Files
cdn/hanzo/market/tools/ambient-sound-journey-composer.json
zeekayandHanzo Dev edabf3842c feat(market): real catalog, verifiable versioning, purge-on-deploy
The Market read plane is files and nothing else. This makes that actually true
and actually deployable.

Catalog: was 10 mock "zoo-eco-agent" placeholders + 5 mock tools, which every
app would have shown to every user. Now generated from the curated flatfile
catalog (hanzoai/store data/{agents,tools}) -> 23 agents + 179 tools, each with
its own detail document. Drops purchases.json: per-user state has no business
on a public CDN. Strips upstream icon URLs, which are expired presigned R2 links
that carry an AWS credential + signature in the query string.

Versioning: index.json gains `schema` (breaking-shape gate, so a client that
does not recognise it keeps its bundle) and a `version` that is a content digest
over every served document. It changes iff what we serve changes, which is what
makes a deploy checkable rather than hopeful.

One writer: gen-market.py -> market.py with `gen` and `check`. It emits the CDN
documents AND each app's offline bundle, so the two cannot disagree about the
schema; `check` re-derives the digest and validates counts, ids, dangling
featured references and per-tool details, with no network and no other checkout.

Deploy: upload, then purge the Cloudflare edge for exactly the URLs written,
then verify the live manifest matches the repo and fail if it does not. Also
resolves wrangler once instead of re-resolving it per object.

CI: hanzo.yml + a 7-line cicd.yml importing hanzoai/ci. Static assets, so no
images:/deploy: — test: is the gate.

Co-authored-by: Hanzo Dev <[email protected]>
2026-07-27 20:40:33 -07:00

48 lines
2.4 KiB
JSON

{
"author": "hanzo.ai",
"category": {
"description": "",
"examples": "",
"id": "entertainment",
"name": "Entertainment"
},
"changelog": "",
"created_at": "2025-10-12T17:05:57.950Z",
"description": "This tool crafts custom, long-form evolving ambient soundscapes from a simple text description. It intelligently orchestrates a detailed composition plan, breaking the total duration into smaller, evolving segments. It then generates each segment individually, ensuring smooth, gradual transitions before seamlessly stitching them into a single, continuous MP3 audio file. It relies on local sound assets.\n\nIt's perfect for creating background audio for focus, relaxation, or storytelling that evolves over time.\n\nThis tool relies on the 'ambient sound composer' tool, which you can configure first.\n\n### How to Use It\n\nTo create your soundscape, simply write a descriptive `request` outlining the audio journey you envision. Be as detailed as you would like, or vague for more random outputs. You can define the `total_duration_minutes`, suggest a number of `segments` to guide the pacing, and provide a custom `output_filename` for the final MP3. These core inputs give you direct control over the final audio composition.\n\nFor more insight, you can use several optional toggles. Set `show_available_sounds` to `true` to get a list of all sound building blocks without generating audio. To see the AI's step-by-step \"recipe\" for your track, enable `show_composition_plan`. Finally, if you wish to examine the individual audio clips used, you can choose to `keep_intermediate_files` rather than having them automatically deleted.",
"downloads": 0,
"icon_url": "",
"id": "ambient-sound-journey-composer",
"install_command": "",
"license": "MIT",
"mcp_config": {
"args": [
"local:::__official_shinkai:::ambient_sound_journey_composer"
],
"command": "any",
"env": {}
},
"name": "Ambient Sound Journey Composer",
"operating_system": [
"linux",
"macos",
"windows"
],
"path": "/tools/ambient-sound-journey-composer",
"price": 0,
"readme": "",
"repository": "github.com/hanzoai/tools",
"router_key": "@hanzo/ambient-sound-journey-composer",
"runner": "any",
"screenshots": [],
"tags": [
"ambient",
"audio",
"sound ",
"journey",
"soudscape"
],
"type": "Tool",
"updated_at": "2025-10-12T17:05:57.950Z",
"version": "1.0.0"
}