Skip to main content
Glama

Server Configuration

Describes the environment variables required to run the server.

NameRequiredDescriptionDefault
LAYA_MODELSNoAllowlist of model checkpoints that may be loaded.
LAYA_REDACT_STATENoIf true, input text is redacted from the JSON audit log.true
LAYA_DEFAULT_MODELNoDefault model to use, e.g. 'auto'.auto
LAYA_MAX_QUESTIONSNoMaximum number of questions per request.
LAYA_ALLOW_DOWNLOADNoAllow downloading model checkpoints on first run. Off by default.false
LAYA_MIN_CONFIDENCENoMinimum confidence threshold; lower-confidence answers are flagged.
LAYA_MAX_INPUT_CHARSNoMaximum number of input characters per request.

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

Features and capabilities supported by this server

Protocol revision2025-11-25

CapabilityDetails
tools
{
  "listChanged": false
}
prompts
{
  "listChanged": false
}
resources
{
  "subscribe": false,
  "listChanged": false
}
experimental
{}

Tools

Functions exposed to the LLM to take actions

NameDescription
decideA

Answer several typed questions about a state in one local forward pass.

Use this to offload System-1 judgment calls from the main model: classification, routing, scoring and yes/no gates over text, an email, a ticket or a JSON object — fast, local, and without hallucination. Each question is one of three types:

  • choice: {"type":"choice","instructions":"...","criteria":{"labelA":"desc","labelB":"desc"}}

  • score: {"type":"score","instructions":"...","criteria":["level0","level1","level2"]}

  • noul: {"type":"noul","instructions":"..."} (yes/no/unknown)

Returns every answer with its calibrated confidence and full probabilities, plus routing metadata explaining which checkpoint answered. model optionally pins english | multilingual | typed-decisions (default: the Router auto-selects per language/task).

classifyB

Assign the single best category to a state (one choice question).

Provide either labels (a list of category names) or criteria (a map of category -> short description; more accurate). Returns the chosen label, calibrated confidence, and the probability over all labels.

scoreB

Rate a state on an ordinal scale (one score question).

levels are the ordered rungs, lowest first, e.g. ["not urgent","soon","critical"]. Returns an expected score (0..len-1), the level legend, calibrated confidence, and per-level probabilities.

checkA

Answer a single yes/no/unknown question about a state (a noul gate).

Returns answer (yes | no), the probability of yes (0..1), and calibrated confidence. Ideal for agent control flow: "does the user request a refund?", "is this a security incident?".

triageA

Run a ready-made set of decisions over a state using a laya preset.

presets: triage (department/urgency/sentiment…), email, moderation (safety categories), guard (prompt-injection / policy gates). Returns all answers with confidence.

detect_languageB

Detect the script and language of a text (sub-millisecond, no model forward pass).

explain_routingA

Explain which checkpoint the Router would use for this state, without running inference.

list_modelsA

List the laya checkpoints this server may use, the default, device and offline status.

Prompts

Interactive templates invoked by user choice

NameDescription

No prompts

Resources

Contextual data attached and managed by the client

NameDescription

No resources

TDQS

A3.5/5.0

Scored across 8 tools

Disambiguation3/5

classify, score, and check are single-question wrappers around decide's choice/score/noul modes, so an agent choosing between decide and a specialized tool may face ambiguity for a one-off task. Their descriptions clearly separate the single-vs-multiple use cases, but the underlying semantics overlap.

Naming Consistency4/5

All tool names are lowercase and start with an imperative verb, with compound names following verb_noun (detect_language, explain_routing, list_models). The single-word verbs (decide, classify, score, check, triage) are a minor stylistic deviation from the compound pattern but remain predictable.

Tool Count4/5

Eight tools is a reasonable size for a decision-model server and stays inside the ideal 3-15 range. The count is slightly padded, though, because classify/score/check are specialized versions of decide's three question types.

Completeness4/5

The set covers general and specialized decisions, ready-made triage presets, language detection, routing explanation, and model listing—no obvious dead ends for inference workflows. Minor gaps include no queryable preset list or way to register custom presets, but these can be worked around.

Maintenance

ActivityMaintained
ResponsivenessNo issues