前沿

NVIDIA · 11-07 05:38

Highlights Known Issues DSA models, including GLM-5.2, may produce incorrect output when using an NVFP4 KV cache. Kimi K3 DSpark with MegaMoE CuTe DSL TEP and CUDA graphs may hang

Anthropic · 11-06 02:58

Features api: add error code for ramp limit errors api: add error codes for External Key validation failures api: add support for signing organization members out everywhere Bug Fi

Anthropic · 11-05 04:27

Features api: add error details types and new error type values api: add ids filter to list workspaces client: add error classes for HTTP statuses and API error codes, and error_co

Anthropic · 11-03 03:07

Features api: add GA methods for analytics, spend limits and RBAC api: add named beta types for unified metrics and RBAC delete responses api: add shared analytics order and increa

NVIDIA · 10-28 23:51

Python package version The Python wheels for this release are published as 1.4.0rc2.post1 . Container images and documentation remain at 1.4.0rc2 . Use 1.4.0rc2.post1 when installi

Anthropic · 10-23 21:10

Features api: add support for message threads api: add usage and cost reports by dimension, mark older reports legacy Bug Fixes client: stop suggesting math.inf in the max_retries

Anthropic · 10-22 06:00

Features api: add enforcement status, actions and filter to user profiles

Anthropic · 10-21 23:51

⚠ BREAKING CHANGES api: add support for new API version 2026-10-21 Features api: add a workspace_id filter and the usage_tier scope type to list spend limits api: add support for n

Anthropic · 10-21 06:13

Features api: add org webhook endpoints and user profile enforcement events api: add RBAC Group owner-access error codes to the Admin API api: document the unsupported_charset erro

Anthropic · 10-21 01:49

Features api: add data_refreshed_at and has_more to analytics report pages api: add workspace rate-limit updates to the Admin API api: make User Profiles generally available client

Anthropic · 10-16 03:45

Features api: add between_tools to thinking types in model capabilities api: add the speed parameter and usage.speed to Messages api: return a Console organization's usage-tier spe

zcbacxc · 10-16 02:29

麦当劳 MCP 聚会/团餐组织助手 — 基于 Model Context Protocol 的派对预订与团餐规划 CLI/Skill

Anthropic · 10-15 01:13

Features api: add execution_identity to Managed Agents agents api: add organization_type_not_supported error to spend limit lists api: add telemetry destination test endpoint api:

Anthropic · 10-09 23:28

Features api: add types for the Chat and Cowork unified analytics metrics api: add workflows, multiagent configuration and thread status filtering to Managed Agents Chores internal

NVIDIA · 10-09 06:16

Highlights Known Issues Multi-GPU (TP2) streaming or RPC executor workloads may hang during worker initialization when MPI worker pools are reused across LLM instances (observed on

Anthropic · 10-08 11:41

Chores ci: check that pull requests update the changelog docs: note that listing Claude Console spend limits is in early access internal: match the package version in uv.lock

Anthropic · 10-08 01:57

1.12.0 (2026-10-07) Full Changelog: v1.11.0...v1.12.0 Features api: add claude-haiku-5-5 and typed computer and browser toolset tool calls ( f6346e6 ) api: add disabled to thinking

Anthropic · 10-01 06:58

1.11.0 (2026-09-30) Full Changelog: v1.10.0...v1.11.0 Features api: add list spend limits endpoint ( e8f0cac ) Chores client: deprecate sonnet 4.5 ( 22b36b1 )

NVIDIA · 09-29 18:56

Highlights Model Support Support Qwen3.5 checkpoints with global FP8 scales across model loading paths #19519 Optimize Gemma4 vision rotary embeddings without a GEMM operation #195

OpenAI · 09-29 08:45

Build plugins that feel like native, first-class features of ChatGPT.

Anthropic · 09-29 02:03

1.9.0 (2026-09-28) Full Changelog: v1.8.0...v1.9.0 Features api: add between_tools thinking type ( a9a577d ) api: add claude-sonnet-5-5 ( a5a25e9 ) api: add include_inherited and s

NVIDIA · 09-23 14:34

Highlights Known Issues Multi-node inference may fail during startup when a requested parallel mapping spans nodes or request payloads reference caller-local Python modules. Disagg

Anthropic · 09-23 00:25

1.8.0 (2026-09-22) Full Changelog: v1.7.0...v1.8.0 Features api: add support for claude-opus-5-5, inline tool definitions and MCP tool-list pinning (beta) ( b5cc700 ) Bug Fixes api

Anthropic · 09-19 00:12

1.7.0 (2026-09-18) Full Changelog: v1.6.0...v1.7.0 Features api: add group with display_name to rate limits, deprecate group_type ( 28f0a83 ) tools: add compact_before_next_turn()

OpenAI · 09-17 01:00

OpenAI shares a framework for tracking, investigating, and disclosing model misalignment, alongside six reports of unexpected or concerning model behavior.

Anthropic · 09-15 23:14

1.6.0 (2026-09-15) Full Changelog: v1.5.0...v1.6.0 Features api: add auto mode tool permissions for Managed Agents ( 909d92f ) api: add compaction parameter and signed compaction b

NVIDIA · 09-14 16:17

Highlights Known Issues GPT-OSS Eagle3 speculative decoding may hang, produce non-terminating output, or lose accuracy when using multi-GPU execution. GPT-OSS W4 inference with the

OpenAI · 09-11 03:51

Install with pip install --upgrade openai-codex==0.154.0 (Python 3.10 or later). This release includes the matching openai-codex-cli-bin==0.154.0 runtime. Add max and ultra reasoni

Anthropic · 09-11 01:45

1.5.0 (2026-09-10) Full Changelog: v1.4.0...v1.5.0 Features api: add auto mode tool permissions for Managed Agents ( 62aa21b ) api: add content_too_large web_fetch tool error code

NVIDIA · 09-09 17:37

Highlights Known Issues LoRA adapters that target the routed experts of Qwen3 mixture-of-experts models are silently ignored and produce base-model output. Adapters targeting atten

Anthropic · 09-05 06:20

1.4.0 (2026-09-04) Full Changelog: v1.3.0...v1.4.0 Features api: add Claude Tag category and user breakdowns to usage reports ( 9fce1e4 ) api: add named types for organization comp

OpenAI · 09-01 21:00

Astra is the first OpenAI model to meet the Critical cybersecurity capability threshold under the Preparedness Framework, with stronger safeguards for release.