IEatCodeDaily e7dd72a8d7 fix(usage): read Responses-shape cached_tokens in extractUsageFromResponse ...

Non-streaming codex traffic recorded cached_tokens: 0 even when upstream
prompt caching worked. The Claude-format branch (which OpenAI Responses
usage also matches) never read input_tokens_details, and the OpenAI
branch ignored a top-level flat cached_tokens. Read both in both
branches; Responses prompts are cache-inclusive so canonicalizeUsage
passes the value through without folding. 5 new regression tests.

2026-09-03 09:48:19 +07:00

..

config

fix(opencode): route Muse Spark models to Responses API and declare vision

2026-09-03 09:24:18 +07:00

executors

fix(opencode): route Muse Spark models to Responses API and declare vision

2026-09-03 09:24:18 +07:00

handlers

fix(usage): read Responses-shape cached_tokens in extractUsageFromResponse

2026-09-03 09:48:19 +07:00

providers

feat(codebuddy-cn): refresh model catalog — add hy4-preview/hy3/glm-5.3/kimi-k3, drop EOL glm-5.0/glm-4.7

2026-09-03 09:41:02 +07:00

rtk

feat(headroom): make the compression request timeout configurable

2026-08-28 16:34:33 +07:00

services

feat(antigravity,gemini): add Gemini 3.8 Flash support and bump IDE fingerprint to 2.11.0

2026-09-03 09:13:45 +07:00

shared

feat(usage): show Zed plan quota on the dashboard

2026-08-28 16:16:01 +07:00

transformer

fix(codex): harden streaming timeouts + Responses terminal events

2026-06-06 16:07:43 +07:00

translator

fix(translator): route Gemini thinking through reasoning_effort on OpenAI-compatible wire

2026-09-03 09:12:34 +07:00

utils

fix(claude): support Fable 5.1

2026-09-02 20:42:53 +07:00

.npmignore

Update jsconfig.json and package.json to correct open-sse path references from relative to local directory.

2026-01-05 10:37:09 +07:00

AGENTS.md

feat(headroom): add proxy lifecycle management + dashboard UI

2026-06-20 10:09:50 +07:00

index.js

fix(providers): remove Qwen provider support

2026-08-05 16:17:26 +07:00