mirror of
https://github.com/profullstack/logicsrc.git
synced 2026-09-10 19:26:00 +00:00
* Add the LogicSRC OpenContext specification OpenContext is an open specification for durable, portable, permissioned, provenance-aware context shared between humans and AI agents. It defines how organizational knowledge is described, authorized, versioned, resolved, audited, and handed between replaceable workers without losing institutional state. Follows the OpenPRD/OpenOntology pattern already in the repo: self-contained JSON Schemas in @logicsrc/schemas, a reference implementation package, CLI subcommands, docs, examples, and an OpenPRD record. Schemas (8, all self-contained so a third party can fetch one file and validate against it with no further resolution): manifest, object, bundle, role, provenance, decision, diagnostic, audit-event — registered in @logicsrc/validators and schemas:validate. Reference implementation (@logicsrc/opencontext): loader with upward manifest discovery, the full resolution pipeline, authority/supersession, permissions, redaction, lifecycle, provenance, deterministic digests, doctor, search, graph, history/diff, guarded writes, audit events, and file/http/git/sqlite adapters. CLI: all 15 specified commands, as a standalone `opencontext` binary and as `logicsrc context`, sharing one implementation so the two cannot drift. Design decisions worth noting: - Supersession is declared, never inferred from version numbers. Inferring it would hide the governance failure it represents and make multiple-active-versions and duplicate-canonical impossible to detect. - The bundle digest identifies the resolved context, not the moment it was computed, so generated_at/bundle_id/digest/as_of are excluded while objects, lifecycle states, exclusions and warnings are covered. That is what lets a decision record cite exactly the context that produced it. - A role's own max_classification beats an inherited one, so a ceiling on a shared base role cannot silently cap a role deliberately granted more; requesting several roles at once still takes the lowest, so combining roles never escalates. - Scope wildcards match whole dotted segments only. A trailing .* covers a subtree; an interior * matches exactly one segment. Substring matching here would be an access-control bug. - --include narrows an existing scope and is applied after it, never merged into it, so a request can never widen what a role holds. Verified: 226 tests across core primitives, permissions/redaction, the resolution pipeline, security, the published conformance fixtures (13 valid, 35 invalid, 8 resolution scenarios), project behaviour, and the five shipped examples — which are held to --strict and a 100% health score. Benchmarks meet every published budget (resolve 1,000 objects in ~33ms against a 2s target). Co-Authored-By: Claude Opus 5 (1M context) <noreply@anthropic.com> * Point install docs at @logicsrc/opencontext; record the npm name collision The unscoped `opencontext` name is already published on npm by an unrelated third party (federicodeponte/opencontext, 2.0.0), so `npx opencontext` would install a stranger's package. Docs now use `npx @logicsrc/opencontext`; the bin stays named `opencontext` so the command reads as the PRD specifies once installed. Recorded in PRD 0003 as a blocker to resolve before any publication, along with the fact that no @logicsrc spec package has ever been published, so there is no existing release path to slot into. Co-Authored-By: Claude Opus 5 (1M context) <noreply@anthropic.com> * Advance the logicsrc-mcp next-PRD-id assertion to 0004 standards.test.ts asserts prd_next_id against the live prd/ directory, so adding PRD 0003 makes the next free id 0004. The test's own comment anticipates this: "advances with every PRD added". Caught by CI, not locally — the earlier verification ran per-package tests for the packages this branch touches, and logicsrc-mcp is coupled to the PRD directory without importing from it. Co-Authored-By: Claude Opus 5 (1M context) <noreply@anthropic.com> --------- Co-authored-by: Claude Opus 5 (1M context) <noreply@anthropic.com>
153 lines
5.2 KiB
TypeScript
153 lines
5.2 KiB
TypeScript
/**
|
|
* Reading context documents off disk.
|
|
*
|
|
* Three shapes are supported and they mean the same thing:
|
|
* - Markdown with YAML front matter — metadata in the fence, prose as content
|
|
* - YAML — the whole document is the object
|
|
* - JSON — the whole document is the object
|
|
*
|
|
* A Markdown file with no front matter is still a valid context object: it
|
|
* becomes content with an id derived from its path. That is what keeps
|
|
* OpenContext adoptable — point it at an existing `docs/` folder and it works,
|
|
* then add metadata where governance actually matters.
|
|
*/
|
|
|
|
import { parse as parseYaml } from "yaml";
|
|
import type { ContextObject } from "./types.js";
|
|
|
|
const FRONT_MATTER = /^---\r?\n([\s\S]*?)\r?\n---(?:\r?\n|$)/;
|
|
|
|
export interface ParsedDocument {
|
|
/** The object as authored. Never has defaults applied. */
|
|
object: ContextObject;
|
|
/** 1-indexed line the front matter / document body starts on. */
|
|
bodyLine: number;
|
|
/** Keys present in the source, for reporting unknown-field errors precisely. */
|
|
declaredKeys: string[];
|
|
format: "markdown" | "yaml" | "json";
|
|
}
|
|
|
|
export class ContextParseError extends Error {
|
|
readonly file: string;
|
|
readonly line?: number;
|
|
|
|
constructor(message: string, file: string, line?: number) {
|
|
super(message);
|
|
this.name = "ContextParseError";
|
|
this.file = file;
|
|
this.line = line;
|
|
}
|
|
}
|
|
|
|
export function parseContextDocument(text: string, file: string): ParsedDocument {
|
|
const lower = file.toLowerCase();
|
|
if (lower.endsWith(".json")) return parseJsonDocument(text, file);
|
|
if (lower.endsWith(".yaml") || lower.endsWith(".yml")) return parseYamlDocument(text, file);
|
|
return parseMarkdownDocument(text, file);
|
|
}
|
|
|
|
function parseJsonDocument(text: string, file: string): ParsedDocument {
|
|
let data: unknown;
|
|
try {
|
|
data = JSON.parse(text);
|
|
} catch (error) {
|
|
throw new ContextParseError(`Invalid JSON: ${(error as Error).message}`, file);
|
|
}
|
|
assertObject(data, file);
|
|
return { object: data as ContextObject, bodyLine: 1, declaredKeys: Object.keys(data as object), format: "json" };
|
|
}
|
|
|
|
function parseYamlDocument(text: string, file: string): ParsedDocument {
|
|
let data: unknown;
|
|
try {
|
|
data = parseYaml(text);
|
|
} catch (error) {
|
|
throw new ContextParseError(`Invalid YAML: ${(error as Error).message}`, file, yamlErrorLine(error));
|
|
}
|
|
if (data === null || data === undefined) {
|
|
throw new ContextParseError("Document is empty.", file, 1);
|
|
}
|
|
assertObject(data, file);
|
|
return { object: data as ContextObject, bodyLine: 1, declaredKeys: Object.keys(data as object), format: "yaml" };
|
|
}
|
|
|
|
function parseMarkdownDocument(text: string, file: string): ParsedDocument {
|
|
const match = FRONT_MATTER.exec(text);
|
|
|
|
if (!match) {
|
|
// No front matter: the whole file is content. Still a valid object once the
|
|
// loader supplies an id and type from the collection it came from.
|
|
return {
|
|
object: { content: stripBom(text) } as unknown as ContextObject,
|
|
bodyLine: 1,
|
|
declaredKeys: [],
|
|
format: "markdown"
|
|
};
|
|
}
|
|
|
|
let meta: unknown;
|
|
try {
|
|
meta = parseYaml(match[1]!);
|
|
} catch (error) {
|
|
throw new ContextParseError(
|
|
`Invalid YAML front matter: ${(error as Error).message}`,
|
|
file,
|
|
1 + (yamlErrorLine(error) ?? 0)
|
|
);
|
|
}
|
|
|
|
if (meta === null || meta === undefined) meta = {};
|
|
assertObject(meta, file);
|
|
|
|
const body = text.slice(match[0].length);
|
|
const bodyLine = countLines(match[0]) + 1;
|
|
// id and type are supplied by the loader when the author omits them, so the
|
|
// parsed front matter is not yet a complete ContextObject.
|
|
const object = { ...(meta as Record<string, unknown>) } as unknown as ContextObject;
|
|
|
|
// Front matter may carry `content` explicitly; otherwise the prose is it.
|
|
// An empty body must not clobber a declared content field.
|
|
if (object.content === undefined && body.trim().length > 0) {
|
|
object.content = body.replace(/^\r?\n/, "");
|
|
}
|
|
|
|
return { object, bodyLine, declaredKeys: Object.keys(meta as object), format: "markdown" };
|
|
}
|
|
|
|
function assertObject(data: unknown, file: string): void {
|
|
if (typeof data !== "object" || data === null || Array.isArray(data)) {
|
|
throw new ContextParseError(
|
|
`Expected a context object (a mapping), got ${Array.isArray(data) ? "an array" : typeof data}.`,
|
|
file,
|
|
1
|
|
);
|
|
}
|
|
}
|
|
|
|
function stripBom(text: string): string {
|
|
return text.charCodeAt(0) === 0xfeff ? text.slice(1) : text;
|
|
}
|
|
|
|
function countLines(text: string): number {
|
|
let count = 0;
|
|
for (const char of text) if (char === "\n") count += 1;
|
|
return count;
|
|
}
|
|
|
|
function yamlErrorLine(error: unknown): number | undefined {
|
|
const pos = (error as { linePos?: Array<{ line: number }> }).linePos;
|
|
return pos?.[0]?.line;
|
|
}
|
|
|
|
/**
|
|
* Best-effort 1-indexed line of a top-level key, so diagnostics can point at the
|
|
* offending field rather than the file. Front matter is scanned from line 2,
|
|
* since line 1 is the opening fence.
|
|
*/
|
|
export function findFieldLine(text: string, field: string): number | undefined {
|
|
const escaped = field.replace(/[.*+?^${}()|[\]\\]/g, "\\$&");
|
|
const pattern = new RegExp(`^\\s*"?${escaped}"?\\s*:`, "m");
|
|
const match = pattern.exec(text);
|
|
if (!match) return undefined;
|
|
return countLines(text.slice(0, match.index)) + 1;
|
|
}
|