dsh-vertex-argon 2.2.2 → 2.2.4
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 +25 -0
- package/README.md +3 -3
- package/adapter.js +235 -76
- package/google-signatures.js +20 -4
- package/index.js +10 -4
- package/interaction-adapter.js +8 -5
- package/interactions-input.js +12 -4
- package/package.json +1 -1
package/CHANGELOG.md
CHANGED
|
@@ -2,6 +2,31 @@
|
|
|
2
2
|
|
|
3
3
|
All notable changes to **Gemini 4 Adapter** (`dsh-vertex-argon`) are documented in this file.
|
|
4
4
|
|
|
5
|
+
## [2.2.4] - 2026-11-19
|
|
6
|
+
|
|
7
|
+
### Fixed
|
|
8
|
+
- **Google Background Interactions `longDecode: false` Clamp & `maxTokens: null` Guard (`interaction-adapter.js`, `interactions-input.js`)**:
|
|
9
|
+
- Clamped outbound `maxTokens` / `generation_config.max_output_tokens` to `65,536` when `longDecode === false` (including Google background Interactions where `explicitMaxTokensCap > 65536`), and rejected explicit `maxTokens: null` in both `buildInteractionRequest` and `argonProvider.streamSimple`.
|
|
10
|
+
- **GenerateContent `onPayload` `extraBody` Thinking Sanitization, Mandatory Output Cap & Cloned Model Ceiling Retention (`adapter.js`)**:
|
|
11
|
+
- Sanitized `httpOptions.extraBody` and `extraBody.generationConfig` / `generation_config` (`thinkingConfig`, `thinkingBudget`, `includeThoughts`, sampling keys) for all Gemini 4 models (plus explicit cache fields on Hydrogen/Neon), and ensured omitted `config.maxOutputTokens` after upstream `onPayload` hooks is restored to the resolved output budget.
|
|
12
|
+
- Preserved trusted `configured` model properties and `MAX_TOKENS_CEILING` symbols in `argonProvider.streamSimple` so JSON-cloned model descriptors cannot bypass configured caps.
|
|
13
|
+
- **Signed Thinking Part Boundaries & Startup Registration Rollback (`google-signatures.js`, `index.js`)**:
|
|
14
|
+
- Split subsequent unsigned thinking parts away from preceding signed thinking parts in `observe()` so empty signed thinking parts preserve 1:1 boundaries.
|
|
15
|
+
- Registered `installGemini4PiAiPatch()` disposal immediately and rolled back the lease if `ctx.llm.registerAdapter()` throws.
|
|
16
|
+
|
|
17
|
+
## [2.2.3] - 2026-11-19
|
|
18
|
+
|
|
19
|
+
### Fixed
|
|
20
|
+
- **Signature Part Boundary Preservation (`google-signatures.js`)**:
|
|
21
|
+
- Split consecutive signed parts (`text` / `thinking`) and signed empty-text parts in `observe()` so distinct signatures and original wire Part boundaries round-trip 1:1 without merging.
|
|
22
|
+
- **Outbound Payload Cap Enforcement & Full `1,048,576` Long-Decode Headroom (`adapter.js`)**:
|
|
23
|
+
- Enforced the resolved route/mode `maxOutputTokens` ceiling after `onPayload` transforms (including `httpOptions.extraBody` and `config.maxOutputTokens` / `max_output_tokens`) and separated host compaction headroom (`contextWindow - 131,072`) from the protocol ceiling (`1,048,576`) so explicit `1,048,576` long-decode budgets are reachable.
|
|
24
|
+
- **Eager Interactions Budget/Option Validation & Model-Aware Defaults (`adapter.js`, `interaction-adapter.js`, `interactions-input.js`)**:
|
|
25
|
+
- Validated `maxTokens` (including `null` and configured caps) and explicit conflicting dual reasoning fields synchronously in `ArgonAdapter.prepareCall` before entering the Interactions async generator.
|
|
26
|
+
- Added `defaultReasoningForModel` (`'high'` for Hydrogen / Neon when user config omits `reasoning`, keeping `'medium'` for Argon / Carbon and channel-level UI defaults).
|
|
27
|
+
- **Overlapping `installGemini4PiAiPatch` / `ensureGemini4ApiClientPatch` Safety (`adapter.js`)**:
|
|
28
|
+
- Managed active installers via an ordered owner stack + shared first-touch model state and reference-counted `ApiClient.prototype.requestStream` leases so out-of-order disposal preserves remaining active patches and restores original properties cleanly when the last installer unmounts.
|
|
29
|
+
|
|
5
30
|
## [2.2.2] - 2026-11-19
|
|
6
31
|
|
|
7
32
|
### Fixed
|
package/README.md
CHANGED
|
@@ -4,7 +4,7 @@
|
|
|
4
4
|
|
|
5
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**:`2.2.
|
|
7
|
+
- **当前版本**:`2.2.4`([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
|
|
|
@@ -93,8 +93,8 @@ dsh plugin --profile desktop add dsh-vertex-argon
|
|
|
93
93
|
| 分组 | 配置项 | 默认值 | 取值范围与说明 |
|
|
94
94
|
|---|---|---|---|
|
|
95
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 |
|
|
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`) |
|
|
97
|
-
| 基础与生成 | `maxTokens` | `65536` | `1`–`1048576`;超过 `65,536`
|
|
96
|
+
| 基础与生成 | `reasoning` | `medium`(UI 设置页)/ 未配置时 Hydrogen 与 Neon 模型默认 `high` | 默认思考档位:`low` / `medium` / `high`(Hydrogen 与 Neon 会话内额外支持 `xhigh`) |
|
|
97
|
+
| 基础与生成 | `maxTokens` | `65536` | `1`–`1048576`;超过 `65,536` 需启用长解码;协议请求上限支持至 `1,048,576`(`configuredMaxTokens` 仍为宿主压缩预留 `131,072` 空间) |
|
|
98
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 |
|
|
99
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 |
|
|
100
100
|
| 协议与服务层级 | `googleProtocol` | `generate-content` | `generate-content` / `interactions`(仅作用于 Gemini API) |
|
package/adapter.js
CHANGED
|
@@ -6,7 +6,7 @@ import { createArgonDiagnosticTracker } from './diagnostics.js'
|
|
|
6
6
|
import { createInteractionsHandler } from './interaction-adapter.js'
|
|
7
7
|
import { interactionImageRequestTarget } from './interaction-image.js'
|
|
8
8
|
import { SERVICE_TIERS, resolveServicePolicy, mergeServiceHeaders } from './service-level.js'
|
|
9
|
-
import { generateContentHistory, resolveOfficialGemini4Model, resolveGemini4ReasoningLevel } from './interactions-input.js'
|
|
9
|
+
import { generateContentHistory, resolveOfficialGemini4Model, resolveGemini4ReasoningLevel, defaultReasoningForModel } from './interactions-input.js'
|
|
10
10
|
import { createGoogleSignatureBridge } from './google-signatures.js'
|
|
11
11
|
import { createInteractionQuery } from './interaction-query.js'
|
|
12
12
|
import { assertPreparedStructuredOutput } from './structured-output.js'
|
|
@@ -277,6 +277,7 @@ function clearAutoToolModeFallback(key) {
|
|
|
277
277
|
|
|
278
278
|
let apiClientProtoRef = null
|
|
279
279
|
let apiClientPatch = null
|
|
280
|
+
const apiClientLeases = new Set()
|
|
280
281
|
|
|
281
282
|
function getApiClientPrototype() {
|
|
282
283
|
if (apiClientProtoRef) return apiClientProtoRef
|
|
@@ -289,29 +290,65 @@ function getApiClientPrototype() {
|
|
|
289
290
|
return apiClientProtoRef
|
|
290
291
|
}
|
|
291
292
|
|
|
292
|
-
|
|
293
|
+
function isGemini4ApiClientPatched() {
|
|
294
|
+
return Boolean(apiClientPatch?.isActive?.())
|
|
295
|
+
}
|
|
296
|
+
|
|
297
|
+
export function ensureGemini4ApiClientPatch({ lease = false } = {}) {
|
|
293
298
|
const proto = getApiClientPrototype()
|
|
294
299
|
if (!proto || typeof proto.requestStream !== 'function') return () => {}
|
|
295
|
-
if (apiClientPatch
|
|
300
|
+
if (apiClientPatch && apiClientPatch.isActive()) {
|
|
301
|
+
const patch = apiClientPatch
|
|
302
|
+
if (lease) {
|
|
303
|
+
const token = Symbol('argonApiClientLease')
|
|
304
|
+
apiClientLeases.add(token)
|
|
305
|
+
return () => {
|
|
306
|
+
if (!apiClientLeases.delete(token)) return
|
|
307
|
+
patch.maybeDispose()
|
|
308
|
+
}
|
|
309
|
+
}
|
|
310
|
+
return patch.disposeUnowned
|
|
311
|
+
}
|
|
296
312
|
const orig = proto.requestStream
|
|
297
313
|
let active = true
|
|
314
|
+
let unowned = !lease
|
|
315
|
+
const token = lease ? Symbol('argonApiClientLease') : null
|
|
316
|
+
if (token) apiClientLeases.add(token)
|
|
298
317
|
function patchedRequestStream(request) {
|
|
299
318
|
const meta = request?.httpOptions?.[ARGON_LONG_DECODE_SYMBOL]
|
|
300
319
|
if (!active || !meta) return orig.call(this, request)
|
|
301
320
|
return continueArgonRequestStream(this, orig, request, meta)
|
|
302
321
|
}
|
|
322
|
+
const deactivate = () => {
|
|
323
|
+
if (!active) return
|
|
324
|
+
active = false
|
|
325
|
+
unowned = false
|
|
326
|
+
apiClientLeases.clear()
|
|
327
|
+
// A later wrapper belongs to its installer, even when it delegates to us.
|
|
328
|
+
if (proto.requestStream === patchedRequestStream) proto.requestStream = orig
|
|
329
|
+
if (apiClientPatch === patch) apiClientPatch = null
|
|
330
|
+
}
|
|
303
331
|
const patch = {
|
|
304
|
-
|
|
332
|
+
isActive: () => active,
|
|
333
|
+
disposeUnowned() {
|
|
334
|
+
if (!active) return
|
|
335
|
+
unowned = false
|
|
336
|
+
if (apiClientLeases.size === 0) deactivate()
|
|
337
|
+
},
|
|
338
|
+
maybeDispose() {
|
|
305
339
|
if (!active) return
|
|
306
|
-
|
|
307
|
-
// A later wrapper belongs to its installer, even when it delegates to us.
|
|
308
|
-
if (proto.requestStream === patchedRequestStream) proto.requestStream = orig
|
|
309
|
-
if (apiClientPatch === patch) apiClientPatch = null
|
|
340
|
+
if (!unowned && apiClientLeases.size === 0) deactivate()
|
|
310
341
|
},
|
|
311
342
|
}
|
|
312
343
|
proto.requestStream = patchedRequestStream
|
|
313
344
|
apiClientPatch = patch
|
|
314
|
-
|
|
345
|
+
if (lease) {
|
|
346
|
+
return () => {
|
|
347
|
+
if (!apiClientLeases.delete(token)) return
|
|
348
|
+
patch.maybeDispose()
|
|
349
|
+
}
|
|
350
|
+
}
|
|
351
|
+
return patch.disposeUnowned
|
|
315
352
|
}
|
|
316
353
|
|
|
317
354
|
function wrapGemini4Stream(rawStream, tracker, signal, retryKey) {
|
|
@@ -367,13 +404,92 @@ function wrapGemini4Stream(rawStream, tracker, signal, retryKey) {
|
|
|
367
404
|
}
|
|
368
405
|
}
|
|
369
406
|
|
|
370
|
-
|
|
371
|
-
|
|
372
|
-
const routeCeiling = requestModel?.provider === PROVIDER
|
|
407
|
+
function routeCeilingFor(requestModel, longDecode = true) {
|
|
408
|
+
return requestModel?.provider === PROVIDER
|
|
373
409
|
? (requestModel?.[MAX_TOKENS_CEILING] ?? MAX_LONG_DECODE_TOKENS)
|
|
374
410
|
: (Number.isSafeInteger(requestModel?.maxTokens) && requestModel.maxTokens > 0
|
|
375
411
|
? Math.min(MAX_LONG_DECODE_TOKENS, requestModel.maxTokens)
|
|
376
412
|
: (longDecode === false ? MAX_SINGLE_CALL_TOKENS : MAX_LONG_DECODE_TOKENS))
|
|
413
|
+
}
|
|
414
|
+
|
|
415
|
+
function isPlainObjectRecord(value) {
|
|
416
|
+
if (!value || typeof value !== 'object' || Array.isArray(value)) return false
|
|
417
|
+
const proto = Object.getPrototypeOf(value)
|
|
418
|
+
return proto === null || proto === Object.prototype
|
|
419
|
+
}
|
|
420
|
+
|
|
421
|
+
const EXTRA_BODY_STRIPPED_KEYS = [
|
|
422
|
+
'thinkingConfig',
|
|
423
|
+
'thinking_config',
|
|
424
|
+
'thinkingBudget',
|
|
425
|
+
'thinking_budget',
|
|
426
|
+
'includeThoughts',
|
|
427
|
+
'include_thoughts',
|
|
428
|
+
'temperature',
|
|
429
|
+
'topP',
|
|
430
|
+
'top_p',
|
|
431
|
+
'topK',
|
|
432
|
+
'top_k',
|
|
433
|
+
'candidateCount',
|
|
434
|
+
'candidate_count',
|
|
435
|
+
'frequencyPenalty',
|
|
436
|
+
'frequency_penalty',
|
|
437
|
+
'presencePenalty',
|
|
438
|
+
'presence_penalty',
|
|
439
|
+
]
|
|
440
|
+
|
|
441
|
+
function sanitizeGemini4ExtraBody(extraBody, stripExplicitCache) {
|
|
442
|
+
if (extraBody === undefined || extraBody === null) return extraBody
|
|
443
|
+
if (!isPlainObjectRecord(extraBody)) {
|
|
444
|
+
throw new LlmError('Gemini 4 httpOptions.extraBody must be a plain object.', 'INVALID_REQUEST')
|
|
445
|
+
}
|
|
446
|
+
const cleanExtraBody = { ...extraBody }
|
|
447
|
+
for (const key of EXTRA_BODY_STRIPPED_KEYS) delete cleanExtraBody[key]
|
|
448
|
+
if (stripExplicitCache) {
|
|
449
|
+
delete cleanExtraBody.cachedContent
|
|
450
|
+
delete cleanExtraBody.cached_content
|
|
451
|
+
}
|
|
452
|
+
for (const cfgKey of ['generationConfig', 'generation_config']) {
|
|
453
|
+
if (cleanExtraBody[cfgKey] === undefined || cleanExtraBody[cfgKey] === null) continue
|
|
454
|
+
if (!isPlainObjectRecord(cleanExtraBody[cfgKey])) {
|
|
455
|
+
throw new LlmError(`Gemini 4 httpOptions.extraBody.${cfgKey} must be a plain object.`, 'INVALID_REQUEST')
|
|
456
|
+
}
|
|
457
|
+
const sub = { ...cleanExtraBody[cfgKey] }
|
|
458
|
+
for (const key of EXTRA_BODY_STRIPPED_KEYS) delete sub[key]
|
|
459
|
+
if (stripExplicitCache) {
|
|
460
|
+
delete sub.cachedContent
|
|
461
|
+
delete sub.cached_content
|
|
462
|
+
}
|
|
463
|
+
cleanExtraBody[cfgKey] = sub
|
|
464
|
+
}
|
|
465
|
+
return cleanExtraBody
|
|
466
|
+
}
|
|
467
|
+
|
|
468
|
+
function assertOutboundMaxOutputTokens(body, cleanConfig, extraBody, ceiling) {
|
|
469
|
+
const locations = [
|
|
470
|
+
cleanConfig?.maxOutputTokens,
|
|
471
|
+
cleanConfig?.max_output_tokens,
|
|
472
|
+
body?.maxOutputTokens,
|
|
473
|
+
body?.max_output_tokens,
|
|
474
|
+
body?.generationConfig?.maxOutputTokens,
|
|
475
|
+
body?.generationConfig?.max_output_tokens,
|
|
476
|
+
extraBody?.maxOutputTokens,
|
|
477
|
+
extraBody?.max_output_tokens,
|
|
478
|
+
extraBody?.generationConfig?.maxOutputTokens,
|
|
479
|
+
extraBody?.generationConfig?.max_output_tokens,
|
|
480
|
+
extraBody?.generation_config?.maxOutputTokens,
|
|
481
|
+
extraBody?.generation_config?.max_output_tokens,
|
|
482
|
+
]
|
|
483
|
+
for (const val of locations) {
|
|
484
|
+
if (val !== undefined && (!Number.isSafeInteger(val) || val < 1 || val > ceiling)) {
|
|
485
|
+
throw new LlmError(`Gemini 4 payload maxOutputTokens must be an integer between 1 and ${ceiling}.`, 'INVALID_REQUEST')
|
|
486
|
+
}
|
|
487
|
+
}
|
|
488
|
+
}
|
|
489
|
+
|
|
490
|
+
export function assertGemini4MaxTokens(options, requestModel, longDecode = true) {
|
|
491
|
+
if (!options || options.maxTokens === undefined) return
|
|
492
|
+
const routeCeiling = routeCeilingFor(requestModel, longDecode)
|
|
377
493
|
if (
|
|
378
494
|
!Number.isSafeInteger(options.maxTokens) ||
|
|
379
495
|
options.maxTokens < 1 ||
|
|
@@ -392,7 +508,7 @@ export function gemini4StreamSimple(
|
|
|
392
508
|
requestModel,
|
|
393
509
|
context,
|
|
394
510
|
options = {},
|
|
395
|
-
defaultLevel =
|
|
511
|
+
defaultLevel = undefined,
|
|
396
512
|
upstreamModelId = requestModel.id,
|
|
397
513
|
longDecode = true,
|
|
398
514
|
recordDiagnostic,
|
|
@@ -401,8 +517,8 @@ export function gemini4StreamSimple(
|
|
|
401
517
|
structuredOutput,
|
|
402
518
|
) {
|
|
403
519
|
assertPreparedStructuredOutput(structuredOutput)
|
|
404
|
-
ensureGemini4ApiClientPatch()
|
|
405
|
-
const fallback = defaultLevel ?? (
|
|
520
|
+
if (!isGemini4ApiClientPatched()) ensureGemini4ApiClientPatch()
|
|
521
|
+
const fallback = defaultLevel ?? defaultReasoningForModel(requestModel?.id)
|
|
406
522
|
const modelId = requestModel?.id
|
|
407
523
|
const supportsXhigh = supportsXhighReasoning(modelId)
|
|
408
524
|
const { level: rawLevel } = validateExplicitReasoningFields(options, modelId, fallback)
|
|
@@ -417,7 +533,9 @@ export function gemini4StreamSimple(
|
|
|
417
533
|
}
|
|
418
534
|
const { reasoning, reasoningEffort: _re, thinking, thinkingBudgets, temperature, onPayload: prior, onProviderStreamEvent: priorEvent, ...rest } = options
|
|
419
535
|
assertGemini4MaxTokens(options, requestModel, longDecode)
|
|
420
|
-
const
|
|
536
|
+
const routeCeiling = routeCeilingFor(requestModel, longDecode)
|
|
537
|
+
const outboundCeiling = longDecode === false ? Math.min(routeCeiling, MAX_SINGLE_CALL_TOKENS) : routeCeiling
|
|
538
|
+
const requestedMaxTokens = options.maxTokens === undefined ? requestModel.maxTokens : options.maxTokens
|
|
421
539
|
if (requestedMaxTokens !== undefined && (!Number.isSafeInteger(requestedMaxTokens) || requestedMaxTokens < 1 || requestedMaxTokens > MAX_LONG_DECODE_TOKENS)) {
|
|
422
540
|
throw new LlmError('Invalid Gemini 4 maxTokens budget.', 'INVALID_REQUEST')
|
|
423
541
|
}
|
|
@@ -472,23 +590,21 @@ export function gemini4StreamSimple(
|
|
|
472
590
|
? cleanConfig.httpOptions
|
|
473
591
|
: {}
|
|
474
592
|
const sanitizedHttpOptions = { ...prevHttpOptions }
|
|
475
|
-
if (
|
|
476
|
-
supportsXhigh
|
|
477
|
-
prevHttpOptions.extraBody &&
|
|
478
|
-
typeof prevHttpOptions.extraBody === 'object' &&
|
|
479
|
-
!Array.isArray(prevHttpOptions.extraBody)
|
|
480
|
-
) {
|
|
481
|
-
const cleanExtraBody = { ...prevHttpOptions.extraBody }
|
|
482
|
-
delete cleanExtraBody.cachedContent
|
|
483
|
-
delete cleanExtraBody.cached_content
|
|
484
|
-
sanitizedHttpOptions.extraBody = cleanExtraBody
|
|
593
|
+
if (Object.hasOwn(prevHttpOptions, 'extraBody') && prevHttpOptions.extraBody !== undefined) {
|
|
594
|
+
sanitizedHttpOptions.extraBody = sanitizeGemini4ExtraBody(prevHttpOptions.extraBody, supportsXhigh)
|
|
485
595
|
}
|
|
596
|
+
assertOutboundMaxOutputTokens(body, cleanConfig, sanitizedHttpOptions.extraBody, outboundCeiling)
|
|
597
|
+
const resolvedPayloadMax = cleanConfig.maxOutputTokens !== undefined
|
|
598
|
+
? cleanConfig.maxOutputTokens
|
|
599
|
+
: (cleanConfig.max_output_tokens !== undefined ? cleanConfig.max_output_tokens : (effectiveMaxTokens ?? outboundCeiling))
|
|
600
|
+
delete cleanConfig.max_output_tokens
|
|
486
601
|
const toolMode = shouldFallbackToAutoToolMode(retryKey) ? 'AUTO' : 'VALIDATED'
|
|
487
602
|
return {
|
|
488
603
|
...body,
|
|
489
604
|
model: upstreamModelId,
|
|
490
605
|
config: {
|
|
491
606
|
...cleanConfig,
|
|
607
|
+
maxOutputTokens: resolvedPayloadMax,
|
|
492
608
|
...(cleanConfig.tools?.some(tool => tool.functionDeclarations?.length) ? {
|
|
493
609
|
toolConfig: {
|
|
494
610
|
...cleanConfig.toolConfig,
|
|
@@ -516,16 +632,25 @@ export function gemini4StreamSimple(
|
|
|
516
632
|
)
|
|
517
633
|
}
|
|
518
634
|
|
|
635
|
+
let activePiAiPatchGeneration = null
|
|
636
|
+
|
|
519
637
|
export function installGemini4PiAiPatch(recordDiagnostic, configInput = {}, responseHub) {
|
|
520
|
-
const unpatchApiClient = ensureGemini4ApiClientPatch()
|
|
638
|
+
const unpatchApiClient = ensureGemini4ApiClientPatch({ lease: true })
|
|
521
639
|
const proto = PiAiAdapter?.prototype
|
|
522
640
|
if (!proto || typeof proto.current !== 'function') return unpatchApiClient
|
|
641
|
+
const owner = { recordDiagnostic, configInput, responseHub }
|
|
642
|
+
if (activePiAiPatchGeneration && activePiAiPatchGeneration.active) {
|
|
643
|
+
const existing = activePiAiPatchGeneration
|
|
644
|
+
existing.owners.push(owner)
|
|
645
|
+
return () => existing.removeOwner(owner, unpatchApiClient)
|
|
646
|
+
}
|
|
523
647
|
const origCurrent = proto.current
|
|
524
648
|
const origPrepareCall = typeof proto.prepareCall === 'function' ? proto.prepareCall : null
|
|
525
649
|
const origProtoStream = typeof proto.stream === 'function' ? proto.stream : null
|
|
526
650
|
const patchedProviders = new Map()
|
|
527
651
|
const patchedModels = new Map()
|
|
528
|
-
|
|
652
|
+
const owners = [owner]
|
|
653
|
+
const currentOwner = () => owners.at(-1)
|
|
529
654
|
const ensureGemini4Capabilities = piProvider => {
|
|
530
655
|
if (typeof piProvider?.getModels !== 'function') return
|
|
531
656
|
try {
|
|
@@ -565,20 +690,21 @@ export function installGemini4PiAiPatch(recordDiagnostic, configInput = {}, resp
|
|
|
565
690
|
const origStream = piProvider.stream
|
|
566
691
|
const origStreamSimple = piProvider.streamSimple
|
|
567
692
|
const dispatchGemini4 = (requestModel, context, options = {}) => {
|
|
568
|
-
const
|
|
693
|
+
const activeOwner = currentOwner()
|
|
694
|
+
const cfg = resolveConfigValues(activeOwner?.configInput)
|
|
569
695
|
return gemini4StreamSimple(
|
|
570
696
|
(m, c, o) => origStream.call(piProvider, m, c, o), requestModel, context, options,
|
|
571
|
-
defaultReasoning, requestModel.id, cfg.longDecode, recordDiagnostic,
|
|
697
|
+
defaultReasoning, requestModel.id, cfg.longDecode, activeOwner?.recordDiagnostic,
|
|
572
698
|
resolveServicePolicy(cfg, requestModel.api, 'generate-content'),
|
|
573
|
-
{ responseHub, retainRawResponses: cfg.retainRawResponses },
|
|
699
|
+
{ responseHub: activeOwner?.responseHub, retainRawResponses: cfg.retainRawResponses },
|
|
574
700
|
)
|
|
575
701
|
}
|
|
576
702
|
function patchedStreamSimple(requestModel, context, options = {}) {
|
|
577
|
-
if (active && isGemini4Model(requestModel)) return dispatchGemini4(requestModel, context, options)
|
|
703
|
+
if (gen.active && isGemini4Model(requestModel)) return dispatchGemini4(requestModel, context, options)
|
|
578
704
|
return origStreamSimple.call(this, requestModel, context, options)
|
|
579
705
|
}
|
|
580
706
|
function patchedStream(requestModel, context, options = {}) {
|
|
581
|
-
if (active && isGemini4Model(requestModel)) return dispatchGemini4(requestModel, context, mapStreamThinkingOption(options))
|
|
707
|
+
if (gen.active && isGemini4Model(requestModel)) return dispatchGemini4(requestModel, context, mapStreamThinkingOption(options))
|
|
582
708
|
return origStream.call(this, requestModel, context, options)
|
|
583
709
|
}
|
|
584
710
|
patchedProviders.set(piProvider, { origStream, patchedStream, origStreamSimple, patchedStreamSimple })
|
|
@@ -586,14 +712,14 @@ export function installGemini4PiAiPatch(recordDiagnostic, configInput = {}, resp
|
|
|
586
712
|
piProvider.streamSimple = patchedStreamSimple
|
|
587
713
|
}
|
|
588
714
|
const isNativeGemini4Target = (instance, provider, model) =>
|
|
589
|
-
active &&
|
|
715
|
+
gen.active &&
|
|
590
716
|
!(instance instanceof ArgonAdapter) &&
|
|
591
717
|
(provider === 'google' || provider === NATIVE_PROVIDER) &&
|
|
592
718
|
typeof model === 'string' &&
|
|
593
719
|
/^(?:models\/)?gemini-4\b/i.test(model)
|
|
594
720
|
function patchedCurrent() {
|
|
595
721
|
const snapshot = origCurrent.call(this)
|
|
596
|
-
if (active && snapshot?.profiles instanceof Map) {
|
|
722
|
+
if (gen.active && snapshot?.profiles instanceof Map) {
|
|
597
723
|
for (const profile of snapshot.profiles.values()) {
|
|
598
724
|
if (profile?.piProvider) wrapProvider(profile.piProvider, profile.reasoning)
|
|
599
725
|
}
|
|
@@ -608,9 +734,9 @@ export function installGemini4PiAiPatch(recordDiagnostic, configInput = {}, resp
|
|
|
608
734
|
return {
|
|
609
735
|
...prepared,
|
|
610
736
|
stream: options => {
|
|
611
|
-
if (!active) return origPreparedStream(options)
|
|
737
|
+
if (!gen.active) return origPreparedStream(options)
|
|
612
738
|
const pinned = preparePinnedStreamOptions(options, provider, model)
|
|
613
|
-
if (resolvedModel) assertGemini4MaxTokens(pinned, resolvedModel, resolveConfigValues(configInput).longDecode)
|
|
739
|
+
if (resolvedModel) assertGemini4MaxTokens(pinned, resolvedModel, resolveConfigValues(currentOwner()?.configInput).longDecode)
|
|
614
740
|
return origPreparedStream(generateContentHistory(pinned, model))
|
|
615
741
|
},
|
|
616
742
|
}
|
|
@@ -619,44 +745,56 @@ export function installGemini4PiAiPatch(recordDiagnostic, configInput = {}, resp
|
|
|
619
745
|
if (options && typeof options === 'object' && !Array.isArray(options) && isNativeGemini4Target(this, options.provider, options.model)) {
|
|
620
746
|
const resolvedModel = this.current?.()?.models?.getModel?.(options.provider, options.model)
|
|
621
747
|
const pinned = preparePinnedStreamOptions(options, options.provider, options.model)
|
|
622
|
-
if (resolvedModel) assertGemini4MaxTokens(pinned, resolvedModel, resolveConfigValues(configInput).longDecode)
|
|
748
|
+
if (resolvedModel) assertGemini4MaxTokens(pinned, resolvedModel, resolveConfigValues(currentOwner()?.configInput).longDecode)
|
|
623
749
|
const normalized = generateContentHistory(pinned, options.model)
|
|
624
750
|
yield* origProtoStream.call(this, normalized)
|
|
625
751
|
return
|
|
626
752
|
}
|
|
627
753
|
yield* origProtoStream.call(this, options)
|
|
628
754
|
}
|
|
755
|
+
const gen = {
|
|
756
|
+
active: true,
|
|
757
|
+
owners,
|
|
758
|
+
removeOwner(targetOwner, ownerApiUnpatch) {
|
|
759
|
+
const idx = owners.indexOf(targetOwner)
|
|
760
|
+
if (idx === -1) return
|
|
761
|
+
owners.splice(idx, 1)
|
|
762
|
+
ownerApiUnpatch()
|
|
763
|
+
if (owners.length > 0 || !gen.active) return
|
|
764
|
+
gen.active = false
|
|
765
|
+
if (activePiAiPatchGeneration === gen) activePiAiPatchGeneration = null
|
|
766
|
+
if (proto.current === patchedCurrent) proto.current = origCurrent
|
|
767
|
+
if (origPrepareCall && proto.prepareCall === patchedPrepareCall) proto.prepareCall = origPrepareCall
|
|
768
|
+
if (origProtoStream && proto.stream === patchedProtoStream) proto.stream = origProtoStream
|
|
769
|
+
for (const [piProvider, { origStream, patchedStream, origStreamSimple, patchedStreamSimple }] of patchedProviders) {
|
|
770
|
+
if (piProvider.stream === patchedStream) piProvider.stream = origStream
|
|
771
|
+
if (piProvider.streamSimple === patchedStreamSimple) piProvider.streamSimple = origStreamSimple
|
|
772
|
+
}
|
|
773
|
+
patchedProviders.clear()
|
|
774
|
+
for (const [m, saved] of patchedModels) {
|
|
775
|
+
try {
|
|
776
|
+
if (saved.hadReasoning) m.reasoning = saved.reasoning
|
|
777
|
+
else delete m.reasoning
|
|
778
|
+
if (saved.hadMap) m.thinkingLevelMap = saved.thinkingLevelMap
|
|
779
|
+
else delete m.thinkingLevelMap
|
|
780
|
+
} catch {}
|
|
781
|
+
}
|
|
782
|
+
patchedModels.clear()
|
|
783
|
+
},
|
|
784
|
+
}
|
|
785
|
+
activePiAiPatchGeneration = gen
|
|
629
786
|
proto.current = patchedCurrent
|
|
630
787
|
if (origPrepareCall) proto.prepareCall = patchedPrepareCall
|
|
631
788
|
if (origProtoStream) proto.stream = patchedProtoStream
|
|
632
|
-
return () =>
|
|
633
|
-
if (!active) return
|
|
634
|
-
active = false
|
|
635
|
-
unpatchApiClient()
|
|
636
|
-
if (proto.current === patchedCurrent) proto.current = origCurrent
|
|
637
|
-
if (origPrepareCall && proto.prepareCall === patchedPrepareCall) proto.prepareCall = origPrepareCall
|
|
638
|
-
if (origProtoStream && proto.stream === patchedProtoStream) proto.stream = origProtoStream
|
|
639
|
-
for (const [piProvider, { origStream, patchedStream, origStreamSimple, patchedStreamSimple }] of patchedProviders) {
|
|
640
|
-
if (piProvider.stream === patchedStream) piProvider.stream = origStream
|
|
641
|
-
if (piProvider.streamSimple === patchedStreamSimple) piProvider.streamSimple = origStreamSimple
|
|
642
|
-
}
|
|
643
|
-
patchedProviders.clear()
|
|
644
|
-
for (const [m, saved] of patchedModels) {
|
|
645
|
-
try {
|
|
646
|
-
if (saved.hadReasoning) m.reasoning = saved.reasoning
|
|
647
|
-
else delete m.reasoning
|
|
648
|
-
if (saved.hadMap) m.thinkingLevelMap = saved.thinkingLevelMap
|
|
649
|
-
else delete m.thinkingLevelMap
|
|
650
|
-
} catch {}
|
|
651
|
-
}
|
|
652
|
-
patchedModels.clear()
|
|
653
|
-
}
|
|
789
|
+
return () => gen.removeOwner(owner, unpatchApiClient)
|
|
654
790
|
}
|
|
655
791
|
|
|
656
792
|
export function resolveConfigValues(raw = {}) {
|
|
657
793
|
const source = typeof raw === 'function' ? raw() : raw
|
|
658
794
|
const showInModelPicker = readVal(source?.showInModelPicker) ?? true
|
|
659
|
-
const
|
|
795
|
+
const rawReasoning = readVal(source?.reasoning)
|
|
796
|
+
const hasExplicitReasoning = rawReasoning !== undefined
|
|
797
|
+
const reasoning = rawReasoning ?? 'medium'
|
|
660
798
|
const longDecode = readVal(source?.longDecode) ?? true
|
|
661
799
|
const contextWindow = readVal(source?.contextWindow) ?? 1048576
|
|
662
800
|
const rawMaxTokens = readVal(source?.maxTokens) ?? MAX_SINGLE_CALL_TOKENS
|
|
@@ -685,11 +823,12 @@ export function resolveConfigValues(raw = {}) {
|
|
|
685
823
|
const safeCompactionCap = contextWindow > COMPACTION_HEADROOM_FLOOR ? contextWindow - COMPACTION_HEADROOM_FLOOR : contextWindow
|
|
686
824
|
const maxTokens = Math.max(1, Math.min(capByMode, safeCompactionCap))
|
|
687
825
|
const explicitMaxTokensCap = hasExplicitMaxTokens
|
|
688
|
-
? Math.max(1, Math.min(rawMaxTokens,
|
|
689
|
-
: Math.max(1, Math.min(MAX_LONG_DECODE_TOKENS,
|
|
826
|
+
? Math.max(1, Math.min(rawMaxTokens, contextWindow, MAX_LONG_DECODE_TOKENS))
|
|
827
|
+
: Math.max(1, Math.min(MAX_LONG_DECODE_TOKENS, contextWindow))
|
|
690
828
|
return {
|
|
691
829
|
showInModelPicker: Boolean(showInModelPicker),
|
|
692
830
|
reasoning,
|
|
831
|
+
hasExplicitReasoning,
|
|
693
832
|
longDecode: enabledLongDecode,
|
|
694
833
|
contextWindow,
|
|
695
834
|
maxTokens,
|
|
@@ -708,7 +847,7 @@ export function resolveConfigValues(raw = {}) {
|
|
|
708
847
|
}
|
|
709
848
|
|
|
710
849
|
/** Serve the official Vertex AI and Gemini API models in one plugin group. */
|
|
711
|
-
export function argonProvider(nativeVertex, models, defaultLevel =
|
|
850
|
+
export function argonProvider(nativeVertex, models, defaultLevel = undefined, nativeGoogle = googleProvider(), longDecode = true, recordDiagnostic, serviceConfig = {}, responseHub, structuredOutput) {
|
|
712
851
|
const modelMap = new Map((Array.isArray(models) ? models : [models]).map(m => [m.id, m]))
|
|
713
852
|
return {
|
|
714
853
|
id: PROVIDER,
|
|
@@ -717,9 +856,23 @@ export function argonProvider(nativeVertex, models, defaultLevel = 'medium', nat
|
|
|
717
856
|
getModels: () => [...modelMap.values()],
|
|
718
857
|
streamSimple(requestModel, context, options = {}) {
|
|
719
858
|
const configured = modelMap.get(requestModel?.id)
|
|
720
|
-
if (!configured || requestModel
|
|
859
|
+
if (!configured || requestModel?.provider !== PROVIDER) {
|
|
721
860
|
throw new LlmError('Gemini 4 Adapter only serves configured Gemini 4 routes.', 'UNSUPPORTED_OPTION')
|
|
722
861
|
}
|
|
862
|
+
if (requestModel.api !== undefined && requestModel.api !== configured.api) {
|
|
863
|
+
throw new LlmError('Gemini 4 Adapter only serves google-vertex or google-generative-ai.', 'UNSUPPORTED_OPTION')
|
|
864
|
+
}
|
|
865
|
+
const effectiveModel = {
|
|
866
|
+
...configured,
|
|
867
|
+
...requestModel,
|
|
868
|
+
id: configured.id,
|
|
869
|
+
provider: PROVIDER,
|
|
870
|
+
api: configured.api,
|
|
871
|
+
maxTokens: configured.maxTokens,
|
|
872
|
+
thinkingLevelMap: configured.thinkingLevelMap,
|
|
873
|
+
[MAX_TOKENS_CEILING]: configured[MAX_TOKENS_CEILING] ?? (Number.isSafeInteger(configured.maxTokens) ? configured.maxTokens : undefined),
|
|
874
|
+
}
|
|
875
|
+
const requestedMaxTokens = options.maxTokens === undefined ? configured.maxTokens : options.maxTokens
|
|
723
876
|
const { env: rawEnv, apiKey: vertexApiKey, ...restOptions } = options
|
|
724
877
|
const cleanEnv = rawEnv ? { ...rawEnv } : undefined
|
|
725
878
|
if (cleanEnv) {
|
|
@@ -731,9 +884,9 @@ export function argonProvider(nativeVertex, models, defaultLevel = 'medium', nat
|
|
|
731
884
|
const policy = resolveServicePolicy(serviceConfig, 'google-generative-ai', 'generate-content')
|
|
732
885
|
return gemini4StreamSimple(
|
|
733
886
|
(m, c, o) => nativeGoogle.stream(m, c, o),
|
|
734
|
-
|
|
887
|
+
effectiveModel,
|
|
735
888
|
context,
|
|
736
|
-
{ ...restOptions, ...(cleanEnv ? { env: cleanEnv } : {}), ...(apiKey ? { apiKey } : {}), maxTokens:
|
|
889
|
+
{ ...restOptions, ...(cleanEnv ? { env: cleanEnv } : {}), ...(apiKey ? { apiKey } : {}), maxTokens: requestedMaxTokens },
|
|
737
890
|
defaultLevel,
|
|
738
891
|
officialUpstreamModel(configured.id),
|
|
739
892
|
longDecode,
|
|
@@ -742,14 +895,14 @@ export function argonProvider(nativeVertex, models, defaultLevel = 'medium', nat
|
|
|
742
895
|
{ responseHub, retainRawResponses: serviceConfig.retainRawResponses }, structuredOutput,
|
|
743
896
|
)
|
|
744
897
|
}
|
|
745
|
-
if (
|
|
898
|
+
if (effectiveModel.api !== 'google-vertex') {
|
|
746
899
|
throw new LlmError('Gemini 4 Adapter only serves google-vertex or google-generative-ai.', 'UNSUPPORTED_OPTION')
|
|
747
900
|
}
|
|
748
901
|
return gemini4StreamSimple(
|
|
749
902
|
(m, c, o) => nativeVertex.stream(m, c, o),
|
|
750
|
-
|
|
903
|
+
effectiveModel,
|
|
751
904
|
context,
|
|
752
|
-
{ ...restOptions, ...(cleanEnv ? { env: cleanEnv } : {}), ...(vertexApiKey ? { apiKey: vertexApiKey } : {}), maxTokens:
|
|
905
|
+
{ ...restOptions, ...(cleanEnv ? { env: cleanEnv } : {}), ...(vertexApiKey ? { apiKey: vertexApiKey } : {}), maxTokens: requestedMaxTokens },
|
|
753
906
|
defaultLevel,
|
|
754
907
|
officialUpstreamModel(configured.id),
|
|
755
908
|
longDecode,
|
|
@@ -789,15 +942,19 @@ export class ArgonAdapter extends LlmAdapter {
|
|
|
789
942
|
const protocol = googleApi ? cfg?.googleProtocol : cfg?.vertexProtocol
|
|
790
943
|
if (provider === PROVIDER && cfg) resolveServicePolicy(cfg, googleApi ? 'google-generative-ai' : 'google-vertex', protocol)
|
|
791
944
|
const prepared = await this.inner.prepareCall(provider, model, signal)
|
|
945
|
+
const resolvedModel = provider === PROVIDER
|
|
946
|
+
? (this.inner.current?.()?.models?.getModel?.(provider, model) ?? (cfg ? { provider, id: model, [MAX_TOKENS_CEILING]: cfg.explicitMaxTokensCap } : undefined))
|
|
947
|
+
: undefined
|
|
792
948
|
if (provider === PROVIDER && protocol === 'interactions' && this.interactionHandler) {
|
|
793
949
|
return {
|
|
794
950
|
model: prepared.model,
|
|
795
|
-
stream: options =>
|
|
951
|
+
stream: options => {
|
|
952
|
+
const pinned = pinPreparedOptions(options, provider, model)
|
|
953
|
+
assertGemini4MaxTokens(pinned, resolvedModel, cfg?.longDecode)
|
|
954
|
+
return this.interactionHandler(syncGemini4ReasoningOptions(pinned, model), cfg)
|
|
955
|
+
},
|
|
796
956
|
}
|
|
797
957
|
}
|
|
798
|
-
const resolvedModel = provider === PROVIDER
|
|
799
|
-
? (this.inner.current?.()?.models?.getModel?.(provider, model) ?? (cfg ? { provider, id: model, [MAX_TOKENS_CEILING]: cfg.explicitMaxTokensCap } : undefined))
|
|
800
|
-
: undefined
|
|
801
958
|
return {
|
|
802
959
|
...prepared,
|
|
803
960
|
stream: options => {
|
|
@@ -854,6 +1011,7 @@ export function createArgonAdapter(ctx, configInput, nativeVertex = googleVertex
|
|
|
854
1011
|
const detected = detectPiAiArgonRoutes(ctx, cfg.routes)
|
|
855
1012
|
const key = JSON.stringify({
|
|
856
1013
|
r: cfg.reasoning,
|
|
1014
|
+
explicitR: cfg.hasExplicitReasoning,
|
|
857
1015
|
ld: cfg.longDecode,
|
|
858
1016
|
cw: cfg.contextWindow,
|
|
859
1017
|
mt: cfg.maxTokens,
|
|
@@ -1033,13 +1191,14 @@ export function createArgonAdapter(ctx, configInput, nativeVertex = googleVertex
|
|
|
1033
1191
|
modelDescriptor[MAX_TOKENS_CEILING] = cfg.explicitMaxTokensCap
|
|
1034
1192
|
}
|
|
1035
1193
|
const configuredMaxTokens = new Map(models.map(m => [m.id, cfg.maxTokens]))
|
|
1036
|
-
const
|
|
1194
|
+
const configuredReasoning = cfg.hasExplicitReasoning ? cfg.reasoning : undefined
|
|
1195
|
+
const provider = argonProvider({ ...nativeVertex, auth }, models, configuredReasoning, nativeGoogle, cfg.longDecode, recordDiagnostic, cfg, responseHub, structuredOutput)
|
|
1037
1196
|
cachedKey = key
|
|
1038
1197
|
cachedProfiles = new Map([[PROVIDER, {
|
|
1039
1198
|
provider: PROVIDER,
|
|
1040
1199
|
displayName: 'Gemini 4 Adapter',
|
|
1041
1200
|
piProvider: provider,
|
|
1042
|
-
reasoning:
|
|
1201
|
+
reasoning: configuredReasoning,
|
|
1043
1202
|
streamIdleTimeoutMs: cfg.longDecode ? STREAM_READ_TIMEOUT_MS + 60000 : STREAM_READ_TIMEOUT_MS,
|
|
1044
1203
|
maxRequestImageBytes: 20 * 1024 * 1024,
|
|
1045
1204
|
requestImagePixelBudget: 2048 * 2048,
|
package/google-signatures.js
CHANGED
|
@@ -115,7 +115,7 @@ export function createGoogleSignatureBridge(context, model) {
|
|
|
115
115
|
const historyDigest = history.digest('hex')
|
|
116
116
|
const content = [], pending = [], standalone = new Map(), usedToolIds = new Set()
|
|
117
117
|
const partial = { role: 'assistant', api: model.api, provider: model.provider, model: model.id, content }
|
|
118
|
-
let current, seen = false, bytes = 0
|
|
118
|
+
let current, currentSignedInThisChunk = false, seen = false, bytes = 0
|
|
119
119
|
const emit = event => {
|
|
120
120
|
if (pending.length >= 32768) throw failure('Google response exceeded the bounded pending event count.')
|
|
121
121
|
pending.push({ ...event, partial })
|
|
@@ -128,8 +128,15 @@ export function createGoogleSignatureBridge(context, model) {
|
|
|
128
128
|
const close = () => {
|
|
129
129
|
if (!current) return
|
|
130
130
|
const index = content.length - 1
|
|
131
|
-
|
|
131
|
+
const sig = current.type === 'text' ? current.textSignature : current.thinkingSignature
|
|
132
|
+
emit({
|
|
133
|
+
type: current.type === 'text' ? 'text_end' : 'thinking_end',
|
|
134
|
+
contentIndex: index,
|
|
135
|
+
content: current.type === 'text' ? current.text : current.thinking,
|
|
136
|
+
...(sig ? { contentSignature: sig } : {}),
|
|
137
|
+
})
|
|
132
138
|
current = undefined
|
|
139
|
+
currentSignedInThisChunk = false
|
|
133
140
|
}
|
|
134
141
|
const finishMessage = message => {
|
|
135
142
|
close()
|
|
@@ -153,6 +160,7 @@ export function createGoogleSignatureBridge(context, model) {
|
|
|
153
160
|
},
|
|
154
161
|
observe(chunk) {
|
|
155
162
|
seen = true
|
|
163
|
+
currentSignedInThisChunk = false
|
|
156
164
|
for (const part of chunk.candidates?.[0]?.content?.parts ?? []) {
|
|
157
165
|
bytes += Buffer.byteLength(JSON.stringify(part))
|
|
158
166
|
if (bytes > 64 * 1024 * 1024) throw failure('Google response exceeded the bounded signature replay buffer.')
|
|
@@ -171,14 +179,22 @@ export function createGoogleSignatureBridge(context, model) {
|
|
|
171
179
|
}
|
|
172
180
|
if (part.text !== undefined) {
|
|
173
181
|
const type = part.thought === true ? 'thinking' : 'text'
|
|
174
|
-
|
|
182
|
+
const sigKey = type === 'text' ? 'textSignature' : 'thinkingSignature'
|
|
183
|
+
const splitSigned = type === 'text'
|
|
184
|
+
? (Boolean(current?.textSignature) || (Boolean(sig) && part.text === ''))
|
|
185
|
+
: ((Boolean(sig) && (Boolean(current?.thinkingSignature) || part.text === '')) ||
|
|
186
|
+
(Boolean(current?.thinkingSignature) && (currentSignedInThisChunk || current.thinking === '')))
|
|
187
|
+
if (!current || current.type !== type || splitSigned) {
|
|
175
188
|
close(); current = type === 'text' ? { type, text: '' } : { type, thinking: '' }
|
|
176
189
|
const index = start(current)
|
|
177
190
|
emit({ type: type === 'text' ? 'text_start' : 'thinking_start', contentIndex: index })
|
|
178
191
|
}
|
|
179
192
|
const key = type === 'text' ? 'text' : 'thinking'
|
|
180
193
|
current[key] += part.text
|
|
181
|
-
if (sig)
|
|
194
|
+
if (sig) {
|
|
195
|
+
current[sigKey] = sig
|
|
196
|
+
if (type === 'thinking') currentSignedInThisChunk = true
|
|
197
|
+
}
|
|
182
198
|
emit({ type: type === 'text' ? 'text_delta' : 'thinking_delta', contentIndex: content.length - 1, delta: part.text })
|
|
183
199
|
}
|
|
184
200
|
if (part.functionCall) {
|
package/index.js
CHANGED
|
@@ -119,11 +119,17 @@ export function apply(ctx, config) {
|
|
|
119
119
|
const recordDiagnostic = record => hub.record(record)
|
|
120
120
|
const adapter = createArgonAdapter(ctx, () => config, undefined, undefined, recordDiagnostic, taskHub, responseHub)
|
|
121
121
|
const unpatchPiAi = installGemini4PiAiPatch(recordDiagnostic, () => config, responseHub)
|
|
122
|
-
|
|
123
|
-
|
|
122
|
+
let registration
|
|
123
|
+
try {
|
|
124
|
+
registration = ctx.llm.registerAdapter([PROVIDER], adapter)
|
|
125
|
+
ctx.effect(() => () => {
|
|
126
|
+
unpatchPiAi()
|
|
127
|
+
registration?.()
|
|
128
|
+
})
|
|
129
|
+
} catch (error) {
|
|
124
130
|
unpatchPiAi()
|
|
125
|
-
|
|
126
|
-
}
|
|
131
|
+
throw error
|
|
132
|
+
}
|
|
127
133
|
if (typeof ctx.on === 'function') {
|
|
128
134
|
ctx.on('llm/stream', (options, next) => associations.stream(options, next))
|
|
129
135
|
ctx.on('agent/assistant-stream', payload => associations.frame(payload))
|
package/interaction-adapter.js
CHANGED
|
@@ -4,15 +4,18 @@ 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
|
-
import { resolveGemini4ReasoningLevel } from './interactions-input.js'
|
|
7
|
+
import { resolveGemini4ReasoningLevel, defaultReasoningForModel } from './interactions-input.js'
|
|
8
8
|
// 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。
|
|
9
9
|
import { isGoogleApiModel, officialUpstreamModel } from './adapter.js'
|
|
10
10
|
|
|
11
11
|
const terminalStates = new Set(['completed', 'requires_action', 'incomplete', 'failed', 'cancelled', 'budget_exceeded'])
|
|
12
12
|
export function assertInteractionOptions(options, cfg, route) {
|
|
13
|
-
const
|
|
14
|
-
|
|
15
|
-
|
|
13
|
+
const requestedMax = options.maxTokens === undefined ? cfg.maxTokens : options.maxTokens
|
|
14
|
+
const maxCeiling = cfg.explicitMaxTokensCap ?? cfg.maxTokens
|
|
15
|
+
if (!Number.isSafeInteger(requestedMax) || requestedMax <= 0 || requestedMax > maxCeiling) throw new Error('Interactions output budget must be a positive integer within the configured effective cap.')
|
|
16
|
+
const max = cfg.longDecode === false ? Math.min(requestedMax, 65536) : requestedMax
|
|
17
|
+
const defaultReasoning = cfg?.hasExplicitReasoning === false ? defaultReasoningForModel(options.model) : cfg.reasoning
|
|
18
|
+
const resolvedReasoning = resolveGemini4ReasoningLevel(options, options.model, defaultReasoning)
|
|
16
19
|
if (!resolvedReasoning.ok) {
|
|
17
20
|
if (resolvedReasoning.errorType === 'conflict') {
|
|
18
21
|
throw new Error('Conflicting reasoning and reasoningEffort options in Interactions request.')
|
|
@@ -162,7 +165,7 @@ export function createInteractionsHandler({ ctx, GoogleGenAI, resolveSecret, get
|
|
|
162
165
|
return block
|
|
163
166
|
}) }))
|
|
164
167
|
const { streamInteractions } = await import('./interactions.js')
|
|
165
|
-
for await (const chunk of streamInteractions({ ...options, messages, signal }, { route, upstreamModel, ...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 } })) {
|
|
168
|
+
for await (const chunk of streamInteractions({ ...options, maxTokens: controls.maxTokens, messages, signal }, { route, upstreamModel, ...controls, longDecode: cfg.longDecode, 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 } })) {
|
|
166
169
|
if (chunk.type === 'usage') {
|
|
167
170
|
recordUsage()
|
|
168
171
|
// Only an observed first-hop input watermark can be normalized for the
|
package/interactions-input.js
CHANGED
|
@@ -16,8 +16,13 @@ export function resolveOfficialGemini4Model(modelId) {
|
|
|
16
16
|
supportsXhigh: family === 'hydrogen' || family === 'neon',
|
|
17
17
|
}
|
|
18
18
|
}
|
|
19
|
+
export function defaultReasoningForModel(modelId) {
|
|
20
|
+
const official = resolveOfficialGemini4Model(modelId)
|
|
21
|
+
if (official) return official.supportsXhigh ? 'high' : 'medium'
|
|
22
|
+
return /cyber-permissive/i.test(String(modelId ?? '')) ? 'high' : 'medium'
|
|
23
|
+
}
|
|
19
24
|
/** 统一校验 thinking/reasoning 双字段,显式非法或双字段互相冲突时当场失败,避免静默回退默认值。 */
|
|
20
|
-
export function resolveGemini4ReasoningLevel(options, modelId, fallback =
|
|
25
|
+
export function resolveGemini4ReasoningLevel(options, modelId, fallback = defaultReasoningForModel(modelId)) {
|
|
21
26
|
const supportsXhigh = Boolean(resolveOfficialGemini4Model(modelId)?.supportsXhigh)
|
|
22
27
|
const allowed = supportsXhigh ? ['low', 'medium', 'high', 'xhigh'] : ['low', 'medium', 'high']
|
|
23
28
|
const validInputs = new Set([...allowed, 'max'])
|
|
@@ -123,7 +128,9 @@ function findUnclaimedToolResultIndex(messages, startIndex, toolCallId, claimedT
|
|
|
123
128
|
// Completed foreign-protocol tool rounds become a textual transcript, never
|
|
124
129
|
// forged function calls or fake thought signatures.
|
|
125
130
|
export async function buildInteractionRequest(options, settings = {}) {
|
|
126
|
-
const
|
|
131
|
+
const rawMax = options.maxTokens !== undefined
|
|
132
|
+
? options.maxTokens
|
|
133
|
+
: (settings.maxTokens !== undefined ? settings.maxTokens : 65536)
|
|
127
134
|
const hasExplicitUpstream = !isOmittedModel(settings.upstreamModel)
|
|
128
135
|
const hasExplicitOption = !isOmittedModel(options.model)
|
|
129
136
|
const resolvedUpstream = hasExplicitUpstream ? resolveOfficialGemini4Model(settings.upstreamModel) : null
|
|
@@ -138,9 +145,10 @@ export async function buildInteractionRequest(options, settings = {}) {
|
|
|
138
145
|
throw new Error('Conflicting Gemini 4 models in Interactions request.')
|
|
139
146
|
}
|
|
140
147
|
const upstreamModel = resolvedUpstream?.upstreamModel ?? resolvedOption?.upstreamModel ?? 'gemini-4-argon'
|
|
141
|
-
const resolvedReasoning = resolveGemini4ReasoningLevel(options, upstreamModel, settings.reasoning ??
|
|
148
|
+
const resolvedReasoning = resolveGemini4ReasoningLevel(options, upstreamModel, settings.reasoning ?? defaultReasoningForModel(upstreamModel))
|
|
142
149
|
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.')
|
|
143
|
-
if (!Number.isSafeInteger(
|
|
150
|
+
if (!Number.isSafeInteger(rawMax) || rawMax<1 || rawMax>1048576) throw new Error('Invalid Interactions output token budget.')
|
|
151
|
+
const max = settings.longDecode === false ? Math.min(rawMax, 65536) : rawMax
|
|
144
152
|
if (!resolvedReasoning.ok) {
|
|
145
153
|
if (resolvedReasoning.errorType === 'conflict') {
|
|
146
154
|
throw new Error('Conflicting reasoning and reasoningEffort options in Interactions request.')
|
package/package.json
CHANGED
|
@@ -1,6 +1,6 @@
|
|
|
1
1
|
{
|
|
2
2
|
"name": "dsh-vertex-argon",
|
|
3
|
-
"version": "2.2.
|
|
3
|
+
"version": "2.2.4",
|
|
4
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": {
|