π The original agent harness. Deploy intelligent multi-player swarms, coordinate autonomous workflows, and build conversational AI systems. Features adaptive memory, self-learning intelligence, federation, vector RAG integration, and native Claude Code / Codex / Hermes and many more Integrated
TypeScript agentic-aiagentic-frameworkagentic-workflowagentsai-agentsai-assistantai-skillsautonomous-agentsclaudecodexdsh-pluginharnessmcp-servermulti-agentmulti-agent-systemsnpmskillsswarmswarm-intelligencetypescript
fix(metaharness): 5 smoke contract failures (iter 124)
ruv0215e7b63342
diff --git a/plugins/ruflo-metaharness/scripts/mcp-scan.mjs b/plugins/ruflo-metaharness/scripts/mcp-scan.mjsindex 6dc3c84b2c..8ca1311f5a 100755--- a/plugins/ruflo-metaharness/scripts/mcp-scan.mjs+++ b/plugins/ruflo-metaharness/scripts/mcp-scan.mjs@@ -53,13 +53,24 @@ function main() {// diff actually works. If a future upstream version DOES emit// findings[], the parsed-text findings are overridden.const parsed = parseMcpScanText(r.stdout);+ // iter 124 β normalize finding shape so consumers see a stable contract.+ // Upstream [email protected] JSON path emits {id, severity, title, detail};+ // our parseMcpScanText emits {severity, message}. Project both into a+ // unified {severity, message, title?, detail?} so audit-trend's fingerprint+ // diff and test-mcp-tools' assertions don't care which path produced them.+ const rawFindings = Array.isArray(r.json?.findings) ? r.json.findings : parsed.findings;+ const findings = rawFindings.map((f) => ({+ ...f,+ message: typeof f.message === 'string' && f.message+ ? f.message+ : (f.title || f.detail || ''),+ }));const payload = {...(r.json ?? {}),- findings: Array.isArray(r.json?.findings) ? r.json.findings : parsed.findings,+ findings,summary: r.json?.summary ?? parsed.summary,rawStdout: r.stdout.slice(0, 400),};- const findings = payload.findings;const threshold = SEVERITY_RANK[ARGS.failOn];// iter 63 β rankSeverity() safe lookup. Pre-iter-63 `undefined >= 3`// was false β unknown-severity findings (e.g., warn / error) werediff --git a/plugins/ruflo-metaharness/scripts/smoke.sh b/plugins/ruflo-metaharness/scripts/smoke.shindex d5d26ee48d..ce5e7222bd 100755--- a/plugins/ruflo-metaharness/scripts/smoke.sh+++ b/plugins/ruflo-metaharness/scripts/smoke.sh@@ -1502,8 +1502,14 @@ grep -q "iter-51-marker" "$F" 2>/dev/null || miss="$miss no-jaccard-mutation"grep -q "drift detected β verdict !== near-identical" "$F" 2>/dev/null || miss="$miss no-verdict-flip"grep -q "drift detected β distance > 0" "$F" 2>/dev/null || miss="$miss no-distance-positive"grep -q "drift alert at threshold" "$F" 2>/dev/null || miss="$miss no-drift-alert"-# Runtime: 31/31 (was 25/25 pre-iter-51)-node "$F" 2>&1 | grep -q "31 passed, 0 failed" || miss="$miss roundtrip-not-31"+# Runtime: assertion count has grown as stages added (was 25β31ββ¦ β 66 at+# iter 79). Smoke gates on "0 failed" with a passed count β₯ 31, not the+# specific number β keeps the gate from breaking every time a new stage+# adds assertions.+ROUNDTRIP_OUT=$(node "$F" 2>&1)+echo "$ROUNDTRIP_OUT" | grep -qE "^[0-9]+ passed, 0 failed$" || miss="$miss roundtrip-has-failures"+ROUNDTRIP_COUNT=$(echo "$ROUNDTRIP_OUT" | grep -oE "^[0-9]+ passed" | grep -oE "[0-9]+" | head -1)+[[ "${ROUNDTRIP_COUNT:-0}" -ge 31 ]] || miss="$miss roundtrip-count-regressed:$ROUNDTRIP_COUNT"[[ -z "$miss" ]] && ok || bad "$miss"step "17z13. mcp-scan findings parsed from text β audit-trend diff works (iter 50)"@@ -1720,10 +1726,15 @@ node "$F" >/dev/null 2>&1 || miss="$miss unit-tests-fail"step "17z. ADR-152 Β§3.1 deep integration β oia-audit fingerprint + audit-trend structuralDistance (iter 38)"miss=""-# oia-audit captures score + genome AND surfaces a fingerprint{score,genome}+# oia-audit captures score + genome AND surfaces a fingerprint{score,genome}.+# iter 56 refactored sequential runOne(...) β parallel+# runMetaharnessAsync(['score'/'genome', path]); accept either form so smoke+# survives the refactor.OIA="$ROOT/scripts/oia-audit.mjs"-grep -q "score = runOne(\['score'" "$OIA" 2>/dev/null || miss="$miss no-score-capture"-grep -q "genome = runOne(\['genome'" "$OIA" 2>/dev/null || miss="$miss no-genome-capture"+grep -qE "score = runOne\\(\\['score'|runMetaharnessAsync\\(\\['score', path\\]\\)" "$OIA" 2>/dev/null \+ || miss="$miss no-score-capture"+grep -qE "genome = runOne\\(\\['genome'|runMetaharnessAsync\\(\\['genome', path\\]\\)" "$OIA" 2>/dev/null \+ || miss="$miss no-genome-capture"grep -q "fingerprint: {" "$OIA" 2>/dev/null || miss="$miss no-fingerprint-field"# audit-trend imports the production similarity module and surfaces a verdictAT="$ROOT/scripts/audit-trend.mjs"@@ -2075,8 +2086,10 @@ F="$ROOT/scripts/audit-trend.mjs"miss=""[[ -x "$F" ]] || miss="$miss not-executable"node --check "$F" 2>/dev/null || miss="$miss syntax-error"-# Severity rank present + correct ordering-grep -q "SEVERITY_RANK = { clean: 0, low: 1, medium: 2, high: 3 }" "$F" || miss="$miss no-severity-rank"+# Severity rank present + correct ordering β iter 63 refactored to shared+# SEVERITY_RANK from _harness.mjs; accept either the import OR the literal.+grep -qE "SEVERITY_RANK.*from.*_harness|SEVERITY_RANK = \{ clean: 0, low: 1, medium: 2, high: 3 \}" "$F" \+ || miss="$miss no-severity-rank"# Both file-input AND memory-key-input pathsgrep -q "baseline-key\|baselineKey" "$F" || miss="$miss no-mem-key-input"grep -q "current-key\|currentKey" "$F" || miss="$miss no-current-key"diff --git a/plugins/ruflo-metaharness/scripts/test-mcp-tools.mjs b/plugins/ruflo-metaharness/scripts/test-mcp-tools.mjsindex 6badf0a17d..88690fcdbd 100755--- a/plugins/ruflo-metaharness/scripts/test-mcp-tools.mjs+++ b/plugins/ruflo-metaharness/scripts/test-mcp-tools.mjs@@ -135,8 +135,11 @@ async function main() {input = { dryRun: true, threshold: 0.5 };}- // 30s budget per tool by default; 90s for chain-tools like drift_from_history.- const timeoutMs = tool.name === 'metaharness_drift_from_history' ? 90_000 : 30_000;+ // iter 124 β bumped default 30s β 60s. The first MCP tool that shells+ // out via npx pays the cold-cache warmup cost (~25s observed), which+ // pushed metaharness_audit_list past the prior 30s budget intermittently.+ // 90s for chain-tools like drift_from_history that compose 3 subprocesses.+ const timeoutMs = tool.name === 'metaharness_drift_from_history' ? 90_000 : 60_000;const handlerPromise = tool.handler(input);const timeoutPromise = new Promise((_, reject) =>setTimeout(() => reject(new Error(`${timeoutMs / 1000}s handler timeout`)), timeoutMs));