mirror of
https://github.com/deepseek-ai/deepseek-harness.git
synced 2026-08-29 04:26:38 +00:00
Chinesezjc
be839a8e53
Two gaps from the previous round's fixes: - checkDoneValue flagged a non-lossless number but skipped counting its encoded bytes, so a value over budget ONLY through that number classified as non-lossless instead of over-budget (e.g. [Infinity] at cap 3, whose encoding is 10 bytes). Count the scalar's bytes even when flagging, so the budget check wins as the JSDoc promises. Add cap-3 regression cases. - The mirror e2e compared the Python TypedDict keys against a hand-written constant, so a field change on the TS side alone would not fail it, and the reply frames were not probed at all. Introduce WIRE_FRAME_FIELDS in protocol.ts, bound to each frame interface's key set via `satisfies` (a renamed/removed field breaks typecheck — verified), and drive the mirror test from it, now covering ReplyOk/ReplyErr too. The test therefore fails on one-sided drift from either language.
code-runtime/ — code-execution capability family
English | 中文
The code-execution capability seam (see capability seams): an abstract runtime interface for executing one model-written program against host-provided async bindings, capturing what it printed and returned. The consumer is the tool registry's Code Mode (tools: { mode: code } — the run_code tool and the SDK generated in the loaded runtime's language); design in the Code Mode Agent Note. Product packages.
| Package | Role | ctx key |
|---|---|---|
code-runtime/ |
Code-execution seam and shared vocabulary | ctx.codeRuntime |
code-runtime-worker/ |
Worker-thread backend | registers ctx.codeRuntime |
Backends register the seam without changing its consumer. The child READMEs own language, isolation, and execution-budget details.