mirror of https://github.com/garrytan/gstack.git
test(parity): rebaseline v1.57.7.0 → v1.64.1.0 + skeleton-cap headroom
The two parallel v1.64 waves (code-smell fix wave + main's #2571) each added shared-preamble prose, pushing document-release / design-consultation / cso past their size ratios on the v1.57.7.0 anchor and four carved skeletons (plan-ceo-review, plan-eng-review, office-hours, design-consultation) 22-280 B over their absolute caps. New baseline is union-normalized (skeleton + sections/*.md, matching what the harness measures); caps get +~1 KB headroom each with per-cap rationale. The v1.57.7.0 fixture stays in test/fixtures/ for the audit trail, and capture-parity-baseline.ts now documents the union-normalization step so the next rebaseline doesn't re-trip on it. Co-Authored-By: Claude Fable 5 <noreply@anthropic.com>
This commit is contained in:
parent
45bc02952d
commit
8f048370a4
|
|
@ -0,0 +1,643 @@
|
|||
{
|
||||
"tag": "v1.64.1.0",
|
||||
"capturedAt": "2026-08-15T15:17:46.061Z",
|
||||
"capturedFromCommit": "9c76f89a",
|
||||
"capturedFromBranch": "garrytan/gbrain-code-smell-audit",
|
||||
"totalSkills": 53,
|
||||
"totalCorpusBytes": 3223808,
|
||||
"estTotalCatalogTokens": 4177,
|
||||
"topHeaviest": [
|
||||
{
|
||||
"skill": "review",
|
||||
"skillMdBytes": 108523,
|
||||
"skillMdLines": 1871,
|
||||
"estTokens": 27131,
|
||||
"tmplBytes": 14123,
|
||||
"descriptionLen": 205,
|
||||
"hasGateEval": true,
|
||||
"hasPeriodicEval": false
|
||||
},
|
||||
{
|
||||
"skill": "design-review",
|
||||
"skillMdBytes": 105842,
|
||||
"skillMdLines": 2003,
|
||||
"estTokens": 26461,
|
||||
"tmplBytes": 11674,
|
||||
"descriptionLen": 306,
|
||||
"hasGateEval": true,
|
||||
"hasPeriodicEval": false
|
||||
},
|
||||
{
|
||||
"skill": "land-and-deploy",
|
||||
"skillMdBytes": 104578,
|
||||
"skillMdLines": 1957,
|
||||
"estTokens": 26145,
|
||||
"tmplBytes": 50736,
|
||||
"descriptionLen": 160,
|
||||
"hasGateEval": true,
|
||||
"hasPeriodicEval": false
|
||||
},
|
||||
{
|
||||
"skill": "autoplan",
|
||||
"skillMdBytes": 101979,
|
||||
"skillMdLines": 1867,
|
||||
"estTokens": 25495,
|
||||
"tmplBytes": 45857,
|
||||
"descriptionLen": 366,
|
||||
"hasGateEval": true,
|
||||
"hasPeriodicEval": true
|
||||
},
|
||||
{
|
||||
"skill": "codex",
|
||||
"skillMdBytes": 98229,
|
||||
"skillMdLines": 1717,
|
||||
"estTokens": 24557,
|
||||
"tmplBytes": 41467,
|
||||
"descriptionLen": 187,
|
||||
"hasGateEval": true,
|
||||
"hasPeriodicEval": false
|
||||
},
|
||||
{
|
||||
"skill": "office-hours",
|
||||
"skillMdBytes": 98193,
|
||||
"skillMdLines": 1706,
|
||||
"estTokens": 24548,
|
||||
"tmplBytes": 30541,
|
||||
"descriptionLen": 860,
|
||||
"hasGateEval": true,
|
||||
"hasPeriodicEval": false
|
||||
},
|
||||
{
|
||||
"skill": "retro",
|
||||
"skillMdBytes": 93029,
|
||||
"skillMdLines": 1821,
|
||||
"estTokens": 23257,
|
||||
"tmplBytes": 42381,
|
||||
"descriptionLen": 648,
|
||||
"hasGateEval": true,
|
||||
"hasPeriodicEval": false
|
||||
},
|
||||
{
|
||||
"skill": "setup-gbrain",
|
||||
"skillMdBytes": 92312,
|
||||
"skillMdLines": 1860,
|
||||
"estTokens": 23078,
|
||||
"tmplBytes": 45975,
|
||||
"descriptionLen": 325,
|
||||
"hasGateEval": true,
|
||||
"hasPeriodicEval": false
|
||||
},
|
||||
{
|
||||
"skill": "plan-ceo-review",
|
||||
"skillMdBytes": 90280,
|
||||
"skillMdLines": 1485,
|
||||
"estTokens": 22570,
|
||||
"tmplBytes": 29268,
|
||||
"descriptionLen": 794,
|
||||
"hasGateEval": true,
|
||||
"hasPeriodicEval": true
|
||||
},
|
||||
{
|
||||
"skill": "plan-design-review",
|
||||
"skillMdBytes": 89383,
|
||||
"skillMdLines": 1531,
|
||||
"estTokens": 22346,
|
||||
"tmplBytes": 18463,
|
||||
"descriptionLen": 218,
|
||||
"hasGateEval": true,
|
||||
"hasPeriodicEval": true
|
||||
}
|
||||
],
|
||||
"skills": {
|
||||
"autoplan": {
|
||||
"skill": "autoplan",
|
||||
"skillMdBytes": 101979,
|
||||
"skillMdLines": 1867,
|
||||
"estTokens": 25495,
|
||||
"tmplBytes": 45857,
|
||||
"descriptionLen": 366,
|
||||
"hasGateEval": true,
|
||||
"hasPeriodicEval": true
|
||||
},
|
||||
"benchmark": {
|
||||
"skill": "benchmark",
|
||||
"skillMdBytes": 37206,
|
||||
"skillMdLines": 794,
|
||||
"estTokens": 9302,
|
||||
"tmplBytes": 9378,
|
||||
"descriptionLen": 213,
|
||||
"hasGateEval": true,
|
||||
"hasPeriodicEval": false
|
||||
},
|
||||
"benchmark-models": {
|
||||
"skill": "benchmark-models",
|
||||
"skillMdBytes": 33273,
|
||||
"skillMdLines": 669,
|
||||
"estTokens": 8318,
|
||||
"tmplBytes": 6631,
|
||||
"descriptionLen": 217,
|
||||
"hasGateEval": false,
|
||||
"hasPeriodicEval": false
|
||||
},
|
||||
"browse": {
|
||||
"skill": "browse",
|
||||
"skillMdBytes": 55782,
|
||||
"skillMdLines": 1031,
|
||||
"estTokens": 13946,
|
||||
"tmplBytes": 13944,
|
||||
"descriptionLen": 181,
|
||||
"hasGateEval": true,
|
||||
"hasPeriodicEval": false
|
||||
},
|
||||
"canary": {
|
||||
"skill": "canary",
|
||||
"skillMdBytes": 57291,
|
||||
"skillMdLines": 1061,
|
||||
"estTokens": 14323,
|
||||
"tmplBytes": 8033,
|
||||
"descriptionLen": 180,
|
||||
"hasGateEval": true,
|
||||
"hasPeriodicEval": false
|
||||
},
|
||||
"careful": {
|
||||
"skill": "careful",
|
||||
"skillMdBytes": 2715,
|
||||
"skillMdLines": 70,
|
||||
"estTokens": 679,
|
||||
"tmplBytes": 2599,
|
||||
"descriptionLen": 331,
|
||||
"hasGateEval": false,
|
||||
"hasPeriodicEval": false
|
||||
},
|
||||
"codex": {
|
||||
"skill": "codex",
|
||||
"skillMdBytes": 98229,
|
||||
"skillMdLines": 1717,
|
||||
"estTokens": 24557,
|
||||
"tmplBytes": 41467,
|
||||
"descriptionLen": 187,
|
||||
"hasGateEval": true,
|
||||
"hasPeriodicEval": false
|
||||
},
|
||||
"context-restore": {
|
||||
"skill": "context-restore",
|
||||
"skillMdBytes": 53516,
|
||||
"skillMdLines": 952,
|
||||
"estTokens": 13379,
|
||||
"tmplBytes": 7092,
|
||||
"descriptionLen": 238,
|
||||
"hasGateEval": true,
|
||||
"hasPeriodicEval": false
|
||||
},
|
||||
"context-save": {
|
||||
"skill": "context-save",
|
||||
"skillMdBytes": 55876,
|
||||
"skillMdLines": 1037,
|
||||
"estTokens": 13969,
|
||||
"tmplBytes": 9293,
|
||||
"descriptionLen": 168,
|
||||
"hasGateEval": true,
|
||||
"hasPeriodicEval": false
|
||||
},
|
||||
"cso": {
|
||||
"skill": "cso",
|
||||
"skillMdBytes": 89500,
|
||||
"skillMdLines": 1294,
|
||||
"estTokens": 18728,
|
||||
"tmplBytes": 21724,
|
||||
"descriptionLen": 196,
|
||||
"hasGateEval": true,
|
||||
"hasPeriodicEval": false
|
||||
},
|
||||
"design-consultation": {
|
||||
"skill": "design-consultation",
|
||||
"skillMdBytes": 90375,
|
||||
"skillMdLines": 1239,
|
||||
"estTokens": 17256,
|
||||
"tmplBytes": 9554,
|
||||
"descriptionLen": 890,
|
||||
"hasGateEval": true,
|
||||
"hasPeriodicEval": false
|
||||
},
|
||||
"design-html": {
|
||||
"skill": "design-html",
|
||||
"skillMdBytes": 76735,
|
||||
"skillMdLines": 1520,
|
||||
"estTokens": 19184,
|
||||
"tmplBytes": 22567,
|
||||
"descriptionLen": 235,
|
||||
"hasGateEval": true,
|
||||
"hasPeriodicEval": false
|
||||
},
|
||||
"design-review": {
|
||||
"skill": "design-review",
|
||||
"skillMdBytes": 105842,
|
||||
"skillMdLines": 2003,
|
||||
"estTokens": 26461,
|
||||
"tmplBytes": 11674,
|
||||
"descriptionLen": 306,
|
||||
"hasGateEval": true,
|
||||
"hasPeriodicEval": false
|
||||
},
|
||||
"design-shotgun": {
|
||||
"skill": "design-shotgun",
|
||||
"skillMdBytes": 73024,
|
||||
"skillMdLines": 1382,
|
||||
"estTokens": 18256,
|
||||
"tmplBytes": 13331,
|
||||
"descriptionLen": 788,
|
||||
"hasGateEval": true,
|
||||
"hasPeriodicEval": false
|
||||
},
|
||||
"devex-review": {
|
||||
"skill": "devex-review",
|
||||
"skillMdBytes": 75374,
|
||||
"skillMdLines": 1314,
|
||||
"estTokens": 18844,
|
||||
"tmplBytes": 7984,
|
||||
"descriptionLen": 201,
|
||||
"hasGateEval": false,
|
||||
"hasPeriodicEval": false
|
||||
},
|
||||
"diagram": {
|
||||
"skill": "diagram",
|
||||
"skillMdBytes": 33341,
|
||||
"skillMdLines": 669,
|
||||
"estTokens": 8335,
|
||||
"tmplBytes": 6732,
|
||||
"descriptionLen": 359,
|
||||
"hasGateEval": true,
|
||||
"hasPeriodicEval": false
|
||||
},
|
||||
"document-generate": {
|
||||
"skill": "document-generate",
|
||||
"skillMdBytes": 64020,
|
||||
"skillMdLines": 1261,
|
||||
"estTokens": 16005,
|
||||
"tmplBytes": 15940,
|
||||
"descriptionLen": 334,
|
||||
"hasGateEval": false,
|
||||
"hasPeriodicEval": false
|
||||
},
|
||||
"document-release": {
|
||||
"skill": "document-release",
|
||||
"skillMdBytes": 76636,
|
||||
"skillMdLines": 970,
|
||||
"estTokens": 13898,
|
||||
"tmplBytes": 6688,
|
||||
"descriptionLen": 192,
|
||||
"hasGateEval": true,
|
||||
"hasPeriodicEval": false
|
||||
},
|
||||
"freeze": {
|
||||
"skill": "freeze",
|
||||
"skillMdBytes": 3313,
|
||||
"skillMdLines": 94,
|
||||
"estTokens": 828,
|
||||
"tmplBytes": 3197,
|
||||
"descriptionLen": 533,
|
||||
"hasGateEval": false,
|
||||
"hasPeriodicEval": false
|
||||
},
|
||||
"gstack-upgrade": {
|
||||
"skill": "gstack-upgrade",
|
||||
"skillMdBytes": 10817,
|
||||
"skillMdLines": 285,
|
||||
"estTokens": 2704,
|
||||
"tmplBytes": 10667,
|
||||
"descriptionLen": 163,
|
||||
"hasGateEval": true,
|
||||
"hasPeriodicEval": false
|
||||
},
|
||||
"guard": {
|
||||
"skill": "guard",
|
||||
"skillMdBytes": 3314,
|
||||
"skillMdLines": 91,
|
||||
"estTokens": 829,
|
||||
"tmplBytes": 3196,
|
||||
"descriptionLen": 703,
|
||||
"hasGateEval": false,
|
||||
"hasPeriodicEval": false
|
||||
},
|
||||
"health": {
|
||||
"skill": "health",
|
||||
"skillMdBytes": 58102,
|
||||
"skillMdLines": 1085,
|
||||
"estTokens": 14526,
|
||||
"tmplBytes": 11617,
|
||||
"descriptionLen": 184,
|
||||
"hasGateEval": true,
|
||||
"hasPeriodicEval": false
|
||||
},
|
||||
"investigate": {
|
||||
"skill": "investigate",
|
||||
"skillMdBytes": 60600,
|
||||
"skillMdLines": 1085,
|
||||
"estTokens": 15150,
|
||||
"tmplBytes": 11566,
|
||||
"descriptionLen": 1241,
|
||||
"hasGateEval": true,
|
||||
"hasPeriodicEval": false
|
||||
},
|
||||
"ios-clean": {
|
||||
"skill": "ios-clean",
|
||||
"skillMdBytes": 51125,
|
||||
"skillMdLines": 883,
|
||||
"estTokens": 12781,
|
||||
"tmplBytes": 3743,
|
||||
"descriptionLen": 254,
|
||||
"hasGateEval": false,
|
||||
"hasPeriodicEval": false
|
||||
},
|
||||
"ios-design-review": {
|
||||
"skill": "ios-design-review",
|
||||
"skillMdBytes": 51817,
|
||||
"skillMdLines": 886,
|
||||
"estTokens": 12954,
|
||||
"tmplBytes": 4417,
|
||||
"descriptionLen": 209,
|
||||
"hasGateEval": false,
|
||||
"hasPeriodicEval": false
|
||||
},
|
||||
"ios-fix": {
|
||||
"skill": "ios-fix",
|
||||
"skillMdBytes": 50946,
|
||||
"skillMdLines": 882,
|
||||
"estTokens": 12737,
|
||||
"tmplBytes": 3574,
|
||||
"descriptionLen": 187,
|
||||
"hasGateEval": false,
|
||||
"hasPeriodicEval": false
|
||||
},
|
||||
"ios-qa": {
|
||||
"skill": "ios-qa",
|
||||
"skillMdBytes": 58828,
|
||||
"skillMdLines": 1026,
|
||||
"estTokens": 14707,
|
||||
"tmplBytes": 11461,
|
||||
"descriptionLen": 223,
|
||||
"hasGateEval": true,
|
||||
"hasPeriodicEval": false
|
||||
},
|
||||
"ios-sync": {
|
||||
"skill": "ios-sync",
|
||||
"skillMdBytes": 51599,
|
||||
"skillMdLines": 880,
|
||||
"estTokens": 12900,
|
||||
"tmplBytes": 4220,
|
||||
"descriptionLen": 269,
|
||||
"hasGateEval": true,
|
||||
"hasPeriodicEval": false
|
||||
},
|
||||
"land-and-deploy": {
|
||||
"skill": "land-and-deploy",
|
||||
"skillMdBytes": 104578,
|
||||
"skillMdLines": 1957,
|
||||
"estTokens": 26145,
|
||||
"tmplBytes": 50736,
|
||||
"descriptionLen": 160,
|
||||
"hasGateEval": true,
|
||||
"hasPeriodicEval": false
|
||||
},
|
||||
"landing-report": {
|
||||
"skill": "landing-report",
|
||||
"skillMdBytes": 53171,
|
||||
"skillMdLines": 928,
|
||||
"estTokens": 13293,
|
||||
"tmplBytes": 6847,
|
||||
"descriptionLen": 195,
|
||||
"hasGateEval": false,
|
||||
"hasPeriodicEval": false
|
||||
},
|
||||
"learn": {
|
||||
"skill": "learn",
|
||||
"skillMdBytes": 51908,
|
||||
"skillMdLines": 962,
|
||||
"estTokens": 12977,
|
||||
"tmplBytes": 5594,
|
||||
"descriptionLen": 178,
|
||||
"hasGateEval": true,
|
||||
"hasPeriodicEval": false
|
||||
},
|
||||
"make-pdf": {
|
||||
"skill": "make-pdf",
|
||||
"skillMdBytes": 37590,
|
||||
"skillMdLines": 796,
|
||||
"estTokens": 9398,
|
||||
"tmplBytes": 9306,
|
||||
"descriptionLen": 177,
|
||||
"hasGateEval": false,
|
||||
"hasPeriodicEval": false
|
||||
},
|
||||
"office-hours": {
|
||||
"skill": "office-hours",
|
||||
"skillMdBytes": 131110,
|
||||
"skillMdLines": 1706,
|
||||
"estTokens": 24548,
|
||||
"tmplBytes": 30541,
|
||||
"descriptionLen": 860,
|
||||
"hasGateEval": true,
|
||||
"hasPeriodicEval": false
|
||||
},
|
||||
"open-gstack-browser": {
|
||||
"skill": "open-gstack-browser",
|
||||
"skillMdBytes": 35570,
|
||||
"skillMdLines": 763,
|
||||
"estTokens": 8893,
|
||||
"tmplBytes": 7719,
|
||||
"descriptionLen": 204,
|
||||
"hasGateEval": false,
|
||||
"hasPeriodicEval": false
|
||||
},
|
||||
"pair-agent": {
|
||||
"skill": "pair-agent",
|
||||
"skillMdBytes": 56845,
|
||||
"skillMdLines": 1075,
|
||||
"estTokens": 14211,
|
||||
"tmplBytes": 9309,
|
||||
"descriptionLen": 167,
|
||||
"hasGateEval": false,
|
||||
"hasPeriodicEval": false
|
||||
},
|
||||
"plan-ceo-review": {
|
||||
"skill": "plan-ceo-review",
|
||||
"skillMdBytes": 151747,
|
||||
"skillMdLines": 1485,
|
||||
"estTokens": 22570,
|
||||
"tmplBytes": 29268,
|
||||
"descriptionLen": 794,
|
||||
"hasGateEval": true,
|
||||
"hasPeriodicEval": true
|
||||
},
|
||||
"plan-design-review": {
|
||||
"skill": "plan-design-review",
|
||||
"skillMdBytes": 127366,
|
||||
"skillMdLines": 1531,
|
||||
"estTokens": 22346,
|
||||
"tmplBytes": 18463,
|
||||
"descriptionLen": 218,
|
||||
"hasGateEval": true,
|
||||
"hasPeriodicEval": true
|
||||
},
|
||||
"plan-devex-review": {
|
||||
"skill": "plan-devex-review",
|
||||
"skillMdBytes": 125243,
|
||||
"skillMdLines": 1469,
|
||||
"estTokens": 19969,
|
||||
"tmplBytes": 18838,
|
||||
"descriptionLen": 250,
|
||||
"hasGateEval": true,
|
||||
"hasPeriodicEval": true
|
||||
},
|
||||
"plan-eng-review": {
|
||||
"skill": "plan-eng-review",
|
||||
"skillMdBytes": 124597,
|
||||
"skillMdLines": 1067,
|
||||
"estTokens": 17041,
|
||||
"tmplBytes": 14195,
|
||||
"descriptionLen": 231,
|
||||
"hasGateEval": true,
|
||||
"hasPeriodicEval": true
|
||||
},
|
||||
"plan-tune": {
|
||||
"skill": "plan-tune",
|
||||
"skillMdBytes": 73241,
|
||||
"skillMdLines": 1422,
|
||||
"estTokens": 18310,
|
||||
"tmplBytes": 26922,
|
||||
"descriptionLen": 327,
|
||||
"hasGateEval": true,
|
||||
"hasPeriodicEval": false
|
||||
},
|
||||
"qa": {
|
||||
"skill": "qa",
|
||||
"skillMdBytes": 84049,
|
||||
"skillMdLines": 1693,
|
||||
"estTokens": 21012,
|
||||
"tmplBytes": 12701,
|
||||
"descriptionLen": 218,
|
||||
"hasGateEval": true,
|
||||
"hasPeriodicEval": false
|
||||
},
|
||||
"qa-only": {
|
||||
"skill": "qa-only",
|
||||
"skillMdBytes": 66607,
|
||||
"skillMdLines": 1265,
|
||||
"estTokens": 16652,
|
||||
"tmplBytes": 3851,
|
||||
"descriptionLen": 165,
|
||||
"hasGateEval": true,
|
||||
"hasPeriodicEval": false
|
||||
},
|
||||
"retro": {
|
||||
"skill": "retro",
|
||||
"skillMdBytes": 93029,
|
||||
"skillMdLines": 1821,
|
||||
"estTokens": 23257,
|
||||
"tmplBytes": 42381,
|
||||
"descriptionLen": 648,
|
||||
"hasGateEval": true,
|
||||
"hasPeriodicEval": false
|
||||
},
|
||||
"review": {
|
||||
"skill": "review",
|
||||
"skillMdBytes": 108523,
|
||||
"skillMdLines": 1871,
|
||||
"estTokens": 27131,
|
||||
"tmplBytes": 14123,
|
||||
"descriptionLen": 205,
|
||||
"hasGateEval": true,
|
||||
"hasPeriodicEval": false
|
||||
},
|
||||
"scrape": {
|
||||
"skill": "scrape",
|
||||
"skillMdBytes": 33093,
|
||||
"skillMdLines": 696,
|
||||
"estTokens": 8273,
|
||||
"tmplBytes": 5237,
|
||||
"descriptionLen": 167,
|
||||
"hasGateEval": true,
|
||||
"hasPeriodicEval": false
|
||||
},
|
||||
"setup-browser-cookies": {
|
||||
"skill": "setup-browser-cookies",
|
||||
"skillMdBytes": 30558,
|
||||
"skillMdLines": 641,
|
||||
"estTokens": 7640,
|
||||
"tmplBytes": 2724,
|
||||
"descriptionLen": 222,
|
||||
"hasGateEval": false,
|
||||
"hasPeriodicEval": false
|
||||
},
|
||||
"setup-deploy": {
|
||||
"skill": "setup-deploy",
|
||||
"skillMdBytes": 54113,
|
||||
"skillMdLines": 990,
|
||||
"estTokens": 13528,
|
||||
"tmplBytes": 7780,
|
||||
"descriptionLen": 197,
|
||||
"hasGateEval": true,
|
||||
"hasPeriodicEval": false
|
||||
},
|
||||
"setup-gbrain": {
|
||||
"skill": "setup-gbrain",
|
||||
"skillMdBytes": 92312,
|
||||
"skillMdLines": 1860,
|
||||
"estTokens": 23078,
|
||||
"tmplBytes": 45975,
|
||||
"descriptionLen": 325,
|
||||
"hasGateEval": true,
|
||||
"hasPeriodicEval": false
|
||||
},
|
||||
"ship": {
|
||||
"skill": "ship",
|
||||
"skillMdBytes": 187706,
|
||||
"skillMdLines": 1435,
|
||||
"estTokens": 20697,
|
||||
"tmplBytes": 26135,
|
||||
"descriptionLen": 293,
|
||||
"hasGateEval": true,
|
||||
"hasPeriodicEval": true
|
||||
},
|
||||
"skillify": {
|
||||
"skill": "skillify",
|
||||
"skillMdBytes": 62696,
|
||||
"skillMdLines": 1222,
|
||||
"estTokens": 15674,
|
||||
"tmplBytes": 15124,
|
||||
"descriptionLen": 233,
|
||||
"hasGateEval": true,
|
||||
"hasPeriodicEval": false
|
||||
},
|
||||
"spec": {
|
||||
"skill": "spec",
|
||||
"skillMdBytes": 81577,
|
||||
"skillMdLines": 1601,
|
||||
"estTokens": 20394,
|
||||
"tmplBytes": 31255,
|
||||
"descriptionLen": 282,
|
||||
"hasGateEval": true,
|
||||
"hasPeriodicEval": false
|
||||
},
|
||||
"sync-gbrain": {
|
||||
"skill": "sync-gbrain",
|
||||
"skillMdBytes": 69975,
|
||||
"skillMdLines": 1259,
|
||||
"estTokens": 17494,
|
||||
"tmplBytes": 23629,
|
||||
"descriptionLen": 246,
|
||||
"hasGateEval": false,
|
||||
"hasPeriodicEval": false
|
||||
},
|
||||
"unfreeze": {
|
||||
"skill": "unfreeze",
|
||||
"skillMdBytes": 1504,
|
||||
"skillMdLines": 49,
|
||||
"estTokens": 376,
|
||||
"tmplBytes": 1386,
|
||||
"descriptionLen": 199,
|
||||
"hasGateEval": false,
|
||||
"hasPeriodicEval": false
|
||||
}
|
||||
}
|
||||
}
|
||||
|
|
@ -22,6 +22,14 @@ import { execSync } from 'child_process';
|
|||
|
||||
export interface SkillBaselineEntry {
|
||||
skill: string;
|
||||
/**
|
||||
* SKILL.md file bytes as captured. NOTE for rebaselines: the parity harness
|
||||
* compares UNION bytes (skeleton + sections/*.md) against this field, so a
|
||||
* committed baseline fixture must have carved skills' entries normalized to
|
||||
* union size (skeleton + sum of sections/*.md) or every carved skill reads
|
||||
* as 1.2-1.4x over on day one. The v1.57.7.0 and v1.64.1.0 fixtures are
|
||||
* union-normalized.
|
||||
*/
|
||||
skillMdBytes: number;
|
||||
skillMdLines: number;
|
||||
estTokens: number; // ~4 chars/token heuristic
|
||||
|
|
|
|||
|
|
@ -144,7 +144,9 @@ export const CARVE_GUARDS: Record<string, CarveGuard> = {
|
|||
},
|
||||
behavioral: 'external',
|
||||
externalTest: 'test/skill-e2e-plan-ceo-review-section-loading.test.ts',
|
||||
maxSkeletonBytes: 90_000,
|
||||
// v1.64.1.0: shared-preamble prose from the two parallel v1.64 waves lands
|
||||
// the skeleton at 90,280 B; +1 KB headroom.
|
||||
maxSkeletonBytes: 91_000,
|
||||
minUnionBytes: 80_000,
|
||||
mustContain: ['SCOPE EXPANSION', 'SELECTIVE EXPANSION', 'HOLD SCOPE', 'SCOPE REDUCTION'],
|
||||
// Default-on Codex outside-voice (codexPreflight block + CODEX_MODE branch
|
||||
|
|
@ -165,7 +167,9 @@ export const CARVE_GUARDS: Record<string, CarveGuard> = {
|
|||
behavioral: 'plan',
|
||||
// v1.2.0 activation lift (shared first-run-guidance preamble) + #2077 ask-first scope gate.
|
||||
// +~1 KB: plan-mode auto-select-B scope-gate exceptions (2026-08).
|
||||
maxSkeletonBytes: 68_000,
|
||||
// v1.64.1.0: shared-preamble prose from the two parallel v1.64 waves lands
|
||||
// the skeleton at 68,163 B; +~1 KB headroom.
|
||||
maxSkeletonBytes: 69_000,
|
||||
minUnionBytes: 70_000,
|
||||
mustContain: ['Architecture', 'Code Quality', 'Test', 'Performance'],
|
||||
// Cross-cutting preamble growth (v1.57.2.0 AUQ-failure prose fallback + the
|
||||
|
|
@ -240,7 +244,9 @@ export const CARVE_GUARDS: Record<string, CarveGuard> = {
|
|||
behavioral: 'prompt',
|
||||
// v1.2.0 activation lift: first-run-guidance section in the shared preamble,
|
||||
// plus the P1 office-hours closing handoff (AUQ that launches the next skill).
|
||||
maxSkeletonBytes: 98_000,
|
||||
// v1.64.1.0: shared-preamble prose from the two parallel v1.64 waves lands
|
||||
// the skeleton at 98,193 B; +~1 KB headroom.
|
||||
maxSkeletonBytes: 99_000,
|
||||
minUnionBytes: 70_000,
|
||||
mustContain: ['design doc', 'problem statement'],
|
||||
maxSizeRatio: 1.07,
|
||||
|
|
@ -289,7 +295,9 @@ export const CARVE_GUARDS: Record<string, CarveGuard> = {
|
|||
// +Conductor AUQ-default-prose rule + one-way/continuation safety in the
|
||||
// always-loaded AskUserQuestion Format section.
|
||||
// v1.2.0 activation lift: first-run-guidance section in the shared preamble.
|
||||
maxSkeletonBytes: 69_000,
|
||||
// v1.64.1.0: shared-preamble prose from the two parallel v1.64 waves lands
|
||||
// the skeleton at 69,022 B; +~1 KB headroom.
|
||||
maxSkeletonBytes: 70_000,
|
||||
minUnionBytes: 72_000,
|
||||
mustContain: ['Typography', 'Color', 'Aesthetic Direction'],
|
||||
// Cross-cutting preamble growth (v1.57.2.0 AUQ-failure prose fallback ~2KB +
|
||||
|
|
|
|||
|
|
@ -2,19 +2,23 @@
|
|||
* Cathedral parity suite — gate-tier (free, structural + content checks).
|
||||
*
|
||||
* Runs every PARITY_INVARIANTS check against the current SKILL.md output
|
||||
* vs the v1.57.7.0 baseline. Failures get an actionable, per-skill report
|
||||
* vs the v1.64.1.0 baseline. Failures get an actionable, per-skill report
|
||||
* showing missing phrases, missing headings, and size ratios.
|
||||
*
|
||||
* Baseline rebased v1.53.0.0 → v1.57.7.0: the v1.54–v1.57 releases (ship/plan
|
||||
* Baseline rebased v1.57.7.0 → v1.64.1.0: two parallel v1.64 waves (the
|
||||
* code-smell fix wave and main's #2571) each added shared-preamble prose,
|
||||
* pushing document-release / design-consultation / cso past their ratios on
|
||||
* the v1.57.7.0 anchor. The v1.64.1.0 baseline captures current UNION sizes
|
||||
* (skeleton + sections/*.md, matching what the harness measures) so the
|
||||
* per-skill ratios still catch future bloat.
|
||||
* Earlier rebase v1.53.0.0 → v1.57.7.0: the v1.54–v1.57 releases (ship/plan
|
||||
* carving, carve-guards, AUQ prose fallback, the cross-session decision-log
|
||||
* preamble) plus the mandatory unresolved-decisions status added to every
|
||||
* GSTACK REVIEW REPORT pushed the three plan-review skills past the 5% ratchet
|
||||
* on the v1.53 anchor even after exhaustive compression. The v1.57.7.0 baseline
|
||||
* captures current UNION sizes (skeleton + sections/*.md, matching what the
|
||||
* harness measures) so the per-skill 1.05 ratio still catches future bloat.
|
||||
* Earlier rebase v1.44.1 → v1.53.0.0: brain-aware-planning (v1.49–v1.52) + the
|
||||
* v1.53 redaction guard. Historical v1.44.1 / v1.46.0.0 / v1.47.0.0 / v1.53.0.0
|
||||
* baselines are retained in test/fixtures/ for the audit trail.
|
||||
* on the v1.53 anchor even after exhaustive compression. Before that,
|
||||
* v1.44.1 → v1.53.0.0: brain-aware-planning (v1.49–v1.52) + the v1.53
|
||||
* redaction guard. Historical baselines are retained in test/fixtures/ for
|
||||
* the audit trail.
|
||||
*
|
||||
* Periodic-tier LLM-judge parity (paid) lands in Phase B (v2.0.0.0)
|
||||
* alongside the sections/ extraction. Plumbing is in parity-harness.ts.
|
||||
|
|
@ -27,9 +31,9 @@ import { runParityChecks, PARITY_INVARIANTS } from './helpers/parity-harness';
|
|||
import type { ParityBaseline } from './helpers/capture-parity-baseline';
|
||||
|
||||
const REPO_ROOT = path.resolve(import.meta.dir, '..');
|
||||
const BASELINE_PATH = path.join(REPO_ROOT, 'test', 'fixtures', 'parity-baseline-v1.57.7.0.json');
|
||||
const BASELINE_PATH = path.join(REPO_ROOT, 'test', 'fixtures', 'parity-baseline-v1.64.1.0.json');
|
||||
|
||||
describe('parity suite vs v1.57.7.0 baseline (gate, free)', () => {
|
||||
describe('parity suite vs v1.64.1.0 baseline (gate, free)', () => {
|
||||
test('baseline exists', () => {
|
||||
expect(fs.existsSync(BASELINE_PATH)).toBe(true);
|
||||
});
|
||||
|
|
|
|||
Loading…
Reference in New Issue