Day 6: Sandboxed Execution & Stderr Triage

---
name: spring-boot-unit-tester
schema-version: "1.0.0"
description: >
  Generates and refactors deterministic, isolated Kotlin unit tests for Spring Boot 3.x 
  using MockK and AssertJ. MUST NOT load Spring ApplicationContext.
tools:
  - name: run-unit-tests
    description: Runs static linting and sandboxed Maven test execution with automatic failure triage.
    file: scripts/run-unit-tests.sh
metadata:
  domain: "backend-quality"
  target-framework: "Spring Boot 3.x / Kotlin 1.9+"
---

# Spring Boot Unit Test Architect Specification

## 1. Tool Execution & Closed-Loop Remediation Contract
Whenever generating or refactoring a test file, the Host Agent MUST trigger verification:
`bash .github/skills/spring-boot-unit-tester/scripts/run-unit-tests.sh <TARGET_TEST_FILE>`

### 1.1 Exit Code Evaluation Matrix

- **Exit Code 0 (SUCCESS)**: Verification passed. Return finalized test code to user immediately.
- **Exit Code 1 (ENVIRONMENT_ERROR)**: Missing dependencies or invalid target. Abort and alert developer.
- **Exit Code 2 (STATIC_INVARIANT_FAIL)**: Negative boundary violated. Read stderr, purge Mockito or Spring runner.
- **Exit Code 3 (COMPILATION_FAILURE)**: Compiler error. Parse location and type error from stderr, fix syntax immediately.
- **Exit Code 4 (ASSERTION_FAILURE)**: Test assertion failed. Adjust MockK stubs or assertion criteria to align with domain logic.
- **Exit Code 124 (EXECUTION_TIMEOUT)**: Execution exceeded 45s. Purge blocking operations or heavy context loaders.

### 1.2 Maximum Retries Limit
The Host Agent MUST NOT invoke this tool more than 3 consecutive times per turn. If unresolved after 3 attempts, halt and output the exact diagnostic trace to the user.
          

#!/usr/bin/env python3
"""
scripts/triage-test-failure.py
Extracts compiler and assertion failures from noisy build logs.
Emits a compact diagnostic markdown card strictly to stderr (< 350 tokens).
"""
import sys
import re

# // [TODAY'S LESSON PLUGS IN HERE: REGEX STREAM PARSING]
def parse_build_diagnostics(raw_log: str) -> dict:
    diagnostics = {
        "category": "BUILD_FAILURE",
        "file": "Unknown",
        "line": "0",
        "message": "Unclassified build or test failure.",
        "root_cause_snippet": []
    }

    lines = raw_log.splitlines()

    # Pattern A: Kotlinc Compilation Failure (e.g. [ERROR] /path/File.kt:22:38: error: type mismatch)
    kt_pattern = re.compile(r"\[ERROR\]\s+(/.+?\.kt):(\d+):(\d+):\s+error:\s+(.+)")
    # Pattern B: MockK Unmocked / Contract Failure
    mockk_pattern = re.compile(r"io\.mockk\.MockKException:\s+(.+)")
    # Pattern C: AssertJ / JUnit Assertion Error
    assert_pattern = re.compile(r"org\.opentest4j\.AssertionFailedError:\s+(.+)")

    for line in lines:
        match_kt = kt_pattern.search(line)
        if match_kt:
            diagnostics["category"] = "COMPILATION_FAILURE"
            diagnostics["file"] = match_kt.group(1).split("/")[-1]
            diagnostics["line"] = match_kt.group(2)
            diagnostics["message"] = match_kt.group(4)
            diagnostics["root_cause_snippet"].append(line.strip())
            return diagnostics

        match_mockk = mockk_pattern.search(line)
        if match_mockk:
            diagnostics["category"] = "MOCKK_CONTRACT_VIOLATION"
            diagnostics["message"] = match_mockk.group(1)
            diagnostics["root_cause_snippet"].append(line.strip())
            return diagnostics

        match_assert = assert_pattern.search(line)
        if match_assert:
            diagnostics["category"] = "ASSERTION_FAILURE"
            diagnostics["message"] = match_assert.group(1)
            diagnostics["root_cause_snippet"].append(line.strip())
            return diagnostics

    # Fallback: Capture last 3 compiler error lines
    error_tail = [l.strip() for l in lines if "[ERROR]" in l][-3:]
    if error_tail:
        diagnostics["root_cause_snippet"] = error_tail

    return diagnostics

def format_agent_card(diag: dict) -> str:
    """Formats output into an ultra-dense markdown block tailored for LLM ingestion."""
    return f"""### 🚨 DETERMINISTIC TRIAGE REPORT
- **Category**: `{diag['category']}`
- **Location**: `{diag['file']}:{diag['line']}`
- **Error**: {diag['message']}
- **Action Required**: Resolve the violation indicated above and re-execute runner.
```text
{chr(10).join(diag['root_cause_snippet'][:3])}
```"""

def main():
    raw_input = ""
    if len(sys.argv) > 1:
        with open(sys.argv[1], "r", encoding="utf-8", errors="ignore") as f:
            raw_input = f.read()
    else:
        raw_input = sys.stdin.read()

    diag = parse_build_diagnostics(raw_input)
    # CONTRACT: Always write triage report strictly to stderr
    sys.stderr.write(format_agent_card(diag) + "\n")

if __name__ == "__main__":
    main()