an open-source alternative to the dots, bots and muses of the world, run an office of claude code/codex like agents on your laptop, sandboxes or anywhere, uses your existing subscriptions
HTML agent-harnessagent-orchestrationagentsai-agentsautonomous-agentsclaude-codecodexcoding-agentsdesktop-appdeveloper-toolselectrongemini-cliharnessharness-engineeringlocal-firstmemorymulti-agentopencodeorchestrationtypescript
release(v0.3.8): usage-limit aware delivery, triggers hub, readable git history
Chaitanya Giri20031d0dd8ae
diff --git a/CHANGELOG.md b/CHANGELOG.mdindex f5e674af..825e7f7a 100644--- a/CHANGELOG.md+++ b/CHANGELOG.md@@ -4,6 +4,73 @@ All notable changes to this project are documented here. The format is based on[Keep a Changelog](https://keepachangelog.com/en/1.1.0/), and this project adheres to[Semantic Versioning](https://semver.org/spec/v2.0.0.html).+## [0.3.8] — 2026-08-11++**The floor stops typing when it can't be heard.**+A rate-limited CLI discards keystrokes silently — no error, no bounce — so every message+delivered during the window was simply gone. That is the headline fix. Behind it, a run of things+that had been quietly costing tokens or hiding in plain sight: compaction firing on two schedules+at once, a commit history that rendered no commit messages, and buttons whose labels were+invisible in dark mode.++### Added+- **Usage-limit guard.** When a CLI reports it has hit its limit, every agent on that provider+ stops being typed into, queues stay intact, and delivery resumes by itself at the reset — one+ message at a time. Holds are scoped to the **provider**, because a usage limit belongs to an+ account and siblings on one subscription are already behind the same wall. Two tiers: a spent+ quota holds until its stated reset, while a transient throttle is off by default since the CLIs+ already retry those themselves. Every hold shows the line that caused it, a countdown, and a+ resume button; the whole guard is one switch in **Settings → Usage limits**. Reset times are+ read from the CLI where it states one (including a two-pass timezone solve so a reset after a+ DST change doesn't land an hour out) and fall back to an escalating backoff where it doesn't.+- **Triggers hub.** Schedules, inbound webhooks, context rules and peer messaging now share one+ home in Settings, with a history of what fired and what it did.+- **Collapsible panels.** The IDE's git rail folds away to give the file tree its height back, and+ the fullscreen roster folds for a full-width terminal. Both remember the choice.+- **The OpenAI key can be set where voice is explained.** Settings → Voice now carries the field+ itself, names the model it pays for (`gpt-realtime-2.1`), and the disabled Talk button links+ straight to it.++### Fixed+- **Claude Code transcripts were read from a directory that has not existed for months.**+ `projectDir()` built the pre-2026 project key — leading slash dropped — while Claude Code dashes+ every non-alphanumeric character. Nothing errored, because every caller reads an absent directory+ as "no transcripts yet", so memory condensation had never once succeeded: a long run of+ `condense-abort`s and zero successes, each failed attempt still writing a full backup first. The+ offline usage reconciler and cross-cwd session-resume read and wrote the same wrong path. Found+ and diagnosed by [@gts-47](https://github.com/gts-47).+- **Compaction ran on two schedules at once.** The hourly ops standup carried an `autoCompact`+ flag that the context trigger was supposed to have replaced, so a default install requested+ compaction on both cadences — and turning the trigger off left the standup compacting anyway.+ There is now one control, and its off-switch is honest.+- **Duplicate `/compact` messages piled up in the queue** and fired together, each answering+ "nothing to compact" after the first had done the work. One pending compaction per agent is now+ enforced in the message store, where no caller can route around it.+- **The commit history is legible.** It rendered through a library that positions rows at a fixed+ 64px regardless of the spacing it draws the graph at (rows overlapped), reserves 500px for the+ graph regardless of available width (text was squeezed into the remainder and wrapped), and+ never displayed the commit subject at all. It is now drawn directly and fits any panel width.+- **Disabled buttons were unreadable, and icons vanished on dark buttons.** Disabled fills swapped+ to a mid surface while the label kept its inverted colour — roughly 1.4:1 in dark mode. Icons+ were painted in the same token as a primary button's fill, so the arrow on **Send** was+ invisible whenever it was enabled.+- **Two scrollers that never scrolled** — the IDE's changed-file list and the per-commit file list.+ `overflow: auto` inside a capped column sizes to its content without `flex: 1`, so it overflowed+ the cap rather than reaching its own scroll threshold.+- **Codex hooks stopped timing out after 1s.** Codex reads `timeout` as seconds and normalises it+ with `.max(1)`, so the `timeout: 0` sentinel copied from Claude's config meant *one second*, not+ "no timeout" — every Codex worker logged a failed SessionStart hook.+- **Every download link on the release page 404'd.** They carried a version-pinned filename that+ stopped resolving four releases ago; mac downloads fell from ~118 to single digits. The release+ gate now refuses to ship links that don't resolve.+- **A tooltip clipped by the agent dock**, and the missing-key notice that overflowed the agent+ card.++### Changed+- Scheduled auto-compact is held while any provider is rate-limited: `/compact` is a model call,+ and sending it into a capped CLI spends a rejected attempt *and* parks a `/compact` ahead of+ your real backlog.+## [0.3.7] — 2026-08-08**Auto-update, fixed.**diff --git a/README.md b/README.mdindex f0e5c237..2a65fce7 100644--- a/README.md+++ b/README.md@@ -16,7 +16,7 @@ you talk to, and visualized as avatars at work on a shared office floor.<p><a href="./LICENSE"><img alt="License: MIT" src="https://img.shields.io/badge/license-MIT-F4D35E.svg?style=flat-square&labelColor=6E1423"></a>- <a href="./CHANGELOG.md"><img alt="Version: 0.3.7" src="https://img.shields.io/badge/version-0.3.7-F4D35E.svg?style=flat-square&labelColor=6E1423"></a>+ <a href="./CHANGELOG.md"><img alt="Version: 0.3.8" src="https://img.shields.io/badge/version-0.3.8-F4D35E.svg?style=flat-square&labelColor=6E1423"></a><img alt="Status: prototype" src="https://img.shields.io/badge/status-working%20prototype-F4F1EA.svg?style=flat-square&labelColor=6E1423"><img alt="Platform: macOS | Windows | Linux" src="https://img.shields.io/badge/platform-macOS%20%7C%20Windows%20%7C%20Linux-F4F1EA.svg?style=flat-square&labelColor=6E1423"><a href="./CONTRIBUTING.md"><img alt="PRs welcome" src="https://img.shields.io/badge/PRs-welcome-F4D35E.svg?style=flat-square&labelColor=6E1423"></a>@@ -136,11 +136,12 @@ terminal/event plane, and [`DESIGN.md`](./DESIGN.md) for the visual system.- **Auto-update** — new releases download in the background; you click restart.> [!NOTE]-> **Status: v0.3.7 — auto-update, fixed.** A CommonJS/ESM import bug meant the native updater-> silently never ran in any packaged build from v0.3.4 on, so the app could only ever offer a link-> to the releases page. It now works, the toolbar version doubles as the update button, and update-> errors reach the UI and a log file instead of being swallowed. **Existing v0.3.5 / v0.3.6 installs-> carry the broken updater and must install v0.3.7 manually, once** — after that, updates are automatic.+> **Status: v0.3.8 — the floor stops typing when it can't be heard.** A rate-limited CLI discards+> keystrokes silently, so every message delivered during a limit window was simply lost. Agents on a+> capped provider are now held, their queues keep filling, and delivery resumes by itself at the+> reset — one message at a time, nothing to resend by hand. Also in this release: a Triggers hub,+> a fix for memory condensation that had never once succeeded, compaction that no longer runs on+> two schedules at once, and a commit history that is actually readable.> macOS (signed & notarized), Windows, and Linux builds are on the> [releases page](https://github.com/chaitanyagiri/munder-difflin/releases/latest).@@ -273,7 +274,7 @@ chrome. The 15 avatars are the cast of *The Office*, differentiated by hair/skin## Roadmap-Shipped through **v0.3.7** — nine agent engines with BYOK keys and local LLMs, voice orchestration,+Shipped through **v0.3.8** — nine agent engines with BYOK keys and local LLMs, voice orchestration,the hive (memory · mailboxes · blackboard · event log), Command Center with kanban and schedules,a built-in Monaco IDE with git rails, integrations registry + secret broker, Slack-spawned workers,shareable hires and the Agent Gallery, observability and the circuit breaker, durable persistence,diff --git a/RELEASE.md b/RELEASE.mdindex a82ec32a..438fe766 100644--- a/RELEASE.md+++ b/RELEASE.md@@ -1,4 +1,4 @@-# Munder Difflin v0.3.7+# Munder Difflin v0.3.8**A local hive of Claude Code, Antigravity, Codex, Grok & Copilot agents that run themselves** — messaging,routing, and remembering, coordinated by a GOD orchestrator you talk to. Local-first and open source.@@ -7,40 +7,58 @@ routing, and remembering, coordinated by a GOD orchestrator you talk to. Local-f----## What's new in 0.3.7 — *Auto-update, fixed*--**Auto-update never actually ran.** Not once, in any packaged build, since it shipped in-v0.3.4. `electron-updater` is a CommonJS module that exposes `autoUpdater` through a lazy-getter, which Node's module lexer can't see — so `await import('electron-updater')` handed-back `undefined`, and the very first line of setup threw-`TypeError: Cannot set properties of undefined (setting 'autoDownload')`. That landed in a-`catch` that silently switched the app to notify-only mode, which is why the only thing it-could ever offer was a link to the releases page. It never showed up in testing because the-whole path is skipped in development.--- **The native updater works.** New releases download in the background and wait for your- click. macOS builds are Developer ID signed, notarized, and stapled, so the update installs- cleanly.-- **The version in the toolbar is now the update button.** Top-left, next to the logo: it- shows `checking…`, then `v0.3.8 ready to install`, then live download progress, then- **restart to update**. With nothing pending, clicking it checks on demand — previously the- app only ever checked 30 seconds after launch and then every six hours, with no way to ask.-- **Nothing fails silently any more.** Update errors now reach the UI *and* an `updater.log`- in the app's data folder. The old code threw the error away, which is exactly why this- survived three releases.-- **One network blip no longer disables updates for the session.** The fallback to- notify-only is now per-check instead of a permanent latch, and a re-check can't wipe out an- update you've already got staged.--> [!IMPORTANT]-> **If you're on v0.3.5 or v0.3.6, this one is a manual install.** Those builds carry the-> broken updater, so they can't fetch this fix by themselves — grab the download below once.-> From v0.3.7 onward, updates arrive on their own.+## What's new in 0.3.8 — *The floor stops typing when it can't be heard*++**A rate-limited CLI throws your messages away.** Not with an error — it just discards the+keystrokes. The harness kept typing at it, so every message delivered during a limit window was+silently gone, and the only way to find out was noticing later that an agent never did the thing+you asked.++- **Usage limits now pause the floor instead of losing work.** When a CLI reports it is capped,+ every agent on that provider stops being typed into, queues keep filling, and delivery starts+ again by itself at the reset — one message at a time. Nothing to resend by hand.+- **Holds are scoped to the account, not the agent.** Six workers on one Claude subscription are+ all behind the same wall the moment one of them hits it, so holding only the agent that printed+ the banner would just lose the next five messages one at a time.+- **A spent quota and a passing throttle are different things.** A quota holds until the stated+ reset; a transient 429 is left alone by default, because the CLIs already retry those and+ parking the floor for a hiccup that has already cleared is its own bug.+- Every hold shows the line that caused it, a countdown, and a **resume now** button. The whole+ guard is one switch in **Settings → Usage limits**.++### Also in this release++- **Triggers, in one place.** Schedules, inbound webhooks, context rules and peer messaging now+ share a home in Settings, with a history of what fired and what it did.+- **Memory condensation has never once worked — now it does.** Claude Code changed how it names+ per-project transcript directories, and the harness kept reading the old spelling. Nothing+ errored, because an absent directory reads as "no transcripts yet", so the summarizer was+ blamed for two months of silence it had nothing to do with. Found and diagnosed by+ [@gts-47](https://github.com/gts-47).+- **Compaction stopped running twice.** The hourly standup and the 2-hour context trigger were+ both asking for it, and turning the trigger off left the standup compacting anyway. One control+ now, and its off-switch means off. Duplicate `/compact` messages can no longer stack up in a+ queue and fire together.+- **The commit history is readable.** It rendered through a library that overlapped its own rows,+ reserved a fixed 500px for the graph no matter how narrow the panel was, and never showed the+ commit message at all. It is drawn directly now and fits any width.+- **Dark mode fixes worth the name.** Disabled buttons had labels at roughly 1.4:1 against their+ own fill, and the arrow on **Send** was painted in the same colour as the button behind it.+- **Panels fold.** The IDE's git rail collapses to give the file tree its height back; the+ fullscreen roster collapses for a full-width terminal.+- **Codex hooks stopped timing out after one second** — `timeout: 0` means *one second* to Codex,+ not "no timeout".++> [!NOTE]+> **Auto-update carries you here from v0.3.7.** If you are still on v0.3.5 or v0.3.6, those builds+> shipped the broken updater and need one manual install — grab the download below, once.---## Previously+- **0.3.7** — auto-update actually runs: a CommonJS/ESM import bug meant the native updater never+ fired in any packaged build since v0.3.4, and the failure was swallowed by a `catch`.- **0.3.6** — *a machine with nothing on it can run agents*: Node and npm install themselves(verified against the official `SHASUMS256.txt`), hooks stopped dying with exit 127, `~/dev/foo`paths resolve, and the office floor rebuilds itself after losing its GPU context.diff --git a/blog/src/posts/when-the-cli-stops-listening.md b/blog/src/posts/when-the-cli-stops-listening.mdnew file mode 100644index 00000000..25f132ae--- /dev/null+++ b/blog/src/posts/when-the-cli-stops-listening.md@@ -0,0 +1,182 @@+---+title: "When the CLI Stops Listening: Rate Limits Are Silent Data Loss"+description: "A rate-limited coding CLI doesn't reject your input — it discards it. No error, no bounce, no record. Munder Difflin was typing into that void for months. Here's how we detect the wall, hold the whole account behind it, and drain the backlog on the other side."+date: 2026-08-11+category: internals+categoryLabel: Internals+type: Technical+primaryKeyword: "claude code rate limit"+secondaryKeywords: ["claude code usage limit reached", "claude code session limit resets", "cli agent rate limit handling", "queue messages during rate limit", "codex rate limit resets_at"]+tags: ["Internals", "Reliability", "Agents", "Release", "Open Source"]+author:+ name: Chaitanya Giri+ initials: CG+faq:+ - q: "What happens if you type into a rate-limited Claude Code session?"+ a: "The TUI accepts the keystrokes and discards them. There is no error, no bounce, and no record that a message existed — the input area simply clears. Anything sent during the limit window is gone, and the only symptom is noticing later that the agent never did the thing you asked. This is why a rate limit is worse than an outage for an automated sender: an outage fails loudly, and this fails silently."+ - q: "How do you detect a usage limit from a CLI's terminal output?"+ a: "You read the terminal stream, not the exit code — these are TUIs, and the limit is a banner rather than a status. Most CLIs relay the provider's own wording, so generic natural-language patterns carry most of the work, with a small per-CLI table for the strings a tool genuinely owns (Claude Code's subscription limits are its own concept, for example). The hard part is negative matching: Claude renders 'Approaching session limit · resets 3pm' from the same component as the real banner at around 80% usage, and matching that would stand your fleet down hours early, every session."+ - q: "Should a rate-limit hold apply to one agent or all of them?"+ a: "The account. A usage limit belongs to a subscription, so every agent running that CLI is already behind the same wall the moment one of them hits it — they just haven't spoken yet. Holding only the agent that printed the banner lets the others walk into it one at a time, losing a message each. Over-holding costs a wait; under-holding costs instructions."+ - q: "Why not just retry when a message fails to send?"+ a: "Because it doesn't fail. The write succeeds — the bytes reach the pseudo-terminal, and the TUI throws them away at the other end. There is no failure to retry against, which is why the fix has to be a gate in front of the send rather than a retry behind it."+---++There is a failure mode that is worse than an error, and most automated systems are built as+though it doesn't exist: the write that succeeds and does nothing.++Munder Difflin drives coding CLIs — Claude Code, Codex, Grok, and half a dozen others — through+real pseudo-terminals. It types into them the way a person would. And for months, whenever one of+those CLIs hit its usage limit, the harness kept typing.++The keystrokes landed. The pty accepted them. The TUI discarded them.++No error. No bounce. No record that a message ever existed. The input area just cleared, and an+instruction that someone had queued an hour earlier ceased to exist. The only symptom was noticing,+much later, that an agent never did the thing it was asked.++## Why this is not a retry problem++The instinct is to add a retry. It doesn't apply here, and the reason is worth sitting with.++A retry needs a failure to hang off. Ours succeeded at every layer we could observe:++```+write(ptyFd, "…") → ok, bytes written+pty → ok, delivered to the child+TUI → reads the input, sees it is rate limited, drops it+```++There is nothing to catch. By the time the message is lost, every call in the stack has already+returned success. That pushes the fix upstream of the send: you cannot recover from this+afterwards, so you have to not do it in the first place.++## Reading the wall++Because these are TUIs, the limit is a banner rather than a status code. So you read the terminal+stream.++The obvious design is a table of per-CLI strings — the shape we already use for slash commands,+where `/compact` differs per tool. Reading the shipped artefacts of the installed fleet, that turns+out to be the wrong shape, because **the limit text is mostly written by the API, not the CLI**.+Five of the CLIs we drive contain no user-facing limit copy at all; they surface whatever the+provider returned. What reaches the terminal is the provider's phrasing, not the tool's.++So generic patterns carry the weight, and a small table covers the strings a CLI genuinely owns —+Claude Code's subscription limits, for instance, are its own concept, with a fixed label set+(`session limit`, `weekly limit`, `Opus limit`, `Sonnet limit`).++One nice piece of corroboration: pi.dev ships its own two classifier regexes, and the line it draws+is the same line we drew independently — terminal quota conditions on one side, retryable transport+errors on the other.++### The pattern that would have broken everything++Claude Code renders this at around 80% usage:++```+Approaching session limit · resets 3pm+```++From the same component as the real banner. Matching the reset clause alone would have stood the+entire fleet down hours early, every single session — turning a feature that exists to prevent lost+work into the largest source of lost time in the app.++It is the first thing the negative filter rejects, and it has a test. The general lesson: when you+add detection to a system, the false positive is not an edge case to handle later. It is the thing+most likely to make the feature a net negative, and it deserves the first test you write.++There is a second class of false positive specific to a harness like this: agents read source code+and echo it to their terminals. A file containing `const RATE_LIMIT = 120;` scrolls past and looks,+to a naive matcher, exactly like a rate limit. Code-shaped contexts are filtered, and lines over+400 characters — a minified bundle going by — are ignored outright.++## Two tiers, because they want opposite responses++Conflating these would be the worst bug the feature could ship:++| | what it is | response |+|---|---|---|+| **throttle** | burst 429, "overloaded", "temporarily limiting requests" | seconds to minutes — **off by default**, the CLIs already retry these |+| **quota** | the plan's allowance is spent | hold until the stated reset |++Parking a whole floor for hours because of a transient 503 that cleared in four seconds is not a+safety feature. It is an outage you caused yourself.++## The hold belongs to the account++A usage limit is a property of a subscription, not a process. Six workers running `claude` share+one account, so the moment one of them hits the wall the other five are already behind it — they+simply haven't spoken yet.++Holding only the agent that printed the banner would let the next five walk into the same wall one+at a time, losing a message each on the way in. So the hold is scoped to the provider.++That over-holds if you deliberately run two accounts across different agents, and that trade is+made on purpose: **over-holding costs a wait, under-holding costs instructions.** Resume is one+click, and every hold shows the line of terminal output that caused it, so a wrong hold is visible+rather than mysterious.++## Telling a repaint from a real re-hit++TUIs redraw constantly, and the banner stays in the scrollback after the limit lifts. A naive+detector re-arms on its own echo forever.++Two mechanisms, and the second is the interesting one:++- the detector suppresses an identical evidence line within a short window;+- the gate refuses to re-arm from identical wording shortly after a release **unless a message has+ actually been delivered since**.++That second condition is what separates an echo from a genuine second rejection. If we sent+something and the wall is still there, that is new information. If we sent nothing, we are looking+at pixels we already reacted to. There is a test that feeds thirty frames of the same banner at+roughly 10fps and asserts exactly one hold.++## What is gated, and what deliberately is not++**Gated:** the queue drain, the spawn seed — an agent seeded into a capped provider has its entire+setup prompt discarded and then sits there looking like a hung spawn — and scheduled auto-compact,+because `/compact` is a model call that spends a rejected attempt *and* parks a `/compact` ahead of+your real backlog when the window reopens.++**Not gated:** writing a message into another agent's inbox file. That is already a queue — the+message waits on disk until the agent next runs — so gating it would convert "delayed" into "lost",+which is the exact bug we are fixing.++**Bypassed:** "send now" overrides a hold, exactly as it already overrides the floor-wide delivery+pause. One override, one meaning. The operator may know something the detector doesn't, and an+override with no escape hatch is worse than a wrong guess.++## Two bugs found while building it++Both are the same species — a setting that describes the world rather than controlling it.++**`autoResume: off` did nothing.** Expiry was a timestamp comparison, so holds lapsed on their own+and the setting was decorative. A hold now ends when it is *swept*, and the sweep is what+auto-resume controls.++**Disabling the guard left the floor stopped.** The drain reads the hold list, not the setting, so+existing holds outlived the switch that was supposed to govern them. Turning it off now releases+everything.++If you take one thing from this post, take that pattern: a boolean that reads well in the UI and is+never consulted on the path it claims to govern is indistinguishable from a working feature right up+until someone needs it.++## What honest verification looks like++The detection tests are built from strings read out of the installed binaries — `strings` and+`rg` over the shipped artefacts — not from a terminal that actually hit a wall. That is a real+limitation and it is worth stating plainly rather than burying: the highest-value check before+trusting this is forcing one live limit and watching a queue drain on the other side of it.++Shipping detection heuristics with a switch to turn them off, evidence attached to every decision,+and a one-click override is not a lack of confidence. It is what you owe people when your feature's+failure mode is "the fleet stopped and I don't know why".++---++*Munder Difflin v0.3.8 is out — usage-limit aware delivery, a Triggers hub, and a git history view+that finally fits its panel. [Download it](https://github.com/chaitanyagiri/munder-difflin/releases/latest),+or read the [changelog](https://github.com/chaitanyagiri/munder-difflin/blob/main/CHANGELOG.md).*diff --git a/docs/blog/append-only-event-log-agents/index.html b/docs/blog/append-only-event-log-agents/index.htmlindex 2bd10945..89a0ae1a 100644--- a/docs/blog/append-only-event-log-agents/index.html+++ b/docs/blog/append-only-event-log-agents/index.html@@ -285,56 +285,56 @@ it’s free and open source.</p><h2>Related in Internals</h2><div class="post-grid"><article class="card">- <a class="thumb t-internals" href="/blog/why-our-auto-update-never-ran/" aria-hidden="true" tabindex="-1">+ <a class="thumb t-internals" href="/blog/when-the-cli-stops-listening/" aria-hidden="true" tabindex="-1"><span>INTERNALS</span></a><div class="body"><div class="meta">- <time datetime="2026-08-08">Aug 8, 2026</time>+ <time datetime="2026-08-11">Aug 11, 2026</time><span class="dot" aria-hidden="true"></span>- <span>5 min</span>+ <span>6 min</span></div>- <h3><a href="/blog/why-our-auto-update-never-ran/">Our Auto-Update Never Ran Once: A CommonJS Export That Vanished Into an ESM Namespace</a></h3>- <p class="dek">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.</p>+ <h3><a href="/blog/when-the-cli-stops-listening/">When the CLI Stops Listening: Rate Limits Are Silent Data Loss</a></h3>+ <p class="dek">A rate-limited coding CLI doesn't reject your input — it discards it. No error, no bounce, no record. Munder Difflin was typing into that void for months. Here's how we detect the wall, hold the whole account behind it, and drain the backlog on the other side.</p><div class="foot"><span class="tag kind">Internals</span>- <a class="more" href="/blog/why-our-auto-update-never-ran/" aria-label="Read: Our Auto-Update Never Ran Once: A CommonJS Export That Vanished Into an ESM Namespace">Read →</a>+ <a class="more" href="/blog/when-the-cli-stops-listening/" aria-label="Read: When the CLI Stops Listening: Rate Limits Are Silent Data Loss">Read →</a></div></div></article><article class="card">- <a class="thumb t-internals" href="/blog/hire-manifest-untrusted-input/" aria-hidden="true" tabindex="-1">+ <a class="thumb t-internals" href="/blog/why-our-auto-update-never-ran/" aria-hidden="true" tabindex="-1"><span>INTERNALS</span></a><div class="body"><div class="meta">- <time datetime="2026-06-15">Jun 15, 2026</time>+ <time datetime="2026-08-08">Aug 8, 2026</time><span class="dot" aria-hidden="true"></span>- <span>12 min</span>+ <span>5 min</span></div>- <h3><a href="/blog/hire-manifest-untrusted-input/">Treating a Hire Manifest as Untrusted Input</a></h3>- <p class="dek">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.</p>+ <h3><a href="/blog/why-our-auto-update-never-ran/">Our Auto-Update Never Ran Once: A CommonJS Export That Vanished Into an ESM Namespace</a></h3>+ <p class="dek">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.</p><div class="foot"><span class="tag kind">Internals</span>- <a class="more" href="/blog/hire-manifest-untrusted-input/" aria-label="Read: Treating a Hire Manifest as Untrusted Input">Read →</a>+ <a class="more" href="/blog/why-our-auto-update-never-ran/" aria-label="Read: Our Auto-Update Never Ran Once: A CommonJS Export That Vanished Into an ESM Namespace">Read →</a></div></div></article><article class="card">- <a class="thumb t-internals" href="/blog/compressing-agent-memory/" aria-hidden="true" tabindex="-1">+ <a class="thumb t-internals" href="/blog/hire-manifest-untrusted-input/" aria-hidden="true" tabindex="-1"><span>INTERNALS</span></a><div class="body"><div class="meta">- <time datetime="2026-06-05">Jun 5, 2026</time>+ <time datetime="2026-06-15">Jun 15, 2026</time><span class="dot" aria-hidden="true"></span>- <span>5 min</span>+ <span>12 min</span></div>- <h3><a href="/blog/compressing-agent-memory/">Compressing Agent Memory Without Losing the Original</a></h3>- <p class="dek">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.</p>+ <h3><a href="/blog/hire-manifest-untrusted-input/">Treating a Hire Manifest as Untrusted Input</a></h3>+ <p class="dek">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.</p><div class="foot"><span class="tag kind">Internals</span>- <a class="more" href="/blog/compressing-agent-memory/" aria-label="Read: Compressing Agent Memory Without Losing the Original">Read →</a>+ <a class="more" href="/blog/hire-manifest-untrusted-input/" aria-label="Read: Treating a Hire Manifest as Untrusted Input">Read →</a></div></div></article>diff --git a/docs/blog/architecture-two-planes-one-renderer/index.html b/docs/blog/architecture-two-planes-one-renderer/index.htmlindex 7af3bc31..f1c3ff5f 100644--- a/docs/blog/architecture-two-planes-one-renderer/index.html+++ b/docs/blog/architecture-two-planes-one-renderer/index.html@@ -288,56 +288,56 @@ free and open source.</p><h2>Related in Internals</h2><div class="post-grid"><article class="card">- <a class="thumb t-internals" href="/blog/why-our-auto-update-never-ran/" aria-hidden="true" tabindex="-1">+ <a class="thumb t-internals" href="/blog/when-the-cli-stops-listening/" aria-hidden="true" tabindex="-1"><span>INTERNALS</span></a><div class="body"><div class="meta">- <time datetime="2026-08-08">Aug 8, 2026</time>+ <time datetime="2026-08-11">Aug 11, 2026</time><span class="dot" aria-hidden="true"></span>- <span>5 min</span>+ <span>6 min</span></div>- <h3><a href="/blog/why-our-auto-update-never-ran/">Our Auto-Update Never Ran Once: A CommonJS Export That Vanished Into an ESM Namespace</a></h3>- <p class="dek">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.</p>+ <h3><a href="/blog/when-the-cli-stops-listening/">When the CLI Stops Listening: Rate Limits Are Silent Data Loss</a></h3>+ <p class="dek">A rate-limited coding CLI doesn't reject your input — it discards it. No error, no bounce, no record. Munder Difflin was typing into that void for months. Here's how we detect the wall, hold the whole account behind it, and drain the backlog on the other side.</p><div class="foot"><span class="tag kind">Internals</span>- <a class="more" href="/blog/why-our-auto-update-never-ran/" aria-label="Read: Our Auto-Update Never Ran Once: A CommonJS Export That Vanished Into an ESM Namespace">Read →</a>+ <a class="more" href="/blog/when-the-cli-stops-listening/" aria-label="Read: When the CLI Stops Listening: Rate Limits Are Silent Data Loss">Read →</a></div></div></article><article class="card">- <a class="thumb t-internals" href="/blog/hire-manifest-untrusted-input/" aria-hidden="true" tabindex="-1">+ <a class="thumb t-internals" href="/blog/why-our-auto-update-never-ran/" aria-hidden="true" tabindex="-1"><span>INTERNALS</span></a><div class="body"><div class="meta">- <time datetime="2026-06-15">Jun 15, 2026</time>+ <time datetime="2026-08-08">Aug 8, 2026</time><span class="dot" aria-hidden="true"></span>- <span>12 min</span>+ <span>5 min</span></div>- <h3><a href="/blog/hire-manifest-untrusted-input/">Treating a Hire Manifest as Untrusted Input</a></h3>- <p class="dek">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.</p>+ <h3><a href="/blog/why-our-auto-update-never-ran/">Our Auto-Update Never Ran Once: A CommonJS Export That Vanished Into an ESM Namespace</a></h3>+ <p class="dek">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.</p><div class="foot"><span class="tag kind">Internals</span>- <a class="more" href="/blog/hire-manifest-untrusted-input/" aria-label="Read: Treating a Hire Manifest as Untrusted Input">Read →</a>+ <a class="more" href="/blog/why-our-auto-update-never-ran/" aria-label="Read: Our Auto-Update Never Ran Once: A CommonJS Export That Vanished Into an ESM Namespace">Read →</a></div></div></article><article class="card">- <a class="thumb t-internals" href="/blog/compressing-agent-memory/" aria-hidden="true" tabindex="-1">+ <a class="thumb t-internals" href="/blog/hire-manifest-untrusted-input/" aria-hidden="true" tabindex="-1"><span>INTERNALS</span></a><div class="body"><div class="meta">- <time datetime="2026-06-05">Jun 5, 2026</time>+ <time datetime="2026-06-15">Jun 15, 2026</time><span class="dot" aria-hidden="true"></span>- <span>5 min</span>+ <span>12 min</span></div>- <h3><a href="/blog/compressing-agent-memory/">Compressing Agent Memory Without Losing the Original</a></h3>- <p class="dek">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.</p>+ <h3><a href="/blog/hire-manifest-untrusted-input/">Treating a Hire Manifest as Untrusted Input</a></h3>+ <p class="dek">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.</p><div class="foot"><span class="tag kind">Internals</span>- <a class="more" href="/blog/compressing-agent-memory/" aria-label="Read: Compressing Agent Memory Without Losing the Original">Read →</a>+ <a class="more" href="/blog/hire-manifest-untrusted-input/" aria-label="Read: Treating a Hire Manifest as Untrusted Input">Read →</a></div></div></article>diff --git a/docs/blog/atomic-file-mailboxes-for-agents/index.html b/docs/blog/atomic-file-mailboxes-for-agents/index.htmlindex 95ee62db..18ee8892 100644--- a/docs/blog/atomic-file-mailboxes-for-agents/index.html+++ b/docs/blog/atomic-file-mailboxes-for-agents/index.html@@ -300,56 +300,56 @@ the office floor; it’s free and open source.</p><h2>Related in Internals</h2><div class="post-grid"><article class="card">- <a class="thumb t-internals" href="/blog/why-our-auto-update-never-ran/" aria-hidden="true" tabindex="-1">+ <a class="thumb t-internals" href="/blog/when-the-cli-stops-listening/" aria-hidden="true" tabindex="-1"><span>INTERNALS</span></a><div class="body"><div class="meta">- <time datetime="2026-08-08">Aug 8, 2026</time>+ <time datetime="2026-08-11">Aug 11, 2026</time><span class="dot" aria-hidden="true"></span>- <span>5 min</span>+ <span>6 min</span></div>- <h3><a href="/blog/why-our-auto-update-never-ran/">Our Auto-Update Never Ran Once: A CommonJS Export That Vanished Into an ESM Namespace</a></h3>- <p class="dek">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.</p>+ <h3><a href="/blog/when-the-cli-stops-listening/">When the CLI Stops Listening: Rate Limits Are Silent Data Loss</a></h3>+ <p class="dek">A rate-limited coding CLI doesn't reject your input — it discards it. No error, no bounce, no record. Munder Difflin was typing into that void for months. Here's how we detect the wall, hold the whole account behind it, and drain the backlog on the other side.</p><div class="foot"><span class="tag kind">Internals</span>- <a class="more" href="/blog/why-our-auto-update-never-ran/" aria-label="Read: Our Auto-Update Never Ran Once: A CommonJS Export That Vanished Into an ESM Namespace">Read →</a>+ <a class="more" href="/blog/when-the-cli-stops-listening/" aria-label="Read: When the CLI Stops Listening: Rate Limits Are Silent Data Loss">Read →</a></div></div></article><article class="card">- <a class="thumb t-internals" href="/blog/hire-manifest-untrusted-input/" aria-hidden="true" tabindex="-1">+ <a class="thumb t-internals" href="/blog/why-our-auto-update-never-ran/" aria-hidden="true" tabindex="-1"><span>INTERNALS</span></a><div class="body"><div class="meta">- <time datetime="2026-06-15">Jun 15, 2026</time>+ <time datetime="2026-08-08">Aug 8, 2026</time><span class="dot" aria-hidden="true"></span>- <span>12 min</span>+ <span>5 min</span></div>- <h3><a href="/blog/hire-manifest-untrusted-input/">Treating a Hire Manifest as Untrusted Input</a></h3>- <p class="dek">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.</p>+ <h3><a href="/blog/why-our-auto-update-never-ran/">Our Auto-Update Never Ran Once: A CommonJS Export That Vanished Into an ESM Namespace</a></h3>+ <p class="dek">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.</p><div class="foot"><span class="tag kind">Internals</span>- <a class="more" href="/blog/hire-manifest-untrusted-input/" aria-label="Read: Treating a Hire Manifest as Untrusted Input">Read →</a>+ <a class="more" href="/blog/why-our-auto-update-never-ran/" aria-label="Read: Our Auto-Update Never Ran Once: A CommonJS Export That Vanished Into an ESM Namespace">Read →</a></div></div></article><article class="card">- <a class="thumb t-internals" href="/blog/compressing-agent-memory/" aria-hidden="true" tabindex="-1">+ <a class="thumb t-internals" href="/blog/hire-manifest-untrusted-input/" aria-hidden="true" tabindex="-1"><span>INTERNALS</span></a><div class="body"><div class="meta">- <time datetime="2026-06-05">Jun 5, 2026</time>+ <time datetime="2026-06-15">Jun 15, 2026</time><span class="dot" aria-hidden="true"></span>- <span>5 min</span>+ <span>12 min</span></div>- <h3><a href="/blog/compressing-agent-memory/">Compressing Agent Memory Without Losing the Original</a></h3>- <p class="dek">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.</p>+ <h3><a href="/blog/hire-manifest-untrusted-input/">Treating a Hire Manifest as Untrusted Input</a></h3>+ <p class="dek">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.</p><div class="foot"><span class="tag kind">Internals</span>- <a class="more" href="/blog/compressing-agent-memory/" aria-label="Read: Compressing Agent Memory Without Losing the Original">Read →</a>+ <a class="more" href="/blog/hire-manifest-untrusted-input/" aria-label="Read: Treating a Hire Manifest as Untrusted Input">Read →</a></div></div></article>diff --git a/docs/blog/building-a-terminal-ui-xterm-node-pty/index.html b/docs/blog/building-a-terminal-ui-xterm-node-pty/index.htmlindex 725d01b9..f7b41cd6 100644--- a/docs/blog/building-a-terminal-ui-xterm-node-pty/index.html+++ b/docs/blog/building-a-terminal-ui-xterm-node-pty/index.html@@ -343,56 +343,56 @@ to watch many real terminals at once; it’s free and open source.</p><h2>Related in Internals</h2><div class="post-grid"><article class="card">- <a class="thumb t-internals" href="/blog/why-our-auto-update-never-ran/" aria-hidden="true" tabindex="-1">+ <a class="thumb t-internals" href="/blog/when-the-cli-stops-listening/" aria-hidden="true" tabindex="-1"><span>INTERNALS</span></a><div class="body"><div class="meta">- <time datetime="2026-08-08">Aug 8, 2026</time>+ <time datetime="2026-08-11">Aug 11, 2026</time><span class="dot" aria-hidden="true"></span>- <span>5 min</span>+ <span>6 min</span></div>- <h3><a href="/blog/why-our-auto-update-never-ran/">Our Auto-Update Never Ran Once: A CommonJS Export That Vanished Into an ESM Namespace</a></h3>- <p class="dek">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.</p>+ <h3><a href="/blog/when-the-cli-stops-listening/">When the CLI Stops Listening: Rate Limits Are Silent Data Loss</a></h3>+ <p class="dek">A rate-limited coding CLI doesn't reject your input — it discards it. No error, no bounce, no record. Munder Difflin was typing into that void for months. Here's how we detect the wall, hold the whole account behind it, and drain the backlog on the other side.</p><div class="foot"><span class="tag kind">Internals</span>- <a class="more" href="/blog/why-our-auto-update-never-ran/" aria-label="Read: Our Auto-Update Never Ran Once: A CommonJS Export That Vanished Into an ESM Namespace">Read →</a>+ <a class="more" href="/blog/when-the-cli-stops-listening/" aria-label="Read: When the CLI Stops Listening: Rate Limits Are Silent Data Loss">Read →</a></div></div></article><article class="card">- <a class="thumb t-internals" href="/blog/hire-manifest-untrusted-input/" aria-hidden="true" tabindex="-1">+ <a class="thumb t-internals" href="/blog/why-our-auto-update-never-ran/" aria-hidden="true" tabindex="-1"><span>INTERNALS</span></a><div class="body"><div class="meta">- <time datetime="2026-06-15">Jun 15, 2026</time>+ <time datetime="2026-08-08">Aug 8, 2026</time><span class="dot" aria-hidden="true"></span>- <span>12 min</span>+ <span>5 min</span></div>- <h3><a href="/blog/hire-manifest-untrusted-input/">Treating a Hire Manifest as Untrusted Input</a></h3>- <p class="dek">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.</p>+ <h3><a href="/blog/why-our-auto-update-never-ran/">Our Auto-Update Never Ran Once: A CommonJS Export That Vanished Into an ESM Namespace</a></h3>+ <p class="dek">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.</p><div class="foot"><span class="tag kind">Internals</span>- <a class="more" href="/blog/hire-manifest-untrusted-input/" aria-label="Read: Treating a Hire Manifest as Untrusted Input">Read →</a>+ <a class="more" href="/blog/why-our-auto-update-never-ran/" aria-label="Read: Our Auto-Update Never Ran Once: A CommonJS Export That Vanished Into an ESM Namespace">Read →</a></div></div></article><article class="card">- <a class="thumb t-internals" href="/blog/compressing-agent-memory/" aria-hidden="true" tabindex="-1">+ <a class="thumb t-internals" href="/blog/hire-manifest-untrusted-input/" aria-hidden="true" tabindex="-1"><span>INTERNALS</span></a><div class="body"><div class="meta">- <time datetime="2026-06-05">Jun 5, 2026</time>+ <time datetime="2026-06-15">Jun 15, 2026</time><span class="dot" aria-hidden="true"></span>- <span>5 min</span>+ <span>12 min</span></div>- <h3><a href="/blog/compressing-agent-memory/">Compressing Agent Memory Without Losing the Original</a></h3>- <p class="dek">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.</p>+ <h3><a href="/blog/hire-manifest-untrusted-input/">Treating a Hire Manifest as Untrusted Input</a></h3>+ <p class="dek">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.</p><div class="foot"><span class="tag kind">Internals</span>- <a class="more" href="/blog/compressing-agent-memory/" aria-label="Read: Compressing Agent Memory Without Losing the Original">Read →</a>+ <a class="more" href="/blog/hire-manifest-untrusted-input/" aria-label="Read: Treating a Hire Manifest as Untrusted Input">Read →</a></div></div></article>diff --git a/docs/blog/building-an-ai-office-floor/index.html b/docs/blog/building-an-ai-office-floor/index.htmlindex cb98b480..5a102e65 100644--- a/docs/blog/building-an-ai-office-floor/index.html+++ b/docs/blog/building-an-ai-office-floor/index.html@@ -288,56 +288,56 @@ techniques — the hard part is wiring them to <em>real</em> agent events, not t<h2>Related in Internals</h2><div class="post-grid"><article class="card">- <a class="thumb t-internals" href="/blog/why-our-auto-update-never-ran/" aria-hidden="true" tabindex="-1">+ <a class="thumb t-internals" href="/blog/when-the-cli-stops-listening/" aria-hidden="true" tabindex="-1"><span>INTERNALS</span></a><div class="body"><div class="meta">- <time datetime="2026-08-08">Aug 8, 2026</time>+ <time datetime="2026-08-11">Aug 11, 2026</time><span class="dot" aria-hidden="true"></span>- <span>5 min</span>+ <span>6 min</span></div>- <h3><a href="/blog/why-our-auto-update-never-ran/">Our Auto-Update Never Ran Once: A CommonJS Export That Vanished Into an ESM Namespace</a></h3>- <p class="dek">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.</p>+ <h3><a href="/blog/when-the-cli-stops-listening/">When the CLI Stops Listening: Rate Limits Are Silent Data Loss</a></h3>+ <p class="dek">A rate-limited coding CLI doesn't reject your input — it discards it. No error, no bounce, no record. Munder Difflin was typing into that void for months. Here's how we detect the wall, hold the whole account behind it, and drain the backlog on the other side.</p><div class="foot"><span class="tag kind">Internals</span>- <a class="more" href="/blog/why-our-auto-update-never-ran/" aria-label="Read: Our Auto-Update Never Ran Once: A CommonJS Export That Vanished Into an ESM Namespace">Read →</a>+ <a class="more" href="/blog/when-the-cli-stops-listening/" aria-label="Read: When the CLI Stops Listening: Rate Limits Are Silent Data Loss">Read →</a></div></div></article><article class="card">- <a class="thumb t-internals" href="/blog/hire-manifest-untrusted-input/" aria-hidden="true" tabindex="-1">+ <a class="thumb t-internals" href="/blog/why-our-auto-update-never-ran/" aria-hidden="true" tabindex="-1"><span>INTERNALS</span></a><div class="body"><div class="meta">- <time datetime="2026-06-15">Jun 15, 2026</time>+ <time datetime="2026-08-08">Aug 8, 2026</time><span class="dot" aria-hidden="true"></span>- <span>12 min</span>+ <span>5 min</span></div>- <h3><a href="/blog/hire-manifest-untrusted-input/">Treating a Hire Manifest as Untrusted Input</a></h3>- <p class="dek">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.</p>+ <h3><a href="/blog/why-our-auto-update-never-ran/">Our Auto-Update Never Ran Once: A CommonJS Export That Vanished Into an ESM Namespace</a></h3>+ <p class="dek">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.</p><div class="foot"><span class="tag kind">Internals</span>- <a class="more" href="/blog/hire-manifest-untrusted-input/" aria-label="Read: Treating a Hire Manifest as Untrusted Input">Read →</a>+ <a class="more" href="/blog/why-our-auto-update-never-ran/" aria-label="Read: Our Auto-Update Never Ran Once: A CommonJS Export That Vanished Into an ESM Namespace">Read →</a></div></div></article><article class="card">- <a class="thumb t-internals" href="/blog/compressing-agent-memory/" aria-hidden="true" tabindex="-1">+ <a class="thumb t-internals" href="/blog/hire-manifest-untrusted-input/" aria-hidden="true" tabindex="-1"><span>INTERNALS</span></a><div class="body"><div class="meta">- <time datetime="2026-06-05">Jun 5, 2026</time>+ <time datetime="2026-06-15">Jun 15, 2026</time><span class="dot" aria-hidden="true"></span>- <span>5 min</span>+ <span>12 min</span></div>- <h3><a href="/blog/compressing-agent-memory/">Compressing Agent Memory Without Losing the Original</a></h3>- <p class="dek">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.</p>+ <h3><a href="/blog/hire-manifest-untrusted-input/">Treating a Hire Manifest as Untrusted Input</a></h3>+ <p class="dek">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.</p><div class="foot"><span class="tag kind">Internals</span>- <a class="more" href="/blog/compressing-agent-memory/" aria-label="Read: Compressing Agent Memory Without Losing the Original">Read →</a>+ <a class="more" href="/blog/hire-manifest-untrusted-input/" aria-label="Read: Treating a Hire Manifest as Untrusted Input">Read →</a></div></div></article>diff --git a/docs/blog/claude-code-hooks-explained/index.html b/docs/blog/claude-code-hooks-explained/index.htmlindex f0ec28b7..82608abd 100644--- a/docs/blog/claude-code-hooks-explained/index.html+++ b/docs/blog/claude-code-hooks-explained/index.html@@ -302,56 +302,56 @@ free and open source.</p><h2>Related in Internals</h2><div class="post-grid"><article class="card">- <a class="thumb t-internals" href="/blog/why-our-auto-update-never-ran/" aria-hidden="true" tabindex="-1">+ <a class="thumb t-internals" href="/blog/when-the-cli-stops-listening/" aria-hidden="true" tabindex="-1"><span>INTERNALS</span></a><div class="body"><div class="meta">- <time datetime="2026-08-08">Aug 8, 2026</time>+ <time datetime="2026-08-11">Aug 11, 2026</time><span class="dot" aria-hidden="true"></span>- <span>5 min</span>+ <span>6 min</span></div>- <h3><a href="/blog/why-our-auto-update-never-ran/">Our Auto-Update Never Ran Once: A CommonJS Export That Vanished Into an ESM Namespace</a></h3>- <p class="dek">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.</p>+ <h3><a href="/blog/when-the-cli-stops-listening/">When the CLI Stops Listening: Rate Limits Are Silent Data Loss</a></h3>+ <p class="dek">A rate-limited coding CLI doesn't reject your input — it discards it. No error, no bounce, no record. Munder Difflin was typing into that void for months. Here's how we detect the wall, hold the whole account behind it, and drain the backlog on the other side.</p><div class="foot"><span class="tag kind">Internals</span>- <a class="more" href="/blog/why-our-auto-update-never-ran/" aria-label="Read: Our Auto-Update Never Ran Once: A CommonJS Export That Vanished Into an ESM Namespace">Read →</a>+ <a class="more" href="/blog/when-the-cli-stops-listening/" aria-label="Read: When the CLI Stops Listening: Rate Limits Are Silent Data Loss">Read →</a></div></div></article><article class="card">- <a class="thumb t-internals" href="/blog/hire-manifest-untrusted-input/" aria-hidden="true" tabindex="-1">+ <a class="thumb t-internals" href="/blog/why-our-auto-update-never-ran/" aria-hidden="true" tabindex="-1"><span>INTERNALS</span></a><div class="body"><div class="meta">- <time datetime="2026-06-15">Jun 15, 2026</time>+ <time datetime="2026-08-08">Aug 8, 2026</time><span class="dot" aria-hidden="true"></span>- <span>12 min</span>+ <span>5 min</span></div>- <h3><a href="/blog/hire-manifest-untrusted-input/">Treating a Hire Manifest as Untrusted Input</a></h3>- <p class="dek">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.</p>+ <h3><a href="/blog/why-our-auto-update-never-ran/">Our Auto-Update Never Ran Once: A CommonJS Export That Vanished Into an ESM Namespace</a></h3>+ <p class="dek">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.</p><div class="foot"><span class="tag kind">Internals</span>- <a class="more" href="/blog/hire-manifest-untrusted-input/" aria-label="Read: Treating a Hire Manifest as Untrusted Input">Read →</a>+ <a class="more" href="/blog/why-our-auto-update-never-ran/" aria-label="Read: Our Auto-Update Never Ran Once: A CommonJS Export That Vanished Into an ESM Namespace">Read →</a></div></div></article><article class="card">- <a class="thumb t-internals" href="/blog/compressing-agent-memory/" aria-hidden="true" tabindex="-1">+ <a class="thumb t-internals" href="/blog/hire-manifest-untrusted-input/" aria-hidden="true" tabindex="-1"><span>INTERNALS</span></a><div class="body"><div class="meta">- <time datetime="2026-06-05">Jun 5, 2026</time>+ <time datetime="2026-06-15">Jun 15, 2026</time><span class="dot" aria-hidden="true"></span>- <span>5 min</span>+ <span>12 min</span></div>- <h3><a href="/blog/compressing-agent-memory/">Compressing Agent Memory Without Losing the Original</a></h3>- <p class="dek">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.</p>+ <h3><a href="/blog/hire-manifest-untrusted-input/">Treating a Hire Manifest as Untrusted Input</a></h3>+ <p class="dek">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.</p><div class="foot"><span class="tag kind">Internals</span>- <a class="more" href="/blog/compressing-agent-memory/" aria-label="Read: Compressing Agent Memory Without Losing the Original">Read →</a>+ <a class="more" href="/blog/hire-manifest-untrusted-input/" aria-label="Read: Treating a Hire Manifest as Untrusted Input">Read →</a></div></div></article>diff --git a/docs/blog/command-center-guide/index.html b/docs/blog/command-center-guide/index.htmlindex 1f3ac5ff..922d3567 100644--- a/docs/blog/command-center-guide/index.html+++ b/docs/blog/command-center-guide/index.html@@ -79,7 +79,7 @@"@context": "https://schema.org","@type": "FAQPage","mainEntity": [- { "@type": "Question", "name": "What is the Command Center in Munder Difflin?", "acceptedAnswer": { "@type": "Answer", "text": "It's Michael's control surface — the management view of the whole hive. It has tabs for the orchestrator Terminal, the Floor (roster, dispatch, per-agent model selector, live fleet monitoring), Memory (semantic search plus a memory graph), Activity (event log, board, real token telemetry, observability, and a CI watcher), Tasks (a dependency-aware kanban board), and Schedules (recurring missions with last/next-fired times)." } },+ { "@type": "Question", "name": "What is the Command Center in Munder Difflin?", "acceptedAnswer": { "@type": "Answer", "text": "It's Michael's control surface — the management view of the whole hive. It has tabs for the orchestrator Terminal, the Floor (roster, dispatch, per-agent model selector, live fleet monitoring), Memory (semantic search plus a memory graph), Activity (event log, board, real token telemetry, observability, and a CI watcher), Tasks (a dependency-aware kanban board), and Triggers (everything that starts work without you — schedules with last/next-fired times, context, webhooks, and organization)." } },{ "@type": "Question", "name": "How does the task kanban work?", "acceptedAnswer": { "@type": "Answer", "text": "The Tasks tab is a dependency-aware kanban board. You assign tasks to agents and track them across todo, doing, blocked, and done. Because tasks can declare dependencies, downstream work waits until its prerequisites finish, so a chain of related tasks starts in the right order without you babysitting the handoffs." } },{ "@type": "Question", "name": "How do per-agent budgets and cost tracking work?", "acceptedAnswer": { "@type": "Answer", "text": "You set a token budget per agent, and live fleet monitoring tracks consumption across the roster. Cost numbers are real, not estimates from vibes: the Activity tab reads the JSONL transcripts Claude Code writes and surfaces actual token counts plus estimated USD cost per agent per session, backed by a durable cost ledger that survives restarts. The budget pairs with a circuit breaker that steers, then constrains, then stops an agent that loops or blows its cap." } },{ "@type": "Question", "name": "When should I watch the office floor versus the Command Center?", "acceptedAnswer": { "@type": "Answer", "text": "The floor is for ambient awareness and single-agent moments — seeing who's working, watching envelopes fly, dropping into one terminal. The Command Center is for management questions: what's queued and blocked, what each agent has spent, whether CI is green, and what fires next on the schedule. Roughly: floor for one agent right now, board for the whole fleet over time." } },@@ -135,7 +135,7 @@<div class="post-wrap wrap"><div class="prose">- <div class="callout tldr"><span class="ic">TL;DR</span><p>The office floor is fun to watch, but you don't manage a team by staring at desks. Munder Difflin's <strong>Command Center</strong> is the management view: a <strong>dependency-aware task kanban</strong>, <strong>live fleet monitoring with per-agent token budgets</strong>, <strong>real cost telemetry</strong> backed by a durable ledger, <strong>OpenTelemetry observability</strong> with a per-agent tool-span waterfall, plus GitHub issue ingestion, a CI watcher, and a Schedules tab. Rule of thumb: <strong>watch the floor for one agent right now, watch the board for the whole fleet over time</strong>.</p></div>+ <div class="callout tldr"><span class="ic">TL;DR</span><p>The office floor is fun to watch, but you don't manage a team by staring at desks. Munder Difflin's <strong>Command Center</strong> is the management view: a <strong>dependency-aware task kanban</strong>, <strong>live fleet monitoring with per-agent token budgets</strong>, <strong>real cost telemetry</strong> backed by a durable ledger, <strong>OpenTelemetry observability</strong> with a per-agent tool-span waterfall, plus GitHub issue ingestion, a CI watcher, and a Triggers tab. Rule of thumb: <strong>watch the floor for one agent right now, watch the board for the whole fleet over time</strong>.</p></div><video controls preload="none" playsinline poster="/media/demo/features-poster.jpg" style="width:100%; border-radius:12px; margin:12px 0 24px;"><source src="/media/demo/features.mp4" type="video/mp4" /></video>@@ -149,7 +149,7 @@<li><strong>Memory</strong> — semantic search over the shared memory palace, plain text search, and a memory graph.</li><li><strong>Activity</strong> — the append-only event log, the blackboard, real token telemetry, the observability view, and a CI watcher.</li><li><strong>Tasks</strong> — the kanban board.</li>-<li><strong>Schedules</strong> — recurring missions and the adaptive heartbeat, with last/next-fired times.</li>+<li><strong>Triggers</strong> — everything that starts work without you, grouped by kind: schedules (recurring missions and the adaptive heartbeat, with last/next-fired times), context, webhooks, and organization.</li></ul><p>You could run the hive from the floor alone. But once you have more than two or three agents, the Command Center is where the actual decisions happen.</p><h2 id="the-task-kanban-work-as-a-board-not-a-chat-log" tabindex="-1">The task kanban: work as a board, not a chat log <a class="anchor" href="#the-task-kanban-work-as-a-board-not-a-chat-log" aria-hidden="true">#</a></h2>@@ -164,8 +164,8 @@<p><strong>Per-agent token budgets.</strong> You set a budget per agent, and live fleet monitoring tracks consumption across the whole roster against it. Budgets pair with the <strong>circuit breaker</strong>, which handles the runaway case on a ladder: <em>steer</em> (nudge the agent), then <em>constrain</em>, then <em>stop</em>. An agent that loops, storms errors, or blows through its cap gets caught by machinery, not by you noticing the bill.</p><p><strong>Real telemetry.</strong> The Activity tab doesn’t estimate from message counts — it reads the JSONL transcripts Claude Code writes to <code>~/.claude/projects/</code> and surfaces <strong>actual token counts and estimated USD cost per agent, per session</strong>, backed by a <strong>durable cost ledger</strong> that survives app restarts. Yesterday’s spend is still there this morning, attributed to the agent that spent it.</p><p><strong>Observability.</strong> Also in Activity: a live <strong>OpenTelemetry collector</strong> with per-model cost attribution, a fleet grid, and a <strong>per-agent tool-span waterfall</strong> — the “what exactly is this agent doing, step by step, and what does each step cost” view. It’s the same discipline we covered in <a href="/blog/observability-for-agent-fleets/">observability for agent fleets</a>, built into the harness instead of bolted on.</p>-<h2 id="schedules-the-boards-fourth-dimension" tabindex="-1">Schedules: the board’s fourth dimension <a class="anchor" href="#schedules-the-boards-fourth-dimension" aria-hidden="true">#</a></h2>-<p>The kanban answers “what’s in flight.” The <strong>Schedules tab</strong> answers “what happens next without me.” Recurring missions carry a label, an interval, a target agent, and a body, and the tab shows last-fired and next-fired times, so drift is visible. A scheduler <strong>heartbeat</strong> re-engages the floor when it goes quiet. Together with the board, it turns the hive from something you drive into something you supervise — the full pattern is in <a href="/blog/scheduling-autonomous-agent-missions/">scheduling autonomous agent missions</a>.</p>+<h2 id="triggers-the-boards-fourth-dimension" tabindex="-1">Triggers: the board’s fourth dimension <a class="anchor" href="#triggers-the-boards-fourth-dimension" aria-hidden="true">#</a></h2>+<p>The kanban answers “what’s in flight.” The <strong>Triggers tab</strong> answers “what happens next without me” — every way the hive wakes up when you aren’t typing. <strong>Schedules</strong> are the first and oldest of them: recurring missions carry a label, an interval, a target agent, and a body, and the tab shows last-fired and next-fired times, so drift is visible. A scheduler <strong>heartbeat</strong> re-engages the floor when it goes quiet. Together with the board, it turns the hive from something you drive into something you supervise — the full pattern is in <a href="/blog/scheduling-autonomous-agent-missions/">scheduling autonomous agent missions</a>.</p><h2 id="floor-or-board-a-simple-rule" tabindex="-1">Floor or board? A simple rule <a class="anchor" href="#floor-or-board-a-simple-rule" aria-hidden="true">#</a></h2><p>Both views are the same hive, so this is about attention, not data:</p><ul>@@ -183,7 +183,7 @@<div class="qa"><p class="q">What is the Command Center in Munder Difflin?</p>- <p class="a">It's Michael's control surface — the management view of the whole hive. It has tabs for the orchestrator Terminal, the Floor (roster, dispatch, per-agent model selector, live fleet monitoring), Memory (semantic search plus a memory graph), Activity (event log, board, real token telemetry, observability, and a CI watcher), Tasks (a dependency-aware kanban board), and Schedules (recurring missions with last/next-fired times).</p>+ <p class="a">It's Michael's control surface — the management view of the whole hive. It has tabs for the orchestrator Terminal, the Floor (roster, dispatch, per-agent model selector, live fleet monitoring), Memory (semantic search plus a memory graph), Activity (event log, board, real token telemetry, observability, and a CI watcher), Tasks (a dependency-aware kanban board), and Triggers (everything that starts work without you — schedules with last/next-fired times, context, webhooks, and organization).</p></div><div class="qa">@@ -227,7 +227,7 @@<aside class="toc-rail" aria-label="Table of contents"><div class="tt">On this page</div><ol>- <li class="lvl-2"><a href="#whats-in-the-command-center">What’s in the Command Center</a></li><li class="lvl-2"><a href="#the-task-kanban-work-as-a-board-not-a-chat-log">The task kanban: work as a board, not a chat log</a></li><li class="lvl-2"><a href="#fleet-status-the-roster-at-a-glance">Fleet status: the roster at a glance</a></li><li class="lvl-2"><a href="#budgets-and-cost-real-numbers-not-vibes">Budgets and cost: real numbers, not vibes</a></li><li class="lvl-2"><a href="#schedules-the-boards-fourth-dimension">Schedules: the board’s fourth dimension</a></li><li class="lvl-2"><a href="#floor-or-board-a-simple-rule">Floor or board? A simple rule</a></li><li class="lvl-2"><a href="#try-it">Try it</a></li>+ <li class="lvl-2"><a href="#whats-in-the-command-center">What’s in the Command Center</a></li><li class="lvl-2"><a href="#the-task-kanban-work-as-a-board-not-a-chat-log">The task kanban: work as a board, not a chat log</a></li><li class="lvl-2"><a href="#fleet-status-the-roster-at-a-glance">Fleet status: the roster at a glance</a></li><li class="lvl-2"><a href="#budgets-and-cost-real-numbers-not-vibes">Budgets and cost: real numbers, not vibes</a></li><li class="lvl-2"><a href="#triggers-the-boards-fourth-dimension">Triggers: the board’s fourth dimension</a></li><li class="lvl-2"><a href="#floor-or-board-a-simple-rule">Floor or board? A simple rule</a></li><li class="lvl-2"><a href="#try-it">Try it</a></li></ol></aside>diff --git a/docs/blog/compressing-agent-memory/index.html b/docs/blog/compressing-agent-memory/index.htmlindex dbc142aa..b5c45c1f 100644--- a/docs/blog/compressing-agent-memory/index.html+++ b/docs/blog/compressing-agent-memory/index.html@@ -270,56 +270,56 @@ without forgetting; it’s free and open source.</p><h2>Related in Internals</h2><div class="post-grid"><article class="card">- <a class="thumb t-internals" href="/blog/why-our-auto-update-never-ran/" aria-hidden="true" tabindex="-1">+ <a class="thumb t-internals" href="/blog/when-the-cli-stops-listening/" aria-hidden="true" tabindex="-1"><span>INTERNALS</span></a><div class="body"><div class="meta">- <time datetime="2026-08-08">Aug 8, 2026</time>+ <time datetime="2026-08-11">Aug 11, 2026</time><span class="dot" aria-hidden="true"></span>- <span>5 min</span>+ <span>6 min</span></div>- <h3><a href="/blog/why-our-auto-update-never-ran/">Our Auto-Update Never Ran Once: A CommonJS Export That Vanished Into an ESM Namespace</a></h3>- <p class="dek">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.</p>+ <h3><a href="/blog/when-the-cli-stops-listening/">When the CLI Stops Listening: Rate Limits Are Silent Data Loss</a></h3>+ <p class="dek">A rate-limited coding CLI doesn't reject your input — it discards it. No error, no bounce, no record. Munder Difflin was typing into that void for months. Here's how we detect the wall, hold the whole account behind it, and drain the backlog on the other side.</p><div class="foot"><span class="tag kind">Internals</span>- <a class="more" href="/blog/why-our-auto-update-never-ran/" aria-label="Read: Our Auto-Update Never Ran Once: A CommonJS Export That Vanished Into an ESM Namespace">Read →</a>+ <a class="more" href="/blog/when-the-cli-stops-listening/" aria-label="Read: When the CLI Stops Listening: Rate Limits Are Silent Data Loss">Read →</a></div></div></article><article class="card">- <a class="thumb t-internals" href="/blog/hire-manifest-untrusted-input/" aria-hidden="true" tabindex="-1">+ <a class="thumb t-internals" href="/blog/why-our-auto-update-never-ran/" aria-hidden="true" tabindex="-1"><span>INTERNALS</span></a><div class="body"><div class="meta">- <time datetime="2026-06-15">Jun 15, 2026</time>+ <time datetime="2026-08-08">Aug 8, 2026</time><span class="dot" aria-hidden="true"></span>- <span>12 min</span>+ <span>5 min</span></div>- <h3><a href="/blog/hire-manifest-untrusted-input/">Treating a Hire Manifest as Untrusted Input</a></h3>- <p class="dek">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.</p>+ <h3><a href="/blog/why-our-auto-update-never-ran/">Our Auto-Update Never Ran Once: A CommonJS Export That Vanished Into an ESM Namespace</a></h3>+ <p class="dek">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.</p><div class="foot"><span class="tag kind">Internals</span>- <a class="more" href="/blog/hire-manifest-untrusted-input/" aria-label="Read: Treating a Hire Manifest as Untrusted Input">Read →</a>+ <a class="more" href="/blog/why-our-auto-update-never-ran/" aria-label="Read: Our Auto-Update Never Ran Once: A CommonJS Export That Vanished Into an ESM Namespace">Read →</a></div></div></article><article class="card">- <a class="thumb t-internals" href="/blog/architecture-two-planes-one-renderer/" aria-hidden="true" tabindex="-1">+ <a class="thumb t-internals" href="/blog/hire-manifest-untrusted-input/" aria-hidden="true" tabindex="-1"><span>INTERNALS</span></a><div class="body"><div class="meta">- <time datetime="2026-06-04">Jun 4, 2026</time>+ <time datetime="2026-06-15">Jun 15, 2026</time><span class="dot" aria-hidden="true"></span>- <span>5 min</span>+ <span>12 min</span></div>- <h3><a href="/blog/architecture-two-planes-one-renderer/">Munder Difflin's Architecture: Two Data Planes, One Renderer</a></h3>- <p class="dek">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.</p>+ <h3><a href="/blog/hire-manifest-untrusted-input/">Treating a Hire Manifest as Untrusted Input</a></h3>+ <p class="dek">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.</p><div class="foot"><span class="tag kind">Internals</span>- <a class="more" href="/blog/architecture-two-planes-one-renderer/" aria-label="Read: Munder Difflin's Architecture: Two Data Planes, One Renderer">Read →</a>+ <a class="more" href="/blog/hire-manifest-untrusted-input/" aria-label="Read: Treating a Hire Manifest as Untrusted Input">Read →</a></div></div></article>diff --git a/docs/blog/feed.xml b/docs/blog/feed.xmlindex 221425a3..6c82980b 100644--- a/docs/blog/feed.xml+++ b/docs/blog/feed.xml@@ -4,9 +4,17 @@<subtitle>Guides, deep dives, and comparisons on running multi-agent Claude Code: orchestration, agent memory, automation, and the tooling landscape.</subtitle><link href="https://munderdiffl.in/blog/feed.xml" rel="self" /><link href="https://munderdiffl.in/blog/" />- <updated>2026-08-08T00:00:00.000Z</updated>+ <updated>2026-08-11T00:00:00.000Z</updated><id>https://munderdiffl.in/blog/</id><author><name>Chaitanya Giri</name><uri>https://munderdiffl.in</uri></author>+ <entry>+ <title>When the CLI Stops Listening: Rate Limits Are Silent Data Loss</title>+ <link href="https://munderdiffl.in/blog/when-the-cli-stops-listening/" />+ <id>https://munderdiffl.in/blog/when-the-cli-stops-listening/</id>+ <published>2026-08-11T00:00:00.000Z</published>+ <updated>2026-08-11T00:00:00.000Z</updated><category term="Internals" />+ <summary>A rate-limited coding CLI doesn't reject your input — it discards it. No error, no bounce, no record. Munder Difflin was typing into that void for months. Here's how we detect the wall, hold the whole account behind it, and drain the backlog on the other side.</summary>+ </entry><entry><title>What's Up With Munder Difflin: Six Weeks, Four Releases, and the Part of the Stack You Actually Own</title><link href="https://munderdiffl.in/blog/whats-up-with-munder-difflin/" />@@ -479,12 +487,4 @@<updated>2026-06-04T00:00:00.000Z</updated><category term="Guides" /><summary>How to debug a multi-agent system: use the event log, per-agent terminals, message trails, and git history to find why a hive of AI agents went sideways.</summary></entry>- <entry>- <title>Do More With Less: Smart Model Routing Across Agents</title>- <link href="https://munderdiffl.in/blog/do-more-with-less-model-routing/" />- <id>https://munderdiffl.in/blog/do-more-with-less-model-routing/</id>- <published>2026-06-04T00:00:00.000Z</published>- <updated>2026-06-04T00:00:00.000Z</updated><category term="Concepts" />- <summary>Why a hive of agents shouldn't all run the biggest model — and how routing the right task to the right model cuts cost and latency without losing quality.</summary>- </entry></feed>diff --git a/docs/blog/file-based-coordination-vs-message-queues/index.html b/docs/blog/file-based-coordination-vs-message-queues/index.htmlindex e3aff91f..8266feeb 100644--- a/docs/blog/file-based-coordination-vs-message-queues/index.html+++ b/docs/blog/file-based-coordination-vs-message-queues/index.html@@ -261,56 +261,56 @@ durable, git-versioned, and debuggable by just looking.<h2>Related in Internals</h2><div class="post-grid"><article class="card">- <a class="thumb t-internals" href="/blog/why-our-auto-update-never-ran/" aria-hidden="true" tabindex="-1">+ <a class="thumb t-internals" href="/blog/when-the-cli-stops-listening/" aria-hidden="true" tabindex="-1"><span>INTERNALS</span></a><div class="body"><div class="meta">- <time datetime="2026-08-08">Aug 8, 2026</time>+ <time datetime="2026-08-11">Aug 11, 2026</time><span class="dot" aria-hidden="true"></span>- <span>5 min</span>+ <span>6 min</span></div>- <h3><a href="/blog/why-our-auto-update-never-ran/">Our Auto-Update Never Ran Once: A CommonJS Export That Vanished Into an ESM Namespace</a></h3>- <p class="dek">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.</p>+ <h3><a href="/blog/when-the-cli-stops-listening/">When the CLI Stops Listening: Rate Limits Are Silent Data Loss</a></h3>+ <p class="dek">A rate-limited coding CLI doesn't reject your input — it discards it. No error, no bounce, no record. Munder Difflin was typing into that void for months. Here's how we detect the wall, hold the whole account behind it, and drain the backlog on the other side.</p><div class="foot"><span class="tag kind">Internals</span>- <a class="more" href="/blog/why-our-auto-update-never-ran/" aria-label="Read: Our Auto-Update Never Ran Once: A CommonJS Export That Vanished Into an ESM Namespace">Read →</a>+ <a class="more" href="/blog/when-the-cli-stops-listening/" aria-label="Read: When the CLI Stops Listening: Rate Limits Are Silent Data Loss">Read →</a></div></div></article><article class="card">- <a class="thumb t-internals" href="/blog/hire-manifest-untrusted-input/" aria-hidden="true" tabindex="-1">+ <a class="thumb t-internals" href="/blog/why-our-auto-update-never-ran/" aria-hidden="true" tabindex="-1"><span>INTERNALS</span></a><div class="body"><div class="meta">- <time datetime="2026-06-15">Jun 15, 2026</time>+ <time datetime="2026-08-08">Aug 8, 2026</time><span class="dot" aria-hidden="true"></span>- <span>12 min</span>+ <span>5 min</span></div>- <h3><a href="/blog/hire-manifest-untrusted-input/">Treating a Hire Manifest as Untrusted Input</a></h3>- <p class="dek">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.</p>+ <h3><a href="/blog/why-our-auto-update-never-ran/">Our Auto-Update Never Ran Once: A CommonJS Export That Vanished Into an ESM Namespace</a></h3>+ <p class="dek">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.</p><div class="foot"><span class="tag kind">Internals</span>- <a class="more" href="/blog/hire-manifest-untrusted-input/" aria-label="Read: Treating a Hire Manifest as Untrusted Input">Read →</a>+ <a class="more" href="/blog/why-our-auto-update-never-ran/" aria-label="Read: Our Auto-Update Never Ran Once: A CommonJS Export That Vanished Into an ESM Namespace">Read →</a></div></div></article><article class="card">- <a class="thumb t-internals" href="/blog/compressing-agent-memory/" aria-hidden="true" tabindex="-1">+ <a class="thumb t-internals" href="/blog/hire-manifest-untrusted-input/" aria-hidden="true" tabindex="-1"><span>INTERNALS</span></a><div class="body"><div class="meta">- <time datetime="2026-06-05">Jun 5, 2026</time>+ <time datetime="2026-06-15">Jun 15, 2026</time><span class="dot" aria-hidden="true"></span>- <span>5 min</span>+ <span>12 min</span></div>- <h3><a href="/blog/compressing-agent-memory/">Compressing Agent Memory Without Losing the Original</a></h3>- <p class="dek">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.</p>+ <h3><a href="/blog/hire-manifest-untrusted-input/">Treating a Hire Manifest as Untrusted Input</a></h3>+ <p class="dek">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.</p><div class="foot"><span class="tag kind">Internals</span>- <a class="more" href="/blog/compressing-agent-memory/" aria-label="Read: Compressing Agent Memory Without Losing the Original">Read →</a>+ <a class="more" href="/blog/hire-manifest-untrusted-input/" aria-label="Read: Treating a Hire Manifest as Untrusted Input">Read →</a></div></div></article>diff --git a/docs/blog/hire-manifest-untrusted-input/index.html b/docs/blog/hire-manifest-untrusted-input/index.htmlindex 8862c636..ed617cda 100644--- a/docs/blog/hire-manifest-untrusted-input/index.html+++ b/docs/blog/hire-manifest-untrusted-input/index.html@@ -286,56 +286,56 @@ for hop in 0..5: // cap at 5 hops<h2>Related in Internals</h2><div class="post-grid"><article class="card">- <a class="thumb t-internals" href="/blog/why-our-auto-update-never-ran/" aria-hidden="true" tabindex="-1">+ <a class="thumb t-internals" href="/blog/when-the-cli-stops-listening/" aria-hidden="true" tabindex="-1"><span>INTERNALS</span></a><div class="body"><div class="meta">- <time datetime="2026-08-08">Aug 8, 2026</time>+ <time datetime="2026-08-11">Aug 11, 2026</time><span class="dot" aria-hidden="true"></span>- <span>5 min</span>+ <span>6 min</span></div>- <h3><a href="/blog/why-our-auto-update-never-ran/">Our Auto-Update Never Ran Once: A CommonJS Export That Vanished Into an ESM Namespace</a></h3>- <p class="dek">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.</p>+ <h3><a href="/blog/when-the-cli-stops-listening/">When the CLI Stops Listening: Rate Limits Are Silent Data Loss</a></h3>+ <p class="dek">A rate-limited coding CLI doesn't reject your input — it discards it. No error, no bounce, no record. Munder Difflin was typing into that void for months. Here's how we detect the wall, hold the whole account behind it, and drain the backlog on the other side.</p><div class="foot"><span class="tag kind">Internals</span>- <a class="more" href="/blog/why-our-auto-update-never-ran/" aria-label="Read: Our Auto-Update Never Ran Once: A CommonJS Export That Vanished Into an ESM Namespace">Read →</a>+ <a class="more" href="/blog/when-the-cli-stops-listening/" aria-label="Read: When the CLI Stops Listening: Rate Limits Are Silent Data Loss">Read →</a></div></div></article><article class="card">- <a class="thumb t-internals" href="/blog/compressing-agent-memory/" aria-hidden="true" tabindex="-1">+ <a class="thumb t-internals" href="/blog/why-our-auto-update-never-ran/" aria-hidden="true" tabindex="-1"><span>INTERNALS</span></a><div class="body"><div class="meta">- <time datetime="2026-06-05">Jun 5, 2026</time>+ <time datetime="2026-08-08">Aug 8, 2026</time><span class="dot" aria-hidden="true"></span><span>5 min</span></div>- <h3><a href="/blog/compressing-agent-memory/">Compressing Agent Memory Without Losing the Original</a></h3>- <p class="dek">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.</p>+ <h3><a href="/blog/why-our-auto-update-never-ran/">Our Auto-Update Never Ran Once: A CommonJS Export That Vanished Into an ESM Namespace</a></h3>+ <p class="dek">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.</p><div class="foot"><span class="tag kind">Internals</span>- <a class="more" href="/blog/compressing-agent-memory/" aria-label="Read: Compressing Agent Memory Without Losing the Original">Read →</a>+ <a class="more" href="/blog/why-our-auto-update-never-ran/" aria-label="Read: Our Auto-Update Never Ran Once: A CommonJS Export That Vanished Into an ESM Namespace">Read →</a></div></div></article><article class="card">- <a class="thumb t-internals" href="/blog/architecture-two-planes-one-renderer/" aria-hidden="true" tabindex="-1">+ <a class="thumb t-internals" href="/blog/compressing-agent-memory/" aria-hidden="true" tabindex="-1"><span>INTERNALS</span></a><div class="body"><div class="meta">- <time datetime="2026-06-04">Jun 4, 2026</time>+ <time datetime="2026-06-05">Jun 5, 2026</time><span class="dot" aria-hidden="true"></span><span>5 min</span></div>- <h3><a href="/blog/architecture-two-planes-one-renderer/">Munder Difflin's Architecture: Two Data Planes, One Renderer</a></h3>- <p class="dek">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.</p>+ <h3><a href="/blog/compressing-agent-memory/">Compressing Agent Memory Without Losing the Original</a></h3>+ <p class="dek">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.</p><div class="foot"><span class="tag kind">Internals</span>- <a class="more" href="/blog/architecture-two-planes-one-renderer/" aria-label="Read: Munder Difflin's Architecture: Two Data Planes, One Renderer">Read →</a>+ <a class="more" href="/blog/compressing-agent-memory/" aria-label="Read: Compressing Agent Memory Without Losing the Original">Read →</a></div></div></article>diff --git a/docs/blog/how-the-god-orchestrator-works/index.html b/docs/blog/how-the-god-orchestrator-works/index.htmlindex ba64395b..eeb2f912 100644--- a/docs/blog/how-the-god-orchestrator-works/index.html+++ b/docs/blog/how-the-god-orchestrator-works/index.html@@ -250,9 +250,10 @@ routes to the human rather than guessing. The default is “ask,” not “act.single-writer and single-committer principles the orchestrator depends on.</p><h2 id="the-orchestrators-interface" tabindex="-1">The orchestrator’s interface <a class="anchor" href="#the-orchestrators-interface" aria-hidden="true">#</a></h2><p>In v0.1.6, Michael’s interface expands significantly. His sidebar becomes a full Command Center: a-Tasks tab gives him a kanban board to track work across agents with dependency links; a Schedules tab-lets you pre-program recurring directives so the floor stays active between your check-ins; an Activity-tab shows real token and dollar cost per agent drawn from transcript files; and a GitHub Issues section+Tasks tab gives him a kanban board to track work across agents with dependency links; a Triggers tab+collects everything that wakes the hive without you — schedules first among them — so you can+pre-program recurring directives and the floor stays active between your check-ins; an Activity tab+shows real token and dollar cost per agent drawn from transcript files; and a GitHub Issues sectionin the Floor tab lets him receive and route repo issues directly. The orchestrator is the same agent —the harness simply gives him better tools.</p><h2 id="faq" tabindex="-1">FAQ <a class="anchor" href="#faq" aria-hidden="true">#</a></h2>diff --git a/docs/blog/how-to-install-and-use-munder-difflin/index.html b/docs/blog/how-to-install-and-use-munder-difflin/index.htmlindex 8a2fb3da..1a997a1e 100644--- a/docs/blog/how-to-install-and-use-munder-difflin/index.html+++ b/docs/blog/how-to-install-and-use-munder-difflin/index.html@@ -301,10 +301,10 @@ agent memories) and a memory graph.</li>directly from your Claude Code transcript files).</li><li><strong>Tasks</strong> — a dependency-aware kanban board. Add tasks with assignees, priorities, and <code>dependsOn</code>links; Michael and his team track status here.</li>-<li><strong>Schedules</strong> — recurring missions. Set a label, interval (1h / 6h / 24h / weekly), and a directive+<li><strong>Triggers</strong> — every way the office wakes itself, starting with recurring missions. Set a label, interval (1h / 6h / 24h / weekly), and a directivebody; the harness dispatches it to the target agent automatically, no human needed.</li></ul>-<p>For long-running floors, the Schedules tab is the most powerful: set a ‘30-minute floor check’ mission+<p>For long-running floors, the Triggers tab is the most powerful: set a ‘30-minute floor check’ missionpointing at Michael with a directive like ‘Are all agents making progress? Re-engage anyone idle.’ —and the harness keeps the team moving even when you’re away.</p><h2 id="tips-for-best-results" tabindex="-1">Tips for best results <a class="anchor" href="#tips-for-best-results" aria-hidden="true">#</a></h2>diff --git a/docs/blog/index.html b/docs/blog/index.htmlindex 92ebf7f6..f81493d4 100644--- a/docs/blog/index.html+++ b/docs/blog/index.html@@ -84,13 +84,13 @@building a self-coordinating hive of agents with a GOD orchestrator you talk to.</p><div class="filters" role="navigation" aria-label="Topics">- <a class="chip" aria-current="page">All<span class="ct">119</span></a>+ <a class="chip" aria-current="page">All<span class="ct">120</span></a><a class="chip" href="/blog/topics/guides/">guides<span class="ct">34</span></a><a class="chip" href="/blog/topics/concepts/">concepts<span class="ct">21</span></a>- <a class="chip" href="/blog/topics/internals/">internals<span class="ct">17</span></a>+ <a class="chip" href="/blog/topics/internals/">internals<span class="ct">18</span></a><a class="chip" href="/blog/topics/comparisons/">comparisons<span class="ct">17</span></a>@@ -107,6 +107,30 @@<div class="wrap featured"><article class="card">+ <a class="thumb t-internals" href="/blog/when-the-cli-stops-listening/" aria-hidden="true" tabindex="-1">+ <span>INTERNALS</span>+ </a>+ <div class="body">+ <div class="meta">+ <time datetime="2026-08-11">Aug 11, 2026</time>+ <span class="dot" aria-hidden="true"></span>+ <span>6 min</span>+ </div>+ <h3><a href="/blog/when-the-cli-stops-listening/">When the CLI Stops Listening: Rate Limits Are Silent Data Loss</a></h3>+ <p class="dek">A rate-limited coding CLI doesn't reject your input — it discards it. No error, no bounce, no record. Munder Difflin was typing into that void for months. Here's how we detect the wall, hold the whole account behind it, and drain the backlog on the other side.</p>+ <div class="foot">+ <span class="tag kind">Internals</span>+ <a class="more" href="/blog/when-the-cli-stops-listening/" aria-label="Read: When the CLI Stops Listening: Rate Limits Are Silent Data Loss">Read →</a>+ </div>+ </div>+</article>++</div>+++<section class="wrap">+ <div class="post-grid">+ <article class="card"><a class="thumb t-story" href="/blog/whats-up-with-munder-difflin/" aria-hidden="true" tabindex="-1"><span>STORY</span></a>@@ -124,13 +148,7 @@</div></div></article>--</div>---<section class="wrap">- <div class="post-grid">- <article class="card">+<article class="card"><a class="thumb t-internals" href="/blog/why-our-auto-update-never-ran/" aria-hidden="true" tabindex="-1"><span>INTERNALS</span></a>diff --git a/docs/blog/node-pty-electron-real-terminals/index.html b/docs/blog/node-pty-electron-real-terminals/index.htmlindex 40332a0a..ed71dd33 100644--- a/docs/blog/node-pty-electron-real-terminals/index.html+++ b/docs/blog/node-pty-electron-real-terminals/index.html@@ -323,56 +323,56 @@ real terminals driving real agents; it’s free and open source.</p><h2>Related in Internals</h2><div class="post-grid"><article class="card">- <a class="thumb t-internals" href="/blog/why-our-auto-update-never-ran/" aria-hidden="true" tabindex="-1">+ <a class="thumb t-internals" href="/blog/when-the-cli-stops-listening/" aria-hidden="true" tabindex="-1"><span>INTERNALS</span></a><div class="body"><div class="meta">- <time datetime="2026-08-08">Aug 8, 2026</time>+ <time datetime="2026-08-11">Aug 11, 2026</time><span class="dot" aria-hidden="true"></span>- <span>5 min</span>+ <span>6 min</span></div>- <h3><a href="/blog/why-our-auto-update-never-ran/">Our Auto-Update Never Ran Once: A CommonJS Export That Vanished Into an ESM Namespace</a></h3>- <p class="dek">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.</p>+ <h3><a href="/blog/when-the-cli-stops-listening/">When the CLI Stops Listening: Rate Limits Are Silent Data Loss</a></h3>+ <p class="dek">A rate-limited coding CLI doesn't reject your input — it discards it. No error, no bounce, no record. Munder Difflin was typing into that void for months. Here's how we detect the wall, hold the whole account behind it, and drain the backlog on the other side.</p><div class="foot"><span class="tag kind">Internals</span>- <a class="more" href="/blog/why-our-auto-update-never-ran/" aria-label="Read: Our Auto-Update Never Ran Once: A CommonJS Export That Vanished Into an ESM Namespace">Read →</a>+ <a class="more" href="/blog/when-the-cli-stops-listening/" aria-label="Read: When the CLI Stops Listening: Rate Limits Are Silent Data Loss">Read →</a></div></div></article><article class="card">- <a class="thumb t-internals" href="/blog/hire-manifest-untrusted-input/" aria-hidden="true" tabindex="-1">+ <a class="thumb t-internals" href="/blog/why-our-auto-update-never-ran/" aria-hidden="true" tabindex="-1"><span>INTERNALS</span></a><div class="body"><div class="meta">- <time datetime="2026-06-15">Jun 15, 2026</time>+ <time datetime="2026-08-08">Aug 8, 2026</time><span class="dot" aria-hidden="true"></span>- <span>12 min</span>+ <span>5 min</span></div>- <h3><a href="/blog/hire-manifest-untrusted-input/">Treating a Hire Manifest as Untrusted Input</a></h3>- <p class="dek">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.</p>+ <h3><a href="/blog/why-our-auto-update-never-ran/">Our Auto-Update Never Ran Once: A CommonJS Export That Vanished Into an ESM Namespace</a></h3>+ <p class="dek">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.</p><div class="foot"><span class="tag kind">Internals</span>- <a class="more" href="/blog/hire-manifest-untrusted-input/" aria-label="Read: Treating a Hire Manifest as Untrusted Input">Read →</a>+ <a class="more" href="/blog/why-our-auto-update-never-ran/" aria-label="Read: Our Auto-Update Never Ran Once: A CommonJS Export That Vanished Into an ESM Namespace">Read →</a></div></div></article><article class="card">- <a class="thumb t-internals" href="/blog/compressing-agent-memory/" aria-hidden="true" tabindex="-1">+ <a class="thumb t-internals" href="/blog/hire-manifest-untrusted-input/" aria-hidden="true" tabindex="-1"><span>INTERNALS</span></a><div class="body"><div class="meta">- <time datetime="2026-06-05">Jun 5, 2026</time>+ <time datetime="2026-06-15">Jun 15, 2026</time><span class="dot" aria-hidden="true"></span>- <span>5 min</span>+ <span>12 min</span></div>- <h3><a href="/blog/compressing-agent-memory/">Compressing Agent Memory Without Losing the Original</a></h3>- <p class="dek">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.</p>+ <h3><a href="/blog/hire-manifest-untrusted-input/">Treating a Hire Manifest as Untrusted Input</a></h3>+ <p class="dek">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.</p><div class="foot"><span class="tag kind">Internals</span>- <a class="more" href="/blog/compressing-agent-memory/" aria-label="Read: Compressing Agent Memory Without Losing the Original">Read →</a>+ <a class="more" href="/blog/hire-manifest-untrusted-input/" aria-label="Read: Treating a Hire Manifest as Untrusted Input">Read →</a></div></div></article>diff --git a/docs/blog/observability-for-agent-fleets/index.html b/docs/blog/observability-for-agent-fleets/index.htmlindex 48eb1433..ee0d613e 100644--- a/docs/blog/observability-for-agent-fleets/index.html+++ b/docs/blog/observability-for-agent-fleets/index.html@@ -260,56 +260,56 @@ open source.</p><h2>Related in Internals</h2><div class="post-grid"><article class="card">- <a class="thumb t-internals" href="/blog/why-our-auto-update-never-ran/" aria-hidden="true" tabindex="-1">+ <a class="thumb t-internals" href="/blog/when-the-cli-stops-listening/" aria-hidden="true" tabindex="-1"><span>INTERNALS</span></a><div class="body"><div class="meta">- <time datetime="2026-08-08">Aug 8, 2026</time>+ <time datetime="2026-08-11">Aug 11, 2026</time><span class="dot" aria-hidden="true"></span>- <span>5 min</span>+ <span>6 min</span></div>- <h3><a href="/blog/why-our-auto-update-never-ran/">Our Auto-Update Never Ran Once: A CommonJS Export That Vanished Into an ESM Namespace</a></h3>- <p class="dek">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.</p>+ <h3><a href="/blog/when-the-cli-stops-listening/">When the CLI Stops Listening: Rate Limits Are Silent Data Loss</a></h3>+ <p class="dek">A rate-limited coding CLI doesn't reject your input — it discards it. No error, no bounce, no record. Munder Difflin was typing into that void for months. Here's how we detect the wall, hold the whole account behind it, and drain the backlog on the other side.</p><div class="foot"><span class="tag kind">Internals</span>- <a class="more" href="/blog/why-our-auto-update-never-ran/" aria-label="Read: Our Auto-Update Never Ran Once: A CommonJS Export That Vanished Into an ESM Namespace">Read →</a>+ <a class="more" href="/blog/when-the-cli-stops-listening/" aria-label="Read: When the CLI Stops Listening: Rate Limits Are Silent Data Loss">Read →</a></div></div></article><article class="card">- <a class="thumb t-internals" href="/blog/hire-manifest-untrusted-input/" aria-hidden="true" tabindex="-1">+ <a class="thumb t-internals" href="/blog/why-our-auto-update-never-ran/" aria-hidden="true" tabindex="-1"><span>INTERNALS</span></a><div class="body"><div class="meta">- <time datetime="2026-06-15">Jun 15, 2026</time>+ <time datetime="2026-08-08">Aug 8, 2026</time><span class="dot" aria-hidden="true"></span>- <span>12 min</span>+ <span>5 min</span></div>- <h3><a href="/blog/hire-manifest-untrusted-input/">Treating a Hire Manifest as Untrusted Input</a></h3>- <p class="dek">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.</p>+ <h3><a href="/blog/why-our-auto-update-never-ran/">Our Auto-Update Never Ran Once: A CommonJS Export That Vanished Into an ESM Namespace</a></h3>+ <p class="dek">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.</p><div class="foot"><span class="tag kind">Internals</span>- <a class="more" href="/blog/hire-manifest-untrusted-input/" aria-label="Read: Treating a Hire Manifest as Untrusted Input">Read →</a>+ <a class="more" href="/blog/why-our-auto-update-never-ran/" aria-label="Read: Our Auto-Update Never Ran Once: A CommonJS Export That Vanished Into an ESM Namespace">Read →</a></div></div></article><article class="card">- <a class="thumb t-internals" href="/blog/compressing-agent-memory/" aria-hidden="true" tabindex="-1">+ <a class="thumb t-internals" href="/blog/hire-manifest-untrusted-input/" aria-hidden="true" tabindex="-1"><span>INTERNALS</span></a><div class="body"><div class="meta">- <time datetime="2026-06-05">Jun 5, 2026</time>+ <time datetime="2026-06-15">Jun 15, 2026</time><span class="dot" aria-hidden="true"></span>- <span>5 min</span>+ <span>12 min</span></div>- <h3><a href="/blog/compressing-agent-memory/">Compressing Agent Memory Without Losing the Original</a></h3>- <p class="dek">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.</p>+ <h3><a href="/blog/hire-manifest-untrusted-input/">Treating a Hire Manifest as Untrusted Input</a></h3>+ <p class="dek">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.</p><div class="foot"><span class="tag kind">Internals</span>- <a class="more" href="/blog/compressing-agent-memory/" aria-label="Read: Compressing Agent Memory Without Losing the Original">Read →</a>+ <a class="more" href="/blog/hire-manifest-untrusted-input/" aria-label="Read: Treating a Hire Manifest as Untrusted Input">Read →</a></div></div></article>diff --git a/docs/blog/recovering-from-agent-failures/index.html b/docs/blog/recovering-from-agent-failures/index.htmlindex 65ade988..3bfc48d7 100644--- a/docs/blog/recovering-from-agent-failures/index.html+++ b/docs/blog/recovering-from-agent-failures/index.html@@ -280,56 +280,56 @@ there to read.</p><h2>Related in Internals</h2><div class="post-grid"><article class="card">- <a class="thumb t-internals" href="/blog/why-our-auto-update-never-ran/" aria-hidden="true" tabindex="-1">+ <a class="thumb t-internals" href="/blog/when-the-cli-stops-listening/" aria-hidden="true" tabindex="-1"><span>INTERNALS</span></a><div class="body"><div class="meta">- <time datetime="2026-08-08">Aug 8, 2026</time>+ <time datetime="2026-08-11">Aug 11, 2026</time><span class="dot" aria-hidden="true"></span>- <span>5 min</span>+ <span>6 min</span></div>- <h3><a href="/blog/why-our-auto-update-never-ran/">Our Auto-Update Never Ran Once: A CommonJS Export That Vanished Into an ESM Namespace</a></h3>- <p class="dek">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.</p>+ <h3><a href="/blog/when-the-cli-stops-listening/">When the CLI Stops Listening: Rate Limits Are Silent Data Loss</a></h3>+ <p class="dek">A rate-limited coding CLI doesn't reject your input — it discards it. No error, no bounce, no record. Munder Difflin was typing into that void for months. Here's how we detect the wall, hold the whole account behind it, and drain the backlog on the other side.</p><div class="foot"><span class="tag kind">Internals</span>- <a class="more" href="/blog/why-our-auto-update-never-ran/" aria-label="Read: Our Auto-Update Never Ran Once: A CommonJS Export That Vanished Into an ESM Namespace">Read →</a>+ <a class="more" href="/blog/when-the-cli-stops-listening/" aria-label="Read: When the CLI Stops Listening: Rate Limits Are Silent Data Loss">Read →</a></div></div></article><article class="card">- <a class="thumb t-internals" href="/blog/hire-manifest-untrusted-input/" aria-hidden="true" tabindex="-1">+ <a class="thumb t-internals" href="/blog/why-our-auto-update-never-ran/" aria-hidden="true" tabindex="-1"><span>INTERNALS</span></a><div class="body"><div class="meta">- <time datetime="2026-06-15">Jun 15, 2026</time>+ <time datetime="2026-08-08">Aug 8, 2026</time><span class="dot" aria-hidden="true"></span>- <span>12 min</span>+ <span>5 min</span></div>- <h3><a href="/blog/hire-manifest-untrusted-input/">Treating a Hire Manifest as Untrusted Input</a></h3>- <p class="dek">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.</p>+ <h3><a href="/blog/why-our-auto-update-never-ran/">Our Auto-Update Never Ran Once: A CommonJS Export That Vanished Into an ESM Namespace</a></h3>+ <p class="dek">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.</p><div class="foot"><span class="tag kind">Internals</span>- <a class="more" href="/blog/hire-manifest-untrusted-input/" aria-label="Read: Treating a Hire Manifest as Untrusted Input">Read →</a>+ <a class="more" href="/blog/why-our-auto-update-never-ran/" aria-label="Read: Our Auto-Update Never Ran Once: A CommonJS Export That Vanished Into an ESM Namespace">Read →</a></div></div></article><article class="card">- <a class="thumb t-internals" href="/blog/compressing-agent-memory/" aria-hidden="true" tabindex="-1">+ <a class="thumb t-internals" href="/blog/hire-manifest-untrusted-input/" aria-hidden="true" tabindex="-1"><span>INTERNALS</span></a><div class="body"><div class="meta">- <time datetime="2026-06-05">Jun 5, 2026</time>+ <time datetime="2026-06-15">Jun 15, 2026</time><span class="dot" aria-hidden="true"></span>- <span>5 min</span>+ <span>12 min</span></div>- <h3><a href="/blog/compressing-agent-memory/">Compressing Agent Memory Without Losing the Original</a></h3>- <p class="dek">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.</p>+ <h3><a href="/blog/hire-manifest-untrusted-input/">Treating a Hire Manifest as Untrusted Input</a></h3>+ <p class="dek">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.</p><div class="foot"><span class="tag kind">Internals</span>- <a class="more" href="/blog/compressing-agent-memory/" aria-label="Read: Compressing Agent Memory Without Losing the Original">Read →</a>+ <a class="more" href="/blog/hire-manifest-untrusted-input/" aria-label="Read: Treating a Hire Manifest as Untrusted Input">Read →</a></div></div></article>diff --git a/docs/blog/rendering-many-live-terminals-performance/index.html b/docs/blog/rendering-many-live-terminals-performance/index.htmlindex a141a78f..5bf2df7f 100644--- a/docs/blog/rendering-many-live-terminals-performance/index.html+++ b/docs/blog/rendering-many-live-terminals-performance/index.html@@ -283,56 +283,56 @@ to run many real terminals without melting your CPU; it’s free and open source<h2>Related in Internals</h2><div class="post-grid"><article class="card">- <a class="thumb t-internals" href="/blog/why-our-auto-update-never-ran/" aria-hidden="true" tabindex="-1">+ <a class="thumb t-internals" href="/blog/when-the-cli-stops-listening/" aria-hidden="true" tabindex="-1"><span>INTERNALS</span></a><div class="body"><div class="meta">- <time datetime="2026-08-08">Aug 8, 2026</time>+ <time datetime="2026-08-11">Aug 11, 2026</time><span class="dot" aria-hidden="true"></span>- <span>5 min</span>+ <span>6 min</span></div>- <h3><a href="/blog/why-our-auto-update-never-ran/">Our Auto-Update Never Ran Once: A CommonJS Export That Vanished Into an ESM Namespace</a></h3>- <p class="dek">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.</p>+ <h3><a href="/blog/when-the-cli-stops-listening/">When the CLI Stops Listening: Rate Limits Are Silent Data Loss</a></h3>+ <p class="dek">A rate-limited coding CLI doesn't reject your input — it discards it. No error, no bounce, no record. Munder Difflin was typing into that void for months. Here's how we detect the wall, hold the whole account behind it, and drain the backlog on the other side.</p><div class="foot"><span class="tag kind">Internals</span>- <a class="more" href="/blog/why-our-auto-update-never-ran/" aria-label="Read: Our Auto-Update Never Ran Once: A CommonJS Export That Vanished Into an ESM Namespace">Read →</a>+ <a class="more" href="/blog/when-the-cli-stops-listening/" aria-label="Read: When the CLI Stops Listening: Rate Limits Are Silent Data Loss">Read →</a></div></div></article><article class="card">- <a class="thumb t-internals" href="/blog/hire-manifest-untrusted-input/" aria-hidden="true" tabindex="-1">+ <a class="thumb t-internals" href="/blog/why-our-auto-update-never-ran/" aria-hidden="true" tabindex="-1"><span>INTERNALS</span></a><div class="body"><div class="meta">- <time datetime="2026-06-15">Jun 15, 2026</time>+ <time datetime="2026-08-08">Aug 8, 2026</time><span class="dot" aria-hidden="true"></span>- <span>12 min</span>+ <span>5 min</span></div>- <h3><a href="/blog/hire-manifest-untrusted-input/">Treating a Hire Manifest as Untrusted Input</a></h3>- <p class="dek">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.</p>+ <h3><a href="/blog/why-our-auto-update-never-ran/">Our Auto-Update Never Ran Once: A CommonJS Export That Vanished Into an ESM Namespace</a></h3>+ <p class="dek">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.</p><div class="foot"><span class="tag kind">Internals</span>- <a class="more" href="/blog/hire-manifest-untrusted-input/" aria-label="Read: Treating a Hire Manifest as Untrusted Input">Read →</a>+ <a class="more" href="/blog/why-our-auto-update-never-ran/" aria-label="Read: Our Auto-Update Never Ran Once: A CommonJS Export That Vanished Into an ESM Namespace">Read →</a></div></div></article><article class="card">- <a class="thumb t-internals" href="/blog/compressing-agent-memory/" aria-hidden="true" tabindex="-1">+ <a class="thumb t-internals" href="/blog/hire-manifest-untrusted-input/" aria-hidden="true" tabindex="-1"><span>INTERNALS</span></a><div class="body"><div class="meta">- <time datetime="2026-06-05">Jun 5, 2026</time>+ <time datetime="2026-06-15">Jun 15, 2026</time><span class="dot" aria-hidden="true"></span>- <span>5 min</span>+ <span>12 min</span></div>- <h3><a href="/blog/compressing-agent-memory/">Compressing Agent Memory Without Losing the Original</a></h3>- <p class="dek">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.</p>+ <h3><a href="/blog/hire-manifest-untrusted-input/">Treating a Hire Manifest as Untrusted Input</a></h3>+ <p class="dek">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.</p><div class="foot"><span class="tag kind">Internals</span>- <a class="more" href="/blog/compressing-agent-memory/" aria-label="Read: Compressing Agent Memory Without Losing the Original">Read →</a>+ <a class="more" href="/blog/hire-manifest-untrusted-input/" aria-label="Read: Treating a Hire Manifest as Untrusted Input">Read →</a></div></div></article>diff --git a/docs/blog/single-committer-git-pattern/index.html b/docs/blog/single-committer-git-pattern/index.htmlindex 7d41693e..f01c0319 100644--- a/docs/blog/single-committer-git-pattern/index.html+++ b/docs/blog/single-committer-git-pattern/index.html@@ -290,56 +290,56 @@ never corrupt their own state; it’s free and open source.</p><h2>Related in Internals</h2><div class="post-grid"><article class="card">- <a class="thumb t-internals" href="/blog/why-our-auto-update-never-ran/" aria-hidden="true" tabindex="-1">+ <a class="thumb t-internals" href="/blog/when-the-cli-stops-listening/" aria-hidden="true" tabindex="-1"><span>INTERNALS</span></a><div class="body"><div class="meta">- <time datetime="2026-08-08">Aug 8, 2026</time>+ <time datetime="2026-08-11">Aug 11, 2026</time><span class="dot" aria-hidden="true"></span>- <span>5 min</span>+ <span>6 min</span></div>- <h3><a href="/blog/why-our-auto-update-never-ran/">Our Auto-Update Never Ran Once: A CommonJS Export That Vanished Into an ESM Namespace</a></h3>- <p class="dek">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.</p>+ <h3><a href="/blog/when-the-cli-stops-listening/">When the CLI Stops Listening: Rate Limits Are Silent Data Loss</a></h3>+ <p class="dek">A rate-limited coding CLI doesn't reject your input — it discards it. No error, no bounce, no record. Munder Difflin was typing into that void for months. Here's how we detect the wall, hold the whole account behind it, and drain the backlog on the other side.</p><div class="foot"><span class="tag kind">Internals</span>- <a class="more" href="/blog/why-our-auto-update-never-ran/" aria-label="Read: Our Auto-Update Never Ran Once: A CommonJS Export That Vanished Into an ESM Namespace">Read →</a>+ <a class="more" href="/blog/when-the-cli-stops-listening/" aria-label="Read: When the CLI Stops Listening: Rate Limits Are Silent Data Loss">Read →</a></div></div></article><article class="card">- <a class="thumb t-internals" href="/blog/hire-manifest-untrusted-input/" aria-hidden="true" tabindex="-1">+ <a class="thumb t-internals" href="/blog/why-our-auto-update-never-ran/" aria-hidden="true" tabindex="-1"><span>INTERNALS</span></a><div class="body"><div class="meta">- <time datetime="2026-06-15">Jun 15, 2026</time>+ <time datetime="2026-08-08">Aug 8, 2026</time><span class="dot" aria-hidden="true"></span>- <span>12 min</span>+ <span>5 min</span></div>- <h3><a href="/blog/hire-manifest-untrusted-input/">Treating a Hire Manifest as Untrusted Input</a></h3>- <p class="dek">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.</p>+ <h3><a href="/blog/why-our-auto-update-never-ran/">Our Auto-Update Never Ran Once: A CommonJS Export That Vanished Into an ESM Namespace</a></h3>+ <p class="dek">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.</p><div class="foot"><span class="tag kind">Internals</span>- <a class="more" href="/blog/hire-manifest-untrusted-input/" aria-label="Read: Treating a Hire Manifest as Untrusted Input">Read →</a>+ <a class="more" href="/blog/why-our-auto-update-never-ran/" aria-label="Read: Our Auto-Update Never Ran Once: A CommonJS Export That Vanished Into an ESM Namespace">Read →</a></div></div></article><article class="card">- <a class="thumb t-internals" href="/blog/compressing-agent-memory/" aria-hidden="true" tabindex="-1">+ <a class="thumb t-internals" href="/blog/hire-manifest-untrusted-input/" aria-hidden="true" tabindex="-1"><span>INTERNALS</span></a><div class="body"><div class="meta">- <time datetime="2026-06-05">Jun 5, 2026</time>+ <time datetime="2026-06-15">Jun 15, 2026</time><span class="dot" aria-hidden="true"></span>- <span>5 min</span>+ <span>12 min</span></div>- <h3><a href="/blog/compressing-agent-memory/">Compressing Agent Memory Without Losing the Original</a></h3>- <p class="dek">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.</p>+ <h3><a href="/blog/hire-manifest-untrusted-input/">Treating a Hire Manifest as Untrusted Input</a></h3>+ <p class="dek">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.</p><div class="foot"><span class="tag kind">Internals</span>- <a class="more" href="/blog/compressing-agent-memory/" aria-label="Read: Compressing Agent Memory Without Losing the Original">Read →</a>+ <a class="more" href="/blog/hire-manifest-untrusted-input/" aria-label="Read: Treating a Hire Manifest as Untrusted Input">Read →</a></div></div></article>diff --git a/docs/blog/tags/agents/index.html b/docs/blog/tags/agents/index.htmlnew file mode 100644index 00000000..ad9ee37a--- /dev/null+++ b/docs/blog/tags/agents/index.html@@ -0,0 +1,122 @@+<!doctype html>+<html lang="en">+<head>+<meta charset="UTF-8" />+<meta name="viewport" content="width=device-width, initial-scale=1.0" />+<title>Agents — Munder Difflin Blog</title>+<meta name="description" content="Munder Difflin blog posts tagged Agents." />+<link rel="canonical" href="https://munderdiffl.in/blog/tags/agents/" />++<link rel="icon" type="image/png" href="https://munderdiffl.in/logo.png" />+<link rel="apple-touch-icon" href="https://munderdiffl.in/logo.png" />+<meta name="theme-color" content="#F5F2E8" />++<!-- Open Graph -->+<meta property="og:site_name" content="Munder Difflin Blog" />+<meta property="og:type" content="website" />+<meta property="og:title" content="Agents — Munder Difflin Blog" />+<meta property="og:description" content="Munder Difflin blog posts tagged Agents." />+<meta property="og:url" content="https://munderdiffl.in/blog/tags/agents/" />+<meta property="og:image" content="https://munderdiffl.in/media/og.png" />+<meta property="og:locale" content="en_US" />+++<!-- Twitter -->+<meta name="twitter:card" content="summary_large_image" />+<meta name="twitter:title" content="Agents — Munder Difflin Blog" />+<meta name="twitter:description" content="Munder Difflin blog posts tagged Agents." />+<meta name="twitter:image" content="https://munderdiffl.in/media/og.png" />++<link rel="alternate" type="application/atom+xml" title="Munder Difflin Blog" href="https://munderdiffl.in/blog/feed.xml" />+<link rel="preconnect" href="https://fonts.googleapis.com" />+<link rel="preconnect" href="https://fonts.gstatic.com" crossorigin />+<link href="https://fonts.googleapis.com/css2?family=Geist:wght@400;500;600&family=JetBrains+Mono:wght@400;500;600;700&display=swap" rel="stylesheet" />+<link rel="stylesheet" href="/blog/assets/blog.css" />++</head>+<body>+<a class="skip-link" href="#main">Skip to content</a>+<nav id="nav">+ <a class="brand" href="https://munderdiffl.in" aria-label="Munder Difflin home">+ <img class="brand-logo" src="https://munderdiffl.in/logo.png" width="1318" height="840" alt="Munder Difflin, Inc. — Multi-Agent Harness" />+ </a>+ <span class="spacer"></span>+ <div class="links">+ <a href="/blog/">Latest</a>+ <a href="/blog/topics/">Topics</a>+ <a href="/blog/about/">About</a>+ <a href="https://munderdiffl.in">↗ Product</a>+ </div>+ <div class="nav-actions">+ <a class="btn sm" href="https://munderdiffl.in/blog/feed.xml" aria-label="RSS feed">⤵ RSS</a>+ <a class="btn sm primary" href="https://munderdiffl.in/#install">⤓ Download</a>+ </div>+</nav>++<main id="main">+<header class="page-head wrap">+ <p class="eyebrow">Tag</p>+ <h1>#Agents</h1>+ <p class="lead">1 post tagged <strong>Agents</strong>.</p>+</header>+<section class="wrap">+ <div class="post-grid">+ <article class="card">+ <a class="thumb t-internals" href="/blog/when-the-cli-stops-listening/" aria-hidden="true" tabindex="-1">+ <span>INTERNALS</span>+ </a>+ <div class="body">+ <div class="meta">+ <time datetime="2026-08-11">Aug 11, 2026</time>+ <span class="dot" aria-hidden="true"></span>+ <span>6 min</span>+ </div>+ <h3><a href="/blog/when-the-cli-stops-listening/">When the CLI Stops Listening: Rate Limits Are Silent Data Loss</a></h3>+ <p class="dek">A rate-limited coding CLI doesn't reject your input — it discards it. No error, no bounce, no record. Munder Difflin was typing into that void for months. Here's how we detect the wall, hold the whole account behind it, and drain the backlog on the other side.</p>+ <div class="foot">+ <span class="tag kind">Internals</span>+ <a class="more" href="/blog/when-the-cli-stops-listening/" aria-label="Read: When the CLI Stops Listening: Rate Limits Are Silent Data Loss">Read →</a>+ </div>+ </div>+</article>++ </div>+</section>+++</main>+<footer>+ <div class="wrap">+ <div class="foot-top">+ <a class="foot-brand brand" href="https://munderdiffl.in" aria-label="Munder Difflin home">+ <img class="brand-logo" src="https://munderdiffl.in/logo.png" width="1318" height="840" alt="Munder Difflin, Inc. — Multi-Agent Harness" />+ </a>+ <div class="foot-links">+ <a href="/blog/">Latest</a>+ <a href="/blog/topics/">Topics</a>+ <a href="/blog/about/">About</a>+ <a href="https://munderdiffl.in/blog/feed.xml">RSS</a>+ <a href="https://github.com/chaitanyagiri/munder-difflin">GitHub</a>+ <a href="https://munderdiffl.in">munderdiffl.in ↗</a>+ </div>+ </div>+ <div class="foot-meta">+ © 2026 Munder Difflin · Local-first · MIT-licensed ·+ Built on <a href="https://munderdiffl.in">Electron, React, Pixi.js, xterm.js & node-pty</a>.+ Run an office of agents while you sleep.+ </div>+ </div>+</footer>++<script>+ // sticky-nav border on scroll+ (function () {+ var nav = document.getElementById('nav');+ if (!nav) return;+ var onScroll = function () { nav.classList.toggle('scrolled', window.scrollY > 8); };+ onScroll(); window.addEventListener('scroll', onScroll, { passive: true });+ })();+</script>++</body>+</html>diff --git a/docs/blog/tags/internals/index.html b/docs/blog/tags/internals/index.htmlindex a1730b9a..93bf4d60 100644--- a/docs/blog/tags/internals/index.html+++ b/docs/blog/tags/internals/index.html@@ -57,11 +57,29 @@<header class="page-head wrap"><p class="eyebrow">Tag</p><h1>#Internals</h1>- <p class="lead">24 posts tagged <strong>Internals</strong>.</p>+ <p class="lead">25 posts tagged <strong>Internals</strong>.</p></header><section class="wrap"><div class="post-grid"><article class="card">+ <a class="thumb t-internals" href="/blog/when-the-cli-stops-listening/" aria-hidden="true" tabindex="-1">+ <span>INTERNALS</span>+ </a>+ <div class="body">+ <div class="meta">+ <time datetime="2026-08-11">Aug 11, 2026</time>+ <span class="dot" aria-hidden="true"></span>+ <span>6 min</span>+ </div>+ <h3><a href="/blog/when-the-cli-stops-listening/">When the CLI Stops Listening: Rate Limits Are Silent Data Loss</a></h3>+ <p class="dek">A rate-limited coding CLI doesn't reject your input — it discards it. No error, no bounce, no record. Munder Difflin was typing into that void for months. Here's how we detect the wall, hold the whole account behind it, and drain the backlog on the other side.</p>+ <div class="foot">+ <span class="tag kind">Internals</span>+ <a class="more" href="/blog/when-the-cli-stops-listening/" aria-label="Read: When the CLI Stops Listening: Rate Limits Are Silent Data Loss">Read →</a>+ </div>+ </div>+</article>+<article class="card"><a class="thumb t-internals" href="/blog/why-our-auto-update-never-ran/" aria-hidden="true" tabindex="-1"><span>INTERNALS</span></a>diff --git a/docs/blog/tags/open-source/index.html b/docs/blog/tags/open-source/index.htmlindex f8de9272..b884c74c 100644--- a/docs/blog/tags/open-source/index.html+++ b/docs/blog/tags/open-source/index.html@@ -57,11 +57,29 @@<header class="page-head wrap"><p class="eyebrow">Tag</p><h1>#Open Source</h1>- <p class="lead">17 posts tagged <strong>Open Source</strong>.</p>+ <p class="lead">18 posts tagged <strong>Open Source</strong>.</p></header><section class="wrap"><div class="post-grid"><article class="card">+ <a class="thumb t-internals" href="/blog/when-the-cli-stops-listening/" aria-hidden="true" tabindex="-1">+ <span>INTERNALS</span>+ </a>+ <div class="body">+ <div class="meta">+ <time datetime="2026-08-11">Aug 11, 2026</time>+ <span class="dot" aria-hidden="true"></span>+ <span>6 min</span>+ </div>+ <h3><a href="/blog/when-the-cli-stops-listening/">When the CLI Stops Listening: Rate Limits Are Silent Data Loss</a></h3>+ <p class="dek">A rate-limited coding CLI doesn't reject your input — it discards it. No error, no bounce, no record. Munder Difflin was typing into that void for months. Here's how we detect the wall, hold the whole account behind it, and drain the backlog on the other side.</p>+ <div class="foot">+ <span class="tag kind">Internals</span>+ <a class="more" href="/blog/when-the-cli-stops-listening/" aria-label="Read: When the CLI Stops Listening: Rate Limits Are Silent Data Loss">Read →</a>+ </div>+ </div>+</article>+<article class="card"><a class="thumb t-story" href="/blog/whats-up-with-munder-difflin/" aria-hidden="true" tabindex="-1"><span>STORY</span></a>diff --git a/docs/blog/tags/release/index.html b/docs/blog/tags/release/index.htmlindex 203bf449..4c4a9a9a 100644--- a/docs/blog/tags/release/index.html+++ b/docs/blog/tags/release/index.html@@ -57,11 +57,29 @@<header class="page-head wrap"><p class="eyebrow">Tag</p><h1>#Release</h1>- <p class="lead">10 posts tagged <strong>Release</strong>.</p>+ <p class="lead">11 posts tagged <strong>Release</strong>.</p></header><section class="wrap"><div class="post-grid"><article class="card">+ <a class="thumb t-internals" href="/blog/when-the-cli-stops-listening/" aria-hidden="true" tabindex="-1">+ <span>INTERNALS</span>+ </a>+ <div class="body">+ <div class="meta">+ <time datetime="2026-08-11">Aug 11, 2026</time>+ <span class="dot" aria-hidden="true"></span>+ <span>6 min</span>+ </div>+ <h3><a href="/blog/when-the-cli-stops-listening/">When the CLI Stops Listening: Rate Limits Are Silent Data Loss</a></h3>+ <p class="dek">A rate-limited coding CLI doesn't reject your input — it discards it. No error, no bounce, no record. Munder Difflin was typing into that void for months. Here's how we detect the wall, hold the whole account behind it, and drain the backlog on the other side.</p>+ <div class="foot">+ <span class="tag kind">Internals</span>+ <a class="more" href="/blog/when-the-cli-stops-listening/" aria-label="Read: When the CLI Stops Listening: Rate Limits Are Silent Data Loss">Read →</a>+ </div>+ </div>+</article>+<article class="card"><a class="thumb t-story" href="/blog/whats-up-with-munder-difflin/" aria-hidden="true" tabindex="-1"><span>STORY</span></a>diff --git a/docs/blog/tags/reliability/index.html b/docs/blog/tags/reliability/index.htmlindex c1cd79e2..da1a374b 100644--- a/docs/blog/tags/reliability/index.html+++ b/docs/blog/tags/reliability/index.html@@ -57,11 +57,29 @@<header class="page-head wrap"><p class="eyebrow">Tag</p><h1>#Reliability</h1>- <p class="lead">4 posts tagged <strong>Reliability</strong>.</p>+ <p class="lead">5 posts tagged <strong>Reliability</strong>.</p></header><section class="wrap"><div class="post-grid"><article class="card">+ <a class="thumb t-internals" href="/blog/when-the-cli-stops-listening/" aria-hidden="true" tabindex="-1">+ <span>INTERNALS</span>+ </a>+ <div class="body">+ <div class="meta">+ <time datetime="2026-08-11">Aug 11, 2026</time>+ <span class="dot" aria-hidden="true"></span>+ <span>6 min</span>+ </div>+ <h3><a href="/blog/when-the-cli-stops-listening/">When the CLI Stops Listening: Rate Limits Are Silent Data Loss</a></h3>+ <p class="dek">A rate-limited coding CLI doesn't reject your input — it discards it. No error, no bounce, no record. Munder Difflin was typing into that void for months. Here's how we detect the wall, hold the whole account behind it, and drain the backlog on the other side.</p>+ <div class="foot">+ <span class="tag kind">Internals</span>+ <a class="more" href="/blog/when-the-cli-stops-listening/" aria-label="Read: When the CLI Stops Listening: Rate Limits Are Silent Data Loss">Read →</a>+ </div>+ </div>+</article>+<article class="card"><a class="thumb t-concepts" href="/blog/loop-engineering-for-ai-agents/" aria-hidden="true" tabindex="-1"><span>CONCEPTS</span></a>diff --git a/docs/blog/the-hook-shim-pattern/index.html b/docs/blog/the-hook-shim-pattern/index.htmlindex 225a6241..1a57676e 100644--- a/docs/blog/the-hook-shim-pattern/index.html+++ b/docs/blog/the-hook-shim-pattern/index.html@@ -279,56 +279,56 @@ at the mercy of the bridge.<h2>Related in Internals</h2><div class="post-grid"><article class="card">- <a class="thumb t-internals" href="/blog/why-our-auto-update-never-ran/" aria-hidden="true" tabindex="-1">+ <a class="thumb t-internals" href="/blog/when-the-cli-stops-listening/" aria-hidden="true" tabindex="-1"><span>INTERNALS</span></a><div class="body"><div class="meta">- <time datetime="2026-08-08">Aug 8, 2026</time>+ <time datetime="2026-08-11">Aug 11, 2026</time><span class="dot" aria-hidden="true"></span>- <span>5 min</span>+ <span>6 min</span></div>- <h3><a href="/blog/why-our-auto-update-never-ran/">Our Auto-Update Never Ran Once: A CommonJS Export That Vanished Into an ESM Namespace</a></h3>- <p class="dek">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.</p>+ <h3><a href="/blog/when-the-cli-stops-listening/">When the CLI Stops Listening: Rate Limits Are Silent Data Loss</a></h3>+ <p class="dek">A rate-limited coding CLI doesn't reject your input — it discards it. No error, no bounce, no record. Munder Difflin was typing into that void for months. Here's how we detect the wall, hold the whole account behind it, and drain the backlog on the other side.</p><div class="foot"><span class="tag kind">Internals</span>- <a class="more" href="/blog/why-our-auto-update-never-ran/" aria-label="Read: Our Auto-Update Never Ran Once: A CommonJS Export That Vanished Into an ESM Namespace">Read →</a>+ <a class="more" href="/blog/when-the-cli-stops-listening/" aria-label="Read: When the CLI Stops Listening: Rate Limits Are Silent Data Loss">Read →</a></div></div></article><article class="card">- <a class="thumb t-internals" href="/blog/hire-manifest-untrusted-input/" aria-hidden="true" tabindex="-1">+ <a class="thumb t-internals" href="/blog/why-our-auto-update-never-ran/" aria-hidden="true" tabindex="-1"><span>INTERNALS</span></a><div class="body"><div class="meta">- <time datetime="2026-06-15">Jun 15, 2026</time>+ <time datetime="2026-08-08">Aug 8, 2026</time><span class="dot" aria-hidden="true"></span>- <span>12 min</span>+ <span>5 min</span></div>- <h3><a href="/blog/hire-manifest-untrusted-input/">Treating a Hire Manifest as Untrusted Input</a></h3>- <p class="dek">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.</p>+ <h3><a href="/blog/why-our-auto-update-never-ran/">Our Auto-Update Never Ran Once: A CommonJS Export That Vanished Into an ESM Namespace</a></h3>+ <p class="dek">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.</p><div class="foot"><span class="tag kind">Internals</span>- <a class="more" href="/blog/hire-manifest-untrusted-input/" aria-label="Read: Treating a Hire Manifest as Untrusted Input">Read →</a>+ <a class="more" href="/blog/why-our-auto-update-never-ran/" aria-label="Read: Our Auto-Update Never Ran Once: A CommonJS Export That Vanished Into an ESM Namespace">Read →</a></div></div></article><article class="card">- <a class="thumb t-internals" href="/blog/compressing-agent-memory/" aria-hidden="true" tabindex="-1">+ <a class="thumb t-internals" href="/blog/hire-manifest-untrusted-input/" aria-hidden="true" tabindex="-1"><span>INTERNALS</span></a><div class="body"><div class="meta">- <time datetime="2026-06-05">Jun 5, 2026</time>+ <time datetime="2026-06-15">Jun 15, 2026</time><span class="dot" aria-hidden="true"></span>- <span>5 min</span>+ <span>12 min</span></div>- <h3><a href="/blog/compressing-agent-memory/">Compressing Agent Memory Without Losing the Original</a></h3>- <p class="dek">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.</p>+ <h3><a href="/blog/hire-manifest-untrusted-input/">Treating a Hire Manifest as Untrusted Input</a></h3>+ <p class="dek">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.</p><div class="foot"><span class="tag kind">Internals</span>- <a class="more" href="/blog/compressing-agent-memory/" aria-label="Read: Compressing Agent Memory Without Losing the Original">Read →</a>+ <a class="more" href="/blog/hire-manifest-untrusted-input/" aria-label="Read: Treating a Hire Manifest as Untrusted Input">Read →</a></div></div></article>diff --git a/docs/blog/topics/comparisons/index.html b/docs/blog/topics/comparisons/index.htmlindex 4f600583..d30ab314 100644--- a/docs/blog/topics/comparisons/index.html+++ b/docs/blog/topics/comparisons/index.html@@ -71,7 +71,7 @@<a class="chip" href="/blog/topics/concepts/">concepts<span class="ct">21</span></a>- <a class="chip" href="/blog/topics/internals/">internals<span class="ct">17</span></a>+ <a class="chip" href="/blog/topics/internals/">internals<span class="ct">18</span></a><a class="chip" href="/blog/topics/comparisons/" aria-current="page">comparisons<span class="ct">17</span></a>diff --git a/docs/blog/topics/concepts/index.html b/docs/blog/topics/concepts/index.htmlindex 912a062b..11a437c3 100644--- a/docs/blog/topics/concepts/index.html+++ b/docs/blog/topics/concepts/index.html@@ -71,7 +71,7 @@<a class="chip" href="/blog/topics/concepts/" aria-current="page">concepts<span class="ct">21</span></a>- <a class="chip" href="/blog/topics/internals/">internals<span class="ct">17</span></a>+ <a class="chip" href="/blog/topics/internals/">internals<span class="ct">18</span></a><a class="chip" href="/blog/topics/comparisons/">comparisons<span class="ct">17</span></a>diff --git a/docs/blog/topics/guides/index.html b/docs/blog/topics/guides/index.htmlindex 77a7b34d..2a400074 100644--- a/docs/blog/topics/guides/index.html+++ b/docs/blog/topics/guides/index.html@@ -71,7 +71,7 @@<a class="chip" href="/blog/topics/concepts/">concepts<span class="ct">21</span></a>- <a class="chip" href="/blog/topics/internals/">internals<span class="ct">17</span></a>+ <a class="chip" href="/blog/topics/internals/">internals<span class="ct">18</span></a><a class="chip" href="/blog/topics/comparisons/">comparisons<span class="ct">17</span></a>diff --git a/docs/blog/topics/index.html b/docs/blog/topics/index.htmlindex cdc6d513..a86c99b7 100644--- a/docs/blog/topics/index.html+++ b/docs/blog/topics/index.html@@ -87,7 +87,7 @@<span class="thumb t-internals" aria-hidden="true">INTERNALS</span><div class="body"><h3 style="color:var(--ink)">internals</h3>- <p class="dek">17 posts.</p>+ <p class="dek">18 posts.</p><div class="foot"><span class="more">View topic →</span></div></div></a>@@ -147,7 +147,7 @@<a class="chip" href="/blog/tags/claude-code/">Claude Code<span class="ct">45</span></a>- <a class="chip" href="/blog/tags/internals/">Internals<span class="ct">24</span></a>+ <a class="chip" href="/blog/tags/internals/">Internals<span class="ct">25</span></a><a class="chip" href="/blog/tags/guides/">Guides<span class="ct">23</span></a>@@ -155,9 +155,9 @@<a class="chip" href="/blog/tags/concepts/">Concepts<span class="ct">18</span></a>- <a class="chip" href="/blog/tags/comparisons/">Comparisons<span class="ct">17</span></a>+ <a class="chip" href="/blog/tags/open-source/">Open Source<span class="ct">18</span></a>- <a class="chip" href="/blog/tags/open-source/">Open Source<span class="ct">17</span></a>+ <a class="chip" href="/blog/tags/comparisons/">Comparisons<span class="ct">17</span></a><a class="chip" href="/blog/tags/local-first/">Local-First<span class="ct">13</span></a>@@ -165,9 +165,9 @@<a class="chip" href="/blog/tags/automation/">Automation<span class="ct">11</span></a>- <a class="chip" href="/blog/tags/tools/">Tools<span class="ct">10</span></a>+ <a class="chip" href="/blog/tags/release/">Release<span class="ct">11</span></a>- <a class="chip" href="/blog/tags/release/">Release<span class="ct">10</span></a>+ <a class="chip" href="/blog/tags/tools/">Tools<span class="ct">10</span></a><a class="chip" href="/blog/tags/getting-started/">Getting Started<span class="ct">9</span></a>@@ -193,14 +193,14 @@<a class="chip" href="/blog/tags/autonomous/">Autonomous<span class="ct">5</span></a>+ <a class="chip" href="/blog/tags/reliability/">Reliability<span class="ct">5</span></a>+<a class="chip" href="/blog/tags/git/">Git<span class="ct">4</span></a><a class="chip" href="/blog/tags/mcp/">MCP<span class="ct">4</span></a><a class="chip" href="/blog/tags/architecture/">Architecture<span class="ct">4</span></a>- <a class="chip" href="/blog/tags/reliability/">Reliability<span class="ct">4</span></a>-<a class="chip" href="/blog/tags/cli-agents/">CLI Agents<span class="ct">4</span></a><a class="chip" href="/blog/tags/voice/">Voice<span class="ct">4</span></a>@@ -373,6 +373,8 @@<a class="chip" href="/blog/tags/onboarding/">Onboarding<span class="ct">1</span></a>+ <a class="chip" href="/blog/tags/agents/">Agents<span class="ct">1</span></a>+</div></section>diff --git a/docs/blog/topics/internals/index.html b/docs/blog/topics/internals/index.htmlindex 2da94172..32b2537e 100644--- a/docs/blog/topics/internals/index.html+++ b/docs/blog/topics/internals/index.html@@ -62,7 +62,7 @@</nav><p class="eyebrow">Topic</p><h1>internals</h1>- <p class="lead">17 posts in this cluster.</p>+ <p class="lead">18 posts in this cluster.</p><div class="filters" role="navigation" aria-label="Topics"><a class="chip" href="/blog/">All</a>@@ -71,7 +71,7 @@<a class="chip" href="/blog/topics/concepts/">concepts<span class="ct">21</span></a>- <a class="chip" href="/blog/topics/internals/" aria-current="page">internals<span class="ct">17</span></a>+ <a class="chip" href="/blog/topics/internals/" aria-current="page">internals<span class="ct">18</span></a><a class="chip" href="/blog/topics/comparisons/">comparisons<span class="ct">17</span></a>@@ -89,6 +89,24 @@<section class="wrap"><div class="post-grid"><article class="card">+ <a class="thumb t-internals" href="/blog/when-the-cli-stops-listening/" aria-hidden="true" tabindex="-1">+ <span>INTERNALS</span>+ </a>+ <div class="body">+ <div class="meta">+ <time datetime="2026-08-11">Aug 11, 2026</time>+ <span class="dot" aria-hidden="true"></span>+ <span>6 min</span>+ </div>+ <h3><a href="/blog/when-the-cli-stops-listening/">When the CLI Stops Listening: Rate Limits Are Silent Data Loss</a></h3>+ <p class="dek">A rate-limited coding CLI doesn't reject your input — it discards it. No error, no bounce, no record. Munder Difflin was typing into that void for months. Here's how we detect the wall, hold the whole account behind it, and drain the backlog on the other side.</p>+ <div class="foot">+ <span class="tag kind">Internals</span>+ <a class="more" href="/blog/when-the-cli-stops-listening/" aria-label="Read: When the CLI Stops Listening: Rate Limits Are Silent Data Loss">Read →</a>+ </div>+ </div>+</article>+<article class="card"><a class="thumb t-internals" href="/blog/why-our-auto-update-never-ran/" aria-hidden="true" tabindex="-1"><span>INTERNALS</span></a>diff --git a/docs/blog/topics/memory/index.html b/docs/blog/topics/memory/index.htmlindex 05e1194a..bd882e65 100644--- a/docs/blog/topics/memory/index.html+++ b/docs/blog/topics/memory/index.html@@ -71,7 +71,7 @@<a class="chip" href="/blog/topics/concepts/">concepts<span class="ct">21</span></a>- <a class="chip" href="/blog/topics/internals/">internals<span class="ct">17</span></a>+ <a class="chip" href="/blog/topics/internals/">internals<span class="ct">18</span></a><a class="chip" href="/blog/topics/comparisons/">comparisons<span class="ct">17</span></a>diff --git a/docs/blog/topics/orchestration/index.html b/docs/blog/topics/orchestration/index.htmlindex 6d5c5d4f..76fed283 100644--- a/docs/blog/topics/orchestration/index.html+++ b/docs/blog/topics/orchestration/index.html@@ -71,7 +71,7 @@<a class="chip" href="/blog/topics/concepts/">concepts<span class="ct">21</span></a>- <a class="chip" href="/blog/topics/internals/">internals<span class="ct">17</span></a>+ <a class="chip" href="/blog/topics/internals/">internals<span class="ct">18</span></a><a class="chip" href="/blog/topics/comparisons/">comparisons<span class="ct">17</span></a>diff --git a/docs/blog/topics/story/index.html b/docs/blog/topics/story/index.htmlindex 6fac3a40..39dd6cc6 100644--- a/docs/blog/topics/story/index.html+++ b/docs/blog/topics/story/index.html@@ -71,7 +71,7 @@<a class="chip" href="/blog/topics/concepts/">concepts<span class="ct">21</span></a>- <a class="chip" href="/blog/topics/internals/">internals<span class="ct">17</span></a>+ <a class="chip" href="/blog/topics/internals/">internals<span class="ct">18</span></a><a class="chip" href="/blog/topics/comparisons/">comparisons<span class="ct">17</span></a>diff --git a/docs/blog/topics/use-cases/index.html b/docs/blog/topics/use-cases/index.htmlindex e4387317..7b4042d6 100644--- a/docs/blog/topics/use-cases/index.html+++ b/docs/blog/topics/use-cases/index.html@@ -71,7 +71,7 @@<a class="chip" href="/blog/topics/concepts/">concepts<span class="ct">21</span></a>- <a class="chip" href="/blog/topics/internals/">internals<span class="ct">17</span></a>+ <a class="chip" href="/blog/topics/internals/">internals<span class="ct">18</span></a><a class="chip" href="/blog/topics/comparisons/">comparisons<span class="ct">17</span></a>diff --git a/docs/blog/visualizing-ai-agents-pixijs/index.html b/docs/blog/visualizing-ai-agents-pixijs/index.htmlindex 22ca15eb..87e6310a 100644--- a/docs/blog/visualizing-ai-agents-pixijs/index.html+++ b/docs/blog/visualizing-ai-agents-pixijs/index.html@@ -280,56 +280,56 @@ to see your agents at work; it’s free and open source.</p><h2>Related in Internals</h2><div class="post-grid"><article class="card">- <a class="thumb t-internals" href="/blog/why-our-auto-update-never-ran/" aria-hidden="true" tabindex="-1">+ <a class="thumb t-internals" href="/blog/when-the-cli-stops-listening/" aria-hidden="true" tabindex="-1"><span>INTERNALS</span></a><div class="body"><div class="meta">- <time datetime="2026-08-08">Aug 8, 2026</time>+ <time datetime="2026-08-11">Aug 11, 2026</time><span class="dot" aria-hidden="true"></span>- <span>5 min</span>+ <span>6 min</span></div>- <h3><a href="/blog/why-our-auto-update-never-ran/">Our Auto-Update Never Ran Once: A CommonJS Export That Vanished Into an ESM Namespace</a></h3>- <p class="dek">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.</p>+ <h3><a href="/blog/when-the-cli-stops-listening/">When the CLI Stops Listening: Rate Limits Are Silent Data Loss</a></h3>+ <p class="dek">A rate-limited coding CLI doesn't reject your input — it discards it. No error, no bounce, no record. Munder Difflin was typing into that void for months. Here's how we detect the wall, hold the whole account behind it, and drain the backlog on the other side.</p><div class="foot"><span class="tag kind">Internals</span>- <a class="more" href="/blog/why-our-auto-update-never-ran/" aria-label="Read: Our Auto-Update Never Ran Once: A CommonJS Export That Vanished Into an ESM Namespace">Read →</a>+ <a class="more" href="/blog/when-the-cli-stops-listening/" aria-label="Read: When the CLI Stops Listening: Rate Limits Are Silent Data Loss">Read →</a></div></div></article><article class="card">- <a class="thumb t-internals" href="/blog/hire-manifest-untrusted-input/" aria-hidden="true" tabindex="-1">+ <a class="thumb t-internals" href="/blog/why-our-auto-update-never-ran/" aria-hidden="true" tabindex="-1"><span>INTERNALS</span></a><div class="body"><div class="meta">- <time datetime="2026-06-15">Jun 15, 2026</time>+ <time datetime="2026-08-08">Aug 8, 2026</time><span class="dot" aria-hidden="true"></span>- <span>12 min</span>+ <span>5 min</span></div>- <h3><a href="/blog/hire-manifest-untrusted-input/">Treating a Hire Manifest as Untrusted Input</a></h3>- <p class="dek">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.</p>+ <h3><a href="/blog/why-our-auto-update-never-ran/">Our Auto-Update Never Ran Once: A CommonJS Export That Vanished Into an ESM Namespace</a></h3>+ <p class="dek">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.</p><div class="foot"><span class="tag kind">Internals</span>- <a class="more" href="/blog/hire-manifest-untrusted-input/" aria-label="Read: Treating a Hire Manifest as Untrusted Input">Read →</a>+ <a class="more" href="/blog/why-our-auto-update-never-ran/" aria-label="Read: Our Auto-Update Never Ran Once: A CommonJS Export That Vanished Into an ESM Namespace">Read →</a></div></div></article><article class="card">- <a class="thumb t-internals" href="/blog/compressing-agent-memory/" aria-hidden="true" tabindex="-1">+ <a class="thumb t-internals" href="/blog/hire-manifest-untrusted-input/" aria-hidden="true" tabindex="-1"><span>INTERNALS</span></a><div class="body"><div class="meta">- <time datetime="2026-06-05">Jun 5, 2026</time>+ <time datetime="2026-06-15">Jun 15, 2026</time><span class="dot" aria-hidden="true"></span>- <span>5 min</span>+ <span>12 min</span></div>- <h3><a href="/blog/compressing-agent-memory/">Compressing Agent Memory Without Losing the Original</a></h3>- <p class="dek">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.</p>+ <h3><a href="/blog/hire-manifest-untrusted-input/">Treating a Hire Manifest as Untrusted Input</a></h3>+ <p class="dek">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.</p><div class="foot"><span class="tag kind">Internals</span>- <a class="more" href="/blog/compressing-agent-memory/" aria-label="Read: Compressing Agent Memory Without Losing the Original">Read →</a>+ <a class="more" href="/blog/hire-manifest-untrusted-input/" aria-label="Read: Treating a Hire Manifest as Untrusted Input">Read →</a></div></div></article>diff --git a/docs/blog/whats-up-with-munder-difflin/index.html b/docs/blog/whats-up-with-munder-difflin/index.htmlindex 72e7bcff..331778d8 100644--- a/docs/blog/whats-up-with-munder-difflin/index.html+++ b/docs/blog/whats-up-with-munder-difflin/index.html@@ -320,7 +320,7 @@ it runs on your machine.</p><footer class="post-foot wrap"><div class="prevnext"><a class="pn prev" href="/blog/why-our-auto-update-never-ran/"><span class="k">← Older</span><span class="t">Our Auto-Update Never Ran Once: A CommonJS Export That Vanished Into an ESM Namespace</span></a>- <span></span>+ <a class="pn next" href="/blog/when-the-cli-stops-listening/"><span class="k">Newer →</span><span class="t">When the CLI Stops Listening: Rate Limits Are Silent Data Loss</span></a></div><section class="related"><h2>Related in Story</h2>diff --git a/docs/blog/when-the-cli-stops-listening/index.html b/docs/blog/when-the-cli-stops-listening/index.htmlnew file mode 100644index 00000000..fa040bd5--- /dev/null+++ b/docs/blog/when-the-cli-stops-listening/index.html@@ -0,0 +1,416 @@+<!doctype html>+<html lang="en">+<head>+<meta charset="UTF-8" />+<meta name="viewport" content="width=device-width, initial-scale=1.0" />+<title>When the CLI Stops Listening: Rate Limits Are Silent Data Loss — Munder Difflin Blog</title>+<meta name="description" content="A rate-limited coding CLI doesn't reject your input — it discards it. No error, no bounce, no record. Munder Difflin was typing into that void for months. Here's how we detect the wall, hold the whole account behind it, and drain the backlog on the other side." />+<link rel="canonical" href="https://munderdiffl.in/blog/when-the-cli-stops-listening/" />++<link rel="icon" type="image/png" href="https://munderdiffl.in/logo.png" />+<link rel="apple-touch-icon" href="https://munderdiffl.in/logo.png" />+<meta name="theme-color" content="#F5F2E8" />++<!-- Open Graph -->+<meta property="og:site_name" content="Munder Difflin Blog" />+<meta property="og:type" content="article" />+<meta property="og:title" content="When the CLI Stops Listening: Rate Limits Are Silent Data Loss — Munder Difflin Blog" />+<meta property="og:description" content="A rate-limited coding CLI doesn't reject your input — it discards it. No error, no bounce, no record. Munder Difflin was typing into that void for months. Here's how we detect the wall, hold the whole account behind it, and drain the backlog on the other side." />+<meta property="og:url" content="https://munderdiffl.in/blog/when-the-cli-stops-listening/" />+<meta property="og:image" content="https://munderdiffl.in/media/og.png" />+<meta property="og:locale" content="en_US" />+<meta property="article:published_time" content="2026-08-11T00:00:00.000Z" />+<meta property="article:author" content="Chaitanya Giri" />+<meta property="article:tag" content="Internals" />+<meta property="article:tag" content="Reliability" />+<meta property="article:tag" content="Agents" />+<meta property="article:tag" content="Release" />+<meta property="article:tag" content="Open Source" />+++<!-- Twitter -->+<meta name="twitter:card" content="summary_large_image" />+<meta name="twitter:title" content="When the CLI Stops Listening: Rate Limits Are Silent Data Loss — Munder Difflin Blog" />+<meta name="twitter:description" content="A rate-limited coding CLI doesn't reject your input — it discards it. No error, no bounce, no record. Munder Difflin was typing into that void for months. Here's how we detect the wall, hold the whole account behind it, and drain the backlog on the other side." />+<meta name="twitter:image" content="https://munderdiffl.in/media/og.png" />++<link rel="alternate" type="application/atom+xml" title="Munder Difflin Blog" href="https://munderdiffl.in/blog/feed.xml" />+<link rel="preconnect" href="https://fonts.googleapis.com" />+<link rel="preconnect" href="https://fonts.gstatic.com" crossorigin />+<link href="https://fonts.googleapis.com/css2?family=Geist:wght@400;500;600&family=JetBrains+Mono:wght@400;500;600;700&display=swap" rel="stylesheet" />+<link rel="stylesheet" href="/blog/assets/blog.css" />++<script type="application/ld+json">+{+ "@context": "https://schema.org",+ "@type": "BlogPosting",+ "headline": "When the CLI Stops Listening: Rate Limits Are Silent Data Loss",+ "description": "A rate-limited coding CLI doesn't reject your input — it discards it. No error, no bounce, no record. Munder Difflin was typing into that void for months. Here's how we detect the wall, hold the whole account behind it, and drain the backlog on the other side.",+ "image": ["https://munderdiffl.in/media/og.png"],+ "datePublished": "2026-08-11T00:00:00.000Z",+ "dateModified": "2026-08-11T00:00:00.000Z",+ "author": { "@type": "Person", "name": "Chaitanya Giri" },+ "publisher": {+ "@type": "Organization",+ "name": "Munder Difflin",+ "logo": { "@type": "ImageObject", "url": "https://munderdiffl.in/logo.png" }+ },+ "mainEntityOfPage": { "@type": "WebPage", "@id": "https://munderdiffl.in/blog/when-the-cli-stops-listening/" },+ "keywords": "claude code rate limit, claude code usage limit reached, claude code session limit resets, cli agent rate limit handling, queue messages during rate limit, codex rate limit resets_at",+ "articleSection": "Internals",+ "inLanguage": "en-US",+ "url": "https://munderdiffl.in/blog/when-the-cli-stops-listening/"+}+</script>+<script type="application/ld+json">+{+ "@context": "https://schema.org",+ "@type": "BreadcrumbList",+ "itemListElement": [+ { "@type": "ListItem", "position": 1, "name": "Home", "item": "https://munderdiffl.in/" },+ { "@type": "ListItem", "position": 2, "name": "Blog", "item": "https://munderdiffl.in/blog/" },+ { "@type": "ListItem", "position": 3, "name": "When the CLI Stops Listening: Rate Limits Are Silent Data Loss", "item": "https://munderdiffl.in/blog/when-the-cli-stops-listening/" }+ ]+}+</script>++<script type="application/ld+json">+{+ "@context": "https://schema.org",+ "@type": "FAQPage",+ "mainEntity": [+ { "@type": "Question", "name": "What happens if you type into a rate-limited Claude Code session?", "acceptedAnswer": { "@type": "Answer", "text": "The TUI accepts the keystrokes and discards them. There is no error, no bounce, and no record that a message existed — the input area simply clears. Anything sent during the limit window is gone, and the only symptom is noticing later that the agent never did the thing you asked. This is why a rate limit is worse than an outage for an automated sender: an outage fails loudly, and this fails silently." } },+ { "@type": "Question", "name": "How do you detect a usage limit from a CLI's terminal output?", "acceptedAnswer": { "@type": "Answer", "text": "You read the terminal stream, not the exit code — these are TUIs, and the limit is a banner rather than a status. Most CLIs relay the provider's own wording, so generic natural-language patterns carry most of the work, with a small per-CLI table for the strings a tool genuinely owns (Claude Code's subscription limits are its own concept, for example). The hard part is negative matching: Claude renders 'Approaching session limit · resets 3pm' from the same component as the real banner at around 80% usage, and matching that would stand your fleet down hours early, every session." } },+ { "@type": "Question", "name": "Should a rate-limit hold apply to one agent or all of them?", "acceptedAnswer": { "@type": "Answer", "text": "The account. A usage limit belongs to a subscription, so every agent running that CLI is already behind the same wall the moment one of them hits it — they just haven't spoken yet. Holding only the agent that printed the banner lets the others walk into it one at a time, losing a message each. Over-holding costs a wait; under-holding costs instructions." } },+ { "@type": "Question", "name": "Why not just retry when a message fails to send?", "acceptedAnswer": { "@type": "Answer", "text": "Because it doesn't fail. The write succeeds — the bytes reach the pseudo-terminal, and the TUI throws them away at the other end. There is no failure to retry against, which is why the fix has to be a gate in front of the send rather than a retry behind it." } }++ ]+}+</script>+++</head>+<body>+<a class="skip-link" href="#main">Skip to content</a>+<nav id="nav">+ <a class="brand" href="https://munderdiffl.in" aria-label="Munder Difflin home">+ <img class="brand-logo" src="https://munderdiffl.in/logo.png" width="1318" height="840" alt="Munder Difflin, Inc. — Multi-Agent Harness" />+ </a>+ <span class="spacer"></span>+ <div class="links">+ <a href="/blog/">Latest</a>+ <a href="/blog/topics/">Topics</a>+ <a href="/blog/about/">About</a>+ <a href="https://munderdiffl.in">↗ Product</a>+ </div>+ <div class="nav-actions">+ <a class="btn sm" href="https://munderdiffl.in/blog/feed.xml" aria-label="RSS feed">⤵ RSS</a>+ <a class="btn sm primary" href="https://munderdiffl.in/#install">⤓ Download</a>+ </div>+</nav>++<main id="main">++<article>+ <header class="post-head wrap">+ <nav class="crumbs" aria-label="Breadcrumb">+ <a href="/blog/">Blog</a>+ <span>/</span>+ <a href="/blog/topics/internals/">Internals</a>+ </nav>+ <h1>When the CLI Stops Listening: Rate Limits Are Silent Data Loss</h1>+ <p class="dek">A rate-limited coding CLI doesn't reject your input — it discards it. No error, no bounce, no record. Munder Difflin was typing into that void for months. Here's how we detect the wall, hold the whole account behind it, and drain the backlog on the other side.</p>+ <div class="byline">+ <span class="av" aria-hidden="true">CG</span>+ <strong>Chaitanya Giri</strong>+ <span class="dot" aria-hidden="true">·</span>+ <time datetime="2026-08-11">Aug 11, 2026</time>+ <span class="dot" aria-hidden="true">·</span>+ <span>6 min read</span>+ <span class="tag kind">Internals</span>+ </div>+ </header>++ <div class="post-wrap wrap">+ <div class="prose">+ <p>There is a failure mode that is worse than an error, and most automated systems are built as+though it doesn’t exist: the write that succeeds and does nothing.</p>+<p>Munder Difflin drives coding CLIs — Claude Code, Codex, Grok, and half a dozen others — through+real pseudo-terminals. It types into them the way a person would. And for months, whenever one of+those CLIs hit its usage limit, the harness kept typing.</p>+<p>The keystrokes landed. The pty accepted them. The TUI discarded them.</p>+<p>No error. No bounce. No record that a message ever existed. The input area just cleared, and an+instruction that someone had queued an hour earlier ceased to exist. The only symptom was noticing,+much later, that an agent never did the thing it was asked.</p>+<h2 id="why-this-is-not-a-retry-problem" tabindex="-1">Why this is not a retry problem <a class="anchor" href="#why-this-is-not-a-retry-problem" aria-hidden="true">#</a></h2>+<p>The instinct is to add a retry. It doesn’t apply here, and the reason is worth sitting with.</p>+<p>A retry needs a failure to hang off. Ours succeeded at every layer we could observe:</p>+<pre><code>write(ptyFd, "…") → ok, bytes written+pty → ok, delivered to the child+TUI → reads the input, sees it is rate limited, drops it+</code></pre>+<p>There is nothing to catch. By the time the message is lost, every call in the stack has already+returned success. That pushes the fix upstream of the send: you cannot recover from this+afterwards, so you have to not do it in the first place.</p>+<h2 id="reading-the-wall" tabindex="-1">Reading the wall <a class="anchor" href="#reading-the-wall" aria-hidden="true">#</a></h2>+<p>Because these are TUIs, the limit is a banner rather than a status code. So you read the terminal+stream.</p>+<p>The obvious design is a table of per-CLI strings — the shape we already use for slash commands,+where <code>/compact</code> differs per tool. Reading the shipped artefacts of the installed fleet, that turns+out to be the wrong shape, because <strong>the limit text is mostly written by the API, not the CLI</strong>.+Five of the CLIs we drive contain no user-facing limit copy at all; they surface whatever the+provider returned. What reaches the terminal is the provider’s phrasing, not the tool’s.</p>+<p>So generic patterns carry the weight, and a small table covers the strings a CLI genuinely owns —+Claude Code’s subscription limits, for instance, are its own concept, with a fixed label set+(<code>session limit</code>, <code>weekly limit</code>, <code>Opus limit</code>, <code>Sonnet limit</code>).</p>+<p>One nice piece of corroboration: pi.dev ships its own two classifier regexes, and the line it draws+is the same line we drew independently — terminal quota conditions on one side, retryable transport+errors on the other.</p>+<h3 id="the-pattern-that-would-have-broken-everything" tabindex="-1">The pattern that would have broken everything <a class="anchor" href="#the-pattern-that-would-have-broken-everything" aria-hidden="true">#</a></h3>+<p>Claude Code renders this at around 80% usage:</p>+<pre><code>Approaching session limit · resets 3pm+</code></pre>+<p>From the same component as the real banner. Matching the reset clause alone would have stood the+entire fleet down hours early, every single session — turning a feature that exists to prevent lost+work into the largest source of lost time in the app.</p>+<p>It is the first thing the negative filter rejects, and it has a test. The general lesson: when you+add detection to a system, the false positive is not an edge case to handle later. It is the thing+most likely to make the feature a net negative, and it deserves the first test you write.</p>+<p>There is a second class of false positive specific to a harness like this: agents read source code+and echo it to their terminals. A file containing <code>const RATE_LIMIT = 120;</code> scrolls past and looks,+to a naive matcher, exactly like a rate limit. Code-shaped contexts are filtered, and lines over+400 characters — a minified bundle going by — are ignored outright.</p>+<h2 id="two-tiers-because-they-want-opposite-responses" tabindex="-1">Two tiers, because they want opposite responses <a class="anchor" href="#two-tiers-because-they-want-opposite-responses" aria-hidden="true">#</a></h2>+<p>Conflating these would be the worst bug the feature could ship:</p>+<table>+<thead>+<tr>+<th></th>+<th>what it is</th>+<th>response</th>+</tr>+</thead>+<tbody>+<tr>+<td><strong>throttle</strong></td>+<td>burst 429, “overloaded”, “temporarily limiting requests”</td>+<td>seconds to minutes — <strong>off by default</strong>, the CLIs already retry these</td>+</tr>+<tr>+<td><strong>quota</strong></td>+<td>the plan’s allowance is spent</td>+<td>hold until the stated reset</td>+</tr>+</tbody>+</table>+<p>Parking a whole floor for hours because of a transient 503 that cleared in four seconds is not a+safety feature. It is an outage you caused yourself.</p>+<h2 id="the-hold-belongs-to-the-account" tabindex="-1">The hold belongs to the account <a class="anchor" href="#the-hold-belongs-to-the-account" aria-hidden="true">#</a></h2>+<p>A usage limit is a property of a subscription, not a process. Six workers running <code>claude</code> share+one account, so the moment one of them hits the wall the other five are already behind it — they+simply haven’t spoken yet.</p>+<p>Holding only the agent that printed the banner would let the next five walk into the same wall one+at a time, losing a message each on the way in. So the hold is scoped to the provider.</p>+<p>That over-holds if you deliberately run two accounts across different agents, and that trade is+made on purpose: <strong>over-holding costs a wait, under-holding costs instructions.</strong> Resume is one+click, and every hold shows the line of terminal output that caused it, so a wrong hold is visible+rather than mysterious.</p>+<h2 id="telling-a-repaint-from-a-real-re-hit" tabindex="-1">Telling a repaint from a real re-hit <a class="anchor" href="#telling-a-repaint-from-a-real-re-hit" aria-hidden="true">#</a></h2>+<p>TUIs redraw constantly, and the banner stays in the scrollback after the limit lifts. A naive+detector re-arms on its own echo forever.</p>+<p>Two mechanisms, and the second is the interesting one:</p>+<ul>+<li>the detector suppresses an identical evidence line within a short window;</li>+<li>the gate refuses to re-arm from identical wording shortly after a release <strong>unless a message has+actually been delivered since</strong>.</li>+</ul>+<p>That second condition is what separates an echo from a genuine second rejection. If we sent+something and the wall is still there, that is new information. If we sent nothing, we are looking+at pixels we already reacted to. There is a test that feeds thirty frames of the same banner at+roughly 10fps and asserts exactly one hold.</p>+<h2 id="what-is-gated-and-what-deliberately-is-not" tabindex="-1">What is gated, and what deliberately is not <a class="anchor" href="#what-is-gated-and-what-deliberately-is-not" aria-hidden="true">#</a></h2>+<p><strong>Gated:</strong> the queue drain, the spawn seed — an agent seeded into a capped provider has its entire+setup prompt discarded and then sits there looking like a hung spawn — and scheduled auto-compact,+because <code>/compact</code> is a model call that spends a rejected attempt <em>and</em> parks a <code>/compact</code> ahead of+your real backlog when the window reopens.</p>+<p><strong>Not gated:</strong> writing a message into another agent’s inbox file. That is already a queue — the+message waits on disk until the agent next runs — so gating it would convert “delayed” into “lost”,+which is the exact bug we are fixing.</p>+<p><strong>Bypassed:</strong> “send now” overrides a hold, exactly as it already overrides the floor-wide delivery+pause. One override, one meaning. The operator may know something the detector doesn’t, and an+override with no escape hatch is worse than a wrong guess.</p>+<h2 id="two-bugs-found-while-building-it" tabindex="-1">Two bugs found while building it <a class="anchor" href="#two-bugs-found-while-building-it" aria-hidden="true">#</a></h2>+<p>Both are the same species — a setting that describes the world rather than controlling it.</p>+<p><strong><code>autoResume: off</code> did nothing.</strong> Expiry was a timestamp comparison, so holds lapsed on their own+and the setting was decorative. A hold now ends when it is <em>swept</em>, and the sweep is what+auto-resume controls.</p>+<p><strong>Disabling the guard left the floor stopped.</strong> The drain reads the hold list, not the setting, so+existing holds outlived the switch that was supposed to govern them. Turning it off now releases+everything.</p>+<p>If you take one thing from this post, take that pattern: a boolean that reads well in the UI and is+never consulted on the path it claims to govern is indistinguishable from a working feature right up+until someone needs it.</p>+<h2 id="what-honest-verification-looks-like" tabindex="-1">What honest verification looks like <a class="anchor" href="#what-honest-verification-looks-like" aria-hidden="true">#</a></h2>+<p>The detection tests are built from strings read out of the installed binaries — <code>strings</code> and+<code>rg</code> over the shipped artefacts — not from a terminal that actually hit a wall. That is a real+limitation and it is worth stating plainly rather than burying: the highest-value check before+trusting this is forcing one live limit and watching a queue drain on the other side of it.</p>+<p>Shipping detection heuristics with a switch to turn them off, evidence attached to every decision,+and a one-click override is not a lack of confidence. It is what you owe people when your feature’s+failure mode is “the fleet stopped and I don’t know why”.</p>+<hr>+<p><em>Munder Difflin v0.3.8 is out — usage-limit aware delivery, a Triggers hub, and a git history view+that finally fits its panel. <a href="https://github.com/chaitanyagiri/munder-difflin/releases/latest">Download it</a>,+or read the <a href="https://github.com/chaitanyagiri/munder-difflin/blob/main/CHANGELOG.md">changelog</a>.</em></p>++++ <section class="faq" aria-label="Frequently asked questions">+ <h2 id="faq">FAQ</h2>++ <div class="qa">+ <p class="q">What happens if you type into a rate-limited Claude Code session?</p>+ <p class="a">The TUI accepts the keystrokes and discards them. There is no error, no bounce, and no record that a message existed — the input area simply clears. Anything sent during the limit window is gone, and the only symptom is noticing later that the agent never did the thing you asked. This is why a rate limit is worse than an outage for an automated sender: an outage fails loudly, and this fails silently.</p>+ </div>++ <div class="qa">+ <p class="q">How do you detect a usage limit from a CLI's terminal output?</p>+ <p class="a">You read the terminal stream, not the exit code — these are TUIs, and the limit is a banner rather than a status. Most CLIs relay the provider's own wording, so generic natural-language patterns carry most of the work, with a small per-CLI table for the strings a tool genuinely owns (Claude Code's subscription limits are its own concept, for example). The hard part is negative matching: Claude renders 'Approaching session limit · resets 3pm' from the same component as the real banner at around 80% usage, and matching that would stand your fleet down hours early, every session.</p>+ </div>++ <div class="qa">+ <p class="q">Should a rate-limit hold apply to one agent or all of them?</p>+ <p class="a">The account. A usage limit belongs to a subscription, so every agent running that CLI is already behind the same wall the moment one of them hits it — they just haven't spoken yet. Holding only the agent that printed the banner lets the others walk into it one at a time, losing a message each. Over-holding costs a wait; under-holding costs instructions.</p>+ </div>++ <div class="qa">+ <p class="q">Why not just retry when a message fails to send?</p>+ <p class="a">Because it doesn't fail. The write succeeds — the bytes reach the pseudo-terminal, and the TUI throws them away at the other end. There is no failure to retry against, which is why the fix has to be a gate in front of the send rather than a retry behind it.</p>+ </div>++ </section>++++ <hr />+ <div class="share">+ <span class="lbl">Tags</span>+ <a class="tag" href="/blog/tags/internals/">Internals</a><a class="tag" href="/blog/tags/reliability/">Reliability</a><a class="tag" href="/blog/tags/agents/">Agents</a><a class="tag" href="/blog/tags/release/">Release</a><a class="tag" href="/blog/tags/open-source/">Open Source</a>+ </div>++ </div>+++ <aside class="toc-rail" aria-label="Table of contents">+ <div class="tt">On this page</div>+ <ol>+ <li class="lvl-2"><a href="#why-this-is-not-a-retry-problem">Why this is not a retry problem</a></li><li class="lvl-2"><a href="#reading-the-wall">Reading the wall</a></li><li class="lvl-3"><a href="#the-pattern-that-would-have-broken-everything">The pattern that would have broken everything</a></li><li class="lvl-2"><a href="#two-tiers-because-they-want-opposite-responses">Two tiers, because they want opposite responses</a></li><li class="lvl-2"><a href="#the-hold-belongs-to-the-account">The hold belongs to the account</a></li><li class="lvl-2"><a href="#telling-a-repaint-from-a-real-re-hit">Telling a repaint from a real re-hit</a></li><li class="lvl-2"><a href="#what-is-gated-and-what-deliberately-is-not">What is gated, and what deliberately is not</a></li><li class="lvl-2"><a href="#two-bugs-found-while-building-it">Two bugs found while building it</a></li><li class="lvl-2"><a href="#what-honest-verification-looks-like">What honest verification looks like</a></li>+ </ol>+ </aside>++ </div>++ <footer class="post-foot wrap"><div class="prevnext">+ <a class="pn prev" href="/blog/whats-up-with-munder-difflin/"><span class="k">← Older</span><span class="t">What's Up With Munder Difflin: Six Weeks, Four Releases, and the Part of the Stack You Actually Own</span></a>+ <span></span>+ </div>+ <section class="related">+ <h2>Related in Internals</h2>+ <div class="post-grid">+ <article class="card">+ <a class="thumb t-internals" href="/blog/why-our-auto-update-never-ran/" aria-hidden="true" tabindex="-1">+ <span>INTERNALS</span>+ </a>+ <div class="body">+ <div class="meta">+ <time datetime="2026-08-08">Aug 8, 2026</time>+ <span class="dot" aria-hidden="true"></span>+ <span>5 min</span>+ </div>+ <h3><a href="/blog/why-our-auto-update-never-ran/">Our Auto-Update Never Ran Once: A CommonJS Export That Vanished Into an ESM Namespace</a></h3>+ <p class="dek">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.</p>+ <div class="foot">+ <span class="tag kind">Internals</span>+ <a class="more" href="/blog/why-our-auto-update-never-ran/" aria-label="Read: Our Auto-Update Never Ran Once: A CommonJS Export That Vanished Into an ESM Namespace">Read →</a>+ </div>+ </div>+</article>+<article class="card">+ <a class="thumb t-internals" href="/blog/hire-manifest-untrusted-input/" aria-hidden="true" tabindex="-1">+ <span>INTERNALS</span>+ </a>+ <div class="body">+ <div class="meta">+ <time datetime="2026-06-15">Jun 15, 2026</time>+ <span class="dot" aria-hidden="true"></span>+ <span>12 min</span>+ </div>+ <h3><a href="/blog/hire-manifest-untrusted-input/">Treating a Hire Manifest as Untrusted Input</a></h3>+ <p class="dek">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.</p>+ <div class="foot">+ <span class="tag kind">Internals</span>+ <a class="more" href="/blog/hire-manifest-untrusted-input/" aria-label="Read: Treating a Hire Manifest as Untrusted Input">Read →</a>+ </div>+ </div>+</article>+<article class="card">+ <a class="thumb t-internals" href="/blog/compressing-agent-memory/" aria-hidden="true" tabindex="-1">+ <span>INTERNALS</span>+ </a>+ <div class="body">+ <div class="meta">+ <time datetime="2026-06-05">Jun 5, 2026</time>+ <span class="dot" aria-hidden="true"></span>+ <span>5 min</span>+ </div>+ <h3><a href="/blog/compressing-agent-memory/">Compressing Agent Memory Without Losing the Original</a></h3>+ <p class="dek">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.</p>+ <div class="foot">+ <span class="tag kind">Internals</span>+ <a class="more" href="/blog/compressing-agent-memory/" aria-label="Read: Compressing Agent Memory Without Losing the Original">Read →</a>+ </div>+ </div>+</article>++ </div>+ </section>++ </footer>+</article>++</main>+<footer>+ <div class="wrap">+ <div class="foot-top">+ <a class="foot-brand brand" href="https://munderdiffl.in" aria-label="Munder Difflin home">+ <img class="brand-logo" src="https://munderdiffl.in/logo.png" width="1318" height="840" alt="Munder Difflin, Inc. — Multi-Agent Harness" />+ </a>+ <div class="foot-links">+ <a href="/blog/">Latest</a>+ <a href="/blog/topics/">Topics</a>+ <a href="/blog/about/">About</a>+ <a href="https://munderdiffl.in/blog/feed.xml">RSS</a>+ <a href="https://github.com/chaitanyagiri/munder-difflin">GitHub</a>+ <a href="https://munderdiffl.in">munderdiffl.in ↗</a>+ </div>+ </div>+ <div class="foot-meta">+ © 2026 Munder Difflin · Local-first · MIT-licensed ·+ Built on <a href="https://munderdiffl.in">Electron, React, Pixi.js, xterm.js & node-pty</a>.+ Run an office of agents while you sleep.+ </div>+ </div>+</footer>++<script>+ // sticky-nav border on scroll+ (function () {+ var nav = document.getElementById('nav');+ if (!nav) return;+ var onScroll = function () { nav.classList.toggle('scrolled', window.scrollY > 8); };+ onScroll(); window.addEventListener('scroll', onScroll, { passive: true });+ })();+</script>++</body>+</html>diff --git a/docs/blog/why-our-auto-update-never-ran/index.html b/docs/blog/why-our-auto-update-never-ran/index.htmlindex a9c9338f..b2d9e6b9 100644--- a/docs/blog/why-our-auto-update-never-ran/index.html+++ b/docs/blog/why-our-auto-update-never-ran/index.html@@ -290,56 +290,56 @@ why.</p><h2>Related in Internals</h2><div class="post-grid"><article class="card">- <a class="thumb t-internals" href="/blog/hire-manifest-untrusted-input/" aria-hidden="true" tabindex="-1">+ <a class="thumb t-internals" href="/blog/when-the-cli-stops-listening/" aria-hidden="true" tabindex="-1"><span>INTERNALS</span></a><div class="body"><div class="meta">- <time datetime="2026-06-15">Jun 15, 2026</time>+ <time datetime="2026-08-11">Aug 11, 2026</time><span class="dot" aria-hidden="true"></span>- <span>12 min</span>+ <span>6 min</span></div>- <h3><a href="/blog/hire-manifest-untrusted-input/">Treating a Hire Manifest as Untrusted Input</a></h3>- <p class="dek">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.</p>+ <h3><a href="/blog/when-the-cli-stops-listening/">When the CLI Stops Listening: Rate Limits Are Silent Data Loss</a></h3>+ <p class="dek">A rate-limited coding CLI doesn't reject your input — it discards it. No error, no bounce, no record. Munder Difflin was typing into that void for months. Here's how we detect the wall, hold the whole account behind it, and drain the backlog on the other side.</p><div class="foot"><span class="tag kind">Internals</span>- <a class="more" href="/blog/hire-manifest-untrusted-input/" aria-label="Read: Treating a Hire Manifest as Untrusted Input">Read →</a>+ <a class="more" href="/blog/when-the-cli-stops-listening/" aria-label="Read: When the CLI Stops Listening: Rate Limits Are Silent Data Loss">Read →</a></div></div></article><article class="card">- <a class="thumb t-internals" href="/blog/compressing-agent-memory/" aria-hidden="true" tabindex="-1">+ <a class="thumb t-internals" href="/blog/hire-manifest-untrusted-input/" aria-hidden="true" tabindex="-1"><span>INTERNALS</span></a><div class="body"><div class="meta">- <time datetime="2026-06-05">Jun 5, 2026</time>+ <time datetime="2026-06-15">Jun 15, 2026</time><span class="dot" aria-hidden="true"></span>- <span>5 min</span>+ <span>12 min</span></div>- <h3><a href="/blog/compressing-agent-memory/">Compressing Agent Memory Without Losing the Original</a></h3>- <p class="dek">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.</p>+ <h3><a href="/blog/hire-manifest-untrusted-input/">Treating a Hire Manifest as Untrusted Input</a></h3>+ <p class="dek">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.</p><div class="foot"><span class="tag kind">Internals</span>- <a class="more" href="/blog/compressing-agent-memory/" aria-label="Read: Compressing Agent Memory Without Losing the Original">Read →</a>+ <a class="more" href="/blog/hire-manifest-untrusted-input/" aria-label="Read: Treating a Hire Manifest as Untrusted Input">Read →</a></div></div></article><article class="card">- <a class="thumb t-internals" href="/blog/architecture-two-planes-one-renderer/" aria-hidden="true" tabindex="-1">+ <a class="thumb t-internals" href="/blog/compressing-agent-memory/" aria-hidden="true" tabindex="-1"><span>INTERNALS</span></a><div class="body"><div class="meta">- <time datetime="2026-06-04">Jun 4, 2026</time>+ <time datetime="2026-06-05">Jun 5, 2026</time><span class="dot" aria-hidden="true"></span><span>5 min</span></div>- <h3><a href="/blog/architecture-two-planes-one-renderer/">Munder Difflin's Architecture: Two Data Planes, One Renderer</a></h3>- <p class="dek">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.</p>+ <h3><a href="/blog/compressing-agent-memory/">Compressing Agent Memory Without Losing the Original</a></h3>+ <p class="dek">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.</p><div class="foot"><span class="tag kind">Internals</span>- <a class="more" href="/blog/architecture-two-planes-one-renderer/" aria-label="Read: Munder Difflin's Architecture: Two Data Planes, One Renderer">Read →</a>+ <a class="more" href="/blog/compressing-agent-memory/" aria-label="Read: Compressing Agent Memory Without Losing the Original">Read →</a></div></div></article>diff --git a/docs/blog/your-first-hour-with-munder-difflin/index.html b/docs/blog/your-first-hour-with-munder-difflin/index.htmlindex f5730125..f4c903cd 100644--- a/docs/blog/your-first-hour-with-munder-difflin/index.html+++ b/docs/blog/your-first-hour-with-munder-difflin/index.html@@ -84,7 +84,7 @@{ "@type": "Question", "name": "Who is Michael and how do I give him work?", "acceptedAnswer": { "@type": "Answer", "text": "Michael is the GOD orchestrator — the one agent you talk to. You type a brief into his terminal (or use the Talk voice channel with your own OpenAI Realtime key) and he adjudicates it: creating tasks, assigning them to workers, routing messages between inboxes, and escalating only critical items back to you. He seats himself in Michael's office automatically on first launch." } },{ "@type": "Question", "name": "Do I have to approve everything the agents do?", "acceptedAnswer": { "@type": "Answer", "text": "No. The GOD orchestrator resolves routine requests itself so the system stays autonomous. Only critical items — spend, destructive operations, scope changes — land in the human-in-the-loop approvals queue for you to act on. A circuit breaker and per-agent token budgets guard the rest." } },{ "@type": "Question", "name": "How do I review what an agent actually changed?", "acceptedAnswer": { "@type": "Answer", "text": "Open the built-in Monaco IDE from the title-bar IDE button. Its git CHANGES rail lists every modified file, and clicking one opens a read-only side-by-side diff against HEAD — the VS Code editor engine, fully self-hosted, with all filesystem and git access brokered through the main process. There's also a per-agent git tab with status, log, and commit graph." } },- { "@type": "Question", "name": "Can Munder Difflin keep working after I walk away?", "acceptedAnswer": { "@type": "Answer", "text": "Yes — that's the point. The Schedules tab in the Command Center holds recurring missions with a label, interval, target agent, and body, plus a heartbeat that re-engages the floor when it goes quiet. It's local-first, so the office runs 24/7 on hardware you already own." } }+ { "@type": "Question", "name": "Can Munder Difflin keep working after I walk away?", "acceptedAnswer": { "@type": "Answer", "text": "Yes — that's the point. The Triggers tab in the Command Center holds recurring missions with a label, interval, target agent, and body, plus a heartbeat that re-engages the floor when it goes quiet. It's local-first, so the office runs 24/7 on hardware you already own." } }]}@@ -163,7 +163,7 @@<p>Sometime in the first hour, something lands in the approvals queue — a spend threshold, a destructive operation, a scope change. This is by design: Michael resolves routine requests himself and escalates only critical items, so the queue stays short and every item in it deserves your attention. (The philosophy behind that gate: <a href="/blog/human-in-the-loop-approving-ai-agents/">approving AI agents without babysitting them</a>.)</p><p>Before you click approve, look at the work. Hit the title-bar <strong>IDE</strong> button and the built-in Monaco editor — the VS Code editor engine, fully self-hosted — opens over the floor. The git CHANGES rail lists what changed; click a file for a read-only side-by-side diff against HEAD. Read the diff, approve the item, watch the envelope fly.</p><h2 id="minute-60-leave-it-running" tabindex="-1">Minute 60 — Leave it running <a class="anchor" href="#minute-60-leave-it-running" aria-hidden="true">#</a></h2>-<p>The last move of the hour is the one that changes your relationship with the tool: schedule something. The Command Center’s <strong>Schedules</strong> tab takes a label, an interval, a target agent, and a mission body — “every morning, triage new GitHub issues,” say — and a heartbeat re-engages the floor if it goes quiet. Last-fired and next-fired times are right there in the tab.</p>+<p>The last move of the hour is the one that changes your relationship with the tool: schedule something. The Command Center’s <strong>Triggers</strong> tab takes a label, an interval, a target agent, and a mission body — “every morning, triage new GitHub issues,” say — and a heartbeat re-engages the floor if it goes quiet. Last-fired and next-fired times are right there in the tab.</p><p>Close the laptop. It’s local-first, so tomorrow the office is exactly where you left it — probably with mail in your queue. For patterns on what’s worth automating, see <a href="/blog/scheduling-autonomous-agent-missions/">scheduling autonomous agent missions</a>.</p><h2 id="the-hour-in-one-line" tabindex="-1">The hour, in one line <a class="anchor" href="#the-hour-in-one-line" aria-hidden="true">#</a></h2><p>Install, answer four wizard questions, brief one agent, watch the floor, read one diff, set one schedule — and you’ve gone from “a CLI in a terminal” to “an office that works while you don’t.”</p>@@ -201,7 +201,7 @@<div class="qa"><p class="q">Can Munder Difflin keep working after I walk away?</p>- <p class="a">Yes — that's the point. The Schedules tab in the Command Center holds recurring missions with a label, interval, target agent, and body, plus a heartbeat that re-engages the floor when it goes quiet. It's local-first, so the office runs 24/7 on hardware you already own.</p>+ <p class="a">Yes — that's the point. The Triggers tab in the Command Center holds recurring missions with a label, interval, target agent, and body, plus a heartbeat that re-engages the floor when it goes quiet. It's local-first, so the office runs 24/7 on hardware you already own.</p></div></section>diff --git a/docs/index.html b/docs/index.htmlindex b5856c5b..8001438e 100644--- a/docs/index.html+++ b/docs/index.html@@ -29,11 +29,11 @@"@context": "https://schema.org","@type": "SoftwareApplication","name": "Munder Difflin",- "description": "Run a virtual office of AI agents on any computer. Munder Difflin is a highly capable local multi-agent harness that makes a multi-CLI agent cluster work 24/7 for you — Claude Code, Codex, Antigravity, Grok, and GitHub Copilot CLI with Slack and webhook integration. New in v0.3.5: voice orchestration with live floor context, markdown previews, git history & branch compare in the built-in IDE, and auto-update.",+ "description": "Run a virtual office of AI agents on any computer. Munder Difflin is a highly capable local multi-agent harness that makes a multi-CLI agent cluster work 24/7 for you — Claude Code, Codex, Antigravity, Grok, and GitHub Copilot CLI with Slack and webhook integration. New in v0.3.8: usage-limit aware delivery that pauses and resumes agents by itself, a Triggers hub for schedules and webhooks, and a rebuilt git history view.","url": "https://munderdiffl.in/","applicationCategory": "DeveloperApplication","operatingSystem": "macOS, Windows, Linux",- "softwareVersion": "0.3.5",+ "softwareVersion": "0.3.8","downloadUrl": "https://github.com/chaitanyagiri/munder-difflin/releases/latest","softwareHelp": "https://github.com/chaitanyagiri/munder-difflin#readme","license": "https://github.com/chaitanyagiri/munder-difflin/blob/main/LICENSE",@@ -613,16 +613,16 @@<div class="wrap"><div class="chip-wrap reveal" id="verWrap"><button class="chip" id="verChip" type="button" aria-haspopup="true" aria-expanded="false" aria-controls="verPop">- <span class="new">NEW</span> <b>v0.3.7</b> · Local agent harness+ <span class="new">NEW</span> <b>v0.3.8</b> · Local agent harness</button>- <div class="ver-pop" id="verPop" role="dialog" aria-label="What's new in v0.3.7">- <h4>What's new in v0.3.7</h4>+ <div class="ver-pop" id="verPop" role="dialog" aria-label="What's new in v0.3.8">+ <h4>What's new in v0.3.8</h4><ul>- <li><b>Auto-update actually works.</b> A CommonJS/ESM import bug meant it silently never ran in any packaged build. Fixed, with a regression test.</li>- <li><b>The version is now a button.</b> Top-left, next to the logo: it shows download progress and turns into "restart to update" when a release is staged.</li>- <li><b>Nothing fails silently.</b> Update errors now reach the UI and a log file instead of being swallowed.</li>+ <li><b>Usage limits pause the floor instead of losing work.</b> A rate-limited CLI discards keystrokes silently. Agents on a capped provider are now held, queues keep filling, and delivery resumes by itself at the reset.</li>+ <li><b>Triggers, in one place.</b> Schedules, webhooks, context rules and peer messaging share a home — with a history of what fired.</li>+ <li><b>Memory condensation works.</b> It had never once succeeded: transcripts were read from a directory Claude Code stopped writing to months ago.</li></ul>- <a class="more" href="/blog/whats-up-with-munder-difflin/">What's up with Munder Difflin →</a>+ <a class="more" href="/blog/when-the-cli-stops-listening/">When the CLI stops listening →</a></div></div><h1 class="hero-title reveal">Forever running cli agent cluster to do all your work</h1>@@ -1099,7 +1099,7 @@<!-- ===================== FINAL CTA ===================== --><div class="final-wrap"><section class="final" style="padding-top: 84px;">- <div class="eyebrow reveal">v0.3.7 · Free & open source</div>+ <div class="eyebrow reveal">v0.3.8 · Free & open source</div><h2 class="reveal">Your virtual office is <span class="hl">one download away.</span></h2><p class="reveal">A full floor of AI agents — planning, building, and shipping around the clock, on your machine.Free, local, and MIT-licensed.</p>diff --git a/docs/llms-full.txt b/docs/llms-full.txtindex aa854759..76ac07e0 100644--- a/docs/llms-full.txt+++ b/docs/llms-full.txt@@ -2,7 +2,7 @@> Munder Difflin is a free, MIT-licensed, local-first multi-agent harness for CLI coding> agents, presented as a virtual office (an affectionate parody of The Office; not-> affiliated with NBC). Current version: 0.3.7 (August 2026). Desktop app (Electron) for+> affiliated with NBC). Current version: 0.3.8 (August 2026). Desktop app (Electron) for> macOS, Windows, and Linux. Website: https://munderdiffl.in — Source:> https://github.com/chaitanyagiri/munder-difflin — Author: Chaitanya Giri.diff --git a/docs/llms.txt b/docs/llms.txtindex ef3dc351..73243d47 100644--- a/docs/llms.txt+++ b/docs/llms.txt@@ -6,7 +6,7 @@> your own computer — each agent a real CLI process in a real terminal, with shared> long-term memory, inter-agent messaging, a GOD orchestrator, scheduled missions, Slack> and webhook triggers, realtime voice orchestration, a built-in Monaco IDE with git-> history and branch compare, markdown previews, and auto-update. Current version: 0.3.7+> history and branch compare, markdown previews, usage-limit aware delivery, and auto-update. Current version: 0.3.8> (August 2026). Desktop app for macOS, Windows, and Linux. No vendor cloud; code never> leaves your machine. It covers the same jobs as YC's qm (security postures, background> crons/watches, Slack, shared skills) as a simpler local-first desktop app, and adds what@@ -22,6 +22,7 @@## Key guides- [What's up with Munder Difflin](https://munderdiffl.in/blog/whats-up-with-munder-difflin/): everything shipped from v0.3.3 to v0.3.7+- [When the CLI stops listening](https://munderdiffl.in/blog/when-the-cli-stops-listening/): the v0.3.8 fix — a rate-limited CLI discards keystrokes silently, so the floor now pauses and resumes itself- [Why our auto-update never ran](https://munderdiffl.in/blog/why-our-auto-update-never-ran/): the v0.3.7 fix — a CommonJS export that vanished into an ESM namespace- [What's new in v0.3.5](https://munderdiffl.in/blog/launching-munder-difflin-v0-3-5/): the v0.3.4+v0.3.5 release wave- [How to install and use Munder Difflin](https://munderdiffl.in/blog/how-to-install-and-use-munder-difflin/)diff --git a/docs/sitemap.xml b/docs/sitemap.xmlindex cbcb7a31..e0eddf39 100644--- a/docs/sitemap.xml+++ b/docs/sitemap.xml@@ -10,13 +10,19 @@<urlset xmlns="http://www.sitemaps.org/schemas/sitemap/0.9"><url><loc>https://munderdiffl.in/</loc>- <lastmod>2026-08-08</lastmod>+ <lastmod>2026-08-11</lastmod><changefreq>weekly</changefreq><priority>1.0</priority></url><url><loc>https://munderdiffl.in/blog/</loc><changefreq>daily</changefreq><priority>0.9</priority></url><url><loc>https://munderdiffl.in/blog/topics/</loc><changefreq>weekly</changefreq><priority>0.6</priority></url><url><loc>https://munderdiffl.in/blog/about/</loc><changefreq>monthly</changefreq><priority>0.4</priority></url>+ <url>+ <loc>https://munderdiffl.in/blog/when-the-cli-stops-listening/</loc>+ <lastmod>2026-08-11</lastmod>+ <changefreq>monthly</changefreq>+ <priority>0.8</priority>+ </url><url><loc>https://munderdiffl.in/blog/whats-up-with-munder-difflin/</loc><lastmod>2026-08-08</lastmod>@@ -745,13 +751,13 @@<url><loc>https://munderdiffl.in/blog/tags/guides/</loc><changefreq>weekly</changefreq><priority>0.3</priority></url><url><loc>https://munderdiffl.in/blog/tags/orchestration/</loc><changefreq>weekly</changefreq><priority>0.3</priority></url><url><loc>https://munderdiffl.in/blog/tags/concepts/</loc><changefreq>weekly</changefreq><priority>0.3</priority></url>- <url><loc>https://munderdiffl.in/blog/tags/comparisons/</loc><changefreq>weekly</changefreq><priority>0.3</priority></url><url><loc>https://munderdiffl.in/blog/tags/open-source/</loc><changefreq>weekly</changefreq><priority>0.3</priority></url>+ <url><loc>https://munderdiffl.in/blog/tags/comparisons/</loc><changefreq>weekly</changefreq><priority>0.3</priority></url><url><loc>https://munderdiffl.in/blog/tags/local-first/</loc><changefreq>weekly</changefreq><priority>0.3</priority></url><url><loc>https://munderdiffl.in/blog/tags/story/</loc><changefreq>weekly</changefreq><priority>0.3</priority></url><url><loc>https://munderdiffl.in/blog/tags/automation/</loc><changefreq>weekly</changefreq><priority>0.3</priority></url>- <url><loc>https://munderdiffl.in/blog/tags/tools/</loc><changefreq>weekly</changefreq><priority>0.3</priority></url><url><loc>https://munderdiffl.in/blog/tags/release/</loc><changefreq>weekly</changefreq><priority>0.3</priority></url>+ <url><loc>https://munderdiffl.in/blog/tags/tools/</loc><changefreq>weekly</changefreq><priority>0.3</priority></url><url><loc>https://munderdiffl.in/blog/tags/getting-started/</loc><changefreq>weekly</changefreq><priority>0.3</priority></url><url><loc>https://munderdiffl.in/blog/tags/memory/</loc><changefreq>weekly</changefreq><priority>0.3</priority></url><url><loc>https://munderdiffl.in/blog/tags/human-in-the-loop/</loc><changefreq>weekly</changefreq><priority>0.3</priority></url>@@ -764,10 +770,10 @@<url><loc>https://munderdiffl.in/blog/tags/guardrails/</loc><changefreq>weekly</changefreq><priority>0.3</priority></url><url><loc>https://munderdiffl.in/blog/tags/electron/</loc><changefreq>weekly</changefreq><priority>0.3</priority></url><url><loc>https://munderdiffl.in/blog/tags/autonomous/</loc><changefreq>weekly</changefreq><priority>0.3</priority></url>+ <url><loc>https://munderdiffl.in/blog/tags/reliability/</loc><changefreq>weekly</changefreq><priority>0.3</priority></url><url><loc>https://munderdiffl.in/blog/tags/git/</loc><changefreq>weekly</changefreq><priority>0.3</priority></url><url><loc>https://munderdiffl.in/blog/tags/mcp/</loc><changefreq>weekly</changefreq><priority>0.3</priority></url><url><loc>https://munderdiffl.in/blog/tags/architecture/</loc><changefreq>weekly</changefreq><priority>0.3</priority></url>- <url><loc>https://munderdiffl.in/blog/tags/reliability/</loc><changefreq>weekly</changefreq><priority>0.3</priority></url><url><loc>https://munderdiffl.in/blog/tags/cli-agents/</loc><changefreq>weekly</changefreq><priority>0.3</priority></url><url><loc>https://munderdiffl.in/blog/tags/voice/</loc><changefreq>weekly</changefreq><priority>0.3</priority></url><url><loc>https://munderdiffl.in/blog/tags/ide/</loc><changefreq>weekly</changefreq><priority>0.3</priority></url>@@ -854,4 +860,5 @@<url><loc>https://munderdiffl.in/blog/tags/tooling-landscape/</loc><changefreq>weekly</changefreq><priority>0.3</priority></url><url><loc>https://munderdiffl.in/blog/tags/harness-engineering/</loc><changefreq>weekly</changefreq><priority>0.3</priority></url><url><loc>https://munderdiffl.in/blog/tags/onboarding/</loc><changefreq>weekly</changefreq><priority>0.3</priority></url>+ <url><loc>https://munderdiffl.in/blog/tags/agents/</loc><changefreq>weekly</changefreq><priority>0.3</priority></url></urlset>