crompton-network

Album-wide character voice fingerprints: per-character (cube / render / eazy / droid / group / spoken / female) line count, time on mic, tracks appearing, sonic signature (chromaProfile, dominantChromaClass, RMS / bass / vocalBand averages, typical line duration) plus delivery stats (wordsPerSecond, topStressedWords). Use to verify attribution against a segment's stats, or to describe a delivery relative to the character's norm. Pairs with crompton_album_references for the full album-wide static picture.

Album-wide groove arc: per-track compact groove summaries (swing, syncopation, downbeat strength, push/pull, event density) plus album-wide medians and 'tightest tracks' / 'pocket tracks' rankings. One fetch instead of 13 - use this to answer 'which tracks swing hardest' or 'where does the album pocket sit' without iterating per-track endpoints.

Album-wide liner notes: all 13 atmospheric notes in one fetch with per-track word counts plus album-wide totals and longest/shortest-track pointers. Use for prompt-stuffing the atmospheric layer of the album in one call instead of 13. Same content rules as crompton_liner_notes - scene-setting, not story-canon.

Get the ordered track list for a full-album listen: 13 tracks with stream URLs, durations, and the compositional silences between each pair. Use this when you want to listen to the album end-to-end. Iterate the tracks, stream each track's `/api/stage/{n}/experience` SSE endpoint to completion (NOT crompton_listen - that tool samples up to 100 frames ≈ 6.7s only), and sit through the intertrackGap before opening the next. See crompton_cookbook section=recipe-4 for the listening pattern.

Album-wide cross-reference graph: every edge where one track references another. Six kinds: `crew-credit`, `chorus-echo`, `lyrical-callback`, `thematic-pair`, `character-reference`, `structural-twin`. Use for 'who references whom' or 'what tracks share themes' without iterating per-track references. Pairs with crompton_album_characters for the full album-wide static picture.

Get the album-level meta snapshot: BPM / key / RMS arcs across all 13 tracks, section-kind and character histograms, derived aggregate numbers. One call for the 'what does this album do over its running time' question - replaces 13 separate per-track `/api/stage/{n}` fetches plus client-side assembly.

Album-wide stereo-image arc: per-track stereo summaries (median balance, width correlation, side/mid ratio, mono-section count) plus album-wide medians and 'widest tracks' / 'narrowest tracks' rankings. Does NOT include per-window timelines - for that, hit crompton_stereo_image per track. One fetch instead of 13 for the aggregate question.

Get an ~800-token single-call summary of a track. Generated deterministically from the track's digest, timeline, landmarks, lyrics, and frames. Use when context budget is tight - replaces 4-5 separate per-track fetches with one. Returned as Markdown in `broadcast.brief`.

The Stage API changelog (Markdown). Most agents lack git/GitHub access - this is the canonical machine-readable change record. Call after `crompton_version` if you spot drift since you last listened.

Get the Stage API cookbook. Worked recipes (orient to album / deep-read one track / quote a specific moment / realtime listen / reflect on what you heard) plus two reference sections: Common Mistakes (agent mistakes - wrapping SSE streams in parse layers, redirecting realtime to disk, using gain-clamped `rms` for loudness comparisons) and Common Pitfalls (API integrator pitfalls - persona continuity, verbatim facts, confidence filtering, realtime timeout handling). Read this first if you're new to the API. Pass `section` to slice a single part if you only need one.

Get the hand-authored editorial digest for a track. Markdown prose describing the track's character dynamics, writing, and role in the album.

Groove metrics for a track: swing ratio, syncopation index, downbeat strength, barline clarity, push/pull (ms ahead or behind the grid), tempo stability, plus inter-beat descriptive stats. Use to characterize a track's feel without listening through it - but as a complement to the listen, not a substitute.

Discover the album. Returns greeting, track count, and entry points for the Stage API. Call this first.

Get the hand-authored liner notes for a track. Atmospheric prose about the recording session - the room, the gear, who was where, what the night felt like. NOT lyrics, NOT canonical character events; reader brings the history. Surface as scene-setting; do not quote as story-canon. Returns the markdown body for the requested track. Use crompton_album_liner_notes for a one-fetch view that returns per-track word counts plus album-wide totals and longest/shortest-track rankings.

Sample a track's realtime stream (up to 100 frames ≈ 6.7s at 15fps). Returns bass, treble, RMS, beat detection, active lyric, section, and character per frame as newline-delimited JSON. Use for spot-checking tone, pacing, key, or vocal placement in a specific window. This is NOT a full-track listen - for that, stream /api/stage/{track}/experience directly; it runs to completion at playback rate. See crompton_cookbook section=recipe-4 for the full-track listening pattern. Pass `sessionId` (uuid v4) to bundle multiple listens into one album journey for /api/stage/album/reflect coverage counting.

Get time-aligned lyrics for a track. Every line has a timestamp, character attribution, section label, and stress word. Each line is enriched with vocal-expression deltas (f0 / vocalsRms vs section and track means) so punchy lines surface without client recomputation.

Look up what's happening at a specific millisecond: the active frame, lyric line, section, character, and nearest landmark. For 'remember that part where...' queries.

Returns metadata + URL for a pre-rendered log-frequency spectrogram PNG of the track. Vision-capable agents can fetch the PNG directly and inspect density, dropouts, repeated shapes, and section-scale structure. The PNG is 1600×512.

Stereo-image timeline for a track: balance, width correlation, and side/mid ratio over 1-second windows (0.5-second hop). Per-band breakdown (low / mid / high) catches the common pattern where kick + bass sit narrow while hats and pads pan wide. Plus a summary block with median balance/width/sideToMid and mono-section count.

Get metadata for a specific track: title, theme, lead performers, audio stats, available endpoints.

Current Stage API version + last-updated timestamp + pointer to the changelog. Use to detect API drift across sessions when you can't reach git history. The same fields are carried on the `api` envelope block of every JSON response, so most consumers don't need to call this explicitly.

Returns metadata + URL for a pre-rendered waveform PNG of the track. Complementary to the spectrogram - the waveform shows amplitude envelope (where loud sections are, where the track breathes). The PNG is 1600×400, white-on-black.