mirror of https://github.com/deepseek-ai/deepseek-harness synced 2026-08-15 21:04:50 +00:00

Files

Tianyi Cui 36a30180b8 feat(tools): validate model-generated tool args at the boundary (RFC 005 pt 1)

defineTool now runs validateArgs against the SchemaSpec before execute, so a
malformed model call returns a self-correctable isError result listing the
violations instead of reaching the typed body untyped-in-practice. The
validator mirrors schemaSpecToJsonSchema semantics exactly (required from
required:true only, extra keys allowed, default not applied, object/array
without properties/items only type-checks, enum membership).

tool-bash's hand-rolled type/required checks (carrying the TODO(RFC 005)
stopgap note) are slimmed to just the value constraints the DSL can't express
(non-empty strings, positive timeout). Graduates RFC 005 pt 1 to ADR 0011.

2026-06-13 23:00:42 +08:00

001-property-based-testing.md

docs: unwrap hard-wrapped Markdown to one line per paragraph

2026-06-13 20:27:04 +08:00

002-mutation-testing.md

docs: unwrap hard-wrapped Markdown to one line per paragraph

2026-06-13 20:27:04 +08:00

003-deterministic-and-stress-testing.md

docs: unwrap hard-wrapped Markdown to one line per paragraph

2026-06-13 20:27:04 +08:00

004-architectural-conformance.md

docs: unwrap hard-wrapped Markdown to one line per paragraph

2026-06-13 20:27:04 +08:00

005-runtime-validation-and-error-taxonomy.md

feat(tools): validate model-generated tool args at the boundary (RFC 005 pt 1)

2026-06-13 23:00:42 +08:00

006-doc-sync-and-api-reports.md

docs: unwrap hard-wrapped Markdown to one line per paragraph

2026-06-13 20:27:04 +08:00

007-supply-chain-and-vendor-drift.md

docs: unwrap hard-wrapped Markdown to one line per paragraph

2026-06-13 20:27:04 +08:00

008-immutable-public-surfaces.md

docs: unwrap hard-wrapped Markdown to one line per paragraph

2026-06-13 20:27:04 +08:00

README.md

feat(tools): validate model-generated tool args at the boundary (RFC 005 pt 1)

2026-06-13 23:00:42 +08:00

README.md

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	proposed
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	partially implemented
006	Doc-sync enforcement and API extractor reports	proposed
007	Supply chain checks and vendor drift verification	proposed
008	Deep-readonly public surfaces	proposed