Files
windmill/ai_evals/adapters/frontend/vitestAdapter.test.ts
centdix 4296a6ae1f feat(ai-chat): cap read_app_file + search_app grep tool to bound context in large raw apps (#9653)
* docs: add global AI chat context-optimization plan for raw apps

Co-Authored-By: Claude Opus 4.8 (1M context) <noreply@anthropic.com>

* test(ai-evals): add global raw-app debugging cases on a large fixture

Adds a ~20-file analytics_dashboard raw-app fixture (incl. a 5k-line data module
and a planted wrong-totals bug), two global cases (read-heavy debug + small-edit
baseline), app-seed support in the mock backend, directory-fixture loading, and a
decorateHelpers seam so read-dedupe is measurable. Records tokenUsage for before/
after comparison of the read-tool optimization.

Co-Authored-By: Claude Opus 4.8 (1M context) <noreply@anthropic.com>

* feat(ai-chat): cap and dedupe read_app_file to bound context in large apps

read_app_file now defaults to a head slice (1500 lines / 50k chars) with offset/
limit to page further, and skips resending a file whose earlier read is still in
context (per-conversation ledger keyed off the originating tool-call id, so it
self-heals after compaction). Bounds the file-content portion of global-chat
context when working in large raw apps.

Co-Authored-By: Claude Opus 4.8 (1M context) <noreply@anthropic.com>

* test(ai-evals): add read-heavy raw-app debug case (large data module)

global-test31 induces the model to inspect the 5k-line seedData module, exercising
the read_app_file cap/offset path. Baseline ~262k tokens vs ~200k with the cap+dedupe
change (-24%).

Co-Authored-By: Claude Opus 4.8 (1M context) <noreply@anthropic.com>

* docs: record A+B benchmark results and fixed-overhead finding

Co-Authored-By: Claude Opus 4.8 (1M context) <noreply@anthropic.com>

* fix(ai-chat): clearer read_app_file past-EOF message + unit tests for cap/dedupe

Addresses local-review nits: out-of-range offset now reports 'offset N is past the
end of the file' instead of a backwards 'lines 11-10' label; adds unit coverage for
the slicing (line cap, offset/limit window, char budget, past-EOF) and re-read dedupe
(hit + miss-when-not-retained).

Co-Authored-By: Claude Opus 4.8 (1M context) <noreply@anthropic.com>

* feat(ai-chat): char-level paging + per-range dedupe for read_app_file

Adds char_offset/char_limit so minified/long-line files can be paged within a line
window, keys the re-read ledger by range (so reading different ranges no longer
collides), and dedupes on the full-file hash (a cached range stub is invalidated
when any byte of the file changes, not just the returned range). Tests updated for
the char-slice behavior plus single-line capping, char paging, and out-of-window
change detection.

Co-Authored-By: Claude Opus 4.8 (1M context) <noreply@anthropic.com>

* test(ai-chat): add read_app_file context micro-benchmark + re-read eval case

Adds a deterministic micro-benchmark (no LLM) that drives read_app_file through a
realistic big-project read pattern (large file, re-read, minified bundle, paging)
and asserts the cap+dedupe cut returned context >50% vs the old whole-file behavior
— isolating the feature's effect from model nondeterminism and guarding against
silent weakening. Adds global-test32, a cross-file consistency investigation that
revisits overlapping files so re-read dedupe is exercised in a real run.

Co-Authored-By: Claude Opus 4.8 (1M context) <noreply@anthropic.com>

* test(ai-evals): clarify test32 measures the read cap, not dedupe

Verified: sonnet and haiku both read each file once per conversation and retain
it, so test32 never triggers read_app_file re-read dedupe. Dedupe is measured
deterministically by the micro-benchmark instead. Comment corrected to match.

Co-Authored-By: Claude Opus 4.8 (1M context) <noreply@anthropic.com>

* refactor(ai-chat): drop read_app_file re-read dedupe, ship the cap only

Benchmarking showed the per-conversation re-read dedupe never fires in practice:
across sonnet/opus/gpt-5.5/haiku, every model reads each file once per conversation
and keeps it in context (0 within-conversation re-reads). It was a correct but unused
guard, so this removes the ledger, full-file hash, retention predicate, the
AIChatManager wiring, and the eval decorateHelpers seam — keeping the read cap +
offset/limit/char paging (A), which is the lever that actually bounds context. The
micro-benchmark is now cap-only; test32 is kept as a multi-file read-load case.

Co-Authored-By: Claude Opus 4.8 (1M context) <noreply@anthropic.com>

* feat(ai-chat): add search_app grep tool for global raw-app chat (experimental)

Client-side grep over a raw app's frontend files and inline runnables (literal,
case-insensitive, optional file_glob/context_lines/max_matches, head-capped).
Completes the list -> search -> ranged-read triad. Includes the eval A/B gate
(WMILL_AI_EVAL_DISABLE_SEARCH_APP), unit tests + micro-benchmark, and a
find-all-usages eval case (global-test33).

Experimental: A/B benchmarking shows it is not an unconditional win — it helps
on find-all-usages but adds agentic iterations on navigable apps.

Co-Authored-By: Claude Opus 4.8 (1M context) <noreply@anthropic.com>

* test(ai-evals): accept search_app as a valid file-inspection tool in raw-app cases

Add requiredToolsAnyOf alternatives-group to ToolValidationSpec and switch
global-test29..32 to it so a model that locates files via search_app instead
of read_app_file no longer false-fails the tool assertion.

Co-Authored-By: Claude Opus 4.8 (1M context) <noreply@anthropic.com>

* docs: remove stale ai-chat context-optimization planning doc

Co-Authored-By: Claude Opus 4.8 (1M context) <noreply@anthropic.com>

* refactor(ai-chat): drop read_app_file char paging for a hard char cap

The char_offset/char_limit params guarded minified files (a single line over
the char budget) but were effectively unused in benchmarks. Remove them and the
in-window char paging; keep the hard 50k-char budget and, when a read hits it,
tell the model to narrow the line limit (or treat the file as unreadable if a
single line exceeds the budget). Proper long-line handling is left as a TODO.

Co-Authored-By: Claude Opus 4.8 (1M context) <noreply@anthropic.com>

* refactor(ai-chat): bake search_app context to 1 line, clarify query is literal

Drop the context_lines param (models varied it to little effect) for a fixed
SEARCH_APP_CONTEXT_LINES=1, and cap on matching lines instead of pushed rows so
max_matches stays accurate with context always on. Sharpen the query description
to state it is a literal (non-regex) substring and to suggest the call form
(e.g. formatCurrency() to hit call sites and skip formatCurrencyPrecise.

Co-Authored-By: Claude Opus 4.8 (1M context) <noreply@anthropic.com>

* refactor(ai-chat): widen baked search_app context to 2 lines

Models that set the old context_lines param leaned to 2; match the lean.

Co-Authored-By: Claude Opus 4.8 (1M context) <noreply@anthropic.com>

* fix(ai-chat): count every file with a match in search_app header

Move fileHadMatch ahead of the render cap so files whose matches fall past max_matches are still counted (with a regression test). Also swap the raw NUL globstar sentinel for a printable escape (the NUL bytes made core.ts read as binary to grep) and reword two comments to describe current constraints instead of drafting history.

Co-Authored-By: Claude Opus 4.8 (1M context) <noreply@anthropic.com>

* fix(ai-chat): drop redundant input echoes from app tool results

read_app_file and search_app no longer prefix results with the tool name or echo back the caller's own inputs (file path, query, file_glob) — the model already has them from the call args, and the unbounded query echo could push the search result past its output budget. Keeps the useful signals (line range, match/file counts, truncation) and the actionable advice. Also reword max_matches to 'matching lines' since it caps lines (each expands to context rows). Unit tests updated to the new format.

Co-Authored-By: Claude Opus 4.8 (1M context) <noreply@anthropic.com>

---------

Co-authored-by: Claude Opus 4.8 (1M context) <noreply@anthropic.com>
2026-06-19 13:33:54 +00:00

472 lines
19 KiB
TypeScript

import { expect, it, vi } from 'vitest'
// @ts-ignore - Node.js fs/promises
import { mkdir, writeFile } from 'fs/promises'
// @ts-ignore - Node.js path
import { dirname, resolve } from 'path'
vi.mock('monaco-editor', () => ({
editor: {},
languages: {},
KeyCode: {},
Uri: {
parse: (value: string) => ({ toString: () => value })
},
MarkerSeverity: {
Error: 8,
Warning: 4,
Info: 2,
Hint: 1
}
}))
vi.mock('@codingame/monaco-vscode-standalone-typescript-language-features', () => ({
getTypeScriptWorker: async () => async () => ({}),
typescriptVersion: 'test'
}))
vi.mock('@codingame/monaco-vscode-languages-service-override', () => ({
default: () => ({})
}))
vi.mock('$lib/components/vscode', () => ({}))
vi.mock('$lib/gen', async () => {
const actual = await vi.importActual<any>('$lib/gen')
const {
getBenchmarkAppByPath,
getBenchmarkCompletedJob,
getBenchmarkCompletedJobResultMaybe,
getBenchmarkDatatableSchema,
getBenchmarkDraftForUser,
getBenchmarkFlowByPath,
getBenchmarkJobLogs,
getBenchmarkScriptByHash,
getBenchmarkScriptByPath,
hasBenchmarkWorkspace,
listBenchmarkApps,
listBenchmarkDatatables,
listBenchmarkDrafts,
listBenchmarkFlows,
listBenchmarkJobs,
listBenchmarkScripts,
createBenchmarkHttpTrigger,
createBenchmarkSchedule,
previewBenchmarkSchedule,
runBenchmarkDatatableSql,
runBenchmarkFlowByPath,
runBenchmarkScriptPreview,
updateBenchmarkDraft
} = await import('./mockBackend')
function wrapService<T extends object>(target: T, overrides: Record<string, unknown>): T {
return new Proxy(target, {
get(source, property, receiver) {
if (typeof property === 'string' && property in overrides) {
return overrides[property]
}
return Reflect.get(source, property, receiver)
}
})
}
return {
...actual,
DraftService: wrapService(actual.DraftService, {
updateDraft: async (data: {
workspace: string
kind: any
path: string
requestBody?: { value?: unknown }
}) =>
hasBenchmarkWorkspace(data.workspace)
? updateBenchmarkDraft(data)
: actual.DraftService.updateDraft(data),
getDraftForUser: async (data: { workspace: string; kind: any; path: string }) =>
hasBenchmarkWorkspace(data.workspace)
? getBenchmarkDraftForUser(data)
: actual.DraftService.getDraftForUser(data),
listDrafts: async (data: { workspace: string }) =>
hasBenchmarkWorkspace(data.workspace)
? listBenchmarkDrafts(data.workspace)
: actual.DraftService.listDrafts(data)
}),
ScriptService: wrapService(actual.ScriptService, {
listScripts: async (data: { workspace: string }) =>
hasBenchmarkWorkspace(data.workspace)
? (listBenchmarkScripts(data.workspace) ?? [])
: actual.ScriptService.listScripts(data),
existsScriptByPath: async (data: { workspace: string; path: string }) =>
hasBenchmarkWorkspace(data.workspace)
? Boolean(getBenchmarkScriptByPath(data.workspace, data.path))
: actual.ScriptService.existsScriptByPath(data),
getScriptByPath: async (data: { workspace: string; path: string }) => {
if (hasBenchmarkWorkspace(data.workspace)) {
const script = getBenchmarkScriptByPath(data.workspace, data.path)
if (!script) {
throw new Error(`Script "${data.path}" not found in benchmark workspace`)
}
return script
}
return actual.ScriptService.getScriptByPath(data)
},
getScriptByPathWithDraft: async (data: { workspace: string; path: string }) => {
if (hasBenchmarkWorkspace(data.workspace)) {
const script = getBenchmarkScriptByPath(data.workspace, data.path)
if (!script) {
throw new Error(`Script "${data.path}" not found in benchmark workspace`)
}
return script
}
return actual.ScriptService.getScriptByPathWithDraft(data)
},
getScriptByHash: async (data: { workspace: string; hash: string }) => {
if (hasBenchmarkWorkspace(data.workspace)) {
const script = getBenchmarkScriptByHash(data.workspace, data.hash)
if (!script) {
throw new Error(`Script hash "${data.hash}" not found in benchmark workspace`)
}
return script
}
return actual.ScriptService.getScriptByHash(data)
}
}),
FlowService: wrapService(actual.FlowService, {
listFlows: async (data: { workspace: string }) =>
hasBenchmarkWorkspace(data.workspace)
? (listBenchmarkFlows(data.workspace) ?? [])
: actual.FlowService.listFlows(data),
existsFlowByPath: async (data: { workspace: string; path: string }) =>
hasBenchmarkWorkspace(data.workspace)
? Boolean(getBenchmarkFlowByPath(data.workspace, data.path))
: actual.FlowService.existsFlowByPath(data),
getFlowByPath: async (data: { workspace: string; path: string }) => {
if (hasBenchmarkWorkspace(data.workspace)) {
const flow = getBenchmarkFlowByPath(data.workspace, data.path)
if (!flow) {
throw new Error(`Flow "${data.path}" not found in benchmark workspace`)
}
return flow
}
return actual.FlowService.getFlowByPath(data)
},
getFlowByPathWithDraft: async (data: { workspace: string; path: string }) => {
if (hasBenchmarkWorkspace(data.workspace)) {
const flow = getBenchmarkFlowByPath(data.workspace, data.path)
if (!flow) {
throw new Error(`Flow "${data.path}" not found in benchmark workspace`)
}
return flow
}
return actual.FlowService.getFlowByPathWithDraft(data)
},
getFlowLatestVersion: async (data: { workspace: string; path: string }) => {
if (hasBenchmarkWorkspace(data.workspace)) {
const flow = getBenchmarkFlowByPath(data.workspace, data.path)
if (!flow) {
throw new Error(`Flow "${data.path}" not found in benchmark workspace`)
}
return { id: 1 }
}
return actual.FlowService.getFlowLatestVersion(data)
}
}),
JobService: wrapService(actual.JobService, {
runScriptPreview: async (data: {
workspace: string
requestBody?: {
content?: string
language?: string
args?: Record<string, unknown>
path?: string
}
}) => {
if (!hasBenchmarkWorkspace(data.workspace)) {
return actual.JobService.runScriptPreview(data)
}
const requestBody = data.requestBody ?? {}
const database = requestBody.args?.database
// Datatable SQL runs as a `postgresql` preview against `datatable://<name>`.
// Execute it through the canned-SQL mock instead of linting it as a script.
if (
requestBody.language === 'postgresql' &&
typeof database === 'string' &&
database.startsWith('datatable://')
) {
return runBenchmarkDatatableSql({
workspace: data.workspace,
datatableName: database.slice('datatable://'.length),
sql: requestBody.content ?? ''
})
}
return runBenchmarkScriptPreview({ workspace: data.workspace, requestBody })
},
runFlowByPath: async (data: {
workspace: string
path: string
requestBody?: Record<string, unknown>
}) =>
hasBenchmarkWorkspace(data.workspace)
? runBenchmarkFlowByPath({
workspace: data.workspace,
path: data.path,
args: data.requestBody
})
: actual.JobService.runFlowByPath(data),
getJob: async (data: { workspace: string; id: string }) => {
if (hasBenchmarkWorkspace(data.workspace)) {
const job = getBenchmarkCompletedJob(data.workspace, data.id)
if (!job) {
throw new Error(`Job "${data.id}" not found in benchmark workspace`)
}
return job
}
return actual.JobService.getJob(data)
},
getCompletedJobResultMaybe: async (data: { workspace: string; id: string }) =>
hasBenchmarkWorkspace(data.workspace)
? getBenchmarkCompletedJobResultMaybe({ workspace: data.workspace, id: data.id })
: actual.JobService.getCompletedJobResultMaybe(data),
listJobs: async (data: { workspace: string }) =>
hasBenchmarkWorkspace(data.workspace)
? (listBenchmarkJobs(data.workspace) ?? [])
: actual.JobService.listJobs(data),
getJobLogs: async (data: { workspace: string; id: string }) =>
hasBenchmarkWorkspace(data.workspace)
? getBenchmarkJobLogs(data.workspace, data.id)
: actual.JobService.getJobLogs(data)
}),
WorkspaceService: wrapService(actual.WorkspaceService, {
listDataTableTables: async (data: { workspace: string }) =>
hasBenchmarkWorkspace(data.workspace)
? (listBenchmarkDatatables(data.workspace) ?? [])
: actual.WorkspaceService.listDataTableTables(data),
getDataTableTableSchema: async (data: {
workspace: string
datatableName: string
schemaName: string
tableName: string
}) =>
hasBenchmarkWorkspace(data.workspace)
? getBenchmarkDatatableSchema({
workspace: data.workspace,
datatableName: data.datatableName,
schemaName: data.schemaName,
tableName: data.tableName
})
: actual.WorkspaceService.getDataTableTableSchema(data)
}),
ScheduleService: wrapService(actual.ScheduleService, {
existsSchedule: async (data: { workspace: string; path: string }) =>
hasBenchmarkWorkspace(data.workspace) ? false : actual.ScheduleService.existsSchedule(data),
listSchedules: async (data: { workspace: string }) =>
hasBenchmarkWorkspace(data.workspace) ? [] : actual.ScheduleService.listSchedules(data),
getSchedule: async (data: { workspace: string; path: string }) => {
if (hasBenchmarkWorkspace(data.workspace)) {
throw new Error(`Schedule "${data.path}" not found in benchmark workspace`)
}
return actual.ScheduleService.getSchedule(data)
},
previewSchedule: async (data: { requestBody?: Record<string, unknown> }) =>
previewBenchmarkSchedule(data),
createSchedule: async (data: { workspace: string; requestBody: Record<string, unknown> }) =>
hasBenchmarkWorkspace(data.workspace)
? createBenchmarkSchedule(data)
: actual.ScheduleService.createSchedule(data)
}),
ResourceService: wrapService(actual.ResourceService, {
existsResource: async (data: { workspace: string; path: string }) =>
hasBenchmarkWorkspace(data.workspace) ? false : actual.ResourceService.existsResource(data),
listResource: async (data: { workspace: string }) =>
hasBenchmarkWorkspace(data.workspace) ? [] : actual.ResourceService.listResource(data),
getResource: async (data: { workspace: string; path: string }) => {
if (hasBenchmarkWorkspace(data.workspace)) {
throw new Error(`Resource "${data.path}" not found in benchmark workspace`)
}
return actual.ResourceService.getResource(data)
},
queryResourceTypes: async (data: { workspace: string }) =>
hasBenchmarkWorkspace(data.workspace) ? [] : actual.ResourceService.queryResourceTypes(data)
}),
VariableService: wrapService(actual.VariableService, {
existsVariable: async (data: { workspace: string; path: string }) =>
hasBenchmarkWorkspace(data.workspace) ? false : actual.VariableService.existsVariable(data),
listVariable: async (data: { workspace: string }) =>
hasBenchmarkWorkspace(data.workspace) ? [] : actual.VariableService.listVariable(data),
getVariable: async (data: { workspace: string; path: string }) => {
if (hasBenchmarkWorkspace(data.workspace)) {
throw new Error(`Variable "${data.path}" not found in benchmark workspace`)
}
return actual.VariableService.getVariable(data)
}
}),
AppService: wrapService(actual.AppService, {
existsApp: async (data: { workspace: string; path: string }) =>
hasBenchmarkWorkspace(data.workspace)
? Boolean(getBenchmarkAppByPath(data.workspace, data.path))
: actual.AppService.existsApp(data),
listApps: async (data: { workspace: string }) =>
hasBenchmarkWorkspace(data.workspace)
? (listBenchmarkApps(data.workspace) ?? [])
: actual.AppService.listApps(data),
getAppByPath: async (data: { workspace: string; path: string }) => {
if (hasBenchmarkWorkspace(data.workspace)) {
const app = getBenchmarkAppByPath(data.workspace, data.path)
if (!app) {
throw new Error(`App "${data.path}" not found in benchmark workspace`)
}
return app
}
return actual.AppService.getAppByPath(data)
}
}),
HttpTriggerService: wrapService(actual.HttpTriggerService, {
existsHttpTrigger: async (data: { workspace: string; path: string }) =>
hasBenchmarkWorkspace(data.workspace) ? false : actual.HttpTriggerService.existsHttpTrigger(data),
listHttpTriggers: async (data: { workspace: string }) =>
hasBenchmarkWorkspace(data.workspace) ? [] : actual.HttpTriggerService.listHttpTriggers(data),
getHttpTrigger: async (data: { workspace: string; path: string }) => {
if (hasBenchmarkWorkspace(data.workspace)) {
throw new Error(`HTTP trigger "${data.path}" not found in benchmark workspace`)
}
return actual.HttpTriggerService.getHttpTrigger(data)
},
createHttpTrigger: async (data: { workspace: string; requestBody: Record<string, unknown> }) =>
hasBenchmarkWorkspace(data.workspace)
? createBenchmarkHttpTrigger(data)
: actual.HttpTriggerService.createHttpTrigger(data)
}),
WebsocketTriggerService: wrapService(actual.WebsocketTriggerService, {
existsWebsocketTrigger: async (data: { workspace: string; path: string }) =>
hasBenchmarkWorkspace(data.workspace)
? false
: actual.WebsocketTriggerService.existsWebsocketTrigger(data),
listWebsocketTriggers: async (data: { workspace: string }) =>
hasBenchmarkWorkspace(data.workspace)
? []
: actual.WebsocketTriggerService.listWebsocketTriggers(data),
getWebsocketTrigger: async (data: { workspace: string; path: string }) => {
if (hasBenchmarkWorkspace(data.workspace)) {
throw new Error(`Websocket trigger "${data.path}" not found in benchmark workspace`)
}
return actual.WebsocketTriggerService.getWebsocketTrigger(data)
}
}),
KafkaTriggerService: wrapService(actual.KafkaTriggerService, {
existsKafkaTrigger: async (data: { workspace: string; path: string }) =>
hasBenchmarkWorkspace(data.workspace)
? false
: actual.KafkaTriggerService.existsKafkaTrigger(data),
listKafkaTriggers: async (data: { workspace: string }) =>
hasBenchmarkWorkspace(data.workspace) ? [] : actual.KafkaTriggerService.listKafkaTriggers(data),
getKafkaTrigger: async (data: { workspace: string; path: string }) => {
if (hasBenchmarkWorkspace(data.workspace)) {
throw new Error(`Kafka trigger "${data.path}" not found in benchmark workspace`)
}
return actual.KafkaTriggerService.getKafkaTrigger(data)
}
}),
NatsTriggerService: wrapService(actual.NatsTriggerService, {
existsNatsTrigger: async (data: { workspace: string; path: string }) =>
hasBenchmarkWorkspace(data.workspace) ? false : actual.NatsTriggerService.existsNatsTrigger(data),
listNatsTriggers: async (data: { workspace: string }) =>
hasBenchmarkWorkspace(data.workspace) ? [] : actual.NatsTriggerService.listNatsTriggers(data),
getNatsTrigger: async (data: { workspace: string; path: string }) => {
if (hasBenchmarkWorkspace(data.workspace)) {
throw new Error(`NATS trigger "${data.path}" not found in benchmark workspace`)
}
return actual.NatsTriggerService.getNatsTrigger(data)
}
}),
PostgresTriggerService: wrapService(actual.PostgresTriggerService, {
existsPostgresTrigger: async (data: { workspace: string; path: string }) =>
hasBenchmarkWorkspace(data.workspace)
? false
: actual.PostgresTriggerService.existsPostgresTrigger(data),
listPostgresTriggers: async (data: { workspace: string }) =>
hasBenchmarkWorkspace(data.workspace)
? []
: actual.PostgresTriggerService.listPostgresTriggers(data),
getPostgresTrigger: async (data: { workspace: string; path: string }) => {
if (hasBenchmarkWorkspace(data.workspace)) {
throw new Error(`Postgres trigger "${data.path}" not found in benchmark workspace`)
}
return actual.PostgresTriggerService.getPostgresTrigger(data)
}
}),
MqttTriggerService: wrapService(actual.MqttTriggerService, {
existsMqttTrigger: async (data: { workspace: string; path: string }) =>
hasBenchmarkWorkspace(data.workspace) ? false : actual.MqttTriggerService.existsMqttTrigger(data),
listMqttTriggers: async (data: { workspace: string }) =>
hasBenchmarkWorkspace(data.workspace) ? [] : actual.MqttTriggerService.listMqttTriggers(data),
getMqttTrigger: async (data: { workspace: string; path: string }) => {
if (hasBenchmarkWorkspace(data.workspace)) {
throw new Error(`MQTT trigger "${data.path}" not found in benchmark workspace`)
}
return actual.MqttTriggerService.getMqttTrigger(data)
}
}),
SqsTriggerService: wrapService(actual.SqsTriggerService, {
existsSqsTrigger: async (data: { workspace: string; path: string }) =>
hasBenchmarkWorkspace(data.workspace) ? false : actual.SqsTriggerService.existsSqsTrigger(data),
listSqsTriggers: async (data: { workspace: string }) =>
hasBenchmarkWorkspace(data.workspace) ? [] : actual.SqsTriggerService.listSqsTriggers(data),
getSqsTrigger: async (data: { workspace: string; path: string }) => {
if (hasBenchmarkWorkspace(data.workspace)) {
throw new Error(`SQS trigger "${data.path}" not found in benchmark workspace`)
}
return actual.SqsTriggerService.getSqsTrigger(data)
}
}),
GcpTriggerService: wrapService(actual.GcpTriggerService, {
existsGcpTrigger: async (data: { workspace: string; path: string }) =>
hasBenchmarkWorkspace(data.workspace) ? false : actual.GcpTriggerService.existsGcpTrigger(data),
listGcpTriggers: async (data: { workspace: string }) =>
hasBenchmarkWorkspace(data.workspace) ? [] : actual.GcpTriggerService.listGcpTriggers(data),
getGcpTrigger: async (data: { workspace: string; path: string }) => {
if (hasBenchmarkWorkspace(data.workspace)) {
throw new Error(`GCP trigger "${data.path}" not found in benchmark workspace`)
}
return actual.GcpTriggerService.getGcpTrigger(data)
}
}),
AzureTriggerService: wrapService(actual.AzureTriggerService, {
existsAzureTrigger: async (data: { workspace: string; path: string }) =>
hasBenchmarkWorkspace(data.workspace)
? false
: actual.AzureTriggerService.existsAzureTrigger(data),
listAzureTriggers: async (data: { workspace: string }) =>
hasBenchmarkWorkspace(data.workspace) ? [] : actual.AzureTriggerService.listAzureTriggers(data),
getAzureTrigger: async (data: { workspace: string; path: string }) => {
if (hasBenchmarkWorkspace(data.workspace)) {
throw new Error(`Azure trigger "${data.path}" not found in benchmark workspace`)
}
return actual.AzureTriggerService.getAzureTrigger(data)
}
})
}
})
const benchmarkOutputPath = process.env.WMILL_FRONTEND_AI_EVAL_OUTPUT_PATH
const benchmarkIt = benchmarkOutputPath ? it : it.skip
benchmarkIt(
'runs the frontend benchmark adapter from environment input',
async () => {
const { resetBenchmarkMockBackend } = await import('./mockBackend')
resetBenchmarkMockBackend()
const { runFrontendBenchmarkFromEnv } = await import('./benchmarkRunner')
try {
const payload = await runFrontendBenchmarkFromEnv()
const absoluteOutputPath = resolve(benchmarkOutputPath!)
await mkdir(dirname(absoluteOutputPath), { recursive: true })
await writeFile(absoluteOutputPath, JSON.stringify(payload, null, 2) + '\n', 'utf8')
expect(payload.cases.length).toBeGreaterThan(0)
} finally {
resetBenchmarkMockBackend()
}
},
// Full-suite runs (30+ cases at concurrency 2-3) routinely exceed 10 minutes.
7_200_000
)