@gentbajko/slopify 4.0.0 → 4.2.0

package/dist/tutorials/Agents-MCP.md

@@ -1,35 +1,35 @@
 # Agents (MCP)
 
-Slopify has a built-in MCP server, so an AI agent on your computer (Claude Code, Codex, or any other client that speaks MCP over HTTP) can run Slopify for you. It can start and fix runs, edit the Library and your setup, answer reviews and approve checkpoints, with the same checks, costs and refusals as the buttons in the web page. Run on a schedule, an agent can clear everything that would otherwise wait for you, right up to **Ready to upload**. Uploading stays yours.
+Slopify has a built-in MCP server, so an AI agent on your computer (Claude Code, Codex, or any other client that speaks MCP over HTTP) can run Slopify for you. It can start and fix runs, edit your prompts, templates and settings, answer AI checks and approve pauses, with the same checks, costs and refusals as the buttons in the web page. Run on a schedule, an agent can clear everything that would otherwise wait for you, right up to **Ready to upload**. Uploading stays yours.
 
-**Where to find it:** **Settings → Connections → Agents (MCP)**.
+**Where to find it:** **Settings → AI agents**.
 
-## What the Agents tab shows
+## What the AI agents page shows
 
 | Part | What it is |
 | --- | --- |
-| **MCP address** | The address agents connect to: this install's address with `/mcp` after it, for example `http://127.0.0.1:6969/mcp`. It uses the address in your browser's address bar, so it matches your port and Docker's published port. |
+| **Address for agents (MCP)** | The address agents connect to: this install's address with `/mcp` after it, for example `http://127.0.0.1:6969/mcp`. It uses the address in your browser's address bar, so it matches your port and Docker's published port. |
 | **Claude Code** | The command that adds Slopify to Claude Code, with **Copy**. Run it once in a terminal. |
 | **Codex** | The lines that add Slopify to Codex, with **Copy**. Add them to `~/.codex/config.toml`. |
 | Last connected | When an agent last connected, or "No agent has connected yet." |
-| **What agents did** | The latest 20 changes made by agents, newest first: what was done, the project or schedule it was done to, and when. Changes outside a project (a Library prompt, a schedule, a setting) are listed here too. "No agent has changed anything yet." when there are none. |
+| **What agents did** | The latest 20 changes made by agents, newest first: what was done, the project or schedule it was done to, and when. Changes outside a project (a prompt, a schedule, a setting) are listed here too. "No agent has changed anything yet." when there are none. |
 
 If the browser blocks the clipboard, **Copy** says so; select the line and copy it yourself.
 
 ## Connect an agent
 
-Slopify must be running. The address in these examples is the default (`127.0.0.1`, port `6969`); copy the real lines from the Agents tab.
+Slopify must be running. The address in these examples is the default (`127.0.0.1`, port `6969`); copy the real lines from Settings → AI agents.
 
 ### Claude Code
 
-1. Open **Settings → Connections → Agents (MCP)** and press **Copy** next to **Claude Code**.
+1. Open **Settings → AI agents** and press **Copy** next to **Claude Code**.
 2. Paste it in a terminal and run it:
 
    ```
    claude mcp add --transport http slopify http://127.0.0.1:6969/mcp
    ```
 
-3. Start Claude Code. `/mcp` there should list `slopify` as connected, and the Agents tab now shows when it last connected.
+3. Start Claude Code. `/mcp` there should list `slopify` as connected, and Settings → AI agents now shows when it last connected.
 
 ### Codex
 
@@ -49,7 +49,7 @@ Any MCP client that connects by URL over Streamable HTTP takes the same **MCP ad
 
 ### Docker
 
-Nothing changes: the agent runs on your computer and connects to the port Docker publishes, the same address you open Slopify at. Copy the lines from the Agents tab in that Slopify. See [Docker](Docker).
+Nothing changes: the agent runs on your computer and connects to the port Docker publishes, the same address you open Slopify at. Copy the lines from Settings → AI agents in that Slopify. See [Docker](Docker).
 
 ## No token, and what keeps web pages out
 
@@ -63,18 +63,18 @@ If you start Slopify with `--host 0.0.0.0` (or another address other computers c
 
 Anything you can do in the web page, except the few things listed under [What agents cannot do](#what-agents-cannot-do). That includes:
 
-- **Projects:** make projects from Play drafts and templates (after the same review and estimate you see), read them, edit them, pause, continue and cancel runs, **Keep as is**, move projects to another channel, delete and restore them.
-- **Fixing runs:** **Try ... again**, **Soften and retry**, remake a step or one item, regenerate a narration chunk, and **Choose what to remake**, with its estimate.
-- **Reviews:** answer reviews set to **External agent (MCP)**, **Overrule** or **Redo** flagged items, and approve review checkpoints.
-- **Planning:** release times, the posting plan, **Mark uploaded**, **Deleted on YouTube**, and **Prepare upload** up to **Ready to upload**.
+- **Projects:** make projects from Create drafts and templates (after the same review and estimate you see), read them, edit them, pause, continue and cancel runs, **Keep as is**, move projects to another channel, delete and restore them.
+- **Fixing runs:** **Try ... again**, **Soften and retry**, make a step or one item again, make a narration chunk again, and **Choose what to make again**, with its estimate.
+- **Pauses and checks:** answer AI checks set to **Your own AI agent**, **Overrule** or **Redo** flagged items, and approve pauses.
+- **Planning:** release times, the posting plan, **Mark uploaded**, **Deleted on YouTube**, and **Copy for YouTube Studio** up to **Ready to upload**.
 - **Schedules:** schedules, their topic lists, approving or turning down held topics, and **Prepare**.
-- **Library and setup:** prompts (with history), templates, channels and cast, Library import and export, and settings other than those below.
+- **Prompts, templates and settings:** prompts (with history), templates, channels and cast, export and import, and settings other than those below.
 - **Reading:** Home's work list, the calendar, costs and estimates, a project's files (pictures come back as pictures; audio and video as their address in Slopify), and the material a review looks at.
 - **Storage:** **Delete old versions** for one project.
 
-Agents never start paid work you could not see: before a remake they get the same **Choose what to remake** list with its estimate, and they must accept it, as you do. There is no extra budget or limit for agents; the costs are the same as yours. Actions with a consequence (deleting, for example) need the agent to confirm them, as a dialog asks you.
+Agents never start paid work you could not see: before anything is made again they get the same **Choose what to make again** list with its estimate, and they must accept it, as you do. There is no extra budget or limit for agents; the costs are the same as yours. Actions with a consequence (deleting, for example) need the agent to confirm them, as a dialog asks you.
 
-Agents and their tools use the same state words as the page: **Queued**, **Running**, **Paused**, **Waiting for your review**, **Waiting for the agent**, **Prepared**, **Stopped**, **Kept as is**, **Failed**, **Done**.
+Agents and their tools use the same state words as the page: **Queued**, **Running**, **Paused**, **Waiting for your review**, **Waiting for the agent**, **Waiting for its day**, **Stopped**, **Kept as is**, **Failed**, **Done**.
 
 ## What agents cannot do
 
@@ -82,7 +82,7 @@ Agents and their tools use the same state words as the page: **Queued**, **Runni
 | --- | --- |
 | Upload to YouTube, or send a video to the Studio extension (**Fill in YouTube Studio**, **Upload**) | Agents stop at **Ready to upload**. Uploading is yours; Slopify never makes a video public. See [Publishing to YouTube](Publishing-to-YouTube). |
 | The extension's automatic pinned comment setting | It posts comments in your name. |
-| Read or change provider keys, or make the extension's pairing token | They are credentials. Agents see each provider only as configured or missing. |
+| Read or change service keys, or make the extension's pairing token | They are credentials. Agents see each service only as set up or missing. |
 | Read the **Notification URL** | It can hold a secret (a private ntfy topic). Agents see only whether one is configured or missing, though they may set a new one. |
 | Backups: export, import, restore, and the daily backup settings | They are yours, in Settings → Backup & storage. |
 | Update Slopify, start at login, CLI paths, the extension's download | They are yours. |
@@ -97,27 +97,27 @@ Everything an agent changes is marked, so you can always tell its work from your
 
 | Where | What you see |
 | --- | --- |
-| Project page → **Project history** | Versions an agent saved end in **· by agent**, and **Done by agents** lists what agents did to the project (approvals, retries, verdicts and so on). |
+| Project → **Edit settings** → **Versions** | Versions an agent saved read **by agent**, and **Done by agents** lists what agents did to the project (approvals, retries, verdicts and so on). |
 | Review badges | **Passed by agent**, **Flagged by agent**, **Redone after agent review**, **Accepted by agent** (an agent pressed Overrule), **Made again by agent** (an agent pressed Redo). |
 | Notifications | A run an agent started ends its notices with **· started by agent** ("Started: *title* · by agent" in the browser); a flag from an agent's review ends with **· by agent**. |
-| Settings → Agents (MCP) | **What agents did**: the latest 20 changes of every kind. |
+| Settings → AI agents | **What agents did**: the latest 20 changes of every kind. |
 
-## The External agent reviewer
+## Your own AI agent as the checker
 
-Instead of paying a reviewer model, you can let your agent do the [automatic reviews](Reviews-and-Checkpoints#automatic-reviews).
+Instead of paying a model to check, you can let your agent do the [AI checks](Reviews-and-Checkpoints#ai-checks).
 
-1. On Play, open the **Reviews** row (or Edit project → **Reviews** on a project).
-2. Set **Who reviews** to **External agent (MCP)**. **Reviewer** and **Reviewer model** are greyed: the agent needs neither.
-3. Pick **Flag only** or **Flag and redo** for each stage, as usual. Picture stages (images, the thumbnail, shorts) work too: the agent is shown the pictures.
+1. On Create, open the **Pauses and checks** row (or **Edit settings** → **Pauses and checks** on a project).
+2. Under **Have an AI check the results**, open **Checker and stages** and set **Who checks** to **Your own AI agent**. **Checked by** goes away: the agent needs no service or model.
+3. Pick **Flag problems** or **Flag and redo**, for every stage or each on its own, as usual. Picture stages (images, the thumbnail, shorts) work too: the agent is shown the pictures.
 
 Reviews by the agent cost nothing and add nothing to the estimate. Redos it asks for cost what the item cost, as always.
 
 ### What happens during the run
 
 1. When an item is made, its review waits for the agent. What depends on it waits too; other work carries on.
-2. If nothing else holds the run, the project reads **Waiting for the agent** everywhere: its header, Projects, Home's **Running now** and the calendar. The project page says "An agent is reviewing what was made." with nothing to press. It is not in **Needs you**, no "Waiting for you" notice goes out and there is no **Continue the run** to press: it goes on by itself.
+2. If nothing else holds the run, the project reads **Waiting for the agent** everywhere: its title row, Projects, Home's **Running** and the calendar. The project page says "An agent is reviewing what was made." with nothing to press. It is not in **Needs you**, no "Waiting for you" notice goes out and there is no **Continue the run** to press: it goes on by itself.
 3. The agent reads the item and answers **pass** or **fail**. A fail needs at least one reason; at most 10 reasons, each up to 500 characters. The answer goes through the stage's mode, exactly like a model's verdict: a pass lets the work go on, a fail is flagged or made again.
-4. **The first answer wins.** If two agents answer the same review, the first one saved is kept and the second is refused ("This review was already answered"). The same goes for you: once an agent has pressed Overrule or Redo on a flagged item, or approved a checkpoint, pressing it yourself changes nothing and says it was already decided.
+4. **The first answer wins.** If two agents answer the same review, the first one saved is kept and the second is refused ("This review was already answered"). The same goes for you: once an agent has pressed Overrule or Redo on a flagged item, or approved a pause, pressing it yourself changes nothing and says it was already decided.
 
 ### If no agent answers
 
@@ -125,7 +125,7 @@ A review nobody answers **passes by itself 2 hours** after it began waiting. Its
 
 - **Paused project:** the review still passes at its two hours, but nothing runs until the run is continued.
 - **Canceled run:** its waiting reviews stop and never pass. If you (or an agent) take the step up again, the review asks again and waits a fresh two hours.
-- **Item made again meanwhile** (an edit or a remake): the old review is dropped and the new item gets its own.
+- **Item made again meanwhile** (after an edit, or made again on purpose): the old review is dropped and the new item gets its own.
 
 ## Paused and stopped runs
 
@@ -139,8 +139,8 @@ Slopify cannot wake an agent; the agent looks. Its work list is the `needs_atten
 | --- | --- |
 | An external review waiting for a verdict | Reads the item and answers. |
 | A flagged verdict nobody acted on | **Overrule** or **Redo**. |
-| A review checkpoint waiting for approval | Checks the work before it and approves. A checkpoint from the template's own **Before Video** is listed; a schedule's **Prepared** hold is not, since that one waits for its day. |
-| A failed step | Does what the error's own sentence says: for example regenerates narration chunk 5, accepts the **Choose what to remake** estimate, then continues the run. |
+| A pause waiting for approval | Checks the work before it and approves. A template's own **Pause after the images (before the video)** is listed; a schedule's made-ahead project (**Waiting for its day**) is not, since that one waits for its day. |
+| A failed step | Does what the error's own sentence says: for example makes narration chunk 5 again, accepts the **Choose what to make again** estimate, then continues the run. |
 | A paused run, or a run a restart **Stopped** | Continues it once nothing on the project still needs fixing. |
 | Topics a schedule holds for approval | Approves the ones that fit and turns down the rest. |
 | A video marked **Late · upload now** | Reports it. It cannot upload. |
@@ -153,13 +153,13 @@ The steps above are the **attend routine**. Slopify hands it to every agent that
 
 ## Tips
 
-- Pair the External agent reviewer with an hourly attend routine, and a [Notification URL](Notifications#get-notifications-on-your-phone-notification-url) so you hear when a review passed without an answer: that usually means the routine stopped running.
-- Check **What agents did** in the Agents tab now and then; each project's **Project history** has the full story for that project.
+- Pair your own AI agent as the checker with an hourly attend routine, and a [Notification URL](Notifications#get-notifications-on-your-phone-notification-url) so you hear when a review passed without an answer: that usually means the routine stopped running.
+- Check **What agents did** in Settings → AI agents now and then; each project's **Edit settings** → **Versions** has the full story for that project.
 - If an agent's request is refused because the project changed meanwhile, it reads the project again and retries once; you do not need to do anything.
 
 ## Related pages
 
-- [Reviews and Checkpoints](Reviews-and-Checkpoints)
+- [Pauses and Checks](Reviews-and-Checkpoints)
 - [Notifications](Notifications)
 - [Recovery and Retries](Recovery-and-Retries)
 - [Home and Projects](Home-and-Projects)

package/dist/tutorials/Assistant.md

@@ -1,6 +1,6 @@
 # Assistant
 
-The assistant is a chat inside Slopify. Ask it how something works, or ask it to do something on the screen you have open: "Which templates do I have?", "Why did this run stop?", "Remake the thumbnail of this project". It runs on your own **Claude Code** or **Codex** sign-in, so it uses your plan's allowance and is not added to a project's run cost.
+The assistant is a chat inside Slopify. Ask it how something works, or ask it to do something on the screen you have open: "Which templates do I have?", "Why did this run stop?", "Make the thumbnail of this project again". It runs on your own **Claude Code** or **Codex** sign-in, so it uses your plan's allowance and is not added to a project's run cost.
 
 **Where to find it:** **Assistant** in the left rail, under the search field. On a phone it is the sparkle button in the top bar. It opens beside the page without moving it.
 
@@ -8,12 +8,12 @@ The assistant is a chat inside Slopify. Ask it how something works, or ask it to
 
 - It uses only Slopify's own tools, the same ones an [agent](Agents-MCP) uses, with the same checks and refusals as the buttons in the page. It reads this guide to answer questions about Slopify.
 - It has no web search, can't run commands and can't open files on your computer. None of your Claude Code or Codex settings, hooks, plugins, skills, memory or other MCP servers are loaded for it. If the CLI ever offers it a tool from outside Slopify, Slopify stops the answer at once and says so.
-- It never answers an external review, exports or imports the Library, uploads a file from disk, empties the Trash or deletes old versions. Uploading to YouTube, backups, provider keys and updates stay yours.
-- What it changes shows as **by assistant** in a project's history, in notifications and in **Settings → Connections → Agents (MCP)**.
+- It never answers an external AI check, exports or imports a backup, uploads a file from disk, empties the Trash or deletes old versions. Uploading to YouTube, backups, service keys and updates stay yours.
+- What it changes shows as **by assistant** in a project's **Versions**, in notifications and in **Settings → AI agents**.
 
 ## It asks first
 
-Anything that costs money (starting a run or a remake, retrying a step, generating topics, a cast picture or a voice sample), anything a button would confirm, anything that removes something, and anything that sends to or changes an address outside Slopify (where notifications go, a test notification) waits for you. The chat shows a card with what it wants to do, for which project, and what it costs: the estimate the remake preview or Play's review showed, or "Slopify can't price it here" when there is none.
+Anything that costs money (starting a run or making something again, retrying a step, generating topics, a cast picture or a voice sample), anything a button would confirm, anything that removes something, and anything that sends to or changes an address outside Slopify (where notifications go, a test notification) waits for you. The chat shows a card with what it wants to do, for which project, and what it costs: the estimate **Choose what to make again** or Create's **See everything this run will do** showed, or "Slopify can't price it here" when there is none.
 
 | Press | What happens |
 | --- | --- |
@@ -36,7 +36,7 @@ The panel says why and links to the fix:
 
 | Message | Fix |
 | --- | --- |
-| Neither Claude Code nor Codex is ready | Install one and sign in, then check it in **Settings → Providers** ([AI CLIs](AI-CLIs)). |
+| Neither Claude Code nor Codex is ready | Install one and sign in, then check it in **Settings → Keys & services** ([AI CLIs](AI-CLIs)). |
 | Claude Code (or Codex) is signed out | Run `claude auth login` (or `codex login`) in a terminal, then send your message again. |
 | Codex is too old | Update Codex CLI to the version the message names. |
 | The Docker version | The assistant isn't available in Docker: there the CLIs run on your computer through the host helper, which can't hand them Slopify's tools safely. Install Slopify with npm ([Install](Install)) to use it. |

package/dist/tutorials/Backups.md

@@ -1,6 +1,6 @@
 # Backups
 
-A backup is one `.tar` file with everything you made in Slopify: every project with its files and history, your library, templates, schedules, channels and settings. Make one by hand at any time with **Export everything**, or let Slopify write one every day. Bring one back with **Import a backup**. Provider keys are never included.
+A backup is one `.tar` file with everything you made in Slopify: every project with its files and versions, your prompts, templates, schedules, channels and settings. Make one by hand at any time with **Export everything**, or let Slopify write one every day. Bring one back with **Import a backup**. Provider keys are never included.
 
 **Where to find it:** **Settings → Backup & storage**: daily backups and Back up now, Export everything and Import a backup.
 
@@ -8,18 +8,18 @@ A backup is one `.tar` file with everything you made in Slopify: every project w
 
 | Included | Left out on purpose |
 |---|---|
-| Every project with its files and history, and its channel | Provider keys |
-| Automatic review verdicts and run cost of each project | The Notification URL |
+| Every project with its files and versions, and its channel | Service keys |
+| AI check verdicts and run cost of each project | The Notification URL |
 | Prompts, intros and outros, with their history | The Studio extension's pairing |
-| Document themes and uploaded fonts | The tutorial's progress |
-| Templates, schedules and Play drafts | The daily backups' folder and status |
+| PDF looks and uploaded fonts | The tutorial's progress |
+| Templates, schedules and Create drafts | The daily backups' folder and status |
 | Channels: brand kit, series brief, episode memory and AI disclosure settings, cast with pictures, end screen images, episode summaries, existing videos, and the last **Keep only titles containing** filter | The telemetry machine id |
-| Channel links and the provider defaults a new Play form starts with | State that only matters while this install runs: the queue, plan-limit waits |
+| Channel links and the service defaults a new Create draft starts with | State that only matters while this install runs: the queue, plan-limit waits |
 | AI use marks: voices marked as a real person, image prompts marked photorealistic, projects with real footage | |
 | Settings and usage history | |
 | The trash: trashed items come back still in the trash, with their original date | |
 
-After an import you add your provider keys again in [Providers and keys](Providers-and-Keys).
+After an import you add your provider keys again in [Keys and Services](Providers-and-Keys).
 
 ## Export everything (a backup right now, downloaded)
 

package/dist/tutorials/Calendar.md

@@ -1,46 +1,38 @@
 # Calendar
 
-The calendar shows the coming four weeks on one screen: what needs you, every scheduled run with the topic and title it will use, the projects running or finished on their day, and the batch queue. You can drag a topic to another day, move it to another schedule, add topics, and accept or reject topics Slopify suggested.
+The calendar shows the coming four weeks on one screen: how much needs you, every scheduled run with the topic and title it will use, the projects running or finished on their day, and the batch queue. You can drag a topic to another day, move it to another schedule, add topics, and accept or reject topics Slopify suggested.
 
-**Where to find it:** **Calendar** in the sidebar. It has two tabs: **Coming weeks**, described here, and **Schedules**, where you create, edit, pause and resume the schedules themselves (see [Schedules](Schedules)).
+**Where to find it:** **Calendar** in the rail. It has two tabs: **Coming weeks**, described here, and **Schedules**, where you create, edit, pause and resume the schedules themselves (see [Schedules](Schedules)).
 
 ## What the calendar shows
 
 The calendar starts on this week's Monday and shows four weeks, Monday to Sunday.
 
 - **Scheduled runs**, each with the project title it will make. A run shows **Queued** when a topic is lined up, **Needs a topic** when its topic is still waiting for your approval or for generation, and **Paused** when its schedule is paused.
-- **Needs you**, above the weeks: every project that is waiting on you or ready to upload (see below).
-- **Projects** running or finished on their day, with their state: **Running**, **Waiting for the agent**, **Paused**, **Queued**, **Waiting for your review**, **Prepared**, **Stopped**, **Kept as is**, **Failed**, **Done with problems**, **Done** or **Canceled**. A project waiting for a CLI plan says so, for example **Waiting for Codex limits (resets at 14:00)**.
-- **Batch queue**: projects waiting to start (see below).
+- **Needs you**, above the weeks: one line with Home's counts of what waits on you and what is ready to upload (see below).
+- **Projects** running or finished on their day, with their state: **Running**, **Waiting for the agent**, **Paused**, **Queued**, **Waiting for your review**, **Waiting for its day**, **Stopped**, **Kept as is**, **Failed**, **Done with problems**, **Done** or **Canceled**. A project waiting for a CLI plan says so, for example **Waiting for Codex limits (resets at 14:00)**.
+- **Waiting to start**: the batch queue, videos started together that wait their turn (see below).
 - **Suggested topics**, beside the weeks, for schedules that hold generated topics for approval.
 
-The calendar follows the channel picked in the sidebar, or shows every channel. See [Channels](Channels).
+The calendar follows the channel picked under **Showing:** in the page header, or shows every channel. See [Channels](Channels).
 
-Each queued run has **Prepare**, which makes its video ahead of the day and leaves only the render for the day; a prepared run shows **Prepared** and **Open**. See [Schedules](Schedules#prepare-a-video-ahead).
+Each queued run has **Make ahead**, which makes everything but its video now (and spends what the run costs) and leaves only putting the video together for its day; such a run shows **Waiting for its day** and **Open**. See [Schedules](Schedules#make-a-video-ahead).
 
 ## Needs you
 
-Above the weeks, **Needs you** lists what cannot move on without you, then what is ready to upload. Its heading counts them, for example "2 waiting for you · 1 ready to upload". It is hidden when there is nothing.
+Above the weeks, one line says what Home's **Needs you** and **Finished** count, in Home's words, for every project of the channel shown (not only the ones in these weeks), for example "1 decision · 1 failed · 2 ready to upload. Open Home to act on them.", with **Open Home**. Decisions are projects held at a pause, paused or **Stopped**; failed are the failed projects and the steps that failed beside a wait; ready to upload are finished videos not marked uploaded. It is hidden when there is nothing, and the bundled samples never count.
 
-| Item | Status | Button |
-| --- | --- | --- |
-| A failed project | **Failed** | **Open to fix** |
-| A project you paused | **Paused** | **Open to continue** |
-| A project a restart stopped before it finished | **Stopped** | **Open to continue** |
-| A project held at a review checkpoint, or with an automatic review that flagged an item and waits for **Overrule** or **Redo** | **Waiting for your review** | **Open to review** |
-| A finished video not marked uploaded | **Ready to upload** | **Prepare upload** |
-
-The bundled samples never show here. A press anywhere on an entry opens its project. See [Reviews and Checkpoints](Reviews-and-Checkpoints) and [Publishing to YouTube](Publishing-to-YouTube).
+Acting on them is Home's job: **Needs you** there lists each one with its button. The calendar keeps its space for what is planned. See [Home and Projects](Home-and-Projects), [Pauses and Checks](Reviews-and-Checkpoints) and [Publishing to YouTube](Publishing-to-YouTube).
 
 ## The batch queue
 
-Videos started together, such as extra videos queued from Play, run one at a time. **Batch queue** lists them in the order they run, numbered (**1 in line**, **2 in line**, …), each marked **Running now**, **Waiting its turn** or **Paused**. Its heading says how many are waiting to start. Pausing a queued project holds the whole queue; when one fails or is canceled, the next one starts. The batch queue is only shown on the calendar; Projects links here and has a **Queued** filter. It is hidden when nothing is queued.
+Videos started together, such as extra videos queued from Create, run one at a time. **Waiting to start** is the same list as Home's: the videos still to start, numbered in the order they start (**1.**, **2.**, …), each marked **Queued** (or **Paused**) with **Earlier**, **Later** and **Remove**. Its heading says how many there are; the one already running is on Home under **Running**. Pausing the started project holds the whole queue, and the list says so; when one fails or is canceled, the next one starts. It follows the channel shown under **Showing:**, and is hidden when nothing waits.
 
 ## Switch between weeks and a list
 
-Use **Calendar view** at the top:
+Use **Show the weeks as** at the top:
 
-- **Weeks** (the default) shows the four weeks as a grid.
+- **Grid** (the default) shows the four weeks as a grid.
 - **List** shows the same runs day by day, with buttons to move each topic.
 
 This browser remembers your choice.
@@ -64,10 +56,10 @@ The topic now runs with the other schedule's template.
 
 ## Add topics
 
-1. Press **Add to calendar**.
+1. Press **Add topics to a schedule**.
 2. Pick the **Schedule** the topics join. Only active and paused schedules are listed, each with the number of topics already queued.
 3. Type or paste **Topics, one per line**. Blank lines are skipped.
-4. Press **Add N topics** (the button counts them). **Keep the calendar as it is** closes the form without adding anything.
+4. Press **Add N topics** (the button counts them). **Cancel** closes the form without adding anything.
 
 The topics go to the end of the schedule's queue, in order, and take its next free runs. Each topic fills the schedule's topic keyword; every other keyword keeps its every-run value. To give topics their own values, edit the schedule's topics as a table on the **Schedules** tab (see [Schedules](Schedules)).
 
@@ -80,7 +72,7 @@ Schedules set to **Generate and hold for approval** list their suggestions under
 - **Queue** adds a topic to the end of that schedule's queue.
 - **Reject** drops it for good; it is never suggested again.
 - **Queue all** adds every suggestion of that schedule, in order.
-- **Suggest topics now** asks the schedule's LLM for more at once (one LLM call).
+- **Suggest topics now · 1 AI call** asks the schedule's AI for more at once.
 
 While Slopify is asking, the panel says so and the topics appear when it finishes. If the last try failed, the panel says so with the reason. When nothing is waiting it says **No suggestions are waiting.**
 
@@ -94,9 +86,9 @@ Editing a suggestion's words before approving it is done under **Topics waiting*
 
 - Use the list view if dragging is fiddly, for example on a touch screen or a narrow window.
 - A browser notification for new suggestions opens the calendar's **Suggested topics** when you click it. See [Notifications](Notifications).
-- `Ctrl+K` → **Add to calendar** works from any screen: it opens the calendar with the form. `G` then `C` goes to the calendar.
+- `Ctrl+K` → **Add topics to a schedule** works from any screen: it opens the calendar with the form. `G` then `C` goes to the calendar.
 - To change a schedule's queued topics one by one (rename, reorder, remove), use the **Schedules** tab. See [Schedules](Schedules#edit-the-queued-topics-in-place).
-- To start one video right now instead of waiting for a run, use [Play](Play-Overview).
+- To start one video right now instead of waiting for a run, use [Create](Create-Overview).
 
 ## Related pages
 

package/dist/tutorials/Cast-Library.md

@@ -1,15 +1,15 @@
-# Cast Library
+# Cast
 
 A channel's cast is its recurring characters, creatures, places and objects. Each member has a name, a description and up to four reference pictures. Whenever a video's title or an image's brief names a member, its pictures go with that image request, so the member looks the same in every image and every episode. A cast member can also have a voice for multi-voice videos.
 
-**Where to find it:** **Channels** → a channel → **Cast** tab. **Add to cast** opens the editor beside the list.
+**Where to find it:** **Channels** → a channel → **Cast** tab. **Add to cast** opens the editor beside the list. An empty cast opens on the form for its first member, across the page.
 
 ## Add a cast member
 
 1. Open **Channels**, pick the channel, and open the **Cast** tab.
 2. Press **Add to cast**.
-3. Fill in the fields (see the table below). At least give it a **Name**: "Name it first, then give it reference pictures."
-4. Press **Add to cast**. The member is saved and the picture section opens.
+3. Fill in the fields (see the table below). At least give it a **Name**: "Name it first, then give it a picture or two." **Add alias** appears once you type another name.
+4. Press **Add to cast**. The member is saved and the picture section opens. Pressed with no name, it says "Give it a name first."
 5. Add one to four reference pictures: upload them or generate them (below).
 
 To change a member later, press **Edit** on it, change what you need and press **Save**. To remove one, press its delete button and confirm with **Delete from cast**.
@@ -48,35 +48,35 @@ Which images get which members:
 1. Open the member in the editor.
 2. Under **Reference pictures**, press **Upload a picture** and choose a PNG or JPEG up to 10 MB.
 
-### Generate a picture
+### Make a picture
 
-1. Under **Make a picture**, pick an **Image provider** and **Image model**.
+1. Under **Make a picture**, pick the **Service** and **Model** under **Drawn by**.
 2. Check **Picture to make**. It starts from the name, the description and a request for a plain background. Edit it as you like (up to 4,000 characters).
-3. Press **Generate a picture**. Wait until "Making the picture…" finishes.
+3. Press **Make the picture · 1 image call**. Wait until "Making the picture…" finishes.
 
-Each press is one image call on that provider, billed at its price for one image. A plain background with the whole figure in view makes the best reference.
+Each press is one image call to that service, billed at its price for one image. A plain background with the whole figure in view makes the best reference.
 
 To remove a picture, press its delete button. A member with no picture is not sent with any image.
 
-## Which image providers use the pictures
+## Which image services use the pictures
 
-| Provider | What happens |
+| Service | What happens |
 |---|---|
 | Codex, OpenAI, Google, and fal.ai edit models (FLUX.2 and Nano Banana 2 edit) | The member's pictures are sent as input pictures. |
 | Models that take no input pictures (Replicate, other fal.ai models) | The member is described in words instead, from its description. |
 
-See [Images](Play-Images) and [Providers and keys](Providers-and-Keys).
+See [Create: Images](Create-Images) and [Keys and Services](Providers-and-Keys).
 
 ## Give a cast member a voice
 
 In multi-voice formats (audiobook, podcast, radio drama, interview) a cast member can speak with the same voice in every episode.
 
-1. In the member's editor, under **Cast voice**, pick a **Voice provider**, **Voice model** and **Voice**. The list shows voices that speak the channel's language. If it says "No voices. Add one in Settings.", add a voice in **Settings → Voices** first.
+1. In the member's editor, under **Voice**, pick the **Service**, **Model** and **Voice** under **Read by**. The list shows voices that speak the channel's language. If it says "No voices for *service* yet", press **Add a voice for *service* ↗** under it and add one in **Settings → Voices** first.
 2. Pick a **Pace**: 0.8, 0.9, 1 (normal), 1.1 or 1.2.
 3. Press **Save**.
-4. On Play, pick the member under **Speakers**. They read with this voice, model and pace.
+4. On Create, pick the member under **Speakers**. They read with this voice, model and pace.
 
-Leave the provider empty for no voice. A run keeps the voice it started with. See [Multiple voices](Multiple-Voices).
+Leave the service empty for no voice. A run keeps the voice it started with. See [Multiple voices](Multiple-Voices).
 
 ### Make a member one of the channel's hosts
 
@@ -86,13 +86,13 @@ A channel's regular presenters can join every new podcast or interview on their
 2. Turn on **One of the channel's hosts**. Without a voice it warns: "A host joins new podcasts and interviews only with a voice. Pick one under Voice above."
 3. Press **Save**. The cast list shows **Host** beside the member.
 
-When you pick **Podcast** or **Interview** on Play for a draft of this channel with no speakers yet, the speakers start with the channel's hosts that have a voice. You can still add or remove speakers on the draft. Projects already made are not changed.
+When you pick **Podcast** or **Interview** on Create for a draft of this channel with no speakers yet, the speakers start with the channel's hosts that have a voice. You can still add or remove speakers on the draft. Projects already made are not changed.
 
 A picture that fails to generate because a CLI is signed out shows the same **Copy sign-in command** and **Check again** buttons as a project. See [Recovery and Retries](Recovery-and-Retries#sign-a-cli-in-again).
 
 ## What happens to finished videos
 
-A run keeps the cast as it was when it started. Editing the cast later never makes a finished video outdated. Only images that actually mention a member change their fingerprint, so only they would be remade if you remake the project's images.
+A run keeps the cast as it was when it started. Editing the cast later never makes a finished video outdated. Only images that actually mention a member change their fingerprint, so only they would be made again if you make the project's images again.
 
 ## Backups
 
@@ -101,12 +101,12 @@ Cast members and their pictures travel in a backup made with **Export everything
 ## Tips
 
 - Upload or generate a picture with the whole figure on a plain background. Busy backgrounds leak into every image.
-- Keep the description short and visual: colours, shape, clothing, one distinctive feature.
+- Keep the description short and visual: colors, shape, clothing, one distinctive feature.
 - Add the plural and possessive-free forms as aliases ("pharaohs", "the Queen"). Matching is whole-word only.
 
 ## Related pages
 
 - [Channels](Channels)
-- [Images](Play-Images)
+- [Create: Images](Create-Images)
 - [Multiple voices](Multiple-Voices)
-- [Providers and keys](Providers-and-Keys)
+- [Keys and Services](Providers-and-Keys)