Files
msd-core/get-shit-done/workflows/settings.md
Rezolv 86fb9c85c3 docs(sdk): registry docs and gsd-sdk query call sites (#2302 Track B) (#2340)
* feat(sdk): golden parity harness and query handler CJS alignment (#2302 Track A)

Golden/read-only parity tests and registry alignment, query handler fixes
(check-completion, state-mutation, commit, validate, summary, etc.), and
WAITING.json dual-write for .gsd/.planning readers.

Refs gsd-build/get-shit-done#2341

* fix(sdk): getMilestoneInfo matches GSD ROADMAP (🟡, last bold, STATE fallback)

- Recognize in-flight 🟡 milestone bullets like 🚧.
- Derive from last **vX.Y Title** before ## Phases when emoji absent.
- Fall back to STATE.md milestone when ROADMAP is missing; use last bare vX.Y
  in cleaned text instead of first (avoids v1.0 from shipped list).
- Fixes init.execute-phase milestone_version and buildStateFrontmatter after
  state.begin-phase (syncStateFrontmatter).

* feat(sdk): phase list, plan task structure, requirements extract handlers

- Register phase.list-plans, phase.list-artifacts, plan.task-structure,
  requirements.extract-from-plans (SDK-only; golden-policy exceptions).
- Add unit tests; document in QUERY-HANDLERS.md.
- writeProfile: honor --output, render dimensions, return profile_path and dimensions_scored.

* feat(sdk): centralize getGsdAgentsDir in query helpers

Extract agent directory resolution to helpers (GSD_AGENTS_DIR, primary
~/.claude/agents, legacy path). Use from init and docs-init init bundles.

docs(15): add 15-CONTEXT for autonomous phase-15 run.

* feat(sdk): query CLI CJS fallback and session correlation

- createRegistry(eventStream, sessionId) threads correlation into mutation events
- gsd-sdk query falls back to gsd-tools.cjs when no native handler matches
  (disable with GSD_QUERY_FALLBACK=off); stderr bridge warnings
- Export createRegistry from @gsd-build/sdk; add sdk/README.md
- Update QUERY-HANDLERS.md and registry module docs for fallback + sessionId
- Agents: prefer node dist/cli.js query over cat/grep for STATE and plans

* fix(sdk): init phase_found parity, docs-init agents path, state field extract

- Normalize findPhase not-found to null before roadmap fallback (matches findPhaseInternal)

- docs-init: use detectRuntime + resolveAgentsDir for checkAgentsInstalled

- state.cjs stateExtractField: horizontal whitespace only after colon (YAML progress guard)

- Tests: commit_docs default true; config-get golden uses temp config; golden integration green

Refs: #2302

* refactor(sdk): share SessionJsonlRecord in profile-extract-messages

CodeRabbit nit: dedupe JSONL record shape for isGenuineUserMessage and streamExtractMessages.

* fix(sdk): address CodeRabbit major threads (paths, gates, audit, verify)

- Resolve @file: and CLI JSON indirection relative to projectDir; guard empty normalized query command

- plan.task-structure + intel extract/patch-meta: resolvePathUnderProject containment

- check.config-gates: safe string booleans; plan_checker alias precedence over plan_check default

- state.validate/sync: phaseTokenMatches + comparePhaseNum ordering

- verify.schema-drift: token match phase dirs; files_modified from parsed frontmatter

- audit-open: has_scan_errors, unreadable rows, human report when scans fail

- requirements PLANNED key PLAN for root PLAN.md; gsd-tools timeout note

- ingest-docs: repo-root path containment; classifier output slug-hash

Golden parity test strips has_scan_errors until CJS adds field.

* fix: Resolve CodeRabbit security and quality findings
- Secure intel.ts and cli.ts against path traversal
- Catch and validate git add status in commit.ts
- Expand roadmap milestone marker extraction
- Fix parsing array-of-objects in frontmatter YAML
- Fix unhandled config evaluations
- Improve coverage test parity mapping

* docs(sdk): registry docs and gsd-sdk query call sites (#2302 Track B)

Update CHANGELOG, architecture and user guides, workflow call sites, and read-guard tests for gsd-sdk query; sync ARCHITECTURE.md command/workflow counts and directory-tree totals with the repo (80 commands, 77 workflows).

Address CodeRabbit: fix markdown tables and emphasis; align CLI-TOOLS GSDTools and state.read docs with implementation; correct roadmap handler name in universal-anti-patterns; resolve settings workflow config path without relying on config_path from state.load.

Refs gsd-build/get-shit-done#2340

* test: raise planner character extraction limit to 48K

* fix(sdk): resolve build TS error and doc conflict markers
2026-04-20 18:09:21 -04:00

13 KiB

Interactive configuration of GSD workflow agents (research, plan_check, verifier) and model profile selection via multi-question prompt. Updates .planning/config.json with user preferences. Optionally saves settings as global defaults (~/.gsd/defaults.json) for future projects.

<required_reading> Read all files referenced by the invoking prompt's execution_context before starting. </required_reading>

Ensure config exists and load current state:
gsd-sdk query config-ensure-section
INIT=$(gsd-sdk query state.load)
if [[ "$INIT" == @file:* ]]; then INIT=$(cat "${INIT#@file:}"); fi
# `state.load` returns STATE frontmatter JSON from the SDK — it does not include `config_path`. Orchestrators may set `GSD_CONFIG_PATH` from init phase-op JSON; otherwise resolve the same path gsd-tools uses for flat vs active workstream (#2282).
if [[ -z "${GSD_CONFIG_PATH:-}" ]]; then
  if [[ -f .planning/active-workstream ]]; then
    WS=$(tr -d '\n\r' < .planning/active-workstream)
    GSD_CONFIG_PATH=".planning/workstreams/${WS}/config.json"
  else
    GSD_CONFIG_PATH=".planning/config.json"
  fi
fi

Creates config.json (at the resolved path) with defaults if missing. INIT still holds state.load output for any step that needs STATE fields. Store $GSD_CONFIG_PATH — all subsequent reads and writes use this path, not a hardcoded .planning/config.json, so active-workstream installs target the correct file (#2282).

```bash cat "$GSD_CONFIG_PATH" ```

Parse current values (default to true if not present):

  • workflow.research — spawn researcher during plan-phase
  • workflow.plan_check — spawn plan checker during plan-phase
  • workflow.verifier — spawn verifier during execute-phase
  • workflow.nyquist_validation — validation architecture research during plan-phase (default: true if absent)
  • workflow.ui_phase — generate UI-SPEC.md design contracts for frontend phases (default: true if absent)
  • workflow.ui_safety_gate — prompt to run /gsd-ui-phase before planning frontend phases (default: true if absent)
  • workflow.ai_integration_phase — framework selection + eval strategy for AI phases (default: true if absent)
  • model_profile — which model each agent uses (default: balanced)
  • git.branching_strategy — branching approach (default: "none")
  • workflow.use_worktrees — whether parallel executor agents run in worktree isolation (default: true)

Text mode (workflow.text_mode: true in config or --text flag): Set TEXT_MODE=true if --text is present in $ARGUMENTS OR text_mode from init JSON is true. When TEXT_MODE is active, replace every AskUserQuestion call with a plain-text numbered list and ask the user to type their choice number. This is required for non-Claude runtimes (OpenAI Codex, Gemini CLI, etc.) where AskUserQuestion is not available. Use AskUserQuestion with current values pre-selected:

AskUserQuestion([
  {
    question: "Which model profile for agents?",
    header: "Model",
    multiSelect: false,
    options: [
      { label: "Quality", description: "Opus everywhere except verification (highest cost)" },
      { label: "Balanced (Recommended)", description: "Opus for planning, Sonnet for research/execution/verification" },
      { label: "Budget", description: "Sonnet for writing, Haiku for research/verification (lowest cost)" },
      { label: "Inherit", description: "Use current session model for all agents (best for OpenRouter, local models, or runtime model switching)" }
    ]
  },
  {
    question: "Spawn Plan Researcher? (researches domain before planning)",
    header: "Research",
    multiSelect: false,
    options: [
      { label: "Yes", description: "Research phase goals before planning" },
      { label: "No", description: "Skip research, plan directly" }
    ]
  },
  {
    question: "Spawn Plan Checker? (verifies plans before execution)",
    header: "Plan Check",
    multiSelect: false,
    options: [
      { label: "Yes", description: "Verify plans meet phase goals" },
      { label: "No", description: "Skip plan verification" }
    ]
  },
  {
    question: "Spawn Execution Verifier? (verifies phase completion)",
    header: "Verifier",
    multiSelect: false,
    options: [
      { label: "Yes", description: "Verify must-haves after execution" },
      { label: "No", description: "Skip post-execution verification" }
    ]
  },
  {
    question: "Auto-advance pipeline? (discuss → plan → execute automatically)",
    header: "Auto",
    multiSelect: false,
    options: [
      { label: "No (Recommended)", description: "Manual /clear + paste between stages" },
      { label: "Yes", description: "Chain stages via Task() subagents (same isolation)" }
    ]
  },
  {
    question: "Enable Nyquist Validation? (researches test coverage during planning)",
    header: "Nyquist",
    multiSelect: false,
    options: [
      { label: "Yes (Recommended)", description: "Research automated test coverage during plan-phase. Adds validation requirements to plans. Blocks approval if tasks lack automated verify." },
      { label: "No", description: "Skip validation research. Good for rapid prototyping or no-test phases." }
    ]
  },
  // Note: Nyquist validation depends on research output. If research is disabled,
  // plan-phase automatically skips Nyquist steps (no RESEARCH.md to extract from).
  {
    question: "Enable UI Phase? (generates UI-SPEC.md design contracts for frontend phases)",
    header: "UI Phase",
    multiSelect: false,
    options: [
      { label: "Yes (Recommended)", description: "Generate UI design contracts before planning frontend phases. Locks spacing, typography, color, and copywriting." },
      { label: "No", description: "Skip UI-SPEC generation. Good for backend-only projects or API phases." }
    ]
  },
  {
    question: "Enable UI Safety Gate? (prompts to run /gsd-ui-phase before planning frontend phases)",
    header: "UI Gate",
    multiSelect: false,
    options: [
      { label: "Yes (Recommended)", description: "plan-phase asks to run /gsd-ui-phase first when frontend indicators detected." },
      { label: "No", description: "No prompt — plan-phase proceeds without UI-SPEC check." }
    ]
  },
  {
    question: "Enable AI Phase? (framework selection + eval strategy for AI phases)",
    header: "AI Phase",
    multiSelect: false,
    options: [
      { label: "Yes (Recommended)", description: "Run /gsd-ai-phase before planning AI system phases. Surfaces the right framework, researches its docs, and designs the evaluation strategy." },
      { label: "No", description: "Skip AI design contract. Good for non-AI phases or when framework is already decided." }
    ]
  },
  {
    question: "Git branching strategy?",
    header: "Branching",
    multiSelect: false,
    options: [
      { label: "None (Recommended)", description: "Commit directly to current branch" },
      { label: "Per Phase", description: "Create branch for each phase (gsd/phase-{N}-{name})" },
      { label: "Per Milestone", description: "Create branch for entire milestone (gsd/{version}-{name})" }
    ]
  },
  {
    question: "Enable context window warnings? (injects advisory messages when context is getting full)",
    header: "Ctx Warnings",
    multiSelect: false,
    options: [
      { label: "Yes (Recommended)", description: "Warn when context usage exceeds 65%. Helps avoid losing work." },
      { label: "No", description: "Disable warnings. Allows Claude to reach auto-compact naturally. Good for long unattended runs." }
    ]
  },
  {
    question: "Research best practices before asking questions? (web search during new-project and discuss-phase)",
    header: "Research Qs",
    multiSelect: false,
    options: [
      { label: "No (Recommended)", description: "Ask questions directly. Faster, uses fewer tokens." },
      { label: "Yes", description: "Search web for best practices before each question group. More informed questions but uses more tokens." }
    ]
  },
  {
    question: "Skip discuss-phase in autonomous mode? (use ROADMAP phase goals as spec)",
    header: "Skip Discuss",
    multiSelect: false,
    options: [
      { label: "No (Recommended)", description: "Run smart discuss before each phase — surfaces gray areas and captures decisions." },
      { label: "Yes", description: "Skip discuss in /gsd-autonomous — chain directly to plan. Best for backend/pipeline work where phase descriptions are the spec." }
    ]
  },
  {
    question: "Use git worktrees for parallel agent isolation?",
    header: "Worktrees",
    multiSelect: false,
    options: [
      { label: "Yes (Recommended)", description: "Each parallel executor runs in its own worktree branch — no conflicts between agents." },
      { label: "No", description: "Disable worktree isolation. Agents run sequentially on the main working tree. Use if EnterWorktree creates branches from wrong base (known cross-platform issue)." }
    ]
  }
])
Merge new settings into existing config.json:
{
  ...existing_config,
  "model_profile": "quality" | "balanced" | "budget" | "adaptive" | "inherit",
  "workflow": {
    "research": true/false,
    "plan_check": true/false,
    "verifier": true/false,
    "auto_advance": true/false,
    "nyquist_validation": true/false,
    "ui_phase": true/false,
    "ui_safety_gate": true/false,
    "ai_integration_phase": true/false,
    "text_mode": true/false,
    "research_before_questions": true/false,
    "discuss_mode": "discuss" | "assumptions",
    "skip_discuss": true/false,
    "use_worktrees": true/false
  },
  "git": {
    "branching_strategy": "none" | "phase" | "milestone",
    "quick_branch_template": <string|null>
  },
  "hooks": {
    "context_warnings": true/false,
    "workflow_guard": true/false
  }
}

Write updated config to $GSD_CONFIG_PATH (the workstream-aware path resolved in ensure_and_load_config). Never hardcode .planning/config.json — workstream installs route to .planning/workstreams/<slug>/config.json.

Ask whether to save these settings as global defaults for future projects:
AskUserQuestion([
  {
    question: "Save these as default settings for all new projects?",
    header: "Defaults",
    multiSelect: false,
    options: [
      { label: "Yes", description: "New projects start with these settings (saved to ~/.gsd/defaults.json)" },
      { label: "No", description: "Only apply to this project" }
    ]
  }
])

If "Yes": write the same config object (minus project-specific fields like brave_search) to ~/.gsd/defaults.json:

mkdir -p ~/.gsd

Write ~/.gsd/defaults.json with:

{
  "mode": <current>,
  "granularity": <current>,
  "model_profile": <current>,
  "commit_docs": <current>,
  "parallelization": <current>,
  "branching_strategy": <current>,
  "quick_branch_template": <current>,
  "workflow": {
    "research": <current>,
    "plan_check": <current>,
    "verifier": <current>,
    "auto_advance": <current>,
    "nyquist_validation": <current>,
    "ui_phase": <current>,
    "ui_safety_gate": <current>,
    "ai_integration_phase": <current>,
    "skip_discuss": <current>
  }
}
Display:
━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━
 GSD ► SETTINGS UPDATED
━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━

| Setting              | Value |
|----------------------|-------|
| Model Profile        | {quality/balanced/budget/inherit} |
| Plan Researcher      | {On/Off} |
| Plan Checker         | {On/Off} |
| Execution Verifier   | {On/Off} |
| Auto-Advance         | {On/Off} |
| Nyquist Validation   | {On/Off} |
| UI Phase             | {On/Off} |
| UI Safety Gate       | {On/Off} |
| AI Integration Phase | {On/Off} |
| Git Branching        | {None/Per Phase/Per Milestone} |
| Skip Discuss         | {On/Off} |
| Context Warnings     | {On/Off} |
| Saved as Defaults    | {Yes/No} |

These settings apply to future /gsd-plan-phase and /gsd-execute-phase runs.

Quick commands:
- /gsd-set-profile <profile> — switch model profile
- /gsd-plan-phase --research — force research
- /gsd-plan-phase --skip-research — skip research
- /gsd-plan-phase --skip-verify — skip plan check

<success_criteria>

  • Current config read
  • User presented with 14 settings (profile + 11 workflow toggles + git branching + ctx warnings)
  • Config updated with model_profile, workflow, and git sections
  • User offered to save as global defaults (~/.gsd/defaults.json)
  • Changes confirmed to user </success_criteria>