Skip to content
Merged
Show file tree
Hide file tree
Changes from all commits
Commits
File filter

Filter by extension

Filter by extension

Conversations
Failed to load comments.
Loading
Jump to
Jump to file
Failed to load files.
Loading
Diff view
Diff view
5 changes: 3 additions & 2 deletions src/node/services/compactionHandler.test.ts
Original file line number Diff line number Diff line change
Expand Up @@ -255,7 +255,7 @@ describe("CompactionHandler", () => {
model: "claude-3-5-sonnet-20241022",
usage,
duration: 2000,
providerMetadata: { foo: "bar" },
providerMetadata: { anthropic: { cacheCreationInputTokens: 50000 } },
systemMessageTokens: 100,
});
await handler.handleCompletion(event);
Expand All @@ -266,14 +266,15 @@ describe("CompactionHandler", () => {
});
expect(summaryEvent).toBeDefined();
const sevt = summaryEvent?.data.message as MuxMessage;
// providerMetadata is omitted to avoid inflating context with pre-compaction cacheCreationInputTokens
expect(sevt.metadata).toMatchObject({
model: "claude-3-5-sonnet-20241022",
usage,
duration: 2000,
providerMetadata: { foo: "bar" },
systemMessageTokens: 100,
compacted: true,
});
expect(sevt.metadata?.providerMetadata).toBeUndefined();
});

it("should emit stream-end event to frontend", async () => {
Expand Down
6 changes: 4 additions & 2 deletions src/node/services/compactionHandler.ts
Original file line number Diff line number Diff line change
Expand Up @@ -112,7 +112,10 @@ export class CompactionHandler {
}
const deletedSequences = clearResult.data;

// Create summary message with metadata
// Create summary message with metadata.
// We omit providerMetadata because it contains cacheCreationInputTokens from the
// pre-compaction context, which inflates context usage display. The historicalUsage
// field preserves full cost accounting from pre-compaction messages.
const summaryMessage = createMuxMessage(
`summary-${Date.now()}-${Math.random().toString(36).substring(2, 11)}`,
"assistant",
Expand All @@ -123,7 +126,6 @@ export class CompactionHandler {
model: metadata.model,
usage: metadata.usage,
historicalUsage,
providerMetadata: metadata.providerMetadata,
duration: metadata.duration,
systemMessageTokens: metadata.systemMessageTokens,
muxMetadata: { type: "normal" },
Expand Down