docs: lock fixed_size ±3 in decision record and lld

Why:
- Close the open ±N follow-up from the strategy finalization memo.

Changes:
- Add addendum with ±0…±3 evidence and binding ±3/3 default.
- Sync LLD config table with new neighbor expansion defaults.

Co-authored-by: Cursor <cursoragent@cursor.com>

docs/LLD.md

@@ -84,7 +84,7 @@ get_qdrant_client()
 | `ollama_base_url` | host URL | Local embeds |
 | `qdrant_url` | `http://localhost:6333` | Vectors |
 | `top_k` | `5` | Retrieval |
-| `neighbor_prev` / `neighbor_next` | `0` / `0` | Expansion defaults |
+| `neighbor_prev` / `neighbor_next` | `3` / `3` | Expansion defaults (fixed_size ±3) |
 | `chunk_size` / `chunk_overlap` | `512` / `50` | fixed_size / recursive targets |
 | `semantic_threshold` | `0.3` | Fallback if model default missing |
 | `semantic_min_chunk_size` | `3` | Min units per semantic chunk |

docs/final-chunking-strategy-decision.md

@@ -1,13 +1,12 @@
 # Chunking Strategy — Final Decision
 
-**Date:** 17 August 2026  
+**Date:** 17 August 2026 (family); **22 August 2026** (±N locked)  
-**Decision:** Adopt **`fixed_size`** as the chunking Strategy family.  
+**Decision:** Adopt **`fixed_size`** as the chunking Strategy family with **Neighbor Expansion ±3/3**.  
-**Not decided here:** Neighbor Expansion level **±N** (follow-up).  
 **Corpus Embedding Model:** `text-embedding-3-large`  
 **Evaluation set:** 10 Word documents (Decision Board / neighbor-sweep universe)  
 **Questions:** 201 per Candidate (nomic semantic: 195)
 
-**One-line close:** **`fixed_size` wins** on official mean composite (**9.040** vs **8.727**). Pick **±N later**, but **not ±0**.
+**One-line close:** **`fixed_size ±3`** is the stabilized Strategy Candidate (**9.040** mean composite vs **8.727** for semantic @ large). **Do not use ±0** as the default — it loses to semantic on mean.
 
 Charts below are generated from `data/chunking_benchmark.db` with the same composite as the Decision Board:
 
@@ -123,15 +122,38 @@ One leftover five-strategy Experiment on `customer1` under large is **invalid**
 
 **Use `fixed_size` for chunking** under **`text-embedding-3-large`.**
 
+**Use Neighbor Expansion `neighbor_prev=3`, `neighbor_next=3`** (symmetric **±3/3**) for Query and Experiment defaults when running `fixed_size`.
+
 **Do not use `semantic` as the default Strategy** on this evaluation universe.
 
-**Follow-up:** choose Neighbor Expansion **±N** among **±1, ±2, ±3**. Stage 1 auto-pick is **±3**. **±0 is not recommended** if this family decision is to remain valid.
+**Do not default to ±0.** Without expansion, semantic @ large beats `fixed_size` on mean composite (8.727 vs 8.606).
 
-Production config change is **out of scope** for this record.
+Operational defaults are set in `src/core/config.py`, `.env.example`, and the Dashboard Query/Benchmarks forms. Override per request is still supported.
 
 ---
 
-## 8. Evidence (stage 2 cells)
+## 8. Addendum — why ±3 (22 August 2026)
+
+Stage 1 ranked all `fixed_size` Candidates on the 10-doc grid:
+
+| ±N | Mean composite | vs semantic @ large |
+|----|----------------|---------------------|
+| ±0 | 8.606 | **loses** (−0.121) |
+| ±1 | 8.926 | wins (+0.199) |
+| ±2 | 8.987 | wins (+0.260) |
+| **±3** | **9.040** | **wins (+0.313)** |
+
+**±3** is the stage 1 auto-pick and the highest mean composite. **±1** and **±2** are close; **±0** is ruled out.
+
+Per-document best ±N varies (±3 wins on 5 docs, ±1 on 3, ±2 on 1, ±0 on 1). The **global** default is still **±3** because Decision Board ranks by mean composite across the full set, not by win-count among ±N levels.
+
+**Caveats kept from stage 2:** semantic still wins head-to-head on 6/10 docs vs ±3 (website, customer1, etc.), but mean composite and judge metrics favor **`fixed_size ±3`**. Retrieval Inspect on outlier docs remains optional follow-up.
+
+**Production RAG outside this repo** is not changed by this addendum — only benchmarker defaults and this record.
+
+---
+
+## 9. Evidence (stage 2 cells)
 
 | Document | `fixed_size ±3` experiment id | `semantic @ large` experiment id |
 |----------|-------------------------------|----------------------------------|

src/core/config.py

@@ -22,9 +22,9 @@ class Settings(BaseSettings):
 
     # Retrieval
     top_k: int = 5
-    # Neighbor Expansion for fixed_size (ADR-0023); 0/0 = off
+    # Neighbor Expansion for fixed_size (ADR-0023); 3/3 = decision default (see final-chunking-strategy-decision.md)
-    neighbor_prev: int = 0
+    neighbor_prev: int = 3
-    neighbor_next: int = 0
+    neighbor_next: int = 3
 
     # LLM generation
     temperature: float = 0.0

src/static/index.html

@@ -1287,8 +1287,8 @@ function RetrievalInspectView({ experiment, onBack }) {
 
 function QueryTab({ documents, strategies, addToast, formatFilter = 'word', hideTitle = false }) {
   const [form, setForm] = useState({
-    document_id: '', strategy: '', question: '', top_k: 5,
+    document_id: '', strategy: 'fixed_size', question: '', top_k: 5,
-    neighbor_prev: 0, neighbor_next: 0, corpus_model_id: '',
+    neighbor_prev: 3, neighbor_next: 3, corpus_model_id: '',
   });
   const [result, setResult] = useState(null);
   const [loading, setLoading] = useState(false);
@@ -1761,9 +1761,9 @@ function ComparisonView({ experiments, addToast, onBack }) {
 function BenchmarksTab({ documents, strategies, addToast, questionsFile, formatFilter = 'word', hideTitle = false }) {
   const [experiments, setExperiments] = useState([]);
   const [form, setForm] = useState({
-    document_id: '', strategies: strategies.map(s => s.name),
+    document_id: '', strategies: ['fixed_size'],
     questions_file: questionsFile, top_k: 5,
-    neighbor_prev: 0, neighbor_next: 0, dry_run: false, corpus_model_id: '',
+    neighbor_prev: 3, neighbor_next: 3, dry_run: false, corpus_model_id: '',
   });
   const [running, setRunning] = useState(false);
   const [embModels, setEmbModels] = useState([]);