TAP version 13 # Subtest: batch APIs enforce ownership and review fingerprints, apply once, and persist the completed batch across restart ok 1 - batch APIs enforce ownership and review fingerprints, apply once, and persist the completed batch across restart --- duration_ms: 6299.9472 type: 'test' ... # Subtest: delivery reports bind actual batch identity and reject corrupted snapshot evidence without changing project files ok 2 - delivery reports bind actual batch identity and reject corrupted snapshot evidence without changing project files --- duration_ms: 3848.2185 type: 'test' ... # Subtest: a compatible model can seal proposals through the real HTTP loop while application stays behind user review ok 3 - a compatible model can seal proposals through the real HTTP loop while application stays behind user review --- duration_ms: 6965.3848 type: 'test' ... # Subtest: a step-limited sealed batch applies and continues the same Task into actual checks without replaying saved tools not ok 4 - a step-limited sealed batch applies and continues the same Task into actual checks without replaying saved tools --- duration_ms: 6449.2848 type: 'test' location: 'D:\\Ai-project\\REA逆向\\Agent-Workbench\\tests\\change-set-api.test.mjs:74:1' failureType: 'testCodeFailure' error: |- Expected values to be strictly equal: + actual - expected + null - 'step_limit' code: 'ERR_ASSERTION' name: 'AssertionError' expected: 'step_limit' actual: ~ operator: 'strictEqual' stack: |- TestContext. (file:///D:/Ai-project/REA%E9%80%86%E5%90%91/Agent-Workbench/tests/change-set-api.test.mjs:99:10) process.processTicksAndRejections (node:internal/process/task_queues:104:5) async Test.run (node:internal/test_runner/test:1409:7) async Test.processPendingSubtests (node:internal/test_runner/test:974:7) ... # Subtest: applied batches cannot turn cancellation, other budgets, restart or unknown commands into a review continuation ok 5 - applied batches cannot turn cancellation, other budgets, restart or unknown commands into a review continuation --- duration_ms: 2288.197 type: 'test' ... # Subtest: a stop from the event loop interrupts immediate model replies before later tools ok 6 - a stop from the event loop interrupts immediate model replies before later tools --- duration_ms: 1539.0459 type: 'test' ... # Subtest: a stop after the first tool preserves a complete interrupted multi-call protocol group ok 7 - a stop after the first tool preserves a complete interrupted multi-call protocol group --- duration_ms: 2310.4461 type: 'test' ... # Subtest: the compatible HTTP loop preserves call IDs, validates errors and waits before executing commands ok 8 - the compatible HTTP loop preserves call IDs, validates errors and waits before executing commands --- duration_ms: 4282.6463 type: 'test' ... # Subtest: denial prevents command execution and produces a paired denied result ok 9 - denial prevents command execution and produces a paired denied result --- duration_ms: 1346.3415 type: 'test' ... # Subtest: stopping during approval interrupts pending calls without executing or replaying them ok 10 - stopping during approval interrupts pending calls without executing or replaying them --- duration_ms: 1687.164 type: 'test' ... # Subtest: stopping a running fixture command terminates its own process tree and retains uncertain state ok 11 - stopping a running fixture command terminates its own process tree and retains uncertain state --- duration_ms: 1493.9296 type: 'test' ... # Subtest: command output decodes split UTF-8 and excludes the workbench key from child environment ok 12 - command output decodes split UTF-8 and excludes the workbench key from child environment --- duration_ms: 1110.5178 type: 'test' ... # Subtest: model-list testing uses a tentative key without changing the saved connection and redacts service errors ok 13 - model-list testing uses a tentative key without changing the saved connection and redacts service errors --- duration_ms: 6.4228 type: 'test' ... # Subtest: truncated or repeated model calls fail before execution; tool input validation rejects unknown capabilities ok 14 - truncated or repeated model calls fail before execution; tool input validation rejects unknown capabilities --- duration_ms: 2837.0483 type: 'test' ... # Subtest: request projection keeps exact tool pairs and complete recent user instructions while preserving disk history ok 15 - request projection keeps exact tool pairs and complete recent user instructions while preserving disk history --- duration_ms: 1849.9172 type: 'test' ... # Subtest: operational questions are diagnostic while explicit repair requests remain execution instructions ok 16 - operational questions are diagnostic while explicit repair requests remain execution instructions --- duration_ms: 1.6404 type: 'test' ... # Subtest: an unsubstantiated text claim cannot complete a requested file delivery ok 17 - an unsubstantiated text claim cannot complete a requested file delivery --- duration_ms: 1172.607 type: 'test' ... # Subtest: HTML without tests ends at reviewed file delivery and never offers automatic rechecking ok 18 - HTML without tests ends at reviewed file delivery and never offers automatic rechecking --- duration_ms: 2547.1385 type: 'test' ... # Subtest: diagnostic answers retain the unfinished task, limits and check result, and enforce read-only tools ok 19 - diagnostic answers retain the unfinished task, limits and check result, and enforce read-only tools --- duration_ms: 3024.3009 type: 'test' ... # Subtest: review continuation is a system action and adds no testing demand or fake user instruction ok 20 - review continuation is a system action and adds no testing demand or fake user instruction --- duration_ms: 1667.2163 type: 'test' ... # Subtest: a provider cannot execute tests against an explicit no-test task even if it ignores advertised tools ok 21 - a provider cannot execute tests against an explicit no-test task even if it ignores advertised tools --- duration_ms: 1096.3211 type: 'test' ... # Subtest: a budget pause becomes visible only after its input snapshot can be sealed with the original Run ok 22 - a budget pause becomes visible only after its input snapshot can be sealed with the original Run --- duration_ms: 1035.6804 type: 'test' ... # Subtest: alternating duplicate file reads and listing files still pauses without treating new pages as duplicates ok 23 - alternating duplicate file reads and listing files still pauses without treating new pages as duplicates --- duration_ms: 10470.9645 type: 'test' ... 1..23 # tests 23 # suites 0 # pass 22 # fail 1 # cancelled 0 # skipped 0 # todo 0 # duration_ms 39737.5146