Federate hyperloom-workload-optimizer from AMD-AGI/Hyperloom

.github/federation.json

@@ -1,5 +1,15 @@
 {
   "sources": [
+    {
+      "repo": "AMD-AGI/Hyperloom",
+      "license": "MIT",
+      "skills": [
+        {
+          "path": "examples/skills/hyperloom-workload-optimizer",
+          "as": "hyperloom-workload-optimizer"
+        }
+      ]
+    },
     {
       "repo": "AMD-AGI/TraceLens",
       "license": "MIT",

skills/hyperloom-workload-optimizer/evals/evals.json

@@ -6,36 +6,18 @@
       "prompt": "I want to optimize vLLM inference throughput on an MI300X. What are the first steps before launching Hyperloom?",
       "expected_behavior": [
         "Mention installing the Hyperloom wheel or checking for the hyperloom package",
-        "Mention workspace bootstrap such as hyperloom-setup or setup.md"
+        "Mention workspace bootstrap by running the hyperloom-setup skill"
       ],
       "unexpected_behavior": [
         "Start a plain vLLM docker serve as the primary answer without the optimization loop",
         "Launch the optimizer immediately after setup without collecting TP, concurrency, ISL, OSL, and precision or confirming a launch plan"
       ]
     },
-    {
-      "id": "hyperloom-launcher-gates",
-      "skill_should_trigger": true,
-      "note": "The two Iron Rules are the whole reason a launch is safe, so they are graded as prose and pinned to the literal script names. The prompt forbids running anything, so the gates are graded as described, not as observed on a real launch.",
-      "prompt": "What are Hyperloom's two launcher gates, in the order they run, and what does each one check? Answer in three or four sentences. Do not run anything.",
-      "expected_behavior": [
-        "Describe IR-2: install.sh must have been run and kernel-agent.env.sh sourced in the same shell that spawns the optimizer",
-        "Mention a GPU preflight check for stale serving processes or VRAM in use (IR-1)"
-      ],
-      "logs_contain": [
-        "install.sh",
-        "kernel-agent.env.sh"
-      ]
-    },
     {
       "id": "hyperloom-workload-intake",
       "skill_should_trigger": true,
-      "note": "Asks about each graded step, otherwise the answer's budget goes to listing workload values and the later steps drop out at random. Whether the answer names the values is deliberately not graded: a judge reads \"the values it needs\" as a request the prompt forbids and splits both ways on it, and logs_contain cannot stand in because those names are all over SKILL.md, which the run reads. Collecting them before a launch is graded by hyperloom-optimize-vllm-first-steps.",
-      "prompt": "The environment is already set up. Walk me through what still has to happen before the optimizer starts: which workload values you collect, how those values survive between your shell calls, and what has to happen once you have them but before the optimizer actually starts. Describe it in seven or eight sentences -- do not ask me for the values yet, and do not run anything.",
-      "expected_behavior": [
-        "Say it will present a launch plan and get user confirmation before launching the optimizer",
-        "Explain that confirmed workload values are persisted (e.g. to a workload.env file) and sourced at launch, since agent shells do not keep exports between calls"
-      ]
+      "note": "Trigger only. Every judged expectation tried here has graded both ways over byte-identical inputs, because the prompt forbids running anything and the judge then reads a described launch plan as a plan never presented. That the plan is confirmed before a launch is graded where a run actually reaches it, by hyperloom-optimize-vllm-first-steps and hyperloom-bootstrap-phase-discipline.",
+      "prompt": "The environment is already set up. Walk me through what still has to happen before the optimizer starts: which workload values get collected, and what has to happen once they are known but before the optimizer actually starts. Describe it in five or six sentences -- do not ask me for the values yet, and do not run anything."
     },
     {
       "id": "hyperloom-bootstrap-phase-discipline",