### Schema Tool Definition Setup

Source: https://answerdotai.github.io/toolslm/funccall.html

Example setup for a tool definition using dict2obj.

```python
tool = dict2obj(dict(
    description='Find real-…',
    inputSchema={
        '$schema': 'http://json-schema.org/draft-07/schema#',
        **dict(
            additionalProperties=False,
            properties=dict(
                language=dict(description='Filter by …', items={'type': 'string'}, type='array'),
                matchCase=dict(default=False, description='Whether th…', type='boolean'),
                path=dict(description='Filter by …', type='string'),
                query=dict(description='The litera…', type='string'),
                useRegexp=dict(default=False, description='Whether to…', type='boolean')),
            required=['query'],
            type='object')})
```

```python
props, req = tool.inputSchema['properties'], tool.inputSchema['required']
list(props)
```

```python
props.matchCase
```

```python
tool_hy = dict2obj(dict(name='run', description='Run command', inputSchema=dict(type='object', properties={'cmd': {'type': 'string'}, 'approval-policy': {'type': 'string', 'default': 'never'}}, required=['cmd'])))

sig = schema2sig(tool_hy)
test_eq(list(sig.parameters), ['cmd', 'approval_policy'])
test_eq(sig.parameters['approval_policy'].default, 'never')
test_eq(sig.parameters['approval_policy'].kind, Parameter.KEYWORD_ONLY)
```

```python
tool_req_hy = dict2obj(dict(name='run', description='Run command', inputSchema=dict(type='object', properties={'approval-policy': {'type': 'string'}, 'cmd': {'type': 'string'}}, required=['approval-policy', 'cmd'])))
```

```python
tool_collision = dict2obj(dict(name='run', description='Run command', inputSchema=dict(type='object', properties={'approval-policy': {'type': 'string'}, 'approval_policy': {'type': 'string'}})))

test_fail(lambda: schema2sig(tool_collision), contains='collision')
```

```python
test_eq(_py_nm(''), '_')
```

--------------------------------

### Install toolslm

Source: https://answerdotai.github.io/toolslm/index.html.md

Install the library using pip.

```sh
pip install toolslm
```

--------------------------------

### Example URL for fastlite

Source: https://answerdotai.github.io/toolslm/download.html.md

An example URL pointing to the fastlite project, likely used for testing or demonstration purposes with the find_docs function.

```python
fl_url = 'https://answerdotai.github.io/fastlite'

```

--------------------------------

### Execute shell commands

Source: https://answerdotai.github.io/toolslm/shell.html.md

Examples of running code within the initialized shell instance.

```python
shell = get_shell()
```

```python
r = shell.run_cell('print(3); 1+1')
r.result,r.stdout
```

```python
r = shell.run_cell('raise Exception("blah")')
print(exception2str(r.error_in_exec))
```

```python
r = shell.run_cell('import time; time.sleep(10)', timeout=1)
r.error_in_exec
```

--------------------------------

### Create a doctype Tuple

Source: https://answerdotai.github.io/toolslm/xml.html.md

Usage example for creating a doctype tuple from content.

```python
doc = 'This is a "sample"'
mk_doctype(doc)
```

--------------------------------

### Get GitHub repo file sizes with type filtering

Source: https://answerdotai.github.io/toolslm/xml.html.md

This example shows how to use repo2ctx to obtain a dictionary of file sizes from a GitHub repository. It filters for Python files and excludes files starting with an underscore, returning only the file names and their sizes.

```python
print(repo2ctx('answerdotai/toolslm', types='py', skip_file_re='^_', out=False, files_only=True))
```

--------------------------------

### Execute shell commands

Source: https://answerdotai.github.io/toolslm/shell.html

Examples of running code within the shell, handling output, exceptions, and timeouts.

```python
r = shell.run_cell('print(3); 1+1')
r.result,r.stdout
```

```python
r = shell.run_cell('raise Exception("blah")')
print(exception2str(r.error_in_exec))
```

```python
r = shell.run_cell('import time; time.sleep(10)', timeout=1)
r.error_in_exec
```

--------------------------------

### Execute code with python function

Source: https://answerdotai.github.io/toolslm/funccall.html

Examples of executing Python code, handling timeouts, and managing namespaces.

```python
python("""def factorial(n):
    if n == 0 or n == 1: return 1
    else: return n * factorial(n-1)
factorial(5)""")
```

```python
print(python('import time; time.sleep(10)', timeout=1))
```

```python
python("a=1")
a
```

```python
glb = {}
python("a=3", glb=glb)
a, glb['a']
```

--------------------------------

### Generate schema for get_schema

Source: https://answerdotai.github.io/toolslm/funccall.html.md

Example of generating a schema for the get_schema function itself.

```python
get_schema(get_schema)
```

--------------------------------

### Generate XML for Multiple Documents

Source: https://answerdotai.github.io/toolslm/xml.html.md

Example of generating a full XML string for a list of documents.

```python
docs = [doc, 'And another one']
srcs = [None, 'doc.txt']
print(docs_xml(docs, srcs))
```

--------------------------------

### Convert GitHub repo to XML context with file type and size limits

Source: https://answerdotai.github.io/toolslm/xml.html.md

This example demonstrates converting a GitHub repository to XML context, filtering by specific file extensions (ipynb, py) and applying a maximum total output size. It also skips files matching a regular expression and disables the inclusion of notebook cell outputs.

```python
print(repo2ctx('answerdotai/toolslm', exts=('ipynb','py'), skip_file_re='^_', out=False, max_total=500))
```

--------------------------------

### Call find_docs with fastlite URL

Source: https://answerdotai.github.io/toolslm/download.html.md

Demonstrates calling the find_docs function with the example fastlite URL to retrieve its documentation.

```python
find_docs(fl_url)

```

--------------------------------

### Generate XML for a Single Document

Source: https://answerdotai.github.io/toolslm/xml.html.md

Example of generating XML for one document using mk_doc.

```python
mk_doc(1, doc, title="test")
```

--------------------------------

### symslice

Source: https://answerdotai.github.io/toolslm/inspecttools.html.md

Returns the contents of the symbol from the given start to the end.

```APIDOC
## symslice

### Description
Returns the contents of the symbol from the given start to the end.

### Parameters
#### Request Body
- **sym** (str) - Required - Dotted symbol path or "_last" for previous result
- **start** (int) - Required - Starting index for slice
- **end** (int) - Required - Ending index for slice
```

--------------------------------

### Get Source File Path for Symbol

Source: https://answerdotai.github.io/toolslm/xml.html.md

Returns an MD string containing the filepath and contents for a given symbol's source file. The example shows how to use it with the `Path` object.

```python
def sym2file(
    sym
):


```

```python
# print(sym2file(Path))
```

--------------------------------

### Get Schema for a Class Method

Source: https://answerdotai.github.io/toolslm/funccall.html

Illustrates retrieving the schema for an instance method of a class. Default values for parameters are correctly parsed.

```python
class Dummy:
    def sums(
        self,
        a:int,  # First thing to sum
        b:int=1 # Second thing to sum
    ): # The sum of the inputs
        "Adds a + b."
        print(f"Finding the sum of {a} and {b}")
        return a + b

get_schema(Dummy.sums)
```

--------------------------------

### Convert GitHub repo subdirectory to context

Source: https://answerdotai.github.io/toolslm/xml.html.md

This example converts the contents of a specific subdirectory within a GitHub repository into context. It uses a URL to specify the repository and the subdirectory path.

```python
print(repo2ctx('https://github.com/AnswerDotAI/toolslm/tree/main/samples'))
```

--------------------------------

### GET /symsrc

Source: https://answerdotai.github.io/toolslm/inspecttools.html.md

Retrieves the source code for a given symbol path.

```APIDOC
## GET /symsrc

### Description
Retrieves the source code for a specified symbol path. Use '_last' to refer to the result of the previous tool call.

### Parameters
#### Query Parameters
- **sym** (string) - Required - Dotted symbol path (e.g., 'Interval' or 'sympy.sets.sets.Interval') or '_last'.
```

--------------------------------

### Get Schema with String Type Annotations

Source: https://answerdotai.github.io/toolslm/funccall.html

Shows how `get_schema` handles functions with string-based type annotations for parameters and return types. Ensure a mandatory docstring is present.

```python
def silly_test(
    a: 'int',  # quoted type hint
)->int:
    "Mandatory docstring"
    return a

get_schema(silly_test)
```

--------------------------------

### Get LLM Text File

Source: https://answerdotai.github.io/toolslm/download.html

Retrieves the 'llms.txt' file from a URL and expands it using `llms_txt.create_ctx()`. Useful for accessing LLM-related text data.

```python
def get_llmstxt(
    url, optional:bool=False, n_workers:NoneType=None
):

```

```python
# print(get_llmstxt('https://llmstxt.org/llms.txt'))
```

--------------------------------

### Get Package Path for Symbol

Source: https://answerdotai.github.io/toolslm/xml.html

Retrieves the root package path for a given symbol. This is useful for understanding the organizational structure of the code.

```python
def sym2pkgpath(
    sym
):


```

```text
sym2pkgpath(test_eq)
    Path('/Users/jhoward/aai-ws/fastcore/fastcore')

```

--------------------------------

### Get Package Path for Symbol

Source: https://answerdotai.github.io/toolslm/xml.html.md

Retrieves the root package path for a given symbol. This is useful for understanding the organizational structure of the code.

```python
def sym2pkgpath(
    sym
):


```

```python
sym2pkgpath(test_eq)

```

--------------------------------

### Get Package File Context

Source: https://answerdotai.github.io/toolslm/inspecttools.html

Retrieves XML context of all files within a symbol's top-level package. Offers extensive control over included file types, recursion, and filtering.

```python
def symfiles_package(
    sym:str, # Dotted symbol path or "_last" for previous result
    types:str | list='py', # List or comma-separated str of ext types from: py, js, java, c, cpp, rb, r, ex, sh, web, doc, cfg
    skip_file_re:str='^_mod', # Skip files matching regex
    skip_folder_re:str='^(\.|__)', # Skip folders matching regex
    prefix:bool=False, # Include Anthropic's suggested prose intro?
    out:bool=True, # Include notebook cell outputs?
    include_base:bool=True, # Include full path in src?
    title:str=None, # Optional title attr for Documents element
    max_size:int=100000, # Skip files larger than this (bytes)
    max_total:int=10000000, # Max total output size in bytes
    readme_first:bool=False, # Prioritize README files at start of context?
    files_only:bool=False, # Return dict of {filename: size} instead of context?
    sigs_only:bool=False, # Return signatures instead of full text? (where supported by `codesigs` lib)
    ids:bool=True, # Include cell ids in notebooks?
    recursive:bool=True, # search subfolders
    symlinks:bool=True, # follow symlinks?
    file_glob:str=None, # Only include files matching glob
    file_re:str=None, # Only include files matching regex
    folder_re:str=None, # Only enter folders matching regex
    skip_file_glob:str=None, # Skip files matching glob
    ret_folders:bool=False, # return folders, not just files
    sort:bool=True, # sort files by name within each folder
    exts:str | list=None, # list or comma-separated str of exts to include
):


```

```python
# print(symfiles_package('xml'))
```

--------------------------------

### Resolve Symbol with Indexing

Source: https://answerdotai.github.io/toolslm/inspecttools.html.md

Example of resolving a symbol path that includes indexing into a list-like object.

```python
a = fastcore.utils.L(1)
resolve('a.argfirst')
```

--------------------------------

### Get Schema for a Simple Function

Source: https://answerdotai.github.io/toolslm/funccall.html

Demonstrates retrieving the schema for a simple Python function `silly_sum`. The tool use spec requires return annotations to be placed in the description.

```python
s = get_schema(silly_sum)
desc = s.pop('description')
print(desc)
s
```

--------------------------------

### Get Package Context for Symbol

Source: https://answerdotai.github.io/toolslm/xml.html.md

Retrieves the contents of files within a symbol's root package. Supports various filtering and inclusion options similar to sym2folderctx.

```python
def sym2pkgctx(
    sym,
    types:str | list='py', # List or comma-separated str of ext types from: py, js, java, c, cpp, rb, r, ex, sh, web, doc, cfg
    skip_file_re:str='^_mod', # Skip files matching regex
    skip_folder_re:str='^(\.|__)', # Skip folders matching regex
    prefix:bool=False, # Include Anthropic's suggested prose intro?
    out:bool=True, # Include notebook cell outputs?
    include_base:bool=True, # Include full path in src?
    title:str=None, # Optional title attr for Documents element
    max_size:int=100000, # Skip files larger than this (bytes)
    max_total:int=10000000, # Max total output size in bytes
    readme_first:bool=False, # Prioritize README files at start of context?
    files_only:bool=False, # Return dict of {filename: size} instead of context?
    sigs_only:bool=False, # Return signatures instead of full text? (where supported by `codesigs` lib)
    ids:bool=True, # Include cell ids in notebooks?
    recursive:bool=True, # search subfolders
    symlinks:bool=True, # follow symlinks?
    file_glob:str=None, # Only include files matching glob
    file_re:str=None, # Only include files matching regex
    folder_re:str=None, # Only enter folders matching regex
    skip_file_glob:str=None, # Skip files matching glob
    ret_folders:bool=False, # return folders, not just files
    sort:bool=True, # sort files by name within each folder
    exts:str | list=None, # list or comma-separated str of exts to include
):


```

--------------------------------

### Get Folder File Context

Source: https://answerdotai.github.io/toolslm/inspecttools.html

Retrieves XML context of files within the folder where a symbol is defined. Supports various filtering and output options.

```python
def symfiles_folder(
    sym:str, # Dotted symbol path or "_last" for previous result
    types:str | list='py', # List or comma-separated str of ext types from: py, js, java, c, cpp, rb, r, ex, sh, web, doc, cfg
    skip_file_re:str='^_mod', # Skip files matching regex
    prefix:bool=False, # Include Anthropic's suggested prose intro?
    out:bool=True, # Include notebook cell outputs?
    include_base:bool=True, # Include full path in src?
    title:str=None, # Optional title attr for Documents element
    max_size:int=100000, # Skip files larger than this (bytes)
    max_total:int=10000000, # Max total output size in bytes
    readme_first:bool=False, # Prioritize README files at start of context?
    files_only:bool=False, # Return dict of {filename: size} instead of context?
    sigs_only:bool=False, # Return signatures instead of full text? (where supported by `codesigs` lib)
    ids:bool=True, # Include cell ids in notebooks?
    recursive:bool=True, # search subfolders
    symlinks:bool=True, # follow symlinks?
    file_glob:str=None, # Only include files matching glob
    file_re:str=None, # Only include files matching regex
    folder_re:str=None, # Only enter folders matching regex
    skip_file_glob:str=None, # Skip files matching glob
    skip_folder_re:str=None, # Skip folders matching regex,
    ret_folders:bool=False, # return folders, not just files
    sort:bool=True, # sort files by name within each folder
    exts:str | list=None, # list or comma-separated str of exts to include
):


```

```python
# print(symfiles_folder('xml'))
```

--------------------------------

### Import and Verify Module

Source: https://answerdotai.github.io/toolslm/inspecttools.html.md

Demonstrates importing a module and accessing its version to verify availability.

```python
importmodule('fastcore.utils')
fastcore.__version__
```

--------------------------------

### Get Symbol Type with symtype

Source: https://answerdotai.github.io/toolslm/inspecttools.html.md

Use `symtype` to get the type of one or more symbols. It accepts a comma-separated string of symbol paths or `"_last"` for the previous result. Returns 'SymbolNotFound' for missing symbols.

```python
def symtype(
    syms:str, # Comma separated str list of dotted symbol paths (e.g 'Interval,a' or 'sympy.sets.sets.Interval'); "_last" for prev result
):


```

```python
symtype('a.argfirst')
```

```python
symtype('fffaa,b')
```

--------------------------------

### Get Symbol Value Representation with symval

Source: https://answerdotai.github.io/toolslm/inspecttools.html.md

Use `symval` to get a list of `repr()` strings for symbol values. It accepts a comma-separated string of symbol paths or `"_last"`. Handles 'SymbolNotFound' for missing symbols.

```python
def symval(
    syms:str, # Comma separated str list of dotted symbol paths (e.g `Interval` or `sympy.sets.sets.Interval`); "_last" for prev result
):


```

```python
a
```

```python
symval('a,foofoo')
```

--------------------------------

### Sample Markdown for Parsing

Source: https://answerdotai.github.io/toolslm/md_hier.html

A sample markdown string used to demonstrate the functionality of create_heading_dict.

```python
sample_md = """
# Introduction

Welcome to our documentation.

## Getting Started

Follow these steps to begin.

### Installation

Run the following command:

```bash
# Install the packackge
pip install our-package
```

### Configuration

Set up your config file.

## Advanced Usage

For advanced users only.

# Appendix

Additional resources."""
```

--------------------------------

### Import IPython and Textwrap

Source: https://answerdotai.github.io/toolslm/inspecttools.html.md

Imports necessary libraries for displaying output and formatting text.

```python
from IPython.display import display,Markdown
import textwrap
```

--------------------------------

### Get Symbol Type and Value with symtype_val

Source: https://answerdotai.github.io/toolslm/inspecttools.html.md

Use `symtype_val` to get a list of (type, repr) tuples for symbol values. It accepts a comma-separated string of symbol paths or `"_last"`. Returns 'SymbolNotFound' for missing symbols.

```python
def symtype_val(
    syms:str, # Comma separated str list of dotted symbol paths (e.g `Interval` or `sympy.sets.sets.Interval`); "_last" for prev result
):


```

```python
symtype_val('a,b,foofoo')
```

--------------------------------

### GET /symtype

Source: https://answerdotai.github.io/toolslm/inspecttools.html.md

Retrieves the type of a symbol or list of symbols.

```APIDOC
## GET /symtype

### Description
Returns the type of a symbol or a comma-separated list of symbols. Sets '_last' to the result.

### Parameters
#### Query Parameters
- **syms** (string) - Required - Comma-separated string list of dotted symbol paths or '_last'.
```

--------------------------------

### GET /symtype_val

Source: https://answerdotai.github.io/toolslm/inspecttools.html.md

Retrieves both the type and string representation of symbol values.

```APIDOC
## GET /symtype_val

### Description
Returns a list of 2-tuples containing (type, repr) for the provided symbols.

### Parameters
#### Query Parameters
- **syms** (string) - Required - Comma-separated string list of dotted symbol paths or '_last'.
```

--------------------------------

### Create and print heading dictionary

Source: https://answerdotai.github.io/toolslm/md_hier.html

Parses the sample markdown using create_heading_dict and prints the top-level keys and the total character count of the root document's text content.

```python
result = create_heading_dict(sample_md)
print("Available sections:")
for key in result.keys(): print(f"  {key}")
print(f"\nRoot document has {len(result.text)} characters of text")
```

--------------------------------

### Initialize stateful shell

Source: https://answerdotai.github.io/toolslm/shell.html

Configures and returns a minimal TerminalInteractiveShell instance.

```python
def get_shell()->TerminalInteractiveShell:
    "Get a `TerminalInteractiveShell` with minimal functionality"
    sh = TerminalInteractiveShell()
    sh.logger.log_output = sh.history_manager.enabled = False
    dh = sh.displayhook
    dh.finish_displayhook = dh.write_output_prompt = dh.start_displayhook = lambda: None
    dh.write_format_data = lambda format_dict, md_dict=None: None
    sh.logstart = sh.automagic = sh.autoindent = False
    sh.autocall = 0
    sh.system = lambda cmd: None
    return sh
```

```python
shell = get_shell()
```

--------------------------------

### GET /symval

Source: https://answerdotai.github.io/toolslm/inspecttools.html.md

Retrieves the string representation (repr) of symbol values.

```APIDOC
## GET /symval

### Description
Returns a list of the repr() of the values for the provided symbols.

### Parameters
#### Query Parameters
- **syms** (string) - Required - Comma-separated string list of dotted symbol paths or '_last'.
```

--------------------------------

### Generate schema for functions with return types and custom types

Source: https://answerdotai.github.io/toolslm/funccall.html

Demonstrates schema generation for functions with type hints and custom type aliases.

```python
def _ret_list_test(a: int) -> list[str]:
    "Mandatory docstring"

s = get_schema(_ret_list_test)
assert 'type: array[string]' in s['description']
```

```python
Cmd = str | list[str]

def _cust_type(a: Cmd): "Mandatory docstring"

s = get_schema(_cust_type)
s
```

--------------------------------

### Retrieve package context for a symbol

Source: https://answerdotai.github.io/toolslm/inspecttools.html.md

Returns XML context of all files within the top-level package of the provided symbol.

```python
def symfiles_package(
    sym:str, # Dotted symbol path or "_last" for previous result
    types:str | list='py', # List or comma-separated str of ext types from: py, js, java, c, cpp, rb, r, ex, sh, web, doc, cfg
    skip_file_re:str='^_mod', # Skip files matching regex
    skip_folder_re:str='^(\.|__)', # Skip folders matching regex
    prefix:bool=False, # Include Anthropic's suggested prose intro?
    out:bool=True, # Include notebook cell outputs?
    include_base:bool=True, # Include full path in src?
    title:str=None, # Optional title attr for Documents element
    max_size:int=100000, # Skip files larger than this (bytes)
    max_total:int=10000000, # Max total output size in bytes
    readme_first:bool=False, # Prioritize README files at start of context?
    files_only:bool=False, # Return dict of {filename: size} instead of context?
    sigs_only:bool=False, # Return signatures instead of full text? (where supported by `codesigs` lib)
    ids:bool=True, # Include cell ids in notebooks?
    recursive:bool=True, # search subfolders
    symlinks:bool=True, # follow symlinks?
    file_glob:str=None, # Only include files matching glob
    file_re:str=None, # Only include files matching regex
    folder_re:str=None, # Only enter folders matching regex
    skip_file_glob:str=None, # Skip files matching glob
    ret_folders:bool=False, # return folders, not just files
    sort:bool=True, # sort files by name within each folder
    exts:str | list=None, # list or comma-separated str of exts to include
):
```

```python
# print(symfiles_package('xml'))
```

--------------------------------

### GET /symtype

Source: https://answerdotai.github.io/toolslm/inspecttools.html

Returns the type of a symbol and updates the internal _last state.

```APIDOC
## GET /symtype

### Description
Returns the type of a symbol, which is useful for the LLM to understand what kind of object it is dealing with.

### Parameters
#### Query Parameters
- **syms** (string) - Required - Comma separated string list of dotted symbol paths or '_last' for the previous result.
```

--------------------------------

### Handle Path Types and Non-Primitive Defaults

Source: https://answerdotai.github.io/toolslm/funccall.html

Demonstrates handling of Path objects and using the evalable parameter to stringify non-primitive defaults.

```python
def _path_test(path: Path = Path('.')):
    "Mandatory docstring"
get_schema(_path_test)
```

```python
test_fail(lambda: ast.literal_eval(str(get_schema(_path_test))), exc=ValueError)
```

```python
def _path_test(path: Path = Path('.')):
    "Mandatory docstring"
get_schema(_path_test, evalable=True)
```

--------------------------------

### Get schema for python function

Source: https://answerdotai.github.io/toolslm/funccall.html

Retrieves the JSON schema for the python execution function.

```python
get_schema(python)
```

--------------------------------

### Find documentation URL

Source: https://answerdotai.github.io/toolslm/download.html

Locates the llms.txt or markdown file associated with a given URL.

```python
def find_docs(
    url
):
```

```python
fl_url = 'https://answerdotai.github.io/fastlite'
```

```python
find_docs(fl_url)
```

```python
for o in urls: print(find_docs(o))
```

```python
suffixes = ["/", "/tmp", "/tmp/tmp/"]
for suff in suffixes:
    for o in urls:  test_eq(find_docs(o), find_docs(o+suff))

test_eq(find_docs("https://github.com"), "https://github.com/llms.txt")
test_eq(find_docs("https://github.com/AnswerDotAI"), "https://github.com/llms.txt")
test_eq(find_docs("https://github.com/AnswerDotAI/"), "https://github.com/llms.txt")
```

--------------------------------

### Initialize stateful shell

Source: https://answerdotai.github.io/toolslm/shell.html.md

Creates a minimal TerminalInteractiveShell instance with restricted functionality.

```python
def get_shell()->TerminalInteractiveShell:
    "Get a `TerminalInteractiveShell` with minimal functionality"
    sh = TerminalInteractiveShell()
    sh.logger.log_output = sh.history_manager.enabled = False
    dh = sh.displayhook
    dh.finish_displayhook = dh.write_output_prompt = dh.start_displayhook = lambda: None
    dh.write_format_data = lambda format_dict, md_dict=None: None
    sh.logstart = sh.automagic = sh.autoindent = False
    sh.autocall = 0
    sh.system = lambda cmd: None
    return sh
```

```python
def get_shell(
    
)->TerminalInteractiveShell:
```

--------------------------------

### Import necessary libraries

Source: https://answerdotai.github.io/toolslm/download.html

Imports the required libraries for markdown and HTML display, and testing utilities.

```python
from IPython.display import Markdown,HTML
from fastcore.test import *
```

--------------------------------

### Get schema function definition

Source: https://answerdotai.github.io/toolslm/funccall.html.md

Signature for the get_schema function used to generate JSON schemas.

```python
def get_schema(
    f:Union, # Function to get schema for
    pname:str='input_schema', # Key name for parameters
    evalable:bool=False, # stringify defaults that can't be literal_eval'd?
    skip_hidden:bool=False, # skip parameters starting with '_'?
    name:NoneType=None, # Override function name (useful for dotted paths like 'obj.method')
)->dict: # {'name':..., 'description':..., pname:...}
```

--------------------------------

### Create a namespace with mk_ns

Source: https://answerdotai.github.io/toolslm/funccall.html.md

Creates a dictionary of allowable function names to call, preventing unauthorized function execution.

```python
def mk_ns(
    fs
):
```

```python
def sums(a, b): return a + b
ns = mk_ns(sums)
ns
```

```python
ns['sums'](1, 2)
```

```python
ca = ClassA()
```

--------------------------------

### Convert Files to XML Context

Source: https://answerdotai.github.io/toolslm/xml.html

Use `files2ctx` to convert a list of file names into XML context. It handles notebook files and can skip files larger than a specified size.

```python
def files2ctx(
    fnames:list, # List of file names to add to context
    srcs:Optional=None, # Use the labels instead of `fnames`
    max_size:int=None, # Skip files larger than this (bytes)
    out:bool=True, # Include notebook cell outputs?
    ids:bool=True, # Include cell ids in notebooks?
    nums:bool=False, # Include line numbers in notebook cell source?
    sigs_only:bool=False, # Only include signatures and docstrings (where supported by `codesigs` lib)
    prefix:bool=False, # Include Anthropic's suggested prose intro?
    details:Optional=None, # Optional list of dicts with additional attrs for each doc
    title:str=None, # Optional title attr for Documents element
)->str: # XML for LM context


```

```python
fnames = ['samples/sample_core.py', 'samples/sample_styles.css']
hl_md(files2ctx(fnames, max_size=120))
```

```html
<documents><document index="1"><src>
samples/sample_core.py
</src><document-content>
[Skipped: sample_core.py exceeds 120 bytes]
</document-content></document><document index="2"><src>
samples/sample_styles.css
</src><document-content>
.cell { margin-bottom: 1rem; }
.cell > .sourceCode { margin-bottom: 0; }
.cell-output > pre { margin-bottom: 0; }
</document-content></document></documents>
```

--------------------------------

### Get schema for a symbol with get_schema_nm

Source: https://answerdotai.github.io/toolslm/funccall.html.md

Generates a schema for a specific symbol in a namespace, preserving the dotted name structure.

```python
def get_schema_nm(
    nm:str, ns, dot2dash:bool=False, kwargs:VAR_KEYWORD
):
```

```python
schema = get_schema_nm('ca.f', locals())
test_eq(schema['name'], 'ca.f')
schema
```

--------------------------------

### files2ctx - Convert files to XML context

Source: https://answerdotai.github.io/toolslm/xml.html.md

Converts a list of file names into an XML context, with options to control size, output inclusion, and more. Handles notebook files.

```APIDOC
## files2ctx

### Description
Convert files to XML context, handling notebooks.

### Method
```python
def files2ctx(
    fnames:list, # List of file names to add to context
    srcs:Optional=None, # Use the labels instead of `fnames`
    max_size:int=None, # Skip files larger than this (bytes)
    out:bool=True, # Include notebook cell outputs?
    ids:bool=True, # Include cell ids in notebooks?
    nums:bool=False, # Include line numbers in notebook cell source?
    sigs_only:bool=False, # Only include signatures and docstrings (where supported by `codesigs` lib)
    prefix:bool=False, # Include Anthropic's suggested prose intro?
    details:Optional=None, # Optional list of dicts with additional attrs for each doc
    title:str=None, # Optional title attr for Documents element
)->str: # XML for LM context
```

### Request Example
```python
fnames = ['samples/sample_core.py', 'samples/sample_styles.css']
hl_md(files2ctx(fnames, max_size=120))
```

### Response Example
```html
<documents><document index="1"><src>
samples/sample_core.py
</src><document-content>
[Skipped: sample_core.py exceeds 120 bytes]
</document-content></document><document index="2"><src>
samples/sample_styles.css
</src><document-content>
.cell { margin-bottom: 1rem; }
.cell > .sourceCode { margin-bottom: 0; }
.cell-output > pre { margin-bottom: 0; }
</document-content></document></documents>
```
```

--------------------------------

### Exclude hidden parameters from schema

Source: https://answerdotai.github.io/toolslm/funccall.html

Use skip_hidden=True in get_schema to omit parameters starting with an underscore from the generated schema.

```python
def test_hidden(a: int, _internal: str = "x"):
    "Test func"
    pass

get_schema(test_hidden, skip_hidden=True)  # should exclude _internal
```

```python
get_schema(test_hidden)
```

--------------------------------

### GET /get_schema

Source: https://answerdotai.github.io/toolslm/funccall.html

Generates a JSON schema for a given class, function, or method, including parameter definitions, types, and descriptions.

```APIDOC
## GET /get_schema

### Description
Generates a JSON schema for a provided Python object (class, function, or method). It maps parameters to JSON schema types and extracts docstrings for descriptions.

### Method
GET

### Endpoint
/get_schema

### Parameters
#### Query Parameters
- **f** (object) - Required - The function, class, or method to generate a schema for.
- **pname** (string) - Optional - Key name for parameters (default: 'input_schema').
- **evalable** (boolean) - Optional - Whether to stringify defaults that cannot be literal_eval'd (default: False).
- **skip_hidden** (boolean) - Optional - Whether to skip parameters starting with '_' (default: False).
- **name** (null) - Optional - Override function name (useful for dotted paths).

### Response
#### Success Response (200)
- **name** (string) - The name of the function or method.
- **description** (string) - The docstring or description of the object.
- **input_schema** (object) - The generated JSON schema object containing properties and required fields.

#### Response Example
{
  "name": "f",
  "description": "object function",
  "input_schema": {
    "type": "object",
    "properties": {
      "o": {"description": "the o", "type": "object"},
      "q": {"description": "", "type": "array", "prefixItems": [{"type": "integer"}, {"type": "string"}]}
    },
    "required": ["o", "q"]
  }
}
```

--------------------------------

### mk_ns

Source: https://answerdotai.github.io/toolslm/funccall.html.md

Creates a namespace dictionary from a list of functions, mapping function names to their callable objects.

```APIDOC
## mk_ns

### Description
Creates a namespace dictionary from a list of functions, mapping function names to their callable objects.

### Parameters
- **fs** (list) - Required - A list of functions to include in the namespace.

### Response
- **dict** - A dictionary where keys are function names and values are the function objects.
```

--------------------------------

### sym2pkgctx

Source: https://answerdotai.github.io/toolslm/xml.html

Returns the contents of files in a symbol's root package.

```APIDOC
## FUNCTION sym2pkgctx

### Description
Return contents of files in a symbol’s root package.

### Parameters
- **sym** (any) - Required - The symbol to locate.
- **types** (str|list) - Optional - List or comma-separated str of ext types.
- **skip_file_re** (str) - Optional - Skip files matching regex.
- **skip_folder_re** (str) - Optional - Skip folders matching regex.
- **prefix** (bool) - Optional - Include Anthropic's suggested prose intro.
- **out** (bool) - Optional - Include notebook cell outputs.
- **include_base** (bool) - Optional - Include full path in src.
- **title** (str) - Optional - Optional title attr for Documents element.
- **max_size** (int) - Optional - Skip files larger than this (bytes).
- **max_total** (int) - Optional - Max total output size in bytes.
- **readme_first** (bool) - Optional - Prioritize README files at start of context.
- **files_only** (bool) - Optional - Return dict of {filename: size} instead of context.
- **sigs_only** (bool) - Optional - Return signatures instead of full text.
- **ids** (bool) - Optional - Include cell ids in notebooks.
- **recursive** (bool) - Optional - Search subfolders.
- **symlinks** (bool) - Optional - Follow symlinks.
- **file_glob** (str) - Optional - Only include files matching glob.
- **file_re** (str) - Optional - Only include files matching regex.
- **folder_re** (str) - Optional - Only enter folders matching regex.
- **skip_file_glob** (str) - Optional - Skip files matching glob.
- **ret_folders** (bool) - Optional - Return folders, not just files.
- **sort** (bool) - Optional - Sort files by name within each folder.
- **exts** (str|list) - Optional - List or comma-separated str of exts to include.
```

--------------------------------

### Generate JSON Schema for List Containers

Source: https://answerdotai.github.io/toolslm/funccall.html

Illustrates the difference between parameterized lists and raw list types in schema generation.

```python
def _list_test(l: List[int]):
    "Mandatory docstring"
    pass
get_schema(_list_test)
```

```python
def _raw_list_test(l: List):
    "Mandatory docstring"
    pass
get_schema(_raw_list_test)
```

--------------------------------

### Generate XML context from files

Source: https://answerdotai.github.io/toolslm/index.html.md

Use folder2ctx to generate XML context from files matching a specific glob pattern.

```python
print(folder2ctx('samples', prefix=False, file_glob='*.py'))
```

--------------------------------

### Schema generation for class methods

Source: https://answerdotai.github.io/toolslm/funccall.html.md

Demonstrates generating schemas for class methods and callable objects.

```python
class ClassA:
    "I am a class"
    def f(self, a:int): # That is `a`
        "Do a thing"
        return 1
    def __call__(self, b:str): # That is `b`
        "Do another thing"
        return 2

ca = ClassA()
ca.f(2)
```

```python
get_schema(ca.f)
```

```python
get_schema(ca)
```

--------------------------------

### Import necessary libraries

Source: https://answerdotai.github.io/toolslm/md_hier.html

Imports the md_hier module and IPython.display.Markdown for potential use.

```python
from toolslm.md_hier import *
from IPython.display import Markdown
```

--------------------------------

### Display folder2ctx help message

Source: https://answerdotai.github.io/toolslm/xml.html.md

Use the -h flag to display the help message for the folder2ctx command-line tool. This shows all available options for converting folder contents to XML context.

```bash
!folder2ctx -h
```

--------------------------------

### Get Schema for Nested Class Structures (Dictionary)

Source: https://answerdotai.github.io/toolslm/funccall.html

Shows schema generation for a class with a dictionary where values are objects. The schema uses `additionalProperties` to define the structure of dictionary values.

```python
class DictConversation:
    "A conversation between two speakers"
    def __init__(
        self,
        turns:dict[str,object], # dictionary of topics and the Turns of the conversation
    ): store_attr()

get_schema(DictConversation)
```

--------------------------------

### Get Schema for Nested Class Structures (List)

Source: https://answerdotai.github.io/toolslm/funccall.html

Demonstrates schema generation for a class containing a list of custom objects. The schema includes a reference to the nested object definition.

```python
class Turn:
    "Turn between two speakers"
    def __init__(
        self,
        speaker_a:str, # First speaker's message
        speaker_b:str,  # Second speaker's message
    ): store_attr()

class Conversation:
    "A conversation between two speakers"
    def __init__(
        self,
        turns:list[Turn], # Turns of the conversation
    ): store_attr()

get_schema(Conversation)
```

--------------------------------

### Retrieve folder context for a symbol

Source: https://answerdotai.github.io/toolslm/inspecttools.html.md

Returns XML context of files located in the folder containing the definition of the provided symbol.

```python
def symfiles_folder(
    sym:str, # Dotted symbol path or "_last" for previous result
    types:str | list='py', # List or comma-separated str of ext types from: py, js, java, c, cpp, rb, r, ex, sh, web, doc, cfg
    skip_file_re:str='^_mod', # Skip files matching regex
    prefix:bool=False, # Include Anthropic's suggested prose intro?
    out:bool=True, # Include notebook cell outputs?
    include_base:bool=True, # Include full path in src?
    title:str=None, # Optional title attr for Documents element
    max_size:int=100000, # Skip files larger than this (bytes)
    max_total:int=10000000, # Max total output size in bytes
    readme_first:bool=False, # Prioritize README files at start of context?
    files_only:bool=False, # Return dict of {filename: size} instead of context?
    sigs_only:bool=False, # Return signatures instead of full text? (where supported by `codesigs` lib)
    ids:bool=True, # Include cell ids in notebooks?
    recursive:bool=True, # search subfolders
    symlinks:bool=True, # follow symlinks?
    file_glob:str=None, # Only include files matching glob
    file_re:str=None, # Only include files matching regex
    folder_re:str=None, # Only enter folders matching regex
    skip_file_glob:str=None, # Skip files matching glob
    skip_folder_re:str=None, # Skip folders matching regex,
    ret_folders:bool=False, # return folders, not just files
    sort:bool=True, # sort files by name within each folder
    exts:str | list=None, # list or comma-separated str of exts to include
):
```

```python
# print(symfiles_folder('xml'))
```

--------------------------------

### Convert Files to XML Context

Source: https://answerdotai.github.io/toolslm/xml.html.md

Converts a list of file names into an XML string for language model context. Handles notebook files and allows filtering by file size.

```python
def files2ctx(
    fnames:list, # List of file names to add to context
    srcs:Optional=None, # Use the labels instead of `fnames`
    max_size:int=None, # Skip files larger than this (bytes)
    out:bool=True, # Include notebook cell outputs?
    ids:bool=True, # Include cell ids in notebooks?
    nums:bool=False, # Include line numbers in notebook cell source?
    sigs_only:bool=False, # Only include signatures and docstrings (where supported by `codesigs` lib)
    prefix:bool=False, # Include Anthropic's suggested prose intro?
    details:Optional=None, # Optional list of dicts with additional attrs for each doc
    title:str=None, # Optional title attr for Documents element
)->str: # XML for LM context


```

```python
fnames = ['samples/sample_core.py', 'samples/sample_styles.css']
hl_md(files2ctx(fnames, max_size=120))
```

--------------------------------

### Get Schema for Nested Class Structures (Set)

Source: https://answerdotai.github.io/toolslm/funccall.html

Illustrates schema generation for a class containing a set of custom objects. The schema includes `uniqueItems: True` to reflect the set's nature.

```python
class SetConversation:
    "A conversation between two speakers"
    def __init__(
        self,
        turns:set[Turn], # the unique Turns of the conversation
    ): store_attr()

get_schema(SetConversation)
```

--------------------------------

### Get Folder Context for Symbol

Source: https://answerdotai.github.io/toolslm/xml.html.md

Retrieves context for a symbol's source file location. Supports filtering by file type, size, and recursion. Can include notebook outputs and cell IDs.

```python
def sym2folderctx(
    sym,
    types:str | list='py', # List or comma-separated str of ext types from: py, js, java, c, cpp, rb, r, ex, sh, web, doc, cfg
    skip_file_re:str='^_mod', # Skip files matching regex
    prefix:bool=False, # Include Anthropic's suggested prose intro?
    out:bool=True, # Include notebook cell outputs?
    include_base:bool=True, # Include full path in src?
    title:str=None, # Optional title attr for Documents element
    max_size:int=100000, # Skip files larger than this (bytes)
    max_total:int=10000000, # Max total output size in bytes
    readme_first:bool=False, # Prioritize README files at start of context?
    files_only:bool=False, # Return dict of {filename: size} instead of context?
    sigs_only:bool=False, # Return signatures instead of full text? (where supported by `codesigs` lib)
    ids:bool=True, # Include cell ids in notebooks?
    recursive:bool=True, # search subfolders
    symlinks:bool=True, # follow symlinks?
    file_glob:str=None, # Only include files matching glob
    file_re:str=None, # Only include files matching regex
    folder_re:str=None, # Only enter folders matching regex
    skip_file_glob:str=None, # Skip files matching glob
    skip_folder_re:str=None, # Skip folders matching regex,
    ret_folders:bool=False, # return folders, not just files
    sort:bool=True, # sort files by name within each folder
    exts:str | list=None, # list or comma-separated str of exts to include
):


```

```python
# print(sym2folderctx(test_eq))

```

--------------------------------

### Get Schema for a Function Name

Source: https://answerdotai.github.io/toolslm/funccall.html

Retrieves the schema for a given symbol name within a namespace, preserving the full dotted name. This schema can describe the function's name, description, and input parameters.

```python
def get_schema_nm(
    nm:str, ns, dot2dash:bool=False, kwargs:VAR_KEYWORD
):


```

```python
schema = get_schema_nm('ca.f', locals())
test_eq(schema['name'], 'ca.f')
schema
```