cd /news/large-language-models/5-undocumented-rules-for-gemini-stru… · home topics large-language-models article
[ARTICLE · art-114136] src=dev.to ↗ pub= topic=large-language-models verified=true sentiment=· neutral

5 Undocumented Rules for Gemini Structured Output, Measured in Production

A developer reports undocumented behaviors in Gemini's structured output schema, discovered through production measurements on a document extraction pipeline. The required array controls emission order, which affects correctness, and reordering it fixed a role classification error in 9 of 9 cases, up from 5 of 9. The findings include that enum descriptions are not enforced and that a PROVIDER_EXHAUSTED error after a prompt change indicates a broken schema.

read10 min views1 publishedAug 28, 2026

We run a document extraction pipeline on Gemini with a native responseSchema

attached, not a "please reply with JSON" instruction in the prompt text. Over two months, three separate production problems traced back to behaviours of that schema that are not in Google's documentation.

These are the rules we ship with now, and the measurement behind each one. The domain is anonymized (no client, no industry, role codes renamed). Every number, date, model name and error string is real.

required

array identity, then evidence, then derived. It controls emission order, and emission order controls correctness.enum

arrays are enforced. Values listed in a description

are not constrained at all.PROVIDER_EXHAUSTED

right after a prompt change means your schema is broken, not that Google is busy.required

identity, evidence, derived Gemini emits every required

property first, in exactly the order the required

array lists them, then the optional ones. The declaration order inside properties

is ignored for the required set.

This is empirical. It is not in Google's docs. We measured it on gemini-3-flash-preview

twice, with opposite orders, reading the raw response text:

| schema | position of role_code in required | position in emitted JSON | |---|---|---| | v18 | 3rd | 3rd | | v19 | 14th (last) | 14th |

In v18 that field was 12th in properties

and 3rd in required

. It came out 3rd. properties

is not the lever.

propertyOrdering

is the documented knob, but if you do not set it (we do not, anywhere), the required

order is what governs.

A model writing JSON does one forward pass. Whatever it has already emitted is in context. Whatever it has not is not. And an emitted token cannot be revised when a later field contradicts it.

So a field emitted early is decided with almost no self-generated evidence, and a field emitted late is decided with everything above it visible.

v18 put role_code

third in required

, after only first_name

and last_name

. Its instruction was a priority ladder:

work_history

entry (Nine CVs, all advertising the same role. Four came back with L3-OPS

, a role from a different department. All four were internally self-contradictory:

{
  "role_code": "L3-OPS",
  "department": "Technical",
  "work_history": [{ "title": "L3-TECH", "...": "..." }]
}

Both codes are valid members of the 143-value enum, so nothing rejected the output. department

, which agreed with the correct reading in all four cases, was emitted 11th, long after the wrong token was committed. The consistency check that would have caught the error was generated downstream of the error.

Ruled out first: environment drift (schemas byte-identical), downstream mapping (the wrong code was already in the raw provider response), a missing enum value (the correct code was present, and used correctly elsewhere in the same responses), and ambiguous source documents (zero matches for any operations wording, 11 to 20 matches for technical wording per document).

Reorder required

. Nothing else. No type change, no enum change, no shape change.

v18:  first_name, last_name, role_code, contacts, nationalities, date_of_birth,
      work_history, certifications, documents, education, languages, address,
      home_airport, department

v19:  first_name, last_name, date_of_birth, nationalities, contacts,
      work_history, certifications, education, documents, languages, address,
      home_airport, department, role_code

Result: 9 of 9 correct, up from 5 of 9. Emitted position of role_code

moved 3 to 14, exactly as predicted.

class meaning position
identity copied off the document, no reasoning (first_name , date_of_birth )
first
evidence the substantive extracted content (work_history , certifications )
middle
derived a judgement about the evidence (role_code , department , any score, total or summary)
last

Three things that come with the reorder:

Descriptions must not forward-reference. Once department

moved ahead of role_code

, its old text ("classify from the stated role_code

") became the same bug in miniature. After any reorder, re-read every description for references to fields that now come later.

Tell the model the evidence is already there. Reordering alone is silent. v19's priority 2 became: "You have ALREADY emitted the work_history array above. Read the title of its first entry and use it."

Check for over-anchoring. The goal is grounding, not echoing. Two candidates whose most recent entry was one level below the applied-for role still correctly emitted the applied-for level, because priority 1 legitimately outranks priority 2. If every derived value suddenly equals evidence[0]

, you have over-corrected.

And the trap: required

is a set to a JSON Schema validator. Reordering it is semantically inert, so a formatter that sorts the array, or a tool that round trips the JSON, silently reverts the behaviour with a diff that looks like whitespace and passes every test. Say so in the file.

Do not respond to a wrong derived field by adding more prose first. v18 already carried four bullets of correct guidance for that field and was still wrong about 44% of the time. The instruction was not being disobeyed. It was being evaluated at a token position where its input did not exist.

Gemini rejects a schema above an undocumented ceiling on the total enum-value count across the whole schema. Google publishes no number, only that "very large or deeply nested schemas may be rejected".

total enum values result when
467 accepted v9, production
610 accepted, months of clean runs v10-revised through v14
740
rejected
v15, 2026-08-17
754 rejected, reverted v10-initial, 2026-07-13

The boundary is in (610, 740]. We never bisected it.

Three checkpoints were tried with the 740 schema, one preview and two GA releases:

model outcome
gemini-3-flash-preview
400 invalid argument
gemini-3.5-flash
400 invalid argument
gemini-3.6-flash
400 invalid argument

Identical rejection across releases spanning months. This is a property of the constrained-decoding compiler, not of a checkpoint, so waiting for a newer model is not a mitigation.

You cannot deduplicate your way under the limit. Gemini's subset has no $ref

and no $defs

(see Rule 4), so every repeated list is paid for in full. A 145-value list used in three places costs 435, not 145.

Practical consequences:

description

instead. Descriptions cost nothing against the budget. Just know they are not enforced either (Rule 3).A rough counter is worth having in CI:

// Sums every enum array in a schema, nulls included.
function countEnums(node) {
  if (Array.isArray(node)) return node.reduce((n, v) => n + countEnums(v), 0);
  if (node && typeof node === 'object') {
    return Object.entries(node).reduce(
      (n, [k, v]) => n + (k === 'enum' && Array.isArray(v) ? v.length : countEnums(v)),
      0
    );
  }
  return 0;
}

responseSchema

guarantees JSON shape and types. It does not guarantee values, with one exception.

how you express it enforced?
"enum": ["L3-TECH", "L3-OPS"]
yes, by constrained decoding
allowed values listed in description
no, purely advisory
maxLength
no
array uniqueness no

In July, a schema change meant constrained decoding stopped being applied for five days. Nothing failed, nothing turned red, and 75 values that do not exist in the vocabulary reached production in a field the rest of the system indexes on.

So:

If the same prompt may run on more than one provider, store the schema in the more restrictive format. Gemini's subset is the floor.

feature OpenAI Gemini
$ref / $defs
supported
not supported, inline everything
$schema , $id
supported
not supported, strip
oneOf
supported
not supported, single type + nullable
["string", "null"]
supported
not supported, use nullable
exclusiveMinimum
supported
not supported, use minimum
pattern
supported stripped
format: "uri"
supported stripped
nullable
not used
required for nullable fields
max nesting no limit 5 levels
property ordering not enforced
required order drives emission

Rejected:

{
  "$schema": "https://json-schema.org/draft/2020-12/schema",
  "type": "object",
  "properties": {
    "role_code":  { "$ref": "#/$defs/RoleCode" },
    "start_year": { "type": "integer", "exclusiveMinimum": 1900 },
    "email":      { "type": ["string", "null"] },
    "website":    { "type": "string", "format": "uri" },
    "ref":        { "type": "string", "pattern": "^[A-Z]{2}-\\d{4}$" }
  }
}

Accepted:

{
  "type": "object",
  "properties": {
    "start_year": { "type": "integer", "minimum": 1901 },
    "email":      { "type": "string", "nullable": true },
    "website":    { "type": "string" },
    "ref":        { "type": "string", "description": "Two uppercase letters, hyphen, four digits" },
    "role_code":  { "type": "string", "enum": ["L3-TECH", "L3-OPS"] }
  },
  "required": ["start_year", "email", "website", "ref", "role_code"]
}

Note role_code

is last in required

, per Rule 1.

A malformed schema does not degrade politely. On 2026-08-27 a single "type": ["string", "null"]

union in one prompt failed every execution of it until the union was removed.

This is the one that costs the most hours, because the label sends you to the wrong system.

What the provider actually returns:

400 . Request contains an invalid argument.

No field pointer, no property name, no mention of size or enums. Deterministic on every retry, every key and every service tier.

What the operator sees by the time it surfaces:

processing_error   PROVIDER_EXHAUSTED: Provider capacity unavailable
error_reason_code  PROVIDER_EXHAUSTED
model              (empty)

The chain is 400, then an API error, then the key circuit opens, then the retry ladder exhausts, then the last event gets reported instead of the first. It reads as a transient capacity shed. It is a permanent schema defect.

Triage table:

symptom actual meaning
PROVIDER_EXHAUSTED with an empty model field, starting right after a prompt change
schema defect, not capacity
the same failure on both STANDARD and FLEX tiers not a tier or quota problem
identical failure across model checkpoints constrained-decoding compiler, not the model
valid JSON with out-of-vocabulary values constrained decoding was not applied at all

The real error survives only in a WARN line, on whichever replica ran the worker, which is usually not the replica that logged the submission. Grep all of them:

for P in $(kubectl -n <ns> get pods -o name | grep -E "^pod/ai-" | grep -v db); do
  kubectl -n <ns> logs $P --since=2h \
    | grep -E "invalid argument|Circuit OPEN|keys exhausted"
done

Time-to-failure tells you nothing. We saw 30s and 165s for the same rejection and briefly read the slow one as "this model accepted the schema". It had not. The difference was retry parking.

If you store parsed responses in a jsonb

column, that column loses key order. Read the raw response text instead:

const raw = require('fs').readFileSync('raw.json', 'utf8').trim();
Object.keys(JSON.parse(raw)).forEach((k, i) => console.log(`${i + 1}. ${k}`));

Compare that against your required

array. If they diverge, the ordering law has changed for your model family and needs re-measuring.

required

ordered identity, then evidence, then derived.description

references a field emitted later.required

order is deliberate and must not be sorted.$ref

, no oneOf

, no type arrays, nullable

used, 5 levels max).PROVIDER_EXHAUSTED

after a prompt change means schema first, capacity second.Two of these five rules describe limits Google does not document, and both were established by breaking production. If you are running structured output at any scale, measure them for your own model family and write your own numbers down. The alternative is rediscovering them next quarter at the same price.

── more in #large-language-models 4 stories · sorted by recency
── more on @gemini 3 stories trending now
sponsored brought to you by zahid.host 4,200+ EU-deployed projects
reading about agents? ship yours in a single git push.

Run your AI side-project on zahid.host

EU-based hosting, git-push deploys, automatic HTTPS, no cold starts. Free tier with a custom domain — perfect for shipping the agent you just read about.

$git push zahid main
Live at https://your-agent.zahid.host
Get free account → Pricing
from €0/mo · no card required
LIVE [news/5-undocumented-rules…] indexed:0 read:10min 2026-08-28 ·