@elvis1513/auto-coding-skill 2.1.3 → 2.2.0
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/README.md +154 -548
- package/cli/assets/agents/browser-debugger.toml +0 -1
- package/cli/assets/agents/docs-researcher.toml +0 -1
- package/cli/assets/agents/explorer.toml +1 -2
- package/cli/assets/agents/fixer.toml +2 -3
- package/cli/assets/agents/reviewer.toml +1 -2
- package/cli/assets/skill/SKILL.md +98 -207
- package/cli/assets/skill/data/templates/ENGINEERING.md +113 -468
- package/cli/assets/skill/data/templates/docs/tasks/closure-log.md +11 -22
- package/cli/assets/skill/data/templates/docs/tasks/taskbook.md +16 -39
- package/cli/assets/skill/data/templates/tools/ap.py +16 -0
- package/cli/assets/skill/scripts/ap.py +666 -129
- package/cli/assets/skill/scripts/scaffold_templates.py +136 -0
- package/cli/src/index.js +317 -42
- package/cli/tests/ap_profiles_test.py +428 -0
- package/cli/tests/index.test.js +373 -62
- package/package.json +3 -3
- package/cli/assets/skill/data/templates/docs/architecture/adr/_TEMPLATE-ADR.md +0 -38
- package/cli/assets/skill/data/templates/docs/architecture/structure-standard.md +0 -92
- package/cli/assets/skill/data/templates/docs/bugs/bug-list.md +0 -5
- package/cli/assets/skill/data/templates/docs/deployment/deploy-records/_TEMPLATE-DEPLOY-RECORD.md +0 -19
- package/cli/assets/skill/data/templates/docs/deployment/deploy-runbook.md +0 -11
- package/cli/assets/skill/data/templates/docs/design/_TEMPLATE-DD.md +0 -49
- package/cli/assets/skill/data/templates/docs/interfaces/api-change-log.md +0 -11
- package/cli/assets/skill/data/templates/docs/interfaces/api.md +0 -36
- package/cli/assets/skill/data/templates/docs/reviews/_TEMPLATE-REVIEW.md +0 -36
- package/cli/assets/skill/data/templates/docs/reviews/optimization-backlog.md +0 -25
- package/cli/assets/skill/data/templates/docs/reviews/project-health-baseline.md +0 -66
- package/cli/assets/skill/data/templates/docs/tasks/summaries/_TEMPLATE-TASK-SUMMARY.md +0 -35
- package/cli/assets/skill/data/templates/docs/testing/regression-matrix.md +0 -11
package/README.md
CHANGED
|
@@ -1,623 +1,229 @@
|
|
|
1
1
|
# auto-coding-skill
|
|
2
2
|
|
|
3
|
-
|
|
4
|
-
|
|
5
|
-
-
|
|
6
|
-
|
|
7
|
-
|
|
8
|
-
|
|
9
|
-
|
|
3
|
+
A generic `.agents` engineering workflow with adaptive execution profiles,
|
|
4
|
+
minimal project scaffolding, evidence-backed closure, and optional CI/Jenkins and
|
|
5
|
+
target-environment verification.
|
|
6
|
+
|
|
7
|
+
## What changed in v2.2.0
|
|
8
|
+
|
|
9
|
+
- Added `micro`, `standard`, and `high-risk` execution profiles.
|
|
10
|
+
- `workflow.profile: auto` classifies changed work and cannot downgrade detected
|
|
11
|
+
high-risk changes.
|
|
12
|
+
- High-risk and explicit verify work now require a real `gate_full`/`full_gate`;
|
|
13
|
+
light and standard commands are no longer accepted as full-gate fallbacks.
|
|
14
|
+
- Generic structure checks are advisory by default. Projects can opt into
|
|
15
|
+
blocking enforcement.
|
|
16
|
+
- Reduced a new project scaffold from 46 files / about 10,120 lines to 20 files /
|
|
17
|
+
about 5,300 lines.
|
|
18
|
+
- Replaced duplicated repository-side Python tools with a small launcher that
|
|
19
|
+
delegates to the single project-local skill runtime.
|
|
20
|
+
- Kept only ENGINEERING, taskbook, and closure log in the default documentation
|
|
21
|
+
scaffold; all specialized documents are materialized on demand.
|
|
22
|
+
- Removed hard-coded model names from managed Agent templates. New installs
|
|
23
|
+
inherit the active client model; existing project model overrides survive sync.
|
|
24
|
+
- Added behavioral regression tests for profile resolution, strict full gates,
|
|
25
|
+
advisory structure checks, minimal scaffold budgets, on-demand docs, and Agent
|
|
26
|
+
model inheritance.
|
|
10
27
|
|
|
11
28
|
## Install
|
|
12
29
|
|
|
13
30
|
```bash
|
|
14
31
|
npm install -g @elvis1513/auto-coding-skill
|
|
32
|
+
autocoding init
|
|
33
|
+
autocoding sync --projects .
|
|
34
|
+
pip install pyyaml requests
|
|
15
35
|
```
|
|
16
36
|
|
|
17
|
-
|
|
37
|
+
`autocoding init` installs the project-local skill and five managed roles under
|
|
38
|
+
`.agents`. `autocoding sync` installs the minimal project scaffold:
|
|
18
39
|
|
|
19
|
-
```
|
|
20
|
-
|
|
40
|
+
```text
|
|
41
|
+
.agents/skills/auto-coding-skill/
|
|
42
|
+
.agents/agents/
|
|
43
|
+
docs/ENGINEERING.md
|
|
44
|
+
docs/tasks/taskbook.md
|
|
45
|
+
docs/tasks/closure-log.md
|
|
46
|
+
docs/tools/autopipeline/ap.py
|
|
21
47
|
```
|
|
22
48
|
|
|
23
|
-
|
|
24
|
-
|
|
25
|
-
### v2.1.2
|
|
26
|
-
|
|
27
|
-
- Fixed `docs-ledger-archive` so settled task states such as `Superseded by ...`, `External Dependency`, `Deployed`, `Completed`, `Archived`, `Local PASS`, and `Local Verified` are recognized as archivable instead of blocking physical ledger cleanup.
|
|
28
|
-
- Added a package-safe regression test for those docs ledger archive states.
|
|
29
|
-
|
|
30
|
-
### v2.1.1
|
|
31
|
-
|
|
32
|
-
- Removed client-specific init targets from the npm CLI; installs now target the shared `.agents` layout only.
|
|
33
|
-
- `ap.py install --bridges` now creates a generic `AGENTS.md` bridge instead of client-named bridge files.
|
|
34
|
-
- `autocoding init --force` now preserves custom files in `.agents/agents`; only managed template files are refreshed.
|
|
35
|
-
- `autocoding init --dest` now accepts a repo root, `.agents` directory, `.agents/skills`, or the direct `.agents/skills/auto-coding-skill` directory without nesting `.agents/.agents`.
|
|
36
|
-
- `autocoding sync` now creates a missing `docs/ENGINEERING.md` from the template, while still preserving existing project-specific config.
|
|
37
|
-
- `autocoding init` now preflights both skill and agent targets before writing files, preventing partial installs when one target already exists.
|
|
38
|
-
- Added CLI installer regression tests for dest variants, partial-init failure, sync convergence, bridge generation, custom-agent preservation, and managed bridge cleanup.
|
|
39
|
-
- Made `npm test` runnable from the published package by testing packaged assets separately from source-tree asset synchronization checks.
|
|
40
|
-
- `autocoding status/sync` now treats `.agents/agents` as a shared directory: managed templates are checked and refreshed, while project-specific custom agents are preserved.
|
|
41
|
-
- Added `install --force` protection: plain `ap.py install` now refuses to overwrite existing generated docs/tooling and directs existing projects to `upgrade`.
|
|
42
|
-
- Added generated-noise filtering for `__pycache__`, `.pyc`, and `.DS_Store` so `impact`, structure checks, and `commit-push` do not treat local Python cache files as real project changes.
|
|
43
|
-
- Added generic `--ci-build` / `--ci-failure` aliases for closure commands while keeping legacy Jenkins flags compatible.
|
|
44
|
-
- Added `ap.py docs-ledger-check` to prevent documentation ledgers from growing without a real archive.
|
|
45
|
-
- Added `ap.py docs-ledger-archive --plan|--write [--period 2026-06]` for generic physical archiving of closed taskbook entries, non-conflicting closure records, and matching top-level DD files.
|
|
46
|
-
- `doctor` now runs docs ledger health checks by default: large `taskbook.md`, `closure-log.md`, or active `docs/design/T*.md` sets require physical archives.
|
|
47
|
-
- `doctor` records a standalone `docs_ledger_check` evidence event with counts and blocking details.
|
|
48
|
-
- `docs-ledger-check` now fails on missing active ledger files instead of treating them as empty ledgers.
|
|
49
|
-
- `autocoding status` now parses `docs/ENGINEERING.md` frontmatter key paths instead of matching config tokens in prose.
|
|
50
|
-
- Added `verification.target_env_required` and `verification.jenkins_required` so non-Jenkins or local-only projects can keep `doctor` generic.
|
|
51
|
-
- Added `docs.task_archive_dir`, `docs.design_archive_dir`, `docs.archive_index`, and active ledger budget settings to `docs/ENGINEERING.md`.
|
|
52
|
-
- Clarified that `archive-index.md` is only navigation; it does not replace monthly or legacy physical archives.
|
|
53
|
-
|
|
54
|
-
### v2.1.0
|
|
55
|
-
|
|
56
|
-
- Added project upgrade support: `ap.py upgrade --dry-run|--write` safely syncs tooling and merges missing `docs/ENGINEERING.md` keys without overwriting existing values.
|
|
57
|
-
- Added baseline initialization: `ap.py baseline init --write --update-config` scans large files/hotspots, creates health baseline + optimization backlog, and can seed `structure.accepted_debt_paths`.
|
|
58
|
-
- Added configurable structure import-boundary checks through `structure.layer_rules`.
|
|
59
|
-
- Added local gate profiling: configured gate commands write `.local/auto-coding-skill/gate-profile.jsonl`, summarized by `ap.py gate-profile`.
|
|
60
|
-
- Added multi-project npm CLI operations: `autocoding status --projects ...` and `autocoding sync --projects ...`.
|
|
61
|
-
- Added structured evidence logging to `docs/tasks/evidence.jsonl` for classify, doctor, structure-check, gates, verification, and closure.
|
|
62
|
-
- Added task classification: `ap.py classify --scope auto` reports risk, categories, required DD/ADR/browser/Jenkins/target checks, and recommended commands.
|
|
63
|
-
|
|
64
|
-
### v2.0.6
|
|
65
|
-
|
|
66
|
-
- Fixed `structure-check --json` so successful output stays machine-readable JSON without a trailing OK line.
|
|
67
|
-
- Moved CLI error messages to stderr, preserving JSON stdout for failing machine-readable commands.
|
|
68
|
-
- Made `structure.enabled: false` disable structure gate integration even when `commands.structure_check` is still present.
|
|
69
|
-
|
|
70
|
-
### v2.0.5
|
|
71
|
-
|
|
72
|
-
- Added generic engineering-structure governance: `docs/architecture/structure-standard.md`, ADR template, project health baseline, and optimization backlog templates.
|
|
73
|
-
- Added `ap.py structure-check --scope auto|changed|standard|full` for large-file thresholds, large-file growth blocking, function-size warnings, and baseline-doc checks.
|
|
74
|
-
- Integrated `structure-check` into `light-gate` when `structure.enabled: true` or `commands.structure_check` is configured.
|
|
75
|
-
- Added baseline-aware optimization policy so “optimization complete” means scoped P0/P1/P2 closure plus tracked/accepted remaining debt, not “no future optimizations exist.”
|
|
76
|
-
|
|
77
|
-
### v2.0.4
|
|
78
|
-
|
|
79
|
-
- Added a generic impact-aware gate engine: `ap.py impact`, `light-gate --scope auto|changed|standard|full`, and `--explain`.
|
|
80
|
-
- Added project-owned `gate.*` policy support in `docs/ENGINEERING.md`; the skill chooses scope, while each project declares its own commands and optional path rules.
|
|
81
|
-
- Kept backward compatibility: projects without `gate.*` continue to use the existing standard `commands.light_gate` / quick-test fallback.
|
|
82
|
-
- Added conservative full-gate upgrades for CI, deploy, Docker, lockfile, build-tool, and autopipeline config changes.
|
|
83
|
-
|
|
84
|
-
### v2.0.3
|
|
85
|
-
|
|
86
|
-
- Fixed `doctor`, `light-gate`, `verify-target`, and Jenkins API verification to accept secret references via `*_password_env`.
|
|
87
|
-
- Kept direct `*_password` fields compatible for legacy projects while making the default template use environment-variable secret references.
|
|
88
|
-
- Updated docs so `docs/ENGINEERING.md` can stay Git-tracked without requiring committed secrets.
|
|
89
|
-
|
|
90
|
-
### v2.0.2
|
|
91
|
-
|
|
92
|
-
- Added default subagent templates under `.agents/agents`.
|
|
93
|
-
- `autocoding init` installs the managed agent templates automatically.
|
|
94
|
-
- Updated agent defaults to current model names: `gpt-5.5`, `gpt-5.4-mini`, and `gpt-5.3-codex-spark`; highest reasoning uses `xhigh`.
|
|
95
|
-
- Added concrete capability routing for MCP servers, installed skills, plugins/apps/connectors, browser tools, GitHub, Figma, security review, and artifact workflows.
|
|
96
|
-
- Changed multi-agent guidance from unconditional delegation to a role model that works either as real subagents or as sequential main-agent phases.
|
|
97
|
-
- Hardened CLI help/argument validation, asset sync checks, and stricter autopipeline config diagnostics.
|
|
49
|
+
The `docs/tools` entry point is a compatibility launcher. Runtime code lives only
|
|
50
|
+
under `.agents/skills/auto-coding-skill/scripts`.
|
|
98
51
|
|
|
99
|
-
|
|
52
|
+
## Execution profiles
|
|
100
53
|
|
|
101
|
-
|
|
102
|
-
|
|
103
|
-
### v0.3.1
|
|
104
|
-
|
|
105
|
-
- Added Jenkins crumb / CSRF retry support for API verification requests.
|
|
106
|
-
- Added finer-grained Jenkins folder / multibranch pipeline resolution.
|
|
107
|
-
- Added multibranch root job + branch child job support, with current Git branch inference when needed.
|
|
108
|
-
- Kept existing `verify-jenkins-build --git-ref` and direct `--job-url` / `--build-number` flows compatible.
|
|
109
|
-
|
|
110
|
-
### v0.3.0
|
|
111
|
-
|
|
112
|
-
- Synced reusable workflow improvements from a production project back into this skill.
|
|
113
|
-
- Moved repo-side helper entrypoint to `docs/tools/autopipeline`.
|
|
114
|
-
- Tightened regression matrix rules: rows start as `TODO`, and `PASS` requires real execution evidence.
|
|
115
|
-
- Added Jenkins API verification flow with credentials sourced from `docs/ENGINEERING.md`.
|
|
116
|
-
|
|
117
|
-
## Optimized Standard Flow
|
|
118
|
-
|
|
119
|
-
模式由 `docs/ENGINEERING.md` 顶部控制:
|
|
54
|
+
Configure the selector in `docs/ENGINEERING.md`:
|
|
120
55
|
|
|
121
56
|
```yaml
|
|
122
57
|
workflow:
|
|
123
|
-
mode:
|
|
124
|
-
|
|
125
|
-
|
|
126
|
-
`dev` 默认闭环:
|
|
127
|
-
|
|
128
|
-
`需求/任务记录 -> 最小设计 -> 开发 -> 本地轻量校验 -> 写 DEV-CLOSED 闭环 -> commit/push -> 结束`
|
|
129
|
-
|
|
130
|
-
`verify` 完整闭环:
|
|
131
|
-
|
|
132
|
-
`需求/任务记录 -> 最小设计 -> 开发 -> 本地轻量校验 -> commit/push -> 已启用的 CI/Jenkins 验证 -> 已启用的目标环境验证 -> 写 PASS 闭环`
|
|
133
|
-
|
|
134
|
-
具体执行顺序:
|
|
135
|
-
|
|
136
|
-
1. 需求确认
|
|
137
|
-
- 明确任务范围、影响服务、是否涉及 API / 数据库 / 部署 / CI/Jenkins / 前端页面。
|
|
138
|
-
2. 最小设计记录
|
|
139
|
-
- 普通小改动只更新 `taskbook` 或相关设计文档的一小段。
|
|
140
|
-
- 跨模块、接口、数据库、部署、CI/Jenkins、关键页面流程变更才补 DD。
|
|
141
|
-
3. 开发实现
|
|
142
|
-
- 只修改本次任务必要文件,不做无关重构。
|
|
143
|
-
4. 本地轻量校验
|
|
144
|
-
- 优先执行一个项目自定义快速门禁命令
|
|
145
|
-
- 若未配置,再执行 quick test / test / build 中最先配置的一项
|
|
146
|
-
- `git diff --check`
|
|
147
|
-
- API 文档检查
|
|
148
|
-
- 已启用的 CI/Jenkins 配置检查
|
|
149
|
-
5. 提交推送
|
|
150
|
-
- `dev` 模式:轻量校验通过后,先写 `DEV-CLOSED` 闭环,再 commit + push 后结束。
|
|
151
|
-
- `verify` 模式:commit + push 后继续等待已启用的 CI/Jenkins 和目标环境验证。
|
|
152
|
-
6. CI/Jenkins 验证
|
|
153
|
-
- 仅 `verify` 模式且 `verification.jenkins_required: true` 时默认执行。看 CI/Jenkins 构建、镜像、部署结果;失败则基于日志修复并再次提交。
|
|
154
|
-
7. 目标环境验证
|
|
155
|
-
- 仅 `verify` 模式且 `verification.target_env_required: true` 时默认执行。在真实目标环境做健康检查、关键接口、关键页面或业务路径验证。
|
|
156
|
-
8. 回归与证据记录
|
|
157
|
-
- 只有真实执行过已启用的 CI/Jenkins / 目标环境验证,或明确要求本地运行验证时,才把 regression matrix 写成 `PASS`。
|
|
158
|
-
9. 闭环记录
|
|
159
|
-
- `dev` 模式记录 `DEV-CLOSED`,表示开发闭环完成但 CI/Jenkins/目标环境未验证。
|
|
160
|
-
- `verify` 模式记录 `PASS` / `FAIL` / `PARTIAL`,必须基于真实验证结果。
|
|
161
|
-
|
|
162
|
-
## Default vs On-demand
|
|
163
|
-
|
|
164
|
-
默认不做:
|
|
165
|
-
- 本地 Docker Compose 启动
|
|
166
|
-
- 本地 Docker build
|
|
167
|
-
- 本地完整 regression
|
|
168
|
-
- 每个小改动强制 `check-matrix`
|
|
169
|
-
- 每个小改动强制生成 summary
|
|
170
|
-
- 未真实执行就要求 regression matrix 全 `PASS`
|
|
171
|
-
- 未真实部署目标环境就生成 deployment record
|
|
172
|
-
|
|
173
|
-
按需保留:
|
|
174
|
-
- `runtime-up` / `runtime-down`
|
|
175
|
-
- 本地 health
|
|
176
|
-
- `check-matrix`
|
|
177
|
-
- `gen-summary`
|
|
178
|
-
- deployment runbook / deployment record
|
|
179
|
-
|
|
180
|
-
## Standard Workflow
|
|
181
|
-
|
|
182
|
-
1. Install skill into project:
|
|
183
|
-
|
|
184
|
-
```bash
|
|
185
|
-
autocoding init
|
|
58
|
+
mode: dev
|
|
59
|
+
profile: auto
|
|
186
60
|
```
|
|
187
61
|
|
|
188
|
-
|
|
62
|
+
| Effective profile | Intended work | Gate scope | Mode |
|
|
63
|
+
| --- | --- | --- | --- |
|
|
64
|
+
| `micro` | docs/tests-only or explicitly isolated work | changed | dev |
|
|
65
|
+
| `standard` | normal feature and defect work | standard | dev |
|
|
66
|
+
| `high-risk` | DB/auth/payment/file transfer/gateway/prod/deploy/build changes | full | verify |
|
|
189
67
|
|
|
190
|
-
|
|
68
|
+
`auto` is a selector, not a fourth effective profile. Full-path patterns,
|
|
69
|
+
high-risk categories, `gate.rules[].profile: high-risk`, and explicit verify work
|
|
70
|
+
raise the plan to `high-risk`. A CLI `--profile micro` or `--mode dev` cannot
|
|
71
|
+
lower it.
|
|
191
72
|
|
|
192
|
-
|
|
73
|
+
An explicit configured `micro`, `standard`, or `high-risk` profile replaces
|
|
74
|
+
auto's low/normal baseline and acts as a floor for CLI overrides. Independently
|
|
75
|
+
detected high-risk signals still force `high-risk`.
|
|
193
76
|
|
|
194
|
-
|
|
195
|
-
python3 .agents/skills/auto-coding-skill/scripts/ap.py --repo . install
|
|
196
|
-
```
|
|
197
|
-
|
|
198
|
-
`install` refuses to overwrite existing generated docs/tooling unless `--force` is passed. For existing projects, use `upgrade` instead of rerunning initialization blindly.
|
|
199
|
-
|
|
200
|
-
3. Fill only one file manually:
|
|
201
|
-
|
|
202
|
-
- `docs/ENGINEERING.md` frontmatter
|
|
203
|
-
|
|
204
|
-
This frontmatter is the only manual config source.
|
|
205
|
-
It must be committed to Git. Do not add it to `.gitignore`.
|
|
206
|
-
|
|
207
|
-
重点字段:
|
|
208
|
-
- `workflow.mode`
|
|
209
|
-
- `commands.*`
|
|
210
|
-
- `gate.*`
|
|
211
|
-
- `structure.*`
|
|
212
|
-
- `optimization.*`
|
|
213
|
-
- `verification.*`
|
|
214
|
-
- `target_env.*`
|
|
215
|
-
- `jenkins.*`
|
|
216
|
-
- `docs.*`
|
|
217
|
-
|
|
218
|
-
默认必填:
|
|
219
|
-
- `workflow.mode`
|
|
220
|
-
- `project.name`
|
|
221
|
-
- `commands.gate_changed` / `commands.gate_standard` / `commands.gate_full`,或 `commands.light_gate` / `commands.quick_test` / `commands.test` / `commands.build`
|
|
222
|
-
- `verification.target_env_required`
|
|
223
|
-
- `verification.jenkins_required`
|
|
224
|
-
|
|
225
|
-
仅当 `verification.target_env_required: true` 时必填:
|
|
226
|
-
- `target_env.name`
|
|
227
|
-
- `target_env.frontend_base_url`
|
|
228
|
-
- `target_env.frontend_username`
|
|
229
|
-
- `target_env.frontend_password` 或 `target_env.frontend_password_env`
|
|
230
|
-
- `target_env.backend_base_url`
|
|
231
|
-
- `target_env.backend_username`
|
|
232
|
-
- `target_env.backend_password` 或 `target_env.backend_password_env`
|
|
233
|
-
- `target_env.backend_root_username`
|
|
234
|
-
- `target_env.backend_root_password` 或 `target_env.backend_root_password_env`
|
|
235
|
-
- `target_env.health_base_url`
|
|
236
|
-
- `target_env.health_path`
|
|
237
|
-
|
|
238
|
-
仅当 `verification.jenkins_required: true` 时必填:
|
|
239
|
-
- `jenkins.base_url`
|
|
240
|
-
- `jenkins.ui_username`
|
|
241
|
-
- `jenkins.ui_password` 或 `jenkins.ui_password_env`
|
|
242
|
-
- `jenkins.api_user`
|
|
243
|
-
- `jenkins.api_password` 或 `jenkins.api_password_env`
|
|
244
|
-
- `jenkins.trigger_branch`
|
|
245
|
-
- `jenkins.image_repository`
|
|
246
|
-
- `jenkins.image_tag_strategy`
|
|
247
|
-
- `jenkins.deploy_env`
|
|
248
|
-
- `jenkins.job_url`
|
|
249
|
-
|
|
250
|
-
4. Start AI development by constraints:
|
|
251
|
-
|
|
252
|
-
- `docs/ENGINEERING.md`
|
|
253
|
-
- `docs/architecture/structure-standard.md`
|
|
254
|
-
- `docs/reviews/project-health-baseline.md`
|
|
255
|
-
- `docs/reviews/optimization-backlog.md`
|
|
256
|
-
- `docs/tasks/taskbook.md`
|
|
257
|
-
- `docs/tasks/closure-log.md`
|
|
258
|
-
- `docs/interfaces/**`
|
|
259
|
-
- `docs/testing/regression-matrix.md`
|
|
260
|
-
- `docs/bugs/bug-list.md`
|
|
261
|
-
|
|
262
|
-
5. Tool selection rule during execution:
|
|
263
|
-
|
|
264
|
-
- Local code, tests, git, and project gates: use shell, repo scripts, and `docs/tools/autopipeline/ap.py`.
|
|
265
|
-
- Current library/framework/API/CLI/cloud docs: use Context7 or the matching installed skill before coding against uncertain behavior.
|
|
266
|
-
- UI verification: use Browser/in-app browser for local pages, Chrome for the user's logged-in Chrome state, Playwright for deterministic automation, and Computer Use only for native or unsupported UI surfaces.
|
|
267
|
-
- GitHub/PR/CI: use GitHub connectors for remote PR, issue, review, and CI state; use local git for local diff, commit, and push.
|
|
268
|
-
- Figma/frontend/design, security review, data/reporting, and document artifacts: use the matching installed plugin or skill before manual recreation.
|
|
269
|
-
- Fall back to shell/manual work only when those capabilities are unavailable, insufficient, unreliable, or slower than direct execution.
|
|
270
|
-
|
|
271
|
-
6. Collaboration rule during execution:
|
|
272
|
-
|
|
273
|
-
- Use `.agents/agents` as the default role model: `explorer`, `docs_researcher`, `browser_debugger`, `fixer`, `reviewer`.
|
|
274
|
-
- If the client permits subagents, split independent work across those roles.
|
|
275
|
-
- If the client cannot run subagents, execute the same role sequence in the main agent.
|
|
276
|
-
- Keep one main agent responsible for scope, integration, quality gates, docs closure, git state, and final delivery.
|
|
277
|
-
|
|
278
|
-
## Structure Governance
|
|
279
|
-
|
|
280
|
-
The default project scaffold includes a generic professional structure standard:
|
|
281
|
-
|
|
282
|
-
- `docs/architecture/structure-standard.md`: layer boundaries, reuse-first rules, file/function size rules, and review priority definitions.
|
|
283
|
-
- `docs/architecture/adr/_TEMPLATE-ADR.md`: architectural decision record template.
|
|
284
|
-
- `docs/reviews/project-health-baseline.md`: accepted current structure, closed optimizations, accepted debt, and completion standard.
|
|
285
|
-
- `docs/reviews/optimization-backlog.md`: ongoing P0/P1/P2/P3 optimization backlog.
|
|
286
|
-
|
|
287
|
-
Useful commands:
|
|
77
|
+
Inspect the plan:
|
|
288
78
|
|
|
289
79
|
```bash
|
|
290
80
|
python3 docs/tools/autopipeline/ap.py classify --scope auto
|
|
291
|
-
python3 docs/tools/autopipeline/ap.py
|
|
292
|
-
python3 docs/tools/autopipeline/ap.py docs-ledger-archive --plan
|
|
293
|
-
python3 docs/tools/autopipeline/ap.py structure-check --scope auto
|
|
294
|
-
python3 docs/tools/autopipeline/ap.py structure-check --scope full
|
|
295
|
-
python3 docs/tools/autopipeline/ap.py light-gate --scope auto --explain
|
|
296
|
-
python3 docs/tools/autopipeline/ap.py baseline init --write --update-config
|
|
297
|
-
python3 docs/tools/autopipeline/ap.py gate-profile
|
|
298
|
-
python3 docs/tools/autopipeline/ap.py upgrade --dry-run
|
|
81
|
+
python3 docs/tools/autopipeline/ap.py impact --scope auto --json
|
|
299
82
|
```
|
|
300
83
|
|
|
301
|
-
|
|
302
|
-
|
|
303
|
-
Do not split files only to reduce line count. Split only when a clear business or technical boundary improves cohesion and change safety; keep cohesive transaction, state-machine, workflow, or test-scenario code together and track it as accepted debt when appropriate.
|
|
304
|
-
|
|
305
|
-
`docs-ledger-check` is intentionally separate from `structure-check`. It treats `docs/tasks/taskbook.md`, `docs/tasks/closure-log.md`, and top-level `docs/design/T*.md` as active working sets. When they exceed `docs.active_*` budgets, the fix is physical archiving under `docs.task_archive_dir` / `docs.design_archive_dir`; `docs.archive_index` is only a navigation index and does not count as archive slimming.
|
|
84
|
+
Each result includes the effective profile, mode, gate scope, reasons, required
|
|
85
|
+
verification surfaces, and recommended Agent roles.
|
|
306
86
|
|
|
307
|
-
|
|
87
|
+
## Gate configuration
|
|
308
88
|
|
|
309
|
-
|
|
310
|
-
|
|
311
|
-
|
|
89
|
+
```yaml
|
|
90
|
+
commands:
|
|
91
|
+
gate_changed: "npm run test:changed"
|
|
92
|
+
gate_standard: "npm test"
|
|
93
|
+
gate_full: "npm run test:full"
|
|
312
94
|
|
|
313
|
-
|
|
314
|
-
|
|
315
|
-
|
|
95
|
+
gate:
|
|
96
|
+
default_scope: auto
|
|
97
|
+
rules:
|
|
98
|
+
- name: payments
|
|
99
|
+
paths: ["src/payments/**"]
|
|
100
|
+
profile: high-risk
|
|
316
101
|
```
|
|
317
102
|
|
|
318
|
-
|
|
103
|
+
For Node projects, a new scaffold can infer changed/standard commands from
|
|
104
|
+
`test`, `test:changed`, and `test:standard`. It only infers a full command from a
|
|
105
|
+
dedicated `test:full` script; ordinary `npm test` is never promoted to full.
|
|
106
|
+
A high-risk or verify run fails clearly when no real full command is configured.
|
|
319
107
|
|
|
320
|
-
|
|
108
|
+
## Structure policy
|
|
321
109
|
|
|
322
|
-
|
|
110
|
+
The generic checker remains useful for surfacing large files, large additions,
|
|
111
|
+
function-size signals, and import-direction heuristics, but it is not universally
|
|
112
|
+
authoritative:
|
|
323
113
|
|
|
324
|
-
|
|
325
|
-
|
|
326
|
-
|
|
327
|
-
|
|
114
|
+
```yaml
|
|
115
|
+
structure:
|
|
116
|
+
enabled: true
|
|
117
|
+
enforcement: advisory # advisory | blocking
|
|
118
|
+
architecture_standard: project-defined
|
|
328
119
|
```
|
|
329
120
|
|
|
330
|
-
|
|
121
|
+
`advisory` reports findings without blocking. Projects with reliable, tailored
|
|
122
|
+
rules can opt into `blocking`. Repository-native architecture, compiler output,
|
|
123
|
+
tests, and real dependency graphs take precedence over generic path heuristics.
|
|
331
124
|
|
|
332
|
-
|
|
333
|
-
- `docs/reviews/optimization-backlog.md`
|
|
334
|
-
- optional `structure.accepted_debt_paths` entries for existing large files
|
|
125
|
+
## Optional documentation
|
|
335
126
|
|
|
336
|
-
|
|
127
|
+
Specialized templates are created only when required:
|
|
337
128
|
|
|
338
|
-
|
|
339
|
-
|
|
129
|
+
```bash
|
|
130
|
+
python3 docs/tools/autopipeline/ap.py scaffold api --write
|
|
131
|
+
python3 docs/tools/autopipeline/ap.py scaffold design --write
|
|
132
|
+
python3 docs/tools/autopipeline/ap.py scaffold architecture --write
|
|
133
|
+
python3 docs/tools/autopipeline/ap.py scaffold review --write
|
|
134
|
+
python3 docs/tools/autopipeline/ap.py scaffold testing --write
|
|
135
|
+
python3 docs/tools/autopipeline/ap.py scaffold deployment --write
|
|
136
|
+
python3 docs/tools/autopipeline/ap.py scaffold bugs --write
|
|
137
|
+
python3 docs/tools/autopipeline/ap.py scaffold all --write
|
|
138
|
+
```
|
|
340
139
|
|
|
341
|
-
|
|
342
|
-
|
|
140
|
+
The command is idempotent and does not overwrite existing project documents
|
|
141
|
+
unless `--force` is supplied. `baseline init` and `gen-summary` generate their
|
|
142
|
+
outputs directly without static templates.
|
|
343
143
|
|
|
344
|
-
|
|
144
|
+
For a one-step legacy-style full scaffold:
|
|
345
145
|
|
|
346
146
|
```bash
|
|
347
|
-
|
|
348
|
-
autocoding sync --projects /path/to/repo1,/path/to/repo2 --dry-run
|
|
349
|
-
autocoding sync --projects /path/to/repo1,/path/to/repo2
|
|
147
|
+
python3 .agents/skills/auto-coding-skill/scripts/ap.py --repo . install --full
|
|
350
148
|
```
|
|
351
149
|
|
|
352
|
-
|
|
353
|
-
|
|
354
|
-
## AGENTS.md Constraint Example
|
|
355
|
-
|
|
356
|
-
```md
|
|
357
|
-
## Mandatory Skill
|
|
358
|
-
- Always use `auto-coding-skill` for implementation tasks.
|
|
359
|
-
- Before any code change, read and obey:
|
|
360
|
-
1) docs/ENGINEERING.md
|
|
361
|
-
2) docs/architecture/structure-standard.md
|
|
362
|
-
3) docs/tasks/taskbook.md
|
|
363
|
-
- Before any optimization review, also read:
|
|
364
|
-
1) docs/reviews/project-health-baseline.md
|
|
365
|
-
2) docs/reviews/optimization-backlog.md
|
|
366
|
-
- Execute workflow commands using `python3 docs/tools/autopipeline/ap.py`.
|
|
367
|
-
- If required docs are missing, create/update docs first, then code.
|
|
368
|
-
|
|
369
|
-
## Tooling Policy
|
|
370
|
-
- Route by source of truth:
|
|
371
|
-
1) local code/tests/git -> shell + repo scripts
|
|
372
|
-
2) current docs/API behavior -> Context7 or matching docs skill
|
|
373
|
-
3) UI/browser proof -> Browser, Chrome, Playwright, or Computer Use by scenario
|
|
374
|
-
4) PR/Issue/CI -> GitHub connector
|
|
375
|
-
5) design/frontend/security/artifacts -> matching installed skill/plugin
|
|
376
|
-
- When a connector or MCP can read or write the authoritative source directly, use it instead of retyping or duplicating state.
|
|
377
|
-
|
|
378
|
-
## Multi-Agent Policy
|
|
379
|
-
- Use `.agents/agents` roles:
|
|
380
|
-
1) explorer
|
|
381
|
-
2) docs_researcher
|
|
382
|
-
3) browser_debugger
|
|
383
|
-
4) fixer
|
|
384
|
-
5) reviewer
|
|
385
|
-
- Spawn subagents only when the client supports and allows it; otherwise run the same role phases in the main agent.
|
|
386
|
-
- Keep one main agent responsible for task framing, integration, quality gates, docs closure, git state, and final delivery.
|
|
387
|
-
|
|
388
|
-
## Default Gate Policy
|
|
389
|
-
- Default local gate is lightweight only.
|
|
390
|
-
- Use `python3 docs/tools/autopipeline/ap.py classify --scope auto` to classify risk, required docs, verification surfaces, and recommended commands.
|
|
391
|
-
- Use `python3 docs/tools/autopipeline/ap.py docs-ledger-check` when docs/task ledgers grow; use `docs-ledger-archive --plan` before `--write`; do not treat `archive-index.md` as a substitute for physical archives.
|
|
392
|
-
- Use `python3 docs/tools/autopipeline/ap.py impact --scope auto` to inspect changed files, matched project rules, and selected gate scope.
|
|
393
|
-
- Use `python3 docs/tools/autopipeline/ap.py structure-check --scope auto` to catch file growth, large-file extension, and missing structure baseline docs.
|
|
394
|
-
- Use `python3 docs/tools/autopipeline/ap.py light-gate --scope auto --explain` for small-step development after a project declares `gate.default_scope: auto`, `commands.gate_changed`, or matching `gate.rules`.
|
|
395
|
-
- Use `light-gate --scope standard` for the backward-compatible configured gate, and `light-gate --scope full` before release/deploy-sensitive closure.
|
|
396
|
-
- The gate engine is generic. Project-specific path mapping belongs in `docs/ENGINEERING.md` under `gate.rules`; unknown or high-risk impact should upgrade to standard/full rather than silently skipping checks.
|
|
397
|
-
- The structure gate is generic. Project-specific thresholds and accepted generated/vendor paths belong in `docs/ENGINEERING.md` under `structure.*`.
|
|
398
|
-
- Do not require local Docker Compose or full local regression unless the task explicitly needs local runtime diagnosis.
|
|
399
|
-
- In `dev` mode, push is the finish line after `DEV-CLOSED` is recorded.
|
|
400
|
-
- In `verify` mode, configured CI/Jenkins success, target environment verification, and closure record are mandatory only when the corresponding `verification.*_required` switch is enabled.
|
|
401
|
-
|
|
402
|
-
## Structure Policy
|
|
403
|
-
- Before coding, identify the right layer and reuse points.
|
|
404
|
-
- Do not add new responsibilities to already-large files.
|
|
405
|
-
- Prefer existing libraries, helpers, components, and scripts over new local frameworks.
|
|
406
|
-
- Self-built concurrency/performance/tooling primitives require a reason plus tests or runtime evidence.
|
|
407
|
-
- For optimization review, read the health baseline and backlog first; accepted debt is not a fresh blocker.
|
|
408
|
-
```
|
|
150
|
+
## Dynamic Agents and models
|
|
409
151
|
|
|
410
|
-
|
|
411
|
-
|
|
412
|
-
|
|
413
|
-
- Purpose: single source of project config + workflow rules.
|
|
414
|
-
- How to record:
|
|
415
|
-
- Fill YAML frontmatter once.
|
|
416
|
-
- Keep target env front/backend usernames, Jenkins UI/API usernames, password fields or `*_password_env` references, commands, and docs paths here only when those verification surfaces are enabled.
|
|
417
|
-
- Target environment also includes backend server root username/password.
|
|
418
|
-
- This file is expected to be committed to Git; prefer `*_password_env` for secrets so actual secret values stay in the current shell.
|
|
419
|
-
- Remaining enabled environment keys are mandatory; blank values, TODO-like placeholders, and incorrect URL/path formats are treated as blocking errors by `doctor`.
|
|
420
|
-
- For secret fields, `doctor` requires either a direct `*_password` value or a `*_password_env` variable name. Commands that actually authenticate require the referenced environment variable to be set at execution time.
|
|
421
|
-
- Do not duplicate config elsewhere.
|
|
422
|
-
|
|
423
|
-
### 2) docs/tasks/taskbook.md
|
|
424
|
-
- Purpose: master task ledger.
|
|
425
|
-
- How to record:
|
|
426
|
-
- Every task writes scope, risk, impact area, minimal design note, acceptance, evidence links.
|
|
427
|
-
- For code changes, record structure placement, reuse check, and whether ADR is needed.
|
|
428
|
-
- Keep this file active-only. Closed history belongs under `docs/tasks/archives/**`; an index-only file is not enough.
|
|
429
|
-
|
|
430
|
-
### 3) docs/tasks/closure-log.md
|
|
431
|
-
- Purpose: default lightweight closure record.
|
|
432
|
-
- How to record:
|
|
433
|
-
- Append one record per task.
|
|
434
|
-
- Required fields: task, commit, configured CI/Jenkins status, target env status, structure check, result, follow-up.
|
|
435
|
-
- If CI/Jenkins failed then was fixed, also record failure reason and fix commit.
|
|
436
|
-
- Keep this file active-only. Historical closure records belong under `docs/tasks/archives/**`.
|
|
437
|
-
|
|
438
|
-
### 4) docs/architecture/
|
|
439
|
-
- Files:
|
|
440
|
-
- `docs/architecture/structure-standard.md`
|
|
441
|
-
- `docs/architecture/adr/_TEMPLATE-ADR.md`
|
|
442
|
-
- Rule:
|
|
443
|
-
- Read the structure standard before adding or relocating code.
|
|
444
|
-
- Create an ADR for decisions that affect long-term structure, module boundaries, framework-like helpers, or major tradeoffs.
|
|
445
|
-
|
|
446
|
-
### 5) docs/reviews/
|
|
447
|
-
- Files:
|
|
448
|
-
- `docs/reviews/project-health-baseline.md`
|
|
449
|
-
- `docs/reviews/optimization-backlog.md`
|
|
450
|
-
- Rule:
|
|
451
|
-
- Structure and optimization reviews must read these before listing findings.
|
|
452
|
-
- Accepted debt is not a fresh blocker unless it worsened or needs priority upgrade.
|
|
453
|
-
|
|
454
|
-
### 6) docs/design/
|
|
455
|
-
- Purpose: DD for cross-module / API / DB / deployment / CI/Jenkins / key-page-flow changes.
|
|
456
|
-
- How to record:
|
|
457
|
-
- Small changes do not need a standalone DD file.
|
|
458
|
-
- Higher-risk changes create `docs/design/<TASK_ID>-<slug>.md`.
|
|
459
|
-
- Keep top-level `docs/design/T*.md` active-only. Historical DDs belong under `docs/archive/design/**`.
|
|
460
|
-
|
|
461
|
-
### 6.5) docs/tasks/archives/ and docs/archive/design/
|
|
462
|
-
- Purpose: physical history archives for closed taskbook entries, closure records, and old DDs.
|
|
463
|
-
- Rule:
|
|
464
|
-
- Archive by period or legacy bucket when active ledgers exceed `docs.active_*` budgets.
|
|
465
|
-
- `docs/tasks/archive-index.md` may summarize and link archives, but it is not the archive itself.
|
|
466
|
-
- `doctor` blocks over-budget active ledgers when `docs.ledger_block_on_exceed: true`.
|
|
467
|
-
|
|
468
|
-
### 7) docs/interfaces/
|
|
469
|
-
- Files:
|
|
470
|
-
- `docs/interfaces/api.md`
|
|
471
|
-
- `docs/interfaces/api-change-log.md`
|
|
472
|
-
- Rule:
|
|
473
|
-
- Any API change updates both files in the same task.
|
|
474
|
-
|
|
475
|
-
### 8) docs/testing/regression-matrix.md
|
|
476
|
-
- Purpose: on-demand regression evidence, not default gate for every small change.
|
|
477
|
-
- Rule:
|
|
478
|
-
- Only real executed items can be marked `PASS`.
|
|
479
|
-
- `check-matrix` is used only when full regression is explicitly required.
|
|
480
|
-
|
|
481
|
-
### 9) docs/tasks/summaries/
|
|
482
|
-
- Purpose: optional long-form summary.
|
|
483
|
-
- Rule:
|
|
484
|
-
- Only for high-risk changes, milestones, or tasks that need full retrospective.
|
|
485
|
-
|
|
486
|
-
### 8) docs/deployment/
|
|
487
|
-
- Purpose: optional heavy deployment audit docs.
|
|
488
|
-
- Rule:
|
|
489
|
-
- Only for manual deploys, high-risk releases, or explicit audit requirements.
|
|
490
|
-
|
|
491
|
-
## High-risk Changes
|
|
492
|
-
|
|
493
|
-
These categories require stronger verification and usually a DD:
|
|
494
|
-
- Database migration
|
|
495
|
-
- Authentication / authorization
|
|
496
|
-
- Payment / order
|
|
497
|
-
- Deployment / CI / Jenkins
|
|
498
|
-
- Nginx / gateway
|
|
499
|
-
- File upload / download
|
|
500
|
-
- Production configuration
|
|
501
|
-
|
|
502
|
-
For these tasks, use `workflow.mode: "verify"` or run an explicit verification pass after the fast `dev` closure.
|
|
503
|
-
|
|
504
|
-
## Commands
|
|
505
|
-
|
|
506
|
-
Recommended default flow:
|
|
152
|
+
Managed role templates define role instructions, permissions, and reasoning
|
|
153
|
+
effort but do not pin a model. The current client therefore supplies a supported
|
|
154
|
+
model automatically.
|
|
507
155
|
|
|
508
|
-
|
|
509
|
-
pip install pyyaml requests
|
|
510
|
-
python3 docs/tools/autopipeline/ap.py doctor
|
|
511
|
-
python3 docs/tools/autopipeline/ap.py commit-push <TASK_ID> --msg "<TASK_ID>: <summary>"
|
|
512
|
-
```
|
|
156
|
+
Existing project-local `model = "..."` lines are treated as explicit overrides:
|
|
513
157
|
|
|
514
|
-
|
|
158
|
+
- `status` reports them but does not mark the project stale for model-only drift.
|
|
159
|
+
- `sync` updates managed instructions while preserving the override.
|
|
160
|
+
- `sync --reset-agent-models` removes managed-role overrides and returns to
|
|
161
|
+
client inheritance.
|
|
162
|
+
- Custom Agent files are always preserved byte-for-byte.
|
|
515
163
|
|
|
516
|
-
|
|
517
|
-
python3 docs/tools/autopipeline/ap.py commit-push <TASK_ID> --mode dev --msg "<TASK_ID>: <summary>"
|
|
518
|
-
```
|
|
164
|
+
The effective profile recommends roles dynamically:
|
|
519
165
|
|
|
520
|
-
|
|
166
|
+
- micro: main Agent only by default
|
|
167
|
+
- standard: explorer → fixer, plus browser/docs roles when indicated
|
|
168
|
+
- high-risk: explorer/docs as indicated → fixer → browser as indicated → reviewer
|
|
521
169
|
|
|
522
|
-
|
|
523
|
-
python3 docs/tools/autopipeline/ap.py commit-push <TASK_ID> \
|
|
524
|
-
--mode verify \
|
|
525
|
-
--msg "<TASK_ID>: <summary>" \
|
|
526
|
-
--backend-path /health \
|
|
527
|
-
--frontend-path /
|
|
528
|
-
```
|
|
170
|
+
## Verification configuration
|
|
529
171
|
|
|
530
|
-
|
|
172
|
+
Generic projects start with both optional external surfaces disabled:
|
|
531
173
|
|
|
532
|
-
```
|
|
533
|
-
|
|
534
|
-
|
|
535
|
-
|
|
536
|
-
python3 docs/tools/autopipeline/ap.py record-closure <TASK_ID> --commit HEAD --ci-build <build-url-or-skipped> --result PASS --verification "health check" --verification "key api" --verification "key page"
|
|
174
|
+
```yaml
|
|
175
|
+
verification:
|
|
176
|
+
target_env_required: false
|
|
177
|
+
jenkins_required: false
|
|
537
178
|
```
|
|
538
179
|
|
|
539
|
-
|
|
180
|
+
When target verification is enabled, `doctor` requires only the health URL/path
|
|
181
|
+
needed by the default health check. Frontend/backend URLs and credentials are
|
|
182
|
+
validated when the corresponding path or basic-auth options are actually used.
|
|
183
|
+
Jenkins keeps its explicit configuration checks. Unused sections should stay
|
|
184
|
+
absent rather than containing placeholders.
|
|
185
|
+
|
|
186
|
+
## Core commands
|
|
540
187
|
|
|
541
188
|
```bash
|
|
542
189
|
python3 docs/tools/autopipeline/ap.py doctor
|
|
190
|
+
python3 docs/tools/autopipeline/ap.py classify --scope auto
|
|
191
|
+
python3 docs/tools/autopipeline/ap.py light-gate --scope auto --explain
|
|
192
|
+
python3 docs/tools/autopipeline/ap.py structure-check --scope auto
|
|
543
193
|
python3 docs/tools/autopipeline/ap.py docs-ledger-check
|
|
544
|
-
python3 docs/tools/autopipeline/ap.py
|
|
545
|
-
python3 docs/tools/autopipeline/ap.py
|
|
546
|
-
python3 docs/tools/autopipeline/ap.py verify-jenkins
|
|
547
|
-
python3 docs/tools/autopipeline/ap.py verify-target --backend-path /health --frontend-path /
|
|
548
|
-
python3 docs/tools/autopipeline/ap.py verify-jenkins-build --job-name <job-name> --build-number <number>
|
|
549
|
-
python3 docs/tools/autopipeline/ap.py verify-jenkins-build --job-url <job-url> --build-number <number>
|
|
550
|
-
python3 docs/tools/autopipeline/ap.py verify-jenkins-build --multibranch-root-job <root-job> --branch-name <branch> --build-number <number>
|
|
551
|
-
python3 docs/tools/autopipeline/ap.py runtime-up
|
|
552
|
-
python3 docs/tools/autopipeline/ap.py wait-health --scope runtime
|
|
553
|
-
python3 docs/tools/autopipeline/ap.py runtime-down
|
|
554
|
-
python3 docs/tools/autopipeline/ap.py check-matrix
|
|
555
|
-
python3 docs/tools/autopipeline/ap.py gen-summary <TASK_ID>
|
|
194
|
+
python3 docs/tools/autopipeline/ap.py gate-profile
|
|
195
|
+
python3 docs/tools/autopipeline/ap.py commit-push T0001 --msg "T0001: summary"
|
|
556
196
|
```
|
|
557
197
|
|
|
558
|
-
##
|
|
198
|
+
## Upgrade and multi-project sync
|
|
559
199
|
|
|
560
|
-
|
|
561
|
-
|
|
562
|
-
- `verify-jenkins-build --job-name <folder/job> --build-number <N>`
|
|
563
|
-
- Use when you already know the Jenkins job and build number.
|
|
564
|
-
- `verify-jenkins-build --job-url <full-job-url> --build-number <N>`
|
|
565
|
-
- Use when you want to bypass configured job resolution.
|
|
566
|
-
- `verify-jenkins-build --multibranch-root-job <folder/repo> --branch-name <branch> --build-number <N>`
|
|
567
|
-
- Use for multibranch or organization-folder jobs where the branch is a child job.
|
|
568
|
-
- `verify-jenkins-build --multibranch-root-job <folder/repo> --git-ref HEAD`
|
|
569
|
-
- Use when the current Git branch should be inferred automatically.
|
|
570
|
-
- If Jenkins returns `403`, the script retries with crumb / CSRF handling automatically.
|
|
200
|
+
```bash
|
|
201
|
+
autocoding sync --projects /path/a,/path/b
|
|
571
202
|
|
|
572
|
-
|
|
203
|
+
python3 docs/tools/autopipeline/ap.py upgrade --dry-run
|
|
204
|
+
python3 docs/tools/autopipeline/ap.py upgrade --write
|
|
573
205
|
|
|
574
|
-
|
|
575
|
-
|
|
576
|
-
|
|
577
|
-
- Now prefers one curated fast gate command instead of serially running every expensive check.
|
|
578
|
-
- `verify-target`
|
|
579
|
-
- Performs real target-environment verification beyond health checks when you provide key backend/frontend paths.
|
|
580
|
-
- `commit-push --record-closure`
|
|
581
|
-
- Kept for compatibility; normal `commit-push` now records closure automatically based on `workflow.mode`.
|
|
206
|
+
autocoding status --projects /path/a,/path/b
|
|
207
|
+
autocoding sync --projects /path/a,/path/b --dry-run
|
|
208
|
+
```
|
|
582
209
|
|
|
583
|
-
|
|
210
|
+
For a v2.1 project, run the new CLI sync first; invoking its old project-local
|
|
211
|
+
`upgrade` command would still execute v2.1 logic. Upgrade and sync preserve
|
|
212
|
+
existing optional docs, legacy `core.py` /
|
|
213
|
+
`http_checks.py` tool copies, custom Agents, and project-specific configuration.
|
|
214
|
+
Retired template files do not count as drift.
|
|
584
215
|
|
|
585
|
-
|
|
216
|
+
## Development
|
|
586
217
|
|
|
587
218
|
```bash
|
|
588
219
|
npm run sync-assets
|
|
220
|
+
npm run check:assets
|
|
221
|
+
npm run test:src
|
|
589
222
|
npm test
|
|
590
|
-
```
|
|
591
|
-
|
|
592
|
-
2. Bump version:
|
|
593
|
-
|
|
594
|
-
```bash
|
|
595
|
-
npm version patch
|
|
596
|
-
# or: npm version minor / major
|
|
597
|
-
```
|
|
598
|
-
|
|
599
|
-
3. Release check:
|
|
600
|
-
|
|
601
|
-
```bash
|
|
602
|
-
npm whoami
|
|
603
223
|
npm run release:check
|
|
604
224
|
```
|
|
605
225
|
|
|
606
|
-
|
|
607
|
-
|
|
608
|
-
```bash
|
|
609
|
-
npm publish --access public
|
|
610
|
-
# or
|
|
611
|
-
npm publish --access public --otp <6-digit-otp>
|
|
612
|
-
```
|
|
613
|
-
|
|
614
|
-
5. Verify and update:
|
|
615
|
-
|
|
616
|
-
```bash
|
|
617
|
-
npm view @elvis1513/auto-coding-skill version
|
|
618
|
-
npm install -g @elvis1513/auto-coding-skill@latest
|
|
619
|
-
```
|
|
620
|
-
|
|
621
|
-
## License
|
|
226
|
+
`release:check` synchronizes source assets, validates Python 3.11 grammar and
|
|
227
|
+
TOML, runs installer and profile regressions, and performs `npm pack --dry-run`.
|
|
622
228
|
|
|
623
|
-
MIT
|
|
229
|
+
License: MIT.
|