User: Analyze my latest session health

# Read latest trace file from .claude-trace/
trace_dir = Path(".claude-trace")
trace_files = sorted(trace_dir.glob("*.jsonl"), key=lambda f: f.stat().st_mtime)
latest = trace_files[-1] if trace_files else None

# Parse and analyze
if latest:
    analysis = analyze_trace_file(latest)
    print(format_session_report(analysis))

User: Compare token usage across my last 5 sessions

trace_files = sorted(Path(".claude-trace").glob("*.jsonl"))[-5:]
comparison = compare_sessions(trace_files)
print(format_comparison_table(comparison))

# From each JSONL line containing a request/response pair:
{
    "timestamp": "...",
    "request": {
        "method": "POST",
        "url": "https://api.anthropic.com/v1/messages",
        "body": {
            "model": "claude-...",
            "messages": [...],
            "tools": [...]
        }
    },
    "response": {
        "usage": {
            "input_tokens": N,
            "output_tokens": N
        },
        "content": [...],
        "stop_reason": "..."
    }
}

Session Health Report
=====================
File: log-2025-11-23-19-32-36.jsonl
Duration: 45 minutes

Token Usage:
- Input: 125,432 tokens
- Output: 34,521 tokens
- Total: 159,953 tokens
- Efficiency: 27.5% output ratio

Request Stats:
- Total requests: 23
- Average latency: 2.3s
- Errors: 2 (8.7%)

Tool Usage:
- Read: 45 calls
- Edit: 12 calls
- Bash: 8 calls
- Grep: 15 calls

Health Score: 82/100 (Good)
- Minor issue: 2 errors detected

Error Analysis
==============
Sessions analyzed: 5
Total errors: 12

Error Categories:
1. Rate limit (429): 5 occurrences
   - Recommendation: Add delays between requests

2. Token limit: 3 occurrences
   - Recommendation: Use context management skill

3. Tool failures: 4 occurrences
   - Bash timeout: 2
   - File not found: 2
   - Recommendation: Check paths before operations

Session Comparison
==================
                    Session 1   Session 2   Session 3   Trend
Tokens (total)      150K        180K        120K        -17%
Requests            25          30          18          -28%
Errors              2           0           1           stable
Duration (min)      45          60          30          -33%
Efficiency          0.27        0.32        0.35        +7%

Tool Usage Analysis
===================
Tool          Calls   Avg Time   Success Rate
Read          45      0.1s       100%
Edit          12      0.3s       92%
Bash          8       1.2s       75%
Grep          15      0.2s       100%
Task          3       45s        100%

Optimization Opportunities:
1. 5 Read calls to same file within 2 minutes
   - Consider caching strategy

2. 3 sequential Bash calls could be parallelized
   - Use multiple Bash calls in single message

import json
from pathlib import Path
from typing import Dict, List, Any

def parse_trace_file(path: Path) -> List[Dict[str, Any]]:
    """Parse a claude-trace JSONL file."""
    entries = []
    with open(path) as f:
        for line in f:
            if line.strip():
                try:
                    entry = json.loads(line)
                    entries.append(entry)
                except json.JSONDecodeError:
                    continue
    return entries

def extract_metrics(entries: List[Dict]) -> Dict[str, Any]:
    """Extract session metrics from trace entries."""
    metrics = {
        "total_input_tokens": 0,
        "total_output_tokens": 0,
        "request_count": 0,
        "error_count": 0,
        "tool_usage": {},
        "timestamps": [],
    }

    for entry in entries:
        if "request" in entry:
            metrics["request_count"] += 1
            metrics["timestamps"].append(entry.get("timestamp", 0))

        if "response" in entry:
            usage = entry["response"].get("usage", {})
            metrics["total_input_tokens"] += usage.get("input_tokens", 0)
            metrics["total_output_tokens"] += usage.get("output_tokens", 0)

            # Check for errors
            if entry["response"].get("error"):
                metrics["error_count"] += 1

        # Extract tool usage from request body
        if "request" in entry and "body" in entry["request"]:
            body = entry["request"]["body"]
            if isinstance(body, dict) and "tools" in body:
                for tool in body["tools"]:
                    name = tool.get("name", "unknown")
                    metrics["tool_usage"][name] = metrics["tool_usage"].get(name, 0) + 1

    return metrics

def find_trace_files(trace_dir: str = ".claude-trace") -> List[Path]:
    """Find all trace files, sorted by modification time."""
    trace_path = Path(trace_dir)
    if not trace_path.exists():
        return []
    return sorted(
        trace_path.glob("*.jsonl"),
        key=lambda f: f.stat().st_mtime,
        reverse=True  # Most recent first
    )

def safe_parse_trace_file(path: Path) -> Tuple[List[Dict], List[str]]:
    """Parse trace file with error collection for malformed lines.

    Returns:
        Tuple of (valid_entries, error_messages)
    """
    entries = []
    errors = []

    if not path.exists():
        return [], [f"Trace file not found: {path}"]

    try:
        with open(path) as f:
            for line_num, line in enumerate(f, 1):
                if not line.strip():
                    continue
                try:
                    entry = json.loads(line)
                    entries.append(entry)
                except json.JSONDecodeError as e:
                    errors.append(f"Line {line_num}: Invalid JSON - {e}")
    except PermissionError:
        return [], [f"Permission denied: {path}"]
    except UnicodeDecodeError:
        return [], [f"Encoding error: {path} (expected UTF-8)"]

    return entries, errors


def format_error_report(errors: List[str], path: Path) -> str:
    """Format error report for user display."""
    if not errors:
        return ""

    report = f"""
Trace File Issues
=================
File: {path.name}
Issues found: {len(errors)}

"""
    for error in errors[:10]:  # Limit to first 10
        report += f"- {error}\n"

    if len(errors) > 10:
        report += f"\n... and {len(errors) - 10} more issues"

    return report

1. session-replay: Analyze token usage patterns (health action)
2. Identify high-token operations
3. context_management skill: Apply proactive trimming
4. session-replay: Compare before/after sessions (compare action)

1. session-replay: Identify error patterns (errors action)
2. /transcripts: Review conversation context around errors
3. session-replay: Check tool usage around failures (tools action)
4. Document findings in DISCOVERIES.md

1. session-replay: Analyze 5-10 recent sessions (compare action)
2. Establish baseline metrics (tokens, latency, errors)
3. Track deviations from baseline over time

User: My last session was really slow, analyze it

1. Run health action on latest trace
2. Check request latencies
3. Identify tool bottlenecks
4. Report findings with recommendations

User: I'm hitting token limits, help me understand usage

1. Compare token usage across sessions
2. Identify high-token operations
3. Suggest context management strategies
4. Recommend workflow optimizations

User: I keep getting errors, find the pattern

1. Run errors action across last 10 sessions
2. Categorize and count error types
3. Identify root causes
4. Provide targeted fixes