pi-makora-provider 1.12.2 → 1.12.3

package/README.md

@@ -23,12 +23,7 @@ _DeepSeek V4, Kimi K2.7 Code, GLM 5.2, Qwen 3.6 for [pi](https://github.com/eare
 | Gemma 4 26B A4B | `google/gemma-4-26B-A4B` | No |  |
 | GLM 5.2 FP8 | `zai-org/GLM-5.2-FP8` | Yes | off via top-level `reasoning_effort: "none"` (only lever GLM responds to; `enable_thinking`/`thinking`/chat_template_kwargs toggles are ignored); effort `high`/`max` only (minimal/low/medium clamp to `high`); multi-turn continuity via `clear_thinking` (false when thinking on = preserve, true when off = clear; `preserve_thinking` is inert for GLM) injected via onPayload; returns `reasoning` field |
 | GLM 5.2 NVFP4 | `zai-org/GLM-5.2-NVFP4` | Yes | off via top-level `reasoning_effort: "none"` (only lever GLM responds to; `enable_thinking`/`thinking`/chat_template_kwargs toggles are ignored); effort `high`/`max` only (minimal/low/medium clamp to `high`); multi-turn continuity via `clear_thinking` (false when thinking on = preserve, true when off = clear; `preserve_thinking` is inert for GLM) injected via onPayload; returns `reasoning` field |
-| GPT-OSS 120B | `openai/gpt-oss-120b` | No |  |
-| Kimi K2.7 Code | `moonshotai/Kimi-K2.7-Code` | Yes | on/off via namespaced `chat_template_kwargs.thinking` (toggled with thinking switch); `preserve_thinking` (toggled) for multi-turn continuity; onPayload aliases each assistant message's `reasoning` → `reasoning_content` (Kimi's template reads `reasoning_content` but pi-ai sends `reasoning`); returns `reasoning` field. `reasoning_effort` is not emitted (Kimi's template reads namespaced `thinking`, not `reasoning_effort`) |
 | Llama 3.3 70B FP8 | `amd/Llama-3.3-70B-Instruct-FP8-KV` | No |  |
-| Llama 3.3 70B Instruct | `meta-llama/Llama-3.3-70B-Instruct` | No |  |
-| Qwen 3.6 27B NVFP4 | `unsloth/Qwen3.6-27B-NVFP4` | Yes | off via top-level `reasoning_effort: "none"`; `preserve_thinking` (toggled with thinking switch) injected via onPayload for multi-turn continuity; returns `reasoning` field |
-| Qwen 3.6 35B A3B NVFP4 | `unsloth/Qwen3.6-35B-A3B-NVFP4` | Yes | off via top-level `reasoning_effort: "none"`; `preserve_thinking` (toggled with thinking switch) injected via onPayload for multi-turn continuity; returns `reasoning` field |
 <!-- MODELS_TABLE_END -->
 
 ## Installation

package/deprecated-models.json

@@ -0,0 +1 @@
+{}

package/index.ts

@@ -52,6 +52,7 @@ import { clampThinkingLevel, streamOpenAICompletions } from "@earendil-works/pi-
 import modelsData from "./models.json" with { type: "json" };
 import customModelsData from "./custom-models.json" with { type: "json" };
 import patchData from "./patch.json" with { type: "json" };
+import deprecatedData from "./deprecated-models.json" with { type: "json" };
 import { registerNanCollapseGuard, nanCanary, canaryEnabled, isGuardedModel } from "./nan-collapse-guard.js";
 import fs from "fs";
 import path from "path";
@@ -549,6 +550,35 @@ export function streamMakora(
   });
 }
 
+// Grace period for delisted models. When the provider API stops listing a
+// model, update-models.js moves its last-known definition into
+// deprecated-models.json (stamped with deprecatedAt) instead of dropping it.
+// For 14 days the model keeps working here so in-flight sessions and saved
+// model settings do not break; afterwards it is evicted permanently.
+const DEPRECATED_MODEL_TTL_MS = 14 * 24 * 60 * 60 * 1000;
+
+// Grace-period deprecated models with deprecation metadata stripped.
+function activeDeprecatedModels(): JsonModel[] {
+  const now = Date.now();
+  const result: JsonModel[] = [];
+  for (const entry of Object.values(deprecatedData as Record<string, JsonModel & { deprecatedAt?: string }>)) {
+    if (!entry?.id) continue;
+    const removedAt = Date.parse(entry.deprecatedAt ?? "");
+    if (Number.isNaN(removedAt) || now - removedAt > DEPRECATED_MODEL_TTL_MS) continue;
+    const model = { ...entry } as JsonModel & { deprecatedAt?: string };
+    delete model.deprecatedAt;
+    result.push(model);
+  }
+  return result;
+}
+
+// Append grace-period deprecated models the list does not already have (live data wins).
+function withDeprecated(models: JsonModel[]): JsonModel[] {
+  const seen = new Set(models.map((m) => m.id));
+  const extras = activeDeprecatedModels().filter((m) => !seen.has(m.id));
+  return extras.length > 0 ? [...models, ...extras] : models;
+}
+
 // Extension Entry Point
 
 const PROVIDER_ID = "makora";
@@ -564,7 +594,7 @@ export default function (pi: ExtensionAPI) {
   }
 
   function builtModels(): JsonModel[] {
-    return buildModels(embeddedModels, customModels, patches, activeOverrides());
+    return withDeprecated(buildModels(embeddedModels, customModels, patches, activeOverrides()));
   }
 
   // apiKey resolution order: auth.json ("makora" key) → MAKORA_OPTIMIZE_TOKEN env var.

package/models.json

@@ -62,111 +62,6 @@
       "maxTokensField": "max_completion_tokens"
     }
   },
-  {
-    "id": "meta-llama/Llama-3.3-70B-Instruct",
-    "name": "Llama 3.3 70B Instruct",
-    "reasoning": false,
-    "input": [
-      "text"
-    ],
-    "cost": {
-      "input": 0,
-      "output": 0,
-      "cacheRead": 0,
-      "cacheWrite": 0
-    },
-    "contextWindow": 4096,
-    "maxTokens": 0,
-    "compat": {
-      "supportsDeveloperRole": false,
-      "supportsStore": false,
-      "maxTokensField": "max_completion_tokens"
-    }
-  },
-  {
-    "id": "moonshotai/Kimi-K2.7-Code",
-    "name": "Kimi K2.7 Code",
-    "reasoning": false,
-    "input": [
-      "text"
-    ],
-    "cost": {
-      "input": 0,
-      "output": 0,
-      "cacheRead": 0,
-      "cacheWrite": 0
-    },
-    "contextWindow": 262144,
-    "maxTokens": 0,
-    "compat": {
-      "supportsDeveloperRole": false,
-      "supportsStore": false,
-      "maxTokensField": "max_completion_tokens"
-    }
-  },
-  {
-    "id": "openai/gpt-oss-120b",
-    "name": "GPT-OSS 120B",
-    "reasoning": false,
-    "input": [
-      "text"
-    ],
-    "cost": {
-      "input": 0,
-      "output": 0,
-      "cacheRead": 0,
-      "cacheWrite": 0
-    },
-    "contextWindow": 131072,
-    "maxTokens": 0,
-    "compat": {
-      "supportsDeveloperRole": false,
-      "supportsStore": false,
-      "maxTokensField": "max_completion_tokens"
-    }
-  },
-  {
-    "id": "unsloth/Qwen3.6-27B-NVFP4",
-    "name": "Qwen 3.6 27B NVFP4",
-    "reasoning": false,
-    "input": [
-      "text"
-    ],
-    "cost": {
-      "input": 0,
-      "output": 0,
-      "cacheRead": 0,
-      "cacheWrite": 0
-    },
-    "contextWindow": 262144,
-    "maxTokens": 0,
-    "compat": {
-      "supportsDeveloperRole": false,
-      "supportsStore": false,
-      "maxTokensField": "max_completion_tokens"
-    }
-  },
-  {
-    "id": "unsloth/Qwen3.6-35B-A3B-NVFP4",
-    "name": "Qwen 3.6 35B A3B NVFP4",
-    "reasoning": false,
-    "input": [
-      "text"
-    ],
-    "cost": {
-      "input": 0,
-      "output": 0,
-      "cacheRead": 0,
-      "cacheWrite": 0
-    },
-    "contextWindow": 262144,
-    "maxTokens": 0,
-    "compat": {
-      "supportsDeveloperRole": false,
-      "supportsStore": false,
-      "maxTokensField": "max_completion_tokens"
-    }
-  },
   {
     "id": "zai-org/GLM-5.2-FP8",
     "name": "GLM 5.2 FP8",

package/package.json

@@ -1,6 +1,6 @@
 {
   "name": "pi-makora-provider",
-  "version": "1.12.2",
+  "version": "1.12.3",
   "description": "Makora provider extension for pi - Access DeepSeek V4, GLM 5.2, Kimi K2.7 Code, Llama 3.3, Qwen 3.6, and more through the Makora inference API",
   "type": "module",
   "main": "index.ts",
@@ -23,6 +23,7 @@
     "index.ts",
     "nan-collapse-guard.ts",
     "models.json",
+    "deprecated-models.json",
     "custom-models.json",
     "patch.json",
     "README.md",
@@ -34,8 +35,8 @@
     ]
   },
   "devDependencies": {
-    "@earendil-works/pi-agent-core": "^0.80.2",
-    "@earendil-works/pi-coding-agent": "^0.80.2",
+    "@earendil-works/pi-agent-core": "^0.83.0",
+    "@earendil-works/pi-coding-agent": "^0.83.0",
     "vitest": "^4.1.9"
   },
   "scripts": {