Run lint checks (ruff for Python, Biome for TS/JS), type checks (pyright for Python, tsc for TS/JS), and the standard pytest tiers (unit + e2e + tests skipped during pre-commit). Investigates failures to determine if they are application bugs or test issues, and fixes application bugs rather than weakening tests. Does not run paid-LLM real-API tests or scenario probes from the test-* command family.
Installer avec Codex ou Claude Copiez ce prompt, collez-le dans Codex, Claude ou un autre assistant, puis laissez-le vérifier la page du skill et l'installer pour vous.
Une commande directe contourne le prompt de vérification. Examinez la source avant de l'exécuter.
Run lint checks (ruff for Python, Biome for TS/JS), type checks (pyright for Python, tsc for TS/JS), and the standard pytest tiers (unit + e2e + tests skipped during pre-commit). Investigates failures to determine if they are application bugs or test issues, and fixes application bugs rather than weakening tests. Does not run paid-LLM real-API tests or scenario probes from the test-* command family.
Check and Test
Run the standard check-and-test flow (lint + type-check + pytest tiers), including tests normally skipped during pre-commit hooks.
Overview
This command runs the standard check-and-test tiers:
Python lint checks via ruff (code quality, security, complexity)
Python type checks via pyright (type safety)
TypeScript/JavaScript lint checks via Biome (code quality, formatting, import sorting)
TypeScript/JavaScript type checks via tsc (type safety)
Unit tests in reflexio/tests/ (excluding e2e and tests under reflexio/tests/server/llm/)
E2E tests in reflexio/tests/e2e_tests/ (skip all the low priority test by NOT setting RUN_LOW_PRIORITY env variable)
Tests skipped during pre-commit (those decorated with @skip_in_precommit)
The key difference from pre-commit is that PRECOMMIT env var is NOT set, so all tests run.
Prerequisites
Before running tests, activate the virtual environment:
source .venv/bin/activate
Test Execution
IMPORTANT: Run all tests sequentially using -n 0 to avoid test conflicts. The default pytest config uses parallel execution (), but this can cause race conditions and shared state issues between tests.
-n auto
Step 0: Run Lint and Type Checks
Run lint and type checks across the full codebase before running tests.
0a. Ruff auto-fix:
ruff check --fix reflexio/
ruff format reflexio/
0b. Ruff remaining errors:
ruff check reflexio/
If any errors remain that ruff could not auto-fix, read each error, understand the issue, and fix the code yourself. Do NOT skip unfixed lint errors.
0c. Pyright type check:
pyright
Pyright uses pyrightconfig.json for scope. If any type errors are reported, read each error, understand the type issue, and fix the code yourself. Do NOT skip unfixed type errors.
0d. Biome auto-fix (TypeScript/JavaScript):
cd reflexio/website && npx biome check --write . && cd ../..
cd reflexio/public_docs && npx biome check --write . && cd ../..
0e. Biome remaining errors:
cd reflexio/website && npx biome check . && cd ../..
cd reflexio/public_docs && npx biome check . && cd ../..
If any errors remain that Biome could not auto-fix, read each error, understand the issue, and fix the code yourself. Do NOT skip unfixed Biome errors.
0f. TypeScript type check:
cd reflexio/website && npx tsc --noEmit && cd ../..
cd reflexio/public_docs && npx tsc --noEmit && cd ../..
If any type errors are reported, read each error, understand the type issue, and fix the code yourself. Do NOT skip unfixed tsc errors.
Only proceed to tests after all lint and type errors are resolved.
Step 1: Run All Unit Tests (excluding e2e)
Run unit tests first as they are faster and don't require external services:
E2E tests require the server to be running at http://localhost:8081. Run them separately:
pytest reflexio/tests/e2e_tests/ -n 0 -v
Step 3: Run Full Suite (if individual runs pass)
To run everything together:
pytest reflexio/tests/ -n 0 -v
Note: The -n 0 flag disables pytest-xdist parallel execution, ensuring tests run sequentially to prevent conflicts from shared database state, file locks, or other resource contention.
Test Failure Investigation Protocol
When a test fails, ALWAYS investigate thoroughly before making any changes. Never take shortcuts.
Investigation Steps
Read the full test failure output
Understand what assertion failed
Note the expected vs actual values
Check the stack trace for the error location
Read the failing test code
Understand what the test is validating
Identify what behavior the test expects
Read the application code being tested
Trace through the code path
Understand the intended behavior
Determine root cause - Is this an application bug or test issue?
Decision Framework
It's an APPLICATION BUG if:
The code doesn't match documented/expected behavior
A recent change broke existing functionality
The test correctly validates a contract that the code violates
Edge cases are not handled properly
Error handling is missing or incorrect
It's a TEST ISSUE if:
The test has incorrect assertions (wrong expected values)
The test setup is flawed (missing mocks, wrong fixtures)
The test is testing implementation details that legitimately changed
The test has race conditions or timing issues
The test dependencies are not properly configured
Critical Rules
NEVER weaken tests to pass - If a test checks for important behavior, fix the application
NEVER remove assertions - Unless they are genuinely wrong
NEVER skip tests - Unless there's a documented reason and a plan to fix
ALWAYS fix the root cause - Don't just make the error go away
Fixing Application Bugs
When you identify an application bug:
Understand the intended behavior - Check docstrings, README, related tests
Fix the application code - Make it behave as expected
Verify the fix - Re-run the failing test
Check for regressions - Run related tests to ensure nothing else broke
Document if needed - Add comments explaining non-obvious fixes
Fixing Test Issues
When you identify a test issue:
Fix the test setup - Correct fixtures, mocks, or configuration
Update assertions - Only if the expected values were genuinely wrong
Improve test clarity - Add comments explaining what's being tested
Re-run to verify - Ensure the test passes with correct behavior
Example Investigation
FAILED test_user_profile_update - AssertionError: expected 'active' but got 'pending'
Bad approach (NEVER DO THIS):
# Just change the assertion to passassert status == 'pending'# Changed from 'active'
Good approach:
Read test_user_profile_update to understand what it's testing
Check if 'active' is the correct expected status after an update
If yes, investigate why the code returns 'pending' - this is an app bug
Fix the application code to return 'active' when appropriate
Re-run the test to confirm the fix
Test Categories
Tests with @skip_in_precommit
These tests are skipped during pre-commit but should run in full test suite:
Integration tests requiring real API calls
Long-running tests
Tests requiring specific infrastructure
Location: Check reflexio/tests/server/test_utils.py for the decorator definition.
