valuelesser 6f1c806591 fix(gateway): emit OpenAI-standard token usage in responses ...

- TokenUsage.MarshalJSON now emits both standard (prompt_tokens,
  completion_tokens, total_tokens) and legacy (prompt, completion, total)
  keys, so OpenAI-compatible clients (DSH, DevEco Code, etc.) can read
  token usage.
- ChatChunk gains an optional Usage field; stream responses now send a
  final usage chunk (empty choices) before [DONE].

Refs: usage not visible in clients because the gateway serialized only the
internal short keys and never emitted a streaming usage chunk.

2026-08-18 18:14:37 +08:00

..

config

chore(compliance): drop opencode zen free-pool from default config and docs

2026-08-17 08:53:42 +08:00

core

feat: opencode zen adapter + first-run config generation, fix stats/stream bugs

2026-08-13 12:25:07 +08:00

gateway

fix(gateway): emit OpenAI-standard token usage in responses

2026-08-18 18:14:37 +08:00

lua

test(lua): add opencode role normalization test

2026-08-16 17:51:43 +08:00

provider

fix(status): source column reflects real traffic + theme-aware tray menu

2026-08-17 17:37:04 +08:00

scheduler

feat: opencode zen adapter + first-run config generation, fix stats/stream bugs

2026-08-13 12:25:07 +08:00

types

fix(gateway): emit OpenAI-standard token usage in responses

2026-08-18 18:14:37 +08:00