db-mcp 1.1.0 → 2.0.0

package/test-server/test-tool-groups/test-admin-core.md

@@ -0,0 +1,165 @@
+# db-mcp Tool Group Testing: [admin-core]
+
+> [!IMPORTANT]
+> **Do not track progress in this file.** Track your test progress, coverage matrix, and findings in your internal task tracking system (artifact). However, you SHOULD edit this file to fix any factual errors, broken code, or incorrect assertions in the test prompts.
+> If there is nothing to fix, don't update UNRELEASED.md.
+> We're currently testing Native mode.
+
+## WASM Mode
+
+> When testing against a **WASM backend** (`sqlite-wasm` / sql.js), apply these adjustments:
+>
+> - **Items 13-15** (`sqlite_backup`, `sqlite_verify_backup`, `sqlite_restore`) — return `{success: false, error: "...WASM mode"}`. Treat as **negative validation** — verify the structured error, do not skip.
+> - **Item 10** (`sqlite_pragma_compile_options` FTS filter) — WASM shows FTS3 instead of FTS5.
+> - **Item 3** (`sqlite_dbstat` with `summarize: true`) — WASM returns counts-only (JS fallback) instead of per-table storage breakdown.
+
+**Step 1:** Confirm you read the server help content sourced from `C:\Users\chris\Desktop\db-mcp\src\constants\server-instructions\gotchas.md` using `view_file` (not grep or search) — to understand documented behaviors, edge cases, and response structures for this tool group.
+
+**Step 2:** Please conduct an exhaustive test of the **admin-core** tool group specified in the group-specific checklist below using live MCP server tool calls directly — not scripts/terminal.
+
+**Step 3:** The agent should update C:\Users\chris\Desktop\db-mcp\UNRELEASED.md with any/all changes/fixes.
+
+**Note** If temp tables are present from a previous test pass, it's because the database is locked. Ignore them.
+
+## Reporting Format
+
+- ❌ Fail: Tool errors or produces incorrect results (include error message)
+- ⚠️ Issue: Unexpected behavior or improvement opportunity
+- 📦 Payload: Unnecessarily large response that should be optimized — **blocking, equally important as ❌ bugs**.
+
+## Test Database Schema
+
+| Table             | Rows | Columns                                                                       | JSON Columns                                                                              |
+| ----------------- | ---- | ----------------------------------------------------------------------------- | ----------------------------------------------------------------------------------------- |
+| test_products     | 16   | id, name, description, price, category, created_at                            | —                                                                                         |
+| test_orders       | 20   | id, product_id (FK), customer_name, quantity, total_price, order_date, status | —                                                                                         |
+| test_jsonb_docs   | 6    | id, doc, metadata, tags, created_at                                           | **doc**, **metadata** (nested), **tags** (array)                                          |
+| test_articles     | 8    | id, title, body, author, category, published_at                               | —                                                                                         |
+| test_users        | 9    | id, username, email, phone, bio, created_at                                   | —                                                                                         |
+| test_measurements | 200  | id, sensor_id, temperature, humidity, pressure, measured_at                   | —                                                                                         |
+| test_embeddings   | 20   | id, content, category, embedding                                              | **embedding** (8-dim float array); category values: database, fitness, food, tech, travel |
+| test_locations    | 15   | id, name, city, latitude, longitude, type                                     | —                                                                                         |
+| test_categories   | 17   | id, name, path, level                                                         | —                                                                                         |
+| test_events       | 100  | id, event_type, user_id (INT, 8 values), payload, event_date                  | **payload** (JSON)                                                                        |
+
+## Testing Requirements
+
+> [!CAUTION]
+> **Zero tolerance for raw MCP errors.** ANY response that is a raw MCP error (e.g., `-32602`, `isError: true`, no `success` field) is a **bug that must be reported and fixed**.
+
+1. Use existing `test_*` tables for read operations
+2. Create temporary views with `temp_view_*` prefix for write operations
+3. **Error path testing**: For **every** tool, test (a) domain error and (b) Zod validation error (`{}`). Both must return `{success: false, error: "..."}`.
+4. **Output schema testing**: For tools with `outputSchema`, confirm valid calls return structured JSON.
+
+## Structured Error Response Pattern
+
+```json
+{ "success": false, "error": "Human-readable error message" }
+```
+
+| Type                 | Source                                                             | What you see                                                | Verdict            |
+| -------------------- | ------------------------------------------------------------------ | ----------------------------------------------------------- | ------------------ |
+| **Handler error** ✅ | Handler catches error and returns `{success: false, error: "..."}` | Parseable JSON object with `success` and `error` fields     | Correct            |
+| **MCP error** ❌     | Uncaught throw propagates to MCP framework                         | Raw text error string, `isError: true` — no `success` field | Bug — report as ❌ |
+
+### Zod Validation Errors
+
+**Zod refinement leak pattern:** `.partial()` does NOT strip `.min(N)` / `.max(N)` refinements. **Fix:** Remove refinements from schema, validate inside handler.
+
+### Output Schema Validation Errors
+
+If valid inputs return raw MCP `-32602` mentioning "output schema", report as ❌.
+
+---
+
+## Group Focus: admin-core
+
+> **Instructions**: Execute every numbered checklist item with the exact inputs shown. Compare responses against the expected results. Report any deviation.
+
+### admin-core Group Tools (19)
+
+1. sqlite_create_view
+2. sqlite_list_views
+3. sqlite_drop_view
+4. sqlite_dbstat
+5. sqlite_vacuum
+6. sqlite_backup
+7. sqlite_analyze
+8. sqlite_integrity_check
+9. sqlite_optimize
+10. sqlite_restore
+11. sqlite_verify_backup
+12. sqlite_index_stats
+13. sqlite_pragma_compile_options
+14. sqlite_pragma_database_list
+15. sqlite_pragma_optimize
+16. sqlite_pragma_settings
+17. sqlite_pragma_table_info
+18. sqlite_append_insight
+19. sqlite_execute_code
+
+**Checklist — Pragma & Inspection:**
+
+1. `sqlite_pragma_database_list` → verify database path matches `test.db`
+2. `sqlite_index_stats` → verify index statistics for test database
+3. `sqlite_dbstat({summarize: true})` → per-table storage metrics
+4. `sqlite_integrity_check` → `ok` result
+5. `sqlite_analyze` → success
+6. `sqlite_vacuum` → success
+7. `sqlite_optimize` → success with optimization details
+8. `sqlite_pragma_optimize` → success (note: distinct from `sqlite_optimize` — this runs `PRAGMA optimize`)
+9. `sqlite_pragma_compile_options` → verify list of compile options returned
+10. `sqlite_pragma_compile_options({filter: "FTS"})` → filtered subset containing FTS-related options (`ENABLE_FTS3`, `ENABLE_FTS4`, `ENABLE_FTS5`)
+11. `sqlite_pragma_settings({pragma: "journal_mode"})` → `{value: "wal"}`
+12. `sqlite_pragma_table_info({table: "test_products"})` → verify columns: id, name, description, price, category, created_at
+
+**Checklist — Backup/Restore:**
+
+13. `sqlite_backup({targetPath: "<absolute-path>/test-server/test-backup.db"})` → success with backup file info (⚠️ use absolute path — relative paths resolve from IDE CWD)
+14. `sqlite_verify_backup({backupPath: "<absolute-path>/test-server/test-backup.db"})` → integrity verified
+15. `sqlite_restore({sourcePath: "<absolute-path>/test-server/test-backup.db"})` → restore from backup, verify success
+16. Cleanup: note backup file location for manual removal if desired
+
+**Checklist — View Management:**
+
+17. `sqlite_create_view({viewName: "temp_view_orders", selectQuery: "SELECT product_id, COUNT(*) as order_count, SUM(total_price) as revenue FROM test_orders GROUP BY product_id"})` → success
+18. `sqlite_list_views` → verify `temp_view_orders` present
+19. `sqlite_drop_view({viewName: "temp_view_orders"})` → success
+
+**Checklist — Insights:**
+
+20. `sqlite_append_insight({insight: "Test insight for verification"})` → success
+
+**Code mode testing:**
+
+21. `sqlite_execute_code({code: "const result = await sqlite.admin.integrityCheck(); return result;"})` → `ok` result
+22. `sqlite_execute_code({code: "const result = await sqlite.admin.pragmaSettings({pragma: 'journal_mode'}); return result;"})` → `{pragma: "journal_mode", value: "wal"}`
+
+**Error path testing:**
+
+🔴 23. `sqlite_pragma_table_info({table: "nonexistent_table_xyz"})` → report behavior
+🔴 24. `sqlite_verify_backup({backupPath: "nonexistent_file.db"})` → structured error
+
+**Zod validation sweep** — call each tool with `{}` (empty params). Must return handler error, NOT raw MCP error:
+
+🔴 25. `sqlite_backup({})` → handler error
+🔴 26. `sqlite_restore({})` → handler error
+🔴 27. `sqlite_verify_backup({})` → handler error
+🔴 28. `sqlite_pragma_table_info({})` → handler error
+🔴 29. `sqlite_pragma_settings({})` → handler error (has required `pragma` param)
+🔴 30. `sqlite_append_insight({})` → handler error
+🔴 31. `sqlite_create_view({})` → handler error
+🔴 32. `sqlite_drop_view({})` → handler error
+🔴 33. `sqlite_dbstat({})` → handler error (or success if no required params)
+
+---
+
+## Post-Test Procedures
+
+1. **Triage findings**: Create implementation plan if issues found
+2. **Scope of fixes**: Handler code, server-instructions, test database, this prompt
+3. **Validate**: Instruct the user to run the test suite (Vitest/Playwright), lint, and typecheck. Do NOT run them yourself.
+4. **Commit**: Stage and commit — do NOT push
+5. **Live re-test**: After server rebuild
+6. **Final summary**: After testing/re-testing

package/test-server/test-tool-groups/test-admin-extensions.md

@@ -0,0 +1,133 @@
+# db-mcp Tool Group Testing: [admin-extensions]
+
+> [!IMPORTANT]
+> **Do not track progress in this file.** Track your test progress, coverage matrix, and findings in your internal task tracking system (artifact). However, you SHOULD edit this file to fix any factual errors, broken code, or incorrect assertions in the test prompts.
+> If there is nothing to fix, don't update UNRELEASED.md.
+> We're currently testing Native mode.
+
+## WASM Mode
+
+> When testing against a **WASM backend** (`sqlite-wasm` / sql.js), apply these adjustments:
+>
+> - **Items 3-4** (`sqlite_create_csv_table`, `sqlite_analyze_csv_schema`) — return `{success: false}` in WASM (CSV extension unavailable). Treat as **negative validation**.
+> - **Item 5** (`sqlite_create_rtree_table`) — returns `{success: false}` in WASM (R-Tree unavailable). Treat as **negative validation**.
+> - **Item 1** (`sqlite_list_virtual_tables`) — `test_articles_fts` may appear but is not queryable.
+
+**Step 1:** Confirm you read the server help content sourced from `C:\Users\chris\Desktop\db-mcp\src\constants\server-instructions\gotchas.md` using `view_file` (not grep or search) — to understand documented behaviors, edge cases, and response structures for this tool group.
+
+**Step 2:** Please conduct an exhaustive test of the **admin-extensions** tool group specified in the group-specific checklist below using live MCP server tool calls directly — not scripts/terminal.
+
+**Step 3:** The agent should update C:\Users\chris\Desktop\db-mcp\UNRELEASED.md with any/all changes/fixes.
+
+**Note** If temp tables are present from a previous test pass, it's because the database is locked. Ignore them.
+
+## Reporting Format
+
+- ❌ Fail: Tool errors or produces incorrect results (include error message)
+- ⚠️ Issue: Unexpected behavior or improvement opportunity
+- 📦 Payload: Unnecessarily large response that should be optimized.
+
+## Test Database Schema
+
+| Table             | Rows | Columns                                                                       | JSON Columns                                                                              |
+| ----------------- | ---- | ----------------------------------------------------------------------------- | ----------------------------------------------------------------------------------------- |
+| test_products     | 16   | id, name, description, price, category, created_at                            | —                                                                                         |
+| test_orders       | 20   | id, product_id (FK), customer_name, quantity, total_price, order_date, status | —                                                                                         |
+| test_jsonb_docs   | 6    | id, doc, metadata, tags, created_at                                           | **doc**, **metadata** (nested), **tags** (array)                                          |
+| test_articles     | 8    | id, title, body, author, category, published_at                               | —                                                                                         |
+| test_users        | 9    | id, username, email, phone, bio, created_at                                   | —                                                                                         |
+| test_measurements | 200  | id, sensor_id, temperature, humidity, pressure, measured_at                   | —                                                                                         |
+| test_embeddings   | 20   | id, content, category, embedding                                              | **embedding** (8-dim float array); category values: database, fitness, food, tech, travel |
+| test_locations    | 15   | id, name, city, latitude, longitude, type                                     | —                                                                                         |
+| test_categories   | 17   | id, name, path, level                                                         | —                                                                                         |
+| test_events       | 100  | id, event_type, user_id (INT, 8 values), payload, event_date                  | **payload** (JSON)                                                                        |
+
+## Testing Requirements
+
+> [!CAUTION]
+> **Zero tolerance for raw MCP errors.** ANY response that is a raw MCP error (e.g., `-32602`, `isError: true`, no `success` field) is a **bug that must be reported and fixed**.
+
+1. Use existing `test_*` tables for read operations
+2. Create temporary tables with `temp_*` prefix for write operations
+3. **Error path testing**: For **every** tool, test (a) domain error and (b) Zod validation error (`{}`). Both must return `{success: false, error: "..."}`.
+4. **Output schema testing**: For tools with `outputSchema`, confirm valid calls return structured JSON.
+
+## Structured Error Response Pattern
+
+```json
+{ "success": false, "error": "Human-readable error message" }
+```
+
+| Type                 | Source                                                             | What you see                                                | Verdict            |
+| -------------------- | ------------------------------------------------------------------ | ----------------------------------------------------------- | ------------------ |
+| **Handler error** ✅ | Handler catches error and returns `{success: false, error: "..."}` | Parseable JSON object with `success` and `error` fields     | Correct            |
+| **MCP error** ❌     | Uncaught throw propagates to MCP framework                         | Raw text error string, `isError: true` — no `success` field | Bug — report as ❌ |
+
+### Zod Validation Errors
+
+**Zod refinement leak pattern:** `.partial()` does NOT strip `.min(N)` / `.max(N)` refinements. **Fix:** Remove refinements from schema, validate inside handler.
+
+### Output Schema Validation Errors
+
+If valid inputs return raw MCP `-32602` mentioning "output schema", report as ❌.
+
+---
+
+## Group Focus: admin-extensions
+
+> **Instructions**: Execute every numbered checklist item with the exact inputs shown. Compare responses against the expected results. Report any deviation.
+
+> **CSV Testing Note:** Use `test-server/sample.csv` (columns: id, name, category, price, quantity, created_at) with **absolute paths** for CSV tool testing — relative paths resolve from IDE CWD.
+
+### admin-extensions Group Tools (8)
+
+1. sqlite_generate_series
+2. sqlite_list_virtual_tables
+3. sqlite_virtual_table_info
+4. sqlite_drop_virtual_table
+5. sqlite_create_csv_table
+6. sqlite_analyze_csv_schema
+7. sqlite_create_rtree_table
+8. sqlite_create_series_table
+
+**Checklist:**
+
+**Virtual Tables:**
+
+1. `sqlite_list_virtual_tables` → verify `test_articles_fts` present (Native)
+2. `sqlite_virtual_table_info({tableName: "test_articles_fts"})` → verify module and column info (Native)
+3. `sqlite_generate_series({start: 1, stop: 5, step: 1})` → 5 values
+4. `sqlite_create_rtree_table({tableName: "temp_rtree_test", dimensions: 2})` → R-Tree virtual table created with 2D bounding box columns
+5. `sqlite_create_series_table({tableName: "temp_series_test", start: 1, stop: 10})` → regular table created with 10 rows (not a virtual table — see gotcha #14)
+6. Cleanup: `sqlite_drop_virtual_table({tableName: "temp_rtree_test"})` and `sqlite_drop_table({table: "temp_series_test"})` (series is a regular table — use core `sqlite_drop_table`)
+
+**CSV:**
+
+7. `sqlite_analyze_csv_schema({filePath: "<absolute-path>/test-server/sample.csv"})` → inferred column types (⚠️ CSV requires absolute paths — see gotcha #13)
+8. `sqlite_create_csv_table({tableName: "temp_csv_test", filePath: "<absolute-path>/test-server/sample.csv"})` → virtual table created
+9. Cleanup: `sqlite_drop_virtual_table({tableName: "temp_csv_test"})`
+
+**Error path testing:**
+
+🔴 10. `sqlite_virtual_table_info({tableName: "nonexistent_table_xyz"})` → structured error
+
+**Zod validation sweep** — call each tool with `{}` (empty params). Must return handler error, NOT raw MCP error:
+
+🔴 11. `sqlite_virtual_table_info({})` → handler error
+🔴 12. `sqlite_drop_virtual_table({})` → handler error
+🔴 13. `sqlite_create_csv_table({})` → handler error
+🔴 14. `sqlite_analyze_csv_schema({})` → handler error
+🔴 15. `sqlite_create_rtree_table({})` → handler error
+🔴 16. `sqlite_create_series_table({})` → handler error
+🔴 17. `sqlite_generate_series({})` → handler error
+
+---
+
+## Post-Test Procedures
+
+1. **Triage findings**: Create implementation plan if issues found
+2. **Scope of fixes**: Handler code, server-instructions, test database, this prompt
+3. **Validate**: Instruct the user to run the test suite (Vitest/Playwright), lint, and typecheck. Do NOT run them yourself.
+4. **Commit**: Stage and commit — do NOT push
+5. **Live re-test**: After server rebuild
+6. **Final summary**: After testing/re-testing

package/test-server/{test-tools.md → test-tool-groups/test-core-data.md}

@@ -1,13 +1,28 @@
-# db-mcp (SQLite) Tool Testing
+# db-mcp Tool Group Testing: [core-data]
 
-**Ignore WASM content. Test Native Mode Only**
+> [!IMPORTANT]
+> **Do not track progress in this file.** Track your test progress, coverage matrix, and findings in your internal task tracking system (artifact). However, you SHOULD edit this file to fix any factual errors, broken code, or incorrect assertions in the test prompts.
+> If there is nothing to fix, don't update UNRELEASED.md.
+> We're currently testing Native mode.
+
+## WASM Mode
+
+> When testing against a **WASM backend** (`sqlite-wasm` / sql.js): All 7 core data tools are fully WASM-compatible. No items to skip or adjust.
 
 **Step 1:** Confirm you read the server help content sourced from `C:\Users\chris\Desktop\db-mcp\src\constants\server-instructions\gotchas.md` using `view_file` (not grep or search) — to understand documented behaviors, edge cases, and response structures for this tool group.
 
-**Step 2:** Please conduct an exhaustive test of the tool group specified in the group-specific checklist (pasted after this document) using live MCP server tool calls directly — not scripts/terminal.
+**Step 2:** Please conduct an exhaustive test of the **core-data** tool group specified in the group-specific checklist below using live MCP server tool calls directly — not scripts/terminal.
+
+**Step 3:** The agent should update C:\Users\chris\Desktop\db-mcp\UNRELEASED.md with any/all changes/fixes.
 
 **Note** If temp tables are present from a previous test pass, it's because the database is locked. Ignore them.
 
+## Reporting Format
+
+- ❌ Fail: Tool errors or produces incorrect results (include error message)
+- ⚠️ Issue: Unexpected behavior or improvement opportunity
+- 📦 Payload: Unnecessarily large response that should be optimized — **blocking, equally important as ❌ bugs**. Oversized payloads waste LLM context window tokens and degrade downstream tool-calling quality. Report the response size in KB and suggest a concrete optimization (e.g., filter system tables, add `compact` option, omit empty arrays).
+
 ## Test Database Schema
 
 The test database (test-server/test.db) contains these tables with JSON-relevant columns:
@@ -36,8 +51,6 @@ The test database (test-server/test.db) contains these tables with JSON-relevant
 
 > **Note:** `test_measurements.sensor_id` is an **INTEGER** column (values 1-5), not a string. Use `sensor_id = 1`, not `sensor_id = 'S001'`.
 
-> **Note:** When testing `sqlite_execute_code`, do **not** pass `readonly: true` unless specifically testing read-only filtering. The `readonly` flag makes write methods return structured errors (`{success: false, code: "CODEMODE_READONLY_VIOLATION"}`). Methods remain callable but reject write operations. Use `readonly: false` (or omit it) to get the full API surface.
-
 ## Testing Requirements
 
 > [!CAUTION]
@@ -49,8 +62,9 @@ The test database (test-server/test.db) contains these tables with JSON-relevant
 4. Report all failures, unexpected behaviors, improvement opportunities, or unnecessarily large payloads
 5. Do not mention what already works well or issues well documented in help resources and runtime hints which are already optimal
 6. **Error path testing**: For **every** tool, test at least **two** invalid inputs: (a) a domain error (nonexistent table, invalid column, missing required parameter) and (b) a **Zod validation error** (call the tool with `{}` empty params if it has required parameters, or pass the wrong type). Both must return a **structured handler error** (`{success: false, error: "..."}`) — NOT a raw MCP error frame. See the "Structured Error Response Pattern" section below for how to distinguish the two. This is the most common deficiency found across tool groups.
-7. **Output schema testing**: For **every** tool that has an `outputSchema`, confirm that at least one valid happy-path call returns a structured JSON response — NOT a raw MCP `-32602` "output schema" error. Output schema mismatches (handler returns fields not declared in the schema) produce the same `-32602` code as input errors but are only caught with valid inputs. See "Output Schema Validation Errors" below. Also check for the inverse: if a schema is **defined** in `src/adapters/sqlite/output-schemas/` but **not wired** to the tool definition, report as ⚠️ — the schema exists but provides no enforcement.
+7. **Output schema testing**: For **every** tool that has an `outputSchema`, confirm that at least one valid happy-path call returns a structured JSON response — NOT a raw MCP `-32602` "output schema" error. Output schema mismatches (handler returns fields not declared in the schema) produce the same `-32602` code as input errors but are only caught with valid inputs. See "Output Schema Validation Errors" below. Also check for the inverse: if a schema is **defined** in `src/adapters/sqlite/schemas/` but **not wired** to the tool definition, report as ⚠️ — the schema exists but provides no enforcement.
 8. **Deterministic checklist first**: Complete ALL items in the group-specific checklist before moving to freeform exploration. The checklist uses exact inputs and expected outputs to ensure reproducible coverage every run.
+9. **Code Over Docs**: Fix the handler code if standards (Structured Errors/Zod) are violated. Do NOT change docs/prompts to accommodate broken code.
 
 ## Structured Error Response Pattern
 
@@ -119,7 +133,7 @@ The MCP SDK enforces `additionalProperties: false` on **output** schemas. If a h
 - **Input `-32602`**: Triggered by sending unrecognized/invalid parameters → caught by the Zod sweep (call with `{}` or `extraParam`)
 - **Output `-32602`**: Triggered by the handler **returning** undeclared fields → caught by a valid happy-path call that still produces a raw MCP error
 
-**How to detect:** If a tool call with **correct, valid inputs** returns a raw MCP `-32602` mentioning "does not match the tool's output schema" or "additional properties", the output schema in `src/adapters/sqlite/output-schemas/` is missing fields that the handler returns. Report as ❌ with both the tool name and the missing field(s).
+**How to detect:** If a tool call with **correct, valid inputs** returns a raw MCP `-32602` mentioning "does not match the tool's output schema" or "additional properties", the output schema in `src/adapters/sqlite/schemas/` is missing fields that the handler returns. Report as ❌ with both the tool name and the missing field(s).
 
 **Fix pattern:** Add the missing fields to the output schema (e.g., `durationMs: z.number().optional()`, `message: z.string().optional()`). Do NOT remove fields from the handler response — the schema must match reality.
 
@@ -134,8 +148,21 @@ During testing, check for these inconsistencies across tool groups:
 3. **Zod validation leaks**: If calling a tool with an invalid enum value or missing required field produces a raw MCP `-32602` error instead of a structured response, report as ❌.
 4. **Output schema leaks**: If calling a tool with valid inputs produces a raw MCP `-32602` mentioning "output schema" or "additional properties", report as ❌ (see "Output Schema Validation Errors" above).
 5. **Centralized error formatting**: db-mcp uses `DbMcpError`. If any tool group catches errors but formats them inconsistently (e.g., different message patterns for the same error type), report as ⚠️.
-6. **Orphaned output schemas**: If a schema is exported from `src/adapters/sqlite/output-schemas/` (e.g., `TransactionBeginOutputSchema`) but the corresponding tool definition does not reference it via `outputSchema`, report as ⚠️. Use `grep_search` to check whether the schema name appears in any tool file under `src/adapters/`. Defined-but-unwired schemas provide zero enforcement.
-7. **Inline output schemas**: If any tool defines `outputSchema: z.object({...})` inline in the handler file instead of importing a named schema from `output-schemas/`, report as ⚠️. All output schemas must live in `src/adapters/sqlite/output-schemas/` with named exports. Use `grep_search` with pattern `outputSchema: z.object` across `src/adapters/` to detect violations.
+6. **Orphaned output schemas**: If a schema is exported from `src/adapters/sqlite/schemas/` (e.g., `TransactionBeginOutputSchema`) but the corresponding tool definition does not reference it via `outputSchema`, report as ⚠️. Use `grep_search` to check whether the schema name appears in any tool file under `src/adapters/`. Defined-but-unwired schemas provide zero enforcement.
+7. **Inline output schemas**: If any tool defines `outputSchema: z.object({...})` inline in the handler file instead of importing a named schema from `schemas/`, report as ⚠️. All output schemas must live in `src/adapters/sqlite/schemas/` with named exports. Use `grep_search` with pattern `outputSchema: z.object` across `src/adapters/` to detect violations.
+
+## Error Path Testing Checklist
+
+For each tool group under test, verify at least one scenario from each applicable row:
+
+| Error Scenario                    | Tool Groups to Test                 | Example Input                                                           |
+| --------------------------------- | ----------------------------------- | ----------------------------------------------------------------------- |
+| Nonexistent table                 | All table-accepting tools           | `table: "nonexistent_xyz"`                                              |
+| Invalid SQL syntax                | Core (`read_query`, `write_query`)  | `query: "SELEKT * FROM"`                                                |
+| Invalid column name               | Stats, JSON, text, vector, geo      | `column: "nonexistent_col"`                                             |
+| Missing required field            | All tools with required params      | Omit `table`, `query`, etc.                                             |
+| **Zod validation (empty params)** | **Every tool with required params** | `{}` (empty object — must return handler error, not MCP `-32602` error) |
+| **Zod validation (wrong type)**   | **Tools with typed params**         | Pass string where number expected, etc.                                 |
 
 ### Split Schema Pattern Verification
 
@@ -144,11 +171,72 @@ All tools use the Split Schema pattern: a plain `z.object()` Base schema for MCP
 1. **Parameter visibility**: For tools with optional parameters (e.g., `limit`, `readonly`), make a direct MCP call using those parameters. If the tool ignores or rejects documented parameters, report as a Split Schema violation.
 2. **Alias acceptance**: For tools with documented parameter aliases (e.g., `table`/`tableName`, `query`/`sql`, `indexName`/`name`), verify that direct MCP tool calls correctly accept the aliases.
 
-## Reporting Format
+## Cleanup Conventions
 
-- ❌ Fail: Tool errors or produces incorrect results (include error message)
-- ⚠️ Issue: Unexpected behavior or improvement opportunity
-- 📦 Payload: Unnecessarily large response that should be optimized — **blocking, equally important as ❌ bugs**. Oversized payloads waste LLM context window tokens and degrade downstream tool-calling quality. Report the response size in KB and suggest a concrete optimization (e.g., filter system tables, add `compact` option, omit empty arrays).
+During testing, use these naming conventions:
+
+- **Temporary tables**: Prefix with `temp_` (e.g., `temp_core_test`)
+
+After testing, clean up:
+
+```sql
+-- Drop temp table
+DROP TABLE IF EXISTS temp_core_test;
+```
+
+---
+
+## Group Focus: core-data
+
+> **Instructions**: Execute every numbered checklist item with the exact inputs shown. Compare responses against the expected results. Report any deviation.
+
+### Built-in Tools (3)
+
+1. server_info
+2. server_health
+3. list_adapters
+
+### core-data Group Tools (7)
+
+4. sqlite_read_query
+5. sqlite_write_query
+6. sqlite_upsert
+7. sqlite_batch_insert
+8. sqlite_count
+9. sqlite_exists
+10. sqlite_truncate
+
+**Checklist:**
+
+1. `server_info` → verify server name, version, adapter info present
+2. `server_health` → verify healthy status
+3. `list_adapters` → verify at least one adapter listed
+4. `sqlite_read_query({query: "SELECT COUNT(*) AS n FROM test_products"})` → `{rows: [{n: 16}]}`
+5. `sqlite_read_query({query: "SELECT name, price FROM test_products WHERE price > ?", params: [500]})` → 1 result: `Laptop Pro 15` (1299.99) (Note: Parameter binding test)
+6. `sqlite_read_query({query: "SELECT COUNT(*) AS n FROM test_orders WHERE status = 'completed'"})` → `{rows: [{n: 8}]}`
+7. `sqlite_create_table({table: "temp_core_test2", columns: [{name: "id", type: "INTEGER", primaryKey: true}, {name: "val", type: "TEXT"}]})` → success
+8. `sqlite_batch_insert({table: "temp_core_test2", rows: [{id: 1, val: "a"}, {id: 2, val: "b"}], returning: true})` → `{rowsAffected: 2}` and returns inserted rows (Note: Test `returning` parameter)
+9. `sqlite_upsert({table: "temp_core_test2", data: {id: 1, val: "c"}, conflictColumns: ["id"], updateColumns: ["val"], returning: true})` → `{rowsAffected: 1}` and returns updated row
+10. `sqlite_count({table: "test_products"})` → `{count: 16}`
+11. `sqlite_exists({table: "test_products", where: "id = 1"})` → `{exists: true}`
+12. `sqlite_truncate({table: "temp_core_test2"})` → `{rowsAffected: 2}`
+13. `sqlite_drop_table({table: "temp_core_test2"})` → success
+
+**Error path testing:**
+
+🔴 14. `sqlite_read_query({query: "SELECT * FROM nonexistent_table_xyz"})` → structured error mentioning table name
+
+**Zod validation sweep** — call each tool with `{}` (empty params). Every response must be a handler error (`{success: false, error: "Validation error: ..."}`) — NOT a raw MCP error frame:
+
+🔴 15. `sqlite_read_query({})` → handler error
+🔴 16. `sqlite_write_query({})` → handler error
+🔴 17. `sqlite_upsert({})` → handler error
+🔴 18. `sqlite_batch_insert({})` → handler error
+🔴 19. `sqlite_count({})` → handler error
+🔴 20. `sqlite_exists({})` → handler error
+🔴 21. `sqlite_truncate({})` → handler error
+
+---
 
 ## Post-Test Procedures
 
@@ -164,13 +252,11 @@ All tools use the Split Schema pattern: a plain `z.object()` Base schema for MCP
    - Handler code
    - `src/constants/server-instructions/*.md` (per-group help files) — run `npm run generate:instructions` after editing to regenerate `server-instructions.ts`
    - Test database (`test-server/test.db`)
-   - This prompt (`test-tools.md`) and group file (`test-group-tools.md`)
+   - This prompt
 
 ### After Implementation
 
-3. **Validate**: Run test suite and fix broken tests, run lint + typecheck and fix issues, update changelog (no duplicate headers)
+3. **Validate**: Instruct the user to run the test suite (Vitest/Playwright), lint, and typecheck. Do NOT run them yourself.
 4. **Commit**: Stage and commit all changes — do NOT push
 5. **Live re-test**: Test fixes with direct MCP tool calls. I will have already rebuilt and restarted the server.
 6. **Final summary**: If no issues found, provide the final summary after testing. If issues were fixed, provide the summary after live MCP re-testing confirms fixes are working. If the test prompt/database can be improved, make the improvements.
-
----