Family Recipes Catalog

Family recipes represent concrete model deployments. Rather than authoring custom rule arrays from scratch, configure your guard middleware with any of the 38 pre-defined family recipe keys. Thirty-eight is not a claim that we've catalogued every vendor on Earth — it's how many mutually incompatible tool-calling conventions our own research pass turned up before we stopped counting and started shipping. It's a floor, not a census, and it grows every time we go looking again or a new lab invents a new way to disagree.

When passed as strings in OrderingGuardOptions.profiles, recipe keys are resolved and composed automatically by the middleware.

What a recipe will and will not do to your dispatch

Two things are worth knowing before selecting one, because neither is visible from the table below.

Every rule here is advisory unless it says otherwise. A live audit dispatched each rule in this catalog against its own native vendor API and found that 16 of 17 describe shapes the vendor in fact accepts — often because a gateway between you and the model was quietly normalizing them, and sometimes because the constraint was never real to begin with. So a recipe records what it finds and lets the dispatch proceed. The single exception is thought_signature_required (gemini-3), which stays blocking because Gemini genuinely returns a 400 naming the missing field and its position.

If you want a recipe to gate rather than annotate, set severity: 'blocking' on the rules you care about — and read API surface scope first, because a rule applied on a surface it was not derived from guards against a constraint that layer already handles.

In mutate mode, every rule type in this catalog is repairable except preservation. Ordering and adjacency violations reorder, alternation gaps take a filler, and required metadata fills from a documented fallback where the repair is authorized. preservation is the deliberate exception: when history has been dropped or altered upstream, there is nothing to repair toward — the guard will not invent lost context. See Modes for the full table.

Complete Family Recipes Matrix

Recipe Key	Composed Atomic Behaviors	Description / Model Invariants
anthropic-manual-thinking	thinking_before_tool_use, payload_field_preservation:signature	Claude 4.5 and earlier manual thinking mode: thoughts must precede tool calls in the active turn; thought signatures must remain stable.
anthropic-adaptive-thinking	payload_field_preservation:signature	Claude 5.x and adaptive thinking mode: relaxed thinking placement; thought signatures must remain stable.
gemini-3	thought_signature_required, function_response_adjacency	Google Gemini 3 and 3 Flash: mandatory thoughtSignature on first functionCall; messages may not immediately follow tool calls.
gemini-2-5	thought_signature_advisory, function_response_adjacency	Google Gemini 2.5: advisory thoughtSignature on first functionCall; messages may not immediately follow tool calls.
nova	strict_alternation, openai_shape_baseline	Amazon Nova: strict user/assistant role alternation; messages may not immediately follow tool calls.
bedrock-converse	converse_text_before_tool_use	AWS Bedrock Converse hosting layer: within one assistant turn, all text messages must precede any tool call.
deepseek-v3-base	strict_alternation, openai_shape_baseline	DeepSeek V3 (non-thinking): strict role alternation; messages may not immediately follow tool calls.
deepseek-thinking	strict_alternation, full_history_preservation:thought	DeepSeek R1 / V3.1 / V3.2 reasoner: strict alternation; historical reasoning traces must be preserved across turns.
deepseek-v4	strict_alternation, full_history_preservation:thought	DeepSeek V4 (Pro/Flash): strict alternation; historical reasoning traces must be preserved across turns.
qwen-2-5	openai_shape_baseline	Alibaba Qwen 2.5 and earlier: standard tool-result adjacency baseline.
qwen-3	openai_shape_baseline, reasoning_pruned_after_latest_turn	Alibaba Qwen 3.x (enable_thinking): recent reasoning preserved; historical reasoning older than latest user turn may be pruned.
glm-4-5	openai_shape_baseline	Z.AI GLM-4.5: standard tool-result adjacency baseline.
glm-4-7	openai_shape_baseline, payload_field_preservation:clear_thinking	Z.AI GLM-4.7 and GLM-5: preserved thinking flag (clear_thinking) kept stable across iterations.
kimi-k2	openai_shape_baseline, full_history_preservation:toolCall	Moonshot Kimi K2 family: historical tool calls must never be dropped across multi-turn sessions.
kimi-k3	openai_shape_baseline, full_history_preservation:toolCall, full_history_preservation:thought	Moonshot Kimi K3: preserves both historical tool calls and reasoning traces across turns.
minimax-m2	openai_shape_baseline, full_history_preservation:toolCall, full_history_preservation:thought	MiniMax M2 / M2.1 / M2.7: tool-call and reasoning trace preservation across multi-turn dispatch.
minimax-m3	openai_shape_baseline, full_history_preservation:toolCall, full_history_preservation:thought	MiniMax M3: tool-call and reasoning trace preservation across multi-turn dispatch.
mistral	openai_shape_baseline	Mistral / Devstral: standard tool-result adjacency baseline.
llama-3	openai_shape_baseline, single_tool_call_per_turn	Meta Llama 3.x: maximum 1 tool call per assistant turn (no parallel tool execution).
llama-4	openai_shape_baseline	Meta Llama 4: standard tool-result adjacency baseline (parallel tool execution allowed).
nemotron	openai_shape_baseline	Nvidia Nemotron: standard tool-result adjacency baseline.
gemma-3	strict_alternation	Google Gemma 3: strict two-role (user/model) alternation.
gemma-4	strict_alternation, stale_thinking_advisory	Google Gemma 4: strict alternation + non-blocking advisory against resending stale prior-turn thinking.
gpt-oss	harmony_commentary_channel	OpenAI GPT-OSS: every function tool call must carry a Harmony commentary-channel tag.
codex-responses	payload_field_preservation:encrypted_content	OpenAI Codex / Responses API: reasoning encrypted content must remain stable across turns.
cohere-command-r	openai_shape_baseline	Cohere Command R / R+: standard tool-result adjacency baseline.
phi	openai_shape_baseline	Microsoft Phi: ChatML format, standard tool-result adjacency baseline.
mai	openai_shape_baseline	Microsoft Foundry MAI-Thinking / MAI-Code: standard tool-result adjacency baseline.
jamba	openai_shape_baseline	AI21 Jamba: standard tool-result adjacency baseline.
falcon	openai_shape_baseline	TII Falcon: standard tool-result adjacency baseline.
palmyra	openai_shape_baseline	Writer Palmyra: standard tool-result adjacency baseline.
ernie	openai_shape_baseline	Baidu ERNIE: standard tool-result adjacency baseline.
gpt-4-legacy	openai_shape_baseline	OpenAI legacy GPT-4 (end-of-life): standard tool-result adjacency baseline.
bytedance-seed	openai_shape_baseline	ByteDance Seed / Doubao (UNCONFIRMED baseline guess): verify before relying on in enforce mode.
muse-spark	openai_shape_baseline	Meta Muse Spark (UNCONFIRMED baseline guess): verify before relying on in enforce mode.
muse-glimmer	openai_shape_baseline	Meta Muse Glimmer (UNCONFIRMED baseline guess): verify before relying on in enforce mode.
granite-3-x	role_remap_split_tool_roles	IBM Granite 3.x: producer must set a role-remap marker confirming its split tool-call/tool-response wire roles.
granite-4-x	role_remap_inline_tool_call	IBM Granite 4.x: producer must set a role-remap marker confirming its inline tool-call, remapped-response wire roles.

'grok' is a recognized profile key that resolves directly to 'permissive'. It is the single vendor in this entire catalog that just has no opinion on message ordering, which, after reading the rest of this table, should feel almost suspicious.

Composing Recipes in Middleware

You can specify family recipes directly in OrderingGuardOptions.profiles. Composing multiple recipes lets you capture layered constraints — for example, pairing a model family recipe with a hosting-layer recipe when deploying through Bedrock Converse. This two-layer conflict (where the model requires one structure and the hosting wrapper bolts on a second, conflicting constraint) is precisely why testing models in isolation is never enough: you must validate the actual deployment shape.

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

// Single family recipe
const middleware = orderingGuardDispatchMiddleware({
  profiles: ['gemini-3'],
  action: 'enforce',
})

// Combining a family recipe with a hosting-layer recipe
const bedrockClaudeMiddleware = orderingGuardDispatchMiddleware({
  profiles: ['anthropic-manual-thinking', 'bedrock-converse'],
  action: 'mutate',
})

See Also

• Validation Hub — Overview and model selector table.
• Atomic Behaviors — Breakdown of each composed atomic profile.
• Operating Modes — Configuring enforce vs mutate execution.
• Advisories & Placeholders — Guidance on unconfirmed recipes (bytedance-seed, muse-spark, muse-glimmer).