notebook-intelligence 5.2.1__tar.gz → 5.3.0a1__tar.gz

{notebook_intelligence-5.2.1 → notebook_intelligence-5.3.0a1}/PKG-INFO

@@ -1,6 +1,6 @@
 Metadata-Version: 2.4
 Name: notebook_intelligence
-Version: 5.2.1
+Version: 5.3.0a1
 Summary: AI coding assistant for JupyterLab
 Project-URL: Homepage, https://github.com/plmbr/notebook-intelligence
 Project-URL: Bug Tracker, https://github.com/plmbr/notebook-intelligence/issues
@@ -835,6 +835,12 @@ Long Claude turns surface an elapsed-time counter and a heartbeat-driven pulse w
 
 In Claude mode, workspace files attached as chat context arrive as `@`-mention pointers rather than inlined file contents. Claude's Read tool fetches them on demand, which means images, large files, and notebooks (cell-aware) now work where the older content-injection path silently truncated or skipped them.
 
+#### Usage footer
+
+Enable **Show usage after each turn** in the Settings dialog to append a small footer under each Claude-mode reply with the turn's duration, token counts (with a cached-input breakdown), and cost — for example `12.3s · 45.2K in (38.1K cached) / 1.2K out · $0.0842`. It is off by default.
+
+The cost figure comes from the Claude Code CLI, priced from Anthropic's public list rates. It is shown only when NBI is configured with a direct Anthropic API key on the default endpoint, and is omitted otherwise — on a subscription login (where the marginal cost is effectively $0), an enterprise-negotiated contract, or a custom **Base URL** (proxy, gateway, or non-Anthropic endpoint) — since the list-price figure would not match your actual billing. Duration and token counts are always shown.
+
 #### Claude Code launcher tile
 
 When the Claude CLI is on `PATH`, the JupyterLab launcher (the panel that opens with new tabs) shows a **Claude Code** tile alongside the standard kernel launchers. Clicking it opens a session picker; search across past transcripts and resume one in a fresh terminal, or start a new session in the file browser's active subdirectory. Session IDs are copyable from the picker for paste into a `claude --resume <id>` command.
@@ -1119,7 +1125,7 @@ c.NotebookIntelligence.enable_chat_feedback = True
 jupyter lab --NotebookIntelligence.enable_chat_feedback=true
 ```
 
-The feedback fires an in-process `telemetry` event. Nothing leaves the process by default — see the [admin guide](docs/admin-guide.md#chat-feedback-event-hook) for how to wire it into your observability stack.
+The feedback fires an in-process `telemetry` event. Nothing leaves the process by default. See the [admin guide](docs/admin-guide.md#telemetry-events) for the full set of telemetry events and how to wire them into your observability stack.
 
 The thumbs buttons reveal on hover by default. To keep them always visible, enable:
 

{notebook_intelligence-5.2.1 → notebook_intelligence-5.3.0a1}/PRIVACY.md

@@ -62,9 +62,9 @@ The encrypted GitHub token uses a default password (`nbi-access-token-password`)
 
 ## Telemetry
 
-NBI does not collect telemetry, send analytics, or report usage.
+NBI has no central server and sends no telemetry, analytics, or usage data to any external service.
 
-The `enable_chat_feedback` traitlet (off by default) emits an internal `telemetry` event when a user gives thumbs-up/down feedback in chat. The event is **emitted in-process only** — nothing leaves the process unless you write a custom handler that listens for it. See [`docs/admin-guide.md`](docs/admin-guide.md#chat-feedback-event-hook).
+Internally, NBI emits `telemetry` events that signal feature usage: chat, inline completion, and cell inline chat lifecycle events (including when a suggestion is accepted or dismissed), plus thumbs-up/down chat feedback when `enable_chat_feedback` is on. These events are **emitted in-process only**. By default nothing listens for them, so they go nowhere and never leave the process; an administrator can register a listener to collect them. See [`docs/admin-guide.md`](docs/admin-guide.md#telemetry-events).
 
 ## Reproducibility caveat
 

{notebook_intelligence-5.2.1 → notebook_intelligence-5.3.0a1}/README.md

@@ -117,6 +117,12 @@ Long Claude turns surface an elapsed-time counter and a heartbeat-driven pulse w
 
 In Claude mode, workspace files attached as chat context arrive as `@`-mention pointers rather than inlined file contents. Claude's Read tool fetches them on demand, which means images, large files, and notebooks (cell-aware) now work where the older content-injection path silently truncated or skipped them.
 
+#### Usage footer
+
+Enable **Show usage after each turn** in the Settings dialog to append a small footer under each Claude-mode reply with the turn's duration, token counts (with a cached-input breakdown), and cost — for example `12.3s · 45.2K in (38.1K cached) / 1.2K out · $0.0842`. It is off by default.
+
+The cost figure comes from the Claude Code CLI, priced from Anthropic's public list rates. It is shown only when NBI is configured with a direct Anthropic API key on the default endpoint, and is omitted otherwise — on a subscription login (where the marginal cost is effectively $0), an enterprise-negotiated contract, or a custom **Base URL** (proxy, gateway, or non-Anthropic endpoint) — since the list-price figure would not match your actual billing. Duration and token counts are always shown.
+
 #### Claude Code launcher tile
 
 When the Claude CLI is on `PATH`, the JupyterLab launcher (the panel that opens with new tabs) shows a **Claude Code** tile alongside the standard kernel launchers. Clicking it opens a session picker; search across past transcripts and resume one in a fresh terminal, or start a new session in the file browser's active subdirectory. Session IDs are copyable from the picker for paste into a `claude --resume <id>` command.
@@ -401,7 +407,7 @@ c.NotebookIntelligence.enable_chat_feedback = True
 jupyter lab --NotebookIntelligence.enable_chat_feedback=true
 ```
 
-The feedback fires an in-process `telemetry` event. Nothing leaves the process by default — see the [admin guide](docs/admin-guide.md#chat-feedback-event-hook) for how to wire it into your observability stack.
+The feedback fires an in-process `telemetry` event. Nothing leaves the process by default. See the [admin guide](docs/admin-guide.md#telemetry-events) for the full set of telemetry events and how to wire them into your observability stack.
 
 The thumbs buttons reveal on hover by default. To keep them always visible, enable:
 

{notebook_intelligence-5.2.1 → notebook_intelligence-5.3.0a1}/docs/admin-guide.md

@@ -21,7 +21,7 @@ This guide covers deploying Notebook Intelligence at scale — JupyterHub, KubeS
 - [Restricting features for managed deployments](#restricting-features-for-managed-deployments)
 - [Multi-tenancy and per-team scoping](#multi-tenancy-and-per-team-scoping)
 - [Managed Claude Skills token](#managed-claude-skills-token)
-- [Chat feedback event hook](#chat-feedback-event-hook)
+- [Telemetry events](#telemetry-events)
 - [HTTP API surface](#http-api-surface)
 - [Failure modes](#failure-modes)
 - [Version matrix](#version-matrix)
@@ -643,13 +643,43 @@ The reconciler handles skill name collisions between manifests and user-authored
 
 ---
 
-## Chat feedback event hook
+## Telemetry events
 
-When `enable_chat_feedback = True`, NBI emits a `telemetry` event in-process whenever a user gives thumbs-up/down feedback in chat. The event payload includes the rating, the prompt, the response, and the model.
+NBI emits `telemetry` events in-process to signal feature usage. The events are **emitted in-process only**: by default nothing listens for them, so they go nowhere and never leave the process. To collect them (for example, to forward usage into an internal observability stack such as Kafka or an OTel collector), write a JupyterLab extension that registers a listener through NBI's `INotebookIntelligence` token and forwards what it receives. Payload shapes are not currently considered stable API; if you build on them, pin to a specific NBI version.
 
-The event is **emitted in-process only**. Nothing leaves the process unless you write a custom handler that listens for it. The payload shape is not currently considered stable API; if you build on it, pin to a specific NBI version.
+Each event has a `type` (the identifier below) and a `data` payload carrying the relevant model and context. Auto-complete (inline completion) and cell inline chat are reported as separate event families, so a listener can tell the two features apart by `type` alone.
 
-To pipe feedback into your internal observability stack (Kafka, OTel collector), write an extension that registers a listener for the `telemetry` event and forwards it.
+Auto-complete:
+
+| Event `type`                 | Fires when                                                    |
+| ---------------------------- | ------------------------------------------------------------- |
+| `inline-completion-request`  | A ghost-text completion is requested as the user types.       |
+| `inline-completion-response` | A suggestion is returned (carries `timeElapsed`).             |
+| `inline-completion-accepted` | The user accepts a suggestion (Tab or the completer toolbar). |
+
+Cell inline chat:
+
+| Event `type`            | Fires when                                                          |
+| ----------------------- | ------------------------------------------------------------------- |
+| `inline-chat-request`   | The user submits an inline-chat prompt (carries the `prompt`).      |
+| `inline-chat-response`  | A generation completes (carries `timeElapsed`).                     |
+| `inline-chat-accepted`  | Generated code is applied, with `mode` = `review` or `auto-insert`. |
+| `inline-chat-dismissed` | The popover is closed after code was shown but never applied.       |
+
+Chat and feedback:
+
+| Event `type`                     | Fires when                                                                                 |
+| -------------------------------- | ------------------------------------------------------------------------------------------ |
+| `chat-request` / `chat-response` | A message is sent to / answered by the chat sidebar.                                       |
+| `feedback`                       | The user gives thumbs-up/down on a chat response (`sentiment` = `positive` or `negative`). |
+
+NBI also emits request events for the chat sidebar's code and output actions (`generate-code-request`, `explain-this-request`, `fix-this-code-request`, `explain-this-output-request`, `troubleshoot-this-output-request`, `output-follow-up-request`).
+
+The `inline-completion-*`, `inline-chat-*`, and chat/action events fire whenever those features are used; they are not gated by any setting. To measure how often auto-complete suggestions are taken, compare `inline-completion-accepted` against `inline-completion-response`; the gap is the ignore rate. Only the `feedback` event is gated, by `enable_chat_feedback` (off by default), which also controls the thumbs-up/down UI:
+
+```python
+c.NotebookIntelligence.enable_chat_feedback = True
+```
 
 The thumbs buttons reveal on hover by default. To keep them always visible, enable:
 
@@ -663,40 +693,40 @@ c.NotebookIntelligence.enable_chat_feedback_always_visible = True
 
 All routes live under `/notebook-intelligence/`. All require Jupyter authentication (XSRF token plus Jupyter login token) including the `/copilot` WebSocket upgrade, which now inherits Jupyter's `WebSocketMixin` + `JupyterHandler` so the same `allow_origin` and identity-provider checks that apply to REST handlers also apply to the chat WS endpoint. The labextension obtains these automatically. There is no admin-only route; access control runs through Jupyter Server itself.
 
-| Route                                                       | Method          | Purpose                                                                                                              |
-| ----------------------------------------------------------- | --------------- | -------------------------------------------------------------------------------------------------------------------- |
-| `/notebook-intelligence/capabilities`                       | GET             | Capabilities + tool/provider gate state.                                                                             |
-| `/notebook-intelligence/config`                             | GET/POST        | Read or update user-scope config.                                                                                    |
-| `/notebook-intelligence/update-provider-models`             | POST            | Refresh model list for a provider (e.g., Anthropic SDK refresh).                                                     |
-| `/notebook-intelligence/mcp-config-file`                    | GET/POST        | Read or write `~/.jupyter/nbi/mcp.json`.                                                                             |
-| `/notebook-intelligence/reload-mcp-servers`                 | POST            | Re-discover MCP servers without restarting JupyterLab.                                                               |
-| `/notebook-intelligence/emit-telemetry-event`               | POST            | Used by the frontend to emit `telemetry` events (e.g., chat feedback).                                               |
-| `/notebook-intelligence/gh-login-status`                    | GET             | GitHub Copilot login state.                                                                                          |
-| `/notebook-intelligence/gh-login`                           | POST            | Begin GitHub Copilot device-flow login.                                                                              |
-| `/notebook-intelligence/gh-logout`                          | GET             | Sign out of GitHub Copilot.                                                                                          |
-| `/notebook-intelligence/copilot`                            | WS              | Streaming chat / inline-completion WebSocket.                                                                        |
-| `/notebook-intelligence/rules`                              | GET             | List discovered rules.                                                                                               |
-| `/notebook-intelligence/rules/<id>/toggle`                  | PUT             | Toggle a rule's `active` field.                                                                                      |
-| `/notebook-intelligence/rules/reload`                       | POST            | Manually reload all rules.                                                                                           |
-| `/notebook-intelligence/skills`                             | GET/POST        | List or create skills.                                                                                               |
-| `/notebook-intelligence/skills/context`                     | GET             | Skill context info for the active workspace.                                                                         |
-| `/notebook-intelligence/skills/import/preview`              | POST            | Preview a GitHub-hosted skill before installing.                                                                     |
-| `/notebook-intelligence/skills/import`                      | POST            | Install a GitHub-hosted skill (user-initiated).                                                                      |
-| `/notebook-intelligence/skills/reconcile`                   | POST            | Run the managed-skills reconciler. Returns 409 if `NBI_SKILLS_MANIFEST` is unset.                                    |
-| `/notebook-intelligence/skills/reconciler/stop`             | POST            | Incident-response kill switch. Stops the background reconciler without a server restart. Idempotent.                 |
-| `/notebook-intelligence/skills/<scope>/<name>`              | GET/PUT/DELETE  | Skill detail; managed skills are read-only.                                                                          |
-| `/notebook-intelligence/skills/<scope>/<name>/rename`       | POST            | Rename a skill (denied for managed skills).                                                                          |
-| `/notebook-intelligence/skills/<scope>/<name>/files`        | GET/POST/DELETE | Skill bundle file ops.                                                                                               |
-| `/notebook-intelligence/skills/<scope>/<name>/files/rename` | POST            | Rename a file inside a skill bundle.                                                                                 |
-| `/notebook-intelligence/upload-file`                        | POST            | Upload a file to attach as chat context (size and retention governed by `upload_max_mb` / `upload_retention_hours`). |
-| `/notebook-intelligence/claude-sessions`                    | GET             | List Claude Code sessions for the working directory.                                                                 |
-| `/notebook-intelligence/claude-sessions/resume`             | POST            | Resume a Claude session.                                                                                             |
-| `/notebook-intelligence/claude-mcp`                         | GET/POST        | List or add Claude-mode MCP servers. Gated by `claude_mcp_management_policy`.                                        |
-| `/notebook-intelligence/claude-mcp/<scope>/<name>`          | GET/DELETE      | Get or remove a Claude-mode MCP server by scope (user/project/local) and name.                                       |
-| `/notebook-intelligence/plugins`                            | GET/POST        | List or install Claude plugins. Gated by `claude_plugins_management_policy`.                                         |
-| `/notebook-intelligence/plugins/<scope>/<name>`             | POST/DELETE     | Enable or disable (POST with `{"action": "enable"\|"disable"}`) or uninstall (DELETE) a plugin.                      |
-| `/notebook-intelligence/plugins/marketplace`                | GET/POST        | List or add plugin marketplaces. GitHub-sourced adds are gated by `allow_github_plugin_import`.                      |
-| `/notebook-intelligence/plugins/marketplace/<name>`         | DELETE          | Remove a plugin marketplace.                                                                                         |
+| Route                                                       | Method          | Purpose                                                                                                                                              |
+| ----------------------------------------------------------- | --------------- | ---------------------------------------------------------------------------------------------------------------------------------------------------- |
+| `/notebook-intelligence/capabilities`                       | GET             | Capabilities + tool/provider gate state.                                                                                                             |
+| `/notebook-intelligence/config`                             | GET/POST        | Read or update user-scope config.                                                                                                                    |
+| `/notebook-intelligence/update-provider-models`             | POST            | Refresh model list for a provider (e.g., Anthropic SDK refresh).                                                                                     |
+| `/notebook-intelligence/mcp-config-file`                    | GET/POST        | Read or write `~/.jupyter/nbi/mcp.json`.                                                                                                             |
+| `/notebook-intelligence/reload-mcp-servers`                 | POST            | Re-discover MCP servers without restarting JupyterLab.                                                                                               |
+| `/notebook-intelligence/emit-telemetry-event`               | POST            | Used by the frontend to emit `telemetry` events (chat feedback, inline completion and inline chat usage). See [Telemetry events](#telemetry-events). |
+| `/notebook-intelligence/gh-login-status`                    | GET             | GitHub Copilot login state.                                                                                                                          |
+| `/notebook-intelligence/gh-login`                           | POST            | Begin GitHub Copilot device-flow login.                                                                                                              |
+| `/notebook-intelligence/gh-logout`                          | GET             | Sign out of GitHub Copilot.                                                                                                                          |
+| `/notebook-intelligence/copilot`                            | WS              | Streaming chat / inline-completion WebSocket.                                                                                                        |
+| `/notebook-intelligence/rules`                              | GET             | List discovered rules.                                                                                                                               |
+| `/notebook-intelligence/rules/<id>/toggle`                  | PUT             | Toggle a rule's `active` field.                                                                                                                      |
+| `/notebook-intelligence/rules/reload`                       | POST            | Manually reload all rules.                                                                                                                           |
+| `/notebook-intelligence/skills`                             | GET/POST        | List or create skills.                                                                                                                               |
+| `/notebook-intelligence/skills/context`                     | GET             | Skill context info for the active workspace.                                                                                                         |
+| `/notebook-intelligence/skills/import/preview`              | POST            | Preview a GitHub-hosted skill before installing.                                                                                                     |
+| `/notebook-intelligence/skills/import`                      | POST            | Install a GitHub-hosted skill (user-initiated).                                                                                                      |
+| `/notebook-intelligence/skills/reconcile`                   | POST            | Run the managed-skills reconciler. Returns 409 if `NBI_SKILLS_MANIFEST` is unset.                                                                    |
+| `/notebook-intelligence/skills/reconciler/stop`             | POST            | Incident-response kill switch. Stops the background reconciler without a server restart. Idempotent.                                                 |
+| `/notebook-intelligence/skills/<scope>/<name>`              | GET/PUT/DELETE  | Skill detail; managed skills are read-only.                                                                                                          |
+| `/notebook-intelligence/skills/<scope>/<name>/rename`       | POST            | Rename a skill (denied for managed skills).                                                                                                          |
+| `/notebook-intelligence/skills/<scope>/<name>/files`        | GET/POST/DELETE | Skill bundle file ops.                                                                                                                               |
+| `/notebook-intelligence/skills/<scope>/<name>/files/rename` | POST            | Rename a file inside a skill bundle.                                                                                                                 |
+| `/notebook-intelligence/upload-file`                        | POST            | Upload a file to attach as chat context (size and retention governed by `upload_max_mb` / `upload_retention_hours`).                                 |
+| `/notebook-intelligence/claude-sessions`                    | GET             | List Claude Code sessions for the working directory.                                                                                                 |
+| `/notebook-intelligence/claude-sessions/resume`             | POST            | Resume a Claude session.                                                                                                                             |
+| `/notebook-intelligence/claude-mcp`                         | GET/POST        | List or add Claude-mode MCP servers. Gated by `claude_mcp_management_policy`.                                                                        |
+| `/notebook-intelligence/claude-mcp/<scope>/<name>`          | GET/DELETE      | Get or remove a Claude-mode MCP server by scope (user/project/local) and name.                                                                       |
+| `/notebook-intelligence/plugins`                            | GET/POST        | List or install Claude plugins. Gated by `claude_plugins_management_policy`.                                                                         |
+| `/notebook-intelligence/plugins/<scope>/<name>`             | POST/DELETE     | Enable or disable (POST with `{"action": "enable"\|"disable"}`) or uninstall (DELETE) a plugin.                                                      |
+| `/notebook-intelligence/plugins/marketplace`                | GET/POST        | List or add plugin marketplaces. GitHub-sourced adds are gated by `allow_github_plugin_import`.                                                      |
+| `/notebook-intelligence/plugins/marketplace/<name>`         | DELETE          | Remove a plugin marketplace.                                                                                                                         |
 
 The extension respects `c.ServerApp.base_url`. Behind JupyterHub at `/user/<name>/` everything still works because JupyterLab proxies routes through the per-user base URL automatically.
 

{notebook_intelligence-5.2.1 → notebook_intelligence-5.3.0a1}/notebook_intelligence/_version.py

@@ -1,4 +1,4 @@
 # This file is auto-generated by Hatchling. As such, do not:
 #   - modify
 #   - track in version control e.g. be sure to add to .gitignore
-__version__ = VERSION = '5.2.1'
+__version__ = VERSION = '5.3.0a1'

{notebook_intelligence-5.2.1 → notebook_intelligence-5.3.0a1}/notebook_intelligence/api.py

@@ -141,6 +141,8 @@ class ChatRequest:
     tool_selection: RequestToolSelection = None
     command: str = ''
     prompt: str = ''
+    language: str = ''
+    kernel_name: str = ''
     chat_history: list[dict] = None
     cancel_token: CancelToken = None
     # NEW: Add context for rule evaluation
@@ -909,7 +911,10 @@ class TelemetryEventType(str, Enum):
     InlineChatRequest = 'inline-chat-request'
     ChatResponse = 'chat-response'
     InlineChatResponse = 'inline-chat-response'
+    InlineChatAccepted = 'inline-chat-accepted'
+    InlineChatDismissed = 'inline-chat-dismissed'
     InlineCompletionResponse = 'inline-completion-response'
+    InlineCompletionAccepted = 'inline-completion-accepted'
     Feedback = 'feedback'
 
 class TelemetryEvent:

{notebook_intelligence-5.2.1 → notebook_intelligence-5.3.0a1}/notebook_intelligence/base_chat_participant.py

@@ -102,6 +102,14 @@ class CreateNewNotebookTool(Tool):
                                     }
                                 }
                             }
+                        },
+                        "language": {
+                            "type": "string",
+                            "description": "Programming language for the notebook kernel, e.g. python or r"
+                        },
+                        "kernel_name": {
+                            "type": "string",
+                            "description": "Jupyter kernel name to use when creating the notebook"
                         }
                     },
                     "required": [],
@@ -120,8 +128,13 @@ class CreateNewNotebookTool(Tool):
 
     async def handle_tool_call(self, request: ChatRequest, response: ChatResponse, tool_context: dict, tool_args: dict) -> str:
         cell_sources = tool_args.get('cell_sources', [])
+        language = tool_args.get('language') or request.language or 'python'
+        kernel_name = tool_args.get('kernel_name') or request.kernel_name or ''
     
-        ui_cmd_response = await response.run_ui_command('notebook-intelligence:create-new-notebook-from-py', {'code': ''})
+        ui_cmd_response = await response.run_ui_command(
+            'notebook-intelligence:create-new-notebook',
+            {'code': '', 'language': language, 'kernelName': kernel_name}
+        )
         file_path = ui_cmd_response['path']
 
         for cell_source in cell_sources:
@@ -133,7 +146,55 @@ class CreateNewNotebookTool(Tool):
                 source = cell_source.get('source', '')
                 ui_cmd_response = await response.run_ui_command('notebook-intelligence:add-code-cell-to-notebook', {'code': source, 'path': file_path})
 
-        return "Notebook created successfully at {file_path}"
+        return f"Notebook created successfully at {file_path}"
+
+
+class ListAvailableNotebookKernelsTool(Tool):
+    @property
+    def name(self) -> str:
+        return "list_available_notebook_kernels"
+
+    @property
+    def title(self) -> str:
+        return "List available notebook kernels"
+
+    @property
+    def tags(self) -> list[str]:
+        return ["default-participant-tool"]
+
+    @property
+    def description(self) -> str:
+        return "Lists Jupyter kernels available in the current frontend environment"
+
+    @property
+    def schema(self) -> dict:
+        return {
+            "type": "function",
+            "function": {
+                "name": self.name,
+                "description": self.description,
+                "strict": True,
+                "parameters": {
+                    "type": "object",
+                    "properties": {},
+                    "required": [],
+                    "additionalProperties": False,
+                },
+            },
+        }
+
+    def pre_invoke(self, request: ChatRequest, tool_args: dict) -> Union[ToolPreInvokeResponse, None]:
+        return ToolPreInvokeResponse(
+            f"Calling tool '{self.name}'",
+            detail={"title": "Parameters", "content": json.dumps(tool_args)},
+        )
+
+    async def handle_tool_call(self, request: ChatRequest, response: ChatResponse, tool_context: dict, tool_args: dict) -> str:
+        ui_cmd_response = await response.run_ui_command(
+            'notebook-intelligence:list-available-notebook-kernels',
+            {}
+        )
+        return json.dumps(ui_cmd_response)
 
 class AddMarkdownCellToNotebookTool(Tool):
     def __init__(self, auto_approve: bool = False):
@@ -379,7 +440,8 @@ class BaseChatParticipant(ChatParticipant):
         chat_model = request.host.chat_model
         messages = request.chat_history.copy()
         messages.pop()
-        messages.insert(0, {"role": "system", "content": f"You are an assistant that creates Python code which will be used in a Jupyter notebook. Generate only Python code and some comments for the code. You should return the code directly, without wrapping it inside ```."})
+        language = request.language or 'python'
+        messages.insert(0, {"role": "system", "content": f"You are an assistant that creates {language} code which will be used in a Jupyter notebook. Generate only {language} code and some comments for the code. You should return the code directly, without wrapping it inside ```."})
         messages.append({"role": "user", "content": f"Generate code for: {request.prompt}"})
         generated = chat_model.completions(messages)
         code = generated['choices'][0]['message']['content']
@@ -440,8 +502,17 @@ class BaseChatParticipant(ChatParticipant):
     async def handle_ask_mode_chat_request(self, request: ChatRequest, response: ChatResponse, options: dict = {}) -> None:
         chat_model = request.host.chat_model
         if request.command == 'newNotebook':
+            language = request.language or 'python'
+            kernel_name = request.kernel_name or ''
             # create a new notebook
-            ui_cmd_response = await response.run_ui_command('notebook-intelligence:create-new-notebook-from-py', {'code': ''})
+            ui_cmd_response = await response.run_ui_command(
+                'notebook-intelligence:create-new-notebook',
+                {
+                    'code': '',
+                    'language': language,
+                    'kernelName': kernel_name,
+                }
+            )
             file_path = ui_cmd_response['path']
 
             code = await self.generate_code_cell(request)
@@ -494,6 +565,8 @@ class BaseChatParticipant(ChatParticipant):
     def get_tool_by_name(name: str) -> Tool:
         if name == "create_new_notebook":
             return CreateNewNotebookTool()
+        elif name == "list_available_notebook_kernels":
+            return ListAvailableNotebookKernelsTool()
         elif name == "add_markdown_cell_to_notebook":
             return AddMarkdownCellToNotebookTool()
         elif name == "add_code_cell_to_notebook":