87 lines
7.9 KiB
Plaintext
87 lines
7.9 KiB
Plaintext
✔ engineering inspection preserves a dirty Git baseline and treats project rules as data (2545.0663ms)
|
||
✔ real npm tests and build produce counted results, log artifacts and persistent verification (2925.1483ms)
|
||
✔ an actual failing test retains the nonzero exit code and failed count (1876.2903ms)
|
||
✔ unchanged automatic checks return original failure evidence, while explicit user reruns and changed source still execute (3849.0442ms)
|
||
✔ agent loops cannot hide identical failing checks behind new plan IDs or unrelated reads (6660.6303ms)
|
||
✔ zero tests, skipped tests and unrecognized stdout cannot become verification passes (6353.1516ms)
|
||
✔ a successful build with no selected tests does not verify the task (1680.7554ms)
|
||
✔ stale check plans and forged script names execute no project commands (1218.3321ms)
|
||
✔ applying a later proposal invalidates the prior passed engineering snapshot (2368.9972ms)
|
||
✔ stopping an actual check terminates its child process and blocks concurrent jobs (1677.1643ms)
|
||
✔ check timeout records a failure with its actual termination result (2127.1477ms)
|
||
✔ source edits during a successful check make the result stale (2860.1758ms)
|
||
✔ bounded large logs retain the test footer and readable artifact instead of inventing counts (2068.8691ms)
|
||
✔ model-selected checks require a run-bound decision and denial creates no check job (2583.1084ms)
|
||
✔ check APIs expose owned plans and jobs and preserve the authoritative results across restart (6361.6781ms)
|
||
✖ reviewed changes continue the original task without reopening a generic completed run (2389.2644ms)
|
||
✔ concurrent review-continuation API requests accept one run and retain the goal after restart (6954.4069ms)
|
||
✔ the model reads owned failure logs without running the check again (2856.1186ms)
|
||
✔ process exit at check queued preserves results and never replays commands (1588.615ms)
|
||
✔ process exit at check result_committed preserves results and never replays commands (1782.8096ms)
|
||
✔ controlled engine HTTP freezes one child, pages original owned input/report, rejects foreign reads and prevents changed-source reuse (14756.6728ms)
|
||
✔ native text and call IDs preserve original result pairing while unsupported content fails closed (0.7933ms)
|
||
✔ one engine child freezes real installation identity before creating tasks and rejects a changed source (7861.6339ms)
|
||
✔ owned native tools return saved results, use real approvals/checks and account each actual request once across new engine Runs (24812.4684ms)
|
||
✔ forged native scope cannot change a parent file and a final completion claim cannot replace worker proof (11560.7206ms)
|
||
✔ duplicate native IDs are rejected without replaying a saved tool (11954.1437ms)
|
||
✔ native input exceeding the context budget is retained and sends no model request (10363.614ms)
|
||
✔ stop retains a late reported model usage once and executes no tool from that output (10826.2269ms)
|
||
✔ a source change after the original model intent stops before native tools execute (11281.2103ms)
|
||
✔ an engine source change while approval is pending invalidates the old permission before any check starts (15964.5227ms)
|
||
✔ missing or noncompleted turn end cannot be adopted even with an owned receipt and assistant text (0.5717ms)
|
||
✔ closed root with an original live descendant remains unknown and retains its process tree (0.2552ms)
|
||
✔ host recovery reserves original pending attempts exactly once and explicit review preserves unknown outcomes (12996.7269ms)
|
||
✔ corrupted model reservation cannot reduce recovered budget or permit a new engine request (9468.4383ms)
|
||
✔ HTTP download preserves original malformed SSE bytes and artifact SHA instead of decoding invalid UTF8 (2149.9149ms)
|
||
✔ terminated SSE adapts empty optional tool arguments, retains the exact wire bytes and executes the validated batch once (2961.0366ms)
|
||
✔ reported SSE usage survives rejected required arguments "" without dispatching any tool (1882.199ms)
|
||
✔ reported SSE usage survives rejected required arguments "{\"path\":" without dispatching any tool (1873.6733ms)
|
||
✔ reported SSE usage survives rejected required arguments "null" without dispatching any tool (2060.5854ms)
|
||
✔ a stream without DONE retains reported usage but cannot adapt or execute even an optional tool (1279.4024ms)
|
||
✔ a timeout after reasoning-only fragments creates one unknown receipt and never invents reported tokens (1830.9344ms)
|
||
✔ real Chat SSE carries UTF8 and split tool JSON; Runtime executes only after DONE, stores partial progress and original usage (2377.5495ms)
|
||
✔ Responses typed SSE validates original item identity, terminal data, raw usage and tool result pair (3214.5157ms)
|
||
✔ incomplete network stream retains unknown attempt and never automatically switches pool or dispatches fragment tools (2041.1841ms)
|
||
✔ stopping an active HTTP stream closes only original request and keeps partial text without executing tools (1375.6341ms)
|
||
✔ explicit streaming probe uses actual SSE despite unknown declaration and binds its own original attempt (737.0617ms)
|
||
✔ coalesced initial SSE events publish the latest partial state even when the upstream stays idle (1521.7301ms)
|
||
✔ stream timeout closes the original HTTP response, preserves redacted capture and never retries (921.6323ms)
|
||
✔ SSE accepts CR-only final event boundaries and retains exact invalid UTF8 bytes without dispatch (0.8165ms)
|
||
▶ stream parser rejects truncation, finish length, malformed JSON, duplicate sequence, changed final item and oversized data
|
||
✔ reject 0 (0.2756ms)
|
||
✔ reject 1 (0.1534ms)
|
||
✔ reject 2 (0.3027ms)
|
||
✔ reject 3 (4.8004ms)
|
||
✔ reject 4 (0.1477ms)
|
||
✔ reject 5 (0.1334ms)
|
||
✔ stream parser rejects truncation, finish length, malformed JSON, duplicate sequence, changed final item and oversized data (6.3383ms)
|
||
✔ continuation reads advance through historical pages without a false pause while repeated current-Run pages still pause (1.8753ms)
|
||
✔ a new tool page replaces old latest-feedback space and still obeys its escaped protocol budget (0.5978ms)
|
||
✔ budgeted artifact pages count escaped protocol bytes and reconstruct original multilingual JSON without losing characters (9.0127ms)
|
||
✔ known artifact coverage detects semantic repeats despite changing limits, and advancing pages or direct evidence restore progress (0.3275ms)
|
||
✔ actual large artifact reads are present in the next bounded HTTP request and next_offset progresses without redoing tools (4131.6609ms)
|
||
✔ a real repeated artifact loop pauses the same Task after recorded results, survives reload and only resumes explicitly (4981.5002ms)
|
||
✔ actual HTTP continuation after reload sends distinct historically covered pages without false no_progress or replay (4561.5837ms)
|
||
✔ HTML without tests ends at reviewed file delivery and never offers automatic rechecking (2752.5698ms)
|
||
✔ diagnostic answers retain the unfinished task, limits and check result, and enforce read-only tools (2703.2991ms)
|
||
✔ review continuation is a system action and adds no testing demand or fake user instruction (1995.9131ms)
|
||
✔ a provider cannot execute tests against an explicit no-test task even if it ignores advertised tools (1562.275ms)
|
||
✔ alternating duplicate file reads and listing files still pauses without treating new pages as duplicates (5808.2319ms)
|
||
ℹ tests 68
|
||
ℹ suites 0
|
||
ℹ pass 67
|
||
ℹ fail 1
|
||
ℹ cancelled 0
|
||
ℹ skipped 0
|
||
ℹ todo 0
|
||
ℹ duration_ms 142273.8389
|
||
|
||
✖ failing tests:
|
||
|
||
test at tests\checks.test.mjs:193:1
|
||
✖ reviewed changes continue the original task without reopening a generic completed run (2389.2644ms)
|
||
TypeError [Error]: Cannot read properties of undefined (reading 'source')
|
||
at TestContext.<anonymous> (file:///D:/Ai-project/REA%E9%80%86%E5%90%91/Agent-Workbench/tests/checks.test.mjs:211:137)
|
||
at async Test.run (node:internal/test_runner/test:1409:7)
|
||
at async Test.processPendingSubtests (node:internal/test_runner/test:974:7)
|