165 lines
16 KiB
Plaintext
165 lines
16 KiB
Plaintext
✔ input that fits the engine window but exceeds remaining credit diagnoses the credit limit (0.4772ms)
|
||
✔ window overflow and historical pauses retain distinct and honest diagnoses (0.0852ms)
|
||
✔ a budget pause persists concrete text/tool/history/image breakdown and never dispatches an oversized request (2289.0781ms)
|
||
✔ explicit frozen preview resumes the same Task in a new Run, preserves completed tools and does not change global config or selected model (3281.4316ms)
|
||
✔ insufficient budgets, silently clamped capacity and arbitrary config fields reject without a physical request or mutating task budget (2319.3069ms)
|
||
✔ changed session, changed registry, expiry and altered frozen preview all require a new explicit preview (2561.6087ms)
|
||
✔ preview preserves unknown invocation status and increasing Task allowance is committed only with confirmed new Run (3368.5301ms)
|
||
✔ batch APIs enforce ownership and review fingerprints, apply once, and persist the completed batch across restart (6183.6659ms)
|
||
✔ delivery reports bind actual batch identity and reject corrupted snapshot evidence without changing project files (4166.4571ms)
|
||
✔ a compatible model can seal proposals through the real HTTP loop while application stays behind user review (7035.2368ms)
|
||
✔ a sealed batch at the step limit hands off and continues the same Task into actual checks without replaying saved tools (16179.7998ms)
|
||
✔ applied batches cannot turn cancellation, other budgets, restart or unknown commands into a review continuation (2376.4348ms)
|
||
▶ complete sealed batch hands off after all tools settle with no next model request
|
||
✔ complete (4778.2753ms)
|
||
✔ later-error (5124.2499ms)
|
||
✔ complete sealed batch hands off after all tools settle with no next model request (9903.25ms)
|
||
▶ partial, changed, failed or cancelled batches cannot claim complete review handoff
|
||
✔ partial (4367.8721ms)
|
||
✔ new-proposal (4670.0788ms)
|
||
✔ failed (3984.8518ms)
|
||
✔ conflict (4780.9337ms)
|
||
✔ cancelled (4050.7866ms)
|
||
✔ unknown (4783.6294ms)
|
||
✔ tampered (4320.9493ms)
|
||
✔ partial, changed, failed or cancelled batches cannot claim complete review handoff (30960.5505ms)
|
||
✔ actual process exit at file-batch prepared preserves durable identity and never replays writes (1958.466ms)
|
||
✔ actual process exit at file-batch application_started preserves durable identity and never replays writes (2141.3829ms)
|
||
✔ actual process exit at file-batch write_intent preserves durable identity and never replays writes (1903.4023ms)
|
||
✔ actual process exit at file-batch staged preserves durable identity and never replays writes (2181.5025ms)
|
||
✔ actual process exit at file-batch replaced preserves durable identity and never replays writes (2603.3938ms)
|
||
✔ actual process exit at file-batch file_recorded preserves durable identity and never replays writes (2711.7967ms)
|
||
✔ actual process exit at file-batch finished preserves durable identity and never replays writes (2792.3029ms)
|
||
✔ actual process exit at file-batch rollback_started preserves durable identity and never replays writes (3211.5358ms)
|
||
✔ actual process exit at file-batch restore_intent preserves durable identity and never replays writes (3090.5842ms)
|
||
✔ actual process exit at file-batch restore_staged preserves durable identity and never replays writes (3054.1173ms)
|
||
✔ actual process exit at file-batch restored preserves durable identity and never replays writes (3422.2453ms)
|
||
✔ actual process exit at file-batch restore_recorded preserves durable identity and never replays writes (3428.2859ms)
|
||
✔ actual process exit at file-batch rollback_finished preserves durable identity and never replays writes (3268.199ms)
|
||
warning: in the working copy of 'README.md', LF will be replaced by CRLF the next time Git touches it
|
||
warning: in the working copy of 'src/two.mjs', LF will be replaced by CRLF the next time Git touches it
|
||
✔ sealed batches preserve bytes until review, then apply and explicitly restore BOM/CRLF/new files (2789.106ms)
|
||
Switched to a new branch 'owner-branch'
|
||
✔ a conflict in the last file or Git branch prevents writing every file in the batch (3138.8255ms)
|
||
✔ duplicate canonical paths, ancestor collisions, links, dependencies and Windows aliases never form a batch (1401.5944ms)
|
||
✔ fingerprints, changed proposals and corrupt snapshot artifacts cannot write or restore any target (2630.57ms)
|
||
✔ a failure after replacement restores only batch bytes and never retries an old application (2052.9028ms)
|
||
✔ rollback preserves owner edits, blocks other project writers, and explicit acknowledgement releases recovery (2371.6453ms)
|
||
✔ an unattempted owner-created file identical to a suggestion remains external and is never removed (1812.6214ms)
|
||
✔ active batch requests are serialized and cancellation leaves a verifiable ended batch (1578.6312ms)
|
||
✔ batch application and rollback preserve unrelated Git index and worktree bytes (4063.2938ms)
|
||
✔ recovery reuses exact staged bytes but retains a conflicting temporary file for owner inspection (2186.2208ms)
|
||
✔ one Task can seal pending proposals from earlier Runs while snapshots retain each source Run (1758.31ms)
|
||
✔ controlled installation pins the native kernel and bridge independently of the existing connection-probe identity (913.9585ms)
|
||
✔ controlled profiles disable every native project/terminal provider and native model/retry route using the actual include patch contract (0.5076ms)
|
||
✔ owned tool catalogues seal full schemas canonically and reject duplicate or malformed declarations (4.9788ms)
|
||
✔ bridge authentication, current Run, process, SDK session and browser-origin checks reject before dispatch (911.7935ms)
|
||
✔ bridge duplicates, unknown tools, malformed arguments and source changes are refused before a second side effect (896.0863ms)
|
||
✔ bridge model requests bind the exact catalogue, route and output bound and preserve raw request/result identity (777.3973ms)
|
||
✔ stopped and oversized bridge requests never reach a local model or tool callback (647.5694ms)
|
||
✔ native text and call IDs preserve original result pairing while unsupported content fails closed (0.8548ms)
|
||
✔ one engine child freezes real installation identity before creating tasks and rejects a changed source (12113.3469ms)
|
||
✔ owned native tools return saved results, use real approvals/checks and account each actual request once across new engine Runs (34838.6695ms)
|
||
✔ forged native scope cannot change a parent file and a final completion claim cannot replace worker proof (12766.7581ms)
|
||
✔ duplicate native IDs are rejected without replaying a saved tool (12244.7175ms)
|
||
✖ native input exceeding the context budget is retained and sends no model request (10231.6607ms)
|
||
✔ bounded native sends verify original tool provenance and reject forged views or missing versions (13910.8387ms)
|
||
✔ stop retains a late reported model usage once and executes no tool from that output (10764.0046ms)
|
||
✔ a source change after the original model intent stops before native tools execute (10878.0128ms)
|
||
✔ an engine source change while approval is pending invalidates the old permission before any check starts (14440.3452ms)
|
||
✔ missing or noncompleted turn end cannot be adopted even with an owned receipt and assistant text (0.5113ms)
|
||
✔ closed root with an original live descendant remains unknown and retains its process tree (0.276ms)
|
||
✔ host recovery reserves original pending attempts exactly once and explicit review preserves unknown outcomes (15173.7566ms)
|
||
✔ corrupted model reservation cannot reduce recovered budget or permit a new engine request (11399.5634ms)
|
||
✔ reservation uses actual known usage from the same route, never lowers estimates or rewrites original receipts (1.6494ms)
|
||
✔ reservation verification binds original Task/Run consumption and rejects changed usage or foreign provenance (0.5599ms)
|
||
✔ known high input calibrates the next request and stops before dispatch while preserving the completed read (1459.3979ms)
|
||
✔ one reported overrun stops legacy requests and keeps actual use and excess (1056.8394ms)
|
||
✔ one reported overrun stops pool requests and keeps actual use and excess (1440.2433ms)
|
||
✔ one reported overrun stops connection requests and keeps actual use and excess (1383.0982ms)
|
||
✔ reported usage below the limit prevents an unaffordable legacy retry before another dispatch (1058.4368ms)
|
||
✔ reported usage below the limit prevents an unaffordable pool retry before another dispatch (1725.2826ms)
|
||
✔ native bridge seals calibrated refusal with original consumption and preserves versioned request verification (21403.8819ms)
|
||
✔ continuation reads advance through historical pages without a false pause while repeated current-Run pages still pause (2.477ms)
|
||
✔ a new tool page replaces old latest-feedback space and still obeys its escaped protocol budget (0.6507ms)
|
||
✔ budgeted artifact pages count escaped protocol bytes and reconstruct original multilingual JSON without losing characters (9.9559ms)
|
||
✔ known artifact coverage detects semantic repeats despite changing limits, and advancing pages or direct evidence restore progress (0.3856ms)
|
||
✔ actual large artifact reads are present in the next bounded HTTP request and next_offset progresses without redoing tools (3914.7979ms)
|
||
✔ a real repeated artifact loop pauses the same Task after recorded results, survives reload and only resumes explicitly (4138.5565ms)
|
||
✔ actual HTTP continuation after reload sends distinct historically covered pages without false no_progress or replay (4226.3619ms)
|
||
✔ context APIs retain exact request identity, paginate archived groups and reject foreign sessions/runs (3569.4716ms)
|
||
✔ delivery reports verify request body, sealed plan and original archived bytes, and show corruption as needing verification (1689.8337ms)
|
||
✔ native seed framing reserves capacity before optional history without changing the selected window (724.4385ms)
|
||
✔ direct code evidence remains selected while recent historical-index browsing is archived within the complete request budget (1372.5234ms)
|
||
✔ one long user turn becomes bounded complete groups with exact UTF-8 history and recent JSON arguments (3293.3926ms)
|
||
✔ tool definitions, exact system bytes, output reserve and remaining Run/Task budget are accounted before requests (711.6186ms)
|
||
✔ oversized required user instructions pause intact and can be explicitly resumed after increasing the window (1191.9811ms)
|
||
✔ all task instructions, constraints and acceptance remain in the runtime system instead of an eight-item or byte prefix (1375.2786ms)
|
||
✔ a newest manageable multi-tool group stays exact even beyond the working target; oversized earlier groups are archived (899.1092ms)
|
||
✔ invalid orphan result is rejected before archive or network preparation (622.664ms)
|
||
✔ invalid missing result is rejected before archive or network preparation (549.8002ms)
|
||
✔ invalid wrong result is rejected before archive or network preparation (538.4463ms)
|
||
✔ invalid duplicate call is rejected before archive or network preparation (557.9724ms)
|
||
✔ a group larger than the artifact limit uses verified Unicode-safe chunks without replacing tool JSON (1348.7152ms)
|
||
✔ changed or missing archived evidence stops reuse and is never silently recreated (779.1231ms)
|
||
✔ transaction failure prevents publishing a plan and any corresponding model request (647.6709ms)
|
||
✔ the Provider rejects body mutation after a sealed plan before calling HTTP (565.72ms)
|
||
✔ HTTP failure and explicit same-Task resume reuse exact completed results and request hashes without repeating a command (7571.2057ms)
|
||
✔ a real process exit after plan persistence marks interruption and never issues an automatic model request (1035.0103ms)
|
||
✔ a stop from the event loop interrupts immediate model replies before later tools (1013.9589ms)
|
||
✔ a stop after the first tool preserves a complete interrupted multi-call protocol group (1523.4857ms)
|
||
✔ the compatible HTTP loop preserves call IDs, validates errors and waits before executing commands (4367.8721ms)
|
||
✔ denial prevents command execution and produces a paired denied result (1646.7693ms)
|
||
✔ stopping during approval interrupts pending calls without executing or replaying them (1174.5599ms)
|
||
✔ stopping a running fixture command terminates its own process tree and retains uncertain state (1774.138ms)
|
||
✔ command output decodes split UTF-8 and excludes the workbench key from child environment (949.2318ms)
|
||
✔ model-list testing uses a tentative key without changing the saved connection and redacts service errors (7.4022ms)
|
||
✔ truncated or repeated model calls fail before execution; tool input validation rejects unknown capabilities (2022.9889ms)
|
||
✔ request projection keeps exact tool pairs and complete recent user instructions while preserving disk history (1174.8941ms)
|
||
✔ the latest oversized session result reaches the next request together with already read source modules (2136.7538ms)
|
||
✔ every call in a large latest group keeps its actual outcome, including denied and unknown results (1232.4305ms)
|
||
✔ a small complete latest tool group is sent once and needs no duplicate feedback view (1373.7421ms)
|
||
✔ real HTTP repeated state inspection pauses after three identical engineering outcomes and preserves tool pairing (3238.5874ms)
|
||
✔ small code and actual failed command stay visible when their original multi-tool group cannot fit (1218.3437ms)
|
||
✔ mixed group retains six distinct small file observations with exact multilingual text and bounded request bytes (1655.731ms)
|
||
✔ working observations are bound to the current Task and stop treating a pre-application file revision as current evidence (1984.6639ms)
|
||
✔ a sealed observation rejects changed or missing original result artifacts instead of recreating evidence (1300.0902ms)
|
||
✔ a real passed-check observation is excluded after a source edit invalidates the check, while its historical sent evidence remains valid (5803.0905ms)
|
||
✔ budgeted file pages reconstruct UTF-8 text including long single lines and surrogate boundaries (4.1628ms)
|
||
✔ actual HTTP multi-tool reads survive an oversized runtime snapshot and the sealed evidence survives reopening (9861.9122ms)
|
||
✔ actual HTTP file pagination advances over a long file with each returned page visible in the next request (2883.8982ms)
|
||
✔ later mixed history pages cannot displace the actual module sources and complete requirements (6923.8193ms)
|
||
✔ a later narrow page of the same file revision cannot evict the wider actual observation (3869.6365ms)
|
||
✔ six small source files stay complete across metadata turns even when mandatory evidence exceeds the soft target (3272.3634ms)
|
||
✔ historical read-artifact navigation points to the original artifact and next page, never its result wrapper (1180.1926ms)
|
||
✔ a 1.6.1 full-provenance sent view remains verifiable after introducing the compact view (1202.8665ms)
|
||
✔ actual HTTP requests keep four observed modules after a later large history read and preserve all source bytes (12322.1705ms)
|
||
ℹ tests 131
|
||
ℹ suites 0
|
||
ℹ pass 130
|
||
ℹ fail 1
|
||
ℹ cancelled 0
|
||
ℹ skipped 0
|
||
ℹ todo 0
|
||
ℹ duration_ms 235230.262
|
||
|
||
✖ failing tests:
|
||
|
||
test at tests\engine-worker.test.mjs:90:1
|
||
✖ native input exceeding the context budget is retained and sends no model request (10231.6607ms)
|
||
AssertionError [ERR_ASSERTION]: The input did not match the regular expression /预算/. Input:
|
||
|
||
'原引擎必需输入超过上下文窗口可用容量,未发送模型请求。原输入和容量分项已保存;请核对模型容量后显式继续。'
|
||
|
||
at TestContext.<anonymous> (file:///D:/Ai-project/REA%E9%80%86%E5%90%91/Agent-Workbench/tests/engine-worker.test.mjs:98:91)
|
||
at process.processTicksAndRejections (node:internal/process/task_queues:104:5)
|
||
at async Test.run (node:internal/test_runner/test:1409:7)
|
||
at async Test.processPendingSubtests (node:internal/test_runner/test:974:7) {
|
||
generatedMessage: true,
|
||
code: 'ERR_ASSERTION',
|
||
actual: '原引擎必需输入超过上下文窗口可用容量,未发送模型请求。原输入和容量分项已保存;请核对模型容量后显式继续。',
|
||
expected: /预算/,
|
||
operator: 'match',
|
||
diff: 'simple'
|
||
}
|