> ## Documentation Index
> Fetch the complete documentation index at: https://docs.multivon.ai/llms.txt
> Use this file to discover all available pages before exploring further.

# Migrating to 0.19

> Adopt complete claim coverage, provider evidence, retry contracts, and the new experimental adapters.

Version 0.19.0 publishes the development work accumulated after 0.18.0. Existing
reports remain readable. New comparisons and acceptance decisions are stricter
when evidence, grader dependencies, execution state, or claim coverage is missing.

```bash theme={null}
pip install --upgrade "multivon-eval==0.19.0"
```

## Revalidate Faithfulness baselines

`Faithfulness` no longer treats an empty extracted claim list as a perfect score,
checks only the first ten claims, or drops unknown verdicts from its denominator.
It now verifies every unique extracted claim up to `max_claims=10`. Empty or
over-limit extraction is skipped; malformed claims raise an evaluator error; any
unknown verdict raises `JudgeUnavailable`.

```python theme={null}
from multivon_eval import Faithfulness

# Increase deliberately when long answers need complete extracted-set coverage.
faithfulness = Faithfulness(threshold=0.9, max_claims=30)
```

This may make more judge calls. A perfect score covers the extracted claims; it
does not prove the extractor found every claim. Require `faithfulness` in an
`AcceptancePolicy` when missing measurements must block a release. Regenerate or
regrade baselines before comparison because the grading contract changed. Shipped
historical calibration packs have not been revalidated for this stricter protocol.

## Bind comparisons and retries to their dependencies

Use `declare_dependencies` for custom graders and `declare_target` for target
callbacks whose behavior depends on code, configuration or named files. Use
`bind_inspect_task` before importing or retrying native Inspect logs. Unknown or
changed dependencies remain diagnostic and block controlled comparisons instead
of being inferred from callable names.

## Capture and account for provider calls

Wrap supported native SDK execution with `capture_provider_events`, optionally
backed by `ProviderJournal`. `account_provider_events` reconciles observed physical
attempts and native usage. A dollar total requires explicit complete-run coverage,
no observed gaps and a validated estimator; `recorded_cost_usd` remains a scoped
subtotal. The optional `pricing` extra provides the LiteLLM bridge.

```bash theme={null}
pip install "multivon-eval[pricing]==0.19.0"
```

Captured prompts and responses can contain sensitive application data. Apply your
own retention and access controls. Missing responses remain execution and billing
unknown rather than being retried automatically.

## Experimental adapters

The release includes bounded adapters and evidence profiles for Label Studio,
OpenTelemetry, Gymnasium, media inputs, robustness validation and numeric vector
dynamics. They reuse upstream tools and preserve unknown states. Their guides
describe tested versions and limitations; none constitutes regulatory validation,
security isolation, complete trace capture, or a general world-model claim.

The packaged report JSON Schema validates v1, v2 and schema-less legacy envelopes.
Unknown versions, malformed field types and nonfinite values now fail loading.
Extension authors should use the public protocols and compatibility fixtures in
[extensions and compatibility](./extensions-and-compatibility).