allow using /context command (#268)

I experimented with https://agentclientprotocol.com/rfds/session-usage
(see
https://github.com/agentclientprotocol/agent-client-protocol/pull/415),
but the Claude Agent SDK does not seem to return the information we need
for an accurate context indicator. For example, one request to explore a
project returned 500k+ cached read tokens in Claude's `result` message,
while the agent reported 64k tokens used. I can open a PR with those
changes for reference once the Typescript SDK is updated.

To allow users to still see the current context usage, allowing to run
`/context` seems to be the second best option. This PR changes the code
to handle the `<local-command-stdout>` message that the SDK generates
when sending `/context` and includes `/context` as allowed command.

Screenshot from Tidewave with this change:

<img width="460" height="1079" alt="image"
src="https://github.com/user-attachments/assets/a3796e46-4014-4988-a993-e13d38d38d96"
/>
This commit is contained in:
Steffen Deusch
2026-01-29 16:34:39 +01:00
committed by GitHub
parent 32898580a5
commit 11ca660dec

View File

@@ -350,6 +350,21 @@ export class ClaudeAcpAgent implements Agent {
typeof message.message.content === "string" &&
message.message.content.includes("<local-command-stdout>")
) {
// Handle /context by sending its reply as regular agent message.
if (message.message.content.includes("Context Usage")) {
for (const notification of toAcpNotifications(
message.message.content
.replace("<local-command-stdout>", "")
.replace("</local-command-stdout>", ""),
"assistant",
params.sessionId,
this.toolUseCache,
this.client,
this.logger,
)) {
await this.client.sessionUpdate(notification);
}
}
this.logger.log(message.message.content);
break;
}
@@ -872,7 +887,6 @@ async function getAvailableModels(query: Query): Promise<SessionModelState> {
async function getAvailableSlashCommands(query: Query): Promise<AvailableCommand[]> {
const UNSUPPORTED_COMMANDS = [
"context",
"cost",
"login",
"logout",