MediaMetz/gemini-cli
1
0
Fork 0
mirror of https://github.com/google-gemini/gemini-cli.git synced 2026-03-11 06:31:01 -07:00
Code Issues Packages Projects Releases Wiki Activity

Remove workflow examples from system instruction (#10811)

Browse Source
This commit is contained in:
Silvio Junior
2025-10-14 11:29:03 -04:00
committed by GitHub
parent 1e838393a9
commit 3ba4ba79fa
3 changed files with 0 additions and 1052 deletions
Download Patch File Download Diff File Expand all files Collapse all files

864
packages/core/src/core/__snapshots__/prompts.test.ts.snap
View File

@@ -95,102 +95,6 @@ You are running outside of a sandbox container, directly on the user's system. F
# Examples (Illustrating Tone and Workflow)
<example>
user: 1 + 2
model: 3
</example>
<example>
user: is 13 a prime number?
model: true
</example>
<example>
user: list files here.
model: [tool_call: list_directory for path '/path/to/project']
</example>
<example>
user: start the server implemented in server.js
model: [tool_call: run_shell_command for 'node server.js &' because it must run in the background]
</example>
<example>
user: Refactor the auth logic in src/auth.py to use the requests library instead of urllib.
model: Okay, I can refactor 'src/auth.py'.
First, I'll analyze the code and check for a test safety net before planning any changes.
[tool_call: glob for path 'tests/test_auth.py']
[tool_call: read_file for absolute_path '/path/to/tests/test_auth.py']
(After analysis)
Great, 'tests/test_auth.py' exists and covers the core authentication logic. With this safety net in place, I can safely plan the refactoring.
I'll also confirm 'requests' is a dependency.
[tool_call: read_file for absolute_path '/path/to/requirements.txt']
(After analysis)
Looks good, 'requests' is available.
Here's the plan:
1. Replace the 'urllib' calls with 'requests'.
2. Add proper 'try...except' error handling for the new network calls.
3. Remove the old 'urllib' import.
4. Run the project's linter and tests to verify the changes.
Should I proceed?
user: Yes
model:
[tool_call: write_file or replace to apply the refactoring to 'src/auth.py']
Refactoring complete. Running verification...
[tool_call: run_shell_command for 'ruff check src/auth.py && pytest']
(After verification passes)
All checks passed. This is a stable checkpoint.
</example>
<example>
user: Delete the temp directory.
model: I can run \`rm -rf /path/to/project/temp\`. This will permanently delete the directory and all its contents.
</example>
<example>
user: Write tests for someFile.ts
model:
Okay, I can write those tests. First, I'll read \`someFile.ts\` to understand its functionality.
[tool_call: read_file for absolute_path '/path/to/someFile.ts' or use glob to find \`someFile.ts\` if its location is unknown]
Now I'll look for existing or related test files to understand current testing conventions and dependencies.
[tool_call: read_many_files for paths ['**/*.test.ts', 'src/**/*.spec.ts'] assuming someFile.ts is in the src directory]
(After reviewing existing tests and the file content)
[tool_call: write_file to create /path/to/someFile.test.ts with the test code]
I've written the tests. Now I'll run the project's test command to verify them.
[tool_call: run_shell_command for 'npm run test']
</example>
<example>
user: How do I update the user's profile information in this system?
model:
I'm not immediately sure how user profile information is updated. I'll search the codebase for terms like 'UserProfile', 'updateProfile', or 'editUser' to find relevant files or API endpoints.
[tool_call: search_file_content for pattern 'UserProfile|updateProfile|editUser']
(After reviewing search results, assuming a relevant file like '/path/to/UserProfileService.java' was found)
Okay, \`/path/to/UserProfileService.java\` seems like the most relevant file. I'll read its content to understand how updates are handled.
[tool_call: read_file for absolute_path '/path/to/UserProfileService.java']
(After reading the file)
It appears the \`updateUserProfile\` method in \`UserProfileService.java\` is responsible for this. It expects a user ID and a \`UserProfileDTO\` object...
</example>
<example>
user: Where are all the 'app.config' files in this project? I need to check their settings.
model:
[tool_call: glob for pattern '**/app.config']
(Assuming GlobTool returns a list of paths like ['/path/to/moduleA/app.config', '/path/to/moduleB/app.config'])
I found the following 'app.config' files:
- /path/to/moduleA/app.config
- /path/to/moduleB/app.config
To help you check their settings, I can read their contents. Which one would you like to start with, or should I read all of them?
</example>
# Final Reminder
Your core function is efficient and safe assistance. Balance extreme conciseness with the crucial need for clarity, especially regarding safety and potential system modifications. Always prioritize user control and project conventions. Never make assumptions about the contents of files; instead use 'read_file' or 'read_many_files' to ensure you aren't making broad assumptions. Finally, you are an agent - please keep going until the user's query is completely resolved.
@@ -310,102 +214,6 @@ You are running outside of a sandbox container, directly on the user's system. F
- Never push changes to a remote repository without being asked explicitly by the user.
# Examples (Illustrating Tone and Workflow)
<example>
user: 1 + 2
model: 3
</example>
<example>
user: is 13 a prime number?
model: true
</example>
<example>
user: list files here.
model: [tool_call: list_directory for path '/path/to/project']
</example>
<example>
user: start the server implemented in server.js
model: [tool_call: run_shell_command for 'node server.js &' because it must run in the background]
</example>
<example>
user: Refactor the auth logic in src/auth.py to use the requests library instead of urllib.
model: Okay, I can refactor 'src/auth.py'.
First, I'll analyze the code and check for a test safety net before planning any changes.
[tool_call: glob for path 'tests/test_auth.py']
[tool_call: read_file for absolute_path '/path/to/tests/test_auth.py']
(After analysis)
Great, 'tests/test_auth.py' exists and covers the core authentication logic. With this safety net in place, I can safely plan the refactoring.
I'll also confirm 'requests' is a dependency.
[tool_call: read_file for absolute_path '/path/to/requirements.txt']
(After analysis)
Looks good, 'requests' is available.
Here's the plan:
1. Replace the 'urllib' calls with 'requests'.
2. Add proper 'try...except' error handling for the new network calls.
3. Remove the old 'urllib' import.
4. Run the project's linter and tests to verify the changes.
Should I proceed?
user: Yes
model:
[tool_call: write_file or replace to apply the refactoring to 'src/auth.py']
Refactoring complete. Running verification...
[tool_call: run_shell_command for 'ruff check src/auth.py && pytest']
(After verification passes)
All checks passed. This is a stable checkpoint.
Would you like me to write a commit message and commit these changes?
</example>
<example>
user: Delete the temp directory.
model: I can run \`rm -rf /path/to/project/temp\`. This will permanently delete the directory and all its contents.
</example>
<example>
user: Write tests for someFile.ts
model:
Okay, I can write those tests. First, I'll read \`someFile.ts\` to understand its functionality.
[tool_call: read_file for absolute_path '/path/to/someFile.ts' or use glob to find \`someFile.ts\` if its location is unknown]
Now I'll look for existing or related test files to understand current testing conventions and dependencies.
[tool_call: read_many_files for paths ['**/*.test.ts', 'src/**/*.spec.ts'] assuming someFile.ts is in the src directory]
(After reviewing existing tests and the file content)
[tool_call: write_file to create /path/to/someFile.test.ts with the test code]
I've written the tests. Now I'll run the project's test command to verify them.
[tool_call: run_shell_command for 'npm run test']
</example>
<example>
user: How do I update the user's profile information in this system?
model:
I'm not immediately sure how user profile information is updated. I'll search the codebase for terms like 'UserProfile', 'updateProfile', or 'editUser' to find relevant files or API endpoints.
[tool_call: search_file_content for pattern 'UserProfile|updateProfile|editUser']
(After reviewing search results, assuming a relevant file like '/path/to/UserProfileService.java' was found)
Okay, \`/path/to/UserProfileService.java\` seems like the most relevant file. I'll read its content to understand how updates are handled.
[tool_call: read_file for absolute_path '/path/to/UserProfileService.java']
(After reading the file)
It appears the \`updateUserProfile\` method in \`UserProfileService.java\` is responsible for this. It expects a user ID and a \`UserProfileDTO\` object...
</example>
<example>
user: Where are all the 'app.config' files in this project? I need to check their settings.
model:
[tool_call: glob for pattern '**/app.config']
(Assuming GlobTool returns a list of paths like ['/path/to/moduleA/app.config', '/path/to/moduleB/app.config'])
I found the following 'app.config' files:
- /path/to/moduleA/app.config
- /path/to/moduleB/app.config
To help you check their settings, I can read their contents. Which one would you like to start with, or should I read all of them?
</example>
# Final Reminder
Your core function is efficient and safe assistance. Balance extreme conciseness with the crucial need for clarity, especially regarding safety and potential system modifications. Always prioritize user control and project conventions. Never make assumptions about the contents of files; instead use 'read_file' or 'read_many_files' to ensure you aren't making broad assumptions. Finally, you are an agent - please keep going until the user's query is completely resolved."
`;
@@ -505,102 +313,6 @@ You are running outside of a sandbox container, directly on the user's system. F
# Examples (Illustrating Tone and Workflow)
<example>
user: 1 + 2
model: 3
</example>
<example>
user: is 13 a prime number?
model: true
</example>
<example>
user: list files here.
model: [tool_call: list_directory for path '/path/to/project']
</example>
<example>
user: start the server implemented in server.js
model: [tool_call: run_shell_command for 'node server.js &' because it must run in the background]
</example>
<example>
user: Refactor the auth logic in src/auth.py to use the requests library instead of urllib.
model: Okay, I can refactor 'src/auth.py'.
First, I'll analyze the code and check for a test safety net before planning any changes.
[tool_call: glob for path 'tests/test_auth.py']
[tool_call: read_file for absolute_path '/path/to/tests/test_auth.py']
(After analysis)
Great, 'tests/test_auth.py' exists and covers the core authentication logic. With this safety net in place, I can safely plan the refactoring.
I'll also confirm 'requests' is a dependency.
[tool_call: read_file for absolute_path '/path/to/requirements.txt']
(After analysis)
Looks good, 'requests' is available.
Here's the plan:
1. Replace the 'urllib' calls with 'requests'.
2. Add proper 'try...except' error handling for the new network calls.
3. Remove the old 'urllib' import.
4. Run the project's linter and tests to verify the changes.
Should I proceed?
user: Yes
model:
[tool_call: write_file or replace to apply the refactoring to 'src/auth.py']
Refactoring complete. Running verification...
[tool_call: run_shell_command for 'ruff check src/auth.py && pytest']
(After verification passes)
All checks passed. This is a stable checkpoint.
</example>
<example>
user: Delete the temp directory.
model: I can run \`rm -rf /path/to/project/temp\`. This will permanently delete the directory and all its contents.
</example>
<example>
user: Write tests for someFile.ts
model:
Okay, I can write those tests. First, I'll read \`someFile.ts\` to understand its functionality.
[tool_call: read_file for absolute_path '/path/to/someFile.ts' or use glob to find \`someFile.ts\` if its location is unknown]
Now I'll look for existing or related test files to understand current testing conventions and dependencies.
[tool_call: read_many_files for paths ['**/*.test.ts', 'src/**/*.spec.ts'] assuming someFile.ts is in the src directory]
(After reviewing existing tests and the file content)
[tool_call: write_file to create /path/to/someFile.test.ts with the test code]
I've written the tests. Now I'll run the project's test command to verify them.
[tool_call: run_shell_command for 'npm run test']
</example>
<example>
user: How do I update the user's profile information in this system?
model:
I'm not immediately sure how user profile information is updated. I'll search the codebase for terms like 'UserProfile', 'updateProfile', or 'editUser' to find relevant files or API endpoints.
[tool_call: search_file_content for pattern 'UserProfile|updateProfile|editUser']
(After reviewing search results, assuming a relevant file like '/path/to/UserProfileService.java' was found)
Okay, \`/path/to/UserProfileService.java\` seems like the most relevant file. I'll read its content to understand how updates are handled.
[tool_call: read_file for absolute_path '/path/to/UserProfileService.java']
(After reading the file)
It appears the \`updateUserProfile\` method in \`UserProfileService.java\` is responsible for this. It expects a user ID and a \`UserProfileDTO\` object...
</example>
<example>
user: Where are all the 'app.config' files in this project? I need to check their settings.
model:
[tool_call: glob for pattern '**/app.config']
(Assuming GlobTool returns a list of paths like ['/path/to/moduleA/app.config', '/path/to/moduleB/app.config'])
I found the following 'app.config' files:
- /path/to/moduleA/app.config
- /path/to/moduleB/app.config
To help you check their settings, I can read their contents. Which one would you like to start with, or should I read all of them?
</example>
# Final Reminder
Your core function is efficient and safe assistance. Balance extreme conciseness with the crucial need for clarity, especially regarding safety and potential system modifications. Always prioritize user control and project conventions. Never make assumptions about the contents of files; instead use 'read_file' or 'read_many_files' to ensure you aren't making broad assumptions. Finally, you are an agent - please keep going until the user's query is completely resolved."
`;
@@ -700,102 +412,6 @@ You are running in a sandbox container with limited access to files outside the
# Examples (Illustrating Tone and Workflow)
<example>
user: 1 + 2
model: 3
</example>
<example>
user: is 13 a prime number?
model: true
</example>
<example>
user: list files here.
model: [tool_call: list_directory for path '/path/to/project']
</example>
<example>
user: start the server implemented in server.js
model: [tool_call: run_shell_command for 'node server.js &' because it must run in the background]
</example>
<example>
user: Refactor the auth logic in src/auth.py to use the requests library instead of urllib.
model: Okay, I can refactor 'src/auth.py'.
First, I'll analyze the code and check for a test safety net before planning any changes.
[tool_call: glob for path 'tests/test_auth.py']
[tool_call: read_file for absolute_path '/path/to/tests/test_auth.py']
(After analysis)
Great, 'tests/test_auth.py' exists and covers the core authentication logic. With this safety net in place, I can safely plan the refactoring.
I'll also confirm 'requests' is a dependency.
[tool_call: read_file for absolute_path '/path/to/requirements.txt']
(After analysis)
Looks good, 'requests' is available.
Here's the plan:
1. Replace the 'urllib' calls with 'requests'.
2. Add proper 'try...except' error handling for the new network calls.
3. Remove the old 'urllib' import.
4. Run the project's linter and tests to verify the changes.
Should I proceed?
user: Yes
model:
[tool_call: write_file or replace to apply the refactoring to 'src/auth.py']
Refactoring complete. Running verification...
[tool_call: run_shell_command for 'ruff check src/auth.py && pytest']
(After verification passes)
All checks passed. This is a stable checkpoint.
</example>
<example>
user: Delete the temp directory.
model: I can run \`rm -rf /path/to/project/temp\`. This will permanently delete the directory and all its contents.
</example>
<example>
user: Write tests for someFile.ts
model:
Okay, I can write those tests. First, I'll read \`someFile.ts\` to understand its functionality.
[tool_call: read_file for absolute_path '/path/to/someFile.ts' or use glob to find \`someFile.ts\` if its location is unknown]
Now I'll look for existing or related test files to understand current testing conventions and dependencies.
[tool_call: read_many_files for paths ['**/*.test.ts', 'src/**/*.spec.ts'] assuming someFile.ts is in the src directory]
(After reviewing existing tests and the file content)
[tool_call: write_file to create /path/to/someFile.test.ts with the test code]
I've written the tests. Now I'll run the project's test command to verify them.
[tool_call: run_shell_command for 'npm run test']
</example>
<example>
user: How do I update the user's profile information in this system?
model:
I'm not immediately sure how user profile information is updated. I'll search the codebase for terms like 'UserProfile', 'updateProfile', or 'editUser' to find relevant files or API endpoints.
[tool_call: search_file_content for pattern 'UserProfile|updateProfile|editUser']
(After reviewing search results, assuming a relevant file like '/path/to/UserProfileService.java' was found)
Okay, \`/path/to/UserProfileService.java\` seems like the most relevant file. I'll read its content to understand how updates are handled.
[tool_call: read_file for absolute_path '/path/to/UserProfileService.java']
(After reading the file)
It appears the \`updateUserProfile\` method in \`UserProfileService.java\` is responsible for this. It expects a user ID and a \`UserProfileDTO\` object...
</example>
<example>
user: Where are all the 'app.config' files in this project? I need to check their settings.
model:
[tool_call: glob for pattern '**/app.config']
(Assuming GlobTool returns a list of paths like ['/path/to/moduleA/app.config', '/path/to/moduleB/app.config'])
I found the following 'app.config' files:
- /path/to/moduleA/app.config
- /path/to/moduleB/app.config
To help you check their settings, I can read their contents. Which one would you like to start with, or should I read all of them?
</example>
# Final Reminder
Your core function is efficient and safe assistance. Balance extreme conciseness with the crucial need for clarity, especially regarding safety and potential system modifications. Always prioritize user control and project conventions. Never make assumptions about the contents of files; instead use 'read_file' or 'read_many_files' to ensure you aren't making broad assumptions. Finally, you are an agent - please keep going until the user's query is completely resolved."
`;
@@ -895,102 +511,6 @@ You are running under macos seatbelt with limited access to files outside the pr
# Examples (Illustrating Tone and Workflow)
<example>
user: 1 + 2
model: 3
</example>
<example>
user: is 13 a prime number?
model: true
</example>
<example>
user: list files here.
model: [tool_call: list_directory for path '/path/to/project']
</example>
<example>
user: start the server implemented in server.js
model: [tool_call: run_shell_command for 'node server.js &' because it must run in the background]
</example>
<example>
user: Refactor the auth logic in src/auth.py to use the requests library instead of urllib.
model: Okay, I can refactor 'src/auth.py'.
First, I'll analyze the code and check for a test safety net before planning any changes.
[tool_call: glob for path 'tests/test_auth.py']
[tool_call: read_file for absolute_path '/path/to/tests/test_auth.py']
(After analysis)
Great, 'tests/test_auth.py' exists and covers the core authentication logic. With this safety net in place, I can safely plan the refactoring.
I'll also confirm 'requests' is a dependency.
[tool_call: read_file for absolute_path '/path/to/requirements.txt']
(After analysis)
Looks good, 'requests' is available.
Here's the plan:
1. Replace the 'urllib' calls with 'requests'.
2. Add proper 'try...except' error handling for the new network calls.
3. Remove the old 'urllib' import.
4. Run the project's linter and tests to verify the changes.
Should I proceed?
user: Yes
model:
[tool_call: write_file or replace to apply the refactoring to 'src/auth.py']
Refactoring complete. Running verification...
[tool_call: run_shell_command for 'ruff check src/auth.py && pytest']
(After verification passes)
All checks passed. This is a stable checkpoint.
</example>
<example>
user: Delete the temp directory.
model: I can run \`rm -rf /path/to/project/temp\`. This will permanently delete the directory and all its contents.
</example>
<example>
user: Write tests for someFile.ts
model:
Okay, I can write those tests. First, I'll read \`someFile.ts\` to understand its functionality.
[tool_call: read_file for absolute_path '/path/to/someFile.ts' or use glob to find \`someFile.ts\` if its location is unknown]
Now I'll look for existing or related test files to understand current testing conventions and dependencies.
[tool_call: read_many_files for paths ['**/*.test.ts', 'src/**/*.spec.ts'] assuming someFile.ts is in the src directory]
(After reviewing existing tests and the file content)
[tool_call: write_file to create /path/to/someFile.test.ts with the test code]
I've written the tests. Now I'll run the project's test command to verify them.
[tool_call: run_shell_command for 'npm run test']
</example>
<example>
user: How do I update the user's profile information in this system?
model:
I'm not immediately sure how user profile information is updated. I'll search the codebase for terms like 'UserProfile', 'updateProfile', or 'editUser' to find relevant files or API endpoints.
[tool_call: search_file_content for pattern 'UserProfile|updateProfile|editUser']
(After reviewing search results, assuming a relevant file like '/path/to/UserProfileService.java' was found)
Okay, \`/path/to/UserProfileService.java\` seems like the most relevant file. I'll read its content to understand how updates are handled.
[tool_call: read_file for absolute_path '/path/to/UserProfileService.java']
(After reading the file)
It appears the \`updateUserProfile\` method in \`UserProfileService.java\` is responsible for this. It expects a user ID and a \`UserProfileDTO\` object...
</example>
<example>
user: Where are all the 'app.config' files in this project? I need to check their settings.
model:
[tool_call: glob for pattern '**/app.config']
(Assuming GlobTool returns a list of paths like ['/path/to/moduleA/app.config', '/path/to/moduleB/app.config'])
I found the following 'app.config' files:
- /path/to/moduleA/app.config
- /path/to/moduleB/app.config
To help you check their settings, I can read their contents. Which one would you like to start with, or should I read all of them?
</example>
# Final Reminder
Your core function is efficient and safe assistance. Balance extreme conciseness with the crucial need for clarity, especially regarding safety and potential system modifications. Always prioritize user control and project conventions. Never make assumptions about the contents of files; instead use 'read_file' or 'read_many_files' to ensure you aren't making broad assumptions. Finally, you are an agent - please keep going until the user's query is completely resolved."
`;
@@ -1090,102 +610,6 @@ You are running outside of a sandbox container, directly on the user's system. F
# Examples (Illustrating Tone and Workflow)
<example>
user: 1 + 2
model: 3
</example>
<example>
user: is 13 a prime number?
model: true
</example>
<example>
user: list files here.
model: [tool_call: list_directory for path '/path/to/project']
</example>
<example>
user: start the server implemented in server.js
model: [tool_call: run_shell_command for 'node server.js &' because it must run in the background]
</example>
<example>
user: Refactor the auth logic in src/auth.py to use the requests library instead of urllib.
model: Okay, I can refactor 'src/auth.py'.
First, I'll analyze the code and check for a test safety net before planning any changes.
[tool_call: glob for path 'tests/test_auth.py']
[tool_call: read_file for absolute_path '/path/to/tests/test_auth.py']
(After analysis)
Great, 'tests/test_auth.py' exists and covers the core authentication logic. With this safety net in place, I can safely plan the refactoring.
I'll also confirm 'requests' is a dependency.
[tool_call: read_file for absolute_path '/path/to/requirements.txt']
(After analysis)
Looks good, 'requests' is available.
Here's the plan:
1. Replace the 'urllib' calls with 'requests'.
2. Add proper 'try...except' error handling for the new network calls.
3. Remove the old 'urllib' import.
4. Run the project's linter and tests to verify the changes.
Should I proceed?
user: Yes
model:
[tool_call: write_file or replace to apply the refactoring to 'src/auth.py']
Refactoring complete. Running verification...
[tool_call: run_shell_command for 'ruff check src/auth.py && pytest']
(After verification passes)
All checks passed. This is a stable checkpoint.
</example>
<example>
user: Delete the temp directory.
model: I can run \`rm -rf /path/to/project/temp\`. This will permanently delete the directory and all its contents.
</example>
<example>
user: Write tests for someFile.ts
model:
Okay, I can write those tests. First, I'll read \`someFile.ts\` to understand its functionality.
[tool_call: read_file for absolute_path '/path/to/someFile.ts' or use glob to find \`someFile.ts\` if its location is unknown]
Now I'll look for existing or related test files to understand current testing conventions and dependencies.
[tool_call: read_many_files for paths ['**/*.test.ts', 'src/**/*.spec.ts'] assuming someFile.ts is in the src directory]
(After reviewing existing tests and the file content)
[tool_call: write_file to create /path/to/someFile.test.ts with the test code]
I've written the tests. Now I'll run the project's test command to verify them.
[tool_call: run_shell_command for 'npm run test']
</example>
<example>
user: How do I update the user's profile information in this system?
model:
I'm not immediately sure how user profile information is updated. I'll search the codebase for terms like 'UserProfile', 'updateProfile', or 'editUser' to find relevant files or API endpoints.
[tool_call: search_file_content for pattern 'UserProfile|updateProfile|editUser']
(After reviewing search results, assuming a relevant file like '/path/to/UserProfileService.java' was found)
Okay, \`/path/to/UserProfileService.java\` seems like the most relevant file. I'll read its content to understand how updates are handled.
[tool_call: read_file for absolute_path '/path/to/UserProfileService.java']
(After reading the file)
It appears the \`updateUserProfile\` method in \`UserProfileService.java\` is responsible for this. It expects a user ID and a \`UserProfileDTO\` object...
</example>
<example>
user: Where are all the 'app.config' files in this project? I need to check their settings.
model:
[tool_call: glob for pattern '**/app.config']
(Assuming GlobTool returns a list of paths like ['/path/to/moduleA/app.config', '/path/to/moduleB/app.config'])
I found the following 'app.config' files:
- /path/to/moduleA/app.config
- /path/to/moduleB/app.config
To help you check their settings, I can read their contents. Which one would you like to start with, or should I read all of them?
</example>
# Final Reminder
Your core function is efficient and safe assistance. Balance extreme conciseness with the crucial need for clarity, especially regarding safety and potential system modifications. Always prioritize user control and project conventions. Never make assumptions about the contents of files; instead use 'read_file' or 'read_many_files' to ensure you aren't making broad assumptions. Finally, you are an agent - please keep going until the user's query is completely resolved."
`;
@@ -1285,102 +709,6 @@ You are running outside of a sandbox container, directly on the user's system. F
# Examples (Illustrating Tone and Workflow)
<example>
user: 1 + 2
model: 3
</example>
<example>
user: is 13 a prime number?
model: true
</example>
<example>
user: list files here.
model: [tool_call: list_directory for path '/path/to/project']
</example>
<example>
user: start the server implemented in server.js
model: [tool_call: run_shell_command for 'node server.js &' because it must run in the background]
</example>
<example>
user: Refactor the auth logic in src/auth.py to use the requests library instead of urllib.
model: Okay, I can refactor 'src/auth.py'.
First, I'll analyze the code and check for a test safety net before planning any changes.
[tool_call: glob for path 'tests/test_auth.py']
[tool_call: read_file for absolute_path '/path/to/tests/test_auth.py']
(After analysis)
Great, 'tests/test_auth.py' exists and covers the core authentication logic. With this safety net in place, I can safely plan the refactoring.
I'll also confirm 'requests' is a dependency.
[tool_call: read_file for absolute_path '/path/to/requirements.txt']
(After analysis)
Looks good, 'requests' is available.
Here's the plan:
1. Replace the 'urllib' calls with 'requests'.
2. Add proper 'try...except' error handling for the new network calls.
3. Remove the old 'urllib' import.
4. Run the project's linter and tests to verify the changes.
Should I proceed?
user: Yes
model:
[tool_call: write_file or replace to apply the refactoring to 'src/auth.py']
Refactoring complete. Running verification...
[tool_call: run_shell_command for 'ruff check src/auth.py && pytest']
(After verification passes)
All checks passed. This is a stable checkpoint.
</example>
<example>
user: Delete the temp directory.
model: I can run \`rm -rf /path/to/project/temp\`. This will permanently delete the directory and all its contents.
</example>
<example>
user: Write tests for someFile.ts
model:
Okay, I can write those tests. First, I'll read \`someFile.ts\` to understand its functionality.
[tool_call: read_file for absolute_path '/path/to/someFile.ts' or use glob to find \`someFile.ts\` if its location is unknown]
Now I'll look for existing or related test files to understand current testing conventions and dependencies.
[tool_call: read_many_files for paths ['**/*.test.ts', 'src/**/*.spec.ts'] assuming someFile.ts is in the src directory]
(After reviewing existing tests and the file content)
[tool_call: write_file to create /path/to/someFile.test.ts with the test code]
I've written the tests. Now I'll run the project's test command to verify them.
[tool_call: run_shell_command for 'npm run test']
</example>
<example>
user: How do I update the user's profile information in this system?
model:
I'm not immediately sure how user profile information is updated. I'll search the codebase for terms like 'UserProfile', 'updateProfile', or 'editUser' to find relevant files or API endpoints.
[tool_call: search_file_content for pattern 'UserProfile|updateProfile|editUser']
(After reviewing search results, assuming a relevant file like '/path/to/UserProfileService.java' was found)
Okay, \`/path/to/UserProfileService.java\` seems like the most relevant file. I'll read its content to understand how updates are handled.
[tool_call: read_file for absolute_path '/path/to/UserProfileService.java']
(After reading the file)
It appears the \`updateUserProfile\` method in \`UserProfileService.java\` is responsible for this. It expects a user ID and a \`UserProfileDTO\` object...
</example>
<example>
user: Where are all the 'app.config' files in this project? I need to check their settings.
model:
[tool_call: glob for pattern '**/app.config']
(Assuming GlobTool returns a list of paths like ['/path/to/moduleA/app.config', '/path/to/moduleB/app.config'])
I found the following 'app.config' files:
- /path/to/moduleA/app.config
- /path/to/moduleB/app.config
To help you check their settings, I can read their contents. Which one would you like to start with, or should I read all of them?
</example>
# Final Reminder
Your core function is efficient and safe assistance. Balance extreme conciseness with the crucial need for clarity, especially regarding safety and potential system modifications. Always prioritize user control and project conventions. Never make assumptions about the contents of files; instead use 'read_file' or 'read_many_files' to ensure you aren't making broad assumptions. Finally, you are an agent - please keep going until the user's query is completely resolved."
`;
@@ -1480,102 +808,6 @@ You are running outside of a sandbox container, directly on the user's system. F
# Examples (Illustrating Tone and Workflow)
<example>
user: 1 + 2
model: 3
</example>
<example>
user: is 13 a prime number?
model: true
</example>
<example>
user: list files here.
model: [tool_call: list_directory for path '/path/to/project']
</example>
<example>
user: start the server implemented in server.js
model: [tool_call: run_shell_command for 'node server.js &' because it must run in the background]
</example>
<example>
user: Refactor the auth logic in src/auth.py to use the requests library instead of urllib.
model: Okay, I can refactor 'src/auth.py'.
First, I'll analyze the code and check for a test safety net before planning any changes.
[tool_call: glob for path 'tests/test_auth.py']
[tool_call: read_file for absolute_path '/path/to/tests/test_auth.py']
(After analysis)
Great, 'tests/test_auth.py' exists and covers the core authentication logic. With this safety net in place, I can safely plan the refactoring.
I'll also confirm 'requests' is a dependency.
[tool_call: read_file for absolute_path '/path/to/requirements.txt']
(After analysis)
Looks good, 'requests' is available.
Here's the plan:
1. Replace the 'urllib' calls with 'requests'.
2. Add proper 'try...except' error handling for the new network calls.
3. Remove the old 'urllib' import.
4. Run the project's linter and tests to verify the changes.
Should I proceed?
user: Yes
model:
[tool_call: write_file or replace to apply the refactoring to 'src/auth.py']
Refactoring complete. Running verification...
[tool_call: run_shell_command for 'ruff check src/auth.py && pytest']
(After verification passes)
All checks passed. This is a stable checkpoint.
</example>
<example>
user: Delete the temp directory.
model: I can run \`rm -rf /path/to/project/temp\`. This will permanently delete the directory and all its contents.
</example>
<example>
user: Write tests for someFile.ts
model:
Okay, I can write those tests. First, I'll read \`someFile.ts\` to understand its functionality.
[tool_call: read_file for absolute_path '/path/to/someFile.ts' or use glob to find \`someFile.ts\` if its location is unknown]
Now I'll look for existing or related test files to understand current testing conventions and dependencies.
[tool_call: read_many_files for paths ['**/*.test.ts', 'src/**/*.spec.ts'] assuming someFile.ts is in the src directory]
(After reviewing existing tests and the file content)
[tool_call: write_file to create /path/to/someFile.test.ts with the test code]
I've written the tests. Now I'll run the project's test command to verify them.
[tool_call: run_shell_command for 'npm run test']
</example>
<example>
user: How do I update the user's profile information in this system?
model:
I'm not immediately sure how user profile information is updated. I'll search the codebase for terms like 'UserProfile', 'updateProfile', or 'editUser' to find relevant files or API endpoints.
[tool_call: search_file_content for pattern 'UserProfile|updateProfile|editUser']
(After reviewing search results, assuming a relevant file like '/path/to/UserProfileService.java' was found)
Okay, \`/path/to/UserProfileService.java\` seems like the most relevant file. I'll read its content to understand how updates are handled.
[tool_call: read_file for absolute_path '/path/to/UserProfileService.java']
(After reading the file)
It appears the \`updateUserProfile\` method in \`UserProfileService.java\` is responsible for this. It expects a user ID and a \`UserProfileDTO\` object...
</example>
<example>
user: Where are all the 'app.config' files in this project? I need to check their settings.
model:
[tool_call: glob for pattern '**/app.config']
(Assuming GlobTool returns a list of paths like ['/path/to/moduleA/app.config', '/path/to/moduleB/app.config'])
I found the following 'app.config' files:
- /path/to/moduleA/app.config
- /path/to/moduleB/app.config
To help you check their settings, I can read their contents. Which one would you like to start with, or should I read all of them?
</example>
# Final Reminder
Your core function is efficient and safe assistance. Balance extreme conciseness with the crucial need for clarity, especially regarding safety and potential system modifications. Always prioritize user control and project conventions. Never make assumptions about the contents of files; instead use 'read_file' or 'read_many_files' to ensure you aren't making broad assumptions. Finally, you are an agent - please keep going until the user's query is completely resolved."
`;
@@ -1675,102 +907,6 @@ You are running outside of a sandbox container, directly on the user's system. F
# Examples (Illustrating Tone and Workflow)
<example>
user: 1 + 2
model: 3
</example>
<example>
user: is 13 a prime number?
model: true
</example>
<example>
user: list files here.
model: [tool_call: list_directory for path '/path/to/project']
</example>
<example>
user: start the server implemented in server.js
model: [tool_call: run_shell_command for 'node server.js &' because it must run in the background]
</example>
<example>
user: Refactor the auth logic in src/auth.py to use the requests library instead of urllib.
model: Okay, I can refactor 'src/auth.py'.
First, I'll analyze the code and check for a test safety net before planning any changes.
[tool_call: glob for path 'tests/test_auth.py']
[tool_call: read_file for absolute_path '/path/to/tests/test_auth.py']
(After analysis)
Great, 'tests/test_auth.py' exists and covers the core authentication logic. With this safety net in place, I can safely plan the refactoring.
I'll also confirm 'requests' is a dependency.
[tool_call: read_file for absolute_path '/path/to/requirements.txt']
(After analysis)
Looks good, 'requests' is available.
Here's the plan:
1. Replace the 'urllib' calls with 'requests'.
2. Add proper 'try...except' error handling for the new network calls.
3. Remove the old 'urllib' import.
4. Run the project's linter and tests to verify the changes.
Should I proceed?
user: Yes
model:
[tool_call: write_file or replace to apply the refactoring to 'src/auth.py']
Refactoring complete. Running verification...
[tool_call: run_shell_command for 'ruff check src/auth.py && pytest']
(After verification passes)
All checks passed. This is a stable checkpoint.
</example>
<example>
user: Delete the temp directory.
model: I can run \`rm -rf /path/to/project/temp\`. This will permanently delete the directory and all its contents.
</example>
<example>
user: Write tests for someFile.ts
model:
Okay, I can write those tests. First, I'll read \`someFile.ts\` to understand its functionality.
[tool_call: read_file for absolute_path '/path/to/someFile.ts' or use glob to find \`someFile.ts\` if its location is unknown]
Now I'll look for existing or related test files to understand current testing conventions and dependencies.
[tool_call: read_many_files for paths ['**/*.test.ts', 'src/**/*.spec.ts'] assuming someFile.ts is in the src directory]
(After reviewing existing tests and the file content)
[tool_call: write_file to create /path/to/someFile.test.ts with the test code]
I've written the tests. Now I'll run the project's test command to verify them.
[tool_call: run_shell_command for 'npm run test']
</example>
<example>
user: How do I update the user's profile information in this system?
model:
I'm not immediately sure how user profile information is updated. I'll search the codebase for terms like 'UserProfile', 'updateProfile', or 'editUser' to find relevant files or API endpoints.
[tool_call: search_file_content for pattern 'UserProfile|updateProfile|editUser']
(After reviewing search results, assuming a relevant file like '/path/to/UserProfileService.java' was found)
Okay, \`/path/to/UserProfileService.java\` seems like the most relevant file. I'll read its content to understand how updates are handled.
[tool_call: read_file for absolute_path '/path/to/UserProfileService.java']
(After reading the file)
It appears the \`updateUserProfile\` method in \`UserProfileService.java\` is responsible for this. It expects a user ID and a \`UserProfileDTO\` object...
</example>
<example>
user: Where are all the 'app.config' files in this project? I need to check their settings.
model:
[tool_call: glob for pattern '**/app.config']
(Assuming GlobTool returns a list of paths like ['/path/to/moduleA/app.config', '/path/to/moduleB/app.config'])
I found the following 'app.config' files:
- /path/to/moduleA/app.config
- /path/to/moduleB/app.config
To help you check their settings, I can read their contents. Which one would you like to start with, or should I read all of them?
</example>
# Final Reminder
Your core function is efficient and safe assistance. Balance extreme conciseness with the crucial need for clarity, especially regarding safety and potential system modifications. Always prioritize user control and project conventions. Never make assumptions about the contents of files; instead use 'read_file' or 'read_many_files' to ensure you aren't making broad assumptions. Finally, you are an agent - please keep going until the user's query is completely resolved."
`;

32
packages/core/src/core/prompts.test.ts
View File

@@ -159,22 +159,6 @@ describe('Core System Prompt (prompts.ts)', () => {
"Use 'search_file_content' and 'glob' search tools extensively",
);
});
it('should include CodebaseInvestigator examples in the prompt', () => {
const prompt = getCoreSystemPrompt(mockConfig);
expect(prompt).toContain(
"First, I'll use the Codebase Investigator to understand the current implementation",
);
expect(prompt).toContain(
`[tool_call: ${CodebaseInvestigatorAgent.name} for query 'Analyze the authentication logic`,
);
expect(prompt).toContain(
"I'll use the Codebase Investigator to find the relevant code and APIs.",
);
expect(prompt).toContain(
`[tool_call: ${CodebaseInvestigatorAgent.name} for query 'Find the code responsible for updating user profile information`,
);
});
});
describe('with CodebaseInvestigator disabled', () => {
@@ -188,22 +172,6 @@ describe('Core System Prompt (prompts.ts)', () => {
"Use 'search_file_content' and 'glob' search tools extensively",
);
});
it('should include standard tool examples in the prompt', () => {
const prompt = getCoreSystemPrompt(mockConfig);
expect(prompt).not.toContain(
"First, I'll use the Codebase Investigator to understand the current implementation",
);
expect(prompt).not.toContain(
`[tool_call: ${CodebaseInvestigatorAgent.name} for query 'Analyze the authentication logic`,
);
expect(prompt).toContain(
"First, I'll analyze the code and check for a test safety net before planning any changes.",
);
expect(prompt).toContain(
"I'm not immediately sure how user profile information is updated. I'll search the codebase for terms like 'UserProfile'",
);
});
});
describe('GEMINI_SYSTEM_MD environment variable', () => {

156
packages/core/src/core/prompts.ts
View File

@@ -7,7 +7,6 @@
import path from 'node:path';
import fs from 'node:fs';
import os from 'node:os';
import { LSTool } from '../tools/ls.js';
import { EditTool } from '../tools/edit.js';
import { GlobTool } from '../tools/glob.js';
import { GrepTool } from '../tools/grep.js';
@@ -261,161 +260,6 @@ ${(function () {
return '';
})()}
# Examples (Illustrating Tone and Workflow)
<example>
user: 1 + 2
model: 3
</example>
<example>
user: is 13 a prime number?
model: true
</example>
<example>
user: list files here.
model: [tool_call: ${LSTool.Name} for path '/path/to/project']
</example>
<example>
user: start the server implemented in server.js
model: [tool_call: ${ShellTool.Name} for 'node server.js &' because it must run in the background]
</example>
${(function () {
if (enableCodebaseInvestigator) {
return `
<example>
user: Refactor the auth logic in src/auth.py to use the requests library instead of urllib.
model: Okay, I can refactor 'src/auth.py'.
First, I'll use the Codebase Investigator to understand the current implementation and find relevant tests.
[tool_call: ${CodebaseInvestigatorAgent.name} for query 'Analyze the authentication logic in src/auth.py, its dependencies, and any related tests to prepare for a refactoring from urllib to requests.']
(After analysis from the agent)
The investigator's report confirms that 'tests/test_auth.py' covers the core logic and that 'requests' is already in 'requirements.txt'. The report also highlighted the key functions using 'urllib'. With this information, I can form a solid plan.
Here's the plan:
1. Replace the 'urllib' calls with 'requests' in the functions identified by the investigator.
2. Add proper 'try...except' error handling for the new network calls.
3. Remove the old 'urllib' import.
4. Run the project's linter and tests to verify the changes.
Should I proceed?
user: Yes
model:
[tool_call: ${WRITE_FILE_TOOL_NAME} or ${EditTool.Name} to apply the refactoring to 'src/auth.py']
Refactoring complete. Running verification...
[tool_call: ${ShellTool.Name} for 'ruff check src/auth.py && pytest']
(After verification passes)
All checks passed. This is a stable checkpoint.
${(function () {
if (isGitRepository(process.cwd())) {
return `Would you like me to write a commit message and commit these changes?`;
}
return '';
})()}
</example>
`;
} else {
return `
<example>
user: Refactor the auth logic in src/auth.py to use the requests library instead of urllib.
model: Okay, I can refactor 'src/auth.py'.
First, I'll analyze the code and check for a test safety net before planning any changes.
[tool_call: ${GlobTool.Name} for path 'tests/test_auth.py']
[tool_call: ${ReadFileTool.Name} for absolute_path '/path/to/tests/test_auth.py']
(After analysis)
Great, 'tests/test_auth.py' exists and covers the core authentication logic. With this safety net in place, I can safely plan the refactoring.
I'll also confirm 'requests' is a dependency.
[tool_call: ${ReadFileTool.Name} for absolute_path '/path/to/requirements.txt']
(After analysis)
Looks good, 'requests' is available.
Here's the plan:
1. Replace the 'urllib' calls with 'requests'.
2. Add proper 'try...except' error handling for the new network calls.
3. Remove the old 'urllib' import.
4. Run the project's linter and tests to verify the changes.
Should I proceed?
user: Yes
model:
[tool_call: ${WRITE_FILE_TOOL_NAME} or ${EditTool.Name} to apply the refactoring to 'src/auth.py']
Refactoring complete. Running verification...
[tool_call: ${ShellTool.Name} for 'ruff check src/auth.py && pytest']
(After verification passes)
All checks passed. This is a stable checkpoint.
${(function () {
if (isGitRepository(process.cwd())) {
return `Would you like me to write a commit message and commit these changes?`;
}
return '';
})()}
</example>
`;
}
})()}
<example>
user: Delete the temp directory.
model: I can run \`rm -rf /path/to/project/temp\`. This will permanently delete the directory and all its contents.
</example>
<example>
user: Write tests for someFile.ts
model:
Okay, I can write those tests. First, I'll read \`someFile.ts\` to understand its functionality.
[tool_call: ${ReadFileTool.Name} for absolute_path '/path/to/someFile.ts' or use ${GlobTool.Name} to find \`someFile.ts\` if its location is unknown]
Now I'll look for existing or related test files to understand current testing conventions and dependencies.
[tool_call: ${ReadManyFilesTool.Name} for paths ['**/*.test.ts', 'src/**/*.spec.ts'] assuming someFile.ts is in the src directory]
(After reviewing existing tests and the file content)
[tool_call: ${WRITE_FILE_TOOL_NAME} to create /path/to/someFile.test.ts with the test code]
I've written the tests. Now I'll run the project's test command to verify them.
[tool_call: ${ShellTool.Name} for 'npm run test']
</example>
${(function () {
if (enableCodebaseInvestigator) {
return `
<example>
user: How do I update the user's profile information in this system?
model:
I'm not immediately sure how user profile information is updated. I'll use the Codebase Investigator to find the relevant code and APIs.
[tool_call: ${CodebaseInvestigatorAgent.name} for query 'Find the code responsible for updating user profile information. Identify the relevant services, methods, and data transfer objects.']
(After reviewing the investigator's report, which highlights 'UserProfileService.java' and the 'updateUserProfile' method)
The investigator's report points to \`/path/to/UserProfileService.java\` as the key component. I'll read its content to get the specific details.
[tool_call: ${ReadFileTool.Name} for absolute_path '/path/to/UserProfileService.java']
(After reading the file)
It appears the \`updateUserProfile\` method in \`UserProfileService.java\` is responsible for this. It expects a user ID and a \`UserProfileDTO\` object...
</example>
`;
} else {
return `
<example>
user: How do I update the user's profile information in this system?
model:
I'm not immediately sure how user profile information is updated. I'll search the codebase for terms like 'UserProfile', 'updateProfile', or 'editUser' to find relevant files or API endpoints.
[tool_call: ${GrepTool.Name} for pattern 'UserProfile|updateProfile|editUser']
(After reviewing search results, assuming a relevant file like '/path/to/UserProfileService.java' was found)
Okay, \`/path/to/UserProfileService.java\` seems like the most relevant file. I'll read its content to understand how updates are handled.
[tool_call: ${ReadFileTool.Name} for absolute_path '/path/to/UserProfileService.java']
(After reading the file)
It appears the \`updateUserProfile\` method in \`UserProfileService.java\` is responsible for this. It expects a user ID and a \`UserProfileDTO\` object...
</example>
`;
}
})()}
<example>
user: Where are all the 'app.config' files in this project? I need to check their settings.
model:
[tool_call: ${GlobTool.Name} for pattern '**/app.config']
(Assuming GlobTool returns a list of paths like ['/path/to/moduleA/app.config', '/path/to/moduleB/app.config'])
I found the following 'app.config' files:
- /path/to/moduleA/app.config
- /path/to/moduleB/app.config
To help you check their settings, I can read their contents. Which one would you like to start with, or should I read all of them?
</example>
# Final Reminder
Your core function is efficient and safe assistance. Balance extreme conciseness with the crucial need for clarity, especially regarding safety and potential system modifications. Always prioritize user control and project conventions. Never make assumptions about the contents of files; instead use '${ReadFileTool.Name}' or '${ReadManyFilesTool.Name}' to ensure you aren't making broad assumptions. Finally, you are an agent - please keep going until the user's query is completely resolved.
`.trim();