0 Fork 0

Files

T

Tianyi Cui 11a29fdefe feat(invariants): dev-mode event-contract assertions + session-log freeze (RFC 005 pt 3, RFC 008)

New @deepseek-ai/dsh-invariants plugin (pure listeners, off in prod) asserts
the event taxonomy at runtime — seq monotonicity, turn/step nesting, a
tool/result needs a prior tool/call (NOT the converse), legal agent/status
transitions — and deep-freezes logged event data so mutating history throws.
Seeded sessions are checked + frozen on session/created.

The real RFC 008 fix is always-on: deriveMessages now structured-clones the
content it emits, so the loop's sanctioned request/adapter mutation can no
longer reach back and rewrite the append-only log. The pervasive
DeepReadonly<T> type flip is rejected (compile-only, high-noise, castable) —
recorded in ADR 0012, which folds in RFC 008. Wired into both demos.

2026-06-13 23:25:12 +08:00

2.4 KiB

Raw Blame History

RFC 005: Runtime validation at the model boundary, error taxonomy, dev-mode invariants

Status: partially implemented — part 1 (arg validation) → ADR 0011; part 3 (dev invariants) → ADR 0012; part 2 (error taxonomy) in progress

Problem

Three gaps where compile-time guarantees stop:

Tool args are model-generated JSON — defineTool's InferArgs<S> claim is only as true as the model's output. Today a malformed call reaches execute untyped-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 an isError ToolExecutionResult 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, cause chaining). ToolExecutionResult gains optional error: { name, code } alongside the model-facing text. The loop's errorData consumes it; session error events carry the code. This also properly fixes the non-Error-throw message degradation found in review.
Dev-mode invariants: a dsh-invariants debug plugin (everything is a plugin — it's just listeners) asserting, when enabled: session seq strictly increases; step/start precedes its chunks; turn/start/turn/end pair 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.

2.4 KiB Raw Blame History