@therocketcode/gsd-core 1.4.0 → 1.6.0
This diff represents the content of publicly available package versions that have been released to one of the supported registries. The information contained in this diff is provided for informational purposes only and reflects changes between package versions as they appear in their respective public registries.
- package/.claude-plugin/plugin.json +1 -1
- package/README.ja-JP.md +2 -2
- package/README.ko-KR.md +2 -2
- package/README.pt-BR.md +2 -2
- package/README.zh-CN.md +2 -2
- package/gemini-extension.json +1 -1
- package/gsd-core/workflows/discuss-phase.md +1 -0
- package/gsd-core/workflows/plan-phase.md +2 -0
- package/package.json +1 -1
- package/scripts/sync-upstream.sh +56 -0
|
@@ -1,7 +1,7 @@
|
|
|
1
1
|
{
|
|
2
2
|
"name": "gsd-core",
|
|
3
3
|
"displayName": "GSD Core",
|
|
4
|
-
"version": "1.
|
|
4
|
+
"version": "1.6.0",
|
|
5
5
|
"description": "GSD Core is a meta-prompting, context engineering, and spec-driven development system for AI coding agents.",
|
|
6
6
|
"author": {
|
|
7
7
|
"name": "TheRocketCodeMX",
|
package/README.ja-JP.md
CHANGED
|
@@ -8,8 +8,8 @@
|
|
|
8
8
|
|
|
9
9
|
**Claude Code、OpenCode、Gemini CLI、Kilo、Codex、Copilot、Cursor、Windsurf などに対応した、軽量なメタプロンプティング・コンテキストエンジニアリング・仕様駆動開発システムです。**
|
|
10
10
|
|
|
11
|
-
[](https://www.npmjs.com/package/@therocketcode/gsd-core)
|
|
12
|
+
[](https://www.npmjs.com/package/@therocketcode/gsd-core)
|
|
13
13
|
[](https://github.com/TheRocketCodeMX/gsd-core/actions/workflows/test.yml)
|
|
14
14
|
[](https://discord.gg/mYgfVNfA2r)
|
|
15
15
|
[](https://github.com/TheRocketCodeMX/gsd-core)
|
package/README.ko-KR.md
CHANGED
|
@@ -8,8 +8,8 @@
|
|
|
8
8
|
|
|
9
9
|
**Claude Code, OpenCode, Gemini CLI, Kilo, Codex, Copilot, Cursor, Windsurf 등을 위한 경량 메타 프롬프팅, 컨텍스트 엔지니어링, 스펙 기반 개발 시스템.**
|
|
10
10
|
|
|
11
|
-
[](https://www.npmjs.com/package/@therocketcode/gsd-core)
|
|
12
|
+
[](https://www.npmjs.com/package/@therocketcode/gsd-core)
|
|
13
13
|
[](https://github.com/TheRocketCodeMX/gsd-core/actions/workflows/test.yml)
|
|
14
14
|
[](https://discord.gg/mYgfVNfA2r)
|
|
15
15
|
[](https://github.com/TheRocketCodeMX/gsd-core)
|
package/README.pt-BR.md
CHANGED
|
@@ -8,8 +8,8 @@
|
|
|
8
8
|
|
|
9
9
|
**Um sistema leve de meta-prompting, engenharia de contexto e desenvolvimento orientado a especificações para Claude Code, OpenCode, Gemini CLI, Kilo, Codex, Copilot, Cursor, Windsurf e muito mais.**
|
|
10
10
|
|
|
11
|
-
[](https://www.npmjs.com/package/@therocketcode/gsd-core)
|
|
12
|
+
[](https://www.npmjs.com/package/@therocketcode/gsd-core)
|
|
13
13
|
[](https://github.com/TheRocketCodeMX/gsd-core/actions/workflows/test.yml)
|
|
14
14
|
[](https://discord.gg/mYgfVNfA2r)
|
|
15
15
|
[](https://github.com/TheRocketCodeMX/gsd-core)
|
package/README.zh-CN.md
CHANGED
|
@@ -8,8 +8,8 @@
|
|
|
8
8
|
|
|
9
9
|
**一套轻量级的元提示、上下文工程与规范驱动开发系统，适用于 Claude Code、OpenCode、Gemini CLI、Kilo、Codex、Copilot、Cursor、Windsurf 等 AI 编程工具。**
|
|
10
10
|
|
|
11
|
-
[](https://www.npmjs.com/package/@therocketcode/gsd-core)
|
|
12
|
+
[](https://www.npmjs.com/package/@therocketcode/gsd-core)
|
|
13
13
|
[](https://github.com/TheRocketCodeMX/gsd-core/actions/workflows/test.yml)
|
|
14
14
|
[](https://discord.gg/mYgfVNfA2r)
|
|
15
15
|
[](https://github.com/TheRocketCodeMX/gsd-core)
|
package/gemini-extension.json
CHANGED
|
@@ -1,6 +1,6 @@
|
|
|
1
1
|
{
|
|
2
2
|
"name": "gsd-core",
|
|
3
|
-
"version": "1.
|
|
3
|
+
"version": "1.6.0",
|
|
4
4
|
"description": "GSD Core — a meta-prompting, context engineering, and spec-driven development system for AI coding agents. Loads gsd's operating context into every Gemini CLI session.",
|
|
5
5
|
"contextFileName": "GEMINI.md"
|
|
6
6
|
}
|
|
@@ -293,6 +293,7 @@ Analyze the phase to identify gray areas. Use both `prior_decisions` and `codeba
|
|
|
293
293
|
|
|
294
294
|
1b. **Initialize canonical refs accumulator** — Start building `<canonical_refs>` for CONTEXT.md. Sources:
|
|
295
295
|
- **Now:** Copy `Canonical refs:` from ROADMAP.md for this phase. Expand each to a full relative path. Check REQUIREMENTS.md and PROJECT.md for specs/ADRs referenced.
|
|
296
|
+
- **Project discovery artifacts (if present):** add `.planning/DOMAIN-MODEL.md` (ubiquitous language + core/supporting/generic subdomains), the most recent `.planning/adr/*.md` (the architecture decision — per-subdomain domain-logic rung + topology), and `.planning/TEST-STRATEGY.md` (per-subdomain test levels + the linked test-infra how-to references). These are project-wide and apply to EVERY phase: planning and implementation MUST follow the domain model, the architecture decision, and the test strategy. For each, note its role (e.g. "Architecture decision — MUST follow the chosen rung per subdomain"). When `TEST-STRATEGY.md` is present, the plan's test tasks must also pull in the specific `gsd-core/references/<test-infra>.md` it links for the level being written.
|
|
296
297
|
- **`scout_codebase`:** If existing code references docs (e.g., comments citing ADRs), add those.
|
|
297
298
|
- **`discuss_areas`:** When the user says "read X", "check Y", or references any doc/spec/ADR — add it immediately. These are often the MOST important refs.
|
|
298
299
|
|
|
@@ -831,6 +831,7 @@ Pattern mapper prompt:
|
|
|
831
831
|
|
|
832
832
|
<files_to_read>
|
|
833
833
|
- {context_path} (USER DECISIONS from /gsd:discuss-phase)
|
|
834
|
+
- **Every file listed under `## Canonical References` inside {context_path}** — these are MANDATORY ("Downstream agents MUST read these before planning"). When they include a DOMAIN-MODEL.md, an architecture ADR, or a TEST-STRATEGY.md, the plan MUST follow the domain model's subdomain classification, the architecture decision's per-subdomain rung, and the test strategy's per-subdomain test levels — and pull the test-infra references that TEST-STRATEGY links into the `@`-context of the relevant test tasks. Also read `.planning/DOMAIN-MODEL.md`, the latest `.planning/adr/*.md`, and `.planning/TEST-STRATEGY.md` directly if they exist — they are project-wide and always apply, even when not listed.
|
|
834
835
|
- {research_path} (Technical Research)
|
|
835
836
|
</files_to_read>
|
|
836
837
|
|
|
@@ -895,6 +896,7 @@ Planner prompt:
|
|
|
895
896
|
- {roadmap_path} (Roadmap)
|
|
896
897
|
- {requirements_path} (Requirements)
|
|
897
898
|
- {context_path} (USER DECISIONS from /gsd:discuss-phase)
|
|
899
|
+
- **Every file listed under `## Canonical References` inside {context_path}** — these are MANDATORY ("Downstream agents MUST read these before planning"). When they include a DOMAIN-MODEL.md, an architecture ADR, or a TEST-STRATEGY.md, the plan MUST follow the domain model's subdomain classification, the architecture decision's per-subdomain rung, and the test strategy's per-subdomain test levels — and pull the test-infra references that TEST-STRATEGY links into the `@`-context of the relevant test tasks. Also read `.planning/DOMAIN-MODEL.md`, the latest `.planning/adr/*.md`, and `.planning/TEST-STRATEGY.md` directly if they exist — they are project-wide and always apply, even when not listed.
|
|
898
900
|
- {research_path} (Technical Research)
|
|
899
901
|
- {PATTERNS_PATH} (Pattern Map — analog files and code excerpts, if exists)
|
|
900
902
|
- {verification_path} (Verification Gaps - if --gaps)
|
package/package.json
CHANGED
|
@@ -0,0 +1,56 @@
|
|
|
1
|
+
#!/usr/bin/env bash
|
|
2
|
+
#
|
|
3
|
+
# Re-apply the @therocketcode fork rebrand over files touched by an upstream cherry-pick.
|
|
4
|
+
#
|
|
5
|
+
# Why: cherry-picking from `upstream` (open-gsd/gsd-core) reintroduces the upstream
|
|
6
|
+
# coordinate (@opengsd/gsd-core, open-gsd/gsd-core, the cache slug, the encoded npm badge).
|
|
7
|
+
# This script rewrites all six forms back to ours in one pass. The legacy migration package
|
|
8
|
+
# refs (the get-shit-done-* and gsd-sdk packages under the old scope) are NOT touched — the
|
|
9
|
+
# patterns only match the gsd-core coordinate, so install-migration code is preserved.
|
|
10
|
+
#
|
|
11
|
+
# Usage:
|
|
12
|
+
# git fetch upstream --tags
|
|
13
|
+
# git cherry-pick <sha> # resolve content conflicts, keep ours for branding
|
|
14
|
+
# ./scripts/sync-upstream.sh [file ...] # rebrand specific files, or the whole tree if no args
|
|
15
|
+
#
|
|
16
|
+
# After running:
|
|
17
|
+
# npm run generate:identity && npm run build:lib && \
|
|
18
|
+
# npm run test:unit && npm run check:identity-drift && npm run lint
|
|
19
|
+
#
|
|
20
|
+
set -euo pipefail
|
|
21
|
+
cd "$(git rev-parse --show-toplevel)"
|
|
22
|
+
|
|
23
|
+
rebrand() {
|
|
24
|
+
sed -i \
|
|
25
|
+
-e 's#@opengsd/gsd-core#@therocketcode/gsd-core#g' \
|
|
26
|
+
-e 's#@opengsd\\/gsd-core#@therocketcode\\/gsd-core#g' \
|
|
27
|
+
-e 's#open-gsd/gsd-core#TheRocketCodeMX/gsd-core#g' \
|
|
28
|
+
-e 's#open-gsd\\/gsd-core#TheRocketCodeMX\\/gsd-core#g' \
|
|
29
|
+
-e 's#opengsd-gsd-core#therocketcode-gsd-core#g' \
|
|
30
|
+
-e 's#%40opengsd%2Fgsd-core#%40therocketcode%2Fgsd-core#g' \
|
|
31
|
+
"$@"
|
|
32
|
+
}
|
|
33
|
+
|
|
34
|
+
if [ "$#" -gt 0 ]; then
|
|
35
|
+
rebrand "$@"
|
|
36
|
+
echo "Rebranded $# file(s)."
|
|
37
|
+
else
|
|
38
|
+
# whole tree: text files only, excluding reference clones / deps / git
|
|
39
|
+
mapfile -t files < <(grep -rIlE 'opengsd|open-gsd' \
|
|
40
|
+
--exclude-dir=_reference --exclude-dir=node_modules --exclude-dir=.git . || true)
|
|
41
|
+
if [ "${#files[@]}" -gt 0 ]; then
|
|
42
|
+
rebrand "${files[@]}"
|
|
43
|
+
echo "Rebranded ${#files[@]} file(s) across the tree."
|
|
44
|
+
else
|
|
45
|
+
echo "Nothing to rebrand."
|
|
46
|
+
fi
|
|
47
|
+
fi
|
|
48
|
+
|
|
49
|
+
# package.json identity (name/author/repo) is ours by convention — verify it didn't drift back:
|
|
50
|
+
name="$(node -p "require('./package.json').name" 2>/dev/null || echo '')"
|
|
51
|
+
if [ "$name" != "@therocketcode/gsd-core" ]; then
|
|
52
|
+
echo "WARNING: package.json name is '$name' (expected @therocketcode/gsd-core) — fix it before publishing." >&2
|
|
53
|
+
fi
|
|
54
|
+
|
|
55
|
+
echo ""
|
|
56
|
+
echo "Next: npm run generate:identity && npm run build:lib && npm run test:unit && npm run check:identity-drift && npm run lint"
|