From aca94361d15da7c73fcfe5e4e2eed7cd84f9fb96 Mon Sep 17 00:00:00 2001
From: Spencer Gilbert <me@spencergilbert.dev>
Date: Mon, 28 Sep 2026 13:58:22 -0400
Subject: [PATCH] [pi] Add gufo provider over its OpenAI chat endpoint

Serve qwen3.8-flash from desktop:8080 and enable it for model cycling.
The endpoint needs no compat scaffolding: pi's URL auto-detection picks
openai reasoning_effort, max_completion_tokens, developer role, and
streamed usage, all of which gufo honors. Only supportsStrictMode is
stated, since gufo compiles strict tool schemas and pi omits strict by
default.

All seven thinking levels work, so the opencode-go gating does not
apply. Keep samplingParams clear: gufo rejects logit_bias, typical_p,
tfs_z, mirostat*, dynatemp_*, xtc_*, dry_*, samplers, and draft fields
with unsupported_sampling.
---
 pi/models.json         | 33 +++++++++++++++++++++++++++++++++
 pi/settings.linux.json |  1 +
 2 files changed, 34 insertions(+)

diff --git a/pi/models.json b/pi/models.json
index e5618ef..8c5a67f 100644
--- a/pi/models.json
+++ b/pi/models.json
@@ -1,5 +1,38 @@
 {
   "providers": {
+    "gufo": {
+      "baseUrl": "http://desktop:8080/v1",
+      "api": "openai-completions",
+      "apiKey": "no-key",
+      "models": [
+        {
+          "id": "qwen3.8-flash",
+          "name": "Qwen3.8 Flash",
+          "reasoning": true,
+          "input": ["text", "image"],
+          "cost": {
+            "input": 0,
+            "output": 0,
+            "cacheRead": 0,
+            "cacheWrite": 0
+          },
+          "contextWindow": 262144,
+          "maxTokens": 131072,
+          "thinkingLevelMap": {
+            "off": "off",
+            "minimal": "minimal",
+            "low": "low",
+            "medium": "medium",
+            "high": "high",
+            "xhigh": "xhigh",
+            "max": "max"
+          },
+          "compat": {
+            "supportsStrictMode": true
+          }
+        }
+      ]
+    },
     "qwen-token-plan": {
       "modelOverrides": {
         "qwen3.8-flash": {
diff --git a/pi/settings.linux.json b/pi/settings.linux.json
index e052902..95960d5 100644
--- a/pi/settings.linux.json
+++ b/pi/settings.linux.json
@@ -6,6 +6,7 @@
   "defaultProvider": "qwen-token-plan",
   "defaultModel": "qwen3.8-flash",
   "enabledModels": [
+    "gufo/**",
     "opencode-go/**",
     "qwen-token-plan/**"
   ],
-- 
2.51.2