@neon/ai-sdk-provider 1.3.1 → 1.4.0
This diff represents the content of publicly available package versions that have been released to one of the supported registries. The information contained in this diff is provided for informational purposes only and reflects changes between package versions as they appear in their respective public registries.
- package/README.md +4 -4
- package/dist/lib/neon-chat-options.d.ts +1 -1
- package/dist/lib/neon-chat-options.d.ts.map +1 -1
- package/dist/lib/neon-chat-options.js +3 -0
- package/dist/lib/neon-chat-options.js.map +1 -1
- package/dist/lib/neon-model-capabilities.d.ts.map +1 -1
- package/dist/lib/neon-model-capabilities.js +4 -2
- package/dist/lib/neon-model-capabilities.js.map +1 -1
- package/dist/package.js +1 -1
- package/package.json +1 -1
package/README.md
CHANGED
|
@@ -73,16 +73,16 @@ These rules apply on the Anthropic Messages and Chat Completions routes. The Res
|
|
|
73
73
|
|
|
74
74
|
| Models | Dropped |
|
|
75
75
|
| --- | --- |
|
|
76
|
-
| 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` |
|
|
76
|
+
| 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-fable-5-2`, `claude-haiku-5-5`, `claude-sonnet-5-5`) | `temperature`, `topP` |
|
|
77
77
|
| All Claude | `frequencyPenalty`, `presencePenalty`, `seed`, `reasoningEffort`, and `topP` when you set both `temperature` and `topP` (Anthropic accepts only one) |
|
|
78
78
|
| `gpt-oss` | `frequencyPenalty`, `presencePenalty`, `seed`, `stopSequences` |
|
|
79
79
|
| Qwen, Gemma | `frequencyPenalty`, `presencePenalty`, `seed` |
|
|
80
|
-
| `glm-5-2`, `glm-5-3`, `glm-5-3-flash`, `kimi-k3` | `frequencyPenalty`, `presencePenalty` |
|
|
80
|
+
| `glm-5-2`, `glm-5-3`, `glm-5-3-flash`, `kimi-k3`, `kimi-k3-1-pro` | `frequencyPenalty`, `presencePenalty` |
|
|
81
81
|
| Grok, DeepSeek | `frequencyPenalty`, `presencePenalty` |
|
|
82
82
|
| Meta Llama | `frequencyPenalty`, `presencePenalty`, `seed` |
|
|
83
83
|
| `gemini-3-5-flash-lite` | `frequencyPenalty`, `presencePenalty` |
|
|
84
84
|
| `gemini-3-6-flash` | `temperature`, `topP`, `frequencyPenalty`, `presencePenalty` |
|
|
85
|
-
| `gemini-3-7-flash`, `gemini-3-8-flash`, `gemini-4-argon` | `temperature`, `topP`, `frequencyPenalty`, `presencePenalty` |
|
|
85
|
+
| `gemini-3-7-flash`, `gemini-3-8-flash`, `gemini-4-argon`, `gemini-4-carbon` | `temperature`, `topP`, `frequencyPenalty`, `presencePenalty` |
|
|
86
86
|
| Every other Gemini | nothing |
|
|
87
87
|
| `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` |
|
|
88
88
|
|
|
@@ -108,7 +108,7 @@ getNeonModelCapabilities('gpt-6-astra').supportsTemperature; // false
|
|
|
108
108
|
getNeonModelCapabilities('glm-5-2').supportsPenalties; // false
|
|
109
109
|
```
|
|
110
110
|
|
|
111
|
-
**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-
|
|
111
|
+
**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`, `gemini-4-argon`, and `gemini-4-carbon` reject `temperature` and `topP` outright, so reading a row for "Gemini" is not enough; check the id. `reasoningEffort` is forwarded to every Gemini id, and the gateway currently answers it with a `400` on `gemini-4-argon` and `gemini-4-carbon`, so leave it unset on those two. 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.
|
|
112
112
|
|
|
113
113
|
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.
|
|
114
114
|
|
|
@@ -1,5 +1,5 @@
|
|
|
1
1
|
/** Published catalog ids from https://neon.com/models.json (canonical, unprefixed). */
|
|
2
|
-
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", "kimi-k3", "deepseek-v4-1-flash"];
|
|
2
|
+
declare const NEON_MODELS_DEV_IDS: readonly ["claude-fable-5", "claude-fable-5-1", "claude-fable-5-2", "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", "gemini-4-carbon", "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", "kimi-k3", "kimi-k3-1-pro", "deepseek-v4-1-flash"];
|
|
3
3
|
/** A known Neon AI Gateway model id. */
|
|
4
4
|
type NeonKnownModelId = (typeof NEON_MODELS_DEV_IDS)[number];
|
|
5
5
|
/**
|
|
@@ -1 +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,
|
|
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,mBAuEH,EAAA,SAAA,CAAA,gBAAA,EAAA,kBAAA,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,iBAAA,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,eAAA,EAAA,qBAAA,CAAA;AAGV;AAOYE,KAPAD,gBAAAA,GAOe,CAAGA,OAPSD,mBAOO,CAAA,CAAA,MAAA,CAAA;;;;;;A,KAAlCE,eAAAA,GAAkBD,gB"}
|
|
@@ -3,6 +3,7 @@
|
|
|
3
3
|
const NEON_MODELS_DEV_IDS = [
|
|
4
4
|
"claude-fable-5",
|
|
5
5
|
"claude-fable-5-1",
|
|
6
|
+
"claude-fable-5-2",
|
|
6
7
|
"claude-haiku-4-5",
|
|
7
8
|
"claude-haiku-5-5",
|
|
8
9
|
"claude-opus-4-1",
|
|
@@ -45,6 +46,7 @@ const NEON_MODELS_DEV_IDS = [
|
|
|
45
46
|
"gemini-3-8-flash",
|
|
46
47
|
"gemini-3-flash",
|
|
47
48
|
"gemini-4-argon",
|
|
49
|
+
"gemini-4-carbon",
|
|
48
50
|
"gemma-3-12b",
|
|
49
51
|
"llama-4-maverick",
|
|
50
52
|
"meta-llama-3-1-8b-instruct",
|
|
@@ -57,6 +59,7 @@ const NEON_MODELS_DEV_IDS = [
|
|
|
57
59
|
"grok-4-6",
|
|
58
60
|
"grok-4-7",
|
|
59
61
|
"kimi-k3",
|
|
62
|
+
"kimi-k3-1-pro",
|
|
60
63
|
"deepseek-v4-1-flash"
|
|
61
64
|
];
|
|
62
65
|
export { NEON_MODELS_DEV_IDS };
|
|
@@ -1 +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` 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// 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;AACD"}
|
|
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` 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-fable-5-2\",\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\"gemini-4-carbon\",\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// Moonshot (unified MLflow endpoint)\n\t\"kimi-k3\",\n\t\"kimi-k3-1-pro\",\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;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;CACA;CAEA;CACA;CACA;CAEA;CACA;CAEA;CACA;CACA;CAEA;CACA;CAEA;CACA;CAEA;AACD"}
|
|
@@ -1 +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":"A,KAAYA,eAAAA,G;AAAZ;AAiBA;AAEA;AAiBA;
|
|
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":"A,KAAYA,eAAAA,G;AAAZ;AAiBA;AAEA;AAiBA;AAsIA;;;;;;A,KAzJYC,cAAAA,G;A,iBAEIC,iBAAAA,C,kBAAoCD,c;A,UAiBnCE,qBAAAA,C;E,QACRH,e;;;;;;;;;;;;;;;;;;;;;;;;;;;;;A,iBAqIOI,wBAAAA,C,kBAEbD,qB"}
|
|
@@ -19,14 +19,16 @@ const GEMINI_NO_PENALTIES = /* @__PURE__ */ new Set([
|
|
|
19
19
|
"gemini-3-6-flash",
|
|
20
20
|
"gemini-3-7-flash",
|
|
21
21
|
"gemini-3-8-flash",
|
|
22
|
-
"gemini-4-argon"
|
|
22
|
+
"gemini-4-argon",
|
|
23
|
+
"gemini-4-carbon"
|
|
23
24
|
]);
|
|
24
25
|
/** Gemini models that reject `temperature` and `topP` outright. */
|
|
25
26
|
const GEMINI_NO_SAMPLING = /* @__PURE__ */ new Set([
|
|
26
27
|
"gemini-3-6-flash",
|
|
27
28
|
"gemini-3-7-flash",
|
|
28
29
|
"gemini-3-8-flash",
|
|
29
|
-
"gemini-4-argon"
|
|
30
|
+
"gemini-4-argon",
|
|
31
|
+
"gemini-4-carbon"
|
|
30
32
|
]);
|
|
31
33
|
/**
|
|
32
34
|
* GPT-5 ids that reject `temperature` despite carrying a minor version.
|
|
@@ -1 +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\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(\"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,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"}
|
|
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\t\"gemini-3-7-flash\",\n\t\"gemini-3-8-flash\",\n\t\"gemini-4-argon\",\n\t\"gemini-4-carbon\",\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\t\"gemini-4-carbon\",\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 Gemini 3 takes\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// That mapping is broken for Gemini 4: `gemini-4-argon` and\n\t// `gemini-4-carbon` answer `reasoning_effort` with a 400 (`Unknown name\n\t// \"reasoning_effort\" at 'generation_config'`). It is still forwarded to\n\t// them, because dropping it needs a Gemini-specific warning (the\n\t// reasoningEffort one points at Claude's effort option).\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(\"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;CACA;AACD,CAAC;;AAGD,MAAM,qCAAqB,IAAI,IAAI;CAClC;CACA;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;CAoBA,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,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/package.js
CHANGED