livepilot 1.27.1 → 1.27.3

package/livepilot/skills/livepilot-core/references/overview.md

@@ -1,4 +1,4 @@
-# LivePilot v1.27.1 — Architecture & Tool Reference
+# LivePilot v1.27.3 — Architecture & Tool Reference
 
 Agentic production system for Ableton Live 12. 467 tools across 56 domains. Device atlas (5264 devices, 120 enriched, 47 with aesthetic-tagged `signature_techniques`), spectral perception (M4L analyzer with 9-band FFT — sub_low / sub / low / low_mid / mid / high_mid / high / presence / air), technique memory, automation intelligence (16 curve types, 15 recipes), music theory (Krumhansl-Schmuckler, species counterpoint), generative algorithms (Euclidean rhythm, tintinnabuli, phase shift, additive process), neo-Riemannian harmony (PRL transforms, Tonnetz), MIDI file I/O, **LIVE Splice describe-a-sound + variations via captured GraphQL endpoints (v1.17)**, drum-rack pad-by-pad construction, live dead-device detection via meter sampling, role-aware Simpler defaults, session-record arrangement-automation workaround.
 
@@ -44,9 +44,16 @@ A flat tool list lets the AI press buttons. LivePilot's three layers give it con
 
 This turns "set EQ band 3 to -4 dB" into "cut 400 Hz by 4 dB, then read the spectrum to confirm the mud is actually reduced."
 
-## The 467 Tools — What Each One Does
+## Core-Domain Reference (~228 tools, 13 of 56 domains)
 
-### Transport (12) — Playback, tempo, global state, diagnostics
+This section documents the 13 highest-traffic domains in prose (what each
+tool does, when to reach for it). It is intentionally NOT exhaustive — the
+remaining domains (sample_engine, atlas, agent_os, wonder_mode, and the rest
+of the Creative Intelligence layer) are covered by their own domain skills
+and by the auto-generated **[Tool Catalog](../../../../docs/manual/tool-catalog.md)**,
+which lists all 467 tools across all 56 domains.
+
+### Transport (showing 12 of 21) — Playback, tempo, global state, diagnostics
 
 | Tool | What it does | Key params |
 |------|-------------|------------|
@@ -63,7 +70,7 @@ This turns "set EQ band 3 to -4 dB" into "cut 400 Hz by 4 dB, then read the spec
 | `get_recent_actions` | Returns log of recent commands sent to Ableton (newest first) | `limit` (1-50, default 20) |
 | `get_session_diagnostics` | Analyzes session for issues: armed tracks, solo leftovers, unnamed tracks, empty clips | — |
 
-### Tracks (14) — Create, delete, configure, group tracks
+### Tracks (showing 14 of 21) — Create, delete, configure, group tracks
 
 | Tool | What it does | Key params |
 |------|-------------|------------|
@@ -82,7 +89,7 @@ This turns "set EQ band 3 to -4 dB" into "cut 400 Hz by 4 dB, then read the spec
 | `set_group_fold` | Folds/unfolds a group track | `track_index`, `folded` (bool) |
 | `set_track_input_monitoring` | Sets input monitoring state | `track_index`, `state` (0=In, 1=Auto, 2=Off) |
 
-### Clips (11) — Clip lifecycle, properties, warp
+### Clips (showing 11 of 16) — Clip lifecycle, properties, warp
 
 | Tool | What it does | Key params |
 |------|-------------|------------|
@@ -122,7 +129,7 @@ This turns "set EQ band 3 to -4 dB" into "cut 400 Hz by 4 dB, then read the spec
 - `velocity_deviation` — -127.0 to 127.0
 - `release_velocity` — 0.0-127.0
 
-### Devices (15) — Instruments, effects, racks, 12.3+ device insertion
+### Devices (showing 15 of 42) — Instruments, effects, racks, 12.3+ device insertion
 
 | Tool | What it does | Key params |
 |------|-------------|------------|
@@ -142,7 +149,7 @@ This turns "set EQ band 3 to -4 dB" into "cut 400 Hz by 4 dB, then read the spec
 | `set_chain_volume` | Sets volume of a rack chain | `track_index`, `device_index`, `chain_index`, `volume` |
 | `get_device_presets` | Lists presets for a device (audio effects, instruments, MIDI effects) | `device_name` |
 
-### Scenes (8) — Scene management
+### Scenes (showing 8 of 12) — Scene management
 
 | Tool | What it does | Key params |
 |------|-------------|------------|
@@ -180,7 +187,7 @@ This turns "set EQ band 3 to -4 dB" into "cut 400 Hz by 4 dB, then read the spec
 | `search_browser` | Searches the browser | `query` |
 | `load_browser_item` | Loads a browser item onto a track — **`uri` MUST come from `search_browser` results, NEVER invented** | `track_index`, `uri` |
 
-### Arrangement (20) — Timeline, recording, cue points, arrangement notes
+### Arrangement (showing 20 of 21) — Timeline, recording, cue points, arrangement notes
 
 | Tool | What it does | Key params |
 |------|-------------|------------|
@@ -205,7 +212,7 @@ This turns "set EQ band 3 to -4 dB" into "cut 400 Hz by 4 dB, then read the spec
 | `jump_to_cue` | Jumps to a cue point by index | `cue_index` |
 | `toggle_cue_point` | Creates/removes cue point at current position | — |
 
-### Memory (8) — Technique library persistence
+### Memory (showing 8 of 18) — Technique library persistence
 
 | Tool | What it does | Key params |
 |------|-------------|------------|
@@ -218,7 +225,7 @@ This turns "set EQ band 3 to -4 dB" into "cut 400 Hz by 4 dB, then read the spec
 | `memory_update` | Updates name, tags, or qualities | `technique_id`, `name`, `tags`, `qualities` |
 | `memory_delete` | Removes technique (backs up first) | `technique_id` |
 
-### Analyzer (38) — Real-time DSP analysis (requires LivePilot Analyzer M4L device on master track)
+### Analyzer (showing 20 of 38) — Real-time DSP analysis (requires LivePilot Analyzer M4L device on master track)
 
 | Tool | What it does | Key params |
 |------|-------------|------------|
@@ -243,7 +250,7 @@ This turns "set EQ band 3 to -4 dB" into "cut 400 Hz by 4 dB, then read the spec
 | `stop_scrub` | Stop preview | `track_index`, `clip_index` |
 | `get_display_values` | Human-readable parameter values ("440 Hz", "-6 dB") | `track_index`, `device_index` |
 
-### Automation (8) — Clip automation CRUD + intelligent curve generation
+### Automation (showing 8 of 9) — Clip automation CRUD + intelligent curve generation
 
 | Tool | What it does | Key params |
 |------|-------------|------------|

package/livepilot/skills/livepilot-core/references/perception.md

@@ -0,0 +1,125 @@
+# Perception (Analyzer) Reference
+
+Deep-dive detail for `mcp_server/tools/analyzer.py` tools. The tool
+docstrings carry a trimmed operational contract (params, ranges,
+gotchas); this file carries the full band tables, classification
+thresholds, and historical bug context that motivated each behavior.
+Read this before deep spectral/health-check work — the tool docstrings
+point back here for the parts that don't change from call to call.
+
+## `get_master_spectrum` — 9-band table
+
+Band energies (fffb~ center frequencies shown in parens), values 0.0-1.0:
+
+| Band | Range | Center | Use |
+|---|---|---|---|
+| sub_low | 20-60 Hz | ~35 Hz | kick fundamentals, deep sub-bass |
+| sub | 60-120 Hz | ~85 Hz | 808s, sub-bass body |
+| low | 120-250 Hz | ~175 Hz | bass body, warmth |
+| low_mid | 250-500 Hz | ~350 Hz | mud zone, male vocal lows |
+| mid | 500 Hz-1 kHz | ~700 Hz | vocal presence, snare body |
+| high_mid | 1-2 kHz | ~1.4 kHz | consonants, pick attack |
+| high | 2-4 kHz | ~2.8 kHz | presence, vocal intelligibility |
+| presence | 4-8 kHz | ~5.6 kHz | cymbal definition, air of breath |
+| air | 8-20 kHz | ~12 kHz | shimmer, sparkle |
+
+Older `.amxd` builds (pre-v1.16) emit the legacy 8-band layout without
+the explicit `sub_low` split — the server auto-detects band count from
+the OSC payload and picks the right name set. Re-freeze the Max device
+to get the 9-band resolution.
+
+**BUG-2026-04-22#6 fix — windowed averaging.** Kick transients make
+single snapshots swing wildly (0.45 → 0.05 → 0.16 within a bar). The
+`window_ms` param samples the cache over a time window and mean-pools
+instead of returning one instantaneous frame.
+
+**BUG-2026-04-22#15 fix — sub-band resolution.** `sub_detail=True`
+derives three finer buckets from the FluCoMa 40-band mel spectrum
+(band 0-1 ≈ sub_deep 0-45 Hz — kick fundamental, band 2 ≈ sub_mid
+45-60 Hz — 808 body/kick upper, band 3 ≈ sub_high 60-80 Hz — bass
+guitar low/sub-bass crossover). Mel band edges are perceptual, not
+linear Hz, so these are approximations tight enough for mixing
+decisions ("is energy in the 30 Hz or 60 Hz range?"). Requires FluCoMa
+active — omitted with `sub_detail_warning` otherwise.
+
+## `verify_device_health` / `verify_all_devices_health`
+
+**BUG-2026-04-22#19 fix.** `parameter_count` alone can't tell you
+whether an AU/VST is alive — plenty of "loaded" plugins return N
+params and silence. These tools fire a real test MIDI note and read
+the track meter across a window (`get_track_meters(samples=N)` to
+dodge the BUG-#7 "left=right=0 while level>0" artifact).
+
+Common dead-device causes (surfaced in the `hint` field when
+`alive=False`): (1) plugin waiting for preset/bank selection, (2)
+algorithm/envelope configured for zero output, (3) wrong MIDI channel
+or velocity curve, (4) dead VST (reinstall). Try opening the device UI
+and auditioning manually.
+
+`verify_all_devices_health` (BUG-2026-04-26#1 fix): audio-track
+detection uses `has_midi_input`/`has_audio_input` from
+`get_session_info` (earlier code checked nonexistent `is_audio_track`/
+`type` fields, so detection silently always evaluated False).
+Empty-track detection requires a `get_track_info` round-trip per track
+because `get_session_info` doesn't embed per-track `devices` arrays.
+
+## `classify_simpler_slices` — classification thresholds
+
+Validated on "Break Ghosts 90 bpm" reference material:
+- KICK: sub+low >= 45%, high < 40%
+- HAT: high >= 70% AND mid < 25% (thin metal disc = no drum body)
+- SNARE: mid >= 25% AND high >= 40% AND peak >= 0.6 (broadband loud)
+- ghost: peak < 0.35
+
+**Always run this before programming drum patterns on a sliced break.**
+Slice content depends on transient detection order in the source
+audio — slice 0 is NOT guaranteed to be a kick. Assuming drum-rack
+convention produces wrong grooves that take iterations to diagnose.
+
+File-path resolution order: explicit `file_path` param, then Remote
+Script TCP (`get_simpler_file_path` via direct LOM read — most
+reliable), then M4L bridge UDP fallback (kept registered for
+environments where Remote Script is stale/unavailable; call
+`reload_handlers` to refresh without a full restart).
+
+## `add_drum_rack_pad`
+
+**BUG-2026-04-22#1 fix** — this tool closes a gap where
+`load_browser_item` replaced the existing chain on repeat calls and
+`load_sample_to_simpler` couldn't address nested rack paths. It chains
+six steps atomically: locate/auto-detect the Drum Rack, insert a chain,
+assign the trigger note, insert an empty Simpler into the chain, native
+`replace_sample_native` with nested addressing, Snap=0 hygiene.
+
+## `replace_simpler_sample` / `load_sample_to_simpler`
+
+Prefer `load_browser_item(track, uri)` when the file is browser-indexed
+— the M4L bridge's replace path can silently keep the bootstrap
+placeholder in some conditions (this is why both tools verify by
+reading back the device name post-load and error if the replace didn't
+actually take effect).
+
+Nested addressing (`chain_index` + `nested_device_index`) is Live
+12.4+ only (BUG-#1, 2026-04-22) — resolves at
+`track.devices[device_index].chains[chain_index].devices[nested_device_index or 0]`,
+which is how Drum Rack pad-by-pad construction works. The M4L bridge
+fallback cannot resolve nested paths; only the native 12.4 path honors
+`chain_index`.
+
+`load_sample_to_simpler`'s bootstrap flow (used pre-12.4 or when no
+Simpler exists yet): loads a dummy sample via the browser to force
+Ableton to create a Simpler, replaces it with the target file, then
+runs the same post-load hygiene/verification as `replace_simpler_sample`.
+
+## `simpler_set_warp` / `compressor_set_sidechain` — LOM gap tools
+
+**BUG-A2**: Python's Remote Script ControlSurface API can't reach
+Simpler's `warping`/`warp_mode` — they live on the sample child object
+(`SimplerDevice.sample.*`) that only Max for Live's JavaScript LiveAPI
+can step into. Hence the M4L bridge round-trip.
+
+**BUG-A3**: `compressor_set_sidechain`'s routing properties
+(`sidechain_input_routing_type`/`_channel`) aren't in Compressor's
+automatable parameter list, but Python's Remote Script reaches them
+directly as device properties (same LOM pattern as `set_track_routing`)
+— no M4L bridge needed here, unlike the warp case above.

package/livepilot/skills/livepilot-devices/references/device-parameter-units.md

@@ -0,0 +1,66 @@
+# Device Parameter Units Reference
+
+Full per-device unit table for `set_device_parameter` / `batch_set_parameters`
+(`mcp_server/tools/devices.py`). The tool docstrings carry the most
+commonly-hit gotchas inline; this file is the complete list plus the
+bug history that motivated the error-enrichment behavior.
+
+## Parameter ranges are NOT always 0-1 (BUG-B4 / B9 / 2026-04-26#2)
+
+Ableton devices use MIXED units depending on the parameter. Always read
+the `value_string` in the response (and `min`/`max` from
+`get_device_parameters`) before assuming 0-1 semantics:
+
+- Auto Filter `Frequency`: 20-135 index (NOT normalized)
+- Auto Filter Legacy `LFO Amount`: 0-30 absolute (displays as %)
+- Auto Filter `Resonance`: 0-1.25 on legacy, 0-1 on AutoFilter2
+- Auto Filter `Env. Modulation`: -127..+127 on legacy
+- Compressor I (legacy): pre-2010 units (Threshold dB direct)
+- **Compressor 2 (modern, default)**: 0-1 NORMALIZED. `Threshold 0.85 ≈
+  0 dB`, `Ratio 0.75 = 4:1`, `Release 0.16 = 30 ms`. Setting Threshold
+  to a dB value like -22 will fail. Compute normalized: `(dB + 50) / 50`
+  for typical dB→0-1 mapping, OR read the param's `value_string` after
+  a probe write.
+- **Saturator** `Drive`, `Output`, `Threshold`, `Color *`: 0-1
+  NORMALIZED (Drive 0.5 ≈ 0 dB, Drive 0.6 ≈ +7 dB).
+- Dynamic Tube, Vocoder: pre-2010 units
+- EQ Three `Frequency Hi/Lo`: 50Hz-15kHz absolute
+- Wavetable `Osc 1 Pos`: 0-1 normalized ✓
+- Drift / Analog / Operator macros: 0-1 normalized ✓
+- Pedal `Output`: -20..+20 dB direct
+- Pedal `Bass / Mid / Treble`: -1..+1 direct
+
+## Error enrichment (BUG-2026-04-26#2)
+
+If the Remote Script rejects the value as out-of-range,
+`set_device_parameter` fetches the parameter's actual
+min/max/value_string and re-raises with that context inline — saves a
+follow-up `get_device_parameters` round-trip in the agent loop after
+every miss.
+
+## Silent snapping (BUG #4, v1.20.2)
+
+Quantized-enum params (e.g. Beat Repeat's "Gate" at an integer enum)
+silently snap a caller's float request to the nearest step. Both
+`set_device_parameter` (via the `snapped` field) and
+`batch_set_parameters` (via `snapped_params`, tolerance 1e-5) surface
+this so callers driving deterministic state don't mistake a snap for
+success. `batch_set_parameters` accepts any of `parameter_index`,
+`parameter_name`, `name`, `index`, or the legacy `name_or_index` per
+entry (BUG-F4 / BUG-2026-04-22#3 — the sibling tools originally had
+inconsistent schemas, so all shapes are now normalized so
+`get_device_parameters`'s output can be fed straight back in).
+
+## Drum Rack construction workflow (12.3+)
+
+Shared by `insert_device`, `insert_rack_chain`, and the atomic
+`add_drum_rack_pad` (see `perception.md` for that one's full history):
+
+1. `insert_device(track_index, 'Drum Rack')` — create empty rack
+2. `insert_rack_chain(track_index, device_index)` — add a chain
+3. `set_drum_chain_note(chain_index, note=36)` — assign C1 (kick)
+4. `insert_device(track_index, 'Simpler', device_index=rack_idx,
+   chain_index=0)` — add the instrument into that chain
+
+On Live < 12.3, `insert_device`/`insert_rack_chain` return an error
+suggesting `find_and_load_device` instead.

package/livepilot/skills/livepilot-evaluation/references/capability-modes.md

@@ -173,7 +173,7 @@ Live 12.4 introduces a new capability tier that unlocks native LOM access for sa
 **Tool signatures:** unchanged. Callers do not need to detect the tier —
 routing is transparent.
 
-**Probe-first 12.4 surfaces in v1.27.1:**
+**Probe-first 12.4 surfaces in v1.27.3:**
 - `probe_link_audio()` reports observed peer/input/routing visibility and
   returns `manual_only`, `readable`, `routable`, or `unavailable`.
 - `probe_stem_workflow()` reports observed callable paths and returns

package/livepilot/skills/livepilot-mix-engine/SKILL.md

@@ -27,6 +27,14 @@ If the M4L analyzer bridge is absent, critics fall back to role-based heuristics
 
 For detailed frequency collision data, call `get_masking_report`. For a quick status overview without the full critic pass, call `get_mix_summary`.
 
+Each masking entry carries `measured` and `severity_basis`: `measured=True` /
+`severity_basis="spectral_overlap"` means `severity` came from real per-track
+spectral data; `measured=False` / `severity_basis="role_heuristic"` means it's
+a role-pair prior with no per-track measurement behind it. Treat
+`measured=False` entries as low-confidence hypotheses, not verified problems —
+solo the pair and read `get_master_spectrum` before acting on them. See
+`livepilot-core` SKILL.md → "Response Fields You Must Check".
+
 ### Step 2 — Plan
 
 Pick the highest-severity issue from the `issues` array. Call `plan_mix_move` with the issue data. The planner returns the smallest intervention that addresses the problem — a single parameter change, not a chain of edits.

package/livepilot/skills/livepilot-release/SKILL.md

@@ -31,7 +31,7 @@ Run this checklist EVERY time the user says "update everything", "push", "releas
 Current: **467 tools across 56 domains**.
 Spectral/analyzer (bridge-only): **38**. The remaining tool surface works without the bridge or degrades gracefully. Backed by 32 bridge commands.
 
-Verify: `grep -rc "@mcp.tool" mcp_server/tools/ | grep -v ":0" | awk -F: '{sum+=$2} END{print sum}'`
+Verify: `python3 scripts/sync_metadata.py --check`
 
 Files that reference tool count:
 - [ ] `README.md` — header ("467 tools. 56 domains"), bridge section ("38 spectral/analyzer tools require bridge")

package/livepilot/skills/livepilot-sample-engine/references/splice-tools-notes.md

@@ -0,0 +1,56 @@
+# Splice Tool Notes
+
+Implementation history and worked examples for the Splice-facing tools
+in `mcp_server/sample_engine/tools.py`. The tool docstrings carry the
+operational contract (params, return shape, gating rules); this file
+carries endpoint-capture history and full response examples.
+
+## `get_splice_credits` — full response example (Ableton Live plan)
+
+```json
+{
+  "connected": true,
+  "username": "user-1367453956",
+  "plan_raw": "subscribed",
+  "plan_kind": "ableton_live",
+  "sounds_plan_id": 12,
+  "features": {"ableton_unmetered": true},
+  "credits_remaining": 80,
+  "credit_floor": 5,
+  "daily_quota": {
+    "used_today": 3, "remaining_today": 97, "daily_limit": 100,
+    "near_limit": false, "at_limit": false
+  },
+  "can_download_sample": true,
+  "download_gating": "daily_quota"
+}
+```
+
+`download_gating` is `"daily_quota"` on the Ableton Live plan (the
+100/day unmetered quota) or `"credit_floor"` on Sounds+/Creator/
+Creator+ plans (the `CREDIT_HARD_FLOOR` protects the last 5 credits).
+`connected: false` with zero credits means the Splice desktop app isn't
+running or `grpcio` isn't installed.
+
+## `splice_describe_sound` / `splice_generate_variation` — endpoint history
+
+Both hit GraphQL operations on `surfaces-graphql.splice.com`, captured
+via mitmproxy against Splice desktop 5.4.9 + the Sounds Plugin
+(status: LIVE as of 2026-04-22):
+
+- `splice_describe_sound` → `SamplesSearch` with `semantic=1` +
+  `rephrase=true`. This is the Sounds Plugin's "Describe a Sound"
+  feature — Splice's AI matches free-form descriptions like "dark
+  ambient pad with shimmer" to catalog samples.
+- `splice_generate_variation` → `AssetSimilarSoundsQuery` (the
+  right-click "Variations" menu item). Up to 10 results, no credit
+  cost — despite the tool name, this is a similarity-recommender
+  lookup, not AI audio synthesis (the "generate" naming in the original
+  handoff spec was aspirational).
+
+Both tools strip the raw GraphQL response before returning (~270KB of
+noise per call) — only the flattened sample list ships back.
+
+`splice_search_with_sound` was removed 2026-04-22 — the user does this
+in-Splice manually. The capture recipe for resurrecting it is at
+`docs/2026-04-22-splice-https-capture-recipe.md`.

package/livepilot/skills/livepilot-wonder/SKILL.md

@@ -111,6 +111,12 @@ Wonder Mode now serves two callers:
   references/move-family-diversity-rule.md)
 - 1 executable + 2 analytical is an honest, useful result
 - The `variant_count_actual` field tells you how many are real
+- **Check `degraded_reason`** on every `enter_wonder_mode` response — when
+  non-empty, fewer than 3 variants are actually executable (or none matched
+  and the set is cold-start fallback). Do not present a degraded set as
+  "three genuinely different options"; surface the degradation to the user
+  in the same terms the field describes. See `livepilot-core` SKILL.md →
+  "Response Fields You Must Check".
 
 ## Presenting Results
 

package/m4l_device/livepilot_bridge.js

@@ -34,7 +34,7 @@ outlets = 2; // 0: to udpsend (responses), 1: to buffer~/status
 // Single source of truth for the bridge version — bumped alongside the
 // rest of the release manifest. Surfaced in the UI via messnamed("livepilot_version", ...)
 // so the frozen .amxd visibly reports which build it was last exported from.
-var VERSION = "1.27.1";
+var VERSION = "1.27.3";
 
 // ── State ──────────────────────────────────────────────────────────────────
 
@@ -45,6 +45,7 @@ var pitch_history = []; // Rolling buffer for key detection
 var MAX_PITCH_HISTORY = 128;
 var detected_key = "";
 var detected_scale = "";
+var current_response_request_id = "";
 
 // Capture state
 var capture_active = false;
@@ -85,9 +86,19 @@ function anything() {
     var cmd = messagename;
     if (cmd.charAt(0) === "/") cmd = cmd.substring(1);
     var args = _decode_arg_strings(arrayfromargs(arguments));
+    var request_id = "";
+    if (args.length > 0 && typeof args[args.length - 1] === "string") {
+        var last_arg = args[args.length - 1];
+        var request_prefix = "__livepilot_request_id:";
+        if (last_arg.indexOf(request_prefix) === 0) {
+            request_id = last_arg.substring(request_prefix.length);
+            args.pop();
+        }
+    }
 
     // Defer to low-priority thread for LiveAPI safety
     var task = new Task(function() {
+        current_response_request_id = request_id;
         try {
             dispatch(cmd, args);
         } catch(e) {
@@ -223,6 +234,11 @@ function cmd_get_params(args) {
 
     var batch_size = 8;
     var current = 0;
+    // Capture the request id now: read_batch reschedules itself via
+    // Task.schedule(20), and an interleaved command arriving in that gap can
+    // overwrite the module-level current_response_request_id before the final
+    // send_response fires. The closure keeps OUR id stable across batches.
+    var captured_request_id = current_response_request_id;
 
     function read_batch() {
         try {
@@ -246,7 +262,7 @@ function cmd_get_params(args) {
                 var next_task = new Task(read_batch);
                 next_task.schedule(20);
             } else {
-                send_response({"track": track_idx, "device": device_idx, "params": params});
+                send_response({"track": track_idx, "device": device_idx, "params": params}, captured_request_id);
             }
         } catch (e) {
             send_response({
@@ -254,7 +270,7 @@ function cmd_get_params(args) {
                 "track": track_idx,
                 "device": device_idx,
                 "partial_params": params
-            });
+            }, captured_request_id);
         }
     }
 
@@ -275,6 +291,9 @@ function cmd_get_hidden_params(args) {
     var params = [];
     var current = 0;
     var batch_size = 8;
+    // See cmd_get_params: capture the request id so the closure survives the
+    // Task.schedule(20) gaps without being clobbered by an interleaved command.
+    var captured_request_id = current_response_request_id;
 
     function read_batch() {
         try {
@@ -307,7 +326,7 @@ function cmd_get_hidden_params(args) {
                     "device_name": device_name,
                     "total_params": param_count,
                     "params": params
-                });
+                }, captured_request_id);
             }
         } catch (e) {
             send_response({
@@ -316,7 +335,7 @@ function cmd_get_hidden_params(args) {
                 "device": device_idx,
                 "device_name": device_name,
                 "partial_params": params
-            });
+            }, captured_request_id);
         }
     }
 
@@ -334,6 +353,9 @@ function cmd_get_auto_state(args) {
     var results = [];
     var current = 0;
     var batch_size = 8;
+    // See cmd_get_params: capture the request id so the closure survives the
+    // Task.schedule(20) gaps without being clobbered by an interleaved command.
+    var captured_request_id = current_response_request_id;
 
     function read_batch() {
         try {
@@ -362,7 +384,7 @@ function cmd_get_auto_state(args) {
                     "total_params": param_count,
                     "automated_params": results,
                     "automated_count": results.length
-                });
+                }, captured_request_id);
             }
         } catch (e) {
             send_response({
@@ -372,7 +394,7 @@ function cmd_get_auto_state(args) {
                 "total_params": param_count,
                 "automated_params": results,
                 "automated_count": results.length
-            });
+            }, captured_request_id);
         }
     }
 
@@ -689,22 +711,37 @@ function correlate(a, b) {
 
 // ── Response Encoding ──────────────────────────────────────────────────────
 
-function send_response(obj) {
-    var json = JSON.stringify(obj);
+function send_response(obj, explicit_id) {
+    var response = obj || {};
+    // Async/batched handlers (cmd_get_params et al.) capture the request id in
+    // a closure and pass it explicitly here, because the module-level
+    // current_response_request_id can be clobbered by an interleaved command
+    // that arrives during a Task.schedule() gap between batches.
+    var rid = (typeof explicit_id === "string" && explicit_id !== "")
+        ? explicit_id
+        : current_response_request_id;
+    if (rid) {
+        response._livepilot_request_id = rid;
+    }
+    var json = JSON.stringify(response);
     var encoded = base64_encode(json);
 
     // Check if chunking needed (Max OSC packet limit ~8KB)
     if (encoded.length < 1400) {
         outlet(0, "/response", encoded);
     } else {
-        // Split into chunks
+        // Split into chunks. The request id rides the chunk header (first arg)
+        // so the Python side buckets chunks per-response and never mixes two
+        // commands' chunks — the id inside the JSON can't be read until the
+        // chunks are reassembled.
         var chunk_size = 1400;
         var total = Math.ceil(encoded.length / chunk_size);
         for (var i = 0; i < total; i++) {
             var piece = encoded.substring(i * chunk_size, (i + 1) * chunk_size);
-            outlet(0, "/response_chunk", i, total, piece);
+            outlet(0, "/response_chunk", (rid || ""), i, total, piece);
         }
     }
+    current_response_request_id = "";
 }
 
 function base64_encode(str) {

package/mcp_server/__init__.py

@@ -1,2 +1,2 @@
 """LivePilot MCP Server — bridges MCP protocol to Ableton Live."""
-__version__ = "1.27.1"
+__version__ = "1.27.3"