Release AKOÚŌ v0.6 — Instrumented Listening · sonicfieldlabs/akouo

AKOÚŌ becomes consumable as data, not just prose, and connects to sound-memory stores.

New

akouo.manifest.json — machine-readable system contract: skills with structured metadata (facets, cost tier, memory policy, corrective eligibility), command chains as data, the Evidence Ladder as data, and command permission overrides. Host apps load this instead of hand-copying tables that drift. Validated by schemas/manifest.schema.json.
presets/presets.json — thirteen portable listening presets for recurring use-cases (basic, signal, field, music, voice, recall, remember, deep, forensic, access, fiction, generative, extended-spectrum), validated by schemas/preset.schema.json.
memory-lineage-listening — the fourteenth mode: listening WITH stored sound-memories (earworm-style akousma records) — recurrence, kinship, lineage, change over time — while keeping memory a distinct evidence stream, never proof about the present sound.
/remember — the memory command: situate a sound in its lineage and register the listening into a store.

Listening outputs gain optional akouo_version, apparatus (substrate, perception sources, known blind spots), listener (human/agent/hybrid), and memory (akousma links) blocks.
Claims gain optional source (audio, dsp, metadata, model, transcript, context, memory, human, other) and time_range anchors — evidence streams never blur, temporal claims stay anchored.
Routing plans gain optional budget (light/standard/deep) and preset_id; risk always overrides budget.
Router: substrate awareness with derived claim limits, causal-confidence guidance by listening situation, vococentrism correction, memory-route scoring, preset/budget honoring.
/forensic suppresses interpreted/speculative claims and /fiction grants declared speculation — now data in the manifest, not just prose.

/one-sound-many-ears comparative outputs: mode_comparison now requires the memory_lineage key.