tkmind/tkmind_go
1
0
Fork 0
Code Issues Pull Requests Actions 4 Packages Projects Releases Wiki Activity

docs: max tokens config (#6596)

Browse Source
This commit is contained in:
dianed-square
2026-01-20 15:40:31 -08:00
committed by GitHub
parent 2f083b827a
commit 51cc5db387
2 changed files with 13 additions and 5 deletions
Download Patch File Download Diff File Expand all files Collapse all files
documentation/docs/guides/environment-variables.md
+8 -1
View File
@@ -19,14 +19,21 @@ These are the minimum required variables to get started with goose.
| `GOOSE_PROVIDER` | Specifies the LLM provider to use | [See available providers](/docs/getting-started/providers#available-providers) | None (must be [configured](/docs/getting-started/providers#configure-provider-and-model)) |
| `GOOSE_MODEL` | Specifies which model to use from the provider | Model name (e.g., "gpt-4", "claude-sonnet-4-20250514") | None (must be [configured](/docs/getting-started/providers#configure-provider-and-model)) |
| `GOOSE_TEMPERATURE` | Sets the [temperature](https://medium.com/@kelseyywang/a-comprehensive-guide-to-llm-temperature-%EF%B8%8F-363a40bbc91f) for model responses | Float between 0.0 and 1.0 | Model-specific default |
| `GOOSE_MAX_TOKENS` | Sets the maximum number of tokens for each model response (truncates longer responses) | Positive integer (e.g., 4096, 8192) | Model-specific default |
**Examples**
```bash
# Basic model configuration
export GOOSE_PROVIDER="anthropic"
export GOOSE_MODEL="claude-sonnet-4-20250514"
export GOOSE_MODEL="claude-sonnet-4-5-20250929"
export GOOSE_TEMPERATURE=0.7
# Set a lower limit for shorter interactions
export GOOSE_MAX_TOKENS=4096
# Set a higher limit for tasks requiring longer output (e.g. code generation)
export GOOSE_MAX_TOKENS=16000
```
### Advanced Provider Configuration