@boyingliu01/opencode-plugin 0.12.0 → 0.12.2
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/package.json
CHANGED
|
@@ -1,9 +1,9 @@
|
|
|
1
1
|
# SKILLS/DELPHI-REVIEW KNOWLEDGE BASE
|
|
2
2
|
|
|
3
3
|
**Generated:** 2026-07-01
|
|
4
|
-
**Commit:**
|
|
4
|
+
**Commit:** 58ec6df
|
|
5
5
|
**Branch:** main
|
|
6
|
-
**Version:** 0.12.
|
|
6
|
+
**Version:** 0.12.2.0
|
|
7
7
|
|
|
8
8
|
## OVERVIEW
|
|
9
9
|
Delphi Consensus Review — multi-round anonymous expert review (≥90% threshold, 3 experts from ≥2 providers, domestic models only). Supports design + code-walkthrough modes.
|
|
@@ -32,9 +32,9 @@ skills/delphi-review/
|
|
|
32
32
|
- 3 experts anonymous in Round 1 (no cross-expert bias)
|
|
33
33
|
- ≥90% consensus threshold (was 95%, now unified to 90%)
|
|
34
34
|
- Max 5 rounds before forcing decision
|
|
35
|
-
- Cross-provider required: experts from ≥2 different providers
|
|
36
|
-
-
|
|
37
|
-
-
|
|
35
|
+
- Cross-provider required: experts from ≥2 different providers (model list read from `opencode.json` agent config, not hardcoded)
|
|
36
|
+
- Model selection: reads `delphi-reviewer-*` agent `model` fields from `opencode.json`
|
|
37
|
+
- No hardcoded model lists — models defined by user's `opencode.json` configuration
|
|
38
38
|
- Code-walkthrough mode: triggered on git push, stores result in .code-walkthrough-result.json
|
|
39
39
|
- Code-walkthrough skipped on main/master pushes (by design)
|
|
40
40
|
|
|
@@ -88,22 +88,44 @@ Permitted variants (all satisfy L1 trigger):
|
|
|
88
88
|
| 2 专家（默认） | A(架构) + B(实现) | 代码变更、小型设计 |
|
|
89
89
|
| 3 专家 | A(架构) + B(实现) + C(可行性) | 架构决策、需求文档 |
|
|
90
90
|
|
|
91
|
-
###
|
|
91
|
+
### 模型选择策略（强制 — 从 opencode.json 读取）
|
|
92
92
|
|
|
93
|
-
**MUST
|
|
93
|
+
**MUST 从 `opencode.json` 的 agent 配置中读取模型**，**严禁** hardcode 模型名称。
|
|
94
94
|
|
|
95
|
-
|
|
96
|
-
|
|
97
|
-
|
|
98
|
-
|
|
99
|
-
| 阿里 Qwen | `qwen3.6-plus`, `qwen3.5-plus` |
|
|
100
|
-
| 智谱 GLM | `glm-5.1`, `glm-5.0` |
|
|
101
|
-
| MiniMax | `minimax-m2.7`, `minimax-m2.5` |
|
|
95
|
+
模型选择流程：
|
|
96
|
+
1. 读取 `opencode.json` 中 `agent` 字段下 `delphi-reviewer-architecture`、`delphi-reviewer-technical`、`delphi-reviewer-feasibility` 三个 agent 定义
|
|
97
|
+
2. 提取每个 agent 的 `model` 字段（格式：`provider/model-name`）
|
|
98
|
+
3. 分别作为 Expert A(架构)、Expert B(技术)、Expert C(可行性) 的模型
|
|
102
99
|
|
|
103
100
|
**关键原则**：
|
|
104
|
-
- ✅ 三个专家必须来自 **至少 2
|
|
105
|
-
- ❌
|
|
106
|
-
- ❌
|
|
101
|
+
- ✅ 三个专家必须来自 **至少 2 家不同 provider**（通过 `model` 字段的 `provider/` 前缀判断）
|
|
102
|
+
- ❌ 禁止 hardcode 模型名称（模型列表以 `opencode.json` 为准）
|
|
103
|
+
- ❌ 禁止三个专家全部使用同一 provider 的模型
|
|
104
|
+
|
|
105
|
+
**`opencode.json` agent 配置示例**（参考 `opencode.json.delphi.example`）：
|
|
106
|
+
```json
|
|
107
|
+
{
|
|
108
|
+
"agent": {
|
|
109
|
+
"delphi-reviewer-architecture": {
|
|
110
|
+
"description": "...",
|
|
111
|
+
"mode": "subagent",
|
|
112
|
+
"model": "deepseek/deepseek-chat",
|
|
113
|
+
"tools": { "read": true, "bash": true, "write": false, "edit": false }
|
|
114
|
+
},
|
|
115
|
+
"delphi-reviewer-technical": {
|
|
116
|
+
"mode": "subagent",
|
|
117
|
+
"model": "bailian-coding-plan/qwen3.6-plus",
|
|
118
|
+
"tools": { "read": true, "bash": true, "write": false, "edit": false }
|
|
119
|
+
},
|
|
120
|
+
"delphi-reviewer-feasibility": {
|
|
121
|
+
"mode": "subagent",
|
|
122
|
+
"model": "deepseek/deepseek-chat",
|
|
123
|
+
"tools": { "read": true, "bash": true, "write": false, "edit": false }
|
|
124
|
+
}
|
|
125
|
+
}
|
|
126
|
+
}
|
|
127
|
+
```
|
|
128
|
+
> 上例中 3 个专家使用了 2 个不同 provider（deepseek + bailian-coding-plan），满足跨 provider 要求。**实际模型名称以你的 `opencode.json` 配置为准，无需在 SKILL.md 维护模型列表。**
|
|
107
129
|
|
|
108
130
|
### 共识阈值
|
|
109
131
|
|