---
url: 'https://adk.nht.io/batteries/validation/advisories.md'
description: >-
  Understanding non-blocking advisory rules, selective advisory opt-outs, and
  guidance on unconfirmed baseline recipes in the validation battery.
---

# Advisories & Unconfirmed Recipes

## LLM summary — Advisories & Unconfirmed Recipes

* **Advisory rules are non-blocking:** `StaleContentAdvisoryRule` and `RequiredMetadataRule` with `severity: 'advisory'` (e.g. Gemini 2.5 `thought_signature_advisory`, Gemma 4 `stale_thinking_advisory`) never halt execution, never reject via `nack`/`abort`, and never count as unrepaired violations.
* Findings are retained in `OrderingGuardResult.advisories` on `ctx.stash` for observability.
* **Selective opt-outs:** Use `disableAdvisoryRuleIds: ['<rule-id>']` in [`OrderingGuardOptions`](https://adk.nht.io/api/@nhtio/adk/batteries/validation/types/interfaces/OrderingGuardOptions) to disable evaluation of specific advisories.
* **Unconfirmed baseline recipes:** `bytedance-seed`, `muse-spark`, and `muse-glimmer` are placeholder baselines seeded from `openai_shape_baseline` due to vendor documentation gaps. Do not rely on them in `enforce` mode without testing against upstream targets.

The validation battery distinguishes between hard protocol invariants (which break turn execution if violated) and vendor best-practice advisories (which represent soft recommendations or hygiene practices).

Treating a vendor's soft "please don't do this" as a fatal rejection is how a validation library becomes more annoying than the problems it was built to solve. The advisory tier exists specifically so this battery never pretends a suggestion is an invariant just because treating everything as an error is easier to code.

## Non-Blocking Advisories

Advisory rules represent vendor recommendations or soft deprecations, **not** fatal protocol violations.

Examples include:

* `stale_thinking_advisory` (used in `gemma-4`): Recommends pruning thought content predating the latest user turn.
* `thought_signature_advisory` (used in `gemini-2-5`): Notes the absence of a thought signature without blocking execution.

### How the Guard Handles Advisories

When an advisory rule triggers:

1. It is recorded in `OrderingGuardResult.advisories` under `__orderingGuardLastResult` on `ctx.stash`.
2. It is **never** added to `unrepaired` violations.
3. It will **never** trigger `ctx.nack()`, `ctx.abort()`, or throw an exception, in either `enforce` or `mutate` mode.

### Selectively Disabling Advisories

If you intentionally deviate from a vendor's default hygiene recommendation (for example, setting Gemma 4's `preserve_thinking` flag to maintain long-term reasoning history), you can silence the rule by ID using `disableAdvisoryRuleIds`:

```ts
import { orderingGuardDispatchMiddleware } from '@nhtio/adk/batteries/validation'

const middleware = orderingGuardDispatchMiddleware({
  profiles: ['gemma-4'],
  // Silences the Gemma 4 stale thinking advisory; skips evaluation entirely
  disableAdvisoryRuleIds: ['stale-thinking-gemma4'],
})
```

`disableAdvisoryRuleIds` only suppresses rules with `severity: 'advisory'` or rule type `staleContentAdvisory`; it cannot suppress blocking validation rules.

## Unconfirmed & Placeholder Recipes

Not all model vendors publish complete specifications for their chat templates, tool calling roles, and ordering constraints.

For the models below, this battery is guessing based on the closest documented analog. We do this because the alternative — shipping nothing — leaves those model keys completely unresolvable, while shipping a guess dressed up as certainty would be far worse.

The following family recipes in `FAMILY_RECIPES` are **unconfirmed baseline guesses** seeded from `openai_shape_baseline`:

* **`bytedance-seed`** (Doubao / Seed models on Volcano Engine Ark)
* **`muse-spark`** (Meta Superintelligence Labs Muse Spark)
* **`muse-glimmer`** (Meta Muse Glimmer)

These profiles are registered in the family catalog so that model keys resolve consistently. But do not confuse registration with verification: **do not rely on these recipes in `enforce` mode in production without testing against upstream endpoints first.** If upstream rejects a payload shape we guessed at, that's not a bug in your agent — it's the inevitable cost of vendor documentation voids.

## See Also

* **[Validation Hub](./index)** — Overview and model selector matrix.
* **[Rule Types Reference](./rule-types)** — Full schema of `StaleContentAdvisoryRule` and `RequiredMetadataRule`.
* **[Family Recipes Catalog](./recipes)** — Matrix of all 38 family recipes.