dsh-vertex-argon 2.1.0 → 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/CHANGELOG.md +15 -0
- package/README.md +11 -9
- package/adapter.js +85 -25
- package/client.js +8 -8
- package/index.js +3 -3
- package/interaction-adapter.js +8 -3
- package/interactions-input.js +5 -5
- package/locale/en.json +1 -1
- package/locale/zh.json +1 -1
- package/package.json +3 -2
package/CHANGELOG.md
CHANGED
|
@@ -2,6 +2,21 @@
|
|
|
2
2
|
|
|
3
3
|
All notable changes to **Gemini 4 Adapter** (`dsh-vertex-argon`) are documented in this file.
|
|
4
4
|
|
|
5
|
+
## [2.2.0] - 2026-11-19
|
|
6
|
+
|
|
7
|
+
### Added
|
|
8
|
+
- **Gemini 4 Neon Support Across Both Official Channels (`adapter.js`, `index.js`, `package.json`)**:
|
|
9
|
+
- Added `NEON_MODEL = 'gemini-4-neon'` (Vertex AI) and `GOOGLE_API_NEON_MODEL = 'gemini-4-neon-google'` (Gemini API), `isNeonModel()`, and `supportsXhighReasoning()` (`isHydrogenModel(modelId) || isNeonModel(modelId)`).
|
|
10
|
+
- Updated `isGoogleApiModel`, `officialUpstreamModel`, `detectPiAiArgonRoutes` (`hasVertexNeon` / `hasGoogleNeon` explicit, auto-detection, and empty Argon fallback), and `createArgonAdapter().getProfiles()` (`vn` / `gn` cache keys, `HYDROGEN_THINKING_MAP`), expanding the official matrix to 8 models with 1M context window (`1,048,576`), `65,536` single-hop / `1,048,576` long decode, four reasoning levels (`low` / `medium` / `high` / `xhigh`, `max` → `xhigh`, rejecting `minimal` / `off`), and outbound `cachedContent` / `cached_content` stripping.
|
|
11
|
+
|
|
12
|
+
### Fixed
|
|
13
|
+
- **Interactions `xhigh` & `max` → `xhigh` Convergence Parity (`interaction-adapter.js`, `interactions-input.js`, `adapter.js`, `index.js`)**:
|
|
14
|
+
- Updated `assertInteractionOptions` and `buildInteractionRequest` to share model-scoped validation (`supportsXhighReasoning`), allowing `['low', 'medium', 'high', 'xhigh']` and narrowing `max` → `xhigh` for both `gemini-4-hydrogen*` and `gemini-4-neon*` across `adapter.stream`, `prepareCall().stream`, and `agent/request` hooks, while keeping Argon and Carbon strictly 3-level (`max` → `high`) and rejecting unsupported efforts before dispatch.
|
|
15
|
+
|
|
16
|
+
### Changed
|
|
17
|
+
- **Settings UI, Locale & Documentation (`client.js`, `locale/zh.json`, `locale/en.json`, `README.md`, `AGENTS.md`, `docs/implementation/`)**:
|
|
18
|
+
- Bumped version to `2.2.0`, added `gemini-4-neon` keyword, and updated Chinese and English descriptions and setup instructions for the 8-model matrix and Hydrogen/Neon `XHigh` support.
|
|
19
|
+
|
|
5
20
|
## [2.1.0] - 2026-11-15
|
|
6
21
|
|
|
7
22
|
### Added
|
package/README.md
CHANGED
|
@@ -2,22 +2,22 @@
|
|
|
2
2
|
|
|
3
3
|

|
|
4
4
|
|
|
5
|
-
**面向 [DeepSeek Harness](<https://github.com/deepseek-ai/deepseek-harness>) 的 Google 官方双通道(Vertex AI + Gemini Developer API)Gemini 4 适配器,原生支持 Argon、Carbon 与
|
|
5
|
+
**面向 [DeepSeek Harness](<https://github.com/deepseek-ai/deepseek-harness>) 的 Google 官方双通道(Vertex AI + Gemini Developer API)Gemini 4 适配器,原生支持 Argon、Carbon、Hydrogen 与 Neon 八模型路由、GenerateContent / Interactions 双协议、65K+ 多跳长解码与请求级诊断。**
|
|
6
6
|
|
|
7
|
-
- **当前版本**:`2.
|
|
7
|
+
- **当前版本**:`2.2.0`([CHANGELOG.md](<CHANGELOG.md>))
|
|
8
8
|
- **npm 包名**:`dsh-vertex-argon`(保留既有包名、官方通道路由与本地存储域 ID,官方通道用户可直接原地升级;`2.0.0` 已移除 `1.6.x` 非官方反代通道)
|
|
9
9
|
- **运行要求**:DSH `>=0.2.0-rc.2`,Node.js `^22.19.0 || >=24.0.0`(见 [package.json](<package.json>))
|
|
10
10
|
|
|
11
|
-
[快速开始](<#快速开始>) · [
|
|
11
|
+
[快速开始](<#快速开始>) · [双官方通道与八模型](<#双官方通道与八模型>) · [长解码与流式恢复](<#generatecontent长解码与四项韧性机制>) · [配置速查](<#完整配置13-项>) · [诊断与工具](<#gemini-4-诊断与-argon_inspect-工具>) · [长解码实测参考](<#历史实测参考奥德赛七号全年舰长日志>)
|
|
12
12
|
|
|
13
13
|
---
|
|
14
14
|
|
|
15
15
|
## 核心特性
|
|
16
16
|
|
|
17
|
-
- **双官方通道 ×
|
|
17
|
+
- **双官方通道 × 八模型路由**:同时接入 Google Cloud **Vertex AI**(`gemini-4-argon` / `gemini-4-carbon` / `gemini-4-hydrogen` / `gemini-4-neon`)与 **Gemini Developer API**(`gemini-4-argon-google` / `gemini-4-carbon-google` / `gemini-4-hydrogen-google` / `gemini-4-neon-google`),两通道凭据与网关严格隔离,绝不暗中互借或静默回退。
|
|
18
18
|
- **65K+ 多跳长解码与流自愈**:单跳上限 `65,536` tokens,最大输出预算可达 `1,048,576`(最多 32 跳);首个检查点前实时流式输出,支持检查点尾段回滚续传、逐跳四阶段超时看门狗、零交付首包重试、仅思考结束单次续答自愈,以及 `MALFORMED_FUNCTION_CALL` 后 `VALIDATED` → `AUTO` 工具模式自动退避。
|
|
19
19
|
- **Interactions 协议与后台任务恢复**:支持前台流式及显式授权后的云端后台执行;内置 `creating` 预写防重计费锁、`last_event_id` 断点续读、`2026-05-20` 独立生命周期事件兼容,以及同会话新提示词触发的历史死锁非流式探针对账。
|
|
20
|
-
- **签名保真与跨模型安全降级**:完整保留并回放 `thoughtSignature` / `thought_signature
|
|
20
|
+
- **签名保真与跨模型安全降级**:完整保留并回放 `thoughtSignature` / `thought_signature`(含无文本独立签名块);Argon / Carbon 原生映射 `low` / `medium` / `high` 三档(`max` 收敛为 `high`),Hydrogen / Neon 额外放行 `xhigh` 第四档(`max` 收敛为 `xhigh` 并剥离显式 `cachedContent` / `cached_content`,永不下发 `thinkingBudget`);在 Argon ↔ Carbon ↔ Hydrogen ↔ Neon 或跨通道切换时自动将旧工具历史安全降级为文本记录并清洗污染块。
|
|
21
21
|
- **Gemini 4 诊断面板与只读工具**:在右侧栏、会话详情页与单条回复底部提供请求摘要、基础 Token 水位(严格区分首跳上下文水位与跨跳累计用量)、11 列逐跳轨迹、分页原始响应证据、云端 Interaction ID 只读查询与全局恢复锁管理,并向智能体提供延迟加载的只读工具 `argon_inspect`。
|
|
22
22
|
|
|
23
23
|
---
|
|
@@ -40,7 +40,7 @@ dsh plugin --profile desktop add dsh-vertex-argon
|
|
|
40
40
|
|
|
41
41
|
### 2. 声明模型入口
|
|
42
42
|
|
|
43
|
-
在 DSH「**设置 → 模型**」的原生 `Google` 或 `Google Vertex AI` 供应商下添加 `gemini-4-argon`、`gemini-4-carbon` 和/或 `gemini-4-
|
|
43
|
+
在 DSH「**设置 → 模型**」的原生 `Google` 或 `Google Vertex AI` 供应商下添加 `gemini-4-argon`、`gemini-4-carbon`、`gemini-4-hydrogen` 和/或 `gemini-4-neon`,插件会自动识别并在模型选择器中暴露 **Gemini 4 Adapter** 分组下的对应模型。
|
|
44
44
|
|
|
45
45
|
### 3. 配置官方凭据
|
|
46
46
|
|
|
@@ -52,7 +52,7 @@ dsh plugin --profile desktop add dsh-vertex-argon
|
|
|
52
52
|
|
|
53
53
|
---
|
|
54
54
|
|
|
55
|
-
##
|
|
55
|
+
## 双官方通道与八模型
|
|
56
56
|
|
|
57
57
|
底层 Provider ID 为 `google-vertex-argon`,模型选择器分组显示为 **Gemini 4 Adapter**(实现见 [adapter.js](<adapter.js>) 与 [google-connection.js](<google-connection.js>))。
|
|
58
58
|
|
|
@@ -61,14 +61,16 @@ dsh plugin --profile desktop add dsh-vertex-argon
|
|
|
61
61
|
| **Vertex AI** | `gemini-4-argon` | `gemini-4-argon` | `google-vertex` | `vertexProtocol` / `vertexServiceTier` |
|
|
62
62
|
| **Vertex AI** | `gemini-4-carbon` | `gemini-4-carbon` | `google-vertex` | `vertexProtocol` / `vertexServiceTier` |
|
|
63
63
|
| **Vertex AI** | `gemini-4-hydrogen` | `gemini-4-hydrogen` | `google-vertex` | `vertexProtocol` / `vertexServiceTier` |
|
|
64
|
+
| **Vertex AI** | `gemini-4-neon` | `gemini-4-neon` | `google-vertex` | `vertexProtocol` / `vertexServiceTier` |
|
|
64
65
|
| **Gemini API** | `gemini-4-argon-google` | `gemini-4-argon` | `google-generative-ai` | `googleProtocol` / `googleServiceTier` |
|
|
65
66
|
| **Gemini API** | `gemini-4-carbon-google` | `gemini-4-carbon` | `google-generative-ai` | `googleProtocol` / `googleServiceTier` |
|
|
66
67
|
| **Gemini API** | `gemini-4-hydrogen-google` | `gemini-4-hydrogen` | `google-generative-ai` | `googleProtocol` / `googleServiceTier` |
|
|
68
|
+
| **Gemini API** | `gemini-4-neon-google` | `gemini-4-neon` | `google-generative-ai` | `googleProtocol` / `googleServiceTier` |
|
|
67
69
|
|
|
68
70
|
### 跨模型切换与历史清洗规则
|
|
69
71
|
|
|
70
72
|
- **同模型连续对话**:完整保留原生 `thoughtSignature` / `thought_signature` 与 `functionCall` / `functionResponse` 签名回放。
|
|
71
|
-
- **跨模型或跨通道切换(如 Argon ↔ Carbon ↔ Hydrogen、Vertex ↔ Gemini API)**:出站前自动将含推理或工具调用的旧回合降级为纯文本记录(剔除旧思考块,将已完成工具调用转为角色安全的文本摘要,未完成调用直接拦截),避免因底层摘除跨模型签名而发出裸 `functionCall` 或孤立 `functionResponse`。
|
|
73
|
+
- **跨模型或跨通道切换(如 Argon ↔ Carbon ↔ Hydrogen ↔ Neon、Vertex ↔ Gemini API)**:出站前自动将含推理或工具调用的旧回合降级为纯文本记录(剔除旧思考块,将已完成工具调用转为角色安全的文本摘要,未完成调用直接拦截),避免因底层摘除跨模型签名而发出裸 `functionCall` 或孤立 `functionResponse`。
|
|
72
74
|
- **原生入口兼容保护**:插件同时为宿主原生 `google` 与 `google-vertex` 适配器中的 Gemini 4 模型注入 GenerateContent 思考档位映射、采样参数剥离与签名回放保护。
|
|
73
75
|
|
|
74
76
|
---
|
|
@@ -91,7 +93,7 @@ dsh plugin --profile desktop add dsh-vertex-argon
|
|
|
91
93
|
| 分组 | 配置项 | 默认值 | 取值范围与说明 |
|
|
92
94
|
|---|---|---|---|
|
|
93
95
|
| 基础与生成 | `showInModelPicker` | `true` | 是否在会话模型选择器中显示 **Gemini 4 Adapter** 分组 |
|
|
94
|
-
| 基础与生成 | `reasoning` | `medium` | 默认思考档位:`low` / `medium` / `high` |
|
|
96
|
+
| 基础与生成 | `reasoning` | `medium` | 默认思考档位:`low` / `medium` / `high`(Hydrogen 与 Neon 会话内额外支持 `xhigh`) |
|
|
95
97
|
| 基础与生成 | `maxTokens` | `65536` | `1`–`1048576`;超过 `65,536` 需启用长解码(窗口 > 131K 时自动预留 131,072 历史空间) |
|
|
96
98
|
| 基础与生成 | `contextWindow` | `1048576` | `1`–`1048576`;供 DSH 本地预算与上下文压缩计算使用 |
|
|
97
99
|
| 基础与生成 | `longDecode` | `true` | 控制 > 65,536 输出上限、GenerateContent 检查点续传与仅思考自愈 |
|
package/adapter.js
CHANGED
|
@@ -27,18 +27,26 @@ export const CARBON_MODEL = 'gemini-4-carbon'
|
|
|
27
27
|
export const GOOGLE_API_CARBON_MODEL = 'gemini-4-carbon-google'
|
|
28
28
|
export const HYDROGEN_MODEL = 'gemini-4-hydrogen'
|
|
29
29
|
export const GOOGLE_API_HYDROGEN_MODEL = 'gemini-4-hydrogen-google'
|
|
30
|
-
|
|
30
|
+
export const NEON_MODEL = 'gemini-4-neon'
|
|
31
|
+
export const GOOGLE_API_NEON_MODEL = 'gemini-4-neon-google'
|
|
32
|
+
/** Gemini API 官方直连模型判定(Argon、Carbon、Hydrogen 与 Neon)。 */
|
|
31
33
|
export function isGoogleApiModel(modelId) {
|
|
32
|
-
return
|
|
34
|
+
return (
|
|
35
|
+
modelId === GOOGLE_API_MODEL ||
|
|
36
|
+
modelId === GOOGLE_API_CARBON_MODEL ||
|
|
37
|
+
modelId === GOOGLE_API_HYDROGEN_MODEL ||
|
|
38
|
+
modelId === GOOGLE_API_NEON_MODEL
|
|
39
|
+
)
|
|
33
40
|
}
|
|
34
41
|
/** 官方直连(Vertex AI / Gemini API)对应的上游模型 ID。 */
|
|
35
42
|
export function officialUpstreamModel(modelId) {
|
|
43
|
+
if (modelId === NEON_MODEL || modelId === GOOGLE_API_NEON_MODEL) return NEON_MODEL
|
|
36
44
|
if (modelId === HYDROGEN_MODEL || modelId === GOOGLE_API_HYDROGEN_MODEL) return HYDROGEN_MODEL
|
|
37
45
|
return modelId === CARBON_MODEL || modelId === GOOGLE_API_CARBON_MODEL ? CARBON_MODEL : MODEL
|
|
38
46
|
}
|
|
39
47
|
export const LEVELS = ['low', 'medium', 'high']
|
|
40
48
|
/**
|
|
41
|
-
* Gemini 4 Hydrogen
|
|
49
|
+
* Gemini 4 Hydrogen 与 Neon 支持的第四档 xhigh(官方默认 high)。
|
|
42
50
|
* Argon / Carbon 的允许集合必须严格维持三档,绝不泄漏 xhigh。
|
|
43
51
|
*/
|
|
44
52
|
export const HYDROGEN_LEVELS = ['low', 'medium', 'high', 'xhigh']
|
|
@@ -47,7 +55,7 @@ export const MAX_LONG_DECODE_TOKENS = 1048576
|
|
|
47
55
|
const COMPACTION_HEADROOM_FLOOR = 131072
|
|
48
56
|
const ENV_KEYS = ['GOOGLE_APPLICATION_CREDENTIALS', 'GOOGLE_CLOUD_PROJECT', 'GCLOUD_PROJECT', 'GOOGLE_CLOUD_LOCATION', 'GOOGLE_CLOUD_API_KEY']
|
|
49
57
|
const DEFAULT_THINKING_MAP = { off: null, minimal: null, low: 'low', medium: 'medium', high: 'high', xhigh: null, max: null }
|
|
50
|
-
/** Hydrogen
|
|
58
|
+
/** Hydrogen 与 Neon 的档位映射:把 xhigh 放行到 thinkingConfig。 */
|
|
51
59
|
const HYDROGEN_THINKING_MAP = { off: null, minimal: null, low: 'low', medium: 'medium', high: 'high', xhigh: 'xhigh', max: null }
|
|
52
60
|
|
|
53
61
|
/** Hydrogen 模型 ID 判定:同时识别 `gemini-4-hydrogen` 与 `gemini-4-hydrogen-google`(可带 models/ 前缀)。 */
|
|
@@ -55,14 +63,24 @@ export function isHydrogenModel(modelId) {
|
|
|
55
63
|
return typeof modelId === 'string' && /^(?:models\/)?gemini-4-hydrogen(?:-google)?$/i.test(modelId)
|
|
56
64
|
}
|
|
57
65
|
|
|
58
|
-
/**
|
|
66
|
+
/** Neon 模型 ID 判定:同时识别 `gemini-4-neon` 与 `gemini-4-neon-google`(可带 models/ 前缀)。 */
|
|
67
|
+
export function isNeonModel(modelId) {
|
|
68
|
+
return typeof modelId === 'string' && /^(?:models\/)?gemini-4-neon(?:-google)?$/i.test(modelId)
|
|
69
|
+
}
|
|
70
|
+
|
|
71
|
+
/** 判断模型是否支持 xhigh 第四档思考及对应无显式缓存限制(Hydrogen 与 Neon)。 */
|
|
72
|
+
export function supportsXhighReasoning(modelId) {
|
|
73
|
+
return isHydrogenModel(modelId) || isNeonModel(modelId)
|
|
74
|
+
}
|
|
75
|
+
|
|
76
|
+
/** 模型对应的合法思考档位集合:Hydrogen 与 Neon 放行 xhigh。 */
|
|
59
77
|
export function levelsForModel(modelId) {
|
|
60
|
-
return
|
|
78
|
+
return supportsXhighReasoning(modelId) ? HYDROGEN_LEVELS : LEVELS
|
|
61
79
|
}
|
|
62
80
|
|
|
63
|
-
/** 模型对应的档位映射表:Hydrogen 放行 xhigh,其余模型仍为 null。 */
|
|
81
|
+
/** 模型对应的档位映射表:Hydrogen 与 Neon 放行 xhigh,其余模型仍为 null。 */
|
|
64
82
|
export function thinkingLevelMapFor(modelId) {
|
|
65
|
-
return
|
|
83
|
+
return supportsXhighReasoning(modelId) ? HYDROGEN_THINKING_MAP : DEFAULT_THINKING_MAP
|
|
66
84
|
}
|
|
67
85
|
|
|
68
86
|
// The host's agent/request hook already narrows 'max' to 'high'. Direct adapter
|
|
@@ -72,8 +90,8 @@ export function narrowMaxReasoning(options, modelId = options?.model) {
|
|
|
72
90
|
if (!options || typeof options !== 'object') return options
|
|
73
91
|
const requested = [options.reasoning, options.reasoningEffort]
|
|
74
92
|
if (!requested.some(value => typeof value === 'string' && value.toLowerCase() === 'max')) return options
|
|
75
|
-
// Hydrogen 的最高档是 xhigh;其余模型仍是 high。
|
|
76
|
-
const ceiling =
|
|
93
|
+
// Hydrogen 与 Neon 的最高档是 xhigh;其余模型仍是 high。
|
|
94
|
+
const ceiling = supportsXhighReasoning(modelId) ? 'xhigh' : 'high'
|
|
77
95
|
return { ...options, reasoning: ceiling, reasoningEffort: ceiling }
|
|
78
96
|
}
|
|
79
97
|
|
|
@@ -99,6 +117,8 @@ export function detectPiAiArgonRoutes(ctx, explicitRoutes) {
|
|
|
99
117
|
const hasGoogleCarbon = Boolean(explicitRoutes.hasGoogleCarbon)
|
|
100
118
|
const hasVertexHydrogen = Boolean(explicitRoutes.hasVertexHydrogen)
|
|
101
119
|
const hasGoogleHydrogen = Boolean(explicitRoutes.hasGoogleHydrogen)
|
|
120
|
+
const hasVertexNeon = Boolean(explicitRoutes.hasVertexNeon)
|
|
121
|
+
const hasGoogleNeon = Boolean(explicitRoutes.hasGoogleNeon)
|
|
102
122
|
const hasVertexArgon = explicitRoutes.hasVertexArgon !== undefined
|
|
103
123
|
? Boolean(explicitRoutes.hasVertexArgon)
|
|
104
124
|
: explicitRoutes.hasVertex !== false
|
|
@@ -106,14 +126,16 @@ export function detectPiAiArgonRoutes(ctx, explicitRoutes) {
|
|
|
106
126
|
? Boolean(explicitRoutes.hasGoogleArgon)
|
|
107
127
|
: Boolean(explicitRoutes.hasGoogle)
|
|
108
128
|
return {
|
|
109
|
-
hasVertex: hasVertexArgon || hasVertexCarbon || hasVertexHydrogen,
|
|
110
|
-
hasGoogle: hasGoogleArgon || hasGoogleCarbon || hasGoogleHydrogen,
|
|
129
|
+
hasVertex: hasVertexArgon || hasVertexCarbon || hasVertexHydrogen || hasVertexNeon,
|
|
130
|
+
hasGoogle: hasGoogleArgon || hasGoogleCarbon || hasGoogleHydrogen || hasGoogleNeon,
|
|
111
131
|
hasVertexArgon,
|
|
112
132
|
hasGoogleArgon,
|
|
113
133
|
hasVertexCarbon,
|
|
114
134
|
hasGoogleCarbon,
|
|
115
135
|
hasVertexHydrogen,
|
|
116
136
|
hasGoogleHydrogen,
|
|
137
|
+
hasVertexNeon,
|
|
138
|
+
hasGoogleNeon,
|
|
117
139
|
googleApiKeyEnv: googleKeyEnvironment(explicitRoutes.googleApiKeyEnv),
|
|
118
140
|
googleBaseUrl: explicitRoutes.googleBaseUrl,
|
|
119
141
|
vertexBaseUrl: explicitRoutes.vertexBaseUrl,
|
|
@@ -135,17 +157,21 @@ export function detectPiAiArgonRoutes(ctx, explicitRoutes) {
|
|
|
135
157
|
const hasVertexCarbon = hasModel(vertexModels, /^(?:models\/)?gemini-4-carbon\b/i)
|
|
136
158
|
const hasGoogleHydrogen = hasModel(googleModels, /^(?:models\/)?gemini-4-hydrogen\b/i)
|
|
137
159
|
const hasVertexHydrogen = hasModel(vertexModels, /^(?:models\/)?gemini-4-hydrogen\b/i)
|
|
138
|
-
const
|
|
139
|
-
const
|
|
160
|
+
const hasGoogleNeon = hasModel(googleModels, /^(?:models\/)?gemini-4-neon\b/i)
|
|
161
|
+
const hasVertexNeon = hasModel(vertexModels, /^(?:models\/)?gemini-4-neon\b/i)
|
|
162
|
+
const hasGoogle = hasGoogleArgon || hasGoogleCarbon || hasGoogleHydrogen || hasGoogleNeon
|
|
163
|
+
const hasVertex = hasVertexArgon || hasVertexCarbon || hasVertexHydrogen || hasVertexNeon || !hasGoogle
|
|
140
164
|
return {
|
|
141
165
|
hasVertex,
|
|
142
166
|
hasGoogle,
|
|
143
|
-
hasVertexArgon: hasVertexArgon || (!hasGoogle && !hasVertexCarbon && !hasVertexHydrogen),
|
|
167
|
+
hasVertexArgon: hasVertexArgon || (!hasGoogle && !hasVertexCarbon && !hasVertexHydrogen && !hasVertexNeon),
|
|
144
168
|
hasGoogleArgon,
|
|
145
169
|
hasVertexCarbon,
|
|
146
170
|
hasGoogleCarbon,
|
|
147
171
|
hasVertexHydrogen,
|
|
148
172
|
hasGoogleHydrogen,
|
|
173
|
+
hasVertexNeon,
|
|
174
|
+
hasGoogleNeon,
|
|
149
175
|
googleApiKeyEnv: googleKeyEnvironment(readVal(googleCfg?.apiKeyEnv)),
|
|
150
176
|
googleBaseUrl: readVal(googleCfg?.baseURL),
|
|
151
177
|
vertexBaseUrl: readVal(vertexCfg?.baseURL),
|
|
@@ -161,6 +187,8 @@ export function detectPiAiArgonRoutes(ctx, explicitRoutes) {
|
|
|
161
187
|
hasGoogleCarbon: false,
|
|
162
188
|
hasVertexHydrogen: false,
|
|
163
189
|
hasGoogleHydrogen: false,
|
|
190
|
+
hasVertexNeon: false,
|
|
191
|
+
hasGoogleNeon: false,
|
|
164
192
|
googleApiKeyEnv: 'GOOGLE_API_KEY',
|
|
165
193
|
}
|
|
166
194
|
}
|
|
@@ -304,19 +332,19 @@ export function gemini4StreamSimple(
|
|
|
304
332
|
ensureGemini4ApiClientPatch()
|
|
305
333
|
const fallback = defaultLevel ?? (/cyber-permissive/i.test(requestModel?.id ?? '') ? 'high' : 'medium')
|
|
306
334
|
const modelId = requestModel?.id
|
|
307
|
-
const
|
|
335
|
+
const supportsXhigh = supportsXhighReasoning(modelId)
|
|
308
336
|
const requestedLevel = options.reasoning ?? fallback
|
|
309
|
-
// max 按目标模型收敛:Hydrogen
|
|
337
|
+
// max 按目标模型收敛:Hydrogen 与 Neon 收到四档最高档 xhigh,Argon / Carbon 仍是 high。
|
|
310
338
|
const rawLevel = typeof requestedLevel === 'string' && requestedLevel.toLowerCase() === 'max'
|
|
311
|
-
? (
|
|
339
|
+
? (supportsXhigh ? 'xhigh' : 'high')
|
|
312
340
|
: (typeof requestedLevel === 'string' ? requestedLevel.toLowerCase() : requestedLevel)
|
|
313
341
|
const mapped = requestModel?.thinkingLevelMap?.[rawLevel] ?? rawLevel
|
|
314
342
|
const level = typeof mapped === 'string' ? mapped.toLowerCase() : fallback
|
|
315
343
|
if (!levelsForModel(modelId).includes(level)) {
|
|
316
344
|
throw new LlmError(
|
|
317
|
-
|
|
318
|
-
? 'Gemini 4 Hydrogen requires low, medium, high or xhigh.'
|
|
319
|
-
: 'Gemini 4 (Argon / Carbon
|
|
345
|
+
supportsXhigh
|
|
346
|
+
? 'Gemini 4 (Hydrogen / Neon) requires low, medium, high or xhigh.'
|
|
347
|
+
: 'Gemini 4 (Argon / Carbon) requires low, medium or high.',
|
|
320
348
|
'UNSUPPORTED_REASONING_EFFORT',
|
|
321
349
|
)
|
|
322
350
|
}
|
|
@@ -358,13 +386,13 @@ export function gemini4StreamSimple(
|
|
|
358
386
|
}
|
|
359
387
|
body = signatures.restorePayload(body)
|
|
360
388
|
if (structuredOutput) body = structuredOutput.generateContent(body)
|
|
361
|
-
// Gemini 4 Hydrogen 官方不支持显式缓存(cachedContents),残留字段会被上游拒绝。
|
|
362
|
-
if (
|
|
389
|
+
// Gemini 4 Hydrogen / Neon 官方不支持显式缓存(cachedContents),残留字段会被上游拒绝。
|
|
390
|
+
if (supportsXhigh) {
|
|
363
391
|
delete body.cachedContent
|
|
364
392
|
delete body.cached_content
|
|
365
393
|
}
|
|
366
394
|
const { temperature: _t, topP: _tp, topK: _tk, candidateCount: _cc, frequencyPenalty: _fp, presencePenalty: _pp, ...cleanConfig } = body.config
|
|
367
|
-
if (
|
|
395
|
+
if (supportsXhigh) {
|
|
368
396
|
delete cleanConfig.cachedContent
|
|
369
397
|
delete cleanConfig.cached_content
|
|
370
398
|
}
|
|
@@ -596,7 +624,7 @@ export class ArgonAdapter extends LlmAdapter {
|
|
|
596
624
|
if (provider === PROVIDER && cfg) resolveServicePolicy(cfg, googleApi ? 'google-generative-ai' : 'google-vertex', protocol)
|
|
597
625
|
const prepared = await this.inner.prepareCall(provider, model, signal)
|
|
598
626
|
if (provider === PROVIDER && protocol === 'interactions' && this.interactionHandler) {
|
|
599
|
-
return { model: prepared.model, stream: options => this.interactionHandler(narrowMaxReasoning(options, model), cfg) }
|
|
627
|
+
return { model: prepared.model, stream: options => this.interactionHandler(narrowMaxReasoning(options && typeof options === 'object' && !options.model ? { ...options, model } : options, model), cfg) }
|
|
600
628
|
}
|
|
601
629
|
return { ...prepared, stream: options => prepared.stream(generateContentHistory(narrowMaxReasoning(options, model), model)) }
|
|
602
630
|
}
|
|
@@ -666,6 +694,8 @@ export function createArgonAdapter(ctx, configInput, nativeVertex = googleVertex
|
|
|
666
694
|
gc: detected.hasGoogleCarbon,
|
|
667
695
|
vh: detected.hasVertexHydrogen,
|
|
668
696
|
gh: detected.hasGoogleHydrogen,
|
|
697
|
+
vn: detected.hasVertexNeon,
|
|
698
|
+
gn: detected.hasGoogleNeon,
|
|
669
699
|
ge: detected.googleApiKeyEnv,
|
|
670
700
|
gb: detected.googleBaseUrl,
|
|
671
701
|
vb: detected.vertexBaseUrl,
|
|
@@ -742,6 +772,21 @@ export function createArgonAdapter(ctx, configInput, nativeVertex = googleVertex
|
|
|
742
772
|
cost: { input: 0, output: 0, cacheRead: 0, cacheWrite: 0 },
|
|
743
773
|
})
|
|
744
774
|
}
|
|
775
|
+
if (detected.hasVertexNeon) {
|
|
776
|
+
models.push({
|
|
777
|
+
id: NEON_MODEL,
|
|
778
|
+
name: detected.hasGoogle ? 'Gemini 4 Neon (Vertex AI)' : 'Gemini 4 Neon',
|
|
779
|
+
provider: PROVIDER,
|
|
780
|
+
api: 'google-vertex',
|
|
781
|
+
baseUrl: detected.vertexBaseUrl || 'https://{location}-aiplatform.googleapis.com',
|
|
782
|
+
reasoning: true,
|
|
783
|
+
input: ['text', 'image'],
|
|
784
|
+
contextWindow: cfg.contextWindow,
|
|
785
|
+
maxTokens: cfg.maxTokens,
|
|
786
|
+
thinkingLevelMap: { ...HYDROGEN_THINKING_MAP },
|
|
787
|
+
cost: { input: 0, output: 0, cacheRead: 0, cacheWrite: 0 },
|
|
788
|
+
})
|
|
789
|
+
}
|
|
745
790
|
if (detected.hasGoogleArgon ?? detected.hasGoogle) {
|
|
746
791
|
models.push({
|
|
747
792
|
id: GOOGLE_API_MODEL,
|
|
@@ -787,6 +832,21 @@ export function createArgonAdapter(ctx, configInput, nativeVertex = googleVertex
|
|
|
787
832
|
cost: { input: 0, output: 0, cacheRead: 0, cacheWrite: 0 },
|
|
788
833
|
})
|
|
789
834
|
}
|
|
835
|
+
if (detected.hasGoogleNeon) {
|
|
836
|
+
models.push({
|
|
837
|
+
id: GOOGLE_API_NEON_MODEL,
|
|
838
|
+
name: 'Gemini 4 Neon (Gemini API)',
|
|
839
|
+
provider: PROVIDER,
|
|
840
|
+
api: 'google-generative-ai',
|
|
841
|
+
baseUrl: detected.googleBaseUrl || 'https://generativelanguage.googleapis.com/v1beta',
|
|
842
|
+
reasoning: true,
|
|
843
|
+
input: ['text', 'image'],
|
|
844
|
+
contextWindow: cfg.contextWindow,
|
|
845
|
+
maxTokens: cfg.maxTokens,
|
|
846
|
+
thinkingLevelMap: { ...HYDROGEN_THINKING_MAP },
|
|
847
|
+
cost: { input: 0, output: 0, cacheRead: 0, cacheWrite: 0 },
|
|
848
|
+
})
|
|
849
|
+
}
|
|
790
850
|
const configuredMaxTokens = new Map(models.map(m => [m.id, cfg.maxTokens]))
|
|
791
851
|
const provider = argonProvider({ ...nativeVertex, auth }, models, cfg.reasoning, nativeGoogle, cfg.longDecode, recordDiagnostic, cfg, responseHub, structuredOutput)
|
|
792
852
|
cachedKey = key
|
package/client.js
CHANGED
|
@@ -153,7 +153,7 @@ window.__ModuleLoader__.load({
|
|
|
153
153
|
const dictionaries = {
|
|
154
154
|
zh: {
|
|
155
155
|
title: 'Gemini 4 Adapter',
|
|
156
|
-
subtitle: '聚合 Gemini API 与 Vertex AI 官方双通道(Argon / Carbon / Hydrogen)·
|
|
156
|
+
subtitle: '聚合 Gemini API 与 Vertex AI 官方双通道(Argon / Carbon / Hydrogen / Neon)· 原生思考档位、独立协议与韧性长解码',
|
|
157
157
|
summaryLabel: '当前配置摘要',
|
|
158
158
|
summaryLongDecode: '长解码',
|
|
159
159
|
summaryEffectiveCap: '静态有效预算上限',
|
|
@@ -164,7 +164,7 @@ window.__ModuleLoader__.load({
|
|
|
164
164
|
visible: '已显示',
|
|
165
165
|
hidden: '已隐藏',
|
|
166
166
|
reasoningLabel: '默认思考档位(Thinking Level)',
|
|
167
|
-
reasoningHint: '通道默认支持 Low / Medium(默认) / High 三档;Gemini 4 Hydrogen 会话内额外支持 XHigh 第四档。按所选协议映射原生思考级别与思考摘要,永不发送 thinkingBudget。',
|
|
167
|
+
reasoningHint: '通道默认支持 Low / Medium(默认) / High 三档;Gemini 4 Hydrogen 与 Neon 会话内额外支持 XHigh 第四档。按所选协议映射原生思考级别与思考摘要,永不发送 thinkingBudget。',
|
|
168
168
|
level_low: 'Low(低)',
|
|
169
169
|
level_medium: 'Medium(默认)',
|
|
170
170
|
level_high: 'High(高)',
|
|
@@ -199,12 +199,12 @@ window.__ModuleLoader__.load({
|
|
|
199
199
|
advTitle: '5. 能力边界、自动兼容与接入说明',
|
|
200
200
|
capabilities: '实测边界:两通道 GenerateContent 均有真实生成记录,两通道 Interactions 短调用与本地工具往返已实测;Gemini Interactions 后台已测至 63,303 tokens 与单次 POST 冷恢复入口;严格跨 65,536 真实输出尚未观测,Vertex Interactions > 65,536 保持门控。',
|
|
201
201
|
how: '自动检测与凭据复用',
|
|
202
|
-
step1: '在 DSH「设置 → 模型」的 Google 或 Google Vertex AI 中添加 gemini-4-argon / gemini-4-carbon / gemini-4-hydrogen 后,本分组自动出现对应双通道入口。',
|
|
202
|
+
step1: '在 DSH「设置 → 模型」的 Google 或 Google Vertex AI 中添加 gemini-4-argon / gemini-4-carbon / gemini-4-hydrogen / gemini-4-neon 后,本分组自动出现对应双通道入口。',
|
|
203
203
|
step2: 'Vertex AI 读取 GOOGLE_APPLICATION_CREDENTIALS / GOOGLE_CLOUD_PROJECT / GOOGLE_CLOUD_LOCATION;Gemini API 复用已配置的 GOOGLE_API_KEY。',
|
|
204
204
|
step3: '插件同时为原生 google 与 google-vertex 入口注入 GenerateContent 兼容保护(原生思考档位映射、剥离采样参数与签名回传);Interactions 后台冷恢复与单次 POST 防重锁属于本插件对应的 Interactions 协议通道。',
|
|
205
205
|
scope: '路由标识',
|
|
206
206
|
detail: 'GenerateContent 检查点重连、工具签名回放与 Interactions 未知远端状态防重锁均为各自协议的内置自动机制;若遇云端终止未确认或未知中断,请结合下方诊断记录人工核查。',
|
|
207
|
-
route: '提供方路由:google-vertex-argon · 模型 ID:gemini-4-argon / gemini-4-carbon / gemini-4-hydrogen (Vertex AI) · gemini-4-argon-google / gemini-4-carbon-google / gemini-4-hydrogen-google (Gemini API)',
|
|
207
|
+
route: '提供方路由:google-vertex-argon · 模型 ID:gemini-4-argon / gemini-4-carbon / gemini-4-hydrogen / gemini-4-neon (Vertex AI) · gemini-4-argon-google / gemini-4-carbon-google / gemini-4-hydrogen-google / gemini-4-neon-google (Gemini API)',
|
|
208
208
|
recoveryTitle: '后台任务恢复',
|
|
209
209
|
recoveryHint: '最近 20 条脱敏状态,未解除记录优先。这里只解除本地防重拦截,不取消云端任务,也不自动重发。',
|
|
210
210
|
recoveryRefresh: '刷新恢复状态',
|
|
@@ -238,7 +238,7 @@ window.__ModuleLoader__.load({
|
|
|
238
238
|
},
|
|
239
239
|
en: {
|
|
240
240
|
title: 'Gemini 4 Adapter',
|
|
241
|
-
subtitle: 'Official Gemini API & Vertex AI dual-route integration (Argon, Carbon &
|
|
241
|
+
subtitle: 'Official Gemini API & Vertex AI dual-route integration (Argon, Carbon, Hydrogen & Neon) · native thinking levels, independent protocols & resilient long decode',
|
|
242
242
|
summaryLabel: 'Current configuration',
|
|
243
243
|
summaryLongDecode: 'Long Decode',
|
|
244
244
|
summaryEffectiveCap: 'Static effective cap',
|
|
@@ -249,7 +249,7 @@ window.__ModuleLoader__.load({
|
|
|
249
249
|
visible: 'Visible',
|
|
250
250
|
hidden: 'Hidden',
|
|
251
251
|
reasoningLabel: 'Default Thinking Level',
|
|
252
|
-
reasoningHint: 'The channel defaults to Low, Medium (default), and High; Gemini 4 Hydrogen additionally
|
|
252
|
+
reasoningHint: 'The channel defaults to Low, Medium (default), and High; Gemini 4 Hydrogen and Neon additionally accept XHigh in-session. Mapped to each protocol\'s native thinking level and summary output without sending thinkingBudget.',
|
|
253
253
|
level_low: 'Low',
|
|
254
254
|
level_medium: 'Medium (Default)',
|
|
255
255
|
level_high: 'High',
|
|
@@ -284,12 +284,12 @@ window.__ModuleLoader__.load({
|
|
|
284
284
|
advTitle: '5. Capabilities, Verification & Setup Guide',
|
|
285
285
|
capabilities: 'Verification boundaries: both routes have live-verified GenerateContent generation records, and both routes have live-verified Interactions short calls and local tool round-trips. Gemini Interactions background is verified up to 63,303 tokens with single-POST cold resume entry; strict > 65,536 live output is not yet observed, and Vertex Interactions > 65,536 remains gated.',
|
|
286
286
|
how: 'Auto-detection & credential reuse',
|
|
287
|
-
step1: 'Add gemini-4-argon, gemini-4-carbon, or gemini-4-
|
|
287
|
+
step1: 'Add gemini-4-argon, gemini-4-carbon, gemini-4-hydrogen, or gemini-4-neon under Google or Google Vertex AI in Models settings to expose both routes automatically.',
|
|
288
288
|
step2: 'Vertex AI reads GOOGLE_APPLICATION_CREDENTIALS / GOOGLE_CLOUD_PROJECT / GOOGLE_CLOUD_LOCATION; Gemini API reuses your configured GOOGLE_API_KEY.',
|
|
289
289
|
step3: 'Native google and google-vertex entries receive GenerateContent compatibility protection (native thinkingLevel mapping, sampling parameter stripping, and thoughtSignature replay); Interactions background cold resume and single-POST dedup locks belong to this plugin\'s Interactions protocol route.',
|
|
290
290
|
scope: 'Route identifiers',
|
|
291
291
|
detail: 'GenerateContent checkpoint reconnect, tool signature replay, and Interactions unknown-remote-state dedup locks run automatically within their respective protocols; if remote termination is unconfirmed or interrupted in an unknown state, inspect the diagnostics panel below.',
|
|
292
|
-
route: 'Provider route: google-vertex-argon · Models: gemini-4-argon / gemini-4-carbon / gemini-4-hydrogen (Vertex AI) · gemini-4-argon-google / gemini-4-carbon-google / gemini-4-hydrogen-google (Gemini API)',
|
|
292
|
+
route: 'Provider route: google-vertex-argon · Models: gemini-4-argon / gemini-4-carbon / gemini-4-hydrogen / gemini-4-neon (Vertex AI) · gemini-4-argon-google / gemini-4-carbon-google / gemini-4-hydrogen-google / gemini-4-neon-google (Gemini API)',
|
|
293
293
|
recoveryTitle: 'Background Task Recovery',
|
|
294
294
|
recoveryHint: 'Latest 20 redacted states, unreleased records first. This only releases the local duplicate-send block; it never cancels a cloud task or automatically resends a request.',
|
|
295
295
|
recoveryRefresh: 'Refresh recovery status',
|
package/index.js
CHANGED
|
@@ -15,7 +15,7 @@ import {
|
|
|
15
15
|
PROVIDER,
|
|
16
16
|
NATIVE_PROVIDER,
|
|
17
17
|
LEVELS,
|
|
18
|
-
|
|
18
|
+
supportsXhighReasoning,
|
|
19
19
|
MAX_SINGLE_CALL_TOKENS,
|
|
20
20
|
MAX_LONG_DECODE_TOKENS,
|
|
21
21
|
} from './adapter.js'
|
|
@@ -137,10 +137,10 @@ export function apply(ctx, config) {
|
|
|
137
137
|
/^(?:models\/)?gemini-4\b/i.test(proposed?.model ?? ''))) &&
|
|
138
138
|
proposed.reasoningEffort === 'max'
|
|
139
139
|
) {
|
|
140
|
-
// Hydrogen
|
|
140
|
+
// Hydrogen 与 Neon 的最高档是第四档 xhigh;其余 Gemini 4 模型仍是 high。
|
|
141
141
|
return {
|
|
142
142
|
...proposed,
|
|
143
|
-
reasoningEffort:
|
|
143
|
+
reasoningEffort: supportsXhighReasoning(proposed?.model) ? 'xhigh' : 'high',
|
|
144
144
|
}
|
|
145
145
|
}
|
|
146
146
|
return proposed
|
package/interaction-adapter.js
CHANGED
|
@@ -5,15 +5,20 @@ import { createArgonDiagnosticTracker } from './diagnostics.js'
|
|
|
5
5
|
import { interactionExitReason } from './interaction-lifecycle.js'
|
|
6
6
|
import { resolveServicePolicy } from './service-level.js'
|
|
7
7
|
// 循环导入:adapter.js 只在本模块的函数被调用时才读取这些绑定,函数声明本身已提升。
|
|
8
|
-
import { isGoogleApiModel, officialUpstreamModel } from './adapter.js'
|
|
8
|
+
import { isGoogleApiModel, officialUpstreamModel, supportsXhighReasoning, levelsForModel } from './adapter.js'
|
|
9
9
|
|
|
10
10
|
const terminalStates = new Set(['completed', 'requires_action', 'incomplete', 'failed', 'cancelled', 'budget_exceeded'])
|
|
11
11
|
export function assertInteractionOptions(options, cfg, route) {
|
|
12
12
|
const max = options.maxTokens ?? cfg.maxTokens
|
|
13
13
|
if (!Number.isSafeInteger(max) || max <= 0 || max > cfg.maxTokens) throw new Error('Interactions output budget must be a positive integer within the configured effective cap.')
|
|
14
|
+
const xhighSupported = supportsXhighReasoning(options.model)
|
|
14
15
|
const requestedLevel = options.reasoningEffort ?? cfg.reasoning
|
|
15
|
-
const
|
|
16
|
-
|
|
16
|
+
const normalizedRequested = typeof requestedLevel === 'string' ? requestedLevel.toLowerCase() : requestedLevel
|
|
17
|
+
// max 按目标模型收敛:Hydrogen 与 Neon 收到四档最高档 xhigh,Argon / Carbon 仍是 high。
|
|
18
|
+
const level = normalizedRequested === 'max' ? (xhighSupported ? 'xhigh' : 'high') : normalizedRequested
|
|
19
|
+
if (!levelsForModel(options.model).includes(level)) {
|
|
20
|
+
throw new Error(xhighSupported ? 'Gemini 4 (Hydrogen / Neon) requires low, medium, high, or xhigh thinking.' : 'Argon requires low, medium, or high thinking.')
|
|
21
|
+
}
|
|
17
22
|
if (cfg.interactionsBackground && !cfg.allowInteractionStorage) throw new Error('Background Interactions requires explicit cloud-storage consent in Gemini 4 Adapter settings.')
|
|
18
23
|
if (max > 65536 && !cfg.interactionsBackground) throw new Error('Interactions above 65,536 tokens requires background execution; no request was sent.')
|
|
19
24
|
if (route === 'google-vertex' && max > 65536) throw new Error('Vertex Interactions long decode is not verified; choose GenerateContent or explicitly lower the budget to 65,536.')
|
package/interactions-input.js
CHANGED
|
@@ -63,15 +63,15 @@ async function contentOf(blocks, settings, scrubText = false) {
|
|
|
63
63
|
export async function buildInteractionRequest(options, settings) {
|
|
64
64
|
const max = options.maxTokens ?? settings.maxTokens ?? 65536
|
|
65
65
|
const interactionModel = String(settings.upstreamModel ?? options.model ?? '')
|
|
66
|
-
const
|
|
66
|
+
const supportsXhigh = /^(?:models\/)?gemini-4-(?:hydrogen|neon)(?:-google)?$/i.test(interactionModel)
|
|
67
67
|
const requestedLevel = options.reasoningEffort ?? settings.reasoning ?? 'medium'
|
|
68
68
|
const normalizedRequested = typeof requestedLevel === 'string' ? requestedLevel.toLowerCase() : requestedLevel
|
|
69
|
-
// max 按目标模型收敛:Hydrogen
|
|
70
|
-
const level = normalizedRequested === 'max' ? (
|
|
69
|
+
// max 按目标模型收敛:Hydrogen 与 Neon 收到四档最高档 xhigh,Argon / Carbon 仍是 high。
|
|
70
|
+
const level = normalizedRequested === 'max' ? (supportsXhigh ? 'xhigh' : 'high') : normalizedRequested
|
|
71
71
|
for (const flag of [settings.background, settings.store]) if (flag !== undefined && typeof flag !== 'boolean') throw new Error('Interactions background and storage consent must be booleans.')
|
|
72
72
|
if (!Number.isSafeInteger(max) || max<1 || max>1048576) throw new Error('Invalid Interactions output token budget.')
|
|
73
|
-
const allowedLevels =
|
|
74
|
-
if (!allowedLevels.includes(level)) throw new Error(
|
|
73
|
+
const allowedLevels = supportsXhigh ? ['low','medium','high','xhigh'] : ['low','medium','high']
|
|
74
|
+
if (!allowedLevels.includes(level)) throw new Error(supportsXhigh ? 'Gemini 4 (Hydrogen / Neon) requires low, medium, high, or xhigh thinking.' : 'Argon requires low, medium, or high thinking.')
|
|
75
75
|
if (settings.background && !settings.store) throw new Error('Background Interactions requires explicit storage consent.')
|
|
76
76
|
if (max>65536 && !settings.background) throw new Error('Interactions above 65,536 tokens requires background execution.')
|
|
77
77
|
if (max>65536 && settings.route==='google-vertex') throw new Error('Vertex Interactions long decode is not verified; use GenerateContent.')
|
package/locale/en.json
CHANGED
|
@@ -1,6 +1,6 @@
|
|
|
1
1
|
{
|
|
2
2
|
"meta": {
|
|
3
3
|
"title": "Gemini 4 Adapter",
|
|
4
|
-
"description": "Official Vertex AI and Gemini API Gemini 4 adapter for DSH (Argon, Carbon and
|
|
4
|
+
"description": "Official Vertex AI and Gemini API Gemini 4 adapter for DSH (Argon, Carbon, Hydrogen and Neon): resilient multi-hop long decode, explicit protocols and service tiers, background recovery, and request diagnostics."
|
|
5
5
|
}
|
|
6
6
|
}
|
package/locale/zh.json
CHANGED
|
@@ -1,6 +1,6 @@
|
|
|
1
1
|
{
|
|
2
2
|
"meta": {
|
|
3
3
|
"title": "Gemini 4 Adapter",
|
|
4
|
-
"description": "面向 DSH 的 Gemini 4 官方双通道适配器(Vertex AI 与 Gemini API,覆盖 Argon、Carbon 与
|
|
4
|
+
"description": "面向 DSH 的 Gemini 4 官方双通道适配器(Vertex AI 与 Gemini API,覆盖 Argon、Carbon、Hydrogen 与 Neon 模型),支持 65K+ 多跳长解码、显式协议与服务层级、后台任务恢复及请求级诊断。"
|
|
5
5
|
}
|
|
6
6
|
}
|
package/package.json
CHANGED
|
@@ -1,7 +1,7 @@
|
|
|
1
1
|
{
|
|
2
2
|
"name": "dsh-vertex-argon",
|
|
3
|
-
"version": "2.
|
|
4
|
-
"description": "Gemini 4 Adapter for DSH: official Vertex AI & Gemini API channels (Argon, Carbon &
|
|
3
|
+
"version": "2.2.0",
|
|
4
|
+
"description": "Gemini 4 Adapter for DSH: official Vertex AI & Gemini API channels (Argon, Carbon, Hydrogen & Neon), resilient long decode, explicit service tiers, and request diagnostics.",
|
|
5
5
|
"license": "MIT",
|
|
6
6
|
"repository": {
|
|
7
7
|
"type": "git",
|
|
@@ -64,6 +64,7 @@
|
|
|
64
64
|
"gemini-4-argon",
|
|
65
65
|
"gemini-4-carbon",
|
|
66
66
|
"gemini-4-hydrogen",
|
|
67
|
+
"gemini-4-neon",
|
|
67
68
|
"plugin"
|
|
68
69
|
],
|
|
69
70
|
"dsh": {
|