DeepSeek Harness

Connect DeepSeek Harness (dsh) to Requesty for access to 600+ models, cost tracking and fallback routing

DeepSeek Harness is a plugin based coding agent from DeepSeek. It runs in your terminal as dsh and in a local web UI.

Using the Requesty integration, you can:

• Access 600+ models from DeepSeek, OpenAI, Anthropic, Google, Mistral and many other providers through one API key.
• Keep every request, its cost and its latency in one dashboard.
• Apply fallback policies, load balancing and latency routing to your agent runs.
• Switch models without reinstalling or reconfiguring the harness.

The Requesty CLI writes this configuration for you: run requesty, select DeepSeek Harness, pick a model, and it backs up your existing files before writing.

Prerequisites

• DeepSeek Harness installed on your machine. npx @deepseek-ai/dsh web runs it without a global install, and Node 22.19 or later is required.
• A Requesty API key from the API Keys page.

How the configuration works

DeepSeek Harness keeps user configuration in its harness home, which is ~/.dsh unless you set DSH_HOME:

File	Purpose
~/.dsh/profiles/<profile>/cordis.patch.yml	Providers, models and the default model for one profile, such as web or headless.
~/.dsh/.credentials.yaml	API keys, referenced by name from the profile config.

Older harness versions used a single ~/.dsh/settings.yaml. Current versions import that file once, into whichever profile starts first, and rename it to settings.yaml.imported. Other profiles never see it, so put the Requesty config in each profile you use.

Requesty is an OpenAI compatible endpoint, so it plugs into the harness as a custom provider on the llm-pi-ai plugin. No plugin needs to be installed for this.

Configuration

1. Install DeepSeek Harness

   Run the web UI once to create the harness home:

   npx @deepseek-ai/dsh web
   

   You can also install from source. See the DeepSeek Harness README for that path.

2. Store your Requesty API key

   Add your key to ~/.dsh/.credentials.yaml:

   REQUESTY_API_KEY: rqsty-sk-....
   

   Replace rqsty-sk-.... with your key from the API Keys page.

   The harness requires this file to be readable by you only. Set the permissions after creating it:

   chmod 700 ~/.dsh && chmod 600 ~/.dsh/.credentials.yaml
   

   Exporting REQUESTY_API_KEY in your shell works as well, and a value from the environment wins over the stored one. Use the file when you want the key to survive across terminals.

3. Add Requesty as a provider

   Edit the patch file of the profile you run, for example ~/.dsh/profiles/headless/cordis.patch.yml for terminal runs or ~/.dsh/profiles/web/cordis.patch.yml for the web UI. The harness creates the profile folder the first time that profile starts. The file is a YAML list of plugin entries:

   - id: agent-default-model
     name: "@deepseek-ai/dsh-agent-default-model"
     config:
       provider: requesty
       model: deepseek/deepseek-v4-pro-0813
   - id: llm-pi-ai
     name: "@deepseek-ai/dsh-llm-pi-ai"
     config:
       providers:
         requesty:
           displayName: Requesty
           apiKeyEnv: REQUESTY_API_KEY
           api: openai-completions
           baseURL: https://router.requesty.ai/v1
           defaultContextWindow: 200000
           defaultMaxTokens: 8192
           headers:
             HTTP-Referer: https://requesty.ai
             X-Title: DeepSeek Harness
           models:
             - id: deepseek/deepseek-v4-pro-0813
               name: DeepSeek V4 Pro (Requesty)
             - id: anthropic/claude-sonnet-4-6
               name: Claude Sonnet 4.6 (Requesty)
               input: [text, image]
             - id: openai/gpt-5.4
               name: GPT-5.4 (Requesty)
   - id: web-search-deepseek
     disabled: true
   - id: web
     disabled: true
   - id: tool-web
     disabled: true
   

   What each field does:

   Field	Value
   apiKeyEnv	Name of the credential to use, not the key itself.
   api	openai-completions, the Requesty Chat Completions format.
   baseURL	https://router.requesty.ai/v1, including the /v1 suffix.
   models	The models you want in the model picker, each with a full Requesty model id.
   headers	Optional analytics headers that tag these requests in your dashboard.

   The three disabled entries turn off the default web search plugins, which call DeepSeek directly and fail with MISSING_CREDENTIAL unless you also set DEEPSEEK_API_KEY. Remove them if you have a DeepSeek key and want web search.

   Use a full Requesty model id such as deepseek/deepseek-v4-pro-0813 to pin a provider, or a bare Managed Policy name such as deepseek-v4.1-flash (or deepseek-v4.1-flash@eu) to let Requesty pick the provider.

   A model that accepts images needs input: [text, image] on its entry. Text only is the default.

4. Start the harness

   Run a task in your terminal:

   dsh --profile headless "list the files in this directory"
   

   Or open the web UI:

   dsh web
   

   From source, prefix the commands with pnpm, for example pnpm dsh web.

Configuring from the web UI

The web UI writes the same files, so you can skip the YAML:

1. Run dsh web and open the printed URL.
2. Go to Settings, then Models.
3. Choose Add a custom provider and fill in the form:
   • Provider id: requesty
   • Base URL: https://router.requesty.ai/v1
   • Protocol: OpenAI Chat Completions
   • API key: your Requesty key
4. Select Fetch available models to load the Requesty catalog, then pick the models you want.
5. Select a Requesty model as the default model for new sessions.

Selecting a model

The model picker lists every model on the requesty provider. Add or remove entries under models in the profile’s cordis.patch.yml to change that list, and set agent-default-model to the model new sessions should start with.

Browse ids in the Requesty model library. Policies work here too: use the policy id as the model id, for example policy/coding-fallback.

Verifying the integration

Run one task, then open the Requesty analytics dashboard. The request appears within seconds with its model, token counts and cost. Requests configured with the headers above are tagged DeepSeek Harness, so you can filter your dashboard by this integration.

You can also confirm that the harness reaches the router at all:

curl https://router.requesty.ai/v1/models \
  -H "Authorization: Bearer $REQUESTY_API_KEY"

This is the same endpoint the Fetch available models button calls.

Troubleshooting

MISSING_CREDENTIAL: no API key for provider route

The harness found the provider but no key. Check that the name in apiKeyEnv matches a key in ~/.dsh/.credentials.yaml exactly, or export that variable in the shell you start dsh from. The harness reads the environment at launch, so exporting a key after startup has no effect.

Credentials file rejected

The harness refuses to read ~/.dsh/.credentials.yaml if the file is readable by other users. Run chmod 600 ~/.dsh/.credentials.yaml. The file must be a plain mapping of credential name to key, with no wrapper level and no empty values.

404 page not found

The base URL does not match the protocol. Use https://router.requesty.ai/v1 with api: openai-completions. For api: anthropic-messages, use https://router.requesty.ai without the /v1 suffix, because the harness appends /v1/messages itself.

Model not found

Add the provider prefix to the id, for example openai/gpt-5.4. Confirm the id in the model library, and check approved models if your organization restricts which models a key may use.

Changes to the profile config do not apply

The harness watches its profile files, so most edits take effect immediately. If a run still uses the old provider, stop the process and start it again. Confirm you edited cordis.patch.yml for the profile you started, under the harness home in use, which is $DSH_HOME when that variable is set.

References

• DeepSeek Harness on GitHub
• Requesty CLI
• Requesty API Keys
• Requesty Model Library
• Analytics Headers
• Approved Models