# v0.4.0 Release Verification

> Measured test, coverage, lint, and schema-tax benchmark results

The release gate verifies correctness and schema-tax measurements. It does not make a universal latency, retention, or provider-cost claim.

Target: Python runtime · Baseline: LLMSlim v0.4.0 release gate

## Environment

| Setting | Value |
|---|---|
| cpu | Environment-dependent; benchmark locally |
| ram | Environment-dependent |
| os | Cross-platform Python |
| pythonVersion | Python 3.8+ |
| packageVersion | llmslim v0.4.0 |
| tokenizerVersion | tiktoken when available; otherwise documented heuristic |
| sampleSize | 375 generated tool schemas across 18 catalogs |
| iterationsPerSample | See benchmark scripts; pytest results are collected from test reports |

## Methodology

Run pytest, branch coverage, Ruff, and python benchmark.py against the checked-in repository. The runner uses pytest_runtest_logreport to collect actual results.

## Results

| Method | Token reduction | Latency | Cost per 10k requests | Semantic retention | Instruction retention | Entity preservation |
|---|---|---|---|---|---|---|
| Pytest | Not measured by this gate | 489 passed / 0 failed | N/A | N/A | N/A | 90.93% coverage |
| Schema-tax benchmark | 0.00% lossless serialization reduction | 18 catalogs | N/A | 375 generated schemas | 0 provenance-boundary violations | Ruff passed |

## Findings

- Stable tool APIs preserve contracts through canonicalization, fingerprints, and verification.
- Tool retrieval and selective exposure remain explicit research-only features.
- Untrusted RAG/tool/assistant content cannot obtain protected priority from imperative wording.

## Limitations

- Compression ratio and latency vary with text, hardware, tokenizer availability, and strategy.
- The schema-tax benchmark contains 375 generated schemas in 18 catalogs; it is not a broad model-quality evaluation.
- LLMSlim mitigates compression-induced instruction elevation; it is not a complete prompt-injection defense.

## Reproduce

```bash
pytest tests
pytest --cov=llmslim --cov-branch --cov-report=term-missing
ruff check llmslim benchmarks/benchmark.py tests
python benchmark.py
```

Canonical page: https://www.llmslim.app/benchmarks/release-verification