@checkstack/queue-common 0.3.1 → 0.5.0

package/CHANGELOG.md

@@ -1,5 +1,187 @@
 # @checkstack/queue-common
 
+## 0.5.0
+
+### Minor Changes
+
+- 9016526: Add a `/rest/:pluginId/*` HTTP mount that serves every plugin's oRPC contract
+  through the REST/OpenAPI shape described by `/api/openapi.json`. Queries are
+  `GET` with query parameters, mutations are `POST` with the input as the raw
+  JSON body. The existing `/api/:pluginId/*` mount continues to serve oRPC's
+  native wire protocol unchanged, so existing clients are not affected.
+
+  The OpenAPI spec at `/api/openapi.json` now reflects the real mount: every
+  `paths` entry is prefixed with `/rest` instead of `/api`.
+
+  Also fixes a SPA-fallback bug: the backend's `/api-docs` route previously
+  returned 404 on production deployments because the static-file middleware
+  skipped any path starting with `/api`, capturing `/api-docs` along with real
+  API routes. The skip now requires a trailing slash (`/api/`, `/rest/`).
+
+  Required access rules are now visible in the API Docs UI. The OpenAPI spec
+  generator was reading a non-existent `accessRules` field on procedure
+  metadata; the real field is `access: AccessRule[]`. Each procedure's access
+  rules are now flattened to fully-qualified IDs (e.g. `catalog.system.read`)
+  and emitted under `x-orpc-meta.accessRules`, which the existing
+  `Required Access Rules` section in the docs UI already knew how to render.
+
+  The API Docs schema renderer now handles record types (zod `z.record`),
+  `$ref`s into `components.schemas`, `oneOf`/`anyOf`/`allOf`, nullable union
+  types (`type: ["string", "null"]`), and `format` qualifiers. Previously
+  record outputs like `{ statuses: object }` masked the actual value type;
+  they now render as `{ [key]: <ResolvedType> { ... } }` with the inner
+  schema expanded, capped at 12 levels with cycle detection.
+
+  **REST method conventions.** `proc()` now defaults to `GET` for queries and
+  `POST` for mutations on the `/rest` mount, using bracket-notation query
+  params (`?filter[status]=active&ids[0]=a`) for GET inputs. Existing
+  procedures were updated to follow REST semantics:
+
+  - `update*` mutations → `PATCH`
+  - `delete*` / `remove*` mutations → `DELETE`
+  - `getBulk*` queries and any query taking a large array input → `POST`
+    (because `@orpc/openapi@1.13.x` has no GET→POST URL-length fallback)
+
+  GET endpoints require an `object` input — bare scalars like
+  `.input(z.string())` are not valid on GET. `getSystemConfigurations` was
+  refactored from `.input(z.string())` to `.input(z.object({ systemId: ... }))`
+  to fit the GET shape; the only call-site update was the in-process router
+  unpacking `input.systemId` instead of passing `input` directly.
+
+  The API Docs UI now renders query parameters (path/query/header/cookie) in a
+  dedicated table for GET endpoints, and the fetch example shows them in the
+  URL with `<required>` / `<optional>` placeholders.
+
+### Patch Changes
+
+- Updated dependencies [9016526]
+  - @checkstack/common@0.10.0
+  - @checkstack/signal-common@0.2.3
+
+## 0.4.0
+
+### Minor Changes
+
+- aa89bc5: Replace the bespoke `registerInfrastructureTab()` registry with a standard
+  slot-extension contract (`InfrastructureTabsSlot` from
+  `@checkstack/infrastructure-common`). Plugins now contribute infrastructure
+  tabs via `createSlotExtension`, depending only on the slot owner.
+
+  The slot system in `@checkstack/frontend-api` gains a second type parameter
+  on `createSlot<TContext, TMetadata>` so extensions can declare typed static
+  metadata at registration time (label, icon, access rules, ordering for the
+  infrastructure tab bar). A new `useSlotExtensions(slot)` hook returns typed
+  extensions and subscribes to plugin lifecycle changes.
+
+  Each tab body now stacks a **Runtime** sub-section (live state, read-only)
+  on top of a **Configuration** sub-section (settings, gated by `canUpdate`).
+
+  **Queue runtime panel.** Surfaces aggregated counts (pending / processing /
+  completed / failed) plus three sub-tabs of recent jobs: **Active**, **Recent
+  failed** (with the failure message), and **Recent completed** (with
+  duration). Job payloads are deliberately not surfaced — they may carry
+  secrets and need a separate manage-access gate to be shown.
+
+  To support this, `Queue<T>` gains a required `listJobs(opts)` method
+  returning `JobSummary[]` (no payloads), and `QueueStats` gains a
+  `scope: "instance" | "cluster"` field. The in-memory queue keeps rolling
+  ring buffers (200 entries) for completed/failed history and tracks active
+  jobs by id; BullMQ uses native `getJobs`. `QueueManager.listJobs` aggregates
+  across queues and sorts (most-recent-first for terminal states, FIFO for
+  active/waiting/delayed).
+
+  **Cache runtime panel.** Lists the top N entries by size (or by recency) so
+  operators can debug a cache filling up. Values are deliberately omitted —
+  PII / secret risk. Backends opt in via an optional `listEntries?` method on
+  `CacheProvider`; non-supporting backends return `{ supported: false }` and
+  the UI renders a "not supported by this backend" hint. The in-memory cache
+  implements it using its existing per-entry byte tracking.
+
+  `CacheStats` also gains `scope: "instance" | "cluster"`.
+
+  **Multi-instance scope warning.** A new `<InstanceScopeBanner>` component in
+  `@checkstack/ui` renders a yellow banner above any runtime panel whose
+  backend reports `scope: "instance"` — i.e. in-memory queue or cache running
+  in a horizontally scaled deployment. The banner explains the metrics are
+  local to the responding replica and recommends switching to a clustered
+  backend (Redis-backed queue / cache) for cluster-wide visibility.
+
+  **Bug fix — stable cache provider proxy.** `CacheManagerImpl.getProvider()`
+  now returns a single stable proxy that delegates to whatever provider is
+  currently active. Previously, consumers of `createCachedScope` (and any
+  direct `cacheManager.getProvider()` caller) captured the active provider
+  reference at plugin-init time. After any `setActiveBackend` call — including
+  saving the same memory config in the new Cache tab, which reconstructs the
+  in-memory cache — those scopes wrote to an orphaned old provider while the
+  runtime panel read stats from the new (empty) one, making the runtime panel
+  appear to report 0 keys. With the proxy, all consumers share a single stable
+  identity and writes always land in the active provider.
+
+  **Bytes tracking on the in-memory cache.** `InMemoryCache.getStats().sizeBytes`
+  now returns a running approximation (UTF-8 bytes of the key plus
+  `v8.serialize(value).byteLength`, with a JSON fallback) that's kept in sync
+  across all eviction paths. Treat the number as a sanity gauge; it doesn't
+  include `Map` per-entry overhead.
+
+  **Pagination.** Both `Queue<T>.listJobs` and `CacheProvider.listEntries?`
+  are offset-paginated. Inputs gain an `offset: number`; outputs change to
+  `{ items, total: number | null, hasMore: boolean }`. `total` is nullable
+  so backends that can't compute it cheaply still paginate via `hasMore`.
+  The UI uses the existing `<Pagination>` component with a 25-row default
+  page size. `QueueManager.listJobs` aggregates by over-fetching
+  `[0, offset+limit)` per queue, merge-sorting, then slicing the window —
+  optimal for the single-queue case, acceptable for the multi-queue case
+  within the UI's reasonable page-depth bounds. BullMQ uses native offset
+  ranges via `getJobs(types, start, end)` plus `getJobCounts` for `total`.
+
+  **Pending tab.** The Queue runtime panel exposes a virtual `"pending"`
+  state (waiting ∪ delayed, FIFO). It's now the default sub-tab, since
+  "what's queued up?" is the most common question. Per-row state is shown
+  when viewing the combined list.
+
+  **Recurring schedules visible under Pending.** Cron- and interval-based
+  recurring jobs (e.g. healthchecks) are surfaced under Pending/Delayed
+  between fires, with a `nextRunAt` countdown column and a "(recurring)"
+  label. `JobSummary` gains optional `nextRunAt: Date` and `recurring:
+boolean` fields. The in-memory queue synthesises these rows from its
+  `recurringJobs` registry; BullMQ already materialises the next fire of
+  each scheduler as a delayed job and we now surface its trigger time and
+  the `repeatJobKey`-derived `recurring` flag.
+
+  **Bug fix — drop hook emits with no listeners.** `EventBus.emit` no
+  longer enqueues a job when zero listeners (distributed or instance-local)
+  are registered for the hook. Previously, hooks like
+  `core.plugin.initialized` — emitted on every plugin init but subscribed
+  to by nothing in the core repo — accumulated one waiting job per emit
+  forever. The in-memory queue's `processNext` short-circuits when there
+  are zero consumer groups, so its post-loop cleanup never ran for these
+  orphaned jobs. The fix drops the emit at the source and logs a debug
+  line. Note: in distributed deployments using a Redis-backed queue, this
+  means a subscriber on another replica won't receive an event if no
+  replica that emits it has a local listener. Plugins needing cross-process
+  delivery must register their listener on every replica that should
+  receive the hook.
+
+  **Breaking notes (treated as minor under beta semantics)**:
+
+  - `@checkstack/infrastructure-common` removes `registerInfrastructureTab`
+    and `getInfrastructureTabs`; former callers must register an extension
+    into `InfrastructureTabsSlot`.
+  - `@checkstack/queue-api`'s `Queue<T>` interface requires the new
+    `listJobs(opts)` method returning `ListJobsResult` (paginated). Both
+    bundled queue backends (memory, BullMQ) are updated; out-of-tree
+    implementations will need to add it.
+  - `QueueStats` and `CacheStats` add a required `scope` field.
+  - `CacheProvider.listEntries?` (when implemented) now returns
+    `ListEntriesResult` instead of `CacheEntrySummary[]`.
+  - `JobState` adds a `"pending"` variant.
+
+### Patch Changes
+
+- Updated dependencies [42abfff]
+  - @checkstack/common@0.9.0
+  - @checkstack/signal-common@0.2.2
+
 ## 0.3.1
 
 ### Patch Changes

package/package.json

@@ -1,6 +1,6 @@
 {
   "name": "@checkstack/queue-common",
-  "version": "0.3.1",
+  "version": "0.5.0",
   "license": "Elastic-2.0",
   "type": "module",
   "exports": {
@@ -14,15 +14,15 @@
     "lint:code": "eslint . --max-warnings 0"
   },
   "dependencies": {
-    "@checkstack/common": "0.7.0",
-    "@checkstack/signal-common": "0.2.0",
+    "@checkstack/common": "0.9.0",
+    "@checkstack/signal-common": "0.2.2",
     "@orpc/contract": "^1.13.14",
     "zod": "^4.0.0"
   },
   "devDependencies": {
     "typescript": "^5.7.2",
-    "@checkstack/tsconfig": "0.0.6",
-    "@checkstack/scripts": "0.1.2"
+    "@checkstack/tsconfig": "0.0.7",
+    "@checkstack/scripts": "0.3.1"
   },
   "checkstack": {
     "type": "common"

package/src/rpc-contract.ts

@@ -9,6 +9,8 @@ import {
   QueueStatsDtoSchema,
   QueueLagStatusSchema,
   QueueLagThresholdsSchema,
+  ListJobsInputSchema,
+  ListJobsResultSchema,
 } from "./schemas";
 
 // Queue RPC Contract with access metadata
@@ -32,6 +34,7 @@ export const queueContract = {
     userType: "authenticated",
     access: [queueAccess.settings.manage],
   })
+    .route({ method: "PATCH" })
     .input(UpdateQueueConfigurationSchema)
     .output(QueueConfigurationDtoSchema),
 
@@ -55,8 +58,18 @@ export const queueContract = {
     userType: "authenticated",
     access: [queueAccess.settings.manage],
   })
+    .route({ method: "PATCH" })
     .input(QueueLagThresholdsSchema)
     .output(QueueLagThresholdsSchema),
+
+  // List jobs in a state — read access. Payloads omitted by design.
+  listJobs: proc({
+    operationType: "query",
+    userType: "authenticated",
+    access: [queueAccess.settings.read],
+  })
+    .input(ListJobsInputSchema)
+    .output(ListJobsResultSchema),
 };
 
 // Export contract type

package/src/schemas.ts

@@ -38,17 +38,68 @@ export type UpdateQueueConfiguration = z.infer<
 >;
 
 /**
- * Queue statistics DTO
+ * Scope of a stats response: `"instance"` if the figures reflect just the
+ * local process (in-memory backends), `"cluster"` if they're shared across
+ * the deployment (Redis-backed backends).
+ */
+export const StatsScopeSchema = z.enum(["instance", "cluster"]);
+export type StatsScope = z.infer<typeof StatsScopeSchema>;
+
+/**
+ * Queue statistics DTO. The `scope` field exists so the UI can warn users
+ * when in-memory backends are running with horizontal scaling.
  */
 export const QueueStatsDtoSchema = z.object({
   pending: z.number(),
   processing: z.number(),
   completed: z.number(),
   failed: z.number(),
+  scope: StatsScopeSchema,
 });
 
 export type QueueStatsDto = z.infer<typeof QueueStatsDtoSchema>;
 
+export const JobStateSchema = z.enum([
+  "pending",
+  "waiting",
+  "active",
+  "delayed",
+  "completed",
+  "failed",
+]);
+export type JobStateDto = z.infer<typeof JobStateSchema>;
+
+export const JobSummaryDtoSchema = z.object({
+  id: z.string(),
+  name: z.string().optional(),
+  state: JobStateSchema,
+  enqueuedAt: z.coerce.date(),
+  startedAt: z.coerce.date().optional(),
+  finishedAt: z.coerce.date().optional(),
+  attempts: z.number().int().nonnegative(),
+  failedReason: z.string().optional(),
+  nextRunAt: z.coerce.date().optional(),
+  recurring: z.boolean().optional(),
+});
+
+export type JobSummaryDto = z.infer<typeof JobSummaryDtoSchema>;
+
+export const ListJobsInputSchema = z.object({
+  state: JobStateSchema,
+  offset: z.number().int().nonnegative().default(0),
+  limit: z.number().int().min(1).max(200),
+});
+
+export type ListJobsInput = z.infer<typeof ListJobsInputSchema>;
+
+export const ListJobsResultSchema = z.object({
+  items: z.array(JobSummaryDtoSchema),
+  total: z.number().int().nonnegative().nullable(),
+  hasMore: z.boolean(),
+});
+
+export type ListJobsResultDto = z.infer<typeof ListJobsResultSchema>;
+
 /**
  * Lag severity levels
  */