{ "grant": "sage-3004", "head": "f3a55ddf73cde1d1eadf593d35953d0bc03921e4", "base": "0cbe2e9b3", "manifest": "d746620768df71585dd2be1bc8a9fff93cb493fdf4a59fd16bc479dde4bc067d", "scope": { "whole_files": [ "packages/cli/tests/case1-accept.test.mjs", "packages/cli/tests/case2-unit.test.mjs" ], "shells": [ "scripts/test-auth.sh", "scripts/test-conductor.sh", "scripts/test-config.sh", "scripts/test-discord.sh", "scripts/test-extension-package.sh", "scripts/test-foundation.sh", "scripts/test-land-work.sh", "scripts/test-queue.sh", "scripts/test-release.sh", "scripts/test-task.sh" ], "mutants": [ "M1", "M2", "M3", "M4", "M5", "M6", "M7", "M8", "M9", "M10", "M11", "M12", "M13", "M14", "M15", "M16", "M17" ], "red_pattern": "row276 talk legacy inner timeout", "node_seconds": 900, "estimate_minutes": "12-18; no row276 measured runtime yet" }, "limits": { "files": { "packages/cli/tests/case1-accept.test.mjs": 900, "packages/cli/tests/case2-unit.test.mjs": 900 }, "basis": "No row276 timing yet; initial900s per whole file; Sage may adjust before CLEAR." }, "shell_limits": { "authority": [ "mos-1275", "sage-2659" ], "scope": "Own Gander row196 receipt set documented for row278, plus the complete row278 run3 shell phase. Row253 old C4 results do not carry. Receipts choose timeouts only.", "consulted_records": [ "ec1e7fad8:agents/gander/work/queue-196/evidence/suite-results-run1.json", "ec1e7fad8:agents/gander/work/queue-196/evidence/suite-results.json", "ec1e7fad8:agents/gander/work/queue-196/r2/mutants/results.json", "ec1e7fad8:agents/gander/work/queue-196/r2/run2/base-results.json", "ec1e7fad8:agents/gander/work/queue-196/r2/run2/killers/results.json", "ec1e7fad8:agents/gander/work/queue-196/r3/gate/base-results.json", "ec1e7fad8:agents/gander/work/queue-196/r3/gate/killers/results.json", "ec1e7fad8:agents/gander/work/queue-196/r3/gate/sso-results.json", "ec1e7fad8:agents/gander/work/queue-196/r4/gate/base-results.json", "ec1e7fad8:agents/gander/work/queue-196/r4/gate/killers/results.json", "ec1e7fad8:agents/gander/work/queue-196/r4/gate/sso-results.json", "ec1e7fad8:agents/gander/work/queue-196/r4/gate/whole-results.json", "ec1e7fad8:agents/gander/work/queue-196/r5/gate/whole-results.json", "ec1e7fad8:agents/gander/work/queue-196/r5/resume/summary.json", "ec1e7fad8:agents/gander/work/queue-196/r5/resume/whole-results.json", "ec1e7fad8:agents/gander/work/queue-196/r6/base-results.json", "ec1e7fad8:agents/gander/work/queue-196/r6/first-attempt/results.json", "ec1e7fad8:agents/gander/work/queue-196/r6/killers/results.json", "ec1e7fad8:agents/gander/work/queue-196/r6/summary.json", "ec1e7fad8:agents/gander/work/queue-196/r6/whole-results.json", "385a7194c:agents/gander/work/queue-278/run3/whole/results.json" ], "scripts": { "scripts/test-auth.sh": { "recorded_duration_seconds": 1.9081228229999543, "receipt": "3b91cfdaf:agents/gander/work/queue-253/run5-gate/SUMMARY.json (with earlier maximum retained)", "limit_seconds": 126, "derivation": "ceil(3 * longest successful whole-file receipt) + 120s headroom", "script_sha256": "dd4720cb0cbecd2fc523a318f2222d21d257c8c5889996a3d69e522ee971a707", "previous_maximum_seconds": 1.9081228229999543, "previous_receipt": "ec1e7fad8:agents/gander/work/queue-196/r6/whole-results.json", "row278_run3_seconds": 0.816 }, "scripts/test-conductor.sh": { "recorded_duration_seconds": 8.057173820000026, "receipt": "3b91cfdaf:agents/gander/work/queue-253/run5-gate/SUMMARY.json (with earlier maximum retained)", "limit_seconds": 145, "derivation": "ceil(3 * longest successful whole-file receipt) + 120s headroom", "script_sha256": "da84150467494a4c979759f400854411bd93a7efce981139757bf526d688a23b", "previous_maximum_seconds": 8.057173820000026, "previous_receipt": "ec1e7fad8:agents/gander/work/queue-196/r6/whole-results.json", "row278_run3_seconds": 6.078 }, "scripts/test-config.sh": { "recorded_duration_seconds": 3.1678915339999367, "receipt": "3b91cfdaf:agents/gander/work/queue-253/run5-gate/SUMMARY.json (with earlier maximum retained)", "limit_seconds": 130, "derivation": "ceil(3 * longest successful whole-file receipt) + 120s headroom", "script_sha256": "3301c1fabf616bb961d62f6decd0a46dadb0f399b8ba7f3c2ca60023d2b24c78", "previous_maximum_seconds": 3.1678915339999367, "previous_receipt": "ec1e7fad8:agents/gander/work/queue-196/r6/whole-results.json", "row278_run3_seconds": 1.868 }, "scripts/test-discord.sh": { "recorded_duration_seconds": 8.776727847000002, "receipt": "3b91cfdaf:agents/gander/work/queue-253/run5-gate/SUMMARY.json (with earlier maximum retained)", "limit_seconds": 147, "derivation": "ceil(3 * longest successful whole-file receipt) + 120s headroom", "script_sha256": "a5dcf783c51a5d5d184a357f91ebf9fa1c4e054f0cb84a3d1d7668f6156e025e", "previous_maximum_seconds": 8.776727847000002, "previous_receipt": "ec1e7fad8:agents/gander/work/queue-196/r5/resume/whole-results.json", "row278_run3_seconds": 7.431 }, "scripts/test-extension-package.sh": { "recorded_duration_seconds": 3.01285702399991, "receipt": "3b91cfdaf:agents/gander/work/queue-253/run5-gate/SUMMARY.json (with earlier maximum retained)", "limit_seconds": 130, "derivation": "ceil(3 * longest successful whole-file receipt) + 120s headroom", "script_sha256": "5d7b687f16fd1a9414b229501177d530ba3af4eadd3cac319b33f38fdba9bf99", "previous_maximum_seconds": 3.01285702399991, "previous_receipt": "ec1e7fad8:agents/gander/work/queue-196/r5/resume/whole-results.json", "row278_run3_seconds": 1.366 }, "scripts/test-foundation.sh": { "recorded_duration_seconds": 49.367, "receipt": "3b91cfdaf:agents/gander/work/queue-253/run5-gate/SUMMARY.json (with earlier maximum retained)", "limit_seconds": 269, "derivation": "ceil(3 * longest successful whole-file receipt) + 120s headroom", "script_sha256": "2e11038e7f784ec4f539eb768f63bab0fab9c9940334388a1fe2d47ab9e2b008", "previous_maximum_seconds": 39.70872647900006, "previous_receipt": "ec1e7fad8:agents/gander/work/queue-196/r5/resume/whole-results.json", "row278_run3_seconds": 39.901 }, "scripts/test-land-work.sh": { "recorded_duration_seconds": 16.854, "receipt": "3b91cfdaf:agents/gander/work/queue-253/run5-gate/SUMMARY.json (with earlier maximum retained)", "limit_seconds": 171, "derivation": "ceil(3 * longest successful whole-file receipt) + 120s headroom", "script_sha256": "c9d1d5c9b006d5c12e5f796a9828361059f8e0410846fc55c070c0148b15cef4", "previous_maximum_seconds": 12.623263413000037, "previous_receipt": "ec1e7fad8:agents/gander/work/queue-196/r5/resume/whole-results.json", "row278_run3_seconds": 11.338 }, "scripts/test-queue.sh": { "recorded_duration_seconds": 35.155, "receipt": "3b91cfdaf:agents/gander/work/queue-253/run5-gate/SUMMARY.json (with earlier maximum retained)", "limit_seconds": 226, "derivation": "ceil(3 * longest successful whole-file receipt) + 120s headroom", "script_sha256": "c270f181d1fa8b6d42ff4131c339beba786a8fd620bb66f8afdcec05e8b10868", "previous_maximum_seconds": 23.443742031000088, "previous_receipt": "ec1e7fad8:agents/gander/work/queue-196/r5/resume/whole-results.json", "row278_run3_seconds": 21.158 }, "scripts/test-release.sh": { "recorded_duration_seconds": 12.168674453999964, "receipt": "3b91cfdaf:agents/gander/work/queue-253/run5-gate/SUMMARY.json (with earlier maximum retained)", "limit_seconds": 157, "derivation": "ceil(3 * longest successful whole-file receipt) + 120s headroom", "script_sha256": "be706dff832257bd4781abeabd19faa4ac16edf9a4af0c96457e33cf3bb6deb3", "previous_maximum_seconds": 12.168674453999964, "previous_receipt": "ec1e7fad8:agents/gander/work/queue-196/r5/resume/whole-results.json", "row278_run3_seconds": 2.67 }, "scripts/test-task.sh": { "recorded_duration_seconds": 36.783798266, "receipt": "3b91cfdaf:agents/gander/work/queue-253/run5-gate/SUMMARY.json (with earlier maximum retained)", "limit_seconds": 231, "derivation": "ceil(3 * longest successful whole-file receipt) + 120s headroom", "script_sha256": "10c4abb70bf9b83e617089b06a5436cc7fa6b866a176458b22128c3a15163f94", "previous_maximum_seconds": 36.783798266, "previous_receipt": "ec1e7fad8:agents/gander/work/queue-196/r5/resume/whole-results.json", "row278_run3_seconds": 13.843 } } }, "carry": "NONE; fresh run4 per mos-1345/duckworth0208" } START whole-1 TAP version 13 # Subtest: row253 socket observation uses configured root, metadata and the Console peer without sending bytes ok 1 - row253 socket observation uses configured root, metadata and the Console peer without sending bytes --- duration_ms: 2382.905768 type: 'test' ... # Subtest: row253 P10 refuses unsafe metadata, wrong peers and an unsafe Python without claiming closure ok 2 - row253 P10 refuses unsafe metadata, wrong peers and an unsafe Python without claiming closure --- duration_ms: 32808.565531 type: 'test' ... # Subtest: row253 acceptance rejects bad config and unsupported copies before talk ok 3 - row253 acceptance rejects bad config and unsupported copies before talk --- duration_ms: 1532.966192 type: 'test' ... # Subtest: row253 stalled peer observation ends within its bound without leaving a reader ok 4 - row253 stalled peer observation ends within its bound without leaving a reader --- duration_ms: 4226.036952 type: 'test' ... # Subtest: row253 P8 refuses both retired TCP and board listeners ok 5 - row253 P8 refuses both retired TCP and board listeners --- duration_ms: 4093.370563 type: 'test' ... # Subtest: row253 C4 acceptance query inner reason holds under both sudo models ok 6 - row253 C4 acceptance query inner reason holds under both sudo models --- duration_ms: 10771.174759 type: 'test' ... # Subtest: row253 C4 acceptance query outer reason discards stdout and names residual cleanup ok 7 - row253 C4 acceptance query outer reason discards stdout and names residual cleanup --- duration_ms: 14196.557616 type: 'test' ... # Subtest: row253 C4 acceptance query overflow is output-limit in both models ok 8 - row253 C4 acceptance query overflow is output-limit in both models --- duration_ms: 494.350009 type: 'test' ... # Subtest: row253 C4 P10 inner reason holds under both sudo models not ok 9 - row253 C4 P10 inner reason holds under both sudo models --- duration_ms: 4212.907096 type: 'test' location: '/home/jwoltje/.t3/worktrees/mosaic-stack/gander-row196/packages/cli/tests/case1-accept.test.mjs:368:49' failureType: 'testCodeFailure' error: 'exec: 4.196571339999995s includes functional checks' code: 'ERR_ASSERTION' name: 'AssertionError' expected: true actual: false operator: '==' stack: |- TestContext. (file:///home/jwoltje/.t3/worktrees/mosaic-stack/gander-row196/packages/cli/tests/case1-accept.test.mjs:380:29) Test.runInAsyncScope (node:async_hooks:226:14) Test.run (node:internal/test_runner/test:1402:25) Test.processPendingSubtests (node:internal/test_runner/test:974:18) Test.postRun (node:internal/test_runner/test:1542:19) Test.run (node:internal/test_runner/test:1467:12) process.processTicksAndRejections (node:internal/process/task_queues:104:5) async Test.processPendingSubtests (node:internal/test_runner/test:974:7) ... # Subtest: row253 C4 P10 outer reason holds under both sudo models ok 10 - row253 C4 P10 outer reason holds under both sudo models --- duration_ms: 11787.811949 type: 'test' ... # Subtest: row253 C4 P10 overflow reason holds under both sudo models ok 11 - row253 C4 P10 overflow reason holds under both sudo models --- duration_ms: 4130.665081 type: 'test' ... # Subtest: row 195 accept: every check passing exits 0, with each P mark and counts that match the lines ok 12 - row 195 accept: every check passing exits 0, with each P mark and counts that match the lines --- duration_ms: 1942.69162 type: 'test' ... # Subtest: row 195 accept: exits 1 with each F check failing alone, and its line names it ok 13 - row 195 accept: exits 1 with each F check failing alone, and its line names it --- duration_ms: 22752.034579 type: 'test' ... # Subtest: row 195 accept: F3 fails on exit 0 with no reply line, and its evidence takes talk's error ok 14 - row 195 accept: F3 fails on exit 0 with no reply line, and its evidence takes talk's error --- duration_ms: 3929.312009 type: 'test' ... # Subtest: row 195 accept: F1 fails on a unit that isn't active or isn't User=mosaic ok 15 - row 195 accept: F1 fails on a unit that isn't active or isn't User=mosaic --- duration_ms: 3898.532647 type: 'test' ... # Subtest: row 195 accept: F2 fails when healthz doesn't answer and when another pid holds the port ok 16 - row 195 accept: F2 fails when healthz doesn't answer and when another pid holds the port --- duration_ms: 4366.57563 type: 'test' ... # Subtest: row 195 accept: F5 fails on unpriv_bwrap (enforce), on complain and on a trailing space ok 17 - row 195 accept: F5 fails on unpriv_bwrap (enforce), on complain and on a trailing space --- duration_ms: 9838.222823 type: 'test' ... # Subtest: row 195 accept: F5 fails with no bwrap of mosaic's, and passes on comm alone ok 18 - row 195 accept: F5 fails with no bwrap of mosaic's, and passes on comm alone --- duration_ms: 4668.88132 type: 'test' ... # Subtest: row 195 accept: F6 fails on a stub that prints nothing, on a path outside claude- and on a .. segment ok 19 - row 195 accept: F6 fails on a stub that prints nothing, on a path outside claude- and on a .. segment --- duration_ms: 5713.829938 type: 'test' ... # Subtest: row 195 accept: F7 fails on two live PM launches, one for another business, and no launch.by ok 20 - row 195 accept: F7 fails on two live PM launches, one for another business, and no launch.by --- duration_ms: 6209.075615 type: 'test' ... # Subtest: row 195 accept: F8 fails on 0640, on another owner and on a symlink, and never prints the credential ok 21 - row 195 accept: F8 fails on 0640, on another owner and on a symlink, and never prints the credential --- duration_ms: 6473.171739 type: 'test' ... # Subtest: row 195 accept: F9 fails on another owner, a group-writable mode and a number for the flag ok 22 - row 195 accept: F9 fails on another owner, a group-writable mode and a number for the flag --- duration_ms: 6213.723726 type: 'test' ... # Subtest: row 195 accept: F9 won't run --node as root off the pin path or with a writable directory above it ok 23 - row 195 accept: F9 won't run --node as root off the pin path or with a writable directory above it --- duration_ms: 6016.277175 type: 'test' ... # Subtest: row 195 accept: F11 fails on one *.json under discord/ and passes on an empty directory ok 24 - row 195 accept: F11 fails on one *.json under discord/ and passes on an empty directory --- duration_ms: 4586.041986 type: 'test' ... # Subtest: row 195 accept: each P check reports unnamed on its fault, and the exit stays 0 ok 25 - row 195 accept: each P check reports unnamed on its fault, and the exit stays 0 --- duration_ms: 18724.032782 type: 'test' ... # Subtest: row 195 accept: P2 is unnamed with a supplementary group, and P5 names docker ok 26 - row 195 accept: P2 is unnamed with a supplementary group, and P5 names docker --- duration_ms: 4306.726814 type: 'test' ... # Subtest: row 195 accept: P5 is closed with no jarvis account, and P2 with an empty authorized_keys ok 27 - row 195 accept: P5 is closed with no jarvis account, and P2 with an empty authorized_keys --- duration_ms: 2034.549139 type: 'test' ... # Subtest: row 195 accept: P9 is unnamed once for each item missing ok 28 - row 195 accept: P9 is unnamed once for each item missing --- duration_ms: 10394.742707 type: 'test' ... # Subtest: row253 accept: P10 fails its observation with another peer; P11 with the unit disabled ok 29 - row253 accept: P10 fails its observation with another peer; P11 with the unit disabled --- duration_ms: 4270.380528 type: 'test' ... # Subtest: row 195 accept: every P check unnamed together still exits 0 ok 30 - row 195 accept: every P check unnamed together still exits 0 --- duration_ms: 1859.930246 type: 'test' ... # Subtest: row 195 accept: a bad args file refuses with exit 2 before any check, each for its own reason ok 31 - row 195 accept: a bad args file refuses with exit 2 before any check, each for its own reason --- duration_ms: 117.410521 type: 'test' ... # Subtest: row 195 accept: usage errors and a run without --root as a user exit 2 ok 32 - row 195 accept: usage errors and a run without --root as a user exit 2 --- duration_ms: 14.287058 type: 'test' ... # Subtest: row 195 accept: every in-instance call goes through sudo -u mosaic -H env PATH=:... ok 33 - row 195 accept: every in-instance call goes through sudo -u mosaic -H env PATH=:... --- duration_ms: 2172.062142 type: 'test' ... # Subtest: row 195 accept: the host check runs with --check and never --enforce ok 34 - row 195 accept: the host check runs with --check and never --enforce --- duration_ms: 2107.070518 type: 'test' ... # Subtest: row276 legacy call inventory pins every production bound and the conversation contract ok 35 - row276 legacy call inventory pins every production bound and the conversation contract --- duration_ms: 0.430447 type: 'test' ... # Subtest: row276 talk legacy inner timeout cleans both sudo models ok 36 - row276 talk legacy inner timeout cleans both sudo models --- duration_ms: 1804.941733 type: 'test' ... # Subtest: row276 precheck legacy inner timeout cleans both sudo models ok 37 - row276 precheck legacy inner timeout cleans both sudo models --- duration_ms: 1868.88839 type: 'test' ... # Subtest: row276 claude-version legacy inner timeout cleans both sudo models ok 38 - row276 claude-version legacy inner timeout cleans both sudo models --- duration_ms: 1714.839012 type: 'test' ... # Subtest: row276 pm-list legacy inner timeout cleans both sudo models ok 39 - row276 pm-list legacy inner timeout cleans both sudo models --- duration_ms: 1708.30916 type: 'test' ... # Subtest: row276 node-version legacy inner timeout cleans both sudo models ok 40 - row276 node-version legacy inner timeout cleans both sudo models --- duration_ms: 1721.472041 type: 'test' ... # Subtest: row276 legacy streams and display status preserve failures without granting success ok 41 - row276 legacy streams and display status preserve failures without granting success --- duration_ms: 2801.676908 type: 'test' ... # Subtest: row276 trailer grammar cannot make supervisor failure pass ok 42 - row276 trailer grammar cannot make supervisor failure pass --- duration_ms: 2221.823199 type: 'test' ... # Subtest: row276 earlier forged trailer and appended zero remain failures ok 43 - row276 earlier forged trailer and appended zero remain failures --- duration_ms: 594.314017 type: 'test' ... # Subtest: row276 precheck outer bound discards success status and fixture cleans residual ok 44 - row276 precheck outer bound discards success status and fixture cleans residual --- duration_ms: 2218.865472 type: 'test' ... # Subtest: row276 case1 capture and legacy tools refuse unsafe system tools ok 45 - row276 case1 capture and legacy tools refuse unsafe system tools --- duration_ms: 81.609844 type: 'test' ... # Subtest: row276 stderr retention is bounded and keeps the final diagnostic ok 46 - row276 stderr retention is bounded and keeps the final diagnostic --- duration_ms: 286.857078 type: 'test' ... # Subtest: row276 version and PM checks refuse successful-looking stdout on supervisor failure ok 47 - row276 version and PM checks refuse successful-looking stdout on supervisor failure --- duration_ms: 17.876988 type: 'test' ... # Subtest: row276 full acceptance keeps all five healthy calls in both sudo models ok 48 - row276 full acceptance keeps all five healthy calls in both sudo models --- duration_ms: 4170.98118 type: 'test' ... # Subtest: row276 vanished pid stat read returns 3 with empty stderr in both scripts ok 49 - row276 vanished pid stat read returns 3 with empty stderr in both scripts --- duration_ms: 5.049826 type: 'test' ... # Subtest: row276 legacy stdout snapshot preserves exact bytes on success and command failure ok 50 - row276 legacy stdout snapshot preserves exact bytes on success and command failure --- duration_ms: 3373.039347 type: 'test' ... 1..50 # tests 50 # suites 0 # pass 49 # fail 1 # cancelled 0 # skipped 0 # todo 0 # duration_ms 247951.35731 Traceback (most recent call last): File "/home/jwoltje/.t3/worktrees/mosaic-stack/gander-row196/agents/gander/work/queue-276/run4/execute.py", line 13, in for i,f in enumerate(scope['whole_files']):step('whole-'+str(i+1),['node','--test','--test-reporter=tap',f]) ^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^ File "/home/jwoltje/.t3/worktrees/mosaic-stack/gander-row196/agents/gander/work/queue-276/run4/execute.py", line 9, in step if v['timeout'] or (v['code']==0 if red else v['code']!=0):raise RuntimeError('unexpected result: stop and classify '+name) ^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^ RuntimeError: unexpected result: stop and classify whole-1