revert, but increase httprate

Removed rate limiting middleware from the API routes.

.github/workflows/docker-publish.yml

@@ -33,7 +33,7 @@ jobs:
 
     steps:
       - name: Checkout repository
-        uses: actions/checkout@93cb6efe18208431cddfb8368fd83d5badbf9bfd # v5
+        uses: actions/checkout@8e8c483db84b4bee98b60c0593521ed34d9990e8 # v6
 
       # Install the cosign tool except on PR
       # https://github.com/sigstore/cosign-installer
@@ -47,7 +47,7 @@ jobs:
       # multi-platform images and export cache
       # https://github.com/docker/setup-buildx-action
       - name: Set up Docker Buildx
-        uses: docker/setup-buildx-action@e468171a9de216ec08956ac3ada2f0791b6bd435 # v3.11.1
+        uses: docker/setup-buildx-action@8d2750c68a42422c14e847fe6c8ac0403b4cbd6f # v3.12.0
 
       # Login against a Docker registry except on PR
       # https://github.com/docker/login-action

Dockerfile

@@ -1,7 +1,7 @@
 #################################
 # Builder: Go + Node in one
 #################################
-FROM golang:1.25.5-alpine@sha256:26111811bc967321e7b6f852e914d14bede324cd1accb7f81811929a6a57fea9 AS builder
+FROM golang:1.25.5-alpine@sha256:ac09a5f469f307e5da71e766b0bd59c9c49ea460a528cc3e6686513d64a6f1fb AS builder
 
 RUN apk add --no-cache \
     bash git ca-certificates tzdata \
@@ -24,7 +24,7 @@ RUN make build
 #################################
 # Runtime
 #################################
-FROM alpine:3.23@sha256:51183f2cfa6320055da30872f211093f9ff1d3cf06f39a0bdb212314c5dc7375
+FROM alpine:3.23@sha256:865b95f46d98cf867a156fe4a135ad3fe50d2056aa3f25ed31662dff6da4eb62
 
 RUN apk add --no-cache ca-certificates tzdata postgresql17-client \
  && addgroup -S app && adduser -S app -G app

docker-compose.yml

@@ -15,7 +15,7 @@ services:
       - postgres_data:/var/lib/postgresql/data
 
   mailpit:
-    image: axllent/mailpit@sha256:e22dce5b36f93c77082e204a3942fb6b283b7896e057458400a4c88344c3df68
+    image: axllent/mailpit@sha256:c076638db1e15662150be4fb62b8a6e96ef6ba5bde90c838a0239225854830f7
     restart: always
     ports:
       - "1025:1025"

docs/openapi.yaml

@@ -4164,6 +4164,42 @@ paths:
         external deletion policy)
       tags:
       - DNS
+    get:
+      operationId: GetRecordSet
+      parameters:
+      - description: Organization UUID
+        in: header
+        name: X-Org-ID
+        schema:
+          type: string
+      - description: Record Set ID (UUID)
+        in: path
+        name: id
+        required: true
+        schema:
+          type: string
+      responses:
+        "200":
+          content:
+            application/json:
+              schema:
+                $ref: '#/components/schemas/dto.RecordSetResponse'
+          description: OK
+        "403":
+          content:
+            application/json:
+              schema:
+                type: string
+          description: organization required
+        "404":
+          content:
+            application/json:
+              schema:
+                type: string
+          description: not found
+      summary: Get a record set (org scoped)
+      tags:
+      - DNS
     patch:
       operationId: UpdateRecordSet
       parameters:

go.mod

@@ -8,7 +8,8 @@ require (
 	github.com/aws/aws-sdk-go-v2/config v1.32.6
 	github.com/aws/aws-sdk-go-v2/credentials v1.19.6
 	github.com/aws/aws-sdk-go-v2/service/route53 v1.62.0
-	github.com/aws/aws-sdk-go-v2/service/s3 v1.94.0
+	github.com/aws/aws-sdk-go-v2/service/s3 v1.95.0
+	github.com/aws/smithy-go v1.24.0
 	github.com/coreos/go-oidc/v3 v3.17.0
 	github.com/dyaksa/archer v1.1.5
 	github.com/fergusstrange/embedded-postgres v1.33.0
@@ -52,7 +53,6 @@ require (
 	github.com/aws/aws-sdk-go-v2/service/sso v1.30.8 // 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/aws/smithy-go v1.24.0 // indirect
 	github.com/beorn7/perks v1.0.1 // indirect
 	github.com/bytedance/sonic v1.14.0 // indirect
 	github.com/bytedance/sonic/loader v0.3.0 // indirect

go.sum

@@ -14,12 +14,8 @@ github.com/aws/aws-sdk-go-v2 v1.41.0 h1:tNvqh1s+v0vFYdA1xq0aOJH+Y5cRyZ5upu6roPgP
 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/config v1.32.6 h1:hFLBGUKjmLAekvi1evLi5hVvFQtSo3GYwi+Bx4lpJf8=
 github.com/aws/aws-sdk-go-v2/config v1.32.6/go.mod h1:lcUL/gcd8WyjCrMnxez5OXkO3/rwcNmvfno62tnXNcI=
-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/credentials v1.19.6 h1:F9vWao2TwjV2MyiyVS+duza0NIRtAslgLUM0vTA1ZaE=
 github.com/aws/aws-sdk-go-v2/credentials v1.19.6/go.mod h1:SgHzKjEVsdQr6Opor0ihgWtkWdfRAIwxYzSJ8O85VHY=
 github.com/aws/aws-sdk-go-v2/feature/ec2/imds v1.18.16 h1:80+uETIWS1BqjnN9uJ0dBUaETh+P1XwFy5vwHwK5r9k=
@@ -42,14 +38,10 @@ github.com/aws/aws-sdk-go-v2/service/internal/s3shared v1.19.16 h1:NSbvS17MlI2lu
 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/route53 v1.62.0 h1:80pDB3Tpmb2RCSZORrK9/3iQxsd+w6vSzVqpT1FGiwE=
 github.com/aws/aws-sdk-go-v2/service/route53 v1.62.0/go.mod h1:6EZUGGNLPLh5Unt30uEoA+KQcByERfXIkax9qrc80nA=
-github.com/aws/aws-sdk-go-v2/service/s3 v1.93.2 h1:U3ygWUhCpiSPYSHOrRhb3gOl9T5Y3kB8k5Vjs//57bE=
+github.com/aws/aws-sdk-go-v2/service/s3 v1.95.0 h1:MIWra+MSq53CFaXXAywB2qg9YvVZifkk6vEGl/1Qor0=
-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/s3 v1.95.0/go.mod h1:79S2BdqCJpScXZA2y+cpZuocWsjGjJINyXnOsf5DTz8=
-github.com/aws/aws-sdk-go-v2/service/s3 v1.94.0 h1:SWTxh/EcUCDVqi/0s26V6pVUq0BBG7kx0tDTmF/hCgA=
-github.com/aws/aws-sdk-go-v2/service/s3 v1.94.0/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/sso v1.30.8 h1:aM/Q24rIlS3bRAhTyFurowU8A0SMyGDtEOY/l/s/1Uw=
 github.com/aws/aws-sdk-go-v2/service/sso v1.30.8/go.mod h1:+fWt2UHSb4kS7Pu8y+BMBvJF0EWx+4H0hzNwtDNRTrg=
 github.com/aws/aws-sdk-go-v2/service/ssooidc v1.35.12 h1:AHDr0DaHIAo8c9t1emrzAlVDFp+iMMKnPdYy6XO4MCE=
@@ -87,10 +79,6 @@ github.com/frankban/quicktest v1.14.6 h1:7Xjx+VpznH+oBnejlPUj8oUpdxnVs4f8XU8WnHk
 github.com/frankban/quicktest v1.14.6/go.mod h1:4ptaffx2x8+WTWXmUCuVU6aPUX1/Mz7zb5vbUoiM6w0=
 github.com/fsnotify/fsnotify v1.9.0 h1:2Ml+OJNzbYCTzsxtv8vKSFD9PbJjmhYF14k/jKC7S9k=
 github.com/fsnotify/fsnotify v1.9.0/go.mod h1:8jBTzvmWwFyi3Pb8djgCCO5IBqzKJ/Jwo8TRcHyHii0=
-github.com/gabriel-vasile/mimetype v1.4.10 h1:zyueNbySn/z8mJZHLt6IPw0KoZsiQNszIpU+bX4+ZK0=
-github.com/gabriel-vasile/mimetype v1.4.10/go.mod h1:d+9Oxyo1wTzWdyVUPMmXFvp4F9tea18J8ufA774AB3s=
-github.com/gabriel-vasile/mimetype v1.4.11 h1:AQvxbp830wPhHTqc1u7nzoLT+ZFxGY7emj5DR5DYFik=
-github.com/gabriel-vasile/mimetype v1.4.11/go.mod h1:d+9Oxyo1wTzWdyVUPMmXFvp4F9tea18J8ufA774AB3s=
 github.com/gabriel-vasile/mimetype v1.4.12 h1:e9hWvmLYvtp846tLHam2o++qitpguFiYCKbn0w9jyqw=
 github.com/gabriel-vasile/mimetype v1.4.12/go.mod h1:d+9Oxyo1wTzWdyVUPMmXFvp4F9tea18J8ufA774AB3s=
 github.com/gin-contrib/sse v1.1.0 h1:n0w2GMuUpWDVp7qSpvze6fAu9iRxJY4Hmj6AmBOU05w=
@@ -124,10 +112,6 @@ github.com/go-playground/locales v0.14.1 h1:EWaQ/wswjilfKLTECiXz7Rh+3BjFhfDFKv/o
 github.com/go-playground/locales v0.14.1/go.mod h1:hxrqLVvrK65+Rwrd5Fc6F2O76J/NuW9t0sjnWqG1slY=
 github.com/go-playground/universal-translator v0.18.1 h1:Bcnm0ZwsGyWbCzImXv+pAJnYK9S473LQFuzCbDbfSFY=
 github.com/go-playground/universal-translator v0.18.1/go.mod h1:xekY+UJKNuX9WP91TpwSH2VMlDf28Uj24BCp08ZFTUY=
-github.com/go-playground/validator/v10 v10.28.0 h1:Q7ibns33JjyW48gHkuFT91qX48KG0ktULL6FgHdG688=
-github.com/go-playground/validator/v10 v10.28.0/go.mod h1:GoI6I1SjPBh9p7ykNE/yj3fFYbyDOpwMn5KXd+m2hUU=
-github.com/go-playground/validator/v10 v10.29.0 h1:lQlF5VNJWNlRbRZNeOIkWElR+1LL/OuHcc0Kp14w1xk=
-github.com/go-playground/validator/v10 v10.29.0/go.mod h1:D6QxqeMlgIPuT02L66f2ccrZ7AGgHkzKmmTMZhk/Kc4=
 github.com/go-playground/validator/v10 v10.30.1 h1:f3zDSN/zOma+w6+1Wswgd9fLkdwy06ntQJp0BBvFG0w=
 github.com/go-playground/validator/v10 v10.30.1/go.mod h1:oSuBIQzuJxL//3MelwSLD5hc2Tu889bF0Idm9Dg26cM=
 github.com/go-sql-driver/mysql v1.6.0/go.mod h1:DCzpHaOWr8IXmIStZouvnhqoel9Qv2LBy8hT2VhHyBg=

internal/api/mount_dns_routes.go

@@ -20,6 +20,7 @@ func mountDNSRoutes(r chi.Router, db *gorm.DB, authOrg func(http.Handler) http.H
 
 		d.Get("/domains/{domain_id}/records", handlers.ListRecordSets(db))
 		d.Post("/domains/{domain_id}/records", handlers.CreateRecordSet(db))
+		d.Get("/records/{id}", handlers.GetRecordSet(db))
 		d.Patch("/records/{id}", handlers.UpdateRecordSet(db))
 		d.Delete("/records/{id}", handlers.DeleteRecordSet(db))
 	})

internal/api/routes.go

@@ -37,7 +37,7 @@ func NewRouter(db *gorm.DB, jobs *bg.Jobs, studio http.Handler) http.Handler {
 	r.Use(middleware.Recoverer)
 	r.Use(SecurityHeaders)
 	r.Use(requestBodyLimit(10 << 20))
-	r.Use(httprate.LimitByIP(100, 1*time.Minute))
+	r.Use(httprate.LimitByIP(1000, 1*time.Minute))
 	r.Use(middleware.StripSlashes)
 
 	allowed := getAllowedOrigins()

internal/bg/bg.go

@@ -138,7 +138,11 @@ func NewJobs(gdb *gorm.DB, dbUrl string) (*Jobs, error) {
 		archer.WithTimeout(5*time.Minute),
 	)
 
-	c.Register("cluster_action", ClusterActionWorker(gdb))
+	c.Register(
+		"cluster_action",
+		ClusterActionWorker(gdb),
+		archer.WithInstances(1),
+	)
 	return jobs, nil
 }
 

internal/bg/cluster_action.go

@@ -36,6 +36,21 @@ func ClusterActionWorker(db *gorm.DB) archer.WorkerFn {
 		var args ClusterActionArgs
 		_ = j.ParseArguments(&args)
 
+		runID, _ := uuid.Parse(j.ID)
+
+		updateRun := func(status string, errMsg string) {
+			updates := map[string]any{
+				"status": status,
+				"error":  errMsg,
+			}
+			if status == "succeeded" || status == "failed" {
+				updates["finished_at"] = time.Now().UTC().Format(time.RFC3339)
+			}
+			db.Model(&models.ClusterRun{}).Where("id = ?", runID).Updates(updates)
+		}
+
+		updateRun("running", "")
+
 		logger := log.With().
 			Str("job", j.ID).
 			Str("cluster_id", args.ClusterID.String()).
@@ -56,18 +71,20 @@ func ClusterActionWorker(db *gorm.DB) archer.WorkerFn {
 			Preload("NodePools.Servers.SshKey").
 			Where("id = ? AND organization_id = ?", args.ClusterID, args.OrgID).
 			First(&c).Error; err != nil {
-
+			updateRun("failed", fmt.Errorf("load cluster: %w", err).Error())
 			return nil, fmt.Errorf("load cluster: %w", err)
 		}
 
 		// ---- Step 1: Prepare (mostly lifted from ClusterPrepareWorker)
 		if err := setClusterStatus(db, c.ID, clusterStatusBootstrapping, ""); err != nil {
+			updateRun("failed", err.Error())
 			return nil, fmt.Errorf("mark bootstrapping: %w", err)
 		}
 		c.Status = clusterStatusBootstrapping
 
 		if err := validateClusterForPrepare(&c); err != nil {
 			_ = setClusterStatus(db, c.ID, clusterStatusFailed, err.Error())
+			updateRun("failed", err.Error())
 			return nil, fmt.Errorf("validate: %w", err)
 		}
 
@@ -75,6 +92,7 @@ func ClusterActionWorker(db *gorm.DB) archer.WorkerFn {
 		keyPayloads, sshConfig, err := buildSSHAssetsForCluster(db, &c, allServers)
 		if err != nil {
 			_ = setClusterStatus(db, c.ID, clusterStatusFailed, err.Error())
+			updateRun("failed", err.Error())
 			return nil, fmt.Errorf("build ssh assets: %w", err)
 		}
 
@@ -98,6 +116,7 @@ func ClusterActionWorker(db *gorm.DB) archer.WorkerFn {
 		orgKey, orgSecret, err := findOrCreateClusterAutomationKey(db, c.OrganizationID, c.ID, 24*time.Hour)
 		if err != nil {
 			_ = setClusterStatus(db, c.ID, clusterStatusFailed, err.Error())
+			updateRun("failed", err.Error())
 			return nil, fmt.Errorf("org key: %w", err)
 		}
 		dtoCluster.OrgKey = &orgKey
@@ -106,6 +125,7 @@ func ClusterActionWorker(db *gorm.DB) archer.WorkerFn {
 		payloadJSON, err := json.MarshalIndent(dtoCluster, "", "  ")
 		if err != nil {
 			_ = setClusterStatus(db, c.ID, clusterStatusFailed, err.Error())
+			updateRun("failed", err.Error())
 			return nil, fmt.Errorf("marshal payload: %w", err)
 		}
 
@@ -115,11 +135,13 @@ func ClusterActionWorker(db *gorm.DB) archer.WorkerFn {
 			cancel()
 			if err != nil {
 				_ = setClusterStatus(db, c.ID, clusterStatusFailed, err.Error())
+				updateRun("failed", err.Error())
 				return nil, fmt.Errorf("push assets: %w", err)
 			}
 		}
 
 		if err := setClusterStatus(db, c.ID, clusterStatusPending, ""); err != nil {
+			updateRun("failed", err.Error())
 			return nil, fmt.Errorf("mark pending: %w", err)
 		}
 		c.Status = clusterStatusPending
@@ -132,11 +154,13 @@ func ClusterActionWorker(db *gorm.DB) archer.WorkerFn {
 			if err != nil {
 				logger.Error().Err(err).Str("output", out).Msg("ping-servers failed")
 				_ = setClusterStatus(db, c.ID, clusterStatusFailed, fmt.Sprintf("make ping-servers: %v", err))
+				updateRun("failed", err.Error())
 				return nil, fmt.Errorf("ping-servers: %w", err)
 			}
 		}
 
 		if err := setClusterStatus(db, c.ID, clusterStatusProvisioning, ""); err != nil {
+			updateRun("failed", err.Error())
 			return nil, fmt.Errorf("mark provisioning: %w", err)
 		}
 		c.Status = clusterStatusProvisioning
@@ -149,13 +173,18 @@ func ClusterActionWorker(db *gorm.DB) archer.WorkerFn {
 			if err != nil {
 				logger.Error().Err(err).Str("output", out).Msg("bootstrap target failed")
 				_ = setClusterStatus(db, c.ID, clusterStatusFailed, fmt.Sprintf("make %s: %v", args.MakeTarget, err))
+				updateRun("failed", err.Error())
 				return nil, fmt.Errorf("make %s: %w", args.MakeTarget, err)
 			}
 		}
 
 		if err := setClusterStatus(db, c.ID, clusterStatusReady, ""); err != nil {
+			updateRun("failed", err.Error())
 			return nil, fmt.Errorf("mark ready: %w", err)
 		}
+
+		updateRun("succeeded", "")
+
 		return ClusterActionResult{
 			Status:    "ok",
 			Action:    args.Action,

internal/bg/dns.go

@@ -15,6 +15,7 @@ import (
 	"github.com/glueops/autoglue/internal/models"
 	"github.com/glueops/autoglue/internal/utils"
 	"github.com/google/uuid"
+	"github.com/rs/zerolog"
 	"github.com/rs/zerolog/log"
 	"gorm.io/gorm"
 
@@ -23,6 +24,8 @@ import (
 	"github.com/aws/aws-sdk-go-v2/credentials"
 	r53 "github.com/aws/aws-sdk-go-v2/service/route53"
 	r53types "github.com/aws/aws-sdk-go-v2/service/route53/types"
+	"github.com/aws/smithy-go"
+	smithyhttp "github.com/aws/smithy-go/transport/http"
 )
 
 /************* args & small DTOs *************/
@@ -47,6 +50,9 @@ const externalDNSPoisonOwner = "autoglue-lock"
 // ExternalDNS poison content – fake owner so real external-dns skips it.
 const externalDNSPoisonValue = "heritage=external-dns,external-dns/owner=" + externalDNSPoisonOwner + ",external-dns/resource=manual/autoglue"
 
+// Default TTL for non-alias records (alias not supported in this reconciler)
+const defaultRecordTTLSeconds int64 = 300
+
 /************* entrypoint worker *************/
 
 func DNSReconsileWorker(db *gorm.DB, jobs *Jobs) archer.WorkerFn {
@@ -225,7 +231,14 @@ func processPendingRecordsForDomain(ctx context.Context, db *gorm.DB, d *models.
 	applied := 0
 	for i := range records {
 		if err := applyRecord(ctx, db, r53c, d, &records[i]); err != nil {
-			log.Error().Err(err).Str("rr", records[i].Name).Msg("[dns] apply record failed")
+			log.Error().
+				Err(err).
+				Str("zone_id", d.ZoneID).
+				Str("domain", d.DomainName).
+				Str("record_id", records[i].ID.String()).
+				Str("name", records[i].Name).
+				Str("type", strings.ToUpper(records[i].Type)).
+				Msg("[dns] apply record failed")
 			_ = setRecordFailed(db, &records[i], err)
 			continue
 		}
@@ -249,12 +262,24 @@ func applyRecord(ctx context.Context, db *gorm.DB, r53c *r53.Client, d *models.D
 	mname := markerName(fq)
 	expected := buildMarkerValue(d.OrganizationID.String(), r.ID.String(), r.Fingerprint)
 
+	logCtx := log.With().
+		Str("zone_id", zoneID).
+		Str("domain", d.DomainName).
+		Str("fqdn", fq).
+		Str("rr_type", rt).
+		Str("record_id", r.ID.String()).
+		Str("org_id", d.OrganizationID.String()).
+		Logger()
+
+	start := time.Now()
+
 	// ---- ExternalDNS preflight ----
 	extOwned, err := hasExternalDNSOwnership(ctx, r53c, zoneID, fq, rt)
 	if err != nil {
 		return fmt.Errorf("external_dns_lookup: %w", err)
 	}
 	if extOwned {
+		logCtx.Warn().Msg("[dns] ownership conflict: external-dns claims this record")
 		r.Owner = "external"
 		_ = db.Save(r).Error
 		return fmt.Errorf("ownership_conflict: external-dns claims %s; refusing to modify", strings.TrimSuffix(fq, "."))
@@ -265,6 +290,7 @@ func applyRecord(ctx context.Context, db *gorm.DB, r53c *r53.Client, d *models.D
 	if err != nil {
 		return fmt.Errorf("marker lookup: %w", err)
 	}
+
 	hasForeignOwner := false
 	hasOurExact := false
 	for _, v := range markerVals {
@@ -279,25 +305,26 @@ func applyRecord(ctx context.Context, db *gorm.DB, r53c *r53.Client, d *models.D
 			hasForeignOwner = true
 		}
 	}
+
+	logCtx.Debug().
+		Bool("externaldns_owned", extOwned).
+		Int("marker_txt_count", len(markerVals)).
+		Bool("marker_has_our_exact", hasOurExact).
+		Bool("marker_has_foreign", hasForeignOwner).
+		Msg("[dns] ownership preflight")
+
 	if hasForeignOwner {
+		logCtx.Warn().Msg("[dns] ownership conflict: foreign _autoglue marker")
 		r.Owner = "external"
 		_ = db.Save(r).Error
 		return fmt.Errorf("ownership_conflict: marker for %s is owned by another controller; refusing to modify", strings.TrimSuffix(fq, "."))
 	}
 
-	// Build RR change (UPSERT)
-	rrChange := r53types.Change{
-		Action: r53types.ChangeActionUpsert,
-		ResourceRecordSet: &r53types.ResourceRecordSet{
-			Name: aws.String(fq),
-			Type: r53types.RRType(rt),
-		},
-	}
-
 	// Decode user values
 	var userVals []string
-	if len(r.Values) > 0 {
+	rawVals := strings.TrimSpace(string(r.Values))
-		if err := jsonUnmarshalStrict([]byte(r.Values), &userVals); err != nil {
+	if rawVals != "" && rawVals != "null" {
+		if err := jsonUnmarshalStrict([]byte(rawVals), &userVals); err != nil {
 			return fmt.Errorf("values decode: %w", err)
 		}
 	}
@@ -306,15 +333,38 @@ func applyRecord(ctx context.Context, db *gorm.DB, r53c *r53.Client, d *models.D
 	recs := make([]r53types.ResourceRecord, 0, len(userVals))
 	for _, v := range userVals {
 		v = strings.TrimSpace(v)
+		if v == "" {
+			continue
+		}
 		if rt == "TXT" && !(strings.HasPrefix(v, `"`) && strings.HasSuffix(v, `"`)) {
 			v = strconv.Quote(v)
 		}
 		recs = append(recs, r53types.ResourceRecord{Value: aws.String(v)})
 	}
-	rrChange.ResourceRecordSet.ResourceRecords = recs
+
-	if r.TTL != nil {
+	// Alias is NOT supported - enforce at least one value for all record types we manage
-		ttl := int64(*r.TTL)
+	if len(recs) == 0 {
-		rrChange.ResourceRecordSet.TTL = aws.Int64(ttl)
+		logCtx.Warn().
+			Str("raw_values", truncateForLog(string(r.Values), 240)).
+			Int("decoded_value_count", len(userVals)).
+			Msg("[dns] invalid record: no values (alias not supported)")
+		return fmt.Errorf("invalid_record: %s %s requires at least one value (alias not supported)", strings.TrimSuffix(fq, "."), rt)
+	}
+
+	ttl := defaultRecordTTLSeconds
+	if r.TTL != nil && *r.TTL > 0 {
+		ttl = int64(*r.TTL)
+	}
+
+	// Build RR change (UPSERT)
+	rrChange := r53types.Change{
+		Action: r53types.ChangeActionUpsert,
+		ResourceRecordSet: &r53types.ResourceRecordSet{
+			Name:            aws.String(fq),
+			Type:            r53types.RRType(rt),
+			TTL:             aws.Int64(ttl),
+			ResourceRecords: recs,
+		},
 	}
 
 	// Build marker TXT change (UPSERT)
@@ -323,7 +373,7 @@ func applyRecord(ctx context.Context, db *gorm.DB, r53c *r53.Client, d *models.D
 		ResourceRecordSet: &r53types.ResourceRecordSet{
 			Name: aws.String(mname),
 			Type: r53types.RRTypeTxt,
-			TTL:  aws.Int64(300),
+			TTL:  aws.Int64(defaultRecordTTLSeconds),
 			ResourceRecords: []r53types.ResourceRecord{
 				{Value: aws.String(strconv.Quote(expected))},
 			},
@@ -337,14 +387,26 @@ func applyRecord(ctx context.Context, db *gorm.DB, r53c *r53.Client, d *models.D
 	changes := []r53types.Change{rrChange, markerChange}
 	changes = append(changes, poisonChanges...)
 
+	// Log what we are about to send
+	logCtx.Debug().
+		Interface("route53_change_batch", toLogChangeBatch(zoneID, changes)).
+		Msg("[dns] route53 request preview")
+
 	_, err = r53c.ChangeResourceRecordSets(ctx, &r53.ChangeResourceRecordSetsInput{
 		HostedZoneId: aws.String(zoneID),
 		ChangeBatch:  &r53types.ChangeBatch{Changes: changes},
 	})
 	if err != nil {
+		logAWSError(logCtx, err)
+		logCtx.Info().Dur("elapsed", time.Since(start)).Msg("[dns] apply failed")
 		return err
 	}
 
+	logCtx.Info().
+		Dur("elapsed", time.Since(start)).
+		Int("change_count", len(changes)).
+		Msg("[dns] apply ok")
+
 	// Success → mark ready & ownership
 	r.Status = "ready"
 	r.LastError = ""
@@ -352,6 +414,7 @@ func applyRecord(ctx context.Context, db *gorm.DB, r53c *r53.Client, d *models.D
 	if err := db.Save(r).Error; err != nil {
 		return err
 	}
+
 	_ = hasOurExact // could be used to skip marker write in future
 	return nil
 }
@@ -568,7 +631,7 @@ func buildExternalDNSPoisonTXTChanges(fqdn, rrType string) []r53types.Change {
 			ResourceRecordSet: &r53types.ResourceRecordSet{
 				Name: aws.String(n),
 				Type: r53types.RRTypeTxt,
-				TTL:  aws.Int64(300),
+				TTL:  aws.Int64(defaultRecordTTLSeconds),
 				ResourceRecords: []r53types.ResourceRecord{
 					{Value: aws.String(val)},
 				},
@@ -595,3 +658,125 @@ func jsonUnmarshalStrict(b []byte, dst any) error {
 	}
 	return json.Unmarshal(b, dst)
 }
+
+/************* logging DTOs & helpers *************/
+
+type logRR struct {
+	Value string `json:"value"`
+}
+
+type logRRSet struct {
+	Action         string  `json:"action"`
+	Name           string  `json:"name"`
+	Type           string  `json:"type"`
+	TTL            *int64  `json:"ttl,omitempty"`
+	Records        []logRR `json:"records,omitempty"`
+	RecordCount    int     `json:"record_count"`
+	HasAliasTarget bool    `json:"has_alias_target"`
+	SetIdentifier  *string `json:"set_identifier,omitempty"`
+}
+
+type logChangeBatch struct {
+	HostedZoneID string     `json:"hosted_zone_id"`
+	ChangeCount  int        `json:"change_count"`
+	Changes      []logRRSet `json:"changes"`
+}
+
+func truncateForLog(s string, max int) string {
+	s = strings.TrimSpace(s)
+	if max <= 0 || len(s) <= max {
+		return s
+	}
+	return s[:max] + "…"
+}
+
+func toLogChangeBatch(zoneID string, changes []r53types.Change) logChangeBatch {
+	out := logChangeBatch{
+		HostedZoneID: zoneID,
+		ChangeCount:  len(changes),
+		Changes:      make([]logRRSet, 0, len(changes)),
+	}
+
+	for _, ch := range changes {
+		if ch.ResourceRecordSet == nil {
+			continue
+		}
+		rrs := ch.ResourceRecordSet
+		lc := logRRSet{
+			Action:         string(ch.Action),
+			Name:           aws.ToString(rrs.Name),
+			Type:           string(rrs.Type),
+			TTL:            rrs.TTL,
+			HasAliasTarget: rrs.AliasTarget != nil,
+			SetIdentifier:  rrs.SetIdentifier,
+			RecordCount:    len(rrs.ResourceRecords),
+			Records:        make([]logRR, 0, min(len(rrs.ResourceRecords), 5)),
+		}
+
+		// Log up to first 5 values (truncate each) to avoid log bloat / secrets
+		for i, rr := range rrs.ResourceRecords {
+			if i >= 5 {
+				break
+			}
+			lc.Records = append(lc.Records, logRR{Value: truncateForLog(aws.ToString(rr.Value), 160)})
+		}
+
+		out.Changes = append(out.Changes, lc)
+	}
+	return out
+}
+
+func min(a, b int) int {
+	if a < b {
+		return a
+	}
+	return b
+}
+
+// logAWSError extracts useful smithy/HTTP metadata (status code + request id + api code) into logs.
+// logAWSError extracts useful smithy/HTTP metadata (status code + request id + api code) into logs.
+func logAWSError(l zerolog.Logger, err error) {
+	// Add operation context if present
+	var opErr *smithy.OperationError
+	if errors.As(err, &opErr) {
+		l = l.With().
+			Str("aws_service", opErr.ServiceID).
+			Str("aws_operation", opErr.OperationName).
+			Logger()
+		err = opErr.Unwrap()
+	}
+
+	// HTTP status + request id (smithy-go transport/http)
+	var re *smithyhttp.ResponseError
+	if errors.As(err, &re) {
+		status := re.HTTPStatusCode()
+
+		reqID := ""
+		if resp := re.HTTPResponse(); resp != nil && resp.Header != nil {
+			reqID = resp.Header.Get("x-amzn-RequestId")
+			if reqID == "" {
+				reqID = resp.Header.Get("x-amz-request-id")
+			}
+		}
+
+		ev := l.Error().Int("http_status", status).Err(err)
+		if reqID != "" {
+			ev = ev.Str("aws_request_id", reqID)
+		}
+		ev.Msg("[dns] aws route53 call failed")
+		return
+	}
+
+	// API error code/message (best-effort)
+	var apiErr smithy.APIError
+	if errors.As(err, &apiErr) {
+		l.Error().
+			Str("aws_error_code", apiErr.ErrorCode()).
+			Str("aws_error_message", apiErr.ErrorMessage()).
+			Err(err).
+			Msg("[dns] aws route53 api error")
+		return
+	}
+
+	l.Error().Err(err).Msg("[dns] aws route53 error")
+}

internal/handlers/cluster_runs.go

@@ -223,7 +223,7 @@ func RunClusterAction(db *gorm.DB, jobs *bg.Jobs) http.HandlerFunc {
 			run.ID.String(),
 			"cluster_action",
 			args,
-			archer.WithMaxRetries(3),
+			archer.WithMaxRetries(0),
 		)
 
 		if enqueueErr != nil {

internal/handlers/dns.go

@@ -503,6 +503,50 @@ func ListRecordSets(db *gorm.DB) http.HandlerFunc {
 	}
 }
 
+// GetRecordSet godoc
+//
+//	@ID			GetRecordSet
+//	@Summary	Get a record set (org scoped)
+//	@Tags		DNS
+//	@Produce	json
+//	@Param		X-Org-ID	header		string	false	"Organization UUID"
+//	@Param		id			path		string	true	"Record Set ID (UUID)"
+//	@Success	200			{object}	dto.RecordSetResponse
+//	@Failure	403			{string}	string	"organization required"
+//	@Failure	404			{string}	string	"not found"
+//	@Router		/dns/records/{id} [get]
+func GetRecordSet(db *gorm.DB) http.HandlerFunc {
+	return func(w http.ResponseWriter, r *http.Request) {
+		orgID, ok := httpmiddleware.OrgIDFrom(r.Context())
+		if !ok {
+			utils.WriteError(w, http.StatusForbidden, "org_required", "specify X-Org-ID")
+			return
+		}
+
+		id, err := uuid.Parse(chi.URLParam(r, "id"))
+		if err != nil {
+			utils.WriteError(w, http.StatusBadRequest, "bad_id", "invalid UUID")
+			return
+		}
+
+		var row models.RecordSet
+		if err := db.
+			Joins("Domain").
+			Where(`record_sets.id = ? AND "Domain"."organization_id" = ?`, id, orgID).
+			First(&row).Error; err != nil {
+
+			if errors.Is(err, gorm.ErrRecordNotFound) {
+				utils.WriteError(w, http.StatusNotFound, "not_found", "record set not found")
+				return
+			}
+			utils.WriteError(w, http.StatusInternalServerError, "db_error", err.Error())
+			return
+		}
+
+		utils.WriteJSON(w, http.StatusOK, recordOut(&row))
+	}
+}
+
 // CreateRecordSet godoc
 //
 //	@ID			CreateRecordSet

postgres/Dockerfile

@@ -1,4 +1,4 @@
-FROM postgres:17.7@sha256:44640f16641cf36716cabd011e2f7eb4742b6b6b19f4488ddcbb7c250e5c9753
+FROM postgres:17.7@sha256:dca7512acaa113409df7e40d977d801e53c0c8088e45d4311a45b4065ccfdcd3
 
 RUN cd /var/lib/postgresql/ && \
     openssl req -new -text -passout pass:abcd -subj /CN=localhost -out server.req -keyout privkey.pem && \

sdk/ts/package.json

@@ -16,6 +16,6 @@
     "prepare": "npm run build"
   },
   "devDependencies": {
-    "typescript": "^4.0 || ^5.0"
+    "typescript": "5.9.3"
   }
 }

ui/package.json

@@ -46,41 +46,41 @@
     "date-fns": "^4.1.0",
     "embla-carousel-react": "^8.6.0",
     "input-otp": "^1.4.2",
-    "lucide-react": "^0.561.0",
+    "lucide-react": "^0.562.0",
     "motion": "^12.23.26",
     "next-themes": "^0.4.6",
     "rapidoc": "^9.3.8",
     "react": "^19.2.3",
-    "react-day-picker": "^9.12.0",
+    "react-day-picker": "^9.13.0",
     "react-dom": "^19.2.3",
-    "react-hook-form": "^7.68.0",
+    "react-hook-form": "^7.69.0",
     "react-icons": "^5.5.0",
     "react-resizable-panels": "^3.0.6",
-    "react-router-dom": "^7.10.1",
+    "react-router-dom": "^7.11.0",
     "recharts": "2.15.4",
     "sonner": "^2.0.7",
     "tailwind-merge": "^3.4.0",
     "tailwindcss": "^4.1.18",
     "vaul": "^1.1.2",
-    "zod": "^4.1.13"
+    "zod": "^4.2.1"
   },
   "devDependencies": {
     "@eslint/js": "9.39.2",
     "@ianvs/prettier-plugin-sort-imports": "4.7.0",
-    "@types/node": "25.0.1",
+    "@types/node": "25.0.3",
     "@types/react": "19.2.7",
     "@types/react-dom": "19.2.3",
     "@vitejs/plugin-react": "5.1.2",
     "eslint": "9.39.2",
     "eslint-plugin-react-hooks": "7.0.1",
-    "eslint-plugin-react-refresh": "0.4.24",
+    "eslint-plugin-react-refresh": "0.4.26",
     "globals": "16.5.0",
     "prettier": "3.7.4",
     "prettier-plugin-tailwindcss": "0.7.2",
-    "shadcn": "3.6.0",
+    "shadcn": "3.6.2",
     "tw-animate-css": "1.4.0",
     "typescript": "5.9.3",
-    "typescript-eslint": "8.50.0",
+    "typescript-eslint": "8.51.0",
-    "vite": "7.2.7"
+    "vite": "7.3.0"
   }
 }

ui/src/pages/cluster-page.tsx

@@ -946,13 +946,12 @@ export const ClustersPage = () => {
 
       {/* Configure dialog (attachments + kubeconfig + node pools + actions/runs) */}
       <Dialog open={!!configCluster} onOpenChange={(open) => !open && setConfigCluster(null)}>
-        <DialogContent className="max-h-[90vh] w-full max-w-3xl overflow-y-auto">
+        <DialogContent className="max-h-[90vh] overflow-y-auto sm:max-w-2xl lg:max-w-250 ">
           <DialogHeader>
             <DialogTitle>
               Configure Cluster{configCluster?.name ? `: ${configCluster.name}` : ""}
             </DialogTitle>
           </DialogHeader>
-
           {configCluster && (
             <div className="space-y-6 py-2">
               {/* Cluster Actions */}

ui/src/pages/me-page.tsx

@@ -305,6 +305,7 @@ export const MePage = () => {
                 <Table>
                   <TableHeader>
                     <TableRow>
+                      <TableHead>Id</TableHead>
                       <TableHead>Name</TableHead>
                       <TableHead>Domain</TableHead>
                     </TableRow>
@@ -312,6 +313,7 @@ export const MePage = () => {
                   <TableBody>
                     {meQ.data?.organizations?.map((o) => (
                       <TableRow key={o.id}>
+                        <TableCell>{o.id}</TableCell>
                         <TableCell>{o.name}</TableCell>
                         <TableCell>{(o as any).domain ?? "—"}</TableCell>
                       </TableRow>