From the Inside Claude Code - The Claude Code Ecosystem architecture map
Spend and run length are bounded at the transport
strength · low · verified
max_budget_usd, task_budget and max_turns are passed to the CLI as flags, and Control Protocol Query bounds how long stdin stays open between turns with a 10-minute ceiling (CLAUDE_CODE_PRINT_BG_WAIT_CEILING_MS), so a background agent that never reports idle cannot hold a session open indefinitely.
These limits are enforced by the CLI, so they hold even when the embedding code forgets to stop iterating. The SDK does not check them itself.
The trail
Open on the mapMore from this board
- Optional SessionStore methods raise instead of being absent, so a change in Types reaches 13 modules
- The Lowerer is one struct spread over 38 files and 29,700 lines with no unit tests
- Day 1: start with marketplace.json, the contract everything else serves
- Every SDK module imports its exceptions from one file, _errors.py
- Partner MCP plugins launch unpinned packages on every user's machine
- PR-controlled agent config is restored from the base branch before Claude starts
- Control-protocol failures escape the SDK exception hierarchy
- Both public entry points share one control-protocol engine
- The triage and dedupe agents are boxed in identity, tools and network
- Label decisions by the triage agent leave no reason a maintainer can see
- The subprocess transport carries five responsibilities in one file
- Command-line construction is hardened against argument injection
- Every agent-driven closure has a human override before it happens
- Skip for now: config-only integrations, CI plumbing and single-file plugins
- External-PR workflows never execute contributor code
- Channel servers keep bot tokens owner-only and refuse injected pairing requests