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
blog: observability-for-agent-fleets (71 → 72)
Chaitanya Giri116402c65eae
diff --git a/blog/src/posts/observability-for-agent-fleets.md b/blog/src/posts/observability-for-agent-fleets.mdnew file mode 100644index 00000000..fe03c881--- /dev/null+++ b/blog/src/posts/observability-for-agent-fleets.md@@ -0,0 +1,119 @@+---+title: "Observability for Agent Fleets: Seeing What Your Agents Do"+description: "Agent fleet observability: the four questions your dashboard must answer about who's working, what they're doing, what it costs, and what they know."+date: 2026-06-04+category: internals+categoryLabel: Internals+type: Technical+primaryKeyword: "ai agent observability"+secondaryKeywords: ["agent fleet monitoring", "agent token cost tracking", "multi-agent dashboard"]+tags: ["Internals", "Observability", "Multi-Agent", "Claude Code"]+author:+ name: Chaitanya Giri+ initials: CG+faq:+ - q: "How is observability for AI agents different from normal app observability?"+ a: "App observability watches deterministic services — latency, error rates, throughput. Agent observability watches non-deterministic actors that make their own choices: which tools they call, what they decide, what they spend, what they remember. You're not just asking 'is it up?' but 'what is it doing and why, and is that what I wanted?' That needs a feed of intent and actions, not just health metrics."+ - q: "Why track token cost per agent?"+ a: "Because autonomous agents spend money without asking, and a runaway loop or an over-eager agent shows up first as a cost spike. Per-agent token and dollar telemetry turns 'the bill is high' into 'this agent is the reason' — fast enough to intervene. It's the cheapest early-warning signal an agent fleet has."+ - q: "Where does the telemetry come from?"+ a: "Two sources: lifecycle hooks stream what each agent is doing in real time, and the agents' own transcript files record exact token counts. Combine the live event stream with the on-disk usage and you can reconstruct both 'what happened' and 'what it cost' without instrumenting the model itself."+---++<div class="callout tldr"><span class="ic">TL;DR</span><p>A fleet of autonomous agents you can't see is a+fleet you can't manage. Good agent observability answers four questions at a glance: <strong>who's+working</strong> (roster + status), <strong>what are they doing</strong> (a live activity feed from the+event log), <strong>what is it costing</strong> (per-agent token + dollar telemetry from their+transcripts), and <strong>what do they know</strong> (task board + memory). Build that dashboard and+"my agents are off doing something" becomes "I can see exactly what, and step in early."</p></div>++When you run one agent, you watch its terminal. When you run twenty, you can't — and the failure modes+change. An agent quietly loops and burns tokens. Two pick up overlapping work. One stalls waiting on a+message that never came. None of that shows up in a terminal you're not staring at. A fleet needs a+dashboard, and "agent observability" is a different problem from watching a normal service. Here's the+shape of one that works.++## The four questions a fleet dashboard must answer++App monitoring asks "is it healthy?" Agent monitoring asks four sharper questions:++1. **Who's working?** Which agents are active vs idle vs archived.+2. **What are they doing?** A live, human-readable stream of their actions and messages.+3. **What is it costing?** Token and dollar spend, per agent, in near-real-time.+4. **What do they know?** The shared task state and memory driving their decisions.++Miss any one and you're flying partly blind. Below is how each maps to something concrete.++## A live activity feed from the event log++The backbone is a single [append-only event log](/blog/append-only-event-log-agents/): every spawn,+message, inbox drain, and escalation gets one line. A dashboard renders that log as a human-readable feed —+not raw JSON, but sentences:++- `spawned Pam`+- `Jim → Stanley: Task from you`+- `Stanley drained 2 msg(s)`+- `escalated to human: merge approval`++Now "what's the fleet doing right now" is a glance, not an investigation. The feed is fed by+[lifecycle hooks](/blog/the-hook-shim-pattern/): every agent's tool-use, stops, and notifications stream+into the main process in real time, so the picture is live rather than a periodic poll. The same+[orchestrator](/blog/how-the-god-orchestrator-works/) that routes work reads this feed to keep its+situational awareness current.++## Token and cost telemetry, per agent++This is the part teams skip and regret. Autonomous agents spend money on their own, so **cost is a+first-class signal**, not an end-of-month surprise.++The trick is that you don't have to instrument the model — the usage is already on disk. Each agent's+Claude Code transcripts record exact input and output token counts. A usage meter reads those transcripts+per agent (polling every few seconds), shows input/output tokens and an estimated dollar cost, and+normalizes a bar against the most-expensive agent so the outlier is obvious at a glance. A runaway loop or+an over-eager agent stops being "the bill looks high" and becomes "that row is three times everyone else"+— early enough to intervene. Cost telemetry is the cheapest smoke detector a fleet has.++## State at a glance: task board, memory, roster++Actions and cost tell you *what's happening*; state tells you *why*.++- **A task board.** A kanban of todo / doing / blocked / done makes coordination visible — what's queued,+ what's stuck, who owns what. "Blocked" columns are where fleets silently stall.+- **A memory view and graph.** What the hive [knows](/blog/semantic-memory-for-ai-agents/) — and being able+ to jump into any agent's memory — explains decisions. An agent acting oddly usually has an odd memory.+- **A roster with per-agent model.** Who exists, who's active, and which model each runs. Useful for both+ "is everyone alive?" and "why is the Opus agent the cost outlier?"++Add a full-text search across the board, tasks, and memory and you can answer ad-hoc questions ("who+mentioned the release?") without grepping files by hand.++## Observability vs debugging++These are different jobs. [Debugging a multi-agent system](/blog/debugging-multi-agent-systems/) is+*reactive* — something broke, you reconstruct why. Observability is *proactive* — a standing picture that+lets you catch the loop, the collision, or the cost spike **before** it becomes an incident. The activity+feed and usage meter are how you notice; the event log and transcripts are how you then dig in. You want+both, and the observability layer is what tells you when to switch from watching to debugging.++The quiet payoff: once you can *see* a fleet cheaply, you trust it to run unattended. Visibility is what+makes "leave the agents working" a calm decision instead of a leap of faith.++## FAQ++**Do I need a metrics stack like Prometheus/Grafana?** Not to start. A fleet of dozens of local agents is+well served by reading the event log and transcripts directly and rendering them. Reach for a heavy+metrics stack when you're distributed across machines and need retention and alerting at scale.++**What's the single highest-value signal?** Per-agent cost. It catches runaway loops, surfaces the+expensive outlier, and is trivial to read from transcripts. If you add one thing, add that.++**How live is "live"?** The activity feed is event-driven (pushed by hooks as things happen); the usage+meter polls transcripts every several seconds. Plenty fast for agent turns measured in seconds to minutes.++---++Munder Difflin ships this as the orchestrator's control surface — a live activity feed, per-agent token+and cost meters, a task board, and a memory graph for a whole+[hive of Claude Code agents](https://munderdiffl.in/#how), all local.+[Download Munder Difflin](https://munderdiffl.in/#install) to watch your fleet at a glance; it's free and+open source.diff --git a/docs/blog/append-only-event-log-agents/index.html b/docs/blog/append-only-event-log-agents/index.htmlindex fb4e4666..c859da6d 100644--- a/docs/blog/append-only-event-log-agents/index.html+++ b/docs/blog/append-only-event-log-agents/index.html@@ -322,20 +322,20 @@ it’s free and open source.</p></div></article><article class="card">- <a class="thumb t-internals" href="/blog/recovering-from-agent-failures/" aria-hidden="true" tabindex="-1">+ <a class="thumb t-internals" href="/blog/observability-for-agent-fleets/" aria-hidden="true" tabindex="-1"><span>INTERNALS</span></a><div class="body"><div class="meta"><time datetime="2026-06-04">Jun 4, 2026</time><span class="dot" aria-hidden="true"></span>- <span>6 min</span>+ <span>4 min</span></div>- <h3><a href="/blog/recovering-from-agent-failures/">Recovering From Agent Failures: Resilience Patterns for a Hive</a></h3>- <p class="dek">How multi-agent systems survive partial failure: retry with stale-lock recovery, poison-message quarantine, hop-cap circuit breaking, idempotent handling.</p>+ <h3><a href="/blog/observability-for-agent-fleets/">Observability for Agent Fleets: Seeing What Your Agents Do</a></h3>+ <p class="dek">Agent fleet observability: the four questions your dashboard must answer about who's working, what they're doing, what it costs, and what they know.</p><div class="foot"><span class="tag kind">Internals</span>- <a class="more" href="/blog/recovering-from-agent-failures/" aria-label="Read: Recovering From Agent Failures: Resilience Patterns for a Hive">Read →</a>+ <a class="more" href="/blog/observability-for-agent-fleets/" aria-label="Read: Observability for Agent Fleets: Seeing What Your Agents Do">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 631f7d8b..3fc31948 100644--- a/docs/blog/architecture-two-planes-one-renderer/index.html+++ b/docs/blog/architecture-two-planes-one-renderer/index.html@@ -307,25 +307,25 @@ free and open source.</p></div></article><article class="card">- <a class="thumb t-internals" href="/blog/recovering-from-agent-failures/" aria-hidden="true" tabindex="-1">+ <a class="thumb t-internals" href="/blog/observability-for-agent-fleets/" aria-hidden="true" tabindex="-1"><span>INTERNALS</span></a><div class="body"><div class="meta"><time datetime="2026-06-04">Jun 4, 2026</time><span class="dot" aria-hidden="true"></span>- <span>6 min</span>+ <span>4 min</span></div>- <h3><a href="/blog/recovering-from-agent-failures/">Recovering From Agent Failures: Resilience Patterns for a Hive</a></h3>- <p class="dek">How multi-agent systems survive partial failure: retry with stale-lock recovery, poison-message quarantine, hop-cap circuit breaking, idempotent handling.</p>+ <h3><a href="/blog/observability-for-agent-fleets/">Observability for Agent Fleets: Seeing What Your Agents Do</a></h3>+ <p class="dek">Agent fleet observability: the four questions your dashboard must answer about who's working, what they're doing, what it costs, and what they know.</p><div class="foot"><span class="tag kind">Internals</span>- <a class="more" href="/blog/recovering-from-agent-failures/" aria-label="Read: Recovering From Agent Failures: Resilience Patterns for a Hive">Read →</a>+ <a class="more" href="/blog/observability-for-agent-fleets/" aria-label="Read: Observability for Agent Fleets: Seeing What Your Agents Do">Read →</a></div></div></article><article class="card">- <a class="thumb t-internals" href="/blog/the-hook-shim-pattern/" aria-hidden="true" tabindex="-1">+ <a class="thumb t-internals" href="/blog/recovering-from-agent-failures/" aria-hidden="true" tabindex="-1"><span>INTERNALS</span></a><div class="body">@@ -334,11 +334,11 @@ free and open source.</p><span class="dot" aria-hidden="true"></span><span>6 min</span></div>- <h3><a href="/blog/the-hook-shim-pattern/">The Hook Shim Pattern: Wiring Agent Hooks to a Live Process</a></h3>- <p class="dek">How a tiny shim bridges Claude Code's lifecycle hooks to one live process over a Unix socket, turning per-event hooks into a telemetry and control channel.</p>+ <h3><a href="/blog/recovering-from-agent-failures/">Recovering From Agent Failures: Resilience Patterns for a Hive</a></h3>+ <p class="dek">How multi-agent systems survive partial failure: retry with stale-lock recovery, poison-message quarantine, hop-cap circuit breaking, idempotent handling.</p><div class="foot"><span class="tag kind">Internals</span>- <a class="more" href="/blog/the-hook-shim-pattern/" aria-label="Read: The Hook Shim Pattern: Wiring Agent Hooks to a Live Process">Read →</a>+ <a class="more" href="/blog/recovering-from-agent-failures/" aria-label="Read: Recovering From Agent Failures: Resilience Patterns for a Hive">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 29d13b93..d132d527 100644--- a/docs/blog/atomic-file-mailboxes-for-agents/index.html+++ b/docs/blog/atomic-file-mailboxes-for-agents/index.html@@ -337,20 +337,20 @@ the office floor; it’s free and open source.</p></div></article><article class="card">- <a class="thumb t-internals" href="/blog/recovering-from-agent-failures/" aria-hidden="true" tabindex="-1">+ <a class="thumb t-internals" href="/blog/observability-for-agent-fleets/" aria-hidden="true" tabindex="-1"><span>INTERNALS</span></a><div class="body"><div class="meta"><time datetime="2026-06-04">Jun 4, 2026</time><span class="dot" aria-hidden="true"></span>- <span>6 min</span>+ <span>4 min</span></div>- <h3><a href="/blog/recovering-from-agent-failures/">Recovering From Agent Failures: Resilience Patterns for a Hive</a></h3>- <p class="dek">How multi-agent systems survive partial failure: retry with stale-lock recovery, poison-message quarantine, hop-cap circuit breaking, idempotent handling.</p>+ <h3><a href="/blog/observability-for-agent-fleets/">Observability for Agent Fleets: Seeing What Your Agents Do</a></h3>+ <p class="dek">Agent fleet observability: the four questions your dashboard must answer about who's working, what they're doing, what it costs, and what they know.</p><div class="foot"><span class="tag kind">Internals</span>- <a class="more" href="/blog/recovering-from-agent-failures/" aria-label="Read: Recovering From Agent Failures: Resilience Patterns for a Hive">Read →</a>+ <a class="more" href="/blog/observability-for-agent-fleets/" aria-label="Read: Observability for Agent Fleets: Seeing What Your Agents Do">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 815f610f..670c283c 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@@ -380,20 +380,20 @@ to watch many real terminals at once; it’s free and open source.</p></div></article><article class="card">- <a class="thumb t-internals" href="/blog/recovering-from-agent-failures/" aria-hidden="true" tabindex="-1">+ <a class="thumb t-internals" href="/blog/observability-for-agent-fleets/" aria-hidden="true" tabindex="-1"><span>INTERNALS</span></a><div class="body"><div class="meta"><time datetime="2026-06-04">Jun 4, 2026</time><span class="dot" aria-hidden="true"></span>- <span>6 min</span>+ <span>4 min</span></div>- <h3><a href="/blog/recovering-from-agent-failures/">Recovering From Agent Failures: Resilience Patterns for a Hive</a></h3>- <p class="dek">How multi-agent systems survive partial failure: retry with stale-lock recovery, poison-message quarantine, hop-cap circuit breaking, idempotent handling.</p>+ <h3><a href="/blog/observability-for-agent-fleets/">Observability for Agent Fleets: Seeing What Your Agents Do</a></h3>+ <p class="dek">Agent fleet observability: the four questions your dashboard must answer about who's working, what they're doing, what it costs, and what they know.</p><div class="foot"><span class="tag kind">Internals</span>- <a class="more" href="/blog/recovering-from-agent-failures/" aria-label="Read: Recovering From Agent Failures: Resilience Patterns for a Hive">Read →</a>+ <a class="more" href="/blog/observability-for-agent-fleets/" aria-label="Read: Observability for Agent Fleets: Seeing What Your Agents Do">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 7fbd3f94..457fc422 100644--- a/docs/blog/building-an-ai-office-floor/index.html+++ b/docs/blog/building-an-ai-office-floor/index.html@@ -325,20 +325,20 @@ techniques — the hard part is wiring them to <em>real</em> agent events, not t</div></article><article class="card">- <a class="thumb t-internals" href="/blog/recovering-from-agent-failures/" aria-hidden="true" tabindex="-1">+ <a class="thumb t-internals" href="/blog/observability-for-agent-fleets/" aria-hidden="true" tabindex="-1"><span>INTERNALS</span></a><div class="body"><div class="meta"><time datetime="2026-06-04">Jun 4, 2026</time><span class="dot" aria-hidden="true"></span>- <span>6 min</span>+ <span>4 min</span></div>- <h3><a href="/blog/recovering-from-agent-failures/">Recovering From Agent Failures: Resilience Patterns for a Hive</a></h3>- <p class="dek">How multi-agent systems survive partial failure: retry with stale-lock recovery, poison-message quarantine, hop-cap circuit breaking, idempotent handling.</p>+ <h3><a href="/blog/observability-for-agent-fleets/">Observability for Agent Fleets: Seeing What Your Agents Do</a></h3>+ <p class="dek">Agent fleet observability: the four questions your dashboard must answer about who's working, what they're doing, what it costs, and what they know.</p><div class="foot"><span class="tag kind">Internals</span>- <a class="more" href="/blog/recovering-from-agent-failures/" aria-label="Read: Recovering From Agent Failures: Resilience Patterns for a Hive">Read →</a>+ <a class="more" href="/blog/observability-for-agent-fleets/" aria-label="Read: Observability for Agent Fleets: Seeing What Your Agents Do">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 f2a6f0b4..6ca63695 100644--- a/docs/blog/claude-code-hooks-explained/index.html+++ b/docs/blog/claude-code-hooks-explained/index.html@@ -339,20 +339,20 @@ free and open source.</p></div></article><article class="card">- <a class="thumb t-internals" href="/blog/recovering-from-agent-failures/" aria-hidden="true" tabindex="-1">+ <a class="thumb t-internals" href="/blog/observability-for-agent-fleets/" aria-hidden="true" tabindex="-1"><span>INTERNALS</span></a><div class="body"><div class="meta"><time datetime="2026-06-04">Jun 4, 2026</time><span class="dot" aria-hidden="true"></span>- <span>6 min</span>+ <span>4 min</span></div>- <h3><a href="/blog/recovering-from-agent-failures/">Recovering From Agent Failures: Resilience Patterns for a Hive</a></h3>- <p class="dek">How multi-agent systems survive partial failure: retry with stale-lock recovery, poison-message quarantine, hop-cap circuit breaking, idempotent handling.</p>+ <h3><a href="/blog/observability-for-agent-fleets/">Observability for Agent Fleets: Seeing What Your Agents Do</a></h3>+ <p class="dek">Agent fleet observability: the four questions your dashboard must answer about who's working, what they're doing, what it costs, and what they know.</p><div class="foot"><span class="tag kind">Internals</span>- <a class="more" href="/blog/recovering-from-agent-failures/" aria-label="Read: Recovering From Agent Failures: Resilience Patterns for a Hive">Read →</a>+ <a class="more" href="/blog/observability-for-agent-fleets/" aria-label="Read: Observability for Agent Fleets: Seeing What Your Agents Do">Read →</a></div></div></article>diff --git a/docs/blog/feed.xml b/docs/blog/feed.xmlindex 7e2c4518..696d0669 100644--- a/docs/blog/feed.xml+++ b/docs/blog/feed.xml@@ -199,6 +199,14 @@<updated>2026-06-04T00:00:00.000Z</updated><category term="Concepts" /><summary>Agents used to answer in seconds; now they run for hours. The data behind the shift — and why a longer agent is a different problem, not just a bigger one.</summary></entry>+ <entry>+ <title>Observability for Agent Fleets: Seeing What Your Agents Do</title>+ <link href="https://munderdiffl.in/blog/observability-for-agent-fleets/" />+ <id>https://munderdiffl.in/blog/observability-for-agent-fleets/</id>+ <published>2026-06-04T00:00:00.000Z</published>+ <updated>2026-06-04T00:00:00.000Z</updated><category term="Internals" />+ <summary>Agent fleet observability: the four questions your dashboard must answer about who's working, what they're doing, what it costs, and what they know.</summary>+ </entry><entry><title>Building AI Dev Tools in the Open, On Purpose</title><link href="https://munderdiffl.in/blog/open-source-ai-tools-on-purpose/" />@@ -479,12 +487,4 @@<updated>2026-06-01T00:00:00.000Z</updated><category term="Internals" /><summary>How an append-only event log makes a multi-agent system debuggable and replayable: what to record, and why one JSON line per event beats a database.</summary></entry>- <entry>- <title>How to Run Multiple Claude Code Agents (Without Losing Track)</title>- <link href="https://munderdiffl.in/blog/how-to-run-multiple-claude-code-agents/" />- <id>https://munderdiffl.in/blog/how-to-run-multiple-claude-code-agents/</id>- <published>2026-06-01T00:00:00.000Z</published>- <updated>2026-06-01T00:00:00.000Z</updated><category term="Guides" />- <summary>Run several Claude Code agents in parallel without the chaos: give each a role, let them coordinate, and stop alt-tabbing between terminal windows.</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 902e2b2c..b0fd655b 100644--- a/docs/blog/file-based-coordination-vs-message-queues/index.html+++ b/docs/blog/file-based-coordination-vs-message-queues/index.html@@ -280,25 +280,25 @@ durable, git-versioned, and debuggable by just looking.</div></article><article class="card">- <a class="thumb t-internals" href="/blog/recovering-from-agent-failures/" aria-hidden="true" tabindex="-1">+ <a class="thumb t-internals" href="/blog/observability-for-agent-fleets/" aria-hidden="true" tabindex="-1"><span>INTERNALS</span></a><div class="body"><div class="meta"><time datetime="2026-06-04">Jun 4, 2026</time><span class="dot" aria-hidden="true"></span>- <span>6 min</span>+ <span>4 min</span></div>- <h3><a href="/blog/recovering-from-agent-failures/">Recovering From Agent Failures: Resilience Patterns for a Hive</a></h3>- <p class="dek">How multi-agent systems survive partial failure: retry with stale-lock recovery, poison-message quarantine, hop-cap circuit breaking, idempotent handling.</p>+ <h3><a href="/blog/observability-for-agent-fleets/">Observability for Agent Fleets: Seeing What Your Agents Do</a></h3>+ <p class="dek">Agent fleet observability: the four questions your dashboard must answer about who's working, what they're doing, what it costs, and what they know.</p><div class="foot"><span class="tag kind">Internals</span>- <a class="more" href="/blog/recovering-from-agent-failures/" aria-label="Read: Recovering From Agent Failures: Resilience Patterns for a Hive">Read →</a>+ <a class="more" href="/blog/observability-for-agent-fleets/" aria-label="Read: Observability for Agent Fleets: Seeing What Your Agents Do">Read →</a></div></div></article><article class="card">- <a class="thumb t-internals" href="/blog/the-hook-shim-pattern/" aria-hidden="true" tabindex="-1">+ <a class="thumb t-internals" href="/blog/recovering-from-agent-failures/" aria-hidden="true" tabindex="-1"><span>INTERNALS</span></a><div class="body">@@ -307,11 +307,11 @@ durable, git-versioned, and debuggable by just looking.<span class="dot" aria-hidden="true"></span><span>6 min</span></div>- <h3><a href="/blog/the-hook-shim-pattern/">The Hook Shim Pattern: Wiring Agent Hooks to a Live Process</a></h3>- <p class="dek">How a tiny shim bridges Claude Code's lifecycle hooks to one live process over a Unix socket, turning per-event hooks into a telemetry and control channel.</p>+ <h3><a href="/blog/recovering-from-agent-failures/">Recovering From Agent Failures: Resilience Patterns for a Hive</a></h3>+ <p class="dek">How multi-agent systems survive partial failure: retry with stale-lock recovery, poison-message quarantine, hop-cap circuit breaking, idempotent handling.</p><div class="foot"><span class="tag kind">Internals</span>- <a class="more" href="/blog/the-hook-shim-pattern/" aria-label="Read: The Hook Shim Pattern: Wiring Agent Hooks to a Live Process">Read →</a>+ <a class="more" href="/blog/recovering-from-agent-failures/" aria-label="Read: Recovering From Agent Failures: Resilience Patterns for a Hive">Read →</a></div></div></article>diff --git a/docs/blog/index.html b/docs/blog/index.htmlindex 01ee76d0..9a43ba23 100644--- a/docs/blog/index.html+++ b/docs/blog/index.html@@ -85,11 +85,11 @@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">71</span></a>+ <a class="chip" aria-current="page">All<span class="ct">72</span></a><a class="chip" href="/blog/topics/guides/">guides<span class="ct">19</span></a>- <a class="chip" href="/blog/topics/internals/">internals<span class="ct">13</span></a>+ <a class="chip" href="/blog/topics/internals/">internals<span class="ct">14</span></a><a class="chip" href="/blog/topics/concepts/">concepts<span class="ct">11</span></a>@@ -545,6 +545,24 @@</div></div></article>+<article class="card">+ <a class="thumb t-internals" href="/blog/observability-for-agent-fleets/" aria-hidden="true" tabindex="-1">+ <span>INTERNALS</span>+ </a>+ <div class="body">+ <div class="meta">+ <time datetime="2026-06-04">Jun 4, 2026</time>+ <span class="dot" aria-hidden="true"></span>+ <span>4 min</span>+ </div>+ <h3><a href="/blog/observability-for-agent-fleets/">Observability for Agent Fleets: Seeing What Your Agents Do</a></h3>+ <p class="dek">Agent fleet observability: the four questions your dashboard must answer about who's working, what they're doing, what it costs, and what they know.</p>+ <div class="foot">+ <span class="tag kind">Internals</span>+ <a class="more" href="/blog/observability-for-agent-fleets/" aria-label="Read: Observability for Agent Fleets: Seeing What Your Agents Do">Read →</a>+ </div>+ </div>+</article><article class="card"><a class="thumb t-concepts" href="/blog/open-source-ai-tools-on-purpose/" aria-hidden="true" tabindex="-1"><span>CONCEPTS</span>diff --git a/docs/blog/long-running-agents-the-2026-shift/index.html b/docs/blog/long-running-agents-the-2026-shift/index.htmlindex c7f1ceec..d4f07652 100644--- a/docs/blog/long-running-agents-the-2026-shift/index.html+++ b/docs/blog/long-running-agents-the-2026-shift/index.html@@ -287,7 +287,7 @@ source.</p></div><footer class="post-foot wrap"><div class="prevnext">- <a class="pn prev" href="/blog/open-source-ai-tools-on-purpose/"><span class="k">← Older</span><span class="t">Building AI Dev Tools in the Open, On Purpose</span></a>+ <a class="pn prev" href="/blog/observability-for-agent-fleets/"><span class="k">← Older</span><span class="t">Observability for Agent Fleets: Seeing What Your Agents Do</span></a><a class="pn next" href="/blog/local-first-vs-cloud-agent-sdks/"><span class="k">Newer →</span><span class="t">Local-First vs Cloud Agent SDKs: Which Wins in 2026?</span></a></div><section class="related">diff --git a/docs/blog/node-pty-electron-real-terminals/index.html b/docs/blog/node-pty-electron-real-terminals/index.htmlindex dd266cfd..718e94ee 100644--- a/docs/blog/node-pty-electron-real-terminals/index.html+++ b/docs/blog/node-pty-electron-real-terminals/index.html@@ -360,20 +360,20 @@ real terminals driving real agents; it’s free and open source.</p></div></article><article class="card">- <a class="thumb t-internals" href="/blog/recovering-from-agent-failures/" aria-hidden="true" tabindex="-1">+ <a class="thumb t-internals" href="/blog/observability-for-agent-fleets/" aria-hidden="true" tabindex="-1"><span>INTERNALS</span></a><div class="body"><div class="meta"><time datetime="2026-06-04">Jun 4, 2026</time><span class="dot" aria-hidden="true"></span>- <span>6 min</span>+ <span>4 min</span></div>- <h3><a href="/blog/recovering-from-agent-failures/">Recovering From Agent Failures: Resilience Patterns for a Hive</a></h3>- <p class="dek">How multi-agent systems survive partial failure: retry with stale-lock recovery, poison-message quarantine, hop-cap circuit breaking, idempotent handling.</p>+ <h3><a href="/blog/observability-for-agent-fleets/">Observability for Agent Fleets: Seeing What Your Agents Do</a></h3>+ <p class="dek">Agent fleet observability: the four questions your dashboard must answer about who's working, what they're doing, what it costs, and what they know.</p><div class="foot"><span class="tag kind">Internals</span>- <a class="more" href="/blog/recovering-from-agent-failures/" aria-label="Read: Recovering From Agent Failures: Resilience Patterns for a Hive">Read →</a>+ <a class="more" href="/blog/observability-for-agent-fleets/" aria-label="Read: Observability for Agent Fleets: Seeing What Your Agents Do">Read →</a></div></div></article>diff --git a/docs/blog/observability-for-agent-fleets/index.html b/docs/blog/observability-for-agent-fleets/index.htmlnew file mode 100644index 00000000..ee7835eb--- /dev/null+++ b/docs/blog/observability-for-agent-fleets/index.html@@ -0,0 +1,360 @@+<!doctype html>+<html lang="en">+<head>+<meta charset="UTF-8" />+<meta name="viewport" content="width=device-width, initial-scale=1.0" />+<title>Observability for Agent Fleets: Seeing What Your Agents Do — Munder Difflin Blog</title>+<meta name="description" content="Agent fleet observability: the four questions your dashboard must answer about who's working, what they're doing, what it costs, and what they know." />+<link rel="canonical" href="https://munderdiffl.in/blog/observability-for-agent-fleets/" />++<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="Observability for Agent Fleets: Seeing What Your Agents Do — Munder Difflin Blog" />+<meta property="og:description" content="Agent fleet observability: the four questions your dashboard must answer about who's working, what they're doing, what it costs, and what they know." />+<meta property="og:url" content="https://munderdiffl.in/blog/observability-for-agent-fleets/" />+<meta property="og:image" content="https://munderdiffl.in/media/og.png" />+<meta property="og:locale" content="en_US" />+<meta property="article:published_time" content="2026-06-04T00:00:00.000Z" />+<meta property="article:author" content="Chaitanya Giri" />+<meta property="article:tag" content="Internals" />+<meta property="article:tag" content="Observability" />+<meta property="article:tag" content="Multi-Agent" />+<meta property="article:tag" content="Claude Code" />+++<!-- Twitter -->+<meta name="twitter:card" content="summary_large_image" />+<meta name="twitter:title" content="Observability for Agent Fleets: Seeing What Your Agents Do — Munder Difflin Blog" />+<meta name="twitter:description" content="Agent fleet observability: the four questions your dashboard must answer about who's working, what they're doing, what it costs, and what they know." />+<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": "Observability for Agent Fleets: Seeing What Your Agents Do",+ "description": "Agent fleet observability: the four questions your dashboard must answer about who's working, what they're doing, what it costs, and what they know.",+ "image": ["https://munderdiffl.in/media/og.png"],+ "datePublished": "2026-06-04T00:00:00.000Z",+ "dateModified": "2026-06-04T00:00:00.000Z",+ "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/observability-for-agent-fleets/" },+ "keywords": "ai agent observability, agent fleet monitoring, agent token cost tracking, multi-agent dashboard",+ "articleSection": "Internals",+ "inLanguage": "en-US",+ "url": "https://munderdiffl.in/blog/observability-for-agent-fleets/"+}+</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": "Observability for Agent Fleets: Seeing What Your Agents Do", "item": "https://munderdiffl.in/blog/observability-for-agent-fleets/" }+ ]+}+</script>++<script type="application/ld+json">+{+ "@context": "https://schema.org",+ "@type": "FAQPage",+ "mainEntity": [+ { "@type": "Question", "name": "How is observability for AI agents different from normal app observability?", "acceptedAnswer": { "@type": "Answer", "text": "App observability watches deterministic services — latency, error rates, throughput. Agent observability watches non-deterministic actors that make their own choices: which tools they call, what they decide, what they spend, what they remember. You're not just asking 'is it up?' but 'what is it doing and why, and is that what I wanted?' That needs a feed of intent and actions, not just health metrics." } },+ { "@type": "Question", "name": "Why track token cost per agent?", "acceptedAnswer": { "@type": "Answer", "text": "Because autonomous agents spend money without asking, and a runaway loop or an over-eager agent shows up first as a cost spike. Per-agent token and dollar telemetry turns 'the bill is high' into 'this agent is the reason' — fast enough to intervene. It's the cheapest early-warning signal an agent fleet has." } },+ { "@type": "Question", "name": "Where does the telemetry come from?", "acceptedAnswer": { "@type": "Answer", "text": "Two sources: lifecycle hooks stream what each agent is doing in real time, and the agents' own transcript files record exact token counts. Combine the live event stream with the on-disk usage and you can reconstruct both 'what happened' and 'what it cost' without instrumenting the model itself." } }++ ]+}+</script>+++</head>+<body>+<a class="skip-link" href="#main">Skip to content</a>+<nav id="nav">+ <a class="brand" href="/blog/" aria-label="Munder Difflin Blog home">+ <span class="brand-mark">MD</span>+ <span class="brand-word">MUNDER DIFFLIN<span class="sep">/</span><span class="blog">BLOG</span></span>+ </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>Observability for Agent Fleets: Seeing What Your Agents Do</h1>+ <p class="dek">Agent fleet observability: the four questions your dashboard must answer about who's working, what they're doing, what it costs, and what they know.</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="2026-06-04">Jun 4, 2026</time>+ <span class="dot" aria-hidden="true">·</span>+ <span>4 min read</span>+ <span class="tag kind">Internals</span>+ </div>+ </header>++ <div class="post-wrap wrap">+ <div class="prose">+ <div class="callout tldr"><span class="ic">TL;DR</span><p>A fleet of autonomous agents you can't see is a+fleet you can't manage. Good agent observability answers four questions at a glance: <strong>who's+working</strong> (roster + status), <strong>what are they doing</strong> (a live activity feed from the+event log), <strong>what is it costing</strong> (per-agent token + dollar telemetry from their+transcripts), and <strong>what do they know</strong> (task board + memory). Build that dashboard and+"my agents are off doing something" becomes "I can see exactly what, and step in early."</p></div>+<p>When you run one agent, you watch its terminal. When you run twenty, you can’t — and the failure modes+change. An agent quietly loops and burns tokens. Two pick up overlapping work. One stalls waiting on a+message that never came. None of that shows up in a terminal you’re not staring at. A fleet needs a+dashboard, and “agent observability” is a different problem from watching a normal service. Here’s the+shape of one that works.</p>+<h2 id="the-four-questions-a-fleet-dashboard-must-answer" tabindex="-1">The four questions a fleet dashboard must answer <a class="anchor" href="#the-four-questions-a-fleet-dashboard-must-answer" aria-hidden="true">#</a></h2>+<p>App monitoring asks “is it healthy?” Agent monitoring asks four sharper questions:</p>+<ol>+<li><strong>Who’s working?</strong> Which agents are active vs idle vs archived.</li>+<li><strong>What are they doing?</strong> A live, human-readable stream of their actions and messages.</li>+<li><strong>What is it costing?</strong> Token and dollar spend, per agent, in near-real-time.</li>+<li><strong>What do they know?</strong> The shared task state and memory driving their decisions.</li>+</ol>+<p>Miss any one and you’re flying partly blind. Below is how each maps to something concrete.</p>+<h2 id="a-live-activity-feed-from-the-event-log" tabindex="-1">A live activity feed from the event log <a class="anchor" href="#a-live-activity-feed-from-the-event-log" aria-hidden="true">#</a></h2>+<p>The backbone is a single <a href="/blog/append-only-event-log-agents/">append-only event log</a>: every spawn,+message, inbox drain, and escalation gets one line. A dashboard renders that log as a human-readable feed —+not raw JSON, but sentences:</p>+<ul>+<li><code>spawned Pam</code></li>+<li><code>Jim → Stanley: Task from you</code></li>+<li><code>Stanley drained 2 msg(s)</code></li>+<li><code>escalated to human: merge approval</code></li>+</ul>+<p>Now “what’s the fleet doing right now” is a glance, not an investigation. The feed is fed by+<a href="/blog/the-hook-shim-pattern/">lifecycle hooks</a>: every agent’s tool-use, stops, and notifications stream+into the main process in real time, so the picture is live rather than a periodic poll. The same+<a href="/blog/how-the-god-orchestrator-works/">orchestrator</a> that routes work reads this feed to keep its+situational awareness current.</p>+<h2 id="token-and-cost-telemetry-per-agent" tabindex="-1">Token and cost telemetry, per agent <a class="anchor" href="#token-and-cost-telemetry-per-agent" aria-hidden="true">#</a></h2>+<p>This is the part teams skip and regret. Autonomous agents spend money on their own, so <strong>cost is a+first-class signal</strong>, not an end-of-month surprise.</p>+<p>The trick is that you don’t have to instrument the model — the usage is already on disk. Each agent’s+Claude Code transcripts record exact input and output token counts. A usage meter reads those transcripts+per agent (polling every few seconds), shows input/output tokens and an estimated dollar cost, and+normalizes a bar against the most-expensive agent so the outlier is obvious at a glance. A runaway loop or+an over-eager agent stops being “the bill looks high” and becomes “that row is three times everyone else”+— early enough to intervene. Cost telemetry is the cheapest smoke detector a fleet has.</p>+<h2 id="state-at-a-glance-task-board-memory-roster" tabindex="-1">State at a glance: task board, memory, roster <a class="anchor" href="#state-at-a-glance-task-board-memory-roster" aria-hidden="true">#</a></h2>+<p>Actions and cost tell you <em>what’s happening</em>; state tells you <em>why</em>.</p>+<ul>+<li><strong>A task board.</strong> A kanban of todo / doing / blocked / done makes coordination visible — what’s queued,+what’s stuck, who owns what. “Blocked” columns are where fleets silently stall.</li>+<li><strong>A memory view and graph.</strong> What the hive <a href="/blog/semantic-memory-for-ai-agents/">knows</a> — and being able+to jump into any agent’s memory — explains decisions. An agent acting oddly usually has an odd memory.</li>+<li><strong>A roster with per-agent model.</strong> Who exists, who’s active, and which model each runs. Useful for both+“is everyone alive?” and “why is the Opus agent the cost outlier?”</li>+</ul>+<p>Add a full-text search across the board, tasks, and memory and you can answer ad-hoc questions (“who+mentioned the release?”) without grepping files by hand.</p>+<h2 id="observability-vs-debugging" tabindex="-1">Observability vs debugging <a class="anchor" href="#observability-vs-debugging" aria-hidden="true">#</a></h2>+<p>These are different jobs. <a href="/blog/debugging-multi-agent-systems/">Debugging a multi-agent system</a> is+<em>reactive</em> — something broke, you reconstruct why. Observability is <em>proactive</em> — a standing picture that+lets you catch the loop, the collision, or the cost spike <strong>before</strong> it becomes an incident. The activity+feed and usage meter are how you notice; the event log and transcripts are how you then dig in. You want+both, and the observability layer is what tells you when to switch from watching to debugging.</p>+<p>The quiet payoff: once you can <em>see</em> a fleet cheaply, you trust it to run unattended. Visibility is what+makes “leave the agents working” a calm decision instead of a leap of faith.</p>+<h2 id="faq" tabindex="-1">FAQ <a class="anchor" href="#faq" aria-hidden="true">#</a></h2>+<p><strong>Do I need a metrics stack like Prometheus/Grafana?</strong> Not to start. A fleet of dozens of local agents is+well served by reading the event log and transcripts directly and rendering them. Reach for a heavy+metrics stack when you’re distributed across machines and need retention and alerting at scale.</p>+<p><strong>What’s the single highest-value signal?</strong> Per-agent cost. It catches runaway loops, surfaces the+expensive outlier, and is trivial to read from transcripts. If you add one thing, add that.</p>+<p><strong>How live is “live”?</strong> The activity feed is event-driven (pushed by hooks as things happen); the usage+meter polls transcripts every several seconds. Plenty fast for agent turns measured in seconds to minutes.</p>+<hr>+<p>Munder Difflin ships this as the orchestrator’s control surface — a live activity feed, per-agent token+and cost meters, a task board, and a memory graph for a whole+<a href="https://munderdiffl.in/#how">hive of Claude Code agents</a>, all local.+<a href="https://munderdiffl.in/#install">Download Munder Difflin</a> to watch your fleet at a glance; it’s free and+open source.</p>++++ <section class="faq" aria-label="Frequently asked questions">+ <h2 id="faq">FAQ</h2>++ <div class="qa">+ <p class="q">How is observability for AI agents different from normal app observability?</p>+ <p class="a">App observability watches deterministic services — latency, error rates, throughput. Agent observability watches non-deterministic actors that make their own choices: which tools they call, what they decide, what they spend, what they remember. You're not just asking 'is it up?' but 'what is it doing and why, and is that what I wanted?' That needs a feed of intent and actions, not just health metrics.</p>+ </div>++ <div class="qa">+ <p class="q">Why track token cost per agent?</p>+ <p class="a">Because autonomous agents spend money without asking, and a runaway loop or an over-eager agent shows up first as a cost spike. Per-agent token and dollar telemetry turns 'the bill is high' into 'this agent is the reason' — fast enough to intervene. It's the cheapest early-warning signal an agent fleet has.</p>+ </div>++ <div class="qa">+ <p class="q">Where does the telemetry come from?</p>+ <p class="a">Two sources: lifecycle hooks stream what each agent is doing in real time, and the agents' own transcript files record exact token counts. Combine the live event stream with the on-disk usage and you can reconstruct both 'what happened' and 'what it cost' without instrumenting the model itself.</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/observability/">Observability</a><a class="tag" href="/blog/tags/multi-agent/">Multi-Agent</a><a class="tag" href="/blog/tags/claude-code/">Claude Code</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="#the-four-questions-a-fleet-dashboard-must-answer">The four questions a fleet dashboard must answer</a></li><li class="lvl-2"><a href="#a-live-activity-feed-from-the-event-log">A live activity feed from the event log</a></li><li class="lvl-2"><a href="#token-and-cost-telemetry-per-agent">Token and cost telemetry, per agent</a></li><li class="lvl-2"><a href="#state-at-a-glance-task-board-memory-roster">State at a glance: task board, memory, roster</a></li><li class="lvl-2"><a href="#observability-vs-debugging">Observability vs debugging</a></li><li class="lvl-2"><a href="#faq">FAQ</a></li>+ </ol>+ </aside>++ </div>++ <footer class="post-foot wrap"><div class="prevnext">+ <a class="pn prev" href="/blog/open-source-ai-tools-on-purpose/"><span class="k">← Older</span><span class="t">Building AI Dev Tools in the Open, On Purpose</span></a>+ <a class="pn next" href="/blog/long-running-agents-the-2026-shift/"><span class="k">Newer →</span><span class="t">Long-Running Agents: The 2026 Shift from Minutes to Hours</span></a>+ </div>+ <section class="related">+ <h2>Related in Internals</h2>+ <div class="post-grid">+ <article class="card">+ <a class="thumb t-internals" href="/blog/architecture-two-planes-one-renderer/" aria-hidden="true" tabindex="-1">+ <span>INTERNALS</span>+ </a>+ <div class="body">+ <div class="meta">+ <time datetime="2026-06-04">Jun 4, 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>+ <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>+ </div>+ </div>+</article>+<article class="card">+ <a class="thumb t-internals" href="/blog/file-based-coordination-vs-message-queues/" aria-hidden="true" tabindex="-1">+ <span>INTERNALS</span>+ </a>+ <div class="body">+ <div class="meta">+ <time datetime="2026-06-04">Jun 4, 2026</time>+ <span class="dot" aria-hidden="true"></span>+ <span>4 min</span>+ </div>+ <h3><a href="/blog/file-based-coordination-vs-message-queues/">File-Based Coordination vs Message Queues for AI Agents</a></h3>+ <p class="dek">Why a local agent hive coordinates through plain files, not Redis or RabbitMQ: the zero-ops wins, the real tradeoffs, and where files hit a ceiling.</p>+ <div class="foot">+ <span class="tag kind">Internals</span>+ <a class="more" href="/blog/file-based-coordination-vs-message-queues/" aria-label="Read: File-Based Coordination vs Message Queues for AI Agents">Read →</a>+ </div>+ </div>+</article>+<article class="card">+ <a class="thumb t-internals" href="/blog/recovering-from-agent-failures/" aria-hidden="true" tabindex="-1">+ <span>INTERNALS</span>+ </a>+ <div class="body">+ <div class="meta">+ <time datetime="2026-06-04">Jun 4, 2026</time>+ <span class="dot" aria-hidden="true"></span>+ <span>6 min</span>+ </div>+ <h3><a href="/blog/recovering-from-agent-failures/">Recovering From Agent Failures: Resilience Patterns for a Hive</a></h3>+ <p class="dek">How multi-agent systems survive partial failure: retry with stale-lock recovery, poison-message quarantine, hop-cap circuit breaking, idempotent handling.</p>+ <div class="foot">+ <span class="tag kind">Internals</span>+ <a class="more" href="/blog/recovering-from-agent-failures/" aria-label="Read: Recovering From Agent Failures: Resilience Patterns for a Hive">Read →</a>+ </div>+ </div>+</article>++ </div>+ </section>++ </footer>+</article>++</main>+<footer>+ <div class="wrap">+ <div class="foot-top">+ <a class="foot-brand brand" href="/blog/">+ <span class="brand-mark">MD</span>+ <span class="brand-word">MUNDER DIFFLIN<span class="sep">/</span><span class="blog">BLOG</span></span>+ </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/open-source-ai-tools-on-purpose/index.html b/docs/blog/open-source-ai-tools-on-purpose/index.htmlindex 2b071d63..87f66d60 100644--- a/docs/blog/open-source-ai-tools-on-purpose/index.html+++ b/docs/blog/open-source-ai-tools-on-purpose/index.html@@ -261,7 +261,7 @@ autonomous. <a href="https://munderdiffl.in/#install">Download Munder Difflin</a<footer class="post-foot wrap"><div class="prevnext"><a class="pn prev" href="/blog/overnight-ai-coding-realistic-expectations/"><span class="k">← Older</span><span class="t">Overnight AI Coding: What's Realistic (and What's Not)</span></a>- <a class="pn next" href="/blog/long-running-agents-the-2026-shift/"><span class="k">Newer →</span><span class="t">Long-Running Agents: The 2026 Shift from Minutes to Hours</span></a>+ <a class="pn next" href="/blog/observability-for-agent-fleets/"><span class="k">Newer →</span><span class="t">Observability for Agent Fleets: Seeing What Your Agents Do</span></a></div><section class="related"><h2>Related in Concepts</h2>diff --git a/docs/blog/recovering-from-agent-failures/index.html b/docs/blog/recovering-from-agent-failures/index.htmlindex e4c5b200..ea3b3845 100644--- a/docs/blog/recovering-from-agent-failures/index.html+++ b/docs/blog/recovering-from-agent-failures/index.html@@ -317,20 +317,20 @@ there to read.</p></div></article><article class="card">- <a class="thumb t-internals" href="/blog/the-hook-shim-pattern/" aria-hidden="true" tabindex="-1">+ <a class="thumb t-internals" href="/blog/observability-for-agent-fleets/" aria-hidden="true" tabindex="-1"><span>INTERNALS</span></a><div class="body"><div class="meta"><time datetime="2026-06-04">Jun 4, 2026</time><span class="dot" aria-hidden="true"></span>- <span>6 min</span>+ <span>4 min</span></div>- <h3><a href="/blog/the-hook-shim-pattern/">The Hook Shim Pattern: Wiring Agent Hooks to a Live Process</a></h3>- <p class="dek">How a tiny shim bridges Claude Code's lifecycle hooks to one live process over a Unix socket, turning per-event hooks into a telemetry and control channel.</p>+ <h3><a href="/blog/observability-for-agent-fleets/">Observability for Agent Fleets: Seeing What Your Agents Do</a></h3>+ <p class="dek">Agent fleet observability: the four questions your dashboard must answer about who's working, what they're doing, what it costs, and what they know.</p><div class="foot"><span class="tag kind">Internals</span>- <a class="more" href="/blog/the-hook-shim-pattern/" aria-label="Read: The Hook Shim Pattern: Wiring Agent Hooks to a Live Process">Read →</a>+ <a class="more" href="/blog/observability-for-agent-fleets/" aria-label="Read: Observability for Agent Fleets: Seeing What Your Agents Do">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 f428fb6d..fc779cbd 100644--- a/docs/blog/rendering-many-live-terminals-performance/index.html+++ b/docs/blog/rendering-many-live-terminals-performance/index.html@@ -320,20 +320,20 @@ to run many real terminals without melting your CPU; it’s free and open source</div></article><article class="card">- <a class="thumb t-internals" href="/blog/recovering-from-agent-failures/" aria-hidden="true" tabindex="-1">+ <a class="thumb t-internals" href="/blog/observability-for-agent-fleets/" aria-hidden="true" tabindex="-1"><span>INTERNALS</span></a><div class="body"><div class="meta"><time datetime="2026-06-04">Jun 4, 2026</time><span class="dot" aria-hidden="true"></span>- <span>6 min</span>+ <span>4 min</span></div>- <h3><a href="/blog/recovering-from-agent-failures/">Recovering From Agent Failures: Resilience Patterns for a Hive</a></h3>- <p class="dek">How multi-agent systems survive partial failure: retry with stale-lock recovery, poison-message quarantine, hop-cap circuit breaking, idempotent handling.</p>+ <h3><a href="/blog/observability-for-agent-fleets/">Observability for Agent Fleets: Seeing What Your Agents Do</a></h3>+ <p class="dek">Agent fleet observability: the four questions your dashboard must answer about who's working, what they're doing, what it costs, and what they know.</p><div class="foot"><span class="tag kind">Internals</span>- <a class="more" href="/blog/recovering-from-agent-failures/" aria-label="Read: Recovering From Agent Failures: Resilience Patterns for a Hive">Read →</a>+ <a class="more" href="/blog/observability-for-agent-fleets/" aria-label="Read: Observability for Agent Fleets: Seeing What Your Agents Do">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 ac3babf8..f0709d5e 100644--- a/docs/blog/single-committer-git-pattern/index.html+++ b/docs/blog/single-committer-git-pattern/index.html@@ -327,20 +327,20 @@ never corrupt their own state; it’s free and open source.</p></div></article><article class="card">- <a class="thumb t-internals" href="/blog/recovering-from-agent-failures/" aria-hidden="true" tabindex="-1">+ <a class="thumb t-internals" href="/blog/observability-for-agent-fleets/" aria-hidden="true" tabindex="-1"><span>INTERNALS</span></a><div class="body"><div class="meta"><time datetime="2026-06-04">Jun 4, 2026</time><span class="dot" aria-hidden="true"></span>- <span>6 min</span>+ <span>4 min</span></div>- <h3><a href="/blog/recovering-from-agent-failures/">Recovering From Agent Failures: Resilience Patterns for a Hive</a></h3>- <p class="dek">How multi-agent systems survive partial failure: retry with stale-lock recovery, poison-message quarantine, hop-cap circuit breaking, idempotent handling.</p>+ <h3><a href="/blog/observability-for-agent-fleets/">Observability for Agent Fleets: Seeing What Your Agents Do</a></h3>+ <p class="dek">Agent fleet observability: the four questions your dashboard must answer about who's working, what they're doing, what it costs, and what they know.</p><div class="foot"><span class="tag kind">Internals</span>- <a class="more" href="/blog/recovering-from-agent-failures/" aria-label="Read: Recovering From Agent Failures: Resilience Patterns for a Hive">Read →</a>+ <a class="more" href="/blog/observability-for-agent-fleets/" aria-label="Read: Observability for Agent Fleets: Seeing What Your Agents Do">Read →</a></div></div></article>diff --git a/docs/blog/tags/claude-code/index.html b/docs/blog/tags/claude-code/index.htmlindex 1eb9c973..425f11bc 100644--- a/docs/blog/tags/claude-code/index.html+++ b/docs/blog/tags/claude-code/index.html@@ -58,7 +58,7 @@<header class="page-head wrap"><p class="eyebrow">Tag</p><h1>#Claude Code</h1>- <p class="lead">35 posts tagged <strong>Claude Code</strong>.</p>+ <p class="lead">36 posts tagged <strong>Claude Code</strong>.</p></header><section class="wrap"><div class="post-grid">@@ -296,6 +296,24 @@</div></div></article>+<article class="card">+ <a class="thumb t-internals" href="/blog/observability-for-agent-fleets/" aria-hidden="true" tabindex="-1">+ <span>INTERNALS</span>+ </a>+ <div class="body">+ <div class="meta">+ <time datetime="2026-06-04">Jun 4, 2026</time>+ <span class="dot" aria-hidden="true"></span>+ <span>4 min</span>+ </div>+ <h3><a href="/blog/observability-for-agent-fleets/">Observability for Agent Fleets: Seeing What Your Agents Do</a></h3>+ <p class="dek">Agent fleet observability: the four questions your dashboard must answer about who's working, what they're doing, what it costs, and what they know.</p>+ <div class="foot">+ <span class="tag kind">Internals</span>+ <a class="more" href="/blog/observability-for-agent-fleets/" aria-label="Read: Observability for Agent Fleets: Seeing What Your Agents Do">Read →</a>+ </div>+ </div>+</article><article class="card"><a class="thumb t-guides" href="/blog/security-for-ai-coding-agents/" aria-hidden="true" tabindex="-1"><span>GUIDES</span>diff --git a/docs/blog/tags/internals/index.html b/docs/blog/tags/internals/index.htmlindex 3a831e0c..c81386fe 100644--- a/docs/blog/tags/internals/index.html+++ b/docs/blog/tags/internals/index.html@@ -58,7 +58,7 @@<header class="page-head wrap"><p class="eyebrow">Tag</p><h1>#Internals</h1>- <p class="lead">18 posts tagged <strong>Internals</strong>.</p>+ <p class="lead">19 posts tagged <strong>Internals</strong>.</p></header><section class="wrap"><div class="post-grid">@@ -170,6 +170,24 @@</div></div></article>+<article class="card">+ <a class="thumb t-internals" href="/blog/observability-for-agent-fleets/" aria-hidden="true" tabindex="-1">+ <span>INTERNALS</span>+ </a>+ <div class="body">+ <div class="meta">+ <time datetime="2026-06-04">Jun 4, 2026</time>+ <span class="dot" aria-hidden="true"></span>+ <span>4 min</span>+ </div>+ <h3><a href="/blog/observability-for-agent-fleets/">Observability for Agent Fleets: Seeing What Your Agents Do</a></h3>+ <p class="dek">Agent fleet observability: the four questions your dashboard must answer about who's working, what they're doing, what it costs, and what they know.</p>+ <div class="foot">+ <span class="tag kind">Internals</span>+ <a class="more" href="/blog/observability-for-agent-fleets/" aria-label="Read: Observability for Agent Fleets: Seeing What Your Agents Do">Read →</a>+ </div>+ </div>+</article><article class="card"><a class="thumb t-internals" href="/blog/recovering-from-agent-failures/" aria-hidden="true" tabindex="-1"><span>INTERNALS</span>diff --git a/docs/blog/tags/multi-agent/index.html b/docs/blog/tags/multi-agent/index.htmlindex a1ab4fd3..7c00bb4a 100644--- a/docs/blog/tags/multi-agent/index.html+++ b/docs/blog/tags/multi-agent/index.html@@ -58,7 +58,7 @@<header class="page-head wrap"><p class="eyebrow">Tag</p><h1>#Multi-Agent</h1>- <p class="lead">48 posts tagged <strong>Multi-Agent</strong>.</p>+ <p class="lead">49 posts tagged <strong>Multi-Agent</strong>.</p></header><section class="wrap"><div class="post-grid">@@ -350,6 +350,24 @@</div></div></article>+<article class="card">+ <a class="thumb t-internals" href="/blog/observability-for-agent-fleets/" aria-hidden="true" tabindex="-1">+ <span>INTERNALS</span>+ </a>+ <div class="body">+ <div class="meta">+ <time datetime="2026-06-04">Jun 4, 2026</time>+ <span class="dot" aria-hidden="true"></span>+ <span>4 min</span>+ </div>+ <h3><a href="/blog/observability-for-agent-fleets/">Observability for Agent Fleets: Seeing What Your Agents Do</a></h3>+ <p class="dek">Agent fleet observability: the four questions your dashboard must answer about who's working, what they're doing, what it costs, and what they know.</p>+ <div class="foot">+ <span class="tag kind">Internals</span>+ <a class="more" href="/blog/observability-for-agent-fleets/" aria-label="Read: Observability for Agent Fleets: Seeing What Your Agents Do">Read →</a>+ </div>+ </div>+</article><article class="card"><a class="thumb t-concepts" href="/blog/open-source-ai-tools-on-purpose/" aria-hidden="true" tabindex="-1"><span>CONCEPTS</span>diff --git a/docs/blog/tags/observability/index.html b/docs/blog/tags/observability/index.htmlindex 07f4a0ab..a156000e 100644--- a/docs/blog/tags/observability/index.html+++ b/docs/blog/tags/observability/index.html@@ -58,7 +58,7 @@<header class="page-head wrap"><p class="eyebrow">Tag</p><h1>#Observability</h1>- <p class="lead">3 posts tagged <strong>Observability</strong>.</p>+ <p class="lead">4 posts tagged <strong>Observability</strong>.</p></header><section class="wrap"><div class="post-grid">@@ -80,6 +80,24 @@</div></div></article>+<article class="card">+ <a class="thumb t-internals" href="/blog/observability-for-agent-fleets/" aria-hidden="true" tabindex="-1">+ <span>INTERNALS</span>+ </a>+ <div class="body">+ <div class="meta">+ <time datetime="2026-06-04">Jun 4, 2026</time>+ <span class="dot" aria-hidden="true"></span>+ <span>4 min</span>+ </div>+ <h3><a href="/blog/observability-for-agent-fleets/">Observability for Agent Fleets: Seeing What Your Agents Do</a></h3>+ <p class="dek">Agent fleet observability: the four questions your dashboard must answer about who's working, what they're doing, what it costs, and what they know.</p>+ <div class="foot">+ <span class="tag kind">Internals</span>+ <a class="more" href="/blog/observability-for-agent-fleets/" aria-label="Read: Observability for Agent Fleets: Seeing What Your Agents Do">Read →</a>+ </div>+ </div>+</article><article class="card"><a class="thumb t-internals" href="/blog/visualizing-ai-agents-pixijs/" aria-hidden="true" tabindex="-1"><span>INTERNALS</span>diff --git a/docs/blog/the-hook-shim-pattern/index.html b/docs/blog/the-hook-shim-pattern/index.htmlindex f073fc7f..5f8cd3c6 100644--- a/docs/blog/the-hook-shim-pattern/index.html+++ b/docs/blog/the-hook-shim-pattern/index.html@@ -316,20 +316,20 @@ at the mercy of the bridge.</div></article><article class="card">- <a class="thumb t-internals" href="/blog/recovering-from-agent-failures/" aria-hidden="true" tabindex="-1">+ <a class="thumb t-internals" href="/blog/observability-for-agent-fleets/" aria-hidden="true" tabindex="-1"><span>INTERNALS</span></a><div class="body"><div class="meta"><time datetime="2026-06-04">Jun 4, 2026</time><span class="dot" aria-hidden="true"></span>- <span>6 min</span>+ <span>4 min</span></div>- <h3><a href="/blog/recovering-from-agent-failures/">Recovering From Agent Failures: Resilience Patterns for a Hive</a></h3>- <p class="dek">How multi-agent systems survive partial failure: retry with stale-lock recovery, poison-message quarantine, hop-cap circuit breaking, idempotent handling.</p>+ <h3><a href="/blog/observability-for-agent-fleets/">Observability for Agent Fleets: Seeing What Your Agents Do</a></h3>+ <p class="dek">Agent fleet observability: the four questions your dashboard must answer about who's working, what they're doing, what it costs, and what they know.</p><div class="foot"><span class="tag kind">Internals</span>- <a class="more" href="/blog/recovering-from-agent-failures/" aria-label="Read: Recovering From Agent Failures: Resilience Patterns for a Hive">Read →</a>+ <a class="more" href="/blog/observability-for-agent-fleets/" aria-label="Read: Observability for Agent Fleets: Seeing What Your Agents Do">Read →</a></div></div></article>diff --git a/docs/blog/topics/comparisons/index.html b/docs/blog/topics/comparisons/index.htmlindex d8049c8a..2afa33e5 100644--- a/docs/blog/topics/comparisons/index.html+++ b/docs/blog/topics/comparisons/index.html@@ -70,7 +70,7 @@<a class="chip" href="/blog/topics/guides/">guides<span class="ct">19</span></a>- <a class="chip" href="/blog/topics/internals/">internals<span class="ct">13</span></a>+ <a class="chip" href="/blog/topics/internals/">internals<span class="ct">14</span></a><a class="chip" href="/blog/topics/concepts/">concepts<span class="ct">11</span></a>diff --git a/docs/blog/topics/concepts/index.html b/docs/blog/topics/concepts/index.htmlindex 4ed6b801..5234a4da 100644--- a/docs/blog/topics/concepts/index.html+++ b/docs/blog/topics/concepts/index.html@@ -70,7 +70,7 @@<a class="chip" href="/blog/topics/guides/">guides<span class="ct">19</span></a>- <a class="chip" href="/blog/topics/internals/">internals<span class="ct">13</span></a>+ <a class="chip" href="/blog/topics/internals/">internals<span class="ct">14</span></a><a class="chip" href="/blog/topics/concepts/" aria-current="page">concepts<span class="ct">11</span></a>diff --git a/docs/blog/topics/guides/index.html b/docs/blog/topics/guides/index.htmlindex 5473ea93..0549895d 100644--- a/docs/blog/topics/guides/index.html+++ b/docs/blog/topics/guides/index.html@@ -70,7 +70,7 @@<a class="chip" href="/blog/topics/guides/" aria-current="page">guides<span class="ct">19</span></a>- <a class="chip" href="/blog/topics/internals/">internals<span class="ct">13</span></a>+ <a class="chip" href="/blog/topics/internals/">internals<span class="ct">14</span></a><a class="chip" href="/blog/topics/concepts/">concepts<span class="ct">11</span></a>diff --git a/docs/blog/topics/index.html b/docs/blog/topics/index.htmlindex f8d1b094..3b3fdad3 100644--- a/docs/blog/topics/index.html+++ b/docs/blog/topics/index.html@@ -79,7 +79,7 @@<span class="thumb t-internals" aria-hidden="true">INTERNALS</span><div class="body"><h3 style="color:var(--ink)">internals</h3>- <p class="dek">13 posts.</p>+ <p class="dek">14 posts.</p><div class="foot"><span class="more">View topic →</span></div></div></a>@@ -144,11 +144,11 @@<div class="filters" style="padding-top:36px"><span class="eyebrow" style="align-self:center">Tags</span>- <a class="chip" href="/blog/tags/multi-agent/">Multi-Agent<span class="ct">48</span></a>+ <a class="chip" href="/blog/tags/multi-agent/">Multi-Agent<span class="ct">49</span></a>- <a class="chip" href="/blog/tags/claude-code/">Claude Code<span class="ct">35</span></a>+ <a class="chip" href="/blog/tags/claude-code/">Claude Code<span class="ct">36</span></a>- <a class="chip" href="/blog/tags/internals/">Internals<span class="ct">18</span></a>+ <a class="chip" href="/blog/tags/internals/">Internals<span class="ct">19</span></a><a class="chip" href="/blog/tags/orchestration/">Orchestration<span class="ct">12</span></a>@@ -170,6 +170,8 @@<a class="chip" href="/blog/tags/autonomous/">Autonomous<span class="ct">5</span></a>+ <a class="chip" href="/blog/tags/observability/">Observability<span class="ct">4</span></a>+<a class="chip" href="/blog/tags/use-cases/">Use Cases<span class="ct">4</span></a><a class="chip" href="/blog/tags/local-first/">Local-First<span class="ct">4</span></a>@@ -178,8 +180,6 @@<a class="chip" href="/blog/tags/workflow/">Workflow<span class="ct">3</span></a>- <a class="chip" href="/blog/tags/observability/">Observability<span class="ct">3</span></a>-<a class="chip" href="/blog/tags/human-in-the-loop/">Human-in-the-Loop<span class="ct">3</span></a><a class="chip" href="/blog/tags/guardrails/">Guardrails<span class="ct">3</span></a>diff --git a/docs/blog/topics/internals/index.html b/docs/blog/topics/internals/index.htmlindex a269edad..6e13c82c 100644--- a/docs/blog/topics/internals/index.html+++ b/docs/blog/topics/internals/index.html@@ -63,14 +63,14 @@</nav><p class="eyebrow">Topic</p><h1>internals</h1>- <p class="lead">13 posts in this cluster.</p>+ <p class="lead">14 posts in this cluster.</p><div class="filters" role="navigation" aria-label="Topics"><a class="chip" href="/blog/">All</a><a class="chip" href="/blog/topics/guides/">guides<span class="ct">19</span></a>- <a class="chip" href="/blog/topics/internals/" aria-current="page">internals<span class="ct">13</span></a>+ <a class="chip" href="/blog/topics/internals/" aria-current="page">internals<span class="ct">14</span></a><a class="chip" href="/blog/topics/concepts/">concepts<span class="ct">11</span></a>@@ -125,6 +125,24 @@</div></div></article>+<article class="card">+ <a class="thumb t-internals" href="/blog/observability-for-agent-fleets/" aria-hidden="true" tabindex="-1">+ <span>INTERNALS</span>+ </a>+ <div class="body">+ <div class="meta">+ <time datetime="2026-06-04">Jun 4, 2026</time>+ <span class="dot" aria-hidden="true"></span>+ <span>4 min</span>+ </div>+ <h3><a href="/blog/observability-for-agent-fleets/">Observability for Agent Fleets: Seeing What Your Agents Do</a></h3>+ <p class="dek">Agent fleet observability: the four questions your dashboard must answer about who's working, what they're doing, what it costs, and what they know.</p>+ <div class="foot">+ <span class="tag kind">Internals</span>+ <a class="more" href="/blog/observability-for-agent-fleets/" aria-label="Read: Observability for Agent Fleets: Seeing What Your Agents Do">Read →</a>+ </div>+ </div>+</article><article class="card"><a class="thumb t-internals" href="/blog/recovering-from-agent-failures/" aria-hidden="true" tabindex="-1"><span>INTERNALS</span>diff --git a/docs/blog/topics/memory/index.html b/docs/blog/topics/memory/index.htmlindex f3dc46b6..8c9675aa 100644--- a/docs/blog/topics/memory/index.html+++ b/docs/blog/topics/memory/index.html@@ -70,7 +70,7 @@<a class="chip" href="/blog/topics/guides/">guides<span class="ct">19</span></a>- <a class="chip" href="/blog/topics/internals/">internals<span class="ct">13</span></a>+ <a class="chip" href="/blog/topics/internals/">internals<span class="ct">14</span></a><a class="chip" href="/blog/topics/concepts/">concepts<span class="ct">11</span></a>diff --git a/docs/blog/topics/orchestration/index.html b/docs/blog/topics/orchestration/index.htmlindex 2ca719c1..a34ad4b0 100644--- a/docs/blog/topics/orchestration/index.html+++ b/docs/blog/topics/orchestration/index.html@@ -70,7 +70,7 @@<a class="chip" href="/blog/topics/guides/">guides<span class="ct">19</span></a>- <a class="chip" href="/blog/topics/internals/">internals<span class="ct">13</span></a>+ <a class="chip" href="/blog/topics/internals/">internals<span class="ct">14</span></a><a class="chip" href="/blog/topics/concepts/">concepts<span class="ct">11</span></a>diff --git a/docs/blog/topics/story/index.html b/docs/blog/topics/story/index.htmlindex 36c40ab9..28bf8478 100644--- a/docs/blog/topics/story/index.html+++ b/docs/blog/topics/story/index.html@@ -70,7 +70,7 @@<a class="chip" href="/blog/topics/guides/">guides<span class="ct">19</span></a>- <a class="chip" href="/blog/topics/internals/">internals<span class="ct">13</span></a>+ <a class="chip" href="/blog/topics/internals/">internals<span class="ct">14</span></a><a class="chip" href="/blog/topics/concepts/">concepts<span class="ct">11</span></a>diff --git a/docs/blog/topics/use-cases/index.html b/docs/blog/topics/use-cases/index.htmlindex b4cba6ff..2f3ac498 100644--- a/docs/blog/topics/use-cases/index.html+++ b/docs/blog/topics/use-cases/index.html@@ -70,7 +70,7 @@<a class="chip" href="/blog/topics/guides/">guides<span class="ct">19</span></a>- <a class="chip" href="/blog/topics/internals/">internals<span class="ct">13</span></a>+ <a class="chip" href="/blog/topics/internals/">internals<span class="ct">14</span></a><a class="chip" href="/blog/topics/concepts/">concepts<span class="ct">11</span></a>diff --git a/docs/blog/visualizing-ai-agents-pixijs/index.html b/docs/blog/visualizing-ai-agents-pixijs/index.htmlindex 6c7f82f4..7c076b08 100644--- a/docs/blog/visualizing-ai-agents-pixijs/index.html+++ b/docs/blog/visualizing-ai-agents-pixijs/index.html@@ -317,20 +317,20 @@ to see your agents at work; it’s free and open source.</p></div></article><article class="card">- <a class="thumb t-internals" href="/blog/recovering-from-agent-failures/" aria-hidden="true" tabindex="-1">+ <a class="thumb t-internals" href="/blog/observability-for-agent-fleets/" aria-hidden="true" tabindex="-1"><span>INTERNALS</span></a><div class="body"><div class="meta"><time datetime="2026-06-04">Jun 4, 2026</time><span class="dot" aria-hidden="true"></span>- <span>6 min</span>+ <span>4 min</span></div>- <h3><a href="/blog/recovering-from-agent-failures/">Recovering From Agent Failures: Resilience Patterns for a Hive</a></h3>- <p class="dek">How multi-agent systems survive partial failure: retry with stale-lock recovery, poison-message quarantine, hop-cap circuit breaking, idempotent handling.</p>+ <h3><a href="/blog/observability-for-agent-fleets/">Observability for Agent Fleets: Seeing What Your Agents Do</a></h3>+ <p class="dek">Agent fleet observability: the four questions your dashboard must answer about who's working, what they're doing, what it costs, and what they know.</p><div class="foot"><span class="tag kind">Internals</span>- <a class="more" href="/blog/recovering-from-agent-failures/" aria-label="Read: Recovering From Agent Failures: Resilience Patterns for a Hive">Read →</a>+ <a class="more" href="/blog/observability-for-agent-fleets/" aria-label="Read: Observability for Agent Fleets: Seeing What Your Agents Do">Read →</a></div></div></article>diff --git a/docs/sitemap.xml b/docs/sitemap.xmlindex 37b4c891..049f017b 100644--- a/docs/sitemap.xml+++ b/docs/sitemap.xml@@ -161,6 +161,12 @@<changefreq>monthly</changefreq><priority>0.8</priority></url>+ <url>+ <loc>https://munderdiffl.in/blog/observability-for-agent-fleets/</loc>+ <lastmod>2026-06-04</lastmod>+ <changefreq>monthly</changefreq>+ <priority>0.8</priority>+ </url><url><loc>https://munderdiffl.in/blog/open-source-ai-tools-on-purpose/</loc><lastmod>2026-06-04</lastmod>@@ -464,11 +470,11 @@<url><loc>https://munderdiffl.in/blog/tags/automation/</loc><changefreq>weekly</changefreq><priority>0.3</priority></url><url><loc>https://munderdiffl.in/blog/tags/mempalace/</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/observability/</loc><changefreq>weekly</changefreq><priority>0.3</priority></url><url><loc>https://munderdiffl.in/blog/tags/use-cases/</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/security/</loc><changefreq>weekly</changefreq><priority>0.3</priority></url><url><loc>https://munderdiffl.in/blog/tags/workflow/</loc><changefreq>weekly</changefreq><priority>0.3</priority></url>- <url><loc>https://munderdiffl.in/blog/tags/observability/</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><url><loc>https://munderdiffl.in/blog/tags/guardrails/</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>