Files
Agent-Workbench/docs/task-control-j-release-evidence/0220-task-control-j-remaining-fixed-regression.tap
T
2026-11-01 16:35:58 +08:00

215 lines
9.3 KiB
Plaintext

TAP version 13
# Subtest: Python HTTP plans keep npm defaults, require owned approval and preserve actual results across restart
ok 1 - Python HTTP plans keep npm defaults, require owned approval and preserve actual results across restart
---
duration_ms: 13520.0123
type: 'test'
...
# Subtest: an isolated three-module Python Task repairs, checks and delivers a source-bound Git report without extra model calls
ok 2 - an isolated three-module Python Task repairs, checks and delivers a source-bound Git report without extra model calls
---
duration_ms: 58943.248
type: 'test'
...
# Subtest: continuation reads advance through historical pages without a false pause while repeated current-Run pages still pause
ok 3 - continuation reads advance through historical pages without a false pause while repeated current-Run pages still pause
---
duration_ms: 2.4966
type: 'test'
...
# Subtest: a new tool page replaces old latest-feedback space and still obeys its escaped protocol budget
ok 4 - a new tool page replaces old latest-feedback space and still obeys its escaped protocol budget
---
duration_ms: 0.5986
type: 'test'
...
# Subtest: budgeted artifact pages count escaped protocol bytes and reconstruct original multilingual JSON without losing characters
ok 5 - budgeted artifact pages count escaped protocol bytes and reconstruct original multilingual JSON without losing characters
---
duration_ms: 9.2139
type: 'test'
...
# Subtest: known artifact coverage detects semantic repeats despite changing limits, and advancing pages or direct evidence restore progress
ok 6 - known artifact coverage detects semantic repeats despite changing limits, and advancing pages or direct evidence restore progress
---
duration_ms: 0.4167
type: 'test'
...
# Subtest: actual large artifact reads are present in the next bounded HTTP request and next_offset progresses without redoing tools
ok 7 - actual large artifact reads are present in the next bounded HTTP request and next_offset progresses without redoing tools
---
duration_ms: 6586.5361
type: 'test'
...
# Subtest: a real repeated artifact loop pauses the same Task after recorded results, survives reload and only resumes explicitly
ok 8 - a real repeated artifact loop pauses the same Task after recorded results, survives reload and only resumes explicitly
---
duration_ms: 5056.233
type: 'test'
...
# Subtest: actual HTTP continuation after reload sends distinct historically covered pages without false no_progress or replay
ok 9 - actual HTTP continuation after reload sends distinct historically covered pages without false no_progress or replay
---
duration_ms: 5624.9767
type: 'test'
...
# Subtest: direct code evidence remains selected while recent historical-index browsing is archived within the complete request budget
ok 10 - direct code evidence remains selected while recent historical-index browsing is archived within the complete request budget
---
duration_ms: 1506.3286
type: 'test'
...
# Subtest: one long user turn becomes bounded complete groups with exact UTF-8 history and recent JSON arguments
ok 11 - one long user turn becomes bounded complete groups with exact UTF-8 history and recent JSON arguments
---
duration_ms: 4037.9268
type: 'test'
...
# Subtest: tool definitions, exact system bytes, output reserve and remaining Run/Task budget are accounted before requests
ok 12 - tool definitions, exact system bytes, output reserve and remaining Run/Task budget are accounted before requests
---
duration_ms: 1004.3704
type: 'test'
...
# Subtest: oversized required user instructions pause intact and can be explicitly resumed after increasing the window
ok 13 - oversized required user instructions pause intact and can be explicitly resumed after increasing the window
---
duration_ms: 1545.5527
type: 'test'
...
# Subtest: all task instructions, constraints and acceptance remain in the runtime system instead of an eight-item or byte prefix
ok 14 - all task instructions, constraints and acceptance remain in the runtime system instead of an eight-item or byte prefix
---
duration_ms: 1385.8941
type: 'test'
...
# Subtest: a newest manageable multi-tool group stays exact even beyond the working target; oversized earlier groups are archived
ok 15 - a newest manageable multi-tool group stays exact even beyond the working target; oversized earlier groups are archived
---
duration_ms: 1510.6174
type: 'test'
...
# Subtest: invalid orphan result is rejected before archive or network preparation
ok 16 - invalid orphan result is rejected before archive or network preparation
---
duration_ms: 555.9787
type: 'test'
...
# Subtest: invalid missing result is rejected before archive or network preparation
ok 17 - invalid missing result is rejected before archive or network preparation
---
duration_ms: 544.7862
type: 'test'
...
# Subtest: invalid wrong result is rejected before archive or network preparation
ok 18 - invalid wrong result is rejected before archive or network preparation
---
duration_ms: 812.1619
type: 'test'
...
# Subtest: invalid duplicate call is rejected before archive or network preparation
ok 19 - invalid duplicate call is rejected before archive or network preparation
---
duration_ms: 1134.544
type: 'test'
...
# Subtest: a group larger than the artifact limit uses verified Unicode-safe chunks without replacing tool JSON
ok 20 - a group larger than the artifact limit uses verified Unicode-safe chunks without replacing tool JSON
---
duration_ms: 2065.3226
type: 'test'
...
# Subtest: changed or missing archived evidence stops reuse and is never silently recreated
ok 21 - changed or missing archived evidence stops reuse and is never silently recreated
---
duration_ms: 1407.0019
type: 'test'
...
# Subtest: transaction failure prevents publishing a plan and any corresponding model request
ok 22 - transaction failure prevents publishing a plan and any corresponding model request
---
duration_ms: 820.0021
type: 'test'
...
# Subtest: the Provider rejects body mutation after a sealed plan before calling HTTP
ok 23 - the Provider rejects body mutation after a sealed plan before calling HTTP
---
duration_ms: 1223.8612
type: 'test'
...
# Subtest: HTTP failure and explicit same-Task resume reuse exact completed results and request hashes without repeating a command
ok 24 - HTTP failure and explicit same-Task resume reuse exact completed results and request hashes without repeating a command
---
duration_ms: 9862.2924
type: 'test'
...
# Subtest: a real process exit after plan persistence marks interruption and never issues an automatic model request
ok 25 - a real process exit after plan persistence marks interruption and never issues an automatic model request
---
duration_ms: 2047.084
type: 'test'
...
# Subtest: operational questions are diagnostic while explicit repair requests remain execution instructions
ok 26 - operational questions are diagnostic while explicit repair requests remain execution instructions
---
duration_ms: 1.0183
type: 'test'
...
# Subtest: file delivery requires a positive instruction, not saved evidence or a prohibited write
ok 27 - file delivery requires a positive instruction, not saved evidence or a prohibited write
---
duration_ms: 1.2456
type: 'test'
...
# Subtest: an unsubstantiated text claim cannot complete a requested file delivery
ok 28 - an unsubstantiated text claim cannot complete a requested file delivery
---
duration_ms: 1534.2028
type: 'test'
...
# Subtest: HTML without tests ends at reviewed file delivery and never offers automatic rechecking
ok 29 - HTML without tests ends at reviewed file delivery and never offers automatic rechecking
---
duration_ms: 4245.0117
type: 'test'
...
# Subtest: diagnostic answers retain the unfinished task, limits and check result, and enforce read-only tools
ok 30 - diagnostic answers retain the unfinished task, limits and check result, and enforce read-only tools
---
duration_ms: 4442.2059
type: 'test'
...
# Subtest: review continuation is a system action and adds no testing demand or fake user instruction
ok 31 - review continuation is a system action and adds no testing demand or fake user instruction
---
duration_ms: 2306.9875
type: 'test'
...
# Subtest: a provider cannot execute tests against an explicit no-test task even if it ignores advertised tools
ok 32 - a provider cannot execute tests against an explicit no-test task even if it ignores advertised tools
---
duration_ms: 2481.3613
type: 'test'
...
# Subtest: a budget pause becomes visible only after its input snapshot can be sealed with the original Run
ok 33 - a budget pause becomes visible only after its input snapshot can be sealed with the original Run
---
duration_ms: 1902.7676
type: 'test'
...
# Subtest: alternating duplicate file reads and listing files still pauses without treating new pages as duplicates
ok 34 - alternating duplicate file reads and listing files still pauses without treating new pages as duplicates
---
duration_ms: 11940.4518
type: 'test'
...
1..34
# tests 34
# suites 0
# pass 34
# fail 0
# cancelled 0
# skipped 0
# todo 0
# duration_ms 78112.3324