🤖 refactor: address review comments

- Make cache keys more generic and future-proof
- Cache Ollama binary separately for instant cached runs
- Update model examples to popular models (gpt-oss, qwen3-coder)

Changes:
- Split Ollama caching into binary + models for better performance
- Only install Ollama if binary is not cached (saves time)
- Update docs to reference gpt-oss:20b, gpt-oss:120b, qwen3-coder:30b

_Generated with `cmux`_

Author: ammar-agent

.github/workflows/ci.yml

@@ -99,25 +99,37 @@ jobs:
 
       - uses: ./.github/actions/setup-cmux
 
+      - name: Cache Ollama binary
+        id: cache-ollama-binary
+        uses: actions/cache@v4
+        with:
+          path: /usr/local/bin/ollama
+          key: ${{ runner.os }}-ollama-binary-v1
+          restore-keys: |
+            ${{ runner.os }}-ollama-binary-
+
       - name: Cache Ollama models
         id: cache-ollama-models
         uses: actions/cache@v4
         with:
           path: ~/.ollama/models
-          key: ${{ runner.os }}-ollama-gpt-oss-20b-v1
+          key: ${{ runner.os }}-ollama-models-v1
           restore-keys: |
-            ${{ runner.os }}-ollama-gpt-oss-
+            ${{ runner.os }}-ollama-models-
 
       - name: Install Ollama
+        if: steps.cache-ollama-binary.outputs.cache-hit != 'true'
         run: |
           curl -fsSL https://ollama.com/install.sh | sh
+
+      - name: Start Ollama and pull models
+        run: |
           # Start Ollama service in background
           ollama serve &
           # Wait for Ollama to be ready
           timeout 30 sh -c 'until curl -s http://localhost:11434/api/tags > /dev/null 2>&1; do sleep 1; done'
           echo "Ollama is ready"
-          # Pull the gpt-oss:20b model for tests (this may take a few minutes on first run)
-          # Subsequent runs will use cached model
+          # Pull the gpt-oss:20b model for tests (cached after first run)
           ollama pull gpt-oss:20b
           echo "Model pulled successfully"
 

docs/models.md

@@ -31,16 +31,15 @@ TODO: add issue link here.
 
 Run models locally with Ollama. No API key required:
 
-- `ollama:llama3.2:7b`
-- `ollama:llama3.2:13b`
-- `ollama:codellama:7b`
-- `ollama:qwen2.5:7b`
+- `ollama:gpt-oss:20b`
+- `ollama:gpt-oss:120b`
+- `ollama:qwen3-coder:30b`
 - Any model from the [Ollama Library](https://ollama.com/library)
 
 **Setup:**
 
 1. Install Ollama from [ollama.com](https://ollama.com)
-2. Pull a model: `ollama pull llama3.2:7b`
+2. Pull a model: `ollama pull gpt-oss:20b`
 3. Configure in `~/.cmux/providers.jsonc`:
 
 ```jsonc