✨ feat(kebab-mcp): ask tool (fb-30)

Fourth (and final v1) tool — `ask` (input: query / optional session_id).
Multi-turn via optional session_id (kebab_app::ask_with_session_with_config),
single-shot via ask_with_config when None. Refusal (grounded:false) NOT
mapped to isError — agent branches on the wire payload's grounded flag.

AskOpts has no Default impl (must construct manually). Answer carries no
schema_version field (tagged inline via entry().or_insert_with, idempotent).
Mode defaulted to Lexical: reqwest::blocking::Client::build creates and
drops a tokio runtime, panicking inside async context — the empty-corpus
refusal test avoids this via spawn_blocking; the tool itself uses Lexical
as the default mode since MCP callers typically run without an embedding
provider configured.

Co-Authored-By: Claude Opus 4.7 (1M context) <noreply@anthropic.com>

crates/kebab-mcp/src/lib.rs

@@ -65,6 +65,11 @@ impl ServerHandler for KebabHandler {
                 "Full-text / vector / hybrid search over the knowledge base. Returns search_hit.v1 array.",
                 schema_for_type::<tools::search::SearchInput>(),
             ),
+            Tool::new(
+                "ask",
+                "RAG question answering over the knowledge base. Returns answer.v1 JSON. Pass session_id for multi-turn context.",
+                schema_for_type::<tools::ask::AskInput>(),
+            ),
         ]))
     }
 
@@ -93,6 +98,17 @@ impl ServerHandler for KebabHandler {
                     };
                 Ok(tools::search::handle(&self.state, input))
             }
+            "ask" => {
+                let args = request.arguments.unwrap_or_default();
+                let input: tools::ask::AskInput =
+                    match serde_json::from_value(serde_json::Value::Object(args)) {
+                        Ok(i) => i,
+                        Err(e) => {
+                            return Ok(error::to_tool_error(&anyhow::Error::from(e)));
+                        }
+                    };
+                Ok(tools::ask::handle(&self.state, input))
+            }
             _other => Err(ErrorData::method_not_found::<
                 rmcp::model::CallToolRequestMethod,
             >()),

crates/kebab-mcp/src/tools/ask.rs

@@ -0,0 +1,63 @@
+//! `ask` tool — wraps `kebab_app::ask_with_config` (single-shot) or
+//! `kebab_app::ask_with_session_with_config` when `session_id` is provided.
+//! Input: { query, session_id? }. Output: answer.v1 JSON.
+//!
+//! `Answer` (kebab-core) does NOT carry a `schema_version` field; we tag
+//! it inline here, matching the pattern from `search.rs`.
+
+use rmcp::model::CallToolResult;
+use schemars::JsonSchema;
+use serde::{Deserialize, Serialize};
+
+use crate::error::{to_tool_error, to_tool_success};
+use crate::state::KebabAppState;
+
+#[derive(Debug, Deserialize, Serialize, JsonSchema)]
+pub struct AskInput {
+    /// The user question.
+    pub query: String,
+    /// Optional session id for multi-turn RAG context.
+    pub session_id: Option<String>,
+}
+
+pub fn handle(state: &KebabAppState, input: AskInput) -> CallToolResult {
+    // Default to Lexical mode — the MCP server is typically called by
+    // agent hosts that may not have an embedding provider configured.
+    // Hybrid/vector retrieval would hard-error when embeddings are
+    // disabled; lexical FTS is always available and covers the common
+    // RAG case well.
+    let opts = kebab_app::AskOpts {
+        k: 10,
+        explain: false,
+        mode: kebab_core::SearchMode::Lexical,
+        temperature: None,
+        seed: None,
+        stream_sink: None,
+        history: Vec::new(),
+        conversation_id: None,
+        turn_index: None,
+    };
+    let cfg_clone = (*state.config).clone();
+    let result = match input.session_id {
+        Some(sid) => {
+            kebab_app::ask_with_session_with_config(cfg_clone, &sid, &input.query, opts)
+        }
+        None => kebab_app::ask_with_config(cfg_clone, &input.query, opts),
+    };
+    match result {
+        Ok(answer) => {
+            // `Answer` does not carry `schema_version`; tag inline (idempotent
+            // via entry().or_insert_with in case a future version adds it).
+            let mut v = serde_json::to_value(&answer).unwrap_or_default();
+            if let serde_json::Value::Object(ref mut map) = v {
+                map.entry("schema_version".to_string())
+                    .or_insert_with(|| serde_json::Value::String("answer.v1".to_string()));
+            }
+            match serde_json::to_string(&v) {
+                Ok(json) => to_tool_success(json),
+                Err(e) => to_tool_error(&anyhow::anyhow!(e)),
+            }
+        }
+        Err(e) => to_tool_error(&e),
+    }
+}

crates/kebab-mcp/src/tools/mod.rs

@@ -3,4 +3,4 @@
 pub mod schema;
 pub mod doctor;
 pub mod search;
-// pub mod ask;      // wired in Plan Task 7
+pub mod ask;

crates/kebab-mcp/tests/tools_call_ask.rs

@@ -0,0 +1,89 @@
+//! `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,
+            },
+        )
+    })
+    .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"
+    );
+}