refactor(tooling): drop stem cap + scope dedup to per-system (#833)

The stem cap (--stem-cap 20) was rejecting valid names because common
feature-type vocabulary tokens like "ridge", "hill", "range" hit the
cap after ~200 bodies and blocked all subsequent names containing
them. With sub-style rotation already providing variety, the cap was
doing more harm than good. Removed entirely.

Cross-body dedup narrowed from (hop, corridor, feature_type) to
(system_id, feature_type). Two rivers in the same system can't share
a name; two rivers in different systems can. This matches how
settlers actually name things — they don't coordinate with other
star systems.

Co-Authored-By: Claude Opus 4.6 (1M context) <noreply@anthropic.com>

tooling/planet-gen/gemma_naming.py

@@ -1303,38 +1303,6 @@ def body_population_band(population: int) -> str:
     return "megaworld (1B+)"
 
 
-_STEM_WORD_RE = re.compile(r"[A-Za-z][A-Za-z'\-]{2,}")
-
-# Tokens so generic they should never count toward stem-dominance — they
-# just describe the feature type and don't carry cultural identity.
-_IGNORED_STEMS = {
-    "the", "of", "a", "an", "and", "or",
-    "river", "sea", "lake", "ocean", "bay", "gulf", "range", "peak",
-    "peaks", "ridge", "spine", "scarp", "heights", "hollow", "run",
-    "beck", "water", "course", "flow", "basin", "reach", "hold",
-    "cross", "prime", "city", "town", "capital", "gate", "terminal",
-    "transit", "exchange", "concourse", "assembly", "archive",
-    "commons", "grounds", "square", "circle", "mountain", "mountains",
-    "stream", "brook", "spring", "tarn", "mere", "pool", "deep",
-    "expanse", "crest", "summit", "fells", "series", "sea", "maris",
-    "mare", "aquae", "fluvius", "terrae",
-}
-
-
-def _extract_stems(name: str) -> list[str]:
-    """Return the lowercase 'interesting' stems of a name — cultural
-    root tokens only, with 'the', 'of', 'river', 'peaks' etc. dropped.
-
-    Used to enforce per-stem dominance caps across the full run so no
-    single root (e.g. 'Arcturus') can appear in hundreds of names
-    across 3240 bodies.
-    """
-    return [
-        t.lower() for t in _STEM_WORD_RE.findall(name)
-        if t.lower() not in _IGNORED_STEMS
-    ]
-
-
 def name_feature(
     voice: VoiceSubprocess,
     feature_type: str,
@@ -1342,8 +1310,6 @@ def name_feature(
     blocklist: set[str],
     corpus: dict[tuple, set[str]],
     body_used: set[str],
-    stem_counts: dict[str, int],
-    stem_cap: int,
     system_hook: str | None,
     system_id: str,
     world_seed: int,
@@ -1354,15 +1320,12 @@ def name_feature(
     verbose: bool,
     max_attempts: int = 3,
 ) -> str:
-    """Request a name from Gemma, enforce blocklist + hop/corridor dedup +
-    per-body cross-type dedup, fall back to the palette generator on
-    persistent failure.
+    """Request a name from Gemma, enforce blocklist + per-system dedup +
+    per-body cross-type dedup, skip on persistent failure.
 
     Dedup scopes:
-      - `corpus[(hop, corridor, feature_type)]` — cross-body dedup within
-        the same gate-hop distance and corridor. Systems at the same hop
-        in the same corridor are near neighbors and shouldn't share
-        feature names. Systems at different hops can.
+      - `corpus[(system_id, feature_type)]` — no two features of the
+        same type in the same system share a name.
       - `body_used` — per-body set across ALL feature types. Prevents
         the same name from appearing as a river AND an ocean AND a
         mountain range on the same world.
@@ -1374,7 +1337,7 @@ def name_feature(
     palette = palette_for(corridor, system_id)
     planet_class = ctx.get("planet_class") or "habitable"
 
-    dedup_key = (hop, corridor, feature_type)
+    dedup_key = (system_id, feature_type)
     used = corpus.setdefault(dedup_key, set())
 
     # Capture mode: build the attempt-0 prompt, log it, return a unique
@@ -1417,24 +1380,12 @@ def name_feature(
             or lc in (n.lower() for n in body_used)
         )
 
-    def _exceeds_stem_cap(candidate: str) -> str | None:
-        """Return the first stem in `candidate` that would exceed the
-        cap after this accept, or None if all stems are under the cap."""
-        if stem_cap <= 0:
-            return None
-        for stem in _extract_stems(candidate):
-            if stem_counts.get(stem, 0) >= stem_cap:
-                return stem
-        return None
-
     def _commit_name(final: str) -> None:
         used.add(final)
         body_used.add(final)
-        for stem in _extract_stems(final):
-            stem_counts[stem] = stem_counts.get(stem, 0) + 1
 
     rejections: dict[str, int] = {"empty": 0, "placeholder": 0, "blocklist": 0,
-                                   "dedup": 0, "stem_cap": 0, "error": 0}
+                                   "dedup": 0, "error": 0}
 
     for attempt in range(max_attempts):
         seed = _seed_for(world_seed, body_id, local_id, attempt)
@@ -1473,11 +1424,6 @@ def name_feature(
             rejections["dedup"] += 1
             log(f"    dedup '{cleaned}' {body_id}/{local_id}")
             continue
-        over_stem = _exceeds_stem_cap(cleaned)
-        if over_stem is not None:
-            rejections["stem_cap"] += 1
-            log(f"    stem_cap '{cleaned}' ('{over_stem}' ≥{stem_cap}) {body_id}/{local_id}")
-            continue
         _commit_name(cleaned)
         return cleaned
 
@@ -1602,8 +1548,6 @@ def process_body(
     conn: sqlite3.Connection,
     blocklist: set[str],
     corpus: dict[tuple, set[str]],
-    stem_counts: dict[str, int],
-    stem_cap: int,
     system_hook: str | None,
     world_seed: int,
     hop: int,
@@ -1641,22 +1585,17 @@ def process_body(
     # Per-body dedup set — no name may appear twice on the same body,
     # even across feature types. Seeded with every hand-authored name
     # already present so templates (Lendel, Edict, Estrade, …) keep their
-    # canonical identifiers and new features don't collide with them.
-    # Hand-authored names also count against the stem cap so those
-    # anchors take priority over generator output.
     body_used: set[str] = set()
     for key in ("cities", "rivers", "oceans", "mountain_ranges", "pois"):
         for feat in markers.get(key) or []:
             name = feat.get("name")
             if name and isinstance(name, str) and name.strip():
                 body_used.add(name.strip())
-                for stem in _extract_stems(name):
-                    stem_counts[stem] = stem_counts.get(stem, 0) + 1
 
     # Cities
     for city in markers.get("cities") or []:
         if not _is_blank(city.get("name")):
-            corpus.setdefault((hop, corridor, _feature_type_for_city(city)), set()).add(
+            corpus.setdefault((system_id, _feature_type_for_city(city)), set()).add(
                 city["name"]
             )
             counts["preserved"] += 1
@@ -1664,7 +1603,7 @@ def process_body(
         feature_type = _feature_type_for_city(city)
         name = name_feature(
             voice, feature_type, ctx, blocklist, corpus, body_used,
-            stem_counts, stem_cap, system_hook, system_id,
+            system_hook, system_id,
             world_seed, body_id, city.get("id") or "city_?",
             hop, log, verbose,
         )
@@ -1677,12 +1616,12 @@ def process_body(
     # Rivers
     for river in markers.get("rivers") or []:
         if not _is_blank(river.get("name")):
-            corpus.setdefault((hop, corridor, "river"), set()).add(river["name"])
+            corpus.setdefault((system_id, "river"), set()).add(river["name"])
             counts["preserved"] += 1
             continue
         name = name_feature(
             voice, "river", ctx, blocklist, corpus, body_used,
-            stem_counts, stem_cap, system_hook, system_id,
+            system_hook, system_id,
             world_seed, body_id, river.get("id") or "river_?",
             hop, log, verbose,
         )
@@ -1695,7 +1634,7 @@ def process_body(
     # Oceans / seas / lakes
     for water in markers.get("oceans") or []:
         if not _is_blank(water.get("name")):
-            corpus.setdefault((hop, corridor, _feature_type_for_ocean(water)), set()).add(
+            corpus.setdefault((system_id, _feature_type_for_ocean(water)), set()).add(
                 water["name"]
             )
             counts["preserved"] += 1
@@ -1703,7 +1642,7 @@ def process_body(
         feature_type = _feature_type_for_ocean(water)
         name = name_feature(
             voice, feature_type, ctx, blocklist, corpus, body_used,
-            stem_counts, stem_cap, system_hook, system_id,
+            system_hook, system_id,
             world_seed, body_id, water.get("id") or "water_?",
             hop, log, verbose,
         )
@@ -1716,14 +1655,14 @@ def process_body(
     # Mountain ranges
     for rng_feat in markers.get("mountain_ranges") or []:
         if not _is_blank(rng_feat.get("name")):
-            corpus.setdefault((hop, corridor, "mountain_range"), set()).add(
+            corpus.setdefault((system_id, "mountain_range"), set()).add(
                 rng_feat["name"]
             )
             counts["preserved"] += 1
             continue
         name = name_feature(
             voice, "mountain_range", ctx, blocklist, corpus, body_used,
-            stem_counts, stem_cap, system_hook, system_id,
+            system_hook, system_id,
             world_seed, body_id, rng_feat.get("id") or "range_?",
             hop, log, verbose,
         )
@@ -1736,7 +1675,7 @@ def process_body(
     # POIs
     for poi in markers.get("pois") or []:
         if not _is_blank(poi.get("name")):
-            corpus.setdefault((hop, corridor, _feature_type_for_poi(poi)), set()).add(
+            corpus.setdefault((system_id, _feature_type_for_poi(poi)), set()).add(
                 poi["name"]
             )
             counts["preserved"] += 1
@@ -1744,7 +1683,7 @@ def process_body(
         feature_type = _feature_type_for_poi(poi)
         name = name_feature(
             voice, feature_type, ctx, blocklist, corpus, body_used,
-            stem_counts, stem_cap, system_hook, system_id,
+            system_hook, system_id,
             world_seed, body_id, poi.get("id") or "poi_?",
             hop, log, verbose,
         )
@@ -1862,14 +1801,6 @@ def main():
         default=42,
         help="World seed for deterministic naming (default: 42)",
     )
-    parser.add_argument(
-        "--stem-cap",
-        type=int,
-        default=20,
-        help="Max times any single cultural stem (e.g. 'Arcturus', "
-             "'Meridian') may appear across the full run before dedup "
-             "starts rejecting it. 0 = disabled. Default: 20.",
-    )
     parser.add_argument(
         "--log",
         default=str(REPO_ROOT / ".tmp" / "gemma_naming.log"),
@@ -1968,8 +1899,7 @@ def main():
     log.raw(f"  sr-voice: {MOCK_STDIO if args.mock else sr_voice_bin}")
     if not args.mock:
         log.raw(f"  model: {model_path}")
-    log.raw(f"  seed: {args.seed}   refresh: every {args.refresh} requests   "
-            f"stem-cap: {args.stem_cap}")
+    log.raw(f"  seed: {args.seed}   refresh: every {args.refresh} requests")
     log.raw(f"  {len(markers_paths)} markers.json files to process")
     log.raw(f"  hop {first_hop} → hop {last_hop}, core-first ordering")
     log.raw(f"  {total_systems} distinct systems")
@@ -1983,8 +1913,7 @@ def main():
     )
     log.raw("")
 
-    corpus: dict[tuple[str, str], set[str]] = {}
-    stem_counts: dict[str, int] = {}
+    corpus: dict[tuple, set[str]] = {}
 
     # Cache of system_id → proper_name so we can emit a header line the
     # first time we hit each system without re-querying per body.
@@ -2046,8 +1975,6 @@ def main():
                     conn=conn,
                     blocklist=blocklist,
                     corpus=corpus,
-                    stem_counts=stem_counts,
-                    stem_cap=args.stem_cap,
                     system_hook=system_gttr_hooks.get(system_id),
                     world_seed=args.seed,
                     hop=hop,