question_cmd: added testclass for the 'question_cmd()' function

README.md

@@ -46,80 +46,79 @@ cmm [global options] command [command options]
 The `question` command is used to ask, create, and process questions.
 
 ```bash
-cmm question [-t OTAGS]... [-k ATAGS]... [-x XTAGS]... [-o OUTTAGS]... [-A AI_ID] [-M MODEL] [-n NUM] [-m MAX] [-T TEMP] (-a QUESTION | -c QUESTION | -r [MESSAGE ...] | -p [MESSAGE ...]) [-O] [-s FILE]... [-S FILE]...
+cmm question [-t OTAGS]... [-k ATAGS]... [-x XTAGS]... [-o OUTTAGS]... [-A AI] [-M MODEL] [-n NUM] [-m MAX] [-T TEMP] (-a ASK | -c CREATE | -r REPEAT | -p PROCESS) [-O] [-s SOURCE]... [-S SOURCE]...
 ```
 
-* `-t, --or-tags OTAGS`: List of tags (one must match)
+* `-t, --or-tags OTAGS` : List of tags (one must match)
-* `-k, --and-tags ATAGS`: List of tags (all must match)
+* `-k, --and-tags ATAGS` : List of tags (all must match)
-* `-x, --exclude-tags XTAGS`: List of tags to exclude
+* `-x, --exclude-tags XTAGS` : List of tags to exclude
-* `-o, --output-tags OUTTAGS`: List of output tags (default: use input tags)
+* `-o, --output-tags OUTTAGS` : List of output tags (default: use input tags)
-* `-A, --AI AI_ID`: AI ID to use
+* `-A, --AI AI` : AI ID to use
-* `-M, --model MODEL`: Model to use
+* `-M, --model MODEL` : Model to use
-* `-n, --num-answers NUM`: Number of answers to request
+* `-n, --num-answers NUM` : Number of answers to request
-* `-m, --max-tokens MAX`: Max. number of tokens
+* `-m, --max-tokens MAX` : Max. number of tokens
-* `-T, --temperature TEMP`: Temperature value
+* `-T, --temperature TEMP` : Temperature value
-* `-a, --ask QUESTION`: Ask a question
+* `-a, --ask ASK` : Ask a question
-* `-c, --create QUESTION`: Create a question
+* `-c, --create CREATE` : Create a question
-* `-r, --repeat [MESSAGE ...]`: Repeat a question
+* `-r, --repeat REPEAT` : Repeat a question
-* `-p, --process [MESSAGE ...]`: Process existing questions
+* `-p, --process PROCESS` : Process existing questions
-* `-O, --overwrite`: Overwrite existing messages when repeating them
+* `-O, --overwrite` : Overwrite existing messages when repeating them
-* `-s, --source-text FILE`: Add content of a file to the query
+* `-s, --source-text SOURCE` : Add content of a file to the query
-* `-S, --source-code FILE`: Add source code file content to the chat history
+* `-S, --source-code SOURCE` : Add source code file content to the chat history
 
 #### Hist
 
 The `hist` command is used to print the chat history.
 
 ```bash
-cmm hist [-t OTAGS]... [-k ATAGS]... [-x XTAGS]... [-w] [-W] [-S] [-A SUBSTRING] [-Q SUBSTRING]
+cmm hist [-t OTAGS]... [-k ATAGS]... [-x XTAGS]... [-w] [-W] [-S] [-A ANSWER] [-Q QUESTION]
 ```
 
-* `-t, --or-tags OTAGS`: List of tags (one must match)
+* `-t, --or-tags OTAGS` : List of tags (one must match)
-* `-k, --and-tags ATAGS`: List of tags (all must match)
+* `-k, --and-tags ATAGS` : List of tags (all must match)
-* `-x, --exclude-tags XTAGS`: List of tags to exclude
+* `-x, --exclude-tags XTAGS` : List of tags to exclude
-* `-w, --with-tags`: Print chat history with tags
+* `-w, --with-tags` : Print chat history with tags
-* `-W, --with-files`: Print chat history with filenames
+* `-W, --with-files` : Print chat history with filenames
-* `-S, --source-code-only`: Only print embedded source code
+* `-S, --source-code-only` : Print only source code
-* `-A, --answer SUBSTRING`: Search for answer substring
+* `-A, --answer ANSWER` : Search for answer substring
-* `-Q, --question SUBSTRING`: Search for question substring
+* `-Q, --question QUESTION` : Search for question substring
 
 #### Tags
 
 The `tags` command is used to manage tags.
 
 ```bash
-cmm tags (-l | -p PREFIX | -c SUBSTRING)
+cmm tags (-l | -p PREFIX | -c CONTENT)
 ```
 
-* `-l, --list`: List all tags and their frequency
+* `-l, --list` : List all tags and their frequency
-* `-p, --prefix PREFIX`: Filter tags by prefix
+* `-p, --prefix PREFIX` : Filter tags by prefix
-* `-c, --contain SUBSTRING`: Filter tags by contained substring
+* `-c, --contain CONTENT` : Filter tags by contained substring
 
 #### Config
 
 The `config` command is used to manage the configuration.
 
 ```bash
-cmm config (-l | -m | -c FILE)
+cmm config (-l | -m | -c CREATE)
 ```
 
-* `-l, --list-models`: List all available models
+* `-l, --list-models` : List all available models
-* `-m, --print-model`: Print the currently configured model
+* `-m, --print-model` : Print the currently configured model
-* `-c, --create FILE`: Create config with default settings in the given file
+* `-c, --create CREATE` : Create config with default settings in the given file
 
 #### Print
 
 The `print` command is used to print message files.
 
 ```bash
-cmm print (-f FILE | -l) [-q | -a | -S]
+cmm print -f FILE [-q | -a | -S]
 ```
 
-* `-f, --file FILE`: Print given file
+* `-f, --file FILE` : File to print
-* `-l, --latest`: Print latest message
+* `-q, --question` : Print only question
-* `-q, --question`: Only print the question
+* `-a, --answer` : Print only answer
-* `-a, --answer`: Only print the answer
+* `-S, --only-source-code` : Print only source code
-* `-S, --only-source-code`: Only print embedded source code
 
 ### Examples
 
@@ -161,27 +160,18 @@ cmm print -f example.yaml
 
 ## Configuration
 
-The default configuration filename is `.config.yaml` (it is searched in the current working directory).
+The configuration file (`.config.yaml`) should contain the following fields:
-Use the command `cmm config --create <FILENAME>` to create a default configuration:
 
-```
+- `openai`:
-cache: .
+  - `api_key`: Your OpenAI API key.
-db: ./db/
+  - `model`: The name of the OpenAI model to use (e.g. "text-davinci-002").
-ais:
+  - `temperature`: The temperature value for the model.
-  myopenai:
+  - `max_tokens`: The maximum number of tokens for the model.
-    name: openai
+  - `top_p`: The top P value for the model.
-    model: gpt-3.5-turbo-16k
+  - `frequency_penalty`: The frequency penalty value.
-    api_key: 0123456789
+  - `presence_penalty`: The presence penalty value.
-    temperature: 1.0
+- `system`: The system message used to set the behavior of the AI.
-    max_tokens: 4000
+- `db`: The directory where the question-answer pairs are stored in YAML files.
-    top_p: 1.0
-    frequency_penalty: 0.0
-    presence_penalty: 0.0
-    system: You are an assistant
-```
-
-Each AI has its own section and the name of that section is called the 'AI ID' (in the example above it is `myopenai`).
-The AI ID can be any string, as long as it's unique within the `ais` section. The AI ID is used for all commands that support the `AI` parameter and it's also stored within each message file.
 
 ## Autocompletion
 
@@ -196,33 +186,33 @@ After adding this line, restart your shell or run `source <your-shell-config-fil
 ## Contributing
 
 ### Enable commit hooks
-```bash
+```
 pip install pre-commit
 pre-commit install
 ```
 ### Execute tests before opening a PR
-```bash
+```
 pytest
 ```
 ### Consider using `pyenv` / `pyenv-virtualenv`
 Short installation instructions:
 * install `pyenv`:
-```bash
+```
 cd ~
 git clone https://github.com/pyenv/pyenv .pyenv
 cd ~/.pyenv && src/configure && make -C src
 ```
-* make sure that `~/.pyenv/shims` and `~/.pyenv/bin` are the first entries in your `PATH`, e.g., by setting it in `~/.bashrc`
+* make sure that `~/.pyenv/shims` and `~/.pyenv/bin` are the first entries in your `PATH`, e. g. by setting it in `~/.bashrc`
 * add the following to your `~/.bashrc` (after setting `PATH`): `eval "$(pyenv init -)"`
-* create a new terminal or source the changes (e.g., `source ~/.bashrc`)
+* create a new terminal or source the changes (e. g. `source ~/.bashrc`)
 * install `virtualenv`
-```bash
+```
 git clone https://github.com/pyenv/pyenv-virtualenv.git $(pyenv root)/plugins/pyenv-virtualenv
 ```
 * add the following to your `~/.bashrc` (after the commands above): `eval "$(pyenv virtualenv-init -)`
-* create a new terminal or source the changes (e.g., `source ~/.bashrc`)
+* create a new terminal or source the changes (e. g. `source ~/.bashrc`)
-* go back to the `ChatMasterMind` repo and create a virtual environment with the latest `Python`, e.g., `3.11.4`:
+* go back to the `ChatMasterMind` repo and create a virtual environment with the latest `Python`, e. g. `3.11.4`:
-```bash
+```
 cd <CMM_REPO_PATH>
 pyenv install 3.11.4
 pyenv virtualenv 3.11.4 py311
@@ -233,3 +223,5 @@ pyenv activate py311
 ## License
 
 This project is licensed under the terms of the WTFPL License.
+
+

chatmastermind/ai_factory.py

@@ -3,20 +3,18 @@ Creates different AI instances, based on the given configuration.
 """
 
 import argparse
-from typing import cast, Optional
+from typing import cast
 from .configuration import Config, AIConfig, OpenAIConfig
 from .ai import AI, AIError
 from .ais.openai import OpenAI
 
 
-def create_ai(args: argparse.Namespace, config: Config,  # noqa: 11
+def create_ai(args: argparse.Namespace, config: Config) -> AI:  # noqa: 11
-              def_ai: Optional[str] = None,
-              def_model: Optional[str] = None) -> AI:
     """
-    Creates an AI subclass instance from the given arguments and configuration file.
+    Creates an AI subclass instance from the given arguments
-    If AI has not been set in the arguments, it searches for the ID 'default'. If
+    and configuration file. If AI has not been set in the
-    that is not found, it uses the first AI in the list. It's also possible to
+    arguments, it searches for the ID 'default'. If that
-    specify a default AI and model using 'def_ai' and 'def_model'.
+    is not found, it uses the first AI in the list.
     """
     ai_conf: AIConfig
     if hasattr(args, 'AI') and args.AI:
@@ -24,8 +22,6 @@ def create_ai(args: argparse.Namespace, config: Config,  # noqa: 11
             ai_conf = config.ais[args.AI]
         except KeyError:
             raise AIError(f"AI ID '{args.AI}' does not exist in this configuration")
-    elif def_ai:
-        ai_conf = config.ais[def_ai]
     elif 'default' in config.ais:
         ai_conf = config.ais['default']
     else:
@@ -38,8 +34,6 @@ def create_ai(args: argparse.Namespace, config: Config,  # noqa: 11
         ai = OpenAI(cast(OpenAIConfig, ai_conf))
         if hasattr(args, 'model') and args.model:
             ai.config.model = args.model
-        elif def_model:
-            ai.config.model = def_model
         if hasattr(args, 'max_tokens') and args.max_tokens:
             ai.config.max_tokens = args.max_tokens
         if hasattr(args, 'temperature') and args.temperature:

chatmastermind/ais/openai.py

@@ -44,7 +44,7 @@ class OpenAI(AI):
             frequency_penalty=self.config.frequency_penalty,
             presence_penalty=self.config.presence_penalty)
         question.answer = Answer(response['choices'][0]['message']['content'])
-        question.tags = set(otags) if otags is not None else None
+        question.tags = otags
         question.ai = self.ID
         question.model = self.config.model
         answers: list[Message] = [question]

chatmastermind/commands/hist.py

@@ -15,7 +15,7 @@ def hist_cmd(args: argparse.Namespace, config: Config) -> None:
                             tags_not=args.exclude_tags,
                             question_contains=args.question,
                             answer_contains=args.answer)
-    chat = ChatDB.from_dir(Path(config.cache),
+    chat = ChatDB.from_dir(Path('.'),
                            Path(config.db),
                            mfilter=mfilter)
     chat.print(args.source_code_only,

chatmastermind/commands/print.py

@@ -3,43 +3,25 @@ import argparse
 from pathlib import Path
 from ..configuration import Config
 from ..message import Message, MessageError
-from ..chat import ChatDB
-
-
-def print_message(message: Message, args: argparse.Namespace) -> None:
-    """
-    Print given message according to give arguments.
-    """
-    if args.question:
-        print(message.question)
-    elif args.answer:
-        print(message.answer)
-    elif message.answer and args.only_source_code:
-        for code in message.answer.source_code():
-            print(code)
-    else:
-        print(message.to_str())
 
 
 def print_cmd(args: argparse.Namespace, config: Config) -> None:
     """
     Handler for the 'print' command.
     """
-    # print given file
+    fname = Path(args.file)
-    if args.file is not None:
+    try:
-        fname = Path(args.file)
+        message = Message.from_file(fname)
-        try:
+        if message:
-            message = Message.from_file(fname)
+            if args.question:
-            if message:
+                print(message.question)
-                print_message(message, args)
+            elif args.answer:
-        except MessageError:
+                print(message.answer)
-            print(f"File is not a valid message: {args.file}")
+            elif message.answer and args.only_source_code:
-            sys.exit(1)
+                for code in message.answer.source_code():
-    # print latest message
+                    print(code)
-    elif args.latest:
+            else:
-        chat = ChatDB.from_dir(Path(config.cache), Path(config.db))
+                print(message.to_str())
-        latest = chat.msg_latest(loc='disk')
+    except MessageError:
-        if not latest:
+        print(f"File is not a valid message: {args.file}")
-            print("No message found!")
+        sys.exit(1)
-            sys.exit(1)
-        print_message(latest, args)

chatmastermind/commands/question.py

@@ -2,7 +2,6 @@ import sys
 import argparse
 from pathlib import Path
 from itertools import zip_longest
-from copy import deepcopy
 from ..configuration import Config
 from ..chat import ChatDB
 from ..message import Message, MessageFilter, MessageError, Question, source_code
@@ -72,7 +71,7 @@ def create_message(chat: ChatDB, args: argparse.Namespace) -> Message:
     full_question = '\n\n'.join(question_parts)
 
     message = Message(question=Question(full_question),
-                      tags=args.output_tags,
+                      tags=args.output_tags,  # FIXME
                       ai=args.AI,
                       model=args.model)
     # only write the new message to the cache,
@@ -93,8 +92,8 @@ def make_request(ai: AI, chat: ChatDB, message: Message, args: argparse.Namespac
     print(message.to_str())
     response: AIResponse = ai.request(message,
                                       chat,
-                                      args.num_answers,
+                                      args.num_answers,  # FIXME
-                                      args.output_tags)
+                                      args.output_tags)  # FIXME
     # only write the response messages to the cache,
     # don't add them to the internal list
     chat.cache_write(response.messages)
@@ -106,76 +105,14 @@ def make_request(ai: AI, chat: ChatDB, message: Message, args: argparse.Namespac
         print(response.tokens)
 
 
-def create_msg_args(msg: Message, args: argparse.Namespace) -> argparse.Namespace:
-    """
-    Takes an existing message and CLI arguments, and returns modified args based
-    on the members of the given message. Used e.g. when repeating messages, where
-    it's necessary to determine the correct AI, module and output tags to use
-    (either from the existing message or the given args).
-    """
-    msg_args = args
-    # if AI, model or output tags have not been specified,
-    # use those from the original message
-    if (args.AI is None
-       or args.model is None  # noqa: W503
-       or args.output_tags is None):  # noqa: W503
-        msg_args = deepcopy(args)
-        if args.AI is None and msg.ai is not None:
-            msg_args.AI = msg.ai
-        if args.model is None and msg.model is not None:
-            msg_args.model = msg.model
-        if args.output_tags is None and msg.tags is not None:
-            msg_args.output_tags = msg.tags
-    return msg_args
-
-
-def repeat_messages(messages: list[Message], chat: ChatDB, args: argparse.Namespace, config: Config) -> None:
-    """
-    Repeat the given messages using the given arguments.
-    """
-    ai: AI
-    for msg in messages:
-        msg_args = create_msg_args(msg, args)
-        ai = create_ai(msg_args, config)
-        print(f"--------- Repeating message '{msg.msg_id()}': ---------")
-        # overwrite the latest message if requested or empty
-        # -> but not if it's in the DB!
-        if ((msg.answer is None or msg_args.overwrite is True)
-           and (not chat.msg_in_db(msg))):  # noqa: W503
-            msg.clear_answer()
-            make_request(ai, chat, msg, msg_args)
-        # otherwise create a new one
-        else:
-            msg_args.ask = [msg.question]
-            message = create_message(chat, msg_args)
-            make_request(ai, chat, message, msg_args)
-
-
-def invert_input_tag_args(args: argparse.Namespace) -> None:
-    """
-    Changes the semantics of the INPUT tags for this command:
-    * not tags specified on the CLI -> no tags are selected
-    * empty tags specified on the CLI -> all tags are selected
-    """
-    if args.or_tags is None:
-        args.or_tags = set()
-    elif len(args.or_tags) == 0:
-        args.or_tags = None
-    if args.and_tags is None:
-        args.and_tags = set()
-    elif len(args.and_tags) == 0:
-        args.and_tags = None
-
-
 def question_cmd(args: argparse.Namespace, config: Config) -> None:
     """
     Handler for the 'question' command.
     """
-    invert_input_tag_args(args)
+    mfilter = MessageFilter(tags_or=args.or_tags if args.or_tags is not None else set(),
-    mfilter = MessageFilter(tags_or=args.or_tags,
+                            tags_and=args.and_tags if args.and_tags is not None else set(),
-                            tags_and=args.and_tags,
+                            tags_not=args.exclude_tags if args.exclude_tags is not None else set())
-                            tags_not=args.exclude_tags)
+    chat = ChatDB.from_dir(cache_path=Path('.'),
-    chat = ChatDB.from_dir(cache_path=Path(config.cache),
                            db_path=Path(config.db),
                            mfilter=mfilter)
     # if it's a new question, create and store it immediately
@@ -184,24 +121,30 @@ def question_cmd(args: argparse.Namespace, config: Config) -> None:
     if args.create:
         return
 
+    # create the correct AI instance
+    ai: AI = create_ai(args, config)
+
     # === ASK ===
     if args.ask:
-        ai: AI = create_ai(args, config)
         make_request(ai, chat, message, args)
     # === REPEAT ===
     elif args.repeat is not None:
-        repeat_msgs: list[Message] = []
+        lmessage = chat.msg_latest(loc='cache')
-        # repeat latest message
+        if lmessage is None:
-        if len(args.repeat) == 0:
+            print("No message found to repeat!")
-            lmessage = chat.msg_latest(loc='cache')
+            sys.exit(1)
-            if lmessage is None:
-                print("No message found to repeat!")
-                sys.exit(1)
-            repeat_msgs.append(lmessage)
-        # repeat given message(s)
         else:
-            repeat_msgs = chat.msg_find(args.repeat, loc='disk')
+            print(f"Repeating message '{lmessage.msg_id()}':")
-        repeat_messages(repeat_msgs, chat, args, config)
+        # overwrite the latest message if requested or empty
+        if lmessage.answer is None or args.overwrite is True:
+            lmessage.clear_answer()
+            make_request(ai, chat, lmessage, args)
+        # otherwise create a new one
+        else:
+            args.ask = [lmessage.question]
+            message = create_message(chat, args)
+            make_request(ai, chat, message, args)
+
     # === PROCESS ===
     elif args.process is not None:
         # TODO: process either all questions without an

chatmastermind/commands/tags.py

@@ -8,7 +8,7 @@ def tags_cmd(args: argparse.Namespace, config: Config) -> None:
     """
     Handler for the 'tags' command.
     """
-    chat = ChatDB.from_dir(cache_path=Path(config.cache),
+    chat = ChatDB.from_dir(cache_path=Path('.'),
                            db_path=Path(config.db))
     if args.list:
         tags_freq = chat.msg_tags_frequency(args.prefix, args.contain)

chatmastermind/configuration.py

@@ -116,7 +116,6 @@ class Config:
     """
     # all members have default values, so we can easily create
     # a default configuration
-    cache: str = '.'
     db: str = './db/'
     ais: dict[str, AIConfig] = field(default_factory=create_default_ai_configs)
 
@@ -133,7 +132,6 @@ class Config:
             ai_conf = ai_config_instance(conf['name'], conf)
             ais[ID] = ai_conf
         return cls(
-            cache=str(source['cache']) if 'cache' in source else '.',
             db=str(source['db']),
             ais=ais
         )

chatmastermind/main.py

@@ -34,23 +34,23 @@ def create_parser() -> argparse.ArgumentParser:
 
     # a parent parser for all commands that support tag selection
     tag_parser = argparse.ArgumentParser(add_help=False)
-    tag_arg = tag_parser.add_argument('-t', '--or-tags', nargs='*',
+    tag_arg = tag_parser.add_argument('-t', '--or-tags', nargs='+',
                                       help='List of tags (one must match)', metavar='OTAGS')
     tag_arg.completer = tags_completer  # type: ignore
-    atag_arg = tag_parser.add_argument('-k', '--and-tags', nargs='*',
+    atag_arg = tag_parser.add_argument('-k', '--and-tags', nargs='+',
                                        help='List of tags (all must match)', metavar='ATAGS')
     atag_arg.completer = tags_completer  # type: ignore
-    etag_arg = tag_parser.add_argument('-x', '--exclude-tags', nargs='*',
+    etag_arg = tag_parser.add_argument('-x', '--exclude-tags', nargs='+',
                                        help='List of tags to exclude', metavar='XTAGS')
     etag_arg.completer = tags_completer  # type: ignore
     otag_arg = tag_parser.add_argument('-o', '--output-tags', nargs='+',
-                                       help='List of output tags (default: use input tags)', metavar='OUTAGS')
+                                       help='List of output tags (default: use input tags)', metavar='OUTTAGS')
     otag_arg.completer = tags_completer  # type: ignore
 
     # a parent parser for all commands that support AI configuration
     ai_parser = argparse.ArgumentParser(add_help=False)
-    ai_parser.add_argument('-A', '--AI', help='AI ID to use', metavar='AI_ID')
+    ai_parser.add_argument('-A', '--AI', help='AI ID to use')
-    ai_parser.add_argument('-M', '--model', help='Model to use', metavar='MODEL')
+    ai_parser.add_argument('-M', '--model', help='Model to use')
     ai_parser.add_argument('-n', '--num-answers', help='Number of answers to request', type=int, default=1)
     ai_parser.add_argument('-m', '--max-tokens', help='Max. nr. of tokens', type=int)
     ai_parser.add_argument('-T', '--temperature', help='Temperature value', type=float)
@@ -61,15 +61,14 @@ def create_parser() -> argparse.ArgumentParser:
                                                aliases=['q'])
     question_cmd_parser.set_defaults(func=question_cmd)
     question_group = question_cmd_parser.add_mutually_exclusive_group(required=True)
-    question_group.add_argument('-a', '--ask', nargs='+', help='Ask a question', metavar='QUESTION')
+    question_group.add_argument('-a', '--ask', nargs='+', help='Ask a question')
-    question_group.add_argument('-c', '--create', nargs='+', help='Create a question', metavar='QUESTION')
+    question_group.add_argument('-c', '--create', nargs='+', help='Create a question')
-    question_group.add_argument('-r', '--repeat', nargs='*', help='Repeat a question', metavar='MESSAGE')
+    question_group.add_argument('-r', '--repeat', nargs='*', help='Repeat a question')
-    question_group.add_argument('-p', '--process', nargs='*', help='Process existing questions', metavar='MESSAGE')
+    question_group.add_argument('-p', '--process', nargs='*', help='Process existing questions')
     question_cmd_parser.add_argument('-O', '--overwrite', help='Overwrite existing messages when repeating them',
                                      action='store_true')
-    question_cmd_parser.add_argument('-s', '--source-text', nargs='+', help='Add content of a file to the query', metavar='FILE')
+    question_cmd_parser.add_argument('-s', '--source-text', nargs='+', help='Add content of a file to the query')
-    question_cmd_parser.add_argument('-S', '--source-code', nargs='+', help='Add source code file content to the chat history',
+    question_cmd_parser.add_argument('-S', '--source-code', nargs='+', help='Add source code file content to the chat history')
-                                     metavar='FILE')
 
     # 'hist' command parser
     hist_cmd_parser = cmdparser.add_parser('hist', parents=[tag_parser],
@@ -80,10 +79,10 @@ def create_parser() -> argparse.ArgumentParser:
                                  action='store_true')
     hist_cmd_parser.add_argument('-W', '--with-files', help="Print chat history with filenames.",
                                  action='store_true')
-    hist_cmd_parser.add_argument('-S', '--source-code-only', help='Only print embedded source code',
+    hist_cmd_parser.add_argument('-S', '--source-code-only', help='Print only source code',
                                  action='store_true')
-    hist_cmd_parser.add_argument('-A', '--answer', help='Search for answer substring', metavar='SUBSTRING')
+    hist_cmd_parser.add_argument('-A', '--answer', help='Search for answer substring')
-    hist_cmd_parser.add_argument('-Q', '--question', help='Search for question substring', metavar='SUBSTRING')
+    hist_cmd_parser.add_argument('-Q', '--question', help='Search for question substring')
 
     # 'tags' command parser
     tags_cmd_parser = cmdparser.add_parser('tags',
@@ -93,8 +92,8 @@ def create_parser() -> argparse.ArgumentParser:
     tags_group = tags_cmd_parser.add_mutually_exclusive_group(required=True)
     tags_group.add_argument('-l', '--list', help="List all tags and their frequency",
                             action='store_true')
-    tags_cmd_parser.add_argument('-p', '--prefix', help="Filter tags by prefix", metavar='PREFIX')
+    tags_cmd_parser.add_argument('-p', '--prefix', help="Filter tags by prefix")
-    tags_cmd_parser.add_argument('-c', '--contain', help="Filter tags by contained substring", metavar='SUBSTRING')
+    tags_cmd_parser.add_argument('-c', '--contain', help="Filter tags by contained substring")
 
     # 'config' command parser
     config_cmd_parser = cmdparser.add_parser('config',
@@ -107,20 +106,18 @@ def create_parser() -> argparse.ArgumentParser:
                               action='store_true')
     config_group.add_argument('-m', '--print-model', help="Print the currently configured model",
                               action='store_true')
-    config_group.add_argument('-c', '--create', help="Create config with default settings in the given file", metavar='FILE')
+    config_group.add_argument('-c', '--create', help="Create config with default settings in the given file")
 
     # 'print' command parser
     print_cmd_parser = cmdparser.add_parser('print',
                                             help="Print message files.",
                                             aliases=['p'])
     print_cmd_parser.set_defaults(func=print_cmd)
-    print_group = print_cmd_parser.add_mutually_exclusive_group(required=True)
+    print_cmd_parser.add_argument('-f', '--file', help='File to print', required=True)
-    print_group.add_argument('-f', '--file', help='Print given message file', metavar='FILE')
-    print_group.add_argument('-l', '--latest', help='Print latest message', action='store_true')
     print_cmd_modes = print_cmd_parser.add_mutually_exclusive_group()
-    print_cmd_modes.add_argument('-q', '--question', help='Only print the question', action='store_true')
+    print_cmd_modes.add_argument('-q', '--question', help='Print only question', action='store_true')
-    print_cmd_modes.add_argument('-a', '--answer', help='Only print the answer', action='store_true')
+    print_cmd_modes.add_argument('-a', '--answer', help='Print only answer', action='store_true')
-    print_cmd_modes.add_argument('-S', '--only-source-code', help='Only print embedded source code', action='store_true')
+    print_cmd_modes.add_argument('-S', '--only-source-code', help='Print only source code', action='store_true')
 
     argcomplete.autocomplete(parser)
     return parser

chatmastermind/message.py

@@ -222,36 +222,12 @@ class Message():
     ai_yaml_key: ClassVar[str] = 'ai'
     model_yaml_key: ClassVar[str] = 'model'
 
-    def __post_init__(self) -> None:
-        # convert some types that are often set wrong
-        if self.tags is not None and not isinstance(self.tags, set):
-            self.tags = set(self.tags)
-        if self.file_path is not None and not isinstance(self.file_path, pathlib.Path):
-            self.file_path = pathlib.Path(self.file_path)
-
     def __hash__(self) -> int:
         """
         The hash value is computed based on immutable members.
         """
         return hash((self.question, self.answer))
 
-    def equals(self, other: MessageInst, tags: bool = True, ai: bool = True,
-               model: bool = True, file_path: bool = True, verbose: bool = False) -> bool:
-        """
-        Compare this message with another one, including the metadata.
-        Return True if everything is identical, False otherwise.
-        """
-        equal: bool = ((not tags or (self.tags == other.tags))
-                       and (not ai or (self.ai == other.ai))  # noqa: W503
-                       and (not model or (self.model == other.model))  # noqa: W503
-                       and (not file_path or (self.file_path == other.file_path))  # noqa: W503
-                       and (self == other))  # noqa: W503
-        if not equal and verbose:
-            print("Messages not equal:")
-            print(self)
-            print(other)
-        return equal
-
     @classmethod
     def from_dict(cls: Type[MessageInst], data: dict[str, Any]) -> MessageInst:
         """
@@ -442,6 +418,9 @@ class Message():
             output.append(self.answer)
         return '\n'.join(output)
 
+    def __str__(self) -> str:
+        return self.to_str(True, True, False)
+
     def to_file(self, file_path: Optional[pathlib.Path]=None) -> None:  # noqa: 11
         """
         Write a Message to the given file. Type is determined based on the suffix.

tests/test_chat.py

@@ -10,18 +10,7 @@ from chatmastermind.message import Message, Question, Answer, Tag, MessageFilter
 from chatmastermind.chat import Chat, ChatDB, ChatError
 
 
-class TestChatBase(unittest.TestCase):
+class TestChat(unittest.TestCase):
-    def assert_messages_equal(self, msg1: list[Message], msg2: list[Message]) -> None:
-        """
-        Compare messages using more than just Question and Answer.
-        """
-        self.assertEqual(len(msg1), len(msg2))
-        for m1, m2 in zip(msg1, msg2):
-            # exclude the file_path, compare only Q, A and metadata
-            self.assertTrue(m1.equals(m2, file_path=False, verbose=True))
-
-
-class TestChat(TestChatBase):
     def setUp(self) -> None:
         self.chat = Chat([])
         self.message1 = Message(Question('Question 1'),
@@ -37,24 +26,24 @@ class TestChat(TestChatBase):
     def test_unique_id(self) -> None:
         # test with two identical messages
         self.chat.msg_add([self.message1, self.message1])
-        self.assert_messages_equal(self.chat.messages, [self.message1, self.message1])
+        self.assertSequenceEqual(self.chat.messages, [self.message1, self.message1])
         self.chat.msg_unique_id()
-        self.assert_messages_equal(self.chat.messages, [self.message1])
+        self.assertSequenceEqual(self.chat.messages, [self.message1])
         # test with two different messages
         self.chat.msg_add([self.message2])
         self.chat.msg_unique_id()
-        self.assert_messages_equal(self.chat.messages, [self.message1, self.message2])
+        self.assertSequenceEqual(self.chat.messages, [self.message1, self.message2])
 
     def test_unique_content(self) -> None:
         # test with two identical messages
         self.chat.msg_add([self.message1, self.message1])
-        self.assert_messages_equal(self.chat.messages, [self.message1, self.message1])
+        self.assertSequenceEqual(self.chat.messages, [self.message1, self.message1])
         self.chat.msg_unique_content()
-        self.assert_messages_equal(self.chat.messages, [self.message1])
+        self.assertSequenceEqual(self.chat.messages, [self.message1])
         # test with two different messages
         self.chat.msg_add([self.message2])
         self.chat.msg_unique_content()
-        self.assert_messages_equal(self.chat.messages, [self.message1, self.message2])
+        self.assertSequenceEqual(self.chat.messages, [self.message1, self.message2])
 
     def test_filter(self) -> None:
         self.chat.msg_add([self.message1, self.message2])
@@ -161,7 +150,7 @@ Answer 2
         self.assertEqual(mock_stdout.getvalue(), expected_output)
 
 
-class TestChatDB(TestChatBase):
+class TestChatDB(unittest.TestCase):
     def setUp(self) -> None:
         self.db_path = tempfile.TemporaryDirectory()
         self.cache_path = tempfile.TemporaryDirectory()
@@ -580,7 +569,7 @@ class TestChatDB(TestChatBase):
         search_names = ['0001', '0002.yaml', self.message3.msg_id(), str(self.message3.file_path)]
         expected_result = [self.message1, self.message2, self.message3]
         result = chat_db.msg_find(search_names, loc='all')
-        self.assert_messages_equal(result, expected_result)
+        self.assertSequenceEqual(result, expected_result)
 
     def test_msg_latest(self) -> None:
         chat_db = ChatDB.from_dir(pathlib.Path(self.cache_path.name),
@@ -606,47 +595,47 @@ class TestChatDB(TestChatBase):
         chat_db = ChatDB.from_dir(pathlib.Path(self.cache_path.name),
                                   pathlib.Path(self.db_path.name))
         all_messages = [self.message1, self.message2, self.message3, self.message4]
-        self.assert_messages_equal(chat_db.msg_gather(loc='all'), all_messages)
+        self.assertSequenceEqual(chat_db.msg_gather(loc='all'), all_messages)
-        self.assert_messages_equal(chat_db.msg_gather(loc='db'), all_messages)
+        self.assertSequenceEqual(chat_db.msg_gather(loc='db'), all_messages)
-        self.assert_messages_equal(chat_db.msg_gather(loc='mem'), all_messages)
+        self.assertSequenceEqual(chat_db.msg_gather(loc='mem'), all_messages)
-        self.assert_messages_equal(chat_db.msg_gather(loc='disk'), all_messages)
+        self.assertSequenceEqual(chat_db.msg_gather(loc='disk'), all_messages)
-        self.assert_messages_equal(chat_db.msg_gather(loc='cache'), [])
+        self.assertSequenceEqual(chat_db.msg_gather(loc='cache'), [])
         # add a new message, but only to the internal list
         new_message = Message(Question("What?"))
         all_messages_mem = all_messages + [new_message]
         chat_db.msg_add([new_message])
-        self.assert_messages_equal(chat_db.msg_gather(loc='mem'), all_messages_mem)
+        self.assertSequenceEqual(chat_db.msg_gather(loc='mem'), all_messages_mem)
-        self.assert_messages_equal(chat_db.msg_gather(loc='all'), all_messages_mem)
+        self.assertSequenceEqual(chat_db.msg_gather(loc='all'), all_messages_mem)
         # the nr. of messages on disk did not change -> expect old result
-        self.assert_messages_equal(chat_db.msg_gather(loc='db'), all_messages)
+        self.assertSequenceEqual(chat_db.msg_gather(loc='db'), all_messages)
-        self.assert_messages_equal(chat_db.msg_gather(loc='disk'), all_messages)
+        self.assertSequenceEqual(chat_db.msg_gather(loc='disk'), all_messages)
-        self.assert_messages_equal(chat_db.msg_gather(loc='cache'), [])
+        self.assertSequenceEqual(chat_db.msg_gather(loc='cache'), [])
         # test with MessageFilter
-        self.assert_messages_equal(chat_db.msg_gather(loc='all', mfilter=MessageFilter(tags_or={Tag('tag1')})),
+        self.assertSequenceEqual(chat_db.msg_gather(loc='all', mfilter=MessageFilter(tags_or={Tag('tag1')})),
-                                   [self.message1])
+                                 [self.message1])
-        self.assert_messages_equal(chat_db.msg_gather(loc='disk', mfilter=MessageFilter(tags_or={Tag('tag2')})),
+        self.assertSequenceEqual(chat_db.msg_gather(loc='disk', mfilter=MessageFilter(tags_or={Tag('tag2')})),
-                                   [self.message2])
+                                 [self.message2])
-        self.assert_messages_equal(chat_db.msg_gather(loc='cache', mfilter=MessageFilter(tags_or={Tag('tag3')})),
+        self.assertSequenceEqual(chat_db.msg_gather(loc='cache', mfilter=MessageFilter(tags_or={Tag('tag3')})),
-                                   [])
+                                 [])
-        self.assert_messages_equal(chat_db.msg_gather(loc='mem', mfilter=MessageFilter(question_contains="What")),
+        self.assertSequenceEqual(chat_db.msg_gather(loc='mem', mfilter=MessageFilter(question_contains="What")),
-                                   [new_message])
+                                 [new_message])
 
     def test_msg_move_and_gather(self) -> None:
         chat_db = ChatDB.from_dir(pathlib.Path(self.cache_path.name),
                                   pathlib.Path(self.db_path.name))
         all_messages = [self.message1, self.message2, self.message3, self.message4]
-        self.assert_messages_equal(chat_db.msg_gather(loc='db'), all_messages)
+        self.assertSequenceEqual(chat_db.msg_gather(loc='db'), all_messages)
-        self.assert_messages_equal(chat_db.msg_gather(loc='cache'), [])
+        self.assertSequenceEqual(chat_db.msg_gather(loc='cache'), [])
         # move first message to the cache
         chat_db.cache_move(self.message1)
-        self.assert_messages_equal(chat_db.msg_gather(loc='cache'), [self.message1])
+        self.assertSequenceEqual(chat_db.msg_gather(loc='cache'), [self.message1])
         self.assertEqual(self.message1.file_path.parent, pathlib.Path(self.cache_path.name))  # type: ignore [union-attr]
-        self.assert_messages_equal(chat_db.msg_gather(loc='db'), [self.message2, self.message3, self.message4])
+        self.assertSequenceEqual(chat_db.msg_gather(loc='db'), [self.message2, self.message3, self.message4])
-        self.assert_messages_equal(chat_db.msg_gather(loc='all'), all_messages)
+        self.assertSequenceEqual(chat_db.msg_gather(loc='all'), all_messages)
-        self.assert_messages_equal(chat_db.msg_gather(loc='disk'), all_messages)
+        self.assertSequenceEqual(chat_db.msg_gather(loc='disk'), all_messages)
-        self.assert_messages_equal(chat_db.msg_gather(loc='mem'), all_messages)
+        self.assertSequenceEqual(chat_db.msg_gather(loc='mem'), all_messages)
         # now move first message back to the DB
         chat_db.db_move(self.message1)
-        self.assert_messages_equal(chat_db.msg_gather(loc='cache'), [])
+        self.assertSequenceEqual(chat_db.msg_gather(loc='cache'), [])
         self.assertEqual(self.message1.file_path.parent, pathlib.Path(self.db_path.name))  # type: ignore [union-attr]
-        self.assert_messages_equal(chat_db.msg_gather(loc='db'), all_messages)
+        self.assertSequenceEqual(chat_db.msg_gather(loc='db'), all_messages)

tests/test_common.py

@@ -1,100 +0,0 @@
-import unittest
-import argparse
-from typing import Union, Optional
-from chatmastermind.configuration import Config, AIConfig
-from chatmastermind.tags import Tag
-from chatmastermind.message import Message, Answer
-from chatmastermind.chat import Chat
-from chatmastermind.ai import AI, AIResponse, Tokens, AIError
-
-
-class FakeAI(AI):
-    """
-    A mocked version of the 'AI' class.
-    """
-    ID: str
-    name: str
-    config: AIConfig
-
-    def models(self) -> list[str]:
-        raise NotImplementedError
-
-    def tokens(self, data: Union[Message, Chat]) -> int:
-        return 123
-
-    def print(self) -> None:
-        pass
-
-    def print_models(self) -> None:
-        pass
-
-    def __init__(self, ID: str, model: str, error: bool = False):
-        self.ID = ID
-        self.model = model
-        self.error = error
-
-    def request(self,
-                question: Message,
-                chat: Chat,
-                num_answers: int = 1,
-                otags: Optional[set[Tag]] = None) -> AIResponse:
-        """
-        Mock the 'ai.request()' function by either returning fake
-        answers or raising an exception.
-        """
-        if self.error:
-            raise AIError
-        question.answer = Answer("Answer 0")
-        question.tags = set(otags) if otags is not None else None
-        question.ai = self.ID
-        question.model = self.model
-        answers: list[Message] = [question]
-        for n in range(1, num_answers):
-            answers.append(Message(question=question.question,
-                                   answer=Answer(f"Answer {n}"),
-                                   tags=otags,
-                                   ai=self.ID,
-                                   model=self.model))
-        return AIResponse(answers, Tokens(10, 10, 20))
-
-
-class TestWithFakeAI(unittest.TestCase):
-    """
-    Base class for all tests that need to use the FakeAI.
-    """
-    def assert_msgs_equal_except_file_path(self, msg1: list[Message], msg2: list[Message]) -> None:
-        """
-        Compare messages using Question, Answer and all metadata excecot for the file_path.
-        """
-        self.assertEqual(len(msg1), len(msg2))
-        for m1, m2 in zip(msg1, msg2):
-            # exclude the file_path, compare only Q, A and metadata
-            self.assertTrue(m1.equals(m2, file_path=False, verbose=True))
-
-    def assert_msgs_all_equal(self, msg1: list[Message], msg2: list[Message]) -> None:
-        """
-        Compare messages using Question, Answer and ALL metadata.
-        """
-        self.assertEqual(len(msg1), len(msg2))
-        for m1, m2 in zip(msg1, msg2):
-            self.assertTrue(m1.equals(m2, verbose=True))
-
-    def assert_msgs_content_equal(self, msg1: list[Message], msg2: list[Message]) -> None:
-        """
-        Compare messages using only Question and Answer.
-        """
-        self.assertEqual(len(msg1), len(msg2))
-        for m1, m2 in zip(msg1, msg2):
-            self.assertEqual(m1, m2)
-
-    def mock_create_ai(self, args: argparse.Namespace, config: Config) -> AI:
-        """
-        Mocked 'create_ai' that returns a 'FakeAI' instance.
-        """
-        return FakeAI(args.AI, args.model)
-
-    def mock_create_ai_with_error(self, args: argparse.Namespace, config: Config) -> AI:
-        """
-        Mocked 'create_ai' that returns a 'FakeAI' instance.
-        """
-        return FakeAI(args.AI, args.model, error=True)

tests/test_configuration.py

@@ -57,7 +57,6 @@ class TestConfig(unittest.TestCase):
 
     def test_from_dict_should_create_config_from_dict(self) -> None:
         source_dict = {
-            'cache': '.',
             'db': './test_db/',
             'ais': {
                 'myopenai': {
@@ -74,7 +73,6 @@ class TestConfig(unittest.TestCase):
             }
         }
         config = Config.from_dict(source_dict)
-        self.assertEqual(config.cache, '.')
         self.assertEqual(config.db, './test_db/')
         self.assertEqual(len(config.ais), 1)
         self.assertEqual(config.ais['myopenai'].name, 'openai')
@@ -91,7 +89,6 @@ class TestConfig(unittest.TestCase):
 
     def test_from_file_should_load_config_from_file(self) -> None:
         source_dict = {
-            'cache': './test_cache/',
             'db': './test_db/',
             'ais': {
                 'default': {
@@ -111,7 +108,6 @@ class TestConfig(unittest.TestCase):
             yaml.dump(source_dict, f)
         config = Config.from_file(self.test_file.name)
         self.assertIsInstance(config, Config)
-        self.assertEqual(config.cache, './test_cache/')
         self.assertEqual(config.db, './test_db/')
         self.assertEqual(len(config.ais), 1)
         self.assertIsInstance(config.ais['default'], AIConfig)
@@ -119,7 +115,6 @@ class TestConfig(unittest.TestCase):
 
     def test_to_file_should_save_config_to_file(self) -> None:
         config = Config(
-            cache='./test_cache/',
             db='./test_db/',
             ais={
                 'myopenai': OpenAIConfig(
@@ -138,14 +133,12 @@ class TestConfig(unittest.TestCase):
         config.to_file(Path(self.test_file.name))
         with open(self.test_file.name, 'r') as f:
             saved_config = yaml.load(f, Loader=yaml.FullLoader)
-        self.assertEqual(saved_config['cache'], './test_cache/')
         self.assertEqual(saved_config['db'], './test_db/')
         self.assertEqual(len(saved_config['ais']), 1)
         self.assertEqual(saved_config['ais']['myopenai']['system'], 'Custom system')
 
     def test_from_file_error_unknown_ai(self) -> None:
         source_dict = {
-            'cache': './test_cache/',
             'db': './test_db/',
             'ais': {
                 'default': {

tests/test_question_cmd.py

@@ -1,30 +1,28 @@
 import os
+import unittest
 import argparse
 import tempfile
-from copy import copy
 from pathlib import Path
 from unittest import mock
 from unittest.mock import MagicMock, call
 from chatmastermind.configuration import Config
 from chatmastermind.commands.question import create_message, question_cmd
-from chatmastermind.tags import Tag
 from chatmastermind.message import Message, Question, Answer
-from chatmastermind.chat import Chat, ChatDB
+from chatmastermind.chat import ChatDB
-from chatmastermind.ai import AIError
+from chatmastermind.ai import AI, AIResponse, Tokens
-from .test_common import TestWithFakeAI
 
 
-class TestMessageCreate(TestWithFakeAI):
+class TestMessageCreate(unittest.TestCase):
     """
     Test if messages created by the 'question' command have
     the correct format.
     """
     def setUp(self) -> None:
         # create ChatDB structure
-        self.db_dir = tempfile.TemporaryDirectory()
+        self.db_path = tempfile.TemporaryDirectory()
-        self.cache_dir = tempfile.TemporaryDirectory()
+        self.cache_path = tempfile.TemporaryDirectory()
-        self.chat = ChatDB.from_dir(cache_path=Path(self.cache_dir.name),
+        self.chat = ChatDB.from_dir(cache_path=Path(self.cache_path.name),
-                                    db_path=Path(self.db_dir.name))
+                                    db_path=Path(self.db_path.name))
         # create some messages
         self.message_text = Message(Question("What is this?"),
                                     Answer("It is pure text"))
@@ -87,10 +85,10 @@ Aaaand again some text."""
 
     def test_message_file_created(self) -> None:
         self.args.ask = ["What is this?"]
-        cache_dir_files = self.message_list(self.cache_dir)
+        cache_dir_files = self.message_list(self.cache_path)
         self.assertEqual(len(cache_dir_files), 0)
         create_message(self.chat, self.args)
-        cache_dir_files = self.message_list(self.cache_dir)
+        cache_dir_files = self.message_list(self.cache_path)
         self.assertEqual(len(cache_dir_files), 1)
         message = Message.from_file(cache_dir_files[0])
         self.assertIsInstance(message, Message)
@@ -201,23 +199,21 @@ It is embedded code
 """))
 
 
-class TestQuestionCmd(TestWithFakeAI):
+class TestQuestionCmd(unittest.TestCase):
 
     def setUp(self) -> None:
         # create DB and cache
-        self.db_dir = tempfile.TemporaryDirectory()
+        self.db_path = tempfile.TemporaryDirectory()
-        self.cache_dir = tempfile.TemporaryDirectory()
+        self.cache_path = tempfile.TemporaryDirectory()
         # create configuration
         self.config = Config()
-        self.config.cache = self.cache_dir.name
-        self.config.db = self.db_dir.name
         # create a mock argparse.Namespace
         self.args = argparse.Namespace(
             ask=['What is the meaning of life?'],
             num_answers=1,
             output_tags=['science'],
-            AI='FakeAI',
+            AI='openai',
-            model='FakeModel',
+            model='gpt-3.5-turbo',
             or_tags=None,
             and_tags=None,
             exclude_tags=None,
@@ -225,68 +221,63 @@ class TestQuestionCmd(TestWithFakeAI):
             source_code=None,
             create=None,
             repeat=None,
-            process=None,
+            process=None
-            overwrite=None
         )
 
-    def message_list(self, tmp_dir: tempfile.TemporaryDirectory) -> list[Path]:
+    def input_message(self, args: argparse.Namespace) -> Message:
-        # exclude '.next'
-        return sorted([f for f in Path(tmp_dir.name).glob('*.[ty]*')])
-
-
-class TestQuestionCmdAsk(TestQuestionCmd):
-
-    @mock.patch('chatmastermind.commands.question.create_ai')
-    def test_ask_single_answer(self, mock_create_ai: MagicMock) -> None:
         """
-        Test single answer with no errors.
+        Create the expected input message for a question using the
+        given arguments.
         """
-        mock_create_ai.side_effect = self.mock_create_ai
+        # NOTE: we only use the first question from the "ask" list
-        expected_question = Message(Question(self.args.ask[0]),
+        # -> message creation using "question.create_message()" is
-                                    tags=set(self.args.output_tags),
+        #    tested above
-                                    ai=self.args.AI,
+        # the answer is always empty for the input message
-                                    model=self.args.model,
+        return Message(Question(args.ask[0]),
-                                    file_path=Path('<NOT COMPARED>'))
+                       tags=args.output_tags,
-        fake_ai = self.mock_create_ai(self.args, self.config)
+                       ai=args.AI,
-        expected_responses = fake_ai.request(expected_question,
+                       model=args.model)
-                                             Chat([]),
-                                             self.args.num_answers,
-                                             self.args.output_tags).messages
 
-        # execute the command
+    def response(self, args: argparse.Namespace) -> AIResponse:
-        question_cmd(self.args, self.config)
+        """
-
+        Create the expected AI response from the give arguments.
-        # check for the expected message files
+        """
-        chat = ChatDB.from_dir(Path(self.cache_dir.name),
+        input_msg = self.input_message(args)
-                               Path(self.db_dir.name))
+        response = AIResponse(messages=[], tokens=Tokens(10, 10, 20))
-        cached_msg = chat.msg_gather(loc='cache')
+        for n in range(args.num_answers):
-        self.assertEqual(len(self.message_list(self.cache_dir)), 1)
+            response_msg = Message(input_msg.question,
-        self.assert_msgs_equal_except_file_path(cached_msg, expected_responses)
+                                   Answer(f"Answer {n}"),
+                                   tags=input_msg.tags,
+                                   ai=input_msg.ai,
+                                   model=input_msg.model)
+            response.messages.append(response_msg)
+        return response
 
     @mock.patch('chatmastermind.commands.question.ChatDB.from_dir')
     @mock.patch('chatmastermind.commands.question.create_ai')
-    def test_ask_single_answer_mocked(self, mock_create_ai: MagicMock, mock_from_dir: MagicMock) -> None:
+    def test_ask_single_answer(self, mock_create_ai: MagicMock, mock_from_dir: MagicMock) -> None:
-        """
+
-        Test single answer with no errors (mocked ChatDB version).
+        # FIXME: this mock is only neccessary because the cache dir is not
-        """
+        # configurable in the configuration file
         chat = MagicMock(spec=ChatDB)
         mock_from_dir.return_value = chat
 
-        mock_create_ai.side_effect = self.mock_create_ai
+        # create a mock AI instance
-        expected_question = Message(Question(self.args.ask[0]),
+        ai = MagicMock(spec=AI)
-                                    tags=set(self.args.output_tags),
+        ai.request.return_value = self.response(self.args)
-                                    ai=self.args.AI,
+        mock_create_ai.return_value = ai
-                                    model=self.args.model,
+        expected_question = self.input_message(self.args)
-                                    file_path=Path('<NOT COMPARED>'))
+        expected_responses = ai.request.return_value.messages
-        fake_ai = self.mock_create_ai(self.args, self.config)
-        expected_responses = fake_ai.request(expected_question,
-                                             Chat([]),
-                                             self.args.num_answers,
-                                             self.args.output_tags).messages
 
         # execute the command
         question_cmd(self.args, self.config)
 
+        # check for correct request call
+        ai.request.assert_called_once_with(expected_question,
+                                           chat,
+                                           self.args.num_answers,
+                                           self.args.output_tags)
+
         # check for the correct ChatDB calls:
         # - initial question has been written (prior to the actual request)
         # - responses have been written (after the request)
@@ -296,280 +287,3 @@ class TestQuestionCmdAsk(TestQuestionCmd):
 
         # check that the messages have not been added to the internal message list
         chat.cache_add.assert_not_called()
-
-    @mock.patch('chatmastermind.commands.question.create_ai')
-    def test_ask_with_error(self, mock_create_ai: MagicMock) -> None:
-        """
-        Provoke an error during the AI request and verify that the question
-        has been correctly stored in the cache.
-        """
-        mock_create_ai.side_effect = self.mock_create_ai_with_error
-        expected_question = Message(Question(self.args.ask[0]),
-                                    tags=set(self.args.output_tags),
-                                    ai=self.args.AI,
-                                    model=self.args.model,
-                                    file_path=Path('<NOT COMPARED>'))
-
-        # execute the command
-        with self.assertRaises(AIError):
-            question_cmd(self.args, self.config)
-
-        # check for the expected message files
-        chat = ChatDB.from_dir(Path(self.cache_dir.name),
-                               Path(self.db_dir.name))
-        cached_msg = chat.msg_gather(loc='cache')
-        self.assertEqual(len(self.message_list(self.cache_dir)), 1)
-        self.assert_msgs_equal_except_file_path(cached_msg, [expected_question])
-
-
-class TestQuestionCmdRepeat(TestQuestionCmd):
-
-    @mock.patch('chatmastermind.commands.question.create_ai')
-    def test_repeat_single_question(self, mock_create_ai: MagicMock) -> None:
-        """
-        Repeat a single question.
-        """
-        mock_create_ai.side_effect = self.mock_create_ai
-        # create a message
-        message = Message(Question(self.args.ask[0]),
-                          Answer('Old Answer'),
-                          tags=set(self.args.output_tags),
-                          ai=self.args.AI,
-                          model=self.args.model,
-                          file_path=Path(self.cache_dir.name) / '0001.txt')
-        message.to_file()
-
-        # repeat the last question (without overwriting)
-        # -> expect two identical messages (except for the file_path)
-        self.args.ask = None
-        self.args.repeat = []
-        self.args.overwrite = False
-        expected_response = Message(Question(message.question),
-                                    Answer('Answer 0'),
-                                    ai=message.ai,
-                                    model=message.model,
-                                    tags=message.tags,
-                                    file_path=Path('<NOT COMPARED>'))
-        # we expect the original message + the one with the new response
-        expected_responses = [message] + [expected_response]
-        question_cmd(self.args, self.config)
-        chat = ChatDB.from_dir(Path(self.cache_dir.name),
-                               Path(self.db_dir.name))
-        cached_msg = chat.msg_gather(loc='cache')
-        print(self.message_list(self.cache_dir))
-        self.assertEqual(len(self.message_list(self.cache_dir)), 2)
-        self.assert_msgs_equal_except_file_path(cached_msg, expected_responses)
-
-    @mock.patch('chatmastermind.commands.question.create_ai')
-    def test_repeat_single_question_overwrite(self, mock_create_ai: MagicMock) -> None:
-        """
-        Repeat a single question and overwrite the old one.
-        """
-        mock_create_ai.side_effect = self.mock_create_ai
-        # create a message
-        message = Message(Question(self.args.ask[0]),
-                          Answer('Old Answer'),
-                          tags=set(self.args.output_tags),
-                          ai=self.args.AI,
-                          model=self.args.model,
-                          file_path=Path(self.cache_dir.name) / '0001.txt')
-        message.to_file()
-        chat = ChatDB.from_dir(Path(self.cache_dir.name),
-                               Path(self.db_dir.name))
-        cached_msg = chat.msg_gather(loc='cache')
-        assert cached_msg[0].file_path
-        cached_msg_file_id = cached_msg[0].file_path.stem
-
-        # repeat the last question (WITH overwriting)
-        # -> expect a single message afterwards (with a new answer)
-        self.args.ask = None
-        self.args.repeat = []
-        self.args.overwrite = True
-        expected_response = Message(Question(message.question),
-                                    Answer('Answer 0'),
-                                    ai=message.ai,
-                                    model=message.model,
-                                    tags=message.tags,
-                                    file_path=Path('<NOT COMPARED>'))
-        question_cmd(self.args, self.config)
-        cached_msg = chat.msg_gather(loc='cache')
-        self.assertEqual(len(self.message_list(self.cache_dir)), 1)
-        self.assert_msgs_equal_except_file_path(cached_msg, [expected_response])
-        # also check that the file ID has not been changed
-        assert cached_msg[0].file_path
-        self.assertEqual(cached_msg_file_id, cached_msg[0].file_path.stem)
-
-    @mock.patch('chatmastermind.commands.question.create_ai')
-    def test_repeat_single_question_after_error(self, mock_create_ai: MagicMock) -> None:
-        """
-        Repeat a single question after an error.
-        """
-        mock_create_ai.side_effect = self.mock_create_ai
-        # create a question WITHOUT an answer
-        # -> just like after an error, which is tested above
-        message = Message(Question(self.args.ask[0]),
-                          tags=set(self.args.output_tags),
-                          ai=self.args.AI,
-                          model=self.args.model,
-                          file_path=Path(self.cache_dir.name) / '0001.txt')
-        message.to_file()
-        chat = ChatDB.from_dir(Path(self.cache_dir.name),
-                               Path(self.db_dir.name))
-        cached_msg = chat.msg_gather(loc='cache')
-        assert cached_msg[0].file_path
-        cached_msg_file_id = cached_msg[0].file_path.stem
-
-        # repeat the last question (without overwriting)
-        # -> expect a single message because if the original has
-        #    no answer, it should be overwritten by default
-        self.args.ask = None
-        self.args.repeat = []
-        self.args.overwrite = False
-        expected_response = Message(Question(message.question),
-                                    Answer('Answer 0'),
-                                    ai=message.ai,
-                                    model=message.model,
-                                    tags=message.tags,
-                                    file_path=Path('<NOT COMPARED>'))
-        question_cmd(self.args, self.config)
-        cached_msg = chat.msg_gather(loc='cache')
-        self.assertEqual(len(self.message_list(self.cache_dir)), 1)
-        self.assert_msgs_equal_except_file_path(cached_msg, [expected_response])
-        # also check that the file ID has not been changed
-        assert cached_msg[0].file_path
-        self.assertEqual(cached_msg_file_id, cached_msg[0].file_path.stem)
-
-    @mock.patch('chatmastermind.commands.question.create_ai')
-    def test_repeat_single_question_new_args(self, mock_create_ai: MagicMock) -> None:
-        """
-        Repeat a single question with new arguments.
-        """
-        mock_create_ai.side_effect = self.mock_create_ai
-        # create a message
-        message = Message(Question(self.args.ask[0]),
-                          Answer('Old Answer'),
-                          tags=set(self.args.output_tags),
-                          ai=self.args.AI,
-                          model=self.args.model,
-                          file_path=Path(self.cache_dir.name) / '0001.txt')
-        message.to_file()
-        chat = ChatDB.from_dir(Path(self.cache_dir.name),
-                               Path(self.db_dir.name))
-        cached_msg = chat.msg_gather(loc='cache')
-        assert cached_msg[0].file_path
-
-        # repeat the last question with new arguments (without overwriting)
-        # -> expect two messages with identical question but different metadata and new answer
-        self.args.ask = None
-        self.args.repeat = []
-        self.args.overwrite = False
-        self.args.output_tags = ['newtag']
-        self.args.AI = 'newai'
-        self.args.model = 'newmodel'
-        new_expected_response = Message(Question(message.question),
-                                        Answer('Answer 0'),
-                                        ai='newai',
-                                        model='newmodel',
-                                        tags={Tag('newtag')},
-                                        file_path=Path('<NOT COMPARED>'))
-        question_cmd(self.args, self.config)
-        cached_msg = chat.msg_gather(loc='cache')
-        self.assertEqual(len(self.message_list(self.cache_dir)), 2)
-        self.assert_msgs_equal_except_file_path(cached_msg, [message] + [new_expected_response])
-
-    @mock.patch('chatmastermind.commands.question.create_ai')
-    def test_repeat_single_question_new_args_overwrite(self, mock_create_ai: MagicMock) -> None:
-        """
-        Repeat a single question with new arguments, overwriting the old one.
-        """
-        mock_create_ai.side_effect = self.mock_create_ai
-        # create a message
-        message = Message(Question(self.args.ask[0]),
-                          Answer('Old Answer'),
-                          tags=set(self.args.output_tags),
-                          ai=self.args.AI,
-                          model=self.args.model,
-                          file_path=Path(self.cache_dir.name) / '0001.txt')
-        message.to_file()
-        chat = ChatDB.from_dir(Path(self.cache_dir.name),
-                               Path(self.db_dir.name))
-        cached_msg = chat.msg_gather(loc='cache')
-        assert cached_msg[0].file_path
-
-        # repeat the last question with new arguments
-        self.args.ask = None
-        self.args.repeat = []
-        self.args.overwrite = True
-        self.args.output_tags = ['newtag']
-        self.args.AI = 'newai'
-        self.args.model = 'newmodel'
-        new_expected_response = Message(Question(message.question),
-                                        Answer('Answer 0'),
-                                        ai='newai',
-                                        model='newmodel',
-                                        tags={Tag('newtag')},
-                                        file_path=Path('<NOT COMPARED>'))
-        question_cmd(self.args, self.config)
-        cached_msg = chat.msg_gather(loc='cache')
-        self.assertEqual(len(self.message_list(self.cache_dir)), 1)
-        self.assert_msgs_equal_except_file_path(cached_msg, [new_expected_response])
-
-    @mock.patch('chatmastermind.commands.question.create_ai')
-    def test_repeat_multiple_questions(self, mock_create_ai: MagicMock) -> None:
-        """
-        Repeat multiple  questions.
-        """
-        mock_create_ai.side_effect = self.mock_create_ai
-        # 1. === create three questions ===
-        # cached message without an answer
-        message1 = Message(Question(self.args.ask[0]),
-                           tags=self.args.output_tags,
-                           ai=self.args.AI,
-                           model=self.args.model,
-                           file_path=Path(self.cache_dir.name) / '0001.txt')
-        # cached message with an answer
-        message2 = Message(Question(self.args.ask[0]),
-                           Answer('Old Answer'),
-                           tags=self.args.output_tags,
-                           ai=self.args.AI,
-                           model=self.args.model,
-                           file_path=Path(self.cache_dir.name) / '0002.txt')
-        # DB message without an answer
-        message3 = Message(Question(self.args.ask[0]),
-                           tags=self.args.output_tags,
-                           ai=self.args.AI,
-                           model=self.args.model,
-                           file_path=Path(self.db_dir.name) / '0003.txt')
-        message1.to_file()
-        message2.to_file()
-        message3.to_file()
-        questions = [message1, message2, message3]
-        expected_responses: list[Message] = []
-        fake_ai = self.mock_create_ai(self.args, self.config)
-        for question in questions:
-            # since the  message's answer is modified, we use a copy
-            # -> the original is used for comparison below
-            expected_responses += fake_ai.request(copy(question),
-                                                  Chat([]),
-                                                  self.args.num_answers,
-                                                  set(self.args.output_tags)).messages
-
-        # 2. === repeat all three questions (without overwriting) ===
-        self.args.ask = None
-        self.args.repeat = ['0001', '0002', '0003']
-        self.args.overwrite = False
-        question_cmd(self.args, self.config)
-        # two new files should be in the cache directory
-        # * the repeated cached message with answer
-        # * the repeated DB message
-        # -> the cached message without answer should be overwritten
-        self.assertEqual(len(self.message_list(self.cache_dir)), 4)
-        self.assertEqual(len(self.message_list(self.db_dir)), 1)
-        expected_cache_messages = [expected_responses[0], message2, expected_responses[1], expected_responses[2]]
-        chat = ChatDB.from_dir(Path(self.cache_dir.name),
-                               Path(self.db_dir.name))
-        cached_msg = chat.msg_gather(loc='cache')
-        self.assert_msgs_equal_except_file_path(cached_msg, expected_cache_messages)
-        # check that the DB message has not been modified at all
-        db_msg = chat.msg_gather(loc='db')
-        self.assert_msgs_all_equal(db_msg, [message3])