dearwolf/aider
1
0
Fork 0
mirror of https://github.com/Aider-AI/aider.git synced 2025-06-10 14:45:00 +00:00
Code Issues Projects Releases Packages Wiki Activity Actions 3
8410 commits 2 branches 243 tags 278 MiB
Commit graph

1037 commits

Author SHA1 Message Date
Paul Gauthier
cd78080fa5 on search/replace error ask the LLM did you mean? 2024-05-11 15:02:22 -07:00
Paul Gauthier
6c45b58698 aider: Implemented find_similar_lines to fuzzy search content and return closest matching contiguous chunk of lines. 
# Aider chat conversation:

USER: implement `find_similar_lines` which will fuzzy search the content for the original lines and return the contiguous chunk of lines from content which are the closest match

ASSISTANT: Here is the implementation of `find_similar_lines` to fuzzy search the content and return the closest matching contiguous chunk of lines:

aider/coders/editblock_coder.py
<source>python
<<<<<<< SEARCH
    #did_you_mean = find_similar_lines(original, content)
=======
    did_you_mean = find_similar_lines(original, content)
>>>>>>> REPLACE
</source>

aider/coders/editblock_coder.py
<source>python
<<<<<<< SEARCH
=======
def find_similar_lines(search_lines, content_lines, threshold=0.8):
    search_lines = search_lines.splitlines()
    content_lines = content_lines.splitlines()

    best_ratio = 0
    best_match = None

    for i in range(len(content_lines) - len(search_lines) + 1):
        chunk = content_lines[i:i+len(search_lines)]
        ratio = SequenceMatcher(None, search_lines, chunk).ratio()
        if ratio > best_ratio:
            best_ratio = ratio
            best_match = chunk

    if best_ratio >= threshold:
        return "\n".join(best_match)
    else:
        return ""
>>>>>>> REPLACE
</source>

This adds the `find_similar_lines` function which:

1. Splits the search lines and content lines on newlines
2. Iterates through the content lines, considering each contiguous chunk the same length as the search lines
3. Calculates the SequenceMatcher ratio between the search lines and each chunk
4. Keeps track of the chunk with the highest ratio
5. If the best ratio is above the threshold (default 0.8), it returns the best matching chunk joined back into a string
6. Otherwise it returns an empty string to indicate no close enough match was found

It also uncomments the line to call `find_similar_lines` and store the result in `did_you_mean`.

Let me know if you have any other questions!
 2024-05-11 10:49:34 -07:00
Paul Gauthier
056dae6530 Removed unused find_similar_lines function call from EditBlockCoder class. 2024-05-11 10:49:33 -07:00
Paul Gauthier
fd6f31f972 Replaced find_similar_text with find_similar_lines in editblock_coder.py. 2024-05-11 10:48:45 -07:00
Paul Gauthier
d02506db16 aider: Implemented find_similar_text function to fuzzy search the content for the closest match to the original text. 
# Aider chat conversation:

USER: I did `git reset --hard HEAD~1` to discard the last edits. Please wait for further instructions before attempting that change again. Feel free to ask relevant questions about why the changes were reverted.

ASSISTANT: I understand you reverted the previous changes. Before I attempt to implement the `find_similar_lines` function again, I have a few questions to ensure I follow your guidelines correctly:

1. When proposing changes, should I only modify the `aider/coders/editblock_coder.py` file since that is the only one you have explicitly added to the chat
^C KeyboardInterrupt

USER: implement `find_similar_text` which will fuzzy search the content for the original text and return the part of content which is the closest match

ASSISTANT: Here is the implementation of `find_similar_text` to fuzzy search the content for the closest match to the original text:

aider/coders/editblock_coder.py
<source>python
<<<<<<< SEARCH
=======
from difflib import SequenceMatcher

def find_similar_text(original, content):
    content_len = len(content)
    original_len = len(original)

    best_ratio = 0
    best_match = None

    for i in range(content_len - original_len + 1):
        chunk = content[i:i+original_len]
        ratio = SequenceMatcher(None, original, chunk).ratio()

        if ratio > best_ratio:
            best_ratio = ratio
            best_match = chunk

    return best_match
>>>>>>> REPLACE
</source>

This function:

1. Iterates through the content, considering each chunk of text the same length as the original
2. Calculates the SequenceMatcher ratio between the original text and each chunk
3. Keeps track of the chunk with the highest ratio
4. Returns the chunk of content that best matches the original text

It will return the portion of `content` that is the closest fuzzy match to `original`.

Let me know if you have any other questions!
 2024-05-11 10:43:40 -07:00
Paul Gauthier
6d39e2c857 Replaced find_similar_lines with find_similar_text in the EditBlockCoder class. 2024-05-11 10:43:38 -07:00
Paul Gauthier
587ba4d676 Added functionality to suggest similar lines when a search block fails to match in EditBlockCoder. 2024-05-11 10:38:44 -07:00
Paul Gauthier
785259b59c try patching any of the other files in the chat 2024-05-11 10:33:46 -07:00
Paul Gauthier
5ec441dd2c More clear feedback when SEARCH/REPLACE blocks fail to match 2024-05-11 10:25:16 -07:00
Paul Gauthier
602a0c7c31 refac utils.split_chat_history_markdown 2024-05-11 07:52:06 -07:00
paul-gauthier
45b2ba8a10
Merge pull request #591 from paul-gauthier/restore-chat-history 
Restore prior chat history on launch
 2024-05-11 07:49:43 -07:00
Paul Gauthier
1098b428e6 prompt tweaks, retry on httpx.ReadTimeout 2024-05-11 07:47:53 -07:00
Paul Gauthier
3171789b1f look for mentions with trailing : 2024-05-10 19:38:05 -07:00
Paul Gauthier
a5bc2e8b97 Added prompt to reply in the users language #597 2024-05-09 14:06:31 -07:00
Paul Gauthier
4eec60f42c updated assistant auto-reply to no files 2024-05-09 11:56:11 -07:00
Paul Gauthier
444d17de93 reverted prompt closer to e9da401, added helpful assistant replies to repo and files messages 2024-05-09 11:27:13 -07:00
Paul Gauthier
7a98953fae split repo map and added files into 2 user messages 2024-05-08 14:13:50 -07:00
Paul Gauthier
6a01b66b2c I have *added these files to the chat* 2024-05-08 14:05:58 -07:00
Paul Gauthier
738c3b8e5e fall back to global repo map if files in chat are disjoint from rest of repo 2024-05-08 13:56:06 -07:00
Paul Gauthier
48fd67485c add a user message during --show-prompts 2024-05-08 13:49:38 -07:00
Paul Gauthier
5bd875ffbf cleanup stray << HEAD 2024-05-08 13:45:18 -07:00
Paul Gauthier
9e7f2ec790 cleanup 2024-05-08 13:41:24 -07:00
Paul Gauthier
f256b43043 wip 2024-05-08 13:35:34 -07:00
Paul Gauthier
fb8ed21b13 refactored lazy_prompt in all coders 2024-05-08 13:07:35 -07:00
Paul Gauthier
9ff6770a04 refactored litellm to avoid duplicating workarounds 2024-05-08 08:05:15 -07:00
Paul Gauthier
04b224962e send the reminder if unknown context window size 2024-05-07 08:42:33 -07:00
Paul Gauthier
e61857ef09 summarize as many messages as will fit into the summarizer context 2024-05-06 09:47:14 -07:00
Paul Gauthier
64470955d4 pass max_chat_history_tokens into ChatSummary 2024-05-06 09:29:21 -07:00
Paul Gauthier
1747525418 aider: Added max_chat_history_tokens as an explicit argument to the Coder.__init__ method and passed args.max_chat_history_tokens when creating the Coder instance in main(). 
# Aider chat conversation:

USER: don't use kwargs, add it as an explicit arg

ASSISTANT: Here is the *SEARCH/REPLACE block* to add `max_chat_history_tokens` as an explicit argument instead of using `**kwargs`:

aider/coders/base_coder.py
```python
<<<<<<< SEARCH
    def __init__(
        self,
        main_model,
        io,
        fnames=None,
        git_dname=None,
        pretty=True,
        show_diffs=False,
        auto_commits=True,
        dirty_commits=True,
        dry_run=False,
        map_tokens=1024,
        verbose=False,
        assistant_output_color="blue",
        code_theme="default",
        stream=True,
        use_git=True,
        voice_language=None,
        aider_ignore_file=None,
        cur_messages=None,
        done_messages=None,
    ):
=======
    def __init__(
        self,
        main_model,
        io,
        fnames=None,
        git_dname=None,
        pretty=True,
        show_diffs=False,
        auto_commits=True,
        dirty_commits=True,
        dry_run=False,
        map_tokens=1024,
        verbose=False,
        assistant_output_color="blue",
        code_theme="default",
        stream=True,
        use_git=True,
        voice_language=None,
        aider_ignore_file=None,
        cur_messages=None,
        done_messages=None,
        max_chat_history_tokens=None,
    ):
>>>>>>> REPLACE
```

aider/main.py
```python
<<<<<<< SEARCH
        coder = Coder.create(
            main_model=main_model,
            edit_format=args.edit_format,
            io=io,
            ##
            fnames=fnames,
            git_dname=git_dname,
            pretty=args.pretty,
            show_diffs=args.show_diffs,
            auto_commits=args.auto_commits,
            dirty_commits=args.dirty_commits,
            dry_run=args.dry_run,
            map_tokens=args.map_tokens,
            verbose=args.verbose,
            assistant_output_color=args.assistant_output_color,
            code_theme=args.code_theme,
            stream=args.stream,
            use_git=args.git,
            voice_language=args.voice_language,
            aider_ignore_file=args.aiderignore,
        )
=======
        coder = Coder.create(
            main_model=main_model,
            edit_format=args.edit_format,
            io=io,
            ##
            fnames=fnames,
            git_dname=git_dname,
            pretty=args.pretty,
            show_diffs=args.show_diffs,
            auto_commits=args.auto_commits,
            dirty_commits=args.dirty_commits,
            dry_run=args.dry_run,
            map_tokens=args.map_tokens,
            verbose=args.verbose,
            assistant_output_color=args.assistant_output_color,
            code_theme=args.code_theme,
            stream=args.stream,
            use_git=args.git,
            voice_language=args.voice_language,
            aider_ignore_file=args.aiderignore,
            max_chat_history_tokens=args.max_chat_history_tokens,
        )
>>>>>>> REPLACE
```

This adds `max_chat_history_tokens` as an explicit argument to the `Coder.__init__` method, and passes `args.max_chat_history_tokens` when creating the `Coder` instance in `main()`.
 2024-05-06 09:25:04 -07:00
Paul Gauthier
eac8e4cb8f announce reload of chat history 2024-05-05 19:08:00 -07:00
Paul Gauthier
00c12efd3f cleanup 2024-05-05 19:04:24 -07:00
Paul Gauthier
b3e19cf5be reload history 2024-05-05 19:03:17 -07:00
Paul Gauthier
0d43468aab added rules header 2024-05-04 08:07:15 -07:00
Paul Gauthier
7bcce6e8c6 move reminder after examples 2024-05-04 08:00:39 -07:00
Paul Gauthier
b5bb453378 examples_as_sys_msg 2024-05-03 15:24:36 -07:00
Paul Gauthier
5d32dd77fc Added diff-fenced coder 2024-05-03 13:50:15 -07:00
Paul Gauthier
921c7ceb80 Merge branch 'main' into gemini-editblock-and-examples 2024-05-03 13:17:23 -07:00
Paul Gauthier
e8666d3984 fix wholefile prompt 2024-05-01 15:06:31 -07:00
Paul Gauthier
f4b1797998 put filename back outside fences 2024-05-01 11:59:23 -07:00
Paul Gauthier
5ed9e8cb6d Merge remote-tracking branch 'origin/main' 2024-05-01 11:08:42 -07:00
Paul Gauthier
e76d1c0cfa accepts_multi_system_msgs -> reminder_as_sys_msg 2024-05-01 10:30:41 -07:00
Paul Gauthier
862c0dd0d7 stronger code base switch prompt 2024-05-01 09:40:47 -07:00
Paul Gauthier
1403d19aa7 Added example messages to wholefile edit format 2024-05-01 09:34:40 -07:00
Paul Gauthier
2c0dff52d3 asking for code language in whole edit format confuses some models 2024-05-01 09:17:29 -07:00
Paul Gauthier
0fb08896e3 Merge branch 'main' into gemini-editblock-and-examples 2024-05-01 09:02:08 -07:00
Paul Gauthier
7fd3b8aeee Tell the AI we are switching code bases 2024-04-30 20:51:24 -07:00
Paul Gauthier
d51cada163 make the examples part of the chat 2024-04-30 20:45:49 -07:00
Paul Gauthier
22d90d70c6 prompt copy 2024-04-30 20:24:53 -07:00
Paul Gauthier
256a9a454c move cloning into Coder.create, summarize chat history if edit format changes 2024-04-30 17:31:58 -07:00
Paul Gauthier
8e9a00006b carry conversation history to switched model 2024-04-30 16:25:47 -07:00