Files
msd-core/get-shit-done/workflows/import.md
Rezolv d3a79917fa feat: Phase 2 caller migration — gsd-sdk query in workflows, agents, commands (#2179)
* feat: Phase 2 caller migration — gsd-sdk query in workflows (#2122)

Cherry-picked orchestration rewrites from feat/sdk-foundation (#2008, 4018fee) onto current main, resolving conflicts to keep upstream worktree guards and post-merge test gate. SDK stub registry omitted (out of Phase 2 scope per #2122).

Refs: #2122 #2008
Made-with: Cursor

* docs: add gsd-sdk query migration blurb

Made-with: Cursor

* docs(workflows): extend Phase 2 gsd-sdk query caller migration

- Swap node gsd-tools.cjs for gsd-sdk query in review, plan-phase, execute-plan,
  ship, extract_learnings, ai-integration-phase, eval-review, next, thread
- Document graphify CJS-only in gsd-planner; dual-path in CLI-TOOLS and ARCHITECTURE
- Update tests: workstreams gsd-sdk path, thread frontmatter.get, workspace init.*,
  CRLF-safe autonomous frontmatter parse
- CHANGELOG: Phase 2 caller migration scope

Made-with: Cursor

* docs(phase2): USER-GUIDE + remaining gsd-sdk query call sites

- USER-GUIDE: dual-path CLI section; state validate/sync use full CJS path
- Commands: debug (config-get+tdd), quick (security note), intel Task prompt
- Agent: gsd-debug-session-manager resolve-model via jq
- Workflows: milestone-summary, forensics, next, complete-milestone/verify-work
  (audit-open CJS notes), discuss-phase, progress, verify-phase, add/insert/remove
  phase, transition, manager, quick workflow; remove-phase commit without --files
- Test: quick-session-management accepts frontmatter.get
- CHANGELOG: Phase 2 follow-up bullet

Made-with: Cursor

* docs(phase2): align gsd-sdk query examples in commands and agents

- init.* query names; frontmatter.get uses positional field name
- state.* handlers use positional args; commit uses positional paths
- CJS-only notes for from-gsd2 and graphify; learnings.query wording
- CHANGELOG: Phase 2 orchestration doc pass

Made-with: Cursor

* docs(phase2): normalize gsd-sdk query commit to positional file paths

- Strip --files from commit examples in workflows, references, commands
- Keep commit-to-subrepo ... --files (separate handler)
- git-planning-commit.md: document positional args
- Tests: new-project commit line, state.record-session, gates CRLF, roadmap.analyze
- CHANGELOG [Unreleased]

Made-with: Cursor

* feat(sdk): gsd-sdk query parity with gsd-tools and PR 2179 registry fixes

- Route query via longest-prefix match and dotted single-token expansion; fall back
  to runGsdToolsQuery (same argv as node gsd-tools.cjs) for full CLI coverage.
- Parse gsd-sdk query permissively so gsd-tools flags (--json, --verify, etc.) are
  not rejected by strict parseArgs.
- resolveGsdToolsPath: honor GSD_TOOLS_PATH; prefer bundled get-shit-done copy
  over project .claude installs; export runGsdToolsQuery from the SDK.
- Fix gsd-tools audit-open (core.output; pass object for --json JSON).
- Register summary-extract as alias of summary.extract; fix audit-fix workflow to
  call audit-uat instead of invalid init.audit-uat (PR review).

Updates QUERY-HANDLERS.md and CHANGELOG [Unreleased].

Made-with: Cursor

* fix(sdk): Phase 2 scope — Trek-e review (#2179, #2122)

- Remove gsd-sdk query passthrough to gsd-tools.cjs; drop GSD_TOOLS_PATH
- Consolidate argv routing in resolveQueryArgv(); update USAGE and QUERY-HANDLERS
- Surface @file: read failures in GSDTools.parseOutput
- execute-plan: defer Task Commit Protocol to gsd-executor
- stale-colon-refs: skip .planning/ and root CLAUDE.md (gitignored overlays)
- CHANGELOG [Unreleased]: maintainer review and routing notes

Made-with: Cursor
2026-04-15 22:46:31 -04:00

9.2 KiB

Import Workflow

External plan ingestion with conflict detection and agent delegation.

  • --from: Import external plan → conflict detection → write PLAN.md → validate via gsd-plan-checker

Future: --prd mode (PRD extraction into PROJECT.md + REQUIREMENTS.md + ROADMAP.md) is planned for a follow-up PR.


Display the stage banner:

━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━
 GSD ► IMPORT
━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━

Parse $ARGUMENTS to determine the execution mode:

  • If --from is present: extract FILEPATH (the next token after --from), set MODE=plan
  • If --prd is present: display message that --prd is not yet implemented and exit:
    GSD > --prd mode is planned for a future release. Use --from to import plan files.
    
  • If neither flag is found: display usage and exit:
Usage: /gsd-import --from <path>

  --from <path>   Import an external plan file into GSD format

Validate the file path:

Verify the path does not contain traversal sequences and the file exists:

case "{FILEPATH}" in
  *..* ) echo "SECURITY_ERROR: path contains traversal sequence"; exit 1 ;;
esac
test -f "{FILEPATH}" || echo "FILE_NOT_FOUND"

If FILE_NOT_FOUND: display error and exit:

╔══════════════════════════════════════════════════════════════╗
║  ERROR                                                       ║
╚══════════════════════════════════════════════════════════════╝

File not found: {FILEPATH}

**To fix:** Verify the file path and try again.

Path A: MODE=plan (--from)

Load project context for conflict detection:

  1. Read .planning/ROADMAP.md — extract phase structure, phase numbers, dependencies
  2. Read .planning/PROJECT.md — extract project constraints, tech stack, scope boundaries. If PROJECT.md does not exist: skip constraint checks that rely on it and display:
    GSD > Note: No PROJECT.md found. Conflict checks against project constraints will be skipped.
    
  3. Read .planning/REQUIREMENTS.md — extract existing requirements for overlap and contradiction checks. If REQUIREMENTS.md does not exist: skip requirement conflict checks and continue.
  4. Glob for all CONTEXT.md files across phase directories:
    find .planning/phases/ -name "*-CONTEXT.md" -o -name "CONTEXT.md" 2>/dev/null
    
    Read each CONTEXT.md found — extract locked decisions (any decision in a <decisions> block)

Store loaded context for conflict detection in the next step.

Read the imported file at FILEPATH.

Determine the format:

  • GSD PLAN.md format: Has YAML frontmatter with phase:, plan:, type: fields
  • Freeform document: Any other format (markdown spec, design doc, task list, etc.)

Extract from the imported content:

  • Phase target: Which phase this plan belongs to (from frontmatter or inferred from content)
  • Plan objectives: What the plan aims to accomplish
  • Tasks listed: Individual work items described in the plan
  • Files modified: Any files mentioned as targets
  • Dependencies: Any referenced prerequisites

Run conflict checks against the loaded project context. Output as a plain-text conflict report using [BLOCKER], [WARNING], and [INFO] labels. Do NOT use markdown tables (no |---| format).

BLOCKER checks (any one prevents import):

  • Plan targets a phase number that does not exist in ROADMAP.md → [BLOCKER]
  • Plan specifies a tech stack that contradicts PROJECT.md constraints → [BLOCKER]
  • Plan contradicts a locked decision in any CONTEXT.md <decisions> block → [BLOCKER]
  • Plan contradicts an existing requirement in REQUIREMENTS.md → [BLOCKER]

WARNING checks (user confirmation required):

  • Plan partially overlaps existing requirement coverage in REQUIREMENTS.md → [WARNING]
  • Plan has depends_on referencing plans that are not yet complete → [WARNING]
  • Plan modifies files that overlap with existing incomplete plans → [WARNING]
  • Plan phase number conflicts with existing phase numbering in ROADMAP.md → [WARNING]

INFO checks (informational, no action needed):

  • Plan uses a library not currently in the project tech stack → [INFO]
  • Plan adds a new phase to the ROADMAP.md structure → [INFO]

Display the full Conflict Detection Report:

## Conflict Detection Report

### BLOCKERS ({N})

[BLOCKER] {Short title}
  Found: {what the imported plan says}
  Expected: {what project context requires}
  → {Specific action to resolve}

### WARNINGS ({N})

[WARNING] {Short title}
  Found: {what was detected}
  Impact: {what could go wrong}
  → {Suggested action}

### INFO ({N})

[INFO] {Short title}
  Note: {relevant information}

If any [BLOCKER] exists:

Display:

GSD > BLOCKED: {N} blockers must be resolved before import can proceed.

Exit WITHOUT writing any files. This is the safety gate — no PLAN.md is written when blockers exist.

If only WARNINGS and/or INFO (no blockers):

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. Ask via AskUserQuestion using the approve-revise-abort pattern:

  • question: "Review the warnings above. Proceed with import?"
  • header: "Approve?"
  • options: Approve | Abort

If user selects "Abort": exit cleanly with message "Import cancelled."

Convert the imported content to GSD PLAN.md format.

Ensure the PLAN.md has all required frontmatter fields:

---
phase: "{NN}-{slug}"
plan: "{NN}-{MM}"
type: "feature|refactor|config|test|docs"
wave: 1
depends_on: []
files_modified: []
autonomous: true
must_haves:
  truths: []
  artifacts: []
---

Reject PBR naming conventions in source content: If the imported plan references PBR plan naming (e.g., PLAN-01.md, plan-01.md), rename all references to GSD {NN}-{MM}-PLAN.md convention during conversion.

Apply GSD naming convention for the output filename:

  • Format: {NN}-{MM}-PLAN.md (e.g., 04-01-PLAN.md)
  • NEVER use PLAN-01.md, plan-01.md, or any other format
  • NN = phase number (zero-padded), MM = plan number within the phase (zero-padded)

Determine the target directory:

.planning/phases/{NN}-{slug}/

If the directory does not exist, create it:

mkdir -p ".planning/phases/{NN}-{slug}/"

Write the PLAN.md file to the target directory.

Delegate validation to gsd-plan-checker:

Task({
  subagent_type: "gsd-plan-checker",
  prompt: "Validate: .planning/phases/{phase}/{plan}-PLAN.md — check frontmatter completeness, task structure, and GSD conventions. Report any issues."
})

If the checker returns errors:

  • Display the errors to the user
  • Ask the user to resolve issues before the plan is considered imported
  • Do not delete the written file — the user can fix and re-validate manually

If the checker returns clean:

  • Display: "Plan validation passed"

Update .planning/ROADMAP.md to reflect the new plan:

  • Add the plan to the Plans list under the correct phase section
  • Include the plan name and description

Update .planning/STATE.md if appropriate (e.g., increment total plan count).

Commit the imported plan and updated files:

gsd-sdk query commit "docs({phase}): import plan from {basename FILEPATH}" .planning/phases/{phase}/{plan}-PLAN.md .planning/ROADMAP.md

Display completion:

━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━
 GSD ► IMPORT COMPLETE
━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━

Show: plan filename written, phase directory, validation result, next steps.


Anti-Patterns

Do NOT:

  • Use markdown tables (|---|) in the conflict detection report — use plain-text [BLOCKER]/[WARNING]/[INFO] labels
  • Write PLAN.md files as PLAN-01.md or plan-01.md — always use {NN}-{MM}-PLAN.md
  • Use pbr:plan-checker or pbr:planner — use gsd-plan-checker and gsd-planner
  • Write .planning/.active-skill — this is a PBR pattern with no GSD equivalent
  • Reference pbr-tools, pbr:, or PLAN-BUILD-RUN anywhere
  • Write any PLAN.md file when blockers exist — the safety gate must hold
  • Skip path validation on the --from file argument