkCH6gUX+bZA/BU=
+github.com/aws/aws-sdk-go-v2/aws/protocol/eventstream v1.7.4/go.mod h1:IOAPF6oT9KCsceNTvvYMNHy0+kMF8akOjeDvPENWxp4=
+github.com/aws/aws-sdk-go-v2/config v1.32.5 h1:pz3duhAfUgnxbtVhIK39PGF/AHYyrzGEyRD9Og0QrE8=
+github.com/aws/aws-sdk-go-v2/config v1.32.5/go.mod h1:xmDjzSUs/d0BB7ClzYPAZMmgQdrodNjPPhd6bGASwoE=
+github.com/aws/aws-sdk-go-v2/credentials v1.19.5 h1:xMo63RlqP3ZZydpJDMBsH9uJ10hgHYfQFIk1cHDXrR4=
+github.com/aws/aws-sdk-go-v2/credentials v1.19.5/go.mod h1:hhbH6oRcou+LpXfA/0vPElh/e0M3aFeOblE1sssAAEk=
+github.com/aws/aws-sdk-go-v2/feature/ec2/imds v1.18.16 h1:80+uETIWS1BqjnN9uJ0dBUaETh+P1XwFy5vwHwK5r9k=
+github.com/aws/aws-sdk-go-v2/feature/ec2/imds v1.18.16/go.mod h1:wOOsYuxYuB/7FlnVtzeBYRcjSRtQpAW0hCP7tIULMwo=
+github.com/aws/aws-sdk-go-v2/internal/configsources v1.4.16 h1:rgGwPzb82iBYSvHMHXc8h9mRoOUBZIGFgKb9qniaZZc=
+github.com/aws/aws-sdk-go-v2/internal/configsources v1.4.16/go.mod h1:L/UxsGeKpGoIj6DxfhOWHWQ/kGKcd4I1VncE4++IyKA=
+github.com/aws/aws-sdk-go-v2/internal/endpoints/v2 v2.7.16 h1:1jtGzuV7c82xnqOVfx2F0xmJcOw5374L7N6juGW6x6U=
+github.com/aws/aws-sdk-go-v2/internal/endpoints/v2 v2.7.16/go.mod h1:M2E5OQf+XLe+SZGmmpaI2yy+J326aFf6/+54PoxSANc=
+github.com/aws/aws-sdk-go-v2/internal/ini v1.8.4 h1:WKuaxf++XKWlHWu9ECbMlha8WOEGm0OUEZqm4K/Gcfk=
+github.com/aws/aws-sdk-go-v2/internal/ini v1.8.4/go.mod h1:ZWy7j6v1vWGmPReu0iSGvRiise4YI5SkR3OHKTZ6Wuc=
+github.com/aws/aws-sdk-go-v2/internal/v4a v1.4.16 h1:CjMzUs78RDDv4ROu3JnJn/Ig1r6ZD7/T2DXLLRpejic=
+github.com/aws/aws-sdk-go-v2/internal/v4a v1.4.16/go.mod h1:uVW4OLBqbJXSHJYA9svT9BluSvvwbzLQ2Crf6UPzR3c=
+github.com/aws/aws-sdk-go-v2/service/internal/accept-encoding v1.13.4 h1:0ryTNEdJbzUCEWkVXEXoqlXV72J5keC1GvILMOuD00E=
+github.com/aws/aws-sdk-go-v2/service/internal/accept-encoding v1.13.4/go.mod h1:HQ4qwNZh32C3CBeO6iJLQlgtMzqeG17ziAA/3KDJFow=
+github.com/aws/aws-sdk-go-v2/service/internal/checksum v1.9.7 h1:DIBqIrJ7hv+e4CmIk2z3pyKT+3B6qVMgRsawHiR3qso=
+github.com/aws/aws-sdk-go-v2/service/internal/checksum v1.9.7/go.mod h1:vLm00xmBke75UmpNvOcZQ/Q30ZFjbczeLFqGx5urmGo=
+github.com/aws/aws-sdk-go-v2/service/internal/presigned-url v1.13.16 h1:oHjJHeUy0ImIV0bsrX0X91GkV5nJAyv1l1CC9lnO0TI=
+github.com/aws/aws-sdk-go-v2/service/internal/presigned-url v1.13.16/go.mod h1:iRSNGgOYmiYwSCXxXaKb9HfOEj40+oTKn8pTxMlYkRM=
+github.com/aws/aws-sdk-go-v2/service/internal/s3shared v1.19.16 h1:NSbvS17MlI2lurYgXnCOLvCFX38sBW4eiVER7+kkgsU=
+github.com/aws/aws-sdk-go-v2/service/internal/s3shared v1.19.16/go.mod h1:SwT8Tmqd4sA6G1qaGdzWCJN99bUmPGHfRwwq3G5Qb+A=
+github.com/aws/aws-sdk-go-v2/service/s3 v1.93.2 h1:U3ygWUhCpiSPYSHOrRhb3gOl9T5Y3kB8k5Vjs//57bE=
+github.com/aws/aws-sdk-go-v2/service/s3 v1.93.2/go.mod h1:79S2BdqCJpScXZA2y+cpZuocWsjGjJINyXnOsf5DTz8=
+github.com/aws/aws-sdk-go-v2/service/signin v1.0.4 h1:HpI7aMmJ+mm1wkSHIA2t5EaFFv5EFYXePW30p1EIrbQ=
+github.com/aws/aws-sdk-go-v2/service/signin v1.0.4/go.mod h1:C5RdGMYGlfM0gYq/tifqgn4EbyX99V15P2V3R+VHbQU=
+github.com/aws/aws-sdk-go-v2/service/sso v1.30.7 h1:eYnlt6QxnFINKzwxP5/Ucs1vkG7VT3Iezmvfgc2waUw=
+github.com/aws/aws-sdk-go-v2/service/sso v1.30.7/go.mod h1:+fWt2UHSb4kS7Pu8y+BMBvJF0EWx+4H0hzNwtDNRTrg=
+github.com/aws/aws-sdk-go-v2/service/ssooidc v1.35.12 h1:AHDr0DaHIAo8c9t1emrzAlVDFp+iMMKnPdYy6XO4MCE=
+github.com/aws/aws-sdk-go-v2/service/ssooidc v1.35.12/go.mod h1:GQ73XawFFiWxyWXMHWfhiomvP3tXtdNar/fi8z18sx0=
+github.com/aws/aws-sdk-go-v2/service/sts v1.41.5 h1:SciGFVNZ4mHdm7gpD1dgZYnCuVdX1s+lFTg4+4DOy70=
+github.com/aws/aws-sdk-go-v2/service/sts v1.41.5/go.mod h1:iW40X4QBmUxdP+fZNOpfmkdMZqsovezbAeO+Ubiv2pk=
+github.com/aws/smithy-go v1.24.0 h1:LpilSUItNPFr1eY85RYgTIg5eIEPtvFbskaFcmmIUnk=
+github.com/aws/smithy-go v1.24.0/go.mod h1:LEj2LM3rBRQJxPZTB4KuzZkaZYnZPnvgIhb4pu07mx0=
 github.com/aymanbagabas/go-osc52/v2 v2.0.1 h1:HwpRHbFMcZLEVr42D4p7XBqjyuxQH5SMiErDT4WkJ2k=
 github.com/aymanbagabas/go-osc52/v2 v2.0.1/go.mod h1:uYgXzlJ7ZpABp8OJ+exZzJJhRNQ2ASbcXHWsFqH8hp8=
 github.com/cenkalti/backoff/v5 v5.0.3 h1:ZN+IMa753KfX5hd8vVaMixjnqRZ3y8CuJKRKj1xcsSM=

pkg/commands/lab.go

@@ -56,6 +56,7 @@ Use 'xcli lab [command] --help' for more information about a command.`,
 	cmd.AddCommand(NewLabTUICommand(log, configPath))
 	cmd.AddCommand(NewLabDiagnoseCommand(log, configPath))
 	cmd.AddCommand(NewLabReleaseCommand(log, configPath))
+	cmd.AddCommand(NewLabXatuCBTCommand(log, configPath))
 
 	return cmd
 }

pkg/commands/lab_xatu_cbt.go

@@ -0,0 +1,31 @@
+package commands
+
+import (
+	"github.com/sirupsen/logrus"
+	"github.com/spf13/cobra"
+)
+
+// NewLabXatuCBTCommand creates the lab xatu-cbt command namespace.
+func NewLabXatuCBTCommand(log logrus.FieldLogger, configPath string) *cobra.Command {
+	cmd := &cobra.Command{
+		Use:   "xatu-cbt",
+		Short: "Xatu-CBT related commands",
+		Long: `Commands for working with xatu-cbt, including generating seed data
+for tests.
+
+Common workflows:
+  1. Generate seed data for a single external model:
+     xcli lab xatu-cbt generate-seed-data
+
+  2. Generate test YAML for transformation models (auto-resolves dependencies):
+     xcli lab xatu-cbt generate-transformation-test
+
+Use 'xcli lab xatu-cbt [command] --help' for more information about a command.`,
+	}
+
+	// Add xatu-cbt subcommands
+	cmd.AddCommand(NewLabXatuCBTGenerateSeedDataCommand(log, configPath))
+	cmd.AddCommand(NewLabXatuCBTGenerateTransformationTestCommand(log, configPath))
+
+	return cmd
+}