compose
compose
¶
Compose command — mzt compose.
Compiles semantic agent definitions into Mozart scores. Takes a YAML config describing agents as people (voice, focus, meditation, techniques) and produces complete self-chaining scores with identity seeding, technique wiring, instrument resolution, and validation generation.
Usage::
mzt compose config.yaml --output scores/my-project/
mzt compose config.yaml --output scores/ --fleet
mzt compose config.yaml --dry-run
mzt compose config.yaml --seed-only
Classes¶
Functions¶
compose
¶
compose(config=Argument(..., help='Path to the semantic agent config YAML'), output=Option(None, '--output', '-o', help='Output directory for generated scores'), fleet=Option(False, '--fleet', help='Force generation of a fleet config (auto-generated for multi-agent configs)'), dry_run=Option(False, '--dry-run', help='Show what would be generated without writing files'), seed_only=Option(False, '--seed-only', help="Only seed agent identities, don't generate scores"), agents_dir=Option(None, '--agents-dir', help='Override agents identity directory (default: ~/.mzt/agents)'), techniques_dir=Option(None, '--techniques-dir', help='Path to technique module documents'))
Compile semantic agent definitions into Mozart scores.
Takes a YAML config describing agents and produces complete self-chaining scores with identity, techniques, instruments, and validations.
Source code in src/marianne/cli/commands/compose.py
34 35 36 37 38 39 40 41 42 43 44 45 46 47 48 49 50 51 52 53 54 55 56 57 58 59 60 61 62 63 64 65 66 67 68 69 70 71 72 73 74 75 76 77 78 79 80 81 82 83 84 85 86 87 88 89 90 91 92 93 94 95 96 97 98 99 100 101 102 103 104 105 106 107 108 109 110 111 112 113 114 115 116 117 118 119 120 121 122 123 124 125 126 127 128 129 130 131 132 133 134 135 136 137 138 139 140 141 142 143 144 145 | |