feat(core): steer model to use edit tool for surgical edits, fix a typo (#26480)

2026-05-13 21:32:56 -07:00 · 2026-05-05 15:35:04 -04:00
parent 0803007c8f
commit 0218817fe3
4 changed files with 24 additions and 24 deletions
@@ -26,7 +26,7 @@ Use the following guidelines to optimize your search and read patterns.
 - Prefer using tools like grep_search to identify points of interest instead of reading lots of files individually.
 - If you need to read multiple ranges in a file, do so parallel, in as few turns as possible.
 - It is more important to reduce extra turns, but please also try to minimize unnecessarily large file reads and search results, when doing so doesn't result in extra turns. Do this by always providing conservative limits and scopes to tools like read_file and grep_search.
- read_file fails if old_string is ambiguous, causing extra turns. Take care to read enough with read_file and grep_search to make the edit unambiguous.
+- replace fails if old_string is ambiguous, causing extra turns. Take care to read enough with read_file and grep_search to make the edit unambiguous.
 - You can compensate for the risk of missing results with scoped or limited searches by doing multiple searches in parallel.
 - Your primary goal is still to do your best quality work. Efficiency is an important, but secondary concern.
 </guidelines>
@@ -206,7 +206,7 @@ Use the following guidelines to optimize your search and read patterns.
 - Prefer using tools like grep_search to identify points of interest instead of reading lots of files individually.
 - If you need to read multiple ranges in a file, do so parallel, in as few turns as possible.
 - It is more important to reduce extra turns, but please also try to minimize unnecessarily large file reads and search results, when doing so doesn't result in extra turns. Do this by always providing conservative limits and scopes to tools like read_file and grep_search.
- read_file fails if old_string is ambiguous, causing extra turns. Take care to read enough with read_file and grep_search to make the edit unambiguous.
+- replace fails if old_string is ambiguous, causing extra turns. Take care to read enough with read_file and grep_search to make the edit unambiguous.
 - You can compensate for the risk of missing results with scoped or limited searches by doing multiple searches in parallel.
 - Your primary goal is still to do your best quality work. Efficiency is an important, but secondary concern.
 </guidelines>
@@ -507,7 +507,7 @@ Use the following guidelines to optimize your search and read patterns.
 - Prefer using tools like grep_search to identify points of interest instead of reading lots of files individually.
 - If you need to read multiple ranges in a file, do so parallel, in as few turns as possible.
 - It is more important to reduce extra turns, but please also try to minimize unnecessarily large file reads and search results, when doing so doesn't result in extra turns. Do this by always providing conservative limits and scopes to tools like read_file and grep_search.
- read_file fails if old_string is ambiguous, causing extra turns. Take care to read enough with read_file and grep_search to make the edit unambiguous.
+- replace fails if old_string is ambiguous, causing extra turns. Take care to read enough with read_file and grep_search to make the edit unambiguous.
 - You can compensate for the risk of missing results with scoped or limited searches by doing multiple searches in parallel.
 - Your primary goal is still to do your best quality work. Efficiency is an important, but secondary concern.
 </guidelines>
@@ -687,7 +687,7 @@ Use the following guidelines to optimize your search and read patterns.
 - Prefer using tools like grep_search to identify points of interest instead of reading lots of files individually.
 - If you need to read multiple ranges in a file, do so parallel, in as few turns as possible.
 - It is more important to reduce extra turns, but please also try to minimize unnecessarily large file reads and search results, when doing so doesn't result in extra turns. Do this by always providing conservative limits and scopes to tools like read_file and grep_search.
- read_file fails if old_string is ambiguous, causing extra turns. Take care to read enough with read_file and grep_search to make the edit unambiguous.
+- replace fails if old_string is ambiguous, causing extra turns. Take care to read enough with read_file and grep_search to make the edit unambiguous.
 - You can compensate for the risk of missing results with scoped or limited searches by doing multiple searches in parallel.
 - Your primary goal is still to do your best quality work. Efficiency is an important, but secondary concern.
 </guidelines>
@@ -868,7 +868,7 @@ Use the following guidelines to optimize your search and read patterns.
 - Prefer using tools like grep_search to identify points of interest instead of reading lots of files individually.
 - If you need to read multiple ranges in a file, do so parallel, in as few turns as possible.
 - It is more important to reduce extra turns, but please also try to minimize unnecessarily large file reads and search results, when doing so doesn't result in extra turns. Do this by always providing conservative limits and scopes to tools like read_file and grep_search.
- read_file fails if old_string is ambiguous, causing extra turns. Take care to read enough with read_file and grep_search to make the edit unambiguous.
+- replace fails if old_string is ambiguous, causing extra turns. Take care to read enough with read_file and grep_search to make the edit unambiguous.
 - You can compensate for the risk of missing results with scoped or limited searches by doing multiple searches in parallel.
 - Your primary goal is still to do your best quality work. Efficiency is an important, but secondary concern.
 </guidelines>
@@ -1001,7 +1001,7 @@ Use the following guidelines to optimize your search and read patterns.
 - Prefer using tools like grep_search to identify points of interest instead of reading lots of files individually.
 - If you need to read multiple ranges in a file, do so parallel, in as few turns as possible.
 - It is more important to reduce extra turns, but please also try to minimize unnecessarily large file reads and search results, when doing so doesn't result in extra turns. Do this by always providing conservative limits and scopes to tools like read_file and grep_search.
- read_file fails if old_string is ambiguous, causing extra turns. Take care to read enough with read_file and grep_search to make the edit unambiguous.
+- replace fails if old_string is ambiguous, causing extra turns. Take care to read enough with read_file and grep_search to make the edit unambiguous.
 - You can compensate for the risk of missing results with scoped or limited searches by doing multiple searches in parallel.
 - Your primary goal is still to do your best quality work. Efficiency is an important, but secondary concern.
 </guidelines>
@@ -1616,7 +1616,7 @@ Use the following guidelines to optimize your search and read patterns.
 - Prefer using tools like grep_search to identify points of interest instead of reading lots of files individually.
 - If you need to read multiple ranges in a file, do so parallel, in as few turns as possible.
 - It is more important to reduce extra turns, but please also try to minimize unnecessarily large file reads and search results, when doing so doesn't result in extra turns. Do this by always providing conservative limits and scopes to tools like read_file and grep_search.
- read_file fails if old_string is ambiguous, causing extra turns. Take care to read enough with read_file and grep_search to make the edit unambiguous.
+- replace fails if old_string is ambiguous, causing extra turns. Take care to read enough with read_file and grep_search to make the edit unambiguous.
 - You can compensate for the risk of missing results with scoped or limited searches by doing multiple searches in parallel.
 - Your primary goal is still to do your best quality work. Efficiency is an important, but secondary concern.
 </guidelines>
@@ -1793,7 +1793,7 @@ Use the following guidelines to optimize your search and read patterns.
 - Prefer using tools like grep_search to identify points of interest instead of reading lots of files individually.
 - If you need to read multiple ranges in a file, do so parallel, in as few turns as possible.
 - It is more important to reduce extra turns, but please also try to minimize unnecessarily large file reads and search results, when doing so doesn't result in extra turns. Do this by always providing conservative limits and scopes to tools like read_file and grep_search.
- read_file fails if old_string is ambiguous, causing extra turns. Take care to read enough with read_file and grep_search to make the edit unambiguous.
+- replace fails if old_string is ambiguous, causing extra turns. Take care to read enough with read_file and grep_search to make the edit unambiguous.
 - You can compensate for the risk of missing results with scoped or limited searches by doing multiple searches in parallel.
 - Your primary goal is still to do your best quality work. Efficiency is an important, but secondary concern.
 </guidelines>
@@ -1961,7 +1961,7 @@ Use the following guidelines to optimize your search and read patterns.
 - Prefer using tools like grep_search to identify points of interest instead of reading lots of files individually.
 - If you need to read multiple ranges in a file, do so parallel, in as few turns as possible.
 - It is more important to reduce extra turns, but please also try to minimize unnecessarily large file reads and search results, when doing so doesn't result in extra turns. Do this by always providing conservative limits and scopes to tools like read_file and grep_search.
- read_file fails if old_string is ambiguous, causing extra turns. Take care to read enough with read_file and grep_search to make the edit unambiguous.
+- replace fails if old_string is ambiguous, causing extra turns. Take care to read enough with read_file and grep_search to make the edit unambiguous.
 - You can compensate for the risk of missing results with scoped or limited searches by doing multiple searches in parallel.
 - Your primary goal is still to do your best quality work. Efficiency is an important, but secondary concern.
 </guidelines>
@@ -2129,7 +2129,7 @@ Use the following guidelines to optimize your search and read patterns.
 - Prefer using tools like grep_search to identify points of interest instead of reading lots of files individually.
 - If you need to read multiple ranges in a file, do so parallel, in as few turns as possible.
 - It is more important to reduce extra turns, but please also try to minimize unnecessarily large file reads and search results, when doing so doesn't result in extra turns. Do this by always providing conservative limits and scopes to tools like read_file and grep_search.
- read_file fails if old_string is ambiguous, causing extra turns. Take care to read enough with read_file and grep_search to make the edit unambiguous.
+- replace fails if old_string is ambiguous, causing extra turns. Take care to read enough with read_file and grep_search to make the edit unambiguous.
 - You can compensate for the risk of missing results with scoped or limited searches by doing multiple searches in parallel.
 - Your primary goal is still to do your best quality work. Efficiency is an important, but secondary concern.
 </guidelines>
@@ -2293,7 +2293,7 @@ Use the following guidelines to optimize your search and read patterns.
 - Prefer using tools like grep_search to identify points of interest instead of reading lots of files individually.
 - If you need to read multiple ranges in a file, do so parallel, in as few turns as possible.
 - It is more important to reduce extra turns, but please also try to minimize unnecessarily large file reads and search results, when doing so doesn't result in extra turns. Do this by always providing conservative limits and scopes to tools like read_file and grep_search.
- read_file fails if old_string is ambiguous, causing extra turns. Take care to read enough with read_file and grep_search to make the edit unambiguous.
+- replace fails if old_string is ambiguous, causing extra turns. Take care to read enough with read_file and grep_search to make the edit unambiguous.
 - You can compensate for the risk of missing results with scoped or limited searches by doing multiple searches in parallel.
 - Your primary goal is still to do your best quality work. Efficiency is an important, but secondary concern.
 </guidelines>
@@ -2457,7 +2457,7 @@ Use the following guidelines to optimize your search and read patterns.
 - Prefer using tools like grep_search to identify points of interest instead of reading lots of files individually.
 - If you need to read multiple ranges in a file, do so parallel, in as few turns as possible.
 - It is more important to reduce extra turns, but please also try to minimize unnecessarily large file reads and search results, when doing so doesn't result in extra turns. Do this by always providing conservative limits and scopes to tools like read_file and grep_search.
- read_file fails if old_string is ambiguous, causing extra turns. Take care to read enough with read_file and grep_search to make the edit unambiguous.
+- replace fails if old_string is ambiguous, causing extra turns. Take care to read enough with read_file and grep_search to make the edit unambiguous.
 - You can compensate for the risk of missing results with scoped or limited searches by doing multiple searches in parallel.
 - Your primary goal is still to do your best quality work. Efficiency is an important, but secondary concern.
 </guidelines>
@@ -2615,7 +2615,7 @@ Use the following guidelines to optimize your search and read patterns.
 - Prefer using tools like grep_search to identify points of interest instead of reading lots of files individually.
 - If you need to read multiple ranges in a file, do so parallel, in as few turns as possible.
 - It is more important to reduce extra turns, but please also try to minimize unnecessarily large file reads and search results, when doing so doesn't result in extra turns. Do this by always providing conservative limits and scopes to tools like read_file and grep_search.
- read_file fails if old_string is ambiguous, causing extra turns. Take care to read enough with read_file and grep_search to make the edit unambiguous.
+- replace fails if old_string is ambiguous, causing extra turns. Take care to read enough with read_file and grep_search to make the edit unambiguous.
 - You can compensate for the risk of missing results with scoped or limited searches by doing multiple searches in parallel.
 - Your primary goal is still to do your best quality work. Efficiency is an important, but secondary concern.
 </guidelines>
@@ -2747,7 +2747,7 @@ Use the following guidelines to optimize your search and read patterns.
 - Prefer using tools like grep_search to identify points of interest instead of reading lots of files individually.
 - If you need to read multiple ranges in a file, do so parallel, in as few turns as possible.
 - It is more important to reduce extra turns, but please also try to minimize unnecessarily large file reads and search results, when doing so doesn't result in extra turns. Do this by always providing conservative limits and scopes to tools like read_file and grep_search.
- read_file fails if old_string is ambiguous, causing extra turns. Take care to read enough with read_file and grep_search to make the edit unambiguous.
+- replace fails if old_string is ambiguous, causing extra turns. Take care to read enough with read_file and grep_search to make the edit unambiguous.
 - You can compensate for the risk of missing results with scoped or limited searches by doing multiple searches in parallel.
 - Your primary goal is still to do your best quality work. Efficiency is an important, but secondary concern.
 </guidelines>
@@ -3039,7 +3039,7 @@ Use the following guidelines to optimize your search and read patterns.
 - Prefer using tools like grep_search to identify points of interest instead of reading lots of files individually.
 - If you need to read multiple ranges in a file, do so parallel, in as few turns as possible.
 - It is more important to reduce extra turns, but please also try to minimize unnecessarily large file reads and search results, when doing so doesn't result in extra turns. Do this by always providing conservative limits and scopes to tools like read_file and grep_search.
- read_file fails if old_string is ambiguous, causing extra turns. Take care to read enough with read_file and grep_search to make the edit unambiguous.
+- replace fails if old_string is ambiguous, causing extra turns. Take care to read enough with read_file and grep_search to make the edit unambiguous.
 - You can compensate for the risk of missing results with scoped or limited searches by doing multiple searches in parallel.
 - Your primary goal is still to do your best quality work. Efficiency is an important, but secondary concern.
 </guidelines>
@@ -3461,7 +3461,7 @@ Use the following guidelines to optimize your search and read patterns.
 - Prefer using tools like grep_search to identify points of interest instead of reading lots of files individually.
 - If you need to read multiple ranges in a file, do so parallel, in as few turns as possible.
 - It is more important to reduce extra turns, but please also try to minimize unnecessarily large file reads and search results, when doing so doesn't result in extra turns. Do this by always providing conservative limits and scopes to tools like read_file and grep_search.
- read_file fails if old_string is ambiguous, causing extra turns. Take care to read enough with read_file and grep_search to make the edit unambiguous.
+- replace fails if old_string is ambiguous, causing extra turns. Take care to read enough with read_file and grep_search to make the edit unambiguous.
 - You can compensate for the risk of missing results with scoped or limited searches by doing multiple searches in parallel.
 - Your primary goal is still to do your best quality work. Efficiency is an important, but secondary concern.
 </guidelines>
@@ -3625,7 +3625,7 @@ Use the following guidelines to optimize your search and read patterns.
 - Prefer using tools like grep_search to identify points of interest instead of reading lots of files individually.
 - If you need to read multiple ranges in a file, do so parallel, in as few turns as possible.
 - It is more important to reduce extra turns, but please also try to minimize unnecessarily large file reads and search results, when doing so doesn't result in extra turns. Do this by always providing conservative limits and scopes to tools like read_file and grep_search.
- read_file fails if old_string is ambiguous, causing extra turns. Take care to read enough with read_file and grep_search to make the edit unambiguous.
+- replace fails if old_string is ambiguous, causing extra turns. Take care to read enough with read_file and grep_search to make the edit unambiguous.
 - You can compensate for the risk of missing results with scoped or limited searches by doing multiple searches in parallel.
 - Your primary goal is still to do your best quality work. Efficiency is an important, but secondary concern.
 </guidelines>
@@ -3903,7 +3903,7 @@ Use the following guidelines to optimize your search and read patterns.
 - Prefer using tools like grep_search to identify points of interest instead of reading lots of files individually.
 - If you need to read multiple ranges in a file, do so parallel, in as few turns as possible.
 - It is more important to reduce extra turns, but please also try to minimize unnecessarily large file reads and search results, when doing so doesn't result in extra turns. Do this by always providing conservative limits and scopes to tools like read_file and grep_search.
- read_file fails if old_string is ambiguous, causing extra turns. Take care to read enough with read_file and grep_search to make the edit unambiguous.
+- replace fails if old_string is ambiguous, causing extra turns. Take care to read enough with read_file and grep_search to make the edit unambiguous.
 - You can compensate for the risk of missing results with scoped or limited searches by doing multiple searches in parallel.
 - Your primary goal is still to do your best quality work. Efficiency is an important, but secondary concern.
 </guidelines>
@@ -4067,7 +4067,7 @@ Use the following guidelines to optimize your search and read patterns.
 - Prefer using tools like grep_search to identify points of interest instead of reading lots of files individually.
 - If you need to read multiple ranges in a file, do so parallel, in as few turns as possible.
 - It is more important to reduce extra turns, but please also try to minimize unnecessarily large file reads and search results, when doing so doesn't result in extra turns. Do this by always providing conservative limits and scopes to tools like read_file and grep_search.
- read_file fails if old_string is ambiguous, causing extra turns. Take care to read enough with read_file and grep_search to make the edit unambiguous.
+- replace fails if old_string is ambiguous, causing extra turns. Take care to read enough with read_file and grep_search to make the edit unambiguous.
 - You can compensate for the risk of missing results with scoped or limited searches by doing multiple searches in parallel.
 - Your primary goal is still to do your best quality work. Efficiency is an important, but secondary concern.
 </guidelines>
@@ -242,7 +242,7 @@ Use the following guidelines to optimize your search and read patterns.
 - Prefer using tools like ${GREP_TOOL_NAME} to identify points of interest instead of reading lots of files individually.
 - If you need to read multiple ranges in a file, do so parallel, in as few turns as possible.
 - It is more important to reduce extra turns, but please also try to minimize unnecessarily large file reads and search results, when doing so doesn't result in extra turns. Do this by always providing conservative limits and scopes to tools like ${READ_FILE_TOOL_NAME} and ${GREP_TOOL_NAME}.
- ${READ_FILE_TOOL_NAME} fails if ${EDIT_PARAM_OLD_STRING} is ambiguous, causing extra turns. Take care to read enough with ${READ_FILE_TOOL_NAME} and ${GREP_TOOL_NAME} to make the edit unambiguous.
+- ${EDIT_TOOL_NAME} fails if ${EDIT_PARAM_OLD_STRING} is ambiguous, causing extra turns. Take care to read enough with ${READ_FILE_TOOL_NAME} and ${GREP_TOOL_NAME} to make the edit unambiguous.
 - You can compensate for the risk of missing results with scoped or limited searches by doing multiple searches in parallel.
 - Your primary goal is still to do your best quality work. Efficiency is an important, but secondary concern.
 </guidelines>
@@ -1333,7 +1333,7 @@ Use this tool when the user's query implies needing the content of several files

 exports[`coreTools snapshots for specific models > Model: gemini-3-pro-preview > snapshot for tool: replace 1`] = `
 {
-  "description": "Replaces text within a file. By default, the tool expects to find and replace exactly ONE occurrence of \`old_string\`. If you want to replace multiple occurrences of the exact same string, set \`allow_multiple\` to true. This tool requires providing significant context around the change to ensure precise targeting.
+  "description": "Replaces text within a file. By default, the tool expects to find and replace exactly ONE occurrence of \`old_string\`. If you want to replace multiple occurrences of the exact same string, set \`allow_multiple\` to true. This tool is preferred for surgical edits to existing files as it minimizes token usage, simplifies code reviews, and avoids accidental deletions. This tool requires providing significant context around the change to ensure precise targeting.
 The user has the ability to modify the \`new_string\` content. If modified, this will be stated in the response.",
  "name": "replace",
  "parametersJsonSchema": {
@@ -1496,7 +1496,7 @@ exports[`coreTools snapshots for specific models > Model: gemini-3-pro-preview >

 exports[`coreTools snapshots for specific models > Model: gemini-3-pro-preview > snapshot for tool: write_file 1`] = `
 {
-  "description": "Writes the complete content to a file, automatically creating missing parent directories. Overwrites existing files. The user has the ability to modify 'content' before it is saved. Best for new or small files; use 'replace' for targeted edits to large files.",
+  "description": "Writes the complete content to a file, automatically creating missing parent directories. Overwrites existing files. The user has the ability to modify 'content' before it is saved. Best for new or small files; use 'replace' for targeted edits to large files to minimize token usage and simplify reviews.",
  "name": "write_file",
  "parametersJsonSchema": {
    "properties": {
@@ -120,7 +120,7 @@ export const GEMINI_3_SET: CoreToolSet = {

  write_file: {
    name: WRITE_FILE_TOOL_NAME,
-    description: `Writes the complete content to a file, automatically creating missing parent directories. Overwrites existing files. The user has the ability to modify 'content' before it is saved. Best for new or small files; use '${EDIT_TOOL_NAME}' for targeted edits to large files.`,
+    description: `Writes the complete content to a file, automatically creating missing parent directories. Overwrites existing files. The user has the ability to modify 'content' before it is saved. Best for new or small files; use '${EDIT_TOOL_NAME}' for targeted edits to large files to minimize token usage and simplify reviews.`,
    parametersJsonSchema: {
      type: 'object',
      properties: {
@@ -355,7 +355,7 @@ export const GEMINI_3_SET: CoreToolSet = {

  replace: {
    name: EDIT_TOOL_NAME,
-    description: `Replaces text within a file. By default, the tool expects to find and replace exactly ONE occurrence of \`old_string\`. If you want to replace multiple occurrences of the exact same string, set \`allow_multiple\` to true. This tool requires providing significant context around the change to ensure precise targeting.
+    description: `Replaces text within a file. By default, the tool expects to find and replace exactly ONE occurrence of \`old_string\`. If you want to replace multiple occurrences of the exact same string, set \`allow_multiple\` to true. This tool is preferred for surgical edits to existing files as it minimizes token usage, simplifies code reviews, and avoids accidental deletions. This tool requires providing significant context around the change to ensure precise targeting.
 The user has the ability to modify the \`new_string\` content. If modified, this will be stated in the response.`,
    parametersJsonSchema: {
      type: 'object',