Skip to main content
The claude_local adapter runs Anthropic’s Claude Code CLI locally. It supports session persistence, skills injection, and structured output parsing.

Prerequisites

  • Claude Code CLI installed (claude command available)
  • ANTHROPIC_API_KEY set in the environment or agent config

Configuration Fields

FieldTypeRequiredDescription
cwdstringYesWorking directory for the agent process (absolute path; created automatically if missing when permissions allow)
modelstringNoClaude model to use (e.g. claude-opus-4-6)
promptTemplatestringNoPrompt used for all runs
envobjectNoEnvironment variables (supports secret refs)
timeoutSecnumberNoProcess timeout (0 = no timeout)
graceSecnumberNoGrace period before force-kill
maxTurnsPerRunnumberNoMax agentic turns per heartbeat
dangerouslySkipPermissionsbooleanNoSkip permission prompts (dev only)

Prompt Templates

Templates support {{variable}} substitution:
VariableValue
{{agentId}}Agent’s ID
{{companyId}}Company ID
{{runId}}Current run ID
{{agent.name}}Agent’s name
{{company.name}}Company name

Session Persistence

The adapter persists Claude Code session IDs between heartbeats. On the next wake, it resumes the existing conversation so the agent retains full context. Session resume is cwd-aware: if the agent’s working directory changed since the last run, a fresh session starts instead. If resume fails with an unknown session error, the adapter automatically retries with a fresh session.

Skills Injection

The adapter creates a temporary directory with symlinks to Paperclip skills and passes it via --add-dir. This makes skills discoverable without polluting the agent’s working directory.

Environment Test

Use the “Test Environment” button in the UI to validate the adapter config. It checks:
  • Claude CLI is installed and accessible
  • Working directory is absolute and available (auto-created if missing and permitted)
  • API key/auth mode hints (ANTHROPIC_API_KEY vs subscription login)
  • A live hello probe (claude --print - --output-format stream-json --verbose with prompt Respond with hello.) to verify CLI readiness