feat(fleet): multi-runtime harness — verifier tests + capped builder shell

The harness layer (builder sessions, cold verifiers, evidence flow) gets a committable home, per the PRD model-fleet § harness portability and erp#63: - fleet/harness/verifier/: the two canonical verifier tests (locate-test, cold-reader backlog audit) with pinned inputs, verbatim prompts, ground truth and pass rules — judged context-free, never self-graded. - fleet/harness/bin/run-verifier.sh: runs a test against any OpenAI-style local endpoint (Ornith/MLX) or vibe -p (Mistral); emits sha256-pinned JSON transcripts. - fleet/harness/bin/vibe-builder.sh: the bounded shell for scoped builders and recurring tasks — refuses the trunk (linked-worktree guard), hard --max-turns/--max-price caps, full JSON journal per run. - fleet/README.md layout + AGENTS.md Fleet section updated in the same change (same-change freshness rule). Part of erp#63 (harness portability spike, D2). Co-Authored-By: Claude Fable 5 <[email protected]> Claude-Session: https://claude.ai/code/session_01VRShc4QhLLU73FLHx9vskh
2026-07-18 18:52:53 +02:00
parent fe6909a2a6
commit f2a60817e2
7 changed files with 349 additions and 1 deletions
@@ -0,0 +1,125 @@
+#!/usr/bin/env bash
+# Run a canonical verifier test against a runtime; emit a JSON transcript.
+# See fleet/harness/README.md (runtimes, no-self-grading protocol).
+set -euo pipefail
+
+usage() {
+  cat >&2 <<'EOF'
+usage: run-verifier.sh <locate|backlog> <ornith|mlx|mistral> [options]
+       run-verifier.sh <locate|backlog> --print-prompt [options]
+
+options:
+  --agents-file PATH   AGENTS.md to pin (default: repo-root AGENTS.md)
+  --status-file PATH   STATUS.md to pin (required for the backlog test)
+  --model ID           model id (required for mlx; optional override for ornith)
+  --endpoint URL       OpenAI-style base (default: http://127.0.0.1:18080/v1)
+  --out DIR            transcript dir (default: $TMPDIR/harness-runs)
+  --print-prompt       print the assembled prompt to stdout and exit
+EOF
+  exit 2
+}
+
+TEST="${1:-}"; shift || usage
+case "$TEST" in locate|backlog) ;; *) usage ;; esac
+
+RUNTIME="" PRINT_ONLY=0 MODEL="" ENDPOINT="http://127.0.0.1:18080/v1"
+AGENTS_FILE="" STATUS_FILE="" OUT_DIR="${TMPDIR:-/tmp}/harness-runs"
+while [ $# -gt 0 ]; do
+  case "$1" in
+    ornith|mlx|mistral) RUNTIME="$1" ;;
+    --print-prompt) PRINT_ONLY=1 ;;
+    --agents-file) AGENTS_FILE="$2"; shift ;;
+    --status-file) STATUS_FILE="$2"; shift ;;
+    --model) MODEL="$2"; shift ;;
+    --endpoint) ENDPOINT="$2"; shift ;;
+    --out) OUT_DIR="$2"; shift ;;
+    *) usage ;;
+  esac
+  shift
+done
+[ "$PRINT_ONLY" = 1 ] || [ -n "$RUNTIME" ] || usage
+
+HERE="$(cd "$(dirname "$0")/.." && pwd)"
+REPO_ROOT="$(git -C "$HERE" rev-parse --show-toplevel)"
+[ -n "$AGENTS_FILE" ] || AGENTS_FILE="$REPO_ROOT/AGENTS.md"
+[ -f "$AGENTS_FILE" ] || { echo "missing AGENTS.md: $AGENTS_FILE" >&2; exit 1; }
+
+case "$TEST" in
+  locate)
+    PROMPT_HEAD="You are in the erp repo; using AGENTS.md alone, state where the atom registry, the class skeletons and the environment rules live."
+    ;;
+  backlog)
+    [ -f "${STATUS_FILE:-}" ] || { echo "backlog test requires --status-file" >&2; exit 1; }
+    PROMPT_HEAD="You are a cold reader auditing the Arcodange AI back-office backlog. Using ONLY the two documents below — no other knowledge, no tools — answer:
+1. What shipped most recently?
+2. What should be worked on next, and why that item?
+3. What would you verify before trusting these documents, and in what order?"
+    ;;
+esac
+
+PROMPT="$PROMPT_HEAD
+
+--- AGENTS.md ---
+$(cat "$AGENTS_FILE")"
+if [ "$TEST" = backlog ]; then
+  PROMPT="$PROMPT
+
+--- STATUS.md ---
+$(cat "$STATUS_FILE")"
+fi
+
+if [ "$PRINT_ONLY" = 1 ]; then
+  printf '%s\n' "$PROMPT"
+  exit 0
+fi
+
+mkdir -p "$OUT_DIR"
+TS="$(date +%Y%m%dT%H%M%S)"
+OUT_FILE="$OUT_DIR/${TEST}-${RUNTIME}${MODEL:+-$(basename "$MODEL")}-$TS.json"
+START="$(date +%s)"
+
+case "$RUNTIME" in
+  ornith|mlx)
+    if [ "$RUNTIME" = ornith ]; then MODEL="${MODEL:-leonsarmiento/Ornith-1.0-35B-5bit-mlx}"; fi
+    [ -n "$MODEL" ] || { echo "mlx runtime requires --model" >&2; exit 1; }
+    RESPONSE="$(PROMPT="$PROMPT" MODEL="$MODEL" python3 - "$ENDPOINT" <<'PY'
+import json, os, sys, urllib.request
+body = json.dumps({
+    "model": os.environ["MODEL"],
+    "messages": [{"role": "user", "content": os.environ["PROMPT"]}],
+    "temperature": 0,
+    "max_tokens": 3000,
+}).encode()
+req = urllib.request.Request(sys.argv[1].rstrip("/") + "/chat/completions",
+                             data=body, headers={"Content-Type": "application/json"})
+with urllib.request.urlopen(req, timeout=900) as r:
+    print(json.load(r)["choices"][0]["message"]["content"])
+PY
+)"
+    ;;
+  mistral)
+    MODEL="vibe-active-model"
+    RESPONSE="$(vibe -p "$PROMPT" --max-turns 1 --enabled-tools __none__ --output text)"
+    ;;
+esac
+
+LATENCY=$(( $(date +%s) - START ))
+RESPONSE="$RESPONSE" PROMPT="$PROMPT" TEST="$TEST" RUNTIME="$RUNTIME" MODEL="$MODEL" \
+ENDPOINT="$ENDPOINT" LATENCY="$LATENCY" TS="$TS" AGENTS_FILE="$AGENTS_FILE" STATUS_FILE="${STATUS_FILE:-}" \
+python3 - > "$OUT_FILE" <<'PY'
+import hashlib, json, os
+def sha(p):
+    return hashlib.sha256(open(p, "rb").read()).hexdigest() if p and os.path.exists(p) else None
+e = os.environ
+inputs = {"AGENTS.md": {"path": e["AGENTS_FILE"], "sha256": sha(e["AGENTS_FILE"])}}
+if e["STATUS_FILE"]:
+    inputs["STATUS.md"] = {"path": e["STATUS_FILE"], "sha256": sha(e["STATUS_FILE"])}
+print(json.dumps({
+    "test": e["TEST"], "runtime": e["RUNTIME"], "model": e["MODEL"],
+    "endpoint": e["ENDPOINT"] if e["RUNTIME"] != "mistral" else "vibe -p",
+    "timestamp": e["TS"], "latency_s": int(e["LATENCY"]),
+    "prompt_sha256": hashlib.sha256(e["PROMPT"].encode()).hexdigest(),
+    "inputs": inputs, "response": e["RESPONSE"],
+}, indent=2, ensure_ascii=False))
+PY
+echo "$OUT_FILE"