feat: add argent server start for long-lived tool-server

[filip131311]

Human summary:

This adds argent server start command to enable us to spawn tools server in arbitrary location. we want this to enable using remote tools-server via our mcp not only local ones.

Summary

• Adds argent server start to spawn a tool-server that does not auto-shutdown on idle, with configurable bind port and host — the missing piece for running tool-server on a remote/dedicated host.
• Foreground by default so process supervisors (systemd, Docker, supervisord) own the lifecycle; --detach keeps the existing daemon-spawn behavior. Refuses to clobber a healthy running server unless --force.
• Phase 2 (consumer-side --tools-url flag pointing the MCP / CLI at a remote tool-server) is now a one-flag change away — tools-client.ts and mcp-server.ts already honor ARGENT_TOOLS_URL. Out of scope for this PR.

What changed

• tool-server — read HOST env var (default 127.0.0.1 so the existing auto-spawn path is unaffected), bind to it, attach an error listener on app.listen so EADDRINUSE / EACCES exit cleanly instead of routing through uncaughtException.
• argent-tools-client — broaden the readiness regex to match any host; extend buildToolsServerEnv with optional { host, idleTimeoutMinutes }; record host in ~/.argent/tool-server.json (backward-compat: missing field defaults to 127.0.0.1); export spawnToolsServer, findFreePort, isToolsServerHealthy, isToolsServerProcessAlive, the state read/write/clear helpers, and formatToolsServerUrl so the CLI can reuse them.
• argent-cli — new server start [flags]: --port/-p (default 3001, 0 = pick free), --host (default 127.0.0.1), --idle-timeout (default 0 = never), --detach/-d, --force, --help. Warns when host is non-loopback. Foreground mode forwards SIGINT/SIGTERM to the child and writes the state file so local argent run / argent mcp can attach.
• argent dispatcher — pass BUNDLED_RUNTIME_PATHS to server() so the new subcommand can find the bundled tool-server.

Test plan

• argent server --help lists the new start subcommand
• argent server start --help shows full flag reference
• argent server start --detach --port 0 → status alive/healthy, /tools reachable, state file populated with host field
• Second argent server start --detach refuses (exit 1) with helpful message
• argent server start --detach --force kills the old PID and starts a new one
• Foreground argent server start --port 0 runs with inherited stdio; child PID is the actual tool-server (not the wrapper); argent server stop from a sibling shell tears down both
• Existing auto-spawn path (argent tools) still works — verifies the regex broadening + default-host change is backward-compatible
• tool-server (444 tests) + argent-tools-client (1) + argent dispatcher (1) suites pass
• Manual smoke on --host 0.0.0.0 — could not exercise locally (sandbox declined the public-interface bind); the warning + bind path is identical to loopback besides the listen address

[pFornagiel]

I would change both the PORT and HOST env varibales in all the code references to ARGENT_HOST and ARGENT_PORT. There is a chance someone will have defined HOST env variable in their shell and this will cause hard-to-reproduce problems.

[pFornagiel]

Tiny NIT, because it is only user-facing, but if host is ipv6 the authority part should be written in square brackets like this:

http://[::1]:3001

[pFornagiel]

The writeToolServerState is asynchronous, so there could be a situation when:

• parent spawns child tool-server
• parent starts async writeToolsServerState, which is not awaited
• child may exit quickly (bind fail for example)
• exit handler runs and only clears state if stateWritten === true
• if write resolves after exit handler, stale state file remains, which can cause agent confusion as the data will be referencing a server that has failed at startup

or it may be fine, hard to tell, but this seems like a real edge-case

[pFornagiel]

Taking it from here