<title>Retiring the Supervisor: Pi's Flow-Native Brain — Tinqs Blog</title>
<metaname="description"content="We deleted 1,050 lines of hardcoded supervisor logic and replaced it with oracle-backed pi-flows. The verify_build oracle now powers a gate-based pipeline that agents compose dynamically.">
"headline":"Retiring the Supervisor: Pi's Flow-Native Brain",
"datePublished":"2026-06-03",
"author":{
"@type":"Person",
"name":"Ozan Bozkurt"
},
"publisher":{
"@type":"Organization",
"name":"Tinqs Limited",
"url":"https://www.tinqs.com"
},
"description":"We deleted 1,050 lines of hardcoded supervisor logic and replaced it with oracle-backed pi-flows. The verify_build oracle now powers a gate-based pipeline that agents compose dynamically."
<ahref="/blog/"class="post__back">← All Posts</a>
<spanclass="post__date">3 June 2026</span>
<h1class="post__title">Retiring the Supervisor: Pi's Flow-Native Brain</h1>
<pclass="post__lead">The supervisor was 1,050 lines of TypeScript spread across 15 files — a hardcoded orchestration loop that ran contract-gated, verify-heavy sessions over isolated Pi processes. Today we deleted it. What replaced it is simpler, more flexible, and already passing real builds.</p>
<divclass="post__body">
<h2>What the Supervisor Did</h2>
<p>The <code>.pi/supervisor/</code> directory was the orchestration brain Pi left to us. For every task, it ran a fixed loop:</p>
<p>1. <strong>Contract gate</strong> — skip-to-human if "done" wasn't programmatically verifiable</p>
<p>2. <strong>TDAID phase A</strong> — a test-writer agent writes RED tests, never implementation</p>
<p>3. <strong>TDAID phase B</strong> — a code-writer agent makes them green; on failure, a Reflexion follow-up retries (capped)</p>
<p>4. <strong>Verification gate</strong> — run the build, check tests, pass or fail with a report</p>
<p>It worked. It caught broken builds before they hit CI. It enforced the discipline of "define done before you start." But it had a structural problem: the loop was <strong>hardcoded</strong>. Every decision tree, every gate, every retry policy was baked into TypeScript. To change the workflow, you changed code. To add a new gate — vision QA, linting, asset validation — you added more code to the same monolithic loop.</p>
<p>The supervisor was doing what <code>pi-flows</code> was designed to do, but from the wrong side of the architecture. Flows composes agents, gates, and decision points into pipelines. The supervisor reimplemented that logic in a single file. It was fighting the framework.</p>
<h2>What Replaced It</h2>
<p>The verify-heavy brain now runs <strong>as a pi-flows flow</strong> — a pipeline of oracle-backed gates orchestrated by the flow engine, visualized in FlowDashboard, and composable by agents themselves.</p>
<p>The core pieces:</p>
<ul>
<li><strong>Oracle-backed gates.</strong> The <code>verify_build</code> tool (<code>.pi/extensions/tinqs-verify.ts</code>) is the canonical gate. It compiles the game and sim, runs tests, and returns a structured PASS/FAIL verdict with file:line errors. Agents route through it; the gate decides whether to proceed.</li>
<li><strong>Agent-loop-decision Reflexion.</strong> Instead of a fixed two-phase TDAID loop, agents self-reflect on build failures. The flow engine gives them the failure report; they decide whether to fix and retry or escalate.</li>
<li><strong>Role-split agents.</strong> G1 build, G2 tests, G3 behaviour (drives the live game), G4 feel (measured game-feel) and G5 visual (animation) are separate sub-agents, each with its own toolset and context, composed by the flow.</li>
<pathd="M820,150 C 908,96 716,50 556,61"fill="none"stroke="#f59e0b"stroke-width="1.8"stroke-dasharray="6 5"marker-end="url(#ahA)"/>
<textx="694"y="96"fill="#f59e0b"font-size="12.5">Reflexion · fix & retry ≤ 3</text>
</svg>
<figcaptionstyle="color:#9aa7b4;font-size:0.85rem;margin-top:8px;">A real in-game failure loops back to <em>implement</em> with the gate evidence (bounded to three tries); anything green — or skipped because no live instance is running — falls through to a single honest judge.</figcaption>
</figure>
<p>It started as three gates — build, test, vision. Gates are cheap to add, so it grew: a feature now also passes a live-game <strong>behaviour</strong> probe and a measured <strong>feel</strong> check before the judge signs off. Critically, the flow is not fixed. Agents can add gates, reorder steps, or branch on conditions. The flow engine handles orchestration; the agents handle decisions.</p>
<figcaptionstyle="color:#9aa7b4;font-size:0.85rem;margin-top:8px;">The whole orchestration loop was deleted; only the build oracle survived — and it became the gate that powers the flow.</figcaption>
<p>None of this was bad code. It was just the wrong layer. Flows gives us all of this — orchestration, state, gates, retry policy, event routing — as a framework primitive. We were maintaining a parallel implementation of something the framework already provided.</p>
<p>The durable asset we kept: <code>verify_build</code>, the build oracle. It's now reused as the gate tool that powers the flow pipeline.</p>
<h2>The Bug That Took a Day to Find</h2>
<p>Moving to flows exposed a subtle problem. Flow sub-agents run in their <strong>own extension stack</strong> — the main session's extensions don't reach them. The build-verifier and test-runner agents declared <code>verify_build</code> in their frontmatter, but the tool was never actually in their toolset.</p>
<p>The symptom was confusing: the agents would report "oracle not available" and route to fail/report, silently skipping the test gate entirely. The build would pass, tests would never run, and the pipeline would report success. A false green.</p>
<p>The fix was a single pattern: emit <code>flow:register-tool</code> with the full tool definition at extension activation, and re-announce on <code>flow:rediscover</code>. The flow engine collects these into <code>getExtensionTools()</code> and hands them to every sub-agent that declares the tool. Three lines of orchestration, a day of debugging.</p>
<p>Verified live: <code>game-check</code> now routes <code>context → build → build-gate(pass) → tests → tests-gate(pass) → vision</code>. Every gate fires. No false greens.</p>
<h2>Why This Architecture Wins</h2>
<p><strong>Composability.</strong> Agents can add gates without touching framework code. Want a linting gate? Add a sub-agent with a linter tool. Want a security scan? Same pattern. The flow engine handles routing; you just declare the gate.</p>
<p><strong>Reusability.</strong> The <code>verify_build</code> oracle that powered the old supervisor now powers the flow gates. Same tool, same interface, different orchestration. No rewrite needed.</p>
<p><strong>Observability.</strong> FlowDashboard visualizes the entire pipeline. You can see which gates passed, which failed, and where the agent decided to retry. The old supervisor logged to stdout.</p>
<p><strong>Self-modification.</strong> Agents can read the flow graph, understand where they are in the pipeline, and decide what to do next. The supervisor's decision tree was opaque to the agents it was supervising. Flows makes the pipeline itself part of the agent's context.</p>
<trstyle="border-bottom:1px solid #1c2230;"><tdstyle="padding:9px 12px;color:#e6edf3;vertical-align:top;"><strongstyle="color:#f59e0b;">Sub-agents</strong></td><tdstyle="padding:9px 12px;color:#cdd7e2;vertical-align:top;">G1 build · G2 tests · G3 behaviour · G4 feel · G5 visual</td><tdstyle="padding:9px 12px;color:#9aa7b4;vertical-align:top;">Role-split, each with its own toolset</td></tr>
<trstyle="border-bottom:1px solid #1c2230;"><tdstyle="padding:9px 12px;color:#e6edf3;vertical-align:top;"><strongstyle="color:#f59e0b;">Decision</strong></td><tdstyle="padding:9px 12px;color:#cdd7e2;vertical-align:top;">Agent-loop Reflexion</td><tdstyle="padding:9px 12px;color:#9aa7b4;vertical-align:top;">Self-reflect on failures, retry (≤3) or escalate</td></tr>
<tr><tdstyle="padding:9px 12px;color:#e6edf3;vertical-align:top;"><strongstyle="color:#f59e0b;">Visualization</strong></td><tdstyle="padding:9px 12px;color:#cdd7e2;vertical-align:top;">FlowDashboard</td><tdstyle="padding:9px 12px;color:#9aa7b4;vertical-align:top;">Real-time pipeline state at localhost:33634</td></tr>
<p>The old supervisor was 1,050 lines of code that did one thing well: verify that agent output compiled and passed tests. The new flow-native brain does the same thing with less code, more flexibility, and a bug we'll never hit again. Sometimes the best commit is a deletion.</p>
<p><em>The flow-native brain runs on our <ahref="https://tinqs.com/tinqs/pi"style="color: var(–c-accent-l);">Pi fork</a> inside <ahref="https://tinqs.com"style="color: var(–c-accent-l);">Tinqs Studio</a>. The verify_build extension is ~300 lines of TypeScript, MIT licensed, and reusable in any Pi project.</em></p>
