@neon/ai-sdk-provider 1.1.0 → 1.2.0

package/README.md

@@ -69,20 +69,24 @@ Which ids your branch serves is account-specific during the beta; `GET $NEON_AI_
 
 Upstream backends behind the gateway accept different subsets of the OpenAI-style parameters the AI SDK emits, and sending one an upstream rejects is a hard `400`. The provider drops those before the request and records a warning in `result.warnings`, so a call succeeds instead of failing on a parameter you passed in good faith.
 
-These rules apply on the Anthropic Messages and Chat Completions routes. The Responses route (every `gpt-*` id) relies on the upstream OpenAI model's own stripping instead, so its behaviour and its warning wording are the AI SDK's rather than described here — but `getNeonModelCapabilities` still answers for those ids, and the `gpt-5` row below is what it reports rather than something this provider drops.
+These rules apply on the Anthropic Messages and Chat Completions routes. The Responses route (every `gpt-*` id) relies on the upstream OpenAI model's own stripping instead, so its behaviour and its warning wording are the AI SDK's rather than described here. `getNeonModelCapabilities` still answers for those ids, and the `gpt-5` and `gpt-6` rows below are what it reports rather than something this provider drops.
 
 | Models | Dropped |
 | --- | --- |
-| Claude 4.7 and newer (`claude-opus-4-7`, `claude-opus-4-8`, `claude-opus-5`, `claude-sonnet-5`, `claude-fable-5`, `claude-fable-5-1`) | `temperature`, `topP` |
+| Claude 4.7 and newer (`claude-opus-4-7`, `claude-opus-4-8`, `claude-opus-5`, `claude-sonnet-5`, `claude-fable-5`, `claude-fable-5-1`, `claude-haiku-5-5`, `claude-sonnet-5-5`) | `temperature`, `topP` |
 | All Claude | `frequencyPenalty`, `presencePenalty`, `seed`, `reasoningEffort`, and `topP` when you set both `temperature` and `topP` (Anthropic accepts only one) |
 | `gpt-oss` | `frequencyPenalty`, `presencePenalty`, `seed`, `stopSequences` |
 | Qwen, Gemma | `frequencyPenalty`, `presencePenalty`, `seed` |
-| `glm-5-2`, `glm-5-3-flash`, `inkling`, `kimi-k3` | `frequencyPenalty`, `presencePenalty` |
+| `glm-5-2`, `glm-5-3`, `glm-5-3-flash`, `inkling`, `kimi-k3` | `frequencyPenalty`, `presencePenalty` |
+| Grok, DeepSeek | `frequencyPenalty`, `presencePenalty` |
 | Meta Llama | `frequencyPenalty`, `presencePenalty`, `seed` |
 | `gemini-3-5-flash-lite` | `frequencyPenalty`, `presencePenalty` |
 | `gemini-3-6-flash` | `temperature`, `topP`, `frequencyPenalty`, `presencePenalty` |
+| `gemini-3-7-flash`, `gemini-3-8-flash`, `gemini-4-argon` | `temperature`, `topP`, `frequencyPenalty`, `presencePenalty` |
 | Every other Gemini | nothing |
-| `gpt-5`, `gpt-5-mini`, `gpt-5-nano`, `gpt-5-5-pro` (reported only — Responses strips these upstream) | `temperature`, `topP` |
+| `gpt-5`, `gpt-5-mini`, `gpt-5-nano`, `gpt-5-5`, `gpt-5-5-pro`, `gpt-5-6-luna`, `gpt-5-6-sol`, `gpt-5-6-terra`, `gpt-6-astra`, `gpt-6-sol`, `gpt-6-luna`, `gpt-6-1-sol` (reported only; Responses strips these upstream) | `temperature`, `topP` |
+
+On the Responses API, the gateway accepts `temperature` and `topP` only when reasoning effort is `none`, so the `gpt-*` rows describe each model's default effort. `gpt-6-astra`, `gpt-6-1-sol`, `gpt-5`, and `gpt-5-5-pro` don't accept effort `none`, so they never accept either parameter. The upstream OpenAI model drops both for every `gpt-5*` and `gpt-6*` id, even when reasoning effort is `none`.
 
 **`temperature` on a Claude 5 model therefore has no effect.** That is the gateway's behaviour, not a provider choice; sending it returns `does not support the temperature parameter`. Steer those models with Anthropic's own effort control instead — note that this is `effort`, not the OpenAI-style `reasoningEffort`, which every Claude id drops:
 
@@ -104,7 +108,7 @@ getNeonModelCapabilities('gpt-6-astra').supportsTemperature; // false
 getNeonModelCapabilities('glm-5-2').supportsPenalties; // false
 ```
 
-**The rules are per model, not per family.** Two Gemini ids reject penalties while their siblings accept them, and `gemini-3-6-flash` rejects `temperature` and `topP` outright, so reading a row for "Gemini" is not enough — check the id. Every dropped-options table row was measured against the gateway rather than inherited from the upstream provider's own documentation, which disagrees in both directions. `getNeonModelCapabilities('gpt-6-astra').supportsTemperature` is `false` because [neon.com/models.json](https://neon.com/models.json) lists `temperature: false` for that id; it is not a live gateway measurement.
+**The rules are per model, not per family.** Some Gemini ids reject penalties while their siblings accept them, and `gemini-3-6-flash`, `gemini-3-7-flash`, `gemini-3-8-flash`, and `gemini-4-argon` reject `temperature` and `topP` outright, so reading a row for "Gemini" is not enough; check the id. Every dropped-options table row was measured against the gateway rather than inherited from the upstream provider's own documentation, which disagrees in both directions.
 
 A model none of these rules match is left untouched, so a brand-new id gets the gateway's own error rather than a guess. That is also why the table can lag: an id added since the last release inherits the permissive default until someone measures it.
 
@@ -128,7 +132,7 @@ const { embeddings } = await embedMany({
 });
 ```
 
-Both models return 1024-dimensional vectors. `qwen3-embedding-0-6b` honors `providerOptions.neon.dimensions` for shorter vectors; `gte-large-en` ignores it. The gateway accepts at most 150 inputs per request, so `embedMany()` splits larger lists into batches of 150. `NeonEmbeddingModelId` autocompletes the known ids; any other string is passed through to the gateway. `textEmbeddingModel()` is a deprecated alias.
+`qwen3-embedding-0-6b`, `gte-large-en`, and `bge-large-en` return 1024-dimensional vectors. `qwen3-embedding-0-6b` honors `providerOptions.neon.dimensions` for shorter vectors; `gte-large-en` and `bge-large-en` ignore it. The gateway accepts at most 150 inputs per request, so `embedMany()` splits larger lists into batches of 150. `NeonEmbeddingModelId` autocompletes the known ids; any other string is passed through to the gateway. `textEmbeddingModel()` is a deprecated alias.
 
 ## Decisions
 

package/dist/lib/neon-anthropic-language-model.d.ts.map

@@ -1 +1 @@
-{"version":3,"file":"neon-anthropic-language-model.d.ts","names":["AnthropicMessagesLanguageModel","LanguageModelV3","LanguageModelV3CallOptions","LanguageModelV3GenerateResult","LanguageModelV3StreamResult","NeonAnthropicLanguageModel","Promise","AnthropicMessagesLanguageModel","LanguageModelV3","LanguageModelV3CallOptions","LanguageModelV3GenerateResult","LanguageModelV3StreamResult","NeonAnthropicLanguageModel","withGatewayCompat","doGenerate","options","Promise","doStream"],"sources":["../../src/lib/neon-anthropic-language-model.ts"],"mappings":";;;;;;;AA+BA;AACC;AA6BUE;AACCC;AAARG;AASOJ;AACCE;AAARE;AAxCKN;AACGC;AAAe;;;;;;cAFdI,0BAAAA,SACJL,8BAAAA,YACGC;;sBA4BDC,6BACPI,QAAQH;oBASDD,6BACPI,QAAQF"}
+{"version":3,"file":"neon-anthropic-language-model.d.ts","names":["AnthropicMessagesLanguageModel","LanguageModelV3","LanguageModelV3CallOptions","LanguageModelV3GenerateResult","LanguageModelV3StreamResult","NeonAnthropicLanguageModel","Promise","AnthropicMessagesLanguageModel","LanguageModelV3","LanguageModelV3CallOptions","LanguageModelV3GenerateResult","LanguageModelV3StreamResult","NeonAnthropicLanguageModel","withGatewayCompat","doGenerate","options","Promise","doStream"],"sources":["../../src/lib/neon-anthropic-language-model.ts"],"mappings":";;;;;;;AA+BA;AACC;AA6BUE;AACCC;AAARG;AASOJ;AACCE;AAARE;AAxCKN;AACGC;AAAe;;;;;;A,cAFdI,0BAAAA,SACJL,8BAAAA,YACGC,e;;E,oBA4BDC,0B,GACPI,O,CAAQH,6B;E,kBASDD,0B,GACPI,O,CAAQF,2B"}

package/dist/lib/neon-chat-options.d.ts

@@ -1,6 +1,6 @@
 //#region src/lib/neon-chat-options.d.ts
 /** Published catalog ids from https://neon.com/models.json (canonical, unprefixed). */
-declare const NEON_MODELS_DEV_IDS: readonly ["claude-fable-5", "claude-fable-5-1", "claude-haiku-4-5", "claude-opus-4-1", "claude-opus-4-5", "claude-opus-4-6", "claude-opus-4-7", "claude-opus-4-8", "claude-opus-5", "claude-opus-5-5", "claude-sonnet-4-5", "claude-sonnet-4-6", "claude-sonnet-5", "gpt-5", "gpt-5-1", "gpt-5-2", "gpt-5-3-codex", "gpt-5-4", "gpt-5-4-mini", "gpt-5-4-nano", "gpt-5-5", "gpt-5-5-pro", "gpt-5-6-luna", "gpt-5-6-sol", "gpt-5-6-terra", "gpt-5-mini", "gpt-5-nano", "gpt-6-astra", "gpt-oss-120b", "gpt-oss-20b", "gemini-3-1-flash-lite", "gemini-3-1-pro", "gemini-3-5-flash", "gemini-3-5-flash-lite", "gemini-3-6-flash", "gemini-3-flash", "gemma-3-12b", "llama-4-maverick", "meta-llama-3-1-8b-instruct", "meta-llama-3-3-70b-instruct", "qwen3-next-80b-a3b-instruct", "qwen35-122b-a10b", "glm-5-2", "glm-5-3-flash", "grok-4-6", "inkling", "kimi-k3"];
+declare const NEON_MODELS_DEV_IDS: readonly ["claude-fable-5", "claude-fable-5-1", "claude-haiku-4-5", "claude-haiku-5-5", "claude-opus-4-1", "claude-opus-4-5", "claude-opus-4-6", "claude-opus-4-7", "claude-opus-4-8", "claude-opus-5", "claude-opus-5-5", "claude-sonnet-4-5", "claude-sonnet-4-6", "claude-sonnet-5", "claude-sonnet-5-5", "gpt-5", "gpt-5-1", "gpt-5-2", "gpt-5-3-codex", "gpt-5-4", "gpt-5-4-mini", "gpt-5-4-nano", "gpt-5-5", "gpt-5-5-pro", "gpt-5-6-luna", "gpt-5-6-sol", "gpt-5-6-terra", "gpt-5-mini", "gpt-5-nano", "gpt-6-1-sol", "gpt-6-astra", "gpt-6-luna", "gpt-6-sol", "gpt-oss-120b", "gpt-oss-20b", "gemini-3-1-flash-lite", "gemini-3-1-pro", "gemini-3-5-flash", "gemini-3-5-flash-lite", "gemini-3-6-flash", "gemini-3-7-flash", "gemini-3-8-flash", "gemini-3-flash", "gemini-4-argon", "gemma-3-12b", "llama-4-maverick", "meta-llama-3-1-8b-instruct", "meta-llama-3-3-70b-instruct", "qwen3-next-80b-a3b-instruct", "qwen35-122b-a10b", "glm-5-2", "glm-5-3", "glm-5-3-flash", "grok-4-6", "grok-4-7", "inkling", "kimi-k3", "deepseek-v4-1-flash"];
 /** A known Neon AI Gateway model id. */
 type NeonKnownModelId = (typeof NEON_MODELS_DEV_IDS)[number];
 /**

package/dist/lib/neon-chat-options.d.ts.map

@@ -1 +1 @@
-{"version":3,"file":"neon-chat-options.d.ts","names":["NEON_MODELS_DEV_IDS","NeonKnownModelId","NeonChatModelId","NEON_MODELS_DEV_IDS","NeonKnownModelId","NeonChatModelId"],"sources":["../../src/lib/neon-chat-options.ts"],"mappings":";;AAiBaA,cAAAA,mBA0DH,EAAA,SAAA,CAAA,gBAAA,EAAA,kBAAA,EAAA,kBAAA,EAAA,iBAAA,EAAA,iBAAA,EAAA,iBAAA,EAAA,iBAAA,EAAA,iBAAA,EAAA,eAAA,EAAA,iBAAA,EAAA,mBAAA,EAAA,mBAAA,EAAA,iBAAA,EAAA,OAAA,EAAA,SAAA,EAAA,SAAA,EAAA,eAAA,EAAA,SAAA,EAAA,cAAA,EAAA,cAAA,EAAA,SAAA,EAAA,aAAA,EAAA,cAAA,EAAA,aAAA,EAAA,eAAA,EAAA,YAAA,EAAA,YAAA,EAAA,aAAA,EAAA,cAAA,EAAA,aAAA,EAAA,uBAAA,EAAA,gBAAA,EAAA,kBAAA,EAAA,uBAAA,EAAA,kBAAA,EAAA,gBAAA,EAAA,aAAA,EAAA,kBAAA,EAAA,4BAAA,EAAA,6BAAA,EAAA,6BAAA,EAAA,kBAAA,EAAA,SAAA,EAAA,eAAA,EAAA,UAAA,EAAA,SAAA,EAAA,SAAA,CAAA;AAGV;AAOYE,KAPAD,gBAAAA,GAOe,CAAGA,OAPSD,mBAOO,CAAA,CAAA,MAAA,CAAA;;;;;;KAAlCE,eAAAA,GAAkBD"}
+{"version":3,"file":"neon-chat-options.d.ts","names":["NEON_MODELS_DEV_IDS","NeonKnownModelId","NeonChatModelId","NEON_MODELS_DEV_IDS","NeonKnownModelId","NeonChatModelId"],"sources":["../../src/lib/neon-chat-options.ts"],"mappings":";;AAiBaA,cAAAA,mBAsEH,EAAA,SAAA,CAAA,gBAAA,EAAA,kBAAA,EAAA,kBAAA,EAAA,kBAAA,EAAA,iBAAA,EAAA,iBAAA,EAAA,iBAAA,EAAA,iBAAA,EAAA,iBAAA,EAAA,eAAA,EAAA,iBAAA,EAAA,mBAAA,EAAA,mBAAA,EAAA,iBAAA,EAAA,mBAAA,EAAA,OAAA,EAAA,SAAA,EAAA,SAAA,EAAA,eAAA,EAAA,SAAA,EAAA,cAAA,EAAA,cAAA,EAAA,SAAA,EAAA,aAAA,EAAA,cAAA,EAAA,aAAA,EAAA,eAAA,EAAA,YAAA,EAAA,YAAA,EAAA,aAAA,EAAA,aAAA,EAAA,YAAA,EAAA,WAAA,EAAA,cAAA,EAAA,aAAA,EAAA,uBAAA,EAAA,gBAAA,EAAA,kBAAA,EAAA,uBAAA,EAAA,kBAAA,EAAA,kBAAA,EAAA,kBAAA,EAAA,gBAAA,EAAA,gBAAA,EAAA,aAAA,EAAA,kBAAA,EAAA,4BAAA,EAAA,6BAAA,EAAA,6BAAA,EAAA,kBAAA,EAAA,SAAA,EAAA,SAAA,EAAA,eAAA,EAAA,UAAA,EAAA,UAAA,EAAA,SAAA,EAAA,SAAA,EAAA,qBAAA,CAAA;AAGV;AAOYE,KAPAD,gBAAAA,GAOe,CAAGA,OAPSD,mBAOO,CAAA,CAAA,MAAA,CAAA;;;;;;A,KAAlCE,eAAAA,GAAkBD,gB"}

package/dist/lib/neon-chat-options.js

@@ -4,6 +4,7 @@ const NEON_MODELS_DEV_IDS = [
 	"claude-fable-5",
 	"claude-fable-5-1",
 	"claude-haiku-4-5",
+	"claude-haiku-5-5",
 	"claude-opus-4-1",
 	"claude-opus-4-5",
 	"claude-opus-4-6",
@@ -14,6 +15,7 @@ const NEON_MODELS_DEV_IDS = [
 	"claude-sonnet-4-5",
 	"claude-sonnet-4-6",
 	"claude-sonnet-5",
+	"claude-sonnet-5-5",
 	"gpt-5",
 	"gpt-5-1",
 	"gpt-5-2",
@@ -28,7 +30,10 @@ const NEON_MODELS_DEV_IDS = [
 	"gpt-5-6-terra",
 	"gpt-5-mini",
 	"gpt-5-nano",
+	"gpt-6-1-sol",
 	"gpt-6-astra",
+	"gpt-6-luna",
+	"gpt-6-sol",
 	"gpt-oss-120b",
 	"gpt-oss-20b",
 	"gemini-3-1-flash-lite",
@@ -36,7 +41,10 @@ const NEON_MODELS_DEV_IDS = [
 	"gemini-3-5-flash",
 	"gemini-3-5-flash-lite",
 	"gemini-3-6-flash",
+	"gemini-3-7-flash",
+	"gemini-3-8-flash",
 	"gemini-3-flash",
+	"gemini-4-argon",
 	"gemma-3-12b",
 	"llama-4-maverick",
 	"meta-llama-3-1-8b-instruct",
@@ -44,10 +52,13 @@ const NEON_MODELS_DEV_IDS = [
 	"qwen3-next-80b-a3b-instruct",
 	"qwen35-122b-a10b",
 	"glm-5-2",
+	"glm-5-3",
 	"glm-5-3-flash",
 	"grok-4-6",
+	"grok-4-7",
 	"inkling",
-	"kimi-k3"
+	"kimi-k3",
+	"deepseek-v4-1-flash"
 ];
 //#endregion
 export { NEON_MODELS_DEV_IDS };

package/dist/lib/neon-chat-options.js.map

@@ -1 +1 @@
-{"version":3,"file":"neon-chat-options.js","names":[],"sources":["../../src/lib/neon-chat-options.ts"],"sourcesContent":["// Models served by the Neon AI Gateway. Anthropic and OpenAI models are routed\n// to their provider-native endpoints; everything else uses the unified MLflow\n// (OpenAI-compatible) endpoint.\n//\n// Ids use the canonical Neon (unprefixed) form, matching\n// https://neon.com/models.json. The gateway also accepts the legacy\n// `databricks-` prefixed form, which still resolves via the `(string & {})`\n// fallback on `NeonChatModelId`.\n//\n// `NEON_MODELS_DEV_IDS` mirrors the `released: true` entries of\n// neon.com/models.json `neon.models` exactly — `neon-catalog-drift.test.ts`\n// fails if the two diverge. A branch's live list\n// is `GET $NEON_AI_GATEWAY_BASE_URL/v1/models`. There is deliberately no second\n// list for ids the gateway serves ahead of the published catalog: such an id\n// already works because `NeonChatModelId` accepts any string.\n\n/** Published catalog ids from https://neon.com/models.json (canonical, unprefixed). */\nexport const NEON_MODELS_DEV_IDS = [\n\t// Anthropic (native Messages API)\n\t\"claude-fable-5\",\n\t\"claude-fable-5-1\",\n\t\"claude-haiku-4-5\",\n\t\"claude-opus-4-1\",\n\t\"claude-opus-4-5\",\n\t\"claude-opus-4-6\",\n\t\"claude-opus-4-7\",\n\t\"claude-opus-4-8\",\n\t\"claude-opus-5\",\n\t\"claude-opus-5-5\",\n\t\"claude-sonnet-4-5\",\n\t\"claude-sonnet-4-6\",\n\t\"claude-sonnet-5\",\n\t// OpenAI (native Responses API)\n\t\"gpt-5\",\n\t\"gpt-5-1\",\n\t\"gpt-5-2\",\n\t\"gpt-5-3-codex\",\n\t\"gpt-5-4\",\n\t\"gpt-5-4-mini\",\n\t\"gpt-5-4-nano\",\n\t\"gpt-5-5\",\n\t\"gpt-5-5-pro\",\n\t\"gpt-5-6-luna\",\n\t\"gpt-5-6-sol\",\n\t\"gpt-5-6-terra\",\n\t\"gpt-5-mini\",\n\t\"gpt-5-nano\",\n\t\"gpt-6-astra\",\n\t// OpenAI open-weight (unified MLflow endpoint)\n\t\"gpt-oss-120b\",\n\t\"gpt-oss-20b\",\n\t// Google (unified MLflow endpoint)\n\t\"gemini-3-1-flash-lite\",\n\t\"gemini-3-1-pro\",\n\t\"gemini-3-5-flash\",\n\t\"gemini-3-5-flash-lite\",\n\t\"gemini-3-6-flash\",\n\t\"gemini-3-flash\",\n\t\"gemma-3-12b\",\n\t// Meta (unified MLflow endpoint)\n\t\"llama-4-maverick\",\n\t\"meta-llama-3-1-8b-instruct\",\n\t\"meta-llama-3-3-70b-instruct\",\n\t// Alibaba (unified MLflow endpoint)\n\t\"qwen3-next-80b-a3b-instruct\",\n\t\"qwen35-122b-a10b\",\n\t// Zhipu (unified MLflow endpoint)\n\t\"glm-5-2\",\n\t\"glm-5-3-flash\",\n\t// xAI (unified MLflow endpoint)\n\t\"grok-4-6\",\n\t// Thinking Machines (unified MLflow endpoint)\n\t\"inkling\",\n\t// Moonshot (unified MLflow endpoint)\n\t\"kimi-k3\",\n] as const;\n\n/** A known Neon AI Gateway model id. */\nexport type NeonKnownModelId = (typeof NEON_MODELS_DEV_IDS)[number];\n\n/**\n * A Neon AI Gateway model id. Known ids are listed for autocomplete; any other\n * id (e.g. a brand-new model, or the legacy `databricks-` prefixed form) is\n * accepted via the `(string & {})` fallback.\n */\nexport type NeonChatModelId = NeonKnownModelId | (string & {});\n"],"mappings":";;AAiBA,MAAa,sBAAsB;CAElC;CACA;CACA;CACA;CACA;CACA;CACA;CACA;CACA;CACA;CACA;CACA;CACA;CAEA;CACA;CACA;CACA;CACA;CACA;CACA;CACA;CACA;CACA;CACA;CACA;CACA;CACA;CACA;CAEA;CACA;CAEA;CACA;CACA;CACA;CACA;CACA;CACA;CAEA;CACA;CACA;CAEA;CACA;CAEA;CACA;CAEA;CAEA;CAEA;AACD"}
+{"version":3,"file":"neon-chat-options.js","names":[],"sources":["../../src/lib/neon-chat-options.ts"],"sourcesContent":["// Models served by the Neon AI Gateway. Anthropic and OpenAI models are routed\n// to their provider-native endpoints; everything else uses the unified MLflow\n// (OpenAI-compatible) endpoint.\n//\n// Ids use the canonical Neon (unprefixed) form, matching\n// https://neon.com/models.json. The gateway also accepts the legacy\n// `databricks-` prefixed form, which still resolves via the `(string & {})`\n// fallback on `NeonChatModelId`.\n//\n// `NEON_MODELS_DEV_IDS` mirrors the `released: true` chat entries of\n// neon.com/models.json `neon.models` exactly — `neon-catalog-drift.test.ts`\n// fails if the two diverge. A branch's live list\n// is `GET $NEON_AI_GATEWAY_BASE_URL/v1/models`. There is deliberately no second\n// list for ids the gateway serves ahead of the published catalog: such an id\n// already works because `NeonChatModelId` accepts any string.\n\n/** Published catalog ids from https://neon.com/models.json (canonical, unprefixed). */\nexport const NEON_MODELS_DEV_IDS = [\n\t// Anthropic (native Messages API)\n\t\"claude-fable-5\",\n\t\"claude-fable-5-1\",\n\t\"claude-haiku-4-5\",\n\t\"claude-haiku-5-5\",\n\t\"claude-opus-4-1\",\n\t\"claude-opus-4-5\",\n\t\"claude-opus-4-6\",\n\t\"claude-opus-4-7\",\n\t\"claude-opus-4-8\",\n\t\"claude-opus-5\",\n\t\"claude-opus-5-5\",\n\t\"claude-sonnet-4-5\",\n\t\"claude-sonnet-4-6\",\n\t\"claude-sonnet-5\",\n\t\"claude-sonnet-5-5\",\n\t// OpenAI (native Responses API)\n\t\"gpt-5\",\n\t\"gpt-5-1\",\n\t\"gpt-5-2\",\n\t\"gpt-5-3-codex\",\n\t\"gpt-5-4\",\n\t\"gpt-5-4-mini\",\n\t\"gpt-5-4-nano\",\n\t\"gpt-5-5\",\n\t\"gpt-5-5-pro\",\n\t\"gpt-5-6-luna\",\n\t\"gpt-5-6-sol\",\n\t\"gpt-5-6-terra\",\n\t\"gpt-5-mini\",\n\t\"gpt-5-nano\",\n\t\"gpt-6-1-sol\",\n\t\"gpt-6-astra\",\n\t\"gpt-6-luna\",\n\t\"gpt-6-sol\",\n\t// OpenAI open-weight (unified MLflow endpoint)\n\t\"gpt-oss-120b\",\n\t\"gpt-oss-20b\",\n\t// Google (unified MLflow endpoint)\n\t\"gemini-3-1-flash-lite\",\n\t\"gemini-3-1-pro\",\n\t\"gemini-3-5-flash\",\n\t\"gemini-3-5-flash-lite\",\n\t\"gemini-3-6-flash\",\n\t\"gemini-3-7-flash\",\n\t\"gemini-3-8-flash\",\n\t\"gemini-3-flash\",\n\t\"gemini-4-argon\",\n\t\"gemma-3-12b\",\n\t// Meta (unified MLflow endpoint)\n\t\"llama-4-maverick\",\n\t\"meta-llama-3-1-8b-instruct\",\n\t\"meta-llama-3-3-70b-instruct\",\n\t// Alibaba (unified MLflow endpoint)\n\t\"qwen3-next-80b-a3b-instruct\",\n\t\"qwen35-122b-a10b\",\n\t// Zhipu (unified MLflow endpoint)\n\t\"glm-5-2\",\n\t\"glm-5-3\",\n\t\"glm-5-3-flash\",\n\t// xAI (unified MLflow endpoint)\n\t\"grok-4-6\",\n\t\"grok-4-7\",\n\t// Thinking Machines (unified MLflow endpoint)\n\t\"inkling\",\n\t// Moonshot (unified MLflow endpoint)\n\t\"kimi-k3\",\n\t// DeepSeek (unified MLflow endpoint)\n\t\"deepseek-v4-1-flash\",\n] as const;\n\n/** A known Neon AI Gateway model id. */\nexport type NeonKnownModelId = (typeof NEON_MODELS_DEV_IDS)[number];\n\n/**\n * A Neon AI Gateway model id. Known ids are listed for autocomplete; any other\n * id (e.g. a brand-new model, or the legacy `databricks-` prefixed form) is\n * accepted via the `(string & {})` fallback.\n */\nexport type NeonChatModelId = NeonKnownModelId | (string & {});\n"],"mappings":";;AAiBA,MAAa,sBAAsB;CAElC;CACA;CACA;CACA;CACA;CACA;CACA;CACA;CACA;CACA;CACA;CACA;CACA;CACA;CACA;CAEA;CACA;CACA;CACA;CACA;CACA;CACA;CACA;CACA;CACA;CACA;CACA;CACA;CACA;CACA;CACA;CACA;CACA;CAEA;CACA;CAEA;CACA;CACA;CACA;CACA;CACA;CACA;CACA;CACA;CACA;CAEA;CACA;CACA;CAEA;CACA;CAEA;CACA;CACA;CAEA;CACA;CAEA;CAEA;CAEA;AACD"}

package/dist/lib/neon-decision-model.d.ts.map

@@ -1 +1 @@
-{"version":3,"file":"neon-decision-model.d.ts","names":["APICallError","SharedV3Headers","SharedV3ProviderMetadata","SharedV3Warning","FetchFunction","ResponseHandler","NeonDecisionModelId","NeonDecisionInput","Record","Readonly","NeonDecisionQuestion","NeonDecisionStatePart","NeonDecisionCallOptions","AbortSignal","NeonDecisionAnswer","NeonDecisionResult","NeonDecisionModelConfig","NeonDecisionModel","state","questions","abortSignal","headers","Promise","APICallError","SharedV3Headers","SharedV3ProviderMetadata","SharedV3Warning","FetchFunction","ResponseHandler","NeonDecisionModelId","NeonDecisionInput","Readonly","Record","NeonDecisionQuestion","type","instructions","criteria","true","false","NeonDecisionStatePart","text","mediaType","data","value","NeonDecisionCallOptions","state","questions","abortSignal","AbortSignal","headers","NeonDecisionAnswer","choice","probabilities","score","probability","NeonDecisionResult","answers","rounding","probabilityDecimals","scoreDecimals","usage","inputTokens","outputTokens","warnings","providerMetadata","response","modelId","body","NeonDecisionModelConfig","provider","url","fetch","failedResponseHandler","NeonDecisionModel","specificationVersion","supportedQuestionTypes","config","constructor","doDecide","Promise"],"sources":["../../src/lib/neon-decision-model.ts"],"mappings":";;;;;;;AAqBA;AAAyC;AAMnB;AAEVQ,KARAF,mBAAAA,GAQAE,MAAAA;AAATC,KAFEF,iBAAAA,GAEFE,MAAAA,GAAAA,QAAAA,CAASD,MAATC,CAAAA,MAAAA,EAAAA,OAAAA,CAAAA,CAAAA,GAAAA,SAAAA,OAAAA,EAAAA;AAAQ,KAGCC,oBAAAA,GAHD;EAGCA,SAAAA,IAAAA,EAAAA,QAAoB;EAAA,SAAAyB,YAAA,EAGN5B,iBAHM;EAGNA,SAAAA,QAAAA,EACJE,QADIF,CAEtBC,MAFsBD,CAAAA,MAAAA,EAEPA,iBAFOA,GAAAA,IAAAA,CAAAA,CAAAA;AAEPA,CAAAA,GAAAA;EAAfC,SAAAA,IAAAA,EAAAA,OAAAA;EADkBC,SAAAA,YAAAA,EAMIF,iBANJE;EAMIF,SAAAA,QAAAA,EAAAA,SAAAA,CACMA,iBADNA,GAAAA,IAAAA,CAAAA,EAAAA;AACMA,CAAAA,GAAAA;EAINA,SAAAA,IAAAA,EAAAA,SAAAA;EAENA,SAAAA,YAAAA,EAFMA,iBAENA;EACCA,SAAAA,QAAAA,CAAAA,EAAAA;IAAiB,SAAA8B,IAAA,CAAA,EADlB9B,iBACkB,GAAA,IAAA;IAIjCI,SAAAA,KAAAA,CAAAA,EAJgBJ,iBAIK,GAAA,IAAA;EAKTK,CAAAA;AAAuB,CAAA;AACvBD,KANZA,qBAAAA,GAMYA;EACmBD,IAAAA,EAAAA,MAAAA;EAAfF,IAAAA,EAAAA,MAAAA;AAATC,CAAAA,GAAAA;EACGI,IAAAA,EAAAA,MAAAA;EACJZ,SAAAA,EAAAA,MAAAA;EAAeyC,IAAA,EAAA,OAAA;AAG1B,CAAA,GAAY5B;EAAkBoB,IAAA,EAAA,MAAA;EACuB1B,KAAAA,EAAAA,OAAAA;AACFA,CAAAA;AAAM,UATxCI,uBAAAA,CASwC;EAIxCG,KAAAA,EAAAA,SAZAJ,qBAYkB,EAAA;EAAAmC,SAAA,EAXvBrC,QAWuB,CAXdD,MAWc,CAAA,MAAA,EAXCE,oBAWD,CAAA,CAAA;EACVI,WAAAA,CAAAA,EAXVD,WAWUC;EAAfN,OAAAA,CAAAA,EAVCP,eAUDO;AAGCL;AACSD,KAXRY,kBAAAA,GAWQZ;EACsBD,IAAAA,EAAAA,QAAAA;EAAekD,MAAA,EAAA,MAAA;EAGxCnC,aAAAA,CAAAA,EAdoCR,MAcpCQ,CAAAA,MAAuB,EAAA,MAAA,CAAA;AAAA,CAAA,GAAA;EAGxBR,IAAAA,EAAAA,OAAAA;EACPJ,KAAAA,EAAAA,MAAAA;EAC+BJ,aAAAA,CAAAA,EAlBWQ,MAkBXR,CAAAA,MAAAA,EAAAA,MAAAA,CAAAA;AAAhBK,CAAAA,GAAAA;EAAe6B,IAAA,EAAA,SAAA;EAoC1BjB,WAAAA,EAAAA,MAAAA;AAAiB,CAAA,GAAA;EAGXX,IAAAA,EAAAA,SAAAA;AAGGA,CAAAA;AAA6BU,UAxDlCD,kBAAAA,CAwDkCC;EAUjDE,OAAAA,EAjEQV,MAiERU,CAAAA,MAAAA,EAjEuBJ,kBAiEvBI,CAAAA;EACAC,QAAAA,CAAAA,EAAAA;IACAC,mBAAAA,CAAAA,EAAAA,MAAAA;IACAC,aAAAA,CAAAA,EAAAA,MAAAA;EACET,CAAAA;EAAkCG,KAAAA,CAAAA,EAAAA;IAARO,WAAAA,CAAAA,EAAAA,MAAAA;IAAOwC,YAAA,CAAA,EAAA,MAAA;;YAlE1B3D;qBACSD;;;cACsBD;;;;UAGzBe,uBAAAA;;;iBAGDR;UACPJ;yBACeC,gBAAgBL;;;cAoC3BiB,iBAAAA;;;oBAGMX;;uBAGGA,6BAA6BU;;;;;;;KAc/CJ,0BAA0BU,QAAQP"}
+{"version":3,"file":"neon-decision-model.d.ts","names":["APICallError","SharedV3Headers","SharedV3ProviderMetadata","SharedV3Warning","FetchFunction","ResponseHandler","NeonDecisionModelId","NeonDecisionInput","Record","Readonly","NeonDecisionQuestion","NeonDecisionStatePart","NeonDecisionCallOptions","AbortSignal","NeonDecisionAnswer","NeonDecisionResult","NeonDecisionModelConfig","NeonDecisionModel","state","questions","abortSignal","headers","Promise","APICallError","SharedV3Headers","SharedV3ProviderMetadata","SharedV3Warning","FetchFunction","ResponseHandler","NeonDecisionModelId","NeonDecisionInput","Readonly","Record","NeonDecisionQuestion","type","instructions","criteria","true","false","NeonDecisionStatePart","text","mediaType","data","value","NeonDecisionCallOptions","state","questions","abortSignal","AbortSignal","headers","NeonDecisionAnswer","choice","probabilities","score","probability","NeonDecisionResult","answers","rounding","probabilityDecimals","scoreDecimals","usage","inputTokens","outputTokens","warnings","providerMetadata","response","modelId","body","NeonDecisionModelConfig","provider","url","fetch","failedResponseHandler","NeonDecisionModel","specificationVersion","supportedQuestionTypes","config","constructor","doDecide","Promise"],"sources":["../../src/lib/neon-decision-model.ts"],"mappings":";;;;;;;AAqBA;AAAyC;AAMnB;AAEVQ,KARAF,mBAAAA,GAQAE,MAAAA;AAATC,KAFEF,iBAAAA,GAEFE,MAAAA,GAAAA,QAAAA,CAASD,MAATC,CAAAA,MAAAA,EAAAA,OAAAA,CAAAA,CAAAA,GAAAA,SAAAA,OAAAA,EAAAA;AAAQ,KAGCC,oBAAAA,GAHD;EAGCA,SAAAA,IAAAA,EAAAA,QAAoB;EAAA,SAAAyB,YAAA,EAGN5B,iBAHM;EAGNA,SAAAA,QAAAA,EACJE,QADIF,CAEtBC,MAFsBD,CAAAA,MAAAA,EAEPA,iBAFOA,GAAAA,IAAAA,CAAAA,CAAAA;AAEPA,CAAAA,GAAAA;EAAfC,SAAAA,IAAAA,EAAAA,OAAAA;EADkBC,SAAAA,YAAAA,EAMIF,iBANJE;EAMIF,SAAAA,QAAAA,EAAAA,SAAAA,CACMA,iBADNA,GAAAA,IAAAA,CAAAA,EAAAA;AACMA,CAAAA,GAAAA;EAINA,SAAAA,IAAAA,EAAAA,SAAAA;EAENA,SAAAA,YAAAA,EAFMA,iBAENA;EACCA,SAAAA,QAAAA,CAAAA,EAAAA;IAAiB,SAAA8B,IAAA,CAAA,EADlB9B,iBACkB,GAAA,IAAA;IAIjCI,SAAAA,KAAAA,CAAAA,EAJgBJ,iBAIK,GAAA,IAAA;EAKTK,CAAAA;AAAuB,CAAA;AACvBD,KANZA,qBAAAA,GAMYA;EACmBD,IAAAA,EAAAA,MAAAA;EAAfF,IAAAA,EAAAA,MAAAA;AAATC,CAAAA,GAAAA;EACGI,IAAAA,EAAAA,MAAAA;EACJZ,SAAAA,EAAAA,MAAAA;EAAeyC,IAAA,EAAA,OAAA;AAG1B,CAAA,GAAY5B;EAAkBoB,IAAA,EAAA,MAAA;EACuB1B,KAAAA,EAAAA,OAAAA;AACFA,CAAAA;AAAM,UATxCI,uBAAAA,CASwC;EAIxCG,KAAAA,EAAAA,SAZAJ,qBAYkB,EAAA;EAAAmC,SAAA,EAXvBrC,QAWuB,CAXdD,MAWc,CAAA,MAAA,EAXCE,oBAWD,CAAA,CAAA;EACVI,WAAAA,CAAAA,EAXVD,WAWUC;EAAfN,OAAAA,CAAAA,EAVCP,eAUDO;AAGCL;AACSD,KAXRY,kBAAAA,GAWQZ;EACsBD,IAAAA,EAAAA,QAAAA;EAAekD,MAAA,EAAA,MAAA;EAGxCnC,aAAAA,CAAAA,EAdoCR,MAcpCQ,CAAAA,MAAuB,EAAA,MAAA,CAAA;AAAA,CAAA,GAAA;EAGxBR,IAAAA,EAAAA,OAAAA;EACPJ,KAAAA,EAAAA,MAAAA;EAC+BJ,aAAAA,CAAAA,EAlBWQ,MAkBXR,CAAAA,MAAAA,EAAAA,MAAAA,CAAAA;AAAhBK,CAAAA,GAAAA;EAAe6B,IAAA,EAAA,SAAA;EAoC1BjB,WAAAA,EAAAA,MAAAA;AAAiB,CAAA,GAAA;EAGXX,IAAAA,EAAAA,SAAAA;AAGGA,CAAAA;AAA6BU,UAxDlCD,kBAAAA,CAwDkCC;EAUjDE,OAAAA,EAjEQV,MAiERU,CAAAA,MAAAA,EAjEuBJ,kBAiEvBI,CAAAA;EACAC,QAAAA,CAAAA,EAAAA;IACAC,mBAAAA,CAAAA,EAAAA,MAAAA;IACAC,aAAAA,CAAAA,EAAAA,MAAAA;EACET,CAAAA;EAAkCG,KAAAA,CAAAA,EAAAA;IAARO,WAAAA,CAAAA,EAAAA,MAAAA;IAAOwC,YAAA,CAAA,EAAA,MAAA;;E,UAlE1B3D,e;E,mBACSD,wB;;;I,UACsBD,e;;;;A,UAGzBe,uBAAAA,C;;;E,eAGDR,M;E,QACPJ,a;E,uBACeC,e,CAAgBL,Y;;;A,cAoC3BiB,iBAAAA,C;;;E,kBAGMX,mB;;E,qBAGGA,mB,UAA6BU,uB;;;;;;;E,GAc/CJ,uB,GAA0BU,O,CAAQP,kB"}

package/dist/lib/neon-embedding-options.d.ts

@@ -1,6 +1,6 @@
 //#region src/lib/neon-embedding-options.d.ts
 /** Published embedding model ids from https://neon.com/models.json. */
-declare const NEON_EMBEDDING_MODEL_IDS: readonly ["gte-large-en", "qwen3-embedding-0-6b"];
+declare const NEON_EMBEDDING_MODEL_IDS: readonly ["bge-large-en", "gte-large-en", "qwen3-embedding-0-6b"];
 /**
  * A Neon AI Gateway embedding model id. Known ids are listed for autocomplete;
  * any other id is accepted via the `(string & {})` fallback.

package/dist/lib/neon-embedding-options.d.ts.map

@@ -1 +1 @@
-{"version":3,"file":"neon-embedding-options.d.ts","names":["NEON_EMBEDDING_MODEL_IDS","NeonEmbeddingModelId","NEON_MAX_EMBEDDINGS_PER_CALL","NEON_EMBEDDING_MODEL_IDS","NeonEmbeddingModelId","NEON_MAX_EMBEDDINGS_PER_CALL"],"sources":["../../src/lib/neon-embedding-options.ts"],"mappings":";;AAMaA,cAAAA,wBAGH,EAAA,SAAA,CAAA,cAAA,EAAA,sBAAA,CAAA;AAMV;AAKA;;;KALYC,oBAAAA,WACDD;;cAIEE,4BAAAA"}
+{"version":3,"file":"neon-embedding-options.d.ts","names":["NEON_EMBEDDING_MODEL_IDS","NeonEmbeddingModelId","NEON_MAX_EMBEDDINGS_PER_CALL","NEON_EMBEDDING_MODEL_IDS","NeonEmbeddingModelId","NEON_MAX_EMBEDDINGS_PER_CALL"],"sources":["../../src/lib/neon-embedding-options.ts"],"mappings":";;AAMaA,cAAAA,wBAIH,EAAA,SAAA,CAAA,cAAA,EAAA,cAAA,EAAA,sBAAA,CAAA;AAMV;AAKA;;;A,KALYC,oBAAAA,G,QACDD,wB;;A,cAIEE,4BAAAA,G"}

package/dist/lib/neon-embedding-options.js

@@ -1,6 +1,10 @@
 //#region src/lib/neon-embedding-options.ts
 /** Published embedding model ids from https://neon.com/models.json. */
-const NEON_EMBEDDING_MODEL_IDS = ["gte-large-en", "qwen3-embedding-0-6b"];
+const NEON_EMBEDDING_MODEL_IDS = [
+	"bge-large-en",
+	"gte-large-en",
+	"qwen3-embedding-0-6b"
+];
 /** The gateway rejects an embeddings request with more inputs than this. */
 const NEON_MAX_EMBEDDINGS_PER_CALL = 150;
 //#endregion

package/dist/lib/neon-embedding-options.js.map

@@ -1 +1 @@
-{"version":3,"file":"neon-embedding-options.js","names":[],"sources":["../../src/lib/neon-embedding-options.ts"],"sourcesContent":["// Embedding models served on the Neon AI Gateway's OpenAI-compatible\n// `/v1/embeddings` endpoint. Mirrors the released `\"type\": \"embedding\"` entries\n// of https://neon.com/models.json — `neon-catalog-drift.test.ts` fails if the\n// two diverge.\n\n/** Published embedding model ids from https://neon.com/models.json. */\nexport const NEON_EMBEDDING_MODEL_IDS = [\n\t\"gte-large-en\",\n\t\"qwen3-embedding-0-6b\",\n] as const;\n\n/**\n * A Neon AI Gateway embedding model id. Known ids are listed for autocomplete;\n * any other id is accepted via the `(string & {})` fallback.\n */\nexport type NeonEmbeddingModelId =\n\t| (typeof NEON_EMBEDDING_MODEL_IDS)[number]\n\t| (string & {});\n\n/** The gateway rejects an embeddings request with more inputs than this. */\nexport const NEON_MAX_EMBEDDINGS_PER_CALL = 150;\n"],"mappings":";;AAMA,MAAa,2BAA2B,CACvC,gBACA,sBACD;;AAWA,MAAa,+BAA+B"}
+{"version":3,"file":"neon-embedding-options.js","names":[],"sources":["../../src/lib/neon-embedding-options.ts"],"sourcesContent":["// Embedding models served on the Neon AI Gateway's OpenAI-compatible\n// `/v1/embeddings` endpoint. Mirrors the released `\"type\": \"embedding\"` entries\n// of https://neon.com/models.json — `neon-catalog-drift.test.ts` fails if the\n// two diverge.\n\n/** Published embedding model ids from https://neon.com/models.json. */\nexport const NEON_EMBEDDING_MODEL_IDS = [\n\t\"bge-large-en\",\n\t\"gte-large-en\",\n\t\"qwen3-embedding-0-6b\",\n] as const;\n\n/**\n * A Neon AI Gateway embedding model id. Known ids are listed for autocomplete;\n * any other id is accepted via the `(string & {})` fallback.\n */\nexport type NeonEmbeddingModelId =\n\t| (typeof NEON_EMBEDDING_MODEL_IDS)[number]\n\t| (string & {});\n\n/** The gateway rejects an embeddings request with more inputs than this. */\nexport const NEON_MAX_EMBEDDINGS_PER_CALL = 150;\n"],"mappings":";;AAMA,MAAa,2BAA2B;CACvC;CACA;CACA;AACD;;AAWA,MAAa,+BAA+B"}

package/dist/lib/neon-gateway-error.d.ts.map

@@ -1 +1 @@
-{"version":3,"file":"neon-gateway-error.d.ts","names":["FetchFunction","GatewayErrorDialect","normalizeGatewayErrorBody","wrapFetchWithGatewayErrorNormalization","FetchFunction","GatewayErrorDialect","normalizeGatewayErrorBody","body","dialect","wrapFetchWithGatewayErrorNormalization","baseFetch"],"sources":["../../src/lib/neon-gateway-error.ts"],"mappings":";;;;;;AA4CA;AAqHA;AAiBA;AAAsD;AAC1CA;AACFC;AACPD;AAAa;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;KAzIJC,mBAAAA;;;;;iBAqHIC,yBAAAA,yBAEND;;iBAeME,sCAAAA,YACJH,oCACFC,sBACPD"}
+{"version":3,"file":"neon-gateway-error.d.ts","names":["FetchFunction","GatewayErrorDialect","normalizeGatewayErrorBody","wrapFetchWithGatewayErrorNormalization","FetchFunction","GatewayErrorDialect","normalizeGatewayErrorBody","body","dialect","wrapFetchWithGatewayErrorNormalization","baseFetch"],"sources":["../../src/lib/neon-gateway-error.ts"],"mappings":";;;;;;AA4CA;AAqHA;AAiBA;AAAsD;AAC1CA;AACFC;AACPD;AAAa;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;A,KAzIJC,mBAAAA,G;;;;;A,iBAqHIC,yBAAAA,C,wBAEND,mB;;A,iBAeME,sCAAAA,C,WACJH,a,uBACFC,mB,GACPD,a"}

package/dist/lib/neon-harmony-normalize.d.ts.map

@@ -1 +1 @@
-{"version":3,"file":"neon-harmony-normalize.d.ts","names":["FetchFunction","ExtractedHarmony","NormalizeResult","extractHarmonyContent","normalizeCompletionBody","normalizeChunkBody","wrapFetchWithHarmonyNormalization","FetchFunction","ExtractedHarmony","text","reasoning","NormalizeResult","body","changed","extractHarmonyContent","content","normalizeCompletionBody","normalizeChunkBody","wrapFetchWithHarmonyNormalization","baseFetch"],"sources":["../../src/lib/neon-harmony-normalize.ts"],"mappings":";;;UAwCUC,gBAAAA;;EAAAA,SAAAA,EAAAA,MAAAA;AAAgB;AAgB1B;AAkDA,UA5DUC,eAAAA,CA4DME;EAkCAC,IAAAA,EAAAA,OAAAA;EAuGAC,OAAAA,EAAAA,OAAAA;AAAiC;AACpCN;AACVA;AAAa;;;iBA7LAG,qBAAAA,oBAEbF;;;;;iBAgDaG,uBAAAA,iBAAwCF;;;;;iBAkCxCG,kBAAAA,iBAAmCH;;;;;;;;;;iBAuGnCI,iCAAAA,aACHN,gBACVA"}
+{"version":3,"file":"neon-harmony-normalize.d.ts","names":["FetchFunction","ExtractedHarmony","NormalizeResult","extractHarmonyContent","normalizeCompletionBody","normalizeChunkBody","wrapFetchWithHarmonyNormalization","FetchFunction","ExtractedHarmony","text","reasoning","NormalizeResult","body","changed","extractHarmonyContent","content","normalizeCompletionBody","normalizeChunkBody","wrapFetchWithHarmonyNormalization","baseFetch"],"sources":["../../src/lib/neon-harmony-normalize.ts"],"mappings":";;;A,UAwCUC,gBAAAA,C;;EAAAA,SAAAA,EAAAA,MAAAA;AAAgB;AAgB1B;AAkDA,UA5DUC,eAAAA,CA4DME;EAkCAC,IAAAA,EAAAA,OAAAA;EAuGAC,OAAAA,EAAAA,OAAAA;AAAiC;AACpCN;AACVA;AAAa;;;A,iBA7LAG,qBAAAA,C,mBAEbF,gB;;;;;A,iBAgDaG,uBAAAA,C,gBAAwCF,e;;;;;A,iBAkCxCG,kBAAAA,C,gBAAmCH,e;;;;;;;;;;A,iBAuGnCI,iCAAAA,C,YACHN,a,GACVA,a"}

package/dist/lib/neon-model-capabilities.d.ts.map

@@ -1 +1 @@
-{"version":3,"file":"neon-model-capabilities.d.ts","names":["NeonModelFamily","NeonModelRoute","getNeonModelRoute","NeonModelCapabilities","getNeonModelCapabilities","NeonModelFamily","NeonModelRoute","getNeonModelRoute","modelId","NeonModelCapabilities","family","supportsTemperature","supportsTopP","temperatureTopPMutuallyExclusive","supportsPenalties","supportsSeed","supportsStopSequences","supportsReasoningEffort","claudeSamplingUnrecognized","getNeonModelCapabilities"],"sources":["../../src/lib/neon-model-capabilities.ts"],"mappings":";KAAYA,eAAAA;AAAZ;AAiBA;AAEA;AAiBA;AAiGA;;;;;;KApHYC,cAAAA;iBAEIC,iBAAAA,mBAAoCD;UAiBnCE,qBAAAA;UACRH;;;;;;;;;;;;;;;;;;;;;;;;;;;;;iBAgGOI,wBAAAA,mBAEbD"}
+{"version":3,"file":"neon-model-capabilities.d.ts","names":["NeonModelFamily","NeonModelRoute","getNeonModelRoute","NeonModelCapabilities","getNeonModelCapabilities","NeonModelFamily","NeonModelRoute","getNeonModelRoute","modelId","NeonModelCapabilities","family","supportsTemperature","supportsTopP","temperatureTopPMutuallyExclusive","supportsPenalties","supportsSeed","supportsStopSequences","supportsReasoningEffort","claudeSamplingUnrecognized","getNeonModelCapabilities"],"sources":["../../src/lib/neon-model-capabilities.ts"],"mappings":";A,KAAYA,eAAAA,G;AAAZ;AAiBA;AAEA;AAiBA;AAoIA;;;;;;A,KAvJYC,cAAAA,G;A,iBAEIC,iBAAAA,C,kBAAoCD,c;A,UAiBnCE,qBAAAA,C;E,QACRH,e;;;;;;;;;;;;;;;;;;;;;;;;;;;;;A,iBAmIOI,wBAAAA,C,kBAEbD,qB"}

package/dist/lib/neon-model-capabilities.js

@@ -14,17 +14,54 @@ function getNeonModelRoute(modelId) {
 * restriction on the strength of a shared prefix is how the Gemini rule was
 * wrong for these two in the first place.
 */
-const GEMINI_NO_PENALTIES = /* @__PURE__ */ new Set(["gemini-3-5-flash-lite", "gemini-3-6-flash"]);
+const GEMINI_NO_PENALTIES = /* @__PURE__ */ new Set([
+	"gemini-3-5-flash-lite",
+	"gemini-3-6-flash",
+	"gemini-3-7-flash",
+	"gemini-3-8-flash",
+	"gemini-4-argon"
+]);
 /** Gemini models that reject `temperature` and `topP` outright. */
-const GEMINI_NO_SAMPLING = /* @__PURE__ */ new Set(["gemini-3-6-flash"]);
+const GEMINI_NO_SAMPLING = /* @__PURE__ */ new Set([
+	"gemini-3-6-flash",
+	"gemini-3-7-flash",
+	"gemini-3-8-flash",
+	"gemini-4-argon"
+]);
 /**
 * GPT-5 ids that reject `temperature` despite carrying a minor version.
 *
 * The version rule below reads `gpt-5-5-pro` as 5.5 and concludes it takes
 * sampling parameters. It does not — the Responses API answers
-* `Unsupported parameter: temperature`.
+* `Unsupported parameter: temperature`. Measured the same for `top_p`, and for
+* gpt-5.5 and the gpt-5.6 family at their default reasoning effort.
+*
+* The Responses API accepts `temperature` and `top_p` only when reasoning effort
+* is `none`, so these values describe each model's default effort. gpt-5.1
+* through gpt-5.4 default to `none` and accept both; with effort `low` they
+* reject them too. gpt-5.5 and gpt-5.6 accept both when effort is `none`.
+*/
+const GPT5_NO_SAMPLING = /* @__PURE__ */ new Set([
+	"gpt-5-5",
+	"gpt-5-5-pro",
+	"gpt-5-6-luna",
+	"gpt-5-6-sol",
+	"gpt-5-6-terra"
+]);
+/**
+* GPT-6 ids that reject `temperature` and `top_p` on the Responses API at their
+* default reasoning effort
+* (`Unsupported parameter: 'temperature' is not supported with this model`).
+* gpt-6-sol and gpt-6-luna accept both when effort is `none`; gpt-6-astra and
+* gpt-6-1-sol reject effort `none`, so they never accept them.
+* Exact ids: a future gpt-6-* is unmeasured.
 */
-const GPT5_NO_SAMPLING = /* @__PURE__ */ new Set(["gpt-5-5-pro"]);
+const GPT6_NO_SAMPLING = /* @__PURE__ */ new Set([
+	"gpt-6-1-sol",
+	"gpt-6-astra",
+	"gpt-6-luna",
+	"gpt-6-sol"
+]);
 /**
 * The gateway accepts an optional `databricks-` prefix on any id, so strip it
 * before an exact-match lookup. Prefix rules elsewhere in this file tolerate it
@@ -106,10 +143,10 @@ function getNeonModelCapabilities(modelId) {
 			supportsReasoningEffort: true
 		};
 	}
-	if (canonicalId(id) === "gpt-6-astra") return {
+	if (GPT6_NO_SAMPLING.has(canonicalId(id))) return {
 		family: "openai",
 		supportsTemperature: false,
-		supportsTopP: true,
+		supportsTopP: false,
 		temperatureTopPMutuallyExclusive: false,
 		supportsPenalties: true,
 		supportsSeed: true,
@@ -139,7 +176,7 @@ function getNeonModelCapabilities(modelId) {
 		supportsPenalties: false,
 		supportsSeed: false
 	};
-	if (id.includes("glm") || id.includes("inkling") || id.includes("kimi")) return {
+	if (id.includes("glm") || id.includes("inkling") || id.includes("kimi") || id.includes("grok") || id.includes("deepseek")) return {
 		family: "other",
 		...PERMISSIVE,
 		supportsPenalties: false

package/dist/lib/neon-model-capabilities.js.map

@@ -1 +1 @@
-{"version":3,"file":"neon-model-capabilities.js","names":[],"sources":["../../src/lib/neon-model-capabilities.ts"],"sourcesContent":["export type NeonModelFamily =\n\t| \"anthropic\"\n\t| \"google\"\n\t| \"openai\"\n\t| \"meta\"\n\t| \"other\";\n\n/**\n * Which gateway endpoint a model should be routed to.\n *\n * - `anthropic`: native Messages API — streaming structured output + native reasoning.\n * - `openai`: native Responses API — models served only natively (e.g. Codex),\n *   native reasoning, and the image-generation tool.\n * - `mlflow`: the unified, OpenAI-compatible endpoint (the fallback). Gemini is\n *   routed here because the gateway's native Gemini endpoint does not support\n *   streaming (`streamGenerateContent` is rejected).\n */\nexport type NeonModelRoute = \"anthropic\" | \"openai\" | \"mlflow\";\n\nexport function getNeonModelRoute(modelId: string): NeonModelRoute {\n\tconst id = modelId.toLowerCase();\n\tif (id.includes(\"claude\")) {\n\t\treturn \"anthropic\";\n\t}\n\t// OpenAI proprietary models (gpt-4/gpt-5 families, Codex) are served only via\n\t// the native Responses API. `gpt-oss` is open-weight and served on the\n\t// unified chat endpoint, so it is intentionally excluded here.\n\tif (\n\t\t(id.includes(\"gpt-\") && !id.includes(\"gpt-oss\")) ||\n\t\tid.includes(\"codex\")\n\t) {\n\t\treturn \"openai\";\n\t}\n\treturn \"mlflow\";\n}\n\nexport interface NeonModelCapabilities {\n\tfamily: NeonModelFamily;\n\tsupportsTemperature: boolean;\n\tsupportsTopP: boolean;\n\t/**\n\t * Whether `temperature` and `topP` may be sent together. Anthropic models\n\t * accept only one of the two.\n\t */\n\ttemperatureTopPMutuallyExclusive: boolean;\n\tsupportsPenalties: boolean;\n\tsupportsSeed: boolean;\n\tsupportsStopSequences: boolean;\n\tsupportsReasoningEffort: boolean;\n\t/**\n\t * True when a `claude-*` id could not be parsed into a version and was\n\t * assumed to be new. The sampling restriction is then a precaution rather\n\t * than something measured, and the warning says so instead of asserting a\n\t * capability nobody checked.\n\t */\n\tclaudeSamplingUnrecognized?: boolean;\n}\n\n/**\n * Gemini models the gateway rejects penalties on, by measurement. Their older\n * siblings accept them, so this cannot be derived from the id.\n *\n * Matched exactly rather than by substring: `gemini-3-6-flash` is a prefix of\n * any `gemini-3-6-flash-*` id Google may ship next, and inheriting a measured\n * restriction on the strength of a shared prefix is how the Gemini rule was\n * wrong for these two in the first place.\n */\nconst GEMINI_NO_PENALTIES = new Set([\n\t\"gemini-3-5-flash-lite\",\n\t\"gemini-3-6-flash\",\n]);\n\n/** Gemini models that reject `temperature` and `topP` outright. */\nconst GEMINI_NO_SAMPLING = new Set([\"gemini-3-6-flash\"]);\n\n/**\n * GPT-5 ids that reject `temperature` despite carrying a minor version.\n *\n * The version rule below reads `gpt-5-5-pro` as 5.5 and concludes it takes\n * sampling parameters. It does not — the Responses API answers\n * `Unsupported parameter: temperature`.\n */\nconst GPT5_NO_SAMPLING = new Set([\"gpt-5-5-pro\"]);\n\n/**\n * The gateway accepts an optional `databricks-` prefix on any id, so strip it\n * before an exact-match lookup. Prefix rules elsewhere in this file tolerate it\n * incidentally; exact matches do not.\n */\nfunction canonicalId(id: string): string {\n\treturn id.startsWith(\"databricks-\") ? id.slice(\"databricks-\".length) : id;\n}\n\nconst PERMISSIVE: Omit<NeonModelCapabilities, \"family\"> = {\n\tsupportsTemperature: true,\n\tsupportsTopP: true,\n\ttemperatureTopPMutuallyExclusive: false,\n\tsupportsPenalties: true,\n\tsupportsSeed: true,\n\tsupportsStopSequences: true,\n\tsupportsReasoningEffort: true,\n};\n\n/**\n * Whether a Claude id predates the 4.7 cutoff where the gateway stopped\n * accepting `temperature` and `top_p`. Ids look like `claude-<tier>-<major>` or\n * `claude-<tier>-<major>-<minor>`, optionally behind the legacy `databricks-`\n * prefix. An id we cannot parse is treated as new, which is the safe direction.\n */\nfunction claudeVersion(id: string): { major: number; minor: number } | null {\n\t// Anchored: `claude-opus-4-beta` and `claude-opus-4.7` must not match their\n\t// leading digits and be read as old models. A dated id such as\n\t// `claude-3-5-sonnet-20241022` does not parse either, and is reported as\n\t// unrecognised rather than silently classified.\n\tconst match = /^(?:databricks-)?claude-[a-z]+-(\\d+)(?:-(\\d+))?$/.exec(id);\n\tif (!match) {\n\t\treturn null;\n\t}\n\treturn {\n\t\tmajor: Number(match[1]),\n\t\tminor: match[2] === undefined ? 0 : Number(match[2]),\n\t};\n}\n\n/**\n * Heuristic, prefix-based capability detection for MLflow-routed Neon models.\n *\n * The unified endpoint proxies to heterogeneous upstream providers, each of\n * which accepts a different subset of the OpenAI-style parameters the AI SDK\n * emits. Sending a parameter an upstream rejects results in a hard `400`, so we\n * strip the parameters a family is known to reject and surface a warning\n * instead. Unknown/untested models stay permissive (passed through unchanged).\n */\nexport function getNeonModelCapabilities(\n\tmodelId: string,\n): NeonModelCapabilities {\n\tconst id = modelId.toLowerCase();\n\n\t// Anthropic (Claude): rejects penalties and seed, accepts only one of\n\t// temperature/topP, and rejects the OpenAI `reasoning_effort` field.\n\t//\n\t// From Claude 4.7 onward the gateway also rejects non-default sampling\n\t// entirely — `does not support the temperature parameter` /\n\t// `does not support sampling parameters: top_p` — because those models are\n\t// steered with `output_config.effort` instead. Measured: 4.1/4.5/4.6 accept\n\t// both, 4.7/4.8/5 reject both, and every id accepts the default\n\t// `temperature: 1.0`. A version comparison rather than a list of ids, so a\n\t// future Claude inherits the restriction: dropping a parameter the model\n\t// would have accepted costs a warning, claiming one it rejects costs a 400.\n\tif (id.includes(\"claude\")) {\n\t\tconst version = claudeVersion(id);\n\t\tconst sampling =\n\t\t\tversion !== null &&\n\t\t\t(version.major < 4 || (version.major === 4 && version.minor <= 6));\n\t\treturn {\n\t\t\tfamily: \"anthropic\",\n\t\t\tsupportsTemperature: sampling,\n\t\t\tsupportsTopP: sampling,\n\t\t\ttemperatureTopPMutuallyExclusive: true,\n\t\t\tsupportsPenalties: false,\n\t\t\tsupportsSeed: false,\n\t\t\tsupportsStopSequences: true,\n\t\t\tsupportsReasoningEffort: false,\n\t\t\t...(version === null ? { claudeSamplingUnrecognized: true } : {}),\n\t\t};\n\t}\n\n\t// Google (Gemini): accepts standard sampling params, and does take\n\t// `reasoning_effort` — the gateway maps it onto Gemini's thinking config.\n\t// Measured on gemini-3-6-flash: `minimal` produces 0 reasoning tokens and\n\t// `high` produces 310, against 130 with the field absent.\n\t//\n\t// Newer Gemini models are stricter, and not in a way the id predicts: the\n\t// gateway rejects penalties on `gemini-3-5-flash-lite` while accepting them\n\t// on `gemini-3-1-flash-lite`, so neither the version nor the `-lite` suffix\n\t// is the rule. `gemini-3-6-flash` refuses temperature and topP outright\n\t// (\"does not support the temperature parameter\"). Both are listed by id\n\t// because that is what was measured; a new Gemini model inherits the\n\t// permissive default until someone measures it.\n\tif (id.includes(\"gemini\")) {\n\t\tconst canonical = canonicalId(id);\n\t\tconst acceptsSampling = !GEMINI_NO_SAMPLING.has(canonical);\n\t\treturn {\n\t\t\tfamily: \"google\",\n\t\t\t...PERMISSIVE,\n\t\t\tsupportsTemperature: acceptsSampling,\n\t\t\tsupportsTopP: acceptsSampling,\n\t\t\tsupportsPenalties: !GEMINI_NO_PENALTIES.has(canonical),\n\t\t};\n\t}\n\n\t// OpenAI GPT-5 reasoning family (routed to the native Responses API). The\n\t// Responses model strips parameters the Responses API doesn't accept\n\t// (penalties, seed, stop), but its reasoning-model detection matches the bare\n\t// model id (`gpt-5`), which the gateway's optional `databricks-` prefix can\n\t// defeat. So we only handle the temperature/topP restriction here: the\n\t// original gpt-5 / gpt-5-mini / gpt-5-nano require the default temperature and\n\t// reject topP, while gpt-5.1+ (a minor version digit follows) accept them\n\t// again. The regex matches both prefixed and unprefixed ids.\n\tif (/gpt-5/.test(id)) {\n\t\tconst hasMinorVersion =\n\t\t\t/gpt-5[.-]\\d/.test(id) && !GPT5_NO_SAMPLING.has(canonicalId(id));\n\t\treturn {\n\t\t\tfamily: \"openai\",\n\t\t\tsupportsTemperature: hasMinorVersion,\n\t\t\tsupportsTopP: hasMinorVersion,\n\t\t\ttemperatureTopPMutuallyExclusive: false,\n\t\t\tsupportsPenalties: true,\n\t\t\tsupportsSeed: true,\n\t\t\tsupportsStopSequences: true,\n\t\t\tsupportsReasoningEffort: true,\n\t\t};\n\t}\n\n\t// Catalog `temperature: false` on gpt-6-astra; the gpt-5 minor-version rule\n\t// does not match gpt-6. Exact id: a future gpt-6-* is unmeasured.\n\tif (canonicalId(id) === \"gpt-6-astra\") {\n\t\treturn {\n\t\t\tfamily: \"openai\",\n\t\t\tsupportsTemperature: false,\n\t\t\tsupportsTopP: true,\n\t\t\ttemperatureTopPMutuallyExclusive: false,\n\t\t\tsupportsPenalties: true,\n\t\t\tsupportsSeed: true,\n\t\t\tsupportsStopSequences: true,\n\t\t\tsupportsReasoningEffort: true,\n\t\t};\n\t}\n\n\t// Meta (Llama): rejects penalties and seed; accepts sampling params and stop.\n\tif (id.includes(\"llama\")) {\n\t\treturn {\n\t\t\tfamily: \"meta\",\n\t\t\tsupportsTemperature: true,\n\t\t\tsupportsTopP: true,\n\t\t\ttemperatureTopPMutuallyExclusive: false,\n\t\t\tsupportsPenalties: false,\n\t\t\tsupportsSeed: false,\n\t\t\tsupportsStopSequences: true,\n\t\t\tsupportsReasoningEffort: true,\n\t\t};\n\t}\n\n\t// Everything else on the unified endpoint rejects penalties with\n\t// `parameter \"frequency_penalty\" must be equal to 0`. Only the older Gemini\n\t// models, handled above, accept them. Seed and stop vary, so each family\n\t// carries what was measured rather than inheriting a guess.\n\tif (id.includes(\"gpt-oss\")) {\n\t\treturn {\n\t\t\tfamily: \"other\",\n\t\t\t...PERMISSIVE,\n\t\t\tsupportsPenalties: false,\n\t\t\tsupportsSeed: false,\n\t\t\tsupportsStopSequences: false,\n\t\t};\n\t}\n\n\tif (id.includes(\"qwen\") || id.includes(\"gemma\")) {\n\t\treturn {\n\t\t\tfamily: \"other\",\n\t\t\t...PERMISSIVE,\n\t\t\tsupportsPenalties: false,\n\t\t\tsupportsSeed: false,\n\t\t};\n\t}\n\n\tif (id.includes(\"glm\") || id.includes(\"inkling\") || id.includes(\"kimi\")) {\n\t\treturn { family: \"other\", ...PERMISSIVE, supportsPenalties: false };\n\t}\n\n\treturn { family: \"other\", ...PERMISSIVE };\n}\n"],"mappings":";AAmBA,SAAgB,kBAAkB,SAAiC;CAClE,MAAM,KAAK,QAAQ,YAAY;CAC/B,IAAI,GAAG,SAAS,QAAQ,GACvB,OAAO;CAKR,IACE,GAAG,SAAS,MAAM,KAAK,CAAC,GAAG,SAAS,SAAS,KAC9C,GAAG,SAAS,OAAO,GAEnB,OAAO;CAER,OAAO;AACR;;;;;;;;;;AAiCA,MAAM,sCAAsB,IAAI,IAAI,CACnC,yBACA,kBACD,CAAC;;AAGD,MAAM,qCAAqB,IAAI,IAAI,CAAC,kBAAkB,CAAC;;;;;;;;AASvD,MAAM,mCAAmB,IAAI,IAAI,CAAC,aAAa,CAAC;;;;;;AAOhD,SAAS,YAAY,IAAoB;CACxC,OAAO,GAAG,WAAW,aAAa,IAAI,GAAG,MAAM,EAAoB,IAAI;AACxE;AAEA,MAAM,aAAoD;CACzD,qBAAqB;CACrB,cAAc;CACd,kCAAkC;CAClC,mBAAmB;CACnB,cAAc;CACd,uBAAuB;CACvB,yBAAyB;AAC1B;;;;;;;AAQA,SAAS,cAAc,IAAqD;CAK3E,MAAM,QAAQ,mDAAmD,KAAK,EAAE;CACxE,IAAI,CAAC,OACJ,OAAO;CAER,OAAO;EACN,OAAO,OAAO,MAAM,EAAE;EACtB,OAAO,MAAM,OAAO,KAAA,IAAY,IAAI,OAAO,MAAM,EAAE;CACpD;AACD;;;;;;;;;;AAWA,SAAgB,yBACf,SACwB;CACxB,MAAM,KAAK,QAAQ,YAAY;CAa/B,IAAI,GAAG,SAAS,QAAQ,GAAG;EAC1B,MAAM,UAAU,cAAc,EAAE;EAChC,MAAM,WACL,YAAY,SACX,QAAQ,QAAQ,KAAM,QAAQ,UAAU,KAAK,QAAQ,SAAS;EAChE,OAAO;GACN,QAAQ;GACR,qBAAqB;GACrB,cAAc;GACd,kCAAkC;GAClC,mBAAmB;GACnB,cAAc;GACd,uBAAuB;GACvB,yBAAyB;GACzB,GAAI,YAAY,OAAO,EAAE,4BAA4B,KAAK,IAAI,CAAC;EAChE;CACD;CAcA,IAAI,GAAG,SAAS,QAAQ,GAAG;EAC1B,MAAM,YAAY,YAAY,EAAE;EAChC,MAAM,kBAAkB,CAAC,mBAAmB,IAAI,SAAS;EACzD,OAAO;GACN,QAAQ;GACR,GAAG;GACH,qBAAqB;GACrB,cAAc;GACd,mBAAmB,CAAC,oBAAoB,IAAI,SAAS;EACtD;CACD;CAUA,IAAI,QAAQ,KAAK,EAAE,GAAG;EACrB,MAAM,kBACL,cAAc,KAAK,EAAE,KAAK,CAAC,iBAAiB,IAAI,YAAY,EAAE,CAAC;EAChE,OAAO;GACN,QAAQ;GACR,qBAAqB;GACrB,cAAc;GACd,kCAAkC;GAClC,mBAAmB;GACnB,cAAc;GACd,uBAAuB;GACvB,yBAAyB;EAC1B;CACD;CAIA,IAAI,YAAY,EAAE,MAAM,eACvB,OAAO;EACN,QAAQ;EACR,qBAAqB;EACrB,cAAc;EACd,kCAAkC;EAClC,mBAAmB;EACnB,cAAc;EACd,uBAAuB;EACvB,yBAAyB;CAC1B;CAID,IAAI,GAAG,SAAS,OAAO,GACtB,OAAO;EACN,QAAQ;EACR,qBAAqB;EACrB,cAAc;EACd,kCAAkC;EAClC,mBAAmB;EACnB,cAAc;EACd,uBAAuB;EACvB,yBAAyB;CAC1B;CAOD,IAAI,GAAG,SAAS,SAAS,GACxB,OAAO;EACN,QAAQ;EACR,GAAG;EACH,mBAAmB;EACnB,cAAc;EACd,uBAAuB;CACxB;CAGD,IAAI,GAAG,SAAS,MAAM,KAAK,GAAG,SAAS,OAAO,GAC7C,OAAO;EACN,QAAQ;EACR,GAAG;EACH,mBAAmB;EACnB,cAAc;CACf;CAGD,IAAI,GAAG,SAAS,KAAK,KAAK,GAAG,SAAS,SAAS,KAAK,GAAG,SAAS,MAAM,GACrE,OAAO;EAAE,QAAQ;EAAS,GAAG;EAAY,mBAAmB;CAAM;CAGnE,OAAO;EAAE,QAAQ;EAAS,GAAG;CAAW;AACzC"}
+{"version":3,"file":"neon-model-capabilities.js","names":[],"sources":["../../src/lib/neon-model-capabilities.ts"],"sourcesContent":["export type NeonModelFamily =\n\t| \"anthropic\"\n\t| \"google\"\n\t| \"openai\"\n\t| \"meta\"\n\t| \"other\";\n\n/**\n * Which gateway endpoint a model should be routed to.\n *\n * - `anthropic`: native Messages API — streaming structured output + native reasoning.\n * - `openai`: native Responses API — models served only natively (e.g. Codex),\n *   native reasoning, and the image-generation tool.\n * - `mlflow`: the unified, OpenAI-compatible endpoint (the fallback). Gemini is\n *   routed here because the gateway's native Gemini endpoint does not support\n *   streaming (`streamGenerateContent` is rejected).\n */\nexport type NeonModelRoute = \"anthropic\" | \"openai\" | \"mlflow\";\n\nexport function getNeonModelRoute(modelId: string): NeonModelRoute {\n\tconst id = modelId.toLowerCase();\n\tif (id.includes(\"claude\")) {\n\t\treturn \"anthropic\";\n\t}\n\t// OpenAI proprietary models (gpt-4/gpt-5 families, Codex) are served only via\n\t// the native Responses API. `gpt-oss` is open-weight and served on the\n\t// unified chat endpoint, so it is intentionally excluded here.\n\tif (\n\t\t(id.includes(\"gpt-\") && !id.includes(\"gpt-oss\")) ||\n\t\tid.includes(\"codex\")\n\t) {\n\t\treturn \"openai\";\n\t}\n\treturn \"mlflow\";\n}\n\nexport interface NeonModelCapabilities {\n\tfamily: NeonModelFamily;\n\tsupportsTemperature: boolean;\n\tsupportsTopP: boolean;\n\t/**\n\t * Whether `temperature` and `topP` may be sent together. Anthropic models\n\t * accept only one of the two.\n\t */\n\ttemperatureTopPMutuallyExclusive: boolean;\n\tsupportsPenalties: boolean;\n\tsupportsSeed: boolean;\n\tsupportsStopSequences: boolean;\n\tsupportsReasoningEffort: boolean;\n\t/**\n\t * True when a `claude-*` id could not be parsed into a version and was\n\t * assumed to be new. The sampling restriction is then a precaution rather\n\t * than something measured, and the warning says so instead of asserting a\n\t * capability nobody checked.\n\t */\n\tclaudeSamplingUnrecognized?: boolean;\n}\n\n/**\n * Gemini models the gateway rejects penalties on, by measurement. Their older\n * siblings accept them, so this cannot be derived from the id.\n *\n * Matched exactly rather than by substring: `gemini-3-6-flash` is a prefix of\n * any `gemini-3-6-flash-*` id Google may ship next, and inheriting a measured\n * restriction on the strength of a shared prefix is how the Gemini rule was\n * wrong for these two in the first place.\n */\nconst GEMINI_NO_PENALTIES = new Set([\n\t\"gemini-3-5-flash-lite\",\n\t\"gemini-3-6-flash\",\n\t\"gemini-3-7-flash\",\n\t\"gemini-3-8-flash\",\n\t\"gemini-4-argon\",\n]);\n\n/** Gemini models that reject `temperature` and `topP` outright. */\nconst GEMINI_NO_SAMPLING = new Set([\n\t\"gemini-3-6-flash\",\n\t\"gemini-3-7-flash\",\n\t\"gemini-3-8-flash\",\n\t\"gemini-4-argon\",\n]);\n\n/**\n * GPT-5 ids that reject `temperature` despite carrying a minor version.\n *\n * The version rule below reads `gpt-5-5-pro` as 5.5 and concludes it takes\n * sampling parameters. It does not — the Responses API answers\n * `Unsupported parameter: temperature`. Measured the same for `top_p`, and for\n * gpt-5.5 and the gpt-5.6 family at their default reasoning effort.\n *\n * The Responses API accepts `temperature` and `top_p` only when reasoning effort\n * is `none`, so these values describe each model's default effort. gpt-5.1\n * through gpt-5.4 default to `none` and accept both; with effort `low` they\n * reject them too. gpt-5.5 and gpt-5.6 accept both when effort is `none`.\n */\nconst GPT5_NO_SAMPLING = new Set([\n\t\"gpt-5-5\",\n\t\"gpt-5-5-pro\",\n\t\"gpt-5-6-luna\",\n\t\"gpt-5-6-sol\",\n\t\"gpt-5-6-terra\",\n]);\n\n/**\n * GPT-6 ids that reject `temperature` and `top_p` on the Responses API at their\n * default reasoning effort\n * (`Unsupported parameter: 'temperature' is not supported with this model`).\n * gpt-6-sol and gpt-6-luna accept both when effort is `none`; gpt-6-astra and\n * gpt-6-1-sol reject effort `none`, so they never accept them.\n * Exact ids: a future gpt-6-* is unmeasured.\n */\nconst GPT6_NO_SAMPLING = new Set([\n\t\"gpt-6-1-sol\",\n\t\"gpt-6-astra\",\n\t\"gpt-6-luna\",\n\t\"gpt-6-sol\",\n]);\n\n/**\n * The gateway accepts an optional `databricks-` prefix on any id, so strip it\n * before an exact-match lookup. Prefix rules elsewhere in this file tolerate it\n * incidentally; exact matches do not.\n */\nfunction canonicalId(id: string): string {\n\treturn id.startsWith(\"databricks-\") ? id.slice(\"databricks-\".length) : id;\n}\n\nconst PERMISSIVE: Omit<NeonModelCapabilities, \"family\"> = {\n\tsupportsTemperature: true,\n\tsupportsTopP: true,\n\ttemperatureTopPMutuallyExclusive: false,\n\tsupportsPenalties: true,\n\tsupportsSeed: true,\n\tsupportsStopSequences: true,\n\tsupportsReasoningEffort: true,\n};\n\n/**\n * Whether a Claude id predates the 4.7 cutoff where the gateway stopped\n * accepting `temperature` and `top_p`. Ids look like `claude-<tier>-<major>` or\n * `claude-<tier>-<major>-<minor>`, optionally behind the legacy `databricks-`\n * prefix. An id we cannot parse is treated as new, which is the safe direction.\n */\nfunction claudeVersion(id: string): { major: number; minor: number } | null {\n\t// Anchored: `claude-opus-4-beta` and `claude-opus-4.7` must not match their\n\t// leading digits and be read as old models. A dated id such as\n\t// `claude-3-5-sonnet-20241022` does not parse either, and is reported as\n\t// unrecognised rather than silently classified.\n\tconst match = /^(?:databricks-)?claude-[a-z]+-(\\d+)(?:-(\\d+))?$/.exec(id);\n\tif (!match) {\n\t\treturn null;\n\t}\n\treturn {\n\t\tmajor: Number(match[1]),\n\t\tminor: match[2] === undefined ? 0 : Number(match[2]),\n\t};\n}\n\n/**\n * Heuristic, prefix-based capability detection for MLflow-routed Neon models.\n *\n * The unified endpoint proxies to heterogeneous upstream providers, each of\n * which accepts a different subset of the OpenAI-style parameters the AI SDK\n * emits. Sending a parameter an upstream rejects results in a hard `400`, so we\n * strip the parameters a family is known to reject and surface a warning\n * instead. Unknown/untested models stay permissive (passed through unchanged).\n */\nexport function getNeonModelCapabilities(\n\tmodelId: string,\n): NeonModelCapabilities {\n\tconst id = modelId.toLowerCase();\n\n\t// Anthropic (Claude): rejects penalties and seed, accepts only one of\n\t// temperature/topP, and rejects the OpenAI `reasoning_effort` field.\n\t//\n\t// From Claude 4.7 onward the gateway also rejects non-default sampling\n\t// entirely — `does not support the temperature parameter` /\n\t// `does not support sampling parameters: top_p` — because those models are\n\t// steered with `output_config.effort` instead. Measured: 4.1/4.5/4.6 accept\n\t// both, 4.7/4.8/5 reject both, and every id accepts the default\n\t// `temperature: 1.0`. A version comparison rather than a list of ids, so a\n\t// future Claude inherits the restriction: dropping a parameter the model\n\t// would have accepted costs a warning, claiming one it rejects costs a 400.\n\tif (id.includes(\"claude\")) {\n\t\tconst version = claudeVersion(id);\n\t\tconst sampling =\n\t\t\tversion !== null &&\n\t\t\t(version.major < 4 || (version.major === 4 && version.minor <= 6));\n\t\treturn {\n\t\t\tfamily: \"anthropic\",\n\t\t\tsupportsTemperature: sampling,\n\t\t\tsupportsTopP: sampling,\n\t\t\ttemperatureTopPMutuallyExclusive: true,\n\t\t\tsupportsPenalties: false,\n\t\t\tsupportsSeed: false,\n\t\t\tsupportsStopSequences: true,\n\t\t\tsupportsReasoningEffort: false,\n\t\t\t...(version === null ? { claudeSamplingUnrecognized: true } : {}),\n\t\t};\n\t}\n\n\t// Google (Gemini): accepts standard sampling params, and does take\n\t// `reasoning_effort` — the gateway maps it onto Gemini's thinking config.\n\t// Measured on gemini-3-6-flash: `minimal` produces 0 reasoning tokens and\n\t// `high` produces 310, against 130 with the field absent.\n\t//\n\t// Newer Gemini models are stricter, and not in a way the id predicts: the\n\t// gateway rejects penalties on `gemini-3-5-flash-lite` while accepting them\n\t// on `gemini-3-1-flash-lite`, so neither the version nor the `-lite` suffix\n\t// is the rule. The `GEMINI_NO_SAMPLING` ids refuse temperature and topP\n\t// outright (\"does not support the temperature parameter\"). Both sets above\n\t// are listed by id because that is what was measured; a new Gemini model\n\t// inherits the permissive default until someone measures it.\n\tif (id.includes(\"gemini\")) {\n\t\tconst canonical = canonicalId(id);\n\t\tconst acceptsSampling = !GEMINI_NO_SAMPLING.has(canonical);\n\t\treturn {\n\t\t\tfamily: \"google\",\n\t\t\t...PERMISSIVE,\n\t\t\tsupportsTemperature: acceptsSampling,\n\t\t\tsupportsTopP: acceptsSampling,\n\t\t\tsupportsPenalties: !GEMINI_NO_PENALTIES.has(canonical),\n\t\t};\n\t}\n\n\t// OpenAI GPT-5 reasoning family (routed to the native Responses API). The\n\t// Responses model strips parameters the Responses API doesn't accept\n\t// (penalties, seed, stop), but its reasoning-model detection matches the bare\n\t// model id (`gpt-5`), which the gateway's optional `databricks-` prefix can\n\t// defeat. So we only handle the temperature/topP restriction here: the\n\t// original gpt-5 / gpt-5-mini / gpt-5-nano require the default temperature and\n\t// reject topP, while gpt-5.1+ (a minor version digit follows) accept them\n\t// again. The regex matches both prefixed and unprefixed ids.\n\tif (/gpt-5/.test(id)) {\n\t\tconst hasMinorVersion =\n\t\t\t/gpt-5[.-]\\d/.test(id) && !GPT5_NO_SAMPLING.has(canonicalId(id));\n\t\treturn {\n\t\t\tfamily: \"openai\",\n\t\t\tsupportsTemperature: hasMinorVersion,\n\t\t\tsupportsTopP: hasMinorVersion,\n\t\t\ttemperatureTopPMutuallyExclusive: false,\n\t\t\tsupportsPenalties: true,\n\t\t\tsupportsSeed: true,\n\t\t\tsupportsStopSequences: true,\n\t\t\tsupportsReasoningEffort: true,\n\t\t};\n\t}\n\n\t// The gpt-5 minor-version rule does not match gpt-6.\n\tif (GPT6_NO_SAMPLING.has(canonicalId(id))) {\n\t\treturn {\n\t\t\tfamily: \"openai\",\n\t\t\tsupportsTemperature: false,\n\t\t\tsupportsTopP: false,\n\t\t\ttemperatureTopPMutuallyExclusive: false,\n\t\t\tsupportsPenalties: true,\n\t\t\tsupportsSeed: true,\n\t\t\tsupportsStopSequences: true,\n\t\t\tsupportsReasoningEffort: true,\n\t\t};\n\t}\n\n\t// Meta (Llama): rejects penalties and seed; accepts sampling params and stop.\n\tif (id.includes(\"llama\")) {\n\t\treturn {\n\t\t\tfamily: \"meta\",\n\t\t\tsupportsTemperature: true,\n\t\t\tsupportsTopP: true,\n\t\t\ttemperatureTopPMutuallyExclusive: false,\n\t\t\tsupportsPenalties: false,\n\t\t\tsupportsSeed: false,\n\t\t\tsupportsStopSequences: true,\n\t\t\tsupportsReasoningEffort: true,\n\t\t};\n\t}\n\n\t// Everything else on the unified endpoint rejects penalties with\n\t// `parameter \"frequency_penalty\" must be equal to 0`. Only the older Gemini\n\t// models, handled above, accept them. Seed and stop vary, so each family\n\t// carries what was measured rather than inheriting a guess.\n\tif (id.includes(\"gpt-oss\")) {\n\t\treturn {\n\t\t\tfamily: \"other\",\n\t\t\t...PERMISSIVE,\n\t\t\tsupportsPenalties: false,\n\t\t\tsupportsSeed: false,\n\t\t\tsupportsStopSequences: false,\n\t\t};\n\t}\n\n\tif (id.includes(\"qwen\") || id.includes(\"gemma\")) {\n\t\treturn {\n\t\t\tfamily: \"other\",\n\t\t\t...PERMISSIVE,\n\t\t\tsupportsPenalties: false,\n\t\t\tsupportsSeed: false,\n\t\t};\n\t}\n\n\tif (\n\t\tid.includes(\"glm\") ||\n\t\tid.includes(\"inkling\") ||\n\t\tid.includes(\"kimi\") ||\n\t\tid.includes(\"grok\") ||\n\t\tid.includes(\"deepseek\")\n\t) {\n\t\treturn { family: \"other\", ...PERMISSIVE, supportsPenalties: false };\n\t}\n\n\treturn { family: \"other\", ...PERMISSIVE };\n}\n"],"mappings":";AAmBA,SAAgB,kBAAkB,SAAiC;CAClE,MAAM,KAAK,QAAQ,YAAY;CAC/B,IAAI,GAAG,SAAS,QAAQ,GACvB,OAAO;CAKR,IACE,GAAG,SAAS,MAAM,KAAK,CAAC,GAAG,SAAS,SAAS,KAC9C,GAAG,SAAS,OAAO,GAEnB,OAAO;CAER,OAAO;AACR;;;;;;;;;;AAiCA,MAAM,sCAAsB,IAAI,IAAI;CACnC;CACA;CACA;CACA;CACA;AACD,CAAC;;AAGD,MAAM,qCAAqB,IAAI,IAAI;CAClC;CACA;CACA;CACA;AACD,CAAC;;;;;;;;;;;;;;AAeD,MAAM,mCAAmB,IAAI,IAAI;CAChC;CACA;CACA;CACA;CACA;AACD,CAAC;;;;;;;;;AAUD,MAAM,mCAAmB,IAAI,IAAI;CAChC;CACA;CACA;CACA;AACD,CAAC;;;;;;AAOD,SAAS,YAAY,IAAoB;CACxC,OAAO,GAAG,WAAW,aAAa,IAAI,GAAG,MAAM,EAAoB,IAAI;AACxE;AAEA,MAAM,aAAoD;CACzD,qBAAqB;CACrB,cAAc;CACd,kCAAkC;CAClC,mBAAmB;CACnB,cAAc;CACd,uBAAuB;CACvB,yBAAyB;AAC1B;;;;;;;AAQA,SAAS,cAAc,IAAqD;CAK3E,MAAM,QAAQ,mDAAmD,KAAK,EAAE;CACxE,IAAI,CAAC,OACJ,OAAO;CAER,OAAO;EACN,OAAO,OAAO,MAAM,EAAE;EACtB,OAAO,MAAM,OAAO,KAAA,IAAY,IAAI,OAAO,MAAM,EAAE;CACpD;AACD;;;;;;;;;;AAWA,SAAgB,yBACf,SACwB;CACxB,MAAM,KAAK,QAAQ,YAAY;CAa/B,IAAI,GAAG,SAAS,QAAQ,GAAG;EAC1B,MAAM,UAAU,cAAc,EAAE;EAChC,MAAM,WACL,YAAY,SACX,QAAQ,QAAQ,KAAM,QAAQ,UAAU,KAAK,QAAQ,SAAS;EAChE,OAAO;GACN,QAAQ;GACR,qBAAqB;GACrB,cAAc;GACd,kCAAkC;GAClC,mBAAmB;GACnB,cAAc;GACd,uBAAuB;GACvB,yBAAyB;GACzB,GAAI,YAAY,OAAO,EAAE,4BAA4B,KAAK,IAAI,CAAC;EAChE;CACD;CAcA,IAAI,GAAG,SAAS,QAAQ,GAAG;EAC1B,MAAM,YAAY,YAAY,EAAE;EAChC,MAAM,kBAAkB,CAAC,mBAAmB,IAAI,SAAS;EACzD,OAAO;GACN,QAAQ;GACR,GAAG;GACH,qBAAqB;GACrB,cAAc;GACd,mBAAmB,CAAC,oBAAoB,IAAI,SAAS;EACtD;CACD;CAUA,IAAI,QAAQ,KAAK,EAAE,GAAG;EACrB,MAAM,kBACL,cAAc,KAAK,EAAE,KAAK,CAAC,iBAAiB,IAAI,YAAY,EAAE,CAAC;EAChE,OAAO;GACN,QAAQ;GACR,qBAAqB;GACrB,cAAc;GACd,kCAAkC;GAClC,mBAAmB;GACnB,cAAc;GACd,uBAAuB;GACvB,yBAAyB;EAC1B;CACD;CAGA,IAAI,iBAAiB,IAAI,YAAY,EAAE,CAAC,GACvC,OAAO;EACN,QAAQ;EACR,qBAAqB;EACrB,cAAc;EACd,kCAAkC;EAClC,mBAAmB;EACnB,cAAc;EACd,uBAAuB;EACvB,yBAAyB;CAC1B;CAID,IAAI,GAAG,SAAS,OAAO,GACtB,OAAO;EACN,QAAQ;EACR,qBAAqB;EACrB,cAAc;EACd,kCAAkC;EAClC,mBAAmB;EACnB,cAAc;EACd,uBAAuB;EACvB,yBAAyB;CAC1B;CAOD,IAAI,GAAG,SAAS,SAAS,GACxB,OAAO;EACN,QAAQ;EACR,GAAG;EACH,mBAAmB;EACnB,cAAc;EACd,uBAAuB;CACxB;CAGD,IAAI,GAAG,SAAS,MAAM,KAAK,GAAG,SAAS,OAAO,GAC7C,OAAO;EACN,QAAQ;EACR,GAAG;EACH,mBAAmB;EACnB,cAAc;CACf;CAGD,IACC,GAAG,SAAS,KAAK,KACjB,GAAG,SAAS,SAAS,KACrB,GAAG,SAAS,MAAM,KAClB,GAAG,SAAS,MAAM,KAClB,GAAG,SAAS,UAAU,GAEtB,OAAO;EAAE,QAAQ;EAAS,GAAG;EAAY,mBAAmB;CAAM;CAGnE,OAAO;EAAE,QAAQ;EAAS,GAAG;CAAW;AACzC"}

package/dist/lib/neon-openai-tools.d.ts.map

@@ -1 +1 @@
-{"version":3,"file":"neon-openai-tools.d.ts","names":["openai","openaiProvider","z","NeonImageGenerationArgs","imageGeneration","core","$strip","ZodObject","ZodString","NeonOpenAITools","tools","Omit","neonOpenAITools","openaiProvider","z","openai","NeonImageGenerationArgs","background","inputFidelity","inputImageMask","fileId","imageUrl","model","moderation","outputCompression","outputFormat","partialImages","quality","size","imageGeneration","args","type","id","inputSchema","ZodObject","core","$strip","outputSchema","result","ZodString","isProviderExecuted","NeonOpenAITools","Omit","tools","neonOpenAITools"],"sources":["../../src/lib/neon-openai-tools.ts"],"mappings":";;;;KAGYG,uBAAAA;;EAAAA,aAAAA,CAAAA,EAAAA,KAAAA,GAAAA,MAAuB;EA2BnBC,cAAAA,CAAAA,EAAAA;IAAegB,MAAA,CAAA,EAAA,MAAA;IAAOjB,QAAAA,CAAAA,EAAAA,MAAAA;;;;;;;EAe1BM,OAAAA,CAAAA,EAAAA,MAAAA,GAAe,KAAA,GAAA,QAAA,GAAA,MAAA;EAAAmB,IAAA,CAAA,EAAA,MAAA,GAAA,WAAA,GAAA,WAAA,GAAA,WAAA;AACnB3B,CAAAA;AADsBU;AAILP;AAAe;AAGxC;;;;;iBAtBgBA,eAAAA,QAAsBD;;;;;;;;;;;;;;;;;;;;;;;;KAe1BM,eAAAA,GAAkBE,YACtBV,MAAAA,CAAeS;0BAGEN;;cAGZQ,iBAAiBH"}
+{"version":3,"file":"neon-openai-tools.d.ts","names":["openai","openaiProvider","z","NeonImageGenerationArgs","imageGeneration","core","$strip","ZodObject","ZodString","NeonOpenAITools","tools","Omit","neonOpenAITools","openaiProvider","z","openai","NeonImageGenerationArgs","background","inputFidelity","inputImageMask","fileId","imageUrl","model","moderation","outputCompression","outputFormat","partialImages","quality","size","imageGeneration","args","type","id","inputSchema","ZodObject","core","$strip","outputSchema","result","ZodString","isProviderExecuted","NeonOpenAITools","Omit","tools","neonOpenAITools"],"sources":["../../src/lib/neon-openai-tools.ts"],"mappings":";;;;A,KAGYG,uBAAAA,G;;EAAAA,aAAAA,CAAAA,EAAAA,KAAAA,GAAAA,MAAuB;EA2BnBC,cAAAA,CAAAA,EAAAA;IAAegB,MAAA,CAAA,EAAA,MAAA;IAAOjB,QAAAA,CAAAA,EAAAA,MAAAA;;;;;;;EAe1BM,OAAAA,CAAAA,EAAAA,MAAAA,GAAe,KAAA,GAAA,QAAA,GAAA,MAAA;EAAAmB,IAAA,CAAA,EAAA,MAAA,GAAA,WAAA,GAAA,WAAA,GAAA,WAAA;AACnB3B,CAAAA;AADsBU;AAILP;AAAe;AAGxC;;;;;A,iBAtBgBA,eAAAA,C,OAAsBD,uB;;;;;;;;;;;;;;;;;;;;;;;;A,KAe1BM,eAAAA,GAAkBE,I,QACtBV,MAAAA,CAAeS,K;E,wBAGEN,e;;A,cAGZQ,e,EAAiBH,e"}

package/dist/lib/neon-responses-options.d.ts.map

@@ -1 +1 @@
-{"version":3,"file":"neon-responses-options.d.ts","names":["LanguageModelV3CallOptions","isReasoningModelId","withResponsesGatewayDefaults","LanguageModelV3CallOptions","isReasoningModelId","modelId","withResponsesGatewayDefaults","options"],"sources":["../../src/lib/neon-responses-options.ts"],"mappings":";;;;iBAmCgBC,kBAAAA;AAAhB;AASA;AAA4C;AAElCD;AACPA;AAA0B,iBAHbE,4BAAAA,CAGaG,OAAA,EAAA,MAAA,EAAAE,OAAA,EADnBP,0BACmB,CAAA,EAA1BA,0BAA0B"}
+{"version":3,"file":"neon-responses-options.d.ts","names":["LanguageModelV3CallOptions","isReasoningModelId","withResponsesGatewayDefaults","LanguageModelV3CallOptions","isReasoningModelId","modelId","withResponsesGatewayDefaults","options"],"sources":["../../src/lib/neon-responses-options.ts"],"mappings":";;;;A,iBAsCgBC,kBAAAA,C;AAAhB;AASA;AAA4C;AAElCD;AACPA;AAA0B,iBAHbE,4BAAAA,CAGaG,OAAA,EAAA,MAAA,EAAAE,OAAA,EADnBP,0BACmB,CAAA,EAA1BA,0BAA0B"}

package/dist/lib/neon-responses-options.js

@@ -23,12 +23,15 @@ import { UnsupportedFunctionalityError } from "@ai-sdk/provider";
 * `forceReasoning: true` covers a gap in the shared model's own detection,
 * which matches a bare `gpt-5` prefix. The gateway also accepts the legacy
 * `databricks-` form, and `databricks-gpt-5-2` fails that match while still
-* being a reasoning model.
+* being a reasoning model. The gpt-6 models are reasoning models too and fail
+* that match entirely. Without it, the shared model does not send
+* `reasoningEffort`, does not request `reasoning.encrypted_content`, and passes
+* `temperature` and `topP` through to a route that rejects them.
 */
 const STATELESS_HELP = "See https://github.com/neondatabase/neon-pkgs/tree/main/packages/ai-sdk-provider#errors";
 /** Models the gateway serves as reasoning models on this route. */
 function isReasoningModelId(modelId) {
-	return /gpt-5/.test(modelId.toLowerCase());
+	return /gpt-[56]/.test(modelId.toLowerCase());
 }
 /**
 * Apply the route's defaults to one call, or throw when a caller asked for

package/dist/lib/neon-responses-options.js.map

@@ -1 +1 @@
-{"version":3,"file":"neon-responses-options.js","names":[],"sources":["../../src/lib/neon-responses-options.ts"],"sourcesContent":["import {\n\ttype LanguageModelV3CallOptions,\n\tUnsupportedFunctionalityError,\n} from \"@ai-sdk/provider\";\n\n/**\n * Request defaults for the Neon AI Gateway's Responses route.\n *\n * `store: false` is the one value this gateway accepts, not a preference. It\n * serves the Responses API statelessly and keeps no items — a response comes\n * back with `\"store\": false` even when the request never set it. Left alone the\n * shared OpenAI model assumes stored-item semantics and replays earlier\n * reasoning as `{ type: \"item_reference\", id }`, which nothing upstream can\n * resolve; the gateway answers `502 INTERNAL_ERROR` on the second step of a\n * tool loop, after the first has already succeeded. Sending `false` makes the\n * model inline the encrypted reasoning instead.\n *\n * Since no other value can work, an explicit `store` that is not `false` is\n * refused rather than sent: the request would come back `400\n * INVALID_PARAMETER_VALUE` after a round trip, and quietly forcing it to\n * `false` would be the wrong kind of quiet for a data-retention flag. A\n * type-level constraint is not available — `providerOptions` is\n * `Record<string, JSONObject>`, so a provider cannot narrow it at the call\n * site.\n *\n * `forceReasoning: true` covers a gap in the shared model's own detection,\n * which matches a bare `gpt-5` prefix. The gateway also accepts the legacy\n * `databricks-` form, and `databricks-gpt-5-2` fails that match while still\n * being a reasoning model.\n */\n\nconst STATELESS_HELP =\n\t\"See https://github.com/neondatabase/neon-pkgs/tree/main/packages/ai-sdk-provider#errors\";\n\n/** Models the gateway serves as reasoning models on this route. */\nexport function isReasoningModelId(modelId: string): boolean {\n\treturn /gpt-5/.test(modelId.toLowerCase());\n}\n\n/**\n * Apply the route's defaults to one call, or throw when a caller asked for\n * something the gateway cannot do. Returns the options unchanged when there is\n * nothing to add.\n */\nexport function withResponsesGatewayDefaults(\n\tmodelId: string,\n\toptions: LanguageModelV3CallOptions,\n): LanguageModelV3CallOptions {\n\tconst openai = options.providerOptions?.openai;\n\tconst defaults: Record<string, boolean> = {};\n\n\t// `undefined` counts as unset rather than as a choice: it serializes away,\n\t// so `{ store: undefined }` and `{}` are the same request on the wire.\n\tif (openai?.store === undefined) {\n\t\tdefaults.store = false;\n\t} else if (openai.store === true || openai.store === null) {\n\t\t// `null` reads as \"omitted\" but is not: the shared model resolves it\n\t\t// with `store ?? true`, so it asks for storage just as `true` does.\n\t\tthrow new UnsupportedFunctionalityError({\n\t\t\tfunctionality: \"storing responses (providerOptions.openai.store)\",\n\t\t\tmessage:\n\t\t\t\t`\\`store: ${String(openai.store)}\\` is not available on the Neon AI ` +\n\t\t\t\t\"Gateway, which serves the Responses API statelessly and never \" +\n\t\t\t\t\"persists response items. Remove `providerOptions.openai.store`, or \" +\n\t\t\t\t\"set it to `false`.\" +\n\t\t\t\t(openai.store === null\n\t\t\t\t\t? \" `null` is not the same as omitting it — the AI SDK reads a null\" +\n\t\t\t\t\t\t\" `store` as `true`.\"\n\t\t\t\t\t: \"\") +\n\t\t\t\t` ${STATELESS_HELP}`,\n\t\t});\n\t}\n\n\t// Any other type is left for the shared model's own provider-option schema\n\t// (`store: z.boolean().nullish()`), which rejects it locally with a type\n\t// error. Only `true` and `null` pass that schema and are refused by the\n\t// gateway, so only they need saying something about here.\n\n\t// The same statelessness rules these out, and they belong to the same set:\n\t// refusing one and forwarding the others would read as an oversight.\n\tfor (const option of [\"previousResponseId\", \"conversation\"] as const) {\n\t\tif (openai?.[option] != null) {\n\t\t\tthrow new UnsupportedFunctionalityError({\n\t\t\t\tfunctionality: `server-side conversation state (providerOptions.openai.${option})`,\n\t\t\t\tmessage:\n\t\t\t\t\t`\\`${option}\\` is not available on the Neon AI Gateway, which ` +\n\t\t\t\t\t\"serves the Responses API statelessly and never persists response \" +\n\t\t\t\t\t`items, so there is nothing for \\`${option}\\` to refer to. Send ` +\n\t\t\t\t\t`the full message history instead. ${STATELESS_HELP}`,\n\t\t\t});\n\t\t}\n\t}\n\n\tif (isReasoningModelId(modelId) && openai?.forceReasoning === undefined) {\n\t\tdefaults.forceReasoning = true;\n\t}\n\n\tif (Object.keys(defaults).length === 0) {\n\t\treturn options;\n\t}\n\treturn {\n\t\t...options,\n\t\tproviderOptions: {\n\t\t\t...options.providerOptions,\n\t\t\topenai: { ...openai, ...defaults },\n\t\t},\n\t};\n}\n"],"mappings":";;;;;;;;;;;;;;;;;;;;;;;;;;;AA+BA,MAAM,iBACL;;AAGD,SAAgB,mBAAmB,SAA0B;CAC5D,OAAO,QAAQ,KAAK,QAAQ,YAAY,CAAC;AAC1C;;;;;;AAOA,SAAgB,6BACf,SACA,SAC6B;CAC7B,MAAM,SAAS,QAAQ,iBAAiB;CACxC,MAAM,WAAoC,CAAC;CAI3C,IAAI,QAAQ,UAAU,KAAA,GACrB,SAAS,QAAQ;MACX,IAAI,OAAO,UAAU,QAAQ,OAAO,UAAU,MAGpD,MAAM,IAAI,8BAA8B;EACvC,eAAe;EACf,SACC,YAAY,OAAO,OAAO,KAAK,EAAE,+LAIhC,OAAO,UAAU,OACf,wFAEA,MACH,IAAI;CACN,CAAC;CAUF,KAAK,MAAM,UAAU,CAAC,sBAAsB,cAAc,GACzD,IAAI,SAAS,WAAW,MACvB,MAAM,IAAI,8BAA8B;EACvC,eAAe,0DAA0D,OAAO;EAChF,SACC,KAAK,OAAO,sJAEwB,OAAO,yDACN;CACvC,CAAC;CAIH,IAAI,mBAAmB,OAAO,KAAK,QAAQ,mBAAmB,KAAA,GAC7D,SAAS,iBAAiB;CAG3B,IAAI,OAAO,KAAK,QAAQ,CAAC,CAAC,WAAW,GACpC,OAAO;CAER,OAAO;EACN,GAAG;EACH,iBAAiB;GAChB,GAAG,QAAQ;GACX,QAAQ;IAAE,GAAG;IAAQ,GAAG;GAAS;EAClC;CACD;AACD"}
+{"version":3,"file":"neon-responses-options.js","names":[],"sources":["../../src/lib/neon-responses-options.ts"],"sourcesContent":["import {\n\ttype LanguageModelV3CallOptions,\n\tUnsupportedFunctionalityError,\n} from \"@ai-sdk/provider\";\n\n/**\n * Request defaults for the Neon AI Gateway's Responses route.\n *\n * `store: false` is the one value this gateway accepts, not a preference. It\n * serves the Responses API statelessly and keeps no items — a response comes\n * back with `\"store\": false` even when the request never set it. Left alone the\n * shared OpenAI model assumes stored-item semantics and replays earlier\n * reasoning as `{ type: \"item_reference\", id }`, which nothing upstream can\n * resolve; the gateway answers `502 INTERNAL_ERROR` on the second step of a\n * tool loop, after the first has already succeeded. Sending `false` makes the\n * model inline the encrypted reasoning instead.\n *\n * Since no other value can work, an explicit `store` that is not `false` is\n * refused rather than sent: the request would come back `400\n * INVALID_PARAMETER_VALUE` after a round trip, and quietly forcing it to\n * `false` would be the wrong kind of quiet for a data-retention flag. A\n * type-level constraint is not available — `providerOptions` is\n * `Record<string, JSONObject>`, so a provider cannot narrow it at the call\n * site.\n *\n * `forceReasoning: true` covers a gap in the shared model's own detection,\n * which matches a bare `gpt-5` prefix. The gateway also accepts the legacy\n * `databricks-` form, and `databricks-gpt-5-2` fails that match while still\n * being a reasoning model. The gpt-6 models are reasoning models too and fail\n * that match entirely. Without it, the shared model does not send\n * `reasoningEffort`, does not request `reasoning.encrypted_content`, and passes\n * `temperature` and `topP` through to a route that rejects them.\n */\n\nconst STATELESS_HELP =\n\t\"See https://github.com/neondatabase/neon-pkgs/tree/main/packages/ai-sdk-provider#errors\";\n\n/** Models the gateway serves as reasoning models on this route. */\nexport function isReasoningModelId(modelId: string): boolean {\n\treturn /gpt-[56]/.test(modelId.toLowerCase());\n}\n\n/**\n * Apply the route's defaults to one call, or throw when a caller asked for\n * something the gateway cannot do. Returns the options unchanged when there is\n * nothing to add.\n */\nexport function withResponsesGatewayDefaults(\n\tmodelId: string,\n\toptions: LanguageModelV3CallOptions,\n): LanguageModelV3CallOptions {\n\tconst openai = options.providerOptions?.openai;\n\tconst defaults: Record<string, boolean> = {};\n\n\t// `undefined` counts as unset rather than as a choice: it serializes away,\n\t// so `{ store: undefined }` and `{}` are the same request on the wire.\n\tif (openai?.store === undefined) {\n\t\tdefaults.store = false;\n\t} else if (openai.store === true || openai.store === null) {\n\t\t// `null` reads as \"omitted\" but is not: the shared model resolves it\n\t\t// with `store ?? true`, so it asks for storage just as `true` does.\n\t\tthrow new UnsupportedFunctionalityError({\n\t\t\tfunctionality: \"storing responses (providerOptions.openai.store)\",\n\t\t\tmessage:\n\t\t\t\t`\\`store: ${String(openai.store)}\\` is not available on the Neon AI ` +\n\t\t\t\t\"Gateway, which serves the Responses API statelessly and never \" +\n\t\t\t\t\"persists response items. Remove `providerOptions.openai.store`, or \" +\n\t\t\t\t\"set it to `false`.\" +\n\t\t\t\t(openai.store === null\n\t\t\t\t\t? \" `null` is not the same as omitting it — the AI SDK reads a null\" +\n\t\t\t\t\t\t\" `store` as `true`.\"\n\t\t\t\t\t: \"\") +\n\t\t\t\t` ${STATELESS_HELP}`,\n\t\t});\n\t}\n\n\t// Any other type is left for the shared model's own provider-option schema\n\t// (`store: z.boolean().nullish()`), which rejects it locally with a type\n\t// error. Only `true` and `null` pass that schema and are refused by the\n\t// gateway, so only they need saying something about here.\n\n\t// The same statelessness rules these out, and they belong to the same set:\n\t// refusing one and forwarding the others would read as an oversight.\n\tfor (const option of [\"previousResponseId\", \"conversation\"] as const) {\n\t\tif (openai?.[option] != null) {\n\t\t\tthrow new UnsupportedFunctionalityError({\n\t\t\t\tfunctionality: `server-side conversation state (providerOptions.openai.${option})`,\n\t\t\t\tmessage:\n\t\t\t\t\t`\\`${option}\\` is not available on the Neon AI Gateway, which ` +\n\t\t\t\t\t\"serves the Responses API statelessly and never persists response \" +\n\t\t\t\t\t`items, so there is nothing for \\`${option}\\` to refer to. Send ` +\n\t\t\t\t\t`the full message history instead. ${STATELESS_HELP}`,\n\t\t\t});\n\t\t}\n\t}\n\n\tif (isReasoningModelId(modelId) && openai?.forceReasoning === undefined) {\n\t\tdefaults.forceReasoning = true;\n\t}\n\n\tif (Object.keys(defaults).length === 0) {\n\t\treturn options;\n\t}\n\treturn {\n\t\t...options,\n\t\tproviderOptions: {\n\t\t\t...options.providerOptions,\n\t\t\topenai: { ...openai, ...defaults },\n\t\t},\n\t};\n}\n"],"mappings":";;;;;;;;;;;;;;;;;;;;;;;;;;;;;;AAkCA,MAAM,iBACL;;AAGD,SAAgB,mBAAmB,SAA0B;CAC5D,OAAO,WAAW,KAAK,QAAQ,YAAY,CAAC;AAC7C;;;;;;AAOA,SAAgB,6BACf,SACA,SAC6B;CAC7B,MAAM,SAAS,QAAQ,iBAAiB;CACxC,MAAM,WAAoC,CAAC;CAI3C,IAAI,QAAQ,UAAU,KAAA,GACrB,SAAS,QAAQ;MACX,IAAI,OAAO,UAAU,QAAQ,OAAO,UAAU,MAGpD,MAAM,IAAI,8BAA8B;EACvC,eAAe;EACf,SACC,YAAY,OAAO,OAAO,KAAK,EAAE,+LAIhC,OAAO,UAAU,OACf,wFAEA,MACH,IAAI;CACN,CAAC;CAUF,KAAK,MAAM,UAAU,CAAC,sBAAsB,cAAc,GACzD,IAAI,SAAS,WAAW,MACvB,MAAM,IAAI,8BAA8B;EACvC,eAAe,0DAA0D,OAAO;EAChF,SACC,KAAK,OAAO,sJAEwB,OAAO,yDACN;CACvC,CAAC;CAIH,IAAI,mBAAmB,OAAO,KAAK,QAAQ,mBAAmB,KAAA,GAC7D,SAAS,iBAAiB;CAG3B,IAAI,OAAO,KAAK,QAAQ,CAAC,CAAC,WAAW,GACpC,OAAO;CAER,OAAO;EACN,GAAG;EACH,iBAAiB;GAChB,GAAG,QAAQ;GACX,QAAQ;IAAE,GAAG;IAAQ,GAAG;GAAS;EAClC;CACD;AACD"}

package/dist/lib/provider.d.ts.map

@@ -1 +1 @@
-{"version":3,"file":"provider.d.ts","names":["EmbeddingModelV3","LanguageModelV3","ProviderV3","FetchFunction","z","NeonChatModelId","NeonDecisionModel","NeonDecisionModelId","NeonEmbeddingModelId","neonOpenAITools","neonErrorSchema","ZodString","ZodNullable","ZodOptional","ZodUnknown","core","$strip","ZodObject","NeonErrorData","infer","NeonProviderSettings","Record","NeonProvider","createNeon","neon","NeonChatModelId","NeonDecisionModel","NeonDecisionModelId","NeonEmbeddingModelId","neonOpenAITools","EmbeddingModelV3","LanguageModelV3","ProviderV3","FetchFunction","z","neonErrorSchema","ZodObject","error","message","ZodString","type","ZodOptional","ZodNullable","param","ZodUnknown","code","core","$strip","NeonErrorData","infer","NeonProviderSettings","baseURL","apiKey","headers","Record","fetch","NeonProvider","modelId","languageModel","chat","tools","embeddingModel","textEmbeddingModel","decisionModel","createNeon","options","neon"],"sources":["../../src/lib/provider.ts"],"mappings":";;;;;;;;;cAkDMU,iBAAeN,CAAAA,CAAAa;;IAAfP,OAAAA,aAOJ;IAAA8B,IAAA,eAAA,cAAA,YAAA,CAAA,CAAA;;;;GAAApC,CAAAA,CAAAW,IAAAA,CAAAC;KAEUE,aAAAA,GAAgBd,CAAAA,CAAEe,aAAaT;UA4C1BU,oBAAAA;;;;;;;EA9CfhB;AAPmBA;AAAA;AASrB;EAAyBgD,MAAA,CAAA,EAAA,MAAA;EAAkB1C;EAAfN,OAAEe,CAAAA,EA2DnBE,MA3DmBF,CAAAA,MAAAA,EAAAA,MAAAA,CAAAA;EAAK;EA4ClBC,KAAAA,CAAAA,EAkBRjB,aAlBQiB;AAAoB;AAe1BC,UAMMC,YAAAA,SAAqBpB,UAN3BmB,CAAAA;EAGFlB;EAAa,CAAAsD,OAAA,EAKXpD,eALW,CAAA,EAKOJ,eALP;EAGLqB;EAAaoC,aAAA,CAAAD,OAAA,EAKNpD,eALM,CAAA,EAKYJ,eALZ;EAEnBI;EAAkBJ,IAAAA,CAAAA,OAAAA,EAMdI,eANcJ,CAAAA,EAMIA,eANJA;EAGLI;EAAkBJ,KAAAA,EAAAA,OAM3BQ,eAN2BR;EAG3BI;AAAkBJ;AAGlBQ;AAMUD;EAAuBR,cAAAA,CAAAA,OAAAA,EAAvBQ,oBAAuBR,CAAAA,EAAAA,gBAAAA;EAGnBQ;EAAuBR,kBAAAA,CAAAA,OAAAA,EAAvBQ,oBAAuBR,CAAAA,EAAAA,gBAAAA;EAM5BO;AAAsBD;AA1BRJ;AAAU;EA6BhCqB,aAAU,CAAAkC,OAAA,EAHFlD,mBAGE,CAAA,EAHoBD,iBAGpB;AAAA;AAAUc,iBAApBG,UAAAA,CAAoBH,OAAAA,CAAAA,EAAAA,oBAAAA,CAAAA,EAA4BE,YAA5BF;AAA4BE;AAAY,cA0I/DE,IA1I+D,EA0I3DF,YA1I2D"}
+{"version":3,"file":"provider.d.ts","names":["EmbeddingModelV3","LanguageModelV3","ProviderV3","FetchFunction","z","NeonChatModelId","NeonDecisionModel","NeonDecisionModelId","NeonEmbeddingModelId","neonOpenAITools","neonErrorSchema","ZodString","ZodNullable","ZodOptional","ZodUnknown","core","$strip","ZodObject","NeonErrorData","infer","NeonProviderSettings","Record","NeonProvider","createNeon","neon","NeonChatModelId","NeonDecisionModel","NeonDecisionModelId","NeonEmbeddingModelId","neonOpenAITools","EmbeddingModelV3","LanguageModelV3","ProviderV3","FetchFunction","z","neonErrorSchema","ZodObject","error","message","ZodString","type","ZodOptional","ZodNullable","param","ZodUnknown","code","core","$strip","NeonErrorData","infer","NeonProviderSettings","baseURL","apiKey","headers","Record","fetch","NeonProvider","modelId","languageModel","chat","tools","embeddingModel","textEmbeddingModel","decisionModel","createNeon","options","neon"],"sources":["../../src/lib/provider.ts"],"mappings":";;;;;;;;;A,cAkDMU,e,EAAeN,CAAAA,CAAAa,S;;IAAfP,OAAAA,E,WAOJ;IAAA8B,IAAA,E,aAAA,C,aAAA,C,WAAA,CAAA,CAAA;;;;A,GAAApC,CAAAA,CAAAW,IAAAA,CAAAC,M;A,KAEUE,aAAAA,GAAgBd,CAAAA,CAAEe,K,QAAaT,e;A,UA4C1BU,oBAAAA,C;;;;;;;EA9CfhB;AAPmBA;AAAA;AASrB;EAAyBgD,MAAA,CAAA,EAAA,MAAA;EAAkB1C;EAAfN,OAAEe,CAAAA,EA2DnBE,MA3DmBF,CAAAA,MAAAA,EAAAA,MAAAA,CAAAA;EAAK;EA4ClBC,KAAAA,CAAAA,EAkBRjB,aAlBQiB;AAAoB;AAe1BC,UAMMC,YAAAA,SAAqBpB,UAN3BmB,CAAAA;EAGFlB;EAAa,CAAAsD,OAAA,EAKXpD,eALW,CAAA,EAKOJ,eALP;EAGLqB;EAAaoC,aAAA,CAAAD,OAAA,EAKNpD,eALM,CAAA,EAKYJ,eALZ;EAEnBI;EAAkBJ,IAAAA,CAAAA,OAAAA,EAMdI,eANcJ,CAAAA,EAMIA,eANJA;EAGLI;EAAkBJ,KAAAA,EAAAA,OAM3BQ,eAN2BR;EAG3BI;AAAkBJ;AAGlBQ;AAMUD;EAAuBR,cAAAA,CAAAA,OAAAA,EAAvBQ,oBAAuBR,CAAAA,EAAAA,gBAAAA;EAGnBQ;EAAuBR,kBAAAA,CAAAA,OAAAA,EAAvBQ,oBAAuBR,CAAAA,EAAAA,gBAAAA;EAM5BO;AAAsBD;AA1BRJ;AAAU;EA6BhCqB,aAAU,CAAAkC,OAAA,EAHFlD,mBAGE,CAAA,EAHoBD,iBAGpB;AAAA;AAAUc,iBAApBG,UAAAA,CAAoBH,OAAAA,CAAAA,EAAAA,oBAAAA,CAAAA,EAA4BE,YAA5BF;AAA4BE;AAAY,cA0I/DE,IA1I+D,EA0I3DF,YA1I2D"}

package/dist/lib/version.d.ts.map

@@ -1 +1 @@
-{"version":3,"file":"version.d.ts","names":["VERSION","VERSION"],"sources":["../../src/lib/version.ts"],"mappings":";cAIaA"}
+{"version":3,"file":"version.d.ts","names":["VERSION","VERSION"],"sources":["../../src/lib/version.ts"],"mappings":";A,cAIaA,O"}

package/dist/package.js

@@ -1,5 +1,5 @@
 //#region package.json
-var version = "1.1.0";
+var version = "1.2.0";
 //#endregion
 export { version };
 

package/package.json

@@ -1,6 +1,6 @@
 {
   "name": "@neon/ai-sdk-provider",
-  "version": "1.1.0",
+  "version": "1.2.0",
   "description": "Community Vercel AI SDK provider for the Neon AI Gateway.",
   "keywords": [
     "neon",