@saluzi/codegraph 0.1.0 → 0.2.1

package/scripts/agent-eval/ab-hook.sh

@@ -0,0 +1,86 @@
+#!/usr/bin/env bash
+# A/B the PreToolUse(Read) REDIRECT hook (P1): does steering Read → codegraph_node
+# file-view actually move the agent off Read during implementation? BOTH arms use
+# the CURRENT build with codegraph attached and pre-warmed; the only difference is
+# the hook. Isolates the hook's behavioral effect from the build/file-view change
+# (use ab-new-vs-baseline.sh for the build A/B).
+#
+#   arm [nohook] — codegraph on, no hook   (does the better file-view get picked on its own?)
+#   arm [hook]   — codegraph on, + redirect hook   (does routing close it?)
+#
+# Reliable attach (works nested): each arm pre-warms a persistent daemon and skips
+# the startup re-exec (CODEGRAPH_WASM_RELAUNCHED=1), so claude connects before the
+# agent's first turn. Judge by ACTUAL codegraph usage in parse-run.mjs's "by type",
+# not claude's init snapshot (which can read pending even when it then connects).
+#
+# Usage: ab-hook.sh <indexed-repo> "<implementation task>" [runs-per-arm]
+#   <indexed-repo>  a repo with a .codegraph index (copied per arm; never mutated)
+#   "<task>"        a GENUINELY-NEW implementation task (verify it isn't already done)
+#   [runs-per-arm]  default 2 (n=1 is noisy — the doctrine says >=2)
+# Env: AGENT_EVAL_OUT (default: /tmp/ab-hook)
+set -uo pipefail
+
+TARGET="${1:?usage: ab-hook.sh <indexed-repo> \"<task>\" [runs-per-arm]}"
+TASK="${2:?task required}"
+RUNS="${3:-2}"
+ENGINE="$(cd "$(dirname "$0")/../.." && pwd)"
+BIN="$ENGINE/dist/bin/codegraph.js"
+HOOK="$ENGINE/scripts/agent-eval/redirect-read-hook.sh"
+OUT="${AGENT_EVAL_OUT:-/tmp/ab-hook}"
+PARSE="$ENGINE/scripts/agent-eval/parse-run.mjs"
+
+command -v claude >/dev/null || { echo "claude CLI not on PATH"; exit 1; }
+command -v jq >/dev/null || { echo "jq not on PATH (the hook needs it)"; exit 1; }
+[ -d "$TARGET/.codegraph" ] || { echo "target not indexed: run 'codegraph init $TARGET' first"; exit 1; }
+chmod +x "$HOOK"
+
+cleanup() { pkill -9 -f "serve --mcp --path $OUT/" 2>/dev/null; }
+trap cleanup EXIT
+
+mkdir -p "$OUT"
+echo "###### engine=$ENGINE"
+echo "###### target=$TARGET   runs/arm=$RUNS"
+echo "###### task=$TASK"
+echo
+
+( cd "$ENGINE" && npm run build >/dev/null 2>&1 ) && echo "built"
+
+# A settings file carrying ONLY the PreToolUse(Read) redirect hook.
+HOOK_SETTINGS="$OUT/hook-settings.json"
+jq -n --arg cmd "bash $HOOK" \
+  '{hooks:{PreToolUse:[{matcher:"Read",hooks:[{type:"command",command:$cmd}]}]}}' > "$HOOK_SETTINGS"
+
+prewarm() { # target — spawn a persistent daemon and wait for its socket
+  pkill -9 -f "serve --mcp --path $1" 2>/dev/null
+  CODEGRAPH_DAEMON_IDLE_TIMEOUT_MS=1800000 node "$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]+"/.codegraph/daemon.sock")){clearInterval(t);process.exit(0)}if(n++>150){clearInterval(t);process.exit(1)}},100)' "$1" \
+    && echo "  daemon warm: $1" || echo "  WARN: daemon never bound for $1"
+}
+
+run_one() { # arm-label, run-index, use-hook(0|1)
+  local label="$1" idx="$2" hook="$3"
+  local tgt="$OUT/t-$label-$idx" c="$OUT/mcp-$label.json"
+  rm -rf "$tgt"
+  rsync -a --exclude node_modules --exclude .git --exclude dist --exclude .codegraph "$TARGET/" "$tgt/"
+  node "$BIN" init "$tgt" >/dev/null 2>&1
+  printf '{"mcpServers":{"codegraph":{"command":"env","args":["CODEGRAPH_WASM_RELAUNCHED=1","node","%s","serve","--mcp","--path","%s"]}}}' "$BIN" "$tgt" > "$c"
+  prewarm "$tgt"
+  local extra=()
+  [ "$hook" = "1" ] && extra=(--settings "$HOOK_SETTINGS")
+  echo "----- [$label] run $idx -----"
+  # ${extra[@]+...} guard: bash 3.2 (macOS) under `set -u` errors on an empty
+  # array expansion otherwise, which would skip the no-hook arm's claude run.
+  ( cd "$tgt" && claude -p "$TASK" \
+      --output-format stream-json --verbose --permission-mode bypassPermissions \
+      --model "${MODEL:-sonnet}" --effort "${EFFORT:-high}" --max-budget-usd 4 --strict-mcp-config --mcp-config "$c" ${extra[@]+"${extra[@]}"} \
+      </dev/null > "$OUT/run-$label-$idx.jsonl" 2>"$OUT/run-$label-$idx.err" )
+  node "$PARSE" "$OUT/run-$label-$idx.jsonl" 2>&1 | grep -E "by type|Result" || echo "  (parse failed — see $OUT/run-$label-$idx.jsonl)"
+  pkill -9 -f "serve --mcp --path $tgt" 2>/dev/null
+  echo
+}
+
+for i in $(seq 1 "$RUNS"); do run_one nohook "$i" 0; done
+for i in $(seq 1 "$RUNS"); do run_one hook   "$i" 1; done
+
+echo "###### DONE. Compare [nohook] vs [hook] 'by type' — Read should fall and"
+echo "###### mcp__codegraph__codegraph_node should rise in the [hook] arm. Logs: $OUT"

package/scripts/agent-eval/ab-impl.sh

@@ -0,0 +1,78 @@
+#!/usr/bin/env bash
+# Sufficiency A/B for an IMPLEMENTATION task (the agent edits): when it uses
+# codegraph (explore/node) to understand before editing, does it still Read? Like
+# ab-sufficiency.sh but copies+indexes a FRESH target per run (the agent mutates
+# it), so runs don't see each other's edits.
+#
+# WITH codegraph (pre-warmed) vs WITHOUT (empty MCP), N runs each. Reports
+# explore/node vs Read/Grep + the files Read, and whether the build still passes.
+#
+# Usage: ab-impl.sh <indexed-repo> "<task>" [runs] [build-cmd]
+# Env: AGENT_EVAL_OUT (default: /tmp/ab-impl)
+set -uo pipefail
+REPO="${1:?usage: ab-impl.sh <indexed-repo> \"<task>\" [runs] [build-cmd]}"
+Q="${2:?task required}"
+RUNS="${3:-2}"
+BUILD_CMD="${4:-}"
+ENGINE="$(cd "$(dirname "$0")/../.." && pwd)"
+BIN="$ENGINE/dist/bin/codegraph.js"
+OUT="${AGENT_EVAL_OUT:-/tmp/ab-impl}"
+command -v claude >/dev/null || { echo "claude CLI not on PATH"; exit 1; }
+[ -d "$REPO/.codegraph" ] || { echo "no .codegraph index at $REPO"; exit 1; }
+cleanup(){ pkill -9 -f "serve --mcp --path $OUT/" 2>/dev/null; }
+trap cleanup EXIT
+mkdir -p "$OUT"
+( cd "$ENGINE" && npm run build >/dev/null 2>&1 ) && echo "built engine"
+echo "###### repo=$REPO  runs/arm=$RUNS"
+echo "###### task=$Q"; echo
+echo '{"mcpServers":{}}' > "$OUT/mcp-empty.json"
+
+prewarm(){
+  pkill -9 -f "serve --mcp --path $1" 2>/dev/null
+  CODEGRAPH_DAEMON_IDLE_TIMEOUT_MS=1800000 node "$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]+"/.codegraph/daemon.sock")){clearInterval(t);process.exit(0)}if(n++>150){clearInterval(t);process.exit(1)}},100)' "$1" >/dev/null 2>&1
+}
+
+analyze(){
+  node -e '
+    const fs=require("fs");
+    const L=fs.readFileSync(process.argv[1],"utf8").split("\n").filter(Boolean);
+    let ex=0,nf=0,ns=0,oc=0,gr=0,ed=0,exposed="?";const reads=[];
+    for(const l of L){try{const o=JSON.parse(l);
+      if(o.type==="system"&&o.subtype==="init")exposed=(o.tools||[]).filter(t=>/codegraph/.test(t)).length;
+      for(const b of (o.message?.content||[])){if(b.type!=="tool_use")continue;
+        if(b.name==="mcp__codegraph__codegraph_explore")ex++;
+        else if(b.name==="mcp__codegraph__codegraph_node"){if(b.input&&b.input.symbol)ns++;else nf++;}
+        else if(/mcp__codegraph__/.test(b.name))oc++;
+        else if(b.name==="Read")reads.push((b.input?.file_path||"").split("/").pop());
+        else if(b.name==="Grep")gr++;
+        else if(b.name==="Edit"||b.name==="Write")ed++;
+      }}catch{}}
+    console.log(`    explore=${ex} node[sym]=${ns} node[file]=${nf} other_cg=${oc} | Read=${reads.length}${reads.length?" ("+reads.join(", ")+")":""} Grep=${gr} Edit=${ed}  [cg exposed=${exposed}]`);
+  ' "$1"
+}
+
+run(){ # label, withCodegraph(0/1)
+  local label="$1" wcg="$2"
+  for i in $(seq 1 "$RUNS"); do
+    local tgt="$OUT/t-$label-$i" cfg="$OUT/mcp-$label.json"
+    rm -rf "$tgt"
+    rsync -a --exclude node_modules --exclude .git --exclude dist --exclude .codegraph "$REPO/" "$tgt/"
+    node "$BIN" init "$tgt" >/dev/null 2>&1
+    if [ "$wcg" = "1" ]; then
+      printf '{"mcpServers":{"codegraph":{"command":"env","args":["CODEGRAPH_WASM_RELAUNCHED=1","node","%s","serve","--mcp","--path","%s"]}}}' "$BIN" "$tgt" > "$cfg"
+      prewarm "$tgt"
+    else cp "$OUT/mcp-empty.json" "$cfg"; fi
+    ( cd "$tgt" && claude -p "$Q" --output-format stream-json --verbose \
+        --permission-mode bypassPermissions --model "${MODEL:-sonnet}" --effort "${EFFORT:-high}" --max-budget-usd 4 \
+        --strict-mcp-config --mcp-config "$cfg" </dev/null > "$OUT/$label-$i.jsonl" 2>"$OUT/$label-$i.err" )
+    echo "[$label] run $i:"; analyze "$OUT/$label-$i.jsonl"
+    if [ -n "$BUILD_CMD" ]; then ( cd "$tgt" && eval "$BUILD_CMD" >/dev/null 2>&1 && echo "      build: PASS" || echo "      build: FAIL" ); fi
+    pkill -9 -f "serve --mcp --path $tgt" 2>/dev/null
+  done
+  echo
+}
+
+echo "== WITH codegraph =="; run with 1
+echo "== WITHOUT (Read/Grep only) =="; run without 0
+echo "###### DONE: $OUT"

package/scripts/agent-eval/ab-new-vs-baseline.sh

@@ -0,0 +1,102 @@
+#!/usr/bin/env bash
+# A/B a codegraph retrieval/steering change: the NEW build (current HEAD) vs a
+# BASELINE build (a git ref) — BOTH with codegraph attached — on the same
+# implementation task, measuring how many Read vs codegraph calls the agent
+# makes. ISOLATES the change (unlike run-all.sh's with-vs-without). The agent
+# works on a throwaway copy of the target, so your repos are never touched.
+#
+# Reliable attach (works even when this is itself run nested inside a Claude
+# session): each arm PRE-WARMS a persistent codegraph daemon for its target so
+# claude connects to an already-bound, index-loaded daemon instantly — before
+# the agent's first turn — and SKIPS codegraph's startup re-exec via
+# CODEGRAPH_WASM_RELAUNCHED=1. Without this, on a multi-step task the agent
+# dives into Read/grep before codegraph finishes its ~2-3s startup (worse under
+# the CPU contention of a nested run) and runs with NO codegraph.
+#
+# Gotcha: claude's `system/init` snapshot can read status:"pending" / 0 tools
+# even when the server then connects fine — judge by ACTUAL codegraph usage in
+# parse-run.mjs's "by type", not the init line.
+#
+# Usage: ab-new-vs-baseline.sh <indexed-repo> "<task>" [baseline-ref]
+#   <indexed-repo>  a repo with a .codegraph index (copied per arm)
+#   "<task>"        an implementation task, e.g. "Add X to Y and wire it through"
+#   [baseline-ref]  git ref for the BEFORE build (default: HEAD~1)
+# Env: AGENT_EVAL_OUT (default: /tmp/ab-new-vs-baseline)
+set -uo pipefail
+
+TARGET="${1:?usage: ab-new-vs-baseline.sh <indexed-repo> \"<task>\" [baseline-ref]}"
+TASK="${2:?task required}"
+BASE_REF="${3:-HEAD~1}"
+ENGINE="$(cd "$(dirname "$0")/../.." && pwd)"
+BIN="$ENGINE/dist/bin/codegraph.js"
+OUT="${AGENT_EVAL_OUT:-/tmp/ab-new-vs-baseline}"
+PARSE="$ENGINE/scripts/agent-eval/parse-run.mjs"
+
+command -v claude >/dev/null || { echo "claude CLI not on PATH"; exit 1; }
+[ -d "$TARGET/.codegraph" ] || { echo "target not indexed: run 'codegraph init $TARGET' first"; exit 1; }
+if ! git -C "$ENGINE" diff --quiet || ! git -C "$ENGINE" diff --cached --quiet; then
+  echo "engine repo has uncommitted changes — commit or stash first (this script checks files out)"; exit 1
+fi
+CHANGED=$(git -C "$ENGINE" diff --name-only "$BASE_REF" HEAD -- src 2>/dev/null)
+[ -n "$CHANGED" ] || { echo "no src/ changes between $BASE_REF and HEAD — nothing to A/B"; exit 1; }
+
+# On exit: kill any eval daemons + restore the engine to HEAD.
+cleanup() {
+  pkill -9 -f "serve --mcp --path $OUT/" 2>/dev/null
+  git -C "$ENGINE" checkout HEAD -- $CHANGED 2>/dev/null
+  ( cd "$ENGINE" && npm run build >/dev/null 2>&1 )
+}
+trap cleanup EXIT
+
+mkdir -p "$OUT"
+echo "###### engine=$ENGINE  baseline=$BASE_REF"
+echo "###### changed: $(echo "$CHANGED" | tr '\n' ' ')"
+echo "###### target=$TARGET"
+echo "###### task=$TASK"
+echo
+
+# Two pristine copies so each arm starts clean (the agent edits its own copy).
+rm -rf "$OUT/t-new" "$OUT/t-base"
+rsync -a --exclude node_modules --exclude .git --exclude dist --exclude .codegraph "$TARGET/" "$OUT/t-new/"
+cp -R "$OUT/t-new" "$OUT/t-base"
+
+prewarm() { # target — spawn a persistent daemon (current $BIN) and wait for its socket
+  pkill -9 -f "serve --mcp --path $1" 2>/dev/null
+  CODEGRAPH_DAEMON_IDLE_TIMEOUT_MS=1800000 node "$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]+"/.codegraph/daemon.sock")){clearInterval(t);process.exit(0)}if(n++>150){clearInterval(t);process.exit(1)}},100)' "$1" \
+    && echo "  daemon warm: $1" || echo "  WARN: daemon never bound for $1 (arm may run without codegraph)"
+}
+
+run_arm() { # label, target-copy
+  local label="$1" tgt="$2" c="$OUT/mcp-$1.json"
+  # Connect to the pre-warmed daemon; skip the startup re-exec for a fast attach.
+  printf '{"mcpServers":{"codegraph":{"command":"env","args":["CODEGRAPH_WASM_RELAUNCHED=1","node","%s","serve","--mcp","--path","%s"]}}}' "$BIN" "$tgt" > "$c"
+  prewarm "$tgt"
+  echo "############## ARM [$label] ##############"
+  ( cd "$tgt" && claude -p "$TASK" \
+      --output-format stream-json --verbose --permission-mode bypassPermissions \
+      --model "${MODEL:-sonnet}" --effort "${EFFORT:-high}" --max-budget-usd 4 --strict-mcp-config --mcp-config "$c" \
+      </dev/null > "$OUT/run-$label.jsonl" 2>"$OUT/run-$label.err" )
+  node "$PARSE" "$OUT/run-$label.jsonl" 2>&1 | grep -E "by type|Result" || echo "  (parse failed — see $OUT/run-$label.jsonl)"
+  pkill -9 -f "serve --mcp --path $tgt" 2>/dev/null
+  echo
+}
+
+echo "== NEW build (HEAD) =="
+( cd "$ENGINE" && npm run build >/dev/null 2>&1 ) && echo "  built"
+node "$BIN" init "$OUT/t-new" >/dev/null 2>&1 && echo "  indexed t-new"
+run_arm new "$OUT/t-new"
+
+echo "== BASELINE build ($BASE_REF) =="
+# Per-file: a file ADDED since baseline has no pathspec on the ref — and a
+# single multi-file checkout with one bad pathspec checks out NOTHING, which
+# silently ran the NEW build in the baseline arm. Absent-on-baseline → remove.
+for f in $CHANGED; do
+  git -C "$ENGINE" checkout "$BASE_REF" -- "$f" 2>/dev/null || rm -f "$ENGINE/$f"
+done
+( cd "$ENGINE" && npm run build >/dev/null 2>&1 ) && echo "  built"
+node "$BIN" init "$OUT/t-base" >/dev/null 2>&1 && echo "  indexed t-base"
+run_arm baseline "$OUT/t-base"
+
+echo "###### DONE. Compare the [new] vs [baseline] 'by type' counts above"
+echo "###### (especially Read vs mcp__codegraph__*). Full logs in: $OUT"

package/scripts/agent-eval/ab-sufficiency.sh

@@ -0,0 +1,78 @@
+#!/usr/bin/env bash
+# Sufficiency A/B: on a real understanding/flow question, WHEN the agent uses
+# codegraph (explore/node), does it still Read? Premise under test: explore/node
+# return source WITH line numbers, so a Read should not be needed.
+#
+# WITH codegraph (pre-warmed daemon, reliable nested attach) vs WITHOUT (empty
+# MCP, Read/Grep only), N runs each, on a throwaway copy of the repo. Reports
+# explore/node vs Read/Grep, and LISTS the files Read in the WITH arm so a true
+# sufficiency gap (an indexed source file) is distinguishable from out-of-scope
+# (configs, docs, a file codegraph didn't index).
+#
+# Usage: ab-sufficiency.sh <indexed-repo> "<question>" [runs-per-arm]
+# Env: AGENT_EVAL_OUT (default: /tmp/ab-sufficiency)
+set -uo pipefail
+REPO="${1:?usage: ab-sufficiency.sh <indexed-repo> \"<question>\" [runs]}"
+Q="${2:?question required}"
+RUNS="${3:-2}"
+ENGINE="$(cd "$(dirname "$0")/../.." && pwd)"
+BIN="$ENGINE/dist/bin/codegraph.js"
+OUT="${AGENT_EVAL_OUT:-/tmp/ab-sufficiency}"
+TGT="$OUT/target"
+command -v claude >/dev/null || { echo "claude CLI not on PATH"; exit 1; }
+[ -d "$REPO/.codegraph" ] || { echo "no .codegraph index at $REPO"; exit 1; }
+cleanup(){ pkill -9 -f "serve --mcp --path $TGT" 2>/dev/null; }
+trap cleanup EXIT
+mkdir -p "$OUT"
+( cd "$ENGINE" && npm run build >/dev/null 2>&1 ) && echo "built"
+
+# Throwaway copy + fresh index (the agent works here; a read-only question won't
+# edit, but isolate anyway). Excludes the source repo's index/build/vcs.
+rm -rf "$TGT"
+rsync -a --exclude node_modules --exclude .git --exclude dist --exclude .codegraph "$REPO/" "$TGT/"
+node "$BIN" init "$TGT" >/dev/null 2>&1 && echo "indexed copy ($(node "$BIN" status --json 2>/dev/null | node -e 'let s="";process.stdin.on("data",d=>s+=d).on("end",()=>{try{console.log(JSON.parse(s).fileCount+" files")}catch{console.log("?")}})' 2>/dev/null || echo '?'))"
+
+echo "###### repo=$REPO  runs/arm=$RUNS"
+echo "###### Q=$Q"; echo
+echo '{"mcpServers":{}}' > "$OUT/mcp-empty.json"
+printf '{"mcpServers":{"codegraph":{"command":"env","args":["CODEGRAPH_WASM_RELAUNCHED=1","node","%s","serve","--mcp","--path","%s"]}}}' "$BIN" "$TGT" > "$OUT/mcp-cg.json"
+
+prewarm(){
+  pkill -9 -f "serve --mcp --path $TGT" 2>/dev/null
+  CODEGRAPH_DAEMON_IDLE_TIMEOUT_MS=1800000 node "$BIN" serve --mcp --path "$TGT" </dev/null >/dev/null 2>&1 &
+  node -e 'const fs=require("fs");let n=0;const t=setInterval(()=>{if(fs.existsSync(process.argv[1]+"/.codegraph/daemon.sock")){clearInterval(t);process.exit(0)}if(n++>150){clearInterval(t);process.exit(1)}},100)' "$TGT" >/dev/null 2>&1
+}
+
+analyze(){
+  node -e '
+    const fs=require("fs");
+    const L=fs.readFileSync(process.argv[1],"utf8").split("\n").filter(Boolean);
+    let ex=0,nf=0,ns=0,oc=0,gr=0,exposed="?";const reads=[];
+    for(const l of L){try{const o=JSON.parse(l);
+      if(o.type==="system"&&o.subtype==="init")exposed=(o.tools||[]).filter(t=>/codegraph/.test(t)).length;
+      for(const b of (o.message?.content||[])){if(b.type!=="tool_use")continue;
+        if(b.name==="mcp__codegraph__codegraph_explore")ex++;
+        else if(b.name==="mcp__codegraph__codegraph_node"){if(b.input&&b.input.symbol)ns++;else nf++;}
+        else if(/mcp__codegraph__/.test(b.name))oc++;
+        else if(b.name==="Read")reads.push((b.input?.file_path||"").split("/").pop());
+        else if(b.name==="Grep")gr++;
+      }}catch{}}
+    console.log(`    explore=${ex} node[sym]=${ns} node[file]=${nf} other_cg=${oc} | Read=${reads.length}${reads.length?" ("+reads.join(", ")+")":""} Grep=${gr}  [cg exposed=${exposed}]`);
+  ' "$1"
+}
+
+run(){ # label, cfg, prewarm(0/1)
+  local label="$1" cfg="$2" pw="$3"
+  for i in $(seq 1 "$RUNS"); do
+    [ "$pw" = "1" ] && prewarm
+    ( cd "$TGT" && claude -p "$Q" --output-format stream-json --verbose \
+        --permission-mode bypassPermissions --model "${MODEL:-sonnet}" --effort "${EFFORT:-high}" --max-budget-usd 4 \
+        --strict-mcp-config --mcp-config "$cfg" </dev/null > "$OUT/$label-$i.jsonl" 2>"$OUT/$label-$i.err" )
+    echo "[$label] run $i:"; analyze "$OUT/$label-$i.jsonl"
+  done
+  echo
+}
+
+echo "== WITH codegraph (premise: explore/node used -> Read ~0) =="; run with "$OUT/mcp-cg.json" 1
+echo "== WITHOUT (Read/Grep only — the contrast) =="; run without "$OUT/mcp-empty.json" 0
+echo "###### DONE. In the WITH arm: are explore/node>0 and Read~0? Any Read of an INDEXED source file = sufficiency gap. Logs: $OUT"

package/scripts/agent-eval/arms-F.sh

@@ -0,0 +1,21 @@
+#!/usr/bin/env bash
+# Arm F (body-inlining trace + trace-first steering) across the same 6 repos as
+# arms-matrix.sh, so F vs B isolates the trace-enrichment effect (same surface,
+# old thin trace in B vs body-inlining trace here).
+set -uo pipefail
+H="$(cd "$(dirname "$0")" && pwd)"; RUNS="${RUNS:-2}"; C="${CORPUS:-/tmp/codegraph-corpus}"
+ROWS=(
+"$C/flutter-samples/add_to_app/books/flutter_module_books|How does the books UI build and what child widgets does it show?"
+"$C/aspnet-realworld|How is creating an article handled? Trace the controller to the service."
+"$C/spring-mall|How is a product-list request handled? Trace the controller to the service."
+"$C/vapor-spi|How is a package-show request handled? Name the route and controller."
+"$C/excalidraw|How does updating an element re-render the canvas on screen? Trace the flow."
+"$C/spring-halo|How is publishing a post handled? Trace the controller to the service."
+)
+ARM="${ARM:-F}"
+echo "### ARM $ARM START $(date) RUNS=$RUNS"
+for row in "${ROWS[@]}"; do
+  repo="${row%%|*}"; q="${row#*|}"
+  for r in $(seq 1 "$RUNS"); do bash "$H/run-arms.sh" "$repo" "$q" "$ARM" "$r"; done
+done
+echo "### ARM $ARM COMPLETE $(date)"

package/scripts/agent-eval/arms-matrix.sh

@@ -0,0 +1,37 @@
+#!/usr/bin/env bash
+# Drive the tool-surface ablation across the chosen repos × arms (A–E).
+# Arms A–D ask the canonical FLOW question; arm E asks a NON-flow survey
+# question (the control probe — should degrade without explore+context).
+# Output: /tmp/arms/<repo>/<arm>-r<n>.jsonl  (parse with parse-arms.mjs).
+set -uo pipefail
+HARNESS="$(cd "$(dirname "$0")" && pwd)"
+RUNS="${RUNS:-2}"
+C="${CORPUS:-/tmp/codegraph-corpus}"
+NFQ='What are the main modules/components of this codebase and what does each one do? Give an overview of how it is organized.'
+
+# repo-path|flow-question  (2 small, 2 medium, 2 large — spans the size range)
+ROWS=(
+"$C/flutter-samples/add_to_app/books/flutter_module_books|How does the books UI build and what child widgets does it show?"
+"$C/aspnet-realworld|How is creating an article handled? Trace the controller to the service."
+"$C/spring-mall|How is a product-list request handled? Trace the controller to the service."
+"$C/vapor-spi|How is a package-show request handled? Name the route and controller."
+"$C/excalidraw|How does updating an element re-render the canvas on screen? Trace the flow."
+"$C/spring-halo|How is publishing a post handled? Trace the controller to the service."
+)
+
+echo "### ARMS MATRIX START $(date) RUNS=$RUNS"
+for row in "${ROWS[@]}"; do
+  repo="${row%%|*}"; q="${row#*|}"
+  for arm in A B C D; do
+    for r in $(seq 1 "$RUNS"); do
+      bash "$HARNESS/run-arms.sh" "$repo" "$q" "$arm" "$r"
+    done
+  done
+done
+# E: non-flow control probe on two repos (must degrade without explore+context)
+for repo in "$C/excalidraw" "$C/spring-mall"; do
+  for r in $(seq 1 "$RUNS"); do
+    bash "$HARNESS/run-arms.sh" "$repo" "$NFQ" E "$r"
+  done
+done
+echo "### ARMS MATRIX COMPLETE $(date)"

package/scripts/agent-eval/audit.sh

@@ -0,0 +1,68 @@
+#!/usr/bin/env bash
+# One-shot CodeGraph quality audit:
+#   set version -> ensure corpus repo -> wipe+reindex with that version ->
+#   run with/without A/B -> restore the local dev link.
+#
+# Usage: audit.sh <version> <repo-name> <repo-url> "<question>" [headless|all]
+#   <version>    "local" (build + npm link this repo) | "latest" | a version (e.g. 0.7.10)
+#   <repo-name>  dir name under the corpus dir
+#   <repo-url>   git URL (cloned --depth 1 when the repo dir is missing)
+#   [mode]       headless (default) | all (also the interactive tmux arms)
+# Env: CORPUS  corpus dir (default: /tmp/codegraph-corpus)
+set -uo pipefail
+
+VERSION="${1:?usage: audit.sh <version> <repo-name> <repo-url> \"<question>\" [mode]}"
+NAME="${2:?repo-name required}"
+URL="${3:?repo-url required}"
+Q="${4:?question required}"
+MODE="${5:-headless}"
+
+HARNESS="$(cd "$(dirname "$0")" && pwd)"
+REPO_ROOT="$(cd "$HARNESS/../.." && pwd)"     # codegraph repo root
+CORPUS="${CORPUS:-/tmp/codegraph-corpus}"
+REPO="$CORPUS/$NAME"
+PKG="@colbymchenry/codegraph"
+
+echo "==================== CodeGraph audit ===================="
+echo "version=$VERSION  repo=$NAME  mode=$MODE  corpus=$CORPUS"
+echo
+
+# 1. Set the codegraph version under test (mutates the global install).
+if [ "$VERSION" = local ]; then
+  echo "→ [1/4] building + linking local dev build (local-install.sh)"
+  ( cd "$REPO_ROOT" && ./scripts/local-install.sh ) || { echo "local-install.sh failed"; exit 1; }
+else
+  echo "→ [1/4] installing $PKG@$VERSION globally"
+  npm install -g "$PKG@$VERSION" || { echo "npm install -g $PKG@$VERSION failed"; exit 1; }
+fi
+ACTUAL="$(codegraph --version 2>/dev/null || echo '?')"
+echo "  codegraph on PATH: $(command -v codegraph) -> $ACTUAL"
+
+# 2. Ensure the corpus repo exists (clone shallow if missing, reuse if present).
+mkdir -p "$CORPUS"
+if [ -d "$REPO/.git" ]; then
+  echo "→ [2/4] reusing existing checkout: $REPO"
+else
+  echo "→ [2/4] cloning $URL"
+  git clone --depth 1 "$URL" "$REPO" || { echo "git clone failed"; exit 1; }
+fi
+
+# 3. Wipe + re-index with THIS version (the index must be built by the same
+#    binary that serves it — different versions extract differently).
+echo "→ [3/4] wiping .codegraph and re-indexing with $ACTUAL"
+rm -rf "$REPO/.codegraph"
+( cd "$REPO" && codegraph init -i ) || { echo "indexing failed"; exit 1; }
+
+# 4. Run the with/without A/B.
+echo "→ [4/4] running A/B harness (mode=$MODE)"
+bash "$HARNESS/run-all.sh" "$REPO" "$Q" "$MODE"
+
+# Restore the dev link (the normal working state in this repo).
+echo
+echo "→ restoring local dev link (local-install.sh)"
+if ( cd "$REPO_ROOT" && ./scripts/local-install.sh >/dev/null 2>&1 ); then
+  echo "  global codegraph restored to dev build"
+else
+  echo "  WARN: restore failed — run ./scripts/local-install.sh manually"
+fi
+echo "==================== audit complete ===================="

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

@@ -0,0 +1,28 @@
+#!/usr/bin/env bash
+# Re-run the README "Benchmark Results" A/B (with vs without codegraph) 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
+# $CORPUS (default /tmp/codegraph-corpus) by the build under test.
+set -uo pipefail
+H="$(cd "$(dirname "$0")" && pwd)"
+C="${CORPUS:-/tmp/codegraph-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

@@ -0,0 +1,22 @@
+#!/usr/bin/env bash
+# One README repo, WITH-codegraph only, N runs. Each run appends a why-Read
+# diagnostic so the agent explains any Read/Grep. (The WITHOUT baseline is
+# codegraph-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/codegraph/dist/bin/codegraph.js"
+OUT="/tmp/ab-why/$NAME"; mkdir -p "$OUT"
+WHY=$'\n\nIMPORTANT — diagnostic: if you use the Read or Grep tool at ANY point, for EACH such call explain why codegraph_explore / codegraph_node did not already give you what you needed. End your entire answer with a section titled exactly "## Why I read" listing every Read and Grep you made and the precise reason codegraph fell short for it. If you used neither, write "## Why I read" then "none — codegraph was sufficient."'
+printf '{"mcpServers":{"codegraph":{"command":"%s","args":["serve","--mcp","--path","%s"]}}}' "$CG" "$REPO" > "$OUT/cg.json"
+
+for i in $(seq 1 "$N"); do
+  pkill -f "serve --mcp" 2>/dev/null; sleep 1; rm -f "$REPO/.codegraph/daemon.sock"
+  ( cd "$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

@@ -0,0 +1,19 @@
+#!/usr/bin/env bash
+# PreToolUse hook (experiment): deny Read of codegraph-indexed source files and
+# steer the agent to codegraph_explore/codegraph_node instead. Tests whether
+# codegraph 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 — codegraph already has this file indexed (with line numbers, kept in sync on every change). Use codegraph_explore (several related symbols at once) or codegraph_node (one symbol's full source). If a symbol you need wasn't in a prior explore, run ANOTHER codegraph_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

@@ -0,0 +1,15 @@
+{
+  "hooks": {
+    "PreToolUse": [
+      {
+        "matcher": "Read",
+        "hooks": [
+          {
+            "type": "command",
+            "command": "bash /Users/colby/Development/Personal/codegraph/scripts/agent-eval/block-read-hook.sh"
+          }
+        ]
+      }
+    ]
+  }
+}