ktx/docs-site/lib/llm-docs.ts

161 lines
5.5 KiB
TypeScript
Raw Permalink Normal View History

import { source } from "@/lib/source";
feat: merge ingest and scan * docs: add CLI component reuse guidance * docs: add unified ingest ux design * Refine unified ingest UX design after adversarial review iteration 1 * Refine unified ingest UX design after adversarial review iteration 2 * Refine unified ingest UX design after adversarial review iteration 3 * feat(cli): route public connection ingest command * feat(cli): hide standalone scan from public help * feat(cli): plan public ingest depth and query history * feat(cli): execute public database ingest facets * feat(ingest): read connection query history config * fix(cli): use public ingest wording * fix(config): stop generating ingest adapter allow lists * docs: document public ingest command * test: align ingest surface expectations * docs: add unified ingest public CLI surface plan * feat(cli): preflight deep public ingest readiness * feat(setup): store query history in connection context * feat(setup): store database context depth * feat(setup): verify context readiness by database depth * fix(setup): keep context build foreground only * fix(config): reject reserved ingest connection ids * test: close unified ingest v1 expectations * docs: add unified ingest v1 closure plan * fix(ingest): bypass adapter allow-list for public source ingest * fix(ingest): honor query history window intent * fix(ingest): hide scan internals from public database ingest * feat(ingest): use foreground view for interactive public ingest * fix(setup): use schema context and query history wording * test(cli): verify unified ingest public output * docs: add unified ingest v1 public output closure plan * fix(setup): forward query history flags * fix(setup): prompt for postgres query history * fix(status): report query history readiness * fix(ingest): remove legacy public guidance * fix(ingest): polish foreground retry copy * docs(examples): use unified query history wording * chore(ingest): finish public query history cleanup * docs: add unified ingest v1 query history status cleanup plan * test(docs): cover unified ingest public docs * docs: align ingest CLI reference with unified UX * docs: update context build guides for unified ingest * docs: update setup and primary source ingest wording * docs: stop advertising adapter-backed example ingest * docs: close unified ingest public docs gaps * docs: add unified ingest v1 docs site closure plan * fix: render unified ingest foreground warnings * fix: explain query history schema order * fix: add public ingest retry guidance * fix: align setup next steps with unified ingest * fix: remove scan wording from demo progress * test: verify unified ingest ux closure * docs: add unified ingest v1 foreground and retry closure plan * fix(cli): preserve query-history pull config in public ingest * fix(cli): omit hidden commands from docs command tree * test(cli): close unified ingest final public surface checks * docs: add unified ingest v1 final public surface closure plan * fix(cli): use public source labels in ingest reports * fix(cli): suppress low-level public ingest output * test(cli): verify unified ingest public plain output * docs: add unified ingest v1 public plain output closure plan * fix(cli): add public ingest copy sanitizers * fix(cli): sanitize public ingest progress copy * fix(cli): rename setup schema scope prompt * docs(plan): add progress copy closure; test: align setup back-nav fixture Adds the iter9 plan and updates the setup back-navigation test fixture to pass disableQueryHistory plus listSchemas/listTables stubs that the unified ingest setup step now requires. * docs(plan): add final ux labels plan with narrowed label scans * fix(cli): aggregate unsupported query-history warnings * fix(cli): align setup database labels * test(cli): fix setup database test type-check * fix(cli): remove primary-source wording from setup output * test(cli): verify unified ingest setup closure * docs(plan): add unified ingest v1 verification copy closure plan * fix(cli): remove top-level scan command * fix(cli): remove legacy ingest and wiki commands * Merge scan into ingest flow * feat(cli): split ingest progress into per-phase rows, rename work units to tasks Each database target in the unified ingest dashboard now renders one row per real subprocess (Schema, then Query history when enabled) instead of a single combined bar. Each phase has its own monotonic 0-100% bar so the progress never snaps back to zero when historic-sql starts after scan completes. Completed phases keep their final bar, summary, and elapsed time visible as an inline audit trail; queued and skipped phases are shown explicitly. Also rename user-facing "work units" / "Failed work units" to "tasks" / "Failed tasks" in ingest output and parseIngestSummary. The parser still accepts the legacy "Work units:" wording in captured output for backward compat. Internal memory-flow event names and type fields are left alone. * Fix test harness failures * Fix CI smoke checks --------- Co-authored-by: Andrey Avtomonov <7889985+andreybavt@users.noreply.github.com>
2026-05-14 01:43:06 +02:00
import { readDocsPageMarkdown } from "@/lib/docs-markdown";
const siteOrigin = "https://docs.kaelio.com/ktx";
export type LlmDocsPage = {
title: string;
description?: string;
url: string;
markdownUrl: string;
slug: string[];
getMarkdown: () => Promise<string>;
};
export function getLlmDocsPages(): LlmDocsPage[] {
return source.getPages().map(toLlmDocsPage);
}
export function getLlmDocsPage(slug: string[] | undefined) {
const page = source.getPage(slug);
return page ? toLlmDocsPage(page) : null;
}
export async function getPageMarkdown(page: LlmDocsPage) {
const description = page.description ? `\n\n> ${page.description}` : "";
const body = await page.getMarkdown();
return normalizeMarkdown(`# ${page.title}${description}
Canonical URL: ${absoluteUrl(page.url)}
Markdown URL: ${absoluteUrl(page.markdownUrl)}
${body}
`);
}
export function buildLlmsTxt() {
const pages = getLlmDocsPages();
const byUrl = new Map(pages.map((page) => [page.url, page]));
const link = (url: string, label: string, fallbackDescription: string) => {
const page = byUrl.get(url);
const description = page?.description ?? fallbackDescription;
const markdownUrl = page?.markdownUrl ?? `${url}.md`;
return `- [${label}](${absoluteUrl(markdownUrl)}): ${description}`;
};
return `# KTX
> Agent-native context layer for analytics engineering and database agents.
KTX provides semantic-layer files, warehouse scans, wiki pages, provenance, and agent-facing tools that help coding agents answer analytics questions without inventing metrics or joins.
## Agent Entry Points
${link("/docs/ai-resources", "AI Resources", "Machine-readable docs, prompt recipes, and agent setup paths")}
${link("/docs/ai-resources/agent-quickstart", "Agent Quickstart", "Task-first route for coding assistants using KTX")}
${link("/docs/ai-resources/markdown-access", "Markdown Access", "Fetch KTX docs as llms.txt, llms-full.txt, or per-page Markdown")}
${link("/docs/ai-resources/agent-instructions", "Agent Instructions", "Suggested instructions for coding assistants that need to read and cite KTX docs")}
## Start Here
${link("/docs/getting-started/introduction", "Introduction", "What KTX is and who it is for")}
${link("/docs/getting-started/quickstart", "Quickstart", "Set up KTX and build your first context")}
${link("/docs/guides/writing-context", "Writing Context", "Write semantic sources and wiki pages")}
## Machine-Readable Documentation
- [Full documentation](${absoluteUrl("/llms-full.txt")}): All docs pages in one plain-text markdown response
- [Markdown access guide](${absoluteUrl("/docs/ai-resources/markdown-access.md")}): How to fetch llms.txt, llms-full.txt, and per-page Markdown
- [Quickstart markdown](${absoluteUrl("/docs/getting-started/quickstart.md")}): Human setup walkthrough
- [Semantic-layer CLI markdown](${absoluteUrl("/docs/cli-reference/ktx-sl.md")}): Semantic-layer commands and JSON output
- [Wiki CLI markdown](${absoluteUrl("/docs/cli-reference/ktx-wiki.md")}): Wiki page commands and JSON output
## CLI Reference
${link("/docs/cli-reference/ktx-setup", "ktx setup", "Interactive project setup")}
${link("/docs/cli-reference/ktx-sl", "ktx sl", "Semantic-layer commands")}
${link("/docs/cli-reference/ktx-wiki", "ktx wiki", "Wiki page commands")}
${link("/docs/cli-reference/ktx-connection", "ktx connection", "Connection management commands")}
## Integrations
${link("/docs/integrations/primary-sources", "Primary Sources", "Connect KTX to databases and warehouses")}
${link("/docs/integrations/context-sources", "Context Sources", "Ingest dbt, LookML, Metabase, Looker, MetricFlow, and Notion")}
## All Documentation
${buildPageIndex(pages)}
`;
}
export async function buildLlmsFullTxt() {
const rendered = await Promise.all(getLlmDocsPages().map(getPageMarkdown));
return [`# KTX Full Documentation`, `Source: ${siteOrigin}`, ...rendered].join(
"\n\n---\n\n",
);
}
function toLlmDocsPage(page: ReturnType<typeof source.getPages>[number]) {
return {
title: page.data.title,
description: page.data.description,
url: page.url,
markdownUrl: `${page.url}.md`,
slug: page.slugs,
feat: merge ingest and scan * docs: add CLI component reuse guidance * docs: add unified ingest ux design * Refine unified ingest UX design after adversarial review iteration 1 * Refine unified ingest UX design after adversarial review iteration 2 * Refine unified ingest UX design after adversarial review iteration 3 * feat(cli): route public connection ingest command * feat(cli): hide standalone scan from public help * feat(cli): plan public ingest depth and query history * feat(cli): execute public database ingest facets * feat(ingest): read connection query history config * fix(cli): use public ingest wording * fix(config): stop generating ingest adapter allow lists * docs: document public ingest command * test: align ingest surface expectations * docs: add unified ingest public CLI surface plan * feat(cli): preflight deep public ingest readiness * feat(setup): store query history in connection context * feat(setup): store database context depth * feat(setup): verify context readiness by database depth * fix(setup): keep context build foreground only * fix(config): reject reserved ingest connection ids * test: close unified ingest v1 expectations * docs: add unified ingest v1 closure plan * fix(ingest): bypass adapter allow-list for public source ingest * fix(ingest): honor query history window intent * fix(ingest): hide scan internals from public database ingest * feat(ingest): use foreground view for interactive public ingest * fix(setup): use schema context and query history wording * test(cli): verify unified ingest public output * docs: add unified ingest v1 public output closure plan * fix(setup): forward query history flags * fix(setup): prompt for postgres query history * fix(status): report query history readiness * fix(ingest): remove legacy public guidance * fix(ingest): polish foreground retry copy * docs(examples): use unified query history wording * chore(ingest): finish public query history cleanup * docs: add unified ingest v1 query history status cleanup plan * test(docs): cover unified ingest public docs * docs: align ingest CLI reference with unified UX * docs: update context build guides for unified ingest * docs: update setup and primary source ingest wording * docs: stop advertising adapter-backed example ingest * docs: close unified ingest public docs gaps * docs: add unified ingest v1 docs site closure plan * fix: render unified ingest foreground warnings * fix: explain query history schema order * fix: add public ingest retry guidance * fix: align setup next steps with unified ingest * fix: remove scan wording from demo progress * test: verify unified ingest ux closure * docs: add unified ingest v1 foreground and retry closure plan * fix(cli): preserve query-history pull config in public ingest * fix(cli): omit hidden commands from docs command tree * test(cli): close unified ingest final public surface checks * docs: add unified ingest v1 final public surface closure plan * fix(cli): use public source labels in ingest reports * fix(cli): suppress low-level public ingest output * test(cli): verify unified ingest public plain output * docs: add unified ingest v1 public plain output closure plan * fix(cli): add public ingest copy sanitizers * fix(cli): sanitize public ingest progress copy * fix(cli): rename setup schema scope prompt * docs(plan): add progress copy closure; test: align setup back-nav fixture Adds the iter9 plan and updates the setup back-navigation test fixture to pass disableQueryHistory plus listSchemas/listTables stubs that the unified ingest setup step now requires. * docs(plan): add final ux labels plan with narrowed label scans * fix(cli): aggregate unsupported query-history warnings * fix(cli): align setup database labels * test(cli): fix setup database test type-check * fix(cli): remove primary-source wording from setup output * test(cli): verify unified ingest setup closure * docs(plan): add unified ingest v1 verification copy closure plan * fix(cli): remove top-level scan command * fix(cli): remove legacy ingest and wiki commands * Merge scan into ingest flow * feat(cli): split ingest progress into per-phase rows, rename work units to tasks Each database target in the unified ingest dashboard now renders one row per real subprocess (Schema, then Query history when enabled) instead of a single combined bar. Each phase has its own monotonic 0-100% bar so the progress never snaps back to zero when historic-sql starts after scan completes. Completed phases keep their final bar, summary, and elapsed time visible as an inline audit trail; queued and skipped phases are shown explicitly. Also rename user-facing "work units" / "Failed work units" to "tasks" / "Failed tasks" in ingest output and parseIngestSummary. The parser still accepts the legacy "Work units:" wording in captured output for backward compat. Internal memory-flow event names and type fields are left alone. * Fix test harness failures * Fix CI smoke checks --------- Co-authored-by: Andrey Avtomonov <7889985+andreybavt@users.noreply.github.com>
2026-05-14 01:43:06 +02:00
getMarkdown: async () => normalizeMarkdown(await readDocsPageMarkdown(page.slugs)),
} satisfies LlmDocsPage;
}
function normalizeMarkdown(markdown: string) {
return markdown
.trim()
.replace(/^---\n[\s\S]*?\n---\n?/, "")
.trim()
.replace(/\n{3,}/g, "\n\n");
}
function buildPageIndex(pages: LlmDocsPage[]) {
const grouped = new Map<string, LlmDocsPage[]>();
for (const page of pages) {
const category = page.slug[0] ?? "general";
grouped.set(category, [...(grouped.get(category) ?? []), page]);
}
return [...grouped.entries()]
.map(([category, categoryPages]) => {
const links = categoryPages
.map((page) => {
const description = page.description ? `: ${page.description}` : "";
return `- [${page.title}](${absoluteUrl(page.markdownUrl)})${description}`;
})
.join("\n");
return `### ${formatCategoryName(category)}
${links}`;
})
.join("\n\n");
}
function absoluteUrl(path: string) {
return `${siteOrigin}${path}`;
}
function formatCategoryName(category: string) {
const labels: Record<string, string> = {
"ai-resources": "AI Resources",
"cli-reference": "CLI Reference",
};
if (labels[category]) {
return labels[category];
}
return category
.split("-")
.map((word) => word.charAt(0).toUpperCase() + word.slice(1))
.join(" ");
}