65 lines
5.9 KiB
Plaintext
65 lines
5.9 KiB
Plaintext
✔ engineering inspection preserves a dirty Git baseline and treats project rules as data (2702.5765ms)
|
||
✔ real npm tests and build produce counted results, log artifacts and persistent verification (2569.4318ms)
|
||
✔ an actual failing test retains the nonzero exit code and failed count (2252.8093ms)
|
||
✔ unchanged automatic checks return original failure evidence, while explicit user reruns and changed source still execute (3784.8343ms)
|
||
✔ agent loops cannot hide identical failing checks behind new plan IDs or unrelated reads (9510.7716ms)
|
||
✔ zero tests, skipped tests and unrecognized stdout cannot become verification passes (7995.0283ms)
|
||
✔ a successful build with no selected tests does not verify the task (2043.1069ms)
|
||
✔ stale check plans and forged script names execute no project commands (1539.6436ms)
|
||
✔ applying a later proposal invalidates the prior passed engineering snapshot (2793.5203ms)
|
||
✔ stopping an actual check terminates its child process and blocks concurrent jobs (2048.8725ms)
|
||
✔ check timeout records a failure with its actual termination result (2788.2215ms)
|
||
✔ source edits during a successful check make the result stale (3815.2259ms)
|
||
✔ bounded large logs retain the test footer and readable artifact instead of inventing counts (3024.1205ms)
|
||
✔ model-selected checks require a run-bound decision and denial creates no check job (4449.4773ms)
|
||
✔ check APIs expose owned plans and jobs and preserve the authoritative results across restart (7494.451ms)
|
||
✔ reviewed changes continue the original task without reopening a generic completed run (4759.3128ms)
|
||
✔ concurrent review-continuation API requests accept one run and retain the goal after restart (16309.1948ms)
|
||
✔ the model reads owned failure logs without running the check again (5343.3675ms)
|
||
✔ process exit at check queued preserves results and never replays commands (2216.8371ms)
|
||
✔ process exit at check result_committed preserves results and never replays commands (2870.5215ms)
|
||
✔ HTTP download preserves original malformed SSE bytes and artifact SHA instead of decoding invalid UTF8 (2867.0308ms)
|
||
✔ terminated SSE adapts empty optional tool arguments, retains the exact wire bytes and executes the validated batch once (3445.4665ms)
|
||
✔ reported SSE usage survives rejected required arguments "" without dispatching any tool (1483.337ms)
|
||
✔ reported SSE usage survives rejected required arguments "{\"path\":" without dispatching any tool (1591.5308ms)
|
||
✔ reported SSE usage survives rejected required arguments "null" without dispatching any tool (1457.1147ms)
|
||
✔ a stream without DONE retains reported usage but cannot adapt or execute even an optional tool (2224.6439ms)
|
||
✔ a timeout after reasoning-only fragments creates one unknown receipt and never invents reported tokens (2836.847ms)
|
||
✔ real Chat SSE carries UTF8 and split tool JSON; Runtime executes only after DONE, stores partial progress and original usage (3710.1718ms)
|
||
✔ Responses typed SSE validates original item identity, terminal data, raw usage and tool result pair (3583.5143ms)
|
||
✔ incomplete network stream retains unknown attempt and never automatically switches pool or dispatches fragment tools (2475.7553ms)
|
||
✔ stopping an active HTTP stream closes only original request and keeps partial text without executing tools (1879.7497ms)
|
||
✔ explicit streaming probe uses actual SSE despite unknown declaration and binds its own original attempt (982.1347ms)
|
||
✔ coalesced initial SSE events publish the latest partial state even when the upstream stays idle (2391.6893ms)
|
||
✔ stream timeout closes the original HTTP response, preserves redacted capture and never retries (1365.9387ms)
|
||
✔ SSE accepts CR-only final event boundaries and retains exact invalid UTF8 bytes without dispatch (0.7314ms)
|
||
▶ stream parser rejects truncation, finish length, malformed JSON, duplicate sequence, changed final item and oversized data
|
||
✔ reject 0 (0.351ms)
|
||
✔ reject 1 (0.1877ms)
|
||
✔ reject 2 (0.1636ms)
|
||
✔ reject 3 (4.9466ms)
|
||
✔ reject 4 (0.1718ms)
|
||
✔ reject 5 (0.137ms)
|
||
✔ stream parser rejects truncation, finish length, malformed JSON, duplicate sequence, changed final item and oversized data (6.6902ms)
|
||
✔ continuation reads advance through historical pages without a false pause while repeated current-Run pages still pause (2.6777ms)
|
||
✔ a new tool page replaces old latest-feedback space and still obeys its escaped protocol budget (0.6335ms)
|
||
✔ budgeted artifact pages count escaped protocol bytes and reconstruct original multilingual JSON without losing characters (9.0948ms)
|
||
✔ known artifact coverage detects semantic repeats despite changing limits, and advancing pages or direct evidence restore progress (0.3422ms)
|
||
✔ actual large artifact reads are present in the next bounded HTTP request and next_offset progresses without redoing tools (4933.5479ms)
|
||
✔ a real repeated artifact loop pauses the same Task after recorded results, survives reload and only resumes explicitly (7328.3306ms)
|
||
✔ actual HTTP continuation after reload sends distinct historically covered pages without false no_progress or replay (8212.053ms)
|
||
✔ operational questions are diagnostic while explicit repair requests remain execution instructions (1.0844ms)
|
||
✔ HTML without tests ends at reviewed file delivery and never offers automatic rechecking (4032.3353ms)
|
||
✔ diagnostic answers retain the unfinished task, limits and check result, and enforce read-only tools (5030.3006ms)
|
||
✔ review continuation is a system action and adds no testing demand or fake user instruction (4684.2044ms)
|
||
✔ a provider cannot execute tests against an explicit no-test task even if it ignores advertised tools (2702.4452ms)
|
||
✔ alternating duplicate file reads and listing files still pauses without treating new pages as duplicates (24905.3452ms)
|
||
ℹ tests 55
|
||
ℹ suites 0
|
||
ℹ pass 55
|
||
ℹ fail 0
|
||
ℹ cancelled 0
|
||
ℹ skipped 0
|
||
ℹ todo 0
|
||
ℹ duration_ms 94531.2905
|