MediaMetz/gemini-cli
1
0
Fork 0
mirror of https://github.com/google-gemini/gemini-cli.git synced 2026-03-18 10:01:29 -07:00
Code Issues Packages Projects Releases Wiki Activity

fix(patch): cherry-pick 3332703 to release/v0.12.0-preview.5-pr-12317 to patch version v0.12.0-preview.5 and create version 0.12.0-preview.6 (#12334)

Browse Source 
Co-authored-by: Tommaso Sciortino <sciortino@gmail.com>
This commit is contained in:
gemini-cli-robot
2025-10-30 18:58:03 -07:00
committed by GitHub
parent 2072d90ab2
commit fe44afe892
10 changed files with 41 additions and 109 deletions
Download Patch File Download Diff File Expand all files Collapse all files

15
docs/get-started/configuration-v1.md
View File

@@ -473,21 +473,6 @@ a few things you can try in order of recommendation:
"loadMemoryFromIncludeDirectories": true
```
- **`chatCompression`** (object):
- **Description:** Controls the settings for chat history compression, both
automatic and when manually invoked through the /compress command.
- **Properties:**
- **`contextPercentageThreshold`** (number): A value between 0 and 1 that
specifies the token threshold for compression as a percentage of the
model's total token limit. For example, a value of `0.6` will trigger
compression when the chat history exceeds 60% of the token limit.
- **Example:**
```json
"chatCompression": {
"contextPercentageThreshold": 0.6
}
```
- **`showLineNumbers`** (boolean):
- **Description:** Controls whether line numbers are displayed in code blocks
in the CLI output.

6
docs/get-started/configuration.md
View File

@@ -245,13 +245,13 @@ their corresponding top-level category object in your `settings.json` file.
example `{"run_shell_command": {"tokenBudget": 2000}}`
- **Default:** `undefined`
- **`model.chatCompression.contextPercentageThreshold`** (number):
- **`model.compressionThreshold`** (number):
- **Description:** Sets the threshold for chat history compression as a
percentage of the model's total token limit. This is a value between 0 and 1
fraction of the model's total token limit. This is a value between 0 and 1
that applies to both automatic compression and the manual `/compress`
command. For example, a value of `0.6` will trigger compression when the
chat history exceeds 60% of the token limit.
- **Default:** `0.7`
- **Default:** `0.2`
- **`model.skipNextSpeakerCheck`** (boolean):
- **Description:** Skip the next speaker check.