@gtrabanco/pi-nan-provider 0.6.11 → 0.8.0

package/scripts/models.generated.ts

@@ -1,7 +1,7 @@
 // This file is auto-generated by scripts/generate-models.ts
 // Do not edit manually — run `bun run generate-models` to update.
 //
-// Source: https://models.dev/api.json (provider "nan"), fetched 2026-09-22T08:55:04.775Z
+// Source: https://models.dev/api.json (provider "nan"), fetched 2026-09-27T21:25:24.946Z
 // Provenance: every contextWindow/maxTokens/input/cost value traces to
 // models.dev or to the per-entry notes below. Nothing is invented; entries
 // models.dev documents incompletely are omitted and flagged instead.
@@ -28,6 +28,7 @@ export const NAN_GENERATED_MODELS: readonly GeneratedModelEntry[] = [
 		},
 		"contextWindow": 1000000,
 		"maxTokens": 384000,
+		"reasoningEffortValues": [],
 		"compat": {
 			"supportsDeveloperRole": false,
 			"supportsReasoningEffort": true,
@@ -37,7 +38,7 @@ export const NAN_GENERATED_MODELS: readonly GeneratedModelEntry[] = [
 		},
 		"notes": [
 			"compat matches the maintainer's working ~/.pi/agent/models.json LiteLLM config for api.nan.builders (2026-09-04): supportsDeveloperRole false, supportsReasoningEffort true, maxTokensField max_tokens. NaN's docs example sets only supportsDeveloperRole: true and is not battle-tested. supportsFinishReason true (2026-09-13, issue #2): the LiteLLM gateway intermittently closes SSE streams before emitting finish_reason; with true pi-ai raises 'Stream ended without finish_reason', which matches pi-ai's retryable-provider pattern ('ended without') and is retried automatically, whereas false silently synthesized stop/toolUse and stalled the turn mid-answer. supportsUsageInStreaming true (2026-09-16, issue #7): NaN's published schema is silent about stream_options, but the live gateway honors it — two identical streaming calls per model, differing only in stream_options: { include_usage: true }, returned 0 usage chunks without it and exactly 1 with it (prompt/completion/reasoning/cached token counts) on deepseek-v4-flash, glm5.3-flash, qwen3.6, mimo-v2.5 and gemma4, and a real pi session then recorded token counts where it recorded zeros. pi-ai only sends stream_options when this is not false, and the sanitizer forwards it when the model declares true, so chat models opt in by default and usage is reported (issue #4). A model that does not report streaming usage can still opt out per model with a models.json compat override (supportsUsageInStreaming: false); the sanitizer then strips stream_options and the payload stays strict.",
-			"input includes image: NaN serves the Vision-Exp variant ('takes images as input', https://nan.builders/docs/models; the image_url content-parts in https://nan.builders/openapi.json list deepseek-v4-flash among the vision models). models.dev provider nan also lists text+image now (DeepSeek V4.1 Flash entry, checked 2026-09-13; its 2026-09-07 snapshot listed text only), so this override is kept as a pin for the vision capability rather than as a divergence."
+			"input includes image: NaN serves the Vision-Exp variant ('takes images as input', https://nan.builders/docs/models; the image_url content-parts in https://nan.builders/openapi.json list deepseek-v4-flash among the vision models). models.dev provider nan also lists text+image now (DeepSeek V4.1 Flash entry, checked 2026-09-13; its 2026-09-07 snapshot listed text only), so this override is kept as a pin for the vision capability rather than as a divergence. reasoning_effort_values=[]: the model decides per-request how much to reason (https://nan.builders/docs/models, checked 2026-09-25)."
 		],
 		"extras": {
 			"id": "deepseek-v4-flash",
@@ -89,6 +90,14 @@ export const NAN_GENERATED_MODELS: readonly GeneratedModelEntry[] = [
 		},
 		"contextWindow": 262144,
 		"maxTokens": 32768,
+		"reasoningEffortValues": [
+			"none",
+			"minimal",
+			"low",
+			"medium",
+			"high",
+			"max"
+		],
 		"compat": {
 			"supportsDeveloperRole": false,
 			"supportsReasoningEffort": true,
@@ -152,6 +161,12 @@ export const NAN_GENERATED_MODELS: readonly GeneratedModelEntry[] = [
 		},
 		"contextWindow": 1000000,
 		"maxTokens": 131072,
+		"reasoningEffortValues": [
+			"low",
+			"medium",
+			"high",
+			"max"
+		],
 		"compat": {
 			"supportsDeveloperRole": false,
 			"supportsReasoningEffort": true,
@@ -211,6 +226,7 @@ export const NAN_GENERATED_MODELS: readonly GeneratedModelEntry[] = [
 		},
 		"contextWindow": 1048576,
 		"maxTokens": 131072,
+		"reasoningEffortValues": [],
 		"compat": {
 			"supportsDeveloperRole": false,
 			"supportsReasoningEffort": true,
@@ -255,6 +271,35 @@ export const NAN_GENERATED_MODELS: readonly GeneratedModelEntry[] = [
 			}
 		}
 	},
+	{
+		"id": "mimo-v2.6-flash",
+		"name": "mimo-v2.6-flash",
+		"reasoning": true,
+		"input": [
+			"text",
+			"image"
+		],
+		"cost": {
+			"input": 0,
+			"output": 0,
+			"cacheRead": 0,
+			"cacheWrite": 0
+		},
+		"contextWindow": 1048576,
+		"maxTokens": 131072,
+		"compat": {
+			"supportsDeveloperRole": false,
+			"supportsReasoningEffort": true,
+			"supportsUsageInStreaming": true,
+			"supportsFinishReason": true,
+			"maxTokensField": "max_tokens"
+		},
+		"notes": [
+			"compat matches the maintainer's working ~/.pi/agent/models.json LiteLLM config for api.nan.builders (2026-09-04): supportsDeveloperRole false, supportsReasoningEffort true, maxTokensField max_tokens. NaN's docs example sets only supportsDeveloperRole: true and is not battle-tested. supportsFinishReason true (2026-09-13, issue #2): the LiteLLM gateway intermittently closes SSE streams before emitting finish_reason; with true pi-ai raises 'Stream ended without finish_reason', which matches pi-ai's retryable-provider pattern ('ended without') and is retried automatically, whereas false silently synthesized stop/toolUse and stalled the turn mid-answer. supportsUsageInStreaming true (2026-09-16, issue #7): NaN's published schema is silent about stream_options, but the live gateway honors it — two identical streaming calls per model, differing only in stream_options: { include_usage: true }, returned 0 usage chunks without it and exactly 1 with it (prompt/completion/reasoning/cached token counts) on deepseek-v4-flash, glm5.3-flash, qwen3.6, mimo-v2.5 and gemma4, and a real pi session then recorded token counts where it recorded zeros. pi-ai only sends stream_options when this is not false, and the sanitizer forwards it when the model declares true, so chat models opt in by default and usage is reported (issue #4). A model that does not report streaming usage can still opt out per model with a models.json compat override (supportsUsageInStreaming: false); the sanitizer then strips stream_options and the payload stays strict.",
+			"manual-only: \"mimo-v2.6-flash\" not yet on models.dev provider nan (omnimodal model (text, image, audio input) served by NaN, not yet listed on models.dev provider nan (checked 2026-09-25); included so the live /models refresh does not hand it UNKNOWN_MODEL_LIMITS. Same limits as mimo-v2.5: 1,048,576 / 131,072 / 1.0B monthly quota per member. Reasoning: accepted, depth not adjustable. Tool calling: yes. Streaming: yes. Input modalities (pi-representable): text, image (audio not representable in pi's Model type).)."
+		],
+		"extras": {}
+	},
 	{
 		"id": "qwen3.6",
 		"name": "Qwen3.6 35B-A3B",
@@ -271,6 +316,14 @@ export const NAN_GENERATED_MODELS: readonly GeneratedModelEntry[] = [
 		},
 		"contextWindow": 262144,
 		"maxTokens": 65536,
+		"reasoningEffortValues": [
+			"none",
+			"minimal",
+			"low",
+			"medium",
+			"high",
+			"max"
+		],
 		"compat": {
 			"supportsDeveloperRole": false,
 			"supportsReasoningEffort": true,
@@ -334,6 +387,7 @@ export const NAN_GENERATED_MODELS: readonly GeneratedModelEntry[] = [
 		},
 		"contextWindow": 262144,
 		"maxTokens": 131072,
+		"reasoningEffortValues": [],
 		"compat": {
 			"supportsDeveloperRole": false,
 			"supportsReasoningEffort": true,
@@ -382,14 +436,15 @@ export const NAN_GENERATED_MODELS: readonly GeneratedModelEntry[] = [
 export const GENERATED_CATALOG_META = {
 	source: "https://models.dev/api.json",
 	modelsDevProvider: "nan",
-	fetchedAt: "2026-09-22T08:55:04.775Z",
-	modelCount: 6,
-	models: ["deepseek-v4-flash","gemma4","glm5.3-flash","mimo-v2.5","qwen3.6","qwen3.8-flash"],
+	fetchedAt: "2026-09-27T21:25:24.946Z",
+	modelCount: 7,
+	models: ["deepseek-v4-flash","gemma4","glm5.3-flash","mimo-v2.5","mimo-v2.6-flash","qwen3.6","qwen3.8-flash"],
 	notes: [
 	"live-only: \"glm5.3\" kept out of the static catalog (premium-tier model (models.dev now documents it with 1M context / 131,072 max output; NaN docs https://nan.builders/docs/models + https://nan.builders/openapi.json, checked 2026-09-13) kept live-only so a non-premium key never sees a model it cannot call when the live /models fetch is unavailable; premium keys still get it via the /models refresh with conservative placeholder limits)",
 	"provider-removed: \"glm5.2\" excluded from the catalog (removed by NaN (2026-09-05); absent from the official chat model list in https://nan.builders/openapi.json and https://nan.builders/docs/models (checked 2026-09-07) while models.dev provider nan still listed it — excluded so regeneration does not resurrect it)",
 	"compat matches the maintainer's working ~/.pi/agent/models.json LiteLLM config for api.nan.builders (2026-09-04): supportsDeveloperRole false, supportsReasoningEffort true, maxTokensField max_tokens. NaN's docs example sets only supportsDeveloperRole: true and is not battle-tested. supportsFinishReason true (2026-09-13, issue #2): the LiteLLM gateway intermittently closes SSE streams before emitting finish_reason; with true pi-ai raises 'Stream ended without finish_reason', which matches pi-ai's retryable-provider pattern ('ended without') and is retried automatically, whereas false silently synthesized stop/toolUse and stalled the turn mid-answer. supportsUsageInStreaming true (2026-09-16, issue #7): NaN's published schema is silent about stream_options, but the live gateway honors it — two identical streaming calls per model, differing only in stream_options: { include_usage: true }, returned 0 usage chunks without it and exactly 1 with it (prompt/completion/reasoning/cached token counts) on deepseek-v4-flash, glm5.3-flash, qwen3.6, mimo-v2.5 and gemma4, and a real pi session then recorded token counts where it recorded zeros. pi-ai only sends stream_options when this is not false, and the sanitizer forwards it when the model declares true, so chat models opt in by default and usage is reported (issue #4). A model that does not report streaming usage can still opt out per model with a models.json compat override (supportsUsageInStreaming: false); the sanitizer then strips stream_options and the payload stays strict.",
-	"input includes image: NaN serves the Vision-Exp variant ('takes images as input', https://nan.builders/docs/models; the image_url content-parts in https://nan.builders/openapi.json list deepseek-v4-flash among the vision models). models.dev provider nan also lists text+image now (DeepSeek V4.1 Flash entry, checked 2026-09-13; its 2026-09-07 snapshot listed text only), so this override is kept as a pin for the vision capability rather than as a divergence.",
+	"input includes image: NaN serves the Vision-Exp variant ('takes images as input', https://nan.builders/docs/models; the image_url content-parts in https://nan.builders/openapi.json list deepseek-v4-flash among the vision models). models.dev provider nan also lists text+image now (DeepSeek V4.1 Flash entry, checked 2026-09-13; its 2026-09-07 snapshot listed text only), so this override is kept as a pin for the vision capability rather than as a divergence. reasoning_effort_values=[]: the model decides per-request how much to reason (https://nan.builders/docs/models, checked 2026-09-25).",
+	"manual-only: \"mimo-v2.6-flash\" not yet on models.dev provider nan (omnimodal model (text, image, audio input) served by NaN, not yet listed on models.dev provider nan (checked 2026-09-25); included so the live /models refresh does not hand it UNKNOWN_MODEL_LIMITS. Same limits as mimo-v2.5: 1,048,576 / 131,072 / 1.0B monthly quota per member. Reasoning: accepted, depth not adjustable. Tool calling: yes. Streaming: yes. Input modalities (pi-representable): text, image (audio not representable in pi's Model type).).",
 	"contextWindow 262,144: the earlier 1,000,000 override (maintainer-confirmed 2026-09-05) was withdrawn 2026-09-07 — the updated https://nan.builders/docs/models still states '262K token context, the model's native window' and models.dev agrees at 262,144; NaN docs are treated as the most reliable source (maintainer instruction, 2026-09-07)."
 ],
 } as const;

package/src/fetch-models.ts

@@ -39,6 +39,13 @@ export interface GeneratedModelEntry {
 	cost: { input: number; output: number; cacheRead: number; cacheWrite: number };
 	contextWindow: number;
 	maxTokens: number;
+	/**
+	 * Reasoning effort values as declared by NaN docs.
+	 * An empty array means the parameter is accepted but depth is not
+	 * adjustable by the user — the model manages its own reasoning depth.
+	 * An undefined array means the field was not set (legacy / uncatalogued).
+	 */
+	reasoningEffortValues?: string[];
 	/** Compat applied to every NaN-compatible model (LiteLLM-confirmed, see scripts/generate-models.ts). */
 	compat?: OpenAICompletionsCompat;
 	/** Provenance notes for values overriding models.dev or needing manual confirmation. */