Files
deepseek-harness/docs/rfc
Tianyi Cui 825b57aff9 feat(llm): structured error taxonomy with a shared HarnessError base (RFC 005 pt 2)
Introduce HarnessError in dsh-llm (the leaf package): a stable machine-routable
code distinct from the message, cause chaining, name from the subclass, plus
isHarnessError. LlmError, ToolArgsError, and InvariantError now extend it.

Tool failures carry the structure end-to-end: ToolExecutionResult gains
error: { name, code } (populated from a thrown HarnessError), and the loop
forwards it onto the tool/result session event (which gained the same optional
field) for retry/sandbox plugins and replay. The loop's toError wraps non-Error
throws in a HarnessError(code: UNKNOWN, cause) instead of a bare Error.

Landed last and in isolation so it's a pure upgrade over the plain Error+code
the earlier PRs used — independently revertible. Graduates RFC 005 pt 2 ->
ADR 0015; RFC 005 now fully implemented.
2026-06-14 01:07:28 +08:00
..

RFCs

Proposals for substantial future work — reviewed before implementation, unlike ADRs (which record decisions already made). Each RFC groups a related set of ideas from the quality/robustness proposal (2026-06-11); statuses move proposed → accepted → implemented (then usually graduate to an ADR).

# Title Status
001 Property-based testing for protocol-shaped code implemented
002 Mutation testing as the coverage counterweight proposed
003 Deterministic tests + replay invariant fixture + race stress proposed
004 Architectural rules: dependency-cruiser, adapter conformance kit proposed
005 Runtime arg validation, structured error taxonomy, dev-mode invariants implemented
006 Doc-sync enforcement and API extractor reports implemented (pts 1-2; pt 3 deferred)
007 Supply chain checks and vendor drift verification proposed
008 Deep-readonly public surfaces implemented (revised)