aider-ce 0.87.10.dev0__tar.gz → 0.87.12__tar.gz

{aider_ce-0.87.10.dev0/aider_ce.egg-info → aider_ce-0.87.12}/PKG-INFO

@@ -1,6 +1,6 @@
 Metadata-Version: 2.4
 Name: aider-ce
-Version: 0.87.10.dev0
+Version: 0.87.12
 Summary: Aider is AI pair programming in your terminal
 Project-URL: Homepage, https://github.com/dwash96/aider-ce
 Classifier: Development Status :: 4 - Beta
@@ -78,6 +78,34 @@ Provides-Extra: playwright
 Requires-Dist: playwright; extra == "playwright"
 Dynamic: license-file
 
+## Project Roadmap/Goals
+
+The current priorities are to improve core capabilities and user experience of the Aider project
+
+1. **Base Asynchronicity (aider-ce coroutine-experiment branch)**
+  * [x] Refactor codebase to have the main loop run asynchronously
+  * [x] Update test harness to work with new asynchronous methods
+
+2. **Repo Map Accuracy**
+  * [ ] [Bias page ranking toward active/editable files in repo map parsing](https://github.com/Aider-AI/aider/issues/2405)
+  * [ ] [Handle non-unique symbols that break down in large codebases](https://github.com/Aider-AI/aider/issues/2341)
+  * [ ] [Include AST information in repo map for richer context](https://github.com/Aider-AI/aider/issues/2688)
+
+3. **Context Discovery**
+  * [ ] Develop AST-based search capabilities
+  * [ ] Enhance file search with ripgrep integration
+  * [ ] Implement RAG (Retrieval-Augmented Generation) for better code retrieval
+  * [ ] Build an explicit workflow and local tooling for internal discovery mechanisms
+
+4. **Context Delivery**
+  * [ ] Use workflow for internal discovery to better target file snippets needed for specific tasks
+  * [ ] Add support for partial files and code snippets in model completion messages   
+
+5. **TUI Experience**
+  * [ ] Add a full TUI (probably using textual) to have a visual interface competitive with the other coding agent terminal programs
+  * [ ] Re-integrate pretty output formatting
+  * [ ] Implement a response area, a prompt area with current auto completion capabilities, and a helper area for management utility commands
+
 ## Fork Additions
 
 This project aims to be compatible with upstream Aider, but with priority commits merged in and with some opportunistic bug fixes and optimizations
@@ -112,6 +140,7 @@ This project aims to be compatible with upstream Aider, but with priority commit
 * [Remove Confirm Responses from History](https://github.com/Aider-AI/aider/pull/3958)
 * [Benchmark Results By Language](https://github.com/dwash96/aider-ce/pull/27)
 * [Allow Benchmarks to Use Repo Map For Better Accuracy](https://github.com/dwash96/aider-ce/pull/25)
+* [Read File Globbing](https://github.com/Aider-AI/aider/pull/3395)
 
 ### Other Notes
 * [MCP Configuration](https://github.com/dwash96/aider-ce/blob/main/aider/website/docs/config/mcp.md)

{aider_ce-0.87.10.dev0 → aider_ce-0.87.12}/README.md

@@ -1,3 +1,31 @@
+## Project Roadmap/Goals
+
+The current priorities are to improve core capabilities and user experience of the Aider project
+
+1. **Base Asynchronicity (aider-ce coroutine-experiment branch)**
+  * [x] Refactor codebase to have the main loop run asynchronously
+  * [x] Update test harness to work with new asynchronous methods
+
+2. **Repo Map Accuracy**
+  * [ ] [Bias page ranking toward active/editable files in repo map parsing](https://github.com/Aider-AI/aider/issues/2405)
+  * [ ] [Handle non-unique symbols that break down in large codebases](https://github.com/Aider-AI/aider/issues/2341)
+  * [ ] [Include AST information in repo map for richer context](https://github.com/Aider-AI/aider/issues/2688)
+
+3. **Context Discovery**
+  * [ ] Develop AST-based search capabilities
+  * [ ] Enhance file search with ripgrep integration
+  * [ ] Implement RAG (Retrieval-Augmented Generation) for better code retrieval
+  * [ ] Build an explicit workflow and local tooling for internal discovery mechanisms
+
+4. **Context Delivery**
+  * [ ] Use workflow for internal discovery to better target file snippets needed for specific tasks
+  * [ ] Add support for partial files and code snippets in model completion messages   
+
+5. **TUI Experience**
+  * [ ] Add a full TUI (probably using textual) to have a visual interface competitive with the other coding agent terminal programs
+  * [ ] Re-integrate pretty output formatting
+  * [ ] Implement a response area, a prompt area with current auto completion capabilities, and a helper area for management utility commands
+
 ## Fork Additions
 
 This project aims to be compatible with upstream Aider, but with priority commits merged in and with some opportunistic bug fixes and optimizations
@@ -32,6 +60,7 @@ This project aims to be compatible with upstream Aider, but with priority commit
 * [Remove Confirm Responses from History](https://github.com/Aider-AI/aider/pull/3958)
 * [Benchmark Results By Language](https://github.com/dwash96/aider-ce/pull/27)
 * [Allow Benchmarks to Use Repo Map For Better Accuracy](https://github.com/dwash96/aider-ce/pull/25)
+* [Read File Globbing](https://github.com/Aider-AI/aider/pull/3395)
 
 ### Other Notes
 * [MCP Configuration](https://github.com/dwash96/aider-ce/blob/main/aider/website/docs/config/mcp.md)

{aider_ce-0.87.10.dev0 → aider_ce-0.87.12}/aider/__init__.py

@@ -1,6 +1,6 @@
 from packaging import version
 
-__version__ = "0.87.10.dev"
+__version__ = "0.87.12.dev"
 safe_version = __version__
 
 try:

{aider_ce-0.87.10.dev0 → aider_ce-0.87.12}/aider/_version.py

@@ -28,7 +28,7 @@ version_tuple: VERSION_TUPLE
 commit_id: COMMIT_ID
 __commit_id__: COMMIT_ID
 
-__version__ = version = '0.87.10.dev0'
-__version_tuple__ = version_tuple = (0, 87, 10, 'dev0')
+__version__ = version = '0.87.12'
+__version_tuple__ = version_tuple = (0, 87, 12)
 
-__commit_id__ = commit_id = 'gc94daebab'
+__commit_id__ = commit_id = 'g102a12195'

{aider_ce-0.87.10.dev0 → aider_ce-0.87.12}/aider/args.py

@@ -780,13 +780,13 @@ def get_parser(default_config_files, git_root):
         "--file",
         action="append",
         metavar="FILE",
-        help="specify a file to edit (can be used multiple times)",
+        help="specify a file to edit (can be used multiple times, glob patterns supported)",
     ).complete = shtab.FILE
     group.add_argument(
         "--read",
         action="append",
         metavar="FILE",
-        help="specify a read-only file (can be used multiple times)",
+        help="specify a read-only file (can be used multiple times, glob patterns supported)",
     ).complete = shtab.FILE
     group.add_argument(
         "--vim",

{aider_ce-0.87.10.dev0 → aider_ce-0.87.12}/aider/coders/editblock_prompts.py

@@ -15,8 +15,6 @@ If the request is ambiguous, ask questions.
 Consider potential edge cases.
 Think about how to verify your changes are correct.
 
-Always reply to the user in {language}.
-
 Once you understand the request and have a plan, you MUST:
 
 1. Decide if you need to propose *SEARCH/REPLACE* edits to any files that haven't been added to the chat. You can create new files without asking!

{aider_ce-0.87.10.dev0 → aider_ce-0.87.12}/aider/coders/patch_prompts.py

@@ -15,8 +15,6 @@ Respect and use existing conventions, libraries, etc that are already present in
 Take requests for changes to the supplied code.
 If the request is ambiguous, ask questions.
 
-Always reply to the user in {language}.
-
 Once you understand the request you MUST:
 
 1. Decide if you need to propose edits to any files that haven't been added to the chat. You can create new files without asking!

{aider_ce-0.87.10.dev0 → aider_ce-0.87.12}/aider/coders/udiff_prompts.py

@@ -15,8 +15,6 @@ Think about how to verify your changes are correct.
 Take requests for changes to the supplied code.
 If the request is ambiguous, ask questions.
 
-Always reply to the user in {language}.
-
 Once you have a plan, for each file that needs to be changed, write out the changes similar to a unified diff like `diff -U0` would produce.
 """
 

{aider_ce-0.87.10.dev0 → aider_ce-0.87.12}/aider/coders/wholefile_prompts.py

@@ -8,11 +8,6 @@ class WholeFilePrompts(CoderPrompts):
 Think step-by-step. Plan your changes carefully. Explain your plan first.
 Take requests for changes to the supplied code.
 If the request is ambiguous, ask questions.
-Consider potential edge cases.
-Think about how to verify your changes are correct.
-
-Always reply to the user in {language}.
-
 {final_reminders}
 Once you understand the request and have a plan, you MUST:
 1. Determine if any code changes are needed.

{aider_ce-0.87.10.dev0 → aider_ce-0.87.12}/aider/main.py

@@ -1,3 +1,4 @@
+import glob
 import json
 import os
 import re
@@ -449,6 +450,25 @@ def sanity_check_repo(repo, io):
     return False
 
 
+def expand_glob_patterns(patterns, root="."):
+    """Expand glob patterns in a list of file paths."""
+    expanded_files = []
+    for pattern in patterns:
+        # Check if the pattern contains glob characters
+        if any(c in pattern for c in "*?[]"):
+            # Use glob to expand the pattern
+            matches = glob.glob(pattern, recursive=True)
+            if matches:
+                expanded_files.extend(matches)
+            else:
+                # If no matches, keep the original pattern
+                expanded_files.append(pattern)
+        else:
+            # Not a glob pattern, keep as is
+            expanded_files.append(pattern)
+    return expanded_files
+
+
 def main(argv=None, input=None, output=None, force_git_root=None, return_coder=False):
     report_uncaught_exceptions()
 
@@ -677,10 +697,16 @@ def main(argv=None, input=None, output=None, force_git_root=None, return_coder=F
         for fname in loaded_dotenvs:
             io.tool_output(f"Loaded {fname}")
 
+    # Expand glob patterns in files and file arguments
     all_files = args.files + (args.file or [])
+    all_files = expand_glob_patterns(all_files)
     fnames = [str(Path(fn).resolve()) for fn in all_files]
+
+    # Expand glob patterns in read arguments
+    read_patterns = args.read or []
+    read_expanded = expand_glob_patterns(read_patterns)
     read_only_fnames = []
-    for fn in args.read or []:
+    for fn in read_expanded:
         path = Path(fn).expanduser().resolve()
         if path.is_dir():
             read_only_fnames.extend(str(f) for f in path.rglob("*") if f.is_file())

{aider_ce-0.87.10.dev0 → aider_ce-0.87.12}/aider/models.py

@@ -8,7 +8,6 @@ import platform
 import sys
 import time
 from dataclasses import dataclass, fields
-from datetime import datetime
 from pathlib import Path
 from typing import Optional, Union
 
@@ -903,57 +902,6 @@ 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, tools=None, max_tokens=None
     ):
@@ -1029,8 +977,6 @@ class Model(ModelSettings):
                     "Copilot-Integration-Id": "vscode-chat",
                 }
 
-            self.github_copilot_token_to_open_ai_key(kwargs["extra_headers"])
-
         try:
             res = litellm.completion(**kwargs)
         except Exception as err:

{aider_ce-0.87.10.dev0 → aider_ce-0.87.12}/aider/resources/model-metadata.json

@@ -1,6 +1,6 @@
 {
     "deepseek/deepseek-reasoner": {
-        "max_tokens": 64000,
+        "max_tokens": 128000,
         "max_input_tokens": 128000,
         "max_output_tokens": 64000,
         "input_cost_per_token": 0.00000028,
@@ -15,9 +15,9 @@
         "supports_prompt_caching": true
     },
     "deepseek/deepseek-chat": {
-        "max_tokens": 8192,
+        "max_tokens": 128000,
         "max_input_tokens": 128000,
-        "max_output_tokens": 8192,
+        "max_output_tokens": 8000,
         "input_cost_per_token": 0.00000028,
         "input_cost_per_token_cache_hit": 0.000000028,
         "cache_read_input_token_cost": 0.000000028,

{aider_ce-0.87.10.dev0 → aider_ce-0.87.12/aider_ce.egg-info}/PKG-INFO

@@ -1,6 +1,6 @@
 Metadata-Version: 2.4
 Name: aider-ce
-Version: 0.87.10.dev0
+Version: 0.87.12
 Summary: Aider is AI pair programming in your terminal
 Project-URL: Homepage, https://github.com/dwash96/aider-ce
 Classifier: Development Status :: 4 - Beta
@@ -78,6 +78,34 @@ Provides-Extra: playwright
 Requires-Dist: playwright; extra == "playwright"
 Dynamic: license-file
 
+## Project Roadmap/Goals
+
+The current priorities are to improve core capabilities and user experience of the Aider project
+
+1. **Base Asynchronicity (aider-ce coroutine-experiment branch)**
+  * [x] Refactor codebase to have the main loop run asynchronously
+  * [x] Update test harness to work with new asynchronous methods
+
+2. **Repo Map Accuracy**
+  * [ ] [Bias page ranking toward active/editable files in repo map parsing](https://github.com/Aider-AI/aider/issues/2405)
+  * [ ] [Handle non-unique symbols that break down in large codebases](https://github.com/Aider-AI/aider/issues/2341)
+  * [ ] [Include AST information in repo map for richer context](https://github.com/Aider-AI/aider/issues/2688)
+
+3. **Context Discovery**
+  * [ ] Develop AST-based search capabilities
+  * [ ] Enhance file search with ripgrep integration
+  * [ ] Implement RAG (Retrieval-Augmented Generation) for better code retrieval
+  * [ ] Build an explicit workflow and local tooling for internal discovery mechanisms
+
+4. **Context Delivery**
+  * [ ] Use workflow for internal discovery to better target file snippets needed for specific tasks
+  * [ ] Add support for partial files and code snippets in model completion messages   
+
+5. **TUI Experience**
+  * [ ] Add a full TUI (probably using textual) to have a visual interface competitive with the other coding agent terminal programs
+  * [ ] Re-integrate pretty output formatting
+  * [ ] Implement a response area, a prompt area with current auto completion capabilities, and a helper area for management utility commands
+
 ## Fork Additions
 
 This project aims to be compatible with upstream Aider, but with priority commits merged in and with some opportunistic bug fixes and optimizations
@@ -112,6 +140,7 @@ This project aims to be compatible with upstream Aider, but with priority commit
 * [Remove Confirm Responses from History](https://github.com/Aider-AI/aider/pull/3958)
 * [Benchmark Results By Language](https://github.com/dwash96/aider-ce/pull/27)
 * [Allow Benchmarks to Use Repo Map For Better Accuracy](https://github.com/dwash96/aider-ce/pull/25)
+* [Read File Globbing](https://github.com/Aider-AI/aider/pull/3395)
 
 ### Other Notes
 * [MCP Configuration](https://github.com/dwash96/aider-ce/blob/main/aider/website/docs/config/mcp.md)