yt-briefing 0.5.0 → 0.6.0

package/.claude/skills/yt-search/SKILL.md

@@ -1,15 +1,19 @@
 ---
 name: yt-search
-description: Research a topic across YouTube — describe an intent, the engine expands it into search queries, ranks results against your intent, then lazily yields ONE video at a time with a rich summary. You keep or skip each; at the end it synthesizes a comparison from everything you kept. Same transcript engine + proxy as /yt; lazy on purpose (no transcript bursts → no IP block). Summaries and prompts use the language chosen at onboarding.
-argument-hint: A descriptive intent in quotes, e.g. "which terminal for coding with Claude Code". Optional --max N, --since YYYY-MM-DD, --queries 1..3.
+description: Search WITHIN one YouTube channel by intent — name a channel and what you're after; the engine lists that channel's uploads, ranks them against your intent (metadata only, no transcript yet), then lazily yields ONE matching video at a time with a rich summary. You keep or skip each; at the end it synthesizes a comparison from everything you kept. Channel-scoped, not whole-YouTube. Same transcript engine + proxy as /yt; lazy on purpose (no transcript bursts → no IP block). Summaries and prompts use the language chosen at onboarding.
+argument-hint: A channel (@handle or URL) and a descriptive intent, e.g. "@t3dotgg which terminal for AI coding". Optional --max N, --scan N, --since YYYY-MM-DD.
 ---
 
 ## How it works
 
-`src/yt-search.ts` is the whole engine: intent → query expansion (LLM) → `search.list` → re-rank against the intent on metadata only (no transcript) → **lazy** one-candidate-at-a-time yield with a rich summary → record keep/skip → on demand synthesize a comparison from everything kept. Matching is **descriptive, not exact-keyword** — YouTube ranks by relevance and the LLM bridges intent→query and filters noise. This skill is a thin loop: paste the summary, collect keep/skip, show the final comparison. It runs no filters and formats nothing itself.
+`src/yt-search.ts` is the whole engine: list one channel's uploads (cheap — `playlistItems`, ~1 quota unit/page; NOT `search.list`) → re-rank them against your intent on metadata only (title/description, no transcript) → **lazy** one-candidate-at-a-time yield with a rich summary → record keep/skip → on demand synthesize a comparison from everything kept. **Channel-scoped on purpose** — you choose where to look; it does NOT search all of YouTube. Matching is descriptive: the LLM filters the channel's videos by intent. This skill is a thin loop — paste the summary, collect keep/skip, show the final comparison.
 
 **Lazy on purpose:** one transcript per step, never a burst — a burst looks like scraping and gets the IP blocked (same reason `/yt` is lazy). Run the engine bare — stdout is a single JSON line, stderr empty; never redirect.
 
+## Inputs
+
+The user gives a **channel** (`@handle` or a channel URL) and an **intent** (what to look for). Pass the channel via `--channel` and the intent as the quoted positional. If the user names a channel but no clear intent (or vice versa), ask for the missing half before running.
+
 ## Language
 
 Read `data/config.json` → `output_lang` once at the start. Phrase the question text and option descriptions in that language. The two button labels stay the short English words `Keep` / `Skip`. Summaries and the final comparison are already written in `output_lang` by the engine — paste them verbatim.
@@ -17,11 +21,11 @@ Read `data/config.json` → `output_lang` once at the start. Phrase the question
 ## Loop
 
 ```
-out = JSON.parse(`bun run src/yt-search.ts "<intent from the user>" --reset`)   // first call
+out = JSON.parse(`bun run src/yt-search.ts "<intent>" --channel <@handle|url> --reset`)   // first call
 while true:
   out.status:
     "error"           → show out.error verbatim, stop
-    "no_results"      → tell the user nothing relevant was found, stop
+    "no_results"      → tell the user nothing in that channel matched, stop
     "rate_limited"    → transcript fetch blocked (datacenter IP) — tell the user, stop; recovery in README.md → Running on a VPS
     "decision_needed" → steps A–C
     "done"            → step D
@@ -38,16 +42,16 @@ while true:
     - Keep → `bun run src/yt-search.ts --keep`
     - Skip → `bun run src/yt-search.ts --skip`
     - stop/dismissed → `bun run src/yt-search.ts --compare` (skip straight to D)
-  - The script reads the pending candidate from cache; pass only `--keep` / `--skip` / `--compare`. Its JSON becomes the next `out` — back to the top of the loop.
+  - The script reads the pending candidate from cache; pass only `--keep` / `--skip` / `--compare` (no channel/intent again). Its JSON becomes the next `out` — back to the top of the loop.
 
 **On `done` (step D):**
 
-- If `out.kept > 0` → run `out = JSON.parse(\`bun run src/yt-search.ts --compare\`)`; when it returns `status:"compare"`, paste `out.comparison` **verbatim** as your chat text (it's the artifact — a decision-grade comparison in `output_lang`). Stop.
+- If `out.kept > 0` → run `out = JSON.parse(\`bun run src/yt-search.ts --compare\`)`; when it returns `status:"compare"`, paste `out.comparison` **verbatim** as your chat text (the artifact — a decision-grade comparison in `output_lang`). Stop.
 - If `out.kept == 0` → tell the user nothing was kept, so there's nothing to compare. Stop.
 
 ## Rules
 
 - **Verbatim:** paste `summary` and `comparison` exactly as returned; never paste a raw transcript.
 - **Language:** question text + option descriptions follow `output_lang`; button labels stay `Keep` / `Skip`.
-- **Cost awareness:** each search runs `search.list` (100 quota units/query, up to `--queries`). Don't silently re-run `--reset` in a loop. A bare resume (no `--reset`) continues the same ranked queue without new searches.
-- **Stateless triage:** this is independent of `/yt` (no channels, no ratings). For the recurring channel briefing use `/yt`; for one video use `/yt-transcribe`.
+- **Scope:** one channel per search. Listing is cheap; the cost is the lazy transcript fetches, so let the user keep/skip rather than pulling everything. A bare resume (no `--reset`) continues the same ranked queue. `--scan N` (default 50) caps how many recent uploads are considered; `--since` widens by date.
+- **Stateless triage:** independent of `/yt` (no channel profiles, no ratings written). For the recurring multi-channel briefing use `/yt`; for one known video use `/yt-transcribe`.

package/README.md

@@ -77,24 +77,26 @@ The skill is installed alongside `/yt` by `init` / `install-skill`. From the pla
 npx yt-briefing transcribe <url-or-id> --lang auto   # prints the transcript to stdout
 ```
 
-## Research a topic across YouTube
+## Search within a channel
 
-Want to know what YouTube says about something — and get an actual comparison, not a pile of
-links? Run `/yt-search` and describe the intent, e.g. `which terminal for coding with Claude
-Code`. The matching is **descriptive, not exact keywords**: an LLM turns your intent into search
-queries, then ranks the results against what you actually meant (on titles/descriptions — no
-transcripts yet). Then it hands you **one video at a time** with a rich summary; you **Keep** or
-**Skip** each. At the end it synthesizes a **comparison** from everything you kept.
+Following a creator and want to mine *their* videos for something specific — and get an actual
+comparison, not a pile of links? Run `/yt-search`, name a **channel** and your **intent**, e.g.
+`@t3dotgg which terminal for AI coding`. It lists that channel's uploads, ranks them against your
+intent (titles/descriptions — no transcripts yet, matching is **descriptive, not exact keywords**),
+then hands you **one matching video at a time** with a rich summary; you **Keep** or **Skip** each.
+At the end it synthesizes a **comparison** from everything you kept.
 
-It's lazy on purpose — one transcript per step, never a burst (a burst gets your IP blocked, same
-as `/yt`). Summaries and the comparison use the language you chose at setup.
+It's channel-scoped on purpose (you choose where to look) and lazy — one transcript per step, never
+a burst (a burst gets your IP blocked, same as `/yt`). Summaries and the comparison use the
+language you chose at setup.
 
 ```bash
-yt-briefing search "<intent>" [--max N] [--queries 1..3] [--since YYYY-MM-DD]   # JSON status line
+yt-briefing search "<intent>" --channel <@handle|url> [--max N] [--scan N] [--since YYYY-MM-DD]
 ```
 
-> Each search calls the YouTube `search.list` endpoint, which costs **100 quota units per query**
-> (plain reads cost 1; the daily free quota is 10,000). `--queries` (default 2) caps how many.
+> Listing a channel's uploads is cheap (`playlistItems`, ~1 quota unit per 50 videos — not the
+> 100-unit `search.list`). `--scan` (default 50) caps how many recent uploads are considered;
+> `--since` widens by date.
 
 ## Run it
 

package/dist/cli.js

@@ -12,7 +12,7 @@
  *   yt-briefing sweep [--reset]            advance one step; prints a JSON status line
  *   yt-briefing rate --rating 0|1 [...]    record a rating for the pending video
  *   yt-briefing transcribe <url|id>        print a single video's transcript
- *   yt-briefing search "<intent>" [...]    topic search → lazy triage → compare (JSON status line)
+ *   yt-briefing search "<intent>" --channel <@handle|url>   search within one channel → triage → compare
  */
 import { spawnSync } from 'node:child_process';
 import { script } from "./lib/paths.js";

package/dist/lib/yt-api.js

@@ -58,7 +58,7 @@ async function listUploads(playlistId, since, maxCount) {
                 hitOld = true;
                 break;
             }
-            videos.push({ videoId: item.snippet.resourceId.videoId, title: item.snippet.title, publishedAt });
+            videos.push({ videoId: item.snippet.resourceId.videoId, title: item.snippet.title, publishedAt, description: item.snippet.description ?? '' });
             if (maxCount !== null && videos.length >= maxCount)
                 return videos;
         }
@@ -110,35 +110,6 @@ async function enrichWithTypes(videos) {
     }
     return out;
 }
-/**
- * Free-text video search via `search.list`. YouTube ranks by relevance, so the query can be
- * descriptive — no exact keyword match required. NOTE: search.list costs 100 quota units per
- * call (plain reads cost 1), so callers should keep the number of queries small.
- *
- * `since` (ISO date) maps to publishedAfter — useful to cut stale results on fast-moving topics.
- */
-export async function searchVideos(query, opts = {}) {
-    const { maxResults = 10, since = null } = opts;
-    const params = {
-        part: 'snippet',
-        q: query,
-        type: 'video',
-        order: 'relevance',
-        maxResults: String(Math.min(Math.max(maxResults, 1), 50)),
-    };
-    if (since)
-        params.publishedAfter = new Date(since).toISOString();
-    const data = await get('search', params);
-    return (data.items || [])
-        .filter((it) => it.id?.videoId)
-        .map((it) => ({
-        videoId: it.id.videoId,
-        title: it.snippet?.title ?? '',
-        channelTitle: it.snippet?.channelTitle ?? '',
-        publishedAt: it.snippet?.publishedAt ?? '',
-        description: it.snippet?.description ?? '',
-    }));
-}
 /**
  * List a channel's uploads (newest first). With `enrich` (default true) each video is
  * typed (short/live/longform) and current/upcoming live broadcasts are filtered out.

package/dist/yt-search.js

@@ -1,23 +1,22 @@
 #!/usr/bin/env node
 /**
- * yt-search.ts — ad-hoc topic search → lazy triage → comparison. The third yt-briefing mode,
- * sibling to the channel briefing (yt-sweep) and one-shot transcribe (yt-transcript).
+ * yt-search.ts — search WITHIN one channel by intent, then lazy triage → comparison. The third
+ * yt-briefing mode, sibling to the channel briefing (yt-sweep) and one-shot transcribe.
  *
- * You describe an intent ("which terminal for coding with Claude Code"); the engine:
- *   1. expands it into a few YouTube search queries (LLM),
- *   2. runs search.list and merges candidates,
- *   3. re-ranks candidates against your intent on metadata only — title/channel/description,
- *      NO transcript yet (cheap; protects the expensive/rate-limited transcript step),
- *   4. yields ONE candidate at a time with a rich summary, lazily — never a burst of transcript
- *      fetches (a burst looks like scraping and gets the IP blocked, same reason yt-sweep is lazy),
- *   5. records your keep/skip decision; kept summaries accumulate in a cache,
- *   6. on demand synthesizes a comparison across everything you kept.
+ * You point it at a channel and describe what you're after ("which terminal does he recommend
+ * for AI coding"); the engine:
+ *   1. lists that channel's uploads (cheap — playlistItems, 1 quota unit/page; NOT search.list),
+ *   2. re-ranks them against your intent on metadata only — title/description, NO transcript yet,
+ *   3. yields ONE matching video at a time with a rich summary, lazily — never a burst of
+ *      transcript fetches (a burst looks like scraping and gets the IP blocked),
+ *   4. records your keep/skip decision; kept summaries accumulate in a cache,
+ *   5. on demand synthesizes a comparison across everything you kept.
  *
- * Matching is descriptive, not exact-keyword: search.list already ranks by relevance, and the
- * LLM bridges intent→query (step 1) and filters noise (step 3).
+ * Channel-scoped on purpose: you choose where to look. Matching is descriptive — the LLM filters
+ * the channel's videos by intent (no exact-keyword needed).
  *
  * Usage (the skill / CLI drives these; one JSON line per call):
- *   yt-search "<intent>" [--reset] [--max N] [--queries N] [--since DATE] [--lang auto]
+ *   yt-search "<intent>" --channel <@handle|url> [--reset] [--max N] [--scan N] [--since DATE] [--lang auto]
  *   yt-search --keep        record the pending candidate, advance, yield next
  *   yt-search --skip        drop the pending candidate, advance, yield next
  *   yt-search --compare     synthesize a comparison from everything kept
@@ -26,9 +25,9 @@
  *   {"status":"decision_needed","summary":"<md>","pending":{videoId,title,channelTitle,publishedAt,position,total}}
  *   {"status":"done","kept":N}              queue exhausted — caller runs --compare if kept>0
  *   {"status":"compare","comparison":"<md>"}
- *   {"status":"no_results"}                 search returned nothing for the intent
+ *   {"status":"no_results"}                 the channel has no videos matching the intent
  *   {"status":"rate_limited"}               transcript fetch blocked (datacenter IP — see docs/warp-proxy.md)
- *   {"status":"error","error":"<msg>"}      setup/config problem (missing key, etc.)
+ *   {"status":"error","error":"<msg>"}      setup/config problem (missing key, missing channel, …)
  *
  * Cache (all throwaway, under DATA_DIR/.cache): search-queue.json (ranked candidates + cursor),
  * search-pending.json (current candidate), search-kept.json (kept summaries = compare corpus).
@@ -38,27 +37,43 @@ import { spawn } from 'node:child_process';
 import dotenv from 'dotenv';
 import { chat, getModel } from "./lib/llm.js";
 import { outputLang } from "./lib/config.js";
-import { searchVideos } from "./lib/yt-api.js";
+import { fetchChannelVideos } from "./lib/yt-api.js";
+import { normalizeHandle } from "./lib/channels.js";
 import { PKG_ROOT, ENV_PATH, CACHE_DIR, SEARCH_QUEUE_FILE, SEARCH_PENDING_FILE, SEARCH_KEPT_FILE, script, } from "./lib/paths.js";
 dotenv.config({ path: ENV_PATH });
 mkdirSync(CACHE_DIR, { recursive: true });
 const RUNTIME = process.execPath;
 const LANG = outputLang();
 const argv = process.argv.slice(2);
+const VALUE_FLAGS = new Set(['--channel', '--max', '--scan', '--since', '--lang']);
 const has = (f) => argv.includes(f);
 const flagVal = (f) => {
     const i = argv.indexOf(f);
-    return i !== -1 && argv[i + 1] ? argv[i + 1] : null;
+    return i !== -1 && argv[i + 1] != null ? argv[i + 1] : null;
 };
-// First non-flag token is the intent (only on the initial / --reset call).
-const positional = argv.filter((a, i) => !a.startsWith('--') && !(i > 0 && argv[i - 1].startsWith('--') && argv[i - 1] !== '--reset' && argv[i - 1] !== '--keep' && argv[i - 1] !== '--skip' && argv[i - 1] !== '--compare'));
-const intentArg = positional[0] ?? null;
+// First token that is neither a flag nor a flag's value is the intent.
+function positionalIntent() {
+    for (let i = 0; i < argv.length; i++) {
+        const a = argv[i];
+        if (a.startsWith('--')) {
+            if (VALUE_FLAGS.has(a))
+                i++;
+            continue;
+        }
+        if (i > 0 && VALUE_FLAGS.has(argv[i - 1]))
+            continue;
+        return a;
+    }
+    return null;
+}
+const intentArg = positionalIntent();
 const RESET = has('--reset');
 const KEEP = has('--keep');
 const SKIP = has('--skip');
 const COMPARE = has('--compare');
+const CHANNEL = flagVal('--channel');
 const MAX = Math.max(1, parseInt(flagVal('--max') || '8', 10));
-const QUERIES = Math.max(1, Math.min(3, parseInt(flagVal('--queries') || '2', 10)));
+const SCAN = Math.max(1, parseInt(flagVal('--scan') || '50', 10)); // recent uploads to consider when no --since
 const SINCE = flagVal('--since');
 const LANGTRACK = flagVal('--lang') || 'auto';
 function emit(obj) {
@@ -89,7 +104,7 @@ function fetchTranscript(videoId) {
         p.on('error', reject);
     });
 }
-/** Strip ```fences``` and slice the outermost JSON array from an LLM reply. */
+/** Slice the outermost JSON array from an LLM reply (tolerates stray prose / fences). */
 function parseJsonArray(out) {
     const start = out.indexOf('['), end = out.lastIndexOf(']');
     if (start === -1 || end === -1 || end < start)
@@ -101,44 +116,27 @@ function parseJsonArray(out) {
         return null;
     }
 }
-// ---------- stage 1: intent → search queries ----------
-async function expandQueries(intent) {
-    const prompt = `A user wants to research a topic on YouTube. Turn their intent into up to ${QUERIES} effective YouTube search queries (short, keyword-rich, the way people actually search). Cover slightly different angles if useful. Use the language the topic is most discussed in (usually English for tech).
-
-Intent: "${intent}"
-
-Output ONLY a raw JSON array of strings, no fences, no commentary. Example: ["query one","query two"]`;
-    try {
-        const out = await chat(prompt, { system: 'You output ONLY a raw JSON array of search-query strings.', temperature: 0.4 });
-        const arr = parseJsonArray(out);
-        const qs = (arr ?? []).filter((s) => typeof s === 'string' && s.trim().length > 0).slice(0, QUERIES);
-        return qs.length ? qs : [intent];
-    }
-    catch {
-        return [intent]; // expansion is best-effort; fall back to the raw intent
-    }
-}
-// ---------- stage 3: re-rank candidates against intent (metadata only) ----------
-async function rerank(intent, hits) {
-    if (hits.length === 0)
+/** Re-rank a channel's videos against the intent (metadata only — no transcript). */
+async function rerank(intent, items) {
+    if (items.length === 0)
         return [];
-    const compact = hits.map(h => ({ id: h.videoId, title: h.title, channel: h.channelTitle, published: h.publishedAt, desc: (h.description || '').slice(0, 280) }));
-    const prompt = `Rank these YouTube videos by how well they serve the user's intent. Judge on title + channel + description only (no transcripts). Drop clearly off-topic, clickbait, or duplicate-angle results.
+    const compact = items.map(h => ({ id: h.videoId, title: h.title, published: h.publishedAt, desc: (h.description || '').slice(0, 280) }));
+    const prompt = `From this YouTube channel's videos, pick the ones that serve the user's intent and rank them. Judge on title + description only (no transcripts). Drop anything off-topic.
 
 Intent: "${intent}"
 
-Candidates:
+Videos:
 ${JSON.stringify(compact)}
 
 Output ONLY a raw JSON array, best first, no fences:
 [{"id":"VIDEO_ID","keep":true,"score":0-100,"reason":"max 12 words"},...]
-Set keep=false for anything not worth the user's time.`;
+Set keep=false for anything not relevant to the intent.`;
     try {
         const out = await chat(prompt, { system: 'You output ONLY a raw JSON array as instructed.', temperature: 0 });
         const arr = parseJsonArray(out);
         if (!arr)
-            return hits.map(h => ({ ...h })); // fall back: keep all, original order
-        const byId = new Map(hits.map(h => [h.videoId, h]));
+            return items; // fall back: keep all, original (newest-first) order
+        const byId = new Map(items.map(h => [h.videoId, h]));
         const ranked = [];
         for (const r of arr) {
             if (!r || r.keep === false)
@@ -147,13 +145,13 @@ Set keep=false for anything not worth the user's time.`;
             if (h)
                 ranked.push({ ...h, score: typeof r.score === 'number' ? r.score : undefined, reason: r.reason });
         }
-        return ranked.length ? ranked : hits.map(h => ({ ...h }));
+        return ranked.length ? ranked : items;
     }
     catch {
-        return hits.map(h => ({ ...h }));
+        return items;
     }
 }
-// ---------- mega-summary for one candidate (the triage artifact) ----------
+/** Rich, standalone summary for one candidate — the triage artifact + compare input. */
 async function megaSummary(c, transcript, intent) {
     const prompt = `Summarize this YouTube video in ${LANG} for a user researching: "${intent}". Make it a RICH, standalone summary they can decide on and that will later feed a cross-video comparison — OR return 'OFFTOPIC: <reason>' if the transcript clearly doesn't serve the intent.
 
@@ -181,7 +179,7 @@ Output ONLY the summary OR 'OFFTOPIC: <reason>'. No preamble.`;
         model: getModel(),
     });
 }
-// ---------- stage 6: comparison across kept summaries ----------
+/** Synthesize a comparison across everything kept. */
 async function synthesizeComparison(intent, kept) {
     const corpus = kept.map((k, i) => `--- VIDEO ${i + 1}: ${k.channelTitle} — "${k.title}" (${k.publishedAt})\nhttps://youtube.com/watch?v=${k.videoId}\n${k.summary}`).join('\n\n');
     const prompt = `The user researched "${intent}" and kept ${kept.length} YouTube video summaries below. Synthesize a single comparison in ${LANG} that actually helps them decide.
@@ -197,7 +195,7 @@ Write:
 Language: natural ${LANG}; foreign words only for proper nouns or established technical terms. Cite videos as [1], [2]… matching the order above. Output only the comparison.`;
     return chat(prompt, { system: `You synthesize a decision-grade comparison in ${LANG}. No preamble.`, model: getModel() });
 }
-// ---------- lazy yield: advance to the next candidate that has a transcript ----------
+/** Lazy yield: advance to the next candidate that has a transcript, summarize, emit. */
 async function yieldNext(queue) {
     while (queue.cursor < queue.candidates.length) {
         const c = queue.candidates[queue.cursor];
@@ -225,11 +223,7 @@ async function yieldNext(queue) {
     }
     emit({ status: 'done', kept: loadKept().length });
 }
-// ---------- main ----------
 async function main() {
-    if (!process.env.YT_BRIEFING_YOUTUBE_API_KEY && (RESET || (intentArg && !loadQueue()))) {
-        emit({ status: 'error', error: 'YT_BRIEFING_YOUTUBE_API_KEY is not set — add a YouTube Data API v3 key to .yt-briefing/.env (see README → setup / .env.example).' });
-    }
     // --compare: synthesize from kept summaries.
     if (COMPARE) {
         const queue = loadQueue();
@@ -243,7 +237,7 @@ async function main() {
     if (KEEP || SKIP) {
         const queue = loadQueue();
         if (!queue)
-            emit({ status: 'error', error: 'No active search. Start one: yt-search "<intent>".' });
+            emit({ status: 'error', error: 'No active search. Start one: yt-search "<intent>" --channel <@handle>.' });
         if (KEEP) {
             const pending = readJSON(SEARCH_PENDING_FILE, null);
             if (pending) {
@@ -256,37 +250,36 @@ async function main() {
         writeJSON(SEARCH_QUEUE_FILE, queue);
         await yieldNext(queue);
     }
-    // Resume an in-progress search (bare call, same intent) without rebuilding.
+    // Resume an in-progress search (bare call, same intent + channel) without rebuilding.
     const existing = loadQueue();
-    if (existing && !RESET && (!intentArg || intentArg === existing.intent)) {
+    if (existing && !RESET && (!intentArg || intentArg === existing.intent) && (!CHANNEL || normalizeHandle(CHANNEL) === existing.channel)) {
         await yieldNext(existing);
     }
-    // Fresh search (new intent or --reset).
+    // Fresh search: needs an intent AND a channel.
+    if (!process.env.YT_BRIEFING_YOUTUBE_API_KEY) {
+        emit({ status: 'error', error: 'YT_BRIEFING_YOUTUBE_API_KEY is not set — add a YouTube Data API v3 key to .yt-briefing/.env (see README → setup / .env.example).' });
+    }
     if (!intentArg)
-        emit({ status: 'error', error: 'Provide an intent: yt-search "<what to research>".' });
-    const queries = await expandQueries(intentArg);
-    const seen = new Set();
-    const hits = [];
-    for (const q of queries) {
-        let batch = [];
-        try {
-            batch = await searchVideos(q, { maxResults: 10, since: SINCE });
-        }
-        catch (e) {
-            emit({ status: 'error', error: e.message });
-        }
-        for (const h of batch)
-            if (!seen.has(h.videoId)) {
-                seen.add(h.videoId);
-                hits.push(h);
-            }
+        emit({ status: 'error', error: 'Provide an intent: yt-search "<what to look for>" --channel <@handle|url>.' });
+    if (!CHANNEL)
+        emit({ status: 'error', error: 'Provide a channel: --channel <@handle|url>. /yt-search searches within one channel, not all of YouTube.' });
+    const handle = normalizeHandle(CHANNEL);
+    if (!handle)
+        emit({ status: 'error', error: `Could not read a channel handle from "${CHANNEL}" — use @name or the channel URL.` });
+    let videos;
+    try {
+        videos = await fetchChannelVideos(handle, { since: SINCE, limit: SINCE ? null : SCAN, enrich: false });
+    }
+    catch (e) {
+        emit({ status: 'error', error: e.message });
     }
-    if (hits.length === 0)
+    if (videos.length === 0)
         emit({ status: 'no_results' });
-    const ranked = (await rerank(intentArg, hits)).slice(0, MAX);
+    const pool = videos.map(v => ({ videoId: v.videoId, title: v.title, channelTitle: handle, publishedAt: v.publishedAt, description: v.description }));
+    const ranked = (await rerank(intentArg, pool)).slice(0, MAX);
     if (ranked.length === 0)
         emit({ status: 'no_results' });
-    const queue = { built_at: new Date().toISOString(), intent: intentArg, candidates: ranked, cursor: 0 };
+    const queue = { built_at: new Date().toISOString(), intent: intentArg, channel: handle, candidates: ranked, cursor: 0 };
     writeJSON(SEARCH_QUEUE_FILE, queue);
     writeJSON(SEARCH_KEPT_FILE, []); // fresh search → fresh compare corpus
     await yieldNext(queue);

package/package.json

@@ -1,6 +1,6 @@
 {
   "name": "yt-briefing",
-  "version": "0.5.0",
+  "version": "0.6.0",
   "description": "A self-learning YouTube briefing engine: it sweeps the channels you follow, filters noise in two stages (title, then transcript), summarizes the rest in your language, and adapts to your ratings — one video at a time.",
   "type": "module",
   "bin": {