60 Einträge aus 1 Quelle. Zuletzt aktualisiert:
Folge Vercel AI, um die Release Notes in deinen Feed zu holen.
Datum aus der Quelle.
Erstmals gesehen am .
@ai-sdk/topaz 3.0.2 aktualisiert lediglich interne Abhängigkeiten (provider-utils, provider).
Datum aus der Quelle.
Erstmals gesehen am .
@ai-sdk/togetherai 3.0.65 aktualisiert lediglich interne Abhängigkeiten (provider-utils, provider, openai-compatible).
Datum aus der Quelle.
Erstmals gesehen am .
@ai-sdk/test-server 2.0.4 wurde auf TypeScript 6 umgestellt.
Datum aus der Quelle.
Erstmals gesehen am .
@ai-sdk/svelte 5.0.129 aktualisiert lediglich interne Abhängigkeiten auf ai@7.0.129 und provider-utils@5.0.55.
Datum aus der Quelle.
Erstmals gesehen am .
@ai-sdk/sandbox-vercel 1.0.140 aktualisiert lediglich interne Abhängigkeiten (provider-utils, harness).
Datum aus der Quelle.
Erstmals gesehen am .
@ai-sdk/sandbox-just-bash 1.0.140 aktualisiert lediglich interne Abhängigkeiten (provider-utils, harness).
Datum aus der Quelle.
Erstmals gesehen am .
@ai-sdk/rsc 3.0.129 aktualisiert lediglich interne Abhängigkeiten (provider-utils, ai, provider).
Datum aus der Quelle.
Erstmals gesehen am .
@ai-sdk/revai 3.0.55 wurde auf TypeScript 6 umgestellt und aktualisiert interne Abhängigkeiten.
Datum aus der Quelle.
Erstmals gesehen am .
@ai-sdk/replicate 3.0.56 aktualisiert lediglich interne Abhängigkeiten (provider-utils, provider).
Datum aus der Quelle.
Erstmals gesehen am .
@ai-sdk/react 4.0.132 aktualisiert lediglich interne Abhängigkeiten (provider-utils, ai, provider, mcp).
Datum aus der Quelle.
Erstmals gesehen am .
@ai-sdk/quiverai 2.0.56 aktualisiert ausschließlich die Abhängigkeiten @ai-sdk/provider-utils@5.0.55, @ai-sdk/provider@4.0.23 und @ai-sdk/open-responses@2.0.60.
Datum aus der Quelle.
Erstmals gesehen am .
max eingeführt@ai-sdk/provider 4.0.23 führt eine portable Reasoning-Stufe max mit nativen Provider-Mappings, Kompatibilitätsanpassungen und Budget-Fallback ein, wodurch sich der Typ ReasoningLevel erweitert und exhaustive Switches angepasst werden müssen; bei Amazon Bedrock Nova 2 wird xhigh nun als high gesendet, bei Fireworks gibt es Kompatibilitätswarnungen.
268225c: feat(provider): add a portable max reasoning level with native provider mappings, compatibility coercions, and budget-based fallback support.
Compatibility notes:
max widens LanguageModelV4CallOptions['reasoning'] and the derived ReasoningLevel type. Third-party providers and consumers with exhaustive switches or Record<ReasoningLevel, ...> mappings must handle max before upgrading. Ordinary calls using existing reasoning levels remain accepted.reasoning: 'xhigh' now send maxReasoningEffort: 'high' instead of the unsupported 'max', and return a compatibility warning. Anthropic and OpenAI Bedrock effort mappings retain their existing xhigh behavior. Partial Bedrock reasoning configurations continue to preserve explicit values and derive missing fields; explicit effort/budget overrides and disabled thinking no longer emit warnings for portable mappings that are not sent.minimal and xhigh calls keep their request mappings to low and high, respectively, and now return compatibility warnings in generation and streaming results. Portable max maps to high with the same warning behavior. …Datum aus der Quelle.
Erstmals gesehen am .
max@ai-sdk/provider-utils 5.0.55 begrenzt JSONL-Zeilen bei Batch-Ergebnis-Downloads auf 64 MB, erhält parallele Tool-Calls bei fehlenden oder wiederverwendeten Stream-Labels und ergänzt die portable Reasoning-Stufe max.
fc1e19e: fix: limit jsonl rows to 64mb during batch result downloads
5094ebd: fix(provider-utils): preserve parallel tool calls when stream labels are missing or reused
268225c: feat(provider): add a portable max reasoning level with native provider mappings, compatibility coercions, and budget-based fallback support.
Compatibility notes:
max widens LanguageModelV4CallOptions['reasoning'] and the derived ReasoningLevel type. Third-party providers and consumers with exhaustive switches or Record<ReasoningLevel, ...> mappings must handle max before upgrading. Ordinary calls using existing reasoning levels remain accepted.reasoning: 'xhigh' now send maxReasoningEffort: 'high' instead of the unsupported 'max', and return a compatibility warning. Anthropic and OpenAI Bedrock effort mappings retain their existing xhigh behavior. Partial Bedrock reasoning configurations continue to preserve explicit values and derive missing fields; explicit effort/budget overrides and disabled thinking no longer emit warnings for portable mappings that are not sent.minimal and xhigh calls keep their request mappings to low and high, respectively, and now return compatibility warnings in generation and streaming results. Portable max maps to high with the same warning behavior. …Datum aus der Quelle.
Erstmals gesehen am .
@ai-sdk/prodia 2.0.56 wechselt auf TypeScript 6 und aktualisiert die Abhängigkeiten @ai-sdk/provider-utils@5.0.55 und @ai-sdk/provider@4.0.23.
Datum aus der Quelle.
Erstmals gesehen am .
@ai-sdk/policy-opa 1.0.129 aktualisiert ausschließlich die Abhängigkeiten @ai-sdk/provider-utils@5.0.55, ai@7.0.129 und @ai-sdk/provider@4.0.23.
Datum aus der Quelle.
Erstmals gesehen am .
max@ai-sdk/perplexity 5.0.7 unterstützt die neue portable Reasoning-Stufe max mit nativen Provider-Mappings, Kompatibilitätsanpassungen und Budget-Fallback.
268225c: feat(provider): add a portable max reasoning level with native provider mappings, compatibility coercions, and budget-based fallback support.
Compatibility notes:
max widens LanguageModelV4CallOptions['reasoning'] and the derived ReasoningLevel type. Third-party providers and consumers with exhaustive switches or Record<ReasoningLevel, ...> mappings must handle max before upgrading. Ordinary calls using existing reasoning levels remain accepted.reasoning: 'xhigh' now send maxReasoningEffort: 'high' instead of the unsupported 'max', and return a compatibility warning. Anthropic and OpenAI Bedrock effort mappings retain their existing xhigh behavior. Partial Bedrock reasoning configurations continue to preserve explicit values and derive missing fields; explicit effort/budget overrides and disabled thinking no longer emit warnings for portable mappings that are not sent.minimal and xhigh calls keep their request mappings to low and high, respectively, and now return compatibility warnings in generation and streaming results. Portable max maps to high with the same warning behavior. …Datum aus der Quelle.
Erstmals gesehen am .
@ai-sdk/otel 1.0.129 aktualisiert ausschließlich die Abhängigkeiten ai@7.0.129 und @ai-sdk/provider@4.0.23.
Datum aus der Quelle.
Erstmals gesehen am .
max@ai-sdk/openai 4.0.85 begrenzt JSONL-Zeilen bei Batch-Downloads auf 64 MB, ersetzt den Structured-Output-Wrapper für decide durch die native Decisions API (derzeit nur mit gpt-6-luna, Responses-API-Optionen wie reasoningEffort entfallen) und unterstützt die portable Reasoning-Stufe max.
fc1e19e: fix: limit jsonl rows to 64mb during batch result downloads
99bdcd2: Replace the OpenAI structured-output wrapper for decide with the native Decisions API. Only gpt-6-luna is currently supported by this endpoint; other Responses models no longer work with openai.decisionModel() or its deprecated evaluationModel() alias.
Responses API options, such as reasoningEffort, are no longer applied and produce unsupported-option warnings. The Decisions API supports providerOptions.openai.safetyIdentifier. Native token usage and confidence values are preserved, and per-question refusals fail the decision call.
268225c: feat(provider): add a portable max reasoning level with native provider mappings, compatibility coercions, and budget-based fallback support.
Compatibility notes:
max widens LanguageModelV4CallOptions['reasoning'] and the derived ReasoningLevel type. Third-party providers and consumers with exhaustive switches or Record<ReasoningLevel, ...> mappings must handle max before upgrading. Ordinary calls using existing reasoning levels remain accepted. …Datum aus der Quelle.
Erstmals gesehen am .
max@ai-sdk/openai-compatible 3.0.64 unterstützt die neue portable Reasoning-Stufe max mit nativen Provider-Mappings, Kompatibilitätsanpassungen und Budget-Fallback.
268225c: feat(provider): add a portable max reasoning level with native provider mappings, compatibility coercions, and budget-based fallback support.
Compatibility notes:
max widens LanguageModelV4CallOptions['reasoning'] and the derived ReasoningLevel type. Third-party providers and consumers with exhaustive switches or Record<ReasoningLevel, ...> mappings must handle max before upgrading. Ordinary calls using existing reasoning levels remain accepted.reasoning: 'xhigh' now send maxReasoningEffort: 'high' instead of the unsupported 'max', and return a compatibility warning. Anthropic and OpenAI Bedrock effort mappings retain their existing xhigh behavior. Partial Bedrock reasoning configurations continue to preserve explicit values and derive missing fields; explicit effort/budget overrides and disabled thinking no longer emit warnings for portable mappings that are not sent.minimal and xhigh calls keep their request mappings to low and high, respectively, and now return compatibility warnings in generation and streaming results. Portable max maps to high with the same warning behavior. …Datum aus der Quelle.
Erstmals gesehen am .
max@ai-sdk/open-responses 2.0.60 unterstützt die neue portable Reasoning-Stufe max mit nativen Provider-Mappings, Kompatibilitätsanpassungen und Budget-Fallback.
268225c: feat(provider): add a portable max reasoning level with native provider mappings, compatibility coercions, and budget-based fallback support.
Compatibility notes:
max widens LanguageModelV4CallOptions['reasoning'] and the derived ReasoningLevel type. Third-party providers and consumers with exhaustive switches or Record<ReasoningLevel, ...> mappings must handle max before upgrading. Ordinary calls using existing reasoning levels remain accepted.reasoning: 'xhigh' now send maxReasoningEffort: 'high' instead of the unsupported 'max', and return a compatibility warning. Anthropic and OpenAI Bedrock effort mappings retain their existing xhigh behavior. Partial Bedrock reasoning configurations continue to preserve explicit values and derive missing fields; explicit effort/budget overrides and disabled thinking no longer emit warnings for portable mappings that are not sent.minimal and xhigh calls keep their request mappings to low and high, respectively, and now return compatibility warnings in generation and streaming results. Portable max maps to high with the same warning behavior. …