Files
kebab/crates/kebab-mcp/tests/tools_call_ask.rs
altair823 8a2f7affa6 feat(mcp): fb-41 PR-5 — MCP ask multi_hop arg + SKILL.md 안내
fb-41 multi-hop RAG 의 **PR-5** (PR-4 머지 직후). PR-4 의 CLI `--multi-hop`
flag 와 sister surface — agent (Claude Code 등 MCP host) 가 `mcp__kebab__ask`
호출 시 `multi_hop: true` 옵션 사용 가능.

설계: docs/superpowers/specs/2026-05-25-p9-fb-41-multi-hop-rag-design.md
계획: docs/superpowers/plans/2026-05-25-p9-fb-41-multi-hop-rag.md (PR-5 단락)

## MCP surface

- `crates/kebab-mcp/src/tools/ask.rs`:
  - `AskInput.multi_hop: Option<bool>` 추가. JsonSchema derive 가 tools/list
    에 자동 반영 — agent capability discovery 가 새 필드 인식.
  - `handle()` 가 `AskOpts.multi_hop = input.multi_hop.unwrap_or(false)` —
    기존 caller (필드 누락 / null) 는 single-pass 그대로.
- `crates/kebab-mcp/src/lib.rs` (tools/list):
  - `ask` tool description 에 multi-hop 한 줄 (decompose → retrieve →
    synthesize, 2-5× LLM cost, per-hop trace on Answer.hops).

## SKILL.md 안내

- `integrations/claude-code/kebab/SKILL.md` 의 `mcp__kebab__ask` 절:
  - Input shape JSON 예제에 `multi_hop: false` 추가.
  - Returns 절에 `hops` (multi-hop only) 추가.
  - 신규 bullet (p9-fb-41) — opt-in 조건 / 비용 trade-off / 사용 케이스
    (compound questions / prereq chains / cross-doc reasoning) /
    `Answer.hops` 의 per-hop trace shape / `multi_hop_decompose_failed`
    refusal 처리.

## Tests (`tests/tools_call_ask_multi_hop.rs` 신규, 2 Ollama-free pins)

- `ask_tool_routes_multi_hop_true_to_decompose_first`: dispatch
  divergence 핀. invalid LLM endpoint (`http://127.0.0.1:1`,
  request_timeout_secs=2) 로 force unreachable. multi_hop=true 는
  decompose 먼저 호출 → `error.v1` (code=model_unreachable) /
  isError=true. multi_hop=false (single-pass) 는 empty KB 에서 retrieve
  먼저 → no LLM call → `answer.v1` grounded=false / isError=false. 두
  shape 의 분기가 dispatch 가 실제로 다른 path 로 라우팅됨의 증거.
- `ask_input_schema_advertises_multi_hop_field`: AskInput 의 JsonSchema
  가 `multi_hop` property 노출 — MCP host capability discovery
  (tools/list 의 input schema) 회귀 핀.

기존 `tools_call_ask.rs` 의 AskInput literal 도 `multi_hop: None`
추가 (struct field 추가에 따른 minimal cascade).

## 변경 없음

- `prompt_template_version` (`rag-multi-hop-v1`) — 그대로.
- TUI surface — PR-6 의 책임.
- error.v1 매핑 — PR-4 의 enum reservation 그대로 (no error_wire
  promotion).

## 검증

- `cargo test -p kebab-mcp -j 1` — 신규 tools_call_ask_multi_hop 2 +
  기존 ask / search / bulk_search / fetch / ingest / schema / doctor /
  tools_list / initialize 등 모두 통과 (회귀 없음).
- `cargo clippy -p kebab-mcp --all-targets -j 1 -- -D warnings` clean.
- 단일 crate 직렬 build (16 GB RAM 제약).

## 다음 PR

- PR-6: TUI Ask 패널 multi-hop toggle (F2 / Ctrl-T) + hop trace render +
  cheatsheet 갱신.
- v0.18.0 cut (PR-6 머지 후).

Co-Authored-By: Claude Opus 4.7 (1M context) <noreply@anthropic.com>
2026-05-25 09:06:28 +00:00

94 lines
3.2 KiB
Rust

//! `ask` tool returns answer.v1 — refusal path covered (no Ollama
//! required for refusal-on-empty-corpus case).
use kebab_config::Config;
use kebab_core::SourceScope;
use kebab_mcp::{KebabAppState, KebabHandler};
use rmcp::model::RawContent;
fn minimal_config(data_dir: &std::path::Path, workspace_root: &std::path::Path) -> Config {
let mut cfg = Config::defaults();
cfg.storage.data_dir = data_dir.to_string_lossy().into_owned();
cfg.storage.model_dir = data_dir
.join("models")
.to_string_lossy()
.into_owned();
cfg.workspace.root = workspace_root.to_string_lossy().into_owned();
cfg.workspace.exclude.clear();
cfg.models.embedding.provider = "none".to_string();
cfg.models.embedding.dimensions = 0;
cfg
}
#[tokio::test]
async fn ask_tool_returns_answer_v1_with_refusal_on_empty_kb() {
let dir = tempfile::tempdir().unwrap();
let data_dir = dir.path().join("data");
let workspace_root = dir.path().join("notes");
std::fs::create_dir_all(&data_dir).unwrap();
std::fs::create_dir_all(&workspace_root).unwrap();
let cfg = minimal_config(&data_dir, &workspace_root);
// Seed kebab.sqlite (empty corpus — no documents ingested).
let scope = SourceScope {
root: workspace_root.clone(),
include: vec![],
exclude: vec![],
};
let _ = kebab_app::ingest_with_config(cfg.clone(), scope, false).unwrap();
let state = KebabAppState::new(cfg, None);
let handler = KebabHandler::new(state);
// `ask_with_config` builds a `reqwest::blocking::Client` internally (for
// `OllamaLanguageModel`), which spins up and drops a tokio runtime — that
// panics when called from inside an async context. Run it on the blocking
// thread pool to avoid the conflict.
let state_clone = handler.state().clone();
let result = tokio::task::spawn_blocking(move || {
kebab_mcp::tools::ask::handle(
&state_clone,
kebab_mcp::tools::ask::AskInput {
query: "what is the meaning of life".to_string(),
session_id: None,
// Test env uses provider="none" — Hybrid would hard-error on embedding.
// Pass Lexical explicitly so the test stays functional.
mode: Some("lexical".to_string()),
multi_hop: None,
},
)
})
.await
.unwrap();
// Empty KB → refusal (grounded:false) is normal — NOT isError.
assert!(
!result.is_error.unwrap_or(false),
"expected isError=false on refusal, got {:?}",
result
);
let content = result
.content
.first()
.expect("expected at least one content item");
let text = match &content.raw {
RawContent::Text(t) => &t.text,
other => panic!("expected text content, got {other:?}"),
};
let v: serde_json::Value = serde_json::from_str(text).unwrap();
assert_eq!(
v.get("schema_version").and_then(|s| s.as_str()),
Some("answer.v1"),
"response should carry schema_version=answer.v1"
);
assert_eq!(
v.get("grounded").and_then(|b| b.as_bool()),
Some(false),
"empty KB should produce grounded=false"
);
}