homegraph 1.5.0 → 1.5.1

package/scripts/agent-eval/offload-eval-metrics.mjs

@@ -1,94 +1,94 @@
-#!/usr/bin/env node
-// Extract one eval run's metrics from its Claude stream-json transcript + the
-// offload usage sidecar log, emit ONE merged JSON line.
-//
-// Usage: extract-metrics.mjs --run <run.jsonl> --usage <usage.jsonl|-> \
-//          --arm <a> --rep <n> --repo <r> --tier <t> --q <question>
-import { readFileSync, existsSync } from 'fs';
-
-const args = {};
-for (let i = 2; i < process.argv.length; i += 2) args[process.argv[i].replace(/^--/, '')] = process.argv[i + 1];
-
-const runFile = args.run;
-const lines = existsSync(runFile) ? readFileSync(runFile, 'utf8').split('\n').filter(Boolean) : [];
-
-const toolCounts = {};
-let result = null;
-const tok = { gen: 0, fresh: 0, cached: 0 };
-const offloadAnswers = [];
-let exploreResults = 0; // tool_results from explore (offload or raw)
-let lastAssistantText = '';
-
-for (const line of lines) {
-  let ev; try { ev = JSON.parse(line); } catch { continue; }
-
-  // per-turn token usage (authoritative token measure; result.usage is last-turn only)
-  const u = ev.message?.usage;
-  if (u) {
-    tok.gen += u.output_tokens || 0;
-    tok.fresh += (u.input_tokens || 0) + (u.cache_creation_input_tokens || 0);
-    tok.cached += u.cache_read_input_tokens || 0;
-  }
-
-  if (ev.type === 'assistant' && Array.isArray(ev.message?.content)) {
-    for (const b of ev.message.content) {
-      if (b.type === 'tool_use') toolCounts[b.name] = (toolCounts[b.name] || 0) + 1;
-      if (b.type === 'text' && b.text?.trim()) lastAssistantText = b.text.trim();
-    }
-  }
-  // tool_results arrive in user messages
-  if (ev.type === 'user' && Array.isArray(ev.message?.content)) {
-    for (const b of ev.message.content) {
-      if (b.type !== 'tool_result') continue;
-      const text = Array.isArray(b.content)
-        ? b.content.map(c => (typeof c === 'string' ? c : c.text || '')).join('')
-        : (typeof b.content === 'string' ? b.content : '');
-      // An offload answer is either the 'plain'/'report' synthesis (carries the
-      // "Synthesized by HomeGraph" footer) or a 'refs' answer (carries the re-expanded
-      // "### Referenced source — verbatim" appendix). A refs call that cited nothing
-      // valid falls back to RAW source, which is correctly counted as a raw explore below.
-      if (/Synthesized by HomeGraph|### Referenced source — verbatim/.test(text)) { offloadAnswers.push(text); exploreResults++; }
-      else if (/Found \d+ symbols? across|\*\*Exploration:/.test(text)) exploreResults++;
-    }
-  }
-  if (ev.type === 'result') result = ev;
-}
-
-// offload usage sidecar (HomeGraph AI tokens + cost) — one JSON line per offload call
-const ai = { calls: 0, promptTokens: 0, completionTokens: 0, totalTokens: 0, credits: 0, costUsd: 0, ms: 0 };
-if (args.usage && args.usage !== '-' && existsSync(args.usage)) {
-  for (const line of readFileSync(args.usage, 'utf8').split('\n').filter(Boolean)) {
-    let e; try { e = JSON.parse(line); } catch { continue; }
-    ai.calls++;
-    ai.promptTokens += e.promptTokens || 0;
-    ai.completionTokens += e.completionTokens || 0;
-    ai.totalTokens += e.totalTokens || 0;
-    ai.credits += e.creditsCharged || 0;
-    ai.costUsd += e.costUsd || 0;
-    ai.ms += e.ms || 0;
-  }
-}
-
-// front-load hook fired iff its injected header appears in the transcript
-const frontload = lines.some(l => l.includes('auto-retrieved for this question'));
-const get = (n) => toolCounts[n] || 0;
-const read = get('Read');
-const grep = get('Grep') + get('Bash') + get('Glob');
-const explore = get('mcp__homegraph__homegraph_explore');
-const cgAny = Object.keys(toolCounts).filter(k => /mcp__homegraph__/.test(k)).reduce((s, k) => s + toolCounts[k], 0);
-
-const out = {
-  repo: args.repo, tier: args.tier, arm: args.arm, rep: Number(args.rep), question: args.q,
-  ok: result?.subtype === 'success',
-  durationSec: result ? +(result.duration_ms / 1000).toFixed(1) : null,
-  numTurns: result?.num_turns ?? null,
-  costUsdMain: result ? +(result.total_cost_usd || 0).toFixed(4) : null,
-  tokGen: tok.gen, tokFresh: tok.fresh, tokCached: tok.cached, tokBillable: tok.gen + tok.fresh,
-  read, grep, explore, cgAny, frontload,
-  offloadFired: offloadAnswers.length,
-  ai,
-  // text payloads for the accuracy judge (kept separate; large)
-  finalAnswer: (result?.result || lastAssistantText || '').slice(0, 8000),
-  offloadAnswers: offloadAnswers.map(a => a.slice(0, 6000)),
-};
-process.stdout.write(JSON.stringify(out) + '\n');
+#!/usr/bin/env node
+// Extract one eval run's metrics from its Claude stream-json transcript + the
+// offload usage sidecar log, emit ONE merged JSON line.
+//
+// Usage: extract-metrics.mjs --run <run.jsonl> --usage <usage.jsonl|-> \
+//          --arm <a> --rep <n> --repo <r> --tier <t> --q <question>
+import { readFileSync, existsSync } from 'fs';
+
+const args = {};
+for (let i = 2; i < process.argv.length; i += 2) args[process.argv[i].replace(/^--/, '')] = process.argv[i + 1];
+
+const runFile = args.run;
+const lines = existsSync(runFile) ? readFileSync(runFile, 'utf8').split('\n').filter(Boolean) : [];
+
+const toolCounts = {};
+let result = null;
+const tok = { gen: 0, fresh: 0, cached: 0 };
+const offloadAnswers = [];
+let exploreResults = 0; // tool_results from explore (offload or raw)
+let lastAssistantText = '';
+
+for (const line of lines) {
+  let ev; try { ev = JSON.parse(line); } catch { continue; }
+
+  // per-turn token usage (authoritative token measure; result.usage is last-turn only)
+  const u = ev.message?.usage;
+  if (u) {
+    tok.gen += u.output_tokens || 0;
+    tok.fresh += (u.input_tokens || 0) + (u.cache_creation_input_tokens || 0);
+    tok.cached += u.cache_read_input_tokens || 0;
+  }
+
+  if (ev.type === 'assistant' && Array.isArray(ev.message?.content)) {
+    for (const b of ev.message.content) {
+      if (b.type === 'tool_use') toolCounts[b.name] = (toolCounts[b.name] || 0) + 1;
+      if (b.type === 'text' && b.text?.trim()) lastAssistantText = b.text.trim();
+    }
+  }
+  // tool_results arrive in user messages
+  if (ev.type === 'user' && Array.isArray(ev.message?.content)) {
+    for (const b of ev.message.content) {
+      if (b.type !== 'tool_result') continue;
+      const text = Array.isArray(b.content)
+        ? b.content.map(c => (typeof c === 'string' ? c : c.text || '')).join('')
+        : (typeof b.content === 'string' ? b.content : '');
+      // An offload answer is either the 'plain'/'report' synthesis (carries the
+      // "Synthesized by HomeGraph" footer) or a 'refs' answer (carries the re-expanded
+      // "### Referenced source — verbatim" appendix). A refs call that cited nothing
+      // valid falls back to RAW source, which is correctly counted as a raw explore below.
+      if (/Synthesized by HomeGraph|### Referenced source — verbatim/.test(text)) { offloadAnswers.push(text); exploreResults++; }
+      else if (/Found \d+ symbols? across|\*\*Exploration:/.test(text)) exploreResults++;
+    }
+  }
+  if (ev.type === 'result') result = ev;
+}
+
+// offload usage sidecar (HomeGraph AI tokens + cost) — one JSON line per offload call
+const ai = { calls: 0, promptTokens: 0, completionTokens: 0, totalTokens: 0, credits: 0, costUsd: 0, ms: 0 };
+if (args.usage && args.usage !== '-' && existsSync(args.usage)) {
+  for (const line of readFileSync(args.usage, 'utf8').split('\n').filter(Boolean)) {
+    let e; try { e = JSON.parse(line); } catch { continue; }
+    ai.calls++;
+    ai.promptTokens += e.promptTokens || 0;
+    ai.completionTokens += e.completionTokens || 0;
+    ai.totalTokens += e.totalTokens || 0;
+    ai.credits += e.creditsCharged || 0;
+    ai.costUsd += e.costUsd || 0;
+    ai.ms += e.ms || 0;
+  }
+}
+
+// front-load hook fired iff its injected header appears in the transcript
+const frontload = lines.some(l => l.includes('auto-retrieved for this question'));
+const get = (n) => toolCounts[n] || 0;
+const read = get('Read');
+const grep = get('Grep') + get('Bash') + get('Glob');
+const explore = get('mcp__homegraph__homegraph_explore');
+const cgAny = Object.keys(toolCounts).filter(k => /mcp__homegraph__/.test(k)).reduce((s, k) => s + toolCounts[k], 0);
+
+const out = {
+  repo: args.repo, tier: args.tier, arm: args.arm, rep: Number(args.rep), question: args.q,
+  ok: result?.subtype === 'success',
+  durationSec: result ? +(result.duration_ms / 1000).toFixed(1) : null,
+  numTurns: result?.num_turns ?? null,
+  costUsdMain: result ? +(result.total_cost_usd || 0).toFixed(4) : null,
+  tokGen: tok.gen, tokFresh: tok.fresh, tokCached: tok.cached, tokBillable: tok.gen + tok.fresh,
+  read, grep, explore, cgAny, frontload,
+  offloadFired: offloadAnswers.length,
+  ai,
+  // text payloads for the accuracy judge (kept separate; large)
+  finalAnswer: (result?.result || lastAssistantText || '').slice(0, 8000),
+  offloadAnswers: offloadAnswers.map(a => a.slice(0, 6000)),
+};
+process.stdout.write(JSON.stringify(out) + '\n');

package/scripts/agent-eval/offload-eval-refs1.sh

@@ -1,50 +1,50 @@
-#!/usr/bin/env bash
-# ONE offload run on ONE indexed repo at a given offload STYLE (plain|refs), so we can
-# watch a single agent transcript at a time (the user's one-run-at-a-time methodology).
-# The OFFLOAD reasoning runs in the prewarmed DAEMON process, so the style env must be
-# set on BOTH the daemon and the client MCP config. Writes one metrics line to RESULTS
-# and leaves the raw stream-json at $RUNS/<repo>-<style>-<n>.jsonl for inspection.
-#
-# Usage: offload-eval-refs1.sh <indexed-repo> <style> <n> "<question>"
-set -uo pipefail
-HERE="$(cd "$(dirname "$0")" && pwd)"; ENGINE="$(cd "$HERE/../.." && pwd)"; BIN="$ENGINE/dist/bin/homegraph.js"
-OUT="${AGENT_EVAL_OUT:-/tmp/cg-offload-eval}"; RUNS="$OUT/runs"; EXTRACT="$HERE/offload-eval-metrics.mjs"
-TARGET="${1:?repo}"; STYLE="${2:?style}"; N="${3:?run-tag}"; Q="${4:?question}"
-RESULTS="${RESULTS:-$OUT/results-refs.jsonl}"; REPO=$(basename "$TARGET"); TARGET=$(cd "$TARGET" && pwd -P)
-mkdir -p "$RUNS"; command -v claude >/dev/null || { echo "no claude"; exit 1; }
-USAGE="$RUNS/$REPO-$STYLE-usage.jsonl"; : > "$USAGE"
-CFG="$RUNS/mcp-$REPO-$STYLE.json"
-# `raw` is a pseudo-style: homegraph attached but the offload DISABLED (the ceiling —
-# verbatim source, no reasoning model). Any other value is an offload style (plain|refs).
-if [ "$STYLE" = "raw" ]; then
-  DAEMON_ENV="HOMEGRAPH_OFFLOAD_DISABLE=1"
-  printf '{"mcpServers":{"homegraph":{"command":"env","args":["HOMEGRAPH_WASM_RELAUNCHED=1","HOMEGRAPH_OFFLOAD_DISABLE=1","node","%s","serve","--mcp","--path","%s"]}}}' \
-    "$BIN" "$TARGET" > "$CFG"
-  USAGE="-"
-else
-  DAEMON_ENV="HOMEGRAPH_OFFLOAD_STYLE=$STYLE HOMEGRAPH_OFFLOAD_USAGE_LOG=$USAGE"
-  printf '{"mcpServers":{"homegraph":{"command":"env","args":["HOMEGRAPH_WASM_RELAUNCHED=1","HOMEGRAPH_OFFLOAD_STYLE=%s","HOMEGRAPH_OFFLOAD_USAGE_LOG=%s","node","%s","serve","--mcp","--path","%s"]}}}' \
-    "$STYLE" "$USAGE" "$BIN" "$TARGET" > "$CFG"
-fi
-
-# Prewarm a persistent daemon carrying the SAME offload config (it does the reasoning).
-pkill -9 -f "serve --mcp --path $TARGET" 2>/dev/null; rm -f "$TARGET/.homegraph/daemon.sock" 2>/dev/null; sleep 0.6
-env $DAEMON_ENV HOMEGRAPH_DAEMON_IDLE_TIMEOUT_MS=1800000 \
-  node "$BIN" serve --mcp --path "$TARGET" </dev/null >/dev/null 2>&1 &
-node -e 'const fs=require("fs");let n=0;const t=setInterval(()=>{if(fs.existsSync(process.argv[1]+"/.homegraph/daemon.sock")){clearInterval(t);process.exit(0)}if(n++>150){clearInterval(t);process.exit(1)}},100)' "$TARGET" \
-  && echo "daemon warm ($STYLE)" || echo "WARN daemon never bound"
-
-tag="$REPO-$STYLE-$N"
-echo "== run $tag =="
-# DISALLOW (optional): block tools that confound the offload-sufficiency signal —
-# chiefly "Agent" (sub-agent delegation: the spawned Explore subagent has low MCP
-# salience, ignores homegraph, and thrashes via Bash+Read, making the A/B noise).
-( cd "$TARGET" && claude -p "$Q" --output-format stream-json --verbose --permission-mode bypassPermissions \
-    --model "${MODEL:-sonnet}" --effort "${EFFORT:-high}" --max-budget-usd 4 \
-    ${DISALLOW:+--disallowedTools "$DISALLOW"} \
-    --strict-mcp-config --mcp-config "$CFG" </dev/null > "$RUNS/$tag.jsonl" 2>"$RUNS/$tag.err" )
-node "$EXTRACT" --run "$RUNS/$tag.jsonl" --usage "$USAGE" --arm "offload-$STYLE" --rep "$N" \
-    --repo "$REPO" --tier "complex" --q "$Q" >> "$RESULTS"
-node -e 'const o=JSON.parse(require("fs").readFileSync(process.argv[1],"utf8").trim().split("\n").pop());console.log(`  [${o.arm} #${o.rep}] ${o.durationSec}s | main $${o.costUsdMain} ${o.tokBillable} tok | read=${o.read} grep=${o.grep} explore=${o.explore} offload=${o.offloadFired} | AI ${o.ai.calls}call/${o.ai.totalTokens}tok/$${o.ai.costUsd.toFixed(4)} | ok=${o.ok}`)' "$RESULTS"
-pkill -9 -f "serve --mcp --path $TARGET" 2>/dev/null; rm -f "$TARGET/.homegraph/daemon.sock" 2>/dev/null
-echo "raw transcript: $RUNS/$tag.jsonl"
+#!/usr/bin/env bash
+# ONE offload run on ONE indexed repo at a given offload STYLE (plain|refs), so we can
+# watch a single agent transcript at a time (the user's one-run-at-a-time methodology).
+# The OFFLOAD reasoning runs in the prewarmed DAEMON process, so the style env must be
+# set on BOTH the daemon and the client MCP config. Writes one metrics line to RESULTS
+# and leaves the raw stream-json at $RUNS/<repo>-<style>-<n>.jsonl for inspection.
+#
+# Usage: offload-eval-refs1.sh <indexed-repo> <style> <n> "<question>"
+set -uo pipefail
+HERE="$(cd "$(dirname "$0")" && pwd)"; ENGINE="$(cd "$HERE/../.." && pwd)"; BIN="$ENGINE/dist/bin/homegraph.js"
+OUT="${AGENT_EVAL_OUT:-/tmp/cg-offload-eval}"; RUNS="$OUT/runs"; EXTRACT="$HERE/offload-eval-metrics.mjs"
+TARGET="${1:?repo}"; STYLE="${2:?style}"; N="${3:?run-tag}"; Q="${4:?question}"
+RESULTS="${RESULTS:-$OUT/results-refs.jsonl}"; REPO=$(basename "$TARGET"); TARGET=$(cd "$TARGET" && pwd -P)
+mkdir -p "$RUNS"; command -v claude >/dev/null || { echo "no claude"; exit 1; }
+USAGE="$RUNS/$REPO-$STYLE-usage.jsonl"; : > "$USAGE"
+CFG="$RUNS/mcp-$REPO-$STYLE.json"
+# `raw` is a pseudo-style: homegraph attached but the offload DISABLED (the ceiling —
+# verbatim source, no reasoning model). Any other value is an offload style (plain|refs).
+if [ "$STYLE" = "raw" ]; then
+  DAEMON_ENV="HOMEGRAPH_OFFLOAD_DISABLE=1"
+  printf '{"mcpServers":{"homegraph":{"command":"env","args":["HOMEGRAPH_WASM_RELAUNCHED=1","HOMEGRAPH_OFFLOAD_DISABLE=1","node","%s","serve","--mcp","--path","%s"]}}}' \
+    "$BIN" "$TARGET" > "$CFG"
+  USAGE="-"
+else
+  DAEMON_ENV="HOMEGRAPH_OFFLOAD_STYLE=$STYLE HOMEGRAPH_OFFLOAD_USAGE_LOG=$USAGE"
+  printf '{"mcpServers":{"homegraph":{"command":"env","args":["HOMEGRAPH_WASM_RELAUNCHED=1","HOMEGRAPH_OFFLOAD_STYLE=%s","HOMEGRAPH_OFFLOAD_USAGE_LOG=%s","node","%s","serve","--mcp","--path","%s"]}}}' \
+    "$STYLE" "$USAGE" "$BIN" "$TARGET" > "$CFG"
+fi
+
+# Prewarm a persistent daemon carrying the SAME offload config (it does the reasoning).
+pkill -9 -f "serve --mcp --path $TARGET" 2>/dev/null; rm -f "$TARGET/.homegraph/daemon.sock" 2>/dev/null; sleep 0.6
+env $DAEMON_ENV HOMEGRAPH_DAEMON_IDLE_TIMEOUT_MS=1800000 \
+  node "$BIN" serve --mcp --path "$TARGET" </dev/null >/dev/null 2>&1 &
+node -e 'const fs=require("fs");let n=0;const t=setInterval(()=>{if(fs.existsSync(process.argv[1]+"/.homegraph/daemon.sock")){clearInterval(t);process.exit(0)}if(n++>150){clearInterval(t);process.exit(1)}},100)' "$TARGET" \
+  && echo "daemon warm ($STYLE)" || echo "WARN daemon never bound"
+
+tag="$REPO-$STYLE-$N"
+echo "== run $tag =="
+# DISALLOW (optional): block tools that confound the offload-sufficiency signal —
+# chiefly "Agent" (sub-agent delegation: the spawned Explore subagent has low MCP
+# salience, ignores homegraph, and thrashes via Bash+Read, making the A/B noise).
+( cd "$TARGET" && claude -p "$Q" --output-format stream-json --verbose --permission-mode bypassPermissions \
+    --model "${MODEL:-sonnet}" --effort "${EFFORT:-high}" --max-budget-usd 4 \
+    ${DISALLOW:+--disallowedTools "$DISALLOW"} \
+    --strict-mcp-config --mcp-config "$CFG" </dev/null > "$RUNS/$tag.jsonl" 2>"$RUNS/$tag.err" )
+node "$EXTRACT" --run "$RUNS/$tag.jsonl" --usage "$USAGE" --arm "offload-$STYLE" --rep "$N" \
+    --repo "$REPO" --tier "complex" --q "$Q" >> "$RESULTS"
+node -e 'const o=JSON.parse(require("fs").readFileSync(process.argv[1],"utf8").trim().split("\n").pop());console.log(`  [${o.arm} #${o.rep}] ${o.durationSec}s | main $${o.costUsdMain} ${o.tokBillable} tok | read=${o.read} grep=${o.grep} explore=${o.explore} offload=${o.offloadFired} | AI ${o.ai.calls}call/${o.ai.totalTokens}tok/$${o.ai.costUsd.toFixed(4)} | ok=${o.ok}`)' "$RESULTS"
+pkill -9 -f "serve --mcp --path $TARGET" 2>/dev/null; rm -f "$TARGET/.homegraph/daemon.sock" 2>/dev/null
+echo "raw transcript: $RUNS/$tag.jsonl"

package/scripts/agent-eval/offload-eval-setup.sh

@@ -1,24 +1,24 @@
-#!/usr/bin/env bash
-# Clone + index the 4 "not-trained-on" eval repos into $AGENT_EVAL_OUT/repos. These were
-# selected via a no-tools memory-probe gate (Sonnet cannot answer their flow questions from
-# memory — so the no-homegraph baseline is honest). Env: AGENT_EVAL_OUT=<scratch dir>
-set -uo pipefail
-HERE="$(cd "$(dirname "$0")" && pwd)"
-ENGINE="$(cd "$HERE/../.." && pwd)"
-BIN="$ENGINE/dist/bin/homegraph.js"
-OUT="${AGENT_EVAL_OUT:-/tmp/cg-offload-eval}"
-ROOT="$OUT/repos"; mkdir -p "$ROOT"
-export HOMEGRAPH_TELEMETRY=0 DO_NOT_TRACK=1
-[ -f "$BIN" ] || { echo "engine not built: run 'npm run build' in $ENGINE first"; exit 1; }
-
-clone_index() { # url name
-  echo "=== $2: clone ==="; rm -rf "$ROOT/$2"
-  git clone --quiet --depth 1 "$1" "$ROOT/$2" || { echo "  clone FAILED"; return 1; }
-  echo "=== $2: index ==="
-  node "$BIN" init "$ROOT/$2" 2>&1 | grep -iE 'indexed|nodes|edges|error' | tail -2
-}
-clone_index https://github.com/MTKruto/MTKruto.git mtkruto          # small  (~322 TS)
-clone_index https://github.com/mvdicarlo/postybirb-plus.git postybirb  # medium (~608 TS)
-clone_index https://github.com/shapeshift/web.git shapeshift        # complex (~3.2k TS, 35-pkg monorepo)
-clone_index https://github.com/trezor/trezor-suite.git trezor       # large  (~8k TS monorepo)
-echo "###### SETUP DONE -> $ROOT"
+#!/usr/bin/env bash
+# Clone + index the 4 "not-trained-on" eval repos into $AGENT_EVAL_OUT/repos. These were
+# selected via a no-tools memory-probe gate (Sonnet cannot answer their flow questions from
+# memory — so the no-homegraph baseline is honest). Env: AGENT_EVAL_OUT=<scratch dir>
+set -uo pipefail
+HERE="$(cd "$(dirname "$0")" && pwd)"
+ENGINE="$(cd "$HERE/../.." && pwd)"
+BIN="$ENGINE/dist/bin/homegraph.js"
+OUT="${AGENT_EVAL_OUT:-/tmp/cg-offload-eval}"
+ROOT="$OUT/repos"; mkdir -p "$ROOT"
+export HOMEGRAPH_TELEMETRY=0 DO_NOT_TRACK=1
+[ -f "$BIN" ] || { echo "engine not built: run 'npm run build' in $ENGINE first"; exit 1; }
+
+clone_index() { # url name
+  echo "=== $2: clone ==="; rm -rf "$ROOT/$2"
+  git clone --quiet --depth 1 "$1" "$ROOT/$2" || { echo "  clone FAILED"; return 1; }
+  echo "=== $2: index ==="
+  node "$BIN" init "$ROOT/$2" 2>&1 | grep -iE 'indexed|nodes|edges|error' | tail -2
+}
+clone_index https://github.com/MTKruto/MTKruto.git mtkruto          # small  (~322 TS)
+clone_index https://github.com/mvdicarlo/postybirb-plus.git postybirb  # medium (~608 TS)
+clone_index https://github.com/shapeshift/web.git shapeshift        # complex (~3.2k TS, 35-pkg monorepo)
+clone_index https://github.com/trezor/trezor-suite.git trezor       # large  (~8k TS monorepo)
+echo "###### SETUP DONE -> $ROOT"

package/scripts/agent-eval/offload-eval-styles.sh

@@ -1,72 +1,72 @@
-#!/usr/bin/env bash
-# Offload reasoning-OUTPUT-STYLE A/B — all homegraph-on, isolating the Worker's
-# output shape's effect on main-session tokens / latency / accuracy:
-#   raw  : HOMEGRAPH_OFFLOAD_DISABLE=1            (verbatim explore source, the floor)
-#   refs : managed offload, default              (Cerebras map re-expanded to verbatim, ~24K)
-#   map  : managed offload, STYLE=map            (compact reasoned map + file:line anchors, ~1-3K)
-#   src  : managed offload, STYLE=src            (map + cited line ranges only, ~1-5K)
-# Delegation BLOCKED by default (DISALLOW=Agent) so we measure the offload payload's
-# effect on the main Sonnet agent, not whether it spawns a Haiku Explore subagent.
-#
-# Usage: offload-eval-styles.sh <indexed-repo> <reps> "<question>"
-# Env:   RESULTS=<file>  AGENT_EVAL_OUT=<dir>  REP_START=1  DISALLOW=Agent  MODEL/EFFORT
-set -uo pipefail
-HERE="$(cd "$(dirname "$0")" && pwd)"
-ENGINE="$(cd "$HERE/../.." && pwd)"
-BIN="$ENGINE/dist/bin/homegraph.js"
-OUT="${AGENT_EVAL_OUT:-/tmp/cg-offload-eval}"
-TARGET="${1:?usage: offload-eval-styles.sh <indexed-repo> <reps> \"<question>\"}"
-REPS="${2:?reps}"; Q="${3:?question}"
-RUNS="$OUT/runs"; EXTRACT="$HERE/offload-eval-metrics.mjs"
-RESULTS="${RESULTS:-$OUT/results-styles.jsonl}"
-REPO=$(basename "$TARGET")
-DISALLOW="${DISALLOW-Agent}"   # default: block delegation. `DISALLOW= ` to allow.
-START="${REP_START:-1}"; END=$((START + REPS - 1))
-mkdir -p "$RUNS"
-command -v claude >/dev/null || { echo "no claude on PATH"; exit 1; }
-[ -d "$TARGET/.homegraph" ] || { echo "not indexed: $TARGET"; exit 1; }
-TARGET=$(cd "$TARGET" && pwd -P)
-
-prewarm() { # path  extra-env
-  pkill -9 -f "serve --mcp --path $1" 2>/dev/null; rm -f "$1/.homegraph/daemon.sock" 2>/dev/null; sleep 0.6
-  env ${2:-} HOMEGRAPH_DAEMON_IDLE_TIMEOUT_MS=1800000 node "$BIN" serve --mcp --path "$1" </dev/null >/dev/null 2>&1 &
-  node -e 'const fs=require("fs");let n=0;const t=setInterval(()=>{if(fs.existsSync(process.argv[1]+"/.homegraph/daemon.sock")){clearInterval(t);process.exit(0)}if(n++>150){clearInterval(t);process.exit(1)}},100)' "$1" \
-    && echo "  daemon warm" || echo "  WARN daemon never bound"
-}
-kill_daemon() { pkill -9 -f "serve --mcp --path $TARGET" 2>/dev/null; rm -f "$TARGET/.homegraph/daemon.sock" 2>/dev/null; sleep 1; }
-
-run() { # arm rep mcp-config usage-log-or-dash
-  local arm="$1" rep="$2" cfg="$3" usage="$4" tag="$REPO-$1-$2"
-  [ "$usage" != "-" ] && : > "$usage"
-  ( cd "$TARGET" && claude -p "$Q" \
-      --output-format stream-json --verbose --permission-mode bypassPermissions \
-      --model "${MODEL:-sonnet}" --effort "${EFFORT:-high}" --max-budget-usd 4 \
-      ${DISALLOW:+--disallowedTools "$DISALLOW"} \
-      --strict-mcp-config --mcp-config "$cfg" \
-      </dev/null > "$RUNS/$tag.jsonl" 2>"$RUNS/$tag.err" )
-  node "$EXTRACT" --run "$RUNS/$tag.jsonl" --usage "$usage" --arm "$arm" --rep "$rep" \
-      --repo "$REPO" --tier styles --q "$Q" >> "$RESULTS"
-  node -e 'const o=JSON.parse(require("fs").readFileSync(process.argv[1],"utf8").trim().split("\n").pop());console.log(`  [${o.arm} #${o.rep}] ${o.durationSec}s | ${o.tokBillable} billable tok | read=${o.read} grep=${o.grep} explore=${o.explore} offload=${o.offloadFired} | AI ${o.ai.calls}c/${o.ai.totalTokens}t | ok=${o.ok}`)' "$RESULTS"
-}
-
-# MCP configs: env baked into the daemon-spawn command claude uses.
-USAGE="$RUNS/$REPO-usage.jsonl"
-mkcfg() { # file extra-env-pairs(JSON array entries, comma-led or empty)
-  printf '{"mcpServers":{"homegraph":{"command":"env","args":["HOMEGRAPH_WASM_RELAUNCHED=1"%s,"node","%s","serve","--mcp","--path","%s"]}}}' "$1" "$BIN" "$TARGET"
-}
-CFG_RAW="$RUNS/mcp-sty-raw-$REPO.json";   mkcfg ',"HOMEGRAPH_OFFLOAD_DISABLE=1"' > "$CFG_RAW"
-CFG_REFS="$RUNS/mcp-sty-refs-$REPO.json"; mkcfg ",\"HOMEGRAPH_OFFLOAD_USAGE_LOG=$USAGE\"" > "$CFG_REFS"
-CFG_MAP="$RUNS/mcp-sty-map-$REPO.json";   mkcfg ",\"HOMEGRAPH_OFFLOAD_USAGE_LOG=$USAGE\",\"HOMEGRAPH_OFFLOAD_STYLE=map\"" > "$CFG_MAP"
-CFG_SRC="$RUNS/mcp-sty-src-$REPO.json";   mkcfg ",\"HOMEGRAPH_OFFLOAD_USAGE_LOG=$USAGE\",\"HOMEGRAPH_OFFLOAD_STYLE=src\"" > "$CFG_SRC"
-
-echo "###### repo=$REPO reps=$START..$END model=${MODEL:-sonnet}/${EFFORT:-high} disallow=${DISALLOW:-<none>}"
-echo "###### Q=$Q"
-echo "== ARM raw ==";  prewarm "$TARGET" "HOMEGRAPH_OFFLOAD_DISABLE=1"
-for r in $(seq "$START" "$END"); do run raw  "$r" "$CFG_RAW"  "-"; done; kill_daemon
-echo "== ARM refs =="; prewarm "$TARGET" "HOMEGRAPH_OFFLOAD_USAGE_LOG=$USAGE"
-for r in $(seq "$START" "$END"); do run refs "$r" "$CFG_REFS" "$USAGE"; done; kill_daemon
-echo "== ARM map ==";  prewarm "$TARGET" "HOMEGRAPH_OFFLOAD_USAGE_LOG=$USAGE HOMEGRAPH_OFFLOAD_STYLE=map"
-for r in $(seq "$START" "$END"); do run map  "$r" "$CFG_MAP"  "$USAGE"; done; kill_daemon
-echo "== ARM src ==";  prewarm "$TARGET" "HOMEGRAPH_OFFLOAD_USAGE_LOG=$USAGE HOMEGRAPH_OFFLOAD_STYLE=src"
-for r in $(seq "$START" "$END"); do run src  "$r" "$CFG_SRC"  "$USAGE"; done; kill_daemon
+#!/usr/bin/env bash
+# Offload reasoning-OUTPUT-STYLE A/B — all homegraph-on, isolating the Worker's
+# output shape's effect on main-session tokens / latency / accuracy:
+#   raw  : HOMEGRAPH_OFFLOAD_DISABLE=1            (verbatim explore source, the floor)
+#   refs : managed offload, default              (Cerebras map re-expanded to verbatim, ~24K)
+#   map  : managed offload, STYLE=map            (compact reasoned map + file:line anchors, ~1-3K)
+#   src  : managed offload, STYLE=src            (map + cited line ranges only, ~1-5K)
+# Delegation BLOCKED by default (DISALLOW=Agent) so we measure the offload payload's
+# effect on the main Sonnet agent, not whether it spawns a Haiku Explore subagent.
+#
+# Usage: offload-eval-styles.sh <indexed-repo> <reps> "<question>"
+# Env:   RESULTS=<file>  AGENT_EVAL_OUT=<dir>  REP_START=1  DISALLOW=Agent  MODEL/EFFORT
+set -uo pipefail
+HERE="$(cd "$(dirname "$0")" && pwd)"
+ENGINE="$(cd "$HERE/../.." && pwd)"
+BIN="$ENGINE/dist/bin/homegraph.js"
+OUT="${AGENT_EVAL_OUT:-/tmp/cg-offload-eval}"
+TARGET="${1:?usage: offload-eval-styles.sh <indexed-repo> <reps> \"<question>\"}"
+REPS="${2:?reps}"; Q="${3:?question}"
+RUNS="$OUT/runs"; EXTRACT="$HERE/offload-eval-metrics.mjs"
+RESULTS="${RESULTS:-$OUT/results-styles.jsonl}"
+REPO=$(basename "$TARGET")
+DISALLOW="${DISALLOW-Agent}"   # default: block delegation. `DISALLOW= ` to allow.
+START="${REP_START:-1}"; END=$((START + REPS - 1))
+mkdir -p "$RUNS"
+command -v claude >/dev/null || { echo "no claude on PATH"; exit 1; }
+[ -d "$TARGET/.homegraph" ] || { echo "not indexed: $TARGET"; exit 1; }
+TARGET=$(cd "$TARGET" && pwd -P)
+
+prewarm() { # path  extra-env
+  pkill -9 -f "serve --mcp --path $1" 2>/dev/null; rm -f "$1/.homegraph/daemon.sock" 2>/dev/null; sleep 0.6
+  env ${2:-} HOMEGRAPH_DAEMON_IDLE_TIMEOUT_MS=1800000 node "$BIN" serve --mcp --path "$1" </dev/null >/dev/null 2>&1 &
+  node -e 'const fs=require("fs");let n=0;const t=setInterval(()=>{if(fs.existsSync(process.argv[1]+"/.homegraph/daemon.sock")){clearInterval(t);process.exit(0)}if(n++>150){clearInterval(t);process.exit(1)}},100)' "$1" \
+    && echo "  daemon warm" || echo "  WARN daemon never bound"
+}
+kill_daemon() { pkill -9 -f "serve --mcp --path $TARGET" 2>/dev/null; rm -f "$TARGET/.homegraph/daemon.sock" 2>/dev/null; sleep 1; }
+
+run() { # arm rep mcp-config usage-log-or-dash
+  local arm="$1" rep="$2" cfg="$3" usage="$4" tag="$REPO-$1-$2"
+  [ "$usage" != "-" ] && : > "$usage"
+  ( cd "$TARGET" && claude -p "$Q" \
+      --output-format stream-json --verbose --permission-mode bypassPermissions \
+      --model "${MODEL:-sonnet}" --effort "${EFFORT:-high}" --max-budget-usd 4 \
+      ${DISALLOW:+--disallowedTools "$DISALLOW"} \
+      --strict-mcp-config --mcp-config "$cfg" \
+      </dev/null > "$RUNS/$tag.jsonl" 2>"$RUNS/$tag.err" )
+  node "$EXTRACT" --run "$RUNS/$tag.jsonl" --usage "$usage" --arm "$arm" --rep "$rep" \
+      --repo "$REPO" --tier styles --q "$Q" >> "$RESULTS"
+  node -e 'const o=JSON.parse(require("fs").readFileSync(process.argv[1],"utf8").trim().split("\n").pop());console.log(`  [${o.arm} #${o.rep}] ${o.durationSec}s | ${o.tokBillable} billable tok | read=${o.read} grep=${o.grep} explore=${o.explore} offload=${o.offloadFired} | AI ${o.ai.calls}c/${o.ai.totalTokens}t | ok=${o.ok}`)' "$RESULTS"
+}
+
+# MCP configs: env baked into the daemon-spawn command claude uses.
+USAGE="$RUNS/$REPO-usage.jsonl"
+mkcfg() { # file extra-env-pairs(JSON array entries, comma-led or empty)
+  printf '{"mcpServers":{"homegraph":{"command":"env","args":["HOMEGRAPH_WASM_RELAUNCHED=1"%s,"node","%s","serve","--mcp","--path","%s"]}}}' "$1" "$BIN" "$TARGET"
+}
+CFG_RAW="$RUNS/mcp-sty-raw-$REPO.json";   mkcfg ',"HOMEGRAPH_OFFLOAD_DISABLE=1"' > "$CFG_RAW"
+CFG_REFS="$RUNS/mcp-sty-refs-$REPO.json"; mkcfg ",\"HOMEGRAPH_OFFLOAD_USAGE_LOG=$USAGE\"" > "$CFG_REFS"
+CFG_MAP="$RUNS/mcp-sty-map-$REPO.json";   mkcfg ",\"HOMEGRAPH_OFFLOAD_USAGE_LOG=$USAGE\",\"HOMEGRAPH_OFFLOAD_STYLE=map\"" > "$CFG_MAP"
+CFG_SRC="$RUNS/mcp-sty-src-$REPO.json";   mkcfg ",\"HOMEGRAPH_OFFLOAD_USAGE_LOG=$USAGE\",\"HOMEGRAPH_OFFLOAD_STYLE=src\"" > "$CFG_SRC"
+
+echo "###### repo=$REPO reps=$START..$END model=${MODEL:-sonnet}/${EFFORT:-high} disallow=${DISALLOW:-<none>}"
+echo "###### Q=$Q"
+echo "== ARM raw ==";  prewarm "$TARGET" "HOMEGRAPH_OFFLOAD_DISABLE=1"
+for r in $(seq "$START" "$END"); do run raw  "$r" "$CFG_RAW"  "-"; done; kill_daemon
+echo "== ARM refs =="; prewarm "$TARGET" "HOMEGRAPH_OFFLOAD_USAGE_LOG=$USAGE"
+for r in $(seq "$START" "$END"); do run refs "$r" "$CFG_REFS" "$USAGE"; done; kill_daemon
+echo "== ARM map ==";  prewarm "$TARGET" "HOMEGRAPH_OFFLOAD_USAGE_LOG=$USAGE HOMEGRAPH_OFFLOAD_STYLE=map"
+for r in $(seq "$START" "$END"); do run map  "$r" "$CFG_MAP"  "$USAGE"; done; kill_daemon
+echo "== ARM src ==";  prewarm "$TARGET" "HOMEGRAPH_OFFLOAD_USAGE_LOG=$USAGE HOMEGRAPH_OFFLOAD_STYLE=src"
+for r in $(seq "$START" "$END"); do run src  "$r" "$CFG_SRC"  "$USAGE"; done; kill_daemon
 echo "###### DONE $REPO — judge: node $HERE/offload-eval-judge.mjs --results $RESULTS --truth $HERE/offload-eval-ground-truth.json --out $OUT/judged-styles.jsonl"