pi-ollama-cloud 0.12.1 → 0.12.2

package/CHANGELOG.md

@@ -2,6 +2,10 @@
 
 All notable changes to this project will be documented in this file.
 
+## [0.12.2] - 2026-09-27
+
+- Refresh the model catalog for the September 25, 2026 retirements (`deepseek-v4-flash:0731`, `glm-5.1`, `qwen3.5:397b`): dropped from the generated catalog and pricing, 20 -> 17 models. Recommended replacements per Ollama: `deepseek-v4.1-flash`, `glm-5.3`, and `glm-5.3-flash` / `deepseek-v4.1-flash`.
+
 ## [0.12.1] - 2026-09-14
 
 - Omit empty `openRouterRouting` / `vercelGatewayRouting` from `buildCompat` (set to `undefined`, not `{}`): pi-ai reads the raw `model.compat` and treats `{}` as truthy, sending a stray `provider: {}` on every Ollama chat completion. Fixes #60. Thanks @0xbentang (#61).

package/models.generated.ts

@@ -1,49 +1,11 @@
 // Auto-generated by scripts/generate-models.ts
 // Do not edit manually.
-// Generated: 2026-09-14T10:27:20.856Z
-// Model count: 20
+// Generated: 2026-09-27T00:52:07.773Z
+// Model count: 17
 
 import type { ProviderModelConfig } from "@earendil-works/pi-coding-agent";
 
 export const GENERATED_MODELS: ProviderModelConfig[] = [
-  {
-    id: "deepseek-v4-flash:0731",
-    name: "deepseek-v4-flash:0731",
-    compat: {
-      maxTokensField: "max_tokens",
-      requiresAssistantAfterToolResult: false,
-      requiresReasoningContentOnAssistantMessages: false,
-      requiresThinkingAsText: false,
-      requiresToolResultName: false,
-      sendSessionAffinityHeaders: false,
-      supportsDeveloperRole: false,
-      supportsLongCacheRetention: false,
-      supportsReasoningEffort: true,
-      supportsStore: false,
-      supportsStrictMode: false,
-      supportsUsageInStreaming: true,
-      thinkingFormat: "openai",
-      zaiToolStream: false,
-    },
-    contextWindow: 1048576,
-    cost: {
-      cacheRead: 0.014,
-      cacheWrite: 0,
-      input: 0.44,
-      output: 1.32,
-    },
-    input: ["text"],
-    maxTokens: 65536,
-    reasoning: true,
-    thinkingLevelMap: {
-      high: "high",
-      low: null,
-      medium: null,
-      minimal: null,
-      off: "none",
-      xhigh: "max",
-    },
-  },
   {
     id: "deepseek-v4-pro:0813",
     name: "deepseek-v4-pro:0813",
@@ -158,44 +120,6 @@ export const GENERATED_MODELS: ProviderModelConfig[] = [
       xhigh: null,
     },
   },
-  {
-    id: "glm-5.1",
-    name: "glm-5.1",
-    compat: {
-      maxTokensField: "max_tokens",
-      requiresAssistantAfterToolResult: false,
-      requiresReasoningContentOnAssistantMessages: false,
-      requiresThinkingAsText: false,
-      requiresToolResultName: false,
-      sendSessionAffinityHeaders: false,
-      supportsDeveloperRole: false,
-      supportsLongCacheRetention: false,
-      supportsReasoningEffort: true,
-      supportsStore: false,
-      supportsStrictMode: false,
-      supportsUsageInStreaming: true,
-      thinkingFormat: "openai",
-      zaiToolStream: false,
-    },
-    contextWindow: 202752,
-    cost: {
-      cacheRead: 0.2,
-      cacheWrite: 0,
-      input: 1,
-      output: 3.2,
-    },
-    input: ["text"],
-    maxTokens: 131072,
-    reasoning: true,
-    thinkingLevelMap: {
-      high: null,
-      low: null,
-      medium: "medium",
-      minimal: null,
-      off: "none",
-      xhigh: null,
-    },
-  },
   {
     id: "glm-5.2",
     name: "glm-5.2",
@@ -720,42 +644,4 @@ export const GENERATED_MODELS: ProviderModelConfig[] = [
       xhigh: null,
     },
   },
-  {
-    id: "qwen3.5:397b",
-    name: "qwen3.5:397b",
-    compat: {
-      maxTokensField: "max_tokens",
-      requiresAssistantAfterToolResult: false,
-      requiresReasoningContentOnAssistantMessages: false,
-      requiresThinkingAsText: false,
-      requiresToolResultName: false,
-      sendSessionAffinityHeaders: false,
-      supportsDeveloperRole: false,
-      supportsLongCacheRetention: false,
-      supportsReasoningEffort: true,
-      supportsStore: false,
-      supportsStrictMode: false,
-      supportsUsageInStreaming: true,
-      thinkingFormat: "openai",
-      zaiToolStream: false,
-    },
-    contextWindow: 262144,
-    cost: {
-      cacheRead: 0.6,
-      cacheWrite: 0,
-      input: 0.6,
-      output: 3.6,
-    },
-    input: ["text", "image"],
-    maxTokens: 65536,
-    reasoning: true,
-    thinkingLevelMap: {
-      high: null,
-      low: null,
-      medium: "medium",
-      minimal: null,
-      off: "none",
-      xhigh: null,
-    },
-  },
 ];

package/package.json

@@ -1,6 +1,6 @@
 {
   "name": "pi-ollama-cloud",
-  "version": "0.12.1",
+  "version": "0.12.2",
   "type": "module",
   "keywords": [
     "pi-package"

package/pricing.generated.ts

@@ -1,7 +1,7 @@
 // Auto-generated by scripts/generate-pricing.ts
 // Do not edit manually.
-// Generated: 2026-09-14T10:27:19.243Z
-// Model count: 20
+// Generated: 2026-09-27T00:52:06.074Z
+// Model count: 17
 
 export interface ModelPrice {
   input: number;
@@ -11,11 +11,9 @@ export interface ModelPrice {
 }
 
 export const MODEL_PRICING: Record<string, ModelPrice> = {
-  "deepseek-v4-flash:0731": { input: 0.44, output: 1.32, cacheRead: 0.014, cacheWrite: 0 },
   "deepseek-v4-pro:0813": { input: 1.32, output: 3.96, cacheRead: 0.044, cacheWrite: 0 },
   "deepseek-v4.1-flash": { input: 0.3, output: 1.2, cacheRead: 0.006, cacheWrite: 0 },
   "gemma4:31b": { input: 0.14, output: 0.4, cacheRead: 0.05, cacheWrite: 0 },
-  "glm-5.1": { input: 1, output: 3.2, cacheRead: 0.2, cacheWrite: 0 },
   "glm-5.2": { input: 1.4, output: 4.4, cacheRead: 0.26, cacheWrite: 0 },
   "glm-5.3": { input: 1.4, output: 4.4, cacheRead: 0.26, cacheWrite: 0 },
   "glm-5.3-flash": { input: 0.15, output: 0.5, cacheRead: 0.03, cacheWrite: 0 },
@@ -30,5 +28,4 @@ export const MODEL_PRICING: Record<string, ModelPrice> = {
   "nemotron-3-nano:30b": { input: 0.06, output: 0.24, cacheRead: 0.06, cacheWrite: 0 },
   "nemotron-3-super": { input: 0.015, output: 0.6, cacheRead: 0.015, cacheWrite: 0 },
   "nemotron-3-ultra": { input: 0.1, output: 3, cacheRead: 0.1, cacheWrite: 0 },
-  "qwen3.5:397b": { input: 0.6, output: 3.6, cacheRead: 0.6, cacheWrite: 0 },
 };