Switch ollama api endpoint from /api/generate to /api/chat (#304)

* 3.0.11

* build

* docs: update ollama usage readme (#301)

Signed-off-by: Albert Simon <albert.simon.sge@mango.com>
Co-authored-by: Albert Simon <albert.simon.sge@mango.com>

* 🚨 BREAKING CHANGES 🚨

- feat(engine/ollama): add support for local models and change prompt format to improve AI performance
+ fix(engine/ollama): fix issue with local model not responding correctly to requests

The commit message is now more concise, clear, and informative. It also includes a breaking changes section that highlights the significant changes made in this commit.

---------

Signed-off-by: Albert Simon <albert.simon.sge@mango.com>
Co-authored-by: di-sukharev <dim.sukharev@gmail.com>
Co-authored-by: Albert Simon <47634918+willyw0nka@users.noreply.github.com>
Co-authored-by: Albert Simon <albert.simon.sge@mango.com>
Co-authored-by: Константин Шуткин <shutkin-kn@mosmetro.ru>

out/github-action.cjs

@@ -27486,12 +27486,11 @@ var api = new OpenAi();
 var OllamaAi = class {
   async generateCommitMessage(messages) {
     const model = "mistral";
-    let prompt = messages.map((x2) => x2.content).join("\n");
-    prompt += "Summarize above git diff in 10 words or less";
-    const url2 = "http://localhost:11434/api/generate";
+    const url2 = "http://localhost:11434/api/chat";
     const p2 = {
       model,
-      prompt,
+      messages,
+      options: { temperature: 0, top_p: 0.1 },
       stream: false
     };
     try {
@@ -27500,8 +27499,8 @@ var OllamaAi = class {
           "Content-Type": "application/json"
         }
       });
-      const answer = response.data?.response;
-      return answer;
+      const message = response.data.message;
+      return message?.content;
     } catch (err) {
       const message = err.response?.data?.error ?? err.message;
       throw new Error("local model issues. details: " + message);