set version to 0.65.1.dev

Add dart support

.github/workflows/close-stale.yml

@@ -1,24 +0,0 @@
-name: 'Close stale issues and PRs'
-on:
-  schedule:
-    - cron: '30 1 * * *'
-  workflow_dispatch:
-
-permissions:
-  issues: write
-
-jobs:
-  stale:
-    runs-on: ubuntu-latest
-    steps:
-      - uses: actions/stale@v9
-        with:
-          stale-issue-message: 'This issue has been labelled stale because it has been open for 2 weeks with no activity. Remove stale label or add a comment to keep this issue open. Otherwise, it will be closed in 7 days.'
-          close-issue-message: 'This issue was closed because it has been stalled for 3 weeks with no activity. Feel free to add a comment here and we can re-open it. Or feel free to file a new issue any time.'
-          days-before-stale: 14
-          days-before-close: 7
-          stale-issue-label: 'stale'
-          stale-pr-label: 'stale'
-          only-labels: 'question'
-          days-before-pr-stale: -1
-          days-before-pr-close: -1

.gitignore

@@ -11,4 +11,5 @@ _site
 .jekyll-cache/
 .jekyll-metadata
 aider/__version__.py
-.venv/
+.venv/
+.gitattributes

CONTRIBUTING.md

@@ -187,8 +187,8 @@ pytest
 You can also run specific test files or test cases by providing the file path or test name:
 
 ```
-pytest aider/tests/test_coder.py
-pytest aider/tests/test_coder.py::TestCoder::test_specific_case
+pytest tests/basic/test_coder.py
+pytest tests/basic/test_coder.py::TestCoder::test_specific_case
 ```
 
 #### Continuous Integration

HISTORY.md

@@ -1,8 +1,82 @@
-
 # Release history
 
 ### main branch
 
+- Added `--alias` config to define [custom model aliases](https://aider.chat/docs/config/model-aliases.html).
+- Added `--[no-]detect-urls` flag to disable detecting and offering to scrape URLs found in the chat.
+- Ollama models now default to an 8k context window.
+- Added [RepoMap support for Dart language](https://aider.chat/docs/languages.html) by @malkoG.
+- Ask 2.5% of users if they want to opt-in to [analytics](https://aider.chat/docs/more/analytics.html).
+- Skip suggesting files that share names with files already in chat.
+- `/editor` returns and prefill the file content into the prompt, so you can use `/editor` to compose messages that start with `/commands`, etc.
+- Enhanced error handling for analytics.
+- Improved handling of UnknownEditFormat exceptions with helpful documentation links.
+- Bumped dependencies to pick up grep-ast 0.4.0 for Dart language support.
+- Aider wrote 81% of the code in this release.
+
+### Aider v0.64.1
+
+- Disable streaming for o1 on OpenRouter.
+
+### Aider v0.64.0
+
+- Added [`/editor` command](https://aider.chat/docs/usage/commands.html) to open system editor for writing prompts, by @thehunmonkgroup.
+- Full support for `gpt-4o-2024-11-20`.
+- Stream o1 models by default.
+- `/run` and suggested shell commands are less mysterious and now confirm that they "Added XX lines of output to the chat."
+- Ask 1% of users if they want to opt-in to [analytics](https://aider.chat/docs/more/analytics.html).
+- Added support for [optional multiline input tags](https://aider.chat/docs/usage/commands.html#entering-multi-line-chat-messages) with matching closing tags.
+- Improved [model settings configuration](https://aider.chat/docs/config/adv-model-settings.html#global-extra-params) with support for global `extra_params` for `litellm.completion()`.
+- Architect mode now asks to add files suggested by the LLM.
+- Fixed bug in fuzzy model name matching.
+- Added Timeout exception to handle API provider timeouts.
+- Added `--show-release-notes` to control release notes display on first run of new version.
+- Save empty dict to cache file on model metadata download failure, to delay retry.
+- Improved error handling and code formatting.
+- Aider wrote 74% of the code in this release.
+
+###  Aider v0.63.2
+
+- Fixed bug in fuzzy model name matching when litellm provider info is missing.
+- Modified model metadata file loading to allow override of resource file.
+- Allow recursive loading of dirs using `--read`.
+- Updated dependency versions to pick up litellm fix for ollama models.
+- Added exponential backoff retry when writing files to handle editor file locks.
+- Updated Qwen 2.5 Coder 32B model configuration.
+
+### Aider v0.63.1
+
+- Fixed bug in git ignored file handling.
+- Improved error handling for git operations.
+
+### Aider v0.63.0
+
+- Support for Qwen 2.5 Coder 32B.
+- `/web` command just adds the page to the chat, without triggering an LLM response.
+- Improved prompting for the user's preferred chat language.
+- Improved handling of LiteLLM exceptions.
+- Bugfix for double-counting tokens when reporting cache stats.
+- Bugfix for the LLM creating new files.
+- Other small bug fixes.
+- Aider wrote 55% of the code in this release.
+
+### Aider v0.62.0
+
+- Full support for Claude 3.5 Haiku
+  - Scored 75% on [aider's code editing leaderboard](https://aider.chat/docs/leaderboards/).
+  - Almost as good as Sonnet at much lower cost.
+  - Launch with `--haiku` to use it.
+- Easily apply file edits from ChatGPT, Claude or other web apps
+  - Chat with ChatGPT or Claude via their web app. 
+  - Give it your source files and ask for the changes you want.
+  - Use the web app's "copy response" button to copy the entire reply from the LLM.
+  - Run `aider --apply-clipboard-edits file-to-edit.js`.
+  - Aider will edit your file with the LLM's changes.
+- Bugfix for creating new files.
+- Aider wrote 84% of the code in this release.  
+
+### Aider v0.61.0
+
 - Load and save aider slash-commands to files:
   - `/save <fname>` command will make a file of `/add` and `/read-only` commands that recreate the current file context in the chat.
   - `/load <fname>` will replay the commands in the file.

aider/__init__.py

@@ -1,6 +1,6 @@
 try:
     from aider.__version__ import __version__
 except Exception:
-    __version__ = "0.61.1.dev"
+    __version__ = "0.65.1.dev"
 
 __all__ = [__version__]

aider/analytics.py

@@ -5,7 +5,7 @@ import time
 import uuid
 from pathlib import Path
 
-from mixpanel import Mixpanel
+from mixpanel import Mixpanel, MixpanelException
 from posthog import Posthog
 
 from aider import __version__
@@ -62,8 +62,47 @@ class Analytics:
             self.permanently_disable = True
             self.save_data()
 
-    def need_to_ask(self):
-        return not self.asked_opt_in and not self.permanently_disable
+    def need_to_ask(self, args_analytics):
+        if args_analytics is False:
+            return False
+
+        could_ask = not self.asked_opt_in and not self.permanently_disable
+        if not could_ask:
+            return False
+
+        if args_analytics is True:
+            return True
+
+        assert args_analytics is None, args_analytics
+
+        if not self.user_id:
+            return False
+
+        PERCENT = 2.5
+        return self.is_uuid_in_percentage(self.user_id, PERCENT)
+
+    def is_uuid_in_percentage(self, uuid_str, percent):
+        """Check if a UUID string falls within the first X percent of the UUID space.
+
+        Args:
+            uuid_str: UUID string to test
+            percent: Percentage threshold (0-100)
+
+        Returns:
+            bool: True if UUID falls within the first X percent
+        """
+        if not (0 <= percent <= 100):
+            raise ValueError("Percentage must be between 0 and 100")
+
+        if not uuid_str:
+            return False
+
+        # Convert percentage to hex threshold (1% = "04...", 10% = "1a...", etc)
+        # Using first 6 hex digits
+        if percent == 0:
+            return False
+        threshold = format(int(0xFFFFFF * percent / 100), "06x")
+        return uuid_str[:6] <= threshold
 
     def get_data_file_path(self):
         data_file = Path.home() / ".aider" / "analytics.json"
@@ -120,7 +159,7 @@ class Analytics:
         return None
 
     def event(self, event_name, main_model=None, **kwargs):
-        if not (self.mp or self.ph) and not self.logfile:
+        if not self.mp and not self.ph and not self.logfile:
             return
 
         properties = {}
@@ -143,7 +182,10 @@ class Analytics:
         properties["aider_version"] = __version__
 
         if self.mp:
-            self.mp.track(self.user_id, event_name, dict(properties))
+            try:
+                self.mp.track(self.user_id, event_name, dict(properties))
+            except MixpanelException:
+                self.mp = None  # Disable mixpanel on connection errors
 
         if self.ph:
             self.ph.capture(self.user_id, event_name, dict(properties))

aider/args.py

@@ -66,6 +66,14 @@ def get_parser(default_config_files, git_root):
         const=sonnet_model,
         help=f"Use {sonnet_model} model for the main chat",
     )
+    haiku_model = "claude-3-5-haiku-20241022"
+    group.add_argument(
+        "--haiku",
+        action="store_const",
+        dest="model",
+        const=haiku_model,
+        help=f"Use {haiku_model} model for the main chat",
+    )
     gpt_4_model = "gpt-4-0613"
     group.add_argument(
         "--4",
@@ -185,6 +193,12 @@ def get_parser(default_config_files, git_root):
         default=".aider.model.metadata.json",
         help="Specify a file with context window and costs for unknown models",
     )
+    group.add_argument(
+        "--alias",
+        action="append",
+        metavar="ALIAS:MODEL",
+        help="Add a model alias (can be used multiple times)",
+    )
     group.add_argument(
         "--verify-ssl",
         action=argparse.BooleanOptionalAction,
@@ -554,8 +568,8 @@ def get_parser(default_config_files, git_root):
     group.add_argument(
         "--analytics",
         action=argparse.BooleanOptionalAction,
-        default=False,
-        help="Enable/disable analytics for one session (default: False)",
+        default=None,
+        help="Enable/disable analytics for current session (default: random)",
     )
     group.add_argument(
         "--analytics-log",
@@ -612,6 +626,12 @@ def get_parser(default_config_files, git_root):
         help="Check for new aider versions on launch",
         default=True,
     )
+    group.add_argument(
+        "--show-release-notes",
+        action=argparse.BooleanOptionalAction,
+        help="Show release notes on first run of new version (default: None, ask user)",
+        default=None,
+    )
     group.add_argument(
         "--install-main-branch",
         action="store_true",
@@ -630,6 +650,12 @@ def get_parser(default_config_files, git_root):
         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",
@@ -718,6 +744,16 @@ def get_parser(default_config_files, git_root):
         default=True,
         help="Enable/disable fancy input with history and completion (default: True)",
     )
+    group.add_argument(
+        "--detect-urls",
+        action=argparse.BooleanOptionalAction,
+        default=True,
+        help="Enable/disable detection and offering to add URLs to chat (default: True)",
+    )
+    group.add_argument(
+        "--editor",
+        help="Specify which editor to use for the /editor command",
+    )
 
     ##########
     group = parser.add_argument_group("Voice Settings")

aider/coders/architect_coder.py

@@ -10,6 +10,9 @@ class ArchitectCoder(AskCoder):
     def reply_completed(self):
         content = self.partial_response_content
 
+        if not content or not content.strip():
+            return
+
         if not self.io.confirm_ask("Edit the files?"):
             return
 

aider/coders/architect_prompts.py

@@ -13,7 +13,7 @@ Just show the changes needed.
 
 DO NOT show the entire updated function/file/etc!
 
-Always reply in the same language as the change request.
+Always reply to the user in {language}.
 """
 
     example_messages = []

aider/coders/ask_prompts.py

@@ -6,7 +6,7 @@ from .base_prompts import CoderPrompts
 class AskPrompts(CoderPrompts):
     main_system = """Act as an expert code analyst.
 Answer questions about the supplied code.
-Always reply to the user in the same language they are using.
+Always reply to the user in {language}.
 """
 
     example_messages = []

aider/coders/base_coder.py

@@ -13,7 +13,6 @@ import sys
 import threading
 import time
 import traceback
-import webbrowser
 from collections import defaultdict
 from datetime import datetime
 from json.decoder import JSONDecodeError
@@ -23,6 +22,7 @@ from typing import List
 from aider import __version__, models, prompts, urls, utils
 from aider.analytics import Analytics
 from aider.commands import Commands
+from aider.exceptions import LiteLLMExceptions
 from aider.history import ChatSummary
 from aider.io import ConfirmGroup, InputOutput
 from aider.linter import Linter
@@ -30,13 +30,22 @@ from aider.llm import litellm
 from aider.repo import ANY_GIT_ERROR, GitRepo
 from aider.repomap import RepoMap
 from aider.run_cmd import run_cmd
-from aider.sendchat import RETRY_TIMEOUT, retry_exceptions, send_completion
+from aider.sendchat import RETRY_TIMEOUT, send_completion
 from aider.utils import format_content, format_messages, format_tokens, is_image_file
 
 from ..dump import dump  # noqa: F401
 from .chat_chunks import ChatChunks
 
 
+class UnknownEditFormat(ValueError):
+    def __init__(self, edit_format, valid_formats):
+        self.edit_format = edit_format
+        self.valid_formats = valid_formats
+        super().__init__(
+            f"Unknown edit format {edit_format}. Valid formats are: {', '.join(valid_formats)}"
+        )
+
+
 class MissingAPIKeyError(ValueError):
     pass
 
@@ -91,6 +100,7 @@ class Coder:
     cache_warming_thread = None
     num_cache_warming_pings = 0
     suggest_shell_commands = True
+    detect_urls = True
     ignore_mentions = None
     chat_language = None
 
@@ -156,7 +166,12 @@ class Coder:
                 res.original_kwargs = dict(kwargs)
                 return res
 
-        raise ValueError(f"Unknown edit format {edit_format}")
+        valid_formats = [
+            str(c.edit_format)
+            for c in coders.__all__
+            if hasattr(c, "edit_format") and c.edit_format is not None
+        ]
+        raise UnknownEditFormat(edit_format, valid_formats)
 
     def clone(self, **kwargs):
         new_coder = Coder.create(from_coder=self, **kwargs)
@@ -267,6 +282,7 @@ class Coder:
         num_cache_warming_pings=0,
         suggest_shell_commands=True,
         chat_language=None,
+        detect_urls=True,
     ):
         # Fill in a dummy Analytics if needed, but it is never .enable()'d
         self.analytics = analytics if analytics is not None else Analytics()
@@ -280,6 +296,7 @@ class Coder:
         self.ignore_mentions = set()
 
         self.suggest_shell_commands = suggest_shell_commands
+        self.detect_urls = detect_urls
 
         self.num_cache_warming_pings = num_cache_warming_pings
 
@@ -355,6 +372,9 @@ class Coder:
 
         for fname in fnames:
             fname = Path(fname)
+            if self.repo and self.repo.git_ignored_file(fname):
+                self.io.tool_warning(f"Skipping {fname} that matches gitignore spec.")
+
             if self.repo and self.repo.ignored_file(fname):
                 self.io.tool_warning(f"Skipping {fname} that matches aiderignore spec.")
                 continue
@@ -790,34 +810,9 @@ class Coder:
             self.num_reflections += 1
             message = self.reflected_message
 
-    def check_and_open_urls(self, exc: Exception) -> List[str]:
-        import openai
-
+    def check_and_open_urls(self, exc, friendly_msg=None):
         """Check exception for URLs, offer to open in a browser, with user-friendly error msgs."""
         text = str(exc)
-        friendly_msg = None
-
-        if isinstance(exc, (openai.APITimeoutError, openai.APIConnectionError)):
-            friendly_msg = (
-                "There is a problem connecting to the API provider. Please try again later or check"
-                " your model settings."
-            )
-        elif isinstance(exc, openai.RateLimitError):
-            friendly_msg = (
-                "The API provider's rate limits have been exceeded. Check with your provider or"
-                " wait awhile and retry."
-            )
-        elif isinstance(exc, openai.InternalServerError):
-            friendly_msg = (
-                "The API provider seems to be down or overloaded. Please try again later."
-            )
-        elif isinstance(exc, openai.BadRequestError):
-            friendly_msg = "The API provider refused the request as invalid?"
-        elif isinstance(exc, openai.AuthenticationError):
-            friendly_msg = (
-                "The API provider refused your authentication. Please check that you are using a"
-                " valid API key."
-            )
 
         if friendly_msg:
             self.io.tool_warning(text)
@@ -829,12 +824,14 @@ class Coder:
         urls = list(set(url_pattern.findall(text)))  # Use set to remove duplicates
         for url in urls:
             url = url.rstrip(".',\"")
-            if self.io.confirm_ask("Open URL for more info about this error?", subject=url):
-                webbrowser.open(url)
+            self.io.offer_url(url)
         return urls
 
     def check_for_urls(self, inp: str) -> List[str]:
         """Check input for URLs and offer to add them to the chat."""
+        if not self.detect_urls:
+            return []
+
         url_pattern = re.compile(r"(https?://[^\s/$.?#].[^\s]*[^\s,.])")
         urls = list(set(url_pattern.findall(inp)))  # Use set to remove duplicates
         added_urls = []
@@ -846,7 +843,7 @@ class Coder:
                     "Add URL to the chat?", subject=url, group=group, allow_never=True
                 ):
                     inp += "\n\n"
-                    inp += self.commands.cmd_web(url)
+                    inp += self.commands.cmd_web(url, return_content=True)
                     added_urls.append(url)
                 else:
                     self.rejected_urls.add(url)
@@ -982,12 +979,18 @@ class Coder:
                 platform=platform_text
             )
 
+        if self.chat_language:
+            language = self.chat_language
+        else:
+            language = "the same language they are using"
+
         prompt = prompt.format(
             fence=self.fence,
             lazy_prompt=lazy_prompt,
             platform=platform_text,
             shell_cmd_prompt=shell_cmd_prompt,
             shell_cmd_reminder=shell_cmd_reminder,
+            language=language,
         )
         return prompt
 
@@ -1076,7 +1079,7 @@ class Coder:
         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.
         if (
-            max_input_tokens is None
+            not max_input_tokens
             or total_tokens < max_input_tokens
             and self.gpt_prompts.system_reminder
         ):
@@ -1154,8 +1157,6 @@ class Coder:
         return chunks
 
     def send_message(self, inp):
-        import openai  # for error codes below
-
         self.cur_messages += [
             dict(role="user", content=inp),
         ]
@@ -1175,6 +1176,8 @@ class Coder:
 
         retry_delay = 0.125
 
+        litellm_ex = LiteLLMExceptions()
+
         self.usage_report = None
         exhausted = False
         interrupted = False
@@ -1183,30 +1186,37 @@ class Coder:
                 try:
                     yield from self.send(messages, functions=self.functions)
                     break
-                except retry_exceptions() as err:
-                    # Print the error and its base classes
-                    # for cls in err.__class__.__mro__: dump(cls.__name__)
+                except litellm_ex.exceptions_tuple() as err:
+                    ex_info = litellm_ex.get_ex_info(err)
 
-                    retry_delay *= 2
-                    if retry_delay > RETRY_TIMEOUT:
-                        self.mdstream = None
-                        self.check_and_open_urls(err)
+                    if ex_info.name == "ContextWindowExceededError":
+                        exhausted = True
                         break
+
+                    should_retry = ex_info.retry
+                    if should_retry:
+                        retry_delay *= 2
+                        if retry_delay > RETRY_TIMEOUT:
+                            should_retry = False
+
+                    if not should_retry:
+                        self.mdstream = None
+                        self.check_and_open_urls(err, ex_info.description)
+                        break
+
                     err_msg = str(err)
-                    self.io.tool_error(err_msg)
+                    if ex_info.description:
+                        self.io.tool_warning(err_msg)
+                        self.io.tool_error(ex_info.description)
+                    else:
+                        self.io.tool_error(err_msg)
+
                     self.io.tool_output(f"Retrying in {retry_delay:.1f} seconds...")
                     time.sleep(retry_delay)
                     continue
                 except KeyboardInterrupt:
                     interrupted = True
                     break
-                except litellm.ContextWindowExceededError:
-                    # The input is overflowing the context window!
-                    exhausted = True
-                    break
-                except litellm.exceptions.BadRequestError as br_err:
-                    self.io.tool_error(f"BadRequestError: {br_err}")
-                    return
                 except FinishReasonLength:
                     # We hit the output limit!
                     if not self.main_model.info.get("supports_assistant_prefill"):
@@ -1221,12 +1231,8 @@ class Coder:
                         messages.append(
                             dict(role="assistant", content=self.multi_response_content, prefix=True)
                         )
-                except (openai.APIError, openai.APIStatusError) as err:
-                    # for cls in err.__class__.__mro__: dump(cls.__name__)
-                    self.mdstream = None
-                    self.check_and_open_urls(err)
-                    break
                 except Exception as err:
+                    self.mdstream = None
                     lines = traceback.format_exception(type(err), err, err.__traceback__)
                     self.io.tool_warning("".join(lines))
                     self.io.tool_error(str(err))
@@ -1259,10 +1265,19 @@ class Coder:
         else:
             content = ""
 
-        try:
-            self.reply_completed()
-        except KeyboardInterrupt:
-            interrupted = True
+        if not interrupted:
+            add_rel_files_message = self.check_for_file_mentions(content)
+            if add_rel_files_message:
+                if self.reflected_message:
+                    self.reflected_message += "\n\n" + add_rel_files_message
+                else:
+                    self.reflected_message = add_rel_files_message
+                return
+
+            try:
+                self.reply_completed()
+            except KeyboardInterrupt:
+                interrupted = True
 
         if interrupted:
             content += "\n^C KeyboardInterrupt"
@@ -1313,13 +1328,6 @@ class Coder:
                     self.update_cur_messages()
                     return
 
-        add_rel_files_message = self.check_for_file_mentions(content)
-        if add_rel_files_message:
-            if self.reflected_message:
-                self.reflected_message += "\n\n" + add_rel_files_message
-            else:
-                self.reflected_message = add_rel_files_message
-
     def reply_completed(self):
         pass
 
@@ -1374,11 +1382,9 @@ class Coder:
             res.append("- Use /clear to clear the chat history.")
             res.append("- Break your code into smaller source files.")
 
-        res.append("")
-        res.append(f"For more info: {urls.token_limits}")
-
         res = "".join([line + "\n" for line in res])
         self.io.tool_error(res)
+        self.io.offer_url(urls.token_limits)
 
     def lint_edited(self, fnames):
         res = ""
@@ -1419,9 +1425,18 @@ class Coder:
 
         addable_rel_fnames = self.get_addable_relative_files()
 
+        # Get basenames of files already in chat or read-only
+        existing_basenames = {os.path.basename(f) for f in self.get_inchat_relative_files()} | {
+            os.path.basename(self.get_rel_fname(f)) for f in self.abs_read_only_fnames
+        }
+
         mentioned_rel_fnames = set()
         fname_to_rel_fnames = {}
         for rel_fname in addable_rel_fnames:
+            # Skip files that share a basename with files already in chat
+            if os.path.basename(rel_fname) in existing_basenames:
+                continue
+
             normalized_rel_fname = rel_fname.replace("\\", "/")
             normalized_words = set(word.replace("\\", "/") for word in words)
             if normalized_rel_fname in normalized_words:
@@ -1622,7 +1637,6 @@ class Coder:
                 completion.usage, "cache_creation_input_tokens"
             ):
                 self.message_tokens_sent += prompt_tokens
-                self.message_tokens_sent += cache_hit_tokens
                 self.message_tokens_sent += cache_write_tokens
             else:
                 self.message_tokens_sent += prompt_tokens
@@ -1799,6 +1813,10 @@ class Coder:
             self.check_for_dirty_commit(path)
             return True
 
+        if self.repo and self.repo.git_ignored_file(path):
+            self.io.tool_warning(f"Skipping edits to {path} that matches gitignore spec.")
+            return
+
         if not Path(full_path).exists():
             if not self.io.confirm_ask("Create new file?", subject=path):
                 self.io.tool_output(f"Skipping edits to {path}")
@@ -2072,9 +2090,10 @@ class Coder:
             if output:
                 accumulated_output += f"Output from {command}\n{output}\n"
 
-        if accumulated_output.strip() and not self.io.confirm_ask(
+        if accumulated_output.strip() and self.io.confirm_ask(
             "Add command output to the chat?", allow_never=True
         ):
-            accumulated_output = ""
-
-        return accumulated_output
+            num_lines = len(accumulated_output.strip().splitlines())
+            line_plural = "line" if num_lines == 1 else "lines"
+            self.io.tool_output(f"Added {num_lines} {line_plural} of output to the chat.")
+            return accumulated_output

aider/coders/editblock_coder.py

@@ -46,9 +46,16 @@ class EditBlockCoder(Coder):
         for edit in edits:
             path, original, updated = edit
             full_path = self.abs_root_path(path)
-            content = self.io.read_text(full_path)
-            new_content = do_replace(full_path, content, original, updated, self.fence)
-            if not new_content:
+            new_content = None
+
+            if Path(full_path).exists():
+                content = self.io.read_text(full_path)
+                new_content = do_replace(full_path, content, original, updated, self.fence)
+
+            # If the edit failed, and
+            # this is not a "create a new file" with an empty original...
+            # https://github.com/Aider-AI/aider/issues/2258
+            if not new_content and original.strip():
                 # try patching any of the other files in the chat
                 for full_path in self.abs_fnames:
                     content = self.io.read_text(full_path)

aider/coders/editblock_prompts.py

@@ -11,7 +11,7 @@ Respect and use existing conventions, libraries, etc that are already present in
 Take requests for changes to the supplied code.
 If the request is ambiguous, ask questions.
 
-Always reply to the user in the same language they are using.
+Always reply to the user in {language}.
 
 Once you understand the request you MUST:
 

aider/coders/udiff_prompts.py

@@ -12,7 +12,7 @@ Respect and use existing conventions, libraries, etc that are already present in
 Take requests for changes to the supplied code.
 If the request is ambiguous, ask questions.
 
-Always reply to the user in the same language they are using.
+Always reply to the user in {language}.
 
 For each file that needs to be changed, write out the changes similar to a unified diff like `diff -U0` would produce.
 """

aider/coders/wholefile_prompts.py

@@ -8,7 +8,7 @@ class WholeFilePrompts(CoderPrompts):
 Take requests for changes to the supplied code.
 If the request is ambiguous, ask questions.
 
-Always reply to the user in the same language they are using.
+Always reply to the user in {language}.
 
 {lazy_prompt}
 Once you understand the request you MUST:

aider/commands.py

@@ -14,6 +14,7 @@ from prompt_toolkit.completion import Completion, PathCompleter
 from prompt_toolkit.document import Document
 
 from aider import models, prompts, voice
+from aider.editor import pipe_editor
 from aider.format_settings import format_settings
 from aider.help import Help, install_help_extra
 from aider.llm import litellm
@@ -45,7 +46,15 @@ class Commands:
         )
 
     def __init__(
-        self, io, coder, voice_language=None, verify_ssl=True, args=None, parser=None, verbose=False
+        self,
+        io,
+        coder,
+        voice_language=None,
+        verify_ssl=True,
+        args=None,
+        parser=None,
+        verbose=False,
+        editor=None,
     ):
         self.io = io
         self.coder = coder
@@ -60,6 +69,7 @@ class Commands:
         self.voice_language = voice_language
 
         self.help = None
+        self.editor = editor
 
     def cmd_model(self, args):
         "Switch to a new LLM"
@@ -139,7 +149,7 @@ class Commands:
         else:
             self.io.tool_output("Please provide a partial model name to search for.")
 
-    def cmd_web(self, args):
+    def cmd_web(self, args, return_content=False):
         "Scrape a webpage, convert to markdown and send in a message"
 
         url = args.strip()
@@ -158,11 +168,16 @@ class Commands:
             )
 
         content = self.scraper.scrape(url) or ""
-        content = f"{url}:\n\n" + content
+        content = f"Here is the content of {url}:\n\n" + content
+        if return_content:
+            return content
 
-        self.io.tool_output("... done.")
+        self.io.tool_output("... added to chat.")
 
-        return content
+        self.coder.cur_messages += [
+            dict(role="user", content=content),
+            dict(role="assistant", content="Ok."),
+        ]
 
     def is_command(self, inp):
         return inp[0] in "/!"
@@ -738,6 +753,10 @@ class Commands:
                 )
                 continue
 
+            if self.coder.repo and self.coder.repo.git_ignored_file(matched_file):
+                self.io.tool_error(f"Can't add {matched_file} which is in gitignore")
+                continue
+
             if abs_file_path in self.coder.abs_fnames:
                 self.io.tool_error(f"{matched_file} is already in the chat as an editable file")
                 continue
@@ -859,7 +878,6 @@ class Commands:
         exit_status, combined_output = run_cmd(
             args, verbose=self.verbose, error_print=self.io.tool_error
         )
-        instructions = None
 
         if combined_output is None:
             return
@@ -867,36 +885,22 @@ class Commands:
         if add_on_nonzero_exit:
             add = exit_status != 0
         else:
-            self.io.tool_output()
-            response = self.io.prompt_ask(
-                "Add the output to the chat?\n(Y)es/(n)o/message with instructions:",
-            ).strip()
-            self.io.tool_output()
-
-            if response.lower() in ["yes", "y"]:
-                add = True
-            elif response.lower() in ["no", "n"]:
-                add = False
-            else:
-                add = True
-                instructions = response
-                if response.strip():
-                    self.io.user_input(response, log_only=True)
-                    self.io.add_to_input_history(response)
+            add = self.io.confirm_ask("Add command output to the chat?")
 
         if add:
-            for line in combined_output.splitlines():
-                self.io.tool_output(line, log_only=True)
+            num_lines = len(combined_output.strip().splitlines())
+            line_plural = "line" if num_lines == 1 else "lines"
+            self.io.tool_output(f"Added {num_lines} {line_plural} of output to the chat.")
 
             msg = prompts.run_output.format(
                 command=args,
                 output=combined_output,
             )
 
-            if instructions:
-                msg = instructions + "\n\n" + msg
-
-            return msg
+            self.coder.cur_messages += [
+                dict(role="user", content=msg),
+                dict(role="assistant", content="Ok."),
+            ]
 
     def cmd_exit(self, args):
         "Exit the application"
@@ -1357,6 +1361,13 @@ class Commands:
 
         report_github_issue(issue_text, title=title, confirm=False)
 
+    def cmd_editor(self, initial_content=""):
+        "Open an editor to write a prompt"
+
+        user_input = pipe_editor(initial_content, suffix="md", editor=self.editor)
+        if user_input.strip():
+            self.io.set_placeholder(user_input.rstrip())
+
 
 def expand_subdir(file_path):
     if file_path.is_file():

aider/diffs.py

@@ -50,7 +50,6 @@ def diff_partial_update(lines_orig, lines_updated, final=False, fname=None):
     # dump(lines_orig)
     # dump(lines_updated)
 
-    assert_newlines(lines_orig)
     assert_newlines(lines_orig)
 
     num_orig_lines = len(lines_orig)

aider/editor.py

@@ -0,0 +1,146 @@
+"""
+Editor module for handling system text editor interactions.
+
+This module provides functionality to:
+- Discover and launch the system's configured text editor
+- Create and manage temporary files for editing
+- Handle editor preferences from environment variables
+- Support cross-platform editor operations
+"""
+
+import os
+import platform
+import shlex
+import subprocess
+import tempfile
+
+from rich.console import Console
+
+DEFAULT_EDITOR_NIX = "vi"
+DEFAULT_EDITOR_OS_X = "vim"
+DEFAULT_EDITOR_WINDOWS = "notepad"
+
+console = Console()
+
+
+def print_status_message(success, message, style=None):
+    """
+    Print a status message with appropriate styling.
+
+    :param success: Whether the operation was successful
+    :param message: The message to display
+    :param style: Optional style override. If None, uses green for success and red for failure
+    """
+    if style is None:
+        style = "bold green" if success else "bold red"
+    console.print(message, style=style)
+    print("")
+
+
+def write_temp_file(
+    input_data="",
+    suffix=None,
+    prefix=None,
+    dir=None,
+):
+    """
+    Create a temporary file with the given input data.
+
+    :param input_data: Content to write to the temporary file
+    :param suffix: Optional file extension (without the dot)
+    :param prefix: Optional prefix for the temporary filename
+    :param dir: Optional directory to create the file in
+    :return: Path to the created temporary file
+    :raises: OSError if file creation or writing fails
+    """
+    kwargs = {"prefix": prefix, "dir": dir}
+    if suffix:
+        kwargs["suffix"] = f".{suffix}"
+    fd, filepath = tempfile.mkstemp(**kwargs)
+    try:
+        with os.fdopen(fd, "w") as f:
+            f.write(input_data)
+    except Exception:
+        os.close(fd)
+        raise
+    return filepath
+
+
+def get_environment_editor(default=None):
+    """
+    Fetches the preferred editor from the environment variables.
+
+    This function checks the following environment variables in order to
+    determine the user's preferred editor:
+
+     - VISUAL
+     - EDITOR
+
+    :param default: The default editor to return if no environment variable is set.
+    :type default: str or None
+    :return: The preferred editor as specified by environment variables or the default value.
+    :rtype: str or None
+    """
+    editor = os.environ.get("VISUAL", os.environ.get("EDITOR", default))
+    return editor
+
+
+def discover_editor(editor_override=None):
+    """
+    Discovers and returns the appropriate editor command as a list of arguments.
+
+    Handles cases where the editor command includes arguments, including quoted arguments
+    with spaces (e.g. 'vim -c "set noswapfile"').
+
+    :return: A list of command parts ready for subprocess execution
+    :rtype: list[str]
+    """
+    system = platform.system()
+    if system == "Windows":
+        default_editor = DEFAULT_EDITOR_WINDOWS
+    elif system == "Darwin":
+        default_editor = DEFAULT_EDITOR_OS_X
+    else:
+        default_editor = DEFAULT_EDITOR_NIX
+    if editor_override:
+        editor = editor_override
+    else:
+        editor = get_environment_editor(default_editor)
+    try:
+        return shlex.split(editor)
+    except ValueError as e:
+        raise RuntimeError(f"Invalid editor command format '{editor}': {e}")
+
+
+def pipe_editor(input_data="", suffix=None, editor=None):
+    """
+    Opens the system editor with optional input data and returns the edited content.
+
+    This function creates a temporary file with the provided input data, opens it in
+    the system editor, waits for the user to make changes and close the editor, then
+    reads and returns the modified content. The temporary file is deleted afterwards.
+
+    :param input_data: Initial content to populate the editor with
+    :type input_data: str
+    :param suffix: Optional file extension for the temporary file (e.g. '.txt', '.md')
+    :type suffix: str or None
+    :return: The edited content after the editor is closed
+    :rtype: str
+    """
+    filepath = write_temp_file(input_data, suffix)
+    command_parts = discover_editor(editor)
+    command_parts.append(filepath)
+    subprocess.call(command_parts)
+    with open(filepath, "r") as f:
+        output_data = f.read()
+    try:
+        os.remove(filepath)
+    except PermissionError:
+        print_status_message(
+            False,
+            (
+                f"WARNING: Unable to delete temporary file {filepath!r}. You may need to delete it"
+                " manually."
+            ),
+        )
+    return output_data

aider/exceptions.py

@@ -0,0 +1,81 @@
+from dataclasses import dataclass
+
+
+@dataclass
+class ExInfo:
+    name: str
+    retry: bool
+    description: str
+
+
+EXCEPTIONS = [
+    ExInfo("APIConnectionError", True, None),
+    ExInfo("APIError", True, None),
+    ExInfo("APIResponseValidationError", True, None),
+    ExInfo(
+        "AuthenticationError",
+        False,
+        "The API provider is not able to authenticate you. Check your API key.",
+    ),
+    ExInfo("AzureOpenAIError", True, None),
+    ExInfo("BadRequestError", False, None),
+    ExInfo("BudgetExceededError", True, None),
+    ExInfo(
+        "ContentPolicyViolationError",
+        True,
+        "The API provider has refused the request due to a safety policy about the content.",
+    ),
+    ExInfo("ContextWindowExceededError", False, None),  # special case handled in base_coder
+    ExInfo("InternalServerError", True, "The API provider's servers are down or overloaded."),
+    ExInfo("InvalidRequestError", True, None),
+    ExInfo("JSONSchemaValidationError", True, None),
+    ExInfo("NotFoundError", False, None),
+    ExInfo("OpenAIError", True, None),
+    ExInfo(
+        "RateLimitError",
+        True,
+        "The API provider has rate limited you. Try again later or check your quotas.",
+    ),
+    ExInfo("RouterRateLimitError", True, None),
+    ExInfo("ServiceUnavailableError", True, "The API provider's servers are down or overloaded."),
+    ExInfo("UnprocessableEntityError", True, None),
+    ExInfo("UnsupportedParamsError", True, None),
+    ExInfo(
+        "Timeout",
+        True,
+        "The API provider timed out without returning a response. They may be down or overloaded.",
+    ),
+]
+
+
+class LiteLLMExceptions:
+    exceptions = dict()
+
+    def __init__(self):
+        self._load()
+
+    def _load(self, strict=False):
+        import litellm
+
+        for var in dir(litellm):
+            if not var.endswith("Error"):
+                continue
+
+            ex_info = None
+            for exi in EXCEPTIONS:
+                if var == exi.name:
+                    ex_info = exi
+                    break
+
+            if strict and not ex_info:
+                raise ValueError(f"{var} is in litellm but not in aider's exceptions list")
+
+            ex = getattr(litellm, var)
+            self.exceptions[ex] = ex_info
+
+    def exceptions_tuple(self):
+        return tuple(self.exceptions)
+
+    def get_ex_info(self, ex):
+        """Return the ExInfo for a given exception instance"""
+        return self.exceptions.get(ex.__class__, ExInfo(None, None, None))

aider/help_pats.py

@@ -7,4 +7,5 @@ exclude_website_pats = [
     "docs/unified-diffs.md",
     "docs/leaderboards/index.md",
     "assets/**",
+    "**/.DS_Store",
 ]

aider/io.py

@@ -1,5 +1,7 @@
 import base64
 import os
+import time
+import webbrowser
 from collections import defaultdict
 from dataclasses import dataclass
 from datetime import datetime
@@ -196,6 +198,7 @@ class InputOutput:
         editingmode=EditingMode.EMACS,
         fancy_input=True,
     ):
+        self.placeholder = None
         self.never_prompts = set()
         self.editingmode = editingmode
         no_color = os.environ.get("NO_COLOR")
@@ -332,14 +335,36 @@ class InputOutput:
             self.tool_error("Use --encoding to set the unicode encoding.")
             return
 
-    def write_text(self, filename, content):
+    def write_text(self, filename, content, max_retries=5, initial_delay=0.1):
+        """
+        Writes content to a file, retrying with progressive backoff if the file is locked.
+
+        :param filename: Path to the file to write.
+        :param content: Content to write to the file.
+        :param max_retries: Maximum number of retries if a file lock is encountered.
+        :param initial_delay: Initial delay (in seconds) before the first retry.
+        """
         if self.dry_run:
             return
-        try:
-            with open(str(filename), "w", encoding=self.encoding) as f:
-                f.write(content)
-        except OSError as err:
-            self.tool_error(f"Unable to write file {filename}: {err}")
+
+        delay = initial_delay
+        for attempt in range(max_retries):
+            try:
+                with open(str(filename), "w", encoding=self.encoding) as f:
+                    f.write(content)
+                return  # Successfully wrote the file
+            except PermissionError as err:
+                if attempt < max_retries - 1:
+                    time.sleep(delay)
+                    delay *= 2  # Exponential backoff
+                else:
+                    self.tool_error(
+                        f"Unable to write file {filename} after {max_retries} attempts: {err}"
+                    )
+                    raise
+            except OSError as err:
+                self.tool_error(f"Unable to write file {filename}: {err}")
+                raise
 
     def rule(self):
         if self.pretty:
@@ -403,8 +428,13 @@ class InputOutput:
 
             try:
                 if self.prompt_session:
+                    # Use placeholder if set, then clear it
+                    default = self.placeholder or ""
+                    self.placeholder = None
+
                     line = self.prompt_session.prompt(
                         show,
+                        default=default,
                         completer=completer_instance,
                         reserve_space_for_menu=4,
                         complete_style=CompleteStyle.MULTI_COLUMN,
@@ -417,13 +447,38 @@ class InputOutput:
                 self.tool_error(str(err))
                 return ""
 
-            if line and line[0] == "{" and not multiline_input:
-                multiline_input = True
-                inp += line[1:] + "\n"
+            if line.strip("\r\n") and not multiline_input:
+                stripped = line.strip("\r\n")
+                if stripped == "{":
+                    multiline_input = True
+                    multiline_tag = None
+                    inp += ""
+                elif stripped[0] == "{":
+                    # Extract tag if it exists (only alphanumeric chars)
+                    tag = "".join(c for c in stripped[1:] if c.isalnum())
+                    if stripped == "{" + tag:
+                        multiline_input = True
+                        multiline_tag = tag
+                        inp += ""
+                    else:
+                        inp = line
+                        break
+                else:
+                    inp = line
+                    break
                 continue
-            elif line and line[-1] == "}" and multiline_input:
-                inp += line[:-1] + "\n"
-                break
+            elif multiline_input and line.strip():
+                if multiline_tag:
+                    # Check if line is exactly "tag}"
+                    if line.strip("\r\n") == f"{multiline_tag}}}":
+                        break
+                    else:
+                        inp += line + "\n"
+                # Check if line is exactly "}"
+                elif line.strip("\r\n") == "}":
+                    break
+                else:
+                    inp += line + "\n"
             elif multiline_input:
                 inp += line + "\n"
             else:
@@ -439,8 +494,8 @@ class InputOutput:
             return
         FileHistory(self.input_history_file).append_string(inp)
         # Also add to the in-memory history if it exists
-        if hasattr(self, "session") and hasattr(self.session, "history"):
-            self.session.history.append_string(inp)
+        if self.prompt_session and self.prompt_session.history:
+            self.prompt_session.history.append_string(inp)
 
     def get_input_history(self):
         if not self.input_history_file:
@@ -457,14 +512,17 @@ class InputOutput:
             log_file.write(f"{role.upper()} {timestamp}\n")
             log_file.write(content + "\n")
 
+    def display_user_input(self, inp):
+        if self.pretty and self.user_input_color:
+            style = dict(style=self.user_input_color)
+        else:
+            style = dict()
+
+        self.console.print(Text(inp), **style)
+
     def user_input(self, inp, log_only=True):
         if not log_only:
-            if self.pretty and self.user_input_color:
-                style = dict(style=self.user_input_color)
-            else:
-                style = dict()
-
-            self.console.print(Text(inp), **style)
+            self.display_user_input(inp)
 
         prefix = "####"
         if inp:
@@ -484,6 +542,15 @@ class InputOutput:
         hist = "\n" + content.strip() + "\n\n"
         self.append_chat_history(hist)
 
+    def offer_url(self, url, prompt="Open URL for more info?", allow_never=True):
+        """Offer to open a URL in the browser, returns True if opened."""
+        if url in self.never_prompts:
+            return False
+        if self.confirm_ask(prompt, subject=url, allow_never=allow_never):
+            webbrowser.open(url)
+            return True
+        return False
+
     def confirm_ask(
         self,
         question,
@@ -678,6 +745,10 @@ class InputOutput:
 
         self.console.print(show_resp)
 
+    def set_placeholder(self, placeholder):
+        """Set a one-time placeholder text for the next input prompt."""
+        self.placeholder = placeholder
+
     def print(self, message=""):
         print(message)
 
@@ -722,13 +793,23 @@ class InputOutput:
         editable_files = [f for f in sorted(rel_fnames) if f not in rel_read_only_fnames]
 
         if read_only_files:
-            console.print("Read only files:", style="bold")
-            console.print(Columns(read_only_files))
+            files_with_label = ["Readonly:"] + read_only_files
+            read_only_output = StringIO()
+            Console(file=read_only_output, force_terminal=False).print(Columns(files_with_label))
+            read_only_lines = read_only_output.getvalue().splitlines()
+            console.print(Columns(files_with_label))
+
         if editable_files:
+            files_with_label = editable_files
             if read_only_files:
-                console.print()
-                console.print("Editable files:", style="bold")
-            console.print(Columns(editable_files))
+                files_with_label = ["Editable:"] + editable_files
+                editable_output = StringIO()
+                Console(file=editable_output, force_terminal=False).print(Columns(files_with_label))
+                editable_lines = editable_output.getvalue().splitlines()
+
+                if len(read_only_lines) > 1 or len(editable_lines) > 1:
+                    console.print()
+            console.print(Columns(files_with_label))
 
         return output.getvalue()
 

aider/main.py

@@ -6,6 +6,7 @@ import sys
 import threading
 import traceback
 import webbrowser
+from dataclasses import fields
 from pathlib import Path
 
 import git
@@ -17,11 +18,13 @@ from aider import __version__, models, urls, utils
 from aider.analytics import Analytics
 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.format_settings import format_settings, scrub_sensitive_info
 from aider.history import ChatSummary
 from aider.io import InputOutput
 from aider.llm import litellm  # noqa: F401; properly init litellm on launch
+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
@@ -88,15 +91,25 @@ def make_new_repo(git_root, io):
 
 
 def setup_git(git_root, io):
+    try:
+        cwd = Path.cwd()
+    except OSError:
+        cwd = None
+
     repo = None
 
     if git_root:
-        repo = git.Repo(git_root)
-    elif Path.cwd() == Path.home():
+        try:
+            repo = git.Repo(git_root)
+        except ANY_GIT_ERROR:
+            pass
+    elif cwd == Path.home():
         io.tool_warning("You should probably run aider in a directory, not your home dir.")
         return
-    elif io.confirm_ask("No git repo found, create one to track aider's changes (recommended)?"):
-        git_root = str(Path.cwd().resolve())
+    elif cwd and io.confirm_ask(
+        "No git repo found, create one to track aider's changes (recommended)?"
+    ):
+        git_root = str(cwd.resolve())
         repo = make_new_repo(git_root, io)
 
     if not repo:
@@ -323,14 +336,16 @@ def load_dotenv_files(git_root, dotenv_fname, encoding="utf-8"):
 
 
 def register_litellm_models(git_root, model_metadata_fname, io, verbose=False):
-    model_metatdata_files = generate_search_path_list(
-        ".aider.model.metadata.json", git_root, model_metadata_fname
-    )
+    model_metatdata_files = []
 
     # Add the resource file path
     resource_metadata = importlib_resources.files("aider.resources").joinpath("model-metadata.json")
     model_metatdata_files.append(str(resource_metadata))
 
+    model_metatdata_files += generate_search_path_list(
+        ".aider.model.metadata.json", git_root, model_metadata_fname
+    )
+
     try:
         model_metadata_files_loaded = models.register_litellm_models(model_metatdata_files)
         if len(model_metadata_files_loaded) > 0 and verbose:
@@ -367,8 +382,7 @@ def sanity_check_repo(repo, io):
         io.tool_error("Aider only works with git repos with version number 1 or 2.")
         io.tool_output("You may be able to convert your repo: git update-index --index-version=2")
         io.tool_output("Or run aider --no-git to proceed without using git.")
-        if io.confirm_ask("Open documentation url for more info?", subject=urls.git_index_version):
-            webbrowser.open(urls.git_index_version)
+        io.offer_url(urls.git_index_version, "Open documentation url for more info?")
         return False
 
     io.tool_error("Unable to read git repository, it may be corrupt?")
@@ -432,7 +446,6 @@ def main(argv=None, input=None, output=None, force_git_root=None, return_coder=F
     if args.analytics_disable:
         analytics = Analytics(permanently_disable=True)
         print("Analytics have been permanently disabled.")
-        return
 
     if not args.verify_ssl:
         import httpx
@@ -496,8 +509,8 @@ def main(argv=None, input=None, output=None, force_git_root=None, return_coder=F
         io.tool_warning("Terminal does not support pretty output (UnicodeDecodeError)")
 
     analytics = Analytics(logfile=args.analytics_log, permanently_disable=args.analytics_disable)
-    if args.analytics:
-        if analytics.need_to_ask():
+    if args.analytics is not False:
+        if analytics.need_to_ask(args.analytics):
             io.tool_output(
                 "Aider respects your privacy and never collects your code, chat messages, keys or"
                 " personal info."
@@ -533,7 +546,14 @@ def main(argv=None, input=None, output=None, force_git_root=None, return_coder=F
 
     all_files = args.files + (args.file or [])
     fnames = [str(Path(fn).resolve()) for fn in all_files]
-    read_only_fnames = [str(Path(fn).resolve()) for fn in (args.read or [])]
+    read_only_fnames = []
+    for fn in args.read or []:
+        path = Path(fn).resolve()
+        if path.is_dir():
+            read_only_fnames.extend(str(f) for f in path.rglob("*") if f.is_file())
+        else:
+            read_only_fnames.append(str(path))
+
     if len(all_files) > 1:
         good = True
         for fname in all_files:
@@ -596,7 +616,8 @@ def main(argv=None, input=None, output=None, force_git_root=None, return_coder=F
     cmd_line = scrub_sensitive_info(args, cmd_line)
     io.tool_output(cmd_line, log_only=True)
 
-    check_and_load_imports(io, verbose=args.verbose)
+    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
@@ -615,6 +636,18 @@ def main(argv=None, input=None, output=None, force_git_root=None, return_coder=F
     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)
 
+    # Process any command line aliases
+    if args.alias:
+        for alias_def in args.alias:
+            # Split on first colon only
+            parts = alias_def.split(":", 1)
+            if len(parts) != 2:
+                io.tool_error(f"Invalid alias format: {alias_def}")
+                io.tool_output("Format should be: alias:model-name")
+                return 1
+            alias, model = parts
+            models.MODEL_ALIASES[alias.strip()] = model.strip()
+
     if not args.model:
         args.model = "gpt-4o-2024-08-06"
         if os.environ.get("ANTHROPIC_API_KEY"):
@@ -628,9 +661,15 @@ def main(argv=None, input=None, output=None, force_git_root=None, return_coder=F
     )
 
     if args.verbose:
-        io.tool_output("Model info:")
+        io.tool_output("Model metadata:")
         io.tool_output(json.dumps(main_model.info, indent=4))
 
+        io.tool_output("Model settings:")
+        for attr in sorted(fields(ModelSettings), key=lambda x: x.name):
+            val = getattr(main_model, attr.name)
+            val = json.dumps(val, indent=4)
+            io.tool_output(f"{attr.name}: {val}")
+
     lint_cmds = parse_lint_cmds(args.lint_cmd, io)
     if lint_cmds is None:
         return 1
@@ -642,10 +681,7 @@ def main(argv=None, input=None, output=None, force_git_root=None, return_coder=F
             io.tool_output("You can skip this check with --no-show-model-warnings")
 
             try:
-                if io.confirm_ask(
-                    "Open documentation url for more info?", subject=urls.model_warnings
-                ):
-                    webbrowser.open(urls.model_warnings)
+                io.offer_url(urls.model_warnings, "Open documentation url for more info?")
                 io.tool_output()
             except KeyboardInterrupt:
                 return 1
@@ -674,7 +710,13 @@ def main(argv=None, input=None, output=None, force_git_root=None, return_coder=F
             return 1
 
     commands = Commands(
-        io, None, verify_ssl=args.verify_ssl, args=args, parser=parser, verbose=args.verbose
+        io,
+        None,
+        verify_ssl=args.verify_ssl,
+        args=args,
+        parser=parser,
+        verbose=args.verbose,
+        editor=args.editor,
     )
 
     summarizer = ChatSummary(
@@ -722,7 +764,12 @@ def main(argv=None, input=None, output=None, force_git_root=None, return_coder=F
             num_cache_warming_pings=args.cache_keepalive_pings,
             suggest_shell_commands=args.suggest_shell_commands,
             chat_language=args.chat_language,
+            detect_urls=args.detect_urls,
         )
+    except UnknownEditFormat as err:
+        io.tool_error(str(err))
+        io.offer_url(urls.edit_formats, "Open documentation about edit formats?")
+        return 1
     except ValueError as err:
         io.tool_error(str(err))
         return 1
@@ -774,12 +821,28 @@ def main(argv=None, input=None, output=None, force_git_root=None, return_coder=F
         coder.apply_updates()
         return
 
+    if args.apply_clipboard_edits:
+        args.edit_format = main_model.editor_edit_format
+        args.message = "/paste"
+
     if "VSCODE_GIT_IPC_HANDLE" in os.environ:
         args.pretty = False
         io.tool_output("VSCode terminal detected, pretty output has been disabled.")
 
     io.tool_output('Use /help <question> for help, run "aider --help" to see cmd line args')
 
+    if args.show_release_notes is True:
+        io.tool_output(f"Opening release notes: {urls.release_notes}")
+        io.tool_output()
+        webbrowser.open(urls.release_notes)
+    elif args.show_release_notes is None and is_first_run:
+        io.tool_output()
+        io.offer_url(
+            urls.release_notes,
+            "Would you like to see what's new in this version?",
+            allow_never=False,
+        )
+
     if git_root and Path.cwd().resolve() != Path(git_root).resolve():
         io.tool_warning(
             "Note: in-chat filenames are always relative to the git working dir, not the current"
@@ -835,7 +898,8 @@ def main(argv=None, input=None, output=None, force_git_root=None, return_coder=F
                 coder.show_announcements()
 
 
-def check_and_load_imports(io, verbose=False):
+def is_first_run_of_new_version(io, verbose=False):
+    """Check if this is the first run of a new version/executable combination"""
     installs_file = Path.home() / ".aider" / "installs.json"
     key = (__version__, sys.executable)
 
@@ -856,7 +920,26 @@ def check_and_load_imports(io, verbose=False):
             if verbose:
                 io.tool_output("Installs file does not exist, creating new dictionary")
 
-        if str(key) not in installs:
+        is_first_run = str(key) not in installs
+
+        if is_first_run:
+            installs[str(key)] = True
+            installs_file.parent.mkdir(parents=True, exist_ok=True)
+            with open(installs_file, "w") as f:
+                json.dump(installs, f, indent=4)
+
+        return is_first_run
+
+    except Exception as e:
+        io.tool_warning(f"Error checking version: {e}")
+        if verbose:
+            io.tool_output(f"Full exception details: {traceback.format_exc()}")
+        return True  # Safer to assume it's a first run if we hit an error
+
+
+def check_and_load_imports(io, is_first_run, verbose=False):
+    try:
+        if is_first_run:
             if verbose:
                 io.tool_output(
                     "First run for this version and executable, loading imports synchronously"
@@ -866,17 +949,9 @@ def check_and_load_imports(io, verbose=False):
             except Exception as err:
                 io.tool_error(str(err))
                 io.tool_output("Error loading required imports. Did you install aider properly?")
-                if io.confirm_ask(
-                    "Open documentation url for more info?", subject=urls.install_properly
-                ):
-                    webbrowser.open(urls.install_properly)
-
+                io.offer_url(urls.install_properly, "Open documentation url for more info?")
                 sys.exit(1)
 
-            installs[str(key)] = True
-            installs_file.parent.mkdir(parents=True, exist_ok=True)
-            with open(installs_file, "w") as f:
-                json.dump(installs, f, indent=4)
             if verbose:
                 io.tool_output("Imports loaded and installs file updated")
         else:
@@ -885,8 +960,9 @@ def check_and_load_imports(io, verbose=False):
             thread = threading.Thread(target=load_slow_imports)
             thread.daemon = True
             thread.start()
+
     except Exception as e:
-        io.tool_warning(f"Error in checking imports: {e}")
+        io.tool_warning(f"Error in loading imports: {e}")
         if verbose:
             io.tool_output(f"Full exception details: {traceback.format_exc()}")
 

aider/models.py

@@ -52,6 +52,7 @@ ANTHROPIC_MODELS = """
 claude-2
 claude-2.1
 claude-3-haiku-20240307
+claude-3-5-haiku-20241022
 claude-3-opus-20240229
 claude-3-sonnet-20240229
 claude-3-5-sonnet-20240620
@@ -60,6 +61,23 @@ claude-3-5-sonnet-20241022
 
 ANTHROPIC_MODELS = [ln.strip() for ln in ANTHROPIC_MODELS.splitlines() if ln.strip()]
 
+# Mapping of model aliases to their canonical names
+MODEL_ALIASES = {
+    # Claude models
+    "sonnet": "claude-3-sonnet-20241022",
+    "haiku": "claude-3-haiku-20241022",
+    "opus": "claude-3-opus-20240229",
+    # GPT models
+    "4": "gpt-4-0613",
+    "4o": "gpt-4o-2024-08-06",
+    "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",
+}
+
 
 @dataclass
 class ModelSettings:
@@ -160,6 +178,22 @@ MODEL_SETTINGS = [
         lazy=True,
         reminder="sys",
     ),
+    ModelSettings(
+        "gpt-4o-2024-11-20",
+        "diff",
+        weak_model_name="gpt-4o-mini",
+        use_repo_map=True,
+        lazy=True,
+        reminder="sys",
+    ),
+    ModelSettings(
+        "openai/gpt-4o-2024-11-20",
+        "diff",
+        weak_model_name="gpt-4o-mini",
+        use_repo_map=True,
+        lazy=True,
+        reminder="sys",
+    ),
     ModelSettings(
         "gpt-4o",
         "diff",
@@ -233,24 +267,24 @@ MODEL_SETTINGS = [
     ModelSettings(
         "claude-3-opus-20240229",
         "diff",
-        weak_model_name="claude-3-haiku-20240307",
+        weak_model_name="claude-3-5-haiku-20241022",
         use_repo_map=True,
     ),
     ModelSettings(
         "openrouter/anthropic/claude-3-opus",
         "diff",
-        weak_model_name="openrouter/anthropic/claude-3-haiku",
+        weak_model_name="openrouter/anthropic/claude-3-5-haiku",
         use_repo_map=True,
     ),
     ModelSettings(
         "claude-3-sonnet-20240229",
         "whole",
-        weak_model_name="claude-3-haiku-20240307",
+        weak_model_name="claude-3-5-haiku-20241022",
     ),
     ModelSettings(
         "claude-3-5-sonnet-20240620",
         "diff",
-        weak_model_name="claude-3-haiku-20240307",
+        weak_model_name="claude-3-5-haiku-20241022",
         editor_model_name="claude-3-5-sonnet-20240620",
         editor_edit_format="editor-diff",
         use_repo_map=True,
@@ -267,7 +301,7 @@ MODEL_SETTINGS = [
     ModelSettings(
         "anthropic/claude-3-5-sonnet-20240620",
         "diff",
-        weak_model_name="anthropic/claude-3-haiku-20240307",
+        weak_model_name="anthropic/claude-3-5-haiku-20241022",
         editor_model_name="anthropic/claude-3-5-sonnet-20240620",
         editor_edit_format="editor-diff",
         use_repo_map=True,
@@ -284,7 +318,7 @@ MODEL_SETTINGS = [
     ModelSettings(
         "anthropic/claude-3-5-sonnet-20241022",
         "diff",
-        weak_model_name="anthropic/claude-3-haiku-20240307",
+        weak_model_name="anthropic/claude-3-5-haiku-20241022",
         editor_model_name="anthropic/claude-3-5-sonnet-20241022",
         editor_edit_format="editor-diff",
         use_repo_map=True,
@@ -298,10 +332,27 @@ MODEL_SETTINGS = [
         cache_control=True,
         reminder="user",
     ),
+    ModelSettings(
+        "bedrock/anthropic.claude-3-5-sonnet-20241022-v2:0",
+        "diff",
+        weak_model_name="bedrock/anthropic.claude-3-5-haiku-20241022-v1:0",
+        editor_model_name="bedrock/anthropic.claude-3-5-sonnet-20241022-v2:0",
+        editor_edit_format="editor-diff",
+        use_repo_map=True,
+        examples_as_sys_msg=True,
+        extra_params={
+            "extra_headers": {
+                "anthropic-beta": ANTHROPIC_BETA_HEADER,
+            },
+            "max_tokens": 8192,
+        },
+        cache_control=True,
+        reminder="user",
+    ),
     ModelSettings(
         "anthropic/claude-3-5-sonnet-latest",
         "diff",
-        weak_model_name="anthropic/claude-3-haiku-20240307",
+        weak_model_name="anthropic/claude-3-5-haiku-20241022",
         editor_model_name="anthropic/claude-3-5-sonnet-20241022",
         editor_edit_format="editor-diff",
         use_repo_map=True,
@@ -318,7 +369,7 @@ MODEL_SETTINGS = [
     ModelSettings(
         "claude-3-5-sonnet-20241022",
         "diff",
-        weak_model_name="claude-3-haiku-20240307",
+        weak_model_name="claude-3-5-haiku-20241022",
         editor_model_name="claude-3-5-sonnet-20241022",
         editor_edit_format="editor-diff",
         use_repo_map=True,
@@ -344,6 +395,52 @@ MODEL_SETTINGS = [
         },
         cache_control=True,
     ),
+    ModelSettings(
+        "anthropic/claude-3-5-haiku-20241022",
+        "diff",
+        weak_model_name="anthropic/claude-3-5-haiku-20241022",
+        use_repo_map=True,
+        extra_params={
+            "extra_headers": {
+                "anthropic-beta": ANTHROPIC_BETA_HEADER,
+            },
+        },
+        cache_control=True,
+    ),
+    ModelSettings(
+        "bedrock/anthropic.claude-3-5-haiku-20241022-v1:0",
+        "diff",
+        weak_model_name="bedrock/anthropic.claude-3-5-haiku-20241022-v1:0",
+        use_repo_map=True,
+        extra_params={
+            "extra_headers": {
+                "anthropic-beta": ANTHROPIC_BETA_HEADER,
+            },
+        },
+        cache_control=True,
+    ),
+    ModelSettings(
+        "claude-3-5-haiku-20241022",
+        "diff",
+        weak_model_name="claude-3-5-haiku-20241022",
+        use_repo_map=True,
+        examples_as_sys_msg=True,
+        extra_params={
+            "extra_headers": {
+                "anthropic-beta": ANTHROPIC_BETA_HEADER,
+            },
+        },
+        cache_control=True,
+    ),
+    ModelSettings(
+        "vertex_ai/claude-3-5-haiku@20241022",
+        "diff",
+        weak_model_name="vertex_ai/claude-3-5-haiku@20241022",
+        use_repo_map=True,
+        extra_params={
+            "max_tokens": 4096,
+        },
+    ),
     ModelSettings(
         "claude-3-haiku-20240307",
         "whole",
@@ -359,7 +456,7 @@ MODEL_SETTINGS = [
     ModelSettings(
         "openrouter/anthropic/claude-3.5-sonnet",
         "diff",
-        weak_model_name="openrouter/anthropic/claude-3-haiku",
+        weak_model_name="openrouter/anthropic/claude-3-5-haiku",
         editor_model_name="openrouter/anthropic/claude-3.5-sonnet",
         editor_edit_format="editor-diff",
         use_repo_map=True,
@@ -373,7 +470,7 @@ MODEL_SETTINGS = [
     ModelSettings(
         "openrouter/anthropic/claude-3.5-sonnet:beta",
         "diff",
-        weak_model_name="openrouter/anthropic/claude-3-haiku:beta",
+        weak_model_name="openrouter/anthropic/claude-3-5-haiku:beta",
         editor_model_name="openrouter/anthropic/claude-3.5-sonnet:beta",
         editor_edit_format="editor-diff",
         use_repo_map=True,
@@ -389,7 +486,7 @@ MODEL_SETTINGS = [
     ModelSettings(
         "vertex_ai/claude-3-5-sonnet@20240620",
         "diff",
-        weak_model_name="vertex_ai/claude-3-haiku@20240307",
+        weak_model_name="vertex_ai/claude-3-5-haiku@20241022",
         editor_model_name="vertex_ai/claude-3-5-sonnet@20240620",
         editor_edit_format="editor-diff",
         use_repo_map=True,
@@ -402,7 +499,7 @@ MODEL_SETTINGS = [
     ModelSettings(
         "vertex_ai/claude-3-5-sonnet-v2@20241022",
         "diff",
-        weak_model_name="vertex_ai/claude-3-haiku@20240307",
+        weak_model_name="vertex_ai/claude-3-5-haiku@20241022",
         editor_model_name="vertex_ai/claude-3-5-sonnet-v2@20241022",
         editor_edit_format="editor-diff",
         use_repo_map=True,
@@ -415,13 +512,13 @@ MODEL_SETTINGS = [
     ModelSettings(
         "vertex_ai/claude-3-opus@20240229",
         "diff",
-        weak_model_name="vertex_ai/claude-3-haiku@20240307",
+        weak_model_name="vertex_ai/claude-3-5-haiku@20241022",
         use_repo_map=True,
     ),
     ModelSettings(
         "vertex_ai/claude-3-sonnet@20240229",
         "whole",
-        weak_model_name="vertex_ai/claude-3-haiku@20240307",
+        weak_model_name="vertex_ai/claude-3-5-haiku@20241022",
     ),
     # Cohere
     ModelSettings(
@@ -486,6 +583,11 @@ MODEL_SETTINGS = [
         "diff-fenced",
         use_repo_map=True,
     ),
+    ModelSettings(
+        "vertex_ai/gemini-pro-experimental",
+        "diff-fenced",
+        use_repo_map=True,
+    ),
     ModelSettings(
         "gemini/gemini-1.5-flash-exp-0827",
         "whole",
@@ -560,7 +662,6 @@ MODEL_SETTINGS = [
         reminder="user",
         use_system_prompt=False,
         use_temperature=False,
-        streaming=False,
     ),
     ModelSettings(
         "azure/o1-mini",
@@ -572,7 +673,6 @@ MODEL_SETTINGS = [
         reminder="user",
         use_system_prompt=False,
         use_temperature=False,
-        streaming=False,
     ),
     ModelSettings(
         "o1-mini",
@@ -584,7 +684,6 @@ MODEL_SETTINGS = [
         reminder="user",
         use_system_prompt=False,
         use_temperature=False,
-        streaming=False,
     ),
     ModelSettings(
         "openai/o1-preview",
@@ -596,7 +695,6 @@ MODEL_SETTINGS = [
         reminder="user",
         use_system_prompt=False,
         use_temperature=False,
-        streaming=False,
     ),
     ModelSettings(
         "azure/o1-preview",
@@ -608,7 +706,6 @@ MODEL_SETTINGS = [
         reminder="user",
         use_system_prompt=False,
         use_temperature=False,
-        streaming=False,
     ),
     ModelSettings(
         "o1-preview",
@@ -620,7 +717,6 @@ MODEL_SETTINGS = [
         reminder="user",
         use_system_prompt=False,
         use_temperature=False,
-        streaming=False,
     ),
     ModelSettings(
         "openrouter/openai/o1-mini",
@@ -646,6 +742,14 @@ MODEL_SETTINGS = [
         use_temperature=False,
         streaming=False,
     ),
+    ModelSettings(
+        "openrouter/qwen/qwen-2.5-coder-32b-instruct",
+        "diff",
+        weak_model_name="openrouter/qwen/qwen-2.5-coder-32b-instruct",
+        editor_model_name="openrouter/qwen/qwen-2.5-coder-32b-instruct",
+        editor_edit_format="editor-diff",
+        use_repo_map=True,
+    ),
 ]
 
 
@@ -685,6 +789,11 @@ class ModelInfoManager:
                     pass
         except Exception as ex:
             print(str(ex))
+            try:
+                # Save empty dict to cache file on failure
+                self.cache_file.write_text("{}")
+            except OSError:
+                pass
 
     def get_model_from_cached_json_db(self, model):
         if not self.content:
@@ -706,16 +815,20 @@ class ModelInfoManager:
         return dict()
 
     def get_model_info(self, model):
-        if not litellm._lazy_module:
-            info = self.get_model_from_cached_json_db(model)
-            if info:
-                return info
+        cached_info = self.get_model_from_cached_json_db(model)
 
-        # If all else fails, do it the slow way...
-        try:
-            return litellm.get_model_info(model)
-        except Exception:
-            return dict()
+        litellm_info = None
+        if litellm._lazy_module or not cached_info:
+            try:
+                litellm_info = litellm.get_model_info(model)
+            except Exception as ex:
+                if "model_prices_and_context_window.json" not in str(ex):
+                    print(str(ex))
+
+        if litellm_info:
+            return litellm_info
+
+        return cached_info
 
 
 model_info_manager = ModelInfoManager()
@@ -723,11 +836,17 @@ model_info_manager = ModelInfoManager()
 
 class Model(ModelSettings):
     def __init__(self, model, weak_model=None, editor_model=None, editor_edit_format=None):
-        self.name = model
+        # Map any alias to its canonical name
+        self.name = MODEL_ALIASES.get(model, model)
         self.max_chat_history_tokens = 1024
         self.weak_model = None
         self.editor_model = None
 
+        # Find the extra settings
+        self.extra_model_settings = next(
+            (ms for ms in MODEL_SETTINGS if ms.name == "aider/extra_params"), None
+        )
+
         self.info = self.get_model_info(model)
 
         # Are all needed keys/params available?
@@ -755,17 +874,44 @@ class Model(ModelSettings):
     def get_model_info(self, model):
         return model_info_manager.get_model_info(model)
 
+    def _copy_fields(self, source):
+        """Helper to copy fields from a ModelSettings instance to self"""
+        for field in fields(ModelSettings):
+            val = getattr(source, field.name)
+            setattr(self, field.name, val)
+
     def configure_model_settings(self, model):
+        # Look for exact model match
+        exact_match = False
         for ms in MODEL_SETTINGS:
             # direct match, or match "provider/<model>"
             if model == ms.name:
-                for field in fields(ModelSettings):
-                    val = getattr(ms, field.name)
-                    setattr(self, field.name, val)
-                return  # <--
+                self._copy_fields(ms)
+                exact_match = True
+                break  # Continue to apply overrides
 
         model = model.lower()
 
+        # If no exact match, try generic settings
+        if not exact_match:
+            self.apply_generic_model_settings(model)
+
+        # Apply override settings last if they exist
+        if self.extra_model_settings and self.extra_model_settings.extra_params:
+            # Initialize extra_params if it doesn't exist
+            if not self.extra_params:
+                self.extra_params = {}
+
+            # Deep merge the extra_params dicts
+            for key, value in self.extra_model_settings.extra_params.items():
+                if isinstance(value, dict) and isinstance(self.extra_params.get(key), dict):
+                    # For nested dicts, merge recursively
+                    self.extra_params[key] = {**self.extra_params[key], **value}
+                else:
+                    # For non-dict values, simply update
+                    self.extra_params[key] = value
+
+    def apply_generic_model_settings(self, model):
         if ("llama3" in model or "llama-3" in model) and "70b" in model:
             self.edit_format = "diff"
             self.use_repo_map = True
@@ -787,21 +933,37 @@ class Model(ModelSettings):
 
         if "gpt-3.5" in model or "gpt-4" in model:
             self.reminder = "sys"
+            return  # <--
 
         if "3.5-sonnet" in model or "3-5-sonnet" in model:
             self.edit_format = "diff"
             self.use_repo_map = True
             self.examples_as_sys_msg = True
             self.reminder = "user"
+            return  # <--
 
         if model.startswith("o1-") or "/o1-" in model:
             self.use_system_prompt = False
             self.use_temperature = False
-            self.streaming = False
+            return  # <--
+
+        if (
+            "qwen" in model
+            and "coder" in model
+            and ("2.5" in model or "2-5" in model)
+            and "32b" in model
+        ):
+            self.edit_format = "diff"
+            self.editor_edit_format = "editor-diff"
+            self.use_repo_map = True
+            if model.startswith("ollama/") or model.startswith("ollama_chat/"):
+                self.extra_params = dict(num_ctx=8 * 1024)
+            return  # <--
 
         # use the defaults
         if self.edit_format == "diff":
             self.use_repo_map = True
+            return  # <--
 
     def __str__(self):
         return self.name
@@ -958,6 +1120,9 @@ def register_models(model_settings_fnames):
         if not os.path.exists(model_settings_fname):
             continue
 
+        if not Path(model_settings_fname).read_text().strip():
+            continue
+
         try:
             with open(model_settings_fname, "r") as model_settings_file:
                 model_settings_list = yaml.safe_load(model_settings_file)
@@ -985,8 +1150,14 @@ def register_litellm_models(model_fnames):
             continue
 
         try:
-            with open(model_fname, "r") as model_def_file:
-                model_def = json5.load(model_def_file)
+            data = Path(model_fname).read_text()
+            if not data.strip():
+                continue
+            model_def = json5.loads(data)
+            if not model_def:
+                continue
+
+            # only load litellm if we have actual data
             litellm._load_litellm()
             litellm.register_model(model_def)
         except Exception as e:
@@ -1069,7 +1240,10 @@ def fuzzy_match_models(name):
         model = model.lower()
         if attrs.get("mode") != "chat":
             continue
-        provider = (attrs["litellm_provider"] + "/").lower()
+        provider = attrs.get("litellm_provider", "").lower()
+        if not provider:
+            continue
+        provider += "/"
 
         if model.startswith(provider):
             fq_model = model

aider/queries/tree-sitter-dart-tags.scm

@@ -0,0 +1,91 @@
+(class_definition
+  name: (identifier) @name.definition.class) @definition.class
+
+(method_signature
+  (function_signature)) @definition.method
+
+(type_alias
+  (type_identifier) @name.definition.type) @definition.type
+
+(method_signature
+  (getter_signature
+    name: (identifier) @name.definition.method)) @definition.method
+
+(method_signature
+  (setter_signature
+    name: (identifier) @name.definition.method)) @definition.method
+
+(method_signature
+  (function_signature
+  name: (identifier) @name.definition.method)) @definition.method
+
+(method_signature
+  (factory_constructor_signature
+    (identifier) @name.definition.method)) @definition.method
+
+(method_signature
+  (constructor_signature
+  name: (identifier) @name.definition.method)) @definition.method
+
+(method_signature
+  (operator_signature)) @definition.method
+
+(method_signature) @definition.method
+
+(mixin_declaration
+  (mixin)
+  (identifier) @name.definition.mixin) @definition.mixin
+
+(extension_declaration
+  name: (identifier) @name.definition.extension) @definition.extension
+
+(enum_declaration
+  name: (identifier) @name.definition.enum) @definition.enum
+
+(function_signature
+  name: (identifier) @name.definition.function) @definition.function
+
+(new_expression
+  (type_identifier) @name.reference.class) @reference.class
+
+(initialized_variable_definition
+  name: (identifier)
+  value: (identifier) @name.reference.class
+  value: (selector
+	"!"?
+	(argument_part
+	  (arguments
+	    (argument)*))?)?) @reference.class
+
+(assignment_expression
+  left: (assignable_expression
+		  (identifier)
+		  (unconditional_assignable_selector
+			"."
+			(identifier) @name.reference.call))) @reference.call
+
+(assignment_expression
+  left: (assignable_expression
+		  (identifier)
+		  (conditional_assignable_selector
+			"?."
+			(identifier) @name.reference.call))) @reference.call
+
+((identifier) @name
+ (selector
+    "!"?
+    (conditional_assignable_selector
+      "?." (identifier) @name.reference.call)?
+    (unconditional_assignable_selector
+      "."? (identifier) @name.reference.call)?
+    (argument_part
+      (arguments
+        (argument)*))?)*
+	(cascade_section
+	  (cascade_selector
+		(identifier)) @name.reference.call
+	  (argument_part
+		(arguments
+		  (argument)*))?)?) @reference.call
+
+

aider/repo.py

@@ -169,7 +169,7 @@ class GitRepo:
     def get_rel_repo_dir(self):
         try:
             return os.path.relpath(self.repo.git_dir, os.getcwd())
-        except ValueError:
+        except (ValueError, OSError):
             return self.repo.git_dir
 
     def get_commit_message(self, diffs, context):
@@ -331,6 +331,15 @@ class GitRepo:
                 lines,
             )
 
+    def git_ignored_file(self, path):
+        if not self.repo:
+            return
+        try:
+            if self.repo.ignored(path):
+                return True
+        except ANY_GIT_ERROR:
+            return False
+
     def ignored_file(self, fname):
         self.refresh_aider_ignore()
 

aider/repomap.py

@@ -28,7 +28,7 @@ from tree_sitter_languages import get_language, get_parser  # noqa: E402
 Tag = namedtuple("Tag", "rel_fname fname line name kind".split())
 
 
-SQLITE_ERRORS = (sqlite3.OperationalError, sqlite3.DatabaseError)
+SQLITE_ERRORS = (sqlite3.OperationalError, sqlite3.DatabaseError, OSError)
 
 
 class RepoMap:
@@ -197,7 +197,7 @@ class RepoMap:
             self.TAGS_CACHE = new_cache
             return
 
-        except (SQLITE_ERRORS, OSError) as e:
+        except SQLITE_ERRORS as e:
             # If anything goes wrong, warn and fall back to dict
             self.io.tool_warning(
                 f"Unable to use tags cache at {path}, falling back to memory cache"
@@ -368,6 +368,8 @@ class RepoMap:
             showing_bar = False
 
         for fname in fnames:
+            if self.verbose:
+                self.io.tool_output(f"Processing {fname}")
             if progress and not showing_bar:
                 progress()
 

aider/sendchat.py

@@ -2,9 +2,8 @@ import hashlib
 import json
 import time
 
-import backoff
-
 from aider.dump import dump  # noqa: F401
+from aider.exceptions import LiteLLMExceptions
 from aider.llm import litellm
 
 # from diskcache import Cache
@@ -17,52 +16,6 @@ CACHE = None
 RETRY_TIMEOUT = 60
 
 
-def retry_exceptions():
-    import httpx
-    import openai
-
-    return (
-        # httpx
-        httpx.ConnectError,
-        httpx.RemoteProtocolError,
-        httpx.ReadTimeout,
-        #
-        # litellm exceptions inherit from openai exceptions
-        # https://docs.litellm.ai/docs/exception_mapping
-        #
-        # openai.BadRequestError,
-        # litellm.ContextWindowExceededError,
-        # litellm.ContentPolicyViolationError,
-        #
-        # openai.AuthenticationError,
-        # openai.PermissionDeniedError,
-        # openai.NotFoundError,
-        #
-        openai.APITimeoutError,
-        openai.UnprocessableEntityError,
-        openai.RateLimitError,
-        openai.APIConnectionError,
-        # openai.APIError,
-        # openai.APIStatusError,
-        openai.InternalServerError,
-    )
-
-
-def lazy_litellm_retry_decorator(func):
-    def wrapper(*args, **kwargs):
-        decorated_func = backoff.on_exception(
-            backoff.expo,
-            retry_exceptions(),
-            max_time=RETRY_TIMEOUT,
-            on_backoff=lambda details: print(
-                f"{details.get('exception', 'Exception')}\nRetry in {details['wait']:.1f} seconds."
-            ),
-        )(func)
-        return decorated_func(*args, **kwargs)
-
-    return wrapper
-
-
 def send_completion(
     model_name,
     messages,
@@ -104,6 +57,8 @@ def send_completion(
 
 
 def simple_send_with_retries(model_name, messages, extra_params=None):
+    litellm_ex = LiteLLMExceptions()
+
     retry_delay = 0.125
     while True:
         try:
@@ -116,14 +71,27 @@ def simple_send_with_retries(model_name, messages, extra_params=None):
             }
 
             _hash, response = send_completion(**kwargs)
+            if not response or not hasattr(response, "choices") or not response.choices:
+                return None
             return response.choices[0].message.content
-        except retry_exceptions() as err:
+        except litellm_ex.exceptions_tuple() as err:
+            ex_info = litellm_ex.get_ex_info(err)
+
             print(str(err))
-            retry_delay *= 2
-            if retry_delay > RETRY_TIMEOUT:
-                break
+            if ex_info.description:
+                print(ex_info.description)
+
+            should_retry = ex_info.retry
+            if should_retry:
+                retry_delay *= 2
+                if retry_delay > RETRY_TIMEOUT:
+                    should_retry = False
+
+            if not should_retry:
+                return None
+
             print(f"Retrying in {retry_delay:.1f} seconds...")
             time.sleep(retry_delay)
             continue
         except AttributeError:
-            return
+            return None

aider/urls.py

@@ -12,3 +12,5 @@ github_issues = "https://github.com/Aider-AI/aider/issues/new"
 git_index_version = "https://github.com/Aider-AI/aider/issues/211"
 install_properly = "https://aider.chat/docs/troubleshooting/imports.html"
 analytics = "https://aider.chat/docs/more/analytics.html"
+release_notes = "https://aider.chat/HISTORY.html#release-notes"
+edit_formats = "https://aider.chat/docs/more/edit-formats.html"

aider/website/HISTORY.md

@@ -10,6 +10,12 @@ description: Release notes and stats on aider writing its own code.
 
 {% include blame.md %}
 
+The above 
+[stats are based on the git commit history](/docs/faq.html#how-are-the-aider-wrote-xx-of-code-stats-computed)
+of the aider repo.
+
+## Release notes
+
 <!--[[[cog
 # This page is a copy of HISTORY.md, adding the front matter above.
 text = open("HISTORY.md").read()
@@ -18,9 +24,83 @@ cog.out(text)
 ]]]-->
 
 
-
 ### main branch
 
+- Added `--alias` config to define [custom model aliases](https://aider.chat/docs/config/model-aliases.html).
+- Added `--[no-]detect-urls` flag to disable detecting and offering to scrape URLs found in the chat.
+- Ollama models now default to an 8k context window.
+- Added [RepoMap support for Dart language](https://aider.chat/docs/languages.html) by @malkoG.
+- Ask 2.5% of users if they want to opt-in to [analytics](https://aider.chat/docs/more/analytics.html).
+- Skip suggesting files that share names with files already in chat.
+- `/editor` returns and prefill the file content into the prompt, so you can use `/editor` to compose messages that start with `/commands`, etc.
+- Enhanced error handling for analytics.
+- Improved handling of UnknownEditFormat exceptions with helpful documentation links.
+- Bumped dependencies to pick up grep-ast 0.4.0 for Dart language support.
+- Aider wrote 81% of the code in this release.
+
+### Aider v0.64.1
+
+- Disable streaming for o1 on OpenRouter.
+
+### Aider v0.64.0
+
+- Added [`/editor` command](https://aider.chat/docs/usage/commands.html) to open system editor for writing prompts, by @thehunmonkgroup.
+- Full support for `gpt-4o-2024-11-20`.
+- Stream o1 models by default.
+- `/run` and suggested shell commands are less mysterious and now confirm that they "Added XX lines of output to the chat."
+- Ask 1% of users if they want to opt-in to [analytics](https://aider.chat/docs/more/analytics.html).
+- Added support for [optional multiline input tags](https://aider.chat/docs/usage/commands.html#entering-multi-line-chat-messages) with matching closing tags.
+- Improved [model settings configuration](https://aider.chat/docs/config/adv-model-settings.html#global-extra-params) with support for global `extra_params` for `litellm.completion()`.
+- Architect mode now asks to add files suggested by the LLM.
+- Fixed bug in fuzzy model name matching.
+- Added Timeout exception to handle API provider timeouts.
+- Added `--show-release-notes` to control release notes display on first run of new version.
+- Save empty dict to cache file on model metadata download failure, to delay retry.
+- Improved error handling and code formatting.
+- Aider wrote 74% of the code in this release.
+
+###  Aider v0.63.2
+
+- Fixed bug in fuzzy model name matching when litellm provider info is missing.
+- Modified model metadata file loading to allow override of resource file.
+- Allow recursive loading of dirs using `--read`.
+- Updated dependency versions to pick up litellm fix for ollama models.
+- Added exponential backoff retry when writing files to handle editor file locks.
+- Updated Qwen 2.5 Coder 32B model configuration.
+
+### Aider v0.63.1
+
+- Fixed bug in git ignored file handling.
+- Improved error handling for git operations.
+
+### Aider v0.63.0
+
+- Support for Qwen 2.5 Coder 32B.
+- `/web` command just adds the page to the chat, without triggering an LLM response.
+- Improved prompting for the user's preferred chat language.
+- Improved handling of LiteLLM exceptions.
+- Bugfix for double-counting tokens when reporting cache stats.
+- Bugfix for the LLM creating new files.
+- Other small bug fixes.
+- Aider wrote 55% of the code in this release.
+
+### Aider v0.62.0
+
+- Full support for Claude 3.5 Haiku
+  - Scored 75% on [aider's code editing leaderboard](https://aider.chat/docs/leaderboards/).
+  - Almost as good as Sonnet at much lower cost.
+  - Launch with `--haiku` to use it.
+- Easily apply file edits from ChatGPT, Claude or other web apps
+  - Chat with ChatGPT or Claude via their web app. 
+  - Give it your source files and ask for the changes you want.
+  - Use the web app's "copy response" button to copy the entire reply from the LLM.
+  - Run `aider --apply-clipboard-edits file-to-edit.js`.
+  - Aider will edit your file with the LLM's changes.
+- Bugfix for creating new files.
+- Aider wrote 84% of the code in this release.  
+
+### Aider v0.61.0
+
 - Load and save aider slash-commands to files:
   - `/save <fname>` command will make a file of `/add` and `/read-only` commands that recreate the current file context in the chat.
   - `/load <fname>` will replay the commands in the file.

aider/website/_data/blame.yml

@@ -1801,8 +1801,8 @@
     Paul Gauthier (aider): 113
   start_tag: v0.44.0
   total_lines: 266
-- aider_percentage: 47.04
-  aider_total: 254
+- aider_percentage: 53.3
+  aider_total: 339
   end_date: '2024-07-29'
   end_tag: v0.46.0
   file_counts:
@@ -1853,6 +1853,9 @@
     aider/scrape.py:
       Paul Gauthier: 3
       Paul Gauthier (aider): 32
+    aider/website/docs/leaderboards/index.md:
+      Paul Gauthier: 11
+      Paul Gauthier (aider): 85
     benchmark/Dockerfile:
       Your Name: 1
     tests/basic/test_coder.py:
@@ -1868,13 +1871,13 @@
       Paul Gauthier (aider): 73
   grand_total:
     Charles Joachim: 4
-    Paul Gauthier: 209
-    Paul Gauthier (aider): 204
+    Paul Gauthier: 220
+    Paul Gauthier (aider): 289
     Your Name: 73
     Your Name (aider): 50
   start_tag: v0.45.0
-  total_lines: 540
-- aider_percentage: 59.12
+  total_lines: 636
+- aider_percentage: 57.16
   aider_total: 415
   end_date: '2024-07-31'
   end_tag: v0.47.0
@@ -1920,6 +1923,8 @@
       Paul Gauthier (aider): 2
     aider/utils.py:
       Paul Gauthier: 7
+    aider/website/docs/leaderboards/index.md:
+      Paul Gauthier: 24
     docker/Dockerfile:
       Paul Gauthier: 19
       Paul Gauthier (aider): 21
@@ -1944,10 +1949,10 @@
     tests/basic/test_repomap.py:
       Paul Gauthier: 1
   grand_total:
-    Paul Gauthier: 287
+    Paul Gauthier: 311
     Paul Gauthier (aider): 415
   start_tag: v0.46.0
-  total_lines: 702
+  total_lines: 726
 - aider_percentage: 44.44
   aider_total: 276
   end_date: '2024-08-06'
@@ -2011,8 +2016,8 @@
     paul-gauthier: 1
   start_tag: v0.47.0
   total_lines: 621
-- aider_percentage: 61.52
-  aider_total: 478
+- aider_percentage: 61.2
+  aider_total: 489
   end_date: '2024-08-10'
   end_tag: v0.49.0
   file_counts:
@@ -2055,6 +2060,9 @@
     aider/versioncheck.py:
       Paul Gauthier: 3
       Paul Gauthier (aider): 11
+    aider/website/docs/leaderboards/index.md:
+      Paul Gauthier: 11
+      Paul Gauthier (aider): 11
     docker/Dockerfile:
       Paul Gauthier: 5
       Paul Gauthier (aider): 2
@@ -2075,10 +2083,10 @@
       Paul Gauthier: 1
       Paul Gauthier (aider): 49
   grand_total:
-    Paul Gauthier: 299
-    Paul Gauthier (aider): 478
+    Paul Gauthier: 310
+    Paul Gauthier (aider): 489
   start_tag: v0.48.0
-  total_lines: 777
+  total_lines: 799
 - aider_percentage: 66.05
   aider_total: 214
   end_date: '2024-08-13'
@@ -2135,8 +2143,8 @@
     Paul Gauthier (aider): 201
   start_tag: v0.49.0
   total_lines: 324
-- aider_percentage: 56.25
-  aider_total: 450
+- aider_percentage: 52.49
+  aider_total: 580
   end_date: '2024-08-20'
   end_tag: v0.51.0
   file_counts:
@@ -2170,6 +2178,14 @@
       Paul Gauthier: 3
     aider/utils.py:
       Paul Gauthier (aider): 6
+    aider/website/_includes/code-in-json-benchmark.js:
+      Paul Gauthier: 101
+      Paul Gauthier (aider): 64
+    aider/website/_includes/code-in-json-syntax.js:
+      Paul Gauthier: 73
+      Paul Gauthier (aider): 66
+    aider/website/docs/leaderboards/index.md:
+      Paul Gauthier: 1
     benchmark/benchmark.py:
       Paul Gauthier: 7
     benchmark/over_time.py:
@@ -2188,11 +2204,11 @@
       Paul Gauthier: 15
       Paul Gauthier (aider): 104
   grand_total:
-    Paul Gauthier: 350
-    Paul Gauthier (aider): 450
+    Paul Gauthier: 525
+    Paul Gauthier (aider): 580
   start_tag: v0.50.0
-  total_lines: 800
-- aider_percentage: 68.19
+  total_lines: 1105
+- aider_percentage: 68.1
   aider_total: 521
   end_date: '2024-08-23'
   end_tag: v0.52.0
@@ -2231,6 +2247,8 @@
       Paul Gauthier (aider): 9
     aider/versioncheck.py:
       Paul Gauthier: 2
+    aider/website/docs/leaderboards/index.md:
+      Paul Gauthier: 1
     benchmark/benchmark.py:
       Paul Gauthier: 1
     scripts/blame.py:
@@ -2250,13 +2268,13 @@
     tests/basic/test_wholefile.py:
       Paul Gauthier: 8
   grand_total:
-    Paul Gauthier: 242
+    Paul Gauthier: 243
     Paul Gauthier (aider): 521
     pcamp: 1
   start_tag: v0.51.0
-  total_lines: 764
-- aider_percentage: 58.61
-  aider_total: 405
+  total_lines: 765
+- aider_percentage: 61.4
+  aider_total: 455
   end_date: '2024-08-27'
   end_tag: v0.53.0
   file_counts:
@@ -2321,14 +2339,16 @@
     tests/basic/test_repomap.py:
       Paul Gauthier: 4
       Paul Gauthier (aider): 63
+    tests/fixtures/sample-code-base/sample.js:
+      Paul Gauthier (aider): 50
     tests/fixtures/sample-code-base/sample.py:
       Paul Gauthier (aider): 68
   grand_total:
     Paul Gauthier: 286
-    Paul Gauthier (aider): 405
+    Paul Gauthier (aider): 455
   start_tag: v0.52.0
-  total_lines: 691
-- aider_percentage: 63.95
+  total_lines: 741
+- aider_percentage: 63.75
   aider_total: 204
   end_date: '2024-08-28'
   end_tag: v0.54.0
@@ -2364,6 +2384,8 @@
     aider/versioncheck.py:
       Paul Gauthier: 1
       Paul Gauthier (aider): 13
+    aider/website/docs/leaderboards/index.md:
+      Paul Gauthier: 1
     tests/basic/test_coder.py:
       Paul Gauthier: 36
       Paul Gauthier (aider): 27
@@ -2376,11 +2398,11 @@
       Paul Gauthier: 1
   grand_total:
     Antti Kaihola: 4
-    Paul Gauthier: 111
+    Paul Gauthier: 112
     Paul Gauthier (aider): 204
   start_tag: v0.53.0
-  total_lines: 319
-- aider_percentage: 52.9
+  total_lines: 320
+- aider_percentage: 52.87
   aider_total: 811
   end_date: '2024-09-04'
   end_tag: v0.55.0
@@ -2450,6 +2472,8 @@
     aider/voice.py:
       Paul Gauthier: 7
       Paul Gauthier (aider): 9
+    aider/website/docs/leaderboards/index.md:
+      Paul Gauthier: 1
     scripts/versionbump.py:
       Paul Gauthier: 9
     tests/basic/test_coder.py:
@@ -2478,11 +2502,11 @@
   grand_total:
     Antti Kaihola: 12
     Nikolay Sedelnikov: 45
-    Paul Gauthier: 665
+    Paul Gauthier: 666
     Paul Gauthier (aider): 811
   start_tag: v0.54.0
-  total_lines: 1533
-- aider_percentage: 55.6
+  total_lines: 1534
+- aider_percentage: 55.4
   aider_total: 154
   end_date: '2024-09-09'
   end_tag: v0.56.0
@@ -2517,6 +2541,8 @@
     aider/report.py:
       Paul Gauthier: 2
       Paul Gauthier (aider): 20
+    aider/website/docs/leaderboards/index.md:
+      Paul Gauthier: 1
     benchmark/benchmark.py:
       Paul Gauthier: 1
     tests/basic/test_linter.py:
@@ -2526,13 +2552,13 @@
       Paul Gauthier: 2
       Paul Gauthier (aider): 9
   grand_total:
-    Paul Gauthier: 108
+    Paul Gauthier: 109
     Paul Gauthier (aider): 154
     fry69: 15
   start_tag: v0.55.0
-  total_lines: 277
-- aider_percentage: 69.98
-  aider_total: 394
+  total_lines: 278
+- aider_percentage: 70.36
+  aider_total: 406
   end_date: '2024-09-21'
   end_tag: v0.57.0
   file_counts:
@@ -2575,6 +2601,10 @@
       Paul Gauthier: 3
     aider/utils.py:
       Paul Gauthier: 2
+    aider/website/docs/leaderboards/index.md:
+      Anjor Kanekar: 1
+      Paul Gauthier: 1
+      Paul Gauthier (aider): 12
     benchmark/benchmark.py:
       Paul Gauthier: 4
     scripts/issues.py:
@@ -2592,15 +2622,16 @@
       Paul Gauthier: 18
       Paul Gauthier (aider): 20
   grand_total:
+    Anjor Kanekar: 1
     Christian Clauss: 2
     Jay Alammar: 1
     Jay Alammar (aider): 13
     Krazer: 33
-    Paul Gauthier: 133
-    Paul Gauthier (aider): 381
+    Paul Gauthier: 134
+    Paul Gauthier (aider): 393
   start_tag: v0.56.0
-  total_lines: 563
-- aider_percentage: 53.45
+  total_lines: 577
+- aider_percentage: 47.95
   aider_total: 712
   end_date: '2024-09-29'
   end_tag: v0.58.0
@@ -2677,6 +2708,8 @@
       Mike Bailey: 17
       Paul Gauthier: 2
       Paul Gauthier (aider): 10
+    aider/website/docs/leaderboards/index.md:
+      Paul Gauthier: 153
     benchmark/benchmark.py:
       Paul Gauthier: 25
       Paul Gauthier (aider): 29
@@ -2705,14 +2738,14 @@
   grand_total:
     Jonathan Ellis: 2
     Mike Bailey: 18
-    Paul Gauthier: 376
+    Paul Gauthier: 529
     Paul Gauthier (aider): 712
     Stein Martin Hustad: 26
     fry69: 197
     rti: 1
   start_tag: v0.57.0
-  total_lines: 1332
-- aider_percentage: 76.79
+  total_lines: 1485
+- aider_percentage: 75.44
   aider_total: 172
   end_date: '2024-10-04'
   end_tag: v0.59.0
@@ -2747,6 +2780,8 @@
       Paul Gauthier: 2
     aider/versioncheck.py:
       Paul Gauthier: 1
+    aider/website/docs/leaderboards/index.md:
+      Paul Gauthier: 4
     scripts/issues.py:
       Paul Gauthier: 1
     scripts/update-docs.sh:
@@ -2762,11 +2797,11 @@
     tests/help/test_help.py:
       Paul Gauthier: 1
   grand_total:
-    Paul Gauthier: 52
+    Paul Gauthier: 56
     Paul Gauthier (aider): 172
   start_tag: v0.58.0
-  total_lines: 224
-- aider_percentage: 49.12
+  total_lines: 228
+- aider_percentage: 48.95
   aider_total: 140
   end_date: '2024-10-22'
   end_tag: v0.60.0
@@ -2804,6 +2839,8 @@
       Paul Gauthier: 3
     aider/sendchat.py:
       Paul Gauthier: 3
+    aider/website/docs/leaderboards/index.md:
+      Paul Gauthier: 1
     tests/basic/test_editblock.py:
       Paul Gauthier: 23
     tests/basic/test_main.py:
@@ -2813,9 +2850,259 @@
       Paul Gauthier (aider): 46
   grand_total:
     Jonathan Ellis: 10
-    Paul Gauthier: 93
+    Paul Gauthier: 94
     Paul Gauthier (aider): 140
     Sven Grunewaldt: 24
     fry69: 18
   start_tag: v0.59.0
-  total_lines: 285
+  total_lines: 286
+- aider_percentage: 67.61
+  aider_total: 860
+  end_date: '2024-11-01'
+  end_tag: v0.61.0
+  file_counts:
+    aider/__init__.py:
+      Paul Gauthier: 1
+    aider/analytics.py:
+      Paul Gauthier: 75
+      Paul Gauthier (aider): 89
+    aider/args.py:
+      Paul Gauthier: 5
+      Paul Gauthier (aider): 29
+    aider/coders/base_coder.py:
+      Paul Gauthier: 56
+      Paul Gauthier (aider): 43
+    aider/coders/editblock_coder.py:
+      Paul Gauthier: 14
+    aider/commands.py:
+      Paul Gauthier: 14
+      Paul Gauthier (aider): 86
+    aider/io.py:
+      Paul Gauthier: 12
+      Paul Gauthier (aider): 32
+    aider/linter.py:
+      Paul Gauthier: 6
+    aider/main.py:
+      Paul Gauthier: 48
+      Paul Gauthier (aider): 10
+    aider/models.py:
+      Paul Gauthier: 54
+      Paul Gauthier (aider): 63
+      kAIto47802: 4
+    aider/repomap.py:
+      Paul Gauthier: 12
+      Paul Gauthier (aider): 52
+    aider/sendchat.py:
+      Paul Gauthier: 23
+      Paul Gauthier (aider): 23
+    aider/urls.py:
+      Paul Gauthier: 2
+    aider/utils.py:
+      Paul Gauthier (aider): 6
+    scripts/issues.py:
+      Paul Gauthier (aider): 13
+    scripts/pip-compile.sh:
+      Paul Gauthier (aider): 13
+    scripts/update-docs.sh:
+      Paul Gauthier: 1
+      Paul Gauthier (aider): 5
+    tests/basic/test_analytics.py:
+      Paul Gauthier: 1
+      Paul Gauthier (aider): 99
+    tests/basic/test_commands.py:
+      Konstantin L: 34
+      Paul Gauthier: 45
+      Paul Gauthier (aider): 267
+    tests/basic/test_io.py:
+      Paul Gauthier: 2
+      Paul Gauthier (aider): 4
+    tests/basic/test_main.py:
+      Paul Gauthier (aider): 3
+    tests/basic/test_models.py:
+      Paul Gauthier: 3
+      Paul Gauthier (aider): 9
+    tests/basic/test_sanity_check_repo.py:
+      Paul Gauthier (aider): 6
+    tests/basic/test_sendchat.py:
+      Paul Gauthier (aider): 8
+  grand_total:
+    Konstantin L: 34
+    Paul Gauthier: 374
+    Paul Gauthier (aider): 860
+    kAIto47802: 4
+  start_tag: v0.60.0
+  total_lines: 1272
+- aider_percentage: 82.42
+  aider_total: 75
+  end_date: '2024-11-04'
+  end_tag: v0.62.0
+  file_counts:
+    aider/__init__.py:
+      Paul Gauthier: 1
+    aider/args.py:
+      Paul Gauthier (aider): 14
+    aider/coders/editblock_coder.py:
+      Paul Gauthier: 6
+    aider/main.py:
+      Paul Gauthier (aider): 4
+    aider/models.py:
+      Paul Gauthier: 5
+      Paul Gauthier (aider): 45
+    aider/website/docs/leaderboards/index.md:
+      Paul Gauthier: 4
+      Paul Gauthier (aider): 12
+  grand_total:
+    Paul Gauthier: 16
+    Paul Gauthier (aider): 75
+  start_tag: v0.61.0
+  total_lines: 91
+- aider_percentage: 55.08
+  aider_total: 385
+  end_date: '2024-11-13'
+  end_tag: v0.63.0
+  file_counts:
+    aider/__init__.py:
+      Paul Gauthier: 1
+    aider/coders/architect_coder.py:
+      Paul Gauthier: 3
+    aider/coders/base_coder.py:
+      Paul Gauthier: 42
+      Paul Gauthier (aider): 1
+    aider/coders/editblock_coder.py:
+      Paul Gauthier: 4
+    aider/commands.py:
+      Paul Gauthier: 13
+    aider/exceptions.py:
+      Paul Gauthier: 72
+      Paul Gauthier (aider): 4
+    aider/io.py:
+      Paul Gauthier: 3
+      Paul Gauthier (aider): 23
+    aider/main.py:
+      Paul Gauthier: 9
+      Paul Gauthier (aider): 9
+    aider/models.py:
+      Logan Attwood: 29
+      Paul Gauthier: 50
+      Paul Gauthier (aider): 7
+    aider/repo.py:
+      Paul Gauthier: 7
+    aider/repomap.py:
+      Paul Gauthier: 4
+    aider/sendchat.py:
+      Paul Gauthier: 17
+      Paul Gauthier (aider): 4
+    aider/website/docs/leaderboards/index.md:
+      Paul Gauthier: 1
+    scripts/issues.py:
+      Paul Gauthier: 4
+      Paul Gauthier (aider): 195
+    tests/basic/test_coder.py:
+      Paul Gauthier: 2
+    tests/basic/test_commands.py:
+      Paul Gauthier (aider): 20
+    tests/basic/test_editblock.py:
+      Paul Gauthier: 41
+    tests/basic/test_exceptions.py:
+      Paul Gauthier (aider): 65
+    tests/basic/test_main.py:
+      Paul Gauthier: 1
+    tests/basic/test_sanity_check_repo.py:
+      Paul Gauthier: 2
+      Paul Gauthier (aider): 2
+    tests/basic/test_sendchat.py:
+      Paul Gauthier: 8
+      Paul Gauthier (aider): 55
+    tests/scrape/test_scrape.py:
+      Paul Gauthier: 1
+  grand_total:
+    Logan Attwood: 29
+    Paul Gauthier: 285
+    Paul Gauthier (aider): 385
+  start_tag: v0.62.0
+  total_lines: 699
+- aider_percentage: 73.15
+  aider_total: 880
+  end_date: '2024-11-21'
+  end_tag: v0.64.0
+  file_counts:
+    aider/__init__.py:
+      Paul Gauthier: 1
+    aider/analytics.py:
+      Paul Gauthier: 20
+      Paul Gauthier (aider): 21
+    aider/args.py:
+      Paul Gauthier: 2
+      Paul Gauthier (aider): 10
+    aider/coders/base_coder.py:
+      Paul Gauthier: 15
+      Paul Gauthier (aider): 3
+      caetanominuzzo: 1
+    aider/commands.py:
+      Chad Phillips: 4
+      Paul Gauthier: 5
+      Paul Gauthier (aider): 19
+    aider/editor.py:
+      Chad Phillips: 133
+      Paul Gauthier (aider): 13
+    aider/exceptions.py:
+      Paul Gauthier: 5
+    aider/help_pats.py:
+      Paul Gauthier: 1
+    aider/io.py:
+      Chad Phillips: 9
+      Paul Gauthier (aider): 41
+      mw: 21
+    aider/main.py:
+      Paul Gauthier: 21
+      Paul Gauthier (aider): 41
+    aider/models.py:
+      Paul Gauthier: 41
+      Paul Gauthier (aider): 33
+    aider/repo.py:
+      Paul Gauthier (aider): 5
+    aider/urls.py:
+      Paul Gauthier: 1
+    aider/website/_includes/edit-leaderboard.js:
+      Paul Gauthier (aider): 97
+    aider/website/_includes/quant-chart.js:
+      Paul Gauthier: 3
+      Paul Gauthier (aider): 66
+    aider/website/_includes/refactor-leaderboard.js:
+      Paul Gauthier (aider): 90
+    aider/website/docs/leaderboards/index.md:
+      Paul Gauthier: 1
+      Paul Gauthier (aider): 10
+    aider/website/share/index.md:
+      Paul Gauthier (aider): 29
+    benchmark/over_time.py:
+      Paul Gauthier: 11
+      Paul Gauthier (aider): 162
+    scripts/blame.py:
+      Paul Gauthier: 1
+      Paul Gauthier (aider): 2
+    scripts/issues.py:
+      Paul Gauthier: 5
+      Paul Gauthier (aider): 12
+    scripts/versionbump.py:
+      Paul Gauthier: 7
+    tests/basic/test_analytics.py:
+      Paul Gauthier: 12
+      Paul Gauthier (aider): 30
+    tests/basic/test_commands.py:
+      Paul Gauthier (aider): 4
+    tests/basic/test_editor.py:
+      Paul Gauthier (aider): 129
+    tests/basic/test_main.py:
+      Paul Gauthier (aider): 8
+    tests/basic/test_models.py:
+      Paul Gauthier: 3
+      Paul Gauthier (aider): 55
+  grand_total:
+    Chad Phillips: 146
+    Paul Gauthier: 155
+    Paul Gauthier (aider): 880
+    caetanominuzzo: 1
+    mw: 21
+  start_tag: v0.63.0
+  total_lines: 1203

aider/website/_data/edit_leaderboard.yml

@@ -1,7 +1,7 @@
 - dirname: 2024-05-01-20-05-59--direct-opus-filenames-outside-fence
   test_cases: 133
   model: claude-3-opus-20240229
-  released: 2024-02-29
+  _released: 2024-02-29
   edit_format: diff
   commit_hash: f4b1797-dirty, f4b1797
   pass_rate_1: 53.4
@@ -20,7 +20,7 @@
   versions: 0.30.2-dev
   seconds_per_case: 32.4
   total_cost: 13.8395
-  
+
 - dirname: 2024-03-06-16-42-00--claude3-sonnet-whole
   test_cases: 133
   model: claude-3-sonnet-20240229
@@ -43,10 +43,11 @@
   versions: 0.25.1-dev
   seconds_per_case: 23.1
   total_cost: 0.0000
-  
+
 - dirname: 2024-05-03-20-47-24--gemini-1.5-pro-diff-fenced
   test_cases: 133
-  model: gemini-1.5-pro-latest
+  released: 2024-05-03
+  model: gemini-1.5-pro-001
   edit_format: diff-fenced
   commit_hash: 3a48dfb, 5d32dd7
   pass_rate_1: 45.9
@@ -88,7 +89,7 @@
   versions: 0.33.1-dev
   seconds_per_case: 6.5
   total_cost: 0.5032
-  
+
 - dirname: 2023-11-06-21-23-59--gpt-3.5-turbo-0301
   test_cases: 133
   model: gpt-3.5-turbo-0301
@@ -111,7 +112,7 @@
   versions: 0.16.4-dev
   seconds_per_case: 6.5
   total_cost: 0.4822
-  
+
 - dirname: 2023-11-07-02-41-07--gpt-3.5-turbo-0613
   test_cases: 133
   model: gpt-3.5-turbo-0613
@@ -155,7 +156,7 @@
   versions: 0.30.2-dev
   seconds_per_case: 5.3
   total_cost: 0.3261
-  
+
 - dirname: 2024-01-25-23-37-15--jan-exercism-gpt-4-0125-preview-udiff
   test_cases: 133
   model: gpt-4-0125-preview
@@ -178,7 +179,7 @@
   versions: 0.22.1-dev
   seconds_per_case: 44.8
   total_cost: 14.6428
-  
+
 - dirname: 2024-05-04-15-07-30--redo-gpt-4-0314-diff-reminder-rules
   test_cases: 133
   model: gpt-4-0314
@@ -201,7 +202,7 @@
   versions: 0.31.2-dev
   seconds_per_case: 19.8
   total_cost: 16.2689
-  
+
 - dirname: 2023-12-16-21-24-28--editblock-gpt-4-0613-actual-main
   test_cases: 133
   model: gpt-4-0613
@@ -228,7 +229,7 @@
 - dirname: 2024-05-08-21-16-03--may-gpt-4-1106-preview-udiff
   test_cases: 133
   model: gpt-4-1106-preview
-  released: 2023-11-06  
+  released: 2023-11-06
   edit_format: udiff
   commit_hash: 87664dc
   pass_rate_1: 51.9
@@ -247,7 +248,7 @@
   versions: 0.33.1-dev
   seconds_per_case: 20.4
   total_cost: 6.6061
-  
+
 - dirname: 2024-05-01-02-09-20--gpt-4-turbo-examples
   test_cases: 133
   model: gpt-4-turbo-2024-04-09 (udiff)
@@ -270,11 +271,11 @@
   versions: 0.30.2-dev
   seconds_per_case: 22.8
   total_cost: 6.3337
-  
+
 - dirname: 2024-05-03-22-24-48--openrouter--llama3-diff-examples-sys-msg
   test_cases: 132
   model: llama3-70b-8192
-  released: 2024-04-18
+  _released: 2024-04-18
   edit_format: diff
   commit_hash: b5bb453
   pass_rate_1: 38.6
@@ -293,11 +294,11 @@
   versions: 0.31.2-dev
   seconds_per_case: 14.5
   total_cost: 0.4311
-  
+
 - dirname: 2024-05-06-18-31-08--command-r-plus-whole-final
   test_cases: 133
   model: command-r-plus
-  released: 2024-04-04
+  _released: 2024-04-04
   edit_format: whole
   commit_hash: fc3a43e-dirty
   pass_rate_1: 21.8
@@ -316,11 +317,11 @@
   versions: 0.31.2-dev
   seconds_per_case: 22.9
   total_cost: 2.7494
-  
+
 - dirname: 2024-05-07-20-32-37--qwen1.5-110b-chat-whole
   test_cases: 133
   model: qwen1.5-110b-chat
-  released: 2024-02-04  
+  released: 2024-02-04
   edit_format: whole
   commit_hash: 70b1c0c
   pass_rate_1: 30.8
@@ -339,7 +340,7 @@
   versions: 0.31.2-dev
   seconds_per_case: 46.9
   total_cost: 0.0000
-  
+
 - dirname: 2024-05-07-20-57-04--wizardlm-2-8x22b-whole
   test_cases: 133
   model: WizardLM-2 8x22B
@@ -384,7 +385,7 @@
   versions: 0.34.1-dev
   seconds_per_case: 6.0
   total_cost: 0.0000
-                                          
+
 - dirname: 2024-04-12-22-18-20--gpt-4-turbo-2024-04-09-plain-diff
   test_cases: 33
   model: gpt-4-turbo-2024-04-09 (diff)
@@ -410,6 +411,7 @@
 - dirname: 2024-06-08-22-37-55--qwen2-72b-instruct-whole
   test_cases: 133
   model: Qwen2 72B Instruct
+  released: 2024-06-08
   edit_format: whole
   commit_hash: 02c7335-dirty, 1a97498-dirty
   pass_rate_1: 44.4
@@ -568,7 +570,7 @@
   versions: 0.42.1-dev
   seconds_per_case: 17.6
   total_cost: 3.6346
-    
+
 - dirname: 2024-07-01-21-41-48--haiku-whole
   test_cases: 133
   model: claude-3-haiku-20240307
@@ -623,7 +625,7 @@
   commit_hash: d31eef3-dirty
   pass_rate_1: 40.6
   pass_rate_2: 55.6
-  released: 2024-07-18
+  _released: 2024-07-18
   percent_cases_well_formed: 100.0
   error_outputs: 1
   num_malformed_responses: 0
@@ -671,7 +673,7 @@
   commit_hash: f7ce78b-dirty
   pass_rate_1: 46.6
   pass_rate_2: 63.9
-  released: 2024-07-23
+  _released: 2024-07-23
   percent_cases_well_formed: 92.5
   error_outputs: 84
   num_malformed_responses: 19
@@ -691,6 +693,7 @@
 - dirname: 2024-07-24-06-30-29--llama-405b-whole
   test_cases: 133
   model: llama-3.1-405b-instruct (whole)
+  _released: 2024-07-23
   edit_format: whole
   commit_hash: a362dea-dirty
   pass_rate_1: 48.9
@@ -698,7 +701,6 @@
   percent_cases_well_formed: 100.0
   error_outputs: 0
   num_malformed_responses: 0
-  released: 2024-07-23
   num_with_malformed_responses: 0
   user_asks: 0
   lazy_comments: 0
@@ -770,7 +772,7 @@
   percent_cases_well_formed: 100.0
   error_outputs: 27
   num_malformed_responses: 0
-  released: 2024-07-23
+  _released: 2024-07-23
   num_with_malformed_responses: 0
   user_asks: 23
   lazy_comments: 8
@@ -796,7 +798,7 @@
   num_malformed_responses: 0
   num_with_malformed_responses: 0
   user_asks: 0
-  released: 2024-07-23
+  _released: 2024-07-23
   lazy_comments: 0
   syntax_errors: 0
   indentation_errors: 0
@@ -835,6 +837,7 @@
 - dirname: 2024-08-28-07-10-50--gemini-1.5-pro-exp-0827-diff-fenced
   test_cases: 133
   model: gemini-1.5-pro-exp-0827
+  released: 2024-08-27
   edit_format: diff-fenced
   commit_hash: d8adc75
   pass_rate_1: 54.9
@@ -946,7 +949,7 @@
   versions: 0.54.13.dev
   seconds_per_case: 8.3
   total_cost: 0.0000
-  released: 2024-09-04
+  _released: 2024-09-04
 
 - dirname: 2024-09-04-16-17-33--yi-coder-9b-chat-q4_0-whole
   test_cases: 133
@@ -973,6 +976,7 @@
 
 - dirname: 2024-09-05-14-50-11--deepseek-sep5-no-shell
   test_cases: 133
+  released: 2024-09-05
   model: DeepSeek V2.5
   edit_format: diff
   commit_hash: 1279c86
@@ -1112,6 +1116,7 @@
 - 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
@@ -1131,7 +1136,7 @@
   versions: 0.56.1.dev
   seconds_per_case: 80.9
   total_cost: 63.9190
-                                            
+
 - dirname: 2024-09-19-16-58-29--qwen2.5-coder:7b-instruct-q8_0
   test_cases: 133
   model: qwen2.5-coder:7b-instruct-q8_0
@@ -1154,7 +1159,7 @@
   versions: 0.56.0
   seconds_per_case: 9.3
   total_cost: 0.0000
-  
+
 - dirname: 2024-09-20-20-20-19--qwen-2.5-72b-instruct-diff
   test_cases: 133
   model: qwen-2.5-72b-instruct (bf16)
@@ -1204,6 +1209,7 @@
 - dirname: 2024-09-24-16-26-45--gemini-1.5-pro-002-diff-fenced
   test_cases: 133
   model: gemini-1.5-pro-002
+  released: 2024-09-24
   edit_format: diff-fenced
   commit_hash: 6b5fe9b, 3edcd71
   pass_rate_1: 49.6
@@ -1458,7 +1464,7 @@
   versions: 0.58.1.dev
   seconds_per_case: 63.7
   total_cost: 0.0000
-  
+
 - dirname: 2024-10-01-16-50-09--hermes3-whole-4
   test_cases: 133
   model: ollama/hermes3
@@ -1477,6 +1483,7 @@
 - dirname: 2024-10-04-16-30-08--chatgpt-4o-latest-diff-oct4
   test_cases: 133
   model: openai/chatgpt-4o-latest
+  released: 2024-10-04
   edit_format: diff
   commit_hash: af10953
   pass_rate_1: 56.4
@@ -1592,6 +1599,7 @@
 - dirname: 2024-10-22-17-45-28--sonnet-1022-diff-fixed-model-settings
   test_cases: 133
   model: claude-3-5-sonnet-20241022
+  released: 2024-10-22
   edit_format: diff
   commit_hash: 3b14eb9
   pass_rate_1: 69.2
@@ -1610,4 +1618,331 @@
   date: 2024-10-22
   versions: 0.59.2.dev
   seconds_per_case: 18.6
-  total_cost: 0.0000
+  total_cost: 0.0000
+
+- dirname: 2024-11-04-19-19-32--haiku35-diff-ex-as-sys-false
+  test_cases: 133
+  model: claude-3-5-haiku-20241022
+  released: 2024-10-22
+  edit_format: diff
+  commit_hash: 03bbdb0-dirty
+  pass_rate_1: 61.7
+  pass_rate_2: 75.2
+  percent_cases_well_formed: 95.5
+  error_outputs: 11
+  num_malformed_responses: 11
+  num_with_malformed_responses: 6
+  user_asks: 1
+  lazy_comments: 1
+  syntax_errors: 0
+  indentation_errors: 0
+  exhausted_context_windows: 0
+  test_timeouts: 2
+  command: aider --model anthropic/claude-3-5-haiku-20241022
+  date: 2024-11-04
+  versions: 0.61.1.dev
+  seconds_per_case: 18.4
+  total_cost: 0.0000
+
+- dirname: 2024-11-07-06-15-36--Qwen2.5.1-Coder-7B-Instruct-GGUF:Q8_0-32k-whole
+  test_cases: 133
+  model: ollama/Qwen2.5.1-Coder-7B-Instruct-GGUF:Q8_0-32k
+  edit_format: whole
+  commit_hash: e76704e
+  pass_rate_1: 52.6
+  pass_rate_2: 63.9
+  percent_cases_well_formed: 100.0
+  error_outputs: 0
+  num_malformed_responses: 0
+  num_with_malformed_responses: 0
+  user_asks: 4
+  lazy_comments: 0
+  syntax_errors: 0
+  indentation_errors: 0
+  exhausted_context_windows: 0
+  test_timeouts: 1
+  command: aider --model ollama/Qwen2.5.1-Coder-7B-Instruct-GGUF:Q8_0-32k
+  date: 2024-11-07
+  versions: 0.59.2.dev
+  seconds_per_case: 18.2
+  total_cost: 0.0000
+
+- dirname: 2024-10-29-00-29-09--Qwen2.5-Coder-0.5B-Instruct
+  test_cases: 133
+  model: Qwen2.5-Coder-0.5B-Instruct
+  edit_format: whole
+  commit_hash: 58bd375
+  pass_rate_1: 14.3
+  pass_rate_2: 14.3
+  percent_cases_well_formed: 100.0
+  error_outputs: 20
+  num_malformed_responses: 0
+  num_with_malformed_responses: 0
+  user_asks: 45
+  lazy_comments: 0
+  syntax_errors: 2
+  indentation_errors: 0
+  exhausted_context_windows: 20
+  test_timeouts: 2
+  command: aider --model openai/Qwen2.5-Coder-0.5B-Instruct
+  date: 2024-10-29
+  versions: 0.59.2.dev
+  seconds_per_case: 16.0
+  total_cost: 0.0000
+
+- dirname: 2024-11-11-19-37-01--Qwen2.5-Coder-1.5B-Instruct
+  test_cases: 133
+  model: Qwen2.5-Coder-1.5B-Instruct
+  edit_format: whole
+  commit_hash: bb5681c
+  pass_rate_1: 28.6
+  pass_rate_2: 31.6
+  percent_cases_well_formed: 100.0
+  error_outputs: 5
+  num_malformed_responses: 0
+  num_with_malformed_responses: 0
+  user_asks: 13
+  lazy_comments: 2
+  syntax_errors: 1
+  indentation_errors: 0
+  exhausted_context_windows: 5
+  test_timeouts: 2
+  command: aider --model openai/Qwen2.5-Coder-1.5B-Instruct
+  date: 2024-11-11
+  versions: 0.59.2.dev
+  seconds_per_case: 27.4
+  total_cost: 0.0000
+
+- dirname: 2024-11-04-02-25-32--Qwen2.5-Coder-3B-Instruct
+  test_cases: 133
+  model: Qwen2.5-Coder-3B-Instruct
+  edit_format: whole
+  commit_hash: 0ba3647
+  pass_rate_1: 33.8
+  pass_rate_2: 39.1
+  percent_cases_well_formed: 100.0
+  error_outputs: 4
+  num_malformed_responses: 0
+  num_with_malformed_responses: 0
+  user_asks: 3
+  lazy_comments: 0
+  syntax_errors: 0
+  indentation_errors: 0
+  exhausted_context_windows: 4
+  test_timeouts: 6
+  command: aider --model openai/Qwen2.5-Coder-3B-Instruct
+  date: 2024-11-04
+  versions: 0.59.2.dev
+  seconds_per_case: 18.7
+  total_cost: 0.0000
+
+- dirname: 2024-10-16-16-20-59--Qwen2.5-Coder-7B-Instruct
+  test_cases: 133
+  model: Qwen2.5-Coder-7B-Instruct
+  edit_format: whole
+  commit_hash: 92fe979-dirty
+  pass_rate_1: 51.9
+  pass_rate_2: 57.9
+  percent_cases_well_formed: 100.0
+  error_outputs: 2
+  num_malformed_responses: 0
+  num_with_malformed_responses: 0
+  user_asks: 2
+  lazy_comments: 0
+  syntax_errors: 0
+  indentation_errors: 0
+  exhausted_context_windows: 2
+  test_timeouts: 5
+  command: aider --model openai/Qwen2.5-Coder-7B-Instruct
+  date: 2024-10-16
+  versions: 0.59.2.dev
+  seconds_per_case: 10.5
+  total_cost: 0.0000
+
+- dirname: 2024-10-29-11-53-39--Qwen2.5-Coder-14B-Instruct
+  test_cases: 133
+  model: Qwen2.5-Coder-14B-Instruct
+  edit_format: whole
+  commit_hash: 58bd375
+  pass_rate_1: 58.6
+  pass_rate_2: 69.2
+  percent_cases_well_formed: 100.0
+  error_outputs: 3
+  num_malformed_responses: 0
+  num_with_malformed_responses: 0
+  user_asks: 2
+  lazy_comments: 0
+  syntax_errors: 0
+  indentation_errors: 0
+  exhausted_context_windows: 3
+  test_timeouts: 0
+  command: aider --model openai/Qwen2.5-Coder-14B-Instruct
+  date: 2024-10-29
+  versions: 0.59.2.dev
+  seconds_per_case: 18.3
+  total_cost: 0.0000
+
+- dirname: 2024-11-09-11-09-15--Qwen2.5-Coder-32B-Instruct
+  test_cases: 133
+  model: Qwen2.5-Coder-32B-Instruct
+  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
+  date: 2024-11-09
+  versions: 0.59.2.dev
+  seconds_per_case: 22.5
+  total_cost: 0.0000
+
+- dirname: 2024-11-20-14-57-11--mistral-2411-direct-diff
+  test_cases: 133
+  model: Mistral Large (2411)
+  released: 2024-11-18
+  edit_format: diff
+  commit_hash: dba844c
+  pass_rate_1: 46.6
+  pass_rate_2: 65.4
+  percent_cases_well_formed: 96.2
+  error_outputs: 8
+  num_malformed_responses: 8
+  num_with_malformed_responses: 5
+  user_asks: 5
+  lazy_comments: 0
+  syntax_errors: 0
+  indentation_errors: 1
+  exhausted_context_windows: 0
+  test_timeouts: 1
+  command: aider --model mistral/mistral-large-latest
+  date: 2024-11-20
+  versions: 0.63.3.dev
+  seconds_per_case: 24.9
+  total_cost: 3.2334
+
+- dirname: 2024-11-20-19-28-30--gpt-4o-2024-11-20
+  test_cases: 133
+  model: gpt-4o-2024-11-20
+  released: 2024-11-20
+  edit_format: diff
+  commit_hash: 2ac0776-dirty
+  pass_rate_1: 58.6
+  pass_rate_2: 71.4
+  percent_cases_well_formed: 99.2
+  error_outputs: 1
+  num_malformed_responses: 1
+  num_with_malformed_responses: 1
+  user_asks: 4
+  lazy_comments: 0
+  syntax_errors: 0
+  indentation_errors: 0
+  exhausted_context_windows: 0
+  test_timeouts: 5
+  command: aider --model openai/gpt-4o-2024-11-20
+  date: 2024-11-20
+  versions: 0.63.3.dev
+  seconds_per_case: 6.0
+  total_cost: 0.0000
+
+- dirname: 2024-09-20-21-47-17--qwen2.5-32b-instruct-q8_0-whole
+  test_cases: 133
+  model: ollama/qwen2.5:32b-instruct-q8_0
+  edit_format: whole
+  commit_hash: 2753ac6
+  pass_rate_1: 46.6
+  pass_rate_2: 58.6
+  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: 2
+  command: aider --model ollama/qwen2.5:32b-instruct-q8_0
+  date: 2024-09-20
+  versions: 0.56.1.dev
+  seconds_per_case: 1763.7
+  total_cost: 0.0000
+
+- dirname: 2024-11-20-15-17-37--qwen25-32b-or-diff
+  test_cases: 133
+  model: openrouter/qwen/qwen-2.5-coder-32b-instruct
+  edit_format: diff
+  commit_hash: e917424
+  pass_rate_1: 49.6
+  pass_rate_2: 65.4
+  percent_cases_well_formed: 84.2
+  error_outputs: 43
+  num_malformed_responses: 31
+  num_with_malformed_responses: 21
+  user_asks: 43
+  lazy_comments: 0
+  syntax_errors: 2
+  indentation_errors: 2
+  exhausted_context_windows: 12
+  test_timeouts: 2
+  command: aider --model openrouter/qwen/qwen-2.5-coder-32b-instruct
+  date: 2024-11-20
+  versions: 0.63.3.dev
+  seconds_per_case: 40.7
+  total_cost: 0.1497
+
+- dirname: 2024-11-21-17-46-36--gemini-exp-1121-diff
+  test_cases: 133
+  model: gemini-exp-1121
+  released: 2024-11-21
+  edit_format: diff
+  commit_hash: e94961a
+  pass_rate_1: 46.6
+  pass_rate_2: 57.9
+  percent_cases_well_formed: 83.5
+  error_outputs: 101
+  num_malformed_responses: 101
+  num_with_malformed_responses: 22
+  user_asks: 5
+  lazy_comments: 0
+  syntax_errors: 0
+  indentation_errors: 2
+  exhausted_context_windows: 0
+  test_timeouts: 3
+  command: aider --model gemini/gemini-exp-1121
+  date: 2024-11-21
+  versions: 0.63.3.dev
+  seconds_per_case: 60.3
+  total_cost: 0.0000
+
+- dirname: 2024-11-15-20-33-31--gemini-exp-1114-diff
+  test_cases: 133
+  model: gemini-exp-1114
+  released: 2024-11-14
+  edit_format: diff
+  commit_hash: 0bf17a4
+  pass_rate_1: 50.4
+  pass_rate_2: 60.9
+  percent_cases_well_formed: 85.7
+  error_outputs: 70
+  num_malformed_responses: 70
+  num_with_malformed_responses: 19
+  user_asks: 2
+  lazy_comments: 0
+  syntax_errors: 0
+  indentation_errors: 0
+  exhausted_context_windows: 0
+  test_timeouts: 4
+  command: aider --model gemini/gemini-exp-1114
+  date: 2024-11-15
+  versions: 0.63.2.dev
+  seconds_per_case: 38.6

aider/website/_data/quant.yml

@@ -0,0 +1,299 @@
+- dirname: 2024-11-09-11-09-15--Qwen2.5-Coder-32B-Instruct
+  test_cases: 133
+  model: "HuggingFace via GLHF: BF16"
+  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
+  date: 2024-11-09
+  versions: 0.59.2.dev
+  seconds_per_case: 22.5
+  total_cost: 0.0000
+
+- dirname: 2024-11-22-18-56-13--ollama-qwen2.5-coder:32b-instruct-fp16
+  test_cases: 132
+  model: "Ollama: fp16"
+  edit_format: diff
+  commit_hash: f06452c-dirty, 6a0a97c-dirty, 4e9ae16-dirty, 5506d0f-dirty
+  pass_rate_1: 58.3
+  pass_rate_2: 71.4
+  percent_cases_well_formed: 90.2
+  error_outputs: 27
+  num_malformed_responses: 26
+  num_with_malformed_responses: 13
+  user_asks: 2
+  lazy_comments: 0
+  syntax_errors: 0
+  indentation_errors: 0
+  exhausted_context_windows: 0
+  test_timeouts: 0
+  command: aider --model ollama/qwen2.5-coder:32b-instruct-fp16
+  date: 2024-11-22
+  versions: 0.64.2.dev
+  seconds_per_case: 119.6
+  total_cost: 0.0000
+  
+- dirname: 2024-11-22-14-53-26--hyperbolic-qwen25coder32binstruct
+  test_cases: 133
+  model: "Hyperbolic: BF16"
+  edit_format: diff
+  commit_hash: f9ef161, 17aef7b-dirty
+  pass_rate_1: 57.9
+  pass_rate_2: 69.2
+  percent_cases_well_formed: 91.7
+  error_outputs: 30
+  num_malformed_responses: 29
+  num_with_malformed_responses: 11
+  user_asks: 9
+  lazy_comments: 0
+  syntax_errors: 4
+  indentation_errors: 0
+  exhausted_context_windows: 0
+  test_timeouts: 2
+  command: aider --model openai/Qwen/Qwen2.5-Coder-32B-Instruct --openai-api-base https://api.hyperbolic.xyz/v1/
+  date: 2024-11-22
+  versions: 0.64.2.dev
+  seconds_per_case: 33.2
+  total_cost: 0.0000
+  
+- dirname: 2024-11-22-17-53-35--qwen25-coder-32b-Instruct-4bit
+  test_cases: 133
+  model: "mlx-community: 4bit"
+  edit_format: diff
+  commit_hash: a16dcab-dirty
+  pass_rate_1: 60.2
+  pass_rate_2: 72.2
+  percent_cases_well_formed: 88.7
+  error_outputs: 31
+  num_malformed_responses: 30
+  num_with_malformed_responses: 15
+  user_asks: 6
+  lazy_comments: 0
+  syntax_errors: 0
+  indentation_errors: 0
+  exhausted_context_windows: 1
+  test_timeouts: 0
+  command: aider --model openai/mlx-community/Qwen2.5-Coder-32B-Instruct-4bit
+  date: 2024-11-23
+  versions: 0.64.2.dev
+  seconds_per_case: 53.4
+  total_cost: 0.0000
+
+- dirname: 2024-11-23-15-07-20--qwen25-coder-32b-Instruct-8bit
+  test_cases: 133
+  model: "mlx-community: 8bit"
+  edit_format: diff
+  commit_hash: a16dcab-dirty
+  pass_rate_1: 59.4
+  pass_rate_2: 72.2
+  percent_cases_well_formed: 92.5
+  error_outputs: 20
+  num_malformed_responses: 15
+  num_with_malformed_responses: 10
+  user_asks: 7
+  lazy_comments: 0
+  syntax_errors: 0
+  indentation_errors: 0
+  exhausted_context_windows: 5
+  test_timeouts: 2
+  command: aider --model openai/mlx-community/Qwen2.5-Coder-32B-Instruct-8bit
+  date: 2024-11-23
+  versions: 0.64.2.dev
+  seconds_per_case: 98.4
+  total_cost: 0.0000
+
+- dirname: 2024-11-24-22-18-18--or-all-or-fixed-blank-messages2
+  test_cases: 133
+  model: "OpenRouter: multiple"
+  edit_format: diff
+  commit_hash: 0c59d32
+  pass_rate_1: 57.1
+  pass_rate_2: 67.7
+  percent_cases_well_formed: 95.5
+  error_outputs: 56
+  num_malformed_responses: 10
+  num_with_malformed_responses: 6
+  user_asks: 14
+  lazy_comments: 0
+  syntax_errors: 6
+  indentation_errors: 0
+  exhausted_context_windows: 3
+  test_timeouts: 1
+  command: aider --model openrouter/qwen/qwen-2.5-coder-32b-instruct
+  date: 2024-11-24
+  versions: 0.64.2.dev
+  seconds_per_case: 21.2
+  total_cost: 0.1420
+  
+- dirname: 2024-11-23-21-08-53--ollama-qwen2.5-coder:32b-instruct-q4_K_M-8kctx
+  test_cases: 133
+  model: "Ollama: q4_K_M"
+  edit_format: diff
+  commit_hash: baa1335-dirty, e63df83-dirty, ff8c1aa-dirty
+  pass_rate_1: 54.9
+  pass_rate_2: 66.9
+  percent_cases_well_formed: 94.0
+  error_outputs: 21
+  num_malformed_responses: 21
+  num_with_malformed_responses: 8
+  user_asks: 5
+  lazy_comments: 0
+  syntax_errors: 0
+  indentation_errors: 0
+  exhausted_context_windows: 0
+  test_timeouts: 3
+  command: aider --model ollama/qwen2.5-coder:32b-instruct-q4_K_M
+  date: 2024-11-23
+  versions: 0.64.2.dev
+  seconds_per_case: 35.7
+  total_cost: 0.0000
+
+- dirname: 2024-11-24-02-23-32--deepinfra-qwen-diff
+  test_cases: 133
+  model: "Deepinfra: BF16"
+  edit_format: diff
+  commit_hash: bb78e2f
+  pass_rate_1: 58.6
+  pass_rate_2: 72.2
+  percent_cases_well_formed: 94.7
+  error_outputs: 15
+  num_malformed_responses: 13
+  num_with_malformed_responses: 7
+  user_asks: 3
+  lazy_comments: 0
+  syntax_errors: 0
+  indentation_errors: 0
+  exhausted_context_windows: 2
+  test_timeouts: 3
+  command: aider --model deepinfra/Qwen/Qwen2.5-Coder-32B-Instruct
+  date: 2024-11-24
+  versions: 0.64.2.dev
+  seconds_per_case: 17.5
+  total_cost: 0.0000
+
+- dirname: 2024-11-24-04-12-58--fireworks-qwen-diff
+  test_cases: 133
+  model: "Fireworks: unknown"
+  edit_format: diff
+  commit_hash: 757eac0
+  pass_rate_1: 57.9
+  pass_rate_2: 72.2
+  percent_cases_well_formed: 94.0
+  error_outputs: 23
+  num_malformed_responses: 19
+  num_with_malformed_responses: 8
+  user_asks: 8
+  lazy_comments: 0
+  syntax_errors: 6
+  indentation_errors: 0
+  exhausted_context_windows: 4
+  test_timeouts: 1
+  command: aider --model fireworks_ai/accounts/fireworks/models/qwen2p5-coder-32b-instruct
+  date: 2024-11-24
+  versions: 0.64.2.dev
+  seconds_per_case: 10.4
+  total_cost: 0.5759
+
+- dirname: 2024-11-24-02-04-59--ollama-qwen2.5-coder:32b-instruct-q2_K-8kctx
+  test_cases: 133
+  model: "Ollama: q2_K"
+  edit_format: diff
+  commit_hash: 757eac0, bb78e2f, 8d0ba40-dirty, 1d09e96
+  pass_rate_1: 48.9
+  pass_rate_2: 61.7
+  percent_cases_well_formed: 91.7
+  error_outputs: 32
+  num_malformed_responses: 32
+  num_with_malformed_responses: 11
+  user_asks: 8
+  lazy_comments: 0
+  syntax_errors: 0
+  indentation_errors: 0
+  exhausted_context_windows: 0
+  test_timeouts: 1
+  command: aider --model ollama/qwen2.5-coder:32b-instruct-q2_K
+  date: 2024-11-24
+  versions: 0.64.2.dev
+  seconds_per_case: 97.8
+  total_cost: 0.0000
+
+- dirname: 2024-11-24-14-56-49--qwen25-32b-or-fireworks
+  test_cases: 133
+  model: "Fireworks via OpenRouter: unknown"
+  edit_format: diff
+  commit_hash: c2f184f
+  pass_rate_1: 55.6
+  pass_rate_2: 67.7
+  percent_cases_well_formed: 94.0
+  error_outputs: 39
+  num_malformed_responses: 24
+  num_with_malformed_responses: 8
+  user_asks: 13
+  lazy_comments: 0
+  syntax_errors: 1
+  indentation_errors: 1
+  exhausted_context_windows: 7
+  test_timeouts: 4
+  command: aider --model openrouter/qwen/qwen-2.5-coder-32b-instruct
+  date: 2024-11-24
+  versions: 0.64.2.dev
+  seconds_per_case: 16.1
+  total_cost: 0.1391
+
+- dirname: 2024-11-24-22-03-19--or-hyperbolic-or-fixed-blank-messages2
+  test_cases: 133
+  model: "Hyperbolic via OpenRouter: BF16"
+  edit_format: diff
+  commit_hash: 0c59d32
+  pass_rate_1: 55.6
+  pass_rate_2: 68.4
+  percent_cases_well_formed: 89.5
+  error_outputs: 28
+  num_malformed_responses: 24
+  num_with_malformed_responses: 14
+  user_asks: 29
+  lazy_comments: 0
+  syntax_errors: 1
+  indentation_errors: 0
+  exhausted_context_windows: 4
+  test_timeouts: 1
+  command: aider --model openrouter/qwen/qwen-2.5-coder-32b-instruct
+  date: 2024-11-24
+  versions: 0.64.2.dev
+  seconds_per_case: 41.5
+  total_cost: 0.1402
+  
+- dirname: 2024-11-24-15-00-50--qwen25-32b-or-deepinfra
+  test_cases: 133
+  model: "Deepinfra via OpenRouter: BF16"
+  edit_format: diff
+  commit_hash: c2f184f
+  pass_rate_1: 57.1
+  pass_rate_2: 69.9
+  percent_cases_well_formed: 89.5
+  error_outputs: 35
+  num_malformed_responses: 31
+  num_with_malformed_responses: 14
+  user_asks: 11
+  lazy_comments: 0
+  syntax_errors: 1
+  indentation_errors: 1
+  exhausted_context_windows: 4
+  test_timeouts: 1
+  command: aider --model openrouter/qwen/qwen-2.5-coder-32b-instruct
+  date: 2024-11-24
+  versions: 0.64.2.dev
+  seconds_per_case: 28.5
+  total_cost: 0.1390

aider/website/_includes/blame.md

@@ -1,5 +1,5 @@
-<canvas id="linesChart" width="800" height="360" style="margin-top: 20px"></canvas>
 <canvas id="blameChart" width="800" height="360" style="margin-top: 20px"></canvas>
+<canvas id="linesChart" width="800" height="360" style="margin-top: 20px"></canvas>
 <script src="https://cdn.jsdelivr.net/npm/chart.js"></script>
 <script src="https://cdn.jsdelivr.net/npm/moment"></script>
 <script src="https://cdn.jsdelivr.net/npm/chartjs-adapter-moment"></script>

aider/website/_includes/edit-leaderboard.js

@@ -0,0 +1,97 @@
+document.addEventListener('DOMContentLoaded', function () {
+  var ctx = document.getElementById('editChart').getContext('2d');
+  const HIGHTLIGHT_MODEL = 'no no no no';
+  var leaderboardData = {
+    labels: [],
+    datasets: [{
+      label: 'Percent completed correctly',
+      data: [],
+      backgroundColor: function(context) {
+        const label = context.chart.data.labels[context.dataIndex] || '';
+        return (label && label.includes(HIGHTLIGHT_MODEL)) ? 'rgba(255, 99, 132, 0.2)' : 'rgba(54, 162, 235, 0.2)';
+      },
+      borderColor: function(context) {
+        const label = context.chart.data.labels[context.dataIndex] || '';
+        return (label && label.includes(HIGHTLIGHT_MODEL)) ? 'rgba(255, 99, 132, 1)' : 'rgba(54, 162, 235, 1)';
+      },
+      borderWidth: 1
+    }]
+  };
+
+  var allData = [];
+  {% for row in edit_sorted %}
+    allData.push({
+      model: '{{ row.model }}',
+      pass_rate_2: {{ row.pass_rate_2 }},
+      percent_cases_well_formed: {{ row.percent_cases_well_formed }}
+    });
+  {% endfor %}
+
+  function updateChart() {
+    var selectedRows = document.querySelectorAll('tr.selected');
+    var showAll = selectedRows.length === 0;
+
+    leaderboardData.labels = [];
+    leaderboardData.datasets[0].data = [];
+
+    allData.forEach(function(row, index) {
+      var rowElement = document.getElementById('edit-row-' + index);
+      if (showAll) {
+        rowElement.classList.remove('selected');
+      }
+      if (showAll || rowElement.classList.contains('selected')) {
+        leaderboardData.labels.push(row.model);
+        leaderboardData.datasets[0].data.push(row.pass_rate_2);
+      }
+    });
+
+    leaderboardChart.update();
+  }
+
+  var tableBody = document.querySelector('table tbody');
+  allData.forEach(function(row, index) {
+    var tr = tableBody.children[index];
+    tr.id = 'edit-row-' + index;
+    tr.style.cursor = 'pointer';
+    tr.onclick = function() {
+      this.classList.toggle('selected');
+      updateChart();
+    };
+  });
+
+  var leaderboardChart = new Chart(ctx, {
+    type: 'bar',
+    data: leaderboardData,
+    options: {
+      scales: {
+        y: {
+          beginAtZero: true
+        }
+      }
+    }
+  });
+
+  updateChart();
+  
+  // Add search functionality for edit table
+  document.getElementById('editSearchInput').addEventListener('keyup', function() {
+    var searchWords = this.value.toLowerCase().split(' ').filter(word => word.length > 0);
+    var tableBody = document.querySelector('table:first-of-type tbody');
+    var rows = tableBody.getElementsByTagName('tr');
+    
+    leaderboardData.labels = [];
+    leaderboardData.datasets[0].data = [];
+    
+    for (var i = 0; i < rows.length; i++) {
+      var rowText = rows[i].textContent;
+      if (searchWords.every(word => rowText.toLowerCase().includes(word))) {
+        rows[i].style.display = '';
+        leaderboardData.labels.push(allData[i].model);
+        leaderboardData.datasets[0].data.push(allData[i].pass_rate_2);
+      } else {
+        rows[i].style.display = 'none';
+      }
+    }
+    leaderboardChart.update();
+  });
+});

aider/website/_includes/multi-line.md

@@ -1,5 +1,15 @@
 You can send long, multi-line messages in the chat in a few ways:
   - Paste a multi-line message directly into the chat.
   - Enter `{` alone on the first line to start a multiline message and `}` alone on the last line to end it.
+    - Or, start with `{tag` (where "tag" is any sequence of letters/numbers) and end with `tag}`. This is useful when you need to include closing braces `}` in your message.
   - 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.
+
+Example with a tag:
+```
+{python
+def hello():
+    print("Hello}")  # Note: contains a brace
+python}
+```

aider/website/_includes/quant-chart.js

@@ -0,0 +1,95 @@
+document.addEventListener('DOMContentLoaded', function () {
+  var ctx = document.getElementById('quantChart').getContext('2d');
+  var allData = [];
+  {% for row in site.data.quant %}
+    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: [{
+        label: 'Percent completed correctly',
+        data: filteredData.map(row => row.pass_rate_2),
+        backgroundColor: 'rgba(54, 162, 235, 0.2)',
+        borderColor: 'rgba(54, 162, 235, 1)',
+        borderWidth: 1
+      }]
+    };
+
+    if (chart) {
+      chart.data = chartData;
+      chart.update();
+    } else {
+      chart = new Chart(ctx, {
+        type: 'bar',
+        data: chartData,
+        options: {
+          plugins: {
+            legend: {
+              display: false
+            },
+            title: {
+              display: true,
+              text: 'Aider code editing benchmark',
+              font: {
+                size: 16
+              }
+            }
+          },
+          scales: {
+            y: {
+              beginAtZero: true,
+              title: {
+                display: true,
+                text: 'Percent completed correctly',
+                font: {
+                  size: 14
+                }
+              },
+              ticks: {
+                font: {
+                  size: 16
+                }
+              }
+            },
+            x: {
+              ticks: {
+                font: {
+                  size: 16
+                }
+              },
+              title: {
+                display: true,
+                text: 'Provider: quantization',
+                font: {
+                  size: 14
+                }
+              }
+            }
+          }
+        }
+      });
+    }
+  }
+
+  // Initial chart render
+  updateChart('');
+
+  // Connect search input to chart filtering
+  document.getElementById('quantSearchInput').addEventListener('keyup', function() {
+    updateChart(this.value);
+  });
+});

aider/website/_includes/refactor-leaderboard.js

@@ -0,0 +1,90 @@
+document.addEventListener('DOMContentLoaded', function () {
+  var ctx = document.getElementById('refacChart').getContext('2d');
+  var leaderboardData = {
+    labels: [],
+    datasets: [{
+      label: 'Percent completed correctly',
+      data: [],
+      backgroundColor: 'rgba(54, 162, 235, 0.2)',
+      borderColor: 'rgba(54, 162, 235, 1)',
+      borderWidth: 1
+    }]
+  };
+
+  var allData = [];
+  {% for row in refac_sorted %}
+    allData.push({
+      model: '{{ row.model }}',
+      pass_rate_1: {{ row.pass_rate_1 }},
+      percent_cases_well_formed: {{ row.percent_cases_well_formed }}
+    });
+  {% endfor %}
+
+  function updateChart() {
+    var selectedRows = document.querySelectorAll('tr.selected');
+    var showAll = selectedRows.length === 0;
+
+    leaderboardData.labels = [];
+    leaderboardData.datasets[0].data = [];
+
+    allData.forEach(function(row, index) {
+      var rowElement = document.getElementById('refac-row-' + index);
+      if (showAll) {
+        rowElement.classList.remove('selected');
+      }
+      if (showAll || rowElement.classList.contains('selected')) {
+        leaderboardData.labels.push(row.model);
+        leaderboardData.datasets[0].data.push(row.pass_rate_1);
+      }
+    });
+
+    leaderboardChart.update();
+  }
+
+  var tableBody = document.querySelectorAll('table tbody')[1];
+  allData.forEach(function(row, index) {
+    var tr = tableBody.children[index];
+    tr.id = 'refac-row-' + index;
+    tr.style.cursor = 'pointer';
+    tr.onclick = function() {
+      this.classList.toggle('selected');
+      updateChart();
+    };
+  });
+
+  var leaderboardChart = new Chart(ctx, {
+    type: 'bar',
+    data: leaderboardData,
+    options: {
+      scales: {
+        y: {
+          beginAtZero: true
+        }
+      }
+    }
+  });
+
+  updateChart();
+
+  // Add search functionality for refactoring table
+  document.getElementById('refacSearchInput').addEventListener('keyup', function() {
+    var searchWords = this.value.toLowerCase().split(' ').filter(word => word.length > 0);
+    var tableBody = document.querySelectorAll('table tbody')[1];
+    var rows = tableBody.getElementsByTagName('tr');
+    
+    leaderboardData.labels = [];
+    leaderboardData.datasets[0].data = [];
+    
+    for (var i = 0; i < rows.length; i++) {
+      var rowText = rows[i].textContent;
+      if (searchWords.every(word => rowText.toLowerCase().includes(word))) {
+        rows[i].style.display = '';
+        leaderboardData.labels.push(allData[i].model);
+        leaderboardData.datasets[0].data.push(allData[i].pass_rate_1);
+      } else {
+        rows[i].style.display = 'none';
+      }
+    }
+    leaderboardChart.update();
+  });
+});

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

@@ -12,6 +12,10 @@ nav_exclude: true
 
 [![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).
+
 The
 [aider git repo](https://github.com/Aider-AI/aider)
 currently contains about 4K commits and 14K lines of code.

aider/website/_posts/2024-11-21-quantization.md

@@ -0,0 +1,169 @@
+---
+title: Details matter with open source models
+excerpt: Open source LLMs are becoming very powerful, but pay attention to how you (or your provider) are serving the model. It can affect code editing skill.
+highlight_image: /assets/quantization.jpg
+draft: false
+nav_exclude: true
+---
+{% if page.date %}
+<p class="post-date">{{ page.date | date: "%B %d, %Y" }}</p>
+{% endif %}
+
+# Details matter with open source models
+{: .no_toc }
+
+Open source models like Qwen 2.5 32B Instruct are performing very well on
+aider's code editing benchmark, rivaling closed source frontier models.
+
+But pay attention to how your model is being served and quantized, 
+as it can impact code editing skill.
+Open source models are often available at a variety of quantizations,
+and can be served with different token limits.
+These details matter when working with code.
+
+The graph and table below compares different versions of the Qwen 2.5 Coder 32B Instruct model,
+served both locally and from a variety of cloud providers.
+
+- The [HuggingFace BF16 weights](https://huggingface.co/Qwen/Qwen2.5-Coder-32B-Instruct) served via [glhf.chat](https://glhf.chat).
+- [4bit and 8bit quants for mlx](https://t.co/cwX3DYX35D).
+- The results from [OpenRouter's mix of providers](https://openrouter.ai/qwen/qwen-2.5-coder-32b-instruct/providers) which serve the model with different levels of quantization.
+- Results from individual providers served via OpenRouter and directly to their own APIs.
+- Ollama locally serving different quantizations from the [Ollama model library](https://ollama.com/library/qwen2.5-coder:32b-instruct-q4_K_M).
+
+The best versions of the model rival GPT-4o, while the worst performer
+is more like the older GPT-4 Turbo.
+Suboptimal choices in quantization and token limits can
+easily produce far worse results.
+
+This benchmarking effort highlighted a number of pitfalls and details which
+can have a significant impact on the model's ability to correctly edit code:
+
+- Quantization -- Open source models are often available at dozens of different quantizations.
+- Context window -- Cloud providers can decide how large a context window to accept,
+and they often choose differently. Ollama defaults to a tiny 2k context window,
+and silently discards data that exceeds it.
+- Output token limits -- Open source models are often served with wildly
+differing output token limits. This has a direct impact on how much code the
+model can write or edit in a response.
+- Buggy cloud providers -- Between Qwen and DeepSeep, there were
+multiple cloud providers with broken or buggy API endpoints that seemed
+to be returning result different from expected based on the advertised
+quantization and context sizes.
+
+
+### Sections
+{: .no_toc }
+
+- TOC
+{:toc}
+
+## Benchmark results
+
+<canvas id="quantChart" width="800" height="600" style="margin: 20px 0"></canvas>
+<script src="https://cdn.jsdelivr.net/npm/chart.js"></script>
+<script>
+{% include quant-chart.js %}
+</script>
+
+<input type="text" id="quantSearchInput" placeholder="Search..." style="width: 100%; max-width: 800px; margin: 10px auto; padding: 8px; display: block; border: 1px solid #ddd; border-radius: 4px;">
+
+<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 quant_sorted = site.data.quant | sort: 'pass_rate_2' | reverse %}
+    {% for row in quant_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('quantSearchInput').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>
+
+## Setting Ollama's context window size
+
+[Ollama uses a 2k context window by default](https://github.com/ollama/ollama/blob/main/docs/faq.md#how-can-i-specify-the-context-window-size),
+which is very small for working with aider.
+Unlike most other LLM servers, Ollama does not throw an error if you submit
+a request that exceeds the context window.
+Instead, it just silently truncates the request by discarding the "oldest" messages
+in the chat to make it fit within the context window.
+
+All of the Ollama results above were collected with at least an 8k context window, which
+is large enough to attempt all the coding problems in the benchmark.
+Aider sets Ollama's context window to 8k by default.
+
+You can change the Ollama server's context window with a 
+[`.aider.model.settings.yml` file](https://aider.chat/docs/config/adv-model-settings.html#model-settings)
+like this:
+
+```
+- name: ollama/qwen2.5-coder:32b-instruct-fp16
+  extra_params:
+    num_ctx: 8192
+```
+
+## Choosing providers with OpenRouter
+
+OpenRouter allows you to ignore specific providers in your
+[preferences](https://openrouter.ai/settings/preferences).
+This can be used to limit your OpenRouter requests to be
+served by only your preferred providers.
+
+## Notes
+
+This article went through many revisions as I received feedback from
+numerous members of the community.
+Here are some of the noteworthy learnings and changes:
+
+- The first version of this article included incorrect Ollama models.
+- Earlier Ollama results used the too small default 2k context window,
+artificially harming the benchmark results.
+- The benchmark results appear to have uncovered a problem in the way
+OpenRouter was communicating with Hyperbolic.
+They fixed the issue 11/24/24, shortly after it was pointed out.

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

@@ -32,6 +32,9 @@
 ## Use claude-3-5-sonnet-20241022 model for the main chat
 #sonnet: false
 
+## Use claude-3-5-haiku-20241022 model for the main chat
+#haiku: false
+
 ## Use gpt-4-0613 model for the main chat
 #4: false
 
@@ -83,6 +86,14 @@
 ## Specify a file with context window and costs for unknown models
 #model-metadata-file: .aider.model.metadata.json
 
+## Add a model alias (can be used multiple times)
+#alias: xxx
+## Specify multiple values like this:
+#alias:
+#  - xxx
+#  - yyy
+#  - zzz
+
 ## Verify the SSL cert when connecting to models (default: True)
 #verify-ssl: true
 
@@ -268,8 +279,8 @@
 ############
 # Analytics:
 
-## Enable/disable analytics for one session (default: False)
-#analytics: false
+## Enable/disable analytics for current session (default: random)
+#analytics: xxx
 
 ## Specify a file to log analytics events
 #analytics-log: xxx
@@ -311,6 +322,9 @@
 ## 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
 
@@ -320,6 +334,9 @@
 ## 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
 
@@ -359,6 +376,12 @@
 ## Enable/disable fancy input with history and completion (default: True)
 #fancy-input: true
 
+## 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:
 

aider/website/assets/sample.env

@@ -36,6 +36,9 @@
 ## Use claude-3-5-sonnet-20241022 model for the main chat
 #AIDER_SONNET=
 
+## Use claude-3-5-haiku-20241022 model for the main chat
+#AIDER_HAIKU=
+
 ## Use gpt-4-0613 model for the main chat
 #AIDER_4=
 
@@ -87,6 +90,9 @@
 ## Specify a file with context window and costs for unknown models
 #AIDER_MODEL_METADATA_FILE=.aider.model.metadata.json
 
+## Add a model alias (can be used multiple times)
+#AIDER_ALIAS=
+
 ## Verify the SSL cert when connecting to models (default: True)
 #AIDER_VERIFY_SSL=true
 
@@ -267,8 +273,8 @@
 ############
 # Analytics:
 
-## Enable/disable analytics for one session (default: False)
-#AIDER_ANALYTICS=false
+## Enable/disable analytics for current session (default: random)
+#AIDER_ANALYTICS=
 
 ## Specify a file to log analytics events
 #AIDER_ANALYTICS_LOG=
@@ -297,6 +303,9 @@
 ## Check for new aider versions on launch
 #AIDER_CHECK_UPDATE=true
 
+## Show release notes on first run of new version (default: None, ask user)
+#AIDER_SHOW_RELEASE_NOTES=
+
 ## Install the latest version from the main branch
 #AIDER_INSTALL_MAIN_BRANCH=false
 
@@ -306,6 +315,9 @@
 ## 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=
 
@@ -342,6 +354,12 @@
 ## Enable/disable fancy input with history and completion (default: True)
 #AIDER_FANCY_INPUT=true
 
+## 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=
+
 #################
 # Voice Settings:
 

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

@@ -11,6 +11,13 @@ description: Configuring advanced settings for LLMs.
 In most cases, you can safely ignore aider's warning about unknown context
 window size and model costs.
 
+{: .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
+for unusual models.
+
 But, you can register context window limits and costs for models that aren't known
 to aider. Create a `.aider.model.metadata.json` file in one of these locations:
 
@@ -55,8 +62,10 @@ These model settings are pre-configured for most popular models.
 But it can sometimes be helpful to override them or add settings for
 a model that aider doesn't know about.
 
-To do that,
-create a `.aider.model.settings.yml` file in one of these locations:
+
+### Configuration file locations
+
+You can override or add settings for any model by creating a `.aider.model.settings.yml` file in one of these locations:
 
 - Your home directory.
 - The root if your git repo.
@@ -66,9 +75,31 @@ create a `.aider.model.settings.yml` file in one of these locations:
 If the files above exist, they will be loaded in that order. 
 Files loaded last will take priority.
 
-The yaml file should be a a list of dictionary objects for each model.
-For example, below are all the pre-configured model settings
-to give a sense for the settings which are supported.
+The yaml file should be a list of dictionary objects for each model.
+
+
+### Global extra params
+
+You can use the special model name `aider/extra_params` to define 
+`extra_params` that will be passed to `litellm.completion()` for all models.
+Only the `extra_params` dict is used from this special model name.
+
+For example:
+
+```yaml
+- name: aider/extra_params
+  extra_params:
+    extra_headers:
+      Custom-Header: value
+    max_tokens: 8192
+```
+
+These settings will be merged with any model-specific settings, with the 
+`aider/extra_params` settings taking precedence for any direct conflicts.
+
+### Example model settings
+
+Below are all the pre-configured model settings to give a sense for the settings which are supported.
 
 You can also look at the `ModelSettings` class in
 [models.py](https://github.com/Aider-AI/aider/blob/main/aider/models.py)
@@ -241,6 +272,38 @@ cog.out("```\n")
   use_system_prompt: true
   use_temperature: true
   weak_model_name: gpt-4o-mini
+- 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: true
+  name: gpt-4o-2024-11-20
+  reminder: sys
+  send_undo_reply: false
+  streaming: true
+  use_repo_map: true
+  use_system_prompt: true
+  use_temperature: true
+  weak_model_name: gpt-4o-mini
+- 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: true
+  name: openai/gpt-4o-2024-11-20
+  reminder: sys
+  send_undo_reply: false
+  streaming: true
+  use_repo_map: true
+  use_system_prompt: true
+  use_temperature: true
+  weak_model_name: gpt-4o-mini
 - cache_control: false
   caches_by_default: false
   edit_format: diff
@@ -400,7 +463,7 @@ cog.out("```\n")
   use_repo_map: true
   use_system_prompt: true
   use_temperature: true
-  weak_model_name: claude-3-haiku-20240307
+  weak_model_name: claude-3-5-haiku-20241022
 - cache_control: false
   caches_by_default: false
   edit_format: diff
@@ -416,7 +479,7 @@ cog.out("```\n")
   use_repo_map: true
   use_system_prompt: true
   use_temperature: true
-  weak_model_name: openrouter/anthropic/claude-3-haiku
+  weak_model_name: openrouter/anthropic/claude-3-5-haiku
 - cache_control: false
   caches_by_default: false
   edit_format: whole
@@ -432,7 +495,7 @@ cog.out("```\n")
   use_repo_map: false
   use_system_prompt: true
   use_temperature: true
-  weak_model_name: claude-3-haiku-20240307
+  weak_model_name: claude-3-5-haiku-20241022
 - cache_control: true
   caches_by_default: false
   edit_format: diff
@@ -451,7 +514,7 @@ cog.out("```\n")
   use_repo_map: true
   use_system_prompt: true
   use_temperature: true
-  weak_model_name: claude-3-haiku-20240307
+  weak_model_name: claude-3-5-haiku-20241022
 - cache_control: true
   caches_by_default: false
   edit_format: diff
@@ -470,7 +533,7 @@ cog.out("```\n")
   use_repo_map: true
   use_system_prompt: true
   use_temperature: true
-  weak_model_name: anthropic/claude-3-haiku-20240307
+  weak_model_name: anthropic/claude-3-5-haiku-20241022
 - cache_control: true
   caches_by_default: false
   edit_format: diff
@@ -489,7 +552,26 @@ cog.out("```\n")
   use_repo_map: true
   use_system_prompt: true
   use_temperature: true
-  weak_model_name: anthropic/claude-3-haiku-20240307
+  weak_model_name: anthropic/claude-3-5-haiku-20241022
+- cache_control: true
+  caches_by_default: false
+  edit_format: diff
+  editor_edit_format: editor-diff
+  editor_model_name: bedrock/anthropic.claude-3-5-sonnet-20241022-v2:0
+  examples_as_sys_msg: true
+  extra_params:
+    extra_headers:
+      anthropic-beta: prompt-caching-2024-07-31
+    max_tokens: 8192
+  lazy: false
+  name: bedrock/anthropic.claude-3-5-sonnet-20241022-v2:0
+  reminder: user
+  send_undo_reply: false
+  streaming: true
+  use_repo_map: true
+  use_system_prompt: true
+  use_temperature: true
+  weak_model_name: bedrock/anthropic.claude-3-5-haiku-20241022-v1:0
 - cache_control: true
   caches_by_default: false
   edit_format: diff
@@ -508,7 +590,7 @@ cog.out("```\n")
   use_repo_map: true
   use_system_prompt: true
   use_temperature: true
-  weak_model_name: anthropic/claude-3-haiku-20240307
+  weak_model_name: anthropic/claude-3-5-haiku-20241022
 - cache_control: true
   caches_by_default: false
   edit_format: diff
@@ -527,7 +609,7 @@ cog.out("```\n")
   use_repo_map: true
   use_system_prompt: true
   use_temperature: true
-  weak_model_name: claude-3-haiku-20240307
+  weak_model_name: claude-3-5-haiku-20241022
 - cache_control: true
   caches_by_default: false
   edit_format: whole
@@ -546,6 +628,77 @@ cog.out("```\n")
   use_system_prompt: true
   use_temperature: true
   weak_model_name: anthropic/claude-3-haiku-20240307
+- cache_control: true
+  caches_by_default: false
+  edit_format: diff
+  editor_edit_format: null
+  editor_model_name: null
+  examples_as_sys_msg: false
+  extra_params:
+    extra_headers:
+      anthropic-beta: prompt-caching-2024-07-31
+  lazy: false
+  name: anthropic/claude-3-5-haiku-20241022
+  reminder: user
+  send_undo_reply: false
+  streaming: true
+  use_repo_map: true
+  use_system_prompt: true
+  use_temperature: true
+  weak_model_name: anthropic/claude-3-5-haiku-20241022
+- cache_control: true
+  caches_by_default: false
+  edit_format: diff
+  editor_edit_format: null
+  editor_model_name: null
+  examples_as_sys_msg: false
+  extra_params:
+    extra_headers:
+      anthropic-beta: prompt-caching-2024-07-31
+  lazy: false
+  name: bedrock/anthropic.claude-3-5-haiku-20241022-v1:0
+  reminder: user
+  send_undo_reply: false
+  streaming: true
+  use_repo_map: true
+  use_system_prompt: true
+  use_temperature: true
+  weak_model_name: bedrock/anthropic.claude-3-5-haiku-20241022-v1:0
+- cache_control: true
+  caches_by_default: false
+  edit_format: diff
+  editor_edit_format: null
+  editor_model_name: null
+  examples_as_sys_msg: true
+  extra_params:
+    extra_headers:
+      anthropic-beta: prompt-caching-2024-07-31
+  lazy: false
+  name: claude-3-5-haiku-20241022
+  reminder: user
+  send_undo_reply: false
+  streaming: true
+  use_repo_map: true
+  use_system_prompt: true
+  use_temperature: true
+  weak_model_name: claude-3-5-haiku-20241022
+- 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:
+    max_tokens: 4096
+  lazy: false
+  name: vertex_ai/claude-3-5-haiku@20241022
+  reminder: user
+  send_undo_reply: false
+  streaming: true
+  use_repo_map: true
+  use_system_prompt: true
+  use_temperature: true
+  weak_model_name: vertex_ai/claude-3-5-haiku@20241022
 - cache_control: true
   caches_by_default: false
   edit_format: whole
@@ -580,7 +733,7 @@ cog.out("```\n")
   use_repo_map: true
   use_system_prompt: true
   use_temperature: true
-  weak_model_name: openrouter/anthropic/claude-3-haiku
+  weak_model_name: openrouter/anthropic/claude-3-5-haiku
 - cache_control: true
   caches_by_default: false
   edit_format: diff
@@ -597,7 +750,7 @@ cog.out("```\n")
   use_repo_map: true
   use_system_prompt: true
   use_temperature: true
-  weak_model_name: openrouter/anthropic/claude-3-haiku:beta
+  weak_model_name: openrouter/anthropic/claude-3-5-haiku:beta
 - cache_control: false
   caches_by_default: false
   edit_format: diff
@@ -614,7 +767,7 @@ cog.out("```\n")
   use_repo_map: true
   use_system_prompt: true
   use_temperature: true
-  weak_model_name: vertex_ai/claude-3-haiku@20240307
+  weak_model_name: vertex_ai/claude-3-5-haiku@20241022
 - cache_control: false
   caches_by_default: false
   edit_format: diff
@@ -631,7 +784,7 @@ cog.out("```\n")
   use_repo_map: true
   use_system_prompt: true
   use_temperature: true
-  weak_model_name: vertex_ai/claude-3-haiku@20240307
+  weak_model_name: vertex_ai/claude-3-5-haiku@20241022
 - cache_control: false
   caches_by_default: false
   edit_format: diff
@@ -647,7 +800,7 @@ cog.out("```\n")
   use_repo_map: true
   use_system_prompt: true
   use_temperature: true
-  weak_model_name: vertex_ai/claude-3-haiku@20240307
+  weak_model_name: vertex_ai/claude-3-5-haiku@20241022
 - cache_control: false
   caches_by_default: false
   edit_format: whole
@@ -663,7 +816,7 @@ cog.out("```\n")
   use_repo_map: false
   use_system_prompt: true
   use_temperature: true
-  weak_model_name: vertex_ai/claude-3-haiku@20240307
+  weak_model_name: vertex_ai/claude-3-5-haiku@20241022
 - cache_control: false
   caches_by_default: false
   edit_format: whole
@@ -824,6 +977,22 @@ cog.out("```\n")
   use_system_prompt: true
   use_temperature: true
   weak_model_name: null
+- cache_control: false
+  caches_by_default: false
+  edit_format: diff-fenced
+  editor_edit_format: null
+  editor_model_name: null
+  examples_as_sys_msg: false
+  extra_params: null
+  lazy: false
+  name: vertex_ai/gemini-pro-experimental
+  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: whole
@@ -951,7 +1120,7 @@ cog.out("```\n")
   name: openai/o1-mini
   reminder: user
   send_undo_reply: false
-  streaming: false
+  streaming: true
   use_repo_map: true
   use_system_prompt: false
   use_temperature: false
@@ -967,7 +1136,7 @@ cog.out("```\n")
   name: azure/o1-mini
   reminder: user
   send_undo_reply: false
-  streaming: false
+  streaming: true
   use_repo_map: true
   use_system_prompt: false
   use_temperature: false
@@ -983,7 +1152,7 @@ cog.out("```\n")
   name: o1-mini
   reminder: user
   send_undo_reply: false
-  streaming: false
+  streaming: true
   use_repo_map: true
   use_system_prompt: false
   use_temperature: false
@@ -999,7 +1168,7 @@ cog.out("```\n")
   name: openai/o1-preview
   reminder: user
   send_undo_reply: false
-  streaming: false
+  streaming: true
   use_repo_map: true
   use_system_prompt: false
   use_temperature: false
@@ -1015,7 +1184,7 @@ cog.out("```\n")
   name: azure/o1-preview
   reminder: user
   send_undo_reply: false
-  streaming: false
+  streaming: true
   use_repo_map: true
   use_system_prompt: false
   use_temperature: false
@@ -1031,7 +1200,7 @@ cog.out("```\n")
   name: o1-preview
   reminder: user
   send_undo_reply: false
-  streaming: false
+  streaming: true
   use_repo_map: true
   use_system_prompt: false
   use_temperature: false
@@ -1068,6 +1237,22 @@ cog.out("```\n")
   use_system_prompt: false
   use_temperature: false
   weak_model_name: openrouter/openai/gpt-4o-mini
+- cache_control: false
+  caches_by_default: false
+  edit_format: diff
+  editor_edit_format: editor-diff
+  editor_model_name: openrouter/qwen/qwen-2.5-coder-32b-instruct
+  examples_as_sys_msg: false
+  extra_params: null
+  lazy: false
+  name: openrouter/qwen/qwen-2.5-coder-32b-instruct
+  reminder: user
+  send_undo_reply: false
+  streaming: true
+  use_repo_map: true
+  use_system_prompt: true
+  use_temperature: true
+  weak_model_name: openrouter/qwen/qwen-2.5-coder-32b-instruct
 ```
 <!--[[[end]]]-->
 

aider/website/docs/config/aider_conf.md

@@ -88,6 +88,9 @@ cog.outl("```")
 ## Use claude-3-5-sonnet-20241022 model for the main chat
 #sonnet: false
 
+## Use claude-3-5-haiku-20241022 model for the main chat
+#haiku: false
+
 ## Use gpt-4-0613 model for the main chat
 #4: false
 
@@ -139,6 +142,14 @@ cog.outl("```")
 ## Specify a file with context window and costs for unknown models
 #model-metadata-file: .aider.model.metadata.json
 
+## Add a model alias (can be used multiple times)
+#alias: xxx
+## Specify multiple values like this:
+#alias:
+#  - xxx
+#  - yyy
+#  - zzz
+
 ## Verify the SSL cert when connecting to models (default: True)
 #verify-ssl: true
 
@@ -324,8 +335,8 @@ cog.outl("```")
 ############
 # Analytics:
 
-## Enable/disable analytics for one session (default: False)
-#analytics: false
+## Enable/disable analytics for current session (default: random)
+#analytics: xxx
 
 ## Specify a file to log analytics events
 #analytics-log: xxx
@@ -367,6 +378,9 @@ cog.outl("```")
 ## 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
 
@@ -376,6 +390,9 @@ cog.outl("```")
 ## 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
 
@@ -415,6 +432,12 @@ cog.outl("```")
 ## Enable/disable fancy input with history and completion (default: True)
 #fancy-input: true
 
+## 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:
 

aider/website/docs/config/dotenv.md

@@ -78,6 +78,9 @@ cog.outl("```")
 ## Use claude-3-5-sonnet-20241022 model for the main chat
 #AIDER_SONNET=
 
+## Use claude-3-5-haiku-20241022 model for the main chat
+#AIDER_HAIKU=
+
 ## Use gpt-4-0613 model for the main chat
 #AIDER_4=
 
@@ -129,6 +132,9 @@ cog.outl("```")
 ## Specify a file with context window and costs for unknown models
 #AIDER_MODEL_METADATA_FILE=.aider.model.metadata.json
 
+## Add a model alias (can be used multiple times)
+#AIDER_ALIAS=
+
 ## Verify the SSL cert when connecting to models (default: True)
 #AIDER_VERIFY_SSL=true
 
@@ -309,8 +315,8 @@ cog.outl("```")
 ############
 # Analytics:
 
-## Enable/disable analytics for one session (default: False)
-#AIDER_ANALYTICS=false
+## Enable/disable analytics for current session (default: random)
+#AIDER_ANALYTICS=
 
 ## Specify a file to log analytics events
 #AIDER_ANALYTICS_LOG=
@@ -339,6 +345,9 @@ cog.outl("```")
 ## Check for new aider versions on launch
 #AIDER_CHECK_UPDATE=true
 
+## Show release notes on first run of new version (default: None, ask user)
+#AIDER_SHOW_RELEASE_NOTES=
+
 ## Install the latest version from the main branch
 #AIDER_INSTALL_MAIN_BRANCH=false
 
@@ -348,6 +357,9 @@ cog.outl("```")
 ## 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=
 
@@ -384,6 +396,12 @@ cog.outl("```")
 ## Enable/disable fancy input with history and completion (default: True)
 #AIDER_FANCY_INPUT=true
 
+## 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=
+
 #################
 # Voice Settings:
 

aider/website/docs/config/editor.md

@@ -0,0 +1,127 @@
+---
+parent: Configuration
+nav_order: 15
+description: How to configure a custom editor for aider's /editor command
+---
+
+# Editor configuration
+
+Aider allows you to configure your preferred text editor for use with the `/editor` command. The editor must be capable of running in "blocking mode", meaning the command line will wait until you close the editor before proceeding.
+
+## Using `--editor`
+
+You can specify the text editor with the `--editor` switch or using
+`editor:` in aider's
+[yaml config file](https://aider.chat/docs/config/aider_conf.html).
+
+## Environment variables
+
+Aider checks the following environment variables in order to determine which editor to use:
+
+1. `AIDER_EDITOR`
+2. `VISUAL`
+3. `EDITOR`
+
+## Default behavior
+
+If no editor is configured, aider will use these platform-specific defaults:
+
+- Windows: `notepad`
+- macOS: `vim`
+- Linux/Unix: `vi`
+
+## Using a custom editor
+
+You can set your preferred editor in your shell's configuration file (e.g., `.bashrc`, `.zshrc`):
+
+```bash
+export AIDER_EDITOR=vim
+```
+
+## Popular Editors by Platform
+
+### macOS
+
+1. **vim**
+   ```bash
+   export AIDER_EDITOR=vim
+   ```
+
+2. **Emacs**
+   ```bash
+   export AIDER_EDITOR=emacs
+   ```
+
+3. **VSCode**
+   ```bash
+   export AIDER_EDITOR="code --wait"
+   ```
+
+4. **Sublime Text**
+   ```bash
+   export AIDER_EDITOR="subl --wait"
+   ```
+
+5. **BBEdit**
+   ```bash
+   export AIDER_EDITOR="bbedit --wait"
+   ```
+
+### Linux
+
+1. **vim**
+   ```bash
+   export AIDER_EDITOR=vim
+   ```
+
+2. **Emacs**
+   ```bash
+   export AIDER_EDITOR=emacs
+   ```
+
+3. **nano**
+   ```bash
+   export AIDER_EDITOR=nano
+   ```
+
+4. **VSCode**
+   ```bash
+   export AIDER_EDITOR="code --wait"
+   ```
+
+5. **Sublime Text**
+   ```bash
+   export AIDER_EDITOR="subl --wait"
+   ```
+
+### Windows
+
+1. **Notepad**
+   ```bat
+   set AIDER_EDITOR=notepad
+   ```
+
+2. **VSCode**
+   ```bat
+   set AIDER_EDITOR="code --wait"
+   ```
+
+3. **Notepad++**
+   ```bat
+   set AIDER_EDITOR="notepad++ -multiInst -notabbar -nosession -noPlugin -waitForClose"
+   ```
+
+## Editor command arguments
+
+Some editors require specific command-line arguments to operate in blocking mode. The `--wait` flag (or equivalent) is commonly used to make the editor block until the file is closed.
+
+## Troubleshooting
+
+If you encounter issues with your editor not blocking (returning to the prompt immediately), verify that:
+
+1. Your editor supports blocking mode
+2. You've included the necessary command-line arguments for blocking mode
+3. The editor command is properly quoted if it contains spaces or special characters, e.g.:
+   ```bash
+   export AIDER_EDITOR="code --wait"
+   ```

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

@@ -0,0 +1,72 @@
+---
+parent: Configuration
+nav_order: 1000
+description: Assign convenient short names to models.
+---
+
+# Model Aliases
+
+Model aliases allow you to create shorthand names for models you frequently use. This is particularly useful for models with long names or when you want to standardize model usage across your team.
+
+## Command Line Usage
+
+You can define aliases when launching aider using the `--alias` option:
+
+```bash
+aider --alias "fast:gpt-3.5-turbo" --alias "smart:gpt-4"
+```
+
+Multiple aliases can be defined by using the `--alias` option multiple times. Each alias definition should be in the format `alias:model-name`.
+
+## Configuration File
+
+You can also define aliases in your [`.aider.conf.yml` file](https://aider.chat/docs/config/aider_conf.html):
+
+```yaml
+alias:
+  - "fast:gpt-3.5-turbo"
+  - "smart:gpt-4"
+  - "hacker:claude-3-sonnet-20240229"
+```
+
+## Using Aliases
+
+Once defined, you can use the alias instead of the full model name:
+
+```bash
+aider --model fast  # Uses gpt-3.5-turbo
+aider --model smart  # Uses gpt-4
+```
+
+## Built-in Aliases
+
+Aider includes some built-in aliases for convenience:
+
+<!--[[[cog
+import cog
+from aider.models import MODEL_ALIASES
+
+for alias, model in sorted(MODEL_ALIASES.items()):
+    cog.outl(f"- `{alias}`: {model}")
+]]]-->
+- `3`: gpt-3.5-turbo
+- `35-turbo`: gpt-3.5-turbo
+- `35turbo`: gpt-3.5-turbo
+- `4`: gpt-4-0613
+- `4-turbo`: gpt-4-1106-preview
+- `4o`: gpt-4o-2024-08-06
+- `deepseek`: deepseek/deepseek-coder
+- `haiku`: claude-3-haiku-20241022
+- `opus`: claude-3-opus-20240229
+- `sonnet`: claude-3-sonnet-20241022
+<!--[[[end]]]-->
+
+## Priority
+
+If the same alias is defined in multiple places, the priority is:
+
+1. Command line aliases (highest priority)
+2. Configuration file aliases
+3. Built-in aliases (lowest priority)
+
+This allows you to override built-in aliases with your own preferences.

aider/website/docs/config/options.md

@@ -26,15 +26,15 @@ cog.out(get_md_help())
 ]]]-->
 ```
 usage: aider [-h] [--openai-api-key] [--anthropic-api-key] [--model]
-             [--opus] [--sonnet] [--4] [--4o] [--mini] [--4-turbo]
-             [--35turbo] [--deepseek] [--o1-mini] [--o1-preview]
-             [--list-models] [--openai-api-base] [--openai-api-type]
-             [--openai-api-version] [--openai-api-deployment-id]
-             [--openai-organization-id] [--model-settings-file]
-             [--model-metadata-file]
-             [--verify-ssl | --no-verify-ssl] [--edit-format]
-             [--architect] [--weak-model] [--editor-model]
-             [--editor-edit-format]
+             [--opus] [--sonnet] [--haiku] [--4] [--4o] [--mini]
+             [--4-turbo] [--35turbo] [--deepseek] [--o1-mini]
+             [--o1-preview] [--list-models] [--openai-api-base]
+             [--openai-api-type] [--openai-api-version]
+             [--openai-api-deployment-id] [--openai-organization-id]
+             [--model-settings-file] [--model-metadata-file]
+             [--alias] [--verify-ssl | --no-verify-ssl]
+             [--edit-format] [--architect] [--weak-model]
+             [--editor-model] [--editor-edit-format]
              [--show-model-warnings | --no-show-model-warnings]
              [--max-chat-history-tokens] [--env-file]
              [--cache-prompts | --no-cache-prompts]
@@ -66,14 +66,16 @@ usage: aider [-h] [--openai-api-key] [--anthropic-api-key] [--model]
              [--analytics-disable] [--file] [--read] [--vim]
              [--chat-language] [--version] [--just-check-update]
              [--check-update | --no-check-update]
+             [--show-release-notes | --no-show-release-notes]
              [--install-main-branch] [--upgrade] [--apply]
-             [--yes-always] [-v] [--show-repo-map] [--show-prompts]
-             [--exit] [--message] [--message-file] [--load]
-             [--encoding] [-c]
+             [--apply-clipboard-edits] [--yes-always] [-v]
+             [--show-repo-map] [--show-prompts] [--exit] [--message]
+             [--message-file] [--load] [--encoding] [-c]
              [--gui | --no-gui | --browser | --no-browser]
              [--suggest-shell-commands | --no-suggest-shell-commands]
-             [--fancy-input | --no-fancy-input] [--voice-format]
-             [--voice-language]
+             [--fancy-input | --no-fancy-input]
+             [--detect-urls | --no-detect-urls] [--editor]
+             [--voice-format] [--voice-language]
 
 ```
 
@@ -107,6 +109,10 @@ Environment variable: `AIDER_OPUS`
 Use claude-3-5-sonnet-20241022 model for the main chat  
 Environment variable: `AIDER_SONNET`  
 
+### `--haiku`
+Use claude-3-5-haiku-20241022 model for the main chat  
+Environment variable: `AIDER_HAIKU`  
+
 ### `--4`
 Use gpt-4-0613 model for the main chat  
 Environment variable: `AIDER_4`  
@@ -186,6 +192,10 @@ Specify a file with context window and costs for unknown models
 Default: .aider.model.metadata.json  
 Environment variable: `AIDER_MODEL_METADATA_FILE`  
 
+### `--alias ALIAS:MODEL`
+Add a model alias (can be used multiple times)  
+Environment variable: `AIDER_ALIAS`  
+
 ### `--verify-ssl`
 Verify the SSL cert when connecting to models (default: True)  
 Default: True  
@@ -506,8 +516,7 @@ Environment variable: `AIDER_TEST`
 ## Analytics:
 
 ### `--analytics`
-Enable/disable analytics for one session (default: False)  
-Default: False  
+Enable/disable analytics for current session (default: random)  
 Environment variable: `AIDER_ANALYTICS`  
 Aliases:
   - `--analytics`
@@ -557,6 +566,13 @@ Aliases:
   - `--check-update`
   - `--no-check-update`
 
+### `--show-release-notes`
+Show release notes on first run of new version (default: None, ask user)  
+Environment variable: `AIDER_SHOW_RELEASE_NOTES`  
+Aliases:
+  - `--show-release-notes`
+  - `--no-show-release-notes`
+
 ### `--install-main-branch`
 Install the latest version from the main branch  
 Default: False  
@@ -574,6 +590,11 @@ Aliases:
 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`  
+
 ### `--yes-always`
 Always say yes to every confirmation  
 Environment variable: `AIDER_YES_ALWAYS`  
@@ -657,6 +678,18 @@ Aliases:
   - `--fancy-input`
   - `--no-fancy-input`
 
+### `--detect-urls`
+Enable/disable detection and offering to add URLs to chat (default: True)  
+Default: True  
+Environment variable: `AIDER_DETECT_URLS`  
+Aliases:
+  - `--detect-urls`
+  - `--no-detect-urls`
+
+### `--editor VALUE`
+Specify which editor to use for the /editor command  
+Environment variable: `AIDER_EDITOR`  
+
 ## Voice Settings:
 
 ### `--voice-format VOICE_FORMAT`

aider/website/docs/faq.md

@@ -30,7 +30,7 @@ current chat to build a compact
 Adding a bunch of files that are mostly irrelevant to the
 task at hand will often distract or confuse the LLM.
 The LLM will give worse coding results, and sometimese even fail to correctly edit files.
-Addings extra files will also increase the token costs on your OpenAI invoice.
+Addings extra files will also increase your token costs.
 
 Again, it's usually best to just add the files to the chat that will need to be modified.
 If you still wish to add lots of files to the chat, you can:
@@ -60,6 +60,23 @@ directory you start in.
 You can also create a `.aiderignore` file to tell aider
 to ignore parts of the repo that aren't relevant to your task.
 This file conforms to `.gitignore` syntax and conventions.
+For example, to focus only on specific directories in a monorepo,
+you could create a `.aiderignore` file with:
+
+```
+# Ignore everything
+/*
+
+# Allow specific directories and their contents
+!foo/
+!bar/
+!baz/
+
+# Allow nested files under these directories
+!foo/**
+!bar/**
+!baz/**
+```
 
 You can use `--aiderignore <filename>` to name a specific file
 to use for ignore patterns.
@@ -150,7 +167,6 @@ python -m aider
 
 
 
-
 ## Can I change the system prompts that aider uses?
 
 Aider is set up to support different system prompts and edit formats
@@ -191,6 +207,16 @@ 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).
 
 
+## How are the "aider wrote xx% of code" stats computed?
+
+[Aider is tightly integrated with git](/docs/git.html) so all
+of aider's code changes are committed to the repo with proper attribution.
+The 
+[stats are computed](https://github.com/Aider-AI/aider/blob/main/scripts/blame.py)
+by doing something like `git blame` on the repo,
+and counting up who wrote all the new lines of code in each release.
+Only lines in source code files are counted, not documentation or prompt files.
+
 ## Can I share my aider chat transcript?
 
 Yes, you can now share aider chat logs in a pretty way.
@@ -213,6 +239,15 @@ This will give you a URL like this, which shows the chat history like you'd see
 https://aider.chat/share/?mdurl=https://gist.github.com/Aider-AI/2087ab8b64034a078c0a209440ac8be0
 ```
 
+## Can I edit files myself while aider is running?
+
+Yes. Aider always reads the latest copy of files from the file
+system when you send each message.
+
+While you're waiting for aider's reply to complete, it's probably unwise to
+edit files that you've added to the chat.
+Your edits and aider's edits might conflict.
+
 ## What is Aider AI LLC?
 
 Aider AI LLC is the company behind the aider AI coding tool.
@@ -222,11 +257,5 @@ under an
 [Apache 2.0 license](https://github.com/Aider-AI/aider/blob/main/LICENSE.txt).
 
 
-## Can I edit files myself while aider is running?
+<div style="height:80vh"></div>
 
-Yes. Aider always reads the latest copy of files from the file
-system when you send each message.
-
-While you're waiting for aider's reply to complete, it's probably unwise to
-edit files that you've added to the chat.
-Your edits and aider's edits might conflict.

aider/website/docs/languages.md

@@ -62,6 +62,7 @@ cog.out(get_supported_languages_md())
 | cpp                  | .cc                  |    ✓     |   ✓    |
 | cpp                  | .cpp                 |    ✓     |   ✓    |
 | css                  | .css                 |          |   ✓    |
+| dart                 | .dart                |    ✓     |   ✓    |
 | dockerfile           | .dockerfile          |          |   ✓    |
 | dot                  | .dot                 |          |   ✓    |
 | elisp                | .el                  |    ✓     |   ✓    |

aider/website/docs/leaderboards/index.md

@@ -31,6 +31,8 @@ This measures the LLM's coding ability, and whether it can
 write new code that integrates into existing code.
 The model also has to successfully apply all its changes to the source file without human intervention.
 
+<input type="text" id="editSearchInput" placeholder="Search..." style="width: 100%; max-width: 800px; margin: 10px auto; padding: 8px; display: block; border: 1px solid #ddd; border-radius: 4px;">
+
 <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>
@@ -58,79 +60,7 @@ The model also has to successfully apply all its changes to the source file with
 <canvas id="editChart" width="800" height="450" style="margin-top: 20px"></canvas>
 <script src="https://cdn.jsdelivr.net/npm/chart.js"></script>
 <script>
-  document.addEventListener('DOMContentLoaded', function () {
-    var ctx = document.getElementById('editChart').getContext('2d');
-    var leaderboardData = {
-      labels: [],
-      datasets: [{
-        label: 'Percent completed correctly',
-        data: [],
-        backgroundColor: 'rgba(54, 162, 235, 0.2)',
-        borderColor: 'rgba(54, 162, 235, 1)',
-        borderWidth: 1
-      }]
-    };
-
-    var allData = [];
-    {% for row in edit_sorted %}
-      allData.push({
-        model: '{{ row.model }}',
-        pass_rate_2: {{ row.pass_rate_2 }},
-        percent_cases_well_formed: {{ row.percent_cases_well_formed }}
-      });
-    {% endfor %}
-
-    function updateChart() {
-      var selectedRows = document.querySelectorAll('tr.selected');
-      var showAll = selectedRows.length === 0;
-
-      leaderboardData.labels = [];
-      leaderboardData.datasets[0].data = [];
-
-      allData.forEach(function(row, index) {
-        var rowElement = document.getElementById('edit-row-' + index);
-        if (showAll) {
-          rowElement.classList.remove('selected');
-        }
-        if (showAll || rowElement.classList.contains('selected')) {
-          leaderboardData.labels.push(row.model);
-          leaderboardData.datasets[0].data.push(row.pass_rate_2);
-        }
-      });
-
-      leaderboardChart.update();
-    }
-
-    var tableBody = document.querySelector('table tbody');
-    allData.forEach(function(row, index) {
-      var tr = tableBody.children[index];
-      tr.id = 'edit-row-' + index;
-      tr.style.cursor = 'pointer';
-      tr.onclick = function() {
-        this.classList.toggle('selected');
-        updateChart();
-      };
-    });
-
-    var leaderboardChart = new Chart(ctx, {
-      type: 'bar',
-      data: leaderboardData,
-      options: {
-        scales: {
-          yAxes: [{
-            scaleLabel: {
-              display: true,
-            },
-            ticks: {
-              beginAtZero: true
-            }
-          }]
-        }
-      }
-    });
-
-    updateChart();
-  });
+{% include edit-leaderboard.js %}
 </script>
 <style>
   tr.selected {
@@ -156,6 +86,8 @@ The refactoring benchmark requires a large context window to
 work with large source files.
 Therefore, results are available for fewer models.
 
+<input type="text" id="refacSearchInput" placeholder="Search..." style="width: 100%; max-width: 800px; margin: 10px auto; padding: 8px; display: block; border: 1px solid #ddd; border-radius: 4px;">
+
 <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>
@@ -183,79 +115,7 @@ Therefore, results are available for fewer models.
 <canvas id="refacChart" width="800" height="450" style="margin-top: 20px"></canvas>
 <script src="https://cdn.jsdelivr.net/npm/chart.js"></script>
 <script>
-  document.addEventListener('DOMContentLoaded', function () {
-    var ctx = document.getElementById('refacChart').getContext('2d');
-    var leaderboardData = {
-      labels: [],
-      datasets: [{
-        label: 'Percent completed correctly',
-        data: [],
-        backgroundColor: 'rgba(54, 162, 235, 0.2)',
-        borderColor: 'rgba(54, 162, 235, 1)',
-        borderWidth: 1
-      }]
-    };
-
-    var allData = [];
-    {% for row in refac_sorted %}
-      allData.push({
-        model: '{{ row.model }}',
-        pass_rate_1: {{ row.pass_rate_1 }},
-        percent_cases_well_formed: {{ row.percent_cases_well_formed }}
-      });
-    {% endfor %}
-
-    function updateChart() {
-      var selectedRows = document.querySelectorAll('tr.selected');
-      var showAll = selectedRows.length === 0;
-
-      leaderboardData.labels = [];
-      leaderboardData.datasets[0].data = [];
-
-      allData.forEach(function(row, index) {
-        var rowElement = document.getElementById('refac-row-' + index);
-        if (showAll) {
-          rowElement.classList.remove('selected');
-        }
-        if (showAll || rowElement.classList.contains('selected')) {
-          leaderboardData.labels.push(row.model);
-          leaderboardData.datasets[0].data.push(row.pass_rate_1);
-        }
-      });
-
-      leaderboardChart.update();
-    }
-
-    var tableBody = document.querySelectorAll('table tbody')[1];
-    allData.forEach(function(row, index) {
-      var tr = tableBody.children[index];
-      tr.id = 'refac-row-' + index;
-      tr.style.cursor = 'pointer';
-      tr.onclick = function() {
-        this.classList.toggle('selected');
-        updateChart();
-      };
-    });
-
-    var leaderboardChart = new Chart(ctx, {
-      type: 'bar',
-      data: leaderboardData,
-      options: {
-        scales: {
-          yAxes: [{
-            scaleLabel: {
-              display: true,
-            },
-            ticks: {
-              beginAtZero: true
-            }
-          }]
-        }
-      }
-    });
-
-    updateChart();
-  });
+{% include refactor-leaderboard.js %}
 </script>
 
 
@@ -321,6 +181,6 @@ 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.')}")
 ]]]-->
-October 22, 2024.
+November 24, 2024.
 <!--[[[end]]]-->
 </p>

aider/website/docs/llms/editing-format.md

@@ -1,22 +0,0 @@
----
-parent: Connecting to LLMs
-nav_order: 850
----
-
-# Editing format
-
-Aider uses different "edit formats" to collect code edits from different LLMs.
-The "whole" format is the easiest for an LLM to use, but it uses a lot of tokens
-and may limit how large a file can be edited.
-Models which can use one of the diff formats are much more efficient,
-using far fewer tokens.
-Models that use a diff-like format are able to 
-edit larger files with less cost and without hitting token limits.
-
-Aider is configured to use the best edit format for the popular OpenAI and Anthropic models
-and the [other models recommended on the LLM page](https://aider.chat/docs/llms.html).
-For lesser known models aider will default to using the "whole" editing format
-since it is the easiest format for an LLM to use.
-
-If you would like to experiment with the more advanced formats, you can
-use these switches: `--edit-format diff` or `--edit-format udiff`.

aider/website/docs/llms/lm-studio.md

@@ -0,0 +1,26 @@
+---
+parent: Connecting to LLMs
+nav_order: 400
+---
+
+# LM Studio
+
+To use LM Studio:
+
+```
+python -m pip install -U aider-chat
+
+export LM_STUDIO_API_KEY=<key> # Mac/Linux
+setx   LM_STUDIO_API_KEY <key> # Windows, restart shell after setx
+
+export LM_STUDIO_API_BASE=<url> # Mac/Linux
+setx   LM_STUDIO_API_BASE <url> # Windows, restart shell after setx
+
+aider --model lm_studio/<your-model-name>
+```
+
+
+
+See the [model warnings](warnings.html)
+section for information on warnings which will occur
+when working with models that aider is not familiar with.

aider/website/docs/llms/ollama.md

@@ -20,24 +20,49 @@ python -m pip install -U aider-chat
 export OLLAMA_API_BASE=http://127.0.0.1:11434 # Mac/Linux
 setx   OLLAMA_API_BASE http://127.0.0.1:11434 # Windows, restart shell after setx
 
-aider --model ollama/<model>
+aider --model ollama_chat/<model>
 ```
 
-In particular, `llama3:70b` works well with aider:
+{: .note }
+Using `ollama_chat/` is recommended over `ollama/`.
 
 
-```
-ollama pull llama3:70b
-ollama serve
-
-# In another terminal window...
-export OLLAMA_API_BASE=http://127.0.0.1:11434 # Mac/Linux
-setx   OLLAMA_API_BASE http://127.0.0.1:11434 # Windows, restart shell after setx
-
-aider --model ollama/llama3:70b 
-```
-
 See the [model warnings](warnings.html)
 section for information on warnings which will occur
 when working with models that aider is not familiar with.
 
+## API Key
+
+If you are using an ollama that requires an API key you can set `OLLAMA_API_KEY`:
+
+```
+export OLLAMA_API_KEY=<api-key> # Mac/Linux
+setx   OLLAMA_API_KEY <api-key> # Windows, restart shell after setx
+```
+
+## Setting the context window size
+
+[Ollama uses a 2k context window by default](https://github.com/ollama/ollama/blob/main/docs/faq.md#how-can-i-specify-the-context-window-size),
+which is very small for working with aider.
+
+Aider sets Ollama's context window to 8k by default. 
+If you would like
+a larger context window
+you can use a
+[`.aider.model.settings.yml` file](https://aider.chat/docs/config/adv-model-settings.html#model-settings)
+like this:
+
+```
+- name: ollama/qwen2.5-coder:32b-instruct-fp16
+  extra_params:
+    num_ctx: 8192
+```
+
+Unlike most other LLM servers, Ollama does not throw an error if you submit
+a request that exceeds the context window.
+Instead, it just silently truncates the request by discarding the "oldest" messages
+in the chat to make it fit within the context window.
+So if your context window is too small, you won't get an error.
+Aider will probably just fail to work well and experience
+a lot of 
+[file editing problems](https://aider.chat/docs/troubleshooting/edit-errors.html).

aider/website/docs/llms/other.md

@@ -95,5 +95,6 @@ cog.out(''.join(lines))
 - TOGETHERAI_API_KEY
 - VOLCENGINE_API_KEY
 - VOYAGE_API_KEY
+- XAI_API_KEY
 - XINFERENCE_API_KEY
 <!--[[[end]]]-->

aider/website/docs/llms/xai.md

@@ -0,0 +1,24 @@
+---
+parent: Connecting to LLMs
+nav_order: 400
+---
+
+# xAI
+
+You'll need a [xAI API key](https://console.x.ai.).
+
+To use xAI:
+
+```
+python -m pip install -U aider-chat
+
+export XAI_API_KEY=<key> # Mac/Linux
+setx   XAI_API_KEY <key> # Windows, restart shell after setx
+
+aider --model xai/grok-beta
+
+# List models available from xAI
+aider --list-models xai/
+```
+
+

aider/website/docs/more/analytics.md

@@ -31,7 +31,7 @@ features and commands are most used.
 It also helps uncover bugs that users are experiencing, so that they can be fixed
 in upcoming releases.
 
-## Enabling & disabling analytics
+## Disabling analytics
 
 You can opt out of analytics forever by running this command one time:
 
@@ -39,10 +39,27 @@ You can opt out of analytics forever by running this command one time:
 aider --analytics-disable
 ```
 
-To enable analytics for a single session, you can run aider with `--analytics`.
-This will *not* have any effect if you have permanently disabled analytics with the previous command.
+## Enabling analytics
 
-The first time, you will need to agree to opt-in.
+The `--[no-]analytics` switch controls whether analytics are enabled for the
+current session:
+
+- `--analytics` will turn on analytics for the current session.
+This will *not* have any effect if you have permanently disabled analytics 
+with `--analytics-disable`.
+If this is the first time you have enabled analytics, aider
+will confirm you wish to opt-in to analytics.
+- `--no-analytics` will turn off analytics for the current session.
+- By default, if you don't provide `--analytics` or `--no-analytics`,
+aider will enable analytics for a random subset of users.
+This will never happen if you have permanently disabled analytics 
+with `--analytics-disable`.
+Randomly selected users will be asked if they wish to opt-in to analytics.
+
+
+## Opting in
+
+The first time analytics are enabled, you will need to agree to opt-in.
 
 ```
 aider --analytics
@@ -53,13 +70,8 @@ For more info: https://aider.chat/docs/more/analytics.html
 Allow collection of anonymous analytics to help improve aider? (Y)es/(N)o [Yes]:
 ```
 
-If you've added `analytics: true` to your 
-[yaml config file](/docs/config/aider_conf.html), 
-you can disable analytics for a single session, you can run:
+If you say "no", analytics will be permanently disabled.
 
-```
-aider --no-analytics
-```
 
 ## Details about data being collected
 
@@ -100,7 +112,7 @@ aider --analytics-log filename.jsonl --no-analytics
 If you have concerns about any of the analytics that aider is collecting
 or our data practices
 please contact us by opening a
-[GitHub Issue](https://github.com/paul-gauthier/aider/issues).
+[GitHub Issue](https://github.com/aider-ai/aider/issues).
 
 ## Privacy policy
 

aider/website/docs/more/infinite-output.md

@@ -55,8 +55,9 @@ model_list = "\n".join(f"- {model}" for model in sorted(prefill_models))
 
 cog.out(model_list)
 ]]]-->
+- anthropic.claude-3-5-haiku-20241022-v1:0
 - anthropic.claude-3-5-sonnet-20241022-v2:0
-- anthropic/claude-3-5-sonnet-20241022
+- claude-3-5-haiku-20241022
 - claude-3-5-sonnet-20240620
 - claude-3-5-sonnet-20241022
 - claude-3-haiku-20240307
@@ -87,11 +88,19 @@ cog.out(model_list)
 - mistral/open-mixtral-8x7b
 - mistral/pixtral-12b-2409
 - openrouter/anthropic/claude-3.5-sonnet
+- us.anthropic.claude-3-5-haiku-20241022-v1:0
 - us.anthropic.claude-3-5-sonnet-20241022-v2:0
+- vertex_ai/claude-3-5-haiku
+- vertex_ai/claude-3-5-haiku@20241022
+- vertex_ai/claude-3-5-sonnet
+- vertex_ai/claude-3-5-sonnet-v2
 - vertex_ai/claude-3-5-sonnet-v2@20241022
 - vertex_ai/claude-3-5-sonnet@20240620
+- vertex_ai/claude-3-haiku
 - vertex_ai/claude-3-haiku@20240307
+- vertex_ai/claude-3-opus
 - vertex_ai/claude-3-opus@20240229
+- vertex_ai/claude-3-sonnet
 - vertex_ai/claude-3-sonnet@20240229
 <!--[[[end]]]-->
 

aider/website/docs/scripting.md

@@ -95,3 +95,6 @@ io = InputOutput(yes=True)
 coder = Coder.create(model=model, fnames=fnames, io=io)
 ```
 
+{: .note }
+The scripting API is not officially supported or documented and may
+change without warning.

aider/website/docs/troubleshooting/edit-errors.md

@@ -19,31 +19,7 @@ LLM edits that are "almost" correctly formatted.
 But sometimes the LLM just won't cooperate.
 In these cases, here are some things you might try.
 
-## Use a capable model
-
-If possible try using GPT-4o, Claude 3.5 Sonnet or Claude 3 Opus, 
-as they are the strongest and most capable models.
-
-Weaker models
-are more prone to
-disobeying the system prompt instructions.
-Most local models are just barely capable of working with aider,
-so editing errors are probably unavoidable.
-
-Local models which have been quantized are even more likely to have problems
-because they are not capable enough to follow aider's system prompts.
-
-## Try the whole format
-
-Run aider with `--edit-format whole` if the model is using a different edit format.
-You can see which edit format it is using in the announce lines:
-
-```
-Aider v0.50.2-dev
-Models: claude-3-5-sonnet-20240620 with ♾️ diff edit format
-```
-
-## Reduce distractions
+## Don't add too many files
 
 Many LLMs now have very large context windows,
 but filling them with irrelevant code or conversation 
@@ -55,6 +31,38 @@ Aider also sends the LLM a [map of your entire git repo](https://aider.chat/docs
 - Use `/clear` to remove the conversation history, again to help the LLM focus.
 - Use `/tokens` to see how many tokens you are using for each message.
 
+## Use a more capable model
+
+If possible try using GPT-4o, Claude 3.5 Sonnet or Claude 3 Opus, 
+as they are the strongest and most capable models.
+
+Weaker models
+are more prone to
+disobeying the system prompt instructions.
+Most local models are just barely capable of working with aider,
+so editing errors are probably unavoidable.
+
+## Local models: context window and quantization
+
+Be especially careful about the
+[Ollama context window](https://aider.chat/docs/llms/ollama.html#setting-the-context-window-size)
+when working with local models.
+It defaults to be very small and silently discards data if you exceed it.
+
+Local models which have been quantized are more likely to have editing problems
+because they are not capable enough to follow aider's system prompts.
+
+## Try the whole edit format
+
+Run aider with `--edit-format whole` if were using a different edit format.
+You can see which edit format it is using in the announce lines:
+
+```
+Aider v0.50.2-dev
+Models: claude-3-5-sonnet-20240620 with ♾️ diff edit format
+```
+
+
 ## More help
 
 {% include help.md %}

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

@@ -33,6 +33,13 @@ To reduce output tokens:
 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](http://0.0.0.0:4000/docs/config/adv-model-settings.html#context-window-size-and-token-costs)
+for unusual models.
+
 ## Input tokens & context window size
 
 The most common problem is trying to send too much data to a 

aider/website/docs/usage/commands.md

@@ -3,7 +3,14 @@ parent: Usage
 nav_order: 50
 description: Control aider with in-chat commands like /add, /model, etc.
 ---
+
 # In-chat commands
+{: .no_toc }
+
+- TOC
+{:toc}
+
+## Slash commands
 
 Aider supports commands from within the chat, which all start with `/`.
 
@@ -24,6 +31,7 @@ cog.out(get_help_md())
 | **/copy** | Copy the last assistant message to the clipboard |
 | **/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 |
 | **/exit** | Exit the application |
 | **/git** | Run a git command (output excluded from chat) |
 | **/help** | Ask questions about aider |

aider/website/docs/usage/modes.md

@@ -1,7 +1,7 @@
 ---
 parent: Usage
 nav_order: 60
-description: Using the chat, ask and help chat modes.
+description: Using the code, architect, ask and help chat modes.
 ---
 
 # Chat modes

aider/website/share/index.md

@@ -2,6 +2,12 @@
 nav_exclude: true
 ---
 
+<meta http-equiv="Content-Security-Policy" 
+    content="default-src 'self'; 
+             script-src 'self' 'unsafe-inline' https://cdn.jsdelivr.net https://cdnjs.cloudflare.com; 
+             connect-src http: https:;
+             style-src 'self' 'unsafe-inline';">
+
 # Shared aider chat transcript
 
 A user has shared the following transcript of a pair programming chat session
@@ -37,11 +43,29 @@ print("goodbye")
 </div>
 
 <script src="https://cdn.jsdelivr.net/npm/marked/marked.min.js"></script>
+<script src="https://cdnjs.cloudflare.com/ajax/libs/dompurify/3.0.6/purify.min.js"></script>
 <script>
+function isValidUrl(url) {
+    try {
+        const urlObj = new URL(url);
+        return urlObj.protocol === 'http:' || urlObj.protocol === 'https:';
+    } catch {
+        return false;
+    }
+}
+
+// Configure marked with secure defaults
+marked.setOptions({
+    headerIds: false,
+    mangle: false
+});
+
 window.onload = function() {
     var urlParams = new URLSearchParams(window.location.search);
     var conv = urlParams.get('mdurl');
-    if (!conv) {
+    if (!conv || !isValidUrl(conv)) {
+        document.querySelector('#shared-transcript').innerHTML = 
+            '<div style="color: red; padding: 1em;">Error: Invalid or missing URL provided</div>';
         return;
     }
     document.getElementById('mdurl').href = conv;
@@ -63,11 +87,14 @@ window.onload = function() {
             return line;
         }).join('\n');
         var html = marked.parse(markdown);
+        var sanitizedHtml = DOMPurify.sanitize(html);
         var divElement = document.querySelector('#shared-transcript');
-        divElement.innerHTML = html;
+        divElement.innerHTML = sanitizedHtml;
     })
     .catch(error => {
         console.error('Error fetching markdown:', error);
+        document.querySelector('#shared-transcript').innerHTML = 
+            '<div style="color: red; padding: 1em;">Error: Failed to load chat transcript</div>';
     });
 }
 </script>

benchmark/benchmark.py

@@ -155,6 +155,9 @@ def main(
     tries: int = typer.Option(2, "--tries", "-r", help="Number of tries for running tests"),
     threads: int = typer.Option(1, "--threads", "-t", help="Number of threads to run in parallel"),
     num_tests: int = typer.Option(-1, "--num-tests", "-n", help="Number of tests to run"),
+    num_ctx: Optional[int] = typer.Option(
+        None, "--num-ctx", help="Override model context window size"
+    ),
     exercises_dir: str = typer.Option(
         EXERCISES_DIR_DEFAULT, "--exercises-dir", help="Directory with exercise files"
     ),
@@ -247,6 +250,7 @@ def main(
                 max_apply_update_errors,
                 editor_model,
                 editor_edit_format,
+                num_ctx,
             )
 
             all_results.append(results)
@@ -526,6 +530,7 @@ def run_test_real(
     max_apply_update_errors,
     editor_model,
     editor_edit_format,
+    num_ctx=None,
 ):
     if not os.path.isdir(testdir):
         print("Not a dir:", testdir)
@@ -588,6 +593,11 @@ def run_test_real(
         editor_model=editor_model,
         editor_edit_format=editor_edit_format,
     )
+
+    if num_ctx:
+        if not main_model.extra_params:
+            main_model.extra_params = {}
+        main_model.extra_params["num_ctx"] = num_ctx
     edit_format = edit_format or main_model.edit_format
 
     dump(main_model)

benchmark/docker.sh

@@ -2,6 +2,7 @@
 
 docker run \
        -it --rm \
+       --add-host=host.docker.internal:host-gateway \
        -v `pwd`:/aider \
        -v `pwd`/tmp.benchmarks/.:/benchmarks \
        -e OPENAI_API_KEY=$OPENAI_API_KEY \

benchmark/over_time.py

@@ -1,121 +1,168 @@
+from dataclasses import dataclass
+from datetime import date
+from typing import Dict, List, Tuple
+
 import matplotlib.pyplot as plt
 import yaml
 from imgcat import imgcat
 from matplotlib import rc
 
-from aider.dump import dump  # noqa: 401
+
+@dataclass
+class ModelData:
+    name: str
+    release_date: date
+    pass_rate: float
+
+    @property
+    def color(self) -> str:
+        model = self.name.lower()
+        if "gemini" in model and "pro" in model:
+            return "magenta"
+        if "qwen" in model:
+            return "darkblue"
+        if "mistral" in model:
+            return "cyan"
+        if "haiku" in model:
+            return "pink"
+        if "deepseek" in model:
+            return "brown"
+        if "sonnet" in model:
+            return "orange"
+        if "-4o" in model:
+            return "purple"
+        if "gpt-4" in model:
+            return "red"
+        if "gpt-3.5" in model:
+            return "green"
+        return "lightblue"
+
+    @property
+    def legend_label(self) -> str:
+        model = self.name.lower()
+        if "gemini" in model and "pro" in model:
+            return "Gemini 1.5 Pro"
+        if "claude-3-sonnet" in model:
+            return "Sonnet"
+        if "o1-preview" in model:
+            return "O1 Preview"
+        if "gpt-3.5" in model:
+            return "GPT-3.5 Turbo"
+        if "gpt-4-" in model and "-4o" not in model:
+            return "GPT-4"
+        if "qwen" in model:
+            return "Qwen"
+        if "-4o" in model:
+            return "GPT-4o"
+        if "haiku" in model:
+            return "Haiku"
+        if "deepseek" in model:
+            return "DeepSeek"
+        if "mistral" in model:
+            return "Mistral"
+        return model
 
 
-def get_model_color(model):
-    default = "lightblue"
+class BenchmarkPlotter:
+    LABEL_FONT_SIZE = 16
 
-    if model == "gpt-4o-mini":
-        return default
+    def __init__(self):
+        self.setup_plot_style()
 
-    if "-4o" in model:
-        return "purple"
+    def setup_plot_style(self):
+        plt.rcParams["hatch.linewidth"] = 0.5
+        plt.rcParams["hatch.color"] = "#444444"
+        rc("font", **{"family": "sans-serif", "sans-serif": ["Helvetica"], "size": 10})
+        plt.rcParams["text.color"] = "#444444"
 
-    if "gpt-4" in model:
-        return "red"
+    def load_data(self, yaml_file: str) -> List[ModelData]:
+        with open(yaml_file, "r") as file:
+            data = yaml.safe_load(file)
 
-    if "gpt-3.5" in model:
-        return "green"
+        models = []
+        for entry in data:
+            if "released" in entry and "pass_rate_2" in entry:
+                model = ModelData(
+                    name=entry["model"].split("(")[0].strip(),
+                    release_date=entry["released"],
+                    pass_rate=entry["pass_rate_2"],
+                )
+                models.append(model)
+        return models
 
-    return default
+    def create_figure(self) -> Tuple[plt.Figure, plt.Axes]:
+        fig, ax = plt.subplots(figsize=(12, 8))
+        ax.grid(axis="y", zorder=0, lw=0.2)
+        for spine in ax.spines.values():
+            spine.set_edgecolor("#DDDDDD")
+            spine.set_linewidth(0.5)
+        return fig, ax
 
+    def plot_model_series(self, ax: plt.Axes, models: List[ModelData]):
+        # Group models by color
+        color_groups: Dict[str, List[ModelData]] = {}
+        for model in models:
+            if model.color not in color_groups:
+                color_groups[model.color] = []
+            color_groups[model.color].append(model)
 
-def plot_over_time(yaml_file):
-    with open(yaml_file, "r") as file:
-        data = yaml.safe_load(file)
+        # Plot each color group
+        for color, group in color_groups.items():
+            sorted_group = sorted(group, key=lambda x: x.release_date)
+            dates = [m.release_date for m in sorted_group]
+            rates = [m.pass_rate for m in sorted_group]
 
-    dates = []
-    pass_rates = []
-    models = []
+            # Plot line
+            ax.plot(dates, rates, c=color, alpha=0.5, linewidth=1)
 
-    print("Debug: Raw data from YAML file:")
-    print(data)
+            # Plot points
+            ax.scatter(dates, rates, c=color, alpha=0.5, s=120)
 
-    for entry in data:
-        if "released" in entry and "pass_rate_2" in entry:
-            dates.append(entry["released"])
-            pass_rates.append(entry["pass_rate_2"])
-            models.append(entry["model"].split("(")[0].strip())
+            # Add label for first point
+            first_model = sorted_group[0]
+            ax.annotate(
+                first_model.legend_label,
+                (first_model.release_date, first_model.pass_rate),
+                xytext=(10, 5),
+                textcoords="offset points",
+                color=color,
+                alpha=0.8,
+                fontsize=self.LABEL_FONT_SIZE,
+            )
 
-    print("Debug: Processed data:")
-    print("Dates:", dates)
-    print("Pass rates:", pass_rates)
-    print("Models:", models)
-
-    if not dates or not pass_rates:
-        print(
-            "Error: No data to plot. Check if the YAML file is empty or if the data is in the"
-            " expected format."
+    def set_labels_and_style(self, ax: plt.Axes):
+        ax.set_xlabel("Model release date", fontsize=18, color="#555")
+        ax.set_ylabel(
+            "Aider code editing benchmark,\npercent completed correctly", fontsize=18, color="#555"
         )
-        return
+        ax.set_title("LLM code editing skill by model release date", fontsize=20)
+        ax.set_ylim(30, 90)
+        plt.xticks(fontsize=14, rotation=45, ha="right")
+        plt.tight_layout(pad=1.0)
 
-    plt.rcParams["hatch.linewidth"] = 0.5
-    plt.rcParams["hatch.color"] = "#444444"
+    def save_and_display(self, fig: plt.Figure):
+        plt.savefig("aider/website/assets/models-over-time.png")
+        plt.savefig("aider/website/assets/models-over-time.svg")
+        imgcat(fig)
 
-    rc("font", **{"family": "sans-serif", "sans-serif": ["Helvetica"], "size": 10})
-    plt.rcParams["text.color"] = "#444444"
-
-    fig, ax = plt.subplots(figsize=(12, 6))  # Increase figure size for better visibility
-
-    print("Debug: Figure created. Plotting data...")
-    ax.grid(axis="y", zorder=0, lw=0.2)
-    for spine in ax.spines.values():
-        spine.set_edgecolor("#DDDDDD")
-        spine.set_linewidth(0.5)
-
-    colors = [get_model_color(model) for model in models]
-
-    # Separate data points by color
-    purple_points = [(d, r) for d, r, c in zip(dates, pass_rates, colors) if c == "purple"]
-    red_points = [(d, r) for d, r, c in zip(dates, pass_rates, colors) if c == "red"]
-    green_points = [(d, r) for d, r, c in zip(dates, pass_rates, colors) if c == "green"]
-
-    # Plot lines for purple, red, and green points
-    if purple_points:
-        purple_dates, purple_rates = zip(*sorted(purple_points))
-        ax.plot(purple_dates, purple_rates, c="purple", alpha=0.5, linewidth=1)
-    if red_points:
-        red_dates, red_rates = zip(*sorted(red_points))
-        ax.plot(red_dates, red_rates, c="red", alpha=0.5, linewidth=1)
-    if green_points:
-        green_dates, green_rates = zip(*sorted(green_points))
-        ax.plot(green_dates, green_rates, c="green", alpha=0.5, linewidth=1)
-
-    # Plot all points
-    ax.scatter(dates, pass_rates, c=colors, alpha=0.5, s=120)
-
-    for i, model in enumerate(models):
-        ax.annotate(
-            model,
-            (dates[i], pass_rates[i]),
-            fontsize=8,
-            alpha=0.75,
-            xytext=(5, 5),
-            textcoords="offset points",
-        )
-
-    ax.set_xlabel("Model release date", fontsize=18, color="#555")
-    ax.set_ylabel(
-        "Aider code editing benchmark,\npercent completed correctly", fontsize=18, color="#555"
-    )
-    ax.set_title("LLM code editing skill by model release date", fontsize=20)
-    ax.set_ylim(0, 100)  # Adjust y-axis limit to accommodate higher values
-    plt.xticks(fontsize=14, rotation=45, ha="right")  # Rotate x-axis labels for better readability
-    plt.tight_layout(pad=3.0)
-
-    print("Debug: Saving figures...")
-    plt.savefig("tmp_over_time.png")
-    plt.savefig("tmp_over_time.svg")
-
-    print("Debug: Displaying figure with imgcat...")
-    imgcat(fig)
-
-    print("Debug: Figure generation complete.")
+    def plot(self, yaml_file: str):
+        models = self.load_data(yaml_file)
+        fig, ax = self.create_figure()
+        self.plot_model_series(ax, models)
+        self.set_labels_and_style(ax)
+        self.save_and_display(fig)
 
 
-# Example usage
-plot_over_time("aider/website/_data/edit_leaderboard.yml")
+def main():
+    plotter = BenchmarkPlotter()
+    models = plotter.load_data("aider/website/_data/edit_leaderboard.yml")
+
+    # Print release dates and model names
+    for model in sorted(models, key=lambda x: x.release_date):
+        print(f"{model.release_date}: {model.name}")
+
+    plotter.plot("aider/website/_data/edit_leaderboard.yml")
+
+
+if __name__ == "__main__":
+    main()

pyproject.toml

@@ -58,6 +58,7 @@ include = ["aider*", "aider.website"]
 "docs/unified-diffs.md",
 "docs/leaderboards/index.md",
 "assets/**",
+"**/.DS_Store",
 # [[[end]]]
 ]
 

requirements.txt

@@ -6,7 +6,7 @@
 #
 aiohappyeyeballs==2.4.3
     # via aiohttp
-aiohttp==3.10.10
+aiohttp==3.11.7
     # via litellm
 aiosignal==1.3.1
     # via aiohttp
@@ -62,11 +62,11 @@ gitdb==4.0.11
     # via gitpython
 gitpython==3.1.43
     # via -r requirements/requirements.in
-grep-ast==0.3.3
+grep-ast==0.4.0
     # via -r requirements/requirements.in
 h11==0.14.0
     # via httpcore
-httpcore==1.0.6
+httpcore==1.0.7
     # via httpx
 httpx==0.27.2
     # via openai
@@ -86,9 +86,9 @@ importlib-resources==6.4.5
     # via -r requirements/requirements.in
 jinja2==3.1.4
     # via litellm
-jiter==0.7.0
+jiter==0.7.1
     # via openai
-json5==0.9.25
+json5==0.9.28
     # via -r requirements/requirements.in
 jsonschema==4.23.0
     # via
@@ -96,7 +96,7 @@ jsonschema==4.23.0
     #   litellm
 jsonschema-specifications==2024.10.1
     # via jsonschema
-litellm==1.51.2
+litellm==1.52.16
     # via -r requirements/requirements.in
 markdown-it-py==3.0.0
     # via rich
@@ -120,9 +120,9 @@ numpy==1.26.4
     # via
     #   -r requirements/requirements.in
     #   scipy
-openai==1.53.0
+openai==1.55.1
     # via litellm
-packaging==24.1
+packaging==24.2
     # via
     #   -r requirements/requirements.in
     #   huggingface-hub
@@ -134,12 +134,14 @@ pexpect==4.9.0
     # via -r requirements/requirements.in
 pillow==10.4.0
     # via -r requirements/requirements.in
-posthog==3.7.0
+posthog==3.7.3
     # via -r requirements/requirements.in
 prompt-toolkit==3.0.48
     # via -r requirements/requirements.in
 propcache==0.2.0
-    # via yarl
+    # via
+    #   aiohttp
+    #   yarl
 psutil==6.1.0
     # via -r requirements/requirements.in
 ptyprocess==0.7.0
@@ -148,11 +150,11 @@ pycodestyle==2.12.1
     # via flake8
 pycparser==2.22
     # via cffi
-pydantic==2.9.2
+pydantic==2.10.2
     # via
     #   litellm
     #   openai
-pydantic-core==2.23.4
+pydantic-core==2.27.1
     # via pydantic
 pydub==0.25.1
     # via -r requirements/requirements.in
@@ -176,7 +178,7 @@ referencing==0.35.1
     # via
     #   jsonschema
     #   jsonschema-specifications
-regex==2024.9.11
+regex==2024.11.6
     # via tiktoken
 requests==2.32.3
     # via
@@ -185,9 +187,9 @@ requests==2.32.3
     #   mixpanel
     #   posthog
     #   tiktoken
-rich==13.9.3
+rich==13.9.4
     # via -r requirements/requirements.in
-rpds-py==0.20.1
+rpds-py==0.21.0
     # via
     #   jsonschema
     #   referencing
@@ -217,7 +219,7 @@ tokenizers==0.19.1
     # via
     #   -r requirements/requirements.in
     #   litellm
-tqdm==4.66.6
+tqdm==4.67.1
     # via
     #   huggingface-hub
     #   openai
@@ -239,7 +241,7 @@ urllib3==2.2.3
     #   requests
 wcwidth==0.2.13
     # via prompt-toolkit
-yarl==1.17.1
+yarl==1.18.0
     # via aiohttp
-zipp==3.20.2
+zipp==3.21.0
     # via importlib-metadata

requirements/requirements-browser.txt

@@ -4,109 +4,109 @@
 #
 #    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
 #
-altair==5.4.1
+altair==5.5.0
     # via streamlit
 attrs==24.2.0
     # via
+    #   -c /Users/gauthier/Projects/aider/requirements.txt
     #   -c requirements.txt
-    #   -c requirements/../requirements.txt
     #   -c requirements/requirements-help.txt
     #   jsonschema
     #   referencing
-blinker==1.8.2
+blinker==1.9.0
     # via streamlit
 cachetools==5.5.0
     # via streamlit
 certifi==2024.8.30
     # via
+    #   -c /Users/gauthier/Projects/aider/requirements.txt
     #   -c requirements.txt
-    #   -c requirements/../requirements.txt
     #   -c requirements/requirements-dev.txt
     #   -c requirements/requirements-help.txt
     #   requests
 charset-normalizer==3.4.0
     # via
+    #   -c /Users/gauthier/Projects/aider/requirements.txt
     #   -c requirements.txt
-    #   -c requirements/../requirements.txt
     #   -c requirements/requirements-dev.txt
     #   -c requirements/requirements-help.txt
     #   requests
 click==8.1.7
     # via
+    #   -c /Users/gauthier/Projects/aider/requirements.txt
     #   -c requirements.txt
-    #   -c requirements/../requirements.txt
     #   -c requirements/requirements-dev.txt
     #   -c requirements/requirements-help.txt
     #   streamlit
 gitdb==4.0.11
     # via
+    #   -c /Users/gauthier/Projects/aider/requirements.txt
     #   -c requirements.txt
-    #   -c requirements/../requirements.txt
     #   gitpython
 gitpython==3.1.43
     # via
+    #   -c /Users/gauthier/Projects/aider/requirements.txt
     #   -c requirements.txt
-    #   -c requirements/../requirements.txt
     #   streamlit
 idna==3.10
     # via
+    #   -c /Users/gauthier/Projects/aider/requirements.txt
     #   -c requirements.txt
-    #   -c requirements/../requirements.txt
     #   -c requirements/requirements-dev.txt
     #   -c requirements/requirements-help.txt
     #   requests
 jinja2==3.1.4
     # via
+    #   -c /Users/gauthier/Projects/aider/requirements.txt
     #   -c requirements.txt
-    #   -c requirements/../requirements.txt
     #   -c requirements/requirements-dev.txt
     #   -c requirements/requirements-help.txt
     #   altair
     #   pydeck
 jsonschema==4.23.0
     # via
+    #   -c /Users/gauthier/Projects/aider/requirements.txt
     #   -c requirements.txt
-    #   -c requirements/../requirements.txt
     #   altair
 jsonschema-specifications==2024.10.1
     # via
+    #   -c /Users/gauthier/Projects/aider/requirements.txt
     #   -c requirements.txt
-    #   -c requirements/../requirements.txt
     #   jsonschema
 markdown-it-py==3.0.0
     # via
+    #   -c /Users/gauthier/Projects/aider/requirements.txt
     #   -c requirements.txt
-    #   -c requirements/../requirements.txt
     #   -c requirements/requirements-dev.txt
     #   rich
 markupsafe==3.0.2
     # via
+    #   -c /Users/gauthier/Projects/aider/requirements.txt
     #   -c requirements.txt
-    #   -c requirements/../requirements.txt
     #   -c requirements/requirements-dev.txt
     #   -c requirements/requirements-help.txt
     #   jinja2
 mdurl==0.1.2
     # via
+    #   -c /Users/gauthier/Projects/aider/requirements.txt
     #   -c requirements.txt
-    #   -c requirements/../requirements.txt
     #   -c requirements/requirements-dev.txt
     #   markdown-it-py
-narwhals==1.12.1
+narwhals==1.14.2
     # via altair
 numpy==1.26.4
     # via
+    #   -c /Users/gauthier/Projects/aider/requirements.txt
     #   -c requirements.txt
-    #   -c requirements/../requirements.txt
     #   -c requirements/requirements-dev.txt
     #   -c requirements/requirements-help.txt
     #   pandas
     #   pydeck
     #   streamlit
-packaging==24.1
+packaging==24.2
     # via
+    #   -c /Users/gauthier/Projects/aider/requirements.txt
     #   -c requirements.txt
-    #   -c requirements/../requirements.txt
     #   -c requirements/requirements-dev.txt
     #   -c requirements/requirements-help.txt
     #   altair
@@ -117,27 +117,27 @@ pandas==2.2.3
     #   streamlit
 pillow==10.4.0
     # via
+    #   -c /Users/gauthier/Projects/aider/requirements.txt
     #   -c requirements.txt
-    #   -c requirements/../requirements.txt
     #   -c requirements/requirements-dev.txt
     #   -c requirements/requirements-help.txt
     #   streamlit
 protobuf==5.28.3
     # via streamlit
-pyarrow==18.0.0
+pyarrow==18.1.0
     # via streamlit
 pydeck==0.9.1
     # via streamlit
 pygments==2.18.0
     # via
+    #   -c /Users/gauthier/Projects/aider/requirements.txt
     #   -c requirements.txt
-    #   -c requirements/../requirements.txt
     #   -c requirements/requirements-dev.txt
     #   rich
 python-dateutil==2.9.0.post0
     # via
+    #   -c /Users/gauthier/Projects/aider/requirements.txt
     #   -c requirements.txt
-    #   -c requirements/../requirements.txt
     #   -c requirements/requirements-dev.txt
     #   pandas
 pytz==2024.2
@@ -146,41 +146,41 @@ pytz==2024.2
     #   pandas
 referencing==0.35.1
     # via
+    #   -c /Users/gauthier/Projects/aider/requirements.txt
     #   -c requirements.txt
-    #   -c requirements/../requirements.txt
     #   jsonschema
     #   jsonschema-specifications
 requests==2.32.3
     # via
+    #   -c /Users/gauthier/Projects/aider/requirements.txt
     #   -c requirements.txt
-    #   -c requirements/../requirements.txt
     #   -c requirements/requirements-dev.txt
     #   -c requirements/requirements-help.txt
     #   streamlit
-rich==13.9.3
+rich==13.9.4
     # via
+    #   -c /Users/gauthier/Projects/aider/requirements.txt
     #   -c requirements.txt
-    #   -c requirements/../requirements.txt
     #   -c requirements/requirements-dev.txt
     #   streamlit
-rpds-py==0.20.1
+rpds-py==0.21.0
     # via
+    #   -c /Users/gauthier/Projects/aider/requirements.txt
     #   -c requirements.txt
-    #   -c requirements/../requirements.txt
     #   jsonschema
     #   referencing
 six==1.16.0
     # via
+    #   -c /Users/gauthier/Projects/aider/requirements.txt
     #   -c requirements.txt
-    #   -c requirements/../requirements.txt
     #   -c requirements/requirements-dev.txt
     #   python-dateutil
 smmap==5.0.1
     # via
+    #   -c /Users/gauthier/Projects/aider/requirements.txt
     #   -c requirements.txt
-    #   -c requirements/../requirements.txt
     #   gitdb
-streamlit==1.39.0
+streamlit==1.40.2
     # via -r requirements/requirements-browser.in
 tenacity==8.5.0
     # via
@@ -188,12 +188,12 @@ tenacity==8.5.0
     #   streamlit
 toml==0.10.2
     # via streamlit
-tornado==6.4.1
+tornado==6.4.2
     # via streamlit
 typing-extensions==4.12.2
     # via
+    #   -c /Users/gauthier/Projects/aider/requirements.txt
     #   -c requirements.txt
-    #   -c requirements/../requirements.txt
     #   -c requirements/requirements-dev.txt
     #   -c requirements/requirements-help.txt
     #   altair
@@ -204,8 +204,8 @@ tzdata==2024.2
     #   pandas
 urllib3==2.2.3
     # via
+    #   -c /Users/gauthier/Projects/aider/requirements.txt
     #   -c requirements.txt
-    #   -c requirements/../requirements.txt
     #   -c requirements/requirements-dev.txt
     #   -c requirements/requirements-help.txt
     #   requests

requirements/requirements-dev.txt

@@ -12,27 +12,27 @@ build==1.2.2.post1
     # via pip-tools
 certifi==2024.8.30
     # via
+    #   -c /Users/gauthier/Projects/aider/requirements.txt
     #   -c requirements.txt
-    #   -c requirements/../requirements.txt
     #   requests
 cfgv==3.4.0
     # via pre-commit
 charset-normalizer==3.4.0
     # via
+    #   -c /Users/gauthier/Projects/aider/requirements.txt
     #   -c requirements.txt
-    #   -c requirements/../requirements.txt
     #   requests
 click==8.1.7
     # via
+    #   -c /Users/gauthier/Projects/aider/requirements.txt
     #   -c requirements.txt
-    #   -c requirements/../requirements.txt
     #   pip-tools
     #   typer
 codespell==2.3.0
     # via -r requirements/requirements-dev.in
 cogapp==3.4.1
     # via -r requirements/requirements-dev.in
-contourpy==1.3.0
+contourpy==1.3.1
     # via matplotlib
 cycler==0.12.1
     # via matplotlib
@@ -48,28 +48,28 @@ docutils==0.21.2
     #   sphinx-rtd-theme
 filelock==3.16.1
     # via
+    #   -c /Users/gauthier/Projects/aider/requirements.txt
     #   -c requirements.txt
-    #   -c requirements/../requirements.txt
     #   virtualenv
-fonttools==4.54.1
+fonttools==4.55.0
     # via matplotlib
-identify==2.6.1
+identify==2.6.3
     # via pre-commit
 idna==3.10
     # via
+    #   -c /Users/gauthier/Projects/aider/requirements.txt
     #   -c requirements.txt
-    #   -c requirements/../requirements.txt
     #   requests
 imagesize==1.4.1
     # via sphinx
-imgcat==0.5.0
+imgcat==0.6.0
     # via -r requirements/requirements-dev.in
 iniconfig==2.0.0
     # via pytest
 jinja2==3.1.4
     # via
+    #   -c /Users/gauthier/Projects/aider/requirements.txt
     #   -c requirements.txt
-    #   -c requirements/../requirements.txt
     #   sphinx
 kiwisolver==1.4.7
     # via matplotlib
@@ -77,20 +77,20 @@ lox==0.12.0
     # via -r requirements/requirements-dev.in
 markdown-it-py==3.0.0
     # via
+    #   -c /Users/gauthier/Projects/aider/requirements.txt
     #   -c requirements.txt
-    #   -c requirements/../requirements.txt
     #   rich
 markupsafe==3.0.2
     # via
+    #   -c /Users/gauthier/Projects/aider/requirements.txt
     #   -c requirements.txt
-    #   -c requirements/../requirements.txt
     #   jinja2
 matplotlib==3.9.2
     # via -r requirements/requirements-dev.in
 mdurl==0.1.2
     # via
+    #   -c /Users/gauthier/Projects/aider/requirements.txt
     #   -c requirements.txt
-    #   -c requirements/../requirements.txt
     #   markdown-it-py
 multiprocess==0.70.17
     # via pathos
@@ -98,15 +98,15 @@ nodeenv==1.9.1
     # via pre-commit
 numpy==1.26.4
     # via
+    #   -c /Users/gauthier/Projects/aider/requirements.txt
     #   -c requirements.txt
-    #   -c requirements/../requirements.txt
     #   contourpy
     #   matplotlib
     #   pandas
-packaging==24.1
+packaging==24.2
     # via
+    #   -c /Users/gauthier/Projects/aider/requirements.txt
     #   -c requirements.txt
-    #   -c requirements/../requirements.txt
     #   build
     #   matplotlib
     #   pytest
@@ -117,8 +117,8 @@ pathos==0.3.3
     # via lox
 pillow==10.4.0
     # via
+    #   -c /Users/gauthier/Projects/aider/requirements.txt
     #   -c requirements.txt
-    #   -c requirements/../requirements.txt
     #   matplotlib
 pip-tools==7.4.1
     # via -r requirements/requirements-dev.in
@@ -134,8 +134,8 @@ pre-commit==4.0.1
     # via -r requirements/requirements-dev.in
 pygments==2.18.0
     # via
+    #   -c /Users/gauthier/Projects/aider/requirements.txt
     #   -c requirements.txt
-    #   -c requirements/../requirements.txt
     #   rich
     #   sphinx
 pyparsing==3.2.0
@@ -148,26 +148,26 @@ pytest==8.3.3
     # via -r requirements/requirements-dev.in
 python-dateutil==2.9.0.post0
     # via
+    #   -c /Users/gauthier/Projects/aider/requirements.txt
     #   -c requirements.txt
-    #   -c requirements/../requirements.txt
     #   matplotlib
     #   pandas
 pytz==2024.2
     # via pandas
 pyyaml==6.0.2
     # via
+    #   -c /Users/gauthier/Projects/aider/requirements.txt
     #   -c requirements.txt
-    #   -c requirements/../requirements.txt
     #   pre-commit
 requests==2.32.3
     # via
+    #   -c /Users/gauthier/Projects/aider/requirements.txt
     #   -c requirements.txt
-    #   -c requirements/../requirements.txt
     #   sphinx
-rich==13.9.3
+rich==13.9.4
     # via
+    #   -c /Users/gauthier/Projects/aider/requirements.txt
     #   -c requirements.txt
-    #   -c requirements/../requirements.txt
     #   typer
 semver==3.0.2
     # via -r requirements/requirements-dev.in
@@ -175,8 +175,8 @@ shellingham==1.5.4
     # via typer
 six==1.16.0
     # via
+    #   -c /Users/gauthier/Projects/aider/requirements.txt
     #   -c requirements.txt
-    #   -c requirements/../requirements.txt
     #   python-dateutil
 snowballstemmer==2.2.0
     # via sphinx
@@ -184,7 +184,7 @@ sphinx==8.1.3
     # via
     #   sphinx-rtd-theme
     #   sphinxcontrib-jquery
-sphinx-rtd-theme==3.0.1
+sphinx-rtd-theme==3.0.2
     # via lox
 sphinxcontrib-applehelp==2.0.0
     # via sphinx
@@ -200,23 +200,23 @@ sphinxcontrib-qthelp==2.0.0
     # via sphinx
 sphinxcontrib-serializinghtml==2.0.0
     # via sphinx
-typer==0.12.5
+typer==0.13.1
     # via -r requirements/requirements-dev.in
 typing-extensions==4.12.2
     # via
+    #   -c /Users/gauthier/Projects/aider/requirements.txt
     #   -c requirements.txt
-    #   -c requirements/../requirements.txt
     #   typer
 tzdata==2024.2
     # via pandas
 urllib3==2.2.3
     # via
+    #   -c /Users/gauthier/Projects/aider/requirements.txt
     #   -c requirements.txt
-    #   -c requirements/../requirements.txt
     #   requests
-virtualenv==20.27.1
+virtualenv==20.28.0
     # via pre-commit
-wheel==0.44.0
+wheel==0.45.1
     # via pip-tools
 
 # The following packages are considered to be unsafe in a requirements file:

requirements/requirements-help.txt

@@ -6,79 +6,81 @@
 #
 aiohappyeyeballs==2.4.3
     # via
+    #   -c /Users/gauthier/Projects/aider/requirements.txt
     #   -c requirements.txt
-    #   -c requirements/../requirements.txt
     #   aiohttp
-aiohttp==3.10.10
+aiohttp==3.11.7
     # via
+    #   -c /Users/gauthier/Projects/aider/requirements.txt
     #   -c requirements.txt
-    #   -c requirements/../requirements.txt
     #   huggingface-hub
     #   llama-index-core
 aiosignal==1.3.1
     # via
+    #   -c /Users/gauthier/Projects/aider/requirements.txt
     #   -c requirements.txt
-    #   -c requirements/../requirements.txt
     #   aiohttp
 annotated-types==0.7.0
     # via
+    #   -c /Users/gauthier/Projects/aider/requirements.txt
     #   -c requirements.txt
-    #   -c requirements/../requirements.txt
     #   pydantic
 anyio==4.6.2.post1
     # via
+    #   -c /Users/gauthier/Projects/aider/requirements.txt
     #   -c requirements.txt
-    #   -c requirements/../requirements.txt
     #   httpx
 attrs==24.2.0
     # via
+    #   -c /Users/gauthier/Projects/aider/requirements.txt
     #   -c requirements.txt
-    #   -c requirements/../requirements.txt
     #   aiohttp
 certifi==2024.8.30
     # via
+    #   -c /Users/gauthier/Projects/aider/requirements.txt
     #   -c requirements.txt
-    #   -c requirements/../requirements.txt
     #   -c requirements/requirements-dev.txt
     #   httpcore
     #   httpx
     #   requests
 charset-normalizer==3.4.0
     # via
+    #   -c /Users/gauthier/Projects/aider/requirements.txt
     #   -c requirements.txt
-    #   -c requirements/../requirements.txt
     #   -c requirements/requirements-dev.txt
     #   requests
 click==8.1.7
     # via
+    #   -c /Users/gauthier/Projects/aider/requirements.txt
     #   -c requirements.txt
-    #   -c requirements/../requirements.txt
     #   -c requirements/requirements-dev.txt
     #   nltk
 dataclasses-json==0.6.7
     # via llama-index-core
-deprecated==1.2.14
+deprecated==1.2.15
     # via llama-index-core
 dirtyjson==1.0.8
     # via llama-index-core
 filelock==3.16.1
     # via
+    #   -c /Users/gauthier/Projects/aider/requirements.txt
     #   -c requirements.txt
-    #   -c requirements/../requirements.txt
     #   -c requirements/requirements-dev.txt
     #   huggingface-hub
     #   torch
     #   transformers
+filetype==1.2.0
+    # via llama-index-core
 frozenlist==1.5.0
     # via
+    #   -c /Users/gauthier/Projects/aider/requirements.txt
     #   -c requirements.txt
-    #   -c requirements/../requirements.txt
     #   aiohttp
     #   aiosignal
 fsspec==2024.10.0
     # via
+    #   -c /Users/gauthier/Projects/aider/requirements.txt
     #   -c requirements.txt
-    #   -c requirements/../requirements.txt
     #   huggingface-hub
     #   llama-index-core
     #   torch
@@ -88,31 +90,31 @@ greenlet==3.0.3
     #   sqlalchemy
 h11==0.14.0
     # via
+    #   -c /Users/gauthier/Projects/aider/requirements.txt
     #   -c requirements.txt
-    #   -c requirements/../requirements.txt
     #   httpcore
-httpcore==1.0.6
+httpcore==1.0.7
     # via
+    #   -c /Users/gauthier/Projects/aider/requirements.txt
     #   -c requirements.txt
-    #   -c requirements/../requirements.txt
     #   httpx
 httpx==0.27.2
     # via
+    #   -c /Users/gauthier/Projects/aider/requirements.txt
     #   -c requirements.txt
-    #   -c requirements/../requirements.txt
     #   llama-index-core
 huggingface-hub[inference]==0.26.2
     # via
+    #   -c /Users/gauthier/Projects/aider/requirements.txt
     #   -c requirements.txt
-    #   -c requirements/../requirements.txt
     #   llama-index-embeddings-huggingface
     #   sentence-transformers
     #   tokenizers
     #   transformers
 idna==3.10
     # via
+    #   -c /Users/gauthier/Projects/aider/requirements.txt
     #   -c requirements.txt
-    #   -c requirements/../requirements.txt
     #   -c requirements/requirements-dev.txt
     #   anyio
     #   httpx
@@ -120,34 +122,34 @@ idna==3.10
     #   yarl
 jinja2==3.1.4
     # via
+    #   -c /Users/gauthier/Projects/aider/requirements.txt
     #   -c requirements.txt
-    #   -c requirements/../requirements.txt
     #   -c requirements/requirements-dev.txt
     #   torch
 joblib==1.4.2
     # via
     #   nltk
     #   scikit-learn
-llama-index-core==0.11.21
+llama-index-core==0.12.0
     # via
     #   -r requirements/requirements-help.in
     #   llama-index-embeddings-huggingface
-llama-index-embeddings-huggingface==0.3.1
+llama-index-embeddings-huggingface==0.4.0
     # via -r requirements/requirements-help.in
 markupsafe==3.0.2
     # via
+    #   -c /Users/gauthier/Projects/aider/requirements.txt
     #   -c requirements.txt
-    #   -c requirements/../requirements.txt
     #   -c requirements/requirements-dev.txt
     #   jinja2
-marshmallow==3.23.0
+marshmallow==3.23.1
     # via dataclasses-json
 mpmath==1.3.0
     # via sympy
 multidict==6.1.0
     # via
+    #   -c /Users/gauthier/Projects/aider/requirements.txt
     #   -c requirements.txt
-    #   -c requirements/../requirements.txt
     #   aiohttp
     #   yarl
 mypy-extensions==1.0.0
@@ -156,70 +158,71 @@ nest-asyncio==1.6.0
     # via llama-index-core
 networkx==3.2.1
     # via
+    #   -c /Users/gauthier/Projects/aider/requirements.txt
     #   -c requirements.txt
-    #   -c requirements/../requirements.txt
     #   llama-index-core
     #   torch
 nltk==3.9.1
     # via llama-index-core
 numpy==1.26.4
     # via
+    #   -c /Users/gauthier/Projects/aider/requirements.txt
     #   -c requirements.txt
-    #   -c requirements/../requirements.txt
     #   -c requirements/requirements-dev.txt
     #   llama-index-core
     #   scikit-learn
     #   scipy
     #   transformers
-packaging==24.1
+packaging==24.2
     # via
+    #   -c /Users/gauthier/Projects/aider/requirements.txt
     #   -c requirements.txt
-    #   -c requirements/../requirements.txt
     #   -c requirements/requirements-dev.txt
     #   huggingface-hub
     #   marshmallow
     #   transformers
 pillow==10.4.0
     # via
+    #   -c /Users/gauthier/Projects/aider/requirements.txt
     #   -c requirements.txt
-    #   -c requirements/../requirements.txt
     #   -c requirements/requirements-dev.txt
     #   llama-index-core
     #   sentence-transformers
 propcache==0.2.0
     # via
+    #   -c /Users/gauthier/Projects/aider/requirements.txt
     #   -c requirements.txt
-    #   -c requirements/../requirements.txt
+    #   aiohttp
     #   yarl
-pydantic==2.9.2
+pydantic==2.10.2
     # via
+    #   -c /Users/gauthier/Projects/aider/requirements.txt
     #   -c requirements.txt
-    #   -c requirements/../requirements.txt
     #   llama-index-core
-pydantic-core==2.23.4
+pydantic-core==2.27.1
     # via
+    #   -c /Users/gauthier/Projects/aider/requirements.txt
     #   -c requirements.txt
-    #   -c requirements/../requirements.txt
     #   pydantic
 pyyaml==6.0.2
     # via
+    #   -c /Users/gauthier/Projects/aider/requirements.txt
     #   -c requirements.txt
-    #   -c requirements/../requirements.txt
     #   -c requirements/requirements-dev.txt
     #   huggingface-hub
     #   llama-index-core
     #   transformers
-regex==2024.9.11
+regex==2024.11.6
     # via
+    #   -c /Users/gauthier/Projects/aider/requirements.txt
     #   -c requirements.txt
-    #   -c requirements/../requirements.txt
     #   nltk
     #   tiktoken
     #   transformers
 requests==2.32.3
     # via
+    #   -c /Users/gauthier/Projects/aider/requirements.txt
     #   -c requirements.txt
-    #   -c requirements/../requirements.txt
     #   -c requirements/requirements-dev.txt
     #   huggingface-hub
     #   llama-index-core
@@ -231,16 +234,16 @@ scikit-learn==1.5.2
     # via sentence-transformers
 scipy==1.13.1
     # via
+    #   -c /Users/gauthier/Projects/aider/requirements.txt
     #   -c requirements.txt
-    #   -c requirements/../requirements.txt
     #   scikit-learn
     #   sentence-transformers
-sentence-transformers==3.2.1
+sentence-transformers==3.3.1
     # via llama-index-embeddings-huggingface
 sniffio==1.3.1
     # via
+    #   -c /Users/gauthier/Projects/aider/requirements.txt
     #   -c requirements.txt
-    #   -c requirements/../requirements.txt
     #   anyio
     #   httpx
 sqlalchemy[asyncio]==2.0.36
@@ -255,20 +258,20 @@ threadpoolctl==3.5.0
     # via scikit-learn
 tiktoken==0.8.0
     # via
+    #   -c /Users/gauthier/Projects/aider/requirements.txt
     #   -c requirements.txt
-    #   -c requirements/../requirements.txt
     #   llama-index-core
 tokenizers==0.19.1
     # via
+    #   -c /Users/gauthier/Projects/aider/requirements.txt
     #   -c requirements.txt
-    #   -c requirements/../requirements.txt
     #   transformers
 torch==2.2.2
     # via sentence-transformers
-tqdm==4.66.6
+tqdm==4.67.1
     # via
+    #   -c /Users/gauthier/Projects/aider/requirements.txt
     #   -c requirements.txt
-    #   -c requirements/../requirements.txt
     #   huggingface-hub
     #   llama-index-core
     #   nltk
@@ -278,8 +281,8 @@ transformers==4.44.2
     # via sentence-transformers
 typing-extensions==4.12.2
     # via
+    #   -c /Users/gauthier/Projects/aider/requirements.txt
     #   -c requirements.txt
-    #   -c requirements/../requirements.txt
     #   -c requirements/requirements-dev.txt
     #   huggingface-hub
     #   llama-index-core
@@ -294,16 +297,16 @@ typing-inspect==0.9.0
     #   llama-index-core
 urllib3==2.2.3
     # via
+    #   -c /Users/gauthier/Projects/aider/requirements.txt
     #   -c requirements.txt
-    #   -c requirements/../requirements.txt
     #   -c requirements/requirements-dev.txt
     #   requests
-wrapt==1.16.0
+wrapt==1.17.0
     # via
     #   deprecated
     #   llama-index-core
-yarl==1.17.1
+yarl==1.18.0
     # via
+    #   -c /Users/gauthier/Projects/aider/requirements.txt
     #   -c requirements.txt
-    #   -c requirements/../requirements.txt
     #   aiohttp

requirements/requirements-playwright.txt

@@ -15,8 +15,8 @@ pyee==12.0.0
     # via playwright
 typing-extensions==4.12.2
     # via
+    #   -c /Users/gauthier/Projects/aider/requirements.txt
     #   -c requirements.txt
-    #   -c requirements/../requirements.txt
     #   -c requirements/requirements-browser.txt
     #   -c requirements/requirements-dev.txt
     #   -c requirements/requirements-help.txt

scripts/Dockerfile.jekyll

@@ -15,6 +15,6 @@ RUN bundle install --retry 5 --jobs 20
 ENTRYPOINT [ "docker-entrypoint.sh" ]
 
 # bundle exec jekyll serve --force_polling -H 0.0.0.0 -P 4000
-CMD [ "bundle", "exec", "jekyll", "serve", "--force_polling", "-H", "0.0.0.0", "-P", "4000" ]
+CMD [ "bundle", "exec", "jekyll", "serve", "--verbose", "--trace", "--force_polling", "-H", "0.0.0.0", "-P", "4000" ]
 
 

scripts/blame.py

@@ -23,8 +23,10 @@ def blame(start_tag, end_tag=None):
     files = [
         f
         for f in files
-        if f.endswith((".py", ".scm", ".sh", "Dockerfile", "Gemfile"))
+        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"
     ]
     files = [f for f in files if not f.endswith("prompts.py")]
 

scripts/issues.py

@@ -22,11 +22,27 @@ def has_been_reopened(issue_number):
 # Load environment variables from .env file
 load_dotenv()
 
-DUPLICATE_COMMENT = """Thanks for trying aider and filing this issue.
+BOT_SUFFIX = """Note: A [bot script](https://github.com/Aider-AI/aider/blob/main/scripts/issues.py) made these updates to the issue.
+"""  # noqa
+
+DUPLICATE_COMMENT = (
+    """Thanks for trying aider and filing this issue.
 
 This looks like a duplicate of #{oldest_issue_number}. Please see the comments there for more information, and feel free to continue the discussion within that issue.
 
 I'm going to close this issue for now. But please let me know if you think this is actually a distinct issue and I will reopen this issue."""  # noqa
+    + BOT_SUFFIX
+)
+
+STALE_COMMENT = (
+    """I'm labeling this issue as stale because it has been open for 2 weeks with no activity. If there are no additional comments, I will close it in 7 days."""  # noqa
+    + BOT_SUFFIX
+)
+
+CLOSE_STALE_COMMENT = (
+    """I'm closing this issue because it has been stalled for 3 weeks with no activity. Feel free to add a comment here and we can re-open it. Or feel free to file a new issue at any time."""  # noqa
+    + BOT_SUFFIX
+)
 
 # GitHub API configuration
 GITHUB_API_URL = "https://api.github.com"
@@ -112,22 +128,187 @@ def comment_and_close_duplicate(issue, oldest_issue):
     print(f"  - Commented and closed issue #{issue['number']}")
 
 
-def main():
-    parser = argparse.ArgumentParser(description="Handle duplicate GitHub issues")
-    parser.add_argument(
-        "--yes", action="store_true", help="Automatically close duplicates without prompting"
-    )
-    args = parser.parse_args()
+def find_unlabeled_with_paul_comments(issues):
+    unlabeled_issues = []
+    for issue in issues:
+        # Skip pull requests
+        if "pull_request" in issue:
+            continue
 
-    if not TOKEN:
-        print("Error: Missing GITHUB_TOKEN environment variable. Please check your .env file.")
+        if not issue["labels"] and issue["state"] == "open":
+            # Get comments for this issue
+            comments_url = (
+                f"{GITHUB_API_URL}/repos/{REPO_OWNER}/{REPO_NAME}/issues/{issue['number']}/comments"
+            )
+            response = requests.get(comments_url, headers=headers)
+            response.raise_for_status()
+            comments = response.json()
+
+            # Check if paul-gauthier has commented
+            if any(comment["user"]["login"] == "paul-gauthier" for comment in comments):
+                unlabeled_issues.append(issue)
+    return unlabeled_issues
+
+
+def handle_unlabeled_issues(all_issues, auto_yes):
+    print("\nFinding unlabeled issues with paul-gauthier comments...")
+    unlabeled_issues = find_unlabeled_with_paul_comments(all_issues)
+
+    if not unlabeled_issues:
+        print("No unlabeled issues with paul-gauthier comments found.")
         return
 
-    all_issues = get_issues("all")
+    print(f"\nFound {len(unlabeled_issues)} unlabeled issues with paul-gauthier comments:")
+    for issue in unlabeled_issues:
+        print(f"  - #{issue['number']}: {issue['title']} {issue['html_url']}")
+
+    if not auto_yes:
+        confirm = input("\nDo you want to add the 'question' label to these issues? (y/n): ")
+        if confirm.lower() != "y":
+            print("Skipping labeling.")
+            return
+
+    print("\nAdding 'question' label to issues...")
+    for issue in unlabeled_issues:
+        url = f"{GITHUB_API_URL}/repos/{REPO_OWNER}/{REPO_NAME}/issues/{issue['number']}"
+        response = requests.patch(url, headers=headers, json={"labels": ["question"]})
+        response.raise_for_status()
+        print(f"  - Added 'question' label to #{issue['number']}")
+
+
+def handle_stale_issues(all_issues, auto_yes):
+    print("\nChecking for stale question issues...")
+
+    for issue in all_issues:
+        # Skip if not open, not a question, already stale, or has been reopened
+        if (
+            issue["state"] != "open"
+            or "question" not in [label["name"] for label in issue["labels"]]
+            or "stale" in [label["name"] for label in issue["labels"]]
+            or has_been_reopened(issue["number"])
+        ):
+            continue
+
+        # Get latest activity timestamp from issue or its comments
+        latest_activity = datetime.strptime(issue["updated_at"], "%Y-%m-%dT%H:%M:%SZ")
+
+        # Check if issue is stale (no activity for 14 days)
+        days_inactive = (datetime.now() - latest_activity).days
+        if days_inactive >= 14:
+            print(f"\nStale issue found: #{issue['number']}: {issue['title']}\n{issue['html_url']}")
+            print(f"  No activity for {days_inactive} days")
+
+            if not auto_yes:
+                confirm = input("Add stale label and comment? (y/n): ")
+                if confirm.lower() != "y":
+                    print("Skipping this issue.")
+                    continue
+
+            # Add comment
+            comment_url = (
+                f"{GITHUB_API_URL}/repos/{REPO_OWNER}/{REPO_NAME}/issues/{issue['number']}/comments"
+            )
+            response = requests.post(comment_url, headers=headers, json={"body": STALE_COMMENT})
+            response.raise_for_status()
+
+            # Add stale label
+            url = f"{GITHUB_API_URL}/repos/{REPO_OWNER}/{REPO_NAME}/issues/{issue['number']}"
+            response = requests.patch(url, headers=headers, json={"labels": ["question", "stale"]})
+            response.raise_for_status()
+
+            print(f"  Added stale label and comment to #{issue['number']}")
+
+
+def handle_stale_closing(all_issues, auto_yes):
+    print("\nChecking for issues to close or unstale...")
+
+    for issue in all_issues:
+        # Skip if not open or not stale
+        if issue["state"] != "open" or "stale" not in [label["name"] for label in issue["labels"]]:
+            continue
+
+        # Get the timeline to find when the stale label was last 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 stale label addition
+        stale_events = [
+            event
+            for event in events
+            if event.get("event") == "labeled" and event.get("label", {}).get("name") == "stale"
+        ]
+
+        if not stale_events:
+            continue
+
+        latest_stale = datetime.strptime(stale_events[-1]["created_at"], "%Y-%m-%dT%H:%M:%SZ")
+
+        # Get comments since the stale label
+        comments_url = (
+            f"{GITHUB_API_URL}/repos/{REPO_OWNER}/{REPO_NAME}/issues/{issue['number']}/comments"
+        )
+        response = requests.get(comments_url, headers=headers)
+        response.raise_for_status()
+        comments = response.json()
+
+        # Check for comments newer than the stale label
+        new_comments = [
+            comment
+            for comment in comments
+            if datetime.strptime(comment["created_at"], "%Y-%m-%dT%H:%M:%SZ") > latest_stale
+        ]
+
+        if new_comments:
+            print(f"\nFound new activity on stale issue #{issue['number']}: {issue['title']}")
+            print(f"  {len(new_comments)} new comments since stale label")
+
+            if not auto_yes:
+                confirm = input("Remove stale label? (y/n): ")
+                if confirm.lower() != "y":
+                    print("Skipping this issue.")
+                    continue
+
+            # Remove stale label but keep question label
+            url = f"{GITHUB_API_URL}/repos/{REPO_OWNER}/{REPO_NAME}/issues/{issue['number']}"
+            response = requests.patch(url, headers=headers, json={"labels": ["question"]})
+            response.raise_for_status()
+            print(f"  Removed stale label from #{issue['number']}")
+        else:
+            # Check if it's been 7 days since stale label
+            days_stale = (datetime.now() - latest_stale).days
+            if days_stale >= 7:
+                print(f"\nStale issue ready for closing #{issue['number']}: {issue['title']}")
+                print(f"  No activity for {days_stale} days since stale label")
+
+                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"  # noqa
+                response = requests.post(
+                    comment_url, headers=headers, json={"body": CLOSE_STALE_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)
 
-    print("Analyzing issues (skipping reopened issues)...")
+    print("Looking for duplicate issues (skipping reopened issues)...")
     for subject, issues in grouped_open_issues.items():
         oldest_issue = find_oldest_issue(subject, all_issues)
         if not oldest_issue:
@@ -149,14 +330,12 @@ def main():
             f" {oldest_issue['html_url']} ({oldest_issue['state']})"
         )
 
-        if not args.yes:
-            # Confirmation prompt
+        if not auto_yes:
             confirm = input("Do you want to comment and close duplicate issues? (y/n): ")
             if confirm.lower() != "y":
                 print("Skipping this group of issues.")
                 continue
 
-        # Comment and close duplicate issues
         for issue in issues:
             if issue["number"] != oldest_issue["number"]:
                 comment_and_close_duplicate(issue, oldest_issue)
@@ -165,5 +344,24 @@ def main():
             print(f"Oldest issue #{oldest_issue['number']} left open")
 
 
+def main():
+    parser = argparse.ArgumentParser(description="Handle duplicate GitHub issues")
+    parser.add_argument(
+        "--yes", action="store_true", help="Automatically close duplicates without prompting"
+    )
+    args = parser.parse_args()
+
+    if not TOKEN:
+        print("Error: Missing GITHUB_TOKEN environment variable. Please check your .env file.")
+        return
+
+    all_issues = get_issues("all")
+
+    handle_unlabeled_issues(all_issues, args.yes)
+    handle_stale_issues(all_issues, args.yes)
+    handle_stale_closing(all_issues, args.yes)
+    handle_duplicate_issues(all_issues, args.yes)
+
+
 if __name__ == "__main__":
     main()

scripts/update-docs.sh

@@ -24,6 +24,7 @@ cog $ARG \
     aider/website/docs/config/options.md \
     aider/website/docs/config/aider_conf.md \
     aider/website/docs/config/adv-model-settings.md \
+    aider/website/docs/config/model-aliases.md \
     aider/website/docs/leaderboards/index.md \
     aider/website/docs/llms/other.md \
     aider/website/docs/more/infinite-output.md \

scripts/update-history.py

@@ -0,0 +1,72 @@
+#!/usr/bin/env python3
+
+import os
+import re
+import subprocess
+import tempfile
+
+from aider import __version__
+
+
+def get_base_version():
+    # Parse current version like "0.64.2.dev" to get major.minor
+    match = re.match(r"(\d+\.\d+)", __version__)
+    if not match:
+        raise ValueError(f"Could not parse version: {__version__}")
+    return match.group(1) + ".0"
+
+
+def run_git_log():
+    base_ver = get_base_version()
+    cmd = [
+        "git",
+        "log",
+        "-p",
+        f"v{base_ver}..HEAD",
+        "--",
+        "aider/",
+        ":!aider/website/",
+        ":!scripts/",
+        ":!HISTORY.md",
+    ]
+    result = subprocess.run(cmd, capture_output=True, text=True)
+    return result.stdout
+
+
+def main():
+    # Get the git log output
+    diff_content = run_git_log()
+
+    # Save to temporary file
+    with tempfile.NamedTemporaryFile(mode="w", delete=False, suffix=".diff") as tmp:
+        tmp.write(diff_content)
+        tmp_path = tmp.name
+
+    # Run blame to get aider percentage
+    blame_result = subprocess.run(["python3", "scripts/blame.py"], capture_output=True, text=True)
+    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
+
+    cmd = ["aider", "HISTORY.md", "--read", tmp_path, "--msg", message, "--no-auto-commit"]
+    subprocess.run(cmd)
+
+    # Run update-docs.sh after aider
+    subprocess.run(["scripts/update-docs.sh"])
+
+    # Cleanup
+    os.unlink(tmp_path)
+
+
+if __name__ == "__main__":
+    main()

scripts/versionbump.py

@@ -124,7 +124,10 @@ def main():
     for cmd in git_commands:
         print(f"Running: {' '.join(cmd)}")
         if not dry_run:
-            subprocess.run(cmd, check=True)
+            subprocess.run(
+                cmd,
+                check=True,
+            )
 
     new_dev_version = f"{incremented_version}.dev"
     updated_dev_content = re.sub(

tests/basic/test_analytics.py

@@ -91,10 +91,49 @@ def test_system_info(temp_data_dir):
 
 def test_need_to_ask(temp_data_dir):
     analytics = Analytics()
-    assert analytics.need_to_ask() is True
+    assert analytics.need_to_ask(True) is True
+    assert analytics.need_to_ask(False) is False
+
+    analytics.user_id = "111"
+    assert analytics.need_to_ask(None) is False
+
+    analytics.user_id = "000"
+    assert analytics.need_to_ask(None) is True
 
     analytics.asked_opt_in = True
-    assert analytics.need_to_ask() is False
+    assert analytics.need_to_ask(True) is False
 
     analytics.permanently_disable = True
-    assert analytics.need_to_ask() is False
+    assert analytics.need_to_ask(True) is False
+
+
+def test_is_uuid_in_percentage():
+    analytics = Analytics()
+
+    # Test basic percentage thresholds
+    assert analytics.is_uuid_in_percentage("00000000000000000000000000000000", 1) is True
+    assert analytics.is_uuid_in_percentage("01999000000000000000000000000000", 1) is True
+    assert analytics.is_uuid_in_percentage("02000000000000000000000000000000", 1) is True
+    assert analytics.is_uuid_in_percentage("02910000000000000000000000000001", 1) is False
+    assert analytics.is_uuid_in_percentage("03000000000000000000000000000000", 1) is False
+    assert analytics.is_uuid_in_percentage("ff000000000000000000000000000000", 1) is False
+
+    assert analytics.is_uuid_in_percentage("00000000000000000000000000000000", 10) is True
+    assert analytics.is_uuid_in_percentage("19000000000000000000000000000000", 10) is True
+    assert analytics.is_uuid_in_percentage("1a000000000000000000000000000000", 10) is False
+    assert analytics.is_uuid_in_percentage("ff000000000000000000000000000000", 10) is False
+
+    # Test edge cases
+    assert analytics.is_uuid_in_percentage("00000000000000000000000000000000", 0) is False
+    assert analytics.is_uuid_in_percentage("00000000000000000000000000000000", 100) is True
+    assert analytics.is_uuid_in_percentage("ffffffffffffffffffffffffffffffff", 100) is True
+
+    # Test invalid inputs
+    with pytest.raises(ValueError):
+        analytics.is_uuid_in_percentage("00000000000000000000000000000000", -1)
+    with pytest.raises(ValueError):
+        analytics.is_uuid_in_percentage("00000000000000000000000000000000", 101)
+
+    # Test empty/None UUID
+    assert analytics.is_uuid_in_percentage("", 50) is False
+    assert analytics.is_uuid_in_percentage(None, 50) is False

tests/basic/test_coder.py

@@ -7,6 +7,7 @@ from unittest.mock import MagicMock, patch
 import git
 
 from aider.coders import Coder
+from aider.coders.base_coder import UnknownEditFormat
 from aider.dump import dump  # noqa: F401
 from aider.io import InputOutput
 from aider.models import Model
@@ -17,6 +18,8 @@ from aider.utils import GitTemporaryDirectory
 class TestCoder(unittest.TestCase):
     def setUp(self):
         self.GPT35 = Model("gpt-3.5-turbo")
+        self.webbrowser_patcher = patch("aider.io.webbrowser.open")
+        self.mock_webbrowser = self.webbrowser_patcher.start()
 
     def test_allowed_to_edit(self):
         with GitTemporaryDirectory():
@@ -166,6 +169,37 @@ class TestCoder(unittest.TestCase):
 
             self.assertEqual(coder.abs_fnames, set([str(fname.resolve())]))
 
+    def test_skip_duplicate_basename_mentions(self):
+        with GitTemporaryDirectory():
+            io = InputOutput(pretty=False, yes=True)
+            coder = Coder.create(self.GPT35, None, io)
+
+            # Create files with same basename in different directories
+            fname1 = Path("dir1") / "file.txt"
+            fname2 = Path("dir2") / "file.txt"
+            fname3 = Path("dir3") / "unique.txt"
+
+            for fname in [fname1, fname2, fname3]:
+                fname.parent.mkdir(parents=True, exist_ok=True)
+                fname.touch()
+
+            # Add one file to chat
+            coder.add_rel_fname(str(fname1))
+
+            # Mock get_tracked_files to return all files
+            mock = MagicMock()
+            mock.return_value = set([str(fname1), str(fname2), str(fname3)])
+            coder.repo.get_tracked_files = mock
+
+            # Check that file mentions skip files with duplicate basenames
+            mentioned = coder.get_file_mentions(f"Check {fname2} and {fname3}")
+            self.assertEqual(mentioned, {str(fname3)})
+
+            # Add a read-only file with same basename
+            coder.abs_read_only_fnames.add(str(fname2.resolve()))
+            mentioned = coder.get_file_mentions(f"Check {fname1} and {fname3}")
+            self.assertEqual(mentioned, {str(fname3)})
+
     def test_check_for_file_mentions_read_only(self):
         with GitTemporaryDirectory():
             io = InputOutput(
@@ -819,32 +853,55 @@ This command will print 'Hello, World!' to the console."""
         with GitTemporaryDirectory():
             io = InputOutput(yes=True)
             coder = Coder.create(self.GPT35, "diff", io=io, suggest_shell_commands=False)
+            self.assertFalse(coder.suggest_shell_commands)
 
-            def mock_send(*args, **kwargs):
-                coder.partial_response_content = """Here's a shell command to run:
+    def test_detect_urls_enabled(self):
+        with GitTemporaryDirectory():
+            io = InputOutput(yes=True)
+            coder = Coder.create(self.GPT35, "diff", io=io, detect_urls=True)
+            coder.commands.scraper = MagicMock()
+            coder.commands.scraper.scrape = MagicMock(return_value="some content")
 
-```bash
-echo "Hello, World!"
-```
+            # Test with a message containing a URL
+            message = "Check out https://example.com"
+            coder.check_for_urls(message)
+            coder.commands.scraper.scrape.assert_called_once_with("https://example.com")
 
-This command will print 'Hello, World!' to the console."""
-                coder.partial_response_function_call = dict()
-                return []
+    def test_detect_urls_disabled(self):
+        with GitTemporaryDirectory():
+            io = InputOutput(yes=True)
+            coder = Coder.create(self.GPT35, "diff", io=io, detect_urls=False)
+            coder.commands.scraper = MagicMock()
+            coder.commands.scraper.scrape = MagicMock(return_value="some content")
 
-            coder.send = mock_send
+            # Test with a message containing a URL
+            message = "Check out https://example.com"
+            result = coder.check_for_urls(message)
+            self.assertEqual(result, [])
+            coder.commands.scraper.scrape.assert_not_called()
 
-            # Mock the handle_shell_commands method to check if it's called
-            coder.handle_shell_commands = MagicMock()
+    def test_unknown_edit_format_exception(self):
+        # Test the exception message format
+        invalid_format = "invalid_format"
+        valid_formats = ["diff", "whole", "map"]
+        exc = UnknownEditFormat(invalid_format, valid_formats)
+        expected_msg = (
+            f"Unknown edit format {invalid_format}. Valid formats are: {', '.join(valid_formats)}"
+        )
+        self.assertEqual(str(exc), expected_msg)
 
-            # Run the coder with a message
-            coder.run(with_message="Suggest a shell command")
+    def test_unknown_edit_format_creation(self):
+        # Test that creating a Coder with invalid edit format raises the exception
+        io = InputOutput(yes=True)
+        invalid_format = "invalid_format"
 
-            # Check if the shell command was added to the list
-            self.assertEqual(len(coder.shell_commands), 1)
-            self.assertEqual(coder.shell_commands[0].strip(), 'echo "Hello, World!"')
+        with self.assertRaises(UnknownEditFormat) as cm:
+            Coder.create(self.GPT35, invalid_format, io=io)
 
-            # Check if handle_shell_commands was called with the correct argument
-            coder.handle_shell_commands.assert_not_called()
+        exc = cm.exception
+        self.assertEqual(exc.edit_format, invalid_format)
+        self.assertIsInstance(exc.valid_formats, list)
+        self.assertTrue(len(exc.valid_formats) > 0)
 
     def test_coder_create_with_new_file_oserror(self):
         with GitTemporaryDirectory():

tests/basic/test_commands.py

@@ -1068,8 +1068,10 @@ class TestCommands(TestCase):
             io.prompt_ask = lambda *args, **kwargs: "y"
 
             # Test the cmd_run method with a command that should not raise an error
-            result = commands.cmd_run("exit 1", add_on_nonzero_exit=True)
-            self.assertIn("I ran this command", result)
+            commands.cmd_run("exit 1", add_on_nonzero_exit=True)
+
+            # Check that the output was added to cur_messages
+            self.assertTrue(any("exit 1" in msg["content"] for msg in coder.cur_messages))
 
     def test_cmd_add_drop_untracked_files(self):
         with GitTemporaryDirectory():
@@ -1210,6 +1212,26 @@ class TestCommands(TestCase):
             del commands
             del repo
 
+    def test_cmd_add_gitignored_file(self):
+        with GitTemporaryDirectory():
+            # Create a .gitignore file
+            gitignore = Path(".gitignore")
+            gitignore.write_text("*.ignored\n")
+
+            # Create a file that matches the gitignore pattern
+            ignored_file = Path("test.ignored")
+            ignored_file.write_text("This should be ignored")
+
+            io = InputOutput(pretty=False, fancy_input=False, yes=False)
+            coder = Coder.create(self.GPT35, None, io)
+            commands = Commands(io, coder)
+
+            # Try to add the ignored file
+            commands.cmd_add(str(ignored_file))
+
+            # Verify the file was not added
+            self.assertEqual(len(coder.abs_fnames), 0)
+
     def test_cmd_add_aiderignored_file(self):
         with GitTemporaryDirectory():
             repo = git.Repo()

tests/basic/test_editblock.py

@@ -10,6 +10,7 @@ from aider.coders import editblock_coder as eb
 from aider.dump import dump  # noqa: F401
 from aider.io import InputOutput
 from aider.models import Model
+from aider.utils import ChdirTemporaryDirectory
 
 
 class TestUtils(unittest.TestCase):
@@ -341,6 +342,46 @@ These changes replace the `subprocess.run` patches with `subprocess.check_output
         result = eb.replace_most_similar_chunk(whole, part, replace)
         self.assertEqual(result, expected_output)
 
+    def test_create_new_file_with_other_file_in_chat(self):
+        # https://github.com/Aider-AI/aider/issues/2258
+        with ChdirTemporaryDirectory():
+            # Create a few temporary files
+            file1 = "file.txt"
+
+            with open(file1, "w", encoding="utf-8") as f:
+                f.write("one\ntwo\nthree\n")
+
+            files = [file1]
+
+            # Initialize the Coder object with the mocked IO and mocked repo
+            coder = Coder.create(
+                self.GPT35, "diff", use_git=False, io=InputOutput(yes=True), fnames=files
+            )
+
+            def mock_send(*args, **kwargs):
+                coder.partial_response_content = f"""
+Do this:
+
+newfile.txt
+<<<<<<< SEARCH
+=======
+creating a new file
+>>>>>>> REPLACE
+
+"""
+                coder.partial_response_function_call = dict()
+                return []
+
+            coder.send = mock_send
+
+            coder.run(with_message="hi")
+
+            content = Path(file1).read_text(encoding="utf-8")
+            self.assertEqual(content, "one\ntwo\nthree\n")
+
+            content = Path("newfile.txt").read_text(encoding="utf-8")
+            self.assertEqual(content, "creating a new file\n")
+
     def test_full_edit(self):
         # Create a few temporary files
         _, file1 = tempfile.mkstemp()

tests/basic/test_editor.py

@@ -0,0 +1,129 @@
+import os
+from unittest.mock import MagicMock, patch
+
+import pytest
+
+from aider.editor import (
+    DEFAULT_EDITOR_NIX,
+    DEFAULT_EDITOR_OS_X,
+    DEFAULT_EDITOR_WINDOWS,
+    discover_editor,
+    get_environment_editor,
+    pipe_editor,
+    print_status_message,
+    write_temp_file,
+)
+
+
+def test_get_environment_editor():
+    # Test with no environment variables set
+    with patch.dict(os.environ, {}, clear=True):
+        assert get_environment_editor("default") == "default"
+
+    # Test EDITOR precedence
+    with patch.dict(os.environ, {"EDITOR": "vim"}):
+        assert get_environment_editor() == "vim"
+
+    # Test VISUAL overrides EDITOR
+    with patch.dict(os.environ, {"EDITOR": "vim", "VISUAL": "code"}):
+        assert get_environment_editor() == "code"
+
+
+def test_discover_editor_defaults():
+    with patch("platform.system") as mock_system:
+        # Test Windows default
+        mock_system.return_value = "Windows"
+        with patch.dict(os.environ, {}, clear=True):
+            assert discover_editor() == [DEFAULT_EDITOR_WINDOWS]
+
+        # Test macOS default
+        mock_system.return_value = "Darwin"
+        with patch.dict(os.environ, {}, clear=True):
+            assert discover_editor() == [DEFAULT_EDITOR_OS_X]
+
+        # Test Linux default
+        mock_system.return_value = "Linux"
+        with patch.dict(os.environ, {}, clear=True):
+            assert discover_editor() == [DEFAULT_EDITOR_NIX]
+
+
+def test_write_temp_file():
+    # Test basic file creation
+    content = "test content"
+    filepath = write_temp_file(content)
+    assert os.path.exists(filepath)
+    with open(filepath, "r") as f:
+        assert f.read() == content
+    os.remove(filepath)
+
+    # Test with suffix
+    filepath = write_temp_file("content", suffix="txt")
+    assert filepath.endswith(".txt")
+    os.remove(filepath)
+
+    # Test with prefix
+    filepath = write_temp_file("content", prefix="test_")
+    assert os.path.basename(filepath).startswith("test_")
+    os.remove(filepath)
+
+
+def test_print_status_message(capsys):
+    # Test success message
+    print_status_message(True, "Success!")
+    captured = capsys.readouterr()
+    assert "Success!" in captured.out
+
+    # Test failure message
+    print_status_message(False, "Failed!")
+    captured = capsys.readouterr()
+    assert "Failed!" in captured.out
+
+
+def test_discover_editor_override():
+    # Test editor override
+    assert discover_editor("code") == ["code"]
+    assert discover_editor('vim -c "set noswapfile"') == ["vim", "-c", "set noswapfile"]
+
+    # Test invalid editor command
+    with pytest.raises(RuntimeError):
+        discover_editor('vim "unclosed quote')
+
+
+def test_pipe_editor():
+    # Test with default editor
+    test_content = "Initial content"
+    modified_content = "Modified content"
+
+    # Mock the file operations and editor call
+    with (
+        patch("aider.editor.write_temp_file") as mock_write,
+        patch("builtins.open") as mock_open,
+        patch("os.remove") as mock_remove,
+        patch("subprocess.call") as mock_subprocess,
+    ):
+        # Setup mocks
+        mock_write.return_value = "temp.txt"
+        mock_file = MagicMock()
+        mock_file.__enter__.return_value.read.return_value = modified_content
+        mock_open.return_value = mock_file
+
+        # Test with default editor
+        result = pipe_editor(test_content)
+        assert result == modified_content
+        mock_write.assert_called_with(test_content, None)
+        mock_subprocess.assert_called()
+
+        # Test with custom editor
+        result = pipe_editor(test_content, editor="code")
+        assert result == modified_content
+        mock_subprocess.assert_called()
+
+        # Test with suffix
+        result = pipe_editor(test_content, suffix="md")
+        assert result == modified_content
+        mock_write.assert_called_with(test_content, "md")
+
+        # Test cleanup on permission error
+        mock_remove.side_effect = PermissionError
+        result = pipe_editor(test_content)
+        assert result == modified_content

tests/basic/test_exceptions.py

@@ -0,0 +1,65 @@
+from aider.exceptions import ExInfo, LiteLLMExceptions
+
+
+def test_litellm_exceptions_load():
+    """Test that LiteLLMExceptions loads without errors"""
+    ex = LiteLLMExceptions()
+    assert len(ex.exceptions) > 0
+
+
+def test_exceptions_tuple():
+    """Test that exceptions_tuple returns a non-empty tuple"""
+    ex = LiteLLMExceptions()
+    assert isinstance(ex.exceptions_tuple(), tuple)
+    assert len(ex.exceptions_tuple()) > 0
+
+
+def test_get_ex_info():
+    """Test get_ex_info returns correct ExInfo"""
+    ex = LiteLLMExceptions()
+
+    # Test with a known exception type
+    from litellm import AuthenticationError
+
+    auth_error = AuthenticationError(
+        message="Invalid API key", llm_provider="openai", model="gpt-4"
+    )
+    ex_info = ex.get_ex_info(auth_error)
+    assert isinstance(ex_info, ExInfo)
+    assert ex_info.name == "AuthenticationError"
+    assert ex_info.retry is False
+    assert "API key" in ex_info.description
+
+    # Test with unknown exception type
+    class UnknownError(Exception):
+        pass
+
+    unknown = UnknownError()
+    ex_info = ex.get_ex_info(unknown)
+    assert isinstance(ex_info, ExInfo)
+    assert ex_info.name is None
+    assert ex_info.retry is None
+    assert ex_info.description is None
+
+
+def test_rate_limit_error():
+    """Test specific handling of RateLimitError"""
+    ex = LiteLLMExceptions()
+    from litellm import RateLimitError
+
+    rate_error = RateLimitError(message="Rate limit exceeded", llm_provider="openai", model="gpt-4")
+    ex_info = ex.get_ex_info(rate_error)
+    assert ex_info.retry is True
+    assert "rate limited" in ex_info.description.lower()
+
+
+def test_context_window_error():
+    """Test specific handling of ContextWindowExceededError"""
+    ex = LiteLLMExceptions()
+    from litellm import ContextWindowExceededError
+
+    ctx_error = ContextWindowExceededError(
+        message="Context length exceeded", model="gpt-4", llm_provider="openai"
+    )
+    ex_info = ex.get_ex_info(ctx_error)
+    assert ex_info.retry is False

tests/basic/test_main.py

@@ -32,7 +32,7 @@ class TestMain(TestCase):
         os.environ["HOME"] = self.homedir_obj.name
         self.input_patcher = patch("builtins.input", return_value=None)
         self.mock_input = self.input_patcher.start()
-        self.webbrowser_patcher = patch("webbrowser.open")
+        self.webbrowser_patcher = patch("aider.io.webbrowser.open")
         self.mock_webbrowser = self.webbrowser_patcher.start()
 
     def tearDown(self):
@@ -45,7 +45,7 @@ class TestMain(TestCase):
         self.webbrowser_patcher.stop()
 
     def test_main_with_empty_dir_no_files_on_command(self):
-        main(["--no-git", "--exit"], input=DummyInput(), output=DummyOutput())
+        main(["--no-git", "--exit", "--yes"], input=DummyInput(), output=DummyOutput())
 
     def test_main_with_emptqy_dir_new_file(self):
         main(["foo.txt", "--yes", "--no-git", "--exit"], input=DummyInput(), output=DummyOutput())
@@ -332,7 +332,7 @@ class TestMain(TestCase):
     def test_false_vals_in_env_file(self):
         self.create_env_file(".env", "AIDER_SHOW_DIFFS=off")
         with patch("aider.coders.Coder.create") as MockCoder:
-            main(["--no-git"], input=DummyInput(), output=DummyOutput())
+            main(["--no-git", "--yes"], input=DummyInput(), output=DummyOutput())
             MockCoder.assert_called_once()
             _, kwargs = MockCoder.call_args
             self.assertEqual(kwargs["show_diffs"], False)
@@ -340,7 +340,7 @@ class TestMain(TestCase):
     def test_true_vals_in_env_file(self):
         self.create_env_file(".env", "AIDER_SHOW_DIFFS=on")
         with patch("aider.coders.Coder.create") as MockCoder:
-            main(["--no-git"], input=DummyInput(), output=DummyOutput())
+            main(["--no-git", "--yes"], input=DummyInput(), output=DummyOutput())
             MockCoder.assert_called_once()
             _, kwargs = MockCoder.call_args
             self.assertEqual(kwargs["show_diffs"], True)
@@ -381,7 +381,11 @@ class TestMain(TestCase):
     def test_verbose_mode_lists_env_vars(self):
         self.create_env_file(".env", "AIDER_DARK_MODE=on")
         with patch("sys.stdout", new_callable=StringIO) as mock_stdout:
-            main(["--no-git", "--verbose", "--exit"], input=DummyInput(), output=DummyOutput())
+            main(
+                ["--no-git", "--verbose", "--exit", "--yes"],
+                input=DummyInput(),
+                output=DummyOutput(),
+            )
             output = mock_stdout.getvalue()
             relevant_output = "\n".join(
                 line
@@ -633,6 +637,49 @@ class TestMain(TestCase):
             )
             self.assertTrue(coder.suggest_shell_commands)
 
+    def test_detect_urls_default(self):
+        with GitTemporaryDirectory():
+            coder = main(
+                ["--exit", "--yes"],
+                input=DummyInput(),
+                output=DummyOutput(),
+                return_coder=True,
+            )
+            self.assertTrue(coder.detect_urls)
+
+    def test_detect_urls_disabled(self):
+        with GitTemporaryDirectory():
+            coder = main(
+                ["--no-detect-urls", "--exit", "--yes"],
+                input=DummyInput(),
+                output=DummyOutput(),
+                return_coder=True,
+            )
+            self.assertFalse(coder.detect_urls)
+
+    def test_detect_urls_enabled(self):
+        with GitTemporaryDirectory():
+            coder = main(
+                ["--detect-urls", "--exit", "--yes"],
+                input=DummyInput(),
+                output=DummyOutput(),
+                return_coder=True,
+            )
+            self.assertTrue(coder.detect_urls)
+
+    def test_invalid_edit_format(self):
+        with GitTemporaryDirectory():
+            with patch("aider.io.InputOutput.offer_url") as mock_offer_url:
+                result = main(
+                    ["--edit-format", "not-a-real-format", "--exit", "--yes"],
+                    input=DummyInput(),
+                    output=DummyOutput(),
+                )
+                self.assertEqual(result, 1)  # main() should return 1 on error
+                mock_offer_url.assert_called_once()
+                args, _ = mock_offer_url.call_args
+                self.assertEqual(args[0], "https://aider.chat/docs/more/edit-formats.html")
+
     def test_chat_language_spanish(self):
         with GitTemporaryDirectory():
             coder = main(

tests/basic/test_models.py

@@ -2,8 +2,10 @@ import unittest
 from unittest.mock import ANY, MagicMock, patch
 
 from aider.models import (
+    ANTHROPIC_BETA_HEADER,
     Model,
     ModelInfoManager,
+    register_models,
     sanity_check_model,
     sanity_check_models,
 )
@@ -80,7 +82,9 @@ class TestModels(unittest.TestCase):
         )  # Should return True because there's a problem with the editor model
         mock_io.tool_warning.assert_called_with(ANY)  # Ensure a warning was issued
 
-        warning_messages = [call.args[0] for call in mock_io.tool_warning.call_args_list]
+        warning_messages = [
+            warning_call.args[0] for warning_call in mock_io.tool_warning.call_args_list
+        ]
         print("Warning messages:", warning_messages)  # Add this line
 
         self.assertGreaterEqual(mock_io.tool_warning.call_count, 1)  # Expect two warnings
@@ -88,6 +92,87 @@ class TestModels(unittest.TestCase):
             any("bogus-model" in msg for msg in warning_messages)
         )  # Check that one of the warnings mentions the bogus model
 
+    def test_model_aliases(self):
+        # Test common aliases
+        model = Model("4")
+        self.assertEqual(model.name, "gpt-4-0613")
+
+        model = Model("4o")
+        self.assertEqual(model.name, "gpt-4o-2024-08-06")
+
+        model = Model("35turbo")
+        self.assertEqual(model.name, "gpt-3.5-turbo")
+
+        model = Model("35-turbo")
+        self.assertEqual(model.name, "gpt-3.5-turbo")
+
+        model = Model("3")
+        self.assertEqual(model.name, "gpt-3.5-turbo")
+
+        model = Model("sonnet")
+        self.assertEqual(model.name, "claude-3-sonnet-20241022")
+
+        model = Model("haiku")
+        self.assertEqual(model.name, "claude-3-haiku-20241022")
+
+        model = Model("opus")
+        self.assertEqual(model.name, "claude-3-opus-20240229")
+
+        # Test non-alias passes through unchanged
+        model = Model("gpt-4")
+        self.assertEqual(model.name, "gpt-4")
+
+    def test_aider_extra_model_settings(self):
+        import tempfile
+
+        import yaml
+
+        # Create temporary YAML file with test settings
+        test_settings = [
+            {
+                "name": "aider/extra_params",
+                "extra_params": {
+                    "extra_headers": {"Foo": "bar"},
+                    "some_param": "some value",
+                },
+            },
+        ]
+
+        # Write to a regular file instead of NamedTemporaryFile
+        # for better cross-platform compatibility
+        tmp = tempfile.mktemp(suffix=".yml")
+        try:
+            with open(tmp, "w") as f:
+                yaml.dump(test_settings, f)
+
+            # Register the test settings
+            register_models([tmp])
+
+            # Test that defaults are applied when no exact match
+            model = Model("claude-3-5-sonnet-20240620")
+            # Test that both the override and existing headers are present
+            model = Model("claude-3-5-sonnet-20240620")
+            self.assertEqual(model.extra_params["extra_headers"]["Foo"], "bar")
+            self.assertEqual(
+                model.extra_params["extra_headers"]["anthropic-beta"],
+                ANTHROPIC_BETA_HEADER,
+            )
+            self.assertEqual(model.extra_params["some_param"], "some value")
+            self.assertEqual(model.extra_params["max_tokens"], 8192)
+
+            # Test that exact match overrides defaults but not overrides
+            model = Model("gpt-4")
+            self.assertEqual(model.extra_params["extra_headers"]["Foo"], "bar")
+            self.assertEqual(model.extra_params["some_param"], "some value")
+        finally:
+            # Clean up the temporary file
+            import os
+
+            try:
+                os.unlink(tmp)
+            except OSError:
+                pass
+
 
 if __name__ == "__main__":
     unittest.main()

tests/basic/test_repomap.py

@@ -373,6 +373,19 @@ class TestRepoMapAllLanguages(unittest.TestCase):
 
     def test_get_repo_map_all_languages(self):
         language_files = {
+            "dart": (
+                "test.dart",
+                """void main() {
+  print('Hello, World!');
+}
+
+class Greeter {
+  String sayHello(String name) {
+    return 'Hello, $name!';
+  }
+}
+""",
+            ),
             "c": (
                 "test.c",
                 (

tests/basic/test_sanity_check_repo.py

@@ -127,8 +127,9 @@ def test_git_index_version_greater_than_2(mock_browser, create_repo, mock_io):
         "You may be able to convert your repo: git update-index --index-version=2"
     )
     mock_io.tool_output.assert_any_call("Or run aider --no-git to proceed without using git.")
-    mock_io.confirm_ask.assert_any_call(
-        "Open documentation url for more info?", subject=urls.git_index_version
+    mock_io.offer_url.assert_any_call(
+        urls.git_index_version,
+        "Open documentation url for more info?",
     )
 
 

tests/basic/test_sendchat.py

@@ -1,10 +1,9 @@
 import unittest
 from unittest.mock import MagicMock, patch
 
-import httpx
-
+from aider.exceptions import LiteLLMExceptions
 from aider.llm import litellm
-from aider.sendchat import retry_exceptions, simple_send_with_retries
+from aider.sendchat import send_completion, simple_send_with_retries
 
 
 class PrintCalled(Exception):
@@ -12,9 +11,13 @@ class PrintCalled(Exception):
 
 
 class TestSendChat(unittest.TestCase):
-    def test_retry_exceptions(self):
-        """Test that retry_exceptions() can be called without raising errors"""
-        retry_exceptions()  # Should not raise any exceptions
+    def setUp(self):
+        self.mock_messages = [{"role": "user", "content": "Hello"}]
+        self.mock_model = "gpt-4"
+
+    def test_litellm_exceptions(self):
+        litellm_ex = LiteLLMExceptions()
+        litellm_ex._load(strict=True)
 
     @patch("litellm.completion")
     @patch("builtins.print")
@@ -24,7 +27,7 @@ class TestSendChat(unittest.TestCase):
 
         # Set up the mock to raise
         mock_completion.side_effect = [
-            litellm.exceptions.RateLimitError(
+            litellm.RateLimitError(
                 "rate limit exceeded",
                 response=mock,
                 llm_provider="llm_provider",
@@ -35,17 +38,56 @@ class TestSendChat(unittest.TestCase):
 
         # Call the simple_send_with_retries method
         simple_send_with_retries("model", ["message"])
-        assert mock_print.call_count == 2
+        assert mock_print.call_count == 3
+
+    @patch("litellm.completion")
+    def test_send_completion_basic(self, mock_completion):
+        # Setup mock response
+        mock_response = MagicMock()
+        mock_completion.return_value = mock_response
+
+        # Test basic send_completion
+        hash_obj, response = send_completion(
+            self.mock_model, self.mock_messages, functions=None, stream=False
+        )
+
+        assert response == mock_response
+        mock_completion.assert_called_once()
+
+    @patch("litellm.completion")
+    def test_send_completion_with_functions(self, mock_completion):
+        mock_function = {"name": "test_function", "parameters": {"type": "object"}}
+
+        hash_obj, response = send_completion(
+            self.mock_model, self.mock_messages, functions=[mock_function], stream=False
+        )
+
+        # Verify function was properly included in tools
+        called_kwargs = mock_completion.call_args.kwargs
+        assert "tools" in called_kwargs
+        assert called_kwargs["tools"][0]["function"] == mock_function
+
+    @patch("litellm.completion")
+    def test_simple_send_attribute_error(self, mock_completion):
+        # Setup mock to raise AttributeError
+        mock_completion.return_value = MagicMock()
+        mock_completion.return_value.choices = None
+
+        # Should return None on AttributeError
+        result = simple_send_with_retries(self.mock_model, self.mock_messages)
+        assert result is None
 
     @patch("litellm.completion")
     @patch("builtins.print")
-    def test_simple_send_with_retries_connection_error(self, mock_print, mock_completion):
-        # Set up the mock to raise
-        mock_completion.side_effect = [
-            httpx.ConnectError("Connection error"),
-            None,
-        ]
+    def test_simple_send_non_retryable_error(self, mock_print, mock_completion):
+        # Test with an error that shouldn't trigger retries
+        mock = MagicMock()
+        mock.status_code = 400
 
-        # Call the simple_send_with_retries method
-        simple_send_with_retries("model", ["message"])
-        assert mock_print.call_count == 2
+        mock_completion.side_effect = litellm.NotFoundError(
+            message="Invalid request", llm_provider="test_provider", model="test_model"
+        )
+
+        result = simple_send_with_retries(self.mock_model, self.mock_messages)
+        assert result is None
+        assert mock_print.call_count == 1

tests/scrape/test_scrape.py

@@ -44,7 +44,7 @@ class TestScrape(unittest.TestCase):
         self.commands.io.tool_error = mock_print_error
 
         # Run the cmd_web command
-        result = self.commands.cmd_web("https://example.com")
+        result = self.commands.cmd_web("https://example.com", return_content=True)
 
         # Assert that the result contains some content
         self.assertIsNotNone(result)