PierrunoYT
commented
4 months ago Closed PierrunoYT closed 1 day ago
PierrunoYT
commented
4 months ago 
klieret
commented
4 months ago Please copy the message as text and add the full command that you were running. It also sounds like you're trying to use this software on Go, right? This might need some tweaking
PierrunoYT
commented
4 months ago Please copy the message as text and add the full command that you were running. It also sounds like you're trying to use this software on Go, right? This might need some tweaking
Hey there
I'm trying to run it on WSL Windows 11. I followed the readme for Quick Setup
klieret
commented
4 months ago Please copy the message as text and add the full command that you were running, as well as how you set up the package. We can only help if you give as much information as possible.
PierrunoYT
commented
4 months ago I need to try again and see. I don't have it open anymore.
baibaomen
commented
4 months ago Reproduced on my machine, occasionally. Environment: wsl2 on windows 11.
2024-04-08 13:03:48,357 - httpx - INFO - HTTP Request: POST https://api.openai.com/v1/chat/completions "HTTP/1.1 200 OK"
2024-04-08 13:03:48,357 - api_models - INFO - input_tokens=13_999, output_tokens=226, instance_cost=0.98, cost=0.15
2024-04-08 13:03:48,357 - api_models - INFO - total_tokens_sent=95_868, total_tokens_received=840, total_cost=0.98, total_api_calls=8
INFO 💭 THOUGHT (primary)
Since there are no matches for "tokenCount" in `chat.tsx`, it seems that the token count is not currently being used in this component. We will need to modify the component to include the token count from the chat session
state.
To do this, we need to pass the `tokenCount` from the chat session state to the component where the `chat-message-action-date` is rendered. This will likely involve updating the component's props to include the `tokenCount` and
then modifying the JSX to display it.
Let's edit the `chat.tsx` file to include the token count in the `chat-message-action-date` element. We'll need to add code to retrieve the `tokenCount` from the chat session state and then update the JSX to display it
alongside the date.
First, we need to navigate to the relevant section of the file to make our edits. Since the file is large, we'll use the `goto` command to move the window to include line 1441, which is where we found the
`chat-message-action-date` element.
INFO 🎬 ACTION (primary)
goto 1441
INFO Saved trajectory to trajectories/root/gpt4__baibaomen__ChatGPT-Next-Web__default_from_url__t-0.00__p-0.95__c-3.00__install-1/baibaomen__ChatGPT-Next-Web-i6.traj
INFO 🤖 MODEL INPUT
[File: /baibaomen__ChatGPT-Next-Web/app/components/chat.tsx (1554 lines total)]
(1425 more lines above)
1426: return (
1427: <img
1428: className={
1429: styles["chat-message-item-image-multi"]
1430: }
1431: key={index}
1432: src={image}
1433: alt=""
1434: />
1435: );
1436: })}
1437: </div>
1438: )}
1439: </div>
1440:
1441: <div className={styles["chat-message-action-date"]}>
1442: {isContext
1443: ? Locale.Chat.IsContext
1444: : message.date.toLocaleString()}
1445: </div>
1446: </div>
1447: </div>
1448: {shouldShowClearContextDivider && <ClearContextDivider />}
1449: </Fragment>
1450: );
1451: })}
1452: </div>
1453:
1454: <div className={styles["chat-input-panel"]}>
1455: <PromptHints prompts={promptHints} onPromptSelect={onPromptSelect} />
1456:
1457: <ChatActions
1458: uploadImage={uploadImage}
1459: setAttachImages={setAttachImages}
1460: setUploading={setUploading}
1461: showPromptModal={() => setShowPromptModal(true)}
1462: scrollToBottom={scrollToBottom}
1463: hitBottom={hitBottom}
1464: uploading={uploading}
1465: showPromptHints={() => {
1466: // Click again to close
1467: if (promptHints.length > 0) {
1468: setPromptHints([]);
1469: return;
1470: }
1471:
1472: inputRef.current?.focus();
1473: setUserInput("/");
1474: onSearch("");
1475: }}
1476: />
1477: <label
1478: className={`${styles["chat-input-panel-inner"]} ${
1479: attachImages.length != 0
1480: ? styles["chat-input-panel-inner-attach"]
1481: : ""
1482: }`}
1483: htmlFor="chat-input"
1484: >
1485: <textarea
1486: id="chat-input"
1487: ref={inputRef}
1488: className={styles["chat-input"]}
1489: placeholder={Locale.Chat.Input(submitKey)}
1490: onInput={(e) => onInput(e.currentTarget.value)}
1491: value={userInput}
1492: onKeyDown={onInputKeyDown}
1493: onFocus={scrollToBottom}
1494: onClick={scrollToBottom}
1495: onPaste={handlePaste}
1496: rows={inputRows}
1497: autoFocus={autoFocus}
1498: style={{
1499: fontSize: config.fontSize,
1500: }}
1501: />
1502: {attachImages.length != 0 && (
1503: <div className={styles["attach-images"]}>
1504: {attachImages.map((image, index) => {
1505: return (
1506: <div
1507: key={index}
1508: className={styles["attach-image"]}
1509: style={{ backgroundImage: `url("${image}")` }}
1510: >
1511: <div className={styles["attach-image-mask"]}>
1512: <DeleteImageButton
1513: deleteImage={() => {
1514: setAttachImages(
1515: attachImages.filter((_, i) => i !== index),
1516: );
1517: }}
1518: />
1519: </div>
1520: </div>
1521: );
1522: })}
1523: </div>
1524: )}
1525: <IconButton
(29 more lines below)
(Open file: /baibaomen__ChatGPT-Next-Web/app/components/chat.tsx)
(Current directory: /baibaomen__ChatGPT-Next-Web)
bash-$
2024-04-08 13:04:04,351 - httpx - INFO - HTTP Request: POST https://api.openai.com/v1/chat/completions "HTTP/1.1 200 OK"
2024-04-08 13:04:04,353 - api_models - INFO - input_tokens=15_165, output_tokens=184, instance_cost=1.14, cost=0.16
2024-04-08 13:04:04,354 - api_models - INFO - total_tokens_sent=111_033, total_tokens_received=1_024, total_cost=1.14, total_api_calls=9
INFO 💭 THOUGHT (primary)
Now that we are at the correct location in the `chat.tsx` file, we can proceed to edit the file. We need to modify the JSX to include the token count information alongside the message date. Since we don't have the exact code
that fetches the token count, we will assume that the token count can be accessed from a `tokenCount` property on the `message` object, similar to how the `date` is accessed.
Let's edit the file to include the token count in the `chat-message-action-date` element. We will add a new span to display the token count.
INFO 🎬 ACTION (primary)
edit 1441:1445
<div className={styles["chat-message-action-date"]}>
{isContext
? Locale.Chat.IsContext
: `${message.date.toLocaleString()} - Tokens used: ${message.tokenCount}`}
</div>
end_of_edit
WARNING Failed to execute command: Container crashed. Failed to get exit code. Output:
---
---
RESTARTING PROCESS.
INFO Beginning environment shutdown...
INFO Agent container stopped
DEBUG Starting container with command: docker run -i --rm --name sweagent-swe-agent-latest-dc7a0161ff sweagent/swe-agent:latest /bin/bash -l -m
INFO 🌱 Environment Initialized
INFO Saved trajectory to trajectories/root/gpt4__baibaomen__ChatGPT-Next-Web__default_from_url__t-0.00__p-0.95__c-3.00__install-1/baibaomen__ChatGPT-Next-Web-i6.traj
INFO Saved predictions to trajectories/root/gpt4__baibaomen__ChatGPT-Next-Web__default_from_url__t-0.00__p-0.95__c-3.00__install-1/all_preds.jsonl
INFO No patch to save.
INFO Not openening PR because submission was made.
(swe-agent) root@AlienJack:~/SWE-agent#Please include the exact command you ran, it's really hard to reproduce otherwise
PierrunoYT
commented
4 months ago Please include the exact command you ran, it's really hard to reproduce otherwise
Created a new issue
klieret
commented
4 months ago Copied from @PierrunoYT (#157 ):
docker run --rm -it -v /var/run/docker.sock:/var/run/docker.sock \
-v /mnt/c/Users/pierr/SWE-agent/keys.cfg:/app/keys.cfg \
--platform=linux/arm64 \
sweagent/swe-agent-run:latest \
python run.py --image_name=sweagent/swe-agent:latest \
--model_name gpt4 \
--data_path https://github.com/OpenDevin/OpenDevin/issues/381 \
--config_file config/default_from_url.yaml \
--skip_existing=False \
--open_prwith output
Parsing command file: config/commands/defaults.sh
Parsing command file: config/commands/search.sh
Parsing command file: config/commands/edit_linting.sh
Parsing command file: config/commands/_split_string.py
Parsing command file: config/commands/defaults.sh
Parsing command file: config/commands/search.sh
Parsing command file: config/commands/edit_linting.sh
Parsing command file: config/commands/_split_string.py
INFO 📙 Arguments: actions:
open_pr: true
push_gh_repo_url: ''
skip_if_commits_reference_issue: true
agent:
config:
_commands:
- arguments:
line_number:
description: the line number to move the window to (if not provided, the
window will start at the top of the file)
required: false
type: integer
path:
description: the path to the file to open
required: true
type: string
code: 'open() { if [ -z "$1" ] then echo "Usage: open <file>" return fi #
Check if the second argument is provided if [ -n "$2" ]; then #
Check if the provided argument is a valid number if ! [[ $2 =~ ^[0-9]+$
]]; then echo "Usage: open <file> [<line_number>]" echo
"Error: <line_number> must be a number" return # Exit if the line
number is not valid fi local max_line=$(awk ''END {print NR}''
$1) if [ $2 -gt $max_line ]; then echo "Warning: <line_number>
($2) is greater than the number of lines in the file ($max_line)" echo
"Warning: Setting <line_number> to $max_line" local line_number=$(jq
-n "$max_line") # Set line number to max if greater than max elif
[ $2 -lt 1 ]; then echo "Warning: <line_number> ($2) is less than
1" echo "Warning: Setting <line_number> to 1" local
line_number=$(jq -n "1") # Set line number to 1 if less than 1 else local
OFFSET=$(jq -n "$WINDOW/6" | jq ''floor'') local line_number=$(jq
-n "[$2 + $WINDOW/2 - $OFFSET, 1] | max | floor") fi else local
line_number=$(jq -n "$WINDOW/2") # Set default line number if not provided fi if
[ -f "$1" ]; then export CURRENT_FILE=$(realpath $1) export
CURRENT_LINE=$line_number _constrain_line _print elif [ -d
"$1" ]; then echo "Error: $1 is a directory. You can only open files.
Use cd or ls to navigate directories." else echo "File $1 not found" fi}'
docstring: opens the file at the given path in the editor. If line_number is
provided, the window will be move to include that line
end_name: null
name: open
signature: open <path> [<line_number>]
- arguments:
line_number:
description: the line number to move the window to
required: true
type: integer
code: 'goto() { if [ $# -gt 1 ]; then echo "goto allows only one line
number at a time." return fi if [ -z "$CURRENT_FILE" ] then echo
"No file open. Use the open command first." return fi if [ -z
"$1" ] then echo "Usage: goto <line>" return fi if
! [[ $1 =~ ^[0-9]+$ ]] then echo "Usage: goto <line>" echo
"Error: <line> must be a number" return fi local max_line=$(awk
''END {print NR}'' $CURRENT_FILE) if [ $1 -gt $max_line ] then echo
"Error: <line> must be less than or equal to $max_line" return fi local
OFFSET=$(jq -n "$WINDOW/6" | jq ''floor'') export CURRENT_LINE=$(jq -n
"[$1 + $WINDOW/2 - $OFFSET, 1] | max | floor") _constrain_line _print}'
docstring: moves the window to show <line_number>
end_name: null
name: goto
signature: goto <line_number>
- arguments: null
code: scroll_down() { if [ -z "$CURRENT_FILE" ] then echo "No file
open. Use the open command first." return fi export CURRENT_LINE=$(jq
-n "$CURRENT_LINE + $WINDOW - $OVERLAP") _constrain_line _print}
docstring: moves the window down {WINDOW} lines
end_name: null
name: scroll_down
signature: scroll_down
- arguments: null
code: scroll_up() { if [ -z "$CURRENT_FILE" ] then echo "No file
open. Use the open command first." return fi export CURRENT_LINE=$(jq
-n "$CURRENT_LINE - $WINDOW + $OVERLAP") _constrain_line _print}
docstring: moves the window down {WINDOW} lines
end_name: null
name: scroll_up
signature: scroll_down
- arguments:
filename:
description: the name of the file to create
required: true
type: string
code: "create() { if [ -z \"$1\" ]; then echo \"Usage: create <filename>\"\
\ return fi # Check if the file already exists if [ -e \"\
$1\" ]; then echo \"Error: File '$1' already exists.\"\t\topen \"$1\"\
\ return fi # Create the file an empty new line printf \"\\\
n\" > \"$1\" # Use the existing open command to open the created file \
\ open \"$1\"}"
docstring: creates and opens a new file with the given name
end_name: null
name: create
signature: create <filename>
- arguments: null
code: 'submit() { cd $ROOT # Check if the patch file exists and is non-empty if
[ -s "/root/test.patch" ]; then # Apply the patch in reverse git
apply -R < "/root/test.patch" fi git add -A git diff --cached > model.patch echo
"<<SUBMISSION||" cat model.patch echo "||SUBMISSION>>"}'
docstring: submits your current code and terminates the session
end_name: null
name: submit
signature: submit
- arguments:
dir:
description: the directory to search in (if not provided, searches in the
current directory)
required: false
type: string
search_term:
description: the term to search for
required: true
type: string
code: 'search_dir() { if [ $# -eq 1 ]; then local search_term="$1" local
dir="./" elif [ $# -eq 2 ]; then local search_term="$1" if
[ -d "$2" ]; then local dir="$2" else echo "Directory
$2 not found" return fi else echo "Usage: search_dir
<search_term> [<dir>]" return fi dir=$(realpath "$dir") local
matches=$(find "$dir" -type f ! -path ''*/.*'' -exec grep -nIH -- "$search_term"
{} + | cut -d: -f1 | sort | uniq -c) # if no matches, return if [ -z
"$matches" ]; then echo "No matches found for \"$search_term\" in $dir" return fi #
Calculate total number of matches local num_matches=$(echo "$matches" |
awk ''{sum+=$1} END {print sum}'') # calculate total number of files matched local
num_files=$(echo "$matches" | wc -l | awk ''{$1=$1; print $0}'') # if num_files
is > 100, print an error if [ $num_files -gt 100 ]; then echo "More
than $num_files files matched for \"$search_term\" in $dir. Please narrow
your search." return fi echo "Found $num_matches matches
for \"$search_term\" in $dir:" echo "$matches" | awk ''{$2=$2; gsub(/^\.+\/+/,
"./", $2); print $2 " ("$1" matches)"}'' echo "End of matches for \"$search_term\"
in $dir"}'
docstring: searches for search_term in all files in dir. If dir is not provided,
searches in the current directory
end_name: null
name: search_dir
signature: search_dir <search_term> [<dir>]
- arguments:
file:
description: the file to search in (if not provided, searches in the current
open file)
required: false
type: string
search_term:
description: the term to search for
required: true
type: string
code: 'search_file() { # Check if the first argument is provided if [
-z "$1" ]; then echo "Usage: search_file <search_term> [<file>]" return fi #
Check if the second argument is provided if [ -n "$2" ]; then #
Check if the provided argument is a valid file if [ -f "$2" ]; then local
file="$2" # Set file if valid else echo "Usage: search_file
<search_term> [<file>]" echo "Error: File name $2 not found. Please
provide a valid file name." return # Exit if the file is not valid fi else
#
Check if a file is open if [ -z "$CURRENT_FILE" ]; then echo
"No file open. Use the open command first." return # Exit if no
file is open fi local file="$CURRENT_FILE" # Set file to the
current open file fi local search_term="$1" file=$(realpath "$file") #
Use grep to directly get the desired formatted output local matches=$(grep
-nH -- "$search_term" "$file") # Check if no matches were found if [
-z "$matches" ]; then echo "No matches found for \"$search_term\" in
$file" return fi # Calculate total number of matches local
num_matches=$(echo "$matches" | wc -l | awk ''{$1=$1; print $0}'') #
calculate total number of lines matched local num_lines=$(echo "$matches"
| cut -d: -f1 | sort | uniq | wc -l | awk ''{$1=$1; print $0}'') # if num_lines
is > 100, print an error if [ $num_lines -gt 100 ]; then echo "More
than $num_lines lines matched for \"$search_term\" in $file. Please narrow
your search." return fi # Print the total number of matches and
the matches themselves echo "Found $num_matches matches for \"$search_term\"
in $file:" echo "$matches" | cut -d: -f1-2 | sort -u -t: -k2,2n | while
IFS=: read -r filename line_number; do echo "Line $line_number:$(sed
-n "${line_number}p" "$file")" done echo "End of matches for \"$search_term\"
in $file"}'
docstring: searches for search_term in file. If file is not provided, searches
in the current open file
end_name: null
name: search_file
signature: search_file <search_term> [<file>]
- arguments:
dir:
description: the directory to search in (if not provided, searches in the
current directory)
required: false
type: string
file_name:
description: the name of the file to search for
required: true
type: string
code: 'find_file() { if [ $# -eq 1 ]; then local file_name="$1" local
dir="./" elif [ $# -eq 2 ]; then local file_name="$1" if
[ -d "$2" ]; then local dir="$2" else echo "Directory
$2 not found" return fi else echo "Usage: find_file
<file_name> [<dir>]" return fi dir=$(realpath "$dir") local
matches=$(find "$dir" -type f -name "$file_name") # if no matches, return if
[ -z "$matches" ]; then echo "No matches found for \"$file_name\" in
$dir" return fi # Calculate total number of matches local
num_matches=$(echo "$matches" | wc -l | awk ''{$1=$1; print $0}'') echo
"Found $num_matches matches for \"$file_name\" in $dir:" echo "$matches"
| awk ''{print $0}''}'
docstring: finds all files with the given name in dir. If dir is not provided,
searches in the current directory
end_name: null
name: find_file
signature: find_file <file_name> [<dir>]
- arguments:
end_line:
description: the line number to end the edit at (inclusive)
required: true
type: integer
replacement_text:
description: the text to replace the current selection with
required: true
type: string
start_line:
description: the line number to start the edit at
required: true
type: integer
code: 'edit() { if [ -z "$CURRENT_FILE" ] then echo ''No file open.
Use the `open` command first.'' return fi local start_line="$(echo
$1: | cut -d: -f1)" local end_line="$(echo $1: | cut -d: -f2)" if [
-z "$start_line" ] || [ -z "$end_line" ] then echo "Usage: edit
<start_line>:<end_line>" return fi local re=''^[0-9]+$'' if
! [[ $start_line =~ $re ]]; then echo "Usage: edit <start_line>:<end_line>" echo
"Error: start_line must be a number" return fi if ! [[ $end_line
=~ $re ]]; then echo "Usage: edit <start_line>:<end_line>" echo
"Error: end_line must be a number" return fi # Bash array starts
at 0, so let''s adjust local start_line=$((start_line - 1)) local end_line=$((end_line)) local
line_count=0 local replacement=() while IFS= read -r line do replacement+=("$line")
((line_count++)) done #
Create a backup of the current file cp "$CURRENT_FILE" "/root/$(basename
"$CURRENT_FILE")_backup" # Read the file line by line into an array mapfile
-t lines < "$CURRENT_FILE" local new_lines=("${lines[@]:0:$start_line}"
"${replacement[@]}" "${lines[@]:$((end_line))}") # Write the new stuff
directly back into the original file printf "%s\n" "${new_lines[@]}" >|
"$CURRENT_FILE" # Run linter if [[ $CURRENT_FILE == *.py ]]; then lint_output=$(flake8
--select=F821,F822,F831,E111,E112,E113,E999,E902 "$CURRENT_FILE" 2>&1) else #
do nothing lint_output="" fi # if there is no output, then the
file is good if [ -z "$lint_output" ]; then export CURRENT_LINE=$start_line
_constrain_line _print echo
"File updated. Please review the changes and make sure they are correct (correct
indentation, no duplicate lines, etc). Edit the file again if necessary." else echo
"Your proposed edit has introduced new syntax error(s). Please understand
the fixes and retry your edit commmand." echo "" echo "ERRORS:" _split_string
"$lint_output" echo "" # Save original values original_current_line=$CURRENT_LINE
original_window=$WINDOW #
Update values export CURRENT_LINE=$(( (line_count / 2) + start_line
)) # Set to "center" of edit export WINDOW=$((line_count + 10)) # Show
+/- 5 lines around edit echo "This is how your edit would have looked
if applied" echo "-------------------------------------------------" _constrain_line
_print echo
"-------------------------------------------------" echo "" #
Restoring CURRENT_FILE to original contents. cp "/root/$(basename "$CURRENT_FILE")_backup"
"$CURRENT_FILE" export CURRENT_LINE=$(( ((end_line - start_line + 1)
/ 2) + start_line )) export WINDOW=$((end_line - start_line + 10)) echo
"This is the original code before your edit" echo
"-------------------------------------------------" _constrain_line _print echo
"-------------------------------------------------" # Restore original
values export CURRENT_LINE=$original_current_line export WINDOW=$original_window
echo
"Your changes have NOT been applied. Please fix your edit command and try
again." echo "You either need to 1) Specify the correct start/end line
arguments or 2) Correct your edit code." echo "DO NOT re-run the same
failed edit command. Running it again will lead to the same error." fi #
Remove backup file rm -f "/root/$(basename "$CURRENT_FILE")_backup"}'
docstring: replaces lines <start_line> through <end_line> (inclusive) with the
given text in the open file. The replacement text is terminated by a line
with only end_of_edit on it. All of the <replacement text> will be entered,
so make sure your indentation is formatted properly. Python files will be
checked for syntax errors after the edit. If the system detects a syntax error,
the edit will not be executed. Simply try to edit the file again, but make
sure to read the error message and modify the edit command you issue accordingly.
Issuing the same command a second time will just lead to the same error message
again.
end_name: end_of_edit
name: edit
signature: |-
edit <start_line>:<end_line>
<replacement_text>
end_of_edit
_subroutines: {}
blocklist:
- vim
- vi
- emacs
- nano
- nohup
- git
blocklist_error_template: Interactive operation '{name}' is not supported by this
environment
blocklist_standalone:
- python
- python3
- ipython
- bash
- sh
- exit
- /bin/bash
- /bin/sh
- nohup
- vi
- vim
- emacs
- nano
command_docs: |+
open:
docstring: opens the file at the given path in the editor. If line_number is provided, the window will
be move to include that line
signature: open <path> [<line_number>]
arguments:
- path (string) [required]: the path to the file to open
- line_number (integer) [optional]: the line number to move the window to (if not provided, the
window will start at the top of the file)
goto:
docstring: moves the window to show <line_number>
signature: goto <line_number>
arguments:
- line_number (integer) [required]: the line number to move the window to
scroll_down:
docstring: moves the window down {WINDOW} lines
signature: scroll_down
scroll_up:
docstring: moves the window down {WINDOW} lines
signature: scroll_down
create:
docstring: creates and opens a new file with the given name
signature: create <filename>
arguments:
- filename (string) [required]: the name of the file to create
submit:
docstring: submits your current code and terminates the session
signature: submit
search_dir:
docstring: searches for search_term in all files in dir. If dir is not provided, searches in the
current directory
signature: search_dir <search_term> [<dir>]
arguments:
- search_term (string) [required]: the term to search for
- dir (string) [optional]: the directory to search in (if not provided, searches in the current
directory)
search_file:
docstring: searches for search_term in file. If file is not provided, searches in the current open file
signature: search_file <search_term> [<file>]
arguments:
- search_term (string) [required]: the term to search for
- file (string) [optional]: the file to search in (if not provided, searches in the current open
file)
find_file:
docstring: finds all files with the given name in dir. If dir is not provided, searches in the current
directory
signature: find_file <file_name> [<dir>]
arguments:
- file_name (string) [required]: the name of the file to search for
- dir (string) [optional]: the directory to search in (if not provided, searches in the current
directory)
edit:
docstring: replaces lines <start_line> through <end_line> (inclusive) with the given text in the open
file. The replacement text is terminated by a line with only end_of_edit on it. All of the <replacement text>
will be entered, so make sure your indentation is formatted properly. Python files will be checked for syntax
errors after the edit. If the system detects a syntax error, the edit will not be executed. Simply try to edit
the file again, but make sure to read the error message and modify the edit command you issue accordingly.
Issuing the same command a second time will just lead to the same error message again.
signature: edit <start_line>:<end_line>
<replacement_text>
end_of_edit
arguments:
- start_line (integer) [required]: the line number to start the edit at
- end_line (integer) [required]: the line number to end the edit at (inclusive)
- replacement_text (string) [required]: the text to replace the current selection with
command_files:
- config/commands/defaults.sh
- config/commands/search.sh
- config/commands/edit_linting.sh
- config/commands/_split_string.py
demonstration_template: |
Here is a demonstration of how to correctly accomplish this task.
It is included to show you how to correctly use the interface.
You do not need to follow exactly what is done in the demonstration.
--- DEMONSTRATION ---
{demonstration}
--- END OF DEMONSTRATION ---
demonstrations:
-
trajectories/demonstrations/replay__marshmallow-code__marshmallow-1867__default__t-0.20__p-0.95__c-2.00__instal
l-1___install_from_source/marshmallow-code__marshmallow-1867.traj
env_variables:
CURRENT_FILE: ''
CURRENT_LINE: '0'
OVERLAP: '2'
SEARCH_FILES: ()
SEARCH_INDEX: '0'
SEARCH_RESULTS: ()
WINDOW: '100'
format_error_template: |
Your output was not formatted correctly. You must always include one discussion and one command as part
of your response. Make sure you do not have multiple discussion/command tags.
Please make sure your output precisely matches the following format:
DISCUSSION
Discuss here with yourself about what your planning and what you're going to do in this step.
command(s) that you're going to run
```
history_processor: {}
history_processor_args: {}
instance_template: "We're currently solving the following issue within our repository.\
\ Here's the issue text:\nISSUE:\n{issue}\n\nINSTRUCTIONS:\nNow, you're going\
\ to solve this issue on your own. Your terminal session has started and you're\
\ in the repository's root directory. You can use any bash commands or the special\
\ interface to help you. Edit all the files you need to and run any checks or\
\ tests that you want. \nRemember, YOU CAN ONLY ENTER ONE COMMAND AT A TIME.\
\ You should always wait for feedback after every command. \nWhen you're satisfied\
\ with all of the changes you've made, you can submit your changes to the code\
\ base by simply running the submit command.\nNote however that you cannot use\
\ any interactive session commands (e.g. python, vim) in this environment, but\
\ you can write scripts and run them. E.g. you can write a python script and\
\ then run it with `python <script_name>.py`.\n\nNOTE ABOUT THE EDIT COMMAND:\
\ Indentation really matters! When editing a file, make sure to insert appropriate\
\ indentation before each line! \n\nIMPORTANT TIPS:\n1. Always start by trying\
\ to replicate the bug that the issues discusses. \n If the issue includes\
\ code for reproducing the bug, we recommend that you re-implement that in your\
\ environment, and run it to make sure you can reproduce the bug.\n Then start\
\ trying to fix it.\n When you think you've fixed the bug, re-run the bug\
\ reproduction script to make sure that the bug has indeed been fixed.\n \n\
\ If the bug reproduction script does not print anything when it succesfully\
\ runs, we recommend adding a print(\"Script completed successfully, no errors.\"\
) command at the end of the file,\n so that you can be sure that the script\
\ indeed ran fine all the way through. \n\n2. If you run a command and it doesn't\
\ work, try running a different command. A command that did not work once will\
\ not work the second time unless you modify it!\n\n3. If you open a file and\
\ need to get to an area around a specific line that is not in the first 100\
\ lines, say line 583, don't just use the scroll_down command multiple times.\
\ Instead, use the goto 583 command. It's much quicker. \n \n4. If the bug\
\ reproduction script requires inputting/reading a specific file, such as buggy-input.png,\
\ and you'd like to understand how to input that file, conduct a search in the\
\ existing repo code, to see whether someone else has already done that. Do\
\ this by running the command: find_file \"buggy-input.png\" If that doensn't\
\ work, use the linux 'find' command. \n\n5. Always make sure to look at the\
\ currently open file and the current working directory (which appears right\
\ after the currently open file). The currently open file might be in a different\
\ directory than the working directory! Note that some commands, such as 'create',\
\ open files, so they might change the current open file.\n\n6. When editing\
\ files, it is easy to accidentally specify a wrong line number or to write\
\ code with incorrect indentation. Always check the code after you issue an\
\ edit to make sure that it reflects what you wanted to accomplish. If it didn't,\
\ issue another command to fix it.\n\n7. It may be necessary to install the\
\ repository from source before you can run code. Please think about how to\
\ install the environment from the repository directory if you need to do so.\n\
\ \n\n(Open file: {open_file})\n(Current directory: {working_dir})\nbash-$"
next_step_no_output_template: |-
Your command ran successfully and did not produce any output.
(Open file: {open_file})
(Current directory: {working_dir})
bash-$
next_step_template: |-
{observation}
(Open file: {open_file})
(Current directory: {working_dir})
bash-$
parse_command: {}
parse_function: {}
put_demos_in_history: false
state_command:
arguments: null
code: |
state() {
local working_dir="$PWD";
if [ -z $CURRENT_FILE ]; then
echo '{"open_file": "n/a", "working_dir": "'$working_dir'"}';
else
echo '{"open_file": "'$(realpath $CURRENT_FILE)'", "working_dir": "'$working_dir'"}';
fi
};
docstring: null
end_name: null
name: state
signature: null
strategy_template: null
submit_command: submit
subroutine_types: []
system_template: "SETTING: You are an autonomous programmer, and you're working\
\ directly in the command line with a special interface.\n\nThe special interface\
\ consists of a file editor that shows you {WINDOW} lines of a file at a time.\n\
In addition to typical bash commands, you can also use the following commands\
\ to help you navigate and edit files.\n\nCOMMANDS:\n{command_docs}\n\nPlease\
\ note that THE EDIT COMMAND REQUIRES PROPER INDENTATION. \nIf you'd like to\
\ add the line ' print(x)' you must fully write that out, with all those\
\ spaces before the code! Indentation is important and code that is not indented\
\ correctly will fail and require fixing before it can be run.\n\nRESPONSE FORMAT:\n\
Your shell prompt is formatted as follows:\n(Open file: <path>) <cwd> $\n\n\
You need to format your output using two fields; discussion and command.\nYour\
\ output should always include _one_ discussion and _one_ command field EXACTLY\
\ as in the following example:\nDISCUSSION\nFirst I'll start by using ls to\
\ see what files are in the current directory. Then maybe we can look at some\
\ relevant files to see what they look like.\n```\nls -a\n```\n\nYou should\
\ only include a *SINGLE* command in the command section and then wait for a\
\ response from the shell before continuing with more discussion and commands.\
\ Everything you include in the DISCUSSION section will be saved for future\
\ reference.\nIf you'd like to issue two commands at once, PLEASE DO NOT DO\
\ THAT! Please instead first submit just the first command, and then after receiving\
\ a response you'll be able to issue the second command. \nYou're free to use\
\ any other bash commands you want (e.g. find, grep, cat, ls, cd) in addition\
\ to the special commands listed above.\nHowever, the environment does NOT support\
\ interactive session commands (e.g. python, vim), so please do not invoke them."
util_functions:
- arguments: null
code: '_print() { local total_lines=$(awk ''END {print NR}'' $CURRENT_FILE) echo
"[File: $(realpath $CURRENT_FILE) ($total_lines lines total)]" lines_above=$(jq
-n "$CURRENT_LINE - $WINDOW/2" | jq ''[0, .] | max | floor'') lines_below=$(jq
-n "$total_lines - $CURRENT_LINE - $WINDOW/2" | jq ''[0, .] | max | round'') if
[ $lines_above -gt 0 ]; then echo "($lines_above more lines above)" fi cat
$CURRENT_FILE | grep -n $ | head -n $(jq -n "[$CURRENT_LINE + $WINDOW/2, $WINDOW/2]
| max | floor") | tail -n $(jq -n "$WINDOW") if [ $lines_below -gt 0 ];
then echo "($lines_below more lines below)" fi}'
docstring: null
end_name: null
name: _print
signature: _print
- arguments: null
code: _constrain_line() { if [ -z "$CURRENT_FILE" ] then echo "No
file open. Use the open command first." return fi local max_line=$(awk
'END {print NR}' $CURRENT_FILE) local half_window=$(jq -n "$WINDOW/2" |
jq 'floor') export CURRENT_LINE=$(jq -n "[$CURRENT_LINE, $max_line - $half_window]
| min") export CURRENT_LINE=$(jq -n "[$CURRENT_LINE, $half_window] | max")}
docstring: null
end_name: null
name: _constrain_line
signature: _constrain_line
config_file: config/default_from_url.yaml
model:
host_url: localhost:11434
model_name: gpt4
per_instance_cost_limit: 3.0
replay_path: null
temperature: 0.0
top_p: 0.95
total_cost_limit: 0.0
environment:
base_commit: null
container_name: null
data_path: https://github.com/OpenDevin/OpenDevin/issues/381
image_name: sweagent/swe-agent:latest
install_environment: true
no_mirror: false
split: dev
timeout: 35
verbose: true
instance_filter: .*
raise_exceptions: false
skip_existing: false
suffix: ''INFO 💽 Loaded dataset from https://github.com/OpenDevin/OpenDevin/issues/381 DEBUG Starting container with command: docker run -i --rm --name sweagent-swe-agent-latest-269e338ecd sweagent/swe-agent:latest /bin/bash -l -m INFO 🌱 Environment Initialized INFO ▶️ Beginning task 0
INFO Trying to clone from non-mirror... WARNING install_environment is set to True, but the data path is a GitHub URL. Skipping conda environment installation. INFO Initializing agent settings for container e154a1ba6b6a16758b96ff5b0cdca1475b5e4bad2f36a6d919a83147eab1a206 2024-04-09 19:36:15,708 - api_models - INFO - Resetting model stats INFO SYSTEM (primary) SETTING: You are an autonomous programmer, and you're working directly in the command line with a special interface.
The special interface consists of a file editor that shows you 100 lines of a file at a time.
In addition to typical bash commands, you can also use the following commands to help you navigate and edit
files.
COMMANDS:
open:
docstring: opens the file at the given path in the editor. If line_number is provided, the window will be
move to include that line
signature: open <path> [<line_number>]
arguments:
- path (string) [required]: the path to the file to open
- line_number (integer) [optional]: the line number to move the window to (if not provided, the window will
start at the top of the file)
goto:
docstring: moves the window to show <line_number>
signature: goto <line_number>
arguments:
- line_number (integer) [required]: the line number to move the window to
scroll_down:
docstring: moves the window down {WINDOW} lines
signature: scroll_down
scroll_up:
docstring: moves the window down {WINDOW} lines
signature: scroll_down
create:
docstring: creates and opens a new file with the given name
signature: create <filename>
arguments:
- filename (string) [required]: the name of the file to create
submit:
docstring: submits your current code and terminates the session
signature: submit
search_dir:
docstring: searches for search_term in all files in dir. If dir is not provided, searches in the current
directory
signature: search_dir <search_term> [<dir>]
arguments:
- search_term (string) [required]: the term to search for
- dir (string) [optional]: the directory to search in (if not provided, searches in the current directory)
search_file:
docstring: searches for search_term in file. If file is not provided, searches in the current open file
signature: search_file <search_term> [<file>]
arguments:
- search_term (string) [required]: the term to search for
- file (string) [optional]: the file to search in (if not provided, searches in the current open file)
find_file:
docstring: finds all files with the given name in dir. If dir is not provided, searches in the current
directory
signature: find_file <file_name> [<dir>]
arguments:
- file_name (string) [required]: the name of the file to search for
- dir (string) [optional]: the directory to search in (if not provided, searches in the current directory)
edit:
docstring: replaces lines <start_line> through <end_line> (inclusive) with the given text in the open file.
The replacement text is terminated by a line with only end_of_edit on it. All of the <replacement text> will be
entered, so make sure your indentation is formatted properly. Python files will be checked for syntax errors
after the edit. If the system detects a syntax error, the edit will not be executed. Simply try to edit the
file again, but make sure to read the error message and modify the edit command you issue accordingly. Issuing
the same command a second time will just lead to the same error message again.
signature: edit <start_line>:<end_line>
<replacement_text>
end_of_edit
arguments:
- start_line (integer) [required]: the line number to start the edit at
- end_line (integer) [required]: the line number to end the edit at (inclusive)
- replacement_text (string) [required]: the text to replace the current selection with
Please note that THE EDIT COMMAND REQUIRES PROPER INDENTATION.
If you'd like to add the line ' print(x)' you must fully write that out, with all those spaces before
the code! Indentation is important and code that is not indented correctly will fail and require fixing before
it can be run.
RESPONSE FORMAT:
Your shell prompt is formatted as follows:
(Open file: <path>) <cwd> $
You need to format your output using two fields; discussion and command.
Your output should always include _one_ discussion and _one_ command field EXACTLY as in the following example:
DISCUSSION
First I'll start by using ls to see what files are in the current directory. Then maybe we can look at some
relevant files to see what they look like.
```
ls -a
```
You should only include a *SINGLE* command in the command section and then wait for a response from the shell
before continuing with more discussion and commands. Everything you include in the DISCUSSION section will be
saved for future reference.
If you'd like to issue two commands at once, PLEASE DO NOT DO THAT! Please instead first submit just the first
command, and then after receiving a response you'll be able to issue the second command.
You're free to use any other bash commands you want (e.g. find, grep, cat, ls, cd) in addition to the special
commands listed above.
However, the environment does NOT support interactive session commands (e.g. python, vim), so please do not
invoke them.INFO DEMONSTRATION: trajectories/demonstrations/replaymarshmallow-codemarshmallow-1867defaultt-0.20p-0.95c-2.00__instal l-1_install_from_source/marshmallow-codemarshmallow-1867.traj INFO 🤖 MODEL INPUT We're currently solving the following issue within our repository. Here's the issue text: ISSUE: Disable terminal input until its implemented Describe the bug
I started up OpenDevin, then attempted to write a command to the terminal, but server crashed because it hit a
code path that is not implemented. I was thinking of changing the not implemented error to `await
self.send_error()`, but then started to wonder why we even allow users to type commands from the UI in cases
where we're not prepared to handle them.
**Steps to Reproduce**
1. Start OpenDevin
2. Attempt to write to the terminal prompt
3.
**Actual behavior**
```
ERROR: Exception in ASGI application
Traceback (most recent call last):
File
"/Users/penberg/.local/share/virtualenvs/OpenDevin-q_F4dVcV/lib/python3.10/site-packages/uvicorn/protocols/webs
ockets/websockets_impl.py", line 240, in run_asgi
result = await self.app(self.scope, self.asgi_receive, self.asgi_send)
File
"/Users/penberg/.local/share/virtualenvs/OpenDevin-q_F4dVcV/lib/python3.10/site-packages/uvicorn/middleware/pro
xy_headers.py", line 69, in __call__
return await self.app(scope, receive, send)
File
"/Users/penberg/.local/share/virtualenvs/OpenDevin-q_F4dVcV/lib/python3.10/site-packages/fastapi/applications.p
y", line 1054, in __call__
await super().__call__(scope, receive, send)
File
"/Users/penberg/.local/share/virtualenvs/OpenDevin-q_F4dVcV/lib/python3.10/site-packages/starlette/applications
.py", line 123, in __call__
await self.middleware_stack(scope, receive, send)
File
"/Users/penberg/.local/share/virtualenvs/OpenDevin-q_F4dVcV/lib/python3.10/site-packages/starlette/middleware/e
rrors.py", line 151, in __call__
await self.app(scope, receive, send)
File
"/Users/penberg/.local/share/virtualenvs/OpenDevin-q_F4dVcV/lib/python3.10/site-packages/starlette/middleware/c
ors.py", line 75, in __call__
await self.app(scope, receive, send)
File
"/Users/penberg/.local/share/virtualenvs/OpenDevin-q_F4dVcV/lib/python3.10/site-packages/starlette/middleware/e
xceptions.py", line 62, in __call__
await wrap_app_handling_exceptions(self.app, conn)(scope, receive, send)
File
"/Users/penberg/.local/share/virtualenvs/OpenDevin-q_F4dVcV/lib/python3.10/site-packages/starlette/_exception_h
andler.py", line 64, in wrapped_app
raise exc
File
"/Users/penberg/.local/share/virtualenvs/OpenDevin-q_F4dVcV/lib/python3.10/site-packages/starlette/_exception_h
andler.py", line 53, in wrapped_app
await app(scope, receive, sender)
File
"/Users/penberg/.local/share/virtualenvs/OpenDevin-q_F4dVcV/lib/python3.10/site-packages/starlette/routing.py",
line 758, in __call__
await self.middleware_stack(scope, receive, send)
File
"/Users/penberg/.local/share/virtualenvs/OpenDevin-q_F4dVcV/lib/python3.10/site-packages/starlette/routing.py",
line 778, in app
await route.handle(scope, receive, send)
File
"/Users/penberg/.local/share/virtualenvs/OpenDevin-q_F4dVcV/lib/python3.10/site-packages/starlette/routing.py",
line 375, in handle
await self.app(scope, receive, send)
File
"/Users/penberg/.local/share/virtualenvs/OpenDevin-q_F4dVcV/lib/python3.10/site-packages/starlette/routing.py",
line 98, in app
await wrap_app_handling_exceptions(app, session)(scope, receive, send)
File
"/Users/penberg/.local/share/virtualenvs/OpenDevin-q_F4dVcV/lib/python3.10/site-packages/starlette/_exception_h
andler.py", line 64, in wrapped_app
raise exc
File
"/Users/penberg/.local/share/virtualenvs/OpenDevin-q_F4dVcV/lib/python3.10/site-packages/starlette/_exception_h
andler.py", line 53, in wrapped_app
await app(scope, receive, sender)
File
"/Users/penberg/.local/share/virtualenvs/OpenDevin-q_F4dVcV/lib/python3.10/site-packages/starlette/routing.py",
line 96, in app
await func(session)
File
"/Users/penberg/.local/share/virtualenvs/OpenDevin-q_F4dVcV/lib/python3.10/site-packages/fastapi/routing.py",
line 348, in app
await dependant.call(**values)
File "/Users/penberg/src/penberg/OpenDevin/opendevin/server/listen.py", line 23, in websocket_endpoint
await session.start_listening()
File "/Users/penberg/src/penberg/OpenDevin/opendevin/server/session.py", line 72, in start_listening
raise NotImplementedError
NotImplementedError
```
INSTRUCTIONS:
Now, you're going to solve this issue on your own. Your terminal session has started and you're in the
repository's root directory. You can use any bash commands or the special interface to help you. Edit all the
files you need to and run any checks or tests that you want.
Remember, YOU CAN ONLY ENTER ONE COMMAND AT A TIME. You should always wait for feedback after every command.
When you're satisfied with all of the changes you've made, you can submit your changes to the code base by
simply running the submit command.
Note however that you cannot use any interactive session commands (e.g. python, vim) in this environment, but
you can write scripts and run them. E.g. you can write a python script and then run it with `python
<script_name>.py`.
NOTE ABOUT THE EDIT COMMAND: Indentation really matters! When editing a file, make sure to insert appropriate
indentation before each line!
IMPORTANT TIPS:
1. Always start by trying to replicate the bug that the issues discusses.
If the issue includes code for reproducing the bug, we recommend that you re-implement that in your
environment, and run it to make sure you can reproduce the bug.
Then start trying to fix it.
When you think you've fixed the bug, re-run the bug reproduction script to make sure that the bug has indeed
been fixed.
If the bug reproduction script does not print anything when it succesfully runs, we recommend adding a
print("Script completed successfully, no errors.") command at the end of the file,
so that you can be sure that the script indeed ran fine all the way through.
2. If you run a command and it doesn't work, try running a different command. A command that did not work once
will not work the second time unless you modify it!
3. If you open a file and need to get to an area around a specific line that is not in the first 100 lines, say
line 583, don't just use the scroll_down command multiple times. Instead, use the goto 583 command. It's much
quicker.
4. If the bug reproduction script requires inputting/reading a specific file, such as buggy-input.png, and
you'd like to understand how to input that file, conduct a search in the existing repo code, to see whether
someone else has already done that. Do this by running the command: find_file "buggy-input.png" If that
doensn't work, use the linux 'find' command.
5. Always make sure to look at the currently open file and the current working directory (which appears right
after the currently open file). The currently open file might be in a different directory than the working
directory! Note that some commands, such as 'create', open files, so they might change the current open file.
6. When editing files, it is easy to accidentally specify a wrong line number or to write code with incorrect
indentation. Always check the code after you issue an edit to make sure that it reflects what you wanted to
accomplish. If it didn't, issue another command to fix it.
7. It may be necessary to install the repository from source before you can run code. Please think about how to
install the environment from the repository directory if you need to do so.
(Open file: n/a)
(Current directory: /OpenDevin__OpenDevin)
bash-$2024-04-09 19:36:26,057 - httpx - INFO - HTTP Request: POST https://api.openai.com/v1/chat/completions "HTTP/1.1 200 OK"
2024-04-09 19:36:26,102 - api_models - INFO - input_tokens=11_285, output_tokens=101, instance_cost=0.12, cost=0.12
2024-04-09 19:36:26,102 - api_models - INFO - total_tokens_sent=11_285, total_tokens_received=101, total_cost=0.12, total_api_calls=1
INFO 💭 THOUGHT (primary)
To address the issue described, we need to find the code responsible for handling terminal input and either
disable it or handle it appropriately until the feature is fully implemented. The traceback provided in the
issue text points to a file named session.py and a method start_listening where the NotImplementedError
is raised.
Let's start by searching for the `session.py` file within the current repository to locate the file that we
need to edit.INFO 🎬 ACTION (primary) find_file "session.py"
INFO Saved trajectory to trajectories/root/gpt4OpenDevinOpenDevindefault_from_urlt-0.00p-0.95c-3.00install-1/OpenDevinOp enDevin-i381.traj INFO 🤖 MODEL INPUT Found 1 matches for "session.py" in /OpenDevinOpenDevin: /OpenDevinOpenDevin/opendevin/server/session/session.py
(Open file: n/a)
(Current directory: /OpenDevin__OpenDevin)
bash-$2024-04-09 19:36:36,541 - httpx - INFO - HTTP Request: POST https://api.openai.com/v1/chat/completions "HTTP/1.1 200 OK"
2024-04-09 19:36:36,548 - api_models - INFO - input_tokens=11_449, output_tokens=60, instance_cost=0.23, cost=0.12
2024-04-09 19:36:36,549 - api_models - INFO - total_tokens_sent=22_734, total_tokens_received=161, total_cost=0.23, total_api_calls=2
INFO 💭 THOUGHT (primary)
We have found the session.py file in the opendevin/server/session/ directory. Let's open this file and take
a look at the contents, specifically around the start_listening method mentioned in the traceback.
INFO 🎬 ACTION (primary) open opendevin/server/session/session.py
---
RESTARTING PROCESS.INFO Beginning environment shutdown... INFO Agent container stopped DEBUG Starting container with command: docker run -i --rm --name sweagent-swe-agent-latest-269e338ecd sweagent/swe-agent:latest /bin/bash -l -m INFO 🌱 Environment Initialized INFO Saved trajectory to trajectories/root/gpt4OpenDevinOpenDevindefault_from_urlt-0.00p-0.95c-3.00install-1/OpenDevinOp enDevin-i381.traj INFO Saved predictions to trajectories/root/gpt4OpenDevinOpenDevindefault_from_urlt-0.00p-0.95c-3.00__install-1/all_preds.jso nl INFO No patch to save. INFO Not openening PR because submission was made.
It's still crashing
(base) pierre@Pierruno:/mnt/c/Users/pierr/swe-agent$ docker run --rm -it -v /var/run/docker.sock:/var/run/docker.sock \
-v $(pwd)/keys.cfg:/app/keys.cfg \
--platform=linux/arm64 \
sweagent/swe-agent-run:latest \
python run.py --image_name=sweagent/swe-agent:latest \
--model_name gpt4 \
--data_path https://github.com/princeton-nlp/SWE-agent/issues/40 \
--config_file config/default_from_url.yaml --skip_existing=False
--open_pr
Unable to find image 'sweagent/swe-agent-run:latest' locally
latest: Pulling from sweagent/swe-agent-run
6ee0baa58a3d: Pull complete
992a857ef575: Pull complete
3861a6536e4e: Pull complete
e5e6faea05ea: Pull complete
91c9495e7b5a: Pull complete
9da2a388277a: Pull complete
308655dc4d72: Pull complete
044e84ab5cad: Pull complete
074804ab3f7f: Pull complete
69049993d6ed: Pull complete
e453eec85b13: Pull complete
fdde25d633eb: Pull complete
Digest: sha256:fd1c0187e44727a7ddf04e006d3d3d8f897367921d23bc360578070df561e0ca
Status: Downloaded newer image for sweagent/swe-agent-run:latest
Parsing command file: config/commands/defaults.sh
Parsing command file: config/commands/search.sh
Parsing command file: config/commands/edit_linting.sh
Parsing command file: config/commands/_split_string.py
Parsing command file: config/commands/defaults.sh
Parsing command file: config/commands/search.sh
Parsing command file: config/commands/edit_linting.sh
Parsing command file: config/commands/_split_string.py
INFO 📙 Arguments: actions:
open_pr: false
push_gh_repo_url: ''
skip_if_commits_reference_issue: true
agent:
config:
_commands:
- arguments:
line_number:
description: the line number to move the window to (if not provided, the
window will start at the top of the file)
required: false
type: integer
path:
description: the path to the file to open
required: true
type: string
code: 'open() { if [ -z "$1" ] then echo "Usage: open <file>" return fi #
Check if the second argument is provided if [ -n "$2" ]; then #
Check if the provided argument is a valid number if ! [[ $2 =~ ^[0-9]+$
]]; then echo "Usage: open <file> [<line_number>]" echo
"Error: <line_number> must be a number" return # Exit if the line
number is not valid fi local max_line=$(awk ''END {print NR}''
$1) if [ $2 -gt $max_line ]; then echo "Warning: <line_number>
($2) is greater than the number of lines in the file ($max_line)" echo
"Warning: Setting <line_number> to $max_line" local line_number=$(jq
-n "$max_line") # Set line number to max if greater than max elif
[ $2 -lt 1 ]; then echo "Warning: <line_number> ($2) is less than
1" echo "Warning: Setting <line_number> to 1" local
line_number=$(jq -n "1") # Set line number to 1 if less than 1 else local
OFFSET=$(jq -n "$WINDOW/6" | jq ''floor'') local line_number=$(jq
-n "[$2 + $WINDOW/2 - $OFFSET, 1] | max | floor") fi else local
line_number=$(jq -n "$WINDOW/2") # Set default line number if not provided fi if
[ -f "$1" ]; then export CURRENT_FILE=$(realpath $1) export
CURRENT_LINE=$line_number _constrain_line _print elif [ -d
"$1" ]; then echo "Error: $1 is a directory. You can only open files.
Use cd or ls to navigate directories." else echo "File $1 not found" fi}'
docstring: opens the file at the given path in the editor. If line_number is
provided, the window will be move to include that line
end_name: null
name: open
signature: open <path> [<line_number>]
- arguments:
line_number:
description: the line number to move the window to
required: true
type: integer
code: 'goto() { if [ $# -gt 1 ]; then echo "goto allows only one line
number at a time." return fi if [ -z "$CURRENT_FILE" ] then echo
"No file open. Use the open command first." return fi if [ -z
"$1" ] then echo "Usage: goto <line>" return fi if
! [[ $1 =~ ^[0-9]+$ ]] then echo "Usage: goto <line>" echo
"Error: <line> must be a number" return fi local max_line=$(awk
''END {print NR}'' $CURRENT_FILE) if [ $1 -gt $max_line ] then echo
"Error: <line> must be less than or equal to $max_line" return fi local
OFFSET=$(jq -n "$WINDOW/6" | jq ''floor'') export CURRENT_LINE=$(jq -n
"[$1 + $WINDOW/2 - $OFFSET, 1] | max | floor") _constrain_line _print}'
docstring: moves the window to show <line_number>
end_name: null
name: goto
signature: goto <line_number>
- arguments: null
code: scroll_down() { if [ -z "$CURRENT_FILE" ] then echo "No file
open. Use the open command first." return fi export CURRENT_LINE=$(jq
-n "$CURRENT_LINE + $WINDOW - $OVERLAP") _constrain_line _print}
docstring: moves the window down {WINDOW} lines
end_name: null
name: scroll_down
signature: scroll_down
- arguments: null
code: scroll_up() { if [ -z "$CURRENT_FILE" ] then echo "No file
open. Use the open command first." return fi export CURRENT_LINE=$(jq
-n "$CURRENT_LINE - $WINDOW + $OVERLAP") _constrain_line _print}
docstring: moves the window down {WINDOW} lines
end_name: null
name: scroll_up
signature: scroll_down
- arguments:
filename:
description: the name of the file to create
required: true
type: string
code: "create() { if [ -z \"$1\" ]; then echo \"Usage: create <filename>\"\
\ return fi # Check if the file already exists if [ -e \"\
$1\" ]; then echo \"Error: File '$1' already exists.\"\t\topen \"$1\"\
\ return fi # Create the file an empty new line printf \"\\\
n\" > \"$1\" # Use the existing open command to open the created file \
\ open \"$1\"}"
docstring: creates and opens a new file with the given name
end_name: null
name: create
signature: create <filename>
- arguments: null
code: 'submit() { cd $ROOT # Check if the patch file exists and is non-empty if
[ -s "/root/test.patch" ]; then # Apply the patch in reverse git
apply -R < "/root/test.patch" fi git add -A git diff --cached > model.patch echo
"<<SUBMISSION||" cat model.patch echo "||SUBMISSION>>"}'
docstring: submits your current code and terminates the session
end_name: null
name: submit
signature: submit
- arguments:
dir:
description: the directory to search in (if not provided, searches in the
current directory)
required: false
type: string
search_term:
description: the term to search for
required: true
type: string
code: 'search_dir() { if [ $# -eq 1 ]; then local search_term="$1" local
dir="./" elif [ $# -eq 2 ]; then local search_term="$1" if
[ -d "$2" ]; then local dir="$2" else echo "Directory
$2 not found" return fi else echo "Usage: search_dir
<search_term> [<dir>]" return fi dir=$(realpath "$dir") local
matches=$(find "$dir" -type f ! -path ''*/.*'' -exec grep -nIH -- "$search_term"
{} + | cut -d: -f1 | sort | uniq -c) # if no matches, return if [ -z
"$matches" ]; then echo "No matches found for \"$search_term\" in $dir" return fi #
Calculate total number of matches local num_matches=$(echo "$matches" |
awk ''{sum+=$1} END {print sum}'') # calculate total number of files matched local
num_files=$(echo "$matches" | wc -l | awk ''{$1=$1; print $0}'') # if num_files
is > 100, print an error if [ $num_files -gt 100 ]; then echo "More
than $num_files files matched for \"$search_term\" in $dir. Please narrow
your search." return fi echo "Found $num_matches matches
for \"$search_term\" in $dir:" echo "$matches" | awk ''{$2=$2; gsub(/^\.+\/+/,
"./", $2); print $2 " ("$1" matches)"}'' echo "End of matches for \"$search_term\"
in $dir"}'
docstring: searches for search_term in all files in dir. If dir is not provided,
searches in the current directory
end_name: null
name: search_dir
signature: search_dir <search_term> [<dir>]
- arguments:
file:
description: the file to search in (if not provided, searches in the current
open file)
required: false
type: string
search_term:
description: the term to search for
required: true
type: string
code: 'search_file() { # Check if the first argument is provided if [
-z "$1" ]; then echo "Usage: search_file <search_term> [<file>]" return fi #
Check if the second argument is provided if [ -n "$2" ]; then #
Check if the provided argument is a valid file if [ -f "$2" ]; then local
file="$2" # Set file if valid else echo "Usage: search_file
<search_term> [<file>]" echo "Error: File name $2 not found. Please
provide a valid file name." return # Exit if the file is not valid fi else
#
Check if a file is open if [ -z "$CURRENT_FILE" ]; then echo
"No file open. Use the open command first." return # Exit if no
file is open fi local file="$CURRENT_FILE" # Set file to the
current open file fi local search_term="$1" file=$(realpath "$file") #
Use grep to directly get the desired formatted output local matches=$(grep
-nH -- "$search_term" "$file") # Check if no matches were found if [
-z "$matches" ]; then echo "No matches found for \"$search_term\" in
$file" return fi # Calculate total number of matches local
num_matches=$(echo "$matches" | wc -l | awk ''{$1=$1; print $0}'') #
calculate total number of lines matched local num_lines=$(echo "$matches"
| cut -d: -f1 | sort | uniq | wc -l | awk ''{$1=$1; print $0}'') # if num_lines
is > 100, print an error if [ $num_lines -gt 100 ]; then echo "More
than $num_lines lines matched for \"$search_term\" in $file. Please narrow
your search." return fi # Print the total number of matches and
the matches themselves echo "Found $num_matches matches for \"$search_term\"
in $file:" echo "$matches" | cut -d: -f1-2 | sort -u -t: -k2,2n | while
IFS=: read -r filename line_number; do echo "Line $line_number:$(sed
-n "${line_number}p" "$file")" done echo "End of matches for \"$search_term\"
in $file"}'
docstring: searches for search_term in file. If file is not provided, searches
in the current open file
end_name: null
name: search_file
signature: search_file <search_term> [<file>]
- arguments:
dir:
description: the directory to search in (if not provided, searches in the
current directory)
required: false
type: string
file_name:
description: the name of the file to search for
required: true
type: string
code: 'find_file() { if [ $# -eq 1 ]; then local file_name="$1" local
dir="./" elif [ $# -eq 2 ]; then local file_name="$1" if
[ -d "$2" ]; then local dir="$2" else echo "Directory
$2 not found" return fi else echo "Usage: find_file
<file_name> [<dir>]" return fi dir=$(realpath "$dir") local
matches=$(find "$dir" -type f -name "$file_name") # if no matches, return if
[ -z "$matches" ]; then echo "No matches found for \"$file_name\" in
$dir" return fi # Calculate total number of matches local
num_matches=$(echo "$matches" | wc -l | awk ''{$1=$1; print $0}'') echo
"Found $num_matches matches for \"$file_name\" in $dir:" echo "$matches"
| awk ''{print $0}''}'
docstring: finds all files with the given name in dir. If dir is not provided,
searches in the current directory
end_name: null
name: find_file
signature: find_file <file_name> [<dir>]
- arguments:
end_line:
description: the line number to end the edit at (inclusive)
required: true
type: integer
replacement_text:
description: the text to replace the current selection with
required: true
type: string
start_line:
description: the line number to start the edit at
required: true
type: integer
code: 'edit() { if [ -z "$CURRENT_FILE" ] then echo ''No file open.
Use the `open` command first.'' return fi local start_line="$(echo
$1: | cut -d: -f1)" local end_line="$(echo $1: | cut -d: -f2)" if [
-z "$start_line" ] || [ -z "$end_line" ] then echo "Usage: edit
<start_line>:<end_line>" return fi local re=''^[0-9]+$'' if
! [[ $start_line =~ $re ]]; then echo "Usage: edit <start_line>:<end_line>" echo
"Error: start_line must be a number" return fi if ! [[ $end_line
=~ $re ]]; then echo "Usage: edit <start_line>:<end_line>" echo
"Error: end_line must be a number" return fi # Bash array starts
at 0, so let''s adjust local start_line=$((start_line - 1)) local end_line=$((end_line)) local
line_count=0 local replacement=() while IFS= read -r line do replacement+=("$line")
((line_count++)) done #
Create a backup of the current file cp "$CURRENT_FILE" "/root/$(basename
"$CURRENT_FILE")_backup" # Read the file line by line into an array mapfile
-t lines < "$CURRENT_FILE" local new_lines=("${lines[@]:0:$start_line}"
"${replacement[@]}" "${lines[@]:$((end_line))}") # Write the new stuff
directly back into the original file printf "%s\n" "${new_lines[@]}" >|
"$CURRENT_FILE" # Run linter if [[ $CURRENT_FILE == *.py ]]; then lint_output=$(flake8
--select=F821,F822,F831,E111,E112,E113,E999,E902 "$CURRENT_FILE" 2>&1) else #
do nothing lint_output="" fi # if there is no output, then the
file is good if [ -z "$lint_output" ]; then export CURRENT_LINE=$start_line
_constrain_line _print echo
"File updated. Please review the changes and make sure they are correct (correct
indentation, no duplicate lines, etc). Edit the file again if necessary." else echo
"Your proposed edit has introduced new syntax error(s). Please understand
the fixes and retry your edit commmand." echo "" echo "ERRORS:" _split_string
"$lint_output" echo "" # Save original values original_current_line=$CURRENT_LINE
original_window=$WINDOW #
Update values export CURRENT_LINE=$(( (line_count / 2) + start_line
)) # Set to "center" of edit export WINDOW=$((line_count + 10)) # Show
+/- 5 lines around edit echo "This is how your edit would have looked
if applied" echo "-------------------------------------------------" _constrain_line
_print echo
"-------------------------------------------------" echo "" #
Restoring CURRENT_FILE to original contents. cp "/root/$(basename "$CURRENT_FILE")_backup"
"$CURRENT_FILE" export CURRENT_LINE=$(( ((end_line - start_line + 1)
/ 2) + start_line )) export WINDOW=$((end_line - start_line + 10)) echo
"This is the original code before your edit" echo
"-------------------------------------------------" _constrain_line _print echo
"-------------------------------------------------" # Restore original
values export CURRENT_LINE=$original_current_line export WINDOW=$original_window
echo
"Your changes have NOT been applied. Please fix your edit command and try
again." echo "You either need to 1) Specify the correct start/end line
arguments or 2) Correct your edit code." echo "DO NOT re-run the same
failed edit command. Running it again will lead to the same error." fi #
Remove backup file rm -f "/root/$(basename "$CURRENT_FILE")_backup"}'
docstring: replaces lines <start_line> through <end_line> (inclusive) with the
given text in the open file. The replacement text is terminated by a line
with only end_of_edit on it. All of the <replacement text> will be entered,
so make sure your indentation is formatted properly. Python files will be
checked for syntax errors after the edit. If the system detects a syntax error,
the edit will not be executed. Simply try to edit the file again, but make
sure to read the error message and modify the edit command you issue accordingly.
Issuing the same command a second time will just lead to the same error message
again.
end_name: end_of_edit
name: edit
signature: |-
edit <start_line>:<end_line>
<replacement_text>
end_of_edit
_subroutines: {}
blocklist:
- vim
- vi
- emacs
- nano
- nohup
- git
blocklist_error_template: Interactive operation '{name}' is not supported by this
environment
blocklist_standalone:
- python
- python3
- ipython
- bash
- sh
- exit
- /bin/bash
- /bin/sh
- nohup
- vi
- vim
- emacs
- nano
command_docs: |+
open:
docstring: opens the file at the given path in the editor. If line_number is provided, the window will
be move to include that line
signature: open <path> [<line_number>]
arguments:
- path (string) [required]: the path to the file to open
- line_number (integer) [optional]: the line number to move the window to (if not provided, the
window will start at the top of the file)
goto:
docstring: moves the window to show <line_number>
signature: goto <line_number>
arguments:
- line_number (integer) [required]: the line number to move the window to
scroll_down:
docstring: moves the window down {WINDOW} lines
signature: scroll_down
scroll_up:
docstring: moves the window down {WINDOW} lines
signature: scroll_down
create:
docstring: creates and opens a new file with the given name
signature: create <filename>
arguments:
- filename (string) [required]: the name of the file to create
submit:
docstring: submits your current code and terminates the session
signature: submit
search_dir:
docstring: searches for search_term in all files in dir. If dir is not provided, searches in the
current directory
signature: search_dir <search_term> [<dir>]
arguments:
- search_term (string) [required]: the term to search for
- dir (string) [optional]: the directory to search in (if not provided, searches in the current
directory)
search_file:
docstring: searches for search_term in file. If file is not provided, searches in the current open file
signature: search_file <search_term> [<file>]
arguments:
- search_term (string) [required]: the term to search for
- file (string) [optional]: the file to search in (if not provided, searches in the current open
file)
find_file:
docstring: finds all files with the given name in dir. If dir is not provided, searches in the current
directory
signature: find_file <file_name> [<dir>]
arguments:
- file_name (string) [required]: the name of the file to search for
- dir (string) [optional]: the directory to search in (if not provided, searches in the current
directory)
edit:
docstring: replaces lines <start_line> through <end_line> (inclusive) with the given text in the open
file. The replacement text is terminated by a line with only end_of_edit on it. All of the <replacement text>
will be entered, so make sure your indentation is formatted properly. Python files will be checked for syntax
errors after the edit. If the system detects a syntax error, the edit will not be executed. Simply try to edit
the file again, but make sure to read the error message and modify the edit command you issue accordingly.
Issuing the same command a second time will just lead to the same error message again.
signature: edit <start_line>:<end_line>
<replacement_text>
end_of_edit
arguments:
- start_line (integer) [required]: the line number to start the edit at
- end_line (integer) [required]: the line number to end the edit at (inclusive)
- replacement_text (string) [required]: the text to replace the current selection with
command_files:
- config/commands/defaults.sh
- config/commands/search.sh
- config/commands/edit_linting.sh
- config/commands/_split_string.py
demonstration_template: |
Here is a demonstration of how to correctly accomplish this task.
It is included to show you how to correctly use the interface.
You do not need to follow exactly what is done in the demonstration.
--- DEMONSTRATION ---
{demonstration}
--- END OF DEMONSTRATION ---
demonstrations:
-
trajectories/demonstrations/replay__marshmallow-code__marshmallow-1867__default__t-0.20__p-0.95__c-2.00__instal
l-1___install_from_source/marshmallow-code__marshmallow-1867.traj
env_variables:
CURRENT_FILE: ''
CURRENT_LINE: '0'
OVERLAP: '2'
SEARCH_FILES: ()
SEARCH_INDEX: '0'
SEARCH_RESULTS: ()
WINDOW: '100'
format_error_template: |
Your output was not formatted correctly. You must always include one discussion and one command as part
of your response. Make sure you do not have multiple discussion/command tags.
Please make sure your output precisely matches the following format:
DISCUSSION
Discuss here with yourself about what your planning and what you're going to do in this step.
command(s) that you're going to run
```
history_processor: {}
history_processor_args: {}
instance_template: "We're currently solving the following issue within our repository.\
\ Here's the issue text:\nISSUE:\n{issue}\n\nINSTRUCTIONS:\nNow, you're going\
\ to solve this issue on your own. Your terminal session has started and you're\
\ in the repository's root directory. You can use any bash commands or the special\
\ interface to help you. Edit all the files you need to and run any checks or\
\ tests that you want. \nRemember, YOU CAN ONLY ENTER ONE COMMAND AT A TIME.\
\ You should always wait for feedback after every command. \nWhen you're satisfied\
\ with all of the changes you've made, you can submit your changes to the code\
\ base by simply running the submit command.\nNote however that you cannot use\
\ any interactive session commands (e.g. python, vim) in this environment, but\
\ you can write scripts and run them. E.g. you can write a python script and\
\ then run it with `python <script_name>.py`.\n\nNOTE ABOUT THE EDIT COMMAND:\
\ Indentation really matters! When editing a file, make sure to insert appropriate\
\ indentation before each line! \n\nIMPORTANT TIPS:\n1. Always start by trying\
\ to replicate the bug that the issues discusses. \n If the issue includes\
\ code for reproducing the bug, we recommend that you re-implement that in your\
\ environment, and run it to make sure you can reproduce the bug.\n Then start\
\ trying to fix it.\n When you think you've fixed the bug, re-run the bug\
\ reproduction script to make sure that the bug has indeed been fixed.\n \n\
\ If the bug reproduction script does not print anything when it succesfully\
\ runs, we recommend adding a print(\"Script completed successfully, no errors.\"\
) command at the end of the file,\n so that you can be sure that the script\
\ indeed ran fine all the way through. \n\n2. If you run a command and it doesn't\
\ work, try running a different command. A command that did not work once will\
\ not work the second time unless you modify it!\n\n3. If you open a file and\
\ need to get to an area around a specific line that is not in the first 100\
\ lines, say line 583, don't just use the scroll_down command multiple times.\
\ Instead, use the goto 583 command. It's much quicker. \n \n4. If the bug\
\ reproduction script requires inputting/reading a specific file, such as buggy-input.png,\
\ and you'd like to understand how to input that file, conduct a search in the\
\ existing repo code, to see whether someone else has already done that. Do\
\ this by running the command: find_file \"buggy-input.png\" If that doensn't\
\ work, use the linux 'find' command. \n\n5. Always make sure to look at the\
\ currently open file and the current working directory (which appears right\
\ after the currently open file). The currently open file might be in a different\
\ directory than the working directory! Note that some commands, such as 'create',\
\ open files, so they might change the current open file.\n\n6. When editing\
\ files, it is easy to accidentally specify a wrong line number or to write\
\ code with incorrect indentation. Always check the code after you issue an\
\ edit to make sure that it reflects what you wanted to accomplish. If it didn't,\
\ issue another command to fix it.\n\n7. It may be necessary to install the\
\ repository from source before you can run code. Please think about how to\
\ install the environment from the repository directory if you need to do so.\n\
\ \n\n(Open file: {open_file})\n(Current directory: {working_dir})\nbash-$"
next_step_no_output_template: |-
Your command ran successfully and did not produce any output.
(Open file: {open_file})
(Current directory: {working_dir})
bash-$
next_step_template: |-
{observation}
(Open file: {open_file})
(Current directory: {working_dir})
bash-$
parse_command: {}
parse_function: {}
put_demos_in_history: false
state_command:
arguments: null
code: |
state() {
local working_dir="$PWD";
if [ -z $CURRENT_FILE ]; then
echo '{"open_file": "n/a", "working_dir": "'$working_dir'"}';
else
echo '{"open_file": "'$(realpath $CURRENT_FILE)'", "working_dir": "'$working_dir'"}';
fi
};
docstring: null
end_name: null
name: state
signature: null
strategy_template: null
submit_command: submit
subroutine_types: []
system_template: "SETTING: You are an autonomous programmer, and you're working\
\ directly in the command line with a special interface.\n\nThe special interface\
\ consists of a file editor that shows you {WINDOW} lines of a file at a time.\n\
In addition to typical bash commands, you can also use the following commands\
\ to help you navigate and edit files.\n\nCOMMANDS:\n{command_docs}\n\nPlease\
\ note that THE EDIT COMMAND REQUIRES PROPER INDENTATION. \nIf you'd like to\
\ add the line ' print(x)' you must fully write that out, with all those\
\ spaces before the code! Indentation is important and code that is not indented\
\ correctly will fail and require fixing before it can be run.\n\nRESPONSE FORMAT:\n\
Your shell prompt is formatted as follows:\n(Open file: <path>) <cwd> $\n\n\
You need to format your output using two fields; discussion and command.\nYour\
\ output should always include _one_ discussion and _one_ command field EXACTLY\
\ as in the following example:\nDISCUSSION\nFirst I'll start by using ls to\
\ see what files are in the current directory. Then maybe we can look at some\
\ relevant files to see what they look like.\n```\nls -a\n```\n\nYou should\
\ only include a *SINGLE* command in the command section and then wait for a\
\ response from the shell before continuing with more discussion and commands.\
\ Everything you include in the DISCUSSION section will be saved for future\
\ reference.\nIf you'd like to issue two commands at once, PLEASE DO NOT DO\
\ THAT! Please instead first submit just the first command, and then after receiving\
\ a response you'll be able to issue the second command. \nYou're free to use\
\ any other bash commands you want (e.g. find, grep, cat, ls, cd) in addition\
\ to the special commands listed above.\nHowever, the environment does NOT support\
\ interactive session commands (e.g. python, vim), so please do not invoke them."
util_functions:
- arguments: null
code: '_print() { local total_lines=$(awk ''END {print NR}'' $CURRENT_FILE) echo
"[File: $(realpath $CURRENT_FILE) ($total_lines lines total)]" lines_above=$(jq
-n "$CURRENT_LINE - $WINDOW/2" | jq ''[0, .] | max | floor'') lines_below=$(jq
-n "$total_lines - $CURRENT_LINE - $WINDOW/2" | jq ''[0, .] | max | round'') if
[ $lines_above -gt 0 ]; then echo "($lines_above more lines above)" fi cat
$CURRENT_FILE | grep -n $ | head -n $(jq -n "[$CURRENT_LINE + $WINDOW/2, $WINDOW/2]
| max | floor") | tail -n $(jq -n "$WINDOW") if [ $lines_below -gt 0 ];
then echo "($lines_below more lines below)" fi}'
docstring: null
end_name: null
name: _print
signature: _print
- arguments: null
code: _constrain_line() { if [ -z "$CURRENT_FILE" ] then echo "No
file open. Use the open command first." return fi local max_line=$(awk
'END {print NR}' $CURRENT_FILE) local half_window=$(jq -n "$WINDOW/2" |
jq 'floor') export CURRENT_LINE=$(jq -n "[$CURRENT_LINE, $max_line - $half_window]
| min") export CURRENT_LINE=$(jq -n "[$CURRENT_LINE, $half_window] | max")}
docstring: null
end_name: null
name: _constrain_line
signature: _constrain_line
config_file: config/default_from_url.yaml
model:
host_url: localhost:11434
model_name: gpt4
per_instance_cost_limit: 3.0
replay_path: null
temperature: 0.0
top_p: 0.95
total_cost_limit: 0.0
environment:
base_commit: null
container_name: null
data_path: https://github.com/princeton-nlp/SWE-agent/issues/40
image_name: sweagent/swe-agent:latest
install_environment: true
no_mirror: false
split: dev
timeout: 35
verbose: true
instance_filter: .*
raise_exceptions: false
skip_existing: false
suffix: ''INFO 💽 Loaded dataset from https://github.com/princeton-nlp/SWE-agent/issues/40 DEBUG Starting container with command: docker run -i --rm --name sweagent-swe-agent-latest-86de67791a sweagent/swe-agent:latest /bin/bash -l -m INFO 🌱 Environment Initialized INFO ▶️ Beginning task 0
INFO Trying to clone from non-mirror... WARNING install_environment is set to True, but the data path is a GitHub URL. Skipping conda environment installation. INFO Initializing agent settings for container 61ea94a9ad0c3826088deb090a3e23cb73571de471a750be29df7b79e248e738 2024-04-12 20:31:51,178 - api_models - INFO - Resetting model stats INFO SYSTEM (primary) SETTING: You are an autonomous programmer, and you're working directly in the command line with a special interface.
The special interface consists of a file editor that shows you 100 lines of a file at a time.
In addition to typical bash commands, you can also use the following commands to help you navigate and edit
files.
COMMANDS:
open:
docstring: opens the file at the given path in the editor. If line_number is provided, the window will be
move to include that line
signature: open <path> [<line_number>]
arguments:
- path (string) [required]: the path to the file to open
- line_number (integer) [optional]: the line number to move the window to (if not provided, the window will
start at the top of the file)
goto:
docstring: moves the window to show <line_number>
signature: goto <line_number>
arguments:
- line_number (integer) [required]: the line number to move the window to
scroll_down:
docstring: moves the window down {WINDOW} lines
signature: scroll_down
scroll_up:
docstring: moves the window down {WINDOW} lines
signature: scroll_down
create:
docstring: creates and opens a new file with the given name
signature: create <filename>
arguments:
- filename (string) [required]: the name of the file to create
submit:
docstring: submits your current code and terminates the session
signature: submit
search_dir:
docstring: searches for search_term in all files in dir. If dir is not provided, searches in the current
directory
signature: search_dir <search_term> [<dir>]
arguments:
- search_term (string) [required]: the term to search for
- dir (string) [optional]: the directory to search in (if not provided, searches in the current directory)
search_file:
docstring: searches for search_term in file. If file is not provided, searches in the current open file
signature: search_file <search_term> [<file>]
arguments:
- search_term (string) [required]: the term to search for
- file (string) [optional]: the file to search in (if not provided, searches in the current open file)
find_file:
docstring: finds all files with the given name in dir. If dir is not provided, searches in the current
directory
signature: find_file <file_name> [<dir>]
arguments:
- file_name (string) [required]: the name of the file to search for
- dir (string) [optional]: the directory to search in (if not provided, searches in the current directory)
edit:
docstring: replaces lines <start_line> through <end_line> (inclusive) with the given text in the open file.
The replacement text is terminated by a line with only end_of_edit on it. All of the <replacement text> will be
entered, so make sure your indentation is formatted properly. Python files will be checked for syntax errors
after the edit. If the system detects a syntax error, the edit will not be executed. Simply try to edit the
file again, but make sure to read the error message and modify the edit command you issue accordingly. Issuing
the same command a second time will just lead to the same error message again.
signature: edit <start_line>:<end_line>
<replacement_text>
end_of_edit
arguments:
- start_line (integer) [required]: the line number to start the edit at
- end_line (integer) [required]: the line number to end the edit at (inclusive)
- replacement_text (string) [required]: the text to replace the current selection with
Please note that THE EDIT COMMAND REQUIRES PROPER INDENTATION.
If you'd like to add the line ' print(x)' you must fully write that out, with all those spaces before
the code! Indentation is important and code that is not indented correctly will fail and require fixing before
it can be run.
RESPONSE FORMAT:
Your shell prompt is formatted as follows:
(Open file: <path>) <cwd> $
You need to format your output using two fields; discussion and command.
Your output should always include _one_ discussion and _one_ command field EXACTLY as in the following example:
DISCUSSION
First I'll start by using ls to see what files are in the current directory. Then maybe we can look at some
relevant files to see what they look like.
```
ls -a
```
You should only include a *SINGLE* command in the command section and then wait for a response from the shell
before continuing with more discussion and commands. Everything you include in the DISCUSSION section will be
saved for future reference.
If you'd like to issue two commands at once, PLEASE DO NOT DO THAT! Please instead first submit just the first
command, and then after receiving a response you'll be able to issue the second command.
You're free to use any other bash commands you want (e.g. find, grep, cat, ls, cd) in addition to the special
commands listed above.
However, the environment does NOT support interactive session commands (e.g. python, vim), so please do not
invoke them.INFO DEMONSTRATION: trajectories/demonstrations/replaymarshmallow-codemarshmallow-1867defaultt-0.20p-0.95c-2.00__instal l-1_install_from_source/marshmallow-codemarshmallow-1867.traj INFO 🤖 MODEL INPUT We're currently solving the following issue within our repository. Here's the issue text: ISSUE: Inference - AttributeError: module 'signal' has no attribute 'SIGALRM'
python run.py --model_name gpt4 --data_path https://github.com/pvlib/pvlib-python/issues/1603 --config_file
config/default_from_url.yaml
Parsing command file: config/commands/defaults.sh
Parsing command file: config/commands/search.sh
Parsing command file: config/commands/edit_linting.sh
Parsing command file: config/commands/_split_string.py
Parsing command file: config/commands/defaults.sh
Parsing command file: config/commands/search.sh
Parsing command file: config/commands/edit_linting.sh
Parsing command file: config/commands/_split_string.py
INFO 📙 Arguments: agent:
...
INFO 💽 Loaded dataset from https://github.com/pvlib/pvlib-python/issues/1603
Traceback (most recent call last):
line 140, in __enter__
signal.signal(signal.SIGALRM, self.handle_timeout)
AttributeError: module 'signal' has no attribute 'SIGALRM'
# Maybe incompatible version of Python on Docker image? #
python --version
Python 3.9.19
INSTRUCTIONS:
Now, you're going to solve this issue on your own. Your terminal session has started and you're in the
repository's root directory. You can use any bash commands or the special interface to help you. Edit all the
files you need to and run any checks or tests that you want.
Remember, YOU CAN ONLY ENTER ONE COMMAND AT A TIME. You should always wait for feedback after every command.
When you're satisfied with all of the changes you've made, you can submit your changes to the code base by
simply running the submit command.
Note however that you cannot use any interactive session commands (e.g. python, vim) in this environment, but
you can write scripts and run them. E.g. you can write a python script and then run it with `python
<script_name>.py`.
NOTE ABOUT THE EDIT COMMAND: Indentation really matters! When editing a file, make sure to insert appropriate
indentation before each line!
IMPORTANT TIPS:
1. Always start by trying to replicate the bug that the issues discusses.
If the issue includes code for reproducing the bug, we recommend that you re-implement that in your
environment, and run it to make sure you can reproduce the bug.
Then start trying to fix it.
When you think you've fixed the bug, re-run the bug reproduction script to make sure that the bug has indeed
been fixed.
If the bug reproduction script does not print anything when it succesfully runs, we recommend adding a
print("Script completed successfully, no errors.") command at the end of the file,
so that you can be sure that the script indeed ran fine all the way through.
2. If you run a command and it doesn't work, try running a different command. A command that did not work once
will not work the second time unless you modify it!
3. If you open a file and need to get to an area around a specific line that is not in the first 100 lines, say
line 583, don't just use the scroll_down command multiple times. Instead, use the goto 583 command. It's much
quicker.
4. If the bug reproduction script requires inputting/reading a specific file, such as buggy-input.png, and
you'd like to understand how to input that file, conduct a search in the existing repo code, to see whether
someone else has already done that. Do this by running the command: find_file "buggy-input.png" If that
doensn't work, use the linux 'find' command.
5. Always make sure to look at the currently open file and the current working directory (which appears right
after the currently open file). The currently open file might be in a different directory than the working
directory! Note that some commands, such as 'create', open files, so they might change the current open file.
6. When editing files, it is easy to accidentally specify a wrong line number or to write code with incorrect
indentation. Always check the code after you issue an edit to make sure that it reflects what you wanted to
accomplish. If it didn't, issue another command to fix it.
7. It may be necessary to install the repository from source before you can run code. Please think about how to
install the environment from the repository directory if you need to do so.
(Open file: n/a)
(Current directory: /princeton-nlp__SWE-agent)
bash-$2024-04-12 20:32:03,641 - httpx - INFO - HTTP Request: POST https://api.openai.com/v1/chat/completions "HTTP/1.1 200 OK"
2024-04-12 20:32:03,689 - api_models - INFO - input_tokens=10_368, output_tokens=177, instance_cost=0.11, cost=0.11
2024-04-12 20:32:03,690 - api_models - INFO - total_tokens_sent=10_368, total_tokens_received=177, total_cost=0.11, total_api_calls=1
INFO 💭 THOUGHT (primary)
The issue indicates that there's an AttributeError related to signal.SIGALRM, which is not available on the
current Python version or environment. The SIGALRM signal is typically available on Unix systems and is not
available on Windows. The error suggests that the code is being run in an environment where signal.SIGALRM is
not available, which could be a non-Unix system or a compatibility issue with the Python version.
The first step to address this issue is to replicate the bug. Since the issue mentions a specific command that
triggers the error, we should try to run that command. However, before we do that, we need to ensure that the
repository is installed correctly and that we have all the necessary files.
Let's start by checking the contents of the current directory to see what files and directories are present.INFO 🎬 ACTION (primary) ls -F
INFO Saved trajectory to trajectories/root/gpt4princeton-nlpSWE-agentdefault_from_urlt-0.00p-0.95c-3.00install-1/princeton -nlpSWE-agent-i40.traj INFO 🤖 MODEL INPUT Dockerfile LICENSE README.md assets/ build_deploy.sh codecov.yml config/ docker/ environment.yml evaluation/ inspector/ make_demos/ mlc_config.json pyproject.toml release_dockerhub.sh run.py run_replay.py scripts/ setup.cfg setup.py setup.sh* sweagent/ tests/ trajectories/
(Open file: n/a)
(Current directory: /princeton-nlp__SWE-agent)
bash-$2024-04-12 20:32:18,606 - httpx - INFO - HTTP Request: POST https://api.openai.com/v1/chat/completions "HTTP/1.1 200 OK"
2024-04-12 20:32:18,614 - api_models - INFO - input_tokens=10_654, output_tokens=169, instance_cost=0.22, cost=0.11
2024-04-12 20:32:18,615 - api_models - INFO - total_tokens_sent=21_022, total_tokens_received=346, total_cost=0.22, total_api_calls=2
INFO 💭 THOUGHT (primary)
The repository contains a run.py file, which is mentioned in the issue as the script that triggers the error
when executed with certain arguments. Before running the script, it's important to ensure that the environment
is set up correctly. The presence of environment.yml suggests that there might be a conda environment that
needs to be set up, and setup.py indicates that the repository might need to be installed as a package.
Since we cannot run interactive commands like conda or pip directly in this environment, we'll need to create a
script that sets up the environment and runs the `run.py` file to replicate the bug. Let's create a script
named `reproduce_bug.sh` that will attempt to install the environment and run the `run.py` script with the
provided arguments.INFO 🎬 ACTION (primary) create reproduce_bug.sh
---
RESTARTING PROCESS.INFO Beginning environment shutdown... INFO Agent container stopped DEBUG Starting container with command: docker run -i --rm --name sweagent-swe-agent-latest-86de67791a sweagent/swe-agent:latest /bin/bash -l -m
ofirpress
commented
4 months ago Hi! We have a lot of things on our list and Windows support is probably not something we can get to soon. Please update us if you solve this, but in the meanwhile I recommend trying swe-agent on a linux victual machine.
PierrunoYT
commented
4 months ago Hi! We have a lot of things on our list and Windows support is probably not something we can get to soon. Please update us if you solve this, but in the meanwhile I recommend trying swe-agent on a linux victual machine.
Hey there. I'm running it inside WSL Ubuntu on Windows 11 Pro
klieret
commented
1 day ago Closing this. Let's hope some of the newer changes and improvements prevent this.