Plain-Language Desk
Server Configuration
Describes the environment variables required to run the server.
| Name | Required | Description | Default |
|---|---|---|---|
| BAR | No | Pass bar. Default is 80 (bundle value). | |
| PORT | No | Listen port. Default is 8080. | |
| AUTH_TOKEN | No | Set it and every path but /healthz needs Authorization: Bearer <token>. Unset means open. | |
| MAX_ROUNDS | No | Default round cap for /improve. Default is 3; request can set 1–5. | |
| RULESET_PATH | No | A ruleset bundle directory. Default is the shipped FAA bundle. | |
| INFERENCE_MODEL | Yes | Model name the endpoint serves. | |
| INFERENCE_API_KEY | No | Bearer key, if the endpoint wants one. Default is empty. | |
| INFERENCE_TIMEOUT | No | Per-call timeout. Default is 120 s. | |
| INFERENCE_BASE_URL | Yes | OpenAI-compatible chat-completions endpoint. Without it, /improve returns 503. | |
| INFERENCE_EXTRA_JSON | No | Raw JSON merged into each request body, for engine-specific kwargs. Default is empty. | |
| INFERENCE_MAX_RETRIES | No | Per-call retry count. Default is 2. |
Instructions
Guidance the server publishes about itself, which clients place ahead of the tool catalog so the model reads it before choosing anything.
This server publishes no instructions, or was last inspected before Glama recorded them.
Capabilities
Server capabilities have not been inspected yet.
Tools
Functions exposed to the LLM to take actions
| Name | Description |
|---|---|
No tools | |
Prompts
Interactive templates invoked by user choice
| Name | Description |
|---|---|
No prompts | |
Resources
Contextual data attached and managed by the client
| Name | Description |
|---|---|
No resources | |
This server cannot be deployed
Maintenance
ActivityMaintained
ResponsivenessNo issues