Skip to content

Commit 0a61e14

Browse files
authored
improvement(models): retire deep research, refresh model lifecycle, pricing, and reseller catalogs (#10255)
* improvement(models): remove the retired Gemini Deep Research path * improvement(models): refresh model lifecycle, pricing, and reseller catalogs * fix(models): mirror reseller capabilities and lifecycle, add missing long-context tiers * fix(models): keep retired models from claiming structured outputs on the catalog pages * fix(providers): bill cached prompt tokens at the cached rate for Chat Completions providers * fix(providers): type the Groq client mock in the cache billing test * fix(providers): expect per-call metering in settled Z.ai streams and keep meter types local * chore(audits): shrink baselines for the removed deep research code
1 parent 9743e49 commit 0a61e14

49 files changed

Lines changed: 1378 additions & 2625 deletions

File tree

Some content is hidden

Large Commits have some content hidden by default. Use the searchbox below for content that may be hidden.

‎apps/docs/content/docs/agents/skills.mdx‎

Lines changed: 1 addition & 1 deletion
Original file line numberDiff line numberDiff line change
@@ -19,7 +19,7 @@ Selected skills appear as cards that you can open or remove. Editing depends on
1919

2020
At runtime, the Agent's system prompt includes an `<available_skills>` section with the selected names and descriptions. Sim adds a `load_skill` tool with a `skill_name` input. When the model calls it, the full instructions return as a tool response. Selecting a skill makes it available; the model decides whether to load it.
2121

22-
This uses standard tool calling across compatible models. Deep-research and evaluation models do not expose the ordinary Agent Tools and Skills controls.
22+
This uses standard tool calling across compatible models. Evaluation models do not expose the ordinary Agent Tools and Skills controls.
2323

2424
## Use a skill in Chat
2525

‎apps/docs/content/docs/workflows/blocks/agent.mdx‎

Lines changed: 6 additions & 6 deletions
Original file line numberDiff line numberDiff line change
@@ -188,17 +188,17 @@ Live tool-call chips stream for **OpenAI, Anthropic, Azure Anthropic, Google, Ve
188188

189189
| Provider | Streamed thinking | Models |
190190
|----------|-------------------|--------|
191-
| OpenAI | Summaries only — Requires OpenAI organization verification; falls back to no summaries. | `gpt-6.2-astra`, `gpt-6.2-sol`, `gpt-6-astra`, `gpt-6.1-sol`, `gpt-6.1-terra`, `gpt-6-sol`, `gpt-6-luna`, `gpt-5.6-sol`, `gpt-5.6-terra`, `gpt-5.6-luna`, `gpt-5.5-pro`, `gpt-5.5`, `gpt-5.4-pro`, `gpt-5.4`, `gpt-5.4-mini`, `gpt-5.4-nano`, `gpt-5.3-codex`, `gpt-5.2-pro`, `gpt-5.2`, `gpt-5.1`, `gpt-5-pro`, `gpt-5`, `gpt-5-mini`, `gpt-5-nano`, `o4-mini`, `o3`, `o3-mini`, `o1` |
191+
| OpenAI | Summaries only — Requires OpenAI organization verification; falls back to no summaries. | `gpt-6.2-astra`, `gpt-6.2-sol`, `gpt-6-astra`, `gpt-6.1-sol`, `gpt-6.1-terra`, `gpt-6-sol`, `gpt-6-luna`, `gpt-5.6-sol`, `gpt-5.6-terra`, `gpt-5.6-luna`, `gpt-5.5-pro`, `gpt-5.5`, `gpt-5.4-pro`, `gpt-5.4`, `gpt-5.4-mini`, `gpt-5.4-nano`, `gpt-5.3-codex`, `gpt-5.2-pro`, `gpt-5.2`, `gpt-5.1`, `gpt-5-pro`, `gpt-5`, `gpt-5-mini`, `gpt-5-nano`, `o3` |
192192
| Anthropic | Summaries only — These generations omit full thinking; Sim requests summarized thinking on streaming runs. | `claude-fable-5-2`, `claude-fable-5-1`, `claude-fable-5`, `claude-sonnet-5-5`, `claude-sonnet-5`, `claude-opus-5-5`, `claude-opus-5`, `claude-opus-4-8`, `claude-opus-4-7`, `claude-opus-4-6`, `claude-sonnet-4-6`, `claude-opus-4-5`, `claude-sonnet-4-5`, `claude-haiku-5-5`, `claude-haiku-4-5` |
193-
| Azure OpenAI | Summaries only — Requires OpenAI organization verification; falls back to no summaries. | `azure/gpt-6.1-sol`, `azure/gpt-6-sol`, `azure/gpt-6-luna`, `azure/gpt-6-astra`, `azure/gpt-5.6-sol`, `azure/gpt-5.6-terra`, `azure/gpt-5.6-luna`, `azure/gpt-5.5`, `azure/gpt-5.4-pro`, `azure/gpt-5.4`, `azure/gpt-5.4-mini`, `azure/gpt-5.4-nano`, `azure/gpt-5.2`, `azure/gpt-5.1`, `azure/gpt-5.1-codex`, `azure/gpt-5`, `azure/gpt-5-mini`, `azure/gpt-5-nano`, `azure/o3`, `azure/o4-mini` |
194-
| Azure Anthropic | Summaries only — These generations omit full thinking; Sim requests summarized thinking on streaming runs. | `azure-anthropic/claude-fable-5-1`, `azure-anthropic/claude-opus-5-5`, `azure-anthropic/claude-sonnet-5-5`, `azure-anthropic/claude-haiku-5-5`, `azure-anthropic/claude-opus-5`, `azure-anthropic/claude-opus-4-8`, `azure-anthropic/claude-opus-4-7`, `azure-anthropic/claude-opus-4-6`, `azure-anthropic/claude-opus-4-5`, `azure-anthropic/claude-sonnet-5`, `azure-anthropic/claude-sonnet-4-6`, `azure-anthropic/claude-sonnet-4-5`, `azure-anthropic/claude-opus-4-1`, `azure-anthropic/claude-haiku-4-5` |
193+
| Azure OpenAI | Summaries only — Requires OpenAI organization verification; falls back to no summaries. | `azure/gpt-6.1-sol`, `azure/gpt-6.1-terra`, `azure/gpt-6-sol`, `azure/gpt-6-luna`, `azure/gpt-6-astra`, `azure/gpt-5.6-sol`, `azure/gpt-5.6-terra`, `azure/gpt-5.6-luna`, `azure/gpt-5.5`, `azure/gpt-5.4-pro`, `azure/gpt-5.4`, `azure/gpt-5.4-mini`, `azure/gpt-5.4-nano`, `azure/gpt-5.2`, `azure/gpt-5.1`, `azure/gpt-5.1-codex`, `azure/gpt-5`, `azure/gpt-5-mini`, `azure/gpt-5-nano` |
194+
| Azure Anthropic | Summaries only — These generations omit full thinking; Sim requests summarized thinking on streaming runs. | `azure-anthropic/claude-fable-5-2`, `azure-anthropic/claude-fable-5-1`, `azure-anthropic/claude-fable-5`, `azure-anthropic/claude-opus-5-5`, `azure-anthropic/claude-sonnet-5-5`, `azure-anthropic/claude-haiku-5-5`, `azure-anthropic/claude-opus-5`, `azure-anthropic/claude-opus-4-8`, `azure-anthropic/claude-opus-4-7`, `azure-anthropic/claude-opus-4-6`, `azure-anthropic/claude-opus-4-5`, `azure-anthropic/claude-sonnet-5`, `azure-anthropic/claude-sonnet-4-6`, `azure-anthropic/claude-sonnet-4-5`, `azure-anthropic/claude-haiku-4-5` |
195195
| Google | Summaries only | `gemini-4-neon`, `gemini-4-hydrogen`, `gemini-4-carbon`, `gemini-4-argon`, `gemini-3.8-flash`, `gemini-3.7-flash`, `gemini-3.6-flash`, `gemini-3.5-flash-lite`, `gemini-3.5-flash`, `gemini-3.1-pro-preview`, `gemini-3.1-flash-lite`, `gemini-3-flash-preview`, `gemini-2.5-pro`, `gemini-2.5-flash`, `gemini-2.5-flash-lite` |
196-
| Vertex AI | Summaries only | `vertex/gemini-3.8-flash`, `vertex/gemini-3.7-flash`, `vertex/gemini-3.6-flash`, `vertex/gemini-3.5-flash-lite`, `vertex/gemini-3.5-flash`, `vertex/gemini-3.1-pro-preview`, `vertex/gemini-3.1-flash-lite`, `vertex/gemini-3-flash-preview`, `vertex/gemini-2.5-pro`, `vertex/gemini-2.5-flash`, `vertex/gemini-2.5-flash-lite` |
197-
| DeepSeek | Full thinking deltas | `deepseek-v4-pro`, `deepseek-flash`, `deepseek-v4-flash`, `deepseek-reasoner` |
196+
| Vertex AI | Summaries only | `vertex/gemini-4-neon`, `vertex/gemini-4-hydrogen`, `vertex/gemini-4-carbon`, `vertex/gemini-4-argon`, `vertex/gemini-3.8-flash`, `vertex/gemini-3.7-flash`, `vertex/gemini-3.5-flash-lite`, `vertex/gemini-3.5-flash`, `vertex/gemini-3.1-pro-preview`, `vertex/gemini-3.1-flash-lite`, `vertex/gemini-3-flash-preview` |
197+
| DeepSeek | Full thinking deltas | `deepseek-v4-pro`, `deepseek-flash`, `deepseek-v4-flash` |
198198
| xAI | Full thinking deltas | `grok-4.6`, `grok-4.5`, `grok-4.3`, `grok-4.20-multi-agent-0309` |
199199
| xAI | Summaries only | `grok-4.7` |
200200
| Cerebras | Full thinking deltas | `cerebras/qwen-3.8-27b` |
201-
| Groq | Full thinking deltas | `groq/openai/gpt-oss-120b`, `groq/openai/gpt-oss-20b`, `groq/openai/gpt-oss-safeguard-20b`, `groq/qwen/qwen3.8-27b`, `groq/qwen/qwen3.6-27b` |
201+
| Groq | Full thinking deltas | `groq/openai/gpt-oss-120b`, `groq/openai/gpt-oss-20b`, `groq/openai/gpt-oss-safeguard-20b`, `groq/qwen/qwen3.8-27b` |
202202
| Meta | Not streamed | `muse-spark-1.3`, `muse-spark-1.1` |
203203
| Kimi | Full thinking deltas | `kimi-k3`, `kimi-k2.6` |
204204
| Kie | Summaries only | `kie/claude-sonnet-5-5`, `kie/claude-opus-5-5`, `kie/claude-opus-5`, `kie/claude-fable-5`, `kie/claude-sonnet-5`, `kie/claude-opus-4-8`, `kie/claude-opus-4-7`, `kie/claude-opus-4-6`, `kie/claude-sonnet-4-6`, `kie/claude-opus-4-5`, `kie/claude-sonnet-4-5`, `kie/claude-haiku-4-5`, `kie/gpt-6-1-sol`, `kie/gpt-6-astra`, `kie/gpt-6-sol`, `kie/gpt-6-luna`, `kie/gpt-5-6-sol`, `kie/gpt-5-6-terra`, `kie/gpt-5-6-luna`, `kie/gpt-5-5`, `kie/grok-4-6`, `kie/grok-4-5`, `kie/grok-4-3`, `kie/kimi-k3` |

‎apps/sim/app/(landing)/models/comparisons.ts‎

Lines changed: 0 additions & 1 deletion
Original file line numberDiff line numberDiff line change
@@ -231,7 +231,6 @@ const CAPABILITY_CHECKS: ReadonlyArray<{
231231
supports: (model) => Boolean(model.capabilities.nativeStructuredOutputs),
232232
},
233233
{ label: 'computer use', supports: (model) => Boolean(model.capabilities.computerUse) },
234-
{ label: 'deep research', supports: (model) => Boolean(model.capabilities.deepResearch) },
235234
]
236235

237236
function buildCostSentence({ a, b }: ModelComparison): string {

‎apps/sim/app/(landing)/models/components/model-directory.tsx‎

Lines changed: 1 addition & 1 deletion
Original file line numberDiff line numberDiff line change
@@ -134,7 +134,7 @@ export function ModelDirectory() {
134134
<h3 className='text-[18px] text-[var(--text-primary)]'>No matches found</h3>
135135
<p className='mt-2 text-[var(--text-muted)] text-sm leading-[150%]'>
136136
Try a provider name like OpenAI or Anthropic, or search for capabilities like
137-
&nbsp;structured outputs, reasoning, or deep research.
137+
&nbsp;structured outputs, reasoning, or tool choice.
138138
</p>
139139
</div>
140140
) : (

‎apps/sim/app/(landing)/models/utils.ts‎

Lines changed: 16 additions & 21 deletions
Original file line numberDiff line numberDiff line change
@@ -235,8 +235,15 @@ export function formatCapabilityBoolean(
235235
return value ? positive : negative
236236
}
237237

238-
function supportsCatalogStructuredOutputs(capabilities: ModelCapabilities): boolean {
239-
return !capabilities.deepResearch
238+
/**
239+
* A retired model accepts no requests, and evaluation models answer native questions and reject a
240+
* response format.
241+
*/
242+
function supportsCatalogStructuredOutputs(
243+
capabilities: ModelCapabilities,
244+
retired: boolean
245+
): boolean {
246+
return !retired && !capabilities.evaluation
240247
}
241248

242249
export function getEffectiveMaxOutputTokens(capabilities: ModelCapabilities): number | null {
@@ -385,7 +392,7 @@ function formatModelDisplayName(providerId: string, modelId: string): string {
385392
return displayName.replace(/^GPT (\d[\w.]*)/i, 'GPT-$1').replace(/\bGpt\b/g, 'GPT')
386393
}
387394

388-
function buildCapabilityTags(capabilities: ModelCapabilities): string[] {
395+
function buildCapabilityTags(capabilities: ModelCapabilities, retired: boolean): string[] {
389396
const tags: string[] = []
390397

391398
if (capabilities.temperature) {
@@ -396,18 +403,14 @@ function buildCapabilityTags(capabilities: ModelCapabilities): string[] {
396403
tags.push('Tool choice')
397404
}
398405

399-
if (supportsCatalogStructuredOutputs(capabilities)) {
406+
if (supportsCatalogStructuredOutputs(capabilities, retired)) {
400407
tags.push('Structured outputs')
401408
}
402409

403410
if (capabilities.computerUse) {
404411
tags.push('Computer use')
405412
}
406413

407-
if (capabilities.deepResearch) {
408-
tags.push('Deep research')
409-
}
410-
411414
if (capabilities.reasoningEffort) {
412415
tags.push(`Reasoning ${capabilities.reasoningEffort.values.join(', ')}`)
413416
}
@@ -438,10 +441,6 @@ function buildBestForLine(model: {
438441
}): string | null {
439442
const { pricing, capabilities, contextWindow } = model
440443

441-
if (capabilities.deepResearch) {
442-
return 'Best for multi-step research workflows and agent-led web investigation.'
443-
}
444-
445444
if (capabilities.reasoningEffort || capabilities.thinking) {
446445
return 'Best for reasoning-heavy tasks that need more deliberate model control.'
447446
}
@@ -484,7 +483,6 @@ function computeModelRelevanceScore(model: CatalogModel): number {
484483
return (
485484
(model.capabilities.reasoningEffort ? 10 : 0) +
486485
(model.capabilities.thinking ? 10 : 0) +
487-
(model.capabilities.deepResearch ? 8 : 0) +
488486
(model.capabilities.nativeStructuredOutputs ? 4 : 0) +
489487
(model.contextWindow ?? 0) / 100000
490488
)
@@ -503,12 +501,13 @@ function compareModelsByRelevance(a: CatalogModel, b: CatalogModel): number {
503501
const rawProviders = Object.values(PROVIDER_DEFINITIONS).map((provider) => {
504502
const providerSlug = slugify(provider.id)
505503
const providerDisplayName = provider.name
506-
const providerCapabilityTags = buildCapabilityTags(provider.capabilities ?? {})
504+
const providerCapabilityTags = buildCapabilityTags(provider.capabilities ?? {}, false)
507505

508506
const models: CatalogModel[] = provider.models.map((model) => {
509507
const shortId = stripProviderPrefix(provider.id, model.id)
510508
const mergedCapabilities = { ...provider.capabilities, ...model.capabilities }
511-
const capabilityTags = buildCapabilityTags(mergedCapabilities)
509+
const retired = model.sunset?.status === 'deprecated'
510+
const capabilityTags = buildCapabilityTags(mergedCapabilities, retired)
512511
const bestFor = buildBestForLine({
513512
pricing: model.pricing,
514513
capabilities: mergedCapabilities,
@@ -530,7 +529,7 @@ const rawProviders = Object.values(PROVIDER_DEFINITIONS).map((provider) => {
530529
contextWindow: model.contextWindow ?? null,
531530
releaseDate: model.releaseDate ?? null,
532531
deprecated: !!model.sunset,
533-
retired: model.sunset?.status === 'deprecated',
532+
retired,
534533
featured: model.featured ?? false,
535534
recommended: model.recommended ?? false,
536535
pricing: model.pricing,
@@ -825,7 +824,7 @@ export function buildModelFaqs(provider: CatalogProvider, model: CatalogModel):
825824

826825
export function buildModelCapabilityFacts(model: CatalogModel): CapabilityFact[] {
827826
const { capabilities } = model
828-
const supportsStructuredOutputs = supportsCatalogStructuredOutputs(capabilities)
827+
const supportsStructuredOutputs = supportsCatalogStructuredOutputs(capabilities, model.retired)
829828

830829
return [
831830
{
@@ -868,10 +867,6 @@ export function buildModelCapabilityFacts(model: CatalogModel): CapabilityFact[]
868867
label: 'Computer use',
869868
value: formatCapabilityBoolean(capabilities.computerUse),
870869
},
871-
{
872-
label: 'Deep research',
873-
value: formatCapabilityBoolean(capabilities.deepResearch),
874-
},
875870
{
876871
label: 'Memory support',
877872
value: capabilities.memory === false ? 'Disabled' : 'Supported',

‎apps/sim/blocks/blocks/agent.ts‎

Lines changed: 13 additions & 55 deletions
Original file line numberDiff line numberDiff line change
@@ -16,7 +16,6 @@ import {
1616
getBaseModelProviders,
1717
getEvaluationModels,
1818
getMaxTemperature,
19-
getModelsWithDeepResearch,
2019
getModelsWithoutMemory,
2120
getModelsWithPromptCaching,
2221
getModelsWithReasoningEffort,
@@ -38,10 +37,8 @@ const MODELS_WITH_REASONING_EFFORT = getModelsWithReasoningEffort()
3837
const MODELS_WITH_VERBOSITY = getModelsWithVerbosity()
3938
const MODELS_WITH_THINKING = getModelsWithThinking()
4039
const MODELS_WITH_PROMPT_CACHING = getModelsWithPromptCaching()
41-
const MODELS_WITH_DEEP_RESEARCH = getModelsWithDeepResearch()
4240
const MODELS_WITHOUT_MEMORY = getModelsWithoutMemory()
4341
const EVALUATION_MODELS = getEvaluationModels()
44-
const MODELS_WITHOUT_CHAT_CONTROLS = [...MODELS_WITH_DEEP_RESEARCH, ...EVALUATION_MODELS]
4542

4643
// Helper function to get the tool ID from a block type
4744
const getToolIdFromBlock = (blockType: string): string | undefined => {
@@ -272,7 +269,7 @@ Return ONLY the JSON array.`,
272269
defaultValue: [],
273270
condition: {
274271
field: 'model',
275-
value: MODELS_WITHOUT_CHAT_CONTROLS,
272+
value: EVALUATION_MODELS,
276273
not: true,
277274
},
278275
},
@@ -283,7 +280,7 @@ Return ONLY the JSON array.`,
283280
defaultValue: [],
284281
condition: {
285282
field: 'model',
286-
value: MODELS_WITHOUT_CHAT_CONTROLS,
283+
value: EVALUATION_MODELS,
287284
not: true,
288285
},
289286
},
@@ -355,16 +352,9 @@ Return ONLY the JSON array.`,
355352
mode: 'advanced',
356353
condition: () => ({
357354
field: 'model',
358-
value: (() => {
359-
const deepResearch = new Set(MODELS_WITH_DEEP_RESEARCH.map((m) => m.toLowerCase()))
360-
const allModels = Object.keys(getBaseModelProviders())
361-
return allModels.filter(
362-
(model) =>
363-
supportsTemperature(model) &&
364-
getMaxTemperature(model) === 1 &&
365-
!deepResearch.has(model.toLowerCase())
366-
)
367-
})(),
355+
value: Object.keys(getBaseModelProviders()).filter(
356+
(model) => supportsTemperature(model) && getMaxTemperature(model) === 1
357+
),
368358
}),
369359
},
370360
{
@@ -377,16 +367,9 @@ Return ONLY the JSON array.`,
377367
mode: 'advanced',
378368
condition: () => ({
379369
field: 'model',
380-
value: (() => {
381-
const deepResearch = new Set(MODELS_WITH_DEEP_RESEARCH.map((m) => m.toLowerCase()))
382-
const allModels = Object.keys(getBaseModelProviders())
383-
return allModels.filter(
384-
(model) =>
385-
supportsTemperature(model) &&
386-
getMaxTemperature(model) === 1.5 &&
387-
!deepResearch.has(model.toLowerCase())
388-
)
389-
})(),
370+
value: Object.keys(getBaseModelProviders()).filter(
371+
(model) => supportsTemperature(model) && getMaxTemperature(model) === 1.5
372+
),
390373
}),
391374
},
392375
{
@@ -399,16 +382,9 @@ Return ONLY the JSON array.`,
399382
mode: 'advanced',
400383
condition: () => ({
401384
field: 'model',
402-
value: (() => {
403-
const deepResearch = new Set(MODELS_WITH_DEEP_RESEARCH.map((m) => m.toLowerCase()))
404-
const allModels = Object.keys(getBaseModelProviders())
405-
return allModels.filter(
406-
(model) =>
407-
supportsTemperature(model) &&
408-
getMaxTemperature(model) === 2 &&
409-
!deepResearch.has(model.toLowerCase())
410-
)
411-
})(),
385+
value: Object.keys(getBaseModelProviders()).filter(
386+
(model) => supportsTemperature(model) && getMaxTemperature(model) === 2
387+
),
412388
}),
413389
},
414390
{
@@ -419,7 +395,7 @@ Return ONLY the JSON array.`,
419395
mode: 'advanced',
420396
condition: {
421397
field: 'model',
422-
value: MODELS_WITHOUT_CHAT_CONTROLS,
398+
value: EVALUATION_MODELS,
423399
not: true,
424400
},
425401
},
@@ -431,21 +407,11 @@ Return ONLY the JSON array.`,
431407
language: 'json',
432408
condition: {
433409
field: 'model',
434-
value: MODELS_WITHOUT_CHAT_CONTROLS,
410+
value: EVALUATION_MODELS,
435411
not: true,
436412
},
437413
wandConfig: RESPONSE_FORMAT_WAND_CONFIG,
438414
},
439-
{
440-
id: 'previousInteractionId',
441-
title: 'Previous Interaction ID',
442-
type: 'short-input',
443-
placeholder: 'e.g., {{agent_1.interactionId}}',
444-
condition: {
445-
field: 'model',
446-
value: MODELS_WITH_DEEP_RESEARCH,
447-
},
448-
},
449415
{
450416
...getModelFallbackSubBlock(),
451417
condition: { field: 'model', value: EVALUATION_MODELS, not: true },
@@ -640,13 +606,5 @@ Return ONLY the JSON array.`,
640606
description: 'Provider timing information',
641607
},
642608
cost: { type: 'json', description: 'Cost of the API call' },
643-
interactionId: {
644-
type: 'string',
645-
description: 'Interaction ID for multi-turn deep research follow-ups',
646-
condition: {
647-
field: 'model',
648-
value: MODELS_WITH_DEEP_RESEARCH,
649-
},
650-
},
651609
},
652610
}

‎apps/sim/executor/handlers/agent/handler.test.ts‎

Lines changed: 0 additions & 20 deletions
Original file line numberDiff line numberDiff line change
@@ -70,9 +70,6 @@ const mockResolveBedrockCredentialSession =
7070
llmBedrockCredentialMockFns.mockResolveBedrockCredentialSession
7171
mockImportWorkspaceFileSecretProvenanceForModelView.mockResolvedValue(true)
7272
providersUtilsMockFns.mockGetProviderFromModel.mockReturnValue('mock-provider')
73-
providersUtilsMockFns.mockIsDeepResearchModel.mockImplementation((model: string) =>
74-
model.includes('deep-research')
75-
)
7673
providersUtilsMockFns.mockGetApiKey.mockReturnValue('mock-api-key')
7774

7875
process.env.NEXT_PUBLIC_APP_URL = 'http://localhost:3000'
@@ -1043,23 +1040,6 @@ describe('AgentBlockHandler', () => {
10431040
)
10441041
})
10451042

1046-
it('never falls back on a deep-research follow-up turn', async () => {
1047-
mockExecuteProviderRequest.mockRejectedValueOnce(new Error('overloaded'))
1048-
1049-
await expect(
1050-
handler.execute(mockContext, mockBlock, {
1051-
...baseInputs,
1052-
previousInteractionId: 'interaction-1',
1053-
fallbackModels: [{ model: 'claude-sonnet-5' }],
1054-
})
1055-
).rejects.toThrow('overloaded')
1056-
expect(mockExecuteProviderRequest).toHaveBeenCalledTimes(1)
1057-
expect(mockAgentLogger.info).toHaveBeenCalledWith(
1058-
'Fallback models skipped for a deep-research follow-up turn',
1059-
expect.objectContaining({ blockId: mockBlock.id })
1060-
)
1061-
})
1062-
10631043
it('gives a fallback its own key, the block key on the same provider, and nothing otherwise', async () => {
10641044
mockExecuteProviderRequest
10651045
.mockRejectedValueOnce(new Error('one'))

0 commit comments

Comments
 (0)