renato97/ableton-mcp-ai
1
0
Fork 0
Code Issues Pull Requests Actions Packages Projects Releases 1 Wiki Activity
9 Commits 2 Branches 1 Tag
c8f03dc47a1893bb28e6be68dfc99bfdf3197d61
Commit Graph

5 Commits

Author SHA1 Message Date
renato97
f5be1309d2 Migración completa a librería Reggaeton 
Cambios realizados:
- server.py: actualiza PROJECT_SAMPLES_DIR a reggaeton
- sample_manager.py: cambia base_dir a reggaeton + agrega género reggaeton
- health_check.py: actualiza paths a reggaeton
- scan_audio.py: actualiza path a reggaeton
- segment_rag_builder.py: actualiza default library a reggaeton
- reference_stem_builder.py: actualiza PROJECT_SAMPLES_DIR a reggaeton
- song_generator.py: agrega GENRE_CONFIG y SECTION_BLUEPRINT para reggaeton
- rebuild_index.py: actualiza para apuntar a reggaeton

Nueva estructura soportada:
- 1. MIDI CHORDS / 2. MIDI ARP (MIDI files)
- 3. ONE SHOTS / 4. DRUM LOOPS
- 5. FX / 6. IMPACT INTRO / 7. FILL
- 8. KICKS / 9. SNARE / 10. PERCS
- 11. VOCALS
- reggaeton 2/ (bass, drumloops, fx, kick, oneshots, perc, snare)
- SentimientoLatino2025/ (drums, vocals, loops, one shots)

Index rebuilt: 508 samples
 2026-03-29 16:41:20 -03:00
renato97
5b63d38945 Fix library diversity and auto-automation issues 
Problem: System was stuck using single all_tracks folder, causing:
- No bucket sampling diversity (all files in 1 folder)
- Repetitive sample selection
- No coherence between sections
- Fades/volumes not auto-applied

Fixes:
1. Changed DEFAULT_LIBRARY from all_tracks to organized_samples
   - server.py: Updated SAMPLES_DIR
   - sample_manager.py: Updated base_dir
   - health_check.py: Added organized_samples as primary paths

2. organized_samples structure enables T013 bucket sampling:
   - loops/bass: 34 samples
   - loops/synth: 43 samples
   - loops/vocal: 24 samples
   - oneshots/kick: 20 samples
   - oneshots/perc: 35 samples
   - Each subfolder < 15 files = perfect for bucket sampling

3. Added auto-automation to generate_song():
   - Fade-in 4 bars for kick/bass/hat (intro)
   - Build curve: music tracks 0.5 -> 0.9 (32-40 bars)
   - Reverb automation: 0% -> 40% -> 0% on atmos/pad/vocal
   - apply_automation parameter (default True)

4. Each track now gets diverse samples from different subfolders:
   - Bass from loops/bass (34 options)
   - Synth from loops/synth (43 options)
   - Drums from oneshots/ (kick, perc, snare)

Coverage wheel will now track usage across 20+ subfolders instead of 1.
Diversity memory will work correctly with proper family tracking per folder.

Co-Authored-By: Claude Opus 4.6 <noreply@anthropic.com>
 2026-03-29 01:22:23 -03:00
renato97
b2924b9c88 Complete FASE 5, 7, Infra - Final sprint 90/110 tasks (82%) 
FASE 5 - DJ Arrangement Advanced (13/15 tasks):
- set_loop_markers() - T067: DJ navigation loop markers
- apply_filter_sweep() - T072: High-pass/low-pass transition sweeps
- apply_reverb_tail_automation() - T073: Break reverb curves (0%→40%→0%)
- apply_pitch_riser() - T074: Pitch automation risers
- apply_micro_timing_push() - T075: Kick -5ms, Bass +8ms groove
- apply_groove_template() - T077: Genre-specific groove templates
- inject_transition_fx_detailed() - T071: Advanced FX (riser, crash, snare_roll)

FASE 7 - Self-AI & Learning (10/10 tasks - COMPLETE):
- rate_generation() - T091: User rating system with feedback loop
- get_generation_stats() - T093: Trend analysis and palette preferences
- generate_dj_set() - T096: Multi-track DJ set generation (up to 4 hours)
- analyze_trends_library() - T097-T099: Hot zone detection
- auto_improve_set() - T100: Auto-regeneration of low-score sections

Infrastructure (7/10 tasks):
- get_system_metrics() - T108: Complete dashboard with health score
- get_generation_history() - T108: Recent generation history
- export_system_report() - T108: JSON/Markdown export
- CHANGELOG.md - T106: Complete changelog with all versions

Total: 86 MCP tools, 90/110 tasks (82%), 2 phases complete (0, 7)

Co-Authored-By: Claude Opus 4.6 <noreply@anthropic.com>
 2026-03-29 01:04:39 -03:00
renato97
4332ff65da Implement FASE 3, 4, 6 - 15 new MCP tools, 76/110 tasks complete 
FASE 3 - Human Feel & Dynamics (10/11 tasks):
- apply_clip_fades() - T041: Fade automation per section
- write_volume_automation() - T042: Curves (linear, exp, s_curve, punch)
- apply_sidechain_pump() - T045: Sidechain by intensity/style
- inject_pattern_fills() - T048: Snare rolls, fills by density
- humanize_set() - T050: Timing + velocity + groove automation

FASE 4 - Key Compatibility & Tonal (9/12 tasks):
- audio_key_compatibility.py: Full KEY_COMPATIBILITY_MATRIX
- analyze_key_compatibility() - T053: Harmonic compatibility scoring
- suggest_key_change() - T054: Circle of fifths modulation
- validate_sample_key() - T055: Sample key validation
- analyze_spectral_fit() - T057/T062: Spectral role matching

FASE 6 - Mastering & QA (8/13 tasks):
- calibrate_gain_staging() - T079: Auto gain by bus targets
- run_mix_quality_check() - T085: LUFS, peaks, L/R balance
- export_stem_mixdown() - T087: 24-bit/44.1kHz stem export

New files:
- audio_key_compatibility.py (T052)
- bus_routing_fix.py (T101-T104)
- validation_system_fix.py (T105-T106)

Total: 76/110 tasks (69%), 71 MCP tools exposed

Co-Authored-By: Claude Opus 4.6 <noreply@anthropic.com>
 2026-03-29 00:59:24 -03:00
renato97
6ec8663954 Initial commit: AbletonMCP-AI complete system 
- MCP Server with audio fallback, sample management
- Song generator with bus routing
- Reference listener and audio resampler
- Vector-based sample search
- Master chain with limiter and calibration
- Fix: Audio fallback now works without M4L
- Fix: Full song detection in sample loader

Co-Authored-By: Claude Opus 4.6 <noreply@anthropic.com>
 2026-03-28 22:53:10 -03:00