@fayegram-ai/decision-bridge 0.1.0 → 0.1.2

package/docs/reference/CLI.md

@@ -20,8 +20,9 @@ it with `node bin/decision.mjs` from a source checkout. `decision` and
 The CLI defaults to Jev. Flags override `DECISION_*` environment settings, which
 override an explicit config file and then built-in defaults. It constructs an
 explicit provider for the SDK; `createBridge` itself has no implicit selection.
-Use the root README's [model list](../../README.md#supported-models) to select a
-supported native model. Custom generative presets require an explicit model ID.
+Choose a supported native model from the
+[model selector inventory](../../README.md#model-selectors).
+Custom generative presets require an explicit model ID.
 
 ## Commands
 
@@ -32,6 +33,12 @@ for native request/response structures on `init`, `evaluate`, `validate`, or
 or `-`. See [OpenAI Decisions](../guides/OPENAI_DECISIONS.md) and
 [Cloudflare Clef](../guides/CLOUDFLARE_DECISIONS.md) for examples. Both providers report
 model listing as unsupported.
+OpenAI model selection defaults to `default`; use `--model luna` for the Luna
+family or an explicit supported upstream ID. Both stable selectors currently
+resolve to `gpt-6-luna` within Decision Bridge. OpenAI `validate` reports the
+selected value in `model` and the outgoing ID in `resolvedModel`, without credentials.
+Successful common and native calls include `meta.requestedModel` and
+`meta.resolvedModel`; response models retain the service-reported identity.
 Cloudflare CLI execution uses REST. The Workers AI binding is an SDK transport;
 there is no CLI binding selector. Gateway settings route the selected REST request.
 
@@ -44,6 +51,12 @@ there is no CLI binding selector. Gateway settings route the selected REST reque
 | `models` | List the configured provider's models; may be paginated |
 | `batch FILE\|-` | Stream JSONL inputs and ordered JSONL result/error records |
 
+Jev supports both common and `--native` requests for evaluation, validation,
+initialization, and ordered batches. Experimental images/boxes require
+`--jev-images`, and longer context requires `--jev-long-context` (or matching
+JSON configuration). Use `--no-jev-images` and `--no-jev-long-context` to
+override enabled settings. See the [Jev guide](../guides/JEV.md).
+
 No input filename on `evaluate`, `validate`, or `schema` selects the bundled sample,
 not stdin. Use `-` explicitly for stdin. Empty invocation prints help. Configuration
 and credential errors do not cause fallback to another backend.
@@ -71,6 +84,10 @@ explicit service implementation error until you connect it. An existing
 `--provider-module` is referenced without execution or overwrite. All profiles
 include a copied JSON Schema for editor validation. See [custom providers](../guides/CUSTOM_PROVIDERS.md).
 
+OpenAI initialization writes the selected model into configuration, using `default`
+when omitted. Its generated common and native requests omit `model`, allowing
+later configuration changes to control selection.
+
 ## Flags
 
 | Flag | Meaning |
@@ -80,7 +97,9 @@ include a copied JSON Schema for editor validation. See [custom providers](../gu
 | `--provider NAME` | `jev`, `openai-decisions`, `cloudflare-decisions`, `custom-decision`, `custom-generative` |
 | `--preset NAME` | custom-generative preset: `openai-compatible`, `openrouter`, or `anthropic`; exclusive with module |
 | `--native` | Explicit native Decisions input/output; init/evaluate/validate/batch only |
-| `--model ID` | Overrides input JSON model and provider default |
+| `--jev-images`, `--no-jev-images` | Enable/disable experimental Jev images and boxes |
+| `--jev-long-context`, `--no-jev-long-context` | Enable/disable experimental Jev 262k context |
+| `--model SELECTOR` | Model selector or supported upstream ID; overrides input JSON model and configured default |
 | `--base-url URL` | Custom endpoint; requires explicit credential selection |
 | `--api-key-env NAME` | Environment variable name, never the key itself |
 | `--account-id ID` | Cloudflare REST account ID |
@@ -161,7 +180,10 @@ delivery needs separate validation.
 
 ## I/O and resource limits
 
-Single JSON input: **8 MiB**. JSONL: **8 MiB per line, 64 MiB total**. Config:
+Single JSON input normally uses **8 MiB**. JSONL normally uses **8 MiB per line,
+64 MiB total**. Jev permits **32 MiB** for a single JSON input or JSONL record,
+then checks serialized requests against its configured ceiling (32 MiB by default).
+Config:
 **1 MiB**. Environment file: **64 KiB**. Provider request and response default to
 8 MiB each, configurable to at most 64 MiB. Cloudflare reads single JSON inputs
 and individual JSONL records within 64 MiB, then applies model-specific serialized

package/docs/reference/CONFIGURATION.md

@@ -40,16 +40,17 @@ profile. Gateway configuration is optional for either SDK transport and for CLI
 | `schemaVersion` | 1; optional, but generated profiles include it |
 | `provider` | `jev` default, `openai-decisions`, `cloudflare-decisions`, `custom-decision`, `custom-generative` |
 | `preset` | `custom-generative` only: `openai-compatible`, `openrouter`, `anthropic`; mutually exclusive with module |
-| `model` | Nonempty model ID; built-in native providers have defaults; required for generative evaluation unless the request supplies it |
+| `model` | Nonempty model selector or supported upstream ID; built-in native providers have defaults; required for generative evaluation unless the request supplies it |
 | `baseURL` | HTTPS API base; loopback may use HTTP |
 | `apiKeyEnv` | Credential environment variable name; inline `apiKey` is rejected |
 | `noAuth` | Boolean; true only for loopback OpenAI-compatible endpoints |
 | `timeoutMs` | Positive integer up to 2,147,483,647 milliseconds |
 | `maxRetries` | Integer 0–10; OpenAI/Cloudflare default 0; Jev and generative presets default 2 |
-| `maxRequestBytes`, `maxResponseBytes` | Positive integer through 64 MiB; default 8 MiB. Cloudflare requests: Clef/Clef-flash default/cap 13 MiB; Omni default 36 MiB, configurable through 64 MiB |
+| `maxRequestBytes`, `maxResponseBytes` | Positive integer through 64 MiB; default 8 MiB. Jev requests default/cap 32 MiB. Cloudflare requests: Clef/Clef-flash default/cap 13 MiB; Omni default 36 MiB, configurable through 64 MiB |
 | `accountId` | Cloudflare REST account ID; otherwise `CLOUDFLARE_ACCOUNT_ID` |
 | `rejectIfBusy` | Cloudflare boolean; default false, incompatible with retries. Effective true fails REST preflight with `UNSUPPORTED_CAPABILITY`; see the [binding support and REST limitation](../guides/CLOUDFLARE_DECISIONS.md#capacity-rejection-and-ai-gateway) |
 | `gateway` | Cloudflare Gateway object; see the [Cloudflare guide](../guides/CLOUDFLARE_DECISIONS.md) |
+| `dangerZone` | Jev-only `{ images?: boolean, longContext?: boolean }`; both default false; see the [Jev guide](../guides/JEV.md) |
 | `maxTokens` | Generative output budget, 1–1,048,576; default 4096 |
 | `responseFormat` | Compatible generative presets: `json_schema`, `json_object`, `text` |
 | `tokenParameter` | Compatible generative presets: `max_completion_tokens` or `max_tokens` |
@@ -58,6 +59,10 @@ profile. Gateway configuration is optional for either SDK transport and for CLI
 | `options` | Custom factory's JSON options, e.g. its own baseURL |
 
 Upper numeric limits validate client configuration, not vendor model capabilities.
+Jev requests default to and are capped at 32 MiB; a smaller `maxRequestBytes`
+lowers that ceiling. `DECISION_JEV_IMAGES` and `DECISION_JEV_LONG_CONTEXT`
+accept `true` or `false`; their CLI overrides are `--jev-images`,
+`--no-jev-images`, `--jev-long-context`, and `--no-jev-long-context`.
 Cloudflare selects its byte budget from the effective request model, including
 per-call overrides. An explicit smaller `maxRequestBytes` remains the ceiling;
 selecting Omni cannot enlarge it. Omni's default is a bridge policy, not a
@@ -88,8 +93,8 @@ existing process environment > --env-file values
 The loader does not mutate the process environment. The SDK independently reads
 its documented ambient credential variables at provider construction.
 
-The [supported-model list](../../README.md#supported-models) records native
-selectors, aliases and defaults. Configuration precedence does not expand a
+The [model selector list](../../README.md#model-selectors) records native
+selectors and defaults. Configuration precedence does not expand a
 provider's accepted models or grant account access.
 
 For evaluation model selection:
@@ -99,7 +104,9 @@ For evaluation model selection:
 ```
 
 Jev defaults to `jev-latest`, with `JEV_MODEL` as a legacy/direct convenience.
-Native OpenAI Decisions defaults to `gpt-6-luna`; it accepts transport settings
+Native OpenAI Decisions defaults to `default` and accepts `luna` or explicit
+`gpt-6-luna`; Decision Bridge currently resolves each to upstream `gpt-6-luna`.
+OpenAI accepts transport settings
 and rejects generative output settings. Its default retry count is zero. Cloudflare Clef defaults to `clef`, uses
 account/token credentials, rejects generation settings, and also defaults to zero retries.
 A `DECISION_MODEL` or file model takes precedence over that convenience.

package/docs/reference/ERRORS.md

@@ -77,6 +77,9 @@ validation failures can still return HTTP 422/5012 and retain safe diagnostics.
 Keep the default disabled setting for ordinary REST
 inference; see the [Cloudflare guide](../guides/CLOUDFLARE_DECISIONS.md#capacity-rejection-and-ai-gateway).
 
-Keep a request ID and available Gateway log ID, bridge version, configured provider, requested/reported model,
-and template revision for incident analysis. Log input or results only under your
+Keep a request ID and available Gateway log ID, bridge version, configured provider,
+model selection, reported model, and template revision for incident analysis.
+For successful OpenAI calls, retain
+the requested selection, resolved outgoing ID, and reported model separately;
+see [model identities](../guides/OPENAI_DECISIONS.md#model-selection). Log input or results only under your
 own data-handling policy. No logging or telemetry is enabled by default.

package/docs/reference/PROVIDERS.md

@@ -2,10 +2,10 @@
 
 ## Native routes
 
-| Provider type | Wire API | Credential | Default model | Output strategy |
+| Provider type | Wire API | Credential | Default selector | Output strategy |
 | --- | --- | --- | --- | --- |
 | `jev` | `POST /v1/systemone` at api.typesafe.ai | `TYPESAFE_API_KEY` | `jev-latest` | Native typed decisions |
-| `openai-decisions` | `POST /v1/decisions` at api.openai.com | `OPENAI_API_KEY` | `gpt-6-luna` | Native Decisions with common and dedicated access |
+| `openai-decisions` | `POST /v1/decisions` at api.openai.com | `OPENAI_API_KEY` | `default` | Native Decisions with common and dedicated access |
 | `cloudflare-decisions` | Workers AI REST model route or `AI.run` binding | `CLOUDFLARE_API_TOKEN` and account ID for REST | `clef` | Native Clef decisions with common and dedicated access |
 
 `createProvider()` and the root SDK export these three native providers only.
@@ -15,9 +15,12 @@ maintained, but are not native decision models. See [custom providers](../guides
 
 ## Supported model selection
 
-See the root README's [model list](../../README.md#supported-models) for the
-built-in selectors and aliases. Jev accepts `jev-latest` and explicit Jev IDs from
-its account catalog. OpenAI Decisions supports only `gpt-6-luna` in this release.
+The [model selector inventory](../../README.md#model-selectors) summarizes the
+built-in providers. Jev accepts `jev-latest` and explicit Jev IDs from
+its account catalog. OpenAI Decisions accepts `default`, `luna`, and explicit
+`gpt-6-luna`. Decision Bridge resolves these to the upstream `gpt-6-luna` model
+in this release. The selected value remains in `meta.requestedModel`, the outgoing
+ID in `meta.resolvedModel`, and the service-reported identity in the response's `model`.
 Cloudflare supports `clef`, `clef-flash`, and `clef-omni`, including each full
 `@cf/cloudflare/<model>` alias. Unsupported OpenAI/Cloudflare selectors fail
 local preflight with `UNSUPPORTED_CAPABILITY`.
@@ -41,7 +44,7 @@ contract. The following additional forms are checked before dispatch:
 
 | Provider | Ordered text / embedded images | Typed string/boolean choices | Labelled score levels | Safety identifier | Model listing |
 | --- | --- | --- | --- | --- | --- |
-| Jev | Unsupported | Unsupported | Unsupported | Unsupported | Supported |
+| Jev | Ordered text; images with explicit opt-in | Unsupported | Unsupported | Unsupported | Supported |
 | OpenAI Decisions | Supported; up to 128 images, preserving order | Supported | Supported | Supported | Unsupported |
 | Cloudflare Clef / Clef-flash | Supported; up to four images before text | Supported | Supported; 2–10 levels | Unsupported | Unsupported |
 | Cloudflare Clef-omni | Supported; up to four images before audio/video/text | Supported | Supported; 2–10 levels | Unsupported | Unsupported |
@@ -59,7 +62,11 @@ capability fields `audio`, `videos`, `maxAudioClips`, and `maxVideos` normalize
 false/zero when omitted, preserving legacy custom profiles. Cloudflare's older
 models and all other shipped providers reject audio/video before inference.
 
-Dedicated `createDecision()` access is available on OpenAI Decisions and
+Jev additionally supports `box` questions on `jev-preview` and pinned 1.14+ models
+when `dangerZone.images` is enabled. Other built-ins reject box questions.
+See the [Jev guide](../guides/JEV.md) for asset placement and experimental opt-ins.
+
+Dedicated `createDecision()` access is available on Jev, OpenAI Decisions and
 Cloudflare providers. It uses each service's native request/response shape and
 bypasses bridge preparation and observation hooks.
 
@@ -71,6 +78,12 @@ intermediate language model, skill, portal prompt, or chat conversion is used.
 `GET /v1/models` lists native models. A listed catalog can differ from valid aliases;
 `jev-latest` is the documented stable alias.
 
+`jev-preview` selects the preview release. Images and longer context require
+explicit `dangerZone` settings. Common image input preserves ordering; native
+`createDecision()` additionally accepts JSON assets referenced in state,
+instructions, and criteria. Box outputs preserve normalized edges and confidence.
+See the [Jev guide](../guides/JEV.md) for limits and absence handling.
+
 Pin a version after evaluating it for your workload rather than assuming a moving
 alias yields reproducible quality. Store the returned `model` along with the
 requested model and your question-template revision.

package/docs/reference/SDK.md

@@ -48,7 +48,7 @@ guides. These are SDK options, not per-evaluation bridge options.
 | --- | --- |
 | `timeoutMs` | 30,000 ms; positive integer through 2,147,483,647; one transport budget for dispatch, retries, backoff, and response reading |
 | `maxRetries` | Additional eligible attempts, 0–10; Jev and generative presets default to 2, native OpenAI and Cloudflare to 0 |
-| `maxRequestBytes` | Complete serialized request ceiling; normally 8 MiB, configurable from 1 byte through 64 MiB; Cloudflare applies its [model-specific budgets](../guides/CLOUDFLARE_DECISIONS.md#embedded-images-and-limits) |
+| `maxRequestBytes` | Complete serialized request ceiling; normally 8 MiB, configurable from 1 byte through 64 MiB; Jev defaults to and caps at 32 MiB; Cloudflare applies its [model-specific budgets](../guides/CLOUDFLARE_DECISIONS.md#embedded-images-and-limits) |
 | `maxResponseBytes` | 8 MiB; configurable from 1 byte through 64 MiB; applies while reading the response body |
 | `fetchImpl` | Optional `(url: string, init?: RequestInit) => Promise<Response>`; defaults to the runtime's `fetch` |
 
@@ -72,7 +72,10 @@ they interact; [errors](ERRORS.md#retry-policy) lists retryable statuses.
 `model` and `safetyIdentifier`. New forms require declared provider capabilities;
 see [OpenAI Decisions](../guides/OPENAI_DECISIONS.md) and
 [Cloudflare Clef](../guides/CLOUDFLARE_DECISIONS.md). The request model
-wins over the provider's default. No default is assumed for a generative provider.
+wins over the provider's configured default, which an omitted request model inherits.
+OpenAI Decisions uses the `default` selector when its provider configuration omits
+`model`; `luna` and explicit `gpt-6-luna` are also supported. Its selectors
+resolve to upstream IDs within the provider. No default is assumed for a generative provider.
 `options` accepts `signal: AbortSignal` and `timeoutMs`, overriding the bridge's
 60-second evaluation budget for this call. It does not mutate the provider's
 independent transport timeout, including Workers AI binding calls.
@@ -92,10 +95,12 @@ when client retries are configured.
 ### `bridge.getCapabilities(model?)` and `bridge.validate(request)`
 
 Capability lookup is synchronous and reports implemented features and limits.
-`validate` resolves the model, snapshots/freezes the request, and checks capabilities
+`validate` applies the default model selection, snapshots/freezes the request, and checks capabilities
 and preparation-extension compatibility without inference. Unsupported features
 fail with `UNSUPPORTED_CAPABILITY` before dispatch. Native Decisions has no model
 listing operation; capability lookup is not account model discovery.
+OpenAI validated requests retain the selected value, while preflight checks the
+resolved outgoing request, including its model ID, against the byte limit.
 
 Providers can implement optional `validateRequest(resolvedRequest)` for additional
 static checks. This synchronous hook receives a frozen request, must return no
@@ -141,6 +146,10 @@ const q3 = score('How far did processing progress?', [
 ]);
 ```
 
+`box(instructions)` returns a box question with no criteria; supported providers
+must declare `boxes: true`. Jev supports it with experimental image opt-in and
+a supported model; see [Jev images and boxes](../guides/JEV.md).
+
 Builders return immutable question objects. `choice(instructions, criteria)` accepts
 a label map containing 1 to 255 options. `noul(instructions, criteria?)` accepts an
 optional criteria object,
@@ -196,7 +205,8 @@ rubric exactly. Generative providers calculate score and legend locally. Native
 values are validated and preserved, not normalized or replaced.
 
 **Usage:** `input_tokens` and `output_tokens` are nonnegative integers or null.
-Jev, OpenAI Decisions, and Cloudflare require reported integer counts. OpenAI and
+Jev accepts explicitly null counts as unknown; OpenAI Decisions and Cloudflare
+require reported integer counts. OpenAI and
 Anthropic cache creation/read counts are preserved separately when provided;
 Cloudflare does not fabricate cache or total-token fields. No total price, inferred cache saving, or
 estimated token count is fabricated.
@@ -207,7 +217,8 @@ estimated token count is fabricated.
 | --- | --- |
 | `provider` | Bridge backend name; native Jev reports `typesafe` |
 | `providerKind` | `decision` or `generative`; authoritative provider classification, never response-selected |
-| `requestedModel` | Resolved model requested by the caller |
+| `requestedModel` | Selected model after applying the provider default; OpenAI retains `default`, `luna`, or the explicit ID |
+| `resolvedModel` | Upstream model ID sent by OpenAI Decisions; optional for other providers |
 | `probabilitySource` | `native`, `elicited`, or custom/`unspecified` provenance |
 | `confidenceSource` | `native` or `unavailable` for built-in providers |
 | `modelSource` | `reported` or `requested` fallback for built-in providers |
@@ -225,7 +236,8 @@ unavailable metadata exists. Result objects and nested data returned by the brid
 are immutable. Standalone validation functions return snapshots, not frozen values.
 
 `schemaVersion` remains 1 for legacy requests and 2 for ordered images/text or
-richer question forms. Audio/video requests use 3. This result version is separate
+richer question forms. Audio/video requests use 3; requests with boxes use 4.
+This result version is separate
 from the CLI configuration schema, which remains 1.
 
 ## Extensions
@@ -298,6 +310,8 @@ automatic model fallback. The CLI has a separate streaming JSONL implementation.
 - `createProvider(config)`: factory requiring an explicit `type` equal to `jev`,
   `openai-decisions`, or `cloudflare-decisions`.
 - `JevProvider`, `OpenAIDecisionsProvider`, `CloudflareDecisionsProvider`: native provider classes.
+- `box(instructions)` and `JevProvider.createDecision(request, options?)`:
+  bounding boxes and native JSON assets; see the [Jev guide](../guides/JEV.md).
 - `scoreLevels(instructions, levels)` and the array overload of `choice`:
   labelled rubrics and typed string/boolean options, with provider capability checks.
 - `OpenAIDecisionsProvider.createDecision(request, options?)`: dedicated native
@@ -308,9 +322,9 @@ automatic model fallback. The CLI has a separate streaming JSONL implementation.
   an own `input.model` property or an explicitly supplied default; inherited
   models are ignored, and it never selects a Jev model.
   Question builders and schema generation validate without selecting an inference model.
-- `validateResult(input, questions, { native = false, probabilityDecimalPlaces })`: snapshot supplied
+- `validateResult(input, questions, { native = false, nullableUsage = false, probabilityDecimalPlaces })`: snapshot supplied
   questions and validate the canonical result; native mode requires confidence
-  and reported counts.
+  and reported counts unless the provider explicitly enables nullable usage.
 - `decideChoice(answer, { minProbability, minMargin = 0, abstainOptions = [], probabilityDecimalPlaces })`:
   returns a policy result, never executes an action. `minProbability` is required.
 - `DecisionError`, `publicError(error)`: public structured failure handling.

package/docs/reference/SOURCES.md

@@ -11,6 +11,10 @@ reference does not imply that authenticated inference was run against its servic
 | TypeSafe request/response API | https://docs.typesafe.ai/api |
 | TypeSafe JavaScript examples | https://docs.typesafe.ai/sdk/javascript |
 | Native model listing and aliases | https://docs.typesafe.ai/models |
+| Jev image assets and experimental opt-in | https://docs.typesafe.ai/images |
+| Jev bounding boxes | https://docs.typesafe.ai/primitives/box |
+| Jev 1.14 release | https://typesafe.ai/blog/jev-1-14 |
+| Jev nullable usage compatibility | https://docs.typesafe.ai/sdk/javascript/changelog |
 | Choice decisions | https://docs.typesafe.ai/primitives/choice |
 | Noul probabilities | https://docs.typesafe.ai/primitives/noul |
 | Score rubric and weighted expectation | https://docs.typesafe.ai/primitives/score |

package/examples/configs/openai-decisions.json

@@ -1,7 +1,7 @@
 {
     "schemaVersion": 1,
     "provider": "openai-decisions",
-    "model": "gpt-6-luna",
+    "model": "default",
     "apiKeyEnv": "OPENAI_API_KEY",
     "maxRetries": 0
 }

package/examples/decisions.native.json

@@ -1,5 +1,5 @@
 {
-    "model": "gpt-6-luna",
+    "model": "default",
     "input": "Export fails in Safari but works in Chrome.",
     "questions": [
         { "type": "predicate", "name": "browser_specific", "instructions": "Is the failure browser-specific?" },

package/package.json

@@ -1,6 +1,6 @@
 {
   "name": "@fayegram-ai/decision-bridge",
-  "version": "0.1.0",
+  "version": "0.1.2",
   "description": "JavaScript SDK and CLI for structured decisions across native decision APIs and configurable model providers",
   "repository": {
     "type": "git",

package/schemas/decision.config.schema.json

@@ -29,13 +29,27 @@
                     "$ref": "#/$defs/retries"
                 },
                 "maxRequestBytes": {
-                    "$ref": "#/$defs/bytes"
+                    "type": "integer",
+                    "minimum": 1,
+                    "maximum": 33554432
                 },
                 "maxResponseBytes": {
                     "$ref": "#/$defs/bytes"
                 },
                 "provider": {
                     "const": "jev"
+                },
+                "dangerZone": {
+                    "type": "object",
+                    "additionalProperties": false,
+                    "properties": {
+                        "images": {
+                            "type": "boolean"
+                        },
+                        "longContext": {
+                            "type": "boolean"
+                        }
+                    }
                 }
             }
         },

package/src/capabilities.mjs

@@ -1,6 +1,8 @@
 import { DecisionError, requireCondition as check } from './errors.mjs';
 import { cloneJson, freezeJson, isRecord } from './validation.mjs';
 import { CLOUDFLARE_MODELS } from './providers/cloudflare-profile.mjs';
+import { openaiModelProfile } from './providers/openai-profile.mjs';
+import { jevFeatures } from './providers/jev-profile.mjs';
 
 /** Conservative defaults preserve the pre-existing custom-provider contract. */
 export const LEGACY_CAPABILITIES = freezeJson({
@@ -8,11 +10,7 @@ export const LEGACY_CAPABILITIES = freezeJson({
     labeledScores: false, safetyIdentifier: false,
     maxImages: 0, maxChoiceOptions: 255, maxScoreLevels: 10,
     audio: false, videos: false, maxAudioClips: 0, maxVideos: 0,
-});
-const OPENAI_CAPABILITIES = freezeJson({
-    supported: true, orderedInput: true, images: true, typedChoices: true,
-    labeledScores: true, safetyIdentifier: true,
-    maxImages: 128, maxChoiceOptions: 255, maxScoreLevels: null,
+    boxes: false,
 });
 
 const CLOUDFLARE_CAPABILITIES = freezeJson({
@@ -20,7 +18,9 @@ const CLOUDFLARE_CAPABILITIES = freezeJson({
     labeledScores: true, safetyIdentifier: false, maxImages: 4, maxChoiceOptions: 255, maxScoreLevels: 10,
 });
 
-export function builtInCapabilities(type, model) {
+export function builtInCapabilities(type, model, options = {}) {
+    if (type === 'jev') return freezeJson({ ...LEGACY_CAPABILITIES,
+        ...jevFeatures(model, Object.hasOwn(options, 'dangerZone') ? options.dangerZone : undefined) });
     if (type === 'cloudflare-decisions') {
         const key = typeof model === 'string' ? model.trim().replace(/^@cf\/cloudflare\//, '') : '';
         const profile = Object.hasOwn(CLOUDFLARE_MODELS, key) ? CLOUDFLARE_MODELS[key] : undefined;
@@ -29,7 +29,8 @@ export function builtInCapabilities(type, model) {
             maxAudioClips: profile?.omni ? 4 : 0, maxVideos: profile?.omni ? 2 : 0 });
     }
     if (type !== 'openai-decisions') return LEGACY_CAPABILITIES;
-    return freezeJson({ ...LEGACY_CAPABILITIES, ...OPENAI_CAPABILITIES, supported: model === 'gpt-6-luna' });
+    const profile = openaiModelProfile(model);
+    return freezeJson({ ...LEGACY_CAPABILITIES, ...profile, supported: !!profile });
 }
 
 export function providerCapabilities(provider, model) {
@@ -48,7 +49,7 @@ export function providerCapabilities(provider, model) {
     check(isRecord(profile) && Object.keys(profile).every(key => Object.hasOwn(LEGACY_CAPABILITIES, key)),
         'Invalid capability profile.', 'CONFIGURATION_ERROR');
     const result = { ...LEGACY_CAPABILITIES, ...profile };
-    for (const key of ['supported', 'orderedInput', 'images', 'typedChoices', 'labeledScores', 'safetyIdentifier', 'audio', 'videos']) {
+    for (const key of ['supported', 'orderedInput', 'images', 'typedChoices', 'labeledScores', 'safetyIdentifier', 'audio', 'videos', 'boxes']) {
         check(typeof result[key] === 'boolean', 'Capability flags must be boolean.', 'CONFIGURATION_ERROR');
     }
     for (const key of ['maxImages', 'maxChoiceOptions', 'maxScoreLevels', 'maxAudioClips', 'maxVideos']) {
@@ -78,6 +79,7 @@ export function assertCapabilities(request, capabilities) {
     }
     if (Object.hasOwn(request, 'safetyIdentifier')) requireFeature(capabilities.safetyIdentifier, 'safetyIdentifier');
     for (const q of Object.values(request.questions)) {
+        if (q.type === 'box') requireFeature(capabilities.boxes, 'box questions');
         if (q.options) requireFeature(capabilities.typedChoices, 'typed choices');
         if (q.levels) requireFeature(capabilities.labeledScores, 'labelled scores');
         const choices = q.options?.length ?? (q.type === 'choice' ? Object.keys(q.criteria).length : 0);
@@ -89,6 +91,7 @@ export function assertCapabilities(request, capabilities) {
 }
 
 export function commonSchemaVersion(request) {
+    if (Object.values(request.questions).some(q => q.type === 'box')) return 4;
     if (request.input?.some(part => ['audio', 'video'].includes(part.type))) return 3;
     return Object.hasOwn(request, 'input') || Object.hasOwn(request, 'safetyIdentifier') ||
         Object.values(request.questions).some(q => q.options || q.levels) ? 2 : 1;

package/src/cli/config-validation.mjs

@@ -2,13 +2,14 @@ import { requireCondition as check } from '../errors.mjs';
 import { cloneJson, isRecord } from '../validation.mjs';
 import { cloudflareGateway, validateCloudflareLimits } from '../providers/cloudflare-profile.mjs';
 import { generationOptions } from '../custom/generative/shared.mjs';
+import { jevDangerZone, jevRequestLimit } from '../providers/jev-profile.mjs';
 
 export const PROVIDERS = ['jev', 'openai-decisions', 'cloudflare-decisions', 'custom-decision', 'custom-generative'];
 export const PRESETS = ['openai-compatible', 'openrouter', 'anthropic'];
 export const TRANSPORT = ['baseURL', 'maxRetries', 'maxRequestBytes', 'maxResponseBytes'];
 export const GENERATION = ['maxTokens', 'responseFormat', 'tokenParameter', 'parameters', 'noAuth'];
 export const PROVIDER_FIELDS = [...TRANSPORT, ...GENERATION, 'apiKeyEnv', 'model', 'preset', 'module',
-    'options', 'accountId', 'rejectIfBusy', 'gateway'];
+    'options', 'accountId', 'rejectIfBusy', 'gateway', 'dangerZone'];
 const FIELDS = new Set(['$schema', 'schemaVersion', 'provider', 'timeoutMs', ...PROVIDER_FIELDS]);
 export const NUMERIC = new Set(['timeoutMs', 'maxRetries', 'maxRequestBytes', 'maxResponseBytes', 'maxTokens']);
 export const KEY_ENVS = { jev: 'TYPESAFE_API_KEY', 'openai-decisions': 'OPENAI_API_KEY',
@@ -56,7 +57,14 @@ export function validateConfig(input, { complete = false } = {}) {
     check(config.module === undefined || ['custom-decision', 'custom-generative'].includes(config.provider),
         'module requires custom-decision or custom-generative.', 'CONFIGURATION_ERROR');
     check(config.options === undefined || isModule(config), 'options requires a custom provider module.', 'CONFIGURATION_ERROR');
+    // Validate nested shape even when a partial file omits its provider selector.
+    if (Object.hasOwn(config, 'dangerZone')) config.dangerZone = jevDangerZone(config.dangerZone);
     if (config.provider !== undefined) {
+        if (config.provider !== 'jev') check(!Object.hasOwn(config, 'dangerZone'),
+            'dangerZone requires Jev.', 'CONFIGURATION_ERROR');
+        else {
+            jevRequestLimit(config.maxRequestBytes);
+        }
         if (config.provider !== 'cloudflare-decisions') check(['accountId', 'rejectIfBusy', 'gateway'].every(key => config[key] === undefined),
             'Cloudflare settings require cloudflare-decisions.', 'CONFIGURATION_ERROR');
         else {

package/src/cli/config.mjs

@@ -1,8 +1,10 @@
 import { readFile, stat } from 'node:fs/promises';
 import { resolve, dirname } from 'node:path';
 import { parseEnv } from 'node:util';
+import { OPENAI_DEFAULT_MODEL } from '../providers/openai-profile.mjs';
 import { DecisionError, requireCondition as check } from '../errors.mjs';
 import { validateConfig, NUMERIC, PROVIDER_FIELDS } from './config-validation.mjs';
+import { jevDangerZone } from '../providers/jev-profile.mjs';
 export { validateConfig } from './config-validation.mjs';
 export { configuredProvider } from './provider-loader.mjs';
 
@@ -11,6 +13,7 @@ const ENV_FIELDS = {
     DECISION_API_KEY_ENV: 'apiKeyEnv', DECISION_TIMEOUT_MS: 'timeoutMs',
     DECISION_MAX_RETRIES: 'maxRetries', DECISION_RESPONSE_FORMAT: 'responseFormat',
     DECISION_ACCOUNT_ID: 'accountId', DECISION_REJECT_IF_BUSY: 'rejectIfBusy', DECISION_GATEWAY_ID: 'gateway',
+    DECISION_JEV_IMAGES: 'jevImages', DECISION_JEV_LONG_CONTEXT: 'jevLongContext',
 };
 
 async function boundedFile(path, maxBytes, label) {
@@ -46,13 +49,17 @@ export async function loadConfig({ configPath, envFile, overrides = {}, cwd = pr
     fileConfig = validateConfig(fileConfig);
     moduleBase = dirname(path);
   }
-  const environment = {};
+  const environment = Object.create(null);
   for (const [key, field] of Object.entries(ENV_FIELDS)) {
     if (effectiveEnv[key] === undefined) continue;
     const value = effectiveEnv[key];
     if (NUMERIC.has(field)) check(typeof value === 'string' && /^\d+$/.test(value),
       'Numeric DECISION_* variables must contain decimal integers.', 'CONFIGURATION_ERROR');
-    if (field === 'rejectIfBusy') {
+    if (field === 'jevImages' || field === 'jevLongContext') {
+      check(value === 'true' || value === 'false', 'Jev DECISION_* flags must be true or false.', 'CONFIGURATION_ERROR');
+      environment.dangerZone = { ...(Object.hasOwn(environment, 'dangerZone') ? environment.dangerZone : {}),
+        [field === 'jevImages' ? 'images' : 'longContext']: value === 'true' };
+    } else if (field === 'rejectIfBusy') {
       check(value === 'true' || value === 'false', 'DECISION_REJECT_IF_BUSY must be true or false.', 'CONFIGURATION_ERROR');
       environment[field] = value === 'true';
     } else environment[field] = field === 'gateway' ? { id: value } : NUMERIC.has(field) ? Number(value) : value;
@@ -61,6 +68,10 @@ export async function loadConfig({ configPath, envFile, overrides = {}, cwd = pr
   // environment-selected provider must not inherit that provider's key/endpoint.
   function mergeProviderLayer(base, layer, layerModuleBase = moduleBase) {
     const next = { ...base };
+    const dangerZone = Object.hasOwn(layer, 'dangerZone') ? layer.dangerZone : undefined;
+    // Validate before spreading, without filling defaults that would erase a
+    // different opt-in from a lower layer.
+    if (dangerZone !== undefined) jevDangerZone(dangerZone);
     // File and flag paths have different bases. Equal path text can identify
     // different implementations; compare destinations before changing the base.
     const moduleChanged = layer.module !== undefined && (typeof layer.module !== 'string' ||
@@ -71,6 +82,9 @@ export async function loadConfig({ configPath, envFile, overrides = {}, cwd = pr
     if (changed) for (const key of PROVIDER_FIELDS) delete next[key];
     if (layer.module !== undefined) moduleBase = layerModuleBase;
     return { ...next, ...layer,
+      ...(dangerZone === undefined ? {} : { dangerZone: {
+        ...(Object.hasOwn(next, 'dangerZone') ? next.dangerZone : {}), ...dangerZone,
+      } }),
       ...(layer.gateway === undefined ? {} : { gateway: { ...next.gateway, ...layer.gateway } }) };
   }
   const config = validateConfig(mergeProviderLayer(mergeProviderLayer(
@@ -78,7 +92,7 @@ export async function loadConfig({ configPath, envFile, overrides = {}, cwd = pr
   if (config.provider === 'jev' && config.model === undefined && effectiveEnv.JEV_MODEL?.trim()) {
     config.model = effectiveEnv.JEV_MODEL.trim();
   }
-  if (config.provider === 'openai-decisions' && config.model === undefined) config.model = 'gpt-6-luna';
+  if (config.provider === 'openai-decisions' && config.model === undefined) config.model = OPENAI_DEFAULT_MODEL;
   if (config.provider === 'cloudflare-decisions' && config.model === undefined) config.model = 'clef';
   return { config, env: effectiveEnv, moduleBase };
 }

package/src/cli/decisions.mjs

@@ -3,11 +3,21 @@ import { encodeCommonDecision } from '../providers/decisions-codec.mjs';
 import { preflightCloudflareDecision, preflightCommonCloudflareDecision } from '../providers/cloudflare-preflight.mjs';
 import { encodeCloudflareDecision } from '../providers/cloudflare-codec.mjs';
 import { CLOUDFLARE_MAX_REQUEST_LIMIT } from '../providers/cloudflare-profile.mjs';
+import { resolveOpenAIModel } from '../providers/openai-profile.mjs';
+import { preflightCommonJevDecision, preflightJevDecision, encodeJevDecision } from '../providers/jev-preflight.mjs';
+import { JEV_REQUEST_LIMIT } from '../providers/jev-profile.mjs';
 
 /** Provider-specific native dispatch is shared by validation, initialization and calls. */
 export function decisionProfile(provider) {
+    if (provider === 'jev') return {
+        common: preflightCommonJevDecision, native: preflightJevDecision, encode: encodeJevDecision,
+        models: true, inputLimit: JEV_REQUEST_LIMIT,
+        options: config => ({ model: config.model, maxRequestBytes: config.maxRequestBytes,
+            dangerZone: Object.hasOwn(config, 'dangerZone') ? config.dangerZone : undefined }),
+    };
     if (provider === 'openai-decisions') return {
         common: preflightCommonDecision, native: preflightDecision, encode: encodeCommonDecision,
+        resolveModel: resolveOpenAIModel,
         options: config => ({ model: config.model, maxRequestBytes: config.maxRequestBytes }),
     };
     if (provider === 'cloudflare-decisions') return {

package/src/cli/initialize.mjs

@@ -4,6 +4,7 @@ import { DecisionError } from '../errors.mjs';
 import { validateRequest } from '../validation.mjs';
 import { decisionProfile } from './decisions.mjs';
 import { validateConfig, KEY_ENVS } from './config-validation.mjs';
+import { OPENAI_DEFAULT_MODEL } from '../providers/openai-profile.mjs';
 
 /** Templates are honest edit points for an unknown protocol, never fake inference. */
 function providerTemplate(kind) {
@@ -38,6 +39,7 @@ export async function initialize(directory, config, native = false, moduleBase =
         ...(generateModule ? { module: './provider.mjs' } : {}),
         ...(config.module ? { module: resolve(moduleBase, config.module) } : {}),
         ...(config.provider === 'jev' && config.model === undefined ? { model: 'jev-latest' } : {}),
+        ...(config.provider === 'openai-decisions' && config.model === undefined ? { model: OPENAI_DEFAULT_MODEL } : {}),
         ...(custom && config.model === undefined ? { model: 'YOUR_MODEL' } : {}),
     }, { complete: true });
     const request = { state: "ModuleNotFoundError: No module named 'pytest'", questions: {
@@ -47,12 +49,16 @@ export async function initialize(directory, config, native = false, moduleBase =
         missing_dependency: { type: 'noul', instructions: 'Does this indicate a missing Python package?' },
     } };
     const profile = decisionProfile(config.provider);
+    const sample = native ? profile.native(profile.encode(validateRequest(request, template.model)),
+        profile.options(template)) : request;
+    // OpenAI request files inherit selection from configuration, including after later edits.
+    const generated = { ...sample };
+    if (config.provider === 'openai-decisions') delete generated.model;
     const schema = await readFile(new URL('../../schemas/decision.config.schema.json', import.meta.url), 'utf8');
     const files = {
         'decision.config.json': JSON.stringify(template, null, 2) + '\n',
         'decision.config.schema.json': schema,
-        'request.json': JSON.stringify(native ? profile.native(profile.encode(validateRequest(request, template.model)),
-            profile.options(template)) : request, null, 2) + '\n',
+        'request.json': JSON.stringify(generated, null, 2) + '\n',
         '.env.example': `${template.apiKeyEnv}=replace_with_your_api_key\n` +
             (config.provider === 'cloudflare-decisions' ? 'CLOUDFLARE_ACCOUNT_ID=replace_with_your_account_id\n' : ''),
         '.gitignore': '.env\n.env.*\n!.env.example\nnode_modules/\n*.tmp\n',