Skip to main content
Glama

Server Configuration

Describes the environment variables required to run the server.

NameRequiredDescriptionDefault
REVIEWER_MODELNoReviewer model idgpt-5-mini
REVIEW_TIMEOUTNoTimeout for the whole review in ms (AbortController)120000
TELEMETRY_PATHNoRelative paths resolve against the repo root./data/reviews.jsonl
REVIEWER_API_KEYNoAPI key for the reviewer provider (omit for local servers)
MAX_REVIEW_TOKENSNoNear-hard cap on cumulative tokens (prompt + completion) across all phases20000
REVIEWER_BASE_URLNoAny OpenAI-compatible /chat/completions base URLhttps://api.openai.com/v1
TELEMETRY_ENABLEDNoOpt-in local JSONL telemetry. Booleans accept true/false, 1/0, yes/no, on/off; anything else is a startup errorfalse
REVIEWER_MAX_TOKENSNoMax completion tokens per call4000
BLINDREVIEW_ENV_FILENoSet to use a different .env file instead of <repo>/.env
REVIEWER_TEMPERATURENoOptional 0..2; not sent when empty, dropped automatically if rejected
BLINDNESS_LEAK_THRESHOLDNoProposal/blind-field 5-gram containment at which blind_first refuses (BLINDNESS_LEAK)0.5
BLINDNESS_WARN_THRESHOLDNoContainment at which meta.blindness_warning is set0.15
REVIEWER_REASONING_PARAMNoreasoning_effort (OpenAI/xAI) or reasoning_object (OpenRouter reasoning: {effort}); auto-detected from the URLauto
REVIEWER_REASONING_EFFORTNolow / medium / high; dropped automatically if the API rejects it

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