| 1234567891011121314151617181920212223242526272829303132333435363738394041424344454647484950515253545556575859606162636465666768697071727374757677787980818283848586878889909192939495969798991001011021031041051061071081091101111121131141151161171181191201211221231241251261271281291301311321331341351361371381391401411421431441451461471481491501511521531541551561571581591601611621631641651661671681691701711721731741751761771781791801811821831841851861871881891901911921931941951961971981992002012022032042052062072082092102112122132142152162172182192202212222232242252262272282292302312322332342352362372382392402412422432442452462472482492502512522532542552562572582592602612622632642652662672682692702712722732742752762772782792802812822832842852862872882892902912922932942952962972982993003013023033043053063073083093103113123133143153163173183193203213223233243253263273283293303313323333343353363373383393403413423433443453463473483493503513523533543553563573583593603613623633643653663673683693703713723733743753763773783793803813823833843853863873883893903913923933943953963973983994004014024034044054064074084094104114124134144154164174184194204214224234244254264274284294304314324334344354364374384394404414424434444454464474484494504514524534544554564574584594604614624634644654664674684694704714724734744754764774784794804814824834844854864874884894904914924934944954964974984995005015025035045055065075085095105115125135145155165175185195205215225235245255265275285295305315325335345355365375385395405415425435445455465475485495505515525535545555565575585595605615625635645655665675685695705715725735745755765775785795805815825835845855865875885895905915925935945955965975985996006016026036046056066076086096106116126136146156166176186196206216226236246256266276286296306316326336346356366376386396406416426436446456466476486496506516526536546556566576586596606616626636646656666676686696706716726736746756766776786796806816826836846856866876886896906916926936946956966976986997007017027037047057067077087097107117127137147157167177187197207217227237247257267277287297307317327337347357367377387397407417427437447457467477487497507517527537547557567577587597607617627637647657667677687697707717727737747757767777787797807817827837847857867877887897907917927937947957967977987998008018028038048058068078088098108118128138148158168178188198208218228238248258268278288298308318328338348358368378388398408418428438448458468478488498508518528538548558568578588598608618628638648658668678688698708718728738748758768778788798808818828838848858868878888898908918928938948958968978988999009019029039049059069079089099109119129139149159169179189199209219229239249259269279289299309319329339349359369379389399409419429439449459469479489499509519529539549559569579589599609619629639649659669679689699709719729739749759769779789799809819829839849859869879889899909919929939949959969979989991000100110021003100410051006100710081009101010111012101310141015101610171018101910201021102210231024102510261027102810291030103110321033103410351036103710381039104010411042104310441045104610471048104910501051105210531054105510561057105810591060106110621063106410651066106710681069107010711072107310741075107610771078107910801081108210831084108510861087108810891090109110921093109410951096109710981099110011011102110311041105110611071108110911101111111211131114111511161117111811191120112111221123112411251126112711281129113011311132113311341135113611371138113911401141114211431144114511461147114811491150115111521153115411551156115711581159116011611162116311641165116611671168116911701171117211731174117511761177117811791180118111821183118411851186118711881189119011911192119311941195119611971198119912001201120212031204120512061207120812091210121112121213121412151216121712181219122012211222122312241225122612271228122912301231123212331234123512361237123812391240124112421243124412451246124712481249125012511252125312541255125612571258125912601261126212631264126512661267126812691270127112721273127412751276127712781279128012811282128312841285128612871288128912901291129212931294129512961297129812991300130113021303130413051306130713081309131013111312131313141315131613171318131913201321132213231324132513261327132813291330133113321333133413351336133713381339134013411342134313441345134613471348134913501351135213531354135513561357135813591360136113621363136413651366136713681369137013711372137313741375137613771378137913801381138213831384138513861387138813891390139113921393139413951396139713981399140014011402140314041405140614071408140914101411141214131414141514161417141814191420142114221423142414251426142714281429143014311432143314341435143614371438143914401441144214431444144514461447144814491450145114521453145414551456145714581459146014611462146314641465146614671468146914701471147214731474147514761477147814791480148114821483148414851486148714881489149014911492149314941495149614971498149915001501150215031504150515061507150815091510151115121513151415151516151715181519152015211522152315241525152615271528152915301531153215331534153515361537153815391540154115421543154415451546154715481549155015511552155315541555155615571558155915601561156215631564156515661567156815691570157115721573157415751576157715781579158015811582158315841585158615871588158915901591159215931594159515961597159815991600160116021603160416051606160716081609161016111612161316141615161616171618161916201621162216231624162516261627162816291630163116321633163416351636163716381639164016411642164316441645164616471648164916501651165216531654165516561657165816591660166116621663166416651666166716681669167016711672167316741675167616771678167916801681168216831684168516861687168816891690169116921693169416951696169716981699170017011702170317041705170617071708170917101711171217131714171517161717171817191720172117221723172417251726172717281729173017311732173317341735173617371738173917401741174217431744174517461747174817491750175117521753175417551756175717581759176017611762176317641765176617671768176917701771177217731774177517761777177817791780178117821783178417851786178717881789179017911792179317941795179617971798179918001801180218031804180518061807180818091810181118121813181418151816181718181819182018211822182318241825182618271828182918301831183218331834183518361837183818391840184118421843184418451846184718481849185018511852185318541855185618571858185918601861186218631864186518661867186818691870187118721873187418751876187718781879188018811882188318841885188618871888188918901891189218931894189518961897189818991900190119021903190419051906190719081909191019111912191319141915191619171918191919201921192219231924192519261927192819291930193119321933193419351936193719381939194019411942194319441945194619471948194919501951195219531954195519561957195819591960196119621963196419651966196719681969197019711972197319741975197619771978197919801981198219831984198519861987198819891990199119921993199419951996199719981999200020012002200320042005200620072008200920102011201220132014201520162017201820192020202120222023202420252026202720282029203020312032203320342035203620372038203920402041204220432044204520462047204820492050205120522053205420552056205720582059206020612062206320642065206620672068206920702071207220732074207520762077207820792080208120822083208420852086208720882089209020912092209320942095209620972098209921002101210221032104210521062107210821092110211121122113211421152116211721182119212021212122212321242125212621272128212921302131213221332134213521362137213821392140214121422143214421452146214721482149215021512152215321542155215621572158215921602161216221632164216521662167216821692170217121722173217421752176217721782179218021812182218321842185218621872188218921902191219221932194219521962197219821992200220122022203220422052206220722082209221022112212221322142215221622172218221922202221222222232224222522262227222822292230223122322233223422352236223722382239224022412242224322442245224622472248224922502251225222532254225522562257225822592260226122622263226422652266226722682269227022712272227322742275227622772278227922802281228222832284228522862287228822892290229122922293229422952296229722982299230023012302230323042305230623072308230923102311231223132314231523162317231823192320232123222323232423252326232723282329233023312332233323342335233623372338233923402341234223432344234523462347234823492350235123522353235423552356235723582359236023612362236323642365236623672368236923702371237223732374237523762377237823792380238123822383238423852386238723882389239023912392239323942395239623972398239924002401240224032404240524062407240824092410241124122413241424152416241724182419242024212422242324242425242624272428242924302431243224332434243524362437243824392440244124422443244424452446244724482449245024512452245324542455245624572458245924602461246224632464246524662467246824692470247124722473247424752476247724782479248024812482248324842485248624872488248924902491249224932494249524962497249824992500250125022503250425052506250725082509251025112512251325142515251625172518251925202521252225232524252525262527252825292530253125322533253425352536253725382539254025412542254325442545254625472548254925502551255225532554255525562557255825592560256125622563256425652566256725682569257025712572257325742575257625772578257925802581258225832584258525862587258825892590259125922593259425952596259725982599260026012602260326042605260626072608260926102611261226132614261526162617261826192620262126222623262426252626262726282629263026312632263326342635263626372638263926402641264226432644264526462647264826492650265126522653265426552656265726582659266026612662266326642665266626672668266926702671267226732674267526762677267826792680268126822683268426852686268726882689269026912692269326942695269626972698269927002701270227032704270527062707270827092710271127122713271427152716271727182719272027212722272327242725272627272728272927302731273227332734273527362737273827392740274127422743274427452746274727482749275027512752275327542755275627572758275927602761276227632764276527662767276827692770277127722773277427752776277727782779278027812782278327842785278627872788278927902791279227932794279527962797279827992800280128022803280428052806280728082809281028112812281328142815281628172818281928202821282228232824282528262827282828292830283128322833283428352836283728382839284028412842284328442845284628472848284928502851285228532854285528562857285828592860286128622863286428652866286728682869287028712872287328742875287628772878287928802881288228832884288528862887288828892890289128922893289428952896289728982899290029012902290329042905290629072908290929102911291229132914291529162917291829192920292129222923292429252926292729282929293029312932293329342935293629372938293929402941294229432944294529462947294829492950295129522953295429552956295729582959296029612962296329642965296629672968296929702971297229732974297529762977297829792980298129822983298429852986298729882989299029912992299329942995299629972998299930003001300230033004300530063007300830093010301130123013301430153016301730183019302030213022302330243025302630273028302930303031303230333034303530363037303830393040304130423043304430453046304730483049305030513052305330543055305630573058305930603061306230633064306530663067306830693070307130723073307430753076307730783079308030813082308330843085308630873088308930903091309230933094309530963097309830993100310131023103310431053106310731083109311031113112311331143115311631173118311931203121312231233124312531263127312831293130313131323133313431353136313731383139314031413142314331443145314631473148314931503151315231533154315531563157315831593160316131623163316431653166316731683169317031713172317331743175317631773178317931803181318231833184318531863187318831893190319131923193319431953196319731983199320032013202320332043205320632073208320932103211321232133214321532163217321832193220322132223223322432253226322732283229323032313232323332343235323632373238323932403241324232433244324532463247324832493250325132523253325432553256325732583259326032613262326332643265326632673268326932703271327232733274327532763277327832793280328132823283328432853286328732883289329032913292329332943295329632973298329933003301330233033304330533063307330833093310331133123313331433153316331733183319332033213322332333243325332633273328332933303331333233333334333533363337333833393340334133423343334433453346334733483349335033513352335333543355335633573358335933603361336233633364336533663367336833693370337133723373337433753376337733783379338033813382338333843385338633873388338933903391339233933394339533963397339833993400340134023403340434053406340734083409341034113412341334143415341634173418341934203421342234233424342534263427342834293430343134323433343434353436343734383439344034413442344334443445344634473448344934503451345234533454345534563457345834593460346134623463346434653466346734683469347034713472347334743475347634773478347934803481348234833484348534863487348834893490349134923493349434953496349734983499350035013502350335043505350635073508350935103511351235133514351535163517351835193520352135223523352435253526352735283529353035313532353335343535353635373538353935403541354235433544354535463547354835493550355135523553355435553556355735583559356035613562356335643565356635673568356935703571357235733574357535763577357835793580358135823583358435853586358735883589359035913592359335943595359635973598359936003601360236033604360536063607360836093610361136123613361436153616361736183619362036213622362336243625362636273628362936303631363236333634363536363637363836393640364136423643364436453646364736483649365036513652365336543655365636573658365936603661366236633664366536663667366836693670367136723673367436753676367736783679368036813682368336843685368636873688368936903691369236933694369536963697369836993700370137023703370437053706370737083709371037113712371337143715371637173718371937203721372237233724372537263727372837293730373137323733373437353736373737383739374037413742374337443745374637473748374937503751375237533754375537563757375837593760376137623763376437653766376737683769377037713772377337743775377637773778377937803781378237833784378537863787378837893790379137923793379437953796379737983799380038013802380338043805380638073808380938103811381238133814381538163817381838193820382138223823382438253826382738283829383038313832383338343835383638373838383938403841384238433844384538463847384838493850385138523853385438553856385738583859386038613862386338643865386638673868386938703871387238733874387538763877387838793880388138823883388438853886388738883889389038913892389338943895389638973898389939003901390239033904390539063907390839093910391139123913391439153916391739183919392039213922392339243925392639273928392939303931393239333934393539363937393839393940394139423943394439453946394739483949395039513952395339543955395639573958395939603961396239633964396539663967396839693970397139723973397439753976397739783979398039813982398339843985398639873988398939903991399239933994399539963997399839994000400140024003400440054006400740084009401040114012401340144015401640174018401940204021402240234024402540264027402840294030403140324033403440354036403740384039404040414042404340444045404640474048404940504051405240534054405540564057405840594060406140624063406440654066406740684069407040714072407340744075407640774078407940804081408240834084408540864087408840894090409140924093409440954096409740984099410041014102410341044105410641074108410941104111411241134114411541164117411841194120412141224123412441254126412741284129413041314132413341344135413641374138413941404141414241434144414541464147414841494150415141524153415441554156415741584159416041614162416341644165416641674168416941704171417241734174417541764177417841794180418141824183418441854186418741884189419041914192419341944195419641974198419942004201420242034204420542064207420842094210421142124213421442154216421742184219422042214222422342244225422642274228 |
- import { existsSync, readdirSync, realpathSync, statSync } from 'node:fs'
- import { mkdtemp, writeFile } from 'node:fs/promises'
- import { tmpdir } from 'node:os'
- import { basename, dirname, join } from 'node:path'
- import { describe, expect, it, vi } from 'vitest'
- import { Context } from 'cordis'
- import { PythonCodeRuntime } from '../src/index.ts'
- import { logTruncationMarker } from '../src/protocol.ts'
- import type { Config } from '../src/index.ts'
- import type { CodeBindingFunction, CodeJsonValue, CodeRunResult } from '@deepseek-ai/dsh-code-runtime'
- /**
- * Names one `py/` script whose `copyFileSync` must fail, for the partial-staging
- * case. A real disk-full or missing-asset failure mid-copy cannot be produced
- * from a test, and the leak only shows when `mkdtempSync` has already succeeded.
- */
- const { failNextCopyOf } = vi.hoisted(() => ({ failNextCopyOf: { value: undefined as string | undefined } }))
- vi.mock('node:fs', async (importOriginal) => {
- const actual = await importOriginal<typeof import('node:fs')>()
- return {
- ...actual,
- copyFileSync(source: string, destination: string): void {
- if (failNextCopyOf.value !== undefined && basename(source) === failNextCopyOf.value) {
- failNextCopyOf.value = undefined
- throw Object.assign(new Error('simulated ENOSPC on copy'), { code: 'ENOSPC' })
- }
- actual.copyFileSync(source, destination)
- },
- }
- })
- /**
- * Integration suite over REAL python3 subprocesses (no subprocess mocks — it is
- * cheap and local, per docs/testing.md's real-over-mock policy; the only mock is
- * `node:fs.copyFileSync` for the staging-failure cases). Each test builds a fresh
- * runtime so budgets can be tuned per case.
- */
- async function setup(config: Config = {}) {
- const ctx = new Context()
- const fiber = await ctx.plugin(PythonCodeRuntime, config)
- const runtime = ctx.codeRuntime as PythonCodeRuntime
- return { ctx, fiber, runtime }
- }
- /** Convenience: one namespace `tools` with the given functions. */
- function tools(functions: Record<string, CodeBindingFunction>) {
- return [{ global: 'tools', functions }]
- }
- describe('PythonCodeRuntime — seam descriptors and misuse', () => {
- it('registers the seam descriptors', async () => {
- const { runtime } = await setup()
- expect(runtime.language).toBe('python')
- expect(runtime.isolation).toBe('process')
- })
- it('rejects non-positive config as seam misuse', async () => {
- const ctx = new Context()
- await expect(ctx.plugin(PythonCodeRuntime, { cpuSeconds: 0 }))
- .rejects.toThrow(/cpuSeconds must be a positive number/)
- await expect(ctx.plugin(PythonCodeRuntime, { maxWallMs: -1 }))
- .rejects.toThrow(/maxWallMs must be a positive number/)
- })
- it('rejects a non-integer cpuSeconds at load (setrlimit needs an int)', async () => {
- const ctx = new Context()
- await expect(ctx.plugin(PythonCodeRuntime, { cpuSeconds: 1.5 }))
- .rejects.toThrow(/cpuSeconds must be a positive integer, got 1.5/)
- })
- it('rejects a non-integer byte budget at load (the child int()-truncates it)', async () => {
- // maxLogBytes/maxValueBytes cross to the child, which reads them through
- // int(...): a float would floor there while the host meters the fraction, so
- // the two sides would enforce different public config. Reject at load.
- const ctxLog = new Context()
- await expect(ctxLog.plugin(PythonCodeRuntime, { maxLogBytes: 3.5 }))
- .rejects.toThrow(/maxLogBytes must be a positive integer/)
- const ctxValue = new Context()
- await expect(ctxValue.plugin(PythonCodeRuntime, { maxValueBytes: 1024.5 }))
- .rejects.toThrow(/maxValueBytes must be a positive integer/)
- })
- it('rejects finite numeric config that cannot cross as an exact rlimit integer', async () => {
- // `Number.isFinite` and `Number.isInteger` both admit values that cannot
- // round-trip. `addressSpaceMb: 1e308` overflows to `Infinity` once multiplied
- // by 1 MiB, and `encodeJsonPlain` renders that as `null`, so the child gets no
- // limit at all; `cpuSeconds: 1e100` clears `Number.isInteger` while sitting
- // far past the safe range, so `setrlimit` receives a different number than was
- // configured. Both used to end every run in a bootstrap exception instead of
- // failing at load, where a self-contained configuration error belongs.
- const ctx = new Context()
- await expect(ctx.plugin(PythonCodeRuntime, { addressSpaceMb: 1e308 }))
- .rejects.toThrow(/addressSpaceMb must be at most \d+ .*exact integer/)
- await expect(ctx.plugin(PythonCodeRuntime, { cpuSeconds: 1e100 }))
- .rejects.toThrow(/cpuSeconds must be at most \d+ .*exact integers/)
- // The boundary values still load: the bound rejects what cannot be encoded,
- // not everything large.
- const okMb = await ctx.plugin(PythonCodeRuntime, { addressSpaceMb: Math.floor(Number.MAX_SAFE_INTEGER / (1024 * 1024)) })
- await okMb.dispose()
- const okCpu = await ctx.plugin(PythonCodeRuntime, { cpuSeconds: Number.MAX_SAFE_INTEGER - 1 })
- await okCpu.dispose()
- })
- it('rejects an output cap whose payload could not cross the frame ceiling', async () => {
- // The caps budget a payload that must arrive inside ONE fd-3 frame, and the
- // 256 MiB framing ceiling is fixed. A larger cap is unsatisfiable rather
- // than generous: a completion the cap admits arrives as an over-ceiling
- // frame and fails the run as `worker-exit`, inverting the `output-limit`
- // the cap describes. Both budgets are metered in already-escaped serialized
- // bytes, so a payload occupies at most `cap + envelope` on the wire; the
- // bound is `ceiling - envelope`, not `(ceiling - envelope) / 6` (that
- // divided in escape expansion the charge already counts).
- const admissible = 256 * 1024 * 1024 - 64
- const ctx = new Context()
- await expect(ctx.plugin(PythonCodeRuntime, { maxLogBytes: admissible + 1 }))
- .rejects.toThrow(/maxLogBytes must not exceed 268435392 .*fd-3 frame ceiling/)
- await expect(ctx.plugin(PythonCodeRuntime, { maxValueBytes: admissible + 1 }))
- .rejects.toThrow(/maxValueBytes must not exceed 268435392 .*fd-3 frame ceiling/)
- // The boundary value itself loads: the bound is the largest cap a frame can
- // still carry, not one below it. It needs an address space large enough to
- // clear the separate maxValueBytes/addressSpaceMb worst-case gate (the cap
- // times the 12x Unicode expansion must fit), so this pairs it with a 4 GiB
- // addressSpaceMb — the two load-time bounds are independent.
- const boundary = await ctx.plugin(PythonCodeRuntime, { maxValueBytes: admissible, addressSpaceMb: 4096 })
- await boundary.dispose()
- })
- it('rejects a pythonBin that spawn() would throw on, at load', async () => {
- // Both values pass the string schema and both make `spawn` throw
- // SYNCHRONOUSLY from inside run() — ERR_INVALID_ARG_VALUE for the empty
- // path, ERR_INVALID_ARG_TYPE for the NUL — so run() would REJECT instead of
- // resolving the worker-exit the seam promises for a child that cannot
- // start. Both are self-contained configuration errors, so they fail here.
- const ctx = new Context()
- await expect(ctx.plugin(PythonCodeRuntime, { pythonBin: '' }))
- .rejects.toThrow(/pythonBin must be a non-empty path without NUL bytes/)
- await expect(ctx.plugin(PythonCodeRuntime, { pythonBin: 'py\u0000thon3' }))
- .rejects.toThrow(/pythonBin must be a non-empty path without NUL bytes/)
- })
- it('rejects a timer budget setTimeout would silently clamp to 1 ms', async () => {
- // Node stores a setTimeout delay as a signed 32-bit value and substitutes
- // 1 ms for anything larger, inverting the knob's meaning: a huge maxWallMs
- // would time every run out at once, and a huge graceMs would SIGKILL one
- // millisecond after SIGTERM. Both must fail at load instead.
- const ctx = new Context()
- await expect(ctx.plugin(PythonCodeRuntime, { maxWallMs: 2_147_483_648 }))
- .rejects.toThrow(/maxWallMs must not exceed 2147483647/)
- // graceMs is bounded by the close deadline's added margin, not by the raw
- // timer maximum, because that sum is what gets armed.
- await expect(ctx.plugin(PythonCodeRuntime, { graceMs: 2_147_481_648 }))
- .rejects.toThrow(/graceMs must not exceed 2147481647/)
- // The exact maxima still load.
- await expect(ctx.plugin(PythonCodeRuntime, { maxWallMs: 2_147_483_647, graceMs: 2_147_481_647 }))
- .resolves.toBeDefined()
- })
- it('rejects loading this Unix-only backend on Windows', async () => {
- // The bootstrap needs the POSIX `resource` module, a positional fd 3, and
- // negative-PID process-group signals — none on Windows. The constructor
- // must throw at load rather than register ctx.codeRuntime and defer the
- // failure to the first run.
- const original = process.platform
- Object.defineProperty(process, 'platform', { value: 'win32', configurable: true })
- try {
- const ctx = new Context()
- await expect(ctx.plugin(PythonCodeRuntime, {})).rejects.toThrow(/requires a Unix platform/)
- } finally {
- Object.defineProperty(process, 'platform', { value: original, configurable: true })
- }
- })
- it('rejects a binding global that is not a Python identifier or is reserved', async () => {
- const { runtime } = await setup()
- await expect(runtime.run({
- program: 'return 1',
- bindings: [{ global: '1bad', functions: {} }],
- })).rejects.toThrow(/is not a usable Python identifier/)
- await expect(runtime.run({
- program: 'return 1',
- bindings: [{ global: 'class', functions: {} }],
- })).rejects.toThrow(/is not a usable Python identifier/)
- })
- it('rejects duplicate binding namespaces', async () => {
- const { runtime } = await setup()
- await expect(runtime.run({
- program: 'return 1',
- bindings: [
- { global: 'tools', functions: {} },
- { global: 'tools', functions: {} },
- ],
- })).rejects.toThrow(/duplicate binding global/)
- })
- it('rejects run() after disposal, and unregisters ctx.codeRuntime', async () => {
- const { ctx, fiber, runtime } = await setup()
- await fiber.dispose()
- await expect(runtime.run({ program: 'return 1', bindings: [] }))
- .rejects.toThrow(/after disposal/)
- expect(ctx.get('codeRuntime')).toBeUndefined()
- })
- it('short-circuits when the request signal is already aborted', async () => {
- const { runtime } = await setup()
- const signal = AbortSignal.abort('already-cancelled')
- const result = await runtime.run({ program: 'return 1', bindings: [], signal })
- expect(result.error?.kind).toBe('abort')
- expect(result.error?.message).toContain('already-cancelled')
- expect(result.logs).toEqual([])
- })
- it('short-circuits on an already-aborted signal whose reason cannot be converted', async () => {
- // The pre-flight arm converted the reason with a bare `String()`, so a
- // hostile reason threw out of `run()` — the seam promises to reject only for
- // misuse, and a caller's cancellation token is not misuse.
- const { runtime } = await setup()
- const signal = AbortSignal.abort({
- [Symbol.toPrimitive]() { throw new Error('reason blew up') },
- })
- const result = await runtime.run({ program: 'return 1', bindings: [], signal })
- expect(result.error?.kind).toBe('abort')
- expect(result.error?.message).toBe('<unrenderable rejection value>')
- expect(result.logs).toEqual([])
- })
- it('runs the interpreter from materialized scripts outside the package, and removes them per run', async () => {
- // The interpreter is an EXTERNAL process, so it can only open paths the OS
- // resolves. Inside the single-file Python-SDK executable the packaged `py/`
- // directory lives in pkg's virtual filesystem, which Node reads through its
- // patched `fs` but `python3` cannot see, so spawning from that path fails
- // with ENOENT. The scripts are therefore copied to a real directory first.
- //
- // The path is read from the child's own `__main__` module, so it proves
- // where the interpreter actually loaded the entry script — asserting on a
- // host-side constant would only restate the source. The program namespace
- // seeds `__name__` but no `__file__`, hence the module lookup.
- // `protocol.py` must land in the SAME directory, since `bootstrap.py` puts
- // its own directory on `sys.path` to import it; the run completing at all
- // already exercises that import.
- const { runtime } = await setup()
- const entryOf = async (): Promise<string> => {
- const result = await runtime.run({ program: 'import sys\nreturn sys.modules["__main__"].__file__', bindings: [] })
- expect(result.error).toBeUndefined()
- return result.value as string
- }
- const entry = await entryOf()
- expect(entry.endsWith('/bootstrap.py')).toBe(true)
- const dir = dirname(entry)
- expect(dir.startsWith(realpathSync(tmpdir()))).toBe(true)
- expect(dir).not.toContain('/packages/')
- // Staging is per RUN and removed at settlement, so by the time `run()`
- // resolved the directory is already gone — nothing survives to be rewritten
- // by a later run. `protocol.py` had to be beside the entry script for the run
- // to complete at all, since `bootstrap.py` imports it off `sys.path`.
- expect(existsSync(dir)).toBe(false)
- // A second run stages its own copy rather than reusing the first.
- expect(dirname(await entryOf())).not.toBe(dir)
- })
- it('contains a program that rewrites its own bootstrap to the run that did it', async () => {
- // The child runs as the same UID as the host, so `0o700` does not stop model
- // code from rewriting the scripts it was started from —
- // `sys.modules['__main__'].__file__` names them. While all runs shared one
- // staged copy, a program that overwrote `bootstrap.py` broke the NEXT run
- // (measured: it settled as `worker-exit`), and substituted code would have
- // run before the resource limits were applied.
- const { runtime } = await setup({ maxWallMs: 10_000 })
- const sabotage = await runtime.run({
- program: [
- 'import sys',
- 'path = sys.modules["__main__"].__file__',
- 'open(path, "w").write("raise SystemExit(1)\\n")',
- 'return path',
- ].join('\n'),
- bindings: [],
- })
- expect(sabotage.error).toBeUndefined()
- // The damage stayed inside the run that caused it.
- const after = await runtime.run({ program: 'return 1 + 1', bindings: [] })
- expect(after.error).toBeUndefined()
- expect(after.value).toBe(2)
- }, 20_000)
- it('leaves no subprocess or scripts behind when disposal races the first run', async () => {
- // Staging runs SYNCHRONOUSLY so no async boundary opens between `run()` and
- // the point where `execute` registers the run in `live` and installs the
- // abort listener. With an `await` there, a disposal landing in that window
- // saw an empty `live`, returned, removed the script directory, and let the
- // continuation spawn a subprocess after the fiber was gone.
- //
- // `dispose()` is called in the same synchronous turn as `run()`, with no
- // `await` between them, so it lands exactly in that window.
- //
- // The leak assertion compares before and after rather than requiring an
- // empty tmpdir: other tests in this file build runtimes they never dispose,
- // so only the directories this test adds are its own evidence.
- const staged = (): string[] =>
- readdirSync(realpathSync(tmpdir())).filter(name => name.startsWith('dsh-code-runtime-python-'))
- const before = new Set(staged())
- const { fiber, runtime } = await setup({ maxWallMs: 8_000 })
- const pending = runtime.run({ program: 'import time\nwhile True: time.sleep(0.1)', bindings: [] })
- const disposed = fiber.dispose()
- const result = await pending
- await disposed
- // Whatever the run reports, it must be terminal and must not be a success.
- expect(result.value).toBeUndefined()
- expect(['abort', 'worker-exit', 'timeout']).toContain(result.error?.kind)
- // Disposal is to quiescence, so this run's directory is gone once it
- // resolves, and nothing recreated it afterwards.
- expect(staged().filter(name => !before.has(name))).toEqual([])
- }, 15_000)
- it('settles as abort when the signal fires in the same turn as the first run', async () => {
- // Same window, the other listener. `addEventListener('abort')` does not
- // replay an event that already fired, so an abort landing before the
- // listener was installed used to be missed entirely and the program ran to
- // success or the wall ceiling instead of resolving as `abort`. Synchronous
- // staging keeps the pre-flight check and the listener in one turn, leaving
- // no gap for the signal to slip through.
- const { runtime } = await setup({ maxWallMs: 4_000, graceMs: 200 })
- const controller = new AbortController()
- const pending = runtime.run({
- program: 'import time\nwhile True: time.sleep(0.1)',
- bindings: [],
- signal: controller.signal,
- })
- controller.abort('same-turn-abort')
- const result = await pending
- expect(result.error?.kind).toBe('abort')
- expect(result.error?.message).toContain('same-turn-abort')
- }, 15_000)
- it('reports a staging failure as worker-exit instead of rejecting run()', async () => {
- // Staging touches the filesystem, so it can fail for reasons that are not
- // the caller's doing: a full or read-only temp filesystem, or a deployment
- // that failed to ship the packaged scripts. Those are SUBSTRATE failures,
- // the same class as a child that cannot start, and the seam reserves
- // rejection for misuse — so `run()` must resolve, not throw.
- //
- // `TMPDIR` is the honest lever: `mkdtempSync` builds its path from
- // `os.tmpdir()`, so pointing it at a path that is not a directory makes the
- // real call fail without stubbing the module under test.
- const previous = process.env.TMPDIR
- const notADirectory = join(await mkdtemp(join(tmpdir(), 'dsh-staging-')), 'file')
- await writeFile(notADirectory, '')
- process.env.TMPDIR = notADirectory
- try {
- const { runtime } = await setup()
- const result = await runtime.run({ program: 'return 1', bindings: [] })
- expect(result.error?.kind).toBe('worker-exit')
- expect(result.error?.message).toContain('failed to stage the python bootstrap')
- expect(result.logs).toEqual([])
- } finally {
- if (previous === undefined) delete process.env.TMPDIR
- else process.env.TMPDIR = previous
- }
- })
- it('leaves no staging directory behind when a script copy fails', async () => {
- // `mkdtempSync` succeeding and a later `copyFileSync` failing is its own
- // case: the directory exists but is only partially populated. Recording it
- // before the copies would leak it, because `run` retries staging on the next
- // call and overwrites the single recorded path — teardown could then remove
- // only the newest attempt. Staging must clean up its own partial directory.
- //
- // Only `copyFileSync` is stubbed, and only for the second script, so
- // `mkdtempSync` really runs and the directory under assertion is real.
- const staged = (): string[] =>
- readdirSync(realpathSync(tmpdir())).filter(name => name.startsWith('dsh-code-runtime-python-'))
- const before = new Set(staged())
- failNextCopyOf.value = 'protocol.py'
- try {
- const { runtime } = await setup()
- const result = await runtime.run({ program: 'return 1', bindings: [] })
- expect(result.error?.kind).toBe('worker-exit')
- expect(result.error?.message).toContain('failed to stage the python bootstrap')
- // The partial directory is gone, so nothing accumulates across retries.
- expect(staged().filter(name => !before.has(name))).toEqual([])
- } finally {
- failNextCopyOf.value = undefined
- }
- }, 15_000)
- })
- describe('PythonCodeRuntime — inherited resource limits', () => {
- it('runs under an inherited hard limit tighter than addressSpaceMb', async () => {
- // An unprivileged process may lower a hard rlimit but never raise it. Under
- // a harness started with `ulimit -v` below `addressSpaceBytes`, requesting
- // the configured cap made `setrlimit` raise `ValueError` and every run
- // returned a bootstrap exception — even though the inherited limit is
- // STRONGER than the one asked for. The bootstrap clamps to the inherited
- // hard limit instead, so the run proceeds under the stricter bound.
- //
- // `pythonBin` is the honest lever: a wrapper that lowers RLIMIT_AS and then
- // execs the real interpreter reproduces the inherited-limit condition
- // without touching this test process's own limits.
- const dir = await mkdtemp(join(tmpdir(), 'dsh-rlimit-'))
- const wrapper = join(dir, 'python3-capped')
- // 256 MiB, half the 512 MiB addressSpaceMb default, so the requested cap is
- // unambiguously above the inherited ceiling.
- await writeFile(wrapper, '#!/bin/sh\nulimit -v 262144\nexec python3 "$@"\n', { mode: 0o755 })
- const { runtime } = await setup({ pythonBin: wrapper })
- const result = await runtime.run({
- program: 'import resource\nreturn resource.getrlimit(resource.RLIMIT_AS)[1]',
- bindings: [],
- })
- expect(result.error).toBeUndefined()
- // The applied hard limit is the inherited one, not the configured 512 MiB.
- expect(result.value).toBe(256 * 1024 * 1024)
- }, 15_000)
- it('rejects at boot when an inherited RLIMIT_AS is too tight for the output budgets', async () => {
- // The host gate validates the output budgets against the CONFIGURED
- // addressSpaceMb, but a launch environment can inherit a STRICTER RLIMIT_AS
- // (a `ulimit -v` wrapper below addressSpaceMb), which the bootstrap clamps the
- // effective limit down to — leaving the budgets sized for a ceiling the child
- // never gets, so a near-budget output would OOM mid-run as an opaque
- // worker-exit. The bootstrap re-checks both budgets against the EFFECTIVE
- // clamped limit and fails loud at boot instead. A 128 MiB inherited limit
- // leaves 64 MiB budgetable (~5 MiB admissible under the 12x multiple), under
- // which a 32 MiB maxLogBytes — admitted by the 512 MiB configured default — is
- // rejected. The rejection surfaces as an 'exception' (bootstrap's
- // setrlimit-phase failure class), not a mid-run OOM. The repro is Linux-only
- // (macOS ignores `ulimit -v`); there the run proceeds.
- const dir = await mkdtemp(join(tmpdir(), 'dsh-rlimit-'))
- const wrapper = join(dir, 'python3-tight')
- await writeFile(wrapper, '#!/bin/sh\nulimit -v 131072\nexec python3 "$@"\n', { mode: 0o755 })
- const { runtime } = await setup({ pythonBin: wrapper, maxLogBytes: 32 * 1024 * 1024, addressSpaceMb: 512 })
- const result = await runtime.run({ program: 'return 1', bindings: [] })
- if (process.platform === 'darwin') {
- expect(result.error).toBeUndefined()
- } else {
- // The re-check raises inside bootstrap's resource-limit block, which
- // reports every setrlimit-phase failure as kind 'exception'; the message
- // discriminates this config rejection from a generic setrlimit error.
- expect(result.error?.kind).toBe('exception')
- expect(result.error?.message).toContain('too large for the inherited RLIMIT_AS')
- }
- }, 15_000)
- it('applies the configured limits when nothing tighter is inherited', async () => {
- // The clamp must not weaken the normal path: with an infinite inherited hard
- // limit there is nothing to clamp against, and RLIM_INFINITY compares as -1,
- // so treating it as a numeric bound would collapse every limit to -1.
- const { runtime } = await setup({ cpuSeconds: 42, addressSpaceMb: 400 })
- const result = await runtime.run({
- // `getrlimit` returns a tuple, which the lossless-JSON completion check
- // rejects; the pair is listed explicitly rather than converted.
- program: 'import resource\ncpu = resource.getrlimit(resource.RLIMIT_CPU)\nreturn [cpu[0], cpu[1], resource.getrlimit(resource.RLIMIT_AS)[1]]',
- bindings: [],
- })
- expect(result.error).toBeUndefined()
- // Soft at cpuSeconds, hard at +1 (the SIGKILL backstop), address space at
- // the configured megabytes — exactly what the unclamped path applied.
- expect(result.value).toEqual([42, 43, 400 * 1024 * 1024])
- }, 15_000)
- it('preserves an inherited soft limit stricter than the configured cap', async () => {
- // Clamping reads BOTH inherited bounds, not just the hard one. A deployment
- // that inherited a soft rlimit below the configured cap must keep that
- // stricter soft: returning the configured value would RAISE the effective
- // soft limit, loosening containment. The wrapper lowers only the SOFT CPU
- // limit (`ulimit -S -t`) and leaves the hard limit unlimited, so the
- // requested soft (`cpuSeconds`) sits above the inherited soft — the case that
- // exposed the bug. RLIMIT_CPU is used because macOS ignores `ulimit -v`
- // (RLIMIT_AS), which is exactly why the backend skips address space there.
- const dir = await mkdtemp(join(tmpdir(), 'dsh-rlimit-soft-'))
- const wrapper = join(dir, 'python3-soft-capped')
- // Soft CPU 5 s, well below the configured 30 s, hard left unlimited.
- await writeFile(wrapper, '#!/bin/sh\nulimit -S -t 5\nexec python3 "$@"\n', { mode: 0o755 })
- const { runtime } = await setup({ pythonBin: wrapper, cpuSeconds: 30 })
- const result = await runtime.run({
- program: 'import resource\nreturn resource.getrlimit(resource.RLIMIT_CPU)[0]',
- bindings: [],
- })
- expect(result.error).toBeUndefined()
- // The applied SOFT limit is the inherited 5 s, not the configured 30 s.
- expect(result.value).toBe(5)
- }, 15_000)
- it('rechecks CPU at settlement against the effective inherited soft limit', async () => {
- // The settlement-time CPU recheck must compare against the EFFECTIVE soft
- // limit (`_clamped` may have lowered it to a stricter inherited value), not
- // the configured `cpuSeconds`. A program that traps SIGXCPU, burns past the
- // inherited soft, and returns inside the soft-to-hard gap would otherwise be
- // compared to the configured value and falsely reported successful, bypassing
- // the inherited limit. The wrapper sets a 1 s soft CPU limit; the program
- // traps SIGXCPU and busy-loops past it, then returns — the recheck must
- // re-deliver SIGXCPU so the host classifies the run as a timeout.
- const dir = await mkdtemp(join(tmpdir(), 'dsh-cpu-recheck-'))
- const wrapper = join(dir, 'python3-cpu-capped')
- await writeFile(wrapper, '#!/bin/sh\nulimit -S -t 1\nexec python3 "$@"\n', { mode: 0o755 })
- const { runtime } = await setup({ pythonBin: wrapper, cpuSeconds: 30, maxWallMs: 12_000 })
- const result = await runtime.run({
- program: [
- 'import signal, time',
- // Trap SIGXCPU so the soft limit does not terminate the program; burn
- // CPU well past the inherited 1 s soft, then return normally.
- 'signal.signal(signal.SIGXCPU, lambda *a: None)',
- 'end = time.process_time() + 2.5',
- 'while time.process_time() < end:',
- ' pass',
- 'return "returned"',
- ].join('\n'),
- bindings: [],
- })
- // The recheck compares spent CPU against the effective 1 s soft, not 30 s, so
- // the run is a timeout rather than a false success.
- expect(result.error?.kind).toBe('timeout')
- }, 20_000)
- })
- describe('PythonCodeRuntime — programs and bindings', () => {
- it('runs a top-level script, captures print output, and returns `result`', async () => {
- const { runtime } = await setup()
- const result = await runtime.run({
- program: [
- 'x = 40',
- 'y = 2',
- 'print("hello", x + y)',
- 'return {"answer": x + y}',
- ].join('\n'),
- bindings: [],
- })
- expect(result.error).toBeUndefined()
- expect(result.value).toEqual({ answer: 42 })
- // `print` in Python emits: text, ' ', text, '\n'. Concat the captured
- // fragments and assert the model-visible message survives.
- expect(result.logs.join('')).toContain('hello 42')
- // 15s: this is usually the suite's first real subprocess — a cold python3
- // start (interpreter + asyncio import) on a loaded CI runner can exceed
- // the 5s default alone; later tests reuse the warm page cache.
- }, 15_000)
- it('bridges binding calls both ways and rejects the program-side call on a host rejection', async () => {
- const { runtime } = await setup()
- const calls: unknown[] = []
- const result = await runtime.run({
- program: [
- 'first = await tools.echo({"n": 1})',
- 'caught = ""',
- 'try:',
- ' await tools.fail({})',
- 'except RuntimeError as e:',
- ' caught = str(e)',
- 'return {"first": first, "caught": caught}',
- ].join('\n'),
- bindings: tools({
- echo: async (args) => { calls.push(args); return { echoed: args as CodeJsonValue } },
- fail: async () => { throw new Error('nope') },
- }),
- })
- expect(result.error).toBeUndefined()
- expect(result.value).toEqual({ first: { echoed: { n: 1 } }, caught: 'nope' })
- expect(calls).toEqual([{ n: 1 }])
- })
- it('still answers the call when the rejection value cannot be converted to a string', async () => {
- // `messageOf` calls `String(error)`, which runs the value's own conversion,
- // and this call site is a DETACHED async reply callback. A rejection whose
- // `Symbol.toPrimitive` throws therefore escaped as an unhandled rejection:
- // the reply frame was never written, the program stayed blocked on `await`,
- // and the run degraded to a `maxWallMs` timeout (observed) — a host with no
- // `unhandledRejection` listener would exit instead. The rejection must reach
- // the program as an ordinary error carrying a fixed placeholder.
- const { runtime } = await setup({ maxWallMs: 8_000 })
- const result = await runtime.run({
- program: [
- 'try:',
- ' await tools.hostile({})',
- 'except RuntimeError as e:',
- ' return "rejected: " + str(e)',
- 'return "no rejection"',
- ].join('\n'),
- bindings: tools({
- hostile: async () => {
- throw { [Symbol.toPrimitive]() { throw new Error('toPrimitive blew up') } }
- },
- }),
- })
- expect(result.error).toBeUndefined()
- expect(result.value).toBe('rejected: <unrenderable rejection value>')
- }, 15_000)
- it('still answers the call when an Error carries a cyclic value in place of its message', async () => {
- // `Error.message` is typed `string` but is a plain writable property, so a
- // rejection can carry any value there. Returning it verbatim handed a
- // non-string to `sendReply`, breaching `encodeJsonPlain`'s JSON-plain
- // precondition: a cyclic object grew the encoder stack until the host threw
- // RangeError from the detached reply callback, so no reply frame was written
- // and the run degraded to a `maxWallMs` timeout (observed). The conversion
- // must contain it — `String()` on a cycle throws inside the guard and lands
- // on the placeholder, so the program sees an ordinary error.
- const { runtime } = await setup({ maxWallMs: 8_000 })
- const result = await runtime.run({
- program: [
- 'try:',
- ' await tools.hostile({})',
- 'except RuntimeError as e:',
- ' return "rejected: " + str(e)',
- 'return "no rejection"',
- ].join('\n'),
- bindings: tools({
- hostile: async () => {
- const cyclic: { self?: unknown; [Symbol.toPrimitive]: () => string } = {
- // A cycle alone is inert for `String()`; the throwing conversion is
- // what proves the guard runs rather than the encoder.
- [Symbol.toPrimitive]: () => { throw new Error('cyclic message') },
- }
- cyclic.self = cyclic
- const error = new Error('placeholder')
- // Writable per spec, so no cast is needed to install a non-string.
- ;(error as unknown as { message: unknown }).message = cyclic
- throw error
- },
- }),
- })
- expect(result.error).toBeUndefined()
- expect(result.value).toBe('rejected: <unrenderable rejection value>')
- }, 15_000)
- it('renders an Error whose message is a value with no JSON form', async () => {
- // The non-cyclic arm. A number would not discriminate: `scalarJson` renders
- // it as digits and the child `str()`s the field back, so it survives the
- // wire either way. `undefined` is the value that separates the two orders —
- // `scalarJson` emits a bare `undefined` token, so the reply line is not JSON
- // at all, the child's parse drops the frame, and the program stays blocked
- // on `await` until the wall ceiling (observed). Converting first sends the
- // string "undefined", which the program receives as an ordinary rejection.
- const { runtime } = await setup({ maxWallMs: 8_000 })
- const result = await runtime.run({
- program: [
- 'try:',
- ' await tools.absent({})',
- 'except RuntimeError as e:',
- ' return "rejected: " + str(e)',
- 'return "no rejection"',
- ].join('\n'),
- bindings: tools({
- absent: async () => {
- const error = new Error('placeholder')
- ;(error as unknown as { message: unknown }).message = undefined
- throw error
- },
- }),
- })
- expect(result.error).toBeUndefined()
- expect(result.value).toBe('rejected: undefined')
- }, 15_000)
- it('runs a program with no await', async () => {
- const { runtime } = await setup()
- const result = await runtime.run({
- program: 'return 2 + 2',
- bindings: [],
- })
- expect(result.error).toBeUndefined()
- expect(result.value).toBe(4)
- })
- it('returns JSON null whether the program returns None or falls off the end', async () => {
- // Python has no `undefined`: an async body that returns None and one that
- // never returns both yield None, so both complete as an exact JSON null.
- // (The worker/TS backend can tell `return undefined` from `return null`;
- // Python cannot, and reporting null for both is the honest rendering.)
- const { runtime } = await setup()
- const explicit = await runtime.run({ program: 'return None', bindings: [] })
- expect(explicit.error).toBeUndefined()
- expect(explicit.value).toBeNull()
- const noReturn = await runtime.run({ program: 'x = 1', bindings: [] })
- expect(noReturn.error).toBeUndefined()
- expect(noReturn.value).toBeNull()
- })
- it('settles with no value on a forged valueless done frame', async () => {
- // The child always sends a value now (return None → JSON null), so a done
- // frame with no value key can only be forged; the host settles it as a
- // value-less completion rather than crashing on the absent field.
- const { runtime } = await setup()
- const result = await runtime.run({
- program: [
- 'import os',
- 'os.write(3, b\'{"type":"done"}\\n\')',
- 'import time',
- 'time.sleep(5)',
- ].join('\n'),
- bindings: [],
- })
- expect(result.error).toBeUndefined()
- expect(result.value).toBeUndefined()
- })
- it('coalesces print arguments into one log line, not per-write fragments', async () => {
- // print("a","b") calls write() per arg/sep/newline; the stream must emit
- // one logical line "a b" so Code Mode's join(newline) does not insert
- // spurious blank lines. Two prints → exactly two entries, no empties.
- const { runtime } = await setup()
- const result = await runtime.run({
- program: ['print("a", "b")', 'print("c")', 'return None'].join('\n'),
- bindings: [],
- })
- expect(result.error).toBeUndefined()
- expect(result.logs).toEqual(['a b', 'c'])
- })
- it('flushes a print with no trailing newline', async () => {
- const { runtime } = await setup()
- const result = await runtime.run({
- program: ['print("partial", end="")', 'return None'].join('\n'),
- bindings: [],
- })
- expect(result.error).toBeUndefined()
- expect(result.logs).toEqual(['partial'])
- })
- it('aggregates a large newline-free native write into one log entry, not one per pipe chunk', async () => {
- // A single `os.write` larger than one pipe read arrives as several Node
- // `data` chunks. `logs` entries are joined with `\n` downstream, so pushing
- // one entry per transport chunk would insert model-visible newlines at
- // arbitrary pipe boundaries inside one native write. Stray capture holds a
- // per-stream residual and admits only on a real `\n`, so a 200 KiB blast
- // with no newline reads back as exactly one entry with no interior breaks.
- const { runtime } = await setup({ maxLogBytes: 300_000 })
- const size = 200_000
- const result = await runtime.run({
- program: ['import os', `os.write(1, b"A" * ${size})`, 'return None'].join('\n'),
- bindings: [],
- })
- expect(result.error).toBeUndefined()
- expect(result.logs).toEqual(['A'.repeat(size)])
- })
- it('splits native output on its own newlines, one entry per line', async () => {
- // The complement of the aggregation case: real newlines in a native write
- // still delimit entries, matching the child's line-granular `log` frames.
- const { runtime } = await setup()
- const result = await runtime.run({
- program: ['import os', 'os.write(1, b"one\\ntwo\\nthree")', 'return None'].join('\n'),
- bindings: [],
- })
- expect(result.error).toBeUndefined()
- expect(result.logs).toEqual(['one', 'two', 'three'])
- })
- it('bounds a newline-free native flood by the ledger instead of buffering it whole', async () => {
- // A newline-free write far larger than maxLogBytes must not accumulate in
- // the host-side residual: when the pending residual would cross the budget
- // it is admitted (and truncated) immediately, and once the ledger has
- // truncated, later chunks stop buffering entirely. The run still completes
- // and the captured output ends at the truncation marker rather than
- // retaining the whole flood.
- const { runtime } = await setup({ maxLogBytes: 4096 })
- const result = await runtime.run({
- program: ['import os', 'os.write(1, b"A" * 2_000_000)', 'return None'].join('\n'),
- bindings: [],
- })
- expect(result.error).toBeUndefined()
- expect(result.logs.at(-1)).toBe(logTruncationMarker(4096))
- // The retained output is bounded by the budget, not the 2 MB flood.
- expect(result.logs.join('').length).toBeLessThan(4096)
- })
- it('bounds a control-char-dense native residual by serialized cost, not raw length', async () => {
- // A newline-free NUL flood passes the cheap `length + 3` lower bound at a
- // raw length well under the budget, but each NUL serializes to `�` (6
- // bytes), so the true JSON cost is ~6x. The ledger must charge that
- // serialized cost — and `jsonStringCostUpTo` must measure it WITHOUT
- // allocating the escaped copy, so a near-budget line under a large
- // maxLogBytes cannot momentarily allocate a multi-gigabyte `JSON.stringify`
- // result. Under a small budget the residual is truncated once the serialized
- // cost crosses it.
- const { runtime } = await setup({ maxLogBytes: 4096 })
- const result = await runtime.run({
- program: ['import os', 'os.write(1, b"\\x00" * 4000)', 'return None'].join('\n'),
- bindings: [],
- })
- expect(result.error).toBeUndefined()
- expect(result.logs.at(-1)).toBe(logTruncationMarker(4096))
- })
- it('rejects an output budget that could breach addressSpaceMb during encode at load', async () => {
- // The child builds, charges, and encodes a `maxLogBytes` log entry or a
- // `maxValueBytes` completion value under RLIMIT_AS, and both trigger on
- // character count against a serialized-byte budget — an astral character is
- // one character but ~4 bytes stored and ~4 encoded, and THREE such copies are
- // live at the peak (the caller's write argument, the slice/join handed to
- // push, and the encode copy), so a budget approaching the address space lets a
- // legitimate near-budget output breach it and die as worker-exit. The
- // incompatible pair is rejected at load: each budget times the worst-case
- // multiple (12) must fit the address space LEFT after the fixed interpreter
- // baseline. Against a 256 MiB address space that leaves 192 MiB budgetable
- // (~16 MiB admissible), so a 50 MB cap is far over; the default caps against
- // 512 MiB are not. Both budgets are gated symmetrically — the value case sets
- // a default-fitting maxLogBytes so the maxValueBytes check is what fires.
- const ctxLog = new Context()
- await expect(ctxLog.plugin(PythonCodeRuntime, { maxLogBytes: 50_000_000, addressSpaceMb: 256 }))
- .rejects.toThrow(/maxLogBytes times the 12x worst-case Unicode expansion must fit/)
- const ctxValue = new Context()
- await expect(ctxValue.plugin(PythonCodeRuntime, { maxValueBytes: 50_000_000, addressSpaceMb: 256 }))
- .rejects.toThrow(/maxValueBytes times the 12x worst-case Unicode expansion must fit/)
- // Discriminates 12 from 8: a 48 MiB maxLogBytes against a 512 MiB address
- // space leaves 448 MiB budgetable. 48*8 = 384 MiB fits (the old 8x multiple
- // wrongly ADMITTED this), but 48*12 = 576 MiB does not — and this is exactly
- // the config that OOMs, since a settlement flush holds the pending chunks,
- // their join, and the encode copy at once (~12x). The 12x gate rejects it.
- const ctxTwelve = new Context()
- await expect(ctxTwelve.plugin(PythonCodeRuntime, { maxLogBytes: 48 * 1024 * 1024, addressSpaceMb: 512 }))
- .rejects.toThrow(/maxLogBytes times the 12x worst-case Unicode expansion must fit/)
- // The default caps against the default 512 MiB address space load.
- const ok = new Context()
- const fiber = await ok.plugin(PythonCodeRuntime, { maxLogBytes: 65536, maxValueBytes: 32768, addressSpaceMb: 512 })
- await fiber.dispose()
- })
- it('bounds an illegal-UTF-8 native residual by its U+FFFD-decoded cost', async () => {
- // Every 0xFF byte is illegal in any UTF-8 sequence, so `toString('utf8')`
- // renders each as U+FFFD (3 serialized bytes). `accrueStrayCost` must charge
- // that 3, not the raw 1: otherwise the newline-free residual grows to a full
- // budget's worth of RAW bytes before flushing — a ~3x undercount that near a
- // large maxLogBytes retains hundreds of MiB then expands toward a ~1 GiB peak
- // in flushStray's concat + toString. Paced single-byte writes (each its own
- // `data` chunk, like the sealing case) expose the sub-chunk accrual: charged
- // at 3 the residual crosses a 3072-byte budget after ~1024 bytes and flushes;
- // charged at 1 it would need ~3072 bytes, so the peak residual triples. The
- // largest merged buffer is the discriminator.
- const realConcat = Buffer.concat.bind(Buffer)
- let maxConcat = 0
- Buffer.concat = (list: readonly Uint8Array[], total?: number): Buffer<ArrayBuffer> => {
- const merged = realConcat(list, total)
- if (merged.length > maxConcat) maxConcat = merged.length
- return merged
- }
- let result: CodeRunResult
- try {
- const { runtime } = await setup({ maxLogBytes: 3072, maxWallMs: 30_000 })
- result = await runtime.run({
- program: [
- 'import os',
- 'for _ in range(6000):',
- ' os.write(1, b"\\xff")',
- ' os.sched_yield()',
- 'return None',
- ].join('\n'),
- bindings: [],
- })
- } finally {
- Buffer.concat = realConcat
- }
- expect(result.error).toBeUndefined()
- expect(result.logs.at(-1)).toBe(logTruncationMarker(3072))
- // Charged at 3, the residual flushes around 1024 raw bytes; the largest
- // merged buffer stays well under 2048. A raw-byte undercount would let it
- // reach ~3072 before flushing, so 2048 discriminates.
- expect(maxConcat).toBeLessThan(2048)
- })
- it('charges a structurally-valid but illegal UTF-8 sequence its U+FFFD-decoded cost', async () => {
- // A CESU-8 lone surrogate `ED A0 80` is structurally well-formed (a 3-byte
- // lead plus two 0x80–0xBF continuations) but ILLEGAL: `toString('utf8')`
- // renders each of the three bytes as its own U+FFFD (serialized cost 9), not
- // one width-3 character. The newline-free flush trigger weighs the residual
- // through `accrueStrayCost`, which must validate each lead's
- // first-continuation range (ED excludes A0–BF) and charge the true 9 — else a
- // CESU flood undercounts 3x and the residual grows toward a full budget's raw
- // bytes before flushing, the same peak-memory vector as the 0xFF case. The
- // bytes are written one at a time (each its own `data` chunk, no pipe
- // coalescing) and `Buffer.concat` is wrapped to measure the peak residual.
- const realConcat = Buffer.concat.bind(Buffer)
- let maxConcat = 0
- Buffer.concat = (list: readonly Uint8Array[], total?: number): Buffer<ArrayBuffer> => {
- const merged = realConcat(list, total)
- if (merged.length > maxConcat) maxConcat = merged.length
- return merged
- }
- let result: CodeRunResult
- try {
- const { runtime } = await setup({ maxLogBytes: 3072, maxWallMs: 30_000 })
- result = await runtime.run({
- program: [
- 'import os',
- 'seq = (0xed, 0xa0, 0x80)',
- 'for _ in range(2000):',
- ' for b in seq:',
- ' os.write(1, bytes((b,)))',
- ' os.sched_yield()',
- 'return None',
- ].join('\n'),
- bindings: [],
- })
- } finally {
- Buffer.concat = realConcat
- }
- expect(result.error).toBeUndefined()
- expect(result.logs.at(-1)).toBe(logTruncationMarker(3072))
- // Each 3-byte sequence costs 9 (three U+FFFD), so single-byte-paced the
- // residual crosses the 3072 budget after ~342 raw bytes and flushes; the
- // largest merged buffer stays well under 2048. Charging the structural width
- // 3 would need ~1024 raw bytes, tripling the peak past 2048.
- expect(maxConcat).toBeLessThan(2048)
- })
- it('charges a lone surrogate its full six escaped bytes, not three', async () => {
- // A forged `log` frame carrying `\ud800` escapes materializes lone
- // surrogates after JSON.parse. `Buffer.byteLength` of U+FFFD is 3, but
- // ES2019 well-formed `JSON.stringify` emits `\ud800` at 6 bytes, so charging
- // the raw width would admit ~2x the configured budget of serialized bytes
- // (the same family as the NUL-flood undercount, at 2x rather than 6x). The
- // cost walker charges surrogates the full 6, so a flood truncates at budget.
- // Forged on fd 3 because Python stdout will not emit lone surrogates.
- const { runtime } = await setup({ maxLogBytes: 4096 })
- const result = await runtime.run({
- program: [
- 'import os',
- // 1000 \ud800 escapes: charged at the buggy raw width 1000 * 3 = 3000
- // bytes fits under 4096 (wrongly admitted), but the correct serialized
- // width 1000 * 6 = 6000 bytes is over budget — so the ledger must
- // truncate. The count sits in the 683..1365 window where the two
- // chargings disagree, making the test discriminate.
- String.raw`frame = b'{"type":"log","text":"' + b'\\ud800' * 1000 + b'"}\n'`,
- 'os.write(3, frame)',
- 'return None',
- ].join('\n'),
- bindings: [],
- })
- expect(result.error).toBeUndefined()
- expect(result.logs.at(-1)).toBe(logTruncationMarker(4096))
- })
- it('drops a second stray line in the same chunk once the first truncated the ledger', async () => {
- // One `os.write` carrying two newline-terminated lines where the first
- // exhausts maxLogBytes: the first line's admit truncates and marks the
- // ledger, and the second line's admit — reached in the same `data` callback
- // — must be the post-truncation no-op. Proves that branch is exercised, so
- // it carries no v8-ignore. Kept to 108 bytes (< the smallest PIPE_BUF, 512 on
- // macOS) so the whole payload lands in ONE atomic write and one `data`
- // callback — the two newlines cannot split across callbacks and leave the
- // branch un-exercised, which would be a hard-to-attribute per-file coverage
- // flake. The first line's 100 bytes already exceed the 64-byte budget, so it truncates.
- const { runtime } = await setup({ maxLogBytes: 64 })
- const result = await runtime.run({
- program: ['import os', 'os.write(1, b"A" * 100 + b"\\nSECOND\\n")', 'return None'].join('\n'),
- bindings: [],
- })
- expect(result.error).toBeUndefined()
- expect(result.logs.at(-1)).toBe(logTruncationMarker(64))
- expect(result.logs.join('\n')).not.toContain('SECOND')
- })
- it('charges a broken multibyte sequence its U+FFFD bytes, split across pipe chunks', async () => {
- // A 3-byte lead (0xE4) whose continuation never arrives — the next byte is a
- // fresh ASCII 'A' — must be costed as U+FFFD (3) for the orphaned lead, not
- // folded into a phantom character. Driven byte-by-byte so the lead and the
- // breaking byte land in separate `data` chunks, exercising accrueStrayCost's
- // cross-chunk broken-sequence branch. The run completes and the bytes are
- // captured (rendered U+FFFD by toString), proving the walk resynchronizes.
- const { runtime } = await setup({ maxLogBytes: 1024 })
- const result = await runtime.run({
- program: [
- 'import os',
- 'os.write(1, b"\\xe4")',
- 'os.sched_yield()',
- 'os.write(1, b"A\\n")',
- 'return None',
- ].join('\n'),
- bindings: [],
- })
- expect(result.error).toBeUndefined()
- expect(result.logs.join('')).toContain('A')
- expect(result.logs.join('')).toContain('�')
- })
- it('charges the exact serialized cost of short-escape and quote/backslash characters', async () => {
- // Exercises every branch of jsonStringCostUpTo's per-character cost: a tab
- // and other C0 controls with short JSON forms (\t etc., 2 bytes), a quote
- // and backslash (2 bytes each), a `\uXXXX` control (6 bytes), a multibyte
- // BMP character (raw UTF-8 width), and plain ASCII. Under a budget large
- // enough to admit it, the line survives verbatim — proving the cost walker
- // does not over- or under-charge and the string round-trips unescaped.
- const { runtime } = await setup({ maxLogBytes: 4096 })
- const result = await runtime.run({
- program: ['import os', String.raw`os.write(1, "\ta\"b\\c\x01é\n".encode("utf-8"))`, 'return None'].join('\n'),
- bindings: [],
- })
- expect(result.error).toBeUndefined()
- expect(result.logs).toEqual(['\ta"b\\c\x01é'])
- })
- it('fails a completion dict with a non-string key as invalid-output (no key coercion)', async () => {
- // json.dumps would coerce {1: "a", "1": "b"} to a single "1" key, silently
- // dropping data. The shape validator rejects it before encoding.
- const { runtime } = await setup()
- const result = await runtime.run({
- program: 'return {1: "first", "1": "second"}',
- bindings: [],
- })
- expect(result.value).toBeUndefined()
- expect(result.error?.kind).toBe('invalid-output')
- expect(result.error?.message).toContain('non-string dict key')
- })
- it('rejects a binding argument with a non-string dict key before dispatch', async () => {
- const { runtime } = await setup()
- let called = false
- const result = await runtime.run({
- program: [
- 'caught = ""',
- 'try:',
- ' await tools.sink({1: "x"})',
- 'except RuntimeError as e:',
- ' caught = str(e)',
- 'return caught',
- ].join('\n'),
- bindings: tools({ sink: async () => { called = true; return null } }),
- })
- expect(result.error).toBeUndefined()
- expect(result.value).toContain('lossless JSON')
- expect(called).toBe(false)
- })
- it('fails a non-JSON completion value as invalid-output (no repr substitution)', async () => {
- // A set is not lossless JSON. The old draft substituted repr(); the seam
- // now requires refusing the run instead.
- const { runtime } = await setup()
- const result = await runtime.run({
- program: 'return {1, 2, 3}',
- bindings: [],
- })
- expect(result.value).toBeUndefined()
- expect(result.error?.kind).toBe('invalid-output')
- expect(result.error?.message).toContain('lossless JSON')
- expect(result.error?.message).toContain('set')
- })
- it('fails a negative-zero completion value as invalid-output (sign bit is lossy over JSON)', async () => {
- // JSON serialization turns -0.0 into 0 (or JS -0), silently changing the
- // sign bit; the canonical lossless-JSON boundary rejects it, so the
- // Python side must too — as a completion and as a binding argument.
- const { runtime } = await setup()
- const completion = await runtime.run({
- program: 'return -0.0',
- bindings: [],
- })
- expect(completion.error?.kind).toBe('invalid-output')
- expect(completion.error?.message).toContain('negative zero')
- const argument = await runtime.run({
- program: [
- 'try:',
- ' await tools.echo(-0.0)',
- ' return "accepted"',
- 'except RuntimeError as e:',
- ' return str(e)',
- ].join('\n'),
- bindings: tools({ echo: async args => args as never }),
- })
- expect(argument.error).toBeUndefined()
- expect(argument.value).toContain('negative zero')
- })
- it('fails a NaN completion value as invalid-output (allow_nan=False)', async () => {
- // json.dumps would happily emit NaN by default, but NaN is not JSON; the
- // bootstrap passes allow_nan=False so it fails as invalid-output.
- const { runtime } = await setup()
- const result = await runtime.run({
- program: 'return float("nan")',
- bindings: [],
- })
- expect(result.error?.kind).toBe('invalid-output')
- })
- it('fails an over-budget completion value as output-limit (child-side check)', async () => {
- const { runtime } = await setup({ maxValueBytes: 64 })
- const result = await runtime.run({
- program: 'return "V" * 5000',
- bindings: [],
- })
- expect(result.value).toBeUndefined()
- expect(result.error?.kind).toBe('output-limit')
- expect(result.error?.message).toContain('exceeded 64 bytes')
- })
- it('meters a control-heavy completion value without materializing its escaped form', async () => {
- // The child's lower bound admits a string by CHARACTER count, then the meter
- // charged what `_dump_string(current).encode()` returned -- building the
- // escaped copy plus its encode. Each NUL escapes to six bytes, so metering a
- // value the budget then REJECTS allocated ~6x the original twice over:
- // measured at 228.9 MiB of peak for a 20M-NUL string, against 19.1 MiB for
- // the counting path that returns the identical 120,000,002 bytes. Past
- // RLIMIT_AS the meter died as `exception: MemoryError`, inverting the
- // `output-limit` this seam promises for an over-budget value.
- //
- // 8M NULs is 8,000,002 raw but 48,000,002 escaped: over the 16 MiB budget
- // only when charged the escaped cost, so this also pins that the cheap
- // character bound alone does not decide the verdict.
- const { runtime } = await setup({ maxValueBytes: 16 * 1024 * 1024, maxWallMs: 60_000 })
- const result = await runtime.run({
- program: 'return "\\x00" * 8_000_000',
- bindings: [],
- })
- expect(result.value).toBeUndefined()
- expect(result.error?.kind).toBe('output-limit')
- }, 90_000)
- it('rejects a wide completion as output-limit before materializing its traversal state', async () => {
- // `[0] * 2000000` sits far above maxValueBytes but well below the frame
- // ceiling. The folded checker must reject it via the pre-enqueue bound —
- // BEFORE pushing two million elements onto the walk — so a small
- // addressSpaceMb does not turn the check itself into an RLIMIT_AS death.
- const { runtime } = await setup({ maxValueBytes: 64, addressSpaceMb: 256, maxWallMs: 15_000 })
- const result = await runtime.run({
- program: 'return [0] * 2000000',
- bindings: [],
- })
- expect(result.value).toBeUndefined()
- expect(result.error?.kind).toBe('output-limit')
- expect(result.error?.message).toContain('exceeded 64 bytes')
- }, 20_000)
- it('rejects a wide dict as output-limit without materializing its items list', async () => {
- // Same pre-enqueue bound on the dict branch: `len(current)` replaces
- // `list(current.items())`, which allocated one tuple per member before the
- // bound could reject the value. Two million entries under a 64-byte cap
- // fits the 256 MiB address space as a dict but not as a dict PLUS a
- // two-million-tuple list.
- const { runtime } = await setup({ maxValueBytes: 64, addressSpaceMb: 256, maxWallMs: 15_000 })
- const result = await runtime.run({
- program: 'return {str(i): 0 for i in range(2000000)}',
- bindings: [],
- })
- expect(result.value).toBeUndefined()
- expect(result.error?.kind).toBe('output-limit')
- expect(result.error?.message).toContain('exceeded 64 bytes')
- }, 20_000)
- it('meters a float completion in the host\'s number spelling', async () => {
- // CPython's repr disagrees with the host's String(number): `1.0` is three
- // bytes here and one there, `1e-07` pads the exponent the host writes as
- // `1e-7`. Both sides meter the SAME budget, so the child must count the
- // bytes the host will receive — otherwise a boundary-sized value is
- // falsely reported as output-limit.
- const { runtime } = await setup({ maxValueBytes: 1 })
- const integral = await runtime.run({ program: 'return 1.0', bindings: [] })
- expect(integral.error).toBeUndefined()
- expect(integral.value).toBe(1)
- const exponent = await setup({ maxValueBytes: 4 })
- const small = await exponent.runtime.run({ program: 'return 1e-7', bindings: [] })
- expect(small.error).toBeUndefined()
- expect(small.value).toBe(1e-7)
- // The spelling is a meter input, not a licence to overshoot: `1.5` is three
- // bytes on both sides and still fails a two-byte budget.
- const tight = await setup({ maxValueBytes: 2 })
- const over = await tight.runtime.run({ program: 'return 1.5', bindings: [] })
- expect(over.error?.kind).toBe('output-limit')
- })
- it('carries floats across the wire in the host\'s number spelling', async () => {
- // The child ENCODES with the same speller it meters with, so the frame the
- // host parses must reproduce every double exactly — including the branches
- // where CPython and ECMAScript disagree (integral floats, sub-1e-6
- // exponents, >= 1e21, and beyond-safe-range integral doubles whose exact
- // digits differ from the shortest round-trip form).
- const { runtime } = await setup()
- const result = await runtime.run({
- program: 'return [1.0, 100.0, 1.5, 0.1, 1e-7, 1e-6, 1e-5, 123.456, -2.5e-8, 1e21, float(2**60), 5e-324, 1.7976931348623157e308]',
- bindings: [],
- })
- expect(result.error).toBeUndefined()
- expect(result.value).toEqual([1, 100, 1.5, 0.1, 1e-7, 1e-6, 1e-5, 123.456, -2.5e-8, 1e21, 2 ** 60, 5e-324, 1.7976931348623157e308])
- })
- it('rejects a forged non-lossless done value host-side as invalid-output', async () => {
- // A forged done frame bypasses the child's _check_done_value. JSON.parse
- // turns 1e400 into Infinity; validateChildFrame no longer scans done.value,
- // so the host's own checkDoneValue must catch the non-lossless number.
- const { runtime } = await setup()
- const result = await runtime.run({
- program: [
- 'import os',
- String.raw`os.write(3, b'{"type":"done","value":1e400}' + b'\n')`,
- 'import time',
- 'time.sleep(5)',
- ].join('\n'),
- bindings: [],
- })
- expect(result.value).toBeUndefined()
- expect(result.error?.kind).toBe('invalid-output')
- expect(result.error?.message).toContain('non-lossless number')
- })
- it('reports a syntax error as an exception without settling with a value', async () => {
- const { runtime } = await setup()
- const result = await runtime.run({
- program: '$$invalid python$$',
- bindings: [],
- })
- expect(result.error?.kind).toBe('exception')
- expect(result.error?.message).toContain('SyntaxError')
- expect(result.value).toBeUndefined()
- })
- it('reports a runtime raise as an exception with the traceback', async () => {
- const { runtime } = await setup()
- const result = await runtime.run({
- program: 'raise ValueError("intentional")',
- bindings: [],
- })
- expect(result.error?.kind).toBe('exception')
- expect(result.error?.message).toContain('ValueError')
- expect(result.error?.message).toContain('intentional')
- })
- it('bounds a deep exception cause chain instead of burning the wall budget formatting it', async () => {
- // A chain thousands of links deep would make the rendering walk and
- // format() linear in its length, consuming maxWallMs. Rendering is capped
- // at 100 links with a marker; the run reports the exception well within
- // budget rather than timing out.
- const { runtime } = await setup({ maxValueBytes: 1024 * 1024, maxWallMs: 20_000 })
- const start = Date.now()
- const result = await runtime.run({
- program: [
- 'err = None',
- 'for i in range(3000):',
- ' try:',
- ' raise ValueError(i) from err',
- ' except ValueError as e:',
- ' err = e',
- 'raise err',
- ].join('\n'),
- bindings: [],
- })
- expect(result.error?.kind).toBe('exception')
- expect(result.error?.message).toContain('exception chain truncated at 100 links')
- expect(Date.now() - start).toBeLessThan(15_000)
- }, 25_000)
- it('bounds an over-cap chain without assigning to the live exception', async () => {
- // The cap used to be applied by severing the over-cap link ON the live
- // exception. An exception class overriding __setattr__ to raise turned that
- // assignment into model code running inside the bootstrap's failure
- // handler; the throw skipped the `done` send that sits after the handler,
- // so the host blocked on fd 3 and reported a maxWallMs timeout instead of
- // the model's own exception. Cutting the chain on the TracebackException
- // COPY touches no model hook, so the marker still appears and the run
- // reports `exception`.
- const { runtime } = await setup({ maxValueBytes: 1024 * 1024, maxWallMs: 15_000 })
- const start = Date.now()
- const result = await runtime.run({
- program: [
- 'class Sealed(Exception):',
- ' def __setattr__(self, name, value):',
- ' raise RuntimeError("live mutation refused")',
- 'err = None',
- 'for i in range(150):',
- ' try:',
- ' raise Sealed(i) from err',
- ' except Sealed as e:',
- ' err = e',
- 'raise err',
- ].join('\n'),
- bindings: [],
- })
- expect(result.error?.kind).toBe('exception')
- expect(result.error?.message).toContain('Sealed')
- expect(result.error?.message).toContain('exception chain truncated at 100 links')
- // The sever attempt is what used to leak: its message must not appear, and
- // the run must settle well inside the wall budget rather than timing out.
- expect(result.error?.message).not.toContain('live mutation refused')
- expect(Date.now() - start).toBeLessThan(10_000)
- }, 20_000)
- it('still sends done when rendering the diagnostic itself raises', async () => {
- // format() reaches the exception's own __str__, so a model class whose
- // __str__ raises can throw from inside the failure handler. CPython's
- // _safe_string absorbs a raising __str__ during formatting, but the
- // fallback must hold for any throw on that path (a raising __repr__ of an
- // argument, a MemoryError under RLIMIT_AS), so the assertion is the
- // invariant that matters: a `done` frame carrying `exception`, never a
- // timeout, and never the failing renderer's own message.
- const { runtime } = await setup({ maxWallMs: 10_000 })
- const result = await runtime.run({
- program: [
- 'class Unprintable(Exception):',
- ' def __str__(self):',
- ' raise RuntimeError("str refused")',
- ' def __repr__(self):',
- ' raise RuntimeError("repr refused")',
- 'raise Unprintable()',
- ].join('\n'),
- bindings: [],
- })
- expect(result.error?.kind).toBe('exception')
- expect(result.error?.message).toContain('Unprintable')
- expect(result.error?.message).not.toContain('str refused')
- expect(result.error?.message).not.toContain('repr refused')
- }, 15_000)
- it('sends done with an inert diagnostic when the whole rendering path raises', async () => {
- // Drive the fallback itself. `TracebackException.format` reads the
- // exception class's `__module__` to decide whether to qualify the name, and
- // a metaclass property can raise there — a throw INSIDE the formatter,
- // reached with no rebinding of anything the bootstrap owns. Without the
- // wrapper it escapes the handler, the `done` send never runs, and the host
- // times out at maxWallMs.
- const { runtime } = await setup({ maxWallMs: 10_000 })
- const result = await runtime.run({
- program: [
- 'class Meta(type):',
- ' @property',
- ' def __module__(cls):',
- ' raise RuntimeError("renderer refused")',
- 'class Hostile(ValueError, metaclass=Meta):',
- ' pass',
- 'raise Hostile("original failure")',
- ].join('\n'),
- bindings: [],
- })
- expect(result.error?.kind).toBe('exception')
- // The inert fallback names the class and a fixed literal; it must not carry
- // the renderer's message, and must not have become a timeout. `__name__` is
- // still a plain str here, so the class name survives.
- expect(result.error?.message).toBe('Hostile: <diagnostic rendering failed>')
- }, 15_000)
- it('falls back to a placeholder class name when __name__ itself raises', async () => {
- // The fallback reads type(exc).__name__, which a metaclass property can
- // hijack. It must neither run that override's failure into the handler nor
- // format a non-str __name__ into the message. The hostile `__module__` is
- // what drives execution into the fallback in the first place.
- const { runtime } = await setup({ maxWallMs: 10_000 })
- const result = await runtime.run({
- program: [
- 'class Meta(type):',
- ' @property',
- ' def __module__(cls):',
- ' raise RuntimeError("renderer refused")',
- ' @property',
- ' def __name__(cls):',
- ' raise RuntimeError("name refused")',
- 'class Nameless(Exception, metaclass=Meta):',
- ' pass',
- 'raise Nameless()',
- ].join('\n'),
- bindings: [],
- })
- expect(result.error?.kind).toBe('exception')
- expect(result.error?.message).toBe('<unknown>: <diagnostic rendering failed>')
- }, 15_000)
- it('reports the real exception when the program rebinds every name the failure path uses', async () => {
- // The bootstrap IS __main__, so `import __main__; __main__._X = ...` reaches
- // any module global a call-time lookup would read. The failure path is the
- // worst place for that: the reporter, the byte cap, the traceback formatter,
- // the settlement flush and the `done` send all run AFTER the `except` block,
- // so a replacement that raises skips the send, leaves the host blocked on
- // fd 3, and the run reports a maxWallMs timeout instead of the model's own
- // exception. Rebind all of them at once; the run must still carry the real
- // ValueError.
- const { runtime } = await setup({ maxWallMs: 10_000 })
- const result = await runtime.run({
- program: [
- 'import __main__',
- 'def boom(*a, **k):',
- ' raise RuntimeError("hijacked")',
- '__main__._SAFE_MODEL_TRACEBACK = boom',
- '__main__._cap_message = boom',
- '__main__._model_traceback = boom',
- '__main__._UNRENDERABLE_DIAGNOSTIC = boom',
- '__main__._LogStream.flush_line = boom',
- '__main__.ProtocolChannel.send_sync = boom',
- 'raise ValueError("real failure")',
- ].join('\n'),
- bindings: [],
- })
- expect(result.error?.kind).toBe('exception')
- expect(result.error?.message).toContain('ValueError: real failure')
- expect(result.error?.message).not.toContain('hijacked')
- }, 15_000)
- it('bounds an over-cap exception-group nesting on the copy', async () => {
- // Exception groups link through `exceptions`, not the cause/context
- // dunders, so the cap has to count that edge too — otherwise a deeply
- // nested group walks past the bound the marker claims to enforce.
- const { runtime } = await setup({ maxValueBytes: 1024 * 1024, maxWallMs: 15_000 })
- const result = await runtime.run({
- program: [
- 'group = ValueError("leaf")',
- 'for i in range(150):',
- ' group = ExceptionGroup(f"g{i}", [group])',
- 'raise group',
- ].join('\n'),
- bindings: [],
- })
- expect(result.error?.kind).toBe('exception')
- expect(result.error?.message).toContain('exception chain truncated at 100 links')
- }, 20_000)
- it('filters every bootstrap frame from the traceback of an uncaught binding rejection', async () => {
- // A rejection re-raised by the bootstrap's dispatch adds bootstrap frames
- // AFTER the model's own; only <model> frames may reach model-visible,
- // durable output — a bootstrap.py path would leak host absolutes and make
- // transcripts machine-dependent.
- const { runtime } = await setup()
- const result = await runtime.run({
- program: 'await tools.boom({})',
- bindings: tools({ boom: async () => { throw new Error('exploded') } }),
- })
- expect(result.error?.kind).toBe('exception')
- expect(result.error?.message).toContain('exploded')
- expect(result.error?.message).toContain('<model>')
- expect(result.error?.message).not.toContain('bootstrap.py')
- })
- it('renders a non-Error thrown value from a host binding as its String form', async () => {
- const { runtime } = await setup()
- const result = await runtime.run({
- program: [
- 'caught = ""',
- 'try:',
- ' await tools.failRaw({})',
- 'except RuntimeError as e:',
- ' caught = str(e)',
- 'return caught',
- ].join('\n'),
- bindings: tools({
- failRaw: async () => { throw 'raw-nope' },
- }),
- })
- expect(result.error).toBeUndefined()
- expect(result.value).toContain('raw-nope')
- })
- it('reassembles a frame split across writes behind a completed one', async () => {
- // One os.write carrying "<frame>\n<partial...>" leaves a non-empty
- // residual after the newline loop; the tail must survive until its own
- // newline arrives and then parse as a normal frame.
- const { runtime } = await setup()
- const result = await runtime.run({
- program: [
- 'import os, json',
- 'head = json.dumps({"type":"log","text":"first"}).encode()',
- 'tail = json.dumps({"type":"log","text":"second"}).encode()',
- 'import time',
- 'os.write(3, head + b"\\n" + tail[:5])',
- 'time.sleep(0.2)',
- 'os.write(3, tail[5:] + b"\\n")',
- 'return "ok"',
- ].join('\n'),
- bindings: [],
- })
- expect(result.error).toBeUndefined()
- expect(result.value).toBe('ok')
- expect(result.logs).toContain('first')
- expect(result.logs).toContain('second')
- })
- it('raises the declared errorClass with the member name on rejection', async () => {
- // Code Mode declares { name: ToolCallError, memberNameProperty: toolName };
- // a host rejection must surface as that class, carrying the failed tool.
- const { runtime } = await setup()
- const result = await runtime.run({
- program: [
- 'caught = ""',
- 'try:',
- ' await tools.fail({})',
- 'except ToolCallError as e:',
- ' caught = f"{type(e).__name__}:{e.toolName}:{e}"',
- 'return caught',
- ].join('\n'),
- bindings: [{
- global: 'tools',
- functions: { fail: async () => { throw new Error('typed-nope') } },
- errorClass: { name: 'ToolCallError', memberNameProperty: 'toolName' },
- }],
- })
- expect(result.error).toBeUndefined()
- expect(result.value).toBe('ToolCallError:fail:typed-nope')
- })
- it('rejects an errorClass name colliding with its namespace global at the seam', async () => {
- const { runtime } = await setup()
- await expect(runtime.run({
- program: 'return 1',
- bindings: [{ global: 'tools', functions: {}, errorClass: { name: 'tools', memberNameProperty: 'toolName' } }],
- })).rejects.toThrow(/collides with another injected global/)
- })
- it('rejects a namespace global colliding with a runtime-owned name at the seam', async () => {
- // `__dsh_main__` passes the identifier check, but exec()ing the generated
- // wrapper would silently overwrite the binding after injection. `console`
- // is the WORKER backend's slot — refused here too so a namespace list
- // valid on one backend is valid on all.
- const { runtime } = await setup()
- // `__debug__` is refused for a different reason than a collision: CPython
- // compiles a bare `__debug__` reference to the constant True and refuses to
- // assign the name at compile time, so an injected global under it is
- // unreachable from the program — accepted by the seam, unusable here.
- for (const global of ['__dsh_main__', 'console', '__debug__']) {
- await expect(runtime.run({
- program: 'x = 1',
- bindings: [{ global, functions: {} }],
- })).rejects.toThrow(/collides with a runtime-owned global/)
- }
- })
- it('accepts a non-identifier memberNameProperty and rejects only an empty one', async () => {
- // The seam permits any non-empty own property except the reserved
- // members; Python setattr/getattr carry exotic names like `tool-name`,
- // and the worker backend accepts them, so this backend must too.
- const { runtime } = await setup()
- const result = await runtime.run({
- program: [
- 'try:',
- ' await tools.boom({})',
- 'except ToolCallError as e:',
- ' return getattr(e, "tool-name")',
- ].join('\n'),
- bindings: [{
- global: 'tools',
- functions: { boom: async () => { throw new Error('nope') } },
- errorClass: { name: 'ToolCallError', memberNameProperty: 'tool-name' },
- }],
- })
- expect(result.error).toBeUndefined()
- expect(result.value).toBe('boom')
- await expect(runtime.run({
- program: 'return 1',
- bindings: [{ global: 'tools', functions: {}, errorClass: { name: 'ToolCallError', memberNameProperty: '' } }],
- })).rejects.toThrow(/memberNameProperty must be a non-empty attribute name/)
- })
- it('resolves a basename pythonBin to an absolute path (runs a real program)', async () => {
- // A bare `python3` basename must resolve against PATH and actually launch
- // under the empty-env spawn — exercises the accessSync success branch.
- const { runtime } = await setup({ pythonBin: 'python3' })
- const result = await runtime.run({ program: 'return 7', bindings: [] })
- expect(result.error).toBeUndefined()
- expect(result.value).toBe(7)
- })
- it('spawns via an absolute python path resolved from a basename against PATH', async () => {
- // resolvePythonBin turns the default basename into an absolute path before
- // the empty-env spawn; a basename with no PATH match falls through to the
- // normal ENOENT worker-exit rather than throwing.
- const { runtime } = await setup({ pythonBin: 'definitely-no-such-python-xyz' })
- const result = await runtime.run({ program: 'return 1', bindings: [] })
- expect(result.error?.kind).toBe('worker-exit')
- })
- it('rejects a memberNameProperty naming a constrained BaseException attribute', async () => {
- // `__dict__`/`__class__` are constrained descriptors alongside
- // `__traceback__` — setattr of a string raises TypeError while
- // constructing the rejection — so every dunder is refused at the seam.
- const { runtime } = await setup()
- // name/message/stack are the seam's own exclusions (CodeBindingErrorClass
- // forbids replacing them; the worker backend rejects them identically).
- for (const member of ['__traceback__', '__dict__', '__class__', 'args', 'name', 'message', 'stack']) {
- await expect(runtime.run({
- program: 'return 1',
- bindings: [{ global: 'tools', functions: {}, errorClass: { name: 'ToolCallError', memberNameProperty: member } }],
- })).rejects.toThrow(/reserved error member/)
- }
- })
- it('rejects a lossy binding resolution (NaN) instead of coercing it to null', async () => {
- // JSON.stringify would turn NaN into null and drop undefined fields; the
- // seam requires a descriptive rejection so data cannot silently corrupt.
- const { runtime } = await setup()
- const result = await runtime.run({
- program: [
- 'caught = ""',
- 'try:',
- ' await tools.bad({})',
- 'except RuntimeError as e:',
- ' caught = str(e)',
- 'return caught',
- ].join('\n'),
- bindings: tools({ bad: async () => Number.NaN }),
- })
- expect(result.error).toBeUndefined()
- expect(result.value).toContain('lossless JSON')
- })
- it('contains a forged pathological done value without crashing the host', async () => {
- // A ~20k-deep nested array forged onto fd 3 would overflow a recursive
- // JSON.stringify; the host's iterative encoder measures it stack-safely
- // and fails it deterministically on the byte budget (40 kB > 32 KiB).
- const { runtime } = await setup()
- const result = await runtime.run({
- program: [
- 'import os, json',
- 'depth = 20000',
- 'payload = "[" * depth + "]" * depth',
- 'os.write(3, b\'{"type":"done","value":\' + payload.encode() + b\'}\\n\')',
- 'import time',
- 'time.sleep(5)',
- ].join('\n'),
- bindings: [],
- })
- expect(result.value).toBeUndefined()
- expect(result.error?.kind).toBe('output-limit')
- })
- it('preserves a deeply nested completion value below the byte budget', async () => {
- // CodeJsonValue has no depth limit: a 10000-deep nested list is only
- // ~20 kB — under maxValueBytes — and must cross intact. That depth
- // overflows BOTH recursive serializers the pipeline used to rely on
- // (CPython's json.dumps recursion limit ~1000s, V8's JSON.stringify), so
- // it proves the child-side _encode_json_plain and the host-side
- // encodeJsonPlain together. The host JSON.parse of the frame is iterative
- // in V8 for arrays, so only the two encoders were at risk.
- const { runtime } = await setup()
- const result = await runtime.run({
- program: [
- 'v = None',
- 'for _ in range(10000):',
- ' v = [v]',
- 'return v',
- ].join('\n'),
- bindings: [],
- })
- expect(result.error).toBeUndefined()
- // Walk down iteratively (a recursive toEqual would itself overflow).
- let depth = 0
- let cursor: unknown = result.value
- while (Array.isArray(cursor)) {
- expect(cursor).toHaveLength(1)
- cursor = cursor[0]
- depth++
- }
- expect(depth).toBe(10000)
- expect(cursor).toBeNull()
- })
- it('bridges a deeply nested binding resolution back into the program stack-safely', async () => {
- // A binding resolution has no seam-level depth or byte cap; neither the
- // host's reply serialization nor the CHILD's reply decode may die on
- // recursion (json.loads raises RecursionError ~10k levels deep; the
- // bootstrap decodes frames iteratively). 12000 levels sits past that
- // limit while staying tiny in bytes.
- const { runtime } = await setup()
- const deep = ((): unknown => {
- let v: unknown = null
- for (let i = 0; i < 12000; i++) v = [v]
- return v
- })()
- const result = await runtime.run({
- program: [
- 'v = await tools.deep({})',
- 'depth = 0',
- 'while isinstance(v, list):',
- ' v = v[0]',
- ' depth += 1',
- 'return depth',
- ].join('\n'),
- bindings: tools({ deep: async () => deep as never }),
- })
- expect(result.error).toBeUndefined()
- expect(result.value).toBe(12000)
- })
- it('rejects a reserved errorClass name at the seam', async () => {
- const { runtime } = await setup()
- await expect(runtime.run({
- program: 'return 1',
- bindings: [{
- global: 'tools',
- functions: {},
- errorClass: { name: 'class', memberNameProperty: 'toolName' },
- }],
- })).rejects.toThrow(/errorClass.name "class" is not a usable Python identifier/)
- })
- it('routes a declared inherited-attribute name through the bridge via subscript', async () => {
- // __class__ resolves on `object` before any fallback hook; the proxy's
- // __getattribute__ intercepts declared names first, and subscript access
- // is the SDK-advertised route for underscore names.
- const { runtime } = await setup()
- const seen: string[] = []
- const result = await runtime.run({
- program: [
- 'a = await tools["__class__"]({"via": "subscript"})',
- 'b = await tools.__class__({"via": "dot"})',
- 'return [a, b]',
- ].join('\n'),
- bindings: tools({
- '__class__': async () => { seen.push('called'); return 'bridged' },
- }),
- })
- expect(result.error).toBeUndefined()
- expect(result.value).toEqual(['bridged', 'bridged'])
- expect(seen).toEqual(['called', 'called'])
- })
- it('rejects NaN binding arguments immediately instead of hanging', async () => {
- // Default json.dumps would emit a non-standard NaN token that the host
- // JSON.parse drops silently, hanging the call until the wall clock;
- // allow_nan=False raises in-program right away.
- const { runtime } = await setup({ maxWallMs: 8000 })
- const start = Date.now()
- const result = await runtime.run({
- program: [
- 'caught = ""',
- 'try:',
- ' await tools.echo({"x": float("nan")})',
- 'except RuntimeError as e:',
- ' caught = str(e)',
- 'return caught',
- ].join('\n'),
- bindings: tools({ echo: async args => args as CodeJsonValue }),
- })
- expect(result.error).toBeUndefined()
- expect(result.value).toContain('lossless JSON')
- expect(Date.now() - start).toBeLessThan(5000)
- })
- it('carries large binding arguments well past maxValueBytes', async () => {
- // Binding traffic has no seam byte cap: a call frame far larger than the
- // completion budget must reach the host intact (the fd-3 ceiling is a
- // fixed memory-safety bound, not an output budget).
- const maxValueBytes = 4096
- const { runtime } = await setup({ maxValueBytes })
- let receivedLength = 0
- const result = await runtime.run({
- program: [
- `big = "B" * ${maxValueBytes * 50}`,
- 'r = await tools.measure({"payload": big})',
- 'return r',
- ].join('\n'),
- bindings: tools({
- measure: async (args) => {
- receivedLength = ((args as { payload: string }).payload).length
- return receivedLength
- },
- }),
- })
- expect(result.error).toBeUndefined()
- expect(receivedLength).toBe(maxValueBytes * 50)
- expect(result.value).toBe(maxValueBytes * 50)
- })
- it('rejects an unknown binding name inside the program with a matching error', async () => {
- const { runtime } = await setup()
- const result = await runtime.run({
- program: [
- 'caught = ""',
- 'try:',
- ' await tools.nope({})',
- 'except (AttributeError, RuntimeError) as e:',
- ' caught = str(e)',
- 'return caught',
- ].join('\n'),
- bindings: tools({ known: async () => 'ok' }),
- })
- expect(result.error).toBeUndefined()
- expect(result.value).toContain('nope')
- })
- it('bounds an unknown-binding diagnostic built from a forged call frame', async () => {
- // `call.global` and `call.name` carry no byte cap of their own, only the
- // 256 MiB fd-3 frame ceiling, and the reply interpolated them raw: one copy
- // into the template result, one into the `JSON.stringify` escape, one into
- // the `encodeJsonPlain` frame, one into the pipe write. Slicing each field
- // to `maxValueBytes` code units first makes an 8 MiB forged name a
- // 128-byte reply. The observable effect is the reply the child then has to
- // READ: its fd-3 reader is unbuffered, so `readline` consumes an oversized
- // reply one `read(2)` per byte and the run's own legitimate call never gets
- // answered — measured under a 60 s ceiling, the 8 MiB case timed out and a
- // 64 MiB case cost the host 509.9 MiB of heap against 120.3 MiB with the
- // slices in place. The child's address space stays generous enough to BUILD
- // the forgery, which is not what is under test.
- const { runtime } = await setup({ maxValueBytes: 128, addressSpaceMb: 1024, maxWallMs: 20_000 })
- const result = await runtime.run({
- program: [
- 'import os',
- 'frame = b\'{"type":"call","id":9001,"global":"tools","name":"\' + b"n" * (8 * 1024 * 1024) + b\'","args":{}}\\n\'',
- // One os.write returns short past the pipe buffer, and a partial frame
- // would glue itself to the next one and be dropped as malformed, so the
- // forgery goes out through a drain loop.
- 'view = memoryview(frame)',
- 'while view:',
- ' view = view[os.write(3, view):]',
- // A legitimate call after the forgery: its reply can only arrive once
- // the child has read past whatever the forged frame was answered with.
- 'await tools.known({})',
- 'return "settled"',
- ].join('\n'),
- bindings: tools({ known: async () => 'ok' }),
- })
- expect(result.error).toBeUndefined()
- expect(result.value).toBe('settled')
- }, 40_000)
- it('bridges a binding call reached via subscript access (tools["name"])', async () => {
- // The SDK tells the model `await tools["my-tool"](args)` works for exotic
- // names; the proxy's __getitem__ must route it through the bridge.
- const { runtime } = await setup()
- const result = await runtime.run({
- program: [
- 'r = await tools["my-tool"]({"n": 7})',
- 'return r',
- ].join('\n'),
- bindings: tools({ 'my-tool': async args => ({ got: args as CodeJsonValue }) }),
- })
- expect(result.error).toBeUndefined()
- expect(result.value).toEqual({ got: { n: 7 } })
- })
- it('raises KeyError for an undeclared subscript name', async () => {
- const { runtime } = await setup()
- const result = await runtime.run({
- program: [
- 'caught = ""',
- 'try:',
- ' await tools["absent"]({})',
- 'except KeyError as e:',
- ' caught = str(e)',
- 'return caught',
- ].join('\n'),
- bindings: tools({ known: async () => 'ok' }),
- })
- expect(result.error).toBeUndefined()
- expect(result.value).toContain('absent')
- })
- })
- describe('PythonCodeRuntime — budgets, termination, disposal', () => {
- it('kills a wall-clock runaway program via SIGTERM/SIGKILL and reports timeout', async () => {
- const { runtime } = await setup({ maxWallMs: 500, graceMs: 200 })
- const start = Date.now()
- const result = await runtime.run({
- program: 'import time\nwhile True: time.sleep(1)',
- bindings: [],
- })
- const elapsed = Date.now() - start
- // The wall timer may fire first or the exit-after-signal may resolve; both are ok.
- expect(['timeout', 'worker-exit']).toContain(result.error?.kind)
- // We got somewhere in the neighborhood of maxWallMs, not the underlying `sleep(1)`.
- expect(elapsed).toBeLessThan(2000)
- }, 5000)
- it('aborts a run when the outer signal fires mid-flight', async () => {
- const { runtime } = await setup({ maxWallMs: 10_000 })
- const controller = new AbortController()
- const settled: Promise<CodeRunResult> = runtime.run({
- program: 'import time\nwhile True: time.sleep(0.1)',
- bindings: [],
- signal: controller.signal,
- })
- setTimeout(() => { controller.abort('outer-abort') }, 200)
- const result = await settled
- expect(['abort', 'worker-exit']).toContain(result.error?.kind)
- }, 5000)
- it('settles the run when a mid-flight abort reason cannot be converted', async () => {
- // The listener converted the reason before calling `finish()`, so a hostile
- // reason threw from inside an `AbortSignal` listener. Node reports that as an
- // uncaught exception — it can terminate the host — and `finish()` never ran,
- // so the run stayed live until the wall ceiling and misreported as `timeout`
- // (observed) instead of the caller's cancellation. `maxWallMs` is short so
- // that misreport is a fast assertion failure rather than a suite timeout.
- const uncaught: unknown[] = []
- const record = (error: unknown): void => { uncaught.push(error) }
- process.on('uncaughtException', record)
- try {
- const { runtime } = await setup({ maxWallMs: 4_000, graceMs: 200 })
- const controller = new AbortController()
- const settled: Promise<CodeRunResult> = runtime.run({
- program: 'import time\nwhile True: time.sleep(0.1)',
- bindings: [],
- signal: controller.signal,
- })
- setTimeout(() => {
- controller.abort({ [Symbol.toPrimitive]() { throw new Error('reason blew up') } })
- }, 200)
- const result = await settled
- expect(result.error?.kind).toBe('abort')
- expect(result.error?.message).toBe('<unrenderable rejection value>')
- expect(uncaught).toEqual([])
- } finally {
- process.off('uncaughtException', record)
- }
- }, 15_000)
- it('disposes to quiescence: an in-flight run resolves as abort and the child exits', async () => {
- const { fiber, runtime } = await setup({ maxWallMs: 10_000 })
- const pending = runtime.run({
- program: 'import time\nwhile True: time.sleep(0.1)',
- bindings: [],
- })
- // Give the process time to spawn and start running.
- await new Promise(resolve => setTimeout(resolve, 200))
- await fiber.dispose()
- const result = await pending
- expect(['abort', 'worker-exit']).toContain(result.error?.kind)
- }, 5000)
- it('reports a spawn failure via a bogus python binary as worker-exit', async () => {
- const { runtime } = await setup({ pythonBin: '/nonexistent/python-binary', maxWallMs: 3000 })
- const result = await runtime.run({
- program: 'return 1',
- bindings: [],
- })
- expect(result.error?.kind).toBe('worker-exit')
- }, 8000)
- it('applies the strictest of the configured and inherited resource limits', async () => {
- // This case used to drive the bootstrap's `applying resource limits failed`
- // handler with `cpuSeconds: 2 ** 63`, asserting that a cap the child cannot
- // apply fails the run rather than running it uncapped. That premise no longer
- // holds, for two independent reasons, so the test now pins what is actually
- // guaranteed instead of a path no admissible input reaches.
- //
- // First, `2 ** 63` is not a safe integer, so it is now rejected at LOAD as a
- // configuration error — it can never reach the child at all. Second, even the
- // largest admissible values are applied successfully, because `_clamped`
- // bounds every requested pair by the inherited hard limit: an unprivileged
- // process may lower a hard limit but never raise one, so the child keeps the
- // stricter of the two rather than asking for something `setrlimit` refuses.
- // The failure handler remains as a substrate guard (a platform whose kernel
- // refuses the call for its own reasons), but it is no longer reachable from
- // configuration, and a test that pretends otherwise documents a contract the
- // code does not have.
- //
- // What is observable: a very large cap still yields a working run, and the
- // containment it promises is met by the inherited ceiling.
- const { runtime } = await setup({ cpuSeconds: Number.MAX_SAFE_INTEGER - 1, maxWallMs: 10_000 })
- const result = await runtime.run({ program: 'return 1', bindings: [] })
- expect(result.error).toBeUndefined()
- expect(result.value).toBe(1)
- }, 20_000)
- it('settles as worker-exit when the child exits before sending done (no hang)', async () => {
- // Regression: settlement must key off `close` (process reaped AND stdio
- // drained), not `exit`. With `exit`, finish() re-armed a second exit
- // listener that never fired — run() hung forever whenever the exit event
- // beat the final fd-3 data (deterministic on macOS, a lost race elsewhere).
- const { runtime } = await setup({ maxWallMs: 10_000 })
- const result = await runtime.run({
- program: 'import os\nos._exit(7)',
- bindings: [],
- })
- expect(result.error?.kind).toBe('worker-exit')
- expect(result.error?.message).toContain('code=7')
- }, 5000)
- it('classifies RLIMIT_CPU soft-limit expiry (SIGXCPU) as a timeout', async () => {
- // A CPU hot loop burns the soft limit; the kernel delivers SIGXCPU, whose
- // close signal the host maps to `timeout`. macOS re-delivers SIGXCPU
- // differently, so we assert only kind/message here — CI's darwin leg
- // validates real delivery. cpuSeconds must be an integer for setrlimit.
- const { runtime } = await setup({ cpuSeconds: 1, maxWallMs: 20_000 })
- const result = await runtime.run({
- program: 'while True: pass',
- bindings: [],
- })
- expect(result.error?.kind).toBe('timeout')
- expect(result.error?.message).toContain('CPU time exhausted')
- }, 8000)
- it('keeps an early self-inflicted SIGKILL a worker-exit, not a CPU timeout', async () => {
- // The unsolicited-SIGKILL-as-timeout classification applies only when the
- // CPU budget could have expired (wall time >= cpuSeconds). A SIGKILL
- // seconds before that (cgroup OOM, an operator, os.kill) is substrate
- // death and stays worker-exit per the orthogonal taxonomy.
- const { runtime } = await setup({ cpuSeconds: 60, maxWallMs: 10_000 })
- const result = await runtime.run({
- program: [
- 'import os, signal',
- 'os.kill(os.getpid(), signal.SIGKILL)',
- ].join('\n'),
- bindings: [],
- })
- expect(result.error?.kind).toBe('worker-exit')
- expect(result.error?.message).toContain('SIGKILL')
- })
- it('charges a forked descendant against the run CPU budget', async () => {
- // RLIMIT_CPU is per-process and every child inherits a FRESH budget, so a
- // program that shells out multiplies `cpuSeconds` by the number of
- // descendants it starts. Measured before the aggregate meter existed: with
- // cpuSeconds 1, two sequential busy children burned 2.0 CPU-seconds
- // (RUSAGE_CHILDREN) and the run still returned a SUCCESS completion. The
- // settle-time check meters RUSAGE_SELF + RUSAGE_CHILDREN and converts the
- // overrun into the same SIGXCPU the untrapped soft limit sends.
- const { runtime } = await setup({ cpuSeconds: 1, maxWallMs: 30_000 })
- const result = await runtime.run({
- program: [
- 'import subprocess, sys',
- 'for _ in range(2):',
- ' subprocess.run([sys.executable, "-c", "import time\\nt=time.time()\\nwhile time.time()-t<1.2: pass"])',
- 'return "escaped the cpu budget"',
- ].join('\n'),
- bindings: [],
- })
- // Darwin's SIGXCPU re-delivery differs, so accept either terminal
- // classification; what must NOT happen is the completion crossing.
- expect(['timeout', 'worker-exit']).toContain(result.error?.kind)
- expect(result.value).toBeUndefined()
- }, 40_000)
- it('does not charge wall time or a cheap descendant against the CPU budget', async () => {
- // The meter is CPU, not wall clock, and it must not fire on a child that
- // burns almost nothing: a sleeping program and a trivial subprocess both
- // have to complete normally, or the check would reject every program that
- // shells out.
- const { runtime } = await setup({ cpuSeconds: 1, maxWallMs: 30_000 })
- const slept = await runtime.run({
- program: 'import time\ntime.sleep(1.5)\nreturn "slept"',
- bindings: [],
- })
- expect(slept.error).toBeUndefined()
- expect(slept.value).toBe('slept')
- const cheap = await runtime.run({
- program: [
- 'import subprocess, sys',
- 'subprocess.run([sys.executable, "-c", "pass"])',
- 'return "cheap child"',
- ].join('\n'),
- bindings: [],
- })
- expect(cheap.error).toBeUndefined()
- expect(cheap.value).toBe('cheap child')
- }, 40_000)
- it('spends no part of addressSpaceMb on bootstrap machinery', async () => {
- // RLIMIT_AS counts RESERVED address space, so anything the bootstrap maps
- // for its own accounting is subtracted from the program's `addressSpaceMb`.
- // A sampling thread for the descendant-CPU meter cost 72 MiB here (an 8 MiB
- // stack plus a 64 MiB glibc per-thread malloc arena reservation) and turned
- // the 2-million-entry dict rejection below into a MemoryError under a
- // 256 MiB cap on a slower runner. Assert the child's own mappings directly
- // rather than inferring the budget from a near-cap allocation, so the bound
- // is read from /proc instead of from how much headroom one machine happens
- // to have; 48 MiB is well above the ~30 MiB a bare interpreter maps and
- // well below the 102 MiB the thread produced. `addressSpaceMb` itself is
- // skipped on darwin (the dyld shared cache makes any practical cap
- // unsettable) and /proc/self/maps does not exist there, so the mapping
- // assertion is Linux-only; the completion path is checked everywhere.
- const { runtime } = await setup({ maxValueBytes: 4096, addressSpaceMb: 256 })
- const mapped = await runtime.run({
- program: [
- 'import sys',
- 'if sys.platform != "linux":',
- ' return 0',
- 'total = 0',
- 'with open("/proc/self/maps") as handle:',
- ' for line in handle:',
- ' low, high = (int(part, 16) for part in line.split(" ", 1)[0].split("-"))',
- ' total += high - low',
- 'return total // (1024 * 1024)',
- ].join('\n'),
- bindings: [],
- })
- expect(mapped.error).toBeUndefined()
- expect(mapped.value).toBeLessThan(48)
- }, 20_000)
- it('spends no part of addressSpaceMb on the reply pump, across a binding await', async () => {
- // The test above measures BEFORE the program yields, so it could not see the
- // reply pump's cost: `loop.run_in_executor(None, read_frame)` created the
- // default executor's first thread on the first `await tools.*`, and that
- // thread's 8 MiB stack plus a 64 MiB glibc per-thread malloc arena are
- // charged to RLIMIT_AS while the limit is already in force — measured, the
- // child went from 30.34 MiB to 102.39 MiB across one binding call. Under a
- // small `addressSpaceMb` the thread cannot start and a legitimate call hangs
- // to `maxWallMs`; under a larger one an allocation that should have fit dies
- // as MemoryError. `loop.add_reader` watches the fd with no thread at all.
- //
- // Measuring both sides inside one run is what discriminates: a single
- // after-the-fact number cannot separate the pump's cost from the
- // interpreter's own footprint. Linux-only for the same reason as above.
- const { runtime } = await setup({ addressSpaceMb: 256, maxWallMs: 20_000 })
- const result = await runtime.run({
- program: [
- 'import sys',
- 'def mapped():',
- ' if sys.platform != "linux":',
- ' return 0',
- ' total = 0',
- ' with open("/proc/self/maps") as handle:',
- ' for line in handle:',
- ' low, high = (int(part, 16) for part in line.split(" ", 1)[0].split("-"))',
- ' total += high - low',
- ' return total // (1024 * 1024)',
- 'before = mapped()',
- 'echoed = await tools.echo({"ping": True})',
- 'return {"before": before, "after": mapped(), "echoed": echoed}',
- ].join('\n'),
- bindings: tools({ echo: async args => args as CodeJsonValue }),
- })
- expect(result.error).toBeUndefined()
- const value = result.value as { before: number; after: number; echoed: unknown }
- // The binding call really happened, so the pump really ran.
- expect(value.echoed).toEqual({ ping: true })
- // Awaiting a binding maps nothing extra. The 8 MiB allowance absorbs ordinary
- // heap growth while staying far below the 72 MiB a pump thread cost.
- expect(value.after - value.before).toBeLessThan(8)
- }, 30_000)
- it('still terminates a program that ignores SIGXCPU (hard-limit backstop)', async () => {
- // A hot loop under SIG_IGN burns through the soft limit; the kernel's
- // hard limit (cpuSeconds + 1) SIGKILLs it. Only a kernel-authoritative
- // SIGXCPU close classifies as the CPU timeout — a bare SIGKILL is
- // indistinguishable from a cgroup OOM kill, so it reports worker-exit
- // (Darwin re-delivers SIGXCPU instead, where the wall clock settles it
- // as timeout). Either way the run TERMINATES within the budget — the
- // backstop holds even when the classification is the opaque one.
- const { runtime } = await setup({ cpuSeconds: 1, maxWallMs: 6_000 })
- const result = await runtime.run({
- program: [
- 'import signal',
- 'signal.signal(signal.SIGXCPU, signal.SIG_IGN)',
- 'while True: pass',
- ].join('\n'),
- bindings: [],
- })
- expect(['timeout', 'worker-exit']).toContain(result.error?.kind)
- }, 12_000)
- it('enforces the CPU budget even when the program monkeypatches the enforcement primitives', async () => {
- // The check uses import-time-captured references, so replacing
- // resource.getrusage / signal.signal / os.kill on the modules cannot
- // defang it: a trapping program that also swaps the callables and burns
- // past the budget still dies by the authoritative SIGXCPU.
- const { runtime } = await setup({ cpuSeconds: 1, maxWallMs: 15_000 })
- const result = await runtime.run({
- program: [
- 'import signal, os, resource, time',
- 'signal.signal(signal.SIGXCPU, lambda *a: None)',
- 'resource.getrusage = lambda *a: (_ for _ in ()).throw(RuntimeError("nope"))',
- 'os.kill = lambda *a: None',
- 'signal.signal = lambda *a: None',
- 'deadline = time.process_time() + 1.05',
- 'while time.process_time() < deadline: pass',
- 'return "escaped"',
- ].join('\n'),
- bindings: [],
- })
- expect(result.error?.kind).toBe('timeout')
- expect(result.value).toBeUndefined()
- }, 15_000)
- it('re-delivers SIGXCPU when a trapping program returns inside the soft-to-hard gap', async () => {
- // A program can trap SIGXCPU and settle during the one-second gap; the
- // bootstrap re-checks the kernel CPU meter (getrusage) after settlement
- // and dies by SIGXCPU with the default disposition restored, so the host
- // still classifies the exhausted budget as a timeout instead of success.
- const { runtime } = await setup({ cpuSeconds: 1, maxWallMs: 15_000 })
- const result = await runtime.run({
- program: [
- 'import signal, time',
- 'fired = []',
- 'signal.signal(signal.SIGXCPU, lambda *a: fired.append(1))',
- 'deadline = time.process_time() + 1.05',
- 'while time.process_time() < deadline: pass',
- 'return "escaped"',
- ].join('\n'),
- bindings: [],
- })
- expect(result.error?.kind).toBe('timeout')
- expect(result.error?.message).toContain('CPU time exhausted')
- expect(result.value).toBeUndefined()
- }, 15_000)
- it('enforces the CPU budget when the program rebinds the enforcer on __main__', async () => {
- // The bootstrap IS `__main__`, so `import __main__` reaches its globals.
- // The enforcement callable holds its primitives in closure cells (not
- // module attributes) and `_run` reads the callable into a frame local
- // before the program starts, so neither replacing the global nor swapping
- // the module's captured names changes what runs after settlement.
- const { runtime } = await setup({ cpuSeconds: 1, maxWallMs: 15_000 })
- const result = await runtime.run({
- program: [
- 'import signal, time, __main__',
- 'signal.signal(signal.SIGXCPU, lambda *a: None)',
- '__main__._DIE_IF_CPU_EXHAUSTED = lambda *_: None',
- 'deadline = time.process_time() + 1.05',
- 'while time.process_time() < deadline: pass',
- 'return "escaped"',
- ].join('\n'),
- bindings: [],
- })
- expect(result.error?.kind).toBe('timeout')
- expect(result.value).toBeUndefined()
- }, 15_000)
- it('bounds a program that defeats the post-check by writing its closure cell', async () => {
- // The closure-cell capture raises the cost of defeating the post-check; it
- // does NOT make it unreachable, and nothing in-process could: a cell is
- // writable through `fn.__closure__[i].cell_contents`, and `sys._getframe`
- // reads _run's frame locals. This program does exactly that — walks to
- // _run's frame, takes the enforcement callable, and replaces its captured
- // `getrusage` with one reporting zero CPU used — then burns past cpuSeconds
- // with SIGXCPU trapped. The run must still fail, because the bound that
- // model code cannot forge is outside the interpreter: the RLIMIT_CPU HARD
- // limit at cpuSeconds + 1, whose SIGKILL admits no handler. No success is
- // reportable either way.
- const { runtime } = await setup({ cpuSeconds: 1, maxWallMs: 20_000 })
- const start = Date.now()
- const result = await runtime.run({
- program: [
- 'import signal, sys, time',
- 'signal.signal(signal.SIGXCPU, lambda *a: None)',
- // Walk out of __dsh_main__ to _run's frame and take its local.
- 'die = None',
- 'depth = 1',
- 'while depth < 12:',
- ' frame = sys._getframe(depth)',
- ' if "die_if_cpu_exhausted" in frame.f_locals:',
- ' die = frame.f_locals["die_if_cpu_exhausted"]',
- ' break',
- ' depth += 1',
- 'assert die is not None, "enforcer not reachable from the frame chain"',
- 'class Zero:',
- ' ru_utime = 0.0',
- ' ru_stime = 0.0',
- 'names = die.__code__.co_freevars',
- 'die.__closure__[names.index("getrusage")].cell_contents = lambda *a: Zero()',
- // Burn well past the soft limit into the hard limit's SIGKILL.
- 'while True: pass',
- ].join('\n'),
- bindings: [],
- })
- // What holds on EVERY platform: the tampering bought no success. The run
- // failed, carried no value, and the reported kind is one of the two
- // kernel-level outcomes — never a completion.
- expect(result.value).toBeUndefined()
- expect(result.error?.kind === 'worker-exit' || result.error?.kind === 'timeout').toBe(true)
- if (process.platform === 'linux') {
- // Linux enforces the RLIMIT_CPU HARD limit at cpuSeconds + 1 promptly, so
- // the CPU bound — not the 20 s wall ceiling — is what stops the program.
- // Its SIGKILL is not SIGXCPU, so the orthogonal-failure taxonomy reports
- // `worker-exit`: a bare SIGKILL is not evidence of CPU burn.
- expect(result.error?.kind).toBe('worker-exit')
- expect(Date.now() - start).toBeLessThan(15_000)
- } else {
- // Darwin does not deliver the hard limit's SIGKILL on the same schedule;
- // observed on the macOS lane, a program that patches the post-check runs
- // to the WALL ceiling instead. The CPU budget is therefore not the
- // binding constraint against a tampering program there — the wall clock
- // is. Asserted rather than skipped so the difference stays visible.
- expect(result.error?.kind).toBe('timeout')
- }
- }, 30_000)
- it('keeps a finished-but-not-closed run live so dispose awaits the child\'s death', async () => {
- // finish() no longer drops the run from `live`; settle() (at close) does.
- // A SIGTERM-trapping program with a small graceMs sits in the grace window
- // after finish() fires — dispose() must not resolve until the SIGKILL
- // backstop actually reaps the child. The program prints its pid (captured
- // as a log even on abort); once dispose() resolves, that pid must be dead
- // (process.kill(pid, 0) throws ESRCH).
- const { fiber, runtime } = await setup({ maxWallMs: 10_000, graceMs: 400 })
- // Deterministic readiness: the program reports its pid through a binding
- // AFTER installing the trap, so dispose cannot race the spawn (a fixed
- // sleep lost that race on slow CI runners — SIGTERM landed pre-trap).
- let reportedPid!: (pid: number) => void
- const trapReady = new Promise<number>((resolve) => { reportedPid = resolve })
- const pending = runtime.run({
- program: [
- 'import signal, time, os',
- 'signal.signal(signal.SIGTERM, lambda *a: None)',
- 'await tools.ready({"pid": os.getpid()})',
- 'while True: time.sleep(0.05)',
- ].join('\n'),
- bindings: tools({
- ready: async (args) => {
- reportedPid((args as { pid: number }).pid)
- return 'ok'
- },
- }),
- })
- const pid = await trapReady
- const start = Date.now()
- await fiber.dispose()
- const elapsed = Date.now() - start
- const result = await pending
- expect(['abort', 'worker-exit', 'timeout']).toContain(result.error?.kind)
- // dispose() returned only after the grace window elapsed (the SIGTERM trap
- // forces the SIGKILL backstop path), proving the run stayed live past finish().
- expect(elapsed).toBeGreaterThanOrEqual(300)
- expect(Number.isInteger(pid) && pid > 0).toBe(true)
- // The child is fully reaped by the time dispose() resolved.
- expect(() => process.kill(pid, 0)).toThrow(/ESRCH/)
- }, 8000)
- it('settles on the decided result even when a setsid-escaped orphan holds stdio open past close', async () => {
- // `close` only fires once every inherited stdio stream drains. A descendant
- // started with start_new_session=True escapes the child's process group, so
- // the SIGTERM/SIGKILL aimed at that group never reaches it; if it inherited
- // our stdout/stderr/fd 3 and outlives the run, `close` would never fire and
- // run() would hang forever. The close-deadline backstop (graceMs + margin)
- // must force settlement on the value the `done` frame already decided.
- const { runtime } = await setup({ graceMs: 100 })
- const start = Date.now()
- const result = await runtime.run({
- program: [
- 'import subprocess, sys',
- // Orphan in a fresh session, inheriting our stdout/stderr/fd 3, alive
- // past the close-deadline so `close` cannot fire on its own. Its own
- // 5 s self-exit is the leak ceiling AND the discriminator: it must stay
- // ABOVE the < 4000 ms upper-bound assertion below, so if the deadline
- // backstop failed to settle, settlement could only come from this
- // self-exit at ~5 s and blow the bound — a sharper signal than the wall
- // ceiling would give.
- 'subprocess.Popen([sys.executable, "-c", "import time; time.sleep(5)"],',
- ' start_new_session=True)',
- 'return "escaped"',
- ].join('\n'),
- bindings: [],
- })
- const elapsed = Date.now() - start
- // The done frame decided the value; the deadline settled it despite the
- // orphan pinning the pipes open.
- expect(result.error).toBeUndefined()
- expect(result.value).toBe('escaped')
- // Settlement waited for the backstop (graceMs + CLOSE_REAP_MARGIN_MS ≈ 2.1s),
- // not the orphan's 5 s self-exit — proving the deadline, not a fallback, fired.
- expect(elapsed).toBeGreaterThanOrEqual(1_500)
- expect(elapsed).toBeLessThan(4_000)
- }, 8000)
- it('flushes a newline-free diagnostic when the closeDeadline forces settlement', async () => {
- // A leader that writes an unterminated diagnostic via `os.write(1, ...)` and
- // then exits, leaving a setsid orphan holding the pipes open, settles through
- // the closeDeadline destroy() path — which fires no `end`. The residual must
- // be flushed before destroy() drops it, or the diagnostic is lost from
- // `logs`. The value is decided by the done frame; the diagnostic must survive.
- const { runtime } = await setup({ graceMs: 100 })
- const result = await runtime.run({
- program: [
- 'import os, subprocess, sys',
- 'os.write(1, b"leader-diagnostic-no-newline")',
- 'subprocess.Popen([sys.executable, "-c", "import time; time.sleep(5)"],',
- ' start_new_session=True)',
- 'return "escaped"',
- ].join('\n'),
- bindings: [],
- })
- expect(result.error).toBeUndefined()
- expect(result.value).toBe('escaped')
- expect(result.logs).toContain('leader-diagnostic-no-newline')
- }, 8000)
- it('reaps a same-group child that ignores SIGTERM and releases the pipes before close', async () => {
- // The same-group counterpart to the setsid-orphan case above. A descendant
- // left in the child's OWN process group (no setsid, so `kill(-pid)` reaches
- // it) can ignore SIGTERM yet still release the inherited stdout/stderr/fd 3
- // it does not hold — here by giving the Popen child DEVNULL streams and
- // letting close_fds drop fd 3. The leader then writes `done` and exits, its
- // `close` fires because the pipes drained, and settle() runs while that
- // descendant is still alive. settle() then keeps a REF'd poll alive until the
- // grace-window SIGKILL has emptied the whole process group, so the host cannot
- // exit and reparent the survivor to init: no subprocess outlives the fiber.
- //
- // The descendant must have SIG_IGN installed BEFORE the host sends SIGTERM,
- // or it dies from the default SIGTERM whether the fix is present or not — so
- // it writes a readiness marker after trapping and the leader waits for that
- // marker before returning. While alive it bumps a heartbeat file every 50 ms;
- // the test asserts the heartbeat STOPS, which is what "no longer executing"
- // means whether the killed descendant is reaped or lingers as a zombie (a
- // SIGKILL'd process runs no more code either way). It sleeps 30 s as a safety
- // net so a broken fix cannot leak it forever.
- const handoff = await mkdtemp(join(tmpdir(), 'dsh-samegroup-'))
- const readyMarker = join(handoff, 'ready')
- const heartbeat = join(handoff, 'heartbeat')
- const { runtime } = await setup({ maxWallMs: 10_000, graceMs: 300 })
- const result = await runtime.run({
- program: [
- 'import subprocess, sys, os, time',
- `marker = ${JSON.stringify(readyMarker)}`,
- `heartbeat = ${JSON.stringify(heartbeat)}`,
- // Same group (no start_new_session); ignores SIGTERM; holds none of the
- // leader's pipes (DEVNULL std streams, close_fds drops fd 3). It writes
- // the marker (argv[1]) only AFTER the trap is installed — so the leader
- // cannot return, and the host cannot send SIGTERM, before it is ignored —
- // then rewrites the heartbeat (argv[2]) every 50 ms for up to 30 s.
- 'code = ("import signal, sys, time\\n"',
- ' "signal.signal(signal.SIGTERM, signal.SIG_IGN)\\n"',
- ' "open(sys.argv[1], \'w\').close()\\n"',
- ' "end = time.time() + 30\\n"',
- ' "while time.time() < end:\\n"',
- ' " open(sys.argv[2], \'w\').close()\\n"',
- ' " time.sleep(0.05)\\n")',
- 'child = subprocess.Popen([sys.executable, "-c", code, marker, heartbeat],',
- ' stdin=subprocess.DEVNULL,',
- ' stdout=subprocess.DEVNULL,',
- ' stderr=subprocess.DEVNULL)',
- 'deadline = time.time() + 5',
- 'while not os.path.exists(marker) and time.time() < deadline:',
- ' time.sleep(0.02)',
- 'return "spawned"',
- ].join('\n'),
- bindings: [],
- })
- expect(result.error).toBeUndefined()
- expect(result.value).toBe('spawned')
- // The trap really installed before the leader returned, so this is the
- // SIGTERM-ignoring descendant, not one that would have died to the default.
- expect(existsSync(readyMarker)).toBe(true)
- // The grace-window SIGKILL (graceMs 300 + reap margin) empties the group. Once
- // it has, the descendant stops bumping the heartbeat. Poll the heartbeat's
- // mtime: two consecutive reads far enough apart with no change means it is no
- // longer executing — true whether it was reaped or lingers as a zombie, so
- // the assertion holds in a container whose init does not wait() orphans. The
- // window (well under the 30 s self-timeout) proves the SIGKILL did the work.
- const mtime = (): number => { try { return statSync(heartbeat).mtimeMs } catch { return 0 } }
- const stopDeadline = Date.now() + 8_000
- let last = mtime()
- let still = false
- while (Date.now() < stopDeadline) {
- await new Promise(resolve => setTimeout(resolve, 400))
- const now = mtime()
- if (now === last && now !== 0) { still = true; break }
- last = now
- }
- expect(still).toBe(true)
- }, 20_000)
- it('dispose awaits reaping of a same-group survivor from a completed run', async () => {
- // The quiescence contract also holds for a run that ALREADY resolved: the run
- // stays tracked in `live` until its process group is reaped, so a `dispose()`
- // that races a just-returned run() still awaits the survivor rather than
- // snapshotting an empty `live` and returning while it lives. Here the run
- // completes (leaving a SIGTERM-ignoring same-group descendant), then dispose()
- // is called; the heartbeat must be stale BY THE TIME dispose() resolves —
- // proving teardown waited for the reap, not merely that the reap eventually
- // happened.
- const handoff = await mkdtemp(join(tmpdir(), 'dsh-dispose-quiesce-'))
- const readyMarker = join(handoff, 'ready')
- const heartbeat = join(handoff, 'heartbeat')
- const { runtime, fiber } = await setup({ maxWallMs: 10_000, graceMs: 300 })
- const result = await runtime.run({
- program: [
- 'import subprocess, sys, os, time',
- `marker = ${JSON.stringify(readyMarker)}`,
- `heartbeat = ${JSON.stringify(heartbeat)}`,
- 'code = ("import signal, sys, time\\n"',
- ' "signal.signal(signal.SIGTERM, signal.SIG_IGN)\\n"',
- ' "open(sys.argv[1], \'w\').close()\\n"',
- ' "end = time.time() + 30\\n"',
- ' "while time.time() < end:\\n"',
- ' " open(sys.argv[2], \'w\').close()\\n"',
- ' " time.sleep(0.05)\\n")',
- 'child = subprocess.Popen([sys.executable, "-c", code, marker, heartbeat],',
- ' stdin=subprocess.DEVNULL,',
- ' stdout=subprocess.DEVNULL,',
- ' stderr=subprocess.DEVNULL)',
- 'deadline = time.time() + 5',
- 'while not os.path.exists(marker) and time.time() < deadline:',
- ' time.sleep(0.02)',
- 'return "spawned"',
- ].join('\n'),
- bindings: [],
- })
- expect(result.error).toBeUndefined()
- expect(existsSync(readyMarker)).toBe(true)
- // dispose() must not return until the group is reaped. After it resolves, the
- // heartbeat must already be stale: read its mtime, wait past the heartbeat
- // interval, and confirm it did not advance — the descendant is no longer
- // executing (reaped or zombie), so teardown was genuinely quiescent.
- await fiber.dispose()
- const mtime = (): number => { try { return statSync(heartbeat).mtimeMs } catch { return 0 } }
- const afterDispose = mtime()
- // Pin the assertion to a heartbeat that actually ran: mtime() returns 0 when
- // the file never existed, so without this the `toBe` below would pass
- // vacuously (0 === 0) if the survivor never wrote a heartbeat at all.
- expect(afterDispose).toBeGreaterThan(0)
- await new Promise(resolve => setTimeout(resolve, 500))
- expect(mtime()).toBe(afterDispose)
- }, 20_000)
- it('sends SIGKILL at the poll deadline when the event loop was blocked past both timers', async () => {
- // If the host event loop is blocked (a big synchronous computation) from
- // before the group-reap poll was scheduled until after the deadline, both the
- // poll timer and the grace-window SIGKILL timer are overdue when the loop
- // resumes. Node runs the earlier-scheduled poll first, so the SIGKILL timer
- // may not have fired yet. The deadline arm must then send SIGKILL ITSELF
- // rather than cancel the unfired escalation — otherwise a SIGTERM-ignoring
- // same-group survivor is released for good. A synchronous busy-loop after
- // run() resolves reproduces the block deterministically.
- const handoff = await mkdtemp(join(tmpdir(), 'dsh-deadline-'))
- const readyMarker = join(handoff, 'ready')
- const heartbeat = join(handoff, 'heartbeat')
- const graceMs = 300
- const { runtime } = await setup({ maxWallMs: 10_000, graceMs })
- const result = await runtime.run({
- program: [
- 'import subprocess, sys, os, time',
- `marker = ${JSON.stringify(readyMarker)}`,
- `heartbeat = ${JSON.stringify(heartbeat)}`,
- 'code = ("import signal, sys, time\\n"',
- ' "signal.signal(signal.SIGTERM, signal.SIG_IGN)\\n"',
- ' "open(sys.argv[1], \'w\').close()\\n"',
- ' "end = time.time() + 30\\n"',
- ' "while time.time() < end:\\n"',
- ' " open(sys.argv[2], \'w\').close()\\n"',
- ' " time.sleep(0.05)\\n")',
- 'child = subprocess.Popen([sys.executable, "-c", code, marker, heartbeat],',
- ' stdin=subprocess.DEVNULL,',
- ' stdout=subprocess.DEVNULL,',
- ' stderr=subprocess.DEVNULL)',
- 'deadline = time.time() + 5',
- 'while not os.path.exists(marker) and time.time() < deadline:',
- ' time.sleep(0.02)',
- 'return "spawned"',
- ].join('\n'),
- bindings: [],
- })
- expect(result.error).toBeUndefined()
- expect(existsSync(readyMarker)).toBe(true)
- // Block the event loop synchronously past graceMs + CLOSE_REAP_MARGIN_MS
- // (2000) with margin, so both timers are overdue when the loop resumes.
- const blockUntil = Date.now() + graceMs + 2_000 + 800
- while (Date.now() < blockUntil) { /* busy-wait, no yield */ }
- // Yield: the overdue poll runs (group still non-empty, deadline passed) and
- // must send SIGKILL itself. The survivor then stops bumping the heartbeat.
- const mtime = (): number => { try { return statSync(heartbeat).mtimeMs } catch { return 0 } }
- const stopDeadline = Date.now() + 5_000
- let last = mtime()
- let stopped = false
- while (Date.now() < stopDeadline) {
- await new Promise(resolve => setTimeout(resolve, 400))
- const now = mtime()
- if (now === last && now !== 0) { stopped = true; break }
- last = now
- }
- expect(stopped).toBe(true)
- }, 20_000)
- })
- describe('PythonCodeRuntime — hostile peer', () => {
- it('drops garbage bytes and unknown-shape frames posted directly to fd 3', async () => {
- // The model program can reach fd 3 and write anything. We inject a
- // non-JSON line, a valid JSON but unknown-shape frame, and a broken done
- // frame; the host must not crash, and the real `done` still settles the run.
- const { runtime } = await setup()
- const result = await runtime.run({
- program: [
- 'import os',
- 'os.write(3, b"not-json\\n")',
- 'os.write(3, b\'{"type":"unknown"}\\n\')',
- 'os.write(3, b\'{"type":"done","error":{"message":42}}\\n\')',
- 'return "survived"',
- ].join('\n'),
- bindings: [],
- })
- expect(result.error).toBeUndefined()
- expect(result.value).toBe('survived')
- })
- it('answers a forged call frame for an unknown binding and never crashes', async () => {
- // The unknown-binding reply path, driven through the id the host expects:
- // the program lets its own first call claim id 0 and forges id 1, which the
- // host answers with the `unknown binding` rejection the honest call would
- // have received. A forged id out of sequence is dropped instead — that is
- // the id-bound test below, not this one.
- const { runtime } = await setup({ maxWallMs: 8_000 })
- let seenLegitCall = false
- const result = await runtime.run({
- program: [
- 'import os, json',
- 'x = await tools.echo({"ping": True})',
- 'os.write(3, json.dumps({"type":"call","id":1,"global":"tools","name":"forged","args":{}}).encode() + b"\\n")',
- // The forged frame is answered, but nothing in the child awaits id 1, so
- // the reply is ignored and the run completes on its own value.
- 'return x',
- ].join('\n'),
- bindings: tools({
- echo: async (args) => { seenLegitCall = true; return args as CodeJsonValue },
- }),
- })
- expect(result.error).toBeUndefined()
- expect(result.value).toEqual({ ping: true })
- expect(seenLegitCall).toBe(true)
- }, 15_000)
- it('drops forged call frames whose ids are not the next in sequence, retaining no per-id state', async () => {
- // The host used to remember every answered id in a Set, so a program could
- // write an unbounded run of unique forged ids — each frame far below the
- // 256 MiB ceiling, so nothing rejected them — and grow host memory for the
- // whole run. Ids are consecutive from 0, so one counter replaces the set.
- //
- // The discriminator is that the forgeries must not be answered. Each names a
- // binding that does exist, so a host answering them would run `echo` once
- // per forgery; the count proves only the legitimate call was dispatched.
- // Ids also run DESCENDING, so a high-water-mark test would drop the honest
- // call that follows rather than the forgeries.
- const { runtime } = await setup()
- let echoCalls = 0
- const result = await runtime.run({
- program: [
- 'import os, json',
- 'for i in range(2000, 0, -1):',
- ' os.write(3, json.dumps({"type":"call","id":i,"global":"tools","name":"echo","args":{"forged":i}}).encode() + b"\\n")',
- 'x = await tools.echo({"ping": True})',
- 'return x',
- ].join('\n'),
- bindings: tools({
- echo: async (args) => { echoCalls += 1; return args as CodeJsonValue },
- }),
- })
- expect(result.error).toBeUndefined()
- expect(result.value).toEqual({ ping: true })
- expect(echoCalls).toBe(1)
- }, 15_000)
- it('keeps answering calls a program makes after one with unserializable arguments', async () => {
- // The child claims an id only once its write succeeds, so a call rejected
- // child-side for non-lossless arguments leaves no gap. Were a gap possible,
- // the host's exact-successor test would drop every later call and the run
- // would hang to the wall ceiling instead of completing.
- const { runtime } = await setup({ maxWallMs: 8_000 })
- const seen: unknown[] = []
- const result = await runtime.run({
- program: [
- 'caught = ""',
- 'try:',
- ' await tools.echo({"bad": float("inf")})',
- 'except RuntimeError as e:',
- ' caught = str(e)',
- 'after = await tools.echo({"ok": True})',
- 'return {"caught": caught, "after": after}',
- ].join('\n'),
- bindings: tools({
- echo: async (args) => { seen.push(args); return args as CodeJsonValue },
- }),
- })
- expect(result.error).toBeUndefined()
- const value = result.value as { caught: string; after: unknown }
- expect(value.caught).toContain('lossless JSON')
- expect(value.after).toEqual({ ok: true })
- // The rejected call never reached the host; the one after it did.
- expect(seen).toEqual([{ ok: true }])
- }, 15_000)
- it('drops a forged frame carrying an integer outside JavaScript safe range', async () => {
- // JSON.parse would silently round 9007199254740993 to ...992 BEFORE any
- // validation, corrupting a dispatched argument or completion. The host
- // scans the raw line and drops such frames as hostile traffic; the honest
- // child cannot produce one (its validator rejects unsafe ints).
- const { runtime } = await setup()
- let dispatched: unknown
- const result = await runtime.run({
- program: [
- 'import os',
- // Forged call frame with an unsafe int argument, then a forged done
- // frame with an unsafe int value — both must be dropped whole.
- 'os.write(3, b\'{"type":"call","id":7,"global":"tools","name":"echo","args":9007199254740993}\\n\')',
- 'os.write(3, b\'{"type":"done","value":9007199254740993}\\n\')',
- 'x = await tools.echo({"ok": True})',
- 'return x',
- ].join('\n'),
- bindings: tools({
- echo: async (args) => { dispatched = args; return args as CodeJsonValue },
- }),
- })
- expect(result.error).toBeUndefined()
- // The forged done did not settle the run; the legit call and completion did.
- expect(result.value).toEqual({ ok: true })
- expect(dispatched).toEqual({ ok: true })
- })
- it('truncates host-side logs once the budget is exhausted and emits the marker', async () => {
- // Set a tiny host-side budget; the Python side has a much larger one, so
- // its LogBuffer will not truncate — the host ledger fires first.
- const { runtime } = await setup({ maxLogBytes: 32 })
- const result = await runtime.run({
- program: [
- 'for _ in range(50):',
- ' print("aaaaaaaaaa")',
- 'return "done"',
- ].join('\n'),
- bindings: [],
- })
- expect(result.error).toBeUndefined()
- const markers = result.logs.filter(line => line.includes('log capture truncated at 32 bytes'))
- expect(markers.length).toBeGreaterThanOrEqual(1)
- })
- it('reports an exception whose message holds an unpaired surrogate instead of stranding to the wall clock', async () => {
- // A strict UTF-8 encode of "\ud800" throws while BUILDING the failure
- // frame; the run would then hang to maxWallMs and misreport as timeout.
- const { runtime } = await setup({ maxWallMs: 8_000 })
- const result = await runtime.run({
- program: String.raw`raise Exception("bad \ud800 surrogate")`,
- bindings: [],
- })
- expect(result.error?.kind).toBe('exception')
- expect(result.error?.message).toContain('bad')
- expect(result.error?.message).toContain('surrogate')
- })
- it('carries a lone-surrogate completion string across the wire as its JSON escape', async () => {
- // UTF-8 has no encoding for a lone surrogate, but JSON does: the ASCII
- // `\ud800` escape, which JSON.parse reads back as the same UTF-16 code
- // unit. `CodeJsonValue`, `snapshotJsonValue`, and the worker backend all
- // accept such a string, so this backend must not narrow the shared seam.
- const { runtime } = await setup()
- const result = await runtime.run({
- program: String.raw`return {"lone": "a\ud800b", "spelled": "😀"}`,
- bindings: [],
- })
- expect(result.error).toBeUndefined()
- // The lone half survives as the code unit itself; a spelled-out high-low
- // PAIR folds into the astral character the host would hold for it.
- expect(result.value).toEqual({ lone: 'a\ud800b', spelled: '\u{1f600}' })
- })
- it('meters a lone surrogate at its six escaped bytes, matching the host', async () => {
- // The child and the host share maxValueBytes, so the child must charge the
- // escape's six ASCII bytes (plus two quotes): eight fits, nine does not.
- const { runtime } = await setup({ maxValueBytes: 8 })
- const ok = await runtime.run({ program: String.raw`return "\ud800"`, bindings: [] })
- expect(ok.error).toBeUndefined()
- expect(ok.value).toBe('\ud800')
- const over = await setup({ maxValueBytes: 7 })
- const result = await over.runtime.run({ program: String.raw`return "\ud800"`, bindings: [] })
- expect(result.error?.kind).toBe('output-limit')
- })
- it('passes a lone-surrogate binding argument through instead of failing the call', async () => {
- // The argument validator shared the same over-narrow rejection; a host
- // binding must receive the code unit the program passed.
- const seen: unknown[] = []
- const { runtime } = await setup()
- const result = await runtime.run({
- program: String.raw`return await tools.echo({"text": "x\udfff"})`,
- bindings: tools({ echo: async (args: unknown) => { seen.push(args); return args as CodeJsonValue } }),
- })
- expect(result.error).toBeUndefined()
- expect(seen).toEqual([{ text: 'x\udfff' }])
- expect(result.value).toEqual({ text: 'x\udfff' })
- })
- it('meters a non-ASCII completion in UTF-8 JSON bytes, matching the host', async () => {
- // json.dumps' default \uXXXX escaping would count "é" as 8 bytes while
- // the host meter counts its UTF-8 JSON form (4); the shared budget must
- // agree, so a 4-byte-fitting value passes a maxValueBytes of 4.
- const { runtime } = await setup({ maxValueBytes: 4 })
- const ok = await runtime.run({ program: 'return "é"', bindings: [] })
- expect(ok.error).toBeUndefined()
- expect(ok.value).toBe('é')
- const over = await runtime.run({ program: 'return "éx"', bindings: [] })
- expect(over.error?.kind).toBe('output-limit')
- })
- it('filters bootstrap frames from exception-group members (TaskGroup)', async () => {
- // Python 3.11+ stores member stacks under TracebackException.exceptions;
- // the <model>-frame filter must recurse into them too.
- const { runtime } = await setup()
- const result = await runtime.run({
- program: [
- 'import asyncio, sys',
- 'if sys.version_info < (3, 11):',
- ' raise ValueError("skip-old <model>")',
- 'async def boom():',
- ' raise ValueError("group-member")',
- 'async with asyncio.TaskGroup() as tg:',
- ' tg.create_task(boom())',
- ].join('\n'),
- bindings: [],
- })
- expect(result.error?.kind).toBe('exception')
- expect(result.error?.message).toContain('<model>')
- expect(result.error?.message).not.toContain('bootstrap.py')
- })
- it('keeps frames intact when a model thread floods logs while a large frame drains', async () => {
- // os.write releases the GIL and a frame beyond PIPE_BUF is not atomic:
- // without the writer lock + full-write loop, the printing thread could
- // interleave bytes mid-frame and the host would drop the malformed JSON,
- // hanging the run to the wall clock (or losing the completion).
- const { runtime } = await setup({ maxValueBytes: 1024 * 1024, maxLogBytes: 4 * 1024 * 1024, maxWallMs: 15_000 })
- const result = await runtime.run({
- program: [
- 'import threading',
- 'stop = False',
- 'def spam():',
- ' while not stop:',
- ' print("spam-line-" + "y" * 100)',
- 't = threading.Thread(target=spam)',
- 't.start()',
- // A ~300 KiB completion — several PIPE_BUF units — while spam runs.
- 'big = "x" * (300 * 1024)',
- 'stop = True',
- 't.join()',
- 'return big',
- ].join('\n'),
- bindings: [],
- })
- expect(result.error).toBeUndefined()
- expect(result.value).toBe('x'.repeat(300 * 1024))
- }, 20_000)
- it('settles cleanly while a daemon thread keeps writing unterminated log text', async () => {
- // WARNING regression: the settlement `flush_out()/flush_err()` on the main
- // coroutine read and clear `_LogStream._pending` and the shared LogBuffer
- // ledger with NO lock, while a model daemon thread's `print`/`write` mutate
- // the same state. Capturing the bound method (`out_stream.flush_line`) only
- // fixes WHICH callable runs, not what it reads mid-flight: the flush could
- // interleave with a concurrent write and join a `_pending` list being
- // mutated under it, corrupting the ledger and costing the `done` frame — the
- // run would then strand to the wall clock instead of completing. The shared
- // re-entrant lock serializes them.
- //
- // A pure data race has no single bad input to reject deterministically, so
- // this maximizes overlap: daemon threads emit UNTERMINATED writes (which
- // pile into `_pending` rather than flushing per line) right up to the moment
- // the body returns and settlement flushes. Repeated so the interleave lands.
- for (let attempt = 0; attempt < 5; attempt++) {
- const { runtime, fiber } = await setup({ maxLogBytes: 4 * 1024 * 1024, maxWallMs: 15_000 })
- const result = await runtime.run({
- program: [
- 'import sys, threading',
- 'stop = False',
- 'def spam():',
- ' while not stop:',
- // No newline: the text accumulates in the stream's `_pending`, which is
- // exactly the state the settlement flush also touches.
- ' sys.stdout.write("tail-fragment-" + "z" * 64)',
- 'workers = [threading.Thread(target=spam, daemon=True) for _ in range(4)]',
- 'for t in workers: t.start()',
- // Let the daemons build up pending writes, then return so settlement
- // flushes while they are still mid-write.
- 'import time; time.sleep(0.05)',
- 'return "settled"',
- ].join('\n'),
- bindings: [],
- })
- expect(result.error).toBeUndefined()
- expect(result.value).toBe('settled')
- await fiber.dispose()
- }
- }, 30_000)
- it('completes a binding called from a worker thread on its own event loop', async () => {
- // A binding reply Future is created on the loop that ran `dispatch`. When the
- // model calls a binding from a worker THREAD via `asyncio.run(tools.x(...))`,
- // that Future belongs to the thread's loop, not the main loop where
- // `_pump_replies` reads the reply. `asyncio.Future` is not thread-safe:
- // completing it from another thread does not wake its own loop, so a direct
- // `set_result` would strand the awaiting thread and the run would degrade to a
- // wall-clock timeout. The pump must schedule completion on the Future's own
- // loop via `call_soon_threadsafe`. The tight maxWallMs makes the pre-fix
- // failure a fast timeout rather than a hang.
- //
- // The main coroutine yields with `await asyncio.sleep` while the worker runs,
- // rather than a synchronous `t.join()`: joining would block the main thread,
- // so the main loop could not run `_pump_replies` and the call would deadlock
- // regardless of the fix — that blocks the pump, not the cross-loop delivery
- // this test pins.
- const { runtime } = await setup({ maxWallMs: 8_000 })
- const seen: unknown[] = []
- const result = await runtime.run({
- program: [
- 'import asyncio, threading',
- 'result = {}',
- 'def worker():',
- // A fresh loop in this thread; the binding Future is created here.
- ' result["value"] = asyncio.run(tools.echo({"from": "thread"}))',
- 't = threading.Thread(target=worker)',
- 't.start()',
- 'while t.is_alive():',
- ' await asyncio.sleep(0.02)',
- 'return result["value"]',
- ].join('\n'),
- bindings: tools({
- echo: async (args) => { seen.push(args); return args as CodeJsonValue },
- }),
- })
- expect(result.error).toBeUndefined()
- expect(result.value).toEqual({ from: 'thread' })
- // The host binding actually ran (the reply round-tripped), not a timeout.
- expect(seen).toEqual([{ from: 'thread' }])
- }, 15_000)
- it('keeps the reply pump alive when a late reply targets a closed thread loop', async () => {
- // A binding called from a worker thread that ABANDONS the call (its
- // `asyncio.run` is cancelled) leaves the pending entry holding that thread's
- // loop, which `asyncio.run` closes on return. When the host later answers
- // that call, `_pump_replies` schedules the completion onto the closed loop —
- // `call_soon_threadsafe` raises `RuntimeError('Event loop is closed')`.
- // Unguarded, that RuntimeError ends the pump task and strands every later
- // reply; the guard drops the moot reply and keeps the pump serving.
- //
- // The ordering is a STRUCTURAL guarantee, not a timing window: the worker
- // closes its loop before the main coroutine signals `closed`; the host
- // answers the abandoned `slow` call (hitting the closed loop) before it
- // answers `release`, because `release`'s handler only resolves `slow` first
- // and then yields a microtask. So the pump provably meets the closed loop on
- // `slow`'s reply before it must deliver `release`'s. Fail-before: the pump
- // dies on `slow`, `release`'s reply is never read, and `await tools.release`
- // hangs to the (small) maxWallMs as a timeout.
- let releaseSlow!: () => void
- const slowGate = new Promise<void>((resolve) => { releaseSlow = resolve })
- const { runtime } = await setup({ maxWallMs: 6_000 })
- const result = await runtime.run({
- program: [
- 'import asyncio, threading',
- 'closed = threading.Event()',
- 'def worker():',
- ' async def body():',
- // Abandon the call: wait_for cancels it, but the pending host-side entry
- // survives (dispatch does not pop on cancellation), holding this loop.
- ' try:',
- ' await asyncio.wait_for(tools.slow({}), timeout=0.1)',
- ' except asyncio.TimeoutError:',
- ' pass',
- ' asyncio.run(body())', // closes the thread's loop on return
- ' closed.set()',
- 't = threading.Thread(target=worker)',
- 't.start()',
- 'while not closed.is_set():',
- ' await asyncio.sleep(0.02)',
- // The loop is closed. Now the host answers slow (dead-loop reply) then
- // release; the pump must survive the first to deliver the second.
- 'after = await tools.release({})',
- 'return after',
- ].join('\n'),
- bindings: tools({
- slow: async () => {
- // Answer only once the worker has closed its loop AND the main
- // coroutine is awaiting release, so this reply reaches the pump against
- // the closed loop.
- await slowGate
- return 'late'
- },
- release: async () => {
- // Let slow's reply be written first, then yield a microtask so the
- // pump processes the dead-loop reply before release's own reply lands.
- releaseSlow()
- await new Promise(resolve => setImmediate(resolve))
- return 'released'
- },
- }),
- })
- expect(result.error).toBeUndefined()
- // The pump survived the closed-loop reply and delivered the later binding.
- expect(result.value).toBe('released')
- }, 15_000)
- it('round-trips an exactly representable large integer through a binding echo', async () => {
- // The reply serializer must print BigInt digits for a beyond-safe
- // integral double: String(2**60) emits a rounded form, and the child
- // would receive a DIFFERENT integer than the binding resolved.
- const { runtime } = await setup()
- const result = await runtime.run({
- program: [
- 'v = await tools.echo(2**60)',
- 'return v == 2**60',
- ].join('\n'),
- bindings: tools({ echo: async args => args as never }),
- })
- expect(result.error).toBeUndefined()
- expect(result.value).toBe(true)
- })
- it('preserves an exactly representable large integer and rejects a rounding one', async () => {
- // The canonical boundary accepts every JS-double-exact value: 2**53 and
- // 2**60 round-trip exactly and must cross (matching the worker backend);
- // 2**53+1 rounds and must fail as invalid-output.
- const { runtime } = await setup()
- const exact = await runtime.run({ program: 'return [2**53, 2**60]', bindings: [] })
- expect(exact.error).toBeUndefined()
- expect(exact.value).toEqual([2 ** 53, 2 ** 60])
- const lossy = await runtime.run({ program: 'return 2**53 + 1', bindings: [] })
- expect(lossy.error?.kind).toBe('invalid-output')
- expect(lossy.error?.message).toContain('not exactly representable')
- })
- it('rejects a container subclass whose overridden methods hide its contents', async () => {
- // A dict subclass returning [] from items() passes an isinstance check but
- // serializes as {}, so the host would receive a value the program did not
- // compute. Exact-type matching fails it as invalid-output instead. The
- // worker backend rejects the prototype-equivalent shapes the same way.
- const { runtime } = await setup()
- const hidden = await runtime.run({
- program: [
- 'class Sneaky(dict):',
- ' def items(self): return []',
- ' def keys(self): return []',
- ' def __iter__(self): return iter([])',
- ' def __len__(self): return 0',
- 'return Sneaky(secret="kept")',
- ].join('\n'),
- bindings: [],
- })
- expect(hidden.error?.kind).toBe('invalid-output')
- expect(hidden.error?.message).toContain('unsupported type (Sneaky)')
- // A list subclass is refused on the same rule.
- const listish = await runtime.run({
- program: ['class L(list):', ' def __iter__(self): return iter([])', 'return L([1, 2, 3])'].join('\n'),
- bindings: [],
- })
- expect(listish.error?.kind).toBe('invalid-output')
- expect(listish.error?.message).toContain('unsupported type (L)')
- // The exact built-in containers still cross unchanged.
- const plain = await runtime.run({ program: 'return {"secret": [1, 2]}', bindings: [] })
- expect(plain.error).toBeUndefined()
- expect(plain.value).toEqual({ secret: [1, 2] })
- })
- it('rejects a scalar subclass whose overrides disagree with what gets serialized', async () => {
- // The validators checked scalars with isinstance, so a subclass passed
- // every check by its real value while the ENCODER read an override — the
- // host then received a value the walk never approved. Each case below is a
- // distinct override reaching a distinct reader.
- const { runtime } = await setup()
- // _dump_float spells a float from repr(value), so an overridden __repr__
- // decides the digits: F(2.5) serialized as 1.
- const floated = await runtime.run({
- program: [
- 'class F(float):',
- ' def __repr__(self): return "1.0"',
- 'return F(2.5)',
- ].join('\n'),
- bindings: [],
- })
- expect(floated.error?.kind).toBe('invalid-output')
- expect(floated.error?.message).toContain('unsupported type (F)')
- // The JS-safe-range bound is two comparisons, so overriding them admits an
- // int whose true digits (json.dumps reads the C-level value) the host's
- // JSON.parse rounds: 9007199254740993 arrives as ...992.
- const inted = await runtime.run({
- program: [
- 'class I(int):',
- ' def __gt__(self, other): return False',
- ' def __lt__(self, other): return False',
- 'return I(2 ** 53 + 1)',
- ].join('\n'),
- bindings: [],
- })
- expect(inted.error?.kind).toBe('invalid-output')
- expect(inted.error?.message).toContain('unsupported type (I)')
- // The pre-encode size bound reads len(), so overriding it to 0 admits a
- // string of any length past maxValueBytes.
- const stringed = await runtime.run({
- program: [
- 'class S(str):',
- ' def __len__(self): return 0',
- 'return S("Q" * 100000)',
- ].join('\n'),
- bindings: [],
- })
- expect(stringed.error?.kind).toBe('invalid-output')
- expect(stringed.error?.message).toContain('unsupported type (S)')
- // A str-subclass dict KEY reaches the same len() bound.
- const keyed = await runtime.run({
- program: [
- 'class S(str):',
- ' def __len__(self): return 0',
- 'return {S("Q" * 100000): 1}',
- ].join('\n'),
- bindings: [],
- })
- expect(keyed.error?.kind).toBe('invalid-output')
- expect(keyed.error?.message).toContain('non-string dict key (S)')
- // bool is an int subclass that IS lossless JSON, and the exact scalars all
- // still cross unchanged.
- const plain = await runtime.run({
- program: 'return {"t": True, "f": False, "n": None, "i": 7, "d": 2.5, "s": "ok"}',
- bindings: [],
- })
- expect(plain.error).toBeUndefined()
- expect(plain.value).toEqual({ t: true, f: false, n: null, i: 7, d: 2.5, s: 'ok' })
- })
- it('rejects a scalar subclass passed as a binding argument', async () => {
- // The uncapped binding-argument validator shares the exact-type rule, so
- // the call fails through its rejection contract instead of dispatching a
- // float whose digits come from an override.
- const { runtime } = await setup()
- const seen: CodeJsonValue[] = []
- const result = await runtime.run({
- program: [
- 'class F(float):',
- ' def __repr__(self): return "1.0"',
- 'try:',
- ' await tools.echo({"v": F(2.5)})',
- 'except Exception as exc:',
- ' return str(exc)',
- ].join('\n'),
- bindings: tools({ echo: async (args) => {
- seen.push(args as CodeJsonValue)
- return null
- } }),
- })
- expect(result.error).toBeUndefined()
- expect(result.value).toContain('unsupported type (F)')
- expect(seen).toEqual([])
- })
- it('rejects a container subclass passed as a binding argument', async () => {
- // Binding arguments run the uncapped validator, which must apply the same
- // exact-type rule: the call fails descriptively instead of dispatching a
- // value whose serialization disagrees with what was validated.
- const { runtime } = await setup()
- const seen: CodeJsonValue[] = []
- const result = await runtime.run({
- program: [
- 'class Sneaky(dict):',
- ' def items(self): return []',
- 'try:',
- ' await tools.echo(Sneaky(secret="kept"))',
- 'except Exception as exc:',
- ' return str(exc)',
- ].join('\n'),
- bindings: tools({ echo: async (args) => {
- seen.push(args as CodeJsonValue)
- return null
- } }),
- })
- expect(result.error).toBeUndefined()
- expect(result.value).toContain('unsupported type (Sneaky)')
- expect(seen).toEqual([])
- })
- it('fails an oversized completion as output-limit without materializing its encoding', async () => {
- // A 100 MiB string under maxValueBytes: 1024 must fail as output-limit.
- // The address-space cap leaves room for the program to BUILD the string
- // (one copy + interpreter) but not for the old full pre-check encode,
- // which materialized chunk fragments plus the joined copy (~2 more
- // copies) and died on RLIMIT_AS as MemoryError/worker-exit.
- const { runtime } = await setup({ maxValueBytes: 1024, addressSpaceMb: 384, maxWallMs: 15_000 })
- const result = await runtime.run({
- program: 'return "x" * (100 * 1024 * 1024)',
- bindings: [],
- })
- expect(result.error?.kind).toBe('output-limit')
- expect(result.error?.message).toContain('exceeded 1024 bytes')
- }, 20_000)
- it('rejects a control-heavy oversized completion on its length, not its escaped copy', async () => {
- // Every "\x00" escapes to the six bytes "�", so the escaped form of a
- // 40 MB string is ~240 MB. The walk must refuse on the cheap
- // `len(current) + 2` lower bound; the 384 MiB address space holds the raw
- // string but not its escaped expansion, so a pre-escape check dies on
- // RLIMIT_AS instead of returning output-limit.
- const { runtime } = await setup({ maxValueBytes: 1024, addressSpaceMb: 384, maxWallMs: 15_000 })
- const result = await runtime.run({
- program: 'return "\\x00" * (40 * 1024 * 1024)',
- bindings: [],
- })
- expect(result.error?.kind).toBe('output-limit')
- expect(result.error?.message).toContain('exceeded 1024 bytes')
- }, 20_000)
- it('truncates a single print far above maxLogBytes instead of dying on the encode', async () => {
- // LogBuffer must reject via the cheap char-count lower bound BEFORE
- // UTF-8-encoding the whole string: the full encode of a ~100 MB line
- // would double the allocation and can breach RLIMIT_AS. 256 MiB
- // address space comfortably holds one copy of the 100 MB string but
- // not the pre-fix double allocation plus interpreter overhead spikes.
- const { runtime } = await setup({ maxLogBytes: 1024, addressSpaceMb: 256, maxWallMs: 15_000 })
- const result = await runtime.run({
- program: [
- 'print("x" * (100 * 1024 * 1024))',
- 'return "done"',
- ].join('\n'),
- bindings: [],
- })
- expect(result.error).toBeUndefined()
- expect(result.value).toBe('done')
- expect(result.logs.some(line => line.includes('log capture truncated'))).toBe(true)
- }, 20_000)
- it('stops host capture at the child ledger truncation, keeping exactly one marker', async () => {
- // The two ledgers exhaust independently. One child entry larger than
- // `maxLogBytes` sends ONLY the marker, so the host budget is still nearly
- // untouched — and the marker used to arrive as an ordinary `log` frame the
- // host could not tell from program output. Text written afterwards was
- // therefore retained AFTER the marker, contradicting the stop-after-
- // truncation contract, and a later host-side exhaustion could append a
- // second marker. The frame now carries `truncated: true`.
- //
- // `os.write(1, ...)` bypasses the child's own stream, so those bytes reach
- // the host as stray stdout and take the host ledger path rather than the
- // child's — which is exactly the route that leaked past the marker.
- const { runtime } = await setup({ maxLogBytes: 64, maxWallMs: 10_000 })
- const result = await runtime.run({
- program: [
- 'import os',
- 'print("y" * 70000)',
- 'os.write(1, b"AFTER")',
- 'return "done"',
- ].join('\n'),
- bindings: [],
- })
- expect(result.error).toBeUndefined()
- expect(result.value).toBe('done')
- const markers = result.logs.filter(line => line.includes('log capture truncated'))
- expect(markers).toHaveLength(1)
- // The marker is the LAST entry: nothing was retained after truncation.
- expect(result.logs.at(-1)).toBe(markers[0])
- expect(result.logs.join('\n')).not.toContain('AFTER')
- }, 20_000)
- it('keeps one marker when a program forges repeated truncation frames', async () => {
- // `truncated` is attacker-reachable: the program owns fd 3 and can write the
- // flag itself, so the field is a hostile input rather than a trusted signal.
- // Repeats must collapse to the single marker the contract promises, and only
- // the literal `true` counts — a forged `"yes"` is rebuilt away by
- // validateChildFrame, so that frame stays ordinary text.
- const { runtime } = await setup({ maxLogBytes: 4096, maxWallMs: 10_000 })
- const result = await runtime.run({
- program: [
- 'import os, json',
- 'os.write(3, json.dumps({"type":"log","text":"first","truncated":"yes"}).encode() + b"\\n")',
- 'os.write(3, json.dumps({"type":"log","text":"MARK-A","truncated":True}).encode() + b"\\n")',
- 'os.write(3, json.dumps({"type":"log","text":"MARK-B","truncated":True}).encode() + b"\\n")',
- 'return "done"',
- ].join('\n'),
- bindings: [],
- })
- expect(result.error).toBeUndefined()
- expect(result.value).toBe('done')
- // The non-boolean flag did not truncate, so its text was captured normally.
- expect(result.logs).toContain('first')
- // The first genuine flag stopped capture and emitted the HOST's own marker;
- // the frame's own text is discarded, so neither payload appears.
- expect(result.logs).not.toContain('MARK-A')
- expect(result.logs).not.toContain('MARK-B')
- expect(result.logs.at(-1)).toBe(logTruncationMarker(4096))
- expect(result.logs.filter(line => line.includes('log capture truncated'))).toHaveLength(1)
- }, 20_000)
- it('discards the text of a forged truncation frame instead of retaining it', async () => {
- // The marker branch bypasses `admit`, so retaining the frame's own text put
- // attacker-controlled bytes into `logs` with no cap at all: measured, a 1 MiB
- // forged text was retained whole under `maxLogBytes: 64`, and the only bound
- // left was the 256 MiB frame ceiling. The host emits its own marker instead,
- // so the retained size is fixed regardless of what the program sent.
- const forgedBytes = 1024 * 1024
- const { runtime } = await setup({ maxLogBytes: 64, maxWallMs: 20_000 })
- const result = await runtime.run({
- program: [
- 'import os, json',
- `big = "A" * ${forgedBytes}`,
- 'os.write(3, json.dumps({"type":"log","truncated":True,"text":big}).encode() + b"\\n")',
- 'return "done"',
- ].join('\n'),
- bindings: [],
- })
- expect(result.error).toBeUndefined()
- expect(result.value).toBe('done')
- // Only the host marker is kept, so the total stays orders of magnitude below
- // what the forgery carried — and below the cap it was trying to escape.
- expect(result.logs).toEqual([logTruncationMarker(64)])
- expect(result.logs.join('').length).toBeLessThan(forgedBytes / 1000)
- }, 30_000)
- it('coalesces unframed fd-3 fragments without recopying the sealed prefix', async () => {
- // The frame ceiling meters payload BYTES, but each retained chunk is its own
- // Buffer with object and backing-store overhead the byte count cannot see:
- // 5000 single-byte newline-free writes produced 5000 chunks holding 5031
- // bytes, so a program pacing such writes could accumulate millions of objects
- // inside the wall budget and exhaust the host heap far below 256 MiB.
- //
- // The observable behavior is that the run still completes normally: the
- // fragments are coalesced rather than rejected, since a slow trickle of bytes
- // is not itself a protocol violation.
- //
- // `Buffer.concat` is wrapped for the duration so the cumulative copy volume
- // is measured rather than inferred: that total is what separates sealing into
- // blocks from re-merging the whole buffer, and both shapes pass every
- // behavioral assertion below.
- //
- // The trickle is terminated with its own newline before the real frame is
- // written. Without that, those 5000 bytes prefix the frame on the SAME line,
- // which then parses as junk and is dropped — correct framing behavior, but it
- // would leave this test asserting the wrong thing.
- // Bound at capture: `Buffer.concat` is a static method, and taking a bare
- // reference to one trips no-unbound-method.
- const realConcat = Buffer.concat.bind(Buffer)
- let copied = 0
- Buffer.concat = (list: readonly Uint8Array[], total?: number): Buffer<ArrayBuffer> => {
- for (const part of list) copied += part.length
- return realConcat(list, total)
- }
- const program = [
- 'import os',
- // Newline-free single-byte writes, spaced so each lands as its own read.
- // 60000 rather than 5000: the trickle has to cross the seal threshold
- // enough times for the two shapes to separate. At 5000 writes there are
- // only four seals, so even the quadratic form copies well under a
- // megabyte and the budget below could not tell them apart.
- 'for _ in range(60000):',
- ' os.write(3, b"x")',
- ' os.sched_yield()',
- 'os.write(3, b"\\n")',
- // A real frame after the trickle proves framing still works on the
- // coalesced residual.
- 'print("after-trickle")',
- 'return "done"',
- ].join('\n')
- let result: CodeRunResult
- try {
- const { runtime } = await setup({ maxWallMs: 30_000 })
- result = await runtime.run({ program, bindings: [] })
- } finally {
- Buffer.concat = realConcat
- }
- expect(result.error).toBeUndefined()
- expect(result.value).toBe('done')
- expect(result.logs).toContain('after-trickle')
- // Sealing appends a finished block rather than re-merging everything held, so
- // each byte is copied once. Re-concatenating the whole buffer at every
- // threshold made the cumulative copy volume quadratic — 10 MiB trickled a
- // byte at a time copies 53.7 GB that way. A per-byte-copied budget is the
- // discriminator, and it is measured rather than reasoned about: this shape
- // copies about 119 KB for 60000 trickled bytes, the re-merging shape about
- // 540 KB. 256 KiB sits between them with margin on both sides — most writes
- // are coalesced by the pipe before they reach us, so the observed ratio is
- // smaller than the asymptotic one, and the threshold has to sit where a real
- // measurement lands rather than where the asymptote suggests.
- expect(copied).toBeLessThan(256 * 1024)
- }, 40_000)
- it('seals trickled stray fragments into blocks without recopying the sealed prefix', async () => {
- // The stray-capture buffer has the same object-overhead exposure as the fd-3
- // reader above: each newline-free `data` chunk is its own Buffer, so a
- // program pacing single-byte `os.write(1, ...)` accumulates one object per
- // write, which the serialized-cost counter cannot see. Past MAX_PENDING_CHUNKS
- // the fragments seal into a finished block; re-merging the whole residual at
- // each threshold instead would copy the sealed prefix again and again, making
- // the cumulative copy volume quadratic. `Buffer.concat` is wrapped to measure
- // that volume — both shapes admit the same final log entry, so the copy total
- // is the discriminator. maxLogBytes is raised so the trickle is retained,
- // not truncated, which is what forces the fragments to accumulate and seal.
- const realConcat = Buffer.concat.bind(Buffer)
- let copied = 0
- Buffer.concat = (list: readonly Uint8Array[], total?: number): Buffer<ArrayBuffer> => {
- for (const part of list) copied += part.length
- return realConcat(list, total)
- }
- let result: CodeRunResult
- try {
- const { runtime } = await setup({ maxLogBytes: 200_000, maxWallMs: 30_000 })
- result = await runtime.run({
- program: [
- 'import os',
- 'for _ in range(60000):',
- ' os.write(1, b"x")',
- ' os.sched_yield()',
- 'os.write(1, b"\\n")',
- 'return "done"',
- ].join('\n'),
- bindings: [],
- })
- } finally {
- Buffer.concat = realConcat
- }
- expect(result.error).toBeUndefined()
- expect(result.value).toBe('done')
- // The trickle coalesces into one log line (no interior newlines). Its exact
- // length depends on pipe coalescing, but it is one entry and non-empty.
- expect(result.logs.length).toBe(1)
- expect((result.logs[0] as string).length).toBeGreaterThan(0)
- // Sealing appends a finished block rather than re-merging everything held, so
- // each byte is copied a bounded number of times. Re-merging the whole
- // residual at every seal threshold instead makes the cumulative copy volume
- // quadratic. Measured like the fd-3 sibling above rather than reasoned about:
- // this sealed shape copies about 120 KB for 60000 trickled bytes, the
- // re-merging shape about 538 KB (the stray path adds one whole-residual
- // concat at the terminating newline over the fd-3 sibling's 119/540, landing
- // at the same order). 256 KiB sits between them with margin on both sides, so
- // reverting the seal to a re-merge turns this assertion red.
- expect(copied).toBeLessThan(256 * 1024)
- }, 40_000)
- it('caps a huge exception diagnostic child-side before it crosses the wire', async () => {
- // A program can raise with a multi-megabyte message; the child must cap
- // it at maxValueBytes before formatting/sending, not ship the whole
- // payload for the host to truncate after parsing.
- const { runtime } = await setup({ maxValueBytes: 1024 })
- const result = await runtime.run({
- program: 'raise ValueError("boom-" + "x" * (8 * 1024 * 1024))',
- bindings: [],
- })
- expect(result.error?.kind).toBe('exception')
- expect(result.error?.message).toContain('boom-')
- expect(result.error?.message.endsWith('… [truncated]')).toBe(true)
- expect(Buffer.byteLength(result.error?.message ?? '', 'utf8')).toBeLessThan(2048)
- })
- it('caps a control-heavy exception diagnostic by its serialized cost, not raw bytes', async () => {
- // The diagnostic crosses fd 3 inside a JSON frame where a control character
- // escapes sixfold (a NUL is one raw byte, six as `�`). Capping by raw
- // UTF-8 length would let a NUL-heavy message near maxValueBytes serialize to
- // ~6x that and breach the frame ceiling — the silent worker-exit inversion
- // the load-time cap check exists to prevent. The child meters the diagnostic
- // by its serialized cost, so a NUL flood is truncated to fit the frame and
- // the run still reports the exception rather than a worker-exit.
- const { runtime } = await setup({ maxValueBytes: 4096 })
- const result = await runtime.run({
- // 512 KiB of NUL: ~3 MiB once escaped, far past the 4 KiB cap.
- program: 'raise ValueError("\\x00" * (512 * 1024))',
- bindings: [],
- })
- expect(result.error?.kind).toBe('exception')
- expect(result.error?.message.endsWith('… [truncated]')).toBe(true)
- // The SERIALIZED form (what the frame carried) fits the budget, so its raw
- // length is well under it too — a raw-byte cap would have admitted ~4 KiB of
- // NULs that serialize to ~24 KiB.
- const serialized = JSON.stringify(result.error?.message ?? '')
- expect(Buffer.byteLength(serialized, 'utf8')).toBeLessThanOrEqual(4096 + 8)
- })
- it('bounds a newline-free partial-line flood while the program is still running', async () => {
- // print("x", end="") never completes a line, so nothing reaches the
- // Python LogBuffer until settlement — the buffered tail must still hit
- // the budget mid-run instead of growing without bound to RLIMIT/timeout.
- const { runtime } = await setup({ maxLogBytes: 1024, maxWallMs: 15_000 })
- const result = await runtime.run({
- program: [
- 'for _ in range(100000):',
- ' print("xxxxxxxxxx", end="")',
- 'return "done"',
- ].join('\n'),
- bindings: [],
- })
- expect(result.error).toBeUndefined()
- expect(result.value).toBe('done')
- expect(result.logs.some(line => line.includes('log capture truncated'))).toBe(true)
- // The retained text is bounded by the budget, not the 1 MB the program wrote.
- expect(result.logs.join('\n').length).toBeLessThan(4096)
- }, 20_000)
- it('discards empty writes instead of buffering one list slot each', async () => {
- // An empty chunk adds no character, so the mid-run budget check (which
- // compares buffered CHARS against the remaining ledger) can never fire on
- // it. Buffering empty strings therefore grew `_pending` without bound —
- // millions of slots per CPU second — until RLIMIT_AS turned an append into
- // a MemoryError, long after the log ledger was exhausted. Two million
- // empty writes must instead settle normally and contribute NO log entry,
- // proving the chunk was dropped rather than joined at flush_line.
- const { runtime } = await setup({ maxLogBytes: 256, addressSpaceMb: 256, maxWallMs: 20_000 })
- const result = await runtime.run({
- program: [
- 'import sys',
- 'for _ in range(2000000):',
- ' sys.stdout.write("")',
- 'return "done"',
- ].join('\n'),
- bindings: [],
- })
- expect(result.error).toBeUndefined()
- expect(result.value).toBe('done')
- expect(result.logs).toEqual([])
- }, 30_000)
- it('stops scanning a single-write newline flood once the log ledger truncates', async () => {
- // One write carrying half a million newlines: the offset scan must exit the
- // instant LogBuffer truncates rather than re-slicing and pushing every
- // remaining line. If it kept scanning it would exhaust the CPU/wall budget;
- // the run instead settles quickly with exactly one truncation marker.
- const { runtime } = await setup({ maxLogBytes: 256, maxWallMs: 10_000 })
- const start = Date.now()
- const result = await runtime.run({
- program: ['print("x\\n" * 500000, end="")', 'return "done"'].join('\n'),
- bindings: [],
- })
- expect(result.error).toBeUndefined()
- expect(result.value).toBe('done')
- expect(result.logs.filter(line => line.includes('log capture truncated'))).toHaveLength(1)
- expect(Date.now() - start).toBeLessThan(8_000)
- }, 15_000)
- it('bounds an oversized newline-terminated write before joining and slicing it', async () => {
- // The newline branch slices the first line out of the write before
- // `LogBuffer.push` can apply its cheap budget rejection, so a single
- // over-budget write cost a full extra copy of itself in peak address space —
- // the amplification that bound exists to avoid, applied one layer too late.
- // Measured under a 400 MiB addressSpaceMb with the slice unbounded: writes
- // of 200 MiB and up died on MemoryError inside `sys.stdout.write`, reported
- // as the PROGRAM's own exception rather than the promised truncation marker.
- // `"\\n".rjust(n, "A")` is a single allocation ending in the newline, so the
- // payload itself fits and the only remaining allocation is the stream's own
- // slice; 340 MiB of a 400 MiB cap cannot survive one more copy of it.
- const { runtime } = await setup({ maxLogBytes: 256, addressSpaceMb: 400, maxWallMs: 30_000 })
- const result = await runtime.run({
- program: [
- 'import sys',
- 'payload = "\\n".rjust(340 * 1024 * 1024, "A")',
- 'sys.stdout.write(payload)',
- 'return "done"',
- ].join('\n'),
- bindings: [],
- })
- expect(result.error).toBeUndefined()
- expect(result.value).toBe('done')
- expect(result.logs).toEqual([logTruncationMarker(256)])
- }, 40_000)
- it('bounds a newline-free write against the already-buffered chunks before joining them', async () => {
- // The newline-free arm buffers the write and then compared the buffered
- // CHARACTER COUNT against the ledger — correct — but paid for the comparison
- // with `"".join(self._pending)`, a second full copy of everything held. One
- // buffered character is enough to make that join a copy of the whole
- // following write. Measured under a 400 MiB addressSpaceMb with a 340 MiB
- // second write: the join raised MemoryError inside `sys.stdout.write`, and
- // because the oversized chunks stayed in `_pending` the settlement
- // `flush_line` raised it again — that throw sits after the `except
- // BaseException` block, so it costs the `done` frame and the run came back
- // `timeout: wall-clock ceiling reached (30000ms)` with no logs at all. The
- // bound must be applied BEFORE the join and the chunks dropped on that path,
- // so the run settles with the truncation marker it promises.
- const { runtime } = await setup({ maxLogBytes: 256, addressSpaceMb: 400, maxWallMs: 30_000 })
- const result = await runtime.run({
- program: [
- 'import sys',
- // One unterminated character first, so `_pending` is non-empty and the
- // large write cannot take the "buffered text IS the write" shortcut.
- 'sys.stdout.write("x")',
- 'payload = "A" * (340 * 1024 * 1024)',
- 'sys.stdout.write(payload)',
- 'return "done"',
- ].join('\n'),
- bindings: [],
- })
- expect(result.error).toBeUndefined()
- expect(result.value).toBe('done')
- expect(result.logs).toEqual([logTruncationMarker(256)])
- }, 40_000)
- it('bounds a newline-terminated write against the already-buffered chunks before joining them', async () => {
- // Same allocation, reached through the newline arm: with chunks pending, the
- // whole write used to be appended and joined so the offset scan could run
- // over one string. Only the FIRST line needs those chunks, so a pending
- // chunk plus a 340 MiB newline-terminated write under a 400 MiB
- // addressSpaceMb died on MemoryError in the join before the per-line bound
- // could reject anything, and the retained chunks made the settlement flush
- // die the same way: measured, `timeout: wall-clock ceiling reached
- // (30000ms)`. The reconstructed first line is now checked against the ledger
- // and only a budget-sized prefix of it is copied; the rest of the write is
- // scanned in place.
- const { runtime } = await setup({ maxLogBytes: 256, addressSpaceMb: 400, maxWallMs: 30_000 })
- const result = await runtime.run({
- program: [
- 'import sys',
- 'sys.stdout.write("x")',
- 'payload = "\\n".rjust(340 * 1024 * 1024, "A")',
- 'sys.stdout.write(payload)',
- 'return "done"',
- ].join('\n'),
- bindings: [],
- })
- expect(result.error).toBeUndefined()
- expect(result.value).toBe('done')
- expect(result.logs).toEqual([logTruncationMarker(256)])
- }, 40_000)
- it('emits pending text on an explicit flush, before the run can be killed', async () => {
- // `_LogStream` inherits TextIOBase's no-op `flush()`, so an explicit
- // `print(..., flush=True)` or `sys.stdout.flush()` left the text in
- // `_pending` with nothing to drain it but `flush_line` after settlement — a
- // call a hanging or killed run never reaches. Measured: printing
- // "before hang" with flush=True ahead of an infinite loop returned
- // `logs: []`, losing the one diagnostic the program deliberately committed.
- const { runtime } = await setup({ maxWallMs: 4_000 })
- const result = await runtime.run({
- program: [
- 'import sys',
- 'print("before hang", end="", flush=True)',
- 'while True: pass',
- ].join('\n'),
- bindings: [],
- })
- expect(result.error?.kind).toBe('timeout')
- expect(result.logs).toContain('before hang')
- }, 15_000)
- it('marks a dropped tail when the ledger lands on exactly zero remaining', async () => {
- // One 100-character line costs 103 serialized bytes (quotes + separator),
- // consuming a 103-byte budget EXACTLY. Landing on zero never trips
- // LogBuffer's "cost > remaining" branch, so `_truncated` stays unset and the
- // stream's own `remaining > 0` guard silently discarded the unscanned tail —
- // the run reported a complete log while dropping text. The tail must be
- // pushed so the marker is emitted. (This surfaced only after empty writes
- // stopped being buffered: `print` issues a trailing `write("")` whose
- // buffered-empty path used to force the marker out incidentally.) A single
- // wide line is used rather than many narrow ones so the CHILD ledger is the
- // one that lands on zero: the host's identical ledger truncates first when
- // many small entries precede the long marker text.
- const { runtime } = await setup({ maxLogBytes: 103, maxWallMs: 10_000 })
- const result = await runtime.run({
- program: ['print("y" * 100 + "\\n" + "z" * 10, end="")', 'return "done"'].join('\n'),
- bindings: [],
- })
- expect(result.error).toBeUndefined()
- expect(result.value).toBe('done')
- expect(result.logs).toContain('y'.repeat(100))
- expect(result.logs.filter(line => line.includes('log capture truncated'))).toHaveLength(1)
- // The dropped tail is not retained, but its loss is now reported.
- expect(result.logs.some(line => line.includes('z'))).toBe(false)
- }, 15_000)
- it('charges the JSON-escaped cost of control characters against the log ledger', async () => {
- // A NUL renders as \u0000 (6 bytes) in the serialized outer logs; the
- // ledger must charge that expansion, or a control-character flood admits
- // 6x the configured cap.
- const { runtime } = await setup({ maxLogBytes: 256 })
- const result = await runtime.run({
- program: [
- 'for _ in range(500):',
- ' print("\\x00" * 10)',
- 'return "done"',
- ].join('\n'),
- bindings: [],
- })
- expect(result.error).toBeUndefined()
- expect(result.logs.some(line => line.includes('log capture truncated'))).toBe(true)
- // Serialized (escaped) size of retained entries stays in the budget's
- // neighborhood: well under the ~30 kB an uncharged flood would retain.
- const serialized = Buffer.byteLength(JSON.stringify(result.logs), 'utf8')
- expect(serialized).toBeLessThan(1024)
- })
- it('charges the serialized cost child-side, so a control-heavy line truncates instead of being admitted whole', async () => {
- // The child's ledger must charge what the entry costs on the wire, not its
- // raw UTF-8 length: a NUL is one raw byte but six as its escape. A 24 MiB NUL
- // line clears the cheap char-count lower bound (24 MiB < 32 MiB budget), so
- // charging raw bytes would ADMIT it and emit a ~144 MiB escaped entry;
- // charging the serialized cost (~144 MiB > the 32 MiB budget) rejects it
- // before any encode and emits the marker instead. The address space (512 MiB,
- // clearing the 12x load gate for a 32 MiB budget) is sized so the run loads;
- // the gate separately guarantees a correctly-charged near-budget entry fits.
- const { runtime } = await setup({ maxLogBytes: 32 * 1024 * 1024, addressSpaceMb: 512, maxWallMs: 20_000 })
- const result = await runtime.run({
- program: [
- 'print("\\x00" * (24 * 1024 * 1024))',
- 'return "done"',
- ].join('\n'),
- bindings: [],
- })
- expect(result.error).toBeUndefined()
- expect(result.value).toBe('done')
- expect(result.logs.filter(line => line.includes('log capture truncated'))).toHaveLength(1)
- // Nothing of the line itself was retained: the ledger refused the whole entry.
- expect(result.logs.every(line => !line.includes(String.fromCharCode(0)))).toBe(true)
- }, 30_000)
- it('bounds a huge unterminated tail after an early newline without copying it whole', async () => {
- // The newline branch of _LogStream.write buffered the whole unterminated
- // tail after the last newline into `_pending` before the flush trigger could
- // bound it, so an early newline followed by a huge tail made a second full
- // copy of the model's own string — a MemoryError the config gate cannot
- // catch (the tail far exceeds maxLogBytes). The tail is now sliced to a
- // budget-sized prefix, so the run truncates and completes. Linux-only RLIMIT_AS
- // repro (Darwin skips the limit); on macOS this asserts the happy path.
- //
- // Sizing: the model builds `tail` (N) then the `"\n" + tail` write argument
- // (another ~N), so construction peaks at ~2N — kept under the 384 MiB address
- // space at N = 150 MiB (~300 MiB). The pre-fix code then buffered the whole
- // ~150 MiB tail again, pushing past 384 MiB; the sliced prefix does not.
- const { runtime } = await setup({ maxLogBytes: 256, addressSpaceMb: 384, maxWallMs: 20_000 })
- const result = await runtime.run({
- program: [
- 'import sys',
- 'tail = "A" * (150 * 1024 * 1024)',
- 'sys.stdout.write("\\n" + tail)',
- 'return "done"',
- ].join('\n'),
- bindings: [],
- })
- expect(result.error).toBeUndefined()
- expect(result.value).toBe('done')
- expect(result.logs.some(line => line.includes('log capture truncated'))).toBe(true)
- }, 30_000)
- it('flushes logs before framing the value so their peaks do not add against RLIMIT_AS', async () => {
- // The load gate bounds maxLogBytes and maxValueBytes INDEPENDENTLY against the
- // address space, each at the 12x worst case. But the child framed the
- // completion value (materializing its escaped form to meter it, then encoding
- // the frame) while a newline-free log tail still sat unflushed in _pending.
- // Those two peaks added: two budgets each admitted alone could together breach
- // RLIMIT_AS, dying as worker-exit instead of settling. The flush now runs
- // before the value is framed, so the log pending is freed first.
- //
- // Config: 32 MiB each against 512 MiB (each 32*12 = 384 MiB < 448 MiB
- // budgetable, so both load). The program writes ~33M astral chars with no
- // newline (buffered ~132 MB, under the char-count flush trigger) then returns
- // ~33M astral chars — a ~132 MB serialized value that is itself OVER the 32 MiB
- // maxValueBytes, so the correct outcome is `output-limit`. Pre-fix the
- // unflushed 132 MB plus the value's build-and-encode (~396 MB) exceeded 512 MiB
- // and OOM'd (reported as exception/worker-exit); flushing first lets the value
- // check complete (~460 MB alone) and report output-limit. On Darwin (no
- // RLIMIT_AS) the value is over budget too, so output-limit holds either way;
- // the OOM the reorder prevents is the Linux-only failure.
- const { runtime } = await setup({
- maxLogBytes: 32 * 1024 * 1024,
- maxValueBytes: 32 * 1024 * 1024,
- addressSpaceMb: 512,
- maxWallMs: 20_000,
- })
- const result = await runtime.run({
- program: [
- 'import sys',
- 'sys.stdout.write("\\U0001F600" * 33_000_000)',
- 'return "\\U0001F600" * 33_000_000',
- ].join('\n'),
- bindings: [],
- })
- expect(result.error?.kind).toBe('output-limit')
- }, 30_000)
- it('checks and encodes a wide completion value in O(depth), not O(width)', async () => {
- // A wide flat list serializes to ~2 bytes per element but the pre-fix walk
- // enqueued one traversal tuple per element (_check_done_value) and one stack
- // entry plus a separator marker per element (_encode_json_plain) — ~56 bytes
- // per element, ~28x the serialized size. A value the byte meter admits could
- // therefore OOM on the checker's or encoder's own bookkeeping, the inversion
- // the load gate exists to prevent (the gate reserves 12x, not 28x). Both now
- // walk with an O(depth) cursor that pulls one child at a time, so the only
- // width-proportional allocation is the output string the meter bounded.
- //
- // Config: maxValueBytes 20 MiB against 384 MiB (20*12 = 240 MiB < 320 MiB
- // budgetable, so it loads). `[0] * 6_000_000` is ~12 MB of JSON, under the
- // 20 MiB budget, so it must round-trip. Pre-fix the ~400 MB of per-element
- // frames plus the interpreter exceeded 384 MiB and returned MemoryError as an
- // exception. Linux-only RLIMIT_AS repro; on macOS the value round-trips
- // either way, but the fixture stays within the address space so it is honest.
- //
- // `maxWallMs` is 60s, not the 20s the memory assertion alone needs: the O(depth)
- // cursor pulls 6M elements one at a time through Python-level frames, which costs
- // ~11s on an idle machine and more under the coverage lane's V8 instrumentation
- // with several workers sharing a box. This budget bounds the run without letting a
- // loaded runner's scheduling latency read as a `timeout` — what this test asserts
- // is the O(depth) memory shape, not a speed claim.
- const { runtime } = await setup({ maxValueBytes: 20 * 1024 * 1024, addressSpaceMb: 384, maxWallMs: 60_000 })
- const result = await runtime.run({ program: 'return [0] * 6_000_000', bindings: [] })
- expect(result.error).toBeUndefined()
- expect(Array.isArray(result.value)).toBe(true)
- expect((result.value as number[]).length).toBe(6_000_000)
- }, 90_000)
- it('validates wide binding arguments in O(depth), not O(width)', async () => {
- // The completion-value walks are budgeted; this one is not. `dispatch` runs
- // `_lossless_json_violation` on the arguments the MODEL built, and no
- // child-side byte budget bounds them first: the frame ceiling is the host's
- // and applies only after this validation returns. A per-member traversal
- // frame therefore turned a legitimate call into the program's own
- // MemoryError. Measured with tracemalloc on the two walk shapes over this
- // exact argument (JSON ~17 MB): the cursor peaks at 0.0 MiB of auxiliary
- // state, the pre-fix `stack.extend` at 459.1 MiB -- past the 384 MiB
- // configured below, so the discriminating failure is real. It is Linux-only:
- // Darwin skips RLIMIT_AS, so this case round-trips there either way.
- //
- // The binding echoes its argument's length back, so the assertion proves the
- // call actually round-tripped rather than merely avoiding a crash.
- const { runtime } = await setup({ addressSpaceMb: 384, maxWallMs: 60_000 })
- const result = await runtime.run({
- program: 'return await tools.width([0] * 6_000_000)',
- bindings: [{
- global: 'tools',
- functions: { width: async (items: unknown) => (items as number[]).length },
- }],
- })
- expect(result.error).toBeUndefined()
- expect(result.value).toBe(6_000_000)
- }, 90_000)
- it('decodes a multi-megabyte binding reply without regex backtracking state', async () => {
- // The child parses every host reply with `_decode_json_plain`. Its scalar
- // regex matched strings with a `(?:[^"\\]|\\.)*` repetition, which makes
- // CPython's backtracking engine retain state proportional to the string's
- // WIDTH -- measured at ~146 MiB of engine state for a 1 MiB string and
- // ~558 MiB for 4 MiB. A legitimate multi-megabyte reply therefore raised
- // MemoryError inside `_pump_replies`; because that pump is the only settler
- // of the call's future, the run stranded until the wall clock reported a
- // `timeout` instead of returning the value the binding produced.
- //
- // Strings now scan chunk-to-chunk over a character class (no backtracking
- // state). Measured on this exact 4 MiB reply: the pre-fix regex peaks at
- // 557.8 MiB, past the default 512 MiB address space, while the scanner peaks
- // at the 4.0 MiB result itself. Linux-only, like the other RLIMIT_AS repros:
- // Darwin does not apply the limit, so the spike is merely allocated there.
- const reply = 'A'.repeat(4 * 1024 * 1024)
- const { runtime } = await setup({ maxWallMs: 60_000 })
- const result = await runtime.run({
- program: 'value = await tools.big({})\nreturn len(value)',
- bindings: [{ global: 'tools', functions: { big: async () => reply } }],
- })
- expect(result.error).toBeUndefined()
- expect(result.value).toBe(reply.length)
- }, 90_000)
- it('bounds a flood of zero-byte log lines through the per-entry separator charge', async () => {
- // Blank print() lines carry zero content bytes; without the +1 separator
- // charge they would bypass maxLogBytes entirely and grow the retained
- // array without bound. Each empty entry costs one byte, so a 64-byte
- // budget retains at most 64 entries before the marker.
- const { runtime } = await setup({ maxLogBytes: 64, maxWallMs: 10_000 })
- const result = await runtime.run({
- program: [
- 'for _ in range(10000):',
- ' print()',
- 'return "done"',
- ].join('\n'),
- bindings: [],
- })
- expect(result.error).toBeUndefined()
- expect(result.logs.length).toBeLessThanOrEqual(65)
- expect(result.logs.some(line => line.includes('log capture truncated'))).toBe(true)
- })
- it('reassembles multibyte UTF-8 split across stray-output pipe chunks', async () => {
- // A single os.write far past the 64 KiB pipe buffer forces multiple
- // 'data' chunks; when the boundary lands inside a multibyte sequence,
- // per-chunk decoding would corrupt it into replacement characters. Raw bytes
- // are buffered and only decoded once a complete line (or the whole tail at
- // flush) is assembled, so the split sequence is whole by the time it is
- // decoded. The payload spans every valid multibyte lead class so
- // accrueStrayCost's per-lead continuation ranges are all exercised: U+0900
- // (E0 A4 80, the range-restricted E0 lead), U+4F60 and U+597D (E4/E5, plain
- // 3-byte), U+1F600 (F0, the range-restricted F0 lead), and U+10FFFF (F4 8F
- // BF BF, the range-restricted F4 lead).
- const { runtime } = await setup({ maxLogBytes: 1024 * 1024 })
- const result = await runtime.run({
- program: [
- 'import os',
- // os.write is one syscall and returns a partial count on a full
- // pipe, so loop until the whole payload (odd prefix -> a chunk
- // boundary lands inside a multibyte sequence) is out.
- String.raw`payload = b"a" * 65535 + "\u0900\u4f60\u597d\U0001f600\U0010ffff".encode("utf-8")`,
- 'view = memoryview(payload)',
- 'while view:',
- ' view = view[os.write(1, view):]',
- 'return "done"',
- ].join('\n'),
- bindings: [],
- })
- expect(result.error).toBeUndefined()
- const text = result.logs.join('')
- expect(text).toContain('\u0900\u4f60\u597d\u{1f600}\u{10ffff}')
- expect(text).not.toContain('\ufffd')
- })
- it('flushes a stray-output byte sequence left incomplete when the pipe ends', async () => {
- // The child writes the first two bytes of a 3-byte UTF-8 character to fd 1
- // and exits, so the pipe closes with the sequence unfinished in the raw
- // residual. The 'end' flush decodes the residual with `toString('utf8')`,
- // which renders the stranded bytes as U+FFFD instead of dropping them.
- const { runtime } = await setup({ maxLogBytes: 1024 * 1024 })
- const result = await runtime.run({
- program: [
- 'import os',
- // b"\xe4\xbd" is the leading two bytes of U+4F60; no continuation byte
- // follows before exit.
- String.raw`os.write(1, b"\xe4\xbd")`,
- 'return "done"',
- ].join('\n'),
- bindings: [],
- })
- expect(result.error).toBeUndefined()
- expect(result.logs.join('')).toContain('�')
- })
- it('rejects reserved words of EITHER backend language as binding globals', async () => {
- // The seam's portable contract: `lambda` (Python keyword, legal JS name)
- // and `typeof` (JS keyword, legal Python name) are both refused, so a
- // namespace list valid on one backend is valid on every backend.
- const { runtime } = await setup()
- for (const global of ['lambda', 'typeof']) {
- await expect(runtime.run({
- program: 'return 1',
- bindings: [{ global, functions: {} }],
- })).rejects.toThrow(/is not a usable Python identifier/)
- }
- })
- it('captures stray stdout bytes the child writes bypassing sys.stdout', async () => {
- // Model code that writes to fd 1 via os.write() bypasses the Python-side
- // LogBuffer, so the host's stray-byte capture on child.stdout is what
- // records it.
- const { runtime } = await setup()
- const result = await runtime.run({
- program: [
- 'import os',
- 'os.write(1, b"stray stdout\\n")',
- 'os.write(2, b"stray stderr\\n")',
- 'return "done"',
- ].join('\n'),
- bindings: [],
- })
- expect(result.error).toBeUndefined()
- expect(result.logs.join('')).toContain('stray stdout')
- expect(result.logs.join('')).toContain('stray stderr')
- })
- it('escalates to SIGKILL when the program traps SIGTERM and ignores the grace period', async () => {
- // A program that traps SIGTERM should still die: the kill() escalation
- // fires SIGKILL after graceMs. The full run reports either timeout (wall)
- // or worker-exit depending on which finish reason wins the race.
- const { runtime } = await setup({ maxWallMs: 400, graceMs: 200 })
- const result = await runtime.run({
- program: [
- 'import signal, time',
- 'signal.signal(signal.SIGTERM, lambda *a: None)',
- 'while True: time.sleep(1)',
- ].join('\n'),
- bindings: [],
- })
- expect(['timeout', 'worker-exit']).toContain(result.error?.kind)
- }, 6000)
- it('bounds the fd-3 receive buffer against a newline-free flood', async () => {
- // A program looping os.write(3, ...) with no newline would grow the host
- // accumulator unbounded (the child's RLIMIT_AS does not cover the host
- // string). The ceiling is a fixed 256 MiB memory-safety invariant —
- // deliberately NOT derived from maxValueBytes, because legitimate binding
- // call frames may be large. We flood slightly past it in 8 MiB writes so
- // the test terminates promptly once the guard trips.
- const ceiling = 256 * 1024 * 1024
- const { runtime } = await setup({ maxWallMs: 60_000, addressSpaceMb: 2048 })
- const start = Date.now()
- const result = await runtime.run({
- program: [
- 'import os',
- `for _ in range(${Math.ceil((ceiling * 1.1) / (8 * 1024 * 1024))}):`,
- ' os.write(3, b"A" * (8 * 1024 * 1024))',
- 'return "never"',
- ].join('\n'),
- bindings: [],
- })
- const elapsed = Date.now() - start
- expect(result.error?.kind).toBe('worker-exit')
- expect(result.error?.message).toContain(`protocol frame exceeded ${ceiling} bytes`)
- // The breach ends the run before the wall ceiling (the run did not idle
- // out); absolute pipe throughput varies too much under parallel suites
- // for a tight bound.
- expect(elapsed).toBeLessThan(30_000)
- }, 45_000)
- it('fails a forged oversized done value host-side as output-limit', async () => {
- // The Python-side _done_with_value check is bypassable by writing a done
- // frame straight to fd 3. The host re-enforces maxValueBytes; the seam
- // forbids substituting a truncated value, so the run FAILS as output-limit
- // instead of returning a lie.
- const maxValueBytes = 64
- const { runtime } = await setup({ maxValueBytes })
- const result = await runtime.run({
- program: [
- 'import os, json',
- 'big = "B" * 5000',
- 'os.write(3, json.dumps({"type":"done","value":big}).encode() + b"\\n")',
- // The real done never sends; the forged one settles the run.
- 'import time',
- 'time.sleep(5)',
- ].join('\n'),
- bindings: [],
- })
- expect(result.value).toBeUndefined()
- expect(result.error?.kind).toBe('output-limit')
- expect(result.error?.message).toContain('exceeded 64 bytes')
- }, 8000)
- it('drops a forged oversized log frame on its code-unit lower bound, before escaping it', async () => {
- // A forged `log` frame carrying a control-heavy string sits below the
- // 256 MiB fd-3 frame ceiling but escapes several-fold: 24 MiB of NULs
- // becomes ~144 MiB of `�`. Charging it required building that escaped
- // copy first, so a 32-byte maxLogBytes could still force a
- // hundreds-of-megabytes host allocation. The cheap `length + 3` lower bound
- // truncates it instead. The host's own heap is what is under test, so keep
- // the child's address space generous enough to BUILD the frame.
- const { runtime } = await setup({ maxLogBytes: 32, addressSpaceMb: 1024, maxWallMs: 60_000 })
- const before = process.memoryUsage().heapUsed
- const result = await runtime.run({
- program: [
- 'import os',
- // Written as a raw frame so the child's own ledger never sees it.
- 'os.write(3, b\'{"type":"log","text":"\' + b"\\\\u0000" * (24 * 1024 * 1024) + b\'"}\\n\')',
- 'return "settled"',
- ].join('\n'),
- bindings: [],
- })
- expect(result.error).toBeUndefined()
- expect(result.value).toBe('settled')
- // The frame was dropped as one truncation marker, not retained.
- expect(result.logs).toEqual([logTruncationMarker(32)])
- // The escaped copy (~144 MiB) was never materialized.
- expect(process.memoryUsage().heapUsed - before).toBeLessThan(256 * 1024 * 1024)
- }, 90_000)
- it('charges a forged log frame its escaped cost once past the code-unit lower bound', async () => {
- // The cheap lower bound only rejects what cannot possibly fit; a SHORT
- // control-heavy frame clears it and must still be charged what it costs on
- // the wire. Ten NULs are 13 against the 32-byte lower bound but 63 escaped
- // (six bytes each, two quotes, one separator), so the full charge truncates.
- const { runtime } = await setup({ maxLogBytes: 32 })
- const result = await runtime.run({
- program: [
- 'import os',
- 'os.write(3, b\'{"type":"log","text":"\' + b"\\\\u0000" * 10 + b\'"}\\n\')',
- 'return "settled"',
- ].join('\n'),
- bindings: [],
- })
- expect(result.error).toBeUndefined()
- expect(result.value).toBe('settled')
- expect(result.logs).toEqual([logTruncationMarker(32)])
- }, 8000)
- it('caps a forged done error.message from its code-unit prefix, never encoding the whole message', async () => {
- // `Buffer.from(message)` on a message near the frame ceiling allocates a
- // full UTF-8 copy before maxValueBytes applies. Only the first
- // maxValueBytes code units can fit the cap, so only that prefix is encoded
- // — at most 3x the cap in bytes. The message here is 48 MiB of ASCII: its
- // full encode would be another 48 MiB in the host.
- const maxValueBytes = 64
- const { runtime } = await setup({ maxValueBytes, addressSpaceMb: 1024, maxWallMs: 60_000 })
- const before = process.memoryUsage().heapUsed
- const result = await runtime.run({
- program: [
- 'import os',
- 'os.write(3, b\'{"type":"done","error":{"kind":"exception","message":"\' + b"E" * (48 * 1024 * 1024) + b\'"}}\\n\')',
- 'import time',
- 'time.sleep(30)',
- ].join('\n'),
- bindings: [],
- })
- expect(result.error?.kind).toBe('exception')
- const message = result.error?.message ?? ''
- // The marker's 15 bytes come OUT of the 64-byte cap, so 49 E's precede it
- // and the whole string is exactly 64 bytes — not 64 plus the marker.
- expect(message).toBe(`${'E'.repeat(maxValueBytes - 15)}… [truncated]`)
- expect(Buffer.byteLength(message, 'utf8')).toBe(maxValueBytes)
- // JSON.parse already holds the 48 MiB string; the cap must not add a
- // second full-length copy on top of it.
- expect(process.memoryUsage().heapUsed - before).toBeLessThan(256 * 1024 * 1024)
- }, 90_000)
- it('keeps a capped diagnostic within maxValueBytes, marker included', async () => {
- // The marker is part of the emitted diagnostic, so its bytes are reserved
- // from the cap rather than appended past it — the host meters this same
- // field downstream. Checked on BOTH producers: the child's own _cap_message
- // (a raised exception) and the host's capMessage (a forged done frame).
- const maxValueBytes = 40
- const { runtime } = await setup({ maxValueBytes })
- const raised = await runtime.run({
- program: 'raise ValueError("R" * 100000)',
- bindings: [],
- })
- expect(raised.error?.kind).toBe('exception')
- const raisedMessage = raised.error?.message ?? ''
- expect(raisedMessage.endsWith('… [truncated]')).toBe(true)
- expect(Buffer.byteLength(raisedMessage, 'utf8')).toBeLessThanOrEqual(maxValueBytes)
- const forged = await runtime.run({
- program: [
- 'import os, json',
- 'msg = "F" * 100000',
- 'os.write(3, json.dumps({"type":"done","error":{"kind":"exception","message":msg}}).encode() + b"\\n")',
- 'import time',
- 'time.sleep(5)',
- ].join('\n'),
- bindings: [],
- })
- expect(forged.error?.kind).toBe('exception')
- const forgedMessage = forged.error?.message ?? ''
- expect(forgedMessage.endsWith('… [truncated]')).toBe(true)
- expect(Buffer.byteLength(forgedMessage, 'utf8')).toBe(maxValueBytes)
- }, 15_000)
- it('emits the marker alone when the cap is smaller than the marker itself', async () => {
- // With maxValueBytes below the marker's own 15 bytes there is no room for
- // message text; the marker still goes out, so the truncation stays reported
- // instead of the diagnostic silently becoming empty. Both producers agree.
- const { runtime } = await setup({ maxValueBytes: 4 })
- const raised = await runtime.run({ program: 'raise ValueError("R" * 500)', bindings: [] })
- expect(raised.error?.kind).toBe('exception')
- expect(raised.error?.message).toBe('… [truncated]')
- const forged = await runtime.run({
- program: [
- 'import os, json',
- 'os.write(3, json.dumps({"type":"done","error":{"kind":"exception","message":"F" * 500}}).encode() + b"\\n")',
- 'import time',
- 'time.sleep(5)',
- ].join('\n'),
- bindings: [],
- })
- expect(forged.error?.kind).toBe('exception')
- expect(forged.error?.message).toBe('… [truncated]')
- }, 15_000)
- it('caps a forged done error.message without splitting a surrogate pair', async () => {
- // At exactly maxValueBytes code units the prefix can end on a high
- // surrogate whose low half sits just outside it. `Buffer.from` encodes that
- // orphan as U+FFFD — the same corruption a mid-sequence byte cut causes —
- // and those three replacement bytes sit past the marker-reserved budget, so
- // the byte trim-back drops them.
- const maxValueBytes = 32
- const { runtime } = await setup({ maxValueBytes })
- const result = await runtime.run({
- program: [
- 'import os, json',
- // 32 ASCII chars then astral characters: code unit 32 is the first
- // character's high surrogate (Python spells it as one code point, so
- // json.dumps emits the raw 4 bytes the host reads back as a pair).
- 'msg = "A" * 32 + "\\U0001f600" * 4',
- 'os.write(3, json.dumps({"type":"done","error":{"kind":"exception","message":msg}}).encode() + b"\\n")',
- 'import time',
- 'time.sleep(5)',
- ].join('\n'),
- bindings: [],
- })
- expect(result.error?.kind).toBe('exception')
- // 17 A's fill the marker-reserved budget; no orphaned half, no U+FFFD.
- expect(result.error?.message).toBe(`${'A'.repeat(17)}… [truncated]`)
- expect(Buffer.byteLength(result.error?.message ?? '', 'utf8')).toBe(maxValueBytes)
- }, 8000)
- it('returns a diagnostic under a third of the cap untouched, skipping the encode', async () => {
- // Under maxValueBytes/3 code units a message cannot overflow the cap
- // whatever it holds (3 bytes is the per-code-unit maximum), so the fast
- // path returns it without encoding anything. Non-ASCII proves the bound is
- // the code-unit count, not a byte assumption: 6 characters at 3 bytes each
- // is 18 bytes, inside the 64-byte cap.
- const { runtime } = await setup({ maxValueBytes: 64 })
- const result = await runtime.run({
- program: [
- 'import os, json',
- 'os.write(3, json.dumps({"type":"done","error":{"kind":"exception","message":"中文中文中文"}}).encode() + b"\\n")',
- 'import time',
- 'time.sleep(5)',
- ].join('\n'),
- bindings: [],
- })
- expect(result.error?.kind).toBe('exception')
- expect(result.error?.message).toBe('中文中文中文')
- }, 8000)
- it('re-caps a forged done error.message host-side on a UTF-8 boundary', async () => {
- // A forged done frame can carry an arbitrarily long error message; the
- // host caps it to maxValueBytes and appends the shared marker. The
- // message is emoji-dense and the cap is chosen so the marker-reserved
- // 51-byte cut lands INSIDE a 4-byte sequence (one ASCII byte then 4-byte
- // runs, so only a cut at 1 + 4k is aligned) — the cap must trim back to a
- // code-point boundary rather than decode a replacement character, which
- // would also exceed the cap.
- const maxValueBytes = 66
- const { runtime } = await setup({ maxValueBytes })
- const result = await runtime.run({
- program: [
- 'import os, json',
- 'msg = "E" + "\\U0001f600" * 2000',
- 'os.write(3, json.dumps({"type":"done","error":{"kind":"exception","message":msg}}).encode() + b"\\n")',
- 'import time',
- 'time.sleep(5)',
- ].join('\n'),
- bindings: [],
- })
- expect(result.error?.kind).toBe('exception')
- const message = result.error?.message ?? ''
- expect(message.endsWith('… [truncated]')).toBe(true)
- const marker = '… [truncated]'
- const body = message.slice(0, message.length - marker.length)
- // The WHOLE message, marker included, honors the cap.
- expect(Buffer.byteLength(message, 'utf8')).toBeLessThanOrEqual(maxValueBytes)
- // 'E' plus 12 emoji is 49 bytes: the trim-back walked the 51-byte budget
- // down past two continuation bytes rather than splitting the 13th.
- expect(body).toBe(`E${'\u{1f600}'.repeat(12)}`)
- // The cut landed on a code-point boundary — no replacement character.
- expect(body).not.toContain('\ufffd')
- }, 8000)
- it('bounds a single oversized newline-terminated line on fd 3', async () => {
- // The same ceiling applies to one giant framed line. Write EXACTLY the
- // ceiling with no newline — at the limit, not past it, so nothing trips —
- // then a small newline tail, which is the chunk that crosses.
- const ceiling = 256 * 1024 * 1024
- const { runtime } = await setup({ maxWallMs: 60_000, addressSpaceMb: 2048 })
- const result = await runtime.run({
- program: [
- 'import os',
- 'chunk = b"A" * (8 * 1024 * 1024)',
- `for _ in range(${ceiling / (8 * 1024 * 1024)}):`,
- ' os.write(3, chunk)',
- 'os.write(3, b"AAAA\\n")',
- 'return "never"',
- ].join('\n'),
- bindings: [],
- })
- expect(result.error?.kind).toBe('worker-exit')
- expect(result.error?.message).toContain(`protocol frame exceeded ${ceiling} bytes`)
- }, 90_000)
- it('rejects an over-ceiling fd-3 buffer without first joining it into one line', async () => {
- // The ceiling has to be enforced on the byte COUNTER before Buffer.concat,
- // not on the joined line afterwards: the join is a second copy of
- // everything held, so a program could force roughly twice the advertised
- // 256 MiB of host memory before anything rejected it.
- //
- // This program makes the two orders observably different rather than merely
- // differently sized. It writes exactly the ceiling with no newline (at the
- // limit, so nothing trips), then a newline followed by 8 MiB more. Checking
- // the counter first sees more than the ceiling on the newline-bearing pipe
- // chunk and rejects. Checking the joined line instead produced a FIRST LINE
- // of exactly the ceiling — inside the per-line bound, so it passed as a junk
- // frame — and left an 8 MiB residual well under the bound, so the breach was
- // never reported: measured, the run settled as
- // `python exited (code=0, signal=null) before completing` after the host had
- // held the ceiling AND copied it, which is the doubling this check prevents.
- const ceiling = 256 * 1024 * 1024
- const { runtime } = await setup({ maxWallMs: 60_000, addressSpaceMb: 2048 })
- const result = await runtime.run({
- program: [
- 'import os',
- 'chunk = b"A" * (8 * 1024 * 1024)',
- `for _ in range(${ceiling / (8 * 1024 * 1024)}):`,
- ' os.write(3, chunk)',
- // One drain loop: a single os.write past the pipe buffer returns short,
- // and a truncated tail would change which bytes cross the ceiling.
- 'view = memoryview(b"\\n" + b"B" * (8 * 1024 * 1024))',
- 'while view:',
- ' view = view[os.write(3, view):]',
- 'return "never"',
- ].join('\n'),
- bindings: [],
- })
- expect(result.value).toBeUndefined()
- expect(result.error?.kind).toBe('worker-exit')
- expect(result.error?.message).toContain(`protocol frame exceeded ${ceiling} bytes`)
- }, 120_000)
- })
|