mirror of
https://github.com/microsoft/BCQuality.git
synced 2026-08-06 17:36:53 +01:00
5c4bb480c9
The index is now produced by BCQuality itself: Entry's preparation step rebuilds knowledge-index.json over the live, already-pruned clone at the start of every run, and a new CI workflow validates the generator's health (determinism, full coverage, selection-input integrity). Consumers no longer invoke or know about the index. Rebuilding over the pruned clone (vs shipping a committed full-corpus index) keeps the index exact for any consumer policy: it can never list a denied article, so policy-excluded rules cannot leak into discovery. READ now states the index is discovery-only -- a finding must cite an article opened in full, and rows whose file is absent are discarded before ranking. - skills/entry.md: new 'Preparation -- knowledge index' precondition - skills/read.md: index ownership + discovery-only invariant - microsoft/skills/review/*.md (6): 'BCQuality builds' (not 'the filter emits') - agent-consumption.md 5a: runtime+CI ownership rationale - .github/workflows/knowledge-index.yml + scripts/Test-KnowledgeIndex.ps1: generator guard - .gitignore: never commit the runtime index Co-authored-by: Copilot <223556219+Copilot@users.noreply.github.com>
89 lines
4.3 KiB
PowerShell
89 lines
4.3 KiB
PowerShell
<#
|
|
.SYNOPSIS
|
|
CI guard for the knowledge-index generator (tools/Build-KnowledgeIndex.ps1).
|
|
|
|
.DESCRIPTION
|
|
BCQuality owns the knowledge index, so BCQuality CI — not each consumer —
|
|
proves the generator is healthy. This script does NOT ship a committed
|
|
index that consumers trust at runtime (the index is rebuilt over each
|
|
consumer's already-pruned clone by Entry's preparation step, which keeps it
|
|
exact for any policy). Instead it asserts the generator itself is sound:
|
|
|
|
1. Determinism — building twice yields byte-identical output once the
|
|
volatile `generatedAt` header is normalized.
|
|
2. Coverage — every `*/knowledge/**/*.md` article appears exactly once;
|
|
every indexed path exists; no duplicates; no article is dropped.
|
|
3. Selection-input integrity — every parsed article row carries the
|
|
non-empty `domain` + `keywords` the worklist predicate selects on, and
|
|
every article parses (an unparseable article is an invalid file).
|
|
|
|
Exit code 0 = healthy; non-zero = a problem CI must block on.
|
|
#>
|
|
[CmdletBinding()]
|
|
param(
|
|
[string] $Root = (Resolve-Path (Join-Path $PSScriptRoot '..' '..'))
|
|
)
|
|
|
|
Set-StrictMode -Version Latest
|
|
$ErrorActionPreference = 'Stop'
|
|
|
|
$generator = Join-Path $Root 'tools/Build-KnowledgeIndex.ps1'
|
|
if (-not (Test-Path $generator)) { throw "Generator not found: $generator" }
|
|
|
|
$tmp = Join-Path ([System.IO.Path]::GetTempPath()) ("kbindex_" + [guid]::NewGuid().ToString('N'))
|
|
New-Item -ItemType Directory -Force -Path $tmp | Out-Null
|
|
$idxA = Join-Path $tmp 'a.json'
|
|
$idxB = Join-Path $tmp 'b.json'
|
|
|
|
$problems = [System.Collections.Generic.List[string]]::new()
|
|
|
|
& $generator -BCQualityRoot $Root -IndexPath $idxA | Out-Null
|
|
& $generator -BCQualityRoot $Root -IndexPath $idxB | Out-Null
|
|
|
|
# 1. Determinism (ignoring the volatile generatedAt timestamp).
|
|
$norm = { param($p) ((Get-Content -LiteralPath $p -Raw) -replace '"generatedAt":"[^"]*"', '"generatedAt":"<n>"') }
|
|
if ((& $norm $idxA) -ne (& $norm $idxB)) {
|
|
$problems.Add('Non-deterministic: two builds differ beyond generatedAt.') | Out-Null
|
|
}
|
|
|
|
$index = Get-Content -LiteralPath $idxA -Raw | ConvertFrom-Json
|
|
$rows = @($index.articles)
|
|
|
|
# 2. Coverage: one row per knowledge .md, every path real, no duplicates.
|
|
$onDisk = @(
|
|
foreach ($layer in 'microsoft', 'community', 'custom') {
|
|
$kb = Join-Path $Root (Join-Path $layer 'knowledge')
|
|
if (Test-Path $kb) {
|
|
Get-ChildItem -LiteralPath $kb -Recurse -File -Filter '*.md' |
|
|
ForEach-Object { ($_.FullName.Substring($Root.Length).TrimStart([char]'/', [char]'\') -replace '\\', '/') }
|
|
}
|
|
}
|
|
)
|
|
if ($rows.Count -ne $onDisk.Count) {
|
|
$problems.Add("Coverage mismatch: index has $($rows.Count) rows, disk has $($onDisk.Count) knowledge .md files.") | Out-Null
|
|
}
|
|
$rowPaths = @($rows | ForEach-Object { $_.path })
|
|
$dupes = @($rowPaths | Group-Object | Where-Object Count -gt 1 | ForEach-Object { $_.Name })
|
|
if ($dupes.Count) { $problems.Add("Duplicate index rows: $($dupes -join ', ')") | Out-Null }
|
|
$missingOnDisk = @($rowPaths | Where-Object { -not (Test-Path (Join-Path $Root $_)) })
|
|
if ($missingOnDisk.Count) { $problems.Add("Indexed paths absent on disk: $($missingOnDisk -join ', ')") | Out-Null }
|
|
$missingInIndex = @($onDisk | Where-Object { $rowPaths -notcontains $_ })
|
|
if ($missingInIndex.Count) { $problems.Add("Articles missing from index: $($missingInIndex -join ', ')") | Out-Null }
|
|
|
|
# 3. Selection-input integrity: parsed rows must carry domain + keywords.
|
|
$unparsed = @($rows | Where-Object { -not $_.parsed } | ForEach-Object { $_.path })
|
|
if ($unparsed.Count) { $problems.Add("Unparseable (invalid) articles: $($unparsed -join ', ')") | Out-Null }
|
|
foreach ($r in $rows | Where-Object { $_.parsed }) {
|
|
if ([string]::IsNullOrWhiteSpace([string]$r.domain)) { $problems.Add("Empty domain: $($r.path)") | Out-Null }
|
|
if (-not @($r.keywords).Where({ "$_".Trim() }).Count) { $problems.Add("Empty keywords: $($r.path)") | Out-Null }
|
|
}
|
|
|
|
Remove-Item -Recurse -Force $tmp -ErrorAction SilentlyContinue
|
|
|
|
if ($problems.Count) {
|
|
Write-Host "Knowledge-index check FAILED ($($problems.Count) problem(s)):" -ForegroundColor Red
|
|
$problems | ForEach-Object { Write-Host " - $_" -ForegroundColor Red }
|
|
exit 1
|
|
}
|
|
Write-Host "Knowledge-index check PASSED: $($rows.Count) articles, deterministic, full coverage, selection inputs intact." -ForegroundColor Green
|
|
exit 0
|