@bonnard/cli 0.2.1 → 0.2.3

package/dist/bin/{cubes-Bf0IPYd7.mjs → cubes-9rklhdAJ.mjs}

@@ -1,4 +1,4 @@
-import { t as getProjectPaths } from "./bon.mjs";
+import { i as getProjectPaths } from "./bon.mjs";
 import fs from "node:fs";
 import path from "node:path";
 import YAML from "yaml";

package/dist/bin/push-mZujN1Ik.mjs

@@ -0,0 +1,35 @@
+import { n as resolveEnvVarsInCredentials, r as post, t as getLocalDatasource } from "./bon.mjs";
+import pc from "picocolors";
+import { confirm } from "@inquirer/prompts";
+
+//#region src/commands/datasource/push.ts
+/**
+* Push a datasource programmatically (for use by deploy command)
+* Returns true on success, false on failure
+*/
+async function pushDatasource(name, options = {}) {
+	const datasource = getLocalDatasource(name);
+	if (!datasource) {
+		if (!options.silent) console.error(pc.red(`Datasource "${name}" not found locally`));
+		return false;
+	}
+	const { resolved, missing } = resolveEnvVarsInCredentials(datasource.credentials);
+	if (missing.length > 0) {
+		if (!options.silent) console.error(pc.red(`Missing env vars for "${name}": ${missing.join(", ")}`));
+		return false;
+	}
+	try {
+		await post("/api/datasources", {
+			name: datasource.name,
+			warehouse_type: datasource.type,
+			config: datasource.config,
+			credentials: resolved
+		});
+		return true;
+	} catch {
+		return false;
+	}
+}
+
+//#endregion
+export { pushDatasource };

package/dist/bin/{validate-DEh1XQnH.mjs → validate-BdqZBH2n.mjs}

@@ -1,4 +1,4 @@
-import { t as getProjectPaths } from "./bon.mjs";
+import { i as getProjectPaths } from "./bon.mjs";
 import fs from "node:fs";
 import path from "node:path";
 import YAML from "yaml";

package/dist/docs/topics/workflow.deploy.md

@@ -148,7 +148,7 @@ Deploy aborted. Fix validation errors first.
 Deploy aborted. Fix connection issues:
   - Check credentials in .bon/datasources.yaml
   - Verify network access to database
-  - Run: bon datasource test analytics
+  - Run: bon datasource add (to reconfigure)
 ```
 
 ### Auth Errors

package/dist/docs/topics/workflow.md

@@ -146,7 +146,6 @@ bonnard/cubes/
 | `bon datasource add --demo` | Add demo dataset (no warehouse needed) |
 | `bon datasource add --from-dbt` | Import from dbt profiles |
 | `bon datasource list` | List configured sources |
-| `bon datasource test <name>` | Test connection (requires login) |
 | `bon validate` | Check cube and view syntax |
 | `bon deploy -m "message"` | Deploy to Bonnard (message required) |
 | `bon deploy --ci` | Non-interactive deploy |

package/dist/docs/topics/workflow.validate.md

@@ -116,7 +116,7 @@ measures:
 1. **Run before every deploy** — `bon validate && bon deploy`
 2. **Add to CI/CD** — validate on pull requests
 3. **Fix errors first** — don't deploy with validation errors
-4. **Test connections** — use `bon datasource test <name>` to check connectivity
+4. **Test connections** — connections are tested automatically during `bon deploy`
 
 ## See Also
 

package/dist/templates/claude/skills/bonnard-get-started/SKILL.md

@@ -15,29 +15,27 @@ confirming progress before moving on.
 Ask the user if they have a warehouse to connect, or want to try a demo dataset first:
 
 ```bash
-# Option A: Import from dbt (if they use it)
+# Option A: Use demo data (no warehouse needed)
+bon datasource add --demo
+
+# Option B: Import from dbt (if they use it)
 bon datasource add --from-dbt
 
-# Option B: Add manually (interactive)
-bon datasource add
+# Option C: Add manually, non-interactive (preferred for agents)
+bon datasource add --name my_warehouse --type postgres \
+  --host db.example.com --port 5432 --database mydb --schema public \
+  --user myuser --password mypassword
 
-# Option C: Use demo data (no warehouse needed)
-bon datasource add --demo
+# Option D: Add manually, interactive (in user's terminal)
+bon datasource add
 ```
 
+Supported types: `postgres` (also works for Redshift), `snowflake`, `bigquery`, `databricks`.
+
 The demo option adds a read-only Contoso retail dataset with tables like
 `fact_sales`, `dim_product`, `dim_store`, and `dim_customer`.
 
-Then verify the connection works:
-
-```bash
-bon datasource test <name>
-```
-
-If the test fails, common issues:
-- Wrong credentials — re-run `bon datasource add`
-- Network/firewall — check warehouse allows connections from this machine
-- SSL issues (Postgres) — may need `sslmode` in connection config
+The connection will be tested automatically during `bon deploy`.
 
 ## Phase 2: Explore the Data
 

package/dist/templates/claude/skills/bonnard-metabase-migrate/SKILL.md

@@ -0,0 +1,258 @@
+---
+name: bonnard-metabase-migrate
+description: Guide migration from an existing Metabase instance to a Bonnard semantic layer. Use when user says "migrate from metabase", "import metabase", "metabase to semantic layer", or has Metabase data they want to model.
+allowed-tools: Bash(bon *)
+---
+
+# Migrate from Metabase to Bonnard
+
+This skill guides you through analyzing an existing Metabase instance and
+building a semantic layer that replicates its most important metrics.
+Walk through each phase in order, confirming progress before moving on.
+
+## Phase 1: Connect to Metabase
+
+Set up a connection to the Metabase instance:
+
+```bash
+bon metabase connect
+```
+
+This prompts for the Metabase URL and API key. The API key should be created
+in Metabase under Admin > Settings > Authentication > API Keys.
+An admin-level key gives the richest analysis (permissions, schema access).
+
+## Phase 2: Analyze the Instance
+
+Generate an intelligence report that maps the entire Metabase instance:
+
+```bash
+bon metabase analyze
+```
+
+This writes a report to `.bon/metabase-analysis.md`. Read it carefully — it
+drives every decision in the remaining phases.
+
+### How to interpret each section
+
+| Report Section | What It Tells You | Action |
+|----------------|-------------------|--------|
+| **Most Referenced Tables** | Tables used most in SQL queries | Create cubes for these first — they are the core of the data model |
+| **Top Cards by Activity** | Most-viewed questions/models | `analytical` cards (GROUP BY + aggregation) map to measures; `lookup` cards indicate key filter dimensions; `display` cards can be skipped |
+| **Common Filter Variables** | Template vars (`{{var}}`) used across 3+ cards | These must be dimensions on relevant cubes |
+| **Foreign Key Relationships** | FK links between tables | Define `joins` between cubes using these relationships |
+| **Collection Structure** | How users organize content by business area | Map each top-level collection to a view (one view per business domain) |
+| **Dashboard Parameters** | Shared filters across dashboards | The most important shared dimensions — ensure they exist on relevant cubes |
+| **Table Inventory** | Field counts and classification per table | Field classification (dims/measures/time) guides each cube definition; tables with 0 refs can be deprioritized |
+| **Schema Access** | Which schemas non-admin groups can query | Focus on user-facing schemas — skip admin-only/staging schemas |
+
+## Phase 3: Connect the Data Warehouse
+
+Add a datasource pointing to the same database that Metabase queries.
+The database connection details can often be found in Metabase under
+Admin > Databases, or in the analysis report header.
+
+```bash
+# Non-interactive (preferred for agents)
+bon datasource add --name my_warehouse --type postgres \
+  --host db.example.com --port 5432 --database mydb --schema public \
+  --user myuser --password mypassword
+
+# Import from dbt if available
+bon datasource add --from-dbt
+
+# Interactive setup (in user's terminal)
+bon datasource add
+```
+
+Supported types: `postgres` (also works for Redshift), `snowflake`, `bigquery`, `databricks`.
+
+The connection will be tested automatically during `bon deploy`.
+
+## Phase 4: Explore Key Tables
+
+Before writing cubes, drill into the most important tables and cards
+identified in Phase 2. Use the explore commands to understand field types
+and existing SQL patterns:
+
+```bash
+# View table fields with type classification
+bon metabase explore table <id>
+
+# View card SQL and columns
+bon metabase explore card <id>
+
+# View schemas and tables in a database
+bon metabase explore database <id>
+
+# View cards in a collection
+bon metabase explore collection <id>
+```
+
+### How explore output maps to cube definitions
+
+| Explore Field | Cube Mapping |
+|---------------|-------------|
+| Field class `pk` | Set `primary_key: true` on dimension |
+| Field class `fk` | Join candidate — note the target table |
+| Field class `time` | Dimension with `type: time` |
+| Field class `measure` | Measure candidate — check card SQL for aggregation type |
+| Field class `dim` | Dimension with `type: string` or `type: number` |
+
+### How card SQL maps to measures
+
+Look at the SQL in `analytical` cards to determine measure types:
+
+| Card SQL Pattern | Cube Measure |
+|-----------------|-------------|
+| `SUM(amount)` | `type: sum`, `sql: amount` |
+| `COUNT(*)` | `type: count` |
+| `COUNT(DISTINCT user_id)` | `type: count_distinct`, `sql: user_id` |
+| `AVG(price)` | `type: avg`, `sql: price` |
+| `MIN(date)` / `MAX(date)` | `type: min` / `type: max`, `sql: date` |
+
+Use `bon docs cubes.measures.types` for all 12 measure types.
+
+## Phase 5: Build Cubes
+
+Create cubes for the most-referenced tables (from Phase 2). Start with the
+highest-referenced table and work down. Create one file per cube in
+`bonnard/cubes/`.
+
+For each cube:
+1. Set `sql_table` to the full `schema.table` path
+2. Set `data_source` to the datasource name from Phase 3
+3. Add a `primary_key` dimension
+4. Add time dimensions for date/datetime columns
+5. Add measures based on card SQL patterns (Phase 4)
+6. Add dimensions for columns used as filters (template vars from Phase 2)
+7. Add `description` to every measure and dimension
+
+Example — `bonnard/cubes/orders.yaml`:
+
+```yaml
+cubes:
+  - name: orders
+    sql_table: public.orders
+    data_source: my_warehouse
+    description: Order transactions
+
+    measures:
+      - name: count
+        type: count
+        description: Total number of orders
+
+      - name: total_revenue
+        type: sum
+        sql: amount
+        description: Sum of order amounts
+
+    dimensions:
+      - name: id
+        type: number
+        sql: id
+        primary_key: true
+
+      - name: created_at
+        type: time
+        sql: created_at
+        description: Order creation timestamp
+
+      - name: status
+        type: string
+        sql: status
+        description: Order status (pending, completed, cancelled)
+```
+
+### Adding joins
+
+Use FK relationships from the analysis report to define joins between cubes:
+
+```yaml
+    joins:
+      - name: customers
+        sql: "{CUBE}.customer_id = {customers.id}"
+        relationship: many_to_one
+```
+
+Use `bon docs cubes.joins` for the full reference.
+
+## Phase 6: Build Views
+
+Map Metabase collections to views. Each top-level collection (business domain)
+from the analysis report becomes a view that composes the relevant cubes.
+
+Create one file per view in `bonnard/views/`.
+
+Example — `bonnard/views/sales_analytics.yaml`:
+
+```yaml
+views:
+  - name: sales_analytics
+    description: Sales metrics and dimensions for the sales team
+    cubes:
+      - join_path: orders
+        includes:
+          - count
+          - total_revenue
+          - created_at
+          - status
+
+      - join_path: orders.customers
+        prefix: true
+        includes:
+          - name
+          - region
+```
+
+Use `bon docs views` for the full reference.
+
+## Phase 7: Validate and Deploy
+
+Validate the semantic layer:
+
+```bash
+bon validate
+```
+
+Fix any errors. Common issues:
+- Missing `primary_key` dimension
+- Unknown measure/dimension types
+- Undefined cube referenced in a view join path
+- Missing `data_source`
+
+Then deploy:
+
+```bash
+bon login
+bon deploy -m "Migrate semantic layer from Metabase"
+```
+
+## Phase 8: Verify
+
+Compare results from the semantic layer against Metabase card outputs.
+Pick 3-5 important `analytical` cards from the analysis report and run
+equivalent queries:
+
+```bash
+# Run a semantic layer query
+bon query '{"measures": ["orders.total_revenue"], "dimensions": ["orders.status"]}'
+
+# SQL format
+bon query --sql "SELECT status, MEASURE(total_revenue) FROM orders GROUP BY 1"
+```
+
+Compare the numbers with the corresponding Metabase card. If they don't match:
+- Check the SQL in the card (`bon metabase explore card <id>`) for filters or transformations
+- Ensure the measure type matches the aggregation (SUM vs COUNT vs AVG)
+- Check for WHERE clauses that should be segments or pre-filters
+
+## Next Steps
+
+After the core migration is working:
+
+- Add remaining tables as cubes (work down the reference count list)
+- Add calculated measures for complex card SQL (`bon docs cubes.measures.calculated`)
+- Add segments for common WHERE clauses (`bon docs cubes.segments`)
+- Set up MCP for AI agent access (`bon mcp`)
+- Review and iterate with `bon deployments` and `bon diff <id>`

package/dist/templates/cursor/rules/bonnard-get-started.mdc

@@ -14,29 +14,27 @@ confirming progress before moving on.
 Ask the user if they have a warehouse to connect, or want to try a demo dataset first:
 
 ```bash
-# Option A: Import from dbt (if they use it)
+# Option A: Use demo data (no warehouse needed)
+bon datasource add --demo
+
+# Option B: Import from dbt (if they use it)
 bon datasource add --from-dbt
 
-# Option B: Add manually (interactive)
-bon datasource add
+# Option C: Add manually, non-interactive (preferred for agents)
+bon datasource add --name my_warehouse --type postgres \
+  --host db.example.com --port 5432 --database mydb --schema public \
+  --user myuser --password mypassword
 
-# Option C: Use demo data (no warehouse needed)
-bon datasource add --demo
+# Option D: Add manually, interactive (in user's terminal)
+bon datasource add
 ```
 
+Supported types: `postgres` (also works for Redshift), `snowflake`, `bigquery`, `databricks`.
+
 The demo option adds a read-only Contoso retail dataset with tables like
 `fact_sales`, `dim_product`, `dim_store`, and `dim_customer`.
 
-Then verify the connection works:
-
-```bash
-bon datasource test <name>
-```
-
-If the test fails, common issues:
-- Wrong credentials — re-run `bon datasource add`
-- Network/firewall — check warehouse allows connections from this machine
-- SSL issues (Postgres) — may need `sslmode` in connection config
+The connection will be tested automatically during `bon deploy`.
 
 ## Phase 2: Explore the Data
 

package/dist/templates/cursor/rules/bonnard-metabase-migrate.mdc

@@ -0,0 +1,257 @@
+---
+description: "Guide migration from an existing Metabase instance to a Bonnard semantic layer. Use when user says 'migrate from metabase', 'import metabase', 'metabase to semantic layer', or has Metabase data they want to model."
+alwaysApply: false
+---
+
+# Migrate from Metabase to Bonnard
+
+This skill guides you through analyzing an existing Metabase instance and
+building a semantic layer that replicates its most important metrics.
+Walk through each phase in order, confirming progress before moving on.
+
+## Phase 1: Connect to Metabase
+
+Set up a connection to the Metabase instance:
+
+```bash
+bon metabase connect
+```
+
+This prompts for the Metabase URL and API key. The API key should be created
+in Metabase under Admin > Settings > Authentication > API Keys.
+An admin-level key gives the richest analysis (permissions, schema access).
+
+## Phase 2: Analyze the Instance
+
+Generate an intelligence report that maps the entire Metabase instance:
+
+```bash
+bon metabase analyze
+```
+
+This writes a report to `.bon/metabase-analysis.md`. Read it carefully — it
+drives every decision in the remaining phases.
+
+### How to interpret each section
+
+| Report Section | What It Tells You | Action |
+|----------------|-------------------|--------|
+| **Most Referenced Tables** | Tables used most in SQL queries | Create cubes for these first — they are the core of the data model |
+| **Top Cards by Activity** | Most-viewed questions/models | `analytical` cards (GROUP BY + aggregation) map to measures; `lookup` cards indicate key filter dimensions; `display` cards can be skipped |
+| **Common Filter Variables** | Template vars (`{{var}}`) used across 3+ cards | These must be dimensions on relevant cubes |
+| **Foreign Key Relationships** | FK links between tables | Define `joins` between cubes using these relationships |
+| **Collection Structure** | How users organize content by business area | Map each top-level collection to a view (one view per business domain) |
+| **Dashboard Parameters** | Shared filters across dashboards | The most important shared dimensions — ensure they exist on relevant cubes |
+| **Table Inventory** | Field counts and classification per table | Field classification (dims/measures/time) guides each cube definition; tables with 0 refs can be deprioritized |
+| **Schema Access** | Which schemas non-admin groups can query | Focus on user-facing schemas — skip admin-only/staging schemas |
+
+## Phase 3: Connect the Data Warehouse
+
+Add a datasource pointing to the same database that Metabase queries.
+The database connection details can often be found in Metabase under
+Admin > Databases, or in the analysis report header.
+
+```bash
+# Non-interactive (preferred for agents)
+bon datasource add --name my_warehouse --type postgres \
+  --host db.example.com --port 5432 --database mydb --schema public \
+  --user myuser --password mypassword
+
+# Import from dbt if available
+bon datasource add --from-dbt
+
+# Interactive setup (in user's terminal)
+bon datasource add
+```
+
+Supported types: `postgres` (also works for Redshift), `snowflake`, `bigquery`, `databricks`.
+
+The connection will be tested automatically during `bon deploy`.
+
+## Phase 4: Explore Key Tables
+
+Before writing cubes, drill into the most important tables and cards
+identified in Phase 2. Use the explore commands to understand field types
+and existing SQL patterns:
+
+```bash
+# View table fields with type classification
+bon metabase explore table <id>
+
+# View card SQL and columns
+bon metabase explore card <id>
+
+# View schemas and tables in a database
+bon metabase explore database <id>
+
+# View cards in a collection
+bon metabase explore collection <id>
+```
+
+### How explore output maps to cube definitions
+
+| Explore Field | Cube Mapping |
+|---------------|-------------|
+| Field class `pk` | Set `primary_key: true` on dimension |
+| Field class `fk` | Join candidate — note the target table |
+| Field class `time` | Dimension with `type: time` |
+| Field class `measure` | Measure candidate — check card SQL for aggregation type |
+| Field class `dim` | Dimension with `type: string` or `type: number` |
+
+### How card SQL maps to measures
+
+Look at the SQL in `analytical` cards to determine measure types:
+
+| Card SQL Pattern | Cube Measure |
+|-----------------|-------------|
+| `SUM(amount)` | `type: sum`, `sql: amount` |
+| `COUNT(*)` | `type: count` |
+| `COUNT(DISTINCT user_id)` | `type: count_distinct`, `sql: user_id` |
+| `AVG(price)` | `type: avg`, `sql: price` |
+| `MIN(date)` / `MAX(date)` | `type: min` / `type: max`, `sql: date` |
+
+Use `bon docs cubes.measures.types` for all 12 measure types.
+
+## Phase 5: Build Cubes
+
+Create cubes for the most-referenced tables (from Phase 2). Start with the
+highest-referenced table and work down. Create one file per cube in
+`bonnard/cubes/`.
+
+For each cube:
+1. Set `sql_table` to the full `schema.table` path
+2. Set `data_source` to the datasource name from Phase 3
+3. Add a `primary_key` dimension
+4. Add time dimensions for date/datetime columns
+5. Add measures based on card SQL patterns (Phase 4)
+6. Add dimensions for columns used as filters (template vars from Phase 2)
+7. Add `description` to every measure and dimension
+
+Example — `bonnard/cubes/orders.yaml`:
+
+```yaml
+cubes:
+  - name: orders
+    sql_table: public.orders
+    data_source: my_warehouse
+    description: Order transactions
+
+    measures:
+      - name: count
+        type: count
+        description: Total number of orders
+
+      - name: total_revenue
+        type: sum
+        sql: amount
+        description: Sum of order amounts
+
+    dimensions:
+      - name: id
+        type: number
+        sql: id
+        primary_key: true
+
+      - name: created_at
+        type: time
+        sql: created_at
+        description: Order creation timestamp
+
+      - name: status
+        type: string
+        sql: status
+        description: Order status (pending, completed, cancelled)
+```
+
+### Adding joins
+
+Use FK relationships from the analysis report to define joins between cubes:
+
+```yaml
+    joins:
+      - name: customers
+        sql: "{CUBE}.customer_id = {customers.id}"
+        relationship: many_to_one
+```
+
+Use `bon docs cubes.joins` for the full reference.
+
+## Phase 6: Build Views
+
+Map Metabase collections to views. Each top-level collection (business domain)
+from the analysis report becomes a view that composes the relevant cubes.
+
+Create one file per view in `bonnard/views/`.
+
+Example — `bonnard/views/sales_analytics.yaml`:
+
+```yaml
+views:
+  - name: sales_analytics
+    description: Sales metrics and dimensions for the sales team
+    cubes:
+      - join_path: orders
+        includes:
+          - count
+          - total_revenue
+          - created_at
+          - status
+
+      - join_path: orders.customers
+        prefix: true
+        includes:
+          - name
+          - region
+```
+
+Use `bon docs views` for the full reference.
+
+## Phase 7: Validate and Deploy
+
+Validate the semantic layer:
+
+```bash
+bon validate
+```
+
+Fix any errors. Common issues:
+- Missing `primary_key` dimension
+- Unknown measure/dimension types
+- Undefined cube referenced in a view join path
+- Missing `data_source`
+
+Then deploy:
+
+```bash
+bon login
+bon deploy -m "Migrate semantic layer from Metabase"
+```
+
+## Phase 8: Verify
+
+Compare results from the semantic layer against Metabase card outputs.
+Pick 3-5 important `analytical` cards from the analysis report and run
+equivalent queries:
+
+```bash
+# Run a semantic layer query
+bon query '{"measures": ["orders.total_revenue"], "dimensions": ["orders.status"]}'
+
+# SQL format
+bon query --sql "SELECT status, MEASURE(total_revenue) FROM orders GROUP BY 1"
+```
+
+Compare the numbers with the corresponding Metabase card. If they don't match:
+- Check the SQL in the card (`bon metabase explore card <id>`) for filters or transformations
+- Ensure the measure type matches the aggregation (SUM vs COUNT vs AVG)
+- Check for WHERE clauses that should be segments or pre-filters
+
+## Next Steps
+
+After the core migration is working:
+
+- Add remaining tables as cubes (work down the reference count list)
+- Add calculated measures for complex card SQL (`bon docs cubes.measures.calculated`)
+- Add segments for common WHERE clauses (`bon docs cubes.segments`)
+- Set up MCP for AI agent access (`bon mcp`)
+- Review and iterate with `bon deployments` and `bon diff <id>`