P4 terminal task. Implements the user-facing payoff: retrieve →
score gate → pack → render → generate → cite-validate → persist.
After this commit, `kb ask` actually works against an Ollama
backend; the pipeline grounds the answer in retrieved chunks and
refuses cleanly when the gate trips or the model self-judges.

New crate kb-rag:
- pub struct RagPipeline { retriever, llm, docs, config } — all
  Arc<dyn Trait + Send + Sync> so the pipeline shares + Sync.
- pub fn ask(query, opts) -> Result<Answer> drives the nine-stage
  flow per spec §1.
- pub struct AskOpts { k, explain, mode, temperature, seed,
  stream_sink: Option<mpsc::Sender<String>> }. k acts as a floor
  over config.search.default_k so a low-k caller can't starve
  retrieval (documented in field doc).

Pipeline stages:
1. Retrieve via the injected dyn Retriever.
2. Score gate: empty hits → NoChunks refusal (no LLM call); top-1 <
   config.rag.score_gate → ScoreGate refusal (no LLM call) with
   top-3 candidates listed in the synthesized answer text.
3. Pack: budget = config.rag.max_context_tokens.saturating_sub
   (prompt overhead). Per-hit `[#n] doc=… heading=… span=…\n<text>`
   with deterministic enumeration. If every hit's chunk is
   unfetchable from the store (deleted between search and pack),
   fall back to NoChunks refusal with a tracing::warn rather than
   feeding an empty [근거] to the LLM.
4. Render rag-v1 prompt with the spec's verbatim Korean system
   string + `[질문]/[근거]` user template.
5. Generate via dyn LanguageModel. Single-thread token loop owns
   the iterator; tokens optionally forward to opts.stream_sink (a
   `mpsc::Sender<String>`). SendError silently dropped — caller
   cancellation never panics the pipeline. After Done the loop
   reads (acc, finish_reason, usage) in lockstep with no race.
   max_completion = llm.context_tokens().saturating_sub
   (used_for_input).max(64) — explicitly NOT capped by
   config.rag.max_context_tokens (that's the packing budget for
   [근거], not the LM completion ceiling).
6. Citation extract via STRICT regex `\[#(\d{1,3})\]` (compiled
   once via OnceLock). Loose forms `[1]`, `[ #1 ]`, `[#foo]`,
   `[#1234]`, `vec![1]` are all rejected to prevent prose
   false-positives.
7. Citation validate covers four cases:
   - unknown marker (e.g. `[#7]` when only 3 packed) →
     LlmSelfJudge refusal.
   - empty answer with hits → LlmSelfJudge.
   - non-empty + no marker + matches `근거 (가|이) 부족` regex →
     LlmSelfJudge (model self-refused with the canonical phrase;
     phrase match logged via tracing::debug for observability).
   - non-empty + no marker + no refusal phrase → LlmSelfJudge
     (silent ungrounded answers are still refusals).
   - non-empty + ≥1 valid marker → grounded = true.
8. Build Answer per kb_core::Answer shape:
   - citations: filter packed list to exactly the markers cited.
     Wire format `marker: Some("[1]")` (square-bracketed bare
     index) per design §2.3, distinct from the prompt-side
     `[#n]` grammar.
   - embedding ModelRef: read from config.models.embedding for
     Vector/Hybrid; None for Lexical. Documented deviation since
     the Retriever trait doesn't expose the embedder. For
     ScoreGate/NoChunks refusals on Vector/Hybrid the embedding
     model is still recorded — the vector retriever WAS consulted
     even when the gate tripped.
   - TraceId minted as `ret_<8-hex>` from blake3(query, top_score,
     model_id, ns).
   - retrieval AnswerRetrievalSummary populated.
   - usage from the final Done chunk; latency_ms wall-clock
     fallback when the LLM reports zero.
   - created_at OffsetDateTime::now_utc().
9. Persist via SqliteStore::put_answer (new inherent method on
   SqliteStore, not on the DocumentStore trait — answers aren't
   documents and adding to kb-core was forbidden). Always inserts,
   refusals included. packed_chunks_json is null unless
   opts.explain == true.

kb-store-sqlite extension:
- pub fn put_answer(&Answer, query, packed_chunks_json) ->
  Result<AnswerId>. Maps all 22 fields of the answers table per
  V001 schema in a single INSERT under a transaction.

kb-app::ask wired:
- bail!("not yet wired (P4-3)") replaced with a real body that
  builds the retriever per opts.mode (Lexical | Vector | Hybrid),
  instantiates OllamaLanguageModel from config, constructs
  RagPipeline, calls pipeline.ask. AskOpts moves to kb-rag and is
  re-exported via `pub use kb_rag::AskOpts` so kb-cli's
  `use kb_app::AskOpts` keeps working.
- kb-app/Cargo.toml gains kb-rag, kb-llm, kb-llm-local. P3-5's
  forbids on these are lifted by P4-3 spec — kb-app is the
  orchestrator and ask requires both the trait crate and the
  Ollama adapter.
- kb-cli/main.rs's AskOpts literal updated with stream_sink: None
  for the CLI path (TUI in P9 will plumb a real sink).

Tests (kb-rag: 18; kb-app: 1 ignored):
- 3 unit in src/pipeline.rs: marker regex strictness (rejects all
  loose forms with byte-equal expectations), Send+Sync compile
  check, embedding_ref_for behavior across modes.
- 15 integration in tests/pipeline.rs covering every spec test row
  + the new "all chunks unfetchable falls back to NoChunks" guard:
  empty-hits, score-gate, grounded happy path, unknown-marker,
  prose-`[1]` rejection, `vec![1]` rejection, refusal-phrase,
  packing-budget overflow, streaming-forwards-to-mpsc, dropped-
  receiver-no-panic, usage-from-final-Done, answers-row-inserted-
  for-each-refusal-kind, determinism temp=0 seed=0, Answer JSON
  shape, unfetchable-chunks-fall-back-to-no-chunks (the new
  M3 test).
- kb-app/tests/ask_smoke.rs: 1 #[ignore]'d real-Ollama smoke that
  drives the wired ask end-to-end against `localhost:11434`.

Workspace: 319 passed / 26 ignored / 0 failed. cargo clippy
--workspace --all-targets -- -D warnings clean.

Allowed deps respected (kb-core, kb-config, kb-search, kb-llm,
kb-store-sqlite, serde, serde_json, regex, time, tracing,
thiserror) plus forced waivers anyhow (Retriever / LanguageModel
trait return types) and blake3 (TraceId minting). Forbidden
(kb-source-fs, kb-parse-md, kb-normalize, kb-chunk, kb-store-
vector direct, kb-embed* direct, kb-llm-local direct, kb-tui,
kb-desktop) all absent from `cargo tree -p kb-rag` — concrete
adapters reach the pipeline only through trait objects.

Out of scope: reranker between retrieve and pack (P+), multi-turn
chat memory (P+), LLM-as-judge eval (P5 uses rule-based
must_contain), --json streaming (buffers per §0 Q5 hybrid).

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

@@ -818,0 +867,4 @@
+            let emb_dyn: Arc<dyn Embedder> = emb;
+            let vec_retr = Arc::new(VectorRetriever::with_settings(
+                vec_dyn,
+                emb_dyn,

@@ -0,0 +162,4 @@
+        if packed_entries.is_empty() {
+            tracing::warn!(
+                target: "kb-rag",
+                chunks_returned = hits.len(),

@@ -0,0 +177,4 @@
+        // Completion budget is bounded only by what the LM context window
+        // has left after the input. NOTE: `rag.max_context_tokens` is the
+        // *packing budget* for the [근거] block (used by `pack_context`)
+        // — it is intentionally NOT used here as a completion cap.

@@ -0,0 +192,4 @@
+            system: system.clone(),
+            user: user.clone(),
+            stop: vec!["\n\n[질문]".to_string()],
+            max_tokens: max_completion,

@@ -0,0 +254,4 @@
+        });
+        let trimmed_answer = acc.trim();
+        let matched_refusal_phrase = refusal_phrase.is_match(&acc);
+        let grounded = !trimmed_answer.is_empty()

@@ -0,0 +275,4 @@
+                // `[1]`. The `[#1]` form is the *prompt-side* citation
+                // grammar (what the LLM emits in its text); the wire-side
+                // `AnswerCitation.marker` strips the `#`.
+                marker: Some(format!("[{n}]")),

@@ -0,0 +540,4 @@
+/// Build the `ModelRef` recorded in `Answer.embedding` for a given
+/// retrieval mode. `Lexical` paths leave it `None`; vector / hybrid
+/// paths attach the configured embedding model so `kb explain` can
+/// later identify which embedder shaped the retrieval (even on

@@ -0,0 +1,113 @@
+//! `answers` row writer (P4-3 — design §5.7).