npcsh 0.3.29__py3-none-any.whl → 0.3.31__py3-none-any.whl

npcsh/shell.py

@@ -378,6 +378,7 @@ def main() -> None:
 
                 current_npc = result["current_npc"]
             output = result.get("output")
+
             conversation_id = result.get("conversation_id")
             model = result.get("model")
             provider = result.get("provider")
@@ -404,102 +405,115 @@ def main() -> None:
                 npc=npc_name,
                 attachments=attachments,
             )
-            if NPCSH_STREAM_OUTPUT and (
-                isgenerator(output)
-                or (hasattr(output, "__iter__") and hasattr(output, "__next__"))
-            ):
-                str_output = ""
-                buffer = ""
-                in_code = False
-                code_buffer = ""
 
-                for chunk in output:
-                    # Get chunk content based on provider
-                    if provider == "anthropic":
-                        chunk_content = (
-                            chunk.delta.text
-                            if chunk.type == "content_block_delta"
-                            else None
-                        )
-                    elif provider in ["openai", "deepseek", "openai-like"]:
-                        chunk_content = "".join(
-                            c.delta.content for c in chunk.choices if c.delta.content
-                        )
-                    elif provider == "ollama":
-                        chunk_content = chunk["message"]["content"]
-                    else:
-                        continue
+            str_output = ""
+            try:
+                if NPCSH_STREAM_OUTPUT and hasattr(output, "__iter__"):
+
+                    buffer = ""
+                    in_code = False
+                    code_buffer = ""
+
+                    for chunk in output:
+
+                        if provider == "anthropic":
+                            chunk_content = (
+                                chunk.delta.text
+                                if chunk.type == "content_block_delta"
+                                else None
+                            )
+                        elif provider in ["openai", "deepseek", "openai-like"]:
+                            chunk_content = "".join(
+                                c.delta.content
+                                for c in chunk.choices
+                                if c.delta.content
+                            )
+                        elif provider == "ollama":
+                            chunk_content = chunk["message"]["content"]
+                        else:
+                            continue
 
-                    if not chunk_content:
-                        continue
+                        if not chunk_content:
+                            continue
 
-                    str_output += chunk_content
+                        str_output += chunk_content
+                        # print(str_output, "str_output")
+                        # Process the content character by character
+                        for char in chunk_content:
+                            buffer += char
 
-                    # Process the content character by character
-                    for char in chunk_content:
-                        buffer += char
-
-                        # Check for triple backticks
-                        if buffer.endswith("```"):
-                            if not in_code:
-                                # Start of code block
-                                in_code = True
-                                # Print everything before the backticks
-                                print(buffer[:-3], end="")
-                                buffer = ""
-                                code_buffer = ""
+                            # Check for triple backticks
+                            if buffer.endswith("```"):
+                                if not in_code:
+                                    # Start of code block
+                                    in_code = True
+                                    # Print everything before the backticks
+                                    print(buffer[:-3], end="")
+                                    buffer = ""
+                                    code_buffer = ""
+                                else:
+                                    # End of code block
+                                    in_code = False
+                                    # Remove the backticks from the end of the buffer
+                                    buffer = buffer[:-3]
+                                    # Add buffer to code content and render
+                                    code_buffer += buffer
+
+                                    # Check for and strip language tag
+                                    if (
+                                        "\n" in code_buffer
+                                        and code_buffer.index("\n") < 15
+                                    ):
+                                        first_line, rest = code_buffer.split("\n", 1)
+                                        if (
+                                            first_line.strip()
+                                            and not "```" in first_line
+                                        ):
+                                            code_buffer = rest
+
+                                    # Render the code block
+                                    render_code_block(code_buffer)
+
+                                    # Reset buffers
+                                    buffer = ""
+                                    code_buffer = ""
+                            elif in_code:
+                                # Just add to code buffer
+                                code_buffer += char
+                                if len(buffer) >= 3:  # Keep buffer small while in code
+                                    buffer = buffer[-3:]
                             else:
-                                # End of code block
-                                in_code = False
-                                # Remove the backticks from the end of the buffer
-                                buffer = buffer[:-3]
-                                # Add buffer to code content and render
-                                code_buffer += buffer
-
-                                # Check for and strip language tag
-                                if "\n" in code_buffer and code_buffer.index("\n") < 15:
-                                    first_line, rest = code_buffer.split("\n", 1)
-                                    if first_line.strip() and not "```" in first_line:
-                                        code_buffer = rest
-
-                                # Render the code block
-                                render_code_block(code_buffer)
-
-                                # Reset buffers
-                                buffer = ""
-                                code_buffer = ""
-                        elif in_code:
-                            # Just add to code buffer
-                            code_buffer += char
-                            if len(buffer) >= 3:  # Keep buffer small while in code
-                                buffer = buffer[-3:]
-                        else:
-                            # Regular text - print if buffer gets too large
-                            if len(buffer) > 100:
-                                print(buffer[:-3], end="")
-                                buffer = buffer[
-                                    -3:
-                                ]  # Keep last 3 chars to check for backticks
-
-                # Handle any remaining content
-                if in_code:
-                    render_code_block(code_buffer)
-                else:
-                    print(buffer, end="")
+                                # Regular text - print if buffer gets too large
+                                if len(buffer) > 100:
+                                    print(buffer[:-3], end="")
+                                    buffer = buffer[
+                                        -3:
+                                    ]  # Keep last 3 chars to check for backticks
+
+                    # Handle any remaining content
+                    if in_code:
+                        render_code_block(code_buffer)
+                    else:
+                        print(buffer, end="")
+
+                    if str_output:
+                        output = str_output
+            except:
+                output = None
 
-                if str_output:
-                    output = str_output
             print("\n")
-            save_conversation_message(
-                command_history,
-                conversation_id,
-                "assistant",
-                output,
-                wd=current_path,
-                model=model,
-                provider=provider,
-                npc=npc_name,
-            )
+
+            if isinstance(output, str):
+                save_conversation_message(
+                    command_history,
+                    conversation_id,
+                    "assistant",
+                    output,
+                    wd=current_path,
+                    model=model,
+                    provider=provider,
+                    npc=npc_name,
+                )
 
             # if there are attachments in most recent user sent message, save them
             # save_attachment_to_message(command_history, message_id, # file_path, attachment_name, attachment_type)

npcsh/shell_helpers.py

@@ -1631,6 +1631,9 @@ def ots(
         output = analyze_image(
             user_prompt, file_path, filename, npc=npc, model=model, provider=provider
         )
+        messages = [
+            {"role": "user", "content": user_prompt},
+        ]
 
     else:
         output = capture_screenshot(npc=npc)
@@ -1651,12 +1654,15 @@ def ots(
         # messages = output["messages"]
 
         output = output["response"]
-
+        messages = [
+            {"role": "user", "content": user_prompt},
+        ]
     if output:
         if isinstance(output, dict) and "filename" in output:
             message = f"Screenshot captured: {output['filename']}\nFull path: {output['file_path']}\nLLM-ready data available."
         else:  # This handles both LLM responses and error messages (both strings)
             message = output
+        messages.append({"role": "assistant", "content": message})
         return {"messages": messages, "output": message}  # Return the message
     else:  # Handle the case where capture_screenshot returns None
         print("Screenshot capture failed.")
@@ -2042,6 +2048,18 @@ def execute_slash_command(
                 device = part.split("=")[1]
             if part.startswith("rag_similarity_threshold="):
                 rag_similarity_threshold = float(part.split("=")[1])
+            if part.startswith("model="):
+                model = part.split("=")[1]
+
+            if part.startswith("provider="):
+                provider = part.split("=")[1]
+            if part.startswith("api_url="):
+                api_url = part.split("=")[1]
+            if part.startswith("api_key="):
+                api_key = part.split("=")[1]
+
+                # load the npc properly
+
         match = re.search(r"files=\s*\[(.*?)\]", command)
         files = []
         if match:
@@ -2066,10 +2084,11 @@ def execute_slash_command(
 
                 print(f"Reattached to previous conversation:\n\n")
                 output = enter_spool_mode(
-                    command_history,
                     inherit_last,
                     files=files,
                     npc=npc,
+                    model=model,
+                    provider=provider,
                     rag_similarity_threshold=rag_similarity_threshold,
                     device=device,
                     messages=spool_context,
@@ -2082,7 +2101,6 @@ def execute_slash_command(
                 return {"messages": [], "output": "No previous conversation found."}
 
         output = enter_spool_mode(
-            command_history,
             inherit_last,
             files=files,
             npc=npc,
@@ -2367,11 +2385,13 @@ def execute_command(
             valid_npcs = get_db_npcs(db_path)
 
             npc_name = get_npc_from_command(command)
+
             if npc_name is None:
                 npc_name = "sibiji"  # Default NPC
             npc_path = get_npc_path(npc_name, db_path)
 
             npc = load_npc_from_file(npc_path, db_conn)
+            current_npc = npc
         else:
             valid_npcs = [current_npc]
             npc = current_npc
@@ -2546,60 +2566,62 @@ def execute_command(
                 except AttributeError:
                     print(output)
 
-            piped_outputs.append(f'"{output}"')
+                piped_outputs.append(f'"{output}"')
 
-            try:
-                # Prepare text to embed (both command and response)
-                texts_to_embed = [command, str(output) if output else ""]
+                try:
+                    # Prepare text to embed (both command and response)
+                    texts_to_embed = [command, str(output) if output else ""]
 
-                # Generate embeddings
-                embeddings = get_embeddings(
-                    texts_to_embed,
-                )
+                    # Generate embeddings
+                    embeddings = get_embeddings(
+                        texts_to_embed,
+                    )
 
-                # Prepare metadata
-                metadata = [
-                    {
-                        "type": "command",
-                        "timestamp": datetime.datetime.now().isoformat(),
-                        "path": os.getcwd(),
-                        "npc": npc.name if npc else None,
-                        "conversation_id": conversation_id,
-                    },
-                    {
-                        "type": "response",
-                        "timestamp": datetime.datetime.now().isoformat(),
-                        "path": os.getcwd(),
-                        "npc": npc.name if npc else None,
-                        "conversation_id": conversation_id,
-                    },
-                ]
-                embedding_model = os.environ.get("NPCSH_EMBEDDING_MODEL")
-                embedding_provider = os.environ.get("NPCSH_EMBEDDING_PROVIDER")
-                collection_name = f"{embedding_provider}_{embedding_model}_embeddings"
+                    # Prepare metadata
+                    metadata = [
+                        {
+                            "type": "command",
+                            "timestamp": datetime.datetime.now().isoformat(),
+                            "path": os.getcwd(),
+                            "npc": npc.name if npc else None,
+                            "conversation_id": conversation_id,
+                        },
+                        {
+                            "type": "response",
+                            "timestamp": datetime.datetime.now().isoformat(),
+                            "path": os.getcwd(),
+                            "npc": npc.name if npc else None,
+                            "conversation_id": conversation_id,
+                        },
+                    ]
+                    embedding_model = os.environ.get("NPCSH_EMBEDDING_MODEL")
+                    embedding_provider = os.environ.get("NPCSH_EMBEDDING_PROVIDER")
+                    collection_name = (
+                        f"{embedding_provider}_{embedding_model}_embeddings"
+                    )
 
-                try:
-                    collection = chroma_client.get_collection(collection_name)
-                except Exception as e:
-                    print(f"Warning: Failed to get collection: {str(e)}")
-                    print("Creating new collection...")
-                    collection = chroma_client.create_collection(collection_name)
-                date_str = datetime.datetime.now().isoformat()
-                # print(date_str)
-
-                # Add to collection
-                current_ids = [f"cmd_{date_str}", f"resp_{date_str}"]
-                collection.add(
-                    embeddings=embeddings,
-                    documents=texts_to_embed,  # Adjust as needed
-                    metadatas=metadata,  # Adjust as needed
-                    ids=current_ids,
-                )
+                    try:
+                        collection = chroma_client.get_collection(collection_name)
+                    except Exception as e:
+                        print(f"Warning: Failed to get collection: {str(e)}")
+                        print("Creating new collection...")
+                        collection = chroma_client.create_collection(collection_name)
+                    date_str = datetime.datetime.now().isoformat()
+                    # print(date_str)
+
+                    # Add to collection
+                    current_ids = [f"cmd_{date_str}", f"resp_{date_str}"]
+                    collection.add(
+                        embeddings=embeddings,
+                        documents=texts_to_embed,  # Adjust as needed
+                        metadatas=metadata,  # Adjust as needed
+                        ids=current_ids,
+                    )
 
-                # print("Stored embeddings.")
-                # print("collection", collection)
-            except Exception as e:
-                print(f"Warning: Failed to store embeddings: {str(e)}")
+                    # print("Stored embeddings.")
+                    # print("collection", collection)
+                except Exception as e:
+                    print(f"Warning: Failed to store embeddings: {str(e)}")
 
     # return following
     # print(current_npc)
@@ -3161,6 +3183,7 @@ def enter_spool_mode(
         Dict : The messages and output.
 
     """
+
     command_history = CommandHistory()
     npc_info = f" (NPC: {npc.name})" if npc else ""
     print(f"Entering spool mode{npc_info}. Type '/sq' to exit spool mode.")

npcsh-0.3.31.data/data/npcsh/npc_team/bash_executer.tool

@@ -0,0 +1,32 @@
+tool_name: bash_executor
+description: Execute bash queries.
+inputs:
+  - bash_command
+  - user_request
+steps:
+  - engine: python
+    code: |
+      import subprocess
+      import os
+      cmd = '{{bash_command}}'  # Properly quote the command input
+      def run_command(cmd):
+        process = subprocess.Popen(cmd, shell=True, stdout=subprocess.PIPE, stderr=subprocess.PIPE)
+        stdout, stderr = process.communicate()
+        if stderr:
+          print(f"Error: {stderr.decode('utf-8')}")
+          return stderr
+        return stdout
+      result = run_command(cmd)
+      output = result.decode('utf-8')
+
+  - engine: natural
+    code: |
+
+      Here is the result of the bash command:
+      ```
+      {{ output }}
+      ```
+      This was the original user request: {{ user_request }}
+
+      Please provide a response accordingly.
+

npcsh-0.3.31.data/data/npcsh/npc_team/code_executor.tool

@@ -0,0 +1,16 @@
+tool_name: code_executor
+description: Execute scripts with a specified language. choose from python, bash, R, or javascript. Set the ultimate result as the "output" variable. It must be a string. Do not add unnecessary print statements.
+inputs:
+  - code
+  - language
+steps:
+  - engine: '{{ language }}'
+    code: |
+      {{code}}
+  - engine: natural
+    code: |
+      Here is the result of the code execution that an agent ran.
+      ```
+      {{ output }}
+      ```
+      please provide a response accordingly.

{npcsh-0.3.29.data → npcsh-0.3.31.data}/data/npcsh/npc_team/generic_search.tool

@@ -2,13 +2,21 @@ tool_name: "internet_search"
 description: Searches the web for information based on a query in order to verify timiely details (e.g. current events) or to corroborate information in uncertain situations. Should be mainly only used when users specifically request a search, otherwise an LLMs basic knowledge should be sufficient.
 inputs:
   - query
+  - provider: ''
 steps:
   - engine: "python"
     code: |
       from npcsh.search import search_web
+      from npcsh.npc_sysenv import NPCSH_SEARCH_PROVIDER
       query = "{{ query }}"
+      provider = '{{ provider }}'
+      if provider.strip() != '':
+          results = search_web(query, num_results=5, provider = provider)
+      else:
+          results = search_web(query, num_results=5, provider = NPCSH_SEARCH_PROVIDER)
+
       print('QUERY in tool', query)
-      results = search_web(query, num_results=5)
+      results = search_web(query, num_results=5, provider = NPCSH_SEARCH_PROVIDER)
       print('RESULTS in tool', results)
   - engine: "natural"
     code: |

{npcsh-0.3.29.data → npcsh-0.3.31.data}/data/npcsh/npc_team/npcsh.ctx

@@ -1,5 +1,11 @@
-text: |
+context: |
     The npcsh NPC team is devoted to providing a safe and helpful
     environment for users where they can work and be as successful as possible.
     npcsh is a command-line tool that makes it easy for users to harness
-    the power of LLMs from a command line shell.
+    the power of LLMs from a command line shell.
+databases:
+    - ~/npcsh_history.db
+mcp_servers:
+    - /path/to/mcp/server.py
+    - @npm for server
+

npcsh-0.3.31.data/data/npcsh/npc_team/npcsh_executor.tool

@@ -0,0 +1,9 @@
+tool_name: npcsh_executor
+description: Execute npcsh commands. Use the macro commands.
+inputs:
+  - code
+  - language
+steps:
+  - engine: "{{language}}"
+    code: |
+      {{code}}

{npcsh-0.3.29.data → npcsh-0.3.31.data}/data/npcsh/npc_team/sql_executor.tool

@@ -1,5 +1,5 @@
-tool_name: sql_executor
-description: Execute SQL queries on the ~/npcsh_history.db and display the result. The database contains only information about conversations and other user-provided data. It does not store any information about individual files.
+tool_name: data_pull
+description: Execute queries on the ~/npcsh_history.db to pull data. The database contains only information about conversations and other user-provided data. It does not store any information about individual files.
 inputs:
   - sql_query
   - interpret: false  # Note that this is not a boolean, but a string

{npcsh-0.3.29.dist-info → npcsh-0.3.31.dist-info}/METADATA

@@ -1,6 +1,6 @@
 Metadata-Version: 2.4
 Name: npcsh
-Version: 0.3.29
+Version: 0.3.31
 Summary: npcsh is a command line tool for integrating LLMs into everyday workflows and for orchestrating teams of NPCs.
 Home-page: https://github.com/cagostino/npcsh
 Author: Christopher Agostino
@@ -112,22 +112,23 @@ Interested to stay in the loop and to hear the latest and greatest about `npcsh`
 ## TLDR Cheat Sheet
 Users can take advantage of `npcsh` through its custom shell or through a command-line interface (CLI) tool. Below is a cheat sheet that shows how to use `npcsh` commands in both the shell and the CLI. For the npcsh commands to work, one must activate `npcsh` by typing it in a shell.
 
+
+
+
 | Task | npc CLI | npcsh |
 |----------|----------|----------|
 | Ask a generic question | npc 'prompt' | 'prompt' |
 | Compile an NPC | npc compile /path/to/npc.npc | /compile /path/to/npc.npc |
 | Computer use | npc plonk -n 'npc_name' -sp 'task for plonk to carry out '| /plonk -n 'npc_name' -sp 'task for plonk to carry out ' |
 | Conjure an NPC team from context and templates | npc init -t 'template1, template2' -ctx 'context'   | /conjure  -t 'template1, 'template2' -ctx 'context'  |
-| Enter a chat with an NPC (NPC needs to be compiled first) | npc npc_name | /npc_name |
+| Enter a chat with an NPC (NPC needs to be compiled first) | npc chat -n npc_name | /spool npc=<npc_name> |
 | Generate image    | npc vixynt 'prompt'  | /vixynt prompt   |
 | Get a sample LLM response  | npc sample 'prompt'   | /sample prompt for llm  |
-| Invoke a tool  | npc tool {tool_name} -args --flags | /tool_name -args --flags |
-| Search locally | npc tool local_search -args --flags | /local_search -args --flags |
 | Search for a term in the npcsh_db only in conversations with a specific npc | npc rag -n 'npc_name' -f 'filename' -q 'query' | /rag -n 'npc_name' -f 'filename' -q 'query' |
-| Search the web | npc search -p provider 'query' | /search -p provider 'query' |
+| Search the web | npc search -q "cal golden bears football schedule" -sp perplexity | /search -p perplexity 'cal bears football schedule' |
 | Serve an NPC team | npc serve --port 5337 --cors='http://localhost:5137/' | /serve --port 5337 --cors='http://localhost:5137/' |
 | Screenshot analysis  | npc ots |  /ots  |
-| Voice Chat    | npc whisper 'npc_name'   | /whisper   |
+| Voice Chat    | npc whisper -n 'npc_name'   | /whisper   |
 
 
 ## Python Examples
@@ -725,19 +726,6 @@ The code in the visible section of your VS Code window appears to be a script fo
 In summary, this code automates the process of capturing a screenshot, saving it with a unique filename, and analyzing that image for specific content or patterns.
 
 
-```
-
-```npcsh
-npcsh> What is the biggest file in my current folder?
-
-LLM suggests the following bash command: ls -S | head -n 1
-
-Running command: ls -S | head -n 1
-
-Command executed with output: image_20241111_000033.png
-
-I ran the command ls -S | head -n 1 in your current folder. This command sorts all files by size in descending order and then selects the first entry, which represents the largest file. The result of this operation shows that the biggest file in your current folder is image_20241111_000033.png.
-
 ```
 
 ```npcsh
@@ -869,7 +857,7 @@ and then the associated image :
 An important facet that makes `npcsh` so powerful is the ability to pipe outputs from one tool call to another. This allows for the chaining of commands and the creation of complex workflows. For example, you can use the output of a search to generate an image, or you can use the output of an image analysis to generate a report. Here is an example of how this might look in practice:
 ```npcsh
 npcsh> what is the gdp of russia in 2024? | /vixynt 'generate an image that contains {0}'
-
+```
 ### Executing Bash Commands
 You can execute bash commands directly within npcsh. The LLM can also generate and execute bash commands based on your natural language requests.
 For example:
@@ -1167,7 +1155,10 @@ Search can be accomplished through the `/search` macro. You can specify the prov
 you must set a perplexity api key as an environment variable as described above. The default provider is duckduckgo.
 
 NOTE: while google is an available search engine, they recently implemented changes (early 2025) that make the python google search package no longer as reliable.
-For now, we will use duckduckgo and revisit this issue when other more critical aspects are handled.
+Duckduckgo's search toool also givies rate limit errors often, so until a more robust
+solution is implemented for it, Perplexity's will be the most reliable.
+
+
 
 
 ```npcsh