Merge branch 'main' into json-coders

.github/workflows/release.yml

@@ -21,12 +21,12 @@ jobs:
     - name: Install dependencies
       run: |
         python -m pip install --upgrade pip
-        pip install setuptools wheel twine importlib-metadata==7.2.1
+        pip install build setuptools wheel twine importlib-metadata==7.2.1
 
     - name: Build and publish
       env:
         TWINE_USERNAME: __token__
         TWINE_PASSWORD: ${{ secrets.PYPI_API_TOKEN }}
       run: |
-        python setup.py sdist bdist_wheel
+        python -m build
         twine upload dist/*

.gitignore

@@ -5,6 +5,7 @@ aider.code-workspace
 .aider*
 aider_chat.egg-info/
 build
+dist/
 Gemfile.lock
 _site
 .jekyll-cache/

HISTORY.md

@@ -1,6 +1,51 @@
 
 # Release history
 
+### Aider v0.50.0
+
+- Infinite output for DeepSeek Coder, Mistral models in addition to Anthropic's models.
+- New `--deepseek` switch to use DeepSeek Coder.
+- DeepSeek Coder uses 8k token output.
+- New `--chat-mode <mode>` switch to launch in ask/help/code modes.
+- New `/code <message>` command request a code edit while in `ask` mode.
+- Web scraper is more robust if page never idles.
+- Improved token and cost reporting for infinite output.
+- Improvements and bug fixes for `/read` only files.
+- Switched from `setup.py` to `pyproject.toml`, by @branchvincent.
+- Bug fix to persist files added during `/ask`.
+- Bug fix for chat history size in `/tokens`.
+- Aider wrote 66% of the code in this release.
+
+### Aider v0.49.1
+
+- Bugfix to `/help`.
+
+### Aider v0.49.0
+
+- Add read-only files to the chat context with `/read` and `--read`,  including from outside the git repo.
+- `/diff` now shows diffs of all changes resulting from your request, including lint and test fixes.
+- New `/clipboard` command to paste images or text from the clipboard, replaces `/add-clipboard-image`.
+- Now shows the markdown scraped when you add a url with `/web`.
+- When [scripting aider](https://aider.chat/docs/scripting.html) messages can now contain in-chat `/` commands.
+- Aider in docker image now suggests the correct command to update to latest version.
+- Improved retries on API errors (was easy to test during Sonnet outage).
+- Added `--mini` for `gpt-4o-mini`.
+- Bugfix to keep session cost accurate when using `/ask` and `/help`.
+- Performance improvements for repo map calculation.
+- `/tokens` now shows the active model.
+- Enhanced commit message attribution options:
+  - New `--attribute-commit-message-author` to prefix commit messages with 'aider: ' if aider authored the changes, replaces `--attribute-commit-message`.
+  - New `--attribute-commit-message-committer` to prefix all commit messages with 'aider: '.
+- Aider wrote 61% of the code in this release.
+
+### Aider v0.48.1
+
+- Added `openai/gpt-4o-2024-08-06`.
+- Worked around litellm bug that removes OpenRouter app headers when using `extra_headers`.
+- Improved progress indication during repo map processing.
+- Corrected instructions for upgrading the docker container to latest aider version.
+- Removed obsolete 16k token limit on commit diffs, use per-model limits.
+
 ### Aider v0.48.0
 
 - Performance improvements for large/mono repos.

MANIFEST.in

@@ -1 +0,0 @@
-include requirements.txt

README.md

@@ -35,18 +35,18 @@ cog.out(open("aider/website/_includes/get-started.md").read())
 You can get started quickly like this:
 
 ```
-$ pip install aider-chat
+python -m pip install aider-chat
 
 # Change directory into a git repo
-$ cd /to/your/git/repo
+cd /to/your/git/repo
 
 # Work with Claude 3.5 Sonnet on your repo
-$ export ANTHROPIC_API_KEY=your-key-goes-here
-$ aider
+export ANTHROPIC_API_KEY=your-key-goes-here
+aider
 
 # Work with GPT-4o on your repo
-$ export OPENAI_API_KEY=your-key-goes-here
-$ aider 
+export OPENAI_API_KEY=your-key-goes-here
+aider 
 ```
 <!--[[[end]]]-->
 

aider/__init__.py

@@ -1 +1 @@
-__version__ = "0.48.1-dev"
+__version__ = "0.50.1-dev"

aider/args.py

@@ -82,6 +82,14 @@ def get_parser(default_config_files, git_root):
         const=gpt_4o_model,
         help=f"Use {gpt_4o_model} model for the main chat",
     )
+    gpt_4o_mini_model = "gpt-4o-mini"
+    group.add_argument(
+        "--mini",
+        action="store_const",
+        dest="model",
+        const=gpt_4o_mini_model,
+        help=f"Use {gpt_4o_mini_model} model for the main chat",
+    )
     gpt_4_turbo_model = "gpt-4-1106-preview"
     group.add_argument(
         "--4-turbo",
@@ -101,6 +109,14 @@ def get_parser(default_config_files, git_root):
         const=gpt_3_model_name,
         help=f"Use {gpt_3_model_name} model for the main chat",
     )
+    deepseek_model = "deepseek/deepseek-coder"
+    group.add_argument(
+        "--deepseek",
+        action="store_const",
+        dest="model",
+        const=deepseek_model,
+        help=f"Use {deepseek_model} model for the main chat",
+    )
 
     ##########
     group = parser.add_argument_group("Model Settings")
@@ -159,6 +175,7 @@ def get_parser(default_config_files, git_root):
     )
     group.add_argument(
         "--edit-format",
+        "--chat-mode",
         metavar="EDIT_FORMAT",
         default=None,
         help="Specify what edit format the LLM should use (default depends on model)",
@@ -350,10 +367,16 @@ def get_parser(default_config_files, git_root):
         help="Attribute aider commits in the git committer name (default: True)",
     )
     group.add_argument(
-        "--attribute-commit-message",
+        "--attribute-commit-message-author",
         action=argparse.BooleanOptionalAction,
         default=False,
-        help="Prefix commit messages with 'aider: ' (default: False)",
+        help="Prefix commit messages with 'aider: ' if aider authored the changes (default: False)",
+    )
+    group.add_argument(
+        "--attribute-commit-message-committer",
+        action=argparse.BooleanOptionalAction,
+        default=False,
+        help="Prefix all commit messages with 'aider: ' (default: False)",
     )
     group.add_argument(
         "--commit",
@@ -420,6 +443,12 @@ def get_parser(default_config_files, git_root):
         metavar="FILE",
         help="specify a file to edit (can be used multiple times)",
     )
+    group.add_argument(
+        "--read",
+        action="append",
+        metavar="FILE",
+        help="specify a read-only file (can be used multiple times)",
+    )
     group.add_argument(
         "--vim",
         action="store_true",

aider/coders/base_coder.py

@@ -30,7 +30,7 @@ from aider.llm import litellm
 from aider.mdstream import MarkdownStream
 from aider.repo import GitRepo
 from aider.repomap import RepoMap
-from aider.sendchat import send_with_retries
+from aider.sendchat import retry_exceptions, send_completion
 from aider.utils import format_content, format_messages, is_image_file
 
 from ..dump import dump  # noqa: F401
@@ -50,6 +50,7 @@ def wrap_fence(name):
 
 class Coder:
     abs_fnames = None
+    abs_read_only_fnames = None
     repo = None
     last_aider_commit_hash = None
     aider_edited_files = None
@@ -70,6 +71,11 @@ class Coder:
     lint_outcome = None
     test_outcome = None
     multi_response_content = ""
+    partial_response_content = ""
+    commit_before_message = []
+    message_cost = 0.0
+    message_tokens_sent = 0
+    message_tokens_received = 0
 
     @classmethod
     def create(
@@ -89,6 +95,8 @@ class Coder:
             else:
                 main_model = models.Model(models.DEFAULT_MODEL_NAME)
 
+        if edit_format == "code":
+            edit_format = None
         if edit_format is None:
             if from_coder:
                 edit_format = from_coder.edit_format
@@ -112,6 +120,7 @@ class Coder:
             # Bring along context from the old Coder
             update = dict(
                 fnames=list(from_coder.abs_fnames),
+                read_only_fnames=list(from_coder.abs_read_only_fnames),  # Copy read-only files
                 done_messages=done_messages,
                 cur_messages=from_coder.cur_messages,
                 aider_commit_hashes=from_coder.aider_commit_hashes,
@@ -143,7 +152,10 @@ class Coder:
         main_model = self.main_model
         weak_model = main_model.weak_model
         prefix = "Model:"
-        output = f" {main_model.name} with {self.edit_format} edit format"
+        output = f" {main_model.name} with"
+        if main_model.info.get("supports_assistant_prefill"):
+            output += " ♾️"
+        output += f" {self.edit_format} edit format"
         if weak_model is not main_model:
             prefix = "Models:"
             output += f", weak model {weak_model.name}"
@@ -193,7 +205,7 @@ class Coder:
         io,
         repo=None,
         fnames=None,
-        pretty=True,
+        read_only_fnames=None,
         show_diffs=False,
         auto_commits=True,
         dirty_commits=True,
@@ -217,6 +229,7 @@ class Coder:
         summarizer=None,
         total_cost=0.0,
     ):
+        self.commit_before_message = []
         self.aider_commit_hashes = set()
         self.rejected_urls = set()
         self.abs_root_path_cache = {}
@@ -240,6 +253,7 @@ class Coder:
 
         self.verbose = verbose
         self.abs_fnames = set()
+        self.abs_read_only_fnames = set()
 
         if cur_messages:
             self.cur_messages = cur_messages
@@ -263,9 +277,9 @@ class Coder:
         self.code_theme = code_theme
 
         self.dry_run = dry_run
-        self.pretty = pretty
+        self.pretty = self.io.pretty
 
-        if pretty:
+        if self.pretty:
             self.console = Console()
         else:
             self.console = Console(force_terminal=False, no_color=True)
@@ -314,6 +328,15 @@ class Coder:
         if not self.repo:
             self.find_common_root()
 
+        if read_only_fnames:
+            self.abs_read_only_fnames = set()
+            for fname in read_only_fnames:
+                abs_fname = self.abs_root_path(fname)
+                if os.path.exists(abs_fname):
+                    self.abs_read_only_fnames.add(abs_fname)
+                else:
+                    self.io.tool_error(f"Error: Read-only file {fname} does not exist. Skipping.")
+
         if map_tokens is None:
             use_repo_map = main_model.use_repo_map
             map_tokens = 1024
@@ -376,8 +399,10 @@ class Coder:
             self.linter.set_linter(lang, cmd)
 
     def show_announcements(self):
+        bold = True
         for line in self.get_announcements():
-            self.io.tool_output(line)
+            self.io.tool_output(line, bold=bold)
+            bold = False
 
     def find_common_root(self):
         if len(self.abs_fnames) == 1:
@@ -444,6 +469,10 @@ class Coder:
         all_content = ""
         for _fname, content in self.get_abs_fnames_content():
             all_content += content + "\n"
+        for _fname in self.abs_read_only_fnames:
+            content = self.io.read_text(_fname)
+            if content is not None:
+                all_content += content + "\n"
 
         good = False
         for fence_open, fence_close in self.fences:
@@ -485,6 +514,19 @@ class Coder:
 
         return prompt
 
+    def get_read_only_files_content(self):
+        prompt = ""
+        for fname in self.abs_read_only_fnames:
+            content = self.io.read_text(fname)
+            if content is not None and not is_image_file(fname):
+                relative_fname = self.get_rel_fname(fname)
+                prompt += "\n"
+                prompt += relative_fname
+                prompt += f"\n{self.fence[0]}\n"
+                prompt += content
+                prompt += f"{self.fence[1]}\n"
+        return prompt
+
     def get_cur_message_text(self):
         text = ""
         for msg in self.cur_messages:
@@ -522,9 +564,13 @@ class Coder:
 
         mentioned_fnames.update(self.get_ident_filename_matches(mentioned_idents))
 
-        other_files = set(self.get_all_abs_files()) - set(self.abs_fnames)
+        all_abs_files = set(self.get_all_abs_files())
+        repo_abs_read_only_fnames = set(self.abs_read_only_fnames) & all_abs_files
+        chat_files = set(self.abs_fnames) | repo_abs_read_only_fnames
+        other_files = all_abs_files - chat_files
+
         repo_content = self.repo_map.get_repo_map(
-            self.abs_fnames,
+            chat_files,
             other_files,
             mentioned_fnames=mentioned_fnames,
             mentioned_idents=mentioned_idents,
@@ -534,7 +580,7 @@ class Coder:
         if not repo_content:
             repo_content = self.repo_map.get_repo_map(
                 set(),
-                set(self.get_all_abs_files()),
+                all_abs_files,
                 mentioned_fnames=mentioned_fnames,
                 mentioned_idents=mentioned_idents,
             )
@@ -543,7 +589,7 @@ class Coder:
         if not repo_content:
             repo_content = self.repo_map.get_repo_map(
                 set(),
-                set(self.get_all_abs_files()),
+                all_abs_files,
             )
 
         return repo_content
@@ -572,12 +618,6 @@ class Coder:
             files_content = self.gpt_prompts.files_no_full_files
             files_reply = "Ok."
 
-        if files_content:
-            files_messages += [
-                dict(role="user", content=files_content),
-                dict(role="assistant", content=files_reply),
-            ]
-
         images_message = self.get_images_message()
         if images_message is not None:
             files_messages += [
@@ -585,6 +625,24 @@ class Coder:
                 dict(role="assistant", content="Ok."),
             ]
 
+        read_only_content = self.get_read_only_files_content()
+        if read_only_content:
+            files_messages += [
+                dict(
+                    role="user", content=self.gpt_prompts.read_only_files_prefix + read_only_content
+                ),
+                dict(
+                    role="assistant",
+                    content="Ok, I will use these files as references.",
+                ),
+            ]
+
+        if files_content:
+            files_messages += [
+                dict(role="user", content=files_content),
+                dict(role="assistant", content=files_reply),
+            ]
+
         return files_messages
 
     def get_images_message(self):
@@ -597,9 +655,11 @@ class Coder:
                 mime_type, _ = mimetypes.guess_type(fname)
                 if mime_type and mime_type.startswith("image/"):
                     image_url = f"data:{mime_type};base64,{content}"
-                    image_messages.append(
-                        {"type": "image_url", "image_url": {"url": image_url, "detail": "high"}}
-                    )
+                    rel_fname = self.get_rel_fname(fname)
+                    image_messages += [
+                        {"type": "text", "text": f"Image file: {rel_fname}"},
+                        {"type": "image_url", "image_url": {"url": image_url, "detail": "high"}},
+                    ]
 
         if not image_messages:
             return None
@@ -609,7 +669,7 @@ class Coder:
     def run_stream(self, user_message):
         self.io.user_input(user_message)
         self.init_before_message()
-        yield from self.send_new_user_message(user_message)
+        yield from self.send_message(user_message)
 
     def init_before_message(self):
         self.reflected_message = None
@@ -617,48 +677,39 @@ class Coder:
         self.lint_outcome = None
         self.test_outcome = None
         self.edit_outcome = None
+        if self.repo:
+            self.commit_before_message.append(self.repo.get_head())
 
-    def run(self, with_message=None):
-        while True:
-            self.init_before_message()
+    def run(self, with_message=None, preproc=True):
+        try:
+            if with_message:
+                self.io.user_input(with_message)
+                self.run_one(with_message, preproc)
+                return self.partial_response_content
 
-            try:
-                if with_message:
-                    new_user_message = with_message
-                    self.io.user_input(with_message)
-                else:
-                    new_user_message = self.run_loop()
+            while True:
+                try:
+                    user_message = self.get_input()
+                    self.run_one(user_message, preproc)
+                    self.show_undo_hint()
+                except KeyboardInterrupt:
+                    self.keyboard_interrupt()
+        except EOFError:
+            return
 
-                while new_user_message:
-                    self.reflected_message = None
-                    list(self.send_new_user_message(new_user_message))
-
-                    new_user_message = None
-                    if self.reflected_message:
-                        if self.num_reflections < self.max_reflections:
-                            self.num_reflections += 1
-                            new_user_message = self.reflected_message
-                        else:
-                            self.io.tool_error(
-                                f"Only {self.max_reflections} reflections allowed, stopping."
-                            )
-
-                if with_message:
-                    return self.partial_response_content
-
-            except KeyboardInterrupt:
-                self.keyboard_interrupt()
-            except EOFError:
-                return
-
-    def run_loop(self):
-        inp = self.io.get_input(
+    def get_input(self):
+        inchat_files = self.get_inchat_relative_files()
+        read_only_files = [self.get_rel_fname(fname) for fname in self.abs_read_only_fnames]
+        all_files = sorted(set(inchat_files + read_only_files))
+        return self.io.get_input(
             self.root,
-            self.get_inchat_relative_files(),
+            all_files,
             self.get_addable_relative_files(),
             self.commands,
+            self.abs_read_only_fnames,
         )
 
+    def preproc_user_input(self, inp):
         if not inp:
             return
 
@@ -670,6 +721,28 @@ class Coder:
 
         return inp
 
+    def run_one(self, user_message, preproc):
+        self.init_before_message()
+
+        if preproc:
+            message = self.preproc_user_input(user_message)
+        else:
+            message = user_message
+
+        while message:
+            self.reflected_message = None
+            list(self.send_message(message))
+
+            if not self.reflected_message:
+                break
+
+            if self.num_reflections >= self.max_reflections:
+                self.io.tool_error(f"Only {self.max_reflections} reflections allowed, stopping.")
+                return
+
+            self.num_reflections += 1
+            message = self.reflected_message
+
     def check_for_urls(self, inp):
         url_pattern = re.compile(r"(https?://[^\s/$.?#].[^\s]*[^\s,.])")
         urls = list(set(url_pattern.findall(inp)))  # Use set to remove duplicates
@@ -678,7 +751,7 @@ class Coder:
             if url not in self.rejected_urls:
                 if self.io.confirm_ask(f"Add {url} to the chat?"):
                     inp += "\n\n"
-                    inp += self.commands.cmd_web(url)
+                    inp += self.commands.cmd_web(url, paginate=False)
                     added_urls.append(url)
                 else:
                     self.rejected_urls.add(url)
@@ -826,6 +899,7 @@ class Coder:
 
         self.summarize_end()
         messages += self.done_messages
+
         messages += self.get_files_messages()
 
         if self.gpt_prompts.system_reminder:
@@ -852,7 +926,7 @@ class Coder:
 
         final = messages[-1]
 
-        max_input_tokens = self.main_model.info.get("max_input_tokens")
+        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
@@ -872,7 +946,7 @@ class Coder:
 
         return messages
 
-    def send_new_user_message(self, inp):
+    def send_message(self, inp):
         self.aider_edited_files = None
 
         self.cur_messages += [
@@ -891,6 +965,8 @@ class Coder:
         else:
             self.mdstream = None
 
+        retry_delay = 0.125
+
         self.usage_report = None
         exhausted = False
         interrupted = False
@@ -899,6 +975,14 @@ class Coder:
                 try:
                     yield from self.send(messages, functions=self.functions)
                     break
+                except retry_exceptions() as err:
+                    self.io.tool_error(str(err))
+                    retry_delay *= 2
+                    if retry_delay > 60:
+                        break
+                    self.io.tool_output(f"Retrying in {retry_delay:.1f} seconds...")
+                    time.sleep(retry_delay)
+                    continue
                 except KeyboardInterrupt:
                     interrupted = True
                     break
@@ -911,7 +995,7 @@ class Coder:
                     return
                 except FinishReasonLength:
                     # We hit the output limit!
-                    if not self.main_model.can_prefill:
+                    if not self.main_model.info.get("supports_assistant_prefill"):
                         exhausted = True
                         break
 
@@ -920,7 +1004,9 @@ class Coder:
                     if messages[-1]["role"] == "assistant":
                         messages[-1]["content"] = self.multi_response_content
                     else:
-                        messages.append(dict(role="assistant", content=self.multi_response_content))
+                        messages.append(
+                            dict(role="assistant", content=self.multi_response_content, prefix=True)
+                        )
                 except Exception as err:
                     self.io.tool_error(f"Unexpected error: {err}")
                     traceback.print_exc()
@@ -935,8 +1021,7 @@ class Coder:
 
         self.io.tool_output()
 
-        if self.usage_report:
-            self.io.tool_output(self.usage_report)
+        self.show_usage_report()
 
         if exhausted:
             self.show_exhausted_error()
@@ -1011,10 +1096,10 @@ class Coder:
         output_tokens = 0
         if self.partial_response_content:
             output_tokens = self.main_model.token_count(self.partial_response_content)
-        max_output_tokens = self.main_model.info.get("max_output_tokens", 0)
+        max_output_tokens = self.main_model.info.get("max_output_tokens") or 0
 
         input_tokens = self.main_model.token_count(self.format_messages())
-        max_input_tokens = self.main_model.info.get("max_input_tokens", 0)
+        max_input_tokens = self.main_model.info.get("max_input_tokens") or 0
 
         total_tokens = input_tokens + output_tokens
 
@@ -1159,9 +1244,8 @@ class Coder:
 
         self.io.log_llm_history("TO LLM", format_messages(messages))
 
-        interrupted = False
         try:
-            hash_object, completion = send_with_retries(
+            hash_object, completion = send_completion(
                 model.name,
                 messages,
                 functions,
@@ -1176,9 +1260,9 @@ class Coder:
                 yield from self.show_send_output_stream(completion)
             else:
                 self.show_send_output(completion)
-        except KeyboardInterrupt:
+        except KeyboardInterrupt as kbi:
             self.keyboard_interrupt()
-            interrupted = True
+            raise kbi
         finally:
             self.io.log_llm_history(
                 "LLM RESPONSE",
@@ -1193,10 +1277,7 @@ class Coder:
                 if args:
                     self.io.ai_output(json.dumps(args, indent=4))
 
-        if interrupted:
-            raise KeyboardInterrupt
-
-        self.calculate_and_show_tokens_and_cost(messages, completion)
+            self.calculate_and_show_tokens_and_cost(messages, completion)
 
     def show_send_output(self, completion):
         if self.verbose:
@@ -1218,7 +1299,7 @@ class Coder:
             show_func_err = func_err
 
         try:
-            self.partial_response_content = completion.choices[0].message.content
+            self.partial_response_content = completion.choices[0].message.content or ""
         except AttributeError as content_err:
             show_content_err = content_err
 
@@ -1312,13 +1393,19 @@ class Coder:
             prompt_tokens = self.main_model.token_count(messages)
             completion_tokens = self.main_model.token_count(self.partial_response_content)
 
-        self.usage_report = f"Tokens: {prompt_tokens:,} sent, {completion_tokens:,} received."
+        self.message_tokens_sent += prompt_tokens
+        self.message_tokens_received += completion_tokens
+
+        tokens_report = (
+            f"Tokens: {self.message_tokens_sent:,} sent, {self.message_tokens_received:,} received."
+        )
 
         if self.main_model.info.get("input_cost_per_token"):
             cost += prompt_tokens * self.main_model.info.get("input_cost_per_token")
             if self.main_model.info.get("output_cost_per_token"):
                 cost += completion_tokens * self.main_model.info.get("output_cost_per_token")
             self.total_cost += cost
+            self.message_cost += cost
 
             def format_cost(value):
                 if value == 0:
@@ -1329,13 +1416,24 @@ class Coder:
                 else:
                     return f"{value:.{max(2, 2 - int(math.log10(magnitude)))}f}"
 
-            self.usage_report += (
-                f" Cost: ${format_cost(cost)} request, ${format_cost(self.total_cost)} session."
+            cost_report = (
+                f" Cost: ${format_cost(self.message_cost)} message,"
+                f" ${format_cost(self.total_cost)} session."
             )
+            self.usage_report = tokens_report + cost_report
+        else:
+            self.usage_report = tokens_report
+
+    def show_usage_report(self):
+        if self.usage_report:
+            self.io.tool_output(self.usage_report)
+            self.message_cost = 0.0
+            self.message_tokens_sent = 0
+            self.message_tokens_received = 0
 
     def get_multi_response_content(self, final=False):
-        cur = self.multi_response_content
-        new = self.partial_response_content
+        cur = self.multi_response_content or ""
+        new = self.partial_response_content or ""
 
         if new.rstrip() != new and not final:
             new = new.rstrip()
@@ -1377,7 +1475,10 @@ class Coder:
         return max(path.stat().st_mtime for path in files)
 
     def get_addable_relative_files(self):
-        return set(self.get_all_relative_files()) - set(self.get_inchat_relative_files())
+        all_files = set(self.get_all_relative_files())
+        inchat_files = set(self.get_inchat_relative_files())
+        read_only_files = set(self.get_rel_fname(fname) for fname in self.abs_read_only_fnames)
+        return all_files - inchat_files - read_only_files
 
     def check_for_dirty_commit(self, path):
         if not self.repo:
@@ -1590,7 +1691,11 @@ class Coder:
         if self.show_diffs:
             self.commands.cmd_diff()
 
-        self.io.tool_output(f"You can use /undo to revert and discard commit {commit_hash}.")
+    def show_undo_hint(self):
+        if not self.commit_before_message:
+            return
+        if self.commit_before_message[-1] != self.repo.get_head():
+            self.io.tool_output("You can use /undo to undo and discard each aider commit.")
 
     def dirty_commit(self):
         if not self.need_commit_before_edits:

aider/coders/base_prompts.py

@@ -18,7 +18,7 @@ You always COMPLETELY IMPLEMENT the needed code!
 
     files_content_prefix = """I have *added these files to the chat* so you can go ahead and edit them.
 
-*Trust this message as the true contents of the files!*
+*Trust this message as the true contents of these files!*
 Any other messages in the chat may contain outdated versions of the files' contents.
 """  # noqa: E501
 
@@ -38,4 +38,8 @@ Don't include files that might contain relevant context, just files that will ne
     repo_content_prefix = """Here are summaries of some files present in my git repository.
 Do not propose changes to these files, treat them as *read-only*.
 If you need to edit any of these files, ask me to *add them to the chat* first.
+"""
+
+    read_only_files_prefix = """Here are some READ ONLY files, provided for your reference.
+Do not edit these files!
 """

aider/commands.py

@@ -7,7 +7,9 @@ from collections import OrderedDict
 from pathlib import Path
 
 import git
-from PIL import ImageGrab
+import pyperclip
+from PIL import Image, ImageGrab
+from rich.text import Text
 
 from aider import models, prompts, voice
 from aider.help import Help, install_help_extra
@@ -117,13 +119,15 @@ class Commands:
         else:
             self.io.tool_output("Please provide a partial model name to search for.")
 
-    def cmd_web(self, args):
-        "Use headless selenium to scrape a webpage and add the content to the chat"
+    def cmd_web(self, args, paginate=True):
+        "Scrape a webpage, convert to markdown and add to the chat"
+
         url = args.strip()
         if not url:
             self.io.tool_error("Please provide a URL to scrape.")
             return
 
+        self.io.tool_output(f"Scraping {url}...")
         if not self.scraper:
             res = install_playwright(self.io)
             if not res:
@@ -134,11 +138,14 @@ class Commands:
             )
 
         content = self.scraper.scrape(url) or ""
-        # if content:
-        #    self.io.tool_output(content)
-
         content = f"{url}:\n\n" + content
 
+        self.io.tool_output("... done.")
+
+        if paginate:
+            with self.io.console.pager():
+                self.io.console.print(Text(content))
+
         return content
 
     def is_command(self, inp):
@@ -304,7 +311,6 @@ class Commands:
         # chat history
         msgs = self.coder.done_messages + self.coder.cur_messages
         if msgs:
-            msgs = [dict(role="dummy", content=msg) for msg in msgs]
             tokens = self.coder.main_model.token_count(msgs)
             res.append((tokens, "chat history", "use /clear to clear"))
 
@@ -316,6 +322,8 @@ class Commands:
                 tokens = self.coder.main_model.token_count(repo_content)
                 res.append((tokens, "repository map", "use --map-tokens to resize"))
 
+        fence = "`" * 3
+
         # files
         for fname in self.coder.abs_fnames:
             relative_fname = self.coder.get_rel_fname(fname)
@@ -324,11 +332,23 @@ class Commands:
                 tokens = self.coder.main_model.token_count_for_image(fname)
             else:
                 # approximate
-                content = f"{relative_fname}\n```\n" + content + "```\n"
+                content = f"{relative_fname}\n{fence}\n" + content + "{fence}\n"
                 tokens = self.coder.main_model.token_count(content)
-            res.append((tokens, f"{relative_fname}", "use /drop to drop from chat"))
+            res.append((tokens, f"{relative_fname}", "/drop to remove"))
 
-        self.io.tool_output("Approximate context window usage, in tokens:")
+        # read-only files
+        for fname in self.coder.abs_read_only_fnames:
+            relative_fname = self.coder.get_rel_fname(fname)
+            content = self.io.read_text(fname)
+            if content is not None and not is_image_file(relative_fname):
+                # approximate
+                content = f"{relative_fname}\n{fence}\n" + content + "{fence}\n"
+                tokens = self.coder.main_model.token_count(content)
+                res.append((tokens, f"{relative_fname} (read-only)", "/drop to remove"))
+
+        self.io.tool_output(
+            f"Approximate context window usage for {self.coder.main_model.name}, in tokens:"
+        )
         self.io.tool_output()
 
         width = 8
@@ -344,7 +364,7 @@ class Commands:
         total_cost = 0.0
         for tk, msg, tip in res:
             total += tk
-            cost = tk * self.coder.main_model.info.get("input_cost_per_token", 0)
+            cost = tk * (self.coder.main_model.info.get("input_cost_per_token") or 0)
             total_cost += cost
             msg = msg.ljust(col_width)
             self.io.tool_output(f"${cost:7.4f} {fmt(tk)} {msg} {tip}")  # noqa: E231
@@ -352,7 +372,7 @@ class Commands:
         self.io.tool_output("=" * (width + cost_width + 1))
         self.io.tool_output(f"${total_cost:7.4f} {fmt(total)} tokens total")  # noqa: E231
 
-        limit = self.coder.main_model.info.get("max_input_tokens", 0)
+        limit = self.coder.main_model.info.get("max_input_tokens") or 0
         if not limit:
             return
 
@@ -440,27 +460,36 @@ class Commands:
         # Get the current HEAD after undo
         current_head_hash = self.coder.repo.repo.head.commit.hexsha[:7]
         current_head_message = self.coder.repo.repo.head.commit.message.strip()
-        self.io.tool_output(f"HEAD is: {current_head_hash} {current_head_message}")
+        self.io.tool_output(f"Now at:  {current_head_hash} {current_head_message}")
 
         if self.coder.main_model.send_undo_reply:
             return prompts.undo_command_reply
 
     def cmd_diff(self, args=""):
-        "Display the diff of the last aider commit"
+        "Display the diff of changes since the last message"
         if not self.coder.repo:
             self.io.tool_error("No git repository found.")
             return
 
-        last_commit_hash = self.coder.repo.repo.head.commit.hexsha[:7]
-
-        if last_commit_hash not in self.coder.aider_commit_hashes:
-            self.io.tool_error(f"Last commit {last_commit_hash} was not an aider commit.")
-            self.io.tool_error("You could try `/git diff` or `/git diff HEAD^`.")
+        current_head = self.coder.repo.get_head()
+        if current_head is None:
+            self.io.tool_error("Unable to get current commit. The repository might be empty.")
             return
 
+        if len(self.coder.commit_before_message) < 2:
+            commit_before_message = current_head + "^"
+        else:
+            commit_before_message = self.coder.commit_before_message[-2]
+
+        if not commit_before_message or commit_before_message == current_head:
+            self.io.tool_error("No changes to display since the last message.")
+            return
+
+        self.io.tool_output(f"Diff since {commit_before_message[:7]}...")
+
         diff = self.coder.repo.diff_commits(
             self.coder.pretty,
-            "HEAD^",
+            commit_before_message,
             "HEAD",
         )
 
@@ -472,6 +501,9 @@ class Commands:
             fname = f'"{fname}"'
         return fname
 
+    def completions_read(self):
+        return self.completions_add()
+
     def completions_add(self):
         files = set(self.coder.get_all_relative_files())
         files = files - set(self.coder.get_inchat_relative_files())
@@ -558,6 +590,18 @@ class Commands:
 
             if abs_file_path in self.coder.abs_fnames:
                 self.io.tool_error(f"{matched_file} is already in the chat")
+            elif abs_file_path in self.coder.abs_read_only_fnames:
+                if self.coder.repo and self.coder.repo.path_in_repo(matched_file):
+                    self.coder.abs_read_only_fnames.remove(abs_file_path)
+                    self.coder.abs_fnames.add(abs_file_path)
+                    self.io.tool_output(
+                        f"Moved {matched_file} from read-only to editable files in the chat"
+                    )
+                    added_fnames.append(matched_file)
+                else:
+                    self.io.tool_error(
+                        f"Cannot add {matched_file} as it's not part of the repository"
+                    )
             else:
                 if is_image_file(matched_file) and not self.coder.main_model.accepts_images:
                     self.io.tool_error(
@@ -575,20 +619,12 @@ class Commands:
                     self.coder.check_added_files()
                     added_fnames.append(matched_file)
 
-        if not added_fnames:
-            return
-
-        # only reply if there's been some chatting since the last edit
-        if not self.coder.cur_messages:
-            return
-
-        reply = prompts.added_files.format(fnames=", ".join(added_fnames))
-        return reply
-
     def completions_drop(self):
         files = self.coder.get_inchat_relative_files()
-        files = [self.quote_fname(fn) for fn in files]
-        return files
+        read_only_files = [self.coder.get_rel_fname(fn) for fn in self.coder.abs_read_only_fnames]
+        all_files = files + read_only_files
+        all_files = [self.quote_fname(fn) for fn in all_files]
+        return all_files
 
     def cmd_drop(self, args=""):
         "Remove files from the chat session to free up context space"
@@ -596,9 +632,19 @@ class Commands:
         if not args.strip():
             self.io.tool_output("Dropping all files from the chat session.")
             self.coder.abs_fnames = set()
+            self.coder.abs_read_only_fnames = set()
+            return
 
         filenames = parse_quoted_filenames(args)
         for word in filenames:
+            # Handle read-only files separately, without glob_filtered_to_repo
+            read_only_matched = [f for f in self.coder.abs_read_only_fnames if word in f]
+
+            if read_only_matched:
+                for matched_file in read_only_matched:
+                    self.coder.abs_read_only_fnames.remove(matched_file)
+                    self.io.tool_output(f"Removed read-only file {matched_file} from the chat")
+
             matched_files = self.glob_filtered_to_repo(word)
 
             if not matched_files:
@@ -678,7 +724,7 @@ class Commands:
             add = result.returncode != 0
         else:
             response = self.io.prompt_ask(
-                "Add the output to the chat? (y/n/instructions): ", default="y"
+                "Add the output to the chat?\n(y/n/instructions)", default=""
             ).strip()
 
             if response.lower() in ["yes", "y"]:
@@ -718,6 +764,7 @@ class Commands:
 
         other_files = []
         chat_files = []
+        read_only_files = []
         for file in files:
             abs_file_path = self.coder.abs_root_path(file)
             if abs_file_path in self.coder.abs_fnames:
@@ -725,8 +772,13 @@ class Commands:
             else:
                 other_files.append(file)
 
-        if not chat_files and not other_files:
-            self.io.tool_output("\nNo files in chat or git repo.")
+        # Add read-only files
+        for abs_file_path in self.coder.abs_read_only_fnames:
+            rel_file_path = self.coder.get_rel_fname(abs_file_path)
+            read_only_files.append(rel_file_path)
+
+        if not chat_files and not other_files and not read_only_files:
+            self.io.tool_output("\nNo files in chat, git repo, or read-only list.")
             return
 
         if other_files:
@@ -734,6 +786,11 @@ class Commands:
         for file in other_files:
             self.io.tool_output(f"  {file}")
 
+        if read_only_files:
+            self.io.tool_output("\nRead-only files:\n")
+        for file in read_only_files:
+            self.io.tool_output(f"  {file}")
+
         if chat_files:
             self.io.tool_output("\nFiles in chat:\n")
         for file in chat_files:
@@ -787,13 +844,23 @@ class Commands:
 """
         user_msg += "\n".join(self.coder.get_announcements()) + "\n"
 
-        assistant_msg = coder.run(user_msg)
+        coder.run(user_msg, preproc=False)
 
-        self.coder.cur_messages += [
-            dict(role="user", content=user_msg),
-            dict(role="assistant", content=assistant_msg),
-        ]
-        self.coder.total_cost += coder.total_cost
+        if self.coder.repo_map:
+            map_tokens = self.coder.repo_map.max_map_tokens
+            map_mul_no_files = self.coder.repo_map.map_mul_no_files
+        else:
+            map_tokens = 0
+            map_mul_no_files = 1
+
+        raise SwitchCoder(
+            edit_format=self.coder.edit_format,
+            summarize_from_coder=False,
+            from_coder=coder,
+            map_tokens=map_tokens,
+            map_mul_no_files=map_mul_no_files,
+            show_announcements=False,
+        )
 
     def clone(self):
         return Commands(
@@ -805,28 +872,35 @@ class Commands:
 
     def cmd_ask(self, args):
         "Ask questions about the code base without editing any files"
+        return self._generic_chat_command(args, "ask")
 
+    def cmd_code(self, args):
+        "Ask for changes to your code"
+        return self._generic_chat_command(args, self.coder.main_model.edit_format)
+
+    def _generic_chat_command(self, args, edit_format):
         if not args.strip():
-            self.io.tool_error("Please provide a question or topic for the chat.")
+            self.io.tool_error(f"Please provide a question or topic for the {edit_format} chat.")
             return
 
         from aider.coders import Coder
 
-        chat_coder = Coder.create(
+        coder = Coder.create(
             io=self.io,
             from_coder=self.coder,
-            edit_format="ask",
+            edit_format=edit_format,
             summarize_from_coder=False,
         )
 
         user_msg = args
-        assistant_msg = chat_coder.run(user_msg)
+        coder.run(user_msg)
 
-        self.coder.cur_messages += [
-            dict(role="user", content=user_msg),
-            dict(role="assistant", content=assistant_msg),
-        ]
-        self.coder.total_cost += chat_coder.total_cost
+        raise SwitchCoder(
+            edit_format=self.coder.edit_format,
+            summarize_from_coder=False,
+            from_coder=coder,
+            show_announcements=False,
+        )
 
     def get_help_md(self):
         "Show help about all commands in markdown"
@@ -894,27 +968,82 @@ class Commands:
 
         return text
 
-    def cmd_add_clipboard_image(self, args):
-        "Add an image from the clipboard to the chat"
+    def cmd_clipboard(self, args):
+        "Add image/text from the clipboard to the chat (optionally provide a name for the image)"
         try:
+            # Check for image first
             image = ImageGrab.grabclipboard()
-            if image is None:
-                self.io.tool_error("No image found in clipboard.")
+            if isinstance(image, Image.Image):
+                if args.strip():
+                    filename = args.strip()
+                    ext = os.path.splitext(filename)[1].lower()
+                    if ext in (".jpg", ".jpeg", ".png"):
+                        basename = filename
+                    else:
+                        basename = f"{filename}.png"
+                else:
+                    basename = "clipboard_image.png"
+
+                temp_dir = tempfile.mkdtemp()
+                temp_file_path = os.path.join(temp_dir, basename)
+                image_format = "PNG" if basename.lower().endswith(".png") else "JPEG"
+                image.save(temp_file_path, image_format)
+
+                abs_file_path = Path(temp_file_path).resolve()
+
+                # Check if a file with the same name already exists in the chat
+                existing_file = next(
+                    (f for f in self.coder.abs_fnames if Path(f).name == abs_file_path.name), None
+                )
+                if existing_file:
+                    self.coder.abs_fnames.remove(existing_file)
+                    self.io.tool_output(f"Replaced existing image in the chat: {existing_file}")
+
+                self.coder.abs_fnames.add(str(abs_file_path))
+                self.io.tool_output(f"Added clipboard image to the chat: {abs_file_path}")
+                self.coder.check_added_files()
+
                 return
 
-            with tempfile.NamedTemporaryFile(suffix=".png", delete=False) as temp_file:
-                image.save(temp_file.name, "PNG")
-                temp_file_path = temp_file.name
+            # If not an image, try to get text
+            text = pyperclip.paste()
+            if text:
+                self.io.tool_output(text)
+                return text
 
-            abs_file_path = Path(temp_file_path).resolve()
-            self.coder.abs_fnames.add(str(abs_file_path))
-            self.io.tool_output(f"Added clipboard image to the chat: {abs_file_path}")
-            self.coder.check_added_files()
-
-            return prompts.added_files.format(fnames=str(abs_file_path))
+            self.io.tool_error("No image or text content found in clipboard.")
+            return
 
         except Exception as e:
-            self.io.tool_error(f"Error adding clipboard image: {e}")
+            self.io.tool_error(f"Error processing clipboard content: {e}")
+
+    def cmd_read(self, args):
+        "Add a file to the chat that is for reference, not to be edited"
+        if not args.strip():
+            self.io.tool_error("Please provide a filename to read.")
+            return
+
+        filename = args.strip()
+        abs_path = os.path.abspath(filename)
+
+        if not os.path.exists(abs_path):
+            self.io.tool_error(f"File not found: {abs_path}")
+            return
+
+        if not os.path.isfile(abs_path):
+            self.io.tool_error(f"Not a file: {abs_path}")
+            return
+
+        self.coder.abs_read_only_fnames.add(abs_path)
+        self.io.tool_output(f"Added {abs_path} to read-only files.")
+
+    def cmd_map(self, args):
+        "Print out the current repository map"
+        repo_map = self.coder.get_repo_map()
+        if repo_map:
+            self.io.tool_output(repo_map)
+        else:
+            self.io.tool_output("No repository map available.")
 
 
 def expand_subdir(file_path):

aider/io.py

@@ -15,6 +15,7 @@ from pygments.lexers import MarkdownLexer, guess_lexer_for_filename
 from pygments.token import Token
 from pygments.util import ClassNotFound
 from rich.console import Console
+from rich.style import Style as RichStyle
 from rich.text import Text
 
 from .dump import dump  # noqa: F401
@@ -22,10 +23,13 @@ from .utils import is_image_file
 
 
 class AutoCompleter(Completer):
-    def __init__(self, root, rel_fnames, addable_rel_fnames, commands, encoding):
+    def __init__(
+        self, root, rel_fnames, addable_rel_fnames, commands, encoding, abs_read_only_fnames=None
+    ):
         self.addable_rel_fnames = addable_rel_fnames
         self.rel_fnames = rel_fnames
         self.encoding = encoding
+        self.abs_read_only_fnames = abs_read_only_fnames or []
 
         fname_to_rel_fnames = defaultdict(list)
         for rel_fname in addable_rel_fnames:
@@ -47,7 +51,11 @@ class AutoCompleter(Completer):
         for rel_fname in rel_fnames:
             self.words.add(rel_fname)
 
-            fname = Path(root) / rel_fname
+        all_fnames = [Path(root) / rel_fname for rel_fname in rel_fnames]
+        if abs_read_only_fnames:
+            all_fnames.extend(abs_read_only_fnames)
+
+        for fname in all_fnames:
             try:
                 with open(fname, "r", encoding=self.encoding) as f:
                     content = f.read()
@@ -217,7 +225,7 @@ class InputOutput:
         with open(str(filename), "w", encoding=self.encoding) as f:
             f.write(content)
 
-    def get_input(self, root, rel_fnames, addable_rel_fnames, commands):
+    def get_input(self, root, rel_fnames, addable_rel_fnames, commands, abs_read_only_fnames=None):
         if self.pretty:
             style = dict(style=self.user_input_color) if self.user_input_color else dict()
             self.console.rule(**style)
@@ -244,7 +252,12 @@ class InputOutput:
             style = None
 
         completer_instance = AutoCompleter(
-            root, rel_fnames, addable_rel_fnames, commands, self.encoding
+            root,
+            rel_fnames,
+            addable_rel_fnames,
+            commands,
+            self.encoding,
+            abs_read_only_fnames=abs_read_only_fnames,
         )
 
         while True:
@@ -317,7 +330,7 @@ class InputOutput:
     def user_input(self, inp, log_only=True):
         if not log_only:
             style = dict(style=self.user_input_color) if self.user_input_color else dict()
-            self.console.print(inp, **style)
+            self.console.print(Text(inp), **style)
 
         prefix = "####"
         if inp:
@@ -341,18 +354,19 @@ class InputOutput:
         self.num_user_asks += 1
 
         if self.yes is True:
-            res = "yes"
+            res = "y"
         elif self.yes is False:
-            res = "no"
+            res = "n"
         else:
             res = prompt(question + " ", default=default)
 
-        hist = f"{question.strip()} {res.strip()}"
+        res = res.lower().strip()
+        is_yes = res in ("y", "yes")
+
+        hist = f"{question.strip()} {'y' if is_yes else 'n'}"
         self.append_chat_history(hist, linebreak=True, blockquote=True)
 
-        if not res or not res.strip():
-            return
-        return res.strip().lower().startswith("y")
+        return is_yes
 
     def prompt_ask(self, question, default=None):
         self.num_user_asks += 1
@@ -389,7 +403,7 @@ class InputOutput:
         style = dict(style=self.tool_error_color) if self.tool_error_color else dict()
         self.console.print(message, **style)
 
-    def tool_output(self, *messages, log_only=False):
+    def tool_output(self, *messages, log_only=False, bold=False):
         if messages:
             hist = " ".join(messages)
             hist = f"{hist.strip()}"
@@ -397,8 +411,10 @@ class InputOutput:
 
         if not log_only:
             messages = list(map(Text, messages))
-            style = dict(style=self.tool_output_color) if self.tool_output_color else dict()
-            self.console.print(*messages, **style)
+            style = dict(color=self.tool_output_color) if self.tool_output_color else dict()
+            style["reverse"] = bold
+            style = RichStyle(**style)
+            self.console.print(*messages, style=style)
 
     def append_chat_history(self, text, linebreak=False, blockquote=False, strip=True):
         if blockquote:

aider/llm.py

@@ -4,8 +4,11 @@ import warnings
 
 warnings.filterwarnings("ignore", category=UserWarning, module="pydantic")
 
-os.environ["OR_SITE_URL"] = "http://aider.chat"
-os.environ["OR_APP_NAME"] = "Aider"
+AIDER_SITE_URL = "https://aider.chat"
+AIDER_APP_NAME = "Aider"
+
+os.environ["OR_SITE_URL"] = AIDER_SITE_URL
+os.environ["OR_APP_NAME"] = AIDER_APP_NAME
 
 # `import litellm` takes 1.5 seconds, defer it!
 

aider/main.py

@@ -384,6 +384,7 @@ 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 [])]
     if len(all_files) > 1:
         good = True
         for fname in all_files:
@@ -415,11 +416,11 @@ def main(argv=None, input=None, output=None, force_git_root=None, return_coder=F
             return main(argv, input, output, right_repo_root, return_coder=return_coder)
 
     if args.just_check_update:
-        update_available = check_version(io, just_check=True)
+        update_available = check_version(io, just_check=True, verbose=args.verbose)
         return 0 if not update_available else 1
 
     if args.check_update:
-        check_version(io)
+        check_version(io, verbose=args.verbose)
 
     if args.models:
         models.print_matching_models(io, args.models)
@@ -475,12 +476,13 @@ def main(argv=None, input=None, output=None, force_git_root=None, return_coder=F
             repo = GitRepo(
                 io,
                 fnames,
-                git_dname or ".",
+                git_dname,
                 args.aiderignore,
                 models=main_model.commit_message_models(),
                 attribute_author=args.attribute_author,
                 attribute_committer=args.attribute_committer,
-                attribute_commit_message=args.attribute_commit_message,
+                attribute_commit_message_author=args.attribute_commit_message_author,
+                attribute_commit_message_committer=args.attribute_commit_message_committer,
                 commit_prompt=args.commit_prompt,
                 subtree_only=args.subtree_only,
             )
@@ -501,7 +503,7 @@ def main(argv=None, input=None, output=None, force_git_root=None, return_coder=F
             io=io,
             repo=repo,
             fnames=fnames,
-            pretty=args.pretty,
+            read_only_fnames=read_only_fnames,
             show_diffs=args.show_diffs,
             auto_commits=args.auto_commits,
             dirty_commits=args.dirty_commits,
@@ -618,8 +620,15 @@ def main(argv=None, input=None, output=None, force_git_root=None, return_coder=F
             coder.run()
             return
         except SwitchCoder as switch:
-            coder = Coder.create(io=io, from_coder=coder, **switch.kwargs)
-            coder.show_announcements()
+            kwargs = dict(io=io, from_coder=coder)
+            kwargs.update(switch.kwargs)
+            if "show_announcements" in kwargs:
+                del kwargs["show_announcements"]
+
+            coder = Coder.create(**kwargs)
+
+            if switch.kwargs.get("show_announcements") is not False:
+                coder.show_announcements()
 
 
 def load_slow_imports():

aider/models.py

@@ -3,6 +3,7 @@ import importlib
 import json
 import math
 import os
+import platform
 import sys
 from dataclasses import dataclass, fields
 from pathlib import Path
@@ -13,7 +14,7 @@ from PIL import Image
 
 from aider import urls
 from aider.dump import dump  # noqa: F401
-from aider.llm import litellm
+from aider.llm import AIDER_APP_NAME, AIDER_SITE_URL, litellm
 
 DEFAULT_MODEL_NAME = "gpt-4o"
 
@@ -70,7 +71,6 @@ class ModelSettings:
     lazy: bool = False
     reminder_as_sys_msg: bool = False
     examples_as_sys_msg: bool = False
-    can_prefill: bool = False
     extra_headers: Optional[dict] = None
     max_tokens: Optional[int] = None
 
@@ -152,6 +152,16 @@ MODEL_SETTINGS = [
         lazy=True,
         reminder_as_sys_msg=True,
     ),
+    ModelSettings(
+        "gpt-4o-2024-08-06",
+        "diff",
+        weak_model_name="gpt-4o-mini",
+        use_repo_map=True,
+        send_undo_reply=True,
+        accepts_images=True,
+        lazy=True,
+        reminder_as_sys_msg=True,
+    ),
     ModelSettings(
         "gpt-4o",
         "diff",
@@ -238,7 +248,6 @@ MODEL_SETTINGS = [
         weak_model_name="claude-3-haiku-20240307",
         use_repo_map=True,
         send_undo_reply=True,
-        can_prefill=True,
     ),
     ModelSettings(
         "openrouter/anthropic/claude-3-opus",
@@ -246,13 +255,11 @@ MODEL_SETTINGS = [
         weak_model_name="openrouter/anthropic/claude-3-haiku",
         use_repo_map=True,
         send_undo_reply=True,
-        can_prefill=True,
     ),
     ModelSettings(
         "claude-3-sonnet-20240229",
         "whole",
         weak_model_name="claude-3-haiku-20240307",
-        can_prefill=True,
     ),
     ModelSettings(
         "claude-3-5-sonnet-20240620",
@@ -260,7 +267,6 @@ MODEL_SETTINGS = [
         weak_model_name="claude-3-haiku-20240307",
         use_repo_map=True,
         examples_as_sys_msg=True,
-        can_prefill=True,
         accepts_images=True,
         max_tokens=8192,
         extra_headers={"anthropic-beta": "max-tokens-3-5-sonnet-2024-07-15"},
@@ -271,9 +277,12 @@ MODEL_SETTINGS = [
         weak_model_name="claude-3-haiku-20240307",
         use_repo_map=True,
         examples_as_sys_msg=True,
-        can_prefill=True,
         max_tokens=8192,
-        extra_headers={"anthropic-beta": "max-tokens-3-5-sonnet-2024-07-15"},
+        extra_headers={
+            "anthropic-beta": "max-tokens-3-5-sonnet-2024-07-15",
+            "HTTP-Referer": AIDER_SITE_URL,
+            "X-Title": AIDER_APP_NAME,
+        },
     ),
     ModelSettings(
         "openrouter/anthropic/claude-3.5-sonnet",
@@ -281,10 +290,13 @@ MODEL_SETTINGS = [
         weak_model_name="openrouter/anthropic/claude-3-haiku-20240307",
         use_repo_map=True,
         examples_as_sys_msg=True,
-        can_prefill=True,
         accepts_images=True,
         max_tokens=8192,
-        extra_headers={"anthropic-beta": "max-tokens-3-5-sonnet-2024-07-15"},
+        extra_headers={
+            "anthropic-beta": "max-tokens-3-5-sonnet-2024-07-15",
+            "HTTP-Referer": "https://aider.chat",
+            "X-Title": "Aider",
+        },
     ),
     # Vertex AI Claude models
     # Does not yet support 8k token
@@ -294,7 +306,6 @@ MODEL_SETTINGS = [
         weak_model_name="vertex_ai/claude-3-haiku@20240307",
         use_repo_map=True,
         examples_as_sys_msg=True,
-        can_prefill=True,
         accepts_images=True,
     ),
     ModelSettings(
@@ -303,13 +314,11 @@ MODEL_SETTINGS = [
         weak_model_name="vertex_ai/claude-3-haiku@20240307",
         use_repo_map=True,
         send_undo_reply=True,
-        can_prefill=True,
     ),
     ModelSettings(
         "vertex_ai/claude-3-sonnet@20240229",
         "whole",
         weak_model_name="vertex_ai/claude-3-haiku@20240307",
-        can_prefill=True,
     ),
     # Cohere
     ModelSettings(
@@ -405,9 +414,7 @@ class Model:
         self.missing_keys = res.get("missing_keys")
         self.keys_in_environment = res.get("keys_in_environment")
 
-        max_input_tokens = self.info.get("max_input_tokens")
-        if not max_input_tokens:
-            max_input_tokens = 0
+        max_input_tokens = self.info.get("max_input_tokens") or 0
         if max_input_tokens < 32 * 1024:
             self.max_chat_history_tokens = 1024
         else:
@@ -470,14 +477,10 @@ class Model:
         if "gpt-3.5" in model or "gpt-4" in model:
             self.reminder_as_sys_msg = True
 
-        if "anthropic" in model:
-            self.can_prefill = True
-
         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.can_prefill = True
 
         # use the defaults
         if self.edit_format == "diff":
@@ -512,6 +515,9 @@ class Model:
         return litellm.encode(model=self.name, text=text)
 
     def token_count(self, messages):
+        if type(messages) is list:
+            return litellm.token_counter(model=self.name, messages=messages)
+
         if not self.tokenizer:
             return
 
@@ -669,6 +675,13 @@ def sanity_check_model(io, model):
         io.tool_error(f"Model {model}: Missing these environment variables:")
         for key in model.missing_keys:
             io.tool_error(f"- {key}")
+
+        if platform.system() == "Windows" or True:
+            io.tool_output(
+                "If you just set these environment variables using `setx` you may need to restart"
+                " your terminal or command prompt for the changes to take effect."
+            )
+
     elif not model.keys_in_environment:
         show = True
         io.tool_output(f"Model {model}: Unknown which environment variables are required.")

aider/repo.py

@@ -29,7 +29,8 @@ class GitRepo:
         models=None,
         attribute_author=True,
         attribute_committer=True,
-        attribute_commit_message=False,
+        attribute_commit_message_author=False,
+        attribute_commit_message_committer=False,
         commit_prompt=None,
         subtree_only=False,
     ):
@@ -41,7 +42,8 @@ class GitRepo:
 
         self.attribute_author = attribute_author
         self.attribute_committer = attribute_committer
-        self.attribute_commit_message = attribute_commit_message
+        self.attribute_commit_message_author = attribute_commit_message_author
+        self.attribute_commit_message_committer = attribute_commit_message_committer
         self.commit_prompt = commit_prompt
         self.subtree_only = subtree_only
         self.ignore_file_cache = {}
@@ -98,7 +100,9 @@ class GitRepo:
         else:
             commit_message = self.get_commit_message(diffs, context)
 
-        if aider_edits and self.attribute_commit_message:
+        if aider_edits and self.attribute_commit_message_author:
+            commit_message = "aider: " + commit_message
+        elif self.attribute_commit_message_committer:
             commit_message = "aider: " + commit_message
 
         if not commit_message:
@@ -130,7 +134,7 @@ class GitRepo:
 
         self.repo.git.commit(cmd)
         commit_hash = self.repo.head.commit.hexsha[:7]
-        self.io.tool_output(f"Commit {commit_hash} {commit_message}")
+        self.io.tool_output(f"Commit {commit_hash} {commit_message}", bold=True)
 
         # Restore the env
 
@@ -155,10 +159,6 @@ class GitRepo:
             return self.repo.git_dir
 
     def get_commit_message(self, diffs, context):
-        if len(diffs) >= 4 * 1024 * 4:
-            self.io.tool_error("Diff is too large to generate a commit message.")
-            return
-
         diffs = "# Diffs:\n" + diffs
 
         content = ""
@@ -172,7 +172,12 @@ class GitRepo:
             dict(role="user", content=content),
         ]
 
+        commit_message = None
         for model in self.models:
+            num_tokens = model.token_count(messages)
+            max_tokens = model.info.get("max_input_tokens") or 0
+            if max_tokens and num_tokens > max_tokens:
+                continue
             commit_message = simple_send_with_retries(model.name, messages)
             if commit_message:
                 break
@@ -226,6 +231,8 @@ class GitRepo:
         args = []
         if pretty:
             args += ["--color"]
+        else:
+            args += ["--color=never"]
 
         args += [from_commit, to_commit]
         diffs = self.repo.git.diff(*args)
@@ -355,3 +362,9 @@ class GitRepo:
             return True
 
         return self.repo.is_dirty(path=path)
+
+    def get_head(self):
+        try:
+            return self.repo.head.commit.hexsha
+        except ValueError:
+            return None

aider/repomap.py

@@ -60,6 +60,9 @@ class RepoMap:
 
         self.main_model = main_model
 
+        self.tree_cache = {}
+        self.tree_context_cache = {}
+
     def token_count(self, text):
         len_text = len(text)
         if len_text < 200:
@@ -471,24 +474,28 @@ class RepoMap:
         if key in self.tree_cache:
             return self.tree_cache[key]
 
-        code = self.io.read_text(abs_fname) or ""
-        if not code.endswith("\n"):
-            code += "\n"
+        if rel_fname not in self.tree_context_cache:
+            code = self.io.read_text(abs_fname) or ""
+            if not code.endswith("\n"):
+                code += "\n"
 
-        context = TreeContext(
-            rel_fname,
-            code,
-            color=False,
-            line_number=False,
-            child_context=False,
-            last_line=False,
-            margin=0,
-            mark_lois=False,
-            loi_pad=0,
-            # header_max=30,
-            show_top_of_file_parent_scope=False,
-        )
+            context = TreeContext(
+                rel_fname,
+                code,
+                color=False,
+                line_number=False,
+                child_context=False,
+                last_line=False,
+                margin=0,
+                mark_lois=False,
+                loi_pad=0,
+                # header_max=30,
+                show_top_of_file_parent_scope=False,
+            )
+            self.tree_context_cache[rel_fname] = context
 
+        context = self.tree_context_cache[rel_fname]
+        context.lines_of_interest = set()
         context.add_lines_of_interest(lois)
         context.add_context()
         res = context.format()

aider/scrape.py

@@ -87,26 +87,48 @@ class Scraper:
 
     def scrape(self, url):
         """
-        Scrape a url and turn it into readable markdown.
+        Scrape a url and turn it into readable markdown if it's HTML.
+        If it's plain text or non-HTML, return it as-is.
 
-        `url` - the URLto scrape.
+        `url` - the URL to scrape.
         """
 
         if self.playwright_available:
-            content = self.scrape_with_playwright(url)
+            content, mime_type = self.scrape_with_playwright(url)
         else:
-            content = self.scrape_with_httpx(url)
+            content, mime_type = self.scrape_with_httpx(url)
 
         if not content:
             self.print_error(f"Failed to retrieve content from {url}")
             return None
 
-        self.try_pandoc()
-
-        content = self.html_to_markdown(content)
+        # Check if the content is HTML based on MIME type or content
+        if (mime_type and mime_type.startswith("text/html")) or (
+            mime_type is None and self.looks_like_html(content)
+        ):
+            self.try_pandoc()
+            content = self.html_to_markdown(content)
 
         return content
 
+    def looks_like_html(self, content):
+        """
+        Check if the content looks like HTML.
+        """
+        if isinstance(content, str):
+            # Check for common HTML tags
+            html_patterns = [
+                r"<!DOCTYPE\s+html",
+                r"<html",
+                r"<head",
+                r"<body",
+                r"<div",
+                r"<p>",
+                r"<a\s+href=",
+            ]
+            return any(re.search(pattern, content, re.IGNORECASE) for pattern in html_patterns)
+        return False
+
     # Internals...
     def scrape_with_playwright(self, url):
         import playwright
@@ -118,7 +140,7 @@ class Scraper:
             except Exception as e:
                 self.playwright_available = False
                 self.print_error(str(e))
-                return
+                return None, None
 
             try:
                 context = browser.new_context(ignore_https_errors=not self.verify_ssl)
@@ -131,23 +153,28 @@ class Scraper:
 
                 page.set_extra_http_headers({"User-Agent": user_agent})
 
+                response = None
                 try:
-                    page.goto(url, wait_until="networkidle", timeout=5000)
+                    response = page.goto(url, wait_until="networkidle", timeout=5000)
                 except playwright._impl._errors.TimeoutError:
                     self.print_error(f"Timeout while loading {url}")
                 except playwright._impl._errors.Error as e:
                     self.print_error(f"Error navigating to {url}: {str(e)}")
-                    return None
+                    return None, None
 
                 try:
                     content = page.content()
+                    mime_type = (
+                        response.header_value("content-type").split(";")[0] if response else None
+                    )
                 except playwright._impl._errors.Error as e:
                     self.print_error(f"Error retrieving page content: {str(e)}")
                     content = None
+                    mime_type = None
             finally:
                 browser.close()
 
-        return content
+        return content, mime_type
 
     def scrape_with_httpx(self, url):
         import httpx
@@ -157,12 +184,12 @@ class Scraper:
             with httpx.Client(headers=headers, verify=self.verify_ssl) as client:
                 response = client.get(url)
                 response.raise_for_status()
-                return response.text
+                return response.text, response.headers.get("content-type", "").split(";")[0]
         except httpx.HTTPError as http_err:
             self.print_error(f"HTTP error occurred: {http_err}")
         except Exception as err:
             self.print_error(f"An error occurred: {err}")
-        return None
+        return None, None
 
     def try_pandoc(self):
         if self.pandoc_available:

aider/sendchat.py

@@ -14,24 +14,28 @@ CACHE = None
 # CACHE = Cache(CACHE_PATH)
 
 
+def retry_exceptions():
+    import httpx
+
+    return (
+        httpx.ConnectError,
+        httpx.RemoteProtocolError,
+        httpx.ReadTimeout,
+        litellm.exceptions.APIConnectionError,
+        litellm.exceptions.APIError,
+        litellm.exceptions.RateLimitError,
+        litellm.exceptions.ServiceUnavailableError,
+        litellm.exceptions.Timeout,
+        litellm.exceptions.InternalServerError,
+        litellm.llms.anthropic.AnthropicError,
+    )
+
+
 def lazy_litellm_retry_decorator(func):
     def wrapper(*args, **kwargs):
-        import httpx
-
         decorated_func = backoff.on_exception(
             backoff.expo,
-            (
-                httpx.ConnectError,
-                httpx.RemoteProtocolError,
-                httpx.ReadTimeout,
-                litellm.exceptions.APIConnectionError,
-                litellm.exceptions.APIError,
-                litellm.exceptions.RateLimitError,
-                litellm.exceptions.ServiceUnavailableError,
-                litellm.exceptions.Timeout,
-                litellm.exceptions.InternalServerError,
-                litellm.llms.anthropic.AnthropicError,
-            ),
+            retry_exceptions(),
             max_time=60,
             on_backoff=lambda details: print(
                 f"{details.get('exception', 'Exception')}\nRetry in {details['wait']:.1f} seconds."
@@ -42,8 +46,7 @@ def lazy_litellm_retry_decorator(func):
     return wrapper
 
 
-@lazy_litellm_retry_decorator
-def send_with_retries(
+def send_completion(
     model_name, messages, functions, stream, temperature=0, extra_headers=None, max_tokens=None
 ):
     from aider.llm import litellm
@@ -54,6 +57,7 @@ def send_with_retries(
         temperature=temperature,
         stream=stream,
     )
+
     if functions is not None:
         kwargs["tools"] = [dict(type="functions", function=functions[0])]
     if extra_headers is not None:
@@ -79,9 +83,10 @@ def send_with_retries(
     return hash_object, res
 
 
+@lazy_litellm_retry_decorator
 def simple_send_with_retries(model_name, messages):
     try:
-        _hash, response = send_with_retries(
+        _hash, response = send_completion(
             model_name=model_name,
             messages=messages,
             functions=None,

aider/utils.py

@@ -44,7 +44,7 @@ class ChdirTemporaryDirectory(IgnorantTemporaryDirectory):
 
     def __enter__(self):
         res = super().__enter__()
-        os.chdir(self.temp_dir.name)
+        os.chdir(Path(self.temp_dir.name).resolve())
         return res
 
     def __exit__(self, exc_type, exc_val, exc_tb):
@@ -112,13 +112,19 @@ def format_messages(messages, title=None):
         content = msg.get("content")
         if isinstance(content, list):  # Handle list content (e.g., image messages)
             for item in content:
-                if isinstance(item, dict) and "image_url" in item:
-                    output.append(f"{role} Image URL: {item['image_url']['url']}")
+                if isinstance(item, dict):
+                    for key, value in item.items():
+                        if isinstance(value, dict) and "url" in value:
+                            output.append(f"{role} {key.capitalize()} URL: {value['url']}")
+                        else:
+                            output.append(f"{role} {key}: {value}")
+                else:
+                    output.append(f"{role} {item}")
         elif isinstance(content, str):  # Handle string content
             output.append(format_content(role, content))
-        content = msg.get("function_call")
-        if content:
-            output.append(f"{role} {content}")
+        function_call = msg.get("function_call")
+        if function_call:
+            output.append(f"{role} Function Call: {function_call}")
 
     return "\n".join(output)
 

aider/versioncheck.py

@@ -10,12 +10,15 @@ from aider import utils
 from aider.dump import dump  # noqa: F401
 
 
-def check_version(io, just_check=False):
+def check_version(io, just_check=False, verbose=False):
     fname = Path.home() / ".aider" / "caches" / "versioncheck"
     if not just_check and fname.exists():
         day = 60 * 60 * 24
         since = time.time() - fname.stat().st_mtime
         if since < day:
+            if verbose:
+                hours = since / 60 / 60
+                io.tool_output(f"Too soon to check version: {hours:.1f} hours")
             return
 
     # To keep startup fast, avoid importing this unless needed
@@ -27,7 +30,7 @@ def check_version(io, just_check=False):
         latest_version = data["info"]["version"]
         current_version = aider.__version__
 
-        if just_check:
+        if just_check or verbose:
             io.tool_output(f"Current version: {current_version}")
             io.tool_output(f"Latest version: {latest_version}")
 
@@ -41,11 +44,13 @@ def check_version(io, just_check=False):
         fname.parent.mkdir(parents=True, exist_ok=True)
         fname.touch()
 
-    if just_check:
+    if just_check or verbose:
         if is_update_available:
             io.tool_output("Update available")
         else:
             io.tool_output("No update available")
+
+    if just_check:
         return is_update_available
 
     if not is_update_available:

aider/website/HISTORY.md

@@ -16,6 +16,51 @@ cog.out(text)
 
 # Release history
 
+### Aider v0.50.0
+
+- Infinite output for DeepSeek Coder, Mistral models in addition to Anthropic's models.
+- New `--deepseek` switch to use DeepSeek Coder.
+- DeepSeek Coder uses 8k token output.
+- New `--chat-mode <mode>` switch to launch in ask/help/code modes.
+- New `/code <message>` command request a code edit while in `ask` mode.
+- Web scraper is more robust if page never idles.
+- Improved token and cost reporting for infinite output.
+- Improvements and bug fixes for `/read` only files.
+- Switched from `setup.py` to `pyproject.toml`, by @branchvincent.
+- Bug fix to persist files added during `/ask`.
+- Bug fix for chat history size in `/tokens`.
+- Aider wrote 66% of the code in this release.
+
+### Aider v0.49.1
+
+- Bugfix to `/help`.
+
+### Aider v0.49.0
+
+- Add read-only files to the chat context with `/read` and `--read`,  including from outside the git repo.
+- `/diff` now shows diffs of all changes resulting from your request, including lint and test fixes.
+- New `/clipboard` command to paste images or text from the clipboard, replaces `/add-clipboard-image`.
+- Now shows the markdown scraped when you add a url with `/web`.
+- When [scripting aider](https://aider.chat/docs/scripting.html) messages can now contain in-chat `/` commands.
+- Aider in docker image now suggests the correct command to update to latest version.
+- Improved retries on API errors (was easy to test during Sonnet outage).
+- Added `--mini` for `gpt-4o-mini`.
+- Bugfix to keep session cost accurate when using `/ask` and `/help`.
+- Performance improvements for repo map calculation.
+- `/tokens` now shows the active model.
+- Enhanced commit message attribution options:
+  - New `--attribute-commit-message-author` to prefix commit messages with 'aider: ' if aider authored the changes, replaces `--attribute-commit-message`.
+  - New `--attribute-commit-message-committer` to prefix all commit messages with 'aider: '.
+- Aider wrote 61% of the code in this release.
+
+### Aider v0.48.1
+
+- Added `openai/gpt-4o-2024-08-06`.
+- Worked around litellm bug that removes OpenRouter app headers when using `extra_headers`.
+- Improved progress indication during repo map processing.
+- Corrected instructions for upgrading the docker container to latest aider version.
+- Removed obsolete 16k token limit on commit diffs, use per-model limits.
+
 ### Aider v0.48.0
 
 - Performance improvements for large/mono repos.

aider/website/_includes/blame.md

@@ -1,90 +1,126 @@
-<canvas id="blameChart" width="800" height="450" 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>
 <script>
 document.addEventListener('DOMContentLoaded', function () {
-    var ctx = document.getElementById('blameChart').getContext('2d');
+    var blameCtx = document.getElementById('blameChart').getContext('2d');
+    var linesCtx = document.getElementById('linesChart').getContext('2d');
+    
+    var labels = [{% for row in site.data.blame %}'{{ row.end_tag }}',{% endfor %}];
+    
     var blameData = {
+        labels: labels,
         datasets: [{
-            label: 'Aider\'s Contribution to Each Release',
-            data: [
-                {% for row in site.data.blame %}
-                {
-                    x: '{{ row.end_date }}',
-                    y: {{ row.aider_percentage }},
-                    r: Math.sqrt({{ row.aider_total }}) * 1.5,
-                    label: '{{ row.end_tag }}',
-                    percentage: {{ row.aider_percentage }},
-                    lines: {{ row.aider_total }}
-                },
-                {% endfor %}
-            ],
-            backgroundColor: 'rgba(54, 162, 235, 0.2)',
+            label: 'Aider\'s percent of new code by release',
+            data: [{% for row in site.data.blame %}{ x: '{{ row.end_tag }}', y: {{ row.aider_percentage }}, lines: {{ row.aider_total }} },{% endfor %}],
+            backgroundColor: 'rgba(54, 162, 235, 0.8)',
             borderColor: 'rgba(54, 162, 235, 1)',
             borderWidth: 1
         }]
     };
 
-    var blameChart = new Chart(ctx, {
-        type: 'bubble',
+    var linesData = {
+        labels: labels,
+        datasets: [{
+            label: 'Aider\'s lines of new code',
+            data: [{% for row in site.data.blame %}{ x: '{{ row.end_tag }}', y: {{ row.aider_total }} },{% endfor %}],
+            backgroundColor: 'rgba(255, 99, 132, 0.8)',
+            borderColor: 'rgba(255, 99, 132, 1)',
+            borderWidth: 1
+        }]
+    };
+
+    var blameChart = new Chart(blameCtx, {
+        type: 'bar',
         data: blameData,
         options: {
             scales: {
                 x: {
-                    type: 'time',
-                    time: {
-                        unit: 'month',
-                        displayFormats: {
-                            month: 'MMM YYYY'
-                        }
-                    },
+                    type: 'category',
                     title: {
                         display: true,
-                        text: 'Release date'
+                        text: 'Version'
                     },
                     ticks: {
                         maxRotation: 45,
                         minRotation: 45
-                    },
-                    min: moment('{{ site.data.blame | first | map: "end_date" | first }}').subtract(1, 'month'),
-                    max: moment('{{ site.data.blame | last | map: "end_date" | first }}').add(1, 'month')
+                    }
                 },
                 y: {
                     title: {
                         display: true,
-                        text: 'Aider Contribution (% of code)'
+                        text: 'Percent of new code'
                     },
                     beginAtZero: true
                 }
             },
             plugins: {
+                legend: {
+                    display: false
+                },
                 tooltip: {
                     callbacks: {
                         label: function(context) {
-                            return `${context.raw.label}: ${Math.round(context.raw.percentage)}% (${context.raw.lines} lines)`;
-                        }
-                    }
-                },
-                legend: {
-                    display: true,
-                    position: 'top',
-                    labels: {
-                        generateLabels: function(chart) {
-                            return [{
-                                text: 'Bubble size: Lines of code contributed by aider',
-                                fillStyle: 'rgba(54, 162, 235, 0.2)',
-                                strokeStyle: 'rgba(54, 162, 235, 1)',
-                                lineWidth: 1,
-                                hidden: false,
-                                index: 0
-                            }];
+                            var label = 'Aider\'s contribution';
+                            var value = context.parsed.y || 0;
+                            var lines = context.raw.lines || 0;
+                            return `${label}: ${Math.round(value)}% (${lines} lines)`;
                         }
                     }
                 },
                 title: {
                     display: true,
-                    text: 'Aider\'s Contribution to Each Release',
+                    text: 'Percent of new code written by aider, by release',
+                    font: {
+                        size: 16
+                    }
+                }
+            }
+        }
+    });
+
+    var linesChart = new Chart(linesCtx, {
+        type: 'bar',
+        data: linesData,
+        options: {
+            scales: {
+                x: {
+                    type: 'category',
+                    title: {
+                        display: true,
+                        text: 'Version'
+                    },
+                    ticks: {
+                        maxRotation: 45,
+                        minRotation: 45
+                    }
+                },
+                y: {
+                    title: {
+                        display: true,
+                        text: 'Lines of new code'
+                    },
+                    beginAtZero: true
+                }
+            },
+            plugins: {
+                legend: {
+                    display: false
+                },
+                tooltip: {
+                    callbacks: {
+                        label: function(context) {
+                            var label = 'New lines of code by aider';
+                            var value = context.parsed.y || 0;
+                            return `${label}: ${value}`;
+                        }
+                    }
+                },
+                title: {
+                    display: true,
+                    text: 'Lines of new code written by aider, by release',
                     font: {
                         size: 16
                     }

aider/website/_includes/get-started.md

@@ -2,16 +2,16 @@
 You can get started quickly like this:
 
 ```
-$ pip install aider-chat
+python -m pip install aider-chat
 
 # Change directory into a git repo
-$ cd /to/your/git/repo
+cd /to/your/git/repo
 
 # Work with Claude 3.5 Sonnet on your repo
-$ export ANTHROPIC_API_KEY=your-key-goes-here
-$ aider
+export ANTHROPIC_API_KEY=your-key-goes-here
+aider
 
 # Work with GPT-4o on your repo
-$ export OPENAI_API_KEY=your-key-goes-here
-$ aider 
+export OPENAI_API_KEY=your-key-goes-here
+aider 
 ```

aider/website/_includes/model-warnings.md

@@ -44,6 +44,10 @@ Model azure/gpt-4-turbo: Missing these environment variables:
 - AZURE_API_KEY
 ```
 
+{: .tip }
+On Windows, 
+if you just set these environment variables using `setx` you may need to restart your terminal or
+command prompt for the changes to take effect.
 
 
 ## Unknown which environment variables are required

aider/website/_includes/python-m-aider.md

@@ -0,0 +1,5 @@
+{: .tip }
+In some environments you may get "aider command not found" errors.
+You can try `python -m aider` or 
+[see here for more info](/docs/troubleshooting/aider-not-found.html).
+

aider/website/_includes/venv-pipx.md

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

aider/website/_posts/2023-10-22-repomap.md

@@ -209,7 +209,7 @@ that aider originally used.
 Switching from ctags to tree-sitter provides a bunch of benefits:
 
 - The map is richer, showing full function call signatures and other details straight from the source files.
-- Thanks to `py-tree-sitter-languages`, we get full support for many programming languages via a python package that's automatically installed as part of the normal `pip install aider-chat`.
+- Thanks to `py-tree-sitter-languages`, we get full support for many programming languages via a python package that's automatically installed as part of the normal `python -m pip install aider-chat`.
 - We remove the requirement for users to manually install `universal-ctags` via some external tool or package manager (brew, apt, choco, etc).
 - Tree-sitter integration is a key enabler for future work and capabilities for aider.
 

aider/website/_posts/2024-03-08-claude-3.md

@@ -23,7 +23,7 @@ making it the best available model for pair programming with AI.
 To use Claude 3 Opus with aider:
 
 ```
-pip install aider-chat
+python -m pip install aider-chat
 export ANTHROPIC_API_KEY=sk-...
 aider --opus
 ```

aider/website/_posts/2024-05-02-browser.md

@@ -46,7 +46,7 @@ It also supports [connecting to almost any LLM](https://aider.chat/docs/llms.htm
 Use the `--browser` switch to launch the browser version of aider:
 
 ```
-pip install aider-chat
+python -m pip install aider-chat
 
 export OPENAI_API_KEY=<key> # Mac/Linux
 setx   OPENAI_API_KEY <key> # Windows, restart shell after setx

aider/website/_posts/2024-07-01-sonnet-not-lazy.md

@@ -116,7 +116,7 @@ for more details, but
 you can get started quickly with aider and Sonnet like this:
 
 ```
-$ pip install aider-chat
+$ python -m pip install aider-chat
 
 $ export ANTHROPIC_API_KEY=<key> # Mac/Linux
 $ setx   ANTHROPIC_API_KEY <key> # Windows, restart shell after setx

aider/website/_posts/2024-07-25-new-models.md

@@ -30,7 +30,7 @@ included for scale.
 You can code with all of these models using aider like this:
 
 ```
-$ pip install aider-chat
+$ python -m pip install aider-chat
 
 # Change directory into a git repo to work on
 $ cd /to/your/git/repo

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

@@ -38,12 +38,18 @@
 ## Use gpt-4o model for the main chat
 #4o: false
 
+## Use gpt-4o-mini model for the main chat
+#mini: false
+
 ## Use gpt-4-1106-preview model for the main chat
 #4-turbo: false
 
 ## Use gpt-3.5-turbo model for the main chat
 #35turbo: false
 
+## Use deepseek/deepseek-coder model for the main chat
+#deepseek: false
+
 #################
 # Model Settings:
 
@@ -167,8 +173,11 @@
 ## Attribute aider commits in the git committer name (default: True)
 #attribute-committer: true
 
-## Prefix commit messages with 'aider: ' (default: False)
-#attribute-commit-message: false
+## Prefix commit messages with 'aider: ' if aider authored the changes (default: False)
+#attribute-commit-message-author: false
+
+## Prefix all commit messages with 'aider: ' (default: False)
+#attribute-commit-message-committer: false
 
 ## Commit all pending changes with a suitable commit message, then exit
 #commit: false
@@ -206,6 +215,9 @@
 ## specify a file to edit (can be used multiple times)
 #file:
 
+## specify a read-only file (can be used multiple times)
+#read:
+
 ## Use VI editing mode in the terminal (default: False)
 #vim: false
 

aider/website/assets/sample.env

@@ -42,12 +42,18 @@
 ## Use gpt-4o model for the main chat
 #AIDER_4O=
 
+## Use gpt-4o-mini model for the main chat
+#AIDER_MINI=
+
 ## Use gpt-4-1106-preview model for the main chat
 #AIDER_4_TURBO=
 
 ## Use gpt-3.5-turbo model for the main chat
 #AIDER_35TURBO=
 
+## Use deepseek/deepseek-coder model for the main chat
+#AIDER_DEEPSEEK=
+
 #################
 # Model Settings:
 
@@ -171,8 +177,11 @@
 ## Attribute aider commits in the git committer name (default: True)
 #AIDER_ATTRIBUTE_COMMITTER=true
 
-## Prefix commit messages with 'aider: ' (default: False)
-#AIDER_ATTRIBUTE_COMMIT_MESSAGE=false
+## Prefix commit messages with 'aider: ' if aider authored the changes (default: False)
+#AIDER_ATTRIBUTE_COMMIT_MESSAGE_AUTHOR=false
+
+## Prefix all commit messages with 'aider: ' (default: False)
+#AIDER_ATTRIBUTE_COMMIT_MESSAGE_COMMITTER=false
 
 ## Commit all pending changes with a suitable commit message, then exit
 #AIDER_COMMIT=false
@@ -210,6 +219,9 @@
 ## specify a file to edit (can be used multiple times)
 #AIDER_FILE=
 
+## specify a read-only file (can be used multiple times)
+#AIDER_READ=
+
 ## Use VI editing mode in the terminal (default: False)
 #AIDER_VIM=false
 

aider/website/docs/config/aider_conf.md

@@ -77,12 +77,18 @@ cog.outl("```")
 ## Use gpt-4o model for the main chat
 #4o: false
 
+## Use gpt-4o-mini model for the main chat
+#mini: false
+
 ## Use gpt-4-1106-preview model for the main chat
 #4-turbo: false
 
 ## Use gpt-3.5-turbo model for the main chat
 #35turbo: false
 
+## Use deepseek/deepseek-coder model for the main chat
+#deepseek: false
+
 #################
 # Model Settings:
 
@@ -206,8 +212,11 @@ cog.outl("```")
 ## Attribute aider commits in the git committer name (default: True)
 #attribute-committer: true
 
-## Prefix commit messages with 'aider: ' (default: False)
-#attribute-commit-message: false
+## Prefix commit messages with 'aider: ' if aider authored the changes (default: False)
+#attribute-commit-message-author: false
+
+## Prefix all commit messages with 'aider: ' (default: False)
+#attribute-commit-message-committer: false
 
 ## Commit all pending changes with a suitable commit message, then exit
 #commit: false
@@ -245,6 +254,9 @@ cog.outl("```")
 ## specify a file to edit (can be used multiple times)
 #file:
 
+## specify a read-only file (can be used multiple times)
+#read:
+
 ## Use VI editing mode in the terminal (default: False)
 #vim: false
 

aider/website/docs/config/dotenv.md

@@ -84,12 +84,18 @@ cog.outl("```")
 ## Use gpt-4o model for the main chat
 #AIDER_4O=
 
+## Use gpt-4o-mini model for the main chat
+#AIDER_MINI=
+
 ## Use gpt-4-1106-preview model for the main chat
 #AIDER_4_TURBO=
 
 ## Use gpt-3.5-turbo model for the main chat
 #AIDER_35TURBO=
 
+## Use deepseek/deepseek-coder model for the main chat
+#AIDER_DEEPSEEK=
+
 #################
 # Model Settings:
 
@@ -213,8 +219,11 @@ cog.outl("```")
 ## Attribute aider commits in the git committer name (default: True)
 #AIDER_ATTRIBUTE_COMMITTER=true
 
-## Prefix commit messages with 'aider: ' (default: False)
-#AIDER_ATTRIBUTE_COMMIT_MESSAGE=false
+## Prefix commit messages with 'aider: ' if aider authored the changes (default: False)
+#AIDER_ATTRIBUTE_COMMIT_MESSAGE_AUTHOR=false
+
+## Prefix all commit messages with 'aider: ' (default: False)
+#AIDER_ATTRIBUTE_COMMIT_MESSAGE_COMMITTER=false
 
 ## Commit all pending changes with a suitable commit message, then exit
 #AIDER_COMMIT=false
@@ -252,6 +261,9 @@ cog.outl("```")
 ## specify a file to edit (can be used multiple times)
 #AIDER_FILE=
 
+## specify a read-only file (can be used multiple times)
+#AIDER_READ=
+
 ## Use VI editing mode in the terminal (default: False)
 #AIDER_VIM=false
 

aider/website/docs/config/options.md

@@ -26,8 +26,8 @@ cog.out(get_md_help())
 ]]]-->
 ```
 usage: aider [-h] [--openai-api-key] [--anthropic-api-key] [--model]
-             [--opus] [--sonnet] [--4] [--4o] [--4-turbo]
-             [--35turbo] [--models] [--openai-api-base]
+             [--opus] [--sonnet] [--4] [--4o] [--mini] [--4-turbo]
+             [--35turbo] [--deepseek] [--models] [--openai-api-base]
              [--openai-api-type] [--openai-api-version]
              [--openai-api-deployment-id] [--openai-organization-id]
              [--model-settings-file] [--model-metadata-file]
@@ -47,12 +47,13 @@ usage: aider [-h] [--openai-api-key] [--anthropic-api-key] [--model]
              [--dirty-commits | --no-dirty-commits]
              [--attribute-author | --no-attribute-author]
              [--attribute-committer | --no-attribute-committer]
-             [--attribute-commit-message | --no-attribute-commit-message]
+             [--attribute-commit-message-author | --no-attribute-commit-message-author]
+             [--attribute-commit-message-committer | --no-attribute-commit-message-committer]
              [--commit] [--commit-prompt] [--dry-run | --no-dry-run]
              [--lint] [--lint-cmd] [--auto-lint | --no-auto-lint]
              [--test-cmd] [--auto-test | --no-auto-test] [--test]
-             [--file] [--vim] [--voice-language] [--version]
-             [--just-check-update]
+             [--file] [--read] [--vim] [--voice-language]
+             [--version] [--just-check-update]
              [--check-update | --no-check-update] [--apply] [--yes]
              [-v] [--show-repo-map] [--show-prompts] [--exit]
              [--message] [--message-file] [--encoding] [-c] [--gui]
@@ -100,6 +101,10 @@ Aliases:
 Use gpt-4o model for the main chat  
 Environment variable: `AIDER_4O`  
 
+### `--mini`
+Use gpt-4o-mini model for the main chat  
+Environment variable: `AIDER_MINI`  
+
 ### `--4-turbo`
 Use gpt-4-1106-preview model for the main chat  
 Environment variable: `AIDER_4_TURBO`  
@@ -113,6 +118,10 @@ Aliases:
   - `--3`
   - `-3`
 
+### `--deepseek`
+Use deepseek/deepseek-coder model for the main chat  
+Environment variable: `AIDER_DEEPSEEK`  
+
 ## Model Settings:
 
 ### `--models MODEL`
@@ -160,6 +169,9 @@ Aliases:
 ### `--edit-format EDIT_FORMAT`
 Specify what edit format the LLM should use (default depends on model)  
 Environment variable: `AIDER_EDIT_FORMAT`  
+Aliases:
+  - `--edit-format EDIT_FORMAT`
+  - `--chat-mode EDIT_FORMAT`
 
 ### `--weak-model WEAK_MODEL`
 Specify the model to use for commit messages and chat history summarization (default depends on --model)  
@@ -327,13 +339,21 @@ Aliases:
   - `--attribute-committer`
   - `--no-attribute-committer`
 
-### `--attribute-commit-message`
-Prefix commit messages with 'aider: ' (default: False)  
+### `--attribute-commit-message-author`
+Prefix commit messages with 'aider: ' if aider authored the changes (default: False)  
 Default: False  
-Environment variable: `AIDER_ATTRIBUTE_COMMIT_MESSAGE`  
+Environment variable: `AIDER_ATTRIBUTE_COMMIT_MESSAGE_AUTHOR`  
 Aliases:
-  - `--attribute-commit-message`
-  - `--no-attribute-commit-message`
+  - `--attribute-commit-message-author`
+  - `--no-attribute-commit-message-author`
+
+### `--attribute-commit-message-committer`
+Prefix all commit messages with 'aider: ' (default: False)  
+Default: False  
+Environment variable: `AIDER_ATTRIBUTE_COMMIT_MESSAGE_COMMITTER`  
+Aliases:
+  - `--attribute-commit-message-committer`
+  - `--no-attribute-commit-message-committer`
 
 ### `--commit`
 Commit all pending changes with a suitable commit message, then exit  
@@ -396,6 +416,10 @@ Environment variable: `AIDER_TEST`
 specify a file to edit (can be used multiple times)  
 Environment variable: `AIDER_FILE`  
 
+### `--read FILE`
+specify a read-only file (can be used multiple times)  
+Environment variable: `AIDER_READ`  
+
 ### `--vim`
 Use VI editing mode in the terminal (default: False)  
 Default: False  

aider/website/docs/faq.md

@@ -73,7 +73,7 @@ cd aider
 # It's recommended to make a virtual environment
 
 # Install the dependencies listed in the `requirements.txt` file:
-pip install -e .
+python -m pip install -e .
 
 # Run the local version of Aider:
 python -m aider

aider/website/docs/git.md

@@ -55,5 +55,9 @@ Aider marks commits that it either authored or committed.
 You can use `--no-attribute-author` and `--no-attribute-committer` to disable
 modification of the git author and committer name fields.
 
-Additionally, you can use `--attribute-commit-message` to prefix commit messages with 'aider: '.
-This option is disabled by default, but can be useful for easily identifying commits made by aider.
+Additionally, you can use the following options to prefix commit messages:
+
+- `--attribute-commit-message-author`: Prefix commit messages with 'aider: ' if aider authored the changes.
+- `--attribute-commit-message-committer`: Prefix all commit messages with 'aider: ', regardless of whether aider authored the changes or not.
+
+Both of these options are disabled by default, but can be useful for easily identifying changes made by aider.

aider/website/docs/install.md

@@ -15,6 +15,8 @@ for more details,
 or the
 [usage instructions](https://aider.chat/docs/usage.html) to start coding with aider.
 
+{% include python-m-aider.md %}
+
 <div class="video-container">
   <video controls poster="/assets/install.jpg">
     <source src="/assets/install.mp4" type="video/mp4">

aider/website/docs/install/install.md

@@ -25,13 +25,7 @@ To work with Anthropic's models like Claude 3.5 Sonnet you need a paid
 [Anthropic API key](https://docs.anthropic.com/claude/reference/getting-started-with-the-api).
 
 
-{: .tip }
-Using a Python 
-[virtual environment](https://docs.python.org/3/library/venv.html){:target="_blank"}
-is recommended.
-Or, you could
-[use pipx to install aider](/docs/install/pipx.html)
-once for your whole system.
+{% include venv-pipx.md %}
 
 ## Mac/Linux install
 
@@ -59,10 +53,7 @@ $ aider --4o --openai-api-key sk-xxx...
 $ aider --sonnet --anthropic-api-key sk-xxx...
 ```
 
-{: .tip }
-In some environments the `aider` command may not be available
-on your shell path.
-You can also run aider like this: `python -m aider`
+{% include python-m-aider.md %}
 
 ## Working with other LLMs
 

aider/website/docs/install/pipx.md

@@ -8,7 +8,7 @@ nav_order: 100
 If you are using aider to work on a python project, sometimes your project will require
 specific versions of python packages which conflict with the versions that aider
 requires.
-If this happens, the `pip install` command may return errors like these:
+If this happens, the `python -m pip install` command may return errors like these:
 
 ```
 aider-chat 0.23.0 requires somepackage==X.Y.Z, but you have somepackage U.W.V which is incompatible.

aider/website/docs/languages.md

@@ -5,7 +5,7 @@ description: Aider supports pretty much all popular coding languages.
 ---
 # Supported languages
 
-Aider supports almost all popular coding languages.
+Aider should work well with most popular coding languages.
 This is because top LLMs are fluent in most mainstream languages,
 and familiar with popular libraries, packages and frameworks.
 
@@ -20,8 +20,6 @@ a [repository map](https://aider.chat/docs/repomap.html).
 Aider can currently produce repository maps for many popular
 mainstream languages, listed below.
 
-Aider should work quite well for other languages, even those
-without repo map or linter support.
 
 <!--[[[cog
 from aider.repomap import get_supported_languages_md
@@ -82,3 +80,30 @@ cog.out(get_supported_languages_md())
 
 <!--[[[end]]]-->
 
+
+
+## How to add support for another language
+
+Aider should work quite well for other languages, even those
+without repo map or linter support.
+You should really try coding with aider before
+assuming it needs better support for your language.
+
+That said, if aider already has support for linting your language,
+then it should be possible to add repo map support.
+To build a repo map, aider needs the `tags.scm` file
+from the given language's tree-sitter grammar.
+If you can find and share that file in a 
+[GitHub issue](https://github.com/paul-gauthier/aider/issues),
+then it may be possible to add repo map support.
+
+If aider doesn't support linting, it will be complicated to
+add linting and repo map support.
+That is because aider relies on 
+[py-tree-sitter-languages](https://github.com/grantjenks/py-tree-sitter-languages)
+to provide pre-packaged versions of tree-sitter
+parsers for many languages.
+
+Aider needs to be easy for users to install in many environments,
+and it is probably too complex to add dependencies on
+additional individual tree-sitter parsers.

aider/website/docs/leaderboards/index.md

@@ -136,6 +136,16 @@ The model also has to successfully apply all its changes to the source file with
   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>
 
 ## Code refactoring leaderboard
@@ -291,7 +301,7 @@ Submit results by opening a PR with edits to the
 By Paul Gauthier,
 last updated
 <!--[[[cog
-import os
+import subprocess
 import datetime
 
 files = [
@@ -300,11 +310,17 @@ files = [
     'aider/website/_data/refactor_leaderboard.yml'
 ]
 
-mod_times = [os.path.getmtime(file) for file in files]
-latest_mod_time = max(mod_times)
-mod_date = datetime.datetime.fromtimestamp(latest_mod_time)
-cog.out(f"{mod_date.strftime('%B %d, %Y.')}")
+def get_last_modified_date(file):
+    result = subprocess.run(['git', 'log', '-1', '--format=%ct', file], capture_output=True, text=True)
+    if result.returncode == 0:
+        timestamp = int(result.stdout.strip())
+        return datetime.datetime.fromtimestamp(timestamp)
+    return datetime.datetime.min
+
+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.')}")
 ]]]-->
-August 06, 2024.
+August 10, 2024.
 <!--[[[end]]]-->
 </p>

aider/website/docs/llms/anthropic.md

@@ -14,7 +14,7 @@ Aider has some built in shortcuts for the most popular Anthropic models and
 has been tested and benchmarked to work well with them:
 
 ```
-pip install aider-chat
+python -m pip install aider-chat
 
 export ANTHROPIC_API_KEY=<key> # Mac/Linux
 setx   ANTHROPIC_API_KEY <key> # Windows, restart shell after setx
@@ -33,8 +33,8 @@ aider --models anthropic/
 Anthropic has very low rate limits. 
 You can access all the Anthropic models via
 [OpenRouter](openrouter.md)
-without rate limits.
-For example: `aider --model openrouter/anthropic/claude-3.5-sonnet`
+or [Google Vertex AI](vertex.md)
+with more generous rate limits.
 
 You can use `aider --model <model-name>` to use any other Anthropic model.
 For example, if you want to use a specific version of Opus

aider/website/docs/llms/azure.md

@@ -8,7 +8,7 @@ nav_order: 500
 Aider can connect to the OpenAI models on Azure.
 
 ```
-pip install aider-chat
+python -m pip install aider-chat
 
 # Mac/Linux:                                           
 export AZURE_API_KEY=<key>

aider/website/docs/llms/cohere.md

@@ -13,7 +13,7 @@ You'll need a [Cohere API key](https://dashboard.cohere.com/welcome/login).
 To use **Command-R+**:
 
 ```
-pip install aider-chat
+python -m pip install aider-chat
 
 export COHERE_API_KEY=<key> # Mac/Linux
 setx   COHERE_API_KEY <key> # Windows, restart shell after setx

aider/website/docs/llms/deepseek.md

@@ -6,19 +6,15 @@ nav_order: 500
 # DeepSeek
 
 Aider can connect to the DeepSeek.com API.
-The DeepSeek Coder V2 model gets the top score on aider's code editing benchmark.
+The DeepSeek Coder V2 model has a top score on aider's code editing benchmark.
 
 ```
-pip install aider-chat
+python -m pip install aider-chat
 
 export DEEPSEEK_API_KEY=<key> # Mac/Linux
 setx   DEEPSEEK_API_KEY <key> # Windows, restart shell after setx
 
 # Use DeepSeek Coder V2
-aider --model deepseek/deepseek-coder
+aider --deepseek
 ```
 
-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/gemini.md

@@ -12,7 +12,7 @@ with code editing capability that's comparable to GPT-3.5.
 You'll need a [Gemini API key](https://aistudio.google.com/app/u/2/apikey).
 
 ```
-pip install aider-chat
+python -m pip install aider-chat
 
 export GEMINI_API_KEY=<key> # Mac/Linux
 setx   GEMINI_API_KEY <key> # Windows, restart shell after setx

aider/website/docs/llms/groq.md

@@ -13,7 +13,7 @@ You'll need a [Groq API key](https://console.groq.com/keys).
 To use **Llama3 70B**:
 
 ```
-pip install aider-chat
+python -m pip install aider-chat
 
 export GROQ_API_KEY=<key> # Mac/Linux
 setx   GROQ_API_KEY <key> # Windows, restart shell after setx

aider/website/docs/llms/ollama.md

@@ -15,7 +15,7 @@ ollama pull <model>
 ollama serve
 
 # In another terminal window...
-pip install aider-chat
+python -m pip install 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/website/docs/llms/openai-compat.md

@@ -8,7 +8,7 @@ nav_order: 500
 Aider can connect to any LLM which is accessible via an OpenAI compatible API endpoint.
 
 ```
-pip install aider-chat
+python -m pip install aider-chat
 
 # Mac/Linux:
 export OPENAI_API_BASE=<endpoint>

aider/website/docs/llms/openai.md

@@ -14,7 +14,7 @@ Aider has some built in shortcuts for the most popular OpenAI models and
 has been tested and benchmarked to work well with them:
 
 ```
-pip install aider-chat
+python -m pip install aider-chat
 
 export OPENAI_API_KEY=<key> # Mac/Linux
 setx   OPENAI_API_KEY <key> # Windows, restart shell after setx

aider/website/docs/llms/openrouter.md

@@ -9,7 +9,7 @@ Aider can connect to [models provided by OpenRouter](https://openrouter.ai/model
 You'll need an [OpenRouter API key](https://openrouter.ai/keys).
 
 ```
-pip install aider-chat
+python -m pip install aider-chat
 
 export OPENROUTER_API_KEY=<key> # Mac/Linux
 setx   OPENROUTER_API_KEY <key> # Windows, restart shell after setx
@@ -21,15 +21,15 @@ aider --model openrouter/<provider>/<model>
 aider --models openrouter/
 ```
 
-In particular, Llama3 70B works well with aider, at low cost:
+In particular, many aider users access Sonnet via OpenRouter:
 
 ```
-pip install aider-chat
+python -m pip install aider-chat
 
 export OPENROUTER_API_KEY=<key> # Mac/Linux
 setx   OPENROUTER_API_KEY <key> # Windows, restart shell after setx
 
-aider --model openrouter/meta-llama/llama-3-70b-instruct
+aider --model openrouter/anthropic/claude-3.5-sonnet
 ```
 
 

aider/website/docs/llms/other.md

@@ -77,6 +77,7 @@ cog.out(''.join(lines))
 - FIREWORKS_API_KEY
 - FRIENDLIAI_API_KEY
 - GEMINI_API_KEY
+- GITHUB_API_KEY
 - GROQ_API_KEY
 - HUGGINGFACE_API_KEY
 - MARITALK_API_KEY

aider/website/docs/llms/vertex.md

@@ -0,0 +1,43 @@
+---
+parent: Connecting to LLMs
+nav_order: 550
+---
+
+# Vertex AI
+
+Aider can connect to models provided by Google Vertex AI.
+You will need to install the
+[gcloud CLI](https://cloud.google.com/sdk/docs/install) and [login](https://cloud.google.com/sdk/docs/initializing) with a GCP account
+or service account with permission to use the Vertex AI API.
+
+With your chosen login method, the gcloud CLI should automatically set the
+`GOOGLE_APPLICATION_CREDENTIALS` environment variable which points to the credentials file.
+
+To configure Aider to use the Vertex AI API, you need to set `VERTEXAI_PROJECT` (the GCP project ID)
+and `VERTEXAI_LOCATION` (the GCP region) [environment variables for Aider](/docs/config/dotenv.html).
+
+Note that Claude on Vertex AI is only available in certain GCP regions, 
+check [the model card](https://console.cloud.google.com/vertex-ai/publishers/anthropic/model-garden/claude-3-5-sonnet) 
+for your model to see which regions are supported.
+
+Example `.env` file:
+
+```
+VERTEXAI_PROJECT=my-project
+VERTEXAI_LOCATION=us-east5
+```
+
+Then you can run aider with the `--model` command line switch, like this:
+
+```
+aider --model vertex_ai/claude-3-5-sonnet@20240620
+```
+
+Or you can use the [yaml config](/docs/config/aider_conf.html) to set the model to any of the 
+models supported by Vertex AI.
+
+Example `.aider.conf.yml` file:
+
+```yaml
+model: vertex_ai/claude-3-5-sonnet@20240620
+```

aider/website/docs/scripting.md

@@ -74,6 +74,10 @@ coder.run("make a script that prints hello world")
 
 # Send another instruction
 coder.run("make it say goodbye")
+
+# You can run in-chat "/" commands too
+coder.run("/tokens")
+
 ```
 
 See the

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

@@ -0,0 +1,25 @@
+---
+parent: Troubleshooting
+nav_order: 28
+---
+
+# Aider not found
+
+In some environments the `aider` command may not be available
+on your shell path.
+This can occur because of permissions/security settings in your OS,
+and often happens to Windows users.
+
+You may see an error message like this:
+
+> aider: The term 'aider' is not recognized as a name of a cmdlet, function, script file, or executable program. Check the spelling of the name, or if a path was included, verify that the path is correct and try again.
+
+Below is the most fail safe way to install and run aider in these situations:
+
+```
+python -m pip install aider-chat
+python -m aider
+```
+
+
+{% include venv-pipx.md %}

aider/website/docs/usage/browser.md

@@ -48,7 +48,7 @@ It also supports [connecting to almost any LLM](https://aider.chat/docs/llms.htm
 Use the `--browser` switch to launch the browser version of aider:
 
 ```
-pip install aider-chat
+python -m pip install aider-chat
 
 export OPENAI_API_KEY=<key> # Mac/Linux
 setx   OPENAI_API_KEY <key> # Windows, restart shell after setx

aider/website/docs/usage/commands.md

@@ -15,27 +15,30 @@ cog.out(get_help_md())
 |Command|Description|
 |:------|:----------|
 | **/add** | Add files to the chat so GPT can edit them or review them in detail |
-| **/add-clipboard-image** | Add an image from the clipboard to the chat |
 | **/ask** | Ask questions about the code base without editing any files |
 | **/chat-mode** | Switch to a new chat mode |
 | **/clear** | Clear the chat history |
+| **/clipboard** | Add image/text from the clipboard to the chat (optionally provide a name for the image) |
+| **/code** | Ask for changes to your code |
 | **/commit** | Commit edits to the repo made outside the chat (commit message optional) |
-| **/diff** | Display the diff of the last aider commit |
+| **/diff** | Display the diff of changes since the last message |
 | **/drop** | Remove files from the chat session to free up context space |
 | **/exit** | Exit the application |
 | **/git** | Run a git command |
 | **/help** | Ask questions about aider |
 | **/lint** | Lint and fix provided files or in-chat files if none provided |
 | **/ls** | List all known files and indicate which are included in the chat session |
+| **/map** | Print out the current repository map |
 | **/model** | Switch to a new LLM |
 | **/models** | Search the list of available models |
 | **/quit** | Exit the application |
+| **/read** | Add a file to the chat that is for reference, not to be edited |
 | **/run** | Run a shell command and optionally add the output to the chat (alias: !) |
 | **/test** | Run a shell command and add the output to the chat on non-zero exit code |
 | **/tokens** | Report on the number of tokens used by the current chat context |
 | **/undo** | Undo the last git commit if it was done by aider |
 | **/voice** | Record and transcribe voice input |
-| **/web** | Use headless selenium to scrape a webpage and add the content to the chat |
+| **/web** | Scrape a webpage, convert to markdown and add to the chat |
 
 <!--[[[end]]]-->
 

aider/website/docs/usage/modes.md

@@ -13,7 +13,20 @@ Aider has 3 different chat modes:
 - `help` - Aider will answer questions about using aider, configuring, troubleshooting, etc.
 
 By default, aider starts in "code" mode. As you are talking, you can
-send messages in other modes using `/ask` and `/help` commands:
+send individual messages in a specific mode using `/code`, `/ask`, and `/help` commands:
+Using `/code`, `/ask`, and `/help` applies just to that particular message.
+Your next message will go back to the active mode (usually "code" mode by default).
+
+You can switch the active mode in a sticky way
+with the `/chat-mode <mode>` command:
+
+```
+/chat-mode code
+/chat-mode ask
+/chat-mode help
+```
+
+Or you can launch aider in one of the modes with the `--chat-mode <mode>` switch.
 
 <div class="chat-transcript" markdown="1">
 
@@ -33,17 +46,22 @@ This is the source code to the popular django package.
 Run `aider --model ollama/<ollama-model>`.
 See these docs for more info: https://aider.chat/docs/llms/ollama.html
 
+#### /code Add a function to calculate the factorial of a number
+
+Certainly! I'll add a function to calculate the factorial of a number. Here's the change:
+
+```python
+def factorial(n):
+    if n == 0 or n == 1:
+        return 1
+    else:
+        return n * factorial(n - 1)
+
+# Example usage
+print(factorial(5))  # Output: 120
+```
+
+This function uses recursion to calculate the factorial. It's been added to your code.
+
 </div>
 
-Using `/ask` and `/help` applies just to that particular message.
-Your next message will go back to code mode.
-
-You can switch between the modes in a sticky way
-with the `/chat-mode <mode>` command:
-
-```
-/chat-mode code
-/chat-mode ask
-/chat-mode help
-```
-

aider/website/index.md

@@ -49,18 +49,18 @@ cog.out(open("aider/website/_includes/get-started.md").read())
 You can get started quickly like this:
 
 ```
-$ pip install aider-chat
+python -m pip install aider-chat
 
 # Change directory into a git repo
-$ cd /to/your/git/repo
+cd /to/your/git/repo
 
 # Work with Claude 3.5 Sonnet on your repo
-$ export ANTHROPIC_API_KEY=your-key-goes-here
-$ aider
+export ANTHROPIC_API_KEY=your-key-goes-here
+aider
 
 # Work with GPT-4o on your repo
-$ export OPENAI_API_KEY=your-key-goes-here
-$ aider 
+export OPENAI_API_KEY=your-key-goes-here
+aider 
 ```
 <!-- NOOP -->
 

pyproject.toml

@@ -0,0 +1,67 @@
+# [[[cog
+# from aider.help_pats import exclude_website_pats
+# ]]]
+# [[[end]]]
+
+[project]
+name = "aider-chat"
+description = "Aider is AI pair programming in your terminal"
+readme = "README.md"
+classifiers = [
+    "Development Status :: 4 - Beta",
+    "Environment :: Console",
+    "Intended Audience :: Developers",
+    "License :: OSI Approved :: Apache Software License",
+    "Programming Language :: Python :: 3",
+    "Programming Language :: Python :: 3.10",
+    "Programming Language :: Python :: 3.11",
+    "Programming Language :: Python :: 3.12",
+    "Programming Language :: Python :: 3.9",
+    "Programming Language :: Python",
+    "Topic :: Software Development",
+]
+requires-python = ">=3.9,<3.13"
+dynamic = ["dependencies", "optional-dependencies", "version"]
+
+[project.urls]
+Homepage = "https://github.com/paul-gauthier/aider"
+
+[project.scripts]
+aider = "aider.main:main"
+
+[tool.setuptools.dynamic]
+version = { attr = "aider.__init__.__version__" }
+dependencies = { file = "requirements.txt" }
+
+[tool.setuptools.dynamic.optional-dependencies]
+dev = { file = "requirements/requirements-dev.txt" }
+help = { file = "requirements/requirements-help.txt" }
+browser = { file = "requirements/requirements-browser.txt" }
+playwright = { file = "requirements/requirements-playwright.txt" }
+
+[tool.setuptools.packages.find]
+include = ["aider*", "aider.website"]
+
+[tool.setuptools.package-data]
+"aider" = ["queries/*.scm"]
+"aider.website" = ["**/*.md"]
+
+[tool.setuptools.exclude-package-data]
+"aider.website" = [
+# [[[cog
+# cog.out("\n".join(f'    "{pat}",' for pat in exclude_website_pats))
+# ]]]
+"examples/**",
+"_posts/**",
+"HISTORY.md",
+"docs/benchmarks*md",
+"docs/ctags.md",
+"docs/unified-diffs.md",
+"docs/leaderboards/index.md",
+"assets/**",
+# [[[end]]]
+]
+
+[build-system]
+requires = ["setuptools>=68"]
+build-backend = "setuptools.build_meta"

requirements.txt

@@ -4,9 +4,9 @@
 #
 #    pip-compile --output-file=requirements.txt requirements/requirements.in
 #
-aiohappyeyeballs==2.3.4
+aiohappyeyeballs==2.3.5
     # via aiohttp
-aiohttp==3.10.0
+aiohttp==3.10.3
     # via litellm
 aiosignal==1.3.1
     # via aiohttp
@@ -16,7 +16,7 @@ anyio==4.4.0
     # via
     #   httpx
     #   openai
-attrs==23.2.0
+attrs==24.2.0
     # via
     #   aiohttp
     #   jsonschema
@@ -30,7 +30,7 @@ certifi==2024.7.4
     #   httpcore
     #   httpx
     #   requests
-cffi==1.16.0
+cffi==1.17.0
     # via
     #   sounddevice
     #   soundfile
@@ -48,7 +48,7 @@ distro==1.9.0
     # via openai
 filelock==3.15.4
     # via huggingface-hub
-flake8==7.1.0
+flake8==7.1.1
     # via -r requirements/requirements.in
 frozenlist==1.4.1
     # via
@@ -84,13 +84,15 @@ importlib-resources==6.4.0
     # via -r requirements/requirements.in
 jinja2==3.1.4
     # via litellm
+jiter==0.5.0
+    # via openai
 jsonschema==4.23.0
     # via
     #   -r requirements/requirements.in
     #   litellm
 jsonschema-specifications==2023.12.1
     # via jsonschema
-litellm==1.42.9
+litellm==1.43.9
     # via -r requirements/requirements.in
 markdown-it-py==3.0.0
     # via rich
@@ -110,7 +112,7 @@ numpy==1.26.4
     # via
     #   -r requirements/requirements.in
     #   scipy
-openai==1.37.2
+openai==1.40.6
     # via litellm
 packaging==24.1
     # via
@@ -123,8 +125,10 @@ pathspec==0.12.1
 pillow==10.4.0
     # via -r requirements/requirements.in
 prompt-toolkit==3.0.47
-    # via -r requirements/requirements.in
-pycodestyle==2.12.0
+    # via
+    #   -r requirements/requirements.in
+    #   pypager
+pycodestyle==2.12.1
     # via flake8
 pycparser==2.22
     # via cffi
@@ -137,12 +141,18 @@ pydantic-core==2.20.1
 pyflakes==3.2.0
     # via flake8
 pygments==2.18.0
-    # via rich
+    # via
+    #   pypager
+    #   rich
+pypager==3.0.1
+    # via -r requirements/requirements.in
 pypandoc==1.13
     # via -r requirements/requirements.in
+pyperclip==1.9.0
+    # via -r requirements/requirements.in
 python-dotenv==1.0.1
     # via litellm
-pyyaml==6.0.1
+pyyaml==6.0.2
     # via
     #   -r requirements/requirements.in
     #   huggingface-hub
@@ -159,7 +169,7 @@ requests==2.32.3
     #   tiktoken
 rich==13.7.1
     # via -r requirements/requirements.in
-rpds-py==0.19.1
+rpds-py==0.20.0
     # via
     #   jsonschema
     #   referencing
@@ -172,7 +182,7 @@ sniffio==1.3.1
     #   anyio
     #   httpx
     #   openai
-sounddevice==0.4.7
+sounddevice==0.5.0
     # via -r requirements/requirements.in
 soundfile==0.12.1
     # via -r requirements/requirements.in
@@ -181,8 +191,10 @@ soupsieve==2.5
 tiktoken==0.7.0
     # via litellm
 tokenizers==0.19.1
-    # via litellm
-tqdm==4.66.4
+    # via
+    #   -r requirements/requirements.in
+    #   litellm
+tqdm==4.66.5
     # via
     #   huggingface-hub
     #   openai
@@ -204,5 +216,5 @@ wcwidth==0.2.13
     # via prompt-toolkit
 yarl==1.9.4
     # via aiohttp
-zipp==3.19.2
+zipp==3.20.0
     # via importlib-metadata

requirements/requirements-browser.txt

@@ -4,9 +4,9 @@
 #
 #    pip-compile --output-file=requirements/requirements-browser.txt requirements/requirements-browser.in
 #
-altair==5.3.0
+altair==5.4.0
     # via streamlit
-attrs==23.2.0
+attrs==24.2.0
     # via
     #   -c requirements/../requirements.txt
     #   jsonschema
@@ -64,10 +64,11 @@ mdurl==0.1.2
     # via
     #   -c requirements/../requirements.txt
     #   markdown-it-py
+narwhals==1.3.0
+    # via altair
 numpy==1.26.4
     # via
     #   -c requirements/../requirements.txt
-    #   altair
     #   pandas
     #   pyarrow
     #   pydeck
@@ -78,9 +79,7 @@ packaging==24.1
     #   altair
     #   streamlit
 pandas==2.2.2
-    # via
-    #   altair
-    #   streamlit
+    # via streamlit
 pillow==10.4.0
     # via
     #   -c requirements/../requirements.txt
@@ -112,7 +111,7 @@ rich==13.7.1
     # via
     #   -c requirements/../requirements.txt
     #   streamlit
-rpds-py==0.19.1
+rpds-py==0.20.0
     # via
     #   -c requirements/../requirements.txt
     #   jsonschema
@@ -123,19 +122,18 @@ smmap==5.0.1
     # via
     #   -c requirements/../requirements.txt
     #   gitdb
-streamlit==1.37.0
+streamlit==1.37.1
     # via -r requirements/requirements-browser.in
 tenacity==8.5.0
     # via streamlit
 toml==0.10.2
     # via streamlit
-toolz==0.12.1
-    # via altair
 tornado==6.4.1
     # via streamlit
 typing-extensions==4.12.2
     # via
     #   -c requirements/../requirements.txt
+    #   altair
     #   streamlit
 tzdata==2024.1
     # via pandas
@@ -143,5 +141,5 @@ urllib3==2.2.2
     # via
     #   -c requirements/../requirements.txt
     #   requests
-watchdog==4.0.1
+watchdog==4.0.2
     # via -r requirements/requirements-browser.in

requirements/requirements-dev.txt

@@ -6,7 +6,7 @@
 #
 alabaster==0.7.16
     # via sphinx
-babel==2.15.0
+babel==2.16.0
     # via sphinx
 build==1.2.1
     # via pip-tools
@@ -75,7 +75,7 @@ markupsafe==2.1.5
     # via
     #   -c requirements/../requirements.txt
     #   jinja2
-matplotlib==3.9.1
+matplotlib==3.9.2
     # via -r requirements/requirements-dev.in
 mdurl==0.1.2
     # via
@@ -137,7 +137,7 @@ python-dateutil==2.9.0.post0
     #   pandas
 pytz==2024.1
     # via pandas
-pyyaml==6.0.1
+pyyaml==6.0.2
     # via
     #   -c requirements/../requirements.txt
     #   pre-commit
@@ -191,7 +191,7 @@ urllib3==2.2.2
     #   requests
 virtualenv==20.26.3
     # via pre-commit
-wheel==0.43.0
+wheel==0.44.0
     # via pip-tools
 
 # The following packages are considered to be unsafe in a requirements file:

requirements/requirements-help.txt

@@ -4,11 +4,11 @@
 #
 #    pip-compile --output-file=requirements/requirements-help.txt requirements/requirements-help.in
 #
-aiohappyeyeballs==2.3.4
+aiohappyeyeballs==2.3.5
     # via
     #   -c requirements/../requirements.txt
     #   aiohttp
-aiohttp==3.10.0
+aiohttp==3.10.3
     # via
     #   -c requirements/../requirements.txt
     #   huggingface-hub
@@ -26,7 +26,7 @@ anyio==4.4.0
     #   -c requirements/../requirements.txt
     #   httpx
     #   openai
-attrs==23.2.0
+attrs==24.2.0
     # via
     #   -c requirements/../requirements.txt
     #   aiohttp
@@ -104,15 +104,19 @@ jinja2==3.1.4
     # via
     #   -c requirements/../requirements.txt
     #   torch
+jiter==0.5.0
+    # via
+    #   -c requirements/../requirements.txt
+    #   openai
 joblib==1.4.2
     # via
     #   nltk
     #   scikit-learn
-llama-index-core==0.10.59
+llama-index-core==0.10.65
     # via
     #   -r requirements/requirements-help.in
     #   llama-index-embeddings-huggingface
-llama-index-embeddings-huggingface==0.2.2
+llama-index-embeddings-huggingface==0.2.3
     # via -r requirements/requirements-help.in
 markupsafe==2.1.5
     # via
@@ -138,7 +142,7 @@ networkx==3.2.1
     #   -c requirements/../requirements.txt
     #   llama-index-core
     #   torch
-nltk==3.8.1
+nltk==3.8.2
     # via llama-index-core
 numpy==1.26.4
     # via
@@ -149,7 +153,7 @@ numpy==1.26.4
     #   scipy
     #   sentence-transformers
     #   transformers
-openai==1.37.2
+openai==1.40.6
     # via
     #   -c requirements/../requirements.txt
     #   llama-index-core
@@ -178,7 +182,7 @@ python-dateutil==2.9.0.post0
     # via pandas
 pytz==2024.1
     # via pandas
-pyyaml==6.0.1
+pyyaml==6.0.2
     # via
     #   -c requirements/../requirements.txt
     #   huggingface-hub
@@ -197,7 +201,7 @@ requests==2.32.3
     #   llama-index-core
     #   tiktoken
     #   transformers
-safetensors==0.4.3
+safetensors==0.4.4
     # via transformers
 scikit-learn==1.5.1
     # via sentence-transformers
@@ -216,11 +220,11 @@ sniffio==1.3.1
     #   anyio
     #   httpx
     #   openai
-sqlalchemy[asyncio]==2.0.31
+sqlalchemy[asyncio]==2.0.32
     # via
     #   llama-index-core
     #   sqlalchemy
-sympy==1.13.1
+sympy==1.13.2
     # via torch
 tenacity==8.5.0
     # via llama-index-core
@@ -236,7 +240,7 @@ tokenizers==0.19.1
     #   transformers
 torch==2.2.2
     # via sentence-transformers
-tqdm==4.66.4
+tqdm==4.66.5
     # via
     #   -c requirements/../requirements.txt
     #   huggingface-hub
@@ -245,7 +249,7 @@ tqdm==4.66.4
     #   openai
     #   sentence-transformers
     #   transformers
-transformers==4.43.3
+transformers==4.44.0
     # via sentence-transformers
 typing-extensions==4.12.2
     # via

requirements/requirements-playwright.txt

@@ -6,7 +6,7 @@
 #
 greenlet==3.0.3
     # via playwright
-playwright==1.45.1
+playwright==1.46.0
     # via -r requirements/requirements-playwright.in
 pyee==11.1.0
     # via playwright

requirements/requirements.in

@@ -22,6 +22,8 @@ pypandoc
 litellm
 flake8
 importlib_resources
+pyperclip
+pypager
 
 # The proper depdendency is networkx[default], but this brings
 # in matplotlib and a bunch of other deps
@@ -46,3 +48,7 @@ importlib-metadata<8.0.0
 
 # Because sentence-transformers doesn't like >=2
 numpy<2
+
+# Going past this makes dependencies unresolvable
+# Seems to be caused by sentence-transformers
+tokenizers==0.19.1

scripts/blame.py

@@ -2,6 +2,7 @@
 
 import argparse
 import subprocess
+import sys
 from collections import defaultdict
 from datetime import datetime
 from operator import itemgetter
@@ -17,10 +18,14 @@ def blame(start_tag, end_tag=None):
 
     authors = get_commit_authors(commits)
 
-    pats = "*.py *.scm *.sh **Dockerfile **Gemfile .github/workflows/*.yml".split()
-    files = []
-    for pat in pats:
-        files += run(["git", "ls-files", pat]).strip().split("\n")
+    revision = end_tag if end_tag else "HEAD"
+    files = run(["git", "ls-tree", "-r", "--name-only", revision]).strip().split("\n")
+    files = [
+        f
+        for f in files
+        if f.endswith((".py", ".scm", ".sh", "Dockerfile", "Gemfile"))
+        or (f.startswith(".github/workflows/") and f.endswith(".yml"))
+    ]
 
     all_file_counts = {}
     grand_total = defaultdict(int)
@@ -186,10 +191,14 @@ def get_counts_for_file(start_tag, end_tag, authors, fname):
             line_counts[author] += 1
 
         return dict(line_counts)
-    except subprocess.CalledProcessError:
-        # print(f"Warning: Unable to blame file {fname}. It may have been added after {start_tag} "
-        #       f"or removed before {end_tag or 'HEAD'}.", file=sys.stderr)
-        return None
+    except subprocess.CalledProcessError as e:
+        if "no such path" in str(e).lower():
+            # File doesn't exist in this revision range, which is okay
+            return None
+        else:
+            # Some other error occurred
+            print(f"Warning: Unable to blame file {fname}. Error: {e}", file=sys.stderr)
+            return None
 
 
 def get_all_tags_since(start_tag):

scripts/versionbump.py

@@ -9,22 +9,36 @@ import sys
 from packaging import version
 
 
+def check_cog_pyproject():
+    result = subprocess.run(["cog", "--check", "pyproject.toml"], capture_output=True, text=True)
+
+    if result.returncode != 0:
+        print("Error: cog --check pyproject.toml failed, updating.")
+        subprocess.run(["cog", "-r", "pyproject.toml"])
+        sys.exit(1)
+
+
 def main():
     parser = argparse.ArgumentParser(description="Bump version")
     parser.add_argument("new_version", help="New version in x.y.z format")
     parser.add_argument(
         "--dry-run", action="store_true", help="Print each step without actually executing them"
     )
+
     # Function to check if we are on the main branch
     def check_branch():
-        branch = subprocess.run(["git", "rev-parse", "--abbrev-ref", "HEAD"], capture_output=True, text=True).stdout.strip()
+        branch = subprocess.run(
+            ["git", "rev-parse", "--abbrev-ref", "HEAD"], capture_output=True, text=True
+        ).stdout.strip()
         if branch != "main":
             print("Error: Not on the main branch.")
             sys.exit(1)
 
     # Function to check if the working directory is clean
     def check_working_directory_clean():
-        status = subprocess.run(["git", "status", "--porcelain"], capture_output=True, text=True).stdout
+        status = subprocess.run(
+            ["git", "status", "--porcelain"], capture_output=True, text=True
+        ).stdout
         if status:
             print("Error: Working directory is not clean.")
             sys.exit(1)
@@ -32,19 +46,33 @@ def main():
     # Function to fetch the latest changes and check if the main branch is up to date
     def check_main_branch_up_to_date():
         subprocess.run(["git", "fetch", "origin"], check=True)
-        local_main = subprocess.run(["git", "rev-parse", "main"], capture_output=True, text=True).stdout.strip()
+        local_main = subprocess.run(
+            ["git", "rev-parse", "main"], capture_output=True, text=True
+        ).stdout.strip()
         print(f"Local main commit hash: {local_main}")
-        origin_main = subprocess.run(["git", "rev-parse", "origin/main"], capture_output=True, text=True).stdout.strip()
+        origin_main = subprocess.run(
+            ["git", "rev-parse", "origin/main"], capture_output=True, text=True
+        ).stdout.strip()
         print(f"Origin main commit hash: {origin_main}")
         if local_main != origin_main:
-            local_date = subprocess.run(["git", "show", "-s", "--format=%ci", "main"], capture_output=True, text=True).stdout.strip()
-            origin_date = subprocess.run(["git", "show", "-s", "--format=%ci", "origin/main"], capture_output=True, text=True).stdout.strip()
+            local_date = subprocess.run(
+                ["git", "show", "-s", "--format=%ci", "main"], capture_output=True, text=True
+            ).stdout.strip()
+            origin_date = subprocess.run(
+                ["git", "show", "-s", "--format=%ci", "origin/main"], capture_output=True, text=True
+            ).stdout.strip()
             local_date = datetime.datetime.strptime(local_date, "%Y-%m-%d %H:%M:%S %z")
             origin_date = datetime.datetime.strptime(origin_date, "%Y-%m-%d %H:%M:%S %z")
             if local_date < origin_date:
-                print("Error: The local main branch is behind origin/main. Please pull the latest changes.")
+                print(
+                    "Error: The local main branch is behind origin/main. Please pull the latest"
+                    " changes."
+                )
             elif local_date > origin_date:
-                print("Error: The origin/main branch is behind the local main branch. Please push your changes.")
+                print(
+                    "Error: The origin/main branch is behind the local main branch. Please push"
+                    " your changes."
+                )
             else:
                 print("Error: The main branch and origin/main have diverged.")
             sys.exit(1)
@@ -53,6 +81,7 @@ def main():
     dry_run = args.dry_run
 
     # Perform checks before proceeding
+    check_cog_pyproject()
     check_branch()
     check_working_directory_clean()
     check_main_branch_up_to_date()

setup.py

@@ -1,73 +0,0 @@
-import re
-from pathlib import Path
-
-from setuptools import find_packages, setup
-
-from aider import __version__
-from aider.help_pats import exclude_website_pats
-
-
-def get_requirements(suffix=""):
-    if suffix:
-        fname = "requirements-" + suffix + ".txt"
-        fname = Path("requirements") / fname
-    else:
-        fname = Path("requirements.txt")
-
-    requirements = fname.read_text().splitlines()
-
-    return requirements
-
-
-requirements = get_requirements()
-
-# README
-with open("README.md", "r", encoding="utf-8") as f:
-    long_description = f.read()
-    long_description = re.sub(r"\n!\[.*\]\(.*\)", "", long_description)
-    # long_description = re.sub(r"\n- \[.*\]\(.*\)", "", long_description)
-
-# Discover packages, plus the website
-packages = find_packages(exclude=["benchmark", "tests"])
-packages += ["aider.website"]
-
-print("Packages:", packages)
-
-extras = "dev help browser playwright".split()
-
-setup(
-    name="aider-chat",
-    version=__version__,
-    packages=packages,
-    include_package_data=True,
-    package_data={
-        "aider": ["queries/*.scm"],
-        "aider.website": ["**/*.md"],
-    },
-    exclude_package_data={"aider.website": exclude_website_pats},
-    install_requires=requirements,
-    extras_require={extra: get_requirements(extra) for extra in extras},
-    python_requires=">=3.9,<3.13",
-    entry_points={
-        "console_scripts": [
-            "aider = aider.main:main",
-        ],
-    },
-    description="Aider is AI pair programming in your terminal",
-    long_description=long_description,
-    long_description_content_type="text/markdown",
-    url="https://github.com/paul-gauthier/aider",
-    classifiers=[
-        "Development Status :: 4 - Beta",
-        "Environment :: Console",
-        "Intended Audience :: Developers",
-        "License :: OSI Approved :: Apache Software License",
-        "Programming Language :: Python :: 3",
-        "Programming Language :: Python :: 3.10",
-        "Programming Language :: Python :: 3.11",
-        "Programming Language :: Python :: 3.12",
-        "Programming Language :: Python :: 3.9",
-        "Programming Language :: Python",
-        "Topic :: Software Development",
-    ],
-)

tests/basic/test_coder.py

@@ -189,6 +189,33 @@ class TestCoder(unittest.TestCase):
 
             self.assertEqual(coder.abs_fnames, set([str(fname.resolve())]))
 
+    def test_check_for_file_mentions_read_only(self):
+        with GitTemporaryDirectory():
+            io = InputOutput(
+                pretty=False,
+                yes=True,
+            )
+            coder = Coder.create(self.GPT35, None, io)
+
+            fname = Path("readonly_file.txt")
+            fname.touch()
+
+            coder.abs_read_only_fnames.add(str(fname.resolve()))
+
+            # Mock the get_tracked_files method
+            mock = MagicMock()
+            mock.return_value = set([str(fname)])
+            coder.repo.get_tracked_files = mock
+
+            # Call the check_for_file_mentions method
+            result = coder.check_for_file_mentions(f"Please check {fname}!")
+
+            # Assert that the method returns None (user not asked to add the file)
+            self.assertIsNone(result)
+
+            # Assert that abs_fnames is still empty (file not added)
+            self.assertEqual(coder.abs_fnames, set())
+
     def test_check_for_subdir_mention(self):
         with GitTemporaryDirectory():
             io = InputOutput(pretty=False, yes=True)
@@ -259,7 +286,7 @@ class TestCoder(unittest.TestCase):
         files = [file1, file2]
 
         # Initialize the Coder object with the mocked IO and mocked repo
-        coder = Coder.create(self.GPT35, None, io=InputOutput(), fnames=files, pretty=False)
+        coder = Coder.create(self.GPT35, None, io=InputOutput(), fnames=files)
 
         def mock_send(*args, **kwargs):
             coder.partial_response_content = "ok"
@@ -286,7 +313,7 @@ class TestCoder(unittest.TestCase):
         files = [file1, file2]
 
         # Initialize the Coder object with the mocked IO and mocked repo
-        coder = Coder.create(self.GPT35, None, io=InputOutput(), fnames=files, pretty=False)
+        coder = Coder.create(self.GPT35, None, io=InputOutput(), fnames=files)
 
         def mock_send(*args, **kwargs):
             coder.partial_response_content = "ok"
@@ -377,7 +404,7 @@ class TestCoder(unittest.TestCase):
             fname = Path("file.txt")
 
             io = InputOutput(yes=True)
-            coder = Coder.create(self.GPT35, "diff", io=io, fnames=[str(fname)], pretty=False)
+            coder = Coder.create(self.GPT35, "diff", io=io, fnames=[str(fname)])
 
             self.assertTrue(fname.exists())
 
@@ -434,9 +461,7 @@ new
             fname1.write_text("ONE\n")
 
             io = InputOutput(yes=True)
-            coder = Coder.create(
-                self.GPT35, "diff", io=io, fnames=[str(fname1), str(fname2)], pretty=False
-            )
+            coder = Coder.create(self.GPT35, "diff", io=io, fnames=[str(fname1), str(fname2)])
 
             def mock_send(*args, **kwargs):
                 coder.partial_response_content = f"""
@@ -489,7 +514,7 @@ TWO
             fname2.write_text("OTHER\n")
 
             io = InputOutput(yes=True)
-            coder = Coder.create(self.GPT35, "diff", io=io, fnames=[str(fname)], pretty=False)
+            coder = Coder.create(self.GPT35, "diff", io=io, fnames=[str(fname)])
 
             def mock_send(*args, **kwargs):
                 coder.partial_response_content = f"""
@@ -567,7 +592,7 @@ three
             repo.git.commit("-m", "initial")
 
             io = InputOutput(yes=True)
-            coder = Coder.create(self.GPT35, "diff", io=io, fnames=[str(fname)], pretty=False)
+            coder = Coder.create(self.GPT35, "diff", io=io, fnames=[str(fname)])
 
             def mock_send(*args, **kwargs):
                 coder.partial_response_content = f"""
@@ -640,7 +665,7 @@ two
 
     def test_check_for_urls(self):
         io = InputOutput(yes=True)
-        coder = Coder.create(self.GPT35, None, io=io, pretty=False)
+        coder = Coder.create(self.GPT35, None, io=io)
         coder.commands.scraper = MagicMock()
         coder.commands.scraper.scrape = MagicMock(return_value="some content")
 

tests/basic/test_commands.py

@@ -10,7 +10,7 @@ from unittest import TestCase, mock
 import git
 
 from aider.coders import Coder
-from aider.commands import Commands
+from aider.commands import Commands, SwitchCoder
 from aider.dump import dump  # noqa: F401
 from aider.io import InputOutput
 from aider.models import Model
@@ -537,6 +537,62 @@ class TestCommands(TestCase):
         commands.cmd_add("file.txt")
         self.assertEqual(coder.abs_fnames, set())
 
+    def test_cmd_add_read_only_file(self):
+        with GitTemporaryDirectory():
+            # Initialize the Commands and InputOutput objects
+            io = InputOutput(pretty=False, yes=True)
+            from aider.coders import Coder
+
+            coder = Coder.create(self.GPT35, None, io)
+            commands = Commands(io, coder)
+
+            # Create a test file
+            test_file = Path("test_read_only.txt")
+            test_file.write_text("Test content")
+
+            # Add the file as read-only
+            commands.cmd_read(str(test_file))
+
+            # Verify it's in abs_read_only_fnames
+            self.assertTrue(
+                any(
+                    os.path.samefile(str(test_file.resolve()), fname)
+                    for fname in coder.abs_read_only_fnames
+                )
+            )
+
+            # Try to add the read-only file
+            commands.cmd_add(str(test_file))
+
+            # It's not in the repo, should not do anything
+            self.assertFalse(
+                any(os.path.samefile(str(test_file.resolve()), fname) for fname in coder.abs_fnames)
+            )
+            self.assertTrue(
+                any(
+                    os.path.samefile(str(test_file.resolve()), fname)
+                    for fname in coder.abs_read_only_fnames
+                )
+            )
+
+            repo = git.Repo()
+            repo.git.add(str(test_file))
+            repo.git.commit("-m", "initial")
+
+            # Try to add the read-only file
+            commands.cmd_add(str(test_file))
+
+            # Verify it's now in abs_fnames and not in abs_read_only_fnames
+            self.assertTrue(
+                any(os.path.samefile(str(test_file.resolve()), fname) for fname in coder.abs_fnames)
+            )
+            self.assertFalse(
+                any(
+                    os.path.samefile(str(test_file.resolve()), fname)
+                    for fname in coder.abs_read_only_fnames
+                )
+            )
+
     def test_cmd_test_unbound_local_error(self):
         with ChdirTemporaryDirectory():
             io = InputOutput(pretty=False, yes=False)
@@ -731,6 +787,140 @@ class TestCommands(TestCase):
             self.assertNotIn(fname2, str(coder.abs_fnames))
             self.assertNotIn(fname3, str(coder.abs_fnames))
 
+    def test_cmd_read(self):
+        with GitTemporaryDirectory():
+            io = InputOutput(pretty=False, yes=False)
+            coder = Coder.create(self.GPT35, None, io)
+            commands = Commands(io, coder)
+
+            # Create a test file
+            test_file = Path("test_read.txt")
+            test_file.write_text("Test content")
+
+            # Test the /read command
+            commands.cmd_read(str(test_file))
+
+            # Check if the file was added to abs_read_only_fnames
+            self.assertTrue(
+                any(
+                    os.path.samefile(str(test_file.resolve()), fname)
+                    for fname in coder.abs_read_only_fnames
+                )
+            )
+
+            # Test dropping the read-only file
+            commands.cmd_drop(str(test_file))
+
+            # Check if the file was removed from abs_read_only_fnames
+            self.assertFalse(
+                any(
+                    os.path.samefile(str(test_file.resolve()), fname)
+                    for fname in coder.abs_read_only_fnames
+                )
+            )
+
+    def test_cmd_read_with_external_file(self):
+        with tempfile.NamedTemporaryFile(mode="w", delete=False) as external_file:
+            external_file.write("External file content")
+            external_file_path = external_file.name
+
+        try:
+            with GitTemporaryDirectory():
+                io = InputOutput(pretty=False, yes=False)
+                coder = Coder.create(self.GPT35, None, io)
+                commands = Commands(io, coder)
+
+                # Test the /read command with an external file
+                commands.cmd_read(external_file_path)
+
+                # Check if the external file was added to abs_read_only_fnames
+                real_external_file_path = os.path.realpath(external_file_path)
+                self.assertTrue(
+                    any(
+                        os.path.samefile(real_external_file_path, fname)
+                        for fname in coder.abs_read_only_fnames
+                    )
+                )
+
+                # Test dropping the external read-only file
+                commands.cmd_drop(Path(external_file_path).name)
+
+                # Check if the file was removed from abs_read_only_fnames
+                self.assertFalse(
+                    any(
+                        os.path.samefile(real_external_file_path, fname)
+                        for fname in coder.abs_read_only_fnames
+                    )
+                )
+        finally:
+            os.unlink(external_file_path)
+
+    def test_cmd_diff(self):
+        with GitTemporaryDirectory() as repo_dir:
+            repo = git.Repo(repo_dir)
+            io = InputOutput(pretty=False, yes=True)
+            coder = Coder.create(self.GPT35, None, io)
+            commands = Commands(io, coder)
+
+            # Create and commit a file
+            filename = "test_file.txt"
+            file_path = Path(repo_dir) / filename
+            file_path.write_text("Initial content\n")
+            repo.git.add(filename)
+            repo.git.commit("-m", "Initial commit\n")
+
+            # Modify the file to make it dirty
+            file_path.write_text("Modified content")
+
+            # Mock repo.get_commit_message to return a canned commit message
+            with mock.patch.object(
+                coder.repo, "get_commit_message", return_value="Canned commit message"
+            ):
+                # Run cmd_commit
+                commands.cmd_commit()
+
+                # Capture the output of cmd_diff
+                with mock.patch("builtins.print") as mock_print:
+                    commands.cmd_diff("")
+
+                # Check if the diff output is correct
+                mock_print.assert_called_with(mock.ANY)
+                diff_output = mock_print.call_args[0][0]
+                self.assertIn("-Initial content", diff_output)
+                self.assertIn("+Modified content", diff_output)
+
+                # Modify the file again
+                file_path.write_text("Further modified content")
+
+                # Run cmd_commit again
+                commands.cmd_commit()
+
+                # Capture the output of cmd_diff
+                with mock.patch("builtins.print") as mock_print:
+                    commands.cmd_diff("")
+
+                # Check if the diff output is correct
+                mock_print.assert_called_with(mock.ANY)
+                diff_output = mock_print.call_args[0][0]
+                self.assertIn("-Modified content", diff_output)
+                self.assertIn("+Further modified content", diff_output)
+
+                # Modify the file a third time
+                file_path.write_text("Final modified content")
+
+                # Run cmd_commit again
+                commands.cmd_commit()
+
+                # Capture the output of cmd_diff
+                with mock.patch("builtins.print") as mock_print:
+                    commands.cmd_diff("")
+
+                # Check if the diff output is correct
+                mock_print.assert_called_with(mock.ANY)
+                diff_output = mock_print.call_args[0][0]
+                self.assertIn("-Further modified content", diff_output)
+                self.assertIn("+Final modified content", diff_output)
+
     def test_cmd_ask(self):
         io = InputOutput(pretty=False, yes=True)
         coder = Coder.create(self.GPT35, None, io)
@@ -742,17 +932,12 @@ class TestCommands(TestCase):
         with mock.patch("aider.coders.Coder.run") as mock_run:
             mock_run.return_value = canned_reply
 
-            commands.cmd_ask(question)
+            with self.assertRaises(SwitchCoder):
+                commands.cmd_ask(question)
 
             mock_run.assert_called_once()
             mock_run.assert_called_once_with(question)
 
-            self.assertEqual(len(coder.cur_messages), 2)
-            self.assertEqual(coder.cur_messages[0]["role"], "user")
-            self.assertEqual(coder.cur_messages[0]["content"], question)
-            self.assertEqual(coder.cur_messages[1]["role"], "assistant")
-            self.assertEqual(coder.cur_messages[1]["content"], canned_reply)
-
     def test_cmd_lint_with_dirty_file(self):
         with GitTemporaryDirectory() as repo_dir:
             repo = git.Repo(repo_dir)

tests/basic/test_editblock.py

@@ -297,7 +297,7 @@ These changes replace the `subprocess.run` patches with `subprocess.check_output
         files = [file1]
 
         # Initialize the Coder object with the mocked IO and mocked repo
-        coder = Coder.create(self.GPT35, "diff", io=InputOutput(), fnames=files, pretty=False)
+        coder = Coder.create(self.GPT35, "diff", io=InputOutput(), fnames=files)
 
         def mock_send(*args, **kwargs):
             coder.partial_response_content = f"""
@@ -340,7 +340,6 @@ new
             io=InputOutput(dry_run=True),
             fnames=files,
             dry_run=True,
-            pretty=False,
         )
 
         def mock_send(*args, **kwargs):

tests/basic/test_main.py

@@ -149,17 +149,6 @@ class TestMain(TestCase):
             _, kwargs = MockCoder.call_args
             assert kwargs["dirty_commits"] is True
             assert kwargs["auto_commits"] is True
-            assert kwargs["pretty"] is True
-
-        with patch("aider.coders.Coder.create") as MockCoder:
-            main(["--no-pretty"], input=DummyInput())
-            _, kwargs = MockCoder.call_args
-            assert kwargs["pretty"] is False
-
-        with patch("aider.coders.Coder.create") as MockCoder:
-            main(["--pretty"], input=DummyInput())
-            _, kwargs = MockCoder.call_args
-            assert kwargs["pretty"] is True
 
         with patch("aider.coders.Coder.create") as MockCoder:
             main(["--no-dirty-commits"], input=DummyInput())
@@ -235,6 +224,15 @@ class TestMain(TestCase):
 
                     main(["--yes", fname, "--encoding", "iso-8859-15"])
 
+    def test_main_exit_calls_version_check(self):
+        with GitTemporaryDirectory():
+            with patch("aider.main.check_version") as mock_check_version, patch(
+                "aider.main.InputOutput"
+            ) as mock_input_output:
+                main(["--exit"], input=DummyInput(), output=DummyOutput())
+                mock_check_version.assert_called_once()
+                mock_input_output.assert_called_once()
+
     @patch("aider.main.InputOutput")
     @patch("aider.coders.base_coder.Coder.run")
     def test_main_message_adds_to_input_history(self, mock_run, MockInputOutput):
@@ -396,3 +394,36 @@ class TestMain(TestCase):
                     output=DummyOutput(),
                 )
                 MockRepoMap.assert_called_once()
+
+    def test_read_option(self):
+        with GitTemporaryDirectory():
+            test_file = "test_file.txt"
+            Path(test_file).touch()
+
+            coder = main(
+                ["--read", test_file, "--exit", "--yes"],
+                input=DummyInput(),
+                output=DummyOutput(),
+                return_coder=True,
+            )
+
+            self.assertIn(str(Path(test_file).resolve()), coder.abs_read_only_fnames)
+
+    def test_read_option_with_external_file(self):
+        with tempfile.NamedTemporaryFile(mode="w", delete=False) as external_file:
+            external_file.write("External file content")
+            external_file_path = external_file.name
+
+        try:
+            with GitTemporaryDirectory():
+                coder = main(
+                    ["--read", external_file_path, "--exit", "--yes"],
+                    input=DummyInput(),
+                    output=DummyOutput(),
+                    return_coder=True,
+                )
+
+                real_external_file_path = os.path.realpath(external_file_path)
+                self.assertIn(real_external_file_path, coder.abs_read_only_fnames)
+        finally:
+            os.unlink(external_file_path)

tests/basic/test_sendchat.py

@@ -4,7 +4,7 @@ from unittest.mock import MagicMock, patch
 import httpx
 
 from aider.llm import litellm
-from aider.sendchat import send_with_retries
+from aider.sendchat import simple_send_with_retries
 
 
 class PrintCalled(Exception):
@@ -14,7 +14,7 @@ class PrintCalled(Exception):
 class TestSendChat(unittest.TestCase):
     @patch("litellm.completion")
     @patch("builtins.print")
-    def test_send_with_retries_rate_limit_error(self, mock_print, mock_completion):
+    def test_simple_send_with_retries_rate_limit_error(self, mock_print, mock_completion):
         mock = MagicMock()
         mock.status_code = 500
 
@@ -29,19 +29,19 @@ class TestSendChat(unittest.TestCase):
             None,
         ]
 
-        # Call the send_with_retries method
-        send_with_retries("model", ["message"], None, False)
+        # Call the simple_send_with_retries method
+        simple_send_with_retries("model", ["message"])
         mock_print.assert_called_once()
 
     @patch("litellm.completion")
     @patch("builtins.print")
-    def test_send_with_retries_connection_error(self, mock_print, mock_completion):
+    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,
         ]
 
-        # Call the send_with_retries method
-        send_with_retries("model", ["message"], None, False)
+        # Call the simple_send_with_retries method
+        simple_send_with_retries("model", ["message"])
         mock_print.assert_called_once()

tests/basic/test_wholefile.py

@@ -288,9 +288,7 @@ after b
         files = [file1]
 
         # Initialize the Coder object with the mocked IO and mocked repo
-        coder = Coder.create(
-            self.GPT35, "whole", io=InputOutput(), fnames=files, stream=False, pretty=False
-        )
+        coder = Coder.create(self.GPT35, "whole", io=InputOutput(), fnames=files, stream=False)
 
         # no trailing newline so the response content below doesn't add ANOTHER newline
         new_content = "new\ntwo\nthree"

tests/help/test_help.py

@@ -22,7 +22,13 @@ class TestHelp(unittest.TestCase):
         help_coder_run = MagicMock(return_value="")
         aider.coders.HelpCoder.run = help_coder_run
 
-        commands.cmd_help("hi")
+        try:
+            commands.cmd_help("hi")
+        except aider.commands.SwitchCoder:
+            pass
+        else:
+            # If no exception was raised, fail the test
+            assert False, "SwitchCoder exception was not raised"
 
         help_coder_run.assert_called_once()
 

tests/scrape/test_scrape.py

@@ -35,7 +35,7 @@ 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", paginate=False)
 
         # Assert that the result contains some content
         self.assertIsNotNone(result)
@@ -100,7 +100,7 @@ class TestScrape(unittest.TestCase):
 
         # Mock the necessary objects and methods
         scraper.scrape_with_playwright = MagicMock()
-        scraper.scrape_with_playwright.return_value = None
+        scraper.scrape_with_playwright.return_value = (None, None)
 
         # Call the scrape method
         result = scraper.scrape("https://example.com")
@@ -113,6 +113,54 @@ class TestScrape(unittest.TestCase):
             "Failed to retrieve content from https://example.com"
         )
 
+        # Reset the mock
+        mock_print_error.reset_mock()
+
+        # Test with a different return value
+        scraper.scrape_with_playwright.return_value = ("Some content", "text/html")
+        result = scraper.scrape("https://example.com")
+
+        # Assert that the result is not None
+        self.assertIsNotNone(result)
+
+        # Assert that print_error was not called
+        mock_print_error.assert_not_called()
+
+    def test_scrape_text_plain(self):
+        # Create a Scraper instance
+        scraper = Scraper(print_error=MagicMock(), playwright_available=True)
+
+        # Mock the scrape_with_playwright method
+        plain_text = "This is plain text content."
+        scraper.scrape_with_playwright = MagicMock(return_value=(plain_text, "text/plain"))
+
+        # Call the scrape method
+        result = scraper.scrape("https://example.com")
+
+        # Assert that the result is the same as the input plain text
+        self.assertEqual(result, plain_text)
+
+    def test_scrape_text_html(self):
+        # Create a Scraper instance
+        scraper = Scraper(print_error=MagicMock(), playwright_available=True)
+
+        # Mock the scrape_with_playwright method
+        html_content = "<html><body><h1>Test</h1><p>This is HTML content.</p></body></html>"
+        scraper.scrape_with_playwright = MagicMock(return_value=(html_content, "text/html"))
+
+        # Mock the html_to_markdown method
+        expected_markdown = "# Test\n\nThis is HTML content."
+        scraper.html_to_markdown = MagicMock(return_value=expected_markdown)
+
+        # Call the scrape method
+        result = scraper.scrape("https://example.com")
+
+        # Assert that the result is the expected markdown
+        self.assertEqual(result, expected_markdown)
+
+        # Assert that html_to_markdown was called with the HTML content
+        scraper.html_to_markdown.assert_called_once_with(html_content)
+
 
 if __name__ == "__main__":
     unittest.main()