Files
msd-core/docs
Tom Boucher 96806003c5 fix(#3229): shared model catalog source of truth for agent profiles + runtime tier defaults (#3230)
* docs(adr): add ADR-0003 model catalog module

* fix(#3229): add shared model catalog as source of truth for agent profiles and runtime tier defaults

Research / design (ADR-0003):
- Existing drift came from 4 independent model truths:
  1. CJS model-profiles.cjs
  2. SDK config-query.ts stale copy (18 agents)
  3. settings-advanced.md runtime tier table
  4. session-runner Claude-only profile map
- New design: one machine-readable Model Catalog Module in sdk/shared/
  that both packages ship and consume.

Implementation:
- sdk/shared/model-catalog.json — canonical source of truth for:
  - full 33-agent registry
  - per-agent golden (quality) alias + balanced/budget aliases
  - adaptive derivation from routingTier
  - agent→phaseType map
  - agent→dynamic-routing default tier map
  - runtime tier defaults for all supported runtimes
- get-shit-done/bin/lib/model-catalog.cjs — CJS adapter over the catalog
- sdk/src/model-catalog.ts — SDK adapter over the same catalog
- CJS model-profiles.cjs now re-exports derived data from model-catalog.cjs
- SDK config-query.ts now re-exports MODEL_PROFILES/VALID_PROFILES from
  model-catalog.ts instead of maintaining its own list
- sdk/src/query/helpers.ts runtime list now comes from the catalog (fixes hermes drift)
- sdk/src/session-runner.ts Claude profile→model-id mapping now resolves via catalog
- docs/CONFIGURATION.md + settings-advanced.md runtime tables updated to match catalog

Behavior changes:
- resolve-model now covers every shipped agent file on disk (33 agents)
- unknown-agent fallback is profile-semantic, not hardcoded sonnet:
  quality→opus, budget→haiku, balanced/adaptive→sonnet, inherit→inherit
- Group B runtimes remain known runtimes but do not get built-in tier defaults

Tests (RED→GREEN):
- root tests: shipped agent files must equal MODEL_PROFILES keys
- sdk tests: shipped agent files must equal MODEL_PROFILES keys
- direct fix assertion: gsd-code-reviewer resolves to opus under quality with no unknown_agent
- runtime defaults parity test: settings-advanced.md + CONFIGURATION.md tables must match catalog
- helper tests: hermes included in SUPPORTED_RUNTIMES and getRuntimeConfigDir()

Closes #3229

* chore(changeset): update #3229 changeset pr field to 3230

* fix(ci): update inherit fallback expectations and inventory parity for model catalog
2026-05-08 21:25:37 -04:00
..

GSD Documentation

Comprehensive documentation for the Get Shit Done (GSD) framework — a meta-prompting, context engineering, and spec-driven development system for AI coding agents.

Language versions: English · Português (pt-BR) · 日本語 · 简体中文

Documentation Index

Document Audience Description
Architecture Contributors, advanced users System architecture, agent model, data flow, and internal design
Feature Reference All users Feature narratives and requirements for released features (see CHANGELOG for latest additions)
Command Reference All users Stable commands with syntax, flags, options, and examples
Configuration Reference All users Full config schema, workflow toggles, model profiles, git branching
CLI Tools Reference Contributors, agent authors gsd-tools.cjs programmatic API for workflows and agents
Agent Reference Contributors, advanced users Role cards for primary agents — roles, tools, spawn patterns (the agents/ filesystem is authoritative)
User Guide All users Workflow walkthroughs, troubleshooting, and recovery
Issue-Driven Orchestration All users Recipe for driving GSD from a tracker issue (GitHub / Linear / Jira) using existing primitives — no new commands or daemon
Context Monitor All users Context window monitoring hook architecture
Discuss Mode All users Assumptions vs interview mode for discuss-phase
Canary Stream Contributors, early adopters dev → @canary dist-tag policy, when to install, rollback path