Files
AutoGPT/autogpt_platform/analytics/queries/retention_execution_weekly.sql
Zamil Majdy a8259ca935 feat(analytics): read-only SQL views layer with analytics schema (#12367)
### Changes 🏗️

Adds `autogpt_platform/analytics/` — 14 SQL view definitions that expose
production data safely through a locked-down `analytics` schema.

**Security model:**
- Views use `security_invoker = false` (PostgreSQL 15+), so they execute
as their owner (`postgres`), not the caller
- `analytics_readonly` role only has access to `analytics.*` — cannot
touch `platform` or `auth` tables directly

**Files:**
- `backend/generate_views.py` — does everything; auto-reads credentials
from `backend/.env`
- `analytics/queries/*.sql` — 14 documented view definitions (auth, user
activity, executions, onboarding funnel, cohort retention)

---

### Running locally (dev)

```bash
cd autogpt_platform/backend

# First time only — creates analytics schema, role, grants
poetry run analytics-setup

# Create / refresh views (auto-reads backend/.env)
poetry run analytics-views
```

### Running in production (Supabase)

```bash
cd autogpt_platform/backend

# Step 1 — first time only (run in Supabase SQL Editor as postgres superuser)
poetry run analytics-setup --dry-run
# Paste the output into Supabase SQL Editor and run

# Step 2 — apply views (use direct connection host, not pooler)
poetry run analytics-views --db-url "postgresql://postgres:PASSWORD@db.<ref>.supabase.co:5432/postgres"

# Step 3 — set password for analytics_readonly so external tools can connect
# Run in Supabase SQL Editor:
# ALTER ROLE analytics_readonly WITH PASSWORD 'your-password';
```

---

### Checklist 📋

#### For code changes:
- [x] I have clearly listed my changes in the PR description
- [x] I have made a test plan
- [x] I have tested my changes according to the test plan:
  - [x] Setup + views applied cleanly on local Postgres 15
- [x] `analytics_readonly` can `SELECT` from all 14 `analytics.*` views
- [x] `analytics_readonly` gets `permission denied` on `platform.*` and
`auth.*` directly

---------

Co-authored-by: Otto (AGPT) <otto@agpt.co>
2026-03-13 12:04:42 +00:00

82 lines
3.9 KiB
SQL

-- =============================================================
-- View: analytics.retention_execution_weekly
-- Looker source alias: ds92 | Charts: 2
-- =============================================================
-- DESCRIPTION
-- Weekly cohort retention based on agent executions.
-- Cohort anchor = week of user's FIRST ever agent execution
-- (not first login). Only includes cohorts from the last 180 days.
-- Useful when you care about product engagement, not just visits.
--
-- SOURCE TABLES
-- platform.AgentGraphExecution — Execution records
--
-- OUTPUT COLUMNS
-- Same pattern as retention_login_weekly.
-- cohort_week_start = week of first execution (not first login)
--
-- EXAMPLE QUERIES
-- -- Week-2 execution retention
-- SELECT cohort_label, retention_rate_bounded
-- FROM analytics.retention_execution_weekly
-- WHERE user_lifetime_week = 2 ORDER BY cohort_week_start;
-- =============================================================
WITH params AS (SELECT 12::int AS max_weeks, (CURRENT_DATE - INTERVAL '180 days') AS cohort_start),
events AS (
SELECT e."userId"::text AS user_id, e."createdAt"::timestamptz AS created_at,
DATE_TRUNC('week', e."createdAt")::date AS week_start
FROM platform."AgentGraphExecution" e WHERE e."userId" IS NOT NULL
),
first_exec AS (
SELECT user_id, MIN(created_at) AS first_exec_at,
DATE_TRUNC('week', MIN(created_at))::date AS cohort_week_start
FROM events GROUP BY 1
HAVING MIN(created_at) >= (SELECT cohort_start FROM params)
),
activity_weeks AS (SELECT DISTINCT user_id, week_start FROM events),
user_week_age AS (
SELECT aw.user_id, fe.cohort_week_start,
((aw.week_start - DATE_TRUNC('week',fe.first_exec_at)::date)/7)::int AS user_lifetime_week
FROM activity_weeks aw JOIN first_exec fe USING (user_id)
WHERE aw.week_start >= DATE_TRUNC('week',fe.first_exec_at)::date
),
bounded_counts AS (
SELECT cohort_week_start, user_lifetime_week, COUNT(DISTINCT user_id) AS active_users_bounded
FROM user_week_age WHERE user_lifetime_week >= 0 GROUP BY 1,2
),
last_active AS (
SELECT cohort_week_start, user_id, MAX(user_lifetime_week) AS last_active_week FROM user_week_age GROUP BY 1,2
),
unbounded_counts AS (
SELECT la.cohort_week_start, gs AS user_lifetime_week, COUNT(*) AS retained_users_unbounded
FROM last_active la
CROSS JOIN LATERAL generate_series(0, LEAST(la.last_active_week,(SELECT max_weeks FROM params))) gs
GROUP BY 1,2
),
cohort_sizes AS (SELECT cohort_week_start, COUNT(DISTINCT user_id) AS cohort_users FROM first_exec GROUP BY 1),
cohort_caps AS (
SELECT cs.cohort_week_start, cs.cohort_users,
LEAST((SELECT max_weeks FROM params),
GREATEST(0,((DATE_TRUNC('week',CURRENT_DATE)::date-cs.cohort_week_start)/7)::int)) AS cap_weeks
FROM cohort_sizes cs
),
grid AS (
SELECT cc.cohort_week_start, gs AS user_lifetime_week, cc.cohort_users
FROM cohort_caps cc CROSS JOIN LATERAL generate_series(0, cc.cap_weeks) gs
)
SELECT
g.cohort_week_start,
TO_CHAR(g.cohort_week_start,'IYYY-"W"IW') AS cohort_label,
TO_CHAR(g.cohort_week_start,'IYYY-"W"IW')||' (n='||g.cohort_users||')' AS cohort_label_n,
g.user_lifetime_week, g.cohort_users,
COALESCE(b.active_users_bounded,0) AS active_users_bounded,
COALESCE(u.retained_users_unbounded,0) AS retained_users_unbounded,
CASE WHEN g.cohort_users>0 THEN COALESCE(b.active_users_bounded,0)::float/g.cohort_users END AS retention_rate_bounded,
CASE WHEN g.cohort_users>0 THEN COALESCE(u.retained_users_unbounded,0)::float/g.cohort_users END AS retention_rate_unbounded,
CASE WHEN g.user_lifetime_week=0 THEN g.cohort_users ELSE 0 END AS cohort_users_w0
FROM grid g
LEFT JOIN bounded_counts b ON b.cohort_week_start=g.cohort_week_start AND b.user_lifetime_week=g.user_lifetime_week
LEFT JOIN unbounded_counts u ON u.cohort_week_start=g.cohort_week_start AND u.user_lifetime_week=g.user_lifetime_week
ORDER BY g.cohort_week_start, g.user_lifetime_week;