Read-only chat modes documentation is ambiguous

[PaulWaldo]

Issue

The docs at In-chat commands | aider say the folowing:l

• /architect Enter architect mode to discuss high-level design and architecture. If no prompt provided, switches to architect mode.
• /ask Ask questions about the code base without editing any files. If no prompt provided, switches to ask mode.

Based on these descriptions, it is difficult to tell which mode to use.

• How do the two differ?
• Isn't discussing architecture the same thing as asking things about the code base?
• What are the advantages and disadvantages of each?

Version and model info

Aider v0.71.1
Model: openai/hf:meta-llama/Llama-3.1-405B-Instruct with whole edit format
Git repo: .git with 32 files
Repo-map: using 512 tokens, auto refresh
Added project_docs/vision/project_vision.md to the chat (read-only).
Added project_docs/requirements/core_requirements.md to the chat (read-only).
Added ../../third-party/software-dev-prompt-library/prompts/architecture/assistant-specific/aider/tech-stack-prompt.md to the 
chat (read-only).
Added 
../../third-party/software-dev-prompt-library/prompts/requirements/assistant-specific/aider/initial-project-requirements-manag
ement-prompt.md to the chat (read-only).
Added go.mod to the chat (read-only).
Restored previous conversation history.
Config File (/Users/paul/src/personal/glimmer/.aider.conf.yml):
  model:             openai/hf:meta-llama/Llama-3.1-405B-Instruct
  openai-api-base:   https://glhf.chat/api/openai/v1
  map-tokens:        512
  attribute-committer:True
  attribute-commit-message-author:True
  attribute-author:  True
Defaults:
  --set-env:         []
  --api-key:         []
  --model-settings-file:.aider.model.settings.yml
  --model-metadata-file:.aider.model.metadata.json
  --cache-keepalive-pings:0
  --map-refresh:     auto
  --map-multiplier-no-files:2
  --input-history-file:/Users/paul/src/personal/glimmer/.aider.input.history
  --chat-history-file:/Users/paul/src/personal/glimmer/.aider.chat.history.md
  --user-input-color:#00cc00
  --tool-error-color:#FF2222
  --tool-warning-color:#FFA500
  --assistant-output-color:#0088ff
  --code-theme:      default
  --aiderignore:     /Users/paul/src/personal/glimmer/.aiderignore
  --lint-cmd:        []
  --test-cmd:        []
  --voice-format:    wav
  --voice-language:  en
  --encoding:        utf-8
  --env-file:        /Users/paul/src/personal/glimmer/.env

Option settings:
  - aiderignore: /Users/paul/src/personal/glimmer/.aiderignore
  - alias: None
  - analytics: None
  - analytics_disable: False
  - analytics_log: None
  - anthropic_api_key: None
  - api_key: []
  - apply: None
  - apply_clipboard_edits: False
  - assistant_output_color: #0088ff
  - attribute_author: True
  - attribute_commit_message_author: True
  - attribute_commit_message_committer: False
  - attribute_committer: True
  - auto_commits: True
  - auto_lint: True
  - auto_test: False
  - cache_keepalive_pings: 0
  - cache_prompts: False
  - chat_history_file: /Users/paul/src/personal/glimmer/.aider.chat.history.md
  - chat_language: None
  - check_update: True
  - code_theme: default
  - commit: False
  - commit_prompt: None
  - completion_menu_bg_color: None
  - completion_menu_color: None
  - completion_menu_current_bg_color: None
  - completion_menu_current_color: None
  - config: None
  - copy_paste: False
  - dark_mode: False
  - detect_urls: True
  - dirty_commits: True
  - dry_run: False
  - edit_format: None
  - editor: None
  - editor_edit_format: None
  - editor_model: None
  - encoding: utf-8
  - env_file: /Users/paul/src/personal/glimmer/.env
  - exit: False
  - fancy_input: True
  - file: None
  - files: []
  - git: True
  - gitignore: True
  - gui: False
  - input_history_file: /Users/paul/src/personal/glimmer/.aider.input.history
  - install_main_branch: False
  - just_check_update: False
  - light_mode: False
  - lint: False
  - lint_cmd: []
  - list_models: None
  - llm_history_file: None
  - load: None
  - map_multiplier_no_files: 2
  - map_refresh: auto
  - map_tokens: 512
  - max_chat_history_tokens: None
  - message: None
  - message_file: None
  - model: openai/hf:meta-llama/Llama-3.1-405B-Instruct
  - model_metadata_file: .aider.model.metadata.json
  - model_settings_file: .aider.model.settings.yml
  - multiline: False
  - openai_api_base: https://glhf.chat/api/openai/v1
  - openai_api_deployment_id: None
  - openai_api_key: None
  - openai_api_type: None
  - openai_api_version: None
  - openai_organization_id: None
  - pretty: True
  - read: None
  - restore_chat_history: False
  - set_env: []
  - show_diffs: False
  - show_model_warnings: True
  - show_prompts: False
  - show_release_notes: None
  - show_repo_map: False
  - skip_sanity_check_repo: False
  - stream: True
  - subtree_only: False
  - suggest_shell_commands: True
  - test: False
  - test_cmd: []
  - timeout: None
  - tool_error_color: #FF2222
  - tool_output_color: None
  - tool_warning_color: #FFA500
  - upgrade: False
  - user_input_color: #00cc00
  - verbose: False
  - verify_ssl: True
  - vim: False
  - voice_format: wav
  - voice_input_device: None
  - voice_language: en
  - watch_files: False
  - weak_model: None
  - yes_always: None

[paul-gauthier]

Thanks for trying aider and filing this issue. I've updated the description.

[paul-gauthier]

The change is available in the main branch. You can get it by installing the latest version from github:

aider --install-main-branch

# or...

python -m pip install --upgrade --upgrade-strategy only-if-needed git+https://github.com/Aider-AI/aider.git

If you have a chance to try it, let me know if it works better for you.

[PaulWaldo]

@paul-gauthier The wording change is a good start. I am still fuzzy on the distinction between the two modes. I gather from Separating code reasoning and editing | aider that ask mode uses the main model, but how do you select a model for use with architect mode and a model for editor mode, automatically switching between the two?

[github-actions]

I'm labeling this issue as stale because it has been open for 2 weeks with no activity. If there are no additional comments, I will close it in 7 days.

Note: A bot script made these updates to the issue.

[github-actions]

I'm closing this issue because it has been stalled for 3 weeks with no activity. Feel free to add a comment here and we can re-open it. Or feel free to file a new issue at any time.

Note: A bot script made these updates to the issue.