dsh-vertex-argon 1.6.2 → 1.6.4

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 CHANGED
@@ -2,6 +2,32 @@
2
2
 
3
3
  All notable changes to `dsh-vertex-argon` are documented in this file.
4
4
 
5
+ ## [1.6.4] - 2026-11-05
6
+
7
+ ### Fixed
8
+ - **MALFORMED_FUNCTION_CALL & Stream-Timeout Tool-Mode Auto-Fallback (`adapter.js`)**:
9
+ - Added a bounded 180-second fallback map (`autoToolModeFallbacks`) keyed by session, model, and message tail so retries after `MALFORMED_FUNCTION_CALL`, transient stop reasons, or `STREAM_PHASE_TIMEOUT` automatically downgrade `toolConfig.functionCallingConfig.mode` from `VALIDATED` to `AUTO` and clear the fallback once a turn completes cleanly.
10
+ - **Role-Safe Tool Demotion & Polluted History Scrubbing (`google-signatures.js`, `interactions-input.js`)**:
11
+ - Moved demoted `[Previously executed tool ...]` headers out of `role: "model"` assistant content and prepended them to the corresponding `role: "user"` tool-result message across both `createGoogleSignatureBridge` and `generateContentHistory` / `buildInteractionRequest`, preventing the model from seeing and imitating self-authored pseudo tool-call tags in assistant history.
12
+ - Added `scrubPollutedAssistantText` and `scrubPollutedCheckpointText` to strip leaked `[:thinking:]` / `思考过程:` prefixes and trailing forged tool-call blocks from historical assistant turns and compacted `[Checkpoint N]` summaries while preserving inline backtick diagnostic quotes and `[PASS]` replies.
13
+ - Preserved ordinary empty-text `thoughtSignature` parts without standalone codecs across same-model replays.
14
+
15
+ ### Changed
16
+ - **Host Compatibility (`package.json`, `test/plugin-lifecycle.test.mjs`)**:
17
+ - Broadened `engines.dsh`, `dsh.engines.dsh`, and `@deepseek-ai/*` peer ranges to `>=0.2.0-rc.2` (and `@earendil-works/pi-ai` to `>=1.1.0`, `@google/genai` to `>=2.21.0`) for seamless compatibility with DSH `0.2.2-rc.1+`, and updated `test/plugin-lifecycle.test.mjs` to mount `@deepseek-ai/dsh-tool-executor-native` when testing against `0.2.2+` tool runtimes.
18
+
19
+ ## [1.6.3] - 2026-10-28
20
+
21
+ ### Added
22
+ - **Gemini 3.8 Flash on the Antigravity Proxy (`adapter.js`, `interaction-adapter.js`, `client.js`)**:
23
+ - Added `PROXY_FLASH_MODEL = 'gemini-3.8-flash-proxy'` (`Gemini 3.8 Flash (Antigravity)`) next to `PROXY_MODEL`; both register only when `proxyEnabled || explicitRoutes.hasProxy`, share the proxy base URL and the dedicated `ANTIGRAVITY_API_KEY` / `proxyApiKey` credential, and never touch Google / Vertex credentials.
24
+ - Added `isProxyModel` / `proxyUpstreamBaseModel` / `resolveProxyUpstreamModel` as the single proxy-map; `gemini-3.8-flash-proxy` maps `low` / `medium` / `high` 1:1 to `gemini-3.8-flash-low` / `gemini-3.8-flash-medium` / `gemini-3.8-flash-high` across both GenerateContent and Interactions, while official Vertex AI and Gemini API routes keep `gemini-4-argon`.
25
+ - Inspector shows **Antigravity Proxy** for both proxy model IDs. The 16 volatile settings are unchanged.
26
+
27
+ ### Fixed
28
+ - **Cross-Model GenerateContent History Downgrade (`interactions-input.js`, `adapter.js`)**:
29
+ - `generateContentHistory(options, model)` now also downgrades history when switching between `gemini-4-argon-proxy` and `gemini-3.8-flash-proxy` (or across providers) and the message carries `reasoning` / `tool-call` blocks: thought blocks are dropped, completed tool round-trips become explicit text, unfinished calls throw, and `replayState` is stripped. pi-ai no longer emits a signature-stripped native `functionCall` or an orphan `functionResponse` after a proxy-model switch, and old reasoning is no longer replayed as public prose. Same-model history keeps native signature replay; pure-text cross-model messages still fall through to the signature bridge.
30
+
5
31
  ## [1.6.2] - 2026-10-26
6
32
 
7
33
  ### Fixed
package/README.md CHANGED
@@ -4,13 +4,13 @@
4
4
 
5
5
  **为 [DeepSeek Harness](<https://github.com/deepseek-ai/deepseek-harness>) 提供 Vertex AI、Gemini API、Antigravity 三路由,以及 GenerateContent / Interactions 双协议接入。**
6
6
 
7
- 工程版本 **1.6.2**;兼容 **DSH 0.2.1-rc.2 / 0.2.1-rc.3**,Node.js `^22.19.0 || >=24.0.0`。版本与依赖以 [package.json](<package.json>) 为准;历史变更见 [CHANGELOG.md](<CHANGELOG.md>)。本文说明本地工程,不代表已安装、已发布或已完成本轮云端实测。
7
+ 工程版本 **1.6.4**;兼容 **DSH >=0.2.0-rc.2**,Node.js `^22.19.0 || >=24.0.0`。版本与依赖以 [package.json](<package.json>) 为准;历史变更见 [CHANGELOG.md](<CHANGELOG.md>)。本文说明本地工程,不代表已安装、已发布或已完成本轮云端实测。
8
8
 
9
9
  [三路由与凭据](<#三路由与凭据>) · [完整配置](<#完整配置16-项>) · [流式恢复](<#generatecontent四项韧性机制>) · [Inspector](<#argon-inspectordebug-与-operations>) · [历史实测](<#历史实测奥德赛七号全年舰长日志>)
10
10
 
11
11
  ## 核心能力
12
12
 
13
- - **独立第三模型**:Antigravity 使用 `gemini-4-argon-proxy`,独立地址与专属密钥,不覆盖 Gemini API 模型。
13
+ - **独立代理模型**:Antigravity 路由下有 `gemini-4-argon-proxy` 与 `gemini-3.8-flash-proxy` 两个独立模型,共用独立地址与专属密钥,不覆盖 Gemini API 模型。
14
14
  - **GenerateContent 长解码**:单跳输出上限 `65,536`,输出预算配置最高 `1,048,576`,所有尝试共用 32 跳上限;支持检查点恢复、阶段超时、安全首包重试和仅思考结束自愈。
15
15
  - **Interactions 后台恢复与状态对账**:显式启用后台与存储后,用 `creating` 预写锁防止未知创建被自动重发,以 `last_event_id` 续读已知任务;兼容 `2026-05-20` 独立生命周期事件,并在同会话发起新提示词时自动以有界非流式探针对账历史任务(清理已 `failed` / `cancelled` / `404` 死锁,保留未回放终态句柄的同时放行新提示词)。
16
16
  - **签名保真**:保留并回放仅含 `thoughtSignature` / `thought_signature` 的空 `Part`;思考档位为 `low` / `medium` / `high`,宿主传入 `max` 时收敛为 `high`。
@@ -25,8 +25,9 @@ Provider ID 保持 `google-vertex-argon`,模型位于 **Vertex Argon** 分组
25
25
  | Vertex AI | `gemini-4-argon` | `google-vertex` | `vertexProtocol` / `vertexServiceTier` |
26
26
  | Gemini Developer API | `gemini-4-argon-google` | `google-generative-ai` | `googleProtocol` / `googleServiceTier` |
27
27
  | Antigravity Proxy | `gemini-4-argon-proxy` | `google-generative-ai` | 复用 `googleProtocol` / `googleServiceTier` |
28
+ | Antigravity Proxy | `gemini-3.8-flash-proxy` | `google-generative-ai` | 同上;与 Argon 共用代理地址与专属密钥 |
28
29
 
29
- 这里的“三路由”指三个独立模型与连接目标,**并未新增第三种诊断 `route` 值**。Inspector 根据独立 `model` 显示 **Antigravity Proxy**。代理启用条件为 `proxyEnabled === true || explicitRoutes.hasProxy === true`;默认关闭,仅配置密钥不会自动开启。
30
+ 这里的“三路由”指三个连接目标、四个独立模型 ID,**并未新增第三种诊断 `route` 值**。Inspector 根据独立 `model` 显示 **Antigravity Proxy**。代理启用条件为 `proxyEnabled === true || explicitRoutes.hasProxy === true`;默认关闭,仅配置密钥不会自动开启。
30
31
 
31
32
  ### Vertex AI
32
33
 
@@ -46,7 +47,8 @@ Provider ID 保持 `google-vertex-argon`,模型位于 **Vertex Argon** 分组
46
47
  - `proxyApiKey` 先去除首尾空白;有值时使用设置值,否则只读取 `ANTIGRAVITY_API_KEY`。
47
48
  - **绝不回退到 Google/Vertex 密钥,也不把代理密钥送往 Google/Vertex。** 缺少专属密钥时应明确失败。
48
49
  - 地址和密钥使用草稿输入,失焦或点击保存后提交,重置恢复默认值。填写的 Key 保存在插件配置中,密码框仅遮挡显示;也可留空并使用 DSH 凭据中的 `ANTIGRAVITY_API_KEY`,避免直接填写配置。设置实时更新时,模型列表缓存随之失效。
49
- - 选中 `gemini-4-argon-proxy` 时,插件按推理档位(`low` / `medium` / `high`)将上游模型 ID 1:1 映射为 `gemini-4-argon-low`、`gemini-4-argon-medium`、`gemini-4-argon-high`(官方 Vertex AI 与 Gemini API 路由保持 `gemini-4-argon`)。代理沿用 Google 协议与服务层级配置;具体端点是否支持所选能力仍取决于代理实现,不是新增的云端验证结论。
50
+ - 选中代理模型时,插件按推理档位(`low` / `medium` / `high`)把上游模型 ID 1:1 映射:`gemini-4-argon-proxy` → `gemini-4-argon-low`、`gemini-4-argon-medium`、`gemini-4-argon-high`;`gemini-3.8-flash-proxy` → `gemini-3.8-flash-low`、`gemini-3.8-flash-medium`、`gemini-3.8-flash-high`(官方 Vertex AI 与 Gemini API 路由保持 `gemini-4-argon`)。GenerateContent 与 Interactions 走同一份映射。代理沿用 Google 协议与服务层级配置;具体端点是否支持所选能力仍取决于代理实现,不是新增的云端验证结论。
51
+ - **两个代理模型之间切换**时,旧模型的 GenerateContent 工具历史会在出站前降级成文本记录、旧思考一并剔除;未完成的工具调用直接报错。只有与当前代理模型完全一致的历史才保留原生签名回放,避免底层按 provider/model 摘掉签名后仍发出裸 `functionCall` 或孤立 `functionResponse`。
50
52
 
51
53
  ## 完整配置:16 项
52
54
 
@@ -148,7 +150,7 @@ billedPromptTokens, billedCachedTokens, billedTotalTokens
148
150
 
149
151
  ## 历史实测:奥德赛七号全年舰长日志
150
152
 
151
- > 以下是 **v1.5.0 历史云端实测**,保留用于说明长解码已有依据;**不是 v1.6.2 本轮新增 live 验证,也不能证明 Antigravity 或新增恢复分支已在云端验证**。本轮验证状态见 [验证账本](<docs/implementation/STATUS.md>)。
153
+ > 以下是 **v1.5.0 历史云端实测**,保留用于说明长解码已有依据;**不是 v1.6.3 本轮新增 live 验证,也不能证明 Antigravity 或新增恢复分支已在云端验证**。本轮验证状态见 [验证账本](<docs/implementation/STATUS.md>)。
152
154
 
153
155
  历史任务要求单回合连续输出 `DAY 001` 至 `DAY 365` 的全年日志,保持每日状态、每周维护、月末报告以及第 100/200/215/300/365 天的长期事件。原记录记载全年日志与状态台账完成;本文未重新运行或逐篇复核内容。
154
156
 
package/adapter.js CHANGED
@@ -24,6 +24,26 @@ export const NATIVE_PROVIDER = 'google-vertex'
24
24
  export const MODEL = 'gemini-4-argon'
25
25
  export const GOOGLE_API_MODEL = 'gemini-4-argon-google'
26
26
  export const PROXY_MODEL = 'gemini-4-argon-proxy'
27
+ /** Antigravity 反代暴露的 Gemini 3.8 Flash;与 Argon 共用同一份反代地址与专属密钥。 */
28
+ export const PROXY_FLASH_MODEL = 'gemini-3.8-flash-proxy'
29
+ export const FLASH_UPSTREAM_MODEL = 'gemini-3.8-flash'
30
+ export const PROXY_MODELS = Object.freeze([PROXY_MODEL, PROXY_FLASH_MODEL])
31
+ export const PROXY_MODEL_NAMES = Object.freeze({
32
+ [PROXY_MODEL]: 'Gemini 4 Argon (Antigravity)',
33
+ [PROXY_FLASH_MODEL]: 'Gemini 3.8 Flash (Antigravity)',
34
+ })
35
+ /** 反代模型判定:Argon 与 Flash 都走同一条 Antigravity 通道。 */
36
+ export function isProxyModel(modelId) {
37
+ return typeof modelId === 'string' && PROXY_MODELS.includes(modelId)
38
+ }
39
+ /** 反代模型对应的上游基础 ID;档位后缀由 resolveProxyUpstreamModel 追加。 */
40
+ export function proxyUpstreamBaseModel(modelId) {
41
+ return modelId === PROXY_FLASH_MODEL ? FLASH_UPSTREAM_MODEL : MODEL
42
+ }
43
+ /** 反代上游模型 ID:`<基础 ID>-<low|medium|high>`,与反代暴露的档位模型一一对应。 */
44
+ export function resolveProxyUpstreamModel(modelId, level) {
45
+ return `${proxyUpstreamBaseModel(modelId)}-${level}`
46
+ }
27
47
  export const PROXY_API_KEY_ENV = 'ANTIGRAVITY_API_KEY'
28
48
  export const DEFAULT_PROXY_BASE_URL = 'http://127.0.0.1:8045/v1beta'
29
49
  export const LEVELS = ['low', 'medium', 'high']
@@ -94,6 +114,34 @@ export function detectPiAiArgonRoutes(ctx, explicitRoutes) {
94
114
  }
95
115
 
96
116
  const TRANSIENT_GEMINI_STOP_RE = /(?:Unhandled stop reason:\s*(?:MALFORMED_RESPONSE|MALFORMED_FUNCTION_CALL|UNEXPECTED_TOOL_CALL|TOO_MANY_TOOL_CALLS)|Provider stopped with:\s*(?:MALFORMED_RESPONSE|MALFORMED_FUNCTION_CALL|UNEXPECTED_TOOL_CALL|OTHER|FINISH_REASON_UNSPECIFIED))/i
117
+ const AUTO_TOOL_MODE_TTL_MS = 180_000
118
+ const autoToolModeFallbacks = new Map()
119
+
120
+ function retryKeyOf(requestModel, context, options) {
121
+ const tail = context?.messages?.at?.(-1)
122
+ const tailHint = typeof tail?.content === 'string' ? tail.content.slice(0, 160) : JSON.stringify(tail?.content ?? '').slice(0, 160)
123
+ return `${options?.sessionId ?? 'anon'}:${requestModel?.id ?? ''}:${context?.messages?.length ?? 0}:${tailHint}`
124
+ }
125
+
126
+ function markAutoToolModeFallback(key) {
127
+ if (!key) return
128
+ if (autoToolModeFallbacks.size >= 256) autoToolModeFallbacks.delete(autoToolModeFallbacks.keys().next().value)
129
+ autoToolModeFallbacks.set(key, Date.now())
130
+ }
131
+
132
+ function shouldFallbackToAutoToolMode(key) {
133
+ const ts = key ? autoToolModeFallbacks.get(key) : undefined
134
+ if (ts === undefined) return false
135
+ if (Date.now() - ts > AUTO_TOOL_MODE_TTL_MS) {
136
+ autoToolModeFallbacks.delete(key)
137
+ return false
138
+ }
139
+ return true
140
+ }
141
+
142
+ function clearAutoToolModeFallback(key) {
143
+ if (key) autoToolModeFallbacks.delete(key)
144
+ }
97
145
 
98
146
  let apiClientProtoRef = null
99
147
  let apiClientPatch = null
@@ -134,13 +182,14 @@ export function ensureGemini4ApiClientPatch() {
134
182
  return patch.dispose
135
183
  }
136
184
 
137
- function wrapGemini4Stream(rawStream, tracker, signal) {
185
+ function wrapGemini4Stream(rawStream, tracker, signal, retryKey) {
138
186
  if (!rawStream || typeof rawStream[Symbol.asyncIterator] !== 'function') return rawStream
139
187
  return {
140
188
  [Symbol.asyncIterator]: async function* () {
141
189
  try {
142
190
  for await (const event of rawStream) {
143
191
  if (event?.type === 'done') {
192
+ clearAutoToolModeFallback(retryKey)
144
193
  const stop = event.message?.stopReason
145
194
  const outcome = stop === 'toolUse' ? 'tool-calls' : stop === 'length' ? 'max-tokens' : 'done'
146
195
  tracker?.finishStream({ outcome })
@@ -148,6 +197,9 @@ function wrapGemini4Stream(rawStream, tracker, signal) {
148
197
  const isTransient =
149
198
  typeof event?.error?.errorMessage === 'string' &&
150
199
  TRANSIENT_GEMINI_STOP_RE.test(event.error.errorMessage)
200
+ if (isTransient || event?.error?.code === 'STREAM_PHASE_TIMEOUT' || /stream phase timed out/i.test(String(event?.error?.errorMessage ?? ''))) {
201
+ markAutoToolModeFallback(retryKey)
202
+ }
151
203
  tracker?.finishStream({
152
204
  outcome: signal?.aborted ? 'aborted' : 'error',
153
205
  error: event.error,
@@ -167,6 +219,9 @@ function wrapGemini4Stream(rawStream, tracker, signal) {
167
219
  yield event
168
220
  }
169
221
  } catch (error) {
222
+ if (error?.code === 'STREAM_PHASE_TIMEOUT' || /stream phase timed out/i.test(String(error?.message ?? ''))) {
223
+ markAutoToolModeFallback(retryKey)
224
+ }
170
225
  tracker?.finishStream({
171
226
  outcome: signal?.aborted ? 'aborted' : 'error',
172
227
  error,
@@ -200,7 +255,7 @@ export function gemini4StreamSimple(
200
255
  const mapped = requestModel?.thinkingLevelMap?.[rawLevel] ?? rawLevel
201
256
  const level = typeof mapped === 'string' ? mapped.toLowerCase() : fallback
202
257
  if (!LEVELS.includes(level)) throw new LlmError('Gemini 4 Argon requires low, medium or high.', 'UNSUPPORTED_REASONING_EFFORT')
203
- const resolvedUpstreamModelId = requestModel?.id === PROXY_MODEL ? `${MODEL}-${level}` : upstreamModelId
258
+ const resolvedUpstreamModelId = isProxyModel(requestModel?.id) ? resolveProxyUpstreamModel(requestModel.id, level) : upstreamModelId
204
259
  const { reasoning, thinking, thinkingBudgets, temperature, onPayload: prior, onProviderStreamEvent: priorEvent, ...rest } = options
205
260
  const requestedMaxTokens = options.maxTokens ?? requestModel.maxTokens
206
261
  const effectiveMaxTokens =
@@ -222,6 +277,7 @@ export function gemini4StreamSimple(
222
277
  captureOptions,
223
278
  )
224
279
  const signatures = createGoogleSignatureBridge(context, requestModel)
280
+ const retryKey = retryKeyOf(requestModel, context, options)
225
281
  return wrapGemini4Stream(
226
282
  signatures.stream(nativeStream(requestModel, signatures.context, {
227
283
  ...rest,
@@ -243,6 +299,7 @@ export function gemini4StreamSimple(
243
299
  cleanConfig.httpOptions && typeof cleanConfig.httpOptions === 'object' && !Array.isArray(cleanConfig.httpOptions)
244
300
  ? cleanConfig.httpOptions
245
301
  : {}
302
+ const toolMode = shouldFallbackToAutoToolMode(retryKey) ? 'AUTO' : 'VALIDATED'
246
303
  return {
247
304
  ...body,
248
305
  model: resolvedUpstreamModelId,
@@ -251,7 +308,7 @@ export function gemini4StreamSimple(
251
308
  ...(cleanConfig.tools?.some(tool => tool.functionDeclarations?.length) ? {
252
309
  toolConfig: {
253
310
  ...cleanConfig.toolConfig,
254
- functionCallingConfig: { ...cleanConfig.toolConfig?.functionCallingConfig, mode: 'VALIDATED' },
311
+ functionCallingConfig: { ...cleanConfig.toolConfig?.functionCallingConfig, mode: toolMode },
255
312
  },
256
313
  } : {}),
257
314
  automaticContinuation: false,
@@ -271,6 +328,7 @@ export function gemini4StreamSimple(
271
328
  })),
272
329
  tracker,
273
330
  options.signal,
331
+ retryKey,
274
332
  )
275
333
  }
276
334
 
@@ -409,7 +467,7 @@ export function argonProvider(nativeVertex, models, defaultLevel = 'medium', nat
409
467
  delete cleanEnv.__ANTIGRAVITY_API_KEY__
410
468
  }
411
469
  if (configured.api === 'google-generative-ai') {
412
- const proxy = configured.id === PROXY_MODEL
470
+ const proxy = isProxyModel(configured.id)
413
471
  const apiKey = proxy ? rawEnv?.__ANTIGRAVITY_API_KEY__ : rawEnv?.__GOOGLE_API_KEY__
414
472
  if (!apiKey) throw new LlmError(proxy ? 'Antigravity proxy requires its dedicated API key.' : 'Gemini API credentials are not configured.', 'MISSING_CREDENTIAL')
415
473
  return gemini4StreamSimple(
@@ -418,7 +476,7 @@ export function argonProvider(nativeVertex, models, defaultLevel = 'medium', nat
418
476
  context,
419
477
  { ...restOptions, ...(cleanEnv ? { env: cleanEnv } : {}), ...(apiKey ? { apiKey } : {}), maxTokens: options.maxTokens ?? configured.maxTokens },
420
478
  defaultLevel,
421
- MODEL,
479
+ proxy ? proxyUpstreamBaseModel(configured.id) : MODEL,
422
480
  longDecode,
423
481
  recordDiagnostic,
424
482
  resolveServicePolicy(serviceConfig, 'google-generative-ai', 'generate-content'),
@@ -457,7 +515,7 @@ export class ArgonAdapter extends LlmAdapter {
457
515
  imageRequestPricing(provider, model) { return this.inner.imageRequestPricing?.(provider, model) }
458
516
  imageRequestTarget(provider, model, image) {
459
517
  const cfg = this.configSnapshot?.()
460
- const protocol = (model === GOOGLE_API_MODEL || model === PROXY_MODEL) ? cfg?.googleProtocol : cfg?.vertexProtocol
518
+ const protocol = (model === GOOGLE_API_MODEL || isProxyModel(model)) ? cfg?.googleProtocol : cfg?.vertexProtocol
461
519
  if (provider === PROVIDER && protocol === 'interactions' && this.interactionHandler) return interactionImageRequestTarget(image)
462
520
  return this.inner.imageRequestTarget(provider, model, image)
463
521
  }
@@ -468,13 +526,13 @@ export class ArgonAdapter extends LlmAdapter {
468
526
  resolveModel(provider, model, signal) { return this.inner.resolveModel(provider, model, signal) }
469
527
  async prepareCall(provider, model, signal) {
470
528
  const cfg = this.configSnapshot?.()
471
- if (provider === PROVIDER && cfg) resolveServicePolicy(cfg, (model === GOOGLE_API_MODEL || model === PROXY_MODEL) ? 'google-generative-ai' : 'google-vertex', (model === GOOGLE_API_MODEL || model === PROXY_MODEL) ? cfg.googleProtocol : cfg.vertexProtocol)
529
+ if (provider === PROVIDER && cfg) resolveServicePolicy(cfg, (model === GOOGLE_API_MODEL || isProxyModel(model)) ? 'google-generative-ai' : 'google-vertex', (model === GOOGLE_API_MODEL || isProxyModel(model)) ? cfg.googleProtocol : cfg.vertexProtocol)
472
530
  const prepared = await this.inner.prepareCall(provider, model, signal)
473
- const protocol = (model === GOOGLE_API_MODEL || model === PROXY_MODEL) ? cfg?.googleProtocol : cfg?.vertexProtocol
531
+ const protocol = (model === GOOGLE_API_MODEL || isProxyModel(model)) ? cfg?.googleProtocol : cfg?.vertexProtocol
474
532
  if (provider === PROVIDER && protocol === 'interactions' && this.interactionHandler) {
475
533
  return { model: prepared.model, stream: options => this.interactionHandler(options, cfg) }
476
534
  }
477
- return { ...prepared, stream: options => prepared.stream(generateContentHistory(options)) }
535
+ return { ...prepared, stream: options => prepared.stream(generateContentHistory(options, model)) }
478
536
  }
479
537
  async *stream(options) {
480
538
  const prepared = await this.prepareCall(options.provider, options.model, options.signal)
@@ -606,7 +664,20 @@ export function createArgonAdapter(ctx, configInput, nativeVertex = googleVertex
606
664
  if (cfg.proxyEnabled || detected.hasProxy) {
607
665
  models.push({
608
666
  id: PROXY_MODEL,
609
- name: 'Gemini 4 Argon (Antigravity)',
667
+ name: PROXY_MODEL_NAMES[PROXY_MODEL],
668
+ provider: PROVIDER,
669
+ api: 'google-generative-ai',
670
+ baseUrl: cfg.proxyBaseUrl,
671
+ reasoning: true,
672
+ input: ['text', 'image'],
673
+ contextWindow: cfg.contextWindow,
674
+ maxTokens: cfg.maxTokens,
675
+ thinkingLevelMap: { ...DEFAULT_THINKING_MAP },
676
+ cost: { input: 0, output: 0, cacheRead: 0, cacheWrite: 0 },
677
+ })
678
+ models.push({
679
+ id: PROXY_FLASH_MODEL,
680
+ name: PROXY_MODEL_NAMES[PROXY_FLASH_MODEL],
610
681
  provider: PROVIDER,
611
682
  api: 'google-generative-ai',
612
683
  baseUrl: cfg.proxyBaseUrl,
package/client.js CHANGED
@@ -531,7 +531,7 @@ window.__ModuleLoader__.load({
531
531
  inspectorTimeline: '请求列表', inspectorThinking: '思考等级', inspectorFailure: '失败类别', inspectorDuration: '耗时',
532
532
  inspectorAssociation: '关联状态', inspectorTokenWatermark: 'Token 水位', inspectorEyebrow: 'ARGON / DEBUG',
533
533
  proxyTitle: 'Antigravity 反代通道 (Antigravity Proxy)', proxyEnabled: '启用独立代理模型', proxyBaseUrl: '代理 Base URL', proxyApiKey: '代理 API Key',
534
- proxyHint: '独立模型 gemini-4-argon-proxy;共用 Gemini API 的协议与服务等级。密钥只使用此处配置或 ANTIGRAVITY_API_KEY,不复用 Google / Vertex 凭据。',
534
+ proxyHint: '独立模型 gemini-4-argon-proxy 与 gemini-3.8-flash-proxy;共用 Gemini API 的协议与服务等级。密钥只使用此处配置或 ANTIGRAVITY_API_KEY,不复用 Google / Vertex 凭据。',
535
535
  proxySaveHint: '开关点击即保存;地址和密钥在离开输入框或点击对应保存按钮时保存,不逐字提交。恢复默认值会关闭代理、恢复默认地址并清空专属密钥。',
536
536
  proxySaveBaseUrl: '保存代理地址', proxySaveApiKey: '保存代理密钥',
537
537
  })
@@ -539,7 +539,7 @@ window.__ModuleLoader__.load({
539
539
  inspectorTimeline: 'Requests', inspectorThinking: 'Thinking level', inspectorFailure: 'Failure category', inspectorDuration: 'Duration',
540
540
  inspectorAssociation: 'Association status', inspectorTokenWatermark: 'Token watermark', inspectorEyebrow: 'ARGON / DEBUG',
541
541
  proxyTitle: 'Antigravity Proxy', proxyEnabled: 'Enable the independent proxy model', proxyBaseUrl: 'Proxy Base URL', proxyApiKey: 'Proxy API Key',
542
- proxyHint: 'Independent gemini-4-argon-proxy model; shares Gemini API protocol and service tier settings. Uses only this key or ANTIGRAVITY_API_KEY, never Google / Vertex credentials.',
542
+ proxyHint: 'Independent gemini-4-argon-proxy and gemini-3.8-flash-proxy models; they share Gemini API protocol and service tier settings. Uses only this key or ANTIGRAVITY_API_KEY, never Google / Vertex credentials.',
543
543
  proxySaveHint: 'The switch saves immediately. URL and key save on blur or with their Save buttons, never on each keystroke. Reset disables the proxy, restores the default URL and clears its dedicated key.',
544
544
  proxySaveBaseUrl: 'Save proxy URL', proxySaveApiKey: 'Save proxy key',
545
545
  })
@@ -1047,7 +1047,7 @@ window.__ModuleLoader__.load({
1047
1047
  navigate()
1048
1048
  }
1049
1049
  const association = row => t(row?.association === 'linked' ? 'inspectorAssociated' : row?.association === 'unverified' ? 'inspectorUnverified' : 'inspectorUnassociated')
1050
- const routeName = record => record?.model === 'gemini-4-argon-proxy' || record?.route === 'antigravity-proxy' ? 'Antigravity Proxy' : record?.route === 'google-generative-ai' ? 'Gemini API' : record?.route === 'google-vertex' ? 'Vertex AI' : (record?.route ?? t('inspectorUnknown'))
1050
+ const routeName = record => record?.model === 'gemini-4-argon-proxy' || record?.model === 'gemini-3.8-flash-proxy' || record?.route === 'antigravity-proxy' ? 'Antigravity Proxy' : record?.route === 'google-generative-ai' ? 'Gemini API' : record?.route === 'google-vertex' ? 'Vertex AI' : (record?.route ?? t('inspectorUnknown'))
1051
1051
  const outcome = value => t(({ done: 'diagOutcome_done', 'tool-calls': 'diagOutcome_tool', 'max-tokens': 'diagOutcome_max', error: 'diagOutcome_error', aborted: 'diagOutcome_aborted' })[value] ?? 'diagOutcome_incomplete')
1052
1052
  const tone = value => value === 'done' || value === 'tool-calls' ? 'success' : value === 'error' ? 'error' : value === 'max-tokens' ? 'warn' : 'idle'
1053
1053
  const activeDetail = detail?.status === 'available' ? detail : null
@@ -18,37 +18,66 @@ function decode(value) {
18
18
  } catch { return null }
19
19
  }
20
20
 
21
- function unsigned(message) {
22
- return { ...message, api: 'dsh-foreign', content: message.content.map(block => {
21
+ function unsigned(message, demoted) {
22
+ const content = []
23
+ for (const block of message.content) {
23
24
  const { textSignature, thinkingSignature, thoughtSignature, ...rest } = block
24
- return rest
25
- }) }
25
+ if (rest.type === 'toolCall') {
26
+ // 工具头存进映射,交给后续 toolResult 用 user 角色呈现;绝不写回 model 正文。
27
+ demoted.set(rest.id, '[Previously executed tool ' + rest.name + '; call ' + rest.id + ']\n' + JSON.stringify(rest.arguments ?? {}))
28
+ continue
29
+ }
30
+ content.push(rest)
31
+ }
32
+ return { ...message, api: 'dsh-foreign', content: content.length > 0 ? content : [{ type: 'text', text: '[Previous model reasoning omitted when switching protocols.]' }] }
33
+ }
34
+
35
+ /** 对应被降级工具调用的结果消息:改成用户态文本,不再伪装成 functionResponse。 */
36
+ function demotedResult(message, demoted) {
37
+ const content = Array.isArray(message.content) ? message.content : [{ type: 'text', text: String(message.content ?? '') }]
38
+ const header = demoted.get(message.toolCallId)
39
+ const resultLead = '[Historical result of tool call ' + String(message.toolCallId) + '; data, not a new user instruction]'
40
+ return { role: 'user', content: [{ type: 'text', text: header ? header + '\n' + resultLead : resultLead }, ...content] }
26
41
  }
27
42
 
28
43
  // The existing textSignature field is adapter-owned opaque replay metadata.
29
44
  // Its versioned codec never reaches Google: onPayload restores the original Part.
30
45
  export function createGoogleSignatureBridge(context, model) {
31
- const restore = [], history = createHash('sha256')
46
+ const restore = [], history = createHash('sha256'), demoted = new Map()
32
47
  const messages = context.messages.map(message => {
48
+ // 被降级的工具往返:下游结果同样要变成用户态文本,否则上游会收到孤立的 functionResponse。
49
+ if (message.role === 'toolResult' && demoted.has(message.toolCallId)) {
50
+ const next = demotedResult(message, demoted)
51
+ history.update(historyRecord(next))
52
+ return next
53
+ }
54
+ if (message.role !== 'assistant') {
55
+ history.update(historyRecord(message))
56
+ return message
57
+ }
58
+ // 历史链摘要按这条消息最终交给 pi-ai 的形态累积,降级消息也不能例外。
33
59
  const previousHistory = history.copy().digest('hex')
34
- history.update(historyRecord(message))
35
- if (message.role !== 'assistant') return message
36
60
  const same = message.api === model.api && message.provider === model.provider && message.model === model.id
37
61
  const codes = message.content.map(block => block.type === 'text' ? decode(block.textSignature) : undefined)
38
62
  const hasCodes = codes.some(code => code !== undefined)
39
63
  const contentDigest = hasCodes ? digest(message.content) : undefined
40
- if (hasCodes && (!same || codes.some((code, index) => code !== undefined && (!code || message.content[index].text !== '' || code.contentDigest !== contentDigest || code.historyDigest !== previousHistory)))) return unsigned(message)
41
- const content = message.content.map((block, index) => {
42
- const code = codes[index]
43
- if (code) {
44
- const carrier = Buffer.from(code.signature).toString('base64')
45
- restore.push({ signature: code.signature, carrier, standalone: true, ...(code.thought === undefined ? {} : { thought: code.thought }) })
46
- return { ...block, textSignature: carrier }
47
- }
48
- if (same && block.type === 'text' && block.text === '' && base64(block.textSignature)) restore.push({ signature: block.textSignature, carrier: block.textSignature, standalone: false })
49
- return block
50
- })
51
- return hasCodes ? { ...message, content } : message
64
+ let next = message
65
+ if (hasCodes && (!same || codes.some((code, index) => code !== undefined && (!code || message.content[index].text !== '' || code.contentDigest !== contentDigest || code.historyDigest !== previousHistory)))) next = unsigned(message, demoted)
66
+ else {
67
+ const content = message.content.map((block, index) => {
68
+ const code = codes[index]
69
+ if (code) {
70
+ const carrier = Buffer.from(code.signature).toString('base64')
71
+ restore.push({ signature: code.signature, carrier, standalone: true, ...(code.thought === undefined ? {} : { thought: code.thought }) })
72
+ return { ...block, textSignature: carrier }
73
+ }
74
+ if (same && block.type === 'text' && block.text === '' && base64(block.textSignature)) restore.push({ signature: block.textSignature, carrier: block.textSignature, standalone: false })
75
+ return block
76
+ })
77
+ if (hasCodes) next = { ...message, content }
78
+ }
79
+ history.update(historyRecord(next))
80
+ return next
52
81
  })
53
82
  const historyDigest = history.digest('hex')
54
83
  const content = [], pending = [], standalone = new Map(), usedToolIds = new Set()
@@ -4,6 +4,8 @@ import { durableInteractionTransport } from './interaction-state.js'
4
4
  import { createArgonDiagnosticTracker } from './diagnostics.js'
5
5
  import { interactionExitReason } from './interaction-lifecycle.js'
6
6
  import { resolveServicePolicy } from './service-level.js'
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 { isProxyModel, resolveProxyUpstreamModel } from './adapter.js'
7
9
 
8
10
  const terminalStates = new Set(['completed', 'requires_action', 'incomplete', 'failed', 'cancelled', 'budget_exceeded'])
9
11
  export function assertInteractionOptions(options, cfg, route) {
@@ -19,7 +21,7 @@ export function assertInteractionOptions(options, cfg, route) {
19
21
 
20
22
  export function createInteractionsHandler({ ctx, GoogleGenAI, resolveSecret, getRoutes, taskHub, recordDiagnostic, responseHub, structuredOutput }) {
21
23
  return async function* interactions(options, cfg) {
22
- const proxy = options.model === 'gemini-4-argon-proxy'
24
+ const proxy = isProxyModel(options.model)
23
25
  const route = proxy || options.model === 'gemini-4-argon-google' ? 'google-generative-ai' : 'google-vertex'
24
26
  const requestController = new AbortController()
25
27
  const signal = options.signal ? AbortSignal.any([options.signal, requestController.signal]) : requestController.signal
@@ -153,7 +155,7 @@ export function createInteractionsHandler({ ctx, GoogleGenAI, resolveSecret, get
153
155
  return block
154
156
  }) }))
155
157
  const { streamInteractions } = await import('./interactions.js')
156
- for await (const chunk of streamInteractions({ ...options, messages, signal }, { route, upstreamModel: proxy ? `gemini-4-argon-${controls.reasoning}` : 'gemini-4-argon', ...controls, serviceTier: route === 'google-generative-ai' ? servicePolicy.tier : undefined, background: cfg.interactionsBackground, store: cfg.allowInteractionStorage, transport, resolveImage, structuredOutput, onEvent: observed, onReconnectDelay: ms => { pendingBackoffMs = ms }, onTerminal: () => { complete = true }, onExit: reason => { exitReason = reason } })) {
158
+ for await (const chunk of streamInteractions({ ...options, messages, signal }, { route, upstreamModel: proxy ? resolveProxyUpstreamModel(options.model, controls.reasoning) : 'gemini-4-argon', ...controls, serviceTier: route === 'google-generative-ai' ? servicePolicy.tier : undefined, background: cfg.interactionsBackground, store: cfg.allowInteractionStorage, transport, resolveImage, structuredOutput, onEvent: observed, onReconnectDelay: ms => { pendingBackoffMs = ms }, onTerminal: () => { complete = true }, onExit: reason => { exitReason = reason } })) {
157
159
  if (chunk.type === 'usage') {
158
160
  recordUsage()
159
161
  // Only an observed first-hop input watermark can be normalized for the
@@ -3,15 +3,47 @@ export const INTERACTIONS_REPLAY_API = 'google-interactions-v1'
3
3
  export const contentHash = content => createHash('sha256').update(JSON.stringify(content)).digest('hex')
4
4
  export const historyHash = messages => contentHash(messages.map(m => ({ role: m.role, content: m.content, toolCallId: m.toolCallId, isError: m.isError })))
5
5
  const copy = value => JSON.parse(JSON.stringify(value))
6
+ const FORGED_THINKING_PREFIX_RE = /^\s*(?:\[:thinking:\]|\[thinking\]|思考过程[::]\r?\n)\s*/i
7
+ const FORGED_PASS_SUFFIX_RE = /^[\s\S]*?(\[\s*PASS\s*\])\s*$/i
8
+ const FORGED_TOOL_CALL_TAIL_RE = /(?:\r?\n)?(?<!`)\[Previously executed tool [\w.-]+; call [^\]]+\](?: \([^)\r\n]*\))?\r?\n\{[\s\S]*$/
9
+ const THINKING_TRANSITION_RE = /^[\s\S]*?(?:(?:来,(?:我们)?|让我们|我们先)?(?:先发一句简短(?:提示|回复|确认)|用一句话说明要[^\n。!]*|先在群里(?:回复|回)一句短话|先调一次 `ops_bash`[^\n。!]*|不需要调工具,直接简明扼要回复群聊|无需在这里自己调工具[^\n。!]*|直接把这份完整诊断报告发出来[^\n。!]*|让我组织好清晰、简明的话术[^\n。!]*|开始撰写回复)[^\n。!]*[。!]|Let's (?:run|call|update) [^\n!]+!)\s*/
10
+ const CHECKPOINT_THINKING_TEST_RE = /(\[Checkpoint \d+\]\r?\n)\s*(?:\[:thinking:\]|\[thinking\]|思考过程[::]\r?\n)[\s\S]*?(?=##\s)/
11
+ const CHECKPOINT_THINKING_RE = /(\[Checkpoint \d+\]\r?\n)\s*(?:\[:thinking:\]|\[thinking\]|思考过程[::]\r?\n)[\s\S]*?(?=##\s)/g
12
+ export function hasPollutedAssistantText(text) {
13
+ return typeof text === 'string' && (FORGED_THINKING_PREFIX_RE.test(text) || FORGED_TOOL_CALL_TAIL_RE.test(text))
14
+ }
15
+ export function hasPollutedCheckpointText(text) {
16
+ return typeof text === 'string' && text.includes('[Checkpoint ') && CHECKPOINT_THINKING_TEST_RE.test(text)
17
+ }
18
+ export function scrubPollutedCheckpointText(text) {
19
+ if (typeof text !== 'string' || !text.includes('[Checkpoint ')) return text
20
+ return text.replace(CHECKPOINT_THINKING_RE, '$1')
21
+ }
22
+ export function scrubPollutedAssistantText(text) {
23
+ if (typeof text !== 'string') return text
24
+ let next = text
25
+ if (FORGED_TOOL_CALL_TAIL_RE.test(next)) next = next.replace(FORGED_TOOL_CALL_TAIL_RE, '').trimEnd()
26
+ if (FORGED_THINKING_PREFIX_RE.test(next)) {
27
+ const passMatch = next.match(FORGED_PASS_SUFFIX_RE)
28
+ if (passMatch) return passMatch[1]
29
+ const stripped = next.replace(FORGED_THINKING_PREFIX_RE, '')
30
+ const afterTransition = stripped.replace(THINKING_TRANSITION_RE, '').trimStart()
31
+ next = afterTransition.length > 0 && afterTransition.length < stripped.length ? afterTransition : stripped
32
+ }
33
+ return next
34
+ }
6
35
  function argsOf(value) {
7
36
  const args = typeof value === 'string' ? JSON.parse(value) : value
8
37
  if (!args || typeof args !== 'object' || Array.isArray(args)) throw new Error('Function arguments must be a complete JSON object.')
9
38
  return args
10
39
  }
11
- async function contentOf(blocks, settings) {
40
+ async function contentOf(blocks, settings, scrubText = false) {
12
41
  const content=[]
13
42
  for (const block of blocks ?? []) {
14
- if (block.type === 'text') content.push({type:'text',text:block.text})
43
+ if (block.type === 'text') {
44
+ const text = scrubText ? scrubPollutedAssistantText(block.text) : block.text
45
+ if (!scrubText || text.length > 0) content.push({type:'text',text})
46
+ }
15
47
  else if (block.type === 'image') {
16
48
  if (!settings.resolveImage) throw new Error('Interactions image input needs the host attachment resolver.')
17
49
  const image=await settings.resolveImage(block)
@@ -46,30 +78,37 @@ export async function buildInteractionRequest(options, settings) {
46
78
  system.push(parts.map(p=>p.text).join('\n'))
47
79
  continue
48
80
  }
49
- if (message.role==='user') { input.push({type:'user_input',content:await contentOf(message.content,settings)}); continue }
81
+ if (message.role==='user') {
82
+ const blocks = Array.isArray(message.content)
83
+ ? message.content.map(b => b?.type === 'text' && hasPollutedCheckpointText(b.text) ? { ...b, text: scrubPollutedCheckpointText(b.text) } : b)
84
+ : message.content
85
+ input.push({type:'user_input',content:await contentOf(blocks,settings)})
86
+ continue
87
+ }
50
88
  if (message.role==='assistant') {
51
89
  const replay=message.source?.replayState?.response
52
- const native=replay?.api===INTERACTIONS_REPLAY_API && replay.provider===options.provider && replay.model===options.model && replay.route===settings.route && replay.contentHash===contentHash(message.content) && replay.historyHash===historyHash(options.messages.slice(0,position)) && Array.isArray(replay.steps)
90
+ const polluted=message.content.some(b=>b?.type==='text'&&hasPollutedAssistantText(b.text))
91
+ const native=!polluted && replay?.api===INTERACTIONS_REPLAY_API && replay.provider===options.provider && replay.model===options.model && replay.route===settings.route && replay.contentHash===contentHash(message.content) && replay.historyHash===historyHash(options.messages.slice(0,position)) && Array.isArray(replay.steps)
53
92
  const calls=message.content.filter(b=>b.type==='tool-call')
54
93
  for(const call of calls){
55
94
  callNames.set(call.id,call.name)
56
- callModes.set(call.id,native?'native':'transcript')
57
95
  if(!native&&!resultIds.has(call.id))throw new Error('An unfinished foreign or edited tool call cannot be replayed through Interactions.')
96
+ callModes.set(call.id,native?'native':'[Previously executed tool '+call.name+'; call '+call.id+']\n'+JSON.stringify(argsOf(call.arguments)))
58
97
  }
59
98
  if(native){
60
99
  if(replay.steps.some(s=>!['thought','model_output','function_call'].includes(s.type)))throw new Error('Invalid Interactions replay step.')
61
100
  input.push(...copy(replay.steps))
62
101
  }else{
63
- const content=await contentOf(message.content,settings)
64
- for(const call of calls)content.push({type:'text',text:'[Previously executed tool '+call.name+'; call '+call.id+']\n'+JSON.stringify(argsOf(call.arguments))})
102
+ const content=await contentOf(message.content,settings,true)
65
103
  input.push({type:'model_output',content:content.length?content:[{type:'text',text:'[Previous model reasoning omitted.]'}]})
66
104
  }
67
105
  continue
68
106
  }
69
107
  if(message.role==='tool'){
70
108
  const content=await contentOf(message.content,settings)
71
- if(callModes.get(message.toolCallId)==='native')input.push({type:'function_result',call_id:message.toolCallId,name:callNames.get(message.toolCallId),is_error:Boolean(message.isError),result:content.length?content:[{type:'text',text:'[Tool completed without output.]'}]})
72
- else input.push({type:'user_input',content:[{type:'text',text:'[Result of previously executed tool call '+message.toolCallId+(message.isError?'; error':'')+']'},...content]})
109
+ const mode=callModes.get(message.toolCallId)
110
+ if(mode==='native')input.push({type:'function_result',call_id:message.toolCallId,name:callNames.get(message.toolCallId),is_error:Boolean(message.isError),result:content.length?content:[{type:'text',text:'[Tool completed without output.]'}]})
111
+ else input.push({type:'user_input',content:[{type:'text',text:(typeof mode==='string'?mode+'\n':'')+'[Result of previously executed tool call '+message.toolCallId+(message.isError?'; error':'')+']'},...content]})
73
112
  continue
74
113
  }
75
114
  throw new Error('Unsupported Interactions message role.')
@@ -91,27 +130,67 @@ export async function buildInteractionRequest(options, settings) {
91
130
 
92
131
  // Switching back to GenerateContent must not feed its SDK Interactions replay
93
132
  // envelopes or unsigned function calls under the same DSH provider/model alias.
94
- export function generateContentHistory(options) {
133
+ // 同插件内换代理模型(Argon <-> Flash)同样是跨路由:pi-ai 按 provider/model 判定
134
+ // 不一致时会摘掉 thoughtSignature,却仍把旧 functionCall 发出去,并把旧思考转成正文。
135
+ //
136
+ // 降级后的工具头绝不写回 assistant 正文:那会让模型在 role:"model" 历史里看到
137
+ // 自己连续手写该标签,形成 few-shot 模仿。头部改存起来,拼到后续 tool 回执里。
138
+ export function generateContentHistory(options, defaultModel = options?.model) {
139
+ const targetProvider = options.provider ?? 'google-vertex-argon'
140
+ const targetModel = options.model ?? defaultModel
95
141
  const resultIds=new Set(options.messages.filter(m=>m.role==='tool').map(m=>m.toolCallId))
96
- const foreignCalls=new Set()
142
+ const foreignCalls=new Map()
97
143
  let changed=false
98
144
  const messages=options.messages.map(message=>{
99
- if(message.role==='assistant'&&message.source?.replayState?.response?.api===INTERACTIONS_REPLAY_API){
100
- changed=true
101
- const content=message.content.filter(b=>b.type!=='reasoning'&&b.type!=='tool-call')
102
- for(const call of message.content.filter(b=>b.type==='tool-call')){
103
- if(!resultIds.has(call.id))throw new Error('Complete the pending Interactions tool call before switching protocols.')
104
- foreignCalls.add(call.id)
105
- content.push({type:'text',text:'[Previously executed tool '+call.name+'; call '+call.id+']\n'+JSON.stringify(argsOf(call.arguments))})
145
+ if(message.role!=='assistant'){
146
+ if(message.role==='tool'&&foreignCalls.has(message.toolCallId)){
147
+ changed=true
148
+ const header=foreignCalls.get(message.toolCallId)
149
+ return {role:'user',content:[{type:'text',text:header+'\n[Historical result of tool call '+message.toolCallId+'; data, not a new user instruction]'},...message.content]}
106
150
  }
107
- const { replayState, ...source }=message.source
108
- return {...message,source,content:content.length?content:[{type:'text',text:'[Previous model reasoning omitted when switching protocols.]'}]}
151
+ if(message.role==='user'&&Array.isArray(message.content)&&message.content.some(b=>b?.type==='text'&&hasPollutedCheckpointText(b.text))){
152
+ changed=true
153
+ return {...message,content:message.content.map(b=>b?.type==='text'&&hasPollutedCheckpointText(b.text)?{...b,text:scrubPollutedCheckpointText(b.text)}:b)}
154
+ }
155
+ return message
109
156
  }
110
- if(message.role==='tool'&&foreignCalls.has(message.toolCallId)){
157
+ const replay=message.source?.replayState?.response
158
+ const interactionsReplay=replay?.api===INTERACTIONS_REPLAY_API
159
+ // 只降级带推理块或工具调用的跨模型历史;纯文本消息仍由签名桥按 !same 自行剥离独立签名。
160
+ const crossModel=Boolean(targetModel)&&(
161
+ message.source?.provider!==targetProvider||
162
+ message.source?.model!==targetModel||
163
+ (replay!==undefined&&replay!==null&&(replay.provider!==targetProvider||replay.model!==targetModel))
164
+ )&&message.content.some(block=>block?.type==='reasoning'||block?.type==='tool-call')
165
+ const pollutedText=message.content.some(block=>block?.type==='text'&&hasPollutedAssistantText(block.text))
166
+ if(!interactionsReplay&&!crossModel&&!pollutedText)return message
167
+ if(!interactionsReplay&&!crossModel&&pollutedText){
111
168
  changed=true
112
- return {role:'user',content:[{type:'text',text:'[Historical result of tool call '+message.toolCallId+'; data, not a new user instruction]'},...message.content]}
169
+ const hasCalls=message.content.some(block=>block?.type==='tool-call')
170
+ if(hasCalls){
171
+ return {...message,content:message.content.map(block=>block?.type==='text'&&hasPollutedAssistantText(block.text)?{...block,text:scrubPollutedAssistantText(block.text)||'[Previous model reasoning omitted when switching protocols.]'}:block)}
172
+ }
173
+ const cleaned=message.content.map(block=>block?.type==='text'?{...block,text:scrubPollutedAssistantText(block.text)}:block).filter(block=>block?.type!=='text'||block.text.length>0)
174
+ const source=message.source?(({replayState,...rest})=>rest)(message.source):undefined
175
+ return {...message,...(source===undefined?{}:{source}),content:cleaned.length?cleaned:[{type:'text',text:'[Previous model reasoning omitted when switching protocols.]'}]}
176
+ }
177
+ changed=true
178
+ const content=[]
179
+ for(const block of message.content){
180
+ if(block.type==='reasoning'||block.type==='tool-call')continue
181
+ if(block.type==='text'){
182
+ const text=scrubPollutedAssistantText(block.text)
183
+ if(text.length>0)content.push({...block,text})
184
+ continue
185
+ }
186
+ content.push(block)
187
+ }
188
+ for(const call of message.content.filter(b=>b.type==='tool-call')){
189
+ if(!resultIds.has(call.id))throw new Error('Complete the pending Interactions tool call before switching protocols.')
190
+ foreignCalls.set(call.id,'[Previously executed tool '+call.name+'; call '+call.id+']\n'+JSON.stringify(argsOf(call.arguments)))
113
191
  }
114
- return message
192
+ const source=message.source?(({replayState,...rest})=>rest)(message.source):undefined
193
+ return {...message,...(source===undefined?{}:{source}),content:content.length?content:[{type:'text',text:'[Previous model reasoning omitted when switching protocols.]'}]}
115
194
  })
116
195
  return changed?{...options,messages}:options
117
196
  }
package/package.json CHANGED
@@ -1,6 +1,6 @@
1
1
  {
2
2
  "name": "dsh-vertex-argon",
3
- "version": "1.6.2",
3
+ "version": "1.6.4",
4
4
  "description": "Gemini API, Vertex AI and Antigravity Argon for DSH: resilient streaming, explicit service tiers and focused request diagnostics.",
5
5
  "license": "MIT",
6
6
  "repository": {
@@ -53,7 +53,7 @@
53
53
  ],
54
54
  "engines": {
55
55
  "node": "^22.19.0 || >=24.0.0",
56
- "dsh": "0.2.1-rc.2 || 0.2.1-rc.3"
56
+ "dsh": ">=0.2.0-rc.2"
57
57
  },
58
58
  "keywords": [
59
59
  "deepseek-harness",
@@ -66,7 +66,7 @@
66
66
  ],
67
67
  "dsh": {
68
68
  "engines": {
69
- "dsh": "0.2.1-rc.2 || 0.2.1-rc.3"
69
+ "dsh": ">=0.2.0-rc.2"
70
70
  },
71
71
  "bundle": {
72
72
  "patch": "./cordis.patch.yml"
@@ -86,13 +86,13 @@
86
86
  "ajv": "8.20.0"
87
87
  },
88
88
  "peerDependencies": {
89
- "@deepseek-ai/dsh-llm": "0.2.1-rc.2 || 0.2.1-rc.3",
90
- "@deepseek-ai/dsh-llm-pi-ai": "0.2.1-rc.2 || 0.2.1-rc.3",
91
- "@deepseek-ai/dsh-launch-environment": "0.2.1-rc.2 || 0.2.1-rc.3",
89
+ "@deepseek-ai/dsh-llm": ">=0.2.0-rc.2",
90
+ "@deepseek-ai/dsh-llm-pi-ai": ">=0.2.0-rc.2",
91
+ "@deepseek-ai/dsh-launch-environment": ">=0.2.0-rc.2",
92
92
  "@deepseek-ai/schemastery": "^3.18.4",
93
- "@earendil-works/pi-ai": "1.1.0",
94
- "@google/genai": "2.21.0",
95
- "@deepseek-ai/dsh-typert-protocol": "0.2.1-rc.2 || 0.2.1-rc.3",
93
+ "@earendil-works/pi-ai": ">=1.1.0",
94
+ "@google/genai": ">=2.21.0",
95
+ "@deepseek-ai/dsh-typert-protocol": ">=0.2.0-rc.2",
96
96
  "zod": "^4.0.0"
97
97
  },
98
98
  "peerDependenciesMeta": {