chore(db): drop unused schema and redundant indexes

Удалены мёртвые колонки, fetch_log и избыточные индексы.

Co-authored-by: Cursor <cursoragent@cursor.com>

.commitlintrc.json

@@ -1,3 +0,0 @@
-{
-  "extends": ["@commitlint/config-conventional"]
-}

.cursor/rules/conventional-commits.mdc

@@ -142,6 +142,8 @@ feat(web): add module create dialog on /modules
 | `.cursor/` | `chore` |
 | прочее в корне | `chore` |
 
+**Запрещено:** несколько scope через запятую (`refactor(web, httpapi): …`) — semantic-release не распознает `type`, релиз не будет (см. [docs/releasing.md](../../docs/releasing.md)).
+
 `type` определять по **содержимому diff**, не только по пути.
 
 ## Multi-change

.gitea/workflows/ci.yaml

@@ -303,6 +303,8 @@ jobs:
           cache-dependency-path: package-lock.json
       - name: Install release tooling
         run: npm ci
+      - name: Verify releasable commit messages
+        run: node scripts/commit/verify-release-commits.mjs
       - name: Semantic release
         run: npx semantic-release
         env:

commitlint.config.cjs

@@ -0,0 +1,22 @@
+/** @type {import('@commitlint/types').UserConfig} */
+module.exports = {
+	extends: ['@commitlint/config-conventional'],
+	plugins: [
+		{
+			rules: {
+				'scope-no-commas': ({ scope }) => {
+					if (scope && scope.includes(',')) {
+						return [
+							false,
+							'scope must not contain commas (semantic-release will not parse the commit type)'
+						];
+					}
+					return [true];
+				}
+			}
+		}
+	],
+	rules: {
+		'scope-no-commas': [2, 'always']
+	}
+};

deploy/compose/docker-compose.remote-speaker.yaml

@@ -27,9 +27,7 @@ services:
     network_mode: host
     cap_add:
       - NET_ADMIN
-    sysctls:
-      net.ipv4.ip_forward: "1"
-      net.ipv6.conf.all.forwarding: "1"
+    # sysctls нельзя с network_mode: host — включите ip_forward на VPS (см. docs/remote-speakers.md)
     volumes:
       - bird_etc:/etc/bird
       - bird_run:/run/bird

docs/db-diagnostics.md

@@ -0,0 +1,90 @@
+# Диагностика схемы PostgreSQL (EvoBGP)
+
+Runbook для оценки объёма БД и узких мест **перед** и **после** миграций оптимизации схемы. Выполнять на staging или production read-only сессией.
+
+## Подключение
+
+```bash
+psql "$EVOBGP_DATABASE_URL"
+```
+
+## 1. Размеры таблиц и индексов
+
+```sql
+SELECT relname,
+       pg_size_pretty(pg_total_relation_size(relid)) AS total,
+       pg_size_pretty(pg_relation_size(relid)) AS heap,
+       pg_size_pretty(pg_indexes_size(relid)) AS indexes
+FROM pg_catalog.pg_statio_user_tables
+ORDER BY pg_total_relation_size(relid) DESC;
+```
+
+**Ожидание:** лидеры — `revision_materialized_prefix`, `config_revision` (TOAST от preview), JSONB-кэши.
+
+## 2. Seq scan (горячие таблицы)
+
+```sql
+SELECT schemaname, relname, seq_scan, seq_tup_read, idx_scan
+FROM pg_stat_user_tables
+WHERE schemaname = 'public'
+ORDER BY seq_tup_read DESC;
+```
+
+Сброс статистики после деплоя: `SELECT pg_stat_reset();` (только осознанно, теряется baseline).
+
+## 3. Неиспользуемые индексы
+
+```sql
+SELECT indexrelname, idx_scan, pg_size_pretty(pg_relation_size(indexrelid)) AS size
+FROM pg_stat_user_indexes
+WHERE schemaname = 'public' AND idx_scan = 0
+ORDER BY pg_relation_size(indexrelid) DESC;
+```
+
+## 4. Дубликаты в materialized prefixes
+
+Перед UNIQUE `(revision_id, prefix, community_id, source)`:
+
+```sql
+SELECT revision_id, prefix, community_id, source, COUNT(*) AS n
+FROM revision_materialized_prefix
+GROUP BY 1, 2, 3, 4
+HAVING COUNT(*) > 1
+LIMIT 20;
+```
+
+## 5. Шаблон отчёта staging
+
+| Метрика | До | После | Дата |
+|---------|-----|-------|------|
+| `revision_materialized_prefix` total | | | |
+| `config_revision` total | | | |
+| `module_prefix_snapshot` total | | | |
+| `asn_prefix_cache` total | | | |
+| Top seq_scan table | | | |
+| Unused indexes (count) | | | |
+
+## 6. EXPLAIN для типовых запросов
+
+```sql
+-- Список префиксов ревизии (keyset)
+EXPLAIN (ANALYZE, BUFFERS)
+SELECT prefix::text, community_id::text, source
+FROM revision_materialized_prefix
+WHERE revision_id = '<revision-uuid>'::uuid
+ORDER BY id
+LIMIT 51;
+
+-- Diff added (anti-join)
+EXPLAIN (ANALYZE, BUFFERS)
+SELECT b.prefix::text
+FROM revision_materialized_prefix b
+LEFT JOIN revision_materialized_prefix a
+  ON a.revision_id = '<rev-a>'::uuid AND a.prefix = b.prefix
+WHERE b.revision_id = '<rev-b>'::uuid
+  AND a.prefix IS NULL
+ORDER BY b.prefix
+LIMIT 5001;
+```
+
+Цель: Index Scan / Bitmap Index Scan по `(revision_id, …)`, без Seq Scan на больших таблицах.

docs/openapi.yaml

@@ -755,6 +755,42 @@ components:
         bgp_speaker_id:
           type: ["string", "null"]
           description: "`null` - политика для всех спикеров."
+        connected_speaker_id:
+          type: ["string", "null"]
+          description: >
+            Live (GET /v1/peers?live=1): спикер, на котором сессия Established; опрос CP birdc + agent /v1/agent/bird/protocols.
+        connected_speaker_label:
+          type: string
+          description: Человекочитаемая метка ноды из live-опроса.
+        session_on_speakers:
+          type: array
+          description: Состояние протокола пира на каждой опрошенной ноде.
+          items:
+            type: object
+            properties:
+              speaker_id:
+                type: string
+              label:
+                type: string
+              state:
+                type: string
+        established_on_speakers:
+          type: array
+          description: Ноды, где сессия в состоянии Established (один пир может быть на нескольких).
+          items:
+            type: object
+            properties:
+              speaker_id:
+                type: string
+              label:
+                type: string
+              state:
+                type: string
+        session_mismatch:
+          type: boolean
+          description: >
+            true если bgp_speaker_id задан, но на этой ноде нет Established
+            (сессия может быть на других нодах — это не ошибка для tenant-wide пиров).
         policies_json:
           type: string
           description: >
@@ -809,6 +845,89 @@ components:
           description: >
             Расширяемый объект. Ключи agent_domain, agent_secret (только при создании),
             agent_port, node_ipv4, bird_bgp_source_ipv4, bird_bgp_source_ipv6.
+        live:
+          $ref: "#/components/schemas/SpeakerLiveStatus"
+          description: >
+            При GET /v1/speakers?live=1 — runtime-статус agent и BGP-опроса на ноде.
+      additionalProperties: true
+
+    SpeakerLiveStatus:
+      type: object
+      description: Live runtime snapshot for one speaker (GET /v1/speakers?live=1).
+      properties:
+        label:
+          type: string
+          description: Человекочитаемая метка ноды (agent domain или CP master).
+        agent_ok:
+          type: boolean
+          description: true если agent /v1/agent/health успешен (master — local birdc poll).
+        agent_error:
+          type: string
+        agent_last_sync_at:
+          type: string
+          format: date-time
+        agent_last_applied_revision_id:
+          type: string
+        bgp_poll_ok:
+          type: boolean
+          description: true если birdc (CP) или GET /v1/agent/bird/protocols (replica) успешен.
+        bgp_poll_error:
+          type: string
+        bgp_sessions_total:
+          type: integer
+        bgp_established:
+          type: integer
+        sessions:
+          type: array
+          items:
+            $ref: "#/components/schemas/BgpSessionLive"
+      additionalProperties: true
+
+    BgpSessionLive:
+      type: object
+      properties:
+        name:
+          type: string
+        neighbor:
+          type: string
+        state:
+          type: string
+      additionalProperties: true
+
+    LiveSpeakerPoll:
+      type: object
+      description: Метаданные опроса одной ноды в GET /v1/peers?live=1.
+      properties:
+        speaker_id:
+          type: string
+        label:
+          type: string
+        ok:
+          type: boolean
+        session_count:
+          type: integer
+        poll_error:
+          type: string
+      additionalProperties: true
+
+    BirdLocalStatus:
+      type: object
+      description: Статус локального BIRD на хосте API (GET /v1/bird/status).
+      properties:
+        birdc_configured:
+          type: boolean
+        message:
+          type: string
+        error:
+          type: string
+        protocols_excerpt:
+          type: string
+        bgp_sessions_total:
+          type: integer
+        bgp_established:
+          type: integer
+        healthy:
+          type: ["boolean", "null"]
       additionalProperties: true
 
     BundleSigningPublicKey:
@@ -2156,6 +2275,13 @@ paths:
         - $ref: "#/components/parameters/Cursor"
         - $ref: "#/components/parameters/Limit"
         - $ref: "#/components/parameters/SpeakerFilter"
+        - name: live
+          in: query
+          schema:
+            type: string
+            enum: ["1"]
+          description: >
+            Опрос birdc на CP и GET /v1/agent/bird/protocols на репликах; обогащает session_state и connected_speaker_*.
       responses:
         "200":
           description: Успешно.
@@ -2173,6 +2299,12 @@ paths:
                     type: ["string", "null"]
                   has_more:
                     type: boolean
+                  live_speaker_poll:
+                    type: array
+                    description: >
+                      При live=1 — результат опроса каждой ноды (CP birdc + agent protocols).
+                    items:
+                      $ref: "#/components/schemas/LiveSpeakerPoll"
         default:
           $ref: "#/components/responses/DefaultProblem"
     post:
@@ -2293,6 +2425,14 @@ paths:
         - $ref: "#/components/parameters/TenantId"
         - $ref: "#/components/parameters/Cursor"
         - $ref: "#/components/parameters/Limit"
+        - name: live
+          in: query
+          schema:
+            type: string
+            enum: ["1"]
+          description: >
+            Live-опрос agent /v1/agent/health и BGP protocols на репликах; CP — local birdc.
+            Обогащает каждый item полем `live`.
       responses:
         "200":
           description: Успешно.
@@ -2627,6 +2767,26 @@ paths:
         default:
           $ref: "#/components/responses/DefaultProblem"
 
+  /v1/bird/status:
+    get:
+      tags: [Deploy]
+      summary: Статус локального BIRD на хосте API
+      description: >
+        Опрос birdc через EVOBGP_BIRDC_SOCKET на процессе API (обычно CP master).
+        На репликах без birdc на CP — birdc_configured=false.
+      operationId: getBirdStatus
+      parameters:
+        - $ref: "#/components/parameters/TenantId"
+      responses:
+        "200":
+          description: Успешно.
+          content:
+            application/json:
+              schema:
+                $ref: "#/components/schemas/BirdLocalStatus"
+        default:
+          $ref: "#/components/responses/DefaultProblem"
+
   /v1/bird/reload:
     post:
       tags: [Deploy]

docs/production-checklist.md

@@ -0,0 +1,26 @@
+# Production checklist
+
+Краткий чеклист перед выводом EvoBGP в production (10+ клиентов, нестабильная сеть).
+
+## Обязательно
+
+- `EVOBGP_SEED_DEMO=0` — отключить demo-tenant и токен `Bearer dev`.
+- `EVOBGP_DEV_INSECURE` не задавать или `0` — не использовать lab-флаги в prod.
+- `EVOBGP_BUNDLE_SEED_HEX` — задать стабильный hex-ключ подписи бандлов; сохранить pubkey для нод.
+- PostgreSQL с TLS (`sslmode` не `disable`) при доступе вне private network.
+- `EVOBGP_CORS_ORIGINS` — явный whitelist origin веб-панели.
+- `EVOBGP_STALE_ON_UPSTREAM_ERROR=1` (по умолчанию) — stale snapshot при сбоях CDN/ASN/DoH.
+
+## Рекомендуется
+
+- `EVOBGP_JOB_MAX_CONCURRENT=16`, `EVOBGP_DB_MAX_CONNS=25`, `EVOBGP_COLLECT_CONCURRENCY=16` при росте tenants.
+- `EVOBGP_NODE_DISPATCH_INSECURE_TLS=0` — только валидный TLS к agent.
+- Ограничить `/metrics` сетевой политикой или reverse proxy.
+- Профиль `evobgp-all` или HA API + персистентная `job_audit` (PostgreSQL).
+- Мониторинг drift: `evobgp-deploy`, `last_applied_revision_id` vs published.
+
+## Не использовать в prod
+
+- `EVOBGP_CDN_ALLOW_PRIVATE=1` — только тесты/lab.
+- Plaintext `EVOBGP_API_KEYS` без ротации (break-glass — временно).
+- Ручное редактирование `evobgp_*.conf` на нодах без ревизии.

docs/releasing.md

@@ -11,6 +11,8 @@ EvoBGP использует [Conventional Commits](https://www.conventionalcommi
 | `feat!`, `fix!` или `BREAKING CHANGE:` в теле | major (1.0.0 → 2.0.0) |
 | `docs`, `chore`, `test` | без релиза |
 
+**Scope:** один идентификатор **без запятых** (`web`, `httpapi`, `api`). Заголовок `refactor(a, b): …` **не парсится** semantic-release → релиз не создаётся (commitlint на PR это тоже отклонит). Подробнее — раздел «Scope и semantic-release» ниже.
+
 `refactor` — patch без новых функций: перестройка кода/UI при том же поведении для пользователя. По semver на одном уровне с `fix`, но семантически «мельче» `feat` (не minor).
 
 Отдельного суффикса `1.x.y.fix` в semver нет: «fix» в Conventional Commits означает **patch** (третья цифра). Для починки пайплайна без смены продукта — `fix(ci):` или `ci:` (оба дают patch после настройки `.releaserc.json`).
@@ -62,6 +64,21 @@ API: `GET /version`, `GET /v1/version` — поля `version`, `git_sha`, `build
 
 Web UI показывает версию из API (footer sidebar, страница «Мониторинг»).
 
+## Scope и semantic-release
+
+Парсер [conventional-commits-parser](https://github.com/conventional-changelog/conventional-changelog/tree/master/packages/conventional-commits-parser) (его использует semantic-release) **не понимает запятые в scope**:
+
+| Заголовок | Парсится | Релиз |
+|-----------|----------|-------|
+| `refactor(web): fix layout` | да, `refactor` | patch |
+| `refactor(NetworkOverviewTab, NetworkSpeakersCard): fix layout` | **нет**, `type: null` | **нет** |
+
+Правило: **один scope** из таблицы в [.cursor/rules/conventional-commits.mdc](../.cursor/rules/conventional-commits.mdc) (`web`, `httpapi`, `api`, …).
+
+На push в `main` job **release** запускает `scripts/commit/verify-release-commits.mjs` — в логе будут предупреждения о непарсящихся коммитах.
+
+Если релиз «не создался», а CI зелёный: смотрите лог release — часто `No releasable commits`. Исправление: новый коммит с корректным заголовком (например `refactor(web): …`).
+
 ## CHANGELOG
 
 Release notes — в Gitea Release; файл `CHANGELOG.md` генерируется в CI и прикрепляется как asset, **не** попадает в git history.

docs/remote-speakers.md

@@ -47,10 +47,22 @@ Runbook для реплик **bird2 + evobgp-agent** на отдельных VPS
 
 | Порт | Кто | Зачем |
 |------|-----|-------|
-| **443** | IP CP (`PANEL_IP_WHITELIST`) | HTTPS dispatch + health |
+| **443** | IP CP (`PANEL_IP_WHITELIST`) | HTTPS dispatch, health, **`GET /v1/agent/bird/protocols`** (live peer sessions) |
 | **179** | BGP peers | Data plane |
 | **80** | ACME | Traefik → 443 |
 
+## Подготовка VPS (перед `docker compose up`)
+
+`bird2` — **`network_mode: host`**. Docker **не может** задать `net.ipv4.ip_forward` в таком контейнере; включите на **хосте**:
+
+```bash
+sysctl -w net.ipv4.ip_forward=1
+sysctl -w net.ipv6.conf.all.forwarding=1
+echo 'net.ipv4.ip_forward=1' | tee /etc/sysctl.d/99-evobgp-bird.conf
+echo 'net.ipv6.conf.all.forwarding=1' >> /etc/sysctl.d/99-evobgp-bird.conf
+sysctl --system
+```
+
 ## Безопасность (три участка)
 
 1. **CP → реплика:** HTTPS (LE) + Traefik ipallowlist + `agent_secret`.
@@ -82,6 +94,8 @@ Tenant `/v1/settings` (`bird_bgp_source_ipv4`) — fallback для master / ес
 
 | Симптом | Проверка |
 |---------|----------|
+| `sysctl net.ipv4.ip_forward not allowed in host network` | Уберите sysctls из compose (уже так в main); включите ip_forward на VPS (см. выше) |
+| `no service selected` | `--profile production` или `COMPOSE_PROFILES=production` |
 | Offline в UI | `GET https://AGENT_DOMAIN/v1/agent/health` с CP; LE cert; whitelist |
 | dispatch error | CP logs job meta; firewall 443; `agent_secret` |
 | verify-bundle fail | pubkey совпадает с CP seed; пересоберите pubkey после смены seed |

internal/agentserver/server.go

@@ -10,9 +10,12 @@ import (
 	"strings"
 	"time"
 
+	"evobgp/internal/birdfmt"
 	"evobgp/internal/nodecli"
 )
 
+const upstreamErrorDetail = "upstream request failed"
+
 // Config holds evobgp-agent serve settings.
 type Config struct {
 	Listen          string
@@ -41,6 +44,7 @@ type Server struct {
 func New(cfg Config) *Server {
 	s := &Server{cfg: cfg, mux: http.NewServeMux()}
 	s.mux.HandleFunc("GET /v1/agent/health", s.handleHealth)
+	s.mux.HandleFunc("GET /v1/agent/bird/protocols", s.handleBirdProtocols)
 	s.mux.HandleFunc("POST /v1/agent/sync", s.handleSync)
 	return s
 }
@@ -68,6 +72,30 @@ func (s *Server) handleHealth(w http.ResponseWriter, r *http.Request) {
 	writeJSON(w, http.StatusOK, body)
 }
 
+func (s *Server) handleBirdProtocols(w http.ResponseWriter, r *http.Request) {
+	if !s.authorize(r) {
+		writeProblem(w, http.StatusUnauthorized, "missing or invalid Authorization")
+		return
+	}
+	sock := strings.TrimSpace(s.cfg.Socket)
+	if sock == "" {
+		writeProblem(w, http.StatusServiceUnavailable, "EVOBGP_BIRDC_SOCKET not configured")
+		return
+	}
+	ctx, cancel := context.WithTimeout(r.Context(), 10*time.Second)
+	defer cancel()
+	out, err := birdfmt.ShowProtocols(ctx, sock, strings.TrimSpace(s.cfg.BirdcBin))
+	if err != nil {
+		log.Printf("agentserver: bird protocols: %v", err)
+		writeProblem(w, http.StatusBadGateway, upstreamErrorDetail)
+		return
+	}
+	writeJSON(w, http.StatusOK, map[string]any{
+		"ok":       true,
+		"sessions": birdfmt.ParseBGPSessions(out),
+	})
+}
+
 func (s *Server) handleSync(w http.ResponseWriter, r *http.Request) {
 	if !s.authorize(r) {
 		writeProblem(w, http.StatusUnauthorized, "missing or invalid Authorization")
@@ -100,7 +128,7 @@ func (s *Server) handleSync(w http.ResponseWriter, r *http.Request) {
 	})
 	if err != nil {
 		log.Printf("agentserver: sync: %v", err)
-		writeProblem(w, http.StatusBadGateway, err.Error())
+		writeProblem(w, http.StatusBadGateway, upstreamErrorDetail)
 		return
 	}
 	if s.cfg.OnSyncSuccess != nil {

internal/asnresolve/ripestat.go

@@ -13,6 +13,8 @@ import (
 	"strconv"
 	"strings"
 	"time"
+
+	"evobgp/internal/httpclient"
 )
 
 // DefaultRIPEStatURL is the RIPEstat announced-prefixes data call (no API key).
@@ -24,7 +26,7 @@ const DefaultASOverviewURL = "https://stat.ripe.net/data/as-overview/data.json"
 // AnnouncedPrefixes returns currently announced IPv4/IPv6 prefixes for the ASN (best-effort via RIPEstat).
 func AnnouncedPrefixes(ctx context.Context, hc *http.Client, asn int64) ([]netip.Prefix, error) {
 	if hc == nil {
-		hc = http.DefaultClient
+		hc = httpclient.New(httpclient.DefaultTimeout)
 	}
 	base := strings.TrimSpace(os.Getenv("EVOBGP_RIPESTAT_ANNOUNCED_PREFIXES_URL"))
 	if base == "" {
@@ -38,7 +40,7 @@ func AnnouncedPrefixes(ctx context.Context, hc *http.Client, asn int64) ([]netip
 	req.Header.Set("Accept", "application/json")
 	req.Header.Set("User-Agent", "evobgp-asnresolve/1.0")
 
-	resp, err := hc.Do(req)
+	resp, err := httpclient.DoWithBreaker(ctx, hc, req, 3)
 	if err != nil {
 		return nil, fmt.Errorf("ripestat fetch AS%d: %w", asn, err)
 	}
@@ -86,7 +88,7 @@ func AnnouncedPrefixes(ctx context.Context, hc *http.Client, asn int64) ([]netip
 // ASHolderName returns the holder / organization label for the ASN from RIPEstat as-overview (best-effort).
 func ASHolderName(ctx context.Context, hc *http.Client, asn int64) (string, error) {
 	if hc == nil {
-		hc = http.DefaultClient
+		hc = httpclient.New(httpclient.DefaultTimeout)
 	}
 	base := strings.TrimSpace(os.Getenv("EVOBGP_RIPESTAT_AS_OVERVIEW_URL"))
 	if base == "" {
@@ -100,7 +102,7 @@ func ASHolderName(ctx context.Context, hc *http.Client, asn int64) (string, erro
 	req.Header.Set("Accept", "application/json")
 	req.Header.Set("User-Agent", "evobgp-asnresolve/1.0")
 
-	resp, err := hc.Do(req)
+	resp, err := httpclient.DoWithBreaker(ctx, hc, req, 3)
 	if err != nil {
 		return "", fmt.Errorf("ripestat as-overview AS%d: %w", asn, err)
 	}

internal/birdfmt/bgp_sessions.go

@@ -0,0 +1,54 @@
+package birdfmt
+
+import (
+	"strings"
+)
+
+// BGPSession is one BGP protocol block from `birdc show protocols all`.
+type BGPSession struct {
+	Name     string `json:"name"`
+	Neighbor string `json:"neighbor,omitempty"`
+	State    string `json:"state"`
+}
+
+// ParseBGPSessions extracts BGP protocol name, state, and neighbor (if present) from birdc output.
+func ParseBGPSessions(output string) []BGPSession {
+	var out []BGPSession
+	var cur *BGPSession
+	for _, raw := range strings.Split(output, "\n") {
+		line := strings.TrimRight(raw, "\r")
+		trim := strings.TrimSpace(line)
+		if trim == "" {
+			cur = nil
+			continue
+		}
+		low := strings.ToLower(trim)
+		if strings.HasPrefix(low, "bird ") || strings.HasPrefix(low, "name ") || strings.HasPrefix(low, "table ") {
+			continue
+		}
+		if !strings.HasPrefix(line, " ") && !strings.HasPrefix(line, "\t") {
+			if isBGPProtocolSummaryRow(trim) {
+				fields := strings.Fields(trim)
+				state := extractBGPSessionStateLine(trim)
+				if state == "" && len(fields) >= 4 {
+					state = fields[3]
+				}
+				out = append(out, BGPSession{Name: fields[0], State: state})
+				cur = &out[len(out)-1]
+			} else {
+				cur = nil
+			}
+			continue
+		}
+		if cur == nil {
+			continue
+		}
+		for _, prefix := range []string{"Neighbor address:", "Neighbor Address:", "Neighbor:"} {
+			if idx := strings.Index(trim, prefix); idx >= 0 {
+				cur.Neighbor = strings.TrimSpace(trim[idx+len(prefix):])
+				break
+			}
+		}
+	}
+	return out
+}

internal/birdfmt/bgp_sessions_test.go

@@ -0,0 +1,26 @@
+package birdfmt
+
+import "testing"
+
+func TestParseBGPSessions_neighborAndState(t *testing.T) {
+	sample := `
+BIRD 2.14 ready.
+Name       Proto      Table      State  Since         Info
+device1    Device     ---        up     10:00:00
+evobgp_p_abc123 BGP      master4    up     10:00:05     Established
+  Neighbor address: 198.51.100.2
+  Neighbor AS:    65001
+evobgp_p_def456 BGP      master4    up     10:00:06     Active
+  Neighbor address: 2001:db8::2
+`
+	sessions := ParseBGPSessions(sample)
+	if len(sessions) != 2 {
+		t.Fatalf("got %d sessions want 2", len(sessions))
+	}
+	if sessions[0].Name != "evobgp_p_abc123" || sessions[0].State != "Established" || sessions[0].Neighbor != "198.51.100.2" {
+		t.Fatalf("session0: %+v", sessions[0])
+	}
+	if sessions[1].Neighbor != "2001:db8::2" || sessions[1].State != "Active" {
+		t.Fatalf("session1: %+v", sessions[1])
+	}
+}

internal/birdfmt/peer_protocol.go

@@ -0,0 +1,16 @@
+package birdfmt
+
+import "strings"
+
+// PeerProtocolName returns the BIRD protocol name for a control-plane peer UUID.
+// Must stay in sync with pipeline peer rendering.
+func PeerProtocolName(peerID string) string {
+	s := strings.ReplaceAll(strings.TrimSpace(peerID), "-", "")
+	if len(s) > 16 {
+		s = s[:16]
+	}
+	if s == "" {
+		s = "x"
+	}
+	return "evobgp_p_" + s
+}

internal/httpapi/bootstrap.go

@@ -7,6 +7,7 @@ import (
 	"time"
 
 	"evobgp/internal/db"
+	"evobgp/internal/httpclient"
 	"evobgp/internal/jobs"
 	"evobgp/internal/observability"
 	"evobgp/internal/repository"
@@ -17,7 +18,7 @@ import (
 
 // NewCDNHTTPClient returns the shared HTTP client for CDN and preview fetches (PERF-02 / ERR-03).
 func NewCDNHTTPClient() *http.Client {
-	return &http.Client{Timeout: 45 * time.Second}
+	return httpclient.New(httpclient.DefaultTimeout)
 }
 
 // BootstrapWorkers opens the same store.Backend and jobs.Registry as New (without HTTP or bundle keys).
@@ -55,18 +56,40 @@ func BootstrapWorkers(ctx context.Context, opts Options) (store.Backend, *jobs.R
 	wk.Registry = reg
 	if pool != nil {
 		audit := repository.NewJobAuditWriter(pool)
-		reg.SetTerminalHook(func(j *jobs.Job) {
+		jobMeta := func(j *jobs.Job) map[string]any {
 			if j == nil {
-				return
+				return nil
 			}
 			st := j.Snapshot()
-			status, _ := st["status"].(string)
-			var errMsg *string
-			if e, ok := st["error"].(string); ok && e != "" {
-				errMsg = &e
-			}
-			audit.MarkTerminal(context.Background(), j.TenantID, j.ID, status, errMsg, time.Now().UTC())
-		})
+			meta, _ := st["meta"].(map[string]any)
+			return meta
+		}
+		reg.SetPersistHooks(
+			func(j *jobs.Job) {
+				if j == nil {
+					return
+				}
+				audit.UpsertQueued(context.Background(), j.TenantID, j.ID, j.Kind, j.IdempotencyKey, j.ModuleID, jobMeta(j))
+			},
+			func(j *jobs.Job) {
+				if j == nil {
+					return
+				}
+				audit.UpsertRunning(context.Background(), j.TenantID, j.ID, j.Kind, j.IdempotencyKey, jobMeta(j))
+			},
+			func(j *jobs.Job) {
+				if j == nil {
+					return
+				}
+				st := j.Snapshot()
+				status, _ := st["status"].(string)
+				var errMsg *string
+				if e, ok := st["error"].(string); ok && e != "" {
+					errMsg = &e
+				}
+				audit.MarkTerminal(context.Background(), j.TenantID, j.ID, status, errMsg, time.Now().UTC())
+			},
+		)
 	}
 	observability.RegisterStoreBackend(backend)
 	return backend, reg, pool, nil

internal/httpapi/peers_live.go

@@ -0,0 +1,295 @@
+package httpapi
+
+import (
+	"context"
+	"net/netip"
+	"os"
+	"strings"
+	"sync"
+	"time"
+
+	"evobgp/internal/birdfmt"
+	"evobgp/internal/nodedispatch"
+	"evobgp/internal/store"
+)
+
+const peerLiveCacheTTL = 15 * time.Second
+
+type speakerBGPLive struct {
+	SpeakerID string
+	Label     string
+	Sessions  []birdfmt.BGPSession
+	Error     string
+}
+
+type peerLiveCacheEntry struct {
+	at    time.Time
+	views []speakerBGPLive
+}
+
+var peerLiveCache sync.Map // tenantID -> peerLiveCacheEntry
+
+type peerSessionOnSpeaker struct {
+	SpeakerID string `json:"speaker_id"`
+	Label     string `json:"label"`
+	State     string `json:"state"`
+	PollError string `json:"poll_error,omitempty"`
+}
+
+type liveSpeakerPoll struct {
+	SpeakerID    string `json:"speaker_id"`
+	Label        string `json:"label"`
+	OK           bool   `json:"ok"`
+	SessionCount int    `json:"session_count"`
+	PollError    string `json:"poll_error,omitempty"`
+}
+
+func speakerDisplayLabel(sp *store.Speaker) string {
+	if sp == nil {
+		return ""
+	}
+	meta := store.ParseSpeakerMeta(sp.MetaJSON)
+	host := strings.TrimSpace(meta.AgentDomain)
+	if host == "" {
+		host = strings.TrimSpace(sp.Endpoint)
+	}
+	if strings.EqualFold(strings.TrimSpace(sp.Role), "master") {
+		if host != "" {
+			return "CP · " + host
+		}
+		return "CP (master)"
+	}
+	if host != "" {
+		return host
+	}
+	return sp.ID
+}
+
+func masterSpeakerID(speakers []*store.Speaker) string {
+	for _, sp := range speakers {
+		if sp != nil && strings.EqualFold(strings.TrimSpace(sp.Role), "master") {
+			return sp.ID
+		}
+	}
+	return ""
+}
+
+func (s *Server) collectSpeakerBGPLive(ctx context.Context, tenantID string, fresh bool) []speakerBGPLive {
+	if !fresh {
+		if v, ok := peerLiveCache.Load(tenantID); ok {
+			ent := v.(peerLiveCacheEntry)
+			if time.Since(ent.at) < peerLiveCacheTTL {
+				return ent.views
+			}
+		}
+	}
+	speakers := s.store.ListSpeakersForTenant(tenantID)
+	views := make([]speakerBGPLive, 0, len(speakers)+1)
+
+	if sock := strings.TrimSpace(os.Getenv("EVOBGP_BIRDC_SOCKET")); sock != "" {
+		v := speakerBGPLive{Label: "CP (local BIRD)"}
+		if mid := masterSpeakerID(speakers); mid != "" {
+			v.SpeakerID = mid
+			for _, sp := range speakers {
+				if sp != nil && sp.ID == mid {
+					v.Label = speakerDisplayLabel(sp)
+					break
+				}
+			}
+		}
+		out, err := birdfmt.ShowProtocols(ctx, sock, strings.TrimSpace(os.Getenv("EVOBGP_BIRDC_BIN")))
+		if err != nil {
+			v.Error = err.Error()
+		} else {
+			v.Sessions = birdfmt.ParseBGPSessions(out)
+		}
+		views = append(views, v)
+	}
+
+	opts := nodedispatch.Options{Timeout: 8 * time.Second}
+	type resWrap struct {
+		sp  *store.Speaker
+		res nodedispatch.BirdProtocolsResult
+	}
+	ch := make(chan resWrap, len(speakers))
+	var wg sync.WaitGroup
+	for _, sp := range speakers {
+		if sp == nil {
+			continue
+		}
+		meta := store.ParseSpeakerMeta(sp.MetaJSON)
+		if !store.SpeakerNeedsRemoteDispatch(sp.Role, meta) {
+			continue
+		}
+		wg.Add(1)
+		go func(speaker *store.Speaker) {
+			defer wg.Done()
+			ch <- resWrap{
+				sp:  speaker,
+				res: nodedispatch.FetchBirdProtocols(ctx, speaker, opts),
+			}
+		}(sp)
+	}
+	wg.Wait()
+	close(ch)
+	for rw := range ch {
+		views = append(views, speakerBGPLive{
+			SpeakerID: rw.sp.ID,
+			Label:     speakerDisplayLabel(rw.sp),
+			Sessions:  rw.res.Sessions,
+			Error:     rw.res.Error,
+		})
+	}
+
+	peerLiveCache.Store(tenantID, peerLiveCacheEntry{at: time.Now(), views: views})
+	return views
+}
+
+func liveSpeakerPollJSON(views []speakerBGPLive) []liveSpeakerPoll {
+	out := make([]liveSpeakerPoll, 0, len(views))
+	for _, v := range views {
+		out = append(out, liveSpeakerPoll{
+			SpeakerID:    v.SpeakerID,
+			Label:        v.Label,
+			OK:           v.Error == "",
+			SessionCount: len(v.Sessions),
+			PollError:    v.Error,
+		})
+	}
+	return out
+}
+
+func findPeerSession(sessions []birdfmt.BGPSession, protoName string, neighbor netip.Addr, hasNeighbor bool) *birdfmt.BGPSession {
+	for i := range sessions {
+		if peerSessionMatches(sessions[i], protoName, neighbor, hasNeighbor) {
+			return &sessions[i]
+		}
+	}
+	return nil
+}
+
+func matchPeerOnSpeakers(peer *store.BGPPeer, views []speakerBGPLive) (
+	bestState string,
+	connectedID string,
+	connectedLabel string,
+	establishedOn []peerSessionOnSpeaker,
+	on []peerSessionOnSpeaker,
+	mismatch bool,
+) {
+	if peer == nil {
+		return "", "", "", nil, nil, false
+	}
+	neighbor, hasNeighbor := store.ParsePeerNeighbor(peer.Neighbor)
+	protoName := birdfmt.PeerProtocolName(peer.ID)
+
+	for _, v := range views {
+		if v.Error != "" && len(v.Sessions) == 0 {
+			on = append(on, peerSessionOnSpeaker{
+				SpeakerID: v.SpeakerID,
+				Label:     v.Label,
+				PollError: v.Error,
+			})
+			continue
+		}
+		sess := findPeerSession(v.Sessions, protoName, neighbor, hasNeighbor)
+		if sess == nil {
+			on = append(on, peerSessionOnSpeaker{
+				SpeakerID: v.SpeakerID,
+				Label:     v.Label,
+				State:     "absent",
+			})
+			continue
+		}
+		hit := peerSessionOnSpeaker{
+			SpeakerID: v.SpeakerID,
+			Label:     v.Label,
+			State:     sess.State,
+		}
+		on = append(on, hit)
+		if strings.EqualFold(strings.TrimSpace(sess.State), "Established") {
+			establishedOn = append(establishedOn, hit)
+		}
+		if bestState == "" || sessionStateRank(sess.State) > sessionStateRank(bestState) {
+			bestState = sess.State
+		}
+	}
+
+	if len(establishedOn) > 0 {
+		bestState = "Established"
+		labels := make([]string, 0, len(establishedOn))
+		for _, e := range establishedOn {
+			labels = append(labels, e.Label)
+		}
+		connectedLabel = strings.Join(labels, ", ")
+		if len(establishedOn) == 1 {
+			connectedID = establishedOn[0].SpeakerID
+		}
+	} else if len(on) == 1 && on[0].PollError == "" && on[0].State != "" {
+		connectedID = on[0].SpeakerID
+		connectedLabel = on[0].Label
+	}
+
+	if peer.SpeakerID != nil && strings.TrimSpace(*peer.SpeakerID) != "" && len(establishedOn) > 0 {
+		want := strings.TrimSpace(*peer.SpeakerID)
+		found := false
+		for _, e := range establishedOn {
+			if strings.EqualFold(strings.TrimSpace(e.SpeakerID), want) {
+				found = true
+				break
+			}
+		}
+		mismatch = !found
+	}
+	return bestState, connectedID, connectedLabel, establishedOn, on, mismatch
+}
+
+func peerSessionMatches(sess birdfmt.BGPSession, protoName string, neighbor netip.Addr, hasNeighbor bool) bool {
+	if strings.EqualFold(strings.TrimSpace(sess.Name), protoName) {
+		return true
+	}
+	if !hasNeighbor || strings.TrimSpace(sess.Neighbor) == "" {
+		return false
+	}
+	peerAddr, ok := store.ParsePeerNeighbor(sess.Neighbor)
+	if !ok {
+		return false
+	}
+	return peerAddr == neighbor
+}
+
+func sessionStateRank(state string) int {
+	switch strings.ToLower(strings.TrimSpace(state)) {
+	case "established":
+		return 100
+	case "openconfirm", "opensent":
+		return 80
+	case "active", "connect":
+		return 60
+	case "idle":
+		return 20
+	default:
+		return 10
+	}
+}
+
+func applyPeerLiveFields(row map[string]any, peer *store.BGPPeer, views []speakerBGPLive) {
+	state, connID, connLabel, establishedOn, on, mismatch := matchPeerOnSpeakers(peer, views)
+	row["session_on_speakers"] = on
+	row["established_on_speakers"] = establishedOn
+	row["session_conflict"] = false
+	row["session_mismatch"] = mismatch
+	if state != "" {
+		row["session_state"] = state
+	}
+	if connLabel != "" {
+		row["connected_speaker_label"] = connLabel
+	}
+	row["connected_speaker_id"] = peerLiveSpeakerIDOrNull(connID)
+}
+
+func peerLiveSpeakerIDOrNull(id string) any {
+	if strings.TrimSpace(id) == "" {
+		return nil
+	}
+	return id
+}

internal/httpapi/peers_live_test.go

@@ -0,0 +1,79 @@
+package httpapi
+
+import (
+	"testing"
+
+	"evobgp/internal/birdfmt"
+	"evobgp/internal/store"
+)
+
+func TestMatchPeerOnSpeakers_establishedOnReplica(t *testing.T) {
+	peer := &store.BGPPeer{
+		ID:       "aaaaaaaa-bbbb-cccc-dddd-eeeeeeeeeeee",
+		Neighbor: "198.51.100.2",
+	}
+	views := []speakerBGPLive{
+		{
+			SpeakerID: "master-id",
+			Label:     "CP · bgp.shz.su",
+			Sessions: []birdfmt.BGPSession{
+				{Name: birdfmt.PeerProtocolName(peer.ID), Neighbor: "198.51.100.2", State: "Established"},
+			},
+		},
+		{
+			SpeakerID: "replica-id",
+			Label:     "bgp2.shz.su",
+			Sessions: []birdfmt.BGPSession{
+				{Name: birdfmt.PeerProtocolName(peer.ID), Neighbor: "198.51.100.2", State: "Established"},
+			},
+		},
+	}
+	state, connID, connLabel, established, on, mismatch := matchPeerOnSpeakers(peer, views)
+	if state != "Established" || connID != "" || connLabel != "CP · bgp.shz.su, bgp2.shz.su" {
+		t.Fatalf("got state=%q conn=%q label=%q", state, connID, connLabel)
+	}
+	if mismatch || len(on) != 2 || len(established) != 2 {
+		t.Fatalf("on=%+v established=%+v mismatch=%v", on, established, mismatch)
+	}
+}
+
+func TestMatchPeerOnSpeakers_multipleEstablished(t *testing.T) {
+	peer := &store.BGPPeer{ID: "aaaaaaaa-bbbb-cccc-dddd-eeeeeeeeeeee", Neighbor: "198.51.100.2/32"}
+	views := []speakerBGPLive{
+		{SpeakerID: "a", Label: "n1", Sessions: []birdfmt.BGPSession{{Name: birdfmt.PeerProtocolName(peer.ID), State: "Established"}}},
+		{SpeakerID: "b", Label: "n2", Sessions: []birdfmt.BGPSession{{Name: birdfmt.PeerProtocolName(peer.ID), State: "Established"}}},
+	}
+	_, connID, label, established, on, mismatch := matchPeerOnSpeakers(peer, views)
+	if mismatch || connID != "" || label != "n1, n2" || len(established) != 2 || len(on) != 2 {
+		t.Fatalf("connID=%q label=%q established=%+v on=%+v mismatch=%v", connID, label, established, on, mismatch)
+	}
+}
+
+func TestMatchPeerOnSpeakers_mismatchConfiguredSpeaker(t *testing.T) {
+	replica := "replica-id"
+	peer := &store.BGPPeer{
+		ID:        "aaaaaaaa-bbbb-cccc-dddd-eeeeeeeeeeee",
+		Neighbor:  "198.51.100.2",
+		SpeakerID: &replica,
+	}
+	views := []speakerBGPLive{
+		{SpeakerID: "master-id", Label: "CP", Sessions: []birdfmt.BGPSession{{Name: birdfmt.PeerProtocolName(peer.ID), State: "Established"}}},
+		{SpeakerID: replica, Label: "bgp2", Sessions: []birdfmt.BGPSession{{Name: birdfmt.PeerProtocolName(peer.ID), State: "Idle"}}},
+	}
+	_, _, _, _, _, mismatch := matchPeerOnSpeakers(peer, views)
+	if !mismatch {
+		t.Fatal("expected mismatch when configured replica has no Established")
+	}
+}
+
+func TestMatchPeerOnSpeakers_pollError(t *testing.T) {
+	peer := &store.BGPPeer{ID: "aaaaaaaa-bbbb-cccc-dddd-eeeeeeeeeeee", Neighbor: "198.51.100.2"}
+	views := []speakerBGPLive{
+		{Label: "CP (local BIRD)", Sessions: []birdfmt.BGPSession{{Name: birdfmt.PeerProtocolName(peer.ID), State: "Established"}}},
+		{SpeakerID: "replica-id", Label: "bgp2.shz.su", Error: "HTTP 404: Not Found"},
+	}
+	_, _, _, established, on, _ := matchPeerOnSpeakers(peer, views)
+	if len(established) != 1 || len(on) != 2 || on[1].PollError == "" {
+		t.Fatalf("on=%+v established=%+v", on, established)
+	}
+}

internal/httpapi/routes.go

@@ -283,17 +283,21 @@ func (s *Server) handleListPeers(w http.ResponseWriter, r *http.Request) {
 	}
 	allPeers := s.store.ListPeers(a.TenantID)
 	page, next, more := store.PaginateOffset(allPeers, r.URL.Query().Get("cursor"), parseListLimit(r))
-	liveStates := s.liveBGPProtocolStates(r)
+	fresh := r != nil && strings.EqualFold(strings.TrimSpace(r.URL.Query().Get("live")), "1")
+	ctx, cancel := context.WithTimeout(r.Context(), 12*time.Second)
+	defer cancel()
+	liveViews := s.collectSpeakerBGPLive(ctx, a.TenantID, fresh)
 	items := make([]map[string]any, 0, len(page))
 	for _, p := range page {
 		row := peerJSON(p)
-		if st, ok := liveStates[peerProtocolNameForID(p.ID)]; ok && strings.TrimSpace(st) != "" {
-			row["session_state"] = strings.TrimSpace(st)
-		}
+		applyPeerLiveFields(row, p, liveViews)
 		items = append(items, row)
 	}
 	writeJSON(w, http.StatusOK, map[string]any{
-		"items": items, "next_cursor": strPtrOrNull(next), "has_more": more,
+		"items":             items,
+		"next_cursor":       strPtrOrNull(next),
+		"has_more":          more,
+		"live_speaker_poll": liveSpeakerPollJSON(liveViews),
 	})
 }
 
@@ -366,16 +370,9 @@ func extractBGPSessionState(line string) string {
 	return ""
 }
 
-// peerProtocolNameForID must stay in sync with pipeline peer protocol naming.
+// peerProtocolNameForID forwards to birdfmt for tests and legacy callers.
 func peerProtocolNameForID(peerID string) string {
-	s := strings.ReplaceAll(strings.TrimSpace(peerID), "-", "")
-	if len(s) > 16 {
-		s = s[:16]
-	}
-	if s == "" {
-		s = "x"
-	}
-	return "evobgp_p_" + s
+	return birdfmt.PeerProtocolName(peerID)
 }
 
 func (s *Server) handleListSpeakers(w http.ResponseWriter, r *http.Request) {
@@ -388,9 +385,22 @@ func (s *Server) handleListSpeakers(w http.ResponseWriter, r *http.Request) {
 		return
 	}
 	speakers := s.store.ListSpeakersForTenant(a.TenantID)
+	fresh := r != nil && strings.EqualFold(strings.TrimSpace(r.URL.Query().Get("live")), "1")
+	var liveByID map[string]map[string]any
+	if fresh {
+		ctx, cancel := context.WithTimeout(r.Context(), 12*time.Second)
+		defer cancel()
+		liveByID = s.collectSpeakerLiveStatus(ctx, a.TenantID, true, speakers)
+	}
 	items := make([]map[string]any, 0, len(speakers))
 	for _, sp := range speakers {
-		items = append(items, speakerJSONFromStore(s.store, sp))
+		row := speakerJSONFromStore(s.store, sp)
+		if liveByID != nil {
+			if live, ok := liveByID[sp.ID]; ok {
+				row["live"] = live
+			}
+		}
+		items = append(items, row)
 	}
 	writeJSON(w, http.StatusOK, map[string]any{
 		"items": items, "next_cursor": nil, "has_more": false,
@@ -569,7 +579,7 @@ func (s *Server) handleGetRevision(w http.ResponseWriter, r *http.Request) {
 	if !s.requireAtLeast(w, a, "viewer") {
 		return
 	}
-	rev, err := s.store.GetRevision(a.TenantID, r.PathValue("revision_id"))
+	rev, err := s.store.GetRevisionSummary(a.TenantID, r.PathValue("revision_id"))
 	if err != nil {
 		writeProblem(w, http.StatusNotFound, "Not Found", "revision not found")
 		return

internal/httpapi/routes_crud.go

@@ -242,6 +242,14 @@ func (s *Server) handlePreviewCDNSource(w http.ResponseWriter, r *http.Request)
 		writeProblem(w, http.StatusUnprocessableEntity, "Unprocessable Entity", "url is required")
 		return
 	}
+	if _, err := pipeline.ValidateCDNURL(u); err != nil {
+		writeProblem(w, http.StatusUnprocessableEntity, "Unprocessable Entity", invalidInputDetail)
+		return
+	}
+	if err := pipeline.ResolveCDNURLHost(r.Context(), u); err != nil {
+		writeProblem(w, http.StatusUnprocessableEntity, "Unprocessable Entity", invalidInputDetail)
+		return
+	}
 	mod, err := s.store.GetModule(a.TenantID, r.PathValue("module_id"))
 	if err != nil {
 		writeStoreErr(w, err)
@@ -304,6 +312,16 @@ func (s *Server) handlePostCDNSource(w http.ResponseWriter, r *http.Request) {
 		writeProblem(w, http.StatusBadRequest, "Bad Request", "invalid json")
 		return
 	}
+	if body.URL != "" {
+		if _, err := pipeline.ValidateCDNURL(body.URL); err != nil {
+			writeProblem(w, http.StatusUnprocessableEntity, "Unprocessable Entity", invalidInputDetail)
+			return
+		}
+		if err := pipeline.ResolveCDNURLHost(r.Context(), body.URL); err != nil {
+			writeProblem(w, http.StatusUnprocessableEntity, "Unprocessable Entity", invalidInputDetail)
+			return
+		}
+	}
 	mid := r.PathValue("module_id")
 	x, err := s.store.CreateCDNSource(a.TenantID, mid, &body)
 	if err != nil {
@@ -324,6 +342,16 @@ func (s *Server) handlePatchCDNSource(w http.ResponseWriter, r *http.Request) {
 		writeProblem(w, http.StatusBadRequest, "Bad Request", "invalid json")
 		return
 	}
+	if body.URL != nil && strings.TrimSpace(*body.URL) != "" {
+		if _, err := pipeline.ValidateCDNURL(*body.URL); err != nil {
+			writeProblem(w, http.StatusUnprocessableEntity, "Unprocessable Entity", invalidInputDetail)
+			return
+		}
+		if err := pipeline.ResolveCDNURLHost(r.Context(), *body.URL); err != nil {
+			writeProblem(w, http.StatusUnprocessableEntity, "Unprocessable Entity", invalidInputDetail)
+			return
+		}
+	}
 	mid := r.PathValue("module_id")
 	x, err := s.store.UpdateCDNSource(a.TenantID, mid, r.PathValue("source_id"), &body)
 	if err != nil {

internal/httpapi/speakers.go

@@ -39,7 +39,10 @@ func speakerJSONFromStore(st store.Backend, sp *store.Speaker) map[string]any {
 	if strings.TrimSpace(sp.MetaJSON) != "" && sp.MetaJSON != "{}" {
 		var raw map[string]any
 		if json.Unmarshal([]byte(sp.MetaJSON), &raw) == nil {
-			m["meta_json"] = raw
+			delete(raw, "agent_secret")
+			if len(raw) > 0 {
+				m["meta_json"] = raw
+			}
 		}
 	}
 	if meta.AgentDomain != "" {

internal/httpapi/speakers_live.go

@@ -0,0 +1,129 @@
+package httpapi
+
+import (
+	"context"
+	"strings"
+	"sync"
+	"time"
+
+	"evobgp/internal/birdfmt"
+	"evobgp/internal/nodedispatch"
+	"evobgp/internal/store"
+)
+
+func countBGPSessions(sessions []birdfmt.BGPSession) (total, established int) {
+	total = len(sessions)
+	for _, s := range sessions {
+		if strings.EqualFold(strings.TrimSpace(s.State), "Established") {
+			established++
+		}
+	}
+	return total, established
+}
+
+func speakerLiveStatusJSON(sp *store.Speaker, view speakerBGPLive, health *nodedispatch.AgentHealthResult) map[string]any {
+	total, established := countBGPSessions(view.Sessions)
+	m := map[string]any{
+		"label":              view.Label,
+		"bgp_poll_ok":        view.Error == "",
+		"bgp_sessions_total": total,
+		"bgp_established":    established,
+	}
+	if view.Error != "" {
+		m["bgp_poll_error"] = view.Error
+	}
+	if health != nil {
+		m["agent_ok"] = health.OK
+		if health.Error != "" {
+			m["agent_error"] = health.Error
+		}
+		if health.LastSyncAt != "" {
+			m["agent_last_sync_at"] = health.LastSyncAt
+		}
+		if health.LastAppliedRevisionID != "" {
+			m["agent_last_applied_revision_id"] = health.LastAppliedRevisionID
+		}
+	} else if sp != nil && strings.EqualFold(strings.TrimSpace(sp.Role), "master") {
+		m["agent_ok"] = view.Error == ""
+		if view.Error != "" {
+			m["agent_error"] = view.Error
+		}
+	} else if sp != nil && store.SpeakerNeedsRemoteDispatch(sp.Role, store.ParseSpeakerMeta(sp.MetaJSON)) {
+		m["agent_ok"] = false
+		m["agent_error"] = "agent health not polled"
+	}
+	if len(view.Sessions) > 0 {
+		sess := make([]map[string]any, 0, len(view.Sessions))
+		for _, s := range view.Sessions {
+			row := map[string]any{
+				"name":  s.Name,
+				"state": s.State,
+			}
+			if strings.TrimSpace(s.Neighbor) != "" {
+				row["neighbor"] = s.Neighbor
+			}
+			sess = append(sess, row)
+		}
+		m["sessions"] = sess
+	}
+	return m
+}
+
+func (s *Server) collectSpeakerLiveStatus(ctx context.Context, tenantID string, fresh bool, speakers []*store.Speaker) map[string]map[string]any {
+	views := s.collectSpeakerBGPLive(ctx, tenantID, fresh)
+	viewByID := make(map[string]speakerBGPLive, len(views))
+	for _, v := range views {
+		if v.SpeakerID != "" {
+			viewByID[v.SpeakerID] = v
+		}
+	}
+
+	opts := nodedispatch.Options{Timeout: 8 * time.Second}
+	type healthWrap struct {
+		id string
+		h  nodedispatch.AgentHealthResult
+	}
+	healthCh := make(chan healthWrap, len(speakers))
+	var wg sync.WaitGroup
+	for _, sp := range speakers {
+		if sp == nil {
+			continue
+		}
+		meta := store.ParseSpeakerMeta(sp.MetaJSON)
+		if !store.SpeakerNeedsRemoteDispatch(sp.Role, meta) {
+			continue
+		}
+		wg.Add(1)
+		go func(speaker *store.Speaker) {
+			defer wg.Done()
+			healthCh <- healthWrap{
+				id: speaker.ID,
+				h:  nodedispatch.FetchAgentHealth(ctx, speaker, opts),
+			}
+		}(sp)
+	}
+	wg.Wait()
+	close(healthCh)
+	healthByID := make(map[string]nodedispatch.AgentHealthResult, len(speakers))
+	for hw := range healthCh {
+		healthByID[hw.id] = hw.h
+	}
+
+	out := make(map[string]map[string]any, len(speakers))
+	for _, sp := range speakers {
+		if sp == nil {
+			continue
+		}
+		view, ok := viewByID[sp.ID]
+		if !ok {
+			view = speakerBGPLive{SpeakerID: sp.ID, Label: speakerDisplayLabel(sp)}
+		}
+		var hp *nodedispatch.AgentHealthResult
+		if h, ok := healthByID[sp.ID]; ok {
+			hCopy := h
+			hp = &hCopy
+		}
+		out[sp.ID] = speakerLiveStatusJSON(sp, view, hp)
+	}
+	return out
+}

internal/httpapi/speakers_live_test.go

@@ -0,0 +1,74 @@
+package httpapi
+
+import (
+	"testing"
+
+	"evobgp/internal/birdfmt"
+	"evobgp/internal/nodedispatch"
+	"evobgp/internal/store"
+)
+
+func TestCountBGPSessions(t *testing.T) {
+	total, est := countBGPSessions([]birdfmt.BGPSession{
+		{Name: "p1", State: "Established"},
+		{Name: "p2", State: "Idle"},
+		{Name: "p3", State: "established"},
+	})
+	if total != 3 || est != 2 {
+		t.Fatalf("total=%d established=%d", total, est)
+	}
+}
+
+func TestSpeakerLiveStatusJSON_masterUsesBirdPoll(t *testing.T) {
+	sp := &store.Speaker{ID: "m1", Role: "master", Endpoint: "https://cp.example"}
+	view := speakerBGPLive{
+		SpeakerID: "m1",
+		Label:     "CP · cp.example",
+		Sessions: []birdfmt.BGPSession{
+			{Name: "evobgp_peer_x", State: "Established"},
+		},
+	}
+	m := speakerLiveStatusJSON(sp, view, nil)
+	if m["agent_ok"] != true || m["bgp_established"] != 1 || m["bgp_sessions_total"] != 1 {
+		t.Fatalf("got %#v", m)
+	}
+}
+
+func TestSpeakerLiveStatusJSON_replicaWithHealth(t *testing.T) {
+	sp := &store.Speaker{
+		ID:       "r1",
+		Role:     "replica",
+		Endpoint: "https://node.example",
+		MetaJSON: `{"agent_domain":"node.example","agent_secret":"s"}`,
+	}
+	view := speakerBGPLive{
+		SpeakerID: "r1",
+		Label:     "node.example",
+		Sessions:  []birdfmt.BGPSession{{Name: "p", State: "Idle"}},
+	}
+	health := &nodedispatch.AgentHealthResult{
+		OK:                    true,
+		LastSyncAt:            "2026-05-21T12:00:00Z",
+		LastAppliedRevisionID: "rev-1",
+	}
+	m := speakerLiveStatusJSON(sp, view, health)
+	if m["agent_ok"] != true || m["agent_last_sync_at"] != "2026-05-21T12:00:00Z" {
+		t.Fatalf("got %#v", m)
+	}
+	if m["bgp_established"] != 0 || m["bgp_poll_ok"] != true {
+		t.Fatalf("bgp fields: %#v", m)
+	}
+}
+
+func TestSpeakerLiveStatusJSON_pollError(t *testing.T) {
+	sp := &store.Speaker{ID: "r1", Role: "replica", MetaJSON: `{"agent_domain":"x.example"}`}
+	view := speakerBGPLive{SpeakerID: "r1", Label: "x.example", Error: "HTTP 503"}
+	health := &nodedispatch.AgentHealthResult{OK: false, Error: "timeout"}
+	m := speakerLiveStatusJSON(sp, view, health)
+	if m["bgp_poll_ok"] != false || m["bgp_poll_error"] != "HTTP 503" {
+		t.Fatalf("got %#v", m)
+	}
+	if m["agent_ok"] != false {
+		t.Fatalf("agent_ok: %#v", m)
+	}
+}

internal/httpapi/speakers_redact_test.go

@@ -0,0 +1,62 @@
+package httpapi
+
+import (
+	"encoding/json"
+	"net/http"
+	"net/http/httptest"
+	"strings"
+	"testing"
+)
+
+func TestGetSpeaker_redactsAgentSecret(t *testing.T) {
+	srv, err := New(Options{InsecureDev: true, SeedDemo: true, BundleSeedHex: testBundleSeed})
+	if err != nil {
+		t.Fatal(err)
+	}
+	defer srv.Close()
+	tenant, _, _, _, demoSpk := srv.Store().DemoIDs()
+	mustSetTestAPIKeys(t, srv, "vwkey|"+tenant+"|viewer")
+
+	req := httptest.NewRequest(http.MethodGet, "/v1/speakers/"+demoSpk, nil)
+	req.Header.Set("Authorization", "Bearer vwkey")
+	rec := httptest.NewRecorder()
+	srv.Handler().ServeHTTP(rec, req)
+	if rec.Code != http.StatusOK {
+		t.Fatalf("status %d body %s", rec.Code, rec.Body.String())
+	}
+	var out map[string]any
+	if err := json.Unmarshal(rec.Body.Bytes(), &out); err != nil {
+		t.Fatal(err)
+	}
+	if out["agent_secret"] != nil {
+		t.Fatalf("agent_secret must not appear at top level: %#v", out["agent_secret"])
+	}
+	meta, _ := out["meta_json"].(map[string]any)
+	if meta != nil {
+		if v, ok := meta["agent_secret"]; ok && v != nil && v != "" {
+			t.Fatalf("agent_secret must be redacted from meta_json: %#v", v)
+		}
+	}
+}
+
+func TestListSpeakers_redactsAgentSecret(t *testing.T) {
+	srv, err := New(Options{InsecureDev: true, SeedDemo: true, BundleSeedHex: testBundleSeed})
+	if err != nil {
+		t.Fatal(err)
+	}
+	defer srv.Close()
+	tenant, _, _, _, _ := srv.Store().DemoIDs()
+	mustSetTestAPIKeys(t, srv, "vwkey|"+tenant+"|viewer")
+
+	req := httptest.NewRequest(http.MethodGet, "/v1/speakers", nil)
+	req.Header.Set("Authorization", "Bearer vwkey")
+	rec := httptest.NewRecorder()
+	srv.Handler().ServeHTTP(rec, req)
+	if rec.Code != http.StatusOK {
+		t.Fatalf("status %d body %s", rec.Code, rec.Body.String())
+	}
+	body := rec.Body.String()
+	if strings.Contains(body, "agent_secret") {
+		t.Fatalf("list response must not contain agent_secret: %s", body)
+	}
+}

internal/httpclient/circuit.go

@@ -0,0 +1,55 @@
+package httpclient
+
+import (
+	"sync"
+	"time"
+)
+
+const (
+	defaultBreakerThreshold = 5
+	defaultBreakerCooldown  = 30 * time.Second
+)
+
+type hostBreaker struct {
+	mu        sync.Mutex
+	failures  int
+	openUntil time.Time
+}
+
+var hostBreakers sync.Map // string -> *hostBreaker
+
+func breakerForHost(host string) *hostBreaker {
+	if host == "" {
+		host = "_"
+	}
+	v, _ := hostBreakers.LoadOrStore(host, &hostBreaker{})
+	return v.(*hostBreaker)
+}
+
+func (b *hostBreaker) allow() bool {
+	b.mu.Lock()
+	defer b.mu.Unlock()
+	return time.Now().After(b.openUntil)
+}
+
+func (b *hostBreaker) recordSuccess() {
+	b.mu.Lock()
+	defer b.mu.Unlock()
+	b.failures = 0
+	b.openUntil = time.Time{}
+}
+
+func (b *hostBreaker) recordFailure() {
+	b.mu.Lock()
+	defer b.mu.Unlock()
+	b.failures++
+	if b.failures >= defaultBreakerThreshold {
+		b.openUntil = time.Now().Add(defaultBreakerCooldown)
+		b.failures = 0
+	}
+}
+
+// ResetHostBreakers clears all circuit breakers (tests only).
+func ResetHostBreakers() {
+	hostBreakers = sync.Map{}
+}

internal/httpclient/circuit_test.go

@@ -0,0 +1,34 @@
+package httpclient
+
+import (
+	"context"
+	"net/http"
+	"net/http/httptest"
+	"sync/atomic"
+	"testing"
+	"time"
+)
+
+func TestDoWithBreaker_opensAfterFailures(t *testing.T) {
+	ResetHostBreakers()
+	var calls atomic.Int32
+	srv := httptest.NewServer(http.HandlerFunc(func(w http.ResponseWriter, r *http.Request) {
+		calls.Add(1)
+		http.Error(w, "fail", http.StatusBadGateway)
+	}))
+	defer srv.Close()
+
+	hc := New(5 * time.Second)
+	for i := 0; i < defaultBreakerThreshold*3; i++ {
+		req, _ := http.NewRequest(http.MethodGet, srv.URL, nil)
+		_, _ = DoWithBreaker(context.Background(), hc, req, 1)
+	}
+	req, _ := http.NewRequest(http.MethodGet, srv.URL, nil)
+	_, err := DoWithBreaker(context.Background(), hc, req, 1)
+	if err == nil || err.Error() == "" {
+		t.Fatal("expected circuit open error")
+	}
+	if got := calls.Load(); got == 0 {
+		t.Fatal("expected at least one upstream call")
+	}
+}

internal/httpclient/httpclient.go

@@ -0,0 +1,87 @@
+// Package httpclient provides shared HTTP clients and retry helpers for outbound calls.
+package httpclient
+
+import (
+	"context"
+	"fmt"
+	"io"
+	"net/http"
+	"time"
+)
+
+const DefaultTimeout = 45 * time.Second
+
+// New returns an HTTP client with timeout and tuned idle connection pooling.
+func New(timeout time.Duration) *http.Client {
+	if timeout <= 0 {
+		timeout = DefaultTimeout
+	}
+	tr := http.DefaultTransport.(*http.Transport).Clone()
+	tr.MaxIdleConns = 100
+	tr.MaxIdleConnsPerHost = 10
+	return &http.Client{Timeout: timeout, Transport: tr}
+}
+
+// DoWithRetry executes hc.Do(req) up to maxAttempts times with linear backoff.
+func DoWithRetry(ctx context.Context, hc *http.Client, req *http.Request, maxAttempts int) (*http.Response, error) {
+	if maxAttempts <= 0 {
+		maxAttempts = 3
+	}
+	var lastErr error
+	for attempt := 0; attempt < maxAttempts; attempt++ {
+		if attempt > 0 {
+			wait := time.Duration(attempt) * 2 * time.Second
+			select {
+			case <-ctx.Done():
+				return nil, ctx.Err()
+			case <-time.After(wait):
+			}
+			if req.GetBody != nil {
+				body, err := req.GetBody()
+				if err != nil {
+					return nil, err
+				}
+				req.Body = body
+			}
+		}
+		reqClone := req.Clone(ctx)
+		resp, err := hc.Do(reqClone)
+		if err != nil {
+			lastErr = err
+			continue
+		}
+		if resp.StatusCode >= 500 {
+			_, _ = io.Copy(io.Discard, resp.Body)
+			_ = resp.Body.Close()
+			lastErr = fmt.Errorf("httpclient: upstream %s", resp.Status)
+			continue
+		}
+		return resp, nil
+	}
+	if lastErr != nil {
+		return nil, lastErr
+	}
+	return nil, fmt.Errorf("httpclient: request failed after %d attempts", maxAttempts)
+}
+
+// DoWithBreaker applies per-host circuit breaking then retries transient failures.
+func DoWithBreaker(ctx context.Context, hc *http.Client, req *http.Request, maxAttempts int) (*http.Response, error) {
+	if req == nil || req.URL == nil {
+		return nil, fmt.Errorf("httpclient: nil request")
+	}
+	br := breakerForHost(req.URL.Hostname())
+	if !br.allow() {
+		return nil, fmt.Errorf("httpclient: circuit open for %s", req.URL.Hostname())
+	}
+	resp, err := DoWithRetry(ctx, hc, req, maxAttempts)
+	if err != nil {
+		br.recordFailure()
+		return nil, err
+	}
+	if resp.StatusCode >= 500 {
+		br.recordFailure()
+		return resp, nil
+	}
+	br.recordSuccess()
+	return resp, nil
+}

internal/httpclient/httpclient_test.go

@@ -0,0 +1,39 @@
+package httpclient
+
+import (
+	"context"
+	"net/http"
+	"net/http/httptest"
+	"testing"
+	"time"
+)
+
+func TestDoWithRetry_retriesOn500(t *testing.T) {
+	var calls int
+	srv := httptest.NewServer(http.HandlerFunc(func(w http.ResponseWriter, r *http.Request) {
+		calls++
+		if calls < 3 {
+			http.Error(w, "fail", http.StatusBadGateway)
+			return
+		}
+		w.WriteHeader(http.StatusOK)
+		_, _ = w.Write([]byte("ok"))
+	}))
+	defer srv.Close()
+
+	req, err := http.NewRequest(http.MethodGet, srv.URL, nil)
+	if err != nil {
+		t.Fatal(err)
+	}
+	resp, err := DoWithRetry(context.Background(), New(5*time.Second), req, 3)
+	if err != nil {
+		t.Fatal(err)
+	}
+	defer func() { _ = resp.Body.Close() }()
+	if resp.StatusCode != http.StatusOK {
+		t.Fatalf("status %d", resp.StatusCode)
+	}
+	if calls != 3 {
+		t.Fatalf("want 3 calls, got %d", calls)
+	}
+}

internal/ingest/run.go

@@ -3,11 +3,11 @@ package ingest
 import (
 	"context"
 	"log"
-	"net/http"
 	"time"
 
 	"evobgp/internal/broker"
 	"evobgp/internal/config"
+	"evobgp/internal/httpclient"
 	"evobgp/internal/pipeline"
 	"evobgp/internal/store"
 )
@@ -17,6 +17,8 @@ type Deps struct {
 	Store store.Backend
 }
 
+var lastMaintenance time.Time
+
 // Run blocks until ctx is cancelled.
 func Run(ctx context.Context, deps *Deps) {
 	cfg := config.Load()
@@ -24,7 +26,7 @@ func Run(ctx context.Context, deps *Deps) {
 	if deps == nil || deps.Store == nil {
 		log.Fatalf("evobgp-ingest: missing store (pass ingest.Deps from BootstrapWorkers or evobgp-all)")
 	}
-	hc := &http.Client{Timeout: 45 * time.Second}
+	hc := httpclient.New(httpclient.DefaultTimeout)
 	t := time.NewTicker(60 * time.Second)
 	defer t.Stop()
 	log.Printf("evobgp-ingest: active (CDN conditional GET / ETag prefetch)")
@@ -34,7 +36,14 @@ func Run(ctx context.Context, deps *Deps) {
 			log.Printf("evobgp-ingest: stopped")
 			return
 		case <-t.C:
-			if err := pipeline.PrefetchCDNSourceETags(context.Background(), deps.Store, hc); err != nil {
+			if deps.Store != nil && time.Since(lastMaintenance) > time.Hour {
+				deps.Store.RunPeriodicMaintenance(ctx)
+				lastMaintenance = time.Now()
+			}
+			prefetchCtx, cancel := context.WithTimeout(ctx, 50*time.Second)
+			err := pipeline.PrefetchCDNSourceETags(prefetchCtx, deps.Store, hc)
+			cancel()
+			if err != nil {
 				log.Printf("evobgp-ingest: prefetch: %v", err)
 			}
 		}

internal/jobs/job.go

@@ -182,6 +182,8 @@ type Registry struct {
 	workerStart func(j *Job)
 	workerSem   chan struct{}
 	onTerminal  func(j *Job)
+	onEnqueued  func(j *Job)
+	onRunning   func(j *Job)
 }
 
 type idempoKey struct {
@@ -209,6 +211,44 @@ func (r *Registry) SetTerminalHook(fn func(j *Job)) {
 	r.onTerminal = fn
 }
 
+// SetPersistHooks registers best-effort callbacks for job lifecycle persistence.
+func (r *Registry) SetPersistHooks(onEnqueued, onRunning, onTerminal func(j *Job)) {
+	if r == nil {
+		return
+	}
+	r.mu.Lock()
+	defer r.mu.Unlock()
+	r.onEnqueued = onEnqueued
+	r.onRunning = onRunning
+	if onTerminal != nil {
+		r.onTerminal = onTerminal
+	}
+}
+
+func (r *Registry) fireEnqueued(j *Job) {
+	if r == nil || j == nil {
+		return
+	}
+	r.mu.RLock()
+	fn := r.onEnqueued
+	r.mu.RUnlock()
+	if fn != nil {
+		fn(j)
+	}
+}
+
+func (r *Registry) fireRunning(j *Job) {
+	if r == nil || j == nil {
+		return
+	}
+	r.mu.RLock()
+	fn := r.onRunning
+	r.mu.RUnlock()
+	if fn != nil {
+		fn(j)
+	}
+}
+
 func (r *Registry) fireTerminal(j *Job) {
 	if r == nil || j == nil {
 		return
@@ -271,8 +311,6 @@ func (r *Registry) pruneTerminalIfOver(maxJobs int) {
 // Enqueue creates a job or returns an existing one for the same idempotency key.
 func (r *Registry) Enqueue(tenantID, kind string, idempotencyKey *string, moduleID *string, meta map[string]any) (*Job, bool, error) {
 	r.mu.Lock()
-	defer r.mu.Unlock()
-
 	maxJobs := registryMaxJobsFromEnv()
 	r.pruneTerminalIfOver(maxJobs)
 
@@ -281,6 +319,7 @@ func (r *Registry) Enqueue(tenantID, kind string, idempotencyKey *string, module
 		if existing, ok := r.byIdempo[k]; ok {
 			st := existing.statusLocked()
 			if st == StatusQueued || st == StatusRunning {
+				r.mu.Unlock()
 				return existing, false, nil
 			}
 			delete(r.byIdempo, k)
@@ -302,8 +341,14 @@ func (r *Registry) Enqueue(tenantID, kind string, idempotencyKey *string, module
 	}
 	r.byID[j.ID] = j
 	r.pruneTerminalIfOver(maxJobs)
+	enqueuedHook := r.onEnqueued
+	workerStart := r.workerStart
+	r.mu.Unlock()
 
-	if r.workerStart != nil {
+	if enqueuedHook != nil {
+		enqueuedHook(j)
+	}
+	if workerStart != nil {
 		go func() {
 			r.workerSem <- struct{}{}
 			active := len(r.workerSem)
@@ -313,7 +358,7 @@ func (r *Registry) Enqueue(tenantID, kind string, idempotencyKey *string, module
 				<-r.workerSem
 				observability.RecordJobQueueDepth(len(r.workerSem), capacity)
 			}()
-			r.workerStart(j)
+			workerStart(j)
 		}()
 	}
 	return j, true, nil

internal/jobs/worker.go

@@ -13,6 +13,7 @@ import (
 
 	"evobgp/internal/birddeploy"
 	"evobgp/internal/birdfmt"
+	"evobgp/internal/httpclient"
 	"evobgp/internal/nodedispatch"
 	"evobgp/internal/observability"
 	"evobgp/internal/pipeline"
@@ -70,7 +71,7 @@ type revisionLogEntry struct {
 	Message        string   `json:"message"`
 }
 
-var defaultWorkerHTTP = &http.Client{Timeout: 45 * time.Second}
+var defaultWorkerHTTP = httpclient.New(httpclient.DefaultTimeout)
 
 func (w *Worker) httpClient() *http.Client {
 	if w != nil && w.HTTPClient != nil {
@@ -94,6 +95,9 @@ func (w *Worker) Process(j *Job) {
 		return
 	}
 	j.MarkRunning()
+	if w != nil && w.Registry != nil {
+		w.Registry.fireRunning(j)
+	}
 	if j.IsCancelRequested() {
 		j.MarkCancelled()
 		return

internal/nodecli/commands.go

@@ -16,6 +16,7 @@ import (
 
 	"evobgp/internal/birdfmt"
 	"evobgp/internal/bundle"
+	"evobgp/internal/httpclient"
 	"evobgp/internal/signing"
 )
 
@@ -55,6 +56,10 @@ func CmdPullBundle(args []string) int {
 	return 0
 }
 
+func nodeHTTPClient() *http.Client {
+	return httpclient.New(60 * time.Second)
+}
+
 func fetchLatestRevision(base, token, speaker string) (string, error) {
 	u := strings.TrimRight(base, "/") + "/v1/speakers/" + speaker + "/revisions/latest"
 	req, err := http.NewRequest(http.MethodGet, u, nil)
@@ -62,7 +67,9 @@ func fetchLatestRevision(base, token, speaker string) (string, error) {
 		return "", err
 	}
 	req.Header.Set("Authorization", "Bearer "+token)
-	resp, err := http.DefaultClient.Do(req)
+	ctx, cancel := context.WithTimeout(context.Background(), 60*time.Second)
+	defer cancel()
+	resp, err := httpclient.DoWithRetry(ctx, nodeHTTPClient(), req, 3)
 	if err != nil {
 		return "", err
 	}
@@ -90,7 +97,9 @@ func fetchBundle(base, token, speaker, revision string) ([]byte, error) {
 		return nil, err
 	}
 	req.Header.Set("Authorization", "Bearer "+token)
-	resp, err := http.DefaultClient.Do(req)
+	ctx, cancel := context.WithTimeout(context.Background(), 120*time.Second)
+	defer cancel()
+	resp, err := httpclient.DoWithRetry(ctx, nodeHTTPClient(), req, 3)
 	if err != nil {
 		return nil, err
 	}

internal/nodedispatch/bird.go

@@ -0,0 +1,69 @@
+package nodedispatch
+
+import (
+	"context"
+	"encoding/json"
+	"fmt"
+	"io"
+	"net/http"
+	"strings"
+
+	"evobgp/internal/birdfmt"
+	"evobgp/internal/store"
+)
+
+// BirdProtocolsResult is agent birdc scrape outcome.
+type BirdProtocolsResult struct {
+	SpeakerID string               `json:"speaker_id,omitempty"`
+	Sessions  []birdfmt.BGPSession `json:"sessions"`
+	Error     string               `json:"error,omitempty"`
+}
+
+// FetchBirdProtocols GETs /v1/agent/bird/protocols on a replica agent.
+func FetchBirdProtocols(ctx context.Context, sp *store.Speaker, opts Options) BirdProtocolsResult {
+	res := BirdProtocolsResult{}
+	if sp != nil {
+		res.SpeakerID = sp.ID
+	}
+	if sp == nil {
+		res.Error = "nil speaker"
+		return res
+	}
+	meta := store.ParseSpeakerMeta(sp.MetaJSON)
+	url := store.AgentBirdProtocolsURL(meta)
+	if url == "" {
+		res.Error = "agent_domain not configured"
+		return res
+	}
+	secret := strings.TrimSpace(meta.AgentSecret)
+	if secret == "" {
+		res.Error = "agent_secret missing"
+		return res
+	}
+	req, err := http.NewRequestWithContext(ctx, http.MethodGet, url, nil)
+	if err != nil {
+		res.Error = err.Error()
+		return res
+	}
+	req.Header.Set("Authorization", "Bearer "+secret)
+	resp, err := opts.client().Do(req)
+	if err != nil {
+		res.Error = err.Error()
+		return res
+	}
+	defer func() { _ = resp.Body.Close() }()
+	b, _ := io.ReadAll(resp.Body)
+	if resp.StatusCode < 200 || resp.StatusCode >= 300 {
+		res.Error = fmt.Sprintf("HTTP %d: %s", resp.StatusCode, strings.TrimSpace(string(b)))
+		return res
+	}
+	var out struct {
+		Sessions []birdfmt.BGPSession `json:"sessions"`
+	}
+	if err := json.Unmarshal(b, &out); err != nil {
+		res.Error = err.Error()
+		return res
+	}
+	res.Sessions = out.Sessions
+	return res
+}

internal/nodedispatch/dispatch.go

@@ -156,33 +156,14 @@ func WakeReplicas(ctx context.Context, st store.Backend, tenantID, revisionID st
 	return out
 }
 
-// CheckHealth GETs /v1/agent/health for UI Connected/Offline status.
+// CheckHealth is deprecated; use FetchAgentHealth.
 func CheckHealth(ctx context.Context, sp *store.Speaker, opts Options) (ok bool, detail string) {
-	if sp == nil {
-		return false, "nil speaker"
-	}
-	meta := store.ParseSpeakerMeta(sp.MetaJSON)
-	url := store.AgentHealthURL(meta)
-	if url == "" {
-		return false, "agent_domain not configured"
-	}
-	secret := strings.TrimSpace(meta.AgentSecret)
-	if secret == "" {
-		return false, "agent_secret missing"
-	}
-	req, err := http.NewRequestWithContext(ctx, http.MethodGet, url, nil)
-	if err != nil {
-		return false, err.Error()
-	}
-	req.Header.Set("Authorization", "Bearer "+secret)
-	resp, err := opts.client().Do(req)
-	if err != nil {
-		return false, err.Error()
-	}
-	defer func() { _ = resp.Body.Close() }()
-	if resp.StatusCode >= 200 && resp.StatusCode < 300 {
+	res := FetchAgentHealth(ctx, sp, opts)
+	if res.OK {
 		return true, "connected"
 	}
-	b, _ := io.ReadAll(resp.Body)
-	return false, fmt.Sprintf("HTTP %d: %s", resp.StatusCode, strings.TrimSpace(string(b)))
+	if res.Error != "" {
+		return false, res.Error
+	}
+	return false, "agent unhealthy"
 }

internal/nodedispatch/health.go

@@ -0,0 +1,69 @@
+package nodedispatch
+
+import (
+	"context"
+	"encoding/json"
+	"fmt"
+	"io"
+	"net/http"
+	"strings"
+
+	"evobgp/internal/store"
+)
+
+// AgentHealthResult is the parsed outcome of GET /v1/agent/health on a replica.
+type AgentHealthResult struct {
+	OK                    bool
+	Error                 string
+	LastAppliedRevisionID string
+	LastSyncAt            string
+}
+
+// FetchAgentHealth GETs /v1/agent/health for UI Connected/Offline status.
+func FetchAgentHealth(ctx context.Context, sp *store.Speaker, opts Options) AgentHealthResult {
+	if sp == nil {
+		return AgentHealthResult{Error: "nil speaker"}
+	}
+	meta := store.ParseSpeakerMeta(sp.MetaJSON)
+	url := store.AgentHealthURL(meta)
+	if url == "" {
+		return AgentHealthResult{Error: "agent_domain not configured"}
+	}
+	secret := strings.TrimSpace(meta.AgentSecret)
+	if secret == "" {
+		return AgentHealthResult{Error: "agent_secret missing"}
+	}
+	req, err := http.NewRequestWithContext(ctx, http.MethodGet, url, nil)
+	if err != nil {
+		return AgentHealthResult{Error: err.Error()}
+	}
+	req.Header.Set("Authorization", "Bearer "+secret)
+	resp, err := opts.client().Do(req)
+	if err != nil {
+		return AgentHealthResult{Error: err.Error()}
+	}
+	defer func() { _ = resp.Body.Close() }()
+	b, _ := io.ReadAll(resp.Body)
+	if resp.StatusCode < 200 || resp.StatusCode >= 300 {
+		return AgentHealthResult{
+			Error: fmt.Sprintf("HTTP %d: %s", resp.StatusCode, strings.TrimSpace(string(b))),
+		}
+	}
+	var out struct {
+		OK                    bool   `json:"ok"`
+		LastAppliedRevisionID string `json:"last_applied_revision_id"`
+		LastSyncAt            string `json:"last_sync_at"`
+	}
+	if err := json.Unmarshal(b, &out); err != nil {
+		return AgentHealthResult{Error: err.Error()}
+	}
+	res := AgentHealthResult{
+		OK:                    out.OK,
+		LastAppliedRevisionID: strings.TrimSpace(out.LastAppliedRevisionID),
+		LastSyncAt:            strings.TrimSpace(out.LastSyncAt),
+	}
+	if !res.OK {
+		res.Error = "agent reported ok=false"
+	}
+	return res
+}

internal/pipeline/cdn_prefetch_test.go

@@ -11,6 +11,7 @@ import (
 )
 
 func TestCollectModulePrefixRows_CDNSendsIfNoneMatch(t *testing.T) {
+	t.Setenv("EVOBGP_CDN_ALLOW_PRIVATE", "1")
 	m := store.NewMemory()
 	m.SeedDemo()
 	tenant, _, _, _, _ := m.DemoIDs()
@@ -25,7 +26,7 @@ func TestCollectModulePrefixRows_CDNSendsIfNoneMatch(t *testing.T) {
 	}
 
 	var gotIfNoneMatch string
-	srv := httptest.NewServer(http.HandlerFunc(func(w http.ResponseWriter, r *http.Request) {
+	srv := httptest.NewTLSServer(http.HandlerFunc(func(w http.ResponseWriter, r *http.Request) {
 		gotIfNoneMatch = strings.TrimSpace(r.Header.Get("If-None-Match"))
 		w.Header().Set("ETag", "etag-new")
 		_, _ = w.Write([]byte("198.51.100.0/24\n"))
@@ -54,6 +55,7 @@ func TestCollectModulePrefixRows_CDNSendsIfNoneMatch(t *testing.T) {
 }
 
 func TestCollectModulePrefixRows_CDN304UsesSnapshot(t *testing.T) {
+	t.Setenv("EVOBGP_CDN_ALLOW_PRIVATE", "1")
 	m := store.NewMemory()
 	m.SeedDemo()
 	tenant, _, _, _, _ := m.DemoIDs()
@@ -67,7 +69,7 @@ func TestCollectModulePrefixRows_CDN304UsesSnapshot(t *testing.T) {
 		t.Fatal(err)
 	}
 
-	srv := httptest.NewServer(http.HandlerFunc(func(w http.ResponseWriter, r *http.Request) {
+	srv := httptest.NewTLSServer(http.HandlerFunc(func(w http.ResponseWriter, r *http.Request) {
 		w.WriteHeader(http.StatusNotModified)
 	}))
 	defer srv.Close()
@@ -99,6 +101,7 @@ func TestCollectModulePrefixRows_CDN304UsesSnapshot(t *testing.T) {
 }
 
 func TestRefreshModuleIngest_CDN304UsesStoredSnapshot(t *testing.T) {
+	t.Setenv("EVOBGP_CDN_ALLOW_PRIVATE", "1")
 	m := store.NewMemory()
 	m.SeedDemo()
 	tenant, _, _, _, _ := m.DemoIDs()
@@ -112,7 +115,7 @@ func TestRefreshModuleIngest_CDN304UsesStoredSnapshot(t *testing.T) {
 		t.Fatal(err)
 	}
 
-	srv := httptest.NewServer(http.HandlerFunc(func(w http.ResponseWriter, r *http.Request) {
+	srv := httptest.NewTLSServer(http.HandlerFunc(func(w http.ResponseWriter, r *http.Request) {
 		w.WriteHeader(http.StatusNotModified)
 	}))
 	defer srv.Close()
@@ -140,6 +143,7 @@ func TestRefreshModuleIngest_CDN304UsesStoredSnapshot(t *testing.T) {
 }
 
 func TestCollectModulePrefixRows_CDN304RetriesWithoutETag(t *testing.T) {
+	t.Setenv("EVOBGP_CDN_ALLOW_PRIVATE", "1")
 	m := store.NewMemory()
 	m.SeedDemo()
 	tenant, _, _, _, _ := m.DemoIDs()
@@ -154,7 +158,7 @@ func TestCollectModulePrefixRows_CDN304RetriesWithoutETag(t *testing.T) {
 	}
 
 	var calls int
-	srv := httptest.NewServer(http.HandlerFunc(func(w http.ResponseWriter, r *http.Request) {
+	srv := httptest.NewTLSServer(http.HandlerFunc(func(w http.ResponseWriter, r *http.Request) {
 		calls++
 		if calls == 1 {
 			if got := strings.TrimSpace(r.Header.Get("If-None-Match")); got != "etag-stable" {

internal/pipeline/cdn_snapshot.go

@@ -119,6 +119,12 @@ func applyCDNSourceHTTPResult(ctx context.Context, st store.Backend, hc *http.Cl
 	if u == "" {
 		return nil, nil
 	}
+	if _, err := ValidateCDNURL(u); err != nil {
+		return nil, err
+	}
+	if err := ResolveCDNURLHost(ctx, u); err != nil {
+		return nil, err
+	}
 	sourceKey := cdnSourceKey(src.ID)
 	req, err := http.NewRequestWithContext(ctx, http.MethodGet, u, nil)
 	if err != nil {
@@ -127,7 +133,7 @@ func applyCDNSourceHTTPResult(ctx context.Context, st store.Backend, hc *http.Cl
 	if etag := strings.TrimSpace(src.Etag); etag != "" {
 		req.Header.Set("If-None-Match", etag)
 	}
-	resp, err := hc.Do(req)
+	resp, err := upstreamHTTPDo(ctx, hc, req)
 	if err != nil {
 		return nil, fmt.Errorf("cdn fetch %s: %w", u, err)
 	}
@@ -143,7 +149,7 @@ func applyCDNSourceHTTPResult(ctx context.Context, st store.Backend, hc *http.Cl
 		if err != nil {
 			return nil, err
 		}
-		resp, err = hc.Do(req2)
+		resp, err = upstreamHTTPDo(ctx, hc, req2)
 		if err != nil {
 			return nil, fmt.Errorf("cdn fetch %s: %w", u, err)
 		}
@@ -189,6 +195,12 @@ func fetchCDNSourceRows(ctx context.Context, st store.Backend, hc *http.Client,
 	if u == "" {
 		return nil, nil
 	}
+	if _, err := ValidateCDNURL(u); err != nil {
+		return nil, err
+	}
+	if err := ResolveCDNURLHost(ctx, u); err != nil {
+		return nil, err
+	}
 	sourceKey := cdnSourceKey(src.ID)
 	req, err := http.NewRequestWithContext(ctx, http.MethodGet, u, nil)
 	if err != nil {
@@ -197,7 +209,7 @@ func fetchCDNSourceRows(ctx context.Context, st store.Backend, hc *http.Client,
 	if etag := strings.TrimSpace(src.Etag); etag != "" {
 		req.Header.Set("If-None-Match", etag)
 	}
-	resp, err := hc.Do(req)
+	resp, err := upstreamHTTPDo(ctx, hc, req)
 	if err != nil {
 		return nil, fmt.Errorf("cdn fetch %s: %w", u, err)
 	}
@@ -212,7 +224,7 @@ func fetchCDNSourceRows(ctx context.Context, st store.Backend, hc *http.Client,
 		if err != nil {
 			return nil, err
 		}
-		resp, err = hc.Do(req2)
+		resp, err = upstreamHTTPDo(ctx, hc, req2)
 		if err != nil {
 			return nil, fmt.Errorf("cdn fetch %s: %w", u, err)
 		}

internal/pipeline/cdn_url.go

@@ -0,0 +1,116 @@
+package pipeline
+
+import (
+	"context"
+	"fmt"
+	"net"
+	"net/netip"
+	"net/url"
+	"os"
+	"strings"
+	"time"
+)
+
+func isBlockedCDNIP(ip netip.Addr) bool {
+	if allowPrivateCDNURLs() {
+		return false
+	}
+	if !ip.IsValid() {
+		return true
+	}
+	return ip.IsLoopback() || ip.IsPrivate() || ip.IsLinkLocalUnicast() || ip.IsMulticast() ||
+		ip.IsUnspecified() || ip == netip.MustParseAddr("169.254.169.254")
+}
+
+func allowPrivateCDNURLs() bool {
+	v := strings.TrimSpace(os.Getenv("EVOBGP_CDN_ALLOW_PRIVATE"))
+	return v == "1" || strings.EqualFold(v, "true")
+}
+
+func isBlockedCDNHostname(host string) bool {
+	if allowPrivateCDNURLs() {
+		return false
+	}
+	h := strings.ToLower(strings.TrimSpace(host))
+	if h == "" || h == "localhost" {
+		return true
+	}
+	if strings.HasSuffix(h, ".local") || strings.HasSuffix(h, ".internal") || strings.HasSuffix(h, ".localhost") {
+		return true
+	}
+	return false
+}
+
+// ValidateCDNURL checks CDN source URLs for SSRF-safe HTTPS endpoints (hostname only; no DNS resolve).
+func ValidateCDNURL(raw string) (string, error) {
+	raw = strings.TrimSpace(raw)
+	if raw == "" {
+		return "", fmt.Errorf("pipeline: cdn url is required")
+	}
+	u, err := url.Parse(raw)
+	if err != nil {
+		return "", fmt.Errorf("pipeline: cdn url invalid: %w", err)
+	}
+	if u.Scheme != "https" {
+		return "", fmt.Errorf("pipeline: cdn url must use https")
+	}
+	if u.User != nil {
+		return "", fmt.Errorf("pipeline: cdn url must not include credentials")
+	}
+	host := strings.TrimSpace(u.Hostname())
+	if host == "" {
+		return "", fmt.Errorf("pipeline: cdn url missing host")
+	}
+	if isBlockedCDNHostname(host) {
+		return "", fmt.Errorf("pipeline: cdn url blocked host")
+	}
+	if ip, err := netip.ParseAddr(host); err == nil {
+		if isBlockedCDNIP(ip) {
+			return "", fmt.Errorf("pipeline: cdn url blocked host")
+		}
+	}
+	return u.String(), nil
+}
+
+// ResolveCDNURLHost resolves a CDN hostname and rejects private/link-local targets (SSRF at fetch time).
+func ResolveCDNURLHost(ctx context.Context, raw string) error {
+	u, err := url.Parse(strings.TrimSpace(raw))
+	if err != nil {
+		return err
+	}
+	host := strings.TrimSpace(u.Hostname())
+	if host == "" {
+		return fmt.Errorf("pipeline: cdn url missing host")
+	}
+	if ip, err := netip.ParseAddr(host); err == nil {
+		if isBlockedCDNIP(ip) {
+			return fmt.Errorf("pipeline: cdn url blocked host")
+		}
+		return nil
+	}
+	if isBlockedCDNHostname(host) {
+		return fmt.Errorf("pipeline: cdn url blocked host")
+	}
+	if ctx == nil {
+		ctx = context.Background()
+	}
+	resolveCtx, cancel := context.WithTimeout(ctx, 5*time.Second)
+	defer cancel()
+	ips, err := net.DefaultResolver.LookupIP(resolveCtx, "ip", host)
+	if err != nil {
+		return fmt.Errorf("pipeline: cdn url dns lookup: %w", err)
+	}
+	if len(ips) == 0 {
+		return fmt.Errorf("pipeline: cdn url dns lookup: no addresses")
+	}
+	for _, ip := range ips {
+		addr, ok := netip.AddrFromSlice(ip)
+		if !ok {
+			continue
+		}
+		if isBlockedCDNIP(addr) {
+			return fmt.Errorf("pipeline: cdn url resolves to blocked address")
+		}
+	}
+	return nil
+}

internal/pipeline/cdn_url_test.go

@@ -0,0 +1,34 @@
+package pipeline
+
+import "testing"
+
+func TestValidateCDNURL(t *testing.T) {
+	tests := []struct {
+		raw  string
+		ok   bool
+		want string
+	}{
+		{"https://cdn.example.com/prefixes.txt", true, "https://cdn.example.com/prefixes.txt"},
+		{"http://cdn.example.com/x", false, ""},
+		{"https://127.0.0.1/x", false, ""},
+		{"https://10.0.0.1/x", false, ""},
+		{"https://169.254.169.254/latest/meta-data", false, ""},
+		{"https://localhost/x", false, ""},
+		{"file:///etc/passwd", false, ""},
+		{"https://user:pass@cdn.example.com/x", false, ""},
+	}
+	for _, tc := range tests {
+		got, err := ValidateCDNURL(tc.raw)
+		if tc.ok && err != nil {
+			t.Errorf("%q: unexpected err %v", tc.raw, err)
+			continue
+		}
+		if !tc.ok && err == nil {
+			t.Errorf("%q: expected error", tc.raw)
+			continue
+		}
+		if tc.ok && got != tc.want {
+			t.Errorf("%q: got %q want %q", tc.raw, got, tc.want)
+		}
+	}
+}

internal/pipeline/collect_parallel.go

@@ -25,7 +25,7 @@ func prefixRowsForSource(rows []store.PrefixRow, sourceKey string) []store.Prefi
 	return out
 }
 
-func collectASPrefixRows(ctx context.Context, st store.Backend, hc *http.Client, tenantID string, mod *store.Module, list []*store.ASEntry) ([]store.PrefixRow, error) {
+func collectASPrefixRows(ctx context.Context, st store.Backend, hc *http.Client, tenantID string, mod *store.Module, list []*store.ASEntry, priorSnapshot []store.PrefixRow) ([]store.PrefixRow, error) {
 	moduleID := mod.ID
 	legacy := strings.TrimSpace(os.Getenv("EVOBGP_ASN_RESOLVE")) == "0"
 	if legacy {
@@ -76,6 +76,41 @@ func collectASPrefixRows(ctx context.Context, st store.Backend, hc *http.Client,
 			}
 			pfxs, holder, err := resolveASNForEntry(ctx, st, hc, entry.ASN)
 			if err != nil {
+				if staleOnUpstreamError() {
+					if staleRows, staleHolder, ok := staleASNPrefixes(st, priorSnapshot, entry.ASN); ok {
+						logStaleUpstream("asn", fmt.Sprintf("AS%d: %v", entry.ASN, err))
+						src := fmt.Sprintf("as:%d", entry.ASN)
+						rows := append([]store.PrefixRow(nil), staleRows...)
+						for i := range rows {
+							rows[i].CommunityID = comm
+							rows[i].Source = src
+						}
+						results[idx] = entryResult{
+							rows:   rows,
+							metaID: entry.ID,
+							asn:    entry.ASN,
+							holder: staleHolder,
+							count:  int64(len(rows)),
+						}
+						return
+					}
+					if pfxs2, holder2, ok := asnCacheExpired(st, entry.ASN); ok {
+						logStaleUpstream("asn", fmt.Sprintf("AS%d expired cache: %v", entry.ASN, err))
+						src := fmt.Sprintf("as:%d", entry.ASN)
+						var rows []store.PrefixRow
+						for _, pfx := range pfxs2 {
+							rows = append(rows, store.PrefixRow{Prefix: pfx.String(), CommunityID: comm, Source: src})
+						}
+						results[idx] = entryResult{
+							rows:   rows,
+							metaID: entry.ID,
+							asn:    entry.ASN,
+							holder: holder2,
+							count:  int64(len(pfxs2)),
+						}
+						return
+					}
+				}
 				results[idx] = entryResult{err: fmt.Errorf("resolve AS%d: %w", entry.ASN, err)}
 				return
 			}
@@ -167,6 +202,13 @@ func collectCDNPrefixRows(ctx context.Context, st store.Backend, hc *http.Client
 			}
 			rows, err := fetchCDNSourceRows(ctx, st, hc, tenantID, moduleID, mod, src, priorSnapshot, now)
 			if err != nil {
+				if staleOnUpstreamError() {
+					if cached, ok := staleCDNPrefixes(st, tenantID, moduleID, priorSnapshot, src.ID); ok {
+						logStaleUpstream("cdn", fmt.Sprintf("source %s: %v", src.ID, err))
+						results[idx] = srcResult{rows: cached}
+						return
+					}
+				}
 				results[idx] = srcResult{err: err}
 				return
 			}
@@ -190,7 +232,7 @@ func collectCDNPrefixRows(ctx context.Context, st store.Backend, hc *http.Client
 	return out, nil
 }
 
-func collectDomainPrefixRows(ctx context.Context, hc *http.Client, mod *store.Module, profiles []*store.DohProfile, policy string, entries []*store.DomainEntry) ([]store.PrefixRow, error) {
+func collectDomainPrefixRows(ctx context.Context, hc *http.Client, mod *store.Module, profiles []*store.DohProfile, policy string, entries []*store.DomainEntry, priorSnapshot []store.PrefixRow) ([]store.PrefixRow, error) {
 	var validDom []*store.DomainEntry
 	for _, e := range entries {
 		if e != nil {
@@ -219,6 +261,19 @@ func collectDomainPrefixRows(ctx context.Context, hc *http.Client, mod *store.Mo
 			}
 			addrs, err := resolveDomainIPsWithPolicy(ctx, hc, profiles, policy, entry.FQDN)
 			if err != nil {
+				if staleOnUpstreamError() {
+					if cached, ok := staleDomainPrefixes(priorSnapshot, entry.FQDN); ok {
+						logStaleUpstream("domain", fmt.Sprintf("%q: %v", entry.FQDN, err))
+						rows := append([]store.PrefixRow(nil), cached...)
+						for i := range rows {
+							if rows[i].CommunityID == nil {
+								rows[i].CommunityID = comm
+							}
+						}
+						results[idx] = domResult{rows: rows}
+						return
+					}
+				}
 				results[idx] = domResult{err: fmt.Errorf("resolve domain %q: %w", entry.FQDN, err)}
 				return
 			}

internal/pipeline/collect_stale.go

@@ -0,0 +1,86 @@
+package pipeline
+
+import (
+	"fmt"
+	"log"
+	"net/netip"
+	"os"
+	"strings"
+
+	"evobgp/internal/store"
+)
+
+// staleOnUpstreamError reports whether ingest should keep last-known prefixes when an upstream fetch fails.
+// Enabled by default; set EVOBGP_STALE_ON_UPSTREAM_ERROR=0 to restore fail-fast behavior.
+func staleOnUpstreamError() bool {
+	v := strings.TrimSpace(os.Getenv("EVOBGP_STALE_ON_UPSTREAM_ERROR"))
+	if v == "" || v == "1" || strings.EqualFold(v, "true") {
+		return true
+	}
+	return false
+}
+
+func logStaleUpstream(kind, detail string) {
+	log.Printf("pipeline: stale upstream fallback (%s): %s", kind, detail)
+}
+
+func staleASNPrefixes(st store.Backend, priorSnapshot []store.PrefixRow, asn int64) ([]store.PrefixRow, string, bool) {
+	sourceKey := fmt.Sprintf("as:%d", asn)
+	if cached := prefixRowsForSource(priorSnapshot, sourceKey); len(cached) > 0 {
+		return cached, "", true
+	}
+	if st == nil {
+		return nil, "", false
+	}
+	ent, ok, err := st.GetASNPrefixCache(asn)
+	if err != nil || !ok || ent == nil || len(ent.Prefixes) == 0 {
+		return nil, "", false
+	}
+	var rows []store.PrefixRow
+	for _, p := range ent.Prefixes {
+		pfx, perr := netip.ParsePrefix(strings.TrimSpace(p))
+		if perr != nil {
+			continue
+		}
+		rows = append(rows, store.PrefixRow{Prefix: pfx.Masked().String(), Source: sourceKey})
+	}
+	if len(rows) == 0 {
+		return nil, "", false
+	}
+	return rows, ent.Holder, true
+}
+
+func staleDomainPrefixes(priorSnapshot []store.PrefixRow, fqdn string) ([]store.PrefixRow, bool) {
+	sourceKey := "domain:" + strings.TrimSpace(fqdn)
+	cached := prefixRowsForSource(priorSnapshot, sourceKey)
+	return cached, len(cached) > 0
+}
+
+func staleCDNPrefixes(st store.Backend, tenantID, moduleID string, priorSnapshot []store.PrefixRow, sourceID string) ([]store.PrefixRow, bool) {
+	sourceKey := cdnSourceKey(sourceID)
+	cached := cachedCDNPrefixRows(st, tenantID, moduleID, priorSnapshot, sourceKey)
+	return cached, len(cached) > 0
+}
+
+// asnCacheExpired returns cached ASN prefixes even past TTL (for stale fallback only).
+func asnCacheExpired(st store.Backend, asn int64) ([]netip.Prefix, string, bool) {
+	if st == nil {
+		return nil, "", false
+	}
+	ent, ok, err := st.GetASNPrefixCache(asn)
+	if err != nil || !ok || ent == nil || len(ent.Prefixes) == 0 {
+		return nil, "", false
+	}
+	out := make([]netip.Prefix, 0, len(ent.Prefixes))
+	for _, p := range ent.Prefixes {
+		pfx, perr := netip.ParsePrefix(strings.TrimSpace(p))
+		if perr != nil {
+			continue
+		}
+		out = append(out, pfx.Masked())
+	}
+	if len(out) == 0 {
+		return nil, "", false
+	}
+	return out, ent.Holder, true
+}

internal/pipeline/collect_stale_test.go

@@ -0,0 +1,72 @@
+package pipeline
+
+import (
+	"context"
+	"net/http"
+	"net/http/httptest"
+	"testing"
+
+	"evobgp/internal/store"
+)
+
+func TestCollectCDNPrefixRows_StaleOnFetchError(t *testing.T) {
+	t.Setenv("EVOBGP_STALE_ON_UPSTREAM_ERROR", "1")
+	t.Setenv("EVOBGP_CDN_ALLOW_PRIVATE", "1")
+
+	srv := httptest.NewTLSServer(http.HandlerFunc(func(w http.ResponseWriter, r *http.Request) {
+		http.Error(w, "upstream down", http.StatusServiceUnavailable)
+	}))
+	defer srv.Close()
+
+	st := store.NewMemory()
+	st.SeedDemo()
+	tenant, _, _, _, _ := st.DemoIDs()
+	mod, err := st.CreateModule(tenant, &store.Module{Type: "CDN_CIDRS", Name: "cdn", Enabled: true})
+	if err != nil {
+		t.Fatal(err)
+	}
+	if _, err := st.CreateCDNSource(tenant, mod.ID, &store.CDNSource{
+		ID: "s1", URL: srv.URL, SourceKind: "plain",
+	}); err != nil {
+		t.Fatal(err)
+	}
+
+	prior := []store.PrefixRow{
+		{Prefix: "203.0.113.0/24", Source: "cdn:s1"},
+	}
+	rows, err := collectCDNPrefixRows(context.Background(), st, srv.Client(), tenant, mod, []*store.CDNSource{{ID: "s1", URL: srv.URL, SourceKind: "plain"}}, prior)
+	if err != nil {
+		t.Fatalf("expected stale fallback, got err: %v", err)
+	}
+	if len(rows) != 1 || rows[0].Prefix != "203.0.113.0/24" {
+		t.Fatalf("unexpected rows: %+v", rows)
+	}
+}
+
+func TestCollectCDNPrefixRows_FailFastWhenNoStale(t *testing.T) {
+	t.Setenv("EVOBGP_STALE_ON_UPSTREAM_ERROR", "0")
+	t.Setenv("EVOBGP_CDN_ALLOW_PRIVATE", "1")
+
+	srv := httptest.NewTLSServer(http.HandlerFunc(func(w http.ResponseWriter, r *http.Request) {
+		http.Error(w, "upstream down", http.StatusServiceUnavailable)
+	}))
+	defer srv.Close()
+
+	st := store.NewMemory()
+	st.SeedDemo()
+	tenant, _, _, _, _ := st.DemoIDs()
+	mod, err := st.CreateModule(tenant, &store.Module{Type: "CDN_CIDRS", Name: "cdn", Enabled: true})
+	if err != nil {
+		t.Fatal(err)
+	}
+	if _, err := st.CreateCDNSource(tenant, mod.ID, &store.CDNSource{
+		ID: "s1", URL: srv.URL, SourceKind: "plain",
+	}); err != nil {
+		t.Fatal(err)
+	}
+
+	_, err = collectCDNPrefixRows(context.Background(), st, srv.Client(), tenant, mod, []*store.CDNSource{{ID: "s1", URL: srv.URL, SourceKind: "plain"}}, nil)
+	if err == nil {
+		t.Fatal("expected error when stale disabled and no cache")
+	}
+}

internal/pipeline/prefetch.go

@@ -5,86 +5,116 @@ import (
 	"io"
 	"net/http"
 	"strings"
+	"sync"
 	"time"
 
+	"evobgp/internal/httpclient"
 	"evobgp/internal/store"
 )
 
+type prefetchTask struct {
+	tenantID string
+	mod      *store.Module
+	src      *store.CDNSource
+}
+
 // PrefetchCDNSourceETags performs conditional GETs for CDN sources; on 200 parses CIDRs into module_prefix_snapshot.
 func PrefetchCDNSourceETags(ctx context.Context, st store.Backend, hc *http.Client) error {
 	if hc == nil {
-		hc = http.DefaultClient
+		hc = httpclient.New(httpclient.DefaultTimeout)
+	}
+	if ctx == nil {
+		ctx = context.Background()
 	}
 	tenants, err := st.ListTenantIDs()
 	if err != nil {
 		return err
 	}
-	now := time.Now().UTC()
+	var tasks []prefetchTask
 	for _, tid := range tenants {
 		for _, mod := range st.ListModules(tid) {
 			if mod == nil || !mod.Enabled || mod.Type != "CDN_CIDRS" {
 				continue
 			}
-			omod, err := st.GetModule(tid, mod.ID)
-			if err != nil {
-				continue
-			}
 			sources, err := st.ListCDNSources(tid, mod.ID)
 			if err != nil {
 				continue
 			}
-			var prior []store.PrefixRow
-			if snap, ok, _ := st.GetModulePrefixSnapshot(tid, mod.ID); ok && snap != nil {
-				prior = snap.Prefixes
-			}
 			for _, src := range sources {
-				if src == nil || strings.TrimSpace(src.URL) == "" {
-					continue
-				}
-				req, err := http.NewRequestWithContext(ctx, http.MethodGet, strings.TrimSpace(src.URL), nil)
-				if err != nil {
-					continue
-				}
-				if etag := strings.TrimSpace(src.Etag); etag != "" {
-					req.Header.Set("If-None-Match", etag)
-				}
-				resp, err := hc.Do(req)
-				if err != nil {
-					continue
-				}
-				if resp.StatusCode == http.StatusNotModified {
-					_ = resp.Body.Close()
-					continue
-				}
-				if resp.StatusCode != http.StatusOK {
-					_, _ = io.Copy(io.Discard, resp.Body)
-					_ = resp.Body.Close()
-					continue
-				}
-				body, err := io.ReadAll(io.LimitReader(resp.Body, 8<<20))
-				_ = resp.Body.Close()
-				if err != nil {
-					continue
-				}
-				prefixStrs, err := parseCDNBody(string(body), src)
-				if err != nil {
-					continue
-				}
-				newEtag := strings.TrimSpace(resp.Header.Get("ETag"))
-				patch := &store.CDNSourcePatch{LastRefreshedAt: &now}
-				if newEtag != "" && newEtag != strings.TrimSpace(src.Etag) {
-					e := newEtag
-					patch.Etag = &e
-				}
-				_, _ = st.UpdateCDNSource(tid, mod.ID, src.ID, patch)
-				rows := cdnRowsFromParsed(omod, src, prefixStrs)
-				_ = mergeCDNSourceIntoModuleSnapshot(st, tid, omod, src.ID, rows)
-				_ = prior // prior may be stale after merge; refresh for next source in loop
-				if snap, ok, _ := st.GetModulePrefixSnapshot(tid, mod.ID); ok && snap != nil {
-					prior = snap.Prefixes
+				if src != nil && strings.TrimSpace(src.URL) != "" {
+					tasks = append(tasks, prefetchTask{tenantID: tid, mod: mod, src: src})
 				}
 			}
 		}
 	}
+	if len(tasks) == 0 {
+		return nil
+	}
+	sem := make(chan struct{}, collectConcurrency())
+	var wg sync.WaitGroup
+	for _, task := range tasks {
+		wg.Add(1)
+		go func(t prefetchTask) {
+			defer wg.Done()
+			sem <- struct{}{}
+			defer func() { <-sem }()
+			prefetchOneCDNSource(ctx, st, hc, t)
+		}(task)
+	}
+	wg.Wait()
 	return nil
 }
+
+func prefetchOneCDNSource(ctx context.Context, st store.Backend, hc *http.Client, t prefetchTask) {
+	now := time.Now().UTC()
+	tid, mod, src := t.tenantID, t.mod, t.src
+	u := strings.TrimSpace(src.URL)
+	if _, err := ValidateCDNURL(u); err != nil {
+		return
+	}
+	if err := ResolveCDNURLHost(ctx, u); err != nil {
+		return
+	}
+	omod, err := st.GetModule(tid, mod.ID)
+	if err != nil {
+		return
+	}
+	req, err := http.NewRequestWithContext(ctx, http.MethodGet, u, nil)
+	if err != nil {
+		return
+	}
+	if etag := strings.TrimSpace(src.Etag); etag != "" {
+		req.Header.Set("If-None-Match", etag)
+	}
+	resp, err := upstreamHTTPDo(ctx, hc, req)
+	if err != nil {
+		return
+	}
+	if resp.StatusCode == http.StatusNotModified {
+		_ = resp.Body.Close()
+		return
+	}
+	if resp.StatusCode != http.StatusOK {
+		_, _ = io.Copy(io.Discard, resp.Body)
+		_ = resp.Body.Close()
+		return
+	}
+	body, err := io.ReadAll(io.LimitReader(resp.Body, 8<<20))
+	_ = resp.Body.Close()
+	if err != nil {
+		return
+	}
+	prefixStrs, err := parseCDNBody(string(body), src)
+	if err != nil {
+		return
+	}
+	newEtag := strings.TrimSpace(resp.Header.Get("ETag"))
+	patch := &store.CDNSourcePatch{LastRefreshedAt: &now}
+	if newEtag != "" && newEtag != strings.TrimSpace(src.Etag) {
+		e := newEtag
+		patch.Etag = &e
+	}
+	_, _ = st.UpdateCDNSource(tid, mod.ID, src.ID, patch)
+	rows := cdnRowsFromParsed(omod, src, prefixStrs)
+	_ = mergeCDNSourceIntoModuleSnapshot(st, tid, omod, src.ID, rows)
+}

internal/pipeline/refresh.go

@@ -19,6 +19,7 @@ import (
 	"time"
 
 	"evobgp/internal/birdfmt"
+	"evobgp/internal/httpclient"
 	"evobgp/internal/observability"
 	"evobgp/internal/store"
 
@@ -50,7 +51,7 @@ func MaterializedASPrefixKey(asn int64) string {
 // It does not create a new config revision.
 func RefreshModuleIngest(ctx context.Context, st store.Backend, hc *http.Client, tenantID, moduleID string) error {
 	if hc == nil {
-		hc = http.DefaultClient
+		hc = httpclient.New(httpclient.DefaultTimeout)
 	}
 	start := time.Now()
 	mod, err := st.GetModule(tenantID, moduleID)
@@ -84,7 +85,7 @@ func RefreshModuleIngest(ctx context.Context, st store.Backend, hc *http.Client,
 // If materialized prefixes are unchanged, returns latest revision id without creating a duplicate.
 func RenderTenantRevision(ctx context.Context, st store.Backend, hc *http.Client, tenantID, triggerModuleID string) (revisionID string, err error) {
 	if hc == nil {
-		hc = http.DefaultClient
+		hc = httpclient.New(httpclient.DefaultTimeout)
 	}
 	agg, err := aggregateTenantPrefixRowsAll(ctx, st, hc, tenantID)
 	if err != nil {
@@ -117,7 +118,7 @@ func RenderTenantRevision(ctx context.Context, st store.Backend, hc *http.Client
 func RenderTenantRevisionFromPrefixes(ctx context.Context, st store.Backend, hc *http.Client, tenantID, triggerModuleID string, rows []store.PrefixRow) (revisionID string, err error) {
 	_ = ctx
 	if hc == nil {
-		hc = http.DefaultClient
+		hc = httpclient.New(httpclient.DefaultTimeout)
 	}
 	agg := append([]store.PrefixRow(nil), rows...)
 	rawCount := len(agg)
@@ -176,7 +177,7 @@ func collectModulePrefixRows(ctx context.Context, st store.Backend, hc *http.Cli
 			return nil, err
 		}
 		sort.Slice(list, func(i, j int) bool { return list[i].ASN < list[j].ASN })
-		return collectASPrefixRows(ctx, st, hc, tenantID, mod, list)
+		return collectASPrefixRows(ctx, st, hc, tenantID, mod, list, priorSnapshot)
 	case "CDN_CIDRS":
 		sources, err := st.ListCDNSources(tenantID, moduleID)
 		if err != nil {
@@ -192,7 +193,7 @@ func collectModulePrefixRows(ctx context.Context, st store.Backend, hc *http.Cli
 		if err != nil {
 			return nil, err
 		}
-		return collectDomainPrefixRows(ctx, hc, mod, profiles, policy, entries)
+		return collectDomainPrefixRows(ctx, hc, mod, profiles, policy, entries, priorSnapshot)
 	default:
 		return nil, fmt.Errorf("pipeline: unknown module type %q", mod.Type)
 	}
@@ -1029,7 +1030,7 @@ func renderPeersBirdFragment(st store.Backend, tenantID string, loc birdLocals)
 		}
 		pol := parsePeerPolicies(p.PoliciesJSON)
 		lv4, lv6, asn := effectivePeerLocals(loc, pol)
-		proto := peerProtocolName(p.ID)
+		proto := birdfmt.PeerProtocolName(p.ID)
 		ra := uint32(p.RemoteASN)
 		if addr.Is4() {
 			opts := birdfmt.BGPPeerFromTemplateOptions{
@@ -1083,17 +1084,6 @@ func parsePeerPolicies(raw string) peerPolicyJSON {
 	return pol
 }
 
-func peerProtocolName(peerID string) string {
-	s := strings.ReplaceAll(strings.TrimSpace(peerID), "-", "")
-	if len(s) > 16 {
-		s = s[:16]
-	}
-	if s == "" {
-		s = "x"
-	}
-	return "evobgp_p_" + s
-}
-
 // buildExpandedBirdText concatenates bird.conf and the contents of each standard include (for UI / preview).
 func buildExpandedBirdText(main string, frags map[string]string) string {
 	var b strings.Builder

internal/pipeline/tenant_refresh.go

@@ -7,13 +7,14 @@ import (
 	"strings"
 	"sync"
 
+	"evobgp/internal/httpclient"
 	"evobgp/internal/store"
 )
 
 // RefreshTenantModules ingests all listed modules in parallel and updates per-module snapshots.
 func RefreshTenantModules(ctx context.Context, st store.Backend, hc *http.Client, tenantID string, moduleIDs []string) error {
 	if hc == nil {
-		hc = http.DefaultClient
+		hc = httpclient.New(httpclient.DefaultTimeout)
 	}
 	var ids []string
 	seen := make(map[string]struct{})

internal/pipeline/upstream_http.go

@@ -0,0 +1,23 @@
+package pipeline
+
+import (
+	"context"
+	"fmt"
+	"net/http"
+
+	"evobgp/internal/httpclient"
+)
+
+func upstreamHTTPDo(ctx context.Context, hc *http.Client, req *http.Request) (*http.Response, error) {
+	if hc == nil {
+		hc = httpclient.New(httpclient.DefaultTimeout)
+	}
+	resp, err := httpclient.DoWithBreaker(ctx, hc, req, 3)
+	if err != nil {
+		if req.URL != nil {
+			return nil, fmt.Errorf("cdn fetch %s: %w", req.URL.String(), err)
+		}
+		return nil, err
+	}
+	return resp, nil
+}

internal/repository/asn_cache.go

@@ -11,14 +11,22 @@ import (
 	"github.com/jackc/pgx/v5"
 )
 
+func asnCacheRowTableExists(ctx context.Context, q queryRower) bool {
+	var n int
+	err := q.QueryRow(ctx, `
+		SELECT 1 FROM information_schema.tables
+		WHERE table_schema = 'public' AND table_name = 'asn_prefix_cache_row'
+		LIMIT 1`).Scan(&n)
+	return err == nil
+}
+
 func (p *Postgres) GetASNPrefixCache(asn int64) (*store.ASNPrefixCacheEntry, bool, error) {
 	ctx := context.Background()
 	var holder string
 	var fetchedAt time.Time
-	var raw []byte
 	err := p.pool.QueryRow(ctx, `
-		SELECT holder, fetched_at, prefixes_json FROM asn_prefix_cache WHERE asn = $1`, asn).
-		Scan(&holder, &fetchedAt, &raw)
+		SELECT holder, fetched_at FROM asn_prefix_cache WHERE asn = $1`, asn).
+		Scan(&holder, &fetchedAt)
 	if err != nil {
 		if errors.Is(err, pgx.ErrNoRows) {
 			return nil, false, nil
@@ -26,8 +34,25 @@ func (p *Postgres) GetASNPrefixCache(asn int64) (*store.ASNPrefixCacheEntry, boo
 		return nil, false, err
 	}
 	var prefixes []string
-	if len(raw) > 0 {
-		_ = json.Unmarshal(raw, &prefixes)
+	if asnCacheRowTableExists(ctx, p.pool) {
+		rows, qerr := p.pool.Query(ctx, `
+			SELECT prefix::text FROM asn_prefix_cache_row WHERE asn = $1 ORDER BY prefix`, asn)
+		if qerr != nil {
+			return nil, false, qerr
+		}
+		defer rows.Close()
+		for rows.Next() {
+			var s string
+			if err := rows.Scan(&s); err != nil {
+				continue
+			}
+			prefixes = append(prefixes, s)
+		}
+	} else {
+		var raw []byte
+		if err := p.pool.QueryRow(ctx, `SELECT prefixes_json FROM asn_prefix_cache WHERE asn = $1`, asn).Scan(&raw); err == nil && len(raw) > 0 {
+			_ = json.Unmarshal(raw, &prefixes)
+		}
 	}
 	return &store.ASNPrefixCacheEntry{
 		ASN:       asn,
@@ -38,18 +63,40 @@ func (p *Postgres) GetASNPrefixCache(asn int64) (*store.ASNPrefixCacheEntry, boo
 }
 
 func (p *Postgres) SetASNPrefixCache(asn int64, holder string, prefixes []string) error {
-	raw, err := json.Marshal(prefixes)
+	ctx := context.Background()
+	tx, err := p.pool.Begin(ctx)
 	if err != nil {
 		return err
 	}
-	ctx := context.Background()
-	_, err = p.pool.Exec(ctx, `
-		INSERT INTO asn_prefix_cache (asn, holder, prefixes_json, fetched_at)
-		VALUES ($1, $2, $3::jsonb, now())
+	defer func() { _ = tx.Rollback(ctx) }()
+	_, err = tx.Exec(ctx, `
+		INSERT INTO asn_prefix_cache (asn, holder, fetched_at)
+		VALUES ($1, $2, now())
 		ON CONFLICT (asn) DO UPDATE SET
 			holder = EXCLUDED.holder,
-			prefixes_json = EXCLUDED.prefixes_json,
-			fetched_at = EXCLUDED.fetched_at`,
-		asn, holder, string(raw))
-	return err
+			fetched_at = EXCLUDED.fetched_at`, asn, holder)
+	if err != nil {
+		return err
+	}
+	if asnCacheRowTableExists(ctx, tx) {
+		if _, err := tx.Exec(ctx, `DELETE FROM asn_prefix_cache_row WHERE asn = $1`, asn); err != nil {
+			return err
+		}
+		for _, pfx := range prefixes {
+			if _, err := tx.Exec(ctx, `
+				INSERT INTO asn_prefix_cache_row (asn, prefix) VALUES ($1, $2::cidr)`, asn, pfx); err != nil {
+				return err
+			}
+		}
+	} else {
+		raw, err := json.Marshal(prefixes)
+		if err != nil {
+			return err
+		}
+		if _, err := tx.Exec(ctx, `
+			UPDATE asn_prefix_cache SET prefixes_json = $2::jsonb WHERE asn = $1`, asn, string(raw)); err != nil {
+			return err
+		}
+	}
+	return tx.Commit(ctx)
 }

internal/repository/ctx.go

@@ -0,0 +1,19 @@
+package repository
+
+import (
+	"context"
+	"time"
+)
+
+const defaultRepoTimeout = 60 * time.Second
+
+// boundedRepoCtx returns a context with default repository I/O timeout.
+func boundedRepoCtx(parent context.Context) (context.Context, context.CancelFunc) {
+	if parent == nil {
+		parent = context.Background()
+	}
+	if _, ok := parent.Deadline(); ok {
+		return parent, func() {}
+	}
+	return context.WithTimeout(parent, defaultRepoTimeout)
+}

internal/repository/job_audit.go

@@ -20,6 +20,28 @@ func NewJobAuditWriter(pool *pgxpool.Pool) *JobAuditWriter {
 	return &JobAuditWriter{pool: pool}
 }
 
+// UpsertQueued inserts a queued job row (best-effort).
+func (w *JobAuditWriter) UpsertQueued(ctx context.Context, tenantID, jobID, kind string, idempotencyKey *string, moduleID *string, meta map[string]any) {
+	if w == nil || w.pool == nil {
+		return
+	}
+	metaJSON, _ := json.Marshal(meta)
+	var idem any
+	if idempotencyKey != nil && *idempotencyKey != "" {
+		idem = *idempotencyKey
+	}
+	var mod any
+	if moduleID != nil && *moduleID != "" {
+		mod = *moduleID
+	}
+	_, _ = w.pool.Exec(ctx, `
+		INSERT INTO job_audit (id, tenant_id, kind, status, idempotency_key, module_id, meta_json, created_at)
+		VALUES ($1::uuid, $2::uuid, $3, 'queued', $4, $5::uuid, $6::jsonb, now())
+		ON CONFLICT (tenant_id, idempotency_key) WHERE idempotency_key IS NOT NULL
+		DO UPDATE SET status='queued', meta_json=EXCLUDED.meta_json, module_id=EXCLUDED.module_id`,
+		jobID, tenantID, kind, idem, mod, metaJSON)
+}
+
 // UpsertRunning inserts or updates a running job row (best-effort).
 func (w *JobAuditWriter) UpsertRunning(ctx context.Context, tenantID, jobID, kind string, idempotencyKey *string, meta map[string]any) {
 	if w == nil || w.pool == nil {
@@ -33,8 +55,7 @@ func (w *JobAuditWriter) UpsertRunning(ctx context.Context, tenantID, jobID, kin
 	_, _ = w.pool.Exec(ctx, `
 		INSERT INTO job_audit (id, tenant_id, kind, status, idempotency_key, meta_json, created_at, started_at)
 		VALUES ($1::uuid, $2::uuid, $3, 'running', $4, $5::jsonb, now(), now())
-		ON CONFLICT (tenant_id, idempotency_key) WHERE idempotency_key IS NOT NULL
-		DO UPDATE SET status='running', started_at=now(), meta_json=EXCLUDED.meta_json`,
+		ON CONFLICT (id) DO UPDATE SET status='running', started_at=COALESCE(job_audit.started_at, now()), meta_json=EXCLUDED.meta_json`,
 		jobID, tenantID, kind, idem, metaJSON)
 }
 

internal/repository/maintenance.go

@@ -0,0 +1,29 @@
+package repository
+
+import (
+	"context"
+	"time"
+)
+
+const (
+	jobAuditRetentionDays = 90
+	asnCacheRetentionDays = 7
+)
+
+// RunPeriodicMaintenance prunes stale job_audit and asn_prefix_cache rows (PostgreSQL).
+func (p *Postgres) RunPeriodicMaintenance(ctx context.Context) {
+	if p == nil || p.pool == nil {
+		return
+	}
+	if ctx == nil {
+		ctx = context.Background()
+	}
+	jobCutoff := time.Now().UTC().Add(-time.Duration(jobAuditRetentionDays) * 24 * time.Hour)
+	_, _ = p.pool.Exec(ctx, `
+		DELETE FROM job_audit
+		WHERE created_at < $1
+		  AND status IN ('succeeded', 'failed', 'cancelled')`, jobCutoff)
+	asnCutoff := time.Now().UTC().Add(-time.Duration(asnCacheRetentionDays) * 24 * time.Hour)
+	_, _ = p.pool.Exec(ctx, `
+		DELETE FROM asn_prefix_cache WHERE fetched_at < $1`, asnCutoff)
+}

internal/repository/module_snapshot.go

@@ -12,16 +12,24 @@ import (
 	"github.com/jackc/pgx/v5"
 )
 
+func moduleSnapshotRowTableExists(ctx context.Context, q queryRower) bool {
+	var n int
+	err := q.QueryRow(ctx, `
+		SELECT 1 FROM information_schema.tables
+		WHERE table_schema = 'public' AND table_name = 'module_prefix_snapshot_row'
+		LIMIT 1`).Scan(&n)
+	return err == nil
+}
+
 func (p *Postgres) GetModulePrefixSnapshot(tenantID, moduleID string) (*store.ModulePrefixSnapshot, bool, error) {
 	ctx := context.Background()
 	var inputHash string
 	var collectedAt time.Time
-	var raw []byte
 	err := p.pool.QueryRow(ctx, `
-		SELECT input_hash, collected_at, prefixes_json
+		SELECT input_hash, collected_at
 		FROM module_prefix_snapshot
 		WHERE tenant_id = $1 AND module_id = $2`,
-		tenantID, moduleID).Scan(&inputHash, &collectedAt, &raw)
+		tenantID, moduleID).Scan(&inputHash, &collectedAt)
 	if err != nil {
 		if errors.Is(err, pgx.ErrNoRows) {
 			return nil, false, nil
@@ -29,9 +37,31 @@ func (p *Postgres) GetModulePrefixSnapshot(tenantID, moduleID string) (*store.Mo
 		return nil, false, err
 	}
 	var prefixes []store.PrefixRow
-	if len(raw) > 0 {
-		if err := json.Unmarshal(raw, &prefixes); err != nil {
-			return nil, false, err
+	if moduleSnapshotRowTableExists(ctx, p.pool) {
+		rows, qerr := p.pool.Query(ctx, `
+			SELECT prefix::text, community_id::text, source
+			FROM module_prefix_snapshot_row
+			WHERE tenant_id = $1::uuid AND module_id = $2::uuid
+			ORDER BY ord`, tenantID, moduleID)
+		if qerr != nil {
+			return nil, false, qerr
+		}
+		defer rows.Close()
+		for rows.Next() {
+			var pr store.PrefixRow
+			var comm *string
+			if err := rows.Scan(&pr.Prefix, &comm, &pr.Source); err != nil {
+				continue
+			}
+			pr.CommunityID = comm
+			prefixes = append(prefixes, pr)
+		}
+	} else {
+		var raw []byte
+		if err := p.pool.QueryRow(ctx, `
+			SELECT prefixes_json FROM module_prefix_snapshot
+			WHERE tenant_id = $1 AND module_id = $2`, tenantID, moduleID).Scan(&raw); err == nil && len(raw) > 0 {
+			_ = json.Unmarshal(raw, &prefixes)
 		}
 	}
 	return &store.ModulePrefixSnapshot{
@@ -45,20 +75,57 @@ func (p *Postgres) SetModulePrefixSnapshot(tenantID, moduleID, inputHash string,
 	if strings.TrimSpace(tenantID) == "" || strings.TrimSpace(moduleID) == "" || strings.TrimSpace(inputHash) == "" {
 		return store.ErrInvalidInput
 	}
-	raw, err := json.Marshal(prefixes)
+	ctx := context.Background()
+	tx, err := p.pool.Begin(ctx)
 	if err != nil {
 		return err
 	}
-	ctx := context.Background()
-	_, err = p.pool.Exec(ctx, `
-		INSERT INTO module_prefix_snapshot (tenant_id, module_id, input_hash, collected_at, prefixes_json)
-		VALUES ($1::uuid, $2::uuid, $3, now(), $4::jsonb)
+	defer func() { _ = tx.Rollback(ctx) }()
+	_, err = tx.Exec(ctx, `
+		INSERT INTO module_prefix_snapshot (tenant_id, module_id, input_hash, collected_at)
+		VALUES ($1::uuid, $2::uuid, $3, now())
 		ON CONFLICT (tenant_id, module_id) DO UPDATE SET
 			input_hash = EXCLUDED.input_hash,
-			collected_at = EXCLUDED.collected_at,
-			prefixes_json = EXCLUDED.prefixes_json`,
-		tenantID, moduleID, inputHash, string(raw))
-	return err
+			collected_at = EXCLUDED.collected_at`,
+		tenantID, moduleID, inputHash)
+	if err != nil {
+		return err
+	}
+	if moduleSnapshotRowTableExists(ctx, tx) {
+		if _, err := tx.Exec(ctx, `
+			DELETE FROM module_prefix_snapshot_row
+			WHERE tenant_id = $1::uuid AND module_id = $2::uuid`, tenantID, moduleID); err != nil {
+			return err
+		}
+		for i, pr := range prefixes {
+			var comm any
+			if pr.CommunityID != nil && strings.TrimSpace(*pr.CommunityID) != "" {
+				comm = strings.TrimSpace(*pr.CommunityID)
+			}
+			src := pr.Source
+			if strings.TrimSpace(src) == "" {
+				src = "render"
+			}
+			if _, err := tx.Exec(ctx, `
+				INSERT INTO module_prefix_snapshot_row (tenant_id, module_id, ord, prefix, community_id, source)
+				VALUES ($1::uuid, $2::uuid, $3, $4::cidr, $5::uuid, $6)`,
+				tenantID, moduleID, i, strings.TrimSpace(pr.Prefix), comm, src); err != nil {
+				return err
+			}
+		}
+	} else {
+		raw, err := json.Marshal(prefixes)
+		if err != nil {
+			return err
+		}
+		if _, err := tx.Exec(ctx, `
+			UPDATE module_prefix_snapshot SET prefixes_json = $3::jsonb
+			WHERE tenant_id = $1::uuid AND module_id = $2::uuid`,
+			tenantID, moduleID, string(raw)); err != nil {
+			return err
+		}
+	}
+	return tx.Commit(ctx)
 }
 
 func (p *Postgres) DeleteModulePrefixSnapshot(tenantID, moduleID string) error {

internal/repository/postgres.go

@@ -659,7 +659,8 @@ func (p *Postgres) DeleteSpeaker(tenantID, id string) error {
 }
 
 func (p *Postgres) GetRevision(tenantID, revisionID string) (*store.Revision, error) {
-	ctx := context.Background()
+	ctx, cancel := boundedRepoCtx(context.Background())
+	defer cancel()
 	var r store.Revision
 	var mod *string
 	var parent *string
@@ -686,11 +687,38 @@ func (p *Postgres) GetRevision(tenantID, revisionID string) (*store.Revision, er
 	if mj.PreviewFragments == nil {
 		mj.PreviewFragments = map[string]string{}
 	}
-	r.PreviewFragments = mj.PreviewFragments
+	r.PreviewFragments = loadRevisionPreview(ctx, p.pool, revisionID, mj.PreviewFragments)
 	r.MaterializedPrefixCount = mj.MaterializedPrefixCount
 	return &r, nil
 }
 
+func (p *Postgres) GetRevisionSummary(tenantID, revisionID string) (*store.Revision, error) {
+	ctx, cancel := boundedRepoCtx(context.Background())
+	defer cancel()
+	var r store.Revision
+	var mod *string
+	var parent *string
+	var prefixCount int
+	err := p.pool.QueryRow(ctx, `
+		SELECT id::text, tenant_id::text, module_id::text, content_hash, parent_revision_id::text,
+			COALESCE((meta_json->>'materialized_prefix_count')::int, 0), created_at
+		FROM config_revision WHERE id=$1 AND tenant_id=$2`, revisionID, tenantID).Scan(
+		&r.ID, &r.TenantID, &mod, &r.ContentHash, &parent, &prefixCount, &r.CreatedAt)
+	if err != nil {
+		if errors.Is(err, pgx.ErrNoRows) {
+			return nil, store.ErrNotFound
+		}
+		return nil, err
+	}
+	if mod != nil {
+		r.ModuleID = *mod
+	}
+	r.ParentRevisionID = strOrNil(parent)
+	r.MaterializedPrefixCount = prefixCount
+	r.PreviewFragments = map[string]string{}
+	return &r, nil
+}
+
 func (p *Postgres) ListRevisions(tenantID, moduleID string, cursor string, limit int) ([]*store.Revision, string, bool) {
 	if limit <= 0 {
 		limit = 50
@@ -761,12 +789,7 @@ func (p *Postgres) ListRevisionPrefixes(tenantID, revisionID string, cursor stri
 	if limit <= 0 {
 		limit = 50
 	}
-	off := 0
-	if cursor != "" {
-		if n, err := strconv.Atoi(cursor); err == nil && n >= 0 {
-			off = n
-		}
-	}
+	afterID, off, useOffset := store.ParsePrefixPageCursor(cursor)
 	ctx := context.Background()
 	var one int
 	if err := p.pool.QueryRow(ctx, `
@@ -777,34 +800,55 @@ func (p *Postgres) ListRevisionPrefixes(tenantID, revisionID string, cursor stri
 		}
 		return nil, "", false
 	}
-	rows, err := p.pool.Query(ctx, `
-		SELECT prefix::text, community_id::text, source FROM revision_materialized_prefix
-		WHERE revision_id=$1 ORDER BY id
-		LIMIT $2 OFFSET $3`, revisionID, limit+1, off)
+	if snapID, ok := p.revisionPrefixSnapshotID(ctx, revisionID); ok {
+		return p.listSnapshotPrefixes(ctx, snapID, cursor, limit)
+	}
+	var rows pgx.Rows
+	var err error
+	if useOffset {
+		rows, err = p.pool.Query(ctx, `
+			SELECT id, prefix::text, community_id::text, source FROM revision_materialized_prefix
+			WHERE revision_id=$1::uuid ORDER BY id
+			LIMIT $2 OFFSET $3`, revisionID, limit+1, off)
+	} else {
+		var afterArg any
+		if afterID != nil {
+			afterArg = *afterID
+		}
+		rows, err = p.pool.Query(ctx, `
+			SELECT id, prefix::text, community_id::text, source FROM revision_materialized_prefix
+			WHERE revision_id=$1::uuid AND ($2::bigint IS NULL OR id > $2::bigint)
+			ORDER BY id
+			LIMIT $3`, revisionID, afterArg, limit+1)
+	}
 	if err != nil {
 		return nil, "", false
 	}
 	defer rows.Close()
 	var all []store.PrefixRow
+	var ids []int64
 	for rows.Next() {
+		var rowID int64
 		var pr store.PrefixRow
 		var comm *string
-		if err := rows.Scan(&pr.Prefix, &comm, &pr.Source); err != nil {
+		if err := rows.Scan(&rowID, &pr.Prefix, &comm, &pr.Source); err != nil {
 			continue
 		}
 		pr.CommunityID = comm
+		ids = append(ids, rowID)
 		all = append(all, pr)
 	}
 	agentDebugNDJSON3214("B", "repository/postgres.go:ListRevisionPrefixes", "list_prefixes_fetched", map[string]any{
-		"rows": len(all), "limit": limit, "offset": off,
+		"rows": len(all), "limit": limit, "keyset": !useOffset,
 	})
 	more := len(all) > limit
 	if more {
 		all = all[:limit]
+		ids = ids[:limit]
 	}
 	next := ""
-	if more {
-		next = fmt.Sprintf("%d", off+limit)
+	if more && len(ids) > 0 {
+		next = store.FormatPrefixPageCursor(ids[len(ids)-1])
 	}
 	if len(all) == 0 {
 		return nil, "", false
@@ -820,26 +864,35 @@ func (p *Postgres) CreateRollbackRevision(tenantID, sourceRevisionID string) (st
 	ctx := context.Background()
 	newID := uuid.NewString()
 	parent := sourceRevisionID
-	meta, _ := json.Marshal(map[string]any{
-		"preview_fragments":         src.PreviewFragments,
-		"materialized_prefix_count": src.MaterializedPrefixCount,
-	})
+	meta, err := revisionMetaWithoutPreview(src.MaterializedPrefixCount)
+	if err != nil {
+		return "", err
+	}
 	var modArg any
 	if strings.TrimSpace(src.ModuleID) != "" {
 		modArg = src.ModuleID
 	}
-	_, err = p.pool.Exec(ctx, `
-		INSERT INTO config_revision (id, tenant_id, module_id, content_hash, parent_revision_id, meta_json)
-		VALUES ($1,$2,$3,$4,$5::uuid,$6::jsonb)`,
-		newID, tenantID, modArg, src.ContentHash+":rollback", parent, string(meta))
+	tx, err := p.pool.Begin(ctx)
 	if err != nil {
 		return "", err
 	}
-	// copy materialized prefixes
-	_, _ = p.pool.Exec(ctx, `
-		INSERT INTO revision_materialized_prefix (revision_id, prefix, community_id, source, meta_json)
-		SELECT $1::uuid, prefix, community_id, source, meta_json FROM revision_materialized_prefix WHERE revision_id=$2::uuid`,
-		newID, sourceRevisionID)
+	defer func() { _ = tx.Rollback(ctx) }()
+	_, err = tx.Exec(ctx, `
+		INSERT INTO config_revision (id, tenant_id, module_id, content_hash, parent_revision_id, meta_json)
+		VALUES ($1,$2,$3,$4,$5::uuid,$6::jsonb)`,
+		newID, tenantID, modArg, src.ContentHash+":rollback", parent, meta)
+	if err != nil {
+		return "", err
+	}
+	if err := copyRevisionPreview(ctx, tx, newID, sourceRevisionID); err != nil {
+		return "", err
+	}
+	if err := p.copyRevisionPrefixSnapshotRef(ctx, tx, newID, sourceRevisionID); err != nil {
+		return "", err
+	}
+	if err := tx.Commit(ctx); err != nil {
+		return "", err
+	}
 	return newID, nil
 }
 
@@ -856,20 +909,18 @@ func (p *Postgres) RevisionDiff(tenantID, aID, bID string) (map[string]any, erro
 	var unchanged int
 	err := p.pool.QueryRow(ctx, `
 		SELECT COUNT(*)::int FROM (
-			SELECT prefix FROM revision_materialized_prefix WHERE revision_id=$1::uuid
-			INTERSECT
-			SELECT prefix FROM revision_materialized_prefix WHERE revision_id=$2::uuid
+			SELECT b.prefix FROM (`+sqlRevisionPrefixes("$2")+`) b
+			INNER JOIN (`+sqlRevisionPrefixes("$1")+`) a ON a.prefix = b.prefix
 		) t`, aID, bID).Scan(&unchanged)
 	if err != nil {
 		return nil, err
 	}
-	// added: в B, нет в A; removed: в A, нет в B — без загрузки полных снапшотов в память.
 	rowsAdded, err := p.pool.Query(ctx, `
-		SELECT prefix::text FROM (
-			SELECT prefix FROM revision_materialized_prefix WHERE revision_id=$1::uuid
-			EXCEPT
-			SELECT prefix FROM revision_materialized_prefix WHERE revision_id=$2::uuid
-		) s ORDER BY 1 LIMIT $3`, bID, aID, maxRevisionDiffRows+1)
+		SELECT b.prefix::text FROM (`+sqlRevisionPrefixes("$2")+`) b
+		LEFT JOIN (`+sqlRevisionPrefixes("$1")+`) a ON a.prefix = b.prefix
+		WHERE a.prefix IS NULL
+		ORDER BY b.prefix
+		LIMIT $3`, aID, bID, maxRevisionDiffRows+1)
 	if err != nil {
 		return nil, err
 	}
@@ -888,11 +939,11 @@ func (p *Postgres) RevisionDiff(tenantID, aID, bID string) (map[string]any, erro
 	}
 	addedTruncated := len(added) >= maxRevisionDiffRows
 	rowsRem, err := p.pool.Query(ctx, `
-		SELECT prefix::text FROM (
-			SELECT prefix FROM revision_materialized_prefix WHERE revision_id=$1::uuid
-			EXCEPT
-			SELECT prefix FROM revision_materialized_prefix WHERE revision_id=$2::uuid
-		) s ORDER BY 1 LIMIT $3`, aID, bID, maxRevisionDiffRows+1)
+		SELECT a.prefix::text FROM (`+sqlRevisionPrefixes("$1")+`) a
+		LEFT JOIN (`+sqlRevisionPrefixes("$2")+`) b ON b.prefix = a.prefix
+		WHERE b.prefix IS NULL
+		ORDER BY a.prefix
+		LIMIT $3`, aID, bID, maxRevisionDiffRows+1)
 	if err != nil {
 		return nil, err
 	}
@@ -1028,10 +1079,7 @@ func (p *Postgres) CreateRenderRevision(revisionID, tenantID, moduleID string, p
 	if previewFragments == nil {
 		previewFragments = map[string]string{}
 	}
-	meta, err := json.Marshal(map[string]any{
-		"preview_fragments":         previewFragments,
-		"materialized_prefix_count": len(prefixes),
-	})
+	meta, err := revisionMetaWithoutPreview(len(prefixes))
 	if err != nil {
 		return err
 	}
@@ -1045,32 +1093,23 @@ func (p *Postgres) CreateRenderRevision(revisionID, tenantID, moduleID string, p
 	if parentRevisionID != nil && strings.TrimSpace(*parentRevisionID) != "" {
 		parent = strings.TrimSpace(*parentRevisionID)
 	}
+	revID := strings.TrimSpace(revisionID)
 	_, err = tx.Exec(ctx, `
 		INSERT INTO config_revision (id, tenant_id, module_id, content_hash, parent_revision_id, meta_json)
 		VALUES ($1::uuid, $2::uuid, $3::uuid, $4, $5::uuid, $6::jsonb)`,
-		strings.TrimSpace(revisionID), tenantID, moduleID, strings.TrimSpace(contentHash), parent, string(meta))
+		revID, tenantID, moduleID, strings.TrimSpace(contentHash), parent, meta)
 	if err != nil {
 		return err
 	}
-	if len(prefixes) > 0 {
-		_, err = tx.CopyFrom(ctx,
-			pgx.Identifier{"revision_materialized_prefix"},
-			[]string{"revision_id", "prefix", "community_id", "source"},
-			pgx.CopyFromSlice(len(prefixes), func(i int) ([]any, error) {
-				pr := prefixes[i]
-				var comm any
-				if pr.CommunityID != nil && strings.TrimSpace(*pr.CommunityID) != "" {
-					comm = strings.TrimSpace(*pr.CommunityID)
-				}
-				src := pr.Source
-				if strings.TrimSpace(src) == "" {
-					src = "render"
-				}
-				return []any{strings.TrimSpace(revisionID), strings.TrimSpace(pr.Prefix), comm, src}, nil
-			}))
-		if err != nil {
-			return err
-		}
+	if err := insertRevisionPreview(ctx, tx, revID, previewFragments); err != nil {
+		return err
+	}
+	snapID, err := p.ensurePrefixSnapshot(ctx, tx, contentHash, prefixes)
+	if err != nil {
+		return err
+	}
+	if err := p.linkRevisionPrefixSnapshot(ctx, tx, revID, snapID); err != nil {
+		return err
 	}
 	if err := tx.Commit(ctx); err != nil {
 		return err

internal/repository/postgres_prefix_snapshot.go

@@ -0,0 +1,186 @@
+package repository
+
+import (
+	"context"
+	"errors"
+	"strings"
+
+	"evobgp/internal/store"
+
+	"github.com/google/uuid"
+	"github.com/jackc/pgx/v5"
+)
+
+func prefixSnapshotTableExists(ctx context.Context, q queryRower) bool {
+	var n int
+	err := q.QueryRow(ctx, `
+		SELECT 1 FROM information_schema.tables
+		WHERE table_schema = 'public' AND table_name = 'prefix_snapshot'
+		LIMIT 1`).Scan(&n)
+	return err == nil
+}
+
+func normalizeSnapshotHash(contentHash string) string {
+	h := strings.TrimSpace(contentHash)
+	if strings.HasPrefix(h, "sha256:") {
+		h = strings.TrimPrefix(h, "sha256:")
+	}
+	if len(h) > 64 {
+		h = h[:64]
+	}
+	if len(h) < 64 {
+		h = h + strings.Repeat("0", 64-len(h))
+	}
+	return h
+}
+
+func (p *Postgres) revisionPrefixSnapshotID(ctx context.Context, revisionID string) (string, bool) {
+	if !prefixSnapshotTableExists(ctx, p.pool) {
+		return "", false
+	}
+	var snap *string
+	err := p.pool.QueryRow(ctx, `
+		SELECT prefix_snapshot_id::text FROM config_revision
+		WHERE id = $1::uuid AND prefix_snapshot_id IS NOT NULL`, revisionID).Scan(&snap)
+	if err != nil || snap == nil || strings.TrimSpace(*snap) == "" {
+		return "", false
+	}
+	return *snap, true
+}
+
+func (p *Postgres) ensurePrefixSnapshot(ctx context.Context, db execQuerier, contentHash string, prefixes []store.PrefixRow) (string, error) {
+	if !prefixSnapshotTableExists(ctx, db) {
+		return "", nil
+	}
+	hash := normalizeSnapshotHash(contentHash)
+	var existing string
+	err := db.QueryRow(ctx, `SELECT id::text FROM prefix_snapshot WHERE content_hash = $1`, hash).Scan(&existing)
+	if err == nil && existing != "" {
+		return existing, nil
+	}
+	if err != nil && !errors.Is(err, pgx.ErrNoRows) {
+		return "", err
+	}
+	snapID := uuid.NewString()
+	if _, err := db.Exec(ctx, `
+		INSERT INTO prefix_snapshot (id, content_hash) VALUES ($1::uuid, $2)
+		ON CONFLICT (content_hash) DO NOTHING`, snapID, hash); err != nil {
+		return "", err
+	}
+	if err := db.QueryRow(ctx, `SELECT id::text FROM prefix_snapshot WHERE content_hash = $1`, hash).Scan(&snapID); err != nil {
+		return "", err
+	}
+	var rowCount int
+	_ = db.QueryRow(ctx, `SELECT COUNT(*)::int FROM prefix_snapshot_row WHERE snapshot_id = $1::uuid`, snapID).Scan(&rowCount)
+	if rowCount > 0 {
+		return snapID, nil
+	}
+	for i, pr := range prefixes {
+		var comm any
+		if pr.CommunityID != nil && strings.TrimSpace(*pr.CommunityID) != "" {
+			comm = strings.TrimSpace(*pr.CommunityID)
+		}
+		src := pr.Source
+		if strings.TrimSpace(src) == "" {
+			src = "render"
+		}
+		if _, err := db.Exec(ctx, `
+			INSERT INTO prefix_snapshot_row (snapshot_id, ord, prefix, community_id, source)
+			VALUES ($1::uuid, $2, $3::cidr, $4::uuid, $5)`,
+			snapID, i, strings.TrimSpace(pr.Prefix), comm, src); err != nil {
+			return "", err
+		}
+	}
+	return snapID, nil
+}
+
+func (p *Postgres) listSnapshotPrefixes(ctx context.Context, snapshotID, cursor string, limit int) ([]store.PrefixRow, string, bool) {
+	afterOrd, off, useOffset := store.ParsePrefixPageCursor(cursor)
+	var rows pgx.Rows
+	var err error
+	if useOffset {
+		rows, err = p.pool.Query(ctx, `
+			SELECT ord, prefix::text, community_id::text, source
+			FROM prefix_snapshot_row
+			WHERE snapshot_id = $1::uuid
+			ORDER BY ord
+			LIMIT $2 OFFSET $3`, snapshotID, limit+1, off)
+	} else {
+		var afterArg any
+		if afterOrd != nil {
+			afterArg = int(*afterOrd)
+		}
+		rows, err = p.pool.Query(ctx, `
+			SELECT ord, prefix::text, community_id::text, source
+			FROM prefix_snapshot_row
+			WHERE snapshot_id = $1::uuid AND ($2::int IS NULL OR ord > $2::int)
+			ORDER BY ord
+			LIMIT $3`, snapshotID, afterArg, limit+1)
+	}
+	if err != nil {
+		return nil, "", false
+	}
+	defer rows.Close()
+	var all []store.PrefixRow
+	var ords []int64
+	for rows.Next() {
+		var ord int
+		var pr store.PrefixRow
+		var comm *string
+		if err := rows.Scan(&ord, &pr.Prefix, &comm, &pr.Source); err != nil {
+			continue
+		}
+		pr.CommunityID = comm
+		ords = append(ords, int64(ord))
+		all = append(all, pr)
+	}
+	more := len(all) > limit
+	if more {
+		all = all[:limit]
+		ords = ords[:limit]
+	}
+	next := ""
+	if more && len(ords) > 0 {
+		next = store.FormatPrefixPageCursor(ords[len(ords)-1])
+	}
+	if len(all) == 0 {
+		return nil, "", false
+	}
+	return all, next, more
+}
+
+func (p *Postgres) linkRevisionPrefixSnapshot(ctx context.Context, db execQuerier, revisionID, snapshotID string) error {
+	if snapshotID == "" || !prefixSnapshotTableExists(ctx, db) {
+		return nil
+	}
+	_, err := db.Exec(ctx, `
+		UPDATE config_revision SET prefix_snapshot_id = $2::uuid WHERE id = $1::uuid`,
+		revisionID, snapshotID)
+	return err
+}
+
+func (p *Postgres) copyRevisionPrefixSnapshotRef(ctx context.Context, db execQuerier, dstRevisionID, srcRevisionID string) error {
+	if !prefixSnapshotTableExists(ctx, db) {
+		return nil
+	}
+	_, err := db.Exec(ctx, `
+		UPDATE config_revision dst
+		SET prefix_snapshot_id = src.prefix_snapshot_id
+		FROM config_revision src
+		WHERE dst.id = $1::uuid AND src.id = $2::uuid AND src.prefix_snapshot_id IS NOT NULL`,
+		dstRevisionID, srcRevisionID)
+	return err
+}
+
+func sqlRevisionPrefixes(revParam string) string {
+	return `SELECT psr.prefix FROM config_revision cr
+JOIN prefix_snapshot_row psr ON psr.snapshot_id = cr.prefix_snapshot_id
+WHERE cr.id = ` + revParam + `::uuid AND cr.prefix_snapshot_id IS NOT NULL
+UNION ALL
+SELECT rmp.prefix FROM revision_materialized_prefix rmp
+WHERE rmp.revision_id = ` + revParam + `::uuid
+  AND NOT EXISTS (
+    SELECT 1 FROM config_revision cr2
+    WHERE cr2.id = ` + revParam + `::uuid AND cr2.prefix_snapshot_id IS NOT NULL
+  )`
+}

internal/repository/postgres_revision_preview.go

@@ -0,0 +1,90 @@
+package repository
+
+import (
+	"context"
+	"encoding/json"
+	"errors"
+
+	"github.com/jackc/pgx/v5"
+	"github.com/jackc/pgx/v5/pgconn"
+)
+
+func revisionPreviewTableExists(ctx context.Context, q queryRower) bool {
+	var n int
+	err := q.QueryRow(ctx, `
+		SELECT 1 FROM information_schema.tables
+		WHERE table_schema = 'public' AND table_name = 'config_revision_preview'
+		LIMIT 1`).Scan(&n)
+	return err == nil
+}
+
+type queryRower interface {
+	QueryRow(ctx context.Context, sql string, args ...any) pgx.Row
+}
+
+func loadRevisionPreview(ctx context.Context, q queryRower, revisionID string, metaPreview map[string]string) map[string]string {
+	if revisionPreviewTableExists(ctx, q) {
+		var raw []byte
+		err := q.QueryRow(ctx, `
+			SELECT fragments FROM config_revision_preview WHERE revision_id = $1::uuid`,
+			revisionID).Scan(&raw)
+		if err == nil {
+			out := map[string]string{}
+			_ = json.Unmarshal(raw, &out)
+			if out == nil {
+				out = map[string]string{}
+			}
+			return out
+		}
+		if !errors.Is(err, pgx.ErrNoRows) {
+			return metaPreview
+		}
+	}
+	if metaPreview == nil {
+		return map[string]string{}
+	}
+	return metaPreview
+}
+
+type execQuerier interface {
+	queryRower
+	Exec(ctx context.Context, sql string, arguments ...any) (pgconn.CommandTag, error)
+}
+
+func insertRevisionPreview(ctx context.Context, db execQuerier, revisionID string, preview map[string]string) error {
+	if !revisionPreviewTableExists(ctx, db) {
+		return nil
+	}
+	if preview == nil {
+		preview = map[string]string{}
+	}
+	raw, err := json.Marshal(preview)
+	if err != nil {
+		return err
+	}
+	_, err = db.Exec(ctx, `
+		INSERT INTO config_revision_preview (revision_id, fragments)
+		VALUES ($1::uuid, $2::jsonb)
+		ON CONFLICT (revision_id) DO UPDATE SET fragments = EXCLUDED.fragments`,
+		revisionID, string(raw))
+	return err
+}
+
+func copyRevisionPreview(ctx context.Context, db execQuerier, dstRevisionID, srcRevisionID string) error {
+	if !revisionPreviewTableExists(ctx, db) {
+		return nil
+	}
+	_, err := db.Exec(ctx, `
+		INSERT INTO config_revision_preview (revision_id, fragments)
+		SELECT $1::uuid, fragments FROM config_revision_preview WHERE revision_id = $2::uuid
+		ON CONFLICT (revision_id) DO UPDATE SET fragments = EXCLUDED.fragments`,
+		dstRevisionID, srcRevisionID)
+	return err
+}
+
+func revisionMetaWithoutPreview(materializedPrefixCount int) (string, error) {
+	raw, err := json.Marshal(map[string]any{
+		"materialized_prefix_count": materializedPrefixCount,
+	})
+	return string(raw), err
+}

internal/repository/postgres_seed.go

@@ -26,9 +26,8 @@ func (p *Postgres) seedDemo(ctx context.Context) error {
 	p1 := uuid.NewString()
 	p2 := uuid.NewString()
 
-	preview := map[string]any{
-		"preview_fragments": map[string]string{
-			"bird.conf": `# EvoBGP demo bundle
+	previewFrags := map[string]string{
+		"bird.conf": `# EvoBGP demo bundle
 router id 192.0.2.1;
 
 protocol device {
@@ -39,15 +38,12 @@ protocol direct {
     ipv6;
 }
 `,
-			"bird.d/evobgp_demo.conf": "# static demo fragment\n",
-		},
-		"materialized_prefix_count": 128,
+		"bird.d/evobgp_demo.conf": "# static demo fragment\n",
 	}
-	previewB, _ := json.Marshal(preview)
-	parentMeta, _ := json.Marshal(map[string]any{
-		"preview_fragments":         map[string]string{"bird.conf": "# parent revision\n"},
-		"materialized_prefix_count": 0,
-	})
+	previewMeta, _ := json.Marshal(map[string]any{"materialized_prefix_count": 128})
+	parentMeta, _ := json.Marshal(map[string]any{"materialized_prefix_count": 0})
+	parentPreview, _ := json.Marshal(map[string]string{"bird.conf": "# parent revision\n"})
+	previewFragsB, _ := json.Marshal(previewFrags)
 
 	tx, err := p.pool.Begin(ctx)
 	if err != nil {
@@ -77,13 +73,32 @@ protocol direct {
 		return err
 	}
 	if _, err := tx.Exec(ctx, `
-		INSERT INTO config_revision (id, tenant_id, content_hash, parent_revision_id, meta_json)
-		VALUES ($1,$2,'sha256:demo-rev-1',$3::uuid,$4::jsonb)`, rid, tid, parent, string(previewB)); err != nil {
+		INSERT INTO config_revision_preview (revision_id, fragments) VALUES ($1::uuid, $2::jsonb)`, parent, string(parentPreview)); err != nil {
 		return err
 	}
 	if _, err := tx.Exec(ctx, `
-		INSERT INTO revision_materialized_prefix (revision_id, prefix, community_id, source)
-		VALUES ($1::uuid,'203.0.113.0/24',$2::uuid,'demo'), ($1::uuid,'2001:db8::/32',$2::uuid,'demo')`, rid, cid); err != nil {
+		INSERT INTO config_revision (id, tenant_id, content_hash, parent_revision_id, meta_json)
+		VALUES ($1,$2,'sha256:demo-rev-1',$3::uuid,$4::jsonb)`, rid, tid, parent, string(previewMeta)); err != nil {
+		return err
+	}
+	if _, err := tx.Exec(ctx, `
+		INSERT INTO config_revision_preview (revision_id, fragments) VALUES ($1::uuid, $2::jsonb)`, rid, string(previewFragsB)); err != nil {
+		return err
+	}
+	snapID := uuid.NewString()
+	demoHash := normalizeSnapshotHash("sha256:demo-rev-1")
+	if _, err := tx.Exec(ctx, `
+		INSERT INTO prefix_snapshot (id, content_hash) VALUES ($1::uuid, $2)`, snapID, demoHash); err != nil {
+		return err
+	}
+	if _, err := tx.Exec(ctx, `
+		UPDATE config_revision SET prefix_snapshot_id = $2::uuid WHERE id = $1::uuid`, rid, snapID); err != nil {
+		return err
+	}
+	if _, err := tx.Exec(ctx, `
+		INSERT INTO prefix_snapshot_row (snapshot_id, ord, prefix, community_id, source)
+		VALUES ($1::uuid, 0, '203.0.113.0/24'::cidr, $2::uuid, 'demo'),
+		       ($1::uuid, 1, '2001:db8::/32'::cidr, $2::uuid, 'demo')`, snapID, cid); err != nil {
 		return err
 	}
 	if _, err := tx.Exec(ctx, `

internal/scheduler/run.go

@@ -14,6 +14,7 @@ import (
 
 	"evobgp/internal/broker"
 	"evobgp/internal/config"
+	"evobgp/internal/httpclient"
 	"evobgp/internal/jobs"
 	"evobgp/internal/pipeline"
 	"evobgp/internal/store"
@@ -108,6 +109,9 @@ func postTenantRefresh(ctx context.Context, deps *Deps, moduleIDs []string, idem
 	if err != nil {
 		return err
 	}
+	req.GetBody = func() (io.ReadCloser, error) {
+		return io.NopCloser(bytes.NewReader(body)), nil
+	}
 	req.Header.Set("Authorization", "Bearer "+strings.TrimSpace(deps.APIToken))
 	req.Header.Set("Content-Type", "application/json")
 	if idempotencyKey != "" {
@@ -115,9 +119,9 @@ func postTenantRefresh(ctx context.Context, deps *Deps, moduleIDs []string, idem
 	}
 	hc := deps.HTTP
 	if hc == nil {
-		hc = http.DefaultClient
+		hc = httpclient.New(httpclient.DefaultTimeout)
 	}
-	resp, err := hc.Do(req)
+	resp, err := httpclient.DoWithRetry(ctx, hc, req, 3)
 	if err != nil {
 		return err
 	}

internal/store/backend.go

@@ -76,6 +76,8 @@ type Backend interface {
 	DeleteSpeaker(tenantID, id string) error
 
 	GetRevision(tenantID, revisionID string) (*Revision, error)
+	// GetRevisionSummary returns revision metadata without preview_fragments payloads.
+	GetRevisionSummary(tenantID, revisionID string) (*Revision, error)
 	ListRevisions(tenantID, moduleID string, cursor string, limit int) (items []*Revision, nextCursor string, hasMore bool)
 	ListRevisionPrefixes(tenantID, revisionID string, cursor string, limit int) (prefixes []PrefixRow, next string, more bool)
 	CreateRollbackRevision(tenantID, sourceRevisionID string) (newID string, err error)
@@ -110,6 +112,9 @@ type Backend interface {
 
 	// Ping verifies backend connectivity (no-op for in-memory).
 	Ping(ctx context.Context) error
+
+	// RunPeriodicMaintenance prunes stale DB rows (no-op for in-memory).
+	RunPeriodicMaintenance(ctx context.Context)
 }
 
 // ASNPrefixCacheEntry is a cached RIPEstat response for one ASN.

internal/store/memory.go

@@ -305,6 +305,11 @@ func (m *Memory) Ping(ctx context.Context) error {
 	return nil
 }
 
+// RunPeriodicMaintenance is a no-op for the in-memory backend.
+func (m *Memory) RunPeriodicMaintenance(ctx context.Context) {
+	_ = ctx
+}
+
 // ListTenantIDs returns tenant ids sorted lexicographically.
 func (m *Memory) ListTenantIDs() ([]string, error) {
 	m.mu.RLock()
@@ -424,14 +429,19 @@ func (m *Memory) GetModule(tenantID, moduleID string) (*Module, error) {
 func (m *Memory) GetRevision(tenantID, revisionID string) (*Revision, error) {
 	m.mu.RLock()
 	defer m.mu.RUnlock()
-	rev, ok := m.revisions[revisionID]
-	if !ok {
-		return nil, ErrNotFound
+	return m.getRevisionLocked(tenantID, revisionID)
+}
+
+func (m *Memory) GetRevisionSummary(tenantID, revisionID string) (*Revision, error) {
+	m.mu.RLock()
+	defer m.mu.RUnlock()
+	rev, err := m.getRevisionLocked(tenantID, revisionID)
+	if err != nil {
+		return nil, err
 	}
-	if rev.TenantID != tenantID {
-		return nil, ErrTenantScope
-	}
-	return rev, nil
+	cp := *rev
+	cp.PreviewFragments = nil
+	return &cp, nil
 }
 
 func (m *Memory) GetSpeaker(tenantID, speakerID string) (*Speaker, error) {

internal/store/memory_crud.go

@@ -1,8 +1,6 @@
 package store
 
 import (
-	"fmt"
-	"strconv"
 	"strings"
 	"time"
 
@@ -795,31 +793,37 @@ func (m *Memory) ListRevisionPrefixes(tenantID, revisionID string, cursor string
 	if limit <= 0 {
 		limit = 50
 	}
+	afterID, off, useOffset := ParsePrefixPageCursor(cursor)
 	m.mu.RLock()
 	defer m.mu.RUnlock()
 	if _, err := m.getRevisionLocked(tenantID, revisionID); err != nil {
 		return nil, "", false
 	}
-	all := m.revPrefixes[revisionID]
-	off := 0
-	if cursor != "" {
-		if n, err := strconv.Atoi(cursor); err == nil && n >= 0 {
-			off = n
-		}
+	allRows := m.revPrefixes[revisionID]
+	start := 0
+	if useOffset {
+		start = off
+	} else if afterID != nil {
+		start = int(*afterID) + 1
 	}
-	end := off + limit
-	next := ""
-	more := false
-	if end > len(all) {
-		end = len(all)
-	} else {
-		more = true
-		next = fmt.Sprintf("%d", end)
-	}
-	if off >= len(all) {
+	if start > len(allRows) {
 		return nil, "", false
 	}
-	return all[off:end], next, more
+	end := start + limit
+	next := ""
+	more := false
+	if end > len(allRows) {
+		end = len(allRows)
+	} else {
+		more = true
+		next = FormatPrefixPageCursor(int64(end - 1))
+	}
+	if start >= end {
+		return nil, "", false
+	}
+	out := make([]PrefixRow, end-start)
+	copy(out, allRows[start:end])
+	return out, next, more
 }
 
 func (m *Memory) ListGlobalSettings(tenantID string) (map[string]any, error) {

internal/store/pagination.go

@@ -0,0 +1,30 @@
+package store
+
+import (
+	"strconv"
+	"strings"
+)
+
+// ParsePrefixPageCursor decodes opaque cursors for revision prefix pagination.
+func ParsePrefixPageCursor(cursor string) (afterID *int64, offset int, useOffset bool) {
+	cursor = strings.TrimSpace(cursor)
+	if cursor == "" {
+		return nil, 0, false
+	}
+	if strings.HasPrefix(cursor, "o:") {
+		n, err := strconv.Atoi(strings.TrimPrefix(cursor, "o:"))
+		if err != nil || n < 0 {
+			return nil, 0, false
+		}
+		return nil, n, true
+	}
+	if n, err := strconv.ParseInt(cursor, 10, 64); err == nil && n >= 0 {
+		return &n, 0, false
+	}
+	return nil, 0, false
+}
+
+// FormatPrefixPageCursor encodes the keyset cursor (last row id or slice index).
+func FormatPrefixPageCursor(lastID int64) string {
+	return strconv.FormatInt(lastID, 10)
+}

internal/store/speaker_meta.go

@@ -72,7 +72,9 @@ func MergeSpeakerMetaJSON(existing string, patch SpeakerMeta) string {
 	if patch.LastDispatchAt != "" {
 		cur.LastDispatchAt = patch.LastDispatchAt
 	}
-	if patch.LastDispatchError != "" {
+	if patch.LastDispatchStatus == "ok" {
+		cur.LastDispatchError = ""
+	} else if patch.LastDispatchError != "" {
 		cur.LastDispatchError = patch.LastDispatchError
 	}
 	if patch.LastDispatchStatus != "" {
@@ -124,11 +126,20 @@ func AgentSyncURL(meta SpeakerMeta) string {
 
 // AgentHealthURL returns HTTPS health URL for agent_domain.
 func AgentHealthURL(meta SpeakerMeta) string {
+	return agentHTTPSURL(meta, "/v1/agent/health")
+}
+
+// AgentBirdProtocolsURL returns HTTPS bird protocols URL for agent_domain.
+func AgentBirdProtocolsURL(meta SpeakerMeta) string {
+	return agentHTTPSURL(meta, "/v1/agent/bird/protocols")
+}
+
+func agentHTTPSURL(meta SpeakerMeta, path string) string {
 	domain := strings.TrimSpace(meta.AgentDomain)
 	if domain == "" {
 		return ""
 	}
-	return "https://" + strings.TrimSuffix(domain, "/") + "/v1/agent/health"
+	return "https://" + strings.TrimSuffix(domain, "/") + path
 }
 
 // SpeakerNeedsRemoteDispatch reports whether deploy_apply should wake this speaker via agent HTTP.

internal/store/speaker_meta_test.go

@@ -34,3 +34,24 @@ func TestAgentSyncURL(t *testing.T) {
 		t.Fatalf("got %q", u)
 	}
 }
+
+func TestMergeSpeakerMetaJSON_clearsDispatchErrorOnOk(t *testing.T) {
+	t.Parallel()
+	existing := store.SpeakerMetaJSON(store.SpeakerMeta{
+		LastDispatchError:  "HTTP 502: bundle 403",
+		LastDispatchStatus: "error",
+		SyncStatus:         "error",
+	})
+	merged := store.MergeSpeakerMetaJSON(existing, store.SpeakerMeta{
+		LastDispatchStatus: "ok",
+		SyncStatus:         "synced",
+		LastDispatchAt:     "2026-05-21T15:06:43Z",
+	})
+	m := store.ParseSpeakerMeta(merged)
+	if m.LastDispatchError != "" {
+		t.Fatalf("LastDispatchError should clear on ok dispatch, got %q", m.LastDispatchError)
+	}
+	if m.LastDispatchStatus != "ok" || m.SyncStatus != "synced" {
+		t.Fatalf("status: dispatch=%q sync=%q", m.LastDispatchStatus, m.SyncStatus)
+	}
+}

migrations/postgres/000014_query_indexes.down.sql

@@ -0,0 +1,6 @@
+DROP INDEX IF EXISTS idx_rev_mat_prefix_uniq;
+DROP INDEX IF EXISTS idx_rev_mat_prefix_rev_cover;
+CREATE INDEX IF NOT EXISTS idx_rev_mat_prefix_rev_id
+    ON revision_materialized_prefix (revision_id, id);
+DROP INDEX IF EXISTS idx_module_tenant_active_sort;
+DROP INDEX IF EXISTS idx_rev_mat_prefix_rev_prefix;

migrations/postgres/000014_query_indexes.up.sql

@@ -0,0 +1,17 @@
+-- Query indexes: revision diff/list and module sort (H4 + M4).
+
+CREATE INDEX IF NOT EXISTS idx_rev_mat_prefix_rev_prefix
+    ON revision_materialized_prefix (revision_id, prefix);
+
+CREATE INDEX IF NOT EXISTS idx_module_tenant_active_sort
+    ON module (tenant_id, priority, name)
+    WHERE deleted_at IS NULL;
+
+-- Covering index for prefix list pagination (PostgreSQL 11+ INCLUDE).
+DROP INDEX IF EXISTS idx_rev_mat_prefix_rev_id;
+CREATE INDEX IF NOT EXISTS idx_rev_mat_prefix_rev_cover
+    ON revision_materialized_prefix (revision_id, id)
+    INCLUDE (prefix, community_id, source);
+
+CREATE UNIQUE INDEX IF NOT EXISTS idx_rev_mat_prefix_uniq
+    ON revision_materialized_prefix (revision_id, prefix, community_id, source);

migrations/postgres/000015_revision_preview.down.sql

@@ -0,0 +1,6 @@
+UPDATE config_revision cr
+SET meta_json = cr.meta_json || jsonb_build_object('preview_fragments', COALESCE(p.fragments, '{}'::jsonb))
+FROM config_revision_preview p
+WHERE p.revision_id = cr.id;
+
+DROP TABLE IF EXISTS config_revision_preview;

migrations/postgres/000015_revision_preview.up.sql

@@ -0,0 +1,15 @@
+-- Split BIRD preview fragments out of config_revision.meta_json (H1).
+
+CREATE TABLE config_revision_preview (
+    revision_id   UUID PRIMARY KEY REFERENCES config_revision (id) ON DELETE CASCADE,
+    fragments     JSONB NOT NULL DEFAULT '{}'
+);
+
+INSERT INTO config_revision_preview (revision_id, fragments)
+SELECT id, COALESCE(meta_json->'preview_fragments', '{}'::jsonb)
+FROM config_revision
+WHERE meta_json ? 'preview_fragments';
+
+UPDATE config_revision
+SET meta_json = meta_json - 'preview_fragments'
+WHERE meta_json ? 'preview_fragments';

migrations/postgres/000016_prefix_snapshot.down.sql

@@ -0,0 +1,3 @@
+ALTER TABLE config_revision DROP COLUMN IF EXISTS prefix_snapshot_id;
+DROP TABLE IF EXISTS prefix_snapshot_row;
+DROP TABLE IF EXISTS prefix_snapshot;

migrations/postgres/000016_prefix_snapshot.up.sql

@@ -0,0 +1,22 @@
+-- Content-addressed prefix snapshots (H2 expand).
+
+CREATE TABLE prefix_snapshot (
+    id            UUID PRIMARY KEY DEFAULT gen_random_uuid(),
+    content_hash  CHAR(64) NOT NULL,
+    created_at    TIMESTAMPTZ NOT NULL DEFAULT now(),
+    CONSTRAINT prefix_snapshot_hash_uniq UNIQUE (content_hash)
+);
+
+CREATE TABLE prefix_snapshot_row (
+    snapshot_id   UUID NOT NULL REFERENCES prefix_snapshot (id) ON DELETE CASCADE,
+    ord           INTEGER NOT NULL,
+    prefix        CIDR NOT NULL,
+    community_id  UUID REFERENCES bgp_community (id) ON DELETE SET NULL,
+    source        TEXT NOT NULL DEFAULT '',
+    PRIMARY KEY (snapshot_id, ord)
+);
+
+CREATE INDEX idx_prefix_snapshot_row_snapshot ON prefix_snapshot_row (snapshot_id);
+
+ALTER TABLE config_revision
+    ADD COLUMN prefix_snapshot_id UUID REFERENCES prefix_snapshot (id) ON DELETE RESTRICT;

migrations/postgres/000017_prefix_snapshot_backfill.down.sql

@@ -0,0 +1,3 @@
+DELETE FROM prefix_snapshot_row;
+UPDATE config_revision SET prefix_snapshot_id = NULL WHERE prefix_snapshot_id IS NOT NULL;
+DELETE FROM prefix_snapshot;

migrations/postgres/000017_prefix_snapshot_backfill.up.sql

@@ -0,0 +1,31 @@
+-- Backfill prefix snapshots from revision_materialized_prefix.
+
+WITH new_snaps AS (
+    INSERT INTO prefix_snapshot (id, content_hash)
+    SELECT gen_random_uuid(),
+        substr(replace(cr.id::text, '-', '') || replace(cr.id::text, '-', ''), 1, 64)
+    FROM config_revision cr
+    WHERE cr.prefix_snapshot_id IS NULL
+      AND EXISTS (
+          SELECT 1 FROM revision_materialized_prefix rmp WHERE rmp.revision_id = cr.id
+      )
+    RETURNING id, content_hash
+)
+UPDATE config_revision cr
+SET prefix_snapshot_id = ns.id
+FROM new_snaps ns
+WHERE cr.prefix_snapshot_id IS NULL
+  AND ns.content_hash = substr(replace(cr.id::text, '-', '') || replace(cr.id::text, '-', ''), 1, 64);
+
+INSERT INTO prefix_snapshot_row (snapshot_id, ord, prefix, community_id, source)
+SELECT cr.prefix_snapshot_id,
+    (row_number() OVER (PARTITION BY cr.id ORDER BY rmp.id) - 1)::int,
+    rmp.prefix,
+    rmp.community_id,
+    rmp.source
+FROM config_revision cr
+JOIN revision_materialized_prefix rmp ON rmp.revision_id = cr.id
+WHERE cr.prefix_snapshot_id IS NOT NULL
+  AND NOT EXISTS (
+      SELECT 1 FROM prefix_snapshot_row psr WHERE psr.snapshot_id = cr.prefix_snapshot_id
+  );

migrations/postgres/000018_prefix_snapshot_contract.down.sql

@@ -0,0 +1 @@
+COMMENT ON COLUMN config_revision.prefix_snapshot_id IS NULL;

migrations/postgres/000018_prefix_snapshot_contract.up.sql

@@ -0,0 +1,3 @@
+-- H2 contract marker: new revisions use prefix_snapshot_id only (enforced in application code).
+
+COMMENT ON COLUMN config_revision.prefix_snapshot_id IS 'Materialized prefixes; revision_materialized_prefix deprecated for new rows';

migrations/postgres/000019_module_snapshot_rows.down.sql

@@ -0,0 +1,16 @@
+ALTER TABLE module_prefix_snapshot ADD COLUMN prefixes_json JSONB NOT NULL DEFAULT '[]';
+
+UPDATE module_prefix_snapshot mps
+SET prefixes_json = COALESCE((
+    SELECT jsonb_agg(
+        jsonb_build_object(
+            'prefix', psr.prefix::text,
+            'community_id', psr.community_id,
+            'source', psr.source
+        ) ORDER BY psr.ord
+    )
+    FROM module_prefix_snapshot_row psr
+    WHERE psr.tenant_id = mps.tenant_id AND psr.module_id = mps.module_id
+), '[]'::jsonb);
+
+DROP TABLE IF EXISTS module_prefix_snapshot_row;

migrations/postgres/000019_module_snapshot_rows.up.sql

@@ -0,0 +1,25 @@
+CREATE TABLE module_prefix_snapshot_row (
+    tenant_id     UUID NOT NULL,
+    module_id     UUID NOT NULL,
+    ord           INTEGER NOT NULL,
+    prefix        CIDR NOT NULL,
+    community_id  UUID,
+    source        TEXT NOT NULL DEFAULT '',
+    PRIMARY KEY (tenant_id, module_id, ord),
+    FOREIGN KEY (tenant_id, module_id)
+        REFERENCES module_prefix_snapshot (tenant_id, module_id) ON DELETE CASCADE
+);
+
+INSERT INTO module_prefix_snapshot_row (tenant_id, module_id, ord, prefix, community_id, source)
+SELECT mps.tenant_id,
+    mps.module_id,
+    (t.ordinality - 1)::int,
+    (t.elem->>'prefix')::cidr,
+    NULLIF(t.elem->>'community_id', '')::uuid,
+    COALESCE(NULLIF(t.elem->>'source', ''), '')
+FROM module_prefix_snapshot mps
+CROSS JOIN LATERAL jsonb_array_elements(mps.prefixes_json) WITH ORDINALITY AS t(elem, ordinality)
+WHERE jsonb_typeof(mps.prefixes_json) = 'array'
+  AND jsonb_array_length(mps.prefixes_json) > 0;
+
+ALTER TABLE module_prefix_snapshot DROP COLUMN prefixes_json;

migrations/postgres/000020_asn_cache_rows.down.sql

@@ -0,0 +1,10 @@
+ALTER TABLE asn_prefix_cache ADD COLUMN prefixes_json JSONB NOT NULL DEFAULT '[]';
+
+UPDATE asn_prefix_cache apc
+SET prefixes_json = COALESCE((
+    SELECT jsonb_agg(apcr.prefix::text ORDER BY apcr.prefix::text)
+    FROM asn_prefix_cache_row apcr
+    WHERE apcr.asn = apc.asn
+), '[]'::jsonb);
+
+DROP TABLE IF EXISTS asn_prefix_cache_row;

migrations/postgres/000020_asn_cache_rows.up.sql

@@ -0,0 +1,14 @@
+CREATE TABLE asn_prefix_cache_row (
+    asn     BIGINT NOT NULL REFERENCES asn_prefix_cache (asn) ON DELETE CASCADE,
+    prefix  CIDR NOT NULL,
+    PRIMARY KEY (asn, prefix)
+);
+
+INSERT INTO asn_prefix_cache_row (asn, prefix)
+SELECT apc.asn, t.elem::cidr
+FROM asn_prefix_cache apc
+CROSS JOIN LATERAL jsonb_array_elements_text(apc.prefixes_json) AS t(elem)
+WHERE jsonb_typeof(apc.prefixes_json) = 'array'
+  AND jsonb_array_length(apc.prefixes_json) > 0;
+
+ALTER TABLE asn_prefix_cache DROP COLUMN prefixes_json;

migrations/postgres/000021_job_audit_brin.down.sql

@@ -0,0 +1 @@
+DROP INDEX IF EXISTS idx_job_audit_created_brin;

migrations/postgres/000021_job_audit_brin.up.sql

@@ -0,0 +1,2 @@
+CREATE INDEX IF NOT EXISTS idx_job_audit_created_brin
+    ON job_audit USING BRIN (created_at);

migrations/postgres/000022_schema_cleanup.down.sql

@@ -0,0 +1,18 @@
+CREATE TABLE IF NOT EXISTS module_cdn_fetch_log (
+    id          BIGSERIAL PRIMARY KEY,
+    module_id   UUID NOT NULL REFERENCES module (id) ON DELETE CASCADE,
+    source_id   UUID REFERENCES module_cdn_source (id) ON DELETE SET NULL,
+    http_status INTEGER,
+    bytes       BIGINT,
+    error       TEXT,
+    fetched_at  TIMESTAMPTZ NOT NULL DEFAULT now()
+);
+CREATE INDEX IF NOT EXISTS idx_module_cdn_fetch_log_module ON module_cdn_fetch_log (module_id, fetched_at DESC);
+
+ALTER TABLE revision_materialized_prefix ADD COLUMN IF NOT EXISTS meta_json JSONB NOT NULL DEFAULT '{}';
+ALTER TABLE module_domain_entry ADD COLUMN IF NOT EXISTS resolve_meta JSONB NOT NULL DEFAULT '{}';
+
+CREATE INDEX IF NOT EXISTS idx_rev_mat_prefix_revision ON revision_materialized_prefix (revision_id);
+CREATE INDEX IF NOT EXISTS idx_module_tenant ON module (tenant_id);
+CREATE INDEX IF NOT EXISTS idx_module_prefix_snapshot_collected ON module_prefix_snapshot (collected_at);
+CREATE INDEX IF NOT EXISTS idx_rev_mat_prefix_value ON revision_materialized_prefix (prefix);

migrations/postgres/000022_schema_cleanup.up.sql

@@ -0,0 +1,8 @@
+ALTER TABLE revision_materialized_prefix DROP COLUMN IF EXISTS meta_json;
+ALTER TABLE module_domain_entry DROP COLUMN IF EXISTS resolve_meta;
+DROP TABLE IF EXISTS module_cdn_fetch_log;
+
+DROP INDEX IF EXISTS idx_rev_mat_prefix_revision;
+DROP INDEX IF EXISTS idx_module_tenant;
+DROP INDEX IF EXISTS idx_module_prefix_snapshot_collected;
+DROP INDEX IF EXISTS idx_rev_mat_prefix_value;

migrations/sqlite/000014_query_indexes.down.sql

@@ -0,0 +1,3 @@
+DROP INDEX IF EXISTS idx_rev_mat_prefix_uniq;
+DROP INDEX IF EXISTS idx_module_tenant_active_sort;
+DROP INDEX IF EXISTS idx_rev_mat_prefix_rev_prefix;

migrations/sqlite/000014_query_indexes.up.sql

@@ -0,0 +1,9 @@
+CREATE INDEX IF NOT EXISTS idx_rev_mat_prefix_rev_prefix
+    ON revision_materialized_prefix (revision_id, prefix);
+
+CREATE INDEX IF NOT EXISTS idx_module_tenant_active_sort
+    ON module (tenant_id, priority, name)
+    WHERE deleted_at IS NULL;
+
+CREATE UNIQUE INDEX IF NOT EXISTS idx_rev_mat_prefix_uniq
+    ON revision_materialized_prefix (revision_id, prefix, community_id, source);

migrations/sqlite/000015_revision_preview.down.sql

@@ -0,0 +1,9 @@
+UPDATE config_revision
+SET meta_json = json_set(
+    meta_json,
+    '$.preview_fragments',
+    json(COALESCE((SELECT fragments FROM config_revision_preview p WHERE p.revision_id = config_revision.id), '{}'))
+)
+WHERE id IN (SELECT revision_id FROM config_revision_preview);
+
+DROP TABLE IF EXISTS config_revision_preview;

migrations/sqlite/000015_revision_preview.up.sql

@@ -0,0 +1,13 @@
+CREATE TABLE config_revision_preview (
+    revision_id   TEXT NOT NULL PRIMARY KEY REFERENCES config_revision (id) ON DELETE CASCADE,
+    fragments     TEXT NOT NULL DEFAULT '{}'
+);
+
+INSERT INTO config_revision_preview (revision_id, fragments)
+SELECT id, json(COALESCE(json_extract(meta_json, '$.preview_fragments'), '{}'))
+FROM config_revision
+WHERE json_extract(meta_json, '$.preview_fragments') IS NOT NULL;
+
+UPDATE config_revision
+SET meta_json = json_remove(meta_json, '$.preview_fragments')
+WHERE json_extract(meta_json, '$.preview_fragments') IS NOT NULL;

migrations/sqlite/000016_prefix_snapshot.down.sql

@@ -0,0 +1,3 @@
+ALTER TABLE config_revision DROP COLUMN prefix_snapshot_id;
+DROP TABLE IF EXISTS prefix_snapshot_row;
+DROP TABLE IF EXISTS prefix_snapshot;

migrations/sqlite/000016_prefix_snapshot.up.sql

@@ -0,0 +1,18 @@
+CREATE TABLE prefix_snapshot (
+    id            TEXT NOT NULL PRIMARY KEY,
+    content_hash  TEXT NOT NULL UNIQUE,
+    created_at    TEXT NOT NULL DEFAULT (strftime('%Y-%m-%dT%H:%M:%fZ', 'now'))
+);
+
+CREATE TABLE prefix_snapshot_row (
+    snapshot_id   TEXT NOT NULL REFERENCES prefix_snapshot (id) ON DELETE CASCADE,
+    ord           INTEGER NOT NULL,
+    prefix        TEXT NOT NULL,
+    community_id  TEXT,
+    source        TEXT NOT NULL DEFAULT '',
+    PRIMARY KEY (snapshot_id, ord)
+);
+
+CREATE INDEX idx_prefix_snapshot_row_snapshot ON prefix_snapshot_row (snapshot_id);
+
+ALTER TABLE config_revision ADD COLUMN prefix_snapshot_id TEXT REFERENCES prefix_snapshot (id) ON DELETE RESTRICT;

migrations/sqlite/000017_prefix_snapshot_backfill.down.sql

@@ -0,0 +1,3 @@
+DELETE FROM prefix_snapshot_row;
+UPDATE config_revision SET prefix_snapshot_id = NULL;
+DELETE FROM prefix_snapshot;

migrations/sqlite/000017_prefix_snapshot_backfill.up.sql

@@ -0,0 +1,30 @@
+-- SQLite backfill: one snapshot per revision with materialized prefixes.
+
+INSERT INTO prefix_snapshot (id, content_hash)
+SELECT lower(hex(randomblob(16))),
+    substr(replace(cr.id, '-', '') || replace(cr.id, '-', ''), 1, 64)
+FROM config_revision cr
+WHERE cr.prefix_snapshot_id IS NULL
+  AND EXISTS (SELECT 1 FROM revision_materialized_prefix rmp WHERE rmp.revision_id = cr.id);
+
+UPDATE config_revision
+SET prefix_snapshot_id = (
+    SELECT ps.id FROM prefix_snapshot ps
+    WHERE ps.content_hash = substr(replace(config_revision.id, '-', '') || replace(config_revision.id, '-', ''), 1, 64)
+)
+WHERE prefix_snapshot_id IS NULL
+  AND EXISTS (SELECT 1 FROM revision_materialized_prefix rmp WHERE rmp.revision_id = config_revision.id);
+
+INSERT INTO prefix_snapshot_row (snapshot_id, ord, prefix, community_id, source)
+SELECT cr.prefix_snapshot_id,
+    (SELECT COUNT(*) FROM revision_materialized_prefix r2
+     WHERE r2.revision_id = cr.id AND r2.id <= rmp.id) - 1,
+    rmp.prefix,
+    rmp.community_id,
+    rmp.source
+FROM config_revision cr
+JOIN revision_materialized_prefix rmp ON rmp.revision_id = cr.id
+WHERE cr.prefix_snapshot_id IS NOT NULL
+  AND NOT EXISTS (
+      SELECT 1 FROM prefix_snapshot_row psr WHERE psr.snapshot_id = cr.prefix_snapshot_id
+  );

migrations/sqlite/000018_prefix_snapshot_contract.up.sql

@@ -0,0 +1 @@
+-- H2 contract marker (application stops writing revision_materialized_prefix for new revisions).

migrations/sqlite/000019_module_snapshot_rows.down.sql

@@ -0,0 +1,2 @@
+ALTER TABLE module_prefix_snapshot ADD COLUMN prefixes_json TEXT NOT NULL DEFAULT '[]';
+DROP TABLE IF EXISTS module_prefix_snapshot_row;

migrations/sqlite/000019_module_snapshot_rows.up.sql

@@ -0,0 +1,13 @@
+CREATE TABLE module_prefix_snapshot_row (
+    tenant_id     TEXT NOT NULL,
+    module_id     TEXT NOT NULL,
+    ord           INTEGER NOT NULL,
+    prefix        TEXT NOT NULL,
+    community_id  TEXT,
+    source        TEXT NOT NULL DEFAULT '',
+    PRIMARY KEY (tenant_id, module_id, ord),
+    FOREIGN KEY (tenant_id, module_id)
+        REFERENCES module_prefix_snapshot (tenant_id, module_id) ON DELETE CASCADE
+);
+
+ALTER TABLE module_prefix_snapshot DROP COLUMN prefixes_json;

migrations/sqlite/000020_asn_cache_rows.down.sql

@@ -0,0 +1,2 @@
+ALTER TABLE asn_prefix_cache ADD COLUMN prefixes_json TEXT NOT NULL DEFAULT '[]';
+DROP TABLE IF EXISTS asn_prefix_cache_row;

migrations/sqlite/000020_asn_cache_rows.up.sql

@@ -0,0 +1,7 @@
+CREATE TABLE asn_prefix_cache_row (
+    asn     INTEGER NOT NULL REFERENCES asn_prefix_cache (asn) ON DELETE CASCADE,
+    prefix  TEXT NOT NULL,
+    PRIMARY KEY (asn, prefix)
+);
+
+ALTER TABLE asn_prefix_cache DROP COLUMN prefixes_json;

migrations/sqlite/000021_job_audit_brin.down.sql

@@ -0,0 +1 @@
+DROP INDEX IF EXISTS idx_job_audit_created_brin;

migrations/sqlite/000021_job_audit_brin.up.sql

@@ -0,0 +1 @@
+CREATE INDEX IF NOT EXISTS idx_job_audit_created_brin ON job_audit (created_at);

migrations/sqlite/000022_schema_cleanup.down.sql

@@ -0,0 +1,18 @@
+ALTER TABLE revision_materialized_prefix ADD COLUMN meta_json TEXT NOT NULL DEFAULT '{}';
+ALTER TABLE module_domain_entry ADD COLUMN resolve_meta TEXT NOT NULL DEFAULT '{}';
+
+CREATE TABLE IF NOT EXISTS module_cdn_fetch_log (
+    id          INTEGER PRIMARY KEY AUTOINCREMENT,
+    module_id   TEXT NOT NULL REFERENCES module (id) ON DELETE CASCADE,
+    source_id   TEXT REFERENCES module_cdn_source (id) ON DELETE SET NULL,
+    http_status INTEGER,
+    bytes       INTEGER,
+    error       TEXT,
+    fetched_at  TEXT NOT NULL DEFAULT (strftime('%Y-%m-%dT%H:%M:%fZ', 'now'))
+);
+CREATE INDEX IF NOT EXISTS idx_module_cdn_fetch_log_module ON module_cdn_fetch_log (module_id, fetched_at DESC);
+
+CREATE INDEX IF NOT EXISTS idx_rev_mat_prefix_revision ON revision_materialized_prefix (revision_id);
+CREATE INDEX IF NOT EXISTS idx_module_tenant ON module (tenant_id);
+CREATE INDEX IF NOT EXISTS idx_module_prefix_snapshot_collected ON module_prefix_snapshot (collected_at);
+CREATE INDEX IF NOT EXISTS idx_rev_mat_prefix_value ON revision_materialized_prefix (prefix);

migrations/sqlite/000022_schema_cleanup.up.sql

@@ -0,0 +1,8 @@
+ALTER TABLE revision_materialized_prefix DROP COLUMN meta_json;
+ALTER TABLE module_domain_entry DROP COLUMN resolve_meta;
+DROP TABLE IF EXISTS module_cdn_fetch_log;
+
+DROP INDEX IF EXISTS idx_rev_mat_prefix_revision;
+DROP INDEX IF EXISTS idx_module_tenant;
+DROP INDEX IF EXISTS idx_module_prefix_snapshot_collected;
+DROP INDEX IF EXISTS idx_rev_mat_prefix_value;

scripts/commit/verify-release-commits.mjs

@@ -0,0 +1,64 @@
+#!/usr/bin/env node
+/**
+ * Warns about commits since the last tag that semantic-release cannot parse.
+ * Exit 0 always — semantic-release still decides release/no-op.
+ */
+import { execSync } from 'node:child_process';
+import parser from 'conventional-commits-parser';
+
+const RELEASABLE = new Set(['feat', 'fix', 'perf', 'ci', 'refactor']);
+
+function lastTag() {
+	try {
+		return execSync('git describe --tags --abbrev=0', { encoding: 'utf8' }).trim();
+	} catch {
+		return '';
+	}
+}
+
+function commitsSince(ref) {
+	const range = ref ? `${ref}..HEAD` : 'HEAD';
+	const out = execSync(`git log ${range} --format=%H%x09%s`, { encoding: 'utf8' }).trim();
+	if (!out) return [];
+	return out.split('\n').map((line) => {
+		const [hash, subject] = line.split('\t');
+		return { hash: hash.trim(), subject: subject.trim() };
+	});
+}
+
+const tag = lastTag();
+const commits = commitsSince(tag);
+const unparseable = [];
+const releasable = [];
+
+for (const { hash, subject } of commits) {
+	const parsed = parser.sync(subject);
+	if (!parsed.type) {
+		unparseable.push({ hash: hash.slice(0, 7), subject });
+		continue;
+	}
+	if (RELEASABLE.has(parsed.type)) {
+		releasable.push({ hash: hash.slice(0, 7), subject, type: parsed.type });
+	}
+}
+
+if (commits.length === 0) {
+	console.log(`No new commits since ${tag || 'initial'}.`);
+	process.exit(0);
+}
+
+if (unparseable.length > 0) {
+	console.warn('::warning:: Commits not parseable by semantic-release (no version bump):');
+	for (const b of unparseable) {
+		console.warn(`  ${b.hash}  ${b.subject}`);
+	}
+	console.warn('Fix: single scope without commas, e.g. refactor(web): summary');
+}
+
+if (releasable.length > 0) {
+	console.log(`Releasable since ${tag}: ${releasable.length} commit(s).`);
+} else {
+	console.warn('::warning:: No releasable commits since last tag — release job will no-op.');
+}
+
+process.exit(0);

web/src/lib/api/types.ts

@@ -152,6 +152,13 @@ export type BgpCommunityPatch = Partial<BgpCommunityCreate>;
 export type CommunitiesResponse = Page<BgpCommunity>;
 
 // ---- Peers ----
+export type PeerSessionOnSpeaker = {
+	speaker_id: string;
+	label: string;
+	state: string;
+	poll_error?: string;
+};
+
 export type PeerRow = {
 	id: string;
 	name?: string;
@@ -160,8 +167,20 @@ export type PeerRow = {
 	enabled?: boolean;
 	session_state: string;
 	bgp_speaker_id: string | null;
+	connected_speaker_id?: string | null;
+	connected_speaker_label?: string;
+	session_on_speakers?: PeerSessionOnSpeaker[];
+	established_on_speakers?: PeerSessionOnSpeaker[];
+	session_mismatch?: boolean;
 };
-export type PeersResponse = Page<PeerRow>;
+export type LiveSpeakerPoll = {
+	speaker_id: string;
+	label: string;
+	ok: boolean;
+	session_count: number;
+	poll_error?: string;
+};
+export type PeersResponse = Page<PeerRow> & { live_speaker_poll?: LiveSpeakerPoll[] };
 export type BgpPeerCreate = {
 	name?: string;
 	neighbor: string;
@@ -172,6 +191,25 @@ export type BgpPeerCreate = {
 export type BgpPeerPatch = Partial<BgpPeerCreate>;
 
 // ---- Speakers ----
+export type BgpSessionLive = {
+	name: string;
+	neighbor?: string;
+	state: string;
+};
+
+export type SpeakerLiveStatus = {
+	label?: string;
+	agent_ok?: boolean;
+	agent_error?: string;
+	agent_last_sync_at?: string;
+	agent_last_applied_revision_id?: string;
+	bgp_poll_ok?: boolean;
+	bgp_poll_error?: string;
+	bgp_sessions_total?: number;
+	bgp_established?: number;
+	sessions?: BgpSessionLive[];
+};
+
 export type SpeakerRow = {
 	id: string;
 	role: string;
@@ -188,6 +226,7 @@ export type SpeakerRow = {
 	last_dispatch_error?: string | null;
 	meta_json?: Record<string, unknown>;
 	agent_secret?: string;
+	live?: SpeakerLiveStatus;
 };
 export type SpeakersResponse = Page<SpeakerRow>;
 export type BgpSpeakerCreate = {