@haven_ai/sdk 0.0.0-dev.202609061923.f3d53db → 0.0.0-dev.202609070908.bee3844

package/dist/index.cjs

@@ -4354,6 +4354,17 @@ Four of the six steps are your user's \u2014 each needs a human signature or a h
 5. **HUMAN \u2014 approve the budget** with their passkey, in the Haven tab they created the agent in: it advances to the approval step by itself once your run registers.
 6. **YOU \u2014 verify, then pay.**
 
+## Budget changes later (second token, raise, revoke)
+
+The first budget rides the setup above. After the agent exists, a CLI session can construct the LATER changes \u2014 a second token, a bigger amount, a recipient pin, a stop \u2014 and hand your user a link; the human still signs, every time:
+
+\`\`\`
+haven budget grant <agentId> --amount <n> --token USDC --period <minutes> [--recipient <address>] [--wait]
+haven budget revoke <agentId> <delegationHash> [--wait]
+\`\`\`
+
+The CLI never signs: it prints a dashboard link, your user opens it and signs with their passkey or wallet. \`--wait\` polls until the human's signature lands. The hash for \`revoke\` is in \`haven agents show <agentId>\`.
+
 ## Hand-off scripts
 
 Send these as your own message, \`<host>\` replaced by the host you fetched this file from. Say what you cannot do, not only what they must.