Eight proposals grouped by category, each with problem statement, concrete plan, and risks: property-based testing over the protocol-shaped core (chunk streams, event logs, schema DSL); mutation testing as the counterweight to the 100%-coverage gate; deterministic tests + a universal replay-invariant fixture + nightly race stress; architectural conformance (dependency-cruiser rules and the LlmAdapter conformance kit); runtime arg validation at the model boundary with a structured error taxonomy and dev-mode invariants; doc-sync enforcement (typechecked doc snippets, API reports); supply-chain checks and nightly vendor-drift verification against the manifest; and deep-readonly public surfaces (logged-vs-in-flight mutability boundary). AGENTS.md points at docs/adr and docs/rfc.
2.3 KiB
2.3 KiB
RFC 005: Runtime validation at the model boundary, error taxonomy, dev-mode invariants
Status: proposed
Problem
Three gaps where compile-time guarantees stop:
- Tool args are model-generated JSON —
defineTool'sInferArgs<S>claim is only as true as the model's output. Today a malformed call reachesexecuteuntyped-in-practice. - Tool errors flatten to a text block; name/code/stack are lost, so future sandbox/retry plugins can't distinguish ENOENT from EACCES, and the model gets less actionable feedback than it could.
- Loop ordering invariants (seq monotonicity, step/turn event nesting, turn-number continuity) are asserted only where tests look.
Proposal
- Schema validation in defineTool: before
execute, validate parsed args against the SchemaSpec (the converter already encodes the structure — a small interpreter walks it: presence of required keys, primitive type checks, enum membership, recursion into objects/arrays). On mismatch, return anisErrorToolExecutionResult describing the violation — the model can self-correct. Raw-registered tools (MCP) keep validating their own input. - Structured error taxonomy: per-package error classes extending a
common
HarnessError(name,code,causechaining).ToolExecutionResultgains optionalerror: { name, code }alongside the model-facing text. The loop'serrorDataconsumes it; sessionerrorevents carry the code. This also properly fixes the non-Error-throw message degradation found in review. - Dev-mode invariants: a
dsh-invariantsdebug plugin (everything is a plugin — it's just listeners) asserting, when enabled: session seq strictly increases;step/startprecedes its chunks;turn/start/turn/endpair and nest; tool/call has a matching tool/result; status transitions are legal. Enabled in tests and the demo; off in production. Doubles as executable documentation of the event contract.
Plan
2 first (taxonomy is a dependency of 1's error shape), then 1, then 3. Property tests (RFC 001) then close the loop: generated args ↔ validator ↔ InferArgs agreement.
Risks
Validator/InferArgs drift — covered by the RFC 001 composition property. Validation cost per call is negligible next to a model call.