JianFeeeee 791d198f47 fix(opencode): make x-opencode-session stable so the upstream prefix cache can hit ...

The opencode adapters derived x-opencode-session from meta.timestamp, i.e. a
brand new session on every request. The upstream prefix cache is
session-scoped, so no request could ever hit it, and the cache fields the
endpoint does report (prompt_tokens_details.cached_tokens,
prompt_cache_hit_tokens/prompt_cache_miss_tokens) always came back 0/absent.

Measured against the live endpoint, same 6032-token prompt:

  fixed session id   -> 2nd call: hit 5888, miss 144
  rotating session id -> every call: hit 0, miss 6032

Fix: derive the session from the source name (stable), matching how
x-opencode-project is already derived. x-opencode-request stays unique per
request — it is only a request identifier, not part of the cache key.
Applied to both opencodego and opencodezen.

Through the gateway the same prompt now reports, on the 2nd call:
  details={'cached_tokens': 5888} hit=5888 miss=144      (non-streaming)
  prompt_tokens_details={'cached_tokens': 5888}          (streaming)

Test: TestOpenCodeSessionIsStableForCache asserts the session is stable
across requests for one source while the request id differs.

2026-09-11 15:42:22 +08:00

..

adapters

fix(opencode): make x-opencode-session stable so the upstream prefix cache can hit

2026-09-11 15:42:22 +08:00

toolcall_preservation_test.go

fix(opencode): make x-opencode-session stable so the upstream prefix cache can hit

2026-09-11 15:42:22 +08:00

vm_test.go

fix(opencode): never drop an assistant turn that carries tool_calls

2026-09-10 19:32:47 +08:00

vm.go

fix(lua): bound prewarm by queue depth, not by the ceiling

2026-08-30 08:25:18 +08:00