homegraph 1.5.0 → 1.5.1

package/scripts/agent-eval/bench-readme.sh

@@ -1,28 +1,28 @@
-#!/usr/bin/env bash
-# Re-run the README "Benchmark Results" A/B (with vs without homegraph) on the
-# current build: the 7 README repos, same queries, RUNS per arm (default 4).
-# Output → /tmp/ab-readme/<repo>/run<n>/run-headless-{with,without}.jsonl
-# Aggregate with parse-bench-readme.mjs. Repos must be cloned + indexed under
-# $CORPUS (default /tmp/homegraph-corpus) by the build under test.
-set -uo pipefail
-H="$(cd "$(dirname "$0")" && pwd)"
-C="${CORPUS:-/tmp/homegraph-corpus}"
-RUNS="${RUNS:-4}"
-ROWS=(
-"vscode|How does the extension host communicate with the main process?"
-"excalidraw|How does Excalidraw render and update canvas elements?"
-"django|How does Django's ORM build and execute a query from a QuerySet?"
-"tokio|How does tokio schedule and run async tasks on its runtime?"
-"okhttp|How does OkHttp process a request through its interceptor chain?"
-"gin|How does gin route requests through its middleware chain?"
-"alamofire|How does Alamofire build, send, and validate a request?"
-)
-echo "### README A/B START $(date) RUNS=$RUNS"
-for row in "${ROWS[@]}"; do
-  repo="${row%%|*}"; q="${row#*|}"
-  echo "===== $repo ====="
-  for run in $(seq 1 "$RUNS"); do
-    AGENT_EVAL_OUT="/tmp/ab-readme/$repo/run$run" bash "$H/run-all.sh" "$C/$repo" "$q" headless 2>&1 | grep -E "exit [0-9]" || echo "  run$run: (no exit line)"
-  done
-done
-echo "### README A/B DONE $(date)"
+#!/usr/bin/env bash
+# Re-run the README "Benchmark Results" A/B (with vs without homegraph) on the
+# current build: the 7 README repos, same queries, RUNS per arm (default 4).
+# Output → /tmp/ab-readme/<repo>/run<n>/run-headless-{with,without}.jsonl
+# Aggregate with parse-bench-readme.mjs. Repos must be cloned + indexed under
+# $CORPUS (default /tmp/homegraph-corpus) by the build under test.
+set -uo pipefail
+H="$(cd "$(dirname "$0")" && pwd)"
+C="${CORPUS:-/tmp/homegraph-corpus}"
+RUNS="${RUNS:-4}"
+ROWS=(
+"vscode|How does the extension host communicate with the main process?"
+"excalidraw|How does Excalidraw render and update canvas elements?"
+"django|How does Django's ORM build and execute a query from a QuerySet?"
+"tokio|How does tokio schedule and run async tasks on its runtime?"
+"okhttp|How does OkHttp process a request through its interceptor chain?"
+"gin|How does gin route requests through its middleware chain?"
+"alamofire|How does Alamofire build, send, and validate a request?"
+)
+echo "### README A/B START $(date) RUNS=$RUNS"
+for row in "${ROWS[@]}"; do
+  repo="${row%%|*}"; q="${row#*|}"
+  echo "===== $repo ====="
+  for run in $(seq 1 "$RUNS"); do
+    AGENT_EVAL_OUT="/tmp/ab-readme/$repo/run$run" bash "$H/run-all.sh" "$C/$repo" "$q" headless 2>&1 | grep -E "exit [0-9]" || echo "  run$run: (no exit line)"
+  done
+done
+echo "### README A/B DONE $(date)"

package/scripts/agent-eval/bench-why-repo.sh

@@ -1,22 +1,22 @@
-#!/usr/bin/env bash
-# One README repo, WITH-homegraph only, N runs. Each run appends a why-Read
-# diagnostic so the agent explains any Read/Grep. (The WITHOUT baseline is
-# homegraph-independent and already in the README — no point re-running it.)
-# Output -> /tmp/ab-why/<repo>/with<n>.jsonl
-# Usage: bench-why-repo.sh <repo-path> "<query>" [N]
-set -uo pipefail
-REPO="$1"; Q="$2"; N="${3:-4}"
-NAME="$(basename "$REPO")"
-CG="/Users/colby/Development/Personal/homegraph/dist/bin/homegraph.js"
-OUT="/tmp/ab-why/$NAME"; mkdir -p "$OUT"
-WHY=$'\n\nIMPORTANT — diagnostic: if you use the Read or Grep tool at ANY point, for EACH such call explain why homegraph_explore / homegraph_node did not already give you what you needed. End your entire answer with a section titled exactly "## Why I read" listing every Read and Grep you made and the precise reason homegraph fell short for it. If you used neither, write "## Why I read" then "none — homegraph was sufficient."'
-printf '{"mcpServers":{"homegraph":{"command":"%s","args":["serve","--mcp","--path","%s"]}}}' "$CG" "$REPO" > "$OUT/cg.json"
-
-for i in $(seq 1 "$N"); do
-  pkill -f "serve --mcp" 2>/dev/null; sleep 1; rm -f "$REPO/.homegraph/daemon.sock"
-  ( cd "$REPO" && claude -p "$Q$WHY" --output-format stream-json --verbose \
-      --permission-mode bypassPermissions --model "${MODEL:-sonnet}" --effort "${EFFORT:-high}" --max-budget-usd 4 \
-      --strict-mcp-config --mcp-config "$OUT/cg.json" > "$OUT/with$i.jsonl" 2>"$OUT/with$i.err" )
-  echo "WITH run $i: exit $? ($(wc -l < "$OUT/with$i.jsonl" | tr -d ' ') lines)"
-done
-echo "DONE $NAME"
+#!/usr/bin/env bash
+# One README repo, WITH-homegraph only, N runs. Each run appends a why-Read
+# diagnostic so the agent explains any Read/Grep. (The WITHOUT baseline is
+# homegraph-independent and already in the README — no point re-running it.)
+# Output -> /tmp/ab-why/<repo>/with<n>.jsonl
+# Usage: bench-why-repo.sh <repo-path> "<query>" [N]
+set -uo pipefail
+REPO="$1"; Q="$2"; N="${3:-4}"
+NAME="$(basename "$REPO")"
+CG="/Users/colby/Development/Personal/homegraph/dist/bin/homegraph.js"
+OUT="/tmp/ab-why/$NAME"; mkdir -p "$OUT"
+WHY=$'\n\nIMPORTANT — diagnostic: if you use the Read or Grep tool at ANY point, for EACH such call explain why homegraph_explore / homegraph_node did not already give you what you needed. End your entire answer with a section titled exactly "## Why I read" listing every Read and Grep you made and the precise reason homegraph fell short for it. If you used neither, write "## Why I read" then "none — homegraph was sufficient."'
+printf '{"mcpServers":{"homegraph":{"command":"%s","args":["serve","--mcp","--path","%s"]}}}' "$CG" "$REPO" > "$OUT/cg.json"
+
+for i in $(seq 1 "$N"); do
+  pkill -f "serve --mcp" 2>/dev/null; sleep 1; rm -f "$REPO/.homegraph/daemon.sock"
+  ( cd "$REPO" && claude -p "$Q$WHY" --output-format stream-json --verbose \
+      --permission-mode bypassPermissions --model "${MODEL:-sonnet}" --effort "${EFFORT:-high}" --max-budget-usd 4 \
+      --strict-mcp-config --mcp-config "$OUT/cg.json" > "$OUT/with$i.jsonl" 2>"$OUT/with$i.err" )
+  echo "WITH run $i: exit $? ($(wc -l < "$OUT/with$i.jsonl" | tr -d ' ') lines)"
+done
+echo "DONE $NAME"

package/scripts/agent-eval/block-read-hook.sh

@@ -1,19 +1,19 @@
-#!/usr/bin/env bash
-# PreToolUse hook (experiment): deny Read of homegraph-indexed source files and
-# steer the agent to homegraph_explore/homegraph_node instead. Tests whether
-# homegraph can FULLY replace Read for code-understanding once the escape hatch
-# is removed. Non-source reads (config, .env, markdown, new files) pass through.
-#
-# Wire via:  claude ... --settings scripts/agent-eval/hook-settings.json
-set -uo pipefail
-input="$(cat)"
-fp="$(printf '%s' "$input" | jq -r '.tool_input.file_path // empty' 2>/dev/null)"
-
-case "$fp" in
-  *.ts|*.tsx|*.js|*.jsx|*.mjs|*.cjs|*.py|*.go|*.rs|*.java|*.rb|*.php|*.swift|*.kt|*.kts|*.c|*.cc|*.cpp|*.h|*.hpp|*.cs|*.lua|*.vue|*.svelte)
-    msg="Read is disabled for source files in this session — homegraph already has this file indexed (with line numbers, kept in sync on every change). Use homegraph_explore (several related symbols at once) or homegraph_node (one symbol's full source). If a symbol you need wasn't in a prior explore, run ANOTHER homegraph_explore with its exact name instead of reading the file."
-    jq -n --arg m "$msg" '{reason:$m, hookSpecificOutput:{hookEventName:"PreToolUse",permissionDecision:"deny",permissionDecisionReason:$m}}'
-    exit 0
-    ;;
-esac
-exit 0
+#!/usr/bin/env bash
+# PreToolUse hook (experiment): deny Read of homegraph-indexed source files and
+# steer the agent to homegraph_explore/homegraph_node instead. Tests whether
+# homegraph can FULLY replace Read for code-understanding once the escape hatch
+# is removed. Non-source reads (config, .env, markdown, new files) pass through.
+#
+# Wire via:  claude ... --settings scripts/agent-eval/hook-settings.json
+set -uo pipefail
+input="$(cat)"
+fp="$(printf '%s' "$input" | jq -r '.tool_input.file_path // empty' 2>/dev/null)"
+
+case "$fp" in
+  *.ts|*.tsx|*.js|*.jsx|*.mjs|*.cjs|*.py|*.go|*.rs|*.java|*.rb|*.php|*.swift|*.kt|*.kts|*.c|*.cc|*.cpp|*.h|*.hpp|*.cs|*.lua|*.vue|*.svelte)
+    msg="Read is disabled for source files in this session — homegraph already has this file indexed (with line numbers, kept in sync on every change). Use homegraph_explore (several related symbols at once) or homegraph_node (one symbol's full source). If a symbol you need wasn't in a prior explore, run ANOTHER homegraph_explore with its exact name instead of reading the file."
+    jq -n --arg m "$msg" '{reason:$m, hookSpecificOutput:{hookEventName:"PreToolUse",permissionDecision:"deny",permissionDecisionReason:$m}}'
+    exit 0
+    ;;
+esac
+exit 0

package/scripts/agent-eval/hook-settings.json

@@ -1,15 +1,15 @@
-{
-  "hooks": {
-    "PreToolUse": [
-      {
-        "matcher": "Read",
-        "hooks": [
-          {
-            "type": "command",
-            "command": "bash /Users/colby/Development/Personal/homegraph/scripts/agent-eval/block-read-hook.sh"
-          }
-        ]
-      }
-    ]
-  }
-}
+{
+  "hooks": {
+    "PreToolUse": [
+      {
+        "matcher": "Read",
+        "hooks": [
+          {
+            "type": "command",
+            "command": "bash /Users/colby/Development/Personal/homegraph/scripts/agent-eval/block-read-hook.sh"
+          }
+        ]
+      }
+    ]
+  }
+}

package/scripts/agent-eval/itrun.sh

@@ -1,120 +1,120 @@
-#!/usr/bin/env bash
-# Drive an INTERACTIVE Claude Code session in tmux, send a prompt, wait for the
-# agent to finish, then print the tool-call breakdown from the session logs.
-#
-# Why interactive (not `claude -p`): headless print-mode picks the
-# general-purpose subagent, while real interactive sessions delegate to the
-# Explore subagent (or drive homegraph from the main thread). Only the
-# interactive TUI reproduces the behavior users actually see. (Idle-detection
-# technique borrowed from devpit's WaitForIdle.)
-#
-# Usage: itrun.sh <repo-path> <label> "<prompt>"
-# Output dir: $AGENT_EVAL_OUT (default /tmp/agent-eval)
-# Requires: tmux 3.0+, a logged-in `claude` CLI, homegraph MCP configured.
-set -uo pipefail
-REPO="$1"; LABEL="$2"; PROMPT="$3"
-SESSION="cgt_${LABEL}"
-OUT_DIR="${AGENT_EVAL_OUT:-/tmp/agent-eval}"; mkdir -p "$OUT_DIR"
-OUT="$OUT_DIR/itrun-${LABEL}.txt"
-HERE="$(cd "$(dirname "$0")" && pwd)"
-
-cap() { tmux capture-pane -p -t "$SESSION" -S -40; }
-
-tmux kill-session -t "$SESSION" 2>/dev/null
-
-# Wide pane so the TUI doesn't hard-wrap tool lines.
-tmux new-session -d -s "$SESSION" -x 230 -y 60
-tmux send-keys -t "$SESSION" "cd $REPO && claude --dangerously-skip-permissions ${CLAUDE_EXTRA_ARGS:-}" Enter
-
-# Wait for the ❯ prompt (claude drew its UI), up to 60s. NOTE: ❯ appears on the
-# welcome screen seconds before the input actually accepts keystrokes, so this is
-# necessary but NOT sufficient — the type-and-verify loop below is what proves
-# the input is live.
-ready=0
-for _ in $(seq 1 120); do
-  cap | grep -q "❯" && { ready=1; break; }
-  sleep 0.5
-done
-[ "$ready" = 1 ] || { echo "claude never drew its UI"; cap; tmux kill-session -t "$SESSION" 2>/dev/null; exit 1; }
-
-# Accept the per-folder "Is this a project you trust?" dialog if it shows (first
-# time claude opens a given repo). Option 1 ("Yes, I trust this folder") is
-# pre-selected, so Enter accepts. This dialog also contains ❯, so it must be
-# cleared before the type-and-verify loop or keystrokes land on the menu.
-for _ in $(seq 1 20); do
-  cap | grep -q "trust this folder" || break
-  tmux send-keys -t "$SESSION" Enter
-  sleep 1
-done
-
-# Type-and-verify: send the prompt, confirm a distinctive chunk of it actually
-# landed in the input box, retry if it didn't (handles the early-❯ race where
-# the welcome screen shows the prompt glyph but MCP init is still eating keys).
-needle="${PROMPT:0:24}"
-typed=0
-for _ in $(seq 1 30); do
-  tmux send-keys -l -t "$SESSION" "$PROMPT"
-  sleep 1
-  if cap | grep -Fq "$needle"; then typed=1; break; fi
-  # Clear whatever partial text may have landed, then retry.
-  tmux send-keys -t "$SESSION" C-u
-  sleep 1
-done
-[ "$typed" = 1 ] || { echo "prompt never landed in the input box"; cap; tmux kill-session -t "$SESSION" 2>/dev/null; exit 1; }
-sleep 0.5
-tmux send-keys -t "$SESSION" Enter
-
-# Busy signals. The robust one is the spinner's elapsed-time-in-parens, which
-# EVERY working state shows — both the pre-stream thinking phase
-# "(8s · thinking with max effort)" and the streaming phase
-# "(24s · ↑ 2.5k tokens · …)", and it survives the 32s→"1m 3s" rollover. We OR
-# in the token arrows, "esc to interrupt", and "Initializing" as belt-and-braces
-# (some TUI versions/states show one but not the others).
-BUSY_RE='esc to interrupt|↓ [0-9]|↑ [0-9]|Initializing|\(([0-9]+m )?[0-9]+s ·'
-
-# Wait for work to START (busy indicator appears), up to 60s. If it never starts,
-# fail loudly rather than silently reporting an empty run.
-started=0
-for _ in $(seq 1 120); do
-  cap | grep -qE "$BUSY_RE" && { started=1; break; }
-  sleep 0.5
-done
-[ "$started" = 1 ] || { echo "agent never started working"; cap; tmux kill-session -t "$SESSION" 2>/dev/null; exit 1; }
-
-# Poll for idle. CRITICAL: Opus 4.8 (extended thinking) renders NO spinner /
-# "esc to interrupt" / timer while it STREAMS its final answer — those appear
-# only during the thinking + tool-use phases ("✻ Marinating… (32s · ↓ 1.3k
-# tokens · thinking with max effort)"). So BUSY_RE reads "not busy" for the whole
-# 10-30s answer stream, and any short not-busy threshold kills the run mid-answer
-# (the truncation bug). We therefore detect "done" by CONTENT STABILITY, not by a
-# spinner string: while the agent streams, the captured pane changes every poll,
-# so stability never accrues; it accrues only once the agent has finished and the
-# static "✻ Brewed for 1m 9s" summary is all that is left. BUSY_RE still hard-
-# resets stability (covers thinking/tool-use/live-timer, where text can briefly
-# sit still). Need STABLE_NEEDED polls (~8s) of zero pane change + ❯ present.
-# Content-stability is model-agnostic — it survives future spinner re-wordings.
-STABLE_NEEDED=16
-prev=""; stable=0
-for _ in $(seq 1 2400); do            # up to ~20 min
-  pane="$(cap)"
-  sig="$(printf '%s' "$pane" | tr -s '[:space:]' ' ')"
-  if printf '%s' "$pane" | grep -qE "$BUSY_RE"; then
-    stable=0                          # thinking / tool use / live timer → busy
-  elif [ -n "$sig" ] && [ "$sig" = "$prev" ] && printf '%s' "$pane" | grep -q "❯"; then
-    stable=$((stable+1)); [ "$stable" -ge "$STABLE_NEEDED" ] && break
-  else
-    stable=0                          # answer still streaming → pane changing
-  fi
-  prev="$sig"
-  sleep 0.5
-done
-sleep 1
-
-tmux capture-pane -p -t "$SESSION" -S - > "$OUT"
-echo "captured $(wc -l < "$OUT") lines -> $OUT"
-grep -oE "Done \([^)]*\)|[A-Z][a-z]+ for ([0-9]+m )?[0-9]+s" "$OUT" | tail -1
-grep -oE "[0-9.]+k?/[0-9.]+M" "$OUT" | tail -1 | sed 's/^/Context /'
-tmux kill-session -t "$SESSION" 2>/dev/null
-
-# Clean tool breakdown from the session logs (main + subagents).
-node "$HERE/parse-session.mjs" "$REPO" 2>/dev/null || true
+#!/usr/bin/env bash
+# Drive an INTERACTIVE Claude Code session in tmux, send a prompt, wait for the
+# agent to finish, then print the tool-call breakdown from the session logs.
+#
+# Why interactive (not `claude -p`): headless print-mode picks the
+# general-purpose subagent, while real interactive sessions delegate to the
+# Explore subagent (or drive homegraph from the main thread). Only the
+# interactive TUI reproduces the behavior users actually see. (Idle-detection
+# technique borrowed from devpit's WaitForIdle.)
+#
+# Usage: itrun.sh <repo-path> <label> "<prompt>"
+# Output dir: $AGENT_EVAL_OUT (default /tmp/agent-eval)
+# Requires: tmux 3.0+, a logged-in `claude` CLI, homegraph MCP configured.
+set -uo pipefail
+REPO="$1"; LABEL="$2"; PROMPT="$3"
+SESSION="cgt_${LABEL}"
+OUT_DIR="${AGENT_EVAL_OUT:-/tmp/agent-eval}"; mkdir -p "$OUT_DIR"
+OUT="$OUT_DIR/itrun-${LABEL}.txt"
+HERE="$(cd "$(dirname "$0")" && pwd)"
+
+cap() { tmux capture-pane -p -t "$SESSION" -S -40; }
+
+tmux kill-session -t "$SESSION" 2>/dev/null
+
+# Wide pane so the TUI doesn't hard-wrap tool lines.
+tmux new-session -d -s "$SESSION" -x 230 -y 60
+tmux send-keys -t "$SESSION" "cd $REPO && claude --dangerously-skip-permissions ${CLAUDE_EXTRA_ARGS:-}" Enter
+
+# Wait for the ❯ prompt (claude drew its UI), up to 60s. NOTE: ❯ appears on the
+# welcome screen seconds before the input actually accepts keystrokes, so this is
+# necessary but NOT sufficient — the type-and-verify loop below is what proves
+# the input is live.
+ready=0
+for _ in $(seq 1 120); do
+  cap | grep -q "❯" && { ready=1; break; }
+  sleep 0.5
+done
+[ "$ready" = 1 ] || { echo "claude never drew its UI"; cap; tmux kill-session -t "$SESSION" 2>/dev/null; exit 1; }
+
+# Accept the per-folder "Is this a project you trust?" dialog if it shows (first
+# time claude opens a given repo). Option 1 ("Yes, I trust this folder") is
+# pre-selected, so Enter accepts. This dialog also contains ❯, so it must be
+# cleared before the type-and-verify loop or keystrokes land on the menu.
+for _ in $(seq 1 20); do
+  cap | grep -q "trust this folder" || break
+  tmux send-keys -t "$SESSION" Enter
+  sleep 1
+done
+
+# Type-and-verify: send the prompt, confirm a distinctive chunk of it actually
+# landed in the input box, retry if it didn't (handles the early-❯ race where
+# the welcome screen shows the prompt glyph but MCP init is still eating keys).
+needle="${PROMPT:0:24}"
+typed=0
+for _ in $(seq 1 30); do
+  tmux send-keys -l -t "$SESSION" "$PROMPT"
+  sleep 1
+  if cap | grep -Fq "$needle"; then typed=1; break; fi
+  # Clear whatever partial text may have landed, then retry.
+  tmux send-keys -t "$SESSION" C-u
+  sleep 1
+done
+[ "$typed" = 1 ] || { echo "prompt never landed in the input box"; cap; tmux kill-session -t "$SESSION" 2>/dev/null; exit 1; }
+sleep 0.5
+tmux send-keys -t "$SESSION" Enter
+
+# Busy signals. The robust one is the spinner's elapsed-time-in-parens, which
+# EVERY working state shows — both the pre-stream thinking phase
+# "(8s · thinking with max effort)" and the streaming phase
+# "(24s · ↑ 2.5k tokens · …)", and it survives the 32s→"1m 3s" rollover. We OR
+# in the token arrows, "esc to interrupt", and "Initializing" as belt-and-braces
+# (some TUI versions/states show one but not the others).
+BUSY_RE='esc to interrupt|↓ [0-9]|↑ [0-9]|Initializing|\(([0-9]+m )?[0-9]+s ·'
+
+# Wait for work to START (busy indicator appears), up to 60s. If it never starts,
+# fail loudly rather than silently reporting an empty run.
+started=0
+for _ in $(seq 1 120); do
+  cap | grep -qE "$BUSY_RE" && { started=1; break; }
+  sleep 0.5
+done
+[ "$started" = 1 ] || { echo "agent never started working"; cap; tmux kill-session -t "$SESSION" 2>/dev/null; exit 1; }
+
+# Poll for idle. CRITICAL: Opus 4.8 (extended thinking) renders NO spinner /
+# "esc to interrupt" / timer while it STREAMS its final answer — those appear
+# only during the thinking + tool-use phases ("✻ Marinating… (32s · ↓ 1.3k
+# tokens · thinking with max effort)"). So BUSY_RE reads "not busy" for the whole
+# 10-30s answer stream, and any short not-busy threshold kills the run mid-answer
+# (the truncation bug). We therefore detect "done" by CONTENT STABILITY, not by a
+# spinner string: while the agent streams, the captured pane changes every poll,
+# so stability never accrues; it accrues only once the agent has finished and the
+# static "✻ Brewed for 1m 9s" summary is all that is left. BUSY_RE still hard-
+# resets stability (covers thinking/tool-use/live-timer, where text can briefly
+# sit still). Need STABLE_NEEDED polls (~8s) of zero pane change + ❯ present.
+# Content-stability is model-agnostic — it survives future spinner re-wordings.
+STABLE_NEEDED=16
+prev=""; stable=0
+for _ in $(seq 1 2400); do            # up to ~20 min
+  pane="$(cap)"
+  sig="$(printf '%s' "$pane" | tr -s '[:space:]' ' ')"
+  if printf '%s' "$pane" | grep -qE "$BUSY_RE"; then
+    stable=0                          # thinking / tool use / live timer → busy
+  elif [ -n "$sig" ] && [ "$sig" = "$prev" ] && printf '%s' "$pane" | grep -q "❯"; then
+    stable=$((stable+1)); [ "$stable" -ge "$STABLE_NEEDED" ] && break
+  else
+    stable=0                          # answer still streaming → pane changing
+  fi
+  prev="$sig"
+  sleep 0.5
+done
+sleep 1
+
+tmux capture-pane -p -t "$SESSION" -S - > "$OUT"
+echo "captured $(wc -l < "$OUT") lines -> $OUT"
+grep -oE "Done \([^)]*\)|[A-Z][a-z]+ for ([0-9]+m )?[0-9]+s" "$OUT" | tail -1
+grep -oE "[0-9.]+k?/[0-9.]+M" "$OUT" | tail -1 | sed 's/^/Context /'
+tmux kill-session -t "$SESSION" 2>/dev/null
+
+# Clean tool breakdown from the session logs (main + subagents).
+node "$HERE/parse-session.mjs" "$REPO" 2>/dev/null || true

package/scripts/agent-eval/offload-eval-3arm.sh

@@ -1,72 +1,72 @@
-#!/usr/bin/env bash
-# 3-arm offload eval for ONE indexed repo + ONE question, n reps each.
-#   ARM offload : homegraph attached, managed offload ON  (per-run AI usage log)
-#   ARM raw     : homegraph attached, HOMEGRAPH_OFFLOAD_DISABLE=1 (raw source)
-#   ARM nocg    : no homegraph (empty MCP config) -> Read/Grep baseline
-# All arms: claude -p sonnet --effort high. One JSON metrics line/run -> $RESULTS.
-#
-# Usage: offload-eval-3arm.sh <indexed-repo> <tier> <reps> "<question>"
-# Env:   MODEL=sonnet EFFORT=high  RESULTS=<file>  AGENT_EVAL_OUT=<scratch dir>
-set -uo pipefail
-HERE="$(cd "$(dirname "$0")" && pwd)"
-ENGINE="$(cd "$HERE/../.." && pwd)"
-BIN="$ENGINE/dist/bin/homegraph.js"
-OUT="${AGENT_EVAL_OUT:-/tmp/cg-offload-eval}"
-TARGET="${1:?usage: offload-eval-3arm.sh <indexed-repo> <tier> <reps> \"<question>\"}"
-TIER="${2:?tier}"; REPS="${3:?reps}"; Q="${4:?question}"
-RUNS="$OUT/runs"
-EXTRACT="$HERE/offload-eval-metrics.mjs"
-RESULTS="${RESULTS:-$OUT/results.jsonl}"
-REPO=$(basename "$TARGET")
-mkdir -p "$RUNS"
-command -v claude >/dev/null || { echo "no claude on PATH"; exit 1; }
-[ -d "$TARGET/.homegraph" ] || { echo "not indexed: $TARGET (run offload-eval-setup.sh first)"; exit 1; }
-# Physical path so pkill matches the daemon's real cmdline (macOS /tmp->/private/tmp symlink
-# otherwise makes the kill miss the daemon, and the next arm connects to the SURVIVING daemon
-# — contaminating the raw arm with offload).
-TARGET=$(cd "$TARGET" && pwd -P)
-
-prewarm() { # path  extra-env (e.g. "FOO=bar")
-  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"
-}
-
-run() { # arm rep mcp-config usage-log-or-dash
-  local arm="$1" rep="$2" cfg="$3" usage="$4" tag="$REPO-$1-$2"
-  [ "$usage" != "-" ] && : > "$usage"
-  # DISALLOW (optional): block sub-agent delegation across all arms so the A/B
-  # measures the retrieval mode, not whether Sonnet decides to spawn a homegraph-blind
-  # Explore subagent (which thrashes regardless and adds huge variance).
-  ( cd "$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 "$TIER" --q "$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"
-}
-
-CFG_OFF="$RUNS/mcp-offload-$REPO.json"; CFG_RAW="$RUNS/mcp-raw-$REPO.json"; CFG_NOCG="$RUNS/mcp-nocg.json"
-USAGE="$RUNS/$REPO-usage.jsonl"
-printf '{"mcpServers":{"homegraph":{"command":"env","args":["HOMEGRAPH_WASM_RELAUNCHED=1","HOMEGRAPH_OFFLOAD_USAGE_LOG=%s","node","%s","serve","--mcp","--path","%s"]}}}' "$USAGE" "$BIN" "$TARGET" > "$CFG_OFF"
-printf '{"mcpServers":{"homegraph":{"command":"env","args":["HOMEGRAPH_WASM_RELAUNCHED=1","HOMEGRAPH_OFFLOAD_DISABLE=1","node","%s","serve","--mcp","--path","%s"]}}}' "$BIN" "$TARGET" > "$CFG_RAW"
-printf '{"mcpServers":{}}' > "$CFG_NOCG"
-
-# REP_START lets a later batch ADD reps without clobbering earlier jsonls
-# (e.g. REP_START=4 REPS=3 -> reps 4,5,6; default starts at 1).
-START="${REP_START:-1}"; END=$((START + REPS - 1))
-echo "###### repo=$REPO tier=$TIER reps=$START..$END model=${MODEL:-sonnet}/${EFFORT:-high}"
-echo "###### Q=$Q"
-echo "== ARM offload =="; prewarm "$TARGET" "HOMEGRAPH_OFFLOAD_USAGE_LOG=$USAGE"
-for r in $(seq "$START" "$END"); do run offload "$r" "$CFG_OFF" "$USAGE"; done
-pkill -9 -f "serve --mcp --path $TARGET" 2>/dev/null; rm -f "$TARGET/.homegraph/daemon.sock" 2>/dev/null; sleep 1
-echo "== ARM raw =="; prewarm "$TARGET" "HOMEGRAPH_OFFLOAD_DISABLE=1"
-for r in $(seq "$START" "$END"); do run raw "$r" "$CFG_RAW" "-"; done
-pkill -9 -f "serve --mcp --path $TARGET" 2>/dev/null; rm -f "$TARGET/.homegraph/daemon.sock" 2>/dev/null; sleep 1
-echo "== ARM nocg =="
-for r in $(seq "$START" "$END"); do run nocg "$r" "$CFG_NOCG" "-"; done
-echo "###### DONE $REPO"
+#!/usr/bin/env bash
+# 3-arm offload eval for ONE indexed repo + ONE question, n reps each.
+#   ARM offload : homegraph attached, managed offload ON  (per-run AI usage log)
+#   ARM raw     : homegraph attached, HOMEGRAPH_OFFLOAD_DISABLE=1 (raw source)
+#   ARM nocg    : no homegraph (empty MCP config) -> Read/Grep baseline
+# All arms: claude -p sonnet --effort high. One JSON metrics line/run -> $RESULTS.
+#
+# Usage: offload-eval-3arm.sh <indexed-repo> <tier> <reps> "<question>"
+# Env:   MODEL=sonnet EFFORT=high  RESULTS=<file>  AGENT_EVAL_OUT=<scratch dir>
+set -uo pipefail
+HERE="$(cd "$(dirname "$0")" && pwd)"
+ENGINE="$(cd "$HERE/../.." && pwd)"
+BIN="$ENGINE/dist/bin/homegraph.js"
+OUT="${AGENT_EVAL_OUT:-/tmp/cg-offload-eval}"
+TARGET="${1:?usage: offload-eval-3arm.sh <indexed-repo> <tier> <reps> \"<question>\"}"
+TIER="${2:?tier}"; REPS="${3:?reps}"; Q="${4:?question}"
+RUNS="$OUT/runs"
+EXTRACT="$HERE/offload-eval-metrics.mjs"
+RESULTS="${RESULTS:-$OUT/results.jsonl}"
+REPO=$(basename "$TARGET")
+mkdir -p "$RUNS"
+command -v claude >/dev/null || { echo "no claude on PATH"; exit 1; }
+[ -d "$TARGET/.homegraph" ] || { echo "not indexed: $TARGET (run offload-eval-setup.sh first)"; exit 1; }
+# Physical path so pkill matches the daemon's real cmdline (macOS /tmp->/private/tmp symlink
+# otherwise makes the kill miss the daemon, and the next arm connects to the SURVIVING daemon
+# — contaminating the raw arm with offload).
+TARGET=$(cd "$TARGET" && pwd -P)
+
+prewarm() { # path  extra-env (e.g. "FOO=bar")
+  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"
+}
+
+run() { # arm rep mcp-config usage-log-or-dash
+  local arm="$1" rep="$2" cfg="$3" usage="$4" tag="$REPO-$1-$2"
+  [ "$usage" != "-" ] && : > "$usage"
+  # DISALLOW (optional): block sub-agent delegation across all arms so the A/B
+  # measures the retrieval mode, not whether Sonnet decides to spawn a homegraph-blind
+  # Explore subagent (which thrashes regardless and adds huge variance).
+  ( cd "$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 "$TIER" --q "$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"
+}
+
+CFG_OFF="$RUNS/mcp-offload-$REPO.json"; CFG_RAW="$RUNS/mcp-raw-$REPO.json"; CFG_NOCG="$RUNS/mcp-nocg.json"
+USAGE="$RUNS/$REPO-usage.jsonl"
+printf '{"mcpServers":{"homegraph":{"command":"env","args":["HOMEGRAPH_WASM_RELAUNCHED=1","HOMEGRAPH_OFFLOAD_USAGE_LOG=%s","node","%s","serve","--mcp","--path","%s"]}}}' "$USAGE" "$BIN" "$TARGET" > "$CFG_OFF"
+printf '{"mcpServers":{"homegraph":{"command":"env","args":["HOMEGRAPH_WASM_RELAUNCHED=1","HOMEGRAPH_OFFLOAD_DISABLE=1","node","%s","serve","--mcp","--path","%s"]}}}' "$BIN" "$TARGET" > "$CFG_RAW"
+printf '{"mcpServers":{}}' > "$CFG_NOCG"
+
+# REP_START lets a later batch ADD reps without clobbering earlier jsonls
+# (e.g. REP_START=4 REPS=3 -> reps 4,5,6; default starts at 1).
+START="${REP_START:-1}"; END=$((START + REPS - 1))
+echo "###### repo=$REPO tier=$TIER reps=$START..$END model=${MODEL:-sonnet}/${EFFORT:-high}"
+echo "###### Q=$Q"
+echo "== ARM offload =="; prewarm "$TARGET" "HOMEGRAPH_OFFLOAD_USAGE_LOG=$USAGE"
+for r in $(seq "$START" "$END"); do run offload "$r" "$CFG_OFF" "$USAGE"; done
+pkill -9 -f "serve --mcp --path $TARGET" 2>/dev/null; rm -f "$TARGET/.homegraph/daemon.sock" 2>/dev/null; sleep 1
+echo "== ARM raw =="; prewarm "$TARGET" "HOMEGRAPH_OFFLOAD_DISABLE=1"
+for r in $(seq "$START" "$END"); do run raw "$r" "$CFG_RAW" "-"; done
+pkill -9 -f "serve --mcp --path $TARGET" 2>/dev/null; rm -f "$TARGET/.homegraph/daemon.sock" 2>/dev/null; sleep 1
+echo "== ARM nocg =="
+for r in $(seq "$START" "$END"); do run nocg "$r" "$CFG_NOCG" "-"; done
+echo "###### DONE $REPO"