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

👀22

🔥82

Vercel Security Review Enters Public Beta: Vulnerability Review on Every GitHub Push, One-Click Fixes with Vercel Agent

On November 3 (US Pacific time), Vercel launched Security Review in public beta. It is a new Vercel Agent capability alongside Code Review and Investigation: once enabled, every push to connected GitHub repositories triggers a diff-only vulnerability review that finishes in seconds. Findings land in the Security dashboard, PR comments and the CLI, and can be fixed with one click by Vercel Agent or pulled into your own coding agent via vercel security vulnerabilities. It is available to Pro and Enterprise teams, and reviews are free until November 10.

Key Takeaways

Trigger: every GitHub push (including direct pushes to production) is reviewed automatically; only the diff is scanned, which Vercel says finishes in seconds, so it can run on every preview and production deployment
Beyond pattern matching: the agent traces how changed code is reached, checks existing protections and rechecks each finding, which Vercel says catches logic flaws such as missing authorization checks
Teams can write security policies in plain language, scoped to projects or the whole team, and manage them with vercel security policy
Pricing: Vercel Agent rate, model tokens at provider cost with no markup, plus $0.25 per million tokens; reviews are free until November 10, 2026, while Agent fixes are billed
Availability: public beta for Pro and Enterprise teams; Vercel has not published detection-rate or false-positive benchmarks

Read full story

Linked Models & Agents:

🤖 Vercel Agent 🤖 Claude Code 🤖 Codex 🤖 v0 by Vercel 🌐 Vercel 🌐 GitHub

#Vercel#Security Review#Vercel Agent#vulnerability scanning#AppSec#code review#public beta

ClaudeDevs@ClaudeDevs·Collected 1d ago

👀27

🔥86

View on 𝕏 ↗

Anthropic Launches Message Threads in Public Beta on the Messages API: Server-Side Conversations Cut Claude Code TTFT About 35% on 500K-1M Token Requests

On November 2 (US time) Anthropic put message threads into public beta on the Messages API (beta header message-threads-2026-08-12). The API keeps the conversation on the server: the first request sends the full conversation and creates a thread, and each later request sends only new messages plus the previous response id. Anthropic says threads are on by default for most Claude Code users, cutting median time to first token by about 35% on 500K-1M token requests, while the median long-conversation request shrank from about 800 KB to 1.8 KB. Threads expire after 5 idle minutes; pricing and rate limits are unchanged.

Key Takeaways

Per Anthropic, median time to first token on 500K-1M token Claude Code requests is about 35% lower.
The median long-conversation request fell from about 800 KB to about 1.8 KB, since each turn uploads only new messages plus previous_message_id.
A thread expires 5 minutes after its last request and is deleted within 1 hour; an expired thread returns 404 thread_not_found and must be replayed in full.
Pricing and rate limits are unchanged; Message Batches, token counting and on-demand compaction are unsupported, and threads are not ZDR or HIPAA eligible.
Available on the Claude API, Claude Platform on AWS, Google Cloud (Anthropic managed) and Microsoft Foundry, with a thread helper in the SDKs.

Read full story

Linked Models & Agents:

🤖 Claude Code 🌐 Anthropic

#Anthropic#Claude API#Messages API#message threads#Claude Code#Latency#Agents

Claude Devs@ClaudeDevs·Collected 20d ago

👀92

🔥88

View on 𝕏 ↗

Claude Platform opens OpenTelemetry tracing beta: Messages API, Managed Agents and SDK spans flow to your own observability stack

On 2026-10-14 Anthropic put OpenTelemetry tracing for Claude Platform into public beta. Admins add a telemetry destination in the Claude Console and the API exports spans for Messages API requests and Managed Agents sessions server-side with no code changes, while the Claude SDKs export client-side spans for requests and tool-runner tools. Spans follow the OpenTelemetry gen_ai conventions and default to metadata (duration, status, token counts, model, tool names), with an optional full-content mode.

Key Takeaways

Two paths: a server-side destination via Console/Admin API (Messages API + Managed Agents, no code changes) or client-side spans from the Claude SDK (overview)
Destinations need OTLP/HTTP with protobuf over HTTPS on port 443; the Admin API uses the anthropic-beta: telemetry-destinations-2026-08-11 header (API guide)
SDK tracing covers Python, TypeScript, Go and Java (anthropic-java 2.72.0+), and runs on Claude API, AWS, Bedrock, Google Cloud and Microsoft Foundry, all in beta (SDK guide)
Metadata-only or full-content modes; ZDR customers can still export full content for Messages API requests (held in memory until delivered); Managed Agents is not ZDR-eligible
Anthropic warns span names and SDK options may change during the beta, so pin SDK versions

Read full story

Linked Models & Agents:

🤖 claude-managed-agents 🤖 claude-agent-sdk 🌐 Anthropic 🌐 datadog 🌐 grafana 🌐 honeycomb 🌐 langfuse

#Anthropic#Claude Platform#OpenTelemetry#Managed Agents#Claude SDK

TestingCatalog Newstestingcatalog·Collected 26d ago

👀158

🔥88

View on 𝕏 ↗

Claude Managed Agents dynamic workflows hit public beta: the lead agent writes an orchestration program running up to 64 concurrent threads and 1,000 agents per run

Anthropic expanded dynamic workflows in Claude Managed Agents to public beta. With workflows enabled in an agent's multiagent block, Claude writes a workflow program that runs many agents in background phases and combines their results, aimed at audits, migrations, deep research and cross-checking.

Key Takeaways

Enable with multiagent.type: "multiagent_20261001" and workflows: {"type":"enabled"} under the managed-agents-2026-04-01 beta header
Up to 64 threads working at once per run and 1,000 agents over a run's life (thread_limit_error beyond)
Runs last 24h by default; 10 open runs per session by default; runs don't nest
No separate run price: thread tokens bill at model rates and count toward the session budget, which pauses runs when reached

Read full story

Linked Models & Agents:

⚡ Claude🤖 Claude Managed Agents 🌐 Anthropic

#Anthropic#Managed Agents

OpenAI@OpenAI·Collected 28d ago

👀159

🔥87

OpenAI opens the Decisions API public beta: POST /v1/decisions on gpt-6-luna returns typed predicate, choice and score answers ~10x faster than the Responses API, billed only for input at $0.10 per 1M tokens

Per the OpenAI API changelog, the Decisions API entered public beta on 2026-10-06 with gpt-6-luna: a dedicated POST /v1/decisions endpoint takes text/images plus a list of questions and returns typed predicate, choice or score answers with probabilities, about 10x faster than the Responses API. Billing is input-only at $0.10 per 1M tokens (no output or cache charges); ZDR and HIPAA are supported and GA is expected within weeks.

Key Takeaways

Speed: typed answers about 10x faster than the Responses API (Decisions guide)
Price: input-only $0.10 per 1M tokens, no output or cache read/write fees; regular gpt-6-luna is $0.10 in / $0.50 out
3 question types: predicate (0–1 probability), choice (value + probabilities + confidence), score (probability-weighted ordinal level)
Compliance: ZDR and HIPAA eligible, US and Europe (EEA + Switzerland) data residency; GA expected in weeks
Limits: gpt-6-luna only; images must be inline base64, no hosted URLs or file_id

Read full story

Linked Models & Agents:

⚡ GPT-6 Luna 🌐 OpenAI

#OpenAI#Decisions API#Gpt 6 luna#Classification#Routing#Agents#API

Anthropic@AnthropicAI·Collected 29d ago

👀142

🔥88

Anthropic opens Claude for Google Workspace public beta: a Docs/Sheets/Slides sidebar that edits files in place, plus new Google file connectors inside Claude

On 2026-10-06 Anthropic put Claude for Google Workspace into public beta on every paid plan. One Marketplace install adds a Claude sidebar to Docs, Sheets and Slides that reads the open file and selection and edits in place, with an 'Ask before edits' approval mode by default and an 'Accept all edits' mode. New Docs/Sheets/Slides connectors (beta) let Claude create and live-edit Google files from chat, scoped to existing Google sharing permissions.

Key Takeaways

Coverage: one install spans 3 apps (Docs, Sheets, Slides) on all 4 paid tiers (Pro, Max, Team, Enterprise)
Sheets: formulas, pivot tables, native charts, new tabs; joins and cleaning run through Python and write back
Limits: a single long operation stops after ~6 minutes (Google limit); no Firefox; closing the sidebar stops the task
Enterprise: Compliance API, CMEK and OpenTelemetry audit export apply; third-party inference (Bedrock, Vertex, Azure Foundry, LLM gateways) not supported in this beta
Benchmarks: Anthropic published no quantitative scores

Read full story

Linked Models & Agents:

⚡ Claude🤖 Claude for Google Workspace 🌐 Anthropic 🌐 Google

#Anthropic#Claude#Google Workspace#Google Docs#Google Sheets#Google Slides#Connectors#Office agent#Beta

ClaudeDevs@ClaudeDevs·Collected 48d ago

👀128

🔥88

View on 𝕏 ↗

Claude Code Projects opens to every Pro and Max user on the waitlist: one conversation coordinating parallel cloud threads

On Oct 9 ClaudeDevs said every Pro and Max user on the Claude Code Projects waitlist has been let in. A project is a long-running coordinator conversation that spins each task into its own thread, usually a parallel cloud session on its own branch that opens a PR when needed; threads can also run locally via Remote Control. Still public beta; not yet on Team or Enterprise.

Key Takeaways

From Oct 9, every Pro/Max user on the waitlist has access; still public beta, not on Team/Enterprise.
A project is one coordinator conversation plus N threads, each with its own context window; cloud threads work on their own branch and open PRs.
Since Sep 23, threads can run on your own machine via Remote Control when a task needs local tools.
New threads inherit project instructions and memory, each repo's CLAUDE.md and skills, and your claude.ai connectors.
Projects draw on the same plan limits as other Claude Code sessions and use them faster; no benchmarks were published.

Read full story

Linked Models & Agents:

🤖 Claude Code 🌐 Anthropic

#Claude Code#Projects#Anthropic

Zed@zeddotdev·Collected 48d ago

👀101

🔥94

View on 𝕏 ↗

Zed Delta Public Beta: Multiplayer Agent Coding With Changes Tied to Conversation Threads

Zed launched Delta into public beta: a multiplayer environment for coding with agents and reviewing what they build, with every code change linked to the conversation that produced it. Downloads are available today for macOS, Linux, and Windows. Zed has already stopped opening GitHub PRs on the Delta repo and lands changes with Delta itself via guided review and /land.

Key Takeaways

Public beta: download for macOS, Linux, and Windows from delta.dev for multiplayer agent coding and review
Threads as the unit of work: every change links to the conversation that produced it; DeltaDB records in-between edits and discussion
Dogfooding: Delta repo no longer uses GitHub PRs; guided review then /land squash, CI, and land with approval

Read full story

Linked Models & Agents:

🌐 zed

#Zed#Delta#DeltaDB#Agents#code review#public beta#Multiplayer

Marwan Atef@Marwan_3atef·Collected 57d ago

👀48

🔥85

View on 𝕏 ↗

Supernova ships Editor MCP public beta: one URL lets Cursor, Claude, and Codex write design systems

Marwan Atef (@Marwan_3atef) reported Supernova shipping Editor MCP in public beta (free for now): after sign-in and picking a design system, one URL at mcp.supernova.io/mcp lets Cursor, Claude, and Codex edit docs, tokens, components, skills, and pipelines—not just read them. The company blog frames write access as the first real agentic design-system step beyond read-only MCP.

Key Takeaways

Editor MCP public beta via one URL at mcp.supernova.io/mcp.
Cursor, Claude, and Codex can write docs, tokens, components, skills, and pipelines.
Free for now; framed as the step from read-only MCP to writable design systems.

Read full story

Linked Models & Agents:

🤖 Claude Code (Anthropic)🤖 openai-codex

#Supernova#Editor MCP#design system#Cursor#Claude#Codex

LangChain@LangChain·Collected 66d ago

👀32

🔥88

View on 𝕏 ↗

LangChain Launches Managed Deep Agents Public Beta with Scaffold CLI, Hosted Infra, and Harbor Evals

LangChain opened the public beta for Managed Deep Agents, providing CLI scaffolding, LangSmith-managed infrastructure sandboxes, and integrated Harbor behavioral evaluations.

Key Takeaways

Agent PaaS model matures: packages scaffolding, isolated sandboxes, and behavioral evals into a unified deployment flow;
LangSmith expands into the production control plane managing long-horizon agent runtimes and state;
Harbor evaluation suite embeds into CI/CD pipelines to enforce automated behavioral quality gates before release.

Read full story

Linked Models & Agents:

⚡ Claude 3.7 Sonnet (Hybrid Reasoning)

Claude@claudeai·Collected 66d ago

👀29

🔥91

View on 𝕏 ↗

Claude Security Public Beta: Mythos 5 Scans GitHub Repos, Patches Open in Claude Code

Anthropic moved Claude Security scans onto Claude Mythos 5, now in public beta for all Claude Enterprise customers. Point it at a GitHub repo and Mythos traces data across files, returning CWE, confidence, severity, and a suggested fix that opens in Claude Code on the web.

Key Takeaways

No separate Mythos 5 access required: the model runs behind the scan and bills as standard plan tokens
Findings include CWE, confidence, and severity; suggested patches open in Claude Code on the web
Paired with a $35M Defender Advantage Fund for open-source security and an expanded Cyber Verification Program

Read full story

Linked Models & Agents:

⚡ Claude Mythos 5 ⚡ Claude Opus 5 🤖 Claude Code (Anthropic)🌐 Anthropic

#Claude Security#Mythos 5#Claude Code#CWE#Enterprise

Cursor@cursor_ai·Collected 66d ago

👀47

🔥96

View on 𝕏 ↗

Cursor Origin code-hosting platform goes live with GitHub repo sync and native Vercel integration

Cursor launched Origin, its dedicated code-hosting platform, into public beta. Tightly integrated with Cursor IDE, Origin allows developers to sync repositories seamlessly from GitHub and ships with day-one ecosystem integrations for Vercel, Buildkite, and Depot for AI-native deployment.

Key Takeaways

Cursor launches Origin as an AI-native Git hosting platform tailored for agentic multi-branch flows.
Supports two-way continuous synchronization with existing GitHub repositories.
Day-one CI/CD integrations with Vercel, Buildkite, and Depot for instant automated deploys.

Read full story

Linked Models & Agents:

🤖 Cursor Composer (Agent Mode)🌐 Cursor (Anysphere)

#Cursor#Cursor origin#Git hosting#Vercel#Buildkite#Developer tools