opensource/kilocode
3
0
Fork 0
mirror of https://github.com/Kilo-Org/kilocode.git synced 2026-09-24 16:02:55 +08:00
Code Issues Packages Projects Releases Wiki Activity

Merge pull request #6946 from Kilo-Org/docs/update-auto-model-frontier-sonnet-4.6

Browse Source 
docs: update Auto Model Frontier tier from Sonnet 4.5 to Sonnet 4.6
This commit is contained in:
Joshua Lambert
2026-03-12 08:29:46 -04:00
committed by GitHub
parent 652647b2ed e1edd0f793
commit 9a2b6e5cce
2 changed files with 10 additions and 10 deletions
Download Patch File Download Diff File Expand all files Collapse all files
packages/kilo-docs/pages/code-with-ai/agents/auto-model.md
+5 -5
View File
@@ -26,14 +26,14 @@ Auto Model routes to different models based on the task type:
| `ask` | Claude Opus 4.6 | Questions, explanations |
| `plan` | Claude Opus 4.6 | Planning, reasoning |
| `general` | Claude Opus 4.6 | General assistance |
| `code` | Claude Sonnet 4.5 | Writing and editing code |
| `build` | Claude Sonnet 4.5 | Implementation tasks |
| `debug` | Claude Sonnet 4.5 | Debugging and fixing issues |
| `explore` | Claude Sonnet 4.5 | Codebase exploration |
| `debug` | Claude Opus 4.6 | Debugging and fixing issues |
| `code` | Claude Sonnet 4.6 | Writing and editing code |
| `build` | Claude Sonnet 4.6 | Implementation tasks |
| `explore` | Claude Sonnet 4.6 | Codebase exploration |
**Planning and reasoning tasks** use Claude Opus 4.6, which excels at complex reasoning, architectural decisions, and breaking down problems.
**Implementation tasks** use Claude Sonnet 4.5, which is optimized for fast, accurate code generation and editing.
**Implementation tasks** use Claude Sonnet 4.6, which is optimized for fast, accurate code generation and editing.
## Benefits
packages/kilo-docs/pages/gateway/models-and-providers.md
+5 -5
View File
@@ -13,7 +13,7 @@ Models are identified using the format `provider/model-name`. Pass this as the `
```typescript
const result = streamText({
model: kilo.chat("anthropic/claude-sonnet-4.5"),
model: kilo.chat("anthropic/claude-sonnet-4.6"),
prompt: "Hello!",
})
```
@@ -22,7 +22,7 @@ Or in a raw API request:
```json
{
"model": "anthropic/claude-sonnet-4.5",
"model": "anthropic/claude-sonnet-4.6",
"messages": [{ "role": "user", "content": "Hello!" }]
}
```
@@ -42,7 +42,7 @@ This returns model information including pricing, context window, and supported
| Model ID | Provider | Description |
| ------------------------------- | --------- | ----------------------------------------------- |
| `anthropic/claude-opus-4.6` | Anthropic | Most capable Claude model for complex reasoning |
| `anthropic/claude-sonnet-4.5` | Anthropic | Balanced performance and cost |
| `anthropic/claude-sonnet-4.6` | Anthropic | Balanced performance and cost |
| `anthropic/claude-haiku-4.5` | Anthropic | Fast and cost-effective |
| `openai/gpt-5.2` | OpenAI | Latest GPT model |
| `google/gemini-3-pro-preview` | Google | Advanced reasoning with 1M context |
@@ -71,8 +71,8 @@ The `kilo-auto/frontier` virtual model automatically selects the best model base
| Mode | Resolved Model |
| -------------------------------------------------------------- | ----------------------------- |
| `plan`, `general`, `architect`, `orchestrator`, `ask`, `debug` | `anthropic/claude-opus-4.6` |
| `build`, `explore`, `code` | `anthropic/claude-sonnet-4.5` |
| Default (no mode specified) | `anthropic/claude-sonnet-4.5` |
| `build`, `explore`, `code` | `anthropic/claude-sonnet-4.6` |
| Default (no mode specified) | `anthropic/claude-sonnet-4.6` |
```json
{