Merge pull request #4172 from jesstelford/patch-1

Use system prompt prefix for commit messages

HISTORY.md

@@ -1,11 +1,31 @@
 # Release history
 
+### Aider v0.84.0
+
+- Added support for new Claude models including the Sonnet 4 and Opus 4 series (e.g., `claude-sonnet-4-20250514`,
+`claude-opus-4-20250514`) across various providers. The default `sonnet` and `opus` aliases were updated to these newer
+versions.
+- Added support for the `vertex_ai/gemini-2.5-flash-preview-05-20` model.
+- Fixed OpenRouter token cost calculation for improved accuracy.
+- Updated default OpenRouter models during onboarding to `deepseek/deepseek-r1:free` for the free tier and
+`anthropic/claude-sonnet-4` for paid tiers.
+- Automatically refresh GitHub Copilot tokens when used as OpenAI API keys, by Lih Chen.
+- Aider wrote 79% of the code in this release.
+
+### Aider v0.83.2
+
+- Bumped configargparse to 1.7.1 as 1.7 was pulled.
+- Added shell tab completion for file path arguments (by saviour) and for `--edit-format`/`--editor-edit-format` options.
+- Improved OpenRouter model metadata handling by introducing a local cache, increasing reliability and performance.
+- The `/settings` command now displays detailed metadata for active main, editor, and weak models.
+- Fixed an issue where files explicitly added via the command line were not correctly ignored if listed in `.gitignore`.
+- Improved automatic commit messages by providing more context during their generation, by wangboxue.
+
 ### Aider v0.83.1
 
 - Improved user language detection by correctly normalizing hyphenated language codes (e.g., `en-US` to `en`) and enhancing the validation of locale results.
 - Prevented Aider from instructing the LLM to reply in 'C' or 'POSIX' when these are detected as the system locale.
 - Displayed a spinner with the model name when generating commit messages.
-- Aider wrote 74% of the code in this release.
 
 ### Aider v0.83.0
 
@@ -411,7 +431,7 @@
 - [Aider works with LLM web chat UIs](https://aider.chat/docs/usage/copypaste.html).
   - New `--copy-paste` mode.
   - New `/copy-context` command.
-- [Set API keys and other environment variables for all providers from command line or yaml conf file](https://aider.chat/docs/config/aider_conf.html#storing-llm-keys).
+- [Set API keys and other environment variables for all providers from command line or YAML conf file](https://aider.chat/docs/config/aider_conf.html#storing-llm-keys).
   - New `--api-key provider=key` setting.
   - New `--set-env VAR=value` setting.
 - Added bash and zsh support to `--watch-files`.
@@ -579,7 +599,7 @@
 
 ### Aider v0.59.1
 
-- Check for obsolete `yes: true` in yaml config, show helpful error.
+- Check for obsolete `yes: true` in YAML config, show helpful error.
 - Model settings for openrouter/anthropic/claude-3.5-sonnet:beta
 
 ### Aider v0.59.0
@@ -589,7 +609,7 @@
   - Still auto-completes the full paths of the repo files like `/add`.
   - Now supports globs like `src/**/*.py`
 - Renamed `--yes` to `--yes-always`.
-  - Now uses `AIDER_YES_ALWAYS` env var and `yes-always:` yaml key.
+  - Now uses `AIDER_YES_ALWAYS` env var and `yes-always:` YAML key.
   - Existing YAML and .env files will need to be updated.
   - Can still abbreviate to `--yes` on the command line.
 - Config file now uses standard YAML list syntax with `  - list entries`, one per line.  
@@ -796,7 +816,7 @@
   - Use `--map-refresh <always|files|manual|auto>` to configure.
 - Improved cost estimate logic for caching.
 - Improved editing performance on Jupyter Notebook `.ipynb` files.
-- Show which config yaml file is loaded with `--verbose`.
+- Show which config YAML file is loaded with `--verbose`.
 - Bumped dependency versions.
 - Bugfix: properly load `.aider.models.metadata.json` data.
 - Bugfix: Using `--msg /ask ...` caused an exception.

README.md

@@ -27,13 +27,13 @@ cog.out(text)
   <a href="https://github.com/Aider-AI/aider/stargazers"><img alt="GitHub Stars" title="Total number of GitHub stars the Aider project has received"
 src="https://img.shields.io/github/stars/Aider-AI/aider?style=flat-square&logo=github&color=f1c40f&labelColor=555555"/></a>
   <a href="https://pypi.org/project/aider-chat/"><img alt="PyPI Downloads" title="Total number of installations via pip from PyPI"
-src="https://img.shields.io/badge/📦%20Installs-2.2M-2ecc71?style=flat-square&labelColor=555555"/></a>
+src="https://img.shields.io/badge/📦%20Installs-2.4M-2ecc71?style=flat-square&labelColor=555555"/></a>
   <img alt="Tokens per week" title="Number of tokens processed weekly by Aider users"
 src="https://img.shields.io/badge/📈%20Tokens%2Fweek-15B-3498db?style=flat-square&labelColor=555555"/>
   <a href="https://openrouter.ai/#options-menu"><img alt="OpenRouter Ranking" title="Aider's ranking among applications on the OpenRouter platform"
 src="https://img.shields.io/badge/🏆%20OpenRouter-Top%2020-9b59b6?style=flat-square&labelColor=555555"/></a>
   <a href="https://aider.chat/HISTORY.html"><img alt="Singularity" title="Percentage of the new code in Aider's last release written by Aider itself"
-src="https://img.shields.io/badge/🔄%20Singularity-54%25-e74c3c?style=flat-square&labelColor=555555"/></a>
+src="https://img.shields.io/badge/🔄%20Singularity-79%25-e74c3c?style=flat-square&labelColor=555555"/></a>
 <!--[[[end]]]-->  
 </p>
 
@@ -136,6 +136,7 @@ See the [installation instructions](https://aider.chat/docs/install.html) and [u
 - [LLM Leaderboards](https://aider.chat/docs/leaderboards/)
 - [GitHub Repository](https://github.com/Aider-AI/aider)
 - [Discord Community](https://discord.gg/Y7X7bhMQFV)
+- [Release notes](https://aider.chat/HISTORY.html)
 - [Blog](https://aider.chat/blog/)
 
 ## Kind Words From Users

aider/__init__.py

@@ -1,6 +1,6 @@
 from packaging import version
 
-__version__ = "0.83.2.dev"
+__version__ = "0.84.1.dev"
 safe_version = __version__
 
 try:

aider/args.py

@@ -40,10 +40,22 @@ def get_parser(default_config_files, git_root):
         config_file_parser_class=configargparse.YAMLConfigFileParser,
         auto_env_var_prefix="AIDER_",
     )
+    # List of valid edit formats for argparse validation & shtab completion.
+    # Dynamically gather them from the registered coder classes so the list
+    # stays in sync if new formats are added.
+    from aider import coders as _aider_coders
+
+    edit_format_choices = sorted(
+        {
+            c.edit_format
+            for c in _aider_coders.__all__
+            if hasattr(c, "edit_format") and c.edit_format is not None
+        }
+    )
     group = parser.add_argument_group("Main model")
     group.add_argument(
         "files", metavar="FILE", nargs="*", help="files to edit with an LLM (optional)"
-    )
+    ).complete = shtab.FILE
     group.add_argument(
         "--model",
         metavar="MODEL",
@@ -110,13 +122,13 @@ def get_parser(default_config_files, git_root):
         metavar="MODEL_SETTINGS_FILE",
         default=".aider.model.settings.yml",
         help="Specify a file with aider model settings for unknown models",
-    )
+    ).complete = shtab.FILE
     group.add_argument(
         "--model-metadata-file",
         metavar="MODEL_METADATA_FILE",
         default=".aider.model.metadata.json",
         help="Specify a file with context window and costs for unknown models",
-    )
+    ).complete = shtab.FILE
     group.add_argument(
         "--alias",
         action="append",
@@ -149,6 +161,7 @@ def get_parser(default_config_files, git_root):
         "--edit-format",
         "--chat-mode",
         metavar="EDIT_FORMAT",
+        choices=edit_format_choices,
         default=None,
         help="Specify what edit format the LLM should use (default depends on model)",
     )
@@ -183,6 +196,7 @@ def get_parser(default_config_files, git_root):
     group.add_argument(
         "--editor-edit-format",
         metavar="EDITOR_EDIT_FORMAT",
+        choices=edit_format_choices,
         default=None,
         help="Specify the edit format for the editor model (default: depends on editor model)",
     )
@@ -262,13 +276,13 @@ def get_parser(default_config_files, git_root):
         metavar="INPUT_HISTORY_FILE",
         default=default_input_history_file,
         help=f"Specify the chat input history file (default: {default_input_history_file})",
-    )
+    ).complete = shtab.FILE
     group.add_argument(
         "--chat-history-file",
         metavar="CHAT_HISTORY_FILE",
         default=default_chat_history_file,
         help=f"Specify the chat history file (default: {default_chat_history_file})",
-    )
+    ).complete = shtab.FILE
     group.add_argument(
         "--restore-chat-history",
         action=argparse.BooleanOptionalAction,
@@ -280,7 +294,7 @@ def get_parser(default_config_files, git_root):
         metavar="LLM_HISTORY_FILE",
         default=None,
         help="Log the conversation with the LLM to this file (for example, .aider.llm.history)",
-    )
+    ).complete = shtab.FILE
 
     ##########
     group = parser.add_argument_group("Output settings")
@@ -406,7 +420,7 @@ def get_parser(default_config_files, git_root):
         type=lambda path_str: resolve_aiderignore_path(path_str, git_root),
         default=default_aiderignore_file,
         help="Specify the aider ignore file (default: .aiderignore in git root)",
-    )
+    ).complete = shtab.FILE
     group.add_argument(
         "--subtree-only",
         action="store_true",
@@ -552,7 +566,7 @@ def get_parser(default_config_files, git_root):
         "--analytics-log",
         metavar="ANALYTICS_LOG_FILE",
         help="Specify a file to log analytics events",
-    )
+    ).complete = shtab.FILE
     group.add_argument(
         "--analytics-disable",
         action="store_true",
@@ -619,7 +633,7 @@ def get_parser(default_config_files, git_root):
             "Specify a file containing the message to send the LLM, process reply, then exit"
             " (disables chat mode)"
         ),
-    )
+    ).complete = shtab.FILE
     group.add_argument(
         "--gui",
         "--browser",
@@ -637,7 +651,7 @@ def get_parser(default_config_files, git_root):
         "--apply",
         metavar="FILE",
         help="Apply the changes from the given file instead of running the chat (debug)",
-    )
+    ).complete = shtab.FILE
     group.add_argument(
         "--apply-clipboard-edits",
         action="store_true",
@@ -698,13 +712,13 @@ def get_parser(default_config_files, git_root):
         action="append",
         metavar="FILE",
         help="specify a file to edit (can be used multiple times)",
-    )
+    ).complete = shtab.FILE
     group.add_argument(
         "--read",
         action="append",
         metavar="FILE",
         help="specify a read-only file (can be used multiple times)",
-    )
+    ).complete = shtab.FILE
     group.add_argument(
         "--vim",
         action="store_true",
@@ -717,6 +731,12 @@ def get_parser(default_config_files, git_root):
         default=None,
         help="Specify the language to use in the chat (default: None, uses system settings)",
     )
+    group.add_argument(
+        "--commit-language",
+        metavar="COMMIT_LANGUAGE",
+        default=None,
+        help="Specify the language to use in the commit message (default: None, user language)",
+    )
     group.add_argument(
         "--yes-always",
         action="store_true",
@@ -734,7 +754,7 @@ def get_parser(default_config_files, git_root):
         "--load",
         metavar="LOAD_FILE",
         help="Load and execute /commands from a file on launch",
-    )
+    ).complete = shtab.FILE
     group.add_argument(
         "--encoding",
         default="utf-8",
@@ -755,7 +775,7 @@ def get_parser(default_config_files, git_root):
             "Specify the config file (default: search for .aider.conf.yml in git root, cwd"
             " or home directory)"
         ),
-    )
+    ).complete = shtab.FILE
     # This is a duplicate of the argument in the preparser and is a no-op by this time of
     # argument parsing, but it's here so that the help is displayed as expected.
     group.add_argument(
@@ -763,7 +783,7 @@ def get_parser(default_config_files, git_root):
         metavar="ENV_FILE",
         default=default_env_file(git_root),
         help="Specify the .env file to load (default: .env in git root)",
-    )
+    ).complete = shtab.FILE
     group.add_argument(
         "--suggest-shell-commands",
         action=argparse.BooleanOptionalAction,

aider/args_formatter.py

@@ -96,7 +96,7 @@ class YamlHelpFormatter(argparse.HelpFormatter):
 # Place in your home dir, or at the root of your git repo.
 ##########################################################
 
-# Note: You can only put OpenAI and Anthropic API keys in the yaml
+# Note: You can only put OpenAI and Anthropic API keys in the YAML
 # config file. Keys for all APIs can be stored in a .env file
 # https://aider.chat/docs/config/dotenv.html
 

aider/coders/base_coder.py

@@ -118,6 +118,7 @@ class Coder:
     detect_urls = True
     ignore_mentions = None
     chat_language = None
+    commit_language = None
     file_watcher = None
 
     @classmethod
@@ -328,6 +329,7 @@ class Coder:
         num_cache_warming_pings=0,
         suggest_shell_commands=True,
         chat_language=None,
+        commit_language=None,
         detect_urls=True,
         ignore_mentions=None,
         total_tokens_sent=0,
@@ -341,6 +343,7 @@ class Coder:
 
         self.event = self.analytics.event
         self.chat_language = chat_language
+        self.commit_language = commit_language
         self.commit_before_message = []
         self.aider_commit_hashes = set()
         self.rejected_urls = set()
@@ -445,6 +448,7 @@ class Coder:
             fname = Path(fname)
             if self.repo and self.repo.git_ignored_file(fname):
                 self.io.tool_warning(f"Skipping {fname} that matches gitignore spec.")
+                continue
 
             if self.repo and self.repo.ignored_file(fname):
                 self.io.tool_warning(f"Skipping {fname} that matches aiderignore spec.")

aider/coders/search_replace.py

@@ -109,7 +109,7 @@ class RelativeIndenter:
         """
 
         if self.marker in text:
-            raise ValueError("Text already contains the outdent marker: {self.marker}")
+            raise ValueError(f"Text already contains the outdent marker: {self.marker}")
 
         lines = text.splitlines(keepends=True)
 

aider/commands.py

@@ -346,7 +346,7 @@ class Commands:
             return
 
         commit_message = args.strip() if args else None
-        self.coder.repo.commit(message=commit_message)
+        self.coder.repo.commit(message=commit_message, coder=self.coder)
 
     def cmd_lint(self, args="", fnames=None):
         "Lint and fix in-chat files or all dirty files if none in chat"
@@ -1392,7 +1392,30 @@ class Commands:
         "Print out the current settings"
         settings = format_settings(self.parser, self.args)
         announcements = "\n".join(self.coder.get_announcements())
+
+        # Build metadata for the active models (main, editor, weak)
+        model_sections = []
+        active_models = [
+            ("Main model", self.coder.main_model),
+            ("Editor model", getattr(self.coder.main_model, "editor_model", None)),
+            ("Weak model", getattr(self.coder.main_model, "weak_model", None)),
+        ]
+        for label, model in active_models:
+            if not model:
+                continue
+            info = getattr(model, "info", {}) or {}
+            if not info:
+                continue
+            model_sections.append(f"{label} ({model.name}):")
+            for k, v in sorted(info.items()):
+                model_sections.append(f"  {k}: {v}")
+            model_sections.append("")  # blank line between models
+
+        model_metadata = "\n".join(model_sections)
+
         output = f"{announcements}\n{settings}"
+        if model_metadata:
+            output += "\n" + model_metadata
         self.io.tool_output(output)
 
     def completions_raw_load(self, document, complete_event):

aider/io.py

@@ -749,7 +749,7 @@ class InputOutput:
         if not self.llm_history_file:
             return
         timestamp = datetime.now().isoformat(timespec="seconds")
-        with open(self.llm_history_file, "a", encoding=self.encoding) as log_file:
+        with open(self.llm_history_file, "a", encoding="utf-8") as log_file:
             log_file.write(f"{role.upper()} {timestamp}\n")
             log_file.write(content + "\n")
 

aider/main.py

@@ -993,6 +993,7 @@ def main(argv=None, input=None, output=None, force_git_root=None, return_coder=F
             num_cache_warming_pings=args.cache_keepalive_pings,
             suggest_shell_commands=args.suggest_shell_commands,
             chat_language=args.chat_language,
+            commit_language=args.commit_language,
             detect_urls=args.detect_urls,
             auto_copy_context=args.copy_paste,
             auto_accept_architect=args.auto_accept_architect,

aider/models.py

@@ -8,6 +8,7 @@ import platform
 import sys
 import time
 from dataclasses import dataclass, fields
+from datetime import datetime
 from pathlib import Path
 from typing import Optional, Union
 
@@ -15,8 +16,10 @@ import json5
 import yaml
 from PIL import Image
 
+from aider import __version__
 from aider.dump import dump  # noqa: F401
 from aider.llm import litellm
+from aider.openrouter import OpenRouterModelManager
 from aider.sendchat import ensure_alternating_roles, sanity_check_messages
 from aider.utils import check_pip_install_extra
 
@@ -69,6 +72,8 @@ claude-3-opus-20240229
 claude-3-sonnet-20240229
 claude-3-5-sonnet-20240620
 claude-3-5-sonnet-20241022
+claude-sonnet-4-20250514
+claude-opus-4-20250514
 """
 
 ANTHROPIC_MODELS = [ln.strip() for ln in ANTHROPIC_MODELS.splitlines() if ln.strip()]
@@ -76,9 +81,9 @@ 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": "anthropic/claude-3-7-sonnet-20250219",
+    "sonnet": "anthropic/claude-sonnet-4-20250514",
     "haiku": "claude-3-5-haiku-20241022",
-    "opus": "claude-3-opus-20240229",
+    "opus": "claude-opus-4-20250514",
     # GPT models
     "4": "gpt-4-0613",
     "4o": "gpt-4o",
@@ -149,8 +154,13 @@ class ModelInfoManager:
         self.verify_ssl = True
         self._cache_loaded = False
 
+        # Manager for the cached OpenRouter model database
+        self.openrouter_manager = OpenRouterModelManager()
+
     def set_verify_ssl(self, verify_ssl):
         self.verify_ssl = verify_ssl
+        if hasattr(self, "openrouter_manager"):
+            self.openrouter_manager.set_verify_ssl(verify_ssl)
 
     def _load_cache(self):
         if self._cache_loaded:
@@ -232,6 +242,12 @@ class ModelInfoManager:
             return litellm_info
 
         if not cached_info and model.startswith("openrouter/"):
+            # First try using the locally cached OpenRouter model database
+            openrouter_info = self.openrouter_manager.get_model_info(model)
+            if openrouter_info:
+                return openrouter_info
+
+            # Fallback to legacy web-scraping if the API cache does not contain the model
             openrouter_info = self.fetch_openrouter_model_info(model)
             if openrouter_info:
                 return openrouter_info
@@ -861,6 +877,57 @@ class Model(ModelSettings):
     def is_ollama(self):
         return self.name.startswith("ollama/") or self.name.startswith("ollama_chat/")
 
+    def github_copilot_token_to_open_ai_key(self, extra_headers):
+        # check to see if there's an openai api key
+        # If so, check to see if it's expire
+        openai_api_key = "OPENAI_API_KEY"
+
+        if openai_api_key not in os.environ or (
+            int(dict(x.split("=") for x in os.environ[openai_api_key].split(";"))["exp"])
+            < int(datetime.now().timestamp())
+        ):
+            import requests
+
+            class GitHubCopilotTokenError(Exception):
+                """Custom exception for GitHub Copilot token-related errors."""
+
+                pass
+
+            # Validate GitHub Copilot token exists
+            if "GITHUB_COPILOT_TOKEN" not in os.environ:
+                raise KeyError("GITHUB_COPILOT_TOKEN environment variable not found")
+
+            github_token = os.environ["GITHUB_COPILOT_TOKEN"]
+            if not github_token.strip():
+                raise KeyError("GITHUB_COPILOT_TOKEN environment variable is empty")
+
+            headers = {
+                "Authorization": f"Bearer {os.environ['GITHUB_COPILOT_TOKEN']}",
+                "Editor-Version": extra_headers["Editor-Version"],
+                "Copilot-Integration-Id": extra_headers["Copilot-Integration-Id"],
+                "Content-Type": "application/json",
+            }
+
+            url = "https://api.github.com/copilot_internal/v2/token"
+            res = requests.get(url, headers=headers)
+            if res.status_code != 200:
+                safe_headers = {k: v for k, v in headers.items() if k != "Authorization"}
+                token_preview = github_token[:5] + "..." if len(github_token) >= 5 else github_token
+                safe_headers["Authorization"] = f"Bearer {token_preview}"
+                raise GitHubCopilotTokenError(
+                    f"GitHub Copilot API request failed (Status: {res.status_code})\n"
+                    f"URL: {url}\n"
+                    f"Headers: {json.dumps(safe_headers, indent=2)}\n"
+                    f"JSON: {res.text}"
+                )
+
+            response_data = res.json()
+            token = response_data.get("token")
+            if not token:
+                raise GitHubCopilotTokenError("Response missing 'token' field")
+
+            os.environ[openai_api_key] = token
+
     def send_completion(self, messages, functions, stream, temperature=None):
         if os.environ.get("AIDER_SANITY_CHECK_TURNS"):
             sanity_check_messages(messages)
@@ -902,6 +969,16 @@ class Model(ModelSettings):
             dump(kwargs)
         kwargs["messages"] = messages
 
+        # Are we using github copilot?
+        if "GITHUB_COPILOT_TOKEN" in os.environ:
+            if "extra_headers" not in kwargs:
+                kwargs["extra_headers"] = {
+                    "Editor-Version": f"aider/{__version__}",
+                    "Copilot-Integration-Id": "vscode-chat",
+                }
+
+            self.github_copilot_token_to_open_ai_key(kwargs["extra_headers"])
+
         res = litellm.completion(**kwargs)
         return hash_object, res
 

aider/onboarding.py

@@ -55,9 +55,9 @@ def try_to_select_default_model():
         # Check if the user is on a free tier
         is_free_tier = check_openrouter_tier(openrouter_key)
         if is_free_tier:
-            return "openrouter/google/gemini-2.5-pro-exp-03-25:free"
+            return "openrouter/deepseek/deepseek-r1:free"
         else:
-            return "openrouter/anthropic/claude-3.7-sonnet"
+            return "openrouter/anthropic/claude-sonnet-4"
 
     # Select model based on other available API keys
     model_key_pairs = [

aider/openrouter.py

@@ -0,0 +1,128 @@
+"""
+OpenRouter model metadata caching and lookup.
+
+This module keeps a local cached copy of the OpenRouter model list
+(downloaded from ``https://openrouter.ai/api/v1/models``) and exposes a
+helper class that returns metadata for a given model in a format compatible
+with litellm’s ``get_model_info``.
+"""
+from __future__ import annotations
+
+import json
+import time
+from pathlib import Path
+from typing import Dict
+
+import requests
+
+
+def _cost_per_token(val: str | None) -> float | None:
+    """Convert a price string (USD per token) to a float."""
+    if val in (None, "", "0"):
+        return 0.0 if val == "0" else None
+    try:
+        return float(val)
+    except Exception:  # noqa: BLE001
+        return None
+
+
+class OpenRouterModelManager:
+    MODELS_URL = "https://openrouter.ai/api/v1/models"
+    CACHE_TTL = 60 * 60 * 24  # 24 h
+
+    def __init__(self) -> None:
+        self.cache_dir = Path.home() / ".aider" / "caches"
+        self.cache_file = self.cache_dir / "openrouter_models.json"
+        self.content: Dict | None = None
+        self.verify_ssl: bool = True
+        self._cache_loaded = False
+
+    # ------------------------------------------------------------------ #
+    # Public API                                                         #
+    # ------------------------------------------------------------------ #
+    def set_verify_ssl(self, verify_ssl: bool) -> None:
+        """Enable/disable SSL verification for API requests."""
+        self.verify_ssl = verify_ssl
+
+    def get_model_info(self, model: str) -> Dict:
+        """
+        Return metadata for *model* or an empty ``dict`` when unknown.
+
+        ``model`` should use the aider naming convention, e.g.
+        ``openrouter/nousresearch/deephermes-3-mistral-24b-preview:free``.
+        """
+        self._ensure_content()
+        if not self.content or "data" not in self.content:
+            return {}
+
+        route = self._strip_prefix(model)
+
+        # Consider both the exact id and id without any “:suffix”.
+        candidates = {route}
+        if ":" in route:
+            candidates.add(route.split(":", 1)[0])
+
+        record = next((item for item in self.content["data"] if item.get("id") in candidates), None)
+        if not record:
+            return {}
+
+        context_len = (
+            record.get("top_provider", {}).get("context_length")
+            or record.get("context_length")
+            or None
+        )
+
+        pricing = record.get("pricing", {})
+        return {
+            "max_input_tokens": context_len,
+            "max_tokens": context_len,
+            "max_output_tokens": context_len,
+            "input_cost_per_token": _cost_per_token(pricing.get("prompt")),
+            "output_cost_per_token": _cost_per_token(pricing.get("completion")),
+            "litellm_provider": "openrouter",
+        }
+
+    # ------------------------------------------------------------------ #
+    # Internal helpers                                                   #
+    # ------------------------------------------------------------------ #
+    def _strip_prefix(self, model: str) -> str:
+        return model[len("openrouter/") :] if model.startswith("openrouter/") else model
+
+    def _ensure_content(self) -> None:
+        self._load_cache()
+        if not self.content:
+            self._update_cache()
+
+    def _load_cache(self) -> None:
+        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:
+                    try:
+                        self.content = json.loads(self.cache_file.read_text())
+                    except json.JSONDecodeError:
+                        self.content = None
+        except OSError:
+            # Cache directory might be unwritable; ignore.
+            pass
+
+        self._cache_loaded = True
+
+    def _update_cache(self) -> None:
+        try:
+            response = requests.get(self.MODELS_URL, timeout=10, verify=self.verify_ssl)
+            if response.status_code == 200:
+                self.content = response.json()
+                try:
+                    self.cache_file.write_text(json.dumps(self.content, indent=2))
+                except OSError:
+                    pass  # Non-fatal if we can’t write the cache
+        except Exception as ex:  # noqa: BLE001
+            print(f"Failed to fetch OpenRouter model list: {ex}")
+            try:
+                self.cache_file.write_text("{}")
+            except OSError:
+                pass

aider/repo.py

@@ -210,7 +210,9 @@ class GitRepo:
         else:
             user_language = None
             if coder:
-                user_language = coder.get_user_language()
+                user_language = coder.commit_language
+                if not user_language:
+                    user_language = coder.get_user_language()
             commit_message = self.get_commit_message(diffs, context, user_language)
 
         # Retrieve attribute settings, prioritizing coder.args if available
@@ -332,24 +334,32 @@ class GitRepo:
         content += diffs
 
         system_content = self.commit_prompt or prompts.commit_system
+
         language_instruction = ""
         if user_language:
             language_instruction = f"\n- Is written in {user_language}."
         system_content = system_content.format(language_instruction=language_instruction)
 
-        messages = [
-            dict(role="system", content=system_content),
-            dict(role="user", content=content),
-        ]
-
         commit_message = None
         for model in self.models:
             spinner_text = f"Generating commit message with {model.name}"
             with WaitingSpinner(spinner_text):
+                if model.system_prompt_prefix:
+                    current_system_content = model.system_prompt_prefix + "\n" + system_content
+                else:
+                    current_system_content = system_content
+
+                messages = [
+                    dict(role="system", content=current_system_content),
+                    dict(role="user", content=content),
+                ]
+
                 num_tokens = model.token_count(messages)
                 max_tokens = model.info.get("max_input_tokens") or 0
+
                 if max_tokens and num_tokens > max_tokens:
                     continue
+
                 commit_message = model.simple_send_with_retries(messages)
                 if commit_message:
                     break  # Found a model that could generate the message
@@ -389,14 +399,20 @@ class GitRepo:
         try:
             if current_branch_has_commits:
                 args = ["HEAD", "--"] + list(fnames)
-                diffs += self.repo.git.diff(*args)
+                diffs += self.repo.git.diff(*args, stdout_as_string=False).decode(
+                    self.io.encoding, "replace"
+                )
                 return diffs
 
             wd_args = ["--"] + list(fnames)
             index_args = ["--cached"] + wd_args
 
-            diffs += self.repo.git.diff(*index_args)
+            diffs += self.repo.git.diff(*index_args, stdout_as_string=False).decode(
-            diffs += self.repo.git.diff(*wd_args)
+                self.io.encoding, "replace"
+            )
+            diffs += self.repo.git.diff(*wd_args, stdout_as_string=False).decode(
+                self.io.encoding, "replace"
+            )
 
             return diffs
         except ANY_GIT_ERROR as err:
@@ -410,7 +426,9 @@ class GitRepo:
             args += ["--color=never"]
 
         args += [from_commit, to_commit]
-        diffs = self.repo.git.diff(*args)
+        diffs = self.repo.git.diff(*args, stdout_as_string=False).decode(
+            self.io.encoding, "replace"
+        )
 
         return diffs
 

aider/resources/model-metadata.json

@@ -49,7 +49,7 @@
     },
     "openrouter/deepseek/deepseek-chat-v3-0324": {
         "max_tokens": 8192,
-        "max_input_tokens": 64000,
+        "max_input_tokens": 131072,
         "max_output_tokens": 8192,
         "input_cost_per_token": 0.00000055,
         "input_cost_per_token_cache_hit": 0.00000014,

aider/resources/model-settings.yml

@@ -1436,3 +1436,332 @@
 #    min_p: 0.0
 #    temperature: 0.7  
 
+
+- name: claude-sonnet-4-20250514
+  edit_format: diff
+  weak_model_name: claude-3-5-haiku-20241022
+  use_repo_map: true
+  examples_as_sys_msg: false
+  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-sonnet-4-20250514
+  editor_edit_format: editor-diff
+  accepts_settings: ["thinking_tokens"]
+
+- name: anthropic/claude-sonnet-4-20250514
+  edit_format: diff
+  weak_model_name: anthropic/claude-3-5-haiku-20241022
+  use_repo_map: true
+  examples_as_sys_msg: false
+  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-sonnet-4-20250514
+  editor_edit_format: editor-diff
+  accepts_settings: ["thinking_tokens"]
+
+- name: bedrock/anthropic.claude-sonnet-4-20250514-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: false
+  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-sonnet-4-20250514-v1:0
+  editor_edit_format: editor-diff
+  accepts_settings: ["thinking_tokens"]
+
+- name: bedrock/us.anthropic.claude-sonnet-4-20250514-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: false
+  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-sonnet-4-20250514-v1:0
+  editor_edit_format: editor-diff
+  accepts_settings: ["thinking_tokens"]
+
+- name: bedrock_converse/anthropic.claude-sonnet-4-20250514-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: false
+  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-sonnet-4-20250514-v1:0
+  editor_edit_format: editor-diff
+  accepts_settings: ["thinking_tokens"]
+
+- name: bedrock_converse/us.anthropic.claude-sonnet-4-20250514-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: false
+  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-sonnet-4-20250514-v1:0
+  editor_edit_format: editor-diff
+  accepts_settings: ["thinking_tokens"]
+
+- name: vertex_ai/claude-sonnet-4@20250514
+  edit_format: diff
+  weak_model_name: vertex_ai/claude-3-5-haiku@20241022
+  use_repo_map: true
+  examples_as_sys_msg: false
+  extra_params:
+    max_tokens: 64000
+  editor_model_name: vertex_ai/claude-sonnet-4@20250514
+  editor_edit_format: editor-diff
+  accepts_settings: ["thinking_tokens"]
+
+- name: vertex_ai-anthropic_models/vertex_ai/claude-sonnet-4@20250514
+  edit_format: diff
+  weak_model_name: vertex_ai/claude-3-5-haiku@20241022
+  use_repo_map: true
+  examples_as_sys_msg: false
+  extra_params:
+    max_tokens: 64000
+  editor_model_name: vertex_ai-anthropic_models/vertex_ai/claude-sonnet-4@20250514
+  editor_edit_format: editor-diff
+  accepts_settings: ["thinking_tokens"]
+
+- name: openrouter/anthropic/claude-sonnet-4
+  edit_format: diff
+  weak_model_name: openrouter/anthropic/claude-3-5-haiku
+  use_repo_map: true
+  examples_as_sys_msg: false
+  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-sonnet-4
+  editor_edit_format: editor-diff
+  accepts_settings: ["thinking_tokens"]
+
+- name: anthropic.claude-sonnet-4-20250514-v1:0
+  edit_format: diff
+  weak_model_name: anthropic.claude-3-5-haiku-20241022-v1:0
+  use_repo_map: true
+  examples_as_sys_msg: false
+  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-sonnet-4-20250514-v1:0
+  editor_edit_format: editor-diff
+  accepts_settings: ["thinking_tokens"]
+
+- name: bedrock_converse/eu.anthropic.claude-sonnet-4-20250514-v1:0
+  edit_format: diff
+  weak_model_name: bedrock_converse/eu.anthropic.claude-3-5-haiku-20241022-v1:0
+  use_repo_map: true
+  examples_as_sys_msg: false
+  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/eu.anthropic.claude-sonnet-4-20250514-v1:0
+  editor_edit_format: editor-diff
+  accepts_settings: ["thinking_tokens"]
+
+- name: eu.anthropic.claude-sonnet-4-20250514-v1:0
+  edit_format: diff
+  weak_model_name: eu.anthropic.claude-3-5-haiku-20241022-v1:0
+  use_repo_map: true
+  examples_as_sys_msg: false
+  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: eu.anthropic.claude-sonnet-4-20250514-v1:0
+  editor_edit_format: editor-diff
+  accepts_settings: ["thinking_tokens"]
+
+- name: us.anthropic.claude-sonnet-4-20250514-v1:0
+  edit_format: diff
+  weak_model_name: us.anthropic.claude-3-5-haiku-20241022-v1:0
+  use_repo_map: true
+  examples_as_sys_msg: false
+  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: us.anthropic.claude-sonnet-4-20250514-v1:0
+  editor_edit_format: editor-diff
+  accepts_settings: ["thinking_tokens"]
+
+- name: claude-opus-4-20250514
+  edit_format: diff
+  weak_model_name: claude-3-5-haiku-20241022
+  use_repo_map: true
+  examples_as_sys_msg: false
+  extra_params:
+    extra_headers:
+      anthropic-beta: prompt-caching-2024-07-31,pdfs-2024-09-25,output-128k-2025-02-19
+    max_tokens: 32000
+  cache_control: true
+  editor_model_name: claude-sonnet-4-20250514
+  editor_edit_format: editor-diff
+  accepts_settings: ["thinking_tokens"]
+
+- name: anthropic/claude-opus-4-20250514
+  edit_format: diff
+  weak_model_name: anthropic/claude-3-5-haiku-20241022
+  use_repo_map: true
+  examples_as_sys_msg: false
+  extra_params:
+    extra_headers:
+      anthropic-beta: prompt-caching-2024-07-31,pdfs-2024-09-25,output-128k-2025-02-19
+    max_tokens: 32000
+  cache_control: true
+  editor_model_name: anthropic/claude-sonnet-4-20250514
+  editor_edit_format: editor-diff
+  accepts_settings: ["thinking_tokens"]
+
+- name: anthropic.claude-opus-4-20250514-v1:0
+  edit_format: diff
+  weak_model_name: anthropic.claude-3-5-haiku-20241022-v1:0
+  use_repo_map: true
+  examples_as_sys_msg: false
+  extra_params:
+    extra_headers:
+      anthropic-beta: prompt-caching-2024-07-31,pdfs-2024-09-25,output-128k-2025-02-19
+    max_tokens: 32000
+  cache_control: true
+  editor_model_name: anthropic.claude-sonnet-4-20250514-v1:0
+  editor_edit_format: editor-diff
+  accepts_settings: ["thinking_tokens"]
+
+- name: bedrock_converse/anthropic.claude-opus-4-20250514-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: false
+  extra_params:
+    extra_headers:
+      anthropic-beta: prompt-caching-2024-07-31,pdfs-2024-09-25,output-128k-2025-02-19
+    max_tokens: 32000
+  cache_control: true
+  editor_model_name: bedrock_converse/anthropic.claude-sonnet-4-20250514-v1:0
+  editor_edit_format: editor-diff
+  accepts_settings: ["thinking_tokens"]
+
+- name: bedrock_converse/us.anthropic.claude-opus-4-20250514-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: false
+  extra_params:
+    extra_headers:
+      anthropic-beta: prompt-caching-2024-07-31,pdfs-2024-09-25,output-128k-2025-02-19
+    max_tokens: 32000
+  cache_control: true
+  editor_model_name: bedrock_converse/us.anthropic.claude-sonnet-4-20250514-v1:0
+  editor_edit_format: editor-diff
+  accepts_settings: ["thinking_tokens"]
+
+- name: bedrock_converse/eu.anthropic.claude-opus-4-20250514-v1:0
+  edit_format: diff
+  weak_model_name: bedrock_converse/eu.anthropic.claude-3-5-haiku-20241022-v1:0
+  use_repo_map: true
+  examples_as_sys_msg: false
+  extra_params:
+    extra_headers:
+      anthropic-beta: prompt-caching-2024-07-31,pdfs-2024-09-25,output-128k-2025-02-19
+    max_tokens: 32000
+  cache_control: true
+  editor_model_name: bedrock_converse/eu.anthropic.claude-sonnet-4-20250514-v1:0
+  editor_edit_format: editor-diff
+  accepts_settings: ["thinking_tokens"]
+
+- name: eu.anthropic.claude-opus-4-20250514-v1:0
+  edit_format: diff
+  weak_model_name: eu.anthropic.claude-3-5-haiku-20241022-v1:0
+  use_repo_map: true
+  examples_as_sys_msg: false
+  extra_params:
+    extra_headers:
+      anthropic-beta: prompt-caching-2024-07-31,pdfs-2024-09-25,output-128k-2025-02-19
+    max_tokens: 32000
+  cache_control: true
+  editor_model_name: eu.anthropic.claude-sonnet-4-20250514-v1:0
+  editor_edit_format: editor-diff
+  accepts_settings: ["thinking_tokens"]
+
+- name: us.anthropic.claude-opus-4-20250514-v1:0
+  edit_format: diff
+  weak_model_name: us.anthropic.claude-3-5-haiku-20241022-v1:0
+  use_repo_map: true
+  examples_as_sys_msg: false
+  extra_params:
+    extra_headers:
+      anthropic-beta: prompt-caching-2024-07-31,pdfs-2024-09-25,output-128k-2025-02-19
+    max_tokens: 32000
+  cache_control: true
+  editor_model_name: us.anthropic.claude-sonnet-4-20250514-v1:0
+  editor_edit_format: editor-diff
+  accepts_settings: ["thinking_tokens"]
+
+- name: vertex_ai/claude-opus-4@20250514
+  edit_format: diff
+  weak_model_name: vertex_ai/claude-3-5-haiku@20241022
+  use_repo_map: true
+  examples_as_sys_msg: false
+  extra_params:
+    max_tokens: 32000
+  editor_model_name: vertex_ai/claude-sonnet-4@20250514
+  editor_edit_format: editor-diff
+  accepts_settings: ["thinking_tokens"]
+
+- name: vertex_ai-anthropic_models/vertex_ai/claude-opus-4@20250514
+  edit_format: diff
+  weak_model_name: vertex_ai/claude-3-5-haiku@20241022
+  use_repo_map: true
+  examples_as_sys_msg: false
+  extra_params:
+    max_tokens: 32000
+  editor_model_name: vertex_ai-anthropic_models/vertex_ai/claude-sonnet-4@20250514
+  editor_edit_format: editor-diff
+  accepts_settings: ["thinking_tokens"]
+
+- name: vertex_ai/gemini-2.5-flash-preview-05-20
+  edit_format: diff
+  use_repo_map: true
+  accepts_settings: ["reasoning_effort", "thinking_tokens"]
+- name: openrouter/anthropic/claude-opus-4
+  edit_format: diff
+  weak_model_name: openrouter/anthropic/claude-3-5-haiku
+  use_repo_map: true
+  examples_as_sys_msg: false
+  extra_params:
+    extra_headers:
+      anthropic-beta: prompt-caching-2024-07-31,pdfs-2024-09-25,output-128k-2025-02-19
+    max_tokens: 32000
+  cache_control: true
+  editor_model_name: openrouter/anthropic/claude-sonnet-4
+  editor_edit_format: editor-diff
+  accepts_settings: ["thinking_tokens"]
+

aider/website/HISTORY.md

@@ -24,12 +24,32 @@ cog.out(text)
 ]]]-->
 
 
+### Aider v0.84.0
+
+- Added support for new Claude models including the Sonnet 4 and Opus 4 series (e.g., `claude-sonnet-4-20250514`,
+`claude-opus-4-20250514`) across various providers. The default `sonnet` and `opus` aliases were updated to these newer
+versions.
+- Added support for the `vertex_ai/gemini-2.5-flash-preview-05-20` model.
+- Fixed OpenRouter token cost calculation for improved accuracy.
+- Updated default OpenRouter models during onboarding to `deepseek/deepseek-r1:free` for the free tier and
+`anthropic/claude-sonnet-4` for paid tiers.
+- Automatically refresh GitHub Copilot tokens when used as OpenAI API keys, by Lih Chen.
+- Aider wrote 79% of the code in this release.
+
+### Aider v0.83.2
+
+- Bumped configargparse to 1.7.1 as 1.7 was pulled.
+- Added shell tab completion for file path arguments (by saviour) and for `--edit-format`/`--editor-edit-format` options.
+- Improved OpenRouter model metadata handling by introducing a local cache, increasing reliability and performance.
+- The `/settings` command now displays detailed metadata for active main, editor, and weak models.
+- Fixed an issue where files explicitly added via the command line were not correctly ignored if listed in `.gitignore`.
+- Improved automatic commit messages by providing more context during their generation, by wangboxue.
+
 ### Aider v0.83.1
 
 - Improved user language detection by correctly normalizing hyphenated language codes (e.g., `en-US` to `en`) and enhancing the validation of locale results.
 - Prevented Aider from instructing the LLM to reply in 'C' or 'POSIX' when these are detected as the system locale.
 - Displayed a spinner with the model name when generating commit messages.
-- Aider wrote 74% of the code in this release.
 
 ### Aider v0.83.0
 
@@ -435,7 +455,7 @@ cog.out(text)
 - [Aider works with LLM web chat UIs](https://aider.chat/docs/usage/copypaste.html).
   - New `--copy-paste` mode.
   - New `/copy-context` command.
-- [Set API keys and other environment variables for all providers from command line or yaml conf file](https://aider.chat/docs/config/aider_conf.html#storing-llm-keys).
+- [Set API keys and other environment variables for all providers from command line or YAML conf file](https://aider.chat/docs/config/aider_conf.html#storing-llm-keys).
   - New `--api-key provider=key` setting.
   - New `--set-env VAR=value` setting.
 - Added bash and zsh support to `--watch-files`.
@@ -603,7 +623,7 @@ cog.out(text)
 
 ### Aider v0.59.1
 
-- Check for obsolete `yes: true` in yaml config, show helpful error.
+- Check for obsolete `yes: true` in YAML config, show helpful error.
 - Model settings for openrouter/anthropic/claude-3.5-sonnet:beta
 
 ### Aider v0.59.0
@@ -613,7 +633,7 @@ cog.out(text)
   - Still auto-completes the full paths of the repo files like `/add`.
   - Now supports globs like `src/**/*.py`
 - Renamed `--yes` to `--yes-always`.
-  - Now uses `AIDER_YES_ALWAYS` env var and `yes-always:` yaml key.
+  - Now uses `AIDER_YES_ALWAYS` env var and `yes-always:` YAML key.
   - Existing YAML and .env files will need to be updated.
   - Can still abbreviate to `--yes` on the command line.
 - Config file now uses standard YAML list syntax with `  - list entries`, one per line.  
@@ -820,7 +840,7 @@ cog.out(text)
   - Use `--map-refresh <always|files|manual|auto>` to configure.
 - Improved cost estimate logic for caching.
 - Improved editing performance on Jupyter Notebook `.ipynb` files.
-- Show which config yaml file is loaded with `--verbose`.
+- Show which config YAML file is loaded with `--verbose`.
 - Bumped dependency versions.
 - Bugfix: properly load `.aider.models.metadata.json` data.
 - Bugfix: Using `--msg /ask ...` caused an exception.

aider/website/_data/blame.yml

@@ -4659,3 +4659,69 @@
     zjy1412: 54
   start_tag: v0.82.0
   total_lines: 2594
+- aider_percentage: 78.92
+  aider_total: 655
+  end_date: '2025-05-30'
+  end_tag: v0.84.0
+  file_counts:
+    aider/__init__.py:
+      Paul Gauthier: 1
+    aider/args.py:
+      Paul Gauthier (aider): 27
+      saviour: 2
+    aider/args_formatter.py:
+      Paul Gauthier: 1
+    aider/coders/base_coder.py:
+      Paul Gauthier: 4
+      Paul Gauthier (aider): 10
+    aider/commands.py:
+      Paul Gauthier (aider): 23
+      wangboxue: 1
+    aider/models.py:
+      Lih Chen: 15
+      Paul Gauthier: 16
+      Paul Gauthier (aider): 12
+    aider/onboarding.py:
+      Paul Gauthier: 2
+    aider/openrouter.py:
+      Paul Gauthier (aider): 120
+    aider/repo.py:
+      Paul Gauthier: 1
+      Paul Gauthier (aider): 10
+    aider/repomap.py:
+      Paul Gauthier (aider): 1
+    aider/resources/model-settings.yml:
+      Paul Gauthier: 71
+      Paul Gauthier (aider): 193
+      Trung Dinh: 11
+    aider/utils.py:
+      Paul Gauthier (aider): 1
+    aider/waiting.py:
+      Paul Gauthier: 2
+      Paul Gauthier (aider): 6
+    aider/website/docs/leaderboards/index.md:
+      Paul Gauthier: 1
+    aider/website/index.html:
+      Paul Gauthier: 43
+    scripts/update-history.py:
+      Paul Gauthier: 2
+    tests/basic/test_coder.py:
+      Paul Gauthier: 2
+      Paul Gauthier (aider): 144
+    tests/basic/test_main.py:
+      Paul Gauthier (aider): 28
+    tests/basic/test_models.py:
+      Paul Gauthier (aider): 2
+    tests/basic/test_onboarding.py:
+      Paul Gauthier (aider): 5
+    tests/basic/test_openrouter.py:
+      Paul Gauthier (aider): 73
+  grand_total:
+    Lih Chen: 15
+    Paul Gauthier: 146
+    Paul Gauthier (aider): 655
+    Trung Dinh: 11
+    saviour: 2
+    wangboxue: 1
+  start_tag: v0.83.0
+  total_lines: 830

aider/website/_data/polyglot_leaderboard.yml

@@ -1307,3 +1307,174 @@
   seconds_per_case: 45.4
   total_cost: 0.0000
 
+- dirname: 2025-05-24-21-17-54--sonnet4-diff-exuser
+  test_cases: 225
+  model: claude-sonnet-4-20250514 (no thinking)
+  edit_format: diff
+  commit_hash: ef3f8bb-dirty
+  pass_rate_1: 20.4
+  pass_rate_2: 56.4
+  pass_num_1: 46
+  pass_num_2: 127
+  percent_cases_well_formed: 98.2
+  error_outputs: 6
+  num_malformed_responses: 4
+  num_with_malformed_responses: 4
+  user_asks: 129
+  lazy_comments: 0
+  syntax_errors: 0
+  indentation_errors: 0
+  exhausted_context_windows: 1
+  prompt_tokens: 3460663
+  completion_tokens: 433373
+  test_timeouts: 7
+  total_tests: 225
+  command: aider --model claude-sonnet-4-20250514
+  date: 2025-05-24
+  versions: 0.83.3.dev
+  seconds_per_case: 29.8
+  total_cost: 15.8155
+  
+- dirname: 2025-05-24-22-10-36--sonnet4-diff-exuser-think32k
+  test_cases: 225
+  model: claude-sonnet-4-20250514 (32k thinking)
+  edit_format: diff
+  commit_hash: e3cb907
+  thinking_tokens: 32000
+  pass_rate_1: 25.8
+  pass_rate_2: 61.3
+  pass_num_1: 58
+  pass_num_2: 138
+  percent_cases_well_formed: 97.3
+  error_outputs: 10
+  num_malformed_responses: 10
+  num_with_malformed_responses: 6
+  user_asks: 111
+  lazy_comments: 0
+  syntax_errors: 0
+  indentation_errors: 0
+  exhausted_context_windows: 0
+  prompt_tokens: 2863068
+  completion_tokens: 1271074
+  test_timeouts: 6
+  total_tests: 225
+  command: aider --model claude-sonnet-4-20250514
+  date: 2025-05-24
+  versions: 0.83.3.dev
+  seconds_per_case: 79.9
+  total_cost: 26.5755
+
+- dirname: 2025-05-25-19-57-20--opus4-diff-exuser
+  test_cases: 225
+  model: claude-opus-4-20250514 (no think)
+  edit_format: diff
+  commit_hash: 9ef3211
+  pass_rate_1: 32.9
+  pass_rate_2: 70.7
+  pass_num_1: 74
+  pass_num_2: 159
+  percent_cases_well_formed: 98.7
+  error_outputs: 3
+  num_malformed_responses: 3
+  num_with_malformed_responses: 3
+  user_asks: 105
+  lazy_comments: 0
+  syntax_errors: 0
+  indentation_errors: 0
+  exhausted_context_windows: 0
+  prompt_tokens: 2671437
+  completion_tokens: 380717
+  test_timeouts: 3
+  total_tests: 225
+  command: aider --model claude-opus-4-20250514
+  date: 2025-05-25
+  versions: 0.83.3.dev
+  seconds_per_case: 42.5
+  total_cost: 68.6253
+
+- dirname: 2025-05-25-20-40-51--opus4-diff-exuser
+  test_cases: 225
+  model: claude-opus-4-20250514 (32k thinking)
+  edit_format: diff
+  commit_hash: 9ef3211
+  thinking_tokens: 32000
+  pass_rate_1: 37.3
+  pass_rate_2: 72.0
+  pass_num_1: 84
+  pass_num_2: 162
+  percent_cases_well_formed: 97.3
+  error_outputs: 10
+  num_malformed_responses: 6
+  num_with_malformed_responses: 6
+  user_asks: 97
+  lazy_comments: 0
+  syntax_errors: 0
+  indentation_errors: 0
+  exhausted_context_windows: 0
+  prompt_tokens: 2567514
+  completion_tokens: 363142
+  test_timeouts: 4
+  total_tests: 225
+  command: aider --model claude-opus-4-20250514
+  date: 2025-05-25
+  versions: 0.83.3.dev
+  seconds_per_case: 44.1
+  total_cost: 65.7484
+
+- dirname: 2025-05-26-15-56-31--flash25-05-20-24k-think # dirname is misleading
+  test_cases: 225
+  model: gemini-2.5-flash-preview-05-20 (no think)
+  edit_format: diff
+  commit_hash: 214b811-dirty
+  thinking_tokens: 0 # <-- no thinking
+  pass_rate_1: 20.9
+  pass_rate_2: 44.0
+  pass_num_1: 47
+  pass_num_2: 99
+  percent_cases_well_formed: 93.8
+  error_outputs: 16
+  num_malformed_responses: 16
+  num_with_malformed_responses: 14
+  user_asks: 79
+  lazy_comments: 0
+  syntax_errors: 0
+  indentation_errors: 0
+  exhausted_context_windows: 0
+  prompt_tokens: 5512458
+  completion_tokens: 514145
+  test_timeouts: 4
+  total_tests: 225
+  command: aider --model gemini/gemini-2.5-flash-preview-05-20
+  date: 2025-05-26
+  versions: 0.83.3.dev
+  seconds_per_case: 12.2
+  total_cost: 1.1354
+  
+- dirname: 2025-05-25-22-58-44--flash25-05-20-24k-think
+  test_cases: 225
+  model: gemini-2.5-flash-preview-05-20 (24k think)
+  edit_format: diff
+  commit_hash: a8568c3-dirty
+  thinking_tokens: 24576
+  pass_rate_1: 26.2
+  pass_rate_2: 55.1
+  pass_num_1: 59
+  pass_num_2: 124
+  percent_cases_well_formed: 95.6
+  error_outputs: 15
+  num_malformed_responses: 15
+  num_with_malformed_responses: 10
+  user_asks: 101
+  lazy_comments: 0
+  syntax_errors: 0
+  indentation_errors: 0
+  exhausted_context_windows: 0
+  prompt_tokens: 3666792
+  completion_tokens: 2703162
+  test_timeouts: 4
+  total_tests: 225
+  command: aider --model gemini/gemini-2.5-flash-preview-05-20
+  date: 2025-05-25
+  versions: 0.83.3.dev
+  seconds_per_case: 53.9
+  total_cost: 8.5625

aider/website/_posts/2024-05-13-models-over-time.md

@@ -15,12 +15,12 @@ nav_exclude: true
 I recently wanted to draw a graph showing how LLM code editing skill has been
 changing over time as new models have been released by OpenAI, Anthropic and others.
 I have all the
-[data in a yaml file](https://github.com/Aider-AI/aider/blob/main/website/_data/edit_leaderboard.yml) that is used to render
+[data in a YAML file](https://github.com/Aider-AI/aider/blob/main/website/_data/edit_leaderboard.yml) that is used to render
 [aider's LLM leaderboards](https://aider.chat/docs/leaderboards/).
 
 Below is the aider chat transcript, which shows:
 
-- I launch aider with the yaml file, a file with other plots I've done recently (so GPT can crib the style) and an empty file called `over_time.py`.
+- I launch aider with the YAML file, a file with other plots I've done recently (so GPT can crib the style) and an empty file called `over_time.py`.
 - Then I ask GPT to draw the scatterplot I want.
 - I run the resulting script and share the error output with GPT so it can fix a small bug.
 - I ask it to color the points for GPT-4 and GPT-3.5 family models differently, to better see trends within those model families.
@@ -28,7 +28,7 @@ Below is the aider chat transcript, which shows:
 - I work through a series of other small style changes, like changing fonts and the graph border.
 
 In the end I have the graph, but I also have the python code in my repo.
-So I can update this graph easily whenever I add new entries to the yaml data file.
+So I can update this graph easily whenever I add new entries to the YAML data file.
 
 
 ## Aider chat transcript

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

@@ -4,7 +4,7 @@
 # Place in your home dir, or at the root of your git repo.
 ##########################################################
 
-# Note: You can only put OpenAI and Anthropic API keys in the yaml
+# Note: You can only put OpenAI and Anthropic API keys in the YAML
 # config file. Keys for all APIs can be stored in a .env file
 # https://aider.chat/docs/config/dotenv.html
 
@@ -386,6 +386,9 @@
 ## Specify the language to use in the chat (default: None, uses system settings)
 #chat-language: xxx
 
+## Specify the language to use in the commit message (default: None, user language)
+#commit-language: xxx
+
 ## Always say yes to every confirmation
 #yes-always: false
 

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

@@ -81,7 +81,7 @@ You can override or add settings for any model by creating a `.aider.model.setti
 If the files above exist, they will be loaded in that order. 
 Files loaded last will take priority.
 
-The yaml file should be a list of dictionary objects for each model.
+The YAML file should be a list of dictionary objects for each model.
 
 
 ### Passing extra params to litellm.completion
@@ -158,6 +158,34 @@ cog.out("```\n")
   system_prompt_prefix: null
   accepts_settings: null
 
+- name: anthropic.claude-opus-4-20250514-v1:0
+  edit_format: diff
+  weak_model_name: anthropic.claude-3-5-haiku-20241022-v1:0
+  use_repo_map: true
+  extra_params:
+    extra_headers:
+      anthropic-beta: prompt-caching-2024-07-31,pdfs-2024-09-25,output-128k-2025-02-19
+    max_tokens: 32000
+  cache_control: true
+  editor_model_name: anthropic.claude-sonnet-4-20250514-v1:0
+  editor_edit_format: editor-diff
+  accepts_settings:
+  - thinking_tokens
+
+- name: anthropic.claude-sonnet-4-20250514-v1:0
+  edit_format: diff
+  weak_model_name: anthropic.claude-3-5-haiku-20241022-v1:0
+  use_repo_map: 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-sonnet-4-20250514-v1:0
+  editor_edit_format: editor-diff
+  accepts_settings:
+  - thinking_tokens
+
 - name: anthropic/claude-3-5-haiku-20241022
   edit_format: diff
   weak_model_name: anthropic/claude-3-5-haiku-20241022
@@ -246,6 +274,34 @@ cog.out("```\n")
       anthropic-beta: prompt-caching-2024-07-31,pdfs-2024-09-25
   cache_control: true
 
+- name: anthropic/claude-opus-4-20250514
+  edit_format: diff
+  weak_model_name: anthropic/claude-3-5-haiku-20241022
+  use_repo_map: true
+  extra_params:
+    extra_headers:
+      anthropic-beta: prompt-caching-2024-07-31,pdfs-2024-09-25,output-128k-2025-02-19
+    max_tokens: 32000
+  cache_control: true
+  editor_model_name: anthropic/claude-sonnet-4-20250514
+  editor_edit_format: editor-diff
+  accepts_settings:
+  - thinking_tokens
+
+- name: anthropic/claude-sonnet-4-20250514
+  edit_format: diff
+  weak_model_name: anthropic/claude-3-5-haiku-20241022
+  use_repo_map: 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-sonnet-4-20250514
+  editor_edit_format: editor-diff
+  accepts_settings:
+  - thinking_tokens
+
 - name: azure/gpt-4.1
   edit_format: diff
   weak_model_name: azure/gpt-4.1-mini
@@ -407,6 +463,20 @@ cog.out("```\n")
   accepts_settings:
   - thinking_tokens
 
+- name: bedrock/anthropic.claude-sonnet-4-20250514-v1:0
+  edit_format: diff
+  weak_model_name: bedrock/anthropic.claude-3-5-haiku-20241022-v1:0
+  use_repo_map: 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-sonnet-4-20250514-v1:0
+  editor_edit_format: editor-diff
+  accepts_settings:
+  - thinking_tokens
+
 - 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
@@ -423,6 +493,20 @@ cog.out("```\n")
   accepts_settings:
   - thinking_tokens
 
+- name: bedrock/us.anthropic.claude-sonnet-4-20250514-v1:0
+  edit_format: diff
+  weak_model_name: bedrock/us.anthropic.claude-3-5-haiku-20241022-v1:0
+  use_repo_map: 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-sonnet-4-20250514-v1:0
+  editor_edit_format: editor-diff
+  accepts_settings:
+  - thinking_tokens
+
 - 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
@@ -439,6 +523,62 @@ cog.out("```\n")
   accepts_settings:
   - thinking_tokens
 
+- name: bedrock_converse/anthropic.claude-opus-4-20250514-v1:0
+  edit_format: diff
+  weak_model_name: bedrock_converse/anthropic.claude-3-5-haiku-20241022-v1:0
+  use_repo_map: true
+  extra_params:
+    extra_headers:
+      anthropic-beta: prompt-caching-2024-07-31,pdfs-2024-09-25,output-128k-2025-02-19
+    max_tokens: 32000
+  cache_control: true
+  editor_model_name: bedrock_converse/anthropic.claude-sonnet-4-20250514-v1:0
+  editor_edit_format: editor-diff
+  accepts_settings:
+  - thinking_tokens
+
+- name: bedrock_converse/anthropic.claude-sonnet-4-20250514-v1:0
+  edit_format: diff
+  weak_model_name: bedrock_converse/anthropic.claude-3-5-haiku-20241022-v1:0
+  use_repo_map: 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-sonnet-4-20250514-v1:0
+  editor_edit_format: editor-diff
+  accepts_settings:
+  - thinking_tokens
+
+- name: bedrock_converse/eu.anthropic.claude-opus-4-20250514-v1:0
+  edit_format: diff
+  weak_model_name: bedrock_converse/eu.anthropic.claude-3-5-haiku-20241022-v1:0
+  use_repo_map: true
+  extra_params:
+    extra_headers:
+      anthropic-beta: prompt-caching-2024-07-31,pdfs-2024-09-25,output-128k-2025-02-19
+    max_tokens: 32000
+  cache_control: true
+  editor_model_name: bedrock_converse/eu.anthropic.claude-sonnet-4-20250514-v1:0
+  editor_edit_format: editor-diff
+  accepts_settings:
+  - thinking_tokens
+
+- name: bedrock_converse/eu.anthropic.claude-sonnet-4-20250514-v1:0
+  edit_format: diff
+  weak_model_name: bedrock_converse/eu.anthropic.claude-3-5-haiku-20241022-v1:0
+  use_repo_map: 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/eu.anthropic.claude-sonnet-4-20250514-v1:0
+  editor_edit_format: editor-diff
+  accepts_settings:
+  - thinking_tokens
+
 - 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
@@ -455,6 +595,34 @@ cog.out("```\n")
   accepts_settings:
   - thinking_tokens
 
+- name: bedrock_converse/us.anthropic.claude-opus-4-20250514-v1:0
+  edit_format: diff
+  weak_model_name: bedrock_converse/us.anthropic.claude-3-5-haiku-20241022-v1:0
+  use_repo_map: true
+  extra_params:
+    extra_headers:
+      anthropic-beta: prompt-caching-2024-07-31,pdfs-2024-09-25,output-128k-2025-02-19
+    max_tokens: 32000
+  cache_control: true
+  editor_model_name: bedrock_converse/us.anthropic.claude-sonnet-4-20250514-v1:0
+  editor_edit_format: editor-diff
+  accepts_settings:
+  - thinking_tokens
+
+- name: bedrock_converse/us.anthropic.claude-sonnet-4-20250514-v1:0
+  edit_format: diff
+  weak_model_name: bedrock_converse/us.anthropic.claude-3-5-haiku-20241022-v1:0
+  use_repo_map: 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-sonnet-4-20250514-v1:0
+  editor_edit_format: editor-diff
+  accepts_settings:
+  - thinking_tokens
+
 - name: claude-3-5-haiku-20241022
   edit_format: diff
   weak_model_name: claude-3-5-haiku-20241022
@@ -538,6 +706,34 @@ cog.out("```\n")
 - name: claude-3-sonnet-20240229
   weak_model_name: claude-3-5-haiku-20241022
 
+- name: claude-opus-4-20250514
+  edit_format: diff
+  weak_model_name: claude-3-5-haiku-20241022
+  use_repo_map: true
+  extra_params:
+    extra_headers:
+      anthropic-beta: prompt-caching-2024-07-31,pdfs-2024-09-25,output-128k-2025-02-19
+    max_tokens: 32000
+  cache_control: true
+  editor_model_name: claude-sonnet-4-20250514
+  editor_edit_format: editor-diff
+  accepts_settings:
+  - thinking_tokens
+
+- name: claude-sonnet-4-20250514
+  edit_format: diff
+  weak_model_name: claude-3-5-haiku-20241022
+  use_repo_map: 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-sonnet-4-20250514
+  editor_edit_format: editor-diff
+  accepts_settings:
+  - thinking_tokens
+
 - name: cohere_chat/command-a-03-2025
   examples_as_sys_msg: true
 
@@ -600,6 +796,34 @@ cog.out("```\n")
   editor_model_name: deepseek/deepseek-chat
   editor_edit_format: editor-diff
 
+- name: eu.anthropic.claude-opus-4-20250514-v1:0
+  edit_format: diff
+  weak_model_name: eu.anthropic.claude-3-5-haiku-20241022-v1:0
+  use_repo_map: true
+  extra_params:
+    extra_headers:
+      anthropic-beta: prompt-caching-2024-07-31,pdfs-2024-09-25,output-128k-2025-02-19
+    max_tokens: 32000
+  cache_control: true
+  editor_model_name: eu.anthropic.claude-sonnet-4-20250514-v1:0
+  editor_edit_format: editor-diff
+  accepts_settings:
+  - thinking_tokens
+
+- name: eu.anthropic.claude-sonnet-4-20250514-v1:0
+  edit_format: diff
+  weak_model_name: eu.anthropic.claude-3-5-haiku-20241022-v1:0
+  use_repo_map: 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: eu.anthropic.claude-sonnet-4-20250514-v1:0
+  editor_edit_format: editor-diff
+  accepts_settings:
+  - thinking_tokens
+
 - name: fireworks_ai/accounts/fireworks/models/deepseek-r1
   edit_format: diff
   weak_model_name: fireworks_ai/accounts/fireworks/models/deepseek-v3
@@ -1145,6 +1369,34 @@ cog.out("```\n")
   accepts_settings:
   - thinking_tokens
 
+- name: openrouter/anthropic/claude-opus-4
+  edit_format: diff
+  weak_model_name: openrouter/anthropic/claude-3-5-haiku
+  use_repo_map: true
+  extra_params:
+    extra_headers:
+      anthropic-beta: prompt-caching-2024-07-31,pdfs-2024-09-25,output-128k-2025-02-19
+    max_tokens: 32000
+  cache_control: true
+  editor_model_name: openrouter/anthropic/claude-sonnet-4
+  editor_edit_format: editor-diff
+  accepts_settings:
+  - thinking_tokens
+
+- name: openrouter/anthropic/claude-sonnet-4
+  edit_format: diff
+  weak_model_name: openrouter/anthropic/claude-3-5-haiku
+  use_repo_map: 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-sonnet-4
+  editor_edit_format: editor-diff
+  accepts_settings:
+  - thinking_tokens
+
 - name: openrouter/cohere/command-a-03-2025
   examples_as_sys_msg: true
 
@@ -1434,6 +1686,34 @@ cog.out("```\n")
   accepts_settings:
   - reasoning_effort
 
+- name: us.anthropic.claude-opus-4-20250514-v1:0
+  edit_format: diff
+  weak_model_name: us.anthropic.claude-3-5-haiku-20241022-v1:0
+  use_repo_map: true
+  extra_params:
+    extra_headers:
+      anthropic-beta: prompt-caching-2024-07-31,pdfs-2024-09-25,output-128k-2025-02-19
+    max_tokens: 32000
+  cache_control: true
+  editor_model_name: us.anthropic.claude-sonnet-4-20250514-v1:0
+  editor_edit_format: editor-diff
+  accepts_settings:
+  - thinking_tokens
+
+- name: us.anthropic.claude-sonnet-4-20250514-v1:0
+  edit_format: diff
+  weak_model_name: us.anthropic.claude-3-5-haiku-20241022-v1:0
+  use_repo_map: 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: us.anthropic.claude-sonnet-4-20250514-v1:0
+  editor_edit_format: editor-diff
+  accepts_settings:
+  - thinking_tokens
+
 - 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
@@ -1447,6 +1727,28 @@ cog.out("```\n")
   accepts_settings:
   - thinking_tokens
 
+- name: vertex_ai-anthropic_models/vertex_ai/claude-opus-4@20250514
+  edit_format: diff
+  weak_model_name: vertex_ai/claude-3-5-haiku@20241022
+  use_repo_map: true
+  extra_params:
+    max_tokens: 32000
+  editor_model_name: vertex_ai-anthropic_models/vertex_ai/claude-sonnet-4@20250514
+  editor_edit_format: editor-diff
+  accepts_settings:
+  - thinking_tokens
+
+- name: vertex_ai-anthropic_models/vertex_ai/claude-sonnet-4@20250514
+  edit_format: diff
+  weak_model_name: vertex_ai/claude-3-5-haiku@20241022
+  use_repo_map: true
+  extra_params:
+    max_tokens: 64000
+  editor_model_name: vertex_ai-anthropic_models/vertex_ai/claude-sonnet-4@20250514
+  editor_edit_format: editor-diff
+  accepts_settings:
+  - thinking_tokens
+
 - name: vertex_ai-language-models/gemini-2.5-flash-preview-04-17
   edit_format: diff
   use_repo_map: true
@@ -1502,6 +1804,35 @@ cog.out("```\n")
 - name: vertex_ai/claude-3-sonnet@20240229
   weak_model_name: vertex_ai/claude-3-5-haiku@20241022
 
+- name: vertex_ai/claude-opus-4@20250514
+  edit_format: diff
+  weak_model_name: vertex_ai/claude-3-5-haiku@20241022
+  use_repo_map: true
+  extra_params:
+    max_tokens: 32000
+  editor_model_name: vertex_ai/claude-sonnet-4@20250514
+  editor_edit_format: editor-diff
+  accepts_settings:
+  - thinking_tokens
+
+- name: vertex_ai/claude-sonnet-4@20250514
+  edit_format: diff
+  weak_model_name: vertex_ai/claude-3-5-haiku@20241022
+  use_repo_map: true
+  extra_params:
+    max_tokens: 64000
+  editor_model_name: vertex_ai/claude-sonnet-4@20250514
+  editor_edit_format: editor-diff
+  accepts_settings:
+  - thinking_tokens
+
+- name: vertex_ai/gemini-2.5-flash-preview-05-20
+  edit_format: diff
+  use_repo_map: true
+  accepts_settings:
+  - reasoning_effort
+  - thinking_tokens
+
 - name: vertex_ai/gemini-2.5-pro-exp-03-25
   edit_format: diff-fenced
   weak_model_name: vertex_ai-language-models/gemini-2.5-flash-preview-04-17

aider/website/docs/config/aider_conf.md

@@ -1,7 +1,7 @@
 ---
 parent: Configuration
 nav_order: 15
-description: How to configure aider with a yaml config file.
+description: How to configure aider with a YAML config file.
 ---
 
 # YAML config file
@@ -58,7 +58,7 @@ cog.outl("```")
 # Place in your home dir, or at the root of your git repo.
 ##########################################################
 
-# Note: You can only put OpenAI and Anthropic API keys in the yaml
+# Note: You can only put OpenAI and Anthropic API keys in the YAML
 # config file. Keys for all APIs can be stored in a .env file
 # https://aider.chat/docs/config/dotenv.html
 
@@ -440,6 +440,9 @@ cog.outl("```")
 ## Specify the language to use in the chat (default: None, uses system settings)
 #chat-language: xxx
 
+## Specify the language to use in the commit message (default: None, user language)
+#commit-language: xxx
+
 ## Always say yes to every confirmation
 #yes-always: false
 

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

@@ -40,9 +40,9 @@ OPENAI_API_KEY=<key>
 ANTHROPIC_API_KEY=<key>
 ```
 
-#### Yaml config file
+#### YAML config file
 You can also set those API keys via special entries in the
-[yaml config file](/docs/config/aider_conf.html), like this:
+[YAML config file](/docs/config/aider_conf.html), like this:
 
 ```yaml
 openai-api-key: <key>
@@ -74,7 +74,7 @@ OPENROUTER_API_KEY=bar
 DEEPSEEK_API_KEY=baz
 ```
 
-#### Yaml config file
+#### YAML config file
 
 
 You can also set API keys in the 

aider/website/docs/config/editor.md

@@ -12,7 +12,7 @@ Aider allows you to configure your preferred text editor for use with the `/edit
 
 You can specify the text editor with the `--editor` switch or using
 `editor:` in aider's
-[yaml config file](https://aider.chat/docs/config/aider_conf.html).
+[YAML config file](https://aider.chat/docs/config/aider_conf.html).
 
 ## Environment variables
 

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

@@ -86,10 +86,10 @@ for alias, model in sorted(MODEL_ALIASES.items()):
 - `grok3`: xai/grok-3-beta
 - `haiku`: claude-3-5-haiku-20241022
 - `optimus`: openrouter/openrouter/optimus-alpha
-- `opus`: claude-3-opus-20240229
+- `opus`: claude-opus-4-20250514
 - `quasar`: openrouter/openrouter/quasar-alpha
 - `r1`: deepseek/deepseek-reasoner
-- `sonnet`: anthropic/claude-3-7-sonnet-20250219
+- `sonnet`: anthropic/claude-sonnet-4-20250514
 <!--[[[end]]]-->
 
 ## Priority

aider/website/docs/config/options.md

@@ -74,7 +74,7 @@ usage: aider [-h] [--model] [--openai-api-key] [--anthropic-api-key]
              [--apply-clipboard-edits] [--exit] [--show-repo-map]
              [--show-prompts] [--voice-format] [--voice-language]
              [--voice-input-device] [--disable-playwright] [--file]
-             [--read] [--vim] [--chat-language] [--yes-always] [-v]
+             [--read] [--vim] [--chat-language] [--commit-language] [--yes-always] [-v]
              [--load] [--encoding] [--line-endings] [-c]
              [--env-file]
              [--suggest-shell-commands | --no-suggest-shell-commands]
@@ -683,6 +683,10 @@ Environment variable: `AIDER_VIM`
 Specify the language to use in the chat (default: None, uses system settings)  
 Environment variable: `AIDER_CHAT_LANGUAGE`  
 
+### `--commit-language COMMIT_LANGUAGE`
+Specify the language to use in the commit message (default: None, user language)  
+Environment variable: `AIDER_COMMIT_LANGUAGE`  
+
 ### `--yes-always`
 Always say yes to every confirmation  
 Environment variable: `AIDER_YES_ALWAYS`  

aider/website/docs/faq.md

@@ -264,9 +264,12 @@ tr:hover { background-color: #f5f5f5; }
 </style>
 <table>
 <tr><th>Model Name</th><th class='right'>Total Tokens</th><th class='right'>Percent</th></tr>
-<tr><td>gemini/gemini-2.5-pro-exp-03-25</td><td class='right'>1,253,243</td><td class='right'>90.6%</td></tr>
+<tr><td>o3</td><td class='right'>542,669</td><td class='right'>45.1%</td></tr>
-<tr><td>o3</td><td class='right'>121,023</td><td class='right'>8.8%</td></tr>
+<tr><td>gemini/gemini-2.5-pro-exp-03-25</td><td class='right'>479,518</td><td class='right'>39.9%</td></tr>
-<tr><td>openrouter/REDACTED</td><td class='right'>8,745</td><td class='right'>0.6%</td></tr>
+<tr><td>anthropic/claude-sonnet-4-20250514</td><td class='right'>131,972</td><td class='right'>11.0%</td></tr>
+<tr><td>gemini/gemini-2.5-pro-preview-05-06</td><td class='right'>40,256</td><td class='right'>3.3%</td></tr>
+<tr><td>gemini/gemini-2.5-flash-preview-05-20</td><td class='right'>7,638</td><td class='right'>0.6%</td></tr>
+<tr><td>gemini/REDACTED</td><td class='right'>643</td><td class='right'>0.1%</td></tr>
 </table>
 
 {: .note :}

aider/website/docs/install.md

@@ -28,12 +28,6 @@ These one-liners will install aider, along with python 3.12 if needed.
 They are based on the 
 [uv installers](https://docs.astral.sh/uv/getting-started/installation/).
 
-#### Windows
-
-```powershell
-powershell -ExecutionPolicy ByPass -c "irm https://aider.chat/install.ps1 | iex"
-```
-
 #### Mac & Linux
 
 Use curl to download the script and execute it with sh:
@@ -48,6 +42,12 @@ If your system doesn't have curl, you can use wget:
 wget -qO- https://aider.chat/install.sh | sh
 ```
 
+#### Windows
+
+```powershell
+powershell -ExecutionPolicy ByPass -c "irm https://aider.chat/install.ps1 | iex"
+```
+
 
 ## Install with uv
 
@@ -55,7 +55,7 @@ You can install aider with uv:
 
 ```bash
 python -m pip install uv  # If you need to install uv
-uv tool install --force --python python3.12 aider-chat@latest
+uv tool install --force --python python3.12 --with pip aider-chat@latest
 ```
 
 This will install uv using your existing python version 3.8-3.13,

aider/website/docs/leaderboards/index.md

@@ -285,6 +285,6 @@ mod_dates = [get_last_modified_date(file) for file in files]
 latest_mod_date = max(mod_dates)
 cog.out(f"{latest_mod_date.strftime('%B %d, %Y.')}")
 ]]]-->
-May 09, 2025.
+May 26, 2025.
 <!--[[[end]]]-->
 </p>

aider/website/docs/llms/github.md

@@ -0,0 +1,105 @@
+---
+parent: Connecting to LLMs
+nav_order: 510
+---
+
+# GitHub Copilot
+
+Aider can connect to GitHub Copilot’s LLMs because Copilot exposes a standard **OpenAI-style**
+endpoint at:
+
+```
+https://api.githubcopilot.com
+```
+
+First, install aider:
+
+{% include install.md %}
+
+---
+
+## Configure your environment
+
+```bash
+# macOS/Linux
+export OPENAI_API_BASE=https://api.githubcopilot.com
+export OPENAI_API_KEY=<oauth_token>
+
+# Windows (PowerShell)
+setx OPENAI_API_BASE https://api.githubcopilot.com
+setx OPENAI_API_KEY  <oauth_token>
+# …restart the shell after setx commands
+```
+
+---
+
+### Where do I get the token?
+The easiest path is to sign in to Copilot from any JetBrains IDE (PyCharm, GoLand, etc).
+After you authenticate a file appears:
+
+```
+~/.config/github-copilot/apps.json
+```
+
+Copy the `oauth_token` value – that string is your `OPENAI_API_KEY`.
+
+*Note:* tokens created by the Neovim **copilot.lua** plugin (old `hosts.json`) sometimes lack the
+needed scopes. If you see “access to this endpoint is forbidden”, regenerate the token with a
+JetBrains IDE.
+
+---
+
+## Discover available models
+
+Copilot hosts many models (OpenAI, Anthropic, Google, etc).  
+List the models your subscription allows with:
+
+```bash
+curl -s https://api.githubcopilot.com/models \
+  -H "Authorization: Bearer $OPENAI_API_KEY" \
+  -H "Content-Type: application/json" \
+  -H "Copilot-Integration-Id: vscode-chat" | jq -r '.data[].id'
+```
+
+Each returned ID can be used with aider by **prefixing it with `openai/`**:
+
+```bash
+aider --model openai/gpt-4o
+# or
+aider --model openai/claude-3.7-sonnet-thought
+```
+
+---
+
+## Quick start
+
+```bash
+# change into your project
+cd /to/your/project
+
+# talk to Copilot
+aider --model openai/gpt-4o
+```
+
+---
+
+## Optional config file (`~/.aider.conf.yml`)
+
+```yaml
+openai-api-base: https://api.githubcopilot.com
+openai-api-key:  "<oauth_token>"
+model:           openai/gpt-4o
+weak-model:      openai/gpt-4o-mini
+show-model-warnings: false
+```
+
+---
+
+## FAQ
+
+* Calls made through aider are billed through your Copilot subscription  
+  (aider will still print *estimated* costs).
+* The Copilot docs explicitly allow third-party “agents” that hit this API – aider is playing by
+  the rules.
+* Aider talks directly to the REST endpoint—no web-UI scraping or browser automation.
+

aider/website/docs/llms/vertex.md

@@ -40,7 +40,7 @@ cd /to/your/project
 aider --model vertex_ai/claude-3-5-sonnet@20240620
 ```
 
-Or you can use the [yaml config](/docs/config/aider_conf.html) to set the model to any of the 
+Or you can use the [YAML config](/docs/config/aider_conf.html) to set the model to any of the 
 models supported by Vertex AI.
 
 Example `.aider.conf.yml` file:

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

@@ -58,6 +58,9 @@ cog.out(model_list)
 - anthropic.claude-3-5-haiku-20241022-v1:0
 - anthropic.claude-3-5-sonnet-20241022-v2:0
 - anthropic.claude-3-7-sonnet-20250219-v1:0
+- anthropic.claude-opus-4-20250514-v1:0
+- anthropic.claude-sonnet-4-20250514-v1:0
+- azure_ai/mistral-medium-2505
 - claude-3-5-haiku-20241022
 - claude-3-5-haiku-latest
 - claude-3-5-sonnet-20240620
@@ -69,6 +72,8 @@ cog.out(model_list)
 - claude-3-opus-20240229
 - claude-3-opus-latest
 - claude-3-sonnet-20240229
+- claude-opus-4-20250514
+- claude-sonnet-4-20250514
 - codestral/codestral-2405
 - codestral/codestral-latest
 - databricks/databricks-claude-3-7-sonnet
@@ -77,15 +82,20 @@ cog.out(model_list)
 - deepseek/deepseek-reasoner
 - eu.anthropic.claude-3-5-haiku-20241022-v1:0
 - eu.anthropic.claude-3-5-sonnet-20241022-v2:0
+- eu.anthropic.claude-3-7-sonnet-20250219-v1:0
+- eu.anthropic.claude-opus-4-20250514-v1:0
+- eu.anthropic.claude-sonnet-4-20250514-v1:0
 - mistral/codestral-2405
 - mistral/codestral-latest
 - mistral/codestral-mamba-latest
+- mistral/devstral-small-2505
 - mistral/mistral-large-2402
 - mistral/mistral-large-2407
 - mistral/mistral-large-2411
 - mistral/mistral-large-latest
 - mistral/mistral-medium
 - mistral/mistral-medium-2312
+- mistral/mistral-medium-2505
 - mistral/mistral-medium-latest
 - mistral/mistral-small
 - mistral/mistral-small-latest
@@ -105,6 +115,8 @@ cog.out(model_list)
 - us.anthropic.claude-3-5-haiku-20241022-v1:0
 - us.anthropic.claude-3-5-sonnet-20241022-v2:0
 - us.anthropic.claude-3-7-sonnet-20250219-v1:0
+- us.anthropic.claude-opus-4-20250514-v1:0
+- us.anthropic.claude-sonnet-4-20250514-v1:0
 - vertex_ai/claude-3-5-haiku
 - vertex_ai/claude-3-5-haiku@20241022
 - vertex_ai/claude-3-5-sonnet
@@ -118,6 +130,8 @@ cog.out(model_list)
 - vertex_ai/claude-3-opus@20240229
 - vertex_ai/claude-3-sonnet
 - vertex_ai/claude-3-sonnet@20240229
+- vertex_ai/claude-opus-4@20250514
+- vertex_ai/claude-sonnet-4@20250514
 <!--[[[end]]]-->
 
 

aider/website/index.html

@@ -69,11 +69,11 @@ cog.out(text)
 ]]]-->
 <a href="https://github.com/Aider-AI/aider" class="github-badge badge-stars" title="Total number of GitHub stars the Aider project has received">
     <span class="badge-label">⭐ GitHub Stars</span>
-    <span class="badge-value">33K</span>
+    <span class="badge-value">34K</span>
 </a>
 <a href="https://pypi.org/project/aider-chat/" class="github-badge badge-installs" title="Total number of installations via pip from PyPI">
     <span class="badge-label">📦 Installs</span>
-    <span class="badge-value">2.2M</span>
+    <span class="badge-value">2.4M</span>
 </a>
 <div class="github-badge badge-tokens" title="Number of tokens processed weekly by Aider users">
     <span class="badge-label">📈 Tokens/week</span>
@@ -85,7 +85,7 @@ cog.out(text)
 </a>
 <a href="/HISTORY.html" class="github-badge badge-coded" title="Percentage of the new code in Aider's last release written by Aider itself">
     <span class="badge-label">🔄 Singularity</span>
-    <span class="badge-value">54%</span>
+    <span class="badge-value">79%</span>
 </a>
 <!--[[[end]]]-->  
             </div>
@@ -642,6 +642,7 @@ const testimonials = [
                         <li><a href="/docs/leaderboards/">LLM Leaderboards</a></li>
                         <li><a href="https://github.com/Aider-AI/aider">GitHub Repository</a></li>
                         <li><a href="https://discord.gg/Y7X7bhMQFV">Discord Community</a></li>
+                        <li><a href="https://aider.chat/HISTORY.html">Release notes</a></li>
                         <li><a href="/blog/">Blog</a></li>
                     </ul>
                 </div>

aider/website/install.ps1

@@ -425,7 +425,7 @@ function Invoke-Installer($artifacts, $platforms) {
 
   Write-Information ""
   Write-Information "Installing aider-chat..."
-  & "$dest_dir\uv.exe" tool install --force --python python3.12 aider-chat@latest
+  & "$dest_dir\uv.exe" tool install --force --python python3.12 --with pip aider-chat@latest
 
   if (-not $NoModifyPath) {
     Add-Ci-Path $dest_dir

aider/website/install.sh

@@ -1178,7 +1178,7 @@ install() {
     say "Installing aider..."
     say ""
     # Install aider-chat using the newly installed uv
-    ensure "${_install_dir}/uv" tool install --force --python python3.12 aider-chat@latest
+    ensure "${_install_dir}/uv" tool install --force --python python3.12 --with pip aider-chat@latest
     
     # Avoid modifying the users PATH if they are managing their PATH manually
     case :$PATH:

requirements.txt

@@ -60,7 +60,7 @@ click==8.1.8
     # via
     #   -c requirements/common-constraints.txt
     #   litellm
-configargparse==1.7
+configargparse==1.7.1
     # via
     #   -c requirements/common-constraints.txt
     #   -r requirements/requirements.in

requirements/common-constraints.txt

@@ -65,7 +65,7 @@ cogapp==3.4.1
     # via -r requirements/requirements-dev.in
 colorama==0.4.6
     # via griffe
-configargparse==1.7
+configargparse==1.7.1
     # via -r requirements/requirements.in
 contourpy==1.3.2
     # via matplotlib

requirements/requirements.in

@@ -46,3 +46,6 @@ scipy
 # https://github.com/pypa/twine/blob/6fbf880ee60915cf1666348c4bdd78a10415f2ac/twine/__init__.py#L40
 # Uses importlib-metadata
 importlib-metadata<8.0.0
+
+# configargparse was 1.7 pulled
+configargparse>1.7

scripts/Dockerfile.jekyll

@@ -5,7 +5,7 @@ FROM bretfisher/jekyll-serve
 WORKDIR /site
 
 # Copy the current directory contents into the container at /srv/jekyll
-COPY website /site
+COPY aider/website /site
 
 RUN apt-get update && apt-get install libcurl4
 

scripts/update-history.py

@@ -112,6 +112,8 @@ def main():
 
     cmd = [
         "aider",
+        "--model",
+        "sonnet",
         hist_path,
         "--read",
         log_path,

tests/basic/test_coder.py

@@ -834,6 +834,36 @@ two
             self.assertNotIn(fname2, str(coder.abs_fnames))
             self.assertNotIn(fname3, str(coder.abs_fnames))
 
+    def test_skip_gitignored_files_on_init(self):
+        with GitTemporaryDirectory() as _:
+            repo_path = Path(".")
+            repo = git.Repo.init(repo_path)
+
+            ignored_file = repo_path / "ignored_by_git.txt"
+            ignored_file.write_text("This file should be ignored by git.")
+
+            regular_file = repo_path / "regular_file.txt"
+            regular_file.write_text("This is a regular file.")
+
+            gitignore_content = "ignored_by_git.txt\n"
+            (repo_path / ".gitignore").write_text(gitignore_content)
+
+            repo.index.add([str(regular_file), ".gitignore"])
+            repo.index.commit("Initial commit with gitignore and regular file")
+
+            mock_io = MagicMock()
+            mock_io.tool_warning = MagicMock()
+
+            fnames_to_add = [str(ignored_file), str(regular_file)]
+
+            coder = Coder.create(self.GPT35, None, mock_io, fnames=fnames_to_add)
+
+            self.assertNotIn(str(ignored_file.resolve()), coder.abs_fnames)
+            self.assertIn(str(regular_file.resolve()), coder.abs_fnames)
+            mock_io.tool_warning.assert_any_call(
+                f"Skipping {ignored_file.name} that matches gitignore spec."
+            )
+
     def test_check_for_urls(self):
         io = InputOutput(yes=True)
         coder = Coder.create(self.GPT35, None, io=io)

tests/basic/test_main.py

@@ -949,16 +949,19 @@ class TestMain(TestCase):
 
     def test_invalid_edit_format(self):
         with GitTemporaryDirectory():
-            with patch("aider.io.InputOutput.offer_url") as mock_offer_url:
+            # Suppress stderr for this test as argparse prints an error message
-                result = main(
+            with patch("sys.stderr", new_callable=StringIO) as mock_stderr:
-                    ["--edit-format", "not-a-real-format", "--exit", "--yes"],
+                with self.assertRaises(SystemExit) as cm:
-                    input=DummyInput(),
+                    _ = main(
-                    output=DummyOutput(),
+                        ["--edit-format", "not-a-real-format", "--exit", "--yes"],
-                )
+                        input=DummyInput(),
-                self.assertEqual(result, 1)  # main() should return 1 on error
+                        output=DummyOutput(),
-                mock_offer_url.assert_called_once()
+                    )
-                args, _ = mock_offer_url.call_args
+                # argparse.ArgumentParser.exit() is called with status 2 for invalid choice
-                self.assertEqual(args[0], "https://aider.chat/docs/more/edit-formats.html")
+                self.assertEqual(cm.exception.code, 2)
+                stderr_output = mock_stderr.getvalue()
+                self.assertIn("invalid choice", stderr_output)
+                self.assertIn("not-a-real-format", stderr_output)
 
     def test_default_model_selection(self):
         with GitTemporaryDirectory():
@@ -1032,6 +1035,16 @@ class TestMain(TestCase):
             system_info = coder.get_platform_info()
             self.assertIn("Spanish", system_info)
 
+    def test_commit_language_japanese(self):
+        with GitTemporaryDirectory():
+            coder = main(
+                ["--commit-language", "japanese", "--exit", "--yes"],
+                input=DummyInput(),
+                output=DummyOutput(),
+                return_coder=True,
+            )
+            self.assertIn("japanese", coder.commit_language)
+
     @patch("git.Repo.init")
     def test_main_exit_with_git_command_not_found(self, mock_git_init):
         mock_git_init.side_effect = git.exc.GitCommandNotFound("git", "Command 'git' not found")
@@ -1275,6 +1288,21 @@ class TestMain(TestCase):
         for call in mock_io_instance.tool_warning.call_args_list:
             self.assertNotIn("Cost estimates may be inaccurate", call[0][0])
 
+    def test_argv_file_respects_git(self):
+        with GitTemporaryDirectory():
+            fname = Path("not_in_git.txt")
+            fname.touch()
+            with open(".gitignore", "w+") as f:
+                f.write("not_in_git.txt")
+            coder = main(
+                argv=["--file", "not_in_git.txt"],
+                input=DummyInput(),
+                output=DummyOutput(),
+                return_coder=True,
+            )
+            self.assertNotIn("not_in_git.txt", str(coder.abs_fnames))
+            self.assertFalse(coder.allowed_to_edit("not_in_git.txt"))
+
     def test_load_dotenv_files_override(self):
         with GitTemporaryDirectory() as git_dir:
             git_dir = Path(git_dir)

tests/basic/test_models.py

@@ -138,13 +138,13 @@ class TestModels(unittest.TestCase):
         self.assertEqual(model.name, "gpt-3.5-turbo")
 
         model = Model("sonnet")
-        self.assertEqual(model.name, "anthropic/claude-3-7-sonnet-20250219")
+        self.assertEqual(model.name, "anthropic/claude-sonnet-4-20250514")
 
         model = Model("haiku")
         self.assertEqual(model.name, "claude-3-5-haiku-20241022")
 
         model = Model("opus")
-        self.assertEqual(model.name, "claude-3-opus-20240229")
+        self.assertEqual(model.name, "claude-opus-4-20250514")
 
         # Test non-alias passes through unchanged
         model = Model("gpt-4")

tests/basic/test_onboarding.py

@@ -93,16 +93,14 @@ class TestOnboarding(unittest.TestCase):
     @patch.dict(os.environ, {"OPENROUTER_API_KEY": "or_key"}, clear=True)
     def test_try_select_default_model_openrouter_free(self, mock_check_tier):
         """Test OpenRouter free model selection."""
-        self.assertEqual(
+        self.assertEqual(try_to_select_default_model(), "openrouter/deepseek/deepseek-r1:free")
-            try_to_select_default_model(), "openrouter/google/gemini-2.5-pro-exp-03-25:free"
-        )
         mock_check_tier.assert_called_once_with("or_key")
 
     @patch("aider.onboarding.check_openrouter_tier", return_value=False)  # Assume paid tier
     @patch.dict(os.environ, {"OPENROUTER_API_KEY": "or_key"}, clear=True)
     def test_try_select_default_model_openrouter_paid(self, mock_check_tier):
         """Test OpenRouter paid model selection."""
-        self.assertEqual(try_to_select_default_model(), "openrouter/anthropic/claude-3.7-sonnet")
+        self.assertEqual(try_to_select_default_model(), "openrouter/anthropic/claude-sonnet-4")
         mock_check_tier.assert_called_once_with("or_key")
 
     @patch("aider.onboarding.check_openrouter_tier")
@@ -146,7 +144,7 @@ class TestOnboarding(unittest.TestCase):
     )
     def test_try_select_default_model_priority_openrouter(self, mock_check_tier):
         """Test OpenRouter key takes priority."""
-        self.assertEqual(try_to_select_default_model(), "openrouter/anthropic/claude-3.7-sonnet")
+        self.assertEqual(try_to_select_default_model(), "openrouter/anthropic/claude-sonnet-4")
         mock_check_tier.assert_called_once_with("or_key")
 
     @patch("aider.onboarding.check_openrouter_tier")
@@ -346,7 +344,7 @@ class TestOnboarding(unittest.TestCase):
 
     @patch(
         "aider.onboarding.try_to_select_default_model",
-        side_effect=[None, "openrouter/google/gemini-2.5-pro-exp-03-25:free"],
+        side_effect=[None, "openrouter/deepseek/deepseek-r1:free"],
     )  # Fails first, succeeds after oauth
     @patch(
         "aider.onboarding.offer_openrouter_oauth", return_value=True
@@ -360,7 +358,7 @@ class TestOnboarding(unittest.TestCase):
 
         selected_model = select_default_model(args, io_mock, analytics_mock)
 
-        self.assertEqual(selected_model, "openrouter/google/gemini-2.5-pro-exp-03-25:free")
+        self.assertEqual(selected_model, "openrouter/deepseek/deepseek-r1:free")
         self.assertEqual(mock_try_select.call_count, 2)  # Called before and after oauth
         mock_offer_oauth.assert_called_once_with(io_mock, analytics_mock)
         # Only one warning is expected: "No LLM model..."

tests/basic/test_openrouter.py

@@ -0,0 +1,73 @@
+from pathlib import Path
+
+from aider.models import ModelInfoManager
+from aider.openrouter import OpenRouterModelManager
+
+
+class DummyResponse:
+    """Minimal stand-in for requests.Response used in tests."""
+
+    def __init__(self, json_data):
+        self.status_code = 200
+        self._json_data = json_data
+
+    def json(self):
+        return self._json_data
+
+
+def test_openrouter_get_model_info_from_cache(monkeypatch, tmp_path):
+    """
+    OpenRouterModelManager should return correct metadata taken from the
+    downloaded (and locally cached) models JSON payload.
+    """
+    payload = {
+        "data": [
+            {
+                "id": "mistralai/mistral-medium-3",
+                "context_length": 32768,
+                "pricing": {"prompt": "100", "completion": "200"},
+                "top_provider": {"context_length": 32768},
+            }
+        ]
+    }
+
+    # Fake out the network call and the HOME directory used for the cache file
+    monkeypatch.setattr("requests.get", lambda *a, **k: DummyResponse(payload))
+    monkeypatch.setattr(Path, "home", staticmethod(lambda: tmp_path))
+
+    manager = OpenRouterModelManager()
+    info = manager.get_model_info("openrouter/mistralai/mistral-medium-3")
+
+    assert info["max_input_tokens"] == 32768
+    assert info["input_cost_per_token"] == 100.0
+    assert info["output_cost_per_token"] == 200.0
+    assert info["litellm_provider"] == "openrouter"
+
+
+def test_model_info_manager_uses_openrouter_manager(monkeypatch):
+    """
+    ModelInfoManager should delegate to OpenRouterModelManager when litellm
+    provides no data for an OpenRouter-prefixed model.
+    """
+    # Ensure litellm path returns no info so that fallback logic triggers
+    monkeypatch.setattr("aider.models.litellm.get_model_info", lambda *a, **k: {})
+
+    stub_info = {
+        "max_input_tokens": 512,
+        "max_tokens": 512,
+        "max_output_tokens": 512,
+        "input_cost_per_token": 100.0,
+        "output_cost_per_token": 200.0,
+        "litellm_provider": "openrouter",
+    }
+
+    # Force OpenRouterModelManager to return our stub info
+    monkeypatch.setattr(
+        "aider.models.OpenRouterModelManager.get_model_info",
+        lambda self, model: stub_info,
+    )
+
+    mim = ModelInfoManager()
+    info = mim.get_model_info("openrouter/fake/model")
+
+    assert info == stub_info

tests/basic/test_repo.py

@@ -59,6 +59,28 @@ class TestRepo(unittest.TestCase):
             self.assertIn("index", diffs)
             self.assertIn("workingdir", diffs)
 
+    def test_diffs_with_single_byte_encoding(self):
+        with GitTemporaryDirectory():
+            encoding = "cp1251"
+
+            repo = git.Repo()
+
+            fname = Path("foo.txt")
+            fname.write_text("index\n", encoding=encoding)
+            repo.git.add(str(fname))
+
+            # Make a change with non-ASCII symbols in the working dir
+            fname.write_text("АБВ\n", encoding=encoding)
+
+            git_repo = GitRepo(InputOutput(encoding=encoding), None, ".")
+            diffs = git_repo.get_diffs()
+
+            # check that all diff output can be converted to utf-8 for sending to model
+            diffs.encode("utf-8")
+
+            self.assertIn("index", diffs)
+            self.assertIn("АБВ", diffs)
+
     def test_diffs_detached_head(self):
         with GitTemporaryDirectory():
             repo = git.Repo()
@@ -661,3 +683,34 @@ class TestRepo(unittest.TestCase):
             # Verify the commit was actually made
             latest_commit_msg = raw_repo.head.commit.message
             self.assertEqual(latest_commit_msg.strip(), "Should succeed")
+
+    @patch("aider.models.Model.simple_send_with_retries")
+    def test_get_commit_message_uses_system_prompt_prefix(self, mock_send):
+        """
+        Verify that GitRepo.get_commit_message() prepends the model.system_prompt_prefix
+        to the system prompt sent to the LLM.
+        """
+        mock_send.return_value = "good commit message"
+
+        prefix = "MY-CUSTOM-PREFIX"
+        model = Model("gpt-3.5-turbo")
+        model.system_prompt_prefix = prefix
+
+        with GitTemporaryDirectory():
+            repo = GitRepo(InputOutput(), None, None, models=[model])
+
+            # Call the function under test
+            repo.get_commit_message("dummy diff", "dummy context")
+
+            # Ensure the LLM was invoked once
+            mock_send.assert_called_once()
+
+            # Grab the system message sent to the model
+            messages = mock_send.call_args[0][0]
+            system_msg_content = messages[0]["content"]
+
+            # Verify the prefix is at the start of the system message
+            self.assertTrue(
+                system_msg_content.startswith(prefix),
+                "system_prompt_prefix should be prepended to the system prompt",
+            )