jev-router
Server Configuration
Describes the environment variables required to run the server.
| Name | Required | Description | Default |
|---|---|---|---|
| TYPESAFE_MODEL | No | Default model. | jev-latest |
| TYPESAFE_API_KEY | Yes | TypeSafe API key (get one at https://console.typesafe.ai/keys). Set in the environment of the harness, never in prompts or state. | |
| MAX_CONTEXT_CHARS | No | Cap on file context sent as state. | 200000 |
| TYPESAFE_API_BASE | No | API base URL. | https://api.typesafe.ai |
| JEV_ROUTER_TIMEOUT_MS | No | Per-request timeout. | 60000 |
| JEV_ROUTER_CONCURRENCY | No | Max in-flight requests in jev_batch (max 16). | 6 |
| JEV_ROUTER_MAX_RETRIES | No | Retries on 429/529/5xx (exponential backoff, honors Retry-After). | 3 |
| JEV_ROUTER_ALLOW_IMAGES | No | Send TypeSafe-Danger-Zone-Images: true for assets/box (experimental). | true |
| JEV_ROUTER_LONG_CONTEXT | No | Send TypeSafe-Danger-Zone-Long-Context: true. | false |
| JEV_ROUTER_MAX_CANDIDATES | No | Cap on workstream candidates in jev_plan_workstreams. | 24 |
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 recent community issues