Files
deepseek-harness/docs/rfc
Tianyi Cui 1b7c376aec docs: address second-round PR review on RFC 012 (alternatives, framing)
- Add an Alternatives section comparing Code Mode against the narrower
  result-elision/summarization route over native tool-calling (solves
  context-bloat but not composition/round-trips) and against parallel native
  dispatch (a core-loop change that still lacks composition); states why
  Code Mode is chosen and why the new code-execution surface is the price.
- Fix the Problem-section framing: it said the model "can run independent
  calls concurrently," which contradicted the serialize-by-default decision.
  Reworded to "express fan-out, initially serialized until concurrency-safety
  metadata exists" — early win is composition + fewer round-trips, not parallelism.
2026-06-15 01:46:26 +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)
009 Durable session persistence — abstract, append-only, event-based store proposed
010 Agent Client Protocol (ACP) support for external editors proposed
011 Multiplex concurrent ACP sessions over one connection proposed
012 Optional Code Mode — model writes TypeScript against an SDK of all tools proposed