fix(agentserver): hide upstream errors from clients

Generic 502 detail как в httpapi; добавлен docs/production-checklist.md.

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']
+	}
+};

docs/openapi.yaml

@@ -845,6 +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:
@@ -2216,6 +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:
@@ -2336,6 +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.
@@ -2670,6 +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.

internal/agentserver/server.go

@@ -14,6 +14,8 @@ import (
 	"evobgp/internal/nodecli"
 )
 
+const upstreamErrorDetail = "upstream request failed"
+
 // Config holds evobgp-agent serve settings.
 type Config struct {
 	Listen          string
@@ -85,7 +87,7 @@ func (s *Server) handleBirdProtocols(w http.ResponseWriter, r *http.Request) {
 	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, err.Error())
+		writeProblem(w, http.StatusBadGateway, upstreamErrorDetail)
 		return
 	}
 	writeJSON(w, http.StatusOK, map[string]any{
@@ -126,7 +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/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/routes.go

@@ -385,9 +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,
@@ -566,7 +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"
 )
@@ -24,7 +24,7 @@ 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 +34,10 @@ 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 {
+			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/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)
 	}

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/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/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
@@ -691,6 +692,33 @@ func (p *Postgres) GetRevision(tenantID, revisionID string) (*store.Revision, er
 	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

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)

internal/store/memory.go

@@ -424,14 +424,19 @@ 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/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 != "" {

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)
+	}
+}

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

@@ -173,7 +173,14 @@ export type PeerRow = {
 	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;
@@ -184,6 +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;
@@ -200,6 +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 = {

web/src/lib/components/network/NetworkAutoRefreshToggle.svelte

@@ -0,0 +1,30 @@
+<script lang="ts">
+	import { Label } from '$lib/ui/core/label/index.js';
+	import { Switch } from '$lib/ui/core/switch/index.js';
+	import { readNetworkAutoRefresh, writeNetworkAutoRefresh } from '$lib/network/network-metrics.js';
+
+	type Props = {
+		enabled?: boolean;
+		onchange?: (enabled: boolean) => void;
+		disabled?: boolean;
+	};
+
+	let {
+		enabled = $bindable(readNetworkAutoRefresh()),
+		onchange,
+		disabled = false
+	}: Props = $props();
+
+	function onToggle(checked: boolean) {
+		enabled = checked;
+		writeNetworkAutoRefresh(checked);
+		onchange?.(checked);
+	}
+</script>
+
+<div class="flex items-center gap-2">
+	<Switch id="network-auto-refresh" bind:checked={enabled} onCheckedChange={onToggle} {disabled} />
+	<Label for="network-auto-refresh" class="cursor-pointer text-sm text-muted-foreground">
+		Авто (~15 с)
+	</Label>
+</div>

web/src/lib/components/network/NetworkOverviewTab.svelte

@@ -0,0 +1,240 @@
+<script lang="ts">
+	import { resolve } from '$app/paths';
+	import type { BirdStatus, PeerRow, SpeakerRow } from '$lib/api/types.js';
+	import {
+		aggregateNetworkMetrics,
+		collectNetworkIssues,
+		deriveNetworkOverallStatus,
+		networkOverallStatusHint,
+		networkOverallStatusLabel
+	} from '$lib/network/network-metrics.js';
+	import { Alert, AlertDescription, AlertTitle } from '$lib/ui/core/alert/index.js';
+	import { Button } from '$lib/ui/core/button/index.js';
+	import KpiMetricsGrid from '$lib/ui/patterns/kpi/kpi-metrics-grid.svelte';
+	import NetworkSpeakerStatusCard from '$lib/components/network/NetworkSpeakerStatusCard.svelte';
+	import CheckCircle from '@lucide/svelte/icons/check-circle';
+	import AlertTriangle from '@lucide/svelte/icons/alert-triangle';
+	import XCircle from '@lucide/svelte/icons/x-circle';
+	import Share2 from '@lucide/svelte/icons/share-2';
+	import CheckCircle2 from '@lucide/svelte/icons/check-circle-2';
+	import Server from '@lucide/svelte/icons/server';
+	import GitBranch from '@lucide/svelte/icons/git-branch';
+	import Activity from '@lucide/svelte/icons/activity';
+	import Bird from '@lucide/svelte/icons/bird';
+	import Gauge from '@lucide/svelte/icons/gauge';
+
+	type Props = {
+		peers: PeerRow[];
+		speakers: SpeakerRow[];
+		bird: BirdStatus | null;
+		loading?: boolean;
+		initialLoading?: boolean;
+		onSpeakerSelect?: (speaker: SpeakerRow) => void;
+	};
+
+	let {
+		peers,
+		speakers,
+		bird,
+		loading = false,
+		initialLoading = false,
+		onSpeakerSelect
+	}: Props = $props();
+
+	const statAccents = [
+		{
+			border: 'border-l-chart-3',
+			bg: 'bg-chart-3/5',
+			iconBg: 'bg-chart-3/15',
+			iconText: 'text-chart-3'
+		},
+		{
+			border: 'border-l-chart-2',
+			bg: 'bg-chart-2/5',
+			iconBg: 'bg-chart-2/15',
+			iconText: 'text-chart-2'
+		},
+		{
+			border: 'border-l-chart-4',
+			bg: 'bg-chart-4/5',
+			iconBg: 'bg-chart-4/15',
+			iconText: 'text-chart-4'
+		},
+		{
+			border: 'border-l-warning',
+			bg: 'bg-warning/5',
+			iconBg: 'bg-warning/15',
+			iconText: 'text-warning'
+		},
+		{
+			border: 'border-l-destructive',
+			bg: 'bg-destructive/5',
+			iconBg: 'bg-destructive/15',
+			iconText: 'text-destructive'
+		},
+		{
+			border: 'border-l-info',
+			bg: 'bg-info/10',
+			iconBg: 'bg-info/15',
+			iconText: 'text-info'
+		}
+	] as const;
+
+	const metrics = $derived(aggregateNetworkMetrics(peers, speakers, bird));
+	const overallStatus = $derived(deriveNetworkOverallStatus(metrics));
+	const overallHint = $derived(networkOverallStatusHint(overallStatus, metrics));
+	const issues = $derived(collectNetworkIssues(peers, speakers, 5));
+
+	const birdText = $derived.by(() => {
+		if (!bird?.birdc_configured) return '—';
+		if (bird.error) return '—';
+		return `${bird.bgp_established}/${bird.bgp_sessions_total}`;
+	});
+
+	const kpiCards = $derived.by(() => [
+		{
+			id: 'peers',
+			label: 'BGP-пиры',
+			value: initialLoading ? '—' : String(metrics.peersTotal),
+			description: initialLoading
+				? ''
+				: `${metrics.peersEstablished} Established из ${metrics.peersEnabled} вкл.`,
+			icon: Share2,
+			accent: statAccents[0],
+			badge: metrics.peersMismatch > 0 ? `mismatch ${metrics.peersMismatch}` : 'peers',
+			badgeClass:
+				metrics.peersMismatch > 0 ? 'border-warning/30 bg-warning/15 text-warning' : undefined
+		},
+		{
+			id: 'established',
+			label: 'Активные сессии',
+			value: initialLoading ? '—' : String(metrics.peersEstablished),
+			description: 'Established среди включённых пиров',
+			icon: CheckCircle2,
+			accent: statAccents[1],
+			badge: metrics.peersEstablished > 0 ? 'Established' : 'нет сессий',
+			badgeClass:
+				metrics.peersEstablished > 0 ? 'border-success/30 bg-success/15 text-success' : undefined
+		},
+		{
+			id: 'speakers',
+			label: 'Спикеры online',
+			value: initialLoading ? '—' : `${metrics.speakersOnline}/${metrics.speakersTotal}`,
+			description: 'agent + BGP poll',
+			icon: Server,
+			accent: statAccents[2],
+			badge: metrics.speakersOnline === metrics.speakersTotal ? 'все online' : 'есть offline',
+			badgeClass:
+				metrics.speakersOnline === metrics.speakersTotal
+					? 'border-success/30 bg-success/15 text-success'
+					: 'border-warning/30 bg-warning/15 text-warning'
+		},
+		{
+			id: 'drift',
+			label: 'Drift',
+			value: initialLoading ? '—' : String(metrics.speakersDrift),
+			description: 'applied ≠ published',
+			icon: GitBranch,
+			accent: statAccents[3],
+			badge: metrics.speakersDrift > 0 ? 'требует apply' : 'синхронно',
+			badgeVariant: metrics.speakersDrift > 0 ? ('secondary' as const) : ('outline' as const)
+		},
+		{
+			id: 'poll-errors',
+			label: 'Ошибки опроса',
+			value: initialLoading ? '—' : String(metrics.pollErrors),
+			description: 'agent или BGP poll',
+			icon: Activity,
+			accent: statAccents[4],
+			badge: metrics.pollErrors > 0 ? 'ошибки' : 'ok',
+			badgeClass:
+				metrics.pollErrors === 0 ? 'border-success/30 bg-success/15 text-success' : undefined
+		},
+		{
+			id: 'cp-bird',
+			label: 'BGP на CP',
+			value: initialLoading ? '—' : birdText,
+			description: bird?.birdc_configured
+				? 'Established / total на API-хосте'
+				: (bird?.message ?? 'birdc не настроен'),
+			icon: Bird,
+			accent: statAccents[5],
+			badge: !bird?.birdc_configured ? 'N/A' : bird?.healthy ? 'В норме' : 'Деградация',
+			href: '/monitoring' as const
+		}
+	]);
+</script>
+
+<div class="flex min-w-0 flex-col gap-6">
+	{#if !initialLoading && !loading}
+		{#if overallStatus === 'ok'}
+			<Alert class="border-success/30 bg-success/5">
+				<CheckCircle class="text-success" />
+				<AlertTitle>{networkOverallStatusLabel(overallStatus)}</AlertTitle>
+				<AlertDescription>{overallHint}</AlertDescription>
+			</Alert>
+		{:else if overallStatus === 'warn'}
+			<Alert class="border-warning/30 bg-warning/5">
+				<AlertTriangle class="text-warning" />
+				<AlertTitle>{networkOverallStatusLabel(overallStatus)}</AlertTitle>
+				<AlertDescription>
+					{overallHint}
+					{#if issues.length > 0}
+						<ul class="mt-2 list-inside list-disc text-sm">
+							{#each issues as issue (issue.id)}
+								<li>{issue.message}</li>
+							{/each}
+						</ul>
+					{/if}
+				</AlertDescription>
+			</Alert>
+		{:else}
+			<Alert variant="destructive">
+				<XCircle />
+				<AlertTitle>{networkOverallStatusLabel(overallStatus)}</AlertTitle>
+				<AlertDescription>
+					{overallHint}
+					{#if issues.length > 0}
+						<ul class="mt-2 list-inside list-disc text-sm">
+							{#each issues as issue (issue.id)}
+								<li>{issue.message}</li>
+							{/each}
+						</ul>
+					{/if}
+				</AlertDescription>
+			</Alert>
+		{/if}
+	{/if}
+
+	<KpiMetricsGrid
+		cards={kpiCards}
+		loading={initialLoading || loading}
+		skeletonCount={6}
+		class="sm:grid-cols-2 xl:grid-cols-3"
+	/>
+
+	<section class="flex min-w-0 flex-col gap-4">
+		<div class="flex flex-wrap items-center justify-between gap-2">
+			<h2 class="text-base font-semibold">Ноды</h2>
+			<Button variant="outline" size="sm" href={resolve('/monitoring')}>
+				<Gauge class="size-3.5" />
+				Мониторинг API
+			</Button>
+		</div>
+
+		{#if speakers.length === 0 && !initialLoading && !loading}
+			<p class="text-sm text-muted-foreground">Спикеры не зарегистрированы.</p>
+		{:else}
+			<div class="grid auto-rows-fr gap-4 sm:grid-cols-2 xl:grid-cols-3">
+				{#each speakers as speaker (speaker.id)}
+					<NetworkSpeakerStatusCard
+						{speaker}
+						{peers}
+						class="h-full"
+						onclick={onSpeakerSelect ? () => onSpeakerSelect(speaker) : undefined}
+					/>
+				{/each}
+			</div>
+		{/if}
+	</section>
+</div>

web/src/lib/components/network/NetworkSpeakerDetailSheet.svelte

@@ -0,0 +1,203 @@
+<script lang="ts">
+	import type { PeerRow, SpeakerRow } from '$lib/api/types.js';
+	import {
+		peersForSpeaker,
+		speakerDisplayStatus,
+		speakerDispatchError,
+		speakerHasDrift,
+		speakerLabel,
+		speakerLiveAgentError,
+		speakerLiveBgpError
+	} from '$lib/network/network-metrics.js';
+	import { Alert, AlertDescription, AlertTitle } from '$lib/ui/core/alert/index.js';
+	import { Badge } from '$lib/ui/core/badge/index.js';
+	import { Button } from '$lib/ui/core/button/index.js';
+	import { Separator } from '$lib/ui/core/separator/index.js';
+	import {
+		Sheet,
+		SheetContent,
+		SheetDescription,
+		SheetHeader,
+		SheetTitle
+	} from '$lib/ui/core/sheet/index.js';
+	import {
+		Table,
+		TableBody,
+		TableCell,
+		TableHead,
+		TableHeader,
+		TableRow
+	} from '$lib/ui/core/table/index.js';
+	import AlertTriangle from '@lucide/svelte/icons/alert-triangle';
+
+	type Props = {
+		speaker: SpeakerRow | null;
+		peers: PeerRow[];
+		open?: boolean;
+		onOpenChange?: (open: boolean) => void;
+		onApply?: (speaker: SpeakerRow) => void;
+	};
+
+	let { speaker, peers, open = $bindable(false), onOpenChange, onApply }: Props = $props();
+
+	const status = $derived(speaker ? speakerDisplayStatus(speaker) : null);
+	const label = $derived(speaker ? speakerLabel(speaker) : '');
+	const relatedPeers = $derived(speaker ? peersForSpeaker(peers, speaker.id) : []);
+	const sessions = $derived(speaker?.live?.sessions ?? []);
+	const dispatchError = $derived(speaker ? speakerDispatchError(speaker) : null);
+	const agentError = $derived(speaker ? speakerLiveAgentError(speaker) : null);
+	const bgpError = $derived(speaker ? speakerLiveBgpError(speaker) : null);
+
+	function driftLabel(s: SpeakerRow): string {
+		const pub = s.published_revision_id?.slice(0, 8) ?? '—';
+		const app = s.last_applied_revision_id?.slice(0, 8) ?? '—';
+		return `${app} / ${pub}`;
+	}
+
+	function formatSyncAt(iso: string | undefined): string {
+		if (!iso) return '—';
+		const d = new Date(iso);
+		return Number.isNaN(d.getTime()) ? iso : d.toLocaleString('ru-RU');
+	}
+
+	$effect(() => {
+		onOpenChange?.(open);
+	});
+</script>
+
+<Sheet bind:open>
+	<SheetContent class="flex w-full flex-col gap-0 overflow-y-auto p-0 sm:max-w-md">
+		{#if speaker}
+			<div class="flex min-w-0 flex-col gap-4 px-4 pt-4 pb-6">
+				<SheetHeader class="space-y-1 pr-8 text-left">
+					<SheetTitle class="truncate">{label}</SheetTitle>
+					<SheetDescription class="truncate">
+						{speaker.role} · {speaker.agent_domain ?? speaker.endpoint}
+					</SheetDescription>
+				</SheetHeader>
+
+				<div class="flex flex-wrap items-center gap-2">
+					{#if status}
+						<Badge variant={status.variant}>{status.label}</Badge>
+					{/if}
+					{#if speakerHasDrift(speaker)}
+						<Badge variant="secondary">Drift</Badge>
+					{/if}
+				</div>
+
+				<dl class="grid grid-cols-[minmax(0,9rem)_1fr] gap-x-3 gap-y-2 text-sm">
+					<dt class="text-muted-foreground">BGP Established</dt>
+					<dd class="text-right font-medium tabular-nums">
+						{speaker.live?.bgp_established ?? '—'} / {speaker.live?.bgp_sessions_total ?? '—'}
+					</dd>
+					{#if speaker.live?.agent_last_sync_at}
+						<dt class="text-muted-foreground">Последний sync</dt>
+						<dd class="text-right text-xs tabular-nums">
+							{formatSyncAt(speaker.live.agent_last_sync_at)}
+						</dd>
+					{/if}
+					<dt class="text-muted-foreground">Drift (app / pub)</dt>
+					<dd class="truncate text-right font-mono text-xs">{driftLabel(speaker)}</dd>
+					{#if speaker.last_dispatch_at}
+						<dt class="text-muted-foreground">Dispatch</dt>
+						<dd class="text-right text-xs tabular-nums">
+							{formatSyncAt(speaker.last_dispatch_at)}
+						</dd>
+					{/if}
+				</dl>
+
+				{#if dispatchError}
+					<Alert class="border-warning/30 bg-warning/5">
+						<AlertTriangle class="text-warning" />
+						<AlertTitle class="text-sm">{dispatchError.title}</AlertTitle>
+						<AlertDescription class="text-xs leading-relaxed"
+							>{dispatchError.detail}</AlertDescription
+						>
+					</Alert>
+				{/if}
+				{#if agentError}
+					<Alert variant="destructive">
+						<AlertTitle class="text-sm">{agentError.title}</AlertTitle>
+						<AlertDescription class="text-xs">{agentError.detail}</AlertDescription>
+					</Alert>
+				{/if}
+				{#if bgpError}
+					<Alert variant="destructive">
+						<AlertTitle class="text-sm">{bgpError.title}</AlertTitle>
+						<AlertDescription class="text-xs">{bgpError.detail}</AlertDescription>
+					</Alert>
+				{/if}
+
+				{#if onApply && speaker.published_revision_id}
+					<Button variant="outline" size="sm" class="w-fit" onclick={() => onApply(speaker)}>
+						Apply revision
+					</Button>
+				{/if}
+
+				<Separator />
+
+				<section class="min-w-0 space-y-2">
+					<h3 class="text-sm font-medium">BGP-сессии (live)</h3>
+					{#if sessions.length === 0}
+						<p class="text-sm text-muted-foreground">Нет данных или сессий нет.</p>
+					{:else}
+						<div class="rounded-md border">
+							<Table class="table-fixed">
+								<TableHeader>
+									<TableRow>
+										<TableHead class="w-[65%]">Имя</TableHead>
+										<TableHead class="w-[35%] text-right">Состояние</TableHead>
+									</TableRow>
+								</TableHeader>
+								<TableBody>
+									{#each sessions as sess, i (sess.name + i)}
+										<TableRow>
+											<TableCell class="align-top">
+												<p class="truncate font-mono text-xs" title={sess.name}>{sess.name}</p>
+												{#if sess.neighbor}
+													<p class="truncate text-xs text-muted-foreground" title={sess.neighbor}>
+														{sess.neighbor}
+													</p>
+												{/if}
+											</TableCell>
+											<TableCell class="text-right align-top">
+												<Badge variant="outline" class="shrink-0">{sess.state}</Badge>
+											</TableCell>
+										</TableRow>
+									{/each}
+								</TableBody>
+							</Table>
+						</div>
+					{/if}
+				</section>
+
+				<Separator />
+
+				<section class="min-w-0 space-y-2">
+					<h3 class="text-sm font-medium">Пиры на ноде</h3>
+					{#if relatedPeers.length === 0}
+						<p class="text-sm text-muted-foreground">Нет привязанных пиров.</p>
+					{:else}
+						<ul class="divide-y rounded-md border">
+							{#each relatedPeers as p (p.id)}
+								<li class="flex min-w-0 items-start justify-between gap-3 px-3 py-2.5 text-sm">
+									<div class="min-w-0 flex-1">
+										<p class="truncate font-medium" title={p.name?.trim() || p.neighbor}>
+											{p.name?.trim() || p.neighbor}
+										</p>
+										{#if p.session_mismatch}
+											<p class="mt-0.5 text-xs text-warning">
+												Mismatch: сессия не на назначенной ноде
+											</p>
+										{/if}
+									</div>
+									<Badge variant="outline" class="shrink-0">{p.session_state || '—'}</Badge>
+								</li>
+							{/each}
+						</ul>
+					{/if}
+				</section>
+			</div>
+		{/if}
+	</SheetContent>
+</Sheet>

web/src/lib/components/network/NetworkSpeakerStatusCard.svelte

@@ -0,0 +1,85 @@
+<script lang="ts">
+	import type { PeerRow, SpeakerRow } from '$lib/api/types.js';
+	import {
+		speakerBgpText,
+		speakerDisplayStatus,
+		speakerHasDrift,
+		speakerLabel
+	} from '$lib/network/network-metrics.js';
+	import { Badge } from '$lib/ui/core/badge/index.js';
+	import {
+		Card,
+		CardContent,
+		CardHeader,
+		CardTitle,
+		CardDescription
+	} from '$lib/ui/core/card/index.js';
+	import { cn } from '$lib/utils.js';
+	import Server from '@lucide/svelte/icons/server';
+
+	type Props = {
+		speaker: SpeakerRow;
+		peers?: PeerRow[];
+		onclick?: () => void;
+		class?: string;
+	};
+
+	let { speaker, peers = [], onclick, class: className }: Props = $props();
+
+	const status = $derived(speakerDisplayStatus(speaker));
+	const label = $derived(speakerLabel(speaker));
+	const drift = $derived(speakerHasDrift(speaker));
+	const peerCount = $derived(
+		peers.filter(
+			(p) =>
+				p.bgp_speaker_id === speaker.id ||
+				p.bgp_speaker_id === null ||
+				p.bgp_speaker_id === undefined
+		).length
+	);
+</script>
+
+<!-- svelte-ignore a11y_no_noninteractive_tabindex -->
+<Card
+	class={cn(
+		'flex h-full flex-col transition-colors',
+		onclick ? 'cursor-pointer hover:border-primary/35' : '',
+		className
+	)}
+	role={onclick ? 'button' : undefined}
+	tabindex={onclick ? 0 : undefined}
+	{onclick}
+	onkeydown={(e) => {
+		if (onclick && (e.key === 'Enter' || e.key === ' ')) {
+			e.preventDefault();
+			onclick();
+		}
+	}}
+>
+	<CardHeader class="pb-2">
+		<div class="flex items-start gap-2">
+			<div class="min-w-0 flex-1">
+				<CardTitle class="flex items-center gap-2 text-sm">
+					<Server class="size-4 shrink-0 text-muted-foreground" aria-hidden="true" />
+					<span class="truncate" title={label}>{label}</span>
+				</CardTitle>
+				<CardDescription class="truncate font-mono text-xs">{speaker.role}</CardDescription>
+			</div>
+			<Badge variant={status.variant} class="shrink-0">{status.label}</Badge>
+		</div>
+	</CardHeader>
+	<CardContent class="mt-auto pt-0">
+		<dl class="grid grid-cols-[1fr_auto] gap-x-3 gap-y-2 text-sm">
+			<dt class="text-muted-foreground">BGP</dt>
+			<dd class="font-medium tabular-nums">{speakerBgpText(speaker)}</dd>
+			<dt class="text-muted-foreground">Пиры</dt>
+			<dd class="tabular-nums">{peerCount}</dd>
+			<dt class="text-muted-foreground">Drift</dt>
+			<dd>
+				<Badge variant={drift ? 'secondary' : 'outline'} class="text-xs">
+					{drift ? 'есть' : 'нет'}
+				</Badge>
+			</dd>
+		</dl>
+	</CardContent>
+</Card>

web/src/lib/components/network/NetworkSpeakersCard.svelte

@@ -1,6 +1,11 @@
 <script lang="ts">
 	import { apiJSON, apiMutate } from '$lib/api/client.js';
 	import type { SpeakerRow, BgpSpeakerCreate, BundleSigningPublicKey } from '$lib/api/types.js';
+	import {
+		speakerBgpText,
+		speakerDisplayStatus,
+		speakerHasDrift
+	} from '$lib/network/network-metrics.js';
 	import { Badge } from '$lib/ui/core/badge/index.js';
 	import { Button } from '$lib/ui/core/button/index.js';
 	import {
@@ -29,6 +34,7 @@
 	import Play from '@lucide/svelte/icons/play';
 	import Copy from '@lucide/svelte/icons/copy';
 	import Trash2 from '@lucide/svelte/icons/trash-2';
+	import Eye from '@lucide/svelte/icons/eye';
 
 	type Props = {
 		items: SpeakerRow[];
@@ -36,9 +42,17 @@
 		initialLoading?: boolean;
 		error?: string | null;
 		onRefresh: () => void | Promise<void>;
+		onSpeakerSelect?: (speaker: SpeakerRow) => void;
 	};
 
-	let { items, loading = false, initialLoading = false, error = null, onRefresh }: Props = $props();
+	let {
+		items,
+		loading = false,
+		initialLoading = false,
+		error = null,
+		onRefresh,
+		onSpeakerSelect
+	}: Props = $props();
 
 	type SpeakerForm = {
 		endpoint: string;
@@ -72,6 +86,8 @@
 
 	const columns = [
 		{ id: 'status', label: 'Статус' },
+		{ id: 'live_agent', label: 'Agent' },
+		{ id: 'bgp', label: 'BGP' },
 		{
 			id: 'agent_domain',
 			label: 'Agent domain',
@@ -80,7 +96,7 @@
 		},
 		{ id: 'role', label: 'Роль', sortable: true, sortValue: (s: SpeakerRow) => s.role },
 		{ id: 'drift', label: 'Drift' },
-		{ id: 'actions', label: '', class: 'w-40' }
+		{ id: 'actions', label: '', class: 'w-44' }
 	] as const;
 
 	function parseIpv4FromEndpoint(ep: string): string {
@@ -152,16 +168,17 @@
 	}
 
 	function statusVariant(s: SpeakerRow): 'default' | 'secondary' | 'destructive' | 'outline' {
-		if (s.sync_status === 'synced' || s.dispatch_status === 'ok') return 'default';
-		if (s.sync_status === 'error' || s.dispatch_status === 'error') return 'destructive';
-		return 'outline';
+		return speakerDisplayStatus(s).variant;
 	}
 
 	function statusLabel(s: SpeakerRow): string {
-		if (s.sync_status === 'synced') return 'Connected';
-		if (s.sync_status === 'error' || s.last_dispatch_error) return 'Offline';
-		if (s.dispatch_status === 'ok') return 'Synced';
-		return 'Unknown';
+		return speakerDisplayStatus(s).label;
+	}
+
+	function liveAgentLabel(s: SpeakerRow): string {
+		if (!s.live) return '—';
+		if (s.live.agent_ok === true) return 'OK';
+		return s.live.agent_error ? 'Error' : 'Offline';
 	}
 
 	function driftLabel(s: SpeakerRow): string {
@@ -333,16 +350,29 @@ CF_DNS_API_TOKEN=<cloudflare token>
 			{#snippet cell({ row: s, column })}
 				{#if column.id === 'status'}
 					<Badge variant={statusVariant(s)}>{statusLabel(s)}</Badge>
+				{:else if column.id === 'live_agent'}
+					<Badge variant={s.live?.agent_ok ? 'outline' : 'destructive'}>{liveAgentLabel(s)}</Badge>
+				{:else if column.id === 'bgp'}
+					<span class="font-mono text-xs tabular-nums">{speakerBgpText(s)}</span>
 				{:else if column.id === 'agent_domain'}
 					<span class="font-mono text-sm">{s.agent_domain ?? s.endpoint}</span>
 				{:else if column.id === 'role'}
 					<Badge variant="outline">{s.role}</Badge>
 				{:else if column.id === 'drift'}
-					<span class="font-mono text-xs text-muted-foreground" title="applied / published">
+					<span
+						class="font-mono text-xs text-muted-foreground"
+						title="applied / published"
+						class:text-warning={speakerHasDrift(s)}
+					>
 						{driftLabel(s)}
 					</span>
 				{:else if column.id === 'actions'}
 					<div class="flex flex-wrap gap-1">
+						{#if onSpeakerSelect}
+							<Button variant="outline" size="xs" title="Детали" onclick={() => onSpeakerSelect(s)}>
+								<Eye class="size-3" />
+							</Button>
+						{/if}
 						<Button variant="outline" size="xs" title="Copy compose" onclick={() => openCompose(s)}>
 							<Copy class="size-3" />
 						</Button>

web/src/lib/components/overview/OverviewNetworkStatusCard.svelte

@@ -0,0 +1,120 @@
+<script lang="ts">
+	import { resolve } from '$app/paths';
+	import type { PeerRow, SpeakerRow } from '$lib/api/types.js';
+	import {
+		aggregateNetworkMetrics,
+		collectNetworkIssues,
+		deriveNetworkOverallStatus,
+		networkOverallStatusHint,
+		networkOverallStatusLabel
+	} from '$lib/network/network-metrics.js';
+	import { Alert, AlertDescription, AlertTitle } from '$lib/ui/core/alert/index.js';
+	import { Button } from '$lib/ui/core/button/index.js';
+	import {
+		Card,
+		CardContent,
+		CardHeader,
+		CardTitle,
+		CardDescription
+	} from '$lib/ui/core/card/index.js';
+	import CheckCircle from '@lucide/svelte/icons/check-circle';
+	import AlertTriangle from '@lucide/svelte/icons/alert-triangle';
+	import XCircle from '@lucide/svelte/icons/x-circle';
+	import ArrowRight from '@lucide/svelte/icons/arrow-right';
+	import NetworkIcon from '@lucide/svelte/icons/network';
+
+	type Props = {
+		peers: PeerRow[];
+		speakers: SpeakerRow[];
+		loading?: boolean;
+		initialLoading?: boolean;
+		error?: string | null;
+	};
+
+	let { peers, speakers, loading = false, initialLoading = false, error = null }: Props = $props();
+
+	const metrics = $derived(aggregateNetworkMetrics(peers, speakers));
+	const overallStatus = $derived(deriveNetworkOverallStatus(metrics));
+	const overallHint = $derived(networkOverallStatusHint(overallStatus, metrics));
+	const issues = $derived(collectNetworkIssues(peers, speakers, 3));
+</script>
+
+<Card>
+	<CardHeader
+		class="flex flex-col gap-3 border-b py-3 sm:flex-row sm:items-center sm:justify-between"
+	>
+		<div class="min-w-0 flex-1">
+			<CardTitle class="flex items-center gap-2 text-base">
+				<NetworkIcon class="size-4" />
+				Сеть (BGP)
+			</CardTitle>
+			<CardDescription>Live-статус пиров и спикеров</CardDescription>
+		</div>
+		<Button variant="outline" size="sm" href={resolve('/network?tab=overview')}>
+			Подробнее
+			<ArrowRight class="size-3.5" />
+		</Button>
+	</CardHeader>
+	<CardContent class="space-y-3 p-4 pt-4">
+		{#if error}
+			<p class="text-sm text-destructive">{error}</p>
+		{:else if initialLoading || loading}
+			<p class="text-sm text-muted-foreground">Загрузка live-метрик…</p>
+		{:else if overallStatus === 'ok'}
+			<Alert class="border-success/30 bg-success/5 py-3">
+				<CheckCircle class="text-success" />
+				<AlertTitle class="text-sm">{networkOverallStatusLabel(overallStatus)}</AlertTitle>
+				<AlertDescription class="text-xs">{overallHint}</AlertDescription>
+			</Alert>
+		{:else if overallStatus === 'warn'}
+			<Alert class="border-warning/30 bg-warning/5 py-3">
+				<AlertTriangle class="text-warning" />
+				<AlertTitle class="text-sm">{networkOverallStatusLabel(overallStatus)}</AlertTitle>
+				<AlertDescription class="text-xs">
+					{overallHint}
+					{#if issues.length > 0}
+						<ul class="mt-2 list-inside list-disc">
+							{#each issues as issue (issue.id)}
+								<li>{issue.message}</li>
+							{/each}
+						</ul>
+					{/if}
+				</AlertDescription>
+			</Alert>
+		{:else}
+			<Alert variant="destructive" class="py-3">
+				<XCircle />
+				<AlertTitle class="text-sm">{networkOverallStatusLabel(overallStatus)}</AlertTitle>
+				<AlertDescription class="text-xs">
+					{overallHint}
+					{#if issues.length > 0}
+						<ul class="mt-2 list-inside list-disc">
+							{#each issues as issue (issue.id)}
+								<li>{issue.message}</li>
+							{/each}
+						</ul>
+					{/if}
+				</AlertDescription>
+			</Alert>
+		{/if}
+
+		<div class="flex flex-wrap gap-4 text-sm">
+			<div>
+				<p class="text-muted-foreground">Пиры Established</p>
+				<p class="text-xl font-bold tabular-nums">
+					{initialLoading ? '—' : `${metrics.peersEstablished}/${metrics.peersEnabled}`}
+				</p>
+			</div>
+			<div>
+				<p class="text-muted-foreground">Спикеры online</p>
+				<p class="text-xl font-bold tabular-nums">
+					{initialLoading ? '—' : `${metrics.speakersOnline}/${metrics.speakersTotal}`}
+				</p>
+			</div>
+			<div>
+				<p class="text-muted-foreground">Drift</p>
+				<p class="text-xl font-bold tabular-nums">{initialLoading ? '—' : metrics.speakersDrift}</p>
+			</div>
+		</div>
+	</CardContent>
+</Card>

web/src/lib/network/network-metrics.ts

@@ -0,0 +1,295 @@
+import type { BirdStatus, PeerRow, SpeakerRow } from '$lib/api/types.js';
+
+export type NetworkOverallStatus = 'ok' | 'warn' | 'error';
+
+export type NetworkMetrics = {
+	peersTotal: number;
+	peersEnabled: number;
+	peersEstablished: number;
+	peersMismatch: number;
+	speakersTotal: number;
+	speakersOnline: number;
+	speakersRemote: number;
+	speakersRemoteOnline: number;
+	speakersDrift: number;
+	pollErrors: number;
+	hasLiveData: boolean;
+};
+
+export type SpeakerStatusBadge = {
+	label: string;
+	variant: 'default' | 'secondary' | 'destructive' | 'outline';
+};
+
+export type NetworkIssue = {
+	id: string;
+	message: string;
+	severity: 'warn' | 'error';
+};
+
+function isRemoteSpeaker(s: SpeakerRow): boolean {
+	const role = (s.role ?? '').toLowerCase();
+	return role !== 'master' && Boolean(s.agent_domain?.trim());
+}
+
+export function speakerHasDrift(s: SpeakerRow): boolean {
+	const pub = s.published_revision_id?.trim();
+	if (!pub) return false;
+	return (s.last_applied_revision_id ?? '') !== pub;
+}
+
+export function speakerIsOnline(s: SpeakerRow): boolean {
+	if (s.live) {
+		return s.live.agent_ok === true && s.live.bgp_poll_ok !== false;
+	}
+	if (s.sync_status === 'synced') return true;
+	if (s.sync_status === 'error' || s.last_dispatch_error) return false;
+	return s.dispatch_status === 'ok';
+}
+
+export function speakerDisplayStatus(s: SpeakerRow): SpeakerStatusBadge {
+	if (s.live) {
+		if (s.live.agent_ok === true && s.live.bgp_poll_ok !== false) {
+			return { label: 'Online', variant: 'default' };
+		}
+		if (s.live.bgp_poll_error || s.live.agent_error) {
+			return { label: 'Offline', variant: 'destructive' };
+		}
+		return { label: 'Degraded', variant: 'secondary' };
+	}
+	if (s.sync_status === 'synced') return { label: 'Connected', variant: 'default' };
+	if (s.sync_status === 'error' || s.last_dispatch_error) {
+		return { label: 'Offline', variant: 'destructive' };
+	}
+	if (s.dispatch_status === 'ok') return { label: 'Synced', variant: 'outline' };
+	return { label: 'Unknown', variant: 'outline' };
+}
+
+export function speakerLabel(s: SpeakerRow): string {
+	return s.live?.label ?? s.agent_domain ?? s.endpoint ?? s.id;
+}
+
+export function speakerBgpText(s: SpeakerRow): string {
+	if (s.live) {
+		return `${s.live.bgp_established ?? 0}/${s.live.bgp_sessions_total ?? 0}`;
+	}
+	return '—';
+}
+
+export function peersForSpeaker(peers: PeerRow[], speakerId: string): PeerRow[] {
+	return peers.filter(
+		(p) =>
+			p.bgp_speaker_id === speakerId || p.bgp_speaker_id === null || p.bgp_speaker_id === undefined
+	);
+}
+
+export function aggregateNetworkMetrics(
+	peers: PeerRow[],
+	speakers: SpeakerRow[],
+	bird?: BirdStatus | null
+): NetworkMetrics {
+	const enabledPeers = peers.filter((p) => p.enabled !== false);
+	const established = enabledPeers.filter((p) => p.session_state === 'Established').length;
+	const mismatch = peers.filter((p) => p.session_mismatch).length;
+	const remoteSpeakers = speakers.filter(isRemoteSpeaker);
+	const online = speakers.filter(speakerIsOnline).length;
+	const remoteOnline = remoteSpeakers.filter(speakerIsOnline).length;
+	const drift = speakers.filter(speakerHasDrift).length;
+	const pollErrors = speakers.filter(
+		(s) => s.live?.bgp_poll_error || (s.live && s.live.agent_ok === false)
+	).length;
+	const hasLiveData =
+		speakers.some((s) => s.live != null) || peers.some((p) => p.session_on_speakers);
+
+	void bird;
+
+	return {
+		peersTotal: peers.length,
+		peersEnabled: enabledPeers.length,
+		peersEstablished: established,
+		peersMismatch: mismatch,
+		speakersTotal: speakers.length,
+		speakersOnline: online,
+		speakersRemote: remoteSpeakers.length,
+		speakersRemoteOnline: remoteOnline,
+		speakersDrift: drift,
+		pollErrors,
+		hasLiveData
+	};
+}
+
+export function deriveNetworkOverallStatus(metrics: NetworkMetrics): NetworkOverallStatus {
+	if (!metrics.hasLiveData && metrics.speakersTotal === 0 && metrics.peersTotal === 0) {
+		return 'ok';
+	}
+
+	const enabledNotEstablished =
+		metrics.peersEnabled > 0 ? metrics.peersEnabled - metrics.peersEstablished : 0;
+	const majorityPeersDown =
+		metrics.peersEnabled > 0 && enabledNotEstablished / metrics.peersEnabled > 0.5;
+
+	if ((metrics.speakersRemote > 0 && metrics.speakersRemoteOnline === 0) || majorityPeersDown) {
+		return 'error';
+	}
+
+	if (
+		metrics.pollErrors > 0 ||
+		metrics.peersMismatch > 0 ||
+		metrics.speakersDrift > 0 ||
+		metrics.speakersOnline < metrics.speakersTotal
+	) {
+		return 'warn';
+	}
+
+	return 'ok';
+}
+
+export function networkOverallStatusLabel(status: NetworkOverallStatus): string {
+	switch (status) {
+		case 'ok':
+			return 'В норме';
+		case 'warn':
+			return 'Требует внимания';
+		case 'error':
+			return 'Проблема';
+	}
+}
+
+export function networkOverallStatusHint(
+	status: NetworkOverallStatus,
+	metrics: NetworkMetrics
+): string {
+	switch (status) {
+		case 'ok':
+			return metrics.hasLiveData
+				? `${metrics.peersEstablished} Established, ${metrics.speakersOnline}/${metrics.speakersTotal} спикеров online`
+				: 'Сеть настроена; обновите для live-статуса';
+		case 'warn':
+			return 'Есть drift, mismatch или недоступные ноды — проверьте детали';
+		case 'error':
+			return 'Критичная деградация BGP или все remote-ноды недоступны';
+	}
+}
+
+export function collectNetworkIssues(
+	peers: PeerRow[],
+	speakers: SpeakerRow[],
+	limit = 3
+): NetworkIssue[] {
+	const issues: NetworkIssue[] = [];
+
+	for (const s of speakers) {
+		if (!speakerIsOnline(s)) {
+			issues.push({
+				id: `speaker-offline-${s.id}`,
+				message: `Нода offline: ${speakerLabel(s)}`,
+				severity: 'error'
+			});
+		} else if (speakerHasDrift(s)) {
+			issues.push({
+				id: `speaker-drift-${s.id}`,
+				message: `Drift ревизии: ${speakerLabel(s)}`,
+				severity: 'warn'
+			});
+		} else if (s.live?.bgp_poll_error) {
+			issues.push({
+				id: `speaker-poll-${s.id}`,
+				message: `Ошибка BGP-опроса: ${speakerLabel(s)}`,
+				severity: 'warn'
+			});
+		} else if (s.last_dispatch_error) {
+			const err = formatSpeakerError(s.last_dispatch_error);
+			issues.push({
+				id: `speaker-dispatch-${s.id}`,
+				message: `Dispatch: ${speakerLabel(s)}${err ? ` — ${err.detail.slice(0, 80)}` : ''}`,
+				severity: 'warn'
+			});
+		}
+	}
+
+	for (const p of peers) {
+		if (p.session_mismatch) {
+			const name = p.name?.trim() || p.neighbor;
+			issues.push({
+				id: `peer-mismatch-${p.id}`,
+				message: `Mismatch сессии: ${name}`,
+				severity: 'warn'
+			});
+		}
+	}
+
+	return issues.slice(0, limit);
+}
+
+export const NETWORK_AUTO_REFRESH_KEY = 'evobgp.network.autoRefresh';
+export const NETWORK_AUTO_REFRESH_MS = 15_000;
+
+export function readNetworkAutoRefresh(): boolean {
+	if (typeof localStorage === 'undefined') return false;
+	return localStorage.getItem(NETWORK_AUTO_REFRESH_KEY) === '1';
+}
+
+export function writeNetworkAutoRefresh(enabled: boolean): void {
+	if (typeof localStorage === 'undefined') return;
+	localStorage.setItem(NETWORK_AUTO_REFRESH_KEY, enabled ? '1' : '0');
+}
+
+export type FormattedSpeakerError = {
+	title: string;
+	detail: string;
+};
+
+/** Humanize stored dispatch/agent errors (avoid raw JSON in UI). */
+export function formatSpeakerError(raw: string | null | undefined): FormattedSpeakerError | null {
+	if (!raw?.trim()) return null;
+	const text = raw.trim();
+
+	const jsonMatch = text.match(/\{[\s\S]*\}/);
+	if (jsonMatch) {
+		try {
+			const obj = JSON.parse(jsonMatch[0]) as {
+				detail?: string;
+				title?: string;
+				status?: number;
+			};
+			const detail = String(obj.detail ?? text);
+			if (/403/.test(detail) && /bundle/i.test(detail)) {
+				return {
+					title: 'Dispatch: доступ к бандлу',
+					detail:
+						'Нода не смогла скачать бандл с CP (403). Проверьте node API-ключ (роль node) и EVOBGP_NODE_TOKEN на реплике — см. docs/access.md.'
+				};
+			}
+			const httpPrefix = text.match(/^HTTP \d+:\s*/)?.[0] ?? '';
+			return {
+				title: obj.title && obj.title !== 'Bad Gateway' ? obj.title : 'Ошибка dispatch',
+				detail: httpPrefix ? `${httpPrefix.trim()} ${detail}`.trim() : detail
+			};
+		} catch {
+			/* fall through */
+		}
+	}
+
+	if (/^HTTP \d+:/.test(text)) {
+		return { title: 'Ошибка HTTP', detail: text };
+	}
+	return { title: 'Ошибка', detail: text };
+}
+
+export function speakerDispatchError(s: SpeakerRow): FormattedSpeakerError | null {
+	const liveRev = s.live?.agent_last_applied_revision_id?.trim();
+	const pub = s.published_revision_id?.trim();
+	// CP meta can keep a stale dispatch error after a later successful agent sync.
+	if (s.live?.agent_ok && liveRev && pub && liveRev === pub) {
+		return null;
+	}
+	return formatSpeakerError(s.last_dispatch_error);
+}
+
+export function speakerLiveAgentError(s: SpeakerRow): FormattedSpeakerError | null {
+	return formatSpeakerError(s.live?.agent_error);
+}
+
+export function speakerLiveBgpError(s: SpeakerRow): FormattedSpeakerError | null {
+	return formatSpeakerError(s.live?.bgp_poll_error);
+}

web/src/lib/ui/patterns/kpi/kpi-metrics-grid.svelte

@@ -45,7 +45,7 @@
 	let { cards, loading = false, skeletonCount = 3, class: className }: Props = $props();
 </script>
 
-<div class={cn('grid gap-4', className)}>
+<div class={cn('grid auto-rows-fr gap-4', className)}>
 	{#if loading}
 		{#each Array(skeletonCount) as _, i (i)}
 			<CardSkeleton />
@@ -56,7 +56,7 @@
 			{@const a = card.accent}
 			<Card
 				class={cn(
-					'overflow-hidden border-l-4 shadow-sm',
+					'flex h-full flex-col overflow-hidden border-l-4 shadow-sm',
 					card.href ? 'transition-colors hover:border-primary/35' : '',
 					a.border,
 					a.bg
@@ -96,7 +96,7 @@
 						>{card.value}</CardTitle
 					>
 				</CardHeader>
-				<CardContent class="space-y-2">
+				<CardContent class="mt-auto space-y-2">
 					<Badge variant={card.badgeVariant ?? 'outline'} class={card.badgeClass}
 						>{card.badge}</Badge
 					>

web/src/routes/+page.svelte

@@ -31,6 +31,8 @@
 	import { notifyApiError } from '$lib/ui/app/toast.js';
 	import OverviewRecentJobsCard from '$lib/components/overview/OverviewRecentJobsCard.svelte';
 	import OverviewRecentRevisionsCard from '$lib/components/overview/OverviewRecentRevisionsCard.svelte';
+	import OverviewNetworkStatusCard from '$lib/components/overview/OverviewNetworkStatusCard.svelte';
+	import { aggregateNetworkMetrics } from '$lib/network/network-metrics.js';
 	import { cn } from '$lib/utils.js';
 	import CheckCircle from '@lucide/svelte/icons/check-circle';
 	import XCircle from '@lucide/svelte/icons/x-circle';
@@ -47,6 +49,7 @@
 	import Share2 from '@lucide/svelte/icons/share-2';
 	import Play from '@lucide/svelte/icons/play';
 	import Gauge from '@lucide/svelte/icons/gauge';
+	import NetworkIcon from '@lucide/svelte/icons/network';
 
 	let healthy = $state<boolean | null>(null);
 	let moduleItems = $state<ModuleRow[]>([]);
@@ -106,6 +109,8 @@
 		return suffix;
 	}
 
+	const networkMetrics = $derived(aggregateNetworkMetrics(peerItems, speakerItems));
+
 	const kpiCards = $derived.by(() => [
 		{
 			id: 'modules',
@@ -120,22 +125,40 @@
 		{
 			id: 'peers',
 			label: 'Пиры',
-			value: initialLoading ? '—' : String(peerItems.length),
-			href: '/network' as const,
+			value: initialLoading
+				? '—'
+				: `${networkMetrics.peersEstablished}/${networkMetrics.peersEnabled}`,
+			href: '/network?tab=peers' as const,
 			icon: GitBranch,
-			description: 'BGP-соседи',
+			description: 'Established / включённых',
 			accent: statAccents[1],
-			badge: countBadge(peerItems.length, peersHasMore, 'peers')
+			badge:
+				networkMetrics.peersMismatch > 0
+					? `mismatch ${networkMetrics.peersMismatch}`
+					: countBadge(peerItems.length, peersHasMore, 'peers'),
+			badgeClass:
+				networkMetrics.peersMismatch > 0
+					? 'border-warning/30 bg-warning/15 text-warning'
+					: undefined
 		},
 		{
 			id: 'speakers',
 			label: 'Спикеры',
-			value: initialLoading ? '—' : String(speakerItems.length),
-			href: '/network' as const,
+			value: initialLoading
+				? '—'
+				: `${networkMetrics.speakersOnline}/${networkMetrics.speakersTotal}`,
+			href: '/network?tab=overview' as const,
 			icon: Radio,
-			description: 'BIRD-агенты',
+			description: 'online / всего',
 			accent: statAccents[2],
-			badge: countBadge(speakerItems.length, speakersHasMore, 'agents')
+			badge:
+				networkMetrics.speakersOnline < networkMetrics.speakersTotal
+					? 'есть offline'
+					: countBadge(speakerItems.length, speakersHasMore, 'agents'),
+			badgeClass:
+				networkMetrics.speakersOnline === networkMetrics.speakersTotal
+					? 'border-success/30 bg-success/15 text-success'
+					: 'border-warning/30 bg-warning/15 text-warning'
 		},
 		{
 			id: 'revisions',
@@ -183,8 +206,8 @@
 
 			const [m, p, s, r, j] = await Promise.allSettled([
 				apiJSON<ModulesResponse>('/v1/modules?limit=200'),
-				apiJSON<PeersResponse>('/v1/peers?limit=200'),
-				apiJSON<SpeakersResponse>('/v1/speakers?limit=200'),
+				apiJSON<PeersResponse>('/v1/peers?limit=200&live=1'),
+				apiJSON<SpeakersResponse>('/v1/speakers?limit=200&live=1'),
 				apiJSON<RevisionsResponse>('/v1/revisions?limit=10'),
 				apiJSON<JobsResponse>('/v1/jobs?limit=10')
 			]);
@@ -251,11 +274,12 @@
 		<Info class="text-info" />
 		<AlertTitle>Панель управления EvoBGP</AlertTitle>
 		<AlertDescription>
-			Сводка по модулям, сети и фоновым задачам. Настройка префиксов — на странице
-			<Button variant="link" class="h-auto p-0" href={resolve('/modules')}>Модули</Button>, деплой и
-			ревизии —
+			Сводка по модулям, сети и фоновым задачам. BGP и ноды —
+			<Button variant="link" class="h-auto p-0" href={resolve('/network?tab=overview')}>Сеть</Button
+			>, префиксы —
+			<Button variant="link" class="h-auto p-0" href={resolve('/modules')}>Модули</Button>, деплой —
 			<Button variant="link" class="h-auto p-0" href={resolve('/operations')}>Операции</Button>,
-			здоровье системы —
+			здоровье API —
 			<Button variant="link" class="h-auto p-0" href={resolve('/monitoring')}>Мониторинг</Button>.
 		</AlertDescription>
 	</Alert>
@@ -301,7 +325,7 @@
 		class="sm:grid-cols-2 lg:grid-cols-3"
 	/>
 
-	<div class="grid gap-4 lg:grid-cols-2">
+	<div class="grid gap-4 lg:grid-cols-3">
 		<OverviewRecentJobsCard
 			items={recentJobs}
 			{moduleNameById}
@@ -315,6 +339,13 @@
 			{initialLoading}
 			error={loadError}
 		/>
+		<OverviewNetworkStatusCard
+			peers={peerItems}
+			speakers={speakerItems}
+			loading={refreshing}
+			{initialLoading}
+			error={loadError}
+		/>
 	</div>
 
 	<Card>
@@ -331,7 +362,11 @@
 				<Tags class="size-4" />
 				Добавить community
 			</Button>
-			<Button variant="outline" size="sm" href={resolve('/network')}>
+			<Button variant="outline" size="sm" href={resolve('/network?tab=overview')}>
+				<NetworkIcon class="size-4" />
+				Сеть
+			</Button>
+			<Button variant="outline" size="sm" href={resolve('/network?tab=peers')}>
 				<Share2 class="size-4" />
 				Добавить пира
 			</Button>

web/src/routes/monitoring/+page.svelte

@@ -198,7 +198,7 @@
 					? 'border-success/30 bg-success/15 text-success'
 					: undefined,
 			error: birdError ?? bird?.error ?? null,
-			href: '/network' as const
+			href: '/network?tab=overview' as const
 		},
 		{
 			id: 'jobs',
@@ -468,7 +468,9 @@
 							</CardTitle>
 							<CardDescription>GET /v1/bird/status</CardDescription>
 						</div>
-						<Button variant="outline" size="sm" href={resolve('/network')}>Пиры и спикеры</Button>
+						<Button variant="outline" size="sm" href={resolve('/network?tab=overview')}
+							>Пиры и спикеры</Button
+						>
 					</div>
 				</CardHeader>
 				<CardContent class="space-y-4">
@@ -633,7 +635,9 @@
 						<AlertTitle>Низкий ratio BGP</AlertTitle>
 						<AlertDescription>
 							Проверьте <code class="text-xs">/v1/bird/status</code>, затем состояние пиров в
-							<Button variant="link" class="h-auto p-0" href={resolve('/network')}>Сети</Button>.
+							<Button variant="link" class="h-auto p-0" href={resolve('/network?tab=overview')}
+								>Сети</Button
+							>.
 						</AlertDescription>
 					</Alert>
 					<Alert>

web/src/routes/network/+page.svelte

@@ -4,94 +4,50 @@
 	import { page } from '$app/state';
 	import { resolve } from '$app/paths';
 	import { apiJSON } from '$lib/api/client.js';
-	import type { PeerRow, PeersResponse, SpeakerRow, SpeakersResponse } from '$lib/api/types.js';
+	import type {
+		BirdStatus,
+		PeerRow,
+		PeersResponse,
+		SpeakerRow,
+		SpeakersResponse
+	} from '$lib/api/types.js';
+	import { NETWORK_AUTO_REFRESH_MS } from '$lib/network/network-metrics.js';
 	import { Button } from '$lib/ui/core/button/index.js';
 	import { Alert, AlertDescription, AlertTitle } from '$lib/ui/core/alert/index.js';
 	import { Tabs, TabsContent, TabsList, TabsTrigger } from '$lib/ui/core/tabs/index.js';
-	import KpiMetricsGrid from '$lib/ui/patterns/kpi/kpi-metrics-grid.svelte';
 	import PageHeader from '$lib/ui/app/page-header/page-header.svelte';
 	import { notifyApiError } from '$lib/ui/app/toast.js';
 	import NetworkPeersCard from '$lib/components/network/NetworkPeersCard.svelte';
 	import NetworkSpeakersCard from '$lib/components/network/NetworkSpeakersCard.svelte';
 	import BirdSettingsForm from '$lib/components/network/BirdSettingsForm.svelte';
+	import NetworkOverviewTab from '$lib/components/network/NetworkOverviewTab.svelte';
+	import NetworkSpeakerDetailSheet from '$lib/components/network/NetworkSpeakerDetailSheet.svelte';
+	import NetworkAutoRefreshToggle from '$lib/components/network/NetworkAutoRefreshToggle.svelte';
 	import RefreshCw from '@lucide/svelte/icons/refresh-cw';
 	import NetworkIcon from '@lucide/svelte/icons/network';
 	import Info from '@lucide/svelte/icons/info';
-	import Share2 from '@lucide/svelte/icons/share-2';
-	import CheckCircle2 from '@lucide/svelte/icons/check-circle-2';
-	import Server from '@lucide/svelte/icons/server';
+	import LayoutDashboard from '@lucide/svelte/icons/layout-dashboard';
 
-	type NetworkTab = 'peers' | 'speakers' | 'control-plane';
+	type NetworkTab = 'overview' | 'peers' | 'speakers' | 'control-plane';
 
 	function parseNetworkTab(value: string | null): NetworkTab {
-		if (value === 'speakers' || value === 'control-plane') return value;
-		return 'peers';
+		if (value === 'peers' || value === 'speakers' || value === 'control-plane') return value;
+		return 'overview';
 	}
 
 	let peers = $state<PeerRow[]>([]);
 	let speakers = $state<SpeakerRow[]>([]);
+	let birdStatus = $state<BirdStatus | null>(null);
 	let peersLoading = $state(false);
 	let speakersLoading = $state(false);
 	let initialLoading = $state(true);
 	let loadError = $state<string | null>(null);
 	let lastUpdated = $state<Date | null>(null);
-	let activeTab = $state<NetworkTab>('peers');
+	let activeTab = $state<NetworkTab>('overview');
 	let tabSyncReady = $state(false);
-
-	const establishedCount = $derived(peers.filter((p) => p.session_state === 'Established').length);
-
-	const statAccents = [
-		{
-			border: 'border-l-chart-3',
-			bg: 'bg-chart-3/5',
-			iconBg: 'bg-chart-3/15',
-			iconText: 'text-chart-3'
-		},
-		{
-			border: 'border-l-chart-2',
-			bg: 'bg-chart-2/5',
-			iconBg: 'bg-chart-2/15',
-			iconText: 'text-chart-2'
-		},
-		{
-			border: 'border-l-chart-4',
-			bg: 'bg-chart-4/5',
-			iconBg: 'bg-chart-4/15',
-			iconText: 'text-chart-4'
-		}
-	] as const;
-
-	const kpiCards = $derived.by(() => [
-		{
-			id: 'peers',
-			label: 'BGP-пиры',
-			value: initialLoading ? '—' : String(peers.length),
-			description: 'настроенные BGP-соседи',
-			icon: Share2,
-			accent: statAccents[0],
-			badge: 'peers'
-		},
-		{
-			id: 'established',
-			label: 'Активные сессии',
-			value: initialLoading ? '—' : String(establishedCount),
-			description:
-				establishedCount > 0 ? 'Established из текущей выборки' : 'нет установленных сессий',
-			icon: CheckCircle2,
-			accent: statAccents[1],
-			badge: establishedCount > 0 ? 'Established' : 'нет сессий',
-			badgeClass: establishedCount > 0 ? 'border-success/30 bg-success/15 text-success' : undefined
-		},
-		{
-			id: 'speakers',
-			label: 'Спикеры',
-			value: initialLoading ? '—' : String(speakers.length),
-			description: 'BIRD-агенты на нодах',
-			icon: Server,
-			accent: statAccents[2],
-			badge: 'agents'
-		}
-	]);
+	let autoRefresh = $state(false);
+	let detailSpeaker = $state<SpeakerRow | null>(null);
+	let detailOpen = $state(false);
 
 	const refreshing = $derived(peersLoading || speakersLoading);
 
@@ -112,7 +68,7 @@
 	async function loadSpeakers() {
 		speakersLoading = true;
 		try {
-			const sr = await apiJSON<SpeakersResponse>('/v1/speakers?limit=200');
+			const sr = await apiJSON<SpeakersResponse>('/v1/speakers?limit=200&live=1');
 			speakers = sr.items;
 		} catch (e) {
 			loadError = e instanceof Error ? e.message : String(e);
@@ -123,10 +79,18 @@
 		}
 	}
 
+	async function loadBirdStatus() {
+		try {
+			birdStatus = await apiJSON<BirdStatus>('/v1/bird/status');
+		} catch {
+			birdStatus = null;
+		}
+	}
+
 	async function load() {
 		loadError = null;
 		try {
-			await Promise.all([loadPeers(), loadSpeakers()]);
+			await Promise.all([loadPeers(), loadSpeakers(), loadBirdStatus()]);
 			lastUpdated = new Date();
 		} catch {
 			// errors handled in loaders
@@ -153,6 +117,16 @@
 		}
 	}
 
+	function openSpeakerDetail(speaker: SpeakerRow) {
+		detailSpeaker = speaker;
+		detailOpen = true;
+	}
+
+	function handleApplyFromDetail(_speaker: SpeakerRow) {
+		detailOpen = false;
+		activeTab = 'speakers';
+	}
+
 	onMount(() => {
 		activeTab = parseNetworkTab(page.url.searchParams.get('tab'));
 		tabSyncReady = true;
@@ -162,7 +136,7 @@
 	function syncTabToUrl(tab: NetworkTab) {
 		if (!tabSyncReady) return;
 		const url = new URL(page.url);
-		if (tab === 'peers') url.searchParams.delete('tab');
+		if (tab === 'overview') url.searchParams.delete('tab');
 		else url.searchParams.set('tab', tab);
 		const next = `${url.pathname}${url.search}${url.hash}`;
 		if (next !== `${page.url.pathname}${page.url.search}${page.url.hash}`) {
@@ -174,18 +148,38 @@
 		if (!tabSyncReady) return;
 		syncTabToUrl(activeTab);
 	});
+
+	$effect(() => {
+		if (!autoRefresh) return;
+		const id = setInterval(() => {
+			void load();
+		}, NETWORK_AUTO_REFRESH_MS);
+		return () => clearInterval(id);
+	});
+
+	$effect(() => {
+		if (detailSpeaker) {
+			const updated = speakers.find((s) => s.id === detailSpeaker!.id);
+			if (updated) detailSpeaker = updated;
+		}
+	});
 </script>
 
 <div class="flex flex-col gap-6">
 	<PageHeader
 		title="Сеть"
 		description={lastUpdated
-			? `BGP-пиры и спикеры (BIRD-агенты). Обновлено: ${lastUpdated.toLocaleTimeString('ru-RU')}`
-			: 'BGP-пиры и спикеры (BIRD-агенты).'}
+			? `BGP-топология CP и нод. Обновлено: ${lastUpdated.toLocaleTimeString('ru-RU')}`
+			: 'BGP-пиры, спикеры и live-метрики нод.'}
 		icon={NetworkIcon}
 		iconClass="bg-chart-3/15 text-chart-3"
 	>
 		{#snippet actions()}
+			<Button variant="ghost" size="sm" href={resolve('/')}>
+				<LayoutDashboard class="size-3.5" />
+				Обзор
+			</Button>
+			<NetworkAutoRefreshToggle bind:enabled={autoRefresh} disabled={refreshing} />
 			<Button variant="outline" size="sm" onclick={load} disabled={refreshing}>
 				<RefreshCw class={refreshing ? 'animate-spin' : ''} />
 				Обновить
@@ -197,26 +191,30 @@
 		<Info class="text-info" />
 		<AlertTitle>О сетевой конфигурации</AlertTitle>
 		<AlertDescription>
-			Пиры привязаны к спикерам (BIRD-агентам). Apply запускает применение ревизии на ноде. Полный
-			список ревизий и задач — на странице
+			Вкладка «Обзор» — live-статус agent и BGP на CP и репликах. Apply и ревизии — на
 			<Button variant="link" class="h-auto p-0" href={resolve('/operations')}>Операции</Button>.
 		</AlertDescription>
 	</Alert>
 
-	<KpiMetricsGrid
-		cards={kpiCards}
-		loading={initialLoading}
-		skeletonCount={3}
-		class="sm:grid-cols-3"
-	/>
-
 	<Tabs bind:value={activeTab}>
 		<TabsList>
+			<TabsTrigger value="overview">Обзор</TabsTrigger>
 			<TabsTrigger value="peers">Пиры</TabsTrigger>
 			<TabsTrigger value="speakers">Спикеры</TabsTrigger>
 			<TabsTrigger value="control-plane">Control plane</TabsTrigger>
 		</TabsList>
 
+		<TabsContent value="overview" class="mt-4 min-w-0">
+			<NetworkOverviewTab
+				{peers}
+				{speakers}
+				bird={birdStatus}
+				loading={refreshing}
+				{initialLoading}
+				onSpeakerSelect={openSpeakerDetail}
+			/>
+		</TabsContent>
+
 		<TabsContent value="peers" class="mt-4">
 			<NetworkPeersCard
 				items={peers}
@@ -235,6 +233,7 @@
 				{initialLoading}
 				error={loadError}
 				onRefresh={refreshSpeakers}
+				onSpeakerSelect={openSpeakerDetail}
 			/>
 		</TabsContent>
 
@@ -243,3 +242,10 @@
 		</TabsContent>
 	</Tabs>
 </div>
+
+<NetworkSpeakerDetailSheet
+	speaker={detailSpeaker}
+	{peers}
+	bind:open={detailOpen}
+	onApply={handleApplyFromDetail}
+/>