# AI use cases for DSH Agent RP (hewzhew/dsh-agent-rp)

Repo: [hewzhew/dsh-agent-rp](https://github.com/hewzhew/dsh-agent-rp) | Use cases: 4 | Page: https://dedupedai.com/use-cases/hewzhew-dsh-agent-rp/

DSH Agent RP is a TypeScript roleplay runtime for DSH that runs characters as top-level agents and imports SillyTavern character cards, World Info, presets, and chat logs.

This file holds every use case of this repo. Each one starts with a "## " heading and ends with its URL.

- Chat with an imported character card in DSH: https://dedupedai.com/use-cases/hewzhew-dsh-agent-rp/play-imported-character-chat/
- Move a SillyTavern JSONL chat into Agent RP: https://dedupedai.com/use-cases/hewzhew-dsh-agent-rp/migrate-sillytavern-chat-history/
- Write a serial story with the story engine: https://dedupedai.com/use-cases/hewzhew-dsh-agent-rp/run-story-engine-with-workers/
- Build the repo from source and run compatibility checks: https://dedupedai.com/use-cases/hewzhew-dsh-agent-rp/build-and-test-compat-changes/

## How to chat with an imported character card in DSH with DSH Agent RP

Repo: [hewzhew/dsh-agent-rp](https://github.com/hewzhew/dsh-agent-rp) | Difficulty: Intermediate | Time: 30 minutes | Basis: From the README

Install Agent RP on Windows, import a character card, and start a character dialogue session.

**Who it is for:** A roleplay hobbyist with a PNG or JSON character card who wants to chat with it in DSH instead of SillyTavern.

**The problem:** Character cards stay locked to one front end, and setting up a roleplay runtime by hand is slow.

**The outcome:** A running Agent RP session where the imported character talks directly as the top-level agent.

### Steps

1. Run `npm install --global pnpm@11` if pnpm is not installed yet.
2. Run `Invoke-WebRequest 'https://raw.githubusercontent.com/hewzhew/dsh-agent-rp/main/scripts/install-windows.ps1' -OutFile $installerPath` after setting `$installerPath` as shown in the README.
3. Run `powershell -NoProfile -ExecutionPolicy Bypass -File $installerPath -Start` to install and start Agent RP.
4. In DSH, create a blank session, open Agent RP, choose 开始游玩, then 角色对话, and import your character card.
5. Pick a Persona and an opening line, check the listed permissions before launch, then start chatting.

### Prompt to paste into your agent

```text
In the repo hewzhew/dsh-agent-rp, follow the Windows install steps in README.md to install Agent RP, then import the character card at <path-to-card.png> through the 开始游玩 flow. Report the session name and the first line the character sends. Verify that the imported character appears in the resource library as a character card.
```

### Caveat

The README says the Windows installer pins the official DSH 0.1.1-rc.2 with a patch, so run the printed stable entry rather than the official runner.

Risk, remote script: Some cards include scripts, EJS, or HTML front ends; Agent RP checks known scripts and permissions before launch, but you should still review any permission prompt before approving it.

Dual-use notice: only use this on software, sites and systems you own or are authorized to test.

Disclaimer: Third-party repos we don't own or vouch for. AI-generated use cases can be wrong: review everything and run at your own risk. Full text: https://dedupedai.com/disclaimer/

URL: https://dedupedai.com/use-cases/hewzhew-dsh-agent-rp/play-imported-character-chat/

## How to move a SillyTavern JSONL chat into Agent RP with DSH Agent RP

Repo: [hewzhew/dsh-agent-rp](https://github.com/hewzhew/dsh-agent-rp) | Difficulty: Intermediate | Time: 45 minutes | Basis: From the README

Attach a SillyTavern JSONL log to a character session so the old chat carries over.

**Who it is for:** A long-time SillyTavern user who has a saved JSONL chat log and wants to continue that story in DSH.

**The problem:** Years of chat history stay trapped in SillyTavern files and cannot be reused in a new runtime.

**The outcome:** A new character dialogue in DSH that holds the migrated chat, while the source file and source session stay unchanged.

### Steps

1. Install and start Agent RP using the installer path for your operating system from the README.
2. Open a character session in DSH.
3. Attach your SillyTavern JSONL file to the session.
4. In the migration panel, pick a character card already in the resource library, or import a new PNG, JSON, or CHARX card.
5. Confirm the new character dialogue opens and check that the migrated messages appear.

### Prompt to paste into your agent

```text
In the repo hewzhew/dsh-agent-rp, use the migration panel described in the README to migrate <path-to-chat.jsonl> with the character card <path-to-card>. Report the new session name and the message count. Verify that the source JSONL file and the original session are unchanged.
```

### Caveat

The README says migration creates a new character dialogue and does not modify the source file, but it does not describe how much of the original formatting is preserved, so spot-check the result.

Dual-use notice: only use this on software, sites and systems you own or are authorized to test.

Disclaimer: Third-party repos we don't own or vouch for. AI-generated use cases can be wrong: review everything and run at your own risk. Full text: https://dedupedai.com/disclaimer/

URL: https://dedupedai.com/use-cases/hewzhew-dsh-agent-rp/migrate-sillytavern-chat-history/

## How to write a serial story with the story engine with DSH Agent RP

Repo: [hewzhew/dsh-agent-rp](https://github.com/hewzhew/dsh-agent-rp) | Difficulty: Advanced | Time: 60 minutes | Basis: From the README

Enable 故事工程 to keep an outline, foreshadowing, and character knowledge in sync across chapters.

**Who it is for:** A fiction writer with an ongoing multi-character story who needs consistent outlines and private knowledge for each character.

**The problem:** Long stories lose track of foreshadowing, public history, and who knows what, chapter after chapter.

**The outcome:** A story project with an editable outline and per-character knowledge, where the story engine writes each passage and records what happened afterward.

### Steps

1. Install and start Agent RP, then open a session with 开始游玩.
2. Enable 故事工程 and create a story project.
3. Edit the outline, foreshadowing list, public history, and character private knowledge.
4. Write a passage and let the research, character, director, section, and editor workers run before the final reply.
5. Review the events the story engine saved back to the project, then continue to the next passage.

### Prompt to paste into your agent

```text
In the repo hewzhew/dsh-agent-rp, read docs/story-engine.md and set up a story project following it for <story-title>. Report the outline sections created and confirm that character private knowledge is kept separate from public history. Verify that the saved events match the final passage.
```

### Caveat

The README says multi-character story engine support exists, but traditional group chat UI and multiple parallel top-level character agents are not finished yet.

Dual-use notice: only use this on software, sites and systems you own or are authorized to test.

Disclaimer: Third-party repos we don't own or vouch for. AI-generated use cases can be wrong: review everything and run at your own risk. Full text: https://dedupedai.com/disclaimer/

URL: https://dedupedai.com/use-cases/hewzhew-dsh-agent-rp/run-story-engine-with-workers/

## How to build the repo from source and run compatibility checks with DSH Agent RP

Repo: [hewzhew/dsh-agent-rp](https://github.com/hewzhew/dsh-agent-rp) | Difficulty: Advanced | Time: 60 minutes | Basis: From the README

Clone the source, build it, and check a card against the local compatibility benchmark.

**Who it is for:** A developer who wants to fix a SillyTavern compatibility gap and needs to test the change against real cards.

**The problem:** A card renders wrong in DSH, and the fix needs a local build and a repeatable test.

**The outcome:** A local build of Agent RP loaded into the Agent Host with a compatibility result for the card.

### Steps

1. Clone the repository and open it in a terminal at the repo root.
2. Run `pnpm install`.
3. Run `pnpm run build`.
4. Run `dsh plugin --profile web add .` from the Agent Host so it points at the local directory.
5. Follow docs/compatibility-benchmark.md to run the synthetic benchmark and your local card checks, then record the results.

### Prompt to paste into your agent

```text
In the repo hewzhew/dsh-agent-rp, clone the source, run `pnpm install` and `pnpm run build`, then follow docs/compatibility-benchmark.md to test the card at <path-to-card>. Report the build result and any failing compatibility checks. Verify that the build succeeds before running the benchmark.
```

### Caveat

The README says developers should only clone the source when they need to modify it, and the public installer is the normal path for everyone else.

Risk, reverse engineering: The compatibility benchmark runs real community cards, so keep any private or unlicensed card out of public issues and logs.

Dual-use notice: only use this on software, sites and systems you own or are authorized to test.

Disclaimer: Third-party repos we don't own or vouch for. AI-generated use cases can be wrong: review everything and run at your own risk. Full text: https://dedupedai.com/disclaimer/

URL: https://dedupedai.com/use-cases/hewzhew-dsh-agent-rp/build-and-test-compat-changes/