set version to 0.69.2.dev

Update conventions.md to fix url

.github/workflows/issues.yml

@@ -0,0 +1,29 @@
+name: Process GitHub Issues
+on:
+  schedule:
+    - cron: '0 */12 * * *'  # Run every 12 hours
+  workflow_dispatch:  # Allow manual triggers
+
+jobs:
+  process-issues:
+    runs-on: ubuntu-latest
+    permissions:
+      issues: write  # Required to modify issues
+    
+    steps:
+      - uses: actions/checkout@v3
+      
+      - name: Set up Python
+        uses: actions/setup-python@v4
+        with:
+          python-version: '3.x'
+          
+      - name: Install dependencies
+        run: |
+          python -m pip install --upgrade pip
+          pip install requests python-dotenv tqdm
+          
+      - name: Run issues script
+        env:
+          GITHUB_TOKEN: ${{ secrets.GITHUB_TOKEN }}
+        run: python scripts/issues.py --yes

.github/workflows/pages.yml

@@ -84,4 +84,4 @@ jobs:
 
       - name: Run linkchecker
         run: |
-          linkchecker https://aider.chat
+          linkchecker --ignore-url='.+\.(mp4|mov|avi)' https://aider.chat

.gitignore

@@ -13,4 +13,5 @@ _site
 aider/__version__.py
 aider/_version.py
 .venv/
+.#*
 .gitattributes

HISTORY.md

@@ -1,6 +1,58 @@
 # Release history
 
-### main branch
+### Aider v0.69.0
+
+- [Watch files](https://aider.chat/docs/usage/watch.html) improvements:
+  - Use `# ... AI?` comments to trigger aider and ask questions about your code.
+  - Now watches *all* files, not just certain source files.
+  - Use `# AI comments`, `// AI comments`, or `-- AI comments` to give aider instructions in any text file.
+- Full support for Gemini Flash 2.0 Exp:
+  - `aider --model flash` or `aider --model gemini/gemini-2.0-flash-exp`
+- [New `--multiline` flag and `/multiline-mode` command](https://aider.chat/docs/usage/commands.html#entering-multi-line-chat-messages) makes ENTER a soft newline and META-ENTER send the message, by @miradnanali.
+- `/copy-context <instructions>` now takes optional "instructions" when [copying code context to the clipboard](https://aider.chat/docs/usage/copypaste.html#copy-aiders-code-context-to-your-clipboard-paste-into-the-web-ui).
+- Improved clipboard error handling with helpful requirements install info.
+- Ask 5% of users if they want to opt-in to analytics.
+- `/voice` now lets you edit the transcribed text before sending.
+- Disabled auto-complete in Y/N prompts.
+- Aider wrote 68% of the code in this release.
+
+### Aider v0.68.0
+
+- [Aider works with LLM web chat UIs](https://aider.chat/docs/usage/copypaste.html).
+  - New `--copy-paste` mode.
+  - New `/copy-context` command.
+- [Set API keys and other environment variables for all providers from command line or yaml conf file](https://aider.chat/docs/config/aider_conf.html#storing-llm-keys).
+  - New `--api-key provider=key` setting.
+  - New `--set-env VAR=value` setting.
+- Added bash and zsh support to `--watch-files`.
+- Better error messages when missing dependencies for Gemini and Bedrock models.
+- Control-D now properly exits the program.
+- Don't count token costs when API provider returns a hard error.
+- Bugfix so watch files works with files that don't have tree-sitter support.
+- Bugfix so o1 models can be used as weak model.
+- Updated shell command prompt.
+- Added docstrings for all Coders.
+- Reorganized command line arguments with improved help messages and grouping.
+- Use the exact `sys.python` for self-upgrades.
+- Added experimental Gemini models.
+- Aider wrote 71% of the code in this release.
+
+### Aider v0.67.0
+
+- [Use aider in your IDE or editor](https://aider.chat/docs/usage/watch.html).
+  - Run `aider --watch-files` and it will watch for instructions you add to your source files.
+  - One-liner `# ...` or `// ...` comments that start or end with "AI" are instructions to aider.
+  - When aider sees "AI!" it reads and follows all the instructions in AI comments.
+- Support for new Amazon Bedrock Nova models.
+- When `/run` or `/test` have non-zero exit codes, pre-fill "Fix that" into the next message prompt.
+- `/diff` now invokes `git diff` to use your preferred diff tool.
+- Added Ctrl-Z support for process suspension.
+- Spinner now falls back to ASCII art if fancy symbols throw unicode errors.
+- `--read` now expands `~` home dirs.
+- Enabled exception capture in analytics.
+- [Aider wrote 61% of the code in this release.](https://aider.chat/HISTORY.html)
+
+### Aider v0.66.0
 
 - PDF support for Sonnet and Gemini models.
 - Added `--voice-input-device` to select audio input device for voice recording, by @preynal.

MANIFEST.in

@@ -0,0 +1,14 @@
+# This needs to sync with aider/help_pats.py
+
+global-exclude .DS_Store
+recursive-exclude aider/website/examples *
+recursive-exclude aider/website/_posts *
+exclude aider/website/HISTORY.md
+exclude aider/website/docs/benchmarks*.md
+exclude aider/website/docs/ctags.md
+exclude aider/website/docs/unified-diffs.md
+exclude aider/website/docs/leaderboards/index.md
+recursive-exclude aider/website/assets *
+recursive-exclude aider/website *.js
+recursive-exclude aider/website *.html
+recursive-exclude aider/website *.yml

README.md

@@ -43,28 +43,27 @@ VIDEO END -->
 cog.out(open("aider/website/_includes/get-started.md").read())
 ]]]-->
 
-You can get started quickly like this:
+You can get started quickly like this, with python 3.8-3.13:
 
-```
-python -m pip install -U aider-chat
+```bash
+python -m pip install aider-install
+aider-install
 
-# Change directory into a git repo
+# Change directory into your code base
 cd /to/your/git/repo
 
 # Work with Claude 3.5 Sonnet on your repo
-export ANTHROPIC_API_KEY=your-key-goes-here
-aider
+aider --model sonnet --anthropic-api-key your-key-goes-here
 
 # Work with GPT-4o on your repo
-export OPENAI_API_KEY=your-key-goes-here
-aider 
+aider --model gpt-4o --openai-api-key your-key-goes-here
 ```
 <!--[[[end]]]-->
 
 See the
 [installation instructions](https://aider.chat/docs/install.html)
-and other
-[documentation](https://aider.chat/docs/usage.html)
+and
+[usage documentation](https://aider.chat/docs/usage.html)
 for more details.
 
 ## Features

aider/__init__.py

@@ -1,6 +1,6 @@
 from packaging import version
 
-__version__ = "0.66.1.dev"
+__version__ = "0.69.2.dev"
 safe_version = __version__
 
 try:

aider/analytics.py

@@ -5,7 +5,7 @@ import time
 import uuid
 from pathlib import Path
 
-from mixpanel import Mixpanel, MixpanelException
+from mixpanel import MixpanelException
 from posthog import Posthog
 
 from aider import __version__
@@ -50,8 +50,14 @@ class Analytics:
             self.disable(False)
             return
 
-        self.mp = Mixpanel(mixpanel_project_token)
-        self.ph = Posthog(project_api_key=posthog_project_api_key, host=posthog_host)
+        # self.mp = Mixpanel(mixpanel_project_token)
+        self.ph = Posthog(
+            project_api_key=posthog_project_api_key,
+            host=posthog_host,
+            on_error=self.posthog_error,
+            enable_exception_autocapture=True,
+            super_properties=self.get_system_info(),  # Add system info to all events
+        )
 
     def disable(self, permanently):
         self.mp = None
@@ -78,7 +84,7 @@ class Analytics:
         if not self.user_id:
             return False
 
-        PERCENT = 2.5
+        PERCENT = 5
         return self.is_uuid_in_percentage(self.user_id, PERCENT)
 
     def is_uuid_in_percentage(self, uuid_str, percent):
@@ -159,6 +165,7 @@ class Analytics:
             "os_platform": platform.system(),
             "os_release": platform.release(),
             "machine": platform.machine(),
+            "aider_version": __version__,
         }
 
     def _redact_model_name(self, model):
@@ -172,6 +179,13 @@ class Analytics:
             return model.name.split("/")[0] + "/REDACTED"
         return None
 
+    def posthog_error(self):
+        """disable posthog if we get an error"""
+        print("X" * 100)
+        # https://github.com/PostHog/posthog-python/blob/9e1bb8c58afaa229da24c4fb576c08bb88a75752/posthog/consumer.py#L86
+        # https://github.com/Aider-AI/aider/issues/2532
+        self.ph = None
+
     def event(self, event_name, main_model=None, **kwargs):
         if not self.mp and not self.ph and not self.logfile:
             return
@@ -184,7 +198,6 @@ class Analytics:
             properties["editor_model"] = self._redact_model_name(main_model.editor_model)
 
         properties.update(kwargs)
-        properties.update(self.get_system_info())  # Add system info to all events
 
         # Handle numeric values
         for key, value in properties.items():
@@ -193,8 +206,6 @@ class Analytics:
             else:
                 properties[key] = str(value)
 
-        properties["aider_version"] = __version__
-
         if self.mp:
             try:
                 self.mp.track(self.user_id, event_name, dict(properties))
@@ -211,6 +222,9 @@ class Analytics:
                 "user_id": self.user_id,
                 "time": int(time.time()),
             }
-            with open(self.logfile, "a") as f:
-                json.dump(log_entry, f)
-                f.write("\n")
+            try:
+                with open(self.logfile, "a") as f:
+                    json.dump(log_entry, f)
+                    f.write("\n")
+            except OSError:
+                pass  # Ignore OS errors when writing to logfile

aider/args.py

@@ -28,22 +28,10 @@ def get_parser(default_config_files, git_root):
         config_file_parser_class=configargparse.YAMLConfigFileParser,
         auto_env_var_prefix="AIDER_",
     )
-    group = parser.add_argument_group("Main")
+    group = parser.add_argument_group("Main model")
     group.add_argument(
         "files", metavar="FILE", nargs="*", help="files to edit with an LLM (optional)"
     )
-    group.add_argument(
-        "--openai-api-key",
-        metavar="OPENAI_API_KEY",
-        env_var="OPENAI_API_KEY",
-        help="Specify the OpenAI API key",
-    )
-    group.add_argument(
-        "--anthropic-api-key",
-        metavar="ANTHROPIC_API_KEY",
-        env_var="ANTHROPIC_API_KEY",
-        help="Specify the Anthropic API key",
-    )
     group.add_argument(
         "--model",
         metavar="MODEL",
@@ -83,7 +71,7 @@ def get_parser(default_config_files, git_root):
         const=gpt_4_model,
         help=f"Use {gpt_4_model} model for the main chat",
     )
-    gpt_4o_model = "gpt-4o-2024-08-06"
+    gpt_4o_model = "gpt-4o"
     group.add_argument(
         "--4o",
         action="store_const",
@@ -144,43 +132,59 @@ def get_parser(default_config_files, git_root):
     )
 
     ##########
-    group = parser.add_argument_group("Model Settings")
+    group = parser.add_argument_group("API Keys and settings")
+    group.add_argument(
+        "--openai-api-key",
+        help="Specify the OpenAI API key",
+    )
+    group.add_argument(
+        "--anthropic-api-key",
+        help="Specify the Anthropic API key",
+    )
+    group.add_argument(
+        "--openai-api-base",
+        help="Specify the api base url",
+    )
+    group.add_argument(
+        "--openai-api-type",
+        help="(deprecated, use --set-env OPENAI_API_TYPE=<value>)",
+    )
+    group.add_argument(
+        "--openai-api-version",
+        help="(deprecated, use --set-env OPENAI_API_VERSION=<value>)",
+    )
+    group.add_argument(
+        "--openai-api-deployment-id",
+        help="(deprecated, use --set-env OPENAI_API_DEPLOYMENT_ID=<value>)",
+    )
+    group.add_argument(
+        "--openai-organization-id",
+        help="(deprecated, use --set-env OPENAI_ORGANIZATION=<value>)",
+    )
+    group.add_argument(
+        "--set-env",
+        action="append",
+        metavar="ENV_VAR_NAME=value",
+        help="Set an environment variable (to control API settings, can be used multiple times)",
+        default=[],
+    )
+    group.add_argument(
+        "--api-key",
+        action="append",
+        metavar="PROVIDER=KEY",
+        help=(
+            "Set an API key for a provider (eg: --api-key provider=<key> sets"
+            " PROVIDER_API_KEY=<key>)"
+        ),
+        default=[],
+    )
+    group = parser.add_argument_group("Model settings")
     group.add_argument(
         "--list-models",
         "--models",
         metavar="MODEL",
         help="List known models which match the (partial) MODEL name",
     )
-    group.add_argument(
-        "--openai-api-base",
-        metavar="OPENAI_API_BASE",
-        env_var="OPENAI_API_BASE",
-        help="Specify the api base url",
-    )
-    group.add_argument(
-        "--openai-api-type",
-        metavar="OPENAI_API_TYPE",
-        env_var="OPENAI_API_TYPE",
-        help="Specify the api_type",
-    )
-    group.add_argument(
-        "--openai-api-version",
-        metavar="OPENAI_API_VERSION",
-        env_var="OPENAI_API_VERSION",
-        help="Specify the api_version",
-    )
-    group.add_argument(
-        "--openai-api-deployment-id",
-        metavar="OPENAI_API_DEPLOYMENT_ID",
-        env_var="OPENAI_API_DEPLOYMENT_ID",
-        help="Specify the deployment_id",
-    )
-    group.add_argument(
-        "--openai-organization-id",
-        metavar="OPENAI_ORGANIZATION_ID",
-        env_var="OPENAI_ORGANIZATION_ID",
-        help="Specify the OpenAI organization ID",
-    )
     group.add_argument(
         "--model-settings-file",
         metavar="MODEL_SETTINGS_FILE",
@@ -261,17 +265,9 @@ def get_parser(default_config_files, git_root):
             " If unspecified, defaults to the model's max_chat_history_tokens."
         ),
     )
-    # This is a duplicate of the argument in the preparser and is a no-op by this time of
-    # argument parsing, but it's here so that the help is displayed as expected.
-    group.add_argument(
-        "--env-file",
-        metavar="ENV_FILE",
-        default=default_env_file(git_root),
-        help="Specify the .env file to load (default: .env in git root)",
-    )
 
     ##########
-    group = parser.add_argument_group("Cache Settings")
+    group = parser.add_argument_group("Cache settings")
     group.add_argument(
         "--cache-prompts",
         action=argparse.BooleanOptionalAction,
@@ -286,7 +282,7 @@ def get_parser(default_config_files, git_root):
     )
 
     ##########
-    group = parser.add_argument_group("Repomap Settings")
+    group = parser.add_argument_group("Repomap settings")
     group.add_argument(
         "--map-tokens",
         type=int,
@@ -343,7 +339,7 @@ def get_parser(default_config_files, git_root):
     )
 
     ##########
-    group = parser.add_argument_group("Output Settings")
+    group = parser.add_argument_group("Output settings")
     group.add_argument(
         "--dark-mode",
         action="store_true",
@@ -442,7 +438,7 @@ def get_parser(default_config_files, git_root):
     )
 
     ##########
-    group = parser.add_argument_group("Git Settings")
+    group = parser.add_argument_group("Git settings")
     group.add_argument(
         "--git",
         action=argparse.BooleanOptionalAction,
@@ -529,6 +525,12 @@ def get_parser(default_config_files, git_root):
         help="Skip the sanity check for the git repository (default: False)",
         default=False,
     )
+    group.add_argument(
+        "--watch-files",
+        action=argparse.BooleanOptionalAction,
+        default=False,
+        help="Enable/disable watching files for ai coding comments (default: False)",
+    )
     group = parser.add_argument_group("Fixing and committing")
     group.add_argument(
         "--lint",
@@ -589,37 +591,8 @@ def get_parser(default_config_files, git_root):
         default=False,
     )
 
-    group = parser.add_argument_group("Other Settings")
-    group.add_argument(
-        "--file",
-        action="append",
-        metavar="FILE",
-        help="specify a file to edit (can be used multiple times)",
-    )
-    group.add_argument(
-        "--read",
-        action="append",
-        metavar="FILE",
-        help="specify a read-only file (can be used multiple times)",
-    )
-    group.add_argument(
-        "--vim",
-        action="store_true",
-        help="Use VI editing mode in the terminal (default: False)",
-        default=False,
-    )
-    group.add_argument(
-        "--chat-language",
-        metavar="CHAT_LANGUAGE",
-        default=None,
-        help="Specify the language to use in the chat (default: None, uses system settings)",
-    )
-    group.add_argument(
-        "--version",
-        action="version",
-        version=f"%(prog)s {__version__}",
-        help="Show the version number and exit",
-    )
+    #########
+    group = parser.add_argument_group("Upgrading")
     group.add_argument(
         "--just-check-update",
         action="store_true",
@@ -652,47 +625,14 @@ def get_parser(default_config_files, git_root):
         default=False,
     )
     group.add_argument(
-        "--apply",
-        metavar="FILE",
-        help="Apply the changes from the given file instead of running the chat (debug)",
-    )
-    group.add_argument(
-        "--apply-clipboard-edits",
-        action="store_true",
-        help="Apply clipboard contents as edits using the main model's editor format",
-        default=False,
-    )
-    group.add_argument(
-        "--yes-always",
-        action="store_true",
-        help="Always say yes to every confirmation",
-        default=None,
-    )
-    group.add_argument(
-        "-v",
-        "--verbose",
-        action="store_true",
-        help="Enable verbose output",
-        default=False,
-    )
-    group.add_argument(
-        "--show-repo-map",
-        action="store_true",
-        help="Print the repo map and exit (debug)",
-        default=False,
-    )
-    group.add_argument(
-        "--show-prompts",
-        action="store_true",
-        help="Print the system prompts and exit (debug)",
-        default=False,
-    )
-    group.add_argument(
-        "--exit",
-        action="store_true",
-        help="Do all startup activities then exit before accepting user input (debug)",
-        default=False,
+        "--version",
+        action="version",
+        version=f"%(prog)s {__version__}",
+        help="Show the version number and exit",
     )
+
+    ##########
+    group = parser.add_argument_group("Modes")
     group.add_argument(
         "--message",
         "--msg",
@@ -711,6 +651,110 @@ def get_parser(default_config_files, git_root):
             " (disables chat mode)"
         ),
     )
+    group.add_argument(
+        "--gui",
+        "--browser",
+        action=argparse.BooleanOptionalAction,
+        help="Run aider in your browser (default: False)",
+        default=False,
+    )
+    group.add_argument(
+        "--copy-paste",
+        action=argparse.BooleanOptionalAction,
+        default=False,
+        help="Enable automatic copy/paste of chat between aider and web UI (default: False)",
+    )
+    group.add_argument(
+        "--apply",
+        metavar="FILE",
+        help="Apply the changes from the given file instead of running the chat (debug)",
+    )
+    group.add_argument(
+        "--apply-clipboard-edits",
+        action="store_true",
+        help="Apply clipboard contents as edits using the main model's editor format",
+        default=False,
+    )
+    group.add_argument(
+        "--exit",
+        action="store_true",
+        help="Do all startup activities then exit before accepting user input (debug)",
+        default=False,
+    )
+    group.add_argument(
+        "--show-repo-map",
+        action="store_true",
+        help="Print the repo map and exit (debug)",
+        default=False,
+    )
+    group.add_argument(
+        "--show-prompts",
+        action="store_true",
+        help="Print the system prompts and exit (debug)",
+        default=False,
+    )
+
+    ##########
+    group = parser.add_argument_group("Voice settings")
+    group.add_argument(
+        "--voice-format",
+        metavar="VOICE_FORMAT",
+        default="wav",
+        choices=["wav", "mp3", "webm"],
+        help="Audio format for voice recording (default: wav). webm and mp3 require ffmpeg",
+    )
+    group.add_argument(
+        "--voice-language",
+        metavar="VOICE_LANGUAGE",
+        default="en",
+        help="Specify the language for voice using ISO 639-1 code (default: auto)",
+    )
+    group.add_argument(
+        "--voice-input-device",
+        metavar="VOICE_INPUT_DEVICE",
+        default=None,
+        help="Specify the input device name for voice recording",
+    )
+
+    ######
+    group = parser.add_argument_group("Other settings")
+    group.add_argument(
+        "--file",
+        action="append",
+        metavar="FILE",
+        help="specify a file to edit (can be used multiple times)",
+    )
+    group.add_argument(
+        "--read",
+        action="append",
+        metavar="FILE",
+        help="specify a read-only file (can be used multiple times)",
+    )
+    group.add_argument(
+        "--vim",
+        action="store_true",
+        help="Use VI editing mode in the terminal (default: False)",
+        default=False,
+    )
+    group.add_argument(
+        "--chat-language",
+        metavar="CHAT_LANGUAGE",
+        default=None,
+        help="Specify the language to use in the chat (default: None, uses system settings)",
+    )
+    group.add_argument(
+        "--yes-always",
+        action="store_true",
+        help="Always say yes to every confirmation",
+        default=None,
+    )
+    group.add_argument(
+        "-v",
+        "--verbose",
+        action="store_true",
+        help="Enable verbose output",
+        default=False,
+    )
     group.add_argument(
         "--load",
         metavar="LOAD_FILE",
@@ -731,12 +775,13 @@ def get_parser(default_config_files, git_root):
             " or home directory)"
         ),
     )
+    # This is a duplicate of the argument in the preparser and is a no-op by this time of
+    # argument parsing, but it's here so that the help is displayed as expected.
     group.add_argument(
-        "--gui",
-        "--browser",
-        action=argparse.BooleanOptionalAction,
-        help="Run aider in your browser (default: False)",
-        default=False,
+        "--env-file",
+        metavar="ENV_FILE",
+        default=default_env_file(git_root),
+        help="Specify the .env file to load (default: .env in git root)",
     )
     group.add_argument(
         "--suggest-shell-commands",
@@ -750,6 +795,12 @@ def get_parser(default_config_files, git_root):
         default=True,
         help="Enable/disable fancy input with history and completion (default: True)",
     )
+    group.add_argument(
+        "--multiline",
+        action=argparse.BooleanOptionalAction,
+        default=False,
+        help="Enable/disable multi-line input mode with Meta-Enter to submit (default: False)",
+    )
     group.add_argument(
         "--detect-urls",
         action=argparse.BooleanOptionalAction,
@@ -761,28 +812,6 @@ def get_parser(default_config_files, git_root):
         help="Specify which editor to use for the /editor command",
     )
 
-    ##########
-    group = parser.add_argument_group("Voice Settings")
-    group.add_argument(
-        "--voice-format",
-        metavar="VOICE_FORMAT",
-        default="wav",
-        choices=["wav", "mp3", "webm"],
-        help="Audio format for voice recording (default: wav). webm and mp3 require ffmpeg",
-    )
-    group.add_argument(
-        "--voice-language",
-        metavar="VOICE_LANGUAGE",
-        default="en",
-        help="Specify the language for voice using ISO 639-1 code (default: auto)",
-    )
-    group.add_argument(
-        "--voice-input-device",
-        metavar="VOICE_INPUT_DEVICE",
-        default=None,
-        help="Specify the input device name for voice recording",
-    )
-
     return parser
 
 

aider/coders/base_coder.py

@@ -103,6 +103,7 @@ class Coder:
     detect_urls = True
     ignore_mentions = None
     chat_language = None
+    file_watcher = None
 
     @classmethod
     def create(
@@ -153,8 +154,9 @@ class Coder:
                 aider_commit_hashes=from_coder.aider_commit_hashes,
                 commands=from_coder.commands.clone(),
                 total_cost=from_coder.total_cost,
+                ignore_mentions=from_coder.ignore_mentions,
+                file_watcher=from_coder.file_watcher,
             )
-
             use_kwargs.update(update)  # override to complete the switch
             use_kwargs.update(kwargs)  # override passed kwargs
 
@@ -175,7 +177,6 @@ class Coder:
 
     def clone(self, **kwargs):
         new_coder = Coder.create(from_coder=self, **kwargs)
-        new_coder.ignore_mentions = self.ignore_mentions
         return new_coder
 
     def get_announcements(self):
@@ -247,6 +248,9 @@ class Coder:
         if self.done_messages:
             lines.append("Restored previous conversation history.")
 
+        if self.io.multiline_mode:
+            lines.append("Multiline mode: Enabled. Enter inserts newline, Alt-Enter submits text")
+
         return lines
 
     def __init__(
@@ -283,6 +287,9 @@ class Coder:
         suggest_shell_commands=True,
         chat_language=None,
         detect_urls=True,
+        ignore_mentions=None,
+        file_watcher=None,
+        auto_copy_context=False,
     ):
         # Fill in a dummy Analytics if needed, but it is never .enable()'d
         self.analytics = analytics if analytics is not None else Analytics()
@@ -293,7 +300,16 @@ class Coder:
         self.aider_commit_hashes = set()
         self.rejected_urls = set()
         self.abs_root_path_cache = {}
-        self.ignore_mentions = set()
+
+        self.auto_copy_context = auto_copy_context
+
+        self.ignore_mentions = ignore_mentions
+        if not self.ignore_mentions:
+            self.ignore_mentions = set()
+
+        self.file_watcher = file_watcher
+        if self.file_watcher:
+            self.file_watcher.coder = self
 
         self.suggest_shell_commands = suggest_shell_commands
         self.detect_urls = detect_urls
@@ -782,9 +798,10 @@ class Coder:
                 self.io.user_input(with_message)
                 self.run_one(with_message, preproc)
                 return self.partial_response_content
-
             while True:
                 try:
+                    if not self.io.placeholder:
+                        self.copy_context()
                     user_message = self.get_input()
                     self.run_one(user_message, preproc)
                     self.show_undo_hint()
@@ -793,6 +810,10 @@ class Coder:
         except EOFError:
             return
 
+    def copy_context(self):
+        if self.auto_copy_context:
+            self.commands.cmd_copy_context()
+
     def get_input(self):
         inchat_files = self.get_inchat_relative_files()
         read_only_files = [self.get_rel_fname(fname) for fname in self.abs_read_only_fnames]
@@ -1104,7 +1125,10 @@ class Coder:
             # add the reminder anyway
             total_tokens = 0
 
-        final = chunks.cur[-1]
+        if chunks.cur:
+            final = chunks.cur[-1]
+        else:
+            final = None
 
         max_input_tokens = self.main_model.info.get("max_input_tokens") or 0
         # Add the reminder prompt if we still have room to include it.
@@ -1115,7 +1139,7 @@ class Coder:
         ):
             if self.main_model.reminder == "sys":
                 chunks.reminder = reminder_message
-            elif self.main_model.reminder == "user" and final["role"] == "user":
+            elif self.main_model.reminder == "user" and final and final["role"] == "user":
                 # stuff it into the user message
                 new_content = (
                     final["content"]
@@ -1420,6 +1444,8 @@ class Coder:
     def lint_edited(self, fnames):
         res = ""
         for fname in fnames:
+            if not fname:
+                continue
             errors = self.linter.lint(self.abs_root_path(fname))
 
             if errors:
@@ -1448,7 +1474,7 @@ class Coder:
         words = set(word for word in content.split())
 
         # drop sentence punctuation from the end
-        words = set(word.rstrip(",.!;:") for word in words)
+        words = set(word.rstrip(",.!;:?") for word in words)
 
         # strip away all kinds of quotes
         quotes = "".join(['"', "'", "`"])
@@ -1537,6 +1563,16 @@ class Coder:
                 yield from self.show_send_output_stream(completion)
             else:
                 self.show_send_output(completion)
+
+            # Calculate costs for successful responses
+            self.calculate_and_show_tokens_and_cost(messages, completion)
+
+        except LiteLLMExceptions().exceptions_tuple() as err:
+            ex_info = LiteLLMExceptions().get_ex_info(err)
+            if ex_info.name == "ContextWindowExceededError":
+                # Still calculate costs for context window errors
+                self.calculate_and_show_tokens_and_cost(messages, completion)
+            raise
         except KeyboardInterrupt as kbi:
             self.keyboard_interrupt()
             raise kbi
@@ -1554,8 +1590,6 @@ class Coder:
                 if args:
                     self.io.ai_output(json.dumps(args, indent=4))
 
-            self.calculate_and_show_tokens_and_cost(messages, completion)
-
     def show_send_output(self, completion):
         if self.verbose:
             print(completion)

aider/coders/editblock_prompts.py

@@ -35,7 +35,9 @@ ONLY EVER RETURN CODE IN A *SEARCH/REPLACE BLOCK*!
 
 Just suggest shell commands this way, not example code.
 Only suggest complete shell commands that are ready to execute, without placeholders.
-Only suggest at most a few shell commands at a time, not more than 1-3.
+Only suggest at most a few shell commands at a time, not more than 1-3, one per line.
+Do not suggest multi-line shell commands.
+All shell commands will run from the root directory of the user's project.
 
 Use the appropriate shell based on the user's system info:
 {platform}

aider/coders/editor_editblock_coder.py

@@ -3,5 +3,6 @@ from .editor_editblock_prompts import EditorEditBlockPrompts
 
 
 class EditorEditBlockCoder(EditBlockCoder):
+    "A coder that uses search/replace blocks, focused purely on editing files."
     edit_format = "editor-diff"
     gpt_prompts = EditorEditBlockPrompts()

aider/coders/editor_whole_coder.py

@@ -3,5 +3,6 @@ from .wholefile_coder import WholeFileCoder
 
 
 class EditorWholeFileCoder(WholeFileCoder):
+    "A coder that operates on entire files, focused purely on editing files."
     edit_format = "editor-whole"
     gpt_prompts = EditorWholeFilePrompts()

aider/coders/search_replace.py

@@ -3,7 +3,11 @@
 import sys
 from pathlib import Path
 
-import git
+try:
+    import git
+except ImportError:
+    git = None
+
 from diff_match_patch import diff_match_patch
 from tqdm import tqdm
 

aider/commands.py

@@ -43,6 +43,8 @@ class Commands:
             verify_ssl=self.verify_ssl,
             args=self.args,
             parser=self.parser,
+            verbose=self.verbose,
+            editor=self.editor,
         )
 
     def __init__(
@@ -101,6 +103,13 @@ class Commands:
                 ("help", "Get help about using aider (usage, config, troubleshoot)."),
                 ("ask", "Ask questions about your code without making any changes."),
                 ("code", "Ask for changes to your code (using the best edit format)."),
+                (
+                    "architect",
+                    (
+                        "Work with an architect model to design code changes, and an editor to make"
+                        " them."
+                    ),
+                ),
             ]
         )
 
@@ -588,6 +597,10 @@ class Commands:
 
         self.io.tool_output(f"Diff since {commit_before_message[:7]}...")
 
+        if self.coder.pretty:
+            run_cmd(f"git diff {commit_before_message}")
+            return
+
         diff = self.coder.repo.diff_commits(
             self.coder.pretty,
             commit_before_message,
@@ -785,7 +798,8 @@ class Commands:
                     self.io.tool_error(f"Unable to read {matched_file}")
                 else:
                     self.coder.abs_fnames.add(abs_file_path)
-                    self.io.tool_output(f"Added {matched_file} to the chat")
+                    fname = self.coder.get_rel_fname(abs_file_path)
+                    self.io.tool_output(f"Added {fname} to the chat")
                     self.coder.check_added_files()
 
     def completions_drop(self):
@@ -920,6 +934,9 @@ class Commands:
                 dict(role="assistant", content="Ok."),
             ]
 
+            if add and exit_status != 0:
+                self.io.placeholder = "Fix that"
+
     def cmd_exit(self, args):
         "Exit the application"
         self.coder.event("exit", reason="/exit")
@@ -1108,36 +1125,14 @@ class Commands:
                 )
                 return
 
-        history_iter = self.io.get_input_history()
-
-        history = []
-        size = 0
-        for line in history_iter:
-            if line.startswith("/"):
-                continue
-            if line in history:
-                continue
-            if size + len(line) > 1024:
-                break
-            size += len(line)
-            history.append(line)
-
-        history.reverse()
-        history = "\n".join(history)
-
         try:
-            text = self.voice.record_and_transcribe(history, language=self.voice_language)
+            text = self.voice.record_and_transcribe(None, language=self.voice_language)
         except litellm.OpenAIError as err:
             self.io.tool_error(f"Unable to use OpenAI whisper model: {err}")
             return
 
         if text:
-            self.io.add_to_input_history(text)
-            self.io.print()
-            self.io.user_input(text, log_only=False)
-            self.io.print()
-
-        return text
+            self.io.placeholder = text
 
     def cmd_paste(self, args):
         """Paste image/text from the clipboard into the chat.\
@@ -1190,9 +1185,14 @@ class Commands:
             self.io.tool_error(f"Error processing clipboard content: {e}")
 
     def cmd_read_only(self, args):
-        "Add files to the chat that are for reference, not to be edited"
+        "Add files to the chat that are for reference only, or turn added files to read-only"
         if not args.strip():
-            self.io.tool_error("Please provide filenames or directories to read.")
+            # Convert all files in chat to read-only
+            for fname in list(self.coder.abs_fnames):
+                self.coder.abs_fnames.remove(fname)
+                self.coder.abs_read_only_fnames.add(fname)
+                rel_fname = self.coder.get_rel_fname(fname)
+                self.io.tool_output(f"Converted {rel_fname} to read-only")
             return
 
         filenames = parse_quoted_filenames(args)
@@ -1341,6 +1341,10 @@ class Commands:
         except Exception as e:
             self.io.tool_error(f"Error saving commands to file: {e}")
 
+    def cmd_multiline_mode(self, args):
+        "Toggle multiline mode (swaps behavior of Enter and Meta+Enter)"
+        self.io.toggle_multiline_mode()
+
     def cmd_copy(self, args):
         "Copy the last assistant message to the clipboard"
         all_messages = self.coder.done_messages + self.coder.cur_messages
@@ -1389,6 +1393,50 @@ class Commands:
         if user_input.strip():
             self.io.set_placeholder(user_input.rstrip())
 
+    def cmd_copy_context(self, args=None):
+        """Copy the current chat context as markdown, suitable to paste into a web UI"""
+
+        chunks = self.coder.format_chat_chunks()
+
+        markdown = ""
+
+        # Only include specified chunks in order
+        for messages in [chunks.repo, chunks.readonly_files, chunks.chat_files]:
+            for msg in messages:
+                # Only include user messages
+                if msg["role"] != "user":
+                    continue
+
+                content = msg["content"]
+
+                # Handle image/multipart content
+                if isinstance(content, list):
+                    for part in content:
+                        if part.get("type") == "text":
+                            markdown += part["text"] + "\n\n"
+                else:
+                    markdown += content + "\n\n"
+
+        args = args or ""
+        markdown += f"""
+Just tell me how to edit the files to make the changes.
+Don't give me back entire files.
+Just show me the edits I need to make.
+
+{args}
+"""
+
+        try:
+            pyperclip.copy(markdown)
+            self.io.tool_output("Copied code context to clipboard.")
+        except pyperclip.PyperclipException as e:
+            self.io.tool_error(f"Failed to copy to clipboard: {str(e)}")
+            self.io.tool_output(
+                "You may need to install xclip or xsel on Linux, or pbcopy on macOS."
+            )
+        except Exception as e:
+            self.io.tool_error(f"An unexpected error occurred while copying to clipboard: {str(e)}")
+
 
 def expand_subdir(file_path):
     if file_path.is_file():

aider/copypaste.py

@@ -0,0 +1,72 @@
+import threading
+import time
+
+import pyperclip
+
+
+class ClipboardWatcher:
+    """Watches clipboard for changes and updates IO placeholder"""
+
+    def __init__(self, io, verbose=False):
+        self.io = io
+        self.verbose = verbose
+        self.stop_event = None
+        self.watcher_thread = None
+        self.last_clipboard = None
+        self.io.clipboard_watcher = self
+
+    def start(self):
+        """Start watching clipboard for changes"""
+        self.stop_event = threading.Event()
+        self.last_clipboard = pyperclip.paste()
+
+        def watch_clipboard():
+            while not self.stop_event.is_set():
+                try:
+                    current = pyperclip.paste()
+                    if current != self.last_clipboard:
+                        self.last_clipboard = current
+                        self.io.interrupt_input()
+                        self.io.placeholder = current
+                        if len(current.splitlines()) > 1:
+                            self.io.placeholder = "\n" + self.io.placeholder + "\n"
+
+                    time.sleep(0.5)
+                except Exception as e:
+                    if self.verbose:
+                        from aider.dump import dump
+
+                        dump(f"Clipboard watcher error: {e}")
+                    continue
+
+        self.watcher_thread = threading.Thread(target=watch_clipboard, daemon=True)
+        self.watcher_thread.start()
+
+    def stop(self):
+        """Stop watching clipboard for changes"""
+        if self.stop_event:
+            self.stop_event.set()
+        if self.watcher_thread:
+            self.watcher_thread.join()
+            self.watcher_thread = None
+            self.stop_event = None
+
+
+def main():
+    """Example usage of the clipboard watcher"""
+    from aider.io import InputOutput
+
+    io = InputOutput()
+    watcher = ClipboardWatcher(io, verbose=True)
+
+    try:
+        watcher.start()
+        while True:
+            time.sleep(1)
+    except KeyboardInterrupt:
+        print("\nStopped watching clipboard")
+        watcher.stop()
+
+
+if __name__ == "__main__":
+    main()

aider/exceptions.py

@@ -78,4 +78,13 @@ class LiteLLMExceptions:
 
     def get_ex_info(self, ex):
         """Return the ExInfo for a given exception instance"""
+        import litellm
+
+        if ex.__class__ is litellm.APIConnectionError:
+            if "google.auth" in str(ex):
+                return ExInfo(
+                    "APIConnectionError", False, "You need to: pip install google-generativeai"
+                )
+            if "boto3" in str(ex):
+                return ExInfo("APIConnectionError", False, "You need to: pip install boto3")
         return self.exceptions.get(ex.__class__, ExInfo(None, None, None))

aider/help_pats.py

@@ -1,4 +1,7 @@
+# This needs to sync with MANIFEST.in
+
 exclude_website_pats = [
+    "**/.DS_Store",
     "examples/**",
     "_posts/**",
     "HISTORY.md",
@@ -7,5 +10,4 @@ exclude_website_pats = [
     "docs/unified-diffs.md",
     "docs/leaderboards/index.md",
     "assets/**",
-    "**/.DS_Store",
 ]

aider/history.py

@@ -108,9 +108,7 @@ class ChatSummary:
 
         for model in self.models:
             try:
-                summary = simple_send_with_retries(
-                    model.name, summarize_messages, extra_params=model.extra_params
-                )
+                summary = simple_send_with_retries(model, summarize_messages)
                 if summary is not None:
                     summary = prompts.summary_prefix + summary
                     return [dict(role="user", content=summary)]

aider/io.py

@@ -1,5 +1,6 @@
 import base64
 import os
+import signal
 import time
 import webbrowser
 from collections import defaultdict
@@ -11,8 +12,10 @@ from pathlib import Path
 from prompt_toolkit.completion import Completer, Completion, ThreadedCompleter
 from prompt_toolkit.cursor_shapes import ModalCursorShapeConfig
 from prompt_toolkit.enums import EditingMode
+from prompt_toolkit.filters import Condition, is_searching
 from prompt_toolkit.history import FileHistory
 from prompt_toolkit.key_binding import KeyBindings
+from prompt_toolkit.keys import Keys
 from prompt_toolkit.lexers import PygmentsLexer
 from prompt_toolkit.shortcuts import CompleteStyle, PromptSession
 from prompt_toolkit.styles import Style
@@ -173,6 +176,7 @@ class AutoCompleter(Completer):
 class InputOutput:
     num_error_outputs = 0
     num_user_asks = 0
+    clipboard_watcher = None
 
     def __init__(
         self,
@@ -197,10 +201,14 @@ class InputOutput:
         llm_history_file=None,
         editingmode=EditingMode.EMACS,
         fancy_input=True,
+        file_watcher=None,
+        multiline_mode=False,
     ):
         self.placeholder = None
+        self.interrupted = False
         self.never_prompts = set()
         self.editingmode = editingmode
+        self.multiline_mode = multiline_mode
         no_color = os.environ.get("NO_COLOR")
         if no_color is not None and no_color != "":
             pretty = False
@@ -261,6 +269,8 @@ class InputOutput:
         else:
             self.console = Console(force_terminal=False, no_color=True)  # non-pretty
 
+        self.file_watcher = file_watcher
+
     def _get_style(self):
         style_dict = {}
         if not self.pretty:
@@ -314,7 +324,7 @@ class InputOutput:
             self.tool_error(f"{filename}: {e}")
             return
 
-    def read_text(self, filename):
+    def read_text(self, filename, silent=False):
         if is_image_file(filename):
             return self.read_image(filename)
 
@@ -322,17 +332,21 @@ class InputOutput:
             with open(str(filename), "r", encoding=self.encoding) as f:
                 return f.read()
         except OSError as err:
-            self.tool_error(f"{filename}: unable to read: {err}")
+            if not silent:
+                self.tool_error(f"{filename}: unable to read: {err}")
             return
         except FileNotFoundError:
-            self.tool_error(f"{filename}: file not found error")
+            if not silent:
+                self.tool_error(f"{filename}: file not found error")
             return
         except IsADirectoryError:
-            self.tool_error(f"{filename}: is a directory")
+            if not silent:
+                self.tool_error(f"{filename}: is a directory")
             return
         except UnicodeError as e:
-            self.tool_error(f"{filename}: {e}")
-            self.tool_error("Use --encoding to set the unicode encoding.")
+            if not silent:
+                self.tool_error(f"{filename}: {e}")
+                self.tool_error("Use --encoding to set the unicode encoding.")
             return
 
     def write_text(self, filename, content, max_retries=5, initial_delay=0.1):
@@ -373,6 +387,13 @@ class InputOutput:
         else:
             print()
 
+    def interrupt_input(self):
+        if self.prompt_session and self.prompt_session.app:
+            # Store any partial input before interrupting
+            self.placeholder = self.prompt_session.app.current_buffer.text
+            self.interrupted = True
+            self.prompt_session.app.exit()
+
     def get_input(
         self,
         root,
@@ -393,6 +414,8 @@ class InputOutput:
             show = self.format_files_for_input(rel_fnames, rel_read_only_fnames)
         if edit_format:
             show += edit_format
+        if self.multiline_mode:
+            show += (" " if edit_format else "") + "multi"
         show += "> "
 
         inp = ""
@@ -411,8 +434,17 @@ class InputOutput:
             )
         )
 
+        def suspend_to_bg(event):
+            """Suspend currently running application."""
+            event.app.suspend_to_background()
+
         kb = KeyBindings()
 
+        @kb.add(Keys.ControlZ, filter=Condition(lambda: hasattr(signal, "SIGTSTP")))
+        def _(event):
+            "Suspend to background with ctrl-z"
+            suspend_to_bg(event)
+
         @kb.add("c-space")
         def _(event):
             "Ignore Ctrl when pressing space bar"
@@ -428,9 +460,25 @@ class InputOutput:
             "Navigate forward through history"
             event.current_buffer.history_forward()
 
-        @kb.add("escape", "c-m", eager=True)
+        @kb.add("enter", eager=True, filter=~is_searching)
         def _(event):
-            event.current_buffer.insert_text("\n")
+            "Handle Enter key press"
+            if self.multiline_mode:
+                # In multiline mode, Enter adds a newline
+                event.current_buffer.insert_text("\n")
+            else:
+                # In normal mode, Enter submits
+                event.current_buffer.validate_and_handle()
+
+        @kb.add("escape", "enter", eager=True, filter=~is_searching)  # This is Alt+Enter
+        def _(event):
+            "Handle Alt+Enter key press"
+            if self.multiline_mode:
+                # In multiline mode, Alt+Enter submits
+                event.current_buffer.validate_and_handle()
+            else:
+                # In normal mode, Alt+Enter adds a newline
+                event.current_buffer.insert_text("\n")
 
         while True:
             if multiline_input:
@@ -442,6 +490,13 @@ class InputOutput:
                     default = self.placeholder or ""
                     self.placeholder = None
 
+                    self.interrupted = False
+                    if not multiline_input:
+                        if self.file_watcher:
+                            self.file_watcher.start()
+                        if self.clipboard_watcher:
+                            self.clipboard_watcher.start()
+
                     line = self.prompt_session.prompt(
                         show,
                         default=default,
@@ -453,9 +508,30 @@ class InputOutput:
                     )
                 else:
                     line = input(show)
+
+                # Check if we were interrupted by a file change
+                if self.interrupted:
+                    line = line or ""
+                    if self.file_watcher:
+                        cmd = self.file_watcher.process_changes()
+                        return cmd
+
+            except EOFError:
+                raise
+            except Exception as err:
+                import traceback
+
+                self.tool_error(str(err))
+                self.tool_error(traceback.format_exc())
+                return ""
             except UnicodeEncodeError as err:
                 self.tool_error(str(err))
                 return ""
+            finally:
+                if self.file_watcher:
+                    self.file_watcher.stop()
+                if self.clipboard_watcher:
+                    self.clipboard_watcher.stop()
 
             if line.strip("\r\n") and not multiline_input:
                 stripped = line.strip("\r\n")
@@ -573,6 +649,9 @@ class InputOutput:
         group=None,
         allow_never=False,
     ):
+        # Temporarily disable multiline mode for yes/no prompts
+        orig_multiline = self.multiline_mode
+        self.multiline_mode = False
         self.num_user_asks += 1
 
         question_id = (question, subject)
@@ -630,6 +709,7 @@ class InputOutput:
                     res = self.prompt_session.prompt(
                         question,
                         style=style,
+                        complete_while_typing=False,
                     )
                 else:
                     res = input(question)
@@ -670,9 +750,15 @@ class InputOutput:
         hist = f"{question.strip()} {res}"
         self.append_chat_history(hist, linebreak=True, blockquote=True)
 
+        # Restore original multiline mode
+        self.multiline_mode = orig_multiline
+
         return is_yes
 
     def prompt_ask(self, question, default="", subject=None):
+        # Temporarily disable multiline mode for prompts
+        orig_multiline = self.multiline_mode
+        self.multiline_mode = False
         self.num_user_asks += 1
 
         if subject:
@@ -696,6 +782,9 @@ class InputOutput:
         if self.yes in (True, False):
             self.tool_output(hist)
 
+        # Restore original multiline mode
+        self.multiline_mode = orig_multiline
+
         return res
 
     def _tool_message(self, message="", strip=True, color=None):
@@ -765,6 +854,18 @@ class InputOutput:
     def print(self, message=""):
         print(message)
 
+    def toggle_multiline_mode(self):
+        """Toggle between normal and multiline input modes"""
+        self.multiline_mode = not self.multiline_mode
+        if self.multiline_mode:
+            self.tool_output(
+                "Multiline mode: Enabled. Enter inserts newline, Alt-Enter submits text"
+            )
+        else:
+            self.tool_output(
+                "Multiline mode: Disabled. Alt-Enter inserts newline, Enter submits text"
+            )
+
     def append_chat_history(self, text, linebreak=False, blockquote=False, strip=True):
         if blockquote:
             if strip:

aider/llm.py

@@ -13,6 +13,8 @@ os.environ["LITELLM_MODE"] = "PRODUCTION"
 
 # `import litellm` takes 1.5 seconds, defer it!
 
+VERBOSE = False
+
 
 class LazyLiteLLM:
     _lazy_module = None
@@ -27,6 +29,9 @@ class LazyLiteLLM:
         if self._lazy_module is not None:
             return
 
+        if VERBOSE:
+            print("Loading litellm...")
+
         self._lazy_module = importlib.import_module("litellm")
 
         self._lazy_module.suppress_debug_info = True

aider/main.py

@@ -9,7 +9,11 @@ import webbrowser
 from dataclasses import fields
 from pathlib import Path
 
-import git
+try:
+    import git
+except ImportError:
+    git = None
+
 import importlib_resources
 from dotenv import load_dotenv
 from prompt_toolkit.enums import EditingMode
@@ -20,6 +24,7 @@ from aider.args import get_parser
 from aider.coders import Coder
 from aider.coders.base_coder import UnknownEditFormat
 from aider.commands import Commands, SwitchCoder
+from aider.copypaste import ClipboardWatcher
 from aider.format_settings import format_settings, scrub_sensitive_info
 from aider.history import ChatSummary
 from aider.io import InputOutput
@@ -28,6 +33,7 @@ from aider.models import ModelSettings
 from aider.repo import ANY_GIT_ERROR, GitRepo
 from aider.report import report_uncaught_exceptions
 from aider.versioncheck import check_version, install_from_main_branch, install_upgrade
+from aider.watch import FileWatcher
 
 from .dump import dump  # noqa: F401
 
@@ -91,6 +97,9 @@ def make_new_repo(git_root, io):
 
 
 def setup_git(git_root, io):
+    if git is None:
+        return
+
     try:
         cwd = Path.cwd()
     except OSError:
@@ -408,7 +417,9 @@ def main(argv=None, input=None, output=None, force_git_root=None, return_coder=F
     if argv is None:
         argv = sys.argv[1:]
 
-    if force_git_root:
+    if git is None:
+        git_root = None
+    elif force_git_root:
         git_root = force_git_root
     else:
         git_root = get_git_root()
@@ -455,6 +466,9 @@ def main(argv=None, input=None, output=None, force_git_root=None, return_coder=F
     # Parse again to include any arguments that might have been defined in .env
     args = parser.parse_args(argv)
 
+    if git is None:
+        args.git = False
+
     if args.analytics_disable:
         analytics = Analytics(permanently_disable=True)
         print("Analytics have been permanently disabled.")
@@ -513,6 +527,7 @@ def main(argv=None, input=None, output=None, force_git_root=None, return_coder=F
             llm_history_file=args.llm_history_file,
             editingmode=editing_mode,
             fancy_input=args.fancy_input,
+            multiline_mode=args.multiline,
         )
 
     io = get_io(args.pretty)
@@ -524,6 +539,50 @@ def main(argv=None, input=None, output=None, force_git_root=None, return_coder=F
         io = get_io(False)
         io.tool_warning("Terminal does not support pretty output (UnicodeDecodeError)")
 
+    # Process any environment variables set via --set-env
+    if args.set_env:
+        for env_setting in args.set_env:
+            try:
+                name, value = env_setting.split("=", 1)
+                os.environ[name.strip()] = value.strip()
+            except ValueError:
+                io.tool_error(f"Invalid --set-env format: {env_setting}")
+                io.tool_output("Format should be: ENV_VAR_NAME=value")
+                return 1
+
+    # Process any API keys set via --api-key
+    if args.api_key:
+        for api_setting in args.api_key:
+            try:
+                provider, key = api_setting.split("=", 1)
+                env_var = f"{provider.strip().upper()}_API_KEY"
+                os.environ[env_var] = key.strip()
+            except ValueError:
+                io.tool_error(f"Invalid --api-key format: {api_setting}")
+                io.tool_output("Format should be: provider=key")
+                return 1
+
+    if args.anthropic_api_key:
+        os.environ["ANTHROPIC_API_KEY"] = args.anthropic_api_key
+
+    if args.openai_api_key:
+        os.environ["OPENAI_API_KEY"] = args.openai_api_key
+    if args.openai_api_base:
+        os.environ["OPENAI_API_BASE"] = args.openai_api_base
+    if args.openai_api_version:
+        io.tool_warning(
+            "--openai-api-version is deprecated, use --set-env OPENAI_API_VERSION=<value>"
+        )
+        os.environ["OPENAI_API_VERSION"] = args.openai_api_version
+    if args.openai_api_type:
+        io.tool_warning("--openai-api-type is deprecated, use --set-env OPENAI_API_TYPE=<value>")
+        os.environ["OPENAI_API_TYPE"] = args.openai_api_type
+    if args.openai_organization_id:
+        io.tool_warning(
+            "--openai-organization-id is deprecated, use --set-env OPENAI_ORGANIZATION=<value>"
+        )
+        os.environ["OPENAI_ORGANIZATION"] = args.openai_organization_id
+
     analytics = Analytics(logfile=args.analytics_log, permanently_disable=args.analytics_disable)
     if args.analytics is not False:
         if analytics.need_to_ask(args.analytics):
@@ -566,7 +625,7 @@ def main(argv=None, input=None, output=None, force_git_root=None, return_coder=F
     fnames = [str(Path(fn).resolve()) for fn in all_files]
     read_only_fnames = []
     for fn in args.read or []:
-        path = Path(fn).resolve()
+        path = Path(fn).expanduser().resolve()
         if path.is_dir():
             read_only_fnames.extend(str(f) for f in path.rglob("*") if f.is_file())
         else:
@@ -599,7 +658,7 @@ def main(argv=None, input=None, output=None, force_git_root=None, return_coder=F
     # We can't know the git repo for sure until after parsing the args.
     # If we guessed wrong, reparse because that changes things like
     # the location of the config.yml and history files.
-    if args.git and not force_git_root:
+    if args.git and not force_git_root and git is not None:
         right_repo_root = guessed_wrong_repo(io, git_root, fnames, git_dname)
         if right_repo_root:
             analytics.event("exit", reason="Recursing with correct repo")
@@ -644,20 +703,6 @@ def main(argv=None, input=None, output=None, force_git_root=None, return_coder=F
     is_first_run = is_first_run_of_new_version(io, verbose=args.verbose)
     check_and_load_imports(io, is_first_run, verbose=args.verbose)
 
-    if args.anthropic_api_key:
-        os.environ["ANTHROPIC_API_KEY"] = args.anthropic_api_key
-
-    if args.openai_api_key:
-        os.environ["OPENAI_API_KEY"] = args.openai_api_key
-    if args.openai_api_base:
-        os.environ["OPENAI_API_BASE"] = args.openai_api_base
-    if args.openai_api_version:
-        os.environ["OPENAI_API_VERSION"] = args.openai_api_version
-    if args.openai_api_type:
-        os.environ["OPENAI_API_TYPE"] = args.openai_api_type
-    if args.openai_organization_id:
-        os.environ["OPENAI_ORGANIZATION"] = args.openai_organization_id
-
     register_models(git_root, args.model_settings_file, io, verbose=args.verbose)
     register_litellm_models(git_root, args.model_metadata_file, io, verbose=args.verbose)
 
@@ -686,6 +731,10 @@ def main(argv=None, input=None, output=None, force_git_root=None, return_coder=F
         editor_edit_format=args.editor_edit_format,
     )
 
+    if args.copy_paste and args.edit_format is None:
+        if main_model.edit_format in ("diff", "whole"):
+            main_model.edit_format = "editor-" + main_model.edit_format
+
     if args.verbose:
         io.tool_output("Model metadata:")
         io.tool_output(json.dumps(main_model.info, indent=4))
@@ -799,6 +848,7 @@ def main(argv=None, input=None, output=None, force_git_root=None, return_coder=F
             suggest_shell_commands=args.suggest_shell_commands,
             chat_language=args.chat_language,
             detect_urls=args.detect_urls,
+            auto_copy_context=args.copy_paste,
         )
     except UnknownEditFormat as err:
         io.tool_error(str(err))
@@ -814,6 +864,22 @@ def main(argv=None, input=None, output=None, force_git_root=None, return_coder=F
         analytics.event("exit", reason="Returning coder object")
         return coder
 
+    ignores = []
+    if git_root:
+        ignores.append(str(Path(git_root) / ".gitignore"))
+    if args.aiderignore:
+        ignores.append(args.aiderignore)
+
+    if args.watch_files:
+        file_watcher = FileWatcher(
+            coder, gitignores=ignores, verbose=args.verbose, analytics=analytics
+        )
+        coder.file_watcher = file_watcher
+
+    if args.copy_paste:
+        analytics.event("copy-paste mode")
+        ClipboardWatcher(coder.io, verbose=args.verbose)
+
     coder.show_announcements()
 
     if args.show_prompts:
@@ -833,9 +899,9 @@ def main(argv=None, input=None, output=None, force_git_root=None, return_coder=F
             io.tool_error("No --test-cmd provided.")
             analytics.event("exit", reason="No test command provided")
             return 1
-        test_errors = coder.commands.cmd_test(args.test_cmd)
-        if test_errors:
-            coder.run(test_errors)
+        coder.commands.cmd_test(args.test_cmd)
+        if io.placeholder:
+            coder.run(io.placeholder)
 
     if args.commit:
         if args.dry_run:

aider/models.py

@@ -69,13 +69,14 @@ MODEL_ALIASES = {
     "opus": "claude-3-opus-20240229",
     # GPT models
     "4": "gpt-4-0613",
-    "4o": "gpt-4o-2024-08-06",
+    "4o": "gpt-4o",
     "4-turbo": "gpt-4-1106-preview",
     "35turbo": "gpt-3.5-turbo",
     "35-turbo": "gpt-3.5-turbo",
     "3": "gpt-3.5-turbo",
     # Other models
     "deepseek": "deepseek/deepseek-coder",
+    "flash": "gemini/gemini-2.0-flash-exp",
 }
 
 
@@ -583,6 +584,21 @@ MODEL_SETTINGS = [
         "diff-fenced",
         use_repo_map=True,
     ),
+    ModelSettings(
+        "gemini/gemini-exp-1206",
+        "diff",
+        use_repo_map=True,
+    ),
+    ModelSettings(
+        "gemini/gemini-exp-1114",
+        "diff",
+        use_repo_map=True,
+    ),
+    ModelSettings(
+        "gemini/gemini-exp-1121",
+        "diff",
+        use_repo_map=True,
+    ),
     ModelSettings(
         "vertex_ai/gemini-pro-experimental",
         "diff-fenced",
@@ -594,6 +610,12 @@ MODEL_SETTINGS = [
         use_repo_map=False,
         send_undo_reply=False,
     ),
+    ModelSettings(
+        "gemini/gemini-2.0-flash-exp",
+        "diff",
+        use_repo_map=True,
+        send_undo_reply=False,
+    ),
     ModelSettings(
         "deepseek/deepseek-chat",
         "diff",
@@ -1210,10 +1232,10 @@ def sanity_check_model(io, model):
             status = "Set" if value else "Not set"
             io.tool_output(f"- {key}: {status}")
 
-        if platform.system() == "Windows" or True:
+        if platform.system() == "Windows":
             io.tool_output(
-                "If you just set these environment variables using `setx` you may need to restart"
-                " your terminal or command prompt for the changes to take effect."
+                "Note: You may need to restart your terminal or command prompt for `setx` to take"
+                " effect."
             )
 
     elif not model.keys_in_environment:

aider/repo.py

@@ -2,7 +2,17 @@ import os
 import time
 from pathlib import Path, PurePosixPath
 
-import git
+try:
+    import git
+
+    ANY_GIT_ERROR = [
+        git.exc.ODBError,
+        git.exc.GitError,
+    ]
+except ImportError:
+    git = None
+    ANY_GIT_ERROR = []
+
 import pathspec
 
 from aider import prompts, utils
@@ -10,15 +20,14 @@ from aider.sendchat import simple_send_with_retries
 
 from .dump import dump  # noqa: F401
 
-ANY_GIT_ERROR = (
-    git.exc.ODBError,
-    git.exc.GitError,
+ANY_GIT_ERROR += [
     OSError,
     IndexError,
     BufferError,
     TypeError,
     ValueError,
-)
+]
+ANY_GIT_ERROR = tuple(ANY_GIT_ERROR)
 
 
 class GitRepo:
@@ -192,9 +201,7 @@ class GitRepo:
             max_tokens = model.info.get("max_input_tokens") or 0
             if max_tokens and num_tokens > max_tokens:
                 continue
-            commit_message = simple_send_with_retries(
-                model.name, messages, extra_params=model.extra_params
-            )
+            commit_message = simple_send_with_retries(model, messages)
             if commit_message:
                 break
 

aider/resources/model-metadata.json

@@ -0,0 +1,38 @@
+{
+    "vertex_ai-language-models/gemini-2.0-flash-exp": {
+        "max_tokens": 8192,
+        "max_input_tokens": 1048576,
+        "max_output_tokens": 8192,
+        "max_images_per_prompt": 3000,
+        "max_videos_per_prompt": 10,
+        "max_video_length": 1,
+        "max_audio_length_hours": 8.4,
+        "max_audio_per_prompt": 1,
+        "max_pdf_size_mb": 30,
+        "litellm_provider": "vertex_ai-language-models",
+        "mode": "chat",
+        "supports_system_messages": true,
+        "supports_function_calling": true,
+        "supports_vision": true,
+        "supports_response_schema": true,
+        "source": "https://cloud.google.com/vertex-ai/generative-ai/docs/gemini-v2"
+    },
+    "gemini/gemini-2.0-flash-exp": {
+        "max_tokens": 8192,
+        "max_input_tokens": 1048576,
+        "max_output_tokens": 8192,
+        "max_images_per_prompt": 3000,
+        "max_videos_per_prompt": 10,
+        "max_video_length": 1,
+        "max_audio_length_hours": 8.4,
+        "max_audio_per_prompt": 1,
+        "max_pdf_size_mb": 30,
+        "litellm_provider": "gemini",
+        "mode": "chat",
+        "supports_system_messages": true,
+        "supports_function_calling": true,
+        "supports_vision": true,
+        "supports_response_schema": true,
+        "source": "https://cloud.google.com/vertex-ai/generative-ai/docs/gemini-v2"
+    },
+}

aider/run_cmd.py

@@ -113,7 +113,7 @@ def run_cmd_pexpect(command, verbose=False, cwd=None):
             # Use the shell from SHELL environment variable
             if verbose:
                 print("Running pexpect.spawn with shell:", shell)
-            child = pexpect.spawn(shell, args=["-c", command], encoding="utf-8", cwd=cwd)
+            child = pexpect.spawn(shell, args=["-i", "-c", command], encoding="utf-8", cwd=cwd)
         else:
             # Fall back to spawning the command directly
             if verbose:

aider/sendchat.py

@@ -56,18 +56,19 @@ def send_completion(
     return hash_object, res
 
 
-def simple_send_with_retries(model_name, messages, extra_params=None):
+def simple_send_with_retries(model, messages):
     litellm_ex = LiteLLMExceptions()
 
     retry_delay = 0.125
     while True:
         try:
             kwargs = {
-                "model_name": model_name,
+                "model_name": model.name,
                 "messages": messages,
                 "functions": None,
                 "stream": False,
-                "extra_params": extra_params,
+                "temperature": None if not model.use_temperature else 0,
+                "extra_params": model.extra_params,
             }
 
             _hash, response = send_completion(**kwargs)

aider/utils.py

@@ -2,15 +2,12 @@ import itertools
 import os
 import platform
 import shlex
-import shutil
 import subprocess
 import sys
 import tempfile
 import time
 from pathlib import Path
 
-import git
-
 from aider.dump import dump  # noqa: F401
 
 IMAGE_EXTENSIONS = {".png", ".jpg", ".jpeg", ".gif", ".bmp", ".tiff", ".webp", ".pdf"}
@@ -74,6 +71,8 @@ class GitTemporaryDirectory(ChdirTemporaryDirectory):
 
 
 def make_repo(path=None):
+    import git
+
     if not path:
         path = "."
     repo = git.Repo.init(path)
@@ -194,25 +193,9 @@ def split_chat_history_markdown(text, include_tool=False):
     return messages
 
 
-# Copied from pip, MIT license
-# https://github.com/pypa/pip/blob/b989e6ef04810bbd4033a3683020bd4ddcbdb627/src/pip/_internal/utils/entrypoints.py#L73
-def get_best_invocation_for_this_python() -> str:
-    """Try to figure out the best way to invoke the current Python."""
-    exe = sys.executable
-    exe_name = os.path.basename(exe)
-
-    # Try to use the basename, if it's the first executable.
-    found_executable = shutil.which(exe_name)
-    if found_executable and os.path.samefile(found_executable, exe):
-        return exe_name
-
-    # Use the full executable name, because we couldn't find something simpler.
-    return exe
-
-
 def get_pip_install(args):
     cmd = [
-        get_best_invocation_for_this_python(),
+        sys.executable,
         "-m",
         "pip",
         "install",
@@ -268,7 +251,8 @@ def run_install(cmd):
 
 
 class Spinner:
-    spinner_chars = itertools.cycle(["⠋", "⠙", "⠹", "⠸", "⠼", "⠴", "⠦", "⠧", "⠇", "⠏"])
+    unicode_spinner = ["⠋", "⠙", "⠹", "⠸", "⠼", "⠴", "⠦", "⠧", "⠇", "⠏"]
+    ascii_spinner = ["|", "/", "-", "\\"]
 
     def __init__(self, text):
         self.text = text
@@ -276,6 +260,20 @@ class Spinner:
         self.last_update = 0
         self.visible = False
         self.is_tty = sys.stdout.isatty()
+        self.tested = False
+
+    def test_charset(self):
+        if self.tested:
+            return
+        self.tested = True
+        # Try unicode first, fall back to ascii if needed
+        try:
+            # Test if we can print unicode characters
+            print(self.unicode_spinner[0], end="", flush=True)
+            print("\r", end="", flush=True)
+            self.spinner_chars = itertools.cycle(self.unicode_spinner)
+        except UnicodeEncodeError:
+            self.spinner_chars = itertools.cycle(self.ascii_spinner)
 
     def step(self):
         if not self.is_tty:
@@ -293,6 +291,7 @@ class Spinner:
         if not self.visible:
             return
 
+        self.test_charset()
         print(f"\r{self.text} {next(self.spinner_chars)}\r{self.text} ", end="", flush=True)
 
     def end(self):
@@ -382,3 +381,15 @@ def printable_shell_command(cmd_list):
         return subprocess.list2cmdline(cmd_list)
     else:
         return shlex.join(cmd_list)
+
+
+def main():
+    spinner = Spinner("Running spinner...")
+    for _ in range(40):  # 40 steps * 0.25 seconds = 10 seconds
+        time.sleep(0.25)
+        spinner.step()
+    spinner.end()
+
+
+if __name__ == "__main__":
+    main()

aider/voice.py

@@ -14,6 +14,8 @@ from .dump import dump  # noqa: F401
 warnings.filterwarnings(
     "ignore", message="Couldn't find ffmpeg or avconv - defaulting to ffmpeg, but may not work"
 )
+warnings.filterwarnings("ignore", category=SyntaxWarning)
+
 
 from pydub import AudioSegment  # noqa
 
@@ -43,7 +45,6 @@ class Voice:
 
             self.sd = sd
 
-
             devices = sd.query_devices()
 
             if device_name:
@@ -55,7 +56,10 @@ class Voice:
                         break
                 if device_id is None:
                     available_inputs = [d["name"] for d in devices if d["max_input_channels"] > 0]
-                    raise ValueError(f"Device '{device_name}' not found. Available input devices: {available_inputs}")
+                    raise ValueError(
+                        f"Device '{device_name}' not found. Available input devices:"
+                        f" {available_inputs}"
+                    )
 
                 print(f"Using input device: {device_name} (ID: {device_id})")
 
@@ -125,7 +129,9 @@ class Voice:
         self.start_time = time.time()
 
         try:
-            with self.sd.InputStream(samplerate=sample_rate, channels=1, callback=self.callback, device=self.device_id):
+            with self.sd.InputStream(
+                samplerate=sample_rate, channels=1, callback=self.callback, device=self.device_id
+            ):
                 prompt(self.get_prompt, refresh_interval=0.1)
         except self.sd.PortAudioError as err:
             raise SoundDeviceError(f"Error accessing audio input device: {err}")

aider/watch.py

@@ -0,0 +1,278 @@
+import re
+import threading
+from pathlib import Path
+from typing import Optional
+
+from grep_ast import TreeContext
+from pathspec import PathSpec
+from pathspec.patterns import GitWildMatchPattern
+from watchfiles import watch
+
+from aider.dump import dump  # noqa
+from aider.watch_prompts import watch_ask_prompt, watch_code_prompt
+
+
+def load_gitignores(gitignore_paths: list[Path]) -> Optional[PathSpec]:
+    """Load and parse multiple .gitignore files into a single PathSpec"""
+    if not gitignore_paths:
+        return None
+
+    patterns = [
+        ".aider*",
+        ".git",
+        # Common editor backup/temp files
+        "*~",  # Emacs/vim backup
+        "*.bak",  # Generic backup
+        "*.swp",  # Vim swap
+        "*.swo",  # Vim swap
+        "\\#*\\#",  # Emacs auto-save
+        ".#*",  # Emacs lock files
+        "*.tmp",  # Generic temp files
+        "*.temp",  # Generic temp files
+        "*.orig",  # Merge conflict originals
+        "*.pyc",  # Python bytecode
+        "__pycache__/",  # Python cache dir
+        ".DS_Store",  # macOS metadata
+        "Thumbs.db",  # Windows thumbnail cache
+        # IDE files
+        ".idea/",  # JetBrains IDEs
+        ".vscode/",  # VS Code
+        "*.sublime-*",  # Sublime Text
+        ".project",  # Eclipse
+        ".settings/",  # Eclipse
+        "*.code-workspace",  # VS Code workspace
+        # Environment files
+        ".env",  # Environment variables
+        ".venv/",  # Python virtual environments
+        "node_modules/",  # Node.js dependencies
+        "vendor/",  # Various dependencies
+        # Logs and caches
+        "*.log",  # Log files
+        ".cache/",  # Cache directories
+        ".pytest_cache/",  # Python test cache
+        "coverage/",  # Code coverage reports
+    ]  # Always ignore
+    for path in gitignore_paths:
+        if path.exists():
+            with open(path) as f:
+                patterns.extend(f.readlines())
+
+    return PathSpec.from_lines(GitWildMatchPattern, patterns) if patterns else None
+
+
+class FileWatcher:
+    """Watches source files for changes and AI comments"""
+
+    # Compiled regex pattern for AI comments
+    ai_comment_pattern = re.compile(r"(?:#|//|--) *(ai\b.*|ai\b.*|.*\bai[?!]?) *$", re.IGNORECASE)
+
+    def __init__(self, coder, gitignores=None, verbose=False, analytics=None):
+        self.coder = coder
+        self.io = coder.io
+        self.root = Path(coder.root)
+        self.verbose = verbose
+        self.analytics = analytics
+        self.stop_event = None
+        self.watcher_thread = None
+        self.changed_files = set()
+        self.gitignores = gitignores
+
+        self.gitignore_spec = load_gitignores(
+            [Path(g) for g in self.gitignores] if self.gitignores else []
+        )
+
+        coder.io.file_watcher = self
+
+    def filter_func(self, change_type, path):
+        """Filter function for the file watcher"""
+        path_obj = Path(path)
+        path_abs = path_obj.absolute()
+
+        if not path_abs.is_relative_to(self.root.absolute()):
+            return False
+
+        rel_path = path_abs.relative_to(self.root)
+        if self.verbose:
+            dump(rel_path)
+
+        if self.gitignore_spec and self.gitignore_spec.match_file(str(rel_path)):
+            return False
+
+        if self.verbose:
+            dump("ok", rel_path)
+
+        # Check if file contains AI markers
+        try:
+            comments, _, _ = self.get_ai_comments(str(path_abs))
+            return bool(comments)
+        except Exception:
+            return
+
+    def start(self):
+        """Start watching for file changes"""
+        self.stop_event = threading.Event()
+        self.changed_files = set()
+
+        def watch_files():
+            try:
+                for changes in watch(
+                    str(self.root), watch_filter=self.filter_func, stop_event=self.stop_event
+                ):
+                    if not changes:
+                        continue
+                    changed_files = {str(Path(change[1])) for change in changes}
+                    self.changed_files.update(changed_files)
+                    self.io.interrupt_input()
+                    return
+            except Exception as e:
+                if self.verbose:
+                    dump(f"File watcher error: {e}")
+                raise e
+
+        self.watcher_thread = threading.Thread(target=watch_files, daemon=True)
+        self.watcher_thread.start()
+
+    def stop(self):
+        """Stop watching for file changes"""
+        if self.stop_event:
+            self.stop_event.set()
+        if self.watcher_thread:
+            self.watcher_thread.join()
+            self.watcher_thread = None
+            self.stop_event = None
+
+    def process_changes(self):
+        """Get any detected file changes"""
+
+        has_action = None
+        added = False
+        for fname in self.changed_files:
+            _, _, action = self.get_ai_comments(fname)
+            if action in ("!", "?"):
+                has_action = action
+
+            if fname in self.coder.abs_fnames:
+                continue
+            if self.analytics:
+                self.analytics.event("ai-comments file-add")
+            self.coder.abs_fnames.add(fname)
+            rel_fname = self.coder.get_rel_fname(fname)
+            if not added:
+                self.io.tool_output()
+                added = True
+            self.io.tool_output(f"Added {rel_fname} to the chat")
+
+        if not has_action:
+            if added:
+                self.io.tool_output(
+                    "End your comment with AI! to request changes or AI? to ask questions"
+                )
+            return ""
+
+        if self.analytics:
+            self.analytics.event("ai-comments execute")
+        self.io.tool_output("Processing your request...")
+
+        if has_action == "!":
+            res = watch_code_prompt
+        elif has_action == "?":
+            res = watch_ask_prompt
+
+        # Refresh all AI comments from tracked files
+        for fname in self.coder.abs_fnames:
+            line_nums, comments, _action = self.get_ai_comments(fname)
+            if not line_nums:
+                continue
+
+            code = self.io.read_text(fname)
+            if not code:
+                continue
+
+            rel_fname = self.coder.get_rel_fname(fname)
+            res += f"\n{rel_fname}:\n"
+
+            # Convert comment line numbers to line indices (0-based)
+            lois = [ln - 1 for ln, _ in zip(line_nums, comments) if ln > 0]
+
+            try:
+                context = TreeContext(
+                    rel_fname,
+                    code,
+                    color=False,
+                    line_number=False,
+                    child_context=False,
+                    last_line=False,
+                    margin=0,
+                    mark_lois=True,
+                    loi_pad=3,
+                    show_top_of_file_parent_scope=False,
+                )
+                context.lines_of_interest = set()
+                context.add_lines_of_interest(lois)
+                context.add_context()
+                res += context.format()
+            except ValueError:
+                for ln, comment in zip(line_nums, comments):
+                    res += f"  Line {ln}: {comment}\n"
+
+        return res
+
+    def get_ai_comments(self, filepath):
+        """Extract AI comment line numbers, comments and action status from a file"""
+        line_nums = []
+        comments = []
+        has_action = None  # None, "!" or "?"
+        content = self.io.read_text(filepath, silent=True)
+        for i, line in enumerate(content.splitlines(), 1):
+            if match := self.ai_comment_pattern.search(line):
+                comment = match.group(0).strip()
+                if comment:
+                    line_nums.append(i)
+                    comments.append(comment)
+                    comment = comment.lower()
+                    comment = comment.lstrip("/#-")
+                    comment = comment.strip()
+                    if comment.startswith("ai!") or comment.endswith("ai!"):
+                        has_action = "!"
+                    elif comment.startswith("ai?") or comment.endswith("ai?"):
+                        has_action = "?"
+        if not line_nums:
+            return None, None, None
+        return line_nums, comments, has_action
+
+
+def main():
+    """Example usage of the file watcher"""
+    import argparse
+
+    parser = argparse.ArgumentParser(description="Watch source files for changes")
+    parser.add_argument("directory", help="Directory to watch")
+    parser.add_argument(
+        "--gitignore",
+        action="append",
+        help="Path to .gitignore file (can be specified multiple times)",
+    )
+    args = parser.parse_args()
+
+    directory = args.directory
+    print(f"Watching source files in {directory}...")
+
+    # Example ignore function that ignores files with "test" in the name
+    def ignore_test_files(path):
+        return "test" in path.name.lower()
+
+    watcher = FileWatcher(directory, gitignores=args.gitignore)
+    try:
+        watcher.start()
+        while True:
+            if changes := watcher.get_changes():
+                for file in sorted(changes.keys()):
+                    print(file)
+                watcher.changed_files = None
+    except KeyboardInterrupt:
+        print("\nStopped watching files")
+        watcher.stop()
+
+
+if __name__ == "__main__":
+    main()

aider/watch_prompts.py

@@ -0,0 +1,11 @@
+watch_code_prompt = """
+Find the "AI" comments below (marked with █) in the code files I've shared with you.
+They contain your instructions.
+Make the requested changes.
+Be sure to remove all these "AI" comments from the code!
+"""
+
+watch_ask_prompt = """/ask
+Find the "AI" comments below (marked with █) in the code files I've shared with you.
+They contain your questions you need to answer and other instructions.
+"""

aider/website/HISTORY.md

@@ -1,7 +1,6 @@
 ---
 title: Release history
-parent: More info
-nav_order: 900
+nav_order: 925
 highlight_image: /assets/blame.jpg
 description: Release notes and stats on aider writing its own code.
 ---
@@ -24,7 +23,59 @@ cog.out(text)
 ]]]-->
 
 
-### main branch
+### Aider v0.69.0
+
+- [Watch files](https://aider.chat/docs/usage/watch.html) improvements:
+  - Use `# ... AI?` comments to trigger aider and ask questions about your code.
+  - Now watches *all* files, not just certain source files.
+  - Use `# AI comments`, `// AI comments`, or `-- AI comments` to give aider instructions in any text file.
+- Full support for Gemini Flash 2.0 Exp:
+  - `aider --model flash` or `aider --model gemini/gemini-2.0-flash-exp`
+- [New `--multiline` flag and `/multiline-mode` command](https://aider.chat/docs/usage/commands.html#entering-multi-line-chat-messages) makes ENTER a soft newline and META-ENTER send the message, by @miradnanali.
+- `/copy-context <instructions>` now takes optional "instructions" when [copying code context to the clipboard](https://aider.chat/docs/usage/copypaste.html#copy-aiders-code-context-to-your-clipboard-paste-into-the-web-ui).
+- Improved clipboard error handling with helpful requirements install info.
+- Ask 5% of users if they want to opt-in to analytics.
+- `/voice` now lets you edit the transcribed text before sending.
+- Disabled auto-complete in Y/N prompts.
+- Aider wrote 68% of the code in this release.
+
+### Aider v0.68.0
+
+- [Aider works with LLM web chat UIs](https://aider.chat/docs/usage/copypaste.html).
+  - New `--copy-paste` mode.
+  - New `/copy-context` command.
+- [Set API keys and other environment variables for all providers from command line or yaml conf file](https://aider.chat/docs/config/aider_conf.html#storing-llm-keys).
+  - New `--api-key provider=key` setting.
+  - New `--set-env VAR=value` setting.
+- Added bash and zsh support to `--watch-files`.
+- Better error messages when missing dependencies for Gemini and Bedrock models.
+- Control-D now properly exits the program.
+- Don't count token costs when API provider returns a hard error.
+- Bugfix so watch files works with files that don't have tree-sitter support.
+- Bugfix so o1 models can be used as weak model.
+- Updated shell command prompt.
+- Added docstrings for all Coders.
+- Reorganized command line arguments with improved help messages and grouping.
+- Use the exact `sys.python` for self-upgrades.
+- Added experimental Gemini models.
+- Aider wrote 71% of the code in this release.
+
+### Aider v0.67.0
+
+- [Use aider in your IDE or editor](https://aider.chat/docs/usage/watch.html).
+  - Run `aider --watch-files` and it will watch for instructions you add to your source files.
+  - One-liner `# ...` or `// ...` comments that start or end with "AI" are instructions to aider.
+  - When aider sees "AI!" it reads and follows all the instructions in AI comments.
+- Support for new Amazon Bedrock Nova models.
+- When `/run` or `/test` have non-zero exit codes, pre-fill "Fix that" into the next message prompt.
+- `/diff` now invokes `git diff` to use your preferred diff tool.
+- Added Ctrl-Z support for process suspension.
+- Spinner now falls back to ASCII art if fancy symbols throw unicode errors.
+- `--read` now expands `~` home dirs.
+- Enabled exception capture in analytics.
+- [Aider wrote 61% of the code in this release.](https://aider.chat/HISTORY.html)
+
+### Aider v0.66.0
 
 - PDF support for Sonnet and Gemini models.
 - Added `--voice-input-device` to select audio input device for voice recording, by @preynal.

aider/website/_data/edit_leaderboard.yml

@@ -644,7 +644,7 @@
 
 - dirname: 2024-07-19-08-57-13--openrouter-deepseek-chat-v2-0628
   test_cases: 133
-  model: DeepSeek Chat V2 0628 (deprecated)
+  model: DeepSeek Chat V2 0628
   edit_format: diff
   commit_hash: 96ff06e-dirty
   pass_rate_1: 60.9
@@ -716,7 +716,7 @@
 
 - dirname: 2024-07-24-07-10-58--deepseek-coder2-0724-diff-direct
   test_cases: 133
-  model: DeepSeek Coder V2 0724 (deprecated)
+  model: DeepSeek Coder V2 0724
   edit_format: diff
   commit_hash: 89965bf
   pass_rate_1: 57.9
@@ -1232,7 +1232,7 @@
 
 - dirname: 2024-09-24-16-33-23--gemini-1.5-flash-002-whole
   test_cases: 133
-  model: gemini-1.5-flash-002
+  model: gemini-1.5-flash-002 (0924)
   edit_format: whole
   commit_hash: 3edcd71
   pass_rate_1: 37.6
@@ -2020,3 +2020,164 @@
   versions: 0.65.2.dev
   seconds_per_case: 38.1
   total_cost: 0.0000
+
+- dirname: 2024-12-04-13-53-03--nova-whole
+  test_cases: 133
+  model: Nova Pro
+  edit_format: whole
+  commit_hash: 699e283
+  pass_rate_1: 44.4
+  pass_rate_2: 54.1
+  percent_cases_well_formed: 100.0
+  error_outputs: 0
+  num_malformed_responses: 0
+  num_with_malformed_responses: 0
+  user_asks: 7
+  lazy_comments: 0
+  syntax_errors: 0
+  indentation_errors: 0
+  exhausted_context_windows: 0
+  test_timeouts: 4
+  command: aider --model bedrock/us.amazon.nova-pro-v1:0
+  date: 2024-12-04
+  versions: 0.66.1.dev
+  seconds_per_case: 8.7
+  total_cost: 0.0000
+
+- dirname: 2024-12-06-18-27-47--llama33-diff
+  test_cases: 133
+  model: llama-3.3-70b-instruct
+  edit_format: diff
+  commit_hash: 53e0d67
+  pass_rate_1: 42.1
+  pass_rate_2: 59.4
+  percent_cases_well_formed: 88.7
+  error_outputs: 33
+  num_malformed_responses: 33
+  num_with_malformed_responses: 15
+  user_asks: 3
+  lazy_comments: 0
+  syntax_errors: 0
+  indentation_errors: 0
+  exhausted_context_windows: 0
+  test_timeouts: 3
+  command: aider --model openrouter/meta-llama/llama-3.3-70b-instruct
+  date: 2024-12-06
+  versions: 0.67.1.dev
+  seconds_per_case: 20.2
+  total_cost: 0.0000
+
+- dirname: 2024-12-06-21-35-50--gemini-exp-1206-diff
+  test_cases: 133
+  model: gemini-exp-1206 (diff)
+  edit_format: diff
+  commit_hash: f2d2ab5
+  pass_rate_1: 55.6
+  pass_rate_2: 69.2
+  percent_cases_well_formed: 84.2
+  error_outputs: 68
+  num_malformed_responses: 68
+  num_with_malformed_responses: 21
+  user_asks: 5
+  lazy_comments: 0
+  syntax_errors: 2
+  indentation_errors: 0
+  exhausted_context_windows: 0
+  test_timeouts: 0
+  command: aider --model gemini/gemini-exp-1206
+  date: 2024-12-06
+  versions: 0.67.1.dev
+  seconds_per_case: 32.1
+  total_cost: 0.0000
+
+- dirname: 2024-12-08-21-39-06--gemini-exp-1206-whole
+  test_cases: 133
+  model: gemini-exp-1206 (whole)
+  edit_format: whole
+  commit_hash: f2d2ab5
+  pass_rate_1: 60.9
+  pass_rate_2: 80.5
+  percent_cases_well_formed: 100.0
+  error_outputs: 0
+  num_malformed_responses: 0
+  num_with_malformed_responses: 0
+  user_asks: 1
+  lazy_comments: 0
+  syntax_errors: 0
+  indentation_errors: 0
+  exhausted_context_windows: 0
+  test_timeouts: 3
+  command: aider --model gemini/gemini-exp-1206
+  date: 2024-12-08
+  versions: 0.67.1.dev
+  seconds_per_case: 64.2
+  total_cost: 0.0000
+
+- dirname: 2024-12-10-14-45-21--deepseek-1210-diff
+  test_cases: 133
+  model: DeepSeek-V2.5-1210
+  edit_format: diff
+  commit_hash: 16332b2
+  pass_rate_1: 58.6
+  pass_rate_2: 72.2
+  percent_cases_well_formed: 99.2
+  error_outputs: 1
+  num_malformed_responses: 1
+  num_with_malformed_responses: 1
+  user_asks: 2
+  lazy_comments: 0
+  syntax_errors: 0
+  indentation_errors: 0
+  exhausted_context_windows: 0
+  test_timeouts: 2
+  command: aider --model deepseek/deepseek-chat
+  date: 2024-12-10
+  versions: 0.67.1.dev
+  seconds_per_case: 32.7
+  total_cost: 0.1106
+
+- dirname: 2024-12-11-00-37-08--yi-test
+  test_cases: 133
+  model: yi-lightning
+  edit_format: whole
+  commit_hash: e909a3d-dirty
+  pass_rate_1: 49.6
+  pass_rate_2: 65.4
+  percent_cases_well_formed: 97.0
+  error_outputs: 304
+  num_malformed_responses: 5
+  num_with_malformed_responses: 4
+  user_asks: 34
+  lazy_comments: 2
+  syntax_errors: 0
+  indentation_errors: 0
+  exhausted_context_windows: 0
+  test_timeouts: 2
+  command: aider --model openai/yi-lightning
+  date: 2024-12-11
+  versions: 0.67.1.dev
+  seconds_per_case: 57.8
+  total_cost: 0.0000
+
+- dirname: 2024-12-11-21-07-00--gemini-2-flash-diff
+  test_cases: 133
+  model: gemini-2.0-flash-exp
+  edit_format: diff
+  commit_hash: fcb2bac-dirty, 02e7e31-dirty
+  pass_rate_1: 56.4
+  pass_rate_2: 69.9
+  percent_cases_well_formed: 97.0
+  error_outputs: 10
+  num_malformed_responses: 6
+  num_with_malformed_responses: 4
+  user_asks: 8
+  lazy_comments: 0
+  syntax_errors: 1
+  indentation_errors: 0
+  exhausted_context_windows: 2
+  test_timeouts: 1
+  command: aider --model gemini/gemini-2.0-flash-exp
+  date: 2024-12-11
+  versions: 0.68.1.dev
+  seconds_per_case: 7.3
+  total_cost: 0.0000

aider/website/_data/qwq.yml

@@ -0,0 +1,170 @@
+
+- dirname: 2024-11-28-21-38-50--architect-qwq-haiku-whole
+  test_cases: 133
+  model: QwQ + Haiku
+  edit_format: architect
+  commit_hash: e4a1d6f
+  editor_model: claude-3-5-haiku-20241022
+  editor_edit_format: editor-whole
+  pass_rate_1: 54.1
+  pass_rate_2: 71.4
+  percent_cases_well_formed: 100.0
+  error_outputs: 4
+  num_malformed_responses: 0
+  num_with_malformed_responses: 0
+  user_asks: 196
+  lazy_comments: 4
+  syntax_errors: 0
+  indentation_errors: 0
+  exhausted_context_windows: 0
+  test_timeouts: 0
+  command: aider --model openrouter/qwen/qwq-32b-preview --editor-model claude-3-5-haiku-20241022 --edit-format editor-whole
+  date: 2024-11-28
+  versions: 0.65.2.dev
+  seconds_per_case: 154.7
+  total_cost: 1.4196
+
+- dirname: 2024-11-28-19-24-35--architect-qwq-deepseek-whole
+  test_cases: 133
+  model: QwQ + DeepSeek V2.5
+  edit_format: architect
+  commit_hash: e4a1d6f
+  editor_model: deepseek/deepseek-chat
+  editor_edit_format: editor-whole
+  pass_rate_1: 55.6
+  pass_rate_2: 67.7
+  percent_cases_well_formed: 100.0
+  error_outputs: 3
+  num_malformed_responses: 0
+  num_with_malformed_responses: 0
+  user_asks: 193
+  lazy_comments: 2
+  syntax_errors: 0
+  indentation_errors: 0
+  exhausted_context_windows: 0
+  test_timeouts: 0
+  command: aider --model openrouter/qwen/qwq-32b-preview --editor-model deepseek/deepseek-chat --edit-format editor-whole
+  date: 2024-11-28
+  versions: 0.65.2.dev
+  seconds_per_case: 170.3
+  total_cost: 0.1558
+
+
+- dirname: 2024-11-09-11-09-15--Qwen2.5-Coder-32B-Instruct
+  test_cases: 133
+  model: Qwen2.5 Coder 32B-I
+  released: 2024-11-12
+  edit_format: diff
+  commit_hash: ec9982a
+  pass_rate_1: 59.4
+  pass_rate_2: 71.4
+  percent_cases_well_formed: 94.7
+  error_outputs: 17
+  num_malformed_responses: 17
+  num_with_malformed_responses: 7
+  user_asks: 1
+  lazy_comments: 0
+  syntax_errors: 0
+  indentation_errors: 0
+  exhausted_context_windows: 0
+  test_timeouts: 3
+  command: aider --model openai/hf:Qwen/Qwen2.5-Coder-32B-Instruct --openai-api-base https://glhf.chat/api/openai/v1 (via GLHF)
+  date: 2024-11-09
+  versions: 0.59.2.dev
+  seconds_per_case: 22.5
+  total_cost: 0.0000
+
+- dirname: 2024-12-04-00-10-39--architect-qwq-qwen
+  test_cases: 132
+  model: QwQ + Qwen2.5 Coder 32B-I
+  edit_format: architect
+  commit_hash: 51c02da
+  editor_model: openrouter/qwen/qwen-2.5-coder-32b-instruct
+  editor_edit_format: editor-whole
+  pass_rate_1: 58.3
+  pass_rate_2: 73.6
+  percent_cases_well_formed: 100.0
+  error_outputs: 3
+  num_malformed_responses: 0
+  num_with_malformed_responses: 0
+  user_asks: 186
+  lazy_comments: 5
+  syntax_errors: 0
+  indentation_errors: 0
+  exhausted_context_windows: 0
+  test_timeouts: 0
+  command: aider --model openrouter/qwen/qwq-32b-preview --editor-model openrouter/qwen/qwen-2.5-coder-32b-instruct --editor-edit-format editor-whole
+  date: 2024-12-04
+  versions: 0.66.1.dev
+  seconds_per_case: 144.1
+  total_cost: 0.1444
+
+- dirname: 2024-12-04-00-42-05--qwq-alone-whole
+  test_cases: 133
+  model: QwQ
+  edit_format: whole
+  commit_hash: 19004c0
+  pass_rate_1: 33.1
+  pass_rate_2: 42.1
+  percent_cases_well_formed: 91.0
+  error_outputs: 28
+  num_malformed_responses: 12
+  num_with_malformed_responses: 12
+  user_asks: 119
+  lazy_comments: 2
+  syntax_errors: 22
+  indentation_errors: 9
+  exhausted_context_windows: 2
+  test_timeouts: 1
+  command: aider --model openrouter/qwen/qwq-32b-preview
+  date: 2024-12-04
+  versions: 0.66.1.dev
+  seconds_per_case: 414.3
+  total_cost: 0.0000
+
+- dirname: 2024-09-12-19-57-35--o1-mini-whole
+  test_cases: 133
+  model: o1-mini
+  edit_format: whole
+  commit_hash: 36fa773-dirty, 291b456
+  pass_rate_1: 49.6
+  pass_rate_2: 70.7
+  percent_cases_well_formed: 90.0
+  error_outputs: 0
+  num_malformed_responses: 0
+  num_with_malformed_responses: 0
+  user_asks: 17
+  lazy_comments: 0
+  syntax_errors: 0
+  indentation_errors: 0
+  exhausted_context_windows: 0
+  test_timeouts: 1
+  command: aider --model o1-mini
+  date: 2024-09-12
+  versions: 0.56.1.dev
+  seconds_per_case: 103.0
+  total_cost: 5.3725
+
+- dirname: 2024-09-21-16-45-11--o1-preview-flex-sr-markers
+  test_cases: 133
+  model: o1-preview
+  _released: 2024-09-12
+  edit_format: diff
+  commit_hash: 5493654-dirty
+  pass_rate_1: 57.9
+  pass_rate_2: 79.7
+  percent_cases_well_formed: 93.2
+  error_outputs: 11
+  num_malformed_responses: 11
+  num_with_malformed_responses: 9
+  user_asks: 3
+  lazy_comments: 0
+  syntax_errors: 10
+  indentation_errors: 0
+  exhausted_context_windows: 0
+  test_timeouts: 1
+  command: aider --model o1-preview
+  date: 2024-09-21
+  versions: 0.56.1.dev
+  seconds_per_case: 80.9
+  total_cost: 63.9190

aider/website/_includes/edit-leaderboard.js

@@ -1,13 +1,21 @@
 document.addEventListener('DOMContentLoaded', function () {
   var ctx = document.getElementById('editChart').getContext('2d');
-  const HIGHTLIGHT_MODEL = 'no no no no';
+  const blueDiagonalPattern = pattern.draw('diagonal', 'rgba(54, 162, 235, 0.2)');
+  const redDiagonalPattern = pattern.draw('diagonal', 'rgba(255, 99, 132, 0.2)');
+  let displayedData = [];
+
+  const HIGHTLIGHT_MODEL = 'no no no';
   var leaderboardData = {
     labels: [],
     datasets: [{
       label: 'Percent completed correctly',
       data: [],
       backgroundColor: function(context) {
-        const label = context.chart.data.labels[context.dataIndex] || '';
+        const row = allData[context.dataIndex];
+        if (row && row.edit_format === 'whole') {
+          return diagonalPattern;
+        }
+        const label = leaderboardData.labels[context.dataIndex] || '';
         return (label && label.includes(HIGHTLIGHT_MODEL)) ? 'rgba(255, 99, 132, 0.2)' : 'rgba(54, 162, 235, 0.2)';
       },
       borderColor: function(context) {
@@ -23,7 +31,8 @@ document.addEventListener('DOMContentLoaded', function () {
     allData.push({
       model: '{{ row.model }}',
       pass_rate_2: {{ row.pass_rate_2 }},
-      percent_cases_well_formed: {{ row.percent_cases_well_formed }}
+      percent_cases_well_formed: {{ row.percent_cases_well_formed }},
+      edit_format: '{{ row.edit_format }}'
     });
   {% endfor %}
 
@@ -31,6 +40,7 @@ document.addEventListener('DOMContentLoaded', function () {
     var selectedRows = document.querySelectorAll('tr.selected');
     var showAll = selectedRows.length === 0;
 
+    displayedData = [];
     leaderboardData.labels = [];
     leaderboardData.datasets[0].data = [];
 
@@ -40,14 +50,30 @@ document.addEventListener('DOMContentLoaded', function () {
         rowElement.classList.remove('selected');
       }
       if (showAll || rowElement.classList.contains('selected')) {
+        displayedData.push(row);
         leaderboardData.labels.push(row.model);
         leaderboardData.datasets[0].data.push(row.pass_rate_2);
       }
     });
 
     leaderboardChart.update();
+    leaderboardChart.render();
   }
 
+  // Use displayedData in the backgroundColor callback instead of allData
+  leaderboardData.datasets[0].backgroundColor = function(context) {
+    const row = displayedData[context.dataIndex];
+    const label = leaderboardData.labels[context.dataIndex] || '';
+    if (label && label.includes(HIGHTLIGHT_MODEL)) {
+      if (row && row.edit_format === 'whole') return redDiagonalPattern;
+      else return 'rgba(255, 99, 132, 0.2)';
+    } else if (row && row.edit_format === 'whole') {
+      return blueDiagonalPattern;
+    } else {
+      return 'rgba(54, 162, 235, 0.2)';
+    }
+  };
+
   var tableBody = document.querySelector('table tbody');
   allData.forEach(function(row, index) {
     var tr = tableBody.children[index];
@@ -63,9 +89,69 @@ document.addEventListener('DOMContentLoaded', function () {
     type: 'bar',
     data: leaderboardData,
     options: {
+      plugins: {
+        legend: {
+          display: true,
+          labels: {
+            generateLabels: function(chart) {
+              return [
+                {
+                  text: 'Diff-like format',
+                  fillStyle: 'rgba(54, 162, 235, 0.2)',
+                  strokeStyle: 'rgba(54, 162, 235, 1)',
+                  lineWidth: 1
+                },
+                {
+                  text: 'Whole format',
+                  fillStyle: blueDiagonalPattern,
+                  strokeStyle: 'rgba(54, 162, 235, 1)',
+                  lineWidth: 1
+                }
+              ];
+            }
+          }
+        }
+      },
       scales: {
         y: {
-          beginAtZero: true
+          beginAtZero: true,
+          title: {
+            display: true,
+            text: 'Percent completed correctly'
+          }
+        },
+        x: {
+          ticks: {
+            callback: function(value, index) {
+              const label = this.getLabelForValue(value);
+              if (label.length <= "claude-3-5-sonnet".length) {
+                return label;
+              }
+              
+              // Find all possible split positions
+              const splitPositions = [];
+              for (let i = 0; i < label.length; i++) {
+                if (label[i] === '-' || label[i] === ' ') {
+                  splitPositions.push(i);
+                }
+              }
+              
+              if (splitPositions.length === 0) {
+                return label;
+              }
+              
+              // Find split position closest to middle
+              const middle = label.length / 2;
+              const splitIndex = splitPositions.reduce((closest, current) => {
+                return Math.abs(current - middle) < Math.abs(closest - middle) ? current : closest;
+              });
+              
+              return [
+                label.slice(0, splitIndex),
+                label.slice(splitIndex + 1)
+              ];
+            }
+          }
         }
       }
     }
@@ -79,6 +165,7 @@ document.addEventListener('DOMContentLoaded', function () {
     var tableBody = document.querySelector('table:first-of-type tbody');
     var rows = tableBody.getElementsByTagName('tr');
     
+    displayedData = [];
     leaderboardData.labels = [];
     leaderboardData.datasets[0].data = [];
     
@@ -86,6 +173,7 @@ document.addEventListener('DOMContentLoaded', function () {
       var rowText = rows[i].textContent;
       if (searchWords.every(word => rowText.toLowerCase().includes(word))) {
         rows[i].style.display = '';
+        displayedData.push(allData[i]);
         leaderboardData.labels.push(allData[i].model);
         leaderboardData.datasets[0].data.push(allData[i].pass_rate_2);
       } else {

aider/website/_includes/env-keys-tip.md

@@ -1,6 +0,0 @@
-{: .tip }
-All API keys can be stored in a
-[.env file](/docs/config/dotenv.html).
-Only OpenAI and Anthropic keys can be stored in the
-[YAML config file](/docs/config/aider_conf.html).
-

aider/website/_includes/get-started.md

@@ -1,17 +1,16 @@
 
-You can get started quickly like this:
+You can get started quickly like this, with python 3.8-3.13:
 
-```
-python -m pip install -U aider-chat
+```bash
+python -m pip install aider-install
+aider-install
 
-# Change directory into a git repo
+# Change directory into your code base
 cd /to/your/git/repo
 
 # Work with Claude 3.5 Sonnet on your repo
-export ANTHROPIC_API_KEY=your-key-goes-here
-aider
+aider --model sonnet --anthropic-api-key your-key-goes-here
 
 # Work with GPT-4o on your repo
-export OPENAI_API_KEY=your-key-goes-here
-aider 
+aider --model gpt-4o --openai-api-key your-key-goes-here
 ```

aider/website/_includes/head_custom.html

@@ -18,3 +18,63 @@
 <link rel="mask-icon" href="{{ '/assets/icons/safari-pinned-tab.svg' | relative_url }}" color="#5bbad5">
 <meta name="msapplication-TileColor" content="#da532c">
 <meta name="theme-color" content="#ffffff">
+
+<!-- Cookie Consent -->
+<link rel="stylesheet" type="text/css" href="https://cdn.jsdelivr.net/npm/cookieconsent@3/build/cookieconsent.min.css" />
+<script src="https://cdn.jsdelivr.net/npm/cookieconsent@3/build/cookieconsent.min.js" data-cfasync="false"></script>
+<script>
+window.addEventListener('load', function(){
+  window.cookieconsent.initialise({
+    palette: {
+      popup: {
+        background: "#333333",
+        text: "#ffffff"
+      },
+      button: {
+        background: "#ffffff",
+        text: "#333333"
+      }
+    },
+    type: "opt-in",
+    position: "bottom-left",
+    showLink: false,
+    dismissOnScroll: true,
+    cookie: {
+      name: 'cookieconsent_status',
+      path: '/',
+      domain: 'aider.chat',
+      expiryDays: 365
+    },
+    content: {
+      message: "This website uses analytics cookies to help us understand how you use the site.",
+      dismiss: "Decline",
+      allow: "Accept",
+      link: "Learn more",
+      href: "https://aider.chat/docs/legal/privacy.html"
+    },
+    onInitialise: function(status) {
+      var type = this.options.type;
+      var didConsent = this.hasConsented();
+      if (didConsent) {
+        initPostHog();
+      }
+    },
+    onStatusChange: function(status, chosenBefore) {
+      var type = this.options.type;
+      var didConsent = this.hasConsented();
+      if (didConsent) {
+        initPostHog();
+      }
+    }
+  })
+});
+
+// PostHog initialization function
+function initPostHog() {
+    !function(t,e){var o,n,p,r;e.__SV||(window.posthog=e,e._i=[],e.init=function(i,s,a){function g(t,e){var o=e.split(".");2==o.length&&(t=t[o[0]],e=o[1]),t[e]=function(){t.push([e].concat(Array.prototype.slice.call(arguments,0)))}}(p=t.createElement("script")).type="text/javascript",p.crossOrigin="anonymous",p.async=!0,p.src=s.api_host.replace(".i.posthog.com","-assets.i.posthog.com")+"/static/array.js",(r=t.getElementsByTagName("script")[0]).parentNode.insertBefore(p,r);var u=e;for(void 0!==a?u=e[a]=[]:a="posthog",u.people=u.people||[],u.toString=function(t){var e="posthog";return"posthog"!==a&&(e+="."+a),t||(e+=" (stub)"),e},u.people.toString=function(){return u.toString(1)+".people (stub)"},o="init capture register register_once register_for_session unregister unregister_for_session getFeatureFlag getFeatureFlagPayload isFeatureEnabled reloadFeatureFlags updateEarlyAccessFeatureEnrollment getEarlyAccessFeatures on onFeatureFlags onSessionId getSurveys getActiveMatchingSurveys renderSurvey canRenderSurvey getNextSurveyStep identify setPersonProperties group resetGroups setPersonPropertiesForFlags resetPersonPropertiesForFlags setGroupPropertiesForFlags resetGroupPropertiesForFlags reset get_distinct_id getGroups get_session_id get_session_replay_url alias set_config startSessionRecording stopSessionRecording sessionRecordingStarted captureException loadToolbar get_property getSessionProperty createPersonProfile opt_in_capturing opt_out_capturing has_opted_in_capturing has_opted_out_capturing clear_opt_in_out_capturing debug".split(" "),n=0;n<o.length;n++)g(u,o[n]);e._i.push([i,s,a])},e.__SV=1)}(document,window.posthog||[]);
+    posthog.init('phc_99T7muzafUMMZX15H8XePbMSreEUzahHbtWjy3l5Qbv', {
+        api_host:'https://us.i.posthog.com',
+        person_profiles: 'identified_only'
+    })
+}
+</script>

aider/website/_includes/keys.md

@@ -0,0 +1,4 @@
+{: .tip :}
+See the
+[API key configuration docs](/docs/config/api-keys.html)
+for information on how to configure and store your API keys.

aider/website/_includes/multi-line.md

@@ -5,7 +5,10 @@ You can send long, multi-line messages in the chat in a few ways:
   - Use Meta-ENTER to start a new line without sending the message (Esc+ENTER in some environments).
   - Use `/paste` to paste text from the clipboard into the chat.
   - Use the `/editor` command to open your editor to create the next chat message. See [editor configuration docs](/docs/config/editor.html) for more info.
-
+  - Use multiline-mode, which swaps the function of Meta-Enter and Enter, so that Enter inserts a newline, and Meta-Enter submits your command. To enable multiline mode:
+    - Use the `/multiline-mode` command to toggle it during a session.
+    - Use the `--multiline` switch.
+  
 Example with a tag:
 ```
 {python

aider/website/_includes/qwq-chart.js

@@ -0,0 +1,120 @@
+document.addEventListener('DOMContentLoaded', function () {
+  var ctx = document.getElementById('qwqChart').getContext('2d');
+  var allData = [];
+  {% for row in site.data.qwq %}
+    allData.push({
+      model: '{{ row.model }}',
+      pass_rate_2: {{ row.pass_rate_2 }}
+    });
+  {% endfor %}
+
+  // Sort data by pass_rate_2 in descending order
+  allData.sort((a, b) => b.pass_rate_2 - a.pass_rate_2);
+
+  var chart;
+  
+  function updateChart(filterText) {
+    var filteredData = allData.filter(row => 
+      row.model.toLowerCase().includes(filterText.toLowerCase())
+    );
+    
+    var chartData = {
+      labels: filteredData.map(row => row.model),
+      datasets: [{
+        data: filteredData.map(row => row.pass_rate_2),
+        backgroundColor: filteredData.map(row => 
+          (row.model === 'Qwen2.5 Coder 32B-I' || row.model === 'Sonnet (SOTA)' || row.model === 'o1-mini' || row.model === 'o1-preview' || row.model === 'QwQ') 
+            ? 'rgba(75, 192, 192, 0.2)'   // Green for solo models
+            : 'rgba(54, 162, 235, 0.2)'   // Blue for architect+editor
+        ),
+        borderColor: filteredData.map(row => 
+          (row.model === 'Qwen2.5 Coder 32B-I' || row.model === 'Sonnet (SOTA)' || row.model === 'o1-mini' || row.model === 'o1-preview' || row.model === 'QwQ')
+            ? 'rgba(75, 192, 192, 1)'     // Green border for solo models
+            : 'rgba(54, 162, 235, 1)'     // Blue border for architect+editor
+        ),
+        borderWidth: 1
+      }]
+    };
+
+    if (chart) {
+      chart.data = chartData;
+      chart.update();
+    } else {
+      chart = new Chart(ctx, {
+        type: 'bar',
+        data: chartData,
+        options: {
+          plugins: {
+            legend: {
+              display: true,
+              position: 'top',
+              labels: {
+                font: {
+                  size: 14
+                },
+                generateLabels: function(chart) {
+                  return [
+                    {
+                      text: 'Solo model',
+                      fillStyle: 'rgba(75, 192, 192, 0.2)',
+                      strokeStyle: 'rgba(75, 192, 192, 1)',
+                      lineWidth: 1,
+                      fontColor: '#666'
+                    },
+                    {
+                      text: 'Architect + Editor',
+                      fillStyle: 'rgba(54, 162, 235, 0.2)',
+                      strokeStyle: 'rgba(54, 162, 235, 1)',
+                      lineWidth: 1,
+                      fontColor: '#666'
+                    }
+                  ];
+                }
+              }
+            }
+          },
+          scales: {
+            y: {
+              beginAtZero: true,
+              title: {
+                display: true,
+                text: 'Aider code editing benchmark (%)',
+                font: {
+                  size: 18
+                }
+              },
+              ticks: {
+                font: {
+                  size: 16
+                }
+              }
+            },
+            x: {
+              ticks: {
+                font: {
+                  size: 16
+                },
+                callback: function(value, index) {
+                  const label = this.getLabelForValue(value);
+                  if (label.includes(" + ")) {
+                    const parts = label.split(" + ");
+                    return [parts[0] + " +", parts[1]];
+                  }
+                  return label;
+                }
+              }
+            }
+          }
+        }
+      });
+    }
+  }
+
+  // Initial chart render
+  updateChart('');
+
+  // Connect search input to chart filtering
+  document.getElementById('qwqSearchInput').addEventListener('keyup', function() {
+    updateChart(this.value);
+  });
+});

aider/website/_includes/replit-pipx.md

@@ -1,6 +1,6 @@
 To use aider with pipx on replit, you can run these commands in the replit shell:
 
-```
+```bash
 pip install pipx
 pipx run aider-chat ...normal aider args...
 ```

aider/website/_includes/special-keys.md

@@ -1,12 +0,0 @@
-Aider has special support for providing
-OpenAI and Anthropic API keys
-via 
-[command line switches](/docs/config/options.html)
-and 
-[yaml config file](/docs/config/aider_conf.html).
-*All other LLM providers* must 
-have their keys and settings 
-specified in environment variables.
-This can be done in your shell, 
-or by using a 
-[.env file](/docs/config/dotenv.html).

aider/website/_includes/venv-pipx.md

@@ -1,7 +0,0 @@
-{: .tip }
-Using a Python 
-[virtual environment](https://docs.python.org/3/library/venv.html){:target="_blank"}
-is recommended.
-Or, you could
-[use pipx to install aider](/docs/install/pipx.html)
-once for your whole system.

aider/website/_posts/2024-05-24-self-assembly.md

@@ -1,6 +1,6 @@
 ---
-title: Aider has written 7% of its own code
-excerpt: Aider has written 7% of its own code, via 600+ commits that inserted 4.8K and deleted 1.5K lines of code.
+title: Aider has written 7% of its own code (outdated, now 70%)
+excerpt: This article is quite out dated. Aider is currently writing about 70% of the new code in each release.
 highlight_image: /assets/self-assembly.jpg
 nav_exclude: true
 ---
@@ -8,13 +8,16 @@ nav_exclude: true
 <p class="post-date">{{ page.date | date: "%B %d, %Y" }}</p>
 {% endif %}
 
-# Aider has written 7% of its own code
+# Aider has written 7% of its own code (outdated, now 70%)
 
 [![self assembly](/assets/self-assembly.jpg)](https://aider.chat/assets/self-assembly.jpg)
 
 {: .note }
-This article is quite out dated. For current statistics, see
-[aider's release history](/HISTORY.html).
+This article is quite old and outdated. 
+Aider is currently writing about 70% of the new code
+in each release.
+See
+[aider's release history](/HISTORY.html) for the latest statistics.
 
 The
 [aider git repo](https://github.com/Aider-AI/aider)

aider/website/_posts/2024-12-03-qwq.md

@@ -0,0 +1,140 @@
+---
+title: QwQ is a code architect, not an editor
+excerpt: QwQ is reasoning model like o1, and needs to be used as an architect with another model as editor.
+highlight_image: /assets/qwq.jpg
+draft: false
+nav_exclude: true
+---
+{% if page.date %}
+<p class="post-date">{{ page.date | date: "%B %d, %Y" }}</p>
+{% endif %}
+
+# QwQ is a code architect, not an editor
+{: .no_toc }
+
+<canvas id="qwqChart" width="800" height="500" style="margin: 20px 0"></canvas>
+
+QwQ 32B Preview is a "reasoning" model, which spends a lot of tokens thinking before
+rendering a final response.
+This is similar to OpenAI's o1 models, which are most effective with aider
+[when paired as an architect with a traditional LLM as an editor](https://aider.chat/2024/09/26/architect.html).
+In this mode, the reasoning model acts as an "architect" to propose a solution to the
+coding problem without regard for how to actually make edits to the source files.
+The "editor" model receives that proposal, and focuses solely on how to
+edit the existing source code to implement it.
+
+Used alone without being paired with an editor, 
+QwQ was unable to comply with even the simplest 
+[editing format](https://aider.chat/docs/more/edit-formats.html).
+It was not able to reliably edit source code files.
+As a result, QwQ's solo score on the benchmark was quite underwhelming
+(and far worse than the o1 models performing solo).
+
+QwQ is based on
+Qwen 2.5 Coder 32B Instruct,
+and does better when paired with it as an architect + editor combo.
+Though this provided only a modest benchmark improvement over just using Qwen alone,
+and comes with a fairly high cost in terms of latency.
+Each request must wait for QwQ to return all its thinking text
+and the final solution proposal.
+And then one must wait for Qwen to turn that large
+response into actual file edits.
+
+Pairing QwQ with other sensible editor models performed the same or worse than
+just using Qwen 2.5 Coder 32B Instruct alone.
+
+QwQ+Qwen seems to be the best way to use QwQ, achieving a score of 74%.
+That is well below the
+SOTA results for this benchmark: Sonnet alone scores 84%, and
+o1-preview + o1-mini as architect + editor scores 85%.
+
+
+## QwQ specific editing formats
+
+I spent some time experimenting with a variety of custom editing formats
+for QwQ.
+In particular, I tried to parse the QwQ response and discard the long
+sections of "thinking" and retain only the "final" solution.
+None of this custom work seemed to translate 
+into any significant improvement in the benchmark results.
+
+
+## Results
+
+<script src="https://cdn.jsdelivr.net/npm/chart.js"></script>
+<script>
+{% include qwq-chart.js %}
+</script>
+
+<table style="width: 100%; max-width: 800px; margin: auto; border-collapse: collapse; box-shadow: 0 2px 4px rgba(0,0,0,0.1); font-size: 14px;">
+  <thead style="background-color: #f2f2f2;">
+    <tr>
+      <th style="padding: 8px; text-align: left;">Model</th>
+      <th style="padding: 8px; text-align: center;">Percent completed correctly</th>
+      <th style="padding: 8px; text-align: center;">Percent using correct edit format</th>
+      <th style="padding: 8px; text-align: left;">Command</th>
+      <th style="padding: 8px; text-align: center;">Edit format</th>
+    </tr>
+  </thead>
+  <tbody>
+    {% assign qwq_sorted = site.data.qwq | sort: 'pass_rate_2' | reverse %}
+    {% for row in qwq_sorted %}
+      <tr style="border-bottom: 1px solid #ddd;">
+        <td style="padding: 8px;">{{ row.model }}</td>
+        <td style="padding: 8px; text-align: center;">{{ row.pass_rate_2 }}%</td>
+        <td style="padding: 8px; text-align: center;">{{ row.percent_cases_well_formed }}%</td>
+        <td style="padding: 8px;"><code>{{ row.command }}</code></td>
+        <td style="padding: 8px; text-align: center;">{{ row.edit_format }}</td>
+      </tr>
+    {% endfor %}
+  </tbody>
+</table>
+
+<style>
+  tr.selected {
+    color: #0056b3;
+  }
+  table {
+    table-layout: fixed;
+  }
+  td, th {
+    word-wrap: break-word;
+    overflow-wrap: break-word;
+  }
+  td:nth-child(3), td:nth-child(4) {
+    font-size: 12px;
+  }
+</style>
+
+<script>
+document.getElementById('qwqSearchInput').addEventListener('keyup', function() {
+    var input = this.value.toLowerCase();
+    var rows = document.querySelectorAll('tbody tr');
+    
+    rows.forEach(function(row) {
+        var text = row.textContent.toLowerCase();
+        if(text.includes(input)) {
+            row.style.display = '';
+            row.classList.add('selected');
+        } else {
+            row.style.display = 'none';
+            row.classList.remove('selected');
+        }
+    });
+});
+</script>
+
+## Open source model caveats
+
+As discussed in a recent blog post,
+[details matter with open source models](https://aider.chat/2024/11/21/quantization.html).
+For clarity, new benchmark runs for this article were
+performed against OpenRouter's endpoints for
+QwQ 32B Preview and Qwen 2.5 Coder 32B Instruct.
+For the other models, the benchmark was direct to their providers' APIs.
+
+Having recently done extensive testing of OpenRouter's Qwen 2.5 Coder 32B Instruct endpoint,
+it seems reliable.
+The provider Mancer was blocked due to the small context window it provides.
+
+For QwQ 32B Preview, Fireworks was blocked because of its small context window.

aider/website/assets/sample.aider.conf.yml

@@ -14,14 +14,8 @@
 ## show this help message and exit
 #help: xxx
 
-#######
-# Main:
-
-## Specify the OpenAI API key
-#openai-api-key: xxx
-
-## Specify the Anthropic API key
-#anthropic-api-key: xxx
+#############
+# Main model:
 
 ## Specify the model to use for the main chat
 #model: xxx
@@ -38,7 +32,7 @@
 ## Use gpt-4-0613 model for the main chat
 #4: false
 
-## Use gpt-4o-2024-08-06 model for the main chat
+## Use gpt-4o model for the main chat
 #4o: false
 
 ## Use gpt-4o-mini model for the main chat
@@ -59,27 +53,52 @@
 ## Use o1-preview model for the main chat
 #o1-preview: false
 
-#################
-# Model Settings:
+########################
+# API Keys and settings:
 
-## List known models which match the (partial) MODEL name
-#list-models: xxx
+## Specify the OpenAI API key
+#openai-api-key: xxx
+
+## Specify the Anthropic API key
+#anthropic-api-key: xxx
 
 ## Specify the api base url
 #openai-api-base: xxx
 
-## Specify the api_type
+## (deprecated, use --set-env OPENAI_API_TYPE=<value>)
 #openai-api-type: xxx
 
-## Specify the api_version
+## (deprecated, use --set-env OPENAI_API_VERSION=<value>)
 #openai-api-version: xxx
 
-## Specify the deployment_id
+## (deprecated, use --set-env OPENAI_API_DEPLOYMENT_ID=<value>)
 #openai-api-deployment-id: xxx
 
-## Specify the OpenAI organization ID
+## (deprecated, use --set-env OPENAI_ORGANIZATION=<value>)
 #openai-organization-id: xxx
 
+## Set an environment variable (to control API settings, can be used multiple times)
+#set-env: xxx
+## Specify multiple values like this:
+#set-env:
+#  - xxx
+#  - yyy
+#  - zzz
+
+## Set an API key for a provider (eg: --api-key provider=<key> sets PROVIDER_API_KEY=<key>)
+#api-key: xxx
+## Specify multiple values like this:
+#api-key:
+#  - xxx
+#  - yyy
+#  - zzz
+
+#################
+# Model settings:
+
+## List known models which match the (partial) MODEL name
+#list-models: xxx
+
 ## Specify a file with aider model settings for unknown models
 #model-settings-file: .aider.model.settings.yml
 
@@ -121,11 +140,8 @@
 ## Soft limit on tokens for chat history, after which summarization begins. If unspecified, defaults to the model's max_chat_history_tokens.
 #max-chat-history-tokens: xxx
 
-## Specify the .env file to load (default: .env in git root)
-#env-file: .env
-
 #################
-# Cache Settings:
+# Cache settings:
 
 ## Enable caching of prompts (default: False)
 #cache-prompts: false
@@ -134,7 +150,7 @@
 #cache-keepalive-pings: false
 
 ###################
-# Repomap Settings:
+# Repomap settings:
 
 ## Suggested number of tokens to use for repo map, use 0 to disable (default: 1024)
 #map-tokens: xxx
@@ -161,7 +177,7 @@
 #llm-history-file: xxx
 
 ##################
-# Output Settings:
+# Output settings:
 
 ## Use colors suitable for a dark terminal background (default: False)
 #dark-mode: false
@@ -209,7 +225,7 @@
 #show-diffs: false
 
 ###############
-# Git Settings:
+# Git settings:
 
 ## Enable/disable looking for a git repo (default: True)
 #git: true
@@ -253,6 +269,9 @@
 ## Skip the sanity check for the git repository (default: False)
 #skip-sanity-check-repo: false
 
+## Enable/disable watching files for ai coding comments (default: False)
+#watch-files: false
+
 ########################
 # Fixing and committing:
 
@@ -291,8 +310,71 @@
 ## Permanently disable analytics
 #analytics-disable: false
 
+############
+# Upgrading:
+
+## Check for updates and return status in the exit code
+#just-check-update: false
+
+## Check for new aider versions on launch
+#check-update: true
+
+## Show release notes on first run of new version (default: None, ask user)
+#show-release-notes: xxx
+
+## Install the latest version from the main branch
+#install-main-branch: false
+
+## Upgrade aider to the latest version from PyPI
+#upgrade: false
+
+## Show the version number and exit
+#version: xxx
+
+########
+# Modes:
+
+## Specify a single message to send the LLM, process reply then exit (disables chat mode)
+#message: xxx
+
+## Specify a file containing the message to send the LLM, process reply, then exit (disables chat mode)
+#message-file: xxx
+
+## Run aider in your browser (default: False)
+#gui: false
+
+## Enable automatic copy/paste of chat between aider and web UI (default: False)
+#copy-paste: false
+
+## Apply the changes from the given file instead of running the chat (debug)
+#apply: xxx
+
+## Apply clipboard contents as edits using the main model's editor format
+#apply-clipboard-edits: false
+
+## Do all startup activities then exit before accepting user input (debug)
+#exit: false
+
+## Print the repo map and exit (debug)
+#show-repo-map: false
+
+## Print the system prompts and exit (debug)
+#show-prompts: false
+
 #################
-# Other Settings:
+# Voice settings:
+
+## Audio format for voice recording (default: wav). webm and mp3 require ffmpeg
+#voice-format: wav
+
+## Specify the language for voice using ISO 639-1 code (default: auto)
+#voice-language: en
+
+## Specify the input device name for voice recording
+#voice-input-device: xxx
+
+#################
+# Other settings:
 
 ## specify a file to edit (can be used multiple times)
 #file: xxx
@@ -316,51 +398,12 @@
 ## Specify the language to use in the chat (default: None, uses system settings)
 #chat-language: xxx
 
-## Show the version number and exit
-#version: xxx
-
-## Check for updates and return status in the exit code
-#just-check-update: false
-
-## Check for new aider versions on launch
-#check-update: true
-
-## Show release notes on first run of new version (default: None, ask user)
-#show-release-notes: xxx
-
-## Install the latest version from the main branch
-#install-main-branch: false
-
-## Upgrade aider to the latest version from PyPI
-#upgrade: false
-
-## Apply the changes from the given file instead of running the chat (debug)
-#apply: xxx
-
-## Apply clipboard contents as edits using the main model's editor format
-#apply-clipboard-edits: false
-
 ## Always say yes to every confirmation
 #yes-always: false
 
 ## Enable verbose output
 #verbose: false
 
-## Print the repo map and exit (debug)
-#show-repo-map: false
-
-## Print the system prompts and exit (debug)
-#show-prompts: false
-
-## Do all startup activities then exit before accepting user input (debug)
-#exit: false
-
-## Specify a single message to send the LLM, process reply then exit (disables chat mode)
-#message: xxx
-
-## Specify a file containing the message to send the LLM, process reply, then exit (disables chat mode)
-#message-file: xxx
-
 ## Load and execute /commands from a file on launch
 #load: xxx
 
@@ -370,8 +413,8 @@
 ## Specify the config file (default: search for .aider.conf.yml in git root, cwd or home directory)
 #config: xxx
 
-## Run aider in your browser (default: False)
-#gui: false
+## Specify the .env file to load (default: .env in git root)
+#env-file: .env
 
 ## Enable/disable suggesting shell commands (default: True)
 #suggest-shell-commands: true
@@ -379,20 +422,11 @@
 ## Enable/disable fancy input with history and completion (default: True)
 #fancy-input: true
 
+## Enable/disable multi-line input mode with Meta-Enter to submit (default: False)
+#multiline: false
+
 ## Enable/disable detection and offering to add URLs to chat (default: True)
 #detect-urls: true
 
 ## Specify which editor to use for the /editor command
 #editor: xxx
-
-#################
-# Voice Settings:
-
-## Audio format for voice recording (default: wav). webm and mp3 require ffmpeg
-#voice-format: wav
-
-## Specify the language for voice using ISO 639-1 code (default: auto)
-#voice-language: en
-
-## Specify the input device name for voice recording
-#voice-input-device: xxx

aider/website/assets/sample.env

@@ -18,14 +18,8 @@
 
 ##...
 
-#######
-# Main:
-
-## Specify the OpenAI API key
-#OPENAI_API_KEY=
-
-## Specify the Anthropic API key
-#ANTHROPIC_API_KEY=
+#############
+# Main model:
 
 ## Specify the model to use for the main chat
 #AIDER_MODEL=
@@ -42,7 +36,7 @@
 ## Use gpt-4-0613 model for the main chat
 #AIDER_4=
 
-## Use gpt-4o-2024-08-06 model for the main chat
+## Use gpt-4o model for the main chat
 #AIDER_4O=
 
 ## Use gpt-4o-mini model for the main chat
@@ -63,27 +57,42 @@
 ## Use o1-preview model for the main chat
 #AIDER_O1_PREVIEW=
 
+########################
+# API Keys and settings:
+
+## Specify the OpenAI API key
+#AIDER_OPENAI_API_KEY=
+
+## Specify the Anthropic API key
+#AIDER_ANTHROPIC_API_KEY=
+
+## Specify the api base url
+#AIDER_OPENAI_API_BASE=
+
+## (deprecated, use --set-env OPENAI_API_TYPE=<value>)
+#AIDER_OPENAI_API_TYPE=
+
+## (deprecated, use --set-env OPENAI_API_VERSION=<value>)
+#AIDER_OPENAI_API_VERSION=
+
+## (deprecated, use --set-env OPENAI_API_DEPLOYMENT_ID=<value>)
+#AIDER_OPENAI_API_DEPLOYMENT_ID=
+
+## (deprecated, use --set-env OPENAI_ORGANIZATION=<value>)
+#AIDER_OPENAI_ORGANIZATION_ID=
+
+## Set an environment variable (to control API settings, can be used multiple times)
+#AIDER_SET_ENV=
+
+## Set an API key for a provider (eg: --api-key provider=<key> sets PROVIDER_API_KEY=<key>)
+#AIDER_API_KEY=
+
 #################
-# Model Settings:
+# Model settings:
 
 ## List known models which match the (partial) MODEL name
 #AIDER_LIST_MODELS=
 
-## Specify the api base url
-#OPENAI_API_BASE=
-
-## Specify the api_type
-#OPENAI_API_TYPE=
-
-## Specify the api_version
-#OPENAI_API_VERSION=
-
-## Specify the deployment_id
-#OPENAI_API_DEPLOYMENT_ID=
-
-## Specify the OpenAI organization ID
-#OPENAI_ORGANIZATION_ID=
-
 ## Specify a file with aider model settings for unknown models
 #AIDER_MODEL_SETTINGS_FILE=.aider.model.settings.yml
 
@@ -120,11 +129,8 @@
 ## Soft limit on tokens for chat history, after which summarization begins. If unspecified, defaults to the model's max_chat_history_tokens.
 #AIDER_MAX_CHAT_HISTORY_TOKENS=
 
-## Specify the .env file to load (default: .env in git root)
-#AIDER_ENV_FILE=.env
-
 #################
-# Cache Settings:
+# Cache settings:
 
 ## Enable caching of prompts (default: False)
 #AIDER_CACHE_PROMPTS=false
@@ -133,7 +139,7 @@
 #AIDER_CACHE_KEEPALIVE_PINGS=false
 
 ###################
-# Repomap Settings:
+# Repomap settings:
 
 ## Suggested number of tokens to use for repo map, use 0 to disable (default: 1024)
 #AIDER_MAP_TOKENS=
@@ -160,7 +166,7 @@
 #AIDER_LLM_HISTORY_FILE=
 
 ##################
-# Output Settings:
+# Output settings:
 
 ## Use colors suitable for a dark terminal background (default: False)
 #AIDER_DARK_MODE=false
@@ -208,7 +214,7 @@
 #AIDER_SHOW_DIFFS=false
 
 ###############
-# Git Settings:
+# Git settings:
 
 ## Enable/disable looking for a git repo (default: True)
 #AIDER_GIT=true
@@ -252,6 +258,9 @@
 ## Skip the sanity check for the git repository (default: False)
 #AIDER_SKIP_SANITY_CHECK_REPO=false
 
+## Enable/disable watching files for ai coding comments (default: False)
+#AIDER_WATCH_FILES=false
+
 ########################
 # Fixing and committing:
 
@@ -285,20 +294,8 @@
 ## Permanently disable analytics
 #AIDER_ANALYTICS_DISABLE=false
 
-#################
-# Other Settings:
-
-## specify a file to edit (can be used multiple times)
-#AIDER_FILE=
-
-## specify a read-only file (can be used multiple times)
-#AIDER_READ=
-
-## Use VI editing mode in the terminal (default: False)
-#AIDER_VIM=false
-
-## Specify the language to use in the chat (default: None, uses system settings)
-#AIDER_CHAT_LANGUAGE=
+############
+# Upgrading:
 
 ## Check for updates and return status in the exit code
 #AIDER_JUST_CHECK_UPDATE=false
@@ -315,26 +312,8 @@
 ## Upgrade aider to the latest version from PyPI
 #AIDER_UPGRADE=false
 
-## Apply the changes from the given file instead of running the chat (debug)
-#AIDER_APPLY=
-
-## Apply clipboard contents as edits using the main model's editor format
-#AIDER_APPLY_CLIPBOARD_EDITS=false
-
-## Always say yes to every confirmation
-#AIDER_YES_ALWAYS=
-
-## Enable verbose output
-#AIDER_VERBOSE=false
-
-## Print the repo map and exit (debug)
-#AIDER_SHOW_REPO_MAP=false
-
-## Print the system prompts and exit (debug)
-#AIDER_SHOW_PROMPTS=false
-
-## Do all startup activities then exit before accepting user input (debug)
-#AIDER_EXIT=false
+########
+# Modes:
 
 ## Specify a single message to send the LLM, process reply then exit (disables chat mode)
 #AIDER_MESSAGE=
@@ -342,29 +321,29 @@
 ## Specify a file containing the message to send the LLM, process reply, then exit (disables chat mode)
 #AIDER_MESSAGE_FILE=
 
-## Load and execute /commands from a file on launch
-#AIDER_LOAD=
-
-## Specify the encoding for input and output (default: utf-8)
-#AIDER_ENCODING=utf-8
-
 ## Run aider in your browser (default: False)
 #AIDER_GUI=false
 
-## Enable/disable suggesting shell commands (default: True)
-#AIDER_SUGGEST_SHELL_COMMANDS=true
+## Enable automatic copy/paste of chat between aider and web UI (default: False)
+#AIDER_COPY_PASTE=false
 
-## Enable/disable fancy input with history and completion (default: True)
-#AIDER_FANCY_INPUT=true
+## Apply the changes from the given file instead of running the chat (debug)
+#AIDER_APPLY=
 
-## Enable/disable detection and offering to add URLs to chat (default: True)
-#AIDER_DETECT_URLS=true
+## Apply clipboard contents as edits using the main model's editor format
+#AIDER_APPLY_CLIPBOARD_EDITS=false
 
-## Specify which editor to use for the /editor command
-#AIDER_EDITOR=
+## Do all startup activities then exit before accepting user input (debug)
+#AIDER_EXIT=false
+
+## Print the repo map and exit (debug)
+#AIDER_SHOW_REPO_MAP=false
+
+## Print the system prompts and exit (debug)
+#AIDER_SHOW_PROMPTS=false
 
 #################
-# Voice Settings:
+# Voice settings:
 
 ## Audio format for voice recording (default: wav). webm and mp3 require ffmpeg
 #AIDER_VOICE_FORMAT=wav
@@ -374,3 +353,48 @@
 
 ## Specify the input device name for voice recording
 #AIDER_VOICE_INPUT_DEVICE=
+
+#################
+# Other settings:
+
+## specify a file to edit (can be used multiple times)
+#AIDER_FILE=
+
+## specify a read-only file (can be used multiple times)
+#AIDER_READ=
+
+## Use VI editing mode in the terminal (default: False)
+#AIDER_VIM=false
+
+## Specify the language to use in the chat (default: None, uses system settings)
+#AIDER_CHAT_LANGUAGE=
+
+## Always say yes to every confirmation
+#AIDER_YES_ALWAYS=
+
+## Enable verbose output
+#AIDER_VERBOSE=false
+
+## Load and execute /commands from a file on launch
+#AIDER_LOAD=
+
+## Specify the encoding for input and output (default: utf-8)
+#AIDER_ENCODING=utf-8
+
+## Specify the .env file to load (default: .env in git root)
+#AIDER_ENV_FILE=.env
+
+## Enable/disable suggesting shell commands (default: True)
+#AIDER_SUGGEST_SHELL_COMMANDS=true
+
+## Enable/disable fancy input with history and completion (default: True)
+#AIDER_FANCY_INPUT=true
+
+## Enable/disable multi-line input mode with Meta-Enter to submit (default: False)
+#AIDER_MULTILINE=false
+
+## Enable/disable detection and offering to add URLs to chat (default: True)
+#AIDER_DETECT_URLS=true
+
+## Specify which editor to use for the /editor command
+#AIDER_EDITOR=

aider/website/docs/config.md

@@ -40,5 +40,5 @@ Using an `.env` file:
 AIDER_DARK_MODE=true
 ```
 
-{% include env-keys-tip.md %}
+{% include keys.md %}
 

aider/website/docs/config/adv-model-settings.md

@@ -46,13 +46,19 @@ The json file should be a dictionary with an entry for each model, as follows:
 }
 ```
 
-See 
-[litellm's model_prices_and_context_window.json file](https://github.com/BerriAI/litellm/blob/main/model_prices_and_context_window.json) for more examples.
-
 {: .tip }
 Use a fully qualified model name with a `provider/` at the front
 in the `.aider.model.metadata.json` file.
 For example, use `deepseek/deepseek-chat`, not just `deepseek-chat`.
+That prefix should match the `litellm_provider` field.
+
+### Contribute model metadata
+
+Aider relies on
+[litellm's model_prices_and_context_window.json file](https://github.com/BerriAI/litellm/blob/main/model_prices_and_context_window.json) 
+for model metadata.
+
+Consider submitting a PR to that file to add missing models.
 
 ## Model settings
 
@@ -977,6 +983,54 @@ cog.out("```\n")
   use_system_prompt: true
   use_temperature: true
   weak_model_name: null
+- cache_control: false
+  caches_by_default: false
+  edit_format: diff
+  editor_edit_format: null
+  editor_model_name: null
+  examples_as_sys_msg: false
+  extra_params: null
+  lazy: false
+  name: gemini/gemini-exp-1206
+  reminder: user
+  send_undo_reply: false
+  streaming: true
+  use_repo_map: true
+  use_system_prompt: true
+  use_temperature: true
+  weak_model_name: null
+- cache_control: false
+  caches_by_default: false
+  edit_format: diff
+  editor_edit_format: null
+  editor_model_name: null
+  examples_as_sys_msg: false
+  extra_params: null
+  lazy: false
+  name: gemini/gemini-exp-1114
+  reminder: user
+  send_undo_reply: false
+  streaming: true
+  use_repo_map: true
+  use_system_prompt: true
+  use_temperature: true
+  weak_model_name: null
+- cache_control: false
+  caches_by_default: false
+  edit_format: diff
+  editor_edit_format: null
+  editor_model_name: null
+  examples_as_sys_msg: false
+  extra_params: null
+  lazy: false
+  name: gemini/gemini-exp-1121
+  reminder: user
+  send_undo_reply: false
+  streaming: true
+  use_repo_map: true
+  use_system_prompt: true
+  use_temperature: true
+  weak_model_name: null
 - cache_control: false
   caches_by_default: false
   edit_format: diff-fenced
@@ -1009,6 +1063,22 @@ cog.out("```\n")
   use_system_prompt: true
   use_temperature: true
   weak_model_name: null
+- cache_control: false
+  caches_by_default: false
+  edit_format: diff
+  editor_edit_format: null
+  editor_model_name: null
+  examples_as_sys_msg: false
+  extra_params: null
+  lazy: false
+  name: gemini/gemini-2.0-flash-exp
+  reminder: user
+  send_undo_reply: false
+  streaming: true
+  use_repo_map: true
+  use_system_prompt: true
+  use_temperature: true
+  weak_model_name: null
 - cache_control: false
   caches_by_default: false
   edit_format: diff

aider/website/docs/config/aider_conf.md

@@ -15,11 +15,7 @@ load whichever is found first.
 - The root of your git repo.
 - Your home directory.
 
-## Storing LLM keys
-
-{% include special-keys.md %}
-
-{% include env-keys-tip.md %}
+{% include keys.md %}
 
 ## A note on lists
 
@@ -70,14 +66,8 @@ cog.outl("```")
 ## show this help message and exit
 #help: xxx
 
-#######
-# Main:
-
-## Specify the OpenAI API key
-#openai-api-key: xxx
-
-## Specify the Anthropic API key
-#anthropic-api-key: xxx
+#############
+# Main model:
 
 ## Specify the model to use for the main chat
 #model: xxx
@@ -94,7 +84,7 @@ cog.outl("```")
 ## Use gpt-4-0613 model for the main chat
 #4: false
 
-## Use gpt-4o-2024-08-06 model for the main chat
+## Use gpt-4o model for the main chat
 #4o: false
 
 ## Use gpt-4o-mini model for the main chat
@@ -115,27 +105,52 @@ cog.outl("```")
 ## Use o1-preview model for the main chat
 #o1-preview: false
 
-#################
-# Model Settings:
+########################
+# API Keys and settings:
 
-## List known models which match the (partial) MODEL name
-#list-models: xxx
+## Specify the OpenAI API key
+#openai-api-key: xxx
+
+## Specify the Anthropic API key
+#anthropic-api-key: xxx
 
 ## Specify the api base url
 #openai-api-base: xxx
 
-## Specify the api_type
+## (deprecated, use --set-env OPENAI_API_TYPE=<value>)
 #openai-api-type: xxx
 
-## Specify the api_version
+## (deprecated, use --set-env OPENAI_API_VERSION=<value>)
 #openai-api-version: xxx
 
-## Specify the deployment_id
+## (deprecated, use --set-env OPENAI_API_DEPLOYMENT_ID=<value>)
 #openai-api-deployment-id: xxx
 
-## Specify the OpenAI organization ID
+## (deprecated, use --set-env OPENAI_ORGANIZATION=<value>)
 #openai-organization-id: xxx
 
+## Set an environment variable (to control API settings, can be used multiple times)
+#set-env: xxx
+## Specify multiple values like this:
+#set-env:
+#  - xxx
+#  - yyy
+#  - zzz
+
+## Set an API key for a provider (eg: --api-key provider=<key> sets PROVIDER_API_KEY=<key>)
+#api-key: xxx
+## Specify multiple values like this:
+#api-key:
+#  - xxx
+#  - yyy
+#  - zzz
+
+#################
+# Model settings:
+
+## List known models which match the (partial) MODEL name
+#list-models: xxx
+
 ## Specify a file with aider model settings for unknown models
 #model-settings-file: .aider.model.settings.yml
 
@@ -177,11 +192,8 @@ cog.outl("```")
 ## Soft limit on tokens for chat history, after which summarization begins. If unspecified, defaults to the model's max_chat_history_tokens.
 #max-chat-history-tokens: xxx
 
-## Specify the .env file to load (default: .env in git root)
-#env-file: .env
-
 #################
-# Cache Settings:
+# Cache settings:
 
 ## Enable caching of prompts (default: False)
 #cache-prompts: false
@@ -190,7 +202,7 @@ cog.outl("```")
 #cache-keepalive-pings: false
 
 ###################
-# Repomap Settings:
+# Repomap settings:
 
 ## Suggested number of tokens to use for repo map, use 0 to disable (default: 1024)
 #map-tokens: xxx
@@ -217,7 +229,7 @@ cog.outl("```")
 #llm-history-file: xxx
 
 ##################
-# Output Settings:
+# Output settings:
 
 ## Use colors suitable for a dark terminal background (default: False)
 #dark-mode: false
@@ -265,7 +277,7 @@ cog.outl("```")
 #show-diffs: false
 
 ###############
-# Git Settings:
+# Git settings:
 
 ## Enable/disable looking for a git repo (default: True)
 #git: true
@@ -309,6 +321,9 @@ cog.outl("```")
 ## Skip the sanity check for the git repository (default: False)
 #skip-sanity-check-repo: false
 
+## Enable/disable watching files for ai coding comments (default: False)
+#watch-files: false
+
 ########################
 # Fixing and committing:
 
@@ -347,8 +362,71 @@ cog.outl("```")
 ## Permanently disable analytics
 #analytics-disable: false
 
+############
+# Upgrading:
+
+## Check for updates and return status in the exit code
+#just-check-update: false
+
+## Check for new aider versions on launch
+#check-update: true
+
+## Show release notes on first run of new version (default: None, ask user)
+#show-release-notes: xxx
+
+## Install the latest version from the main branch
+#install-main-branch: false
+
+## Upgrade aider to the latest version from PyPI
+#upgrade: false
+
+## Show the version number and exit
+#version: xxx
+
+########
+# Modes:
+
+## Specify a single message to send the LLM, process reply then exit (disables chat mode)
+#message: xxx
+
+## Specify a file containing the message to send the LLM, process reply, then exit (disables chat mode)
+#message-file: xxx
+
+## Run aider in your browser (default: False)
+#gui: false
+
+## Enable automatic copy/paste of chat between aider and web UI (default: False)
+#copy-paste: false
+
+## Apply the changes from the given file instead of running the chat (debug)
+#apply: xxx
+
+## Apply clipboard contents as edits using the main model's editor format
+#apply-clipboard-edits: false
+
+## Do all startup activities then exit before accepting user input (debug)
+#exit: false
+
+## Print the repo map and exit (debug)
+#show-repo-map: false
+
+## Print the system prompts and exit (debug)
+#show-prompts: false
+
 #################
-# Other Settings:
+# Voice settings:
+
+## Audio format for voice recording (default: wav). webm and mp3 require ffmpeg
+#voice-format: wav
+
+## Specify the language for voice using ISO 639-1 code (default: auto)
+#voice-language: en
+
+## Specify the input device name for voice recording
+#voice-input-device: xxx
+
+#################
+# Other settings:
 
 ## specify a file to edit (can be used multiple times)
 #file: xxx
@@ -372,51 +450,12 @@ cog.outl("```")
 ## Specify the language to use in the chat (default: None, uses system settings)
 #chat-language: xxx
 
-## Show the version number and exit
-#version: xxx
-
-## Check for updates and return status in the exit code
-#just-check-update: false
-
-## Check for new aider versions on launch
-#check-update: true
-
-## Show release notes on first run of new version (default: None, ask user)
-#show-release-notes: xxx
-
-## Install the latest version from the main branch
-#install-main-branch: false
-
-## Upgrade aider to the latest version from PyPI
-#upgrade: false
-
-## Apply the changes from the given file instead of running the chat (debug)
-#apply: xxx
-
-## Apply clipboard contents as edits using the main model's editor format
-#apply-clipboard-edits: false
-
 ## Always say yes to every confirmation
 #yes-always: false
 
 ## Enable verbose output
 #verbose: false
 
-## Print the repo map and exit (debug)
-#show-repo-map: false
-
-## Print the system prompts and exit (debug)
-#show-prompts: false
-
-## Do all startup activities then exit before accepting user input (debug)
-#exit: false
-
-## Specify a single message to send the LLM, process reply then exit (disables chat mode)
-#message: xxx
-
-## Specify a file containing the message to send the LLM, process reply, then exit (disables chat mode)
-#message-file: xxx
-
 ## Load and execute /commands from a file on launch
 #load: xxx
 
@@ -426,8 +465,8 @@ cog.outl("```")
 ## Specify the config file (default: search for .aider.conf.yml in git root, cwd or home directory)
 #config: xxx
 
-## Run aider in your browser (default: False)
-#gui: false
+## Specify the .env file to load (default: .env in git root)
+#env-file: .env
 
 ## Enable/disable suggesting shell commands (default: True)
 #suggest-shell-commands: true
@@ -435,22 +474,13 @@ cog.outl("```")
 ## Enable/disable fancy input with history and completion (default: True)
 #fancy-input: true
 
+## Enable/disable multi-line input mode with Meta-Enter to submit (default: False)
+#multiline: false
+
 ## Enable/disable detection and offering to add URLs to chat (default: True)
 #detect-urls: true
 
 ## Specify which editor to use for the /editor command
 #editor: xxx
-
-#################
-# Voice Settings:
-
-## Audio format for voice recording (default: wav). webm and mp3 require ffmpeg
-#voice-format: wav
-
-## Specify the language for voice using ISO 639-1 code (default: auto)
-#voice-language: en
-
-## Specify the input device name for voice recording
-#voice-input-device: xxx
 ```
 <!--[[[end]]]-->

aider/website/docs/config/api-keys.md

@@ -0,0 +1,68 @@
+---
+parent: Configuration
+nav_order: 5
+description: Setting API keys for API providers.
+---
+
+# API Keys
+
+### OpenAI and Anthropic
+
+Aider has special support for providing
+OpenAI and Anthropic API keys
+via dedicated switches and configuration options.
+Settings keys for other providers works a bit differently, see below.
+
+You can set OpenAI and Anthropic API keys via
+[command line switches](/docs/config/options.html#api-keys-and-settings)
+`--openai-api-key` and `--anthropic-api-key`.
+
+You can also set those API keys via special entries in the
+[yaml config file](/docs/config/aider_conf.html), like this:
+
+```yaml
+openai-api-key: <key>
+anthropic-api-key: <key>
+```
+
+You can also store them in environment variables or a 
+[.env file](/docs/config/dotenv.html), which also works
+for every API provider:
+
+```
+OPENAI_API_KEY=<key>
+ANTHROPIC_API_KEY=<key>
+```
+
+All other LLM providers can use one of these other methods to set their API keys.
+
+### API keys on the command line
+{: .no_toc }
+
+Use `--api-key provider=<key>` which has the effect of setting the environment variable `PROVIDER_API_KEY=<key>`. So `--api-key gemini=xxx` would set `GEMINI_API_KEY=xxx`.
+
+### API keys in .aider.conf.yml
+{: .no_toc }
+
+You can also set API keys in the 
+[`.aider.conf.yml` file](/docs/config/aider_conf.html)
+via the `api-key` entry:
+
+```
+api-key:
+- gemini=foo      # Sets env var GEMINI_API_KEY=foo
+- openrouter=bar  # Sets env var OPENROUTER_API_KEY=bar
+- deepseek=baz    # Sets env var DEEPSEEK_API_KEY=baz
+```
+
+### API keys in a .env file
+{: .no_toc }
+
+The [.env file](/docs/config/dotenv.html)
+is a great place to set API keys and other provider API environment variables:
+
+```bash
+GEMINI_API_KEY=foo
+OPENROUTER_API_KEY=bar
+DEEPSEEK_API_KEY=baz
+```

aider/website/docs/config/dotenv.md

@@ -1,6 +1,6 @@
 ---
 parent: Configuration
-nav_order: 900
+nav_order: 20
 description: Using a .env file to store LLM API keys for aider.
 ---
 
@@ -20,9 +20,7 @@ Aider will look for a `.env` file in these locations:
 
 If the files above exist, they will be loaded in that order. Files loaded last will take priority.
 
-## Storing LLM keys
-
-{% include special-keys.md %}
+{% include keys.md %}
 
 ## Sample .env file
 
@@ -60,14 +58,8 @@ cog.outl("```")
 
 ##...
 
-#######
-# Main:
-
-## Specify the OpenAI API key
-#OPENAI_API_KEY=
-
-## Specify the Anthropic API key
-#ANTHROPIC_API_KEY=
+#############
+# Main model:
 
 ## Specify the model to use for the main chat
 #AIDER_MODEL=
@@ -84,7 +76,7 @@ cog.outl("```")
 ## Use gpt-4-0613 model for the main chat
 #AIDER_4=
 
-## Use gpt-4o-2024-08-06 model for the main chat
+## Use gpt-4o model for the main chat
 #AIDER_4O=
 
 ## Use gpt-4o-mini model for the main chat
@@ -105,27 +97,42 @@ cog.outl("```")
 ## Use o1-preview model for the main chat
 #AIDER_O1_PREVIEW=
 
+########################
+# API Keys and settings:
+
+## Specify the OpenAI API key
+#AIDER_OPENAI_API_KEY=
+
+## Specify the Anthropic API key
+#AIDER_ANTHROPIC_API_KEY=
+
+## Specify the api base url
+#AIDER_OPENAI_API_BASE=
+
+## (deprecated, use --set-env OPENAI_API_TYPE=<value>)
+#AIDER_OPENAI_API_TYPE=
+
+## (deprecated, use --set-env OPENAI_API_VERSION=<value>)
+#AIDER_OPENAI_API_VERSION=
+
+## (deprecated, use --set-env OPENAI_API_DEPLOYMENT_ID=<value>)
+#AIDER_OPENAI_API_DEPLOYMENT_ID=
+
+## (deprecated, use --set-env OPENAI_ORGANIZATION=<value>)
+#AIDER_OPENAI_ORGANIZATION_ID=
+
+## Set an environment variable (to control API settings, can be used multiple times)
+#AIDER_SET_ENV=
+
+## Set an API key for a provider (eg: --api-key provider=<key> sets PROVIDER_API_KEY=<key>)
+#AIDER_API_KEY=
+
 #################
-# Model Settings:
+# Model settings:
 
 ## List known models which match the (partial) MODEL name
 #AIDER_LIST_MODELS=
 
-## Specify the api base url
-#OPENAI_API_BASE=
-
-## Specify the api_type
-#OPENAI_API_TYPE=
-
-## Specify the api_version
-#OPENAI_API_VERSION=
-
-## Specify the deployment_id
-#OPENAI_API_DEPLOYMENT_ID=
-
-## Specify the OpenAI organization ID
-#OPENAI_ORGANIZATION_ID=
-
 ## Specify a file with aider model settings for unknown models
 #AIDER_MODEL_SETTINGS_FILE=.aider.model.settings.yml
 
@@ -162,11 +169,8 @@ cog.outl("```")
 ## Soft limit on tokens for chat history, after which summarization begins. If unspecified, defaults to the model's max_chat_history_tokens.
 #AIDER_MAX_CHAT_HISTORY_TOKENS=
 
-## Specify the .env file to load (default: .env in git root)
-#AIDER_ENV_FILE=.env
-
 #################
-# Cache Settings:
+# Cache settings:
 
 ## Enable caching of prompts (default: False)
 #AIDER_CACHE_PROMPTS=false
@@ -175,7 +179,7 @@ cog.outl("```")
 #AIDER_CACHE_KEEPALIVE_PINGS=false
 
 ###################
-# Repomap Settings:
+# Repomap settings:
 
 ## Suggested number of tokens to use for repo map, use 0 to disable (default: 1024)
 #AIDER_MAP_TOKENS=
@@ -202,7 +206,7 @@ cog.outl("```")
 #AIDER_LLM_HISTORY_FILE=
 
 ##################
-# Output Settings:
+# Output settings:
 
 ## Use colors suitable for a dark terminal background (default: False)
 #AIDER_DARK_MODE=false
@@ -250,7 +254,7 @@ cog.outl("```")
 #AIDER_SHOW_DIFFS=false
 
 ###############
-# Git Settings:
+# Git settings:
 
 ## Enable/disable looking for a git repo (default: True)
 #AIDER_GIT=true
@@ -294,6 +298,9 @@ cog.outl("```")
 ## Skip the sanity check for the git repository (default: False)
 #AIDER_SKIP_SANITY_CHECK_REPO=false
 
+## Enable/disable watching files for ai coding comments (default: False)
+#AIDER_WATCH_FILES=false
+
 ########################
 # Fixing and committing:
 
@@ -327,20 +334,8 @@ cog.outl("```")
 ## Permanently disable analytics
 #AIDER_ANALYTICS_DISABLE=false
 
-#################
-# Other Settings:
-
-## specify a file to edit (can be used multiple times)
-#AIDER_FILE=
-
-## specify a read-only file (can be used multiple times)
-#AIDER_READ=
-
-## Use VI editing mode in the terminal (default: False)
-#AIDER_VIM=false
-
-## Specify the language to use in the chat (default: None, uses system settings)
-#AIDER_CHAT_LANGUAGE=
+############
+# Upgrading:
 
 ## Check for updates and return status in the exit code
 #AIDER_JUST_CHECK_UPDATE=false
@@ -357,26 +352,8 @@ cog.outl("```")
 ## Upgrade aider to the latest version from PyPI
 #AIDER_UPGRADE=false
 
-## Apply the changes from the given file instead of running the chat (debug)
-#AIDER_APPLY=
-
-## Apply clipboard contents as edits using the main model's editor format
-#AIDER_APPLY_CLIPBOARD_EDITS=false
-
-## Always say yes to every confirmation
-#AIDER_YES_ALWAYS=
-
-## Enable verbose output
-#AIDER_VERBOSE=false
-
-## Print the repo map and exit (debug)
-#AIDER_SHOW_REPO_MAP=false
-
-## Print the system prompts and exit (debug)
-#AIDER_SHOW_PROMPTS=false
-
-## Do all startup activities then exit before accepting user input (debug)
-#AIDER_EXIT=false
+########
+# Modes:
 
 ## Specify a single message to send the LLM, process reply then exit (disables chat mode)
 #AIDER_MESSAGE=
@@ -384,29 +361,29 @@ cog.outl("```")
 ## Specify a file containing the message to send the LLM, process reply, then exit (disables chat mode)
 #AIDER_MESSAGE_FILE=
 
-## Load and execute /commands from a file on launch
-#AIDER_LOAD=
-
-## Specify the encoding for input and output (default: utf-8)
-#AIDER_ENCODING=utf-8
-
 ## Run aider in your browser (default: False)
 #AIDER_GUI=false
 
-## Enable/disable suggesting shell commands (default: True)
-#AIDER_SUGGEST_SHELL_COMMANDS=true
+## Enable automatic copy/paste of chat between aider and web UI (default: False)
+#AIDER_COPY_PASTE=false
 
-## Enable/disable fancy input with history and completion (default: True)
-#AIDER_FANCY_INPUT=true
+## Apply the changes from the given file instead of running the chat (debug)
+#AIDER_APPLY=
 
-## Enable/disable detection and offering to add URLs to chat (default: True)
-#AIDER_DETECT_URLS=true
+## Apply clipboard contents as edits using the main model's editor format
+#AIDER_APPLY_CLIPBOARD_EDITS=false
 
-## Specify which editor to use for the /editor command
-#AIDER_EDITOR=
+## Do all startup activities then exit before accepting user input (debug)
+#AIDER_EXIT=false
+
+## Print the repo map and exit (debug)
+#AIDER_SHOW_REPO_MAP=false
+
+## Print the system prompts and exit (debug)
+#AIDER_SHOW_PROMPTS=false
 
 #################
-# Voice Settings:
+# Voice settings:
 
 ## Audio format for voice recording (default: wav). webm and mp3 require ffmpeg
 #AIDER_VOICE_FORMAT=wav
@@ -416,5 +393,50 @@ cog.outl("```")
 
 ## Specify the input device name for voice recording
 #AIDER_VOICE_INPUT_DEVICE=
+
+#################
+# Other settings:
+
+## specify a file to edit (can be used multiple times)
+#AIDER_FILE=
+
+## specify a read-only file (can be used multiple times)
+#AIDER_READ=
+
+## Use VI editing mode in the terminal (default: False)
+#AIDER_VIM=false
+
+## Specify the language to use in the chat (default: None, uses system settings)
+#AIDER_CHAT_LANGUAGE=
+
+## Always say yes to every confirmation
+#AIDER_YES_ALWAYS=
+
+## Enable verbose output
+#AIDER_VERBOSE=false
+
+## Load and execute /commands from a file on launch
+#AIDER_LOAD=
+
+## Specify the encoding for input and output (default: utf-8)
+#AIDER_ENCODING=utf-8
+
+## Specify the .env file to load (default: .env in git root)
+#AIDER_ENV_FILE=.env
+
+## Enable/disable suggesting shell commands (default: True)
+#AIDER_SUGGEST_SHELL_COMMANDS=true
+
+## Enable/disable fancy input with history and completion (default: True)
+#AIDER_FANCY_INPUT=true
+
+## Enable/disable multi-line input mode with Meta-Enter to submit (default: False)
+#AIDER_MULTILINE=false
+
+## Enable/disable detection and offering to add URLs to chat (default: True)
+#AIDER_DETECT_URLS=true
+
+## Specify which editor to use for the /editor command
+#AIDER_EDITOR=
 ```
 <!--[[[end]]]-->

aider/website/docs/config/editor.md

@@ -1,6 +1,6 @@
 ---
 parent: Configuration
-nav_order: 15
+nav_order: 100
 description: How to configure a custom editor for aider's /editor command
 ---
 

aider/website/docs/config/model-aliases.md

@@ -54,8 +54,9 @@ for alias, model in sorted(MODEL_ALIASES.items()):
 - `35turbo`: gpt-3.5-turbo
 - `4`: gpt-4-0613
 - `4-turbo`: gpt-4-1106-preview
-- `4o`: gpt-4o-2024-08-06
+- `4o`: gpt-4o
 - `deepseek`: deepseek/deepseek-coder
+- `flash`: gemini/gemini-2.0-flash-exp
 - `haiku`: claude-3-5-haiku-20241022
 - `opus`: claude-3-opus-20240229
 - `sonnet`: claude-3-5-sonnet-20241022

aider/website/docs/config/options.md

@@ -13,10 +13,7 @@ or review them below.
 - TOC
 {:toc}
 
-## LLM keys
-{: .no_toc }
-
-{% include special-keys.md %}
+{% include keys.md %}
 
 ## Usage summary
 
@@ -25,18 +22,19 @@ from aider.args import get_md_help
 cog.out(get_md_help())
 ]]]-->
 ```
-usage: aider [-h] [--openai-api-key] [--anthropic-api-key] [--model]
-             [--opus] [--sonnet] [--haiku] [--4] [--4o] [--mini]
-             [--4-turbo] [--35turbo] [--deepseek] [--o1-mini]
-             [--o1-preview] [--list-models] [--openai-api-base]
+usage: aider [-h] [--model] [--opus] [--sonnet] [--haiku] [--4]
+             [--4o] [--mini] [--4-turbo] [--35turbo] [--deepseek]
+             [--o1-mini] [--o1-preview] [--openai-api-key]
+             [--anthropic-api-key] [--openai-api-base]
              [--openai-api-type] [--openai-api-version]
              [--openai-api-deployment-id] [--openai-organization-id]
+             [--set-env] [--api-key] [--list-models]
              [--model-settings-file] [--model-metadata-file]
              [--alias] [--verify-ssl | --no-verify-ssl] [--timeout]
              [--edit-format] [--architect] [--weak-model]
              [--editor-model] [--editor-edit-format]
              [--show-model-warnings | --no-show-model-warnings]
-             [--max-chat-history-tokens] [--env-file]
+             [--max-chat-history-tokens]
              [--cache-prompts | --no-cache-prompts]
              [--cache-keepalive-pings] [--map-tokens]
              [--map-refresh] [--map-multiplier-no-files]
@@ -59,24 +57,27 @@ usage: aider [-h] [--openai-api-key] [--anthropic-api-key] [--model]
              [--attribute-commit-message-author | --no-attribute-commit-message-author]
              [--attribute-commit-message-committer | --no-attribute-commit-message-committer]
              [--commit] [--commit-prompt] [--dry-run | --no-dry-run]
-             [--skip-sanity-check-repo] [--lint] [--lint-cmd]
-             [--auto-lint | --no-auto-lint] [--test-cmd]
-             [--auto-test | --no-auto-test] [--test]
+             [--skip-sanity-check-repo]
+             [--watch-files | --no-watch-files] [--lint]
+             [--lint-cmd] [--auto-lint | --no-auto-lint]
+             [--test-cmd] [--auto-test | --no-auto-test] [--test]
              [--analytics | --no-analytics] [--analytics-log]
-             [--analytics-disable] [--file] [--read] [--vim]
-             [--chat-language] [--version] [--just-check-update]
+             [--analytics-disable] [--just-check-update]
              [--check-update | --no-check-update]
              [--show-release-notes | --no-show-release-notes]
-             [--install-main-branch] [--upgrade] [--apply]
-             [--apply-clipboard-edits] [--yes-always] [-v]
-             [--show-repo-map] [--show-prompts] [--exit] [--message]
-             [--message-file] [--load] [--encoding] [-c]
+             [--install-main-branch] [--upgrade] [--version]
+             [--message] [--message-file]
              [--gui | --no-gui | --browser | --no-browser]
+             [--copy-paste | --no-copy-paste] [--apply]
+             [--apply-clipboard-edits] [--exit] [--show-repo-map]
+             [--show-prompts] [--voice-format] [--voice-language]
+             [--voice-input-device] [--file] [--read] [--vim]
+             [--chat-language] [--yes-always] [-v] [--load]
+             [--encoding] [-c] [--env-file]
              [--suggest-shell-commands | --no-suggest-shell-commands]
              [--fancy-input | --no-fancy-input]
+             [--multiline | --no-multiline]
              [--detect-urls | --no-detect-urls] [--editor]
-             [--voice-format] [--voice-language]
-             [--voice-input-device]
 
 ```
 
@@ -88,15 +89,7 @@ Aliases:
   - `-h`
   - `--help`
 
-## Main:
-
-### `--openai-api-key OPENAI_API_KEY`
-Specify the OpenAI API key  
-Environment variable: `OPENAI_API_KEY`  
-
-### `--anthropic-api-key ANTHROPIC_API_KEY`
-Specify the Anthropic API key  
-Environment variable: `ANTHROPIC_API_KEY`  
+## Main model:
 
 ### `--model MODEL`
 Specify the model to use for the main chat  
@@ -122,7 +115,7 @@ Aliases:
   - `-4`
 
 ### `--4o`
-Use gpt-4o-2024-08-06 model for the main chat  
+Use gpt-4o model for the main chat  
 Environment variable: `AIDER_4O`  
 
 ### `--mini`
@@ -154,7 +147,47 @@ Environment variable: `AIDER_O1_MINI`
 Use o1-preview model for the main chat  
 Environment variable: `AIDER_O1_PREVIEW`  
 
-## Model Settings:
+## API Keys and settings:
+
+### `--openai-api-key VALUE`
+Specify the OpenAI API key  
+Environment variable: `AIDER_OPENAI_API_KEY`  
+
+### `--anthropic-api-key VALUE`
+Specify the Anthropic API key  
+Environment variable: `AIDER_ANTHROPIC_API_KEY`  
+
+### `--openai-api-base VALUE`
+Specify the api base url  
+Environment variable: `AIDER_OPENAI_API_BASE`  
+
+### `--openai-api-type VALUE`
+(deprecated, use --set-env OPENAI_API_TYPE=<value>)  
+Environment variable: `AIDER_OPENAI_API_TYPE`  
+
+### `--openai-api-version VALUE`
+(deprecated, use --set-env OPENAI_API_VERSION=<value>)  
+Environment variable: `AIDER_OPENAI_API_VERSION`  
+
+### `--openai-api-deployment-id VALUE`
+(deprecated, use --set-env OPENAI_API_DEPLOYMENT_ID=<value>)  
+Environment variable: `AIDER_OPENAI_API_DEPLOYMENT_ID`  
+
+### `--openai-organization-id VALUE`
+(deprecated, use --set-env OPENAI_ORGANIZATION=<value>)  
+Environment variable: `AIDER_OPENAI_ORGANIZATION_ID`  
+
+### `--set-env ENV_VAR_NAME=value`
+Set an environment variable (to control API settings, can be used multiple times)  
+Default: []  
+Environment variable: `AIDER_SET_ENV`  
+
+### `--api-key PROVIDER=KEY`
+Set an API key for a provider (eg: --api-key provider=<key> sets PROVIDER_API_KEY=<key>)  
+Default: []  
+Environment variable: `AIDER_API_KEY`  
+
+## Model settings:
 
 ### `--list-models MODEL`
 List known models which match the (partial) MODEL name  
@@ -163,26 +196,6 @@ Aliases:
   - `--list-models MODEL`
   - `--models MODEL`
 
-### `--openai-api-base OPENAI_API_BASE`
-Specify the api base url  
-Environment variable: `OPENAI_API_BASE`  
-
-### `--openai-api-type OPENAI_API_TYPE`
-Specify the api_type  
-Environment variable: `OPENAI_API_TYPE`  
-
-### `--openai-api-version OPENAI_API_VERSION`
-Specify the api_version  
-Environment variable: `OPENAI_API_VERSION`  
-
-### `--openai-api-deployment-id OPENAI_API_DEPLOYMENT_ID`
-Specify the deployment_id  
-Environment variable: `OPENAI_API_DEPLOYMENT_ID`  
-
-### `--openai-organization-id OPENAI_ORGANIZATION_ID`
-Specify the OpenAI organization ID  
-Environment variable: `OPENAI_ORGANIZATION_ID`  
-
 ### `--model-settings-file MODEL_SETTINGS_FILE`
 Specify a file with aider model settings for unknown models  
 Default: .aider.model.settings.yml  
@@ -244,12 +257,7 @@ Aliases:
 Soft limit on tokens for chat history, after which summarization begins. If unspecified, defaults to the model's max_chat_history_tokens.  
 Environment variable: `AIDER_MAX_CHAT_HISTORY_TOKENS`  
 
-### `--env-file ENV_FILE`
-Specify the .env file to load (default: .env in git root)  
-Default: .env  
-Environment variable: `AIDER_ENV_FILE`  
-
-## Cache Settings:
+## Cache settings:
 
 ### `--cache-prompts`
 Enable caching of prompts (default: False)  
@@ -264,7 +272,7 @@ Number of times to ping at 5min intervals to keep prompt cache warm (default: 0)
 Default: 0  
 Environment variable: `AIDER_CACHE_KEEPALIVE_PINGS`  
 
-## Repomap Settings:
+## Repomap settings:
 
 ### `--map-tokens VALUE`
 Suggested number of tokens to use for repo map, use 0 to disable (default: 1024)  
@@ -304,7 +312,7 @@ Aliases:
 Log the conversation with the LLM to this file (for example, .aider.llm.history)  
 Environment variable: `AIDER_LLM_HISTORY_FILE`  
 
-## Output Settings:
+## Output settings:
 
 ### `--dark-mode`
 Use colors suitable for a dark terminal background (default: False)  
@@ -382,7 +390,7 @@ Show diffs when committing changes (default: False)
 Default: False  
 Environment variable: `AIDER_SHOW_DIFFS`  
 
-## Git Settings:
+## Git settings:
 
 ### `--git`
 Enable/disable looking for a git repo (default: True)  
@@ -480,6 +488,14 @@ Skip the sanity check for the git repository (default: False)
 Default: False  
 Environment variable: `AIDER_SKIP_SANITY_CHECK_REPO`  
 
+### `--watch-files`
+Enable/disable watching files for ai coding comments (default: False)  
+Default: False  
+Environment variable: `AIDER_WATCH_FILES`  
+Aliases:
+  - `--watch-files`
+  - `--no-watch-files`
+
 ## Fixing and committing:
 
 ### `--lint`
@@ -536,27 +552,7 @@ Permanently disable analytics
 Default: False  
 Environment variable: `AIDER_ANALYTICS_DISABLE`  
 
-## Other Settings:
-
-### `--file FILE`
-specify a file to edit (can be used multiple times)  
-Environment variable: `AIDER_FILE`  
-
-### `--read FILE`
-specify a read-only file (can be used multiple times)  
-Environment variable: `AIDER_READ`  
-
-### `--vim`
-Use VI editing mode in the terminal (default: False)  
-Default: False  
-Environment variable: `AIDER_VIM`  
-
-### `--chat-language CHAT_LANGUAGE`
-Specify the language to use in the chat (default: None, uses system settings)  
-Environment variable: `AIDER_CHAT_LANGUAGE`  
-
-### `--version`
-Show the version number and exit  
+## Upgrading:
 
 ### `--just-check-update`
 Check for updates and return status in the exit code  
@@ -591,41 +587,10 @@ Aliases:
   - `--upgrade`
   - `--update`
 
-### `--apply FILE`
-Apply the changes from the given file instead of running the chat (debug)  
-Environment variable: `AIDER_APPLY`  
+### `--version`
+Show the version number and exit  
 
-### `--apply-clipboard-edits`
-Apply clipboard contents as edits using the main model's editor format  
-Default: False  
-Environment variable: `AIDER_APPLY_CLIPBOARD_EDITS`  
-
-### `--yes-always`
-Always say yes to every confirmation  
-Environment variable: `AIDER_YES_ALWAYS`  
-
-### `--verbose`
-Enable verbose output  
-Default: False  
-Environment variable: `AIDER_VERBOSE`  
-Aliases:
-  - `-v`
-  - `--verbose`
-
-### `--show-repo-map`
-Print the repo map and exit (debug)  
-Default: False  
-Environment variable: `AIDER_SHOW_REPO_MAP`  
-
-### `--show-prompts`
-Print the system prompts and exit (debug)  
-Default: False  
-Environment variable: `AIDER_SHOW_PROMPTS`  
-
-### `--exit`
-Do all startup activities then exit before accepting user input (debug)  
-Default: False  
-Environment variable: `AIDER_EXIT`  
+## Modes:
 
 ### `--message COMMAND`
 Specify a single message to send the LLM, process reply then exit (disables chat mode)  
@@ -642,6 +607,95 @@ Aliases:
   - `--message-file MESSAGE_FILE`
   - `-f MESSAGE_FILE`
 
+### `--gui`
+Run aider in your browser (default: False)  
+Default: False  
+Environment variable: `AIDER_GUI`  
+Aliases:
+  - `--gui`
+  - `--no-gui`
+  - `--browser`
+  - `--no-browser`
+
+### `--copy-paste`
+Enable automatic copy/paste of chat between aider and web UI (default: False)  
+Default: False  
+Environment variable: `AIDER_COPY_PASTE`  
+Aliases:
+  - `--copy-paste`
+  - `--no-copy-paste`
+
+### `--apply FILE`
+Apply the changes from the given file instead of running the chat (debug)  
+Environment variable: `AIDER_APPLY`  
+
+### `--apply-clipboard-edits`
+Apply clipboard contents as edits using the main model's editor format  
+Default: False  
+Environment variable: `AIDER_APPLY_CLIPBOARD_EDITS`  
+
+### `--exit`
+Do all startup activities then exit before accepting user input (debug)  
+Default: False  
+Environment variable: `AIDER_EXIT`  
+
+### `--show-repo-map`
+Print the repo map and exit (debug)  
+Default: False  
+Environment variable: `AIDER_SHOW_REPO_MAP`  
+
+### `--show-prompts`
+Print the system prompts and exit (debug)  
+Default: False  
+Environment variable: `AIDER_SHOW_PROMPTS`  
+
+## Voice settings:
+
+### `--voice-format VOICE_FORMAT`
+Audio format for voice recording (default: wav). webm and mp3 require ffmpeg  
+Default: wav  
+Environment variable: `AIDER_VOICE_FORMAT`  
+
+### `--voice-language VOICE_LANGUAGE`
+Specify the language for voice using ISO 639-1 code (default: auto)  
+Default: en  
+Environment variable: `AIDER_VOICE_LANGUAGE`  
+
+### `--voice-input-device VOICE_INPUT_DEVICE`
+Specify the input device name for voice recording  
+Environment variable: `AIDER_VOICE_INPUT_DEVICE`  
+
+## Other settings:
+
+### `--file FILE`
+specify a file to edit (can be used multiple times)  
+Environment variable: `AIDER_FILE`  
+
+### `--read FILE`
+specify a read-only file (can be used multiple times)  
+Environment variable: `AIDER_READ`  
+
+### `--vim`
+Use VI editing mode in the terminal (default: False)  
+Default: False  
+Environment variable: `AIDER_VIM`  
+
+### `--chat-language CHAT_LANGUAGE`
+Specify the language to use in the chat (default: None, uses system settings)  
+Environment variable: `AIDER_CHAT_LANGUAGE`  
+
+### `--yes-always`
+Always say yes to every confirmation  
+Environment variable: `AIDER_YES_ALWAYS`  
+
+### `--verbose`
+Enable verbose output  
+Default: False  
+Environment variable: `AIDER_VERBOSE`  
+Aliases:
+  - `-v`
+  - `--verbose`
+
 ### `--load LOAD_FILE`
 Load and execute /commands from a file on launch  
 Environment variable: `AIDER_LOAD`  
@@ -657,15 +711,10 @@ Aliases:
   - `-c CONFIG_FILE`
   - `--config CONFIG_FILE`
 
-### `--gui`
-Run aider in your browser (default: False)  
-Default: False  
-Environment variable: `AIDER_GUI`  
-Aliases:
-  - `--gui`
-  - `--no-gui`
-  - `--browser`
-  - `--no-browser`
+### `--env-file ENV_FILE`
+Specify the .env file to load (default: .env in git root)  
+Default: .env  
+Environment variable: `AIDER_ENV_FILE`  
 
 ### `--suggest-shell-commands`
 Enable/disable suggesting shell commands (default: True)  
@@ -683,6 +732,14 @@ Aliases:
   - `--fancy-input`
   - `--no-fancy-input`
 
+### `--multiline`
+Enable/disable multi-line input mode with Meta-Enter to submit (default: False)  
+Default: False  
+Environment variable: `AIDER_MULTILINE`  
+Aliases:
+  - `--multiline`
+  - `--no-multiline`
+
 ### `--detect-urls`
 Enable/disable detection and offering to add URLs to chat (default: True)  
 Default: True  
@@ -694,20 +751,4 @@ Aliases:
 ### `--editor VALUE`
 Specify which editor to use for the /editor command  
 Environment variable: `AIDER_EDITOR`  
-
-## Voice Settings:
-
-### `--voice-format VOICE_FORMAT`
-Audio format for voice recording (default: wav). webm and mp3 require ffmpeg  
-Default: wav  
-Environment variable: `AIDER_VOICE_FORMAT`  
-
-### `--voice-language VOICE_LANGUAGE`
-Specify the language for voice using ISO 639-1 code (default: auto)  
-Default: en  
-Environment variable: `AIDER_VOICE_LANGUAGE`  
-
-### `--voice-input-device VOICE_INPUT_DEVICE`
-Specify the input device name for voice recording  
-Environment variable: `AIDER_VOICE_INPUT_DEVICE`  
 <!--[[[end]]]-->

aider/website/docs/faq.md

@@ -209,6 +209,47 @@ all the raw information being sent to/from the LLM in the conversation.
 You can also refer to the
 [instructions for installing a development version of aider](https://aider.chat/docs/install/optional.html#install-the-development-version-of-aider).
 
+## What LLMs do you use to build aider?
+
+Aider writes a lot of its own code, usually about 70% of the new code in each
+release.
+People often ask which LLMs I use with aider, when writing aider.
+Below is a table showing the models I have used recently,
+extracted from the 
+[public log](https://github.com/aider-ai/aider/blob/main/aider/website/assets/sample-analytics.jsonl)
+of my
+[aider analytics](https://aider.chat/docs/more/analytics.html).
+
+<!--[[[cog
+import sys
+sys.path.append(".")
+import scripts.my_models as my_models
+stats = my_models.collect_model_stats()
+html = my_models.format_html_table(stats)
+cog.out(html)
+]]]-->
+<style>
+table { border-collapse: collapse; width: 100%; }
+th, td { padding: 8px; text-align: left; border-bottom: 1px solid #ddd; }
+th { background-color: #f2f2f2; }
+tr:hover { background-color: #f5f5f5; }
+.right { text-align: right; }
+</style>
+<table>
+<tr><th>Model Name</th><th class='right'>Total Tokens</th><th class='right'>Percent</th></tr>
+<tr><td>claude-3-5-sonnet-20241022</td><td class='right'>1,630,102</td><td class='right'>88.9%</td></tr>
+<tr><td>o1-preview</td><td class='right'>83,782</td><td class='right'>4.6%</td></tr>
+<tr><td>gemini/REDACTED</td><td class='right'>82,572</td><td class='right'>4.5%</td></tr>
+<tr><td>deepseek/deepseek-coder</td><td class='right'>24,628</td><td class='right'>1.3%</td></tr>
+<tr><td>gpt-4o</td><td class='right'>9,243</td><td class='right'>0.5%</td></tr>
+<tr><td>gpt-4o-mini</td><td class='right'>3,420</td><td class='right'>0.2%</td></tr>
+<tr><td>mistral/REDACTED</td><td class='right'>620</td><td class='right'>0.0%</td></tr>
+</table>
+
+{: .note :}
+Some models show as REDACTED, because they are new or unpopular models.
+Aider's analytics only records the names of "well known" LLMs.
+<!--[[[end]]]-->
 
 ## How are the "aider wrote xx% of code" stats computed?
 

aider/website/docs/install.md

@@ -5,41 +5,84 @@ nav_order: 20
 description: How to install and get started pair programming with aider.
 ---
 
-# Quick start
+# Installation
+{: .no_toc }
+
+
+## Get started quickly with aider-install
 
 {% include get-started.md %}
 
-Or see the
-[full installation instructions](/docs/install/install.html)
-for more details,
-or the
-[usage instructions](https://aider.chat/docs/usage.html) to start coding with aider.
+If needed, 
+aider-install will automatically install a separate version of python3.12 to use with aider.
+
+There are some [optional install steps](/docs/install/optional.html) you could consider.
+See the [usage instructions](https://aider.chat/docs/usage.html) to start coding with aider.
+
+## Install with uv
+
+A recommended way to install aider is with uv:
+
+```bash
+python -m pip install uv  # If you need to install uv
+uv tool install --python python3.12 aider-chat
+```
+
+You can use uv to install aider with your existing python versions 3.8-3.13.
+If needed, 
+uv will automatically install a separate version of python3.12 to use with aider.
+
+Also see the
+[docs on other methods for installing uv itself](https://docs.astral.sh/uv/getting-started/installation/).
+
+## Install with pipx
+
+A recommended way to install aider is with pipx:
+
+```bash
+python -m pip install pipx  # If you need to install pipx
+pipx install aider-chat
+```
+
+You can use pipx to install aider with python versions 3.9-3.12.
+
+Also see the
+[docs on other methods for installing pipx itself](https://pipx.pypa.io/stable/installation/).
+
+
+## Install with pip
+
+You can directly install aider with pip, but one of the above
+methods is usually safer.
+If you do install with pip, you should consider
+using a 
+[virtual environment](https://docs.python.org/3/library/venv.html)
+to keep aider's dependencies separated.
+
+
+You can use pip to install aider with python versions 3.9-3.12.
+
+```bash
+# Install aider
+python -m pip install -U --upgrade-strategy only-if-needed aider-chat
+
+# To work with GPT-4o:
+aider --4o --openai-api-key sk-xxx...
+
+# To work with Claude 3.5 Sonnet:
+aider --sonnet --anthropic-api-key sk-xxx...
+```
 
 {% include python-m-aider.md %}
 
-<div class="video-container">
-  <video controls poster="/assets/install.jpg">
-    <source src="/assets/install.mp4" type="video/mp4">
-    <a href="/assets/install.mp4">Installing aider</a>
-  </video>
-</div>
+## Installing with package managers
 
-<style>
-.video-container {
-  position: relative;
-  padding-bottom: 76.2711864407%;
-  height: 0;
-  overflow: hidden;
-}
-
-.video-container video {
-  position: absolute;
-  top: 0;
-  left: 0;
-  width: 100%;
-  height: 100%;
-}
-</style>
+It's best to install aider using aider-install, uv or pipx as described above.
+While aider is available in a number of system package managers,
+they often install aider with incorrect dependencies.
 
+## Next steps...
 
+There are some [optional install steps](/docs/install/optional.html) you could consider.
+See the [usage instructions](https://aider.chat/docs/usage.html) to start coding with aider.
 

aider/website/docs/install/codespaces.md

@@ -8,9 +8,9 @@ nav_order: 900
 
 You can use aider in GitHub Codespaces via the built-in Terminal pane.
 See below for an example,
-but you can see the 
+but you can just follow the
 [main install instructions](/docs/install.html)
-for all the details.
+inside your codespace terminal.
 
 
 <div class="video-container">

aider/website/docs/install/install.md

@@ -1,70 +0,0 @@
----
-parent: Installation
-nav_order: 10
----
-
-# Installing aider
-{: .no_toc }
-
-- TOC
-{:toc}
-
-## Python version
-
-Aider currently works with python 3.9-3.12.
-
-## Install git
-
-Make sure you have git installed.
-Here are
-[instructions for installing git in various environments](https://github.com/git-guides/install-git).
-
-## Get your API key
-
-To work with OpenAI's models like GPT-4o or GPT-3.5 you need a paid
-[OpenAI API key](https://help.openai.com/en/articles/4936850-where-do-i-find-my-secret-api-key).
-Note that this is different than being a "ChatGPT Plus" subscriber.
-
-To work with Anthropic's models like Claude 3.5 Sonnet you need a paid
-[Anthropic API key](https://docs.anthropic.com/claude/reference/getting-started-with-the-api).
-
-
-{% include venv-pipx.md %}
-
-## Mac/Linux install
-
-```
-# Install aider
-python -m pip install -U --upgrade-strategy only-if-needed aider-chat
-
-# To work with GPT-4o:
-$ aider --4o --openai-api-key sk-xxx...
-
-# To work with Claude 3.5 Sonnet:
-$ aider --sonnet --anthropic-api-key sk-xxx...
-```
-
-## Windows install
-
-```
-# Install aider
-python -m pip install -U --upgrade-strategy only-if-needed aider-chat
-
-# To work with GPT-4o:
-$ aider --4o --openai-api-key sk-xxx...
-
-# To work with Claude 3.5 Sonnet:
-$ aider --sonnet --anthropic-api-key sk-xxx...
-```
-
-{% include python-m-aider.md %}
-
-## Working with other LLMs
-
-{% include works-best.md %}
-
-## You are done!
-
-There are some [optional install steps](/docs/install/optional.html) you could consider.
-See the [usage instructions](https://aider.chat/docs/usage.html) to start coding with aider.
-

aider/website/docs/install/optional.md

@@ -11,10 +11,29 @@ The steps below are completely optional.
 - TOC
 {:toc}
 
+## Install git
 
-## Store your api keys 
+Aider works best if you have git installed.
+Here are
+[instructions for installing git in various environments](https://github.com/git-guides/install-git).
 
-You can [store your api keys in a .env file](/docs/config/dotenv.html)
+## Get your API key
+
+To work with OpenAI's models like GPT-4o or o1-preview you need a paid
+[OpenAI API key](https://help.openai.com/en/articles/4936850-where-do-i-find-my-secret-api-key).
+Note that this is different than being a "ChatGPT Plus" subscriber.
+
+To work with Anthropic's models like Claude 3.5 Sonnet you need a paid
+[Anthropic API key](https://docs.anthropic.com/claude/reference/getting-started-with-the-api).
+
+
+### Working with other LLMs
+
+{% include works-best.md %}
+
+### Store your api keys 
+
+You can [store your api keys in configuration or env files](/docs/config/api-keys.html)
 and they will be loaded automatically whenever you run aider.
 
 ## Enable Playwright 
@@ -55,13 +74,17 @@ Installing PortAudio is completely optional, but can usually be accomplished lik
 - For Linux, do `sudo apt-get install libportaudio2`
   - Some linux environments may also need `sudo apt install libasound2-plugins`
 
-## Add aider to your editor 
+## Add aider to your IDE/editor
 
-Other projects have integrated aider into some IDE/editors.
+You can use 
+[aider's `--watch-files` mode](https://aider.chat/docs/usage/watch.html)
+to integrate with any IDE or editor.
+
+Other projects have made plugins for various IDE/editors.
 It's not clear if they are tracking the latest
 versions of aider,
 so it may be best to just run the latest
-aider in a terminal alongside your editor.
+aider in a terminal alongside your editor and use `--watch-files`.
 
 ### NeoVim
 
@@ -71,9 +94,9 @@ aider in a terminal alongside your editor.
 
 ### VS Code
 
-joshuavial also confirmed that aider works inside a VS Code terminal window.
-Aider detects if it is running inside VSCode and turns off pretty/color output,
-since the VSCode terminal doesn't seem to support it well.
+You can run aider inside a VS Code terminal window.
+There are a number of 3rd party 
+[aider plugins for VSCode](https://marketplace.visualstudio.com/search?term=aider%20-kodu&target=VSCode&category=All%20categories&sortBy=Relevance).
 
 ### Other editors
 
@@ -85,15 +108,8 @@ please let me know by opening a
 ## Install the development version of aider 
 
 If you want the very latest development version of aider
-you can install directly from GitHub:
+you can install it like this:
 
 ```
-python -m pip install --upgrade git+https://github.com/Aider-AI/aider.git
+aider --install-main-branch
 ```
-
-If you've git cloned the aider repository already, you can install "live" from your local copy. This is mostly useful if you are developing aider and want your current modifications to take effect immediately.
-
-```
-python -m pip install -e .
-```
-

aider/website/docs/install/pipx.md

@@ -1,33 +0,0 @@
----
-parent: Installation
-nav_order: 100
----
-
-# Install with pipx
-
-If you are using aider to work on a python project, sometimes your project will require
-specific versions of python packages which conflict with the versions that aider
-requires.
-If this happens, the `python -m pip install` command may return errors like these:
-
-```
-aider-chat 0.23.0 requires somepackage==X.Y.Z, but you have somepackage U.W.V which is incompatible.
-```
-
-You can avoid this problem by installing aider using `pipx`,
-which will install it globally on your system
-within its own python environment.
-This way you can use aider to work on any python project,
-even if that project has conflicting dependencies.
-
-Install [pipx](https://pipx.pypa.io/stable/) then just do:
-
-```
-pipx install aider-chat
-```
-
-
-## pipx on replit
-
-{% include replit-pipx.md %}
-

aider/website/docs/install/replit.md

@@ -0,0 +1,8 @@
+---
+parent: Installation
+nav_order: 900
+---
+
+### Replit
+
+{% include replit-pipx.md %}

aider/website/docs/leaderboards/index.md

@@ -58,6 +58,7 @@ The model also has to successfully apply all its changes to the source file with
 </table>
 
 <canvas id="editChart" width="800" height="450" style="margin-top: 20px"></canvas>
+<script src="https://unpkg.com/patternomaly/dist/patternomaly.js"></script>
 <script src="https://cdn.jsdelivr.net/npm/chart.js"></script>
 <script>
 {% include edit-leaderboard.js %}
@@ -113,6 +114,7 @@ Therefore, results are available for fewer models.
 </table>
 
 <canvas id="refacChart" width="800" height="450" style="margin-top: 20px"></canvas>
+<script src="https://unpkg.com/patternomaly/dist/patternomaly.js"></script>
 <script src="https://cdn.jsdelivr.net/npm/chart.js"></script>
 <script>
 {% include refactor-leaderboard.js %}
@@ -181,6 +183,6 @@ mod_dates = [get_last_modified_date(file) for file in files]
 latest_mod_date = max(mod_dates)
 cog.out(f"{latest_mod_date.strftime('%B %d, %Y.')}")
 ]]]-->
-November 28, 2024.
+December 11, 2024.
 <!--[[[end]]]-->
 </p>

aider/website/docs/legal/privacy.md

@@ -69,7 +69,7 @@ We make reasonable efforts to protect your information by using physical and ele
 
 ### Children’s Privacy
 
-We do not knowingly collect, maintain, or use personal information from children under 18 years of age, and no part of our Service(s) is directed to children. If you learn that a child has provided us with personal information in violation of this Privacy Policy, then you may alert us at [INSERT EMAIL ADDRESS].
+We do not knowingly collect, maintain, or use personal information from children under 18 years of age, and no part of our Service(s) is directed to children. If you learn that a child has provided us with personal information in violation of this Privacy Policy, then you may alert us at privacy@aider.chat.
 
 ### International Visitors
 
@@ -98,7 +98,7 @@ if result.returncode == 0:
     date = datetime.datetime.fromtimestamp(timestamp)
     cog.out(f"{date.strftime('%B %d, %Y.')}")
 ]]]-->
-October 31, 2024.
+December 06, 2024.
 <!--[[[end]]]-->
 
 </p>

aider/website/docs/llms/bedrock.md

@@ -39,12 +39,18 @@ export AWS_PROFILE=your-profile
 You can add these to your 
 [.env file](/docs/config/dotenv.html).
 
-## Bedrock with `pipx` installation
+## Install boto3
 
-The AWS Bedrock provider requires the `boto3` package in order to function correctly. To use aider installed via `pipx` with AWS Bedrock, you must add the `boto3` dependency to aider's virtual environment by running
+The AWS Bedrock provider requires the `boto3` package in order to function correctly:
 
+```bash
+pip install boto3
 ```
-pipx inject aider boto3
+
+To use aider installed via `pipx` with AWS Bedrock, you must add the `boto3` dependency to aider's virtual environment by running
+
+```bash
+pipx inject aider-chat boto3
 ```
 
 
@@ -56,12 +62,18 @@ Once your AWS credentials are set up, you can run Aider with the `--model` comma
 aider --model bedrock/anthropic.claude-3-5-sonnet-20240620-v1:0
 ```
 
+Sometimes it seems to help if you prefix the model name with "us.":
+
+```bash
+aider --model bedrock/us.anthropic.claude-3-5-sonnet-20240620-v1:0
+```
+
 
 ## Available Models
 
 To see some models available via Bedrock, run:
 
-```
+```bash
 aider --list-models bedrock/
 ```
 

aider/website/docs/llms/gemini.md

@@ -5,15 +5,17 @@ nav_order: 300
 
 # Gemini
 
-Google currently offers
-[*free* API access to the Gemini 1.5 Pro model](https://ai.google.dev/pricing).
-This is the most capable free model to use with aider,
-with code editing capability that's comparable to GPT-3.5.
 You'll need a [Gemini API key](https://aistudio.google.com/app/u/2/apikey).
 
 ```
 python -m pip install -U aider-chat
 
+# You may need to install google-generativeai
+pip install -U google-generativeai
+
+# Or with pipx...
+pipx inject aider-chat google-generativeai
+
 export GEMINI_API_KEY=<key> # Mac/Linux
 setx   GEMINI_API_KEY <key> # Windows, restart shell after setx
 

aider/website/docs/troubleshooting/aider-not-found.md

@@ -14,12 +14,11 @@ You may see an error message like this:
 
 > aider: The term 'aider' is not recognized as a name of a cmdlet, function, script file, or executable program. Check the spelling of the name, or if a path was included, verify that the path is correct and try again.
 
-Below is the most fail safe way to install and run aider in these situations:
+Below is the most fail safe way to run aider in these situations:
 
 ```
-python -m pip install -U aider-chat
 python -m aider
 ```
 
-
-{% include venv-pipx.md %}
+You should also consider 
+[installing aider using aider-install, uv or pipx](/docs/install.html).

aider/website/docs/troubleshooting/imports.md

@@ -5,7 +5,7 @@ nav_order: 28
 
 # Dependency versions
 
-Aider expects to be installed via `pip` or `pipx`, which will install
+Aider expects to be installed with the
 correct versions of all of its required dependencies.
 
 If you've been linked to this doc from a GitHub issue, 
@@ -13,43 +13,38 @@ or if aider is reporting `ImportErrors`
 it is likely that your
 aider install is using incorrect dependencies.
 
-## Install with pipx
+
+## Avoid package conflicts
+
+If you are using aider to work on a python project, sometimes your project will require
+specific versions of python packages which conflict with the versions that aider
+requires.
+If this happens, you may see errors like these when running pip installs:
+
+```
+aider-chat 0.23.0 requires somepackage==X.Y.Z, but you have somepackage U.W.V which is incompatible.
+```
+
+## Install with aider-install, uv or pipx
 
 If you are having dependency problems you should consider
-[installing aider using pipx](/docs/install/pipx.html).
+[installing aider using aider-install, uv or pipx](/docs/install.html).
 This will ensure that aider is installed in its own python environment,
 with the correct set of dependencies.
 
-Try re-installing cleanly:
-
-```
-pipx uninstall aider-chat
-pipx install aider-chat
-```
-
 ## Package managers like Homebrew, AUR, ports
 
 Package managers often install aider with the wrong dependencies, leading
 to import errors and other problems.
 
-The recommended way to 
-install aider is with 
-[pip](/docs/install/install.html).
-Be sure to use the `--upgrade-strategy only-if-needed` switch so that the correct
-versions of dependencies will be installed.
+It is recommended to
+[install aider using aider-install, uv or pipx](/docs/install.html).
 
-```
-python -m pip install -U --upgrade-strategy only-if-needed aider-chat
-```
-
-A very safe way is to
-[install aider using pipx](/docs/install/pipx.html),
-which will ensure it is installed in a stand alone virtual environment.
 
 ## Dependency versions matter
 
 Aider pins its dependencies and is tested to work with those specific versions.
-If you are installing aider with pip (rather than pipx),
+If you are installing aider directly with pip
 you should be careful about upgrading or downgrading the python packages that
 aider uses.
 
@@ -64,9 +59,4 @@ and sometimes introduces bugs or backwards incompatible changes.
 
 ## Replit
 
-You can `pip install -U aider-chat` on replit.
-
-Or you can install aider with
-pipx as follows:
-
 {% include replit-pipx.md %}

aider/website/docs/troubleshooting/token-limits.md

@@ -12,11 +12,12 @@ Every LLM has limits on how many tokens it can process for each request:
 - Each model has limit on how many **output tokens** it can
 produce.
 
-Aider will report an error if a model responds indicating that
+Aider will report an error **if a model responds** indicating that
 it has exceeded a token limit.
 The error will include suggested actions to try and
 avoid hitting token limits.
-Here's an example error:
+
+Here's an example error: 
 
 ```
 Model gpt-3.5-turbo has hit a token limit!
@@ -36,9 +37,7 @@ For more info: https://aider.chat/docs/token-limits.html
 {: .note }
 Aider never *enforces* token limits, it only *reports* token limit errors
 from the API provider.
-You probably don't need to
-[configure aider with the proper token limits](https://aider.chat/docs/config/adv-model-settings.html#context-window-size-and-token-costs)
-for unusual models.
+The token counts that aider reports are *estimates*.
 
 ## Input tokens & context window size
 

aider/website/docs/usage/commands.md

@@ -29,6 +29,7 @@ cog.out(get_help_md())
 | **/code** | Ask for changes to your code |
 | **/commit** | Commit edits to the repo made outside the chat (commit message optional) |
 | **/copy** | Copy the last assistant message to the clipboard |
+| **/copy-context** | Copy the current chat context as markdown, suitable to paste into a web UI |
 | **/diff** | Display the diff of changes since the last message |
 | **/drop** | Remove files from the chat session to free up context space |
 | **/editor** | Open an editor to write a prompt |
@@ -42,9 +43,10 @@ cog.out(get_help_md())
 | **/map-refresh** | Force a refresh of the repository map |
 | **/model** | Switch to a new LLM |
 | **/models** | Search the list of available models |
+| **/multiline-mode** | Toggle multiline mode (swaps behavior of Enter and Meta+Enter) |
 | **/paste** | Paste image/text from the clipboard into the chat.        Optionally provide a name for the image. |
 | **/quit** | Exit the application |
-| **/read-only** | Add files to the chat that are for reference, not to be edited |
+| **/read-only** | Add files to the chat that are for reference only, or turn added files to read-only |
 | **/report** | Report a problem by opening a GitHub Issue |
 | **/reset** | Drop all files and clear the chat history |
 | **/run** | Run a shell command and optionally add the output to the chat (alias: !) |

aider/website/docs/usage/conventions.md

@@ -28,6 +28,11 @@ or `aider --read CONVENTIONS.md`.
 This way it is marked as read-only, and cached if prompt caching
 is enabled.
 
+## Community contributed conventions
+
+You can check the [aider conventions repository](https://github.com/Aider-AI/conventions)
+to find or contribute conventions files.
+
 ## Always load conventions
 
 You can also configure aider to always load your conventions file

aider/website/docs/usage/copypaste.md

@@ -0,0 +1,121 @@
+---
+title: Copy/paste with web chat
+#highlight_image: /assets/browser.jpg
+parent: Usage
+nav_order: 850
+description: Aider works with LLM web chat UIs
+---
+
+# Copy/paste with web chat
+
+<div class="video-container">
+  <video controls loop poster="/assets/copypaste.jpg">
+    <source src="/assets/copypaste.mp4" type="video/mp4">
+    <a href="/assets/copypaste.mp4">Aider browser UI demo video</a>
+  </video>
+</div>
+
+<style>
+.video-container {
+  position: relative;
+  padding-bottom: 66.34%; /* 2160 / 3256 = 0.6634 */
+  height: 0;
+  overflow: hidden;
+}
+
+.video-container video {
+  position: absolute;
+  top: 0;
+  left: 0;
+  width: 100%;
+  height: 100%;
+}
+</style>
+
+## Working with an LLM web chat
+
+[Aider can connect to most LLMs via API](https://aider.chat/docs/llms.html) and works best that way.
+But there are times when you may want to work with an LLM via its web chat interface:
+
+- Workplace policies may limit your LLM usage to a proprietary web chat system.
+- The web chat LLM may have access to unique context or may have been specially fine tuned for your task.
+- It may be cost prohibitive to use some models via API.
+- There may not be an API available.
+
+Aider has features for working with an LLM via its web chat interface.
+This allows you to use the web chat LLM as the "big brain code architect"
+while running aider with a smaller, cheaper LLM to actually make changes
+to your local files.
+
+For this "file editor" part of the process 
+you can run aider with many open source, free or very inexpensive LLMs.
+For example, the demo video above shows aider using DeepSeek to apply the changes
+that o1-preview is suggesting in the web chat.
+
+### Copy aider's code context to your clipboard, paste into the web UI
+
+The `/copy-context <instructions>` command can be used in chat to copy aider's code context to your clipboard.
+It will include:
+
+- All the files which have been added to the chat via `/add`.
+- Any read only files which have been added via `/read`.
+- Aider's [repository map](https://aider.chat/docs/repomap.html) that brings in code context related to the above files from elsewhere in your git repo.
+- Some instructions to the LLM that ask it to output change instructions concisely.
+- If you include `<instructions>`, they will be copied too.
+
+You can paste the context into your browser, and start interacting with the LLM web chat to
+ask for code changes.
+
+### Paste the LLM's reply back into aider to edit your files
+
+Once the LLM has replied, you can use the "copy response" button in the web UI to copy
+the LLM's response.
+Back in aider, you can run `/paste` and aider will edit your files
+to implement the changes suggested by the LLM.
+
+You can use a cheap, efficient model like GPT-4o Mini, DeepSeek or Qwen to do these edits.
+This works best if you run aider with `--edit-format editor-diff` or `--edit-format editor-whole`.
+
+### Copy/paste mode
+
+Aider has a `--copy-paste` mode that streamlines this entire process:
+
+- Whenever you `/add` or `/read` files, aider will automatically copy the entire, updated
+code context to your clipboard. 
+You'll see "Copied code context to clipboard" whenever this happens.
+- When you copy the LLM reply to your clipboard outside aider, aider will automatically notice
+and load it into the aider chat. 
+Just press ENTER to send the message
+and aider will apply the LLMs changes to your local files.
+- Aider will automatically select the best edit format for this copy/paste functionality. 
+Depending on the LLM you have aider use, it will be either `editor-whole` or `editor-diff`.
+
+## Terms of service
+
+Be sure to review the Terms Of Service of any LLM web chat service you use with
+these features.
+These features are not intended to be used in violation of any service's Terms Of Service (TOS).
+
+Aider's web chat features have been designed to be compliant with the 
+terms of service of most LLM web chats.
+
+There are 4 copy/paste steps involved when coding with an LLM web chat:
+
+1. Copy code and context from aider.
+2. Paste the code and context into the LLM web chat.
+3. Copy the reply from the LLM web chat.
+4. Paste the LLM reply into aider.
+
+Most LLM web chat TOS prohibit automating steps (2) and (3) where code
+is copied from and pasted into the web chat.
+Aider's `--copy-paste` mode leaves those as 100% manual steps for the user to complete.
+It simply streamlines steps (1) and (4) that are interactions with aider,
+and which should not be under the scope of an LLM web chat TOS.
+
+If you are concerned that
+the automatic interactions with aider in steps (1) and (4) may be problematic with respect to
+your LLM web chat provider's TOS, you can forego `--copy-paste` mode.
+Instead, manually use the `/copy-context` and `/paste` commands if that
+will keep you in compliance.
+
+Again, do not use these features in violation of any service's Terms Of Service.

aider/website/docs/usage/watch.md

@@ -0,0 +1,295 @@
+---
+title: Aider in your IDE
+#highlight_image: /assets/browser.jpg
+parent: Usage
+nav_order: 750
+description: Aider can run in your browser, not just on the command line.
+---
+
+# Aider in your IDE
+
+<div class="video-container">
+  <video controls loop poster="/assets/watch.jpg">
+    <source src="/assets/watch.mp4" type="video/mp4">
+    <a href="/assets/watch.mp4">Aider browser UI demo video</a>
+  </video>
+</div>
+
+<style>
+.video-container {
+  position: relative;
+  padding-bottom: 102.7%; /1.027 */
+  height: 0;
+  overflow: hidden;
+}
+
+.video-container video {
+  position: absolute;
+  top: 0;
+  left: 0;
+  width: 100%;
+  height: 100%;
+}
+</style>
+
+## AI comments
+
+If you run aider with `--watch-files`, it will watch all files in your repo 
+and look for any AI coding instructions you add using your favorite IDE or text editor.
+
+Specifically, aider looks for one-liner comments (# ... or // ...) that either start or end with `AI`, `AI!` or `AI?` like these:
+
+```python
+# Make a snake game. AI!
+# What is the purpose of this method AI?
+```
+
+Or in `//` comment languages...
+
+```js
+// Write a protein folding prediction engine. AI!
+```
+
+Aider will take note of all the comments that start or end with `AI`.
+Comments that include `AI!` with an exclamation point or `AI?` with a question
+mark are special. 
+They triggers aider to take action to collect *all* the AI comments and use them 
+as your instructions.
+
+- `AI!` triggers aider to make changes to your code.
+- `AI?` triggers aider to answer your question.
+
+See the demo video above that shows aider working with AI comments in VSCode. 
+
+
+## Example
+
+For example, if you included this AI comment in your code:
+
+```js
+function factorial(n) // Implement this. AI!
+```
+
+Then aider would update the file and implement the function:
+
+```js
+function factorial(n) {
+  if (n === 0 || n === 1) {
+    return 1;
+  } else {
+    return n * factorial(n - 1);
+  }
+}
+```
+
+## Comment styles
+
+Aider only watches for these types of **one-liner** comments:
+
+```
+# Python and bash style
+// Javascript style 
+-- SQL style 
+```
+
+Aider will look for those comment types in all files.
+You can use them into any code file you're editing, even if they aren't the
+correct comment syntax for that language.
+
+## Multiple uses
+
+This capability is quite flexible and powerful, and can be used in many ways.
+
+### In-context instructions
+
+You can add an AI comment in the function you want changed, 
+explaining the change request in-context right where you want the changes.
+
+```javascript
+app.get('/sqrt/:n', (req, res) => {
+    const n = parseFloat(req.params.n);
+
+    // Add error handling for NaN and less than zero. AI!
+
+    const result = math.sqrt(n);
+    res.json({ result: result });
+});
+```
+
+### Multiple comments
+
+You can add multiple `AI` comments without the `!`,
+before triggering aider with a final `AI!`.
+Also keep in mind that you can spread the AI comments across
+multiple files, if you want to coordinate changes in multiple places.
+Just use `AI!` last, to trigger aider.
+
+```python
+@app.route('/factorial/<int:n>')
+def factorial(n):
+    if n < 0:
+        return jsonify(error="Factorial is not defined for negative numbers"), 400
+        
+    # AI: Refactor this code...
+    
+    result = 1
+    for i in range(1, n + 1):
+        result *= i
+        
+    # ... into to a compute_factorial() function. AI!
+    
+    return jsonify(result=result)
+```
+
+### Long form instructions
+
+You can add a block of comments, with longer instructions.
+Just be sure to start or end one of the lines with `AI` or `AI!` to draw
+aider's attention to the block.
+
+```python
+# Make these changes: AI!
+# - Add a proper main() function
+# - Use Click to process cmd line args
+# - Accept --host and --port args
+# - Print a welcome message that includes the listening url
+
+if __name__ == "__main__":
+    app.run(debug=True)
+```
+
+### Add a file to the aider chat
+
+Rather than using `/add` to add a file inside the aider chat, you can
+simply put an `#AI` comment in it and save the file.
+You can undo/remove the comment immediately if you like, the file
+will still be added to the aider chat.
+
+## Also use aider chat in the terminal
+
+It can be really helpful to get a change started with AI comments.
+But sometimes you want to build on or refine those changes.
+You can of course continue to do that with AI comments,
+but it can sometimes be effective to switch over to the aider terminal chat.
+The chat has the history of the AI comments you just made,
+so you can continue on naturally from there.
+
+You can also use the normal aider chat in your terminal to work with
+many of aider's more advanced features:
+
+- Use `/undo` to revert changes you don't like. Although you may also be able to use your IDE's undo function to step back in the file history.
+- Use [chat modes](https://aider.chat/docs/usage/modes.html) to ask questions or get help.
+- Manage the chat context with `/tokens`, `/clear`, `/drop`, `/reset`.
+Adding an AI comment will add the file to the chat. 
+Periodically, you may want remove extra context that is no longer needed.
+- [Fix lint and test errors](https://aider.chat/docs/usage/lint-test.html).
+- Run shell commands.
+- Etc.
+
+
+## You can be lazy
+
+The examples above all show AI
+comments with full sentences, proper capitalization, punctuation, etc.
+This was done to help explain how AI comments work, but is not needed in practice.
+
+Most LLMs are perfectly capable of dealing with ambiguity and
+inferring implied intent. 
+This often allows you to be quite lazy with your AI comments.
+In particular, you can start and end comments with lowercase `ai` and `ai!`,
+but you can also be much more terse with the request itself.
+Below are simpler versions of some of the examples given above.
+
+When the context clearly implies the needed action, `ai!` might be all you
+need. For example, to implement a factorial function 
+in a program full of other math functions either of these
+approaches would probably work:
+
+```js
+function factorial(n) // ai!
+```
+
+Or...
+
+```js
+// add factorial() ai!
+```
+
+Rather than a long, explicit comment like "Add error handling for NaN and less than zero,"
+you can let aider infer more about the request.
+This simpler comment may be sufficient:
+
+```javascript
+app.get('/sqrt/:n', (req, res) => {
+    const n = parseFloat(req.params.n);
+
+    // add error handling ai!
+
+    const result = math.sqrt(n);
+    res.json({ result: result });
+});
+```
+
+Similarly, this refactor probably could have been requested with fewer words, like this:
+
+```python
+@app.route('/factorial/<int:n>')
+def factorial(n):
+    if n < 0:
+        return jsonify(error="Factorial is not defined for negative numbers"), 400
+        
+    # ai refactor...
+    
+    result = 1
+    for i in range(1, n + 1):
+        result *= i
+        
+    # ... to compute_factorial() ai!
+    
+    return jsonify(result=result)
+```
+
+As you use aider with your chosen LLM, you can develop a sense for how
+explicit you need to make your AI comments.
+
+## Behind the scenes
+
+Aider sends your AI comments to the LLM with the
+[repo map](https://aider.chat/docs/repomap.html)
+and all the other code context you've added to the chat.
+
+It also pulls out and highlights the AI comments with specific context, showing the LLM
+exactly how they fit into the code base.
+
+```
+The "AI" comments below marked with █ can be found in the code files I've shared with you.
+They contain your instructions.
+Make the requested changes.
+Be sure to remove all these "AI" comments from the code!
+
+todo_app.py:
+⋮...
+│class TodoList:
+⋮...
+│    def __init__(self):
+│        """Initialize an empty todo list"""
+⋮...
+│
+│    def list_tasks(self):
+│        """Display all tasks"""
+█        # Implement this. AI!
+│
+│def main():
+│    todo = TodoList()
+│
+⋮...
+```
+
+--------
+
+#### Credits
+
+*This feature was inspired by 
+the way [Override](https://github.com/oi-overide) watches for file changes
+to find prompts embedded within `//> a specific set of delimiters <//`.*
+

aider/website/index.md

@@ -70,28 +70,27 @@ Aider works best with GPT-4o & Claude 3.5 Sonnet and can
 cog.out(open("aider/website/_includes/get-started.md").read())
 -->
 
-You can get started quickly like this:
+You can get started quickly like this, with python 3.8-3.13:
 
-```
-python -m pip install -U aider-chat
+```bash
+python -m pip install aider-install
+aider-install
 
-# Change directory into a git repo
+# Change directory into your code base
 cd /to/your/git/repo
 
 # Work with Claude 3.5 Sonnet on your repo
-export ANTHROPIC_API_KEY=your-key-goes-here
-aider
+aider --model sonnet --anthropic-api-key your-key-goes-here
 
 # Work with GPT-4o on your repo
-export OPENAI_API_KEY=your-key-goes-here
-aider 
+aider --model gpt-4o --openai-api-key your-key-goes-here
 ```
 <!-- NOOP -->
 
 See the
 [installation instructions](https://aider.chat/docs/install.html)
-and other
-[documentation](https://aider.chat/docs/usage.html)
+and
+[usage documentation](https://aider.chat/docs/usage.html)
 for more details.
 
 ## Features

benchmark/benchmark.py

@@ -24,8 +24,8 @@ from dotenv import load_dotenv
 from plots import plot_refactoring
 from rich.console import Console
 
-from aider import models
-from aider.coders import Coder
+from aider import models, sendchat
+from aider.coders import Coder, base_coder
 from aider.dump import dump  # noqa: F401
 from aider.io import InputOutput
 
@@ -158,6 +158,9 @@ def main(
     dirnames: Optional[List[str]] = typer.Argument(None, help="Directory names"),
     graphs: bool = typer.Option(False, "--graphs", help="Generate graphs"),
     model: str = typer.Option("gpt-3.5-turbo", "--model", "-m", help="Model name"),
+    sleep: float = typer.Option(
+        0, "--sleep", help="Sleep seconds between tests when single threaded"
+    ),
     edit_format: str = typer.Option(None, "--edit-format", "-e", help="Edit format"),
     editor_model: str = typer.Option(None, "--editor-model", help="Editor model name"),
     editor_edit_format: str = typer.Option(None, "--editor-edit-format", help="Editor edit format"),
@@ -267,6 +270,11 @@ def main(
     if num_tests > 0:
         test_dnames = test_dnames[:num_tests]
 
+    # Don't give up when benchmarking
+    LONG_TIMEOUT = 24 * 60 * 60
+    sendchat.RETRY_TIMEOUT = LONG_TIMEOUT
+    base_coder.RETRY_TIMEOUT = LONG_TIMEOUT
+
     if threads == 1:
         all_results = []
         for testname in test_dnames:
@@ -285,10 +293,13 @@ def main(
                 editor_model,
                 editor_edit_format,
                 num_ctx,
+                sleep,
             )
 
             all_results.append(results)
             summarize_results(dirname)
+            if sleep:
+                time.sleep(sleep)
     else:
         run_test_threaded = lox.thread(threads)(run_test)
         for testname in test_dnames:
@@ -565,6 +576,7 @@ def run_test_real(
     editor_model,
     editor_edit_format,
     num_ctx=None,
+    sleep=0,
 ):
     if not os.path.isdir(testdir):
         print("Not a dir:", testdir)

pyproject.toml

@@ -1,7 +1,3 @@
-# [[[cog
-# from aider.help_pats import exclude_website_pats
-# ]]]
-# [[[end]]]
 
 [project]
 name = "aider-chat"
@@ -38,29 +34,11 @@ help = { file = "requirements/requirements-help.txt" }
 browser = { file = "requirements/requirements-browser.txt" }
 playwright = { file = "requirements/requirements-playwright.txt" }
 
+[tool.setuptools]
+include-package-data = true
+
 [tool.setuptools.packages.find]
-include = ["aider*", "aider.website"]
-
-[tool.setuptools.package-data]
-"aider" = ["queries/*.scm"]
-"aider.website" = ["**/*.md"]
-
-[tool.setuptools.exclude-package-data]
-"aider.website" = [
-# [[[cog
-# cog.out("\n".join(f'    "{pat}",' for pat in exclude_website_pats))
-# ]]]
-"examples/**",
-"_posts/**",
-"HISTORY.md",
-"docs/benchmarks*md",
-"docs/ctags.md",
-"docs/unified-diffs.md",
-"docs/leaderboards/index.md",
-"assets/**",
-"**/.DS_Store",
-# [[[end]]]
-]
+include = ["aider"]
 
 [build-system]
 requires = ["setuptools>=68", "setuptools_scm[toml]>=8"]

requirements.txt

@@ -2,20 +2,21 @@
 # This file is autogenerated by pip-compile with Python 3.12
 # by the following command:
 #
-#    pip-compile --output-file=requirements.txt requirements/requirements.in
+#    pip-compile --allow-unsafe --output-file=requirements.txt requirements/requirements.in
 #
-aiohappyeyeballs==2.4.3
+aiohappyeyeballs==2.4.4
     # via aiohttp
-aiohttp==3.11.7
+aiohttp==3.11.10
     # via litellm
 aiosignal==1.3.1
     # via aiohttp
 annotated-types==0.7.0
     # via pydantic
-anyio==4.6.2.post1
+anyio==4.7.0
     # via
     #   httpx
     #   openai
+    #   watchfiles
 attrs==24.2.0
     # via
     #   aiohttp
@@ -69,8 +70,10 @@ h11==0.14.0
 httpcore==1.0.7
     # via httpx
 httpx==0.27.2
-    # via openai
-huggingface-hub==0.26.2
+    # via
+    #   litellm
+    #   openai
+huggingface-hub==0.26.5
     # via tokenizers
 idna==3.10
     # via
@@ -96,7 +99,7 @@ jsonschema==4.23.0
     #   litellm
 jsonschema-specifications==2024.10.1
     # via jsonschema
-litellm==1.52.16
+litellm==1.53.9
     # via -r requirements/requirements.in
 markdown-it-py==3.0.0
     # via rich
@@ -120,7 +123,7 @@ numpy==1.26.4
     # via
     #   -r requirements/requirements.in
     #   scipy
-openai==1.55.2
+openai==1.57.0
     # via litellm
 packaging==24.2
     # via
@@ -134,11 +137,11 @@ pexpect==4.9.0
     # via -r requirements/requirements.in
 pillow==10.4.0
     # via -r requirements/requirements.in
-posthog==3.7.3
+posthog==3.7.4
     # via -r requirements/requirements.in
 prompt-toolkit==3.0.48
     # via -r requirements/requirements.in
-propcache==0.2.0
+propcache==0.2.1
     # via
     #   aiohttp
     #   yarl
@@ -150,7 +153,7 @@ pycodestyle==2.12.1
     # via flake8
 pycparser==2.22
     # via cffi
-pydantic==2.10.2
+pydantic==2.10.3
     # via
     #   litellm
     #   openai
@@ -189,13 +192,13 @@ requests==2.32.3
     #   tiktoken
 rich==13.9.4
     # via -r requirements/requirements.in
-rpds-py==0.21.0
+rpds-py==0.22.3
     # via
     #   jsonschema
     #   referencing
 scipy==1.13.1
     # via -r requirements/requirements.in
-six==1.16.0
+six==1.17.0
     # via
     #   mixpanel
     #   posthog
@@ -231,6 +234,7 @@ tree-sitter-languages==1.10.2
     # via grep-ast
 typing-extensions==4.12.2
     # via
+    #   anyio
     #   huggingface-hub
     #   openai
     #   pydantic
@@ -239,9 +243,15 @@ urllib3==2.2.3
     # via
     #   mixpanel
     #   requests
+watchfiles==1.0.0
+    # via -r requirements/requirements.in
 wcwidth==0.2.13
     # via prompt-toolkit
-yarl==1.18.0
+yarl==1.18.3
     # via aiohttp
 zipp==3.21.0
     # via importlib-metadata
+
+# The following packages are considered to be unsafe in a requirements file:
+pip==24.3.1
+    # via -r requirements/requirements.in

requirements/requirements-browser.txt

@@ -2,7 +2,7 @@
 # This file is autogenerated by pip-compile with Python 3.12
 # by the following command:
 #
-#    pip-compile --constraint=requirements.txt --constraint=requirements/requirements-dev.txt --constraint=requirements/requirements-help.txt --output-file=requirements/requirements-browser.txt requirements/requirements-browser.in
+#    pip-compile --allow-unsafe --constraint=requirements.txt --constraint=requirements/requirements-dev.txt --constraint=requirements/requirements-help.txt --output-file=requirements/requirements-browser.txt requirements/requirements-browser.in
 #
 altair==5.5.0
     # via streamlit
@@ -92,7 +92,7 @@ mdurl==0.1.2
     #   -c requirements.txt
     #   -c requirements/requirements-dev.txt
     #   markdown-it-py
-narwhals==1.14.2
+narwhals==1.16.0
     # via altair
 numpy==1.26.4
     # via
@@ -122,7 +122,7 @@ pillow==10.4.0
     #   -c requirements/requirements-dev.txt
     #   -c requirements/requirements-help.txt
     #   streamlit
-protobuf==5.28.3
+protobuf==5.29.1
     # via streamlit
 pyarrow==18.1.0
     # via streamlit
@@ -163,13 +163,13 @@ rich==13.9.4
     #   -c requirements.txt
     #   -c requirements/requirements-dev.txt
     #   streamlit
-rpds-py==0.21.0
+rpds-py==0.22.3
     # via
     #   -c /Users/gauthier/Projects/aider/requirements.txt
     #   -c requirements.txt
     #   jsonschema
     #   referencing
-six==1.16.0
+six==1.17.0
     # via
     #   -c /Users/gauthier/Projects/aider/requirements.txt
     #   -c requirements.txt

requirements/requirements-dev.txt

@@ -2,7 +2,7 @@
 # This file is autogenerated by pip-compile with Python 3.12
 # by the following command:
 #
-#    pip-compile --constraint=requirements.txt --output-file=requirements/requirements-dev.txt requirements/requirements-dev.in
+#    pip-compile --allow-unsafe --constraint=requirements.txt --output-file=requirements/requirements-dev.txt requirements/requirements-dev.in
 #
 alabaster==1.0.0
     # via sphinx
@@ -51,7 +51,7 @@ filelock==3.16.1
     #   -c /Users/gauthier/Projects/aider/requirements.txt
     #   -c requirements.txt
     #   virtualenv
-fonttools==4.55.0
+fonttools==4.55.2
     # via matplotlib
 identify==2.6.3
     # via pre-commit
@@ -85,7 +85,7 @@ markupsafe==3.0.2
     #   -c /Users/gauthier/Projects/aider/requirements.txt
     #   -c requirements.txt
     #   jinja2
-matplotlib==3.9.2
+matplotlib==3.9.3
     # via -r requirements/requirements-dev.in
 mdurl==0.1.2
     # via
@@ -144,7 +144,7 @@ pyproject-hooks==1.2.0
     # via
     #   build
     #   pip-tools
-pytest==8.3.3
+pytest==8.3.4
     # via
     #   -r requirements/requirements-dev.in
     #   pytest-env
@@ -177,7 +177,7 @@ semver==3.0.2
     # via -r requirements/requirements-dev.in
 shellingham==1.5.4
     # via typer
-six==1.16.0
+six==1.17.0
     # via
     #   -c /Users/gauthier/Projects/aider/requirements.txt
     #   -c requirements.txt
@@ -204,7 +204,7 @@ sphinxcontrib-qthelp==2.0.0
     # via sphinx
 sphinxcontrib-serializinghtml==2.0.0
     # via sphinx
-typer==0.13.1
+typer==0.15.1
     # via -r requirements/requirements-dev.in
 typing-extensions==4.12.2
     # via
@@ -224,5 +224,10 @@ wheel==0.45.1
     # via pip-tools
 
 # The following packages are considered to be unsafe in a requirements file:
-# pip
-# setuptools
+pip==24.3.1
+    # via
+    #   -c /Users/gauthier/Projects/aider/requirements.txt
+    #   -c requirements.txt
+    #   pip-tools
+setuptools==75.6.0
+    # via pip-tools

requirements/requirements-help.txt

@@ -2,14 +2,14 @@
 # This file is autogenerated by pip-compile with Python 3.12
 # by the following command:
 #
-#    pip-compile --constraint=requirements.txt --constraint=requirements/requirements-dev.txt --output-file=requirements/requirements-help.txt requirements/requirements-help.in
+#    pip-compile --allow-unsafe --constraint=requirements.txt --constraint=requirements/requirements-dev.txt --output-file=requirements/requirements-help.txt requirements/requirements-help.in
 #
-aiohappyeyeballs==2.4.3
+aiohappyeyeballs==2.4.4
     # via
     #   -c /Users/gauthier/Projects/aider/requirements.txt
     #   -c requirements.txt
     #   aiohttp
-aiohttp==3.11.7
+aiohttp==3.11.10
     # via
     #   -c /Users/gauthier/Projects/aider/requirements.txt
     #   -c requirements.txt
@@ -25,7 +25,7 @@ annotated-types==0.7.0
     #   -c /Users/gauthier/Projects/aider/requirements.txt
     #   -c requirements.txt
     #   pydantic
-anyio==4.6.2.post1
+anyio==4.7.0
     # via
     #   -c /Users/gauthier/Projects/aider/requirements.txt
     #   -c requirements.txt
@@ -103,7 +103,7 @@ httpx==0.27.2
     #   -c /Users/gauthier/Projects/aider/requirements.txt
     #   -c requirements.txt
     #   llama-index-core
-huggingface-hub[inference]==0.26.2
+huggingface-hub[inference]==0.26.5
     # via
     #   -c /Users/gauthier/Projects/aider/requirements.txt
     #   -c requirements.txt
@@ -188,13 +188,13 @@ pillow==10.4.0
     #   -c requirements/requirements-dev.txt
     #   llama-index-core
     #   sentence-transformers
-propcache==0.2.0
+propcache==0.2.1
     # via
     #   -c /Users/gauthier/Projects/aider/requirements.txt
     #   -c requirements.txt
     #   aiohttp
     #   yarl
-pydantic==2.10.2
+pydantic==2.10.3
     # via
     #   -c /Users/gauthier/Projects/aider/requirements.txt
     #   -c requirements.txt
@@ -284,6 +284,7 @@ typing-extensions==4.12.2
     #   -c /Users/gauthier/Projects/aider/requirements.txt
     #   -c requirements.txt
     #   -c requirements/requirements-dev.txt
+    #   anyio
     #   huggingface-hub
     #   llama-index-core
     #   pydantic
@@ -305,7 +306,7 @@ wrapt==1.17.0
     # via
     #   deprecated
     #   llama-index-core
-yarl==1.18.0
+yarl==1.18.3
     # via
     #   -c /Users/gauthier/Projects/aider/requirements.txt
     #   -c requirements.txt

requirements/requirements-playwright.txt

@@ -2,7 +2,7 @@
 # This file is autogenerated by pip-compile with Python 3.12
 # by the following command:
 #
-#    pip-compile --constraint=requirements.txt --constraint=requirements/requirements-browser.txt --constraint=requirements/requirements-dev.txt --constraint=requirements/requirements-help.txt --output-file=requirements/requirements-playwright.txt requirements/requirements-playwright.in
+#    pip-compile --allow-unsafe --constraint=requirements.txt --constraint=requirements/requirements-browser.txt --constraint=requirements/requirements-dev.txt --constraint=requirements/requirements-help.txt --output-file=requirements/requirements-playwright.txt requirements/requirements-playwright.in
 #
 greenlet==3.0.3
     # via

requirements/requirements.in

@@ -28,6 +28,8 @@ mixpanel
 pexpect
 json5
 psutil
+watchfiles
+pip
 
 # The proper dependency is networkx[default], but this brings
 # in matplotlib and a bunch of other deps

scripts/blame.py

@@ -12,6 +12,12 @@ import semver
 import yaml
 from tqdm import tqdm
 
+website_files = [
+    "aider/website/share/index.md",
+    "aider/website/_includes/head_custom.html",
+    "aider/website/docs/leaderboards/index.md",
+]
+
 
 def blame(start_tag, end_tag=None):
     commits = get_all_commit_hashes_between_tags(start_tag, end_tag)
@@ -26,10 +32,10 @@ def blame(start_tag, end_tag=None):
         for f in files
         if f.endswith((".js", ".py", ".scm", ".sh", "Dockerfile", "Gemfile"))
         or (f.startswith(".github/workflows/") and f.endswith(".yml"))
-        or f == "aider/website/share/index.md"
-        or f == "aider/website/docs/leaderboards/index.md"
+        or f in website_files
     ]
     files = [f for f in files if not f.endswith("prompts.py")]
+    files = [f for f in files if not f.startswith("tests/fixtures/watch")]
 
     all_file_counts = {}
     grand_total = defaultdict(int)
@@ -203,9 +209,23 @@ def main():
 def get_counts_for_file(start_tag, end_tag, authors, fname):
     try:
         if end_tag:
-            text = run(["git", "blame", f"{start_tag}..{end_tag}", "--", fname])
+            text = run(
+                [
+                    "git",
+                    "blame",
+                    "-M",
+                    "-C",
+                    "-C",
+                    "--abbrev=9",
+                    f"{start_tag}..{end_tag}",
+                    "--",
+                    fname,
+                ]
+            )
         else:
-            text = run(["git", "blame", f"{start_tag}..HEAD", "--", fname])
+            text = run(
+                ["git", "blame", "-M", "-C", "-C", "--abbrev=9", f"{start_tag}..HEAD", "--", fname]
+            )
         if not text:
             return None
         text = text.splitlines()

scripts/history_prompts.py

@@ -0,0 +1,16 @@
+history_prompt = """
+Update the history with changes shown in the diffs.
+Describe actual user-facing changes, not every single commit that was made implementing them.
+
+Only add new items not already listed.
+Do NOT edit or update existing history entries.
+Do NOT add duplicate entries for changes that have existing history entries.
+
+End each bullet with a period.
+
+Be sure to attribute changes to the proper .x version.
+Changes in the .x-dev version should be listed under a "### main branch" heading
+
+Also, add this as the last bullet under the "### main branch" section:
+{aider_line}
+"""  # noqa

scripts/issues.py

@@ -46,6 +46,20 @@ CLOSE_STALE_COMMENT = (
     + BOT_SUFFIX
 )
 
+CLOSE_FIXED_ENHANCEMENT_COMMENT = (
+    """I'm closing this enhancement request since it has been marked as 'fixed' for over """
+    """3 weeks. The requested feature should now be available in recent versions of aider.\n\n"""
+    """If you find that this enhancement is still needed, please feel free to reopen this """
+    """issue or create a new one.""" + BOT_SUFFIX
+)
+
+CLOSE_FIXED_BUG_COMMENT = (
+    """I'm closing this bug report since it has been marked as 'fixed' for over """
+    """3 weeks. This issue should be resolved in recent versions of aider.\n\n"""
+    """If you find that this bug is still present, please feel free to reopen this """
+    """issue or create a new one with steps to reproduce.""" + BOT_SUFFIX
+)
+
 # GitHub API configuration
 GITHUB_API_URL = "https://api.github.com"
 REPO_OWNER = "Aider-AI"
@@ -306,6 +320,68 @@ def handle_stale_closing(all_issues, auto_yes):
                 print(f"  Closed issue #{issue['number']}")
 
 
+def handle_fixed_issues(all_issues, auto_yes):
+    print("\nChecking for fixed enhancement and bug issues to close...")
+
+    for issue in all_issues:
+        # Skip if not open or doesn't have fixed label
+        labels = [label["name"] for label in issue["labels"]]
+        if issue["state"] != "open" or "fixed" not in labels:
+            continue
+
+        # Check if it's an enhancement or bug
+        is_enhancement = "enhancement" in labels
+        is_bug = "bug" in labels
+        if not (is_enhancement or is_bug):
+            continue
+
+        # Find when the fixed label was added
+        timeline_url = (
+            f"{GITHUB_API_URL}/repos/{REPO_OWNER}/{REPO_NAME}/issues/{issue['number']}/timeline"
+        )
+        response = requests.get(timeline_url, headers=headers)
+        response.raise_for_status()
+        events = response.json()
+
+        # Find the most recent fixed label addition
+        fixed_events = [
+            event
+            for event in events
+            if event.get("event") == "labeled" and event.get("label", {}).get("name") == "fixed"
+        ]
+
+        if not fixed_events:
+            continue
+
+        latest_fixed = datetime.strptime(fixed_events[-1]["created_at"], "%Y-%m-%dT%H:%M:%SZ")
+        days_fixed = (datetime.now() - latest_fixed).days
+
+        if days_fixed >= 21:
+            issue_type = "enhancement" if is_enhancement else "bug"
+            print(f"\nFixed {issue_type} ready for closing #{issue['number']}: {issue['title']}")
+            print(f"  Has been marked fixed for {days_fixed} days")
+
+            if not auto_yes:
+                confirm = input("Close this issue? (y/n): ")
+                if confirm.lower() != "y":
+                    print("Skipping this issue.")
+                    continue
+
+            # Add closing comment
+            comment_url = (
+                f"{GITHUB_API_URL}/repos/{REPO_OWNER}/{REPO_NAME}/issues/{issue['number']}/comments"
+            )
+            comment = CLOSE_FIXED_ENHANCEMENT_COMMENT if is_enhancement else CLOSE_FIXED_BUG_COMMENT
+            response = requests.post(comment_url, headers=headers, json={"body": comment})
+            response.raise_for_status()
+
+            # Close the issue
+            url = f"{GITHUB_API_URL}/repos/{REPO_OWNER}/{REPO_NAME}/issues/{issue['number']}"
+            response = requests.patch(url, headers=headers, json={"state": "closed"})
+            response.raise_for_status()
+            print(f"  Closed issue #{issue['number']}")
+
+
 def handle_duplicate_issues(all_issues, auto_yes):
     open_issues = [issue for issue in all_issues if issue["state"] == "open"]
     grouped_open_issues = group_issues_by_subject(open_issues)
@@ -363,6 +439,7 @@ def main():
     handle_stale_issues(all_issues, args.yes)
     handle_stale_closing(all_issues, args.yes)
     handle_duplicate_issues(all_issues, args.yes)
+    handle_fixed_issues(all_issues, args.yes)
 
 
 if __name__ == "__main__":

scripts/my_models.py

@@ -0,0 +1,95 @@
+#!/usr/bin/env python3
+
+import json
+from collections import defaultdict, deque
+from pathlib import Path
+
+
+def collect_model_stats(n_lines=1000):
+    """Collect model usage statistics from the analytics file."""
+    analytics_path = Path.home() / ".aider" / "analytics.jsonl"
+    model_stats = defaultdict(int)
+
+    with open(analytics_path) as f:
+        lines = deque(f, n_lines)
+        for line in lines:
+            try:
+                event = json.loads(line)
+                if event["event"] == "message_send":
+                    properties = event["properties"]
+                    main_model = properties.get("main_model")
+                    total_tokens = properties.get("total_tokens", 0)
+                    if main_model:
+                        model_stats[main_model] += total_tokens
+            except json.JSONDecodeError:
+                continue
+
+    return model_stats
+
+
+def format_text_table(model_stats):
+    """Format model statistics as a text table."""
+    total_tokens = sum(model_stats.values())
+    lines = []
+
+    lines.append("\nModel Token Usage Summary:")
+    lines.append("-" * 80)
+    lines.append(f"{'Model Name':<40} {'Total Tokens':>15} {'Percent':>10}")
+    lines.append("-" * 80)
+
+    for model, tokens in sorted(model_stats.items(), key=lambda x: x[1], reverse=True):
+        percentage = (tokens / total_tokens) * 100 if total_tokens > 0 else 0
+        lines.append(f"{model:<40} {tokens:>15,} {percentage:>9.1f}%")
+
+    lines.append("-" * 80)
+    lines.append(f"{'TOTAL':<40} {total_tokens:>15,} {100:>9.1f}%")
+
+    return "\n".join(lines)
+
+
+def format_html_table(model_stats):
+    """Format model statistics as an HTML table."""
+    total_tokens = sum(model_stats.values())
+
+    html = [
+        "<style>",
+        "table { border-collapse: collapse; width: 100%; }",
+        "th, td { padding: 8px; text-align: left; border-bottom: 1px solid #ddd; }",
+        "th { background-color: #f2f2f2; }",
+        "tr:hover { background-color: #f5f5f5; }",
+        ".right { text-align: right; }",
+        "</style>",
+        "<table>",
+        (
+            "<tr><th>Model Name</th><th class='right'>Total Tokens</th><th"
+            " class='right'>Percent</th></tr>"
+        ),
+    ]
+
+    for model, tokens in sorted(model_stats.items(), key=lambda x: x[1], reverse=True):
+        percentage = (tokens / total_tokens) * 100 if total_tokens > 0 else 0
+        html.append(
+            f"<tr><td>{model}</td>"
+            f"<td class='right'>{tokens:,}</td>"
+            f"<td class='right'>{percentage:.1f}%</td></tr>"
+        )
+
+    html.append("</table>")
+
+    # Add note about redacted models if any are present
+    if any("REDACTED" in model for model in model_stats.keys()):
+        html.extend(
+            [
+                "",
+                "{: .note :}",
+                "Some models show as REDACTED, because they are new or unpopular models.",
+                'Aider\'s analytics only records the names of "well known" LLMs.',
+            ]
+        )
+
+    return "\n".join(html)
+
+
+if __name__ == "__main__":
+    stats = collect_model_stats()
+    print(format_text_table(stats))

scripts/pip-compile.sh

@@ -5,6 +5,7 @@ set -e
 
 # First compile the base requirements
 pip-compile \
+    --allow-unsafe \
     requirements/requirements.in \
     --output-file=requirements.txt \
     $1
@@ -15,6 +16,7 @@ CONSTRAINTS="--constraint=requirements.txt"
 
 for SUFFIX in "${SUFFIXES[@]}"; do
     pip-compile \
+        --allow-unsafe \
         requirements/requirements-${SUFFIX}.in \
         --output-file=requirements/requirements-${SUFFIX}.txt \
         ${CONSTRAINTS} \

scripts/update-blame.sh

@@ -3,4 +3,6 @@
 # exit when any command fails
 set -e
 
-./scripts/blame.py v0.1.0 --all --output aider/website/_data/blame.yml
+# Use first argument as version if provided, otherwise default to v0.1.0
+VERSION=${1:-v0.1.0}
+./scripts/blame.py "$VERSION" --all --output aider/website/_data/blame.yml

scripts/update-docs.sh

@@ -20,6 +20,7 @@ cog $ARG \
     aider/website/HISTORY.md \
     aider/website/docs/usage/commands.md \
     aider/website/docs/languages.md \
+    aider/website/docs/faq.md \
     aider/website/docs/config/dotenv.md \
     aider/website/docs/config/options.md \
     aider/website/docs/config/aider_conf.md \

scripts/update-history.py

@@ -5,6 +5,8 @@ import re
 import subprocess
 import tempfile
 
+from history_prompts import history_prompt
+
 from aider import __version__
 
 
@@ -76,16 +78,7 @@ def main():
     aider_line = blame_result.stdout.strip().split("\n")[-1]  # Get last line with percentage
 
     # Construct and run the aider command
-    message = f"""
-Update the history with changes shown in the diffs.
-Describe actual user-facing changes, not every single commit that was made implementing them.
-Don't edit or duplicate changes that have existing history entries, just add any new items not already listed.
-Be sure to attribute changes to the proper .x version.
-Changes in the .x-dev version should be listed under a "### main branch" heading
-
-Also, add this as the last bullet under the "### main branch" section:
-{aider_line}
-"""  # noqa
+    message = history_prompt.format(aider_line=aider_line)
 
     cmd = ["aider", hist_path, "--read", diff_path, "--msg", message, "--no-auto-commit"]
     subprocess.run(cmd)

scripts/versionbump.py

@@ -10,15 +10,6 @@ import sys
 from packaging import version
 
 
-def check_cog_pyproject():
-    result = subprocess.run(["cog", "--check", "pyproject.toml"], capture_output=True, text=True)
-
-    if result.returncode != 0:
-        print("Error: cog --check pyproject.toml failed, updating.")
-        subprocess.run(["cog", "-r", "pyproject.toml"])
-        sys.exit(1)
-
-
 def main():
     parser = argparse.ArgumentParser(description="Bump version")
     parser.add_argument("new_version", help="New version in x.y.z format")
@@ -82,7 +73,6 @@ def main():
     dry_run = args.dry_run
 
     # Perform checks before proceeding
-    check_cog_pyproject()
     check_branch()
     check_working_directory_clean()
     check_main_branch_up_to_date()
@@ -154,8 +144,8 @@ def main():
         if not dry_run:
             subprocess.run(cmd, check=True)
 
-    # Remove aider/__version__.py if it exists
-    version_file = "aider/__version__.py"
+    # Remove aider/_version.py if it exists
+    version_file = "aider/_version.py"
     if os.path.exists(version_file):
         print(f"Removing {version_file}")
         if not dry_run: