yt-briefing 0.8.0 → 0.9.0
This diff represents the content of publicly available package versions that have been released to one of the supported registries. The information contained in this diff is provided for informational purposes only and reflects changes between package versions as they appear in their respective public registries.
- package/README.md +5 -5
- package/package.json +1 -1
package/README.md
CHANGED
|
@@ -77,12 +77,12 @@ npx yt-briefing list # show the current l
|
|
|
77
77
|
|
|
78
78
|
## One-off: transcribe a single video
|
|
79
79
|
|
|
80
|
-
Just want one video
|
|
80
|
+
Just want one video distilled — no channels, no queue, no rating? Run `/yt-transcribe` and
|
|
81
81
|
paste a URL or video ID. It pulls that video's transcript and writes a journalist-grade
|
|
82
|
-
|
|
82
|
+
briefing in the language you chose at setup (the same `output_lang` as `/yt`). Want a one-off in
|
|
83
83
|
another language? Just say so when you run it (e.g. `/yt-transcribe <url> in German`) — it
|
|
84
84
|
won't change your setup. `--lang pl|en` is separate — it picks which caption track to fetch,
|
|
85
|
-
not the
|
|
85
|
+
not the language it's written in.
|
|
86
86
|
|
|
87
87
|
The skill is installed alongside `/yt` by `init` / `install-skill`. From the plain CLI:
|
|
88
88
|
|
|
@@ -128,11 +128,11 @@ OpenAI (`https://api.openai.com/v1`), or a local Ollama (`http://localhost:11434
|
|
|
128
128
|
|
|
129
129
|
## Why an API, not the agent's native model
|
|
130
130
|
|
|
131
|
-
The filtering and the
|
|
131
|
+
The filtering and the briefings go through a plain OpenAI-compatible API call from the engine,
|
|
132
132
|
not through the coding agent's own model. Two reasons.
|
|
133
133
|
|
|
134
134
|
Speed. The engine works ahead in the background. It expands channels in parallel and starts
|
|
135
|
-
|
|
135
|
+
on the next video's briefing while you rate the current one, so the following step is usually
|
|
136
136
|
ready with no wait. An agent's turn-by-turn loop cannot prefetch like that, and every step pays
|
|
137
137
|
its own cold start, which adds up across a whole queue.
|
|
138
138
|
|
package/package.json
CHANGED
|
@@ -1,6 +1,6 @@
|
|
|
1
1
|
{
|
|
2
2
|
"name": "yt-briefing",
|
|
3
|
-
"version": "0.
|
|
3
|
+
"version": "0.9.0",
|
|
4
4
|
"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.",
|
|
5
5
|
"type": "module",
|
|
6
6
|
"bin": {
|