Add social cost proxies to impact tracking hooks
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>
This commit is contained in:
parent
e6e0bf4616
commit
af6062c1f9
8 changed files with 554 additions and 25 deletions
|
|
@ -11,6 +11,11 @@ A PreCompact hook that runs before each context compaction, capturing:
|
|||
- Energy consumption estimate (Wh)
|
||||
- CO2 emissions estimate (grams)
|
||||
- Financial cost estimate (USD)
|
||||
- Model ID
|
||||
- Automation ratio (AI output vs. user input — deskilling proxy)
|
||||
- File churn (edits per file — code quality proxy)
|
||||
- Test pass/fail counts
|
||||
- Public push detection (data pollution risk flag)
|
||||
|
||||
Data is logged to a JSONL file for analysis over time.
|
||||
|
||||
|
|
@ -63,8 +68,10 @@ consider these complementary tools:
|
|||
- **[Hugging Face AI Energy Score](https://huggingface.github.io/AIEnergyScore/)** —
|
||||
Benchmarks model energy efficiency. Useful for choosing between models.
|
||||
|
||||
These tools focus on environmental metrics only. This toolkit and the
|
||||
methodology also cover financial, social, epistemic, and political costs.
|
||||
These tools focus on environmental metrics only. This toolkit also
|
||||
tracks financial cost and proxy metrics for social costs (automation
|
||||
ratio, file churn, test outcomes, public push detection). The
|
||||
accompanying methodology covers additional dimensions in depth.
|
||||
|
||||
## Limitations
|
||||
|
||||
|
|
|
|||
|
|
@ -35,27 +35,102 @@ if [ -f "$TRANSCRIPT_PATH" ]; then
|
|||
# The transcript contains .message.usage with input_tokens,
|
||||
# cache_creation_input_tokens, cache_read_input_tokens, output_tokens.
|
||||
USAGE_DATA=$(python3 -c "
|
||||
import json, sys
|
||||
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())
|
||||
u = d.get('message', {}).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)
|
||||
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
|
||||
# Print as tab-separated for easy shell parsing
|
||||
print(f'{turns}\t{input_tokens}\t{cache_creation}\t{cache_read}\t{output_tokens}')
|
||||
|
||||
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
|
||||
|
|
@ -66,6 +141,14 @@ print(f'{turns}\t{input_tokens}\t{cache_creation}\t{cache_read}\t{output_tokens}
|
|||
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.
|
||||
|
|
@ -93,6 +176,14 @@ print(f'{turns}\t{input_tokens}\t{cache_creation}\t{cache_read}\t{output_tokens}
|
|||
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 ---
|
||||
|
|
@ -127,12 +218,20 @@ else
|
|||
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":$COST_CENTS}
|
||||
{"timestamp":"$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":$HAS_PUBLIC_PUSH}
|
||||
EOF
|
||||
|
||||
exit 0
|
||||
|
|
|
|||
|
|
@ -49,6 +49,35 @@ while IFS= read -r line; do
|
|||
printf " Cache: %s created, %s read\n" "$cache_create" "$cache_read"
|
||||
fi
|
||||
LC_NUMERIC=C printf " Energy: ~%s Wh CO2: ~%sg Cost: ~\$%.2f\n" "$energy" "$co2" "$(echo "$cost / 100" | bc -l 2>/dev/null || echo "$cost cents")"
|
||||
|
||||
# Social cost proxies (if present in log entry)
|
||||
model=$(echo "$line" | jq -r '.model_id // empty')
|
||||
auto_pm=$(echo "$line" | jq -r '.automation_ratio_pm // empty')
|
||||
user_tok=$(echo "$line" | jq -r '.user_tokens_est // empty')
|
||||
files_ed=$(echo "$line" | jq -r '.unique_files_edited // empty')
|
||||
total_ed=$(echo "$line" | jq -r '.total_file_edits // empty')
|
||||
t_pass=$(echo "$line" | jq -r '.test_passes // empty')
|
||||
t_fail=$(echo "$line" | jq -r '.test_failures // empty')
|
||||
pub_push=$(echo "$line" | jq -r '.has_public_push // empty')
|
||||
|
||||
if [ -n "$model" ]; then
|
||||
printf " Model: %s\n" "$model"
|
||||
fi
|
||||
if [ -n "$auto_pm" ] && [ "$auto_pm" != "0" ]; then
|
||||
auto_pct=$(( auto_pm / 10 ))
|
||||
auto_dec=$(( auto_pm % 10 ))
|
||||
printf " Automation ratio: %d.%d%% (user ~%s tokens, AI ~%s tokens)\n" \
|
||||
"$auto_pct" "$auto_dec" "$user_tok" "$output"
|
||||
fi
|
||||
if [ -n "$files_ed" ] && [ "$files_ed" != "0" ]; then
|
||||
printf " File churn: %s edits across %s files\n" "$total_ed" "$files_ed"
|
||||
fi
|
||||
if [ -n "$t_pass" ] && [ -n "$t_fail" ] && { [ "$t_pass" != "0" ] || [ "$t_fail" != "0" ]; }; then
|
||||
printf " Tests: %s passed, %s failed\n" "$t_pass" "$t_fail"
|
||||
fi
|
||||
if [ "$pub_push" = "1" ]; then
|
||||
printf " Public push: yes (data pollution risk)\n"
|
||||
fi
|
||||
echo ""
|
||||
done < "$LOG_FILE"
|
||||
|
||||
|
|
@ -62,3 +91,26 @@ echo "=== Totals ($TOTAL_ENTRIES snapshots) ==="
|
|||
LC_NUMERIC=C printf " Energy: ~%s Wh CO2: ~%sg Cost: ~\$%.2f\n" \
|
||||
"$TOTAL_ENERGY" "$TOTAL_CO2" \
|
||||
"$(echo "$TOTAL_COST / 100" | bc -l 2>/dev/null || echo "$TOTAL_COST cents")"
|
||||
|
||||
# Show annotations if they exist
|
||||
ANNOT_FILE="$PROJECT_DIR/.claude/impact/annotations.jsonl"
|
||||
if [ -f "$ANNOT_FILE" ] && [ -s "$ANNOT_FILE" ]; then
|
||||
echo ""
|
||||
echo "=== Value Annotations ==="
|
||||
echo ""
|
||||
while IFS= read -r line; do
|
||||
sid=$(echo "$line" | jq -r '.session_id')
|
||||
if ! echo "$sid" | grep -q "$FILTER"; then
|
||||
continue
|
||||
fi
|
||||
ts=$(echo "$line" | jq -r '.timestamp')
|
||||
summary=$(echo "$line" | jq -r '.value_summary')
|
||||
reach=$(echo "$line" | jq -r '.estimated_reach')
|
||||
cf=$(echo "$line" | jq -r '.counterfactual')
|
||||
net=$(echo "$line" | jq -r '.net_assessment')
|
||||
printf "%s session=%s\n" "$ts" "${sid:0:12}..."
|
||||
printf " Value: %s\n" "$summary"
|
||||
printf " Reach: %s Counterfactual: %s Net: %s\n" "$reach" "$cf" "$net"
|
||||
echo ""
|
||||
done < "$ANNOT_FILE"
|
||||
fi
|
||||
|
|
|
|||
Loading…
Add table
Add a link
Reference in a new issue