mirror of
https://github.com/microsoft/BCQuality.git
synced 2026-08-06 17:36:53 +01:00
6ed56b95b7
Retire the orchestrator's hardcoded ~28-token signal catalog by compiling a routing index from article front-matter. New tools/Build-RoutingIndex.ps1 scans all knowledge layers and emits routing-index.json (signal-token -> domain + backing articles), seeded from the migrated legacy catalog (routing-seed.json) so recall is never below today. Optional per-article 'signals:' front-matter (validator rule R24) is the authored precision path; domain-normalization reconciles front-matter/orchestrator/feedback domain vocabularies. Artifact is a runtime build (gitignored), orchestrator-facing only (not the lean agent-replayed knowledge index). CI guard Test-RoutingIndex.ps1 asserts determinism, seed recall floor, no orphaned signals, and normalization completeness; wired into the index workflow. Co-authored-by: Copilot <223556219+Copilot@users.noreply.github.com>
80 lines
4.5 KiB
JSON
80 lines
4.5 KiB
JSON
{
|
|
"$schema": "http://json-schema.org/draft-07/schema#",
|
|
"$id": "https://github.com/microsoft/BCQuality/tools/routing-index.schema.json",
|
|
"title": "BCQuality routing index",
|
|
"description": "Orchestrator-facing companion to knowledge-index.json. Maps deterministic PR-diff detection signals (AL tokens / regex) to their owning review domain and the knowledge articles that back them. Consumed by the PR-review orchestrator's manifest builder (Build-ReviewManifest, gated behind BCQ_INDEX_V2) to compute per-domain suspicion scores and shortlist candidate articles WITHOUT reading the hardcoded regex catalog that used to live in orchestrator code. Regenerated deterministically at authoring/CI time by tools/Build-RoutingIndex.ps1; never built in the token-paid path. This is NOT the lean agent-replayed knowledge index — it is not fed into the CLI prompt.",
|
|
"type": "object",
|
|
"required": ["version", "generatedAt", "generator", "articleCount", "signalCount", "domainNormalization", "objectKindDomain", "signals", "domains"],
|
|
"additionalProperties": true,
|
|
"properties": {
|
|
"$schema-note": { "type": "string" },
|
|
"version": { "type": "integer", "const": 1 },
|
|
"generatedAt": { "type": "string", "format": "date-time" },
|
|
"generator": { "type": "string" },
|
|
"enabledLayers": { "type": "array", "items": { "type": "string" } },
|
|
"articleCount": { "type": "integer", "minimum": 0 },
|
|
"signalCount": { "type": "integer", "minimum": 0 },
|
|
"domainNormalization": {
|
|
"description": "Front-matter domain (lowercase-hyphen) -> orchestrator domain label (TitleCase). Resolves the vocabulary mismatch between article front-matter (ui, error-handling), orchestrator $DomainMap (Accessibility, Error Handling), and feedback byDomain (lowercase).",
|
|
"type": "object",
|
|
"additionalProperties": { "type": "string" }
|
|
},
|
|
"objectKindDomain": {
|
|
"description": "AL object kind -> weak domain hint (applied once per changed object). Content-owned successor to the orchestrator's $BcqObjectKindDomain.",
|
|
"type": "object",
|
|
"additionalProperties": { "type": "string" }
|
|
},
|
|
"signals": {
|
|
"description": "Compiled detection signals. Each maps a regex over ADDED diff lines to a domain and the backing articles.",
|
|
"type": "array",
|
|
"items": {
|
|
"type": "object",
|
|
"required": ["token", "pattern", "domain", "source", "weight", "articles"],
|
|
"additionalProperties": false,
|
|
"properties": {
|
|
"token": {
|
|
"description": "Stable signal identifier (e.g. FindSet). Not necessarily an AL token verbatim.",
|
|
"type": "string"
|
|
},
|
|
"pattern": {
|
|
"description": "Regex matched (case-sensitively, as authored) against each added diff line. Escaped for JSON.",
|
|
"type": "string"
|
|
},
|
|
"domain": {
|
|
"description": "Owning review domain in the orchestrator's TitleCase taxonomy (post-normalization).",
|
|
"type": "string"
|
|
},
|
|
"source": {
|
|
"description": "Where the signal came from: 'seed' (legacy catalog migration), 'frontmatter-signal' (article-declared signals: block), or 'keyword' (soft keyword-derived, weight < 1).",
|
|
"type": "string",
|
|
"enum": ["seed", "frontmatter-signal", "keyword"]
|
|
},
|
|
"weight": {
|
|
"description": "Tier-1 confidence multiplier applied to signal hit counts in the domain-suspicion score. 1.0 for authored/seed signals; < 1 for soft keyword-derived signals. Tier-2 feedback weights (later) multiply on top of this.",
|
|
"type": "number",
|
|
"minimum": 0,
|
|
"maximum": 1
|
|
},
|
|
"articles": {
|
|
"description": "Repo-relative paths of the knowledge articles this signal routes to. Complete-by-construction: every article whose domain (and, for keyword signals, keyword) matches is attached, so recall is not limited by a hand-maintained catalog.",
|
|
"type": "array",
|
|
"items": { "type": "string" }
|
|
}
|
|
}
|
|
}
|
|
},
|
|
"domains": {
|
|
"description": "Per-domain aggregates for quick orchestrator lookups.",
|
|
"type": "object",
|
|
"additionalProperties": {
|
|
"type": "object",
|
|
"required": ["articleCount", "signalCount"],
|
|
"additionalProperties": true,
|
|
"properties": {
|
|
"articleCount": { "type": "integer", "minimum": 0 },
|
|
"signalCount": { "type": "integer", "minimum": 0 }
|
|
}
|
|
}
|
|
}
|
|
}
|
|
}
|