* fix(run): serial group failures reach the exit code and the reporters
- exit code folds serial groups: members carry no attempts, so a group's
infrastructure error exited 1, and a launch failure (all members skipped) exited 0
- group attempt that fails before any member runs (launch, file load) fails
the first member with the error, rest skip as serial-predecessor-failed;
an interrupt there skips every member instead
- a retry that never reached its members keeps the verdicts of the attempt before it
- worker crash during a serial member fails that member with WORKER_CRASH
instead of skipping it as never started
* docs(test): an interrupted serial launch skips every member
* fix(secrets): rewrite traces and text downloads whenever the run has a secret value
A registered value a test passed as a plain string (an app.open URL, a fill)
was redacted from titles, labels, and agent input but kept verbatim in
trace.zip: trace and download rewriting was gated on the exposure level,
which only a fill or an engine-held secret raises. Rewriting now depends on
the session ledger holding a value. The engine exposure level had no other
consumer and is removed; exposure now only decides pixels and saved-session
taint.
* fix(secrets): cover a plain-string fill, scope docs to the session's known values
* docs(secrets): download redaction is whole-value; TRACE_WITHHELD outside-path case
* docs(secrets): name the download rewrite failure path
* fix(e2e): load TypeScript with an oxc loader instead of tsx
* fix(e2e): close loader edge cases: sourceless CommonJS, export maps without extensions, unreadable tsconfig, chained source maps, Windows require paths
* fix(e2e): refuse Bun and Deno runtimes, name oxc load failures, follow Yarn PnP export targets
* perf(e2e): skip the syntax check for files whose only @ is in a package import
* fix(e2e): allow type-only exports in .cts, warn from runner only, Bun check first, docs
* fix(e2e): workers warn about tsconfigs runner did not, FILE: urls, foreign infra errors, review tests
* fix(cache): --strict-cache fails a step whose key changed under its recording
A cache key change (REPLAY_POLICY_VERSION, a new key field, an engine minor, the agent's context) turned every committed entry into a no-entry miss, which strict ran live. Strict now lists the file store once per run and fails a no-entry step with REPLAY_STALE when an entry recorded for the same step sits under another key. Entries now record the step's params digest, occurrence, and agent so a repeat or another agent is not mistaken for it.
* fix(cache): never take an entry the attempt claimed for a rekeyed step
An entry from before the occurrence fields matches by test, target, and instruction; an earlier occurrence's entry is now excluded, so an unrecorded repeat runs live. The message no longer says to delete the old entry, which may still serve another app identity.
* fix(cache): match a rekeyed recording only by its whole step
An entry without the params, occurrence, and agent could be another call of the same instruction, so strict now ignores it instead of guessing. A confirmed whole replay in read-write mode writes the missing provenance in, since it proved which step the entry belongs to.
* test(web-benchmark): complete the provenance of 25 agent recordings
Written by a local read-write replay (no model calls); only recordedFor and createdAt change. The 4 gap entries need a live run with a key.
* test(cache): assert the provenance backfill comes from a replay
* fix(expect): unawaited poll fails its own phase, slow first read counts toward negation window
- expect.poll is owned by the phase that started it (body, hook, fixture teardown, suite hook); left running it is cancelled and fails that phase with STEP_NOT_AWAITED instead of a later test
- pollCondition starts the negation window when the first read that saw it was issued and decides at the deadline without a read past it
* fix(expect): own polls by async lineage so a timed-out body never charges the next test
* docs(expect): scope STEP_NOT_AWAITED wording to where it surfaces; test reads past body
* fix(security): allow only http(s) navigation, refuse wrapped schemes on device links
view-source:file:// passed the file:/data:/javascript: denylist and loaded local files via app.open, browser.goto, and the navigate verb. resolveNavigationUrl now admits http: and https: only; mobile links also refuse view-source:, blob:, filesystem:.
* fix(security): admit exact about:blank, sync rule text in AGENTS.md and SECURITY.md
* fix(web): refuse about:blank cookie URL, qualify scheme rule text
* fix(cache): a failure where no model answered evicts no recording
MODEL_PROVIDER_FAILED and MODEL_UNAVAILABLE say nothing about the app. A step that fails with one concludes with no verdict (like a cancellation), and the attempt settles with implicatesUnconfirmed false: confirmed steps are still written, unconfirmed entries stay as stored.
* fix(cache): a later app failure still implicates unconfirmed entries
Settlement reads every failure in the attempt, not only the first: an afterEach assertion failing after a provider failure evicts what nothing confirmed.
* feat!: browser fixture, getByRole name arg, toMatchSchema, top-level hooks, separate credential namespace
API review feedback before launch:
- web fixture renamed browser (Web -> Browser, WebExpectation ->
BrowserExpectation); requires: ['browser']; destructuring web hints the
new name. web() factory and other Web* types unchanged.
- getByRole(role, name, options?) beside the object form; MCP locate
writes the short form.
- expect(value).toMatchSchema(standardSchema): sync, returns the typed
output; poll resolves to it, soft returns undefined after a kept failure.
- describe, beforeEach, afterEach, beforeAll, afterAll exported from e2e;
web and mobile export typed beforeEach/afterEach.
- credentials and secrets are separate namespaces: a password handle is
<name>.password, secrets.get() never returns it. Committed recordings
migrated offline (old key hash verified, then recomputed).
- runtime test.skip keeps Playwright semantics; docs say it throws.
* docs(web): browser acts on one active tab; cookies, routes, dialogs cover the whole browser
* fix(secrets): judge a fill's purpose by the config, not the handle; no old-name hints
A config-time secrets.get() handle reads its purpose from the run's
registry again, and authorizeSecretFill checks the registered purpose, so a
handle claiming generic-secret cannot put a password into a plain field.
Drop the web fixture migration hint. Changesets name the on-screen marker
change for replay entries.
* docs(skill): browser fixture, getByRole name arg, toMatchSchema, top-level hooks, credential namespace on the rewritten skill
* fix(expect): negated toMatchSchema returns nothing, as its type says
* fix(expect,docs): soft double negation stays soft, null ~standard is INVALID_ARGUMENT, Playwright samples keep Playwright's getByRole
Also documents SoftExpectCall, SoftValueExpectation, and NegatedPollExpectation
on the expect reference, requires: ['browser'] in the skill's options table,
and tightens the poll and secret-purpose tests.
* docs(babysit): triage pattern for scripted renames that rewrite another library's code
* docs: engine options take a secrets entry, web package hook exports, vault example imports
* refactor(secrets)!: credentials hold their password, allSecrets feeds fills; engines export describe and every hook; BrowserRoute, BrowserResponse
From the maintainability review:
- ResolvedConfig.secrets is the config.secrets entries only; a credential
carries its password; allSecrets is the one map fills, the ledger, and
redaction read. The per-consumer purpose filters and the .password
suffix parsing are gone, and e2e mcp builds handles from config.
- The config load and a running test name the credential a missing
secrets.get() most likely meant.
- @e2e-dev/web and @e2e-dev/mobile export describe and all four hooks
beside test, so a test file registers from one import.
- WebRoute and WebResponse are BrowserRoute and BrowserResponse.
- getByRole normalizes its arguments once; isTextMatch is the one
string-or-RegExp check; poll reuses ValueMatcherName.
* revert(web): keep WebRoute and WebResponse; Browser names the fixture, Web the network and option types
* feat!: the app is declared on its target; engines only drive it
The app under test moves from the engine's options to `targets: [{ engine,
app }]`: `url`, `bundleId`, `appPath`, `identity`, `environment`,
`launchArguments`, `permissions`, `command`, and `readyUrl`. `web()` and
`mobile()` refuse every moved option in one `INVALID_CONFIG` naming the
target block; `defineEngine({ app })` is gone and engines check what their
platform needs in `validateApp`. `requires: ['browser' | 'native-app']` is
derived from the target's app. Replay cache and session keys are byte for
byte what they were, pinned by target-identity.test.ts.
Dependency services are not part of this version: `services` anywhere, and
`web({ services })`, fail saying so. `app.command` on port 0 without a
command, and `reuseExisting` on a free port, are refused. An `e2e mcp`
open cancelled or disconnected mid-start stops what it started, and a hung
shared start is abandoned once no session waits on it.
* fix: review follow-ups: cancelled opens, abandoned starts, null targets, stale docs
* refactor: drop the moved-option messages; old app keys are unknown keys
* test: give the replaced-nodes suite a budget that survives a loaded runner
* test: size the replaced-nodes hook budget to its seven tests
* fix(agent): extract reports absent data instead of inventing it
Send the caller schema's shape only (no min/max/length/pattern/format) inside
an agent-extract-2 envelope { found, value, missing }. found: false fails the
step ASSERTION_INCONCLUSIVE naming what was missing; the repair round may
decline instead of bending a value to fit. Explore covers a declined plan like
an invalid one.
* fix(cache): ignore a gap's derived rule when comparing re-recorded flows
derived follows how the agent read the value on that run (pixels vs node),
never what a replay does, so read-write runs rewrote committed entries.
* fix(agent): stop blaming a control for an unchanged tree without pixel proof
Tree-only unchanged result now says no listed node changed and a drawn
change needs a screenshot; "no visible effect" only when an identical
screenshot backs it. With no screenshot to be had (secret filled, engine
captures none), an unchanged listing still says to try another way.
* fix(cache): REPLAY_STALE names the strict knob and configured cache dir
Was hardcoded to --strict-cache and .e2e/cache even when cache.strict or
cache.dir came from config.
* fix(web): names read generated content and drop icon-font glyphs
The tree named <button><i class="fa fa-sign-in"> Login</i></button> "Login"
while getByRole read the ::before glyph and found nothing. Names now read
::before/::after content as accname, Chrome, and Playwright do; private-use
glyphs are dropped from the reported name, and a role query's string name
tolerates them in the browser's name.
* fix(web,kernel): waitForDownload works on a Kernel browser
A remote browser saves downloads to its own disk, so Playwright's saveAs
over CDP always failed with 'canceled'. BrowserProvider gains an optional
downloads { dir, read }: the engine points the context's downloads at dir
on the browser's machine and reads the finished file back. kernel()
implements it with the browser filesystem API. Without it, the failure
names the provider.
* fix(web): forward worker-side lease progress to the reporter
Attempt-scope and replacement leases were acquired with a discarded log,
so Kernel's live-view line never showed. Use the worker's init log.
* fix(web,kernel): sweep leases a dead worker left open
A worker killed mid-attempt in kernel({ scope: 'attempt' }) leaked its
browser until Kernel's timeout. BrowserProvider gains an optional sweep,
called once per target in finish after the held leases are released;
kernel() deletes every active browser tagged with the run and target.
* fix(web,e2e): name persistent-context limits early
app.clearState() in attempt scope said 'engine web does not implement it';
the engine now refuses it naming the mode. A session consumed on a target
without a state capability fails selection with COLLECTION_ERROR instead
of failing session.save() after the setup test logged in.
* fix(kernel): trim Kernel error messages; docs: attempt scope rules out userAgent
The SDK keeps the newline Kernel ends an error body with, splitting the
run's error line. Trim every SDK failure's message.
* fix(web): absolute downloads.dir; crosscheck spaces glyphs as the tree does
Also guards the provider-downloads test cleanup and notes in the changeset
that a role query by a glyph-only control's title finds nothing.
* test(skill): fail a skill or docs paragraph that passes the removed --artifacts
* fix(config): name the replacement for a removed createAgent import
* fix(config): keep the code of a config error raised while the config evaluates
* fix(secrets): refuse a secrets.get() reference where a string is needed
* fix(config): reject unknown keys in engine, command, test, and query options
* fix(config): refuse a tests entry naming a directory, name the ! entry excluding a positional
* refactor(config): derive option key lists from their types
* fix(config): one shared unknown-key check; drop undefined env values
Setup and describe option keys typed from their interfaces; a directory tests entry is INVALID_GLOB like a trailing slash.
* fix(collect): name the excluding ! entry when exclusions left nothing, and in on-disk casing
* fix(config): address review - exclusion hint for bare names, array env, qualified hints
* test(select): use a missing tmp root, not /root, which CI cannot stat
* fix(mobile): accept videoTouches, added on main by #671, in the mobile() key list
* fix(mobile): reject unknown permission names and states in mobile() and device.openApp
Names and states are checked against DevicePermission and PermissionState
through satisfies-typed key lists. INVALID_CONFIG at load, INVALID_ARGUMENT
from device.openApp, before any device command. rejectUnknownKeys takes an
optional code for the test-time case.
* fix(eas): reject unknown easSimulators() options with INVALID_CONFIG
Its options are its own, mapped onto EAS's create input, not a passed-through
SDK body, so a typo such as buildID was dropped silently. Its two other option
refusals are INVALID_CONFIG too. e2e is now a peer, for e2e/engine.
* fix(mobile): require a plain object for permissions; clarify eas and permission notes
A Map passed the object check with no own keys, and the preset applied none
of it.
* fix(agent): resend a stalled model request; keep turns of a timed-out step
One provider request with no response held the step until its own timeout
(an explore step spent 220s of 240s on a single call). Each generate
request is now bounded at 120s and fails as a retryable provider error, so
the SDK's transport retries resend it; the turn notes it. Turns attach as
each ends, so a step the clock settles keeps them, and loop notes survive
the report's per-turn clip.
* fix(agent): abandon a stalled request whose provider ignores the abort
* docs(changeset): say where a first-turn stall note shows
* fix(agent): clear the stall timer when a provider throws synchronously
* feat(agents)!: plain-object agents entries, createAgent and limits removed
Each agents entry is one AgentConfig object: model, judge, system, context,
tools, maxSteps, maxModelCalls, judgmentTimeout, maxObservationBytes,
maxInputTokens, providerOptions, or executor for a custom brain (system and
tools rejected beside it). No inheritance between agents.
- createAgent() kept as a stub throwing INVALID_CONFIG; bare StepExecutor or
legacy createAgent value as an entry fails naming { executor } / the object
- timeout -> judgmentTimeout, maxTurns removed (entry and
createToolLoopExecutor), unknown keys get did-you-mean
- top-level limits removed; maxModelTokensPerCall -> per-agent
maxInputTokens, the rest internal constants; report-1 run.limits keeps
its shape, filled from max across agents plus the constants
- tools validated at config load; built-in agent built from the entry at
fixture time; explore and the MCP catalog read the entry's tools
- migrate apps, docs, docs examples, init scaffold, skills, mobile README
* docs: AGENTS.md names the agent entry's model, not createAgent
* refactor(agents)!: delete createAgent instead of a throwing stub
* docs: MODEL_UNAVAILABLE scoped to the built-in agent, fixture-acquisition timing
* feat(config)!: remove specVersion from the config
The runner version is the format version. A config that still sets
specVersion fails INVALID_CONFIG telling the author to remove it. The
report's run.specVersion and the replay cache key keep their hard-coded
copies.
* feat(collect): "!" exclusions in the tests globs
An entry starting with "!" removes files an including glob matched,
in any order. Discovery never reads a directory an exclusion takes
whole, unless an including glob could reach a dot name beneath it.
A list of only exclusions is INVALID_CONFIG.
* refactor!: CacheStore and web({ screencast }) renames
TraceCacheStore is CacheStore, and the docs, skill, and CLI call the
cache the replay cache. web({ video: { size, quality } }) is
web({ screencast }) with WebScreencastOptions; web({ video }) fails
INVALID_CONFIG naming screencast.
* feat(secrets): secrets.get() in engine options, resolved per attempt
At config evaluation, before any run exists, secrets.get(name) returns
a reference by name. An engine declares the handles its options hold
in defineEngine({ secrets }); the config load fails INVALID_CONFIG for
a name no secret or credential has. The engine reads the value through
EngineAttemptContext.resolveSecret, which runs a provider fresh and
registers the value in the session and process ledgers before it
returns, without tainting the viewport. e2e/engine exports isSecret.
web({ basicAuth: { password } }) takes a Secret and declares it. Docs
show process.loadEnvFile('.env') in the config.
* feat(run)!: trace and video share recording modes; artifacts holds only store
One RecordingMode ('off' | 'on' | 'retain-on-failure' | 'on-first-retry' |
'on-all-retries') for trace and video, set on the config, a target, the CLI
(--trace [mode], --video [mode]) and a test, one precedence rule: config,
target, CLI, test. Trace defaults to on locally, on-first-retry in CI, with
a plan-time notice when a retry mode meets retries: 0. Serial members cannot
set trace.
Capability rule: a mode from the config root or a flag applies to targets
whose engine can record it, one notice naming the rest; a mode set on a
target or a test is required and fails with UNSUPPORTED_ARTIFACT.
artifacts.kinds (both forms) and artifacts.trace are removed and fail
INVALID_CONFIG naming the trace mode they meant. Failure screenshot and
screen text are always captured when the engine can. MCP sessions keep the
target's trace mode and trace only under 'on'.
* feat(run)!: output directory for every run result; ArtifactStore.putLink
output (default .e2e) and --output <dir> on run and explore hold report.json,
junit.xml, summary.md, ai-trace.json, artifacts/, sessions/ and the e2e mcp
session files; --last-failed reads <output>/report.json. The reportSibling
derivation from the artifacts dir is gone. --artifacts stays as a hidden
flag that fails with the --output it maps to.
A run clears <output>/artifacts at start. cache.dir stays independent. An
output that is the project root or outside it, is or sits in cache.dir,
would hold cache.dir under artifacts/, sessions/ or videos/, or holds a
tests glob root fails INVALID_CONFIG with the reason.
ArtifactStore gains optional putLink(link) for provider-hosted video links;
its ref lands beside the url. A passed retain-on-failure attempt's link is
never handed over, and a failing putLink never fails the run.
bench-ab and the mobile workflow move to --output.
* test(secrets): a hold's registry is probed by an unknown name, now that get() defers without one
* test(web): the download trigger's measured wait tolerates a timer firing early
* fix(secrets): rewrite the trace of an attempt whose engine holds a secret
A Playwright trace records the context options, basic-auth password in
plaintext, but a trace was rewritten only after a fill. resolveSecret now
marks the session so its trace goes through the redactor, screencast
frames kept since the value never reached the screen. The fake engine
writes a real trace archive, and the basic-auth fixture escapes its echo
and refuses a malformed header.
* fix(web): race the basic-auth secret with the attempt's signal
A provider still resolving after the launch timeout set the session after
the runner ended the attempt, so the retry failed with an attempt already
running. Resolution now runs first, raced with the signal.
* fix(mcp): a session notes a configured trace its engine cannot record
* test: a shadow-free fake trace archive and an ungarbled exclusion title
* docs: output paths, replay cache wording, and review corrections
--last-failed, --ai-trace, and the json reporter name <output> paths;
the skill says output never moves cache/ or the app's log; the
INVALID_GLOB row states the check the code makes; serial members list
only; the engine vocabulary names Secret and isSecret; the basic-auth
example uses a provider; the last trace cache wording is replay cache.
* chore(changeset): leave released notes alone; pending notes match the renames
Released CHANGELOG entries keep TraceCacheStore, the name they shipped
with; cache-store-rename.md announces the rename. The pending video and
provider recording changesets name on-all-retries and web({ screencast }).
* chore(bench): refuse a forwarded --output the harness would not clean up
* fix(secrets): a rewritten trace drops its screencast frames, engine-held secrets included
* test(testbed): admin session saved from a cookie, no secret fill
A setup that signs in without filling a secret carries no pixel taint, so tests and explorations restoring it keep screenshots.
* feat(explore): --session starts the exploration signed in
Explore collects the config's test files unselected, so the runner's own session selection runs exactly the setup that declares the name, then restores it into the exploration. In-process runs adopt the in-memory registration only for its virtual file; setup files import as usual. Planner and explorer are told they start signed in. A missing session producer now lists declared sessions with did-you-mean. Docs: a restored session keeps its setup's taint (authentication.mdx claimed otherwise).
* fix(explore): a --session setup runs as the project's agents
The explorer replaced the configured agent for the whole run, so an agentic setup pulled in by --session got the exploration rules, report_finding, explorer budgets, and cache off. In-memory tests now carry their own agents (InMemoryAttempts) and run with the trace cache off; setups keep the config's agents, cache, and retries. Uncollected-file notice no longer mentions positionals under explore; consumesSession drops the unreachable group walk.
* docs(explore): qualify app.open and screenshot claims, fix errors.mdx clause
* feat(run)!: video modes on the config, targets, the CLI, and tests, with step captions
video: off | on | retain-on-failure | on-first-retry at the config root, per
target, --video [mode], and per test or describe, innermost winning.
artifacts.kinds: ['video'] and artifacts.video are removed. Kept recordings
get WebVTT step captions; a video can be a link to a hosted recording. The
engine contract's VideoSegment is a file or a link, and e2e/engine exports
the provider recording seam.
* feat(web): a browser provider records the attempts it serves, and the screencast takes a size and quality
BrowserProvider.record starts the service's own recording of the browser in
place of the page screencast. The session drives one AttemptVideo, the
screencast or the provider's. web({ video: { size, quality } }) tunes the
screencast.
* feat(mobile): a device provider records the attempts it serves
DeviceProvider.record starts the service's own recording of the leased
device in place of agent-device's. The worker learns its slot's lease id,
so record gets the lease as it traveled.
* feat(integrations): Kernel replays record the attempts that record video
* fix(run): captions never fail a video, provider values are normalized, and one list of modes
- Step captions create their directory and are best-effort.
- A provider's recording is checked at start in both engines and its URL
and start time are stored in the shapes the report schema admits; the
list reporter bounds a hosted URL.
- --video no longer hides an invalid target mode.
- A describe inside a serial group cannot set video.
- A mobile provider may keep its own leaseId field on a lease.
* fix(mobile): keep the lease type narrowed when checking its declared fields
* fix(run): MCP recordings get their step captions, a step spanning a restart is captioned in both recordings, and video.size refuses unknown keys
* fix: address review on the video API
- One stop in flight per provider recording, shared by a retry; mobile
dispose stops it, and a cancelled operation never starts one.
- Kernel retries a failed download without stopping the replay twice.
- Links from any engine are held to an http(s) URL with a host; a file a
provider names must be a regular file; media types are trimmed.
- web({ video }) takes a plain object only; the markdown page labels a
hosted artifact by its kind.
- Tests: fixture byte totals, captions linked by id, temp directories
removed, signals asserted, empty sizes, non-object options.
- Docs: engine support qualified, the explore row, the standalone preflight,
caption status text, a checked stop in the provider example.
* fix(run): a bad engine video link costs no other recording, captions path per recording in debugging guide
* test: fake engine video links doc matches segment order
* fix(mcp): session recordings follow video modes and list a provider's link
* test(web): provider test's fake page reports its viewport
* refactor(run): drop step captions from the video API, tracked in #636
* fix(web): a late provider start never replaces a newer recording, abandon keeps a failed stop's handle, video.size must be a plain object; provider recording errors and hosted URLs bounded
Stacked on #547. The one-off refuse hook and secureRefusal() give way to a
declarative readsWithheld flag on the matcher spec: value, text, and
attribute matchers set it, poll() runs denySecureRead() on it. Every
attribute name is denied, same as getAttribute(), since the contract does
not say which attributes an engine withholds.
* fix(expect): toHaveValue refuses a secure field instead of judging its withheld value as empty
The engine withholds a secure field's value (states.secure, no value), and
readField turned that gap into '' on any value control. So after filling a
password input, expect(locator).toHaveValue('') passed and
.not.toHaveValue('') failed with observed: value "". A test checking that a
sign-in form was cleared could pass falsely. inputValue() already denies the
read with POLICY_DENIED; the matcher now does the same before its predicate
runs, negated or not, so the message never carries the value. Plain fields
are unchanged and an empty non-secure control still reads as ''.
* fix(expect): toHaveText and toContainText refuse a secure field too
The engine withholds a secure field's text as well as its value, and
readField read the gap as '' for text matchers the same way. Same invariant
as toHaveValue: textContent() already denies the read, the text matchers now
do too, negated and in list form. toHaveAccessibleName and the state
matchers still answer on a secure field.
* refactor(expect): share one secure-field read guard with the locator getters
`--last-failed` selects only the tests the previous run did not pass, read
from the `report.json` this run overwrites (beside the artifact root):
failed, timed out, interrupted, or skipped because a setup, a serial
predecessor, a hook, or the worker failed, each named per target and agent
by its result id. No report there is `NO_LAST_RUN`; a run with nothing
failed selects nothing. `--shard <index/total>` runs one contiguous slice of
the selected tests, cut once every other filter and the serial closure
applied, the first shards taking the remainder, so a serial group is never
split and each shard brings only the setup tests it needs. `e2e list` takes
both. `RunOptions` and `ListOptions` carry them as `lastFailed` and `shard`.
* fix(collect): glob forms that match nothing are INVALID_GLOB
A tests glob or a positional glob that could never match a file now fails with INVALID_GLOB and a hint: an absolute path, a trailing slash, braces, a backslash separator, or a .. segment. A leading ./, a . segment, and a doubled slash are dropped, so ./tests/**/*.e2e.ts selects what tests/**/*.e2e.ts does instead of matching nothing, walking .git and .e2e, and pointing the NO_TESTS message at a missing example file.
* fix(collect): review fixes for the glob grammar
Segments without wildcards compile to names, so the near-miss scan reads a glob's leading directory off its segments (literalPrefix) and the positional glob test is the grammar's own GLOB_SYNTAX; the pattern string seam is gone. Character classes and extglobs are rejected with hints like braces. A trailing '.' and a normalized leading '!' are caught. An existing path wins over glob classification for positionals, so a file whose name has braces is still selectable by path. Messages name the fix; docs and the changeset describe positionals as the code treats them; the near-miss regression has a test.
* fix(collect): validate tags and the tests globs where they are written
tags must be a list of distinct names without spaces or commas, checked at registration: a bare string was iterable, so tags: 'smoke' registered five one-letter tags and --tag smoke never matched. tests must be a glob or a list of globs, each compiled at config resolution: a wrong type used to reach the glob compiler during collection as a plain TypeError and exit 1 as a test failure instead of INVALID_CONFIG.
* fix(collect): review fixes for tag and tests validation
The tag rule is what --tag can spell back: distinct names, none blank, no comma, no leading or trailing whitespace; inner spaces stay legal, so the mobile benchmark's 'Login Form' tags collect. A registration error names its file. normalizeTests takes the honest unknown boundary, names an empty glob as a value, and its comment states what changed. Messages quote values through describeValue, which now names objects and undefined. Config tests assert error codes; docs state one rule everywhere and the error-code rows list the new causes.