Fix repetitive generation + context

.github/ISSUE_TEMPLATE/bug-report.yml

@@ -0,0 +1,141 @@
+name: "🪲 Bug Report"
+description: "File a bug report to help us improve"
+labels: ["fix"]
+body:
+
+    - type: "markdown"
+      attributes:
+          value: |
+              > [!IMPORTANT]
+              > To save time for both you and us, try follow these guidelines before submitting a new issue:
+              > 1. Check if there is an existing issue tracking your bug on our Github.
+              > 2. When unsure if your issue is an actual bug, first discuss it on a [Github discussion](https://github.com/mindverse/Second-Me/discussions/new?category=q-a) or other project communication channels.
+              > These steps avoid opening issues which are duplicate or not actual bugs.
+
+    - type: "checkboxes"
+      id: "environment-os"
+      attributes:
+          label: "Operating System"
+          description: "What is your operating system?"
+          options:
+            - label: "macOS"
+            - label: "Linux"
+            - label: "Windows"
+      validations:
+          required: true
+
+    - type: "checkboxes"
+      id: "deployment-method"
+      attributes:
+          label: "Deployment Method"
+          description: "How are you deploying the application?"
+          options:
+            - label: "Docker"
+            - label: "non-Docker"
+      validations:
+          required: true
+
+    - type: "checkboxes"
+      id: "cuda-usage"
+      attributes:
+          label: "CUDA Usage"
+          description: "Are you using a CUDA configuration?"
+          options:
+            - label: "Yes"
+            - label: "No"
+      validations:
+          required: true
+
+    - type: "markdown"
+      attributes:
+          value: |
+              ---
+              **If you are reporting an issue encountered during the training process, please also provide the following information:**
+
+    - type: "textarea"
+      id: "training-details"
+      attributes:
+          label: "Training Process Details (if applicable)"
+          description: "If this bug is related to the training process, please specify: \n1. Model size (e.g., 7B, 13B, etc.) \n2. Machine base configuration (RAM size and VRAM size, e.g., 32GB RAM, 16GB VRAM)."
+          placeholder: "e.g., Model: 7B, RAM: 64GB, VRAM: 24GB"
+      validations:
+          required: false
+
+    - type: "markdown"
+      attributes:
+          value: |
+              ---
+
+    - type: "input"
+      id: "version"
+      attributes:
+          label: "Second-Me version"
+          description: "Please specify the version of Second-Me you are using (e.g., commit hash, release tag, or 'latest master'). If unsure, please indicate that."
+      validations:
+          required: true
+
+    - type: "textarea"
+      id: "description"
+      attributes:
+          label: "Describe the bug"
+          description: "What is the problem? A clear and concise description of the bug."
+      validations:
+          required: true
+
+    - type: "textarea"
+      id: "current"
+      attributes:
+          label: "Current Behavior"
+          description: "What actually happened?\n\n
+                        Please include full errors, uncaught exceptions, stack traces, screenshots, and other relevant logs (e.g., from `log/backend.log` if applicable)."
+      validations:
+          required: true
+
+    - type: "textarea"
+      id: "expected"
+      attributes:
+          label: "Expected Behavior"
+          description: "What did you expect to happen?"
+      validations:
+          required: true
+
+    - type: "textarea"
+      id: "reproduction"
+      attributes:
+          label: "Reproduction Steps"
+          description: "Detail the steps needed to reproduce the issue. This can include a self-contained, concise snippet of
+                        code, if applicable.\n\n
+                        For more complex issues, provide a link to a repository with the smallest sample that reproduces
+                        the bug.\n
+                        If the issue can be replicated without code, please provide a clear, step-by-step description of
+                        the actions or conditions necessary to reproduce it. Any screenshots are also appreciated.\n
+                        Avoid including business logic or unrelated details, as this makes diagnosis more difficult.\n\n
+                        Whether it's a sequence of actions, code samples, or specific conditions, ensure that the steps
+                        are clear enough to be easily followed and replicated."
+      validations:
+          required: true
+
+    - type: "textarea"
+      id: "workaround"
+      attributes:
+          label: "Possible Workaround"
+          description: "If you find any workaround for this problem - please, provide it here."
+      validations:
+          required: false
+
+    - type: "textarea"
+      id: "context"
+      attributes:
+          label: "Additional Information"
+          description: "Anything else that might be relevant for troubleshooting this bug.\n
+                        Providing context helps us come up with a solution that is most useful in the real-world use case."
+      validations:
+          required: false
+
+    - type: "input"
+      id: "discussion_link"
+      attributes:
+          label: "Link to related Github discussion or issue"
+          description: "If there's an existing GitHub discussion or issue related to this bug, please link it here."
+      validations:
+          required: false

.github/ISSUE_TEMPLATE/feature-request.yml

@@ -0,0 +1,54 @@
+name: "🙋 Feature Request"
+description: "Use this template to request new feature or suggest an idea for Second-Me"
+labels: ["upgrade"]
+body:
+    - type: "markdown"
+      attributes:
+          value: |
+              > [!IMPORTANT]
+              > To save time for both you and us, try follow these guidelines before submitting a feature request:
+              > 1. Check if there is an existing feature request that is similar to your on our Github.
+              > 2. We encourage you to first discuss your idea on a [Github discussion](https://github.com/mindverse/Second-Me/discussions/categories/ideas) or the **#ideas** channel of our [Discord server](https://discord.gg/GpWHQNUwrg).
+              > This step helps in understanding the new feature and determining if it's can be implemented at all.
+              Only proceed with this report if your idea was approved after the GitHub/Discord discussion.
+
+    - type: "textarea"
+      id: "description"
+      attributes:
+          label: "Describe the feature"
+          description: "A clear and concise description of the feature you are proposing."
+      validations:
+          required: true
+
+    - type: "textarea"
+      id: "use-case"
+      attributes:
+          label: "Use Case"
+          description: "Why do you need this feature? Provide real world use cases, the more the better."
+      validations:
+          required: true
+
+    - type: "textarea"
+      id: "solution"
+      attributes:
+          label: "Proposed Solution"
+          description: "Suggest how to implement the new feature. Please include prototype/sketch/reference implementation."
+      validations:
+          required: false
+
+    - type: "textarea"
+      id: "additional_info"
+      attributes:
+          label: "Additional Information"
+          description: "Any additional information you would like to provide - links, screenshots, etc."
+      validations:
+          required: false
+
+    - type: "input"
+      id: "discussion_link"
+      attributes:
+          label: "Link to Discord or Github discussion"
+          description: "Provide a link to the first message of feature request's discussion on Discord or Github.\n
+                        This will help to keep history of why this feature request exists."
+      validations:
+          required: false

lpm_kernel/api/services/local_llm_service.py

@@ -112,10 +112,7 @@ def start_server(self, model_path: str, use_gpu: bool = True) -> bool:
                 server_path,
                 "-m", model_path,
                 "--host", "0.0.0.0",
-                "--port", "8080",
-                "--ctx-size", "2048",     # Default context size (adjust based on needs)
-                "--parallel", "2",        # Enable request parallelism
-                "--cont-batching"         # Enable continuous batching
+                "--port", "8080"
             ]
 
             # Set up environment with CUDA variables to ensure GPU detection