* 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
1.6 KiB
GSD SDK query migration (summary blurb)
Copy-paste friendly for Discord and GitHub comments.
@gsd-build/sdk replaces the untyped, monolithic gsd-tools.cjs subprocess with a typed, tested, registry-based query system and gsd-sdk query, giving GSD structured results, classified errors (GSDQueryError), and golden-verified parity with the old CLI. That gives the framework one stable contract instead of a fragile, very large CLI that every workflow had to spawn and parse by hand.
What users can expect
- Same GSD commands and workflows they already use.
- Snappier runs (less Node startup on chained tool calls).
- Fewer mysterious mid-workflow failures and safer upgrades, because behavior is covered by tests and a single stable contract.
- Stronger predictability: outputs and failure modes are consistent and explicit.
Cost and tokens
The SDK does not automatically reduce LLM tokens per model call. Savings show up indirectly: fewer ambiguous tool results and fewer retry or recovery loops, which often lowers real-world session cost and wall time.
Agents then vs now
Agents always followed workflow instructions. What improved is the surface those steps run on. Before, workflows effectively said to shell out to gsd-tools.cjs and interpret stdout or JSON with brittle assumptions. Now they point at gsd-sdk query and typed handlers that return the shapes prompts expect, with clearer error reasons when something must stop or be fixed, so instruction following holds end to end with less thrash from bad parses or silent output drift.