Tag
26 posts tagged Internals.
Our own floor was under reporting what it cost by 59 percent. The counter was cumulative since process start, the app restarts, and the session id stayed the same. Here is how a monotonic invariant let us recover the real number from an append-only log.
A cmd.exe parsing rule from the 1980s meant Windows agents received exactly one line of their multi-line startup protocol — and nothing errored. The anatomy of our worst silent failure, and the fix.
Munder Difflin shipped auto-update in v0.3.4 and it silently never worked in a single packaged build. The cause was one destructuring assignment across the CommonJS/ESM boundary — and a catch block that threw the evidence away. Here's how we found it, and what v0.3.7 changes.
A shareable agent-config manifest is attacker input. How Munder Difflin's import pipeline stays inert: no auto-spawn, default-deny flags, and an SSRF-safe bounded fetch.
A comprehensive guide to every change in Munder Difflin v0.2.4 — how the Codex lifecycle-hook bridge achieves full hive parity, what the Schedules tab adds, why tunnelmole replaced localtunnel, and what else shipped.
How and why to compress an agent's long-term memory: the toolbox, the lossy trap, and keeping a lossless original beside a compact copy.
How to run autonomous AI agents safely: permission modes and the bypassPermissions foot-gun, workspace isolation, and what to gate vs. allow.
A walkthrough of the multi-agent harness architecture: a node-pty terminal plane and a hooks/hive event plane feeding one React + Pixi.js renderer.
Agents fail constantly: tools error, steps stall, output goes wrong. Reliability isn't avoiding failure — it's making each one contained and recoverable.
Why a local agent hive coordinates through plain files, not Redis or RabbitMQ: the zero-ops wins, the real tradeoffs, and where files hit a ceiling.
How to approve what AI agents do without a parallel approval queue: native permission prompts, routing 'to: human' to the orchestrator, remote approval.
How local-first AI agent orchestration works under the hood — the loop, mailboxes, scheduler, and audit log that coordinate a hive on one machine.
Agent fleet observability: the four questions your dashboard must answer about who's working, what they're doing, what it costs, and what they know.
How multi-agent systems survive partial failure: retry with stale-lock recovery, poison-message quarantine, hop-cap circuit breaking, idempotent handling.
How a tiny shim bridges Claude Code's lifecycle hooks to one live process over a Unix socket, turning per-event hooks into a telemetry and control channel.
When do AI agents need a protocol like MCP or A2A? Agents you own coordinate fine with file mailboxes; protocols earn their keep across boundaries.
Wire xterm.js to a node-pty backend: stream output, write keystrokes back, handle resize, and keep many live terminals fast with a terminal pool.
The game-dev techniques behind a dev tool's office floor: Tiled maps, BFS pathfinding, sprite recoloring, and flying message envelopes in Pixi.js.
A practical tour of Claude Code hooks — the PreToolUse, PostToolUse, and Stop lifecycle — and how a Unix-socket hook shim drives a live office floor.
How to run byte-for-byte authentic shells inside Electron with node-pty: the native-rebuild gotcha, the macOS PATH trap, and streaming PTY output over IPC.
xterm.js performance for many live PTYs: a terminal pool, render-only-visible, smart scrollback, and accelerated rendering to stream dozens at once.
Parallel agents corrupt a repo with index.lock races. The single-committer pattern — agents write, one process commits — fixes concurrent git writes.
How we render AI agents as avatars on a Pixi.js office floor — driven by real hook and message events, with seat assignment, pathing, and flying envelopes.
How an append-only event log makes a multi-agent system debuggable and replayable: what to record, and why one JSON line per event beats a database.
Can Claude Code agents talk to each other? Yes — the outbox-router-inbox design that lets agents message safely using plain files and atomic renames.
A deep dive into the Claude Code orchestrator: how a GOD agent reads requests, routes work, adjudicates routine traffic, and escalates the critical few.
