livepilot 1.18.0 → 1.18.2

package/CHANGELOG.md

@@ -1,5 +1,199 @@
 # Changelog
 
+## 1.18.2 — Wonder cold-start + tie-break + genre catalog closure (April 24 2026)
+
+Second patch in the v1.18.x series. Three items from the v1.18.0/v1.18.1
+Known Issues list resolved. Test suite grew to 2785 pass, xfail marker
+removed (formerly 1, now 0).
+
+### Fixes
+
+- **#10 Wonder Mode zero-variant degradation on empty session context.**
+  `enter_wonder_mode` on an empty/sparse session was returning 3
+  IDENTICAL `analytical_only` variants all with intent "Analytical
+  suggestion for: <request>". Live-verified during v1.18.0 Test 4
+  ("I'm stuck" on a 4-track empty session). Fix: introduced
+  `_COLD_START_SEEDS` in `mcp_server/wonder_mode/engine.py` — three
+  distinct starting-point suggestions covering different families
+  (`device_creation × rhythmic` + `sound_design × harmonic` +
+  `mix × architecture-first`). When `executable_count == 0`, the
+  padding loop uses `build_cold_start_variant()` which pulls from
+  the seed set by index, producing genuinely distinct variants with
+  specific actionable `what_changed` / `why_it_matters` text.
+  Partial-match case (1-2 executable) still uses the generic
+  fallback to avoid mixing real moves with architecture-first seeds.
+
+- **#11 Experiment ranking tie-break coarseness.**
+  `ExperimentSet.ranked_branches()` was a single-key sort by score,
+  producing unstable rankings at score ties. Live-verified in v1.18.0
+  Test 8 — 3-branch experiment with `add_space` + `add_warmth` +
+  `widen_stereo` all scored 0.6 with no clear winner. Fix: composite
+  sort key via new `_branch_rank_key()` helper, in priority order:
+  (1) `-score` (primary, higher wins), (2) `-novelty_rank` (higher
+  novelty wins score ties — creative asks reward variation),
+  (3) `risk_rank` (lower risk wins secondary ties — safety default),
+  (4) `step_count` (simpler plans win tertiary ties),
+  (5) `branch_id` (deterministic final tiebreak for reproducibility).
+
+- **Concept packet catalog closure.** 13 new genre YAMLs
+  (drone, downtempo, lo_fi, boom_bap, footwork, techno,
+  detroit_techno, synthwave, deep_house, disco, soul, dub, hyperpop)
+  + 15 too-generic/narrow refs removed from 12 artist packets
+  (electronic ×5, electronica, bass_music, cinematic, acid_techno,
+  french_house, nu_disco, soulful_house, vaporwave, juke, jungle).
+  The xfailing `test_all_artist_genre_refs_resolve_strictly` test
+  is now a required green pass. The concept surface has full graph
+  closure — every artist→genre cross-reference resolves to an actual
+  genre YAML's `id` field.
+
+### Tests added / changed
+
+- `test_wonder_cold_start_has_distinct_variants` (new — guards
+  against regression to the 3-identical-generics degradation)
+- `test_experiment_tie_break_prefers_higher_novelty` (new — unexpected
+  > strong > safe at equal scores)
+- `test_experiment_tie_break_is_deterministic` (new — ranking stable
+  across input order)
+- `test_all_artist_genre_refs_resolve_strictly` (was xfailing, now
+  passing — xfail marker removed)
+- `test_concept_packets_count` (floor updated 14 → 27 genres)
+
+### Still open for v1.18.3 / v1.19
+
+5 items remain from the original v1.18.0 Known Issues list:
+
+- **#7 Packet `avoid` list runtime enforcement** (still advisory —
+  pre-flight check against tool args needed)
+- **#8 `locked_dimensions` runtime enforcement** (same pattern as #7)
+- **Experiment state continuity between branches** (before-snapshot
+  drift)
+- **Hybrid-packet compilation algorithm** (union/intersection logic
+  for "Basic Channel meets Dilla")
+- **Full architectural fix for #3** (route director Phase 6 through
+  semantic_move commits — big redesign, v1.19 scope)
+
+These all need new infrastructure or architectural decisions
+unsuitable for a patch release.
+
+## 1.18.1 — Director HIGH-severity patches (April 23 2026)
+
+Patch release addressing 4 of the 12 known issues documented in v1.18.0.
+All three HIGH-severity bugs are fixed, plus 6 medium-severity items
+(data cleanups and doc clarifications). All fixes landed with
+regression-guard tests. 2779 project tests pass + 1 xfail (pre-existing).
+
+### High-severity fixes
+
+- **#1 `create_experiment` auto-proposal returned single-char move_ids.**
+  Python unpacking bug at `mcp_server/experiment/tools.py:267` —
+  `[m[0] for m, _ in scored]` indexed the first character of each
+  move_id string. Fix: `[move_id for move_id, _ in scored[:limit]]`.
+  Pre-fix, calling the director's Flow B with no explicit seeds/move_ids
+  would always fail at run_experiment with `"Move t not found"`.
+
+- **#2 `propose_composer_branches` ignored concept-packet arrangement
+  idioms.** Dub-techno prompts (referencing Basic Channel, Gas, etc.)
+  were collapsed to the generic techno template (Intro→Build→Drop→
+  Breakdown→Drop 2→Outro with 6 standard layers). Fix: "dub techno"
+  is now its own canonical genre in `GENRE_DEFAULTS` and
+  `SECTION_TEMPLATES`, with a continuous-evolution scaffold
+  (Dawn→Pulse→Chord→Depth→Withdraw→Return, 3-5 layers, energy 0.4).
+  Removed the `dub techno → techno` alias that was causing the
+  collapse; added `dub-techno` (hyphenated) as an alias to the new
+  canonical.
+
+- **#3 Director raw-tool-call path bypassed the action ledger.**
+  Min-effective doc fix: Phase 6 of `livepilot-creative-director`
+  now mandates `add_session_memory(category="move_executed", ...)`
+  after raw-tool execution batches, so anti-repetition detection on
+  subsequent creative turns isn't blind. Added a state-inference
+  fallback table in `anti-repetition-rules.md` for when the ledger
+  is still empty (infer recent family from loaded devices, non-default
+  mixer state, clip slot contents). Full architectural fix (route all
+  Phase 6 execution through `apply_semantic_move`/`commit_experiment`)
+  is deferred to v1.19.
+
+### Medium-severity fixes
+
+- **#4 Ping Pong Delay ghost packet.** `affordances/devices/ping-pong-delay.yaml`
+  previously described a standalone device that doesn't exist in
+  Live 12 (`search_browser` returned empty). Rewritten as an explicit
+  mode-alias for Echo with `Channel Mode = 1`. `echo.yaml` now prominently
+  documents the Channel Mode enum (0=Stereo, 1=Ping Pong, 2=Mid/Side).
+
+- **#5 Auto Filter affordance used legacy 20-135 Hz ranges.** Modern
+  `AutoFilter2` class (Live 12 default) uses 0-1 normalized for
+  Frequency, Resonance, and LFO Amount. Live-verified mapping (raw
+  0.45 → display 448 Hz) is now documented in the YAML. Legacy/modern
+  distinction clarified in the notes.
+
+- **#9 `propose_composer_branches` silent count degradation.** Explicit
+  `count=3` at `freshness<0.7` was silently returning 2 seeds because
+  `layer_contrast` was gated behind `freshness>=0.7`. Fix: explicit
+  `count>=3` now raises freshness internally to 0.7 to admit all
+  strategies. Default `count=2` (no override) still respects the
+  freshness gate — preserves the "freshness shapes default strategy
+  count" contract and the existing tests that assert it.
+
+- **#12 Low-novelty-budget escape hatch for 3-plan diversity rule.**
+  `move-family-diversity-rule.md` gained a dedicated section: when
+  `novelty_budget < 0.35` (user prompts like "keep the vibe, just
+  cleaner"), 1-2 family plans is acceptable and honest. Prevents the
+  rule from fighting cleanup requests.
+
+### Bonus fixes
+
+- **`batch_set_parameters` schema gotcha documented.** Core SKILL.md
+  Rule 15 now shows the correct dict-of-dicts shape:
+  `{"ParamName": {"value": v}}`. Live verification surfaced this during
+  v1.18.0 pressure testing.
+
+- **Convolution Reverb phantom `ir_length` already fixed in v1.18.0
+  commit 9** — regression test now guards against reintroduction.
+
+### Tests added
+
+- `test_create_experiment_auto_proposal_no_m0_bug` (source-pattern
+  regression guard)
+- `test_create_experiment_auto_proposal_functional` (mirror-logic
+  integration check)
+- `test_composer_dub_techno_prompt_avoids_drop_scaffold` (no Drop/Drop 2
+  on Basic Channel prompts)
+- `test_propose_composer_branches_honors_explicit_count` (count=3
+  returns 3 regardless of freshness)
+- `test_medium_freshness_count_3_unlocks_all_strategies` (renamed from
+  test encoding the pre-fix bug as desired behavior)
+- `test_medium_freshness_default_count_gives_two` (preserves
+  default-count-respects-freshness contract)
+- `test_ping_pong_delay_is_documented_as_echo_mode`
+- `test_auto_filter_ranges_are_normalized_for_modern_class`
+- `test_low_novelty_escape_hatch_documented`
+- `test_batch_set_parameters_schema_documented`
+- `test_director_phase6_records_ledger_marker`
+- `test_anti_repetition_has_state_inference_fallback`
+
+### Still open for v1.18.2 / v1.19
+
+8 items remain from the v1.18.0 Known Issues list:
+
+- **#7 Packet `avoid` list runtime enforcement** (currently advisory —
+  pre-flight check against tool args needed)
+- **#8 `locked_dimensions` runtime enforcement** (same pattern as #7)
+- **#10 Wonder Mode zero-variant degradation on empty session context**
+- **#11 Evaluation tie-break coarseness** (3-way ties at score 0.6)
+- **Experiment state continuity between branches** (before-snapshot
+  drift)
+- **Hybrid-packet compilation algorithm** (union/intersection logic
+  for "Basic Channel meets Dilla")
+- **~20 missing genre YAMLs** (downtempo, boom_bap, lo_fi, synthwave,
+  techno, etc.) — xfail test tracks this
+- **Full architectural fix for #3** (route director Phase 6 through
+  semantic_move commits, replacing the doc-level fix shipped here)
+
+These are each scoped for focused follow-up sessions — they need new
+infrastructure or architectural decisions not suitable for a patch
+release.
+
 ## 1.18.0 — Creative Director + concept packets + device affordances (April 23 2026)
 
 A structural feature release. Addresses the "agent doesn't variate

package/mcp_server/__init__.py

@@ -1,2 +1,2 @@
 """LivePilot MCP Server — bridges MCP protocol to Ableton Live."""
-__version__ = "1.18.0"
+__version__ = "1.18.2"

package/mcp_server/composer/branch_producer.py

@@ -124,7 +124,18 @@ def propose_composer_branches(
 
     intent = parse_prompt(request_text)
 
-    # Gate high-novelty strategies on freshness.
+    # v1.18.1 #9 fix: explicit count=3 overrides the freshness default.
+    # Pre-fix, count=3 at freshness=0.6 silently returned 2 (canonical +
+    # energy_shift only; layer_contrast was gated behind freshness>=0.7).
+    # Now: caller asking for all 3 strategies gets them by internally
+    # raising freshness to 0.7. Count=2 (the default) does NOT raise
+    # freshness — the freshness gate still caps at 1 on low-freshness
+    # runs, which is the documented "freshness cautiously shapes default
+    # strategy count" contract.
+    if count >= 3:
+        freshness = max(freshness, 0.7)
+
+    # Gate high-novelty strategies on (possibly-raised) freshness.
     if freshness < 0.4:
         strategies = [_STRATEGIES[0]]  # canonical only
     elif freshness < 0.7:

package/mcp_server/composer/layer_planner.py

@@ -172,6 +172,19 @@ SECTION_TEMPLATES: dict[str, list[dict]] = {
         {"name": "Drop 2",   "bars": 16, "layers": ["drums", "bass", "lead", "percussion", "vocal", "texture"]},
         {"name": "Outro",     "bars": 8,  "layers": ["drums:-6dB", "texture", "pad"]},
     ],
+    # Dub techno — continuous-evolution aesthetic. No Drop structure, no
+    # Build/Break cycle. Section names reflect dub-techno arrangement idioms:
+    # slow reveal, subtraction before addition, return deeper not louder.
+    # Source: concepts/artists/basic-channel.yaml arrangement_idioms +
+    # live-verification finding from v1.18.0 CHANGELOG #2. v1.18.1 #2 fix.
+    "dub techno": [
+        {"name": "Dawn",      "bars": 16, "layers": ["texture:-12dB"]},
+        {"name": "Pulse",     "bars": 16, "layers": ["drums:-6dB", "texture"]},
+        {"name": "Chord",     "bars": 32, "layers": ["drums", "bass", "pad:-6dB", "texture"]},
+        {"name": "Depth",     "bars": 32, "layers": ["drums", "bass", "pad", "texture"]},
+        {"name": "Withdraw",  "bars": 16, "layers": ["pad:-6dB", "texture:-6dB"]},
+        {"name": "Return",    "bars": 16, "layers": ["texture:-12dB"]},
+    ],
     "house": [
         {"name": "Intro",     "bars": 8,  "layers": ["drums:-6dB", "pad"]},
         {"name": "Verse",     "bars": 16, "layers": ["drums", "bass", "pad"]},

package/mcp_server/composer/prompt_parser.py

@@ -51,6 +51,13 @@ GENRE_DEFAULTS: dict[str, dict] = {
         "tempo": 128, "keys": ["Am", "Cm"], "energy": 0.7,
         "layers_min": 5, "layers_max": 7,
     },
+    # Dub techno is its own canonical genre — continuous-evolution aesthetic
+    # referencing Basic Channel / Rhythm & Sound / Gas. Previously aliased to
+    # "techno" which defaulted to Drop-based scaffolds (v1.18.1 #2 fix).
+    "dub techno": {
+        "tempo": 125, "keys": ["Am", "Em"], "energy": 0.4,
+        "layers_min": 3, "layers_max": 5,
+    },
     "house": {
         "tempo": 124, "keys": ["Cm", "Fm"], "energy": 0.6,
         "layers_min": 5, "layers_max": 6,
@@ -93,7 +100,11 @@ _GENRE_ALIASES: dict[str, str] = {
     "industrial techno": "techno",
     "minimal techno": "techno",
     "detroit techno": "techno",
-    "dub techno": "techno",
+    # NOTE: "dub techno" is intentionally NOT aliased to "techno" —
+    # it's now its own canonical genre with dub-appropriate defaults
+    # (see GENRE_DEFAULTS above) and a non-Drop section template (see
+    # layer_planner.SECTION_TEMPLATES).  v1.18.1 #2 fix.
+    "dub-techno": "dub techno",
 }
 
 

package/mcp_server/experiment/models.py

@@ -194,6 +194,52 @@ class ExperimentBranch:
         return d
 
 
+# v1.18.2 #11: composite tie-break ranking for experiment branches.
+# Maps novelty_label / risk_label strings to integer ranks.
+_NOVELTY_RANK: dict[str, int] = {
+    "safe": 0,
+    "medium": 1,       # rarely used, but accept it for robustness
+    "strong": 1,
+    "unexpected": 2,
+    "bold": 2,         # alias in some producer outputs
+}
+_RISK_RANK: dict[str, int] = {
+    "low": 0,
+    "medium": 1,
+    "high": 2,
+}
+
+
+def _branch_rank_key(branch: "ExperimentBranch") -> tuple:
+    """Composite sort key for ExperimentSet.ranked_branches().
+
+    Returns a tuple (-score, -novelty, risk, step_count, branch_id) such
+    that Python's default ascending sort produces the desired ranking:
+    higher scores first, then higher novelty at score ties, then lower
+    risk under equal novelty, then simpler plans, then branch_id as a
+    deterministic final tiebreak.
+    """
+    score = float(getattr(branch, "score", 0.0) or 0.0)
+    seed = getattr(branch, "seed", None)
+
+    if seed is not None:
+        novelty_label = (seed.novelty_label or "").lower()
+        risk_label = (seed.risk_label or "").lower()
+    else:
+        novelty_label = ""
+        risk_label = ""
+
+    novelty_rank = _NOVELTY_RANK.get(novelty_label, 1)  # middle if unknown
+    risk_rank = _RISK_RANK.get(risk_label, 1)
+
+    plan = getattr(branch, "compiled_plan", None) or {}
+    step_count = int(plan.get("step_count", 0) or 0)
+
+    branch_id = getattr(branch, "branch_id", "") or ""
+
+    return (-score, -novelty_rank, risk_rank, step_count, branch_id)
+
+
 @dataclass
 class ExperimentSet:
     """A collection of branches being compared for one request."""
@@ -215,9 +261,33 @@ class ExperimentSet:
         return None
 
     def ranked_branches(self) -> list[ExperimentBranch]:
-        """Return branches sorted by score descending."""
+        """Return evaluated branches sorted by composite rank.
+
+        v1.18.2 #11 fix: pre-fix this was a single-key sort by score,
+        which produced unstable rankings at score ties (live-verified in
+        v1.18.0 Test 8 — three branches at 0.6 with no winner).
+
+        Sort keys, in priority order:
+          1. -score                     — higher score wins
+          2. -novelty_rank              — higher novelty wins at score ties
+                                          (creative asks reward variation)
+          3. risk_rank                  — lower risk wins secondary ties
+                                          (safety default under equal novelty)
+          4. step_count                 — simpler plans win tertiary ties
+          5. branch_id                  — deterministic final tiebreak
+                                          (stable ranking across equal branches)
+
+        Novelty labels rank: "safe"=0, "strong"=1, "unexpected"=2, "bold"=2.
+        Risk labels rank: "low"=0, "medium"=1, "high"=2.
+        Unknown labels default to the middle (1).
+        """
         evaluated = [b for b in self.branches if b.status == "evaluated"]
-        return sorted(evaluated, key=lambda b: -b.score)
+        return sorted(evaluated, key=_branch_rank_key)
+
+    # expose the key function for testing + custom rankers
+    def rank_key_for(self, branch: "ExperimentBranch") -> tuple:
+        """Return the composite rank key for a branch (for tie-break debugging)."""
+        return _branch_rank_key(branch)
 
     def to_dict(self) -> dict:
         return {

package/mcp_server/experiment/tools.py

@@ -244,18 +244,22 @@ def create_experiment(
 
     # ── Mode 2/3: legacy move_ids path ──────────────────────────────────
     if not move_ids:
-        # Auto-propose moves from the registry
+        # Auto-propose moves from the registry by keyword overlap.
+        # v1.18.1 #1 fix: the previous selector indexed the first character
+        # of each move_id (a Python unpacking trap — the variable was
+        # already the full string, the [0] subscript sliced into it).
+        # Result pre-fix: single-char move_ids like 't', 'w', 'm' that
+        # failed at run_experiment with "Move t not found". Now the whole
+        # move_id string is kept.
         from ..semantic_moves import registry
-        from ..semantic_moves.tools import propose_next_best_move
-        # Use the propose function's logic directly
         all_moves = list(registry._REGISTRY.values())
         request_lower = request_text.lower()
-        scored = []
+        request_words = set(request_lower.split())
+        scored: list[tuple[str, float]] = []
         for move in all_moves:
             score = 0.0
             move_words = set(move.move_id.replace("_", " ").split())
             intent_words = set(move.intent.lower().split())
-            request_words = set(request_lower.split())
             overlap = request_words & (move_words | intent_words)
             score += len(overlap) * 0.3
             for dim in move.targets:
@@ -264,7 +268,7 @@ def create_experiment(
             if score > 0.1:
                 scored.append((move.move_id, score))
         scored.sort(key=lambda x: -x[1])
-        move_ids = [m[0] for m, _ in scored[:limit]] if scored else []
+        move_ids = [move_id for move_id, _ in scored[:limit]] if scored else []
 
     if not move_ids:
         return {"error": "No matching semantic moves found for this request"}

package/mcp_server/wonder_mode/engine.py

@@ -321,6 +321,82 @@ def build_analytical_variant(label: str, request_text: str, novelty_level: float
     }
 
 
+# v1.18.2 #10 fix: distinct cold-start variant seeds for empty/sparse
+# sessions. Used when no semantic moves match the request. Each seed has
+# a specific `what_changed` + `why_it_matters` covering a different
+# starting-point family (device_creation × rhythm + device_creation ×
+# harmony + mix-architecture-first). Replaces the 3-identical-generics
+# degradation that v1.18.0 Test 4 surfaced.
+_COLD_START_SEEDS: list[dict] = [
+    {
+        "label": "safe",
+        "family": "device_creation",
+        "intent": "Begin with a rhythmic foundation",
+        "what_changed": "Load a drum kit (Drum Rack or Core Kit) on a fresh MIDI track, program a 4-bar kick-and-hat pattern",
+        "what_preserved": "blank slate — first move sets the tempo and grid foundation",
+        "why_it_matters": "Every track needs a rhythmic anchor before timbral or structural work. Safe starting point — drums-first is the most common composition entry.",
+        "novelty_level": 0.3,
+        "identity_effect": "establishes",
+    },
+    {
+        "label": "strong",
+        "family": "sound_design",
+        "intent": "Begin with a harmonic source",
+        "what_changed": "Load Drift or Meld on a MIDI track with a chord-stab patch (short attack, moderate release, slight detune), sketch a 2-bar chord pattern",
+        "what_preserved": "tempo and key are still open to discovery — lets the harmony suggest the rhythm",
+        "why_it_matters": "A harmonic source opens a different emotional palette than drums-first. Chord-first composition (Isolée / Luomo style) is less common but produces distinctive results.",
+        "novelty_level": 0.55,
+        "identity_effect": "establishes",
+    },
+    {
+        "label": "unexpected",
+        "family": "mix",
+        "intent": "Begin with the space, not the source",
+        "what_changed": "Configure return tracks BEFORE any instrument work — set up Return A with Convolution Reverb (cathedral IR) and Return B with Echo in ping-pong mode",
+        "what_preserved": "the blank slate IS the canvas; the sends are the frame you'll paint into",
+        "why_it_matters": "Dub techno and ambient producers (Basic Channel, Gas, Henke) build sound AROUND pre-configured sends. Unusual but genre-appropriate starting point.",
+        "novelty_level": 0.85,
+        "identity_effect": "establishes",
+    },
+]
+
+
+def build_cold_start_variant(seed: dict, request_text: str, variant_id: str = "") -> dict:
+    """Build a cold-start variant seed for an empty/sparse session.
+
+    Used when no semantic moves match the request. Returns a variant with
+    distinct, actionable `what_changed` / `why_it_matters` text — NOT the
+    generic 'No matching moves found' fallback. Each seed covers a
+    different starting-point family; together they give the user three
+    genuinely distinct first-moves to choose from.
+
+    See `_COLD_START_SEEDS` for the seed set. The variant is
+    `analytical_only=True` (no compiled_plan) — turning these into
+    one-click executable plans is a v1.19 enhancement.
+    """
+    return {
+        "variant_id": variant_id,
+        "label": seed["label"],
+        "move_id": "",
+        "family": seed["family"],
+        "intent": seed["intent"],
+        "what_changed": seed["what_changed"],
+        "what_preserved": seed["what_preserved"],
+        "why_it_matters": seed["why_it_matters"],
+        "identity_effect": seed["identity_effect"],
+        "novelty_level": seed["novelty_level"],
+        "taste_fit": 0.5,
+        "targets_snapshot": {},
+        "compiled_plan": None,
+        "score": 0.0,
+        "rank": 0,
+        "score_breakdown": {},
+        "analytical_only": True,
+        "distinctness_reason": f"Cold-start seed ({seed['family']}) — empty session, no moves matched",
+        "cold_start": True,
+    }
+
+
 # ── Taste fit scoring ────────────────────────────────────────────
 
 
@@ -577,16 +653,37 @@ def generate_wonder_variants(
 
     executable_count = len(variants)
 
-    # Pad with analytical variants
-    while len(variants) < 3:
-        idx = len(variants)
-        v = build_analytical_variant(
-            label=labels[idx],
-            request_text=request_text,
-            novelty_level=_NOVELTY_LEVELS.get(labels[idx], 0.5),
-            variant_id=f"{set_prefix}_{labels[idx]}",
-        )
-        variants.append(v)
+    # v1.18.2 #10 fix: when NO executable moves matched, seed from the
+    # cold-start distinct-starting-points set instead of padding with
+    # identical generic analytical variants. Pre-fix, cold-start on an
+    # empty session returned 3 variants all with the same generic
+    # "No matching moves found" text — unhelpful to the user.
+    #
+    # The partial-match case (1 or 2 executable variants) still pads with
+    # the generic analytical fallback because we don't want to mix real
+    # move-based variants with architecture-first seeds — that would
+    # confuse the presentation.
+    if executable_count == 0:
+        while len(variants) < 3:
+            idx = len(variants)
+            seed = _COLD_START_SEEDS[idx]
+            v = build_cold_start_variant(
+                seed=seed,
+                request_text=request_text,
+                variant_id=f"{set_prefix}_{seed['label']}",
+            )
+            variants.append(v)
+    else:
+        # Partial-match: pad to 3 with generic analytical variants
+        while len(variants) < 3:
+            idx = len(variants)
+            v = build_analytical_variant(
+                label=labels[idx],
+                request_text=request_text,
+                novelty_level=_NOVELTY_LEVELS.get(labels[idx], 0.5),
+                variant_id=f"{set_prefix}_{labels[idx]}",
+            )
+            variants.append(v)
 
     novelty_band = 0.5
     taste_evidence = 0
@@ -603,7 +700,13 @@ def generate_wonder_variants(
 
     degraded_reason = ""
     if executable_count == 0:
-        degraded_reason = "No matching executable moves found"
+        # v1.18.2 #10: cold-start path — distinct starting-point seeds
+        # rather than identical-generic padding.
+        degraded_reason = (
+            "No matching executable moves — cold-start variants seeded "
+            "from distinct starting-point families (device_creation × 2 "
+            "+ mix-architecture-first)"
+        )
     elif executable_count == 1:
         degraded_reason = "Only 1 distinct executable move found"
 

package/package.json

@@ -1,6 +1,6 @@
 {
   "name": "livepilot",
-  "version": "1.18.0",
+  "version": "1.18.2",
   "mcpName": "io.github.dreamrec/livepilot",
   "description": "Agentic production system for Ableton Live 12 — 427 tools, 52 domains. Device atlas (1305 devices), sample engine (Splice + browser + filesystem), auto-composition, spectral perception, technique memory, creative intelligence (12 engines)",
   "author": "Pilot Studio",

package/remote_script/LivePilot/__init__.py

@@ -5,7 +5,7 @@ Entry point for the ControlSurface. Ableton calls create_instance(c_instance)
 when this script is selected in Preferences > Link, Tempo & MIDI.
 """
 
-__version__ = "1.18.0"
+__version__ = "1.18.2"
 
 from _Framework.ControlSurface import ControlSurface
 from . import router

package/server.json

@@ -6,12 +6,12 @@
     "url": "https://github.com/dreamrec/LivePilot",
     "source": "github"
   },
-  "version": "1.18.0",
+  "version": "1.18.2",
   "packages": [
     {
       "registryType": "npm",
       "identifier": "livepilot",
-      "version": "1.18.0",
+      "version": "1.18.2",
       "transport": {
         "type": "stdio"
       }