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

fix(kiro): report real output tokens and stop discarding usable turns

Browse Source
This commit is contained in:
nguyenha935
2026-08-13 11:32:09 +07:00
committed by decolua
parent 456f2a2635
commit b44bb09f72
5 changed files with 495 additions and 30 deletions
Download Patch File Download Diff File Expand all files Collapse all files

12
open-sse/translator/request/claude-to-kiro.js
View File

@@ -287,6 +287,18 @@ export function claudeToKiroRequest(model, body, stream, credentials) {
toolSpecs,
nameMap,
});
// canonicalizeKiroConversation() already ran its second-chance repair (flatten
// every structured tool turn to text, then re-validate). A body that is STILL
// invalid here cannot be made shippable, and Kiro answers it with
// 400 {"message":"Improperly formed request.","reason":"REQUEST_BODY_INVALID"}.
// Fail locally instead: chatCore turns a falsy return into a 400 without
// spending an upstream call or a per-account cooldown. The taxonomy
// (role:N | pair:N | id:N | spec:N | orphan:0 | current) names the offending
// turn so the shape can be diagnosed from the log alone.
if (!canonical.valid) {
console.error(`[Kiro] refusing invalid conversation (claude → kiro): ${(canonical.errors || []).join(", ") || "unknown"} | turns=${(canonical.history || []).length + 1}`);
return null;
}
const replayCurrent = canonical.currentMessage.userInputMessage;
const userInputMessage = {
content: replayCurrent.content || "",

12
open-sse/translator/request/openai-to-kiro.js
View File

@@ -379,6 +379,18 @@ export function openaiToKiroRequest(model, body, stream, credentials) {
toolSpecs,
nameMap,
});
// canonicalizeKiroConversation() already ran its second-chance repair (flatten
// every structured tool turn to text, then re-validate). A body that is STILL
// invalid here cannot be made shippable, and Kiro answers it with
// 400 {"message":"Improperly formed request.","reason":"REQUEST_BODY_INVALID"}.
// Fail locally instead: chatCore turns a falsy return into a 400 without
// spending an upstream call or a per-account cooldown. The taxonomy
// (role:N | pair:N | id:N | spec:N | orphan:0 | current) names the offending
// turn so the shape can be diagnosed from the log alone.
if (!canonical.valid) {
console.error(`[Kiro] refusing invalid conversation (openai → kiro): ${(canonical.errors || []).join(", ") || "unknown"} | turns=${(canonical.history || []).length + 1}`);
return null;
}
const replayCurrent = canonical.currentMessage.userInputMessage;
const payload = {

16
open-sse/translator/response/kiro-to-claude.js
View File

@@ -75,6 +75,15 @@ export function kiroToClaudeResponse(chunk, state) {
? data.usage.completion_tokens
: 0;
state.usage = { input_tokens: promptTokens, output_tokens: outputTokens };
// Claude clients read cache_read/cache_creation to price a turn and to size
// their prompt cache. Both spellings are accepted because the Kiro executor
// emits the Chat shape and passthrough responses use the nested details form.
const cacheRead = data.usage.cache_read_input_tokens
?? data.usage.prompt_tokens_details?.cached_tokens;
const cacheCreation = data.usage.cache_creation_input_tokens
?? data.usage.prompt_tokens_details?.cache_creation_tokens;
if (typeof cacheRead === "number") state.usage.cache_read_input_tokens = cacheRead;
if (typeof cacheCreation === "number") state.usage.cache_creation_input_tokens = cacheCreation;
}
// First chunk → emit message_start.
@@ -254,6 +263,13 @@ export function kiroToClaudeNonStreaming(data) {
usage: {
input_tokens: usage.prompt_tokens || 0,
output_tokens: usage.completion_tokens || 0,
// Same cache preservation as the streaming path above.
...(typeof (usage.cache_read_input_tokens ?? usage.prompt_tokens_details?.cached_tokens) === "number"
? { cache_read_input_tokens: usage.cache_read_input_tokens ?? usage.prompt_tokens_details.cached_tokens }
: {}),
...(typeof (usage.cache_creation_input_tokens ?? usage.prompt_tokens_details?.cache_creation_tokens) === "number"
? { cache_creation_input_tokens: usage.cache_creation_input_tokens ?? usage.prompt_tokens_details.cache_creation_tokens }
: {}),
},
};
}