@steipete/summarize 0.9.0 → 0.11.0

package/docs/assets/site.js

@@ -0,0 +1,72 @@
+const canonicalHost = "summarize.sh";
+const redirectHostnames = new Set(["summarize.is", "www.summarize.is"]);
+
+const maybeRedirect = () => {
+  try {
+    const { hostname, pathname, search, hash } = window.location;
+    if (!redirectHostnames.has(hostname)) return;
+    const target = `https://${canonicalHost}${pathname}${search}${hash}`;
+    window.location.replace(target);
+  } catch {
+    // ignore
+  }
+};
+
+const highlightNav = () => {
+  const path = window.location.pathname;
+  const isDocs = path.includes("/docs/");
+  const navDocs = document.querySelector('a[data-nav="docs"]');
+  const navHome = document.querySelector('a[data-nav="home"]');
+  if (navDocs && isDocs) navDocs.setAttribute("aria-current", "page");
+  if (navHome && !isDocs) navHome.setAttribute("aria-current", "page");
+
+  const sideLinks = document.querySelectorAll(".side a[href]");
+  for (const a of sideLinks) {
+    const href = a.getAttribute("href") ?? "";
+    if (!href) continue;
+    const normalized = href.replace(/^\.\//, "");
+    if (path.endsWith(normalized)) a.setAttribute("aria-current", "page");
+  }
+};
+
+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", () => {
+      void handleCopyClick(button);
+    });
+  }
+};
+
+const reveal = () => {
+  const items = document.querySelectorAll(".reveal");
+  let i = 0;
+  for (const el of items) {
+    const delay = Math.min(380, i * 70);
+    window.setTimeout(() => el.classList.add("is-on"), delay);
+    i++;
+  }
+};
+
+maybeRedirect();
+highlightNav();
+wireCopyButtons();
+reveal();

package/docs/cache.md

@@ -21,15 +21,28 @@ Lightweight, CLI-only SQLite cache. Single DB file.
 - Override: `cache.path` in config.
 - SQLite pragmas: WAL, NORMAL sync, busy timeout, incremental vacuum.
 
+## Media cache (downloads)
+
+Separate file cache for downloaded media (yt-dlp, direct media URLs). This is **not** the SQLite DB.
+
+- Default path: `~/.summarize/cache/media`
+- TTL: 7 days
+- Size cap: 2048 MB
+- Config: `cache.media` (see below)
+- CLI: `--no-media-cache` disables media caching only
+- Note: `--no-cache` **does not** disable the media cache
+
 ## What we cache
 
 - **Transcripts**
-  - key: `sha256({url, namespace, formatVersion})`
+  - key: `sha256({url, namespace, fileMtime?, formatVersion})` (local file paths include `fileMtime` for invalidation)
 - **Extracted content** (URL → text/markdown)
   - key: `sha256({url, extractSettings, formatVersion})`
 - **Summaries**
   - key: `sha256({contentHash, promptHash, model, length, language, formatVersion})`
   - cache hit even if URL differs (content hash wins).
+- **Slides** (manifest + on-disk images in the slides output dir)
+  - key: `sha256({url, slideSettings, formatVersion})`
 
 ## Keys / hashes
 
@@ -46,7 +59,14 @@ Lightweight, CLI-only SQLite cache. Single DB file.
     "enabled": true,
     "maxMb": 512,
     "ttlDays": 30,
-    "path": "~/.summarize/cache.sqlite"
+    "path": "~/.summarize/cache.sqlite",
+    "media": {
+      "enabled": true,
+      "maxMb": 2048,
+      "ttlDays": 7,
+      "path": "~/.summarize/cache/media",
+      "verify": "size"
+    }
   }
 }
 ```
@@ -55,7 +75,7 @@ Defaults: `enabled=true`, `maxMb=512`, `ttlDays=30`, `path` unset.
 
 ## CLI flags
 
-- `--no-cache`: bypass read + write.
+- `--no-cache`: bypass summary cache reads + writes (LLM output). Extract/transcript caches still apply.
 - `--cache-stats`: print cache stats and exit.
 - `--clear-cache`: delete cache DB (and WAL/SHM); must be used alone.
 
@@ -65,6 +85,12 @@ Defaults: `enabled=true`, `maxMb=512`, `ttlDays=30`, `path` unset.
 - Size cap: if DB > `maxMb`, delete oldest entries by `last_accessed_at` until under cap.
 - Optional count cap if needed later.
 
+Media cache eviction:
+
+- TTL sweep on read/write.
+- Size cap: evict least-recently-used files until under cap.
+- `verify` controls integrity checks: `size` (default), `hash`, or `none`.
+
 ## Notes
 
 - No extension cache (daemon uses CLI cache).

package/docs/chrome-extension.md

@@ -4,7 +4,7 @@ read_when:
   - "When working on the extension, daemon, or side panel UX."
 ---
 
-# Chrome Side Panel (Chrome Extension + Daemon)
+# Browser Side Panel (Chrome + Firefox Extension + Daemon)
 
 Goal: Chrome **Side Panel** (“real sidebar”) summarizes **what you see** on the current tab. Panel open → navigation → auto summarize (optional) → **streaming** Markdown rendered in-panel.
 
@@ -14,12 +14,19 @@ Quickstart:
   - `npm i -g @steipete/summarize`
   - `brew install steipete/tap/summarize` (macOS arm64)
 - Build/load extension: `apps/chrome-extension/README.md`
+- Firefox sidebar build: `pnpm -C apps/chrome-extension build:firefox` (load via `about:debugging` → temporary add-on)
 - Open side panel → copy token install command → run:
   - `summarize daemon install --token <TOKEN>` (macOS: LaunchAgent, Linux: systemd user, Windows: Scheduled Task)
 - Verify:
   - `summarize daemon status`
   - Restart (if needed): `summarize daemon restart`
 
+Firefox notes:
+
+- Sidebar UX differs from Chrome’s side panel (persistent sidebar instead of slide-in panel).
+- Firefox testing is limited in Playwright; see `apps/chrome-extension/tests/README-firefox.md`.
+- Compatibility details: `apps/chrome-extension/docs/firefox.md`.
+
 Dev (repo checkout):
 
 - Use: `pnpm summarize daemon install --token <TOKEN> --dev` (autostart service runs `src/cli.ts` via `tsx`, no `dist/` build required).
@@ -32,6 +39,13 @@ Dev (repo checkout):
 - “Daemon not reachable”:
   - `summarize daemon status`
   - Logs: `~/.summarize/logs/daemon.err.log`
+- macOS `launchctl bootstrap` errors (`Input/output error`, `Domain does not support specified action`):
+  - `summarize daemon install` now tries both launchd domains (`gui/<uid>` then `user/<uid>`).
+  - Install as your normal user (not root) so HOME + launchd domain match.
+  - Re-run: `summarize daemon install --token <TOKEN>`.
+- “Need extension-side traces”:
+  - Options → Logs → `extension.log` (panel/background events).
+  - Enable “Extended logging” in Advanced settings for full pipeline traces.
 - “Stream ended unexpectedly” / empty chat response:
   - The daemon likely stopped mid-stream. Restart it, then click “Try again”.
   - `summarize daemon restart`
@@ -61,11 +75,11 @@ Dev (repo checkout):
 
 ## Data Flow
 
-1) User opens side panel (click extension icon).
-2) Panel sends a “ready” message to the background (plus periodic “ping” heartbeats while open).
-3) On nav/tab change (and auto enabled): background asks the content script to extract `{ url, title, text }` (best-effort).
-4) Background `POST`s payload to daemon `/v1/summarize` with `Authorization: Bearer <token>`.
-5) Panel opens `/v1/summarize/<id>/events` (SSE) and renders streamed Markdown.
+1. User opens side panel (click extension icon).
+2. Panel sends a “ready” message to the background (plus periodic “ping” heartbeats while open).
+3. On nav/tab change (and auto enabled): background asks the content script to extract `{ url, title, text }` (best-effort).
+4. Background `POST`s payload to daemon `/v1/summarize` with `Authorization: Bearer <token>`.
+5. Panel opens `/v1/summarize/<id>/events` (SSE) and renders streamed Markdown.
 
 ## Auto Mode (URL + Page Text)
 
@@ -87,6 +101,12 @@ When the page contains embedded audio/video, the Summarize button gains a dropdo
 
 See `docs/media.md` for detection and transcript rules.
 
+## Slides (Side Panel)
+
+- The slides toggle lights up on media-friendly URLs (YouTube/watch|shorts, youtu.be, direct media) or when the page reports video/audio. Defaults to Video on those pages.
+- Turning slides **on** refreshes the current summary and requests slide extraction (`yt-dlp`, `ffmpeg`). OCR text is opt-in (Advanced setting) and requires `tesseract`. Missing tools surface a footer notice with install instructions; restart the daemon after installing.
+- Slides stay off elsewhere and the toggle is disabled on non-media pages.
+
 ## SPA Navigation
 
 - Background listens to `chrome.webNavigation.onHistoryStateUpdated` (SPA route changes) and `tabs.onUpdated` (page loads).
@@ -99,6 +119,11 @@ See `docs/media.md` for detection and transcript rules.
 - `linkify: true`.
 - Render links with `target=_blank` + `rel=noopener noreferrer`.
 
+## Timestamp Links (Chat)
+
+- When timed transcripts are available, chat context includes `[mm:ss]` lines.
+- Assistant is prompted to cite timestamps; clicking them seeks the current media (video/audio) while preserving play/pause state.
+
 ## Model Selection UX
 
 - Settings:
@@ -109,17 +134,21 @@ See `docs/media.md` for detection and transcript rules.
   - Auto summarize: on/off.
   - Hover summaries: on/off (side panel drawer, default off).
   - Typography: font family (dropdown + custom), font size (slider).
-- Advanced overrides (collapsed by default; click the section title to expand).
+- Advanced overrides (Options → Advanced tab).
   - Leave blank to use daemon config/defaults; set a value to override.
   - Chat (advanced): enable/disable the side panel chat input (default on; summary is the first message).
+  - Summary timestamps (advanced): include `[mm:ss]` links in summaries for media when available (default on).
+  - Slides parallel (advanced): show summary first and extract slides in parallel (default on).
+  - Slides OCR text (advanced): allow OCR text as a slide text source (default off).
   - Extended logging: send full input/output to daemon logs (requires daemon logging enabled).
   - Hover summary prompt: customize the prompt used for link hover summaries (prefilled; reset to default).
   - Pipeline mode: `page|url` (default auto).
   - Firecrawl: `off|auto|always`.
   - Markdown mode: `readability|llm|auto|off`.
-  - Preprocess: `off|auto|always`.
-  - YouTube mode: `no-auto|yt-dlp|web|apify` (default auto).
-  - Timeout (e.g. `90s`, `2m`), retries, max output tokens (e.g. `2k`).
+- Preprocess: `off|auto|always`.
+- YouTube mode: `no-auto|yt-dlp|web|apify` (default auto).
+- Timeout (e.g. `90s`, `2m`), retries, max output tokens (e.g. `2k`).
+- Process manager: live list of daemon-spawned tools (ffmpeg, yt-dlp, tesseract, etc.) with logs.
 - Extension includes current settings in request; daemon treats them like CLI flags (`--model`, `--length`, `--language`, `--prompt`).
 
 ## Token Pairing / Setup Mode
@@ -152,20 +181,46 @@ Problem: daemon must be secured; extension must discover and pair with it.
     - `language?: string` (e.g. `auto`, `en`, `de`, `pt-BR`)
     - `prompt?: string` (custom instruction prefix)
     - `mode?: "auto" | "page" | "url"` (default: `"auto"`)
-    - `maxCharacters?: number | null` (caps URL-mode extraction before summarization)
+    - `maxCharacters?: number | null` (caps URL-mode extraction before summarization; ignored for extract-only unless explicitly provided)
+    - `format?: "text" | "markdown"` (default: `"text"`)
+    - `markdownMode?: "readability" | "auto" | "llm" | "off"` (only when `format: "markdown"`)
+    - `preprocess?: "off" | "auto" | "always"` (markitdown/HTML preprocess)
     - `extractOnly?: boolean` (when `true`, returns extracted content without summarizing; requires `mode: "url"`)
     - `text?: string` (required for `mode: "page"`; optional for `auto`)
     - `truncated?: boolean` (optional; indicates extracted `text` was shortened)
   - 200 JSON: `{ ok: true, id }`
-- `POST /v1/chat`
+- `GET /v1/summarize/<id>/slides/events`
+  - Headers: `Authorization: Bearer <token>`
+  - SSE stream of slide updates (`slides`, `status`, `done`, `error`) independent of summary stream.
+- `POST /v1/agent` (SSE by default; JSON via `Accept: application/json` or `?format=json`)
   - Headers: `Authorization: Bearer <token>`
   - Body:
     - `url: string` (required)
     - `title?: string | null`
-    - `pageContent: string` (extracted page content / transcript)
-    - `messages: Array<{ role: "user" | "assistant"; content: string }>`
-    - `model?: string` (same as `/v1/summarize`, optional)
-  - 200 JSON: `{ ok: true, id }` (stream via `/v1/summarize/:id/events`)
+    - `pageContent: string`
+    - `cacheContent?: string` (used for cache key; defaults to `pageContent`)
+    - `messages: Array<Message>` (pi-ai format)
+    - `model?: string`
+    - `length?: string` (e.g. `short`, `xl`, `20k`)
+    - `language?: string` (e.g. `auto`, `en`, `de`)
+    - `tools?: string[]`
+    - `automationEnabled?: boolean`
+  - SSE events:
+    - `event: chunk` `data: { text }`
+    - `event: assistant` `data: { ...assistant }`
+    - `event: done` `data: {}`
+    - `event: error` `data: { message }`
+- `POST /v1/agent/history`
+  - Headers: `Authorization: Bearer <token>`
+  - Body:
+    - `url: string` (required)
+    - `pageContent: string`
+    - `cacheContent?: string` (used for cache key; defaults to `pageContent`)
+    - `model?: string`
+    - `length?: string`
+    - `language?: string`
+    - `automationEnabled?: boolean`
+  - 200 JSON: `{ ok: true, messages }`
 - `GET /v1/summarize/:id/events` (SSE)
   - `event: chunk` `data: { text }`
   - `event: meta` `data: { model }`
@@ -175,6 +230,7 @@ Problem: daemon must be secured; extension must discover and pair with it.
   - `event: error` `data: { message }`
 
 Notes:
+
 - SSE keeps the extension simple + streaming-friendly.
 - Requests keyed by `id`; daemon keeps a small in-memory map while streaming.
 

package/docs/cli.md

@@ -1,35 +1,39 @@
 ---
-summary: "CLI model providers and config for Claude, Codex, and Gemini."
+summary: "CLI model providers and config for Claude, Codex, Gemini, and Cursor Agent."
 read_when:
   - "When changing CLI model integration."
 ---
 
 # CLI models
 
-Summarize can use installed CLIs (Claude, Codex, Gemini) as local model backends.
+Summarize can use installed CLIs (Claude, Codex, Gemini, Cursor Agent) as local model backends.
 
 ## Model ids
 
 - `cli/claude/<model>` (e.g. `cli/claude/sonnet`)
 - `cli/codex/<model>` (e.g. `cli/codex/gpt-5.2`)
 - `cli/gemini/<model>` (e.g. `cli/gemini/gemini-3-flash-preview`)
+- `cli/agent/<model>` (e.g. `cli/agent/gpt-5.2`)
 
 Use `--cli [provider]` (case-insensitive) for the provider default, or `--model cli/<provider>/<model>` to pin a model.
 If `--cli` is provided without a provider, auto selection is used with CLI enabled.
 
 ## Auto mode
 
-Auto mode does **not** use CLIs unless you set `cli.enabled` in config.
+Auto mode can prepend CLI attempts in two ways:
 
-Why: CLI adds ~4s latency per attempt and higher variance.
-Recommendation: enable only Gemini unless you have a reason to add others.
+- `cli.enabled` set in config:
+  - Auto always uses this list order.
+  - Also acts as an allowlist for explicit `--cli` / `--model cli/...`.
+- Auto CLI fallback (`cli.autoFallback`, default enabled):
+  - Applies only to **implicit** auto (when no model is set via flag/env/config).
+  - Default behavior: only when no API key is configured.
+  - Default order: `claude, gemini, codex, agent`.
+  - Remembers + prioritizes the last successful CLI provider (`~/.summarize/cli-state.json`).
 
 Gemini CLI performance: summarize sets `GEMINI_CLI_NO_RELAUNCH=true` for Gemini CLI runs to avoid a costly self-relaunch (can be overridden by setting it yourself).
 
-When enabled, auto prepends CLI attempts in the order listed in `cli.enabled`
-(recommended: `["gemini"]`).
-
-Enable CLI attempts:
+Set explicit CLI allowlist:
 
 ```json
 {
@@ -37,21 +41,36 @@ Enable CLI attempts:
 }
 ```
 
-Disable CLI attempts:
+Configure auto CLI fallback:
 
 ```json
 {
-  "cli": { "enabled": [] }
+  "cli": {
+    "autoFallback": {
+      "enabled": true,
+      "onlyWhenNoApiKeys": true,
+      "order": ["claude", "gemini", "codex", "agent"]
+    }
+  }
 }
 ```
 
-Note: when `cli.enabled` is set, it also acts as an allowlist for explicit `--cli` / `--model cli/...`.
+Disable auto CLI fallback:
+
+```json
+{
+  "cli": { "autoFallback": { "enabled": false } }
+}
+```
+
+Note: `--model auto` (explicit) does not trigger auto CLI fallback unless `cli.enabled` is set.
 
 ## CLI discovery
 
 Binary lookup:
 
 - `CLAUDE_PATH`, `CODEX_PATH`, `GEMINI_PATH` (optional overrides)
+- `AGENT_PATH` (optional override)
 - Otherwise uses `PATH`
 
 ## Attachments (images/files)
@@ -62,19 +81,29 @@ path-based prompt and enables the required tool flags:
 - Claude: `--tools Read --dangerously-skip-permissions`
 - Gemini: `--yolo` and `--include-directories <dir>`
 - Codex: `codex exec --output-last-message ...` and `-i <image>` for images
+- Agent: uses built-in file tools in `agent --print` mode (no extra flags)
 
 ## Config
 
 ```json
 {
   "cli": {
-    "enabled": ["claude", "gemini", "codex"],
+    "enabled": ["claude", "gemini", "codex", "agent"],
+    "autoFallback": {
+      "enabled": true,
+      "onlyWhenNoApiKeys": true,
+      "order": ["claude", "gemini", "codex", "agent"]
+    },
     "codex": { "model": "gpt-5.2" },
     "gemini": { "model": "gemini-3-flash-preview", "extraArgs": ["--verbose"] },
     "claude": {
       "model": "sonnet",
       "binary": "/usr/local/bin/claude",
       "extraArgs": ["--verbose"]
+    },
+    "agent": {
+      "model": "gpt-5.2",
+      "binary": "/usr/local/bin/agent"
     }
   }
 }
@@ -84,6 +113,23 @@ Notes:
 
 - CLI output is treated as text only (no token accounting).
 - If a CLI call fails, auto mode falls back to the next candidate.
+- Cursor Agent CLI uses the `agent` binary and relies on Cursor CLI auth (login or `CURSOR_API_KEY`).
+- Gemini CLI is invoked in headless mode with `--prompt` for compatibility with current Gemini CLI releases.
+
+## Quick smoke test (all CLI providers)
+
+Use a tiny local text file and run each provider with a longer timeout (Gemini can be slower):
+
+```bash
+printf "Summarize CLI smoke input.\nOne short paragraph. Reply can be brief.\n" >/tmp/summarize-cli-smoke.txt
+
+summarize --cli codex --plain --timeout 2m /tmp/summarize-cli-smoke.txt
+summarize --cli claude --plain --timeout 2m /tmp/summarize-cli-smoke.txt
+summarize --cli gemini --plain --timeout 2m /tmp/summarize-cli-smoke.txt
+summarize --cli agent --plain --timeout 2m /tmp/summarize-cli-smoke.txt
+```
+
+If Agent fails with auth, run `agent login` (interactive) or set `CURSOR_API_KEY`.
 
 ## Generate free preset (OpenRouter)
 

package/docs/config.md

@@ -36,6 +36,20 @@ For prompt:
 1. CLI flag `--prompt` / `--prompt-file`
 2. Config file `prompt`
 3. Built-in default prompt
+
+For environment variables:
+
+1. Process environment variables
+2. Config file `env`
+3. Legacy config file `apiKeys` (mapped to env names)
+
+For UI theme:
+
+1. CLI flag `--theme`
+2. Env `SUMMARIZE_THEME`
+3. Config file `ui.theme`
+4. Built-in default (`aurora`)
+
 ## Format
 
 `~/.summarize/config.json`:
@@ -43,8 +57,10 @@ For prompt:
 ```json
 {
   "model": { "id": "google/gemini-3-flash-preview" },
+  "env": { "OPENAI_API_KEY": "sk-..." },
   "output": { "language": "auto" },
-  "prompt": "Explain like I am five."
+  "prompt": "Explain like I am five.",
+  "ui": { "theme": "ember" }
 }
 ```
 
@@ -84,6 +100,39 @@ Example:
 }
 ```
 
+## Environment defaults
+
+Set any env var in config (process env still wins):
+
+```json
+{
+  "env": {
+    "OPENAI_API_KEY": "sk-...",
+    "OPENROUTER_API_KEY": "sk-or-...",
+    "FIRECRAWL_API_KEY": "...",
+    "CUSTOM_FLAG": "1"
+  }
+}
+```
+
+Legacy shortcut (still supported):
+
+```json
+{
+  "apiKeys": {
+    "openai": "sk-...",
+    "anthropic": "sk-ant-...",
+    "google": "...",
+    "openrouter": "sk-or-...",
+    "xai": "...",
+    "zai": "...",
+    "apify": "...",
+    "firecrawl": "...",
+    "fal": "..."
+  }
+}
+```
+
 ## Cache
 
 Configure the on-disk SQLite cache (extracted content, transcripts, summaries).
@@ -94,7 +143,47 @@ Configure the on-disk SQLite cache (extracted content, transcripts, summaries).
     "enabled": true,
     "maxMb": 512,
     "ttlDays": 30,
-    "path": "~/.summarize/cache.sqlite"
+    "path": "~/.summarize/cache.sqlite",
+    "media": {
+      "enabled": true,
+      "maxMb": 2048,
+      "ttlDays": 7,
+      "path": "~/.summarize/cache/media",
+      "verify": "size"
+    }
+  }
+}
+```
+
+Notes:
+
+- `cache.media` controls the **media file** cache (yt-dlp downloads).
+- `--no-cache` bypasses summary caching only (LLM output); extract/transcript caches still apply. Use `--no-media-cache` for media.
+- `verify`: `size` (default), `hash`, or `none`.
+
+## UI theme
+
+Set a default CLI theme:
+
+```json
+{
+  "ui": { "theme": "moss" }
+}
+```
+
+## Slides defaults
+
+Enable slides by default and tune extraction parameters:
+
+```json
+{
+  "slides": {
+    "enabled": true,
+    "ocr": false,
+    "dir": "slides",
+    "sceneThreshold": 0.3,
+    "max": 20,
+    "minDuration": 2
   }
 }
 ```
@@ -224,17 +313,25 @@ Examples:
 ```json
 {
   "cli": {
-    "enabled": ["gemini"],
+    "enabled": ["gemini", "agent"],
+    "autoFallback": {
+      "enabled": true,
+      "onlyWhenNoApiKeys": true,
+      "order": ["claude", "gemini", "codex", "agent"]
+    },
     "codex": { "model": "gpt-5.2" },
-    "claude": { "binary": "/usr/local/bin/claude", "extraArgs": ["--verbose"] }
+    "claude": { "binary": "/usr/local/bin/claude", "extraArgs": ["--verbose"] },
+    "agent": { "binary": "/usr/local/bin/agent", "model": "gpt-5.2" }
   }
 }
 ```
 
 Notes:
 
-- `cli.enabled` is an allowlist (auto uses CLIs only when set; explicit `--cli` / `--model cli/...` must be included).
-- Recommendation: keep `cli.enabled` to `["gemini"]` unless you have a reason to add others (extra latency/variance).
+- `cli.enabled` is an allowlist (and order) for auto + explicit CLI model ids.
+- `cli.autoFallback` controls implicit-auto CLI fallback when `cli.enabled` is not set.
+- Default auto fallback order: `claude, gemini, codex, agent`.
+- Auto fallback stores the last successful provider in `~/.summarize/cli-state.json` and prioritizes it on the next run.
 - `cli.<provider>.binary` overrides CLI binary discovery.
 - `cli.<provider>.extraArgs` appends extra CLI args.
 
@@ -270,9 +367,9 @@ Override API endpoints for any provider to use proxies, gateways, or compatible
 
 Or via environment variables (which take precedence over config):
 
-| Provider   | Environment Variable(s)                |
-| ---------- | -------------------------------------- |
-| OpenAI     | `OPENAI_BASE_URL`                      |
-| Anthropic  | `ANTHROPIC_BASE_URL`                   |
-| Google     | `GOOGLE_BASE_URL` (alias: `GEMINI_BASE_URL`) |
-| xAI        | `XAI_BASE_URL`                         |
+| Provider  | Environment Variable(s)                      |
+| --------- | -------------------------------------------- |
+| OpenAI    | `OPENAI_BASE_URL`                            |
+| Anthropic | `ANTHROPIC_BASE_URL`                         |
+| Google    | `GOOGLE_BASE_URL` (alias: `GEMINI_BASE_URL`) |
+| xAI       | `XAI_BASE_URL`                               |

package/docs/extract-only.md

@@ -13,8 +13,14 @@ Deprecated alias: `--extract-only`.
 ## Notes
 
 - No summarization LLM call happens in this mode.
+- Input must be a URL (`-` stdin is not supported with `--extract`).
+- No extraction cap is applied. Use `--max-extract-characters <count>` to cap output if needed.
 - `--format md` may still convert HTML to Markdown (depending on `--markdown-mode` and available tools).
 - `--length` is intended for summarization guidance; extraction prints full content.
+- `--timestamps` keeps the plain transcript text but also exposes `transcriptSegments` and `transcriptTimedText` (JSON) and prints a timed transcript block when available.
+- `--slides` runs slide detection (YouTube/direct video URLs). Slide metadata is included in JSON output and written to `slides.json` in the slide directory.
+  - When combined with `--extract` for videos that have timed transcripts, the CLI interleaves slide images inline at matching timestamps.
+  - Scene detection auto-tunes using sampled frame hashes.
 - For non-YouTube URLs with `--format md`, the CLI uses Readability article HTML as the default Markdown input (`--markdown-mode readability`).
   - Use `--markdown-mode auto` to prefer LLM/markitdown conversion without Readability preprocessing.
   - Use `--markdown-mode llm` to force an LLM conversion.
@@ -23,3 +29,7 @@ Deprecated alias: `--extract-only`.
   - Force it with `--markdown-mode llm`.
   - If no LLM is configured, `--markdown-mode auto` may fall back to `uvx markitdown` when available.
 - `--markdown-mode readability` uses Readability to extract article HTML before Markdown conversion.
+
+Daemon note:
+
+- `/v1/summarize` supports `format: "markdown"` + `markdownMode` for extract-only output (use `extractOnly: true`).