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.
PydanticAI v0.7.5 adds cost pricing on ModelResponse, span/trace IDs on EvaluationReport, and updated OpenTelemetry GenAI conventions.
└──▷ GET THIS VERSION
$ git clone --branch v0.7.5 https://github.com/pydantic/pydantic-ai.git
# already have the repo? check out this version:$ git checkout v0.7.5
└──▷ USE IT
Inspect the monetary cost of a model response after an agent run, useful for budget tracking or logging.
python
result = await agent.run('Summarise this document')
print(result.new_messages()[-1].price())
›Adds price() method to ModelResponse to retrieve cost information for a model response.
›Adds span_id and trace_id fields to EvaluationReport for linking evaluations to distributed traces.
›Updates OpenTelemetry instrumentation to use the new GenAI chat span attribute conventions.
›Includes thoughts tokens in output_tokens accounting for Google models.
›Allows proper typing on AnthropicProvider when using the Bedrock backend.
└──▷ BREAKING ON UPGRADE
!OpenTelemetry span attributes for GenAI chat now follow the new GenAI conventions — any dashboards, alerts, or attribute-based queries built on the old attribute names will need to be updated.
Continue gains --mcp, --model, and --prompt CLI flags, new multi-edit tools, Novita provider tool support, and a Unified Terminal.
└──▷ GET THIS VERSION
$ git clone --branch @continuedev/[email protected] https://github.com/continuedev/continue.git
# already have the repo? check out this version:$ git checkout @continuedev/[email protected]
└──▷ TRY IT
Run Continue non-interactively against a specific model and MCP server, passing a prompt directly — useful in CI pipelines.
$ continue --model gpt-4o --mcp ./mcp-server.json --prompt 'Review this codebase for hardcoded credentials'
›Adds --mcp and --model CLI flags for specifying MCP servers and models directly from the command line.
›Adds --prompt CLI flag to supply a prompt directly at invocation.
›Adds multi-edit and single search-and-replace tools for applying targeted code edits across files.
›Adds info slash command.
›Adds tool support for Novita provider models.
+4 moreshow less
›Introduces a Unified Terminal UI.
›Adds resource monitoring capability.
›Adds UI for diff tools, surfacing multi-edit and single-replace actions inline.
›Adds plan mode system prompt for structured agent planning workflows.
Get up and running with Kimi-K2.6, GLM-5.2, MiniMax, DeepSeek, gpt-oss, Qwen, Gemma and other models.
Ollama v0.11.7 adds DeepSeek-V3.1 support with hybrid thinking and cloud Turbo mode preview.
└──▷ GET THIS VERSION
$ git clone --branch v0.11.7 https://github.com/ollama/ollama.git
# already have the repo? check out this version:$ git checkout v0.11.7
└──▷ TRY IT
Run DeepSeek-V3.1 with thinking enabled to get chain-of-thought reasoning alongside the final answer.
$ curl http://localhost:11434/api/chat -d '{"model": "deepseek-v3.1", "messages": [{"role": "user", "content": "why is the sky blue?"}], "think": true}'
Run DeepSeek-V3.1 on Ollama's cloud hardware when local VRAM is insufficient for the 671B model.
$ OLLAMA_HOST=ollama.com ollama run deepseek-v3.1
Toggle thinking on or off interactively during a CLI chat session with a hybrid-thinking model.
$ /set think
# or to disable:
/set nothink
›Adds DeepSeek-V3.1 (671B parameter model) to the Ollama model library.
›Supports hybrid thinking on compatible models: enable or disable chain-of-thought reasoning per request via the think field in the API or /set think//set nothink CLI commands.
›Introduces Turbo mode (preview): routes inference for large models like DeepSeek-V3.1 to cloud hardware via OLLAMA_HOST=ollama.com.
Arize Phoenix v11.27.0 adds support for extra volumes and volume mounts in the Helm chart.
└──▷ GET THIS VERSION
$ git clone --branch arize-phoenix-v11.27.0 https://github.com/Arize-ai/phoenix.git
# already have the repo? check out this version:$ git checkout arize-phoenix-v11.27.0
›Adds support for extra volumes and volume mounts in the Helm chart, enabling custom storage configurations for Phoenix deployments.
THE AI TOOLCHAIN