@seanyao/roll 3.613.2 → 3.614.1
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/CHANGELOG.md +17 -0
- package/README.md +7 -1
- package/dist/roll.mjs +15817 -11580
- package/package.json +1 -1
package/CHANGELOG.md
CHANGED
|
@@ -2,6 +2,23 @@
|
|
|
2
2
|
|
|
3
3
|
## Unreleased
|
|
4
4
|
|
|
5
|
+
## v3.614.1 — 2026-06-14
|
|
6
|
+
|
|
7
|
+
### 新功能
|
|
8
|
+
|
|
9
|
+
- **项目进展网页**:roll 现在把项目的真实进展做成一个网页,一眼看清正在做什么、合了没、验收了没。分六个标签——总览、项目章程、待办、循环、发版、谁演什么角色;另有几个本机通用的页(装了哪些 AI、有哪些技能、有哪些约定、roll 是什么)。每张卡片从"说要做"到"已合并"再到"已验收",一步步点亮。左上角能在本机所有用 roll 的项目之间切换。(US-DOSSIER-019~041)
|
|
10
|
+
|
|
11
|
+
- **命令行和网页看到的是同一份真相**:直接敲 `roll` 就有身份、当前状态和一张命令地图;`roll status` 先给结论;`roll cycles`、`roll cycle` 看每一轮各干了什么;`roll cast` 看哪个 AI 演哪个角色;`roll doc` 翻项目文档。命令行和网页用同一份数据、同一个数字。(US-CLI-010~018)
|
|
12
|
+
|
|
13
|
+
- **一条命令跑通整条交付线 `roll showcase`**:在一个用完即弃的沙箱里,让几个不同的真实 AI 各司其职——一个写、一个评审、一个打分——完整走一遍"接活→写→评审→拍验收图→合并→翻牌",每一步都留下看得见的证据。发版时可以顺手跑一遍(就算 AI 抽风也不卡发版)。(US-SHOW-001)
|
|
14
|
+
|
|
15
|
+
### 修复
|
|
16
|
+
|
|
17
|
+
- `roll loop go` 的预算和轮数上限,改成每次启动单独说了算,不再悄悄沿用上回的旧设置;空转的一轮不再被算成"花了不明的钱"而把整轮叫停。(FIX-280)
|
|
18
|
+
- 跑测试时不再把临时数据写进你真实的项目清单。(FIX-281)
|
|
19
|
+
- 修好了项目页里大量打不开的证据图片。(FIX-282)
|
|
20
|
+
- 项目切换器只列还在的项目;从机器页能一键回到项目主页;`roll init` 会自动登记项目。(FIX-283)
|
|
21
|
+
|
|
5
22
|
## v3.613.2 — 2026-06-13
|
|
6
23
|
|
|
7
24
|
### 稳定性
|
package/README.md
CHANGED
|
@@ -50,7 +50,7 @@ First time through? Start with [Getting started](guide/en/getting-started.md).
|
|
|
50
50
|
| `roll brief` | Show latest owner brief |
|
|
51
51
|
| `roll backlog [sync\|block\|defer\|lint\|…]` | View, manage, and sync (from GitHub Issues) pending tasks |
|
|
52
52
|
| `roll loop alert [list\|ack\|resolve\|log]` | View / clear loop alerts |
|
|
53
|
-
| `roll status` |
|
|
53
|
+
| `roll status` | Verdict-first truth summary read from the ONE snapshot — LOOP · CYCLE · RELEASE · STORY, with the STORY line's attest-coverage % (`done ≡ merged ∧ attested`) — then convention/AI-client sync health |
|
|
54
54
|
| `roll doctor [skills]` | Environment + install diagnosis (agents, skill catalog, plists, launchd lanes) |
|
|
55
55
|
| `roll tune [reset]` | Suggest-only self-tuning from loop trends — read-only, never auto-applies |
|
|
56
56
|
| **Cards & evidence** | |
|
|
@@ -62,13 +62,19 @@ First time through? Start with [Getting started](guide/en/getting-started.md).
|
|
|
62
62
|
| `roll test [--where] [--reset]` | Run the test suite (routes through the isolation adapter; unknown types fail loud) |
|
|
63
63
|
| `roll ci [--wait]` | Show or wait for current commit's CI status |
|
|
64
64
|
| `roll release [--dry-run]` | The ONE release flow: bump → changelog fold → package gate → PR → merge → consistency gate → tag push |
|
|
65
|
+
| `roll showcase [--card <ID>]` | The golden-path standard E2E in an isolated sandbox: reset the card, cast a heterogeneous real-agent trio (kimi/claude/pi), deliver via the loop, capture CLI+web screenshots, assemble the evidence chain, emit a pass/fail verdict |
|
|
65
66
|
| `roll pair [init\|status\|score]` | Cross-agent pairing: heterogeneous peer re-checks and scores deliveries |
|
|
66
67
|
| `roll cycles [--since 1d\|3d\|7d\|all]` | The cycle ledger — one line per cycle, failures never swallowed |
|
|
67
68
|
| `roll cycle <id>` | One cycle's full trace tape (cycle→story→build→peer→ci→pr→end) |
|
|
68
69
|
| `roll peer [--reviewer <agent>] (--prompt <text>\|--file <path>)` | One-shot structured external-provider review; records `.roll/peer/runs.jsonl` |
|
|
69
70
|
| **Config & machine** | |
|
|
71
|
+
| `roll ls [--json] [--stale-days <n>]` | List the cross-project registry (`~/.roll/projects.json`): name · tag · verdict · path; missing/stale rows flagged, never dropped |
|
|
70
72
|
| `roll config [lang <zh\|en\|--reset>\|…]` | Read/write roll config (language, loop window, dream time) |
|
|
71
73
|
| `roll agent [set <slot> <agent>\|use <name>\|list]` | Per-machine complexity-slot routing (easy/default/hard/fallback) |
|
|
74
|
+
| `roll cast [--json]` | Print the complexity-ladder → role Casting table (same data the web console grid shows; `--json` for the machine view) |
|
|
75
|
+
| `roll doctor skills [--strict] [--json]` | Strict skills audit (skills · violations · hub lines + the four invocation groups — the SAME yardstick the web Skills page reads) |
|
|
76
|
+
| `roll setup skills` | Sync the `guide/skills.md` skill catalog |
|
|
77
|
+
| `roll doc [--lang en\|zh] [name]` | View the Charter / language guide markdown in the terminal (`--lang` falls back to the configured language) |
|
|
72
78
|
| `roll prices [refresh]` | Model price table (cost accounting source) |
|
|
73
79
|
| `roll setup [skills\|-f]` | First-time install, skill catalog generation, or re-sync conventions to all AI clients |
|
|
74
80
|
| `roll update` | Upgrade to latest + re-sync |
|