← back NO. #0c2072d6

NO.: #0c2072d6
Topic: AGENTS & TOOLS
Source: Claude Code Releases
Published: 2026-05-21 20:39:22
Importance: ★ 8/10 — radar 80
Original: github.com/anthropics/claude-code/releases/tag/v2.1.147

`Claude Code` `v2.1.147` adds deterministic Workflow orchestration

Deterministic multi-agent runs are now built in behind CLAUDE_CODE_WORKFLOWS=1. The release also turns /simplify into PR-focused bug review, making agent workflows easier to automate and audit.

[ KEY POINTS ]

Workflow is off by default and enabled via CLAUDE_CODE_WORKFLOWS=1; useful when ad-hoc agent chains need repeatable orchestration.
Pinned background sessions now survive idle time and restart in place for updates; long-running agent work becomes less fragile.
/simplify is now /code-review, focused on correctness bugs by effort level, with --comment for inline GitHub PR findings.
Sandbox hardening covers prototype-pollution and thenable escape paths; good signal for running agents on less-trusted repo code.
Large diff rendering, MCP pagination, PowerShell, Windows background sessions, and headless slash-command errors all got reliability fixes.

Originalgithub.com/anthropics/claude-code/releases/tag/v2.1.147Read original →

// related

#0001
#0001Agents & tools Latent Space2 hours ago
`Daytona` Pushes Bare-Metal Sandboxes for Agent Workloads
60radar
DaytonaAgent sandbox platform — bare-metal execution environments
Agent infrastructure is moving from browser-like demos to real compute sandboxes. The usage numbers are strong, but the practical takeaway is clear: reliable agent runs need isolated machines, evals, and cost discipline.
- 850K daily runs signals Daytona is past prototype traffic; sandbox reliability is becoming a real platform layer.
- 74% MoM growth points to fast demand for agent execution infra, not just chat or IDE extensions.
- Bare-metal sandboxes fit coding agents that need files, installs, tests, and long-running processes. Watch pricing before moving heavy workloads.
- RL evals plus an Agent Cloud hints at a managed loop: run agents, measure outcomes, improve policies.
Source: www.latent.space/p/daytonaRead original →
FIG-0011:1
60radar
FIG-0011:1
#0002
#0002Agents & tools Simon Willison3 hours ago
`Datasette Agent` brings conversational SQL and charts to Datasette
70radar
Datasette AgentData query AI agent — SQL and charts inside Datasette
Natural-language querying now lands inside existing SQLite-backed Datasette apps. Useful for lightweight admin analytics without building a custom BI layer.
- Datasette Agent answers questions over data stored in Datasette, turning prompts into SQLite queries and responses.
- The datasette-agent-charts plugin adds chart generation, making quick visual exploration possible without a separate dashboard stack.
- The live demo runs on Gemini 3.1 Flash-Lite: cheap and fast is enough for many SQL-writing agent workloads.
Source: simonwillison.net/2026/May/21/datasette-agent/#atom-everRead original →
FIG-0021:1
70radar
FIG-0021:1
#0003
#0003Agents & tools Simon Willison4 hours ago
`datasette-agent-sprites` `0.1a0` runs agent commands in `Fly Sprites`
40radar
datasette-agent-spritesDatasette Agent plugin — runs commands in Fly sandboxes
Agent command execution moves into an isolated sandbox. Early alpha, but useful if you are exposing database-adjacent tools to LLM agents.
- datasette-agent-sprites is a Datasette Agent plugin for running commands inside a Fly Sprites sandbox.
- The release is 0.1a0, so treat it as experimental rather than production-ready infrastructure.
- The practical signal is sandboxed agent execution: useful for reducing blast radius when agents run shell commands.
Source: simonwillison.net/2026/May/21/datasette-agent-sprites/#aRead original →
40radar
PHOTO
FIG-0031:1

`Claude Code` `v2.1.147` adds deterministic Workflow orchestration

// related

`Daytona` Pushes Bare-Metal Sandboxes for Agent Workloads

`Datasette Agent` brings conversational SQL and charts to Datasette

`datasette-agent-sprites` `0.1a0` runs agent commands in `Fly Sprites`