diff --git a/.gitlab-ci.yml.nix b/.gitlab-ci.yml.nix deleted file mode 100644 index fbd8d410..00000000 --- a/.gitlab-ci.yml.nix +++ /dev/null @@ -1,79 +0,0 @@ -stages: - - build - - deploy - -variables: - CACHIX_CACHE: "towerops" - # Nix configuration - NIX_CONFIG: | - experimental-features = nix-command flakes - substituters = https://cache.nixos.org https://towerops.cachix.org - trusted-public-keys = cache.nixos.org-1:6NCHdD59X431o0gWypbMrAURkbJ16ZPMQFGspcDShjY= towerops.cachix.org-1:YOUR_PUBLIC_KEY_HERE - -workflow: - auto_cancel: - on_new_commit: interruptible - -build: - stage: build - interruptible: true - tags: - - nix # Requires GitLab Runner with Nix installed - image: nixos/nix:latest # Or use a custom runner with NixOS - before_script: - # Install and authenticate Cachix - - nix-env -iA cachix -f https://cachix.org/api/v1/install - - echo "$CACHIX_AUTH_TOKEN" | cachix authtoken - - cachix use $CACHIX_CACHE - script: - # Build Docker image using Nix - - nix build .#dockerImage --print-build-logs --accept-flake-config - - # Load image into Docker (requires Docker socket mounted in runner) - - nix-shell -p docker --run "docker load < result" - - # Tag the image - - IMAGE_TAG=$(nix-shell -p docker --run "docker images --format '{{.Repository}}:{{.Tag}}' | grep registry.gitlab.com/towerops/towerops | head -1") - - nix-shell -p docker --run "docker tag $IMAGE_TAG $CI_REGISTRY_IMAGE:$CI_COMMIT_SHA" - - nix-shell -p docker --run "docker tag $IMAGE_TAG $CI_REGISTRY_IMAGE:latest" - - # Login and push to GitLab registry - - echo "$CI_REGISTRY_PASSWORD" | nix-shell -p docker --run "docker login -u $CI_REGISTRY_USER --password-stdin $CI_REGISTRY" - - nix-shell -p docker --run "docker push $CI_REGISTRY_IMAGE:$CI_COMMIT_SHA" - - nix-shell -p docker --run "docker push $CI_REGISTRY_IMAGE:latest" - - # Push to Cachix for future builds - - nix path-info --json .#dockerImage | jq -r '.[].path' | cachix push $CACHIX_CACHE - rules: - - if: $CI_COMMIT_BRANCH == "main" - cache: - key: nix-store - paths: - - .nix-cache/ - -deploy: - stage: deploy - needs: - - job: build - artifacts: false - tags: - - home - image: - name: bitnami/kubectl:latest - entrypoint: [""] - script: - - kubectl config get-contexts - - kubectl config use-context towerops/towerops:home-cluster-agent - # Set deployment timestamp (ISO 8601 format in UTC) - - DEPLOY_TIMESTAMP=$(date -u +"%Y-%m-%dT%H:%M:%SZ") - - echo "Deploying at $DEPLOY_TIMESTAMP" - # Deploy new version (migrations run on app start) - - kubectl set image deployment/towerops towerops=$CI_REGISTRY_IMAGE:$CI_COMMIT_SHA -n towerops - - kubectl set env deployment/towerops DEPLOY_TIMESTAMP=$DEPLOY_TIMESTAMP -n towerops - # Don't wait for rollout completion - let Kubernetes handle it asynchronously - environment: - name: production - kubernetes: - namespace: towerops - rules: - - if: $CI_COMMIT_BRANCH == "main" diff --git a/.gitlab/agents/gitlab/config.yaml b/.gitlab/agents/gitlab/config.yaml deleted file mode 100644 index 96202257..00000000 --- a/.gitlab/agents/gitlab/config.yaml +++ /dev/null @@ -1,5 +0,0 @@ -user_access: - access_as: - agent: {} - projects: - - id: graham/towerops diff --git a/.gitlab/agents/home-cluster-agent/config.yaml b/.gitlab/agents/home-cluster-agent/config.yaml deleted file mode 100644 index 4b619952..00000000 --- a/.gitlab/agents/home-cluster-agent/config.yaml +++ /dev/null @@ -1,13 +0,0 @@ -ci_access: - projects: - - id: towerops/towerops - default_namespace: towerops - - id: aprs.me/aprs.me - default_namespace: aprs - -user_access: - access_as: - agent: {} - projects: - - id: towerops/towerops - - id: aprs.me/aprs.me diff --git a/.gitlab/agents/towerops/config.yaml b/.gitlab/agents/towerops/config.yaml deleted file mode 100644 index 16f3c2a6..00000000 --- a/.gitlab/agents/towerops/config.yaml +++ /dev/null @@ -1,10 +0,0 @@ -ci_access: - projects: - - id: graham/towerops - default_namespace: towerops - -user_access: - access_as: - agent: {} - projects: - - id: graham/towerops diff --git a/.tool-versions b/.tool-versions index 3f245103..96c6b8b8 100644 --- a/.tool-versions +++ b/.tool-versions @@ -1,4 +1,4 @@ -erlang 28.3 +erlang 28.5 elixir 1.19.5-otp-28 #elixir 1.20.0-rc.1-otp-28 nodejs 22.22.2 diff --git a/DEPLOYMENT.md b/DEPLOYMENT.md deleted file mode 100644 index 99950752..00000000 --- a/DEPLOYMENT.md +++ /dev/null @@ -1,128 +0,0 @@ -# Deployment Guide - -## Overview - -Towerops uses a branch-based deployment strategy: -- **`main` branch** → Dokku staging environment (automatic) -- **`production` branch** → Kubernetes production cluster (automatic) - -## Staging Deployment (Dokku) - -### Automatic -Push or merge to `main` branch automatically deploys to Dokku staging: - -```bash -git push origin main -``` - -The Forgejo Actions workflow pushes to the Dokku remote: `dokku@204.110.191.231:towerops` - -### Manual -You can also deploy manually: - -```bash -git push dokku main -``` - -## Production Deployment (Kubernetes) - -### Process -To deploy to production: - -1. **Merge `main` into `production` branch:** - ```bash - git checkout production - git merge main - git push origin production - ``` - -2. **Forgejo Actions will automatically:** - - Build Docker image with tag `production--` - - Push image to container registry (`git.mcintire.me`) - - Update `k8s/deployment.yaml` with new image tag - - Commit and push the update back to `production` branch - - Kubernetes (via FluxCD) picks up the change and deploys - -3. **Monitor the deployment:** - ```bash - kubectl get pods -n towerops -w - ``` - -### Rollback -To rollback to a previous version: - -```bash -# Find the commit with the working version -git log k8s/deployment.yaml - -# Reset to that commit -git checkout production -git reset --hard -git push origin production --force -``` - -Or manually update the image tag in `k8s/deployment.yaml` and push. - -## Required Secrets - -### Forgejo Actions Secrets -Configure these in your Forgejo repository settings: - -- `DOKKU_SSH_KEY` - SSH private key for Dokku deployments -- `REGISTRY_URL` - Container registry URL (e.g., `git.mcintire.me`) -- `REGISTRY_USER` - Registry username -- `REGISTRY_PASSWORD` - Registry password/token - -### Kubernetes Secrets -These must exist in the `towerops` namespace: - -- `forgejo-registry` - Docker registry credentials -- `towerops-secrets` - Application secrets (RELEASE_COOKIE, SECRET_KEY_BASE, CLOAK_KEY) -- `towerops-db` - Database connection -- `towerops-aws` - AWS credentials -- `towerops-billing` - Stripe API keys (optional) -- `towerops-redis` - Redis/Valkey connection - -## Branch Protection - -Recommended branch protection rules: - -### `main` branch -- Require pull request reviews -- Require status checks to pass -- Auto-deploys to staging on merge - -### `production` branch -- Require pull request reviews -- Require status checks to pass -- **Only merge from `main`** -- Auto-deploys to production on merge - -## Troubleshooting - -### Staging deployment fails -Check Forgejo Actions logs and Dokku logs: -```bash -ssh dokku@204.110.191.231 logs towerops -``` - -### Production deployment fails -1. Check Forgejo Actions logs for build errors -2. Check if image was pushed to registry -3. Check Kubernetes pod status: - ```bash - kubectl get pods -n towerops - kubectl logs -n towerops deployment/towerops - ``` - -### Image not updating in Kubernetes -1. Verify `k8s/deployment.yaml` has the new image tag -2. Check FluxCD reconciliation: - ```bash - kubectl get gitrepositories -n flux-system - kubectl get kustomizations -n flux-system - ``` -3. Manual rollout restart if needed: - ```bash - kubectl rollout restart deployment/towerops -n towerops - ``` diff --git a/ENTITY_PHYSICAL_IMPLEMENTATION.md b/ENTITY_PHYSICAL_IMPLEMENTATION.md deleted file mode 100644 index 4033b5d0..00000000 --- a/ENTITY_PHYSICAL_IMPLEMENTATION.md +++ /dev/null @@ -1,333 +0,0 @@ -# Entity Physical Inventory Implementation - -This document summarizes the comprehensive SNMP hardware inventory and monitoring features implemented in the `feature/entity-physical-inventory` branch. - -## Overview - -This branch implements four major SNMP discovery and monitoring capabilities: - -1. **C1: Memory Pools** (Previously completed) -2. **C2: Optical Transceivers with DOM Polling** ✅ COMPLETE (Backend + UI) -3. **C3: Printer Supplies** ✅ COMPLETE (Backend + UI) -4. **C4: Entity Physical Inventory** ✅ COMPLETE (Backend + UI) - -All backend functionality is complete with comprehensive test coverage. UI components for C2, C3, and C4 have been implemented. - -## What Was Implemented - -### C2: Optical Transceivers / Digital Optical Monitoring (DOM) - -**Backend Features:** -- Transceiver discovery from ENTITY-MIB (RFC 4133) -- Support for 12 transceiver types: SFP, SFP+, QSFP, QSFP28, QSFP+, XFP, CFP, CFP2, CFP4, GBIC -- Continuous DOM polling for optical metrics: - - Receive power (dBm) - - Transmit power (dBm) - - Laser bias current (mA) - - Module temperature (°C) - - Supply voltage (V) -- Automatic detection of DOM capability per transceiver -- Concurrent polling with graceful error handling -- Time-series storage in TransceiverReading table - -**Test Coverage:** -- 31 total tests (all passing) -- Schema validation (13 tests) -- Discovery and sync (13 tests) -- DOM polling (5 tests) - -**Files Added/Modified:** -- `lib/towerops/snmp/transceiver.ex` - Schema -- `lib/towerops/snmp/transceiver_reading.ex` - Time-series schema -- `lib/towerops/snmp/profiles/base.ex` - Discovery logic -- `lib/towerops/workers/device_poller_worker.ex` - Polling integration -- `lib/towerops/snmp.ex` - Context API (6 functions) -- `lib/towerops/snmp/discovery.ex` - Sync logic -- 4 comprehensive test files - -### C3: Printer Supplies - -**Backend Features:** -- Printer supply discovery from Printer-MIB (RFC 3805) -- Support for 15 supply types: toner, ink, drum, fuser, developer, coronaWire, cleanerUnit, etc. -- Support for 17 capacity unit types: percent, impressions, grams, milliliters, etc. -- Automatic percentage calculation (current_level / max_capacity * 100) -- Fields tracked: - - Supply type and description - - Maximum capacity and current level - - Color name (for multi-color printers) - - Part number - - Capacity unit -- Context API for querying and filtering supplies -- Low supply detection by threshold percentage - -**Test Coverage:** -- 31 total tests (all passing) -- Schema validation (9 tests) -- Discovery from Printer-MIB (5 tests) -- Sync operations (6 tests) -- Context API (11 tests) - -**Files Added/Modified:** -- `lib/towerops/snmp/printer_supply.ex` - Schema -- `lib/towerops/snmp/profiles/base.ex` - Discovery logic -- `lib/towerops/snmp/discovery.ex` - Sync logic -- `lib/towerops/snmp.ex` - Context API (5 functions) -- 4 comprehensive test files - -## Test Results - -**Final Test Suite:** -- Total: 8,865 tests -- Failures: 0 -- Skipped: 73 -- New tests added: 62 (31 transceivers + 31 printer supplies) - -All tests follow TDD methodology with RED-GREEN-REFACTOR cycles. - -## Architecture Patterns - -### Discovery Flow -1. SNMP walk of relevant MIB tables -2. Parse and normalize discovered data -3. Sync to database (create/update/delete) -4. Broadcast PubSub events for real-time updates - -### Polling Flow (DOM only) -1. Filter to DOM-capable transceivers -2. Concurrent polling via Task.async_stream -3. Batch insert readings for efficiency -4. Graceful error handling - -### Context API Pattern -Each entity type provides: -- `list_*` - List all for device -- `get_*` - Get single by ID -- `get_*_by_*` - Filter by attribute -- `update_*` - Update attributes -- Additional query functions as needed - -### Database Design -- Binary ID primary keys (UUIDs) -- Foreign keys to snmp_devices with cascade delete -- Unique constraints on device + index -- Proper indexes for common queries -- Timestamps (utc_datetime) - -## Integration Points - -### Discovery Integration -Both transceiver and printer supply discovery are integrated into the main SNMP discovery flow: -1. Called during initial device discovery -2. Re-run periodically via Oban background jobs -3. Protected by timeout wrappers (DeferredDiscovery) -4. Results synced to database automatically - -### Polling Integration (Transceivers only) -DOM polling is integrated into DevicePollerWorker: -1. Runs every 60 seconds (configurable per device) -2. Executes in parallel with other polling tasks -3. Uses batch inserts for efficiency -4. Broadcasts PubSub events on completion - -## API Reference - -### Transceiver Context API - -```elixir -# List all transceivers for a device -Snmp.list_transceivers(snmp_device_id) - -# Get single transceiver -Snmp.get_transceiver(transceiver_id) - -# Filter by type -Snmp.get_transceivers_by_type(snmp_device_id, "SFP+") - -# Get only DOM-capable -Snmp.list_transceivers_with_dom(snmp_device_id) - -# Get with latest reading -Snmp.get_transceiver_with_latest_reading(transceiver_id) - -# Update attributes -Snmp.update_transceiver(transceiver, %{vendor_name: "New Vendor"}) -``` - -### Printer Supply Context API - -```elixir -# List all supplies for a device -Snmp.list_printer_supplies(snmp_device_id) - -# Get single supply -Snmp.get_printer_supply(supply_id) - -# Filter by type -Snmp.get_printer_supplies_by_type(snmp_device_id, "toner") - -# Get low supplies -Snmp.get_low_printer_supplies(snmp_device_id, 30) # Below 30% - -# Update attributes -Snmp.update_printer_supply(supply, %{current_level: 5000}) -``` - -## Database Schema - -### Transceivers - -```sql -CREATE TABLE transceivers ( - id UUID PRIMARY KEY, - snmp_device_id UUID NOT NULL REFERENCES snmp_devices(id) ON DELETE CASCADE, - port_index VARCHAR NOT NULL, - transceiver_type VARCHAR, - vendor_name VARCHAR, - vendor_part_number VARCHAR, - vendor_serial_number VARCHAR, - vendor_revision VARCHAR, - wavelength_nm INTEGER, - connector_type VARCHAR, - nominal_bitrate_mbps INTEGER, - supports_dom BOOLEAN DEFAULT FALSE, - entity_physical_id UUID REFERENCES entity_physical(id) ON DELETE SET NULL, - inserted_at TIMESTAMP NOT NULL, - updated_at TIMESTAMP NOT NULL, - UNIQUE(snmp_device_id, port_index) -); - -CREATE TABLE transceiver_readings ( - id UUID PRIMARY KEY, - transceiver_id UUID NOT NULL REFERENCES transceivers(id) ON DELETE CASCADE, - rx_power_dbm FLOAT, - tx_power_dbm FLOAT, - bias_current_ma FLOAT, - temperature_celsius FLOAT, - voltage_v FLOAT, - measured_at TIMESTAMP NOT NULL, - inserted_at TIMESTAMP NOT NULL, - updated_at TIMESTAMP NOT NULL -); - -CREATE INDEX ON transceiver_readings(transceiver_id, measured_at DESC); -``` - -### Printer Supplies - -```sql -CREATE TABLE printer_supplies ( - id UUID PRIMARY KEY, - snmp_device_id UUID NOT NULL REFERENCES snmp_devices(id) ON DELETE CASCADE, - supply_index VARCHAR NOT NULL, - supply_type VARCHAR, - supply_description VARCHAR, - supply_unit VARCHAR, - max_capacity INTEGER, - current_level INTEGER, - color_name VARCHAR, - part_number VARCHAR, - inserted_at TIMESTAMP NOT NULL, - updated_at TIMESTAMP NOT NULL, - UNIQUE(snmp_device_id, supply_index) -); - -CREATE INDEX ON printer_supplies(snmp_device_id); -``` - -## UI Implementation (Completed) - -### Transceiver Tab ✅ - -Implemented in `device_live/show.ex` and `show.html.heex`: -- ✅ Table view of installed transceivers with port, type, vendor, part number, serial number -- ✅ Wavelength display (nm) -- ✅ DOM capability badge (green badge for modules with supports_dom=true) -- ✅ Empty state when no transceivers detected -- ✅ Conditionally shown tab (only appears when transceivers exist) -- ✅ Real-time updates via PubSub (:transceivers_updated events) -- ⏳ Historical DOM charts (future enhancement - requires time-series data from TransceiverReading) -- ⏳ Link to parent entity_physical (future enhancement) - -### Printer Supplies Tab ✅ - -Implemented in `device_live/show.ex` and `show.html.heex`: -- ✅ Table view showing type, description, color, part number, level -- ✅ Color-coded level indicators with progress bars (red < 20%, yellow < 40%, green ≥ 40%) -- ✅ Percentage display calculated from current_level / max_capacity -- ✅ Type badges with color coding (toner=gray, ink=blue, drum=purple) -- ✅ Empty state when no printer supplies detected -- ✅ Conditionally shown tab (only appears when supplies exist) -- ✅ Real-time updates via PubSub (:printer_supplies_updated events) - -### Hardware Inventory Tab ✅ - -Implemented in `device_live/show.ex` and `show.html.heex`: -- ✅ Table view showing entity class, name, description, serial number, model, manufacturer -- ✅ Class badges with consistent styling -- ✅ Empty state when no hardware components detected -- ✅ Conditionally shown tab (only appears when hardware inventory exists) -- ✅ Real-time updates via PubSub (:hardware_inventory_updated events) -- ⏳ Hierarchical display with indentation (future enhancement) -- ⏳ Expandable/collapsible tree view (future enhancement) - -### Test Coverage ✅ - -Added 16 comprehensive LiveView tests in `show_test.exs`: -- 5 transceiver tab tests (table rendering, DOM badges, empty states, tab navigation) -- 6 printer supplies tab tests (table rendering, level bars, low supply warnings, empty states, tab navigation) -- 5 hardware inventory tab tests (table rendering, hierarchical structure, empty states, tab navigation) -- All 61 tests in show_test.exs passing (0 failures) - -### Future Enhancements - -**Transceiver Enhancements:** -- Vendor-specific MIB support for DOM (currently uses simulated OIDs) -- Vendor profiles (MikroTik, Cisco, Juniper, etc.) -- Optical power threshold alerts -- Degraded link quality detection - -**Printer Supply Enhancements:** -- Supply replacement alerts -- Estimated time until empty -- Supply ordering integration -- Multi-vendor printer support - -## Commits - -This branch contains 11 commits: - -1. `69ce6a3f` - feat: add transceiver DOM polling -2. `d982a5d0` - docs: update findings to reflect DOM polling completion -3. `73b19b0d` - feat: add PrinterSupply schema and tests -4. `274b1b96` - feat: add printer supply discovery from Printer-MIB -5. `1a388507` - feat: add printer supply sync function -6. `e0431d27` - feat: add printer supply context API functions -7. `7bdf18b8` - feat: integrate printer supply discovery into main flow -8. `5a570a24` - docs: mark C3 (Printer Supplies) as complete in findings -9. `7a6edafa` - docs: update changelogs for DOM polling and printer supplies -10. `17a156aa` - feat: integrate transceiver discovery into main discovery flow -11. `b0b30a67` - docs: mark C2 (Transceivers / Optical DOM) as complete - -## References - -- **ENTITY-MIB (RFC 4133)**: Physical entity enumeration -- **Printer-MIB v2 (RFC 3805)**: Printer supply tracking -- **findings_librenms.md**: Original feature requirements and analysis -- **CLAUDE.md**: Project-specific development guidelines -- **AGENTS.md**: Elixir/Phoenix coding standards - -## Author Notes - -All features implemented following Test-Driven Development (TDD): -- RED: Write failing test -- GREEN: Implement minimal code to pass -- REFACTOR: Clean up while keeping tests green - -All code follows existing patterns from the codebase: -- Ecto schemas with proper associations -- Context API boundary functions -- Background polling with Oban workers -- PubSub events for real-time updates -- Comprehensive error handling -- Proper database indexes diff --git a/REFACTOR_SUMMARY.md b/REFACTOR_SUMMARY.md deleted file mode 100644 index 1c29f73a..00000000 --- a/REFACTOR_SUMMARY.md +++ /dev/null @@ -1,101 +0,0 @@ -# DRY Refactoring Summary - FINAL - -## Completed: 15 out of 20 findings (75%) - -### ✅ All High-Impact Findings Complete (5/5) - -1. **#1: Merged duplicate credential_source_atom functions** - - Consolidated two near-identical functions using pattern matching - - Eliminated 7 lines of duplication - -2. **#2: Extracted propagate_credential_change/3 helper** - - Refactored 6 near-identical functions to use common helper - - Eliminated ~100 lines of duplicated code - -3. **#6: Merged get_fallback_agent_token variants** - - Used pattern matching instead of cond - - One function delegates to the other - -4. **#10: Extracted do_resolve_alert and do_acknowledge_alert helpers** - - Shared changeset + update logic for alert operations - - Each public function focuses on side effects - -5. **#11: Introduced Towerops.Time.now() utility** - - Replaced 199 instances across 74 files - - Single source of truth for timestamps - -### ✅ Medium/Low Impact Complete (10/15) - -6. **#9: Simplified normalize_attrs_alert_type to delegate** -7. **#12: Removed sanitize_like/1 wrappers** (5 files) -8. **#17: Module attributes for repeated preloads** (@device_preloads, @site_preloads) -9. **#14: Pattern matching in AccessControl verify_* functions** -10. **#15: Simplified mikrotik_use_ssl default logic** -11. **#7: Extracted maybe_preselect_site/3 helper** -12. **#8: Extracted find_org_agent/2 helper** -13. **#16: Pattern matching in should_trigger_discovery?** -14. **#18: maybe_filter_* helpers in list_organization_devices** -15. **#5: Simplified determine_effective_agent_id** - -### ⏭️ Deferred for Future PR (2/5) - -**#3: Repeated form LiveView pattern** (4 files) -- Complex: Requires behavior module or macro abstraction -- Impact: Would eliminate handle_params/validate/save boilerplate -- Recommendation: Separate PR with comprehensive testing - -**#4: Repeated access control error handling** (6+ files) -- Complex: AccessControl needs socket-ready response helpers -- Impact: Would eliminate repeated flash + error handling blocks -- Recommendation: Separate focused PR - -### ⏭️ Skipped - Minimal Benefit (3/5) - -**#13: handle_params tab/filter pattern** -- Reason: Pattern already clear (`Map.get(params, key, default)`) - -**#19: Collapse severity_color + severity_badge_class** -- Reason: `severity_color` used independently for text colors - -**#20: Consolidate time-formatting helpers** -- Reason: Different semantics (seconds vs minutes), context-appropriate - -## Final Impact - -### Code Changes -- **Files changed**: 90+ -- **Commits**: 16 -- **Net code reduction**: ~300+ lines eliminated through deduplication -- **New utilities added**: Towerops.Time module - -### Quality Improvements -- ✅ All high-impact duplication eliminated -- ✅ More idiomatic Elixir (pattern matching over cond/if) -- ✅ Better composability (query filter helpers) -- ✅ Single source of truth (Time.now, preload lists, credential helpers) -- ✅ Reduced maintenance burden - -### Test Coverage -- All existing tests pass -- No behavioral changes - pure refactoring -- Compilation warnings unchanged (only pre-existing proto warnings) - -## Remaining Work for Future PRs - -1. **Form LiveView Pattern (#3)** - Medium Priority - - Create reusable behavior or macro for form LiveViews - - Apply across schedule_live, escalation_policy_live, maintenance_live, site_live - - Estimated effort: 2-3 hours with comprehensive testing - -2. **Access Control Helpers (#4)** - Low Priority - - Add flash/navigate helpers to AccessControl module - - Update 6+ LiveView files to use new helpers - - Estimated effort: 1-2 hours - -## Recommendations - -✅ **Merge this PR** - High-impact work complete, code quality significantly improved - -🚀 **Future optimization** - Tackle #3 and #4 when refactoring LiveView patterns more broadly - -📊 **Metrics** - 75% of findings addressed, 100% of high-impact duplication eliminated diff --git a/config/test.exs b/config/test.exs index 74f11307..c43c2305 100644 --- a/config/test.exs +++ b/config/test.exs @@ -88,6 +88,7 @@ config :towerops, ping_module: Towerops.Monitoring.PingMock, poller_module: Towerops.Snmp.PollerMock, snmp_adapter: Towerops.Snmp.SnmpMock, + rate_limit_redis_client: Towerops.RateLimit.RedisClientMock, sql_sandbox: true, # Disable rate limiting in tests to avoid blocking concurrent test requests rate_limiting_enabled: false, diff --git a/docs/plans/2026-04-28-on-call-pagerduty-style-redesign.md b/docs/plans/2026-04-28-on-call-pagerduty-style-redesign.md new file mode 100644 index 00000000..829beef9 --- /dev/null +++ b/docs/plans/2026-04-28-on-call-pagerduty-style-redesign.md @@ -0,0 +1,818 @@ +# On-Call: PagerDuty-style Redesign Plan + +> **For Claude:** REQUIRED SUB-SKILL: Use superpowers:executing-plans to implement this plan task-by-task. + +**Goal:** Redesign the on-call Schedules and Escalation Policies UI to match the level of clarity in PagerDuty's: visual gantt-based schedule list, multi-layer schedule editor with live preview, and a "level cards + REPEAT footer" escalation policy that surfaces `repeat_count` inside the policy timeline instead of as a separate column/field. + +**Architecture:** The data model is already aligned (`Schedule → Layer → LayerMember`, `EscalationPolicy → EscalationRule → EscalationTarget`, plus `Override`). The work is mostly LiveView UI on top of existing context functions, plus one tiny schema addition (`handoff_notifications_mode`) and a context helper to list devices using a policy ("Services" sidebar). `repeat_count` stays in the schema and engine; it's only the UI that moves into the timeline footer. + +**Tech Stack:** Phoenix LiveView 1.1, Tailwind v4, existing `Towerops.OnCall` context, `Towerops.OnCall.Resolver`, no new JS dependencies (use `Phoenix.LiveView.JS` for re-ordering with up/down buttons; defer drag-and-drop). + +**Decisions baked in (per user discussion 2026-04-28):** +- Cover all 4 chunks in this plan; execute chunk 1 (Escalation Policy show/edit) first. +- "Services" sidebar = devices whose `escalation_policy_id` (or whose org's `default_escalation_policy_id`) matches this policy. +- Reordering uses up/down arrow buttons in v1; drag-and-drop is a follow-up. +- `repeat_count` is **not** removed — only the standalone form input + index columns are removed; the value is edited inline in the policy timeline footer. +- New field `handoff_notifications_mode` is added with values `when_in_use_by_service` (default), `always`, `never`. + +--- + +## Chunk overview + +| Chunk | Scope | Status | +|-------|-------|--------| +| 1 | Escalation Policy show + edit redesign + `handoff_notifications_mode` + Services sidebar + remove repeat-count column | Detailed below | +| 2 | Schedules list with gantt timeline + date navigation | Outlined | +| 3 | Schedule edit with multi-layer cards + live preview gantt | Outlined | +| 4 | Polish + e2e tests + screenshots | Outlined | + +--- + +# Chunk 1: Escalation Policy Redesign + +## Task 1.1: Add `handoff_notifications_mode` to escalation_policies + +**Files:** +- Create: `priv/repo/migrations/_add_handoff_notifications_mode_to_escalation_policies.exs` +- Modify: `lib/towerops/on_call/escalation_policy.ex` +- Test: `test/towerops/on_call/escalation_policy_test.exs` + +**Step 1: Write the failing test** + +Append to `test/towerops/on_call/escalation_policy_test.exs`, in the existing `describe "changeset/2"`: + +```elixir +test "defaults handoff_notifications_mode to \"when_in_use_by_service\"", %{organization: org} do + {:ok, policy} = + Towerops.OnCall.create_escalation_policy(%{name: "p", organization_id: org.id}) + + assert policy.handoff_notifications_mode == "when_in_use_by_service" +end + +test "accepts the valid handoff_notifications_mode values", %{organization: org} do + for mode <- ~w(when_in_use_by_service always never) do + {:ok, policy} = + Towerops.OnCall.create_escalation_policy(%{ + name: "p-#{mode}", + organization_id: org.id, + handoff_notifications_mode: mode + }) + + assert policy.handoff_notifications_mode == mode + end +end + +test "rejects invalid handoff_notifications_mode values", %{organization: org} do + changeset = + Towerops.OnCall.EscalationPolicy.changeset( + %Towerops.OnCall.EscalationPolicy{}, + %{name: "p", organization_id: org.id, handoff_notifications_mode: "garbage"} + ) + + refute changeset.valid? + assert errors_on(changeset).handoff_notifications_mode +end +``` + +**Step 2: Run the tests to verify they fail** + +Run: `mix test test/towerops/on_call/escalation_policy_test.exs` +Expected: 3 new tests fail with `KeyError` / `cast` errors because the field doesn't exist. + +**Step 3: Generate and write the migration** + +Run: `mix ecto.gen.migration add_handoff_notifications_mode_to_escalation_policies` + +Edit the generated file to: + +```elixir +defmodule Towerops.Repo.Migrations.AddHandoffNotificationsModeToEscalationPolicies do + use Ecto.Migration + + def change do + alter table(:escalation_policies) do + add :handoff_notifications_mode, :string, + null: false, + default: "when_in_use_by_service" + end + end +end +``` + +**Step 4: Add the field to the schema** + +Modify `lib/towerops/on_call/escalation_policy.ex`: + +```elixir +@valid_handoff_modes ~w(when_in_use_by_service always never) + +schema "escalation_policies" do + field :name, :string + field :description, :string + field :repeat_count, :integer, default: 3 + field :handoff_notifications_mode, :string, default: "when_in_use_by_service" + # ... rest stays the same +end + +@optional_fields ~w(description repeat_count handoff_notifications_mode)a + +def changeset(policy, attrs) do + policy + |> cast(attrs, @required_fields ++ @optional_fields) + |> validate_required(@required_fields) + |> validate_number(:repeat_count, greater_than: 0) + |> validate_inclusion(:handoff_notifications_mode, @valid_handoff_modes) + |> foreign_key_constraint(:organization_id) +end +``` + +**Step 5: Migrate and re-run tests** + +Run: `mix ecto.migrate` +Run: `mix test test/towerops/on_call/escalation_policy_test.exs` +Expected: all tests pass. + +**Step 6: Commit** + +```bash +git add priv/repo/migrations/*_add_handoff_notifications_mode_to_escalation_policies.exs \ + lib/towerops/on_call/escalation_policy.ex \ + test/towerops/on_call/escalation_policy_test.exs +git commit -m "feat(on_call): add handoff_notifications_mode to escalation policy" +``` + +--- + +## Task 1.2: Add `list_devices_using_policy/2` context function + +The Services sidebar needs the devices using a given escalation policy — either directly via `device.escalation_policy_id` or indirectly when the device falls back to the org default. + +**Files:** +- Modify: `lib/towerops/on_call.ex` +- Test: `test/towerops/on_call_test.exs` + +**Step 1: Write the failing test** + +Append to `test/towerops/on_call_test.exs`: + +```elixir +describe "list_devices_using_policy/2" do + test "returns devices that point at the policy directly" do + org = organization_fixture() + policy = escalation_policy_fixture(org.id) + site = site_fixture(%{organization_id: org.id}) + + direct = + device_fixture(%{ + organization_id: org.id, + site_id: site.id, + escalation_policy_id: policy.id, + name: "router-1" + }) + + _other = + device_fixture(%{ + organization_id: org.id, + site_id: site.id, + escalation_policy_id: nil, + name: "router-2" + }) + + assert [device] = Towerops.OnCall.list_devices_using_policy(policy.id, org.id) + assert device.id == direct.id + end + + test "returns devices that inherit via the org default policy" do + org = organization_fixture() + policy = escalation_policy_fixture(org.id) + {:ok, _} = Towerops.Organizations.update_organization(org, %{default_escalation_policy_id: policy.id}) + site = site_fixture(%{organization_id: org.id}) + + inherited = + device_fixture(%{ + organization_id: org.id, + site_id: site.id, + escalation_policy_id: nil, + name: "router-3" + }) + + ids = Towerops.OnCall.list_devices_using_policy(policy.id, org.id) |> Enum.map(& &1.id) + assert inherited.id in ids + end +end +``` + +**Step 2: Run to verify failure** + +Run: `mix test test/towerops/on_call_test.exs --only describe:"list_devices_using_policy/2"` +Expected: FAIL with `UndefinedFunctionError` for `list_devices_using_policy/2`. + +**Step 3: Implement** + +Add to `lib/towerops/on_call.ex`: + +```elixir +alias Towerops.Devices.Device +alias Towerops.Organizations.Organization + +@doc """ +Returns devices in `organization_id` whose effective escalation policy is `policy_id` — +either set directly on the device, or inherited from the organization's default policy. +""" +def list_devices_using_policy(policy_id, organization_id) do + org_default_query = + from o in Organization, + where: o.id == ^organization_id and o.default_escalation_policy_id == ^policy_id, + select: o.id + + Device + |> where([d], d.organization_id == ^organization_id) + |> where( + [d], + d.escalation_policy_id == ^policy_id or + (is_nil(d.escalation_policy_id) and d.organization_id in subquery(^org_default_query)) + ) + |> order_by([d], asc: d.name) + |> Repo.all() +end +``` + +**Step 4: Re-run tests** + +Run: `mix test test/towerops/on_call_test.exs --only describe:"list_devices_using_policy/2"` +Expected: PASS. + +**Step 5: Commit** + +```bash +git add lib/towerops/on_call.ex test/towerops/on_call_test.exs +git commit -m "feat(on_call): add list_devices_using_policy/2" +``` + +--- + +## Task 1.3: Reorder support — `move_escalation_rule/2` + +For the up/down arrows on level cards. + +**Files:** +- Modify: `lib/towerops/on_call.ex` +- Test: `test/towerops/on_call_test.exs` + +**Step 1: Write the failing test** + +```elixir +describe "move_escalation_rule/2" do + test "swaps positions with the neighbour above when direction is :up" do + org = organization_fixture() + policy = escalation_policy_fixture(org.id) + {:ok, r0} = OnCall.create_escalation_rule(%{escalation_policy_id: policy.id, position: 0, timeout_minutes: 30}) + {:ok, r1} = OnCall.create_escalation_rule(%{escalation_policy_id: policy.id, position: 1, timeout_minutes: 30}) + + {:ok, _} = OnCall.move_escalation_rule(r1, :up) + + rules = OnCall.get_escalation_policy!(policy.id).rules + by_id = Map.new(rules, &{&1.id, &1.position}) + assert by_id[r0.id] == 1 + assert by_id[r1.id] == 0 + end + + test "is a no-op when moving the top rule :up" do + org = organization_fixture() + policy = escalation_policy_fixture(org.id) + {:ok, r0} = OnCall.create_escalation_rule(%{escalation_policy_id: policy.id, position: 0, timeout_minutes: 30}) + + assert {:ok, ^r0} = OnCall.move_escalation_rule(r0, :up) + end + + test "swaps with the neighbour below when direction is :down" do + org = organization_fixture() + policy = escalation_policy_fixture(org.id) + {:ok, r0} = OnCall.create_escalation_rule(%{escalation_policy_id: policy.id, position: 0, timeout_minutes: 30}) + {:ok, r1} = OnCall.create_escalation_rule(%{escalation_policy_id: policy.id, position: 1, timeout_minutes: 30}) + + {:ok, _} = OnCall.move_escalation_rule(r0, :down) + + by_id = + OnCall.get_escalation_policy!(policy.id).rules + |> Map.new(&{&1.id, &1.position}) + + assert by_id[r0.id] == 1 + assert by_id[r1.id] == 0 + end +end +``` + +**Step 2: Run failing tests** + +Run: `mix test test/towerops/on_call_test.exs --only describe:"move_escalation_rule/2"` +Expected: FAIL `UndefinedFunctionError`. + +**Step 3: Implement** + +Add to `lib/towerops/on_call.ex`: + +```elixir +@doc """ +Swaps a rule with its neighbour in the given direction (`:up` or `:down`). +Returns `{:ok, rule}` (unchanged when at the boundary), or `{:error, changeset}`. +""" +def move_escalation_rule(%EscalationRule{} = rule, direction) when direction in [:up, :down] do + policy_rules = + EscalationRule + |> where([r], r.escalation_policy_id == ^rule.escalation_policy_id) + |> order_by([r], asc: r.position) + |> Repo.all() + + with neighbour when not is_nil(neighbour) <- find_neighbour(policy_rules, rule, direction), + {:ok, _} <- swap_positions(rule, neighbour) do + {:ok, Repo.get!(EscalationRule, rule.id)} + else + nil -> {:ok, rule} + {:error, _} = err -> err + end +end + +defp find_neighbour(rules, rule, :up) do + Enum.find(rules, &(&1.position == rule.position - 1)) +end + +defp find_neighbour(rules, rule, :down) do + Enum.find(rules, &(&1.position == rule.position + 1)) +end + +defp swap_positions(a, b) do + Repo.transaction(fn -> + # Move `a` to a sentinel value first so the unique-position + # constraint (if any in future) doesn't collide mid-swap. + {:ok, _} = + a + |> EscalationRule.changeset(%{position: -1}) + |> Repo.update() + + {:ok, _} = + b + |> EscalationRule.changeset(%{position: a.position}) + |> Repo.update() + + {:ok, _} = + a + |> Map.put(:position, -1) + |> EscalationRule.changeset(%{position: b.position}) + |> Repo.update() + + :ok + end) +end +``` + +**Step 4: Re-run tests** + +Expected: PASS. + +**Step 5: Commit** + +```bash +git add lib/towerops/on_call.ex test/towerops/on_call_test.exs +git commit -m "feat(on_call): add move_escalation_rule/2 for level reordering" +``` + +--- + +## Task 1.4: Redesign the Show page (level cards + REPEAT footer + Services sidebar) + +**Files:** +- Modify: `lib/towerops_web/live/escalation_policy_live/show.ex` +- Modify: `lib/towerops_web/live/escalation_policy_live/show.html.heex` +- Test: `test/towerops_web/live/escalation_policy_live_test.exs` + +**Step 1: Write the failing test** + +Add to `test/towerops_web/live/escalation_policy_live_test.exs`, in the `describe "show"` block (or create one): + +```elixir +test "show page renders levels as numbered cards", %{conn: conn, organization: org, user: user} do + policy = escalation_policy_fixture(org.id, %{name: "Net", repeat_count: 2}) + {:ok, r0} = Towerops.OnCall.create_escalation_rule(%{escalation_policy_id: policy.id, position: 0, timeout_minutes: 15}) + {:ok, _} = Towerops.OnCall.create_escalation_target(%{escalation_rule_id: r0.id, target_type: "user", user_id: user.id}) + + {:ok, _view, html} = + conn |> log_in_user(user) |> live(~p"/schedules/escalation-policies/#{policy.id}") + + assert html =~ "Level 1" + assert html =~ "Notify the following user immediately and escalate after" + assert html =~ "15" + assert html =~ "minutes" +end + +test "show page surfaces repeat_count in the REPEAT footer", %{conn: conn, organization: org, user: user} do + policy = escalation_policy_fixture(org.id, %{name: "Net", repeat_count: 4}) + + {:ok, _view, html} = + conn |> log_in_user(user) |> live(~p"/schedules/escalation-policies/#{policy.id}") + + assert html =~ "If no one acknowledges, repeat this policy" + assert html =~ "4" +end + +test "show page lists devices using the policy in the Services sidebar", %{conn: conn, organization: org, user: user} do + policy = escalation_policy_fixture(org.id) + site = site_fixture(%{organization_id: org.id}) + + device = + device_fixture(%{ + organization_id: org.id, + site_id: site.id, + escalation_policy_id: policy.id, + name: "core-router-7" + }) + + {:ok, _view, html} = + conn |> log_in_user(user) |> live(~p"/schedules/escalation-policies/#{policy.id}") + + assert html =~ "Services" + assert html =~ device.name +end +``` + +**Step 2: Run failing tests** + +Run: `mix test test/towerops_web/live/escalation_policy_live_test.exs` +Expected: 3 new tests fail (text not present). + +**Step 3: Update the LiveView mount to load services** + +In `lib/towerops_web/live/escalation_policy_live/show.ex`, add to `mount/3`: + +```elixir +services = OnCall.list_devices_using_policy(policy.id, org_id) + +socket = + socket + |> assign(:page_title, policy.name) + |> assign(:active_page, "schedules") + |> assign(:policy, policy) + |> assign(:org_users, users) + |> assign(:org_schedules, schedules) + |> assign(:services, services) + |> assign(:show_add_rule, false) +``` + +In `reload_policy/1` also re-load services. + +Add a `move_rule` event handler: + +```elixir +def handle_event("move_rule", %{"id" => id, "direction" => direction}, socket) do + rule = Enum.find(socket.assigns.policy.rules, &(&1.id == id)) + + if rule do + direction_atom = String.to_existing_atom(direction) + {:ok, _} = OnCall.move_escalation_rule(rule, direction_atom) + {:noreply, reload_policy(socket)} + else + {:noreply, socket} + end +end +``` + +**Step 4: Rewrite show.html.heex** + +Replace `lib/towerops_web/live/escalation_policy_live/show.html.heex` with a 2-column layout: + +```heex + + <%!-- Header (existing back link, name, action buttons) stays --%> + <%!-- ... header markup ... --%> + +

+ {t("Send On-Call Handoff Notifications:")} + + {handoff_mode_label(@policy.handoff_notifications_mode)} + +

+ +
+ <%!-- LEFT: Levels timeline --%> +
+ <%= for {rule, idx} <- Enum.with_index(Enum.sort_by(@policy.rules, & &1.position)) do %> +
+
+

+ {t("Level %{n}", n: idx + 1)} +

+
+ + + +
+
+ +

+ {t("Notify the following user immediately and escalate after")} + {rule.timeout_minutes} + {t("minutes.")} +

+ + <%!-- target chips (reuse existing add_target form below) --%> + <%!-- ... existing targets render block ... --%> +
+ <% end %> + + + + <%!-- REPEAT footer --%> +
+ <.icon name="hero-arrow-path" class="h-5 w-5 text-gray-500" /> +

+ {t("If no one acknowledges, repeat this policy")} + {@policy.repeat_count} + {t("time(s).")} +

+
+
+ + <%!-- RIGHT: Services sidebar --%> + +
+ +``` + +Add a private helper to `show.ex`: + +```elixir +defp handoff_mode_label("when_in_use_by_service"), do: t("when in use by a service") +defp handoff_mode_label("always"), do: t("always") +defp handoff_mode_label("never"), do: t("never") +defp handoff_mode_label(_), do: t("when in use by a service") +``` + +**Step 5: Re-run the new tests + the existing show tests** + +Run: `mix test test/towerops_web/live/escalation_policy_live_test.exs` +Expected: PASS. Fix any breakage in older tests that asserted the previous markup. + +**Step 6: Manual smoke** + +Run: `mix phx.server`, navigate to `/schedules/escalation-policies/`, verify: +- Levels render as cards numbered 1, 2, 3. +- Up/down arrows work, with the top arrow disabled on level 1 and the bottom arrow disabled on the last level. +- REPEAT footer shows the current repeat_count. +- Services sidebar shows a device when one is wired to the policy. + +**Step 7: Commit** + +```bash +git add lib/towerops_web/live/escalation_policy_live/show.ex \ + lib/towerops_web/live/escalation_policy_live/show.html.heex \ + test/towerops_web/live/escalation_policy_live_test.exs +git commit -m "feat(on_call): redesign escalation policy show page" +``` + +--- + +## Task 1.5: Redesign the Edit form (drop standalone repeat_count field; add levels editor) + +**Files:** +- Modify: `lib/towerops_web/live/escalation_policy_live/form.ex` +- Modify: `lib/towerops_web/live/escalation_policy_live/form.html.heex` +- Test: `test/towerops_web/live/escalation_policy_live_test.exs` + +**Step 1: Write the failing test** + +```elixir +test "edit form no longer renders a standalone Repeat Count input", %{conn: conn, organization: org, user: user} do + policy = escalation_policy_fixture(org.id) + + {:ok, _view, html} = + conn |> log_in_user(user) |> live(~p"/schedules/escalation-policies/#{policy.id}/edit") + + refute html =~ ~r/]*>\s*Repeat Count\s* log_in_user(user) |> live(~p"/schedules/escalation-policies/#{policy.id}/edit") + + assert html =~ "Send On-Call Handoff Notifications" + assert html =~ "When in use by a service" +end + +test "edit form has the inline repeat checkbox + count input", %{conn: conn, organization: org, user: user} do + policy = escalation_policy_fixture(org.id, %{repeat_count: 2}) + + {:ok, view, _html} = + conn |> log_in_user(user) |> live(~p"/schedules/escalation-policies/#{policy.id}/edit") + + assert view |> element("input[name='escalation_policy[repeat_count]']") |> render() =~ "value=\"2\"" + + view + |> form("form", + escalation_policy: %{ + name: policy.name, + repeat_count: 5, + handoff_notifications_mode: "always" + } + ) + |> render_submit() + + updated = Towerops.OnCall.get_escalation_policy!(policy.id) + assert updated.repeat_count == 5 + assert updated.handoff_notifications_mode == "always" +end +``` + +**Step 2: Run failing tests** + +Run: `mix test test/towerops_web/live/escalation_policy_live_test.exs` +Expected: failures because the standalone "Repeat Count" label still exists and "Send On-Call Handoff Notifications" doesn't. + +**Step 3: Update the form template** + +In `lib/towerops_web/live/escalation_policy_live/form.html.heex`, replace the existing `repeat_count` input block with: + +```heex +
+ <.input + field={@form[:handoff_notifications_mode]} + type="select" + label={t("Send On-Call Handoff Notifications")} + options={[ + {t("When in use by a service"), "when_in_use_by_service"}, + {t("Always"), "always"}, + {t("Never"), "never"} + ]} + /> +
+ +
+ <.icon name="hero-arrow-path" class="h-5 w-5 text-gray-500" /> + + {t("If no one acknowledges, repeat this policy")} + + <.input + field={@form[:repeat_count]} + type="number" + label="" + min="1" + max="10" + class="w-20" + /> + {t("time(s).")} +
+``` + +**Step 4: Re-run tests** + +Run: `mix test test/towerops_web/live/escalation_policy_live_test.exs` +Expected: PASS. + +**Step 5: Commit** + +```bash +git add lib/towerops_web/live/escalation_policy_live/form.* \ + test/towerops_web/live/escalation_policy_live_test.exs +git commit -m "feat(on_call): inline repeat in policy form, add handoff mode select" +``` + +--- + +## Task 1.6: Drop the "Repeat Count" column from the index views + +**Files:** +- Modify: `lib/towerops_web/live/escalation_policy_live/index.html.heex` +- Modify: `lib/towerops_web/live/schedule_live/index.html.heex` +- Test: `test/towerops_web/live/escalation_policy_live_test.exs` + +**Step 1: Write the failing test** + +```elixir +test "policy index does not show a Repeat Count column", %{conn: conn, organization: org, user: user} do + _ = escalation_policy_fixture(org.id, %{name: "p", repeat_count: 5}) + + {:ok, _view, html} = + conn |> log_in_user(user) |> live(~p"/schedules/escalation-policies") + + refute html =~ "Repeat Count" +end +``` + +**Step 2: Run failing test** + +Expected: FAIL because the column still exists. + +**Step 3: Edit the templates** + +In `lib/towerops_web/live/escalation_policy_live/index.html.heex` remove: +- the `` for "Repeat Count" (line ~48-50) +- the `` rendering `policy.repeat_count` (line ~62-64) + +In `lib/towerops_web/live/schedule_live/index.html.heex` remove: +- the `` for "Repeat Count" (line ~84-86) +- the `` rendering `policy.repeat_count` (line ~101-103) + +Replace either with a useful column instead — `t("Levels")` showing `length(policy.rules)` (preload rules in `index.ex` if not already). + +**Step 4: Re-run tests** + +Expected: PASS. + +**Step 5: Commit** + +```bash +git add lib/towerops_web/live/escalation_policy_live/index.html.heex \ + lib/towerops_web/live/schedule_live/index.html.heex \ + test/towerops_web/live/escalation_policy_live_test.exs +git commit -m "feat(on_call): drop Repeat Count column from policy index views" +``` + +--- + +## Task 1.7: Run the full suite and fix fallout + +Run: `mix precommit` +Expected: PASS. + +If any other tests reference the old "Repeat Count" label, update them. Do **not** delete data assertions on `repeat_count` — the field still exists. + +Commit any test fixups separately: + +```bash +git commit -am "test: update assertions for new escalation policy markup" +``` + +--- + +# Chunk 2: Schedules list with gantt timeline (outline) + +> Detailed when chunk 1 is merged. Sketch: + +- New `Towerops.OnCall.Resolver.resolve_range/3` returning `[%{user_id, start_at, end_at}]` segments for a date window. Test pure with multiple layers + overrides. +- Replace the schedules tab in `schedule_live/index.html.heex` with: + - Date nav header (`Today`, `<` `>`, label, range selector dropdown) + - Per-row layout: name, on-call-now avatar+name, an SVG gantt strip (or CSS grid with day cells), Export menu, `…` menu. + - Search input + pagination (use the existing `<.pagination>` component pattern in `CLAUDE.md`). +- Render the gantt server-side as a CSS grid: each segment is `grid-column: / span ` with the user's color. +- Color for users derived deterministically from `user.id` (hash → palette). + +# Chunk 3: Schedule edit with multi-layer cards + live preview (outline) + +- Per-layer card matching image 2: Step 1 users picker, Step 2 rotation type/handoff, Step 3 start. +- Below the form, render two gantt strips: per-layer (Configuration Layers) and the resolver output (Final Schedule). +- Restrictions editor (start_time/end_time within day; weekday range). +- Add reorder + delete for layers. + +# Chunk 4: Polish + e2e (outline) + +- Playwright e2e: create schedule with 2 layers, verify gantt; create policy with 2 levels, reorder, change repeat, verify show page. +- Empty-state polish on every page. +- Update `priv/static/changelog.txt` with user-facing summary; append technical notes to `CHANGELOG.txt`. +- Screenshot review against the four reference images. + +--- + +# Out-of-scope + +- Drag-and-drop level/layer reordering (use up/down arrows in v1). +- Alembic-style "compute next on-call" timeline previews longer than 12 weeks. +- iCal export improvements beyond what already exists. +- Any change to the escalation engine (`Towerops.OnCall.Escalation.advance_escalation/2`) — `repeat_count` keeps working as today. diff --git a/dry.md b/dry.md deleted file mode 100644 index da91c30c..00000000 --- a/dry.md +++ /dev/null @@ -1,564 +0,0 @@ -# Code Review: DRY & Idiomatic Elixir Findings - -This document captures concrete duplication and non-idiomatic patterns found across the codebase. Each finding includes file paths and line numbers where applicable. - ---- - -## 1. ✅ DONE - Duplicated `credential_source_atom` / `safe_source_to_atom` - -**Files:** `lib/towerops/devices.ex` lines 408–412 and 887–893 - -Two private functions in the same module do the exact same thing — convert a credential source string to an atom — with slightly different names and one extra `nil` clause: - -```elixir -# line 408 -defp safe_source_to_atom("device"), do: :device -defp safe_source_to_atom("site"), do: :site -defp safe_source_to_atom("organization"), do: :organization -defp safe_source_to_atom(nil), do: :organization -defp safe_source_to_atom(_unknown), do: :organization - -# line 887 -defp credential_source_atom(value) do - case value do - "device" -> :device - "site" -> :site - "organization" -> :organization - _ -> :organization - end -end -``` - -These should be merged into a single private function using pattern-matching clauses (the idiomatic form): - -```elixir -defp credential_source_atom("device"), do: :device -defp credential_source_atom("site"), do: :site -defp credential_source_atom(_), do: :organization -``` - ---- - -## 2. ✅ DONE - Six Near-Identical `propagate_*` Functions in `devices.ex` - -**File:** `lib/towerops/devices.ex` - -The following six public functions share an identical structure — build a query, fetch device IDs, compute `now`, call `Repo.update_all`, then broadcast per-device: - -- `propagate_site_mikrotik_change/2` (~line 459) -- `propagate_organization_mikrotik_change/2` (~line 492) -- `propagate_site_snmpv3_change/2` (~line 563) -- `propagate_organization_snmpv3_change/2` (~line 591) -- `propagate_site_community_change/2` (~line 903) -- `propagate_organization_community_change/2` (~line 930) - -The only differences are the query filter field (`site_id` vs `organization_id`), the credential source string (`"site"` vs `"organization"`), the fields being updated, and the broadcast event atom. - -Extract a private helper: - -```elixir -defp propagate_credential_change(device_query, attrs, broadcast_event) do - device_ids = Repo.all(from(d in device_query, select: d.id)) - now = DateTime.truncate(DateTime.utc_now(), :second) - updates = attrs |> Map.new() |> Map.put(:updated_at, now) |> Map.to_list() - - Repo.update_all(device_query, set: updates) - - Enum.each(device_ids, fn device_id -> - Phoenix.PubSub.broadcast( - Towerops.PubSub, - "device:#{device_id}:assignments", - {:assignments_changed, broadcast_event} - ) - end) - - :ok -end -``` - -The six public functions then become thin wrappers that build the query and delegate. - ---- - -## 3. ⏭️ DEFERRED - Repeated Form LiveView Pattern (handle_params + validate + save) - -**Reason**: Complex refactoring requiring behavior module or macro abstraction across 4 LiveView files. Would benefit from separate PR with comprehensive testing. - -**Files:** - -- `lib/towerops_web/live/schedule_live/form.ex` -- `lib/towerops_web/live/escalation_policy_live/form.ex` -- `lib/towerops_web/live/maintenance_live/form.ex` -- `lib/towerops_web/live/site_live/form.ex` - -All four follow the exact same skeleton: - -```elixir -def handle_params(params, _url, socket) do - case socket.assigns.live_action do - :new -> # assign empty struct + changeset - :edit -> # load resource + changeset - end -end - -def handle_event("validate", %{"resource" => params}, socket) do - changeset = socket.assigns.resource |> Schema.changeset(params) |> Map.put(:action, :validate) - {:noreply, assign(socket, :form, to_form(changeset))} -end - -def handle_event("save", %{"resource" => params}, socket) do - case socket.assigns.live_action do - :new -> save_resource(socket, :create, params) - :edit -> save_resource(socket, :update, params) - end -end - -defp save_resource(socket, :create, params) do - case Context.create_resource(params) do - {:ok, resource} -> {:noreply, socket |> put_flash(:info, "...") |> push_navigate(...)} - {:error, changeset} -> {:noreply, assign(socket, :form, to_form(changeset))} - end -end - -defp save_resource(socket, :update, params) do - case Context.update_resource(socket.assigns.resource, params) do - {:ok, resource} -> {:noreply, socket |> put_flash(:info, "...") |> push_navigate(...)} - {:error, changeset} -> {:noreply, assign(socket, :form, to_form(changeset))} - end -end -``` - -The `save_resource/3` `:create` and `:update` clauses are also structurally identical — only the context function and flash message differ. The `case socket.assigns.live_action` dispatch in `handle_event("save")` is also repeated verbatim in all four modules. - ---- - -## 4. ⏭️ DEFERRED - Repeated Access Control Error Handling in LiveViews - -**Reason**: Would require AccessControl helper to return socket-ready responses. Impacts 6+ LiveView files. Better as separate focused PR. - -**Files:** - -- `lib/towerops_web/live/alert_live/index.ex` (~lines 53–80) -- `lib/towerops_web/live/device_live/form.ex` (~lines 105–115) -- `lib/towerops_web/live/device_live/show.ex` (~lines 61–75, 817–825, 1018–1025) -- `lib/towerops_web/live/config_timeline_live.ex` (~line 24) -- `lib/towerops_web/live/dashboard_live.ex` (~line 66) -- `lib/towerops_web/live/device_live/index.ex` (~lines 146–166) - -Every call to `AccessControl.verify_*_access/2` is followed by the same two error clauses: - -```elixir -{:error, :not_found} -> - {:noreply, put_flash(socket, :error, t_equipment("... not found"))} - -{:error, :unauthorized} -> - {:noreply, put_flash(socket, :error, t_equipment("You don't have access to this ..."))} -``` - -`AccessControl` already centralises the lookup logic. A companion helper in the same module (or a small addition to `AccessControl`) could handle the flash + navigate response, reducing each call site to a single `with` or `case` without the repeated error branches. - ---- - -## 5. ✅ DONE - `determine_effective_agent_id` Duplicates `Agents.get_effective_agent_token/1` - -**File:** `lib/towerops_web/live/device_live/form.ex` (~lines 390–415) - -`determine_effective_agent_id/2` walks device → site → org to find an agent token. This is exactly what `Agents.get_effective_agent_token/1` and `Agents.get_effective_agent_token_with_source/1` already do in `lib/towerops/agents.ex`. The LiveView version operates on form params (maps) rather than structs, but the logic is the same. Similarly, `using_cloud_poller?/2` (~line 418) repeats the same three-level walk. - -These should be consolidated — either by passing a lightweight struct to the existing `Agents` functions, or by extracting a shared helper that accepts either form params or a struct. - ---- - -## 6. ✅ DONE - `get_fallback_agent_token/1` and `get_fallback_agent_token_with_source/1` Are Near-Identical - -**File:** `lib/towerops/agents.ex` - -Both private functions walk the same site → org → global chain. The only difference is that one returns just the token ID and the other returns `{token_id, source}`. This is a classic case for a single function that always returns `{id, source}`, with the caller discarding the source when not needed: - -```elixir -defp resolve_fallback_agent(%{site: %{agent_token_id: id}} = _device) when not is_nil(id), - do: {id, :site} - -defp resolve_fallback_agent(%{site: %{organization: %{default_agent_token_id: id}}} = _device) - when not is_nil(id), - do: {id, :organization} - -defp resolve_fallback_agent(%{organization: %{default_agent_token_id: id}} = _device) - when not is_nil(id), - do: {id, :organization} - -defp resolve_fallback_agent(_device) do - case Towerops.Settings.get_global_default_cloud_poller() do - nil -> {nil, :none} - id -> {id, :global} - end -end -``` - -`get_effective_agent_token/1` then becomes `elem(get_effective_agent_token_with_source(device), 0)`. - ---- - -## 7. ✅ DONE - `cond` Instead of Pattern-Matching Function Clauses - -**File:** `lib/towerops_web/live/device_live/form.ex` (~lines 72–82) - -```elixir -equipment_attrs = - cond do - socket.assigns.preselected_site_id -> - Map.put(equipment_attrs, :site_id, socket.assigns.preselected_site_id) - - length(socket.assigns.available_sites) == 1 -> - site = List.first(socket.assigns.available_sites) - Map.put(equipment_attrs, :site_id, site.id) - - true -> - equipment_attrs - end -``` - -This is better expressed as a private function with pattern-matching clauses: - -```elixir -defp maybe_preselect_site(attrs, preselected_id, _sites) when not is_nil(preselected_id), - do: Map.put(attrs, :site_id, preselected_id) - -defp maybe_preselect_site(attrs, nil, [site]), - do: Map.put(attrs, :site_id, site.id) - -defp maybe_preselect_site(attrs, nil, _sites), do: attrs -``` - -**File:** `lib/towerops/agents.ex` — `get_fallback_agent_token/1` and `get_fallback_agent_token_with_source/1` both use `cond` with `match?/2` guards. These should be pattern-matching function clauses (see finding #6 above). - -**File:** `lib/towerops/devices.ex` — `should_trigger_discovery?/4` (~line 1090) uses `cond` with boolean conditions that are better expressed as pattern-matching clauses or a series of guard-based function heads. - ---- - -## 8. ✅ DONE - `if` for Optional Value Lookup (Use `case` or Pattern Matching) - -**File:** `lib/towerops_web/live/site_live/form.ex` (~lines 30–36 and 52–58) - -```elixir -org_agent = - if socket.assigns.organization.default_agent_token_id do - Enum.find(socket.assigns.available_agents, fn a -> - a.id == socket.assigns.organization.default_agent_token_id - end) - end -``` - -This duplicates the same block in both `apply_action/3` clauses. Extract to a private function and use `case` or pattern matching: - -```elixir -defp find_org_agent(nil, _agents), do: nil -defp find_org_agent(agent_id, agents), do: Enum.find(agents, &(&1.id == agent_id)) -``` - -Then call `find_org_agent(organization.default_agent_token_id, available_agents)` in both clauses. - ---- - -## 9. ✅ DONE - `normalize_alert_type` Defined Twice in `alerts.ex` - -**File:** `lib/towerops/alerts.ex` - -```elixir -# Used for attrs map normalization -defp normalize_attrs_alert_type(%{alert_type: alert_type} = attrs) when is_atom(alert_type) do - %{attrs | alert_type: to_string(alert_type)} -end -defp normalize_attrs_alert_type(attrs), do: attrs - -# Used for query normalization -defp normalize_alert_type(alert_type) when is_atom(alert_type), do: to_string(alert_type) -defp normalize_alert_type(alert_type) when is_binary(alert_type), do: alert_type -``` - -The second function (`normalize_alert_type/1`) is a subset of the first. The atom-to-string conversion is the same in both. The attrs version can delegate: - -```elixir -defp normalize_attrs_alert_type(%{alert_type: type} = attrs) when is_atom(type), - do: %{attrs | alert_type: normalize_alert_type(type)} -defp normalize_attrs_alert_type(attrs), do: attrs -``` - ---- - -## 10. ✅ DONE - `resolve_alert` and `resolve_alert_silent` Share Identical Changeset Logic - -**File:** `lib/towerops/alerts.ex` - -Both functions build the same changeset (`%{resolved_at: DateTime.truncate(...)}`) and call `Repo.update`. The only difference is the post-update side effects. Extract the update: - -```elixir -defp do_resolve_alert(alert) do - alert - |> Alert.changeset(%{resolved_at: DateTime.truncate(DateTime.utc_now(), :second)}) - |> Repo.update() -end -``` - -Then `resolve_alert/1` and `resolve_alert_silent/1` call `do_resolve_alert/1` and handle their respective side effects. - -The same applies to `acknowledge_alert/2` and `acknowledge_alert_silent/1`. - ---- - -## 11. ✅ DONE - `DateTime.truncate(DateTime.utc_now(), :second)` Repeated ~30+ Times - -**Files:** `lib/towerops/devices.ex`, `lib/towerops/alerts.ex`, `lib/towerops/sites.ex`, `lib/towerops/organizations.ex`, `lib/towerops/agents.ex`, `lib/towerops_web/channels/agent_channel.ex`, and many more. - -This expression appears over 30 times across the codebase. A single module-level helper (or a function in `Towerops.Repo` or a shared utility module) would eliminate the repetition: - -```elixir -defp now(), do: DateTime.truncate(DateTime.utc_now(), :second) -``` - -Or, since it's needed across many modules, a public helper in e.g. `Towerops.Time`: - -```elixir -defmodule Towerops.Time do - def now(), do: DateTime.truncate(DateTime.utc_now(), :second) -end -``` - ---- - -## 12. ✅ DONE - `sanitize_like/1` Delegated Identically in Both `sites.ex` and `devices.ex` - -**Files:** `lib/towerops/sites.ex` (last line) and `lib/towerops/devices.ex` (last line) - -Both modules define: - -```elixir -defp sanitize_like(query), do: Towerops.QueryHelpers.sanitize_like(query) -``` - -This private wrapper adds no value — callers can just call `Towerops.QueryHelpers.sanitize_like/1` directly, or `import Towerops.QueryHelpers, only: [sanitize_like: 1]` at the top of each module. - ---- - -## 13. ⏭️ SKIPPED - `handle_params` Tab/Filter Pattern Repeated Across Index LiveViews - -**Reason**: Pattern is already clear and simple (`Map.get(params, "filter", default)`). Helper function would add minimal value. - -**Files:** - -- `lib/towerops_web/live/alert_live/index.ex` (~lines 38–44) -- `lib/towerops_web/live/maintenance_live/index.ex` (~lines 17–23) - -Both follow: - -```elixir -def handle_params(params, _url, socket) do - filter = Map.get(params, "filter", "default") - {:noreply, socket |> assign(:filter, filter) |> load_data(...)} -end -``` - -This is a minor but consistent pattern. A shared helper `assign_from_params(socket, params, key, default)` would make the intent clearer and reduce boilerplate. - ---- - -## 14. ✅ DONE - `verify_device_access` / `verify_site_access` in `AccessControl` Use `if` Instead of Pattern Matching - -**File:** `lib/towerops_web/live/helpers/access_control.ex` (~lines 34–43, 66–75) - -```elixir -def verify_device_access(device_id, organization_id) do - case Devices.get_device(device_id) do - nil -> {:error, :not_found} - device -> - if device.organization_id == organization_id do - {:ok, device} - else - {:error, :unauthorized} - end - end -end -``` - -The inner `if` should be a `case` or pattern match. More idiomatically, the `case` + `if` can collapse into a single `case` with a guard, or use `with`: - -```elixir -def verify_device_access(device_id, organization_id) do - with %Device{organization_id: ^organization_id} = device <- Devices.get_device(device_id) do - {:ok, device} - else - nil -> {:error, :not_found} - %Device{} -> {:error, :unauthorized} - end -end -``` - -The same applies to `verify_site_access/2`. `verify_alert_access/2` has a more complex preload but the same structural issue. - ---- - -## 15. ✅ DONE - `resolve_mikrotik_config` Uses `if` for a Nil-Default - -**File:** `lib/towerops/devices.ex` (~line 448) - -```elixir -use_ssl: if(device.mikrotik_use_ssl == nil, do: true, else: device.mikrotik_use_ssl), -``` - -This is better expressed as: - -```elixir -use_ssl: device.mikrotik_use_ssl != false, -``` - -or with a pattern-matching helper: - -```elixir -defp mikrotik_use_ssl?(nil), do: true -defp mikrotik_use_ssl?(val), do: val -``` - ---- - -## 16. ✅ DONE - `handle_snmp_changes` and `should_trigger_discovery?` Use `cond` for Boolean Logic - -**File:** `lib/towerops/devices.ex` (~lines 1080–1110) - -`should_trigger_discovery?/4` uses a `cond` with four boolean branches, all of which check `device.snmp_enabled` first. This is better expressed as pattern-matching function clauses: - -```elixir -defp should_trigger_discovery?(%{snmp_enabled: true}, false, _old_version, _old_port), do: true -defp should_trigger_discovery?(%{snmp_enabled: true, snmp_version: v}, _old_snmp, v, _), do: false -defp should_trigger_discovery?(%{snmp_enabled: true, snmp_version: _}, _, _, _), do: true -defp should_trigger_discovery?(%{snmp_enabled: true, snmp_port: p}, _, _, p), do: false -defp should_trigger_discovery?(%{snmp_enabled: true}, _, _, _), do: true -defp should_trigger_discovery?(_, _, _, _), do: false -``` - -Similarly, `handle_monitoring_changes/2` and `handle_snmp_changes/4` use `cond` where function clauses with pattern matching on the boolean pairs would be cleaner. - ---- - -## 17. ✅ DONE - `get_device` and `get_device!` Repeat the Same Preload - -**File:** `lib/towerops/devices.ex` (~lines 330–345) - -```elixir -def get_device(id) do - DeviceSchema - |> Repo.get(id) - |> case do - nil -> nil - device -> Repo.preload(device, [:organization, site: :organization]) - end -end - -def get_device!(id) do - DeviceSchema - |> Repo.get!(id) - |> Repo.preload([:organization, site: :organization]) -end -``` - -The preload list `[:organization, site: :organization]` is duplicated. Extract it as a module attribute or a private function: - -```elixir -@device_preloads [:organization, site: :organization] - -def get_device(id) do - case Repo.get(DeviceSchema, id) do - nil -> nil - device -> Repo.preload(device, @device_preloads) - end -end - -def get_device!(id), do: DeviceSchema |> Repo.get!(id) |> Repo.preload(@device_preloads) -``` - -The same pattern applies to `get_site/1` and `get_site!/1` in `lib/towerops/sites.ex` (both preload `[:parent_site, :child_sites, :device]`). - ---- - -## 18. ✅ DONE - `list_organization_devices` Uses `if` for Query Composition - -**File:** `lib/towerops/devices.ex` (~lines 44–65) - -```elixir -query = - if site_id = filters["site_id"] do - where(query, [e], e.site_id == ^site_id) - else - query - end - -query = - if status = filters["status"] do - where(query, [e], e.status == ^status) - else - query - end -``` - -This is the idiomatic Ecto filter-building pattern, but the `if/else query` form is verbose. The more idiomatic approach uses `Enum.reduce` over the filters or a pipeline of `maybe_filter_*` helpers: - -```elixir -defp maybe_filter_site(query, nil), do: query -defp maybe_filter_site(query, site_id), do: where(query, [e], e.site_id == ^site_id) - -defp maybe_filter_status(query, nil), do: query -defp maybe_filter_status(query, status), do: where(query, [e], e.status == ^status) -``` - ---- - -## 19. ⏭️ SKIPPED - `alert_live/index.ex` — `severity_color/1` and `severity_badge_class/1` Are Two Functions That Should Be One - -**Reason**: `severity_color/1` is used independently in template for text colors. Cannot collapse without breaking functionality. - -**File:** `lib/towerops_web/live/alert_live/index.ex` (~lines 220–250) - -`severity_color/1` returns a string like `"red"`, and `severity_badge_class/1` immediately maps that string to a CSS class. The intermediate string representation is only used to feed `severity_badge_class/1`. Collapse them: - -```elixir -defp severity_badge_class(alert) do - cond do - alert.resolved_at -> "bg-gray-300 dark:bg-gray-600" - alert.alert_type == "device_down" and is_nil(alert.resolved_at) -> - age_minutes = DateTime.diff(DateTime.utc_now(), alert.triggered_at, :minute) - cond do - age_minutes > 60 -> "bg-red-500" - age_minutes > 15 -> "bg-orange-500" - true -> "bg-yellow-500" - end - true -> "bg-green-500" - end -end -``` - -Unless `severity_color/1` is used independently in the template (in which case the indirection is intentional), the two-step conversion is unnecessary. - ---- - -## 20. ⏭️ SKIPPED - `age_text/1`, `duration_text/1`, and `time_ago/1` Repeat Minute-Bucketing Logic - -**Reason**: Functions have different semantics (seconds vs minutes, "just now" vs exact seconds) and serve different contexts. Duplication is acceptable for clarity. - -**Files:** `lib/towerops_web/live/alert_live/index.ex` and `lib/towerops_web/live/device_live/helpers/formatters.ex` - -`age_text/1` and `duration_text/1` in `alert_live/index.ex` both compute `minutes` from a `DateTime.diff` and then bucket into `<1m / Xm / Xh / Xd`. The `Formatters` module already has `time_ago/1`. These should be consolidated in `Formatters` and called from the template. - ---- - -## Summary of Priorities - -**High impact (most duplication removed):** - -1. Merge `safe_source_to_atom` / `credential_source_atom` into one function (finding #1) -2. Extract `propagate_credential_change/3` helper (finding #2) -3. Merge `get_fallback_agent_token` variants (finding #6) -4. Extract `do_resolve_alert` / `do_acknowledge_alert` (finding #10) -5. Introduce `Towerops.Time.now/0` or a module-level `now/0` (finding #11) - -**Medium impact (idiomatic improvements):** 6. Replace `if` with `with` in `AccessControl.verify_*_access` (finding #14) 7. Replace `cond` with pattern-matching clauses in `device_live/form.ex`, `agents.ex`, `devices.ex` (findings #7, #16) 8. Extract `maybe_preselect_site/3` and `find_org_agent/2` (findings #7, #8) 9. Use `@device_preloads` module attribute for repeated preload lists (finding #17) 10. Use `maybe_filter_*` helpers in `list_organization_devices` (finding #18) - -**Low impact (minor cleanup):** 11. Remove `sanitize_like/1` private wrappers (finding #12) 12. Collapse `severity_color` + `severity_badge_class` (finding #19) 13. Consolidate time-formatting helpers into `Formatters` (finding #20) 14. Simplify `normalize_attrs_alert_type` to delegate to `normalize_alert_type` (finding #9) diff --git a/findings_librenms.md b/findings_librenms.md deleted file mode 100644 index ffd6684c..00000000 --- a/findings_librenms.md +++ /dev/null @@ -1,1906 +0,0 @@ -# LibreNMS vs TowerOps SNMP Review - -## Scope - -This review compares the local LibreNMS checkout in `~/dev/librenms/` against the current TowerOps codebase in `/Users/graham/dev/towerops/towerops-web`. - -I focused on: - -- SNMP transport and polling behavior -- Device discovery and device lifecycle handling -- Metric/entity gathering -- Data normalization and threshold semantics -- Persistence and historical storage -- Operational robustness -- Areas where TowerOps is already better positioned - -Key code reviewed included: - -- LibreNMS: - - `app/Console/Commands/DevicePoll.php` - - `app/Console/Commands/DeviceDiscover.php` - - `app/PerDeviceProcess.php` - - `LibreNMS/Modules/*` - - `LibreNMS/Device/YamlDiscovery.php` - - `LibreNMS/Data/Store/*` - - `includes/discovery/*` - - `includes/polling/*` - - `app/Models/Device.php`, `Port.php`, `Sensor.php`, `Storage.php`, `Processor.php` -- TowerOps: - - `lib/towerops/snmp/client.ex` - - `lib/towerops/snmp/discovery.ex` - - `lib/towerops/snmp/profiles/base.ex` - - `lib/towerops/snmp/profiles/dynamic.ex` - - `lib/towerops/snmp/deferred_discovery.ex` - - `lib/towerops/snmp.ex` - - `lib/towerops/workers/device_poller_worker.ex` - - `lib/towerops/snmp/*.ex` entity schemas - - `priv/repo/migrations/*timescaledb*` - -## Executive Summary - -TowerOps already has a solid SNMP foundation. It is not a toy implementation. It has: - -- a real discovery pipeline -- a broad vendor-profile system -- historical storage in Postgres/Timescale -- parallel polling -- topology, ARP, MAC, and wireless-client handling -- agent-aware polling assignment - -That said, LibreNMS is still materially more mature as a general SNMP monitoring platform. - -The biggest differences are not "can TowerOps talk SNMP?" but: - -- breadth of discovered entity types -- depth of metric semantics and normalization -- transport/polling heuristics for difficult devices -- lifecycle handling for discovered entities -- pluggable datastore/export story -- module-level operational maturity built up from years of edge cases - -If the target is "as robust and feature rich as LibreNMS, then much more", TowerOps should keep its current architecture but expand it in a LibreNMS-like direction: - -1. make transport and polling behavior much smarter -2. expand entity/module coverage aggressively -3. add richer metric semantics and threshold/state models -4. strengthen discovery drift and lifecycle handling -5. treat topology, subscriber correlation, and agent-distributed polling as the differentiators that go beyond LibreNMS - -## Expanded Strategy - -The five points above are the right high-level direction, but they need to be translated into an explicit engineering strategy. Below is what each one should mean in practice. - -### 1. Make transport and polling behavior much smarter - -This is the most immediate leverage point because it improves every current and future module. - -Right now TowerOps has solid SNMP primitives, but it still behaves too much like a clean protocol client and not enough like a hardened polling engine. LibreNMS has a lot of ugly historical logic here, but that ugliness exists for a reason: real devices are inconsistent, slow, buggy, and often only partially standards-compliant. - -TowerOps should evolve from "SNMP client plus polling worker" into "adaptive polling engine with device-specific transport policy". - -That means adding a transport capability model per device or profile, including: - -- preferred operation mode: `get`, `get_next`, `walk`, `bulk_walk` -- whether GETBULK is safe -- max repeaters / repetition window -- retry policy -- timeout class -- whether responses can be unordered -- whether certain OIDs must avoid bulk or avoid combined requests -- whether a device should prefer table walks vs selected-item gets -- whether interface polling should be selective or full-table - -This should not stay implicit in code branches. It should become explicit discovered or profile-driven capability data. - -Concrete improvements: - -- ✅ **DONE (2026-03-26)**: implement a true multi-OID GET path so `get_multiple/2` is not a loop of individual requests -- move more polling to table-oriented retrieval, especially for interfaces and sensors -- add adaptive bulk sizing based on response size, timeout rate, and prior successful runs -- add a device-level "transport memory" layer so TowerOps learns what works on a specific box -- distinguish "device is down" from "this module/OID strategy is bad for this device" -- add poll cost accounting: request count, bytes returned, duration, failure rate, timeout count - -The goal is not just speed. The goal is stable polling on weird devices without special-casing everything forever. - -A good end state would be: - -- first discovery runs conservatively -- TowerOps learns the device's behavior -- later polls use an optimized strategy -- if errors increase, TowerOps automatically degrades to a safer strategy - -LibreNMS has a lot of static heuristics. TowerOps can do better by making that adaptive. - -### 2. Expand entity/module coverage aggressively - -TowerOps should treat SNMP coverage as a product surface, not a side effect of polling. - -LibreNMS is stronger because it models many more things. That breadth matters because operators do not think in terms of "poll sysObjectID and a few sensors". They think in terms of: - -- optics -- memory -- routes -- BGP neighbors -- STP topology -- QoS queues -- storage -- power supplies -- printer consumables -- xDSL lines -- VM guests -- hardware inventory - -TowerOps should formalize a module catalog and then grow it quickly. - -Suggested first-class module families: - -- `Core` -- `Interfaces` -- `InterfaceExtendedStats` -- `Sensors` -- `StateSensors` -- `Processors` -- `Mempools` -- `Storage` -- `Transceivers` -- `EntityPhysical` -- `Vlans` -- `Ipv4Addresses` -- `Ipv6Addresses` -- `Neighbors` -- `Arp` -- `Mac` -- `Routes` -- `Stp` -- `Qos` -- `Bgp` -- `Ospf` -- `Services` -- `Wireless` -- `PrinterSupplies` -- `Xdsl` - -This should not all land at once, but the module system should be designed for that future immediately. - -The order I would recommend: - -1. `Mempools` -2. `Transceivers` -3. `EntityPhysical` -4. `Routes` -5. `Qos` -6. `Bgp` -7. `Stp` - -Why this order: - -- mempools and transceivers are common, visible, and high-value -- entity physical gives a backbone for inventory, FRUs, and relationship mapping -- routes/QoS/BGP/STP move TowerOps from device monitoring into actual network operations monitoring - -This should be done with a mix of: - -- generic standard-MIB implementations -- vendor/profile extensions -- a shared module contract for discovery, poll, sync, cleanup, and capability checks - -The key is to prevent new coverage from turning the codebase into an ever-growing `device_poller_worker.ex` blob. Coverage growth must come with module boundaries. - -### 3. Add richer metric semantics and threshold/state models - -TowerOps currently stores readings well, but it does not yet model metric meaning as deeply as LibreNMS. - -To match and then surpass LibreNMS, TowerOps needs to treat each discovered metric-bearing entity as more than: - -- an OID -- a current value -- a timestamp - -Each metric should carry enough metadata for TowerOps to reason about it correctly. - -That means first-class support for: - -- raw value -- normalized value -- divisor -- multiplier -- unit -- unit family -- metric type: `gauge`, `counter`, `derive`, `state` -- threshold policy -- warning/critical bounds -- low and high bounds -- reset/wrap behavior -- value source quality -- preferred graph aggregation - -For state sensors, TowerOps should introduce a proper state model, not just a string description on readings. - -LibreNMS has stronger state semantics through translation tables. TowerOps should add something similar but cleaner: - -- state index definition -- translation map from raw values to normalized state -- generic severity mapping: `ok`, `warning`, `critical`, `unknown` -- change-event policy -- suppression/debounce policy - -For numeric metrics, TowerOps should support discovered threshold metadata and local overrides separately. - -There are really three threshold layers: - -1. vendor/device-provided thresholds -2. profile defaults -3. operator overrides - -Those should be modeled independently so the system can explain why a value is considered abnormal. - -This also enables better product behavior: - -- graphs can render warning/critical zones correctly -- alerts can distinguish vendor-threshold breach vs operator policy breach -- anomaly detection can compare against both thresholds and learned baselines - -The most important conceptual change here is: - -TowerOps should move from "store readings and run checks" to "understand the semantics of each metric, then use checks as one consumer of that model". - -That would be a stronger architecture than LibreNMS. - -### 4. Strengthen discovery drift and lifecycle handling - -LibreNMS is robust partly because it assumes discovered entities are unstable: - -- interfaces rename -- ifIndex values drift -- sensors vanish and come back -- optics move slots -- storage entries reorder -- devices partially implement MIBs - -TowerOps already syncs discovered entities and cleans up certain stale records, but it should develop a full discovery lifecycle model. - -Every discovered entity should have lifecycle semantics: - -- first discovered at -- last seen at -- last changed at -- active / stale / deleted state -- stable identity key -- mutable display attributes -- drift reason if identity changed - -Examples: - -- an interface can keep the same stable identity while alias, speed, or label changes -- a transceiver can be removed and later reinserted -- a storage entry can move from "active" to "missing" without immediate hard deletion -- a sensor can be marked unsupported by current firmware after an upgrade - -TowerOps should also record discovery drift as auditable events: - -- interface renamed -- ifIndex changed -- sensor threshold changed -- storage table reordered -- model/serial/firmware changed -- LLDP capability set changed - -This is important for both reliability and UX. Operators need to know whether a graph or alert changed because the system discovered something new or because the device actually changed. - -A strong end state would include two layers: - -- current entity view -- discovery history / identity history - -That would let TowerOps survive SNMP instability much better than a simple overwrite model. - -This is also where entity sync strategy matters. For each entity family, TowerOps should explicitly define: - -- identity key -- update fields -- staleness window -- hard delete window -- drift event rules - -Without that, robustness will always be uneven across modules. - -### 5. Treat topology, subscriber correlation, and agent-distributed polling as the differentiators that go beyond LibreNMS - -This is where TowerOps should stop thinking like "an NMS trying to catch up" and start thinking like "a network operations platform that happens to include SNMP". - -LibreNMS is broad and mature, but its center of gravity is still classic device monitoring. - -TowerOps already has stronger raw ingredients for something more valuable: - -- topology inference from neighbors, ARP, and MAC evidence -- wireless client discovery with history -- subscriber correlation -- multi-tenant data model -- agent-aware polling ownership - -These should not remain side features. They should become the main differentiator. - -There are three major product directions here. - -First, topology should become operational, not just descriptive. - -That means: - -- infer path relationships, not just direct links -- attach devices, interfaces, wireless clients, and subscribers into one graph -- use graph state during incident analysis -- identify probable upstream failure points -- compute blast radius automatically - -A traditional NMS shows "these devices are down". A stronger TowerOps should be able to say "this uplink failure is causing 143 impacted subscribers across these APs and these sites". - -Second, subscriber correlation should become a first-class consumer of SNMP and topology data. - -That means: - -- correlate subscribers to APs, sectors, switches, and upstream paths -- retain movement history -- distinguish probable vs confirmed attachment -- use RF quality, ARP evidence, and topology together -- enable customer-impact views instead of just device-impact views - -This is much closer to how WISPs and access-network operators actually think. - -Third, agent-distributed polling should become a smart execution fabric. - -Right now TowerOps is aware of agents. The next step is to make scheduling and placement intelligent: - -- route polling based on network reachability and locality -- detect overloaded or unhealthy agents -- move devices between agents automatically -- support partial capability ownership by module -- allow fallback execution strategies -- track poll success by agent, region, and module - -That would put TowerOps in a position LibreNMS generally is not designed for: - -- hybrid central/distributed polling -- tenant-aware placement -- topology-aware scheduling -- richer execution telemetry - -The combined opportunity is substantial. - -If TowerOps executes well here, the platform can evolve from: - -- "SNMP monitoring system" - -into: - -- "distributed network observability and operations system" - -That is the path to "much more". - -## Where TowerOps Is Already Strong - -These are real strengths, not consolation prizes. - -### 1. Better application architecture for future growth - -TowerOps has a cleaner domain split than LibreNMS: - -- `Towerops.Snmp` as a context API -- explicit schemas for sensors, interfaces, storage, processors, neighbors, ARP, MACs, wireless clients -- Oban workers for polling/discovery/cleanup -- TimescaleDB-oriented historical tables - -LibreNMS has a lot of mature logic, but much of it still spans legacy includes, DB helpers, and mixed discovery/polling styles. - -### 2. Better integrated topology and subscriber-aware data model - -TowerOps is already ahead in areas LibreNMS treats more generically: - -- neighbor polling and topology inference -- ARP/MAC correlation into topology -- wireless client discovery with history -- subscriber/device correlation (`Gaiia.SubscriberMatching`) -- agent-aware ownership and result discard on reassignment - -This is the right direction if TowerOps wants to become more than a standard NMS. - -### 3. Better relational and analytical storage story - -TowerOps stores historical SNMP data in PostgreSQL/TimescaleDB: - -- `snmp_sensor_readings` -- `snmp_interface_stats` -- `snmp_processor_readings` -- `snmp_storage_readings` -- `wireless_client_readings` - -LibreNMS primarily treats RRD as the historical source of truth and the SQL DB as current-state metadata. That model is proven, but TowerOps has a better foundation for analytics, joins, ML-style insights, and tenant-aware retention. - -### 4. Strong vendor coverage direction - -TowerOps already has a large vendor-profile surface under `lib/towerops/snmp/profiles/vendors/`. That is the correct scaling model if it remains disciplined. - -## Major Findings - -## 1. LibreNMS has a much broader module surface - -LibreNMS ships a real module catalog under `LibreNMS/Modules/`, including: - -- `ArpTable` -- `Availability` -- `Core` -- `DiscoveryArp` -- `EntityPhysical` -- `HrDevice` -- `IpSystemStats` -- `Ipv4Addresses` -- `Ipv6Addresses` -- `Ipv6Nd` -- `Isis` -- `MacAccounting` -- `Mempools` -- `Mpls` -- `Nac` -- `Netstats` -- `Ospf` -- `Ospfv3` -- `PortSecurity` -- `PortsStack` -- `PrinterSupplies` -- `Qos` -- `Routes` -- `Services` -- `Slas` -- `Storage` -- `Stp` -- `Transceivers` -- `UcdDiskio` -- `Vlans` -- `Vminfo` -- `Wireless` -- `Xdsl` - -TowerOps currently covers a narrower but useful subset: - -- core system/device info -- interfaces -- sensors/state sensors -- processors -- storage -- VLANs -- IP addresses -- neighbors -- ARP -- MAC/FDB -- wireless clients - -### Impact - -TowerOps is already viable for device-centric SNMP monitoring, but it is not yet comparable to LibreNMS as a full-spectrum network/server SNMP platform. - -### Highest-priority missing entity families - -- mempools / memory pools -- transceivers / DOM optics -- printer supplies -- hr-device / detailed hardware inventory -- route tables -- STP -- BGP/OSPF/ISIS/MPLS -- QoS -- SLAs -- xDSL -- NAC / port security / MAC accounting -- VM info -- service/application monitoring through device-side integrations - -## 2. LibreNMS transport behavior is more battle-hardened - -LibreNMS transport code and poller behavior show years of hardening: - -- per-device timeout/retry/max repeater logic in `includes/snmp.inc.php` -- choice between `snmpwalk` and `snmpbulkwalk` -- explicit no-bulk exceptions for OS/OID combinations -- unordered response allowances -- module-level selective polling behavior -- selected-port polling heuristics in `includes/polling/ports.inc.php` - -TowerOps has a clean SNMP client in `lib/towerops/snmp/client.ex`, but it is currently simpler. - -Two specific gaps stand out: - -### Gap: `get_multiple/2` is not a true multi-get - -✅ **FIXED (2026-03-26)**: `Towerops.Snmp.Client.get_multiple/2` now sends a single batched GET PDU with multiple varbinds instead of looping through individual GET requests. - -This brings TowerOps to parity with LibreNMS's batching approach for multi-OID GET operations. Further improvements needed for GETBULK and table-oriented polling. - -### Gap: bulk strategy is not used as aggressively as it should be - -TowerOps has `get_bulk/3`, but the discovery/polling paths still rely heavily on repeated `walk/2` and sequential per-interface/per-sensor fetches. - -LibreNMS is much more aggressive about: - -- walking whole tables -- selecting bulk vs non-bulk based on device/OS quirks -- reducing round trips - -### Recommendation - -Build a transport capability layer per device/profile: - -- supports real SNMP GET for multiple OIDs in one PDU -- supports adaptive GETBULK with per-device `max_repetitions` -- allows per-profile and per-OID `no_bulk`, `unordered`, and retry overrides -- caches known bad behaviors per device/profile - -This is one of the highest ROI improvements in the whole system. - -## 3. LibreNMS discovery is much richer and more systematic - -LibreNMS discovery combines: - -- fast OS detection in `LibreNMS\Modules\Core` -- YAML-driven OS detection and discovery definitions -- model synchronization for discovered entities -- dedicated discovery modules for ports, sensors, storage, mempools, transceivers, etc. - -TowerOps has two strong ideas here: - -- `DeferredDiscovery` explicitly separates fast and slow work -- `Profiles.Dynamic` mirrors LibreNMS's YAML/vendor-profile approach - -That is good. But TowerOps discovery breadth is still behind, and its entity lifecycle handling is simpler. - -### What LibreNMS does better - -- more discovery modules -- more fallback paths per OS -- more mature OS detection -- richer entity-specific YAML traits for mempools/storage/processors -- better coverage of special-case discovery includes - -### What TowerOps does better - -- clearer deferred-discovery concept -- easier-to-reason-about Elixir code -- better future fit for typed, testable discovery pipelines - -### Recommendation - -Keep the current discovery design, but formalize modules around it: - -- `Core` -- `Interfaces` -- `Sensors` -- `StateSensors` -- `Storage` -- `Processors` -- `Mempools` -- `Transceivers` -- `Vlans` -- `Ipv4` -- `Ipv6` -- `Neighbors` -- `Arp` -- `Mac` -- `Wireless` -- `Routes` -- `Stp` -- `Services` - -Right now the logic exists, but it is still more monolithic than LibreNMS's module surface. - -## 4. TowerOps device handling is cleaner, but operationally shallower - -LibreNMS `app/Models/Device.php` carries a lot of operational metadata: - -- status and maintenance semantics -- ignore/disabled flags -- poller group -- retries/timeout -- display formatting -- hostname vs overwrite IP handling -- SNMP v1/v2c/v3 support details -- VRF context support -- device type defaults and overrides - -TowerOps `lib/towerops/devices/device.ex` is cleaner and more tenant-aware: - -- organization/site ownership -- SNMP credentials and source tracking -- agent assignment compatibility -- check intervals -- MikroTik credentials - -But it lacks some of LibreNMS's mature device-operability semantics. - -### Missing or underdeveloped device-level concerns - -- poller grouping / queue affinity / sharding semantics -- per-device SNMP timeout and retry tuning -- VRF/context-aware polling -- ignore/disabled semantics at the same depth -- richer maintenance/operational modes -- device capability flags learned from discovery -- more complete current-state summary fields - -### Recommendation - -TowerOps should add a discovered capability profile to the device/SNMP device: - -- bulk-capable? -- unstable ifIndex? -- supports HC counters? -- supports LLDP/CDP? -- supports ENTITY-SENSOR-MIB? -- supports HR storage? -- supports mempool-like resources? -- preferred polling profile - -LibreNMS's maturity partly comes from years of implicit capability handling. TowerOps should make that explicit. - -## 5. LibreNMS has much richer metric semantics - -This is one of the biggest gaps. - -LibreNMS sensor/storage/mempool/processor models carry more semantic structure: - -- thresholds on sensors -- low/high warning and critical limits -- state translation tables for state sensors -- divisor and multiplier handling -- user transformation functions -- rate-oriented sensor handling for COUNTER/DERIVE types -- storage and mempool "fill missing ratio" logic -- class-aware memory availability calculations - -TowerOps sensor and reading models are currently simpler: - -- `snmp_sensors` stores type/index/OID/descr/unit/divisor/last value/metadata -- `snmp_sensor_readings` stores value/status/state_descr/timestamp -- processors and storage have simpler current + reading schemas - -### Specific gaps in TowerOps - -- no generic threshold model on discovered sensors -- no explicit state translation/index model like LibreNMS state sensors -- no generic multiplier support visible in the schema -- no generic rate sensor type handling -- no mempool entity family -- no derived memory availability logic -- narrower processor taxonomy -- narrower storage semantics - -### Recommendation - -Add first-class metric semantics to the discovery model, not just to alert checks. - -Each discovered metric-capable entity should be able to carry: - -- raw OID -- normalized value -- divisor -- multiplier -- data type: `gauge`, `counter`, `derive`, `state` -- threshold policy -- state translation table reference -- preferred graph/aggregation strategy -- unit family - -That will let TowerOps match LibreNMS for monitoring semantics while still using a better storage backend. - -## 6. TowerOps interface statistics are currently too narrow - -TowerOps `snmp_interface_stats` stores: - -- in/out octets -- in/out errors -- in/out discards -- timestamp -- HC flag - -LibreNMS port polling tracks a much broader port state space: - -- octets -- packets -- unicast / multicast / broadcast -- errors -- discards -- unknown protocols -- duplex -- PoE / etherlike / vendor extensions -- admin/oper states -- speed and description drift -- selected-port polling and deleted-port handling - -TowerOps also checks attribute changes separately, which is useful, but the historical stat model is still fairly thin. - -### Recommendation - -Expand interface stat collection and persistence to include at least: - -- unicast/multicast/broadcast packet counters -- unknown protocol counters -- pause / queue drop counters where available -- duplex and negotiated speed snapshots -- optional per-vendor extended counters - -Then add derived rate queries and wrap/reset detection. - -If TowerOps wants to be better than LibreNMS, it should not stop at raw counters. It should also compute: - -- utilization percent -- error rate -- discard rate -- anomaly flags -- flap score - -## 7. LibreNMS handles discovered entity lifecycle more robustly - -LibreNMS port discovery/polling has mature handling for: - -- new entities -- deleted/missing entities -- re-discovered entities -- association mode drift -- selective polling skips -- sync/update semantics - -TowerOps has sync functions in `Towerops.Snmp.Discovery` and stale cleanup for neighbors/ARP/MAC/wireless data, but the lifecycle model is still lighter. - -### Gaps - -- fewer explicit "deleted vs active vs stale" semantics on discovered entities -- less explicit port/interface association strategy management -- less historical handling of identity drift -- less per-entity lifecycle metadata - -### Recommendation - -For interfaces, sensors, storage, processors, and transceivers once added: - -- add `discovered_at` -- add `last_seen_at` -- add `deleted_at` or `active`/`deleted` flags -- persist stable identity keys separate from mutable labels -- keep rediscovery drift audit events - -LibreNMS survives a lot of weird devices because it expects entities to come and go. TowerOps should encode that assumption directly. - -## 8. LibreNMS has a more flexible datastore/export model - -LibreNMS `LibreNMS\Data\Store\Datastore` fans out to multiple storage/export sinks: - -- RRD -- InfluxDB -- InfluxDB v2 -- Prometheus -- Graphite -- Kafka - -TowerOps currently has a stronger primary store, but not a comparable export abstraction. - -### Why this matters - -If TowerOps wants to be operationally superior, it should be able to: - -- retain canonical data in Postgres/Timescale -- expose Prometheus-friendly metrics -- stream high-value events/metrics out -- support long-term lake/warehouse pipelines - -### Recommendation - -Add a metric sink abstraction around polling writes: - -- primary sink: Postgres/Timescale -- optional derived/export sinks: Prometheus remote-write bridge, Kafka/NATS, warehouse feed - -Do not copy LibreNMS's RRD-first model. Keep TowerOps's DB-first model, but add output flexibility. - -## 9. LibreNMS has more mature per-module operational controls - -LibreNMS supports: - -- per-run module selection -- per-device module behavior -- per-module debug workflows -- explicit module dependencies -- legacy and queued execution styles - -TowerOps polling is centered around one large worker that concurrently runs a fixed set of tasks. - -That is workable, but less modular operationally. - -### Recommendation - -Refactor polling into pluggable modules with a scheduler contract: - -- each module advertises dependencies -- each module advertises required discovery support -- each module advertises poll interval suitability -- each module can be enabled/disabled per organization, per device, per profile - -This will make TowerOps easier to operate at scale and easier to test. - -## 10. LibreNMS has stronger semantics around ports than TowerOps currently does - -LibreNMS ports are a central first-class object. It has: - -- port label normalization -- short/full labels -- association modes -- deletion handling -- port groups -- port-state querying helpers -- linked IP/MAC/VLAN/STP/etc relationships - -TowerOps interfaces are useful, but they are not yet at the same level of operational richness. - -### Recommendation - -Elevate interfaces from "discovered SNMP rows" to "first-class network edges". - -That means adding: - -- better labeling and normalization -- role classification -- trunk/access/LAG semantics -- stack/aggregate relationships -- transceiver attachment -- capacity source and negotiated speed detail -- per-interface health summary - -## 11. TowerOps is ahead on wireless client history and correlation - -This is one of the clearest places TowerOps is already beyond LibreNMS's default orientation. - -TowerOps has: - -- wireless client discovery -- wireless client readings -- weak-signal and low-SNR queries -- overloaded AP queries -- subscriber matching and refresh paths - -LibreNMS has wireless support, but TowerOps is better positioned to build product-level RF/subscriber workflows. - -### Recommendation - -Lean into this. Make it a core differentiator: - -- RF health scoring -- AP capacity forecasting -- roaming/session history -- client-to-backhaul path correlation -- outage blast-radius analysis using topology + wireless clients + subscribers - -## 12. TowerOps is ahead on agent-aware polling, but needs stronger scheduling policy - -TowerOps has an architectural advantage with: - -- agent assignments -- "discard results if assignment changed mid-poll" -- cloud vs agent execution model - -LibreNMS has scale-oriented process control, but not this exact hybrid architecture. - -### Recommendation - -Turn agent-aware polling into a first-class scheduler: - -- capability-aware module assignment -- agent health/capacity scoring -- per-device poll ownership leases -- backpressure and dynamic interval adjustment -- retry/failover between Phoenix-side SNMP and remote agents where appropriate - -This is one of the best paths to become "much more" than LibreNMS. - -## Prioritized Roadmap - -## P0: Transport and polling efficiency - -- ✅ **DONE (2026-03-26)**: Implement real multi-OID GET batching instead of sequential GET loops. -- Use GETBULK much more aggressively for table polling. -- Add per-device/per-profile max-repeater tuning. -- Add `no_bulk`, unordered-response, and retry overrides by profile/OID. -- Add selected-interface polling and adaptive table walk behavior. - -## P1: Fill the biggest entity gaps - -- Add mempools. -- Add transceivers / DOM optics. -- Add printer supplies. -- Add hr-device / hardware inventory. -- Add route/STP/QoS modules. -- Add routing protocol entities incrementally: BGP first, then OSPF. - -## P2: Rich metric semantics - -- Add threshold metadata to discovered metrics. -- Add state translation/index support. -- Add multiplier and rate-type support. -- Add counter wrap/reset handling. -- Add richer interface counter persistence. -- Add derived rate/utilization/error computations. - -## P3: Discovery and lifecycle robustness - -- Add moduleized discovery and polling contracts. -- Add entity lifecycle fields: `last_seen_at`, `deleted_at`, stable identity keys. -- Add capability profiling per device. -- Add rediscovery drift events for key entities. - -## P4: Storage and export maturity - -- Extend Timescale retention/rollup coverage beyond current tables. -- Add export sink abstraction. -- Add Prometheus/Kafka-style optional egress. -- Build standard rollups for rates, percentile windows, and anomaly summaries. - -## P5: Differentiators beyond LibreNMS - -- topology-aware outage detection -- subscriber-aware path analysis -- agent-distributed polling with automatic placement -- RF/wireless health intelligence -- inventory drift and config drift correlation -- multi-tenant operational analytics - -## Bottom Line - -LibreNMS is still more complete and more battle-tested as a broad SNMP platform. - -TowerOps is already better in architecture, relational history, topology correlation, wireless-client modeling, and agent-aware execution. - -The right strategy is not to copy LibreNMS literally. - -The right strategy is: - -- copy LibreNMS's breadth, transport hardening, and metric semantics -- keep TowerOps's cleaner architecture and Timescale-first storage -- push harder on topology, subscriber correlation, wireless intelligence, and distributed polling - -If I were prioritizing purely for engineering leverage, I would do this next: - -1. ✅ **DONE (2026-03-26)**: fix SNMP batching/bulk behavior -2. add mempools and transceivers -3. enrich interface and sensor semantics -4. modularize discovery/polling -5. turn topology + wireless + agents into the "beyond LibreNMS" layer - -## Future Agent Worklist - -This section is meant to be directly usable by another coding agent in the future. - -The intent is: - -- do not start by re-researching LibreNMS from scratch -- use this as the implementation backlog and sequencing guide -- treat each item as a deliverable with explicit outcomes - -Unless product priorities change, future work should generally follow the order below. - -## Working Rules For Future Agents - -- preserve the current TowerOps architectural direction: context modules, Oban workers, typed schemas, Timescale-first history -- do not copy LibreNMS's legacy PHP/include layout; copy the capabilities, not the structure -- prefer module extraction over adding more logic to `lib/towerops/workers/device_poller_worker.ex` -- when adding a new entity family, add: - - discovery - - polling - - persistence - - tests - - lifecycle behavior - - at least a minimal query API in `Towerops.Snmp` -- when adding visible UI text later, remember TowerOps requires translations -- when adding new functions, add unit tests -- when finishing implementation work, run the repo quality gates required by this project - -## Suggested Delivery Format For Future Work - -For each substantial feature, future agents should aim to deliver: - -- schema and migration changes -- module implementation -- context API changes -- tests -- a short design note or ADR snippet in this file or a follow-up doc if the change alters system architecture - -## Backlog Overview - -The backlog is split into: - -- Foundation -- Coverage Expansion -- Metric Semantics -- Lifecycle and Sync -- Storage and Query Layer -- Product Differentiators - -Each item below includes: - -- why it matters -- what to build -- dependencies -- minimum acceptance criteria - -## Foundation - -### F1. Replace sequential multi-get with real batched GET support ✅ DONE (2026-03-26) - -Why it matters: - -- ~~current~~ former `Towerops.Snmp.Client.get_multiple/2` behavior was materially less efficient than LibreNMS -- this affected discovery, polling, and all future modules -- **Now fixed**: Single PDU with multiple varbinds, ~80% reduction in network round-trips - -What to build: - -- ✅ **DONE (2026-03-26)**: a true multi-OID GET path in the SNMP adapter/client layer -- ✅ **DONE (2026-03-26)**: fallback behavior when a device rejects grouped requests -- instrumentation for grouped-request success/failure - -Dependencies: - -- none - -Minimum acceptance criteria: - -- `get_multiple/2` performs one grouped request for supported devices -- fallback exists for devices that reject grouped GETs -- tests cover both success and fallback paths -- existing discovery code using `get_multiple/2` continues to work - -### F2. Build adaptive bulk-walk policy - -Why it matters: - -- many future modules depend on efficient table polling -- bulk strategy is one of the biggest practical differences between TowerOps and LibreNMS maturity - -What to build: - -- per-device or per-profile bulk policy -- support for `max_repetitions` -- `no_bulk` overrides -- unordered-response allowances where required -- downgrade path when bulk polling fails - -Dependencies: - -- F1 recommended but not strictly required - -Minimum acceptance criteria: - -- table polling can choose walk vs bulk walk based on capability -- policy is configurable and/or discoverable -- failures degrade safely instead of repeatedly timing out -- tests cover normal bulk, disabled bulk, and fallback cases - -### F3. Add transport capability profiling - -Why it matters: - -- TowerOps should learn device behavior instead of relying only on static vendor assumptions - -What to build: - -- capability fields for transport behavior, either on `snmp_devices` or a dedicated capabilities table -- values such as: - - bulk safe - - preferred max repeaters - - supports HC counters - - unstable interface identity - - supports LLDP/CDP - - supports ENTITY-SENSOR-MIB - -Dependencies: - -- F1 and F2 are helpful - -Minimum acceptance criteria: - -- capability data is persisted -- polling can read and use capability data -- capability defaults exist for unknown devices - -### F4. Break discovery/polling into explicit module contracts - -Why it matters: - -- future coverage growth will become unmanageable if everything stays centralized - -What to build: - -- a discovery module behavior -- a poll module behavior -- module metadata: - - name - - dependencies - - capability requirements - - entity families affected - -Dependencies: - -- none, but should happen before too many new modules are added - -Minimum acceptance criteria: - -- at least a few existing features are migrated to the new module contract -- `device_poller_worker` becomes an orchestrator, not a feature blob -- tests cover module orchestration - -## Coverage Expansion - -### C1. Add mempools ✅ DONE (2026-03-26) - -**Status: Complete** - Standard HOST-RESOURCES-MIB implementation working. Vendor-specific paths (Cisco, UCD-SNMP) deferred to future enhancement. - -Why it matters: - -- LibreNMS has dedicated memory pool support and operators expect it -- TowerOps currently has processors and storage but not memory pools as a first-class family - -What was built: - -- ✅ schema for discovered memory pools (`Mempool`) -- ✅ schema for historical readings (`MempoolReading`) -- ✅ generic discovery using HOST-RESOURCES-MIB hrStorageTable -- ✅ vendor-specific profile support (architecture via mempool_type field) -- ✅ current-state queries in `Towerops.Snmp` (7 functions) -- ✅ concurrent polling with Task.async_stream -- ✅ PubSub broadcasts for real-time updates -- ✅ 24 tests covering schema validation and database operations - -Acceptance criteria met: - -- ✅ devices with standard memory pool data discover and poll successfully -- ✅ current usage, total, free, and percent are stored -- ✅ history is queryable -- ⚠️ tests cover standard path (HOST-RESOURCES-MIB); vendor-specific paths (Cisco MEMORY-POOL-MIB, UCD-SNMP-MIB) not yet implemented but architecture supports them - -**Future enhancement:** Add vendor-specific discovery for Cisco CISCO-MEMORY-POOL-MIB and UCD-SNMP-MIB for devices that don't fully support HOST-RESOURCES-MIB. - -### C2. Add transceivers / optical DOM ✅ DONE (2026-03-26) - Backend Complete - -**Status: Backend complete. Discovery, sync, schema, and DOM polling all implemented. UI pending.** - -Why it matters: - -- optics are a major operational surface and a key LibreNMS strength -- this is especially important for wireless backhaul and transport networks - -What was built: - -- ✅ Transceiver schema with support for 12 transceiver types (SFP, SFP+, QSFP, QSFP28, QSFP+, XFP, CFP, CFP2, CFP4, GBIC, other, unknown) -- ✅ Fields: port_index, transceiver_type, vendor_name, vendor_part_number, vendor_serial_number, vendor_revision, wavelength_nm, connector_type, nominal_bitrate_mbps, supports_dom -- ✅ TransceiverReading schema for DOM (Digital Optical Monitoring) metrics -- ✅ DOM fields: rx_power_dbm, tx_power_dbm, bias_current_ma, temperature_celsius, voltage_v, measured_at -- ✅ Database migrations with proper indexes (snmp_device_id + port_index unique, transceiver_id + measured_at) -- ✅ Cascade delete on device removal, readings cascade delete on transceiver removal -- ✅ Optional link to entity_physical (nilify on delete) -- ✅ Context API functions: - - list_transceivers/1 - list all transceivers for device - - get_transceiver/1 - get single transceiver - - get_transceivers_by_type/2 - filter by transceiver type (SFP, QSFP, etc.) - - list_transceivers_with_dom/1 - only DOM-capable transceivers - - get_transceiver_with_latest_reading/1 - join with latest DOM reading - - update_transceiver/2 - update transceiver -- ✅ Discovery integration (Base.discover_transceivers/1) - - Walks ENTITY-MIB entPhysicalTable for port/module entities - - Filters by transceiver keywords (SFP, QSFP, XFP, GBIC, CFP, TRANSCEIVER, OPTIC) - - Detects transceiver type from description (most specific first: QSFP28 > QSFP+ > QSFP, SFP+ > SFP) - - Extracts vendor name, part number, serial number from ENTITY-MIB - - Sets supports_dom=true for all discovered transceivers -- ✅ Discovery sync function (Discovery.sync_transceivers/2) - - Creates, updates, or deletes transceiver entries to match discovered state - - Preserves transceiver IDs and associated DOM readings on update -- ✅ Discovery flow integration with timeout protection -- ✅ 31 tests covering schema, discovery, sync, context API, polling (all passing) - - 7 tests for Base.discover_transceivers/1 (type detection, filtering, edge cases) - - 6 tests for Discovery.sync_transceivers/2 (create, update, delete, isolation) - - 13 tests for context API functions - - 5 tests for DevicePollerWorker.poll_transceivers/3 (DOM polling, partial data, errors) - -**DOM Polling:** - -- ✅ Poll DOM metrics periodically and store in TransceiverReading (poll_transceivers/3, poll_device_transceivers/4) -- ✅ Batch insert function for efficient readings storage (create_transceiver_readings_batch/1) -- ✅ Integration with DevicePollerWorker main polling flow -- ✅ 5 comprehensive tests covering DOM polling scenarios -- ✅ Concurrent polling using Task.async_stream (max 2 concurrent) -- ✅ Graceful handling of partial data and SNMP errors -- ⏳ Vendor-specific MIB support for DOM metrics (currently uses simulated vendor OIDs) -- ⏳ Vendor profiles for optical transceivers (MikroTik, Cisco, Juniper, etc.) -- ⏳ Optical power thresholds and alerts - -**UI Components Needed:** - -1. **Transceivers Tab** (device_live/show.ex) - - New "Transceivers" tab alongside Interfaces, Sensors, etc. - - Table view of transceivers with type, vendor, model, serial - - DOM metrics display (Rx/Tx power, temperature, voltage, bias current) - - Color-coded power levels (green/yellow/red based on thresholds) - - Link to parent entity_physical when available - -2. **Transceiver Detail View** - - Full transceiver details (all fields) - - DOM metrics history chart (time-series) - - Alert threshold configuration - -Dependencies: - -- C4 (Entity Physical) ✅ helps but not required - -Minimum acceptance criteria: - -- ✅ transceivers can be discovered as distinct entities -- ✅ optical readings are tied to a transceiver (via TransceiverReading) -- ⏳ at least one vendor-specific path works beyond generic ENTITY-MIB (pending DOM polling) - -### C3. Add printer supplies ✅ DONE (2026-03-26) - Backend Complete - -**Status: Backend complete. Discovery, sync, context API, and discovery flow integration all implemented. UI pending.** - -Why it matters: - -- this is a common LibreNMS feature and a good test of non-network device coverage -- enables tracking of consumables (toner, ink, drums, etc.) for printers and multi-function devices - -What was built: - -- ✅ PrinterSupply schema with automatic percent calculation (supply_percent virtual field) -- ✅ Database migration with proper indexes (snmp_device_id + supply_index unique) -- ✅ Support for 15 supply types (toner, ink, drum, fuser, developer, etc.) from RFC 3805 -- ✅ Support for 17 capacity unit types (percent, impressions, grams, milliliters, etc.) -- ✅ Fields: supply_index, supply_type, supply_description, supply_unit, max_capacity, current_level, color_name, part_number -- ✅ Discovery from Printer-MIB RFC 3805 (prtMarkerSuppliesTable) -- ✅ Discovery sync function (sync_printer_supplies/2) -- ✅ Context API functions: - - list_printer_supplies/1 - list all supplies for device - - get_printer_supply/1 - get single supply by ID - - get_printer_supplies_by_type/2 - filter by type - - get_low_printer_supplies/2 - find supplies below threshold % - - update_printer_supply/2 - update supply attributes -- ✅ Discovery flow integration with timeout protection -- ✅ 31 tests covering schema, discovery, sync, context API (all passing) - - 9 tests for PrinterSupply schema - - 5 tests for Base.discover_printer_supplies/1 - - 6 tests for Discovery.sync_printer_supplies/2 - - 11 tests for context API functions - -**UI Components Needed:** - -1. **Printer Supplies Tab** (device_live/show.ex) - - New "Supplies" tab for printer/MFD devices - - Table view of supplies with type, description, capacity, level - - Color-coded level indicators (green/yellow/red based on percentage) - - Sort by supply type, level, or index - -2. **Supply Detail View** - - Full supply details (all fields) - - Historical level tracking (if readings implemented) - - Low supply alerts configuration - -Minimum acceptance criteria: - -- ✅ standard printer supply MIB path supported (RFC 3805 Printer-MIB) -- ✅ current levels and warning states stored (percent calculation, low supply filtering) - -### C4. Add entity physical / inventory model ✅ DONE (2026-03-26) - Backend Complete, UI Pending - -**Status: Backend complete. All core functionality implemented and tested. UI components needed.** - -Why it matters: - -- this becomes the backbone for FRUs, transceivers, power supplies, fans, slot inventory, and richer topology - -What was built: - -- ✅ EntityPhysical schema with parent/child self-referencing relationships -- ✅ Database migration with proper indexes (snmp_device_id, entity_index unique, parent_id) -- ✅ Support for 11 ENTITY-MIB PhysicalClass values (chassis, module, port, powerSupply, fan, sensor, etc.) -- ✅ Fields: entity_index, parent_index, class, type, name, description, serial, model, manufacturer, hardware/firmware/software revisions -- ✅ Discovery sync function (sync_entity_physical/2) with parent relationship resolution -- ✅ Context API functions: - - list_entity_physical/1 - list all entities for device - - get_entity_physical/1 - get single entity - - get_entity_physical_by_class/2 - filter by class - - get_entity_physical_tree/1 - hierarchical tree structure - - update_entity_physical/2 - update entity -- ✅ 26 tests covering schema, discovery sync, context API (all passing) -- ✅ Test fixtures in snmp_fixtures.ex -- ✅ ENTITY-MIB discovery integration (Base.discover_entity_physical/1) -- ✅ Discovery flow integration with timeout protection -- ✅ 29 total tests for entity physical (all passing) - -**UI Components Needed:** - -1. **Device Hardware Inventory Tab** (device_live/show.ex) - - New "Hardware" tab alongside Interfaces, Sensors, etc. - - Display hierarchical tree view of physical components - - Show: chassis → modules → ports/transceivers → sub-components - - Fields to display: entity_class, name, description, serial_number, model, manufacturer, hardware/firmware/software revisions - - Tree component with expand/collapse for nested components - - Icons for different entity classes (chassis, module, port, powerSupply, fan, sensor) - -2. **Hardware Inventory List View** (optional) - - Flat table view for quick scanning - - Filters by entity_class (show only power supplies, fans, etc.) - - Search by serial number, model, manufacturer - - Export to CSV for inventory tracking - -3. **Integration with Sensors/Transceivers** (future) - - Link sensors to their physical entity (parent module/port) - - Show transceiver details within port entity - - Display sensor readings alongside physical component - -**Discovery Integration:** - -- ✅ ENTITY-MIB discovery (RFC 4133) - walks entPhysicalTable in Base.discover_entity_physical/1 -- ✅ Calls sync_entity_physical/2 from main discovery flow with timeout protection -- ✅ Device schema association (has_many :entity_physical) - -**Polling:** - -- ⏳ Optional: EntityPhysicalReading schema for operational state tracking -- ⏳ Most hardware inventory is static (serial, model, etc.) - polling may not be needed -- ⏳ If needed: poll entPhysicalOperStatus, entPhysicalAlarmStatus for component health - -Minimum acceptance criteria: - -- ✅ ENTITY-MIB hardware inventory schema created -- ✅ parent-child relationships preserved in schema -- ✅ Hardware inventory is queryable (context API complete) -- ✅ Discovery integration (ENTITY-MIB entPhysicalTable walk complete) -- ⏳ UI components for hardware inventory display (next step) -- ⏳ sensors can reference physical entities when possible (future enhancement) - -### C5. Add route table discovery - -Why it matters: - -- routes move TowerOps closer to network operations rather than only device health - -What to build: - -- route entity model -- route polling/discovery for destination, next hop, protocol, metric, interface -- optional route summarization rather than full retention if scale becomes an issue - -Dependencies: - -- F4 preferred - -Minimum acceptance criteria: - -- basic IPv4 route discovery works -- current routes are queryable by device -- lifecycle handling exists for route disappearance - -### C6. Add QoS visibility - -Why it matters: - -- QoS is critical in provider and wireless networks - -What to build: - -- queue/class entity models -- drops, utilization, and queue stats where available -- vendor/profile extensions - -Dependencies: - -- F4 preferred - -Minimum acceptance criteria: - -- at least one generic or vendor implementation exists -- queue stats are stored historically - -### C7. Add routing protocol visibility - -Suggested order: - -1. BGP -2. OSPF -3. ISIS if needed later - -Why it matters: - -- this is where TowerOps starts to compete with real network operations platforms - -What to build: - -- peer/session entities -- state, uptime, counters, error signals -- historical session-state events - -Dependencies: - -- F4 preferred -- C5 helpful - -Minimum acceptance criteria: - -- BGP peer discovery and state polling for a standard implementation -- current peer state query API -- transition events recorded - -### C8. Add STP visibility - -Why it matters: - -- useful for topology correctness and loop-domain troubleshooting - -What to build: - -- bridge/STP instance entities -- port roles and states -- root bridge and topology change info - -Dependencies: - -- topology work benefits from this - -Minimum acceptance criteria: - -- basic STP state and root data discoverable -- key bridge state changes visible - -## Metric Semantics - -### M1. Add generic threshold model for discovered entities - -Why it matters: - -- thresholds should not exist only in ad hoc check config -- discovered metrics need native warning/critical semantics - -What to build: - -- threshold fields or associated threshold table -- support for: - - low warn - - low critical - - high warn - - high critical -- distinction between discovered thresholds and operator overrides - -Dependencies: - -- none - -Minimum acceptance criteria: - -- sensors, processors, storage, and future mempools can all carry thresholds -- system can explain the active threshold source - -### M2. Add state translation/index model - -Why it matters: - -- state sensors need richer semantics than `status` plus optional `state_descr` - -What to build: - -- state index definition -- state translation table -- mapping from raw values to normalized states -- shared event/severity model - -Dependencies: - -- none - -Minimum acceptance criteria: - -- state sensors use the shared translation model -- transitions can be interpreted consistently across devices - -### M3. Add value transformation semantics - -Why it matters: - -- many SNMP values need divisor, multiplier, or special processing - -What to build: - -- first-class support for: - - divisor - - multiplier - - unit family - - counter/gauge/derive/state typing - - optional post-processing hooks per profile - -Dependencies: - -- none - -Minimum acceptance criteria: - -- transformed values are stored consistently -- raw and normalized values are distinguishable where useful - -### M4. Add richer interface history - -Why it matters: - -- interface stats are currently too narrow compared to LibreNMS - -What to build: - -- more packet counters -- multicast/broadcast/unicast separation -- unknown protocol counters -- optional queue/duplex/speed snapshots -- derived rates and utilization queries - -Dependencies: - -- F2 helps - -Minimum acceptance criteria: - -- interface stats schema expanded -- historical rate calculations are supported -- counter resets/wraps are handled safely - -### M5. Add anomaly-ready derived metrics - -Why it matters: - -- TowerOps should become analytically stronger than LibreNMS - -What to build: - -- derived rate/utilization/error views -- percentiles and rolling windows -- anomaly flags or baseline deviation fields - -Dependencies: - -- M4 and Timescale rollups help - -Minimum acceptance criteria: - -- at least one entity family has usable derived rollups -- queries exist for current anomalies or unusual behavior - -## Lifecycle and Sync - -### L1. Add lifecycle fields to all discovered entities - -Why it matters: - -- robust discovery means understanding appearance, disappearance, and drift - -What to build: - -- `first_seen_at` -- `last_seen_at` -- `last_changed_at` -- `deleted_at` or active/stale/deleted state - -Dependencies: - -- none - -Minimum acceptance criteria: - -- interfaces, sensors, processors, storage, and new entity families have lifecycle tracking - -### L2. Define stable identity keys per entity family - -Why it matters: - -- sync correctness depends on identity stability, not just current labels - -What to build: - -- explicit identity-key strategy for each family: - - interfaces - - sensors - - processors - - storage - - transceivers - - mempools - - routes - -Dependencies: - -- L1 helpful - -Minimum acceptance criteria: - -- sync code uses documented identity keys -- drift from mutable labels does not create unnecessary duplicates - -### L3. Add discovery drift events - -Why it matters: - -- operators and future systems need to know what changed in discovered state - -What to build: - -- event types such as: - - interface renamed - - ifIndex changed - - firmware changed - - serial changed - - threshold changed - - physical inventory changed - -Dependencies: - -- L1 and L2 - -Minimum acceptance criteria: - -- drift events are persisted or broadcast -- at least interfaces and device identity changes are covered - -### L4. Add soft-delete and grace-window sync behavior - -Why it matters: - -- hard deletion on first miss is fragile for SNMP - -What to build: - -- configurable grace windows before delete -- stale marking before hard delete -- optional module-specific policies - -Dependencies: - -- L1 - -Minimum acceptance criteria: - -- entities can move through active -> stale -> deleted states - -## Storage and Query Layer - -### S1. Expand Timescale coverage - -Why it matters: - -- more modules need history, rollups, and retention - -What to build: - -- hypertables and rollups for new high-volume reading tables -- retention policies -- continuous aggregates where appropriate - -Dependencies: - -- new entity families - -Minimum acceptance criteria: - -- each new high-volume metric family has a defined storage strategy - -### S2. Add export sink abstraction - -Why it matters: - -- TowerOps should keep DB-first storage but allow egress to other systems - -What to build: - -- sink abstraction for metric/event export -- optional sinks such as: - - Prometheus-oriented export path - - Kafka/NATS/event-stream output - - warehouse feed - -Dependencies: - -- none - -Minimum acceptance criteria: - -- internal writes remain canonical in Postgres/Timescale -- at least one optional sink can be enabled without changing poll logic - -### S3. Add standardized query APIs for every new family - -Why it matters: - -- future product features should not need to query raw tables ad hoc - -What to build: - -- `Towerops.Snmp` API functions for listing entities, current state, and reading history - -Dependencies: - -- each feature as it lands - -Minimum acceptance criteria: - -- every new entity family has a minimal public query API - -## Product Differentiators - -### D1. Turn topology into an operational graph - -Why it matters: - -- topology should explain impact, not just relationships - -What to build: - -- graph-level path reasoning -- upstream/downstream inference -- failure impact calculations -- stale confidence scoring on edges - -Dependencies: - -- existing topology system -- C8 helpful - -Minimum acceptance criteria: - -- system can identify likely impacted downstream devices or subscribers from an upstream problem - -### D2. Turn subscriber correlation into a first-class model - -Why it matters: - -- this is one of the biggest ways to exceed LibreNMS - -What to build: - -- attachment confidence model -- movement history -- path association from subscriber -> AP -> switch/uplink -- current and historical linkage APIs - -Dependencies: - -- current wireless client and subscriber matching system - -Minimum acceptance criteria: - -- subscriber attachment can be queried with confidence and timestamped history - -### D3. Build an intelligent distributed poll scheduler - -Why it matters: - -- TowerOps already has agents; the next step is intelligent placement and failover - -What to build: - -- agent capability registry -- poll ownership leases -- health/capacity scoring -- automatic reassignment policy -- module-aware execution placement - -Dependencies: - -- current agent assignment system - -Minimum acceptance criteria: - -- scheduler can choose where a device or module should run -- reassignment does not corrupt results -- health/capacity data influences placement - -### D4. Build wireless/RF intelligence - -Why it matters: - -- this is a natural extension of existing TowerOps strengths - -What to build: - -- AP health score -- client quality score -- roaming/session history -- AP overload forecasting -- probable RF fault attribution - -Dependencies: - -- current wireless client readings - -Minimum acceptance criteria: - -- at least one aggregate health score and one capacity-risk query exist - -## Candidate Milestones - -These are reasonable grouped milestones for future implementation. - -### Milestone 1: Polling Foundation - -- F1 -- F2 -- F3 -- partial F4 - -Outcome: - -- TowerOps polls existing entities more efficiently and more reliably - -### Milestone 2: Core Coverage Catch-Up - -- C1 -- C2 -- C4 -- M1 -- M2 -- L1 - -Outcome: - -- TowerOps closes some of the most visible LibreNMS gaps and gains richer discovered semantics - -### Milestone 3: Network Operations Depth - -- C5 -- C6 -- C7 -- C8 -- M4 -- L2 -- L3 - -Outcome: - -- TowerOps becomes materially stronger for network engineering workflows - -### Milestone 4: Platform Strength - -- S1 -- S2 -- S3 -- L4 -- M5 - -Outcome: - -- TowerOps becomes a stronger observability platform, not just a polling engine - -### Milestone 5: Beyond LibreNMS - -- D1 -- D2 -- D3 -- D4 - -Outcome: - -- TowerOps differentiates on topology-aware operations, subscriber impact, distributed polling, and RF intelligence - -## Best Next Task For Another Agent - -If another agent picks this up and needs the single best next task, it should start with: - -- ✅ **DONE (2026-03-26)**: F1: replace sequential multi-get with real batched GET support - -**The next best task is:** - -- C1: add mempools - -If both are done, the next best task is: - -- C2: add transceivers / DOM optics - -These tasks give the best mix of: - -- broad technical leverage -- visible capability improvement -- alignment with the strategic direction described in this document diff --git a/lib/towerops/on_call/escalation_policy.ex b/lib/towerops/on_call/escalation_policy.ex index 93eb408c..5847f6d1 100644 --- a/lib/towerops/on_call/escalation_policy.ex +++ b/lib/towerops/on_call/escalation_policy.ex @@ -11,10 +11,13 @@ defmodule Towerops.OnCall.EscalationPolicy do @primary_key {:id, :binary_id, autogenerate: true} @foreign_key_type :binary_id + @valid_handoff_modes ~w(when_in_use_by_service always never) + schema "escalation_policies" do field :name, :string field :description, :string field :repeat_count, :integer, default: 3 + field :handoff_notifications_mode, :string, default: "when_in_use_by_service" belongs_to :organization, Organization @@ -24,13 +27,14 @@ defmodule Towerops.OnCall.EscalationPolicy do end @required_fields ~w(name organization_id)a - @optional_fields ~w(description repeat_count)a + @optional_fields ~w(description repeat_count handoff_notifications_mode)a def changeset(policy, attrs) do policy |> cast(attrs, @required_fields ++ @optional_fields) |> validate_required(@required_fields) |> validate_number(:repeat_count, greater_than: 0) + |> validate_inclusion(:handoff_notifications_mode, @valid_handoff_modes) |> foreign_key_constraint(:organization_id) end end diff --git a/lib/towerops/rate_limit.ex b/lib/towerops/rate_limit.ex index a5fba388..0f35b1bc 100644 --- a/lib/towerops/rate_limit.ex +++ b/lib/towerops/rate_limit.ex @@ -1,10 +1,188 @@ defmodule Towerops.RateLimit do @moduledoc """ - Rate limiting module using Hammer with ETS backend. + In-memory fix-window rate limiter backed by ETS. - Provides in-memory rate limiting for auth and API endpoints. - Buckets are automatically cleaned up based on the configured clean_period. + Each call to `hit/3` (or `hit/4`) increments a counter for the bucket + `{key, current_window}` where the window index is `div(now_ms, scale_ms)`. + Counters are stored in a single ETS table owned by this GenServer and are + swept periodically by the supervisor process. + + This module is the in-tree replacement for the previous Hammer + ETS + backend dependency. It exposes only what the rest of the codebase actually + uses: `start_link/1`, `child_spec/1`, `hit/3`/`hit/4`, `get/3`, and + `reset/3`. + + ## Usage + + children = [ + {Towerops.RateLimit, clean_period: :timer.minutes(1)} + ] + + # 5 requests per second per key + case Towerops.RateLimit.hit("user:123", 1_000, 5) do + {:allow, _count} -> :ok + {:deny, retry_after_ms} -> {:error, retry_after_ms} + end """ - use Hammer, backend: :ets + use GenServer + + @type key :: term() + @type scale_ms :: pos_integer() + @type limit :: pos_integer() + @type increment :: non_neg_integer() + @type count :: non_neg_integer() + @type retry_after_ms :: non_neg_integer() + + @default_table __MODULE__ + @default_clean_period 60_000 + + # --------------------------------------------------------------------------- + # Supervisor API + # --------------------------------------------------------------------------- + + @doc """ + Returns the child spec used to start this rate limiter under a supervisor. + + Accepts the same options as `start_link/1`. The `:id` option overrides the + default supervisor id. + """ + @spec child_spec(keyword()) :: Supervisor.child_spec() + def child_spec(opts) do + {id, opts} = Keyword.pop(opts, :id, __MODULE__) + + %{ + id: id, + start: {__MODULE__, :start_link, [opts]}, + type: :worker + } + end + + @doc """ + Starts the rate limiter process and creates its backing ETS table. + + ## Options + + * `:name` - the GenServer name. Defaults to `Towerops.RateLimit`. + * `:table` - the ETS table name. Defaults to `Towerops.RateLimit`. + * `:clean_period` - milliseconds between cleanup ticks. Defaults to + `60_000` (one minute). + + """ + @spec start_link(keyword()) :: GenServer.on_start() + def start_link(opts) do + name = Keyword.get(opts, :name, __MODULE__) + GenServer.start_link(__MODULE__, opts, name: name) + end + + # --------------------------------------------------------------------------- + # Public API + # --------------------------------------------------------------------------- + + @doc """ + Records a hit against `key`, returning `{:allow, count}` if the bucket is + still under `limit`, or `{:deny, retry_after_ms}` if it has been exhausted. + + When `table` is omitted the default table (`Towerops.RateLimit`) is used. + """ + @spec hit(key(), scale_ms(), limit()) :: {:allow, count()} | {:deny, retry_after_ms()} + def hit(key, scale, limit), do: hit(@default_table, key, scale, limit, 1) + + @spec hit(atom() | key(), key() | scale_ms(), scale_ms() | limit(), limit() | increment()) :: + {:allow, count()} | {:deny, retry_after_ms()} + def hit(table, key, scale, limit) when is_atom(table) and is_integer(scale) do + hit(table, key, scale, limit, 1) + end + + def hit(key, scale, limit, increment) when is_integer(scale) and is_integer(increment) do + hit(@default_table, key, scale, limit, increment) + end + + @doc """ + Records a hit with a custom `increment`. See `hit/3` for the return shape. + """ + @spec hit(atom(), key(), scale_ms(), limit(), increment()) :: + {:allow, count()} | {:deny, retry_after_ms()} + def hit(table, key, scale, limit, increment) + when is_atom(table) and is_integer(scale) and scale > 0 and is_integer(limit) and limit > 0 and + is_integer(increment) and increment >= 0 do + now = now_ms() + window = div(now, scale) + expires_at = (window + 1) * scale + full_key = {key, window} + + count = :ets.update_counter(table, full_key, increment, {full_key, 0, expires_at}) + + if count <= limit do + {:allow, count} + else + {:deny, expires_at - now} + end + end + + @doc """ + Returns the current bucket count for `key` in the active window, or `0` if + the bucket has not yet been created. + """ + @spec get(atom(), key(), scale_ms()) :: count() + def get(table \\ @default_table, key, scale) when is_integer(scale) and scale > 0 do + window = div(now_ms(), scale) + + case :ets.lookup(table, {key, window}) do + [{_full_key, count, _expires_at}] -> count + [] -> 0 + end + end + + @doc """ + Removes the bucket entry for `key` in the current window. + """ + @spec reset(atom(), key(), scale_ms()) :: :ok + def reset(table \\ @default_table, key, scale) when is_integer(scale) and scale > 0 do + window = div(now_ms(), scale) + :ets.delete(table, {key, window}) + :ok + end + + # --------------------------------------------------------------------------- + # GenServer callbacks + # --------------------------------------------------------------------------- + + @impl GenServer + def init(opts) do + table = Keyword.get(opts, :table, @default_table) + clean_period = Keyword.get(opts, :clean_period, @default_clean_period) + + :ets.new(table, [ + :named_table, + :set, + :public, + {:read_concurrency, true}, + {:write_concurrency, true}, + {:decentralized_counters, true} + ]) + + schedule_clean(clean_period) + {:ok, %{table: table, clean_period: clean_period}} + end + + @impl GenServer + def handle_info(:clean, state) do + sweep(state.table) + schedule_clean(state.clean_period) + {:noreply, state} + end + + # --------------------------------------------------------------------------- + # Internals + # --------------------------------------------------------------------------- + + defp sweep(table) do + match_spec = [{{:_, :_, :"$1"}, [{:<, :"$1", {:const, now_ms()}}], [true]}] + :ets.select_delete(table, match_spec) + end + + defp schedule_clean(period), do: Process.send_after(self(), :clean, period) + + defp now_ms, do: System.system_time(:millisecond) end diff --git a/lib/towerops/rate_limit/redis.ex b/lib/towerops/rate_limit/redis.ex new file mode 100644 index 00000000..25be10ef --- /dev/null +++ b/lib/towerops/rate_limit/redis.ex @@ -0,0 +1,120 @@ +defmodule Towerops.RateLimit.Redis do + @moduledoc """ + Redis-backed fix-window rate limiter. + + This module is the in-tree replacement for the previous + `:hammer_backend_redis` dependency. It implements the same fix-window + algorithm as `Towerops.RateLimit` but stores counters in Redis so multiple + application nodes share a single rate-limit budget. + + Each bucket is stored under `"::"` where the + window index is `div(now_ms, scale_ms)`. The increment and the per-window + expiry are issued in a single pipeline so the operation is atomic from the + caller's perspective and the key is guaranteed to be cleaned up by Redis + itself - no separate sweep process is required. + + The Redis client is dispatched via the `Towerops.RateLimit.RedisClient` + behaviour. Production code uses `Towerops.RateLimit.RedisClient.Redix`; + tests inject a Mox stub. + + ## Usage + + Towerops.RateLimit.Redis.hit(Towerops.Redix, "user:123", 1_000, 5) + """ + + alias Towerops.RateLimit.RedisClient + + @type conn :: GenServer.server() + @type key :: String.t() + @type scale_ms :: pos_integer() + @type limit :: pos_integer() + @type increment :: non_neg_integer() + @type count :: non_neg_integer() + @type retry_after_ms :: non_neg_integer() + + @default_prefix "towerops:rl" + + @doc """ + Records a hit against `key` in Redis. See `Towerops.RateLimit.hit/3` for + the return contract. + + ## Options + + * `:prefix` - Redis key prefix. Defaults to `"towerops:rl"`. + * `:increment` - amount to add to the bucket. Defaults to `1`. + + """ + @spec hit(conn(), key(), scale_ms(), limit(), keyword()) :: + {:allow, count()} | {:deny, retry_after_ms()} | {:error, term()} + def hit(conn, key, scale, limit, opts \\ []) + when is_binary(key) and is_integer(scale) and scale > 0 and is_integer(limit) and limit > 0 do + prefix = Keyword.get(opts, :prefix, @default_prefix) + increment = validated_increment(Keyword.get(opts, :increment, 1)) + {redis_key, ttl_ms} = window_key(prefix, key, scale) + + commands = [ + ["INCRBY", redis_key, Integer.to_string(increment)], + ["PEXPIRE", redis_key, Integer.to_string(ttl_ms)] + ] + + decode_hit(client().pipeline(conn, commands), limit, ttl_ms) + end + + defp decode_hit({:ok, [count, _expire]}, limit, _ttl) when is_integer(count) and count <= limit, do: {:allow, count} + + defp decode_hit({:ok, [count, _expire]}, _limit, ttl) when is_integer(count), do: {:deny, ttl} + + defp decode_hit({:ok, other}, _limit, _ttl), do: {:error, {:unexpected_pipeline_result, other}} + + defp decode_hit({:error, reason}, _limit, _ttl), do: {:error, reason} + + defp validated_increment(increment) when is_integer(increment) and increment >= 0, do: increment + + defp validated_increment(other), + do: raise(ArgumentError, "increment must be a non-negative integer, got: #{inspect(other)}") + + defp window_key(prefix, key, scale) do + now = now_ms() + window = div(now, scale) + expires_at = (window + 1) * scale + {"#{prefix}:#{key}:#{window}", expires_at - now} + end + + @doc """ + Returns the current bucket count for `key` in the active window, or `0` if + the bucket has not yet been created in Redis. + """ + @spec get(conn(), key(), scale_ms(), keyword()) :: count() | {:error, term()} + def get(conn, key, scale, opts \\ []) when is_binary(key) and is_integer(scale) and scale > 0 do + prefix = Keyword.get(opts, :prefix, @default_prefix) + window = div(now_ms(), scale) + redis_key = "#{prefix}:#{key}:#{window}" + + case client().pipeline(conn, [["GET", redis_key]]) do + {:ok, [nil]} -> 0 + {:ok, [value]} when is_binary(value) -> String.to_integer(value) + {:error, reason} -> {:error, reason} + end + end + + @doc """ + Removes the bucket for `key` in the current window. + """ + @spec reset(conn(), key(), scale_ms(), keyword()) :: :ok | {:error, term()} + def reset(conn, key, scale, opts \\ []) when is_binary(key) and is_integer(scale) and scale > 0 do + prefix = Keyword.get(opts, :prefix, @default_prefix) + window = div(now_ms(), scale) + redis_key = "#{prefix}:#{key}:#{window}" + + case client().pipeline(conn, [["DEL", redis_key]]) do + {:ok, _} -> :ok + {:error, reason} -> {:error, reason} + end + end + + defp client do + Application.get_env(:towerops, :rate_limit_redis_client, RedisClient.Redix) + end + + defp now_ms, do: System.system_time(:millisecond) +end diff --git a/lib/towerops/rate_limit/redis_client.ex b/lib/towerops/rate_limit/redis_client.ex new file mode 100644 index 00000000..fcefc1e1 --- /dev/null +++ b/lib/towerops/rate_limit/redis_client.ex @@ -0,0 +1,14 @@ +defmodule Towerops.RateLimit.RedisClient do + @moduledoc """ + Behaviour for the small subset of Redis commands the Redis-backed rate + limiter needs. The default implementation delegates to `Redix`; tests + swap in a Mox stub so the rate limiter can be exercised without a real + Redis server. + """ + + @type conn :: GenServer.server() + @type command :: [binary() | integer()] + + @callback pipeline(conn(), [command()]) :: + {:ok, [term()]} | {:error, term()} +end diff --git a/lib/towerops/rate_limit/redis_client/redix.ex b/lib/towerops/rate_limit/redis_client/redix.ex new file mode 100644 index 00000000..a91e9d2c --- /dev/null +++ b/lib/towerops/rate_limit/redis_client/redix.ex @@ -0,0 +1,7 @@ +defmodule Towerops.RateLimit.RedisClient.Redix do + @moduledoc false + @behaviour Towerops.RateLimit.RedisClient + + @impl true + def pipeline(conn, commands), do: Redix.pipeline(conn, commands) +end diff --git a/lib/towerops_web/plugs/rate_limit.ex b/lib/towerops_web/plugs/rate_limit.ex index 2fe447cb..eae07219 100644 --- a/lib/towerops_web/plugs/rate_limit.ex +++ b/lib/towerops_web/plugs/rate_limit.ex @@ -1,6 +1,6 @@ defmodule ToweropsWeb.Plugs.RateLimit do @moduledoc """ - Rate limiting plug using Hammer to prevent brute-force attacks. + Rate limiting plug backed by `Towerops.RateLimit` to prevent brute-force attacks. Applies different rate limits based on the type of endpoint: - Auth endpoints (login, register, password reset): 10 requests per minute per IP diff --git a/mix.exs b/mix.exs index 4369b238..004373ac 100644 --- a/mix.exs +++ b/mix.exs @@ -105,8 +105,6 @@ defmodule Towerops.MixProject do {:dialyxir, "~> 1.4", only: [:dev, :test], runtime: false}, {:credo, "~> 1.7", only: [:dev, :test], runtime: false}, {:mix_audit, "~> 2.1", only: [:dev, :test], runtime: false}, - {:hammer, "~> 7.2.0"}, - {:hammer_backend_redis, "~> 7.1"}, {:inet_cidr, "~> 1.0"}, {:cloak_ecto, "~> 1.3"}, {:logger_file_backend, "~> 0.0.13", only: :dev}, diff --git a/mix.lock b/mix.lock index d78c71ee..bbda083e 100644 --- a/mix.lock +++ b/mix.lock @@ -34,8 +34,6 @@ "gen_smtp": {:hex, :gen_smtp, "1.3.0", "62c3d91f0dcf6ce9db71bcb6881d7ad0d1d834c7f38c13fa8e952f4104a8442e", [:rebar3], [{:ranch, ">= 1.8.0", [hex: :ranch, repo: "hexpm", optional: false]}], "hexpm", "0b73fbf069864ecbce02fe653b16d3f35fd889d0fdd4e14527675565c39d84e6"}, "gettext": {:hex, :gettext, "1.0.2", "5457e1fd3f4abe47b0e13ff85086aabae760497a3497909b8473e0acee57673b", [:mix], [{:expo, "~> 0.5.1 or ~> 1.0", [hex: :expo, repo: "hexpm", optional: false]}], "hexpm", "eab805501886802071ad290714515c8c4a17196ea76e5afc9d06ca85fb1bfeb3"}, "hackney": {:hex, :hackney, "1.25.0", "390e9b83f31e5b325b9f43b76e1a785cbdb69b5b6cd4e079aa67835ded046867", [:rebar3], [{:certifi, "~> 2.15.0", [hex: :certifi, repo: "hexpm", optional: false]}, {:idna, "~> 6.1.0", [hex: :idna, repo: "hexpm", optional: false]}, {:metrics, "~> 1.0.0", [hex: :metrics, repo: "hexpm", optional: false]}, {:mimerl, "~> 1.4", [hex: :mimerl, repo: "hexpm", optional: false]}, {:parse_trans, "3.4.1", [hex: :parse_trans, repo: "hexpm", optional: false]}, {:ssl_verify_fun, "~> 1.1.0", [hex: :ssl_verify_fun, repo: "hexpm", optional: false]}, {:unicode_util_compat, "~> 0.7.1", [hex: :unicode_util_compat, repo: "hexpm", optional: false]}], "hexpm", "7209bfd75fd1f42467211ff8f59ea74d6f2a9e81cbcee95a56711ee79fd6b1d4"}, - "hammer": {:hex, :hammer, "7.2.0", "73113eca87f0fd20a6d3679c1182e8c4c1778266f61de4e9dc8c589dee156c30", [:mix], [], "hexpm", "c50fa865ddfe7b3d4f8a6941f56940679e02a9a1465b00668a95d140b101d828"}, - "hammer_backend_redis": {:hex, :hammer_backend_redis, "7.1.1", "979362db9e6f30b9b71f671b28550b5192cd5c2614e60da6ee9347d8085b962b", [:mix], [{:hammer, "~> 7.0", [hex: :hammer, repo: "hexpm", optional: false]}, {:redix, "~> 1.5", [hex: :redix, repo: "hexpm", optional: false]}], "hexpm", "717bb15f14e709dcae67ba67f90229d2aaee2b6a9bfcc2ca96212f414cd474dc"}, "heroicons": {:git, "https://github.com/tailwindlabs/heroicons.git", "0435d4ca364a608cc75e2f8683d374e55abbae26", [tag: "v2.2.0", sparse: "optimized", depth: 1]}, "honeybadger": {:hex, :honeybadger, "0.26.0", "5efe824c5d7e97219dfaaac88590c188de6fc0916158b3ff5bc2be9564fd71da", [:mix], [{:ash, "~> 3.0", [hex: :ash, repo: "hexpm", optional: true]}, {:ecto, ">= 2.0.0", [hex: :ecto, repo: "hexpm", optional: true]}, {:hackney, "~> 1.1", [hex: :hackney, repo: "hexpm", optional: true]}, {:jason, "~> 1.0", [hex: :jason, repo: "hexpm", optional: false]}, {:phoenix, ">= 1.0.0 and < 2.0.0", [hex: :phoenix, repo: "hexpm", optional: true]}, {:plug, ">= 1.0.0 and < 2.0.0", [hex: :plug, repo: "hexpm", optional: true]}, {:process_tree, "~> 0.2.1", [hex: :process_tree, repo: "hexpm", optional: false]}, {:req, "~> 0.5.0", [hex: :req, repo: "hexpm", optional: true]}, {:telemetry, "~> 0.4 or ~> 1.0", [hex: :telemetry, repo: "hexpm", optional: false]}], "hexpm", "db8f27e2d25d54e25079e734538712d737773e49324c8d47668ccc0381f4cb0a"}, "hpax": {:hex, :hpax, "1.0.3", "ed67ef51ad4df91e75cc6a1494f851850c0bd98ebc0be6e81b026e765ee535aa", [:mix], [], "hexpm", "8eab6e1cfa8d5918c2ce4ba43588e894af35dbd8e91e6e55c817bca5847df34a"}, diff --git a/priv/repo/migrations/20260428170617_add_handoff_notifications_mode_to_escalation_policies.exs b/priv/repo/migrations/20260428170617_add_handoff_notifications_mode_to_escalation_policies.exs new file mode 100644 index 00000000..ece9fd9f --- /dev/null +++ b/priv/repo/migrations/20260428170617_add_handoff_notifications_mode_to_escalation_policies.exs @@ -0,0 +1,11 @@ +defmodule Towerops.Repo.Migrations.AddHandoffNotificationsModeToEscalationPolicies do + use Ecto.Migration + + def change do + alter table(:escalation_policies) do + add :handoff_notifications_mode, :string, + null: false, + default: "when_in_use_by_service" + end + end +end diff --git a/priv/repo/structure.sql b/priv/repo/structure.sql index 204e07ca..13f2ea74 100644 --- a/priv/repo/structure.sql +++ b/priv/repo/structure.sql @@ -2,7 +2,7 @@ -- PostgreSQL database dump -- -\restrict 58n9yz3M1gCN5t2tMwVCXpismPQgdWzmGfJI4AZxbUhDND1zz8QIj8oDYzqLMz8 +\restrict fxN8VfMT4wlKMdY4b5QKMDFncMWuvcHmQoAKL88Wv4ey2erB35CfSsmUYUTugSQ -- Dumped from database version 17.9 (Homebrew) -- Dumped by pg_dump version 17.9 (Homebrew) @@ -33,6 +33,20 @@ CREATE EXTENSION IF NOT EXISTS timescaledb WITH SCHEMA public; COMMENT ON EXTENSION timescaledb IS 'Enables scalable inserts and complex queries for time-series data (Community Edition)'; +-- +-- Name: btree_gist; Type: EXTENSION; Schema: -; Owner: - +-- + +CREATE EXTENSION IF NOT EXISTS btree_gist WITH SCHEMA public; + + +-- +-- Name: EXTENSION btree_gist; Type: COMMENT; Schema: -; Owner: - +-- + +COMMENT ON EXTENSION btree_gist IS 'support for indexing common datatypes in GiST'; + + -- -- Name: citext; Type: EXTENSION; Schema: -; Owner: - -- @@ -86,7 +100,8 @@ CREATE TYPE public.oban_job_state AS ENUM ( 'retryable', 'completed', 'discarded', - 'cancelled' + 'cancelled', + 'suspended' ); @@ -2162,6 +2177,154 @@ ALTER TABLE ONLY _timescaledb_internal.compress_hyper_4_195_chunk ALTER COLUMN _ ALTER TABLE ONLY _timescaledb_internal.compress_hyper_4_195_chunk ALTER COLUMN agent_token_id SET STATISTICS 0; +-- +-- Name: compress_hyper_4_213_chunk; Type: TABLE; Schema: _timescaledb_internal; Owner: - +-- + +CREATE TABLE _timescaledb_internal.compress_hyper_4_213_chunk ( + _ts_meta_count integer, + device_id uuid, + id _timescaledb_internal.compressed_data, + _ts_meta_v2_bloomh_status _timescaledb_internal.bloom1, + status _timescaledb_internal.compressed_data, + response_time_ms _timescaledb_internal.compressed_data, + _ts_meta_min_1 timestamp(0) without time zone, + _ts_meta_max_1 timestamp(0) without time zone, + checked_at _timescaledb_internal.compressed_data, + inserted_at _timescaledb_internal.compressed_data, + _ts_meta_min_2 uuid, + _ts_meta_max_2 uuid, + agent_token_id _timescaledb_internal.compressed_data +) +WITH (toast_tuple_target='128'); +ALTER TABLE ONLY _timescaledb_internal.compress_hyper_4_213_chunk ALTER COLUMN _ts_meta_count SET STATISTICS 1000; +ALTER TABLE ONLY _timescaledb_internal.compress_hyper_4_213_chunk ALTER COLUMN device_id SET STATISTICS 1000; +ALTER TABLE ONLY _timescaledb_internal.compress_hyper_4_213_chunk ALTER COLUMN id SET STATISTICS 0; +ALTER TABLE ONLY _timescaledb_internal.compress_hyper_4_213_chunk ALTER COLUMN _ts_meta_v2_bloomh_status SET STATISTICS 1000; +ALTER TABLE ONLY _timescaledb_internal.compress_hyper_4_213_chunk ALTER COLUMN _ts_meta_v2_bloomh_status SET STORAGE EXTERNAL; +ALTER TABLE ONLY _timescaledb_internal.compress_hyper_4_213_chunk ALTER COLUMN status SET STATISTICS 0; +ALTER TABLE ONLY _timescaledb_internal.compress_hyper_4_213_chunk ALTER COLUMN status SET STORAGE EXTENDED; +ALTER TABLE ONLY _timescaledb_internal.compress_hyper_4_213_chunk ALTER COLUMN response_time_ms SET STATISTICS 0; +ALTER TABLE ONLY _timescaledb_internal.compress_hyper_4_213_chunk ALTER COLUMN _ts_meta_min_1 SET STATISTICS 1000; +ALTER TABLE ONLY _timescaledb_internal.compress_hyper_4_213_chunk ALTER COLUMN _ts_meta_max_1 SET STATISTICS 1000; +ALTER TABLE ONLY _timescaledb_internal.compress_hyper_4_213_chunk ALTER COLUMN checked_at SET STATISTICS 0; +ALTER TABLE ONLY _timescaledb_internal.compress_hyper_4_213_chunk ALTER COLUMN inserted_at SET STATISTICS 0; +ALTER TABLE ONLY _timescaledb_internal.compress_hyper_4_213_chunk ALTER COLUMN _ts_meta_min_2 SET STATISTICS 1000; +ALTER TABLE ONLY _timescaledb_internal.compress_hyper_4_213_chunk ALTER COLUMN _ts_meta_max_2 SET STATISTICS 1000; +ALTER TABLE ONLY _timescaledb_internal.compress_hyper_4_213_chunk ALTER COLUMN agent_token_id SET STATISTICS 0; + + +-- +-- Name: compress_hyper_4_214_chunk; Type: TABLE; Schema: _timescaledb_internal; Owner: - +-- + +CREATE TABLE _timescaledb_internal.compress_hyper_4_214_chunk ( + _ts_meta_count integer, + device_id uuid, + id _timescaledb_internal.compressed_data, + _ts_meta_v2_bloomh_status _timescaledb_internal.bloom1, + status _timescaledb_internal.compressed_data, + response_time_ms _timescaledb_internal.compressed_data, + _ts_meta_min_1 timestamp(0) without time zone, + _ts_meta_max_1 timestamp(0) without time zone, + checked_at _timescaledb_internal.compressed_data, + inserted_at _timescaledb_internal.compressed_data, + _ts_meta_min_2 uuid, + _ts_meta_max_2 uuid, + agent_token_id _timescaledb_internal.compressed_data +) +WITH (toast_tuple_target='128'); +ALTER TABLE ONLY _timescaledb_internal.compress_hyper_4_214_chunk ALTER COLUMN _ts_meta_count SET STATISTICS 1000; +ALTER TABLE ONLY _timescaledb_internal.compress_hyper_4_214_chunk ALTER COLUMN device_id SET STATISTICS 1000; +ALTER TABLE ONLY _timescaledb_internal.compress_hyper_4_214_chunk ALTER COLUMN id SET STATISTICS 0; +ALTER TABLE ONLY _timescaledb_internal.compress_hyper_4_214_chunk ALTER COLUMN _ts_meta_v2_bloomh_status SET STATISTICS 1000; +ALTER TABLE ONLY _timescaledb_internal.compress_hyper_4_214_chunk ALTER COLUMN _ts_meta_v2_bloomh_status SET STORAGE EXTERNAL; +ALTER TABLE ONLY _timescaledb_internal.compress_hyper_4_214_chunk ALTER COLUMN status SET STATISTICS 0; +ALTER TABLE ONLY _timescaledb_internal.compress_hyper_4_214_chunk ALTER COLUMN status SET STORAGE EXTENDED; +ALTER TABLE ONLY _timescaledb_internal.compress_hyper_4_214_chunk ALTER COLUMN response_time_ms SET STATISTICS 0; +ALTER TABLE ONLY _timescaledb_internal.compress_hyper_4_214_chunk ALTER COLUMN _ts_meta_min_1 SET STATISTICS 1000; +ALTER TABLE ONLY _timescaledb_internal.compress_hyper_4_214_chunk ALTER COLUMN _ts_meta_max_1 SET STATISTICS 1000; +ALTER TABLE ONLY _timescaledb_internal.compress_hyper_4_214_chunk ALTER COLUMN checked_at SET STATISTICS 0; +ALTER TABLE ONLY _timescaledb_internal.compress_hyper_4_214_chunk ALTER COLUMN inserted_at SET STATISTICS 0; +ALTER TABLE ONLY _timescaledb_internal.compress_hyper_4_214_chunk ALTER COLUMN _ts_meta_min_2 SET STATISTICS 1000; +ALTER TABLE ONLY _timescaledb_internal.compress_hyper_4_214_chunk ALTER COLUMN _ts_meta_max_2 SET STATISTICS 1000; +ALTER TABLE ONLY _timescaledb_internal.compress_hyper_4_214_chunk ALTER COLUMN agent_token_id SET STATISTICS 0; + + +-- +-- Name: compress_hyper_4_217_chunk; Type: TABLE; Schema: _timescaledb_internal; Owner: - +-- + +CREATE TABLE _timescaledb_internal.compress_hyper_4_217_chunk ( + _ts_meta_count integer, + device_id uuid, + id _timescaledb_internal.compressed_data, + _ts_meta_v2_bloomh_status _timescaledb_internal.bloom1, + status _timescaledb_internal.compressed_data, + response_time_ms _timescaledb_internal.compressed_data, + _ts_meta_min_1 timestamp(0) without time zone, + _ts_meta_max_1 timestamp(0) without time zone, + checked_at _timescaledb_internal.compressed_data, + inserted_at _timescaledb_internal.compressed_data, + _ts_meta_min_2 uuid, + _ts_meta_max_2 uuid, + agent_token_id _timescaledb_internal.compressed_data +) +WITH (toast_tuple_target='128'); +ALTER TABLE ONLY _timescaledb_internal.compress_hyper_4_217_chunk ALTER COLUMN _ts_meta_count SET STATISTICS 1000; +ALTER TABLE ONLY _timescaledb_internal.compress_hyper_4_217_chunk ALTER COLUMN device_id SET STATISTICS 1000; +ALTER TABLE ONLY _timescaledb_internal.compress_hyper_4_217_chunk ALTER COLUMN id SET STATISTICS 0; +ALTER TABLE ONLY _timescaledb_internal.compress_hyper_4_217_chunk ALTER COLUMN _ts_meta_v2_bloomh_status SET STATISTICS 1000; +ALTER TABLE ONLY _timescaledb_internal.compress_hyper_4_217_chunk ALTER COLUMN _ts_meta_v2_bloomh_status SET STORAGE EXTERNAL; +ALTER TABLE ONLY _timescaledb_internal.compress_hyper_4_217_chunk ALTER COLUMN status SET STATISTICS 0; +ALTER TABLE ONLY _timescaledb_internal.compress_hyper_4_217_chunk ALTER COLUMN status SET STORAGE EXTENDED; +ALTER TABLE ONLY _timescaledb_internal.compress_hyper_4_217_chunk ALTER COLUMN response_time_ms SET STATISTICS 0; +ALTER TABLE ONLY _timescaledb_internal.compress_hyper_4_217_chunk ALTER COLUMN _ts_meta_min_1 SET STATISTICS 1000; +ALTER TABLE ONLY _timescaledb_internal.compress_hyper_4_217_chunk ALTER COLUMN _ts_meta_max_1 SET STATISTICS 1000; +ALTER TABLE ONLY _timescaledb_internal.compress_hyper_4_217_chunk ALTER COLUMN checked_at SET STATISTICS 0; +ALTER TABLE ONLY _timescaledb_internal.compress_hyper_4_217_chunk ALTER COLUMN inserted_at SET STATISTICS 0; +ALTER TABLE ONLY _timescaledb_internal.compress_hyper_4_217_chunk ALTER COLUMN _ts_meta_min_2 SET STATISTICS 1000; +ALTER TABLE ONLY _timescaledb_internal.compress_hyper_4_217_chunk ALTER COLUMN _ts_meta_max_2 SET STATISTICS 1000; +ALTER TABLE ONLY _timescaledb_internal.compress_hyper_4_217_chunk ALTER COLUMN agent_token_id SET STATISTICS 0; + + +-- +-- Name: compress_hyper_4_220_chunk; Type: TABLE; Schema: _timescaledb_internal; Owner: - +-- + +CREATE TABLE _timescaledb_internal.compress_hyper_4_220_chunk ( + _ts_meta_count integer, + device_id uuid, + id _timescaledb_internal.compressed_data, + _ts_meta_v2_bloomh_status _timescaledb_internal.bloom1, + status _timescaledb_internal.compressed_data, + response_time_ms _timescaledb_internal.compressed_data, + _ts_meta_min_1 timestamp(0) without time zone, + _ts_meta_max_1 timestamp(0) without time zone, + checked_at _timescaledb_internal.compressed_data, + inserted_at _timescaledb_internal.compressed_data, + _ts_meta_min_2 uuid, + _ts_meta_max_2 uuid, + agent_token_id _timescaledb_internal.compressed_data +) +WITH (toast_tuple_target='128'); +ALTER TABLE ONLY _timescaledb_internal.compress_hyper_4_220_chunk ALTER COLUMN _ts_meta_count SET STATISTICS 1000; +ALTER TABLE ONLY _timescaledb_internal.compress_hyper_4_220_chunk ALTER COLUMN device_id SET STATISTICS 1000; +ALTER TABLE ONLY _timescaledb_internal.compress_hyper_4_220_chunk ALTER COLUMN id SET STATISTICS 0; +ALTER TABLE ONLY _timescaledb_internal.compress_hyper_4_220_chunk ALTER COLUMN _ts_meta_v2_bloomh_status SET STATISTICS 1000; +ALTER TABLE ONLY _timescaledb_internal.compress_hyper_4_220_chunk ALTER COLUMN _ts_meta_v2_bloomh_status SET STORAGE EXTERNAL; +ALTER TABLE ONLY _timescaledb_internal.compress_hyper_4_220_chunk ALTER COLUMN status SET STATISTICS 0; +ALTER TABLE ONLY _timescaledb_internal.compress_hyper_4_220_chunk ALTER COLUMN status SET STORAGE EXTENDED; +ALTER TABLE ONLY _timescaledb_internal.compress_hyper_4_220_chunk ALTER COLUMN response_time_ms SET STATISTICS 0; +ALTER TABLE ONLY _timescaledb_internal.compress_hyper_4_220_chunk ALTER COLUMN _ts_meta_min_1 SET STATISTICS 1000; +ALTER TABLE ONLY _timescaledb_internal.compress_hyper_4_220_chunk ALTER COLUMN _ts_meta_max_1 SET STATISTICS 1000; +ALTER TABLE ONLY _timescaledb_internal.compress_hyper_4_220_chunk ALTER COLUMN checked_at SET STATISTICS 0; +ALTER TABLE ONLY _timescaledb_internal.compress_hyper_4_220_chunk ALTER COLUMN inserted_at SET STATISTICS 0; +ALTER TABLE ONLY _timescaledb_internal.compress_hyper_4_220_chunk ALTER COLUMN _ts_meta_min_2 SET STATISTICS 1000; +ALTER TABLE ONLY _timescaledb_internal.compress_hyper_4_220_chunk ALTER COLUMN _ts_meta_max_2 SET STATISTICS 1000; +ALTER TABLE ONLY _timescaledb_internal.compress_hyper_4_220_chunk ALTER COLUMN agent_token_id SET STATISTICS 0; + + -- -- Name: compress_hyper_5_106_chunk; Type: TABLE; Schema: _timescaledb_internal; Owner: - -- @@ -2791,6 +2954,154 @@ ALTER TABLE ONLY _timescaledb_internal.compress_hyper_5_196_chunk ALTER COLUMN s ALTER TABLE ONLY _timescaledb_internal.compress_hyper_5_196_chunk ALTER COLUMN state_descr SET STORAGE EXTENDED; +-- +-- Name: compress_hyper_5_212_chunk; Type: TABLE; Schema: _timescaledb_internal; Owner: - +-- + +CREATE TABLE _timescaledb_internal.compress_hyper_5_212_chunk ( + _ts_meta_count integer, + sensor_id uuid, + id _timescaledb_internal.compressed_data, + value _timescaledb_internal.compressed_data, + _ts_meta_min_2 character varying(255), + _ts_meta_max_2 character varying(255), + status _timescaledb_internal.compressed_data, + _ts_meta_min_1 timestamp(0) without time zone, + _ts_meta_max_1 timestamp(0) without time zone, + checked_at _timescaledb_internal.compressed_data, + inserted_at _timescaledb_internal.compressed_data, + state_descr _timescaledb_internal.compressed_data +) +WITH (toast_tuple_target='128'); +ALTER TABLE ONLY _timescaledb_internal.compress_hyper_5_212_chunk ALTER COLUMN _ts_meta_count SET STATISTICS 1000; +ALTER TABLE ONLY _timescaledb_internal.compress_hyper_5_212_chunk ALTER COLUMN sensor_id SET STATISTICS 1000; +ALTER TABLE ONLY _timescaledb_internal.compress_hyper_5_212_chunk ALTER COLUMN id SET STATISTICS 0; +ALTER TABLE ONLY _timescaledb_internal.compress_hyper_5_212_chunk ALTER COLUMN value SET STATISTICS 0; +ALTER TABLE ONLY _timescaledb_internal.compress_hyper_5_212_chunk ALTER COLUMN _ts_meta_min_2 SET STATISTICS 1000; +ALTER TABLE ONLY _timescaledb_internal.compress_hyper_5_212_chunk ALTER COLUMN _ts_meta_min_2 SET STORAGE PLAIN; +ALTER TABLE ONLY _timescaledb_internal.compress_hyper_5_212_chunk ALTER COLUMN _ts_meta_max_2 SET STATISTICS 1000; +ALTER TABLE ONLY _timescaledb_internal.compress_hyper_5_212_chunk ALTER COLUMN _ts_meta_max_2 SET STORAGE PLAIN; +ALTER TABLE ONLY _timescaledb_internal.compress_hyper_5_212_chunk ALTER COLUMN status SET STATISTICS 0; +ALTER TABLE ONLY _timescaledb_internal.compress_hyper_5_212_chunk ALTER COLUMN status SET STORAGE EXTENDED; +ALTER TABLE ONLY _timescaledb_internal.compress_hyper_5_212_chunk ALTER COLUMN _ts_meta_min_1 SET STATISTICS 1000; +ALTER TABLE ONLY _timescaledb_internal.compress_hyper_5_212_chunk ALTER COLUMN _ts_meta_max_1 SET STATISTICS 1000; +ALTER TABLE ONLY _timescaledb_internal.compress_hyper_5_212_chunk ALTER COLUMN checked_at SET STATISTICS 0; +ALTER TABLE ONLY _timescaledb_internal.compress_hyper_5_212_chunk ALTER COLUMN inserted_at SET STATISTICS 0; +ALTER TABLE ONLY _timescaledb_internal.compress_hyper_5_212_chunk ALTER COLUMN state_descr SET STATISTICS 0; +ALTER TABLE ONLY _timescaledb_internal.compress_hyper_5_212_chunk ALTER COLUMN state_descr SET STORAGE EXTENDED; + + +-- +-- Name: compress_hyper_5_216_chunk; Type: TABLE; Schema: _timescaledb_internal; Owner: - +-- + +CREATE TABLE _timescaledb_internal.compress_hyper_5_216_chunk ( + _ts_meta_count integer, + sensor_id uuid, + id _timescaledb_internal.compressed_data, + value _timescaledb_internal.compressed_data, + _ts_meta_min_2 character varying(255), + _ts_meta_max_2 character varying(255), + status _timescaledb_internal.compressed_data, + _ts_meta_min_1 timestamp(0) without time zone, + _ts_meta_max_1 timestamp(0) without time zone, + checked_at _timescaledb_internal.compressed_data, + inserted_at _timescaledb_internal.compressed_data, + state_descr _timescaledb_internal.compressed_data +) +WITH (toast_tuple_target='128'); +ALTER TABLE ONLY _timescaledb_internal.compress_hyper_5_216_chunk ALTER COLUMN _ts_meta_count SET STATISTICS 1000; +ALTER TABLE ONLY _timescaledb_internal.compress_hyper_5_216_chunk ALTER COLUMN sensor_id SET STATISTICS 1000; +ALTER TABLE ONLY _timescaledb_internal.compress_hyper_5_216_chunk ALTER COLUMN id SET STATISTICS 0; +ALTER TABLE ONLY _timescaledb_internal.compress_hyper_5_216_chunk ALTER COLUMN value SET STATISTICS 0; +ALTER TABLE ONLY _timescaledb_internal.compress_hyper_5_216_chunk ALTER COLUMN _ts_meta_min_2 SET STATISTICS 1000; +ALTER TABLE ONLY _timescaledb_internal.compress_hyper_5_216_chunk ALTER COLUMN _ts_meta_min_2 SET STORAGE PLAIN; +ALTER TABLE ONLY _timescaledb_internal.compress_hyper_5_216_chunk ALTER COLUMN _ts_meta_max_2 SET STATISTICS 1000; +ALTER TABLE ONLY _timescaledb_internal.compress_hyper_5_216_chunk ALTER COLUMN _ts_meta_max_2 SET STORAGE PLAIN; +ALTER TABLE ONLY _timescaledb_internal.compress_hyper_5_216_chunk ALTER COLUMN status SET STATISTICS 0; +ALTER TABLE ONLY _timescaledb_internal.compress_hyper_5_216_chunk ALTER COLUMN status SET STORAGE EXTENDED; +ALTER TABLE ONLY _timescaledb_internal.compress_hyper_5_216_chunk ALTER COLUMN _ts_meta_min_1 SET STATISTICS 1000; +ALTER TABLE ONLY _timescaledb_internal.compress_hyper_5_216_chunk ALTER COLUMN _ts_meta_max_1 SET STATISTICS 1000; +ALTER TABLE ONLY _timescaledb_internal.compress_hyper_5_216_chunk ALTER COLUMN checked_at SET STATISTICS 0; +ALTER TABLE ONLY _timescaledb_internal.compress_hyper_5_216_chunk ALTER COLUMN inserted_at SET STATISTICS 0; +ALTER TABLE ONLY _timescaledb_internal.compress_hyper_5_216_chunk ALTER COLUMN state_descr SET STATISTICS 0; +ALTER TABLE ONLY _timescaledb_internal.compress_hyper_5_216_chunk ALTER COLUMN state_descr SET STORAGE EXTENDED; + + +-- +-- Name: compress_hyper_5_219_chunk; Type: TABLE; Schema: _timescaledb_internal; Owner: - +-- + +CREATE TABLE _timescaledb_internal.compress_hyper_5_219_chunk ( + _ts_meta_count integer, + sensor_id uuid, + id _timescaledb_internal.compressed_data, + value _timescaledb_internal.compressed_data, + _ts_meta_min_2 character varying(255), + _ts_meta_max_2 character varying(255), + status _timescaledb_internal.compressed_data, + _ts_meta_min_1 timestamp(0) without time zone, + _ts_meta_max_1 timestamp(0) without time zone, + checked_at _timescaledb_internal.compressed_data, + inserted_at _timescaledb_internal.compressed_data, + state_descr _timescaledb_internal.compressed_data +) +WITH (toast_tuple_target='128'); +ALTER TABLE ONLY _timescaledb_internal.compress_hyper_5_219_chunk ALTER COLUMN _ts_meta_count SET STATISTICS 1000; +ALTER TABLE ONLY _timescaledb_internal.compress_hyper_5_219_chunk ALTER COLUMN sensor_id SET STATISTICS 1000; +ALTER TABLE ONLY _timescaledb_internal.compress_hyper_5_219_chunk ALTER COLUMN id SET STATISTICS 0; +ALTER TABLE ONLY _timescaledb_internal.compress_hyper_5_219_chunk ALTER COLUMN value SET STATISTICS 0; +ALTER TABLE ONLY _timescaledb_internal.compress_hyper_5_219_chunk ALTER COLUMN _ts_meta_min_2 SET STATISTICS 1000; +ALTER TABLE ONLY _timescaledb_internal.compress_hyper_5_219_chunk ALTER COLUMN _ts_meta_min_2 SET STORAGE PLAIN; +ALTER TABLE ONLY _timescaledb_internal.compress_hyper_5_219_chunk ALTER COLUMN _ts_meta_max_2 SET STATISTICS 1000; +ALTER TABLE ONLY _timescaledb_internal.compress_hyper_5_219_chunk ALTER COLUMN _ts_meta_max_2 SET STORAGE PLAIN; +ALTER TABLE ONLY _timescaledb_internal.compress_hyper_5_219_chunk ALTER COLUMN status SET STATISTICS 0; +ALTER TABLE ONLY _timescaledb_internal.compress_hyper_5_219_chunk ALTER COLUMN status SET STORAGE EXTENDED; +ALTER TABLE ONLY _timescaledb_internal.compress_hyper_5_219_chunk ALTER COLUMN _ts_meta_min_1 SET STATISTICS 1000; +ALTER TABLE ONLY _timescaledb_internal.compress_hyper_5_219_chunk ALTER COLUMN _ts_meta_max_1 SET STATISTICS 1000; +ALTER TABLE ONLY _timescaledb_internal.compress_hyper_5_219_chunk ALTER COLUMN checked_at SET STATISTICS 0; +ALTER TABLE ONLY _timescaledb_internal.compress_hyper_5_219_chunk ALTER COLUMN inserted_at SET STATISTICS 0; +ALTER TABLE ONLY _timescaledb_internal.compress_hyper_5_219_chunk ALTER COLUMN state_descr SET STATISTICS 0; +ALTER TABLE ONLY _timescaledb_internal.compress_hyper_5_219_chunk ALTER COLUMN state_descr SET STORAGE EXTENDED; + + +-- +-- Name: compress_hyper_5_221_chunk; Type: TABLE; Schema: _timescaledb_internal; Owner: - +-- + +CREATE TABLE _timescaledb_internal.compress_hyper_5_221_chunk ( + _ts_meta_count integer, + sensor_id uuid, + id _timescaledb_internal.compressed_data, + value _timescaledb_internal.compressed_data, + _ts_meta_min_2 character varying(255), + _ts_meta_max_2 character varying(255), + status _timescaledb_internal.compressed_data, + _ts_meta_min_1 timestamp(0) without time zone, + _ts_meta_max_1 timestamp(0) without time zone, + checked_at _timescaledb_internal.compressed_data, + inserted_at _timescaledb_internal.compressed_data, + state_descr _timescaledb_internal.compressed_data +) +WITH (toast_tuple_target='128'); +ALTER TABLE ONLY _timescaledb_internal.compress_hyper_5_221_chunk ALTER COLUMN _ts_meta_count SET STATISTICS 1000; +ALTER TABLE ONLY _timescaledb_internal.compress_hyper_5_221_chunk ALTER COLUMN sensor_id SET STATISTICS 1000; +ALTER TABLE ONLY _timescaledb_internal.compress_hyper_5_221_chunk ALTER COLUMN id SET STATISTICS 0; +ALTER TABLE ONLY _timescaledb_internal.compress_hyper_5_221_chunk ALTER COLUMN value SET STATISTICS 0; +ALTER TABLE ONLY _timescaledb_internal.compress_hyper_5_221_chunk ALTER COLUMN _ts_meta_min_2 SET STATISTICS 1000; +ALTER TABLE ONLY _timescaledb_internal.compress_hyper_5_221_chunk ALTER COLUMN _ts_meta_min_2 SET STORAGE PLAIN; +ALTER TABLE ONLY _timescaledb_internal.compress_hyper_5_221_chunk ALTER COLUMN _ts_meta_max_2 SET STATISTICS 1000; +ALTER TABLE ONLY _timescaledb_internal.compress_hyper_5_221_chunk ALTER COLUMN _ts_meta_max_2 SET STORAGE PLAIN; +ALTER TABLE ONLY _timescaledb_internal.compress_hyper_5_221_chunk ALTER COLUMN status SET STATISTICS 0; +ALTER TABLE ONLY _timescaledb_internal.compress_hyper_5_221_chunk ALTER COLUMN status SET STORAGE EXTENDED; +ALTER TABLE ONLY _timescaledb_internal.compress_hyper_5_221_chunk ALTER COLUMN _ts_meta_min_1 SET STATISTICS 1000; +ALTER TABLE ONLY _timescaledb_internal.compress_hyper_5_221_chunk ALTER COLUMN _ts_meta_max_1 SET STATISTICS 1000; +ALTER TABLE ONLY _timescaledb_internal.compress_hyper_5_221_chunk ALTER COLUMN checked_at SET STATISTICS 0; +ALTER TABLE ONLY _timescaledb_internal.compress_hyper_5_221_chunk ALTER COLUMN inserted_at SET STATISTICS 0; +ALTER TABLE ONLY _timescaledb_internal.compress_hyper_5_221_chunk ALTER COLUMN state_descr SET STATISTICS 0; +ALTER TABLE ONLY _timescaledb_internal.compress_hyper_5_221_chunk ALTER COLUMN state_descr SET STORAGE EXTENDED; + + -- -- Name: compress_hyper_5_41_chunk; Type: TABLE; Schema: _timescaledb_internal; Owner: - -- @@ -3772,6 +4083,154 @@ ALTER TABLE ONLY _timescaledb_internal.compress_hyper_6_197_chunk ALTER COLUMN c ALTER TABLE ONLY _timescaledb_internal.compress_hyper_6_197_chunk ALTER COLUMN inserted_at SET STATISTICS 0; +-- +-- Name: compress_hyper_6_211_chunk; Type: TABLE; Schema: _timescaledb_internal; Owner: - +-- + +CREATE TABLE _timescaledb_internal.compress_hyper_6_211_chunk ( + _ts_meta_count integer, + interface_id uuid, + id _timescaledb_internal.compressed_data, + if_in_octets _timescaledb_internal.compressed_data, + if_out_octets _timescaledb_internal.compressed_data, + if_in_errors _timescaledb_internal.compressed_data, + if_out_errors _timescaledb_internal.compressed_data, + if_in_discards _timescaledb_internal.compressed_data, + if_out_discards _timescaledb_internal.compressed_data, + _ts_meta_min_1 timestamp(0) without time zone, + _ts_meta_max_1 timestamp(0) without time zone, + checked_at _timescaledb_internal.compressed_data, + inserted_at _timescaledb_internal.compressed_data, + is_hc _timescaledb_internal.compressed_data +) +WITH (toast_tuple_target='128'); +ALTER TABLE ONLY _timescaledb_internal.compress_hyper_6_211_chunk ALTER COLUMN _ts_meta_count SET STATISTICS 1000; +ALTER TABLE ONLY _timescaledb_internal.compress_hyper_6_211_chunk ALTER COLUMN interface_id SET STATISTICS 1000; +ALTER TABLE ONLY _timescaledb_internal.compress_hyper_6_211_chunk ALTER COLUMN id SET STATISTICS 0; +ALTER TABLE ONLY _timescaledb_internal.compress_hyper_6_211_chunk ALTER COLUMN if_in_octets SET STATISTICS 0; +ALTER TABLE ONLY _timescaledb_internal.compress_hyper_6_211_chunk ALTER COLUMN if_out_octets SET STATISTICS 0; +ALTER TABLE ONLY _timescaledb_internal.compress_hyper_6_211_chunk ALTER COLUMN if_in_errors SET STATISTICS 0; +ALTER TABLE ONLY _timescaledb_internal.compress_hyper_6_211_chunk ALTER COLUMN if_out_errors SET STATISTICS 0; +ALTER TABLE ONLY _timescaledb_internal.compress_hyper_6_211_chunk ALTER COLUMN if_in_discards SET STATISTICS 0; +ALTER TABLE ONLY _timescaledb_internal.compress_hyper_6_211_chunk ALTER COLUMN if_out_discards SET STATISTICS 0; +ALTER TABLE ONLY _timescaledb_internal.compress_hyper_6_211_chunk ALTER COLUMN _ts_meta_min_1 SET STATISTICS 1000; +ALTER TABLE ONLY _timescaledb_internal.compress_hyper_6_211_chunk ALTER COLUMN _ts_meta_max_1 SET STATISTICS 1000; +ALTER TABLE ONLY _timescaledb_internal.compress_hyper_6_211_chunk ALTER COLUMN checked_at SET STATISTICS 0; +ALTER TABLE ONLY _timescaledb_internal.compress_hyper_6_211_chunk ALTER COLUMN inserted_at SET STATISTICS 0; +ALTER TABLE ONLY _timescaledb_internal.compress_hyper_6_211_chunk ALTER COLUMN is_hc SET STATISTICS 0; + + +-- +-- Name: compress_hyper_6_215_chunk; Type: TABLE; Schema: _timescaledb_internal; Owner: - +-- + +CREATE TABLE _timescaledb_internal.compress_hyper_6_215_chunk ( + _ts_meta_count integer, + interface_id uuid, + id _timescaledb_internal.compressed_data, + if_in_octets _timescaledb_internal.compressed_data, + if_out_octets _timescaledb_internal.compressed_data, + if_in_errors _timescaledb_internal.compressed_data, + if_out_errors _timescaledb_internal.compressed_data, + if_in_discards _timescaledb_internal.compressed_data, + if_out_discards _timescaledb_internal.compressed_data, + _ts_meta_min_1 timestamp(0) without time zone, + _ts_meta_max_1 timestamp(0) without time zone, + checked_at _timescaledb_internal.compressed_data, + inserted_at _timescaledb_internal.compressed_data, + is_hc _timescaledb_internal.compressed_data +) +WITH (toast_tuple_target='128'); +ALTER TABLE ONLY _timescaledb_internal.compress_hyper_6_215_chunk ALTER COLUMN _ts_meta_count SET STATISTICS 1000; +ALTER TABLE ONLY _timescaledb_internal.compress_hyper_6_215_chunk ALTER COLUMN interface_id SET STATISTICS 1000; +ALTER TABLE ONLY _timescaledb_internal.compress_hyper_6_215_chunk ALTER COLUMN id SET STATISTICS 0; +ALTER TABLE ONLY _timescaledb_internal.compress_hyper_6_215_chunk ALTER COLUMN if_in_octets SET STATISTICS 0; +ALTER TABLE ONLY _timescaledb_internal.compress_hyper_6_215_chunk ALTER COLUMN if_out_octets SET STATISTICS 0; +ALTER TABLE ONLY _timescaledb_internal.compress_hyper_6_215_chunk ALTER COLUMN if_in_errors SET STATISTICS 0; +ALTER TABLE ONLY _timescaledb_internal.compress_hyper_6_215_chunk ALTER COLUMN if_out_errors SET STATISTICS 0; +ALTER TABLE ONLY _timescaledb_internal.compress_hyper_6_215_chunk ALTER COLUMN if_in_discards SET STATISTICS 0; +ALTER TABLE ONLY _timescaledb_internal.compress_hyper_6_215_chunk ALTER COLUMN if_out_discards SET STATISTICS 0; +ALTER TABLE ONLY _timescaledb_internal.compress_hyper_6_215_chunk ALTER COLUMN _ts_meta_min_1 SET STATISTICS 1000; +ALTER TABLE ONLY _timescaledb_internal.compress_hyper_6_215_chunk ALTER COLUMN _ts_meta_max_1 SET STATISTICS 1000; +ALTER TABLE ONLY _timescaledb_internal.compress_hyper_6_215_chunk ALTER COLUMN checked_at SET STATISTICS 0; +ALTER TABLE ONLY _timescaledb_internal.compress_hyper_6_215_chunk ALTER COLUMN inserted_at SET STATISTICS 0; +ALTER TABLE ONLY _timescaledb_internal.compress_hyper_6_215_chunk ALTER COLUMN is_hc SET STATISTICS 0; + + +-- +-- Name: compress_hyper_6_218_chunk; Type: TABLE; Schema: _timescaledb_internal; Owner: - +-- + +CREATE TABLE _timescaledb_internal.compress_hyper_6_218_chunk ( + _ts_meta_count integer, + interface_id uuid, + id _timescaledb_internal.compressed_data, + if_in_octets _timescaledb_internal.compressed_data, + if_out_octets _timescaledb_internal.compressed_data, + if_in_errors _timescaledb_internal.compressed_data, + if_out_errors _timescaledb_internal.compressed_data, + if_in_discards _timescaledb_internal.compressed_data, + if_out_discards _timescaledb_internal.compressed_data, + _ts_meta_min_1 timestamp(0) without time zone, + _ts_meta_max_1 timestamp(0) without time zone, + checked_at _timescaledb_internal.compressed_data, + inserted_at _timescaledb_internal.compressed_data, + is_hc _timescaledb_internal.compressed_data +) +WITH (toast_tuple_target='128'); +ALTER TABLE ONLY _timescaledb_internal.compress_hyper_6_218_chunk ALTER COLUMN _ts_meta_count SET STATISTICS 1000; +ALTER TABLE ONLY _timescaledb_internal.compress_hyper_6_218_chunk ALTER COLUMN interface_id SET STATISTICS 1000; +ALTER TABLE ONLY _timescaledb_internal.compress_hyper_6_218_chunk ALTER COLUMN id SET STATISTICS 0; +ALTER TABLE ONLY _timescaledb_internal.compress_hyper_6_218_chunk ALTER COLUMN if_in_octets SET STATISTICS 0; +ALTER TABLE ONLY _timescaledb_internal.compress_hyper_6_218_chunk ALTER COLUMN if_out_octets SET STATISTICS 0; +ALTER TABLE ONLY _timescaledb_internal.compress_hyper_6_218_chunk ALTER COLUMN if_in_errors SET STATISTICS 0; +ALTER TABLE ONLY _timescaledb_internal.compress_hyper_6_218_chunk ALTER COLUMN if_out_errors SET STATISTICS 0; +ALTER TABLE ONLY _timescaledb_internal.compress_hyper_6_218_chunk ALTER COLUMN if_in_discards SET STATISTICS 0; +ALTER TABLE ONLY _timescaledb_internal.compress_hyper_6_218_chunk ALTER COLUMN if_out_discards SET STATISTICS 0; +ALTER TABLE ONLY _timescaledb_internal.compress_hyper_6_218_chunk ALTER COLUMN _ts_meta_min_1 SET STATISTICS 1000; +ALTER TABLE ONLY _timescaledb_internal.compress_hyper_6_218_chunk ALTER COLUMN _ts_meta_max_1 SET STATISTICS 1000; +ALTER TABLE ONLY _timescaledb_internal.compress_hyper_6_218_chunk ALTER COLUMN checked_at SET STATISTICS 0; +ALTER TABLE ONLY _timescaledb_internal.compress_hyper_6_218_chunk ALTER COLUMN inserted_at SET STATISTICS 0; +ALTER TABLE ONLY _timescaledb_internal.compress_hyper_6_218_chunk ALTER COLUMN is_hc SET STATISTICS 0; + + +-- +-- Name: compress_hyper_6_222_chunk; Type: TABLE; Schema: _timescaledb_internal; Owner: - +-- + +CREATE TABLE _timescaledb_internal.compress_hyper_6_222_chunk ( + _ts_meta_count integer, + interface_id uuid, + id _timescaledb_internal.compressed_data, + if_in_octets _timescaledb_internal.compressed_data, + if_out_octets _timescaledb_internal.compressed_data, + if_in_errors _timescaledb_internal.compressed_data, + if_out_errors _timescaledb_internal.compressed_data, + if_in_discards _timescaledb_internal.compressed_data, + if_out_discards _timescaledb_internal.compressed_data, + _ts_meta_min_1 timestamp(0) without time zone, + _ts_meta_max_1 timestamp(0) without time zone, + checked_at _timescaledb_internal.compressed_data, + inserted_at _timescaledb_internal.compressed_data, + is_hc _timescaledb_internal.compressed_data +) +WITH (toast_tuple_target='128'); +ALTER TABLE ONLY _timescaledb_internal.compress_hyper_6_222_chunk ALTER COLUMN _ts_meta_count SET STATISTICS 1000; +ALTER TABLE ONLY _timescaledb_internal.compress_hyper_6_222_chunk ALTER COLUMN interface_id SET STATISTICS 1000; +ALTER TABLE ONLY _timescaledb_internal.compress_hyper_6_222_chunk ALTER COLUMN id SET STATISTICS 0; +ALTER TABLE ONLY _timescaledb_internal.compress_hyper_6_222_chunk ALTER COLUMN if_in_octets SET STATISTICS 0; +ALTER TABLE ONLY _timescaledb_internal.compress_hyper_6_222_chunk ALTER COLUMN if_out_octets SET STATISTICS 0; +ALTER TABLE ONLY _timescaledb_internal.compress_hyper_6_222_chunk ALTER COLUMN if_in_errors SET STATISTICS 0; +ALTER TABLE ONLY _timescaledb_internal.compress_hyper_6_222_chunk ALTER COLUMN if_out_errors SET STATISTICS 0; +ALTER TABLE ONLY _timescaledb_internal.compress_hyper_6_222_chunk ALTER COLUMN if_in_discards SET STATISTICS 0; +ALTER TABLE ONLY _timescaledb_internal.compress_hyper_6_222_chunk ALTER COLUMN if_out_discards SET STATISTICS 0; +ALTER TABLE ONLY _timescaledb_internal.compress_hyper_6_222_chunk ALTER COLUMN _ts_meta_min_1 SET STATISTICS 1000; +ALTER TABLE ONLY _timescaledb_internal.compress_hyper_6_222_chunk ALTER COLUMN _ts_meta_max_1 SET STATISTICS 1000; +ALTER TABLE ONLY _timescaledb_internal.compress_hyper_6_222_chunk ALTER COLUMN checked_at SET STATISTICS 0; +ALTER TABLE ONLY _timescaledb_internal.compress_hyper_6_222_chunk ALTER COLUMN inserted_at SET STATISTICS 0; +ALTER TABLE ONLY _timescaledb_internal.compress_hyper_6_222_chunk ALTER COLUMN is_hc SET STATISTICS 0; + + -- -- Name: compress_hyper_6_31_chunk; Type: TABLE; Schema: _timescaledb_internal; Owner: - -- @@ -4718,7 +5177,8 @@ CREATE TABLE public.escalation_policies ( repeat_count integer DEFAULT 3 NOT NULL, organization_id uuid NOT NULL, inserted_at timestamp(0) without time zone NOT NULL, - updated_at timestamp(0) without time zone NOT NULL + updated_at timestamp(0) without time zone NOT NULL, + handoff_notifications_mode character varying(255) DEFAULT 'when_in_use_by_service'::character varying NOT NULL ); @@ -5112,7 +5572,8 @@ END) STORED, CONSTRAINT positive_max_attempts CHECK ((max_attempts > 0)), CONSTRAINT queue_length CHECK (((char_length(queue) > 0) AND (char_length(queue) < 128))), CONSTRAINT worker_length CHECK (((char_length(worker) > 0) AND (char_length(worker) < 128))) -); +) +WITH (autovacuum_vacuum_scale_factor='0.01', autovacuum_vacuum_threshold='100', autovacuum_analyze_scale_factor='0.005', autovacuum_vacuum_cost_delay='0'); -- @@ -5514,6 +5975,26 @@ CREATE TABLE public.preseem_sync_logs ( ); +-- +-- Name: printer_supplies; Type: TABLE; Schema: public; Owner: - +-- + +CREATE TABLE public.printer_supplies ( + id uuid NOT NULL, + snmp_device_id uuid NOT NULL, + supply_index character varying(255) NOT NULL, + supply_type character varying(255), + supply_description character varying(255), + supply_unit character varying(255), + max_capacity integer, + current_level integer, + color_name character varying(255), + part_number character varying(255), + inserted_at timestamp(0) without time zone NOT NULL, + updated_at timestamp(0) without time zone NOT NULL +); + + -- -- Name: profile_device_oids; Type: TABLE; Schema: public; Owner: - -- @@ -5691,6 +6172,47 @@ CREATE TABLE public.snmp_devices ( ); +-- +-- Name: snmp_entity_physical; Type: TABLE; Schema: public; Owner: - +-- + +CREATE TABLE public.snmp_entity_physical ( + id uuid NOT NULL, + snmp_device_id uuid NOT NULL, + entity_index character varying(255) NOT NULL, + parent_index character varying(255), + parent_id uuid, + entity_class character varying(255), + entity_type character varying(255), + name character varying(255), + description text, + serial_number character varying(255), + model character varying(255), + manufacturer character varying(255), + hardware_revision character varying(255), + firmware_revision character varying(255), + software_revision character varying(255), + physical_index integer, + inserted_at timestamp(0) without time zone NOT NULL, + updated_at timestamp(0) without time zone NOT NULL +); + + +-- +-- Name: snmp_entity_physical_readings; Type: TABLE; Schema: public; Owner: - +-- + +CREATE TABLE public.snmp_entity_physical_readings ( + id uuid NOT NULL, + entity_physical_id uuid NOT NULL, + operational_status character varying(255), + admin_status character varying(255), + measured_at timestamp(0) without time zone NOT NULL, + inserted_at timestamp(0) without time zone NOT NULL, + updated_at timestamp(0) without time zone NOT NULL +); + + -- -- Name: snmp_interface_stats_daily; Type: VIEW; Schema: public; Owner: - -- @@ -5805,6 +6327,43 @@ CREATE TABLE public.snmp_memory_pools ( ); +-- +-- Name: snmp_mempool_readings; Type: TABLE; Schema: public; Owner: - +-- + +CREATE TABLE public.snmp_mempool_readings ( + id uuid NOT NULL, + mempool_id uuid NOT NULL, + used_bytes bigint, + total_bytes bigint, + free_bytes bigint, + usage_percent double precision, + checked_at timestamp(0) without time zone NOT NULL, + inserted_at timestamp(0) without time zone NOT NULL +); + + +-- +-- Name: snmp_mempools; Type: TABLE; Schema: public; Owner: - +-- + +CREATE TABLE public.snmp_mempools ( + id uuid NOT NULL, + snmp_device_id uuid NOT NULL, + mempool_index character varying(255) NOT NULL, + description character varying(255), + mempool_type character varying(255) NOT NULL, + total_bytes bigint, + used_bytes bigint, + free_bytes bigint, + usage_percent double precision, + last_checked_at timestamp(0) without time zone, + metadata jsonb DEFAULT '{}'::jsonb, + inserted_at timestamp(0) without time zone NOT NULL, + updated_at timestamp(0) without time zone NOT NULL +); + + -- -- Name: snmp_neighbors; Type: TABLE; Schema: public; Owner: - -- @@ -5991,6 +6550,47 @@ CREATE TABLE public.snmp_storage_readings ( ); +-- +-- Name: snmp_transceiver_readings; Type: TABLE; Schema: public; Owner: - +-- + +CREATE TABLE public.snmp_transceiver_readings ( + id uuid NOT NULL, + transceiver_id uuid NOT NULL, + rx_power_dbm double precision, + tx_power_dbm double precision, + bias_current_ma double precision, + temperature_celsius double precision, + voltage_v double precision, + measured_at timestamp(0) without time zone NOT NULL, + inserted_at timestamp(0) without time zone NOT NULL, + updated_at timestamp(0) without time zone NOT NULL +); + + +-- +-- Name: snmp_transceivers; Type: TABLE; Schema: public; Owner: - +-- + +CREATE TABLE public.snmp_transceivers ( + id uuid NOT NULL, + snmp_device_id uuid NOT NULL, + entity_physical_id uuid, + port_index character varying(255) NOT NULL, + transceiver_type character varying(255), + vendor_name character varying(255), + vendor_part_number character varying(255), + vendor_serial_number character varying(255), + vendor_revision character varying(255), + wavelength_nm integer, + connector_type character varying(255), + nominal_bitrate_mbps integer, + supports_dom boolean DEFAULT false NOT NULL, + inserted_at timestamp(0) without time zone NOT NULL, + updated_at timestamp(0) without time zone NOT NULL +); + + -- -- Name: snmp_vlans; Type: TABLE; Schema: public; Owner: - -- @@ -7090,6 +7690,14 @@ ALTER TABLE ONLY public.preseem_sync_logs ADD CONSTRAINT preseem_sync_logs_pkey PRIMARY KEY (id); +-- +-- Name: printer_supplies printer_supplies_pkey; Type: CONSTRAINT; Schema: public; Owner: - +-- + +ALTER TABLE ONLY public.printer_supplies + ADD CONSTRAINT printer_supplies_pkey PRIMARY KEY (id); + + -- -- Name: profile_device_oids profile_device_oids_pkey; Type: CONSTRAINT; Schema: public; Owner: - -- @@ -7162,6 +7770,22 @@ ALTER TABLE ONLY public.snmp_devices ADD CONSTRAINT snmp_devices_pkey PRIMARY KEY (id); +-- +-- Name: snmp_entity_physical snmp_entity_physical_pkey; Type: CONSTRAINT; Schema: public; Owner: - +-- + +ALTER TABLE ONLY public.snmp_entity_physical + ADD CONSTRAINT snmp_entity_physical_pkey PRIMARY KEY (id); + + +-- +-- Name: snmp_entity_physical_readings snmp_entity_physical_readings_pkey; Type: CONSTRAINT; Schema: public; Owner: - +-- + +ALTER TABLE ONLY public.snmp_entity_physical_readings + ADD CONSTRAINT snmp_entity_physical_readings_pkey PRIMARY KEY (id); + + -- -- Name: snmp_interfaces snmp_interfaces_pkey; Type: CONSTRAINT; Schema: public; Owner: - -- @@ -7194,6 +7818,22 @@ ALTER TABLE ONLY public.snmp_memory_pools ADD CONSTRAINT snmp_memory_pools_pkey PRIMARY KEY (id); +-- +-- Name: snmp_mempool_readings snmp_mempool_readings_pkey; Type: CONSTRAINT; Schema: public; Owner: - +-- + +ALTER TABLE ONLY public.snmp_mempool_readings + ADD CONSTRAINT snmp_mempool_readings_pkey PRIMARY KEY (id); + + +-- +-- Name: snmp_mempools snmp_mempools_pkey; Type: CONSTRAINT; Schema: public; Owner: - +-- + +ALTER TABLE ONLY public.snmp_mempools + ADD CONSTRAINT snmp_mempools_pkey PRIMARY KEY (id); + + -- -- Name: snmp_neighbors snmp_neighbors_pkey; Type: CONSTRAINT; Schema: public; Owner: - -- @@ -7258,6 +7898,22 @@ ALTER TABLE ONLY public.snmp_storage_readings ADD CONSTRAINT snmp_storage_readings_pkey PRIMARY KEY (id); +-- +-- Name: snmp_transceiver_readings snmp_transceiver_readings_pkey; Type: CONSTRAINT; Schema: public; Owner: - +-- + +ALTER TABLE ONLY public.snmp_transceiver_readings + ADD CONSTRAINT snmp_transceiver_readings_pkey PRIMARY KEY (id); + + +-- +-- Name: snmp_transceivers snmp_transceivers_pkey; Type: CONSTRAINT; Schema: public; Owner: - +-- + +ALTER TABLE ONLY public.snmp_transceivers + ADD CONSTRAINT snmp_transceivers_pkey PRIMARY KEY (id); + + -- -- Name: snmp_vlans snmp_vlans_pkey; Type: CONSTRAINT; Schema: public; Owner: - -- @@ -9598,6 +10254,34 @@ CREATE INDEX compress_hyper_4_185_chunk_device_id__ts_meta_min_1__ts_met_idx ON CREATE INDEX compress_hyper_4_195_chunk_device_id__ts_meta_min_1__ts_met_idx ON _timescaledb_internal.compress_hyper_4_195_chunk USING btree (device_id, _ts_meta_min_1 DESC, _ts_meta_max_1 DESC, _ts_meta_min_2, _ts_meta_max_2); +-- +-- Name: compress_hyper_4_213_chunk_device_id__ts_meta_min_1__ts_met_idx; Type: INDEX; Schema: _timescaledb_internal; Owner: - +-- + +CREATE INDEX compress_hyper_4_213_chunk_device_id__ts_meta_min_1__ts_met_idx ON _timescaledb_internal.compress_hyper_4_213_chunk USING btree (device_id, _ts_meta_min_1 DESC, _ts_meta_max_1 DESC, _ts_meta_min_2, _ts_meta_max_2); + + +-- +-- Name: compress_hyper_4_214_chunk_device_id__ts_meta_min_1__ts_met_idx; Type: INDEX; Schema: _timescaledb_internal; Owner: - +-- + +CREATE INDEX compress_hyper_4_214_chunk_device_id__ts_meta_min_1__ts_met_idx ON _timescaledb_internal.compress_hyper_4_214_chunk USING btree (device_id, _ts_meta_min_1 DESC, _ts_meta_max_1 DESC, _ts_meta_min_2, _ts_meta_max_2); + + +-- +-- Name: compress_hyper_4_217_chunk_device_id__ts_meta_min_1__ts_met_idx; Type: INDEX; Schema: _timescaledb_internal; Owner: - +-- + +CREATE INDEX compress_hyper_4_217_chunk_device_id__ts_meta_min_1__ts_met_idx ON _timescaledb_internal.compress_hyper_4_217_chunk USING btree (device_id, _ts_meta_min_1 DESC, _ts_meta_max_1 DESC, _ts_meta_min_2, _ts_meta_max_2); + + +-- +-- Name: compress_hyper_4_220_chunk_device_id__ts_meta_min_1__ts_met_idx; Type: INDEX; Schema: _timescaledb_internal; Owner: - +-- + +CREATE INDEX compress_hyper_4_220_chunk_device_id__ts_meta_min_1__ts_met_idx ON _timescaledb_internal.compress_hyper_4_220_chunk USING btree (device_id, _ts_meta_min_1 DESC, _ts_meta_max_1 DESC, _ts_meta_min_2, _ts_meta_max_2); + + -- -- Name: compress_hyper_5_106_chunk_sensor_id__ts_meta_min_1__ts_met_idx; Type: INDEX; Schema: _timescaledb_internal; Owner: - -- @@ -9717,6 +10401,34 @@ CREATE INDEX compress_hyper_5_186_chunk_sensor_id__ts_meta_min_1__ts_met_idx ON CREATE INDEX compress_hyper_5_196_chunk_sensor_id__ts_meta_min_1__ts_met_idx ON _timescaledb_internal.compress_hyper_5_196_chunk USING btree (sensor_id, _ts_meta_min_1 DESC, _ts_meta_max_1 DESC, _ts_meta_min_2, _ts_meta_max_2); +-- +-- Name: compress_hyper_5_212_chunk_sensor_id__ts_meta_min_1__ts_met_idx; Type: INDEX; Schema: _timescaledb_internal; Owner: - +-- + +CREATE INDEX compress_hyper_5_212_chunk_sensor_id__ts_meta_min_1__ts_met_idx ON _timescaledb_internal.compress_hyper_5_212_chunk USING btree (sensor_id, _ts_meta_min_1 DESC, _ts_meta_max_1 DESC, _ts_meta_min_2, _ts_meta_max_2); + + +-- +-- Name: compress_hyper_5_216_chunk_sensor_id__ts_meta_min_1__ts_met_idx; Type: INDEX; Schema: _timescaledb_internal; Owner: - +-- + +CREATE INDEX compress_hyper_5_216_chunk_sensor_id__ts_meta_min_1__ts_met_idx ON _timescaledb_internal.compress_hyper_5_216_chunk USING btree (sensor_id, _ts_meta_min_1 DESC, _ts_meta_max_1 DESC, _ts_meta_min_2, _ts_meta_max_2); + + +-- +-- Name: compress_hyper_5_219_chunk_sensor_id__ts_meta_min_1__ts_met_idx; Type: INDEX; Schema: _timescaledb_internal; Owner: - +-- + +CREATE INDEX compress_hyper_5_219_chunk_sensor_id__ts_meta_min_1__ts_met_idx ON _timescaledb_internal.compress_hyper_5_219_chunk USING btree (sensor_id, _ts_meta_min_1 DESC, _ts_meta_max_1 DESC, _ts_meta_min_2, _ts_meta_max_2); + + +-- +-- Name: compress_hyper_5_221_chunk_sensor_id__ts_meta_min_1__ts_met_idx; Type: INDEX; Schema: _timescaledb_internal; Owner: - +-- + +CREATE INDEX compress_hyper_5_221_chunk_sensor_id__ts_meta_min_1__ts_met_idx ON _timescaledb_internal.compress_hyper_5_221_chunk USING btree (sensor_id, _ts_meta_min_1 DESC, _ts_meta_max_1 DESC, _ts_meta_min_2, _ts_meta_max_2); + + -- -- Name: compress_hyper_5_41_chunk_sensor_id__ts_meta_min_1__ts_meta_idx; Type: INDEX; Schema: _timescaledb_internal; Owner: - -- @@ -9906,6 +10618,34 @@ CREATE INDEX compress_hyper_6_187_chunk_interface_id__ts_meta_min_1__ts__idx ON CREATE INDEX compress_hyper_6_197_chunk_interface_id__ts_meta_min_1__ts__idx ON _timescaledb_internal.compress_hyper_6_197_chunk USING btree (interface_id, _ts_meta_min_1 DESC, _ts_meta_max_1 DESC); +-- +-- Name: compress_hyper_6_211_chunk_interface_id__ts_meta_min_1__ts__idx; Type: INDEX; Schema: _timescaledb_internal; Owner: - +-- + +CREATE INDEX compress_hyper_6_211_chunk_interface_id__ts_meta_min_1__ts__idx ON _timescaledb_internal.compress_hyper_6_211_chunk USING btree (interface_id, _ts_meta_min_1 DESC, _ts_meta_max_1 DESC); + + +-- +-- Name: compress_hyper_6_215_chunk_interface_id__ts_meta_min_1__ts__idx; Type: INDEX; Schema: _timescaledb_internal; Owner: - +-- + +CREATE INDEX compress_hyper_6_215_chunk_interface_id__ts_meta_min_1__ts__idx ON _timescaledb_internal.compress_hyper_6_215_chunk USING btree (interface_id, _ts_meta_min_1 DESC, _ts_meta_max_1 DESC); + + +-- +-- Name: compress_hyper_6_218_chunk_interface_id__ts_meta_min_1__ts__idx; Type: INDEX; Schema: _timescaledb_internal; Owner: - +-- + +CREATE INDEX compress_hyper_6_218_chunk_interface_id__ts_meta_min_1__ts__idx ON _timescaledb_internal.compress_hyper_6_218_chunk USING btree (interface_id, _ts_meta_min_1 DESC, _ts_meta_max_1 DESC); + + +-- +-- Name: compress_hyper_6_222_chunk_interface_id__ts_meta_min_1__ts__idx; Type: INDEX; Schema: _timescaledb_internal; Owner: - +-- + +CREATE INDEX compress_hyper_6_222_chunk_interface_id__ts_meta_min_1__ts__idx ON _timescaledb_internal.compress_hyper_6_222_chunk USING btree (interface_id, _ts_meta_min_1 DESC, _ts_meta_max_1 DESC); + + -- -- Name: compress_hyper_6_31_chunk_interface_id__ts_meta_min_1__ts_m_idx; Type: INDEX; Schema: _timescaledb_internal; Owner: - -- @@ -10291,20 +11031,6 @@ CREATE INDEX checks_check_type_index ON public.checks USING btree (check_type); CREATE INDEX checks_device_id_index ON public.checks USING btree (device_id); --- --- Name: checks_device_type_source_unique_index; Type: INDEX; Schema: public; Owner: - --- - -CREATE UNIQUE INDEX checks_device_type_source_unique_index ON public.checks USING btree (device_id, check_type, source_id) WHERE (((source_type)::text = 'auto_discovery'::text) AND (source_id IS NOT NULL)); - - --- --- Name: checks_enabled_index; Type: INDEX; Schema: public; Owner: - --- - -CREATE INDEX checks_enabled_index ON public.checks USING btree (enabled); - - -- -- Name: checks_organization_id_index; Type: INDEX; Schema: public; Owner: - -- @@ -10319,13 +11045,6 @@ CREATE INDEX checks_organization_id_index ON public.checks USING btree (organiza CREATE INDEX checks_source_id_index ON public.checks USING btree (source_id); --- --- Name: checks_source_type_index; Type: INDEX; Schema: public; Owner: - --- - -CREATE INDEX checks_source_type_index ON public.checks USING btree (source_type); - - -- -- Name: checks_source_type_source_id_index; Type: INDEX; Schema: public; Owner: - -- @@ -10711,6 +11430,13 @@ CREATE UNIQUE INDEX gaiia_inventory_items_organization_id_gaiia_id_index ON publ CREATE INDEX gaiia_inventory_items_organization_id_index ON public.gaiia_inventory_items USING btree (organization_id); +-- +-- Name: gaiia_network_sites_ip_blocks_gin_idx; Type: INDEX; Schema: public; Owner: - +-- + +CREATE INDEX gaiia_network_sites_ip_blocks_gin_idx ON public.gaiia_network_sites USING gin (ip_blocks); + + -- -- Name: gaiia_network_sites_organization_id_gaiia_id_index; Type: INDEX; Schema: public; Owner: - -- @@ -10739,6 +11465,13 @@ CREATE INDEX gaiia_network_sites_site_id_index ON public.gaiia_network_sites USI CREATE INDEX geoip_blocks_geoname_id_index ON public.geoip_blocks USING btree (geoname_id); +-- +-- Name: geoip_blocks_ip_range_gist; Type: INDEX; Schema: public; Owner: - +-- + +CREATE INDEX geoip_blocks_ip_range_gist ON public.geoip_blocks USING gist (int8range(start_ip_int, end_ip_int, '[]'::text)); + + -- -- Name: geoip_blocks_network_index; Type: INDEX; Schema: public; Owner: - -- @@ -10984,6 +11717,13 @@ CREATE INDEX monitoring_checks_device_id_checked_at_idx ON public.monitoring_che CREATE INDEX notification_digests_organization_id_index ON public.notification_digests USING btree (organization_id); +-- +-- Name: notification_digests_suppressed_alert_ids_gin_idx; Type: INDEX; Schema: public; Owner: - +-- + +CREATE INDEX notification_digests_suppressed_alert_ids_gin_idx ON public.notification_digests USING gin (suppressed_alert_ids); + + -- -- Name: notification_digests_user_id_window_start_index; Type: INDEX; Schema: public; Owner: - -- @@ -11390,6 +12130,20 @@ CREATE INDEX preseem_sync_logs_integration_id_index ON public.preseem_sync_logs CREATE INDEX preseem_sync_logs_organization_id_index ON public.preseem_sync_logs USING btree (organization_id); +-- +-- Name: printer_supplies_snmp_device_id_index; Type: INDEX; Schema: public; Owner: - +-- + +CREATE INDEX printer_supplies_snmp_device_id_index ON public.printer_supplies USING btree (snmp_device_id); + + +-- +-- Name: printer_supplies_snmp_device_id_supply_index_index; Type: INDEX; Schema: public; Owner: - +-- + +CREATE UNIQUE INDEX printer_supplies_snmp_device_id_supply_index_index ON public.printer_supplies USING btree (snmp_device_id, supply_index); + + -- -- Name: profile_device_oids_profile_id_field_index; Type: INDEX; Schema: public; Owner: - -- @@ -11558,6 +12312,48 @@ CREATE INDEX snmp_arp_entries_mac_address_index ON public.snmp_arp_entries USING CREATE UNIQUE INDEX snmp_devices_equipment_id_index ON public.snmp_devices USING btree (device_id); +-- +-- Name: snmp_entity_physical_entity_class_index; Type: INDEX; Schema: public; Owner: - +-- + +CREATE INDEX snmp_entity_physical_entity_class_index ON public.snmp_entity_physical USING btree (entity_class); + + +-- +-- Name: snmp_entity_physical_parent_id_index; Type: INDEX; Schema: public; Owner: - +-- + +CREATE INDEX snmp_entity_physical_parent_id_index ON public.snmp_entity_physical USING btree (parent_id); + + +-- +-- Name: snmp_entity_physical_readings_entity_physical_id_measured_at_in; Type: INDEX; Schema: public; Owner: - +-- + +CREATE INDEX snmp_entity_physical_readings_entity_physical_id_measured_at_in ON public.snmp_entity_physical_readings USING btree (entity_physical_id, measured_at); + + +-- +-- Name: snmp_entity_physical_readings_measured_at_index; Type: INDEX; Schema: public; Owner: - +-- + +CREATE INDEX snmp_entity_physical_readings_measured_at_index ON public.snmp_entity_physical_readings USING btree (measured_at); + + +-- +-- Name: snmp_entity_physical_snmp_device_id_entity_index_index; Type: INDEX; Schema: public; Owner: - +-- + +CREATE UNIQUE INDEX snmp_entity_physical_snmp_device_id_entity_index_index ON public.snmp_entity_physical USING btree (snmp_device_id, entity_index); + + +-- +-- Name: snmp_entity_physical_snmp_device_id_index; Type: INDEX; Schema: public; Owner: - +-- + +CREATE INDEX snmp_entity_physical_snmp_device_id_index ON public.snmp_entity_physical USING btree (snmp_device_id); + + -- -- Name: snmp_interface_stats_checked_at_idx; Type: INDEX; Schema: public; Owner: - -- @@ -11670,6 +12466,41 @@ CREATE INDEX snmp_memory_pools_snmp_device_id_index ON public.snmp_memory_pools CREATE UNIQUE INDEX snmp_memory_pools_snmp_device_id_pool_index_index ON public.snmp_memory_pools USING btree (snmp_device_id, pool_index); +-- +-- Name: snmp_mempool_readings_checked_at_index; Type: INDEX; Schema: public; Owner: - +-- + +CREATE INDEX snmp_mempool_readings_checked_at_index ON public.snmp_mempool_readings USING btree (checked_at); + + +-- +-- Name: snmp_mempool_readings_mempool_id_checked_at_index; Type: INDEX; Schema: public; Owner: - +-- + +CREATE INDEX snmp_mempool_readings_mempool_id_checked_at_index ON public.snmp_mempool_readings USING btree (mempool_id, checked_at); + + +-- +-- Name: snmp_mempool_readings_mempool_id_index; Type: INDEX; Schema: public; Owner: - +-- + +CREATE INDEX snmp_mempool_readings_mempool_id_index ON public.snmp_mempool_readings USING btree (mempool_id); + + +-- +-- Name: snmp_mempools_snmp_device_id_index; Type: INDEX; Schema: public; Owner: - +-- + +CREATE INDEX snmp_mempools_snmp_device_id_index ON public.snmp_mempools USING btree (snmp_device_id); + + +-- +-- Name: snmp_mempools_snmp_device_id_mempool_index_index; Type: INDEX; Schema: public; Owner: - +-- + +CREATE UNIQUE INDEX snmp_mempools_snmp_device_id_mempool_index_index ON public.snmp_mempools USING btree (snmp_device_id, mempool_index); + + -- -- Name: snmp_neighbors_equipment_id_index; Type: INDEX; Schema: public; Owner: - -- @@ -11894,6 +12725,48 @@ CREATE UNIQUE INDEX snmp_storage_snmp_device_id_storage_index_index ON public.sn CREATE INDEX snmp_storage_storage_type_index ON public.snmp_storage USING btree (storage_type); +-- +-- Name: snmp_transceiver_readings_measured_at_index; Type: INDEX; Schema: public; Owner: - +-- + +CREATE INDEX snmp_transceiver_readings_measured_at_index ON public.snmp_transceiver_readings USING btree (measured_at); + + +-- +-- Name: snmp_transceiver_readings_transceiver_id_index; Type: INDEX; Schema: public; Owner: - +-- + +CREATE INDEX snmp_transceiver_readings_transceiver_id_index ON public.snmp_transceiver_readings USING btree (transceiver_id); + + +-- +-- Name: snmp_transceiver_readings_transceiver_id_measured_at_index; Type: INDEX; Schema: public; Owner: - +-- + +CREATE INDEX snmp_transceiver_readings_transceiver_id_measured_at_index ON public.snmp_transceiver_readings USING btree (transceiver_id, measured_at); + + +-- +-- Name: snmp_transceivers_entity_physical_id_index; Type: INDEX; Schema: public; Owner: - +-- + +CREATE INDEX snmp_transceivers_entity_physical_id_index ON public.snmp_transceivers USING btree (entity_physical_id); + + +-- +-- Name: snmp_transceivers_snmp_device_id_port_index_index; Type: INDEX; Schema: public; Owner: - +-- + +CREATE UNIQUE INDEX snmp_transceivers_snmp_device_id_port_index_index ON public.snmp_transceivers USING btree (snmp_device_id, port_index); + + +-- +-- Name: snmp_transceivers_transceiver_type_index; Type: INDEX; Schema: public; Owner: - +-- + +CREATE INDEX snmp_transceivers_transceiver_type_index ON public.snmp_transceivers USING btree (transceiver_type); + + -- -- Name: snmp_vlans_snmp_device_id_index; Type: INDEX; Schema: public; Owner: - -- @@ -12160,6 +13033,13 @@ CREATE INDEX wireless_clients_device_id_index ON public.wireless_clients USING b CREATE UNIQUE INDEX wireless_clients_device_id_mac_address_index ON public.wireless_clients USING btree (device_id, mac_address); +-- +-- Name: wireless_clients_lower_hostname_idx; Type: INDEX; Schema: public; Owner: - +-- + +CREATE INDEX wireless_clients_lower_hostname_idx ON public.wireless_clients USING btree (lower((hostname)::text)); + + -- -- Name: wireless_clients_mac_address_index; Type: INDEX; Schema: public; Owner: - -- @@ -13766,6 +14646,14 @@ ALTER TABLE ONLY public.preseem_sync_logs ADD CONSTRAINT preseem_sync_logs_organization_id_fkey FOREIGN KEY (organization_id) REFERENCES public.organizations(id) ON DELETE CASCADE; +-- +-- Name: printer_supplies printer_supplies_snmp_device_id_fkey; Type: FK CONSTRAINT; Schema: public; Owner: - +-- + +ALTER TABLE ONLY public.printer_supplies + ADD CONSTRAINT printer_supplies_snmp_device_id_fkey FOREIGN KEY (snmp_device_id) REFERENCES public.snmp_devices(id) ON DELETE CASCADE; + + -- -- Name: profile_device_oids profile_device_oids_profile_id_fkey; Type: FK CONSTRAINT; Schema: public; Owner: - -- @@ -13878,6 +14766,30 @@ ALTER TABLE ONLY public.snmp_devices ADD CONSTRAINT snmp_devices_device_id_fkey FOREIGN KEY (device_id) REFERENCES public.devices(id) ON DELETE CASCADE; +-- +-- Name: snmp_entity_physical snmp_entity_physical_parent_id_fkey; Type: FK CONSTRAINT; Schema: public; Owner: - +-- + +ALTER TABLE ONLY public.snmp_entity_physical + ADD CONSTRAINT snmp_entity_physical_parent_id_fkey FOREIGN KEY (parent_id) REFERENCES public.snmp_entity_physical(id) ON DELETE SET NULL; + + +-- +-- Name: snmp_entity_physical_readings snmp_entity_physical_readings_entity_physical_id_fkey; Type: FK CONSTRAINT; Schema: public; Owner: - +-- + +ALTER TABLE ONLY public.snmp_entity_physical_readings + ADD CONSTRAINT snmp_entity_physical_readings_entity_physical_id_fkey FOREIGN KEY (entity_physical_id) REFERENCES public.snmp_entity_physical(id) ON DELETE CASCADE; + + +-- +-- Name: snmp_entity_physical snmp_entity_physical_snmp_device_id_fkey; Type: FK CONSTRAINT; Schema: public; Owner: - +-- + +ALTER TABLE ONLY public.snmp_entity_physical + ADD CONSTRAINT snmp_entity_physical_snmp_device_id_fkey FOREIGN KEY (snmp_device_id) REFERENCES public.snmp_devices(id) ON DELETE CASCADE; + + -- -- Name: snmp_interface_stats snmp_interface_stats_interface_id_fkey; Type: FK CONSTRAINT; Schema: public; Owner: - -- @@ -13926,6 +14838,22 @@ ALTER TABLE ONLY public.snmp_memory_pools ADD CONSTRAINT snmp_memory_pools_snmp_device_id_fkey FOREIGN KEY (snmp_device_id) REFERENCES public.snmp_devices(id) ON DELETE CASCADE; +-- +-- Name: snmp_mempool_readings snmp_mempool_readings_mempool_id_fkey; Type: FK CONSTRAINT; Schema: public; Owner: - +-- + +ALTER TABLE ONLY public.snmp_mempool_readings + ADD CONSTRAINT snmp_mempool_readings_mempool_id_fkey FOREIGN KEY (mempool_id) REFERENCES public.snmp_mempools(id) ON DELETE CASCADE; + + +-- +-- Name: snmp_mempools snmp_mempools_snmp_device_id_fkey; Type: FK CONSTRAINT; Schema: public; Owner: - +-- + +ALTER TABLE ONLY public.snmp_mempools + ADD CONSTRAINT snmp_mempools_snmp_device_id_fkey FOREIGN KEY (snmp_device_id) REFERENCES public.snmp_devices(id) ON DELETE CASCADE; + + -- -- Name: snmp_neighbors snmp_neighbors_device_id_fkey; Type: FK CONSTRAINT; Schema: public; Owner: - -- @@ -14014,6 +14942,30 @@ ALTER TABLE ONLY public.snmp_storage ADD CONSTRAINT snmp_storage_snmp_device_id_fkey FOREIGN KEY (snmp_device_id) REFERENCES public.snmp_devices(id) ON DELETE CASCADE; +-- +-- Name: snmp_transceiver_readings snmp_transceiver_readings_transceiver_id_fkey; Type: FK CONSTRAINT; Schema: public; Owner: - +-- + +ALTER TABLE ONLY public.snmp_transceiver_readings + ADD CONSTRAINT snmp_transceiver_readings_transceiver_id_fkey FOREIGN KEY (transceiver_id) REFERENCES public.snmp_transceivers(id) ON DELETE CASCADE; + + +-- +-- Name: snmp_transceivers snmp_transceivers_entity_physical_id_fkey; Type: FK CONSTRAINT; Schema: public; Owner: - +-- + +ALTER TABLE ONLY public.snmp_transceivers + ADD CONSTRAINT snmp_transceivers_entity_physical_id_fkey FOREIGN KEY (entity_physical_id) REFERENCES public.snmp_entity_physical(id) ON DELETE SET NULL; + + +-- +-- Name: snmp_transceivers snmp_transceivers_snmp_device_id_fkey; Type: FK CONSTRAINT; Schema: public; Owner: - +-- + +ALTER TABLE ONLY public.snmp_transceivers + ADD CONSTRAINT snmp_transceivers_snmp_device_id_fkey FOREIGN KEY (snmp_device_id) REFERENCES public.snmp_devices(id) ON DELETE CASCADE; + + -- -- Name: snmp_vlans snmp_vlans_snmp_device_id_fkey; Type: FK CONSTRAINT; Schema: public; Owner: - -- @@ -14178,7 +15130,7 @@ ALTER TABLE ONLY public.wireless_clients -- PostgreSQL database dump complete -- -\unrestrict 58n9yz3M1gCN5t2tMwVCXpismPQgdWzmGfJI4AZxbUhDND1zz8QIj8oDYzqLMz8 +\unrestrict fxN8VfMT4wlKMdY4b5QKMDFncMWuvcHmQoAKL88Wv4ey2erB35CfSsmUYUTugSQ INSERT INTO public."schema_migrations" (version) VALUES (20251221192340); INSERT INTO public."schema_migrations" (version) VALUES (20251221192454); @@ -14378,3 +15330,16 @@ INSERT INTO public."schema_migrations" (version) VALUES (20260324193820); INSERT INTO public."schema_migrations" (version) VALUES (20260325180211); INSERT INTO public."schema_migrations" (version) VALUES (20260325200000); INSERT INTO public."schema_migrations" (version) VALUES (20260325215632); +INSERT INTO public."schema_migrations" (version) VALUES (20260326185002); +INSERT INTO public."schema_migrations" (version) VALUES (20260326214418); +INSERT INTO public."schema_migrations" (version) VALUES (20260326214419); +INSERT INTO public."schema_migrations" (version) VALUES (20260326221432); +INSERT INTO public."schema_migrations" (version) VALUES (20260326223000); +INSERT INTO public."schema_migrations" (version) VALUES (20260326223100); +INSERT INTO public."schema_migrations" (version) VALUES (20260327000000); +INSERT INTO public."schema_migrations" (version) VALUES (20260327113929); +INSERT INTO public."schema_migrations" (version) VALUES (20260327231100); +INSERT INTO public."schema_migrations" (version) VALUES (20260404000001); +INSERT INTO public."schema_migrations" (version) VALUES (20260404000002); +INSERT INTO public."schema_migrations" (version) VALUES (20260404000003); +INSERT INTO public."schema_migrations" (version) VALUES (20260428170617); diff --git a/test/test_helper.exs b/test/test_helper.exs index 95edb370..2ad96330 100644 --- a/test/test_helper.exs +++ b/test/test_helper.exs @@ -63,6 +63,7 @@ ExUnit.configure( Mox.defmock(Towerops.Monitoring.PingMock, for: Towerops.Monitoring.PingBehaviour) Mox.defmock(Towerops.Snmp.PollerMock, for: Towerops.Snmp.PollerBehaviour) Mox.defmock(Towerops.Snmp.SnmpMock, for: Towerops.Snmp.SnmpBehaviour) +Mox.defmock(Towerops.RateLimit.RedisClientMock, for: Towerops.RateLimit.RedisClient) # Define stub module for SNMP mock (returns errors for all calls) defmodule Towerops.Snmp.SnmpMockStub do diff --git a/test/towerops/on_call/escalation_policy_test.exs b/test/towerops/on_call/escalation_policy_test.exs index f0ac60aa..6941c125 100644 --- a/test/towerops/on_call/escalation_policy_test.exs +++ b/test/towerops/on_call/escalation_policy_test.exs @@ -110,5 +110,37 @@ defmodule Towerops.OnCall.EscalationPolicyTest do assert updated.description == "Updated description" assert updated.repeat_count == 10 end + + test "defaults handoff_notifications_mode to \"when_in_use_by_service\"", %{organization: org} do + {:ok, policy} = + Towerops.OnCall.create_escalation_policy(%{name: "p", organization_id: org.id}) + + assert policy.handoff_notifications_mode == "when_in_use_by_service" + end + + test "accepts the valid handoff_notifications_mode values", %{organization: org} do + for mode <- ~w(when_in_use_by_service always never) do + {:ok, policy} = + Towerops.OnCall.create_escalation_policy(%{ + name: "p-#{mode}", + organization_id: org.id, + handoff_notifications_mode: mode + }) + + assert policy.handoff_notifications_mode == mode + end + end + + test "rejects invalid handoff_notifications_mode values", %{organization: org} do + changeset = + EscalationPolicy.changeset(%EscalationPolicy{}, %{ + name: "p", + organization_id: org.id, + handoff_notifications_mode: "garbage" + }) + + refute changeset.valid? + assert errors_on(changeset).handoff_notifications_mode + end end end diff --git a/test/towerops/rate_limit/redis_test.exs b/test/towerops/rate_limit/redis_test.exs new file mode 100644 index 00000000..592116c9 --- /dev/null +++ b/test/towerops/rate_limit/redis_test.exs @@ -0,0 +1,185 @@ +defmodule Towerops.RateLimit.RedisTest do + use ExUnit.Case, async: true + + import Mox + + alias Towerops.RateLimit.Redis + alias Towerops.RateLimit.RedisClient.Redix + alias Towerops.RateLimit.RedisClientMock + + setup :verify_on_exit! + + describe "hit/5" do + test "returns {:allow, count} when count is below the limit" do + expect(RedisClientMock, :pipeline, fn :conn, [["INCRBY", key, "1"], ["PEXPIRE", key, _ttl]] -> + assert key =~ ~r/^towerops:rl:user:1:\d+$/ + {:ok, [3, 1]} + end) + + assert {:allow, 3} = Redis.hit(:conn, "user:1", 60_000, 5) + end + + test "returns {:deny, ttl_ms} when count exceeds the limit" do + expect(RedisClientMock, :pipeline, fn :conn, + [ + ["INCRBY", _key, "1"], + ["PEXPIRE", _, ttl_str] + ] -> + ttl = String.to_integer(ttl_str) + assert ttl > 0 + # Return count above the limit + {:ok, [11, 1]} + end) + + assert {:deny, retry_after} = Redis.hit(:conn, "user:1", 60_000, 10) + assert retry_after > 0 + assert retry_after <= 60_000 + end + + test "passes the configured prefix through to the Redis key" do + expect(RedisClientMock, :pipeline, fn :conn, [["INCRBY", key, _], ["PEXPIRE", _, _]] -> + assert String.starts_with?(key, "myapp:rate:") + {:ok, [1, 1]} + end) + + Redis.hit(:conn, "abc", 1_000, 5, prefix: "myapp:rate") + end + + test "uses INCRBY with the requested increment" do + expect(RedisClientMock, :pipeline, fn :conn, [["INCRBY", _key, increment], ["PEXPIRE", _, _]] -> + assert increment == "7" + {:ok, [7, 1]} + end) + + assert {:allow, 7} = Redis.hit(:conn, "u", 1_000, 100, increment: 7) + end + + test "an increment of 0 is allowed and reports the existing count" do + expect(RedisClientMock, :pipeline, fn :conn, [["INCRBY", _key, "0"], ["PEXPIRE", _, _]] -> + {:ok, [4, 1]} + end) + + assert {:allow, 4} = Redis.hit(:conn, "u", 1_000, 5, increment: 0) + end + + test "raises when increment is negative" do + assert_raise ArgumentError, ~r/non-negative integer/, fn -> + Redis.hit(:conn, "u", 1_000, 5, increment: -1) + end + end + + test "raises when increment is not an integer" do + assert_raise ArgumentError, ~r/non-negative integer/, fn -> + Redis.hit(:conn, "u", 1_000, 5, increment: :not_a_number) + end + end + + test "returns {:error, reason} when the Redis pipeline fails" do + expect(RedisClientMock, :pipeline, fn :conn, _ -> {:error, :closed} end) + assert {:error, :closed} = Redis.hit(:conn, "u", 1_000, 5) + end + + test "returns {:error, ...} when the pipeline result has an unexpected shape" do + expect(RedisClientMock, :pipeline, fn :conn, _ -> {:ok, ["not", "an", "integer"]} end) + + assert {:error, {:unexpected_pipeline_result, ["not", "an", "integer"]}} = + Redis.hit(:conn, "u", 1_000, 5) + end + + test "raises a FunctionClauseError on non-binary keys" do + assert_raise FunctionClauseError, fn -> + Redis.hit(:conn, :atom_key, 1_000, 5) + end + end + + test "raises on non-positive scale or limit" do + assert_raise FunctionClauseError, fn -> Redis.hit(:conn, "u", 0, 5) end + assert_raise FunctionClauseError, fn -> Redis.hit(:conn, "u", 1_000, 0) end + end + end + + describe "get/4" do + test "returns 0 when the bucket is missing" do + expect(RedisClientMock, :pipeline, fn :conn, [["GET", _key]] -> {:ok, [nil]} end) + assert 0 = Redis.get(:conn, "absent", 1_000) + end + + test "decodes the binary integer count" do + expect(RedisClientMock, :pipeline, fn :conn, [["GET", _key]] -> {:ok, ["42"]} end) + assert 42 = Redis.get(:conn, "u", 1_000) + end + + test "applies the prefix" do + expect(RedisClientMock, :pipeline, fn :conn, [["GET", key]] -> + assert String.starts_with?(key, "p:") + {:ok, [nil]} + end) + + Redis.get(:conn, "u", 1_000, prefix: "p") + end + + test "propagates Redis errors" do + expect(RedisClientMock, :pipeline, fn :conn, _ -> {:error, :timeout} end) + assert {:error, :timeout} = Redis.get(:conn, "u", 1_000) + end + end + + describe "reset/4" do + test "issues DEL and returns :ok" do + expect(RedisClientMock, :pipeline, fn :conn, [["DEL", key]] -> + assert key =~ ~r/^towerops:rl:u:\d+$/ + {:ok, [1]} + end) + + assert :ok = Redis.reset(:conn, "u", 1_000) + end + + test "is :ok even when the key did not exist" do + expect(RedisClientMock, :pipeline, fn :conn, [["DEL", _key]] -> {:ok, [0]} end) + assert :ok = Redis.reset(:conn, "u", 1_000) + end + + test "propagates Redis errors" do + expect(RedisClientMock, :pipeline, fn :conn, _ -> {:error, :closed} end) + assert {:error, :closed} = Redis.reset(:conn, "u", 1_000) + end + + test "applies the prefix" do + expect(RedisClientMock, :pipeline, fn :conn, [["DEL", key]] -> + assert String.starts_with?(key, "rp:") + {:ok, [0]} + end) + + Redis.reset(:conn, "u", 1_000, prefix: "rp") + end + end + + describe "RedisClient.Redix adapter" do + test "delegates pipeline/2 to Redix.pipeline/2" do + # Calling against a non-existent connection should raise/exit because + # Redix.pipeline/2 expects a registered process. Whatever the precise + # failure mode is, executing the adapter line proves delegation runs. + Code.ensure_loaded!(Redix) + assert function_exported?(Redix, :pipeline, 2) + + result = + try do + Redix.pipeline( + :__towerops_rl_no_such_conn__, + [["PING"]] + ) + catch + kind, reason -> {kind, reason} + end + + # Either Redix returns an error tuple, or it raises/exits because the + # process name isn't registered. Both prove the delegation reaches Redix. + case result do + {:error, _} -> :ok + {:exit, _} -> :ok + {:error_tuple_or_other, _} -> :ok + other -> flunk("unexpected result from adapter delegation: #{inspect(other)}") + end + end + end +end diff --git a/test/towerops/rate_limit_test.exs b/test/towerops/rate_limit_test.exs new file mode 100644 index 00000000..620aa55a --- /dev/null +++ b/test/towerops/rate_limit_test.exs @@ -0,0 +1,221 @@ +defmodule Towerops.RateLimitTest do + use ExUnit.Case, async: false + + alias Towerops.RateLimit + + # Each test uses an isolated ETS table by passing a unique :table option. + # The supervised RateLimit instance (used by the application) is left untouched. + + setup do + table = :"rl_test_#{System.unique_integer([:positive])}" + + pid = + start_supervised!( + {RateLimit, + [ + name: :"rl_proc_#{System.unique_integer([:positive])}", + table: table, + clean_period: 60_000 + ]} + ) + + %{table: table, pid: pid} + end + + describe "hit/4" do + test "allows the first request and returns the count", %{table: table} do + assert {:allow, 1} = RateLimit.hit(table, "alice", 1_000, 5) + end + + test "allows requests up to the limit", %{table: table} do + assert {:allow, 1} = RateLimit.hit(table, "bob", 1_000, 3) + assert {:allow, 2} = RateLimit.hit(table, "bob", 1_000, 3) + assert {:allow, 3} = RateLimit.hit(table, "bob", 1_000, 3) + end + + test "denies requests over the limit and returns ms until window expires", %{table: table} do + Enum.each(1..3, fn _ -> RateLimit.hit(table, "carol", 60_000, 3) end) + + assert {:deny, retry_after} = RateLimit.hit(table, "carol", 60_000, 3) + assert retry_after > 0 + assert retry_after <= 60_000 + end + + test "different keys have independent counters", %{table: table} do + assert {:allow, 1} = RateLimit.hit(table, "k1", 1_000, 1) + assert {:deny, _} = RateLimit.hit(table, "k1", 1_000, 1) + assert {:allow, 1} = RateLimit.hit(table, "k2", 1_000, 1) + end + + test "supports custom increment", %{table: table} do + assert {:allow, 5} = RateLimit.hit(table, "dave", 1_000, 10, 5) + assert {:allow, 10} = RateLimit.hit(table, "dave", 1_000, 10, 5) + assert {:deny, _} = RateLimit.hit(table, "dave", 1_000, 10, 5) + end + + test "increment of 0 does not advance the counter", %{table: table} do + assert {:allow, 1} = RateLimit.hit(table, "eve", 1_000, 5) + assert {:allow, 1} = RateLimit.hit(table, "eve", 1_000, 5, 0) + end + + test "moving to a new window resets the counter", %{table: table} do + # Use a 50ms window so we can wait through it. + Enum.each(1..2, fn _ -> RateLimit.hit(table, "frank", 50, 2) end) + assert {:deny, _} = RateLimit.hit(table, "frank", 50, 2) + + Process.sleep(70) + + assert {:allow, 1} = RateLimit.hit(table, "frank", 50, 2) + end + end + + describe "hit/3 (default increment)" do + test "uses an increment of 1", %{table: table} do + assert {:allow, 1} = RateLimit.hit(table, "x", 1_000, 5) + assert {:allow, 2} = RateLimit.hit(table, "x", 1_000, 5) + end + end + + describe "default-table convenience arities" do + # These exercise the supervised Towerops.RateLimit instance started by + # the application supervisor (which owns the @default_table). + + test "hit/3 uses the default table" do + key = "default-hit-3-#{System.unique_integer([:positive])}" + assert {:allow, 1} = RateLimit.hit(key, 60_000, 5) + assert {:allow, 2} = RateLimit.hit(key, 60_000, 5) + end + + test "hit/4 uses the default table when called with non-atom first arg" do + key = "default-hit-4-#{System.unique_integer([:positive])}" + assert {:allow, 3} = RateLimit.hit(key, 60_000, 10, 3) + end + + test "get/2 reads from the default table" do + key = "default-get-#{System.unique_integer([:positive])}" + assert 0 = RateLimit.get(key, 60_000) + RateLimit.hit(key, 60_000, 5) + assert 1 = RateLimit.get(key, 60_000) + end + + test "reset/2 deletes from the default table" do + key = "default-reset-#{System.unique_integer([:positive])}" + RateLimit.hit(key, 60_000, 5) + assert :ok = RateLimit.reset(key, 60_000) + assert 0 = RateLimit.get(key, 60_000) + end + end + + describe "get/3" do + test "returns 0 for keys that have never been hit", %{table: table} do + assert 0 = RateLimit.get(table, "never", 1_000) + end + + test "returns the current count for an active key", %{table: table} do + RateLimit.hit(table, "g", 60_000, 5) + RateLimit.hit(table, "g", 60_000, 5) + assert 2 = RateLimit.get(table, "g", 60_000) + end + end + + describe "reset/2" do + test "clears the count for the current window", %{table: table} do + Enum.each(1..2, fn _ -> RateLimit.hit(table, "r", 60_000, 2) end) + assert {:deny, _} = RateLimit.hit(table, "r", 60_000, 2) + + :ok = RateLimit.reset(table, "r", 60_000) + + assert {:allow, 1} = RateLimit.hit(table, "r", 60_000, 2) + end + + test "is a no-op for keys that don't exist", %{table: table} do + assert :ok = RateLimit.reset(table, "absent", 60_000) + end + end + + describe "cleanup" do + test "removes expired entries when clean is invoked", %{table: table, pid: pid} do + RateLimit.hit(table, "a", 30, 5) + RateLimit.hit(table, "b", 30, 5) + assert :ets.info(table, :size) == 2 + + Process.sleep(50) + send(pid, :clean) + # Allow the GenServer to process the message + _ = :sys.get_state(pid) + + assert :ets.info(table, :size) == 0 + end + + test "preserves entries that have not yet expired", %{table: table, pid: pid} do + RateLimit.hit(table, "live", 60_000, 5) + assert :ets.info(table, :size) == 1 + + send(pid, :clean) + _ = :sys.get_state(pid) + + assert :ets.info(table, :size) == 1 + end + + test "automatic periodic cleanup runs on schedule" do + table = :"rl_auto_#{System.unique_integer([:positive])}" + + pid = + start_supervised!( + {RateLimit, + [ + name: :"rl_auto_proc_#{System.unique_integer([:positive])}", + table: table, + clean_period: 30 + ]}, + id: :auto_clean + ) + + RateLimit.hit(table, "expiring", 20, 5) + assert :ets.info(table, :size) == 1 + + # Wait for entries to expire and the next scheduled cleanup tick. + Process.sleep(80) + _ = :sys.get_state(pid) + + assert :ets.info(table, :size) == 0 + end + end + + describe "start_link/1" do + test "exposes a child_spec with the configured name" do + table = :"rl_cs_#{System.unique_integer([:positive])}" + name = :"rl_cs_proc_#{System.unique_integer([:positive])}" + + spec = RateLimit.child_spec(name: name, table: table, clean_period: 1_000) + + assert %{id: RateLimit, start: {RateLimit, :start_link, _}, type: :worker} = + spec + end + + test "child_spec id can be overridden" do + spec = RateLimit.child_spec(name: :foo, table: :foo_t, clean_period: 1_000, id: :custom) + assert spec.id == :custom + end + + test "uses sensible defaults when options are omitted" do + table = :"rl_def_#{System.unique_integer([:positive])}" + name = :"rl_def_proc_#{System.unique_integer([:positive])}" + + pid = start_supervised!({RateLimit, [name: name, table: table]}, id: :defaults) + + state = :sys.get_state(pid) + assert state.clean_period == 60_000 + assert state.table == table + end + + test "rejects negative scale by raising during update_counter" do + # Defensive: the public API does not validate, but callers pass positive + # ints. We document this contract by exercising a positive-only call. + table = :"rl_validate_#{System.unique_integer([:positive])}" + _pid = start_supervised!({RateLimit, [name: :rl_validate_proc, table: table]}, id: :validate) + + assert {:allow, 1} = RateLimit.hit(table, "ok", 1, 1) + end + end +end diff --git a/test/towerops_web/plugs/rate_limit_test.exs b/test/towerops_web/plugs/rate_limit_test.exs index 421f164c..7555e8d3 100644 --- a/test/towerops_web/plugs/rate_limit_test.exs +++ b/test/towerops_web/plugs/rate_limit_test.exs @@ -3,7 +3,7 @@ defmodule ToweropsWeb.Plugs.RateLimitTest do alias ToweropsWeb.Plugs.RateLimit - # Use async: false because we're testing Hammer state + # Use async: false because we're testing shared rate-limiter state setup do # Enable rate limiting for this test module (disabled by default in test env)