Files
Agent-Workbench/docs/task-control-j-release-evidence/0221-task-control-j-remaining-regression.tap
T
2026-11-01 16:35:58 +08:00

56 lines
5.0 KiB
Plaintext
Raw Blame History

This file contains ambiguous Unicode characters
This file contains Unicode characters that might be confused with other characters. If you think that this is intentional, you can safely ignore this warning. Use the Escape button to reveal them.
✔ Python HTTP plans keep npm defaults, require owned approval and preserve actual results across restart (13931.9562ms)
✖ an isolated three-module Python Task repairs, checks and delivers a source-bound Git report without extra model calls (36368.4393ms)
✔ continuation reads advance through historical pages without a false pause while repeated current-Run pages still pause (2.9393ms)
✔ a new tool page replaces old latest-feedback space and still obeys its escaped protocol budget (0.6877ms)
✔ budgeted artifact pages count escaped protocol bytes and reconstruct original multilingual JSON without losing characters (9.4344ms)
✔ known artifact coverage detects semantic repeats despite changing limits, and advancing pages or direct evidence restore progress (0.3476ms)
✔ actual large artifact reads are present in the next bounded HTTP request and next_offset progresses without redoing tools (4535.8813ms)
✔ a real repeated artifact loop pauses the same Task after recorded results, survives reload and only resumes explicitly (4322.5207ms)
✔ actual HTTP continuation after reload sends distinct historically covered pages without false no_progress or replay (4268.5208ms)
✔ direct code evidence remains selected while recent historical-index browsing is archived within the complete request budget (1918.9441ms)
✔ one long user turn becomes bounded complete groups with exact UTF-8 history and recent JSON arguments (5199.8753ms)
✔ tool definitions, exact system bytes, output reserve and remaining Run/Task budget are accounted before requests (835.3667ms)
✔ oversized required user instructions pause intact and can be explicitly resumed after increasing the window (1354.2961ms)
✔ all task instructions, constraints and acceptance remain in the runtime system instead of an eight-item or byte prefix (1352.4009ms)
✔ a newest manageable multi-tool group stays exact even beyond the working target; oversized earlier groups are archived (840.1969ms)
✔ invalid orphan result is rejected before archive or network preparation (619.6969ms)
✔ invalid missing result is rejected before archive or network preparation (628.9616ms)
✔ invalid wrong result is rejected before archive or network preparation (628.8944ms)
✔ invalid duplicate call is rejected before archive or network preparation (644.2275ms)
✔ a group larger than the artifact limit uses verified Unicode-safe chunks without replacing tool JSON (1873.79ms)
✔ changed or missing archived evidence stops reuse and is never silently recreated (981.0295ms)
✔ transaction failure prevents publishing a plan and any corresponding model request (1181.1103ms)
✔ the Provider rejects body mutation after a sealed plan before calling HTTP (1285.3524ms)
✔ HTTP failure and explicit same-Task resume reuse exact completed results and request hashes without repeating a command (7630.6872ms)
✔ a real process exit after plan persistence marks interruption and never issues an automatic model request (1893.6939ms)
✔ operational questions are diagnostic while explicit repair requests remain execution instructions (1.0451ms)
✔ file delivery requires a positive instruction, not saved evidence or a prohibited write (1.186ms)
✔ an unsubstantiated text claim cannot complete a requested file delivery (1892.2823ms)
✔ HTML without tests ends at reviewed file delivery and never offers automatic rechecking (2829.804ms)
✔ diagnostic answers retain the unfinished task, limits and check result, and enforce read-only tools (3291.7505ms)
✔ review continuation is a system action and adds no testing demand or fake user instruction (1815.7109ms)
✔ a provider cannot execute tests against an explicit no-test task even if it ignores advertised tools (1668.1567ms)
✔ a budget pause becomes visible only after its input snapshot can be sealed with the original Run (2200.895ms)
✔ alternating duplicate file reads and listing files still pauses without treating new pages as duplicates (15230.2363ms)
ℹ tests 34
ℹ suites 0
ℹ pass 33
ℹ fail 1
ℹ cancelled 0
ℹ skipped 0
ℹ todo 0
ℹ duration_ms 71536.4728
✖ failing tests:
test at tests\python-api.test.mjs:38:1
✖ an isolated three-module Python Task repairs, checks and delivers a source-bound Git report without extra model calls (36368.4393ms)
Error: Unexpected Python Task state: paused/verification_incomplete
at file:///D:/Ai-project/REA%E9%80%86%E5%90%91/Agent-Workbench/tests/python-api.test.mjs:74:96
at process.processTicksAndRejections (node:internal/process/task_queues:104:5)
at async until (file:///D:/Ai-project/REA%E9%80%86%E5%90%91/Agent-Workbench/tests/helpers.mjs:38:12)
at async wait (file:///D:/Ai-project/REA%E9%80%86%E5%90%91/Agent-Workbench/tests/python-api.test.mjs:68:7)
at async TestContext.<anonymous> (file:///D:/Ai-project/REA%E9%80%86%E5%90%91/Agent-Workbench/tests/python-api.test.mjs:94:3)
at async Test.run (node:internal/test_runner/test:1409:7)
at async Test.processPendingSubtests (node:internal/test_runner/test:974:7)