Files

91 lines
6.1 KiB
Plaintext

TAP version 13
# usage: {"event":"usage-unknown","business":"acme","run":"rb6ad1f5b21bb","instance":"assistant","turn":"0a2efbe4-6a2f-44e5-af9c-c6d60314afa6","source":"@none","code":"baseline-unknown"}
# usage: {"event":"usage-unknown","business":"acme","run":"r0eb35d40b86a","instance":"assistant","turn":"a496b5ab-090e-493b-a03d-05c06bf5e50c","source":"@none","code":"baseline-unknown"}
# usage: {"event":"usage-unknown","business":"acme","run":"re77ee664419c","instance":"assistant","turn":"9a0eefd5-9a2c-40d9-8c93-fff7383f7fcc","source":"@none","code":"baseline-unknown"}
# usage: {"event":"usage-unknown","business":"acme","run":"r180c2c6ed593","instance":"assistant","turn":"a9aae14a-5e0c-42e8-90be-46e44fc65979","source":"@none","code":"baseline-unknown"}
# Subtest: REQ-THREAD-2 REQ-LAUNCH-1 REQ-MSG-1 a thread message starts the thread's session, which stops when idle; its history survives the stop and a restart and no other thread sees it
ok 1 - REQ-THREAD-2 REQ-LAUNCH-1 REQ-MSG-1 a thread message starts the thread's session, which stops when idle; its history survives the stop and a restart and no other thread sees it
---
duration_ms: 5830.838516
type: 'test'
...
# usage: {"event":"usage-unknown","business":"acme","run":"r5ade9c5abb73","instance":"assistant","turn":"8c1459a9-e7f2-445a-b427-06157fa83852","source":"@none","code":"baseline-unknown"}
# usage: {"event":"usage-unknown","business":"acme","run":"r5ede1873b667","instance":"assistant","turn":"6bde4bc4-f2d1-4765-92b0-c09b7f434390","source":"@none","code":"baseline-unknown"}
# Subtest: REQ-THREAD-2 REQ-LAUNCH-1 a running thread counts against its model's limit and an idle-stopped one doesn't
ok 2 - REQ-THREAD-2 REQ-LAUNCH-1 a running thread counts against its model's limit and an idle-stopped one doesn't
---
duration_ms: 1744.655482
type: 'test'
...
# usage: {"event":"usage-unknown","business":"acme","run":"rbc96143c0955","instance":"assistant","turn":"1db7fc2f-d26b-4ed0-9813-f84604422fcb","source":"@none","code":"baseline-unknown"}
# Subtest: REQ-THREAD-2 REQ-LAUNCH-1 a turn longer than the idle time isn't stopped, and the thread idles out after it
ok 3 - REQ-THREAD-2 REQ-LAUNCH-1 a turn longer than the idle time isn't stopped, and the thread idles out after it
---
duration_ms: 4435.982598
type: 'test'
...
# usage: {"event":"usage-unknown","business":"acme","run":"rdae872029c54","instance":"assistant","turn":"ab9209ff-ef36-44ad-9108-05e7f7af1f4d","source":"@none","code":"baseline-unknown"}
# usage: {"event":"usage-unknown","business":"acme","run":"rdae872029c54","instance":"assistant","turn":"42586325-b659-4e4a-9a4d-1f39be95740e","source":"@none","code":"baseline-unknown"}
# Subtest: REQ-THREAD-2 REQ-LAUNCH-1 a message sent after the idle snapshot keeps the session, which answers it
ok 4 - REQ-THREAD-2 REQ-LAUNCH-1 a message sent after the idle snapshot keeps the session, which answers it
---
duration_ms: 2881.533996
type: 'test'
...
# Subtest: REQ-ROLE-2 REQ-LAUNCH-1 a thread held by a run the launcher didn't start gets no second session
ok 5 - REQ-ROLE-2 REQ-LAUNCH-1 a thread held by a run the launcher didn't start gets no second session
---
duration_ms: 76.274489
type: 'test'
...
# usage: {"event":"usage-unknown","business":"acme","run":"ra70ea4a5dde4","instance":"assistant","turn":"0a70c13f-656d-4af6-b3f6-4e8f83378394","source":"@none","code":"baseline-unknown"}
# Subtest: REQ-LAUNCH-1 a thread run's session file has no landing, even when landHolders names its instance
ok 6 - REQ-LAUNCH-1 a thread run's session file has no landing, even when landHolders names its instance
---
duration_ms: 371.707935
type: 'test'
...
# Subtest: REQ-LAUNCH-1 a run that ends without taking its thread's message isn't started again for that message
ok 7 - REQ-LAUNCH-1 a run that ends without taking its thread's message isn't started again for that message
---
duration_ms: 228.026468
type: 'test'
...
# Subtest: REQ-THREAD-2 REQ-LAUNCH-1 a thread id that isn't a safe segment, or a thread of a non-thread instance, launches nothing
ok 8 - REQ-THREAD-2 REQ-LAUNCH-1 a thread id that isn't a safe segment, or a thread of a non-thread instance, launches nothing
---
duration_ms: 220.298182
type: 'test'
...
# Subtest: REQ-THREAD-1 REQ-LAUNCH-1 the chief can't launch the assistant outside a thread
ok 9 - REQ-THREAD-1 REQ-LAUNCH-1 the chief can't launch the assistant outside a thread
---
duration_ms: 75.436755
type: 'test'
...
# limits: {"event":"limit-reached","business":"acme","check":"token-limit","export":"mayLaunch","subject":{"instance":"assistant","provider":"zai","model":"claude-sonnet-5-5","account":null},"path":["tokens","instances","assistant"],"limit":0,"count":0,"unknownTurns":0}
# limits: {"event":"limit-reached","business":"acme","check":"token-limit","export":"mayLaunch","subject":{"instance":"assistant","provider":"zai","model":"claude-sonnet-5-5","account":null},"path":["tokens","instances","assistant"],"limit":0,"count":0,"unknownTurns":0}
# Subtest: REQ-LIMIT-3 REQ-LIMIT-4 a thread start whose instance is at its token limit is refused, logged once with the limit and the count
ok 10 - REQ-LIMIT-3 REQ-LIMIT-4 a thread start whose instance is at its token limit is refused, logged once with the limit and the count
---
duration_ms: 189.035089
type: 'test'
...
# usage: {"event":"usage-unknown","business":"acme","run":"r8fe913dfa11a","instance":"assistant","turn":"9c6d8e34-432d-4e98-9c84-597e9851c30a","source":"@none","code":"baseline-unknown"}
# limits: {"event":"limit-reached","business":"acme","check":"token-limit","export":"mustStop","subject":{"instance":"assistant","provider":"zai","model":"claude-sonnet-5-5","account":null},"path":["tokens","instances","assistant"],"limit":0,"count":0,"unknownTurns":1}
# Subtest: REQ-LIMIT-4 a thread run at its token limit stops at the end of its turn: the reply lands, and the end record names the limit
ok 11 - REQ-LIMIT-4 a thread run at its token limit stops at the end of its turn: the reply lands, and the end record names the limit
---
duration_ms: 337.389868
type: 'test'
...
1..11
# tests 11
# suites 0
# pass 11
# fail 0
# cancelled 0
# skipped 0
# todo 0
# duration_ms 16519.142963