small update

.opencode/AGENTS.md

@@ -0,0 +1,61 @@
+# AGENTS.md
+
+Behavioral guidelines to reduce common LLM coding mistakes. Merge with project-specific instructions as needed.
+
+**Tradeoff:** These guidelines bias toward caution over speed. For trivial tasks, use judgment.
+
+## 1. Think Before Coding
+
+**Don't assume. Don't hide confusion. Surface tradeoffs.**
+
+Before implementing:
+- State your assumptions explicitly. If uncertain, ask.
+- If multiple interpretations exist, present them - don't pick silently.
+- If a simpler approach exists, say so. Push back when warranted.
+- If something is unclear, stop. Name what's confusing. Ask.
+
+## 2. Simplicity First
+
+**Minimum code that solves the problem. Nothing speculative.**
+
+- No features beyond what was asked.
+- No abstractions for single-use code.
+- No "flexibility" or "configurability" that wasn't requested.
+- No error handling for impossible scenarios.
+- If you write 200 lines and it could be 50, rewrite it.
+
+Ask yourself: "Would a senior engineer say this is overcomplicated?" If yes, simplify.
+
+## 3. Surgical Changes
+
+**Touch only what you must. Clean up only your own mess.**
+
+When editing existing code:
+- Don't "improve" adjacent code, comments, or formatting.
+- Don't refactor things that aren't broken.
+- Match existing style, even if you'd do it differently.
+- If you notice unrelated dead code, mention it - don't delete it.
+
+When your changes create orphans:
+- Remove imports/variables/functions that YOUR changes made unused.
+- Don't remove pre-existing dead code unless asked.
+
+The test: Every changed line should trace directly to the user's request.
+
+## 4. Goal-Driven Execution
+
+**Define success criteria. Loop until verified.**
+
+Transform tasks into verifiable goals:
+- "Add validation" → "Write tests for invalid inputs, then make them pass"
+- "Fix the bug" → "Write a test that reproduces it, then make it pass"
+- "Refactor X" → "Ensure tests pass before and after"
+
+For multi-step tasks, state a brief plan:
+```
+1. [Step] → verify: [check]
+2. [Step] → verify: [check]
+3. [Step] → verify: [check]
+```
+
+Strong success criteria let you loop independently. Weak criteria ("make it work") require constant clarification.

Makefile

@@ -4,10 +4,10 @@ OPENCODE_DIR := $(HOME)/.config/opencode
 REPO_DIR := $(shell pwd)
 
 # Items to symlink
-ITEMS := skills tools agents
+ITEMS := skills tools agents AGENTS.md
 
 # LLM services to manage
-LLM_SERVICES := odin
+LLM_SERVICES := qwen
 
 PLIST_PATH := ~/Library/LaunchAgents
 

models.yaml

@@ -1,26 +0,0 @@
-manager:
-  memory_budget: 450
-  contention_policy:
-    strategy: wait_then_preempt
-    wait_timeout_s: 45
-    preempt_after_s: 15
-
-models:
-  - name: Qwen-Coder-Next
-    model: mlx-community/Qwen3-Coder-Next-4bit
-    estimated_memory_gb: 50
-    reasoning_parser: qwen3
-
-  - name: Qwen3.6
-    model: mlx-community/Qwen3.6-35B-A3B-6bit
-    estimated_memory_gb: 40
-    reasoning_parser: qwen3
-
-  - name: gemma
-    model: mlx-community/gemma-4-31b-it-8bit
-    estimated_memory_gb: 40
-    reasoning_parser: gemma4
-
-  - name: MiniMax-M3
-    model: pipenetwork/MiniMax-M3-MLX-mixed-3_6bit
-    estimated_memory_gb: 200

sample_opencode.json

@@ -1,33 +1,31 @@
 {
   "$schema": "https://opencode.ai/config.json",
+  "model": "qwen/mlx-community/Qwen3.6-35B-A3B-6bit",
+  "compaction": {
+    "auto": true,
+    "prune": true,
+    "reserved": 32768
+  },
   "provider": {
-    "odin": {
+    "qwen": {
       "npm": "@ai-sdk/anthropic",
-      "name": "Odin",
+      "name": "Qwen 3.8",
       "options": {
-        "baseURL": "http://192.168.2.49:12000/v1",
-        "apiKey": "changeme"
+        "baseURL": "http://192.168.2.49:12010/v1",
+        "apiKey": "changeme",
+        "timeout": false,
+        "chunkTimeout": 300000
       },
       "models": {
-        "Qwen-Coder-Next": {
-          "name": "Qwen-Coder-Next",
+        "mlx-community/Qwen3.8-27B-8bit": {
+          "name": "Qwen 3.8 27B 8-bit",
           "tool_call": true,
-          "options": {
-            "temperature": 1.0,
-            "top_p": 0.95
+          "reasoning": true,
+
+          "limit": {
+            "context": 262144,
+            "output": 81920
           }
-        },
-        "Qwen3.6": {
-          "name": "Qwen3.6",
-          "tool_call": true
-        },
-        "gemma": {
-          "name": "gemma",
-          "tool_call": true
-        },
-        "MiniMax-M3": {
-          "name": "MiniMax-M3",
-          "tool_call": true
         }
       }
     }