The method-replacement census marks a method name as an observed slot
when some write might replace it, and calls of observed methods go
through a checked property lookup whose result converts back to the
declared return type. Two kinds of data writes over-approximated that:
- A computed write into a string-keyed dictionary marked every method in
the program unless the dictionary's values were primitives. Class
instances have no implicit index signature, so such a dictionary is a
class view only when the class declares the index signature, and then
every method must be assignable to its value type. Any value type no
function can inhabit now qualifies: primitives, or non-callable object
types that require a property functions lack, or weak types sharing no
property with functions.
- A named write like `this.literal = token` marked `literal` for every
class. The write can only replace a method when the written property
can hold a function, so property writes are now judged by the written
property's type (prefetched in one batch).
Compiling vercel-labs/tsc-ts failed after the canary promotion: one
`changedProjects[id] = {...}` write marked every method, OptionNameMap.get
and the JSON parser's literal() calls returned unknown, and their Map-typed
results could not convert back (SC1100/SC1101, 61 errors).
Also skip abstract methods when materializing observed prototype slots.
An abstract declaration emits no prototype member, so lookup continues
to the ancestors; building its value instead threw an uncaught
PoisonError out of the reachability fixed point (the tsc-ts crash).
Tests: corpus 3171 (fails with SC1100/SC1101 before this change) matches
Node in the plain and sanitized lanes; the 112 corpus programs matching
abstract|prototype|method|callback pass; class-dynamic-dispatch unit
tests pass. tsc-ts now builds and type-checks itself with output
identical to tsgo 7.0.2.
The TypeScript 7 parity job reported tests/corpus/3170-number-conversion-
fast-paths.ts as missing a baseline. Recorded with
SCRIPTC_UPDATE_BASELINES=1 pnpm exec vitest run
packages/compiler/test/ts7/order-parity.test.ts: the re-recorded file
added only this program (and the later stack's console programs, which
belong to #764), with no existing entry changed. The entry is inserted
at its sorted position in the stack's baseline block so it does not
overlap the #764 entries when the stack is rebased.
node scripts/test-ts7.mjs --baselines-only passes.
The bootstrap-seed build rejected `host.rcHelpers ?? []` in shapes.ts
(SC2011: `Set<string> | never[]` has no static representation) and the
spread of that union into a string[] literal (SC1090). A small helper copies
the set's keys into a plain array (empty when inline RC is off), which both
callers iterate; emitInlineRcHelpers still sorts its copy. Behavior is
unchanged.
The default build's largest size contributor on the stack was H23's
-falign-functions=64 on every x86-64 runtime unit (2-11 KB per program;
results/h45-size-budget). Release and library flavors now keep the
compiler's default function alignment; the opt-in speed flavor keeps the
blanket 64-byte alignment. Vendored archives stay 64-byte aligned
(lre_exec keeps its pinned placement) except libunicode.c, whose small
table helpers were most of the regex programs' padding. The runtime-first
link order is unchanged.
Docs and usage text describe speed without the reverted runtime profile.
The speed posture's inline scr_union_release fast path predates the
runtime change that buffers a surviving union box as a cycle candidate
only when its arm_trace can reach a cycle. It still enqueued every
surviving box: sound (an untraced box visits nothing and the runtime death
path reads the header), but it gave back that change's collector savings
under --optimization=speed. The fast path now loads arm_trace and returns
when it is NULL, exactly like scr_union_release; scr_runtime.h pins the
offset.
Re-lands perf/h02-runtime-lto (6d373317, b62448f3) behind the speed
posture.
- Runtime packs gain an executable `speed` flavor whenever the host LLVM
helper can run. Its static units are emitted through the helper's
`runtime-unit` command (promoted unit-local symbols, object and import
bitcode from one module); its SCR_DYNAMIC variants reference the release
objects. Release, dev, and library flavors and the vendor archives are
built exactly as before (the rebuilt macOS pack's flavors and archives
are identical to the baseline's).
- Speed program builds load the speed flavor's bitcode and pass it to the
helper (`--import-bitcode`); release builds never do.
loadRuntimeBitcode only reads a real speed flavor, never release.
- The helper drops the emitter's inert sanitize_address attributes only
when it imports, so release modules reach the pipeline unchanged.
- Tests: runtime-pack.test.ts covers speed-variant bitcode selection,
verification, and that release-flavor bitcode is never imported;
native-codegen.test.ts covers helper arguments and cache keys.
Release executables stay byte-identical to the stack tip with the rebuilt
helper (14/14 workloads, macOS).
Re-lands perf/h30-inline-rc (00051ca0, 40398773, 07972360) behind the
speed posture. With inline RC on, every mirrored runtime RC family
retains inline and releases inline down to the rc == 1 / new cycle
candidate slow path (shapes.ts INLINE_RC_FAMILIES). Release emission is
unchanged: ShapeHost.rcHelpers is null unless LlvmTargetOptions.inlineRc
is set, and every retain/release (including capture boxes) stays a
runtime call; the %ScrMapRc type is only emitted with inline RC.
- index.ts and native/prepare.ts pass inlineRc for speed executables,
speed object/asm emission, and speed library profiles.
- scr_runtime.h keeps H30's static asserts for the mirrored header and
trace-slot offsets (no code change; the rebuilt macOS pack's manifest is
identical to the baseline's).
- Tests: shapes.test.ts pins release symbols and H30's speed fast paths
and header offsets; emitter.test.ts pins that release IR is unchanged
and speed routes releases through the helpers. The differential harness
gains `// @optimization: speed` (and a SCRIPTC_TEST_OPTIMIZATION=speed
lane); corpus 4032 pins every mirrored family under speed.
Release executables stay byte-identical to the stack tip (14/14
workloads, macOS).
Speed is a third native optimization posture next to release (default,
-O2) and dev (-O0). It is optimized exactly like release at the C/LLVM
level and is the switch for optimizations that trade executable size and
build time for run-time speed, so the default release build stays inside
the binary-size budget.
- backend/optimization.ts: the NativeOptimization type, its -O class, and
cache-key helpers. Release keeps its historical key shapes (absent).
- CLI: build/run/cache warm accept speed; usage text names the trade.
Bootstrap's routed executable cache mirrors the posture.
- Early executable cache keys and native-feature validation include speed,
so release, dev, and speed entries never satisfy one another.
- Runtime packs: an optional executable `speed` flavor (-O2, only beside
release). Speed links it when present and the release objects otherwise;
library modes link their release flavor. The sanitizer lane follows the
same flavor key.
- Library profiles accept "speed".
- WASI release-only linker flags apply to speed too.
- bench-runtime: --baseline-optimization/--candidate-optimization and a
per-contender cold_build_ms.
Release executables are byte-identical to the stack tip for all 14
benchmark workloads (macOS arm64, sha256 of executables built from both
trees).
`i in arr` with a non-literal number key boxed the typed array into the
checked-dynamic tree and materialized every element per evaluation, so
`for (...) if (i in arr)` loops were quadratic (1e4 elements: 5.3 s vs
Node 0.7 ms). A number key over an array receiver now lowers to arrayHas
(scr_arr_has), the query the literal fold and Object.hasOwn already use;
the key is stabilized first to keep JS evaluation order.
`k in dict` with a runtime string key over an index-signature record
snapshotted and scanned every overflow key per probe (1e4 keys: 436 ms,
1e5: timeout). The helper now ends in recordOvfHas (scr_map_has_str).
The bootstrap-seed build rejected the compound `value ^= value >> 30n` and
`value ^= value >> 27n` on bigint in string-key-hash.ts (SC1043), while the
plain `^` form on the next line compiles. Spell both as `value = value ^
(...)`. The hash is unchanged.
On 64-bit little-endian targets ScrStr's capacity word is split into a
32-bit cap and a 32-bit cached Map key hash (header stays 24 bytes).
Heap strings fill the hash on first lookup; every in-place mutation path
(unique concat, split scratch reuse, regrow, spare reuse) clears it.
Immortal strings are never written: compiler literals and the runtime's
one-character/empty statics carry the hash precomputed (string-key-hash.ts
mirrors scr_key_hash; both sides pin the same vectors).
scr_key_hash seeds by length multiplicatively: XORing the length into the
low bits cancelled against the last byte ("ab" and "abc" collided).
Map string lookups inline the probe into each getter and reject linear
entries by hash; set specializes its probe/overwrite by lookup kind with a
shared append path.
Tests: runtime map.test.ts (pinned vectors, statics, in-place append
invalidation), string-key-hash.test.ts, corpus 3141-map-string-key-hash
(plain + sanitized; mutation-checked against both invalidation paths).
The bootstrap-seed build rejected `"receiver" in expr` / `"args" in expr`
on the IR expression union in constant-callbacks.ts (SC1090: `in` on an
object union). A switch over the six data-intrinsic kinds now returns their
operands (receiver first; none for mapNew/setNew, as before) and replaces
the DATA_INTRINSICS set. Behavior is unchanged.
Upstream native workers (095b6193) compile the runtime with -DSCR_WORKERS,
which makes scr_cyc_live and scr_weak_dispose_hook thread-local, and the
small-object allocator is compiled out there. The inline allocation paths
address those as ordinary globals, so worker programs keep the out-of-line
runtime calls, exactly like thread-instanced libraries.
A worker-threads test pins that worker LLVM references neither the
allocator state nor the thread-local counters, and that worker programs
keep the fiber path for async bodies (the entry 07 adaptation).
Emitted record and class constructors called scr_rt_calloc/scr_cyc_alloc
with a constant size, so the size class, the zeroing length and the
collector header setup were recomputed per object behind a call (plus an
empty scr_obj_alloc_note call and a variable-length memset). llvm/alloc.ts
now emits the fast paths inline: pop the class free list (clearing only
the bytes the helper does not store itself) or bump, with the old calls as
the cold slow path. Releases inline the weak-dispose hook check, the live
count, and the free-list push; blocks outside the reservation still go to
scr_rt_free.
The emitted IR does not know which runtime it links against (the sanitized
lane only differs at link time), so the runtime now defines scr_sa in
every build. Where the allocator is compiled out (ASan, SCR_RC_AUDIT,
wasm32, Windows, 32-bit, thread-instanced libraries) it stays all-zero and
the inline paths always take the slow path, which keeps the RC-audit
object notes. ScrSaState's layout is pinned with static asserts. Inline
emission is additionally gated off for 32-bit, WASI, Windows triples and
thread-instanced libraries.
Runtime callers with hot constant-size allocations (union boxes, arrays,
boxes, closures, dyn nodes) use new static inline twins
scr_cyc_alloc_inline/scr_cyc_free_inline; scr_cyc_live is exported.
The ABI guard now recognizes function-pointer extern data
(scr_weak_dispose_hook). New corpus program 4410 pins recycled-block
clearing, size classes, objects above the largest class, cycles and weak
observers.
`new Item()` now calls the borrowed constructor body, so no retain transfers the fresh instance into it: the snapshot body retains twice, not three times.
layouts.ts and classes.ts imported NullableRefFields type-only, so the
self-hosted layout stage never saw the class declaration and rejected
`NullableRefFields | undefined`. They now import the class itself, and the
field record names the object variant directly instead of an intersection
type.
The bootstrap-seed build compiles the compiler with scriptc, which rejected
`for (const index of parameters.get(fn.name) ?? [])` in the emitter: the
`Set<number> | never[]` union has no static representation (SC2011). Read
the set once and iterate it only when present. Behavior is unchanged.
A whole-value read of a nullable-pointer field allocated a heap box per
read, so list walks (`p = p.next`) regressed: 0.07 s -> 0.35 s on a 100k
list walked 200 times. Such reads now retain the instance pointer into
the current frame and wrap it in a private stack box with that
independent owner:
- local union storage accepts nullable field reads and copies of another
binding of the same union as sources (the payload is retained; scalar
and unit arms own nothing; retains branch on the tag because not every
retain entry point is NULL-tolerant);
- arguments to projection-only parameters of calls and constructors.
The list walk now takes 0.05 s (baseline 0.07 s). Corpus 4061 adds a copy
that outlives a store to the field and copies across string, number,
-0 and undefined arms.
A class field typed `C | null` or `C | undefined` (one unit arm plus one
emitted class arm) now holds the instance pointer itself: NULL is the unit
arm. The struct slot stays `ptr`, so layouts are unchanged.
- Teardown, trace and gcFree use the slot's storage type (the class arm);
every class retain/release/visit entry point is NULL-tolerant.
- Projections of a field read (tag tests, narrowing, truthiness, unionDisc,
nullish, borrowed equality operands) use a private stack box over the
borrowed pointer; whole-value reads build an owned heap box (or the
immortal unit instance); generic borrowed receivers get that owned box.
- Stores take the payload of a wrap directly, or the retained payload of
a borrowed union; a store of a union binding is a projection use, so
constructor parameters stored this way are projection-only.
- `new` calls the borrowed constructor body when the lifetime analysis
allows it, so projection-only arguments become private stack boxes.
- The dyn bridges (materialize, commit, symbol fields) convert between
the pointer and a temporary union.
alloc-trees no longer allocates a union box per tree edge. Corpus 4061
pins tests, narrowing, nullish, optional chaining, equality with
mutation, escapes, reassignment, subclass instances, unionDisc, `any`
reads/writes, JSON, console output, cycles, and a 300k chain teardown.
macOS arm64 (H23 runner, --layouts=4 --runs=16, vs perf/harness):
alloc-trees -45.5%, records-sort -72.8%, numeric-kernels -29.4%,
ast-interp -21.3%, word-graph -12.4%; template-render +1.9% and
functional-pipeline +0.8% (both within 2%); geomean -17.6%.
Accepting nullish and unionEq as projection uses also proves parameters
projection-only, so callers pass private stack boxes to them. The narrowed
nullish shape now always borrows a binding (no code runs between the read
and the payload extraction), and unionEq routes proven parameters through
the borrowed receiver path, so a stack box never reaches union RC entry
points. Found by the Linux corpus (free(): invalid pointer in 1535 and
others); pinned by a stack-unions unit test and corpus 4060.
Union values consumed only by projections no longer allocate heap boxes:
- closure bodies get local lifetime facts (parameters stay unproven), so
for-of bindings and optional reads inside comparators use stack boxes;
- unionEq and the narrowed nullish shape are projection uses; their
wrapped-literal, optional array read, and Map.get operands are emitted
as private stack boxes;
- optional array reads consumed by tests/narrowing/comparisons use a
stack box with the inline dense lookup; f64/bool elements are supported
(slot bits copied, runtime state check kept for holes and sparse slots);
- scalar union payload reads are inline loads so LLVM can scalarize the
stack boxes.
Corpus 4060 pins holes, sparse/noncanonical indices, -0/NaN/false,
reference identity, closure locals, and mutation inside ?? defaults.
Equal names are common in records-sort, and equal strings at different
addresses still reached scr_str_cmp. When the first words match and both
strings have the same length of at most 16 bytes, the word ending at that
length covers the remaining bytes: equal words answer 0, and a difference
is ordered by its first byte (ASCII-only for the UTF-16 order).
records-sort compares interned literals (`key === "department"`, equal
departments) and names that differ in their first bytes, yet every
comparison was an out-of-line call (and memcmp through a stub).
- sc_str_eq: identity, then byte length, then scr_str_eq.
- sc_str_cmp / sc_str_cmp_u16: identity; then the first differing byte
of one 8-byte word when both strings are that long, otherwise of the
first bytes; the UTF-16 order is decided inline only for ASCII bytes.
Everything else calls the runtime.
The helpers are internal module functions that LLVM inlines; they are
emitted whenever the runtime entry is declared.
The comparator sort kernel also holds one undefined-`this` window for the
whole sort (each emitted call restores the receiver stack it pushes) and
resolves the element retain function once.
The cleanup fixture runs as a closure body; its literal binding is now a
stable immortal value without cleanup, so the test uses an owned value.
Whole-union string equality is a borrowing use, so its caller passes a
stack box instead of a heap union.
After the union fix, records-sort spent most of its time in the IR merge
sort's element moves: every src[i] read retained the swapped `src` array
and the element (scr_arr_get_ref), every dst[k] write released the old
slot, and `dst` grew from an empty array.
scr_arr_sort_values runs the IR helper's exact algorithm (same comparator
call order) over borrowed slot copies of the private, compacted snapshot:
- comparator calls use the callValue ABI (owned element arguments, an
undefined `this` window, pending-exception check);
- the array keeps owning every element and is untouched while user code
runs, so the cycle collector and a throwing comparator see the original
snapshot; the sorted permutation is published only after success;
- f64 and reference-counted element types qualify (isSortValuesElement);
unions with an undefined arm and checked/island values keep the IR.
The new internal arrIntrinsic `sortValues` is validated, may throw, and
is not reference-preserving.
The records-sort comparator spent ~70% of its samples allocating and
freeing union boxes: `for (const key of keys)` binds `key` as
`string | undefined` (array holes), and every `key === "department"`
heap-wrapped the literal as well.
- call-lifetimes: strict union equality borrows a local operand, like
unionIsTag/unionNarrow; closure bodies get local facts (their captured
cells are boxed and already rejected), parameter facts stay limited to
environment-free synchronous bodies.
- unionEq emission: a freshly wrapped operand gets a stack box.
The serialized-IR emission test compared a non-sanitized compile, which
now passes objectAudit: false, against direct emission with the default
objectAudit: true. The extra scr_obj_alloc_note/scr_obj_free_note calls
were an option mismatch, not an IR round-trip loss. Emit from the artifact
with the option compile derives from --sanitize, and check both lanes.
scr_obj_alloc_note/scr_obj_free_note exist for the SCR_RC_AUDIT live-object
audit and are empty in release and dev runtime packs, yet every emitted
record/class new and free helper called them. The LLVM emitter takes an
objectAudit option (default on for direct emission); the production
executable and library pipelines pass it only for --sanitize builds. Runtime
TUs compile their own call sites away outside SCR_RC_AUDIT while scr_object.c
keeps the no-op symbols for objects that still reference them.
% now checks at run time whether both operands are integers (dividend
|x| <= 2^53, nonzero integer divisor) when the integer-range analysis
cannot prove it, and then uses i64 srem with JS sign-of-zero semantics;
fractions, NaN, Infinity, zero divisors and huge dividends keep frem.
Proven integers whose divisor may be zero now only check for zero.
push() appends inline while len < cap (the runtime append is exactly a
dense store at len plus len+1 there) and keeps a cold runtime call that
grows storage otherwise. Element writes were already inlined by H04.
Built on the H04 commits cherry-picked from perf/h04-array-reads
(d88b58a1, a6057a52, 9109cb5a, 657aa3fb). New corpus programs
3150-integer-remainder and 3151-array-push-writes.
Marginal vs perf/h04-array-reads, 15 runs:
| workload | macOS | Linux (focused) |
| numeric-kernels | -18.3% | -10.3% |
| functional-pipeline | -8.8% | -4.3% |
| template-render | -2.9% | (layout, sweep -0.6%) |
| alloc-trees | -2.0% | (layout, sweep +0.3%) |
| records-sort | -1.5% | -0.3% |
| csv-numbers | -0.3% | +0.1% |
geomean marginal: macOS -2.8%, Linux full -0.6%.
vs perf/harness (incl. H04): macOS -14.4% (1.222x Node),
Linux -16.0% (1.160x Node). Linux .text growth <= 3.6%.
Tests: LLVM differential corpus 2008/2008 (Linux, 6 shards, release+dev),
sanitized 3140/3150/3151 pass, backend+ir unit tests pass except one
load-flaky zig COFF cache test that passes in isolation.
The self-hosted layout stage (tests/harness/self-hosting-emission) compiles
cycle-analysis.ts with scriptc itself. The Tarjan work stack held live
Iterator objects and the constructor-escape check read `captures` through
an untyped cast; neither compiles natively. The work frames now walk a
snapshot of each node's edges by index, and the escape check reads
`captures` from the two expression kinds that carry it (closure and
classRef). Behavior is unchanged.
A reference edge that can only be stored while its owner is still under
construction points to an object that existed before the owner, so a heap
cycle made only of such edges is impossible. computeTraced now builds the
shape/union graph with per-edge mutability, finds strongly connected
components, and marks a component cycle-capable only if it holds an
intrinsic reference (closure, dyn, class value, caught, promise) or a
mutable internal edge; units that reach such a component stay traced. With
every edge mutable this is exactly the previous fixpoint.
Mutability comes from the final IR (cycle-mutability.ts), not from the TS
readonly modifier: every fieldSet outside a constructor's own this,
fieldIncDec, recordSet, recordKeySet and recordKeyDelete counts; a
constructor where this escapes (anything but a field store target, a field
read, or the receiver of the direct base constructor call, including
closure/class captures) makes its hierarchy mutable, as does any other call
of a constructor function; every type that can cross into checked-dynamic
code (dynFrom operands including boxed closure signatures, thrown values,
library/intrinsic/JSON/FFI arguments) is mutable with its whole type
closure, because typed-ref capsules commit dynamic writes into native
fields; runtime-rooted hierarchies stay mutable; library builds and
dynamic-island programs disable the refinement. Union arms are immutable
(boxes are), collection edges are always mutable.
New corpus programs pin the acyclic case (DAG sharing, a 200k-node chain,
derived constructors, records) and try to defeat the proof (constructor
escapes, readonly bypass through casts/mapped types/any/Reflect/aliases,
subclass rewrites, readonly arrays, untyped writes through capsules).
`mentionedBy.get(...) ?? []` mixes a Set<string> with an empty array
literal. scriptc compiles its own compiler, and that union has no static
representation, so the bootstrap seed build failed with SC2011 on
emitter.ts. Skip a callee without mentioners explicitly instead.
Verified with scripts/build-native-cli.mts, the build the bootstrap seed
job runs: it fails with the CI's SC2011 before this change and produces
the native CLI after it.
Upstream native workers (095b6193) start each worker thread with a NULL
scr_als_active (SCR_ALS_SLOT() supplies the main slot) and give the fiber
epilogue its own context-termination path. The fiberless frame now goes
through SCR_ALS_SLOT(), and worker programs keep the fiber path, so
termination and AsyncLocalStorage behave exactly as upstream defines them.
Ordinary executables are unchanged.
Linkers lay out code in input order, and executables linked the program
object first, so any change in program size shifted every runtime
function. The vendored archives build at -Os, which drops function
alignment, so the regex interpreter (lre_exec) landed at a different
offset within its cache line after every unrelated edit and swung
template-render by up to 17% and regex-logs by up to 8% on x86-64.
Executable inputs are now runtime objects, runtime archives, the
program object, its partitions, then FFI libraries. Generated code only
references runtime-object symbols, so single-pass GNU ld still resolves
every archive member; when FFI libraries are present, non-Darwin links
list the runtime archives again after them. The native-link-info input
order follows the same plan.
Vendored archives build with -falign-functions=64 on native targets.
On x86-64 the release runtime units do too: generated loops that call
runtime helpers otherwise swing by up to 13% with the program's
position relative to 16-byte-aligned helpers (numeric-kernels). arm64
keeps its runtime units unaligned, where the size cost is higher and
the effect was not measured.
A no-op 32-byte growth of the program object moved the baseline by
+10.8% (template-render, CI +9.3..+12.9%) and is neutral with this
change on every measured workload (Linux, 15 runs).
libregexp compiles every non-sticky pattern with a `.*?` search prefix and
interprets its bytecode one opcode at a time, so an unanchored search pays a
backtrack push/pop and ~7 dispatches per subject position, and each `x+`
iteration pushes a backtrack state. Profiles of regex-logs and
template-render showed 65-85% of samples inside lre_exec.
scr_regex_native.h translates the compiled bytecode body (the bytecode stays
the source of truth for parsing, flags, case folding and capture numbering)
into a small program for one-byte subjects:
- single-character opcodes become 128-entry tables computed by evaluating the
interpreter's own predicate (lre_canonicalize, lre_is_space, range pairs)
for each ASCII code unit, so /i and /u are exact on these subjects;
- quantifiers over one character become counted loops that backtrack by
count; greedy loops whose continuation cannot start with a byte of the
loop's class (or is just saves + match) are possessive;
- runs of literal bytes become one memcmp;
- splits, gotos, saves, capture resets, counted group loops and empty-check
registers keep libregexp's exact backtracking order and undo semantics;
- unanchored searches start only at bytes that can begin a match (memchr for
a single byte) and only at 0 for non-multiline `^` patterns.
Lookaround and back references, and all non-ASCII subjects, keep lre_exec.
scr_exec is the single dispatch point, so every match loop is shared. The
program is built with the bytecode and cached on ScrRegex (new `native` slot;
the emitter's %ScrRegex type and literal initializer gain one null pointer).
Tests: packages/runtime/test/test_regex_native.c fuzzes the matcher against
lre_exec (random patterns over the subset and its bail-outs, every start
index, all capture slots; ASan+UBSan), wired into regex.test.ts; a sweep of
8 seeds x 100k patterns (~575k translated, ~70.7M checks) found no mismatch.
tests/corpus/regex-native-matcher.ts pins each construct through the public
APIs on ASCII subjects and non-ASCII twins.
Squashes 1d210a03: build the fuzz test with -D_GNU_SOURCE on Linux; the
vendored cutils.h needs CLOCK_MONOTONIC, which strict -std=c11 hides on glibc.
Malte Ubl