AI Coding Live News — Real-Time 𝕏/Twitter Updates & Breakthroughs

Microsoft Developermsdev·Collected 5d ago

👀33

🔥84

Microsoft opens the GitHub-built Copilot harness in Foundry Agent Service: public preview, 20+ frontier models plus BYOK, billing from Dec 1

During GitHub Universe on Oct 28, Microsoft put the Microsoft Copilot harness, the shared agent execution layer behind Copilot Code, Copilot Studio, the GitHub Copilot app, the CLI and VS Code, into Foundry Agent Service as a public preview. Microsoft runs the agent loop and sandbox while developers supply instructions, skills, tools and model choice; Microsoft says it works across 20+ frontier models plus bring-your-own-key. Long-running resilience for hosted agents also reached GA. Harness runtime usage is free until Dec 1.

Key Takeaways

Microsoft says the harness spans 20+ frontier models plus bring-your-own-key, so you can swap models without rewriting orchestration (official blog)
Preview building blocks: reusable skills, Foundry and MCP tools with explicit auth and approvals, file and code execution with built-in subagent delegation, and source-controlled agent definitions
Pricing: harness runtime is free until Dec 1; after that sandbox compute is USD 0.0994 per vCPU-hour and 0.0118 per GiB-hour, with model inference billed separately (Foundry blog)
Long-running resilience for hosted agents went GA the same week: interrupted work restarts with its original input, and your app saves checkpoints
Limits: you pick the harness only when creating a new agent; existing agents are unchanged and switching later is not supported yet

Read full story

Linked Models & Agents:

🤖 Microsoft Copilot harness 🤖 Foundry Agent Service 🤖 GitHub Copilot 🤖 Copilot Studio 🌐 Microsoft 🌐 GitHub

#Microsoft#Foundry#Copilot harness#agent runtime#MCP#agent skills#GitHub Universe

Microsoft / Hugging Face@Microsoft·Collected 31d ago

👀129

🔥96

Microsoft×Hugging Face open ThinkingBox: 507 stateful workflows graded on backend state, not chat endings

On 2026-10-03, Microsoft Copilot Studio and Hugging Face released ThinkingBox plus ThinkingBox-Bench (507 tasks × 20 trials): isolated MCP sessions graded by executable terminal-state/side-effect checks, wired into OpenEnv. Vendor board: Claude Opus 5.5 67.16% pass@1; Kimi-K3 93.89% pass@20 but only 13.41% all-20 — one success ≠ reliability. MIT framework microsoft/thinkingbox; CDLA data microsoft/thinkingbox-data; paper arXiv:2608.19741.

Key Takeaways

Sources: HF blog 2026-10-03, OpenEnv docs, microsoft/thinkingbox (MIT), thinkingbox-data (CDLA), arXiv:2608.19741
507 stateful business workflows × 20 isolated MCP trials each
Grade terminal DB/side effects; ~67% of failing traces still terminate cleanly after a mutating tool
Opus 5.5 67.16% pass@1; Kimi-K3 broadest pass@20 (93.89%) but 13.41% all-20; GPT-5.4 ~$6.80/dependable task
Run: OpenEnv + [email protected] → Typesense + MCP proxy → thinkingbox-eval

Read full story

Linked Models & Agents:

⚡ Claude Opus 5.5 ⚡ Claude Opus 5 ⚡ GPT-5.4 ⚡ GPT-6 Astra ⚡ Kimi K3 🤖 ThinkingBox 🤖 OpenEnv 🤖 MCP agents 🌐 Microsoft 🌐 Hugging Face

#Thinkingbox#Microsoft#Huggingface#Openenv#MCP#Agent eval#Benchmark#Reliability

白

白日梦想家@timliu92·Collected 52d ago

👀64

🔥88

View on 𝕏 ↗

Microsoft open-sources Skill Recorder: record a desktop workflow once, Copilot CLI rebuilds a reusable Skill/Automation

Community coverage notes Microsoft open-sourced Skill Recorder (github.com/microsoft/skill-recorder, ~3.9k stars). After a local screen/activity capture, GitHub Copilot CLI reconstructs an intent plus ordered steps, then builds a SKILL.md Skill or schedulable Automation for Microsoft Scout, Copilot Cowork, and Copilot Studio—preferring native agent tools (gh, web_fetch) over click replay.

Key Takeaways

Microsoft open-sourced Skill Recorder (microsoft/skill-recorder), ~3.9k GitHub stars.
Local capture → Copilot CLI reconstructs intent + steps → Skill (SKILL.md) or Automation.
Targets Scout / Copilot Cowork / Copilot Studio; prefers native tools over click replay.

Read full story

Linked Models & Agents:

🤖 GitHub Copilot (Agent Mode / Codex)🌐 Microsoft Azure AI 🌐 github

#Microsoft#Skill Recorder#GitHub Copilot CLI#SKILL.md#Automation#Scout#Copilot Cowork#Copilot Studio

Marwan Atef@Marwan_3atef·Collected 59d ago

👀55

🔥93

View on 𝕏 ↗

Azure DevOps Remote MCP is GA: hosted streamable-HTTP endpoint with Entra auth, no sidecar

Microsoft announced Azure DevOps Remote MCP is generally available: a hosted streamable-HTTP endpoint at https://mcp.dev.azure.com/{org} with Entra auth and no sidecar. Drop it into mcp.json for VS Code Copilot, Foundry, Copilot Studio, and VS/CLI/apps; Claude, Cursor, and ChatGPT stay on a local bridge until Entra DCR/CIMD lands.

Key Takeaways

GA: hosted Remote MCP with streamable HTTP + Entra and no sidecar.
Connect: put mcp.dev.azure.com/{org} in mcp.json for VS Code Copilot / Foundry / Copilot Studio.
Limit: Claude / Cursor / ChatGPT still use a local bridge pending Entra DCR/CIMD.

Read full story

Linked Models & Agents:

🌐 Microsoft Azure AI

#Azure DevOps#MCP#Remote MCP#GA#Entra#VS Code Copilot#Foundry#Copilot Studio

Jeff Teper@jeffteper·Collected 59d ago

👀104

🔥93

View on 𝕏 ↗

Microsoft: GPT-6 Astra available today in Copilot Cowork and Copilot Studio

Microsoft EVP of Apps & Agents Jeff Teper says OpenAI GPT-6 Astra is rolling out today in Microsoft Copilot Cowork and Copilot Studio, with the official hub post at aka.ms/AstraInCopilot. Teams and custom agents can use the frontier model inside Microsoft’s Copilot stack.

Key Takeaways

Microsoft EVP Jeff Teper confirms GPT-6 Astra is live today in Copilot Cowork and Copilot Studio.
Official landing page: aka.ms/AstraInCopilot (Microsoft Community Hub).
Frontier model access for teams and Copilot Studio custom agents.

Read full story

Linked Models & Agents:

⚡ GPT-6 Astra 🌐 Microsoft Azure AI 🌐 OpenAI

#GPT-6 Astra#Microsoft Copilot#Copilot Cowork#Copilot Studio#Jeff Teper#OpenAI