AK-Benchbenchmark report

Runs

every recorded run, newest first

runparametersstartedtaskagentrepetitionstatusverdictscoretimeinput tokensgenerated tokenstotal tokenstool callsfailure classerror
run-20261102-204014-9fa0f82eknowledge_enabled=False, model=qwen/Qwen3.8-Flash-Next2026-11-02 20:40:14stockpile-fefo-001@1.0.0codex@codex-cli 0.166.02completedpassed1.0004 m 59 s256,1898,521264,71014none—
run-20261102-203510-2919460cknowledge_enabled=False, model=qwen/Qwen3.8-Flash-Next2026-11-02 20:35:10stockpile-fefo-001@1.0.0codex@codex-cli 0.166.01completedpassed1.0005 m 3 s287,1487,894295,04217none—
run-20261102-202449-2aaf3e0fknowledge_enabled=False, model=qwen/Qwen3.8-27B2026-11-02 20:24:49stockpile-fefo-001@1.0.0codex@codex-cli 0.166.03completedpassed1.00010 m 20 s433,52915,274448,80323none—
run-20261102-201952-bdfed954knowledge_enabled=False, model=qwen/Qwen3.8-27B2026-11-02 20:19:52stockpile-fefo-001@1.0.0codex@codex-cli 0.166.02completedpassed1.0004 m 57 s212,7845,246218,03014none—
run-20261102-200902-2be9dbd5knowledge_enabled=False, model=qwen/Qwen3.8-27B2026-11-02 20:09:02stockpile-fefo-001@1.0.0codex@codex-cli 0.166.01completedpassed1.00010 m 48 s536,45214,854551,30627none—
run-20261102-195713-1edd6fafknowledge_enabled=True, model=auto_codex2026-11-02 19:57:13ledgerlite-reconcile-001@1.0.0codex@codex-cli 0.166.03completedpartial0.95011 m 48 s732,53118,140750,67127none—
run-20261102-194904-cb1d7f72knowledge_enabled=True, model=auto_codex2026-11-02 19:49:04ledgerlite-reconcile-001@1.0.0codex@codex-cli 0.166.02completedpassed1.0008 m 9 s439,70212,057451,75921none—
run-20261102-193822-f24e2c68knowledge_enabled=True, model=auto_codex2026-11-02 19:38:22ledgerlite-reconcile-001@1.0.0codex@codex-cli 0.166.01completedpassed1.00010 m 41 s452,35117,677470,02821none—
run-20261102-192932-7bb86699knowledge_enabled=False, model=auto_codex2026-11-02 19:29:32ledgerlite-reconcile-001@1.0.0codex@codex-cli 0.166.03completedpassed1.0008 m 49 s435,34914,597449,94621none—
run-20261102-192057-a14677ebknowledge_enabled=False, model=auto_codex2026-11-02 19:20:57ledgerlite-reconcile-001@1.0.0codex@codex-cli 0.166.02completedpassed1.0008 m 34 s439,89515,003454,89819none—
run-20261102-191101-7b74b38fknowledge_enabled=False, model=auto_codex2026-11-02 19:11:01ledgerlite-reconcile-001@1.0.0codex@codex-cli 0.166.01completedpartial0.9509 m 56 s392,28314,473406,75620none—
run-20261102-190125-007b2709knowledge_enabled=False, model=qwen/Qwen3.8-Flash-Next2026-11-02 19:01:25ledgerlite-reconcile-001@1.0.0codex@codex-cli 0.166.03completedpartial0.9509 m 34 s528,14518,654546,79917none—
run-20261102-185122-1a50269fknowledge_enabled=False, model=qwen/Qwen3.8-Flash-Next2026-11-02 18:51:22ledgerlite-reconcile-001@1.0.0codex@codex-cli 0.166.02completedpartial0.95010 m 2 s641,24020,168661,40824none—
run-20261102-183618-1b2f49a8knowledge_enabled=False, model=qwen/Qwen3.8-Flash-Next2026-11-02 18:36:18ledgerlite-reconcile-001@1.0.0codex@codex-cli 0.166.01timeoutnot measurednot measured15 m 4 s788,75733,258822,01527agentTests are green and formatting is clean. Re-running my full spec harness once more and cleaning the `.pyc` noise my runs created.
run-20261102-182113-fb3e7151knowledge_enabled=False, model=qwen/Qwen3.8-27B2026-11-02 18:21:13ledgerlite-reconcile-001@1.0.0codex@codex-cli 0.166.03timeoutnot measurednot measured15 m 4 s417,45224,042441,49420agentI'm checking the line 115 assertion to verify the entry ID matches "e-b", but I'm confused about which entries have the reference "ZZ" — both e-a and e-b do, so I need to figure out which one the assertion is actually pointing to.
run-20261102-180608-fb09d647knowledge_enabled=False, model=qwen/Qwen3.8-27B2026-11-02 18:06:08ledgerlite-reconcile-001@1.0.0codex@codex-cli 0.166.02timeoutnot measurednot measured15 m 4 s306,91223,952330,86416agentI need to fix my test expectations — the test had incorrect sign conventions. Let me trace through what the correct signs should be for each line: `e3` has a debit-normal account with a debit of 700, so it should be +700, meaning L3 should be +700; `e1` is a liability account with a credit of 1000, giving -1000 for L1. The implementation is actually working correctly — the test failures were in my own test expectations, not the code itself. I need to fix the test data: L3 should be +700 instead of -700, and I'll adjust the expected difference_cents and open_candidates accordingly. Then I'll re-run the full test suite to verify everything passes.
run-20261102-175103-7eadf2c3knowledge_enabled=False, model=qwen/Qwen3.8-27B2026-11-02 17:51:03ledgerlite-reconcile-001@1.0.0codex@codex-cli 0.166.01timeoutnot measurednot measured15 m 4 s590,24323,356613,59926agentThe two identical entries are mapping to the same one due to how frozen dataclass equality works — both e1 and e2 have matching field values, so they're treated as equal. That's why the dict comprehension collapsed to a single key when it built the entry_of mapping.
run-20261102-173920-82f7a48cknowledge_enabled=True, model=auto_codex2026-11-02 17:39:20freight-shop-001@1.0.0codex@codex-cli 0.166.03completedpassed1.00011 m 43 s676,05622,481698,53726none—
run-20261102-172849-b26fa228knowledge_enabled=True, model=auto_codex2026-11-02 17:28:49freight-shop-001@1.0.0codex@codex-cli 0.166.02completedpartial0.94110 m 30 s515,52217,044532,56623none—
run-20261102-171345-07e43bdbknowledge_enabled=True, model=auto_codex2026-11-02 17:13:45freight-shop-001@1.0.0codex@codex-cli 0.166.01timeoutnot measurednot measured15 m 3 s581,22026,757607,97724agentAll 19 spec checks pass. Final verification — full suite plus a review of the finished body:
run-20261102-170536-da2abfe7knowledge_enabled=False, model=auto_codex2026-11-02 17:05:36freight-shop-001@1.0.0codex@codex-cli 0.166.03completedpassed1.0008 m 7 s389,74114,953404,69420none—
run-20261102-165407-d907f577knowledge_enabled=False, model=auto_codex2026-11-02 16:54:07freight-shop-001@1.0.0codex@codex-cli 0.166.02completedpartial0.94111 m 28 s361,98619,008380,99417none—
run-20261102-164738-43ff8923knowledge_enabled=False, model=auto_codex2026-11-02 16:47:38freight-shop-001@1.0.0codex@codex-cli 0.166.01completedpartial0.9416 m 29 s254,4259,577264,00214none—
run-20261102-163521-b51708f9knowledge_enabled=False, model=qwen/Qwen3.8-Flash-Next2026-11-02 16:35:21freight-shop-001@1.0.0codex@codex-cli 0.166.03completedpassed1.00012 m 16 s819,72125,306845,02729none—
run-20261102-162330-279c2d0eknowledge_enabled=False, model=qwen/Qwen3.8-Flash-Next2026-11-02 16:23:30freight-shop-001@1.0.0codex@codex-cli 0.166.02completedpassed1.00011 m 50 s597,87025,858623,72824none—
run-20261102-161153-16c04a4eknowledge_enabled=False, model=qwen/Qwen3.8-Flash-Next2026-11-02 16:11:53freight-shop-001@1.0.0codex@codex-cli 0.166.01completedpartial0.94111 m 36 s709,38023,886733,26625none—
run-20261102-160115-cb48ab31knowledge_enabled=False, model=qwen/Qwen3.8-27B2026-11-02 16:01:15freight-shop-001@1.0.0codex@codex-cli 0.166.03completedpartial0.94110 m 38 s402,64615,902418,54817none—
run-20261102-154610-09481f31knowledge_enabled=False, model=qwen/Qwen3.8-27B2026-11-02 15:46:10freight-shop-001@1.0.0codex@codex-cli 0.166.02timeoutnot measurednot measured15 m 3 s345,90824,250370,15818agentThe code works correctly — my test had the wrong assumption. I forgot the default divisor is 5000, so 130×30×20 gives volumetric 15.6 kg (billed 16.0 kg), not 3.0 kg. The linehaul is 4200, surcharge 500, total 4700 — and the group logic worked perfectly: `oversize` won, `heavy` was suppressed, winner named.
run-20261102-153629-de5ac66dknowledge_enabled=False, model=qwen/Qwen3.8-27B2026-11-02 15:36:29freight-shop-001@1.0.0codex@codex-cli 0.166.01completedpartial0.9419 m 40 s514,93012,666527,59625none—
run-20261102-152123-401b3de4knowledge_enabled=True, model=auto_codex2026-11-02 15:21:23cadence-catchup-001@1.0.0codex@codex-cli 0.166.03timeoutnot measurednot measured15 m 5 s405,54824,862430,41022agentMost failures are test-harness artifacts, not implementation bugs — let me fix the script (tz-aware string formatting, wrong window for the staggered case, empty `reasons()` on a fully-planned chain) and re-run.
run-20261102-150618-18c32d85knowledge_enabled=True, model=auto_codex2026-11-02 15:06:18cadence-catchup-001@1.0.0codex@codex-cli 0.166.02timeoutnot measurednot measured15 m 4 s543,45728,631572,08823agentThe scratch script itself is buggy. Let me print actual values to debug quickly.
run-20261102-145348-58a7a3f3knowledge_enabled=True, model=auto_codex2026-11-02 14:53:48cadence-catchup-001@1.0.0codex@codex-cli 0.166.01completedpartial0.92012 m 29 s836,66723,155859,82230none—
run-20261102-143842-25bc3410knowledge_enabled=False, model=auto_codex2026-11-02 14:38:42cadence-catchup-001@1.0.0codex@codex-cli 0.166.03timeoutnot measurednot measured15 m 5 s507,66028,184535,84421agentMy assertion there forgot that `a`'s missing days are also planned and `b@1` is satisfied by history. Let me make the harness self-reporting so mismatches are diagnosable.
run-20261102-142710-0136dc94knowledge_enabled=False, model=auto_codex2026-11-02 14:27:10cadence-catchup-001@1.0.0codex@codex-cli 0.166.02completedpassed1.00011 m 32 s409,64723,502433,14916none—
run-20261102-141204-1573e7b2knowledge_enabled=False, model=auto_codex2026-11-02 14:12:04cadence-catchup-001@1.0.0codex@codex-cli 0.166.01timeoutnot measurednot measured15 m 4 s469,38726,193495,58019agentBoth were again my own expectation errors — the plan output is correct in each case. Now the critical rules: `depends_on_past`, the cap, ordering, and purity.
run-20261102-135659-dfdbb7eeknowledge_enabled=False, model=qwen/Qwen3.8-Flash-Next2026-11-02 13:56:59cadence-catchup-001@1.0.0codex@codex-cli 0.166.03timeoutnot measurednot measured15 m 5 s452,41432,517484,93119agentSeveral more of my expectations were wrong (an always-planned upstream settles its dependents, so real waits need staggered schedules). Rewriting with `(day, hour)` tuples and genuinely blocked upstreams.
run-20261102-134326-1f193cecknowledge_enabled=False, model=qwen/Qwen3.8-Flash-Next2026-11-02 13:43:26cadence-catchup-001@1.0.0codex@codex-cli 0.166.02completedpartial0.96013 m 32 s946,33228,707975,03930none—
run-20261102-132819-55ee19e1knowledge_enabled=False, model=qwen/Qwen3.8-Flash-Next2026-11-02 13:28:19cadence-catchup-001@1.0.0codex@codex-cli 0.166.01timeoutnot measurednot measured15 m 5 s949,88433,200983,08430agentThe `covers` helper was wrong — history-settled occurrences belong to neither list by spec. Fixing the helper.
run-20261102-131314-47751b92knowledge_enabled=False, model=qwen/Qwen3.8-27B2026-11-02 13:13:14cadence-catchup-001@1.0.0codex@codex-cli 0.166.03timeoutnot measurednot measured15 m 5 s1,793,96820,1711,814,13953agentNow let me fix my test's history times (they must match the 06:00 occurrence instants, per "at that exact logical time") and re-run.
run-20261102-125808-280ac90dknowledge_enabled=False, model=qwen/Qwen3.8-27B2026-11-02 12:58:08cadence-catchup-001@1.0.0codex@codex-cli 0.166.02timeoutnot measurednot measured15 m 5 s823,34718,432841,77933agentThe implementation is complete and syntactically valid. Let me run the full test suite and my spec-based checks to confirm everything is green.
run-20261102-124303-45bdfb12knowledge_enabled=False, model=qwen/Qwen3.8-27B2026-11-02 12:43:03cadence-catchup-001@1.0.0codex@codex-cli 0.166.01timeoutnot measurednot measured15 m 4 s1,030,27421,3011,051,57539agentSuite is green. Let me re-verify the full spec behavior with the final implementation, including a few extra edge cases I hadn't covered (staggered schedules, attempts, DST).
run-20261102-124013-4e335fc0knowledge_enabled=True, model=auto_codex2026-11-02 12:40:13stockpile-writeoff-001@1.0.0codex@codex-cli 0.166.03completedpassed1.0002 m 48 s147,8692,504150,37314none—
run-20261102-123722-abf5b6a0knowledge_enabled=True, model=auto_codex2026-11-02 12:37:22stockpile-writeoff-001@1.0.0codex@codex-cli 0.166.02completedpassed1.0002 m 50 s159,4521,673161,12512none—
run-20261102-123353-08bae5f2knowledge_enabled=True, model=auto_codex2026-11-02 12:33:53stockpile-writeoff-001@1.0.0codex@codex-cli 0.166.01completedpassed1.0003 m 28 s174,0553,204177,25912none—
run-20261102-122856-43bd96e6knowledge_enabled=False, model=auto_codex2026-11-02 12:28:56stockpile-writeoff-001@1.0.0codex@codex-cli 0.166.03completedpassed1.0004 m 56 s290,1165,054295,17018none—
run-20261102-122358-fec2acfeknowledge_enabled=False, model=auto_codex2026-11-02 12:23:58stockpile-writeoff-001@1.0.0codex@codex-cli 0.166.02completedpassed1.0004 m 57 s284,3844,090288,47416none—
run-20261102-122054-f8985461knowledge_enabled=False, model=auto_codex2026-11-02 12:20:54stockpile-writeoff-001@1.0.0codex@codex-cli 0.166.01completedpassed1.0003 m 3 s130,7163,022133,73810none—
run-20261102-121528-03d9f220knowledge_enabled=False, model=qwen/Qwen3.8-Flash-Next2026-11-02 12:15:28stockpile-writeoff-001@1.0.0codex@codex-cli 0.166.03completedpassed1.0005 m 26 s293,3468,697302,04317none—
run-20261102-121131-13e4a8b5knowledge_enabled=False, model=qwen/Qwen3.8-Flash-Next2026-11-02 12:11:31stockpile-writeoff-001@1.0.0codex@codex-cli 0.166.02completedpassed1.0003 m 55 s216,2535,255221,50812none—
run-20261102-120616-d577d4b1knowledge_enabled=False, model=qwen/Qwen3.8-Flash-Next2026-11-02 12:06:16stockpile-writeoff-001@1.0.0codex@codex-cli 0.166.01completedpassed1.0005 m 15 s256,4468,216264,66216none—
run-20261102-120435-e4b44447knowledge_enabled=False, model=qwen/Qwen3.8-27B2026-11-02 12:04:35stockpile-writeoff-001@1.0.0codex@codex-cli 0.166.03completedpassed1.0001 m 40 s86,40794887,3557none—
run-20261102-120221-58de15afknowledge_enabled=False, model=qwen/Qwen3.8-27B2026-11-02 12:02:21stockpile-writeoff-001@1.0.0codex@codex-cli 0.166.02completedpassed1.0002 m 13 s131,9341,632133,56610none—
run-20261102-115850-e5f2348fknowledge_enabled=False, model=qwen/Qwen3.8-27B2026-11-02 11:58:50stockpile-writeoff-001@1.0.0codex@codex-cli 0.166.01completedpassed1.0003 m 30 s174,8333,032177,86512none—
run-20261102-115611-ee478152knowledge_enabled=True, model=auto_codex2026-11-02 11:56:11ledgerlite-rates-001@1.0.0codex@codex-cli 0.166.03completedpassed1.0002 m 39 s82,7732,11484,88710none—
run-20261102-115051-39be5247knowledge_enabled=True, model=auto_codex2026-11-02 11:50:51ledgerlite-rates-001@1.0.0codex@codex-cli 0.166.02completedpassed1.0005 m 19 s233,2265,848239,07416none—
run-20261102-114752-9f3f4f92knowledge_enabled=True, model=auto_codex2026-11-02 11:47:52ledgerlite-rates-001@1.0.0codex@codex-cli 0.166.01completedpassed1.0002 m 59 s109,7083,384113,09210none—
run-20261102-114446-b3513377knowledge_enabled=False, model=auto_codex2026-11-02 11:44:46ledgerlite-rates-001@1.0.0codex@codex-cli 0.166.03completedpassed1.0003 m 5 s137,6743,039140,71310none—
run-20261102-114156-1ff0ba59knowledge_enabled=False, model=auto_codex2026-11-02 11:41:56ledgerlite-rates-001@1.0.0codex@codex-cli 0.166.02completedpassed1.0002 m 49 s97,4732,29499,7679none—
run-20261102-113507-5543ffe1knowledge_enabled=False, model=auto_codex2026-11-02 11:35:07ledgerlite-rates-001@1.0.0codex@codex-cli 0.166.01completedpassed1.0006 m 49 s273,4338,650282,08317none—
run-20261102-112953-68b1af75knowledge_enabled=False, model=qwen/Qwen3.8-Flash-Next2026-11-02 11:29:53ledgerlite-rates-001@1.0.0codex@codex-cli 0.166.03completedpassed1.0005 m 12 s266,6577,835274,49219none—
run-20261102-112306-6bc27784knowledge_enabled=False, model=qwen/Qwen3.8-Flash-Next2026-11-02 11:23:06ledgerlite-rates-001@1.0.0codex@codex-cli 0.166.02completedpassed1.0006 m 46 s359,67811,459371,13720none—
run-20261102-111839-c5f2e4c1knowledge_enabled=False, model=qwen/Qwen3.8-Flash-Next2026-11-02 11:18:39ledgerlite-rates-001@1.0.0codex@codex-cli 0.166.01completedpassed1.0004 m 26 s197,7436,744204,48715none—
run-20261102-111537-b9ab2fefknowledge_enabled=False, model=qwen/Qwen3.8-27B2026-11-02 11:15:37ledgerlite-rates-001@1.0.0codex@codex-cli 0.166.03completedpassed1.0003 m 1 s130,3242,843133,16712none—
run-20261102-111326-3c584bd3knowledge_enabled=False, model=qwen/Qwen3.8-27B2026-11-02 11:13:26ledgerlite-rates-001@1.0.0codex@codex-cli 0.166.02completedpassed1.0002 m 10 s81,2801,90383,1837none—
run-20261102-111029-a9c04726knowledge_enabled=False, model=qwen/Qwen3.8-27B2026-11-02 11:10:29ledgerlite-rates-001@1.0.0codex@codex-cli 0.166.01completedpassed1.0002 m 57 s118,8372,616121,45312none—
run-20261102-110711-12e9e01eknowledge_enabled=True, model=auto_codex2026-11-02 11:07:11cadence-takeover-001@1.0.0codex@codex-cli 0.166.03completedpassed1.0003 m 18 s124,5802,632127,21213none—
run-20261102-105924-5844ec5cknowledge_enabled=True, model=auto_codex2026-11-02 10:59:24cadence-takeover-001@1.0.0codex@codex-cli 0.166.02completedpassed1.0007 m 45 s486,0237,446493,46926none—
run-20261102-105332-509d420cknowledge_enabled=True, model=auto_codex2026-11-02 10:53:32cadence-takeover-001@1.0.0codex@codex-cli 0.166.01completedpassed1.0005 m 51 s181,89210,799192,69115none—
run-20261102-105101-7f0ea089knowledge_enabled=False, model=auto_codex2026-11-02 10:51:01cadence-takeover-001@1.0.0codex@codex-cli 0.166.03completedpassed1.0002 m 31 s81,7561,51383,2699none—
run-20261102-104527-df556abcknowledge_enabled=False, model=auto_codex2026-11-02 10:45:27cadence-takeover-001@1.0.0codex@codex-cli 0.166.02completedpassed1.0005 m 33 s231,2506,615237,86516none—
run-20261102-104150-ee470964knowledge_enabled=False, model=auto_codex2026-11-02 10:41:50cadence-takeover-001@1.0.0codex@codex-cli 0.166.01completedpassed1.0003 m 36 s184,2632,829187,09215none—
run-20261102-103806-ca54befbknowledge_enabled=False, model=qwen/Qwen3.8-Flash-Next2026-11-02 10:38:06cadence-takeover-001@1.0.0codex@codex-cli 0.166.03completedpassed1.0003 m 43 s176,8744,786181,66014none—
run-20261102-103500-42595b9bknowledge_enabled=False, model=qwen/Qwen3.8-Flash-Next2026-11-02 10:35:00cadence-takeover-001@1.0.0codex@codex-cli 0.166.02completedpassed1.0003 m 6 s136,1904,248140,43812none—
run-20261102-103139-c174189bknowledge_enabled=False, model=qwen/Qwen3.8-Flash-Next2026-11-02 10:31:39cadence-takeover-001@1.0.0codex@codex-cli 0.166.01completedpassed1.0003 m 20 s142,0814,157146,23813none—
run-20261102-102846-f9da52d1knowledge_enabled=False, model=qwen/Qwen3.8-27B2026-11-02 10:28:46cadence-takeover-001@1.0.0codex@codex-cli 0.166.03completedpassed1.0002 m 53 s166,1052,393168,49814none—
run-20261102-102450-4c4dafd8knowledge_enabled=False, model=qwen/Qwen3.8-27B2026-11-02 10:24:50cadence-takeover-001@1.0.0codex@codex-cli 0.166.02completedpassed1.0003 m 56 s184,0373,928187,96513none—
run-20261102-102224-77a554a3knowledge_enabled=False, model=qwen/Qwen3.8-27B2026-11-02 10:22:24cadence-takeover-001@1.0.0codex@codex-cli 0.166.01completedpassed1.0002 m 25 s87,4412,06289,5039none—
run-20261102-090053-801966e8knowledge_enabled=True, model=auto_codex2026-11-02 09:00:53slugify-001@1.0.0codex@codex-cli 0.166.03completedpassed1.0002 m 15 s78,7282,14180,8698none—
run-20261102-085717-2d40efc9knowledge_enabled=True, model=auto_codex2026-11-02 08:57:17slugify-001@1.0.0codex@codex-cli 0.166.02completedpassed1.0003 m 35 s112,6422,849115,49111none—
run-20261102-085126-7081e5a7knowledge_enabled=True, model=auto_codex2026-11-02 08:51:26slugify-001@1.0.0codex@codex-cli 0.166.01completedpassed1.0005 m 50 s82,1122,40484,5168none—
run-20261102-084925-db233c9dknowledge_enabled=False, model=auto_codex2026-11-02 08:49:25slugify-001@1.0.0codex@codex-cli 0.166.03completedpassed1.0001 m 60 s67,0291,57168,6007none—
run-20261102-084722-12cb8519knowledge_enabled=False, model=auto_codex2026-11-02 08:47:22slugify-001@1.0.0codex@codex-cli 0.166.02completedpassed1.0002 m 3 s68,4371,56470,0017none—
run-20261102-084427-5c4e6c25knowledge_enabled=False, model=auto_codex2026-11-02 08:44:27slugify-001@1.0.0codex@codex-cli 0.166.01completedpassed1.0002 m 54 s92,9172,28995,2069none—
run-20261102-083513-c8a810d4knowledge_enabled=False, model=qwen/Qwen3.8-Flash-Next2026-11-02 08:35:13slugify-001@1.0.0codex@codex-cli 0.166.03completedpassed1.0009 m 13 s139,4507,093146,54315none—
run-20261102-083306-81799937knowledge_enabled=False, model=qwen/Qwen3.8-Flash-Next2026-11-02 08:33:06slugify-001@1.0.0codex@codex-cli 0.166.02completedpassed1.0002 m 6 s77,3502,52779,8778none—
run-20261102-082149-abdd844bknowledge_enabled=False, model=qwen/Qwen3.8-Flash-Next2026-11-02 08:21:49slugify-001@1.0.0codex@codex-cli 0.166.01completedpassed1.00011 m 17 s147,9947,191155,18512none—
run-20261102-081913-0789e06aknowledge_enabled=False, model=qwen/Qwen3.8-27B2026-11-02 08:19:13slugify-001@1.0.0codex@codex-cli 0.166.03completedpassed1.0002 m 35 s113,2332,116115,34911none—
run-20261102-080410-d2c89897knowledge_enabled=False, model=qwen/Qwen3.8-27B2026-11-02 08:04:10slugify-001@1.0.0codex@codex-cli 0.166.02timeoutnot measurednot measured15 m 2 s989,57118,7871,008,35851agentI'm looking at the test results more carefully now—most of them are passing, but there are two specific cases where the hyphen handling is producing unexpected triple hyphens instead of the expected output. The issue seems to be that when I'm building the test strings with the hyphen character, something about how the input is being processed is causing the hyphens to multiply in the output.
run-20261102-080204-89ac58c6knowledge_enabled=False, model=qwen/Qwen3.8-27B2026-11-02 08:02:04slugify-001@1.0.0codex@codex-cli 0.166.01completedpassed1.0002 m 5 s88,7601,40690,1669none—
run-20261102-075736-7dc8b5faknowledge_enabled=True, model=auto_codex2026-11-02 07:57:36notes-sync-001@1.0.0codex@codex-cli 0.166.03completedpassed1.0004 m 27 s126,1184,729130,84710none—
run-20261102-075327-d3b09ae5knowledge_enabled=True, model=auto_codex2026-11-02 07:53:27notes-sync-001@1.0.0codex@codex-cli 0.166.02completedpassed1.0004 m 8 s92,3354,29096,62511none—
run-20261102-074537-1abe2bd8knowledge_enabled=True, model=auto_codex2026-11-02 07:45:37notes-sync-001@1.0.0codex@codex-cli 0.166.01completedpassed1.0007 m 49 s168,2586,167174,42512none—
run-20261102-074114-fb309dd3knowledge_enabled=False, model=auto_codex2026-11-02 07:41:14notes-sync-001@1.0.0codex@codex-cli 0.166.03completedpassed1.0004 m 22 s139,4534,875144,32811none—
run-20261102-073119-046c63c5knowledge_enabled=False, model=auto_codex2026-11-02 07:31:19notes-sync-001@1.0.0codex@codex-cli 0.166.02completedpassed1.0009 m 54 s186,1957,893194,08814none—
run-20261102-072154-ce0a96c9knowledge_enabled=False, model=auto_codex2026-11-02 07:21:54notes-sync-001@1.0.0codex@codex-cli 0.166.01completedpassed1.0009 m 24 s292,5866,876299,46221none—
run-20261102-071535-a34798d9knowledge_enabled=False, model=qwen/Qwen3.8-Flash-Next2026-11-02 07:15:35notes-sync-001@1.0.0codex@codex-cli 0.166.03completedpassed1.0006 m 19 s194,7469,719204,46513none—
run-20261102-070752-ee5e374fknowledge_enabled=False, model=qwen/Qwen3.8-Flash-Next2026-11-02 07:07:52notes-sync-001@1.0.0codex@codex-cli 0.166.02completedpassed1.0007 m 42 s297,81511,995309,81018none—
run-20261102-070225-983f28a4knowledge_enabled=False, model=qwen/Qwen3.8-Flash-Next2026-11-02 07:02:25notes-sync-001@1.0.0codex@codex-cli 0.166.01completedpassed1.0005 m 26 s113,9877,555121,54210none—
run-20261102-065823-56d0518eknowledge_enabled=False, model=qwen/Qwen3.8-27B2026-11-02 06:58:23notes-sync-001@1.0.0codex@codex-cli 0.166.03completedpassed1.0004 m 1 s144,2093,841148,05012none—
run-20261102-065424-0122485bknowledge_enabled=False, model=qwen/Qwen3.8-27B2026-11-02 06:54:24notes-sync-001@1.0.0codex@codex-cli 0.166.02completedpassed1.0003 m 58 s147,5283,954151,48213none—
run-20261102-065152-be03d69aknowledge_enabled=False, model=qwen/Qwen3.8-27B2026-11-02 06:51:52notes-sync-001@1.0.0codex@codex-cli 0.166.01completedpassed1.0002 m 32 s68,6912,28470,9757none—
run-20261102-064601-0d71057aknowledge_enabled=True, model=auto_codex2026-11-02 06:46:01notes-search-001@1.0.0codex@codex-cli 0.166.03completedpassed1.0005 m 50 s190,8287,524198,35215none—
run-20261102-064343-33d90543knowledge_enabled=True, model=auto_codex2026-11-02 06:43:43notes-search-001@1.0.0codex@codex-cli 0.166.02completedpassed1.0002 m 18 s56,6252,03058,6558none—
run-20261102-063921-31a5efefknowledge_enabled=True, model=auto_codex2026-11-02 06:39:21notes-search-001@1.0.0codex@codex-cli 0.166.01completedpassed1.0004 m 21 s151,0275,654156,68113none—
run-20261102-063306-62006f1cknowledge_enabled=False, model=auto_codex2026-11-02 06:33:06notes-search-001@1.0.0codex@codex-cli 0.166.03completedpassed1.0006 m 14 s127,0934,757131,85012none—
run-20261102-061803-ca793f25knowledge_enabled=False, model=auto_codex2026-11-02 06:18:03notes-search-001@1.0.0codex@codex-cli 0.166.02timeoutnot measurednot measured15 m 3 s364,79413,619378,41324agentThe implementation is correct — the last "failure" was another typo in my hand-written expected list (I swapped `t2`/`t1`), and the final direct probe confirmed the spec order `['t0','d','tg','t2','t1','c','b','a','e','m2','m1']` and correct scoring. Cleaning up the stale `.pyc` churn so the diff is just the implementation:
run-20261102-060259-4681bb55knowledge_enabled=False, model=auto_codex2026-11-02 06:02:59notes-search-001@1.0.0codex@codex-cli 0.166.01timeoutnot measurednot measured15 m 3 s92,6555,28797,94211agentFound a real bug: with `for ... else`, my scoring block sits inside `if terms:`, so a blank query appended nothing and returned `[]`. Restructuring so an empty term list scores 0 and matches.
run-20261102-055730-c94232f9knowledge_enabled=False, model=qwen/Qwen3.8-Flash-Next2026-11-02 05:57:30notes-search-001@1.0.0codex@codex-cli 0.166.03completedpassed1.0005 m 28 s193,96210,301204,26317none—
run-20261102-054227-dc5f0497knowledge_enabled=False, model=qwen/Qwen3.8-Flash-Next2026-11-02 05:42:27notes-search-001@1.0.0codex@codex-cli 0.166.02timeoutnot measurednot measured15 m 2 s68,1594,70372,8629agentVerifying against the spec rules with a throwaway script, plus the repo suite.
run-20261102-052723-7c46d753knowledge_enabled=False, model=qwen/Qwen3.8-Flash-Next2026-11-02 05:27:23notes-search-001@1.0.0codex@codex-cli 0.166.01timeoutnot measurednot measured15 m 3 s25,66863226,3006agentI'll start by exploring the repo structure and reading the spec.
run-20261102-051856-7a01f2f0knowledge_enabled=False, model=qwen/Qwen3.8-27B2026-11-02 05:18:56notes-search-001@1.0.0codex@codex-cli 0.166.03completedpassed1.0008 m 27 s334,13711,345345,48220none—
run-20261102-051140-154e7756knowledge_enabled=False, model=qwen/Qwen3.8-27B2026-11-02 05:11:40notes-search-001@1.0.0codex@codex-cli 0.166.02completedpassed1.0007 m 15 s322,2559,563331,81821none—
run-20261102-050517-4824113cknowledge_enabled=False, model=qwen/Qwen3.8-27B2026-11-02 05:05:17notes-search-001@1.0.0codex@codex-cli 0.166.01completedpassed1.0006 m 23 s257,1027,946265,04819none—
run-20261102-045951-9062760dknowledge_enabled=True, model=auto_codex2026-11-02 04:59:51wordcount-001@1.0.0codex@codex-cli 0.166.03completedpassed1.0005 m 25 s111,7232,176113,89912none—
run-20261102-045137-ae782a86knowledge_enabled=True, model=auto_codex2026-11-02 04:51:37wordcount-001@1.0.0codex@codex-cli 0.166.02completedpassed1.0008 m 13 s57,8801,59859,4786none—
run-20261102-044616-5ced7f24knowledge_enabled=True, model=auto_codex2026-11-02 04:46:16wordcount-001@1.0.0codex@codex-cli 0.166.01completedpassed1.0005 m 20 s72,7571,52874,2858none—
run-20261102-043507-07326b31knowledge_enabled=False, model=auto_codex2026-11-02 04:35:07wordcount-001@1.0.0codex@codex-cli 0.166.03completedpassed1.00011 m 9 s91,8942,13994,03310none—
run-20261102-042815-65e2ad9bknowledge_enabled=False, model=auto_codex2026-11-02 04:28:15wordcount-001@1.0.0codex@codex-cli 0.166.02completedpassed1.0006 m 51 s44,29172945,0205none—
run-20261102-042003-4e77ac85knowledge_enabled=False, model=auto_codex2026-11-02 04:20:03wordcount-001@1.0.0codex@codex-cli 0.166.01completedpassed1.0008 m 12 s65,1431,86867,0117none—
run-20261102-040500-60833b88knowledge_enabled=False, model=qwen/Qwen3.8-Flash-Next2026-11-02 04:05:00wordcount-001@1.0.0codex@codex-cli 0.166.03timeoutnot measurednot measured15 m 2 s29,76080330,5634agentFound it — the working tree modified `text.split()` into `text.split(" ")`. Let me confirm which inputs misbehave.
run-20261102-034956-2f8213a2knowledge_enabled=False, model=qwen/Qwen3.8-Flash-Next2026-11-02 03:49:56wordcount-001@1.0.0codex@codex-cli 0.166.02timeoutnot measurednot measured15 m 2 s83,8282,87486,70212agentThe fix is on disk, but git doesn't report `text.py` as modified — verifying against HEAD.
run-20261102-034347-4d78071aknowledge_enabled=False, model=qwen/Qwen3.8-Flash-Next2026-11-02 03:43:47wordcount-001@1.0.0codex@codex-cli 0.166.01completedpassed1.0006 m 8 s59,5932,20261,7959none—
run-20261102-034231-ceec4cf9knowledge_enabled=False, model=qwen/Qwen3.8-27B2026-11-02 03:42:31wordcount-001@1.0.0codex@codex-cli 0.166.03completedpassed1.0001 m 16 s44,33870345,0415none—
run-20261102-034056-a469ad46knowledge_enabled=False, model=qwen/Qwen3.8-27B2026-11-02 03:40:56wordcount-001@1.0.0codex@codex-cli 0.166.02completedpassed1.0001 m 35 s53,8831,04554,9286none—
run-20261102-033745-147a6170knowledge_enabled=False, model=qwen/Qwen3.8-27B2026-11-02 03:37:45wordcount-001@1.0.0codex@codex-cli 0.166.01completedpassed1.0003 m 10 s165,8752,586168,46118none—
run-20261102-032654-eef72cc9knowledge_enabled=True, model=auto_codex2026-11-02 03:26:54bookshop-tiers-001@1.0.0codex@codex-cli 0.166.03completedpassed1.00010 m 50 s89,2001,61190,8118none—
run-20261102-032017-d7e7635dknowledge_enabled=True, model=auto_codex2026-11-02 03:20:17bookshop-tiers-001@1.0.0codex@codex-cli 0.166.02completedpassed1.0006 m 36 s84,4421,52985,9718none—
run-20261102-031245-d48061aaknowledge_enabled=True, model=auto_codex2026-11-02 03:12:45bookshop-tiers-001@1.0.0codex@codex-cli 0.166.01completedpassed1.0007 m 31 s65,0701,52766,5976none—
run-20261102-031005-8ee792e8knowledge_enabled=False, model=auto_codex2026-11-02 03:10:05bookshop-tiers-001@1.0.0codex@codex-cli 0.166.03completedpassed1.0002 m 39 s52,1581,25653,4145none—
run-20261102-030620-307d982cknowledge_enabled=False, model=auto_codex2026-11-02 03:06:20bookshop-tiers-001@1.0.0codex@codex-cli 0.166.02completedpassed1.0003 m 43 s62,5881,46264,0506none—
run-20261102-030330-6e680c03knowledge_enabled=False, model=auto_codex2026-11-02 03:03:30bookshop-tiers-001@1.0.0codex@codex-cli 0.166.01completedpassed1.0002 m 49 s81,2491,66482,9137none—
run-20261102-025838-8e5d4349knowledge_enabled=False, model=qwen/Qwen3.8-Flash-Next2026-11-02 02:58:38bookshop-tiers-001@1.0.0codex@codex-cli 0.166.03completedpassed1.0004 m 52 s185,1266,992192,11817none—
run-20261102-025349-a41ee544knowledge_enabled=False, model=qwen/Qwen3.8-Flash-Next2026-11-02 02:53:49bookshop-tiers-001@1.0.0codex@codex-cli 0.166.02completedpassed1.0004 m 48 s190,9166,504197,42016none—
run-20261102-024900-b4e495b9knowledge_enabled=False, model=qwen/Qwen3.8-Flash-Next2026-11-02 02:49:00bookshop-tiers-001@1.0.0codex@codex-cli 0.166.01completedpassed1.0004 m 48 s204,4546,473210,92718none—
run-20261102-024637-153cbef0knowledge_enabled=False, model=qwen/Qwen3.8-27B2026-11-02 02:46:37bookshop-tiers-001@1.0.0codex@codex-cli 0.166.03completedpassed1.0002 m 22 s84,7901,31086,1008none—
run-20261102-024414-b4a4c0f1knowledge_enabled=False, model=qwen/Qwen3.8-27B2026-11-02 02:44:14bookshop-tiers-001@1.0.0codex@codex-cli 0.166.02completedpassed1.0002 m 22 s73,2531,40774,6607none—
run-20261102-024213-cd12e80fknowledge_enabled=False, model=qwen/Qwen3.8-27B2026-11-02 02:42:13bookshop-tiers-001@1.0.0codex@codex-cli 0.166.01completedpassed1.0001 m 60 s51,44782652,2735none—
run-20261102-023813-b7d6ced3knowledge_enabled=True, model=auto_codex2026-11-02 02:38:13bookshop-stock-002@1.0.0codex@codex-cli 0.166.03completedpassed1.0003 m 58 s180,1993,237183,43613none—
run-20261102-023515-f1dff616knowledge_enabled=True, model=auto_codex2026-11-02 02:35:15bookshop-stock-002@1.0.0codex@codex-cli 0.166.02completedpassed1.0002 m 57 s107,5132,363109,87611none—
run-20261102-023143-af17689aknowledge_enabled=True, model=auto_codex2026-11-02 02:31:43bookshop-stock-002@1.0.0codex@codex-cli 0.166.01completedpassed1.0003 m 31 s124,6783,136127,81410none—
run-20261102-022715-0f5b5375knowledge_enabled=False, model=auto_codex2026-11-02 02:27:15bookshop-stock-002@1.0.0codex@codex-cli 0.166.03completedpassed1.0004 m 27 s173,6503,854177,50415none—
run-20261102-022315-259a16a5knowledge_enabled=False, model=auto_codex2026-11-02 02:23:15bookshop-stock-002@1.0.0codex@codex-cli 0.166.02completedpassed1.0003 m 59 s128,2513,787132,03811none—
run-20261102-021828-a3b13607knowledge_enabled=False, model=auto_codex2026-11-02 02:18:28bookshop-stock-002@1.0.0codex@codex-cli 0.166.01completedpassed1.0004 m 46 s241,2974,789246,08617none—
run-20261102-021319-f8645cebknowledge_enabled=False, model=qwen/Qwen3.8-Flash-Next2026-11-02 02:13:19bookshop-stock-002@1.0.0codex@codex-cli 0.166.03completedpassed1.0005 m 8 s223,6687,523231,19117none—
run-20261102-020922-c802a0eeknowledge_enabled=False, model=qwen/Qwen3.8-Flash-Next2026-11-02 02:09:22bookshop-stock-002@1.0.0codex@codex-cli 0.166.02completedpassed1.0003 m 56 s164,3094,902169,21114none—
run-20261102-020305-819a6a56knowledge_enabled=False, model=qwen/Qwen3.8-Flash-Next2026-11-02 02:03:05bookshop-stock-002@1.0.0codex@codex-cli 0.166.01completedpassed1.0006 m 16 s254,59910,261264,86020none—
run-20261102-020002-c8680ac1knowledge_enabled=False, model=qwen/Qwen3.8-27B2026-11-02 02:00:02bookshop-stock-002@1.0.0codex@codex-cli 0.166.03completedpassed1.0003 m 1 s118,2772,192120,4699none—
run-20261102-015702-033aab98knowledge_enabled=False, model=qwen/Qwen3.8-27B2026-11-02 01:57:02bookshop-stock-002@1.0.0codex@codex-cli 0.166.02completedpassed1.0002 m 59 s110,1852,205112,39010none—
run-20261102-015302-e1907b59knowledge_enabled=False, model=qwen/Qwen3.8-27B2026-11-02 01:53:02bookshop-stock-002@1.0.0codex@codex-cli 0.166.01completedpassed1.0003 m 59 s139,5133,865143,37813none—