> ## 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.

# Input-quality gate

> A free, deterministic preflight over your traces or source docs before any generation spend — trace count, field completeness, near-duplicates, PII density.

Garbage in is a quiet failure. A trace dump that's too thin, mostly
duplicates, or missing the fields calibration needs will still produce a
suite that looks confident. You don't find out until the numbers don't
mean anything. The input-quality gate makes that loud before you spend a
cent on generation.

Shipped in [0.14.0](https://github.com/multivon-ai/multivon-eval/blob/main/CHANGELOG.md#0140--2026-06-16).
It reuses machinery the rest of the framework already trusts, so it adds no
new dependencies and makes no LLM call.

## What it checks

`assess_input()` and `multivon-eval assess` run four signals over your
input:

* **Trace count** — enough data to calibrate against. Below the shared
  `discover.CALIBRATION_MIN_TRACES` threshold, calibration falls back to
  uncalibrated defaults, and the gate says so out loud.
* **Per-field completeness** — what fraction of traces carry the fields a
  suite needs. Zero-output traces are a common silent one; they make
  calibration early-return uncalibrated thresholds, and the gate now
  surfaces that instead of letting it pass quietly.
* **Near-duplicate ratio** — token-Jaccard overlap, reservoir-capped so a
  large dump can't hang the check. A pile of near-identical traces inflates
  apparent coverage without adding any.
* **PII / secret density** — how much sensitive content is present, using
  the same detectors the redaction path uses.

There is deliberately no 0-100 score. A single scalar is exactly the vanity
metric the gate exists to prevent — it would invite tuning the number
instead of fixing the input.

## WARN by default

The gate warns; it does not block.

* **PROCEED** is silent as a preflight: when the input is fine, a `bootstrap`/`generate` run prints nothing extra. (The standalone `multivon-eval assess` command still prints a one-line confirmation, since you asked it a direct question.)
* **WARN** prints a determinacy headline whose denominator counts every
  defined signal (`2 of 4 signals flagged`), one line per flag, and a
  blind-spots footer naming what it did not check.

<Note>
  There is no hard REFUSE, by design: a WARN can't break a CI, and the gate
  informs the decision rather than owning it. The standalone `assess`
  command exits 1 on a WARN so a script can
  detect it, but the inline preflight never changes the host command's exit
  code.
</Note>

## As a standalone check

```bash theme={null}
multivon-eval assess traces.jsonl                  # default: --for bootstrap
multivon-eval assess docs/faq.md --for generate    # a source document
multivon-eval assess cases.jsonl --for cases       # an eval-cases JSONL
```

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

result = assess_input("traces.jsonl", kind="bootstrap")
```

## As a preflight

The gate runs automatically inside `bootstrap` and `generate`, on the
traces they've already loaded, before the first paid call. You don't have
to wire anything up.

```bash theme={null}
multivon-eval generate --from docs/faq.md --n 20            # gate runs first
multivon-eval generate --from docs/faq.md --n 20 --skip-input-gate
```

`--skip-input-gate` turns it off, but it still prints one line on stderr
when it does. Suppressing the gate is never truly silent.