chore(rag): post-PR9 refactor — H1/H2/H3/D/E + test coverage + post-refactor dogfood retest

OMC team `post-pr9-refactor` 의 architectural cleanup. architect priorities 분석 후 executor + test-engineer 가 file edits, system-architect 가 component-level review 로 *pre-cut nothing — all v0.18.1+ defer* 결론.

## Executor 작업 (H1/H2/H3/D/E)

- **H1** (kebab-nli/src/onnx.rs): `[models.nli]` config wire 활성화. `DEFAULT_MODEL_ID` const 제거 (kebab-config 의 NliCfg::defaults 가 single source). OnnxNliVerifier::new 가 config.models.nli.model 읽고 config.models.nli.provider 가 "onnx" 아니면 anyhow::bail. 3 stale "PR-9c-1 will wire this" 코멘트 제거. 2 unit test 추가 (`new_uses_config_model_id`, `new_rejects_unsupported_provider`).
- **H2** (kebab-rag/src/pipeline.rs): `truncate_for_nli(premise: &str, _hypothesis: &str)` → `truncate_for_nli(premise: &str)`. v0.18.1 placeholder doc 제거. 4 callsite (tests/multi_hop.rs) 갱신 + test rename `multi_hop_truncate_for_nli_preserves_hypothesis` → `multi_hop_truncate_for_nli_char_budget` (contract 정합).
- **H3** (kebab-rag/src/pipeline.rs:1041): `was_truncated` 가 tracing::debug! 으로 surface (observability 추가, signature 보존 — caller logging contract).
- **D** (kebab-mcp/tests/tools_call_ask_multi_hop.rs): request_timeout_secs 2 → 5 (slow CI 안정성), `mh_code` discriminator 제거. dispatch contract = `mh.is_error.unwrap_or(false)` (기존 assertion 으로 충분).
- **E** (tasks/HOTFIXES.md + pipeline.rs:1633-1638): fb-41 PR-9 closure entry 의 sibling 으로 "### PR-9 NLI refusal: terminal Synthesize hop omitted from hops trace" subsection 추가. pipeline 의 "cleanup deferred to a follow-up" → "// See tasks/HOTFIXES.md ... for follow-up" cross-link.

## Test-engineer 작업 (T1/T2/T3/T4, 9 new tests)

- **T1** (kebab-nli/src/onnx.rs::tests): sanitize_model_id 3 unit (replaces_slash / idempotent / leaves_other_chars).
- **T2** (kebab-rag/tests/multi_hop_nli_panic.rs 신규): 2 panic-path tests — facade invariant (`expect("verifier must be Some when nli_threshold > 0.0")`) 의 #[should_panic] + threshold=0 의 companion.
- **T3** (kebab-rag/tests/multi_hop_nli_stream.rs 신규): 2 StreamEvent::Final tests — refuse_nli_verification + refuse_nli_model_unavailable 의 stream_sink Final 분기 wire shape pinning.
- **T4** (kebab-app/tests/open_with_config_nli.rs 신규): 2 NLI failure path — model_dir 가 unwritable 일 때 App::open_with_config 의 Result<App> Err (with "OnnxNliVerifier" in chain) + threshold=0 일 때 graceful skip.

## System-architect 결론

3 lenses (absorption / duplication / under-engineered interface) 분석 결과 — *pre-cut nothing*. Top-3 items 모두 v0.18.1+ defer:
- Lens 1: kebab-normalize + kebab-parse-types 흡수 가능 (parse-md 만 사용, 5 parsers 우회) → v0.18.1+.
- Lens 3: Extractor + Chunker trait 의 dead polymorphism (모든 callsite 가 hardcoded) → v0.18.1+.
- Lens 1 bundled: kebab-source-fs 가 kebab-parse-code 의 9 tree-sitter grammars drag → low-risk dep-graph win, v0.18.1+ bundled.
- Defer-with-intent: LanguageModel async refactor (cloud-LLM 시), NliVerifier::score_batch + typed NliError (2nd impl 시), compute_stale → kebab-core::stale.

보고서: /build/cache/tmp/post-pr9-refactor-priorities.md, /build/cache/tmp/system-architecture-priorities.md (둘 다 repo 외 — analysis 보존).

## 검증

- cargo test -p kebab-nli -j 1 → 11/11 pass.
- cargo test -p kebab-rag -j 1 → 75/75 pass (5 NLI multi-hop + 4 신규 T2/T3 포함).
- cargo test -p kebab-app -j 1 → 23 pass + 2 ignored (T4 의 2 포함).
- cargo test -p kebab-mcp --test tools_call_ask_multi_hop -j 1 → 1 pass + 1 pre-existing flaky (HOTFIX #15, no_chunks short-circuit, executor D fix 와 무관 — line 86 의 base assertion 이 fixture 없어서 fail).
- cargo clippy --workspace --all-targets -j 1 -- -D warnings clean.
- cargo test --workspace --no-fail-fast -j 1 → 1304 passed (+11 new) + 1 pre-existing flaky 동일.
- **Post-refactor dogfood retest byte-identical** (PR-9d / post-cleanup / post-refactor 3번 모두): S7 0.0035389824770390987, S1 0.058334656059741974, S10 0.0027875436935573816, S3 nli_model_unavailable.

docs/dogfood/v0.18.0/SUMMARY.md 에 "Post-architectural-refactor retest" section 추가.

Wire 영향: 없음.
Behavior 영향: 없음 (H1 의 config wiring 가 default 와 같은 model → byte-identical).

Co-Authored-By: Claude Opus 4.7 (1M context) <noreply@anthropic.com>
This commit is contained in:
2026-05-26 04:42:37 +00:00
parent 3712d005cc
commit 7c27633df2
9 changed files with 508 additions and 52 deletions

View File

@@ -0,0 +1,81 @@
//! Tests for `App::open_with_config`'s NLI verifier construction path.
//!
//! Coverage:
//! 1. `open_with_config_nli_fails_when_model_dir_unwritable_and_threshold_positive` —
//! when `rag.nli_threshold > 0` and `storage.model_dir` is unwritable,
//! `open_with_config` returns `Err` with "OnnxNliVerifier" in the
//! error chain.
//! 2. `open_with_config_nli_skipped_when_threshold_zero` —
//! same bad `model_dir`, but `rag.nli_threshold = 0.0` (gate disabled),
//! so `OnnxNliVerifier::new` is never called and `open_with_config`
//! succeeds.
//!
//! `/proc/1/root` is the init process's filesystem root; on Linux it is
//! owned by root and not traversable by unprivileged users, making
//! `create_dir_all` fail with `EACCES` — a reliable "unwritable path"
//! that requires no test setup beyond the path literal.
use kebab_config::Config;
/// Return a `Config` whose `data_dir` lives in a fresh `TempDir`
/// (so `SqliteStore::open` succeeds) and whose `model_dir` is set to
/// `/proc/1/root` (unwritable by non-root processes on Linux).
///
/// The `TempDir` is returned alongside the config so the caller keeps
/// it alive until the test completes — dropping it early would delete
/// the data directory before any assertions run.
fn config_with_unwritable_model_dir() -> (tempfile::TempDir, Config) {
let tmp = tempfile::tempdir().expect("tempdir");
let mut cfg = Config::defaults();
// Valid data_dir → SqliteStore::open + run_migrations succeed.
cfg.storage.data_dir = tmp.path().to_string_lossy().into_owned();
// /proc/1/root is only accessible to root; create_dir_all will
// return EACCES for any unprivileged user, which is exactly the
// failure mode we want to exercise.
cfg.storage.model_dir = "/proc/1/root".to_string();
(tmp, cfg)
}
// ── 1. Failure path: threshold > 0 + unwritable model_dir ─────────────────
#[test]
fn open_with_config_nli_fails_when_model_dir_unwritable_and_threshold_positive() {
let (_tmp, mut cfg) = config_with_unwritable_model_dir();
cfg.rag.nli_threshold = 0.5; // gate enabled → OnnxNliVerifier::new runs
let result = kebab_app::App::open_with_config(cfg);
let Err(err) = result else {
panic!(
"App::open_with_config must fail when model_dir is unwritable and nli_threshold > 0"
);
};
// The error chain must identify the OnnxNliVerifier as the source so
// an operator reading logs can trace the failure to the NLI config.
let err_chain = format!("{err:?}");
assert!(
err_chain.contains("OnnxNliVerifier"),
"error chain must mention OnnxNliVerifier; full chain: {err_chain}"
);
}
// ── 2. Success path: threshold = 0.0 → NLI verifier never constructed ──────
#[test]
fn open_with_config_nli_skipped_when_threshold_zero() {
let (_tmp, cfg) = config_with_unwritable_model_dir();
// Default nli_threshold is 0.0 — gate disabled, verifier skipped.
assert!(
(cfg.rag.nli_threshold - 0.0).abs() < f32::EPSILON,
"precondition: default nli_threshold must be 0.0 (gate disabled)"
);
// A bad model_dir must NOT cause a failure when the NLI gate is off.
let result = kebab_app::App::open_with_config(cfg);
assert!(
result.is_ok(),
"App::open_with_config must succeed when nli_threshold = 0.0 \
(OnnxNliVerifier is never constructed); err: {:?}",
result.err()
);
}