LangIntel

External bug-boards, RFCs and papers → Nishi Lang capability requirements & autonomous-engineering answer-keys. Real corpora as sovereign ORACLES (bench-only, never their code).

SOTA-LIVEfull-scale, no samplinginjection-scanned GREENtrust-fence PROVENsovereign authed fetch 5000/hr

The corpus (full-scale, all states, verified)

1,651real bugs ingested
1,272solved = answer-keys
379open gaps
26capability axes

Two real sources, fetched at full scale via a paginating sovereign fetch (stops on rel="next" gone, verified against the rate budget so it is never a truncated sample):

SourceTotalSolved (answer-keys)Open (gaps)
rust-lang/rust I-unsound669546123
llvm/llvm-project miscompilation982726256

Ranked capability requirements for Nishi Lang

Every real bug is classified onto a Nishi Lang capability axis by a deterministic, data-driven, case-insensitive keyword map. Each axis is GAP against the measured 0 / 184 primitive registry — a filed requirement, ranked by real oracle-bug demand:

#Capability axisOracle bugs
1compiler-miscompile-codegen638
2compiler-vectorization78
3compiler-poison-undef54
4memory-safety-pin24
5memory-safety-alignment17
6target-abi-soundness16
7type-soundness-lifetime / compiler-integer-overflow13
8move-safety-aliasing10
+ ownership-drop, trait, stack, atomics, repr, uninit, bounds, double-free …1–7

The pipeline (object-oriented, 10 thin subclasses of one base)

One OO base class nx_ingest_base carries the shared parser + primitives; every stage is a thin subclass — consolidation without losing functionality:

paginating fetchingest (Rust + LLVM connectors) → classify (data-driven hot-read conf) → verify (full-plane histogram, defeats the 64KB read cap) → rank (router → requirements registry) → integrity-scan.

The fetch is fully sovereign — our own TLS 1.3 client with authenticated GitHub access at 5,000 req/hr (runtime-proven: 200 on an auth-only endpoint; no curl, no GraphQL, no libc) — so all 1,272 fix-diff answer-keys can be captured full-scale, each passed through the trust fence before it can become training fuel.

Autonomous engineering: solves as answer-keys

The 1,272 solved bugs are (problem, solution) pairs in the SWE-bench shape — the training fuel for the ecosystem's autonomous-fix loop, which already resolves 71% (FAIL_TO_PASS + PASS_TO_PASS, judged by fresh compile+run, never by trusting the patch).

Security: a 3-stage untrusted-input fence

External data is an untrusted / poisoning surface, so it is guarded before, during, and after submission, deny-by-default, consolidated onto the ecosystem guard lifecycle:

StageControlStatus
PRE-submitSovereign TLS 1.3 + trust store; trust-tier fence — a fix is a tier-1 answer-key ONLY if merged into the canonical repo (not a fork) with a real merge-commit = maintainer-vetted; injection scan of all 1,651 titlesPROVEN — real rust-lang/rust#50000 accepted; 3 crafted trojans (unmerged / attacker-fork / null-merge) each rejected for the correct reason; injection 0/1,651
AT-submitnever-execute (patches are data, never run during ingest); isolated never-brick sandbox for patch-applyPRE done; sandbox building
POST-submitTESTS-JUDGE-NOT-TRUST (a patch failing FAIL_TO_PASS+PASS_TO_PASS is rejected); adversarial CI re-proves the trojan rejections each runbuilding — gated before any patch trains

Sovereign Nishi ecosystem · LangIntel capability · all figures measured full-scale, never sampled. Corpus on the Nishi information plane: langintel-requirements-, langintel-rustunsound-, langintel-llvm-, langintel-axismap-.