Register the exec-log module (MON-21)

Owned by Graphy. `:api` is deliberately two namespaces, so callers get
`exec-log.core` only and the schema, record, sink, and settings stay internal --
the wire format cannot be reached around.

Also adds `exec-log` to query-processor's `:uses`, since the QP now calls the
facade from `save-execution-metadata!`.

Linting the module went from 9 warnings to 0.

.claude/skills/_shared/clojure-style-guide.md

@@ -27,9 +27,28 @@ This guide covers Clojure and ClojureScript coding conventions for Metabase. See
 - Format using Markdown conventions
 - Reference other vars with `[[other-var]]` not backticks
 
+A docstring states the *contract*: what it returns (including when it returns nil), what its
+params mean, what it throws versus swallows, and any precondition or invariant the caller must
+respect. A params block for non-obvious or optional args is good documentation — length is not
+the problem.
+
+These seven things are, and each is a reason to cut or relocate:
+
+| Anti-pattern | Why | Where it goes instead |
+| --- | --- | --- |
+| **Facts you don't own** — how a *callee*, another namespace, or another repo works internally | Drifts silently; nothing fails when it goes stale | Cut. Name the callee and let its own docstring say it |
+| **Said twice** — ns docstring restating its vars', a caller restating its callee's, sibling fns repeating boilerplate | Two copies means one is already wrong | Cut the copy. One fact, one owner |
+| **Design rationale** — why this approach, why it lives in this module, what the alternative was | The caller can't act on it | Commit message, or an inline comment on the specific line it constrains |
+| **Development history** — "matching master", "the X branch", "currently", "for now", "used to" | Stale by construction | Cut |
+| **Instructions to the reader** — "callers should trust this", "don't bother checking", "you should use X" | State the contract; the caller decides | Cut, keeping any actual guarantee as a plain statement |
+| **Invented precision** — score bands, thresholds, or tables no code enforces | Reads as spec, isn't | Cut, or make the code enforce it |
+| **A note on the wrong var** — describing how overrides behave, on the base/default impl | Nobody reading the override sees it | Move to the overrides it describes |
+
 **Comments:**
 
 - `TODO` format: `;; TODO (Name YYYY-MM-DD) -- description`
+- Prefer an inline comment over docstring prose for anything that explains *the body*. Put it on
+  the line it explains, not at the top of the function.
 
 ## Code Organization
 

.claude/skills/_shared/development-workflow.md

@@ -6,3 +6,4 @@
 - Run targeted tests, and lint continuously during development
 - Prioritize understanding existing patterns before implementing
 - Don't commit changes, leave it for the user to review and make commits
+- Minimize comments. Document only non-obvious intent, trade-offs, or constraints that the code itself cannot convey. Do not narrate what the code does — keep code self-descriptive through naming and structure.

.claude/skills/add-malli-schemas/SKILL.md

@@ -149,8 +149,7 @@ ms/NonBlankString               ;; Non-empty string
 ms/BooleanValue                 ;; String "true"/"false" or boolean
 ms/MaybeBooleanValue            ;; BooleanValue or nil
 ms/TemporalString               ;; ISO-8601 date/time string (for REQUEST params only!)
-ms/Map                          ;; Any map
-ms/JSONString                   ;; JSON-encoded string
+ms/OpaqueJSONObject             ;; JSON object whose keys are not ours to declare; string-keyed
 ms/PositiveNum                  ;; Positive number
 ms/IntGreaterThanOrEqualToZero  ;; 0 or positive
 ```

.claude/skills/analytics-events/SKILL.md

@@ -10,23 +10,23 @@ This skill helps you add product analytics (Snowplow) events to track user inter
 
 ## Quick Reference
 
-Analytics events in Metabase use Snowplow with typed event schemas. All events must be defined in TypeScript types before use.
+Analytics events in Metabase use Snowplow with typed event schemas. Simple events are declared **where they are used** — `trackSimpleEvent` is generic and validates the payload at the call site.
 
 **Key Files:**
-- `frontend/src/metabase-types/analytics/event.ts` - Event type definitions
-- `frontend/src/metabase-types/analytics/schema.ts` - Schema registry
-- `frontend/src/metabase/analytics/` - Core tracking functions (import from `metabase/analytics`)
-- Feature-specific `analytics.ts` files - Tracking function wrappers
+- `frontend/src/metabase/analytics/event.ts` - Core tracking functions, `trackSimpleEvent` / `trackSchemaEvent` (import from `metabase/analytics`)
+- `frontend/src/metabase-types/analytics/event.ts` - The shared `SimpleEventSchema` only. **Do not add event types here** (see below)
+- `frontend/src/metabase-types/analytics/schema.ts` - Schema registry (custom/legacy schemas only)
+- Feature-specific `analytics.ts` files - Where your tracking functions and any local types live
 
 ## Quick Checklist
 
 When adding a new analytics event:
 
-- [ ] Define event type in `frontend/src/metabase-types/analytics/event.ts`
-- [ ] Add event to appropriate union type (e.g., `DataStudioEvent`, `SimpleEvent`)
-- [ ] Create tracking function in feature's `analytics.ts` file
-- [ ] Import and call tracking function at the interaction point
-- [ ] Use `trackSimpleEvent()` for basic events (most common)
+- [ ] Pick an event name (snake_case, past tense)
+- [ ] Add a tracking function to the feature's `analytics.ts` file, calling `trackSimpleEvent()`
+- [ ] Keep any field unions (e.g. `"success" | "failure"`) as local types in that same file
+- [ ] Import and call the tracking function at the interaction point
+- [ ] Do **not** add an event type to `metabase-types/analytics/event.ts` or to any union
 
 ## Event Schema Types
 
@@ -47,6 +47,25 @@ type SimpleEventSchema = {
 
 **When to use:** 90% of events fit this schema. Use for clicks, opens, closes, creates, deletes, etc.
 
+`trackSimpleEvent` is generic and enforces this schema on the object literal you pass it:
+
+```typescript
+// frontend/src/metabase/analytics/event.ts
+export function trackSimpleEvent<
+  T extends SimpleEventSchema &
+    Record<Exclude<keyof T, keyof SimpleEventSchema>, never>,
+>(event: T) {
+  trackSchemaEvent("simple_event", event);
+}
+```
+
+That means a missing `event` or any field outside `SimpleEventSchema` is a compile error at the call
+site. There is no separate event type to declare and no `satisfies` clause to add — the old
+`ValidateEvent<...>` helper is no longer exported and is not part of the workflow.
+
+`trackSchemaEvent` is generic too: it correlates the schema name with the payload type, so you can't
+send a dashboard event under the `simple_event` schema.
+
 ### 2. Custom Schemas (legacy, no events are being added)
 
 Consider adding new event schema only in very special cases.
@@ -57,36 +76,7 @@ Consider adding new event schema only in very special cases.
 
 ### Example: Track when a user applies filters in a table picker
 
-#### Step 1: Define Event Types
-
-Add event type definitions to `frontend/src/metabase-types/analytics/event.ts`:
-
-```typescript
-export type DataStudioTablePickerFiltersAppliedEvent = ValidateEvent<{
-  event: "data_studio_table_picker_filters_applied";
-}>;
-
-export type DataStudioTablePickerFiltersClearedEvent = ValidateEvent<{
-  event: "data_studio_table_picker_filters_cleared";
-}>;
-```
-
-#### Step 2: Add to Union Type
-
-Find or create the appropriate union type and add your events:
-
-```typescript
-export type DataStudioEvent =
-  | DataStudioLibraryCreatedEvent
-  | DataStudioTablePublishedEvent
-  | DataStudioGlossaryCreatedEvent
-  | DataStudioGlossaryEditedEvent
-  | DataStudioGlossaryDeletedEvent
-  | DataStudioTablePickerFiltersAppliedEvent  // <- Add here
-  | DataStudioTablePickerFiltersClearedEvent; // <- Add here
-```
-
-#### Step 3: Create Tracking Functions
+#### Step 1: Create Tracking Functions
 
 In your feature's `analytics.ts` file (e.g., `enterprise/frontend/src/metabase-enterprise/data-studio/analytics.ts`):
 
@@ -106,7 +96,7 @@ export const trackDataStudioTablePickerFiltersCleared = () => {
 };
 ```
 
-#### Step 4: Use in Components
+#### Step 2: Use in Components
 
 Import and call the tracking function at the interaction point:
 
@@ -138,16 +128,11 @@ function FilterPopover({ filters, onSubmit }) {
 
 ## Using SimpleEventSchema Fields
 
+All examples below live in the feature's own `analytics.ts` — nothing is registered centrally.
+
 ### Example: Event with target_id
 
 ```typescript
-// Type definition
-export type DataStudioLibraryCreatedEvent = ValidateEvent<{
-  event: "data_studio_library_created";
-  target_id: number | null;
-}>;
-
-// Tracking function
 export const trackDataStudioLibraryCreated = (id: CollectionId) => {
   trackSimpleEvent({
     event: "data_studio_library_created",
@@ -162,14 +147,10 @@ trackDataStudioLibraryCreated(newLibrary.id);
 ### Example: Event with triggered_from
 
 ```typescript
-// Type definition
-export type NewButtonClickedEvent = ValidateEvent<{
-  event: "new_button_clicked";
-  triggered_from: "app-bar" | "empty-collection";
-}>;
+// Local union, exported only if another feature needs to pass the same value
+export type NewButtonLocation = "app-bar" | "empty-collection";
 
-// Tracking function
-export const trackNewButtonClicked = (location: "app-bar" | "empty-collection") => {
+export const trackNewButtonClicked = (location: NewButtonLocation) => {
   trackSimpleEvent({
     event: "new_button_clicked",
     triggered_from: location,
@@ -187,44 +168,31 @@ export const trackNewButtonClicked = (location: "app-bar" | "empty-collection")
 
 ### Example: Event with event_detail
 
-```typescript
-// Type definition
-export type MetadataEditEvent = ValidateEvent<{
-  event: "metadata_edited";
-  event_detail: "type_casting" | "semantic_type_change" | "visibility_change";
-  triggered_from: "admin" | "data_studio";
-}>;
+Real example — `frontend/src/metabase/metadata/pages/shared/analytics.ts`:
 
-// Tracking function
-export const trackMetadataChange = (
-  detail: "type_casting" | "semantic_type_change" | "visibility_change",
-  location: "admin" | "data_studio"
-) => {
+```typescript
+export type MetadataEditEventDetail =
+  | "type_casting"
+  | "semantic_type_change"
+  | "visibility_change";
+
+export const trackMetadataChange = (detail: MetadataEditEventDetail) => {
   trackSimpleEvent({
     event: "metadata_edited",
     event_detail: detail,
-    triggered_from: location,
+    triggered_from: "admin",
   });
 };
 
 // Usage
-trackMetadataChange("semantic_type_change", "data_studio");
+trackMetadataChange("semantic_type_change");
 ```
 
 ### Example: Event with result and duration
 
-```typescript
-// Type definition
-export type MoveToTrashEvent = ValidateEvent<{
-  event: "moved-to-trash";
-  target_id: number | null;
-  triggered_from: "collection" | "detail_page" | "cleanup_modal";
-  duration_ms: number | null;
-  result: "success" | "failure";
-  event_detail: "question" | "model" | "metric" | "dashboard";
-}>;
+See `frontend/src/metabase/archive/analytics.ts` for the real version of this.
 
-// Tracking function
+```typescript
 export const trackMoveToTrash = (params: {
   targetId: number | null;
   triggeredFrom: "collection" | "detail_page" | "cleanup_modal";
@@ -280,17 +248,16 @@ try {
 "filters-applied"            // Use underscore, not hyphen
 ```
 
-### Event Type Names (PascalCase with "Event" suffix)
+### Local Field Types (PascalCase, named after the field)
+
+There is usually no `...Event` type to name anymore. When you do need a union for a field, name it
+after the field it feeds:
 
 ```typescript
 // Good
-DataStudioLibraryCreatedEvent
-TablePickerFiltersAppliedEvent
-MetabotChatOpenedEvent
-
-// Bad
-dataStudioLibraryCreated      // Wrong case
-DataStudioLibraryCreated      // Missing "Event" suffix
+type MetricDimensionResult = "success" | "failure";     // -> result
+export type MetadataEditEventDetail = "type_casting";   // -> event_detail
+type NewButtonLocation = "app-bar" | "empty-collection"; // -> triggered_from
 ```
 
 ### Tracking Function Names (camelCase with "track" prefix)
@@ -309,29 +276,28 @@ logLibraryCreated             // Use "track" prefix
 
 ## Common Patterns
 
-### Pattern 1: Feature-Specific Union Types
+### Pattern 1: Sharing Field Types Across Features
 
-Group related events together:
+When two features send the same event with a different `triggered_from`, export the field union from
+the owning feature's `analytics.ts` and import it — don't hoist anything into `metabase-types`:
 
 ```typescript
-export type DataStudioEvent =
-  | DataStudioLibraryCreatedEvent
-  | DataStudioTablePublishedEvent
-  | DataStudioGlossaryCreatedEvent;
+// frontend/src/metabase/data-studio/data-model/analytics.ts
+import { trackSimpleEvent } from "metabase/analytics";
+import type { MetadataEditEventDetail } from "metabase/metadata/pages/shared/analytics";
 
-export type MetabotEvent =
-  | MetabotChatOpenedEvent
-  | MetabotRequestSentEvent
-  | MetabotFixQueryClickedEvent;
-
-// Then add to SimpleEvent union
-export type SimpleEvent =
-  | /* other events */
-  | DataStudioEvent
-  | MetabotEvent
-  | /* more events */;
+export function trackMetadataChange(detail: MetadataEditEventDetail) {
+  trackSimpleEvent({
+    event: "metadata_edited",
+    event_detail: detail,
+    triggered_from: "data_studio",
+  });
+}
 ```
 
+This is the point of the extensible-events design: enterprise and feature-tier types stay in their
+own module instead of being imported down into a shared union.
+
 ### Pattern 2: Conditional Tracking
 
 Track different events based on user action:
@@ -350,10 +316,10 @@ const handleSave = async () => {
 
 ## Common Pitfalls
 
-### Don't: Add custom fields to SimpleEvent
+### Don't: Add custom fields to a simple event
 
 ```typescript
-// WRONG - SimpleEvent doesn't support custom fields
+// WRONG - SimpleEventSchema doesn't support custom fields (this is a compile error)
 export const trackFiltersApplied = (filters: FilterState) => {
   trackSimpleEvent({
     event: "filters_applied",
@@ -379,23 +345,43 @@ export const trackFilterApplied = (filterType: string) => {
 };
 ```
 
-### Don't: Forget to add event to union type
+### Don't: Add event types to `metabase-types/analytics/event.ts`
+
+The central `SimpleEvent` union was removed — it forced feature-tier types to be imported down into
+shared code, causing module-boundary violations. `trackSimpleEvent` is generic now, so the type adds
+nothing but duplication.
 
 ```typescript
-// Define the event
+// ❌ WRONG - central declaration + re-import for a `satisfies` clause
+// frontend/src/metabase-types/analytics/event.ts
 export type NewFeatureClickedEvent = ValidateEvent<{
   event: "new_feature_clicked";
+  target_id: number;
 }>;
 
-// ❌ WRONG - Forgot to add to SimpleEvent union
-// Event won't be recognized by TypeScript
+// frontend/src/metabase/my-feature/analytics.ts
+import type { NewFeatureClickedEvent } from "metabase-types/analytics";
 
-// ✓ RIGHT - Add to appropriate union
-export type SimpleEvent =
-  | /* other events */
-  | NewFeatureClickedEvent;
+export const trackNewFeatureClicked = (id: number) => {
+  trackSimpleEvent({
+    event: "new_feature_clicked",
+    target_id: id,
+  } satisfies NewFeatureClickedEvent);
+};
+
+// ✓ RIGHT - the object literal is already checked by the generic
+// frontend/src/metabase/my-feature/analytics.ts
+export const trackNewFeatureClicked = (id: number) => {
+  trackSimpleEvent({
+    event: "new_feature_clicked",
+    target_id: id,
+  });
+};
 ```
 
+A few `...Event` types still sit in `metabase-types/analytics/event.ts`. They are leftovers from PRs
+that landed around the refactor — don't copy them, and don't add to them.
+
 ### Don't: Mix up event name formats
 
 ```typescript
@@ -463,41 +449,44 @@ Example console output:
 ### Where to put tracking functions:
 
 ```
-Feature-specific analytics functions:
+Tracking functions AND their local field types (this is where new events live):
 frontend/src/metabase/{feature}/analytics.ts
 enterprise/frontend/src/metabase-enterprise/{feature}/analytics.ts
 
-Event type definitions (all in one place):
-frontend/src/metabase-types/analytics/event.ts
-
 Core tracking utilities:
 frontend/src/metabase/analytics/ (import from `metabase/analytics`)
+
+Shared SimpleEventSchema only — nothing new goes here:
+frontend/src/metabase-types/analytics/event.ts
 ```
 
+In embedding SDK code, use `trackSdkSimpleEvent`
+(`frontend/src/embedding-sdk-bundle/analytics/snowplow.ts`) instead — the main-app `"sp"` tracker
+isn't initialized in the customer's page, so `trackSimpleEvent`'s Snowplow leg is a no-op there.
+
 ## Real-World Examples
 
 See these files for reference:
 
-- **Simple events**: `enterprise/frontend/src/metabase-enterprise/data-studio/analytics.ts`
-- **Events with variants**: `frontend/src/metabase/dashboard/analytics.ts`
-- **Complex events**: `frontend/src/metabase/query_builder/analytics.js`
-- **Event type examples**: `frontend/src/metabase-types/analytics/event.ts`
+- **Simple events + local field union**: `frontend/src/metabase/metadata/pages/shared/analytics.ts`
+- **Reusing another feature's field type**: `frontend/src/metabase/data-studio/data-model/analytics.ts`
+- **Result + duration timing**: `frontend/src/metabase/archive/analytics.ts`
+- **Enterprise feature events**: `enterprise/frontend/src/metabase-enterprise/google_drive/analytics.ts`
 
 ## Workflow Summary
 
 1. **Identify the user interaction** to track
 2. **Decide on event name** (snake_case, descriptive)
-3. **Define event type** in `event.ts` using `ValidateEvent`
-4. **Add to union type** (create feature union if needed)
-5. **Create tracking function** in feature's `analytics.ts`
-6. **Import and call** at the interaction point
-7. **Test** that events fire correctly
+3. **Create tracking function** in feature's `analytics.ts`, calling `trackSimpleEvent()`
+4. **Add local field unions** in that same file if a field has a fixed set of values
+5. **Import and call** at the interaction point
+6. **Test** that events fire correctly
 
 ## Tips
 
 - **Be specific** - `filters_applied` is better than `action_performed`
 - **Use past tense** - `library_created` not `create_library`
-- **Group related events** - Create feature-specific event union types
+- **Group related events** - Keep a feature's tracking functions together in its `analytics.ts`
 - **Track meaningful actions** - Not every click needs tracking
 - **Consider the data** - What would you want to analyze later?
 - **Stay consistent** - Follow existing naming patterns in the codebase

.claude/skills/clojure-review/SKILL.md

@@ -56,6 +56,11 @@ Use this to scan through changes efficiently:
 - [ ] References use `[[other-var]]` not backticks
 - [ ] `TODO` comments include author and date: `;; TODO (Name 2025-01-01) -- description`
 
+Docstring content — check every new or rewritten docstring against the anti-pattern table in the
+style guide above. Read the diff's docstrings on their own, separately from the code: prose is
+where review attention slides off, and a long docstring reads as diligence rather than as the
+liability it usually is.
+
 ### Code Organization
 
 - [ ] Everything `^:private` unless used elsewhere
@@ -135,6 +140,17 @@ Quick scan for common issues:
 
 > This public var needs a docstring explaining its purpose, inputs, and outputs.
 
+**For docstrings documenting code they don't own:**
+
+> This describes how `lib` decides binning strategies internally. Nothing here fails when that
+> changes, so it will go stale silently — drop it and let `available-binning-strategies` answer
+> for its own behavior.
+
+**For docstring content that belongs in the body:**
+
+> This paragraph explains why the branches are ordered this way, which is what someone editing
+> the `cond` needs — but a caller can't act on it. Move it to an inline comment above the `cond`.
+
 **For organization issues:**
 
 > This function is only used in this namespace, so it should be marked `^:private`.

.claude/skills/clojure-write/SKILL.md

@@ -82,10 +82,29 @@ either a bug, or it means callers must handle each case themselves — and
 in *that* case it is the *absence* of the property that must be
 documented. Document deviations from expectation, not conformance to it.
 
-Heuristic: if a sentence would still be true after a full rewrite of the
-body, it may belong in the docstring. If it describes *how the current
-body works*, it belongs in the body — as an inline comment, if it is
-non-obvious.
+Heuristic — a sentence earns its place in the docstring only if it
+passes both tests:
+
+1. Rewrite test (necessary, not sufficient): if rewriting the body to a
+   different implementation with an identical contract could make the
+   sentence false, it describes the implementation, not the contract.
+   Relocate it to an inline comment at the point in the body where it
+   applies.
+
+2. Ownership test: if the sentence states a fact about code this
+   function does not own — a callee's behavior, a library's guarantee —
+   it survives any rewrite trivially, which is exactly why the rewrite
+   test alone is not enough. If this body *relies* on that fact, it is
+   implementation context: relocate it to the call site. If nothing here
+   relies on it, it is blather about someone else's code: delete it, and
+   let the callee's own docstring answer for it.
+
+Say each fact once. Duplicated prose is a stale comment in advance: when
+the fact changes, one copy gets updated and the rest quietly rot. This
+holds even within code you own — a namespace docstring that
+re-summarizes its own multimethods, three sibling functions carrying the
+same paragraph about retry behavior. Give the fact one home, and have
+the other places name it rather than restate it.
 
 Multi-line docstrings are not banned — a genuinely non-obvious constraint
 the code had to deal with can be worth explaining. But be prudent; the

.claude/skills/e2e-test/SKILL.md

@@ -37,14 +37,16 @@ First check if snapshots exist:
 ls e2e/snapshots/default.sql 2>/dev/null && echo "snapshots exist" || echo "snapshots missing"
 ```
 
+Always pass the spec path via `--spec`. The runner feeds its arguments to Cypress's CLI parser (`cypress.cli.parseRunArguments`), which silently drops bare positional paths and then runs the entire suite. A leading `run` argument is harmless, but the path itself must follow `--spec`. Sanity-check that the first `Running:` line says `(1 of 1)`.
+
 If snapshots exist, skip regeneration for speed:
 ```bash
-MB_EDITION=oss CYPRESS_VIDEO=false CYPRESS_RETRIES=0 CYPRESS_GUI=false GENERATE_SNAPSHOTS=false bun test-cypress $ARGUMENTS
+MB_EDITION=oss CYPRESS_VIDEO=false CYPRESS_RETRIES=0 CYPRESS_GUI=false GENERATE_SNAPSHOTS=false bun test-cypress --spec path/to/spec.cy.spec.js
 ```
 
 If snapshots are missing (first run), let the runner generate them:
 ```bash
-MB_EDITION=oss CYPRESS_VIDEO=false CYPRESS_RETRIES=0 CYPRESS_GUI=false bun test-cypress $ARGUMENTS
+MB_EDITION=oss CYPRESS_VIDEO=false CYPRESS_RETRIES=0 CYPRESS_GUI=false bun test-cypress --spec path/to/spec.cy.spec.js
 ```
 
 When running enterprise tests, replace `MB_EDITION=oss` with `MB_EDITION=ee` in the commands above.
@@ -67,9 +69,11 @@ GREP="test name here" MB_EDITION=oss bun test-cypress --spec path/to/spec.js
 When the user asks to verify a test is not flaky:
 
 ```bash
-MB_EDITION=oss bin/e2e-stress-test $ARGUMENTS
+MB_EDITION=oss bin/e2e-stress-test --spec path/to/spec.cy.spec.js
 ```
 
+(The stress script forwards its arguments to `bun test-cypress`, so the same `--spec` rule applies.)
+
 Set `E2E_STRESS_RUNS=N` for more iterations (default: 5). Stops on first failure and prints screenshot paths. Read those screenshots to analyze the failure.
 
 ## Analyzing failures

.claude/skills/fe-modularization/SKILL.md

@@ -0,0 +1,248 @@
+---
+name: fe-modularization
+description: Deciding where frontend code lives — tier model, move mechanics, extension points, side effects, naming, and the traps. Use when moving code between modules, carving new modules, fixing boundary violations, adding a barrel or an endpoint, or reviewing module-shape decisions.
+---
+
+# Frontend modularization
+
+The module is the unit of blast radius: dependency direction, test selection,
+bundle cones, and review scope all follow module boundaries. Every decision
+here serves one goal: **make the file locations tell the truth about who owns
+what and who may depend on whom.**
+
+## Hard rules (check these before anything else)
+
+- NEVER add an `export … from` re-export at an old path, and NEVER `export *`
+  from a barrel. Move the code, codemod every call site, delete the old path,
+  all in the same PR.
+- NEVER import past a module's `index.ts` when that module has
+  `enforcePublicApi: true`, and never past `metabase/ui`'s index at all. If
+  the barrel is heavy, the fix is making the module side-effect free (below),
+  not a deep import.
+- NEVER rewrite a consumer to a lower-level idiom to make the linter pass. If
+  the fix makes the consumer worse, the plan is wrong.
+- NEVER give a new module `enforceSharedTiers: false`; new modules ship
+  enforced with `enforcePublicApi: true` and an explicit `index.ts`.
+- NEVER move code without the consumer-tier check (procedure step 2).
+- ALWAYS delete a module's `enforceSharedTiers: false` line in the PR that
+  takes it to zero violations.
+- ALWAYS measure `bun run module-boundaries` before and after, and report the
+  numbers.
+- ALWAYS import `dayjs` from `metabase/dayjs`, routing from `metabase/router`,
+  Mantine from `metabase/ui`, react-redux hooks from `metabase/redux`; the
+  raw specifiers are lint-forbidden.
+
+## Files that are ground truth
+
+| what | where |
+|---|---|
+| module elements, tiers, `enforceSharedTiers`, `enforcePublicApi` | `frontend/lint/module-boundaries.mjs` |
+| shared sub-tiers and levels, cluster rules | `frontend/lint/shared-tiers.mjs` |
+| standalone boundaries lint (all violations, incl. grandfathered) | `bun run module-boundaries` (config `eslint.config.module-boundaries.mjs`) |
+| PR lint (only enforced modules fail CI) | `bun run lint-eslint-pure` |
+| side-effect-free directories and their exceptions | `frontend/build/shared/rspack/side-effect-free-modules.js` (`SIDE_EFFECT_FREE_PATHS`, `SIDE_EFFECT_PATHS`) |
+| the lint rules that enforce that promise | `metabase/no-module-side-effects`, `metabase/no-base-api-access` in `frontend/lint/eslint-plugin-metabase/rules/` |
+| public-api enforcement | `metabase/enforce-module-public-api` rule, driven by `getPublicApiModules()` |
+
+## The model
+
+Tiers: `lib < basic < shared < feature < app`. Imports point downward, never
+sideways at feature tier (features may not import features; app and EE may
+import anything). The shared tier is subdivided in `shared-tiers.mjs` into
+shared-utils (U0…), shared-platform (P0…), and shared-domain, each ordered
+into levels. A module imports only *strictly lower* levels of its sub-tier
+plus the sub-tiers below; same-level peers are deliberately forbidden, which
+is what makes cycles structurally impossible. A domain may hold two seats
+when consumers demand it: a low core and a high surface (metabase-lib below
+questions below query_builder; viz-core below visualizations).
+
+Enforcement is per module: `enforceSharedTiers: false` on an element exempts
+it from the level rules (counted by `bun run module-boundaries`, invisible to
+PR lint). Modules with `enforcePublicApi: true` may only be imported from
+outside via `metabase/<module>`, and import relatively inside.
+
+## Deciding where code lives (apply in order; first decisive test wins)
+
+1. **Who owns the concept?** Code lives with the module that owns its
+   concept, not the module that renders or calls it. A mode encoding dashboard
+   click behaviour is dashboard code even if viz executes it. Metabot
+   conversation state is metabot state even though the store registers it.
+2. **Consumer-tier check.** The destination must sit at or below the file's
+   *lowest* consumer. A single consumer below the proposed home vetoes the
+   move; report it, don't force it.
+3. **Only four legitimate fixes** for a bad edge: move the code to its
+   terminal home; invert through a designed extension point (a prop, an
+   injected component, a contract type owned by the socket); fix the tier
+   placement when the declared level is wrong; delete a thin wrapper (a rename
+   with no derivation isn't an abstraction — deleting it *is* the migration).
+4. **A bridge lives above the lower endpoint.** Code that needs both sides of
+   a boundary belongs in or above the higher module.
+5. **"Genuinely shared" is proven by consumers.** A shared address needs two
+   or more consumers the tier rules can't serve another way. One consumer
+   pretending to be shared is a feature module at the wrong address.
+
+## Extension points
+
+The socket's owner defines the contract; every plug lives with its extender.
+Visualization owns the `mode` prop and click interfaces, each surface supplies
+its mode; the editor owns its extension contract, metabot supplies tiptap
+extensions; querying owns `TemplateTagsSidebarProps`, parameters implements
+it.
+
+- Prefer plain props/injection at composition sites. `PLUGIN_*` registries are
+  for edition gating; single-reader slots move out to their reading module;
+  slots with many readers live in the module that owns the concept (every
+  slot the whitelabel plugin fills lives in `whitelabel`), tier permitting.
+  Keep contracts type-light so implementations can load lazily.
+- Identical injection at every callsite is acceptable until a fourth consumer
+  or second slot appears; then the composition deserves its own module above
+  both parts. Don't pre-build the wrapper.
+
+## Store shape
+
+A module that has redux state owns it:
+
+- `store/` is private: reducer, plain creators/action types, and selectors,
+  typed against the module's own state (`QueryBuilderStoreState`), never the
+  global `State`. Thunks live in `actions/` and import `store/`, never the
+  reverse.
+- The barrel is the state API: selectors for reads, creators/thunks for
+  writes.
+- Store roots (`reducers-main`, `reducers-public`, the SDK store) import each
+  slice from its module barrel and derive their own state type; no slice
+  registry, no `declare module` merging.
+- Cross-module writes: a callback prop when a composition point exists;
+  otherwise dispatch the owner's exported creator; an event only when the
+  emitter must not know its listeners. Raw `dispatch({ type: "…" })` strings
+  are banned. A reducer or listener matching another module's *internal*
+  action is the coupling to remove.
+- Slices that mirror one endpoint get deleted (the RTK cache is the state); a
+  fold over many sources with one writer (the metadata store) is kept as a
+  module-private slice behind the barrel.
+
+## Endpoints
+
+Endpoints migrate to their owning module via `Api.injectEndpoints` from the
+module's `api/` file (settings, metabot, transforms precedents); `metabase/api`
+trends toward the client only. There is one `Api` object per backend because
+tag invalidation only works within one instance. Consumers reach endpoints
+only through the owner's exports (`useGetCardQuery`, `cardApi.endpoints.…`),
+never by name through the base object; `metabase/no-base-api-access` allows
+injection only in `metabase/api` and `**/api/**` / `**/api.ts`, and reaching by
+name only in `metabase/api` and test support (`invalidateTags` /
+`resetApiState` are fine anywhere). Each endpoint move carries its
+metadata-store hookup: the owner calls `entitiesFetched` from its own
+`onQueryStarted`.
+
+## Import-time side effects
+
+Directories in `SIDE_EFFECT_FREE_PATHS` are marked `sideEffects: false` for
+rspack, so importing one export from their barrel no longer drags the whole
+barrel into a bundle. The price: nothing in those directories may do work at
+import time, or production silently drops it. `metabase/no-module-side-effects`
+enforces this over every listed directory (module-scope calls, writes to
+imported objects or globals, bare imports, control flow at import; escape
+hatches are `/* #__PURE__ */` and the rule's pure-callee list). Files that
+must run at import are listed in `SIDE_EFFECT_PATHS` (files or directories).
+
+- **A library the app configures gets a facade module** owning the vendor
+  import, the registrations, and the types, with the raw specifier
+  lint-forbidden outside it: `metabase/router`, `metabase/ui`,
+  `metabase/redux`, `metabase/dayjs`. Facades are the effect, so they never
+  enter `SIDE_EFFECT_FREE_PATHS`. Never re-register a vendor plugin locally
+  (`dayjs.extend`, `echarts` `use`).
+- **A patch a component needs is an explicit registration module,
+  bare-imported by the provider that needs it** and listed in
+  `SIDE_EFFECT_PATHS` (Mantine's `Popover.Dropdown` replacement, imported by
+  `ThemeProvider`).
+- **Effects with no value to import** (global CSS, polyfills, the CSP nonce,
+  EE plugin bootstrap) live in the entry's side-effects file and nowhere else.
+- **Registries are filled from the composition root at boot**
+  (`initializePlugins`, `registerVisualizations`), never by a module
+  registering itself at import.
+- **RTK injection stays at import**; when a module with an `api/` folder is
+  declared side-effect free, list `<module>/api/` in `SIDE_EFFECT_PATHS`.
+
+## Naming
+
+The feature keeps the plain product-surface name; a shared carve is named for
+what the shared part actually is: the concept when the concept is the shared
+thing (`settings`, `current-user`, `whitelabel`, `dayjs`), or a qualified
+capability when the plain noun is taken (`search-ui`, `metrics-ui`,
+`viz-core`, `data-studio-ui`). Never two modules distinguished only by tier
+prefix; never generic `-shared` / `-feature` suffixes.
+
+## Procedure for a move
+
+1. **Enumerate consumers honestly** (hook-name greps miss the last three):
+   ```
+   grep -rn "metabase/<module>" frontend/src enterprise/frontend/src frontend/test e2e
+   grep -rn "jest.mock(\"metabase/<module>" frontend enterprise/frontend
+   grep -rn "addMatcher(.*<endpoint>" frontend/src enterprise/frontend/src
+   ```
+   plus sibling files importing the moved file relatively. Classify each by
+   module and tier from `module-boundaries.mjs` / `shared-tiers.mjs`.
+2. **Consumer-tier check**: destination at or below the lowest consumer. If
+   not, stop and report the blocking consumer.
+3. **Measure before**: `bun run module-boundaries 2>&1 | tail -1` on the base
+   (write the number down).
+4. **Move**: `git mv`; codemod every importer to `metabase/<module>` (outside)
+   or a relative path (inside); add named exports to the destination barrel
+   for every symbol an outside consumer needs (each must have a real
+   consumer). Delete the old path. If the module didn't exist: add its element
+   in `module-boundaries.mjs` (ordered before any element it's carved from,
+   first match wins), its level in `shared-tiers.mjs`, `enforcePublicApi:
+   true`, an `index.ts`. If the move empties a module's violations, delete
+   its `enforceSharedTiers: false` line. If the module has an `api/` folder
+   and is side-effect free, list `<module>/api/` in `SIDE_EFFECT_PATHS`.
+5. **Verify** (all of these, report the numbers):
+   ```
+   grep -rn "<old path>" frontend enterprise/frontend e2e        # must be empty
+   bunx eslint --no-warn-ignored <touched files>
+   bun run lint-eslint-pure                                       # enforce-module-public-api included
+   bun run type-check-pure
+   bun run test-unit-keep-cljs <touched folders' specs>
+   bun run module-boundaries 2>&1 | tail -1                       # after; no violation may name the new files
+   bun run build-release:static-viz                               # only if viz/static-viz/ui/dayjs touched; hard 3.5 MiB budget
+   ```
+6. **Report**: count before/after (state count-neutral explicitly), the edges
+   removed by file, flags/rules deleted, barrel exports added, anything you
+   skipped and why, and any consumer you found that vetoed part of the move.
+
+## Traps (each has bitten at least once)
+
+- **Late binding.** A bare function reference in a `createSelector` input
+  array, a component identity captured for comparison, a `PLUGIN_*` object
+  read at module scope: all capture at import time and dodge jest spies, EE
+  overrides, and lazy loading. Read at call time (`(_state) => fn()`), or
+  inject.
+- **Plans go stale.** Verify every recipe against current code before
+  executing; things get merged, renamed, or turn out never to have existed.
+  Skip-and-report beats force.
+- **The linter's blind spots**: `export … from` re-exports, bare-specifier
+  packages (custom-viz), pre-seeded caches that never register tags. A grep
+  for the old path is the stronger claim than a green lint run.
+- **Path-keyed baselines reset on rename**: a generated per-file ledger
+  silently loses a file's history when it moves.
+- **A heavy barrel is a bundle hazard until its module is side-effect free.**
+  One constant imported from the `metabase/ui` barrel pulled Mantine into the
+  static-viz bundle and broke its budget; the fix was `SIDE_EFFECT_FREE_PATHS`,
+  never a deep import.
+- **Type augmentation is program-wide.** `declare module "dayjs"` (and
+  similar) makes plugin types available to any file in the same tsconfig, so
+  a passing type-check never proves the setup ran; only importing the facade
+  does.
+- **Environment before diagnosis**: after a dependency-touching merge,
+  `bun install` before declaring a failure real; worktrees share staleness
+  through the node_modules symlink, and a stale `target/cljs_dev` makes
+  `type-check-pure` fail on `metabase-lib/metric/core.ts` (rebuild cljs in the
+  worktree).
+
+## PR shape
+
+One logical change per PR; the body names the specific edges removed (files,
+imports, before/after count) and gives each move's ownership reason in plain
+language a reviewer outside the effort can follow, without campaign labels.
+Stack only for semantic dependency or same-hot-file serialisation, and say
+so. Consider codeowner surface when chunking. Open as a draft until measured
+and green.

.claude/skills/typescript-review/SKILL.md

@@ -13,14 +13,14 @@ allowed-tools: Read, Grep, Bash, Glob, Skill
 
 **Primary standard: the [`typescript-write`](../typescript-write/SKILL.md) skill.** Load it first — it defines the authoring rules this review enforces, alongside `frontend/CLAUDE.md` and `docs/developers-guide/frontend.md`.
 
-Adherence to `typescript-write` is the **highest-priority** review dimension: rank any violation of its provisions above all other findings. Treat its **no-`any` hard rule** (no explicit *or* implicit `any` in new code) as **blocking**, and verify it with the LSP rather than by eye.
+Adherence to `typescript-write` is the **highest-priority** review dimension: rank any violation of its provisions above all other findings. Treat its **no-`any` hard rule** (no explicit *or* implicit `any` in new code) as **blocking**. Use TypeScript LSP tools to inspect inferred types when available; otherwise rely on type-checking and linting.
 
 Review in this priority order:
 
-1. **Violations of [`typescript-write`](../typescript-write/SKILL.md) provisions** — no-`any`, type tightening, type modeling, null/undefined handling, naming, structure, comments. Highest priority; block on the no-`any` rule.
+1. **Violations of [`typescript-write`](../typescript-write/SKILL.md) provisions** — no-`any`, type tightening, type modeling, function signatures, null/undefined handling, naming, structure, comments. Highest priority; block on the no-`any` rule. Apply conditional guidance in context: explain the unsupported type guarantee or concrete readability problem, rather than treating every preference as a blanket ban.
 2. Compliance with `frontend/CLAUDE.md`.
 3. Readability and maintainability.
-4. Appropriate test coverage.
+4. Appropriate test coverage. For internal typed callers, avoid requesting tests solely for inputs the type system excludes. External API data, deserialised values, storage and JavaScript callers can violate annotations: test runtime validation and nontrivial assumptions at those boundaries. Types do not replace behavioural, security or data-integrity tests.
 
 ## Blind spots — act as the missing reviewer
 
@@ -31,3 +31,4 @@ These rarely surface in team reviews, so this skill should raise them. They are
 - **Security.** Evaluate potential security issues in new code.
 - **Bundle size.** Flag new large dependencies, default imports from icon or util libs, and heavy modules imported at route-load time.
 - **Analytics.** User-facing flows should emit tracking events. If a PR adds a new flow (button, modal, navigation) without a tracking event, ask whether one is expected.
+- **Public API surface** (embedding SDK). Consumers should be able to use public signatures and name types they need to import. Export those types deliberately and document public behaviour, including `@deprecated` for deprecated APIs; a referenced structural type does not automatically need its own named export.

.claude/skills/typescript-write/SKILL.md

@@ -13,26 +13,34 @@ description: Write TypeScript and JavaScript code following Metabase coding stan
 
 - **New code must not introduce `any`, explicit or implicit.** No `any` annotations, no `as any` / `as unknown as`, no untyped parameters or returns that infer `any`, no implicitly-`any` destructures or array/object literals.
 - **Untyped third-party / boundary values** must be typed at the boundary (a declared type, `unknown` + type guard, or a small typed wrapper) — never let `any` propagate inward.
-- **Mandatory LSP verification.** After writing or editing any TS/TSX, inspect the changed symbols with the TypeScript Language Server (hover to read inferred types; `goToDefinition` to confirm sources) and run the project type-check.
+- **Mandatory type verification.** Before finishing a TS/TSX change, run `bun run type-check-pure`. If TypeScript LSP tools are available, also inspect changed symbols with hover and go-to-definition; otherwise skip LSP check.
 
 ## Type tightening
 
 - **Avoid type casts and loose `unknown`** — fix the signature instead.
 - **If a function only needs one field of a wide object, accept that field** — not the wide object. The cast often disappears once the signature is right.
 - **Reach for `Partial<T>`, `Pick<T, K>`, `Record<K, V>`, and generics** before reaching for a cast.
+- **Match dictionary keys to the data.** Use a finite key union when the keys are known. Open dictionaries can use an index signature, `Record<string, T>`, or `Map`; index signatures still constrain values, and changing their spelling to `Record<string, T>` does not make missing-key access safe.
 - **Prefer making props/components generic** (`<T>`) when a value flows through unchanged and the caller knows the type.
 - **Prefer `unknown` over loose typing** and narrow before use — an `unknown` value forces a guard at the point of use.
 - **`satisfies` for object literals** that must conform without widening (config objects, lookup maps, discriminated literals) — better than `: T` (widens) or `as T` (unsafe).
 - **Avoid non-null assertions (`!`)**. Prefer a guard, early return, or `?.`. Use `!` only when non-nullness is provably true and localized, with a comment.
+- **Guard indexed lookups that may miss.** Arrays and dictionaries can return `undefined` even when the inferred type omits it. Use an iteration form that preserves the key/value relationship, and only assert `keyof` when the runtime keys are known to belong to the declared type.
 - **No redundant runtime coercion** — don't wrap already-typed values in `Number()` / `String()` / `Boolean()`.
 - **Type guards belong in `frontend/src/metabase-types/guards/`**. Do not redefine them locally.
+- **A cast you can't avoid needs a real justification comment.** The `metabase/no-unjustified-type-casts` rule accepts any preceding comment — state the actual reason the cast is safe. NEVER write the legacy `// Unjustified type cast. FIXME` placeholder; it exists only on casts that predated the rule, and copying it sneaks an unjustified cast past the linter. If you can't articulate why the cast is correct, the cast is wrong — fix the types.
+- **Keep unavoidable assertions local.** Isolate a repeated or complex assertion behind a helper when that makes its invariant easier to enforce. Test nontrivial runtime assumptions that justify it; a trivial assertion does not automatically need a new helper or test. Do not weaken a public signature just to silence implementation errors.
 
 ## Type modeling
 
 - **Reuse existing types; don't re-declare them.** Use canonical IDs and domain entity types from `metabase-types/api` (`FieldId`, `TableId`, `ConcreteTableId`, `SchemaName`, …) and key data structures by them (`new Map<ConcreteTableId, …>()`). Don't duplicate generated/API types — compose or derive (`Pick`, `Omit`, indexed access `SomeType["field"]`, `ReturnType`).
-- **Use generics to allow TypeScript to infer correct types** when creating functions and components that need to be reusable and type-safe. Don't hesitate to introduce complex generics if they allow to derive types automatically instead of manual narrowing.
+- **Generics must make promises the implementation can keep.** A caller-selected `get<T>(): T` must not disguise an unchecked assertion about external data. Return `unknown` and validate, or accept a validator that establishes `T`. A factory such as `function empty<T>(): T[] { return []; }` is valid; judge the implementation, not how often `T` appears in the signature.
+- **Prefer an honest type over false precision.** Use generics when they express a real relationship. If a complex type cannot model the behaviour accurately, choose a simpler type or `unknown` with narrowing instead of asserting an unsupported guarantee.
 - **Model the actual data contract; keep types narrow.** Optional `field?: T` for a key that may be absent, `field: T | undefined` only when the key is always present but the value may be undefined, `| null` for explicit API nulls. Prefer domain unions over broad `string` / `number` / loose `Record`.
 - **Refer to API implementation** when defining or refining types to ensure they match the actual data structure. When considering a type cast, first consider if the type should be refined to match the actual data structure.
+- **Optionality must reflect absence.** Keep required fields required and optional fields optional. Normalise input when the application has a meaningful default, not merely to remove a type error. Preserve the actual wire shape in API types.
+- **Represent related absence together when modelling internal state.** If several fields exist or disappear together, consider a nullable containing object or a discriminated union. Do not reshape a raw API declaration unless the data actually has that shape.
+- **Prefer explicit special states when designing a format.** Use nullability or named union variants when sentinel values such as `-1` hide meaning. Preserve established protocol sentinel values unless the behaviour is deliberately changed, or normalise them at an explicit boundary.
 - **Discriminated unions for variant state, with exhaustive checks.** Model "one of N shapes" as a union with a literal discriminant rather than a bag of optional fields, and exhaust it with ts-pattern's `.exhaustive()` so adding a variant becomes a compile error:
   ```ts
   import { match } from "ts-pattern";
@@ -44,20 +52,30 @@ description: Write TypeScript and JavaScript code following Metabase coding stan
     .exhaustive(); // Compile-time guarantee all cases handled
   ```
 - **Derive union types from constants** (`as const` + `typeof`/`keyof`) so the type and the values can't drift.
-- **`readonly` / immutability where mutation isn't intended** — component props, shared constants, exported config. Prefer `readonly T[]` / `ReadonlyArray<T>` for inputs you don't mutate.
+- **`readonly` / immutability where mutation isn't intended** — component props, shared constants, exported config, and unmutated parameters. Prefer `readonly T[]` / `ReadonlyArray<T>` for inputs you don't mutate. Functions that mutate caller-owned data should make that behaviour explicit.
+- **Construct complete, well-typed objects where practical.** Prefer an object expression when it avoids partially initialised state or assertions. Incremental construction is fine when it is clearer and maintains the type's invariants.
+- **Treat `metabase-lib` opaque types as black boxes.** Use `metabase-lib` functions to work with types such as `Lib.Query`, rather than casting into their internal representation.
 - **Type async and error states explicitly** (a discriminated union or the data-layer's typed result) — never leave loading/error/empty implicit.
 
+## Function signatures
+
+- **Make public contracts explicit where it improves stability and clarity.** Annotate parameters and return types at shared boundaries when useful; let local values infer. Use `satisfies` or an annotation when a declaration needs an explicit shape check.
+- **Accept the inputs the operation supports and return the most precise honest result.** Narrow avoidable uncertainty inside the function, but preserve meaningful nullability and union variants in its return type.
+- **Use named options when positional arguments are easy to confuse.** Consecutive arguments with the same type are a useful warning sign, not an automatic requirement to rewrite a clear API.
+- **Use `async`/`await` when it clarifies control flow or error handling.** Returning an existing promise directly is also valid; a Promise return type alone does not require adding `async`.
+
 ## Null and undefined
 
 - **Narrow at the source**. If a value is optional only in a corner case, don't thread `undefined` through every layer — guard at the producer.
 - **Sensible defaults for optional values**. Use `?.` and `??` at the consumer.
-- **Lists should be filtered** before being used in a map or other iteration.
+- **Narrow nullable list elements when the operation requires present values.** Filter with a type guard when missing entries should be discarded; preserve them when their absence or position carries meaning.
 - **Avoid non-strict null comparisons** (`X != null`) when `X` can never be `null` — use a strict check or narrow the type. Use `checkNotNull` where necessary.
 - **Check actual nullability against API implementation**. Find the API endpoint implementation and check if the field can actually be null.
 
 ## Naming
 
 - **Names describe the entity, not the mechanism**. A name must reflect what the value holds.
+- **Use domain vocabulary and include units where useful** (`timeoutMs`, `widthPx`, `temperatureC`). Prefer a more specific name when `Info`, `Data`, or `Entity` obscures the meaning, while keeping established terminology when it is clear.
 - **Align sibling concepts**: keep verb conventions consistent across a related API.
 - **No names that encode implementation history** rather than current meaning. Suffixes like `Base`, `New`, `Old`, `Initial` need a real semantic distinction, otherwise drop them.
 - **Avoid cryptic identifiers** (`v`, `n`, `$n`) for domain values; short names are fine only in tiny conventional contexts (loop index `i`, coordinates `x`/`y`, generic params `T`/`K`/`V`).
@@ -74,10 +92,6 @@ description: Write TypeScript and JavaScript code following Metabase coding stan
 - **No comments by default**. Well-named identifiers carry the `what`.
 - **Comments should be concise**. Add a short, concise comment only when the `why` is non-obvious: a workaround, a hidden invariant, a subtle ordering constraint, a clever reduction. Never document the actual implementation, focus on the intent and the why.
 
-## TypeScript Migration
-
-**When touching existing JavaScript files, propose to convert them to TypeScript first**. Create a separate PR for the conversion, then implement the changes.
-
 ## Verify before done
 
 - **Run the project type-check** when finished (see the shared TypeScript commands above).

.clj-kondo/config.edn

@@ -7,7 +7,6 @@
 
   :aliased-namespace-symbol     {:level :warning}
   :case-symbol-test             {:level :warning}
-  :condition-always-true        {:level :warning}
   :def-fn                       {:level :warning}
   :dynamic-var-not-earmuffed    {:level :warning}
   :equals-expected-position     {:level :warning, :only-in-test-assertion true}
@@ -50,9 +49,11 @@
   ;; disabled linters
   ;;
 
+  :constant-condition {:level :off} ; TODO (sashko): too confused by defenterprises, some hook/config is needed
   :redundant-ignore {:level :off} ; lots of false positives, see https://github.com/clj-kondo/clj-kondo/issues/2414
   :unexpected-recur {:level :off} ; TODO (cam): I think we just need to tell it how to handle MBQL match and we can enable this?
   :redundant-primitive-coercion {:level :off} ; there are many defensive boolean coercions, kondo looks too much into it
+  :type-mismatch {:level :off} ; Still quite raw, can sometimes give useful insights, but sometimes is just confused
 
   ;;
   ;; globally-enabled custom linters
@@ -71,6 +72,12 @@
   :metabase/namespace-name                                   {:level :warning}
   :metabase/no-jsqlparser-imports                            {:level :warning}
   :metabase/prefer-with-dynamic-fn-redefs                    {:level :warning}
+  :metabase/t2-query-namespace                               {:level :warning}
+  :metabase/table-or-field-query                             {:level :warning}
+  ;; App-DB query hygiene: a value reaching a value slot unmarked, and a query written as
+  ;; `:column value` pairs rather than a map. Off by default and enabled per namespace under
+  ;; `:config-in-ns`; flip it on globally once every `db.clj` has been converted.
+  :metabase/unsafe-app-db-query                              {:level :off}
   :metabase/toucan-model-ns                                  {:level :warning}
   :metabase/require-shape-checker                            {:level :warning}
   :metabase/tests-must-live-in-known-modules                 {:level :warning}
@@ -179,8 +186,19 @@
      clojure.core.async/take!
      clojure.core.async/to-chan!
      clojure.core.async/to-chan!!
+     ;; writes the ratchet files from a :once fixture that finishes before the parallel tests
+     dev.kondo-ratchet/fix!
+     ;; builds Babashka's classpath cache from a :once fixture, before the parallel tests start, so that
+     ;; they don't each race to create it; the side effect is process-external and idempotent
+     metabase.core.modules-consistency-test/warm-babashka-classpath!
      metabase.ai-tracing.core/record!
      metabase.api.macros.defendpoint.tools-manifest/assert-optional-fields-nullable!
+     ;; MCP v2 tool tests: call-tool! dispatches a tool with no shared mutable state across tests
+     metabase.mcp.v2.tools.alert-test/call-tool!
+     metabase.mcp.v2.tools.definitions-test/call-tool!
+     metabase.mcp.v2.tools.metric-test/call-tool!
+     ;; the `!` is for the throw (a teaching error), not a mutation; no shared mutable state
+     metabase.mcp.v2.tools.browse/validate-args-for-action!
      metabase.channel.core/send!
      metabase.channel.render.pdf/draw-too-large!
      metabase.channel.render.pdf/draw-no-results!
@@ -188,6 +206,8 @@
      metabase.channel.render.pdf.font/load-fonts!
      metabase.warehouses.models.database/assert-not-h2!
      metabase.driver.sql-jdbc.execute/execute-prepared-statement!
+     ;; only inspects a details map and throws; the `!` is for the throw, not for a mutation
+     metabase.driver/validate-db-details!
      metabase.mcp.usage/record-mcp-session!
      metabase.mcp.usage/record-mcp-session-end!
      metabase.mcp.usage/record-mcp-tool-call!
@@ -212,7 +232,9 @@
      ;; Safe in tests, where we typically use a private, temporary index per thread.
      metabase.search.core/reindex!
      metabase.util/run-count!
-     next.jdbc/execute!}}
+     next.jdbc/execute!
+     ;; pure validator: parses a keyword and throws on a bad one, touches no state
+     metabase.mcp.v2.tools.question/check-semantic-type!}}
 
   :metabase/i-like-making-cams-eyes-bleed-with-horrifically-long-tests
   {:level      :warning
@@ -275,10 +297,6 @@
     instaparse.core/transform
     (metabase.server.streaming-response/streaming-response)
     (metabase.driver.druid.query-processor-test/druid-query-returning-rows)
-    (metabase.util.match/match-one)
-    (metabase.util.match/match-many)
-    (metabase.util.match/replace-in)
-    (metabase.util.match/replace)
     (metabase.driver-api.core/match-one)
     (metabase.driver-api.core/match-many)
     (metabase.driver-api.core/replace)
@@ -298,7 +316,10 @@
     metabase.query-processor.util/normalize-token                {:namespaces ["metabase.*"]}}}
 
   :discouraged-var
-  {clojure.core/print                                 {:message "Use metabase.util.log instead of clojure.core/print"}
+  {metabase-enterprise.entity-retrieval.core/search-unfiltered {:message "Permission bypass risk: library-index hits are unfiltered — resolve each entity and drop what the current user can't read"}
+   metabase.entity-retrieval.core/search-unfiltered            {:message "Permission bypass risk: library-index hits are unfiltered — resolve each entity and drop what the current user can't read"}
+   metabase.entity-retrieval.mirror/search-unfiltered          {:message "Permission bypass risk: library-index hits are unfiltered — resolve each entity and drop what the current user can't read"}
+   clojure.core/print                                 {:message "Use metabase.util.log instead of clojure.core/print"}
    clojure.core/println                               {:message "Use metabase.util.log instead of clojure.core/println"}
    clojure.core/printf                                {:message "Use metabase.util.log instead of clojure.core/printf"}
    clojure.core/prn                                   {:message "Use metabase.util.log instead of clojure.core/prn"}
@@ -397,6 +418,7 @@
     metabase.channel.render.core              channel.render
     metabase.cloud-migration.core             cloud-migration
     metabase.eid-translation.core             eid-translation
+    metabase.llm.test-util                    llm.tu
     metabase.login-history.core               login-history
     metabase.model-persistence.core           model-persistence
     metabase.notification.core                notification
@@ -460,11 +482,14 @@
   metabase-enterprise.serialization.metadata-file-import.wire-format-test/with-tiny-fixture! clojure.core/fn
   metabase-enterprise.serialization.test-util/with-dbs                                  clojure.core/fn
   metabase-enterprise.serialization.test-util/with-random-dump-dir                      clojure.core/let
+  metabase-enterprise.tenants.pulse-api-test/with-tenant-pulse-fixture!                 clojure.core/fn
   metabase-enterprise.workspaces.test-util/with-resources!                              clojure.core/let
   metabase-enterprise.workspaces.test-util/with-workspaces!                             clojure.core/let
   metabase.actions.test-util/with-actions                                               clojure.core/let
   metabase.transforms.test-util/with-transform-cleanup!                                 clojure.core/let
   metabase.api.common/let-404                                                           clojure.core/let
+  metabase.app-db.connection/with-unshared-connection                                   clojure.core/fn
+  metabase.app-db.core/with-unshared-connection                                         clojure.core/fn
   metabase.app-db.custom-migrations.util/with-temp-scheduler!                           clojure.core/fn
   metabase.app-db.custom-migrations/define-migration                                    clj-kondo.lint-as/def-catch-all
   metabase.app-db.custom-migrations/define-reversible-migration                         clj-kondo.lint-as/def-catch-all
@@ -482,11 +507,13 @@
   metabase.driver.sql-jdbc.connection/with-connection-spec-for-testing-connection       clojure.core/let
   metabase.driver.sql-jdbc.execute.diagnostic/capturing-diagnostic-info                 clojure.core/fn
   metabase.driver-api.core/defsetting                                                   hooks.metabase.settings.models.setting/defsetting
+  metabase.mcp.v2.registry/deftool                                                      clojure.core/defn
   metabase.models.json-migration/def-json-migration                                     clj-kondo.lint-as/def-catch-all
   metabase.models.util.spec-update/define-spec                                          clojure.core/def
   metabase.notification.test-util/with-card-notification                                clojure.core/let
   metabase.notification.test-util/with-system-event-notification!                       clojure.core/let
   metabase.notification.test-util/with-temp-notification                                clojure.core/let
+  metabase.oauth-server.test-util/with-oauth-client                                     clojure.core/fn
   metabase.osi.ai-context.api-test/with-test-entry                                      clojure.core/let
   metabase.premium-features.core/defenterprise-schema                                   clj-kondo.lint-as/def-catch-all
   metabase.premium-features.defenterprise/defenterprise-schema                          clj-kondo.lint-as/def-catch-all
@@ -496,7 +523,9 @@
   metabase.query-processor.pipeline-queries-test/mbql5-query                            clojure.core/->
   metabase.query-processor.pipeline-queries-test/run-mbql5-query                        clojure.core/->
   metabase.query-processor.error-type/deferror                                          clojure.core/def
+  metabase.query-processor.core/with-reducible-deserialized-results                     clojure.core/let
   metabase.query-processor.middleware.cache.impl/with-reducible-deserialized-results    clojure.core/let
+  metabase.query-processor.result-serialization/with-reducible-deserialized-results     clojure.core/let
   metabase.query-processor.middleware.process-userland-query-test/with-query-execution! clojure.core/let
   metabase.query-processor.setup/with-qp-setup                                          clojure.core/let
   metabase.search.api-test/do-test-users                                                clojure.core/let
@@ -513,7 +542,6 @@
   metabase.test.data.interface/defdataset                                               clojure.core/def
   metabase.test.data.interface/defdataset-edn                                           clojure.core/def
   metabase.test.embedded-postgres.core/with-system                                      clojure.core/let
-  metabase.test.gentest/defgentest                                                      clojure.test/deftest
   metabase.test/defdataset                                                              clojure.core/def
   metabase.test/let-url                                                                 clojure.core/let
   metabase.test/with-actions                                                            clojure.core/let
@@ -524,6 +552,7 @@
   metabase.test/with-temp-empty-app-db                                                  clojure.core/let
   metabase.test/with-temp-file                                                          clojure.core/let
   metabase.test/with-user-in-groups                                                     clojure.core/let
+  metabase.transforms-rest.api.transform-runs-test/with-runs-fixture!                   clojure.core/fn
   metabase.upload.impl-test/with-upload-table!                                          clojure.core/let
   metabase.util/for-map                                                                 clojure.core/for
   metabase.util.files/with-open-path-to-resource                                        clojure.core/let
@@ -566,6 +595,7 @@
    clojure.core/defprotocol                                                                                                  hooks.clojure.core.def/lint-def
    clojure.core/defrecord                                                                                                    hooks.clojure.core.def/lint-def
    clojure.core/deftype                                                                                                      hooks.clojure.core.def/lint-def
+   clojure.core/ex-info                                                                                                      hooks.metabase.agent-message/lint-ex-info
    clojure.core/ns                                                                                                           hooks.clojure.core.ns/lint-ns
    clojure.core/require                                                                                                      hooks.clojure.core.require/lint-require
    clojure.core/requiring-resolve                                                                                            hooks.clojure.core.require/lint-requiring-resolve
@@ -581,7 +611,6 @@
    metabase-enterprise.cache.config-test/with-temp-persist-models                                                            hooks.common/with-seven-bindings
    metabase-enterprise.dependencies.api-test/with-dependents-test!                                                           hooks.common/with-two-bindings
    metabase-enterprise.metabot-v3.tools.dependencies-test/with-dependent-transforms!                                         hooks.common/with-two-bindings
-   metabase-enterprise.metabot.tools.dependencies-test/with-dependent-transforms!                                            hooks.common/with-two-bindings
    metabase-enterprise.semantic-search.db.connection/with-migrate-tx                                                         hooks.common/let-one-with-optional-value
    metabase-enterprise.serialization.api-test/with-serialization-test-data!                                                  hooks.common/with-three-bindings
    metabase-enterprise.serialization.test-util/with-temp-dpc                                                                 hooks.toucan2.tools.with-temp/with-temp
@@ -618,10 +647,60 @@
    metabase.lib.schema.mbql-clause/define-tuple-mbql-clause                                                                  hooks.metabase.lib.schema.mbql-clause/define-mbql-clause
    methodical.core/defmethod                                                                                                 hooks.metabase.toucan.table-name/lint-defmethod
    methodical.macros/defmethod                                                                                               hooks.metabase.toucan.table-name/lint-defmethod
+   metabase.app-db.core/query                                                                                                hooks.metabase.toucan.db-ns/lint-query-call
+   metabase.app-db.core/streaming-reducible-query                                                                            hooks.metabase.toucan.db-ns/lint-query-call
+   metabase.app-db.core/select-or-insert!                                                                                    hooks.metabase.toucan.db-ns/lint-query-call
+   metabase.app-db.core/update-or-insert!                                                                                    hooks.metabase.toucan.db-ns/lint-query-call
+   metabase.app-db.core/current-timestamp-string                                                                             hooks.metabase.toucan.db-ns/lint-query-call
+   metabase.app-db.query/query                                                                                               hooks.metabase.toucan.db-ns/lint-query-call
+   metabase.app-db.query/streaming-reducible-query                                                                           hooks.metabase.toucan.db-ns/lint-query-call
+   metabase.app-db.query/select-or-insert!                                                                                   hooks.metabase.toucan.db-ns/lint-query-call
+   metabase.app-db.query/update-or-insert!                                                                                   hooks.metabase.toucan.db-ns/lint-query-call
+   metabase.app-db.query/current-timestamp-string                                                                            hooks.metabase.toucan.db-ns/lint-query-call
+   toucan2.core/count                                                                                                        hooks.metabase.toucan.db-ns/lint-query-call
+   toucan2.core/delete!                                                                                                      hooks.metabase.toucan.db-ns/lint-query-call
+   toucan2.core/exists?                                                                                                      hooks.metabase.toucan.db-ns/lint-query-call
+   toucan2.core/insert!                                                                                                      hooks.metabase.toucan.db-ns/lint-query-call
+   toucan2.core/insert-returning-instance!                                                                                   hooks.metabase.toucan.db-ns/lint-query-call
+   toucan2.core/insert-returning-instances!                                                                                  hooks.metabase.toucan.db-ns/lint-query-call
+   toucan2.core/insert-returning-pk!                                                                                         hooks.metabase.toucan.db-ns/lint-query-call
+   toucan2.core/insert-returning-pks!                                                                                        hooks.metabase.toucan.db-ns/lint-query-call
+   toucan2.core/query                                                                                                        hooks.metabase.toucan.db-ns/lint-query-call
+   toucan2.core/query-one                                                                                                    hooks.metabase.toucan.db-ns/lint-query-call
+   toucan2.core/reducible-query                                                                                              hooks.metabase.toucan.db-ns/lint-query-call
+   toucan2.core/reducible-select                                                                                             hooks.metabase.toucan.db-ns/lint-query-call
+   toucan2.core/reducible-update                                                                                             hooks.metabase.toucan.db-ns/lint-query-call
+   toucan2.core/reducible-update-returning-pks                                                                               hooks.metabase.toucan.db-ns/lint-query-call
+   toucan2.core/save!                                                                                                        hooks.metabase.toucan.db-ns/lint-query-call
+   toucan2.core/select                                                                                                       hooks.metabase.toucan.db-ns/lint-query-call
+   toucan2.core/select-fn->fn                                                                                                hooks.metabase.toucan.db-ns/lint-query-call
+   toucan2.core/select-fn->pk                                                                                                hooks.metabase.toucan.db-ns/lint-query-call
+   toucan2.core/select-fn-reducible                                                                                          hooks.metabase.toucan.db-ns/lint-query-call
+   toucan2.core/select-fn-set                                                                                                hooks.metabase.toucan.db-ns/lint-query-call
+   toucan2.core/select-fn-vec                                                                                                hooks.metabase.toucan.db-ns/lint-query-call
+   toucan2.core/select-one                                                                                                   hooks.metabase.toucan.db-ns/lint-query-call
+   toucan2.core/select-one-fn                                                                                                hooks.metabase.toucan.db-ns/lint-query-call
+   toucan2.core/select-one-pk                                                                                                hooks.metabase.toucan.db-ns/lint-query-call
+   toucan2.core/select-pk->fn                                                                                                hooks.metabase.toucan.db-ns/lint-query-call
+   toucan2.core/select-pks-set                                                                                               hooks.metabase.toucan.db-ns/lint-query-call
+   toucan2.core/select-pks-vec                                                                                               hooks.metabase.toucan.db-ns/lint-query-call
+   toucan2.core/update!                                                                                                      hooks.metabase.toucan.db-ns/lint-query-call
+   toucan2.core/update-returning-pks!                                                                                        hooks.metabase.toucan.db-ns/lint-query-call
    metabase.lib.test-util.macros/$ids                                                                                        hooks.metabase.test.data/$ids
    metabase.lib.test-util.macros/mbql-query                                                                                  hooks.metabase.test.data/mbql-query
    metabase.lib.test-util.macros/mbql-5-query                                                                                hooks.metabase.test.data/mbql-query
    metabase.lib.test-util.macros/with-testing-against-standard-queries                                                       hooks.metabase.lib.test-util.macros/with-testing-against-standard-queries
+   metabase.mcp.transport/jsonrpc-error                                                                                      hooks.metabase.agent-message/lint-jsonrpc-error
+   metabase.mcp.v2.common/ellipsize                                                                                          hooks.metabase.agent-message/lint-ellipsize
+   metabase.mcp.v2.common/error-content                                                                                      hooks.metabase.agent-message/lint-teaching-exit
+   metabase.mcp.v2.common/list-content                                                                                       hooks.metabase.agent-message/lint-list-content
+   metabase.mcp.v2.common/success-content                                                                                    hooks.metabase.agent-message/lint-success-content
+   metabase.mcp.v2.common/throw-teaching-error                                                                               hooks.metabase.agent-message/lint-teaching-exit
+   metabase.mcp.v2.dashboard-ops/op-error!                                                                                   hooks.metabase.agent-message/lint-op-error
+   metabase.mcp.v2.message/msg                                                                                               hooks.metabase.agent-message/lint-msg
+   metabase.mcp.v2.tools.browse/paged-list-content                                                                           hooks.metabase.agent-message/lint-list-content
+   metabase.mcp.v2.tools.parameters-test/with-fixtures                                                                       hooks.common/with-one-binding
+   metabase.metrics.api-dimension-test/with-seeded-metric                                                                    hooks.common/with-one-binding
    metabase.model-persistence.api-test/with-persistence-setup!                                                               hooks.common/with-one-top-level-binding
    metabase.model-persistence.api-test/with-setup!                                                                           hooks.common/with-one-top-level-binding
    metabase.model-persistence.test-util/with-persistence-enabled!                                                            hooks.metabase.model-persistence.test-util/with-persistence-enabled!
@@ -670,7 +749,6 @@
    metabase.test.data/dataset                                                                                                hooks.metabase.test.data/dataset
    metabase.test.data/mbql-query                                                                                             hooks.metabase.test.data/mbql-query
    metabase.test.data/run-mbql-query                                                                                         hooks.metabase.test.data/mbql-query
-   metabase.test.gentest/iterate                                                                                             hooks.metabase.test.gentest/iterate*
    metabase.test.util.async/with-open-channels                                                                               hooks.common/let-with-optional-value-for-last-binding
    metabase.test.util.generators.jvm/with-random-cards                                                                       hooks.metabase.test.util.generators.jvm/with-random-cards
    metabase.test.util.log/with-log-level                                                                                     hooks.common/with-ignored-first-arg
@@ -721,6 +799,7 @@
    metabase.util.malli.registry/def                                                                                          hooks.metabase.util.malli.registry/def
    metabase.util.match/match-one                                                                                             hooks.metabase.util.match/match-one
    metabase.util.match/match-many                                                                                            hooks.metabase.util.match/match-many
+   metabase.util.match/matches?                                                                                              hooks.metabase.util.match/matches?
    metabase.util.match/replace                                                                                               hooks.metabase.util.match/replace
    metabase.util.match/replace-in                                                                                            hooks.metabase.util.match/replace-in
    metabase.util/case-enum                                                                                                   hooks.metabase.util/case-enum
@@ -736,6 +815,7 @@
    clojurewerkz.quartzite.schedule.simple/schedule                                              macros.quartz/simple-schedule
    clojurewerkz.quartzite.triggers/build                                                        macros.quartz/build-trigger
    metabase-enterprise.database-routing.e2e-test/with-temp-dbs!                                 macros.metabase-enterprise.database-routing.e2e-test/with-temp-dbs!
+   metabase-enterprise.database-routing.e2e-test/with-routing-setup!                            macros.metabase-enterprise.database-routing.e2e-test/with-routing-setup!
    metabase-enterprise.impersonation.util-test/with-impersonations!                             macros.metabase-enterprise.impersonation.util-test/with-impersonations!
    metabase-enterprise.query-reference-validation.api-test/with-test-setup!                     macros.metabase-enterprise.query-reference-validation.api-test/with-test-setup!
    metabase-enterprise.sandbox.test-util/with-gtaps!                                            macros.metabase-enterprise.sandbox.test-util/with-gtaps!
@@ -788,7 +868,7 @@
    :name    test-namespaces}
   {:pattern "^(?!.*-test(?:\\..*)?$)(?!.*test-util)(?!^metabase\\.test.*).*$"
    :name    source-namespaces}
-  {:pattern "(?:(?:^metabase\\.cmd.*)|(?:^build.*)|(?:^metabuild-common.*)|(?:^release.*)|(?:^i18n.*)|(?:^lint-migrations-file$))|(?:^mage.*)"
+  {:pattern "(?:(?:^metabase\\.cmd.*)|(?:^build.*)|(?:^metabuild-common.*)|(?:^release.*)|(?:^i18n.*)|(?:^lint-migrations-file$))|(?:^mage.*)|(?:^load-namespaces.*)|(?:^dev\\..*)"
    :name    printable-namespaces}
   {:pattern "^metabase\\.(?:(?:lib)|(?:legacy-mbql))\\..*"
    :name    metabase-lib}
@@ -825,16 +905,40 @@
   {:pattern "^metabase(?:((?:-enterprise\\.sandbox)?\\.query-processor)|(?:\\.driver\\.sql(?!server)(?!ite))).*-test$"
    :name    general-qp-and-driver-test-namespaces}
   {:pattern "(?:^mage.*)"
-   :name    mage-namespaces}]
+   :name    mage-namespaces}
+  ;;
+  ;; the app-db module is the application database layer itself (connections, migrations, encryption), so it gets to
+  ;; run Toucan 2 queries anywhere.
+  ;;
+  {:pattern "^metabase\\.app-db\\..*"
+   :name    app-db-namespaces}
+  ;;
+  ;; MCP source namespaces, OSS and enterprise, whose prose reaches an LLM agent, excluding test namespaces.
+  ;;
+  {:pattern "^(?!.*-test(?:\\..*)?$)(?!.*test-util)metabase(?:-enterprise)?\\.mcp\\..*"
+   :name    agent-message-namespaces}
+  ;;
+  ;; MCP source namespaces whose caller-facing errors are MCP exits: `metabase.mcp.transport` and `metabase.mcp.v2.*`,
+  ;; and their enterprise counterparts. Other MCP namespaces' 4xx `ex-info`s are admin API and middleware errors, not
+  ;; MCP exits.
+  ;;
+  {:pattern "^(?!.*-test(?:\\..*)?$)(?!.*test-util)metabase(?:-enterprise)?\\.mcp\\.(?:transport$|v2\\..*)"
+   :name    agent-exit-namespaces}]
 
  :config-in-ns
- {test-namespaces
+ {metabase.app-db.custom-migrations
+  {:linters
+   ;; a migration reads the rows as they were when it ran; applying today's user settings would make it drift
+   {:metabase/table-or-field-query {:level :off}}}
+
+  test-namespaces
   {:linters
    {:inline-def                                          {:level :off}
     :missing-docstring                                   {:level :off}
     :private-call                                        {:level :off}
     :metabase/defsetting-must-specify-export             {:level :off}
     :metabase/defsetting-namespace                       {:level :off}
+    :metabase/t2-query-namespace                         {:level :off}
     :metabase/test-helpers-use-non-thread-safe-functions {:level :warning} ; more config in `.clj-kondo/config/test-helpers/config.edn`
 
     :discouraged-var
@@ -842,12 +946,33 @@
      metabase.lib.convert/->legacy-MBQL {:level :off}
      metabase.lib.core/->legacy-MBQL    {:level :off}}}}
 
+  app-db-namespaces
+  {:linters {:metabase/t2-query-namespace {:level :off}}}
+
+  agent-message-namespaces
+  {:linters {:metabase/agent-message-lines {:level :warning}}}
+
+  agent-exit-namespaces
+  {:linters {:metabase/agent-message-exit {:level :warning}}}
+
+  ;; Namespaces whose values are marked. Adding one here is what keeps it that way; see
+  ;; `metabase.app-db.value-guard`.
+  metabase.content-translation.db
+  {:linters {:metabase/unsafe-app-db-query {:level :warning}}}
+
   ;; .cljc tests run in both Clojure and ClojureScript — `with-dynamic-fn-redefs` is JVM-only,
   ;; so leave these alone.
   metabase.lib.aggregation-test
   {:linters {:metabase/prefer-with-dynamic-fn-redefs {:level :off}}}
   metabase.util.time-test
   {:linters {:metabase/prefer-with-dynamic-fn-redefs {:level :off}}}
+  metabase.lib.metadata.calculation-test
+  {:linters {:metabase/prefer-with-dynamic-fn-redefs {:level :off}}}
+
+  ;; classloader sits below `util` in the module graph, so it can't use `metabase.util.log` without creating
+  ;; a cycle; it gets to use tools.logging directly.
+  metabase.classloader.impl
+  {:linters {:discouraged-namespace {clojure.tools.logging {:level :off}}}}
 
   source-namespaces
   {:linters

.clj-kondo/config/modules/ratchets.edn

@@ -0,0 +1,7 @@
+;; Budgets for escape hatches in config.edn. Counts may fall but not exceed these values.
+;; Leave reductions to the post-merge shrink workflow; explain increases in the PR.
+{:api-any              1
+ :friend-edges         1
+ :model-imports-bypass 2
+ :ns-prefixes          81
+ :uses-any             4}

.clj-kondo/config/test-helpers/config.edn

@@ -58,6 +58,7 @@
      metabase.app-db.core/finish-db-setup!
      metabase.app-db.core/migrate!
      metabase.app-db.core/setup-db!
+     metabase.app-db.encryption-test-util/do-with-encrypted-app-db!
      metabase.app-db.schema-migrations-test.impl/run-migrations-in-range!
      metabase.app-db.setup/migrate!
      metabase.app-db.setup/setup-db!

.clj-kondo/macros/metabase_enterprise/database_routing/e2e_test.clj

@@ -3,3 +3,8 @@
 (defmacro with-temp-dbs! [bindings & body]
   `(let [~@(interleave bindings (repeat nil))]
      ~@body))
+
+(defmacro with-routing-setup! [[router-binding destinations] & body]
+  `(let [~router-binding nil
+         ~@(interleave (map first destinations) (repeat nil))]
+     ~@body))

.clj-kondo/ratchets.edn

@@ -0,0 +1,82 @@
+;; Budgets for kondo suppressions: inline `:clj-kondo/ignore` forms per linter (:ignore-counts), and
+;; config-level waivers in .clj-kondo/config.edn (:config-counts -- :off switches and :exclude entries).
+;; Each :ignore-counts value is a non-negative integer budget, or :unlimited for no ceiling.
+;; Checks fail when a count exceeds its numeric budget; unused budget is allowed.
+;; Any ignore outside :comment-exempt needs an explanatory comment directly above or trailing on its line.
+;; `./bin/mage kondo-ratchets-shrink` lowers budgets unless `--seed` explicitly adds or raises one.
+;; The workflow runs it on master, so feature branches do not need to record reductions.
+;; Raising or adding a budget (`--seed` for inline ignores, a manual edit otherwise) or widening the
+;; exemptions must be explained in the PR.
+;; :all is the vector-less ignore form, which suppresses every linter on the next form.
+{:ignore-counts  {:aliased-namespace-symbol                                            3
+                  :case-symbol-test                                                    1
+                  :clojure-lsp/unused-public-var                                       9
+                  :consistent-alias                                                    2
+                  :def-fn                                                              1
+                  :deprecated-namespace                                                95
+                  :deprecated-var                                                      95
+                  :discouraged-java-method                                             4
+                  :discouraged-namespace                                               69
+                  :discouraged-var                                                     130
+                  :duplicate-require                                                   1
+                  :equals-true                                                         1
+                  :main-without-gen-class                                              1
+                  :metabase/disallow-hardcoded-driver-names-in-tests                   34
+                  :metabase/discourage-millis-duration                                 1
+                  :metabase/i-like-making-cams-eyes-bleed-with-horrifically-long-tests 13
+                  :metabase/modules                                                    24
+                  :metabase/namespace-name                                             4
+                  :metabase/prefer-with-dynamic-fn-redefs                              :unlimited
+                  :metabase/test-helpers-use-non-thread-safe-functions                 18
+                  :metabase/validate-defendpoint-has-response-schema                   427
+                  :metabase/validate-defendpoint-query-params-use-kebab-case           48
+                  :metabase/validate-defendpoint-route-uses-kebab-case                 44
+                  :metabase/validate-deftest                                           9
+                  :missing-docstring                                                   12
+                  :missing-protocol-method                                             3
+                  :non-arg-vec-return-type-hint                                        1
+                  :reduce-without-init                                                 3
+                  :redundant-do                                                        1
+                  :syntax                                                              2
+                  :type-mismatch                                                       8
+                  :uninitialized-var                                                   1
+                  :unquote-not-syntax-quoted                                           1
+                  :unresolved-namespace                                                3
+                  :unresolved-symbol                                                   11
+                  :unsorted-required-namespaces                                        :unlimited
+                  :unused-alias                                                        2
+                  :unused-binding                                                      9
+                  :unused-excluded-var                                                 2
+                  :unused-namespace                                                    2
+                  :unused-private-var                                                  8
+                  :unused-value                                                        1}
+ :config-counts  {:constant-condition                      1
+                  :deprecated-namespace                    7
+                  :deprecated-var                          16
+                  :discouraged-namespace                   14
+                  :discouraged-var                         14
+                  :inline-def                              1
+                  :main-without-gen-class                  1
+                  :metabase/defsetting-must-specify-export 1
+                  :metabase/defsetting-namespace           1
+                  :metabase/prefer-with-dynamic-fn-redefs  4
+                  :metabase/t2-query-namespace             2
+                  :metabase/table-or-field-query           1
+                  :metabase/unsafe-app-db-query            1
+                  :missing-docstring                       1
+                  :private-call                            1
+                  :redundant-ignore                        1
+                  :redundant-primitive-coercion            1
+                  :refer-all                               1
+                  :type-mismatch                           1
+                  :unexpected-recur                        1
+                  :unresolved-symbol                       15
+                  :unresolved-var                          1
+                  :unused-referred-var                     4}
+ :comment-exempt #{:deprecated-namespace
+                   :discouraged-namespace
+                   :discouraged-var
+                   :metabase/modules
+                   :metabase/validate-defendpoint-has-response-schema
+                   :metabase/validate-defendpoint-query-params-use-kebab-case
+                   :metabase/validate-defendpoint-route-uses-kebab-case}}

.clj-kondo/src/hooks/clojure/core/ns.clj

@@ -71,10 +71,28 @@
   (some-> (ns-form-node->ns-symb-node ns-form-node)
           hooks/sexpr))
 
+(defn- lint-test-parallel-metadata [ns-form-node]
+  (when-let [ns-symb-node (ns-form-node->ns-symb-node ns-form-node)]
+    (let [ns-metadata (meta (hooks/sexpr ns-symb-node))]
+      (cond
+        (:synchronous ns-metadata)
+        (hooks/reg-finding!
+         (assoc (meta ns-symb-node)
+                :message (str "Use `^:synchronized` to mark this namespace explicitly non-parallel; "
+                              "`^:synchronous` is ignored by Hawk. [:metabase/validate-deftest]")
+                :type :metabase/validate-deftest))
+
+        (and (contains? ns-metadata :parallel)
+             (false? (:parallel ns-metadata)))
+        (hooks/reg-finding!
+         (assoc (meta ns-symb-node)
+                :message "Use `^:synchronized` instead of `^{:parallel false}`. [:metabase/validate-deftest]"
+                :type :metabase/validate-deftest))))))
+
 (defn- lint-modules [ns-form-node config]
   (let [ns-symb (ns-form-node->ns-symb ns-form-node)]
     (when-not (modules/ignored-namespace? config ns-symb)
-      (when-let [current-module (modules/module ns-symb)]
+      (when-let [current-module (modules/module config ns-symb)]
         (let [required-namespace-symb-nodes (-> ns-form-node
                                                 ns-form-node->require-node
                                                 require-node->namespace-symb-nodes)]
@@ -140,6 +158,7 @@
     lint-requires-on-new-lines
     (lint-modules (modules/config x))
     lint-namespace-name
+    lint-test-parallel-metadata
     lint-jsqlparser-imports)
   x)
 

.clj-kondo/src/hooks/clojure/core/require.clj

@@ -11,15 +11,32 @@
          (every? simple-symbol? required-namespaces)]}
   (when-not (modules/ignored-namespace? config current-ns)
     ;; ignore namespaces outside of the module system
-    (when-let [current-module (modules/module current-ns)]
+    (when-let [current-module (modules/module config current-ns)]
       (doseq [required-namespace required-namespaces]
         ;; ignore namespaces outside of the module system.
-        (when (modules/module required-namespace)
+        (when (modules/module config required-namespace)
           (when-let [error (modules/usage-error config current-module required-namespace)]
             (hooks/reg-finding! (assoc (meta node)
                                        :message error
                                        :type    :metabase/modules))))))))
 
+(defn- lint-dynamic-require* [node current-ns config]
+  (when (and (not (modules/ignored-namespace? config current-ns))
+             (modules/module config current-ns))
+    (hooks/reg-finding! (assoc (meta node)
+                               :message "Module dependency cannot be statically determined from a dynamic require"
+                               :type    :metabase/modules))))
+
+(defn- quoted-require? [node]
+  (or (= (hooks/tag node) :quote)
+      (and (= (hooks/tag node) :list)
+           (let [[x] (:children node)]
+             (and (hooks/token-node? x)
+                  (= (hooks/sexpr x) 'quote))))))
+
+(defn- keyword-node? [node]
+  (keyword? (hooks/sexpr node)))
+
 (defn- unwrap-require [node]
   (case (hooks/tag node)
     ;; some.namespace of some.namespace/some-var
@@ -42,7 +59,11 @@
 
     ;; something like [some.namespace :as whatever]
     :vector
-    (recur (first (:children node)))))
+    (recur (first (:children node)))
+
+    ;; anything else -- e.g. a runtime expression like `(requiring-resolve (:failing-test-var opts))` --
+    ;; has no statically-known namespace
+    nil))
 
 (comment
   (unwrap-require (-> "(requiring-resolve 'metabase.notification.payload.execute/execute-dashboard)"
@@ -51,20 +72,24 @@
                       second)))
 
 (defn- lint-require* [node current-ns config]
-  (let [[_require & args]   (:children node)
-        required-namespaces (->> (keep unwrap-require args)
-                                 ;; `require` runs through `cc/load-libs` which allows
-                                 ;; #{:as :reload :reload-all :require :use :verbose :refer :as-alias}
-                                 ;; as args. If you use a REPL tool that applies clj-kondo linting (e.g., Clojure MCP)
-                                 ;; you may wish to `:reload` or `:reload-all` a namespace. So we shouldn't assume all
-                                 ;; args are keywords:
-                                 (remove keyword?))]
-    (lint* node current-ns config required-namespaces)))
+  (let [[_require & args]    (:children node)
+        ;; Keywords such as `:reload` and `:reload-all` are options, not namespace dependencies.
+        namespace-nodes     (remove keyword-node? args)
+        static-nodes        (filter quoted-require? namespace-nodes)
+        required-namespaces (->> (keep unwrap-require static-nodes)
+                                 (filter simple-symbol?))]
+    (lint* node current-ns config required-namespaces)
+    (when (or (not= (count static-nodes) (count namespace-nodes))
+              (not= (count required-namespaces) (count static-nodes)))
+      (lint-dynamic-require* node current-ns config))))
 
 (defn- lint-requiring-resolve* [node current-ns config]
   (let [[_requiring-resolve symb-node] (:children node)
         required-namespace             (unwrap-require symb-node)]
-    (lint* node current-ns config [required-namespace])))
+    (if (and (quoted-require? symb-node)
+             (simple-symbol? required-namespace))
+      (lint* node current-ns config [required-namespace])
+      (lint-dynamic-require* node current-ns config))))
 
 (defn lint-require [x]
   (lint-require* (:node x) (:ns x) (modules/config x))

.clj-kondo/src/hooks/clojure/test.clj

@@ -28,11 +28,11 @@
     (walk form)))
 
 (defn- deftest-check-parallel
-  "1. Check if test is marked ^:parallel / ^:synchronized correctly.
+  "1. Check if test is marked `^:parallel` / `^:synchronized` correctly.
    2. Make sure disallowed forms are not used in ^:parallel tests.
-   3. Disallow ^:parallel tests in namespaces marked ^:synchronous -- the
-      ns marker is the author's blanket promise that nothing inside runs
-      in parallel, so an individual ^:parallel deftest contradicts it."
+   3. Disallow `^:parallel` tests in namespaces marked `^:synchronized` --
+      the ns marker is the author's blanket promise that nothing inside runs
+      in parallel, so an individual `^:parallel` deftest contradicts it."
   [{[_ test-name & body] :children, :as _node} ns-sym config]
   (let [test-metadata     (:meta test-name)
         metadata-sexprs   (map hooks/sexpr test-metadata)
@@ -44,28 +44,48 @@
                            (completing merge)
                            {}
                            metadata-sexprs)
-        parallel?     (:parallel combined-metadata)
-        synchronized? (:synchronized combined-metadata)
-        ns-synchronous? (boolean (:synchronous (meta ns-sym)))]
+        parallel?                  (true? (:parallel combined-metadata))
+        synchronized?              (true? (:synchronized combined-metadata))
+        explicitly-nonparallel?    (or synchronized?
+                                       (and (contains? combined-metadata :parallel)
+                                            (false? (:parallel combined-metadata))))
+        ns-metadata                (meta ns-sym)
+        ns-explicitly-nonparallel? (or (true? (:synchronized ns-metadata))
+                                       (and (contains? ns-metadata :parallel)
+                                            (false? (:parallel ns-metadata))))]
+    (when (and (contains? combined-metadata :parallel)
+               (false? (:parallel combined-metadata)))
+      (hooks/reg-finding! (assoc (meta test-name)
+                                 :message (str "Use `^:synchronized` instead of `^{:parallel false}`. "
+                                               "[:metabase/validate-deftest]")
+                                 :type :metabase/validate-deftest)))
+    (when (:sequential combined-metadata)
+      (hooks/reg-finding! (assoc (meta test-name)
+                                 :message (str "Use `^:synchronized` to mark this test explicitly non-parallel; "
+                                               "`^:sequential` is ignored by Hawk. "
+                                               "[:metabase/validate-deftest]")
+                                 :type :metabase/validate-deftest)))
     (when (and parallel? synchronized?)
       (hooks/reg-finding! (assoc (meta test-name)
-                                 :message "Test should not be marked both ^:parallel and ^:synchronized"
+                                 :message "Test should not be marked both `^:parallel` and `^:synchronized`"
                                  :type :metabase/validate-deftest)))
-    (when (and parallel? ns-synchronous?)
+    (when (and parallel? ns-explicitly-nonparallel?)
       (hooks/reg-finding!
        (assoc (meta test-name)
-              :message (str "Test should not be marked ^:parallel in a namespace marked ^:synchronous -- "
+              :message (str "Test should not be marked `^:parallel` in a namespace marked "
+                            "`^:synchronized` -- "
                             "the ns marker promises no parallel execution. "
-                            "Drop ^:parallel from the deftest, or drop ^:synchronous from the ns. "
+                            "Drop `^:parallel` from the deftest, or drop `^:synchronized` from the ns. "
                             "[:metabase/validate-deftest]")
               :type :metabase/validate-deftest)))
-    ;; only when the custom `:metabase/deftest-not-marked-parallel-or-synchronized` is enabled: complain if tests are
-    ;; not explicitly marked `^:parallel` or `^:synchronized`. This is mostly to encourage people to mark everything
-    ;; `^:parallel` in places like `metabase.lib` tests unless there is a really good reason not to.
-    (when-not (or parallel? synchronized?)
+    ;; Only when the custom `:metabase/deftest-not-marked-parallel-or-synchronized` is enabled:
+    ;; complain if tests are not explicitly marked `^:parallel` or `^:synchronized`. This is
+    ;; mostly to encourage people to mark everything `^:parallel` in places like `metabase.lib`
+    ;; tests unless there is a really good reason not to.
+    (when-not (or parallel? explicitly-nonparallel?)
       (hooks/reg-finding!
        (assoc (meta test-name)
-              :message "Test should be marked either ^:parallel or ^:synchronized"
+              :message "Test should be marked either `^:parallel` or `^:synchronized`"
               :type :metabase/deftest-not-marked-parallel-or-synchronized)))
     (when parallel?
       (doseq [form body]
@@ -151,8 +171,11 @@
           (str/starts-with? (name ns-symb) prefix))
         ["build-drivers."
          "build."
+         "hooks." ; clj-kondo hook tests, outside the module system
          "i18n." ; bin/i18n
          "lint-migrations-file-test"
+         "load-namespaces." ; bin/load-namespaces
+         "mage."
          "main-test" ; bin/release-list
          "metabase.deps-edn-test"
          "metabase.driver."
@@ -171,7 +194,7 @@
                (not (contains? @warned-namespaces ns-symb)))
       (swap! warned-namespaces conj ns-symb)
       (let [known-modules  (set (keys (:metabase/modules (modules/config input))))
-            current-module (modules/module ns-symb)]
+            current-module (modules/module (modules/config input) ns-symb)]
         (when (or (not current-module)
                   (not (contains? known-modules current-module)))
           (hooks/reg-finding! (assoc (meta node)
@@ -231,18 +254,20 @@
 
 (defn use-fixtures
   "Flag `:parallel/unsafe` forms inside fixtures. Skipped when the surrounding
-  namespace is marked `^:synchronous` -- the ns marker is the author's
+  namespace is marked `^:synchronized` -- the ns marker is the author's
   explicit opt-in to a single-threaded test ns where destructive setup is
   safe. Without that opt-in, kondo can't know whether sibling deftests will
   be `^:parallel`, so the conservative default is to flag.
 
   Sister to [[deftest-check-parallel]]: the deftest hook rejects `^:parallel`
-  tests inside a `^:synchronous` ns, so the two checks together form a
-  coherent opt-in: either the whole ns is synchronous (fixtures can be
+  tests inside a `^:synchronized` ns, so the two checks together form a
+  coherent opt-in: either the whole ns is explicitly non-parallel (fixtures can be
   anything; no parallel tests allowed) or it isn't (fixtures must be
   parallel-safe)."
   [{:keys [node config], ns-sym :ns, :as input}]
-  (when-not (:synchronous (meta ns-sym))
+  (when-not (or (true? (:synchronized (meta ns-sym)))
+                (and (contains? (meta ns-sym) :parallel)
+                     (false? (:parallel (meta ns-sym)))))
     (let [linter-config (get-in config [:linters :metabase/validate-deftest])]
       (doseq [form (rest (:children node))]
         (warn-about-disallowed-parallel-forms form linter-config))))

.clj-kondo/src/hooks/common/modules.clj

@@ -1,4 +1,8 @@
 (ns hooks.common.modules
+  "Resolves namespaces to modules and enforces module boundaries.
+
+  The Kondo linter, config generator, and CI tooling share this namespace so
+  they apply the same rules."
   (:require
    [clojure.string :as str]))
 
@@ -12,30 +16,146 @@
   (merge (get-in config [:linters :metabase/modules])
          (select-keys config [:metabase/modules])))
 
-(defn module
+;;;; Module tree. These functions take the `:metabase/modules` map, or the prefix map built from it.
+;;;;
+;;;; Dots express nesting: `lib.schema` is a child of `lib`. A declared
+;;;; `enterprise/X` module is also a child of OSS module `X`. A namespace
+;;;; belongs to the module with the most specific matching `:ns-prefix`.
+
+(defn default-ns-prefix
+  "Namespace prefix a module owns unless it sets `:ns-prefix`: `metabase.lib.schema` for `lib.schema`,
+  `metabase-enterprise.foo` for `enterprise/foo`."
+  [module]
+  (str (if (= "enterprise" (namespace module)) "metabase-enterprise." "metabase.") (name module)))
+
+(defn module-ns-prefix
+  "Namespace prefix `module` owns: its `:ns-prefix`, else [[default-ns-prefix]]."
+  [modules module]
+  (or (get-in modules [module :ns-prefix])
+      (default-ns-prefix module)))
+
+(defn build-prefix->module
+  "Map each declared namespace prefix to its module, for [[declared-module]]."
+  [modules]
+  (into {}
+        (map (fn [module] [(module-ns-prefix modules module) module]))
+        (keys modules)))
+
+(defn declared-module
+  "Resolve `ns-symb` to its declared module, or `nil`.
+
+  Chooses the most specific dotted prefix and ignores a trailing `-test`."
+  [prefix->module ns-symb]
+  (loop [candidate (str/replace (str ns-symb) #"-test$" "")]
+    (or (get prefix->module candidate)
+        (when-let [dot (str/last-index-of candidate ".")]
+          (recur (subs candidate 0 dot))))))
+
+(defn resolve-module
   "E.g.
 
-    (module 'metabase.qp.middleware.wow) => 'qp
-    (module 'metabase-enterprise.whatever.core) => enterprise/whatever"
-  [ns-symb]
+    (resolve-module prefix->module 'metabase.qp.middleware.wow) => 'qp
+    (resolve-module prefix->module 'metabase-enterprise.whatever.core) => enterprise/whatever
+
+  An unmatched Metabase namespace resolves to its first segment so the linter can report an undeclared module."
+  [prefix->module ns-symb]
   {:pre [(simple-symbol? ns-symb)]}
   ;; treat something like `metabase.driver-test` (for a module that hasn't fully been updated to use `.core`
   ;; namespaces) as being in the `driver` module
   (let [ns-symb (if (str/ends-with? (name ns-symb) "-test")
                   (symbol (str/replace (name ns-symb) #"-test$" ""))
                   ns-symb)]
-    (or (some->> (re-find #"^metabase-enterprise\.([^.]+)" (str ns-symb))
+    (or (declared-module prefix->module ns-symb)
+        (some->> (re-find #"^metabase-enterprise\.([^.]+)" (str ns-symb))
                  second
                  (symbol "enterprise"))
         (some-> (re-find #"^metabase\.([^.]+)" (str ns-symb))
                 second
                 symbol))))
 
-(defn- module-api-namespaces
+(defn parent-module
+  "The direct parent of `module`, or `nil` when it is top-level."
+  [modules module]
+  (let [module-name (name module)]
+    (if-let [dot (str/last-index-of module-name ".")]
+      (symbol (namespace module) (subs module-name 0 dot))
+      (when (= "enterprise" (namespace module))
+        (let [oss (symbol module-name)]
+          (when (contains? modules oss)
+            oss))))))
+
+(defn descendant-of?
+  "Whether `module` is `ancestor` or one of its descendants."
+  [modules module ancestor]
+  (boolean (some #{ancestor} (take-while some? (iterate #(parent-module modules %) module)))))
+
+(defn module-team
+  "Team owning `module`: its own `:team`, else its nearest ancestor's."
+  [modules module]
+  (some #(get-in modules [% :team])
+        (take-while some? (iterate #(parent-module modules %) module))))
+
+(defn- rest-module? [module]
+  (re-find #"[.-]rest$" (str module)))
+
+(defn- exports-child?
+  [modules parent child]
+  (or (contains? (set (get-in modules [parent :module-exports])) child)
+      ;; A `.rest` child is its parent's public HTTP surface.
+      (rest-module? child)
+      ;; OSS module `X` implicitly exports its `enterprise/X` companion.
+      (and (not= (namespace parent) (namespace child))
+           (contains? modules child))))
+
+(defn- blocking-export
+  "The first missing export from `module` toward the root.
+
+  Returns `{:ancestor parent, :child child}`, or `nil` when every link is
+  exported."
+  [modules module]
+  (loop [child module]
+    (when-let [ancestor (parent-module modules child)]
+      (if (exports-child? modules ancestor child)
+        (recur ancestor)
+        {:ancestor ancestor, :child child}))))
+
+(defn namability-error
+  "Explain why `caller` may not refer to `target` in `:uses`, or return `nil` if it may.
+
+  A nested module is private to the nearest ancestor with a missing export.
+  Exporting every link makes it public."
+  [modules caller target]
+  (when-let [{:keys [ancestor child]} (blocking-export modules target)]
+    (when-not (descendant-of? modules caller ancestor)
+      (format (str "Module %s is nested and not exported by its ancestors; %s may not use it. Add %s to %s's "
+                   ":module-exports, or move the caller into the %s subtree. [:metabase/modules %s :module-exports]")
+              target caller child ancestor ancestor ancestor))))
+
+;;;; Lint rules. These functions take the full linter config.
+
+(defonce ^:private prefix->module-cache
+  (atom nil))
+
+(defn- prefix->module
+  "[[build-prefix->module]] for `config`, cached because Kondo hands every hook call the same `:metabase/modules` map."
+  [config]
+  (let [modules (:metabase/modules config)
+        cached  @prefix->module-cache]
+    (if (identical? modules (:modules cached))
+      (:prefix->module cached)
+      (:prefix->module (reset! prefix->module-cache {:modules        modules
+                                                     :prefix->module (build-prefix->module modules)})))))
+
+(defn module
+  "Resolve `ns-symb` to its module under `config`; see [[resolve-module]]."
+  [config ns-symb]
+  (resolve-module (prefix->module config) ns-symb))
+
+(defn module-api-namespaces
   "Set of API namespace symbols for a given module. `:any` means you can use anything, there are no API namespaces for
-  this module (yet). If unspecified, the default is just the `<module>.core` namespace."
-  [config module]
-  (let [module-config (get-in config [:metabase/modules module :api])]
+  this module (yet). If unspecified, the defaults are `<prefix>.api`, `<prefix>.core`, and `<prefix>.init`."
+  [modules module]
+  (let [module-config (get-in modules [module :api])]
     (cond
       (= module-config :any)
       nil
@@ -44,9 +164,7 @@
       module-config
 
       :else
-      (let [ns-prefix (if (= (namespace module) "enterprise")
-                        (str "metabase-enterprise." (name module))
-                        (name module))]
+      (let [ns-prefix (module-ns-prefix modules module)]
         #{(symbol (str ns-prefix ".api"))
           (symbol (str ns-prefix ".core"))
           (symbol (str ns-prefix ".init"))}))))
@@ -68,15 +186,14 @@
         (contains? (set allowed-modules) required-module))))
 
 (defn- allowed-module-namespace? [config current-module ns-symb]
-  (let [module                (module ns-symb)
-        module-api-namespaces (module-api-namespaces config module)
+  (let [module                (module config ns-symb)
+        module-api-namespaces (module-api-namespaces (:metabase/modules config) module)
         module-friends        (module-friends config module)]
-    (or (empty? module-api-namespaces)
+    (or (nil? module-api-namespaces)
         (contains? module-api-namespaces ns-symb)
-        (contains? module-friends current-module))))
-
-(defn- rest-module? [module]
-  (str/ends-with? module "-rest"))
+        (contains? module-friends current-module)
+        ;; a child may use its ancestors' internals; a parent still goes through its child's `:api`
+        (descendant-of? (:metabase/modules config) current-module module))))
 
 (defn- routes-module? [module]
   (str/ends-with? module "-routes"))
@@ -89,7 +206,7 @@
   error type if there is one, otherwise `nil` if there are no errors."
   [config current-module required-namespace]
   ;; ignore stuff not in a module i.e. non-Metabase stuff.
-  (when-let [required-module (module required-namespace)]
+  (when-let [required-module (module config required-namespace)]
     (when-not (= current-module required-module)
       (cond
         (not (allowed-module? config current-module required-module))
@@ -113,4 +230,8 @@
                 required-module
                 current-module
                 required-module
-                (symbol (str/replace required-module #"-rest$" "")))))))
+                (symbol (str/replace required-module #"[.-]rest$" "")))
+
+        ;; Config tests check explicit `:uses`; wildcard callers are checked here.
+        (= :any (allowed-modules config current-module))
+        (namability-error (:metabase/modules config) current-module required-module)))))

.clj-kondo/src/hooks/metabase/agent_message.clj

@@ -0,0 +1,375 @@
+(ns hooks.metabase.agent-message
+  "Hooks linting agent-facing prose built with `metabase.mcp.v2.message/msg` (`:metabase/agent-message-lines`) and the
+  exits and helpers that carry it to the agent (`:metabase/agent-message-exit`). Each hook checks only when its
+  linter's level is configured and not `:off`, and returns its input unchanged."
+  (:require
+   [clj-kondo.hooks-api :as hooks]
+   [clojure.string :as str]))
+
+(defn- level-on?
+  [config linter-key]
+  (not= :off (get-in config [:linters linter-key :level] :off)))
+
+(defn- call-name
+  "The symbol at the head of list `node`, or nil."
+  [node]
+  (when (hooks/list-node? node)
+    (let [head (first (:children node))]
+      (when (hooks/token-node? head)
+        (let [v (hooks/sexpr head)]
+          (when (symbol? v) v))))))
+
+(defn- calls?
+  "Whether `node` is a call to a var named `var-name` in one of `ns-names` (nil for an unqualified call)."
+  [node ns-names var-name]
+  (when-let [sym (call-name node)]
+    (and (= var-name (name sym))
+         (contains? ns-names (namespace sym)))))
+
+(def ^:private core-ns #{nil "clojure.core"})
+(def ^:private string-ns #{"str" "string" "clojure.string"})
+
+(defn- literal-string
+  "The string value of `node` when it is a string literal or a `str` call over string literals, else nil."
+  [node]
+  (cond
+    (hooks/string-node? node)
+    (hooks/sexpr node)
+
+    (and (calls? node core-ns "str")
+         (every? hooks/string-node? (rest (:children node))))
+    (apply str (map hooks/sexpr (rest (:children node))))))
+
+(defn- digits->long
+  "The value of a string of decimal digits."
+  [s]
+  ;; Kondo's hook interpreter has no `parse-long`.
+  (reduce (fn [n c] (+ (* 10 n) (- (int c) (int \0)))) 0 s))
+
+(def ^:private format-specifier
+  "A `java.util.Formatter` specifier; groups are explicit index, flags, width, precision, and conversion. The index is
+  capped at nine digits, so a longer one reads as malformed rather than a number too large to work with."
+  #"%(?:(\d{1,9})\$)?([-#+ 0,(<]*)(\d+)?(?:\.(\d+))?([tT]?[a-zA-Z%])")
+
+(defn- consumed-args
+  "`[index conversion]` for each argument-consuming specifier in `fmt`, with zero-based argument indexes. An index of
+  -1 marks a reference no argument can satisfy: an explicit `0$`, or a `<` with no specifier before it to repeat."
+  [fmt]
+  (loop [[[_ explicit flags _width _precision conversion] & more] (re-seq format-specifier fmt)
+         next-index                                               0
+         last-index                                               nil
+         acc                                                      []]
+    (if-not conversion
+      acc
+      (let [consumes? (not (contains? #{"%" "n"} conversion))
+            index     (cond
+                        (not consumes?)             nil
+                        explicit                    (dec (digits->long explicit))
+                        (str/includes? flags "<")   (or last-index -1)
+                        :else                       next-index)
+            implicit? (and consumes? (not explicit) (not (str/includes? flags "<")))]
+        (recur more
+               (cond-> next-index implicit? inc)
+               (or index last-index)
+               (cond-> acc
+                 index (conj [index conversion])))))))
+
+(def ^:private msg-linter :metabase/agent-message-lines)
+
+(defn- reg-msg-finding!
+  [node message]
+  (hooks/reg-finding! (assoc (meta node) :message message :type msg-linter)))
+
+(defn- line-break?
+  "Whether format string `line` contains a line-breaking, control, or private-use character, or a `%n` specifier."
+  [line]
+  ;; Private-use characters delimit the argument markers `render` formats with, so a line holding one could fake one.
+  (boolean (or (re-find #"[\p{Cc}\p{Cf}\p{Co}\p{Zl}\p{Zp}]" line)
+               (some #(= "n" (nth % 5)) (re-seq format-specifier line)))))
+
+(defn- allowed-specifier?
+  "Whether specifier match `specifier` renders its value as `render` passes it: a bare `%%`, a `%s` with no flags but
+  `<`, or a `%d` with any flags and width but no precision. An explicit argument index is allowed on each."
+  [[_ explicit flags width precision conversion]]
+  (case conversion
+    "%" (not (or explicit (seq flags) width precision))
+    "s" (not (or width precision (seq (str/replace flags "<" ""))))
+    "d" (not precision)
+    false))
+
+(defn- disallowed-specifier
+  "The first specifier in format string `line` that isn't [[allowed-specifier?]], as it is written, or nil."
+  [line]
+  (some #(when-not (allowed-specifier? %) (first %)) (re-seq format-specifier line)))
+
+(def ^:private valid-conversion
+  "The conversions `java.util.Formatter` accepts, with each date/time conversion's required suffix."
+  #"[bBhHsScCdoxXeEfgGaA%n]|[tT][HIklMSLNpzZsQBbhAaCYyjmdeRTrDFc]")
+
+(defn- malformed-specifier?
+  "Whether format string `line` has a `%` that doesn't begin a valid `java.util.Formatter` specifier."
+  [line]
+  (let [valid-removed (str/replace line format-specifier
+                                   (fn [[specifier & groups]]
+                                     (if (re-matches valid-conversion (last groups)) "" specifier)))]
+    (str/includes? valid-removed "%")))
+
+(defn- line-problem
+  "The finding message for the first problem with a `msg` line, given its literal string or nil; nil when it has none."
+  [line]
+  (cond
+    (nil? line)
+    (str "Each line of a `msg` must be a string literal or a `str` of string literals; "
+         "pass values as arguments after the vector.")
+
+    (line-break? line)
+    (str "A `msg` line can't contain a line break, `%n`, or a control or private-use character; "
+         "put each line in its own string.")
+
+    (malformed-specifier? line)
+    "A `%` in a `msg` line must begin a format specifier; write a literal percent sign as `%%`."
+
+    :else
+    (when-let [specifier (disallowed-specifier line)]
+      (str "A `msg` line may only use `%s`, `%d`, or `%%`; `" specifier "` would alter or hide the value."))))
+
+(defn- lint-lines!
+  "Flag each of `line-nodes` whose literal string, the matching element of `lines`, has a problem."
+  [line-nodes lines]
+  (doseq [[line-node line] (map vector line-nodes lines)]
+    (when-let [problem (line-problem line)]
+      (reg-msg-finding! line-node problem))))
+
+(defn- plural
+  [n word]
+  (str n " " word (when-not (= 1 n) "s")))
+
+(defn- lint-arg-count!
+  "Flag `msg` call `node` when a literal line refers to an argument that can't exist, or when its `args` don't number
+  the arguments its literal `lines` consume."
+  [node lines args]
+  (let [indexes  (map first (consumed-args (str/join "\n" lines)))
+        expected (if (seq indexes) (inc (apply max indexes)) 0)
+        given    (count args)]
+    (cond
+      ;; `String/format` throws on these, so the message would render with every part quoted instead.
+      (some neg? indexes)
+      (reg-msg-finding! node (str "A `msg` line refers to an argument that can't exist; "
+                                  "argument indexes start at `1$`, and `%<` repeats the specifier before it."))
+
+      (not= expected given)
+      (reg-msg-finding! node (format "The `msg` lines take %s but %d %s given."
+                                     (plural expected "argument") given (if (= 1 given) "is" "are"))))))
+
+(defn lint-msg
+  "Flag `msg` calls whose lines aren't a literal vector of single-line literal strings, that hold a malformed
+  specifier or a conversion other than `%s`, `%d`, or `%%`, or whose arguments don't match the lines' specifiers."
+  [{:keys [node config] :as input}]
+  (when (level-on? config msg-linter)
+    (let [[fn-node lines-node & args] (:children node)]
+      (if-not (and lines-node (hooks/vector-node? lines-node))
+        (reg-msg-finding! (or lines-node fn-node)
+                          "`msg` takes a literal vector of line strings, one string per line of the message.")
+        (let [line-nodes (:children lines-node)
+              lines      (map literal-string line-nodes)]
+          (lint-lines! line-nodes lines)
+          ;; A malformed specifier can't be counted, and its line already has a finding.
+          (when (and (every? some? lines) (not-any? malformed-specifier? lines))
+            (lint-arg-count! node lines args))))))
+  input)
+
+(def ^:private exit-linter :metabase/agent-message-exit)
+
+(defn- exit-enabled?
+  [{:keys [config]}]
+  (level-on? config exit-linter))
+
+(defn- reg-exit-finding!
+  [node message]
+  (hooks/reg-finding! (assoc (meta node) :message message :type exit-linter)))
+
+(defn- calls-core?
+  "Whether `node` is a call to a `clojure.core` var or special form named in `var-names`."
+  [node var-names]
+  (when-let [sym (call-name node)]
+    (and (contains? var-names (name sym))
+         (contains? core-ns (namespace sym)))))
+
+(defn- calls-i18n?
+  [node]
+  (when-let [sym (call-name node)]
+    (contains? #{"tru" "trs" "deferred-tru" "deferred-trs"} (name sym))))
+
+(defn- calls-json-encode?
+  "Whether `node` calls `encode` in a namespace or alias whose name ends in `json`."
+  [node]
+  (when-let [sym (call-name node)]
+    (and (= "encode" (name sym))
+         (boolean (some-> (namespace sym) (str/ends-with? "json"))))))
+
+(defn- builds-string?
+  "Whether `node` is a string literal or a call that builds a string."
+  [node]
+  (or (hooks/string-node? node)
+      (calls-core? node #{"str" "format" "pr-str" "ex-message"})
+      (calls-i18n? node)
+      (calls? node string-ns "join")
+      (calls-json-encode? node)))
+
+(defn- clause-results
+  "The result nodes of `clauses`, alternating test and result nodes, with a trailing default when their count is odd."
+  [clauses]
+  (concat (take-nth 2 (rest clauses))
+          (when (odd? (count clauses)) [(last clauses)])))
+
+(defn- result-fn-marker?
+  [node]
+  (and (hooks/keyword-node? node) (= :>> (hooks/sexpr node))))
+
+(defn- condp-results
+  "The result nodes of `condp` `clauses`: each test's result, skipping `:>>` result functions, and any default."
+  [clauses]
+  (loop [[_test result & more :as clauses] clauses
+         acc                               []]
+    (cond
+      (empty? clauses)           acc
+      (nil? (next clauses))      (conj acc (first clauses))
+      (result-fn-marker? result) (recur (next more) acc)
+      :else                      (recur more (conj acc result)))))
+
+(defn- branch-results
+  "The nodes branching form `node` can evaluate to, or nil when it isn't one."
+  [node]
+  (let [args (rest (:children node))]
+    (cond
+      (calls-core? node #{"if" "if-not" "if-let"}) (rest args)
+      (calls-core? node #{"or"})                   args
+      (calls-core? node #{"cond"})                 (clause-results args)
+      (calls-core? node #{"case"})                 (clause-results (rest args))
+      (calls-core? node #{"condp"})                (condp-results (drop 2 args)))))
+
+(defn- step-call
+  "Threading step `node` as the call it stands for: a list as is, anything else as a call with no written arguments."
+  [node]
+  (if (hooks/list-node? node) node (hooks/list-node [node])))
+
+(defn- threading-results
+  "The nodes whose text-ness decides what threading form `node` evaluates to, or nil when it isn't one."
+  [node]
+  (let [[init & steps] (rest (:children node))]
+    (cond
+      (calls-core? node #{"->" "->>" "some->" "some->>"}) [(if steps (step-call (last steps)) init)]
+      (calls-core? node #{"cond->" "cond->>"})           (cons init (map step-call (take-nth 2 (rest steps))))
+      (calls-core? node #{"as->"})                       [(or (last (rest steps)) init)]
+      (calls-core? node #{"doto"})                       [init])))
+
+(defn- tail-result
+  "The node body form `node` evaluates to, or nil when it isn't one."
+  [node]
+  (let [args (rest (:children node))]
+    (cond
+      (calls-core? node #{"when" "when-not" "when-let" "let"}) (when (next args) (last args))
+      (calls-core? node #{"do"})                               (last args))))
+
+(defn- stringy?
+  "Whether `node` syntactically evaluates to text: a string literal, a call that builds a string, or a threading,
+  branching, or body form whose result is one."
+  [node]
+  (boolean
+   (or (builds-string? node)
+       (some stringy? (branch-results node))
+       (some stringy? (threading-results node))
+       (some-> (tail-result node) stringy?))))
+
+(defn- lint-exit-text!
+  "Flag `arg`, the message passed to `target` (a description of where it goes), when it is text rather than a `msg`."
+  [arg target]
+  (when (and arg (stringy? arg))
+    (reg-exit-finding! arg (format (str "`%s` passes text to %s; "
+                                        "build agent-facing text with `msg` so interpolated values are cleaned.")
+                                   (pr-str (hooks/sexpr arg))
+                                   target))))
+
+(defn- lint-exit-arg!
+  "Flag the argument at child `index` of call `node` when it is text rather than a `msg`."
+  [node index]
+  (lint-exit-text! (nth (:children node) index nil) (str "`" (name (call-name node)) "`")))
+
+(defn lint-teaching-exit
+  "Flag a call throwing or returning a teaching error whose message, the first argument, is text rather than a `msg`."
+  [{:keys [node] :as input}]
+  (when (exit-enabled? input)
+    (lint-exit-arg! node 1))
+  input)
+
+(defn lint-jsonrpc-error
+  "Flag a `jsonrpc-error` whose message, the third argument, is text rather than a `msg`."
+  [{:keys [node] :as input}]
+  (when (exit-enabled? input)
+    (lint-exit-arg! node 3))
+  input)
+
+(defn lint-op-error
+  "Flag an `op-error!` whose detail message, the third argument, is text rather than a `msg`."
+  [{:keys [node] :as input}]
+  (when (exit-enabled? input)
+    (lint-exit-arg! node 3))
+  input)
+
+(defn lint-ellipsize
+  "Flag an `ellipsize` whose message, the first argument, is text rather than a `msg`."
+  [{:keys [node] :as input}]
+  (when (exit-enabled? input)
+    (lint-exit-arg! node 1))
+  input)
+
+(defn- map-value
+  "The value node of keyword `k` in map literal `node`, or nil."
+  [node k]
+  (when (hooks/map-node? node)
+    (some (fn [[key-node value-node]]
+            (when (and (hooks/keyword-node? key-node) (= k (hooks/sexpr key-node)))
+              value-node))
+          (partition 2 (:children node)))))
+
+(defn lint-list-content
+  "Flag a `list-content`, or a wrapper taking its options map as the third argument too, whose literal options map
+  has an `:empty-hint` that is text rather than a `msg`."
+  [{:keys [node] :as input}]
+  (when (exit-enabled? input)
+    (lint-exit-text! (map-value (nth (:children node) 3 nil) :empty-hint)
+                     (str "`" (name (call-name node)) "`'s `:empty-hint`")))
+  input)
+
+(defn lint-success-content
+  "Flag a `success-content` whose first argument is text rather than a payload or a `msg`."
+  [{:keys [node] :as input}]
+  (when (exit-enabled? input)
+    (let [text (second (:children node))]
+      (when (and text (stringy? text))
+        (reg-exit-finding! text (str "`success-content` takes data to JSON-encode or a `msg`; "
+                                     "pass the payload itself, or build the text with `msg`.")))))
+  input)
+
+(defn- caller-facing-data?
+  "Whether `node` is a map literal with a 4xx `:status-code` literal or an `error-code` key."
+  [node]
+  (and (hooks/map-node? node)
+       (some (fn [[k v]]
+               (when (hooks/keyword-node? k)
+                 (let [kw (hooks/sexpr k)]
+                   (or (= "error-code" (name kw))
+                       (and (= :status-code kw)
+                            (hooks/token-node? v)
+                            (let [status (hooks/sexpr v)]
+                              (and (number? status) (<= 400 status 499))))))))
+             (partition 2 (:children node)))))
+
+(defn lint-ex-info
+  "Flag an `ex-info` whose data marks it as a caller-facing error."
+  [{:keys [node] :as input}]
+  (when (exit-enabled? input)
+    (when (caller-facing-data? (nth (:children node) 2 nil))
+      (reg-exit-finding! node (str "Caller-facing errors must be thrown with `throw-teaching-error` and a `msg`, "
+                                   "so their text is rendered and cleaned."))))
+  input)

.clj-kondo/src/hooks/metabase/settings/models/setting.clj

@@ -4,9 +4,9 @@
    [hooks.common :as common]))
 
 (defn lint-defsetting-namespace [node context]
-  (when-not (re-matches #"^metabase(?:-enterprise)?\.[^\.]+\.settings$" (name (:ns context)))
+  (when-not (re-matches #"^metabase(?:-enterprise)?\.([^\.]+\.)+settings$" (name (:ns context)))
     (hooks/reg-finding! (assoc (meta node)
-                               :message "All defsettings should live in metabase[-enterprise].<module>.settings namespaces"
+                               :message "All defsettings should live in a namespace ending in .settings under metabase[-enterprise]"
                                :type :metabase/defsetting-namespace))))
 
 ;;; TODO -- move this into a Kondo config file in `.clj-kondo/config/`
@@ -286,6 +286,7 @@
     (update context :node update-node)))
 
 (comment
+  (require '[clojure.pprint])
   (defn- defsetting* [form]
     (hooks/sexpr
      (:node
@@ -293,7 +294,6 @@
         {:node
          (hooks/parse-string
           (with-out-str
-            #_{:clj-kondo/ignore [:unresolved-namespace]}
             (clojure.pprint/pprint
              form)))}))))
 

.clj-kondo/src/hooks/metabase/test/gentest.clj

@@ -1,14 +0,0 @@
-(ns hooks.metabase.test.gentest
-  (:require
-   [clj-kondo.hooks-api :as hooks]))
-
-(defn iterate*
-  "(iterate {:as limit-spec} [s1 val1 & more] body-form body-form...)"
-  [{{:keys [children] :as node} :node :as orig}]
-  (let [[token limit-spec bindings & body-nodes] children
-        node* (-> (hooks/list-node
-                   (list token limit-spec
-                         (hooks/list-node (list* (hooks/token-node 'let) bindings
-                                                 body-nodes))))
-                  (with-meta (meta node)))]
-    (assoc orig :node node*)))

.clj-kondo/src/hooks/metabase/toucan/db_ns.clj

@@ -0,0 +1,146 @@
+(ns hooks.metabase.toucan.db-ns
+  "Lint that application database query calls -- Toucan 2's `t2/select`, `t2/query`, `t2/insert!`, `t2/update!`,
+  `t2/delete!` and friends, plus the `metabase.app-db.core` wrappers around them such as `mdb/query` and
+  `mdb/update-or-insert!` -- live in a module's `db` namespace, i.e. `metabase[-enterprise].<module>.db` (or `metabase.driver.<driver>.db` for
+  driver modules). Every other namespace in a module goes through those functions instead of talking to the
+  application database directly.
+
+  Registered as an `:analyze-call` hook on each of those functions in `.clj-kondo/config.edn`. The hook
+  returns its input unchanged so Kondo's normal analysis of the call (arity, var usage) still runs."
+  (:require
+   [clj-kondo.hooks-api :as hooks]
+   [hooks.common.modules :as modules]))
+
+(def ^:private driver-db-namespace
+  "Matches `metabase.driver.<driver>.db`; individual drivers are not modules."
+  #"^metabase\.driver\.[^.]+\.db$")
+
+(defn- db-namespace? [config ns-sym]
+  (let [ns-str (name ns-sym)]
+    (boolean
+     ;; Resolve ownership first: a nested `.db` name alone does not make a module.
+     (or (when-let [module (modules/module config ns-sym)]
+           (= ns-str (str (modules/module-ns-prefix (:metabase/modules config) module) ".db")))
+         (re-matches driver-db-namespace ns-str)))))
+
+(defn- test-file?
+  "Whether `filename` is in a test source tree. Test namespaces are exempt through the `test-namespaces` group in
+  `config.edn`, but helper namespaces like `metabase.sso.test-helpers` don't match that group's pattern."
+  [filename]
+  (boolean (and filename (re-find #"(?:^|/)test/" filename))))
+
+(def ^:private value-operators
+  "Operators whose second argument is a value rather than a column."
+  '#{= not= < > <= >= like not-like ilike not-ilike in not-in between})
+
+(defn- marked?
+  "Whether `node` is an `[:auto/param v]` marker."
+  [node]
+  (and (hooks/vector-node? node)
+       (= :auto/param (some-> (first (:children node)) hooks/sexpr))))
+
+(defn- value-nodes
+  "The nodes sitting in a value slot of `node`, following the clause shapes a query map uses."
+  [node]
+  (cond
+    ;; A query map -- walk its clause values, not its keys.
+    (hooks/map-node? node)
+    (mapcat value-nodes (take-nth 2 (rest (:children node))))
+
+    (hooks/vector-node? node)
+    (let [[head & args] (:children node)
+          op            (some-> head hooks/sexpr)]
+      (cond
+        (contains? #{:and :or :not} op)
+        (mapcat value-nodes args)
+
+        ;; `[:= col v]`, `[:in col vs]`, `[:between col lo hi]` -- the first argument is the
+        ;; column and the rest are values, whatever the arity.
+        (and (keyword? op) (contains? value-operators (symbol (name op))))
+        (rest args)
+
+        :else
+        (mapcat value-nodes (:children node))))
+
+    :else nil))
+
+(def ^:private write-fns
+  "Calls whose values are written rather than filtered on. A value here is not a where-clause value
+  an attacker can turn into SQL structure, and a `define-before-insert` hook may read it before the
+  query compiles, so a marker would break it rather than protect anything."
+  '#{insert! insert-returning-instance! insert-returning-instances! insert-returning-pk!
+     insert-returning-pks! save!})
+
+(defn- read-call?
+  "Whether `node` is a query call whose values are filtered on rather than written."
+  [node]
+  (let [f (some-> (first (:children node)) hooks/sexpr)]
+    (not (contains? write-fns (some-> f name symbol)))))
+
+(defn- kv-arg-pair
+  "The first `:column value` pair a query call passes after its model, if any.
+
+  `(t2/select :model/X :locale locale)`. Several of these fns take an argument before the model --
+  `(t2/select-one-fn :value :model/X :key k)` -- so the pairs do not start at a fixed offset; they
+  start after the `:model/...` keyword. A call that does not name a literal model is not checked."
+  [args]
+  (let [after-model (->> args
+                         (drop-while #(not (and (hooks/keyword-node? %)
+                                                (= "model" (namespace (hooks/sexpr %))))))
+                         rest)
+        [k v]       after-model]
+    (when (and k v (hooks/keyword-node? k))
+      k)))
+
+(defn- lint-kv-args!
+  "Register a finding for a query written as `:column value` pairs.
+
+  Toucan builds those into the where clause itself, so the query's shape is not on the page: there
+  is nothing for a reader, this linter, or the `.sql` extraction that follows this project to read.
+  The same call takes a map -- `{:where [:= :locale v]}` for a select, `{:locale v}` for an
+  `update!` -- which is the statement, near enough to read off."
+  [node]
+  (when-let [k (kv-arg-pair (rest (:children node)))]
+    (hooks/reg-finding!
+     (assoc (meta k)
+            :message (format "Pass this query a map rather than `%s ...` pairs, so its shape is on the page."
+                             (hooks/sexpr k))
+            :type :metabase/unsafe-app-db-query))))
+
+(defn- lint-unmarked-values!
+  "Register a finding for each argument of the enclosing function that reaches a value slot unmarked.
+
+  Only a symbol is reported. A literal cannot carry a request value, and a value built inside the
+  function is out of reach of a check that does not follow it across a call."
+  [node]
+  (doseq [value (mapcat value-nodes (rest (:children node)))
+          :when (and (hooks/token-node? value)
+                     (symbol? (hooks/sexpr value))
+                     (not (marked? value)))]
+    (hooks/reg-finding!
+     (assoc (meta value)
+            :message (format "`%s` reaches a SQL value slot unmarked. Write it as [:auto/param %s] so it is bound as a parameter."
+                             (hooks/sexpr value) (hooks/sexpr value))
+            :type :metabase/unsafe-app-db-query))))
+
+(defn lint-query-call
+  "Register a `:metabase/t2-query-namespace` finding when a Toucan 2 query call appears outside a `<module>.db`
+  namespace."
+  [{:keys [node ns filename] :as input}]
+  (when (and ns
+             (not (db-namespace? (modules/config input) ns))
+             (not (test-file? filename)))
+    (let [fn-node (first (:children node))]
+      (hooks/reg-finding!
+       (assoc (meta fn-node)
+              :message (format "Application database query calls like `%s` must live in metabase[-enterprise].<module>.db (or metabase.driver.<driver>.db) namespaces"
+                               (hooks/sexpr fn-node))
+              :type :metabase/t2-query-namespace))))
+  ((requiring-resolve 'hooks.metabase.warehouse-schema-overlay.table-or-field-query/lint-read) input)
+  (when (and ns
+             (db-namespace? (modules/config input) ns)
+             (not (test-file? filename))
+             (read-call? node))
+    (lint-unmarked-values! node)
+    (lint-kv-args! node))
+  input)

.clj-kondo/src/hooks/metabase/util/match.clj

@@ -124,6 +124,25 @@
                       (concat [(api/token-node 'clojure.core/or)] result-exprs [opaque-node]))))]
       {:node new-node})))
 
+(defn matches?
+  "clj-kondo :analyze-call hook for matches?. Similar to `match-one`, but supports just a single clause with no result."
+  [{:keys [node]}]
+  (let [[_ value pat] (:children node)]
+    (let [all-bindings (->> (collect-bindings pat)
+                            dedupe-bindings)
+          special-bindings [(api/token-node '_)        value
+                            (api/token-node '&match)   opaque-node
+                            ;; Pretend to use &match so that Kondo doesn't complain about it.
+                            (api/token-node '_) (api/token-node '&match)]
+          binding-nodes (into special-bindings all-bindings)
+          new-node (api/list-node
+                    (list
+                     (api/token-node 'let)
+                     (api/vector-node binding-nodes)
+                     (api/list-node
+                      (list opaque-node))))]
+      {:node new-node})))
+
 (def match-many match-one)
 (def replace match-one)
 

.clj-kondo/src/hooks/metabase/warehouse_schema_overlay/table_or_field_query.clj

@@ -0,0 +1,52 @@
+(ns hooks.metabase.warehouse-schema-overlay.table-or-field-query
+  "Lint that a query over `:model/Field` or `:model/Table` names its source with `field-query`/`table-query` from
+  `metabase.warehouse-schema-overlay.core`, or reads sync's values with `{:user-settings? false}`."
+  (:require
+   [clj-kondo.hooks-api :as hooks]))
+
+(def ^:private read-fn?
+  "The Toucan 2 query functions that read rows. Writes are not affected: they go to `metabase_field` itself."
+  #{"select" "select-one" "select-fn->fn" "select-fn->pk" "select-fn-reducible" "select-fn-set" "select-fn-vec"
+    "select-one-fn" "select-one-pk" "select-pk->fn" "select-pks-set" "select-pks-vec" "select-reducible"
+    "reducible-select" "reducible-query" "query" "query-one" "count" "exists?"})
+
+(def ^:private model->helper
+  {":model/Field" "field-query"
+   ":model/Table" "table-query"})
+
+(defn- test-file? [filename]
+  (boolean (and filename (re-find #"(?:^|/)test/" filename))))
+
+(defn- tokens
+  "Every token in `node`'s tree, as strings."
+  [node]
+  (tree-seq :children :children node))
+
+(defn- mentions?
+  [node pred]
+  (boolean (some (fn [n] (when-let [s (some-> (hooks/sexpr n) pr-str)] (pred s)))
+                 (filter (complement :children) (tokens node)))))
+
+(defn- writes?
+  "Whether a `t2/query` form is really a write spelled as a query."
+  [node]
+  (mentions? node #{":update" ":delete-from" ":insert-into"}))
+
+(defn lint-read
+  "Register a `:metabase/table-or-field-query` finding when a read of `:model/Field` or `:model/Table` does not name
+  its source with the matching helper."
+  [{:keys [node filename]}]
+  (let [fn-node (first (:children node))
+        fn-name (some-> (hooks/sexpr fn-node) name)]
+    (when (and fn-name
+               (read-fn? fn-name)
+               (not (test-file? filename))
+               (not (writes? node)))
+      (doseq [[model helper] model->helper
+              :when (mentions? node #(= % model))
+              :when (not (mentions? node #(re-find (re-pattern (str "\\b" helper "$")) %)))]
+        (hooks/reg-finding!
+         (assoc (meta fn-node)
+                :message (format "A read of %s must name its source: add {:from [(%s)]} (or {:user-settings? false} for sync's own values)"
+                                 model helper)
+                :type :metabase/table-or-field-query))))))

.clj-kondo/test/hooks/clojure/core/ns_test.clj

@@ -19,6 +19,19 @@
 (defn- lint-modules [form config]
   (lint-ns form (assoc-in config [:linters :metabase/modules :level] :warning)))
 
+(deftest ^:parallel explicit-nonparallel-namespace-metadata-test
+  (let [config {:linters {:metabase/validate-deftest {:level :warning}}}]
+    (testing "Hawk's supported namespace marker passes"
+      (is (empty? (lint-ns '(ns ^:synchronized example.test) config))))
+    (testing "the verbose Hawk spelling is not accepted as Metabase style"
+      (is (=? [{:type    :metabase/validate-deftest
+                :message #(re-find #"Use `\^:synchronized` instead" %)}]
+              (lint-ns '(ns ^{:parallel false} example.test) config))))
+    (testing "the legacy marker explains that Hawk ignores it"
+      (is (=? [{:type    :metabase/validate-deftest
+                :message #(re-find #"`\^:synchronous` is ignored by Hawk" %)}]
+              (lint-ns '(ns ^:synchronous example.test) config))))))
+
 (deftest ^:parallel module-checker-allowed-modules-test
   (are [task-namespace] (=? [{:message "Module task should not be used in the api module. [:metabase/modules api :uses]"
                               :type :metabase/modules}]
@@ -43,6 +56,16 @@
            '{:metabase/modules {api    {:uses #{search}}
                                 search {:api  #{metabase.search.core}}}}))))
 
+(deftest ^:parallel module-checker-empty-api-test
+  (is (=? [{:message "Namespace metabase.embeddings.core is not an allowed external API namespace for the embeddings module. [:metabase/modules embeddings :api]"
+            :type :metabase/modules}]
+          (lint-modules
+           '(ns metabase.metabot.core
+              (:require
+               [metabase.embeddings.core :as embeddings]))
+           '{:metabase/modules {metabot   {:uses #{embeddings}}
+                                embeddings {:api #{}}}}))))
+
 (deftest ^:parallel module-checker-friends-test
   (is (= []
          (lint-modules

.clj-kondo/test/hooks/clojure/core/require_test.clj

@@ -0,0 +1,65 @@
+(ns hooks.clojure.core.require-test
+  (:require
+   [clj-kondo.hooks-api :as hooks]
+   [clj-kondo.impl.utils]
+   [clojure.test :refer :all]
+   [hooks.clojure.core.require]))
+
+(def ^:private config
+  '{:linters          {:metabase/modules {:level :warning}}
+    :metabase/modules {search {:uses #{}}
+                       task   {:api #{metabase.task.core}}}})
+
+(defn- lint [hook form current-ns]
+  (binding [clj-kondo.impl.utils/*ctx* {:config     config
+                                        :ignores    (atom nil)
+                                        :findings   (atom [])
+                                        :namespaces (atom {})}]
+    (hook {:node   (hooks/parse-string (pr-str form))
+           :ns     current-ns
+           :config config})
+    @(:findings clj-kondo.impl.utils/*ctx*)))
+
+(defn- lint-require [form current-ns]
+  (lint hooks.clojure.core.require/lint-require form current-ns))
+
+(defn- lint-requiring-resolve [form current-ns]
+  (lint hooks.clojure.core.require/lint-requiring-resolve form current-ns))
+
+(def ^:private dynamic-require-finding
+  {:message "Module dependency cannot be statically determined from a dynamic require"
+   :type    :metabase/modules})
+
+(def ^:private cross-module-finding
+  {:message "Module task should not be used in the search module. [:metabase/modules search :uses]"
+   :type    :metabase/modules})
+
+(deftest ^:parallel dynamic-requiring-resolve-test
+  (testing "outside the module system"
+    (is (= [] (lint-requiring-resolve '(requiring-resolve (:failing-test-var opts)) 'dev))))
+  (testing "inside a module"
+    (are [form] (=? [dynamic-require-finding]
+                    (lint-requiring-resolve form 'metabase.search.core))
+      '(requiring-resolve (:failing-test-var opts))
+      '(requiring-resolve @some-atom)
+      '(requiring-resolve some-local)
+      '(requiring-resolve "not-a-symbol"))))
+
+(deftest ^:parallel dynamic-require-test
+  (testing "outside the module system"
+    (is (= [] (lint-require '(require some-local) 'dev))))
+  (testing "inside a module"
+    (is (=? [dynamic-require-finding]
+            (lint-require '(require some-local) 'metabase.search.core)))))
+
+(deftest ^:parallel static-requiring-resolve-still-linted-test
+  (is (=? [cross-module-finding]
+          (lint-requiring-resolve '(requiring-resolve 'metabase.task.impl/go)
+                                  'metabase.search.core))
+      "a statically-known cross-module violation is still reported"))
+
+(deftest ^:parallel static-require-still-linted-test
+  (is (=? [cross-module-finding]
+          (lint-require '(require 'metabase.task.impl :reload)
+                        'metabase.search.core))
+      "a statically-known cross-module violation is still reported while keyword flags are ignored"))

.clj-kondo/test/hooks/clojure/test_test.clj

@@ -21,6 +21,54 @@
                                             #{:athena}}}}})
     (mapv :message @(:findings clj-kondo.impl.utils/*ctx*))))
 
+(defn- parallel-metadata-findings
+  ([form]
+   (parallel-metadata-findings form 'example.test))
+  ([form ns-sym]
+   (let [linters {:metabase/deftest-not-marked-parallel-or-synchronized {:level :warning}
+                  :metabase/validate-deftest                             {:level :warning}}]
+     (binding [clj-kondo.impl.utils/*ctx* {:config     {:linters linters}
+                                           :ignores    (atom nil)
+                                           :findings   (atom [])
+                                           :namespaces (atom {})}]
+       (hooks.clojure.test/deftest {:node   (api/parse-string form)
+                                    :lang   :clj
+                                    :ns     ns-sym
+                                    :config {:linters {:metabase/validate-deftest {}}}})
+       @(:findings clj-kondo.impl.utils/*ctx*)))))
+
+(deftest ^:parallel explicit-nonparallel-metadata-test
+  (testing "Hawk's supported test markers satisfy the explicit metadata linter"
+    (are [metadata] (empty? (parallel-metadata-findings
+                             (format "(deftest %s example-test (is true))" metadata)))
+      "^:parallel"
+      "^:synchronized"))
+  (testing "an unmarked test still gets the opt-in linter's guidance"
+    (is (=? [{:type    :metabase/deftest-not-marked-parallel-or-synchronized
+              :message "Test should be marked either `^:parallel` or `^:synchronized`"}]
+            (parallel-metadata-findings "(deftest example-test (is true))"))))
+  (testing "the unsupported marker explains that Hawk ignores it"
+    (is (some #(and (= (:type %) :metabase/validate-deftest)
+                    (re-find #"ignored by Hawk" (:message %)))
+              (parallel-metadata-findings
+               "(deftest ^:sequential example-test (is true))"))))
+  (testing "the verbose Hawk spelling is not accepted as Metabase style"
+    (is (some #(and (= (:type %) :metabase/validate-deftest)
+                    (re-find #"Use `\^:synchronized` instead" (:message %)))
+              (parallel-metadata-findings
+               "(deftest ^{:parallel false} example-test (is true))"))))
+  (testing "a test cannot request both execution modes"
+    (is (some #(and (= (:type %) :metabase/validate-deftest)
+                    (re-find #"both `\^:parallel` and `\^:synchronized`" (:message %)))
+              (parallel-metadata-findings
+               "(deftest ^:parallel ^:synchronized example-test (is true))"))))
+  (testing "a namespace-level non-parallel promise rejects parallel tests"
+    (is (=? [{:type    :metabase/validate-deftest
+              :message #(re-find #"namespace marked.*`\^:synchronized`" %)}]
+            (parallel-metadata-findings
+             "(deftest ^:parallel example-test (is true))"
+             (with-meta 'example.test {:synchronized true}))))))
+
 (deftest ^:parallel disallow-hardcoded-driver-names-in-tests-test
   (is (= []
          (deftest-warnings

.clj-kondo/test/hooks/common/modules_test.clj

@@ -5,6 +5,6 @@
 
 (deftest ^:parallel module-test
   (are [symb expected] (= expected
-                          (hooks.common.modules/module symb))
+                          (hooks.common.modules/module {} symb))
     'metabase.qp.middleware.wow        'qp
     'metabase-enterprise.whatever.core 'enterprise/whatever))

.clj-kondo/test/hooks/metabase/agent_message_test.clj

@@ -0,0 +1,334 @@
+(ns hooks.metabase.agent-message-test
+  (:require
+   [clj-kondo.hooks-api :as hooks]
+   [clj-kondo.impl.utils]
+   [clojure.edn :as edn]
+   [clojure.test :refer :all]
+   [hooks.metabase.agent-message :as agent-message]))
+
+(defn- findings
+  "Run `hook-fn` over `form`, a form or its source string, with the linters at `level` (unconfigured when nil) in
+  namespace `ns` of file `filename`; return the findings' messages."
+  ([hook-fn form]
+   (findings hook-fn form :warning))
+  ([hook-fn form level]
+   (findings hook-fn form level 'metabase.mcp.v2.tools.browse "src/metabase/mcp/v2/tools/browse.clj"))
+  ([hook-fn form level ns filename]
+   (let [config (if level
+                  {:linters {:metabase/agent-message-lines {:level level}
+                             :metabase/agent-message-exit  {:level level}}}
+                  {})]
+     (binding [clj-kondo.impl.utils/*ctx* {:config     config
+                                           :ignores    (atom nil)
+                                           :findings   (atom [])
+                                           :namespaces (atom {})}]
+       (let [input  {:node     (hooks/parse-string (if (string? form) form (pr-str form)))
+                     :ns       ns
+                     :filename filename
+                     :config   config}
+             output (hook-fn input)]
+         (is (identical? (:node input) (:node output))
+             "the hook must return the node unchanged so Kondo's normal analysis still runs")
+         (mapv :message @(:findings clj-kondo.impl.utils/*ctx*)))))))
+
+(def ^:private hook-cases
+  "`[hook form]` pairs that each report one finding when their linter is enabled."
+  [[agent-message/lint-msg '(msg lines x)]
+   [agent-message/lint-teaching-exit '(throw-teaching-error "x")]
+   [agent-message/lint-jsonrpc-error '(jsonrpc-error id -32602 "x")]
+   [agent-message/lint-success-content '(success-content "x")]
+   [agent-message/lint-ex-info "(ex-info \"x\" {:status-code 404})"]
+   [agent-message/lint-op-error '(op-error! idx "add_link" "x")]
+   [agent-message/lint-ellipsize '(ellipsize "x" 300)]
+   [agent-message/lint-list-content '(list-content data total {:empty-hint "x"})]])
+
+(defn- linter-enabled-in-ns?
+  "Whether `config` enables `linter` in namespace `ns-name` through an ns-group's `:config-in-ns` entry."
+  [config linter ns-name]
+  (boolean
+   (some (fn [{:keys [pattern name]}]
+           (and (string? pattern)
+                (re-find (re-pattern pattern) ns-name)
+                (not= :off (get-in config [:config-in-ns name :linters linter :level] :off))))
+         (:ns-groups config))))
+
+(deftest ^:parallel config-scope-test
+  (let [config (edn/read-string (slurp ".clj-kondo/config.edn"))]
+    (testing "GHY-4544: `msg` lines are checked in every OSS and enterprise MCP source namespace, and no test one"
+      (doseq [[ns-name enabled?] {"metabase.mcp.ui-resource"                     true
+                                  "metabase.mcp.transport"                       true
+                                  "metabase.mcp.v2.tools.browse"                 true
+                                  "metabase-enterprise.mcp.usage"                true
+                                  "metabase-enterprise.mcp.v2.tools.browse"      true
+                                  "metabase.mcp.ui-resource-test"                false
+                                  "metabase.mcp.v2.tools.browse-test"            false
+                                  "metabase.mcp.test-util"                       false
+                                  "metabase-enterprise.mcp.usage-test"           false
+                                  "metabase-enterprise.mcp.v2.tools.browse-test" false
+                                  "metabase.queries.models.card"                 false}]
+        (testing ns-name
+          (is (= enabled? (linter-enabled-in-ns? config :metabase/agent-message-lines ns-name))))))
+    (testing "GHY-4544: exits are checked in MCP transport and v2 source namespaces, whose 4xx errors reach the agent"
+      (doseq [[ns-name enabled?] {"metabase.mcp.transport"                       true
+                                  "metabase.mcp.v2.common"                       true
+                                  "metabase.mcp.v2.tools.browse"                 true
+                                  "metabase-enterprise.mcp.v2.common"            true
+                                  "metabase.mcp.settings"                        false
+                                  "metabase.mcp.validation"                      false
+                                  "metabase-enterprise.mcp.usage"                false
+                                  "metabase.mcp.transport-test"                  false
+                                  "metabase.mcp.v2.tools.browse-test"            false
+                                  "metabase-enterprise.mcp.v2.tools.browse-test" false
+                                  "metabase.queries.models.card"                 false}]
+        (testing ns-name
+          (is (= enabled? (linter-enabled-in-ns? config :metabase/agent-message-exit ns-name))))))
+    (testing "GHY-4544: `:empty-hint` is checked on `list-content` and on wrappers passing their options map to it"
+      (doseq [fn-sym '[metabase.mcp.v2.common/list-content
+                       metabase.mcp.v2.tools.browse/paged-list-content]]
+        (testing fn-sym
+          (is (= 'hooks.metabase.agent-message/lint-list-content
+                 (get-in config [:hooks :analyze-call fn-sym]))))))
+    (testing (str "GHY-4544: `check-execute-sql-enabled!` isn't checked, since it interpolates its subject into "
+                  "its own `msg` and a plain string is the intended way to name the tool")
+      (is (nil? (get-in config [:hooks
+                                :analyze-call
+                                (symbol "metabase.mcp.v2.queries" "check-execute-sql-enabled!")]))))))
+
+(deftest ^:parallel scope-test
+  (testing "GHY-4544: the hooks leave scoping to config, reporting in any namespace where their linter is enabled"
+    (doseq [[hook form] hook-cases
+            [ns filename]  [['metabase.mcp.v2.tools.browse "src/metabase/mcp/v2/tools/browse.clj"]
+                            ['metabase.queries.models.card "src/metabase/queries/models/card.clj"]
+                            ['metabase.mcp.v2.tools.browse-test "test/metabase/mcp/v2/tools/browse_test.clj"]]]
+      (testing (str ns " " (pr-str form))
+        (is (= 1 (count (findings hook form :warning ns filename)))))))
+  (testing "nothing is reported when the linter is off or unconfigured"
+    (doseq [[hook form] hook-cases
+            level       [:off nil]]
+      (testing (str level " " (pr-str form))
+        (is (empty? (findings hook form level)))))))
+
+(deftest ^:parallel msg-test
+  (testing "GHY-4544: a vector of single-line string literals with matching arguments is accepted"
+    (is (empty? (findings agent-message/lint-msg
+                          '(msg ["Table %s: %d of %d fields." "Continue with `offset: %d`."] t n total next)))))
+  (testing "specifiers that consume no argument aren't counted, and an explicit index can repeat an argument"
+    (is (empty? (findings agent-message/lint-msg '(msg ["100%% done."]))))
+    (is (empty? (findings agent-message/lint-msg '(msg ["%1$s, then %1$s again, then %<s"] x)))))
+  (testing "the lines must be a literal vector"
+    (is (=? [#".*vector.*"]
+            (findings agent-message/lint-msg '(msg lines x))))
+    (is (=? [#".*vector.*"]
+            (findings agent-message/lint-msg '(msg "one line" x)))))
+  (testing "a line may be split across a `str` of string literals"
+    (is (empty? (findings agent-message/lint-msg '(msg [(str "Table %s has " "%d fields.")] t n))))
+    (is (=? [#".*1 argument.*2.*"]
+            (findings agent-message/lint-msg '(msg [(str "only " "%s")] a b)))))
+  (testing "each line must be a string literal or a `str` of string literals"
+    (is (=? [#".*string literal or a `str` of string literals.*"]
+            (findings agent-message/lint-msg '(msg ["ok" line]))))
+    (is (=? [#".*string literal or a `str` of string literals.*"]
+            (findings agent-message/lint-msg '(msg [(str "split " x)])))))
+  (testing "a line can't contain a line break, control, or private-use character; each line is its own string"
+    (is (=? [#".*own string.*"]
+            (findings agent-message/lint-msg '(msg ["first\nsecond"]))))
+    (is (=? [#".*own string.*"]
+            (findings agent-message/lint-msg '(msg [(str "first\n" "second")]))))
+    (is (=? [#".*own string.*"]
+            (findings agent-message/lint-msg (list 'msg [(str "first" (char 0x2028) "second")]))))
+    (is (=? [#".*own string.*"]
+            (findings agent-message/lint-msg '(msg ["tab\tseparated"]))))
+    (is (=? [#".*own string.*"]
+            (findings agent-message/lint-msg '(msg ["done.%n"]))))
+    (testing "GHY-4544: a private-use character, which the truncation markers use, is flagged too"
+      (is (=? [#".*own string.*"]
+              (findings agent-message/lint-msg (list 'msg [(str "first" (char 0xE000) "second")]))))
+      (is (=? [#".*own string.*"]
+              (findings agent-message/lint-msg (list 'msg [(str "marked" (char 0xF8FF))]))))))
+  (testing "the argument count must match the specifiers across all lines"
+    (is (=? [#".*2 arguments.*1.*"]
+            (findings agent-message/lint-msg '(msg ["%s and" "%s"] a))))
+    (is (=? [#".*1 argument.*2.*"]
+            (findings agent-message/lint-msg '(msg ["only %s"] a b)))))
+  (testing (str "GHY-4544: a reference `String/format` can't resolve is flagged, since the runtime would fall back "
+                "to rendering every part quoted")
+    (testing "`%<` with no specifier before it to repeat, which counts as no argument at all"
+      (is (=? [#".*can't exist.*"]
+              (findings agent-message/lint-msg '(msg ["Value: %<s"]))))
+      (is (=? [#".*can't exist.*"]
+              (findings agent-message/lint-msg '(msg ["100%% done," "then %<d"])))))
+    (testing "an explicit index of zero, which is below the first argument"
+      (is (=? [#".*can't exist.*"]
+              (findings agent-message/lint-msg '(msg ["Value: %0$s"]))))
+      (is (=? [#".*can't exist.*"]
+              (findings agent-message/lint-msg '(msg ["Value: %0$s"] x)))))
+    (testing "a `%<` that repeats the first argument is still accepted"
+      (is (empty? (findings agent-message/lint-msg '(msg ["%s then %<s"] x)))))))
+
+(deftest ^:parallel msg-specifier-test
+  (testing "GHY-4544: only `%s` with no flags but `<`, `%d` with flags and width, and `%%` are allowed"
+    (doseq [line ["%s" "%d" "%1$s" "%,d" "%05d" "%-8d" "%(d" "%1$,10d"
+                  "%s again %<s" "%d again %<d" "%s (100%%)"]]
+      (testing line
+        (is (empty? (findings agent-message/lint-msg (list 'msg [(str "Value: " line)] 'x)))))))
+  (testing "GHY-4544: any other conversion, or a `%s` or `%d` that reshapes its value, is flagged"
+    (doseq [line ["%b" "%h" "%c" "%x" "%X" "%f" "%e" "%o" "%g" "%a" "%tY" "%TY" "%B"
+                  "%S" "%.20s" "%10s" "%-5s" "%#s" "%1$.3s" "%-10S" "%.1f" "%.2d" "%1$.2d"]]
+      (testing line
+        (is (=? [#"A `msg` line may only use `%s`, `%d`, or `%%`; .* would alter or hide the value\."]
+                (findings agent-message/lint-msg (list 'msg [(str "Value: " line)] 'x)))))))
+  (testing "GHY-4544: a `%` that doesn't begin a valid format specifier is flagged, since `String/format` rejects it"
+    (doseq [line ["Braces %}" "Dot %." "Trailing %" "Space % " "Unknown %q" "Bad date %tq" "%" "%1$"
+                  ;; GHY-4544: an argument index too large to be one is malformed, not an arithmetic overflow
+                  "%999999999999999999999999$s"]]
+      (testing (pr-str line)
+        (is (=? [#"A `%` in a `msg` line must begin a format specifier.*`%%`.*"]
+                (findings agent-message/lint-msg (list 'msg [line]))))))
+    (testing "an index at the digit cap still parses, and is reported as an argument count"
+      (is (=? [#".*999999999 arguments.*"]
+              (findings agent-message/lint-msg '(msg ["%999999999$s"] x))))))
+  (testing "valid specifiers, including an escaped percent sign, aren't flagged as malformed"
+    (doseq [form ['(msg ["100%% done"])
+                  '(msg ["%,d rows"] n)
+                  '(msg ["%1$s, then %<s"] x)
+                  '(msg [(str "50%" "% of %s")] x)]]
+      (testing (pr-str form)
+        (is (empty? (findings agent-message/lint-msg form)))))))
+
+(def ^:private stringy-texts
+  "Message arguments built as text rather than with `msg`."
+  ['"Query failed."
+   '(str "Query failed: " err)
+   '(format "Table %s not found" (pr-str t))
+   '(cond-> (json/encode body) message (str "\n" message))
+   '(if x "a" (str "b" y))
+   '(if x (msg ["a"]) (str "b" y))
+   '(when-let [e (:error r)] (str/join ", " e))
+   '(or (:message r) (tru "Unknown error"))
+   '(let [s (pr-str x)] (str "Bad value " s))
+   '(cond (:a x) (msg ["a"]) :else "b")
+   '(condp = x :a (str "a" y) (msg ["b"]))
+   '(condp = x :a (msg ["a"]) "b")
+   '(case x :a (msg ["a"]) "b")
+   '(case x :a "a" :b (msg ["b"]))
+   '(->> bad (map name) (str/join ", "))
+   '(-> x (str " suffix"))
+   '(-> x name str)
+   '(some-> e ex-message)
+   '(some->> xs (map name) (clojure.string/join ", "))
+   '(cond->> xs x (map name) y (str/join ", "))
+   '(cond-> "x" y (subs 1))
+   '(as-> x v (assoc v :a 1) (json/encode v))
+   '(doto (str "a" b) println)
+   '(let [s x] (-> s (format y)))])
+
+(def ^:private message-texts
+  "Message arguments that aren't syntactically text."
+  ['(msg ["Table %s not found."] t)
+   'message
+   '(if x (msg ["a"]) (msg ["b"]))
+   '(render-error e)
+   '(cond (str x) (msg ["a"]) :else (msg ["b"]))
+   '(condp = x "a" (msg ["a"]) (msg ["b"]))
+   '(condp get x "a" :>> render-error (msg ["b"]))
+   '(case x "a" (msg ["a"]) ("b" "c") (msg ["b"]))
+   '(-> "x" count)
+   '(->> "x" (map str) set)
+   '(some-> (str "x") render-error)
+   '(-> x)
+   '(-> e :message)
+   '(cond-> {:a 1} x (assoc :b "c"))
+   '(as-> "x" v (count v))
+   '(doto x (println "a"))])
+
+(deftest ^:parallel teaching-exit-test
+  (doseq [fn-name ["throw-teaching-error" "error-content"]]
+    (testing (str "GHY-4544: text passed to `" fn-name "` is flagged")
+      (doseq [text stringy-texts]
+        (testing (pr-str text)
+          (is (=? [(re-pattern (str ".*passes text to `" fn-name "`.*`msg`.*"))]
+                  (findings agent-message/lint-teaching-exit (list (symbol "common" fn-name) text)))))))
+    (testing (str "`" fn-name "` accepts a `msg`, a symbol, and other calls")
+      (doseq [text message-texts]
+        (testing (pr-str text)
+          (is (empty? (findings agent-message/lint-teaching-exit
+                                (list (symbol fn-name) text {:status-code 404}))))))))
+  (testing "only the message argument is checked"
+    (is (empty? (findings agent-message/lint-teaching-exit '(error-content (msg ["x"]) (str "code"))))))
+  (testing "nothing is reported when the linter is off"
+    (is (empty? (findings agent-message/lint-teaching-exit '(throw-teaching-error "x") :off)))))
+
+(def ^:private helper-cases
+  "`[hook fn-name form-fn]`: a message-taking helper's hook, the name its finding cites, and a function of a message
+  returning a call that passes it to the helper."
+  [[agent-message/lint-op-error "op-error!" #(list 'dashboard-ops/op-error! 'idx "add_link" %)]
+   [agent-message/lint-ellipsize "ellipsize" #(list 'common/ellipsize % 300)]
+   [agent-message/lint-list-content "list-content" #(list 'common/list-content 'rows 0 {:offset 0 :empty-hint %})]
+   [agent-message/lint-list-content "paged-list-content"
+    #(list 'paged-list-content 'args 'rows {:empty-hint %} 'identity)]])
+
+(deftest ^:parallel message-helper-test
+  (doseq [[hook fn-name form-fn] helper-cases]
+    (testing (str "GHY-4544: text passed as `" fn-name "`'s message is flagged")
+      (doseq [text stringy-texts]
+        (testing (pr-str text)
+          (is (=? [(re-pattern (str ".*passes text to `" fn-name "`.*`msg`.*"))]
+                  (findings hook (form-fn text)))))))
+    (testing (str "`" fn-name "` accepts a `msg`, a symbol, and other calls as its message")
+      (doseq [text message-texts]
+        (testing (pr-str text)
+          (is (empty? (findings hook (form-fn text))))))))
+  (testing "only the message argument is checked"
+    (is (empty? (findings agent-message/lint-op-error '(op-error! (str "0") (str "op") (msg ["x"])))))
+    (is (empty? (findings agent-message/lint-ellipsize '(ellipsize (msg ["x"]) (str "300")))))
+    (is (empty? (findings agent-message/lint-list-content '(list-content (str "data") 0 {:param (str "x")}))))
+    (is (empty? (findings agent-message/lint-list-content '(list-content data 0 opts))))
+    (is (empty? (findings agent-message/lint-list-content '(list-content data 0))))))
+
+(deftest ^:parallel jsonrpc-error-test
+  (testing "GHY-4544: text passed as the JSON-RPC error message is flagged"
+    (doseq [text stringy-texts]
+      (testing (pr-str text)
+        (is (=? [#".*passes text to `jsonrpc-error`.*`msg`.*"]
+                (findings agent-message/lint-jsonrpc-error (list 'transport/jsonrpc-error 'id -32602 text)))))))
+  (testing "a `msg`, symbol, or other call as the message is accepted"
+    (doseq [text message-texts]
+      (testing (pr-str text)
+        (is (empty? (findings agent-message/lint-jsonrpc-error (list 'jsonrpc-error 'id -32602 text)))))))
+  (testing "only the third argument is the message"
+    (is (empty? (findings agent-message/lint-jsonrpc-error '(jsonrpc-error "id" (str "code") (msg ["x"])))))))
+
+(deftest ^:parallel success-content-test
+  (testing "GHY-4544: text passed to `success-content` is flagged"
+    (doseq [text stringy-texts]
+      (testing (pr-str text)
+        (is (=? [#"`success-content` takes data to JSON-encode or a `msg`.*"]
+                (findings agent-message/lint-success-content (list 'common/success-content text)))))))
+  (testing "a payload, a `msg`, or a symbol is accepted"
+    (doseq [text (conj message-texts '{:data rows} '[a b])]
+      (testing (pr-str text)
+        (is (empty? (findings agent-message/lint-success-content (list 'success-content text))))))
+    (is (empty? (findings agent-message/lint-success-content
+                          '(success-content {:data rows} (str "structured")))))))
+
+(deftest ^:parallel ex-info-test
+  (testing "GHY-4544: an ex-info carrying a 4xx status code or an error code is flagged"
+    (doseq [form ["(ex-info \"Card not found\" {:status-code 404})"
+                  "(ex-info (str \"Bad \" x) {:status-code 400 :field f})"
+                  "(ex-info \"Nope\" {::common/error-code c})"
+                  "(ex-info \"Nope\" {:error-code c})"
+                  "(ex-info (msg [\"Nope\"]) {:error-code c})"]]
+      (testing form
+        (is (=? [#".*`throw-teaching-error` and a `msg`.*"]
+                (findings agent-message/lint-ex-info form))))))
+  (testing "other ex-info calls aren't flagged"
+    (doseq [form ["(ex-info \"boom\" {:status-code 500})"
+                  "(ex-info \"boom\" {:status-code code})"
+                  "(ex-info \"boom\" {:foo 1})"
+                  "(ex-info \"boom\" data)"
+                  "(ex-info \"boom\" (merge {:status-code 400} data))"
+                  "(ex-info \"boom\")"]]
+      (testing form
+        (is (empty? (findings agent-message/lint-ex-info form))))))
+  (testing "nothing is reported when the linter is off"
+    (is (empty? (findings agent-message/lint-ex-info "(ex-info \"x\" {:status-code 404})" :off)))))

.clj-kondo/test/hooks/metabase/toucan/db_ns_test.clj

@@ -0,0 +1,138 @@
+(ns hooks.metabase.toucan.db-ns-test
+  (:require
+   [clj-kondo.hooks-api :as hooks]
+   [clj-kondo.impl.utils]
+   [clojure.test :refer :all]
+   [hooks.metabase.toucan.db-ns :as toucan.db-ns]))
+
+(defn- confinement-findings
+  "Only the `t2-query-namespace` findings, so these tests are not affected by the query-hygiene
+  linter that shares this hook."
+  [findings]
+  (filter #(= :metabase/t2-query-namespace (:type %)) findings))
+
+(defn- lint-query-call [form ns-sym & [filename modules]]
+  (binding [clj-kondo.impl.utils/*ctx* {:config     {:linters {:metabase/t2-query-namespace {:level :warning}
+                                                               :metabase/unsafe-app-db-query  {:level :warning}}}
+                                        :ignores    (atom nil)
+                                        :findings   (atom [])
+                                        :namespaces (atom {})}]
+    (let [input  {:node     (hooks/parse-string (pr-str form))
+                  :ns       ns-sym
+                  :filename (or filename "src/metabase/foo/bar.clj")
+                  :config   {:metabase/modules modules}}
+          output (toucan.db-ns/lint-query-call input)]
+      (is (identical? (:node input) (:node output))
+          "the hook must return the node unchanged so Kondo's normal analysis still runs")
+      @(:findings clj-kondo.impl.utils/*ctx*))))
+
+(deftest ^:parallel t2-query-must-live-in-db-namespace-test
+  (testing "a query call outside a db namespace is flagged"
+    (is (=? [{:type    :metabase/t2-query-namespace
+              :message #".*`t2/select-one`.*"}]
+            (lint-query-call '(t2/select-one :model/Card :id 1) 'metabase.queries.models.card))))
+  (testing "metabase.<module>.db is allowed"
+    (is (empty? (confinement-findings (lint-query-call '(t2/select-one :model/Card :id 1) 'metabase.queries.db)))))
+  (testing "metabase-enterprise.<module>.db is allowed"
+    (is (empty? (confinement-findings (lint-query-call '(t2/select-one :model/Card :id 1) 'metabase-enterprise.sandbox.db)))))
+  (testing "metabase.driver.<driver>.db is allowed for driver modules"
+    (is (empty? (confinement-findings (lint-query-call '(t2/select-one :model/Database :id 1) 'metabase.driver.bigquery-cloud-sdk.db)))))
+  (testing "a nested db namespace is not a module db namespace"
+    (is (=? [{:type :metabase/t2-query-namespace}]
+            (lint-query-call '(t2/query {:select [:*]}) 'metabase.queries.models.db))))
+  (testing "a namespace merely ending in db is not a module db namespace"
+    (is (=? [{:type :metabase/t2-query-namespace}]
+            (lint-query-call '(t2/delete! :model/Card :id 1) 'metabase.queries.dashboards-db))))
+  (testing "files in a test source tree are exempt even when the namespace name doesn't look like a test"
+    (is (empty? (lint-query-call '(t2/update! :model/User 1 {:sso_source nil}) 'metabase.sso.test-helpers
+                                 "test/metabase/sso/test_helpers.clj")))
+    (is (empty? (lint-query-call '(t2/select :model/Card) 'metabase-enterprise.remote-sync.test-helpers
+                                 "/repo/enterprise/backend/test/metabase_enterprise/remote_sync/test_helpers.clj"))))
+  (testing "app-db wrappers around Toucan 2 are reported the same way"
+    (is (=? [{:type    :metabase/t2-query-namespace
+              :message #".*`mdb/update-or-insert!`.*"}]
+            (lint-query-call '(mdb/update-or-insert! :model/Foo {:id 1}) 'metabase.foo.models.foo))))
+  (testing "fully-qualified calls are reported by their written name"
+    (is (=? [{:type    :metabase/t2-query-namespace
+              :message #".*`toucan2.core/insert!`.*"}]
+            (lint-query-call '(toucan2.core/insert! :model/Card {}) 'metabase.queries.models.card)))))
+
+(deftest ^:parallel t2-query-namespace-follows-the-module-tree-test
+  (let [modules '{queries            {}
+                  metabot            {}
+                  metabot.llm        {}
+                  lib.be             {:ns-prefix "metabase.lib-be"}
+                  enterprise/sandbox {}}]
+    (testing "a nested module owns its own db namespace"
+      (is (empty? (lint-query-call '(t2/select :model/Card) 'metabase.metabot.llm.db nil modules))))
+    (testing "the parent's db namespace stays its own"
+      (is (empty? (lint-query-call '(t2/select :model/Card) 'metabase.metabot.db nil modules))))
+    (testing "a module with an explicit :ns-prefix is resolved through it, not its dotted name"
+      (is (empty? (lint-query-call '(t2/select :model/Card) 'metabase.lib-be.db nil modules)))
+      (is (=? [{:type :metabase/t2-query-namespace}]
+              (lint-query-call '(t2/select :model/Card) 'metabase.lib.be.db nil modules))))
+    (testing "a db namespace under a directory naming no module is still a finding"
+      (is (=? [{:type :metabase/t2-query-namespace}]
+              (lint-query-call '(t2/query {:select [:*]}) 'metabase.queries.models.db nil modules)))
+      (is (=? [{:type :metabase/t2-query-namespace}]
+              (lint-query-call '(t2/query {:select [:*]}) 'metabase.metabot.llm.models.db nil modules))))
+    (testing "enterprise modules resolve through the metabase-enterprise root"
+      (is (empty? (lint-query-call '(t2/select :model/Card) 'metabase-enterprise.sandbox.db nil modules))))))
+
+(deftest ^:parallel unmarked-value-in-a-db-namespace-test
+  (testing "a symbol reaching a value slot is flagged"
+    (is (=? [{:type    :metabase/unsafe-app-db-query
+              :message #"`locale` reaches a SQL value slot unmarked.*"}]
+            (lint-query-call '(t2/select :model/X {:where [:= :locale locale]}) 'metabase.foo.db))))
+  (testing "a marked value is not flagged"
+    (is (empty? (lint-query-call '(t2/select :model/X {:where [:= :locale [:auto/param locale]]})
+                                 'metabase.foo.db))))
+  (testing "a literal cannot carry a request value and is not flagged"
+    (is (empty? (lint-query-call '(t2/select :model/X {:where [:= :locale "de"]}) 'metabase.foo.db))))
+  (testing "a column reference is not a value"
+    (is (empty? (lint-query-call '(t2/select :model/X {:where [:= :a.id :b.id]}) 'metabase.foo.db))))
+  (testing "values nested under a boolean connective are reached"
+    (is (=? [{:message #"`b`.*"}]
+            (lint-query-call '(t2/select :model/X {:where [:and [:= :x [:auto/param a]] [:= :y b]]})
+                             'metabase.foo.db))))
+  (testing "only db namespaces are linted for unmarked values"
+    (is (empty? (filter #(= :metabase/unsafe-app-db-query (:type %))
+                        (lint-query-call '(t2/select :model/X {:where [:= :locale locale]})
+                                         'metabase.foo.models.thing)))))
+  (testing "a test source tree is exempt"
+    (is (empty? (lint-query-call '(t2/select :model/X {:where [:= :locale locale]})
+                                 'metabase.foo.db "test/metabase/foo/db_test.clj")))))
+
+(deftest ^:parallel kv-arg-style-test
+  (testing "a query written as :column value pairs is flagged whatever the values are"
+    (are [form] (=? [{:type :metabase/unsafe-app-db-query, :message #"Pass this query a map.*"}]
+                    (lint-query-call form 'metabase.foo.db))
+      '(t2/select :model/X :locale locale)
+      '(t2/select :model/X :archived false)
+      '(t2/select :model/X :locale [:auto/param locale])
+      '(t2/select-one :model/X :id (long id))))
+  (testing "one finding per call, not one per pair"
+    (is (= 1 (count (lint-query-call '(t2/select :model/X :locale locale :msgid msgid)
+                                     'metabase.foo.db)))))
+  (testing "a fn with an argument before the model is still recognised"
+    (is (=? [{:message #"Pass this query a map.*"}]
+            (lint-query-call '(t2/select-one-fn :value :model/Setting :key k) 'metabase.foo.db))))
+  (testing "a map query is not flagged"
+    (are [form] (empty? (lint-query-call form 'metabase.foo.db))
+      '(t2/select :model/X {:where [:= :locale [:auto/param locale]]})
+      '(t2/update! :model/X {:locale [:auto/param locale]} {:msgstr "x"}))))
+
+(deftest ^:parallel write-calls-are-not-linted-for-values-test
+  (testing "an insert's values are written, not filtered on, so they are not flagged"
+    (are [form] (empty? (filter #(= :metabase/unsafe-app-db-query (:type %))
+                                (lint-query-call form 'metabase.foo.db)))
+      '(t2/insert! :model/X :key k :value v)
+      '(t2/insert-returning-instances! :model/X :key k :value v)))
+  (testing "a select's values are still flagged"
+    (is (=? [{:type :metabase/unsafe-app-db-query}]
+            (lint-query-call '(t2/select :model/X :key k) 'metabase.foo.db)))))
+
+(deftest ^:parallel operator-arity-test
+  (testing "a value operator with an unexpected arity still has its args examined"
+    (is (seq (lint-query-call '(t2/select :model/X {:where [:= :a b c]}) 'metabase.foo.db)))
+    (is (seq (lint-query-call '(t2/select :model/X {:where [:between :a lo hi]}) 'metabase.foo.db)))))

.cljfmt.edn

@@ -12,6 +12,7 @@
   "enterprise/backend"
   "bin/build"
   "bin/lint-migrations-file"
+  "bin/load-namespaces"
   "bin/release-list"
   #_"mage/src"
   #_"mage/test"

.codespellrc

@@ -16,7 +16,7 @@ skip =
     frontend/src/metabase/querying/expressions/tokenizer/lezer.js,
     frontend/src/metabase/query_builder/components/NativeQueryEditor/CodeMirrorEditor/language.ts,
     frontend/src/metabase/static-viz/constants/char-sizes.ts,
-    frontend/src/metabase/visualizations/lib/mapping_codes.ts,
+    frontend/src/metabase/viz-core/lib/mapping_codes.ts,
     frontend/*/mocks/*,
     modules/drivers/mongo/src/metabase/driver/mongo/operators.clj,
     src/metabase/analyze/classifiers/name.clj,

.dependency-cruiser.cjs

@@ -2,7 +2,7 @@
 // imported, vs the *allowed* edges in module-boundaries.mjs). Consumed by
 // .github/scripts/create-test-plan.ts.
 //
-//   bunx depcruise frontend/src enterprise/frontend/src \
+//   bunx depcruise frontend/src enterprise/frontend/src .storybook/preview.tsx \
 //     --config .dependency-cruiser.cjs --output-type json > dependency-graph.json
 
 /** @type {import('dependency-cruiser').IConfiguration} */
@@ -10,10 +10,13 @@ module.exports = {
   options: {
     // Keep only edges between our own source files (drops node_modules etc.),
     // which keeps the JSON small.
-    includeOnly: "^(frontend/src|enterprise/frontend/src)/",
+    includeOnly: "^(frontend/src|enterprise/frontend/src|\\.storybook)/",
 
     doNotFollow: { path: "node_modules" },
 
+    // No rules here, so the cycle and orphan analysis has no consumer and only costs time.
+    skipAnalysisNotInRules: true,
+
     // Resolve the `"*": ["./frontend/src/*", ...]` aliases so bare imports like
     // `metabase/lib/foo` map back to a real file.
     tsConfig: { fileName: "tsconfig.json" },

.github/CODEOWNERS

@@ -10,6 +10,7 @@ src/metabase/query_processor @metabase/core-backend-querying-platform
 src/metabase/graph @metabase/graphy
 enterprise/backend/src/metabase_enterprise/dependencies @metabase/graphy
 enterprise/frontend/src/metabase-enterprise/dependencies @metabase/graphy
+enterprise/frontend/src/metabase-enterprise/monitor/dependency-diagnostics @metabase/graphy
 
 # @metabase/embedding
 
@@ -41,6 +42,9 @@ docs/api.json # auto-generated
 docs/configuring-metabase/environment-variables.md # auto-generated
 docs/configuring-metabase/config-template.md # auto-generated
 docs/installation-and-operation/commands.md # auto-generated
+docs/ai/providers.md # auto-generated
+docs/embedding/sdk/api # auto-generated
+docs/embedding/eajs/snippets # auto-generated
 
 # @metabase/devexp
 .github @metabase/devexp
@@ -49,5 +53,17 @@ docs/installation-and-operation/commands.md # auto-generated
 src/metabase/analytics/prometheus.clj @metabase/cloud-ops
 
 # @metabase/metabot-frontend
-enterprise/frontend/src/metabase-enterprise/metabot @metabase/metabot-frontend 
+enterprise/frontend/src/metabase-enterprise/metabot @metabase/metabot-frontend
 frontend/src/metabase/metabot @metabase/metabot-frontend
+
+# @metabase/core-frontend-gadget
+bin/custom-viz @metabase/core-frontend-gadget
+docs/developers-guide/custom-visualizations.md @metabase/core-frontend-gadget
+enterprise/frontend/src/custom-viz @metabase/core-frontend-gadget
+enterprise/frontend/src/metabase-enterprise/api/custom-viz-plugin.ts @metabase/core-frontend-gadget
+enterprise/frontend/src/metabase-enterprise/custom_viz @metabase/core-frontend-gadget
+frontend/src/metabase-types/api/custom-viz-plugin.ts @metabase/core-frontend-gadget
+frontend/src/metabase/plugins/oss/custom-viz.ts @metabase/core-frontend-gadget
+frontend/src/metabase/visualizations/custom-visualizations @metabase/core-frontend-gadget
+frontend/test/__support__/custom-viz-fixtures @metabase/core-frontend-gadget
+.github/workflows/release-custom-viz.yml @metabase/devexp @metabase/core-frontend-gadget

.github/actionlint.yaml

@@ -0,0 +1,19 @@
+self-hosted-runner:
+  # Custom runner labels that actionlint cannot know about. Everything else is
+  # selected through `vars.DEFAULT_RUNNER_KEY` and is not checked.
+  labels:
+    - arm-ubuntu-24-2core
+
+paths:
+  # GitHub added parallel steps (`parallel`, `background`, `wait`, `wait-all`,
+  # `cancel`) in June 2026, and actionlint 1.7.12 does not know the schema yet:
+  # https://github.blog/changelog/2026-06-25-actions-steps-can-now-be-run-in-parallel/
+  .github/workflows/backend.yml:
+    ignore:
+      - 'step must run script with "run" section or run action with "uses" section'
+  .github/workflows/lint.yml:
+    ignore:
+      - 'step must run script with "run" section or run action with "uses" section'
+  .github/workflows/pr.checks.yml:
+    ignore:
+      - 'step must run script with "run" section or run action with "uses" section'

.github/actions/bundle-size-check/action.yml

@@ -0,0 +1,136 @@
+name: Bundle Size Check
+description: |
+  Measures app + embedding SDK bundle sizes from the current and base-ref
+  uberjars (reusing the builds that already ran) plus their bundle-stats
+  artifacts, and flags gzipped size changes beyond the threshold for the main
+  app's initial bundle and the chunked SDK's reachable total. The base ref is
+  read back off the current uberjar so that both sides differ only by the PR.
+  Skips when the base-ref artifacts aren't available rather than rebuilding from
+  source (which would compare across pipelines).
+
+inputs:
+  edition:
+    description: 'Metabase edition (ee or oss)'
+    required: true
+  threshold-percent:
+    description: 'Percent threshold for bundle size change'
+    required: true
+
+outputs:
+  app_status:
+    description: "App initial bundle status: increased, decreased, or stable"
+    value: ${{ steps.compare.outputs.app_initial_status }}
+  app_size_change_percent:
+    description: "App initial bundle size change percent (positive = increase, negative = decrease)"
+    value: ${{ steps.compare.outputs.app_initial_size_change_percent }}
+  sdk_status:
+    description: "Chunked SDK bundle status: increased, decreased, or stable"
+    value: ${{ steps.compare.outputs.embedding_sdk_chunked_total_status }}
+  sdk_size_change_percent:
+    description: "Chunked SDK bundle size change percent (positive = increase, negative = decrease)"
+    value: ${{ steps.compare.outputs.embedding_sdk_chunked_total_size_change_percent }}
+
+runs:
+  using: "composite"
+  steps:
+    - name: Download current uberjar
+      uses: ./.github/actions/fetch-artifact
+      with:
+        commit: ${{ github.event.pull_request.head.sha || github.sha }}
+        edition: ${{ inputs.edition }}
+        extract-path: temp/current-uberjar
+    - name: Resolve the base ref the current uberjar was built against
+      id: base-ref
+      shell: bash
+      env:
+        GH_TOKEN: ${{ github.token }}
+      run: |
+        set -uo pipefail
+
+        # The uberjar job checks out refs/pull/<n>/merge (the PR head already
+        # merged into the base branch tip) but names its artifact after head.sha,
+        # so the comparable base ref is that merge's first parent. Reading it back
+        # off the jar describes the artifact actually being measured. Using
+        # pull_request.base.sha instead compares against a stale snapshot of the
+        # base branch, reporting everything that landed in between as this PR's
+        # own bundle delta.
+        unzip -o -j temp/current-uberjar/metabase.jar version.properties -d temp/current-version >/dev/null
+        built=$(sed -n 's/^hash=//p' temp/current-version/version.properties)
+        base=$(gh api "/repos/${GITHUB_REPOSITORY}/commits/${built}" \
+          --jq 'if (.parents | length) == 2 then .parents[0].sha else empty end' 2>/dev/null) || base=""
+
+        echo "sha=${base}" >> "$GITHUB_OUTPUT"
+        echo "The current uberjar was built from ${built}; its base ref is ${base:-unknown}"
+    - name: Download base-ref uberjar
+      id: base-jar
+      if: steps.base-ref.outputs.sha != ''
+      continue-on-error: true
+      uses: ./.github/actions/fetch-artifact
+      with:
+        commit: ${{ steps.base-ref.outputs.sha }}
+        edition: ${{ inputs.edition }}
+        extract-path: temp/base-uberjar
+    - name: Measure and compare bundle sizes
+      id: compare
+      shell: bash
+      env:
+        GH_TOKEN: ${{ github.token }}
+        EDITION: ${{ inputs.edition }}
+        HEAD_SHA: ${{ github.event.pull_request.head.sha || github.sha }}
+        BASE_SHA: ${{ steps.base-ref.outputs.sha }}
+        THRESHOLD: ${{ inputs.threshold-percent }}
+        MEASURE_BUNDLES: app,embedding-sdk-legacy,embedding-sdk-chunked
+        # The gated bundles, as "<bundle>/<kind>". Each one's step outputs are
+        # named after its key (see outputPrefix in compare.js), which is what the
+        # action outputs above read.
+        GATES: app/initial,embedding-sdk-chunked/total
+      run: |
+        set -uo pipefail
+
+        skip() {
+          echo "::notice::Bundle-size check skipped: $1"
+          for gate in ${GATES//,/ }; do
+            prefix=$(printf '%s' "$gate" | tr -c 'a-zA-Z0-9' '_')
+            echo "${prefix}_status=stable" >> "$GITHUB_OUTPUT"
+            echo "${prefix}_size_change_percent=0" >> "$GITHUB_OUTPUT"
+          done
+          exit 0
+        }
+
+        # The base ref needs an already-built uberjar. Rebuilding it from source
+        # would compare across two build pipelines (the bug this check used to
+        # have), so skip instead when it — or its stats — isn't available.
+        [ -n "${BASE_SHA}" ] || skip "no comparable base ref for the current uberjar"
+        [ -f temp/base-uberjar/metabase.jar ] || skip "base-ref uberjar not found for ${BASE_SHA}"
+
+        extract_js() { # $1=jar  $2=dest-root
+          mkdir -p "$2/resources"
+          unzip -o "$1" \
+            "frontend_client/app/dist/*" \
+            "frontend_client/app/embed.js" \
+            "frontend_client/app/embedding-sdk/*" \
+            -d "$2/resources" >/dev/null || true
+        }
+
+        fetch_stats() { # $1=sha  $2=dest-dir
+          local name="metabase-bundle-stats-${EDITION}-$1"
+          local id
+          id=$(gh api "/repos/${GITHUB_REPOSITORY}/actions/artifacts?name=${name}" --jq '.artifacts[0].id // empty' 2>/dev/null)
+          [ -n "${id}" ] || return 1
+          mkdir -p "$2"
+          gh api "/repos/${GITHUB_REPOSITORY}/actions/artifacts/${id}/zip" > "$2.zip" 2>/dev/null || return 1
+          unzip -o "$2.zip" -d "$2" >/dev/null || return 1
+        }
+
+        extract_js temp/current-uberjar/metabase.jar temp/current
+        extract_js temp/base-uberjar/metabase.jar temp/base
+
+        fetch_stats "${HEAD_SHA}" temp/current/artifacts || skip "bundle stats not found for current ${HEAD_SHA}"
+        fetch_stats "${BASE_SHA}" temp/base/artifacts || skip "bundle stats not found for base ${BASE_SHA}"
+
+        MEASURE_ROOT=temp/current node ./.github/scripts/measure-bundle-sizes.js > temp/current-sizes.json \
+          || { echo "::error::Failed to measure current bundle sizes"; exit 1; }
+        MEASURE_ROOT=temp/base node ./.github/scripts/measure-bundle-sizes.js > temp/base-sizes.json \
+          || { echo "::error::Failed to measure base bundle sizes"; exit 1; }
+
+        node ./.github/actions/bundle-size-check/compare.js temp/current-sizes.json temp/base-sizes.json

.github/actions/bundle-size-check/compare.js

@@ -0,0 +1,133 @@
+/* eslint-disable import/no-commonjs */
+// Diffs the bundle sizes produced by measure-bundle-sizes.js for the current
+// build and the base ref. Every (bundle, kind) is compared strictly against the
+// same (bundle, kind) — never one bundle type against another — using gzipped
+// (served) bytes.
+//
+// The report covers every measured bundle; the gates are the subset that drives
+// PR comments, named as "<bundle>/<kind>" (e.g. "app/initial",
+// "embedding-sdk-chunked/total").
+//
+// compareBundles is pure (data in, data out) so it can be unit-tested; main()
+// is the thin I/O wrapper that reads the size files, prints the report and sets
+// the step outputs / exit code.
+const fs = require("fs");
+
+const pick = (rows, bundle, kind) => rows.find(row => row.bundle === bundle && row.kind === kind);
+const keyOf = row => `${row.bundle}/${row.kind}`;
+const mb = bytes => (bytes / 1024 / 1024).toFixed(2);
+const percentOf = (currentBytes, baseBytes) =>
+  baseBytes ? Math.trunc(((currentBytes - baseBytes) * 100) / baseBytes) : 0;
+
+// Output names are derived from the gate key, so the workflow reads
+// `app_initial_status`, `embedding_sdk_chunked_total_status`, and so on.
+const outputPrefix = gateKey => gateKey.replace(/[^a-zA-Z0-9]+/g, "_");
+
+/**
+ * Evaluate one gate. Returns the key plus exactly one of:
+ *  - `status` / `percent`: the bundle moved by `percent`.
+ *  - `skip`  reason: the gate is non-actionable (reported stable, no comment).
+ *  - `error` reason: the gate inputs are missing (hard failure).
+ */
+function evaluateGate({ current, base, threshold, gateKey }) {
+  const [bundle, kind] = gateKey.split("/");
+  const gateCurrent = pick(current, bundle, kind);
+  const gateBase = pick(base, bundle, kind);
+  if (!gateCurrent || !gateBase || !gateBase.gzipBytes) {
+    return { gateKey, error: `Could not find ${bundle} ${kind} (gzip) in both builds` };
+  }
+
+  // Both sides must measure the bundle the same way. A base ref built before the
+  // reachableAssets enrichment collapses its total to the initial set, so
+  // comparing it against the current reachable total reports a phantom jump
+  // (~30%). Skip until the base ref also carries reachable stats.
+  if (Boolean(gateCurrent.reachable) !== Boolean(gateBase.reachable)) {
+    return {
+      gateKey,
+      skip:
+        `"${gateKey}" measured differently on each side ` +
+        `(current reachable=${Boolean(gateCurrent.reachable)}, base reachable=${Boolean(gateBase.reachable)}); ` +
+        `the base ref predates the reachable-chunk stats. Resolves once this change is on the base ref.`,
+    };
+  }
+
+  const percent = percentOf(gateCurrent.gzipBytes, gateBase.gzipBytes);
+  const status = percent > threshold ? "increased" : percent < -threshold ? "decreased" : "stable";
+  return { gateKey, status, percent };
+}
+
+/**
+ * Compare two measurement sets and evaluate every gate. Returns a
+ * human-readable `report` over all measured bundles plus one entry per gate.
+ */
+function compareBundles({ current, base, threshold, gateKeys }) {
+  const report = ["=== Bundle sizes (gzipped, current vs base) ==="];
+  const keys = [...new Set([...current, ...base].map(keyOf))].sort();
+  for (const key of keys) {
+    const [bundle, kind] = key.split("/");
+    const currentRow = pick(current, bundle, kind);
+    const baseRow = pick(base, bundle, kind);
+    if (!currentRow || !baseRow) {
+      report.push(`${key}: present only in ${currentRow ? "current" : "base"} build`);
+      continue;
+    }
+    const diff = currentRow.gzipBytes - baseRow.gzipBytes;
+    const percent = percentOf(currentRow.gzipBytes, baseRow.gzipBytes);
+    report.push(`${key}: ${mb(currentRow.gzipBytes)}MB vs ${mb(baseRow.gzipBytes)}MB (${percent}%, ${diff} bytes)`);
+  }
+
+  return { report, gates: gateKeys.map(gateKey => evaluateGate({ current, base, threshold, gateKey })) };
+}
+
+module.exports = { compareBundles, outputPrefix };
+
+const setOutput = (name, value) => {
+  if (process.env.GITHUB_OUTPUT) {
+    fs.appendFileSync(process.env.GITHUB_OUTPUT, `${name}=${value}\n`);
+  }
+};
+
+function main() {
+  const [, , currentPath, basePath] = process.argv;
+  const threshold = Number(process.env.THRESHOLD ?? 2);
+  const gateKeys = (process.env.GATES ?? "embedding-sdk-chunked/total").split(",").map(key => key.trim());
+
+  const current = JSON.parse(fs.readFileSync(currentPath, "utf8"));
+  const base = JSON.parse(fs.readFileSync(basePath, "utf8"));
+
+  const { report, gates } = compareBundles({ current, base, threshold, gateKeys });
+  console.log(report.join("\n"));
+  console.log("");
+
+  for (const gate of gates) {
+    const prefix = outputPrefix(gate.gateKey);
+
+    if (gate.error) {
+      // One broken gate must not hide the others, so report them all and fail
+      // the step at the end.
+      console.error(`::error::${gate.error}`);
+      continue;
+    }
+
+    if (gate.skip) {
+      // Treat the gate as non-actionable: report stable so no regression comment
+      // is posted, mirroring the shell skip() for missing artifacts.
+      console.log(`::notice::Bundle-size gate skipped: ${gate.skip}`);
+      setOutput(`${prefix}_status`, "stable");
+      setOutput(`${prefix}_size_change_percent`, "0");
+      continue;
+    }
+
+    console.log(`Gate: ${gate.gateKey} ${gate.percent}% (threshold ${threshold}%) → ${gate.status}`);
+    setOutput(`${prefix}_status`, gate.status);
+    setOutput(`${prefix}_size_change_percent`, gate.percent);
+  }
+
+  if (gates.some(gate => gate.error)) {
+    process.exit(1);
+  }
+}
+
+if (require.main === module) {
+  main();
+}

.github/actions/bundle-size-check/compare.unit.spec.js

@@ -0,0 +1,84 @@
+const { compareBundles, outputPrefix } = require("./compare");
+
+const SDK_GATE = "embedding-sdk-chunked/total";
+const APP_GATE = "app/initial";
+
+const total = (gzipBytes, over = {}) => ({
+  bundle: "embedding-sdk-chunked",
+  kind: "total",
+  gzipBytes,
+  reachable: true,
+  ...over,
+});
+
+const appInitial = gzipBytes => ({ bundle: "app", kind: "initial", gzipBytes });
+
+const compare = ({ current, base, threshold = 2, gateKeys = [SDK_GATE] }) =>
+  compareBundles({ current, base, threshold, gateKeys });
+
+describe("outputPrefix", () => {
+  it("turns a gate key into a step-output prefix", () => {
+    expect(outputPrefix(APP_GATE)).toBe("app_initial");
+    expect(outputPrefix(SDK_GATE)).toBe("embedding_sdk_chunked_total");
+  });
+});
+
+describe("compareBundles", () => {
+  it("gates on the chunked SDK total and flags an increase past the threshold", () => {
+    const { gates, report } = compare({ current: [total(110)], base: [total(100)] });
+
+    expect(gates).toEqual([{ gateKey: SDK_GATE, status: "increased", percent: 10 }]);
+    expect(report[0]).toContain("current vs base");
+  });
+
+  it("flags a decrease and stays stable within the threshold", () => {
+    expect(compare({ current: [total(90)], base: [total(100)] }).gates[0]).toMatchObject({
+      status: "decreased",
+      percent: -10,
+    });
+    expect(compare({ current: [total(101)], base: [total(100)] }).gates[0]).toMatchObject({
+      status: "stable",
+      percent: 1,
+    });
+  });
+
+  it("evaluates each gate against its own bundle", () => {
+    const { gates } = compare({
+      current: [total(100), appInitial(110)],
+      base: [total(100), appInitial(100)],
+      gateKeys: [APP_GATE, SDK_GATE],
+    });
+
+    expect(gates).toEqual([
+      { gateKey: APP_GATE, status: "increased", percent: 10 },
+      { gateKey: SDK_GATE, status: "stable", percent: 0 },
+    ]);
+  });
+
+  it("skips when the two sides measured a gate differently (reachable mismatch)", () => {
+    const { gates } = compare({
+      current: [total(130, { reachable: true })],
+      base: [total(100, { reachable: false })],
+    });
+
+    expect(gates[0].status).toBeUndefined();
+    expect(gates[0].skip).toContain("predates the reachable-chunk stats");
+  });
+
+  it("errors when a gate bundle is missing on either side, without hiding the others", () => {
+    const { gates } = compare({
+      current: [appInitial(100)],
+      base: [appInitial(100)],
+      gateKeys: [APP_GATE, SDK_GATE],
+    });
+
+    expect(gates[0]).toEqual({ gateKey: APP_GATE, status: "stable", percent: 0 });
+    expect(gates[1].error).toContain("embedding-sdk-chunked total");
+  });
+
+  it("reports a bundle/kind present on only one side without erroring", () => {
+    const { report } = compare({ current: [total(100), appInitial(50)], base: [total(100)] });
+
+    expect(report.some(line => line.includes("present only in current build"))).toBe(true);
+  });
+});

.github/actions/collect-profile/action.yml

@@ -0,0 +1,61 @@
+name: Collect profile
+description: >-
+  Attach a flamegraph and per-test wall times to a job whose tests ran under clj-async-profiler.
+  Does nothing when the run was not profiled.
+
+inputs:
+  profiled:
+    required: true
+    description: >-
+      "true" when the test step ran under the profiler. Passed in rather than read from the
+      environment so the decision stays recorded by the step that made it.
+  artifact-name:
+    required: true
+    description: Name for the uploaded artifact. Must be unique across the jobs of one run.
+
+runs:
+  using: "composite"
+  steps:
+    # Unlike a JUnit failure report, these run on a green build too — a suite that passes slowly is
+    # exactly what profiling is for.
+    #
+    # `awk 'NR<=25'` rather than `head -25`: the runner ignores SIGPIPE, so `head` exiting early
+    # leaves `sort` with an EPIPE write error and `pipefail` fails the step. `|| true` covers `grep`
+    # finding no junit files.
+    - name: Summarize test wall times
+      if: ${{ inputs.profiled == 'true' }}
+      continue-on-error: true
+      shell: bash
+      run: |
+        {
+          echo "### Slowest test namespaces (seconds)"
+          echo '```'
+          grep -h '<testsuite' target/junit/*.xml 2>/dev/null \
+            | sed -E 's|.*<testsuite name="([^"]*)" time="([^"]*)".*|\2 \1|' \
+            | sort -rn | awk 'NR<=25' || true
+          echo '```'
+          echo "### Slowest tests (seconds)"
+          echo '```'
+          grep -h '<testcase' target/junit/*.xml 2>/dev/null \
+            | sed -E 's|.*classname="([^"]*)" name="([^"]*)" time="([^"]*)".*|\3 \1/\2|' \
+            | sort -rn | awk 'NR<=25' || true
+          echo '```'
+        } >> "$GITHUB_STEP_SUMMARY"
+
+    # Only the rendered flamegraph is kept: the raw collapsed stacks it was built from run to
+    # hundreds of MB on a long suite, and are reproducible locally from the same test selection.
+    #
+    # The info-level test log rides along on a green profiled run too. The failure-only log artifact
+    # the test jobs upload is not written when nothing failed, which is exactly the run being profiled.
+    - name: Upload profile
+      if: ${{ inputs.profiled == 'true' }}
+      continue-on-error: true
+      uses: actions/upload-artifact@v7
+      with:
+        name: ${{ inputs.artifact-name }}
+        path: |
+          target/clj-async-profiler/results/*flamegraph.html
+          target/junit/*.xml
+          logs/test-log.json
+        retention-days: 14
+        if-no-files-found: warn

.github/actions/create-backport/action.yml

@@ -1,4 +1,5 @@
 name: Create Backport PR
+description: Cherry-picks a commit onto a release branch and opens the backport pull request.
 
 inputs:
   target-version: # major version number like 34 or 86
@@ -24,6 +25,8 @@ runs:
         COMMIT: ${{ inputs.backport-commit }}
       shell: bash
       run: | # bash
+        source "${{ github.action_path }}/kondo-ratchets.sh"
+
         git config --global user.email "metabase-bot@metabase.com"
         git config --global user.name "Metabase bot"
 
@@ -33,7 +36,7 @@ runs:
         git checkout ${TARGET_BRANCH}
         git fetch --all
         git checkout -b ${BACKPORT_BRANCH}
-        git cherry-pick ${COMMIT} || true
+        cherry_pick_backport "${COMMIT}"
 
         CONFLICT_LIST=$(git ls-files -u)
 
@@ -42,13 +45,10 @@ runs:
           git cherry-pick --abort
 
           echo "Could not cherry pick because of a conflict"
-          echo "has-conflicts=true" >> $GITHUB_OUTPUT
+          echo "has-conflicts=true" >> "$GITHUB_OUTPUT"
 
           # Add a shell script for resolving conflicts
-          echo "git reset HEAD~1" > ./backport.sh
-          echo "rm ./backport.sh" >> ./backport.sh
-          echo "git cherry-pick ${COMMIT}" >> ./backport.sh
-          echo "echo 'Resolve conflicts and force push this branch.\n\nTo backport translations run: bin/i18n/merge-translations <release-branch>'" >> ./backport.sh
+          write_backport_script "${COMMIT}"
           chmod +x ./backport.sh
           git add ./backport.sh
           git commit -m "Add backport resolution script"
@@ -57,44 +57,43 @@ runs:
           #${ORIGINAL_PULL_REQUEST_NUMBER}
           > [!IMPORTANT]
           > Manual conflict resolution is required.
-          > Checkout the branch and run \`./backport.sh\` script. Force push your changes after cherry-picking. Check the box below when done.
+          > Checkout the branch and run \`./backport.sh\` script. Force push your changes after cherry-picking. Mark the PR as ready for review once conflicts have been addressed.
 
           Conflicts:
           \`\`\`shell
           ${CONFLICT_LIST}
           \`\`\`
-
-          - [ ] Conflicts resolved
         END
           )
         else
-          echo "has-conflicts=false" >> $GITHUB_OUTPUT
+          echo "has-conflicts=false" >> "$GITHUB_OUTPUT"
           PR_BODY="#${ORIGINAL_PULL_REQUEST_NUMBER}"
         fi
 
         git push -u origin ${BACKPORT_BRANCH}
 
-        BACKPORT_PR_URL=$(gh pr create --base "${TARGET_BRANCH}" --head "${BACKPORT_BRANCH}" --label "was-backported" --assignee "${{ github.event.pull_request.user.login }}" --title "🤖 backported \"${ORIGINAL_TITLE}\"" --body "${PR_BODY}")
+        PR_ARGS=(--base "${TARGET_BRANCH}" --head "${BACKPORT_BRANCH}" --label "was-backported" --assignee "${{ github.event.pull_request.user.login }}" --title "🤖 v${TARGET_VERSION} backported \"${ORIGINAL_TITLE}\"" --body "${PR_BODY}")
+        if [ "$CONFLICTS" -gt 0 ]; then
+          PR_ARGS+=(--draft)
+        fi
+
+        BACKPORT_PR_URL=$(gh pr create "${PR_ARGS[@]}")
         BACKPORT_PR_NUMBER=${BACKPORT_PR_URL##*/}
 
-        echo "backport_pr_number=$BACKPORT_PR_NUMBER" >> $GITHUB_OUTPUT
+        echo "backport_pr_number=$BACKPORT_PR_NUMBER" >> "$GITHUB_OUTPUT"
         echo "New PR has been created: #${BACKPORT_PR_NUMBER}"
 
         git checkout ${{ github.sha }}
 
-    - name: Auto approve backport PR
+    - name: Approve and Merge the PR
       if: ${{ steps.create_backport_pull_request.outputs.has-conflicts == 'false' }}
-      uses: juliangruber/approve-pull-request-action@68fcc9a5a73b5641cadf757cf99d73720dcb05d0 # v2.1.0
-      with:
-        github-token: ${{ inputs.github-token-2 }}
-        number: ${{ steps.create_backport_pull_request.outputs.backport_pr_number }}
-
-    - name: Enable Pull Request Automerge
-      if: ${{ steps.create_backport_pull_request.outputs.has-conflicts == 'false' }}
-      run: gh pr merge --squash --auto "$PR_NUMBER"
+      run: |
+        gh pr review --approve "$PR_NUMBER"
+        gh pr merge --squash --auto "$PR_NUMBER"
       shell: bash
       env:
-        GH_TOKEN: ${{ inputs.github-token }}
+        # uses a different token than the token that created the PR so we can approve and merge it
+        GH_TOKEN: ${{ inputs.github-token-2 }}
         PR_NUMBER: ${{ steps.create_backport_pull_request.outputs.backport_pr_number }}
 
     - uses: ./.github/actions/notify-pull-request

.github/actions/create-backport/create-backport-test.sh

@@ -0,0 +1,375 @@
+#!/usr/bin/env bash
+
+set -euo pipefail
+
+action_dir=$(cd "$(dirname "$0")" && pwd)
+cut_release_workflow="$action_dir/../../workflows/cut-release-branch.yml"
+
+# shellcheck source=.github/actions/create-backport/kondo-ratchets.sh
+source "$action_dir/kondo-ratchets.sh"
+
+# Any editor launch fails the run, so a continuation that waits on an editor cannot pass.
+export GIT_EDITOR=false
+
+test_root=
+trap '[ -z "$test_root" ] || rm -rf -- "$test_root"' EXIT
+trap 'exit 129' HUP
+trap 'exit 130' INT
+trap 'exit 143' TERM
+test_root=$(mktemp -d)
+
+active_ratchets='{:ignore-counts {:example 1}}'
+disabled_ratchets=';; Kondo ignore ratchets apply only to master; this release branch opts out.
+;; The test and fixer recognize this explicit opt-out.
+{:disabled true}'
+
+# Coverage:
+#
+# Target state       Incoming change       Other conflict   Expected result
+# -----------------  --------------------  ---------------  ------------------------------------------
+# active ratchets    unrelated file        none             leave ratchets unchanged
+# active ratchets    ratchets              none             install the release opt-out
+# disabled ratchets  ratchets              none             keep the opt-out; finish with an empty commit
+# divergent ratchets ratchets              none             resolve ratchets and finish the cherry-pick
+# divergent ratchets ratchets (on a pty)   none             finish without opening an editor
+# active ratchets    unrelated file        app.txt          leave the conflict for manual resolution
+# divergent ratchets ratchets + app.txt    app.txt          resolve only ratchets
+# release cut        ratchets              none             cut and backport commit the same opt-out
+# n/a                cut-release workflow  n/a              the workflow calls the shared writer
+# any                invalid commit        n/a              propagate the cherry-pick failure
+# divergent ratchets generated backport.sh app.txt          resolve only ratchets through the manual script
+#
+# Known gaps: an older target with no ratchets file, and an incoming commit that
+# deletes the ratchets file.
+
+test_unrelated_backport_preserves_target_ratchets() (
+  local repo="$test_root/unrelated"
+  init_repo "$repo"
+  local commit
+  commit=$(feature_commit "$repo" change_app)
+  git -C "$repo" checkout -q release
+
+  cd "$repo"
+  cherry_pick_backport "$commit"
+
+  assert_eq feature "$(cat app.txt)" "the unrelated change was not cherry-picked"
+  assert_ratchets "$active_ratchets"
+  assert_cherry_pick_completed
+  assert_worktree_clean
+)
+
+test_clean_ratchet_backport_installs_release_opt_out() (
+  local repo="$test_root/clean-ratchet"
+  init_repo "$repo"
+  local commit
+  commit=$(feature_commit "$repo" change_ratchets)
+  git -C "$repo" checkout -q release
+
+  cd "$repo"
+  cherry_pick_backport "$commit"
+
+  assert_ratchets_disabled
+  assert_cherry_pick_completed
+  assert_worktree_clean
+)
+
+test_disabled_release_absorbs_ratchet_only_backport() (
+  local repo="$test_root/disabled-release"
+  init_repo "$repo"
+  local commit
+  commit=$(feature_commit "$repo" change_ratchets)
+  git -C "$repo" checkout -q release
+  commit_release_change "$repo" disable_release_ratchets "Disable release ratchets"
+
+  cd "$repo"
+  cherry_pick_backport "$commit"
+
+  assert_ratchets_disabled
+  assert_cherry_pick_completed
+  assert_empty_commit
+  assert_worktree_clean
+)
+
+test_ratchet_only_conflict_is_resolved() (
+  local repo="$test_root/ratchet-conflict"
+  init_repo "$repo"
+  local commit
+  commit=$(conflicting_ratchet_commit "$repo")
+
+  cd "$repo"
+  cherry_pick_backport "$commit"
+
+  assert_ratchets_disabled
+  assert_cherry_pick_completed
+  assert_worktree_clean
+)
+
+test_continuation_never_opens_an_editor() (
+  local repo="$test_root/editor"
+  init_repo "$repo"
+  local commit
+  commit=$(conflicting_ratchet_commit "$repo")
+
+  cd "$repo"
+  # Git only opens an editor for the continuation when stdin is a terminal, so run it on a pty. The
+  # exported GIT_EDITOR=false turns any editor launch into a failure. The single quotes are deliberate:
+  # $1 and $2 are for the inner bash, not this shell.
+  # shellcheck disable=SC2016
+  python3 -c 'import os, pty, sys; sys.exit(os.waitstatus_to_exitcode(pty.spawn(sys.argv[1:])))' \
+    bash -c 'source "$1/kondo-ratchets.sh" && cherry_pick_backport "$2"' bash "$action_dir" "$commit" >/dev/null ||
+    fail "the cherry-pick continuation opened an editor"
+
+  assert_ratchets_disabled
+  assert_cherry_pick_completed
+)
+
+test_non_ratchet_conflict_remains_manual() (
+  local repo="$test_root/non-ratchet-conflict"
+  init_repo "$repo"
+  local commit
+  commit=$(feature_commit "$repo" change_app)
+  git -C "$repo" checkout -q release
+  commit_release_change "$repo" change_release_app "Change release app"
+
+  cd "$repo"
+  cherry_pick_backport "$commit"
+
+  assert_ratchets "$active_ratchets"
+  assert_only_conflicts app.txt
+  assert_cherry_pick_pending
+)
+
+test_mixed_conflict_resolves_only_ratchets() (
+  local repo="$test_root/mixed-conflict"
+  init_repo "$repo"
+  local commit
+  commit=$(feature_commit "$repo" change_app_and_ratchets)
+  git -C "$repo" checkout -q release
+  commit_release_change "$repo" change_release_app_and_ratchets "Change release app and ratchets"
+
+  cd "$repo"
+  cherry_pick_backport "$commit"
+
+  assert_ratchets_disabled
+  assert_only_conflicts app.txt
+  assert_cherry_pick_pending
+)
+
+test_release_cut_and_backport_commit_the_same_opt_out() (
+  local cut_repo="$test_root/release-cut"
+  init_repo "$cut_repo"
+  cd "$cut_repo"
+  git checkout -qb release-x.99.x
+  write_disabled_ratchets
+  git add --sparse .clj-kondo/ratchets.edn
+  git commit -q --allow-empty --no-verify -m "Cut release-x.99.x branch"
+  git show HEAD:.clj-kondo/ratchets.edn > "$test_root/release-cut.edn"
+
+  local backport_repo="$test_root/release-cut-backport"
+  init_repo "$backport_repo"
+  local commit
+  commit=$(feature_commit "$backport_repo" change_ratchets)
+  git -C "$backport_repo" checkout -q release
+  cd "$backport_repo"
+  cherry_pick_backport "$commit"
+  git show HEAD:.clj-kondo/ratchets.edn > "$test_root/backport.edn"
+
+  cmp -s "$test_root/release-cut.edn" "$test_root/backport.edn" ||
+    fail "the release cut and the backport committed different opt-out files"
+  assert_eq "$disabled_ratchets" "$(cat "$test_root/release-cut.edn")" \
+    "the release cut did not install the expected opt-out"
+)
+
+test_cut_release_workflow_uses_the_shared_writer() (
+  grep -Fq 'source .github/actions/create-backport/kondo-ratchets.sh' "$cut_release_workflow" ||
+    fail "the cut-release workflow does not source kondo-ratchets.sh"
+  grep -Fq 'write_disabled_ratchets' "$cut_release_workflow" ||
+    fail "the cut-release workflow does not call write_disabled_ratchets"
+  ! grep -Fq ':disabled' "$cut_release_workflow" ||
+    fail "the cut-release workflow carries its own copy of the opt-out"
+)
+
+test_invalid_commit_failure_is_propagated() (
+  local repo="$test_root/invalid"
+  init_repo "$repo"
+  cd "$repo"
+
+  if cherry_pick_backport deadbeef; then
+    fail "an invalid commit succeeded"
+  fi
+)
+
+test_generated_script_resolves_ratchets_end_to_end() (
+  local repo="$test_root/generated-script"
+  init_repo "$repo"
+  local commit
+  commit=$(feature_commit "$repo" change_app_and_ratchets)
+  git -C "$repo" checkout -q release
+  commit_release_change "$repo" change_release_app_and_ratchets "Change release app and ratchets"
+
+  cd "$repo"
+  cherry_pick_backport "$commit"
+  git cherry-pick --abort
+
+  local release_commit
+  release_commit=$(git rev-parse HEAD)
+  write_backport_script "$commit"
+  chmod +x backport.sh
+  git add backport.sh
+  git commit -qm "Add manual backport script"
+
+  bash -n backport.sh
+  grep -Fq 'write_disabled_ratchets ()' backport.sh || fail "the generated script omitted write_disabled_ratchets"
+  ./backport.sh
+
+  assert_ratchets_disabled
+  assert_only_conflicts app.txt
+  assert_cherry_pick_pending
+  assert_eq "$release_commit" "$(git rev-parse HEAD)" "the generated script did not return HEAD to the release commit"
+  [ ! -e backport.sh ] || fail "the generated script did not remove itself"
+  ! git ls-files --error-unmatch backport.sh >/dev/null 2>&1 || fail "the generated script is still tracked"
+  ! git status --porcelain | grep -q backport.sh || fail "the generated script left a status entry"
+)
+
+# Test harness
+
+fail() {
+  echo "FAIL: $*" >&2
+  exit 1
+}
+
+assert_eq() {
+  local expected=$1
+  local actual=$2
+  local message=$3
+  [ "$expected" = "$actual" ] || fail "$message (expected '$expected', got '$actual')"
+}
+
+assert_ratchets() {
+  assert_eq "$1" "$(cat .clj-kondo/ratchets.edn)" "unexpected ratchet state"
+}
+
+assert_ratchets_disabled() {
+  assert_ratchets "$disabled_ratchets"
+}
+
+assert_cherry_pick_completed() {
+  ! git rev-parse -q --verify CHERRY_PICK_HEAD >/dev/null || fail "the cherry-pick is still pending"
+}
+
+assert_cherry_pick_pending() {
+  git rev-parse -q --verify CHERRY_PICK_HEAD >/dev/null || fail "the cherry-pick state was lost"
+}
+
+assert_only_conflicts() {
+  local expected
+  local actual
+  expected=$(printf '%s\n' "$@" | sort)
+  actual=$(git diff --name-only --diff-filter=U | sort)
+  assert_eq "$expected" "$actual" "unexpected unresolved files"
+}
+
+assert_empty_commit() {
+  git diff --quiet HEAD^ HEAD || fail "the backport commit was not empty"
+}
+
+assert_worktree_clean() {
+  [ -z "$(git status --porcelain)" ] || fail "the backport left worktree changes"
+}
+
+init_repo() {
+  local repo=$1
+  git init -q -b release "$repo"
+  git -C "$repo" config user.email test@example.com
+  git -C "$repo" config user.name "Backport test"
+  printf 'base\n' > "$repo/app.txt"
+  mkdir -p "$repo/.clj-kondo"
+  printf '%s\n' "$active_ratchets" > "$repo/.clj-kondo/ratchets.edn"
+  git -C "$repo" add .
+  git -C "$repo" commit -qm "Base"
+}
+
+feature_commit() {
+  local repo=$1
+  shift
+  git -C "$repo" checkout -qb feature
+  "$@" "$repo"
+  git -C "$repo" add .
+  git -C "$repo" commit -qm "Feature"
+  git -C "$repo" rev-parse HEAD
+}
+
+# Sets up a release branch whose ratchets conflict with the feature commit, and prints that commit.
+conflicting_ratchet_commit() {
+  local repo=$1
+  local commit
+  commit=$(feature_commit "$repo" change_ratchets)
+  git -C "$repo" checkout -q release
+  commit_release_change "$repo" change_release_ratchets "Change release ratchets"
+  echo "$commit"
+}
+
+change_app() {
+  printf 'feature\n' > "$1/app.txt"
+}
+
+change_ratchets() {
+  printf '{:ignore-counts {:example 2}}\n' > "$1/.clj-kondo/ratchets.edn"
+}
+
+change_app_and_ratchets() {
+  change_app "$1"
+  change_ratchets "$1"
+}
+
+change_release_app() {
+  printf 'release\n' > "$1/app.txt"
+}
+
+change_release_ratchets() {
+  printf '{:ignore-counts {:release 1}}\n' > "$1/.clj-kondo/ratchets.edn"
+}
+
+change_release_app_and_ratchets() {
+  change_release_app "$1"
+  change_release_ratchets "$1"
+}
+
+# Setup writes the opt-out through the shared writer; the only copy is the expected text at the top.
+disable_release_ratchets() {
+  (cd "$1" && write_disabled_ratchets)
+}
+
+commit_release_change() {
+  local repo=$1
+  local change=$2
+  local message=$3
+  "$change" "$repo"
+  git -C "$repo" add .
+  git -C "$repo" commit -qm "$message"
+}
+
+run_test() {
+  local description=$1
+  local test=${description// /_}
+  test=${test//-/_}
+  test="test_$test"
+
+  declare -F "$test" >/dev/null || fail "missing test function: $test"
+
+  printf 'TEST: %s\n' "$description"
+  "$test"
+  printf 'PASS: %s\n' "$description"
+}
+
+run_test "unrelated backport preserves target ratchets"
+run_test "clean ratchet backport installs release opt-out"
+run_test "disabled release absorbs ratchet-only backport"
+run_test "ratchet-only conflict is resolved"
+run_test "continuation never opens an editor"
+run_test "non-ratchet conflict remains manual"
+run_test "mixed conflict resolves only ratchets"
+run_test "release cut and backport commit the same opt-out"
+run_test "cut-release workflow uses the shared writer"
+run_test "invalid commit failure is propagated"
+run_test "generated script resolves ratchets end-to-end"

.github/actions/create-backport/kondo-ratchets.sh

@@ -0,0 +1,74 @@
+#!/usr/bin/env bash
+
+set -euo pipefail
+
+# The only place that knows what a release branch's opt-out looks like. The cut-release workflow, the
+# backport helper, and the tests all go through this function.
+write_disabled_ratchets() {
+  mkdir -p .clj-kondo
+  printf '%s\n' \
+    ';; Kondo ignore ratchets apply only to master; this release branch opts out.' \
+    ';; The test and fixer recognize this explicit opt-out.' \
+    '{:disabled true}' \
+    > .clj-kondo/ratchets.edn
+}
+
+disable_ratchets() {
+  local commit=$1
+  local file=.clj-kondo/ratchets.edn
+  [ -n "$(git diff-tree --root --no-commit-id --name-only -r "$commit" -- "$file")" ] || return 0
+
+  echo "$file: disabling kondo ratchets on the release branch"
+  write_disabled_ratchets
+  git add -- "$file"
+
+  if ! git rev-parse -q --verify CHERRY_PICK_HEAD >/dev/null; then
+    if ! git diff --cached --quiet HEAD; then
+      git commit --amend --no-edit
+    fi
+    return 0
+  fi
+
+  if [ -z "$(git ls-files -u)" ]; then
+    echo "$file was the only conflict, finishing the cherry-pick"
+    if git diff --cached --quiet HEAD; then
+      echo "nothing left to apply, committing the backport empty"
+      git commit --allow-empty --no-edit
+    else
+      # GIT_EDITOR outranks core.editor, VISUAL, and EDITOR, so the continuation can never wait on
+      # an editor; the repository's own editor configuration is left alone.
+      GIT_EDITOR=true git cherry-pick --continue
+    fi
+  fi
+}
+
+cherry_pick_backport() {
+  local commit=$1
+  local status=0
+  git cherry-pick "$commit" || status=$?
+  if [ "$status" -ne 0 ] && ! git rev-parse -q --verify CHERRY_PICK_HEAD >/dev/null; then
+    echo "cherry-pick failed without entering a resolvable conflict state" >&2
+    return "$status"
+  fi
+
+  disable_ratchets "$commit"
+  if [ "$status" -ne 0 ] &&
+     git rev-parse -q --verify CHERRY_PICK_HEAD >/dev/null &&
+     [ -z "$(git ls-files -u)" ]; then
+    echo "cherry-pick stopped without a file conflict to resolve" >&2
+    return "$status"
+  fi
+}
+
+write_backport_script() {
+  local commit=$1
+  {
+    echo "#!/usr/bin/env bash"
+    echo "set -euo pipefail"
+    echo "git reset HEAD~1"
+    echo "rm ./backport.sh"
+    declare -f write_disabled_ratchets disable_ratchets cherry_pick_backport
+    printf 'cherry_pick_backport %q\n' "$commit"
+    printf '%s\n' "printf 'Resolve conflicts and force push this branch.\\n\\nTo backport translations run: bin/i18n/merge-translations <release-branch>\\n'"
+  } > ./backport.sh
+}

.github/actions/create-test-plan/action.yml

@@ -1,5 +1,5 @@
 name: Create test plan
-description: Cruise the frontend import graph and compute the affected-tests plan.
+description: Compute the affected-tests plan for the changed files.
 
 inputs:
   changed-files:
@@ -28,21 +28,15 @@ outputs:
   stats:
     description: FE Affected Tests stats row (JSON).
     value: ${{ steps.compute.outputs.stats }}
-  fe_unit_specs_to_run:
-    description: Unit specs to run (JSON array).
-    value: ${{ steps.compute.outputs.fe_unit_specs_to_run }}
-  loki_stories_to_run:
-    description: Loki stories to run (JSON array).
-    value: ${{ steps.compute.outputs.loki_stories_to_run }}
-  e2e_specs_to_run:
-    description: E2E specs to run (JSON array).
-    value: ${{ steps.compute.outputs.e2e_specs_to_run }}
+  artifact-id:
+    description: Artifact containing test-plan.json for this run.
+    value: ${{ steps.upload.outputs.artifact-id }}
 
 runs:
   using: composite
   steps:
-    - name: Prepare Node + Bun
-      uses: ./.github/actions/prepare-node-bun
+    - name: Prepare front-end environment
+      uses: ./.github/actions/prepare-frontend
     - name: Resolve closest-ancestor e2e coverage manifest
       id: manifest
       uses: actions/github-script@v9
@@ -61,16 +55,6 @@ runs:
             headSha: context.payload.pull_request?.head?.sha ?? context.sha,
           });
           core.setOutput("path", result?.path ?? "");
-    - name: Build dependency graph
-      shell: bash
-      run: |
-        # Quiet on success; surface output only if install fails.
-        bun install --frozen-lockfile > /tmp/bun-install.log 2>&1 \
-          || { echo "bun install issues (continuing):"; tail -20 /tmp/bun-install.log; }
-        bunx depcruise frontend/src enterprise/frontend/src \
-          --config .dependency-cruiser.cjs \
-          --output-type json > dependency-graph.json || true
-
     - name: Create test plan
       id: compute
       shell: bash
@@ -82,15 +66,20 @@ runs:
         LOKI_INFRA_TOUCHED: ${{ inputs.loki-infra-touched }}
         E2E_INFRA_TOUCHED: ${{ inputs.e2e-infra-touched }}
         SHARED_SOURCES_TOUCHED: ${{ inputs.shared-sources-touched }}
-        DEP_GRAPH_JSON: dependency-graph.json
         E2E_SPEC_MANIFEST: ${{ steps.manifest.outputs.path }}
       run: |
         # stdout is the plan JSON; the planner's own info logs go to stderr.
+        # The planner writes this step's GITHUB_OUTPUT entries.
         bun .github/scripts/create-test-plan.ts > test-plan.json
-        echo "stats=$(jq -c '.stats' test-plan.json)" >> "$GITHUB_OUTPUT"
-        echo "fe_unit_specs_to_run=$(jq -c '.fe_unit_specs_to_run' test-plan.json)" >> "$GITHUB_OUTPUT"
-        echo "loki_stories_to_run=$(jq -c '.loki_stories_to_run' test-plan.json)" >> "$GITHUB_OUTPUT"
-        echo "e2e_specs_to_run=$(jq -c '.e2e_specs_to_run' test-plan.json)" >> "$GITHUB_OUTPUT"
+
+    - name: Upload test plan
+      id: upload
+      uses: actions/upload-artifact@v7
+      with:
+        name: test-plan-${{ github.run_id }}-${{ github.run_attempt }}
+        path: test-plan.json
+        if-no-files-found: error
+        retention-days: 7
 
     - name: Report test plan
       shell: bash
@@ -110,6 +99,10 @@ runs:
           echo
           echo "Changed: $(jq '.stats.fe_files_changed' "$plan") FE / $(jq '.stats.be_files_changed' "$plan") BE file(s) · $(jq '.stats.fe_modules_affected_usage' "$plan") FE module(s) affected"
           echo
+          if [ "$(jq '.stats.loki_preview_touched' "$plan")" = "true" ]; then
+            echo "**Loki: full run**: a file the Storybook preview imports changed."
+            echo
+          fi
           e2e_run=$(jq '.stats.e2e_specs_to_run_usage' "$plan")
           e2e_all=$(jq '.stats.e2e_specs_all' "$plan")
           if [ "$e2e_run" -eq "$e2e_all" ]; then

.github/actions/cross-branch-migration-test/action.yml

@@ -1,4 +1,7 @@
 name: Cross-branch migration test
+description: >-
+  Boot Metabase on the base branch to migrate the app db, then boot the PR branch against the
+  same db, verifying the PR's migrations apply cleanly on top of the base branch's schema.
 
 inputs:
   base-ref: ## Base branch PR came from

.github/actions/e2e-prepare-containers/action.yml

@@ -15,6 +15,10 @@ inputs:
     description: OpenLDAP container
     required: true
     default: false
+  mocksaml:
+    description: Mock SAML container
+    required: true
+    default: false
   postgres:
     description: Postgres container
     required: true
@@ -73,6 +77,7 @@ runs:
         [ "${{ inputs.mongo }}" = true ] && SERVICES+=(mongo-sample)
         [ "${{ inputs.maildev }}" = true ] && SERVICES+=(maildev maildev-ssl)
         [ "${{ inputs.openldap }}" = true ] && SERVICES+=(ldap)
+        [ "${{ inputs.mocksaml }}" = true ] && SERVICES+=(saml-idp)
         [ "${{ inputs.webhook }}" = true ] && SERVICES+=(webhook-tester)
         [ "${{ inputs.snowplow }}" = true ] && SERVICES+=(snowplow-micro)
 
@@ -93,8 +98,8 @@ runs:
 
         if ${{ inputs.maildev }}; then
           echo -e "${Y}checking maildev container..." &&
-          while ! nc -z localhost 1080; do sleep 1; done &&
-          while ! nc -z localhost 1025; do sleep 1; done &&
+          while ! nc -z localhost 1180; do sleep 1; done &&
+          while ! nc -z localhost 1125; do sleep 1; done &&
           echo -e "${G}Maildev is up and running!"
 
           echo -e "${Y}checking maildev-ssl container..." &&
@@ -109,6 +114,12 @@ runs:
           echo -e "${G}Openldap is up and running!"
         fi
 
+        if ${{ inputs.mocksaml }}; then
+          echo -e "${Y}checking mock saml container..." &&
+          while ! nc -z localhost 8090; do sleep 1; done &&
+          echo -e "${G}Mock SAML is up and running!"
+        fi
+
         if ${{ inputs.postgres }}; then
           echo -e "${Y}checking postgres container..." &&
           while ! nc -z localhost 5404; do sleep 1; done &&

.github/actions/fetch-artifact/action.yml

@@ -20,6 +20,15 @@ inputs:
     description: Directory path where the jar should be extracted (defaults to current directory)
     required: false
     default: "."
+  download:
+    description: Default is true. Set to false to only look the artifact up and report `fetch-hit`.
+    required: false
+    default: "true"
+
+outputs:
+  fetch-hit:
+    description: Boolean indicating if an artifact was successfully found and downloaded.
+    value: ${{ steps.find_release_artifact.outputs.fetch-hit }}
 
 runs:
   using: "composite"
@@ -28,11 +37,12 @@ runs:
       id: find_release_artifact
       uses: actions/github-script@v9
       with:
-        result-encoding: string
         script: | # js
           const fs = require('fs');
 
           const isRelease = "${{ inputs.release }}" === "true";
+          const failOnMiss = "${{ inputs.fail-on-fetch-miss }}" !== "false";
+          const shouldDownload = "${{ inputs.download }}" !== "false";
           const prefix = isRelease ? "metabase-release" : "metabase";
           const artifactName = `${prefix}-${{ inputs.edition }}-${{ inputs.commit }}-uberjar`;
           console.log(`Looking for artifact: ${artifactName}`);
@@ -44,12 +54,18 @@ runs:
             per_page: 1,
           });
 
-          if (!artifacts.data?.artifacts?.[0]?.id) {
-            core.setFailed(`No artifacts found for ${artifactName}`);
-            return;
+          const artifact_id = artifacts.data?.artifacts?.[0]?.id;
+
+          if (!artifact_id) {
+            core.setOutput('fetch-hit', 'false');
+          } else {
+            core.setOutput('fetch-hit', 'true');
           }
 
-          const artifact_id = artifacts.data.artifacts[0].id;
+          if (!shouldDownload) {
+            console.log(`skipping download (download: false)`);
+            return;
+          }
 
           let download;
           const maxAttempts = 3;
@@ -74,6 +90,7 @@ runs:
           fs.writeFileSync(`${process.env.GITHUB_WORKSPACE}/mb.zip`, Buffer.from(download.data));
 
     - name: Extract and rename JAR
+      if: ${{ steps.find_release_artifact.outputs.fetch-hit == 'true' && inputs.download != 'false' }}
       shell: bash
       run: | # bash
         OUTPUT_NAME="${{ inputs.output-name }}"
@@ -113,18 +130,20 @@ runs:
 
         # Set the JAR_PATH environment variable
         if [ "$EXTRACT_PATH" == "." ]; then
-          echo "JAR_PATH=$OUTPUT_NAME" >> $GITHUB_ENV
+          echo "JAR_PATH=$OUTPUT_NAME" >> "$GITHUB_ENV"
         else
-          echo "JAR_PATH=$EXTRACT_PATH/$OUTPUT_NAME" >> $GITHUB_ENV
+          echo "JAR_PATH=$EXTRACT_PATH/$OUTPUT_NAME" >> "$GITHUB_ENV"
         fi
 
     - name: Verify that this is a valid JAR file
+      if: ${{ steps.find_release_artifact.outputs.fetch-hit == 'true' && inputs.download != 'false' }}
       shell: bash
       run: |
         echo "Verifying JAR at: $JAR_PATH"
         file --mime-type "$JAR_PATH"
 
     - name: Reveal its version.properties
+      if: ${{ steps.find_release_artifact.outputs.fetch-hit == 'true' && inputs.download != 'false' }}
       shell: bash
       run: |
         echo "Extracting version.properties from: $JAR_PATH"

.github/actions/find-squashed-commit/action.yml

@@ -22,7 +22,7 @@ runs:
         COMMIT=$(env -i git log $BASE_REF --grep="(#$PULL_REQUEST_NUMBER)" --format="%H")
         echo "commit SHA $COMMIT"
 
-        echo "commit=$COMMIT" >> $GITHUB_OUTPUT
+        echo "commit=$COMMIT" >> "$GITHUB_OUTPUT"
       id: find-squashed-commit
       shell: bash
       env:

.github/actions/get-cache-keys/action.yml

@@ -1,45 +0,0 @@
-name: Get cache keys
-description: |
-  Get deterministic cache keys for Maven and Node.js caches based on the centrally controlled cache prefix,
-  and the suffix based on the runner OS and the current week of the year.
-
-outputs:
-  m2-cache-key:
-    description: "The cache key for the Maven cache."
-    value: ${{ steps.keys-factory.outputs.m2-cache-key }}
-  m2-restore-key:
-    description: "The fallback restore key prefix for the Maven cache."
-    value: ${{ steps.keys-factory.outputs.m2-restore-key }}
-  node-cache-key:
-    description: "The cache key for the Node.js cache."
-    value: ${{ steps.keys-factory.outputs.node-cache-key }}
-  node-restore-key:
-    description: "The fallback restore key prefix for the Node.js cache."
-    value: ${{ steps.keys-factory.outputs.node-restore-key }}
-  eslint-cache-key:
-    description: "The cache key for Eslint cache"
-    value: ${{ steps.keys-factory.outputs.eslint-cache-key }}
-  cypress-cache-key:
-    description: "The cache key for Cypress cache"
-    value: ${{ steps.keys-factory.outputs.cypress-cache-key }}
-
-runs:
-  using: "composite"
-  steps:
-    - name: Generate and output cache keys
-      id: keys-factory
-      run: |
-        M2_CACHE_PREFIX='M2'
-        NODE_CACHE_PREFIX='node-modules'
-        ESLINT_CACHE_PREFIX='eslint'
-        CYPRESS_CACHE_PREFIX='cypress'
-        WEEK_OF_YEAR=$(/bin/date "+%G-%V")
-        CACHE_SUFFIX="${{ runner.os }}-$WEEK_OF_YEAR"
-
-        echo "m2-cache-key=$M2_CACHE_PREFIX-$CACHE_SUFFIX" >> $GITHUB_OUTPUT
-        echo "m2-restore-key=$M2_CACHE_PREFIX-" >> $GITHUB_OUTPUT
-        echo "node-cache-key=$NODE_CACHE_PREFIX-$CACHE_SUFFIX" >> $GITHUB_OUTPUT
-        echo "node-restore-key=$NODE_CACHE_PREFIX-" >> $GITHUB_OUTPUT
-        echo "eslint-cache-key=$ESLINT_CACHE_PREFIX-$CACHE_SUFFIX" >> $GITHUB_OUTPUT
-        echo "cypress-cache-key=$CYPRESS_CACHE_PREFIX-$CACHE_SUFFIX" >> $GITHUB_OUTPUT
-      shell: bash

.github/actions/get-docker-info/action.yml

@@ -1,7 +1,19 @@
 name: Get Docker Info
-description: Determines Docker repository and tag based on branch and edition
+description: Determines the registry, repository, and tag a container image is pushed to.
 
 inputs:
+  registry:
+    description: Registry the image is pushed to, either "docker" or "ecr".
+    required: false
+    default: docker
+  repo:
+    description: Repository name, e.g. "metabase-enterprise". Overrides a branch derived repo.
+    required: false
+    default: ''
+  tag:
+    description:  Image tag, e.g. v1.87.2. Overrides a branch derived tag.
+    required: false
+    default: ''
   branch:
     description: Branch name (defaults to current branch)
     required: false
@@ -10,14 +22,22 @@ inputs:
     description: Edition (ee or oss)
     required: false
     default: ee
-  owner:
-    description: Repository owner (defaults to current repo owner)
+  aws-account-id:
+    description: AWS account id hosting the ECR registry. Required for the ecr registry.
     required: false
-    default: ${{ github.repository_owner }}
+    default: ''
+  aws-region:
+    description: Region of the ECR registry.
+    required: false
+    default: us-east-1
+  dockerhub-owner:
+    description: DockerHub owner.
+    required: false
+    default: metabase
 
 outputs:
   repo:
-    description: Docker repository name
+    description: Docker repository, including the registry host (ecr) or the owner (docker)
     value: ${{ steps.docker-info.outputs.repo }}
   tag:
     description: Docker tag
@@ -25,9 +45,6 @@ outputs:
   full_image:
     description: Full Docker image name (repo:tag)
     value: ${{ steps.docker-info.outputs.full_image }}
-  editions:
-    description: JSON array of editions to build
-    value: ${{ steps.docker-info.outputs.editions }}
 
 runs:
   using: "composite"
@@ -35,40 +52,49 @@ runs:
     - name: Determine Docker info
       id: docker-info
       uses: actions/github-script@v9
+      env:
+        REGISTRY: ${{ inputs.registry }}
+        REPO: ${{ inputs.repo }}
+        TAG: ${{ inputs.tag }}
+        BRANCH: ${{ inputs.branch }}
+        EDITION: ${{ inputs.edition }}
+        AWS_ACCOUNT_ID: ${{ inputs.aws-account-id }}
+        AWS_REGION: ${{ inputs.aws-region }}
+        DOCKERHUB_OWNER: ${{ inputs.dockerhub-owner }}
       with:
         script: | # js
-          const branch = '${{ inputs.branch }}';
-          const edition = '${{ inputs.edition }}';
-          const owner = '${{ inputs.owner }}';
+          const { REGISTRY, OWNER, BRANCH, EDITION, AWS_ACCOUNT_ID, AWS_REGION, DOCKERHUB_OWNER } = process.env;
 
-          console.log(`Determining Docker info for branch: ${branch}, edition: ${edition}`);
-
-          let repo, tag, editions;
-
-          if (branch === 'master') {
-            // Master builds both editions with specific repos
-            editions = ['ee', 'oss'];
-            tag = 'latest';
-
-            if (edition === 'ee') {
-              repo = `${owner}/metabase-enterprise-head`;
-            } else {
-              repo = `${owner}/metabase-head`;
-            }
-          } else {
-            // All other branches only build EE to metabase-dev
-            editions = ['ee'];
-            tag = branch.replaceAll('/', '-'); // slashes make docker sad
-            repo = `${owner}/metabase-dev`;
+          let tag = process.env.TAG;
+          if (!tag) {
+            tag = BRANCH === 'master' ? 'latest' : `${BRANCH.replaceAll('/', '-')}-${EDITION}`;
           }
 
-          const fullImage = `${repo}:${tag}`;
+          let name = process.env.REPO;
+          if (!name) {
+            if (BRANCH === 'master') {
+              name = EDITION === 'ee' ? 'metabase-enterprise-head' : 'metabase-head';
+            } else {
+              name = 'metabase-dev';
+            }
+          }
+
+          let repo;
+          if (REGISTRY === 'ecr') {
+            if (!AWS_ACCOUNT_ID) {
+              core.setFailed('Pushing to AWS ECR requires aws-account-id to be set.');
+              return;
+            }
+            repo = `${AWS_ACCOUNT_ID}.dkr.ecr.${AWS_REGION}.amazonaws.com/${name}`;
+          } else if (REGISTRY === 'docker') {
+            repo = `${DOCKERHUB_OWNER}/${name}`;
+          } else {
+            core.setFailed(`Unknown registry "${REGISTRY}", expected "docker" or "ecr".`);
+            return;
+          }
 
-          // Set outputs
           core.setOutput('repo', repo);
           core.setOutput('tag', tag);
-          core.setOutput('full_image', fullImage);
-          core.setOutput('editions', JSON.stringify(editions));
+          core.setOutput('full_image', `${repo}:${tag}`);
 
-          console.log(`Docker image: ${fullImage}`);
-          console.log(`Editions: ${JSON.stringify(editions)}`);
+          console.log(`Resolved: registry = ${REGISTRY}, repo = ${repo}, tag = ${tag}`);

.github/actions/notify-pull-request/action.yml

@@ -1,12 +1,11 @@
 name: Notify Pull Request
+description: Post a comment on the pull request, optionally replacing the previous one with the same message.
 inputs:
   remove-previous-comment:
     required: false
-    type: boolean
     default: false
   add-new-comment:
     required: false
-    type: boolean
     default: true
   message:
     required: true

.github/actions/prepare-backend/action.yml

@@ -5,9 +5,6 @@ inputs:
   java-version:
     required: true
     default: "25"
-  clojure-version:
-    required: true
-    default: "1.12.0.1488"
 
 runs:
   using: "composite"
@@ -17,12 +14,40 @@ runs:
       with:
         java-version: ${{ inputs.java-version }}
         distribution: "temurin"
+    - name: Cache spec
+      id: cache-spec
+      shell: bash
+      run: .github/scripts/cache-keys.sh | tee -a "$GITHUB_OUTPUT"
+
+    - name: Restore Clojure CLI
+      uses: actions/cache/restore@v5
+      with:
+        path: ${{ steps.cache-spec.outputs.clojure-path }}
+        key: ${{ steps.cache-spec.outputs.clojure-key }}
+
     - name: Install Clojure CLI
       shell: bash
+      env:
+        CLOJURE_PREFIX: ${{ steps.cache-spec.outputs.clojure-path }}
+        CLOJURE_VERSION: ${{ steps.cache-spec.outputs.clojure-version }}
       run: |
+        set -uo pipefail
+        echo "$CLOJURE_PREFIX/bin" >> "$GITHUB_PATH"
+        export PATH="$CLOJURE_PREFIX/bin:$PATH"
+
+        # Whether the prefix already holds the right install is decided by running it, not by the
+        # cache-hit flag. The installer bakes the prefix into the clj/clojure shims, so a tree restored
+        # under a different $HOME points at a directory that is not there; and on a runner that is not
+        # ephemeral, a previous version's prefix outlives the cache entry that stopped matching it.
+        if clojure --version | grep -qF "$CLOJURE_VERSION"; then
+          clojure --version
+          exit 0
+        fi
+
+        cd "$RUNNER_TEMP"
         for attempt in 1 2 3; do
-          curl --retry 3 --retry-delay 5 --fail -O https://download.clojure.org/install/linux-install-${{ inputs.clojure-version }}.sh \
-            && sudo bash ./linux-install-${{ inputs.clojure-version }}.sh \
+          curl --retry 3 --retry-delay 5 --fail -O "https://download.clojure.org/install/linux-install-$CLOJURE_VERSION.sh" \
+            && bash "./linux-install-$CLOJURE_VERSION.sh" --prefix "$CLOJURE_PREFIX" \
             && break
           echo "::warning::Clojure install attempt $attempt failed, retrying in 10s..."
           sleep 10
@@ -32,10 +57,6 @@ runs:
           exit 1
         fi
 
-    - name: Get M2 cache key
-      uses: ./.github/actions/get-cache-keys
-      id: get-cache-keys
-
     - name: Install uv (for Python package installation)
       uses: astral-sh/setup-uv@08807647e7069bb48b6ef5acd8ec9567f424441b # v8.1.0
       with:
@@ -46,9 +67,6 @@ runs:
     - name: Restore M2 cache
       uses: actions/cache/restore@v5
       with:
-        path: |
-          ~/.m2
-          ~/.gitlibs
-        key: ${{ steps.get-cache-keys.outputs.m2-cache-key }}
-        restore-keys: |
-          ${{ steps.get-cache-keys.outputs.m2-restore-key }}
+        path: ${{ steps.cache-spec.outputs.m2-path }}
+        key: ${{ steps.cache-spec.outputs.m2-key }}
+        restore-keys: ${{ steps.cache-spec.outputs.m2-restore-key }}

.github/actions/prepare-cypress/action.yml

@@ -25,15 +25,17 @@ runs:
         chrome-version: 144
       id: setup-chrome
 
-    - name: Get cache keys
-      uses: ./.github/actions/get-cache-keys
-      id: get-cache-keys
+    - name: Cache spec
+      id: cache-spec
+      shell: bash
+      run: .github/scripts/cache-keys.sh | tee -a "$GITHUB_OUTPUT"
 
-    - name: Get Cypress cache
+    - name: Restore Cypress binary
       uses: actions/cache/restore@v5
       with:
-        path: ~/.cache/Cypress
-        key: ${{ steps.get-cache-keys.outputs.cypress-cache-key }}
+        path: ${{ steps.cache-spec.outputs.cypress-path }}
+        key: ${{ steps.cache-spec.outputs.cypress-key }}
+        restore-keys: ${{ steps.cache-spec.outputs.cypress-restore-key }}
 
     - name: Ensure that Cypress executable is ready
       run: |

.github/actions/prepare-frontend/action.yml

@@ -16,43 +16,37 @@ runs:
       with:
         node-version: ${{ inputs.node-version }}
 
-    - name: Get cache keys
-      uses: ./.github/actions/get-cache-keys
-      id: get-cache-keys
-
-    - name: Restore M2 cache
-      uses: actions/cache/restore@v5
-      with:
-        path: |
-          ~/.m2
-          ~/.gitlibs
-        key: ${{ steps.get-cache-keys.outputs.m2-cache-key }}
-        restore-keys: |
-          ${{ steps.get-cache-keys.outputs.m2-restore-key }}
-
-    - name: Get bun cache directory
-      id: bun-cache
-      run: |
-        BUN_CACHE_DIR=$(bun pm cache)
-        echo "Bun cache directory: $BUN_CACHE_DIR"
-        echo "dir=$BUN_CACHE_DIR" >> $GITHUB_OUTPUT
+    - name: Cache spec
+      id: cache-spec
       shell: bash
+      run: .github/scripts/cache-keys.sh | tee -a "$GITHUB_OUTPUT"
 
-    - name: Restore node_modules cache
+    # The spec names the store path rather than discovering it, so that a job can restore the cache
+    # before bun exists. Exported job-wide rather than per-step because every later bun invocation has
+    # to resolve against the same store. Confirm bun agreed: if the variable stopped taking effect, bun
+    # would fill its default directory and the cache would silently save an empty tree.
+    - name: Point bun at the cached store
+      shell: bash
+      env:
+        STORE: ${{ steps.cache-spec.outputs.bun-store-path }}
+      run: |
+        echo "BUN_INSTALL_CACHE_DIR=$STORE" >> "$GITHUB_ENV"
+        ACTUAL=$(BUN_INSTALL_CACHE_DIR="$STORE" bun pm cache)
+        if [ "$ACTUAL" != "$STORE" ]; then
+          echo "::error::bun reports its store at $ACTUAL, not $STORE; BUN_INSTALL_CACHE_DIR is not taking effect"
+          exit 1
+        fi
+
+    - name: Restore bun store
       uses: actions/cache/restore@v5
-      id: node-modules-cache
       with:
-        path: |
-          ${{ steps.bun-cache.outputs.dir }}
-          node_modules
-        key: ${{ steps.get-cache-keys.outputs.node-cache-key }}
-        restore-keys: |
-          ${{ steps.get-cache-keys.outputs.node-restore-key }}
+        path: ${{ steps.cache-spec.outputs.bun-store-path }}
+        key: ${{ steps.cache-spec.outputs.bun-store-key }}
+        restore-keys: ${{ steps.cache-spec.outputs.bun-store-restore-key }}
 
     # postinstall lifecycle hook can be dangerous in CI so we only run it locally (see package.json)
     # If a job wants to patch packages, it does so explicitly in the CI. This setting is opt-out.
-    # For example, we never want to cache node_modules with patches already applied so cache-generator.yml skips that step.
-    - name: Clean install
+    - name: Install front-end dependencies
       run: bun install --frozen-lockfile
       shell: bash
     - name: Patch frontend dependencies

.github/actions/prepare-shoppy-e2e/action.yml

@@ -14,21 +14,6 @@ inputs:
   staging-mb-all-features-token:
     description: "Staging MB all features token"
     required: true
-  shoppy-iam-role:
-    description: "Shoppy IAM role for AWS credentials"
-    required: true
-  shoppy-metabase-app-db-s3-bucket:
-    description: "S3 bucket for Shoppy app DB dump"
-    required: true
-  shoppy-metabase-app-db-s3-key:
-    description: "S3 key for Shoppy app DB dump"
-    required: true
-  shoppy-metabase-app-db-user:
-    description: "Shoppy Metabase app DB user"
-    required: true
-  shoppy-metabase-app-db-database:
-    description: "Shoppy Metabase app DB database"
-    required: true
   metastore-dev-server-url:
     description: "Metastore dev server URL"
     required: true
@@ -88,25 +73,11 @@ runs:
         REPO_URL="https://github.com/metabase/shoppy.git"
         echo "Checking if branch '${SAMPLE_APP_BRANCH_NAME}' exists in ${REPO_URL}..."
         if git ls-remote --exit-code --heads "$REPO_URL" "${SAMPLE_APP_BRANCH_NAME}"; then
-          echo "sample_app_branch_exists=true" >> $GITHUB_OUTPUT
+          echo "sample_app_branch_exists=true" >> "$GITHUB_OUTPUT"
         else
-          echo "sample_app_branch_exists=false" >> $GITHUB_OUTPUT
+          echo "sample_app_branch_exists=false" >> "$GITHUB_OUTPUT"
         fi
 
-    - name: Configure AWS credentials
-      if: ${{ steps.check-sample-app-branch.outputs.sample_app_branch_exists == 'true' }}
-      uses: aws-actions/configure-aws-credentials@d979d5b3a71173a29b74b5b88418bfda9437d885
-      with:
-        role-to-assume: ${{ inputs.shoppy-iam-role }}
-        role-session-name: GitHub_to_AWS_via_FederatedOIDC
-        aws-region: us-east-1
-
-    - name: Download Shoppy's App DB PostgreSQL dump from S3
-      if: ${{ steps.check-sample-app-branch.outputs.sample_app_branch_exists == 'true' }}
-      shell: bash
-      run: |
-        aws s3 cp s3://${{ inputs.shoppy-metabase-app-db-s3-bucket }}/${{ inputs.shoppy-metabase-app-db-s3-key }} ./e2e/tmp/db_dumps/shoppy_metabase_app_db_dump.sql
-
     - name: Prepare and launch Shoppy containers
       if: ${{ steps.check-sample-app-branch.outputs.sample_app_branch_exists == 'true' }}
       shell: bash
@@ -115,8 +86,6 @@ runs:
         SAMPLE_APP_ENVIRONMENT: ${{ inputs.sample-app-environment }}
         CYPRESS_MB_ALL_FEATURES_TOKEN: ${{ inputs.staging-mb-all-features-token }}
         METASTORE_DEV_SERVER_URL: ${{ inputs.metastore-dev-server-url }}
-        METABASE_APP_DB_USER: ${{ inputs.shoppy-metabase-app-db-user }}
-        METABASE_APP_DB: ${{ inputs.shoppy-metabase-app-db-database }}
         SHOPPY_DATADOG_APPLICATION_ID: ${{ inputs.shoppy-datadog-application-id }}
         SHOPPY_DATADOG_CLIENT_TOKEN: ${{ inputs.shoppy-datadog-client-token }}
         SHOPPY_DATADOG_SITE: "us5.datadoghq.com"

.github/actions/prepare-test-selection/action.yml

@@ -0,0 +1,39 @@
+name: Prepare test selection
+description: Download this run's test plan and write the suite's selected test paths.
+
+inputs:
+  suite:
+    description: The suite to select tests for (unit, loki or e2e).
+    required: true
+  test-plan-artifact-id:
+    description: ID of this run's test-plan.json artifact.
+    required: true
+  require-download:
+    description: Fail the step when the test plan download fails, instead of running the full suite.
+    required: false
+    default: "false"
+
+outputs:
+  paths-file:
+    description: JSON file listing the selected test paths, or '' when the suite runs in full.
+    value: ${{ steps.selection.outputs.paths-file }}
+  selection:
+    description: full, narrowed or empty, or '' when the plan is unavailable and the suite runs in full.
+    value: ${{ steps.selection.outputs.selection }}
+
+runs:
+  using: composite
+  steps:
+    - name: Download test plan
+      id: test-plan
+      continue-on-error: ${{ inputs.require-download != 'true' }}
+      uses: actions/download-artifact@v8
+      with:
+        artifact-ids: ${{ inputs.test-plan-artifact-id }}
+        path: ${{ runner.temp }}/test-plan
+    - name: Prepare test selection
+      id: selection
+      shell: bash
+      env:
+        PLAN_DOWNLOADED: ${{ steps.test-plan.outcome }}
+      run: bun .github/scripts/prepare-test-selection.ts "${{ inputs.suite }}"

.github/actions/prepare-uberjar-artifact/action.yml

@@ -1,26 +0,0 @@
-name: Prepare Uberjar Artifact
-description: Prepare and upload Metabase JAR as a GitHub artifact.
-
-inputs:
-  edition:
-    required: false
-    default: "ee"
-    description: Metabase edition (ee or oss)
-
-runs:
-  using: "composite"
-  steps:
-    - name: Mark with the commit hash
-      run: git rev-parse --short HEAD > COMMIT-ID
-      shell: bash
-    - name: Calculate SHA256 checksum
-      run: sha256sum ./target/uberjar/metabase.jar > SHA256.sum
-      shell: bash
-    - name: Upload JARs as artifact
-      uses: actions/upload-artifact@v7
-      with:
-        name: metabase-${{ inputs.edition }}-${{ github.event.pull_request.head.sha || github.sha }}-uberjar
-        path: |
-          ./target/uberjar/metabase.jar
-          ./COMMIT-ID
-          ./SHA256.sum

.github/actions/report-failures-to-ci-conductor/action.yml

@@ -25,6 +25,7 @@ runs:
         TARGET_BRANCH: ${{ github.event.pull_request.base.ref || github.ref_name }}
         CI_CONDUCTOR_TEST_SUITE: ${{ inputs.test-suite }}
         ADAPTER: ${{ inputs.adapter }}
+        IS_RERUN: ${{ github.run_attempt != '1' }}
       # Keep the path constrained to known entrypoints.
       run: |
         case "$ADAPTER" in

.github/actions/sdk-bundle-size-check/action.yml

@@ -1,100 +0,0 @@
-name: Embedding SDK Bundle Size Check
-description: |
-  Measures app + embedding SDK bundle sizes from the current and base-ref
-  uberjars (reusing the builds that already ran) plus their bundle-stats
-  artifacts, and flags changes to the chunked SDK's reachable, gzipped size
-  beyond the threshold. Skips when the base-ref artifacts aren't available
-  rather than rebuilding from source (which would compare across pipelines).
-
-inputs:
-  edition:
-    description: 'Metabase edition (ee or oss)'
-    required: true
-  base-ref-commit:
-    description: 'Commit SHA of the base ref.'
-    required: true
-  threshold-percent:
-    description: 'Percent threshold for bundle size change'
-    required: true
-
-outputs:
-  status:
-    description: "Bundle size status: increased, decreased, or stable"
-    value: ${{ steps.compare.outputs.status }}
-  size_change_percent:
-    description: "size change percent (positive = increase, negative = decrease)"
-    value: ${{ steps.compare.outputs.size_change_percent }}
-
-runs:
-  using: "composite"
-  steps:
-    - name: Download current uberjar
-      uses: ./.github/actions/fetch-artifact
-      with:
-        commit: ${{ github.event.pull_request.head.sha || github.sha }}
-        edition: ${{ inputs.edition }}
-        extract-path: temp/current-uberjar
-    - name: Download base-ref uberjar
-      id: base-jar
-      continue-on-error: true
-      uses: ./.github/actions/fetch-artifact
-      with:
-        commit: ${{ inputs.base-ref-commit }}
-        edition: ${{ inputs.edition }}
-        extract-path: temp/base-uberjar
-    - name: Measure and compare bundle sizes
-      id: compare
-      shell: bash
-      env:
-        GH_TOKEN: ${{ github.token }}
-        EDITION: ${{ inputs.edition }}
-        HEAD_SHA: ${{ github.event.pull_request.head.sha || github.sha }}
-        BASE_SHA: ${{ inputs.base-ref-commit }}
-        THRESHOLD: ${{ inputs.threshold-percent }}
-        MEASURE_BUNDLES: app,embedding-sdk-legacy,embedding-sdk-chunked
-      run: |
-        set -uo pipefail
-
-        skip() {
-          echo "::notice::Embedding SDK bundle-size check skipped: $1"
-          echo "status=stable" >> "$GITHUB_OUTPUT"
-          echo "size_change_percent=0" >> "$GITHUB_OUTPUT"
-          exit 0
-        }
-
-        # The base ref needs an already-built uberjar. Rebuilding it from source
-        # would compare across two build pipelines (the bug this check used to
-        # have), so skip instead when it — or its stats — isn't available.
-        [ -f temp/base-uberjar/metabase.jar ] || skip "base-ref uberjar not found for ${BASE_SHA}"
-
-        extract_js() { # $1=jar  $2=dest-root
-          mkdir -p "$2/resources"
-          unzip -o "$1" \
-            "frontend_client/app/dist/*" \
-            "frontend_client/app/embed.js" \
-            "frontend_client/app/embedding-sdk/*" \
-            -d "$2/resources" >/dev/null || true
-        }
-
-        fetch_stats() { # $1=sha  $2=dest-dir
-          local name="metabase-bundle-stats-${EDITION}-$1"
-          local id
-          id=$(gh api "/repos/${GITHUB_REPOSITORY}/actions/artifacts?name=${name}" --jq '.artifacts[0].id // empty' 2>/dev/null)
-          [ -n "${id}" ] || return 1
-          mkdir -p "$2"
-          gh api "/repos/${GITHUB_REPOSITORY}/actions/artifacts/${id}/zip" > "$2.zip" 2>/dev/null || return 1
-          unzip -o "$2.zip" -d "$2" >/dev/null || return 1
-        }
-
-        extract_js temp/current-uberjar/metabase.jar temp/current
-        extract_js temp/base-uberjar/metabase.jar temp/base
-
-        fetch_stats "${HEAD_SHA}" temp/current/artifacts || skip "bundle stats not found for current ${HEAD_SHA}"
-        fetch_stats "${BASE_SHA}" temp/base/artifacts || skip "bundle stats not found for base ${BASE_SHA}"
-
-        MEASURE_ROOT=temp/current node ./.github/scripts/measure-bundle-sizes.js > temp/current-sizes.json \
-          || { echo "::error::Failed to measure current bundle sizes"; exit 1; }
-        MEASURE_ROOT=temp/base node ./.github/scripts/measure-bundle-sizes.js > temp/base-sizes.json \
-          || { echo "::error::Failed to measure base bundle sizes"; exit 1; }
-
-        node ./.github/actions/sdk-bundle-size-check/compare.js temp/current-sizes.json temp/base-sizes.json

.github/actions/sdk-bundle-size-check/compare.js

@@ -1,110 +0,0 @@
-/* eslint-disable import/no-commonjs */
-// Diffs the bundle sizes produced by measure-bundle-sizes.js for the current
-// build and the base ref. Every (bundle, kind) is compared strictly against the
-// same (bundle, kind) — never one bundle type against another — using gzipped
-// (served) bytes. The gate is driven by the chunked SDK's reachable total, which
-// is what the SDK actually delivers.
-//
-// compareBundles is pure (data in, data out) so it can be unit-tested; main()
-// is the thin I/O wrapper that reads the size files, prints the report and sets
-// the step outputs / exit code.
-const fs = require("fs");
-
-const pick = (rows, bundle, kind) => rows.find(row => row.bundle === bundle && row.kind === kind);
-const keyOf = row => `${row.bundle}/${row.kind}`;
-const mb = bytes => (bytes / 1024 / 1024).toFixed(2);
-const percentOf = (currentBytes, baseBytes) =>
-  baseBytes ? Math.trunc(((currentBytes - baseBytes) * 100) / baseBytes) : 0;
-
-/**
- * Compare two measurement sets and decide the gate. Returns a human-readable
- * `report` (always), and exactly one of:
- *  - `gate`  { status, percent }: the chunked SDK total moved by `percent`.
- *  - `skip`  reason: the gate is non-actionable (report stable, no comment).
- *  - `error` reason: the gate inputs are missing (hard failure).
- */
-function compareBundles({ current, base, threshold }) {
-  const report = ["=== Bundle sizes (gzipped, current vs base) ==="];
-  const keys = [...new Set([...current, ...base].map(keyOf))].sort();
-  for (const key of keys) {
-    const [bundle, kind] = key.split("/");
-    const currentRow = pick(current, bundle, kind);
-    const baseRow = pick(base, bundle, kind);
-    if (!currentRow || !baseRow) {
-      report.push(`${key}: present only in ${currentRow ? "current" : "base"} build`);
-      continue;
-    }
-    const diff = currentRow.gzipBytes - baseRow.gzipBytes;
-    const percent = percentOf(currentRow.gzipBytes, baseRow.gzipBytes);
-    report.push(`${key}: ${mb(currentRow.gzipBytes)}MB vs ${mb(baseRow.gzipBytes)}MB (${percent}%, ${diff} bytes)`);
-  }
-
-  // Gate on the chunked SDK's reachable total (gzipped) — what the SDK ships.
-  const gateCurrent = pick(current, "embedding-sdk-chunked", "total");
-  const gateBase = pick(base, "embedding-sdk-chunked", "total");
-  if (!gateCurrent || !gateBase || !gateBase.gzipBytes) {
-    return { report, error: "Could not find embedding-sdk-chunked total (gzip) in both builds" };
-  }
-
-  // Both sides must measure "total" the same way. A base ref built before the
-  // reachableAssets enrichment collapses its total to the initial set, so
-  // comparing it against the current reachable total reports a phantom jump
-  // (~30%). Skip until the base ref also carries reachable stats (i.e. once
-  // this change is on the base).
-  if (Boolean(gateCurrent.reachable) !== Boolean(gateBase.reachable)) {
-    return {
-      report,
-      skip:
-        `chunked "total" measured differently on each side ` +
-        `(current reachable=${Boolean(gateCurrent.reachable)}, base reachable=${Boolean(gateBase.reachable)}); ` +
-        `the base ref predates the reachable-chunk stats. Resolves once this change is on the base ref.`,
-    };
-  }
-
-  const percent = percentOf(gateCurrent.gzipBytes, gateBase.gzipBytes);
-  const status = percent > threshold ? "increased" : percent < -threshold ? "decreased" : "stable";
-  return { report, gate: { status, percent } };
-}
-
-module.exports = { compareBundles };
-
-const setOutput = (name, value) => {
-  if (process.env.GITHUB_OUTPUT) {
-    fs.appendFileSync(process.env.GITHUB_OUTPUT, `${name}=${value}\n`);
-  }
-};
-
-function main() {
-  const [, , currentPath, basePath] = process.argv;
-  const threshold = Number(process.env.THRESHOLD ?? 2);
-
-  const current = JSON.parse(fs.readFileSync(currentPath, "utf8"));
-  const base = JSON.parse(fs.readFileSync(basePath, "utf8"));
-
-  const { report, gate, skip, error } = compareBundles({ current, base, threshold });
-  console.log(report.join("\n"));
-
-  if (error) {
-    console.error(`::error::${error}`);
-    process.exit(1);
-  }
-
-  if (skip) {
-    // Treat the gate as non-actionable: report stable so no regression comment
-    // is posted, mirroring the shell skip() for missing artifacts.
-    console.log(`::notice::Embedding SDK bundle-size gate skipped: ${skip}`);
-    setOutput("status", "stable");
-    setOutput("size_change_percent", "0");
-    process.exit(0);
-  }
-
-  console.log("");
-  console.log(`Gate: embedding-sdk-chunked total ${gate.percent}% (threshold ${threshold}%) → ${gate.status}`);
-
-  setOutput("status", gate.status);
-  setOutput("size_change_percent", gate.percent);
-}
-
-if (require.main === module) {
-  main();
-}

.github/actions/sdk-bundle-size-check/compare.unit.spec.js

@@ -1,65 +0,0 @@
-const { compareBundles } = require("./compare");
-
-const total = (gzipBytes, over = {}) => ({
-  bundle: "embedding-sdk-chunked",
-  kind: "total",
-  gzipBytes,
-  reachable: true,
-  ...over,
-});
-
-describe("compareBundles", () => {
-  it("gates on the chunked SDK total and flags an increase past the threshold", () => {
-    const { gate, report } = compareBundles({
-      current: [total(110)],
-      base: [total(100)],
-      threshold: 2,
-    });
-
-    expect(gate).toEqual({ status: "increased", percent: 10 });
-    expect(report[0]).toContain("current vs base");
-  });
-
-  it("flags a decrease and stays stable within the threshold", () => {
-    expect(compareBundles({ current: [total(90)], base: [total(100)], threshold: 2 }).gate).toEqual({
-      status: "decreased",
-      percent: -10,
-    });
-    expect(compareBundles({ current: [total(101)], base: [total(100)], threshold: 2 }).gate).toEqual({
-      status: "stable",
-      percent: 1,
-    });
-  });
-
-  it("skips when the two sides measured total differently (reachable mismatch)", () => {
-    const result = compareBundles({
-      current: [total(130, { reachable: true })],
-      base: [total(100, { reachable: false })],
-      threshold: 2,
-    });
-
-    expect(result.gate).toBeUndefined();
-    expect(result.skip).toContain("predates the reachable-chunk stats");
-  });
-
-  it("errors when the gate bundle is missing on either side", () => {
-    const result = compareBundles({
-      current: [{ bundle: "app", kind: "total", gzipBytes: 1 }],
-      base: [total(100)],
-      threshold: 2,
-    });
-
-    expect(result.gate).toBeUndefined();
-    expect(result.error).toContain("embedding-sdk-chunked total");
-  });
-
-  it("reports a bundle/kind present on only one side without erroring", () => {
-    const { report } = compareBundles({
-      current: [total(100), { bundle: "app", kind: "total", gzipBytes: 50 }],
-      base: [total(100)],
-      threshold: 2,
-    });
-
-    expect(report.some(line => line.includes("present only in current build"))).toBe(true);
-  });
-});

.github/actions/test-driver/action.yml

@@ -9,20 +9,48 @@ inputs:
   build-static-viz:
     required: true
     default: false
-  logs-artifact-suffix:
+  artifact-suffix:
     required: false
-    description: Suffix to append to the test logs artifact name to avoid conflicts in matrix jobs
+    description: >-
+      Discriminator appended to this job's artifact names (test logs, granular-rerun failed
+      tests). A job whose matrix runs several concurrent legs MUST set a per-leg-unique value,
+      or the legs collide on one artifact — for the rerun artifact that means a leg restores
+      another leg's failed set. Must be stable across attempts of the same job.
   edition:
     required: false
     default: "ee"
     description: Edition to test (oss or ee)
-  quarantine-engine:
+  runner-index:
     required: false
-  driver-status:
-    required: false
-    default: ""
     description: >-
-      Configured status for this driver ("info", "skip", "required", or empty), as reported by `mage driver-decisions`.
+      The index of this runner among those sharing a partitioned suite. See
+      `be-tests-bigquery-cloud-sdk-ee` in `.github/workflows/drivers.yml` for an example.
+  runner-count:
+    required: false
+    description: >-
+      How many runners share the suite. Recommended to set to `strategy.job-total` rather
+      than a literal so that it doesn't need updating if the `runner-index` matrix changes.
+  jvms-per-runner:
+    required: false
+    default: "1"
+    description: >-
+      Concurrent JVMs per runner. Recommended to raise above 1 for drivers whose tests
+      spend a lot of time waiting on a remote warehouse.
+  heap-per-jvm:
+    required: false
+    default: "4g"
+    description: >-
+      `-Xmx` per JVM, applied only when `jvms-per-runner` is more than 1 (otherwise the
+      the `:ci` alias's `-Xmx12g` is used). To size it: reserve ~1G for the OS and ~2G
+      of non-heap per JVM, then divide what's left. On a 16G runner that's ~4G each for
+      two JVMs.
+  granular-rerun:
+    required: false
+    default: "true"
+    description: >-
+      When "true" (default), a re-run of a failed job runs only the tests that failed on the
+      previous attempt (hawk `:only`). Stress workflows set this to "false": they intentionally
+      run a fixed test set `:times N`, and narrowing to failures would drop that repetition.
 
 outputs:
   test-outcome:
@@ -48,16 +76,96 @@ runs:
       env:
         MB_EDITION: ${{ inputs.edition }}
 
+    # Granular rerun: on a re-run of a failed job, restore the list
+    # of tests that failed on the previous attempt (uploaded below) so the test
+    # step can target only those instead of the whole suite. Best-effort: a
+    # missing/empty artifact leaves no file and the run falls back to the full
+    # suite. First attempts skip this entirely.
+    #
+    # Scoped to the IMMEDIATELY preceding attempt: an attempt that passed, or
+    # that failed with nothing attributable to a var, uploads no artifact, and a
+    # narrow set must not outlive it. Reading `attempt - 1` means "only what the
+    # last attempt actually recorded" — anything else falls back to the full suite.
+    # Workflow expressions have no arithmetic, so the shell computes it.
+    #
+    # run-tests.yml calls app-db.yml, backend.yml, drivers.yml and semantic-search.yml
+    # as part of ONE run, so all four share an artifact namespace. `junit-name` alone is not
+    # unique there — app-db.yml and drivers.yml both derive `be-tests-postgres-ee` — so
+    # `artifact-suffix` carries the rest of the discriminator.
+    - name: Resolve rerun artifact names
+      if: ${{ inputs.granular-rerun == 'true' }}
+      shell: bash
+      env:
+        RERUN_ARTIFACT_BASE: ${{ format('failed-tests-{0}{1}', inputs.junit-name, inputs.artifact-suffix && format('-{0}', inputs.artifact-suffix) || '') }}
+      run: |
+        echo "RERUN_ARTIFACT=$RERUN_ARTIFACT_BASE-attempt-$GITHUB_RUN_ATTEMPT" >> "$GITHUB_ENV"
+        echo "RERUN_PREV_ARTIFACT=$RERUN_ARTIFACT_BASE-attempt-$((GITHUB_RUN_ATTEMPT - 1))" >> "$GITHUB_ENV"
+
+    # `pattern` (not `name`) because the artifact is legitimately absent whenever the
+    # previous attempt recorded nothing: `name` treats that as an error, `pattern`
+    # downloads nothing and moves on. The value is a literal — no glob metacharacters —
+    # so it matches exactly one artifact, which lands at `target/failed-tests`. A pattern
+    # that ever matched two would nest them under their artifact names instead, leaving
+    # the file absent and falling back to the full suite.
+    - name: Restore previously-failed tests
+      if: ${{ inputs.granular-rerun == 'true' && github.run_attempt != '1' }}
+      continue-on-error: true
+      uses: actions/download-artifact@v8
+      with:
+        pattern: ${{ env.RERUN_PREV_ARTIFACT }}
+        path: target
+
     - name: Test database driver
-      run: clojure -X:dev:ci:${{ inputs.edition }}:${{ inputs.edition }}-dev:drivers:drivers-dev:test ${{ inputs.test-args }}
+      # On a rerun with a non-empty failed-tests file, target only those vars via
+      # hawk `:only` (a var-level selector bypasses `:only-tags`, which is fine —
+      # every listed var already passed that filter on the first attempt).
+      # Otherwise run exactly as before. Quote the file so the whole `[ns/var ...]`
+      # vector reaches clojure -X as a single argument.
+      run: |
+        ALIASES="dev:ci:${{ inputs.edition }}:${{ inputs.edition }}-dev:drivers:drivers-dev:test"
+        BASE="clojure -X:dev:ci:${{ inputs.edition }}:${{ inputs.edition }}-dev:drivers:drivers-dev:test"
+        # `:profile-tests` overrides `:test`'s exec-fn, so it has to come last. See dev.profile-tests.
+        # The `profiled` output is what the collection steps below key off, so that the decision is
+        # recorded by the step that acts on it rather than re-derived from the environment.
+        if [ "$PROFILE_TESTS" = "true" ]; then
+          echo "Profiling this run; a flamegraph will be attached to the job."
+          echo "profiled=true" >> "$GITHUB_OUTPUT"
+          BASE="$BASE:profile-tests"
+        fi
+        # An explicit selection wins over the rerun narrowing below: it was asked for by hand, on this
+        # attempt. Names may be separated by commas or spaces; hawk wants them as one vector argument.
+        if [ -n "$ONLY_TESTS" ]; then
+          ONLY="[$(echo "$ONLY_TESTS" | tr ',' ' ')]"
+          echo "Running only: $ONLY"
+          $BASE :only "$ONLY"
+        elif [ "${{ inputs.granular-rerun }}" = "true" ] && [ "${{ github.run_attempt }}" != "1" ] && [ -s target/failed-tests ]; then
+          echo "Granular rerun of previously-failed tests: $(cat target/failed-tests)"
+          clojure -X:"$ALIASES" :only "$(cat target/failed-tests)"
+        elif [ -n "$TEST_RUNNER_INDEX" ]; then
+          CLOJURE_ALIASES="$ALIASES" ./.github/scripts/run-backend-test-jvms.sh ${{ inputs.test-args }}
+        else
+          clojure -X:"$ALIASES" ${{ inputs.test-args }}
+        fi
       shell: bash
       id: run-test
-      # Keep this step continue-on-error because the quarantine logic controls whether it ultimately fails.
-      # Driver "info" status can affect this logic. See below.
+      env:
+        TEST_RUNNER_INDEX: ${{ inputs.runner-index }}
+        TEST_RUNNER_COUNT: ${{ inputs.runner-count }}
+        TEST_JVMS_PER_RUNNER: ${{ inputs.jvms-per-runner }}
+        TEST_HEAP_PER_JVM: ${{ inputs.heap-per-jvm }}
+      # Keep this step continue-on-error because the quarantine gate below controls whether it
+      # ultimately fails.
       continue-on-error: true
 
+    - name: Collect profile
+      if: ${{ !cancelled() }}
+      uses: ./.github/actions/collect-profile
+      with:
+        profiled: ${{ steps.run-test.outputs.profiled }}
+        artifact-name: ${{ format('profile-{0}{1}', inputs.junit-name, inputs.artifact-suffix && format('-{0}', inputs.artifact-suffix) || '') }}
+
     - name: Report failed tests to ci-conductor
-      if: ${{ !cancelled() && steps.run-test.outcome == 'failure' }}
+      if: ${{ !cancelled() && ( steps.run-test.outcome == 'failure' || github.run_attempt != '1' ) }}
       # This step should NEVER fail the job!
       continue-on-error: true
       uses: ./.github/actions/report-failures-to-ci-conductor
@@ -65,6 +173,30 @@ runs:
         test-suite: ${{ inputs.junit-name }}
         adapter: backend
 
+    # Granular rerun: record which tests failed so a re-run of this
+    # job targets only those (restored above). Reuses the backend JUnit adapter
+    # from the ci-conductor sources the report step just prepared. Best-effort:
+    # writes nothing unless every failure is attributable to a var, so an
+    # unattributable failure falls back to a full rerun.
+    - name: Collect failed tests for rerun
+      if: ${{ inputs.granular-rerun == 'true' && !cancelled() && steps.run-test.outcome == 'failure' }}
+      continue-on-error: true
+      shell: bash
+      # Clear the restored set first, so a collector that dies before deciding
+      # can't leave the previous attempt's file to be uploaded as this one's.
+      run: |
+        rm -f target/failed-tests
+        bun release/ci-conductor/src/collect-failed-backend.ts
+
+    - name: Upload failed tests for rerun
+      if: ${{ inputs.granular-rerun == 'true' && !cancelled() && steps.run-test.outcome == 'failure' }}
+      continue-on-error: true
+      uses: actions/upload-artifact@v7
+      with:
+        name: ${{ env.RERUN_ARTIFACT }}
+        path: target/failed-tests
+        if-no-files-found: ignore
+
     - name: Publish Test Report (JUnit)
       uses: dorny/test-reporter@a43b3a5f7366b97d083190328d2c652e1a8b6aa2 # v3.0.0
       # As per the documentation: https://docs.github.com/en/actions/reference/workflows-and-actions/contexts#steps-context
@@ -83,8 +215,10 @@ runs:
       if: always() && steps.run-test.outcome != 'success'
       uses: actions/upload-artifact@v7
       with:
-        name: ${{ format('test-logs-{0}{1}', github.job, inputs.logs-artifact-suffix && format('-{0}', inputs.logs-artifact-suffix) || '') }}
-        path: logs/test-log.json
+        name: ${{ format('test-logs-{0}{1}', github.job, inputs.artifact-suffix && format('-{0}', inputs.artifact-suffix) || '') }}
+        # Glob: a single-JVM run writes `logs/test-log.json`; a multi-JVM run merges one
+        # `logs/test-log-p<index>.json` per JVM.
+        path: logs/test-log*.json
         retention-days: 1
       # Failing to upload the artifact should never affect the outcome of the whole test run.
       continue-on-error: true
@@ -92,16 +226,9 @@ runs:
     # Last, because this is the only step allowed to fail the job: everything above it reports the
     # failure (JUnit report, logs, ci-conductor) and must run regardless of the verdict below.
     - name: Quarantine gate
-      # Off master and release branches an "info" driver is data-collection only - the test always passes!
-      # On master and release branches "info" carries no weight - the quarantine logic applies.
-      if: |
-        !cancelled()
-        && steps.run-test.outcome == 'failure'
-        && !(inputs.driver-status == 'info'
-             && !(github.ref_name == 'master' || startsWith(github.ref_name, 'release-x')))
-      continue-on-error: ${{ inputs.quarantine-engine != 'ci-conductor' }}
+      if: ${{ !cancelled() && steps.run-test.outcome == 'failure' }}
       uses: ./.github/actions/quarantine-gate
       with:
         adapter: backend
         test-suite: ${{ inputs.junit-name }}
-        enforce-quarantine: ${{ inputs.quarantine-engine == 'ci-conductor' }}
+        enforce-quarantine: "true"

.github/actions/update-cache/action.yml

@@ -1,41 +0,0 @@
-name: Update cache
-description: |
-  Update a GitHub Actions cache based on a provided path and key.
-  If a cache entry already exists for the given key, it is first removed.
-  This ensures immutability of cache entries, and prevents runtime errors.
-
-inputs:
-  path:
-    description: "The path(s) to cache, separated by newlines."
-    required: true
-  key:
-    description: "The cache key to use."
-    required: true
-
-runs:
-  using: "composite"
-  steps:
-    - name: Check if the cache entry exists
-      id: cache-lookup
-      uses: actions/cache/restore@v5
-      with:
-        path: ${{ inputs.path }}
-        key: ${{ inputs.key }}
-        lookup-only: true # Important bit: the action will not fetch anything, just check for the cache existence.
-    - name: Delete the cache entry if it exists
-      if: ${{ steps.cache-lookup.outputs.cache-hit == 'true' }}
-      run: |
-        echo "Cache entry found for key '${{ inputs.key }}'. Deleting it to ensure immutability."
-        gh api \
-          --method DELETE \
-          -H "Accept: application/vnd.github+json" \
-          -H "X-GitHub-Api-Version: 2022-11-28" \
-          /repos/${{ github.repository }}/actions/caches?key=${{ inputs.key }}
-      env:
-        GH_TOKEN: ${{ github.token }}
-      shell: bash
-    - name: Save the new cache entry
-      uses: actions/cache/save@v5
-      with:
-        path: ${{ inputs.path }}
-        key: ${{ inputs.key }}

.github/actions/upgrade-backend-deps/action.yml

@@ -1,4 +1,5 @@
 name: Create Backend Dep Bump PRs
+description: Opens a pull request for each backend dependency that has a newer version available.
 
 inputs:
   github-token:

.github/actions/upload-test-results/action.yml

@@ -1,185 +0,0 @@
-name: Upload Test Results to s3
-description: Uploads test results files to s3
-
-inputs:
-  input-path:
-    required: true
-  output-name:
-    required: true
-    default: test
-  role-to-assume:
-    required: true
-  aws-region:
-    required: true
-    default: us-east-1
-  bucket:
-    required: true
-  trunk-api-token:
-    required: true
-  variant:
-    required: false
-    default: ""
-  previous-step-outcome:
-    required: true
-  driver-status:
-    required: false
-    default: ""
-    description: >-
-      Configured status for this driver ("info", "skip", "required", or empty). When
-      "info", the job is reported as passing regardless of the real test outcome, and
-      that outcome is surfaced via a job summary and (on PRs) a comment instead.
-  report-variant:
-    required: false
-    default: ""
-    description: >-
-      Optional label disambiguating matrix legs of the same job, so the info-driver
-      job summary and PR comment stay distinct per leg.
-  run-trunk:
-    required: false
-    default: "true"
-    description: Whether to run the Trunk step at all.
-
-runs:
-  using: "composite"
-  steps:
-    - name: Configure AWS credentials
-      uses: aws-actions/configure-aws-credentials@d979d5b3a71173a29b74b5b88418bfda9437d885
-      with:
-        role-to-assume: ${{ inputs.role-to-assume }}
-        aws-region: ${{ inputs.aws-region }}
-    - name: zip test results
-      env:
-        INPUT_DIR: ${{ inputs.input-path }}
-        OUTPUT_FILE: ${{ inputs.output-name }}
-      shell: bash
-      run: | # sh
-        zip ${OUTPUT_FILE}.zip $INPUT_DIR/*.xml
-    - name: Upload test results to S3
-      env:
-        BUCKET: ${{ inputs.bucket }}
-        OUTPUT_FILE: ${{ inputs.output-name }}
-      shell: bash
-      run: | # sh
-        DATE=$(date '+%Y-%m-%d')
-        aws s3 cp ${OUTPUT_FILE}.zip s3://$BUCKET/$DATE/$GITHUB_RUN_ID/$GITHUB_RUN_ATTEMPT/
-
-    - name: Upload results to Trunk
-      if: ${{ always() && github.repository_owner == 'metabase' && inputs.run-trunk == 'true' }}
-      # Important!
-      # For "info" drivers off master/release branches, our own status takes precedence: we let this
-      # step pass so the job is reported as passing regardless of the real outcome (still uploaded).
-      # On master and release branches, info status is ignored and the real outcome gates the job.
-      continue-on-error: ${{ inputs.driver-status == 'info' && !(github.ref_name == 'master' || startsWith(github.ref_name, 'release-x')) }}
-      uses: trunk-io/analytics-uploader@1198efcc0976501147b10a7e343c3fa069527526 # v2.0.9
-      env:
-        TRUNK_REPO_URL: git@github.com:metabase/metabase.git
-      with:
-        junit-paths: ${{ inputs.input-path }}
-        variant: ${{ inputs.variant || inputs.output-name }}
-        org-slug: metabase
-        dry-run: ${{ (github.event_name == 'pull_request' && github.event.pull_request.draft == true) || github.repository != 'metabase/metabase' }} # quarantine, but do not upload results
-        token: ${{ inputs.trunk-api-token }}
-        use-cache: true
-        previous-step-outcome: ${{ inputs.previous-step-outcome }}
-
-    # For "info" drivers the job is forced green above, so surface the real outcome here —
-    # but only when it did NOT pass, to avoid spamming summaries/comments for healthy runs.
-    # Never include logs or stack traces — only the real status and a link to the run.
-    - name: Report info-level driver result (job summary)
-      if: ${{ always() && inputs.driver-status == 'info' && inputs.previous-step-outcome == 'failure' }}
-      shell: bash
-      env:
-        OUTCOME: ${{ inputs.previous-step-outcome }}
-        LABEL: ${{ inputs.output-name }}
-        VARIANT: ${{ inputs.report-variant }}
-      run: | # sh
-        if [ "$OUTCOME" = "success" ]; then EMOJI="✅"; else EMOJI="❌"; fi
-        TITLE="$LABEL"
-        [ -n "$VARIANT" ] && TITLE="$LABEL ($VARIANT)"
-        RUN_URL="$GITHUB_SERVER_URL/$GITHUB_REPOSITORY/actions/runs/$GITHUB_RUN_ID"
-        {
-          echo "### ℹ️ Info-level driver: $TITLE"
-          echo ""
-          echo "Reported as passing (non-blocking). Real result: $EMOJI \`$OUTCOME\`"
-          echo ""
-          echo "[View run]($RUN_URL)"
-        } >> "$GITHUB_STEP_SUMMARY"
-
-    # Maintain ONE PR comment per commit for all info drivers. Each leg upserts its own line
-    # (keyed by a hidden tag); a passing leg removes its line, and the comment is deleted once
-    # no failing legs remain. Comments from older commits are cleaned up. Runs on pass and fail
-    # so recoveries self-heal. Never includes logs or stack traces — only status and a run link.
-    - name: Sync info-level driver result into the PR comment
-      if: ${{ always() && inputs.driver-status == 'info' && github.event_name == 'pull_request' }}
-      uses: actions/github-script@v9
-      continue-on-error: true
-      env:
-        OUTCOME: ${{ inputs.previous-step-outcome }}
-        LABEL: ${{ inputs.output-name }}
-        VARIANT: ${{ inputs.report-variant }}
-      with:
-        script: | # js
-          const { OUTCOME, LABEL, VARIANT, GITHUB_SERVER_URL, GITHUB_REPOSITORY, GITHUB_RUN_ID } = process.env;
-          const pr = context.payload.pull_request;
-          if (!pr) return;
-          const { owner, repo } = context.repo;
-          const sha = pr.head.sha;
-          // PREFIX matches the current per-commit marker AND the older per-leg one, so legacy
-          // comments from a previous version get cleaned up on the next sync.
-          const PREFIX = "<!-- info-driver-result";
-          const marker = `<!-- info-driver-results:${sha} -->`;
-          const header = `${marker}\nℹ️ **Info-level drivers** failed (non-blocking) on \`${sha.slice(0, 7)}\` — these do not gate:`;
-          const lineKey = `${LABEL}:${VARIANT}`;
-          const title = VARIANT ? `${LABEL} (${VARIANT})` : LABEL;
-          const runUrl = `${GITHUB_SERVER_URL}/${GITHUB_REPOSITORY}/actions/runs/${GITHUB_RUN_ID}`;
-          // Only real failures are reported; cancelled/skipped/success remove this leg's line.
-          // List-item line with the hidden key tag at the END so markdown (links) renders.
-          const ourLine = OUTCOME === "failure"
-            ? `- **${title}** — ❌ \`${OUTCOME}\` ([Logs](${runUrl})) <!--l:${lineKey}-->`
-            : null;
-          const linesOf = (body) => body.split("\n").filter((l) => l.includes("<!--l:"));
-
-          const sync = async () => {
-            const { data: comments } = await github.rest.issues.listComments({
-              owner, repo, issue_number: pr.number, per_page: 100,
-            });
-            const tagged = comments.filter((c) => c.body.includes(PREFIX));
-            // Drop comments left over from older commits.
-            for (const c of tagged.filter((c) => !c.body.includes(marker))) {
-              await github.rest.issues.deleteComment({ owner, repo, comment_id: c.id }).catch(() => {});
-            }
-            const mine = tagged
-              .filter((c) => c.body.includes(marker))
-              .sort((a, b) => new Date(a.created_at) - new Date(b.created_at));
-            // Merge any duplicates raced into existence; latest write of each line wins.
-            const byKey = new Map();
-            for (const c of mine) {
-              for (const l of linesOf(c.body)) {
-                const m = l.match(/<!--l:(.*?)-->/);
-                if (m) byKey.set(m[1], l);
-              }
-            }
-            if (ourLine) byKey.set(lineKey, ourLine);
-            else byKey.delete(lineKey);
-            const lines = [...byKey.values()].sort();
-            const target = mine[0];
-            for (const c of mine.slice(1)) {
-              await github.rest.issues.deleteComment({ owner, repo, comment_id: c.id }).catch(() => {});
-            }
-            if (lines.length === 0) {
-              if (target) await github.rest.issues.deleteComment({ owner, repo, comment_id: target.id }).catch(() => {});
-              return;
-            }
-            const body = [header, "", ...lines].join("\n");
-            if (target) {
-              await github.rest.issues.updateComment({ owner, repo, comment_id: target.id, body });
-            } else {
-              await github.rest.issues.createComment({ owner, repo, issue_number: pr.number, body });
-            }
-          };
-
-          // Retry to shrink the window where parallel legs clobber each other's update.
-          for (let i = 0; i < 4; i++) {
-            try { await sync(); break; }
-            catch (e) { if (i === 3) throw e; await new Promise((r) => setTimeout(r, 400 * (i + 1))); }
-          }

.github/actions/verify-membership/action.yml

@@ -1,22 +0,0 @@
-name: 'Verify Organization Membership'
-description: 'Check if a user is a member of a GitHub organization'
-inputs:
-  github_token:
-    description: 'Token with access to the organization'
-    required: true
-  organization_name:
-    description: 'Organization name'
-    required: true
-  username:
-    description: 'Username'
-    required: true
-outputs:
-  is_member:
-    value: ${{ steps.verify-membership.outputs.is_member }}
-    description: "Is the user a member of the organization"
-runs:
-  using: "composite"
-  steps:
-    - run: bash ${{ github.action_path }}/verify_membership.sh ${{ inputs.github_token }} ${{ inputs.organization_name }} ${{ inputs.username }}
-      id: verify-membership
-      shell: bash

.github/actions/verify-membership/verify_membership.sh

@@ -1,25 +0,0 @@
-#!/bin/bash
-
-TOKEN=$1
-ORG_NAME=$2
-USERNAME=$3
-
-response=$(curl -L -o /dev/null -w "%{http_code}" \
-  -H "Accept: application/vnd.github+json" \
-  -H "Authorization: Bearer $TOKEN" \
-  -H "X-GitHub-Api-Version: 2022-11-28" \
-  "https://api.github.com/orgs/$ORG_NAME/members/$USERNAME")
-
-# Github returns an empty response with 204 status if user is a member and 404 status otherwise
-# See: https://docs.github.com/en/rest/orgs/members?apiVersion=2022-11-28#check-organization-membership-for-a-user
-if [ "$response" == "204" ]; then
-    echo "The user $USERNAME is a member of $ORG_NAME"
-    echo "is_member=true" >> $GITHUB_OUTPUT
-elif [ "$response" == "404" ]; then
-    echo "The user $USERNAME is not a member of $ORG_NAME"
-    echo "is_member=false" >> $GITHUB_OUTPUT
-else
-    echo "Failed to determine the membership status for $USERNAME in $ORG_NAME"
-    echo "is_member=false" >> $GITHUB_OUTPUT
-    exit 1
-fi

.github/file-paths.yaml

@@ -7,9 +7,8 @@ default: &default
   - "locales/**"
   - "bin/**/!(*.md)"
 
-actionlint:
-  - ".github/workflows/*.yml"
-  - ".github/workflows/*.yaml"
+workflows:
+  - added|modified: ".github/workflows/*.{yml,yaml}"
 
 shared_sources: &shared_sources
   - "src/**/*.cljc"
@@ -54,11 +53,6 @@ frontend_sources: &frontend_sources
   - "enterprise/frontend/!(test)**/**/{!(*.spec),}.{js,jsx,ts,tsx,css}"
   - "frontend/!(test)**/**/{!(*.spec),}.{js,jsx,ts,tsx,css}"
 
-# Used only in .github/workflows/conventional-commit-pr-title-reminder.yml
-frontend_embedding_sources:
-  - "enterprise/frontend/src/{embedding,embedding-*}/**/{!(*.spec),}.{js,jsx,ts,tsx,css}"
-  - "enterprise/frontend/src/metabase-enterprise/{embedding,embedding-*}**/{!(*.spec),}.{js,jsx,ts,tsx,css}"
-
 # Used only in .github/workflows/embedding-sdk-labels-reminder.yml
 frontend_embedding_sdk_package_sources:
   - "enterprise/frontend/src/embedding-sdk-package/**/!(*.spec).{js,jsx,ts,tsx,css}"
@@ -69,9 +63,10 @@ frontend_specs: &frontend_specs
   - "frontend/**/tests/**"
   - "frontend/**/*.unit.*"
   - "enterprise/frontend/**/*.unit.*"
-  - ".github/**/*.unit.spec.*"
   - "jest.config.js"
-  - "jest.tz.unit.conf.json"
+  - "jest.base.conf.js"
+  - "jest.esm-packages.js"
+  - "jest.tz.unit.conf.js"
 
 release_source: &release_sources
   - "release/**"
@@ -83,6 +78,7 @@ frontend_all: &frontend_all
 
 frontend_loki_ci: &frontend_loki_ci
   - ".github/workflows/loki.yml"
+  - "loki.config.js"
   - ".loki/**"
   - ".storybook/**"
 
@@ -90,14 +86,52 @@ frontend_unit_infra: &frontend_unit_infra
   - *frontend_configs
   - *frontend_ci
   - "jest.config.js"
-  - "jest.tz.unit.conf.json"
+  - "jest.base.conf.js"
+  - "jest.esm-packages.js"
+  - "jest.tz.unit.conf.js"
   - "frontend/test/**"
   - "frontend/**/__mocks__/**"
+  - "frontend/src/embedding-sdk-shared/jest/**"
 
 frontend_loki_infra: &frontend_loki_infra
   - *frontend_configs
   - *shared_ci
   - *frontend_loki_ci
+  - "frontend/build/shared/**"
+  - "frontend/test/__support__/**"
+  - "patches/**"
+  # dependency-cruiser doesn't follow CSS @import, so global styles must run every story.
+  - "frontend/src/metabase/css/**/*.css"
+  # Storybook serves resources/frontend_client as static files, and the stories bundle the app's SVGs.
+  - "resources/frontend_client/**"
+  - "frontend/**/*.svg"
+  - "enterprise/frontend/**/*.svg"
+
+frontend_loki_all:
+  - *frontend_sources
+  - *frontend_loki_infra
+
+# Everything the ci-scripts jest project runs or depends on.
+# test-unit ignores that project, so this filter is the only thing that reruns it.
+ci_scripts:
+  - *frontend_ci
+  - ".nvmrc"
+  # file-paths.unit.spec.ts asserts what this file's own patterns match, so a change to it has to
+  # run the specs that guard it.
+  - ".github/file-paths.yaml"
+  - ".github/scripts/**"
+  - ".github/actions/**"
+  - ".github/workflows/loki.yml"
+  - ".storybook/story-files.cjs"
+  - "frontend/lint/module-boundaries.mjs"
+  - "frontend/lint/shared-tiers.mjs"
+  - "frontend/test/jest-test-paths-filter.ts"
+  - ".dependency-cruiser.cjs"
+  - "jest.config.js"
+  - "jest.base.conf.js"
+  - "jest.esm-packages.js"
+  - "package.json"
+  - "bun.lock"
 
 # e2e harness/support code (commands, support file, runner). Not in the
 # instrumented bundle, so it maps to no covered module — a change here forces a
@@ -111,13 +145,6 @@ backend_ci: &backend_ci
   - ".github/workflows/backend.yml"
   - ".github/workflows/drivers.yml"
 
-backend_presto_kerberos:
-  - "**/presto_jdbc/**"
-  - "**/presto-jdbc/**" # the driver module has a hyphen. underscores are classpaths
-  - "**/presto_jdbc.clj"
-  - "**/presto_jdbc_test.clj"
-  - ".github/workflows/presto-kerberos-integration-test.yml"
-
 backend_sources: &backend_sources
   - *shared_sources
   - "**deps.edn"
@@ -125,11 +152,15 @@ backend_sources: &backend_sources
   - "src/**"
   - "modules/drivers/{*,*/{*,!(test)/**}}"
   - "resources/**"
-  - ".clj-kondo/**"
+  # Ratchet files drive project_ratchet_checks alone, so automation PRs that lower budgets
+  # run the Project tests job by themselves. Patterns are OR-ed, so a separate "!..." entry would match
+  # every other path instead of excluding this one.
+  - ".clj-kondo/**/!(ratchets.edn)"
 
 backend_specs: &backend_specs
   - *shared_specs
   - "test/**"
+  - "dev/test/**"
   - "enterprise/backend/test/**"
   - "test_modules/**"
   - "modules/drivers/*/test/**"
@@ -142,6 +173,48 @@ backend_all: &backend_all
   - *backend_sources
   - *backend_specs
 
+# Project checks have narrower triggers than the backend matrix.
+# Changes to their shared CI entry points exercise every suite; otherwise each
+# suite follows only the files that can affect its result.
+project_tests_infra: &project_tests_infra
+  - ".github/actions/prepare-backend/**"
+  - ".github/file-paths.yaml"
+  - ".github/workflows/backend.yml"
+  - ".github/workflows/run-tests.yml"
+  - "bb.edn"
+  - "bin/mage"
+  - "bin/mage.bb"
+  - "mage/src/mage/color.clj"
+  - "mage/src/mage/project_tests.clj"
+  - "mage/src/mage/shell.clj"
+  - "mage/src/mage/util.clj"
+
+project_backend_checks:
+  - *project_tests_infra
+  - "{src,test,enterprise,dev,bin,mage}/**/*.{clj,cljc,cljs}"
+  - "modules/**/*.clj"
+  - "modules/**/*.cljc"
+  - "modules/**/*.cljs"
+  - "**deps.edn"
+  - ".clj-kondo/{src,test}/**/*.{clj,cljc,cljs}"
+  - "{resources,test_resources,test_config}/**/*.{clj,cljc,cljs}"
+  - ".clj-kondo/config.edn"
+  - ".clj-kondo/config/modules/config.edn"
+  - ".github/team.json"
+  - "dev/resources/dev/modules_config_test/**"
+
+# Only the ratchet check reads the budgets, so a diff that touches nothing else runs that suite alone.
+project_ratchet_checks:
+  - ".clj-kondo/ratchets.edn"
+  - ".clj-kondo/config/modules/ratchets.edn"
+
+project_migration_checks:
+  - *project_tests_infra
+  - "bin/lint-migrations-file/**"
+  - "resources/migrations/**/*.{yaml,yml}"
+  - "src/metabase/app_db/custom_migrations.clj"
+  - "src/metabase/app_db/custom_migrations/**"
+
 sources: &sources
   - *shared_sources
   - *frontend_sources
@@ -155,7 +228,7 @@ custom_viz_all:
 
 e2e_ci: &e2e_ci
   - *shared_ci
-  - ".github/actions/prepare-uberjar-artifact/**"
+  - ".github/workflows/uberjar.yml"
   - ".github/actions/fetch-artifact/action.yml"
   - ".github/actions/e2e-prepare-containers/**"
   - ".github/actions/prepare-cypress/**"
@@ -166,7 +239,7 @@ e2e_specs: &e2e_specs
 
 embedding_sdk_ci: &embedding_sdk_ci
   - *shared_ci
-  - ".github/actions/prepare-uberjar-artifact/**"
+  - ".github/workflows/uberjar.yml"
   - ".github/actions/fetch-artifact/action.yml"
   - ".github/actions/prepare-cypress/**"
   - ".github/workflows/embedding-sdk*.yml"
@@ -188,7 +261,7 @@ embedding_sdk_host_sample_apps:
   - "e2e/test-host-app/**/*.cy.*.{js,ts}"
 
 snowplow: &snowplow
-  - ".github/workflows/snowplow.yml"
+  - ".github/workflows/lint.yml"
   - "snowplow/**"
   - "bin/lint-snowplow-schemas.bb"
   - "bin/lint-snowplow-schemas-test.bb"
@@ -217,7 +290,7 @@ yaml:
   - "**/*.yaml"
 
 codeql:
-  - ".github/workflows/codeql.yml"
+  - ".github/workflows/lint.yml"
   - "frontend/src/**"
   - "enterprise/frontend/src/**"
 
@@ -225,26 +298,50 @@ i18n:
   - *default
   - ".github/actions/prepare-frontend/**"
   - ".github/actions/prepare-backend/**"
-  - ".github/workflows/i18n.yml"
+  - ".github/workflows/lint.yml"
   - *sources
 
-visualizations:
-  - "frontend/src/metabase/visualizations/**"
-  - "frontend/src/metabase/static-viz/**"
-  - "src/metabase/pulse/**"
-
 cljs:
   - *shared_sources
   - *shared_specs
   - ".github/workflows/cljs.yml"
   - "shadow-cljs.edn"
 
+build_scripts:
+  - ".github/actions/prepare-backend/**"
+  - ".github/file-paths.yaml"
+  - ".github/workflows/build-scripts.yml"
+  - "bin/**"
+  - "deps.edn"
+
+embedder_plugin:
+  - ".github/actions/prepare-backend/**"
+  - ".github/file-paths.yaml"
+  - ".github/workflows/build-scripts.yml"
+  - "bin/build-embedder-plugin.sh"
+  - "bin/build/src/build/embedder_model.clj"
+  - "bin/build/src/build/plugin_uberjar.clj"
+  - "bin/build/src/build_embedder_plugin.clj"
+  - "deps.edn"
+  - "modules/embedder/**"
+  - "enterprise/backend/src/metabase_enterprise/data_complexity_score/complexity_embedders.clj"
+  - "enterprise/backend/src/metabase_enterprise/data_complexity_score/settings.clj"
+  - "enterprise/backend/src/metabase_enterprise/data_complexity_score/synonym_source.clj"
+  - "enterprise/backend/src/metabase_enterprise/semantic_search/embedding.clj"
+  - "enterprise/backend/src/metabase_enterprise/semantic_search/settings.clj"
+  - "enterprise/backend/test/metabase_enterprise/semantic_search/appdb_pgvector_mode_test.clj"
+  - "enterprise/backend/test/metabase_enterprise/semantic_search/embedding_test.clj"
+  - "src/metabase/embeddings/provider.clj"
+  - "src/metabase/embeddings/startup.clj"
+  - "src/metabase/plugins/**"
+  - "test/metabase/embeddings/embedder_plugin_artifact_test.clj"
+
 serialization_baseline:
   - ".github/workflows/serialization.yml"
   - "test_resources/serialization_baseline/**"
 
 openapi:
-  - ".github/workflows/openapi.yml"
+  - ".github/workflows/lint.yml"
   - "src/metabase/api/**"
   - "src/metabase/api_routes/**"
   - "src/metabase/*_rest/api.clj"

.github/instructions/e2e.instructions.md

@@ -0,0 +1,12 @@
+---
+applyTo: "e2e/**/*.cy.spec.{js,ts}"
+---
+
+# Cypress E2E Spec Review
+
+When reviewing Cypress E2E specs, apply the guidelines in these files:
+
+- `.claude/skills/_shared/cypress-conventions.md`
+- `.claude/skills/e2e-test-review/SKILL.md`
+
+These are in addition to the TypeScript/JavaScript instructions, which also match these files.

.github/scripts/affected-modules.ts

@@ -1,7 +1,12 @@
 import micromatch from "micromatch";
 
 export type ModuleDef = { type: string; pattern: string };
-export type Rule = { from: string[]; allow: string[] };
+
+export type Rule = {
+  from: string[];
+  allow?: string[];
+  disallow?: string[];
+};
 
 export type ModuleNode = { type: string; regex: RegExp };
 
@@ -100,6 +105,28 @@ export function getAffectedFiles(
   return affected;
 }
 
+/** The file plus every file it transitively imports. */
+export function getTransitiveDependencies(
+  fileDependencies: FileDependency[],
+  file: string,
+): Set<string> {
+  const dependenciesOf = new Map(
+    fileDependencies.map(({ source, dependencies }) => [source, dependencies]),
+  );
+  const reached = new Set([file]);
+  const queue = [file];
+  while (queue.length > 0) {
+    const current = queue.shift()!;
+    for (const dependency of dependenciesOf.get(current) ?? []) {
+      if (!reached.has(dependency)) {
+        reached.add(dependency);
+        queue.push(dependency);
+      }
+    }
+  }
+  return reached;
+}
+
 export type ModuleGraph = {
   nodes: ModuleNode[];
   /**
@@ -203,8 +230,11 @@ export function buildModuleGraph(
     allTypes.map((type) => [type, new Set()]),
   );
   for (const rule of rules) {
+    // Grandfathered imports that break the disallow rules still exist in the code,
+    // and selection must cover every import that actually exists.
+    // So disallow rules are ignored, at the cost of a looser graph.
     const fromTypes = rule.from.flatMap(expandPattern);
-    const allowTypes = rule.allow.flatMap(expandPattern);
+    const allowTypes = (rule.allow ?? []).flatMap(expandPattern);
     for (const target of allowTypes) {
       for (const importer of fromTypes) {
         if (importer !== target) {

.github/scripts/affected-modules.unit.spec.ts

@@ -6,6 +6,7 @@ import {
   getAffectedFiles,
   getAffectedModules,
   getChangedModules,
+  getTransitiveDependencies,
   mapFileToModule,
   parseCruiseModules,
 } from "./affected-modules";
@@ -123,6 +124,31 @@ describe("affected modules", () => {
     });
   });
 
+  describe("getTransitiveDependencies", () => {
+    it("should return the file and everything it transitively imports", () => {
+      expect(
+        [...getTransitiveDependencies(FILE_DEPS, "src/app.js")].sort(),
+      ).toEqual(["src/app.js", "src/foo/foo.tsx", "src/utils/colors.ts"]);
+    });
+
+    it("should return only the file when it imports nothing", () => {
+      expect([
+        ...getTransitiveDependencies(FILE_DEPS, "src/utils/colors.ts"),
+      ]).toEqual(["src/utils/colors.ts"]);
+    });
+
+    it("should stop at an import cycle", () => {
+      const cyclic = [
+        { source: "src/a.ts", dependencies: ["src/b.ts"] },
+        { source: "src/b.ts", dependencies: ["src/a.ts"] },
+      ];
+
+      expect([...getTransitiveDependencies(cyclic, "src/a.ts")].sort()).toEqual(
+        ["src/a.ts", "src/b.ts"],
+      );
+    });
+  });
+
   describe("buildUsageModuleGraph + getAffectedModules", () => {
     const usageGraph = buildUsageModuleGraph(ELEMENTS, FILE_DEPS);
 

.github/scripts/affected-tests.ts

@@ -11,6 +11,7 @@ import {
   buildUsageModuleGraph,
   getAffectedModules,
   getChangedModules,
+  getTransitiveDependencies,
   mapFileToModule,
 } from "./affected-modules";
 
@@ -21,6 +22,7 @@ export type TestPlanStats = {
   be_files_total: number;
   unit_infra_touched: boolean;
   loki_infra_touched: boolean;
+  loki_preview_touched: boolean;
   shared_sources_touched: boolean;
   fe_modules_total: number;
   fe_modules_changed: number;
@@ -48,9 +50,12 @@ export type CreateTestPlanInput = {
   elements: ModuleDef[];
   rules: Rule[];
   changedFiles: string[];
-  // Parsed dependency-cruiser edges, or null to fall back to the rules graph.
-  fileDependencies: FileDependency[] | null;
+  // Loads the dependency-cruiser edges, called only when some suite can be narrowed.
+  // Null falls back to the rules graph.
+  loadFileDependencies: () => FileDependency[] | null;
   testFilesBySuite: { unit: string[]; loki: string[]; e2e: string[] };
+  // Storybook's preview file, whose imports wrap every story.
+  lokiPreviewFile: string;
   e2eSpecFiles: Record<string, string[]> | null;
   unitInfraTouched: boolean;
   lokiInfraTouched: boolean;
@@ -63,6 +68,7 @@ export type CreateTestPlanInput = {
 };
 
 // Tests whose owning module is affected.
+// A spec outside the module tree always runs, because the graph cannot scope it.
 export function filterAffectedTests(
   nodes: ModuleNode[],
   affected: Set<string>,
@@ -70,7 +76,7 @@ export function filterAffectedTests(
 ): string[] {
   return testFiles.filter((file) => {
     const module = mapFileToModule(nodes, file);
-    return module !== null && affected.has(module);
+    return module === null || affected.has(module);
   });
 }
 
@@ -130,8 +136,9 @@ export function createTestPlan({
   elements,
   rules,
   changedFiles,
-  fileDependencies,
+  loadFileDependencies,
   testFilesBySuite,
+  lokiPreviewFile,
   e2eSpecFiles,
   unitInfraTouched,
   lokiInfraTouched,
@@ -143,16 +150,11 @@ export function createTestPlan({
   beFilesTotal,
 }: CreateTestPlanInput): TestPlan {
   const rulesGraph = buildModuleGraph(elements, rules);
-  const usageGraph = fileDependencies
-    ? buildUsageModuleGraph(elements, fileDependencies)
-    : rulesGraph;
-
   const nodes = rulesGraph.nodes;
   // Distinct module types (an element type can span several patterns).
   const totalModules = new Set(elements.map((el) => el.type)).size;
   const changedModules = getChangedModules(nodes, changedFiles);
   const rulesAffected = getAffectedModules(rulesGraph, changedFiles);
-  const usageAffected = getAffectedModules(usageGraph, changedFiles);
 
   // The coarse "feature" tier is the only set the e2e manifest is ever
   // collapsed to (see filterAffectedE2eSpecs).
@@ -161,7 +163,7 @@ export function createTestPlan({
   // cljc/cljs compile into the FE bundle, so they force a full run that module
   // selection can't narrow — same effect as a suite's own infra changing.
   const unitForceAll = unitInfraTouched || sharedSourcesTouched;
-  const lokiForceAll = lokiInfraTouched || sharedSourcesTouched;
+  const lokiInfraForceAll = lokiInfraTouched || sharedSourcesTouched;
   // e2e is integration-level, so anything the FE-coverage manifest can't see
   // forces a full run: cljc/cljs in the bundle (sharedSourcesTouched), a backend
   // change that can break the UI (beFilesChanged), an e2e harness/support change
@@ -172,6 +174,28 @@ export function createTestPlan({
     beFilesChanged > 0 ||
     e2eSpecFiles === null;
 
+  // The cruise takes seconds, so it is skipped when every suite runs in full anyway.
+  const edges =
+    unitForceAll && lokiInfraForceAll && e2eForceAll
+      ? null
+      : loadFileDependencies();
+  const usageGraph = edges
+    ? buildUsageModuleGraph(elements, edges)
+    : rulesGraph;
+  const usageAffected = getAffectedModules(usageGraph, changedFiles);
+
+  // The preview wraps every story, so a change to a file it imports can change any screenshot.
+  const previewDependencies = edges
+    ? getTransitiveDependencies(edges, lokiPreviewFile)
+    : new Set<string>();
+  const lokiPreviewTouched = changedFiles.some((file) =>
+    previewDependencies.has(file),
+  );
+  // Without the cruise, the rules graph cannot account for the preview's
+  // global dependencies, so it cannot safely narrow Loki.
+  const lokiForceAll =
+    lokiInfraForceAll || lokiPreviewTouched || edges === null;
+
   const select = (forceAll: boolean, affected: Set<string>, files: string[]) =>
     forceAll ? files : filterAffectedTests(nodes, affected, files);
 
@@ -208,6 +232,7 @@ export function createTestPlan({
       be_files_total: beFilesTotal,
       unit_infra_touched: unitInfraTouched,
       loki_infra_touched: lokiInfraTouched,
+      loki_preview_touched: lokiPreviewTouched,
       shared_sources_touched: sharedSourcesTouched,
       fe_modules_total: totalModules,
       fe_modules_changed: changedModules.size,

.github/scripts/affected-tests.unit.spec.ts

@@ -26,8 +26,9 @@ const E2E_FILES = ["e2e/test/scenarios/a.cy.spec.ts"];
 const baseInput = {
   elements: ELEMENTS,
   rules: RULES,
-  fileDependencies: null,
+  loadFileDependencies: () => null,
   testFilesBySuite: { unit: UNIT_FILES, loki: LOKI_FILES, e2e: E2E_FILES },
+  lokiPreviewFile: ".storybook/preview.tsx",
   e2eSpecFiles: null,
   unitInfraTouched: false,
   lokiInfraTouched: false,
@@ -41,7 +42,10 @@ const baseInput = {
 
 describe("createTestPlan", () => {
   it("runs only specs in affected modules (rules graph)", () => {
-    const plan = createTestPlan({ ...baseInput, changedFiles: ["src/foo/x.ts"] });
+    const plan = createTestPlan({
+      ...baseInput,
+      changedFiles: ["src/foo/x.ts"],
+    });
 
     expect(plan.stats.fe_modules_changed).toBe(1);
     expect(plan.stats.fe_modules_affected_rules).toBe(1);
@@ -50,8 +54,8 @@ describe("createTestPlan", () => {
       "src/foo/foo.unit.spec.ts",
     ]);
     expect(plan.stats.unit_specs_to_run_rules).toBe(2);
-    expect(plan.stats.loki_stories_to_run_rules).toBe(1);
-    // With no file deps, usage falls back to rules.
+    expect(plan.loki_stories_to_run).toEqual(LOKI_FILES);
+    // With no file deps, unit usage falls back to rules, but Loki runs in full.
     expect(plan.stats.unit_specs_to_run_usage).toBe(2);
   });
 
@@ -60,7 +64,7 @@ describe("createTestPlan", () => {
       ...baseInput,
       changedFiles: ["src/utils/colors.ts"],
       // Only feature/foo actually imports lib/utils.
-      fileDependencies: [
+      loadFileDependencies: () => [
         { source: "src/foo/foo.tsx", dependencies: ["src/utils/colors.ts"] },
       ],
     });
@@ -91,14 +95,69 @@ describe("createTestPlan", () => {
       ...baseInput,
       changedFiles: ["docs/readme.md"],
       unitInfraTouched: true,
+      loadFileDependencies: () => [],
     });
 
     expect(plan.stats.unit_specs_to_run_rules).toBe(UNIT_FILES.length);
     expect(plan.stats.loki_stories_to_run_rules).toBe(0);
   });
 
+  // The preview imports the theme, which imports the colors.
+  const PREVIEW_DEPS = [
+    { source: ".storybook/preview.tsx", dependencies: ["src/utils/theme.ts"] },
+    { source: "src/utils/theme.ts", dependencies: ["src/utils/colors.ts"] },
+    { source: "src/foo/foo.tsx", dependencies: ["src/foo/x.ts"] },
+  ];
+
+  it("forces a full Loki run when the Storybook preview imports a changed file", () => {
+    const plan = createTestPlan({
+      ...baseInput,
+      changedFiles: ["src/utils/colors.ts"],
+      loadFileDependencies: () => PREVIEW_DEPS,
+      e2eSpecFiles: { "e2e/test/scenarios/a.cy.spec.ts": ["src/bar/b.ts"] },
+    });
+
+    expect(plan.stats.loki_preview_touched).toBe(true);
+    expect(plan.stats.loki_stories_to_run_rules).toBe(LOKI_FILES.length);
+    expect(plan.loki_stories_to_run).toEqual(LOKI_FILES);
+    // Unit and e2e still narrow to what the usage graph reaches from the change.
+    expect(plan.fe_unit_specs_to_run).toEqual(["src/utils/utils.unit.spec.ts"]);
+    expect(plan.e2e_specs_to_run).toEqual([]);
+  });
+
+  it("narrows Loki when the Storybook preview does not import the changed file", () => {
+    const plan = createTestPlan({
+      ...baseInput,
+      changedFiles: ["src/foo/x.ts"],
+      loadFileDependencies: () => PREVIEW_DEPS,
+    });
+
+    expect(plan.stats.loki_preview_touched).toBe(false);
+    expect(plan.loki_stories_to_run).toEqual(["src/foo/Foo.stories.tsx"]);
+  });
+
+  it("runs all Loki stories when the cruise fails even if rules select fewer", () => {
+    const plan = createTestPlan({
+      ...baseInput,
+      changedFiles: ["src/foo/x.ts"],
+      loadFileDependencies: () => null,
+      e2eSpecFiles: { "e2e/test/scenarios/a.cy.spec.ts": ["src/bar/b.ts"] },
+    });
+
+    expect(plan.stats.loki_preview_touched).toBe(false);
+    expect(plan.loki_stories_to_run).toEqual(LOKI_FILES);
+    expect(plan.stats.loki_stories_to_run_rules).toBe(LOKI_FILES.length);
+    expect(plan.stats.loki_stories_to_run_usage).toBe(LOKI_FILES.length);
+    // Unit and E2E keep their rules-graph fallback.
+    expect(plan.fe_unit_specs_to_run).toEqual(UNIT_FILES.slice(0, 2));
+    expect(plan.e2e_specs_to_run).toEqual([]);
+  });
+
   it("runs the full e2e suite when no coverage manifest is available", () => {
-    const plan = createTestPlan({ ...baseInput, changedFiles: ["src/foo/x.ts"] });
+    const plan = createTestPlan({
+      ...baseInput,
+      changedFiles: ["src/foo/x.ts"],
+    });
 
     expect(plan.stats.e2e_specs_to_run_rules).toBe(E2E_FILES.length);
     expect(plan.stats.e2e_specs_to_run_usage).toBe(E2E_FILES.length);
@@ -229,21 +288,53 @@ describe("createTestPlan", () => {
     expect(plan.stats.fe_files_changed).toBe(5);
     expect(plan.stats.be_files_changed).toBe(3);
   });
+
+  it("does not build the usage graph when every suite runs in full", () => {
+    const loadFileDependencies = jest.fn(() => null);
+    createTestPlan({
+      ...baseInput,
+      changedFiles: ["src/foo/x.ts"],
+      sharedSourcesTouched: true,
+      loadFileDependencies,
+    });
+
+    expect(loadFileDependencies).not.toHaveBeenCalled();
+  });
+
+  it("builds the usage graph when any suite can be narrowed", () => {
+    const loadFileDependencies = jest.fn(() => null);
+    createTestPlan({
+      ...baseInput,
+      changedFiles: ["src/foo/x.ts"],
+      unitInfraTouched: true, // loki can still be narrowed
+      loadFileDependencies,
+    });
+
+    expect(loadFileDependencies).toHaveBeenCalledTimes(1);
+  });
 });
 
 describe("filterAffectedTests", () => {
-  it("keeps only tests inside affected modules", () => {
+  it("keeps tests inside affected modules, drops tests in unaffected ones", () => {
     const nodes = buildNodes(ELEMENTS);
     const affected = new Set(["feature/foo", "lib/utils"]);
     const tests = [
       "src/foo/foo.unit.spec.ts",
       "src/utils/colors.unit.spec.ts",
       "src/bar/bar.unit.spec.ts",
-      "docs/unrelated.unit.spec.ts",
     ];
     expect(filterAffectedTests(nodes, affected, tests)).toEqual([
       "src/foo/foo.unit.spec.ts",
       "src/utils/colors.unit.spec.ts",
     ]);
   });
+
+  it("keeps a test that maps to no module (unknown scope)", () => {
+    const nodes = buildNodes(ELEMENTS);
+    const affected = new Set(["feature/foo"]);
+    const tests = ["docs/unrelated.unit.spec.ts", "src/bar/bar.unit.spec.ts"];
+    expect(filterAffectedTests(nodes, affected, tests)).toEqual([
+      "docs/unrelated.unit.spec.ts",
+    ]);
+  });
 });

.github/scripts/bundle-size-stats-prepare.js

@@ -1,152 +0,0 @@
-/* eslint-disable import/no-commonjs */
-// Prepares the rows the bundle-size stats logger uploads to stats.metabase.com.
-//
-// For each measured (bundle, kind) it computes the delta — raw, gzipped and
-// brotli (as-served) bytes plus percent — against the previously *plotted* data
-// point (restored from a rolling cache), so the deltas can be charted directly.
-// It also decides whether this commit is worth recording at all: a point is kept
-// when the as-served size moved by at least MIN_DELTA_PERCENT, or when a new
-// bundle/kind appears. Only master builds run through here — releases form
-// non-linear lines whose deltas are meaningless, so they're not recorded (their
-// historical sizes are backfilled separately).
-//
-// buildStatsRows is pure (data in, data out) so it can be unit-tested; main()
-// is the thin I/O wrapper that reads env/files and writes the rows, cache and
-// step outputs.
-const fs = require("fs");
-const path = require("path");
-
-const deltaPercent = (current, base) =>
-  base ? Math.round(((current - base) * 10000) / base) / 100 : "";
-
-/**
- * Turn the current measurements + the last plotted point into upload rows, the
- * slim cache rows for the next diff, and the keep/skip decision.
- *
- * The significance threshold tracks the as-served size: brotli where the build
- * ships a precompressed .br, otherwise gzip. Current measurements always carry
- * brotliBytes (estimated when no .br shipped), but a cached base point recorded
- * before brotli logging may not, so the delta still falls back to gzip per row.
- */
-function buildStatsRows({ measurements, previous, threshold, date, commit, commitMessage, version }) {
-  const previousOf = (bundle, kind) => previous.find(row => row.bundle === bundle && row.kind === kind);
-
-  let maxServedDeltaPercent = 0;
-  let hasNewSeries = false;
-
-  const rows = measurements.map(measurement => {
-    const base = previousOf(measurement.bundle, measurement.kind);
-    const hasBrotli = measurement.brotliBytes != null && base?.brotliBytes != null;
-    const gzipDeltaPercent = deltaPercent(measurement.gzipBytes, base?.gzipBytes);
-    const brotliDeltaPercent = hasBrotli ? deltaPercent(measurement.brotliBytes, base.brotliBytes) : "";
-    if (!base) {
-      hasNewSeries = true;
-    } else {
-      const servedDeltaPercent = hasBrotli ? brotliDeltaPercent : gzipDeltaPercent;
-      maxServedDeltaPercent = Math.max(maxServedDeltaPercent, Math.abs(servedDeltaPercent));
-    }
-    return {
-      "Date": date,
-      "Version": version,
-      "Commit": commit,
-      "Bundle": measurement.bundle,
-      "Kind": measurement.kind, // "initial" or "total"
-      // The stats table carries a free-text Description column; append-csv
-      // requires every table column to be present. Populate it with the commit
-      // subject so the chart's points are self-describing.
-      "Description": commitMessage,
-      "Raw bytes": measurement.rawBytes,
-      "Gzip bytes": measurement.gzipBytes,
-      "Brotli bytes": measurement.brotliBytes, // as-served (shipped .br, else estimated)
-      "File count": measurement.fileCount,
-      "Raw bytes delta": base ? measurement.rawBytes - base.rawBytes : "",
-      "Gzip bytes delta": base ? measurement.gzipBytes - base.gzipBytes : "",
-      "Brotli bytes delta": hasBrotli ? measurement.brotliBytes - base.brotliBytes : "",
-      "Raw delta %": deltaPercent(measurement.rawBytes, base?.rawBytes),
-      "Gzip delta %": gzipDeltaPercent,
-      "Brotli delta %": brotliDeltaPercent,
-    };
-  });
-
-  const firstPoint = previous.length === 0;
-  const significant = firstPoint || hasNewSeries || maxServedDeltaPercent >= threshold;
-
-  // Slim rows the next run diffs against. The workflow only persists this to the
-  // cache when we actually push, so the cached reference always stays the last
-  // *plotted* point (cumulative drift is caught).
-  const cacheRows = measurements.map(({ bundle, kind, rawBytes, gzipBytes, brotliBytes }) => ({
-    bundle,
-    kind,
-    rawBytes,
-    gzipBytes,
-    brotliBytes,
-  }));
-
-  const reason = firstPoint
-    ? "first point"
-    : hasNewSeries
-      ? "new bundle/kind series"
-      : `max served Δ ${maxServedDeltaPercent.toFixed(2)}% (threshold ${threshold}%)`;
-
-  return { rows, cacheRows, significant, reason, maxServedDeltaPercent, firstPoint, hasNewSeries };
-}
-
-module.exports = { buildStatsRows };
-
-const readJson = filePath => (filePath && fs.existsSync(filePath) ? JSON.parse(fs.readFileSync(filePath, "utf8")) : null);
-const writeJson = (filePath, value) => {
-  fs.mkdirSync(path.dirname(filePath), { recursive: true });
-  fs.writeFileSync(filePath, JSON.stringify(value));
-};
-const setOutput = (env, name, value) => {
-  if (env.GITHUB_OUTPUT) {
-    fs.appendFileSync(env.GITHUB_OUTPUT, `${name}=${value}\n`);
-  }
-};
-
-// version.properties (extracted from the uberjar) carries the build's tag.
-// Non-release (master) builds report tag=vUNKNOWN, so leave Version empty there.
-function readVersion(versionPropsPath) {
-  const raw =
-    versionPropsPath && fs.existsSync(versionPropsPath)
-      ? (fs.readFileSync(versionPropsPath, "utf8").match(/^tag=(.*)$/m)?.[1]?.trim() ?? "")
-      : "";
-  return raw === "vUNKNOWN" ? "" : raw;
-}
-
-function main() {
-  const env = process.env;
-
-  const measurements = readJson(env.CURRENT);
-  if (!Array.isArray(measurements) || measurements.length === 0) {
-    console.error(`::error::No bundle measurements found at ${env.CURRENT}`);
-    process.exit(1);
-  }
-
-  const result = buildStatsRows({
-    measurements,
-    // The last plotted point, as slim rows: [{ bundle, kind, rawBytes, gzipBytes, brotliBytes }].
-    previous: readJson(env.LAST) || [],
-    threshold: Number(env.MIN_DELTA_PERCENT ?? 1),
-    date: new Date().toISOString().slice(0, 10), // YYYY-MM-DD
-    commit: (env.HEAD_SHA || "").slice(0, 12),
-    commitMessage: (env.COMMIT_MESSAGE || "").split("\n")[0], // subject line only
-    version: readVersion(env.VERSION_PROPS),
-  });
-
-  writeJson(env.ROWS_OUT, result.rows);
-  writeJson(env.CACHE_OUT, result.cacheRows);
-
-  console.log(`${result.significant ? "RECORD" : "SKIP"} — ${result.reason}`);
-
-  setOutput(env, "significant", result.significant ? "true" : "false");
-  setOutput(
-    env,
-    "max_delta_percent",
-    result.firstPoint || result.hasNewSeries ? "" : result.maxServedDeltaPercent.toFixed(2),
-  );
-}
-
-if (require.main === module) {
-  main();
-}

.github/scripts/bundle-size-stats-prepare.ts

@@ -0,0 +1,227 @@
+// Prepares the rows the bundle-size stats logger imports into eng-stats-importer.
+//
+// For each measured (bundle, kind) it computes the delta — raw, gzipped and
+// brotli (as-served) bytes plus percent — against the previously *plotted* data
+// point (restored from a rolling cache), so the deltas can be charted directly.
+// It also decides whether this commit is worth recording at all: a point is kept
+// when the as-served size moved by at least MIN_DELTA_PERCENT, or when a new
+// bundle/kind appears. Only master builds run through here — releases form
+// non-linear lines whose deltas are meaningless, so they're not recorded (their
+// historical sizes are backfilled separately).
+//
+// buildStatsRows is pure (data in, data out) so it can be unit-tested; main()
+// is the thin I/O wrapper that reads env/files and writes the rows, cache and
+// step outputs.
+import {
+  appendFileSync,
+  existsSync,
+  mkdirSync,
+  readFileSync,
+  writeFileSync,
+} from "node:fs";
+import { dirname } from "node:path";
+
+/** One measurement emitted by measure-bundle-sizes. */
+export interface Measurement {
+  bundle: string;
+  kind: "initial" | "total";
+  rawBytes: number;
+  gzipBytes: number;
+  brotliBytes: number;
+  fileCount: number;
+}
+
+/**
+ * The slim row cached between runs, holding the last *plotted* point.
+ * `brotliBytes` is optional because a point cached before brotli logging
+ * landed does not carry it — see buildStatsRows' per-row gzip fallback.
+ */
+export type CacheRow = Pick<Measurement, "bundle" | "kind" | "rawBytes" | "gzipBytes"> & {
+  brotliBytes?: number;
+};
+
+export interface BuildStatsRowsInput {
+  measurements: Measurement[];
+  previous: CacheRow[];
+  threshold: number;
+  date: string;
+  commit: string;
+  commitMessage: string;
+  version: string;
+}
+
+/** An upload row, keyed by the importer's column display names. */
+export type StatsRow = Record<string, string | number | null>;
+
+export interface BuildStatsRowsResult {
+  rows: StatsRow[];
+  cacheRows: CacheRow[];
+  significant: boolean;
+  reason: string;
+  maxServedDeltaPercent: number;
+  firstPoint: boolean;
+  hasNewSeries: boolean;
+}
+
+// null, not "", for an absent delta: the stats importer coerces values
+// strictly and rejects "" for a numeric column.
+const deltaPercent = (current: number, base: number | undefined | null): number | null =>
+  base ? Math.round(((current - base) * 10000) / base) / 100 : null;
+
+/**
+ * Turn the current measurements + the last plotted point into upload rows, the
+ * slim cache rows for the next diff, and the keep/skip decision.
+ *
+ * The significance threshold tracks the as-served size: brotli where the build
+ * ships a precompressed .br, otherwise gzip. Current measurements always carry
+ * brotliBytes (estimated when no .br shipped), but a cached base point recorded
+ * before brotli logging may not, so the delta still falls back to gzip per row.
+ */
+export function buildStatsRows({
+  measurements,
+  previous,
+  threshold,
+  date,
+  commit,
+  commitMessage,
+  version,
+}: BuildStatsRowsInput): BuildStatsRowsResult {
+  const previousOf = (bundle: string, kind: string) =>
+    previous.find((row) => row.bundle === bundle && row.kind === kind);
+
+  let maxServedDeltaPercent = 0;
+  let hasNewSeries = false;
+
+  const rows = measurements.map((measurement): StatsRow => {
+    const base = previousOf(measurement.bundle, measurement.kind);
+    // Non-null only when BOTH sides carry brotli: a point cached before brotli
+    // logging landed has none, and that row falls back to the gzip delta.
+    const baseBrotli =
+      measurement.brotliBytes != null && base?.brotliBytes != null ? base.brotliBytes : null;
+    const gzipDeltaPercent = deltaPercent(measurement.gzipBytes, base?.gzipBytes);
+    const brotliDeltaPercent =
+      baseBrotli != null ? deltaPercent(measurement.brotliBytes, baseBrotli) : null;
+    if (!base) {
+      hasNewSeries = true;
+    } else {
+      const servedDeltaPercent = baseBrotli != null ? brotliDeltaPercent : gzipDeltaPercent;
+      maxServedDeltaPercent = Math.max(maxServedDeltaPercent, Math.abs(servedDeltaPercent ?? 0));
+    }
+    return {
+      Date: date,
+      Version: version,
+      Commit: commit,
+      Bundle: measurement.bundle,
+      Kind: measurement.kind, // "initial" or "total"
+      // The stats table carries a free-text Description column. Populate it
+      // with the commit subject so the chart's points are self-describing.
+      Description: commitMessage,
+      "Raw bytes": measurement.rawBytes,
+      "Gzip bytes": measurement.gzipBytes,
+      "Brotli bytes": measurement.brotliBytes, // as-served (shipped .br, else estimated)
+      "File count": measurement.fileCount,
+      "Raw bytes delta": base ? measurement.rawBytes - base.rawBytes : null,
+      "Gzip bytes delta": base ? measurement.gzipBytes - base.gzipBytes : null,
+      "Brotli bytes delta": baseBrotli != null ? measurement.brotliBytes - baseBrotli : null,
+      "Raw delta %": deltaPercent(measurement.rawBytes, base?.rawBytes),
+      "Gzip delta %": gzipDeltaPercent,
+      "Brotli delta %": brotliDeltaPercent,
+    };
+  });
+
+  const firstPoint = previous.length === 0;
+  const significant = firstPoint || hasNewSeries || maxServedDeltaPercent >= threshold;
+
+  // Slim rows the next run diffs against. The workflow only persists this to the
+  // cache when we actually push, so the cached reference always stays the last
+  // *plotted* point (cumulative drift is caught).
+  const cacheRows = measurements.map(
+    ({ bundle, kind, rawBytes, gzipBytes, brotliBytes }): CacheRow => ({
+      bundle,
+      kind,
+      rawBytes,
+      gzipBytes,
+      brotliBytes,
+    }),
+  );
+
+  const reason = firstPoint
+    ? "first point"
+    : hasNewSeries
+      ? "new bundle/kind series"
+      : `max served Δ ${maxServedDeltaPercent.toFixed(2)}% (threshold ${threshold}%)`;
+
+  return {
+    rows,
+    cacheRows,
+    significant,
+    reason,
+    maxServedDeltaPercent,
+    firstPoint,
+    hasNewSeries,
+  };
+}
+
+const readJson = <T,>(filePath: string | undefined): T | null =>
+  filePath && existsSync(filePath) ? (JSON.parse(readFileSync(filePath, "utf8")) as T) : null;
+
+const writeJson = (filePath: string, value: unknown) => {
+  mkdirSync(dirname(filePath), { recursive: true });
+  writeFileSync(filePath, JSON.stringify(value));
+};
+
+const setOutput = (name: string, value: string) => {
+  if (process.env.GITHUB_OUTPUT) {
+    appendFileSync(process.env.GITHUB_OUTPUT, `${name}=${value}\n`);
+  }
+};
+
+// version.properties (extracted from the uberjar) carries the build's tag.
+// Non-release (master) builds report tag=vUNKNOWN, so leave Version empty there.
+function readVersion(versionPropsPath: string | undefined): string {
+  const raw =
+    versionPropsPath && existsSync(versionPropsPath)
+      ? (readFileSync(versionPropsPath, "utf8").match(/^tag=(.*)$/m)?.[1]?.trim() ?? "")
+      : "";
+  return raw === "vUNKNOWN" ? "" : raw;
+}
+
+export function main() {
+  const env = process.env;
+
+  const measurements = readJson<Measurement[]>(env.CURRENT);
+  if (!Array.isArray(measurements) || measurements.length === 0) {
+    console.error(`::error::No bundle measurements found at ${env.CURRENT}`);
+    process.exit(1);
+  }
+
+  const result = buildStatsRows({
+    measurements,
+    // The last plotted point, as slim rows: [{ bundle, kind, rawBytes, gzipBytes, brotliBytes }].
+    previous: readJson<CacheRow[]>(env.LAST) || [],
+    threshold: Number(env.MIN_DELTA_PERCENT ?? 1),
+    // The commit's own time rather than the day it was measured, so the merges
+    // of one day keep their order on the chart.
+    date: new Date(env.COMMIT_TIMESTAMP || Date.now()).toISOString(),
+    commit: (env.HEAD_SHA || "").slice(0, 12),
+    commitMessage: (env.COMMIT_MESSAGE || "").split("\n")[0], // subject line only
+    version: readVersion(env.VERSION_PROPS),
+  });
+
+  writeJson(env.ROWS_OUT!, result.rows);
+  writeJson(env.CACHE_OUT!, result.cacheRows);
+
+  console.log(`${result.significant ? "RECORD" : "SKIP"} — ${result.reason}`);
+
+  setOutput("significant", result.significant ? "true" : "false");
+  setOutput(
+    "max_delta_percent",
+    result.firstPoint || result.hasNewSeries ? "" : result.maxServedDeltaPercent.toFixed(2),
+  );
+}
+
+// Only run the I/O wrapper when invoked directly, so importing buildStatsRows
+// (from the spec) has no side effects.
+if ((import.meta as ImportMeta & { main?: boolean }).main) {
+  main();
+}

.github/scripts/bundle-size-stats-prepare.unit.spec.js

@@ -1,87 +0,0 @@
-const { buildStatsRows } = require("./bundle-size-stats-prepare");
-
-const meta = { date: "2026-06-30", commit: "abc123", commitMessage: "Fix the thing (#123)", version: "" };
-const measurement = (over = {}) => ({
-  bundle: "embedding-sdk-chunked",
-  kind: "total",
-  rawBytes: 1000,
-  gzipBytes: 400,
-  brotliBytes: 300,
-  fileCount: 3,
-  ...over,
-});
-
-describe("buildStatsRows", () => {
-  it("records the first point and leaves every delta empty", () => {
-    const result = buildStatsRows({
-      ...meta,
-      measurements: [measurement()],
-      previous: [],
-      threshold: 1,
-    });
-
-    expect(result.firstPoint).toBe(true);
-    expect(result.significant).toBe(true);
-    expect(result.reason).toBe("first point");
-    expect(result.rows[0]["Gzip bytes delta"]).toBe("");
-    expect(result.rows[0]["Brotli delta %"]).toBe("");
-    expect(result.rows[0]["Description"]).toBe("Fix the thing (#123)");
-    expect(result.cacheRows[0]).toEqual({
-      bundle: "embedding-sdk-chunked",
-      kind: "total",
-      rawBytes: 1000,
-      gzipBytes: 400,
-      brotliBytes: 300,
-    });
-  });
-
-  it("records a never-seen bundle/kind as a new series", () => {
-    const result = buildStatsRows({
-      ...meta,
-      measurements: [measurement({ bundle: "app", kind: "initial" })],
-      previous: [{ bundle: "app", kind: "total", rawBytes: 1, gzipBytes: 1, brotliBytes: 1 }],
-      threshold: 99,
-    });
-
-    expect(result.hasNewSeries).toBe(true);
-    expect(result.significant).toBe(true);
-    expect(result.reason).toBe("new bundle/kind series");
-  });
-
-  it("gates significance on the brotli (as-served) delta when both sides have it", () => {
-    const previous = [{ bundle: "embedding-sdk-chunked", kind: "total", rawBytes: 1000, gzipBytes: 400, brotliBytes: 300 }];
-
-    const big = buildStatsRows({
-      ...meta,
-      measurements: [measurement({ brotliBytes: 315, gzipBytes: 400 })], // brotli +5%, gzip 0%
-      previous,
-      threshold: 1,
-    });
-    expect(big.maxServedDeltaPercent).toBeCloseTo(5);
-    expect(big.significant).toBe(true);
-    expect(big.rows[0]["Brotli delta %"]).toBeCloseTo(5);
-
-    const small = buildStatsRows({
-      ...meta,
-      measurements: [measurement({ brotliBytes: 301, gzipBytes: 999 })], // brotli +0.33%, gzip ignored
-      previous,
-      threshold: 1,
-    });
-    expect(small.significant).toBe(false);
-    expect(small.reason).toContain("threshold 1%");
-  });
-
-  it("falls back to the gzip delta when the cached base predates brotli logging", () => {
-    const result = buildStatsRows({
-      ...meta,
-      measurements: [measurement({ gzipBytes: 440, brotliBytes: 300 })], // gzip +10%
-      previous: [{ bundle: "embedding-sdk-chunked", kind: "total", rawBytes: 1000, gzipBytes: 400 }],
-      threshold: 1,
-    });
-
-    expect(result.maxServedDeltaPercent).toBeCloseTo(10);
-    expect(result.significant).toBe(true);
-    expect(result.rows[0]["Brotli bytes delta"]).toBe(""); // no base brotli to diff against
-    expect(result.rows[0]["Gzip delta %"]).toBeCloseTo(10);
-  });
-});

.github/scripts/bundle-size-stats-prepare.unit.spec.ts

@@ -0,0 +1,105 @@
+import {
+  buildStatsRows,
+  type CacheRow,
+  type Measurement,
+} from "./bundle-size-stats-prepare";
+
+const meta = {
+  date: "2026-06-30",
+  commit: "abc123",
+  commitMessage: "Fix the thing (#123)",
+  version: "",
+};
+const measurement = (over: Partial<Measurement> = {}): Measurement => ({
+  bundle: "embedding-sdk-chunked",
+  kind: "total",
+  rawBytes: 1000,
+  gzipBytes: 400,
+  brotliBytes: 300,
+  fileCount: 3,
+  ...over,
+});
+
+describe("buildStatsRows", () => {
+  it("records the first point and leaves every delta empty", () => {
+    const result = buildStatsRows({
+      ...meta,
+      measurements: [measurement()],
+      previous: [],
+      threshold: 1,
+    });
+
+    expect(result.firstPoint).toBe(true);
+    expect(result.significant).toBe(true);
+    expect(result.reason).toBe("first point");
+    expect(result.rows[0]["Gzip bytes delta"]).toBeNull();
+    expect(result.rows[0]["Brotli delta %"]).toBeNull();
+    expect(result.rows[0]["Description"]).toBe("Fix the thing (#123)");
+    expect(result.cacheRows[0]).toEqual({
+      bundle: "embedding-sdk-chunked",
+      kind: "total",
+      rawBytes: 1000,
+      gzipBytes: 400,
+      brotliBytes: 300,
+    });
+  });
+
+  it("records a never-seen bundle/kind as a new series", () => {
+    const result = buildStatsRows({
+      ...meta,
+      measurements: [measurement({ bundle: "app", kind: "initial" })],
+      previous: [{ bundle: "app", kind: "total", rawBytes: 1, gzipBytes: 1, brotliBytes: 1 }],
+      threshold: 99,
+    });
+
+    expect(result.hasNewSeries).toBe(true);
+    expect(result.significant).toBe(true);
+    expect(result.reason).toBe("new bundle/kind series");
+  });
+
+  it("gates significance on the brotli (as-served) delta when both sides have it", () => {
+    const previous: CacheRow[] = [
+      {
+        bundle: "embedding-sdk-chunked",
+        kind: "total",
+        rawBytes: 1000,
+        gzipBytes: 400,
+        brotliBytes: 300,
+      },
+    ];
+
+    const big = buildStatsRows({
+      ...meta,
+      measurements: [measurement({ brotliBytes: 315, gzipBytes: 400 })], // brotli +5%, gzip 0%
+      previous,
+      threshold: 1,
+    });
+    expect(big.maxServedDeltaPercent).toBeCloseTo(5);
+    expect(big.significant).toBe(true);
+    expect(big.rows[0]["Brotli delta %"]).toBeCloseTo(5);
+
+    const small = buildStatsRows({
+      ...meta,
+      measurements: [measurement({ brotliBytes: 301, gzipBytes: 999 })], // brotli +0.33%, gzip ignored
+      previous,
+      threshold: 1,
+    });
+    expect(small.significant).toBe(false);
+    expect(small.reason).toContain("threshold 1%");
+  });
+
+  it("falls back to the gzip delta when the cached base predates brotli logging", () => {
+    const result = buildStatsRows({
+      ...meta,
+      measurements: [measurement({ gzipBytes: 440, brotliBytes: 300 })], // gzip +10%
+      // No brotliBytes: this point was cached before brotli logging landed.
+      previous: [{ bundle: "embedding-sdk-chunked", kind: "total", rawBytes: 1000, gzipBytes: 400 }],
+      threshold: 1,
+    });
+
+    expect(result.maxServedDeltaPercent).toBeCloseTo(10);
+    expect(result.significant).toBe(true);
+    expect(result.rows[0]["Brotli bytes delta"]).toBeNull(); // no base brotli to diff against
+    expect(result.rows[0]["Gzip delta %"]).toBeCloseTo(10);
+  });
+});

.github/scripts/cache-keys.sh

@@ -0,0 +1,162 @@
+#!/usr/bin/env bash
+# Single definition of every CI dependency cache: what it holds, what identifies it, what it falls back to.
+#
+# A GitHub cache entry is identified by its key, a hash of the declared path list, and the ref that saved
+# it. A step declaring a different path list than the one a cache was saved with computes a different
+# identity and can never match it, whatever its key says. So paths and keys are emitted together here and
+# every cache step takes both from this script.
+#
+# Emits `name=value` lines in $GITHUB_OUTPUT format:
+#
+#   .github/scripts/cache-keys.sh >> "$GITHUB_OUTPUT"
+#
+# Run it with no redirect to see the whole scheme, or pass one name to print a single value:
+#
+#   .github/scripts/cache-keys.sh
+#   .github/scripts/cache-keys.sh m2-key
+#
+# Hashes are computed here rather than with GitHub's hashFiles() so that a local run and a CI run of the
+# same commit produce the same keys, and so that an empty match can fail loudly - a hashFiles() call that
+# matches nothing silently yields "", collapsing the key onto its own restore prefix and pointing every
+# dependency set at one entry.
+
+set -euo pipefail
+
+cd "$(git rev-parse --show-toplevel)"
+
+OS="${RUNNER_OS:-$(uname -s)}"
+[ "$OS" = "Darwin" ] && OS="macOS"
+
+sha256() {
+  if command -v sha256sum >/dev/null 2>&1; then
+    sha256sum | cut -d' ' -f1
+  else
+    shasum -a 256 | cut -d' ' -f1
+  fi
+}
+
+# Digest of a set of files: hash each one, then hash the concatenation, so the result depends on every
+# file's contents and on which files exist.
+digest() {
+  local f
+  if [ "$#" -eq 0 ]; then
+    echo "::error::cache-keys.sh: no files matched; refusing to emit a key that would collide across dependency sets" >&2
+    exit 1
+  fi
+  for f in "$@"; do
+    [ -f "$f" ] || { echo "::error::cache-keys.sh: $f does not exist" >&2; exit 1; }
+    sha256 < "$f"
+  done | sha256
+}
+
+shopt -s nullglob
+DEPS_FILES=(deps.edn
+            bin/lint-migrations-file/deps.edn
+            bin/load-namespaces/deps.edn
+            modules/drivers/deps.edn
+            modules/drivers/*/deps.edn)
+shopt -u nullglob
+
+DEPS_HASH="$(digest "${DEPS_FILES[@]}")"
+LOCK_HASH="$(digest bun.lock)"
+
+# The Cypress binary depends on the Cypress version alone, so keying it on the whole lockfile would
+# throw away a 200MB download every time any frontend dependency moved.
+#
+# Reading a version out of a lockfile with a regex is only safe while exactly one line matches. Insist
+# on that rather than taking the first of several: a second match means the format moved under us, and
+# picking one at random would key the binary under a version it is not.
+CYPRESS_VERSIONS="$(sed -n 's/.*"cypress": \["cypress@\([^"]*\)".*/\1/p' bun.lock)"
+CYPRESS_MATCHES="$(printf '%s\n' "$CYPRESS_VERSIONS" | grep -c . || true)"
+if [ "$CYPRESS_MATCHES" != "1" ]; then
+  echo "::error::cache-keys.sh: expected exactly one resolved cypress version in bun.lock, found $CYPRESS_MATCHES" >&2
+  exit 1
+fi
+CYPRESS_VERSION="$CYPRESS_VERSIONS"
+
+# The Clojure CLI version CI installs. It lives here rather than in prepare-backend so that the version
+# and the key that identifies its cache entry cannot drift apart.
+CLOJURE_VERSION="1.12.0.1488"
+
+# An incremental lint cache is only ever an accelerator, so it keys on the commit and always falls back
+# to the newest entry on the prefix. The exact key never pre-exists, which keeps the entry current.
+ESLINT_SHA="${GITHUB_SHA:-$(git rev-parse HEAD)}"
+
+emit_multiline() {
+  local name="$1"; shift
+  printf '%s<<CACHE_KEYS_EOF\n' "$name"
+  printf '%s\n' "$@"
+  printf 'CACHE_KEYS_EOF\n'
+}
+
+# Paths under the home directory are emitted absolute rather than as `~/...`. actions/cache would expand
+# a tilde, but a shell assigning one of these to a variable would not, and would go on to create a
+# directory named `~`. Paths inside the checkout stay relative; actions/cache resolves those against the
+# workspace.
+spec() {
+  emit_multiline m2-path "$HOME/.m2" "$HOME/.gitlibs" "$HOME/.deps.clj" 'bin/bb'
+  echo "m2-key=M2-$OS-$DEPS_HASH"
+  echo "m2-restore-key=M2-$OS-"
+
+  # Pinned rather than discovered via `bun pm cache` so that the path is known before bun is installed;
+  # prepare-frontend exports BUN_INSTALL_CACHE_DIR to match and fails if bun disagrees.
+  echo "bun-store-path=$HOME/.bun/install/cache"
+  echo "bun-store-key=bun-store-$OS-$LOCK_HASH"
+  echo "bun-store-restore-key=bun-store-$OS-"
+
+  # No restore-key: an entry from another version installs a working `clojure` of the wrong version, and
+  # the freshness check in prepare-backend - running the binary - would accept it.
+  #
+  # The installer bakes this prefix into the clj/clojure shims, so the tree only works when restored to
+  # the same absolute path it was built at; prepare-backend reinstalls when it is not.
+  echo "clojure-path=$HOME/.clojure-cli"
+  echo "clojure-key=clojure-cli-$OS-$CLOJURE_VERSION"
+  echo "clojure-version=$CLOJURE_VERSION"
+
+  echo "cypress-path=$HOME/.cache/Cypress"
+  echo "cypress-key=cypress-$OS-$CYPRESS_VERSION"
+  echo "cypress-restore-key=cypress-$OS-"
+
+  echo "eslint-path=.eslintcache"
+  echo "eslint-key=eslint-$OS-$ESLINT_SHA"
+  echo "eslint-restore-key=eslint-$OS-"
+}
+
+# Print one output's value, including the multiline form, and fail on a name that does not exist. A
+# caller that silently received "" would go on to build a key with a hole in it.
+query() {
+  local want="$1" line delim found=0 in_block=0
+  while IFS= read -r line; do
+    if [ "$in_block" = 1 ]; then
+      if [ "$line" = "$delim" ]; then
+        in_block=0
+      else
+        printf '%s\n' "$line"
+      fi
+      continue
+    fi
+    case "$line" in
+      "$want="*)
+        printf '%s\n' "${line#*=}"
+        found=1
+        ;;
+      "$want<<"*)
+        delim="${line#*<<}"
+        in_block=1
+        found=1
+        ;;
+    esac
+  done <<EOF
+$(spec)
+EOF
+  if [ "$found" = 0 ]; then
+    echo "::error::cache-keys.sh: no output named '$want'" >&2
+    exit 1
+  fi
+}
+
+if [ "$#" -eq 0 ]; then
+  spec
+else
+  query "$1"
+fi

.github/scripts/cache-keys.unit.spec.ts

@@ -0,0 +1,80 @@
+import { execFileSync } from "child_process";
+import { join } from "path";
+
+const SCRIPT = join(__dirname, "cache-keys.sh");
+
+const CACHES = ["m2", "bun-store", "cypress", "eslint"];
+
+// stderr is inherited by default, so the deliberate-failure case below would print a literal
+// `::error::` line - which GitHub Actions reads as an annotation directive, making a passing run
+// annotate itself with an error.
+const run = (args: string[] = [], env: NodeJS.ProcessEnv = {}, quiet = false) =>
+  execFileSync(SCRIPT, args, {
+    encoding: "utf8",
+    stdio: quiet ? ["ignore", "pipe", "ignore"] : "pipe",
+    env: { ...process.env, RUNNER_OS: "Linux", GITHUB_SHA: "abc123", ...env },
+  });
+
+const get = (name: string, env: NodeJS.ProcessEnv = {}) =>
+  run([name], env).trimEnd();
+
+describe("cache-keys.sh", () => {
+  it("is deterministic for a given tree", () => {
+    expect(run()).toEqual(run());
+  });
+
+  it("emits every cache's path, key and restore key", () => {
+    for (const cache of CACHES) {
+      expect(get(`${cache}-path`)).not.toEqual("");
+      expect(get(`${cache}-key`)).not.toEqual("");
+      expect(get(`${cache}-restore-key`)).not.toEqual("");
+    }
+  });
+
+  // Silently returning "" for a name that does not exist is how a caller ends up building a key with a
+  // hole in it.
+  it("fails on an unknown output name", () => {
+    expect(() => run(["no-such-output"], {}, true)).toThrow();
+  });
+
+  // A key equal to its own restore prefix points every dependency set at one entry, and nothing reports
+  // it. This is the failure the script exists to prevent.
+  it("never emits a key equal to its own restore prefix", () => {
+    for (const cache of CACHES) {
+      const key = get(`${cache}-key`);
+      const prefix = get(`${cache}-restore-key`);
+      expect(key.startsWith(prefix)).toBe(true);
+      expect(key.length).toBeGreaterThan(prefix.length);
+    }
+  });
+
+  it("scopes every key to the runner OS", () => {
+    for (const cache of CACHES) {
+      expect(get(`${cache}-key`, { RUNNER_OS: "Linux" })).not.toEqual(
+        get(`${cache}-key`, { RUNNER_OS: "macOS" }),
+      );
+    }
+  });
+
+  // Home paths must be absolute: actions/cache expands a tilde but a shell assigning one to a variable
+  // does not, and would create a directory literally named `~`.
+  it("emits absolute paths for home directory locations", () => {
+    expect(get("bun-store-path").startsWith("/")).toBe(true);
+    expect(get("cypress-path").startsWith("/")).toBe(true);
+    for (const line of get("m2-path").split("\n")) {
+      expect(line.startsWith("~")).toBe(false);
+    }
+  });
+
+  // The Cypress binary depends on the Cypress version alone, so an unrelated dependency bump must not
+  // invalidate a 200MB download.
+  it("keys the Cypress binary on the resolved version, not the lockfile", () => {
+    expect(get("cypress-key")).toMatch(/^cypress-Linux-\d+\.\d+\.\d+/);
+  });
+
+  it("keys the ESLint cache on the commit", () => {
+    expect(get("eslint-key", { GITHUB_SHA: "deadbeef" })).toEqual(
+      "eslint-Linux-deadbeef",
+    );
+  });
+});

.github/scripts/check-job-timeouts.sh

@@ -0,0 +1,71 @@
+#!/usr/bin/env bash
+# Fails when a job in .github/workflows/ does not set `timeout-minutes`.
+#
+# Without it a job inherits GitHub's 6-hour default, so a hung job burns six hours of runner time -
+# and holds up everything queued behind it - before anyone notices. actionlint cannot check this: its
+# rule set is compiled in and .github/actionlint.yaml only takes `self-hosted-runner`,
+# `config-variables`, and `paths` (which suppresses findings rather than adding them). Hence this
+# script.
+#
+# The rule is per job: a `timeout-minutes` on a step does not satisfy it, and steps are not required
+# to carry one of their own.
+#
+# Jobs that call a reusable workflow (`uses:` at the job level) are skipped - GitHub rejects
+# `timeout-minutes` there. The called workflow's own jobs are checked when it lives in this repo.
+#
+#   .github/scripts/check-job-timeouts.sh [workflow-file ...]
+#
+# With no arguments it checks every workflow; CI passes the files that changed, like actionlint does.
+
+set -euo pipefail
+
+# Arguments are used as given, so the paths in the annotations match what the caller passed. Without
+# them the full scan has to run from the repo root.
+if [ $# -gt 0 ]; then
+  workflows=("$@")
+else
+  cd "$(git rev-parse --show-toplevel)"
+
+  shopt -s nullglob
+  workflows=(.github/workflows/*.yml .github/workflows/*.yaml)
+
+  if [ ${#workflows[@]} -eq 0 ]; then
+    echo "::error::check-job-timeouts.sh: no workflow files found under .github/workflows/" >&2
+    exit 1
+  fi
+fi
+
+status=0
+
+for file in "${workflows[@]}"; do
+  # `awk NF` drops the blank line yq emits when a file has nothing to report.
+  missing="$(
+    # --header-preprocess=false: yq otherwise slurps any leading comment block before parsing, which
+    # shifts every line number it reports by the size of that block.
+    yq --header-preprocess=false '
+      .jobs
+      | to_entries
+      | .[]
+      | select(((.value | has("timeout-minutes")) or (.value | has("uses"))) | not)
+      | [(.key | line), .key]
+      | @tsv
+    ' "$file" | awk NF
+  )"
+
+  [ -n "$missing" ] || continue
+
+  while IFS=$'\t' read -r line job; do
+    echo "::error file=${file},line=${line}::Job \"${job}\" does not set a job-level timeout-minutes" >&2
+  done <<< "$missing"
+
+  status=1
+done
+
+if [ "$status" -ne 0 ]; then
+  echo >&2
+  echo "Every job must set an explicit timeout-minutes; without one it inherits GitHub's 6-hour default." >&2
+  echo "Pick a value with headroom over the job's normal runtime." >&2
+  exit 1
+fi
+
+echo "All jobs in the ${#workflows[@]} workflow file(s) checked set timeout-minutes."

.github/scripts/check-preresolve-aliases.sh

@@ -0,0 +1,109 @@
+#!/usr/bin/env bash
+# Fails when a Clojure classpath used by CI is not pre-resolved by cache-warm.
+#
+# tools.deps selects dependency versions globally per classpath, so two alias combinations can resolve
+# the same transitive library to different versions. A combination the warm job never resolved is
+# therefore not merely absent from the cache - the cache holds *a* version of those libraries, just not
+# the one this classpath wants, and the job fetches its delta straight from Maven Central on every run.
+# That is the intermittent-403 failure of DEV-2094, and it is invisible: the build still passes.
+#
+# Nothing about a missing combination shows up at runtime, so this check is the only thing standing
+# between a newly added alias combination and a permanently half-cold cache.
+#
+#   .github/scripts/check-preresolve-aliases.sh
+
+set -euo pipefail
+
+cd "$(git rev-parse --show-toplevel)"
+
+WARM=.github/workflows/cache-warm.yml
+
+# Invocations deliberately left out of the warm job. Each needs a reason, because the default answer is
+# to add the combination to the list instead.
+WAIVED="$(
+  cat <<'EOF'
+:deps
+:outdated
+EOF
+)"
+# :deps      - tools.deps built-in used by write-poms.sh; contributes no dependencies of its own.
+# :outdated  - scheduled dependency-bump workflow only; a cold resolve there costs nothing anyone waits on.
+
+# Dependency roots and alias combinations the warm job pre-resolves.
+declared="$({
+  sed -n '/^[[:space:]]*combos=(/,/^ *)/p' "$WARM" \
+    | grep -oE '":[^"]*"' \
+    | tr -d '"' \
+    | sed 's#^#.|#'
+  sed -n '/^[[:space:]]*nested_combos=(/,/^ *)/p' "$WARM" \
+    | grep -oE '"[^"]+\|:[^"]+"' \
+    | tr -d '"'
+} | sort -u)"
+if [ -z "$declared" ]; then
+  echo "::error::check-preresolve-aliases.sh: found no pre-resolved classpaths in $WARM" >&2
+  exit 1
+fi
+
+# Expressions we know how to expand. An unrecognised one has to stop the check rather than be skipped:
+# silently ignoring it is how a whole matrix of combinations would go unchecked.
+unknown="$(grep -rhoE '\$\{\{[^}]*\}\}' --include='*' \
+             --exclude='*.png' --exclude='*.jpg' .github/ 2>/dev/null \
+           | sort -u | grep -v 'edition' || true)"
+
+scan() { # scan <edition>: dependency root and aliases used by .github Clojure invocations
+  grep -rhE 'clojure[[:space:]]+(-P[[:space:]]+)?-[XMATP]?:' \
+       --include='*' --exclude='*.png' --exclude='*.jpg' .github/ 2>/dev/null \
+    | sed "s/\\\${{[^}]*edition[^}]*}}/$1/g" \
+    | grep -oE 'clojure[[:space:]]+(-P[[:space:]]+)?-[XMATP]?:[A-Za-z0-9:_./-]+' \
+    | grep -oE ':[A-Za-z0-9:_./-]+' \
+    | sed -e 's/:$//' -e 's#^#.|#'
+}
+
+scan_project_tests() { # scan_project_tests <function> <dependency-root>
+  # Mage shell commands are vectors split across lines, so flatten each function body before
+  # extracting its alias.
+  sed -n "/(defn- $1 /,/^(defn/p" mage/src/mage/project_tests.clj \
+    | tr '\n' ' ' \
+    | grep -oE '"clojure"[[:space:]]+("-P"[[:space:]]+)?"-[XMATP]?:[A-Za-z0-9:_./-]+' \
+    | grep -oE ':[A-Za-z0-9:_./-]+' \
+    | sed -e 's/:$//' -e "s#^#$2|#"
+}
+
+# Check each scan separately. One scan still finding commands would otherwise conceal that another has
+# stopped matching, which silently drops everything it used to cover.
+require_scan() { # require_scan <what> <result>
+  [ -n "$2" ] && return
+  echo "::error::check-preresolve-aliases.sh: found no Clojure invocation in $1; the scan pattern no longer matches" >&2
+  exit 1
+}
+workflow_checks=$( { scan ee; scan oss; } || true)
+clojure_checks=$(scan_project_tests run-clojure-checks! . || true)
+migration_checks=$(scan_project_tests run-migration-checks! bin/lint-migrations-file || true)
+require_scan ".github/" "$workflow_checks"
+require_scan "run-clojure-checks! (mage/src/mage/project_tests.clj)" "$clojure_checks"
+require_scan "run-migration-checks! (mage/src/mage/project_tests.clj)" "$migration_checks"
+
+scanned="$(printf '%s\n' "$workflow_checks" "$clojure_checks" "$migration_checks" | sort -u)"
+
+found="$( {
+  printf '%s\n' "$scanned"
+  # build-scripts.yml runs this classpath from its own dependency root.
+  printf '%s\n' 'bin/load-namespaces|:test'
+} | sort -u )"
+
+covered="$( {
+  printf '%s\n' "$declared"
+  printf '%s\n' "$WAIVED" | sed 's#^#.|#'
+} | sort -u)"
+missing="$(comm -23 <(printf '%s\n' "$found") <(printf '%s\n' "$covered") || true)"
+
+if [ -n "$missing" ]; then
+  echo "::error::Clojure classpaths used by CI that cache-warm does not pre-resolve:" >&2
+  printf '%s\n' "$missing" | sed 's/^/  /' >&2
+  echo >&2
+  echo "Add each to the matching root or nested combo list in $WARM, or waive it here with a reason." >&2
+  echo "Leaving it uncovered means those jobs re-fetch their version deltas from Maven on every run." >&2
+  exit 1
+fi
+
+echo "All $(printf '%s\n' "$found" | grep -c .) Clojure classpaths used by CI are pre-resolved."

.github/scripts/check-unit-test-results.ts

@@ -0,0 +1,182 @@
+import { spawnSync } from "node:child_process";
+import { readFileSync, statSync } from "node:fs";
+import { join } from "node:path";
+
+const TEST_UNIT_COMMAND = ["bun", "run", "test-unit-keep-cljs"];
+
+type SuiteResult = {
+  name: string;
+  status: string;
+  assertionResults: unknown[];
+};
+
+type JestResults = {
+  wasInterrupted: boolean;
+  testResults: SuiteResult[];
+};
+
+function isSuiteResult(value: unknown): value is SuiteResult {
+  return (
+    typeof value === "object" &&
+    value !== null &&
+    "name" in value &&
+    typeof value.name === "string" &&
+    "status" in value &&
+    typeof value.status === "string" &&
+    "assertionResults" in value &&
+    Array.isArray(value.assertionResults)
+  );
+}
+
+function readResults(file: string): JestResults | null {
+  const value = readJson(file);
+  if (
+    typeof value === "object" &&
+    value !== null &&
+    "wasInterrupted" in value &&
+    typeof value.wasInterrupted === "boolean" &&
+    "testResults" in value &&
+    Array.isArray(value.testResults) &&
+    value.testResults.every(isSuiteResult)
+  ) {
+    return {
+      wasInterrupted: value.wasInterrupted,
+      testResults: value.testResults,
+    };
+  }
+  return null;
+}
+
+function parseJson(text: string): unknown {
+  try {
+    return JSON.parse(text);
+  } catch {
+    return null;
+  }
+}
+
+function readJson(file: string): unknown {
+  try {
+    return parseJson(readFileSync(file, "utf8"));
+  } catch {
+    return null;
+  }
+}
+
+function isStringArray(value: unknown): value is string[] {
+  return (
+    Array.isArray(value) && value.every((item) => typeof item === "string")
+  );
+}
+
+function hasContent(file: string): boolean {
+  try {
+    return statSync(file).size > 0;
+  } catch {
+    return false;
+  }
+}
+
+export function findRunnerFailure(env: NodeJS.ProcessEnv): string | null {
+  const {
+    UNIT_TEST_RESULTS_FILE,
+    JEST_JUNIT_OUTPUT_DIR,
+    JEST_JUNIT_OUTPUT_NAME,
+  } = env;
+  if (
+    !UNIT_TEST_RESULTS_FILE ||
+    !JEST_JUNIT_OUTPUT_DIR ||
+    !JEST_JUNIT_OUTPUT_NAME
+  ) {
+    throw new Error(
+      "UNIT_TEST_RESULTS_FILE, JEST_JUNIT_OUTPUT_DIR and JEST_JUNIT_OUTPUT_NAME are required",
+    );
+  }
+
+  const results = readResults(UNIT_TEST_RESULTS_FILE);
+  if (results === null || results.wasInterrupted) {
+    return "Jest did not finish the run.";
+  }
+  if (!hasContent(join(JEST_JUNIT_OUTPUT_DIR, JEST_JUNIT_OUTPUT_NAME))) {
+    return "Jest did not write a JUnit report.";
+  }
+
+  const failedSuites = results.testResults.filter(
+    (suite) => suite.status === "failed",
+  );
+  // jest-junit leaves out suites with no test results, so the quarantine gate never sees them.
+  const suitesWithoutResults = failedSuites.filter(
+    (suite) => suite.assertionResults.length === 0,
+  );
+  if (suitesWithoutResults.length > 0) {
+    const names = suitesWithoutResults.map((suite) => suite.name).join(", ");
+    return `Test suites failed to run: ${names}`;
+  }
+  if (failedSuites.length === 0) {
+    return "Jest failed without a failing test suite.";
+  }
+  return null;
+}
+
+function listTests(
+  command: readonly string[],
+  env: NodeJS.ProcessEnv,
+): string[] | null {
+  const [program, ...args] = command;
+  const result = spawnSync(program, [...args, "--listTests", "--json"], {
+    env,
+    encoding: "utf8",
+    stdio: ["ignore", "pipe", "inherit"],
+  });
+  if (result.status !== 0) {
+    return null;
+  }
+  const listed = parseJson(result.stdout);
+  return isStringArray(listed) ? listed : null;
+}
+
+// --passWithNoTests lets every shard pass when the selection matches nothing Jest discovers.
+// A single empty shard is normal, so only an unsharded listing that is also empty warns.
+export function findEmptySelection(
+  env: NodeJS.ProcessEnv,
+  command: readonly string[] = TEST_UNIT_COMMAND,
+): string | null {
+  const { UNIT_TEST_RESULTS_FILE, JEST_TEST_PATHS_FILE } = env;
+  if (!UNIT_TEST_RESULTS_FILE || !JEST_TEST_PATHS_FILE) {
+    return null;
+  }
+  const results = readResults(UNIT_TEST_RESULTS_FILE);
+  const selection = readJson(JEST_TEST_PATHS_FILE);
+  if (
+    results === null ||
+    results.testResults.length > 0 ||
+    !isStringArray(selection) ||
+    selection.length === 0
+  ) {
+    return null;
+  }
+
+  const listed = listTests(command, env);
+  if (listed === null) {
+    return "Could not list Jest's unit tests to check the selection.";
+  }
+  if (listed.length > 0) {
+    return null;
+  }
+  return `None of the ${selection.length} selected unit specs match a test Jest discovers, so no unit tests ran.`;
+}
+
+if (require.main === module) {
+  if (process.env.TEST_OUTCOME === "failure") {
+    const failure = findRunnerFailure(process.env);
+    if (failure !== null) {
+      console.error(`::error::${failure}`);
+      process.exitCode = 1;
+    }
+  } else {
+    const warning = findEmptySelection(process.env);
+    if (warning !== null) {
+      console.warn(`::warning::${warning}`);
+    }
+  }
+}

.github/scripts/conventional-commit-pr-title-reminder/utils.js

@@ -1,109 +0,0 @@
-const TYPES = new Set([
-  "feat",
-  "fix",
-  "perf",
-  "docs",
-  "style",
-  "refactor",
-  "test",
-  "build",
-  "ci",
-]);
-
-/**
- * @param title {string}
- */
-function isConventionalTitle(title) {
-  const match = /^(?<type>\w+)\((?<rawScopes>[^)]+)\):/.exec(title);
-
-  if (!match) {
-    return false;
-  }
-
-  const [, type, rawScopes] = match;
-  const scopes = rawScopes
-    .split(",")
-    .map((scope) => scope.trim())
-    .filter(Boolean);
-
-  return TYPES.has(type) && scopes.length > 0;
-}
-
-/** @param {import('@types/github-script').AsyncFunctionArguments} AsyncFunctionArguments */
-async function updateCommentForEmbedding({ github, context }) {
-  const githubUsername = context.payload.sender.login;
-
-  const comment = `${CONVENTIONAL_COMMENT_IDENTIFIER}
-@${githubUsername} You have modified embedding code. Please make sure the PR title follows [Conventional Commits](https://www.conventionalcommits.org/en/v1.0.0/) style.
-Here are all the supported types:
-- \`feat\`
-- \`fix\`
-- \`perf\`
-- \`docs\`
-- \`style\`
-- \`refactor\`
-- \`test\`
-- \`build\`
-- \`ci\`
-
-Please also make sure to include a scope.
-
-For example, these are valid PR titles:
-- \`feat(sdk-bundle): Add interactive dashboard component\`
-- \`fix(sdk-package): Fixed MetabaseProviderPropsStore logic\`
-- \`fix(sdk-package, embed-js): Fix API\``;
-
-  return updateComment(comment, { github, context });
-}
-
-/**
- * @param comment {string}
- * @param {import('@types/github-script').AsyncFunctionArguments} AsyncFunctionArguments
- */
-async function updateComment(comment, { github, context }) {
-  const owner = context.repo.owner;
-  const repo = context.repo.repo;
-  const pullRequestNumber = context.issue.number;
-  const comments = await github.rest.issues.listComments({
-    owner,
-    repo,
-    issue_number: pullRequestNumber,
-  });
-
-  const existingComment = getExistingConventionalCommitReminderComment(
-    comments.data,
-  );
-
-  if (existingComment) {
-    return await github.rest.issues.updateComment({
-      owner,
-      repo,
-      comment_id: existingComment.id,
-      body: comment,
-    });
-  } else {
-    return await github.rest.issues.createComment({
-      owner,
-      repo,
-      issue_number: pullRequestNumber,
-      body: comment,
-    });
-  }
-}
-
-const CONVENTIONAL_COMMENT_IDENTIFIER =
-  "<!---conventional comment identifier-->";
-
-/**
- * @param comments {{body: string}[]}
- */
-function getExistingConventionalCommitReminderComment(comments) {
-  for (const comment of comments) {
-    if (comment.body.startsWith(CONVENTIONAL_COMMENT_IDENTIFIER)) {
-      return comment;
-    }
-  }
-}
-
-exports.isConventionalTitle = isConventionalTitle;
-exports.updateCommentForEmbedding = updateCommentForEmbedding;

.github/scripts/conventional-commit-pr-title-reminder/utils.unit.spec.js

@@ -1,45 +0,0 @@
-const { isConventionalTitle } = require("./utils");
-
-describe("isConventionalTitle", () => {
-  it("returns true for a simple conventional commit", () => {
-    expect(isConventionalTitle("feat: add new feature")).toBe(false);
-  });
-
-  it("returns true for a commit with a scope", () => {
-    expect(isConventionalTitle("fix(api): correct API bug")).toBe(true);
-  });
-
-  it("returns true for a commit with multiple scopes, comma separated", () => {
-    expect(isConventionalTitle("feat(build,deps): update dependencies")).toBe(
-      true,
-    );
-  });
-
-  it("returns true for a commit with multiple scopes, comma separated with space", () => {
-    expect(isConventionalTitle("feat(build, deps): update dependencies")).toBe(
-      true,
-    );
-  });
-
-  it("returns false for a commit with round brackets in a message", () => {
-    expect(isConventionalTitle("feat: (something) update dependencies")).toBe(
-      false,
-    );
-  });
-
-  it("returns false for missing colon", () => {
-    expect(isConventionalTitle("feat add feature")).toBe(false);
-  });
-
-  it("returns false for invalid type", () => {
-    expect(isConventionalTitle("invalidType: some message")).toBe(false);
-  });
-
-  it("returns false for empty message", () => {
-    expect(isConventionalTitle("feat:")).toBe(false);
-  });
-
-  it("returns false for empty input", () => {
-    expect(isConventionalTitle("")).toBe(false);
-  });
-});

.github/scripts/create-test-plan.ts

@@ -1,37 +1,45 @@
-// I/O entrypoint: gather inputs (env vars, the cruise graph, the test-file
-// lists) and hand them to createTestPlan, which does the computing.
+// I/O entrypoint: gather inputs (env vars, the test-file lists, the cruise graph on request),
+// hand them to createTestPlan, which does the computing, and publish its small stats output.
 
-import { execFileSync } from "node:child_process";
-import { existsSync, readFileSync } from "node:fs";
+import { execFileSync, spawnSync } from "node:child_process";
+import { appendFileSync, existsSync, readFileSync } from "node:fs";
 
 import micromatch from "micromatch";
 
+import { MAIN_APP_STORY_GLOBS } from "../../.storybook/story-files.cjs";
 import { elements, rules } from "../../frontend/lint/module-boundaries.mjs";
 
 import { type FileDependency, parseCruiseModules } from "./affected-modules";
 import { createTestPlan } from "./affected-tests";
 import { listSpecFiles } from "./e2e-spec-globs.mjs";
 
-const UNIT_ROOTS = ["frontend/src", "enterprise/frontend/src"];
+// The specs `bun run test-unit` runs.
+const UNIT_ROOTS = ["."];
 const UNIT_GLOBS = [
-  "frontend/src/**/*.unit.spec.{js,jsx,ts,tsx}",
-  "enterprise/frontend/src/**/*.unit.spec.{js,jsx,ts,tsx}",
+  "**/*.unit.spec.{js,jsx,ts,tsx}",
+  "!.github/**", // the ci-scripts project, which test-unit ignores
+  "!release/**", // has its own jest config
+  "!enterprise/frontend/src/custom-viz/**", // modulePathIgnorePatterns in jest.config.js
+  "!**/*.leak.unit.spec.{js,jsx,ts,tsx}", // run only by jest.memory.conf.js
 ];
 
-const STORY_ROOTS = ["frontend", "enterprise/frontend"];
-const STORY_GLOBS = [
-  "frontend/**/*.stories.{js,jsx,ts,tsx}",
-  "enterprise/frontend/**/*.stories.{js,jsx,ts,tsx}",
-];
+const FRONTEND_ROOTS = ["frontend", "enterprise/frontend"];
+
+const LOKI_PREVIEW_FILE = ".storybook/preview.tsx";
+
+// `git ls-files -- frontend enterprise/frontend` already prints just over a
+// megabyte of paths, and node's default maxBuffer is exactly 1 MiB: past that
+// the spawn dies with ENOBUFS. Give the listings room to grow.
+const LS_FILES_MAX_BUFFER = 64 * 1024 * 1024;
 
 // Returns the tracked files under `roots` that match `globs`. The `dot: true`
 // option means files inside dot-directories such as `.storybook` are included.
 function listFiles(roots: string[], globs: string[]): string[] {
-  const tracked = execFileSync("git", ["ls-files", "--", ...roots], {
+  const tracked = execFileSync("git", ["ls-files", "-z", "--", ...roots], {
     encoding: "utf8",
+    maxBuffer: LS_FILES_MAX_BUFFER,
   })
-    .split("\n")
-    .map((line) => line.trim())
+    .split("\0")
     .filter(Boolean);
   return micromatch(tracked, globs, { dot: true });
 }
@@ -43,26 +51,43 @@ const csvToList = (csv: string | undefined) =>
     .map((s) => s.trim())
     .filter(Boolean);
 
-// Reads the dependency-cruiser graph (DEP_GRAPH_JSON). Null falls back to the
-// rules graph, so a missing or unparseable file never breaks the plan.
-function readFileDependencies(): FileDependency[] | null {
-  const path = process.env.DEP_GRAPH_JSON;
-  if (path && existsSync(path)) {
-    try {
-      const { modules } = JSON.parse(readFileSync(path, "utf8"));
-      process.stderr.write(`Using usage graph from ${path}.\n`);
-      return parseCruiseModules(modules);
-    } catch (error) {
-      process.stderr.write(
-        `Failed to read ${path}; falling back to rules graph: ${error}\n`,
-      );
-    }
-  } else {
-    process.stderr.write(
-      "No DEP_GRAPH_JSON found; falling back to rules graph.\n",
+// Runs dependency-cruiser over the frontend sources and the Storybook preview and parses its edges.
+// Null falls back to the rules graph, so a failed cruise never breaks the plan.
+function loadFileDependencies(): FileDependency[] | null {
+  const output = "dependency-graph.json";
+  process.stderr.write("Building usage graph with dependency-cruiser.\n");
+  try {
+    // stdout is the plan JSON, so the cruise's own output goes to stderr.
+    const result = spawnSync(
+      "bunx",
+      [
+        "depcruise",
+        "frontend/src",
+        "enterprise/frontend/src",
+        LOKI_PREVIEW_FILE,
+        "--config",
+        ".dependency-cruiser.cjs",
+        "--output-type",
+        "json",
+        "--output-to",
+        output,
+      ],
+      { stdio: ["ignore", 2, 2] },
     );
+    if (result.error) {
+      throw result.error;
+    }
+    if (result.status !== 0) {
+      throw new Error(`depcruise exited with status ${result.status}`);
+    }
+    const { modules } = JSON.parse(readFileSync(output, "utf8"));
+    return parseCruiseModules(modules);
+  } catch (error) {
+    process.stderr.write(
+      `Failed to build usage graph; falling back to rules graph: ${error}\n`,
+    );
+    return null;
   }
-  return null;
 }
 
 // Reads the nightly coverage manifest (E2E_SPEC_MANIFEST): { builtAt, specs:
@@ -92,12 +117,13 @@ const testPlan = createTestPlan({
   elements,
   rules,
   changedFiles: csvToList(process.env.CHANGED_FILES),
-  fileDependencies: readFileDependencies(),
+  loadFileDependencies,
   testFilesBySuite: {
     unit: listFiles(UNIT_ROOTS, UNIT_GLOBS),
-    loki: listFiles(STORY_ROOTS, STORY_GLOBS),
+    loki: listFiles(FRONTEND_ROOTS, MAIN_APP_STORY_GLOBS),
     e2e: listSpecFiles(),
   },
+  lokiPreviewFile: LOKI_PREVIEW_FILE,
   e2eSpecFiles: readE2eSpecFiles(),
   unitInfraTouched: process.env.UNIT_INFRA_TOUCHED === "true",
   lokiInfraTouched: process.env.LOKI_INFRA_TOUCHED === "true",
@@ -105,8 +131,15 @@ const testPlan = createTestPlan({
   sharedSourcesTouched: process.env.SHARED_SOURCES_TOUCHED === "true",
   feFilesChanged: csvToList(process.env.FE_CHANGED_FILES).length,
   beFilesChanged: csvToList(process.env.BE_CHANGED_FILES).length,
-  feFilesTotal: listFiles(["frontend", "enterprise/frontend"], ["**"]).length,
+  feFilesTotal: listFiles(FRONTEND_ROOTS, ["**"]).length,
   beFilesTotal: listFiles(["src", "enterprise/backend"], ["**"]).length,
 });
 
 process.stdout.write(JSON.stringify(testPlan) + "\n");
+
+if (process.env.GITHUB_OUTPUT) {
+  appendFileSync(
+    process.env.GITHUB_OUTPUT,
+    `stats=${JSON.stringify(testPlan.stats)}\n`,
+  );
+}

.github/scripts/csv-to-mb.js

@@ -1,91 +0,0 @@
-/**
- * jsonData must be in the format:
- * [
- *   { column1: value1, column2: value2, ... },
- *   { column1: value3, column2: value4, ... },
- *   ...
- * ]
- */
-function jsonToCsvFormData(jsonData) {
-  const formData = new FormData();
-  const csvHeader = Object.keys(jsonData[0]).join(',') + '\n';
-  const csvContent = jsonData.map(row =>
-    Object.values(row).map(value => `"${String(value).replace(/"/g, '""')}"`).join(',')
-  ).join('\n');
-
-  const blob = new Blob([csvHeader + csvContent], { type: 'text/csv' });
-  formData.append('file', blob, 'data.csv');
-
-  return formData;
-}
-
-// Transient failures worth retrying: throttling and server-side errors. A 4xx
-// (bad request, auth) won't succeed on retry, so those fail fast.
-const RETRYABLE_STATUS = new Set([429, 500, 502, 503, 504]);
-
-class UploadError extends Error {
-  constructor(message, { retryable }) {
-    super(message);
-    this.retryable = retryable;
-  }
-}
-
-async function attemptUpload(url, jsonData, timeoutMs) {
-  let response;
-  try {
-    response = await fetch(url, {
-      method: 'POST',
-      headers: {
-        "x-api-key": process.env.API_KEY
-      },
-      // Rebuilt per attempt: a consumed request body can't be reused.
-      body: jsonToCsvFormData(jsonData),
-      // Without this the request can hang indefinitely on a stalled server,
-      // eating the whole job timeout. An abort surfaces below as a retryable
-      // network error, so it retries with backoff instead.
-      signal: AbortSignal.timeout(timeoutMs)
-    });
-  } catch (networkError) {
-    throw new UploadError(networkError.message, { retryable: true });
-  }
-
-  if (response.ok) {
-    return;
-  }
-
-  const body = await response.text().catch(() => '');
-  throw new UploadError(
-    `Upload failed: ${response.status} ${response.statusText} ${body}`.trim(),
-    { retryable: RETRYABLE_STATUS.has(response.status) }
-  );
-}
-
-const sleep = ms => new Promise(resolve => setTimeout(resolve, ms));
-
-/**
- * Uploads jsonData as CSV, retrying transient API errors with exponential
- * backoff. `retries` is the number of extra attempts after the first (so the
- * default 2 means up to 3 tries). `timeoutMs` is a per-attempt total deadline
- * (default 60s) that aborts a stalled request. Throws the last error once
- * attempts are exhausted or the error is non-retryable.
- */
-async function uploadCsvToMb({ baseUrl, tableId, jsonData, mode = 'append', retries = 2, retryDelayMs = 1000, timeoutMs = 60_000 }) {
-  const operation = mode === 'replace' ? 'replace-csv' : 'append-csv';
-  const url = `${baseUrl}/api/table/${tableId}/${operation}`;
-
-  for (let attempt = 0; ; attempt++) {
-    try {
-      await attemptUpload(url, jsonData, timeoutMs);
-      return { success: true };
-    } catch (error) {
-      if (!error.retryable || attempt >= retries) {
-        throw error;
-      }
-      const delay = retryDelayMs * 2 ** attempt;
-      console.warn(`Upload attempt ${attempt + 1} failed (${error.message}); retrying in ${delay}ms`);
-      await sleep(delay);
-    }
-  }
-}
-
-module.exports = { uploadCsvToMb };

.github/scripts/csv-to-mb.unit.spec.js

@@ -1,50 +0,0 @@
-const { uploadCsvToMb } = require("./csv-to-mb");
-
-const ok = () => ({ ok: true });
-const fail = status => ({ ok: false, status, statusText: "err", text: async () => "" });
-
-const upload = (over = {}) =>
-  uploadCsvToMb({
-    baseUrl: "https://stats.example.com",
-    tableId: 1,
-    jsonData: [{ a: 1 }],
-    retryDelayMs: 1,
-    ...over,
-  });
-
-describe("uploadCsvToMb retries", () => {
-  afterEach(() => {
-    delete global.fetch;
-  });
-
-  it("retries transient server errors then succeeds", async () => {
-    global.fetch = jest.fn().mockResolvedValueOnce(fail(503)).mockResolvedValueOnce(fail(500)).mockResolvedValueOnce(ok());
-
-    await expect(upload({ retries: 2 })).resolves.toEqual({ success: true });
-    expect(global.fetch).toHaveBeenCalledTimes(3);
-  });
-
-  it("retries network errors", async () => {
-    global.fetch = jest
-      .fn()
-      .mockRejectedValueOnce(new Error("ECONNRESET"))
-      .mockResolvedValueOnce(ok());
-
-    await expect(upload({ retries: 2 })).resolves.toEqual({ success: true });
-    expect(global.fetch).toHaveBeenCalledTimes(2);
-  });
-
-  it("gives up after exhausting retries and throws the last error", async () => {
-    global.fetch = jest.fn().mockResolvedValue(fail(500));
-
-    await expect(upload({ retries: 2 })).rejects.toThrow("Upload failed: 500");
-    expect(global.fetch).toHaveBeenCalledTimes(3); // 1 initial + 2 retries
-  });
-
-  it("does not retry a non-transient 4xx", async () => {
-    global.fetch = jest.fn().mockResolvedValue(fail(400));
-
-    await expect(upload({ retries: 2 })).rejects.toThrow("Upload failed: 400");
-    expect(global.fetch).toHaveBeenCalledTimes(1);
-  });
-});

.github/scripts/file-paths.unit.spec.ts

@@ -0,0 +1,142 @@
+import { readFileSync } from "fs";
+import { join } from "path";
+
+import { load } from "js-yaml";
+import { isMatch } from "micromatch";
+
+const FILTERS = join(__dirname, "..", "file-paths.yaml");
+
+type Filter = string | Filter[] | { [changeType: string]: Filter };
+
+// A filter is a list of patterns, and an entry may name the change types it applies to as
+// { "added|modified": pattern }. Either way the patterns are what matters here.
+const patterns = (value: Filter): string[] => {
+  if (typeof value === "string") {
+    return [value];
+  }
+  if (Array.isArray(value)) {
+    return value.flatMap(patterns);
+  }
+  return Object.values(value).flatMap(patterns);
+};
+
+describe("file-paths.yaml", () => {
+  // js-yaml returns an untyped value, and this repository file defines named path filters.
+  const filters = load(readFileSync(FILTERS, "utf8")) as Record<string, Filter>;
+
+  // dorny/paths-filter matches with picomatch, which micromatch wraps, so this asks the same
+  // question CI asks of a changed path.
+  const matches = (name: string, path: string) =>
+    patterns(filters[name]).some((pattern) =>
+      isMatch(path, pattern, { dot: true }),
+    );
+
+  // dorny/paths-filter ORs the patterns in a filter, so a "!..." entry does not subtract from the
+  // other entries - it matches every path they don't, turning the filter permanently on. Excluding
+  // a path means writing the exclusion inside one pattern, the way backend_sources keeps
+  // ratchet files out with ".clj-kondo/**/!(ratchets.edn)".
+  it("never excludes a path with a standalone negation", () => {
+    const negated = Object.entries(filters).flatMap(([name, filter]) =>
+      patterns(filter)
+        .filter((pattern) => pattern.startsWith("!"))
+        .map((pattern) => `${name}: ${pattern}`),
+    );
+
+    expect(negated).toEqual([]);
+  });
+
+  it.each(["backend_sources", "backend_all"])(
+    "%s skips a ratchets-only change and still follows the rest of .clj-kondo",
+    (name) => {
+      expect(matches(name, ".clj-kondo/ratchets.edn")).toBe(false);
+      expect(matches(name, ".clj-kondo/config/modules/ratchets.edn")).toBe(
+        false,
+      );
+      expect(matches(name, ".clj-kondo/config.edn")).toBe(true);
+      expect(matches(name, ".clj-kondo/config/modules/config.edn")).toBe(true);
+    },
+  );
+
+  it("runs CI script tests when the Node version changes", () => {
+    expect(matches("ci_scripts", ".nvmrc")).toBe(true);
+  });
+
+  it.each([
+    "jest.config.js",
+    "jest.base.conf.js",
+    "jest.esm-packages.js",
+    "jest.tz.unit.conf.js",
+  ])("runs every frontend unit test when %s changes", (path) => {
+    expect(matches("frontend_specs", path)).toBe(true);
+    expect(matches("frontend_unit_infra", path)).toBe(true);
+  });
+
+  it("runs every frontend unit test when an SDK jest setup file changes", () => {
+    expect(
+      matches(
+        "frontend_unit_infra",
+        "frontend/src/embedding-sdk-shared/jest/setup-env.ts",
+      ),
+    ).toBe(true);
+  });
+
+  it.each([
+    "jest.config.js",
+    "jest.base.conf.js",
+    "jest.esm-packages.js",
+    ".storybook/story-files.cjs",
+    ".github/workflows/loki.yml",
+  ])("runs CI script tests when %s changes", (path) => {
+    expect(matches("ci_scripts", path)).toBe(true);
+  });
+
+  it("runs the ratchet check on the ratchets file", () => {
+    expect(matches("project_ratchet_checks", ".clj-kondo/ratchets.edn")).toBe(
+      true,
+    );
+    expect(
+      matches(
+        "project_ratchet_checks",
+        ".clj-kondo/config/modules/ratchets.edn",
+      ),
+    ).toBe(true);
+  });
+
+  it.each([
+    "loki.config.js",
+    ".storybook/story-files.cjs",
+    ".storybook/preview.tsx",
+    ".loki/reference/chrome.laptop-Button.png",
+    ".github/workflows/loki.yml",
+    ".github/workflows/run-tests.yml",
+    ".github/actions/prepare-frontend/action.yml",
+    "frontend/build/shared/rspack/css-config.js",
+    "frontend/test/__support__/custom-viz-fixtures/calendar-heatmap/index.js",
+    "patches/@loki+browser+0.35.0.patch",
+    "frontend/src/metabase/css/index.module.css",
+    "frontend/src/metabase/css/core/base.module.css",
+    "resources/frontend_client/app/fonts/Lato/lato-v16-latin-regular.woff2",
+    "resources/frontend_client/app/assets/img/no_results.svg",
+    "frontend/src/metabase/ui/components/icons/Icon/icons/warning.svg",
+    "enterprise/frontend/src/metabase-enterprise/google_drive/database-error.svg",
+  ])("runs all Loki stories when %s changes", (file) => {
+    expect(matches("frontend_loki_all", file)).toBe(true);
+    expect(matches("frontend_loki_infra", file)).toBe(true);
+  });
+
+  it.each([
+    "frontend/src/metabase/ui/Button.stories.tsx",
+    "frontend/src/metabase/ui/components/feedback/Alert/Alert.module.css",
+    "frontend/build/embedding-sdk/rspack.config.js",
+  ])("allows a change to %s to narrow the Loki run", (file) => {
+    expect(matches("frontend_loki_all", file)).toBe(true);
+    expect(matches("frontend_loki_infra", file)).toBe(false);
+  });
+
+  it.each([
+    ".github/workflows/frontend.yml",
+    "frontend/test/metabase/scenarios/Button.unit.spec.tsx",
+  ])("does not run Loki stories when %s changes", (file) => {
+    expect(matches("frontend_loki_all", file)).toBe(false);
+  });
+});

.github/scripts/find-linear-issue.js

@@ -1,40 +0,0 @@
-async function findLinearIssue({ githubIssueUrl, linearApiKey }) {
-  const response = await fetch("https://api.linear.app/graphql", {
-    method: "POST",
-    headers: {
-      "Content-Type": "application/json",
-      Authorization: linearApiKey,
-    },
-    body: JSON.stringify({
-      query: `
-        query {
-          attachmentsForURL(url: "${githubIssueUrl}") {
-            nodes {
-              issue { identifier }
-            }
-          }
-        }
-      `,
-    }),
-  });
-
-  const data = await response.json();
-
-  if (!response.ok) {
-    return { success: false, message: `Linear API error: ${response.status}` };
-  }
-
-  if (!data.data?.attachmentsForURL?.nodes?.length) {
-    return {
-      success: false,
-      message: `No Linear issue linked to ${githubIssueUrl}`,
-    };
-  }
-
-  return {
-    success: true,
-    issue: data.data.attachmentsForURL.nodes[0].issue.identifier,
-  };
-}
-
-module.exports = { findLinearIssue };

.github/scripts/fix-yarn-lock-aliases.ts

@@ -0,0 +1,66 @@
+/**
+ * Renames aliased dependency keys in a bun-generated yarn.lock.
+ *
+ * Yarn names an alias entry after the alias, for example
+ * `"typescript7@npm:typescript@7.0.2"`. Bun names it after the aliased package
+ * instead, for example `"typescript@npm:typescript@7.0.2"`. Snyk follows the
+ * yarn convention and fails to resolve the dependency.
+ */
+
+import { readFile, writeFile } from "node:fs/promises";
+
+async function main() {
+  const packageJsonPath = `${process.cwd()}/package.json`;
+  const lockPath = `${process.cwd()}/yarn.lock`;
+
+  const packageJson = JSON.parse(await readFile(packageJsonPath, "utf8"));
+
+  const dependencies = Object.entries<string>(
+    Object.assign(
+      {},
+      packageJson.dependencies,
+      packageJson.devDependencies,
+      packageJson.optionalDependencies,
+    ),
+  );
+
+  let lock = await readFile(lockPath, "utf8");
+  const renamedKeys: string[] = [];
+
+  for (const [alias, specifier] of dependencies) {
+    if (!specifier.startsWith("npm:")) {
+      continue;
+    }
+
+    const aliasedPackage = specifier
+      .slice("npm:".length)
+      .replace(/@[^@]*$/, "");
+
+    if (aliasedPackage === alias) {
+      continue;
+    }
+
+    const bunKey = `"${aliasedPackage}@${specifier}"`;
+    const yarnKey = `"${alias}@${specifier}"`;
+
+    if (lock.includes(bunKey)) {
+      lock = lock.replaceAll(bunKey, yarnKey);
+      renamedKeys.push(`${bunKey} -> ${yarnKey}`);
+    }
+  }
+
+  if (renamedKeys.length > 0) {
+    await writeFile(lockPath, lock);
+  }
+
+  process.stdout.write(
+    renamedKeys.length > 0
+      ? `Renamed alias keys in yarn.lock:\n${renamedKeys.join("\n")}\n`
+      : "No alias keys to rename in yarn.lock\n",
+  );
+}
+
+main().catch((error) => {
+  process.stderr.write(`Failed to rename alias keys in yarn.lock: ${error}\n`);
+  process.exit(1);
+});

.github/scripts/frontend-test-plan.unit.spec.ts

@@ -0,0 +1,237 @@
+import { spawnSync } from "node:child_process";
+import {
+  mkdirSync,
+  mkdtempSync,
+  readFileSync,
+  realpathSync,
+  rmSync,
+  writeFileSync,
+} from "node:fs";
+import { tmpdir } from "node:os";
+import { join, resolve } from "node:path";
+
+import { load } from "js-yaml";
+
+import {
+  findEmptySelection,
+  findRunnerFailure,
+} from "./check-unit-test-results";
+import { prepareTestSelection } from "./prepare-test-selection";
+
+type Step = { name: string; run?: string; "continue-on-error"?: boolean };
+// js-yaml returns an untyped value, and this repository workflow defines the job's steps.
+const workflow = load(
+  readFileSync(resolve(__dirname, "../workflows/frontend.yml"), "utf8"),
+) as { jobs: { "fe-tests-unit": { steps: Step[] } } };
+const steps = workflow.jobs["fe-tests-unit"].steps;
+const checkScript = resolve(__dirname, "check-unit-test-results.ts");
+const filter = resolve(
+  __dirname,
+  "../../frontend/test/jest-test-paths-filter.ts",
+);
+
+describe("frontend test plan handoff", () => {
+  let dir: string;
+  let env: NodeJS.ProcessEnv;
+
+  beforeEach(() => {
+    jest.spyOn(console, "warn").mockImplementation(() => {});
+    // Jest reports real paths, and macOS's temporary directory is behind a symlink.
+    dir = realpathSync(mkdtempSync(join(tmpdir(), "frontend-test-plan-")));
+    mkdirSync(join(dir, "test-plan"));
+    writeFileSync(join(dir, "output"), "");
+    env = {
+      ...process.env,
+      NODE_OPTIONS: "",
+      JEST_TEST_PATHS_FILE: "",
+      RUNNER_TEMP: dir,
+      GITHUB_OUTPUT: join(dir, "output"),
+      PLAN_DOWNLOADED: "success",
+      JEST_JUNIT_OUTPUT_DIR: dir,
+      JEST_JUNIT_OUTPUT_NAME: "junit.xml",
+      UNIT_TEST_RESULTS_FILE: join(dir, "unit-test-results.json"),
+    };
+  });
+
+  afterEach(() => {
+    jest.restoreAllMocks();
+    rmSync(dir, { recursive: true, force: true });
+  });
+
+  function plan(files: string[], total = 2) {
+    return {
+      fe_unit_specs_to_run: files,
+      stats: { unit_specs_all: total, unit_specs_to_run_usage: files.length },
+    };
+  }
+
+  function writePlan(value: unknown) {
+    writeFileSync(join(dir, "test-plan/test-plan.json"), JSON.stringify(value));
+  }
+
+  function jestCommand(useFilter: boolean) {
+    return [
+      process.execPath,
+      require.resolve("jest/bin/jest"),
+      "--config",
+      JSON.stringify({
+        rootDir: dir,
+        testMatch: ["**/*.spec.cjs"],
+        reporters: ["default", require.resolve("jest-junit")],
+        ...(useFilter && { filter }),
+      }),
+    ];
+  }
+
+  function runJest(
+    files: Record<string, string>,
+    useFilter = false,
+    args: string[] = [],
+  ) {
+    for (const [name, source] of Object.entries(files)) {
+      writeFileSync(join(dir, name), source);
+    }
+    const [program, ...commandArgs] = jestCommand(useFilter);
+    return spawnSync(
+      program,
+      [
+        ...commandArgs,
+        "--runInBand",
+        "--watch=false",
+        "--json",
+        `--outputFile=${env.UNIT_TEST_RESULTS_FILE}`,
+        ...(useFilter ? ["--passWithNoTests"] : []),
+        ...args,
+      ],
+      { cwd: dir, env, encoding: "utf8" },
+    );
+  }
+
+  function readResults() {
+    return JSON.parse(
+      readFileSync(join(dir, "unit-test-results.json"), "utf8"),
+    );
+  }
+
+  function writeSelection(files: string[]) {
+    env.JEST_TEST_PATHS_FILE = join(dir, "unit-specs.json");
+    writeFileSync(env.JEST_TEST_PATHS_FILE, JSON.stringify(files));
+  }
+
+  it("lets ordinary assertion failures reach quarantine", () => {
+    expect(
+      runJest({ "fail.spec.cjs": "test('fails', () => expect(1).toBe(2));" })
+        .status,
+    ).toBe(1);
+    expect(findRunnerFailure(env)).toBeNull();
+  });
+
+  it("lets suite hook failures reach quarantine", () => {
+    expect(
+      runJest({
+        "hook.spec.cjs":
+          "test('passes', () => {}); afterAll(() => { throw new Error('hook'); });",
+      }).status,
+    ).toBe(1);
+    expect(readFileSync(join(dir, "junit.xml"), "utf8")).toContain(
+      "Test execution failure",
+    );
+    expect(findRunnerFailure(env)).toBeNull();
+  });
+
+  it("fails a filter crash even though the test step permits errors", () => {
+    env.JEST_TEST_PATHS_FILE = join(dir, "broken.json");
+    writeFileSync(env.JEST_TEST_PATHS_FILE, "[");
+    expect(
+      runJest({ "pass.spec.cjs": "test('passes', () => {});" }, true).status,
+    ).toBe(1);
+    env.TEST_OUTCOME = "failure";
+    const result = spawnSync("bun", [checkScript], { env, encoding: "utf8" });
+    expect(result.status).toBe(1);
+    expect(result.stderr).toContain("::error::");
+    const step = steps.find((step) =>
+      step.run?.includes("check-unit-test-results.ts"),
+    );
+    expect(step?.["continue-on-error"]).toBeUndefined();
+  });
+
+  it("fails suite startup errors even alongside ordinary assertion failures", () => {
+    expect(
+      runJest({
+        "crash.spec.cjs": "throw new Error('startup crash');",
+        "fail.spec.cjs": "test('fails', () => expect(1).toBe(2));",
+      }).status,
+    ).toBe(1);
+    expect(readFileSync(join(dir, "junit.xml"), "utf8")).not.toContain(
+      "crash.spec.cjs",
+    );
+    expect(findRunnerFailure(env)).toContain("crash.spec.cjs");
+  });
+
+  it("fails when JUnit results are missing", () => {
+    runJest({ "fail.spec.cjs": "test('fails', () => expect(1).toBe(2));" });
+    rmSync(join(dir, "junit.xml"));
+    expect(findRunnerFailure(env)).not.toBeNull();
+  });
+
+  it.each([true, false])(
+    "loads the TypeScript filter natively with an empty selection: %s",
+    (empty) => {
+      writePlan(plan(empty ? [] : [join(dir, "pass.spec.cjs")]));
+      prepareTestSelection("unit", env);
+      env.JEST_TEST_PATHS_FILE = join(dir, "unit-specs.json");
+      const result = runJest(
+        {
+          "pass.spec.cjs": "test('passes', () => {});",
+          "fail.spec.cjs":
+            "test('excluded', () => { throw new Error('must not run'); });",
+        },
+        true,
+      );
+      expect(result.status === 0 ? "" : result.stderr).toBe("");
+      expect(result.status).toBe(0);
+      expect(readResults()).toMatchObject({
+        numTotalTestSuites: empty ? 0 : 1,
+      });
+    },
+  );
+
+  it("warns when a narrowed run matches none of Jest's test paths", () => {
+    writeSelection([join(dir, "renamed.spec.cjs")]);
+    expect(
+      runJest({ "pass.spec.cjs": "test('passes', () => {});" }, true).status,
+    ).toBe(0);
+    expect(findEmptySelection(env, jestCommand(true))).toContain(
+      "None of the 1 selected unit specs",
+    );
+  });
+
+  it("warns through Bun when the unit test step passed", () => {
+    writeSelection([join(dir, "renamed.spec.cjs")]);
+    runJest({ "pass.spec.cjs": "test('passes', () => {});" }, true);
+    env.TEST_OUTCOME = "success";
+    const result = spawnSync("bun", [checkScript], { env, encoding: "utf8" });
+    expect(result.status).toBe(0);
+    expect(result.stderr).toContain(
+      "::warning::None of the 1 selected unit specs",
+    );
+  });
+
+  it("does not warn for a shard the selection leaves empty", () => {
+    writeSelection([join(dir, "pass.spec.cjs")]);
+    const result = runJest(
+      { "pass.spec.cjs": "test('passes', () => {});" },
+      true,
+      ["--shard=2/2"],
+    );
+    expect(result.status).toBe(0);
+    expect(readResults()).toMatchObject({ numTotalTestSuites: 0 });
+    expect(findEmptySelection(env, jestCommand(true))).toBeNull();
+  });
+
+  it("does not list tests for an empty selection", () => {
+    writeSelection([]);
+    runJest({ "pass.spec.cjs": "test('passes', () => {});" }, true);
+    expect(findEmptySelection(env, ["false"])).toBeNull();
+  });
+});

.github/scripts/get-issue-data.js

@@ -1,84 +0,0 @@
-const githubSlackMap = require("../../release/github-slack-map.json");
-
-async function getIssueData({ context, github, manualIssueNumber }) {
-  let issueNumber;
-  let issueData;
-  let prReviews = [];
-  const triggerType = context.eventName;
-
-  if (context.eventName === "issues") {
-    issueNumber = context.payload.issue.number;
-    issueData = context.payload.issue;
-  } else if (context.eventName === "workflow_dispatch") {
-    issueNumber = parseInt(manualIssueNumber);
-    const { data } = await github.rest.issues.get({
-      owner: context.repo.owner,
-      repo: context.repo.repo,
-      issue_number: issueNumber,
-    });
-    issueData = data;
-  } else if (context.eventName === "pull_request_review") {
-    const prNumber = context.payload.pull_request.number;
-    const { data: prData } = await github.rest.pulls.get({
-      owner: context.repo.owner,
-      repo: context.repo.repo,
-      pull_number: prNumber,
-    });
-
-    // Extract issue number from branch name (e.g., "claude-fix/issue-12345-some-title")
-    const branchMatch = prData.head.ref.match(/claude-fix\/issue-(\d+)/);
-    if (!branchMatch) {
-      throw new Error(
-        `Could not extract issue number from branch name: ${prData.head.ref}`,
-      );
-    }
-
-    issueNumber = parseInt(branchMatch[1]);
-
-    const { data } = await github.rest.issues.get({
-      owner: context.repo.owner,
-      repo: context.repo.repo,
-      issue_number: issueNumber,
-    });
-    issueData = data;
-
-    const { data: reviews } = await github.rest.pulls.listReviews({
-      owner: context.repo.owner,
-      repo: context.repo.repo,
-      pull_number: prNumber,
-    });
-
-    prReviews = reviews.filter(
-      (review) =>
-        review.state === "CHANGES_REQUESTED" &&
-        isMetabaseMember(review.user.login),
-    );
-  }
-
-  const { data: comments } = await github.rest.issues.listComments({
-    owner: context.repo.owner,
-    repo: context.repo.repo,
-    issue_number: issueNumber,
-  });
-
-  const employeeComments = comments.filter((comment) =>
-    isMetabaseMember(comment.user.login),
-  );
-
-  return {
-    issueNumber,
-    issueData,
-    employeeComments,
-    prReviews,
-    triggerType,
-    isIssueAuthorEmployee: isMetabaseMember(issueData.user.login),
-  };
-}
-
-function isMetabaseMember(username) {
-  return username in githubSlackMap;
-}
-
-module.exports = {
-  getIssueData,
-};

.github/scripts/jest-test-paths-filter.unit.spec.ts

@@ -0,0 +1,44 @@
+import fs from "node:fs";
+import os from "node:os";
+import path from "node:path";
+
+// eslint-disable-next-line @typescript-eslint/no-require-imports -- Match Jest's direct CommonJS loading contract.
+const filter = require("../../frontend/test/jest-test-paths-filter");
+
+describe("jest-test-paths-filter", () => {
+  const originalPathsFile = process.env.JEST_TEST_PATHS_FILE;
+  let tempDir: string;
+  let pathsFile: string;
+
+  beforeEach(() => {
+    tempDir = fs.mkdtempSync(path.join(os.tmpdir(), "jest-test-paths-"));
+    pathsFile = path.join(tempDir, "paths.json");
+    process.env.JEST_TEST_PATHS_FILE = pathsFile;
+  });
+
+  afterEach(() => {
+    fs.rmSync(tempDir, { recursive: true, force: true });
+    if (originalPathsFile === undefined) {
+      delete process.env.JEST_TEST_PATHS_FILE;
+    } else {
+      process.env.JEST_TEST_PATHS_FILE = originalPathsFile;
+    }
+  });
+
+  it("should keep the listed paths and drop the rest", () => {
+    const one = path.resolve("frontend/one.unit.spec.ts");
+    const two = path.resolve("frontend/two.unit.spec.ts");
+    const three = path.resolve("frontend/three.unit.spec.ts");
+    fs.writeFileSync(pathsFile, JSON.stringify([one, two]));
+
+    expect(filter([one, three, two])).toEqual({ filtered: [one, two] });
+  });
+
+  it("should resolve relative paths against the working directory", () => {
+    fs.writeFileSync(pathsFile, JSON.stringify(["frontend/one.unit.spec.ts"]));
+    const one = path.resolve("frontend/one.unit.spec.ts");
+    const two = path.resolve("frontend/two.unit.spec.ts");
+
+    expect(filter([one, two])).toEqual({ filtered: [one] });
+  });
+});

.github/scripts/linear-issues.js

@@ -0,0 +1,109 @@
+async function findLinearIssue({ githubIssueUrl, linearApiKey }) {
+  const response = await fetch("https://api.linear.app/graphql", {
+    method: "POST",
+    headers: {
+      "Content-Type": "application/json",
+      Authorization: linearApiKey,
+    },
+    body: JSON.stringify({
+      query: `
+        query {
+          attachmentsForURL(url: "${githubIssueUrl}") {
+            nodes {
+              issue { identifier }
+            }
+          }
+        }
+      `,
+    }),
+  });
+
+  const data = await response.json();
+
+  if (!response.ok) {
+    return { success: false, message: `Linear API error: ${response.status}` };
+  }
+
+  if (!data.data?.attachmentsForURL?.nodes?.length) {
+    return {
+      success: false,
+      message: `No Linear issue linked to ${githubIssueUrl}`,
+    };
+  }
+
+  return {
+    success: true,
+    issue: data.data.attachmentsForURL.nodes[0].issue.identifier,
+  };
+}
+
+async function createLinearIssue({
+  teamId,
+  title,
+  description,
+  projectId,
+  labelIds,
+  linearApiKey,
+}) {
+  const response = await fetch("https://api.linear.app/graphql", {
+    method: "POST",
+    headers: {
+      "Content-Type": "application/json",
+      Authorization: linearApiKey,
+    },
+    body: JSON.stringify({
+      query: `
+        mutation CreateIssue($input: IssueCreateInput!) {
+          issueCreate(input: $input) {
+            success
+            issue {
+              id
+              identifier
+              title
+              url
+            }
+          }
+        }
+      `,
+      variables: {
+        input: {
+          teamId,
+          title,
+          ...(description ? { description } : {}),
+          ...(projectId ? { projectId } : {}),
+          ...(labelIds?.length ? { labelIds } : {}),
+        },
+      },
+    }),
+  });
+
+  if (!response.ok) {
+    return { success: false, message: `Linear API error: ${response.status}` };
+  }
+
+  const data = await response.json();
+
+  if (data.errors?.length) {
+    return {
+      success: false,
+      message: `Linear API error: ${data.errors.map((e) => e.message).join(", ")}`,
+    };
+  }
+
+  if (!data.data?.issueCreate?.success) {
+    return {
+      success: false,
+      message: `Failed to create Linear issue "${title}"`,
+    };
+  }
+
+  return {
+    success: true,
+    issue: data.data.issueCreate.issue,
+  };
+}
+
+module.exports = {
+  findLinearIssue,
+  createLinearIssue,
+};

.github/scripts/measure-bundle-sizes.js

@@ -24,6 +24,15 @@ const SDK_ROOT = "resources/frontend_client/app/embedding-sdk";
 const SDK_RUNTIME_RE = /embedding-sdk-chunk-runtime\./;
 const notRuntime = name => !SDK_RUNTIME_RE.test(name);
 
+// One locale catalogue per chunk, named by the `webpackChunkName: "locale-[request]"`
+// comment in localization.ts. A session loads exactly one and an English session
+// loads none, so counting all 36 in a reachable total overstates it by 35x: 8.5 MB
+// gzip against the SDK's 3.1 MB. Their size also tracks the translation process
+// rather than any code change, so counting them makes every catalogue update look
+// like a bundle regression.
+const LOCALE_CHUNK_RE = /(^|\/)locale-/;
+const notLocale = name => !LOCALE_CHUNK_RE.test(name);
+
 const assetFiles = (root, names) => names.map(name => path.join(root, name));
 const unique = files => [...new Set(files)];
 
@@ -116,7 +125,8 @@ function selectAppAssets(stats) {
   if (!initialAssets) {
     throw new Error('app: stats-main.json / "app-main" entrypoint missing');
   }
-  return { initialAssets, reachableAssets: entrypointJsAssets(stats, "app-main", "reachableAssets") };
+  const reachableAssets = entrypointJsAssets(stats, "app-main", "reachableAssets");
+  return { initialAssets, reachableAssets: reachableAssets?.filter(notLocale) ?? null };
 }
 
 /**
@@ -136,7 +146,9 @@ function selectLegacySdkAssets(stats, { sdkAsyncChunksLoadable }) {
   const initial = unique(initialNames).filter(notRuntime);
   return {
     initialNames: initial,
-    reachableNames: sdkAsyncChunksLoadable ? unique(reachableNames).filter(notRuntime) : initial,
+    reachableNames: sdkAsyncChunksLoadable
+      ? unique(reachableNames).filter(notRuntime).filter(notLocale)
+      : initial,
   };
 }
 
@@ -161,7 +173,9 @@ function selectChunkedSdkAssets(stats, { sdkAsyncChunksLoadable }) {
   const bootstrapReachable = entrypointJsAssets(stats, "embedding-sdk-bootstrap", "reachableAssets") || bootstrapInitial;
   return {
     initialNames: unique([...bootstrapInitial, ...chunkedInitial]).filter(notRuntime),
-    reachableNames: unique([...bootstrapReachable, ...chunkedReachable]).filter(notRuntime),
+    reachableNames: unique([...bootstrapReachable, ...chunkedReachable])
+      .filter(notRuntime)
+      .filter(notLocale),
     includesAsyncChunks: chunkedReachableAssets != null && sdkAsyncChunksLoadable,
   };
 }

.github/scripts/measure-bundle-sizes.unit.spec.js

@@ -6,6 +6,7 @@ const {
 } = require("./measure-bundle-sizes");
 
 const RUNTIME = "embedding-sdk-chunk-runtime.deadbeef.js";
+const LOCALE = "chunks/locale-fr-json.deadbeef.js";
 
 const stats = entrypoints => ({ entrypoints });
 
@@ -30,6 +31,13 @@ describe("selectAppAssets", () => {
   it("throws when the app-main entrypoint is missing", () => {
     expect(() => selectAppAssets(stats({}))).toThrow("app-main");
   });
+
+  it("leaves the locale catalogues out of the reachable total", () => {
+    const s = stats({
+      "app-main": { assets: ["main.js"], reachableAssets: ["main.js", "locale-fr-json.abc.js"] },
+    });
+    expect(selectAppAssets(s).reachableAssets).toEqual(["main.js"]);
+  });
 });
 
 describe("selectChunkedSdkAssets", () => {
@@ -50,6 +58,15 @@ describe("selectChunkedSdkAssets", () => {
     expect(result.includesAsyncChunks).toBe(false);
   });
 
+  it("leaves the locale catalogues out of the reachable total", () => {
+    const withLocale = {
+      ...base,
+      "embedding-sdk-chunked": { assets: ["a.js", RUNTIME], reachableAssets: ["a.js", "b.js", LOCALE, RUNTIME] },
+    };
+    const result = selectChunkedSdkAssets(stats(withLocale), { sdkAsyncChunksLoadable: true });
+    expect(result.reachableNames).toEqual(["boot.js", "a.js", "b.js"]);
+  });
+
   it("collapses total to initial when the stats carry no reachable graph", () => {
     const noGraph = { "embedding-sdk-chunked": { assets: ["a.js"] } };
     const result = selectChunkedSdkAssets(stats(noGraph), { sdkAsyncChunksLoadable: true });

.github/scripts/prepare-test-selection.ts

@@ -0,0 +1,122 @@
+import { appendFileSync, readFileSync, writeFileSync } from "node:fs";
+import { join } from "node:path";
+
+import type { TestPlan, TestPlanStats } from "./affected-tests";
+
+type NumberStat = {
+  [K in keyof TestPlanStats]: TestPlanStats[K] extends number ? K : never;
+}[keyof TestPlanStats];
+
+type Suite = {
+  name: string;
+  filesKey: Exclude<keyof TestPlan, "stats">;
+  totalKey: NumberStat;
+  selectedKey: NumberStat;
+  pathsFile: string;
+};
+
+export const SUITES = {
+  unit: {
+    name: "unit",
+    filesKey: "fe_unit_specs_to_run",
+    totalKey: "unit_specs_all",
+    selectedKey: "unit_specs_to_run_usage",
+    pathsFile: "unit-specs.json",
+  },
+  loki: {
+    name: "Loki",
+    filesKey: "loki_stories_to_run",
+    totalKey: "loki_stories_all",
+    selectedKey: "loki_stories_to_run_usage",
+    pathsFile: "loki-stories.json",
+  },
+  e2e: {
+    name: "E2E",
+    filesKey: "e2e_specs_to_run",
+    totalKey: "e2e_specs_all",
+    selectedKey: "e2e_specs_to_run_usage",
+    pathsFile: "e2e-specs.json",
+  },
+} satisfies Record<string, Suite>;
+
+function isSuiteName(name: string): name is keyof typeof SUITES {
+  return Object.hasOwn(SUITES, name);
+}
+
+function isRecord(value: unknown): value is Record<string, unknown> {
+  return typeof value === "object" && value !== null;
+}
+
+function isStringArray(value: unknown): value is string[] {
+  return (
+    Array.isArray(value) && value.every((item) => typeof item === "string")
+  );
+}
+
+function isCount(value: unknown): value is number {
+  return typeof value === "number" && Number.isInteger(value) && value >= 0;
+}
+
+// null means a full run, and [] is an explicit selection of no tests.
+function readSelection(planFile: string, suite: Suite): string[] | null {
+  const plan: unknown = JSON.parse(readFileSync(planFile, "utf8"));
+  const files = isRecord(plan) ? plan[suite.filesKey] : undefined;
+  const stats = isRecord(plan) && isRecord(plan.stats) ? plan.stats : {};
+  const total = stats[suite.totalKey];
+  if (
+    !isStringArray(files) ||
+    files.some((file) => file.length === 0) ||
+    !isCount(total) ||
+    files.length !== stats[suite.selectedKey] ||
+    files.length > total
+  ) {
+    throw new Error(`Invalid ${suite.name} test selection`);
+  }
+  return files.length === total ? null : files;
+}
+
+export function prepareTestSelection(
+  suiteName: keyof typeof SUITES,
+  env: NodeJS.ProcessEnv = process.env,
+) {
+  const suite: Suite = SUITES[suiteName];
+  const { RUNNER_TEMP, GITHUB_OUTPUT, PLAN_DOWNLOADED } = env;
+  if (!RUNNER_TEMP || !GITHUB_OUTPUT) {
+    throw new Error("RUNNER_TEMP and GITHUB_OUTPUT are required");
+  }
+
+  let files: string[] | null;
+  try {
+    if (PLAN_DOWNLOADED !== "success") {
+      throw new Error("Test plan download failed");
+    }
+    files = readSelection(join(RUNNER_TEMP, "test-plan/test-plan.json"), suite);
+  } catch (error) {
+    console.warn(
+      `::warning::Test plan unavailable or invalid, running the full ${suite.name} suite: ${error}`,
+    );
+    return;
+  }
+
+  if (files === null) {
+    appendFileSync(GITHUB_OUTPUT, "selection=full\n");
+    return;
+  }
+
+  const pathsFile = join(RUNNER_TEMP, suite.pathsFile);
+  writeFileSync(pathsFile, JSON.stringify(files));
+  appendFileSync(
+    GITHUB_OUTPUT,
+    `paths-file=${pathsFile}\nselection=${files.length === 0 ? "empty" : "narrowed"}\n`,
+  );
+}
+
+if (require.main === module) {
+  const suiteName = process.argv[2] ?? "";
+  if (!isSuiteName(suiteName)) {
+    throw new Error(
+      `Unknown test suite "${suiteName}", expected one of: ${Object.keys(SUITES).join(", ")}`,
+    );
+  }
+  prepareTestSelection(suiteName);
+}

.github/scripts/prepare-test-selection.unit.spec.ts

@@ -0,0 +1,268 @@
+import { spawnSync } from "node:child_process";
+import {
+  mkdirSync,
+  mkdtempSync,
+  readFileSync,
+  rmSync,
+  writeFileSync,
+} from "node:fs";
+import { tmpdir } from "node:os";
+import { join, resolve } from "node:path";
+
+import { load } from "js-yaml";
+
+import { SUITES, prepareTestSelection } from "./prepare-test-selection";
+
+type Suite = (typeof SUITES)[keyof typeof SUITES];
+
+type Step = {
+  id?: string;
+  if?: string;
+  uses?: string;
+  run?: string;
+  env?: Record<string, string>;
+  with?: Record<string, string | boolean>;
+};
+
+const SCRIPT = resolve(__dirname, "prepare-test-selection.ts");
+const SUITE_NAMES = ["unit", "loki", "e2e"] satisfies (keyof typeof SUITES)[];
+
+function loadWorkflow(file: string) {
+  // js-yaml returns an untyped value, and these repository workflows define jobs with steps.
+  return load(
+    readFileSync(resolve(__dirname, "../workflows", file), "utf8"),
+  ) as {
+    jobs: Record<
+      string,
+      { if?: string; outputs?: Record<string, string>; steps?: Step[] }
+    >;
+  };
+}
+
+function loadAction() {
+  // js-yaml returns an untyped value, and this repository action defines outputs and steps.
+  return load(
+    readFileSync(
+      resolve(__dirname, "../actions/prepare-test-selection/action.yml"),
+      "utf8",
+    ),
+  ) as {
+    outputs: Record<string, { value: string }>;
+    runs: { steps: Step[] };
+  };
+}
+
+describe("prepareTestSelection", () => {
+  const { loki } = SUITES;
+  let dir: string;
+  let env: NodeJS.ProcessEnv;
+
+  beforeEach(() => {
+    jest.spyOn(console, "warn").mockImplementation(() => {});
+    dir = mkdtempSync(join(tmpdir(), "test-selection-"));
+    mkdirSync(join(dir, "test-plan"));
+    writeFileSync(join(dir, "output"), "");
+    env = {
+      ...process.env,
+      RUNNER_TEMP: dir,
+      GITHUB_OUTPUT: join(dir, "output"),
+      PLAN_DOWNLOADED: "success",
+    };
+  });
+
+  afterEach(() => {
+    jest.restoreAllMocks();
+    rmSync(dir, { recursive: true, force: true });
+  });
+
+  function plan(files: unknown, total = 2, suite: Suite = loki) {
+    return {
+      [suite.filesKey]: files,
+      stats: {
+        [suite.totalKey]: total,
+        [suite.selectedKey]: Array.isArray(files) ? files.length : 0,
+      },
+    };
+  }
+
+  function writePlan(value: unknown) {
+    writeFileSync(join(dir, "test-plan/test-plan.json"), JSON.stringify(value));
+  }
+
+  const output = () => readFileSync(join(dir, "output"), "utf8");
+
+  it.each([{ files: ["one.spec.cjs"] }, { files: [] }])(
+    "preserves an explicit selection: $files",
+    ({ files }) => {
+      writePlan(plan(files));
+      prepareTestSelection("loki", env);
+      expect(output()).toBe(
+        `paths-file=${join(dir, loki.pathsFile)}\nselection=${files.length > 0 ? "narrowed" : "empty"}\n`,
+      );
+      expect(
+        JSON.parse(readFileSync(join(dir, loki.pathsFile), "utf8")),
+      ).toEqual(files);
+    },
+  );
+
+  it("writes the selection when invoked through Bun in CI", () => {
+    writePlan(plan(["one.spec.cjs"]));
+    const result = spawnSync("bun", [SCRIPT, "loki"], {
+      env,
+      encoding: "utf8",
+    });
+    expect(result.status === 0 ? "" : result.stderr).toBe("");
+    expect(result.status).toBe(0);
+    expect(output()).toBe(
+      `paths-file=${join(dir, loki.pathsFile)}\nselection=narrowed\n`,
+    );
+  });
+
+  it("writes no paths file for a full selection", () => {
+    writePlan(plan(["one.spec.cjs", "two.spec.cjs"]));
+    prepareTestSelection("loki", env);
+    expect(output()).toBe("selection=full\n");
+  });
+
+  it.each([
+    null,
+    {},
+    plan("[]"),
+    plan([null]),
+    { ...plan([]), [loki.filesKey]: ["one.spec.cjs"] },
+    plan([""]),
+    plan(["one.spec.cjs"], 0),
+  ])("runs in full for an invalid plan: %j", (value) => {
+    writePlan(value);
+    prepareTestSelection("loki", env);
+    expect(console.warn).toHaveBeenCalledWith(
+      expect.stringContaining("::warning::"),
+    );
+    expect(output()).toBe("");
+  });
+
+  it.each([
+    { scenario: "the test plan is missing", setup: () => {} },
+    {
+      scenario: "the test plan is truncated",
+      setup: () => {
+        writeFileSync(
+          join(dir, "test-plan/test-plan.json"),
+          `{"${loki.filesKey}":[`,
+        );
+      },
+    },
+    {
+      scenario: "the download failed",
+      setup: () => {
+        writePlan(plan([])); // Even a partial download must not be trusted.
+        env.PLAN_DOWNLOADED = "failure";
+      },
+    },
+  ])("runs in full when $scenario", ({ setup }) => {
+    setup();
+    prepareTestSelection("loki", env);
+    expect(console.warn).toHaveBeenCalledWith(
+      expect.stringContaining("::warning::"),
+    );
+    expect(output()).toBe("");
+  });
+
+  it.each(SUITE_NAMES)(
+    "reads the %s selection from its own plan keys",
+    (suiteName) => {
+      const suite = SUITES[suiteName];
+      writePlan(plan(["one.spec.cjs"], 2, suite));
+      prepareTestSelection(suiteName, env);
+      expect(output()).toBe(
+        `paths-file=${join(dir, suite.pathsFile)}\nselection=narrowed\n`,
+      );
+      expect(
+        JSON.parse(readFileSync(join(dir, suite.pathsFile), "utf8")),
+      ).toEqual(["one.spec.cjs"]);
+    },
+  );
+
+  it("ignores the other suites' selections", () => {
+    writePlan({
+      ...plan(["one.spec.cjs", "two.spec.cjs"]),
+      [SUITES.unit.filesKey]: [],
+      [SUITES.e2e.filesKey]: [],
+    });
+    prepareTestSelection("loki", env);
+    expect(console.warn).not.toHaveBeenCalled();
+    expect(output()).toBe("selection=full\n");
+  });
+
+  it("rejects an unknown suite", () => {
+    const result = spawnSync("bun", [SCRIPT, "toString"], {
+      env,
+      encoding: "utf8",
+    });
+    expect(result.status).not.toBe(0);
+    expect(result.stderr).toContain('Unknown test suite "toString"');
+  });
+});
+
+describe("test selection workflow steps", () => {
+  const ACTION = "./.github/actions/prepare-test-selection";
+  const CONSUMERS: Record<string, { suite: keyof typeof SUITES }> = {
+    "frontend.yml": { suite: "unit" },
+    "loki.yml": { suite: "loki" },
+  };
+
+  it("skips Loki visual tests only for an empty story selection", () => {
+    const { jobs } = loadWorkflow("loki.yml");
+    expect(jobs["story-selection"].outputs?.selection).toBe(
+      "${{ steps.loki-selection.outputs.selection }}",
+    );
+    expect(jobs["visual-test"].if).toContain(
+      "needs.story-selection.outputs.selection != 'empty'",
+    );
+    expect(jobs["visual-test"].if).not.toMatch(/outputs\.[\w-]+ *[!=]= *'\d+'/);
+  });
+
+  it.each(Object.entries(CONSUMERS))(
+    "selects tests through the composite action in %s",
+    (file, { suite, ...inputs }) => {
+      const steps = Object.values(loadWorkflow(file).jobs).flatMap(
+        ({ steps = [] }) => steps.filter((step) => step.uses === ACTION),
+      );
+
+      expect(steps.length).toBeGreaterThan(0);
+      for (const step of steps) {
+        expect(step.with).toEqual({
+          suite,
+          "test-plan-artifact-id": expect.stringMatching(/^\$\{\{ .+ \}\}$/),
+          ...inputs,
+        });
+      }
+    },
+  );
+
+  it("downloads the test plan before preparing the selection", () => {
+    const { outputs, runs } = loadAction();
+    const [download, prepare] = runs.steps;
+
+    expect(download).toMatchObject({
+      uses: expect.stringMatching(/^actions\/download-artifact@/),
+      "continue-on-error": "${{ inputs.require-download != 'true' }}",
+      with: {
+        "artifact-ids": "${{ inputs.test-plan-artifact-id }}",
+        path: "${{ runner.temp }}/test-plan",
+      },
+    });
+    expect(prepare).toMatchObject({
+      env: { PLAN_DOWNLOADED: `\${{ steps.${download.id}.outcome }}` },
+      run: expect.stringContaining(
+        'prepare-test-selection.ts "${{ inputs.suite }}"',
+      ),
+    });
+    expect(outputs).toMatchObject({
+      "paths-file": {
+        value: `\${{ steps.${prepare.id}.outputs.paths-file }}`,
+      },
+      selection: { value: `\${{ steps.${prepare.id}.outputs.selection }}` },
+    });
+  });
+});

.github/scripts/run-backend-test-jvms.sh

@@ -0,0 +1,160 @@
+#!/usr/bin/env bash
+#
+# Run this runner's share of a partitioned backend test suite as one or more concurrent
+# JVMs. The caller says how many runners share the suite and how many JVMs each gets.
+#
+# WHY MULTIPLE JVMS PER RUNNER
+# ----------------------------
+# Driver tests spend most of their wall time waiting on the remote warehouse, and they
+# can't use the idle CPU by using more threads because some tests mutate global state.
+# A second JVM gets that isolation for free.
+#
+# Two paths are NOT safe to share:
+#   * `target/junit` — hawk deletes the whole directory at `:begin-test-run`, so a JVM
+#     starting late would wipe an earlier one's results.
+#   * `logs/test-log.json` — the log4j2 File appender truncates it on open.
+# So each JVM runs in its own hardlinked copy of the checkout (inodes, not disk) and
+# outputs are merged back into the workspace afterwards.
+#
+# INPUTS (environment)
+# --------------------
+#   CLOJURE_ALIASES        alias string for `clojure -X`, e.g. dev:ci:ee:ee-dev:drivers:drivers-dev:test
+#   TEST_RUNNER_INDEX      index of this runner among those sharing the suite
+#   TEST_RUNNER_COUNT      how many runners share the suite
+#   TEST_JVMS_PER_RUNNER   concurrent JVMs per runner (default 1)
+#   TEST_HEAP_PER_JVM      -Xmx per JVM, applied only when running more than one
+#
+# Exits non-zero if any JVM fails.
+
+set -uo pipefail
+
+: "${CLOJURE_ALIASES:?CLOJURE_ALIASES is required}"
+: "${TEST_RUNNER_INDEX:?TEST_RUNNER_INDEX is required}"
+: "${TEST_RUNNER_COUNT:?TEST_RUNNER_COUNT is required}"
+TEST_ARGS=("$@")
+TEST_JVMS_PER_RUNNER="${TEST_JVMS_PER_RUNNER:-1}"
+TEST_HEAP_PER_JVM="${TEST_HEAP_PER_JVM:-4g}"
+
+die() {
+  echo "::error::run-backend-test-jvms.sh: $1"
+  exit 1
+}
+
+[[ "$TEST_RUNNER_INDEX" =~ ^[0-9]+$ ]] || die "TEST_RUNNER_INDEX must be a non-negative integer, got '$TEST_RUNNER_INDEX'"
+[[ "$TEST_RUNNER_COUNT" =~ ^[0-9]+$ ]] || die "TEST_RUNNER_COUNT must be a positive integer, got '$TEST_RUNNER_COUNT'"
+[[ "$TEST_JVMS_PER_RUNNER" =~ ^[0-9]+$ ]] || die "TEST_JVMS_PER_RUNNER must be a positive integer, got '$TEST_JVMS_PER_RUNNER'"
+[ "$TEST_RUNNER_COUNT" -ge 1 ] || die "TEST_RUNNER_COUNT must be at least 1"
+[ "$TEST_JVMS_PER_RUNNER" -ge 1 ] || die "TEST_JVMS_PER_RUNNER must be at least 1"
+[ "$TEST_RUNNER_INDEX" -lt "$TEST_RUNNER_COUNT" ] ||
+  die "runner index $TEST_RUNNER_INDEX is out of range for $TEST_RUNNER_COUNT runner(s) — a matrix entry was added without raising runner-count"
+
+# Partition indexes are split across runners rather than handed out in contiguous
+# blocks. E.g. with 2 runners and 2 JVMs the first runner gets partition 0 and 2, and
+# the second runner gets partitions 1 and 3. Hawk partitions in namespace order, so
+# neighbouring partitions have similar runtimes — contiguous blocks would group the slow
+# ones together onto one runner.
+PARTITION_TOTAL=$((TEST_RUNNER_COUNT * TEST_JVMS_PER_RUNNER))
+INDEXES=()
+for ((k = 0; k < TEST_JVMS_PER_RUNNER; k++)); do
+  INDEXES+=($((TEST_RUNNER_INDEX + k * TEST_RUNNER_COUNT)))
+done
+
+# One JVM: run directly in the workspace with no heap override, exactly as a
+# partitioned run behaved before this script existed.
+if [ "$TEST_JVMS_PER_RUNNER" -eq 1 ]; then
+  echo "Running partition ${INDEXES[0]} of $PARTITION_TOTAL"
+  exec clojure -X:"$CLOJURE_ALIASES" "${TEST_ARGS[@]}" \
+    :partition/total "$PARTITION_TOTAL" \
+    :partition/index "${INDEXES[0]}"
+fi
+
+
+WORKSPACE="$PWD"
+# Sibling of the checkout: same filesystem (so `cp -al` can hardlink) but outside the
+# repo, so one JVM's directory never gets copied into another's.
+JVM_DIRS_ROOT="$(dirname "$WORKSPACE")/backend-test-jvms"
+STATUS_DIR="$JVM_DIRS_ROOT/status"
+
+# Merge every JVM's results into the workspace the rest of the job reads from.
+#
+# Each partition's junit XML goes into its own subdirectory: `mb_hawk_var_less_errors.xml`
+# has a fixed name, so a flat copy would silently overwrite it. Nesting is safe because
+# both consumers (dorny/test-reporter and ci-conductor's backend adapter) walk
+# `target/junit` recursively and match on filename suffix.
+#
+# Runs from an EXIT trap so a cancelled or timed-out job still publishes whatever
+# finished.
+# shellcheck disable=SC2329  # invoked by the EXIT trap below, which shellcheck can't see.
+merge_outputs() {
+  mkdir -p "$WORKSPACE/target/junit" "$WORKSPACE/logs"
+  local idx jvm_dir
+  for idx in "${INDEXES[@]}"; do
+    jvm_dir="$JVM_DIRS_ROOT/partition-$idx"
+    if [ -d "$jvm_dir/target/junit" ]; then
+      mkdir -p "$WORKSPACE/target/junit/p$idx"
+      cp -a "$jvm_dir/target/junit/." "$WORKSPACE/target/junit/p$idx/" || true
+    fi
+    # `logs/test-log*.json` is what the action uploads on failure.
+    if [ -f "$jvm_dir/logs/test-log.json" ]; then
+      cp -a "$jvm_dir/logs/test-log.json" "$WORKSPACE/logs/test-log-p$idx.json" || true
+    fi
+  done
+}
+trap merge_outputs EXIT
+trap 'exit 143' TERM
+trap 'exit 130' INT
+
+# Hardlinked copy of the checkout. Skips the paths a run writes to (`target`, `logs`, `.cpcache`)
+# and the two most expensive trees nothing on the test classpath reads (`.git`, `node_modules`).
+prepare_jvm_dir() {
+  local jvm_dir="$1" entry
+  rm -rf "$jvm_dir"
+  mkdir -p "$jvm_dir"
+  for entry in "$WORKSPACE"/* "$WORKSPACE"/.[!.]*; do
+    [ -e "$entry" ] || continue
+    case "$(basename "$entry")" in
+      .git | node_modules | target | logs | .cpcache) continue ;;
+    esac
+    # Fall back to a real copy if the filesystem refuses the hardlink.
+    cp -al "$entry" "$jvm_dir/" 2>/dev/null || cp -a "$entry" "$jvm_dir/"
+  done
+}
+
+# Prefix output with the partition index so interleaved JVM logs stay readable.
+run_partition() {
+  local idx="$1" jvm_dir="$2" rc line
+  (
+    cd "$jvm_dir" || exit 1
+    # `-J` options land after the aliases' `:jvm-opts`, overriding the `:ci` alias's
+    # `-Xms12g -Xmx12g`. Xms stays small so JVMs sharing a runner grow into memory on
+    # demand rather than each committing its ceiling up front.
+    exec clojure -J-Xms512m -J-Xmx"$TEST_HEAP_PER_JVM" -X:"$CLOJURE_ALIASES" \
+      "${TEST_ARGS[@]}" \
+      :partition/total "$PARTITION_TOTAL" \
+      :partition/index "$idx"
+  ) 2>&1 | while IFS= read -r line || [ -n "$line" ]; do printf '[p%s] %s\n' "$idx" "$line"; done
+  rc="${PIPESTATUS[0]}"
+  echo "$rc" > "$STATUS_DIR/p$idx"
+}
+
+rm -rf "$JVM_DIRS_ROOT"
+mkdir -p "$STATUS_DIR"
+
+echo "Runner $TEST_RUNNER_INDEX of $TEST_RUNNER_COUNT: running $TEST_JVMS_PER_RUNNER concurrent JVMs for partition(s) ${INDEXES[*]} of $PARTITION_TOTAL (-Xmx$TEST_HEAP_PER_JVM each)"
+
+for idx in "${INDEXES[@]}"; do
+  prepare_jvm_dir "$JVM_DIRS_ROOT/partition-$idx"
+done
+
+for idx in "${INDEXES[@]}"; do
+  run_partition "$idx" "$JVM_DIRS_ROOT/partition-$idx" &
+done
+wait
+
+overall=0
+for idx in "${INDEXES[@]}"; do
+  rc="$(cat "$STATUS_DIR/p$idx" 2>/dev/null || echo 1)"
+  echo "partition $idx exited $rc"
+  [ "$rc" -eq 0 ] || overall=1
+done
+exit "$overall"