test-deep

Files (4)

• SKILL.md
• fixer-catalog.md · references/
• test-selection.md · references/
• triage-pipeline.md · references/

SKILL.md (first lines)

# Test Deep — Context-Aware Test Orchestration

## Supplementary Agent

When test failures occur, dispatch background triage:

Agent({
  description: "Analyze test failure root cause and suggest fixes",
  subagent_type: "verify-app",
  prompt: `Analyze the following test failure:
<failure output>
Identify root cause and suggest minimal fix.`
})

## Trigger

- Keywords: context-aware testing, smart test, test orchestration, test triage, test failure analysis, test deep, run relevant tests

## When NOT to Use

| Scenario | Alternative |
|----------|------------|
| Writing new tests | `/post-dev-test` |
| Reviewing test coverage | `/codex-test-review` |
| Generating unit tests | `/codex-test-gen` |
| Full manual test run | `/verify` |
| Code review | `/codex-review-fast` |

## Prohibited Actions

```
❌ git add | git commit | git push — per @rules/git-workflow.md
```

This skill runs tests and may apply safe fixers, but does **not** commit. To commit, offer the menu per `rules/git-workflow.md` § Proactive Offer — a commit option on any real branch, a push option only where `review-state.js offer` allows one — and invoke `/smart-commit --execute` on selection; never print the command for the user to copy.

## Workflow

```mermaid
flowchart TD
    U[User: /test-deep] --> S[Phase 0: Test Selection]
    S --> |git diff mapping| T[Test Targets]
    S --> |no mapping| F1[Framework --changedSince]
    S --> |low confidence| F2[Full Suite]
    T --> L[Phase 1: Progressive Ladder]
    F1 --> L
    F2 --> L
    L --> |unit| R1[Run Unit Tests]
    R1 --> |pass| R2[Run Integration Tests]
    R1 --> |fail| TR[Phase 2: Triage Pipeline]
    R2 --> |pass| R3[Run E2E Tests]
    R2 --> |fail| TR
    R3 --> |pass| DONE[All Pass]
    R3 --> |fail| TR
    TR --> P[Parser: Structured Tags]
    P --> LLM[LLM: Root Cause + Action]
    LLM --> FC[Phase 3: Fixer Catalog Lookup]
    FC --> SG{Safety Gate}
    SG --> |safe| AUTO[Auto-run Fix]
    SG --> |side-effect| ASK[AskUserQuestion]
    SG --> |destructive| BLOCK[Manual Only]
    AUTO --> L
    ASK --> |approved| L
```

## Phase 0: Test Selection

Map code changes to test targets. See `references/test-selection.md` for full strategy.

**Strategy priority**:

| Priority | Method | When |
|----------|--------|------|
| 1 | Git diff filename mapping | Default — map changed files to test files via Glob |
| 2 | Framework native | Jest `--changedSince`, Vitest `--changed` |
| 3 | Full suite fallback | Config change, no mapping, `--all` flag |

**Steps**:
1. Collect changed files: union of unstaged + staged + untracked (`--branch` uses merge-base)
2. Apply filename mapping rules to generate candidate test paths
3. Glob-confirm each candidate exists
4. Classify confirmed tests by layer (unit / integration / e2e)

**Full suite escalation triggers**: config file changed, CI/CD file changed, package dependency changed, no test files mapped, `--all` flag.

## Phase 1: Progressive Ladder

Execute tests layer-by-layer with fail-fast.

| Layer | Directory Pattern | Timeout | Fail Behavior |
|-------|------------------|---------|---------------|
| Unit | `test/unit/**`, `test/scripts/lib/**`, unclassified | 60s | Fail-fast → triage |
| Integration | `test/integration/**` | 300s | Fail-fast → triage |
| E2E | `test/e2e/**` | 600s | Enter triage |

**Fail-fast rule**: Unit fail → skip integration + e2e. Integration fail → skip e2e.

**Override**: `--no-fail-fast` disables this behavior (run all layers regardless).

**Layer detection**: Classify test files by directory prefix. Files not matching any integration/e2e pattern → treat as unit.

**Execution**: Run tests using project's configured test command (from `package.json` scripts or `CLAUDE.md`). Capture stdout/stderr and exit code.

## Phase 2: Failure Triage Pipeline

When failures occur, analyze and classify. See `references/triage-pipeline.md` for full spec.

### Step 1: Output Parser

Extract structured tags from test output (no classification — just structure):

| Tag | Description |
|-----|-------------|
| `exit_code` | Process exit code |
| `error_signatures[]` | Regex-matched error patterns |
| `failing_tests[]` | Failed test names |
| `failing_files[]` | Failed test file paths |
| `env_hints[]` | Environment clues (testnet, localhost, etc.) |
| `stack_depth` | Stack trace line count |

From sd0xdev/sd0x-harness, MIT.

More from sd0xdev/sd0x-harness