agent-lattice 0.17.0 → 0.17.1
This diff represents the content of publicly available package versions that have been released to one of the supported registries. The information contained in this diff is provided for informational purposes only and reflects changes between package versions as they appear in their respective public registries.
- package/README.md +7 -1
- package/dist/index.js +7 -7
- package/package.json +1 -1
package/README.md
CHANGED
|
@@ -140,10 +140,16 @@ const result = await agent.prompt("Solve this carefully.", {
|
|
|
140
140
|
|
|
141
141
|
Use `{ type: "adaptive" }` for models that support adaptive thinking. Use
|
|
142
142
|
`{ type: "enabled", budgetTokens }` for models that require a fixed budget, or
|
|
143
|
-
`{ type: "disabled" }` to
|
|
143
|
+
`{ type: "disabled" }` to turn thinking off. A fixed
|
|
144
144
|
budget is capped at `maxTokens - 1` to satisfy the Anthropic API constraint.
|
|
145
145
|
When omitted, the SDK does not send a thinking configuration.
|
|
146
146
|
|
|
147
|
+
`{ type: "disabled" }` is sent to the provider explicitly as
|
|
148
|
+
`thinking: { "type": "disabled" }` rather than omitted, because some
|
|
149
|
+
Anthropic-compatible providers (for example DeepSeek's
|
|
150
|
+
`https://api.deepseek.com/anthropic` endpoint) default thinking to on —
|
|
151
|
+
omitting the field would leave it enabled.
|
|
152
|
+
|
|
147
153
|
For Kimi K3 through an Anthropic-compatible endpoint or gateway, use
|
|
148
154
|
`reasoningEffort` to send the provider's top-level `reasoning_effort` parameter:
|
|
149
155
|
|