mirror of
https://github.com/Egonex-AI/Understand-Anything.git
synced 2026-06-22 10:58:03 +08:00
feat: add /understand-knowledge for Karpathy LLM wiki knowledge bases
Support the Karpathy LLM wiki pattern — a three-layer architecture (raw sources + wiki markdown + schema) with wikilinks, index.md categories, and append-only log.md. Pipeline: - parse-knowledge-base.py: deterministic extraction of articles, wikilinks, categories from index.md, source nodes from raw/ - article-analyzer agent: LLM-based entity/claim extraction and implicit relationship discovery (builds_on, contradicts, etc.) - merge-knowledge-graph.py: combines scan + analysis with entity dedup, layer assignment from categories, tour generation Dashboard: - KnowledgeGraphView with d3-force layout (community clustering by index.md categories, degree-proportional sizing) - 5 knowledge node types (article, entity, topic, claim, source) - 6 knowledge edge types with visual styling - KnowledgeNodeDetails sidebar (wikilinks, backlinks, preview) - Auto-detect kind:"knowledge" → knowledge-only view mode Core: - 5 node types + 6 edge types added to NodeType/EdgeType unions - KnowledgeMeta interface (wikilinks, backlinks, category, content) - kind field on KnowledgeGraph for view mode detection - Zod schemas + node/edge type aliases Co-Authored-By: Claude Opus 4.6 (1M context) <noreply@anthropic.com>
This commit is contained in:
Lum1104
Generated
+28
-9
@@ -82,6 +82,9 @@ importers:
|
||||
'@xyflow/react':
|
||||
specifier: ^12.0.0
|
||||
version: 12.10.1(@types/react@19.2.14)(react-dom@19.2.4(react@19.2.4))(react@19.2.4)
|
||||
d3-force:
|
||||
specifier: ^3.0.0
|
||||
version: 3.0.0
|
||||
devlop:
|
||||
specifier: ^1.1.0
|
||||
version: 1.1.0
|
||||
@@ -104,6 +107,9 @@ importers:
|
||||
'@tailwindcss/vite':
|
||||
specifier: ^4.0.0
|
||||
version: 4.2.1(vite@6.4.1(@types/node@25.5.0)(jiti@2.6.1)(lightningcss@1.31.1)(yaml@2.8.3))
|
||||
'@types/d3-force':
|
||||
specifier: ^3.0.10
|
||||
version: 3.0.10
|
||||
'@types/react':
|
||||
specifier: ^19.0.0
|
||||
version: 19.2.14
|
||||
@@ -1011,6 +1017,9 @@ packages:
|
||||
'@types/d3-drag@3.0.7':
|
||||
resolution: {integrity: sha512-HE3jVKlzU9AaMazNufooRJ5ZpWmLIoc90A37WU2JMmeq28w1FQqCZswHZ3xR+SuxYftzHq6WU6KJHvqxKzTxxQ==}
|
||||
|
||||
'@types/d3-force@3.0.10':
|
||||
resolution: {integrity: sha512-ZYeSaCF3p73RdOKcjj+swRlZfnYpK1EbaDiYICEEp5Q6sUiqFaFQ9qgoshp5CzIyyb/yD09kD9o2zEltCexlgw==}
|
||||
|
||||
'@types/d3-interpolate@3.0.4':
|
||||
resolution: {integrity: sha512-mgLPETlrpVV1YRJIglr4Ez47g7Yxjl1lj7YKsiMCb27VJH9W8NVM6Bb9d8kkpG/uAQS5AmbA48q2IAolKKo1MA==}
|
||||
|
||||
@@ -1317,10 +1326,18 @@ packages:
|
||||
resolution: {integrity: sha512-wR/XK3D3XcLIZwpbvQwQ5fK+8Ykds1ip7A2Txe0yxncXSdq1L9skcG7blcedkOX+ZcgxGAmLX1FrRGbADwzi0w==}
|
||||
engines: {node: '>=12'}
|
||||
|
||||
d3-force@3.0.0:
|
||||
resolution: {integrity: sha512-zxV/SsA+U4yte8051P4ECydjD/S+qeYtnaIyAs9tgHCqfguma/aAQDjo85A9Z6EKhBirHRJHXIgJUlffT4wdLg==}
|
||||
engines: {node: '>=12'}
|
||||
|
||||
d3-interpolate@3.0.1:
|
||||
resolution: {integrity: sha512-3bYs1rOD33uo8aqJfKP3JWPAibgw8Zm2+L9vBKEHJ2Rg+viTR7o5Mmv5mZcieN+FRYaAOWX5SJATX6k1PWz72g==}
|
||||
engines: {node: '>=12'}
|
||||
|
||||
d3-quadtree@3.0.1:
|
||||
resolution: {integrity: sha512-04xDrxQTDTCFwP5H6hRhsRcb9xxv2RzkcsygFzmkSIOJy3PeRJP7sNk3VRIbKXcog561P9oU0/rVH6vDROAgUw==}
|
||||
engines: {node: '>=12'}
|
||||
|
||||
d3-selection@3.0.0:
|
||||
resolution: {integrity: sha512-fmTRWbNMmsmWq6xJV8D19U/gw/bwrHfNXxrIN+HfZgnzqTHp9jOmKMhsTUjXOJnZOdZY9Q28y4yebKzqDKlxlQ==}
|
||||
engines: {node: '>=12'}
|
||||
@@ -3345,6 +3362,8 @@ snapshots:
|
||||
dependencies:
|
||||
'@types/d3-selection': 3.0.11
|
||||
|
||||
'@types/d3-force@3.0.10': {}
|
||||
|
||||
'@types/d3-interpolate@3.0.4':
|
||||
dependencies:
|
||||
'@types/d3-color': 3.1.3
|
||||
@@ -3447,14 +3466,6 @@ snapshots:
|
||||
chai: 5.3.3
|
||||
tinyrainbow: 2.0.0
|
||||
|
||||
'@vitest/mocker@3.2.4(vite@7.3.1(@types/node@22.19.15)(jiti@2.6.1)(lightningcss@1.31.1)(yaml@2.8.3))':
|
||||
dependencies:
|
||||
'@vitest/spy': 3.2.4
|
||||
estree-walker: 3.0.3
|
||||
magic-string: 0.30.21
|
||||
optionalDependencies:
|
||||
vite: 7.3.1(@types/node@22.19.15)(jiti@2.6.1)(lightningcss@1.31.1)(yaml@2.8.3)
|
||||
|
||||
'@vitest/mocker@3.2.4(vite@7.3.1(@types/node@25.5.0)(jiti@2.6.1)(lightningcss@1.31.1)(yaml@2.8.3))':
|
||||
dependencies:
|
||||
'@vitest/spy': 3.2.4
|
||||
@@ -3762,10 +3773,18 @@ snapshots:
|
||||
|
||||
d3-ease@3.0.1: {}
|
||||
|
||||
d3-force@3.0.0:
|
||||
dependencies:
|
||||
d3-dispatch: 3.0.1
|
||||
d3-quadtree: 3.0.1
|
||||
d3-timer: 3.0.1
|
||||
|
||||
d3-interpolate@3.0.1:
|
||||
dependencies:
|
||||
d3-color: 3.1.0
|
||||
|
||||
d3-quadtree@3.0.1: {}
|
||||
|
||||
d3-selection@3.0.0: {}
|
||||
|
||||
d3-timer@3.0.1: {}
|
||||
@@ -5297,7 +5316,7 @@ snapshots:
|
||||
dependencies:
|
||||
'@types/chai': 5.2.3
|
||||
'@vitest/expect': 3.2.4
|
||||
'@vitest/mocker': 3.2.4(vite@7.3.1(@types/node@22.19.15)(jiti@2.6.1)(lightningcss@1.31.1)(yaml@2.8.3))
|
||||
'@vitest/mocker': 3.2.4(vite@7.3.1(@types/node@25.5.0)(jiti@2.6.1)(lightningcss@1.31.1)(yaml@2.8.3))
|
||||
'@vitest/pretty-format': 3.2.4
|
||||
'@vitest/runner': 3.2.4
|
||||
'@vitest/snapshot': 3.2.4
|
||||
|
||||
@@ -0,0 +1,93 @@
|
||||
---
|
||||
name: article-analyzer
|
||||
description: |
|
||||
Analyzes markdown files using pre-parsed structural data and LLM inference to extract knowledge graph nodes and edges (entities, claims, implicit relationships, topic clustering).
|
||||
model: inherit
|
||||
---
|
||||
|
||||
# Article Analyzer Agent
|
||||
|
||||
You are a knowledge graph extraction expert. Your job is to analyze wiki articles and extract **implicit** knowledge — entities, claims, and relationships that are NOT already captured by explicit wikilinks.
|
||||
|
||||
## Input
|
||||
|
||||
You will receive a batch of articles as a JSON array. Each article has:
|
||||
- `id`: the article node ID (e.g., `"article:concepts/concept-brain"`)
|
||||
- `name`: article title
|
||||
- `summary`: first paragraph
|
||||
- `wikilinks`: list of explicit wikilink targets (already captured as `related` edges — do NOT duplicate these)
|
||||
- `category`: index.md category (if any)
|
||||
- `content`: article text (truncated to ~3000 chars)
|
||||
|
||||
You will also receive the full list of existing node IDs so you can reference them.
|
||||
|
||||
## Task
|
||||
|
||||
For each article in the batch, extract:
|
||||
|
||||
### 1. Entities (people, tools, papers, organizations)
|
||||
Named things mentioned in the text that do NOT have their own wiki page (not in existing node IDs). Create `entity` nodes.
|
||||
|
||||
- `id`: `"entity:{normalized-name}"` (lowercase, hyphens for spaces)
|
||||
- `type`: `"entity"`
|
||||
- `name`: proper name as written
|
||||
- `summary`: one-line description from context
|
||||
- `tags`: `["entity"]` plus any relevant category
|
||||
- `complexity`: `"simple"`
|
||||
|
||||
### 2. Claims (decisions, assertions, theses)
|
||||
Specific assertions, architectural decisions, or key insights. Create `claim` nodes.
|
||||
|
||||
- `id`: `"claim:{article-stem}:{short-slug}"` (e.g., `"claim:decision-typescript-python:ts-core-py-clones"`)
|
||||
- `type`: `"claim"`
|
||||
- `name`: short claim title
|
||||
- `summary`: the assertion itself (1-2 sentences)
|
||||
- `tags`: `["claim"]` plus category
|
||||
- `complexity`: `"simple"`
|
||||
|
||||
### 3. Implicit Relationships
|
||||
Relationships between articles that go beyond simple wikilink association. Only emit these when there is clear textual evidence:
|
||||
|
||||
- **`builds_on`**: Article A explicitly extends, refines, or supersedes ideas from article B. Weight: 0.8
|
||||
- **`contradicts`**: Article A conflicts with or reverses a position from article B. Weight: 0.9
|
||||
- **`exemplifies`**: An entity or article is a concrete example of a concept. Weight: 0.7
|
||||
- **`authored_by`**: Article attributed to a specific entity (person/agent). Weight: 0.6
|
||||
- **`cites`**: Article references a raw source document. Weight: 0.7
|
||||
|
||||
Edge format:
|
||||
```json
|
||||
{
|
||||
"source": "article:...",
|
||||
"target": "article:... or entity:... or claim:... or source:...",
|
||||
"type": "builds_on",
|
||||
"direction": "forward",
|
||||
"weight": 0.8,
|
||||
"description": "Brief reason for this relationship"
|
||||
}
|
||||
```
|
||||
|
||||
## Rules
|
||||
|
||||
1. **Do NOT duplicate wikilink edges.** The parse script already created `related` edges for every `[[wikilink]]`. Your job is to find what the wikilinks missed.
|
||||
2. **Be conservative.** Only create edges with clear textual evidence. A vague thematic similarity is not enough.
|
||||
3. **Deduplicate entities.** If the same person/tool appears in multiple articles, create the entity node once.
|
||||
4. **Use existing IDs.** When creating edges to existing articles, use their exact `id` from the provided node list.
|
||||
5. **Keep it small.** For a batch of 10-15 articles, expect ~5-15 entities, ~5-10 claims, and ~10-20 implicit edges. Don't over-extract.
|
||||
|
||||
## Output Format
|
||||
|
||||
Write a JSON file to `$INTERMEDIATE_DIR/analysis-batch-$BATCH_NUM.json`:
|
||||
|
||||
```json
|
||||
{
|
||||
"nodes": [
|
||||
{ "id": "entity:...", "type": "entity", "name": "...", "summary": "...", "tags": [...], "complexity": "simple" },
|
||||
{ "id": "claim:...", "type": "claim", "name": "...", "summary": "...", "tags": [...], "complexity": "simple" }
|
||||
],
|
||||
"edges": [
|
||||
{ "source": "...", "target": "...", "type": "builds_on", "direction": "forward", "weight": 0.8, "description": "..." }
|
||||
]
|
||||
}
|
||||
```
|
||||
|
||||
Do NOT include any article or topic nodes in your output — those already exist from the parse script. Only output NEW entity nodes, claim nodes, and implicit edges.
|
||||
@@ -1,6 +1,6 @@
|
||||
import { z } from "zod";
|
||||
|
||||
// Edge types (29 values across 7 categories)
|
||||
// Edge types (35 values across 8 categories)
|
||||
export const EdgeTypeSchema = z.enum([
|
||||
"imports", "exports", "contains", "inherits", "implements", // Structural
|
||||
"calls", "subscribes", "publishes", "middleware", // Behavioral
|
||||
@@ -10,6 +10,7 @@ export const EdgeTypeSchema = z.enum([
|
||||
"deploys", "serves", "provisions", "triggers", // Infrastructure
|
||||
"migrates", "documents", "routes", "defines_schema", // Schema/Data
|
||||
"contains_flow", "flow_step", "cross_domain", // Domain
|
||||
"cites", "contradicts", "builds_on", "exemplifies", "categorized_under", "authored_by", // Knowledge
|
||||
]);
|
||||
|
||||
// Aliases that LLMs commonly generate instead of canonical node types
|
||||
@@ -55,6 +56,22 @@ export const NODE_TYPE_ALIASES: Record<string, string> = {
|
||||
business_process: "flow",
|
||||
task: "step",
|
||||
business_step: "step",
|
||||
// Knowledge aliases
|
||||
note: "article",
|
||||
page: "article",
|
||||
wiki_page: "article",
|
||||
person: "entity",
|
||||
actor: "entity",
|
||||
organization: "entity",
|
||||
tag: "topic",
|
||||
category: "topic",
|
||||
theme: "topic",
|
||||
assertion: "claim",
|
||||
decision: "claim",
|
||||
thesis: "claim",
|
||||
reference: "source",
|
||||
raw: "source",
|
||||
paper: "source",
|
||||
};
|
||||
|
||||
// Aliases that LLMs commonly generate instead of canonical edge types
|
||||
@@ -88,6 +105,20 @@ export const EDGE_TYPE_ALIASES: Record<string, string> = {
|
||||
has_flow: "contains_flow",
|
||||
next_step: "flow_step",
|
||||
interacts_with: "cross_domain",
|
||||
// Knowledge aliases
|
||||
references: "cites",
|
||||
cites_source: "cites",
|
||||
conflicts_with: "contradicts",
|
||||
disagrees_with: "contradicts",
|
||||
refines: "builds_on",
|
||||
elaborates: "builds_on",
|
||||
illustrates: "exemplifies",
|
||||
instance_of: "exemplifies",
|
||||
example_of: "exemplifies",
|
||||
belongs_to: "categorized_under",
|
||||
tagged_with: "categorized_under",
|
||||
written_by: "authored_by",
|
||||
created_by: "authored_by",
|
||||
// Note: "implemented_by" is intentionally NOT aliased to "implements" —
|
||||
// it inverts edge direction (see commit fd0df15). The LLM should use
|
||||
// "implements" with correct source/target instead.
|
||||
@@ -327,6 +358,13 @@ const DomainMetaSchema = z.object({
|
||||
entryType: z.enum(["http", "cli", "event", "cron", "manual"]).optional(),
|
||||
}).passthrough();
|
||||
|
||||
const KnowledgeMetaSchema = z.object({
|
||||
wikilinks: z.array(z.string()).optional(),
|
||||
backlinks: z.array(z.string()).optional(),
|
||||
category: z.string().optional(),
|
||||
content: z.string().optional(),
|
||||
}).passthrough();
|
||||
|
||||
export const GraphNodeSchema = z.object({
|
||||
id: z.string(),
|
||||
type: z.enum([
|
||||
@@ -334,6 +372,7 @@ export const GraphNodeSchema = z.object({
|
||||
"config", "document", "service", "table", "endpoint",
|
||||
"pipeline", "schema", "resource",
|
||||
"domain", "flow", "step",
|
||||
"article", "entity", "topic", "claim", "source",
|
||||
]),
|
||||
name: z.string(),
|
||||
filePath: z.string().optional(),
|
||||
@@ -343,6 +382,7 @@ export const GraphNodeSchema = z.object({
|
||||
complexity: z.enum(["simple", "moderate", "complex"]),
|
||||
languageNotes: z.string().optional(),
|
||||
domainMeta: DomainMetaSchema.optional(),
|
||||
knowledgeMeta: KnowledgeMetaSchema.optional(),
|
||||
}).passthrough();
|
||||
|
||||
export const GraphEdgeSchema = z.object({
|
||||
@@ -380,6 +420,7 @@ export const ProjectMetaSchema = z.object({
|
||||
|
||||
export const KnowledgeGraphSchema = z.object({
|
||||
version: z.string(),
|
||||
kind: z.enum(["codebase", "knowledge"]).optional(),
|
||||
project: ProjectMetaSchema,
|
||||
nodes: z.array(GraphNodeSchema),
|
||||
edges: z.array(GraphEdgeSchema),
|
||||
|
||||
@@ -1,11 +1,12 @@
|
||||
// Node types (16 total: 5 code + 8 non-code + 3 domain)
|
||||
// Node types (21 total: 5 code + 8 non-code + 3 domain + 5 knowledge)
|
||||
export type NodeType =
|
||||
| "file" | "function" | "class" | "module" | "concept"
|
||||
| "config" | "document" | "service" | "table" | "endpoint"
|
||||
| "pipeline" | "schema" | "resource"
|
||||
| "domain" | "flow" | "step";
|
||||
| "domain" | "flow" | "step"
|
||||
| "article" | "entity" | "topic" | "claim" | "source";
|
||||
|
||||
// Edge types (29 total in 7 categories: Structural, Behavioral, Data flow, Dependencies, Semantic, Infrastructure/Schema, Domain)
|
||||
// Edge types (35 total in 8 categories: Structural, Behavioral, Data flow, Dependencies, Semantic, Infrastructure/Schema, Domain, Knowledge)
|
||||
export type EdgeType =
|
||||
| "imports" | "exports" | "contains" | "inherits" | "implements" // Structural
|
||||
| "calls" | "subscribes" | "publishes" | "middleware" // Behavioral
|
||||
@@ -14,7 +15,16 @@ export type EdgeType =
|
||||
| "related" | "similar_to" // Semantic
|
||||
| "deploys" | "serves" | "provisions" | "triggers" // Infrastructure
|
||||
| "migrates" | "documents" | "routes" | "defines_schema" // Schema/Data
|
||||
| "contains_flow" | "flow_step" | "cross_domain"; // Domain
|
||||
| "contains_flow" | "flow_step" | "cross_domain" // Domain
|
||||
| "cites" | "contradicts" | "builds_on" | "exemplifies" | "categorized_under" | "authored_by"; // Knowledge
|
||||
|
||||
// Optional knowledge metadata for article/entity/topic/claim/source nodes
|
||||
export interface KnowledgeMeta {
|
||||
wikilinks?: string[];
|
||||
backlinks?: string[];
|
||||
category?: string;
|
||||
content?: string;
|
||||
}
|
||||
|
||||
// Optional domain metadata for domain/flow/step nodes
|
||||
export interface DomainMeta {
|
||||
@@ -25,7 +35,7 @@ export interface DomainMeta {
|
||||
entryType?: "http" | "cli" | "event" | "cron" | "manual";
|
||||
}
|
||||
|
||||
// GraphNode with 16 types: 5 code + 8 non-code + 3 domain
|
||||
// GraphNode with 21 types: 5 code + 8 non-code + 3 domain + 5 knowledge
|
||||
export interface GraphNode {
|
||||
id: string;
|
||||
type: NodeType;
|
||||
@@ -37,6 +47,7 @@ export interface GraphNode {
|
||||
complexity: "simple" | "moderate" | "complex";
|
||||
languageNotes?: string;
|
||||
domainMeta?: DomainMeta;
|
||||
knowledgeMeta?: KnowledgeMeta;
|
||||
}
|
||||
|
||||
// GraphEdge with rich relationship modeling
|
||||
@@ -79,6 +90,7 @@ export interface ProjectMeta {
|
||||
// Root KnowledgeGraph
|
||||
export interface KnowledgeGraph {
|
||||
version: string;
|
||||
kind?: "codebase" | "knowledge";
|
||||
project: ProjectMeta;
|
||||
nodes: GraphNode[];
|
||||
edges: GraphEdge[];
|
||||
|
||||
@@ -13,15 +13,17 @@
|
||||
"@dagrejs/dagre": "^2.0.4",
|
||||
"@understand-anything/core": "workspace:*",
|
||||
"@xyflow/react": "^12.0.0",
|
||||
"react": "^19.0.0",
|
||||
"react-dom": "^19.0.0",
|
||||
"d3-force": "^3.0.0",
|
||||
"devlop": "^1.1.0",
|
||||
"hast-util-to-jsx-runtime": "^2.3.6",
|
||||
"react": "^19.0.0",
|
||||
"react-dom": "^19.0.0",
|
||||
"react-markdown": "^10.1.0",
|
||||
"zustand": "^5.0.0"
|
||||
},
|
||||
"devDependencies": {
|
||||
"@tailwindcss/vite": "^4.0.0",
|
||||
"@types/d3-force": "^3.0.10",
|
||||
"@types/react": "^19.0.0",
|
||||
"@types/react-dom": "^19.0.0",
|
||||
"@vitejs/plugin-react": "^4.3.0",
|
||||
|
||||
@@ -4,6 +4,7 @@ import type { GraphIssue } from "@understand-anything/core/schema";
|
||||
import { useDashboardStore } from "./store";
|
||||
import GraphView from "./components/GraphView";
|
||||
import DomainGraphView from "./components/DomainGraphView";
|
||||
import KnowledgeGraphView from "./components/KnowledgeGraphView";
|
||||
import CodeViewer from "./components/CodeViewer";
|
||||
import SearchBar from "./components/SearchBar";
|
||||
import NodeInfo from "./components/NodeInfo";
|
||||
@@ -104,6 +105,7 @@ function Dashboard({ accessToken }: { accessToken: string }) {
|
||||
const [metaTheme, setMetaTheme] = useState<ThemeConfig | null>(null);
|
||||
const viewMode = useDashboardStore((s) => s.viewMode);
|
||||
const setViewMode = useDashboardStore((s) => s.setViewMode);
|
||||
const isKnowledgeGraph = useDashboardStore((s) => s.isKnowledgeGraph);
|
||||
const domainGraph = useDashboardStore((s) => s.domainGraph);
|
||||
const setDomainGraph = useDashboardStore((s) => s.setDomainGraph);
|
||||
|
||||
@@ -240,6 +242,11 @@ function Dashboard({ accessToken }: { accessToken: string }) {
|
||||
if (result.success && result.data) {
|
||||
setGraph(result.data);
|
||||
setGraphIssues(result.issues);
|
||||
// Auto-detect knowledge graph kind
|
||||
if ((data as Record<string, unknown>).kind === "knowledge") {
|
||||
setViewMode("knowledge");
|
||||
useDashboardStore.getState().setIsKnowledgeGraph(true);
|
||||
}
|
||||
for (const issue of result.issues) {
|
||||
if (issue.level === "auto-corrected") {
|
||||
console.warn(`[graph] auto-corrected: ${issue.message}`);
|
||||
@@ -331,7 +338,7 @@ function Dashboard({ accessToken }: { accessToken: string }) {
|
||||
</h1>
|
||||
<div className="w-px h-5 bg-border-subtle" />
|
||||
<PersonaSelector />
|
||||
{graph && domainGraph && (
|
||||
{graph && !isKnowledgeGraph && domainGraph && (
|
||||
<>
|
||||
<div className="w-px h-5 bg-border-subtle" />
|
||||
<div className="flex items-center bg-elevated rounded-lg p-0.5">
|
||||
@@ -369,14 +376,17 @@ function Dashboard({ accessToken }: { accessToken: string }) {
|
||||
<div className="flex items-center gap-4 w-max">
|
||||
<DiffToggle />
|
||||
<div className="flex items-center gap-1">
|
||||
{([
|
||||
{ key: "code", label: "Code", color: "var(--color-node-file)" },
|
||||
{ key: "config", label: "Config", color: "var(--color-node-config)" },
|
||||
{ key: "docs", label: "Docs", color: "var(--color-node-document)" },
|
||||
{ key: "infra", label: "Infra", color: "var(--color-node-service)" },
|
||||
{ key: "data", label: "Data", color: "var(--color-node-table)" },
|
||||
{ key: "domain", label: "Domain", color: "var(--color-node-concept)" },
|
||||
] as const).map((cat) => (
|
||||
{(isKnowledgeGraph ? [
|
||||
{ key: "knowledge" as const, label: "All", color: "var(--color-node-article)" },
|
||||
] : [
|
||||
{ key: "code" as const, label: "Code", color: "var(--color-node-file)" },
|
||||
{ key: "config" as const, label: "Config", color: "var(--color-node-config)" },
|
||||
{ key: "docs" as const, label: "Docs", color: "var(--color-node-document)" },
|
||||
{ key: "infra" as const, label: "Infra", color: "var(--color-node-service)" },
|
||||
{ key: "data" as const, label: "Data", color: "var(--color-node-table)" },
|
||||
{ key: "domain" as const, label: "Domain", color: "var(--color-node-concept)" },
|
||||
{ key: "knowledge" as const, label: "Knowledge", color: "var(--color-node-article)" },
|
||||
]).map((cat) => (
|
||||
<button
|
||||
key={cat.key}
|
||||
onClick={() => toggleNodeTypeFilter(cat.key)}
|
||||
@@ -468,7 +478,9 @@ function Dashboard({ accessToken }: { accessToken: string }) {
|
||||
<div className="flex-1 flex min-h-0 relative">
|
||||
{/* Graph area */}
|
||||
<div className="flex-1 min-w-0 min-h-0 relative">
|
||||
{viewMode === "domain" && domainGraph ? (
|
||||
{viewMode === "knowledge" ? (
|
||||
<KnowledgeGraphView />
|
||||
) : viewMode === "domain" && domainGraph ? (
|
||||
<DomainGraphView />
|
||||
) : (
|
||||
<GraphView />
|
||||
|
||||
@@ -21,6 +21,11 @@ const typeColors: Record<NodeType, string> = {
|
||||
domain: "var(--color-node-concept)",
|
||||
flow: "var(--color-node-pipeline)",
|
||||
step: "var(--color-node-function)",
|
||||
article: "var(--color-node-article)",
|
||||
entity: "var(--color-node-entity)",
|
||||
topic: "var(--color-node-topic)",
|
||||
claim: "var(--color-node-claim)",
|
||||
source: "var(--color-node-source)",
|
||||
};
|
||||
|
||||
const typeTextColors: Record<NodeType, string> = {
|
||||
@@ -40,6 +45,11 @@ const typeTextColors: Record<NodeType, string> = {
|
||||
domain: "text-node-concept",
|
||||
flow: "text-node-pipeline",
|
||||
step: "text-node-function",
|
||||
article: "text-node-article",
|
||||
entity: "text-node-entity",
|
||||
topic: "text-node-topic",
|
||||
claim: "text-node-claim",
|
||||
source: "text-node-source",
|
||||
};
|
||||
|
||||
const complexityColors: Record<string, string> = {
|
||||
|
||||
@@ -57,6 +57,7 @@ const NODE_TYPE_TO_CATEGORY: Record<NodeType, NodeCategory> = {
|
||||
service: "infra", resource: "infra", pipeline: "infra",
|
||||
table: "data", endpoint: "data", schema: "data",
|
||||
domain: "domain", flow: "domain", step: "domain",
|
||||
article: "knowledge", entity: "knowledge", topic: "knowledge", claim: "knowledge", source: "knowledge",
|
||||
} as const;
|
||||
|
||||
// ── Helper components that must live inside <ReactFlow> ────────────────
|
||||
|
||||
@@ -0,0 +1,260 @@
|
||||
import { useMemo, useCallback } from "react";
|
||||
import {
|
||||
ReactFlow,
|
||||
ReactFlowProvider,
|
||||
Background,
|
||||
BackgroundVariant,
|
||||
Controls,
|
||||
MiniMap,
|
||||
} from "@xyflow/react";
|
||||
import type { Edge, Node } from "@xyflow/react";
|
||||
import "@xyflow/react/dist/style.css";
|
||||
|
||||
import CustomNode from "./CustomNode";
|
||||
import type { CustomNodeData } from "./CustomNode";
|
||||
import { useDashboardStore } from "../store";
|
||||
import { applyForceLayout, NODE_WIDTH, NODE_HEIGHT } from "../utils/layout";
|
||||
import type { KnowledgeGraph } from "@understand-anything/core/types";
|
||||
|
||||
const nodeTypes = {
|
||||
custom: CustomNode,
|
||||
};
|
||||
|
||||
/** Edge style presets by knowledge edge type. */
|
||||
const EDGE_STYLES: Record<string, React.CSSProperties> = {
|
||||
related: { stroke: "var(--color-border-medium)", strokeWidth: 0.5, opacity: 0.12 },
|
||||
cites: { stroke: "var(--color-node-source)", strokeWidth: 1.5, strokeDasharray: "6 3" },
|
||||
contradicts: { stroke: "#c97070", strokeWidth: 2 },
|
||||
builds_on: { stroke: "var(--color-node-claim)", strokeWidth: 1.5 },
|
||||
exemplifies: { stroke: "var(--color-node-entity)", strokeWidth: 1, strokeDasharray: "3 3" },
|
||||
categorized_under: { stroke: "var(--color-border-medium)", strokeWidth: 0.5, opacity: 0.08 },
|
||||
authored_by: { stroke: "var(--color-node-entity)", strokeWidth: 1, strokeDasharray: "4 4" },
|
||||
implements: { stroke: "var(--color-node-function)", strokeWidth: 1, opacity: 0.4 },
|
||||
depends_on: { stroke: "var(--color-node-module)", strokeWidth: 1, opacity: 0.4 },
|
||||
};
|
||||
|
||||
/** Compute node size based on connection count. */
|
||||
function getNodeDimensions(
|
||||
edgeCount: number,
|
||||
): { width: number; height: number } {
|
||||
// Scale width/height by degree (connections)
|
||||
const scale = Math.min(1.5, Math.max(0.85, 0.85 + edgeCount * 0.03));
|
||||
return {
|
||||
width: Math.round(NODE_WIDTH * scale),
|
||||
height: Math.round(NODE_HEIGHT * scale),
|
||||
};
|
||||
}
|
||||
|
||||
function buildKnowledgeGraph(
|
||||
graph: KnowledgeGraph,
|
||||
selectedNodeId: string | null,
|
||||
focusNodeId: string | null,
|
||||
searchResults: Map<string, number>,
|
||||
tourHighlightedNodeIds: Set<string>,
|
||||
onNodeClick: (nodeId: string) => void,
|
||||
): { nodes: Node[]; edges: Edge[] } {
|
||||
// Count edges per node for degree-proportional sizing
|
||||
const edgeCounts = new Map<string, number>();
|
||||
for (const edge of graph.edges) {
|
||||
edgeCounts.set(edge.source, (edgeCounts.get(edge.source) ?? 0) + 1);
|
||||
edgeCounts.set(edge.target, (edgeCounts.get(edge.target) ?? 0) + 1);
|
||||
}
|
||||
|
||||
// Build community map from layers
|
||||
const communityMap = new Map<string, number>();
|
||||
graph.layers.forEach((layer, i) => {
|
||||
for (const nodeId of layer.nodeIds) {
|
||||
communityMap.set(nodeId, i);
|
||||
}
|
||||
});
|
||||
|
||||
// Determine neighbor IDs for focus/selection fading
|
||||
const neighborIds = new Set<string>();
|
||||
if (focusNodeId || selectedNodeId) {
|
||||
const focusId = focusNodeId ?? selectedNodeId;
|
||||
for (const edge of graph.edges) {
|
||||
if (edge.source === focusId) neighborIds.add(edge.target);
|
||||
if (edge.target === focusId) neighborIds.add(edge.source);
|
||||
}
|
||||
}
|
||||
|
||||
// Build node dimensions map
|
||||
const dims = new Map<string, { width: number; height: number }>();
|
||||
for (const node of graph.nodes) {
|
||||
const d = getNodeDimensions(edgeCounts.get(node.id) ?? 0);
|
||||
dims.set(node.id, d);
|
||||
}
|
||||
|
||||
// Build xyflow nodes
|
||||
const rfNodes: Node[] = graph.nodes.map((node) => {
|
||||
const isSelected = node.id === selectedNodeId;
|
||||
const isFocused = node.id === focusNodeId;
|
||||
const isNeighbor = neighborIds.has(node.id);
|
||||
const isSelectionFaded =
|
||||
(focusNodeId || selectedNodeId) &&
|
||||
!isSelected &&
|
||||
!isFocused &&
|
||||
!isNeighbor;
|
||||
const searchScore = searchResults.get(node.id);
|
||||
const isHighlighted = searchScore !== undefined;
|
||||
const isTourHighlighted = tourHighlightedNodeIds.has(node.id);
|
||||
|
||||
const data: CustomNodeData = {
|
||||
label: node.name,
|
||||
nodeType: node.type,
|
||||
summary: node.summary,
|
||||
complexity: node.complexity,
|
||||
isHighlighted,
|
||||
searchScore,
|
||||
isSelected,
|
||||
isTourHighlighted,
|
||||
isDiffChanged: false,
|
||||
isDiffAffected: false,
|
||||
isDiffFaded: false,
|
||||
isNeighbor,
|
||||
isSelectionFaded: !!isSelectionFaded,
|
||||
onNodeClick,
|
||||
incomingCount: edgeCounts.get(node.id) ?? 0,
|
||||
tags: node.tags,
|
||||
};
|
||||
|
||||
return {
|
||||
id: node.id,
|
||||
type: "custom" as const,
|
||||
position: { x: 0, y: 0 },
|
||||
data,
|
||||
};
|
||||
});
|
||||
|
||||
// Build xyflow edges
|
||||
const rfEdges: Edge[] = graph.edges.map((e, i) => {
|
||||
const style = EDGE_STYLES[e.type] ?? EDGE_STYLES.related;
|
||||
return {
|
||||
id: `ke-${i}-${e.source}-${e.target}`,
|
||||
source: e.source,
|
||||
target: e.target,
|
||||
style,
|
||||
animated: e.type === "contradicts",
|
||||
label: e.type !== "related" && e.type !== "categorized_under" ? e.type.replace(/_/g, " ") : undefined,
|
||||
labelStyle: { fill: "var(--color-text-muted)", fontSize: 9, opacity: 0.7 },
|
||||
labelBgStyle: { fill: "var(--color-surface)", fillOpacity: 0.9 },
|
||||
labelBgPadding: [4, 2] as [number, number],
|
||||
labelBgBorderRadius: 3,
|
||||
};
|
||||
});
|
||||
|
||||
// Apply force layout with community clustering
|
||||
return applyForceLayout(rfNodes, rfEdges, dims, communityMap);
|
||||
}
|
||||
|
||||
function KnowledgeGraphViewInner() {
|
||||
const graph = useDashboardStore((s) => s.graph);
|
||||
const selectedNodeId = useDashboardStore((s) => s.selectedNodeId);
|
||||
const focusNodeId = useDashboardStore((s) => s.focusNodeId);
|
||||
const selectNode = useDashboardStore((s) => s.selectNode);
|
||||
const searchResultsRaw = useDashboardStore((s) => s.searchResults);
|
||||
const tourHighlightedNodeIds = useDashboardStore((s) => s.tourHighlightedNodeIds);
|
||||
const nodeTypeFilters = useDashboardStore((s) => s.nodeTypeFilters);
|
||||
|
||||
const onNodeClick = useCallback(
|
||||
(nodeId: string) => selectNode(nodeId),
|
||||
[selectNode],
|
||||
);
|
||||
|
||||
const searchResults = useMemo(
|
||||
() => new Map(searchResultsRaw.map((r) => [r.nodeId, r.score])),
|
||||
[searchResultsRaw],
|
||||
);
|
||||
|
||||
const tourSet = useMemo(
|
||||
() => new Set(tourHighlightedNodeIds),
|
||||
[tourHighlightedNodeIds],
|
||||
);
|
||||
|
||||
const { nodes, edges } = useMemo(() => {
|
||||
if (!graph) return { nodes: [], edges: [] };
|
||||
|
||||
// Filter graph by active node type filters
|
||||
const filteredNodes = graph.nodes.filter((n) => {
|
||||
if (["article", "entity", "topic", "claim", "source"].includes(n.type)) {
|
||||
return nodeTypeFilters.knowledge !== false;
|
||||
}
|
||||
return true;
|
||||
});
|
||||
|
||||
const filteredNodeIds = new Set(filteredNodes.map((n) => n.id));
|
||||
const filteredEdges = graph.edges.filter(
|
||||
(e) => filteredNodeIds.has(e.source) && filteredNodeIds.has(e.target),
|
||||
);
|
||||
|
||||
const filteredGraph: KnowledgeGraph = {
|
||||
...graph,
|
||||
nodes: filteredNodes,
|
||||
edges: filteredEdges,
|
||||
};
|
||||
|
||||
return buildKnowledgeGraph(
|
||||
filteredGraph,
|
||||
selectedNodeId,
|
||||
focusNodeId,
|
||||
searchResults,
|
||||
tourSet,
|
||||
onNodeClick,
|
||||
);
|
||||
}, [graph, selectedNodeId, focusNodeId, searchResults, tourSet, onNodeClick, nodeTypeFilters]);
|
||||
|
||||
if (!graph) {
|
||||
return (
|
||||
<div className="h-full flex items-center justify-center text-text-muted text-sm">
|
||||
No knowledge graph available. Run /understand-knowledge to generate one.
|
||||
</div>
|
||||
);
|
||||
}
|
||||
|
||||
return (
|
||||
<div className="h-full w-full relative">
|
||||
<ReactFlow
|
||||
nodes={nodes}
|
||||
edges={edges}
|
||||
nodeTypes={nodeTypes}
|
||||
fitView
|
||||
fitViewOptions={{ padding: 0.15 }}
|
||||
minZoom={0.05}
|
||||
maxZoom={2}
|
||||
proOptions={{ hideAttribution: true }}
|
||||
>
|
||||
<Background
|
||||
variant={BackgroundVariant.Dots}
|
||||
gap={20}
|
||||
size={1}
|
||||
color="var(--color-border-subtle)"
|
||||
/>
|
||||
<Controls />
|
||||
<MiniMap
|
||||
nodeColor={(n) => {
|
||||
const data = n.data as CustomNodeData | undefined;
|
||||
const type = data?.nodeType ?? "article";
|
||||
const colorMap: Record<string, string> = {
|
||||
article: "var(--color-node-article)",
|
||||
entity: "var(--color-node-entity)",
|
||||
topic: "var(--color-node-topic)",
|
||||
claim: "var(--color-node-claim)",
|
||||
source: "var(--color-node-source)",
|
||||
};
|
||||
return colorMap[type] ?? "var(--color-accent)";
|
||||
}}
|
||||
maskColor="var(--glass-bg)"
|
||||
className="!bg-surface !border !border-border-subtle"
|
||||
/>
|
||||
</ReactFlow>
|
||||
</div>
|
||||
);
|
||||
}
|
||||
|
||||
export default function KnowledgeGraphView() {
|
||||
return (
|
||||
<ReactFlowProvider>
|
||||
<KnowledgeGraphViewInner />
|
||||
</ReactFlowProvider>
|
||||
);
|
||||
}
|
||||
@@ -20,6 +20,11 @@ const typeBadgeColors: Record<NodeType, string> = {
|
||||
domain: "text-node-concept border border-node-concept/30 bg-node-concept/10",
|
||||
flow: "text-node-pipeline border border-node-pipeline/30 bg-node-pipeline/10",
|
||||
step: "text-node-function border border-node-function/30 bg-node-function/10",
|
||||
article: "text-node-article border border-node-article/30 bg-node-article/10",
|
||||
entity: "text-node-entity border border-node-entity/30 bg-node-entity/10",
|
||||
topic: "text-node-topic border border-node-topic/30 bg-node-topic/10",
|
||||
claim: "text-node-claim border border-node-claim/30 bg-node-claim/10",
|
||||
source: "text-node-source border border-node-source/30 bg-node-source/10",
|
||||
};
|
||||
|
||||
const complexityBadgeColors: Record<string, string> = {
|
||||
@@ -62,6 +67,12 @@ const EDGE_LABELS: Record<EdgeType, { forward: string; backward: string }> = {
|
||||
contains_flow: { forward: "contains flow", backward: "flow in" },
|
||||
flow_step: { forward: "flow step", backward: "step of" },
|
||||
cross_domain: { forward: "cross-domain to", backward: "cross-domain from" },
|
||||
cites: { forward: "cites", backward: "cited by" },
|
||||
contradicts: { forward: "contradicts", backward: "contradicted by" },
|
||||
builds_on: { forward: "builds on", backward: "built upon by" },
|
||||
exemplifies: { forward: "exemplifies", backward: "exemplified by" },
|
||||
categorized_under: { forward: "categorized under", backward: "categorizes" },
|
||||
authored_by: { forward: "authored by", backward: "authored" },
|
||||
};
|
||||
|
||||
/**
|
||||
@@ -78,6 +89,97 @@ function getDirectionalLabel(edgeType: string, isSource: boolean): string {
|
||||
return isSource ? labels.forward : labels.backward;
|
||||
}
|
||||
|
||||
function KnowledgeNodeDetails({ node, graph }: { node: GraphNode; graph: KnowledgeGraph }) {
|
||||
const navigateToNode = useDashboardStore((s) => s.navigateToNode);
|
||||
const meta = node.knowledgeMeta;
|
||||
|
||||
// Wikilinks (outgoing related edges)
|
||||
const wikilinks = graph.edges
|
||||
.filter((e) => e.type === "related" && e.source === node.id)
|
||||
.map((e) => graph.nodes.find((n) => n.id === e.target))
|
||||
.filter((n): n is GraphNode => n !== undefined);
|
||||
|
||||
// Backlinks (incoming related edges)
|
||||
const backlinks = graph.edges
|
||||
.filter((e) => e.type === "related" && e.target === node.id)
|
||||
.map((e) => graph.nodes.find((n) => n.id === e.source))
|
||||
.filter((n): n is GraphNode => n !== undefined);
|
||||
|
||||
// Category
|
||||
const categoryEdge = graph.edges.find(
|
||||
(e) => e.type === "categorized_under" && e.source === node.id
|
||||
);
|
||||
const categoryNode = categoryEdge
|
||||
? graph.nodes.find((n) => n.id === categoryEdge.target)
|
||||
: null;
|
||||
|
||||
return (
|
||||
<div className="space-y-3">
|
||||
{categoryNode && (
|
||||
<div>
|
||||
<h4 className="text-[10px] uppercase tracking-wider text-text-muted mb-1">Category</h4>
|
||||
<button
|
||||
type="button"
|
||||
onClick={() => navigateToNode(categoryNode.id)}
|
||||
className="text-[11px] px-2 py-0.5 rounded bg-elevated text-accent hover:text-accent-bright transition-colors"
|
||||
>
|
||||
{categoryNode.name}
|
||||
</button>
|
||||
</div>
|
||||
)}
|
||||
{meta?.wikilinks && meta.wikilinks.length > 0 && (
|
||||
<div>
|
||||
<h4 className="text-[10px] uppercase tracking-wider text-text-muted mb-1">
|
||||
Wikilinks ({wikilinks.length})
|
||||
</h4>
|
||||
<div className="space-y-1 max-h-[200px] overflow-auto">
|
||||
{wikilinks.map((n) => (
|
||||
<button
|
||||
key={n.id}
|
||||
type="button"
|
||||
onClick={() => navigateToNode(n.id)}
|
||||
className="block w-full text-left px-2 py-1.5 rounded bg-elevated hover:bg-accent/10 text-[11px] text-text-secondary hover:text-accent transition-colors truncate"
|
||||
>
|
||||
{n.name}
|
||||
</button>
|
||||
))}
|
||||
</div>
|
||||
</div>
|
||||
)}
|
||||
{backlinks.length > 0 && (
|
||||
<div>
|
||||
<h4 className="text-[10px] uppercase tracking-wider text-text-muted mb-1">
|
||||
Backlinks ({backlinks.length})
|
||||
</h4>
|
||||
<div className="space-y-1 max-h-[200px] overflow-auto">
|
||||
{backlinks.map((n) => (
|
||||
<button
|
||||
key={n.id}
|
||||
type="button"
|
||||
onClick={() => navigateToNode(n.id)}
|
||||
className="block w-full text-left px-2 py-1.5 rounded bg-elevated hover:bg-accent/10 text-[11px] text-text-secondary hover:text-accent transition-colors truncate"
|
||||
>
|
||||
{n.name}
|
||||
</button>
|
||||
))}
|
||||
</div>
|
||||
</div>
|
||||
)}
|
||||
{meta?.content && (
|
||||
<div>
|
||||
<h4 className="text-[10px] uppercase tracking-wider text-text-muted mb-1">Preview</h4>
|
||||
<div className="text-[11px] text-text-secondary leading-relaxed bg-elevated rounded-lg p-3 max-h-[300px] overflow-auto whitespace-pre-wrap font-mono">
|
||||
{meta.content.slice(0, 1500)}
|
||||
{meta.content.length > 1500 && (
|
||||
<span className="text-text-muted">... (truncated)</span>
|
||||
)}
|
||||
</div>
|
||||
</div>
|
||||
)}
|
||||
</div>
|
||||
);
|
||||
}
|
||||
|
||||
function DomainNodeDetails({ node, graph }: { node: GraphNode; graph: KnowledgeGraph }) {
|
||||
const navigateToDomain = useDashboardStore((s) => s.navigateToDomain);
|
||||
const selectNode = useDashboardStore((s) => s.selectNode);
|
||||
@@ -380,6 +482,11 @@ export default function NodeInfo() {
|
||||
</div>
|
||||
)}
|
||||
|
||||
{/* Knowledge-specific details */}
|
||||
{activeGraph && node && (node.type === "article" || node.type === "entity" || node.type === "topic" || node.type === "claim" || node.type === "source") && (
|
||||
<KnowledgeNodeDetails node={node} graph={activeGraph} />
|
||||
)}
|
||||
|
||||
{/* Domain-specific details */}
|
||||
{activeGraph && node && (node.type === "domain" || node.type === "flow" || node.type === "step") && (
|
||||
<DomainNodeDetails node={node} graph={activeGraph} />
|
||||
|
||||
@@ -36,6 +36,13 @@
|
||||
--color-node-schema: #fcd34d;
|
||||
--color-node-resource: #a5b4fc;
|
||||
|
||||
/* Knowledge node types */
|
||||
--color-node-article: #d4a574;
|
||||
--color-node-entity: #7ba4c9;
|
||||
--color-node-topic: #c9b06c;
|
||||
--color-node-claim: #6fb07a;
|
||||
--color-node-source: #8a8a8a;
|
||||
|
||||
/* Diff */
|
||||
--color-diff-changed: #e05252;
|
||||
--color-diff-affected: #d4a030;
|
||||
|
||||
@@ -9,10 +9,10 @@ import type { ReactFlowInstance } from "@xyflow/react";
|
||||
|
||||
export type Persona = "non-technical" | "junior" | "experienced";
|
||||
export type NavigationLevel = "overview" | "layer-detail";
|
||||
export type NodeType = "file" | "function" | "class" | "module" | "concept" | "config" | "document" | "service" | "table" | "endpoint" | "pipeline" | "schema" | "resource" | "domain" | "flow" | "step";
|
||||
export type NodeType = "file" | "function" | "class" | "module" | "concept" | "config" | "document" | "service" | "table" | "endpoint" | "pipeline" | "schema" | "resource" | "domain" | "flow" | "step" | "article" | "entity" | "topic" | "claim" | "source";
|
||||
export type Complexity = "simple" | "moderate" | "complex";
|
||||
export type EdgeCategory = "structural" | "behavioral" | "data-flow" | "dependencies" | "semantic" | "infrastructure" | "domain";
|
||||
export type ViewMode = "structural" | "domain";
|
||||
export type EdgeCategory = "structural" | "behavioral" | "data-flow" | "dependencies" | "semantic" | "infrastructure" | "domain" | "knowledge";
|
||||
export type ViewMode = "structural" | "domain" | "knowledge";
|
||||
|
||||
export interface FilterState {
|
||||
nodeTypes: Set<NodeType>;
|
||||
@@ -21,9 +21,9 @@ export interface FilterState {
|
||||
edgeCategories: Set<EdgeCategory>;
|
||||
}
|
||||
|
||||
export const ALL_NODE_TYPES: NodeType[] = ["file", "function", "class", "module", "concept", "config", "document", "service", "table", "endpoint", "pipeline", "schema", "resource", "domain", "flow", "step"];
|
||||
export const ALL_NODE_TYPES: NodeType[] = ["file", "function", "class", "module", "concept", "config", "document", "service", "table", "endpoint", "pipeline", "schema", "resource", "domain", "flow", "step", "article", "entity", "topic", "claim", "source"];
|
||||
export const ALL_COMPLEXITIES: Complexity[] = ["simple", "moderate", "complex"];
|
||||
export const ALL_EDGE_CATEGORIES: EdgeCategory[] = ["structural", "behavioral", "data-flow", "dependencies", "semantic", "infrastructure", "domain"];
|
||||
export const ALL_EDGE_CATEGORIES: EdgeCategory[] = ["structural", "behavioral", "data-flow", "dependencies", "semantic", "infrastructure", "domain", "knowledge"];
|
||||
|
||||
export const EDGE_CATEGORY_MAP: Record<EdgeCategory, string[]> = {
|
||||
structural: ["imports", "exports", "contains", "inherits", "implements"],
|
||||
@@ -33,6 +33,7 @@ export const EDGE_CATEGORY_MAP: Record<EdgeCategory, string[]> = {
|
||||
semantic: ["related", "similar_to"],
|
||||
infrastructure: ["deploys", "serves", "provisions", "triggers", "migrates", "documents", "routes", "defines_schema"],
|
||||
domain: ["contains_flow", "flow_step", "cross_domain"],
|
||||
knowledge: ["cites", "contradicts", "builds_on", "exemplifies", "categorized_under", "authored_by"],
|
||||
};
|
||||
|
||||
export const DOMAIN_EDGE_TYPES = EDGE_CATEGORY_MAP.domain;
|
||||
@@ -45,7 +46,7 @@ const DEFAULT_FILTERS: FilterState = {
|
||||
};
|
||||
|
||||
/** Categories used for node type filter toggles. Single source of truth for NodeCategory. */
|
||||
export type NodeCategory = "code" | "config" | "docs" | "infra" | "data" | "domain";
|
||||
export type NodeCategory = "code" | "config" | "docs" | "infra" | "data" | "domain" | "knowledge";
|
||||
|
||||
/** Find which layer a node belongs to. Returns layerId or null. */
|
||||
function findNodeLayer(graph: KnowledgeGraph, nodeId: string): string | null {
|
||||
@@ -133,13 +134,15 @@ interface DashboardStore {
|
||||
nextTourStep: () => void;
|
||||
prevTourStep: () => void;
|
||||
|
||||
// Domain view
|
||||
// View mode
|
||||
viewMode: ViewMode;
|
||||
isKnowledgeGraph: boolean;
|
||||
domainGraph: KnowledgeGraph | null;
|
||||
activeDomainId: string | null;
|
||||
|
||||
setDomainGraph: (graph: KnowledgeGraph) => void;
|
||||
setViewMode: (mode: ViewMode) => void;
|
||||
setIsKnowledgeGraph: (value: boolean) => void;
|
||||
navigateToDomain: (domainId: string) => void;
|
||||
clearActiveDomain: () => void;
|
||||
}
|
||||
@@ -197,7 +200,7 @@ export const useDashboardStore = create<DashboardStore>()((set, get) => ({
|
||||
pathFinderOpen: false,
|
||||
reactFlowInstance: null,
|
||||
|
||||
nodeTypeFilters: { code: true, config: true, docs: true, infra: true, data: true, domain: true },
|
||||
nodeTypeFilters: { code: true, config: true, docs: true, infra: true, data: true, domain: true, knowledge: true },
|
||||
|
||||
toggleNodeTypeFilter: (category) =>
|
||||
set((state) => ({
|
||||
@@ -464,6 +467,7 @@ export const useDashboardStore = create<DashboardStore>()((set, get) => ({
|
||||
},
|
||||
|
||||
viewMode: "structural",
|
||||
isKnowledgeGraph: false,
|
||||
domainGraph: null,
|
||||
activeDomainId: null,
|
||||
|
||||
@@ -471,6 +475,10 @@ export const useDashboardStore = create<DashboardStore>()((set, get) => ({
|
||||
set({ domainGraph: graph });
|
||||
},
|
||||
|
||||
setIsKnowledgeGraph: (value) => {
|
||||
set({ isKnowledgeGraph: value });
|
||||
},
|
||||
|
||||
setViewMode: (mode) => {
|
||||
set({
|
||||
viewMode: mode,
|
||||
|
||||
@@ -1,4 +1,14 @@
|
||||
import dagre from "@dagrejs/dagre";
|
||||
import {
|
||||
forceSimulation,
|
||||
forceLink,
|
||||
forceManyBody,
|
||||
forceCenter,
|
||||
forceCollide,
|
||||
forceX,
|
||||
forceY,
|
||||
} from "d3-force";
|
||||
import type { SimulationNodeDatum, SimulationLinkDatum } from "d3-force";
|
||||
import type { Node, Edge } from "@xyflow/react";
|
||||
|
||||
export const NODE_WIDTH = 280;
|
||||
@@ -62,4 +72,114 @@ export function applyDagreLayout(
|
||||
return { nodes: layoutedNodes, edges };
|
||||
}
|
||||
|
||||
// ---------------------------------------------------------------------------
|
||||
// Force-directed layout (for knowledge graphs)
|
||||
// ---------------------------------------------------------------------------
|
||||
|
||||
interface ForceNode extends SimulationNodeDatum {
|
||||
id: string;
|
||||
community?: number;
|
||||
}
|
||||
|
||||
/**
|
||||
* Force-directed layout using d3-force — used for knowledge graphs.
|
||||
* Optionally groups nodes by community (layer/category).
|
||||
*/
|
||||
export function applyForceLayout(
|
||||
nodes: Node[],
|
||||
edges: Edge[],
|
||||
nodeDimensions?: Map<string, { width: number; height: number }>,
|
||||
communityMap?: Map<string, number>,
|
||||
): { nodes: Node[]; edges: Edge[] } {
|
||||
if (nodes.length === 0) return { nodes, edges };
|
||||
|
||||
// Build simulation nodes with optional community assignment
|
||||
const simNodes: ForceNode[] = nodes.map((n) => ({
|
||||
id: n.id,
|
||||
x: Math.random() * 800 - 400,
|
||||
y: Math.random() * 800 - 400,
|
||||
community: communityMap?.get(n.id),
|
||||
}));
|
||||
|
||||
const nodeIdSet = new Set(simNodes.map((n) => n.id));
|
||||
const simLinks: SimulationLinkDatum<ForceNode>[] = edges
|
||||
.filter((e) => nodeIdSet.has(e.source as string) && nodeIdSet.has(e.target as string))
|
||||
.map((e) => ({
|
||||
source: e.source as string,
|
||||
target: e.target as string,
|
||||
}));
|
||||
|
||||
// Compute community centers for cluster attraction
|
||||
const communityCount = communityMap
|
||||
? Math.max(1, new Set(communityMap.values()).size)
|
||||
: 1;
|
||||
const communityAngle = (i: number) => (2 * Math.PI * i) / communityCount;
|
||||
// Scale cluster radius with node count for better spread
|
||||
const clusterRadius = Math.max(600, nodes.length * 5);
|
||||
|
||||
// Scale forces based on graph size
|
||||
const isLarge = nodes.length > 100;
|
||||
const chargeStrength = isLarge ? -600 : -350;
|
||||
const linkDistance = isLarge ? 250 : 150;
|
||||
|
||||
const sim = forceSimulation<ForceNode>(simNodes)
|
||||
.force(
|
||||
"link",
|
||||
forceLink<ForceNode, SimulationLinkDatum<ForceNode>>(simLinks)
|
||||
.id((d) => d.id)
|
||||
.distance(linkDistance)
|
||||
.strength(0.2),
|
||||
)
|
||||
.force("charge", forceManyBody().strength(chargeStrength).distanceMax(1500))
|
||||
.force("center", forceCenter(0, 0).strength(0.03))
|
||||
.force(
|
||||
"collide",
|
||||
forceCollide<ForceNode>().radius((d) => {
|
||||
const dims = nodeDimensions?.get(d.id);
|
||||
return Math.max(20, ((dims?.width ?? NODE_WIDTH) + 40) / 2);
|
||||
}).strength(0.8),
|
||||
);
|
||||
|
||||
// Add community clustering force if communities are provided
|
||||
if (communityMap && communityCount > 1) {
|
||||
sim.force(
|
||||
"clusterX",
|
||||
forceX<ForceNode>((d) => {
|
||||
const c = d.community ?? 0;
|
||||
return Math.cos(communityAngle(c)) * clusterRadius;
|
||||
}).strength(0.3),
|
||||
);
|
||||
sim.force(
|
||||
"clusterY",
|
||||
forceY<ForceNode>((d) => {
|
||||
const c = d.community ?? 0;
|
||||
return Math.sin(communityAngle(c)) * clusterRadius;
|
||||
}).strength(0.3),
|
||||
);
|
||||
}
|
||||
|
||||
// Run to convergence synchronously
|
||||
const ticks = Math.min(300, Math.max(100, nodes.length));
|
||||
sim.tick(ticks);
|
||||
sim.stop();
|
||||
|
||||
// Map positions back to xyflow nodes
|
||||
const posMap = new Map(simNodes.map((n) => [n.id, { x: n.x ?? 0, y: n.y ?? 0 }]));
|
||||
const layoutedNodes = nodes.map((node) => {
|
||||
const pos = posMap.get(node.id) ?? { x: 0, y: 0 };
|
||||
const dims = nodeDimensions?.get(node.id);
|
||||
const w = dims?.width ?? NODE_WIDTH;
|
||||
const h = dims?.height ?? NODE_HEIGHT;
|
||||
return {
|
||||
...node,
|
||||
position: {
|
||||
x: pos.x - w / 2,
|
||||
y: pos.y - h / 2,
|
||||
},
|
||||
};
|
||||
});
|
||||
|
||||
return { nodes: layoutedNodes, edges };
|
||||
}
|
||||
|
||||
|
||||
|
||||
+27
@@ -67,6 +67,9 @@ importers:
|
||||
'@xyflow/react':
|
||||
specifier: ^12.0.0
|
||||
version: 12.10.1(@types/react@19.2.14)(react-dom@19.2.4(react@19.2.4))(react@19.2.4)
|
||||
d3-force:
|
||||
specifier: ^3.0.0
|
||||
version: 3.0.0
|
||||
devlop:
|
||||
specifier: ^1.1.0
|
||||
version: 1.1.0
|
||||
@@ -89,6 +92,9 @@ importers:
|
||||
'@tailwindcss/vite':
|
||||
specifier: ^4.0.0
|
||||
version: 4.2.2(vite@6.4.1(@types/node@25.5.0)(jiti@2.6.1)(lightningcss@1.32.0)(yaml@2.8.3))
|
||||
'@types/d3-force':
|
||||
specifier: ^3.0.10
|
||||
version: 3.0.10
|
||||
'@types/react':
|
||||
specifier: ^19.0.0
|
||||
version: 19.2.14
|
||||
@@ -630,6 +636,9 @@ packages:
|
||||
'@types/d3-drag@3.0.7':
|
||||
resolution: {integrity: sha512-HE3jVKlzU9AaMazNufooRJ5ZpWmLIoc90A37WU2JMmeq28w1FQqCZswHZ3xR+SuxYftzHq6WU6KJHvqxKzTxxQ==}
|
||||
|
||||
'@types/d3-force@3.0.10':
|
||||
resolution: {integrity: sha512-ZYeSaCF3p73RdOKcjj+swRlZfnYpK1EbaDiYICEEp5Q6sUiqFaFQ9qgoshp5CzIyyb/yD09kD9o2zEltCexlgw==}
|
||||
|
||||
'@types/d3-interpolate@3.0.4':
|
||||
resolution: {integrity: sha512-mgLPETlrpVV1YRJIglr4Ez47g7Yxjl1lj7YKsiMCb27VJH9W8NVM6Bb9d8kkpG/uAQS5AmbA48q2IAolKKo1MA==}
|
||||
|
||||
@@ -858,10 +867,18 @@ packages:
|
||||
resolution: {integrity: sha512-wR/XK3D3XcLIZwpbvQwQ5fK+8Ykds1ip7A2Txe0yxncXSdq1L9skcG7blcedkOX+ZcgxGAmLX1FrRGbADwzi0w==}
|
||||
engines: {node: '>=12'}
|
||||
|
||||
d3-force@3.0.0:
|
||||
resolution: {integrity: sha512-zxV/SsA+U4yte8051P4ECydjD/S+qeYtnaIyAs9tgHCqfguma/aAQDjo85A9Z6EKhBirHRJHXIgJUlffT4wdLg==}
|
||||
engines: {node: '>=12'}
|
||||
|
||||
d3-interpolate@3.0.1:
|
||||
resolution: {integrity: sha512-3bYs1rOD33uo8aqJfKP3JWPAibgw8Zm2+L9vBKEHJ2Rg+viTR7o5Mmv5mZcieN+FRYaAOWX5SJATX6k1PWz72g==}
|
||||
engines: {node: '>=12'}
|
||||
|
||||
d3-quadtree@3.0.1:
|
||||
resolution: {integrity: sha512-04xDrxQTDTCFwP5H6hRhsRcb9xxv2RzkcsygFzmkSIOJy3PeRJP7sNk3VRIbKXcog561P9oU0/rVH6vDROAgUw==}
|
||||
engines: {node: '>=12'}
|
||||
|
||||
d3-selection@3.0.0:
|
||||
resolution: {integrity: sha512-fmTRWbNMmsmWq6xJV8D19U/gw/bwrHfNXxrIN+HfZgnzqTHp9jOmKMhsTUjXOJnZOdZY9Q28y4yebKzqDKlxlQ==}
|
||||
engines: {node: '>=12'}
|
||||
@@ -2078,6 +2095,8 @@ snapshots:
|
||||
dependencies:
|
||||
'@types/d3-selection': 3.0.11
|
||||
|
||||
'@types/d3-force@3.0.10': {}
|
||||
|
||||
'@types/d3-interpolate@3.0.4':
|
||||
dependencies:
|
||||
'@types/d3-color': 3.1.3
|
||||
@@ -2330,10 +2349,18 @@ snapshots:
|
||||
|
||||
d3-ease@3.0.1: {}
|
||||
|
||||
d3-force@3.0.0:
|
||||
dependencies:
|
||||
d3-dispatch: 3.0.1
|
||||
d3-quadtree: 3.0.1
|
||||
d3-timer: 3.0.1
|
||||
|
||||
d3-interpolate@3.0.1:
|
||||
dependencies:
|
||||
d3-color: 3.1.0
|
||||
|
||||
d3-quadtree@3.0.1: {}
|
||||
|
||||
d3-selection@3.0.0: {}
|
||||
|
||||
d3-timer@3.0.1: {}
|
||||
|
||||
@@ -0,0 +1,132 @@
|
||||
---
|
||||
name: understand-knowledge
|
||||
description: Analyze a Karpathy-pattern LLM wiki knowledge base and generate an interactive knowledge graph with entity extraction, implicit relationships, and topic clustering.
|
||||
argument-hint: [wiki-directory]
|
||||
---
|
||||
|
||||
# /understand-knowledge
|
||||
|
||||
Analyzes a Karpathy-pattern LLM wiki — a three-layer knowledge base with raw sources, wiki markdown, and a schema file — and produces an interactive knowledge graph dashboard.
|
||||
|
||||
## What It Detects
|
||||
|
||||
The **Karpathy LLM wiki pattern** (see https://gist.github.com/karpathy/442a6bf555914893e9891c11519de94f):
|
||||
- **Raw sources** — immutable source documents (articles, papers, data files)
|
||||
- **Wiki** — LLM-generated markdown files with wikilinks (`[[target]]` syntax)
|
||||
- **Schema** — CLAUDE.md, AGENTS.md, or similar configuration file
|
||||
- **index.md** — content catalog organized by categories
|
||||
- **log.md** — chronological operation log
|
||||
|
||||
Detection signals: has `index.md` + multiple `.md` files with wikilinks. May have `raw/` directory and schema file.
|
||||
|
||||
## Instructions
|
||||
|
||||
### Phase 1: DETECT
|
||||
|
||||
1. Determine the target directory:
|
||||
- If the user provided a path argument, use that
|
||||
- Otherwise, use the current working directory
|
||||
|
||||
2. Run the format detection script bundled with this skill:
|
||||
```
|
||||
python3 <SKILL_DIR>/parse-knowledge-base.py <TARGET_DIR>
|
||||
```
|
||||
- If the script exits with an error, tell the user this doesn't appear to be a Karpathy-pattern wiki and explain what was expected
|
||||
- If successful, proceed. The script writes `scan-manifest.json` to `<TARGET_DIR>/.understand-anything/intermediate/`
|
||||
|
||||
3. Read the scan-manifest.json and announce the results:
|
||||
- "Detected Karpathy wiki: N articles, N sources, N topics, N wikilinks (N unresolved)"
|
||||
- List the categories found from index.md
|
||||
|
||||
### Phase 2: SCAN (already done)
|
||||
|
||||
The parse script in Phase 1 already performed the deterministic scan. The scan-manifest.json contains:
|
||||
- Article nodes (one per wiki .md file) with extracted wikilinks, headings, frontmatter
|
||||
- Source nodes (one per raw/ file)
|
||||
- Topic nodes (from index.md section headings)
|
||||
- `related` edges (from wikilinks)
|
||||
- `categorized_under` edges (from index.md sections)
|
||||
|
||||
No additional scanning is needed. Proceed to Phase 3.
|
||||
|
||||
### Phase 3: ANALYZE
|
||||
|
||||
Dispatch `article-analyzer` subagents to extract implicit knowledge:
|
||||
|
||||
1. Read the scan-manifest.json to get the article list
|
||||
|
||||
2. Prepare batches of 10-15 articles each, grouped by category when possible (articles in the same category are more likely to have implicit cross-references)
|
||||
|
||||
3. For each batch, dispatch an `article-analyzer` subagent with:
|
||||
- The batch of articles (id, name, summary, wikilinks, category, content from knowledgeMeta)
|
||||
- The full list of existing node IDs (so the agent can reference them)
|
||||
- The batch number for output file naming
|
||||
- The intermediate directory path: `$INTERMEDIATE_DIR = <TARGET_DIR>/.understand-anything/intermediate`
|
||||
|
||||
The agent will write `analysis-batch-{N}.json` to the intermediate directory.
|
||||
|
||||
4. Run up to 3 batches concurrently. Wait for all batches to complete.
|
||||
|
||||
5. If any batch fails, log a warning but continue — the scan-manifest provides a solid base graph even without LLM analysis.
|
||||
|
||||
### Phase 4: MERGE
|
||||
|
||||
1. Run the merge script bundled with this skill:
|
||||
```
|
||||
python3 <SKILL_DIR>/merge-knowledge-graph.py <TARGET_DIR>
|
||||
```
|
||||
|
||||
2. The script:
|
||||
- Combines scan-manifest.json + all analysis-batch-*.json files
|
||||
- Deduplicates entities (case-insensitive name matching)
|
||||
- Normalizes node/edge types via alias maps
|
||||
- Builds layers from index.md categories
|
||||
- Builds a tour from index.md section ordering
|
||||
- Writes `assembled-graph.json` to the intermediate directory
|
||||
|
||||
3. Read the merge report from stderr and announce:
|
||||
- Total nodes, edges, layers, tour steps
|
||||
- How many entities/claims the LLM analysis added
|
||||
|
||||
### Phase 5: SAVE
|
||||
|
||||
1. Read the assembled-graph.json
|
||||
|
||||
2. Run basic validation:
|
||||
- Every edge source/target must reference an existing node
|
||||
- Every node must have: id, type, name, summary, tags, complexity
|
||||
- Remove any edges with dangling references
|
||||
|
||||
3. Copy the validated graph to `<TARGET_DIR>/.understand-anything/knowledge-graph.json`
|
||||
|
||||
4. Write metadata to `<TARGET_DIR>/.understand-anything/meta.json`:
|
||||
```json
|
||||
{
|
||||
"lastAnalyzedAt": "<ISO timestamp>",
|
||||
"gitCommitHash": "<from git rev-parse HEAD or empty>",
|
||||
"version": "1.0.0",
|
||||
"analyzedFiles": <number of wiki articles>
|
||||
}
|
||||
```
|
||||
|
||||
5. Clean up intermediate files:
|
||||
```
|
||||
rm -rf <TARGET_DIR>/.understand-anything/intermediate
|
||||
```
|
||||
|
||||
6. Report summary to the user:
|
||||
- "Knowledge graph saved: N articles, N entities, N topics, N claims, N sources"
|
||||
- "N edges (N wikilink, N categorized, N implicit)"
|
||||
- "N layers, N tour steps"
|
||||
|
||||
7. Auto-trigger the dashboard:
|
||||
```
|
||||
/understand-dashboard <TARGET_DIR>
|
||||
```
|
||||
|
||||
## Notes
|
||||
|
||||
- The parse script handles ALL deterministic extraction (wikilinks, headings, frontmatter, categories from index.md). The LLM agents only add implicit knowledge that requires inference.
|
||||
- Categories and taxonomy come from index.md section headings, NOT from filename prefixes. The Karpathy spec is intentionally abstract about naming conventions.
|
||||
- The graph uses `kind: "knowledge"` to signal the dashboard to use force-directed layout instead of hierarchical dagre.
|
||||
- Source nodes from raw/ are lightweight (filename + size only) — we don't parse PDFs or binary files.
|
||||
@@ -0,0 +1,397 @@
|
||||
#!/usr/bin/env python3
|
||||
"""
|
||||
Merge script for Karpathy-pattern knowledge graphs.
|
||||
|
||||
Combines the deterministic scan-manifest.json with LLM analysis batches
|
||||
(analysis-batch-*.json) into a final assembled knowledge graph.
|
||||
|
||||
Handles: entity deduplication, edge normalization, layer building from
|
||||
index.md categories, tour generation from index.md section ordering.
|
||||
|
||||
Usage:
|
||||
python merge-knowledge-graph.py <wiki-directory>
|
||||
|
||||
Output:
|
||||
Writes assembled-graph.json to <wiki-directory>/.understand-anything/intermediate/
|
||||
"""
|
||||
|
||||
import json
|
||||
import os
|
||||
import re
|
||||
import sys
|
||||
from datetime import datetime, timezone
|
||||
from pathlib import Path
|
||||
|
||||
# ---------------------------------------------------------------------------
|
||||
# Canonical type sets (must match core/src/types.ts)
|
||||
# ---------------------------------------------------------------------------
|
||||
|
||||
VALID_NODE_TYPES = {
|
||||
"article", "entity", "topic", "claim", "source",
|
||||
# Codebase types (for cross-compatibility)
|
||||
"file", "function", "class", "module", "concept",
|
||||
"config", "document", "service", "table", "endpoint",
|
||||
"pipeline", "schema", "resource", "domain", "flow", "step",
|
||||
}
|
||||
|
||||
VALID_EDGE_TYPES = {
|
||||
"cites", "contradicts", "builds_on", "exemplifies",
|
||||
"categorized_under", "authored_by", "related", "similar_to",
|
||||
# Codebase types
|
||||
"imports", "exports", "contains", "inherits", "implements",
|
||||
"calls", "subscribes", "publishes", "middleware",
|
||||
"reads_from", "writes_to", "transforms", "validates",
|
||||
"depends_on", "tested_by", "configures",
|
||||
"deploys", "serves", "provisions", "triggers",
|
||||
"migrates", "documents", "routes", "defines_schema",
|
||||
"contains_flow", "flow_step", "cross_domain",
|
||||
}
|
||||
|
||||
NODE_TYPE_ALIASES = {
|
||||
"note": "article", "page": "article", "wiki_page": "article",
|
||||
"person": "entity", "actor": "entity", "organization": "entity",
|
||||
"tag": "topic", "category": "topic", "theme": "topic",
|
||||
"assertion": "claim", "decision": "claim", "thesis": "claim",
|
||||
"reference": "source", "raw": "source", "paper": "source",
|
||||
}
|
||||
|
||||
EDGE_TYPE_ALIASES = {
|
||||
"references": "cites", "cites_source": "cites",
|
||||
"conflicts_with": "contradicts", "disagrees_with": "contradicts",
|
||||
"refines": "builds_on", "elaborates": "builds_on",
|
||||
"illustrates": "exemplifies", "instance_of": "exemplifies", "example_of": "exemplifies",
|
||||
"belongs_to": "categorized_under", "tagged_with": "categorized_under",
|
||||
"written_by": "authored_by", "created_by": "authored_by",
|
||||
"relates_to": "related", "related_to": "related",
|
||||
}
|
||||
|
||||
|
||||
# ---------------------------------------------------------------------------
|
||||
# Normalization
|
||||
# ---------------------------------------------------------------------------
|
||||
|
||||
def normalize_node_type(t: str) -> str:
|
||||
t = t.lower().strip()
|
||||
return NODE_TYPE_ALIASES.get(t, t)
|
||||
|
||||
|
||||
def normalize_edge_type(t: str) -> str:
|
||||
t = t.lower().strip()
|
||||
return EDGE_TYPE_ALIASES.get(t, t)
|
||||
|
||||
|
||||
def normalize_entity_name(name: str) -> str:
|
||||
"""Normalize entity names for deduplication."""
|
||||
return re.sub(r'\s+', ' ', name.strip().lower())
|
||||
|
||||
|
||||
# ---------------------------------------------------------------------------
|
||||
# Merge pipeline
|
||||
# ---------------------------------------------------------------------------
|
||||
|
||||
def merge(root: Path) -> dict:
|
||||
intermediate = root / ".understand-anything" / "intermediate"
|
||||
manifest_path = intermediate / "scan-manifest.json"
|
||||
|
||||
if not manifest_path.is_file():
|
||||
print(f"Error: {manifest_path} not found. Run parse-knowledge-base.py first.",
|
||||
file=sys.stderr)
|
||||
sys.exit(1)
|
||||
|
||||
# Load scan manifest (deterministic base)
|
||||
manifest = json.loads(manifest_path.read_text(encoding="utf-8"))
|
||||
nodes = {n["id"]: n for n in manifest["nodes"]}
|
||||
edges = list(manifest["edges"])
|
||||
|
||||
report = {"base_nodes": len(nodes), "base_edges": len(edges),
|
||||
"batches": 0, "new_entities": 0, "new_claims": 0,
|
||||
"new_edges": 0, "deduped_entities": 0, "dropped_edges": 0}
|
||||
|
||||
# Load analysis batches
|
||||
batch_files = sorted(intermediate.glob("analysis-batch-*.json"))
|
||||
entity_name_map: dict[str, str] = {} # normalized_name → entity_id
|
||||
dedup_remap: dict[str, str] = {} # duplicate_id → canonical_id
|
||||
|
||||
for bf in batch_files:
|
||||
report["batches"] += 1
|
||||
try:
|
||||
batch = json.loads(bf.read_text(encoding="utf-8"))
|
||||
except (json.JSONDecodeError, OSError) as e:
|
||||
print(f"[merge] Warning: Failed to load {bf.name}: {e}", file=sys.stderr)
|
||||
continue
|
||||
|
||||
# Process new nodes from LLM analysis
|
||||
for node in batch.get("nodes", []):
|
||||
node_type = normalize_node_type(node.get("type", ""))
|
||||
if node_type not in VALID_NODE_TYPES:
|
||||
print(f"[merge] Warning: Unknown node type '{node.get('type')}' — skipping",
|
||||
file=sys.stderr)
|
||||
continue
|
||||
|
||||
node["type"] = node_type
|
||||
node_id = node.get("id", "")
|
||||
|
||||
# Entity deduplication — track remapping for edge fixup
|
||||
if node_type == "entity":
|
||||
norm_name = normalize_entity_name(node.get("name", ""))
|
||||
if norm_name in entity_name_map:
|
||||
# Map duplicate ID → canonical ID for edge remapping
|
||||
dedup_remap[node_id] = entity_name_map[norm_name]
|
||||
report["deduped_entities"] += 1
|
||||
continue
|
||||
entity_name_map[norm_name] = node_id
|
||||
report["new_entities"] += 1
|
||||
elif node_type == "claim":
|
||||
report["new_claims"] += 1
|
||||
|
||||
# Ensure required fields
|
||||
node.setdefault("summary", node.get("name", ""))
|
||||
node.setdefault("tags", [])
|
||||
node.setdefault("complexity", "simple")
|
||||
|
||||
nodes[node_id] = node
|
||||
|
||||
# Process new edges from LLM analysis
|
||||
for edge in batch.get("edges", []):
|
||||
edge_type = normalize_edge_type(edge.get("type", ""))
|
||||
if edge_type not in VALID_EDGE_TYPES:
|
||||
print(f"[merge] Warning: Unknown edge type '{edge.get('type')}' — "
|
||||
f"mapped to 'related'", file=sys.stderr)
|
||||
edge_type = "related"
|
||||
|
||||
edge["type"] = edge_type
|
||||
edge.setdefault("direction", "forward")
|
||||
edge.setdefault("weight", 0.5)
|
||||
|
||||
# Remap deduped entity IDs, then validate source/target exist
|
||||
src = dedup_remap.get(edge.get("source", ""), edge.get("source", ""))
|
||||
tgt = dedup_remap.get(edge.get("target", ""), edge.get("target", ""))
|
||||
edge["source"] = src
|
||||
edge["target"] = tgt
|
||||
if src in nodes and tgt in nodes:
|
||||
edges.append(edge)
|
||||
report["new_edges"] += 1
|
||||
else:
|
||||
report["dropped_edges"] += 1
|
||||
|
||||
# --- Deduplicate edges ---
|
||||
seen: set[tuple[str, str, str]] = set()
|
||||
final_edges = []
|
||||
for edge in edges:
|
||||
key = (edge["source"], edge["target"], edge["type"])
|
||||
if key not in seen:
|
||||
seen.add(key)
|
||||
final_edges.append(edge)
|
||||
|
||||
# --- Build article→layer map from categories ---
|
||||
categories = manifest.get("categories", [])
|
||||
article_layer_map: dict[str, str] = {} # article_id → layer_id
|
||||
layer_members: dict[str, list[str]] = {} # layer_id → [node_ids]
|
||||
|
||||
for cat in categories:
|
||||
cat_name = cat["name"]
|
||||
cat_slug = cat_name.lower().replace(" ", "-")
|
||||
layer_id = f"layer:{cat_slug}"
|
||||
topic_id = f"topic:{cat_slug}"
|
||||
members = [e["source"] for e in final_edges
|
||||
if e["type"] == "categorized_under" and e["target"] == topic_id]
|
||||
if topic_id in nodes:
|
||||
members.append(topic_id)
|
||||
layer_members[layer_id] = members
|
||||
for mid in members:
|
||||
article_layer_map[mid] = layer_id
|
||||
|
||||
# --- Assign entity/claim nodes to their parent article's layer ---
|
||||
# Step 1: Build entity/claim → article mapping from edges
|
||||
child_to_article: dict[str, str] = {}
|
||||
for edge in final_edges:
|
||||
src_type = nodes.get(edge["source"], {}).get("type", "")
|
||||
tgt_type = nodes.get(edge["target"], {}).get("type", "")
|
||||
# If an article connects to an entity/claim, map the child to the article
|
||||
if src_type == "article" and tgt_type in ("entity", "claim"):
|
||||
child_to_article.setdefault(edge["target"], edge["source"])
|
||||
elif tgt_type == "article" and src_type in ("entity", "claim"):
|
||||
child_to_article.setdefault(edge["source"], edge["target"])
|
||||
|
||||
# Step 2: For orphan entities/claims, try to match by ID prefix
|
||||
# Build a reverse lookup: bare article name → full article ID
|
||||
# e.g., "concept-aaak-compression" → "article:concepts/concept-aaak-compression"
|
||||
bare_to_article: dict[str, str] = {}
|
||||
for nid in nodes:
|
||||
if nid.startswith("article:"):
|
||||
# Extract the bare filename from paths like "article:concepts/concept-foo"
|
||||
bare = nid.split("/")[-1] if "/" in nid else nid.replace("article:", "")
|
||||
bare_to_article[bare] = nid
|
||||
|
||||
for nid, node in nodes.items():
|
||||
if node["type"] in ("entity", "claim") and nid not in child_to_article:
|
||||
# e.g., "claim:concept-aaak-compression:not-zero-loss" → stem "concept-aaak-compression"
|
||||
# e.g., "entity:brain" → stem "brain"
|
||||
raw = nid.split(":", 1)[1] if ":" in nid else nid # "concept-aaak-compression:not-zero-loss"
|
||||
stem = raw.split(":")[0] # "concept-aaak-compression"
|
||||
|
||||
# Try exact bare name match first
|
||||
if stem in bare_to_article:
|
||||
child_to_article[nid] = bare_to_article[stem]
|
||||
else:
|
||||
# Try suffix/substring match against bare names
|
||||
# e.g., entity:brain → segment-brain, entity:mempalace → tool-mempalace
|
||||
matched = False
|
||||
for bare, aid in bare_to_article.items():
|
||||
if stem in bare or bare in stem:
|
||||
child_to_article[nid] = aid
|
||||
matched = True
|
||||
break
|
||||
# Also try: bare ends with -stem (e.g., "segment-brain" ends with "-brain")
|
||||
if bare.endswith(f"-{stem}") or bare.endswith(f"/{stem}"):
|
||||
child_to_article[nid] = aid
|
||||
matched = True
|
||||
break
|
||||
# Last resort: check if the node's name appears in any article's
|
||||
# name OR content (knowledgeMeta.content)
|
||||
if not matched and node.get("name"):
|
||||
node_name_lower = node["name"].lower()
|
||||
for aid, anode in nodes.items():
|
||||
if not aid.startswith("article:"):
|
||||
continue
|
||||
# Match against article name
|
||||
if node_name_lower in anode.get("name", "").lower():
|
||||
child_to_article[nid] = aid
|
||||
matched = True
|
||||
break
|
||||
# Match against article content (wikilinks or text)
|
||||
meta = anode.get("knowledgeMeta", {})
|
||||
content = (meta.get("content") or "").lower()
|
||||
if len(node_name_lower) >= 3 and node_name_lower in content:
|
||||
child_to_article[nid] = aid
|
||||
matched = True
|
||||
break
|
||||
|
||||
# Step 3: Place children into their parent article's layer
|
||||
for child_id, article_id in child_to_article.items():
|
||||
layer_id = article_layer_map.get(article_id)
|
||||
if layer_id and layer_id in layer_members:
|
||||
layer_members[layer_id].append(child_id)
|
||||
article_layer_map[child_id] = layer_id
|
||||
|
||||
# --- Build layers ---
|
||||
layers = []
|
||||
for cat in categories:
|
||||
cat_name = cat["name"]
|
||||
cat_slug = cat_name.lower().replace(" ", "-")
|
||||
layer_id = f"layer:{cat_slug}"
|
||||
members = list(dict.fromkeys(layer_members.get(layer_id, []))) # Deduplicate preserving order
|
||||
layers.append({
|
||||
"id": layer_id,
|
||||
"name": cat_name,
|
||||
"description": f"{cat_name} ({len(members)} nodes)",
|
||||
"nodeIds": members,
|
||||
})
|
||||
|
||||
# Assign uncategorized nodes to an "Other" layer
|
||||
categorized_ids = set()
|
||||
for layer in layers:
|
||||
categorized_ids.update(layer["nodeIds"])
|
||||
uncategorized = [nid for nid in nodes if nid not in categorized_ids]
|
||||
if uncategorized:
|
||||
layers.append({
|
||||
"id": "layer:other",
|
||||
"name": "Other",
|
||||
"description": f"Uncategorized nodes ({len(uncategorized)})",
|
||||
"nodeIds": uncategorized,
|
||||
})
|
||||
|
||||
# --- Build tour from index.md category ordering ---
|
||||
tour = []
|
||||
for i, cat in enumerate(categories):
|
||||
cat_slug = cat["name"].lower().replace(" ", "-")
|
||||
topic_id = f"topic:{cat_slug}"
|
||||
# Pick representative articles (up to 3 per category)
|
||||
members = [e["source"] for e in final_edges
|
||||
if e["type"] == "categorized_under" and e["target"] == topic_id][:3]
|
||||
if not members and topic_id in nodes:
|
||||
members = [topic_id]
|
||||
if members:
|
||||
tour.append({
|
||||
"order": i + 1,
|
||||
"title": cat["name"],
|
||||
"description": f"Explore the {cat['name']} section ({cat['count']} articles)",
|
||||
"nodeIds": members,
|
||||
})
|
||||
|
||||
# --- Detect project name ---
|
||||
project_name = root.name
|
||||
# Try to find a better name from index.md H1
|
||||
index_path = root / "wiki" / "index.md"
|
||||
if not index_path.is_file():
|
||||
index_path = root / "index.md"
|
||||
if index_path.is_file():
|
||||
text = index_path.read_text(encoding="utf-8", errors="replace")
|
||||
h1_match = re.search(r"^#\s+(.+)$", text, re.MULTILINE)
|
||||
if h1_match:
|
||||
project_name = h1_match.group(1).strip()
|
||||
|
||||
# --- Assemble final graph ---
|
||||
graph = {
|
||||
"version": "1.0.0",
|
||||
"kind": "knowledge",
|
||||
"project": {
|
||||
"name": project_name,
|
||||
"languages": ["markdown"],
|
||||
"frameworks": ["karpathy-wiki"],
|
||||
"description": f"Knowledge graph for {project_name}",
|
||||
"analyzedAt": datetime.now(timezone.utc).isoformat(),
|
||||
"gitCommitHash": "",
|
||||
},
|
||||
"nodes": list(nodes.values()),
|
||||
"edges": final_edges,
|
||||
"layers": layers,
|
||||
"tour": tour,
|
||||
}
|
||||
|
||||
# Try to get git commit hash
|
||||
try:
|
||||
import subprocess
|
||||
result = subprocess.run(
|
||||
["git", "rev-parse", "HEAD"],
|
||||
capture_output=True, text=True, cwd=str(root), timeout=5
|
||||
)
|
||||
if result.returncode == 0:
|
||||
graph["project"]["gitCommitHash"] = result.stdout.strip()
|
||||
except (OSError, subprocess.TimeoutExpired):
|
||||
pass
|
||||
|
||||
# Write output
|
||||
out_path = intermediate / "assembled-graph.json"
|
||||
out_path.write_text(json.dumps(graph, indent=2), encoding="utf-8")
|
||||
|
||||
# Report
|
||||
print(f"[merge] Input: {report['base_nodes']} scan nodes, "
|
||||
f"{report['base_edges']} scan edges, {report['batches']} analysis batches",
|
||||
file=sys.stderr)
|
||||
print(f"[merge] Added: {report['new_entities']} entities, "
|
||||
f"{report['new_claims']} claims, {report['new_edges']} edges "
|
||||
f"({report['deduped_entities']} deduped entities, "
|
||||
f"{report['dropped_edges']} dropped dangling edges)", file=sys.stderr)
|
||||
print(f"[merge] Output: {len(graph['nodes'])} nodes, {len(final_edges)} edges, "
|
||||
f"{len(layers)} layers, {len(tour)} tour steps", file=sys.stderr)
|
||||
print(f"[merge] Written: {out_path}", file=sys.stderr)
|
||||
|
||||
return graph
|
||||
|
||||
|
||||
def main():
|
||||
if len(sys.argv) < 2:
|
||||
print("Usage: merge-knowledge-graph.py <wiki-directory>", file=sys.stderr)
|
||||
sys.exit(1)
|
||||
|
||||
root = Path(sys.argv[1]).resolve()
|
||||
if not root.is_dir():
|
||||
print(f"Error: {root} is not a directory", file=sys.stderr)
|
||||
sys.exit(1)
|
||||
|
||||
merge(root)
|
||||
|
||||
|
||||
if __name__ == "__main__":
|
||||
main()
|
||||
@@ -0,0 +1,492 @@
|
||||
#!/usr/bin/env python3
|
||||
"""
|
||||
Deterministic parser for Karpathy-pattern LLM wikis.
|
||||
|
||||
Detects the three-layer pattern (raw sources + wiki markdown + schema),
|
||||
extracts structure from markdown files, resolves wikilinks, and derives
|
||||
categories from index.md section headings.
|
||||
|
||||
Usage:
|
||||
python parse-knowledge-base.py <wiki-directory>
|
||||
|
||||
Output:
|
||||
Writes scan-manifest.json to <wiki-directory>/.understand-anything/intermediate/
|
||||
"""
|
||||
|
||||
import json
|
||||
import os
|
||||
import re
|
||||
import sys
|
||||
from pathlib import Path
|
||||
|
||||
# ---------------------------------------------------------------------------
|
||||
# Regex patterns
|
||||
# ---------------------------------------------------------------------------
|
||||
WIKILINK_RE = re.compile(r"\[\[([^\]|]+)(?:\|([^\]]+))?\]\]")
|
||||
FRONTMATTER_RE = re.compile(r"^---\s*\n(.*?)\n---\s*\n", re.DOTALL)
|
||||
CODE_BLOCK_RE = re.compile(r"```(\w*)")
|
||||
HEADING_RE = re.compile(r"^(#{1,6})\s+(.+)$", re.MULTILINE)
|
||||
INDEX_SECTION_RE = re.compile(r"^##\s+(.+)$", re.MULTILINE)
|
||||
|
||||
# Files that are part of wiki infrastructure, not content articles
|
||||
INFRA_FILES = {"index.md", "log.md", "claude.md", "agents.md", "soul.md"}
|
||||
|
||||
# ---------------------------------------------------------------------------
|
||||
# Detection: is this a Karpathy-pattern wiki?
|
||||
# ---------------------------------------------------------------------------
|
||||
|
||||
def detect_format(root: Path) -> dict:
|
||||
"""Detect if directory follows the Karpathy LLM wiki three-layer pattern."""
|
||||
signals = {
|
||||
"has_index": (root / "index.md").is_file() or (root / "wiki" / "index.md").is_file(),
|
||||
"has_log": (root / "log.md").is_file() or (root / "wiki" / "log.md").is_file(),
|
||||
"has_raw": (root / "raw").is_dir(),
|
||||
"has_schema": any(
|
||||
(root / f).is_file() or (root / "wiki" / f).is_file()
|
||||
for f in ["CLAUDE.md", "AGENTS.md"]
|
||||
),
|
||||
}
|
||||
|
||||
# Find the wiki root — could be the directory itself or a wiki/ subdirectory
|
||||
if (root / "wiki").is_dir():
|
||||
wiki_root = root / "wiki"
|
||||
else:
|
||||
wiki_root = root
|
||||
|
||||
# Count markdown files in the wiki root
|
||||
md_files = list(wiki_root.rglob("*.md"))
|
||||
signals["md_count"] = len(md_files)
|
||||
signals["wiki_root"] = str(wiki_root)
|
||||
|
||||
# Primary signal: has index.md + meaningful number of markdown files
|
||||
if signals["has_index"] and signals["md_count"] >= 3:
|
||||
signals["detected"] = True
|
||||
signals["format"] = "karpathy"
|
||||
else:
|
||||
signals["detected"] = False
|
||||
signals["format"] = "unknown"
|
||||
|
||||
return signals
|
||||
|
||||
|
||||
# ---------------------------------------------------------------------------
|
||||
# Markdown extraction helpers
|
||||
# ---------------------------------------------------------------------------
|
||||
|
||||
def extract_frontmatter(text: str) -> dict:
|
||||
"""Extract YAML frontmatter as a simple key-value dict."""
|
||||
m = FRONTMATTER_RE.match(text)
|
||||
if not m:
|
||||
return {}
|
||||
fm = {}
|
||||
for line in m.group(1).split("\n"):
|
||||
if ":" in line:
|
||||
key, _, val = line.partition(":")
|
||||
fm[key.strip()] = val.strip().strip('"').strip("'")
|
||||
return fm
|
||||
|
||||
|
||||
def extract_wikilinks(text: str) -> list[dict]:
|
||||
"""Extract all [[target]] and [[target|display]] wikilinks."""
|
||||
links = []
|
||||
for m in WIKILINK_RE.finditer(text):
|
||||
links.append({
|
||||
"target": m.group(1).strip(),
|
||||
"display": m.group(2).strip() if m.group(2) else None,
|
||||
})
|
||||
return links
|
||||
|
||||
|
||||
def extract_headings(text: str) -> list[dict]:
|
||||
"""Extract all markdown headings with level and text."""
|
||||
return [
|
||||
{"level": len(m.group(1)), "text": m.group(2).strip()}
|
||||
for m in HEADING_RE.finditer(text)
|
||||
]
|
||||
|
||||
|
||||
def extract_code_blocks(text: str) -> list[str]:
|
||||
"""Extract languages from fenced code blocks."""
|
||||
return [m.group(1) for m in CODE_BLOCK_RE.finditer(text) if m.group(1)]
|
||||
|
||||
|
||||
def extract_first_paragraph(text: str) -> str:
|
||||
"""Extract the first non-empty paragraph after frontmatter and H1."""
|
||||
# Strip frontmatter
|
||||
stripped = FRONTMATTER_RE.sub("", text).strip()
|
||||
if not stripped:
|
||||
return ""
|
||||
lines = stripped.split("\n")
|
||||
|
||||
def _collect_paragraph(start_lines: list[str]) -> str:
|
||||
"""Collect the first paragraph from the given lines."""
|
||||
para: list[str] = []
|
||||
for s_raw in start_lines:
|
||||
s = s_raw.strip()
|
||||
if not s and not para:
|
||||
continue # Skip leading blank lines
|
||||
if not s and para:
|
||||
break # End of paragraph
|
||||
if s.startswith(">"):
|
||||
continue # Skip blockquotes
|
||||
if re.match(r"^[-*_]{3,}\s*$", s):
|
||||
continue # Skip horizontal rules
|
||||
if s.startswith("#"):
|
||||
if para:
|
||||
break # End paragraph at next heading
|
||||
continue # Skip headings before paragraph
|
||||
para.append(s)
|
||||
return " ".join(para)
|
||||
|
||||
# Try: find first paragraph after H1
|
||||
for i, line in enumerate(lines):
|
||||
if line.strip().startswith("# "):
|
||||
result = _collect_paragraph(lines[i + 1:])
|
||||
if result:
|
||||
if len(result) > 200:
|
||||
return result[:197] + "..."
|
||||
return result
|
||||
|
||||
# Fallback: no H1 found, take first paragraph from start
|
||||
result = _collect_paragraph(lines)
|
||||
if len(result) > 200:
|
||||
result = result[:197] + "..."
|
||||
return result or ""
|
||||
|
||||
|
||||
def extract_h1(text: str) -> str:
|
||||
"""Extract the first H1 heading."""
|
||||
for m in HEADING_RE.finditer(text):
|
||||
if len(m.group(1)) == 1:
|
||||
# Strip trailing wiki-style decorations like " — subtitle"
|
||||
return m.group(2).strip()
|
||||
return ""
|
||||
|
||||
|
||||
# ---------------------------------------------------------------------------
|
||||
# Index.md parsing — categories come from section headings
|
||||
# ---------------------------------------------------------------------------
|
||||
|
||||
def parse_index(index_path: Path) -> list[dict]:
|
||||
"""Parse index.md to extract categories from ## headings and their wikilinks."""
|
||||
if not index_path.is_file():
|
||||
return []
|
||||
text = index_path.read_text(encoding="utf-8", errors="replace")
|
||||
categories = []
|
||||
current_category = None
|
||||
|
||||
for line in text.split("\n"):
|
||||
# Detect ## section heading
|
||||
sec_match = re.match(r"^##\s+(.+)$", line)
|
||||
if sec_match:
|
||||
current_category = {
|
||||
"name": sec_match.group(1).strip(),
|
||||
"articles": [],
|
||||
}
|
||||
categories.append(current_category)
|
||||
continue
|
||||
|
||||
# Collect wikilinks under current section
|
||||
if current_category:
|
||||
for wl in WIKILINK_RE.finditer(line):
|
||||
current_category["articles"].append(wl.group(1).strip())
|
||||
|
||||
return categories
|
||||
|
||||
|
||||
# ---------------------------------------------------------------------------
|
||||
# Log.md parsing — extract operation timeline
|
||||
# ---------------------------------------------------------------------------
|
||||
|
||||
def parse_log(log_path: Path) -> list[dict]:
|
||||
"""Parse log.md to extract chronological entries."""
|
||||
if not log_path.is_file():
|
||||
return []
|
||||
text = log_path.read_text(encoding="utf-8", errors="replace")
|
||||
entries = []
|
||||
log_entry_re = re.compile(
|
||||
r"^##\s+\[(\d{4}-\d{2}-\d{2})\]\s+(\w+)\s*\|\s*(.+)$", re.MULTILINE
|
||||
)
|
||||
for m in log_entry_re.finditer(text):
|
||||
entries.append({
|
||||
"date": m.group(1),
|
||||
"operation": m.group(2),
|
||||
"title": m.group(3).strip(),
|
||||
})
|
||||
return entries
|
||||
|
||||
|
||||
# ---------------------------------------------------------------------------
|
||||
# Main pipeline
|
||||
# ---------------------------------------------------------------------------
|
||||
|
||||
def build_name_to_stem_map(wiki_root: Path) -> dict[str, str]:
|
||||
"""Build a case-insensitive map from filename stem to relative stem path."""
|
||||
name_map: dict[str, str] = {}
|
||||
for md_file in wiki_root.rglob("*.md"):
|
||||
rel = md_file.relative_to(wiki_root)
|
||||
stem = str(rel.with_suffix("")) # e.g., "decisions/decision-foo"
|
||||
basename = md_file.stem # e.g., "decision-foo"
|
||||
# Map both full relative path and bare filename (for flat wikilink resolution)
|
||||
name_map[stem.lower()] = stem
|
||||
name_map[basename.lower()] = stem
|
||||
return name_map
|
||||
|
||||
|
||||
def resolve_wikilink(target: str, name_map: dict[str, str], node_ids: set[str] | None = None) -> str | None:
|
||||
"""Resolve a wikilink target to an article node ID.
|
||||
|
||||
If node_ids is provided, only resolve to IDs that exist in the set.
|
||||
"""
|
||||
key = target.lower().strip()
|
||||
# Skip targets that are clearly not page names (shell flags, etc.)
|
||||
if key.startswith("-"):
|
||||
return None
|
||||
stem = name_map.get(key)
|
||||
if stem:
|
||||
candidate = f"article:{stem}"
|
||||
# If we have a node set, verify the target exists
|
||||
if node_ids is not None and candidate not in node_ids:
|
||||
return None
|
||||
return candidate
|
||||
# Try without directory prefix
|
||||
for stored_key, stored_stem in name_map.items():
|
||||
if stored_key.endswith("/" + key) or stored_key == key:
|
||||
candidate = f"article:{stored_stem}"
|
||||
if node_ids is not None and candidate not in node_ids:
|
||||
return None
|
||||
return candidate
|
||||
return None
|
||||
|
||||
|
||||
def parse_wiki(root: Path) -> dict:
|
||||
"""Parse a Karpathy-pattern wiki and produce the scan manifest."""
|
||||
detection = detect_format(root)
|
||||
if not detection["detected"]:
|
||||
print(json.dumps({"error": "Not a Karpathy-pattern wiki", "detection": detection}),
|
||||
file=sys.stderr)
|
||||
sys.exit(1)
|
||||
|
||||
wiki_root = Path(detection["wiki_root"])
|
||||
raw_root = root / "raw"
|
||||
|
||||
# Build name resolution map
|
||||
name_map = build_name_to_stem_map(wiki_root)
|
||||
|
||||
# Find index.md and log.md
|
||||
index_path = wiki_root / "index.md"
|
||||
if not index_path.is_file():
|
||||
index_path = root / "index.md"
|
||||
log_path = wiki_root / "log.md"
|
||||
if not log_path.is_file():
|
||||
log_path = root / "log.md"
|
||||
|
||||
# Parse index for categories
|
||||
categories = parse_index(index_path)
|
||||
log_entries = parse_log(log_path)
|
||||
|
||||
# Build category lookup: wikilink target → category name
|
||||
category_lookup: dict[str, str] = {}
|
||||
for cat in categories:
|
||||
for article_target in cat["articles"]:
|
||||
category_lookup[article_target.lower()] = cat["name"]
|
||||
|
||||
# --- Pre-compute article IDs (for edge resolution validation) ---
|
||||
# Must use the same filter logic as the main loop (skip if EITHER matches INFRA_FILES)
|
||||
article_ids: set[str] = set()
|
||||
for md_file in sorted(wiki_root.rglob("*.md")):
|
||||
rel = md_file.relative_to(wiki_root)
|
||||
stem = str(rel.with_suffix(""))
|
||||
basename = md_file.stem
|
||||
if basename.lower() in INFRA_FILES or rel.name.lower() in INFRA_FILES:
|
||||
continue
|
||||
article_ids.add(f"article:{stem}")
|
||||
|
||||
# --- Build article nodes ---
|
||||
nodes = []
|
||||
edges = []
|
||||
warnings = []
|
||||
stats = {"articles": 0, "sources": 0, "topics": 0, "wikilinks": 0, "unresolved": 0}
|
||||
|
||||
for md_file in sorted(wiki_root.rglob("*.md")):
|
||||
rel = md_file.relative_to(wiki_root)
|
||||
stem = str(rel.with_suffix(""))
|
||||
basename = md_file.stem
|
||||
|
||||
# Skip infrastructure files
|
||||
if basename.lower() in INFRA_FILES or rel.name.lower() in INFRA_FILES:
|
||||
continue
|
||||
|
||||
text = md_file.read_text(encoding="utf-8", errors="replace")
|
||||
h1 = extract_h1(text)
|
||||
frontmatter = extract_frontmatter(text)
|
||||
wikilinks = extract_wikilinks(text)
|
||||
headings = extract_headings(text)
|
||||
code_langs = extract_code_blocks(text)
|
||||
summary = extract_first_paragraph(text)
|
||||
line_count = text.count("\n") + 1
|
||||
word_count = len(text.split())
|
||||
|
||||
# Derive category from index.md lookup
|
||||
category = category_lookup.get(basename.lower(), "")
|
||||
if not category:
|
||||
# Try stem match
|
||||
category = category_lookup.get(stem.lower(), "")
|
||||
|
||||
# Derive tags (deduplicated)
|
||||
tag_set: set[str] = set()
|
||||
if category:
|
||||
tag_set.add(category.lower())
|
||||
if rel.parent != Path("."):
|
||||
tag_set.add(str(rel.parent))
|
||||
fm_tags = frontmatter.get("tags", "")
|
||||
if fm_tags:
|
||||
tag_set.update(t.strip() for t in fm_tags.split(",") if t.strip())
|
||||
tags = sorted(tag_set)
|
||||
|
||||
# Complexity from wikilink density
|
||||
wl_count = len(wikilinks)
|
||||
if wl_count > 15:
|
||||
complexity = "complex"
|
||||
elif wl_count > 5:
|
||||
complexity = "moderate"
|
||||
else:
|
||||
complexity = "simple"
|
||||
|
||||
node_id = f"article:{stem}"
|
||||
nodes.append({
|
||||
"id": node_id,
|
||||
"type": "article",
|
||||
"name": h1 or basename,
|
||||
"filePath": str(rel),
|
||||
"summary": summary or f"Wiki article: {h1 or basename}",
|
||||
"tags": tags,
|
||||
"complexity": complexity,
|
||||
"knowledgeMeta": {
|
||||
"wikilinks": [wl["target"] for wl in wikilinks],
|
||||
"category": category or None,
|
||||
"content": text[:3000], # First 3000 chars for LLM analysis
|
||||
},
|
||||
})
|
||||
stats["articles"] += 1
|
||||
stats["wikilinks"] += wl_count
|
||||
|
||||
# Build edges from wikilinks (resolve against known article IDs)
|
||||
for wl in wikilinks:
|
||||
target_id = resolve_wikilink(wl["target"], name_map, article_ids)
|
||||
if target_id and target_id != node_id:
|
||||
edges.append({
|
||||
"source": node_id,
|
||||
"target": target_id,
|
||||
"type": "related",
|
||||
"direction": "forward",
|
||||
"weight": 0.7,
|
||||
})
|
||||
elif not target_id:
|
||||
warnings.append(f"Unresolved wikilink: [[{wl['target']}]] in {rel}")
|
||||
stats["unresolved"] += 1
|
||||
|
||||
# --- Build topic nodes from index.md categories ---
|
||||
for cat in categories:
|
||||
topic_id = f"topic:{cat['name'].lower().replace(' ', '-')}"
|
||||
nodes.append({
|
||||
"id": topic_id,
|
||||
"type": "topic",
|
||||
"name": cat["name"],
|
||||
"summary": f"Category from index: {cat['name']} ({len(cat['articles'])} articles)",
|
||||
"tags": ["category"],
|
||||
"complexity": "simple",
|
||||
})
|
||||
stats["topics"] += 1
|
||||
|
||||
# categorized_under edges (only resolve to known article nodes)
|
||||
for article_target in cat["articles"]:
|
||||
article_id = resolve_wikilink(article_target, name_map, article_ids)
|
||||
if article_id:
|
||||
edges.append({
|
||||
"source": article_id,
|
||||
"target": topic_id,
|
||||
"type": "categorized_under",
|
||||
"direction": "forward",
|
||||
"weight": 0.6,
|
||||
})
|
||||
|
||||
# --- Build source nodes from raw/ ---
|
||||
if raw_root.is_dir():
|
||||
for raw_file in sorted(raw_root.rglob("*")):
|
||||
if raw_file.is_file() and not raw_file.name.startswith("."):
|
||||
rel_raw = raw_file.relative_to(root)
|
||||
ext = raw_file.suffix.lower()
|
||||
size_kb = raw_file.stat().st_size / 1024
|
||||
source_id = f"source:{raw_file.relative_to(raw_root).with_suffix('')}"
|
||||
nodes.append({
|
||||
"id": source_id,
|
||||
"type": "source",
|
||||
"name": raw_file.name,
|
||||
"filePath": str(rel_raw),
|
||||
"summary": f"Raw source ({ext or 'unknown'}, {size_kb:.0f} KB)",
|
||||
"tags": ["raw", ext.lstrip(".") or "unknown"],
|
||||
"complexity": "simple",
|
||||
})
|
||||
stats["sources"] += 1
|
||||
|
||||
# --- Compute backlinks ---
|
||||
backlink_map: dict[str, list[str]] = {}
|
||||
for edge in edges:
|
||||
if edge["type"] == "related":
|
||||
target = edge["target"]
|
||||
source = edge["source"]
|
||||
backlink_map.setdefault(target, []).append(source)
|
||||
for node in nodes:
|
||||
if node["type"] == "article" and "knowledgeMeta" in node:
|
||||
bl = backlink_map.get(node["id"], [])
|
||||
node["knowledgeMeta"]["backlinks"] = bl
|
||||
|
||||
# --- Deduplicate edges ---
|
||||
seen_edges: set[tuple[str, str, str]] = set()
|
||||
deduped_edges = []
|
||||
for edge in edges:
|
||||
key = (edge["source"], edge["target"], edge["type"])
|
||||
if key not in seen_edges:
|
||||
seen_edges.add(key)
|
||||
deduped_edges.append(edge)
|
||||
|
||||
return {
|
||||
"format": "karpathy",
|
||||
"stats": stats,
|
||||
"categories": [{"name": c["name"], "count": len(c["articles"])} for c in categories],
|
||||
"logEntries": len(log_entries),
|
||||
"nodes": nodes,
|
||||
"edges": deduped_edges,
|
||||
"warnings": warnings[:50], # Cap warnings
|
||||
}
|
||||
|
||||
|
||||
def main():
|
||||
if len(sys.argv) < 2:
|
||||
print("Usage: parse-knowledge-base.py <wiki-directory>", file=sys.stderr)
|
||||
sys.exit(1)
|
||||
|
||||
root = Path(sys.argv[1]).resolve()
|
||||
if not root.is_dir():
|
||||
print(f"Error: {root} is not a directory", file=sys.stderr)
|
||||
sys.exit(1)
|
||||
|
||||
manifest = parse_wiki(root)
|
||||
|
||||
# Write output
|
||||
out_dir = root / ".understand-anything" / "intermediate"
|
||||
out_dir.mkdir(parents=True, exist_ok=True)
|
||||
out_path = out_dir / "scan-manifest.json"
|
||||
out_path.write_text(json.dumps(manifest, indent=2), encoding="utf-8")
|
||||
|
||||
# Report to stderr
|
||||
s = manifest["stats"]
|
||||
print(f"[parse] Karpathy wiki: {s['articles']} articles, {s['sources']} sources, "
|
||||
f"{s['topics']} topics, {s['wikilinks']} wikilinks "
|
||||
f"({s['unresolved']} unresolved)", file=sys.stderr)
|
||||
print(f"[parse] Output: {out_path}", file=sys.stderr)
|
||||
|
||||
|
||||
if __name__ == "__main__":
|
||||
main()
|
||||
Reference in New Issue
Block a user