session-report

1# Session Report
2 
3Generate a detailed session report from the Claude Code Agent Monitor.
4 
5## Input
6 
7The user provides: **$ARGUMENTS**
8 
9This may be a session ID, "latest", or a date range like "last 24 hours".
10 
11## Data Sources
12 
13All data comes from the Agent Monitor API at `http://localhost:4820`:
14 
15| Endpoint | What it returns |
16|----------|----------------|
17| `GET /api/sessions/{id}` | Session with nested `.agents[]` and `.events[]` |
18| `GET /api/sessions?limit=50` | Session list with `agent_count`, `last_activity`, and **inline `cost`** per session (bulk pricing applied server-side) |
19| `GET /api/pricing/cost/{sessionId}` | `{ total_cost, breakdown: [{ model, input_tokens, output_tokens, cache_read_tokens, cache_write_tokens, cost, matched_rule }] }` |
20| `GET /api/events?session_id={id}` | Event stream: each has `event_type`, `tool_name`, `summary`, `data` (JSON), `created_at` |
21 
22### Key data points available per session
23 
24- **Status**: `active` / `completed` / `error` / `abandoned`
25- **Model**: primary model (e.g. `claude-sonnet-4-20250514`)
26- **Metadata (JSON)**: `thinking_blocks` count, `turn_count`, `total_turn_duration_ms`, `usage_extras` (service_tier, speed, inference_geo)
27- **Token usage per model**: Pricing breakdown reports `input_tokens`, `output_tokens`, `cache_read_tokens`, `cache_write_tokens` per model (baselines are pre-summed into these totals at the DB level)
28…