pi-fireworks-provider 1.5.4 → 1.5.6

package/README.md

@@ -15,7 +15,7 @@ _Kimi, MiniMax, GLM, DeepSeek, GPT-OSS — via Fireworks AI's Anthropic Messages
 
 ## Features
 
-- **43+ AI Models** including Kimi K2.5, MiniMax M2.5, GLM 4.5/4.7/5, DeepSeek V3.1/V3.2, DeepSeek V4 Flash, and GPT-OSS
+- **47+ AI Models** including Kimi K2.5, MiniMax M2.5, GLM 4.5/4.7/5, DeepSeek V3.1/V3.2, DeepSeek V4 Flash, and GPT-OSS
 - **Dual API support** via Fireworks AI's Anthropic Messages and OpenAI-compatible completions endpoints (per-model routing, matching pi core's Fireworks provider)
 - **Service tiers** — toggle Fireworks `priority` vs `standard` per request on supported models (with priority pricing reflected in cost tracking), via a keybinding, `/fireworks-tier`, and a footer status area
 - **Preserved thinking** — toggle Fireworks' `reasoning_history: "preserved"` so prior assistant reasoning is retained across turns (better multi-turn recall; uses more tokens), via the `/fireworks-settings` panel, with a model-select notification. Matches neuralwatt/makora's settings-only UX, adapted to Fireworks' single global `reasoning_history` knob
@@ -78,6 +78,7 @@ pi
 | DeepSeek V4 Flash 0731 | Text | 1.0M | 384K | $0.14 | $0.28 |
 | DeepSeek V4 Pro | Text | 1.0M | 384K | $1.74 | $3.48 |
 | DeepSeek V4 Pro (router) | Text | 1.0M | 384K | $1.74 | $3.48 |
+| DeepSeek-V4-Pro-0813 | Text | 1.0M | 0 | Free | Free |
 | Gemma 4 26B A4B IT | Text + Image | 262K | 33K | Free | Free |
 | Gemma 4 31B IT | Text + Image | 262K | 33K | Free | Free |
 | GLM 4.5 | Text | 131K | 131K | $0.55 | $2.19 |
@@ -110,11 +111,14 @@ pi
 | MiniMax-M2.5 | Text | 197K | 197K | $0.30 | $1.20 |
 | MiniMax-M2.7 | Text | 197K | 197K | $0.30 | $1.20 |
 | MiniMax-M3 | Text + Image | 512K | 512K | $0.30 | $1.20 |
+| Muse Glimmer 30B | Text + Image | 131K | 0 | Free | Free |
+| Nemotron Lightning 3.5 30B A3B | Text | 262K | 0 | Free | Free |
 | NVIDIA Nemotron 3 Ultra NVFP4 | Text | 262K | 66K | $0.60 | $2.40 |
 | Qwen 3.7 Plus | Text + Image | 262K | 66K | $0.40 | $1.60 |
 | Qwen3 8B | Text | 41K | 41K | $0.20 | $0.20 |
 | Qwen3 VL 30B A3B Instruct | Text + Image | 262K | 33K | $0.50 | $0.50 |
 | Qwen3 VL 30B A3B Thinking | Text + Image | 262K | 33K | $0.50 | $0.50 |
+| Qwen3.8-2.4T-A95B | Text | 262K | 0 | Free | Free |
 *Costs are per million tokens. Prices subject to change - check [fireworks.ai](https://fireworks.ai) for current pricing.*
 
 ## Service Tiers

package/custom-models.json

@@ -235,12 +235,19 @@
       "off": null,
       "minimal": null,
       "low": "low",
-      "medium": null,
+      "medium": "medium",
       "high": "high",
       "xhigh": null,
       "max": "max"
     },
     "compat": {
+      "supportsStore": false,
+      "supportsDeveloperRole": false,
+      "sendSessionAffinityHeaders": true,
+      "supportsLongCacheRetention": false,
+      "requiresReasoningContentOnAssistantMessages": true,
+      "thinkingFormat": "openai",
+      "deferredToolsMode": "kimi",
       "supportsReasoningEffort": true
     }
   }

package/deprecated-models.json

@@ -1 +1,19 @@
-{}
+{
+  "accounts/fireworks/models/qwen3p8-max": {
+    "id": "accounts/fireworks/models/qwen3p8-max",
+    "name": "Qwen3.8-2.4T-A95B",
+    "reasoning": false,
+    "input": [
+      "text"
+    ],
+    "cost": {
+      "input": 0,
+      "output": 0,
+      "cacheRead": 0,
+      "cacheWrite": 0
+    },
+    "contextWindow": 262144,
+    "maxTokens": 0,
+    "deprecatedAt": "2026-08-14T02:00:11.611Z"
+  }
+}

package/index.ts

@@ -1158,6 +1158,13 @@ export default function (pi: ExtensionAPI) {
     baseUrl: BASE_URL,
     apiKey: "$FIREWORKS_API_KEY",
     api: "openai-completions",
+    // Match pi core's bundled Fireworks catalog pins (pi-ai providers/data/fireworks.json)
+    compat: {
+      supportsStore: false,
+      supportsDeveloperRole: false,
+      sendSessionAffinityHeaders: true,
+      supportsLongCacheRetention: false,
+    },
     models: staleModels,
   });
 
@@ -1177,6 +1184,12 @@ export default function (pi: ExtensionAPI) {
             baseUrl: BASE_URL,
             apiKey: "$FIREWORKS_API_KEY",
             api: "openai-completions",
+            compat: {
+              supportsStore: false,
+              supportsDeveloperRole: false,
+              sendSessionAffinityHeaders: true,
+              supportsLongCacheRetention: false,
+            },
             models: buildModels(freshBase, customModels, patches),
           });
         }

package/models.json

@@ -79,6 +79,22 @@
     "contextWindow": 1048576,
     "maxTokens": 0
   },
+  {
+    "id": "accounts/fireworks/models/deepseek-v4-pro-0813",
+    "name": "DeepSeek-V4-Pro-0813",
+    "reasoning": false,
+    "input": [
+      "text"
+    ],
+    "cost": {
+      "input": 0,
+      "output": 0,
+      "cacheRead": 0,
+      "cacheWrite": 0
+    },
+    "contextWindow": 1048576,
+    "maxTokens": 0
+  },
   {
     "id": "accounts/fireworks/models/glm-4p5",
     "name": "GLM-4.5",
@@ -404,6 +420,23 @@
     "contextWindow": 512000,
     "maxTokens": 0
   },
+  {
+    "id": "accounts/fireworks/models/muse-glimmer-30b",
+    "name": "Muse Glimmer 30B",
+    "reasoning": false,
+    "input": [
+      "text",
+      "image"
+    ],
+    "cost": {
+      "input": 0,
+      "output": 0,
+      "cacheRead": 0,
+      "cacheWrite": 0
+    },
+    "contextWindow": 131072,
+    "maxTokens": 0
+  },
   {
     "id": "accounts/fireworks/models/nemotron-3-ultra-nvfp4",
     "name": "NVIDIA Nemotron 3 Ultra NVFP4",
@@ -420,6 +453,22 @@
     "contextWindow": 262144,
     "maxTokens": 0
   },
+  {
+    "id": "accounts/fireworks/models/nemotron-lightning-3p5-30b-a3b",
+    "name": "Nemotron Lightning 3.5 30B A3B",
+    "reasoning": false,
+    "input": [
+      "text"
+    ],
+    "cost": {
+      "input": 0,
+      "output": 0,
+      "cacheRead": 0,
+      "cacheWrite": 0
+    },
+    "contextWindow": 262144,
+    "maxTokens": 0
+  },
   {
     "id": "accounts/fireworks/models/qwen3-8b",
     "name": "Qwen3 8B",
@@ -436,6 +485,22 @@
     "contextWindow": 40960,
     "maxTokens": 0
   },
+  {
+    "id": "accounts/fireworks/models/qwen3p8-2p4t-a95b",
+    "name": "Qwen3.8-2.4T-A95B",
+    "reasoning": false,
+    "input": [
+      "text"
+    ],
+    "cost": {
+      "input": 0,
+      "output": 0,
+      "cacheRead": 0,
+      "cacheWrite": 0
+    },
+    "contextWindow": 262144,
+    "maxTokens": 0
+  },
   {
     "id": "accounts/fireworks/models/qwen3-vl-30b-a3b-instruct",
     "name": "Qwen3 VL 30B A3B Instruct",

package/package.json

@@ -1,18 +1,9 @@
 {
   "name": "pi-fireworks-provider",
-  "version": "1.5.4",
+  "version": "1.5.6",
   "description": "Fireworks AI provider extension for pi - Access Kimi, MiniMax, GLM, DeepSeek, and GPT-OSS models through the Fireworks AI API",
   "type": "module",
   "main": "index.ts",
-  "scripts": {
-    "clean": "echo 'nothing to clean'",
-    "build": "echo 'nothing to build'",
-    "check": "tsc --noEmit && vitest run && knip --no-gitignore",
-    "lint:dead": "knip --no-gitignore",
-    "test": "vitest run",
-    "test:watch": "vitest",
-    "update-models": "node scripts/update-models.js"
-  },
   "keywords": [
     "pi",
     "extension",
@@ -48,5 +39,13 @@
       "./index.ts"
     ]
   },
-  "packageManager": "pnpm@11.18.0"
-}
+  "scripts": {
+    "clean": "echo 'nothing to clean'",
+    "build": "echo 'nothing to build'",
+    "check": "tsc --noEmit && vitest run && knip --no-gitignore",
+    "lint:dead": "knip --no-gitignore",
+    "test": "vitest run",
+    "test:watch": "vitest",
+    "update-models": "node scripts/update-models.js"
+  }
+}

package/patch.json

@@ -188,7 +188,9 @@
     "maxTokens": 131072,
     "compat": {
       "supportsStore": false,
-      "supportsDeveloperRole": false
+      "supportsDeveloperRole": false,
+      "sendSessionAffinityHeaders": true,
+      "supportsLongCacheRetention": false
     }
   },
   "accounts/fireworks/models/gpt-oss-120b": {
@@ -532,6 +534,10 @@
     "contextWindow": 1048575,
     "maxTokens": 131072,
     "compat": {
+      "supportsStore": false,
+      "supportsDeveloperRole": false,
+      "sendSessionAffinityHeaders": true,
+      "supportsLongCacheRetention": false,
       "supportsReasoningEffort": true
     }
   },
@@ -711,12 +717,19 @@
       "off": null,
       "minimal": null,
       "low": "low",
-      "medium": null,
+      "medium": "medium",
       "high": "high",
       "xhigh": null,
       "max": "max"
     },
     "compat": {
+      "supportsStore": false,
+      "supportsDeveloperRole": false,
+      "sendSessionAffinityHeaders": true,
+      "supportsLongCacheRetention": false,
+      "requiresReasoningContentOnAssistantMessages": true,
+      "thinkingFormat": "openai",
+      "deferredToolsMode": "kimi",
       "supportsReasoningEffort": true
     }
   },