Glinded for Memorial Videos

# extend_upload_url (Tool) - Extend Upload URL **Internal: Extend the expiry of the project's active upload link so a shared link keeps working.** Pushes back the expiration of the current upload session without changing its URL, so a link the user already shared stays valid for longer. ### **Use this tool for:** - **Link about to expire** - User still needs to collect files and the existing upload link is nearing (or past) its expiry. ### **Do NOT use this tool for:** - Creating a new link when none is active (use `create_upload_url`). - Stopping uploads (use `delete_upload_url`). --- ## Returns 1. **id** (string) 2. **url** (string): The upload URL that can be shared 3. **expiresAt** (string): ISO 8601 timestamp of when the URL expires

extend_upload_url

# get_active_upload_url (Tool) - Get Active Upload URL **Internal: Check whether the project already has a live upload link.** Returns the currently active (non-expired) upload session and its URL, or nothing if none exists. Read-only — it does not create or change any link. ### **Use this tool for:** - **Before creating a link** - Check for an existing active link so you reuse it instead of creating a duplicate. - **Re-sharing** - User asks for "the upload link again" and you need the current one. ### **Do NOT use this tool for:** - Creating a link (use `create_upload_url`) or extending one (use `extend_upload_url`). --- ## Returns 1. **uploadSession** (object, nullable): The active upload URL info, or null if none exists or has expired 1.1. **id** (string) 1.2. **url** (string): The upload URL that can be shared 1.3. **expiresAt** (string): ISO 8601 timestamp of when the URL expires

get_active_upload_url

# get_asset_preview (Tool) - Get Asset Preview Shows one uploaded photo or video of the Glinded project as a picture, whether or not the video uses it yet: a photo as the photo itself, a video as a strip of frames taken across the clip, each labelled with its time. The text gives its type, its size in pixels and, for a video, its length. `list_assets` gives ids and sizes, not pictures. Use this to see an upload before placing it, or to tell photos apart: who is in which photo, which one is the portrait the user means, which two belong together. Look at as many uploads as the request needs, one call per upload. `assetId` is the full id as `list_assets` gives it. A restored version has its own id there (`enhanced.assetId`) and can be looked at the same way. To see what is already in the video, use `get_scene_preview` (a whole scene) or `get_frame_preview` (one moment) instead: they show the upload as the video shows it, cropped and with the text over it.

get_asset_preview

# get_download_url (Tool) - Get Download URL **Internal: Get a download link for the finished, rendered video.** Creates a download session and returns a time-limited URL to the final rendered video file (plus its music-license file, when the composition uses licensed music). Only available once the video has been fully rendered. ### **Use this tool for:** - **Delivering the result** - User wants to download or share the completed video after a render has finished. ### **Do NOT use this tool for:** - A composition that has not been rendered yet (use `render_video_task` first). - Previewing before download (use `show_player`). --- ## Returns 1. **downloadUrl** (string): Signed URL for downloading the rendered video

get_download_url

# get_frame_preview (Tool) - Get Frame Preview Shows one moment of the Glinded project's video as a picture, the way a viewer sees it at that time, labelled with the time and the scene it falls in (two scenes during a transition between them). `seconds` is the time from the start of the video, in seconds. Times are all you need: the frame rate is handled for you. A time past the end shows the last frame. Use it to check one moment: a transition, a title as it appears, an overlay over a photo, or a moment the user points at ("at 0:12 the text covers her face"). To see a whole scene from start to end, use `get_scene_preview` instead. It shows the composition as it is stored now, including edits made since the last render. It takes a few seconds.

get_frame_preview

# get_project (Tool) - Get Project Retrieve Glinded project details by ID. --- ## Returns 1. **id** (string) 2. **title** (string) 3. **subjectDetails** (string) 4. **isMemorial** (boolean): True if the subject has passed away 5. **compositionId** (string, nullable): Null if no composition exists yet, which includes while one is generating: a run only starts on a project that has none, and the id appears when that run finishes. 6. **compositionStatus** (enum: "none", "generating", "ready"): Whether this project has a video put together yet. none = nothing built. generating = a run was started and has not finished; it may still be working, or it may be paused waiting on the user to finish a step, so do not assume it will complete on its own. ready = a video exists and can be previewed, edited or rendered. 7. **uploadedFileCount** (number): How many files the user has uploaded to this project. 0 means the project is still empty. 8. **notes** (string, optional): Any other relevant information about this project. 9. **createdAt** (string) 10. **updatedAt** (string) 11. **veryImportant** (string): What tools to load for this project

get_project

# get_scene_preview (Tool) - Get Scene Preview Shows one scene of the Glinded project's video as a picture, the way a viewer sees it: a strip of frames taken across the scene from just after it starts, each labelled with its time, plus the scene's start time and length in seconds. The source code says what a scene should look like; this shows what it does look like. Use it when you need to see the video rather than read it: - before an edit that changes a scene's layout, to see what is there now; - after such an edit, to check the result: text over a face, a photo cropped badly, text running off the edge or hard to read; - when the user says something in a scene looks wrong (cropped, overlapping, too small), to see what they see. `scene` is the scene's name exactly as the composition source gives it, the `name` of its `<TransitionSeries.Sequence>`; a scene can also be addressed by its position, as `#2` for the second, which is how to reach a sequence without a `name` or one whose name repeats. Read or grep the source first if you do not know the names. To look at a single moment anywhere in the video, use `get_frame_preview` instead. It shows the composition as it is stored now, including edits made since the last render. It takes a few seconds.

get_scene_preview

# get_uploadcare_assets (Tool) - Get Uploadcare Assets **Internal: look up metadata for files already stored in the project's Uploadcare storage by their UUIDs.** Fetches details (dimensions, type, name) for specific Uploadcare files by UUID so they can be reconciled into the project's asset list. Output is not shown to the user. ### **Use this tool for:** - **Reconciling known files** - You already have Uploadcare UUIDs (e.g. from an upload webhook) and need their metadata. ### **Do NOT use this tool for:** - Listing the project's assets (use `list_assets`, or `show_assets` to display them). - Importing a file the user shared in chat (use `import_chatgpt_file`). --- ## Returns 1. **results** (array)

get_uploadcare_assets

# grep_composition_source_code (Tool) - Grep Composition Source Code Searches the Glinded project's composition using RE2 regex pattern (no backreferences or lookaheads). Returns matches with context lines: ``` 12 const [count, setCount] = useState(0); 13 > const [active, setActive] = useState(false); 14 const [loading, setLoading] = useState(true); -- 46 > setActive(true); 47 console.log('activated'); [2 matches found] ``` `>` marks matching lines. `--` separates non-contiguous groups. Case-sensitive.

grep_composition_source_code

# import_chatgpt_file (Tool) - Import ChatGPT File **Exception-only: import a file the user has already sent in the conversation.** This tool imports a single file (image, video, or audio) that is already present in the conversation. It is NOT a collection workflow — never encourage users to send files in chat in order to use this tool. `upload_assets` is the mandatory upload method. ### **Use this tool ONLY when:** - The user has **already sent you files** in the conversation, meant for the Glinded project ### **Do NOT use this tool when:** - The user has NOT sent files yet — use `upload_assets` instead - The user asks how to upload — direct them to `upload_assets` - You want to collect new assets — use `upload_assets` ### **Important:** - Call this tool **once per file** (one file per invocation) - Follow the `status` and `askUser` fields in the response — they guide the next action ### **After calling this tool:** ✅ Last file imported → "All 10 files imported! Want me to open the upload interface to add more or share with family?" (offer upload_assets next) ✅ Not the last file → [no message, immediately call import_chatgpt_file for next file] (each import needs user approval — don't add friction) ❌ After all imports, suggesting "send more files in chat" → never encourage chat uploads; memorial videos need 100+ files, each requiring individual approval. Always direct to upload_assets ❌ Narrating each import ("imported photo 3 of 10!") → proceed silently, commentary slows the already-approval-heavy process --- ## Returns 1. **assetId** (string) 2. **type** (enum: "image", "video", "audio"): Detected asset type from MIME 3. **status** (string, optional) 4. **askUser** (string, optional): Ask the user about the next step you should take

import_chatgpt_file

# list_assets (Tool) - List Assets This tool retrieves all uploaded videos, photos, and audio files with their metadata. Returns structured metadata for programmatic use; `show_assets` renders assets visually. ### **Use this tool for:** - **Understand inventory** - Inspect what media is available for the Glinded project ### **Do NOT use this tool for:** - User needs to upload new assets (use `upload_assets` instead). - User asks "show me the assets" (use `show_assets` instead). - Asset list is empty and user needs upload interface (use `upload_assets` instead). **Common mistake:** When the user says "show me the assets", do NOT call `list_assets` and present a text table. The user wants to **see** their assets visually -- call `show_assets` instead. ✅ "Show me the assets" → use `show_assets` (user wants visual thumbnails and interactive UI) ✅ "Are all my assets done processing?" → use `list_assets` (internal programmatic status check, no UI needed) ❌ "Show me the assets" → presenting a markdown table (`| Short ID | Type | Resolution |...`) from list_assets — list_assets output is for internal use only, user can't see thumbnails. Use `show_assets` ### **Restored (enhanced) versions:** - When a photo has a ready restored version, its entry carries an `enhanced` object: `{assetId, width, height}`. - `enhanced.assetId` is a **different** asset id — the restored version. A composition shows it by referencing `enhanced.assetId` via `resolveAsset` (e.g. in an `edit_composition_source_code` call) in place of the original id. - Its `width`/`height` are the restored version's **own** dimensions and may differ from the original's, so check them before choosing a layout. - The field is absent while a restoration is still processing and absent when none exists — only ready restorations appear. ### **Assets not in the video:** - Pass `filter: "notInVideo"` to list only the uploads that no scene of the current video uses, such as photos the user uploaded after the video was made. Newest first by default, so the latest uploads lead. - An upload whose restored version is in the video counts as in the video. - Without a video yet, every upload is listed. ### **Total count:** - `totalCount` counts across **all** pages. Without a filter, it is the number of the user's uploaded photos/videos (assets derived from them, such as restored versions and title cards, are excluded). With `filter: "notInVideo"`, it is the number of uploads not in the video. Use it to answer "how many photos do I have?" without paginating. ### **Pagination:** - Returns up to 50 assets per page by default (configurable via `limit`, max 100) - `nextCursor` is `null` when there are no more pages - Pass the `nextCursor` value as `cursor` in the next request to get the next page --- ## Returns 1. **assets** (array) 1.1. **id** (string) 1.2. **type** (enum: "image", "video", "audio") 1.3. **uploadedAt** (string) 1.4. **width** (number, optional): Image/video only 1.5. **height** (number, optional): Image/video only 1.6. **duration** (string, optional): Video/audio only 1.7. **status** (enum: "uploading", "processing", "ready", "failed"): Processing state 1.8. **datetimeOriginal** (string, optional): Original date from media metadata 1.9. **enhanced** (object, optional): Present when a restored version of this photo is ready. 1.9.1. **assetId** (string): Asset id of the restored version of this photo. 1.9.2. **width** (number, optional): The restored version's own width in pixels. 1.9.3. **height** (number, optional): The restored version's own height in pixels. 2. **nextCursor** (string, nullable) 3. **totalCount** (number): Total number of the user's uploaded assets across ALL pages (derived assets excluded), so the count is available without paginating.

list_assets

# list_projects (Tool) - List Projects This tool retrieves all Glinded projects for the user, ordered by creation date (newest first). ### **Use this tool for:** - **Viewing available Glinded projects** - See all Glinded projects - **Switching between Glinded projects** - Find a Glinded project to resume work on. - **Resolving references** - When the user mentions a person's name, event, or keyword (e.g., "show me the files I uploaded for John"), call this tool to find the matching Glinded project by title or subjectDetails. ### **Do NOT use this tool for:** - Getting details of a **known** Glinded project by ID (use `get_project` instead). --- ## Returns 1. **projects** (array) 1.1. **id** (string) 1.2. **title** (string) 1.3. **subjectDetails** (string) 1.4. **isMemorial** (boolean): True if the subject has passed away 1.5. **compositionId** (string, nullable): Null if no composition exists yet, which includes while one is generating: a run only starts on a project that has none, and the id appears when that run finishes. 1.6. **compositionStatus** (enum: "none", "generating", "ready"): Whether this project has a video put together yet. none = nothing built. generating = a run was started and has not finished; it may still be working, or it may be paused waiting on the user to finish a step, so do not assume it will complete on its own. ready = a video exists and can be previewed, edited or rendered. 1.7. **uploadedFileCount** (number): How many files the user has uploaded to this project. 0 means the project is still empty. 1.8. **notes** (string, optional): Any other relevant information about this project. 1.9. **createdAt** (string) 1.10. **updatedAt** (string) 2. **totalCount** (number) 3. **nextCursor** (string, nullable) 4. **veryImportant** (string): What tools to load for this project

list_projects

# read_composition_source_code (Tool) - Read Composition Source Code Reads the Glinded project's composition with line numbers. Returns lines in the format: ``` 1 import React from 'react'; 2 import {AbsoluteFill} from 'remotion'; ... [Lines 1-6 of more] ``` Use `offset` and `limit` to page through large compositions. The total line count is only shown on the last page (e.g., `[Lines 201-249 of 249]`). The line number of the last line is the `sourceCodeLineCount` needed by `edit_composition_source_code`.

read_composition_source_code

# refresh_asset_list (Tool) - Refresh Asset List **Internal: re-fetch every asset in the project and regenerate fresh CDN URLs.** Reloads the complete, unpaginated asset list and re-signs the CDN URLs so they are current. Output is not shown to the user. No state changes. ### **Use this tool for:** - **After uploads or removals** - Get an up-to-date view of what is in the project. - **Stale/expired CDN URLs** - Previously fetched asset URLs may have expired and need re-signing. ### **Do NOT use this tool for:** - Displaying assets to the user (use `show_assets`). - A quick paginated read when a full refresh is not needed (use `list_assets`). --- ## Returns 1. **assets** (array) 1.1. **id** (string) 1.2. **type** (enum: "image", "video", "audio") 1.3. **srcSet** (string): srcset for responsive rendering 1.4. **uploadedAt** (string) 1.5. **width** (number, optional): Image/video only 1.6. **height** (number, optional): Image/video only 1.7. **duration** (string, optional): Video/audio only 1.8. **status** (enum: "uploading", "processing", "ready", "failed"): Processing state 1.9. **datetimeOriginal** (string, optional): Original date from media metadata

refresh_asset_list

# refresh_firebase_token (Tool) - Refresh Firebase Token Internal tool for widgets to refresh expired Firebase tokens. Not for direct LLM use. --- ## Returns 1. **firebaseToken** (string): Fresh Firebase custom token

refresh_firebase_token

# refresh_task_token (Tool) - Refresh Task Token Internal tool for widgets to refresh expired Firebase tokens for task watching. Not for direct LLM use. --- ## Returns 1. **firebaseToken** (string): Fresh Firebase custom token

refresh_task_token

# remove_assets (Tool) - Remove Assets Remove one or more assets from the Glinded project. They leave the video — any reference the composition still holds is rewritten to an invisible placeholder — and their stored copies are deleted, except a restored copy, which remains stored with the project. ### **Use this tool for:** - **Glinded project cleanup** - Remove unwanted assets - **Duplicate removal** - Remove duplicate or redundant uploads - **Quality control** - Remove low-quality or incorrect uploads - **Workflow cleanup** - Remove test or temporary assets ### **Do NOT use this tool for:** - You're unsure which assets to remove (use `list_assets` to review first). - You want to temporarily exclude assets (modify composition instead). ### **Assets still used in the composition:** You can remove them directly — no need to edit the composition first. Any `resolveAsset(...)` reference to a removed asset is automatically rewritten to an invisible `removedAsset(...)` placeholder so the player keeps working. Afterwards, `grep_composition_source_code` for `removedAsset` and use `edit_composition_source_code` to delete those now-empty scenes. ### **Examples:** ✅ "Remove photo abc123" → `remove_assets({ assetIds: ["abc123"] })` ✅ "Clean up abc123, def456, ghi789" → `remove_assets({ assetIds: ["abc123", "def456", "ghi789"] })` (batch) ❌ "Remove the second scene" → use `edit_composition_source_code` (scenes ≠ assets) ### **Important notes:** - **Batch efficiency** - Remove multiple assets at once when possible - **Per-id outcome** - The response names what happened to each id: removed, already gone, belonging to another project, or left in storage after a failure --- ## Returns 1. **removed** (array): Asset ids that were removed. 2. **notFound** (array): Asset ids that no longer existed — already gone, nothing to remove. 3. **wrongProject** (array): Asset ids that belong to a different project and were left alone. 4. **keptInArchive** (array): Restored photos taken out of the video, whose restored copy remains stored with the project. 5. **failed** (array): Asset ids that are out of the video but whose stored copies could not be deleted. 6. **compositionReferencesRewritten** (number): How many of the requested assets the composition still referenced — including ones kept in the archive or whose storage delete failed, since those leave the video either way. Each is now an invisible removedAsset(...) placeholder standing in an otherwise empty scene. 7. **cleanup** (string, optional): Present when the composition was rewritten: a note about the removedAsset(...) placeholders now standing in the source where the removed assets were.

remove_assets

# render_video_task (Tool) - Render Video **Render the composition to a downloadable video file.** Rendering typically takes 30 seconds to 5 minutes depending on video length and quality. ### **Prerequisites:** - The user has previewed the video via `show_player` and confirmed they are happy with the result ### **Important:** A `message`, when present, describes the run's state — the task widget shows the user any step that needs them. It returns a `taskId`, and when the rendering task completes, the widget provides download buttons directly — no further action needed from you. ### **Examples:** ✅ "I want to download" / "Let's export it" → call `render_video_task`, tell user it takes 1–3 min, download buttons appear in widget when done ❌ Directing user to a download/export button on the player → there is NO such button. The only way to render and download is calling `render_video_task` ❌ Suggesting right-click "Save video as..." → the player is a live preview, not a video file. Must call `render_video_task` --- ## Returns 1. **taskId** (string): The task ID. Use with check_task_status only if the user asks about progress. 2. **message** (string, optional): Anything you need to know about this task, such as a step the run has paused on.

render_video_task

# search_epidemic_sound_music (Tool) - Search Epidemic Sound Music **Search the Epidemic Sound catalog for licensed, royalty-free music tracks.** Searches 55,000+ tracks by keyword, mood, or genre. Returns track details with **inline audio preview in the widget** — the user can listen directly from the results. `compositionId` is required because picking a track in the widget applies it to that composition's source directly. ### **Use this tool when:** - The user asks for a **specific song, artist, genre, or instrument** (e.g., a named commercial song, "I want jazz", "more piano") - The user **didn't find anything they liked** in the Creative Commons catalog - The user explicitly asks for **more options** or a **broader selection** ### **Do NOT use this tool for:** - **General browsing** — when the user just wants to browse or change music without specifics, use `show_creative_commons_music` first (see `<music_workflow>`) - **Epidemic Sound URLs** — when the user shares a direct `epidemicsound.com/music/tracks/<id>` link, do NOT pass it as `externalTrackUrl`. Instead, extract the track ID from the URL and apply it directly via `edit_composition_source_code` using `resolveEpidemicSoundMusic("<extracted-id>")` ### **After the user selects a track:** Follow the `<music_workflow>` to apply it. ### **Matching a song by reference:** When a user names a specific commercial song, **do not search yet**. First explain that this catalog is searched for a track with a similar feel, and ask whether they have a **Spotify link** to use as a reference: > "I can't use [song name] directly due to licensing, but I can search for tracks with a similar feel. If you have a Spotify link to it, I can match the exact sound — otherwise I'll search by name, though the match might not be as precise. Which do you prefer?" - **If they share a Spotify link**: pass it as `externalTrackUrl` for the best style match. Only Spotify track links (`open.spotify.com/track/<id>`) are matched; any other link (TikTok, YouTube, Instagram, ...) is refused, so for those ask for the song title and artist and search with `query`. - **If they don't have one**: fall back to searching the artist/song name as keywords ### **Finding similar tracks:** When the user likes a track but wants variations (e.g., "something like this but slower"), use `similarToTrackId` with the track's ID. Combine with filters to narrow results — for example, `similarToTrackId` + `bpmMax: 100` finds slower alternatives with a similar feel. ### **If the user can't find the right track:** If multiple searches haven't found what the user is looking for, suggest they browse the full Epidemic Sound catalog at https://www.epidemicsound.com/music/search/ and return with the track URL (e.g. `https://www.epidemicsound.com/music/tracks/2d4374c6-be3c-4d2d-9057-8bb4f8a049e0/`). Extract the track ID from the URL path and apply it directly via `edit_composition_source_code` using `resolveEpidemicSoundMusic("<extracted-id>")` — do NOT pass it as `externalTrackUrl`. ### **Examples:** ✅ CC options didn't fit / "more options" → `search_epidemic_sound_music({ query: "gentle memorial piano" })` ✅ Specific genre ("I want jazz") → `search_epidemic_sound_music({ query: "jazz", genre: "jazz" })` (use both query and genre filter, skip CC) ✅ Named commercial song → don't search yet. Two required steps: (1) explain that a similar-feel track is what this finds, (2) ask for a Spotify link to use as a reference (externalTrackUrl gives better results). Only then search: <bad_example> <signal>User names a specific commercial song</signal> <user>Can you use a specific commercial song?</user> <wrong_tool>search_epidemic_sound_music({ "query": "song title and artist" })</wrong_tool> <correct_tool>None — ask about Spotify link first</correct_tool> <why_bad>Two mistakes: (1) did not explain to the user that this catalog is searched for a similar feel rather than that exact song, and (2) searched immediately instead of first asking for a Spotify link. The correct flow is: explain what the search does, ask for a Spotify link (externalTrackUrl gives much better results), then search.</why_bad> </bad_example> <example> <signal>User provides a Spotify link as a reference</signal> <user>Here: https://open.spotify.com/track/abc123</user> <tool_calls>search_epidemic_sound_music({ "externalTrackUrl": "https://open.spotify.com/track/abc123" })</tool_calls> <reasoning>User provided the link. Search with externalTrackUrl for the best style match.</reasoning> </example> <example> <signal>User doesn't have a Spotify link</signal> <user>I don't have a link, just search by name</user> <tool_calls>search_epidemic_sound_music({ "query": "song title and artist" })</tool_calls> <reasoning>No Spotify link available. Fall back to keyword search with song name and artist.</reasoning> </example> ✅ "Similar but slower" → `search_epidemic_sound_music({ similarToTrackId: "<ID_FROM_WIDGET_CONTEXT>", bpmMax: 100 })` ❌ Generic music request ("can I change the music?") → use `show_creative_commons_music` first per music workflow ❌ Epidemic Sound URL (epidemicsound.com/music/tracks/`<uuid>`) → don't search. Extract track ID from URL path, apply directly via `edit_composition_source_code` using `resolveEpidemicSoundMusic("<uuid>")`. `externalTrackUrl` is only for Spotify/non-ES links --- ## Returns 1. **resolveFn** (literal) 2. **tracks** (array) 2.1. **trackId** (string) 2.2. **title** (string) 2.3. **artists** (array) 2.4. **bpm** (number) 2.5. **durationSeconds** (number) 2.6. **moods** (array) 2.7. **genres** (array)

search_epidemic_sound_music

# show_assets (Tool) - Show Assets **Show all uploaded assets.** Opens the visual asset browser where users can see all their uploaded photos, videos, and audio files with thumbnails. ### **Use this tool for:** - **Viewing assets** - User asks "show me the assets", "let me see what's uploaded", "what photos do I have?" - **Reviewing uploads** - User wants to check what they've uploaded so far - **Picking a replacement** - User selects an element in the composition and says "replace this with another photo I uploaded". Open the asset browser so they can pick the one they want ### **Do NOT use this tool for:** - User needs to upload new assets (use `upload_assets` instead). - Just analyzing assets internally during planning (use `list_assets` instead).

show_assets

<music_workflow> # **MUSIC WORKFLOW** Search, preview, and apply background music to the composition. ## **When this workflow applies** Any time the user's request involves music. This includes but is not limited to: - "change the music" / "I don't like this song" / "the music doesn't fit" - "something more upbeat" / "can we try something calmer" - "more piano" / "I want jazz" / "something with guitar" (specific genre or instrument → Epidemic Sound) - "what music do you have?" / "can I hear the options?" - "use Faith Hill's There You'll Be" / "play Something Just Like This" / any specific song or artist name - "add background music" / "I want music" / "can we put a song on this?" - "make it more emotional" / "the vibe is off" (when referring to audio/mood, not visuals) - "something like the current track but slower" / "similar to this one" ## Steps ### Step 1: Search for tracks **Start with Creative Commons** (`show_creative_commons_music`) — it's a curated catalog of instrumental, royalty-free tracks. **Escalate to Epidemic Sound** (`search_epidemic_sound_music`) when: - The user asks for a **specific song, artist, genre, or instrument** (e.g., "use Faith Hill's There You'll Be", "I want jazz", "more piano") - The user **didn't find anything they liked** in the CC catalog - The user explicitly asks for **more options** or a **broader selection** ### Step 2: Let the user preview and choose Both tools return tracks with **inline audio previews in the widget**. Let the user listen and choose. Do NOT skip this step or pick without presenting options. The user selects a track via the widget — you will see their choice in **widget context**. ### Step 3: Apply the user's choice When the user clicks **"+"** or **"Add this"** in the widget, the widget attempts to auto-apply the track directly. Check the widget context: - **`autoApplied: true`** → The music was already switched. Confirm to the user and move on. No `edit_composition_source_code` call needed. - **`autoApplied: false`** (or not present) → The widget could not auto-apply. Apply it manually via `edit_composition_source_code`: - For Creative Commons tracks: `resolveCreativeCommonsMusic("<NEW_TRACK_ID_FROM_WIDGET_CONTEXT>")` - For Epidemic Sound tracks: `resolveEpidemicSoundMusic("<NEW_TRACK_ID_FROM_WIDGET_CONTEXT>")` ### Step 4: Verify If you applied the edit manually (Step 3, `autoApplied: false`), check the `typeErrors` field in the edit response. If there are errors, fix them yourself with follow-up edits, keeping the raw error text out of your replies — confirm the music change in plain language once it's clean. ## Hard rules - **Never guess or invent track IDs.** Every track ID must come from: music widget results, or a direct `epidemicsound.com/music/tracks/<id>` URL the user shared. - **Never skip the preview step.** The user must hear options before you apply anything — unless they provided a direct Epidemic Sound URL (they already know what they want). - **Never claim to have changed the music without actually calling these tools.** Presenting music options is a required step. </music_workflow> # show_creative_commons_music (Tool) - Show Creative Commons Music **Show all available Creative Commons music tracks.** Returns the curated catalog of royalty-free Creative Commons music tracks available for use as background music in compositions. Returns track details with **inline audio preview in the widget** — the user can listen directly from the results. `compositionId` is required because picking a track in the widget applies it to that composition's source directly. ### **Use this tool when:** - The user wants to **change or browse music** — this is the **default first step** in the `<music_workflow>` - The user wants to **hear what's available** without a specific song or artist in mind ### **Do NOT use this tool when:** - The user asks for a **specific song, artist, genre, or instrument** (e.g., "I want jazz", "more piano", "something with guitar") — use `search_epidemic_sound_music` instead, it has 55,000+ tracks to filter from - The user already browsed CC tracks and **wants more options** — `search_epidemic_sound_music` supports genre/mood/BPM filtering across a much larger catalog ### **After the user selects a track:** Follow the `<music_workflow>` to apply it. ### **Examples:** ✅ "Can I change the music?" / "What music do you have?" / "Can I listen first?" → show_creative_commons_music (generic requests always start with CC). Example response: "Sure! Here are our curated Creative Commons tracks — have a listen. If none of these feel right, I can also search a wider royalty-free catalog of 55,000+ tracks." ❌ Generic music request → jumping to `search_epidemic_sound_music`. Start with CC first per the music workflow ❌ Claiming you can't play audio previews → this tool DOES return playable inline audio previews in the widget. There is no separate "music section in the editor" ❌ Inventing a catalog of music categories (e.g., "1. Soft Piano 2. Piano + Strings 3. Ambient / Atmospheric...") instead of calling the tool → always show actual tracks with playable previews --- ## Returns 1. **resolveFn** (literal) 2. **tracks** (array) 2.1. **trackId** (string) 2.2. **title** (string) 2.3. **artists** (array) 2.4. **bpm** (number) 2.5. **durationSeconds** (number) 2.6. **moods** (array) 2.7. **instrumentation** (string)

show_creative_commons_music

# show_player (Tool) - Show Player **Opens the interactive video player widget with real-time editing.** The player renders the current composition and reflects edits instantly via websocket HMR. The user can play, pause, seek through scenes, and click elements to select them. ### **Widget context (critical)** When the player is open, it continuously sends model context with: - **Current frame** and timestamp - **Active scene**: index (1-based), name, start/end frames, duration - **Selected element**: type (text/image/video), content, component path, styles **ALWAYS re-read the player widget context before acting on each user message.** The user may have navigated to a different scene or selected a different element since their last message. The user's references ("this text", "make it bigger", "I don't like this") only make sense when you know what they're looking at *right now*. ### **Interactive workflow** 1. Call `show_player` to open the player widget 2. User watches the video, pauses, and clicks elements to select them 3. Check widget context to understand what the user sees and has selected 4. Use `grep_composition_source_code` to find the relevant code using the component path or content from widget context 5. Use `edit_composition_source_code` to make changes — the player updates in real-time ### **Use this tool for:** - **Showing the video** — When the user wants to see or review the composition - **Interactive editing** — When the user wants to watch and give visual feedback - **Starting an edit session** — Before iterating on composition changes ### **Do NOT use this tool for:** - Reading composition data without showing the player (use `read_composition_source_code` instead) - Searching composition source code (use `grep_composition_source_code` instead) ### **Important notes:** - The user can click text, images and other videos in the player to select them. The selection is sent via widget context including the component path, which maps to the composition source code - If the user's reference is ambiguous and no element is selected, ask them to click the element they mean - Changes via `edit_composition_source_code` are reflected in the player instantly — no need to re-call `show_player` ### **Examples:** ✅ "Show me the video" → show_player (preview existing composition) ✅ "Show me the result" (player already open) → no tool call needed, player updates in real-time via HMR ✅ "I want to tweak some things" → show_player (enables click-to-select for interactive editing) ❌ "How can I download it?" → use `render_video_task` (show_player is a live preview, not an exportable file) ❌ "Make a video from my photos" → use `create_composition_task` ("make"/"create" = generation, show_player only displays existing)

show_player

# update_project (Tool) - Update Project This tool updates an existing Glinded project's metadata. Only the fields you provide will be updated - omitted fields remain unchanged.

update_project

# upload_assets (Tool) - Upload Assets **Open the asset upload widget.** **Mandatory for collecting new assets.** Do not ask users to send files in chat — use this widget instead. It opens a dedicated upload interface where users can: - Upload 100+ photos, videos, and audio files at once via file picker - Share an upload link with family and friends so they can contribute assets Opening the widget provisions the upload session; files are added only when the user (or someone with the shared link) acts inside it. ### **Use this tool for:** - **Collecting assets** - This is the BEST tool for getting new files into a Glinded project - **Adding more files** - User wants to add more assets at any point - **Gathering from family** - The widget lets users share an upload link so family and friends can contribute assets ### **Do NOT use this tool for:** - User asks to see/view/browse their assets (use `show_assets` instead). - Just analyzing assets internally (use `list_assets` instead). ### **Important notes:** - The widget context updates `totalCount` in real-time as the user uploads. Use the latest value from widget context as `assetCount` when calling `create_composition_task`. --- ## Returns 1. **totalCount** (number)

upload_assets