Verify each finding against current code. Fix only still-valid issues, skip the
rest with a brief reason, keep changes minimal, and validate.

Inline comments:
In `@NativeScript/runtime/DevFlags.mm`:
- Around line 95-103: The allowlist check in RemoteUrlMatchesAllowlistEntry is
matching raw URL prefixes too early, which lets path-scoped entries be bypassed
with dot-segment paths. Update the matching logic to canonicalize or normalize
the URL path before applying the prefix/boundary rules, or explicitly reject
plain/encoded dot segments in DevFlags.mm so a trailing-slash allowlist entry
cannot match escaped paths.

In `@NativeScript/runtime/ModuleInternal.mm`:
- Around line 236-264: The debug handling in ModuleInternal.mm is swallowing
non-HTTP ES module failures by returning true or an empty namespace, which
prevents worker error propagation for .mjs loads. Update the
NativeScriptException catch and the moduleNamespace.IsEmpty path so debug mode
still surfaces failures to the caller for worker-loaded ESM, instead of always
pretending success; keep the existing HTTP debug logging, but ensure the
Worker.mm TryCatch can observe the error for the ES module load path.

In `@NativeScript/runtime/URLImpl.cpp`:
- Around line 94-100: The install script execution in URLImpl should not fail
silently: the current Compile/Run flow can leave blob URL support partially
initialized and a pending V8 exception uncleared. Update the script path in
URLImpl to wrap the v8::Script::Compile and script->Run calls in a v8::TryCatch,
then explicitly handle both compile and runtime failures by logging the error
and propagating it (or throwing) instead of ignoring the result. Use the
existing blob_methods script setup in URLImpl as the place to add this error
handling.

In `@NativeScript/runtime/Worker.mm`:
- Around line 486-499: The HMR termination loop in Worker::TerminateWorkers
currently iterates all entries from Caches::Workers, which can affect workers
from other runtimes. Update this callback to filter worker wrappers by the
current main isolate, matching the existing Runtime::~Runtime() behavior via
WorkerWrapper::GetMainIsolate(). Keep the existing running/closing checks and
only call WorkerWrapper::Terminate() for workers belonging to the same isolate.

In `@TestRunner/app/tests/esm/hmr/hot-data-ext.js`:
- Around line 51-73: The hot-data fixture is mutating shared HMR state by
invoking hot.accept, hot.dispose, hot.decline, and hot.invalidate in the shared
test helper, which makes later specs order-dependent. Update hot-data-ext.js so
the shared fixture only checks for the presence of HMR APIs and data on hot, and
remove lifecycle/callback registration from this path. If coverage for those
methods is needed, move it into a separate throwaway module or dedicated test
helper that is not reused across specs.

In `@TestRunner/app/tests/NodeBuiltinsAndOptionalModulesTests.mjs`:
- Around line 55-78: The test cleanup in the __ns_test_vendor__ import-map spec
is not restoring the runtime’s prior import-map state, which can leak
configuration into later specs. Snapshot the existing import-map before calling
configureRuntime in this test, then in the finally block restore that original
import-map instead of resetting to an empty imports object. Keep the existing
__nsVendorRegistry restore logic intact so the test remains hermetic.

In `@TestRunnerTests/Embassy/TCPSocket.swift`:
- Around line 60-66: The SO_NOSIGPIPE setup in TCPSocket is currently ignoring
the result of setsockopt, which can leave the socket in a state where send may
trigger SIGPIPE before Transport.handleWrite() can observe EPIPE. Update the
socket setup path in the TCPSocket initializer/helper to check the setsockopt
return value, and if it fails on Darwin, immediately treat it as a socket error
by closing the socket and propagating an error back to the caller instead of
discarding it. Use the TCPSocket and Transport.handleWrite symbols to locate the
write-path setup and keep the failure handling aligned with the existing socket
lifecycle.

In `@TestRunnerTests/TestRunnerTests.swift`:
- Line 24: The test setup in DefaultHTTPServer is still binding the server to
127.0.0.1 even though TCPSocket.bind(interface:) currently treats the interface
as IPv6, so the listener is not truly IPv4. Update the TestRunnerTests/server
setup to use the matching loopback family consistently (for example, switch both
server and client-side expectations to ::1/[::1]), or if IPv4 is required,
adjust TCPSocket and the DefaultHTTPServer path to support AF_INET first. Use
the existing DefaultHTTPServer initializer and TCPSocket.bind interface handling
to locate the change.

---

Outside diff comments:
In `@NativeScript/runtime/Runtime.mm`:
- Around line 445-458: Runtime::RunMainScript currently ignores the boolean
result from ModuleInternal::RunModule, so startup can continue even when main
module loading fails without throwing. Update RunMainScript to use the same
failure contract as Runtime::RunModule by capturing the return value from
moduleInternal_->RunModule and handling a false result as a startup failure,
using the existing Runtime and ModuleInternal::RunModule symbols to locate the
change.

---

Nitpick comments:
In @.github/workflows/npm_release.yml:
- Around line 263-279: The failure diagnostics step is too broad: it copies the
entire CoreSimulator log tree and runs an unbounded log collect, which can
create oversized artifacts and slow CI. In the diagnostics block that uses DIAG,
xcrun simctl spawn, and log collect, stop archiving the full CoreSimulator
directory and switch to a targeted unified-log collection window using the macOS
15/Xcode 26-supported log collect --last option so only recent logs are
captured.

In `@NativeScript/runtime/ModuleInternalCallbacks.h`:
- Around line 44-45: GetLoadedModuleUrls() is still using an implicit current
isolate, which can mix up worker and main-thread diagnostics now that the module
registry is isolate-keyed. Update the ModuleInternalCallbacks API so
GetLoadedModuleUrls takes a v8::Isolate* parameter, and propagate that isolate
through the implementation and any call sites to match the other registry
helpers. Use the existing registry symbols in ModuleInternalCallbacks to keep
the diagnostics explicitly scoped to the target isolate.

In `@NativeScript/runtime/Runtime.mm`:
- Around line 252-253: The TODO in Runtime.mm about a possible worker queue
leak/race during termination ordering needs to be tracked before merge. Follow
up on the worker lifecycle path in the Runtime-related
initialization/termination flow, especially around the queue handling and the
Terminate-before-Initialize scenario, and either replace the TODO with a
concrete fix or create a tracked issue/fix plan linked to the worker queue race
so it is not lost.

In `@NativeScript/runtime/URLImpl.cpp`:
- Around line 59-90: The URLImpl::searchParams getter caches a single
_searchParams instance and never refreshes it when url.search changes, so later
reads can return stale query data. Update the URL.prototype.searchParams
handling in URLImpl.cpp so the cached URLSearchParams is invalidated or resynced
whenever the search setter runs, and make sure the getter recreates/updates the
instance from the current search string before returning it.

Verify each finding against current code. Fix only still-valid issues, skip the
rest with a brief reason, keep changes minimal, and validate.

Inline comments:
In `@NativeScript/runtime/HMRSupport.mm`:
- Around line 806-814: Timed-out prefetch work in HMRSupport.mm can still
complete later and overwrite g_prefetchCache with stale data after
dispatch_group_wait has already returned. Add a per-prefetch generation or
cancel marker around the prefetch flow in the relevant HMRSupport functions
handling the cache write path, and check that marker immediately before storing
the fetched body. Make sure the guard is shared by the scheduled blocks in both
affected sections so only the active reload cycle can commit into
g_prefetchCache.
- Around line 36-43: `InitializeHmrDevGlobals` only defines the `globalThis`
mirror once, so repeated or re-entrant installs can leave
`globalThis.__NS_DEV__` pointing at a stale object. Update the generated
assignment in `HMRSupport.mm` so the mirror is refreshed on each install instead
of only when undefined, while still preserving the `Object.defineProperty`
behavior used for `name` and the `__NS_DEV__` global.

In `@NativeScript/runtime/Runtime.mm`:
- Around line 137-148: Update the hasUrlScheme handling in Runtime::dirname
logic so single-segment HTTP-style module URLs like http://host/main.js are
reduced to the host root for import.meta.dirname instead of keeping the full
module URL. The current lastSlash > pathStart check in the modulePath branch is
too strict; adjust the condition or split logic so the final path segment is
stripped whenever a URL path exists after the host, while still preserving the
identity for host-only or non-hierarchical schemes such as node:fs and blob:abc.

In `@NativeScript/runtime/URLImpl.cpp`:
- Around line 61-89: The cached URLSearchParams instance in URLImpl is not
refreshed when the search string is reassigned, so stale values can be returned
after setting URL.search. Update the SetSearch logic in URLImpl to either clear
_searchParams when search changes or synchronize the existing object with the
new query string, so later URL.searchParams access reflects the latest value.
- Around line 26-91: The injected blob URL setup in URLImpl.cpp is not
idempotent: repeated execution can redeclare BLOB_STORE and InternalAccessor and
can fail when redefining URL.prototype.searchParams. Update the blob_methods
script so its top-level declarations are guarded or reused on subsequent
installs, and make the searchParams property definition configurable so the
accessor can be safely reinstalled without throwing. Use the existing
URL.createObjectURL, URL.revokeObjectURL, InternalAccessor, and
Object.defineProperty(URL.prototype, 'searchParams', ...) sections as the fix
points.

---

Outside diff comments:
In `@NativeScript/runtime/Worker.mm`:
- Around line 228-229: The worker module loading path in Worker::Start still
ignores Runtime::RunModule’s new false return, so failures that only populate
outErrorMessage never surface to worker.onerror. Update the RunModule call site
to capture the boolean result and error message, then route that failure through
the same worker error handling path used for TryCatch so both thrown and
non-thrown evaluation/load errors are reported consistently.

---

Nitpick comments:
In @.github/workflows/npm_release.yml:
- Around line 262-279: The UDID lookup in the simulator log collection step can
pick the wrong device on runners with multiple runtimes because it falls back to
a name-only search in xcrun simctl list devices. Update the logarchive
collection logic to reuse the exact simulator used by the Xcode Tests step or
filter the fallback by the same runtime/destination as the test run, then keep
using that resolved UDID in the xcrun simctl spawn log collect path.

In `@NativeScript/runtime/HMRSupport.mm`:
- Around line 8-18: Add the missing direct include for <memory> in HMRSupport.mm
because the file uses std::shared_ptr and std::make_shared and should not rely
on transitive headers. Update the include block near the top of the file so the
needed standard library types are declared explicitly, keeping the existing
RuntimeConfig, Worker, and helper includes unchanged.

In `@TestRunner/app/tests/HttpEsmLoaderTests.js`:
- Around line 245-249: The skip guards in the HTTP ESM loader specs contain dead
code after synchronous pending() calls. In the relevant test blocks within
HttpEsmLoaderTests.js, remove the unnecessary done(); return; lines that follow
pending() so the guard reads cleanly and matches the actual control flow; apply
the same simplification to the other pending() skip checks in the same test
file.
- Around line 242-344: The URL key canonicalization tests repeat the same
host-skip guard in each case, making the suite noisy and harder to maintain. Add
a small shared helper near the existing getHostOrigin, withTimeout, and
formatError utilities (for example, a function like
requireHostOriginOrSkip(done)) that checks for a missing origin, calls pending
with the same message, then finishes the test early. Update each of the four
describe("URL Key Canonicalization") specs to use that helper instead of
duplicating the if (!origin) block.

Verify each finding against current code. Fix only still-valid issues, skip the
rest with a brief reason, keep changes minimal, and validate.

Outside diff comments:
In `@NativeScript/runtime/ModuleInternal.mm`:
- Around line 1031-1040: The HTTP module load path in ModuleInternal.mm is
swallowing the real loader failure in the isHttpModule branch by returning an
empty Local<Value>() when LoadHttpModuleForUrl fails. Update the
RunModule/module compilation flow so that, instead of returning empty in the
RuntimeConfig.IsDebug branch, it propagates the exception from
LoadHttpModuleForUrl (or throws a NativeScriptException with the loader error)
and lets outErrorMessage capture that cause. Keep the existing
logPhase("compile", "fail", "http-loader") but ensure the failure exits via an
error path, not a fallback namespace return.

---

Duplicate comments:
In `@NativeScript/runtime/ModuleInternal.mm`:
- Around line 234-256: The ESM worker load path in ModuleInternal.mm still
swallows failures in debug because it only checks RuntimeConfig.IsDebug and
!isHttpModule, so .mjs worker entry errors return true instead of propagating.
Update the ES module handling around the load-failure and empty-namespace
branches to also exclude worker contexts, using the same worker-aware gating
already applied in the require()/cache path, so Worker.mm’s TryCatch can observe
the exception and fire worker.onerror.

---

Nitpick comments:
In @.github/workflows/npm_release.yml:
- Around line 171-176: The runtime-suite note is stale and does not match the
pinned Xcode version. Update the comment near the workflow’s macOS runner and
XCODE_VERSION pin to describe the actual Xcode 15 / iOS 15 runtime instead of
Xcode 26 / iOS 26, keeping the note consistent with the deterministic pinning
rationale in the same block.