Stand up claude self-hosted-runner and enable cross-session SendMessage
Use v2.1.224’s self-hosted runner so Team/Enterprise web, mobile, and desktop sessions run on your machines, then wire cross-session SendMessage/ListAgents and crossSessionInbound approval for multi-machine agent handoffs.
Why this loop
This release adds claude self-hosted-runner for Team and Enterprise, turning your own machines or containers into execution targets for Claude Code web, mobile, and desktop sessions. It also adds cross-session SendMessage and ListAgents (macOS/Linux) so sessions can discover and message each other across machines, plus crossSessionInbound and dialogExpiry so inbound messages to bypassed-permission sessions are held for approval while other sessions auto-deliver. Together these replace ad-hoc “which box is the agent on?” workflows with controlled, multi-surface runners and explicit cross-session routing—especially valuable when sandbox credential-masking and permission bypasses are already in play.
Proposed actions
- On a Team/Enterprise machine or container you control, run: claude self-hosted-runner (register it as a target for Claude Code web, mobile, and desktop sessions)
- In Claude Code settings used by long-lived agents, set crossSessionInbound and dialogExpiry so messages into bypassed-permission sessions require approval and other inbound messages auto-deliver with a defined expiry
- From a macOS or Linux Claude Code session, run ListAgents to discover peers on your machines, then use cross-session SendMessage to hand off tasks to a specific agent inbox and confirm failed deliveries error instead of false “Message sent”
- For internal plugins distributed without git/npm, install via the archive source (zip over HTTPS) and pin the optional SHA-256 so every runner pulls the same artifact
- If you use Bedrock, export ANTHROPIC_BEDROCK_REGION_PREFIX to the preferred cross-region inference profile prefix so self-hosted and local sessions do not silently follow AWS_REGION alone
Agent prompt
Paste into your agent or query via MCP (`get_agent_prompt`) — free, no extra AI costPaste into Claude Code / CLAUDE.md task
# DevAgentRadar → Claude Code You are helping me adopt a real coding-assistant change. Work only from the facts below. Do not invent features. ## Context Assistant: Claude Code Proposal: Stand up claude self-hosted-runner and enable cross-session SendMessage Summary: Use v2.1.224’s self-hosted runner so Team/Enterprise web, mobile, and desktop sessions run on your machines, then wire cross-session SendMessage/ListAgents and crossSessionInbound approval for multi-machine agent handoffs. Primary source: https://github.com/anthropics/claude-code/releases/tag/v2.1.224 ## Why it matters This release adds claude self-hosted-runner for Team and Enterprise, turning your own machines or containers into execution targets for Claude Code web, mobile, and desktop sessions. It also adds cross-session SendMessage and ListAgents (macOS/Linux) so sessions can discover and message each other across machines, plus crossSessionInbound and dialogExpiry so inbound messages to bypassed-permission sessions are held for approval while other sessions auto-deliver. Together these replace ad-hoc “which box is the agent on?” workflows with controlled, multi-surface runners and explicit cross-session routing—especially valuable when sandbox credential-masking and permission bypasses are already in play. ## Suggested actions 1. On a Team/Enterprise machine or container you control, run: claude self-hosted-runner (register it as a target for Claude Code web, mobile, and desktop sessions) 2. In Claude Code settings used by long-lived agents, set crossSessionInbound and dialogExpiry so messages into bypassed-permission sessions require approval and other inbound messages auto-deliver with a defined expiry 3. From a macOS or Linux Claude Code session, run ListAgents to discover peers on your machines, then use cross-session SendMessage to hand off tasks to a specific agent inbox and confirm failed deliveries error instead of false “Message sent” 4. For internal plugins distributed without git/npm, install via the archive source (zip over HTTPS) and pin the optional SHA-256 so every runner pulls the same artifact 5. If you use Bedrock, export ANTHROPIC_BEDROCK_REGION_PREFIX to the preferred cross-region inference profile prefix so self-hosted and local sessions do not silently follow AWS_REGION alone ## Config surfaces this release may change - sandbox settings **(high confidence)** — check your repo before applying - context and compaction settings **(high confidence)** — check your repo before applying - agent context files **(high confidence)** — check your repo before applying - background and headless runs **(high confidence)** — check your repo before applying - skills — check your repo before applying - permission rules — check your repo before applying ## Your job 1. Restate the change in one sentence. 2. Propose a minimal plan for my repo (or a throwaway pilot). 3. Implement only what I approve; prefer small diffs and tests. 4. Call out risks (permissions, breaking APIs, cost). Start by confirming you understood the proposal.
Your loop
This browser · no sign-in · not shared as “you”Community signal · 0 approved · 0 deferred · 0 ignored
Anonymous public tally (one vote per visitor; changing choice updates your vote). Not moderated product truth.