- Consolidated `cosineSimilarity` in `vector-math`, removed duplicate local impls, and treated mismatch/non-finite as zero. - Switched beam, query-cache, recall, shmr, and binary-vectors to consume shared `cosineSimilarity` from `vector-math`. - Changed embeddings to parse `$env/$flag`, return `Float32Array`, lazily import model deps, and retry via `fetchWithRetry`. - Added `@oh-my-pi/pi-utils` and replaced hardcoded FastEmbed cache paths with `getFastembedCacheDir`. - Expanded truthy parsing for lowercase `y`, `true`, `yes`, and `on`, then updated optional-embedding tests for cache behavior. - Updated binary-vectors and optional-embedding tests for NaN-safe cosine, `Float32Array`, and cache-dir expectations.
180 lines
5.6 KiB
TypeScript
180 lines
5.6 KiB
TypeScript
import * as fs from "node:fs";
|
|
import * as os from "node:os";
|
|
import * as path from "node:path";
|
|
import { getAgentDir, getConfigRootDir } from "./dirs";
|
|
|
|
const ENV_NAME_RE = /^[A-Za-z_][A-Za-z0-9_]*$/;
|
|
|
|
/**
|
|
* Strict shell-identifier shape. Used for dotenv keys we accept into
|
|
* `Bun.env` — those should be referenceable as `$NAME` from POSIX shells,
|
|
* so we reject anything outside `[A-Za-z_][A-Za-z0-9_]*`.
|
|
*/
|
|
export function isValidEnvName(name: string): boolean {
|
|
return ENV_NAME_RE.test(name);
|
|
}
|
|
|
|
/**
|
|
* The only names that are genuinely unsafe to forward to a native `execve`
|
|
* spawn: empty, containing `=` (would corrupt the `KEY=VALUE` framing) or
|
|
* NUL (terminates the C string mid-entry). Windows ships standard variables
|
|
* whose names contain parentheses (e.g. `ProgramFiles(x86)`, `CommonProgramFiles(x86)`)
|
|
* — those MUST survive the scrub so downstream resolvers (Git Bash discovery
|
|
* in `procmgr.ts`, etc.) can still read them.
|
|
*/
|
|
export function isSafeEnvName(name: string): boolean {
|
|
return name.length > 0 && !name.includes("=") && !name.includes("\0");
|
|
}
|
|
|
|
export function isSafeEnvValue(value: string): boolean {
|
|
return !value.includes("\0");
|
|
}
|
|
|
|
export function filterProcessEnv(env: Record<string, string | undefined>): Record<string, string> {
|
|
const result: Record<string, string> = {};
|
|
for (const key in env) {
|
|
const value = env[key];
|
|
if (!isSafeEnvName(key) || value === undefined || !isSafeEnvValue(value)) continue;
|
|
result[key] = value;
|
|
}
|
|
return result;
|
|
}
|
|
|
|
/**
|
|
* Parses a .env file synchronously and extracts key-value string pairs.
|
|
* Ignores lines that are empty or start with '#'. Trims whitespace.
|
|
* Allows values to be quoted with single or double quotes.
|
|
* Returns an object of key-value pairs.
|
|
*/
|
|
export function parseEnvFile(filePath: string): Record<string, string> {
|
|
const result: Record<string, string> = {};
|
|
try {
|
|
const content = fs.readFileSync(filePath, "utf-8");
|
|
for (const line of content.split("\n")) {
|
|
const trimmed = line.trim();
|
|
// Skip comments and blank lines
|
|
if (!trimmed || trimmed.startsWith("#")) continue;
|
|
|
|
const eqIndex = trimmed.indexOf("=");
|
|
if (eqIndex === -1) continue;
|
|
|
|
const key = trimmed.slice(0, eqIndex).trim();
|
|
if (!isValidEnvName(key)) continue;
|
|
|
|
let value = trimmed.slice(eqIndex + 1).trim();
|
|
|
|
// Remove surrounding quotes (" or ')
|
|
if ((value.startsWith('"') && value.endsWith('"')) || (value.startsWith("'") && value.endsWith("'"))) {
|
|
value = value.slice(1, -1);
|
|
}
|
|
if (!isSafeEnvValue(value)) continue;
|
|
|
|
result[key] = value;
|
|
}
|
|
} catch {
|
|
// File doesn't exist or can't be read - return empty result
|
|
}
|
|
|
|
// OMP_ overrides PI_
|
|
for (const k in result) {
|
|
if (k.startsWith("OMP_")) {
|
|
result[`PI_${k.slice(4)}`] = result[k];
|
|
}
|
|
}
|
|
|
|
return result;
|
|
}
|
|
|
|
// Eagerly parse the user's $HOME/.env and the current project's .env (from cwd)
|
|
const homeEnv = parseEnvFile(path.join(os.homedir(), ".env"));
|
|
const piEnv = parseEnvFile(path.join(getConfigRootDir(), ".env"));
|
|
const agentEnv = parseEnvFile(path.join(getAgentDir(), ".env"));
|
|
const projectEnv = parseEnvFile(path.join(process.cwd(), ".env"));
|
|
|
|
for (const key of Object.keys(Bun.env)) {
|
|
const value = Bun.env[key];
|
|
if (!isSafeEnvName(key) || value === undefined || !isSafeEnvValue(value)) {
|
|
delete Bun.env[key];
|
|
}
|
|
}
|
|
|
|
for (const file of [projectEnv, agentEnv, piEnv, homeEnv]) {
|
|
for (const key in file) {
|
|
if (!Bun.env[key]) {
|
|
Bun.env[key] = file[key];
|
|
}
|
|
}
|
|
}
|
|
|
|
/**
|
|
* Intentional re-export of Bun.env.
|
|
*
|
|
* All users should import this env module (import { $env } from "@oh-my-pi/pi-utils")
|
|
* before using environment variables. This ensures that .env files have been loaded and
|
|
* overrides (project, home) have been applied, so $env always reflects the correct values.
|
|
*/
|
|
export const $env: Record<string, string> = Bun.env as Record<string, string>;
|
|
|
|
/**
|
|
* Resolve the first environment variable value from the given keys.
|
|
* @param keys - The keys to resolve.
|
|
* @returns The first environment variable value, or undefined if no value is found.
|
|
*/
|
|
export function $pickenv(...keys: string[]): string | undefined {
|
|
for (const key of keys) {
|
|
const value = Bun.env[key]?.trim();
|
|
if (value) {
|
|
return value;
|
|
}
|
|
}
|
|
return undefined;
|
|
}
|
|
|
|
/**
|
|
* Parses a positive decimal integer from `$env[name]`.
|
|
* Empty, invalid, NaN, zero, or negative values return `defaultValue`.
|
|
*/
|
|
export function $envpos(name: string, defaultValue: number): number {
|
|
const raw = $env[name];
|
|
if (!raw) return defaultValue;
|
|
const parsed = Number.parseInt(raw, 10);
|
|
if (Number.isNaN(parsed) || parsed <= 0) return defaultValue;
|
|
return parsed;
|
|
}
|
|
|
|
/** True when `BUN_ENV` or `NODE_ENV` is the string `test`. */
|
|
export function isBunTestRuntime(): boolean {
|
|
return Bun.env.BUN_ENV === "test" || Bun.env.NODE_ENV === "test";
|
|
}
|
|
|
|
/**
|
|
* True when this code is running inside a `bun build --compile` standalone
|
|
* binary. Detects via the embedded virtual-filesystem path markers
|
|
* (`$bunfs`, `~BUN`, or its URL-encoded form `%7EBUN`) in `import.meta.url`,
|
|
* which Bun rewrites for every module bundled into the executable. The
|
|
* `PI_COMPILED` env var (set by the build script's `--define`) is checked
|
|
* first for cheap fast-path detection.
|
|
*/
|
|
export function isCompiledBinary(): boolean {
|
|
if (Bun.env.PI_COMPILED) return true;
|
|
const url = import.meta.url;
|
|
return url.includes("$bunfs") || url.includes("~BUN") || url.includes("%7EBUN");
|
|
}
|
|
|
|
const TRUTHY: Dict<boolean> = {
|
|
"1": true,
|
|
Y: true,
|
|
y: true,
|
|
TRUE: true,
|
|
true: true,
|
|
YES: true,
|
|
yes: true,
|
|
ON: true,
|
|
on: true,
|
|
};
|
|
export function $flag(name: string, def: boolean = false): boolean {
|
|
const value = $env[name];
|
|
if (!value) return def;
|
|
return TRUTHY[value] === true;
|
|
}
|