anthropic-messages: skip usage fields if empty (#6611)

fixes: #6567
This commit is contained in:
David Brailovsky
2026-07-13 18:07:59 +02:00
committed by GitHub
parent 1f0dbc008c
commit 0e6909f050
2 changed files with 49 additions and 19 deletions
+21 -19
View File
@@ -703,25 +703,27 @@ export const stream: StreamFunction<"anthropic-messages", AnthropicOptions> = (
} }
// Only update usage fields if present (not null). // Only update usage fields if present (not null).
// Preserves input_tokens from message_start when proxies omit it in message_delta. // Preserves input_tokens from message_start when proxies omit it in message_delta.
if (event.usage.input_tokens != null) { if (event.usage) {
output.usage.input = event.usage.input_tokens; if (event.usage.input_tokens != null) {
} output.usage.input = event.usage.input_tokens;
if (event.usage.output_tokens != null) { }
output.usage.output = event.usage.output_tokens; if (event.usage.output_tokens != null) {
} output.usage.output = event.usage.output_tokens;
if (event.usage.cache_read_input_tokens != null) { }
output.usage.cacheRead = event.usage.cache_read_input_tokens; if (event.usage.cache_read_input_tokens != null) {
} output.usage.cacheRead = event.usage.cache_read_input_tokens;
if (event.usage.cache_creation_input_tokens != null) { }
output.usage.cacheWrite = event.usage.cache_creation_input_tokens; if (event.usage.cache_creation_input_tokens != null) {
} output.usage.cacheWrite = event.usage.cache_creation_input_tokens;
// Anthropic reports reasoning tokens in `output_tokens_details.thinking_tokens` on the }
// final message_delta usage (a subset of output_tokens). SDK 0.91.1 omits the field from // Anthropic reports reasoning tokens in `output_tokens_details.thinking_tokens` on the
// its Usage type, so read it through a narrow cast. Verified against the live API. // final message_delta usage (a subset of output_tokens). SDK 0.91.1 omits the field from
const thinkingTokens = (event.usage as { output_tokens_details?: { thinking_tokens?: number } }) // its Usage type, so read it through a narrow cast. Verified against the live API.
.output_tokens_details?.thinking_tokens; const thinkingTokens = (event.usage as { output_tokens_details?: { thinking_tokens?: number } })
if (thinkingTokens != null) { .output_tokens_details?.thinking_tokens;
output.usage.reasoning = thinkingTokens; if (thinkingTokens != null) {
output.usage.reasoning = thinkingTokens;
}
} }
// Anthropic doesn't provide total_tokens, compute from components // Anthropic doesn't provide total_tokens, compute from components
output.usage.totalTokens = output.usage.totalTokens =
@@ -224,6 +224,34 @@ describe("Anthropic raw SSE parsing", () => {
expect(result.errorMessage).toBe(explanation); expect(result.errorMessage).toBe(explanation);
}); });
it("treats message_delta without usage as a no-op for usage accumulation", async () => {
const model = getModel("anthropic", "claude-haiku-4-5");
const context: Context = {
messages: [{ role: "user", content: "Say hello.", timestamp: Date.now() }],
};
const response = createSseResponse(
minimalAnthropicEvents.map((event) =>
event.event === "message_delta"
? {
event: "message_delta",
data: JSON.stringify({ type: "message_delta", delta: { stop_reason: "end_turn" } }),
}
: event,
),
);
const stream = streamAnthropic(model, context, {
client: createFakeAnthropicClient(response),
});
const result = await stream.result();
expect(result.stopReason).toBe("stop");
expect(result.errorMessage).toBeUndefined();
expect(result.content).toEqual([{ type: "text", text: "Hello" }]);
expect(result.usage.input).toBe(12);
expect(result.usage.totalTokens).toBe(12);
});
it("ignores unknown SSE events after message_stop", async () => { it("ignores unknown SSE events after message_stop", async () => {
const model = getModel("anthropic", "claude-haiku-4-5"); const model = getModel("anthropic", "claude-haiku-4-5");
const context: Context = { const context: Context = {