pi-lilac-provider 1.8.0 → 1.8.2

package/README.md

@@ -74,10 +74,8 @@ pi
 | Model | Context | Vision | Reasoning | Input $/M | Cache Read $/M | Output $/M |
 |-------|---------|--------|-----------|-----------|-----------------|------------|
 | Gemma 4 | 262K | ✅ | ✅ | $0.11 | — | $0.35 |
-| GLM 5.1 | 203K | ❌ | ✅ | $0.90 | $0.27 | $3.00 |
 | GLM 5.2 | 524K | ❌ | ✅ | $0.90 | $0.27 | $3.00 |
 | Kimi K2.6 | 262K | ✅ | ✅ | $0.70 | $0.20 | $3.50 |
-| MiniMax M2.7 | 205K | ❌ | ✅ | $0.30 | $0.06 | $1.20 |
 | MiniMax M3 | 1.0M | ✅ | ✅ | $0.28 | $0.05 | $1.10 |
 
 *Costs are per million tokens. Prices subject to change — check [getlilac.com](https://getlilac.com/) for current pricing.*
@@ -121,7 +119,7 @@ model's chat template honors differs per family. The provider uses pi's
 Kimi K2.6, GLM 5.1, Gemma 4, and MiniMax M2.7 use the forward-compatible form
 that sends **both** `thinking` and `enable_thinking`, so whichever key the
 template honors is set. GLM 5.2 additionally maps pi's thinking levels to
-`reasoning_effort` (`high` = lower-latency, `xhigh` = `max`). MiniMax M3 uses
+`reasoning_effort` (`high` = lower-latency, `max` = deepest). MiniMax M3 uses
 the `thinking_mode` enum, exposed as three pi thinking levels: `off` →
 `disabled` (never think), `minimal` → `adaptive` (the model decides), `high` →
 `enabled` (always think). Pi starts at `off` (`disabled`); cycle to `minimal`

package/index.ts

@@ -21,7 +21,7 @@
  * MiniMax M3). The forward-compatible form sends BOTH `thinking` and
  * `enable_thinking` so whichever key the template honors is set:
  *   { chat_template_kwargs: { thinking: <bool>, enable_thinking: <bool> } }
- * GLM 5.2 adds `reasoning_effort` (high = lower-latency, xhigh = max) via a
+ * GLM 5.2 adds `reasoning_effort` (high for lower-latency, max for deep) via a
  * thinkingLevelMap. MiniMax M3 maps to the `thinking_mode` enum as three pi
  * thinking levels — off→disabled, minimal→adaptive (model decides), high→enabled
  * — so adaptive is selectable via pi's Shift+Tab cycle (off→minimal→high). Pi
@@ -99,7 +99,7 @@ interface JsonDiscount {
   creditMultiplier: number;
 }
 
-// Maps pi's thinking levels (off, minimal, low, medium, high, xhigh) to the
+// Maps pi's thinking levels (off, minimal, low, medium, high, xhigh, max) to the
 // provider-specific effort string sent on the wire. A `null` value marks a
 // level as unsupported — clampThinkingLevel skips it when resolving the
 // user's selection. Mirrors pi-ai's ThinkingLevelMap shape.
@@ -110,6 +110,7 @@ type ThinkingLevelMap = {
   medium?: string | null;
   high?: string | null;
   xhigh?: string | null;
+  max?: string | null;
 };
 
 // A chat_template_kwargs value, mirroring pi-ai's ChatTemplateKwargSchema. Scalar
@@ -1252,7 +1253,7 @@ export default function (pi: ExtensionAPI) {
           },
           {
             id: "preserved-thinking",
-            label: "Preserved thinking",
+            label: "Preserved thinking ›",
             description: "Per-model Preserve Thinking / Clear Thinking (full-history reasoning). Preserve Thinking keeps all turns' reasoning; Clear Thinking lets the template drop older reasoning (saves tokens, can hurt multi-turn recall / cause overthinking).",
             currentValue: "configure",
             submenu: (_currentValue: string, subDone: (v?: string) => void) => {

package/models.json

@@ -23,29 +23,6 @@
       "zaiToolStream": true
     }
   },
-  {
-    "id": "zai-org/glm-5.1",
-    "name": "GLM 5.1",
-    "reasoning": true,
-    "input": [
-      "text"
-    ],
-    "cost": {
-      "input": 0.9,
-      "output": 3,
-      "cacheRead": 0.27,
-      "cacheWrite": 0
-    },
-    "contextWindow": 202752,
-    "maxTokens": 131072,
-    "compat": {
-      "supportsDeveloperRole": false,
-      "supportsStore": false,
-      "maxTokensField": "max_completion_tokens",
-      "thinkingFormat": "qwen-chat-template",
-      "zaiToolStream": true
-    }
-  },
   {
     "id": "zai-org/glm-5.2",
     "name": "GLM 5.2",
@@ -92,28 +69,6 @@
       "zaiToolStream": true
     }
   },
-  {
-    "id": "minimaxai/minimax-m2.7",
-    "name": "MiniMax M2.7",
-    "reasoning": true,
-    "input": [
-      "text"
-    ],
-    "cost": {
-      "input": 0.3,
-      "output": 1.2,
-      "cacheRead": 0.055,
-      "cacheWrite": 0
-    },
-    "contextWindow": 204800,
-    "maxTokens": 204800,
-    "compat": {
-      "supportsDeveloperRole": true,
-      "supportsStore": false,
-      "maxTokensField": "max_completion_tokens",
-      "thinkingFormat": "qwen-chat-template"
-    }
-  },
   {
     "id": "minimaxai/minimax-m3",
     "name": "MiniMax M3",

package/package.json

@@ -1,6 +1,6 @@
 {
   "name": "pi-lilac-provider",
-  "version": "1.8.0",
+  "version": "1.8.2",
   "description": "Lilac provider extension for pi - Access Kimi K2.6, GLM 5.1, and Gemma 4 models through Lilac's OpenAI-compatible API on idle GPUs",
   "type": "module",
   "main": "index.ts",

package/patch.json

@@ -53,7 +53,7 @@
       "low": "high",
       "medium": "high",
       "high": "high",
-      "xhigh": "max"
+      "max": "max"
     }
   },
   "google/gemma-4-31b-it": {

package/scripts/test-model-overrides.ts

@@ -66,7 +66,6 @@ function eq<T>(actual: T, expected: T, message: string) {
 
 const KIMI = "moonshotai/kimi-k2.6";
 const GLM52 = "zai-org/glm-5.2";
-const GLM51 = "zai-org/glm-5.1";
 
 // ─── applyModelOverride ────────────────────────────────────────────────────────
 
@@ -240,16 +239,6 @@ function find(models: any[], id: string): any {
   assert(glm.compat.chatTemplateKwargs.clear_thinking === false, "non-overridden clear_thinking survives a thinkingLevelMap-only override");
 }
 
-{
-  // Override on glm-5.1 toggles clear_thinking (patch sets false); other compat survives
-  const overrides = { [GLM51]: { compat: { chatTemplateKwargs: { clear_thinking: true } } } } as any;
-  const models = buildModels(modelsData, customModelsData, patchData, overrides);
-  const glm = find(models, GLM51);
-  assert(glm.compat.chatTemplateKwargs.clear_thinking === true, "override wins over patch: glm-5.1 clear_thinking -> true");
-  assert((glm.compat.chatTemplateKwargs as any).thinking?.$var === "thinking.enabled", "override deep-merges: glm-5.1 thinking $var key survives");
-  assert(glm.compat.zaiToolStream === true, "override deep-merges: glm-5.1 zaiToolStream survives");
-}
-
 {
   // Override for an unknown id is a no-op (adds no models)
   const before = buildModels(modelsData, customModelsData, patchData, {});

package/scripts/test-preserved-thinking.ts

@@ -194,25 +194,15 @@ console.log("\n=== GLM 5.2 on the wire (real pi-ai) ===");
   const high = await wire("zai-org/glm-5.2", "high");
   eq(high.chat_template_kwargs, { enable_thinking: true, reasoning_effort: "high", clear_thinking: false },
     "glm-5.2 @ high → enable_thinking+reasoning_effort AND clear_thinking false");
-  const xhigh = await wire("zai-org/glm-5.2", "xhigh");
-  eq(xhigh.chat_template_kwargs, { enable_thinking: true, reasoning_effort: "max", clear_thinking: false },
-    "glm-5.2 @ xhigh → reasoning_effort max, clear_thinking false");
+  const max = await wire("zai-org/glm-5.2", "max");
+  eq(max.chat_template_kwargs, { enable_thinking: true, reasoning_effort: "max", clear_thinking: false },
+    "glm-5.2 @ max → reasoning_effort max, clear_thinking false");
   const off = await wire("zai-org/glm-5.2", "off");
   eq(off.chat_template_kwargs, { enable_thinking: false, clear_thinking: false },
     "glm-5.2 @ off → reasoning_effort omitted (omitWhenOff), clear_thinking false persists");
 }
 
-console.log("\n=== GLM 5.1 on the wire (real pi-ai) ===");
-{
-  const high = await wire("zai-org/glm-5.1", "high");
-  eq(high.chat_template_kwargs, { thinking: true, enable_thinking: true, clear_thinking: false },
-    "glm-5.1 @ high → thinking+enable_thinking true AND clear_thinking false");
-  const off = await wire("zai-org/glm-5.1", "off");
-  eq(off.chat_template_kwargs, { thinking: false, enable_thinking: false, clear_thinking: false },
-    "glm-5.1 @ off → thinking false but clear_thinking false persists");
-}
-
-console.log("\n=== Gemma 4 / MiniMax (no family-wide preserve flag — regression guard) ===");
+console.log("\n=== Gemma / MiniMax (no family-wide preserve flag — regression guard) ===");
 {
   const gemma = await wire("google/gemma-4-31b-it", "high");
   eq(gemma.chat_template_kwargs, { thinking: true, enable_thinking: true },
@@ -224,11 +214,6 @@ console.log("\n=== Gemma 4 / MiniMax (no family-wide preserve flag — regressio
   eq(m3.chat_template_kwargs, { thinking_mode: "enabled" },
     "minimax-m3 @ high → only thinking_mode (no preserve/clear flag)");
   falsy(m3.chat_template_kwargs?.preserve_thinking, "minimax-m3 has no preserve_thinking");
-
-  const m27 = await wire("minimaxai/minimax-m2.7", "high");
-  eq(m27.chat_template_kwargs, { thinking: true, enable_thinking: true },
-    "minimax-m2.7 @ high → only thinking/enable_thinking (no preserve/clear flag)");
-  falsy(m27.chat_template_kwargs?.clear_thinking, "minimax-m2.7 has no clear_thinking");
 }
 
 globalThis.fetch = originalFetch;