github mnfst/manifest manifest@6.8.3
manifest v6.8.3

5 hours ago

🐛 Patch Changes

  • 65bca08: Fix token-cost calculation for providers that report cache-read prompt tokens. Manifest now uses models.dev cache-read/cache-write prices when available, so cached DeepSeek input tokens are billed at the cache-hit rate instead of the full input-token rate.
  • 08f9c6f: Fix /v1/responses streaming to emit the full OpenAI Responses API event lifecycle when bridging a Chat Completions upstream. The converter now opens a message item and content part (response.output_item.added / response.content_part.added) before the text deltas and closes them (response.output_text.done / response.content_part.done / response.output_item.done) with a populated response.completed, instead of emitting bare output_text.delta + response.completed{output:[]}. Strict Responses API clients (Pi, OpenClaw-style) previously dropped the deltas and rendered empty assistant messages.

Don't miss a new manifest release

NewReleases is sending notifications on new releases.