Skip to main content
Glama

Server Configuration

Describes the environment variables required to run the server.

NameRequiredDescriptionDefault
DSH_HOMENoThe DeepSeek Harness home directory, inherited by the child process so it picks up your AGENTS.md, skills and stored credentials.
DSH_SUBAGENT_MODELNoOverrides the child model per machine without editing files, e.g. DSH_SUBAGENT_MODEL=deepseek-v4-pro. Defaults to deepseek-flash (DeepSeek-V4.1-Flash at reasoning effort max).
DSH_SUBAGENT_INLINE_LIMITNoCharacter limit for answers returned inline. Above DSH_SUBAGENT_INLINE_LIMIT (default 24000 chars) the full text spills to state/results/<task>.md and the reply states the percentage shown.
DSH_SUBAGENT_MAX_CONCURRENCYNoBounded concurrency for delegated tasks, with a FIFO queue; extra calls return queued plus their position. 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

NameDescription

No tools

Prompts

Interactive templates invoked by user choice

NameDescription

No prompts

Resources

Contextual data attached and managed by the client

NameDescription

No resources