Verity
by johnnyryan
Server Configuration
Describes the environment variables required to run the server.
| Name | Required | Description | Default |
|---|---|---|---|
| CONSULT_DUAL | No | Set to '0' to disable dual-GPU second-opinion path | 1 |
| WORKER_MODEL | No | Model ID for the cloud worker | |
| CRITIC_A_MODEL | No | Model name for Critic A | |
| CRITIC_B_MODEL | No | Model name for Critic B | |
| WORKER_API_KEY | No | API key for the cloud worker | |
| WORKER_ENDPOINT | No | Base URL for a cloud model worker, e.g. https://api.openai.com/v1 | |
| CRITIC_TIMEOUT_MS | No | Timeout in milliseconds for critic LLM calls | 45000 |
| WORKER_MODEL_NAME | No | Model name of the primary LLM (worker) as used in LM Studio or backend | |
| PIPELINE_TIMEOUT_MS | No | Timeout for the entire verification pipeline | 135000 |
| FAIL_SEVERITY_THRESHOLD | No | Threshold for fail severity | |
| MAX_UNAVAILABLE_CRITICS | No | Maximum number of critics allowed to be unavailable | 0 |
| WARN_SEVERITY_THRESHOLD | No | Threshold for warn severity |
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
ActivityInactive
ResponsivenessNo issues