@steipete/summarize 0.8.2 → 0.10.0

package/docs/website.md

@@ -14,11 +14,24 @@ Use this for non-YouTube URLs.
 - Extracts “article-ish” content and normalizes it into clean text.
 - If extraction looks blocked or too thin, it can retry via Firecrawl (Markdown).
 - If a page is effectively “video-only”, it may treat it as a video input (see `--video-mode`).
+- `--video-mode transcript` prefers embedded media transcripts on pages with audio/video (captions → yt-dlp/Whisper fallback).
 - With `--format md`, the CLI defaults to `--markdown-mode readability` (Readability article HTML as the Markdown input).
   - Use `--firecrawl always` to try Firecrawl first.
 - With `--format md`, `--markdown-mode auto|llm|readability` 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`).
 - For podcast URLs (Apple Podcasts, RSS, Spotify episodes), it downloads the episode audio and transcribes via Whisper (prefers local `whisper.cpp` when installed + model available); progress shows “Downloading audio …” then “Transcribing …” (duration uses RSS hints or `ffprobe` when available).
+ 
+Daemon note:
+- `/v1/summarize` accepts `format: "markdown"` plus `markdownMode`/`preprocess` to return extracted Markdown (especially when `extractOnly: true`).
+
+## Short content
+
+- If extracted content is shorter than the requested summary length, summarize returns the content as-is.
+- Use `--force-summary` to override and always run the LLM.
+
+## Twitter/X
+
+- Tweet audio transcription runs only with `--video-mode transcript` (auto mode skips yt-dlp for tweets).
 
 ## Flags
 

package/docs/youtube.md

@@ -40,3 +40,19 @@ YouTube URLs use transcript-first extraction.
 ```bash
 pnpm summarize -- --extract "https://www.youtube.com/watch?v=I845O57ZSy4&t=11s"
 ```
+
+## Slides
+
+Use `--slides` to extract slide screenshots for YouTube videos (requires `ffmpeg` and `yt-dlp`).
+Scene detection auto-tunes the threshold using sampled frame hashes:
+
+```bash
+summarize "https://www.youtube.com/watch?v=..." --slides
+summarize "https://www.youtube.com/watch?v=..." --slides --slides-ocr
+```
+
+Slides are written to `./slides/<videoId>/` by default (override with `--slides-dir`). OCR results
+are stored in `slides.json` and included in JSON output (`--json`).
+
+Relevant flags:
+- `--slides-scene-threshold <value>`: starting threshold for scene detection (auto-tuned as needed)

package/package.json

@@ -1,6 +1,6 @@
 {
   "name": "@steipete/summarize",
-  "version": "0.8.2",
+  "version": "0.10.0",
   "description": "Link → clean text → summary.",
   "type": "module",
   "bin": {
@@ -35,34 +35,36 @@
     "node": ">=22"
   },
   "dependencies": {
-    "@mariozechner/pi-ai": "^0.30.2",
+    "@mariozechner/pi-ai": "^0.49.2",
     "commander": "^14.0.2",
-    "file-type": "^21.2.0",
+    "file-type": "^21.3.0",
     "gpt-tokenizer": "^3.4.0",
     "json5": "^2.2.3",
-    "markdansi": "^0.2.0",
+    "markdansi": "^0.2.1",
     "mime": "^4.1.0",
-    "ora": "^9.0.0",
-    "osc-progress": "github:steipete/osc-progress#v0.2.0",
-    "tokentally": "github:steipete/tokentally#v0.1.0",
-    "@steipete/summarize-core": "0.8.2"
+    "ora": "^9.1.0",
+    "osc-progress": "^0.3.0",
+    "tokentally": "^0.1.1",
+    "tslog": "^4.10.2",
+    "@steipete/summarize-core": "0.10.0"
   },
   "devDependencies": {
-    "@biomejs/biome": "^2.3.10",
-    "@fal-ai/client": "^1.8.1",
+    "@biomejs/biome": "^2.3.11",
+    "@fal-ai/client": "^1.8.3",
     "@types/jsdom": "^27.0.0",
-    "@types/node": "^25.0.3",
+    "@types/node": "^25.0.9",
     "@types/sanitize-html": "^2.16.0",
-    "@vitest/coverage-v8": "^4.0.16",
+    "@vitest/coverage-v8": "^4.0.17",
     "esbuild": "^0.27.2",
-    "oxlint": "^1.35.0",
-    "oxlint-tsgolint": "^0.10.0",
+    "oxlint": "^1.41.0",
+    "oxlint-tsgolint": "^0.11.1",
+    "rimraf": "^6.1.2",
     "tsx": "^4.21.0",
     "typescript": "^5.9.3",
-    "vitest": "^4.0.16"
+    "vitest": "^4.0.17"
   },
   "scripts": {
-    "clean": "rm -rf dist packages/core/dist",
+    "clean": "rimraf dist packages/core/dist",
     "build": "pnpm clean && pnpm -C packages/core build && pnpm build:lib && pnpm build:cli",
     "build:lib": "tsc -p tsconfig.build.json",
     "build:cli": "node scripts/build-cli.mjs",
@@ -76,8 +78,10 @@
     "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",
+    "test:extension-e2e": "pnpm -C apps/chrome-extension test:e2e",
+    "test": "vitest run",
+    "test:coverage": "vitest run --coverage",
+    "test:coverage:build": "pnpm build && pnpm test:coverage",
     "release": "bash scripts/release.sh"
   }
 }

package/dist/esm/daemon/request-settings.js

@@ -1,91 +0,0 @@
-import { parseDurationMs, parseFirecrawlMode, parseLengthArg, parseMarkdownMode, parseMaxOutputTokensArg, parsePreprocessMode, parseRetriesArg, parseYoutubeMode, } from '../flags.js';
-import { resolveOutputLanguage } from '../language.js';
-export function resolveDaemonSummaryLength(raw) {
-    const value = typeof raw === 'string' ? raw.trim() : '';
-    const lengthArg = parseLengthArg(value || 'xl');
-    const summaryLength = lengthArg.kind === 'preset' ? lengthArg.preset : { maxCharacters: lengthArg.maxCharacters };
-    return { lengthArg, summaryLength };
-}
-export function resolveDaemonOutputLanguage({ raw, fallback, }) {
-    const value = typeof raw === 'string' ? raw.trim() : '';
-    if (!value)
-        return fallback;
-    return resolveOutputLanguage(value);
-}
-export function resolveDaemonYoutubeMode(raw) {
-    if (typeof raw !== 'string')
-        return null;
-    try {
-        return parseYoutubeMode(raw);
-    }
-    catch {
-        return null;
-    }
-}
-export function resolveDaemonFirecrawlMode(raw) {
-    if (typeof raw !== 'string')
-        return null;
-    try {
-        return parseFirecrawlMode(raw);
-    }
-    catch {
-        return null;
-    }
-}
-export function resolveDaemonMarkdownMode(raw) {
-    if (typeof raw !== 'string')
-        return null;
-    try {
-        return parseMarkdownMode(raw);
-    }
-    catch {
-        return null;
-    }
-}
-export function resolveDaemonPreprocessMode(raw) {
-    if (typeof raw !== 'string')
-        return null;
-    try {
-        return parsePreprocessMode(raw);
-    }
-    catch {
-        return null;
-    }
-}
-export function resolveDaemonTimeoutMs(raw) {
-    if (typeof raw === 'number' && Number.isFinite(raw) && raw > 0)
-        return Math.floor(raw);
-    if (typeof raw !== 'string')
-        return null;
-    try {
-        return parseDurationMs(raw);
-    }
-    catch {
-        return null;
-    }
-}
-export function resolveDaemonRetries(raw) {
-    if (typeof raw === 'number' && Number.isFinite(raw) && Number.isInteger(raw))
-        return raw;
-    if (typeof raw !== 'string')
-        return null;
-    try {
-        return parseRetriesArg(raw);
-    }
-    catch {
-        return null;
-    }
-}
-export function resolveDaemonMaxOutputTokens(raw) {
-    if (typeof raw === 'number' && Number.isFinite(raw) && raw > 0)
-        return Math.floor(raw);
-    if (typeof raw !== 'string')
-        return null;
-    try {
-        return parseMaxOutputTokensArg(raw);
-    }
-    catch {
-        return null;
-    }
-}
-//# sourceMappingURL=request-settings.js.map

package/dist/esm/daemon/request-settings.js.map

@@ -1 +0,0 @@
-{"version":3,"file":"request-settings.js","sourceRoot":"","sources":["../../../src/daemon/request-settings.ts"],"names":[],"mappings":"AAOA,OAAO,EACL,eAAe,EACf,kBAAkB,EAClB,cAAc,EACd,iBAAiB,EACjB,uBAAuB,EACvB,mBAAmB,EACnB,eAAe,EACf,gBAAgB,GACjB,MAAM,aAAa,CAAA;AAEpB,OAAO,EAAE,qBAAqB,EAAE,MAAM,gBAAgB,CAAA;AAatD,MAAM,UAAU,0BAA0B,CAAC,GAAY;IAIrD,MAAM,KAAK,GAAG,OAAO,GAAG,KAAK,QAAQ,CAAC,CAAC,CAAC,GAAG,CAAC,IAAI,EAAE,CAAC,CAAC,CAAC,EAAE,CAAA;IACvD,MAAM,SAAS,GAAG,cAAc,CAAC,KAAK,IAAI,IAAI,CAAC,CAAA;IAC/C,MAAM,aAAa,GACjB,SAAS,CAAC,IAAI,KAAK,QAAQ,CAAC,CAAC,CAAC,SAAS,CAAC,MAAM,CAAC,CAAC,CAAC,EAAE,aAAa,EAAE,SAAS,CAAC,aAAa,EAAE,CAAA;IAC7F,OAAO,EAAE,SAAS,EAAE,aAAa,EAAE,CAAA;AACrC,CAAC;AAED,MAAM,UAAU,2BAA2B,CAAC,EAC1C,GAAG,EACH,QAAQ,GAIT;IACC,MAAM,KAAK,GAAG,OAAO,GAAG,KAAK,QAAQ,CAAC,CAAC,CAAC,GAAG,CAAC,IAAI,EAAE,CAAC,CAAC,CAAC,EAAE,CAAA;IACvD,IAAI,CAAC,KAAK;QAAE,OAAO,QAAQ,CAAA;IAC3B,OAAO,qBAAqB,CAAC,KAAK,CAAC,CAAA;AACrC,CAAC;AAED,MAAM,UAAU,wBAAwB,CAAC,GAAY;IACnD,IAAI,OAAO,GAAG,KAAK,QAAQ;QAAE,OAAO,IAAI,CAAA;IACxC,IAAI,CAAC;QACH,OAAO,gBAAgB,CAAC,GAAG,CAAC,CAAA;IAC9B,CAAC;IAAC,MAAM,CAAC;QACP,OAAO,IAAI,CAAA;IACb,CAAC;AACH,CAAC;AAED,MAAM,UAAU,0BAA0B,CAAC,GAAY;IACrD,IAAI,OAAO,GAAG,KAAK,QAAQ;QAAE,OAAO,IAAI,CAAA;IACxC,IAAI,CAAC;QACH,OAAO,kBAAkB,CAAC,GAAG,CAAC,CAAA;IAChC,CAAC;IAAC,MAAM,CAAC;QACP,OAAO,IAAI,CAAA;IACb,CAAC;AACH,CAAC;AAED,MAAM,UAAU,yBAAyB,CAAC,GAAY;IACpD,IAAI,OAAO,GAAG,KAAK,QAAQ;QAAE,OAAO,IAAI,CAAA;IACxC,IAAI,CAAC;QACH,OAAO,iBAAiB,CAAC,GAAG,CAAC,CAAA;IAC/B,CAAC;IAAC,MAAM,CAAC;QACP,OAAO,IAAI,CAAA;IACb,CAAC;AACH,CAAC;AAED,MAAM,UAAU,2BAA2B,CAAC,GAAY;IACtD,IAAI,OAAO,GAAG,KAAK,QAAQ;QAAE,OAAO,IAAI,CAAA;IACxC,IAAI,CAAC;QACH,OAAO,mBAAmB,CAAC,GAAG,CAAC,CAAA;IACjC,CAAC;IAAC,MAAM,CAAC;QACP,OAAO,IAAI,CAAA;IACb,CAAC;AACH,CAAC;AAED,MAAM,UAAU,sBAAsB,CAAC,GAAY;IACjD,IAAI,OAAO,GAAG,KAAK,QAAQ,IAAI,MAAM,CAAC,QAAQ,CAAC,GAAG,CAAC,IAAI,GAAG,GAAG,CAAC;QAAE,OAAO,IAAI,CAAC,KAAK,CAAC,GAAG,CAAC,CAAA;IACtF,IAAI,OAAO,GAAG,KAAK,QAAQ;QAAE,OAAO,IAAI,CAAA;IACxC,IAAI,CAAC;QACH,OAAO,eAAe,CAAC,GAAG,CAAC,CAAA;IAC7B,CAAC;IAAC,MAAM,CAAC;QACP,OAAO,IAAI,CAAA;IACb,CAAC;AACH,CAAC;AAED,MAAM,UAAU,oBAAoB,CAAC,GAAY;IAC/C,IAAI,OAAO,GAAG,KAAK,QAAQ,IAAI,MAAM,CAAC,QAAQ,CAAC,GAAG,CAAC,IAAI,MAAM,CAAC,SAAS,CAAC,GAAG,CAAC;QAAE,OAAO,GAAG,CAAA;IACxF,IAAI,OAAO,GAAG,KAAK,QAAQ;QAAE,OAAO,IAAI,CAAA;IACxC,IAAI,CAAC;QACH,OAAO,eAAe,CAAC,GAAG,CAAC,CAAA;IAC7B,CAAC;IAAC,MAAM,CAAC;QACP,OAAO,IAAI,CAAA;IACb,CAAC;AACH,CAAC;AAED,MAAM,UAAU,4BAA4B,CAAC,GAAY;IACvD,IAAI,OAAO,GAAG,KAAK,QAAQ,IAAI,MAAM,CAAC,QAAQ,CAAC,GAAG,CAAC,IAAI,GAAG,GAAG,CAAC;QAAE,OAAO,IAAI,CAAC,KAAK,CAAC,GAAG,CAAC,CAAA;IACtF,IAAI,OAAO,GAAG,KAAK,QAAQ;QAAE,OAAO,IAAI,CAAA;IACxC,IAAI,CAAC;QACH,OAAO,uBAAuB,CAAC,GAAG,CAAC,CAAA;IACrC,CAAC;IAAC,MAAM,CAAC;QACP,OAAO,IAAI,CAAA;IACb,CAAC;AACH,CAAC"}

package/dist/types/daemon/request-settings.d.ts

@@ -1,27 +0,0 @@
-import type { FirecrawlMode, LengthArg, MarkdownMode, PreprocessMode, YoutubeMode } from '../flags.js';
-import type { OutputLanguage } from '../language.js';
-import type { SummaryLengthTarget } from '../prompts/index.js';
-export type DaemonRunOverrides = {
-    firecrawlMode: FirecrawlMode | null;
-    markdownMode: MarkdownMode | null;
-    preprocessMode: PreprocessMode | null;
-    youtubeMode: YoutubeMode | null;
-    timeoutMs: number | null;
-    retries: number | null;
-    maxOutputTokensArg: number | null;
-};
-export declare function resolveDaemonSummaryLength(raw: unknown): {
-    lengthArg: LengthArg;
-    summaryLength: SummaryLengthTarget;
-};
-export declare function resolveDaemonOutputLanguage({ raw, fallback, }: {
-    raw: unknown;
-    fallback: OutputLanguage;
-}): OutputLanguage;
-export declare function resolveDaemonYoutubeMode(raw: unknown): YoutubeMode | null;
-export declare function resolveDaemonFirecrawlMode(raw: unknown): FirecrawlMode | null;
-export declare function resolveDaemonMarkdownMode(raw: unknown): MarkdownMode | null;
-export declare function resolveDaemonPreprocessMode(raw: unknown): PreprocessMode | null;
-export declare function resolveDaemonTimeoutMs(raw: unknown): number | null;
-export declare function resolveDaemonRetries(raw: unknown): number | null;
-export declare function resolveDaemonMaxOutputTokens(raw: unknown): number | null;