Files
deepseek-harness/docs/rfc/005-runtime-validation-and-error-taxonomy.md
T
Tianyi Cui 066f94c7e0 docs: unwrap hard-wrapped Markdown to one line per paragraph
Hard line breaks mid-paragraph make docs harder to edit and diff — a
one-word change reflows and re-diffs the whole paragraph. Reflow all
tracked non-vendor Markdown (plus vendor/AGENTS.md) so each prose
paragraph is a single line; soft-wrapping is the editor's job. Fenced
code, tables, and list structure are preserved (wrapped list items fold
to one line per bullet). Documents the convention in AGENTS.md.
2026-06-13 20:27:04 +08:00

26 lines
2.2 KiB
Markdown

# RFC 005: Runtime validation at the model boundary, error taxonomy, dev-mode invariants
Status: proposed
## Problem
Three gaps where compile-time guarantees stop:
1. 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.
2. 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.
3. Loop ordering invariants (seq monotonicity, step/turn event nesting, turn-number continuity) are asserted only where tests look.
## Proposal
1. **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.
2. **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.
3. **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.