PulseAugur
中
实时 12:24:50

Ollama v0.40.14 增强了模型限制、API 兼容性和错误处理 · 跟踪 2 个来源

Ollama 发布了 0.40.14 版本,对其模型处理和 API 兼容性进行了一些改进。主要更新包括为 Claude Code 应用特定于模型的输出令牌限制,正确解码压缩的网络搜索响应,以及为 OpenAI 兼容的端点保留采样器默认值。该版本还增强了对 ChatGPT 断开连接和路由问题的错误处理,并加快了 MLX 在大词汇量上的采样速度。 AI

影响 这些更新提高了与 AI 模型交互的工具的可用性和性能,可能简化开发工作流程。

排序理由 此集群包含多个开发工具和 SDK 的软件发行说明,而不是核心 AI 模型发布或研究论文。

在 Ollama — Releases 阅读 →

AI 生成摘要 · Google Gemini · 来自 9 个来源。 我们如何撰写摘要 →

Ollama v0.40.14 增强了模型限制、API 兼容性和错误处理 · 跟踪 2 个来源

本文如何被排名

Signal score
0 / 100
Composite score across the factors below. Higher = stronger signal that this story matters right now.
Newsworthiness bucket
Tool
此集群包含多个开发工具和 SDK 的软件发行说明,而不是核心 AI 模型发布或研究论文。
Source corroboration
9 independent sources
Strong cross-source corroboration — multiple independent publishers covered this within the clustering window.
Topics
product, infra
Editorial topic classification. Feeds into how the story surfaces on /topic/<slug> hub pages and into the per-entity coverage mix.
AI-industry relevance
High
Clearly on-topic for AI-industry coverage.
Story freshness
3 days old
Aged out of breaking-news scoring windows; ranking reflects the durable signal from the full source set.

完整方法见我们的编辑标准。

报道来源 [9]

  1. Ollama — Releases TIER_1 (SK) · github-actions[bot] ·

    v0.40.14

    <h2>What's Changed</h2> <ul> <li><code>ollama launch claude</code> now applies the model's output token limit for Claude Code, so cloud models no longer run into the 128k default cap</li> <li>Cloud web search responses on <code>/api/chat</code> are now decoded correctly, includin…

  2. Ollama — Releases TIER_1 (SK) · github-actions[bot] ·

    v0.40.14

    <h2>What's Changed</h2> <ul> <li>ci: pin buildx to workaround deadlock by <a class="user-mention notranslate" href="https://github.com/dhiltgen">@dhiltgen</a> in <a class="issue-link js-issue-link" href="https://github.com/ollama/ollama/pull/19373">#19373</a></li> <li>openai: pre…

  3. Claude Code — Releases TIER_1 (SK) · ashwin-ant ·

    v2.1.317

    <h2>What's changed</h2> <ul> <li>Added a warning to <code>/schedule</code> when a new cloud scheduled task gets connectors you did not ask for, with how to remove them</li> <li>Added a check that asks before a web or shell tool call sends your account email address to the network…

  4. Anthropic SDK (Python) — Releases TIER_1 (SK) · anthropic-sdks-releaser[bot] ·

    v2.4.0

    <h3>Features</h3> <ul> <li><strong>api:</strong> add GA methods for analytics, spend limits and RBAC</li> <li><strong>api:</strong> add named beta types for unified metrics and RBAC delete responses</li> <li><strong>api:</strong> add shared analytics order and increase request ac…

  5. Claude Agent SDK (Python) — Releases TIER_1 (SK) · github-actions[bot] ·

    v0.2.177

    <h3>New Features</h3> <ul> <li><strong><code>on_failure</code> option for <code>HookMatcher</code></strong>: Control what happens when a hook callback fails. Set <code>on_failure="block"</code> to block the action when a callback raises, returns <code>None</code>, or returns a va…

  6. openai-python — Releases TIER_1 (SK) · openai-sdks[bot] ·

    v3.42.1

    <h2><a href="https://github.com/openai/openai-python/compare/v3.42.0...v3.42.1">3.42.1</a> (2026-11-01)</h2> <h3>Bug Fixes</h3> <ul> <li><strong>api:</strong> preserve Responses WebSocket connection behavior (<a href="https://github.com/openai/openai-python/issues/4221">#4221</a>…

  7. vLLM — Releases TIER_1 (SK) · khluu ·

    v0.33.0

    <p>vLLM v0.33.0</p>

  8. vLLM — Releases TIER_1 (SK) · AndreasKaratzas ·

    v0.33.0rc3

    <p>[CI][Bugfix] Pin the ColUltraVBERT test checkpoint to the revision vL…</p>

  9. openai-python — Releases TIER_1 (SK) · openai-sdks[bot] ·

    v3.42.0

    <h2><a href="https://github.com/openai/openai-python/compare/v3.41.0...v3.42.0">3.42.0</a> (2026-10-31)</h2> <h3>Features</h3> <ul> <li><strong>api:</strong> add agent context compaction settings (<a href="https://github.com/openai/openai-python/issues/4209">#4209</a>) (<a href="…