luulam/9router
1
0
Fork 0
Code Issues Pull Requests Actions Packages Projects Releases Wiki Activity

revert(qoder): drop the Responses usage plumbing from shared code

Browse Source 
The merged Qoder work also rewrote shared translator/handler code so that
/v1/responses clients got token usage on response.completed. That changed
behaviour for every provider, not just Qoder: proxies saw input tokens
rise by the 2000-token context buffer, and the plain token mapping was
replaced by one that always adds input_tokens_details.

A probe confirms the Qoder benefit does not depend on those edits: the
executor's coalescer already emits one include_usage-style finish chunk, so
a Claude client receives input_tokens and cache_read_input_tokens with
every shared file at its original state. Only the Responses path relies on
the shared translator, and that path has no Qoder-owned seam to put it in.

Reverts the shared files to their pre-PR state and drops the Responses
usage test. The Cline envelope unwrap in nonStreamingHandler.js, which
landed after the PR in the same file, is kept.
This commit is contained in:
LLL
2026-09-10 22:52:29 +07:00
parent 998bb3d975
commit 248d7da01c
9 changed files with 74 additions and 341 deletions
Download Patch File Download Diff File Expand all files Collapse all files

34
open-sse/translator/response/openai-responses.js
View File

@@ -5,7 +5,7 @@
import { register } from "../index.js";
import { FORMATS } from "../formats.js";
import { buildChunk } from "../concerns/chunk.js";
import { buildUsage, toResponsesUsage } from "../concerns/usage.js";
import { buildUsage } from "../concerns/usage.js";
import { fallbackToolCallId } from "../concerns/toolCall.js";
import { reasoningDelta, extractReasoningText } from "../concerns/reasoning.js";
import { ROLE, OPENAI_BLOCK, RESPONSES_ITEM, OPENAI_FINISH, MODEL_FALLBACK } from "../schema/index.js";
@@ -18,13 +18,7 @@ export function openaiToOpenAIResponsesResponse(chunk, state) {
if (!chunk) {
return flushEvents(state);
}
// Usage riding on the finish chunk (include_usage style, e.g. coalesced Qoder frames):
// remember it so response.completed can report tokens even outside stream.js.
if (chunk.usage && typeof chunk.usage === "object" && !state.usage) {
state.usage = chunk.usage;
}
if (!chunk.choices?.length) return [];
const events = [];
@@ -374,19 +368,17 @@ function closeToolCall(state, emit, idx) {
function sendCompleted(state, emit) {
if (!state.completedSent) {
state.completedSent = true;
const response = {
id: state.responseId,
object: "response",
created_at: state.created,
status: "completed",
background: false,
error: null
};
// Carry provider usage (recorded by stream.js or from the finish chunk itself) in the
// Responses shape; proxies such as sub2api/Codex read tokens only from here.
const usage = toResponsesUsage(state.usage);
if (usage) response.usage = usage;
emit("response.completed", { type: "response.completed", response });
emit("response.completed", {
type: "response.completed",
response: {
id: state.responseId,
object: "response",
created_at: state.created,
status: "completed",
background: false,
error: null
}
});
}
}