mirror of
https://github.com/deepseek-ai/deepseek-harness
synced 2026-08-15 21:04:50 +00:00
fe4da9244f
The sandbox execute wrapper JSON round-tripped the return and blindly cast it
to ToolExecuteReturn. A JSON-valid but wrong-shape return — a bare string,
{ content: 'ok' }, blocks without a type tag — sailed through: the registry
spreads result.content, so { content: 'ok' } became ['o','k'], passed the
session log's isJsonValue gate, and the DeepSeek serializer then flattened it
to '(no output)' — silent corruption of the next model request and every
replay, instead of a contained tool error.
The round-tripped value is now shape-checked against the two ToolExecuteReturn
forms (array of content blocks, or { content: blocks, meta? }); block checks
are structural only (plain object + string type tag) because the ContentBlock
union is merge-extensible. A wrong shape — and the formerly cryptic
forgot-return/bare-string cases — fails that one call with a teaching error
echoing a truncated preview of what was returned and the two valid forms.
New specs pin the object-form pass-through (meta included), six rejection
shapes, and the preview truncation; per-file 100% coverage holds.
packages/cordis — the self-referential runtime toolset
Model-facing tools over the live cordis runtime the agent itself runs inside: inspect the loaded plugins and service surface, mount model-written plugins, and dispose them again. Design home: the toolset RFC.
| Package | Role | ctx key |
|---|---|---|
tool-cordis/ |
The cordis_inspect / cordis_mount / cordis_unmount tools: read the runtime, evaluate model-written plugin code in a node:vm sandbox, and manage the dynamic mounts under one group fiber |
registers on ctx.tools |