Skip to main content
Glama
koten-ai

io.github.koten-ai/zeus-dev-helper

Official
by koten-ai

Server Configuration

Describes the environment variables required to run the server.

NameRequiredDescriptionDefault
ZEUS_URLYesPublic Zeus API base URL (port 8080). Remote host first; localhost only when Zeus is local.
ZEUS_MODENoDefault catalog modeanalytics
ZEUS_SCOPENoScope for bootstrap and auth probes
LLM_API_KEYNoPresence checked by validate_env; required for smoke_test_agent
ZEUS_BUCKETNoScope for bootstrap and auth probes
ZEUS_PASSWORDNoBasic auth (never logged)
ZEUS_USERNAMENoBasic auth (never logged)
OPENAI_API_KEYNoPresence checked by validate_env; required for smoke_test_agent
ZEUS_AUTH_MODENoAuth mode (none, basic, bearer)
ZEUS_COLLECTIONNoScope for bootstrap and auth probes
ZEUS_BEARER_TOKENNoBearer auth (never logged)
ZEUS_CHAT_REQUEST_DIRNoLocal directory of min catalog templates; auto-set when list_catalog_modes / fetch_chat_request locate or clone public zeus_chat_request
DEMO_TRAVEL_SAMPLE_DIRNoLocal sample directory for use_sample / travel_golden_path
ZEUS_DEV_HELPER_TOOLSETSNoStatic toolsets: core (default), plus catalog,lint,travel,support,handoff or allcore
ZEUS_DEV_HELPER_STATE_DIRNoChecklist, prereqs, and local metrics~/.config/zeus_dev_helper

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
doctorB

Health / doctor. detail: health | env | compat | cache | all.

env/compat/cache fold validate_env, compat_check, and semantic_cache_status (those names stay on the lint toolset).

If the user already gave a Zeus URL or sample name, next call set_prereq with those values (not Helper localhost defaults), then start_project / next_step. Do not grep the Zeus engine tree for first green.

start_projectA

Start or reset first-app coaching checklist (single-agent default).

sample:

  • travel (default) — UI path via demo_travel_sample / use_sample

  • beer — zero-LLM Direct catalog UI (use_sample sample=beer)

  • api — API-only FastAPI scaffold (scaffold_app app_kind=api)

  • yelp / multi — gated until single-agent smokes green unless force_multi

Multi-agent goals (goal=multi or sample=yelp) are gated until single-agent smokes are green, unless force_multi=true (ZDH-11).

next_stepA

Return the single current checklist blocker + recommended Helper tools (coach).

Call only the recommended tool next. If the user named a URL/bucket and prereqs are unset, recommend set_prereq first. Prefer zeus-helper:// + readiness_check / smoke_test_zeus over hand-rolled curl.

set_prereqA

Store non-secret prereqs for readiness (does not store password/token values).

Put real secrets in environment variables (ZEUS_PASSWORD, ZEUS_BEARER_TOKEN, LLM_API_KEY). When the user named a Zeus URL or sample in chat, pass that zeus_url / bucket / scope here (not Helper localhost defaults). Persisted values override MCP host ZEUS_* env defaults so readiness/doctor hit the user's cluster (ZDM-3). Presence flags only for credentials and LLM key.

readiness_checkB

Live Zeus platform gates: healthz/readyz/version, auth, bootstrap, chat_request.

Never returns secret values. Emits failure_class + next_action on red paths.

scaffold_appC

Write a ZeusRuntime middle-man.

app_kind=cli (default) or api (FastAPI POST /turn). coding_language=python only today. UI demos use use_sample / demo_travel_sample, not this tool.

use_sampleB

UI sample: travel clone or beer Direct template.

sample=travel — locate/clone demo_travel_sample; set DEMO_TRAVEL_SAMPLE_DIR. sample=beer — write demo_beer_sample Direct catalog UI (no LLM; find→get). project_name = directory name (defaults: demo_travel_sample / demo_beer_sample). Extra travel-only phases stay on travel_golden_path (travel toolset).

smoke_test_zeusB

Smoke Zeus without LLM: readiness + POST /v2/{bucket}/{scope}/describe.

smoke_test_agentC

One ZeusRuntime run_turn (requires kotenai-zeus-client>=2.3.0 + LLM key).

If the client is missing and demo_travel_sample documents Docker install, returns guide-only docker compose next_action instead of only pip install.

diagnose_errorA

Map error signals to failure_class + errors.md anchor (ZDH-7 / ZDH-19).

Includes Detective URL templates when req_id/chat_id are present (folded detective_links). Does not scrape Hub.

recommend_surfaceC

Pick Direct vs agent surface + Trace-Class (ZDH-18). Does not call Zeus.

bind_contractA

Extract stamped contract.hash only. Refuse placeholders / compute_local (ZDH-22).

Prompts

Interactive templates invoked by user choice

NameDescription
first_greenDay-one path to a first green ZeusRuntime turn.
smoke_questionAdvice-shaped question for smoke_test_agent.
support_packRedacted support pack from a failed turn.

Resources

Contextual data attached and managed by the client

NameDescription
checklistFirst-app coaching checklist JSON
glossaryGlossary topic index (read zeus-helper://glossary/{topic} for a page)
verbsV2 verb index (read zeus-helper://verbs/{name} for a page)
hash_boundaryWhat is excluded from contract_hash (MINI-SCHEMA / brief)
req_id_policyOne UUID per hop; never composite hop ids; never Rewind /turn
catalog_modesV2 min chat_request modes from zeus_chat_request (TEMPLATE ONLY)

TDQS

B3.1/5.0

Scored across 12 tools

Disambiguation3/5

There is some overlap between smoke_test_agent and smoke_test_zeus, and between doctor and readiness_check, which could confuse an agent. However, other tools like bind_contract, scaffold_app, and use_sample have distinct purposes, so the ambiguity is limited.

Naming Consistency3/5

The naming is a mix of verb_noun patterns (e.g., smoke_test_agent, readiness_check) and bare verbs (doctor, next_step). While most use snake_case, the inconsistency between using 'check' in readiness_check and 'doctor' for health might cause minor confusion.

Tool Count4/5

With 12 tools, the count is within the typical well-scoped range for a complex developer assistant. Each tool addresses a different aspect of the development workflow, though the number feels slightly high but not problematic.

Completeness3/5

The set covers the core lifecycle of starting, configuring, and verifying a project, but lacks tools for explicit update or deletion of configuration or samples. Some workflows might require manual steps outside the toolset, creating minor gaps.

Maintenance

ActivityMaintained
ResponsivenessNo issues