Agents
Eclipse Enclave sandboxes coding agents, OVHcloud launches 55 AI products with B300 and Rubin GPUs, OpenAI shows its Codex-run Performance Factory; Claude Code 2.1.329 and Codex 0.171.0
The Eclipse Foundation releases Enclave 1.0, an MIT-licensed sandbox that runs Claude Code, Codex or OpenCode in isolated containers; Kong launches Volcano; the GitHub Copilot app reaches Azure DevOps repos. OpenAI says Codex agents ran more than 1,700 performance investigations in about three months, and ships GPT-Live-1.1 in its API. OVHcloud unveils 55 products and up to 60,000 B300 GPUs, Tencent publishes the Hy4 weights, and Claude Code 2.1.329, Codex 0.171.0 and Zed 1.29 ship.
- Coding agents
- Cloud & infrastructure
- Models
- #Eclipse Enclave
- #Kong
- #Volcano
- #GitHub Copilot
- #Azure DevOps
- #OpenAI
- #Codex
- #GPT-Live
- #OVHcloud
- #Tencent Hy4
- #Claude Code
- #Zed
On November 19 and 20, 2026, the news for developers was less about new agents than about where they run: in a sandbox, on an agent cloud, on Azure DevOps repositories or on European GPUs. Here is what shipped. Unless stated otherwise, figures are the vendors’ own.
Eclipse Enclave 1.0: a vendor-neutral sandbox for coding agents
The Eclipse Foundation released Eclipse Enclave 1.0 on November 19 (Eclipse Foundation). It is an open source runtime and sandbox that runs each agent session in an isolated container, with defined access to files, networks and development resources. It supports Claude Code, Codex, OpenCode and other agents. According to the announcement:
- several agents can work in parallel on separate tasks, and sessions can be resumed without losing progress or configuration;
- access to external services can be restricted, with mechanisms that protect the API keys and OAuth tokens agents use;
- the code comes from EclipseSource, which built it for its own teams, and is released under the MIT license at enclave.eclipse.dev.
Kong launches Volcano, an agent cloud that fixes its own bugs
Kong announced Volcano on November 19 (Volcano). The platform hosts applications, agents and data storage, and can be driven from Cursor, Codex, Claude Code or an online builder. Once the code runs there, Volcano “continuously” looks for issues and proposes fixes, “with no human intervention” according to Kong. The announcement gives no prices.
GitHub: the Copilot app works on Azure DevOps repositories
Microsoft opened a public preview of the Azure DevOps integration in the GitHub Copilot app on November 19 (Azure DevOps Blog). Agents can now create branches, change code, commit and open pull requests on Azure Repos repositories, and Agent Merge can follow a pull request, address review comments, fix CI failures and merge it when it is ready. The integration is switched on under Settings > Experimental; work items and Projects support are planned.
The same day, GitHub updated the new pull request Overview page, in public preview since November 5: failed optional checks no longer make a mergeable pull request look blocked, and comments that mention Copilot now show the action and the selected model before you submit (GitHub). Red Hat Enterprise Linux 9 and 10 images for larger runners are now generally available on GitHub Team and Enterprise Cloud (GitHub).
OpenAI: Codex agents that chase ChatGPT slowdowns, and GPT-Live-1.1
OpenAI described its Performance Factory on November 19 (OpenAI). When a performance alert fires, its Regression Workflow opens a task; a Codex agent investigates, records its findings and proposes a fix that an engineer reviews; after deployment, another agent checks that performance is back to baseline. In just over three months, the workflow tracked more than 1,700 investigations and found the root cause in more than 600 cases, about 17 automated investigations a day. Engineers still review and merge the fixes; OpenAI says it is exploring whether agents can do that too.
In its API, OpenAI released GPT-Live-1.1 on November 19, a full-duplex voice model that transcribes more accurately and keeps a more consistent accent across languages than GPT-Live-1 (API changelog). It is billed $0.05 per active minute and $0.02 per minute on standby (model page). Standby, available for GPT-Live-1 and 1.1 over WebRTC, pauses inference after 5 to 60 seconds of silence and resumes when someone speaks (guide).
For agent builders, OpenAI also published a guide on November 19: with GPT-6.2, the Responses API drops the reasoning items that follow any edit to earlier history, so it recommends an append-only pattern; a new input_transformations field shows which reasoning items were removed and why (OpenAI guide, OpenAI Developers on X).
OVHcloud: 55 products, B300 and Rubin GPUs
At its AI Summit on November 19, OVHcloud unveiled 55 new cloud and AI products (OVHcloud):
- NVIDIA RTX 6000 Pro, Blackwell B300 and Rubin R200 GPUs in Bare Metal and Public Cloud; its data centres can supply up to 60,000 B300 or 35,000 R200 GPUs;
- AI Endpoints adds around a hundred models, including voice and image models, and real-time transcription and voice generation in more than 100 languages with Gladia;
- AI Agents hosts and monitors agents connected to nearly 480 connectors and MCP servers, with a WebAssembly sandbox that starts in two milliseconds, billed only while the agent works.
Everything is offered in Public Cloud, single-tenant Private Cloud and On-Prem, including with SecNumCloud qualification. The release gives no prices.
Tencent publishes the Hy4 weights
Tencent released the weights of Hy4, Hy4-FP8 and the pretrained Hy4 base on Hugging Face, ModelScope and GitCode on November 20 (Guandian, model card). Hy4 is a mixture-of-experts model with 770B total parameters and 49B active per token that understands text, images and video. The license is the Tencent Hy License, not Apache 2.0: a company that offers the model as a service needs a separate written license if its worldwide revenue exceeds US$50 million over 12 months, or for a product with more than 100 million monthly users; internal use is exempt (license).
New versions
- Claude Code v2.1.329 (November 19):
/tasksnow lists the session’s scheduled tasks,/loopwakeups, the goal and forks; the trust dialog says where a folder’s hooks are declared;/code-review <pr number>now reads the pull request withgh pr diff; and a bug that could reset~/.claude.jsonto defaults is fixed (notes). - Codex CLI 0.171.0 (November 20): GPT-6.2 Sol and Astra join the model catalog, with Sol as the default; the TUI workspace is on by default;
codex exec --remote <ADDR>runs non-interactive sessions on an existing app server;/rcand/remotemanage remote control (notes). - Zed 1.29.1 and 1.29.2 (November 18): a Git Panel branch mode, Claude Fable 5.2 for Anthropic BYOK users, a setting to turn off automatic agent thread titles, and an official Snap package for Linux (1.29.1, 1.29.2).
What we updated
- Claude Code page: latest version v2.1.329.
- Codex page: latest version 0.171.0 (Codex CLI).
- Zed page: latest version v1.29.2.
- New counter: up to 60,000 Blackwell B300 GPUs that OVHcloud says its data centres can supply.
Sources
- Eclipse Foundation, Eclipse Enclave 1.0 (Nov 19, 2026)
- Kong, Introducing Volcano (Nov 19, 2026)
- Microsoft, Azure DevOps integration with the GitHub Copilot app (Nov 19, 2026)
- GitHub, Improvements on the pull request overview and RHEL runner images GA (Nov 19, 2026)
- OpenAI, How OpenAI’s Performance Factory keeps ChatGPT fast (Nov 19, 2026)
- OpenAI, API changelog, GPT-Live-1.1, Managing GPT-Live sessions, Keep the prefix unchanged
- OVHcloud, OVH takes the AI turn at full speed (Nov 19, 2026)
- Guandian, Tencent Hy announces Hy4 open source (Nov 20, 2026); Tencent, Hy4 model card and license
- Anthropic, Claude Code v2.1.329 (Nov 19, 2026)
- OpenAI, Codex CLI 0.171.0 (Nov 20, 2026)
- Zed, v1.29.1 and v1.29.2 (Nov 18, 2026)
Spotted an error in this article? Report it · Our corrections policy