claude
af6062c1f9
Extend pre-compact-snapshot.sh to extract 5 new per-conversation metrics from the transcript: automation ratio (deskilling proxy), model ID (monoculture tracking), test pass/fail counts (code quality proxy), file churn (edits per unique file), and public push detection (data pollution risk flag). Update show-impact.sh to display them. New plan: quantify-social-costs.md — roadmap for moving non-environmental cost categories from qualitative to proxy-measurable. Tasks 19-24 done. Task 25 (methodology update) pending. Co-Authored-By: Claude Opus 4.6 (1M context) <noreply@anthropic.com>
237 lines
9.6 KiB
Bash
Executable file
237 lines
9.6 KiB
Bash
Executable file
#!/usr/bin/env bash
|
|
#
|
|
# pre-compact-snapshot.sh — Snapshot impact metrics before context compaction.
|
|
#
|
|
# Runs as a PreCompact hook. Reads the conversation transcript, extracts
|
|
# actual token counts when available (falls back to heuristic estimates),
|
|
# and appends a timestamped entry to the impact log.
|
|
#
|
|
# Input: JSON on stdin with fields: trigger, session_id, transcript_path, cwd
|
|
# Output: nothing on stdout (hook succeeds silently). Logs to impact-log.jsonl.
|
|
|
|
set -euo pipefail
|
|
|
|
HOOK_INPUT=$(cat)
|
|
PROJECT_DIR="${CLAUDE_PROJECT_DIR:-$(echo "$HOOK_INPUT" | jq -r '.cwd')}"
|
|
TRANSCRIPT_PATH=$(echo "$HOOK_INPUT" | jq -r '.transcript_path')
|
|
SESSION_ID=$(echo "$HOOK_INPUT" | jq -r '.session_id')
|
|
TRIGGER=$(echo "$HOOK_INPUT" | jq -r '.trigger')
|
|
TIMESTAMP=$(date -u +"%Y-%m-%dT%H:%M:%SZ")
|
|
|
|
LOG_DIR="$PROJECT_DIR/.claude/impact"
|
|
LOG_FILE="$LOG_DIR/impact-log.jsonl"
|
|
mkdir -p "$LOG_DIR"
|
|
|
|
# --- Extract or estimate metrics from transcript ---
|
|
|
|
if [ -f "$TRANSCRIPT_PATH" ]; then
|
|
TRANSCRIPT_BYTES=$(wc -c < "$TRANSCRIPT_PATH")
|
|
TRANSCRIPT_LINES=$(wc -l < "$TRANSCRIPT_PATH")
|
|
|
|
# Count tool uses
|
|
TOOL_USES=$(grep -c '"tool_use"' "$TRANSCRIPT_PATH" 2>/dev/null || echo 0)
|
|
|
|
# Try to extract actual token counts from usage fields in the transcript.
|
|
# The transcript contains .message.usage with input_tokens,
|
|
# cache_creation_input_tokens, cache_read_input_tokens, output_tokens.
|
|
USAGE_DATA=$(python3 -c "
|
|
import json, sys, re
|
|
|
|
input_tokens = 0
|
|
cache_creation = 0
|
|
cache_read = 0
|
|
output_tokens = 0
|
|
turns = 0
|
|
model_id = ''
|
|
user_bytes = 0
|
|
edited_files = {} # file_path -> edit count
|
|
test_passes = 0
|
|
test_failures = 0
|
|
has_public_push = 0
|
|
|
|
with open(sys.argv[1]) as f:
|
|
for line in f:
|
|
try:
|
|
d = json.loads(line.strip())
|
|
msg = d.get('message', {})
|
|
role = msg.get('role')
|
|
content = msg.get('content', '')
|
|
|
|
# Track user message size (proxy for user contribution)
|
|
if role == 'user':
|
|
if isinstance(content, str):
|
|
user_bytes += len(content.encode('utf-8', errors='replace'))
|
|
elif isinstance(content, list):
|
|
for block in content:
|
|
if isinstance(block, dict) and block.get('type') == 'text':
|
|
user_bytes += len(block.get('text', '').encode('utf-8', errors='replace'))
|
|
|
|
# Extract usage data and model from assistant messages
|
|
if role == 'assistant':
|
|
m = msg.get('model', '')
|
|
if m:
|
|
model_id = m
|
|
|
|
u = msg.get('usage')
|
|
if u and 'input_tokens' in u:
|
|
turns += 1
|
|
input_tokens += u.get('input_tokens', 0)
|
|
cache_creation += u.get('cache_creation_input_tokens', 0)
|
|
cache_read += u.get('cache_read_input_tokens', 0)
|
|
output_tokens += u.get('output_tokens', 0)
|
|
|
|
# Parse tool use blocks
|
|
if isinstance(content, list):
|
|
for block in content:
|
|
if not isinstance(block, dict) or block.get('type') != 'tool_use':
|
|
continue
|
|
name = block.get('name', '')
|
|
inp = block.get('input', {})
|
|
|
|
# File churn: count Edit/Write per file
|
|
if name in ('Edit', 'Write'):
|
|
fp = inp.get('file_path', '')
|
|
if fp:
|
|
edited_files[fp] = edited_files.get(fp, 0) + 1
|
|
|
|
# Public push detection
|
|
if name == 'Bash':
|
|
cmd = inp.get('command', '')
|
|
if re.search(r'git\s+push', cmd):
|
|
has_public_push = 1
|
|
|
|
# Test results from tool_result blocks (user role, tool_result type)
|
|
if role == 'user' and isinstance(content, list):
|
|
for block in content:
|
|
if isinstance(block, dict) and block.get('type') == 'tool_result':
|
|
text = ''
|
|
rc = block.get('content', '')
|
|
if isinstance(rc, str):
|
|
text = rc
|
|
elif isinstance(rc, list):
|
|
text = ' '.join(b.get('text', '') for b in rc if isinstance(b, dict))
|
|
# Detect test outcomes from common test runner output
|
|
if re.search(r'(\d+)\s+(tests?\s+)?passed', text, re.I):
|
|
test_passes += 1
|
|
if re.search(r'(\d+)\s+(tests?\s+)?failed|FAIL[ED]?|ERROR', text, re.I):
|
|
test_failures += 1
|
|
|
|
except Exception:
|
|
pass
|
|
|
|
user_tokens_est = user_bytes // 4 # rough byte-to-token estimate
|
|
unique_files = len(edited_files)
|
|
total_edits = sum(edited_files.values())
|
|
churn = round(total_edits / unique_files, 2) if unique_files > 0 else 0
|
|
|
|
# automation_ratio: 0 = all human, 1 = all AI (as permille for integer arithmetic)
|
|
if output_tokens + user_tokens_est > 0:
|
|
auto_ratio_pm = output_tokens * 1000 // (output_tokens + user_tokens_est)
|
|
else:
|
|
auto_ratio_pm = 0
|
|
|
|
print(f'{turns}\t{input_tokens}\t{cache_creation}\t{cache_read}\t{output_tokens}\t{model_id}\t{auto_ratio_pm}\t{user_tokens_est}\t{unique_files}\t{total_edits}\t{test_passes}\t{test_failures}\t{has_public_push}')
|
|
" "$TRANSCRIPT_PATH" 2>/dev/null || echo "")
|
|
|
|
if [ -n "$USAGE_DATA" ] && [ "$(echo "$USAGE_DATA" | cut -f1)" -gt 0 ] 2>/dev/null; then
|
|
# Actual token counts available
|
|
TOKEN_SOURCE="actual"
|
|
ASSISTANT_TURNS=$(echo "$USAGE_DATA" | cut -f1)
|
|
INPUT_TOKENS=$(echo "$USAGE_DATA" | cut -f2)
|
|
CACHE_CREATION=$(echo "$USAGE_DATA" | cut -f3)
|
|
CACHE_READ=$(echo "$USAGE_DATA" | cut -f4)
|
|
OUTPUT_TOKENS=$(echo "$USAGE_DATA" | cut -f5)
|
|
MODEL_ID=$(echo "$USAGE_DATA" | cut -f6)
|
|
AUTO_RATIO_PM=$(echo "$USAGE_DATA" | cut -f7)
|
|
USER_TOKENS_EST=$(echo "$USAGE_DATA" | cut -f8)
|
|
UNIQUE_FILES=$(echo "$USAGE_DATA" | cut -f9)
|
|
TOTAL_EDITS=$(echo "$USAGE_DATA" | cut -f10)
|
|
TEST_PASSES=$(echo "$USAGE_DATA" | cut -f11)
|
|
TEST_FAILURES=$(echo "$USAGE_DATA" | cut -f12)
|
|
HAS_PUBLIC_PUSH=$(echo "$USAGE_DATA" | cut -f13)
|
|
|
|
# Cumulative input = all tokens that went through the model.
|
|
# Cache reads are cheaper (~10-20% of full compute), so we weight them.
|
|
# Full-cost tokens: input_tokens + cache_creation_input_tokens
|
|
# Reduced-cost tokens: cache_read_input_tokens (weight at 0.1x for energy)
|
|
FULL_COST_INPUT=$(( INPUT_TOKENS + CACHE_CREATION ))
|
|
CACHE_READ_EFFECTIVE=$(( CACHE_READ / 10 ))
|
|
CUMULATIVE_INPUT=$(( FULL_COST_INPUT + CACHE_READ_EFFECTIVE ))
|
|
# Also track raw total for the log
|
|
CUMULATIVE_INPUT_RAW=$(( INPUT_TOKENS + CACHE_CREATION + CACHE_READ ))
|
|
else
|
|
# Fallback: heuristic estimation
|
|
TOKEN_SOURCE="heuristic"
|
|
ESTIMATED_TOKENS=$((TRANSCRIPT_BYTES / 4))
|
|
ASSISTANT_TURNS=$(grep -c '"role":\s*"assistant"' "$TRANSCRIPT_PATH" 2>/dev/null || echo 0)
|
|
|
|
if [ "$ASSISTANT_TURNS" -gt 0 ]; then
|
|
AVG_CONTEXT=$((ESTIMATED_TOKENS / 2))
|
|
CUMULATIVE_INPUT=$((AVG_CONTEXT * ASSISTANT_TURNS))
|
|
else
|
|
CUMULATIVE_INPUT=$ESTIMATED_TOKENS
|
|
fi
|
|
CUMULATIVE_INPUT_RAW=$CUMULATIVE_INPUT
|
|
OUTPUT_TOKENS=$((ESTIMATED_TOKENS / 20))
|
|
CACHE_CREATION=0
|
|
CACHE_READ=0
|
|
INPUT_TOKENS=0
|
|
MODEL_ID=""
|
|
AUTO_RATIO_PM=0
|
|
USER_TOKENS_EST=0
|
|
UNIQUE_FILES=0
|
|
TOTAL_EDITS=0
|
|
TEST_PASSES=0
|
|
TEST_FAILURES=0
|
|
HAS_PUBLIC_PUSH=0
|
|
fi
|
|
|
|
# --- Cost estimates ---
|
|
# Energy: 0.1 Wh per 1K input tokens, 0.5 Wh per 1K output tokens, PUE 1.2
|
|
# Calibrated against Google (Patterson et al., Aug 2025) and Jegham et al. (May 2025)
|
|
# Using integer arithmetic in centiwatt-hours to avoid bc dependency
|
|
INPUT_CWH=$(( CUMULATIVE_INPUT * 100 / 10000 )) # 0.1 Wh/1K = 100 cWh/10K
|
|
OUTPUT_CWH=$(( OUTPUT_TOKENS * 500 / 10000 )) # 0.5 Wh/1K = 500 cWh/10K
|
|
ENERGY_CWH=$(( (INPUT_CWH + OUTPUT_CWH) * 12 / 10 )) # PUE 1.2
|
|
ENERGY_WH=$(( ENERGY_CWH / 100 ))
|
|
|
|
# CO2: 325g/kWh -> 0.325g/Wh -> 325 mg/Wh
|
|
CO2_MG=$(( ENERGY_WH * 325 ))
|
|
CO2_G=$(( CO2_MG / 1000 ))
|
|
|
|
# Financial: $15/M input, $75/M output (in cents)
|
|
# Use effective cumulative input (cache-weighted) for cost too
|
|
COST_INPUT_CENTS=$(( CUMULATIVE_INPUT * 15 / 10000 )) # $15/M = 1.5c/100K
|
|
COST_OUTPUT_CENTS=$(( OUTPUT_TOKENS * 75 / 10000 ))
|
|
COST_CENTS=$(( COST_INPUT_CENTS + COST_OUTPUT_CENTS ))
|
|
else
|
|
TRANSCRIPT_BYTES=0
|
|
TRANSCRIPT_LINES=0
|
|
ASSISTANT_TURNS=0
|
|
TOOL_USES=0
|
|
CUMULATIVE_INPUT=0
|
|
CUMULATIVE_INPUT_RAW=0
|
|
OUTPUT_TOKENS=0
|
|
CACHE_CREATION=0
|
|
CACHE_READ=0
|
|
ENERGY_WH=0
|
|
CO2_G=0
|
|
COST_CENTS=0
|
|
TOKEN_SOURCE="none"
|
|
MODEL_ID=""
|
|
AUTO_RATIO_PM=0
|
|
USER_TOKENS_EST=0
|
|
UNIQUE_FILES=0
|
|
TOTAL_EDITS=0
|
|
TEST_PASSES=0
|
|
TEST_FAILURES=0
|
|
HAS_PUBLIC_PUSH=0
|
|
fi
|
|
|
|
# --- Write log entry ---
|
|
|
|
cat >> "$LOG_FILE" <<EOF
|
|
{"timestamp":"$TIMESTAMP","session_id":"$SESSION_ID","trigger":"$TRIGGER","token_source":"$TOKEN_SOURCE","transcript_bytes":$TRANSCRIPT_BYTES,"transcript_lines":$TRANSCRIPT_LINES,"assistant_turns":$ASSISTANT_TURNS,"tool_uses":$TOOL_USES,"cumulative_input_tokens":$CUMULATIVE_INPUT,"cumulative_input_raw":$CUMULATIVE_INPUT_RAW,"cache_creation_tokens":$CACHE_CREATION,"cache_read_tokens":$CACHE_READ,"output_tokens":$OUTPUT_TOKENS,"energy_wh":$ENERGY_WH,"co2_g":$CO2_G,"cost_cents":$COST_CENTS,"model_id":"$MODEL_ID","automation_ratio_pm":$AUTO_RATIO_PM,"user_tokens_est":$USER_TOKENS_EST,"unique_files_edited":$UNIQUE_FILES,"total_file_edits":$TOTAL_EDITS,"test_passes":$TEST_PASSES,"test_failures":$TEST_FAILURES,"has_public_push":$HAS_PUBLIC_PUSH}
|
|
EOF
|
|
|
|
exit 0
|