Add #rss command family with LLM tags and summaries (v0.20.0)

#rss subcommands on the command channel: help / add <url> <name> / remove <name> / tags / sources / get <name|#tag>. Sources are stored in a new rss_sources table in the existing MESH_DB_PATH file (second node:sqlite connection, case-insensitive names); feeds parsed with fast-xml-parser (RSS 2.0 + Atom); AI tags and headline summaries via injected LlmService.chat() with bounded maxTokens (50/200). CommandService gains prefix registration so one handler owns the whole #rss family while #ping stays an exact match; wired in CommandModule's factory — still no constructor-level cycle, no forwardRef. One dead feed does not sink a tag summary.
2026-09-25 18:44:06 +00:00
parent 023cd3eef3
commit eda1cbd125
15 changed files with 993 additions and 14 deletions
@@ -0,0 +1,205 @@
+import { Injectable, Logger } from '@nestjs/common';
+import { DatabaseSync } from 'node:sqlite';
+// type-only both ways — no runtime import cycle between src/rss and src/commands
+import type { CommandContext } from '../commands/command.service.js';
+import { LlmService } from '../llm/llm.service.js';
+import { parseFeed } from './rss.feed.js';
+import { RssStore } from './rss.store.js';
+
+// ponytail: hardcoded tunables, promote to env if the owner wants them adjustable
+const FETCH_TIMEOUT_MS = 15000; // feed fetches — same budget as the opencode notifier's POSTs
+const MAX_TITLES = 8; // "up to 8 latest item titles" per the design
+const TAG_MAX_TOKENS = 50;
+const SUMMARY_MAX_TOKENS = 200;
+
+/**
+ * The `#rss` command family: stored RSS sources (SQLite, shared MESH_DB_PATH file) with
+ * LLM-generated tags and on-demand headline summaries. All replies are short strings —
+ * CommandService routes them through MeshService.respond() like any other command reply.
+ */
+@Injectable()
+export class RssService {
+  private readonly logger = new Logger(RssService.name);
+  private readonly store: RssStore;
+
+  constructor(
+    private readonly llm: LlmService,
+    db: DatabaseSync,
+  ) {
+    this.store = new RssStore(db);
+  }
+
+  /** Entry point for the `#rss` prefix — always replies (errors included). */
+  async handle(ctx: CommandContext): Promise<string> {
+    const words = ctx.text.trim().split(/\s+/);
+    switch (words[1]) {
+      case undefined: // bare `#rss`
+      case 'help':
+        return this.help();
+      case 'add':
+        return this.add(words.slice(2));
+      case 'remove':
+        return this.remove(words.slice(2).join(' '));
+      case 'tags':
+        return this.tags();
+      case 'sources':
+        return this.sources();
+      case 'get':
+        return this.get((words[2] ?? '').trim());
+      default:
+        return this.help(); // unknown subcommand → help
+    }
+  }
+
+  private help(): string {
+    return [
+      '#rss add <url> <name> - add source with AI tags',
+      '#rss remove <name> - delete a source',
+      '#rss get <name|#tag> - summarize latest items',
+      '#rss tags - all distinct tags',
+      '#rss sources - all source names',
+    ].join('\n');
+  }
+
+  /** `#rss add <url> <name>` — name may contain spaces (everything after the url). */
+  private async add(args: string[]): Promise<string> {
+    const url = args[0];
+    const name = args.slice(1).join(' ').trim();
+    if (!url || !name) return 'usage: #rss add <url> <name>';
+    let parsedUrl: URL;
+    try {
+      parsedUrl = new URL(url);
+    } catch {
+      return 'invalid url';
+    }
+    if (parsedUrl.protocol !== 'http:' && parsedUrl.protocol !== 'https:')
+      return 'invalid url';
+    if (this.store.exists(name))
+      return `${name} already exists - remove it first`;
+
+    let titles: string[];
+    try {
+      titles = await this.fetchLatestTitles(url);
+    } catch (err) {
+      const msg = (err as Error).message;
+      // fetchLatestTitles throws `HTTP <status>` on non-2xx, other errors carry their own message
+      return msg.startsWith('HTTP')
+        ? `feed fetch failed (${msg})`
+        : 'not a valid feed';
+    }
+    if (!titles.length) return 'not a valid feed (no items)';
+
+    // AI tags — best effort: a source is still added when the LLM fails
+    let tags: string[] = [];
+    try {
+      const raw = await this.llm.chat(
+        [
+          {
+            role: 'user',
+            content: `Give 2-4 short lowercase tags for these RSS feed item titles. Reply with comma-separated tags only - no # symbols, no explanation:\n${titles.join('\n')}`,
+          },
+        ],
+        { maxTokens: TAG_MAX_TOKENS },
+      );
+      tags = sanitizeTags(raw);
+    } catch (err) {
+      this.logger.warn(
+        `[rss] tag generation failed for '${name}': ${(err as Error).message}`,
+      );
+    }
+
+    this.store.add({ name, url, tags });
+    return tags.length
+      ? `added ${name} (tags: ${tags.join(', ')})`
+      : 'added ' + name + ' (tag generation failed - no tags)';
+  }
+
+  private remove(name: string): string {
+    if (!name) return 'usage: #rss remove <name>';
+    return this.store.remove(name)
+      ? `removed ${name}`
+      : `no source named ${name}`;
+  }
+
+  private tags(): string {
+    const all = this.store.allTags();
+    return all.length ? all.join(', ') : 'no tags yet';
+  }
+
+  private sources(): string {
+    const names = this.store.list().map((s) => s.name);
+    return names.length ? names.join(', ') : 'no sources yet';
+  }
+
+  /** `#rss get <name>` or `#rss get #<tag>`. */
+  private async get(target: string): Promise<string> {
+    if (!target) return 'usage: #rss get <name|#tag>';
+
+    let urls: string[];
+    if (target.startsWith('#')) {
+      const tag = target.slice(1).toLowerCase();
+      if (!tag) return 'usage: #rss get <name|#tag>';
+      const matching = this.store.list().filter((s) => s.tags.includes(tag));
+      if (!matching.length) return `no sources with tag ${tag}`;
+      urls = matching.map((s) => s.url);
+    } else {
+      const source = this.store.get(target);
+      if (!source) return `no source named ${target}`;
+      urls = [source.url];
+    }
+
+    // one dead feed must not sink the whole summary — collect what answers
+    const results = await Promise.allSettled(
+      urls.map((u) => this.fetchLatestTitles(u)),
+    );
+    const titles: string[] = [];
+    for (const r of results) {
+      if (r.status === 'fulfilled') titles.push(...r.value);
+      else
+        this.logger.warn(
+          `[rss] feed fetch failed: ${(r.reason as Error).message}`,
+        );
+    }
+    if (!titles.length) return 'no items found';
+
+    try {
+      return await this.llm.chat(
+        [
+          {
+            role: 'user',
+            content: `Summarize these RSS headlines into a few short one-line highlights. Be concise:\n${titles.join('\n')}`,
+          },
+        ],
+        { maxTokens: SUMMARY_MAX_TOKENS },
+      );
+    } catch (err) {
+      this.logger.warn(`[rss] summary failed: ${(err as Error).message}`);
+      return 'summary failed';
+    }
+  }
+
+  /** Fetch a feed and return up to MAX_TITLES latest item titles; throws on non-2xx. */
+  private async fetchLatestTitles(url: string): Promise<string[]> {
+    const res = await fetch(url, {
+      signal: AbortSignal.timeout(FETCH_TIMEOUT_MS),
+    });
+    if (!res.ok) throw new Error(`HTTP ${res.status}`);
+    return parseFeed(await res.text())
+      .slice(0, MAX_TITLES)
+      .map((i) => i.title);
+  }
+}
+
+/** Normalize LLM tag output: lowercase, no #, whitespace → '-', deduped. */
+export function sanitizeTags(raw: string): string[] {
+  const seen = new Set<string>();
+  for (const part of raw.split(',')) {
+    const tag = part
+      .trim()
+      .toLowerCase()
+      .replace(/^#+/, '')
+      .replace(/\s+/g, '-');
+    if (tag) seen.add(tag);
+  }
+  return [...seen];
+}