Daan MeijerandClaude Opus 5.5
a66b0980f4
History fetched ahead into the corpus (bulk HDD) is ~60 TB raw for the 1,180B missing articles, and the indexer keeps only ~38% of headers. With CORPUS_FILTER (default on), Corpus.write leaves out the lines the edge worker drops on their own, decided per line as RangeIndexer.line does: a crosspost another indexed group owns, and a subject that names no file part (~48% of the indexed ranges' headers). Release-level rules (garbage, per-article, executable, poster) judge files across chunks and aren't applied. The chunk is compressed again as zlib (the worker takes it as before); beside it a .drops (gzip JSON) keeps the rule version, the owners' priorities and per rule the article numbers (as differences, crossposts by owner), and range.json says filtered. A test shows the worker makes the same releases, candidates and fragments of a filtered chunk. corpus:filter filters chunks stored raw (planned capture ranges; --all for every range). Co-Authored-By: Claude Opus 5.5 <noreply@anthropic.com>
87 lines
3.5 KiB
TypeScript
87 lines
3.5 KiB
TypeScript
/*
|
|
|--------------------------------------------------------------------------
|
|
| Environment variables service
|
|
|--------------------------------------------------------------------------
|
|
|
|
|
| The `Env.create` method creates an instance of the Env service. The
|
|
| service validates the environment variables and also cast values
|
|
| to JavaScript data types.
|
|
|
|
|
*/
|
|
|
|
import { Env } from '@adonisjs/core/env'
|
|
|
|
export default await Env.create(new URL('../', import.meta.url), {
|
|
// Node
|
|
NODE_ENV: Env.schema.enum(['development', 'production', 'test'] as const),
|
|
PORT: Env.schema.number(),
|
|
HOST: Env.schema.string({ format: 'host' }),
|
|
LOG_LEVEL: Env.schema.string(),
|
|
|
|
// App
|
|
APP_KEY: Env.schema.secret(),
|
|
APP_URL: Env.schema.string({ format: 'url', tld: false }),
|
|
|
|
// Session
|
|
SESSION_DRIVER: Env.schema.enum(['cookie', 'memory', 'database'] as const),
|
|
|
|
// Database
|
|
DB_HOST: Env.schema.string({ format: 'host' }),
|
|
DB_PORT: Env.schema.number(),
|
|
DB_USER: Env.schema.string(),
|
|
DB_PASSWORD: Env.schema.string.optional(),
|
|
DB_DATABASE: Env.schema.string(),
|
|
DB_POOL_MAX: Env.schema.number.optional(),
|
|
// Tablespace for the chunk store (the HDD on homelab).
|
|
CHUNK_TABLESPACE: Env.schema.string.optional(),
|
|
DB_DEBUG: Env.schema.boolean.optional(),
|
|
|
|
// NNTP (the coordinator's relay; edge:bench --capture)
|
|
NNTP_HOST: Env.schema.string.optional(),
|
|
NNTP_PORT: Env.schema.number.optional(),
|
|
NNTP_USER: Env.schema.string.optional(),
|
|
NNTP_PASSWORD: Env.schema.string.optional(),
|
|
NNTP_SECURE: Env.schema.boolean.optional(),
|
|
NNTP_CONNECTIONS: Env.schema.number.optional(),
|
|
NNTP_MIN_CONNECTIONS: Env.schema.number.optional(),
|
|
NNTP_ACCOUNT_CONNECTIONS: Env.schema.number.optional(),
|
|
NNTP_RESERVED_CONNECTIONS: Env.schema.number.optional(),
|
|
NNTP_TIMEOUT_MS: Env.schema.number.optional(),
|
|
NNTP_HEDGE_AFTER_SECONDS: Env.schema.number.optional(),
|
|
NNTP_HEDGE_CONNECTIONS: Env.schema.number.optional(),
|
|
NNTP_CONNECTION_MAX_MINUTES: Env.schema.number.optional(),
|
|
NNTP_IDLE_CLOSE_SECONDS: Env.schema.number.optional(),
|
|
CORPUS_FILTER: Env.schema.boolean.optional(),
|
|
NNTP_STALL_KB_PER_MINUTE: Env.schema.number.optional(),
|
|
|
|
// Newznab API key (empty: no key needed)
|
|
NEWZNAB_API_KEY: Env.schema.secret.optional(),
|
|
|
|
// Coordinator
|
|
RANGE_ARTICLES: Env.schema.number.optional(),
|
|
TAIL_EVERY_SECONDS: Env.schema.number.optional(),
|
|
TAIL_MIN_ARTICLES: Env.schema.number.optional(),
|
|
TAIL_MAX_DELAY_MINUTES: Env.schema.number.optional(),
|
|
CHUNK_ARTICLES: Env.schema.number.optional(),
|
|
LEASE_TTL_SECONDS: Env.schema.number.optional(),
|
|
SPOOL_DIR: Env.schema.string.optional(),
|
|
CORPUS_DIR: Env.schema.string.optional(),
|
|
CATALOG_MAX_NVME_GB: Env.schema.number.optional(),
|
|
SPOT_GROUP: Env.schema.string.optional(),
|
|
SPOT_BACKFILL: Env.schema.number.optional(),
|
|
SPOT_EVERY_SECONDS: Env.schema.number.optional(),
|
|
SPOT_MAX_NZB_SEGMENTS: Env.schema.number.optional(),
|
|
SPOT_STANDALONE_AFTER_HOURS: Env.schema.number.optional(),
|
|
CORPUS_AHEAD: Env.schema.number.optional(),
|
|
PROBE_PIPELINE: Env.schema.number.optional(),
|
|
SPOOL_AHEAD_PER_LEASE: Env.schema.number.optional(),
|
|
SPOOL_MIN_AHEAD: Env.schema.number.optional(),
|
|
SPOOL_MAX_GB: Env.schema.number.optional(),
|
|
PREFETCH_PER_RANGE: Env.schema.number.optional(),
|
|
PROBE_CONNECTIONS: Env.schema.number.optional(),
|
|
PROBE_MIN_CONNECTIONS: Env.schema.number.optional(),
|
|
PROBE_MIN_FREE_GB: Env.schema.number.optional(),
|
|
HTTP_ROUTES: Env.schema.enum.optional(['all', 'node', 'public'] as const),
|
|
PREFETCH_PER_GROUP: Env.schema.number.optional(),
|
|
})
|