The daily firehose — everything the toolchain shipped today, already filtered.
// HOW THIS ISSUE IS MADE
We read every release from the 174 tools on our watchlist at the source — GitHub and GitLab release notes, vendor release pages and changelogs, project blogs and feeds, vendor press releases, and the source code behind the tag. Bug-fix-only releases and non-product newsroom noise are dropped; what's left is summarized down to the new capability, how to try it, and any screenshots or videos the release itself published. Every entry links to the sources it was built from.
Claude Code is an agentic coding tool that lives in your terminal, understands your codebase, and helps you code faster by executing routine tasks, explaining complex code, and handling git workflows - all through natural language commands.
Claude Code v2.1.207 makes Auto Mode generally available on Bedrock, Vertex, and Foundry and tightens plugin security.
└──▷ GET THIS VERSION
$ git clone --branch v2.1.207 https://github.com/anthropics/claude-code.git
# already have the repo? check out this version:$ git checkout v2.1.207
└──▷ USE IT
Disable auto mode on Bedrock or Vertex if you relied on the old opt-in flag to keep it off.
json
# In ~/.claude/settings.json
{
"disableAutoMode": true
}
Migrate a plugin hook from shell-form (now rejected for user-config interpolation) to exec form so it survives the security change.
json
# Before (rejected):
# command: "my-hook ${user_config.api_key}"
# After — exec form in hook definition:
{
"args": ["my-hook", "$CLAUDE_PLUGIN_OPTION_API_KEY"]
}
›Auto mode is now available on Bedrock, Vertex AI, and Foundry without the CLAUDE_CODE_ENABLE_AUTO_MODE opt-in flag; disable via disableAutoMode in settings.
›Bedrock, Vertex, and Claude Platform on AWS now default to Claude Opus 4.8.
›Plugin hooks/monitors/MCP headersHelper: ${user_config.*} in shell-form commands is now rejected; hooks must use exec form (args array) or $CLAUDE_PLUGIN_OPTION_<KEY>.
›Plugin option values (pluginConfigs) are no longer read from project-level .claude/settings.json; only user, --settings, and managed settings are honored.
›Agent view: pasting the same text again now expands the existing collapsed [Pasted text #N] placeholder instead of creating a duplicate.
+2 moreshow less
›Agent view: blocked session peeks now lead with the question and display a worded staleness clock (e.g. waiting 3m).
›/doctor now reports when the launcher at ~/.local/bin/claude is externally managed.
└──▷ BREAKING ON UPGRADE
!Auto mode no longer reads autoMode from .claude/settings.local.json (repo-resident); move the setting to ~/.claude/settings.json.
!${user_config.*} interpolation in shell-form plugin hook/monitor/headersHelper commands is rejected; switch to exec form (args array) or $CLAUDE_PLUGIN_OPTION_<KEY> for hooks, or read the value inside the script for monitors and headersHelper.
!pluginConfigs plugin option values are no longer read from project-level .claude/settings.json; only user-level, --settings, and managed settings are honored.
PydanticAI v2.9.0 adds a /usage CLI command, GPT-5.6 + reasoning mode support, and usage_limits exposure on RunContext.
└──▷ GET THIS VERSION
$ git clone --branch v2.9.0 https://github.com/pydantic/pydantic-ai.git
# already have the repo? check out this version:$ git checkout v2.9.0
└──▷ USE IT
Inspect the active run's token limits inside a tool to short-circuit expensive work before hitting the cap.
python
from pydantic_ai import Agent, RunContext
agent = Agent('openai:gpt-4o')
@agent.tool
async def my_tool(ctx: RunContext[None]) -> str:
limits = ctx.usage_limits
if limits and limits.response_tokens_limit and limits.response_tokens_limit < 500:
return 'Skipping — too close to token limit'
return 'Proceeding with full response'
Check cumulative token consumption mid-session in the clai interactive CLI.
$ /usage
›Exposes usage_limits on RunContext so tools and capabilities can inspect the current run's token/request limits at call time.
›Adds /usage slash command to the clai CLI to display cumulative token usage across a session.
›Adds GPT-5.6 models and reasoning mode support to the OpenAI provider.
vLLM v0.25.0 adds a Streaming Parser Engine, static HTTPS/mTLS on the Rust frontend, universal speculative decoding, and a raft of new models and API fields.
└──▷ GET THIS VERSION
$ git clone --branch v0.25.0 https://github.com/vllm-project/vllm.git
# already have the repo? check out this version:$ git checkout v0.25.0
└──▷ TRY IT
Turn on GPU sync checking during development to surface synchronization issues early.
$ VLLM_GPU_SYNC_CHECK=1 vllm serve <model-id>
›Adds VLLM_GPU_SYNC_CHECK environment variable for GPU synchronization checking.
›Adds return_loss_mask field to Chat/Completions responses for training-data generation.
›Adds model_class_overrides CLI option for development and debugging.
›Adds repetition_detection sampling parameter in the Rust frontend.
›Adds kv_transfer_params merging via MultiConnector for PD disaggregation.
+51 moreshow less
›Adds FLASH_ATTN_MLA_SPARSE environment variable to select the Hopper sparse-MLA attention backend.
›Adds ROCM_AITER_FA backend flag to enable the AITER FlashAttention MLA prefill path on ROCm.
›Adds static HTTPS and mTLS support for HTTP and gRPC in the Rust frontend.
›Adds per-request timing metrics field on Chat/Completions responses.
›Adds token offsets on render endpoints.
›Adds profiler control routes in the Rust frontend.
›Adds a DP supervisor via the Rust frontend.
›Introduces a new Streaming Parser Engine — a unified tool-call and reasoning parsing framework — with a new Kimi k2.5/k2.6/k2.7 parser and ports of seed_oss and DeepSeek V4 parsers.
›Adds universal speculative decoding for heterogeneous vocabularies (TLI), enabling spec decode across models with mismatched vocabularies.
›Adds DSpark and DFlash speculative decoding drafters, including a Laguna XS.2.1 drafter.
›Adds tok_sparse_select configuration for MiniMax-M3, replacing Triton kernels.
›Adds LookupResult enum to the KV offloading subsystem.
›Adds TorchCodec as a video decoding backend.
›Adds TTFT and TPS metrics printing in vllm chat.
›Adds usage field exposed for disaggregated serving.
›Adds a dedicated Harmony renderer for gpt-oss / Harmony serving.
›Adds a secondary-tier implementation for PD disaggregation.
›Adds NVFP4 KV cache with skip-layers sliding window support.
›Adds Marlin thread-tile padding extended to MoE (WNA16 + FP8/MXFP8) and int8 grouped WNA16 MoE.
›Adds FlashInfer MXINT4 MoE support for gated SiLU.
›Adds W8A8 FP8 linear kernel with multi-granularity quantization for Intel XPU.
›Adds AITER custom all-reduce in CudaCommunicator for ROCm.
›Adds INT3 quantization for quickreduce on ROCm.
›Adds EPLB support for Quark OCP MXFP4 MoE on ROCm.
›Adds accelerator-agnostic get_memory_info platform API and a C++ implementation for Intel XPU.
›Adds RVV path for W4A8 INT4 GEMM on RISC-V, BF16 support on VLEN=256 hardware, and reduced LMUL pressure in INT4 LUT dequant.
›Adds fp16 support on PowerPC.
›Adds new models: LLaVA-OneVision-2, Unlimited OCR (with Triton R-SWA backend), MOSS-Transcribe-Diarize, openai/privacy-filter, and Hy3 (with token-suffix and JSON Schema array support).
›Adds GLM-5 / DeepSeek-V3.2 to the model zoo and pipeline parallelism for MiniMax-M3.
›Model Runner V2 is now the default execution path for all dense models, adding support for EVS, realtime embeddings, Mamba hybrid prefix caching, multimodal-prefix bidirectional attention, and dynamic speculative decoding with full CUDA graphs.
›Adds sequence parallelism without requiring data parallelism, yielding 1.9–5.0% end-to-end throughput improvement.
›Adds NCCL symmetric memory support extended to AllGather and ReduceScatter operations.
›Adds a fault-tolerance backend to detect all-to-all peer faults and prevent corrupted output.
›Adds Mooncake connector support for GDN (Qwen3.5) and MLA (DeepSeek-V4-Flash) in PD disaggregation.
Phoenix v17.26.0 clarifies forced tool choice menus in the UI.
└──▷ GET THIS VERSION
$ git clone --branch arize-phoenix-v17.26.0 https://github.com/Arize-ai/phoenix.git
# already have the repo? check out this version:$ git checkout arize-phoenix-v17.26.0
›Improves forced tool choice menus with clearer labeling to make tool selection options more distinguishable.
Phoenix v17.25.0 adds approval-gated annotation config tools, a .env file, and a new Metrics tab with experiment charts.
└──▷ GET THIS VERSION
$ git clone --branch arize-phoenix-v17.25.0 https://github.com/Arize-ai/phoenix.git
# already have the repo? check out this version:$ git checkout arize-phoenix-v17.25.0
└──▷ USE IT
Configure Phoenix server settings persistently without passing environment variables on every launch.
THE AI TOOLCHAIN