MediaMetz/gemini-cli
1
0
Fork 0
mirror of https://github.com/google-gemini/gemini-cli.git synced 2026-03-13 15:40:57 -07:00
Code Issues Packages Projects Releases Wiki Activity

Revert "Simplify prompt changes."

Browse Source 
This reverts commit 4e1fa84d75.
This commit is contained in:
Christian Gunderman
2026-01-28 18:19:57 -08:00
parent 3d38eeb0f4
commit 89b1a9abd7
2 changed files with 9 additions and 3 deletions
Download Patch File Download Diff File Expand all files Collapse all files

10
packages/core/src/prompts/snippets.ts
View File

@@ -135,6 +135,7 @@ export function renderCoreMandates(options?: CoreMandatesOptions): string {
return `
# Core Mandates
- **Context Efficiency:** Minimize context usage. Do not read entire files unless necessary. Use 'search_file_content' or 'read_file' with 'limit' to inspect large files.
- **Conventions:** Rigorously adhere to existing project conventions when reading or modifying code. Analyze surrounding code, tests, and configuration first.
- **Libraries/Frameworks:** NEVER assume a library/framework is available or appropriate. Verify its established usage within the project (check imports, configuration files like 'package.json', 'Cargo.toml', 'requirements.txt', 'build.gradle', etc., or observe neighboring files) before employing it.
- **Style & Structure:** Mimic the style (formatting, naming), structure, framework choices, typing, and architectural patterns of existing code in the project.
@@ -367,10 +368,15 @@ function mandateContinueWork(interactive: boolean): string {
function workflowStepUnderstand(options: PrimaryWorkflowsOptions): string {
if (options.enableCodebaseInvestigator) {
return `1. **Understand & Strategize:** Think about the user's request and the relevant codebase context. When the task involves **complex refactoring, codebase exploration or system-wide analysis**, your **first and primary action** must be to delegate to the 'codebase_investigator' agent using the 'codebase_investigator' tool. Use it to build a comprehensive understanding of the code, its structure, and dependencies. For **simple, targeted searches** (like finding a specific function name, file path, or variable declaration), you should use '${GREP_TOOL_NAME}' or '${GLOB_TOOL_NAME}' directly.`;
return `1. **Understand & Strategize:** Think about the user's request and the relevant codebase context. When the task involves **complex refactoring, codebase exploration or system-wide analysis**, your **first and primary action** must be to delegate to the 'codebase_investigator' agent using the 'codebase_investigator' tool. Use it to build a comprehensive understanding of the code, its structure, and dependencies. For **simple, targeted searches** (like finding a specific function name, file path, or variable declaration), you should use '${GREP_TOOL_NAME}' or '${GLOB_TOOL_NAME}' directly.
Use '${READ_FILE_TOOL_NAME}' to understand context and validate any assumptions you may have.
IMPORTANT: extra context consumed by unnecessarily reading entire files will degrade the quality of your answer, so **ALWAYS** use ranged reads if you know approximately which lines you need. For example, when fixing a linter error at line 50, read ~20 lines around it (offset: 40, limit: 20) to get sufficient context for a replacement.`;
}
return `1. **Understand:** Think about the user's request and the relevant codebase context. Use '${GREP_TOOL_NAME}' and '${GLOB_TOOL_NAME}' search tools extensively (in parallel if independent) to understand file structures, existing code patterns, and conventions.
Use '${READ_FILE_TOOL_NAME}' to understand context and validate any assumptions you may have. If you need to read multiple files, you should make multiple parallel calls to '${READ_FILE_TOOL_NAME}'.`;
Use '${READ_FILE_TOOL_NAME}' to understand context and validate any assumptions you may have. If you need to read multiple files, you should make multiple parallel calls to '${READ_FILE_TOOL_NAME}'.
Keep in mind the following as you explore:
- Search and/or read enough files to gain a thorough understanding of the problem.
- IMPORTANT: extra context consumed by unnecessarily reading entire files will degrade the quality of your answer, so **ALWAYS** use ranged reads if you know approximately which lines you need. For example, when fixing a linter error at line 50, read ~20 lines around it (offset: 40, limit: 20) to get sufficient context for a replacement.`;
}
function workflowStepPlan(options: PrimaryWorkflowsOptions): string {

2
packages/core/src/tools/edit.ts
View File

@@ -912,7 +912,7 @@ export class EditTool
super(
EditTool.Name,
'Edit',
`Replaces text within a file. By default, replaces a single occurrence, but can replace multiple occurrences when \`expected_replacements\` is specified. This tool requires providing significant context around the change to ensure precise targeting. Always use the ${READ_FILE_TOOL_NAME} tool (using 'offset' and 'limit' to get at least 50 lines of context around the match) to examine the file's current content before attempting a text replacement.
`Replaces text within a file. By default, replaces a single occurrence, but can replace multiple occurrences when \`expected_replacements\` is specified. This tool requires providing significant context around the change to ensure precise targeting. Always use the ${READ_FILE_TOOL_NAME} tool (using 'offset' and 'limit' to get ~20 lines of context around the match) to examine the file's current content before attempting a text replacement.
The user has the ability to modify the \`new_string\` content. If modified, this will be stated in the response.