set version to 0.77.2.dev

Use a consistent clone url to help those who don't use ssh with GitHub.  This should not break for those who do.

HISTORY.md

@@ -1,5 +1,123 @@
 # Release history
 
+### main branch
+
+- Bumped dependencies to pickup litellm fix for Ollama.
+- Added support for `openrouter/google/gemma-3-27b-it` model.
+- Aider wrote 96% of the code in this release.
+
+### Aider v0.77.0
+
+- Big upgrade in [programming languages supported](https://aider.chat/docs/languages.html) by adopting [tree-sitter-language-pack](https://github.com/Goldziher/tree-sitter-language-pack/).
+  - 130 new languages with linter support.
+  - 20 new languages with repo-map support.
+- Added `/think-tokens` command to set thinking token budget with support for human-readable formats (8k, 10.5k, 0.5M).
+- Added `/reasoning-effort` command to control model reasoning level.
+- The `/think-tokens` and `/reasoning-effort` commands display current settings when called without arguments.
+- Display of thinking token budget and reasoning effort in model information.
+- Changed `--thinking-tokens` argument to accept string values with human-readable formats.
+- Added `--auto-accept-architect` flag (default: true) to automatically accept changes from architect coder format without confirmation.
+- Added support for `cohere_chat/command-a-03-2025` and `gemini/gemma-3-27b-it`
+- The bare `/drop` command now preserves original read-only files provided via args.read.
+- Fixed a bug where default model would be set by deprecated `--shortcut` switches even when already specified in the command line.
+- Improved AutoCompleter to require 3 characters for autocompletion to reduce noise.
+- Aider wrote 72% of the code in this release.
+
+### Aider v0.76.2
+
+- Fixed handling of JSONDecodeError when loading model cache file.
+- Fixed handling of GitCommandError when retrieving git user configuration.
+- Aider wrote 75% of the code in this release.
+
+### Aider v0.76.1
+
+- Added ignore_permission_denied option to file watcher to prevent errors when accessing restricted files, by Yutaka Matsubara.
+- Aider wrote 0% of the code in this release.
+
+### Aider v0.76.0
+
+- Improved support for thinking/reasoningmodels:
+  - Added `--thinking-tokens` CLI option to control token budget for models that support thinking.
+  - Display thinking/reasoning content from LLMs which return it.
+  - Enhanced handling of reasoning tags to better clean up model responses.
+  - Added deprecation warning for `remove_reasoning` setting, now replaced by `reasoning_tag`.
+- Aider will notify you when it's completed the last request and needs your input:
+  - Added [notifications when LLM responses are ready](https://aider.chat/docs/usage/notifications.html) with `--notifications` flag.
+  - Specify desktop notification command with `--notifications-command`.
+- Added support for QWQ 32B.
+- Switch to `tree-sitter-language-pack` for tree sitter support.
+- Improved error handling for EOF (Ctrl+D) in user input prompts.
+- Added helper function to ensure hex color values have a # prefix.
+- Fixed handling of Git errors when reading staged files.
+- Improved SSL verification control for model information requests.
+- Improved empty LLM response handling with clearer warning messages.
+- Fixed Git identity retrieval to respect global configuration, by Akira Komamura.
+- Offer to install dependencies for Bedrock and Vertex AI models.
+- Deprecated model shortcut args (like --4o, --opus) in favor of the --model flag.
+- Aider wrote 85% of the code in this release.
+
+### Aider v0.75.3
+
+- Support for V3 free on OpenRouter: `--model openrouter/deepseek/deepseek-chat:free`.
+
+### Aider v0.75.2
+
+- Added support for Claude 3.7 Sonnet models on OpenRouter, Bedrock and Vertex AI.
+- Updated default model to Claude 3.7 Sonnet on OpenRouter.
+- Added support for GPT-4.5-preview model.
+- Added support for Claude 3.7 Sonnet:beta on OpenRouter.
+- Fixed weak_model_name patterns to match main model name patterns for some models.
+
+### Aider v0.75.1
+
+- Added support for `openrouter/anthropic/claude-3.7-sonnet`
+
+### Aider v0.75.0
+
+- Basic support for Claude 3.7 Sonnet
+  - Use `--model sonnet` to use the new 3.7
+  - Thinking support coming soon.
+- Bugfix to `/editor` command.
+- Aider wrote 46% of the code in this release.
+
+### Aider v0.74.3
+
+- Downgrade streamlit dependency to avoid threading bug.
+- Added support for tree-sitter language pack.
+- Added openrouter/o3-mini-high model configuration.
+- Added build.gradle.kts to special files for Kotlin project support, by Lucas Shadler.
+
+### Aider v0.74.2
+
+- Prevent more than one cache warming thread from becoming active.
+- Fixed continuation prompt ". " for multiline input.
+- Added HCL (Terraform) syntax support, by Warren Krewenki.
+
+### Aider v0.74.1
+
+- Have o1 & o3-mini generate markdown by sending the magic "Formatting re-enabled." string.
+- Bugfix for multi-line inputs, which should not include the ". " continuation prompt.
+
+### Aider v0.74.0
+
+- Dynamically changes the Ollama context window to hold the current chat.
+- Better support for o3-mini, DeepSeek V3 & R1, o1-mini, o1 especially via third-party API providers.
+- Remove `<think>` tags from R1 responses for commit messages (and other weak model uses).
+- Can now specify `use_temperature: <float>` in model settings, not just true/false.
+- The full docker container now includes `boto3` for Bedrock.
+- Docker containers now set `HOME=/app` which is the normal project mount-point, to persist `~/.aider`.
+- Bugfix to prevent creating incorrect filenames like `python`, `php`, etc.
+- Bugfix for `--timeout`
+- Bugfix so that `/model` now correctly reports that the weak model is not changed.
+- Bugfix so that multi-line mode persists through ^C at confirmation prompts.
+- Watch files now fully ignores top-level directories named in ignore files, to reduce the chance of hitting OS watch limits. Helpful to ignore giant subtrees like `node_modules`.
+- Fast startup with more providers and when model metadata provided in local files.
+- Improved .gitignore handling:
+  - Honor ignores already in effect regardless of how they've been configured.
+  - Check for .env only when the file exists.
+- Yes/No prompts now accept All/Skip as alias for Y/N even when not processing a group of confirmations.
+- Aider wrote 77% of the code in this release.
+
 ### Aider v0.73.0
 
 - Full support for o3-mini: `aider --model o3-mini`
@@ -8,7 +126,7 @@
 - Added support for removing model-specific reasoning tags from responses with `remove_reasoning: tagname` model setting.
 - Auto-create parent directories when creating new files, by xqyz.
 - Support for R1 free on OpenRouter: `--model openrouter/deepseek/deepseek-r1:free`
-- Aider wrote 70% of the code in this release.
+- Aider wrote 69% of the code in this release.
 
 ### Aider v0.72.3
 

README.md

@@ -6,8 +6,7 @@
 Aider lets you pair program with LLMs,
 to edit code in your local git repository.
 Start a new project or work with an existing code base.
-Aider works best with Claude 3.5 Sonnet, DeepSeek V3, o1 & GPT-4o and can [connect to almost any LLM](https://aider.chat/docs/llms.html).
+Aider works best with Claude 3.7 Sonnet, DeepSeek R1 & Chat V3, OpenAI o1, o3-mini & GPT-4o. Aider can [connect to almost any LLM, including local models](https://aider.chat/docs/llms.html).
-
 
 <!-- SCREENCAST START -->
 <p align="center">
@@ -55,14 +54,14 @@ cd /to/your/project
 # Work with DeepSeek via DeepSeek's API
 aider --model deepseek --api-key deepseek=your-key-goes-here
 
-# Work with Claude 3.5 Sonnet via Anthropic's API
+# Work with Claude 3.7 Sonnet via Anthropic's API
 aider --model sonnet --api-key anthropic=your-key-goes-here
 
 # Work with GPT-4o via OpenAI's API
 aider --model gpt-4o --api-key openai=your-key-goes-here
 
 # Work with Sonnet via OpenRouter's API
-aider --model openrouter/anthropic/claude-3.5-sonnet --api-key openrouter=your-key-goes-here
+aider --model openrouter/anthropic/claude-3.7-sonnet --api-key openrouter=your-key-goes-here
 
 # Work with DeepSeek via OpenRouter's API
 aider --model openrouter/deepseek/deepseek-chat --api-key openrouter=your-key-goes-here
@@ -96,7 +95,7 @@ Pair program with AI.
 - [Add images to the chat](https://aider.chat/docs/usage/images-urls.html) (GPT-4o, Claude 3.5 Sonnet, etc).
 - [Add URLs to the chat](https://aider.chat/docs/usage/images-urls.html) and aider will read their content.
 - [Code with your voice](https://aider.chat/docs/usage/voice.html).
-- Aider works best with Claude 3.5 Sonnet, DeepSeek V3, o1 & GPT-4o and can [connect to almost any LLM](https://aider.chat/docs/llms.html).
+- Aider works best with Claude 3.7 Sonnet, DeepSeek V3, o1 & GPT-4o and can [connect to almost any LLM](https://aider.chat/docs/llms.html).
 
 
 ## Top tier performance

aider/__init__.py

@@ -1,6 +1,6 @@
 from packaging import version
 
-__version__ = "0.73.1.dev"
+__version__ = "0.77.2.dev"
 safe_version = __version__
 
 try:

aider/args.py

@@ -12,6 +12,7 @@ from aider.args_formatter import (
     MarkdownHelpFormatter,
     YamlHelpFormatter,
 )
+from aider.deprecated import add_deprecated_model_args
 
 from .dump import dump  # noqa: F401
 
@@ -38,98 +39,6 @@ def get_parser(default_config_files, git_root):
         default=None,
         help="Specify the model to use for the main chat",
     )
-    opus_model = "claude-3-opus-20240229"
-    group.add_argument(
-        "--opus",
-        action="store_const",
-        dest="model",
-        const=opus_model,
-        help=f"Use {opus_model} model for the main chat",
-    )
-    sonnet_model = "claude-3-5-sonnet-20241022"
-    group.add_argument(
-        "--sonnet",
-        action="store_const",
-        dest="model",
-        const=sonnet_model,
-        help=f"Use {sonnet_model} model for the main chat",
-    )
-    haiku_model = "claude-3-5-haiku-20241022"
-    group.add_argument(
-        "--haiku",
-        action="store_const",
-        dest="model",
-        const=haiku_model,
-        help=f"Use {haiku_model} model for the main chat",
-    )
-    gpt_4_model = "gpt-4-0613"
-    group.add_argument(
-        "--4",
-        "-4",
-        action="store_const",
-        dest="model",
-        const=gpt_4_model,
-        help=f"Use {gpt_4_model} model for the main chat",
-    )
-    gpt_4o_model = "gpt-4o"
-    group.add_argument(
-        "--4o",
-        action="store_const",
-        dest="model",
-        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",
-        action="store_const",
-        dest="model",
-        const=gpt_4_turbo_model,
-        help=f"Use {gpt_4_turbo_model} model for the main chat",
-    )
-    gpt_3_model_name = "gpt-3.5-turbo"
-    group.add_argument(
-        "--35turbo",
-        "--35-turbo",
-        "--3",
-        "-3",
-        action="store_const",
-        dest="model",
-        const=gpt_3_model_name,
-        help=f"Use {gpt_3_model_name} model for the main chat",
-    )
-    deepseek_model = "deepseek/deepseek-chat"
-    group.add_argument(
-        "--deepseek",
-        action="store_const",
-        dest="model",
-        const=deepseek_model,
-        help=f"Use {deepseek_model} model for the main chat",
-    )
-    o1_mini_model = "o1-mini"
-    group.add_argument(
-        "--o1-mini",
-        action="store_const",
-        dest="model",
-        const=o1_mini_model,
-        help=f"Use {o1_mini_model} model for the main chat",
-    )
-    o1_preview_model = "o1-preview"
-    group.add_argument(
-        "--o1-preview",
-        action="store_const",
-        dest="model",
-        const=o1_preview_model,
-        help=f"Use {o1_preview_model} model for the main chat",
-    )
 
     ##########
     group = parser.add_argument_group("API Keys and settings")
@@ -208,6 +117,11 @@ def get_parser(default_config_files, git_root):
         type=str,
         help="Set the reasoning_effort API parameter (default: not set)",
     )
+    group.add_argument(
+        "--thinking-tokens",
+        type=str,
+        help="Set the thinking token budget for models that support it (default: not set)",
+    )
     group.add_argument(
         "--verify-ssl",
         action=argparse.BooleanOptionalAction,
@@ -216,7 +130,7 @@ def get_parser(default_config_files, git_root):
     )
     group.add_argument(
         "--timeout",
-        type=int,
+        type=float,
         default=None,
         help="Timeout in seconds for API calls (default: None)",
     )
@@ -234,6 +148,12 @@ def get_parser(default_config_files, git_root):
         const="architect",
         help="Use architect edit format for the main chat",
     )
+    group.add_argument(
+        "--auto-accept-architect",
+        action=argparse.BooleanOptionalAction,
+        default=True,
+        help="Enable/disable automatic acceptance of architect changes (default: True)",
+    )
     group.add_argument(
         "--weak-model",
         metavar="WEAK_MODEL",
@@ -813,6 +733,24 @@ def get_parser(default_config_files, git_root):
         default=False,
         help="Enable/disable multi-line input mode with Meta-Enter to submit (default: False)",
     )
+    group.add_argument(
+        "--notifications",
+        action=argparse.BooleanOptionalAction,
+        default=False,
+        help=(
+            "Enable/disable terminal bell notifications when LLM responses are ready (default:"
+            " False)"
+        ),
+    )
+    group.add_argument(
+        "--notifications-command",
+        metavar="COMMAND",
+        default=None,
+        help=(
+            "Specify a command to run for notifications instead of the terminal bell. If not"
+            " specified, a default command for your OS may be used."
+        ),
+    )
     group.add_argument(
         "--detect-urls",
         action=argparse.BooleanOptionalAction,
@@ -824,6 +762,11 @@ def get_parser(default_config_files, git_root):
         help="Specify which editor to use for the /editor command",
     )
 
+    ##########
+    group = parser.add_argument_group("Deprecated model settings")
+    # Add deprecated model shortcut arguments
+    add_deprecated_model_args(parser, group)
+
     return parser
 
 

aider/args_formatter.py

@@ -148,11 +148,14 @@ class YamlHelpFormatter(argparse.HelpFormatter):
             parts.append(f"#{switch}: xxx")
             parts.append("## Specify multiple values like this:")
             parts.append(f"#{switch}:")
-            parts.append(f"#  - xxx")
+            parts.append("#  - xxx")
-            parts.append(f"#  - yyy")
+            parts.append("#  - yyy")
-            parts.append(f"#  - zzz")
+            parts.append("#  - zzz")
         else:
-            parts.append(f"#{switch}: xxx\n")
+            if switch.endswith("color"):
+                parts.append(f'#{switch}: "xxx"\n')
+            else:
+                parts.append(f"#{switch}: xxx\n")
 
         ###
         # parts.append(str(action))

aider/coders/architect_coder.py

@@ -6,6 +6,7 @@ from .base_coder import Coder
 class ArchitectCoder(AskCoder):
     edit_format = "architect"
     gpt_prompts = ArchitectPrompts()
+    auto_accept_architect = False
 
     def reply_completed(self):
         content = self.partial_response_content
@@ -13,7 +14,7 @@ class ArchitectCoder(AskCoder):
         if not content or not content.strip():
             return
 
-        if not self.io.confirm_ask("Edit the files?"):
+        if not self.auto_accept_architect and not self.io.confirm_ask("Edit the files?"):
             return
 
         kwargs = dict()

aider/coders/base_coder.py

@@ -27,10 +27,16 @@ from aider.history import ChatSummary
 from aider.io import ConfirmGroup, InputOutput
 from aider.linter import Linter
 from aider.llm import litellm
+from aider.models import RETRY_TIMEOUT
+from aider.reasoning_tags import (
+    REASONING_TAG,
+    format_reasoning_content,
+    remove_reasoning_content,
+    replace_reasoning_tags,
+)
 from aider.repo import ANY_GIT_ERROR, GitRepo
 from aider.repomap import RepoMap
 from aider.run_cmd import run_cmd
-from aider.sendchat import RETRY_TIMEOUT, send_completion
 from aider.utils import format_content, format_messages, format_tokens, is_image_file
 
 from ..dump import dump  # noqa: F401
@@ -60,7 +66,7 @@ def wrap_fence(name):
 
 all_fences = [
     ("`" * 3, "`" * 3),
-    ("`" * 4, "`" * 4),
+    ("`" * 4, "`" * 4),  # LLMs ignore and revert to triple-backtick, causing #2879
     wrap_fence("source"),
     wrap_fence("code"),
     wrap_fence("pre"),
@@ -85,7 +91,7 @@ class Coder:
     max_reflections = 3
     edit_format = None
     yield_stream = False
-    temperature = 0
+    temperature = None
     auto_lint = True
     auto_test = False
     test_cmd = None
@@ -144,7 +150,13 @@ class Coder:
             # the system prompt.
             done_messages = from_coder.done_messages
             if edit_format != from_coder.edit_format and done_messages and summarize_from_coder:
-                done_messages = from_coder.summarizer.summarize_all(done_messages)
+                try:
+                    done_messages = from_coder.summarizer.summarize_all(done_messages)
+                except ValueError:
+                    # If summarization fails, keep the original messages and warn the user
+                    io.tool_warning(
+                        "Chat history summarization failed, continuing with full history"
+                    )
 
             # Bring along context from the old Coder
             update = dict(
@@ -162,6 +174,7 @@ class Coder:
             use_kwargs.update(kwargs)  # override passed kwargs
 
             kwargs = use_kwargs
+            from_coder.ok_to_warm_cache = False
 
         for coder in coders.__all__:
             if hasattr(coder, "edit_format") and coder.edit_format == edit_format:
@@ -194,10 +207,22 @@ class Coder:
             prefix = "Model"
 
         output = f"{prefix}: {main_model.name} with {self.edit_format} edit format"
+
+        # Check for thinking token budget
+        thinking_tokens = main_model.get_thinking_tokens(main_model)
+        if thinking_tokens:
+            output += f", {thinking_tokens} think tokens"
+
+        # Check for reasoning effort
+        reasoning_effort = main_model.get_reasoning_effort(main_model)
+        if reasoning_effort:
+            output += f", reasoning {reasoning_effort}"
+
         if self.add_cache_headers or main_model.caches_by_default:
             output += ", prompt cache"
         if main_model.info.get("supports_assistant_prefill"):
             output += ", infinite output"
+
         lines.append(output)
 
         if self.edit_format == "architect":
@@ -258,6 +283,8 @@ class Coder:
 
         return lines
 
+    ok_to_warm_cache = False
+
     def __init__(
         self,
         main_model,
@@ -295,6 +322,7 @@ class Coder:
         ignore_mentions=None,
         file_watcher=None,
         auto_copy_context=False,
+        auto_accept_architect=True,
     ):
         # Fill in a dummy Analytics if needed, but it is never .enable()'d
         self.analytics = analytics if analytics is not None else Analytics()
@@ -307,6 +335,7 @@ class Coder:
         self.abs_root_path_cache = {}
 
         self.auto_copy_context = auto_copy_context
+        self.auto_accept_architect = auto_accept_architect
 
         self.ignore_mentions = ignore_mentions
         if not self.ignore_mentions:
@@ -366,6 +395,10 @@ class Coder:
         self.pretty = self.io.pretty
 
         self.main_model = main_model
+        # Set the reasoning tag name based on model settings or default
+        self.reasoning_tag_name = (
+            self.main_model.reasoning_tag if self.main_model.reasoning_tag else REASONING_TAG
+        )
 
         self.stream = stream and main_model.streaming
 
@@ -1055,14 +1088,26 @@ class Coder:
         else:
             language = "the same language they are using"
 
+        if self.fence[0] == "`" * 4:
+            quad_backtick_reminder = (
+                "\nIMPORTANT: Use *quadruple* backticks ```` as fences, not triple backticks!\n"
+            )
+        else:
+            quad_backtick_reminder = ""
+
         prompt = prompt.format(
             fence=self.fence,
+            quad_backtick_reminder=quad_backtick_reminder,
             lazy_prompt=lazy_prompt,
             platform=platform_text,
             shell_cmd_prompt=shell_cmd_prompt,
             shell_cmd_reminder=shell_cmd_reminder,
             language=language,
         )
+
+        if self.main_model.system_prompt_prefix:
+            prompt = self.main_model.system_prompt_prefix + prompt
+
         return prompt
 
     def format_chat_chunks(self):
@@ -1182,8 +1227,11 @@ class Coder:
             return
         if not self.num_cache_warming_pings:
             return
+        if not self.ok_to_warm_cache:
+            return
 
         delay = 5 * 60 - 5
+        delay = float(os.environ.get("AIDER_CACHE_KEEPALIVE_DELAY", delay))
         self.next_cache_warm = time.time() + delay
         self.warming_pings_left = self.num_cache_warming_pings
         self.cache_warming_chunks = chunks
@@ -1192,7 +1240,7 @@ class Coder:
             return
 
         def warm_cache_worker():
-            while True:
+            while self.ok_to_warm_cache:
                 time.sleep(1)
                 if self.warming_pings_left <= 0:
                     continue
@@ -1235,8 +1283,6 @@ class Coder:
         input_tokens = self.main_model.token_count(messages)
         max_input_tokens = self.main_model.info.get("max_input_tokens") or 0
 
-        proceed = None
-
         if max_input_tokens and input_tokens >= max_input_tokens:
             self.io.tool_error(
                 f"Your estimated chat context of {input_tokens:,} tokens exceeds the"
@@ -1246,31 +1292,21 @@ class Coder:
             self.io.tool_output("- Use /drop to remove unneeded files from the chat")
             self.io.tool_output("- Use /clear to clear the chat history")
             self.io.tool_output("- Break your code into smaller files")
-            proceed = "Y"
             self.io.tool_output(
                 "It's probably safe to try and send the request, most providers won't charge if"
                 " the context limit is exceeded."
             )
 
-        # Special warning for Ollama models about context window size
+            if not self.io.confirm_ask("Try to proceed anyway?"):
-        if self.main_model.name.startswith(("ollama/", "ollama_chat/")):
+                return False
-            extra_params = getattr(self.main_model, "extra_params", None) or {}
-            num_ctx = extra_params.get("num_ctx", 2048)
-            if input_tokens > num_ctx:
-                proceed = "N"
-                self.io.tool_warning(f"""
-Your Ollama model is configured with num_ctx={num_ctx} tokens of context window.
-You are attempting to send {input_tokens} tokens.
-See https://aider.chat/docs/llms/ollama.html#setting-the-context-window-size
-""".strip())  # noqa
-
-        if proceed and not self.io.confirm_ask("Try to proceed anyway?", default=proceed):
-            return False
         return True
 
     def send_message(self, inp):
         self.event("message_send_starting")
 
+        # Notify IO that LLM processing is starting
+        self.io.llm_started()
+
         self.cur_messages += [
             dict(role="user", content=inp),
         ]
@@ -1339,7 +1375,7 @@ See https://aider.chat/docs/llms/ollama.html#setting-the-context-window-size
                         exhausted = True
                         break
 
-                    self.multi_response_content = self.get_multi_response_content()
+                    self.multi_response_content = self.get_multi_response_content_in_progress()
 
                     if messages[-1]["role"] == "assistant":
                         messages[-1]["content"] = self.multi_response_content
@@ -1359,9 +1395,15 @@ See https://aider.chat/docs/llms/ollama.html#setting-the-context-window-size
                 self.live_incremental_response(True)
                 self.mdstream = None
 
-            self.partial_response_content = self.get_multi_response_content(True)
+            self.partial_response_content = self.get_multi_response_content_in_progress(True)
+            self.remove_reasoning_content()
             self.multi_response_content = ""
 
+        ###
+        # print()
+        # print("=" * 20)
+        # dump(self.partial_response_content)
+
         self.io.tool_output()
 
         self.show_usage_report()
@@ -1529,6 +1571,10 @@ See https://aider.chat/docs/llms/ollama.html#setting-the-context-window-size
 
         return res
 
+    def __del__(self):
+        """Cleanup when the Coder object is destroyed."""
+        self.ok_to_warm_cache = False
+
     def add_assistant_reply_to_cur_messages(self):
         if self.partial_response_content:
             self.cur_messages += [dict(role="assistant", content=self.partial_response_content)]
@@ -1595,7 +1641,9 @@ See https://aider.chat/docs/llms/ollama.html#setting-the-context-window-size
         added_fnames = []
         group = ConfirmGroup(new_mentions)
         for rel_fname in sorted(new_mentions):
-            if self.io.confirm_ask(f"Add {rel_fname} to the chat?", group=group, allow_never=True):
+            if self.io.confirm_ask(
+                "Add file to the chat?", subject=rel_fname, group=group, allow_never=True
+            ):
                 self.add_rel_fname(rel_fname)
                 added_fnames.append(rel_fname)
             else:
@@ -1605,6 +1653,9 @@ See https://aider.chat/docs/llms/ollama.html#setting-the-context-window-size
             return prompts.added_files.format(fnames=", ".join(added_fnames))
 
     def send(self, messages, model=None, functions=None):
+        self.got_reasoning_content = False
+        self.ended_reasoning_content = False
+
         if not model:
             model = self.main_model
 
@@ -1613,20 +1664,13 @@ See https://aider.chat/docs/llms/ollama.html#setting-the-context-window-size
 
         self.io.log_llm_history("TO LLM", format_messages(messages))
 
-        if self.main_model.use_temperature:
-            temp = self.temperature
-        else:
-            temp = None
-
         completion = None
         try:
-            hash_object, completion = send_completion(
+            hash_object, completion = model.send_completion(
-                model.name,
                 messages,
                 functions,
                 self.stream,
-                temp,
+                self.temperature,
-                extra_params=model.extra_params,
             )
             self.chat_completion_call_hashes.append(hash_object.hexdigest())
 
@@ -1679,6 +1723,14 @@ See https://aider.chat/docs/llms/ollama.html#setting-the-context-window-size
         except AttributeError as func_err:
             show_func_err = func_err
 
+        try:
+            reasoning_content = completion.choices[0].message.reasoning_content
+        except AttributeError:
+            try:
+                reasoning_content = completion.choices[0].message.reasoning
+            except AttributeError:
+                reasoning_content = None
+
         try:
             self.partial_response_content = completion.choices[0].message.content or ""
         except AttributeError as content_err:
@@ -1697,6 +1749,15 @@ See https://aider.chat/docs/llms/ollama.html#setting-the-context-window-size
             raise Exception("No data found in LLM response!")
 
         show_resp = self.render_incremental_response(True)
+
+        if reasoning_content:
+            formatted_reasoning = format_reasoning_content(
+                reasoning_content, self.reasoning_tag_name
+            )
+            show_resp = formatted_reasoning + show_resp
+
+        show_resp = replace_reasoning_tags(show_resp, self.reasoning_tag_name)
+
         self.io.assistant_output(show_resp, pretty=self.show_pretty())
 
         if (
@@ -1706,6 +1767,8 @@ See https://aider.chat/docs/llms/ollama.html#setting-the-context-window-size
             raise FinishReasonLength()
 
     def show_send_output_stream(self, completion):
+        received_content = False
+
         for chunk in completion:
             if len(chunk.choices) == 0:
                 continue
@@ -1724,19 +1787,46 @@ See https://aider.chat/docs/llms/ollama.html#setting-the-context-window-size
                         self.partial_response_function_call[k] += v
                     else:
                         self.partial_response_function_call[k] = v
+                received_content = True
             except AttributeError:
                 pass
 
+            text = ""
+
             try:
-                text = chunk.choices[0].delta.content
+                reasoning_content = chunk.choices[0].delta.reasoning_content
-                if text:
-                    self.partial_response_content += text
             except AttributeError:
-                text = None
+                try:
+                    reasoning_content = chunk.choices[0].delta.reasoning
+                except AttributeError:
+                    reasoning_content = None
+
+            if reasoning_content:
+                if not self.got_reasoning_content:
+                    text += f"<{REASONING_TAG}>\n\n"
+                text += reasoning_content
+                self.got_reasoning_content = True
+                received_content = True
+
+            try:
+                content = chunk.choices[0].delta.content
+                if content:
+                    if self.got_reasoning_content and not self.ended_reasoning_content:
+                        text += f"\n\n</{self.reasoning_tag_name}>\n\n"
+                        self.ended_reasoning_content = True
+
+                    text += content
+                    received_content = True
+            except AttributeError:
+                pass
+
+            self.partial_response_content += text
 
             if self.show_pretty():
                 self.live_incremental_response(False)
             elif text:
+                # Apply reasoning tag formatting
+                text = replace_reasoning_tags(text, self.reasoning_tag_name)
                 try:
                     sys.stdout.write(text)
                 except UnicodeEncodeError:
@@ -1748,12 +1838,25 @@ See https://aider.chat/docs/llms/ollama.html#setting-the-context-window-size
                 sys.stdout.flush()
                 yield text
 
+        if not received_content:
+            self.io.tool_warning("Empty response received from LLM. Check your provider account?")
+
     def live_incremental_response(self, final):
         show_resp = self.render_incremental_response(final)
+        # Apply any reasoning tag formatting
+        show_resp = replace_reasoning_tags(show_resp, self.reasoning_tag_name)
         self.mdstream.update(show_resp, final=final)
 
     def render_incremental_response(self, final):
-        return self.get_multi_response_content()
+        return self.get_multi_response_content_in_progress()
+
+    def remove_reasoning_content(self):
+        """Remove reasoning content from the model's response."""
+
+        self.partial_response_content = remove_reasoning_content(
+            self.partial_response_content,
+            self.reasoning_tag_name,
+        )
 
     def calculate_and_show_tokens_and_cost(self, messages, completion=None):
         prompt_tokens = 0
@@ -1876,22 +1979,14 @@ See https://aider.chat/docs/llms/ollama.html#setting-the-context-window-size
         self.message_tokens_sent = 0
         self.message_tokens_received = 0
 
-    def get_multi_response_content(self, final=False):
+    def get_multi_response_content_in_progress(self, final=False):
         cur = self.multi_response_content or ""
         new = self.partial_response_content or ""
 
         if new.rstrip() != new and not final:
             new = new.rstrip()
 
-        res = cur + new
+        return cur + new
-
-        if self.main_model.remove_reasoning:
-            pattern = (
-                f"<{self.main_model.remove_reasoning}>.*?</{self.main_model.remove_reasoning}>"
-            )
-            res = re.sub(pattern, "", res, flags=re.DOTALL).strip()
-
-        return res
 
     def get_rel_fname(self, fname):
         try:

aider/coders/editblock_coder.py

@@ -401,6 +401,9 @@ missing_filename_err = (
     " {fence[0]}"
 )
 
+# Always be willing to treat triple-backticks as a fence when searching for filenames
+triple_backticks = "`" * 3
+
 
 def strip_filename(filename, fence):
     filename = filename.strip()
@@ -409,7 +412,7 @@ def strip_filename(filename, fence):
         return
 
     start_fence = fence[0]
-    if filename.startswith(start_fence):
+    if filename.startswith(start_fence) or filename.startswith(triple_backticks):
         return
 
     filename = filename.rstrip(":")
@@ -546,7 +549,7 @@ def find_filename(lines, fence, valid_fnames):
             filenames.append(filename)
 
         # Only continue as long as we keep seeing fences
-        if not line.startswith(fence[0]):
+        if not line.startswith(fence[0]) and not line.startswith(triple_backticks):
             break
 
     if not filenames:

aider/coders/editblock_prompts.py

@@ -157,7 +157,7 @@ Every *SEARCH/REPLACE block* must use this format:
 8. The closing fence: {fence[1]}
 
 Use the *FULL* file path, as shown to you by the user.
-
+{quad_backtick_reminder}
 Every *SEARCH* section must *EXACTLY MATCH* the existing file content, character for character, including all comments, docstrings, etc.
 If the file contains code or other data wrapped/escaped in json/xml/quotes or other containers, you need to propose edits to the literal contents of the file, including the container markup.
 

aider/coders/wholefile_coder.py

@@ -17,10 +17,10 @@ class WholeFileCoder(Coder):
         try:
             return self.get_edits(mode="diff")
         except ValueError:
-            return self.get_multi_response_content()
+            return self.get_multi_response_content_in_progress()
 
     def get_edits(self, mode="update"):
-        content = self.get_multi_response_content()
+        content = self.get_multi_response_content_in_progress()
 
         chat_files = self.get_inchat_relative_files()
 

aider/commands.py

@@ -59,6 +59,7 @@ class Commands:
         parser=None,
         verbose=False,
         editor=None,
+        original_read_only_fnames=None,
     ):
         self.io = io
         self.coder = coder
@@ -77,11 +78,14 @@ class Commands:
         self.help = None
         self.editor = editor
 
+        # Store the original read-only filenames provided via args.read
+        self.original_read_only_fnames = set(original_read_only_fnames or [])
+
     def cmd_model(self, args):
         "Switch to a new LLM"
 
         model_name = args.strip()
-        model = models.Model(model_name)
+        model = models.Model(model_name, weak_model=self.coder.main_model.weak_model.name)
         models.sanity_check_models(self.io, model)
         raise SwitchCoder(main_model=model)
 
@@ -355,7 +359,21 @@ class Commands:
 
     def _drop_all_files(self):
         self.coder.abs_fnames = set()
-        self.coder.abs_read_only_fnames = set()
+
+        # When dropping all files, keep those that were originally provided via args.read
+        if self.original_read_only_fnames:
+            # Keep only the original read-only files
+            to_keep = set()
+            for abs_fname in self.coder.abs_read_only_fnames:
+                rel_fname = self.coder.get_rel_fname(abs_fname)
+                if (
+                    abs_fname in self.original_read_only_fnames
+                    or rel_fname in self.original_read_only_fnames
+                ):
+                    to_keep.add(abs_fname)
+            self.coder.abs_read_only_fnames = to_keep
+        else:
+            self.coder.abs_read_only_fnames = set()
 
     def _clear_chat_history(self):
         self.coder.done_messages = []
@@ -404,6 +422,7 @@ class Commands:
 
         fence = "`" * 3
 
+        file_res = []
         # files
         for fname in self.coder.abs_fnames:
             relative_fname = self.coder.get_rel_fname(fname)
@@ -414,7 +433,7 @@ class Commands:
                 # 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}", "/drop to remove"))
+            file_res.append((tokens, f"{relative_fname}", "/drop to remove"))
 
         # read-only files
         for fname in self.coder.abs_read_only_fnames:
@@ -424,7 +443,10 @@ class Commands:
                 # 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"))
+                file_res.append((tokens, f"{relative_fname} (read-only)", "/drop to remove"))
+
+        file_res.sort()
+        res.extend(file_res)
 
         self.io.tool_output(
             f"Approximate context window usage for {self.coder.main_model.name}, in tokens:"
@@ -818,7 +840,12 @@ class Commands:
         "Remove files from the chat session to free up context space"
 
         if not args.strip():
-            self.io.tool_output("Dropping all files from the chat session.")
+            if self.original_read_only_fnames:
+                self.io.tool_output(
+                    "Dropping all files from the chat session except originally read-only files."
+                )
+            else:
+                self.io.tool_output("Dropping all files from the chat session.")
             self._drop_all_files()
             return
 
@@ -1407,6 +1434,58 @@ class Commands:
         if user_input.strip():
             self.io.set_placeholder(user_input.rstrip())
 
+    def cmd_think_tokens(self, args):
+        "Set the thinking token budget (supports formats like 8096, 8k, 10.5k, 0.5M)"
+        model = self.coder.main_model
+
+        if not args.strip():
+            # Display current value if no args are provided
+            formatted_budget = model.get_thinking_tokens(model)
+            if formatted_budget is None:
+                self.io.tool_output("Thinking tokens are not currently set.")
+            else:
+                budget = model.extra_params["thinking"].get("budget_tokens")
+                self.io.tool_output(
+                    f"Current thinking token budget: {budget:,} tokens ({formatted_budget})."
+                )
+            return
+
+        value = args.strip()
+        model.set_thinking_tokens(value)
+
+        formatted_budget = model.get_thinking_tokens(model)
+        budget = model.extra_params["thinking"].get("budget_tokens")
+
+        self.io.tool_output(f"Set thinking token budget to {budget:,} tokens ({formatted_budget}).")
+        self.io.tool_output()
+
+        # Output announcements
+        announcements = "\n".join(self.coder.get_announcements())
+        self.io.tool_output(announcements)
+
+    def cmd_reasoning_effort(self, args):
+        "Set the reasoning effort level (values: number or low/medium/high depending on model)"
+        model = self.coder.main_model
+
+        if not args.strip():
+            # Display current value if no args are provided
+            reasoning_value = model.get_reasoning_effort(model)
+            if reasoning_value is None:
+                self.io.tool_output("Reasoning effort is not currently set.")
+            else:
+                self.io.tool_output(f"Current reasoning effort: {reasoning_value}")
+            return
+
+        value = args.strip()
+        model.set_reasoning_effort(value)
+        reasoning_value = model.get_reasoning_effort(model)
+        self.io.tool_output(f"Set reasoning effort to {reasoning_value}")
+        self.io.tool_output()
+
+        # Output announcements
+        announcements = "\n".join(self.coder.get_announcements())
+        self.io.tool_output(announcements)
+
     def cmd_copy_context(self, args=None):
         """Copy the current chat context as markdown, suitable to paste into a web UI"""
 

aider/deprecated.py

@@ -0,0 +1,126 @@
+def add_deprecated_model_args(parser, group):
+    """Add deprecated model shortcut arguments to the argparse parser."""
+    opus_model = "claude-3-opus-20240229"
+    group.add_argument(
+        "--opus",
+        action="store_true",
+        help=f"Use {opus_model} model for the main chat (deprecated, use --model)",
+        default=False,
+    )
+    sonnet_model = "anthropic/claude-3-7-sonnet-20250219"
+    group.add_argument(
+        "--sonnet",
+        action="store_true",
+        help=f"Use {sonnet_model} model for the main chat (deprecated, use --model)",
+        default=False,
+    )
+    haiku_model = "claude-3-5-haiku-20241022"
+    group.add_argument(
+        "--haiku",
+        action="store_true",
+        help=f"Use {haiku_model} model for the main chat (deprecated, use --model)",
+        default=False,
+    )
+    gpt_4_model = "gpt-4-0613"
+    group.add_argument(
+        "--4",
+        "-4",
+        action="store_true",
+        help=f"Use {gpt_4_model} model for the main chat (deprecated, use --model)",
+        default=False,
+    )
+    gpt_4o_model = "gpt-4o"
+    group.add_argument(
+        "--4o",
+        action="store_true",
+        help=f"Use {gpt_4o_model} model for the main chat (deprecated, use --model)",
+        default=False,
+    )
+    gpt_4o_mini_model = "gpt-4o-mini"
+    group.add_argument(
+        "--mini",
+        action="store_true",
+        help=f"Use {gpt_4o_mini_model} model for the main chat (deprecated, use --model)",
+        default=False,
+    )
+    gpt_4_turbo_model = "gpt-4-1106-preview"
+    group.add_argument(
+        "--4-turbo",
+        action="store_true",
+        help=f"Use {gpt_4_turbo_model} model for the main chat (deprecated, use --model)",
+        default=False,
+    )
+    gpt_3_model_name = "gpt-3.5-turbo"
+    group.add_argument(
+        "--35turbo",
+        "--35-turbo",
+        "--3",
+        "-3",
+        action="store_true",
+        help=f"Use {gpt_3_model_name} model for the main chat (deprecated, use --model)",
+        default=False,
+    )
+    deepseek_model = "deepseek/deepseek-chat"
+    group.add_argument(
+        "--deepseek",
+        action="store_true",
+        help=f"Use {deepseek_model} model for the main chat (deprecated, use --model)",
+        default=False,
+    )
+    o1_mini_model = "o1-mini"
+    group.add_argument(
+        "--o1-mini",
+        action="store_true",
+        help=f"Use {o1_mini_model} model for the main chat (deprecated, use --model)",
+        default=False,
+    )
+    o1_preview_model = "o1-preview"
+    group.add_argument(
+        "--o1-preview",
+        action="store_true",
+        help=f"Use {o1_preview_model} model for the main chat (deprecated, use --model)",
+        default=False,
+    )
+
+
+def handle_deprecated_model_args(args, io):
+    """Handle deprecated model shortcut arguments and provide appropriate warnings."""
+    # Define model mapping
+    model_map = {
+        "opus": "claude-3-opus-20240229",
+        "sonnet": "anthropic/claude-3-7-sonnet-20250219",
+        "haiku": "claude-3-5-haiku-20241022",
+        "4": "gpt-4-0613",
+        "4o": "gpt-4o",
+        "mini": "gpt-4o-mini",
+        "4_turbo": "gpt-4-1106-preview",
+        "35turbo": "gpt-3.5-turbo",
+        "deepseek": "deepseek/deepseek-chat",
+        "o1_mini": "o1-mini",
+        "o1_preview": "o1-preview",
+    }
+
+    # Check if any deprecated args are used
+    for arg_name, model_name in model_map.items():
+        arg_name_clean = arg_name.replace("-", "_")
+        if hasattr(args, arg_name_clean) and getattr(args, arg_name_clean):
+            # Find preferred name to display in warning
+            from aider.models import MODEL_ALIASES
+
+            display_name = model_name
+            # Check if there's a shorter alias for this model
+            for alias, full_name in MODEL_ALIASES.items():
+                if full_name == model_name:
+                    display_name = alias
+                    break
+
+            # Show the warning
+            io.tool_warning(
+                f"The --{arg_name.replace('_', '-')} flag is deprecated and will be removed in a"
+                f" future version. Please use --model {display_name} instead."
+            )
+
+            # Set the model
+            if not args.model:
+                args.model = model_name
+            break

aider/editor.py

@@ -10,12 +10,13 @@ This module provides functionality to:
 
 import os
 import platform
-import shlex
 import subprocess
 import tempfile
 
 from rich.console import Console
 
+from aider.dump import dump  # noqa
+
 DEFAULT_EDITOR_NIX = "vi"
 DEFAULT_EDITOR_OS_X = "vim"
 DEFAULT_EDITOR_WINDOWS = "notepad"
@@ -87,13 +88,13 @@ def get_environment_editor(default=None):
 
 def discover_editor(editor_override=None):
     """
-    Discovers and returns the appropriate editor command as a list of arguments.
+    Discovers and returns the appropriate editor command.
 
     Handles cases where the editor command includes arguments, including quoted arguments
     with spaces (e.g. 'vim -c "set noswapfile"').
 
-    :return: A list of command parts ready for subprocess execution
+    :return: The editor command as a string
-    :rtype: list[str]
+    :rtype: str
     """
     system = platform.system()
     if system == "Windows":
@@ -102,14 +103,13 @@ def discover_editor(editor_override=None):
         default_editor = DEFAULT_EDITOR_OS_X
     else:
         default_editor = DEFAULT_EDITOR_NIX
+
     if editor_override:
         editor = editor_override
     else:
         editor = get_environment_editor(default_editor)
-    try:
+
-        return shlex.split(editor)
+    return editor
-    except ValueError as e:
-        raise RuntimeError(f"Invalid editor command format '{editor}': {e}")
 
 
 def pipe_editor(input_data="", suffix=None, editor=None):
@@ -128,9 +128,10 @@ def pipe_editor(input_data="", suffix=None, editor=None):
     :rtype: str
     """
     filepath = write_temp_file(input_data, suffix)
-    command_parts = discover_editor(editor)
+    command_str = discover_editor(editor)
-    command_parts.append(filepath)
+    command_str += " " + filepath
-    subprocess.call(command_parts)
+
+    subprocess.call(command_str, shell=True)
     with open(filepath, "r") as f:
         output_data = f.read()
     try:

aider/exceptions.py

@@ -1,5 +1,7 @@
 from dataclasses import dataclass
 
+from aider.dump import dump  # noqa: F401
+
 
 @dataclass
 class ExInfo:
@@ -50,6 +52,7 @@ EXCEPTIONS = [
 
 class LiteLLMExceptions:
     exceptions = dict()
+    exception_info = {exi.name: exi for exi in EXCEPTIONS}
 
     def __init__(self):
         self._load()
@@ -58,20 +61,13 @@ class LiteLLMExceptions:
         import litellm
 
         for var in dir(litellm):
-            if not var.endswith("Error"):
+            if var.endswith("Error"):
-                continue
+                if var not in self.exception_info:
-
+                    raise ValueError(f"{var} is in litellm but not in aider's exceptions list")
-            ex_info = None
-            for exi in EXCEPTIONS:
-                if var == exi.name:
-                    ex_info = exi
-                    break
-
-            if strict and not ex_info:
-                raise ValueError(f"{var} is in litellm but not in aider's exceptions list")
 
+        for var in self.exception_info:
             ex = getattr(litellm, var)
-            self.exceptions[ex] = ex_info
+            self.exceptions[ex] = self.exception_info[var]
 
     def exceptions_tuple(self):
         return tuple(self.exceptions)

aider/help_pats.py

@@ -10,4 +10,10 @@ exclude_website_pats = [
     "docs/unified-diffs.md",
     "docs/leaderboards/index.md",
     "assets/**",
+    ".jekyll-metadata",
+    "Gemfile.lock",
+    "Gemfile",
+    "_config.yml",
+    "**/OLD/**",
+    "OLD/**",
 ]

aider/history.py

@@ -2,7 +2,6 @@ import argparse
 
 from aider import models, prompts
 from aider.dump import dump  # noqa: F401
-from aider.sendchat import simple_send_with_retries
 
 
 class ChatSummary:
@@ -114,7 +113,7 @@ class ChatSummary:
 
         for model in self.models:
             try:
-                summary = simple_send_with_retries(model, summarize_messages)
+                summary = model.simple_send_with_retries(summarize_messages)
                 if summary is not None:
                     summary = prompts.summary_prefix + summary
                     return [dict(role="user", content=summary)]

aider/io.py

@@ -1,6 +1,9 @@
 import base64
+import functools
 import os
+import shutil
 import signal
+import subprocess
 import time
 import webbrowser
 from collections import defaultdict
@@ -33,6 +36,37 @@ from aider.mdstream import MarkdownStream
 from .dump import dump  # noqa: F401
 from .utils import is_image_file
 
+# Constants
+NOTIFICATION_MESSAGE = "Aider is waiting for your input"
+
+
+def ensure_hash_prefix(color):
+    """Ensure hex color values have a # prefix."""
+    if not color:
+        return color
+    if isinstance(color, str) and color.strip() and not color.startswith("#"):
+        # Check if it's a valid hex color (3 or 6 hex digits)
+        if all(c in "0123456789ABCDEFabcdef" for c in color) and len(color) in (3, 6):
+            return f"#{color}"
+    return color
+
+
+def restore_multiline(func):
+    """Decorator to restore multiline mode after function execution"""
+
+    @functools.wraps(func)
+    def wrapper(self, *args, **kwargs):
+        orig_multiline = self.multiline_mode
+        self.multiline_mode = False
+        try:
+            return func(self, *args, **kwargs)
+        except Exception:
+            raise
+        finally:
+            self.multiline_mode = orig_multiline
+
+    return wrapper
+
 
 @dataclass
 class ConfirmGroup:
@@ -160,6 +194,11 @@ class AutoCompleter(Completer):
         candidates = [word if type(word) is tuple else (word, word) for word in candidates]
 
         last_word = words[-1]
+
+        # Only provide completions if the user has typed at least 3 characters
+        if len(last_word) < 3:
+            return
+
         completions = []
         for word_match, word_insert in candidates:
             if word_match.lower().startswith(last_word.lower()):
@@ -178,6 +217,8 @@ class InputOutput:
     num_error_outputs = 0
     num_user_asks = 0
     clipboard_watcher = None
+    bell_on_next_input = False
+    notifications_command = None
 
     def __init__(
         self,
@@ -206,25 +247,40 @@ class InputOutput:
         file_watcher=None,
         multiline_mode=False,
         root=".",
+        notifications=False,
+        notifications_command=None,
     ):
         self.placeholder = None
         self.interrupted = False
         self.never_prompts = set()
         self.editingmode = editingmode
         self.multiline_mode = multiline_mode
+        self.bell_on_next_input = False
+        self.notifications = notifications
+        if notifications and notifications_command is None:
+            self.notifications_command = self.get_default_notification_command()
+        else:
+            self.notifications_command = notifications_command
+
         no_color = os.environ.get("NO_COLOR")
         if no_color is not None and no_color != "":
             pretty = False
 
-        self.user_input_color = user_input_color if pretty else None
+        self.user_input_color = ensure_hash_prefix(user_input_color) if pretty else None
-        self.tool_output_color = tool_output_color if pretty else None
+        self.tool_output_color = ensure_hash_prefix(tool_output_color) if pretty else None
-        self.tool_error_color = tool_error_color if pretty else None
+        self.tool_error_color = ensure_hash_prefix(tool_error_color) if pretty else None
-        self.tool_warning_color = tool_warning_color if pretty else None
+        self.tool_warning_color = ensure_hash_prefix(tool_warning_color) if pretty else None
-        self.assistant_output_color = assistant_output_color
+        self.assistant_output_color = ensure_hash_prefix(assistant_output_color)
-        self.completion_menu_color = completion_menu_color if pretty else None
+        self.completion_menu_color = ensure_hash_prefix(completion_menu_color) if pretty else None
-        self.completion_menu_bg_color = completion_menu_bg_color if pretty else None
+        self.completion_menu_bg_color = (
-        self.completion_menu_current_color = completion_menu_current_color if pretty else None
+            ensure_hash_prefix(completion_menu_bg_color) if pretty else None
-        self.completion_menu_current_bg_color = completion_menu_current_bg_color if pretty else None
+        )
+        self.completion_menu_current_color = (
+            ensure_hash_prefix(completion_menu_current_color) if pretty else None
+        )
+        self.completion_menu_current_bg_color = (
+            ensure_hash_prefix(completion_menu_current_bg_color) if pretty else None
+        )
 
         self.code_theme = code_theme
 
@@ -426,6 +482,9 @@ class InputOutput:
     ):
         self.rule()
 
+        # Ring the bell if needed
+        self.ring_bell()
+
         rel_fnames = list(rel_fnames)
         show = ""
         if rel_fnames:
@@ -518,6 +577,9 @@ class InputOutput:
                         if self.clipboard_watcher:
                             self.clipboard_watcher.start()
 
+                    def get_continuation(width, line_number, is_soft_wrap):
+                        return ". "
+
                     line = self.prompt_session.prompt(
                         show,
                         default=default,
@@ -527,6 +589,7 @@ class InputOutput:
                         style=style,
                         key_bindings=kb,
                         complete_while_typing=True,
+                        prompt_continuation=get_continuation,
                     )
                 else:
                     line = input(show)
@@ -662,6 +725,7 @@ class InputOutput:
             return True
         return False
 
+    @restore_multiline
     def confirm_ask(
         self,
         question,
@@ -671,11 +735,11 @@ class InputOutput:
         group=None,
         allow_never=False,
     ):
-        # Temporarily disable multiline mode for yes/no prompts
-        orig_multiline = self.multiline_mode
-        self.multiline_mode = False
         self.num_user_asks += 1
 
+        # Ring the bell if needed
+        self.ring_bell()
+
         question_id = (question, subject)
 
         if question_id in self.never_prompts:
@@ -686,14 +750,12 @@ class InputOutput:
         if group:
             allow_never = True
 
-        valid_responses = ["yes", "no"]
+        valid_responses = ["yes", "no", "skip", "all"]
         options = " (Y)es/(N)o"
         if group:
             if not explicit_yes_required:
                 options += "/(A)ll"
-                valid_responses.append("all")
             options += "/(S)kip all"
-            valid_responses.append("skip")
         if allow_never:
             options += "/(D)on't ask again"
             valid_responses.append("don't")
@@ -732,14 +794,19 @@ class InputOutput:
             self.user_input(f"{question}{res}", log_only=False)
         else:
             while True:
-                if self.prompt_session:
+                try:
-                    res = self.prompt_session.prompt(
+                    if self.prompt_session:
-                        question,
+                        res = self.prompt_session.prompt(
-                        style=style,
+                            question,
-                        complete_while_typing=False,
+                            style=style,
-                    )
+                            complete_while_typing=False,
-                else:
+                        )
-                    res = input(question)
+                    else:
+                        res = input(question)
+                except EOFError:
+                    # Treat EOF (Ctrl+D) as if the user pressed Enter
+                    res = default
+                    break
 
                 if not res:
                     res = default
@@ -777,17 +844,15 @@ class InputOutput:
         hist = f"{question.strip()} {res}"
         self.append_chat_history(hist, linebreak=True, blockquote=True)
 
-        # Restore original multiline mode
-        self.multiline_mode = orig_multiline
-
         return is_yes
 
+    @restore_multiline
     def prompt_ask(self, question, default="", subject=None):
-        # Temporarily disable multiline mode for prompts
-        orig_multiline = self.multiline_mode
-        self.multiline_mode = False
         self.num_user_asks += 1
 
+        # Ring the bell if needed
+        self.ring_bell()
+
         if subject:
             self.tool_output()
             self.tool_output(subject, bold=True)
@@ -799,24 +864,25 @@ class InputOutput:
         elif self.yes is False:
             res = "no"
         else:
-            if self.prompt_session:
+            try:
-                res = self.prompt_session.prompt(
+                if self.prompt_session:
-                    question + " ",
+                    res = self.prompt_session.prompt(
-                    default=default,
+                        question + " ",
-                    style=style,
+                        default=default,
-                    complete_while_typing=True,
+                        style=style,
-                )
+                        complete_while_typing=True,
-            else:
+                    )
-                res = input(question + " ")
+                else:
+                    res = input(question + " ")
+            except EOFError:
+                # Treat EOF (Ctrl+D) as if the user pressed Enter
+                res = default
 
         hist = f"{question.strip()} {res.strip()}"
         self.append_chat_history(hist, linebreak=True, blockquote=True)
         if self.yes in (True, False):
             self.tool_output(hist)
 
-        # Restore original multiline mode
-        self.multiline_mode = orig_multiline
-
         return res
 
     def _tool_message(self, message="", strip=True, color=None):
@@ -872,6 +938,10 @@ class InputOutput:
         return mdStream
 
     def assistant_output(self, message, pretty=None):
+        if not message:
+            self.tool_warning("Empty response received from LLM. Check your provider account?")
+            return
+
         show_resp = message
 
         # Coder will force pretty off if fence is not triple-backticks
@@ -883,7 +953,7 @@ class InputOutput:
                 message, style=self.assistant_output_color, code_theme=self.code_theme
             )
         else:
-            show_resp = Text(message or "<no response>")
+            show_resp = Text(message or "(empty response)")
 
         self.console.print(show_resp)
 
@@ -894,6 +964,61 @@ class InputOutput:
     def print(self, message=""):
         print(message)
 
+    def llm_started(self):
+        """Mark that the LLM has started processing, so we should ring the bell on next input"""
+        self.bell_on_next_input = True
+
+    def get_default_notification_command(self):
+        """Return a default notification command based on the operating system."""
+        import platform
+
+        system = platform.system()
+
+        if system == "Darwin":  # macOS
+            # Check for terminal-notifier first
+            if shutil.which("terminal-notifier"):
+                return f"terminal-notifier -title 'Aider' -message '{NOTIFICATION_MESSAGE}'"
+            # Fall back to osascript
+            return (
+                f'osascript -e \'display notification "{NOTIFICATION_MESSAGE}" with title "Aider"\''
+            )
+        elif system == "Linux":
+            # Check for common Linux notification tools
+            for cmd in ["notify-send", "zenity"]:
+                if shutil.which(cmd):
+                    if cmd == "notify-send":
+                        return f"notify-send 'Aider' '{NOTIFICATION_MESSAGE}'"
+                    elif cmd == "zenity":
+                        return f"zenity --notification --text='{NOTIFICATION_MESSAGE}'"
+            return None  # No known notification tool found
+        elif system == "Windows":
+            # PowerShell notification
+            return (
+                "powershell -command"
+                " \"[System.Reflection.Assembly]::LoadWithPartialName('System.Windows.Forms');"
+                f" [System.Windows.Forms.MessageBox]::Show('{NOTIFICATION_MESSAGE}',"
+                " 'Aider')\""
+            )
+
+        return None  # Unknown system
+
+    def ring_bell(self):
+        """Ring the terminal bell if needed and clear the flag"""
+        if self.bell_on_next_input and self.notifications:
+            if self.notifications_command:
+                try:
+                    result = subprocess.run(
+                        self.notifications_command, shell=True, capture_output=True
+                    )
+                    if result.returncode != 0 and result.stderr:
+                        error_msg = result.stderr.decode("utf-8", errors="replace")
+                        self.tool_warning(f"Failed to run notifications command: {error_msg}")
+                except Exception as e:
+                    self.tool_warning(f"Failed to run notifications command: {e}")
+            else:
+                print("\a", end="", flush=True)  # Ring the bell
+            self.bell_on_next_input = False  # Clear the flag
+
     def toggle_multiline_mode(self):
         """Toggle between normal and multiline input modes"""
         self.multiline_mode = not self.multiline_mode

aider/linter.py

@@ -8,7 +8,7 @@ from dataclasses import dataclass
 from pathlib import Path
 
 from grep_ast import TreeContext, filename_to_lang
-from tree_sitter_languages import get_parser  # noqa: E402
+from grep_ast.tsl import get_parser  # noqa: E402
 
 from aider.dump import dump  # noqa: F401
 from aider.run_cmd import run_cmd_subprocess  # noqa: F401

aider/llm.py

@@ -2,6 +2,8 @@ import importlib
 import os
 import warnings
 
+from aider.dump import dump  # noqa: F401
+
 warnings.filterwarnings("ignore", category=UserWarning, module="pydantic")
 
 AIDER_SITE_URL = "https://aider.chat"

aider/main.py

@@ -1,4 +1,3 @@
-import configparser
 import json
 import os
 import re
@@ -25,6 +24,7 @@ from aider.coders import Coder
 from aider.coders.base_coder import UnknownEditFormat
 from aider.commands import Commands, SwitchCoder
 from aider.copypaste import ClipboardWatcher
+from aider.deprecated import handle_deprecated_model_args
 from aider.format_settings import format_settings, scrub_sensitive_info
 from aider.history import ChatSummary
 from aider.io import InputOutput
@@ -126,17 +126,15 @@ def setup_git(git_root, io):
     if not repo:
         return
 
-    user_name = None
+    try:
-    user_email = None
+        user_name = repo.git.config("--get", "user.name") or None
-    with repo.config_reader() as config:
+    except git.exc.GitCommandError:
-        try:
+        user_name = None
-            user_name = config.get_value("user", "name", None)
+
-        except (configparser.NoSectionError, configparser.NoOptionError):
+    try:
-            pass
+        user_email = repo.git.config("--get", "user.email") or None
-        try:
+    except git.exc.GitCommandError:
-            user_email = config.get_value("user", "email", None)
+        user_email = None
-        except (configparser.NoSectionError, configparser.NoOptionError):
-            pass
 
     if user_name and user_email:
         return repo.working_tree_dir
@@ -158,40 +156,39 @@ def check_gitignore(git_root, io, ask=True):
 
     try:
         repo = git.Repo(git_root)
-        if repo.ignored(".aider") and repo.ignored(".env"):
+        patterns_to_add = []
+
+        if not repo.ignored(".aider"):
+            patterns_to_add.append(".aider*")
+
+        env_path = Path(git_root) / ".env"
+        if env_path.exists() and not repo.ignored(".env"):
+            patterns_to_add.append(".env")
+
+        if not patterns_to_add:
             return
-    except ANY_GIT_ERROR:
-        pass
 
-    patterns = [".aider*", ".env"]
+        gitignore_file = Path(git_root) / ".gitignore"
-    patterns_to_add = []
+        if gitignore_file.exists():
-
+            try:
-    gitignore_file = Path(git_root) / ".gitignore"
+                content = io.read_text(gitignore_file)
-    if gitignore_file.exists():
+                if content is None:
-        try:
+                    return
-            content = io.read_text(gitignore_file)
+                if not content.endswith("\n"):
-            if content is None:
+                    content += "\n"
+            except OSError as e:
+                io.tool_error(f"Error when trying to read {gitignore_file}: {e}")
                 return
-            existing_lines = content.splitlines()
+        else:
-            for pat in patterns:
+            content = ""
-                if pat not in existing_lines:
+    except ANY_GIT_ERROR:
-                    if "*" in pat or (Path(git_root) / pat).exists():
+        return
-                        patterns_to_add.append(pat)
+
-        except OSError as e:
+    if ask:
-            io.tool_error(f"Error when trying to read {gitignore_file}: {e}")
+        io.tool_output("You can skip this check with --no-gitignore")
+        if not io.confirm_ask(f"Add {', '.join(patterns_to_add)} to .gitignore (recommended)?"):
             return
-    else:
-        content = ""
-        patterns_to_add = patterns
 
-    if not patterns_to_add:
-        return
-
-    if ask and not io.confirm_ask(f"Add {', '.join(patterns_to_add)} to .gitignore (recommended)?"):
-        return
-
-    if content and not content.endswith("\n"):
-        content += "\n"
     content += "\n".join(patterns_to_add) + "\n"
 
     try:
@@ -508,10 +505,11 @@ def main(argv=None, input=None, output=None, force_git_root=None, return_coder=F
         litellm._load_litellm()
         litellm._lazy_module.client_session = httpx.Client(verify=False)
         litellm._lazy_module.aclient_session = httpx.AsyncClient(verify=False)
+        # Set verify_ssl on the model_info_manager
+        models.model_info_manager.set_verify_ssl(False)
 
     if args.timeout:
-        litellm._load_litellm()
+        models.request_timeout = args.timeout
-        litellm._lazy_module.request_timeout = args.timeout
 
     if args.dark_mode:
         args.user_input_color = "#32FF32"
@@ -557,6 +555,8 @@ def main(argv=None, input=None, output=None, force_git_root=None, return_coder=F
             editingmode=editing_mode,
             fancy_input=args.fancy_input,
             multiline_mode=args.multiline,
+            notifications=args.notifications,
+            notifications_command=args.notifications_command,
         )
 
     io = get_io(args.pretty)
@@ -596,6 +596,9 @@ def main(argv=None, input=None, output=None, force_git_root=None, return_coder=F
 
     if args.openai_api_key:
         os.environ["OPENAI_API_KEY"] = args.openai_api_key
+
+    # Handle deprecated model shortcut args
+    handle_deprecated_model_args(args, io)
     if args.openai_api_base:
         os.environ["OPENAI_API_BASE"] = args.openai_api_base
     if args.openai_api_version:
@@ -753,7 +756,7 @@ def main(argv=None, input=None, output=None, force_git_root=None, return_coder=F
         model_key_pairs = [
             ("ANTHROPIC_API_KEY", "sonnet"),
             ("DEEPSEEK_API_KEY", "deepseek"),
-            ("OPENROUTER_API_KEY", "openrouter/anthropic/claude-3.5-sonnet"),
+            ("OPENROUTER_API_KEY", "openrouter/anthropic/claude-3.7-sonnet"),
             ("OPENAI_API_KEY", "gpt-4o"),
             ("GEMINI_API_KEY", "flash"),
         ]
@@ -775,15 +778,22 @@ def main(argv=None, input=None, output=None, force_git_root=None, return_coder=F
         weak_model=args.weak_model,
         editor_model=args.editor_model,
         editor_edit_format=args.editor_edit_format,
+        verbose=args.verbose,
     )
 
-    # add --reasoning-effort cli param
+    # Check if deprecated remove_reasoning is set
+    if main_model.remove_reasoning is not None:
+        io.tool_warning(
+            "Model setting 'remove_reasoning' is deprecated, please use 'reasoning_tag' instead."
+        )
+
+    # Set reasoning effort if specified
     if args.reasoning_effort is not None:
-        if not getattr(main_model, "extra_params", None):
+        main_model.set_reasoning_effort(args.reasoning_effort)
-            main_model.extra_params = {}
+
-        if "extra_body" not in main_model.extra_params:
+    # Set thinking tokens if specified
-            main_model.extra_params["extra_body"] = {}
+    if args.thinking_tokens is not None:
-        main_model.extra_params["extra_body"]["reasoning_effort"] = args.reasoning_effort
+        main_model.set_thinking_tokens(args.thinking_tokens)
 
     if args.copy_paste and args.edit_format is None:
         if main_model.edit_format in ("diff", "whole"):
@@ -857,6 +867,7 @@ def main(argv=None, input=None, output=None, force_git_root=None, return_coder=F
         parser=parser,
         verbose=args.verbose,
         editor=args.editor,
+        original_read_only_fnames=read_only_fnames,
     )
 
     summarizer = ChatSummary(
@@ -911,6 +922,7 @@ def main(argv=None, input=None, output=None, force_git_root=None, return_coder=F
             chat_language=args.chat_language,
             detect_urls=args.detect_urls,
             auto_copy_context=args.copy_paste,
+            auto_accept_architect=args.auto_accept_architect,
         )
     except UnknownEditFormat as err:
         io.tool_error(str(err))
@@ -992,6 +1004,9 @@ def main(argv=None, input=None, output=None, force_git_root=None, return_coder=F
             analytics.event("exit", reason="Failed to read apply content")
             return
         coder.partial_response_content = content
+        # For testing #2879
+        # from aider.coders.base_coder import all_fences
+        # coder.fence = all_fences[1]
         coder.apply_updates()
         analytics.event("exit", reason="Applied updates")
         return
@@ -1059,10 +1074,13 @@ def main(argv=None, input=None, output=None, force_git_root=None, return_coder=F
 
     while True:
         try:
+            coder.ok_to_warm_cache = bool(args.cache_keepalive_pings)
             coder.run()
             analytics.event("exit", reason="Completed main CLI coder.run")
             return
         except SwitchCoder as switch:
+            coder.ok_to_warm_cache = False
+
             kwargs = dict(io=io, from_coder=coder)
             kwargs.update(switch.kwargs)
             if "show_announcements" in kwargs:

aider/models.py

@@ -1,4 +1,5 @@
 import difflib
+import hashlib
 import importlib.resources
 import json
 import math
@@ -8,7 +9,7 @@ import sys
 import time
 from dataclasses import dataclass, fields
 from pathlib import Path
-from typing import Optional
+from typing import Optional, Union
 
 import json5
 import yaml
@@ -16,11 +17,21 @@ from PIL import Image
 
 from aider.dump import dump  # noqa: F401
 from aider.llm import litellm
+from aider.sendchat import ensure_alternating_roles, sanity_check_messages
+from aider.utils import check_pip_install_extra
+
+RETRY_TIMEOUT = 60
+
+request_timeout = 600
 
 DEFAULT_MODEL_NAME = "gpt-4o"
 ANTHROPIC_BETA_HEADER = "prompt-caching-2024-07-31,pdfs-2024-09-25"
 
 OPENAI_MODELS = """
+o1
+o1-preview
+o1-mini
+o3-mini
 gpt-4
 gpt-4o
 gpt-4o-2024-05-13
@@ -65,7 +76,7 @@ ANTHROPIC_MODELS = [ln.strip() for ln in ANTHROPIC_MODELS.splitlines() if ln.str
 # Mapping of model aliases to their canonical names
 MODEL_ALIASES = {
     # Claude models
-    "sonnet": "claude-3-5-sonnet-20241022",
+    "sonnet": "anthropic/claude-3-7-sonnet-20250219",
     "haiku": "claude-3-5-haiku-20241022",
     "opus": "claude-3-opus-20240229",
     # GPT models
@@ -80,6 +91,7 @@ MODEL_ALIASES = {
     "r1": "deepseek/deepseek-reasoner",
     "flash": "gemini/gemini-2.0-flash-exp",
 }
+# Model metadata loaded from resources and user's files.
 
 
 @dataclass
@@ -97,11 +109,13 @@ class ModelSettings:
     cache_control: bool = False
     caches_by_default: bool = False
     use_system_prompt: bool = True
-    use_temperature: bool = True
+    use_temperature: Union[bool, float] = True
     streaming: bool = True
     editor_model_name: Optional[str] = None
     editor_edit_format: Optional[str] = None
-    remove_reasoning: Optional[str] = None
+    reasoning_tag: Optional[str] = None
+    remove_reasoning: Optional[str] = None  # Deprecated alias for reasoning_tag
+    system_prompt_prefix: Optional[str] = None
 
 
 # Load model settings from package resource
@@ -123,23 +137,38 @@ class ModelInfoManager:
         self.cache_dir = Path.home() / ".aider" / "caches"
         self.cache_file = self.cache_dir / "model_prices_and_context_window.json"
         self.content = None
-        self._load_cache()
+        self.local_model_metadata = {}
+        self.verify_ssl = True
+        self._cache_loaded = False
+
+    def set_verify_ssl(self, verify_ssl):
+        self.verify_ssl = verify_ssl
 
     def _load_cache(self):
+        if self._cache_loaded:
+            return
+
         try:
             self.cache_dir.mkdir(parents=True, exist_ok=True)
             if self.cache_file.exists():
                 cache_age = time.time() - self.cache_file.stat().st_mtime
                 if cache_age < self.CACHE_TTL:
-                    self.content = json.loads(self.cache_file.read_text())
+                    try:
+                        self.content = json.loads(self.cache_file.read_text())
+                    except json.JSONDecodeError:
+                        # If the cache file is corrupted, treat it as missing
+                        self.content = None
         except OSError:
             pass
 
+        self._cache_loaded = True
+
     def _update_cache(self):
         try:
             import requests
 
-            response = requests.get(self.MODEL_INFO_URL, timeout=5)
+            # Respect the --no-verify-ssl switch
+            response = requests.get(self.MODEL_INFO_URL, timeout=5, verify=self.verify_ssl)
             if response.status_code == 200:
                 self.content = response.json()
                 try:
@@ -155,6 +184,13 @@ class ModelInfoManager:
                 pass
 
     def get_model_from_cached_json_db(self, model):
+        data = self.local_model_metadata.get(model)
+        if data:
+            return data
+
+        # Ensure cache is loaded before checking content
+        self._load_cache()
+
         if not self.content:
             self._update_cache()
 
@@ -194,11 +230,14 @@ model_info_manager = ModelInfoManager()
 
 
 class Model(ModelSettings):
-    def __init__(self, model, weak_model=None, editor_model=None, editor_edit_format=None):
+    def __init__(
+        self, model, weak_model=None, editor_model=None, editor_edit_format=None, verbose=False
+    ):
         # Map any alias to its canonical name
         model = MODEL_ALIASES.get(model, model)
 
         self.name = model
+        self.verbose = verbose
 
         self.max_chat_history_tokens = 1024
         self.weak_model = None
@@ -241,6 +280,11 @@ class Model(ModelSettings):
             val = getattr(source, field.name)
             setattr(self, field.name, val)
 
+        # Handle backward compatibility: if remove_reasoning is set but reasoning_tag isn't,
+        # use remove_reasoning's value for reasoning_tag
+        if self.reasoning_tag is None and self.remove_reasoning is not None:
+            self.reasoning_tag = self.remove_reasoning
+
     def configure_model_settings(self, model):
         # Look for exact model match
         exact_match = False
@@ -273,6 +317,50 @@ class Model(ModelSettings):
                     self.extra_params[key] = value
 
     def apply_generic_model_settings(self, model):
+        if "/o3-mini" in model:
+            self.edit_format = "diff"
+            self.use_repo_map = True
+            self.use_temperature = False
+            self.system_prompt_prefix = "Formatting re-enabled. "
+            return  # <--
+
+        if "/o1-mini" in model:
+            self.use_repo_map = True
+            self.use_temperature = False
+            self.use_system_prompt = False
+            return  # <--
+
+        if "/o1-preview" in model:
+            self.edit_format = "diff"
+            self.use_repo_map = True
+            self.use_temperature = False
+            self.use_system_prompt = False
+            return  # <--
+
+        if "/o1" in model:
+            self.edit_format = "diff"
+            self.use_repo_map = True
+            self.use_temperature = False
+            self.streaming = False
+            self.system_prompt_prefix = "Formatting re-enabled. "
+            return  # <--
+
+        if "deepseek" in model and "v3" in model:
+            self.edit_format = "diff"
+            self.use_repo_map = True
+            self.reminder = "sys"
+            self.examples_as_sys_msg = True
+            return  # <--
+
+        if "deepseek" in model and ("r1" in model or "reasoning" in model):
+            self.edit_format = "diff"
+            self.use_repo_map = True
+            self.examples_as_sys_msg = True
+            self.use_temperature = False
+            self.reasoning_tag = "think"
+            self.reasoning_tag = "think"
+            return  # <--
+
         if ("llama3" in model or "llama-3" in model) and "70b" in model:
             self.edit_format = "diff"
             self.use_repo_map = True
@@ -317,8 +405,16 @@ class Model(ModelSettings):
             self.edit_format = "diff"
             self.editor_edit_format = "editor-diff"
             self.use_repo_map = True
-            if model.startswith("ollama/") or model.startswith("ollama_chat/"):
+            return  # <--
-                self.extra_params = dict(num_ctx=8 * 1024)
+
+        if "qwq" in model and "32b" in model and "preview" not in model:
+            self.edit_format = "diff"
+            self.editor_edit_format = "editor-diff"
+            self.use_repo_map = True
+            self.reasoning_tag = "think"
+            self.examples_as_sys_msg = True
+            self.use_temperature = 0.6
+            self.extra_params = dict(top_p=0.95)
             return  # <--
 
         # use the defaults
@@ -440,14 +536,31 @@ class Model(ModelSettings):
         """Fast path for common models. Avoids forcing litellm import."""
 
         model = self.name
-        if model in OPENAI_MODELS or model.startswith("openai/"):
+
+        pieces = model.split("/")
+        if len(pieces) > 1:
+            provider = pieces[0]
+        else:
+            provider = None
+
+        keymap = dict(
+            openrouter="OPENROUTER_API_KEY",
+            openai="OPENAI_API_KEY",
+            deepseek="DEEPSEEK_API_KEY",
+            gemini="GEMINI_API_KEY",
+            anthropic="ANTHROPIC_API_KEY",
+            groq="GROQ_API_KEY",
+            fireworks_ai="FIREWORKS_API_KEY",
+        )
+        var = None
+        if model in OPENAI_MODELS:
             var = "OPENAI_API_KEY"
-        elif model in ANTHROPIC_MODELS or model.startswith("anthropic/"):
+        elif model in ANTHROPIC_MODELS:
             var = "ANTHROPIC_API_KEY"
         else:
-            return
+            var = keymap.get(provider)
 
-        if os.environ.get(var):
+        if var and os.environ.get(var):
             return dict(keys_in_environment=[var], missing_keys=[])
 
     def validate_environment(self):
@@ -483,6 +596,185 @@ class Model(ModelSettings):
             map_tokens = max(map_tokens, 1024)
         return map_tokens
 
+    def set_reasoning_effort(self, effort):
+        """Set the reasoning effort parameter for models that support it"""
+        if effort is not None:
+            if not self.extra_params:
+                self.extra_params = {}
+            if "extra_body" not in self.extra_params:
+                self.extra_params["extra_body"] = {}
+            self.extra_params["extra_body"]["reasoning_effort"] = effort
+
+    def parse_token_value(self, value):
+        """
+        Parse a token value string into an integer.
+        Accepts formats: 8096, "8k", "10.5k", "0.5M", "10K", etc.
+
+        Args:
+            value: String or int token value
+
+        Returns:
+            Integer token value
+        """
+        if isinstance(value, int):
+            return value
+
+        if not isinstance(value, str):
+            return int(value)  # Try to convert to int
+
+        value = value.strip().upper()
+
+        if value.endswith("K"):
+            multiplier = 1024
+            value = value[:-1]
+        elif value.endswith("M"):
+            multiplier = 1024 * 1024
+            value = value[:-1]
+        else:
+            multiplier = 1
+
+        # Convert to float first to handle decimal values like "10.5k"
+        return int(float(value) * multiplier)
+
+    def set_thinking_tokens(self, value):
+        """
+        Set the thinking token budget for models that support it.
+        Accepts formats: 8096, "8k", "10.5k", "0.5M", "10K", etc.
+        """
+        if value is not None:
+            num_tokens = self.parse_token_value(value)
+            self.use_temperature = False
+            if not self.extra_params:
+                self.extra_params = {}
+            self.extra_params["thinking"] = {"type": "enabled", "budget_tokens": num_tokens}
+
+    def get_thinking_tokens(self, model):
+        """Get formatted thinking token budget if available"""
+        if (
+            model.extra_params
+            and "thinking" in model.extra_params
+            and "budget_tokens" in model.extra_params["thinking"]
+        ):
+            budget = model.extra_params["thinking"]["budget_tokens"]
+            # Format as xx.yK for thousands, xx.yM for millions
+            if budget >= 1024 * 1024:
+                value = budget / (1024 * 1024)
+                if value == int(value):
+                    return f"{int(value)}M"
+                else:
+                    return f"{value:.1f}M"
+            else:
+                value = budget / 1024
+                if value == int(value):
+                    return f"{int(value)}k"
+                else:
+                    return f"{value:.1f}k"
+        return None
+
+    def get_reasoning_effort(self, model):
+        """Get reasoning effort value if available"""
+        if (
+            model.extra_params
+            and "extra_body" in model.extra_params
+            and "reasoning_effort" in model.extra_params["extra_body"]
+        ):
+            return model.extra_params["extra_body"]["reasoning_effort"]
+        return None
+
+    def is_deepseek_r1(self):
+        name = self.name.lower()
+        if "deepseek" not in name:
+            return
+        return "r1" in name or "reasoner" in name
+
+    def is_ollama(self):
+        return self.name.startswith("ollama/") or self.name.startswith("ollama_chat/")
+
+    def send_completion(self, messages, functions, stream, temperature=None):
+        if os.environ.get("AIDER_SANITY_CHECK_TURNS"):
+            sanity_check_messages(messages)
+
+        if self.is_deepseek_r1():
+            messages = ensure_alternating_roles(messages)
+
+        kwargs = dict(
+            model=self.name,
+            messages=messages,
+            stream=stream,
+        )
+
+        if self.use_temperature is not False:
+            if temperature is None:
+                if isinstance(self.use_temperature, bool):
+                    temperature = 0
+                else:
+                    temperature = float(self.use_temperature)
+
+            kwargs["temperature"] = temperature
+
+        if functions is not None:
+            function = functions[0]
+            kwargs["tools"] = [dict(type="function", function=function)]
+            kwargs["tool_choice"] = {"type": "function", "function": {"name": function["name"]}}
+        if self.extra_params:
+            kwargs.update(self.extra_params)
+        if self.is_ollama() and "num_ctx" not in kwargs:
+            num_ctx = int(self.token_count(messages) * 1.25) + 8192
+            kwargs["num_ctx"] = num_ctx
+        key = json.dumps(kwargs, sort_keys=True).encode()
+
+        # dump(kwargs)
+
+        hash_object = hashlib.sha1(key)
+        if "timeout" not in kwargs:
+            kwargs["timeout"] = request_timeout
+        if self.verbose:
+            dump(kwargs)
+        res = litellm.completion(**kwargs)
+        return hash_object, res
+
+    def simple_send_with_retries(self, messages):
+        from aider.exceptions import LiteLLMExceptions
+
+        litellm_ex = LiteLLMExceptions()
+        if "deepseek-reasoner" in self.name:
+            messages = ensure_alternating_roles(messages)
+        retry_delay = 0.125
+
+        while True:
+            try:
+                kwargs = {
+                    "messages": messages,
+                    "functions": None,
+                    "stream": False,
+                }
+
+                _hash, response = self.send_completion(**kwargs)
+                if not response or not hasattr(response, "choices") or not response.choices:
+                    return None
+                res = response.choices[0].message.content
+                from aider.reasoning_tags import remove_reasoning_content
+
+                return remove_reasoning_content(res, self.reasoning_tag)
+
+            except litellm_ex.exceptions_tuple() as err:
+                ex_info = litellm_ex.get_ex_info(err)
+                print(str(err))
+                if ex_info.description:
+                    print(ex_info.description)
+                should_retry = ex_info.retry
+                if should_retry:
+                    retry_delay *= 2
+                    if retry_delay > RETRY_TIMEOUT:
+                        should_retry = False
+                if not should_retry:
+                    return None
+                print(f"Retrying in {retry_delay:.1f} seconds...")
+                time.sleep(retry_delay)
+                continue
+            except AttributeError:
+                return None
+
 
 def register_models(model_settings_fnames):
     files_loaded = []
@@ -527,9 +819,8 @@ def register_litellm_models(model_fnames):
             if not model_def:
                 continue
 
-            # only load litellm if we have actual data
+            # Defer registration with litellm to faster path.
-            litellm._load_litellm()
+            model_info_manager.local_model_metadata.update(model_def)
-            litellm.register_model(model_def)
         except Exception as e:
             raise Exception(f"Error loading model definition from {model_fname}: {e}")
 
@@ -587,6 +878,9 @@ def sanity_check_model(io, model):
         show = True
         io.tool_warning(f"Warning for {model}: Unknown which environment variables are required.")
 
+    # Check for model-specific dependencies
+    check_for_dependencies(io, model.name)
+
     if not model.info:
         show = True
         io.tool_warning(
@@ -602,6 +896,30 @@ def sanity_check_model(io, model):
     return show
 
 
+def check_for_dependencies(io, model_name):
+    """
+    Check for model-specific dependencies and install them if needed.
+
+    Args:
+        io: The IO object for user interaction
+        model_name: The name of the model to check dependencies for
+    """
+    # Check if this is a Bedrock model and ensure boto3 is installed
+    if model_name.startswith("bedrock/"):
+        check_pip_install_extra(
+            io, "boto3", "AWS Bedrock models require the boto3 package.", ["boto3"]
+        )
+
+    # Check if this is a Vertex AI model and ensure google-cloud-aiplatform is installed
+    elif model_name.startswith("vertex_ai/"):
+        check_pip_install_extra(
+            io,
+            "google.cloud.aiplatform",
+            "Google Vertex AI models require the google-cloud-aiplatform package.",
+            ["google-cloud-aiplatform"],
+        )
+
+
 def fuzzy_match_models(name):
     name = name.lower()
 

aider/queries/tree-sitter-language-pack/README.md

@@ -0,0 +1,7 @@
+These scm files are all adapted from the github repositories listed here:
+
+https://github.com/Goldziher/tree-sitter-language-pack/blob/main/sources/language_definitions.json
+
+See this URL for information on the licenses of each repo:
+
+https://github.com/Goldziher/tree-sitter-language-pack/

aider/queries/tree-sitter-language-pack/arduino-tags.scm

@@ -0,0 +1,5 @@
+(function_declarator
+  declarator: (identifier) @name.definition.function) @definition.function
+
+(call_expression
+  function: (identifier) @name.reference.call) @reference.call

aider/queries/tree-sitter-language-pack/chatito-tags.scm

@@ -0,0 +1,16 @@
+; Definitions
+(intent_def
+  (intent) @name.definition.intent) @definition.intent
+
+(slot_def
+  (slot) @name.definition.slot) @definition.slot
+
+(alias_def
+  (alias) @name.definition.alias) @definition.alias
+
+; References
+(slot_ref
+  (slot) @name.reference.slot) @reference.slot
+
+(alias_ref
+  (alias) @name.reference.alias) @reference.alias

aider/queries/tree-sitter-language-pack/commonlisp-tags.scm

@@ -0,0 +1,122 @@
+;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;
+;;; Function Definitions ;;;;;;;;;;;;;;;;;;;;;;;
+
+(defun_header
+  function_name: (sym_lit) @name.definition.function) @definition.function
+
+;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;
+;;; Function Calls ;;;;;;;;;;;;;;;;;;;;;;;;;;;;;
+;;;
+;;; Basically, we consider every list literal with symbol as the
+;;; first element to be a call to a function named by that element.
+;;; But we must exclude some cases. Note, tree-sitter @ignore
+;;; cases only work if they are declared before the cases
+;;; we want to include.
+
+;; Exclude lambda lists for function definitions
+;; For example:
+;;
+;;    (defun my-func (arg1 arg2) ...)
+;;
+;; do not treat (arg1 arg2) as a call of function arg1
+;;
+(defun_header
+  lambda_list: (list_lit . [(sym_lit) (package_lit)] @ignore))
+
+;; Similar to the above, but for
+;;
+;;     (defmethod m ((type1 param1) (type2 param2)) ...)
+;;
+;; where list literals having symbol as their first element
+;; are nested inside the lambda list.
+(defun_header
+  lambda_list: (list_lit (list_lit . [(sym_lit) (package_lit)] @ignore)))
+
+;;
+;;      (let ((var ...) (var2 ...)) ...)
+;;
+;; - exclude var, var2
+;; - the same for let*, flet, labels, macrolet, symbol-macrolet
+(list_lit . [(sym_lit) (package_lit)] @name.reference.call
+          . (list_lit (list_lit . [(sym_lit) (package_lit)] @ignore))
+          (#match? @name.reference.call
+                   "(?i)^(cl:)?(let|let\\*|flet|labels|macrolet|symbol-macrolet)$")
+  )
+
+;; TODO:
+;;     - exclude also:
+;;       - (defclass name (parent parent2)
+;;           ((slot1 ...)
+;;            (slot2 ...))
+;;              exclude the parent, slot1, slot2
+;;       - (flet ((func-1 (param1 param2))) ...)
+;;           - we already exclude func-1, but param1 is still recognized
+;;             as a function call - exclude it too
+;;           - the same for labels
+;;           - the same macrolet
+;;       - what else?
+;;         (that's a non-goal to completely support all macros
+;;          and special operators, but every one we support
+;;          makes the solution a little bit better)
+;;     - (flet ((func-1 (param1 param2))) ...)
+;;       - instead of simply excluding it, as we do today,
+;;         tag func-1 as @local.definition.function (I suppose)
+;;       - the same for labels, macrolet
+;;     - @local.scope for let, let*, flet, labels, macrolet
+;;       - I guess the whole span of the scope text,
+;;         till the closing paren, should be tagged as @local.scope;
+;;         Hopefully, combined with @local.definition.function
+;;         within the scope, the usual  @reference.call within
+;;         that scope will refer to the local definition,
+;;         and there will be no need to use @local.reference.call
+;;         (which is more difficult to implement).
+;;       - When implementing, remember the scope rules differences
+;;         of let vs let*, flet vs labels.
+
+
+;; Include all other cases - list literal with symbol as the
+;; first element
+(list_lit . [(sym_lit) (package_lit)] @name.reference.call) @reference.call
+
+;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;
+;;; classes
+
+(list_lit . [(sym_lit) (package_lit)] @ignore
+          . [(sym_lit) (package_lit)] @name.definition.class
+  (#match? @ignore "(?i)^(cl:)?defclass$")
+          ) @definition.class
+
+(list_lit . [(sym_lit) (package_lit)] @ignore
+          . (quoting_lit [(sym_lit) (package_lit)] @name.reference.class)
+  (#match? @ignore "(?i)^(cl:)?make-instance$")
+          ) @reference.class
+
+;;; TODO:
+;;  - @reference.class for base classes
+
+;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;
+;;; TODO:
+;; - Symbols referenced in defpackage
+;;
+;;       (defpackage ...
+;;         (:export (symbol-a :symbol-b #:symbol-c "SYMBOL-D")))
+;;
+;;   The goal is to allow quick navigation from the API
+;;   overview in the form of defpackage, to the definition
+;;   where user can read parameters, docstring, etc.
+;;   - The @name must not include the colon, or sharpsign colon, quotes,
+;;     just symbol-a, symbol-b, symbol-c, sybmol-d
+;;   - Downcase the names specified as string literals?
+;;     ("SYMBOL-D" -> symbol-d)
+;;   - We don't know if the exported symbol is a function, variable,
+;;     class or something else. The official doc
+;;     (https://tree-sitter.github.io/tree-sitter/code-navigation-systems)
+;;     does not even suggest a tag for variable reference.
+;;     (Although in practice, the `tree-sitter tags` command
+;;     allows any @reference.* and @definition.* tags)
+;;     Probably it's better to just use @reference.call for all
+;;     the symbols in the :export clause.
+;;
+;; - The same for the export function call:
+;; 
+;;       (export '(symbol-a :symbol-b #:symbol-c "SYMBOL-D"))

aider/queries/tree-sitter-language-pack/cpp-tags.scm

@@ -0,0 +1,15 @@
+(struct_specifier name: (type_identifier) @name.definition.class body:(_)) @definition.class
+
+(declaration type: (union_specifier name: (type_identifier) @name.definition.class)) @definition.class
+
+(function_declarator declarator: (identifier) @name.definition.function) @definition.function
+
+(function_declarator declarator: (field_identifier) @name.definition.function) @definition.function
+
+(function_declarator declarator: (qualified_identifier scope: (namespace_identifier) @local.scope name: (identifier) @name.definition.method)) @definition.method
+
+(type_definition declarator: (type_identifier) @name.definition.type) @definition.type
+
+(enum_specifier name: (type_identifier) @name.definition.type) @definition.type
+
+(class_specifier name: (type_identifier) @name.definition.class) @definition.class

aider/queries/tree-sitter-language-pack/csharp-tags.scm

@@ -0,0 +1,26 @@
+; Based on https://github.com/tree-sitter/tree-sitter-c-sharp/blob/master/queries/tags.scm
+; MIT License.
+
+(class_declaration name: (identifier) @name.definition.class) @definition.class
+
+(class_declaration (base_list (_) @name.reference.class)) @reference.class
+
+(interface_declaration name: (identifier) @name.definition.interface) @definition.interface
+
+(interface_declaration (base_list (_) @name.reference.interface)) @reference.interface
+
+(method_declaration name: (identifier) @name.definition.method) @definition.method
+
+(object_creation_expression type: (identifier) @name.reference.class) @reference.class
+
+(type_parameter_constraints_clause (identifier) @name.reference.class) @reference.class
+
+(type_parameter_constraint (type type: (identifier) @name.reference.class)) @reference.class
+
+(variable_declaration type: (identifier) @name.reference.class) @reference.class
+
+(invocation_expression function: (member_access_expression name: (identifier) @name.reference.send)) @reference.send
+
+(namespace_declaration name: (identifier) @name.definition.module) @definition.module
+
+(namespace_declaration name: (identifier) @name.definition.module) @module

aider/queries/tree-sitter-language-pack/d-tags.scm

@@ -0,0 +1,26 @@
+(module_def (module_declaration (module_fqn) @name.definition.module)) @definition.module
+
+(struct_declaration (struct) . (identifier) @name.definition.class) @definition.class
+(interface_declaration (interface) . (identifier) @name.definition.interface) @definition.interface
+(enum_declaration (enum) . (identifier) @name.definition.type) @definition.type
+
+(class_declaration (class) . (identifier) @name.definition.class) @definition.class
+(constructor (this) @name.definition.method) @definition.method
+(destructor (this) @name.definition.method) @definition.method
+(postblit (this) @name.definition.method) @definition.method
+
+(manifest_declarator . (identifier) @name.definition.type) @definition.type
+
+(function_declaration (identifier) @name.definition.function) @definition.function
+
+(union_declaration (union) . (identifier) @name.definition.type) @definition.type
+
+(anonymous_enum_declaration (enum_member . (identifier) @name.definition.constant)) @definition.constant
+
+(enum_declaration (enum_member . (identifier) @name.definition.constant)) @definition.constant
+
+(call_expression (identifier) @name.reference.call) @reference.call
+(call_expression (type (template_instance (identifier) @name.reference.call))) @reference.call
+(parameter (type (identifier) @name.reference.class) @reference.class (identifier))
+
+(variable_declaration (type (identifier) @name.reference.class) @reference.class (declarator))

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

@@ -0,0 +1,92 @@
+
+(class_definition
+  name: (identifier) @name.definition.class) @definition.class
+
+(method_signature
+  (function_signature)) @definition.method
+
+(type_alias
+  (type_identifier) @name.definition.type) @definition.type
+
+(method_signature
+(getter_signature
+  name: (identifier) @name.definition.method)) @definition.method
+
+(method_signature
+(setter_signature
+  name: (identifier) @name.definition.method)) @definition.method 
+
+(method_signature
+  (function_signature
+  name: (identifier) @name.definition.method)) @definition.method
+
+(method_signature
+  (factory_constructor_signature
+    (identifier) @name.definition.method)) @definition.method
+
+(method_signature
+  (constructor_signature
+  name: (identifier) @name.definition.method)) @definition.method
+
+(method_signature
+  (operator_signature)) @definition.method
+
+(method_signature) @definition.method
+
+(mixin_declaration
+  (mixin)
+  (identifier) @name.definition.mixin) @definition.mixin
+
+(extension_declaration
+  name: (identifier) @name.definition.extension) @definition.extension
+
+
+(new_expression
+  (type_identifier) @name.reference.class) @reference.class
+
+(enum_declaration
+  name: (identifier) @name.definition.enum) @definition.enum
+
+(function_signature
+  name: (identifier) @name.definition.function) @definition.function 
+
+(initialized_variable_definition
+  name: (identifier)
+  value: (identifier) @name.reference.class 
+  value: (selector
+	"!"?
+	(argument_part 
+	  (arguments
+	    (argument)*))?)?) @reference.class
+
+(assignment_expression
+  left: (assignable_expression 
+		  (identifier)
+		  (unconditional_assignable_selector
+			"."
+			(identifier) @name.reference.send))) @reference.call
+
+(assignment_expression
+  left: (assignable_expression 
+		  (identifier)
+		  (conditional_assignable_selector
+			"?."
+			(identifier) @name.reference.send))) @reference.call
+
+((identifier) @name.reference.send
+ (selector
+    "!"?
+    (conditional_assignable_selector
+      "?." (identifier) @name.reference.send)?
+    (unconditional_assignable_selector
+      "."? (identifier) @name.reference.send)?
+    (argument_part
+      (arguments
+        (argument)*))?)*
+	(cascade_section
+	  (cascade_selector
+		(identifier)) @name.reference.send 
+	  (argument_part 
+		(arguments
+		  (argument)*))?)?) @reference.call
+

aider/queries/tree-sitter-language-pack/elisp-tags.scm

@@ -0,0 +1,5 @@
+;; defun/defsubst
+(function_definition name: (symbol) @name.definition.function) @definition.function
+
+;; Treat macros as function definitions for the sake of TAGS.
+(macro_definition name: (symbol) @name.definition.function) @definition.function

aider/queries/tree-sitter-language-pack/elixir-tags.scm

@@ -0,0 +1,54 @@
+; Definitions
+
+; * modules and protocols
+(call
+  target: (identifier) @ignore
+  (arguments (alias) @name.definition.module)
+  (#any-of? @ignore "defmodule" "defprotocol")) @definition.module
+
+; * functions/macros
+(call
+  target: (identifier) @ignore
+  (arguments
+    [
+      ; zero-arity functions with no parentheses
+      (identifier) @name.definition.function
+      ; regular function clause
+      (call target: (identifier) @name.definition.function)
+      ; function clause with a guard clause
+      (binary_operator
+        left: (call target: (identifier) @name.definition.function)
+        operator: "when")
+    ])
+  (#any-of? @ignore "def" "defp" "defdelegate" "defguard" "defguardp" "defmacro" "defmacrop" "defn" "defnp")) @definition.function
+
+; References
+
+; ignore calls to kernel/special-forms keywords
+(call
+  target: (identifier) @ignore
+  (#any-of? @ignore "def" "defp" "defdelegate" "defguard" "defguardp" "defmacro" "defmacrop" "defn" "defnp" "defmodule" "defprotocol" "defimpl" "defstruct" "defexception" "defoverridable" "alias" "case" "cond" "else" "for" "if" "import" "quote" "raise" "receive" "require" "reraise" "super" "throw" "try" "unless" "unquote" "unquote_splicing" "use" "with"))
+
+; ignore module attributes
+(unary_operator
+  operator: "@"
+  operand: (call
+    target: (identifier) @ignore))
+
+; * function call
+(call
+  target: [
+   ; local
+   (identifier) @name.reference.call
+   ; remote
+   (dot
+     right: (identifier) @name.reference.call)
+  ]) @reference.call
+
+; * pipe into function call
+(binary_operator
+  operator: "|>"
+  right: (identifier) @name.reference.call) @reference.call
+
+; * modules
+(alias) @name.reference.module @reference.module

aider/queries/tree-sitter-language-pack/elm-tags.scm

@@ -0,0 +1,19 @@
+(value_declaration (function_declaration_left (lower_case_identifier) @name.definition.function)) @definition.function
+
+(function_call_expr (value_expr (value_qid) @name.reference.function)) @reference.function
+(exposed_value (lower_case_identifier) @name.reference.function) @reference.function
+(type_annotation ((lower_case_identifier) @name.reference.function) (colon)) @reference.function
+
+(type_declaration ((upper_case_identifier) @name.definition.type) ) @definition.type
+
+(type_ref (upper_case_qid (upper_case_identifier) @name.reference.type)) @reference.type
+(exposed_type (upper_case_identifier) @name.reference.type) @reference.type
+
+(type_declaration (union_variant (upper_case_identifier) @name.definition.union)) @definition.union
+
+(value_expr (upper_case_qid (upper_case_identifier) @name.reference.union)) @reference.union
+
+
+(module_declaration 
+    (upper_case_qid (upper_case_identifier)) @name.definition.module
+) @definition.module

aider/queries/tree-sitter-language-pack/gleam-tags.scm

@@ -0,0 +1,41 @@
+; Modules
+(module) @name.reference.module @reference.module
+(import alias: (identifier) @name.reference.module) @reference.module
+(remote_type_identifier
+  module: (identifier) @name.reference.module) @reference.module
+((field_access
+  record: (identifier) @name.reference.module)
+ (#is-not? local)) @reference.module
+
+; Functions
+(function
+  name: (identifier) @name.definition.function) @definition.function
+(external_function
+  name: (identifier) @name.definition.function) @definition.function
+(unqualified_import (identifier) @name.reference.function) @reference.function
+((function_call
+   function: (identifier) @name.reference.function) @reference.function
+ (#is-not? local))
+((field_access
+  record: (identifier) @ignore
+  field: (label) @name.reference.function)
+ (#is-not? local)) @reference.function
+((binary_expression
+   operator: "|>"
+   right: (identifier) @name.reference.function)
+ (#is-not? local)) @reference.function
+
+; Types
+(type_definition
+  (type_name
+    name: (type_identifier) @name.definition.type)) @definition.type
+(type_definition
+  (data_constructors
+    (data_constructor
+      name: (constructor_name) @name.definition.constructor))) @definition.constructor
+(external_type
+  (type_name
+    name: (type_identifier) @name.definition.type)) @definition.type
+
+(type_identifier) @name.reference.type @reference.type
+(constructor_name) @name.reference.constructor @reference.constructor

aider/queries/tree-sitter-language-pack/go-tags.scm

@@ -0,0 +1,42 @@
+(
+  (comment)* @doc
+  .
+  (function_declaration
+    name: (identifier) @name.definition.function) @definition.function
+  (#strip! @doc "^//\\s*")
+  (#set-adjacent! @doc @definition.function)
+)
+
+(
+  (comment)* @doc
+  .
+  (method_declaration
+    name: (field_identifier) @name.definition.method) @definition.method
+  (#strip! @doc "^//\\s*")
+  (#set-adjacent! @doc @definition.method)
+)
+
+(call_expression
+  function: [
+    (identifier) @name.reference.call
+    (parenthesized_expression (identifier) @name.reference.call)
+    (selector_expression field: (field_identifier) @name.reference.call)
+    (parenthesized_expression (selector_expression field: (field_identifier) @name.reference.call))
+  ]) @reference.call
+
+(type_spec
+  name: (type_identifier) @name.definition.type) @definition.type
+
+(type_identifier) @name.reference.type @reference.type
+
+(package_clause "package" (package_identifier) @name.definition.module)
+
+(type_declaration (type_spec name: (type_identifier) @name.definition.interface type: (interface_type)))
+
+(type_declaration (type_spec name: (type_identifier) @name.definition.class type: (struct_type)))
+
+(import_declaration (import_spec) @name.reference.module)
+
+(var_declaration (var_spec name: (identifier) @name.definition.variable))
+
+(const_declaration (const_spec name: (identifier) @name.definition.constant))

aider/queries/tree-sitter-language-pack/java-tags.scm

@@ -0,0 +1,20 @@
+(class_declaration
+  name: (identifier) @name.definition.class) @definition.class
+
+(method_declaration
+  name: (identifier) @name.definition.method) @definition.method
+
+(method_invocation
+  name: (identifier) @name.reference.method
+  arguments: (argument_list) @reference.call)
+
+(interface_declaration
+  name: (identifier) @name.definition.interface) @definition.interface
+
+(type_list
+  (type_identifier) @name.reference.interface) @reference.implementation
+
+(object_creation_expression
+  type: (type_identifier) @name.reference.class) @reference.class
+
+(superclass (type_identifier) @name.reference.class) @reference.class

aider/queries/tree-sitter-language-pack/javascript-tags.scm

@@ -0,0 +1,88 @@
+(
+  (comment)* @doc
+  .
+  (method_definition
+    name: (property_identifier) @name.definition.method) @definition.method
+  (#not-eq? @name.definition.method "constructor")
+  (#strip! @doc "^[\\s\\*/]+|^[\\s\\*/]$")
+  (#select-adjacent! @doc @definition.method)
+)
+
+(
+  (comment)* @doc
+  .
+  [
+    (class
+      name: (_) @name.definition.class)
+    (class_declaration
+      name: (_) @name.definition.class)
+  ] @definition.class
+  (#strip! @doc "^[\\s\\*/]+|^[\\s\\*/]$")
+  (#select-adjacent! @doc @definition.class)
+)
+
+(
+  (comment)* @doc
+  .
+  [
+    (function_expression
+      name: (identifier) @name.definition.function)
+    (function_declaration
+      name: (identifier) @name.definition.function)
+    (generator_function
+      name: (identifier) @name.definition.function)
+    (generator_function_declaration
+      name: (identifier) @name.definition.function)
+  ] @definition.function
+  (#strip! @doc "^[\\s\\*/]+|^[\\s\\*/]$")
+  (#select-adjacent! @doc @definition.function)
+)
+
+(
+  (comment)* @doc
+  .
+  (lexical_declaration
+    (variable_declarator
+      name: (identifier) @name.definition.function
+      value: [(arrow_function) (function_expression)]) @definition.function)
+  (#strip! @doc "^[\\s\\*/]+|^[\\s\\*/]$")
+  (#select-adjacent! @doc @definition.function)
+)
+
+(
+  (comment)* @doc
+  .
+  (variable_declaration
+    (variable_declarator
+      name: (identifier) @name.definition.function
+      value: [(arrow_function) (function_expression)]) @definition.function)
+  (#strip! @doc "^[\\s\\*/]+|^[\\s\\*/]$")
+  (#select-adjacent! @doc @definition.function)
+)
+
+(assignment_expression
+  left: [
+    (identifier) @name.definition.function
+    (member_expression
+      property: (property_identifier) @name.definition.function)
+  ]
+  right: [(arrow_function) (function_expression)]
+) @definition.function
+
+(pair
+  key: (property_identifier) @name.definition.function
+  value: [(arrow_function) (function_expression)]) @definition.function
+
+(
+  (call_expression
+    function: (identifier) @name.reference.call) @reference.call
+  (#not-match? @name.reference.call "^(require)$")
+)
+
+(call_expression
+  function: (member_expression
+    property: (property_identifier) @name.reference.call)
+  arguments: (_) @reference.call)
+
+(new_expression
+  constructor: (_) @name.reference.class) @reference.class

aider/queries/tree-sitter-language-pack/lua-tags.scm

@@ -0,0 +1,34 @@
+(function_declaration
+  name: [
+    (identifier) @name.definition.function
+    (dot_index_expression
+      field: (identifier) @name.definition.function)
+  ]) @definition.function
+
+(function_declaration
+  name: (method_index_expression
+    method: (identifier) @name.definition.method)) @definition.method
+
+(assignment_statement
+  (variable_list .
+    name: [
+      (identifier) @name.definition.function
+      (dot_index_expression
+        field: (identifier) @name.definition.function)
+    ])
+  (expression_list .
+    value: (function_definition))) @definition.function
+
+(table_constructor
+  (field
+    name: (identifier) @name.definition.function
+    value: (function_definition))) @definition.function
+
+(function_call
+  name: [
+    (identifier) @name.reference.call
+    (dot_index_expression
+      field: (identifier) @name.reference.call)
+    (method_index_expression
+      method: (identifier) @name.reference.method)
+  ]) @reference.call

aider/queries/tree-sitter-language-pack/pony-tags.scm

@@ -0,0 +1,39 @@
+;Class definitions 	@definition.class
+;Function definitions 	@definition.function
+;Interface definitions 	@definition.interface
+;Method definitions 	@definition.method
+;Module definitions 	@definition.module
+;Function/method calls 	@reference.call
+;Class reference 	@reference.class
+;Interface implementation 	@reference.implementation
+(
+  (identifier) @reference.class
+  (#match? @reference.class "^_*[A-Z][a-zA-Z0-9_]*$")
+)
+
+(class_definition (identifier) @name.definition.class) @definition.class
+(actor_definition (identifier) @name.definition.class) @definition.class
+(primitive_definition (identifier) @name.definition.class) @definition.class
+(struct_definition (identifier) @name.definition.class) @definition.class
+(type_alias (identifier) @name.definition.class) @definition.class
+
+(trait_definition (identifier) @name.definition.interface) @definition.interface
+(interface_definition (identifier) @name.definition.interface) @definition.interface
+
+(constructor (identifier) @name.definition.method) @definition.method
+(method (identifier) @name.definition.method) @definition.method
+(behavior (identifier) @name.definition.method) @definition.method
+
+(class_definition (type) @name.reference.implementation) @reference.implementation
+(actor_definition (type) @name.reference.implementation) @reference.implementation
+(primitive_definition (type) @name.reference.implementation) @reference.implementation
+(struct_definition (type) @name.reference.implementation) @reference.implementation
+(type_alias (type) @name.reference.implementation) @reference.implementation
+
+; calls - not catching all possible call cases of callees for capturing the method name
+(call_expression callee: [(identifier) (ffi_identifier)] @name.reference.call) @reference.call
+(call_expression callee: (generic_expression [(identifier) (ffi_identifier)] @name.reference.call)) @reference.call
+(call_expression callee: (member_expression (identifier) @name.reference.call .)) @reference.call
+(call_expression callee: (member_expression (generic_expression [(identifier) (ffi_identifier)] @name.reference.call) .)) @reference.call
+; TODO: add more possible callee expressions
+(call_expression) @reference.call

aider/queries/tree-sitter-language-pack/properties-tags.scm

@@ -0,0 +1,5 @@
+(property
+  (key) @name.definition.property) @definition.property
+
+(substitution
+  (key) @name.reference.property) @reference.property

aider/queries/tree-sitter-language-pack/python-tags.scm

@@ -0,0 +1,14 @@
+(module (expression_statement (assignment left: (identifier) @name.definition.constant) @definition.constant))
+
+(class_definition
+  name: (identifier) @name.definition.class) @definition.class
+
+(function_definition
+  name: (identifier) @name.definition.function) @definition.function
+
+(call
+  function: [
+      (identifier) @name.reference.call
+      (attribute
+        attribute: (identifier) @name.reference.call)
+  ]) @reference.call

aider/queries/tree-sitter-language-pack/r-tags.scm

@@ -0,0 +1,21 @@
+(binary_operator
+    lhs: (identifier) @name.definition.function
+    operator: "<-"
+    rhs: (function_definition)
+) @definition.function
+
+(binary_operator
+    lhs: (identifier) @name.definition.function
+    operator: "="
+    rhs: (function_definition)
+) @definition.function
+
+(call
+    function: (identifier) @name.reference.call
+) @reference.call
+
+(call
+    function: (namespace_operator
+        rhs: (identifier) @name.reference.call
+    )
+) @reference.call

aider/queries/tree-sitter-language-pack/racket-tags.scm

@@ -0,0 +1,12 @@
+(list
+  .
+  (symbol) @reference._define
+  (#match? @reference._define "^(define|define/contract)$")
+  .
+  (list
+    .
+    (symbol) @name.definition.function) @definition.function)
+
+(list
+  .
+  (symbol) @name.reference.call)

aider/queries/tree-sitter-language-pack/rust-tags.scm

@@ -0,0 +1,60 @@
+; ADT definitions
+
+(struct_item
+    name: (type_identifier) @name.definition.class) @definition.class
+
+(enum_item
+    name: (type_identifier) @name.definition.class) @definition.class
+
+(union_item
+    name: (type_identifier) @name.definition.class) @definition.class
+
+; type aliases
+
+(type_item
+    name: (type_identifier) @name.definition.class) @definition.class
+
+; method definitions
+
+(declaration_list
+    (function_item
+        name: (identifier) @name.definition.method) @definition.method)
+
+; function definitions
+
+(function_item
+    name: (identifier) @name.definition.function) @definition.function
+
+; trait definitions
+(trait_item
+    name: (type_identifier) @name.definition.interface) @definition.interface
+
+; module definitions
+(mod_item
+    name: (identifier) @name.definition.module) @definition.module
+
+; macro definitions
+
+(macro_definition
+    name: (identifier) @name.definition.macro) @definition.macro
+
+; references
+
+(call_expression
+    function: (identifier) @name.reference.call) @reference.call
+
+(call_expression
+    function: (field_expression
+        field: (field_identifier) @name.reference.call)) @reference.call
+
+(macro_invocation
+    macro: (identifier) @name.reference.call) @reference.call
+
+; implementations
+
+(impl_item
+    trait: (type_identifier) @name.reference.implementation) @reference.implementation
+
+(impl_item
+    type: (type_identifier) @name.reference.implementation
+    !trait) @reference.implementation

aider/queries/tree-sitter-language-pack/solidity-tags.scm

@@ -0,0 +1,43 @@
+;; Method and Function declarations
+(contract_declaration (_
+    (function_definition
+        name: (identifier) @name.definition.function) @definition.method))
+
+(source_file
+    (function_definition
+        name: (identifier) @name.definition.function) @definition.function)
+
+;; Contract, struct, enum and interface declarations
+(contract_declaration
+  name: (identifier) @name.definition.class) @definition.class
+
+(interface_declaration
+  name: (identifier) @name.definition.interface) @definition.interface
+
+(library_declaration
+  name: (identifier) @name.definition.class) @definition.interface
+
+(struct_declaration name: (identifier) @name.definition.class) @definition.class
+(enum_declaration name: (identifier) @name.definition.class) @definition.class
+(event_definition name: (identifier) @name.definition.class) @definition.class
+
+;; Function calls
+(call_expression (expression (identifier)) @name.reference.call ) @reference.call
+
+(call_expression
+    (expression (member_expression
+        property: (_) @name.reference.method ))) @reference.call
+
+;; Log emit
+(emit_statement name: (_) @name.reference.class) @reference.class
+
+
+;; Inheritance
+
+(inheritance_specifier
+    ancestor: (user_defined_type (_) @name.reference.class . )) @reference.class
+
+
+;; Imports ( note that unknown is not standardised )
+(import_directive
+  import_name: (_) @name.reference.module ) @reference.unknown

aider/queries/tree-sitter-language-pack/swift-tags.scm

@@ -0,0 +1,51 @@
+(class_declaration
+  name: (type_identifier) @name.definition.class) @definition.class
+
+(protocol_declaration
+  name: (type_identifier) @name.definition.interface) @definition.interface
+
+(class_declaration
+    (class_body
+        [
+            (function_declaration
+                name: (simple_identifier) @name.definition.method
+            )
+            (subscript_declaration
+                (parameter (simple_identifier) @name.definition.method)
+            )
+            (init_declaration "init" @name.definition.method)
+            (deinit_declaration "deinit" @name.definition.method)
+        ]
+    )
+) @definition.method
+
+(protocol_declaration
+    (protocol_body
+        [
+            (protocol_function_declaration
+                name: (simple_identifier) @name.definition.method
+            )
+            (subscript_declaration
+                (parameter (simple_identifier) @name.definition.method)
+            )
+            (init_declaration "init" @name.definition.method)
+        ]
+    )
+) @definition.method
+
+(class_declaration
+    (class_body
+        [
+            (property_declaration
+                (pattern (simple_identifier) @name.definition.property)
+            )
+        ]
+    )
+) @definition.property
+
+(property_declaration
+    (pattern (simple_identifier) @name.definition.property)
+) @definition.property
+
+(function_declaration
+    name: (simple_identifier) @name.definition.function) @definition.function

aider/queries/tree-sitter-language-pack/udev-tags.scm

@@ -0,0 +1,20 @@
+(assignment
+  key: "LABEL"
+  (value
+    (content) @name.definition.label)) @definition.label
+
+(assignment
+  key: "GOTO"
+  (value
+    (content) @name.reference.label)) @reference.label
+
+(assignment
+  key: "ENV"
+  (env_var) @name.definition.variable) @definition.variable
+
+(match
+  key: "ENV"
+  (env_var) @name.reference.variable) @reference.variable
+
+(var_sub
+  (env_var) @name.reference.variable) @reference.variable

aider/queries/tree-sitter-languages/c-tags.scm

@@ -0,0 +1,9 @@
+(struct_specifier name: (type_identifier) @name.definition.class body:(_)) @definition.class
+
+(declaration type: (union_specifier name: (type_identifier) @name.definition.class)) @definition.class
+
+(function_declarator declarator: (identifier) @name.definition.function) @definition.function
+
+(type_definition declarator: (type_identifier) @name.definition.type) @definition.type
+
+(enum_specifier name: (type_identifier) @name.definition.type) @definition.type

aider/queries/tree-sitter-languages/hcl-tags.scm

@@ -0,0 +1,77 @@
+;; Based on https://github.com/tree-sitter-grammars/tree-sitter-hcl/blob/main/make_grammar.js
+;; Which has Apache 2.0 License
+;; tags.scm for Terraform (tree-sitter-hcl)
+
+; === Definitions: Terraform Blocks ===
+(block 
+  (identifier) @block_type
+  (string_lit (template_literal) @resource_type)
+  (string_lit (template_literal) @name.definition.resource)
+  (body) @definition.resource
+) (#eq? @block_type "resource")
+
+(block 
+  (identifier) @block_type
+  (string_lit (template_literal) @name.definition.module)
+  (body) @definition.module
+) (#eq? @block_type "module")
+
+(block 
+  (identifier) @block_type
+  (string_lit (template_literal) @name.definition.variable)
+  (body) @definition.variable
+) (#eq? @block_type "variable")
+
+(block 
+  (identifier) @block_type
+  (string_lit (template_literal) @name.definition.output)
+  (body) @definition.output
+) (#eq? @block_type "output")
+
+(block 
+  (identifier) @block_type
+  (string_lit (template_literal) @name.definition.provider)
+  (body) @definition.provider
+) (#eq? @block_type "provider")
+
+(block 
+  (identifier) @block_type
+  (body 
+    (attribute 
+       (identifier) @name.definition.local 
+       (expression) @definition.local
+    )+
+  )
+) (#eq? @block_type "locals")
+
+; === References: Variables, Locals, Modules, Data, Resources ===
+((variable_expr) @ref_type
+  (get_attr (identifier) @name.reference.variable)
+) @reference.variable
+ (#eq? @ref_type "var")
+
+((variable_expr) @ref_type
+  (get_attr (identifier) @name.reference.local)
+) @reference.local
+ (#eq? @ref_type "local")
+
+((variable_expr) @ref_type
+  (get_attr (identifier) @name.reference.module)
+) @reference.module
+ (#eq? @ref_type "module")
+
+((variable_expr) @ref_type
+  (get_attr (identifier) @data_source_type)
+  (get_attr (identifier) @name.reference.data)
+) @reference.data
+ (#eq? @ref_type "data")
+
+((variable_expr) @resource_type
+  (get_attr (identifier) @name.reference.resource)
+) @reference.resource
+ (#not-eq? @resource_type "var")
+ (#not-eq? @resource_type "local")
+ (#not-eq? @resource_type "module")
+ (#not-eq? @resource_type "data")
+ (#not-eq? @resource_type "provider")
+ (#not-eq? @resource_type "output")

aider/queries/tree-sitter-languages/ruby-tags.scm

@@ -0,0 +1,64 @@
+; Method definitions
+
+(
+  (comment)* @doc
+  .
+  [
+    (method
+      name: (_) @name.definition.method) @definition.method
+    (singleton_method
+      name: (_) @name.definition.method) @definition.method
+  ]
+  (#strip! @doc "^#\\s*")
+  (#select-adjacent! @doc @definition.method)
+)
+
+(alias
+  name: (_) @name.definition.method) @definition.method
+
+(setter
+  (identifier) @ignore)
+
+; Class definitions
+
+(
+  (comment)* @doc
+  .
+  [
+    (class
+      name: [
+        (constant) @name.definition.class
+        (scope_resolution
+          name: (_) @name.definition.class)
+      ]) @definition.class
+    (singleton_class
+      value: [
+        (constant) @name.definition.class
+        (scope_resolution
+          name: (_) @name.definition.class)
+      ]) @definition.class
+  ]
+  (#strip! @doc "^#\\s*")
+  (#select-adjacent! @doc @definition.class)
+)
+
+; Module definitions
+
+(
+  (module
+    name: [
+      (constant) @name.definition.module
+      (scope_resolution
+        name: (_) @name.definition.module)
+    ]) @definition.module
+)
+
+; Calls
+
+(call method: (identifier) @name.reference.call) @reference.call
+
+(
+  [(identifier) (constant)] @name.reference.call @reference.call
+  (#is-not? local)
+  (#not-match? @name.reference.call "^(lambda|load|require|require_relative|__FILE__|__LINE__)$")
+)

aider/reasoning_tags.py

@@ -0,0 +1,82 @@
+#!/usr/bin/env python
+
+import re
+
+from aider.dump import dump  # noqa
+
+# Standard tag identifier
+REASONING_TAG = "thinking-content-" + "7bbeb8e1441453ad999a0bbba8a46d4b"
+# Output formatting
+REASONING_START = "--------------\n► **THINKING**"
+REASONING_END = "------------\n► **ANSWER**"
+
+
+def remove_reasoning_content(res, reasoning_tag):
+    """
+    Remove reasoning content from text based on tags.
+
+    Args:
+        res (str): The text to process
+        reasoning_tag (str): The tag name to remove
+
+    Returns:
+        str: Text with reasoning content removed
+    """
+    if not reasoning_tag:
+        return res
+
+    # Try to match the complete tag pattern first
+    pattern = f"<{reasoning_tag}>.*?</{reasoning_tag}>"
+    res = re.sub(pattern, "", res, flags=re.DOTALL).strip()
+
+    # If closing tag exists but opening tag might be missing, remove everything before closing
+    # tag
+    closing_tag = f"</{reasoning_tag}>"
+    if closing_tag in res:
+        # Split on the closing tag and keep everything after it
+        parts = res.split(closing_tag, 1)
+        res = parts[1].strip() if len(parts) > 1 else res
+
+    return res
+
+
+def replace_reasoning_tags(text, tag_name):
+    """
+    Replace opening and closing reasoning tags with standard formatting.
+    Ensures exactly one blank line before START and END markers.
+
+    Args:
+        text (str): The text containing the tags
+        tag_name (str): The name of the tag to replace
+
+    Returns:
+        str: Text with reasoning tags replaced with standard format
+    """
+    if not text:
+        return text
+
+    # Replace opening tag with proper spacing
+    text = re.sub(f"\\s*<{tag_name}>\\s*", f"\n{REASONING_START}\n\n", text)
+
+    # Replace closing tag with proper spacing
+    text = re.sub(f"\\s*</{tag_name}>\\s*", f"\n\n{REASONING_END}\n\n", text)
+
+    return text
+
+
+def format_reasoning_content(reasoning_content, tag_name):
+    """
+    Format reasoning content with appropriate tags.
+
+    Args:
+        reasoning_content (str): The content to format
+        tag_name (str): The tag name to use
+
+    Returns:
+        str: Formatted reasoning content with tags
+    """
+    if not reasoning_content:
+        return ""
+
+    formatted = f"<{tag_name}>\n\n{reasoning_content}\n\n</{tag_name}>"
+    return formatted

aider/repo.py

@@ -17,7 +17,6 @@ except ImportError:
 import pathspec
 
 from aider import prompts, utils
-from aider.sendchat import simple_send_with_retries
 
 from .dump import dump  # noqa: F401
 
@@ -29,6 +28,7 @@ ANY_GIT_ERROR += [
     ValueError,
     AttributeError,
     AssertionError,
+    TimeoutError,
 ]
 ANY_GIT_ERROR = tuple(ANY_GIT_ERROR)
 
@@ -145,7 +145,7 @@ class GitRepo:
         else:
             cmd += ["-a"]
 
-        original_user_name = self.repo.config_reader().get_value("user", "name")
+        original_user_name = self.repo.git.config("--get", "user.name")
         original_committer_name_env = os.environ.get("GIT_COMMITTER_NAME")
         committer_name = f"{original_user_name} (aider)"
 
@@ -153,7 +153,7 @@ class GitRepo:
             os.environ["GIT_COMMITTER_NAME"] = committer_name
 
         if aider_edits and self.attribute_author:
-            original_auther_name_env = os.environ.get("GIT_AUTHOR_NAME")
+            original_author_name_env = os.environ.get("GIT_AUTHOR_NAME")
             os.environ["GIT_AUTHOR_NAME"] = committer_name
 
         try:
@@ -173,8 +173,8 @@ class GitRepo:
                     del os.environ["GIT_COMMITTER_NAME"]
 
             if aider_edits and self.attribute_author:
-                if original_auther_name_env is not None:
+                if original_author_name_env is not None:
-                    os.environ["GIT_AUTHOR_NAME"] = original_auther_name_env
+                    os.environ["GIT_AUTHOR_NAME"] = original_author_name_env
                 else:
                     del os.environ["GIT_AUTHOR_NAME"]
 
@@ -204,7 +204,7 @@ class GitRepo:
             max_tokens = model.info.get("max_input_tokens") or 0
             if max_tokens and num_tokens > max_tokens:
                 continue
-            commit_message = simple_send_with_retries(model, messages)
+            commit_message = model.simple_send_with_retries(messages)
             if commit_message:
                 break
 
@@ -309,8 +309,11 @@ class GitRepo:
 
         # Add staged files
         index = self.repo.index
-        staged_files = [path for path, _ in index.entries.keys()]
+        try:
-        files.update(self.normalize_path(path) for path in staged_files)
+            staged_files = [path for path, _ in index.entries.keys()]
+            files.update(self.normalize_path(path) for path in staged_files)
+        except ANY_GIT_ERROR as err:
+            self.io.tool_error(f"Unable to read staged files: {err}")
 
         res = [fname for fname in files if not self.ignored_file(fname)]
 

aider/repomap.py

@@ -23,7 +23,7 @@ from aider.utils import Spinner
 
 # tree_sitter is throwing a FutureWarning
 warnings.simplefilter("ignore", category=FutureWarning)
-from tree_sitter_languages import get_language, get_parser  # noqa: E402
+from grep_ast.tsl import USING_TSL_PACK, get_language, get_parser  # noqa: E402
 
 Tag = namedtuple("Tag", "rel_fname fname line name kind".split())
 
@@ -31,8 +31,12 @@ Tag = namedtuple("Tag", "rel_fname fname line name kind".split())
 SQLITE_ERRORS = (sqlite3.OperationalError, sqlite3.DatabaseError, OSError)
 
 
+CACHE_VERSION = 3
+if USING_TSL_PACK:
+    CACHE_VERSION = 4
+
+
 class RepoMap:
-    CACHE_VERSION = 3
     TAGS_CACHE_DIR = f".aider.tags.cache.v{CACHE_VERSION}"
 
     warned_files = set()
@@ -282,10 +286,15 @@ class RepoMap:
         query = language.query(query_scm)
         captures = query.captures(tree.root_node)
 
-        captures = list(captures)
-
         saw = set()
-        for node, tag in captures:
+        if USING_TSL_PACK:
+            all_nodes = []
+            for tag, nodes in captures.items():
+                all_nodes += [(node, tag) for node in nodes]
+        else:
+            all_nodes = list(captures)
+
+        for node, tag in all_nodes:
             if tag.startswith("name.definition."):
                 kind = "def"
             elif tag.startswith("name.reference."):
@@ -422,6 +431,15 @@ class RepoMap:
 
         G = nx.MultiDiGraph()
 
+        # Add a small self-edge for every definition that has no references
+        # Helps with tree-sitter 0.23.2 with ruby, where "def greet(name)"
+        # isn't counted as a def AND a ref. tree-sitter 0.24.0 does.
+        for ident in defines.keys():
+            if ident in references:
+                continue
+            for definer in defines[ident]:
+                G.add_edge(definer, definer, weight=0.1, ident=ident)
+
         for ident in idents:
             if progress:
                 progress()
@@ -732,8 +750,27 @@ def get_random_color():
 
 def get_scm_fname(lang):
     # Load the tags queries
+    if USING_TSL_PACK:
+        subdir = "tree-sitter-language-pack"
+        try:
+            path = resources.files(__package__).joinpath(
+                "queries",
+                subdir,
+                f"{lang}-tags.scm",
+            )
+            if path.exists():
+                return path
+        except KeyError:
+            pass
+
+    # Fall back to tree-sitter-languages
+    subdir = "tree-sitter-languages"
     try:
-        return resources.files(__package__).joinpath("queries", f"tree-sitter-{lang}-tags.scm")
+        return resources.files(__package__).joinpath(
+            "queries",
+            subdir,
+            f"{lang}-tags.scm",
+        )
     except KeyError:
         return
 

aider/resources/model-metadata.json

@@ -47,6 +47,22 @@
         //"supports_tool_choice": true,
         "supports_prompt_caching": true
     },
+    "openrouter/deepseek/deepseek-chat:free": {
+        "max_tokens": 8192,
+        "max_input_tokens": 64000,
+        "max_output_tokens": 8192,
+        "input_cost_per_token": 0.0,
+        "input_cost_per_token_cache_hit": 0.0,
+        "cache_read_input_token_cost": 0.00,
+        "cache_creation_input_token_cost": 0.0,
+        "output_cost_per_token": 0.0,
+        "litellm_provider": "openrouter",
+        "mode": "chat",
+        //"supports_function_calling": true, 
+        "supports_assistant_prefill": true,
+        //"supports_tool_choice": true,
+        "supports_prompt_caching": true
+    },
     "fireworks_ai/accounts/fireworks/models/deepseek-r1": {
         "max_tokens": 160000,
         "max_input_tokens": 128000,
@@ -81,4 +97,148 @@
         "supports_system_messages": true,
         "supports_response_schema": true
     },
+    "openrouter/openai/o3-mini": {
+        "max_tokens": 100000,
+        "max_input_tokens": 200000,
+        "max_output_tokens": 100000,
+        "input_cost_per_token": 0.0000011,
+        "output_cost_per_token": 0.0000044,
+        "cache_read_input_token_cost": 0.00000055,
+        "litellm_provider": "openrouter",
+        "mode": "chat",
+        "supports_function_calling": true,
+        "supports_parallel_function_calling": true,
+        "supports_vision": true,
+        "supports_prompt_caching": true,
+        "supports_system_messages": true,
+        "supports_response_schema": true
+    },
+    "openrouter/openai/o3-mini-high": {
+        "max_tokens": 100000,
+        "max_input_tokens": 200000,
+        "max_output_tokens": 100000,
+        "input_cost_per_token": 0.0000011,
+        "output_cost_per_token": 0.0000044,
+        "cache_read_input_token_cost": 0.00000055,
+        "litellm_provider": "openrouter",
+        "mode": "chat",
+        "supports_function_calling": true,
+        "supports_parallel_function_calling": true,
+        "supports_vision": true,
+        "supports_prompt_caching": true,
+        "supports_system_messages": true,
+        "supports_response_schema": true
+    },
+    "openrouter/openai/gpt-4o-mini": {
+        "max_tokens": 16384,
+        "max_input_tokens": 128000,
+        "max_output_tokens": 16384,
+        "input_cost_per_token": 0.00000015,
+        "output_cost_per_token": 0.00000060,
+        "input_cost_per_token_batches": 0.000000075,
+        "output_cost_per_token_batches": 0.00000030,
+        "cache_read_input_token_cost": 0.000000075,
+        "litellm_provider": "openrouter",
+        "mode": "chat",
+        "supports_function_calling": true,
+        "supports_parallel_function_calling": true,
+        "supports_response_schema": true,
+        "supports_vision": true,
+        "supports_prompt_caching": true,
+        "supports_system_messages": true
+    },
+    "claude-3-7-sonnet-20250219": {
+        "max_tokens": 8192,
+        "max_input_tokens": 200000,
+        "max_output_tokens": 8192,
+        "input_cost_per_token": 0.000003,
+        "output_cost_per_token": 0.000015,
+        "cache_creation_input_token_cost": 0.00000375,
+        "cache_read_input_token_cost": 0.0000003,
+        "litellm_provider": "anthropic",
+        "mode": "chat",
+        "supports_function_calling": true,
+        "supports_vision": true,
+        "tool_use_system_prompt_tokens": 159,
+        "supports_assistant_prefill": true,
+        "supports_pdf_input": true,
+        "supports_prompt_caching": true,
+        "supports_response_schema": true,
+        "deprecation_date": "2025-10-01",
+        "supports_tool_choice": true
+    },
+    "anthropic/claude-3-7-sonnet-20250219": {
+        "max_tokens": 8192,
+        "max_input_tokens": 200000,
+        "max_output_tokens": 8192,
+        "input_cost_per_token": 0.000003,
+        "output_cost_per_token": 0.000015,
+        "cache_creation_input_token_cost": 0.00000375,
+        "cache_read_input_token_cost": 0.0000003,
+        "litellm_provider": "anthropic",
+        "mode": "chat",
+        "supports_function_calling": true,
+        "supports_vision": true,
+        "tool_use_system_prompt_tokens": 159,
+        "supports_assistant_prefill": true,
+        "supports_pdf_input": true,
+        "supports_prompt_caching": true,
+        "supports_response_schema": true,
+        "deprecation_date": "2025-10-01",
+        "supports_tool_choice": true
+    },
+    "openrouter/anthropic/claude-3.7-sonnet": {
+        "max_tokens": 8192,
+        "max_input_tokens": 200000,
+        "max_output_tokens": 8192,
+        "input_cost_per_token": 0.000003,
+        "output_cost_per_token": 0.000015,
+        "cache_creation_input_token_cost": 0.00000375,
+        "cache_read_input_token_cost": 0.0000003,
+        "litellm_provider": "openrouter",
+        "mode": "chat",
+        "supports_function_calling": true,
+        "supports_vision": true,
+        "tool_use_system_prompt_tokens": 159,
+        "supports_assistant_prefill": true,
+        "supports_pdf_input": true,
+        "supports_prompt_caching": true,
+        "supports_response_schema": true,
+        "deprecation_date": "2025-10-01",
+        "supports_tool_choice": true
+    },
+    "gpt-4.5-preview": {
+        "max_tokens": 16384,
+        "max_input_tokens": 128000,
+        "max_output_tokens": 16384,
+        "input_cost_per_token": 0.000075,
+        "output_cost_per_token": 0.00015,
+        "cache_read_input_token_cost": 0.0000375,
+        "litellm_provider": "openai",
+        "mode": "chat",
+        "supports_function_calling": true,
+        "supports_parallel_function_calling": true,
+        "supports_response_schema": true,
+        "supports_vision": true,
+        "supports_prompt_caching": true,
+        "supports_system_messages": true,
+        "supports_tool_choice": true
+    },
+    "openai/gpt-4.5-preview": {
+        "max_tokens": 16384,
+        "max_input_tokens": 128000,
+        "max_output_tokens": 16384,
+        "input_cost_per_token": 0.000075,
+        "output_cost_per_token": 0.00015,
+        "cache_read_input_token_cost": 0.0000375,
+        "litellm_provider": "openai",
+        "mode": "chat",
+        "supports_function_calling": true,
+        "supports_parallel_function_calling": true,
+        "supports_response_schema": true,
+        "supports_vision": true,
+        "supports_prompt_caching": true,
+        "supports_system_messages": true,
+        "supports_tool_choice": true
+    },
 }

aider/resources/model-settings.yml

@@ -184,6 +184,156 @@
   editor_model_name: anthropic/claude-3-5-sonnet-20241022
   editor_edit_format: editor-diff
 
+- name: anthropic/claude-3-7-sonnet-20250219
+  edit_format: diff
+  weak_model_name: anthropic/claude-3-5-haiku-20241022
+  use_repo_map: true
+  examples_as_sys_msg: true
+  extra_params:
+    extra_headers:
+      anthropic-beta: prompt-caching-2024-07-31,pdfs-2024-09-25,output-128k-2025-02-19
+    max_tokens: 64000
+  cache_control: true
+  editor_model_name: anthropic/claude-3-7-sonnet-20250219
+  editor_edit_format: editor-diff
+
+- name: anthropic/claude-3-7-sonnet-latest
+  edit_format: diff
+  weak_model_name: anthropic/claude-3-5-haiku-20241022
+  use_repo_map: true
+  examples_as_sys_msg: true
+  extra_params:
+    extra_headers:
+      anthropic-beta: prompt-caching-2024-07-31,pdfs-2024-09-25,output-128k-2025-02-19
+    max_tokens: 64000
+  cache_control: true
+  editor_model_name: anthropic/claude-3-7-sonnet-latest
+  editor_edit_format: editor-diff
+
+- name: claude-3-7-sonnet-20250219
+  edit_format: diff
+  weak_model_name: claude-3-5-haiku-20241022
+  use_repo_map: true
+  examples_as_sys_msg: true
+  extra_params:
+    extra_headers:
+      anthropic-beta: prompt-caching-2024-07-31,pdfs-2024-09-25,output-128k-2025-02-19
+    max_tokens: 64000
+  cache_control: true
+  editor_model_name: claude-3-7-sonnet-20250219
+  editor_edit_format: editor-diff
+
+- name: claude-3-7-sonnet-latest
+  edit_format: diff
+  weak_model_name: claude-3-5-haiku-20241022
+  use_repo_map: true
+  examples_as_sys_msg: true
+  extra_params:
+    extra_headers:
+      anthropic-beta: prompt-caching-2024-07-31,pdfs-2024-09-25,output-128k-2025-02-19
+    max_tokens: 64000
+  cache_control: true
+  editor_model_name: claude-3-7-sonnet-latest
+  editor_edit_format: editor-diff
+
+- name: bedrock/anthropic.claude-3-7-sonnet-20250219-v1:0
+  edit_format: diff
+  weak_model_name: bedrock/anthropic.claude-3-5-haiku-20241022-v1:0
+  use_repo_map: true
+  examples_as_sys_msg: true
+  extra_params:
+    extra_headers:
+      anthropic-beta: prompt-caching-2024-07-31,pdfs-2024-09-25,output-128k-2025-02-19
+    max_tokens: 64000
+  cache_control: true
+  editor_model_name: bedrock/anthropic.claude-3-7-sonnet-20250219-v1:0
+  editor_edit_format: editor-diff
+
+- name: bedrock/us.anthropic.claude-3-7-sonnet-20250219-v1:0
+  edit_format: diff
+  weak_model_name: bedrock/us.anthropic.claude-3-5-haiku-20241022-v1:0
+  use_repo_map: true
+  examples_as_sys_msg: true
+  extra_params:
+    extra_headers:
+      anthropic-beta: prompt-caching-2024-07-31,pdfs-2024-09-25,output-128k-2025-02-19
+    max_tokens: 64000
+  cache_control: true
+  editor_model_name: bedrock/us.anthropic.claude-3-7-sonnet-20250219-v1:0
+  editor_edit_format: editor-diff
+
+- name: bedrock_converse/anthropic.claude-3-7-sonnet-20250219-v1:0
+  edit_format: diff
+  weak_model_name: bedrock_converse/anthropic.claude-3-5-haiku-20241022-v1:0
+  use_repo_map: true
+  examples_as_sys_msg: true
+  extra_params:
+    extra_headers:
+      anthropic-beta: prompt-caching-2024-07-31,pdfs-2024-09-25,output-128k-2025-02-19
+    max_tokens: 64000
+  cache_control: true
+  editor_model_name: bedrock_converse/anthropic.claude-3-7-sonnet-20250219-v1:0
+  editor_edit_format: editor-diff
+
+- name: bedrock_converse/us.anthropic.claude-3-7-sonnet-20250219-v1:0
+  edit_format: diff
+  weak_model_name: bedrock_converse/us.anthropic.claude-3-5-haiku-20241022-v1:0
+  use_repo_map: true
+  examples_as_sys_msg: true
+  extra_params:
+    extra_headers:
+      anthropic-beta: prompt-caching-2024-07-31,pdfs-2024-09-25,output-128k-2025-02-19
+    max_tokens: 64000
+  cache_control: true
+  editor_model_name: bedrock_converse/us.anthropic.claude-3-7-sonnet-20250219-v1:0
+  editor_edit_format: editor-diff
+
+- name: vertex_ai/claude-3-7-sonnet@20250219
+  edit_format: diff
+  weak_model_name: vertex_ai/claude-3-5-haiku@20241022
+  use_repo_map: true
+  examples_as_sys_msg: true
+  extra_params:
+    max_tokens: 64000
+  editor_model_name: vertex_ai/claude-3-7-sonnet@20250219
+  editor_edit_format: editor-diff
+
+- name: vertex_ai-anthropic_models/vertex_ai/claude-3-7-sonnet@20250219
+  edit_format: diff
+  weak_model_name: vertex_ai/claude-3-5-haiku@20241022
+  use_repo_map: true
+  examples_as_sys_msg: true
+  extra_params:
+    max_tokens: 64000
+  editor_model_name: vertex_ai-anthropic_models/vertex_ai/claude-3-7-sonnet@20250219
+  editor_edit_format: editor-diff
+
+- name: openrouter/anthropic/claude-3.7-sonnet
+  edit_format: diff
+  weak_model_name: openrouter/anthropic/claude-3-5-haiku
+  use_repo_map: true
+  examples_as_sys_msg: true
+  extra_params:
+    extra_headers:
+      anthropic-beta: prompt-caching-2024-07-31,pdfs-2024-09-25,output-128k-2025-02-19
+    max_tokens: 64000
+  cache_control: true
+  editor_model_name: openrouter/anthropic/claude-3.7-sonnet
+  editor_edit_format: editor-diff
+
+- name: openrouter/anthropic/claude-3.7-sonnet:beta
+  edit_format: diff
+  weak_model_name: openrouter/anthropic/claude-3-5-haiku
+  use_repo_map: true
+  examples_as_sys_msg: true
+  extra_params:
+    extra_headers:
+      anthropic-beta: prompt-caching-2024-07-31,pdfs-2024-09-25,output-128k-2025-02-19
+    max_tokens: 64000
+  cache_control: true
+  editor_model_name: openrouter/anthropic/claude-3.7-sonnet
+  editor_edit_format: editor-diff
+
 - name: bedrock/anthropic.claude-3-5-sonnet-20241022-v2:0
   edit_format: diff
   weak_model_name: bedrock/anthropic.claude-3-5-haiku-20241022-v1:0
@@ -386,6 +536,10 @@
   edit_format: diff
   use_repo_map: true
 
+- name: gemini/gemini-2.0-flash
+  edit_format: diff
+  use_repo_map: true
+
 - name: openrouter/deepseek/deepseek-r1
   edit_format: diff
   weak_model_name: openrouter/deepseek/deepseek-chat
@@ -393,21 +547,21 @@
   examples_as_sys_msg: true
   extra_params:
     max_tokens: 8192
+    include_reasoning: true
   caches_by_default: true
-  use_temperature: false
   editor_model_name: openrouter/deepseek/deepseek-chat
   editor_edit_format: editor-diff
 
 - name: openrouter/deepseek/deepseek-r1:free
   edit_format: diff
-  weak_model_name: openrouter/deepseek/deepseek-chat:free
+  weak_model_name: openrouter/deepseek/deepseek-r1:free
   use_repo_map: true
   examples_as_sys_msg: true
   extra_params:
     max_tokens: 8192
   caches_by_default: true
   use_temperature: false
-  editor_model_name: openrouter/deepseek/deepseek-chat:free
+  editor_model_name: openrouter/deepseek/deepseek-r1:free
   editor_edit_format: editor-diff
 
 - name: deepseek/deepseek-reasoner
@@ -431,6 +585,18 @@
     max_tokens: 8192
   caches_by_default: true
 
+- name: openrouter/deepseek/deepseek-chat:free
+  edit_format: diff
+  weak_model_name: openrouter/deepseek/deepseek-chat:free
+  use_repo_map: true
+  examples_as_sys_msg: true
+  extra_params:
+    max_tokens: 8192
+  caches_by_default: true
+  use_temperature: false
+  editor_model_name: openrouter/deepseek/deepseek-chat:free
+  editor_edit_format: editor-diff
+
 - name: deepseek/deepseek-coder
   edit_format: diff
   use_repo_map: true
@@ -565,6 +731,7 @@
   streaming: false
   editor_model_name: openrouter/openai/gpt-4o
   editor_edit_format: editor-diff
+  system_prompt_prefix: "Formatting re-enabled. "
 
 - name: openai/o1
   edit_format: diff
@@ -574,6 +741,7 @@
   streaming: false
   editor_model_name: openai/gpt-4o
   editor_edit_format: editor-diff
+  system_prompt_prefix: "Formatting re-enabled. "
 
 - name: o1
   edit_format: diff
@@ -583,6 +751,7 @@
   streaming: false
   editor_model_name: gpt-4o
   editor_edit_format: editor-diff
+  system_prompt_prefix: "Formatting re-enabled. "
 
 - name: openrouter/qwen/qwen-2.5-coder-32b-instruct
   edit_format: diff
@@ -611,7 +780,7 @@
   streaming: true
   editor_model_name: fireworks_ai/accounts/fireworks/models/deepseek-v3
   editor_edit_format: editor-diff
-  remove_reasoning: think
+  reasoning_tag: think
   extra_params:
       max_tokens: 160000
 
@@ -630,6 +799,7 @@
   use_temperature: false
   editor_model_name: gpt-4o
   editor_edit_format: editor-diff
+  system_prompt_prefix: "Formatting re-enabled. "
   
 - name: o3-mini
   edit_format: diff
@@ -638,4 +808,93 @@
   use_temperature: false
   editor_model_name: gpt-4o
   editor_edit_format: editor-diff
+  system_prompt_prefix: "Formatting re-enabled. "
+
+- name: openrouter/openai/o3-mini
+  edit_format: diff
+  weak_model_name: openrouter/openai/gpt-4o-mini
+  use_repo_map: true
+  use_temperature: false
+  editor_model_name: openrouter/openai/gpt-4o
+  editor_edit_format: editor-diff
+  system_prompt_prefix: "Formatting re-enabled. "
+
+- name: openrouter/openai/o3-mini-high
+  edit_format: diff
+  weak_model_name: openrouter/openai/gpt-4o-mini
+  use_repo_map: true
+  use_temperature: false
+  editor_model_name: openrouter/openai/gpt-4o
+  editor_edit_format: editor-diff
+  system_prompt_prefix: "Formatting re-enabled. "
+
+- name: azure/o3-mini
+  edit_format: diff
+  weak_model_name: azure/gpt-4o-mini
+  use_repo_map: true
+  use_temperature: false
+  editor_model_name: azure/gpt-4o
+  editor_edit_format: editor-diff
+  system_prompt_prefix: "Formatting re-enabled. "
+
+- name: gpt-4.5-preview
+  edit_format: diff
+  weak_model_name: gpt-4o-mini
+  use_repo_map: true
+  lazy: true
+  reminder: sys
+  examples_as_sys_msg: true
+  editor_model_name: gpt-4o
+  editor_edit_format: editor-diff
+  
+- name: openai/gpt-4.5-preview
+  edit_format: diff
+  weak_model_name: gpt-4o-mini
+  use_repo_map: true
+  lazy: true
+  reminder: sys
+  examples_as_sys_msg: true
+  editor_model_name: openai/gpt-4o
+  editor_edit_format: editor-diff
+
+- name: fireworks_ai/accounts/fireworks/models/qwq-32b
+  reasoning_tag: think
+  edit_format: diff
+  weak_model_name: fireworks_ai/accounts/fireworks/models/qwen2p5-coder-32b-instruct
+  use_repo_map: true
+  editor_model_name: fireworks_ai/accounts/fireworks/models/qwen2p5-coder-32b-instruct
+  editor_edit_format: editor-diff
+  reminder: user
+  examples_as_sys_msg: true
+  use_temperature: 0.6
+  extra_params:
+      max_tokens: 32000
+      top_p: 0.95
+
+- name: groq/qwen-qwq-32b
+  reasoning_tag: think
+  edit_format: diff
+  weak_model_name: groq/qwen-2.5-coder-32b
+  use_repo_map: true
+  editor_model_name: groq/qwen-2.5-coder-32b
+  editor_edit_format: editor-diff
+  use_temperature: 0.6
+  extra_params:
+      max_tokens: 128000
+      top_p: 0.95
+
+- name: cohere_chat/command-a-03-2025
+  examples_as_sys_msg: true
+
+- name: openrouter/cohere/command-a-03-2025
+  examples_as_sys_msg: true
+
+- name: gemini/gemma-3-27b-it
+  use_system_prompt: false
+  
+- name: openrouter/google/gemma-3-27b-it:free
+  use_system_prompt: false
+  
+- name: openrouter/google/gemma-3-27b-it
+  use_system_prompt: false
   

aider/sendchat.py

@@ -1,22 +1,6 @@
-import hashlib
-import json
-import os
-import time
-
 from aider.dump import dump  # noqa: F401
-from aider.exceptions import LiteLLMExceptions
-from aider.llm import litellm
 from aider.utils import format_messages
 
-# from diskcache import Cache
-
-
-CACHE_PATH = "~/.aider.send.cache.v1"
-CACHE = None
-# CACHE = Cache(CACHE_PATH)
-
-RETRY_TIMEOUT = 60
-
 
 def sanity_check_messages(messages):
     """Check if messages alternate between user and assistant roles.
@@ -75,99 +59,3 @@ def ensure_alternating_roles(messages):
         prev_role = current_role
 
     return fixed_messages
-
-
-def send_completion(
-    model_name,
-    messages,
-    functions,
-    stream,
-    temperature=0,
-    extra_params=None,
-):
-    #
-    #
-    if os.environ.get("AIDER_SANITY_CHECK_TURNS"):
-        sanity_check_messages(messages)
-    #
-    #
-
-    if "deepseek-reasoner" in model_name:
-        messages = ensure_alternating_roles(messages)
-
-    kwargs = dict(
-        model=model_name,
-        messages=messages,
-        stream=stream,
-    )
-    if temperature is not None:
-        kwargs["temperature"] = temperature
-
-    if functions is not None:
-        function = functions[0]
-        kwargs["tools"] = [dict(type="function", function=function)]
-        kwargs["tool_choice"] = {"type": "function", "function": {"name": function["name"]}}
-
-    if extra_params is not None:
-        kwargs.update(extra_params)
-
-    key = json.dumps(kwargs, sort_keys=True).encode()
-    # dump(kwargs)
-
-    # Generate SHA1 hash of kwargs and append it to chat_completion_call_hashes
-    hash_object = hashlib.sha1(key)
-
-    if not stream and CACHE is not None and key in CACHE:
-        return hash_object, CACHE[key]
-
-    res = litellm.completion(**kwargs)
-
-    if not stream and CACHE is not None:
-        CACHE[key] = res
-
-    return hash_object, res
-
-
-def simple_send_with_retries(model, messages):
-    litellm_ex = LiteLLMExceptions()
-
-    if "deepseek-reasoner" in model.name:
-        messages = ensure_alternating_roles(messages)
-
-    retry_delay = 0.125
-    while True:
-        try:
-            kwargs = {
-                "model_name": model.name,
-                "messages": messages,
-                "functions": None,
-                "stream": False,
-                "temperature": None if not model.use_temperature else 0,
-                "extra_params": model.extra_params,
-            }
-
-            _hash, response = send_completion(**kwargs)
-            if not response or not hasattr(response, "choices") or not response.choices:
-                return None
-            return response.choices[0].message.content
-        except litellm_ex.exceptions_tuple() as err:
-            ex_info = litellm_ex.get_ex_info(err)
-
-            print(str(err))
-            if ex_info.description:
-                print(ex_info.description)
-
-            should_retry = ex_info.retry
-            if should_retry:
-                retry_delay *= 2
-                if retry_delay > RETRY_TIMEOUT:
-                    should_retry = False
-
-            if not should_retry:
-                return None
-
-            print(f"Retrying in {retry_delay:.1f} seconds...")
-            time.sleep(retry_delay)
-            continue
-        except AttributeError:
-            return None

aider/special.py

@@ -41,6 +41,7 @@ ROOT_IMPORTANT_FILES = [
     "composer.lock",
     "pom.xml",
     "build.gradle",
+    "build.gradle.kts",
     "build.sbt",
     "go.mod",
     "go.sum",

aider/watch.py

@@ -95,7 +95,9 @@ class FileWatcher:
         if self.verbose:
             dump(rel_path)
 
-        if self.gitignore_spec and self.gitignore_spec.match_file(str(rel_path)):
+        if self.gitignore_spec and self.gitignore_spec.match_file(
+            rel_path.as_posix() + ("/" if path_abs.is_dir() else "")
+        ):
             return False
 
         if self.verbose:
@@ -108,28 +110,55 @@ class FileWatcher:
         except Exception:
             return
 
+    def get_roots_to_watch(self):
+        """Determine which root paths to watch based on gitignore rules"""
+        if self.gitignore_spec:
+            roots = [
+                str(path)
+                for path in self.root.iterdir()
+                if not self.gitignore_spec.match_file(
+                    path.relative_to(self.root).as_posix() + ("/" if path.is_dir() else "")
+                )
+            ]
+            # Fallback to watching root if all top-level items are filtered out
+            return roots if roots else [str(self.root)]
+        return [str(self.root)]
+
+    def handle_changes(self, changes):
+        """Process the detected changes and update state"""
+        if not changes:
+            return False
+
+        changed_files = {str(Path(change[1])) for change in changes}
+        self.changed_files.update(changed_files)
+        self.io.interrupt_input()
+        return True
+
+    def watch_files(self):
+        """Watch for file changes and process them"""
+        try:
+            roots_to_watch = self.get_roots_to_watch()
+
+            for changes in watch(
+                *roots_to_watch,
+                watch_filter=self.filter_func,
+                stop_event=self.stop_event,
+                ignore_permission_denied=True,
+            ):
+                if self.handle_changes(changes):
+                    return
+
+        except Exception as e:
+            if self.verbose:
+                dump(f"File watcher error: {e}")
+            raise e
+
     def start(self):
         """Start watching for file changes"""
         self.stop_event = threading.Event()
         self.changed_files = set()
 
-        def watch_files():
+        self.watcher_thread = threading.Thread(target=self.watch_files, daemon=True)
-            try:
-                for changes in watch(
-                    str(self.root), watch_filter=self.filter_func, stop_event=self.stop_event
-                ):
-                    if not changes:
-                        continue
-                    changed_files = {str(Path(change[1])) for change in changes}
-                    self.changed_files.update(changed_files)
-                    self.io.interrupt_input()
-                    return
-            except Exception as e:
-                if self.verbose:
-                    dump(f"File watcher error: {e}")
-                raise e
-
-        self.watcher_thread = threading.Thread(target=watch_files, daemon=True)
         self.watcher_thread.start()
 
     def stop(self):

aider/website/HISTORY.md

@@ -23,6 +23,124 @@ cog.out(text)
 ]]]-->
 
 
+### main branch
+
+- Bumped dependencies to pickup litellm fix for Ollama.
+- Added support for `openrouter/google/gemma-3-27b-it` model.
+- Aider wrote 96% of the code in this release.
+
+### Aider v0.77.0
+
+- Big upgrade in [programming languages supported](https://aider.chat/docs/languages.html) by adopting [tree-sitter-language-pack](https://github.com/Goldziher/tree-sitter-language-pack/).
+  - 130 new languages with linter support.
+  - 20 new languages with repo-map support.
+- Added `/think-tokens` command to set thinking token budget with support for human-readable formats (8k, 10.5k, 0.5M).
+- Added `/reasoning-effort` command to control model reasoning level.
+- The `/think-tokens` and `/reasoning-effort` commands display current settings when called without arguments.
+- Display of thinking token budget and reasoning effort in model information.
+- Changed `--thinking-tokens` argument to accept string values with human-readable formats.
+- Added `--auto-accept-architect` flag (default: true) to automatically accept changes from architect coder format without confirmation.
+- Added support for `cohere_chat/command-a-03-2025` and `gemini/gemma-3-27b-it`
+- The bare `/drop` command now preserves original read-only files provided via args.read.
+- Fixed a bug where default model would be set by deprecated `--shortcut` switches even when already specified in the command line.
+- Improved AutoCompleter to require 3 characters for autocompletion to reduce noise.
+- Aider wrote 72% of the code in this release.
+
+### Aider v0.76.2
+
+- Fixed handling of JSONDecodeError when loading model cache file.
+- Fixed handling of GitCommandError when retrieving git user configuration.
+- Aider wrote 75% of the code in this release.
+
+### Aider v0.76.1
+
+- Added ignore_permission_denied option to file watcher to prevent errors when accessing restricted files, by Yutaka Matsubara.
+- Aider wrote 0% of the code in this release.
+
+### Aider v0.76.0
+
+- Improved support for thinking/reasoningmodels:
+  - Added `--thinking-tokens` CLI option to control token budget for models that support thinking.
+  - Display thinking/reasoning content from LLMs which return it.
+  - Enhanced handling of reasoning tags to better clean up model responses.
+  - Added deprecation warning for `remove_reasoning` setting, now replaced by `reasoning_tag`.
+- Aider will notify you when it's completed the last request and needs your input:
+  - Added [notifications when LLM responses are ready](https://aider.chat/docs/usage/notifications.html) with `--notifications` flag.
+  - Specify desktop notification command with `--notifications-command`.
+- Added support for QWQ 32B.
+- Switch to `tree-sitter-language-pack` for tree sitter support.
+- Improved error handling for EOF (Ctrl+D) in user input prompts.
+- Added helper function to ensure hex color values have a # prefix.
+- Fixed handling of Git errors when reading staged files.
+- Improved SSL verification control for model information requests.
+- Improved empty LLM response handling with clearer warning messages.
+- Fixed Git identity retrieval to respect global configuration, by Akira Komamura.
+- Offer to install dependencies for Bedrock and Vertex AI models.
+- Deprecated model shortcut args (like --4o, --opus) in favor of the --model flag.
+- Aider wrote 85% of the code in this release.
+
+### Aider v0.75.3
+
+- Support for V3 free on OpenRouter: `--model openrouter/deepseek/deepseek-chat:free`.
+
+### Aider v0.75.2
+
+- Added support for Claude 3.7 Sonnet models on OpenRouter, Bedrock and Vertex AI.
+- Updated default model to Claude 3.7 Sonnet on OpenRouter.
+- Added support for GPT-4.5-preview model.
+- Added support for Claude 3.7 Sonnet:beta on OpenRouter.
+- Fixed weak_model_name patterns to match main model name patterns for some models.
+
+### Aider v0.75.1
+
+- Added support for `openrouter/anthropic/claude-3.7-sonnet`
+
+### Aider v0.75.0
+
+- Basic support for Claude 3.7 Sonnet
+  - Use `--model sonnet` to use the new 3.7
+  - Thinking support coming soon.
+- Bugfix to `/editor` command.
+- Aider wrote 46% of the code in this release.
+
+### Aider v0.74.3
+
+- Downgrade streamlit dependency to avoid threading bug.
+- Added support for tree-sitter language pack.
+- Added openrouter/o3-mini-high model configuration.
+- Added build.gradle.kts to special files for Kotlin project support, by Lucas Shadler.
+
+### Aider v0.74.2
+
+- Prevent more than one cache warming thread from becoming active.
+- Fixed continuation prompt ". " for multiline input.
+- Added HCL (Terraform) syntax support, by Warren Krewenki.
+
+### Aider v0.74.1
+
+- Have o1 & o3-mini generate markdown by sending the magic "Formatting re-enabled." string.
+- Bugfix for multi-line inputs, which should not include the ". " continuation prompt.
+
+### Aider v0.74.0
+
+- Dynamically changes the Ollama context window to hold the current chat.
+- Better support for o3-mini, DeepSeek V3 & R1, o1-mini, o1 especially via third-party API providers.
+- Remove `<think>` tags from R1 responses for commit messages (and other weak model uses).
+- Can now specify `use_temperature: <float>` in model settings, not just true/false.
+- The full docker container now includes `boto3` for Bedrock.
+- Docker containers now set `HOME=/app` which is the normal project mount-point, to persist `~/.aider`.
+- Bugfix to prevent creating incorrect filenames like `python`, `php`, etc.
+- Bugfix for `--timeout`
+- Bugfix so that `/model` now correctly reports that the weak model is not changed.
+- Bugfix so that multi-line mode persists through ^C at confirmation prompts.
+- Watch files now fully ignores top-level directories named in ignore files, to reduce the chance of hitting OS watch limits. Helpful to ignore giant subtrees like `node_modules`.
+- Fast startup with more providers and when model metadata provided in local files.
+- Improved .gitignore handling:
+  - Honor ignores already in effect regardless of how they've been configured.
+  - Check for .env only when the file exists.
+- Yes/No prompts now accept All/Skip as alias for Y/N even when not processing a group of confirmations.
+- Aider wrote 77% of the code in this release.
+
 ### Aider v0.73.0
 
 - Full support for o3-mini: `aider --model o3-mini`
@@ -31,7 +149,7 @@ cog.out(text)
 - Added support for removing model-specific reasoning tags from responses with `remove_reasoning: tagname` model setting.
 - Auto-create parent directories when creating new files, by xqyz.
 - Support for R1 free on OpenRouter: `--model openrouter/deepseek/deepseek-r1:free`
-- Aider wrote 70% of the code in this release.
+- Aider wrote 69% of the code in this release.
 
 ### Aider v0.72.3
 

aider/website/_data/blame.yml

@@ -3167,8 +3167,8 @@
     malkoG: 83
   start_tag: v0.64.0
   total_lines: 670
-- aider_percentage: 81.65
+- aider_percentage: 86.17
-  aider_total: 574
+  aider_total: 841
   end_date: '2024-12-01'
   end_tag: v0.66.0
   file_counts:
@@ -3240,18 +3240,52 @@
       Paul Gauthier (aider): 103
     tests/browser/test_browser.py:
       Paul Gauthier: 1
+    tests/fixtures/languages/c/test.c:
+      Paul Gauthier (aider): 6
+    tests/fixtures/languages/cpp/test.cpp:
+      Paul Gauthier (aider): 6
+    tests/fixtures/languages/csharp/test.cs:
+      Paul Gauthier (aider): 39
+    tests/fixtures/languages/elisp/test.el:
+      Paul Gauthier (aider): 25
+    tests/fixtures/languages/elixir/test.ex:
+      Paul Gauthier (aider): 5
+    tests/fixtures/languages/elm/test.elm:
+      Paul Gauthier: 1
+      Paul Gauthier (aider): 37
+    tests/fixtures/languages/go/test.go:
+      Paul Gauthier: 1
+      Paul Gauthier (aider): 41
+    tests/fixtures/languages/java/test.java:
+      Paul Gauthier: 2
+      Paul Gauthier (aider): 14
     tests/fixtures/languages/javascript/test.js:
       Paul Gauthier: 1
       Paul Gauthier (aider): 25
+    tests/fixtures/languages/ocaml/test.ml:
+      Paul Gauthier: 2
+      Paul Gauthier (aider): 17
+    tests/fixtures/languages/php/test.php:
+      Paul Gauthier (aider): 5
     tests/fixtures/languages/python/test.py:
       Paul Gauthier: 2
       Paul Gauthier (aider): 26
+    tests/fixtures/languages/ql/test.ql:
+      Paul Gauthier (aider): 3
+    tests/fixtures/languages/ruby/test.rb:
+      Paul Gauthier (aider): 3
+    tests/fixtures/languages/rust/test.rs:
+      Paul Gauthier (aider): 33
+    tests/fixtures/languages/tsx/test.tsx:
+      Paul Gauthier (aider): 30
+    tests/fixtures/languages/typescript/test.ts:
+      Paul Gauthier (aider): 3
   grand_total:
-    Paul Gauthier: 99
+    Paul Gauthier: 105
-    Paul Gauthier (aider): 574
+    Paul Gauthier (aider): 841
     Philippe de Reynal: 30
   start_tag: v0.65.0
-  total_lines: 703
+  total_lines: 976
 - aider_percentage: 67.86
   aider_total: 437
   end_date: '2024-12-06'
@@ -3619,7 +3653,7 @@
     apaz-cli: 18
   start_tag: v0.70.0
   total_lines: 391
-- aider_percentage: 51.69
+- aider_percentage: 48.76
   aider_total: 138
   end_date: '2025-01-20'
   end_tag: v0.72.0
@@ -3680,10 +3714,464 @@
       Paul Gauthier (aider): 39
     tests/basic/test_repomap.py:
       Paul Walker: 1
+    tests/fixtures/languages/kotlin/test.kt:
+      Paul Walker: 16
   grand_total:
     Paul Gauthier: 92
     Paul Gauthier (aider): 138
-    Paul Walker: 28
+    Paul Walker: 44
     Titusz Pan: 9
   start_tag: v0.71.0
-  total_lines: 267
+  total_lines: 283
+- aider_percentage: 37.47
+  aider_total: 284
+  end_date: '2025-01-31'
+  end_tag: v0.73.0
+  file_counts:
+    aider/__init__.py:
+      Paul Gauthier: 1
+    aider/args.py:
+      Paul Gauthier: 3
+      Paul Gauthier (aider): 2
+    aider/coders/base_coder.py:
+      Paul Gauthier: 37
+      Paul Gauthier (aider): 26
+    aider/commands.py:
+      xqyz: 1
+    aider/io.py:
+      Paul Gauthier: 7
+    aider/main.py:
+      Paul Gauthier: 13
+      Paul Gauthier (aider): 15
+    aider/models.py:
+      Paul Gauthier: 8
+      Paul Gauthier (aider): 33
+    aider/resources/model-settings.yml:
+      Paul Gauthier: 334
+      kennyfrc: 11
+      xqyz: 4
+    aider/sendchat.py:
+      Mir Adnan ALI: 28
+      Paul Gauthier: 11
+      Paul Gauthier (aider): 6
+    aider/urls.py:
+      Paul Gauthier: 1
+    aider/website/_includes/leaderboard.js:
+      Paul Gauthier (aider): 1
+    aider/website/docs/leaderboards/index.md:
+      Paul Gauthier: 3
+      Paul Gauthier (aider): 2
+    benchmark/benchmark.py:
+      Paul Gauthier (aider): 21
+    benchmark/rsync.sh:
+      Paul Gauthier: 2
+    tests/basic/test_coder.py:
+      Paul Gauthier: 10
+      Paul Gauthier (aider): 39
+    tests/basic/test_main.py:
+      Paul Gauthier (aider): 62
+    tests/basic/test_sendchat.py:
+      Paul Gauthier (aider): 77
+  grand_total:
+    Mir Adnan ALI: 28
+    Paul Gauthier: 430
+    Paul Gauthier (aider): 284
+    kennyfrc: 11
+    xqyz: 5
+  start_tag: v0.72.0
+  total_lines: 758
+- aider_percentage: 76.07
+  aider_total: 604
+  end_date: '2025-02-06'
+  end_tag: v0.74.0
+  file_counts:
+    aider/__init__.py:
+      Paul Gauthier: 1
+    aider/args.py:
+      Paul Gauthier: 1
+    aider/coders/base_coder.py:
+      Paul Gauthier: 24
+      Paul Gauthier (aider): 9
+    aider/coders/editblock_coder.py:
+      Paul Gauthier: 5
+    aider/coders/wholefile_coder.py:
+      Paul Gauthier: 2
+    aider/commands.py:
+      Paul Gauthier: 1
+    aider/exceptions.py:
+      Paul Gauthier: 4
+      Paul Gauthier (aider): 6
+    aider/history.py:
+      Paul Gauthier (aider): 1
+    aider/io.py:
+      Paul Gauthier: 4
+      Paul Gauthier (aider): 18
+    aider/llm.py:
+      Paul Gauthier: 3
+    aider/main.py:
+      Paul Gauthier: 21
+      Paul Gauthier (aider): 25
+    aider/models.py:
+      Paul Gauthier: 83
+      Paul Gauthier (aider): 77
+    aider/repo.py:
+      Paul Gauthier: 1
+      Paul Gauthier (aider): 2
+      "Viktor Sz\xE9pe": 3
+    aider/resources/model-settings.yml:
+      Paul Gauthier: 11
+    aider/watch.py:
+      Paul Gauthier (aider): 45
+    benchmark/docker.sh:
+      Paul Gauthier: 2
+    docker/Dockerfile:
+      Paul Gauthier: 5
+      Paul Gauthier (aider): 4
+    tests/basic/test_editblock.py:
+      Paul Gauthier: 7
+    tests/basic/test_history.py:
+      Paul Gauthier (aider): 13
+    tests/basic/test_io.py:
+      Paul Gauthier (aider): 46
+    tests/basic/test_main.py:
+      Paul Gauthier: 8
+      Paul Gauthier (aider): 1
+    tests/basic/test_models.py:
+      Paul Gauthier (aider): 297
+    tests/basic/test_repo.py:
+      Paul Gauthier (aider): 11
+    tests/basic/test_sendchat.py:
+      Paul Gauthier (aider): 7
+    tests/basic/test_watch.py:
+      Paul Gauthier: 4
+      Paul Gauthier (aider): 42
+  grand_total:
+    Paul Gauthier: 187
+    Paul Gauthier (aider): 604
+    "Viktor Sz\xE9pe": 3
+  start_tag: v0.73.0
+  total_lines: 794
+- aider_percentage: 44.78
+  aider_total: 163
+  end_date: '2025-02-24'
+  end_tag: v0.75.0
+  file_counts:
+    aider/__init__.py:
+      Paul Gauthier: 1
+    aider/args.py:
+      Paul Gauthier: 7
+    aider/coders/base_coder.py:
+      Paul Gauthier: 12
+      Paul Gauthier (aider): 4
+    aider/commands.py:
+      FeepingCreature (aider): 6
+    aider/editor.py:
+      Paul Gauthier: 7
+      Paul Gauthier (aider): 5
+    aider/io.py:
+      Paul Gauthier: 3
+      Paul Gauthier (aider): 4
+    aider/linter.py:
+      Paul Gauthier: 1
+    aider/main.py:
+      Paul Gauthier: 16
+    aider/models.py:
+      Paul Gauthier: 4
+    aider/queries/tree-sitter-language-pack/javascript-tags.scm:
+      Paul Gauthier: 5
+    aider/queries/tree-sitter-languages/hcl-tags.scm:
+      Paul Gauthier: 3
+      Warren Krewenki: 74
+    aider/queries/tree-sitter-languages/javascript-tags.scm:
+      Paul Gauthier: 5
+    aider/repomap.py:
+      Paul Gauthier: 43
+      Paul Gauthier (aider): 11
+    aider/resources/model-settings.yml:
+      Paul Gauthier: 12
+    aider/special.py:
+      Lucas Shadler: 1
+    aider/website/docs/leaderboards/index.md:
+      Paul Gauthier: 1
+    benchmark/Dockerfile:
+      Paul Gauthier (aider): 1
+    benchmark/benchmark.py:
+      Paul Gauthier: 4
+    benchmark/cpp-test.sh:
+      Paul Gauthier: 1
+    scripts/blame.py:
+      Paul Gauthier (aider): 2
+    scripts/issues.py:
+      Paul Gauthier (aider): 17
+    tests/basic/test_coder.py:
+      Paul Gauthier (aider): 18
+    tests/basic/test_editor.py:
+      Antti Kaihola: 1
+      Paul Gauthier (aider): 41
+    tests/basic/test_models.py:
+      Paul Gauthier (aider): 1
+    tests/basic/test_repomap.py:
+      Paul Gauthier (aider): 1
+    tests/fixtures/languages/hcl/test.tf:
+      Paul Gauthier (aider): 52
+  grand_total:
+    Antti Kaihola: 1
+    FeepingCreature (aider): 6
+    Lucas Shadler: 1
+    Paul Gauthier: 125
+    Paul Gauthier (aider): 157
+    Warren Krewenki: 74
+  start_tag: v0.74.0
+  total_lines: 364
+- aider_percentage: 84.75
+  aider_total: 1589
+  end_date: '2025-03-10'
+  end_tag: v0.76.0
+  file_counts:
+    aider/__init__.py:
+      Paul Gauthier: 1
+    aider/args.py:
+      Paul Gauthier: 2
+      Paul Gauthier (aider): 25
+    aider/args_formatter.py:
+      Paul Gauthier: 4
+      Paul Gauthier (aider): 3
+    aider/coders/base_coder.py:
+      Paul Gauthier: 54
+      Paul Gauthier (aider): 29
+    aider/deprecated.py:
+      Paul Gauthier (aider): 107
+    aider/io.py:
+      Paul Gauthier: 7
+      Paul Gauthier (aider): 127
+    aider/main.py:
+      Akira Komamura: 2
+      Mattias: 1
+      Paul Gauthier: 4
+      Paul Gauthier (aider): 16
+    aider/models.py:
+      Paul Gauthier: 6
+      Paul Gauthier (aider): 68
+    aider/queries/tree-sitter-language-pack/csharp-tags.scm:
+      Paul Gauthier: 14
+      Paul Gauthier (aider): 12
+    aider/reasoning_tags.py:
+      Paul Gauthier: 14
+      Paul Gauthier (aider): 68
+    aider/repo.py:
+      Akira Komamura: 1
+      Paul Gauthier (aider): 4
+    aider/repomap.py:
+      Paul Gauthier: 9
+    aider/resources/model-settings.yml:
+      Paul Gauthier: 61
+      Paul Gauthier (aider): 32
+      gmoz22: 4
+    aider/website/_includes/leaderboard.js:
+      Paul Gauthier (aider): 48
+    aider/website/docs/leaderboards/index.md:
+      Paul Gauthier: 2
+    benchmark/benchmark.py:
+      Paul Gauthier: 1
+    benchmark/problem_stats.py:
+      Paul Gauthier (aider): 2
+    docker/Dockerfile:
+      Paul Gauthier: 1
+    scripts/blame.py:
+      Paul Gauthier: 1
+    scripts/pip-compile.sh:
+      Claudia Pellegrino: 10
+      Paul Gauthier: 6
+      Paul Gauthier (aider): 11
+    scripts/update-history.py:
+      Paul Gauthier: 1
+    scripts/versionbump.py:
+      Paul Gauthier: 4
+      Paul Gauthier (aider): 64
+    tests/basic/test_deprecated.py:
+      Paul Gauthier: 10
+      Paul Gauthier (aider): 130
+    tests/basic/test_io.py:
+      Paul Gauthier (aider): 54
+    tests/basic/test_main.py:
+      Paul Gauthier: 1
+      Paul Gauthier (aider): 93
+    tests/basic/test_model_info_manager.py:
+      Paul Gauthier (aider): 72
+    tests/basic/test_models.py:
+      Paul Gauthier: 27
+      Paul Gauthier (aider): 34
+    tests/basic/test_reasoning.py:
+      Paul Gauthier: 36
+      Paul Gauthier (aider): 525
+    tests/basic/test_repomap.py:
+      Paul Gauthier: 2
+    tests/basic/test_ssl_verification.py:
+      Paul Gauthier (aider): 65
+  grand_total:
+    Akira Komamura: 3
+    Claudia Pellegrino: 10
+    Mattias: 1
+    Paul Gauthier: 268
+    Paul Gauthier (aider): 1589
+    gmoz22: 4
+  start_tag: v0.75.0
+  total_lines: 1875
+- aider_percentage: 71.93
+  aider_total: 1399
+  end_date: '2025-03-13'
+  end_tag: v0.77.0
+  file_counts:
+    aider/__init__.py:
+      Paul Gauthier: 1
+    aider/args.py:
+      Paul Gauthier (aider): 5
+    aider/coders/architect_coder.py:
+      Paul Gauthier (aider): 2
+    aider/coders/base_coder.py:
+      Paul Gauthier (aider): 14
+    aider/commands.py:
+      Paul Gauthier: 4
+      Paul Gauthier (aider): 71
+    aider/deprecated.py:
+      Paul Gauthier: 2
+    aider/io.py:
+      Paul Gauthier (aider): 5
+    aider/main.py:
+      Paul Gauthier (aider): 12
+    aider/models.py:
+      Paul Gauthier (aider): 83
+    aider/queries/tree-sitter-language-pack/arduino-tags.scm:
+      Paul Gauthier: 3
+      Paul Gauthier (aider): 2
+    aider/queries/tree-sitter-language-pack/c-tags.scm:
+      Paul Gauthier: 4
+      Paul Gauthier (aider): 5
+    aider/queries/tree-sitter-language-pack/chatito-tags.scm:
+      Paul Gauthier: 11
+      Paul Gauthier (aider): 5
+    aider/queries/tree-sitter-language-pack/commonlisp-tags.scm:
+      Paul Gauthier: 116
+      Paul Gauthier (aider): 6
+    aider/queries/tree-sitter-language-pack/cpp-tags.scm:
+      Paul Gauthier: 7
+      Paul Gauthier (aider): 8
+    aider/queries/tree-sitter-language-pack/d-tags.scm:
+      Paul Gauthier: 9
+      Paul Gauthier (aider): 17
+    aider/queries/tree-sitter-language-pack/dart-tags.scm:
+      Paul Gauthier: 42
+      Paul Gauthier (aider): 19
+    aider/queries/tree-sitter-language-pack/elisp-tags.scm:
+      Paul Gauthier: 1
+      Paul Gauthier (aider): 2
+    aider/queries/tree-sitter-language-pack/elixir-tags.scm:
+      Paul Gauthier: 10
+      Paul Gauthier (aider): 8
+    aider/queries/tree-sitter-language-pack/elm-tags.scm:
+      Paul Gauthier: 8
+      Paul Gauthier (aider): 11
+    aider/queries/tree-sitter-language-pack/gleam-tags.scm:
+      Paul Gauthier: 26
+      Paul Gauthier (aider): 15
+    aider/queries/tree-sitter-language-pack/go-tags.scm:
+      Paul Gauthier: 14
+      Paul Gauthier (aider): 14
+    aider/queries/tree-sitter-language-pack/java-tags.scm:
+      Paul Gauthier: 10
+      Paul Gauthier (aider): 7
+    aider/queries/tree-sitter-language-pack/lua-tags.scm:
+      Paul Gauthier: 25
+      Paul Gauthier (aider): 9
+    aider/queries/tree-sitter-language-pack/pony-tags.scm:
+      Paul Gauthier: 20
+      Paul Gauthier (aider): 19
+    aider/queries/tree-sitter-language-pack/properties-tags.scm:
+      Paul Gauthier: 3
+      Paul Gauthier (aider): 2
+    aider/queries/tree-sitter-language-pack/python-tags.scm:
+      Paul Gauthier: 9
+      Paul Gauthier (aider): 5
+    aider/queries/tree-sitter-language-pack/r-tags.scm:
+      Paul Gauthier: 17
+      Paul Gauthier (aider): 4
+    aider/queries/tree-sitter-language-pack/racket-tags.scm:
+      Paul Gauthier: 10
+      Paul Gauthier (aider): 2
+    aider/queries/tree-sitter-language-pack/ruby-tags.scm:
+      Paul Gauthier: 23
+      Paul Gauthier (aider): 12
+    aider/queries/tree-sitter-language-pack/rust-tags.scm:
+      Paul Gauthier: 41
+      Paul Gauthier (aider): 14
+    aider/queries/tree-sitter-language-pack/solidity-tags.scm:
+      Paul Gauthier: 30
+      Paul Gauthier (aider): 13
+    aider/queries/tree-sitter-language-pack/swift-tags.scm:
+      Paul Gauthier: 39
+      Paul Gauthier (aider): 12
+    aider/queries/tree-sitter-language-pack/udev-tags.scm:
+      Paul Gauthier: 15
+      Paul Gauthier (aider): 5
+    aider/resources/model-settings.yml:
+      Paul Gauthier: 9
+    aider/watch.py:
+      Yutaka Matsubara: 4
+    aider/website/docs/leaderboards/index.md:
+      Paul Gauthier: 3
+      Paul Gauthier (aider): 8
+    scripts/redact-cast.py:
+      Paul Gauthier: 27
+      Paul Gauthier (aider): 98
+    scripts/tsl_pack_langs.py:
+      Paul Gauthier (aider): 145
+    scripts/versionbump.py:
+      Paul Gauthier (aider): 1
+    tests/basic/test_coder.py:
+      Paul Gauthier (aider): 104
+    tests/basic/test_commands.py:
+      Paul Gauthier: 2
+      Paul Gauthier (aider): 190
+    tests/basic/test_models.py:
+      Paul Gauthier (aider): 44
+    tests/basic/test_repomap.py:
+      Paul Gauthier: 1
+      Paul Gauthier (aider): 125
+    tests/fixtures/languages/arduino/test.ino:
+      Paul Gauthier (aider): 21
+    tests/fixtures/languages/c/test.c:
+      Paul Gauthier (aider): 12
+    tests/fixtures/languages/chatito/test.chatito:
+      Paul Gauthier (aider): 20
+    tests/fixtures/languages/commonlisp/test.lisp:
+      Paul Gauthier (aider): 17
+    tests/fixtures/languages/d/test.d:
+      Paul Gauthier (aider): 26
+    tests/fixtures/languages/dart/test.dart:
+      Paul Gauthier (aider): 21
+    tests/fixtures/languages/elm/test.elm:
+      Paul Gauthier (aider): 16
+    tests/fixtures/languages/gleam/test.gleam:
+      Paul Gauthier (aider): 10
+    tests/fixtures/languages/lua/test.lua:
+      Paul Gauthier (aider): 25
+    tests/fixtures/languages/pony/test.pony:
+      Paul Gauthier (aider): 8
+    tests/fixtures/languages/properties/test.properties:
+      Paul Gauthier (aider): 14
+    tests/fixtures/languages/r/test.r:
+      Paul Gauthier (aider): 17
+    tests/fixtures/languages/racket/test.rkt:
+      Paul Gauthier (aider): 8
+    tests/fixtures/languages/solidity/test.sol:
+      Paul Gauthier (aider): 21
+    tests/fixtures/languages/swift/test.swift:
+      Paul Gauthier (aider): 18
+    tests/fixtures/languages/udev/test.rules:
+      Paul Gauthier (aider): 22
+  grand_total:
+    Paul Gauthier: 542
+    Paul Gauthier (aider): 1399
+    Yutaka Matsubara: 4
+  start_tag: v0.76.0
+  total_lines: 1945

aider/website/_data/polyglot_leaderboard.yml

@@ -1,3 +1,29 @@
+- dirname: 2025-02-25-20-23-07--gemini-pro
+  test_cases: 225
+  model: gemini/gemini-2.0-pro-exp-02-05
+  edit_format: whole
+  commit_hash: 2fccd47
+  pass_rate_1: 20.4
+  pass_rate_2: 35.6
+  pass_num_1: 46
+  pass_num_2: 80
+  percent_cases_well_formed: 100.0
+  error_outputs: 430
+  num_malformed_responses: 0
+  num_with_malformed_responses: 0
+  user_asks: 13
+  lazy_comments: 0
+  syntax_errors: 0
+  indentation_errors: 0
+  exhausted_context_windows: 0
+  test_timeouts: 5
+  total_tests: 225
+  command: aider --model gemini/gemini-2.0-pro-exp-02-05
+  date: 2025-02-25
+  versions: 0.75.2.dev
+  seconds_per_case: 34.8
+  total_cost: 0.0000
+
 - dirname: 2024-12-21-18-41-18--polyglot-gpt-4o-mini
   test_cases: 225
   model: gpt-4o-mini-2024-07-18
@@ -518,3 +544,239 @@
   versions: 0.72.4.dev
   seconds_per_case: 124.6
   total_cost: 18.1584
+
+- dirname: 2025-01-21-22-51-49--gemini-2.0-flash-thinking-exp-01-21-polyglot-diff
+  test_cases: 225
+  model: gemini-2.0-flash-thinking-exp-01-21
+  edit_format: diff
+  commit_hash: 843720a
+  pass_rate_1: 5.8
+  pass_rate_2: 18.2
+  pass_num_1: 13
+  pass_num_2: 41
+  percent_cases_well_formed: 77.8
+  error_outputs: 182
+  num_malformed_responses: 180
+  num_with_malformed_responses: 50
+  user_asks: 26
+  lazy_comments: 0
+  syntax_errors: 0
+  indentation_errors: 0
+  exhausted_context_windows: 2
+  test_timeouts: 7
+  total_tests: 225
+  command: aider --model gemini/gemini-2.0-flash-thinking-exp-01-21
+  date: 2025-01-21
+  versions: 0.72.2.dev
+  seconds_per_case: 24.2
+  total_cost: 0.0000
+
+- dirname: 2025-02-15-19-51-22--chatgpt4o-feb15-diff
+  test_cases: 223
+  model: chatgpt-4o-latest (2025-02-15)
+  edit_format: diff
+  commit_hash: 108ce18-dirty
+  pass_rate_1: 9.0
+  pass_rate_2: 27.1
+  pass_num_1: 20
+  pass_num_2: 61
+  percent_cases_well_formed: 93.3
+  error_outputs: 66
+  num_malformed_responses: 21
+  num_with_malformed_responses: 15
+  user_asks: 57
+  lazy_comments: 0
+  syntax_errors: 0
+  indentation_errors: 0
+  exhausted_context_windows: 0
+  test_timeouts: 2
+  total_tests: 225
+  command: aider --model chatgpt-4o-latest
+  date: 2025-02-15
+  versions: 0.74.3.dev
+  seconds_per_case: 12.4
+  total_cost: 14.3703
+
+- dirname: 2025-02-24-19-54-07--sonnet37-diff
+  test_cases: 225
+  model: claude-3-7-sonnet-20250219 (no thinking)
+  edit_format: diff
+  commit_hash: 75e9ee6
+  pass_rate_1: 24.4
+  pass_rate_2: 60.4
+  pass_num_1: 55
+  pass_num_2: 136
+  percent_cases_well_formed: 93.3
+  error_outputs: 16
+  num_malformed_responses: 16
+  num_with_malformed_responses: 15
+  user_asks: 12
+  lazy_comments: 0
+  syntax_errors: 0
+  indentation_errors: 0
+  exhausted_context_windows: 0
+  test_timeouts: 0
+  total_tests: 225
+  command: aider --model sonnet
+  date: 2025-02-24
+  versions: 0.74.4.dev
+  seconds_per_case: 28.3
+  total_cost: 17.7191
+
+- dirname: 2025-02-24-21-47-23--sonnet37-diff-think-32k-64k
+  test_cases: 225
+  model: claude-3-7-sonnet-20250219 (32k thinking tokens)
+  edit_format: diff
+  commit_hash: 60d11a6, 93edbda
+  pass_rate_1: 29.3
+  pass_rate_2: 64.9
+  pass_num_1: 66
+  pass_num_2: 146
+  percent_cases_well_formed: 97.8
+  error_outputs: 66
+  num_malformed_responses: 5
+  num_with_malformed_responses: 5
+  user_asks: 5
+  lazy_comments: 0
+  syntax_errors: 0
+  indentation_errors: 0
+  exhausted_context_windows: 0
+  test_timeouts: 1
+  total_tests: 225
+  command: "aider --model anthropic/claude-3-7-sonnet-20250219 # plus yml config"
+  date: 2025-02-24
+  versions: 0.75.1.dev
+  seconds_per_case: 105.2
+  total_cost: 36.8343
+
+- dirname: 2025-02-27-20-26-15--gpt45-diff3
+  test_cases: 224
+  model: gpt-4.5-preview
+  edit_format: diff
+  commit_hash: b462e55-dirty
+  pass_rate_1: 22.3
+  pass_rate_2: 44.9
+  pass_num_1: 50
+  pass_num_2: 101
+  percent_cases_well_formed: 97.3
+  error_outputs: 10
+  num_malformed_responses: 8
+  num_with_malformed_responses: 6
+  user_asks: 15
+  lazy_comments: 0
+  syntax_errors: 0
+  indentation_errors: 0
+  exhausted_context_windows: 1
+  test_timeouts: 2
+  total_tests: 225
+  command: aider --model openai/gpt-4.5-preview
+  date: 2025-02-27
+  versions: 0.75.2.dev
+  seconds_per_case: 113.5
+  total_cost: 183.1802
+
+- dirname: 2025-03-06-17-40-24--qwq32b-diff-temp-topp-ex-sys-remind-user-for-real
+  test_cases: 225
+  model: QwQ-32B
+  edit_format: diff
+  commit_hash: 51d118f-dirty
+  pass_rate_1: 8.0
+  pass_rate_2: 20.9
+  pass_num_1: 18
+  pass_num_2: 47
+  percent_cases_well_formed: 67.6
+  error_outputs: 145
+  num_malformed_responses: 143
+  num_with_malformed_responses: 73
+  user_asks: 17
+  lazy_comments: 0
+  syntax_errors: 0
+  indentation_errors: 0
+  exhausted_context_windows: 1
+  test_timeouts: 4
+  total_tests: 225
+  command: aider --model fireworks_ai/accounts/fireworks/models/qwq-32b
+  date: 2025-03-06
+  versions: 0.75.3.dev
+  seconds_per_case: 228.6
+  total_cost: 0.0000
+
+- dirname: 2025-03-07-15-11-27--qwq32b-arch-temp-topp-again
+  test_cases: 225
+  model: QwQ-32B + Qwen 2.5 Coder Instruct
+  edit_format: architect
+  commit_hash: 52162a5
+  editor_model: fireworks_ai/accounts/fireworks/models/qwen2p5-coder-32b-instruct
+  editor_edit_format: editor-diff
+  pass_rate_1: 9.8
+  pass_rate_2: 26.2
+  pass_num_1: 22
+  pass_num_2: 59
+  percent_cases_well_formed: 100.0
+  error_outputs: 122
+  num_malformed_responses: 0
+  num_with_malformed_responses: 0
+  user_asks: 489
+  lazy_comments: 8
+  syntax_errors: 0
+  indentation_errors: 0
+  exhausted_context_windows: 1
+  test_timeouts: 2
+  total_tests: 225
+  command: aider --model fireworks_ai/accounts/fireworks/models/qwq-32b --architect
+  date: 2025-03-07
+  versions: 0.75.3.dev
+  seconds_per_case: 137.4
+  total_cost: 0
+
+- dirname: 2025-03-14-23-40-00--cmda-quality-whole2
+  test_cases: 225
+  model: command-a-03-2025-quality
+  edit_format: whole
+  commit_hash: a1aa63f
+  pass_rate_1: 2.2
+  pass_rate_2: 12.0
+  pass_num_1: 5
+  pass_num_2: 27
+  percent_cases_well_formed: 99.6
+  error_outputs: 2
+  num_malformed_responses: 1
+  num_with_malformed_responses: 1
+  user_asks: 215
+  lazy_comments: 0
+  syntax_errors: 0
+  indentation_errors: 0
+  exhausted_context_windows: 1
+  test_timeouts: 4
+  total_tests: 225
+  command: OPENAI_API_BASE=https://api.cohere.ai/compatibility/v1 aider --model openai/command-a-03-2025-quality
+  date: 2025-03-14
+  versions: 0.77.1.dev
+  seconds_per_case: 85.1
+  total_cost: 0.0000
+
+- dirname: 2025-03-15-01-21-24--gemma3-27b-or
+  test_cases: 225
+  model: gemma-3-27b-it
+  edit_format: whole
+  commit_hash: fd21f51-dirty
+  pass_rate_1: 1.8
+  pass_rate_2: 4.9
+  pass_num_1: 4
+  pass_num_2: 11
+  percent_cases_well_formed: 100.0
+  error_outputs: 3
+  num_malformed_responses: 0
+  num_with_malformed_responses: 0
+  user_asks: 181
+  lazy_comments: 0
+  syntax_errors: 0
+  indentation_errors: 0
+  exhausted_context_windows: 1
+  test_timeouts: 3
+  total_tests: 225
+  command: aider --model openrouter/google/gemma-3-27b-it
+  date: 2025-03-15
+  versions: 0.77.1.dev
+  seconds_per_case: 79.7
+  total_cost: 0.0000

aider/website/_includes/get-started.md

@@ -11,14 +11,14 @@ cd /to/your/project
 # Work with DeepSeek via DeepSeek's API
 aider --model deepseek --api-key deepseek=your-key-goes-here
 
-# Work with Claude 3.5 Sonnet via Anthropic's API
+# Work with Claude 3.7 Sonnet via Anthropic's API
 aider --model sonnet --api-key anthropic=your-key-goes-here
 
 # Work with GPT-4o via OpenAI's API
 aider --model gpt-4o --api-key openai=your-key-goes-here
 
 # Work with Sonnet via OpenRouter's API
-aider --model openrouter/anthropic/claude-3.5-sonnet --api-key openrouter=your-key-goes-here
+aider --model openrouter/anthropic/claude-3.7-sonnet --api-key openrouter=your-key-goes-here
 
 # Work with DeepSeek via OpenRouter's API
 aider --model openrouter/deepseek/deepseek-chat --api-key openrouter=your-key-goes-here

aider/website/_includes/leaderboard.js

@@ -23,6 +23,16 @@ document.addEventListener('DOMContentLoaded', function () {
         return (label && label.includes(HIGHLIGHT_MODEL)) ? 'rgba(255, 99, 132, 1)' : 'rgba(54, 162, 235, 1)';
       },
       borderWidth: 1
+    }, {
+      label: 'Total Cost ($)',
+      data: [],
+      type: 'scatter',
+      yAxisID: 'y1',
+      backgroundColor: 'rgba(153, 102, 255, 1)',
+      borderColor: '#fff',
+      borderWidth: 1,
+      pointRadius: 5,
+      pointHoverRadius: 7
     }]
   };
 
@@ -32,7 +42,8 @@ document.addEventListener('DOMContentLoaded', function () {
       model: '{{ row.model }}',
       pass_rate: {{ row[pass_rate_field] }},
       percent_cases_well_formed: {{ row.percent_cases_well_formed }},
-      edit_format: '{{ row.edit_format | default: "diff" }}'
+      edit_format: '{{ row.edit_format | default: "diff" }}',
+      total_cost: {{ row.total_cost | default: 0 }}
     });
   {% endfor %}
 
@@ -43,6 +54,7 @@ document.addEventListener('DOMContentLoaded', function () {
     displayedData = [];
     leaderboardData.labels = [];
     leaderboardData.datasets[0].data = [];
+    leaderboardData.datasets[1].data = [];
 
     allData.forEach(function(row, index) {
       var rowElement = document.getElementById('edit-row-' + index);
@@ -53,6 +65,8 @@ document.addEventListener('DOMContentLoaded', function () {
         displayedData.push(row);
         leaderboardData.labels.push(row.model);
         leaderboardData.datasets[0].data.push(row.pass_rate);
+        // Only include cost if it's not zero (placeholder for unknown)
+        leaderboardData.datasets[1].data.push(row.total_cost > 0 ? row.total_cost : null);
       }
     });
 
@@ -111,10 +125,29 @@ document.addEventListener('DOMContentLoaded', function () {
                   fillStyle: blueDiagonalPattern,
                   strokeStyle: 'rgba(54, 162, 235, 1)',
                   lineWidth: 1
+                },
+                {
+                  text: 'Total Cost ($)',
+                  fillStyle: 'rgba(153, 102, 255, 1)',
+                  strokeStyle: '#fff',
+                  lineWidth: 1,
+                  pointStyle: 'circle'
                 }
               ];
             }
           }
+        },
+        tooltip: {
+          callbacks: {
+            label: function(context) {
+              const datasetLabel = context.dataset.label || '';
+              const value = context.parsed.y;
+              if (datasetLabel === 'Total Cost ($)') {
+                return datasetLabel + ': $' + value.toFixed(2);
+              }
+              return datasetLabel + ': ' + value.toFixed(1) + '%';
+            }
+          }
         }
       },
       scales: {
@@ -125,6 +158,17 @@ document.addEventListener('DOMContentLoaded', function () {
             text: 'Percent completed correctly'
           }
         },
+        y1: {
+          beginAtZero: true,
+          position: 'right',
+          grid: {
+            drawOnChartArea: false
+          },
+          title: {
+            display: true,
+            text: 'Total Cost ($)'
+          }
+        },
         x: {
           ticks: {
             callback: function(value, index) {
@@ -173,6 +217,7 @@ document.addEventListener('DOMContentLoaded', function () {
     displayedData = [];
     leaderboardData.labels = [];
     leaderboardData.datasets[0].data = [];
+    leaderboardData.datasets[1].data = [];
     
     for (var i = 0; i < rows.length; i++) {
       var rowText = rows[i].textContent;
@@ -181,6 +226,8 @@ document.addEventListener('DOMContentLoaded', function () {
         displayedData.push(allData[i]);
         leaderboardData.labels.push(allData[i].model);
         leaderboardData.datasets[0].data.push(allData[i].pass_rate);
+        // Only include cost if it's not zero (placeholder for unknown)
+        leaderboardData.datasets[1].data.push(allData[i].total_cost > 0 ? allData[i].total_cost : null);
       } else {
         rows[i].style.display = 'none';
       }

aider/website/_includes/recording.css

@@ -0,0 +1,183 @@
+/* Terminal header styling */
+.terminal-header {
+  background-color: #e0e0e0;
+  border-top-left-radius: 6px;
+  border-top-right-radius: 6px;
+  padding: 4px 10px;
+  display: flex;
+  align-items: center;
+  border-bottom: 1px solid #c0c0c0;
+}
+
+.terminal-buttons {
+  display: flex;
+  gap: 4px;
+  margin-right: 10px;
+}
+
+.terminal-button {
+  width: 10px;
+  height: 10px;
+  border-radius: 50%;
+}
+
+.terminal-close {
+  background-color: #ff5f56;
+  border: 1px solid #e0443e;
+}
+
+.terminal-minimize {
+  background-color: #ffbd2e;
+  border: 1px solid #dea123;
+}
+
+.terminal-expand {
+  background-color: #27c93f;
+  border: 1px solid #1aab29;
+}
+
+.terminal-title {
+  flex-grow: 1;
+  text-align: center;
+  font-family: -apple-system, BlinkMacSystemFont, "Segoe UI", Roboto, Helvetica, Arial, sans-serif;
+  font-size: 11px;
+  color: #666;
+}
+
+/* Toast notification styling */
+.toast-container {
+  position: fixed;
+  top: 50%;
+  left: 50%;
+  transform: translate(-50%, -50%);
+  z-index: 9999;
+  pointer-events: none;
+}
+
+.toast-notification {
+  background-color: rgba(0, 0, 0, 0.7);
+  color: white;
+  padding: 12px 25px;
+  border-radius: 8px;
+  margin-bottom: 10px;
+  box-shadow: 0 2px 8px rgba(0, 0, 0, 0.2);
+  opacity: 0;
+  transition: opacity 0.3s ease-in-out;
+  font-family: -apple-system, BlinkMacSystemFont, "Segoe UI", Roboto, Helvetica, Arial, sans-serif;
+  font-size: 18px;
+  text-align: center;
+  display: inline-block;
+  min-width: 200px;
+  max-width: 90%;
+}
+
+/* Page container styling */
+.page-container {
+  max-width: 900px;
+  margin-left: auto;
+  margin-right: auto;
+  position: relative;
+}
+
+.terminal-container {
+  border-radius: 6px;
+  overflow: hidden;
+  box-shadow: 0 3px 10px rgba(0, 0, 0, 0.1);
+  margin-top: 20px;
+  margin-bottom: 20px;
+  position: relative;
+}
+
+/* Timestamp link styling */
+.timestamp-link {
+  color: #0366d6;
+  text-decoration: none;
+  font-weight: bold;
+  cursor: pointer;
+}
+
+.timestamp-link:hover {
+  text-decoration: underline;
+}
+
+/* Active timestamp styling */
+.timestamp-active {
+  background-color: #f0f8ff; /* Light blue background */
+  border-radius: 3px;
+  padding: 2px 4px;
+  margin: -2px -4px;
+}
+
+/* Highlight the list item containing the active timestamp */
+li.active-marker {
+  background-color: #f6f8fa;
+  border-radius: 4px;
+  padding: 4px 8px;
+  margin-left: -8px;
+}
+
+/* Make list items clickable */
+.transcript-item {
+  cursor: pointer;
+  transition: background-color 0.2s ease;
+  padding: 4px 8px;
+  margin-left: -8px;
+  border-radius: 4px;
+}
+
+.transcript-item:hover {
+  background-color: #f0f0f0;
+}
+
+/* Keyboard shortcuts styling */
+.keyboard-shortcuts {
+  text-align: center;
+  font-size: 14px;
+  color: #666;
+  margin-top: 10px;
+  margin-bottom: 20px;
+}
+
+/* Hide keyboard shortcuts on devices likely without physical keyboards */
+.no-physical-keyboard .keyboard-shortcuts {
+  display: none;
+}
+
+.keyboard-shortcuts kbd {
+  background-color: #f7f7f7;
+  border: 1px solid #ccc;
+  border-radius: 3px;
+  box-shadow: 0 1px 0 rgba(0,0,0,0.2);
+  color: #333;
+  display: inline-block;
+  font-family: monospace;
+  line-height: 1;
+  margin: 0 2px;
+  padding: 3px 5px;
+  white-space: nowrap;
+}
+.asciinema-player-theme-aider {
+  /* Foreground (default text) color */
+  --term-color-foreground: #444444;  /* colour238 */
+
+  /* Background color */
+  --term-color-background: #dadada;  /* colour253 */
+
+  /* Palette of 16 standard ANSI colors */
+  --term-color-0: #21222c;
+  --term-color-1: #ff5555;
+  --term-color-2: #50fa7b;
+  --term-color-3: #f1fa8c;
+  --term-color-4: #bd93f9;
+  --term-color-5: #ff79c6;
+  --term-color-6: #8be9fd;
+  --term-color-7: #f8f8f2;
+  --term-color-8: #6272a4;
+  --term-color-9: #ff6e6e;
+  --term-color-10: #69ff94;
+  --term-color-11: #ffffa5;
+  --term-color-12: #d6acff;
+  --term-color-13: #ff92df;
+  --term-color-14: #a4ffff;
+  --term-color-15: #ffffff;
+}

aider/website/_includes/recording.js

@@ -0,0 +1,349 @@
+document.addEventListener('DOMContentLoaded', function() {
+  let player; // Store player reference to make it accessible to click handlers
+  let globalAudio; // Global audio element to be reused
+  
+  // Detect if device likely has no physical keyboard
+  function detectNoKeyboard() {
+    // Check if it's a touch device (most mobile devices)
+    const isTouchDevice = ('ontouchstart' in window) || 
+                         (navigator.maxTouchPoints > 0) ||
+                         (navigator.msMaxTouchPoints > 0);
+                         
+    // Check common mobile user agents as additional signal
+    const isMobileUA = /Android|webOS|iPhone|iPad|iPod|BlackBerry|IEMobile|Opera Mini/i.test(navigator.userAgent);
+    
+    // If it's a touch device and has a mobile user agent, likely has no physical keyboard
+    if (isTouchDevice && isMobileUA) {
+      document.body.classList.add('no-physical-keyboard');
+    }
+  }
+  
+  // Run detection
+  detectNoKeyboard();
+  
+  // Parse the transcript section to create markers and convert timestamps to links
+  function parseTranscript() {
+    const markers = [];
+    // Find the Commentary heading
+    const transcriptHeading = Array.from(document.querySelectorAll('h2')).find(el => el.textContent.trim() === 'Commentary');
+    
+    if (transcriptHeading) {
+      // Get all list items after the transcript heading
+      let currentElement = transcriptHeading.nextElementSibling;
+      
+      while (currentElement && currentElement.tagName === 'UL') {
+        const listItems = currentElement.querySelectorAll('li');
+        
+        listItems.forEach(item => {
+          const text = item.textContent.trim();
+          const match = text.match(/(\d+):(\d+)\s+(.*)/);
+          
+          if (match) {
+            const minutes = parseInt(match[1], 10);
+            const seconds = parseInt(match[2], 10);
+            const timeInSeconds = minutes * 60 + seconds;
+            const formattedTime = `${minutes}:${seconds.toString().padStart(2, '0')}`;
+            const message = match[3].trim();
+            
+            // Create link for the timestamp
+            const timeLink = document.createElement('a');
+            timeLink.href = '#';
+            timeLink.textContent = formattedTime;
+            timeLink.className = 'timestamp-link';
+            timeLink.dataset.time = timeInSeconds;
+            timeLink.dataset.message = message;
+            
+            // Add click event to seek the player
+            timeLink.addEventListener('click', function(e) {
+              e.preventDefault();
+              if (player && typeof player.seek === 'function') {
+                player.seek(timeInSeconds);
+                player.play();
+                
+                // Also trigger toast and speech
+                showToast(message);
+                speakText(message, timeInSeconds);
+                
+                // Highlight this timestamp
+                highlightTimestamp(timeInSeconds);
+              }
+            });
+            
+            // Replace text with the link + message
+            item.textContent = '';
+            item.appendChild(timeLink);
+            item.appendChild(document.createTextNode(' ' + message));
+            
+            // Add class and click handler to the entire list item
+            item.classList.add('transcript-item');
+            item.dataset.time = timeInSeconds;
+            item.dataset.message = message;
+            
+            item.addEventListener('click', function(e) {
+              // Prevent click event if the user clicked directly on the timestamp link
+              // This prevents double-firing of the event
+              if (e.target !== timeLink) {
+                e.preventDefault();
+                if (player && typeof player.seek === 'function') {
+                  player.seek(timeInSeconds);
+                  player.play();
+                  
+                  // Also trigger toast and speech
+                  showToast(message);
+                  speakText(message, timeInSeconds);
+                  
+                  // Highlight this timestamp
+                  highlightTimestamp(timeInSeconds);
+                }
+              }
+            });
+            
+            markers.push([timeInSeconds, message]);
+          }
+        });
+        
+        currentElement = currentElement.nextElementSibling;
+      }
+    }
+    
+    return markers;
+  }
+
+  // Parse transcript and create markers
+  const markers = parseTranscript();
+  
+  // Create player with a single call
+  player = AsciinemaPlayer.create(
+    recording_url,
+    document.getElementById('demo'),
+    {
+      speed: 1.25,
+      idleTimeLimit: 1,
+      theme: "aider",
+      poster: "npt:0:01",
+      markers: markers
+    }
+  );
+  
+  // Focus on the player element so keyboard shortcuts work immediately
+  setTimeout(() => {
+    // Use setTimeout to ensure the player is fully initialized
+    if (player && typeof player.focus === 'function') {
+      player.focus();
+    } else {
+      // If player doesn't have a focus method, try to find and focus the terminal element
+      const playerElement = document.querySelector('.asciinema-terminal');
+      if (playerElement) {
+        playerElement.focus();
+      } else {
+        // Last resort - try to find element with tabindex
+        const tabbableElement = document.querySelector('[tabindex]');
+        if (tabbableElement) {
+          tabbableElement.focus();
+        }
+      }
+    }
+  }, 100);
+  
+  // Function to display toast notification
+  function showToast(text) {
+    // Get the appropriate container based on fullscreen state
+    let container = document.getElementById('toast-container');
+    const isFullscreen = document.fullscreenElement || 
+                         document.webkitFullscreenElement || 
+                         document.mozFullScreenElement || 
+                         document.msFullscreenElement;
+    
+    // If in fullscreen, check if we need to create a fullscreen toast container
+    if (isFullscreen) {
+      // Target the fullscreen element as the container parent
+      const fullscreenElement = document.fullscreenElement || 
+                               document.webkitFullscreenElement || 
+                               document.mozFullScreenElement || 
+                               document.msFullscreenElement;
+      
+      // Look for an existing fullscreen toast container
+      let fsContainer = fullscreenElement.querySelector('.fs-toast-container');
+      
+      if (!fsContainer) {
+        // Create a new container for fullscreen mode
+        fsContainer = document.createElement('div');
+        fsContainer.className = 'toast-container fs-toast-container';
+        fsContainer.id = 'fs-toast-container';
+        fullscreenElement.appendChild(fsContainer);
+      }
+      
+      container = fsContainer;
+    }
+    
+    // Create toast element
+    const toast = document.createElement('div');
+    toast.className = 'toast-notification';
+    toast.textContent = text;
+    
+    // Add to container
+    container.appendChild(toast);
+    
+    // Trigger animation
+    setTimeout(() => {
+      toast.style.opacity = '1';
+    }, 10);
+    
+    // Remove after 3 seconds
+    setTimeout(() => {
+      toast.style.opacity = '0';
+      setTimeout(() => {
+        if (container && container.contains(toast)) {
+          container.removeChild(toast);
+        }
+      }, 300); // Wait for fade out animation
+    }, 3000);
+  }
+  
+  // Improved browser TTS function
+  function useBrowserTTS(text) {
+    if ('speechSynthesis' in window) {
+      console.log('Using browser TTS fallback');
+      
+      // Cancel any ongoing speech
+      window.speechSynthesis.cancel();
+      
+      const utterance = new SpeechSynthesisUtterance(text);
+      utterance.rate = 1.0;
+      utterance.pitch = 1.0;
+      utterance.volume = 1.0;
+      
+      // For iOS, use a shorter utterance if possible
+      if (/iPad|iPhone|iPod/.test(navigator.userAgent) && !window.MSStream) {
+        utterance.text = text.length > 100 ? text.substring(0, 100) + '...' : text;
+      }
+      
+      utterance.onstart = () => console.log('Speech started');
+      utterance.onend = () => console.log('Speech ended');
+      utterance.onerror = (e) => console.warn('Speech error:', e);
+      
+      window.speechSynthesis.speak(utterance);
+      return true;
+    }
+    console.warn('SpeechSynthesis not supported');
+    return false;
+  }
+  
+  // Function to play pre-generated TTS audio files
+  function speakText(text, timeInSeconds) {
+    // Format time for filename (MM-SS)
+    const minutes = Math.floor(timeInSeconds / 60);
+    const seconds = timeInSeconds % 60;
+    const formattedTime = `${minutes.toString().padStart(2, '0')}-${seconds.toString().padStart(2, '0')}`;
+    
+    // Get recording_id from the page or use default from the URL
+    const recordingId = typeof recording_id !== 'undefined' ? recording_id : 
+                       window.location.pathname.split('/').pop().replace('.html', '');
+                       
+    // Construct audio file path
+    const audioPath = `/assets/audio/${recordingId}/${formattedTime}.mp3`;
+    
+    // Log for debugging
+    console.log(`Attempting to play audio: ${audioPath}`);
+    
+    // Detect iOS
+    const isIOS = /iPad|iPhone|iPod/.test(navigator.userAgent) && !window.MSStream;
+    console.log(`Device is iOS: ${isIOS}`);
+    
+    try {
+      // Create or reuse audio element
+      if (!globalAudio) {
+        globalAudio = new Audio();
+        console.log("Created new global Audio element");
+      }
+      
+      // Set up event handlers
+      globalAudio.onerror = (e) => {
+        console.warn(`Audio error: ${e.type}`, e);
+        useBrowserTTS(text);
+      };
+      
+      // For iOS, preload might help with subsequent plays
+      if (isIOS) {
+        globalAudio.preload = "auto";
+      }
+      
+      // Set the new source
+      globalAudio.src = audioPath;
+      
+      // Play with proper error handling
+      const playPromise = globalAudio.play();
+      
+      if (playPromise !== undefined) {
+        playPromise.catch(error => {
+          console.warn(`Play error: ${error.message}`);
+          
+          // On iOS, a user gesture might be required
+          if (isIOS) {
+            console.log("iOS playback failed, trying SpeechSynthesis");
+          }
+          
+          useBrowserTTS(text);
+        });
+      }
+    } catch (e) {
+      console.error(`Exception in audio playback: ${e.message}`);
+      useBrowserTTS(text);
+    }
+  }
+  
+  // Function to highlight the active timestamp in the transcript
+  function highlightTimestamp(timeInSeconds) {
+    // Remove previous highlights
+    document.querySelectorAll('.timestamp-active').forEach(el => {
+      el.classList.remove('timestamp-active');
+    });
+    
+    document.querySelectorAll('.active-marker').forEach(el => {
+      el.classList.remove('active-marker');
+    });
+    
+    // Find the timestamp link with matching time
+    const timestampLinks = document.querySelectorAll('.timestamp-link');
+    let activeLink = null;
+    
+    for (const link of timestampLinks) {
+      if (parseInt(link.dataset.time) === timeInSeconds) {
+        activeLink = link;
+        break;
+      }
+    }
+    
+    if (activeLink) {
+      // Add highlight class to the link
+      activeLink.classList.add('timestamp-active');
+      
+      // Also highlight the parent list item
+      const listItem = activeLink.closest('li');
+      if (listItem) {
+        listItem.classList.add('active-marker');
+        
+        // No longer scrolling into view to avoid shifting focus
+      }
+    }
+  }
+
+  // Add event listener with safety checks
+  if (player && typeof player.addEventListener === 'function') {
+    player.addEventListener('marker', function(event) {
+      try {
+        const { index, time, label } = event;
+        console.log(`marker! ${index} - ${time} - ${label}`);
+        
+        // Speak the marker label and show toast
+        speakText(label, time);
+        showToast(label);
+        
+        // Highlight the corresponding timestamp in the transcript
+        highlightTimestamp(time);
+      } catch (error) {
+        console.error('Error in marker event handler:', error);
+      }
+    });
+  }
+});

aider/website/_includes/recording.md

@@ -0,0 +1,32 @@
+<link rel="stylesheet" type="text/css" href="/assets/asciinema/asciinema-player.css" />
+
+<style>
+{% include recording.css %}
+</style>
+
+<script src="/assets/asciinema/asciinema-player.min.js"></script>
+<script>
+{% include recording.js %}
+</script>
+
+<div class="page-container">
+  <div class="toast-container" id="toast-container"></div>
+
+  <div class="terminal-container">
+    <div class="terminal-header">
+      <div class="terminal-buttons">
+        <div class="terminal-button terminal-close"></div>
+        <div class="terminal-button terminal-minimize"></div>
+        <div class="terminal-button terminal-expand"></div>
+      </div>
+      <div class="terminal-title">aider</div>
+    </div>
+    <div id="demo"></div>
+  </div>
+</div>
+
+<div class="keyboard-shortcuts">
+  <kbd>Space</kbd> Play/pause —
+  <kbd>f</kbd> Fullscreen —
+  <kbd>←</kbd><kbd>→</kbd> ±5s
+</div>

aider/website/_includes/works-best.md

@@ -1 +1 @@
-Aider works best with Claude 3.5 Sonnet, DeepSeek V3, o1 & GPT-4o and can [connect to almost any LLM](https://aider.chat/docs/llms.html).
+Aider works best with Claude 3.5 Sonnet, DeepSeek R1 & Chat V3, OpenAI o1, o3-mini & GPT-4o. Aider can [connect to almost any LLM, including local models](https://aider.chat/docs/llms.html).

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

@@ -39,9 +39,7 @@ Aider will directly edit the code in your local source files,
 and [git commit the changes](https://aider.chat/docs/git.html)
 with sensible commit messages.
 You can start a new project or work with an existing git repo.
-Aider works well with GPT 3.5, GPT-4, GPT-4 Turbo with Vision,
+{% include works-best.md %}
-and Claude 3 Opus.
-It also supports [connecting to almost any LLM](https://aider.chat/docs/llms.html).
 
 Use the `--browser` switch to launch the browser version of aider:
 

aider/website/assets/audio/auto-accept-architect/metadata.json

@@ -0,0 +1,11 @@
+{
+  "00-01": "We're going to add a new feature to automatically accept edits proposed by the architect model.",
+  "00-11": "First, let's add the new switch.",
+  "00-40": "Aider figured out that it should be passed to the Coder class.",
+  "00-48": "Now we need to implement the functionality.",
+  "01-00": "Let's do some manual testing.",
+  "01-28": "That worked. Let's make sure we can turn it off too.",
+  "02-00": "Let's quickly tidy up the changes to HISTORY.",
+  "02-05": "All done!",
+  "01-42": "That worked too. Let's have aider update the HISTORY file to document the new feature."
+}