@steipete/summarize 0.3.0 → 0.5.0

package/docs/model-auto.md

@@ -0,0 +1,92 @@
+# Auto model selection (`--model auto`)
+
+`--model auto` picks a model based on input kind + token size, and retries with fallbacks when something fails.
+
+This is also the built-in default when you don’t specify a model.
+
+## What it does
+
+- Builds an ordered list of model “attempts” from `candidates[]` (native first, optional OpenRouter fallback).
+- Skips attempts that don’t have the required API key configured.
+- On any request error, tries the next attempt.
+- If no model is usable, prints the extracted text (no LLM summary). Use `--extract` if you want the raw extracted content even when models are available.
+- Auto prepends CLI attempts only when `cli.enabled` is set (see `docs/cli.md`).
+  - Order follows `cli.enabled`.
+
+## OpenRouter vs native
+
+Model ids:
+
+- Native: `<provider>/<model>` (e.g. `openai/gpt-5-mini`, `google/gemini-3-flash-preview`)
+- Forced OpenRouter: `openrouter/<author>/<slug>` (e.g. `openrouter/meta-llama/llama-3.3-70b-instruct:free`)
+
+Behavior:
+
+- If you pass an `openrouter/...` model id, the request uses OpenRouter (and requires `OPENROUTER_API_KEY`).
+- If you pass a native model id, the CLI prefers the native provider SDK when its key is available, and can fall back to OpenRouter when no native key exists (and `OPENROUTER_API_KEY` is set).
+
+## How selection works
+
+- Uses the order you provide in `model.rules[].candidates[]` (or `bands[].candidates[]`).
+- Filters out candidates that can’t fit the prompt (max input tokens, LiteLLM catalog).
+- For a native candidate, auto mode may add an OpenRouter fallback attempt right after it (when `OPENROUTER_API_KEY` is set and video understanding isn’t required).
+
+Notes:
+
+- Auto mode is non-streaming (so a failed attempt won’t partially print output).
+- Video understanding is only attempted when `--video-mode` is `auto` or `understand`, and a video-capable model is selected.
+
+## Config
+
+Default config file: `~/.summarize/config.json`
+
+This file is parsed leniently (JSON5), but **comments are not allowed**.
+
+`model.rules` is optional; when omitted, built-in defaults apply.
+
+`model.rules[].when` is optional, and when present must be an array (e.g. `["video","youtube"]`).
+
+Rules can be either:
+
+- `candidates: string[]`
+- `bands: [{ token?: { min?: number; max?: number }, candidates: string[] }]`
+
+Example:
+
+```json
+{
+  "model": {
+    "mode": "auto",
+    "rules": [
+      {
+        "when": ["video"],
+        "candidates": ["google/gemini-3-flash-preview"]
+      },
+      {
+        "when": ["website", "youtube"],
+        "bands": [
+          {
+            "token": { "max": 8000 },
+            "candidates": ["openai/gpt-5-mini"]
+          },
+          {
+            "candidates": ["xai/grok-4-fast-non-reasoning"]
+          }
+        ]
+      },
+      {
+        "candidates": ["openai/gpt-5-mini", "openrouter/openai/gpt-5-mini"]
+      }
+    ]
+  },
+  "media": { "videoMode": "auto" }
+}
+```
+
+Minimal shorthand:
+
+```json
+{
+  "model": "auto"
+}
+```

package/docs/site/assets/site.js

@@ -31,24 +31,27 @@ const highlightNav = () => {
 
 const wireCopyButtons = () => {
   const buttons = document.querySelectorAll('[data-copy]')
+  const handleCopyClick = async (button) => {
+    const selector = button.getAttribute('data-copy')
+    const target = selector ? document.querySelector(selector) : null
+    const text = target?.textContent?.trim() ?? ''
+    if (!text) return
+    try {
+      await navigator.clipboard.writeText(text)
+      const prev = button.textContent ?? ''
+      button.textContent = 'Copied'
+      button.setAttribute('data-copied', '1')
+      window.setTimeout(() => {
+        button.textContent = prev
+        button.removeAttribute('data-copied')
+      }, 900)
+    } catch {
+      // ignore
+    }
+  }
   for (const button of buttons) {
-    button.addEventListener('click', async () => {
-      const selector = button.getAttribute('data-copy')
-      const target = selector ? document.querySelector(selector) : null
-      const text = target?.textContent?.trim() ?? ''
-      if (!text) return
-      try {
-        await navigator.clipboard.writeText(text)
-        const prev = button.textContent ?? ''
-        button.textContent = 'Copied'
-        button.setAttribute('data-copied', '1')
-        window.setTimeout(() => {
-          button.textContent = prev
-          button.removeAttribute('data-copied')
-        }, 900)
-      } catch {
-        // ignore
-      }
+    button.addEventListener('click', () => {
+      void handleCopyClick(button)
     })
   }
 }

package/docs/site/docs/config.html

@@ -31,7 +31,7 @@
           <a href="./index.html">Overview</a>
           <a href="./website.html">Website mode</a>
           <a href="./youtube.html">YouTube mode</a>
-          <a href="./extract-only.html">Extract-only</a>
+          <a href="./extract-only.html">Extract</a>
           <a href="./llm.html">LLM</a>
           <a href="./openai.html">OpenAI</a>
           <a href="./firecrawl.html">Firecrawl</a>
@@ -46,7 +46,7 @@
           <h2>Environment variables</h2>
           <ul>
             <li><code>OPENAI_API_KEY</code>, <code>XAI_API_KEY</code>, <code>GEMINI_API_KEY</code> — provider keys (only needed when a mode actually calls an LLM).</li>
-            <li><code>FIRECRAWL_API_KEY</code> — optional extraction fallback for blocked/thin sites.</li>
+            <li><code>FIRECRAWL_API_KEY</code> — optional extraction fallback / preferred Markdown output in extract mode.</li>
           </ul>
 
           <h2>Tips</h2>
@@ -57,7 +57,7 @@
           </ul>
 
           <div class="note">
-            Want the raw content? Use <code>--extract-only</code> (then decide where the summary should happen).
+            Want the raw content? Use <code>--extract</code> (then decide where the summary should happen).
           </div>
         </article>
       </section>

package/docs/site/docs/extract-only.html

@@ -4,7 +4,7 @@
     <meta charset="utf-8" />
     <meta name="viewport" content="width=device-width,initial-scale=1" />
     <meta name="color-scheme" content="dark light" />
-    <title>Extract-only — summarize</title>
+    <title>Extract — summarize</title>
     <link rel="canonical" href="https://summarize.sh/docs/extract-only" />
     <link rel="preconnect" href="https://fonts.googleapis.com" />
     <link rel="preconnect" href="https://fonts.gstatic.com" crossorigin />
@@ -31,7 +31,7 @@
           <a href="./index.html">Overview</a>
           <a href="./website.html">Website mode</a>
           <a href="./youtube.html">YouTube mode</a>
-          <a href="./extract-only.html">Extract-only</a>
+          <a href="./extract-only.html">Extract</a>
           <a href="./llm.html">LLM</a>
           <a href="./openai.html">OpenAI</a>
           <a href="./firecrawl.html">Firecrawl</a>
@@ -40,7 +40,7 @@
 
         <article class="doc reveal">
           <p class="kicker">mode</p>
-          <h1>Extract-only</h1>
+          <h1>Extract</h1>
           <p>Print the extracted content and stop. No summary call.</p>
 
           <h2>Usage</h2>
@@ -50,7 +50,7 @@
               <span class="terminal__dot terminal__dot--b"></span>
               <span class="terminal__dot terminal__dot--c"></span>
             </div>
-            <pre><code id="ex-only">summarize --extract-only "https://example.com/article"</code></pre>
+            <pre><code id="ex-only">summarize --extract "https://example.com/article"</code></pre>
           </div>
           <div class="copyRow">
             <span class="hint">Good for piping into your own tooling.</span>
@@ -63,7 +63,9 @@
             <li><code>--verbose</code> — show which extractor ran and why.</li>
             <li><code>--timeout</code> — tune crawling budget (<code>2m</code> default).</li>
             <li><code>--firecrawl off|auto|always</code> — choose the fallback strategy.</li>
-            <li><code>--markdown off|auto|llm</code> — for non-YouTube URLs, control HTML→Markdown conversion.</li>
+            <li><code>--format md|text</code> — choose extracted output format.</li>
+            <li><code>--markdown-mode off|auto|llm</code> — for non-YouTube URLs with <code>--format md</code>, control HTML→Markdown conversion (LLM) + fallbacks.</li>
+            <li><code>--preprocess off|auto|always</code> — controls markitdown usage (default <code>auto</code>).</li>
           </ul>
         </article>
       </section>

package/docs/site/docs/firecrawl.html

@@ -31,7 +31,7 @@
           <a href="./index.html">Overview</a>
           <a href="./website.html">Website mode</a>
           <a href="./youtube.html">YouTube mode</a>
-          <a href="./extract-only.html">Extract-only</a>
+          <a href="./extract-only.html">Extract</a>
           <a href="./llm.html">LLM</a>
           <a href="./openai.html">OpenAI</a>
           <a href="./firecrawl.html">Firecrawl</a>
@@ -41,7 +41,7 @@
         <article class="doc reveal">
           <p class="kicker">extractor</p>
           <h1>Firecrawl</h1>
-          <p>Used as a fallback when HTML extraction looks blocked or too thin (or when forced via <code>--firecrawl always</code>).</p>
+          <p>Used as a fallback when HTML extraction looks blocked or too thin — and as a preferred Markdown source in extract mode (when configured).</p>
 
           <h2>Key</h2>
           <ul>
@@ -49,14 +49,14 @@
             <li>Control behavior with <code>--firecrawl off|auto|always</code>.</li>
           </ul>
 
-          <h2>Extract-only + Markdown</h2>
+          <h2>Extract + Markdown</h2>
           <ul>
-            <li><code>--extract-only</code> prints the extracted content.</li>
-            <li><code>--markdown auto|llm</code> can output Markdown for non-YouTube URLs.</li>
+            <li><code>--extract</code> prints the extracted content.</li>
+            <li><code>--extract --format md</code> outputs Markdown for non-YouTube URLs.</li>
           </ul>
 
           <div class="note">
-            If you only want plain text: use <code>--firecrawl off --markdown off</code>.
+            If you only want plain text: use <code>--extract --format text</code>.
           </div>
         </article>
       </section>

package/docs/site/docs/index.html

@@ -34,7 +34,7 @@
             <div class="pillRow">
               <span class="pill"><span class="pill__dot" aria-hidden="true"></span> Website</span>
               <span class="pill"><span class="pill__dot" aria-hidden="true" style="background: var(--accent2)"></span> YouTube</span>
-              <span class="pill"><span class="pill__dot" aria-hidden="true" style="background: var(--accent3)"></span> Extract-only</span>
+              <span class="pill"><span class="pill__dot" aria-hidden="true" style="background: var(--accent3)"></span> Extract</span>
             </div>
           </div>
         </div>
@@ -52,7 +52,7 @@
           <div class="small">docs/youtube.md</div>
         </a>
         <a class="card reveal" href="./extract-only.html">
-          <h2>Extract-only</h2>
+          <h2>Extract</h2>
           <p>Get the cleaned content and stop; perfect for piping.</p>
           <div class="small">docs/extract-only.md</div>
         </a>

package/docs/site/docs/llm.html

@@ -31,7 +31,7 @@
           <a href="./index.html">Overview</a>
           <a href="./website.html">Website mode</a>
           <a href="./youtube.html">YouTube mode</a>
-          <a href="./extract-only.html">Extract-only</a>
+          <a href="./extract-only.html">Extract</a>
           <a href="./llm.html">LLM</a>
           <a href="./openai.html">OpenAI</a>
           <a href="./firecrawl.html">Firecrawl</a>
@@ -53,7 +53,7 @@
           <h2>Practical advice</h2>
           <ul>
             <li>Pin <code>--model</code> for stable output.</li>
-            <li>When using <code>--markdown llm</code>, provider fallback is disabled by design.</li>
+            <li>When using <code>--markdown-mode llm</code>, provider fallback is disabled by design.</li>
             <li>For audits / tooling, prefer <code>--json</code> + fixed model.</li>
           </ul>
         </article>

package/docs/site/docs/openai.html

@@ -31,7 +31,7 @@
           <a href="./index.html">Overview</a>
           <a href="./website.html">Website mode</a>
           <a href="./youtube.html">YouTube mode</a>
-          <a href="./extract-only.html">Extract-only</a>
+          <a href="./extract-only.html">Extract</a>
           <a href="./llm.html">LLM</a>
           <a href="./openai.html">OpenAI</a>
           <a href="./firecrawl.html">Firecrawl</a>
@@ -45,7 +45,7 @@
 
           <h2>Notes</h2>
           <ul>
-            <li>Some modes (like <code>--extract-only</code>) don’t need an LLM at all.</li>
+            <li>Some modes (like <code>--extract</code>) don’t need an LLM at all.</li>
             <li>When output is used downstream, prefer <code>--json</code> and pin <code>--model</code>.</li>
           </ul>
 

package/docs/site/docs/website.html

@@ -31,7 +31,7 @@
           <a href="./index.html">Overview</a>
           <a href="./website.html">Website mode</a>
           <a href="./youtube.html">YouTube mode</a>
-          <a href="./extract-only.html">Extract-only</a>
+          <a href="./extract-only.html">Extract</a>
           <a href="./llm.html">LLM</a>
           <a href="./openai.html">OpenAI</a>
           <a href="./firecrawl.html">Firecrawl</a>
@@ -41,20 +41,23 @@
         <article class="doc reveal">
           <p class="kicker">mode</p>
           <h1>Website mode</h1>
-          <p>Fetch HTML → extract “article-ish” content → normalize to clean text. If extraction looks blocked or too thin, retry via Firecrawl Markdown (optional).</p>
+          <p>Fetch HTML → extract “article-ish” content → normalize to clean text. If extraction looks blocked or too thin, retry via Firecrawl Markdown (optional). With <code>--format md</code>, the CLI prefers Firecrawl Markdown when configured and can also convert HTML → Markdown via <code>--markdown-mode</code> (LLM) or <code>uvx markitdown</code>.</p>
 
           <h2>Flags</h2>
           <ul>
             <li><code>--firecrawl off|auto|always</code></li>
             <li><code>--timeout 30s|2m|5000ms</code> (default <code>2m</code>)</li>
-            <li><code>--extract-only</code> (print extracted content; no summary call)</li>
+            <li><code>--extract</code> (print extracted content; no summary call)</li>
+            <li><code>--format md|text</code> (default <code>text</code>)</li>
+            <li><code>--markdown-mode off|auto|llm</code> (only with <code>--format md</code>)</li>
+            <li><code>--preprocess off|auto|always</code> (default <code>auto</code>; controls markitdown usage)</li>
             <li><code>--json</code> (emit a single JSON object)</li>
             <li><code>--verbose</code> (progress + which extractor was used)</li>
             <li><code>--metrics off|on|detailed</code></li>
           </ul>
 
           <div class="note">
-            Plain-text mode: <code>--firecrawl off --markdown off</code>.
+            Plain-text mode: <code>--extract --format text</code>.
           </div>
         </article>
       </section>

package/docs/site/docs/youtube.html

@@ -31,7 +31,7 @@
           <a href="./index.html">Overview</a>
           <a href="./website.html">Website mode</a>
           <a href="./youtube.html">YouTube mode</a>
-          <a href="./extract-only.html">Extract-only</a>
+          <a href="./extract-only.html">Extract</a>
           <a href="./llm.html">LLM</a>
           <a href="./openai.html">OpenAI</a>
           <a href="./firecrawl.html">Firecrawl</a>
@@ -45,7 +45,7 @@
 
           <h2>Tip</h2>
           <ul>
-            <li>If you only want the transcript: use <code>--extract-only</code>.</li>
+            <li>If you only want the transcript: use <code>--extract</code>.</li>
             <li>For pipelines: add <code>--json</code>.</li>
           </ul>
         </article>

package/docs/site/index.html

@@ -104,7 +104,7 @@
         </div>
         <div class="card reveal">
           <h2>Built for pipelines</h2>
-          <p><code>--extract-only</code>, <code>--json</code>, and <code>--metrics</code> make it scriptable.</p>
+          <p><code>--extract</code>, <code>--json</code>, and <code>--metrics</code> make it scriptable.</p>
           <div class="small">Compose it with your own tools</div>
         </div>
         <div class="card reveal">

package/docs/smoketest.md

@@ -0,0 +1,58 @@
+# Smoke Test Plan (20 combos)
+
+Goal: exercise URL + file inputs, extraction + LLM summary paths, multiple models.
+
+## Preconditions
+- API keys set for at least: `OPENAI_API_KEY`, `GEMINI_API_KEY`.
+- Optional: `FIRECRAWL_API_KEY` to test fallback (if available).
+
+## Models (cheap/fast)
+- `openai/gpt-5-mini`
+- `google/gemini-3-flash-preview`
+
+## Matrix (20 cases)
+
+### Websites (LLM summary, 10)
+1) Static HTML: `https://example.com` (model: gemini-3-flash)
+2) Wikipedia article: `https://en.wikipedia.org/wiki/Swift_(programming_language)` (model: gpt-5-mini)
+3) MDN doc: `https://developer.mozilla.org/en-US/docs/Web/HTTP/Status/200` (model: gemini-3-flash)
+4) Reuters article: `https://www.reuters.com/world/` (model: gpt-5-mini)
+5) BBC article: `https://www.bbc.com/news` (model: gemini-3-flash)
+6) GitHub README: `https://github.com/vitejs/vite` (model: gpt-5-mini)
+7) Substack post: pick any public post (model: gemini-3-flash)
+8) Medium post: pick any public post (model: gpt-5-mini)
+9) JS-heavy page: `https://vercel.com` (model: gemini-3-flash)
+10) 404 page: `https://example.com/does-not-exist` (model: gpt-5-mini)
+
+### YouTube (LLM summary, 2)
+11) Captions available: pick a popular talk/interview (model: gemini-3-flash, `--youtube auto`)
+12) No captions: pick a random channel upload w/o captions (model: gpt-5-mini, `--youtube auto`)
+
+### Remote files (LLM summary, 4)
+13) PDF URL: any public PDF report (model: gemini-3-flash)
+14) PNG URL: `https://upload.wikimedia.org/wikipedia/commons/7/70/Example.png` (model: gpt-5-mini)
+15) MP3 URL: any public MP3 sample (model: gemini-3-flash)
+16) CSV URL: any public CSV sample (model: gpt-5-mini)
+
+### Local files (LLM summary, 4)
+17) `tests/fixtures/sample.txt` (create if missing) (model: gemini-3-flash)
+18) `tests/fixtures/sample.md` (create if missing) (model: gpt-5-mini)
+19) `tests/fixtures/sample.json` (create if missing) (model: gemini-3-flash)
+20) `tests/fixtures/sample.png` (create if missing; use a real PNG, not 1x1) (model: gpt-5-mini)
+
+## Commands (template)
+- Website: `pnpm summarize -- "<url>" --model <model> --length short`
+- YouTube: `pnpm summarize -- "<url>" --model <model> --youtube auto`
+- File URL: `pnpm summarize -- "<url>" --model <model>`
+- Local file: `pnpm summarize -- "<path>" --model <model>`
+
+## Capture
+- Log: stdout + stderr, exit code, and timing line.
+- Note extraction path (HTML vs Firecrawl vs YouTube transcript).
+- File errors: media type rejection, size limits, token preflight.
+
+## Bug bar
+- Crash, hang, or non-zero exit.
+- Empty summary with non-empty input.
+- Incorrect mode selection (e.g., YouTube treated as normal URL).
+- Wrong fallback behavior or misleading error text.

package/docs/website.md

@@ -7,21 +7,26 @@ Use this for non-YouTube URLs.
 - Fetches the page HTML.
 - Extracts “article-ish” content and normalizes it into clean text.
 - If extraction looks blocked or too thin, it can retry via Firecrawl (Markdown).
-- In `--extract-only` mode, Firecrawl is only used when HTML extraction looks blocked/thin (or when forced via `--firecrawl always`).
-- In `--extract-only` mode, `--markdown auto|llm` can convert HTML → Markdown via an LLM using the configured `--model` (no provider fallback).
+- If a page is effectively “video-only”, it may treat it as a video input (see `--video-mode`).
+- With `--format md`, the CLI prefers Firecrawl Markdown by default when `FIRECRAWL_API_KEY` is configured.
+- With `--format md`, `--markdown-mode auto|llm` can also convert HTML → Markdown via an LLM using the configured `--model` (no provider fallback).
+- With `--format md`, `--markdown-mode auto` may fall back to `uvx markitdown` when available (disable with `--preprocess off`).
 
 ## Flags
 
 - `--firecrawl off|auto|always`
-- `--markdown off|auto|llm` (default: `auto`; only affects `--extract-only` for non-YouTube URLs)
-- Plain-text mode: use `--firecrawl off --markdown off`.
+- `--format md|text` (default: `text`)
+- `--markdown-mode off|auto|llm` (default: `auto`; only affects `--format md` for non-YouTube URLs)
+- `--preprocess off|auto|always` (default: `auto`; controls markitdown usage; `always` only affects file inputs)
+- `--video-mode auto|transcript|understand` (only affects video inputs / video-only pages)
+- Plain-text mode: use `--format text`.
 - `--timeout 30s|30|2m|5000ms` (default: `2m`)
-- `--extract-only` (print extracted content; no summary LLM call)
+- `--extract` (print extracted content; no summary LLM call)
 - `--json` (emit a single JSON object)
 - `--verbose` (progress + which extractor was used)
-- `--metrics off|on|detailed` (default: `on`; `detailed` prints a breakdown to stderr)
+- `--metrics off|on|detailed` (default: `on`; `detailed` adds a compact 2nd-line breakdown on stderr)
 
 ## API keys
 
-- Optional: `FIRECRAWL_API_KEY` (for the Firecrawl fallback)
-- Optional: `XAI_API_KEY` / `OPENAI_API_KEY` / `GEMINI_API_KEY` (also accepts `GOOGLE_GENERATIVE_AI_API_KEY` / `GOOGLE_API_KEY`) (required only when `--markdown llm` is used, or when `--markdown auto` falls back to LLM conversion)
+- Optional: `FIRECRAWL_API_KEY` (for the Firecrawl fallback / preferred Markdown output)
+- Optional: `XAI_API_KEY` / `OPENAI_API_KEY` / `GEMINI_API_KEY` (also accepts `GOOGLE_GENERATIVE_AI_API_KEY` / `GOOGLE_API_KEY`) (required only when `--markdown-mode llm` is used, or when `--markdown-mode auto` falls back to LLM conversion)

package/docs/youtube.md

@@ -31,5 +31,5 @@ YouTube URLs use transcript-first extraction.
 ## Example
 
 ```bash
-pnpm summarize -- --extract-only "https://www.youtube.com/watch?v=I845O57ZSy4&t=11s"
+pnpm summarize -- --extract "https://www.youtube.com/watch?v=I845O57ZSy4&t=11s"
 ```

package/package.json

@@ -1,10 +1,11 @@
 {
   "name": "@steipete/summarize",
-  "version": "0.3.0",
+  "version": "0.5.0",
   "description": "Link → clean text → summary.",
   "type": "module",
   "bin": {
-    "summarize": "./dist/cli.cjs"
+    "summarize": "./dist/cli.cjs",
+    "summarizer": "./dist/cli.cjs"
   },
   "main": "./dist/esm/index.js",
   "module": "./dist/esm/index.js",
@@ -38,6 +39,7 @@
     "cheerio": "^1.1.2",
     "es-toolkit": "^1.43.0",
     "gpt-tokenizer": "^3.4.0",
+    "json5": "^2.2.3",
     "sanitize-html": "^2.17.0"
   },
   "devDependencies": {
@@ -57,6 +59,8 @@
     "mime": "^4.1.0",
     "ora": "^9.0.0",
     "osc-progress": "^0.1.0",
+    "oxlint": "^1.35.0",
+    "oxlint-tsgolint": "^0.10.0",
     "tokentally": "github:steipete/tokentally#v0.1.0",
     "tsx": "^4.21.0",
     "typescript": "^5.9.3",
@@ -71,8 +75,8 @@
     "typecheck": "tsc -p tsconfig.build.json --noEmit",
     "summarize": "tsx src/cli.ts",
     "format": "biome format --write .",
-    "lint": "biome check .",
-    "lint:fix": "biome check --write .",
+    "lint": "biome check . && oxlint --type-aware --tsconfig tsconfig.build.json --config .oxlintrc.json .",
+    "lint:fix": "biome check --write . && oxlint --type-aware --tsconfig tsconfig.build.json --config .oxlintrc.json --fix .",
     "check": "pnpm lint && pnpm test:coverage",
     "test": "pnpm build && vitest run",
     "test:coverage": "pnpm build && vitest run --coverage",

package/dist/esm/content/link-preview/transcript/providers/twitter.js

@@ -1,12 +0,0 @@
-const TWITTER_URL_PATTERN = /twitter\.com|x\.com/i;
-export const canHandle = ({ url }) => TWITTER_URL_PATTERN.test(url);
-export const fetchTranscript = async (_context, _options) => {
-    await Promise.resolve();
-    return {
-        text: null,
-        source: null,
-        attemptedProviders: [],
-        metadata: { provider: 'twitter', reason: 'not_implemented' },
-    };
-};
-//# sourceMappingURL=twitter.js.map

package/dist/esm/content/link-preview/transcript/providers/twitter.js.map

@@ -1 +0,0 @@
-{"version":3,"file":"twitter.js","sourceRoot":"","sources":["../../../../../../src/content/link-preview/transcript/providers/twitter.ts"],"names":[],"mappings":"AAEA,MAAM,mBAAmB,GAAG,sBAAsB,CAAA;AAElD,MAAM,CAAC,MAAM,SAAS,GAAG,CAAC,EAAE,GAAG,EAAmB,EAAW,EAAE,CAAC,mBAAmB,CAAC,IAAI,CAAC,GAAG,CAAC,CAAA;AAE7F,MAAM,CAAC,MAAM,eAAe,GAAG,KAAK,EAClC,QAAyB,EACzB,QAA8B,EACL,EAAE;IAC3B,MAAM,OAAO,CAAC,OAAO,EAAE,CAAA;IACvB,OAAO;QACL,IAAI,EAAE,IAAI;QACV,MAAM,EAAE,IAAI;QACZ,kBAAkB,EAAE,EAAE;QACtB,QAAQ,EAAE,EAAE,QAAQ,EAAE,SAAS,EAAE,MAAM,EAAE,iBAAiB,EAAE;KAC7D,CAAA;AACH,CAAC,CAAA"}

package/dist/esm/content/link-preview/transcript/providers/youtube/ytdlp.js

@@ -1,114 +0,0 @@
-import { execFile } from 'node:child_process';
-import { promisify } from 'node:util';
-import { fetchWithTimeout } from '../../../fetch-with-timeout.js';
-import { sanitizeYoutubeJsonResponse } from '../../utils.js';
-const execFileAsync = promisify(execFile);
-const isRecord = (value) => typeof value === 'object' && value !== null && !Array.isArray(value);
-const parseJson3Transcript = (raw) => {
-    try {
-        const parsed = JSON.parse(raw);
-        if (!isRecord(parsed)) {
-            return null;
-        }
-        const eventsUnknown = parsed.events;
-        if (!Array.isArray(eventsUnknown)) {
-            return null;
-        }
-        const lines = [];
-        for (const event of eventsUnknown) {
-            if (!isRecord(event)) {
-                continue;
-            }
-            const eventRecord = event;
-            const segs = Array.isArray(eventRecord.segs) ? eventRecord.segs : null;
-            if (!segs) {
-                continue;
-            }
-            const text = segs
-                .map((seg) => {
-                if (!isRecord(seg)) {
-                    return '';
-                }
-                const segRecord = seg;
-                return typeof segRecord.utf8 === 'string' ? segRecord.utf8 : '';
-            })
-                .join('')
-                .trim();
-            if (text.length > 0) {
-                lines.push(text);
-            }
-        }
-        const transcript = lines.join('\n').trim();
-        return transcript.length > 0 ? transcript : null;
-    }
-    catch {
-        return null;
-    }
-};
-function pickCaptionUrl(info) {
-    const sources = [info.subtitles, info.automatic_captions];
-    const candidates = [];
-    for (const source of sources) {
-        if (!isRecord(source))
-            continue;
-        for (const [lang, entries] of Object.entries(source)) {
-            candidates.push([lang, entries]);
-        }
-    }
-    const languagePreference = (lang) => {
-        const lower = lang.toLowerCase();
-        if (lower === 'en')
-            return 0;
-        if (lower.startsWith('en-'))
-            return 1;
-        if (lower.startsWith('en'))
-            return 2;
-        return 10;
-    };
-    const sorted = candidates.toSorted(([a], [b]) => languagePreference(a) - languagePreference(b));
-    for (const [, entries] of sorted) {
-        if (!Array.isArray(entries))
-            continue;
-        const normalized = entries.filter((entry) => isRecord(entry));
-        const json3 = normalized.find((entry) => entry.ext === 'json3' && typeof entry.url === 'string');
-        if (json3?.url && typeof json3.url === 'string') {
-            return json3.url;
-        }
-        const vtt = normalized.find((entry) => entry.ext === 'vtt' && typeof entry.url === 'string');
-        if (vtt?.url && typeof vtt.url === 'string') {
-            return vtt.url;
-        }
-    }
-    return null;
-}
-export async function fetchTranscriptWithYtDlp(fetchImpl, url, { timeoutMs } = {}) {
-    try {
-        const { stdout } = await execFileAsync('yt-dlp', ['--dump-single-json', '--no-playlist', '--no-warnings', url], { timeout: typeof timeoutMs === 'number' && Number.isFinite(timeoutMs) ? timeoutMs : 60_000 });
-        const parsed = JSON.parse(stdout);
-        if (!isRecord(parsed)) {
-            return null;
-        }
-        const info = parsed;
-        const captionUrl = pickCaptionUrl(info);
-        if (!captionUrl) {
-            return null;
-        }
-        const response = await fetchWithTimeout(fetchImpl, captionUrl, undefined, 60_000);
-        if (!response.ok) {
-            return null;
-        }
-        const raw = await response.text();
-        const sanitized = sanitizeYoutubeJsonResponse(raw);
-        return parseJson3Transcript(sanitized);
-    }
-    catch (error) {
-        const code = error && typeof error === 'object' && 'code' in error
-            ? error.code
-            : null;
-        if (code === 'ENOENT') {
-            return null;
-        }
-        return null;
-    }
-}
-//# sourceMappingURL=ytdlp.js.map