[{"id":"coding-agents-cells","title":"Every task and agent: sessions that passed (of 2)","viz":"HeatMatrix","columns":{"$k":["key","label","unit"],"$r":[["task","Task","text"],["a0","Sonnet 5.5 in Claude Code","text"],["a1","Opus 5.5 in Claude Code","text"],["a2","GPT-6.1 Sol in Codex CLI","text"],["checks","Hidden checks","text"]]},"rows":{"$k":["task","a0","a1","a2","checks"],"$r":[["Pagination fix","2/2","2/2","2/2","13 hidden tests"],["CLI --top flag","2/2","2/2","2/2","11 hidden tests that run the CLI"],["Invoice refactor","2/2","2/2","2/2","20 golden behaviour tests and 4 structure tests"],["LRU cache","2/2","2/2","2/2","16 hidden tests"],["Queue race","2/2","2/2","2/2","10 hidden tests"],["Strict TypeScript types","2/2","2/2","2/2","static checks, tsc with a hidden usage file (11 @ts-expect-error probes) and 4 runtime tests"]]}},{"id":"coding-agents-tasks","title":"The six tasks and their controls","columns":{"$k":["key","label","unit"],"$r":[["task","Task","text"],["what","What the agent had to do","text"],["checks","Hidden checks","text"],["base","Base repository","text"],["reference","Reference patch","text"]]},"rows":{"$k":["task","what","checks","base","reference"],"$r":[["Pagination fix","Fix a pagination bug that spans two files (offset, page count, next and previous flags, validation) to the README rules","13 hidden tests","fails (tests 1/13)","passes (tests 13/13)"],["CLI --top flag","Add a --top <n> flag with strict validation and exact error text to a small CLI","11 hidden tests that run the CLI","fails (tests 2/11)","passes (tests 11/11)"],["Invoice refactor","Remove duplication without a change in behaviour, floating-point and validation-order quirks included","20 golden behaviour tests and 4 structure tests","fails (tests 21/24)","passes (tests 24/24)"],["LRU cache","Implement an LRU cache to a written spec (recency, eviction callback, TTL with an injected clock, SameValueZero keys, O(1) get and set)","16 hidden tests","fails (tests 0/16)","passes (tests 16/16)"],["Queue race","Fix a concurrency race and an onIdle hang in an async task queue","10 hidden tests","fails (tests 4/10)","passes (tests 10/10)"],["Strict TypeScript types","Make tsc pass on strict settings with no any and no suppressions; the usage file and the config stay unchanged","static checks, tsc with a hidden usage file (11 @ts-expect-error probes) and 4 runtime tests","fails (tests 4/4; static checks fail)","passes (tests 4/4)"]]}}]