feat(ms-ai-architect): Sesjon 15 — B2 K10 søsken-scope-ikke-overlapp
- Refaktor: overlap-kjerne flyttet til scripts/kb-eval/lib/sibling-overlap.mjs (bryter sirkulær import eval.mjs<->detect); detect re-eksporterer → B1-tester urørt - K10 = søsken-scope-ikke-overlapp, deterministisk cross-skill: perSkillSiblingOverlap + attachSiblingOverlap i eval.mjs. combined = boundaryTension + df-vektet leksikalsk; per-skill verdikt = verste søskenpar; terskel 7.0 (naturlig gap 7.42→6.67) - Empirisk (alle 5): eng+infra FAIL (7.42 mot hverandre), advisor/gov/sec PASS → eng↔infra-signal mater B3 merge/saner (ikke blokkering) - Gated baseline-regen via --write (descriptions urørt → judge K1/K4/K7/K8/K9 merget uendret, ikke fabrikkert); rubric K1-K10 - TDD: +9 tester (tests/kb-eval/test-k10-sibling-overlap.test.mjs), kb-eval 31→40 - 0 skriving til skills/. Suiter: validate 239 · kb-update 122 · kb-integrity 192/192
This commit is contained in:
parent
5ad4ed025c
commit
ba597eb988
5 changed files with 400 additions and 123 deletions
|
|
@ -1,6 +1,6 @@
|
|||
{
|
||||
"rubric": "K1-K9",
|
||||
"note": "Deterministic: K2,K3,K5,K6,refCountConsistency. LLM-judge (operator-gated): K1,K4,K7,K8,K9.",
|
||||
"rubric": "K1-K10",
|
||||
"note": "Deterministic: K2,K3,K5,K6,refCountConsistency,K10(siblingScopeOverlap). LLM-judge (operator-gated): K1,K4,K7,K8,K9.",
|
||||
"skills": [
|
||||
{
|
||||
"name": "ms-ai-advisor",
|
||||
|
|
@ -55,6 +55,12 @@
|
|||
"2026",
|
||||
"v3.0"
|
||||
]
|
||||
},
|
||||
"K10_siblingScopeOverlap": {
|
||||
"maxCombined": 4.5833,
|
||||
"worstSibling": "ms-ai-engineering",
|
||||
"pass": true,
|
||||
"threshold": 7
|
||||
}
|
||||
},
|
||||
"judgeInputs": {
|
||||
|
|
@ -158,6 +164,12 @@
|
|||
"preview",
|
||||
"GA"
|
||||
]
|
||||
},
|
||||
"K10_siblingScopeOverlap": {
|
||||
"maxCombined": 7.4167,
|
||||
"worstSibling": "ms-ai-infrastructure",
|
||||
"pass": false,
|
||||
"threshold": 7
|
||||
}
|
||||
},
|
||||
"judgeInputs": {
|
||||
|
|
@ -253,6 +265,12 @@
|
|||
"sample": [
|
||||
"2024"
|
||||
]
|
||||
},
|
||||
"K10_siblingScopeOverlap": {
|
||||
"maxCombined": 6.6667,
|
||||
"worstSibling": "ms-ai-engineering",
|
||||
"pass": true,
|
||||
"threshold": 7
|
||||
}
|
||||
},
|
||||
"judgeInputs": {
|
||||
|
|
@ -348,6 +366,12 @@
|
|||
"preview",
|
||||
"GA"
|
||||
]
|
||||
},
|
||||
"K10_siblingScopeOverlap": {
|
||||
"maxCombined": 7.4167,
|
||||
"worstSibling": "ms-ai-engineering",
|
||||
"pass": false,
|
||||
"threshold": 7
|
||||
}
|
||||
},
|
||||
"judgeInputs": {
|
||||
|
|
@ -443,6 +467,12 @@
|
|||
"sample": [
|
||||
"2025"
|
||||
]
|
||||
},
|
||||
"K10_siblingScopeOverlap": {
|
||||
"maxCombined": 6.5,
|
||||
"worstSibling": "ms-ai-governance",
|
||||
"pass": true,
|
||||
"threshold": 7
|
||||
}
|
||||
},
|
||||
"judgeInputs": {
|
||||
|
|
|
|||
Loading…
Add table
Add a link
Reference in a new issue