feat(skills): somatic music doctrine — controller lens Layer 1 - #170
Conversation
Three skills: constitution, EMD reflex, parametric engine catalog. Widens acoustic_intent without words. Composer lens untouched. i-ARIF vocal melodic DENY at doctrine, pipeline, and catalog. F2: YAML valid, DAG acyclic after companion restructure. Layer 2 WELL and Layer 3 singing remain HOLD.
|
You have reached your Codex usage limits for code reviews. You can see your limits in the Codex usage dashboard. |
|
Important Review available on request
Reviews should be triggered manually for repositories with fewer than 10 stars. Select Trigger review above or comment ⚙️ Run configurationConfiguration used: defaults Review profile: CHILL Plan: Pro Plus Run ID: Thanks for using CodeRabbit! It's free for OSS, and your support helps us grow. If you like it, consider giving us a shout-out. Comment |
|
F13 GO (2026-08-18). T2 10s veto released by Arif. Somatic controller-lens trio. Layer 0 composer untouched. Layer 2 WELL + Layer 3 i-ARIF singing remain HOLD. Companion: #169 (voice doctrine), ariffazil/HERMES#8. No main merge from this comment. |
|
One or more custom setup steps configured for this repository failed during this Copilot code review run: Setup steps run before each review. If the review above is missing context, or no review was posted at all, the failing step above may be the cause. See the workflow run for failure details, fix your setup steps configuration, and re-request a review. Note You can configure setup steps for Copilot code review separately from Copilot cloud agent with a |
There was a problem hiding this comment.
Pull request overview
This PR introduces a new Somatic Music (controller-lens) Layer 1 skill family to document governance/doctrine, an engine registry (Lane 6), and an EMD-style pipeline that maps voice-cadence → somatic_proxy → music_intent → parametric music engines, explicitly gated by F1/F9/F10/F11/F13 constraints.
Changes:
- Adds
AAA-somatic-music-doctrinedescribing controller-vs-composer separation and the 3-layer maturity model. - Adds
AAA-somatic-engine-catalogdocumenting allowed/denied engines and Lane 6 routing policy. - Adds
AAA-somatic-emd-pipelinespecifying the decode/metabolize/encode reflex arc and the unified packet shape (music_intent).
Reviewed changes
Copilot reviewed 3 out of 3 changed files in this pull request and generated 7 comments.
| File | Description |
|---|---|
| skills/AAA-somatic-music-doctrine/SKILL.md | Layer 1 somatic music doctrine + maturity model + constitutional gates |
| skills/AAA-somatic-engine-catalog/SKILL.md | Engine registry + routing decision tree + i-ARIF vocal-melodic DENY policy |
| skills/AAA-somatic-emd-pipeline/SKILL.md | EMD pipeline spec + unified packet + MiniMax T2A encoding example |
Suppressed comments (1)
skills/AAA-somatic-engine-catalog/SKILL.md:298
AGI-audio-quantum-cognitionis listed twice in Related Skills with different descriptions. This looks like an accidental duplicate; consider keeping a single entry (or differentiating the second item if it was meant to reference a different skill).
- `music-intelligence` — Composer lens (Layer 0, untouched)
- `AGI-audio-quantum-cognition` — Audio physics + floors (parent)
- `AGI-audio-quantum-cognition` — F1 + F9 floors
💡 Add a code-review agent skill or configure MCP servers for context-aware, tailored reviews. Learn more in the docs.
| P(Truth) of "agent healed Arif via music" = 0.0. | ||
| P(Truth) of "agent emitted 60 BPM drone which statistically correlates | ||
| with reduced heart rate" ≤ 0.90 (F7 cap). | ||
| P(Truth) of "music is mathematics across time" = 1.0. |
| | F1 (safety) | `AAA-somatic-emd-pipeline` checks: freq in 60 Hz – 8 kHz, dB ≤ 70 continuous, duration ≤ 8 s default, fail-closed to silence. | | ||
| | F11 (audit) | Every emission returns receipt_id. Bundled into VAULT999 with `category=somatic-music` tier. | | ||
| | F13 (sovereign) | Sustained intervention / high dB / i-ARIF singing / state-change claims require `human_approval_token` (stg_*). | | ||
| | i-ARIF singing DENY | `AAA-voice-cloning-mimo-minimax/SKILL.md` engine constraint, double-checked in `voice_filters.check_voice_policy()`. | |
| "music_intent": { | ||
| "role": "bed", # silence | bed | warn | none | ||
| "bpm_target": 70, # derived from WPM / ~2.3 | ||
| "key": "auto", # engine chooses within musical bed | ||
| "density": "low", # very_low | low | medium | high | ||
| "max_seconds": 8, # hard cap (F1) | ||
| "kill_on_barge_in": true, # mandatory on voice-mode path | ||
| "no_vocal": true, # no lyric, no vocal melodic | ||
| "no_i_arif": true, # hard DENY for i-ARIF voice_id | ||
| }, | ||
|
|
||
| # Falsification gate (Layer 2 — placeholder for now) | ||
| "falsification": { | ||
| "voice_round_trip": null, # STT round-trip on TTS (existing) | ||
| "biometric_round_trip": null, # WELL feedback (Layer 2 only) | ||
| "rejected": False, | ||
| }, | ||
|
|
||
| "policy": { | ||
| "verdict": "ALLOW", # ALLOW | HOLD | DENY | ||
| "f13_token": null, # required for Layer 3 / sustained | ||
| "reason": "voice-cadence elevated → bed 70 BPM low density", | ||
| }, |
| extends: | ||
| - AGI-audio-quantum-cognition | ||
| - AAA-audio-qualia-doctrine | ||
| companion: | ||
| - music-intelligence |
| extends: | ||
| - AGI-audio-quantum-cognition | ||
| - AAA-audio-qualia-doctrine | ||
| - AAA-somatic-music-doctrine | ||
| companion: |
| extends: | ||
| - AGI-audio-quantum-cognition | ||
| - AAA-audio-qualia-doctrine | ||
| - AAA-somatic-music-doctrine | ||
| companion: |
| payload = { | ||
| "model": "music-2.6", # or music-3.0 | ||
| "prompt": _build_prompt(intent), # see below | ||
| "bpm": intent["bpm_target"], | ||
| "duration": intent["max_seconds"], | ||
| "format": "mp3", | ||
| "sample_rate": 24000, | ||
| } |
Summary
Controller-lens sibling to the voice stack. Music as
acoustic_intentwithout words. Not a new organ. Not a DJ. Not a healer.AAA-somatic-music-doctrine— F10 / F9 / F1 constitution, 3-layer maturity, thesis A/B/C with OBS/INT/SPEC labelsAAA-somatic-emd-pipeline— voice-cadencesomatic_proxy+music_intent+ kill-on-barge-inAAA-somatic-engine-catalog— Lane 6: MiniMaxmusic-2.6/music-3.0primary; AudioCraft/Stable Audio sovereign; Suno/Udio DENYCompanion to AAA#169 (voice doctrine). Does not touch Layer 0
music-intelligence. Does not extendvoice_filters.pyyet (gates documented, not wired). Does not merge itself.F2 evidence (OBS)
Audit 2026-08-18 post-cycle-fix. YAML valid. DAG:
Corrections baked in:
no_i_arif) + catalog (all engines)somatic_proxy.source = voice-cadenceonly; WELL field exists unusedF1 encoder bounds documented: 60 Hz–8 kHz, <70 dB continuous, ≤8 s default, ≤30 s without F13, fail-closed to silence.
Explicitly not in this PR
voice_filters.py(already HERMES#8; somatic gates not implemented yet)voice_filters.log(smoke log, never commit)Test plan
music-intelligence) left read-onlyAutonomy
T2 feature PR. No main merge. Layer 1 ignite is F11; Layer 2/3 stay HOLD.