Make the avatar control panel a hover-reveal overlay
Claude
Unverified signature
364bce5
The Play/Stop button and caption now sit inside the photo as a
gradient overlay, hidden until hover (or while loading/speaking, so
the Stop control isn't lost mid-line) — keeps the portrait clean
instead of stacking controls below it.
Mark which stages are actually responsible for perceived realism
Claude
Unverified signature
6b5c34f
Adds a realismCritical flag to PipelineNode, set on Avatar/TTS/Video
Quality (the stages whose own output quality directly drives how
human this looks/sounds) but not Vision/ASR/LLM/Orchestration (affect
correctness/latency, not realism itself). Shown as a fuchsia REALISM
badge in the full graph and a compact eye icon in the Test Bench grid.
Also added to the pipeline-generation schema so grounded/generated
pipelines can flag it too.
Give Jessica a Play button: real LLM line + real speech, audio-reactive puppet
Claude
Unverified signature
6553b8c
/api/avatar-speak asks the same NIM/Anthropic model already wired up
to generate one short first-person line as the avatar. The browser's
real speech synthesis speaks it, and its actual boundary/playback
events drive a mouth-open pulse and periodic blink overlaid on
Jessica's photo. This is real audio driving real motion — not neural
lip-sync, which would need a GPU-hosted video model instead.
Archive completed Test Bench runs to a paginated Gallery page
Claude
Unverified signature
4df7155
Every run that reaches a terminal state (done/blocked) is retained
with its checksum, byte size, LOC, node count, and full log — browser
localStorage, not a shared database. The Gallery page (grid, newest
first, IntersectionObserver pagination matching the Briefing page)
lets you browse and expand past runs. Gallery added to the top nav.
Add persistent top-center nav across Home/Pipeline/Briefing/Test Bench
Claude
Unverified signature
e79b700
A global nav bar in the root layout replaces the scattered one-off
links that existed only on some pages, so every page is reachable
from every other page. Pipeline and Test Bench's full-viewport layouts
now size against the new nav height instead of assuming 100dvh alone.
Add Test Bench: grid-inspect pipeline stages against real reference implementations
Claude
Unverified signature
e1e33d1
Grid layout of compact stage cards next to an Artifact panel with Project
(live-fetched HF Space + GitHub context), Console (scripted, honestly-labeled
simulated GPU test run under a 3-min budget), and Samantha tabs. DEEP DIVE
seeds Samantha with a compare-against-reference question. Extracted repo/space
fetch helpers into src/lib/repo-fetch.ts for reuse with generate-pipeline.
Add "Group by Layer" — cluster nodes by Senses/Brain/Face
Claude
Unverified signature
b4ad384
New biological-metaphor grouping mode (distinct from the existing
Circular/Rows layouts): Vision+ASR cluster under THE SENSES,
LLM+Orchestration under THE BRAIN, TTS+Avatar+Video+Keyframer under
THE FACE, matching a diagram from the user's own research. Toggling
it doesn't remount the graph like switching Circular/Rows does —
node positions update in place with a ~950ms CSS transform
transition, so nodes glide slowly into their cluster instead of
re-landing. Gold data-flow edges cross between the columns showing
the actual handoffs.
Fix pasted-source bug: actually generate a pipeline instead of relabeling the demo
Claude
Unverified signature
9dc9b9a
Previously, pasting a GitHub URL just slapped the URL on as a label
while showing the same static Beryl demo underneath. New
/api/generate-pipeline route fetches real repo metadata/README when
given a github.com URL and has Samantha synthesize a grounded
Pipeline via forced tool-use, marking every node confirmed/inferred
honestly. Falls back to the demo pipeline with a visible error if
generation fails (e.g. missing API key) instead of silently
mislabeling.
Also: node cards are larger with full (non-clamped) 200+ char
summaries covering who/what/when; data edges render in a vivid gold
with a glow; nodes animate in on a staggered mid-speed landing with
a brief gold sunburst flash; each node gets a gold DEEP DIVE button
that jumps to Samantha with a seeded question about that node.
Add LAYER Briefing dashboard and two research subagents
Claude
Unverified signature
f9a7ee2
CNN-style /briefing page (topic nav, key-finding hero, card grid with
verified/unverified/needs-code-check status badges) seeded with the
25-paper index and the uploaded 4D-avatars research doc's key claims.
Two new subagents:
- research-curator: keeps the briefing feed current, same
verify-before-trusting discipline as Samantha's audits.
- hopper-nvidia: NVIDIA-native pipeline architect — translates any
researched pipeline into NGC/NIM equivalents, knows the Developer
Program vs Enterprise boundary, only pitches his recommendation
when asked.
Add rows layout toggle and C Protocol candidate data model
Claude
Unverified signature
bc55b9c
Circular/Rows layout toggle in the pipeline workspace (layered
top-down DAG as an alternative to the radial view). Added the C
Protocol (Code, Claim, Consensus, Cost, Connectivity, each 0-1, Code
gates the tier below 0.3) as the candidate-repo scoring model,
seeded with real GitHub data for the Avatar node's six candidates.
First worked-example report (Avatar) written to docs/reports/.
Ground the expert panel as Samantha: 5-failure-mode audit + tiering
Claude
Unverified signature
11c5c3c
Every node now carries a tier (A/B/C) and per-failure-mode verdicts
(Uncanny Valley, End-of-Speech Pop, Cascaded Latency, VRAM Death,
VASA-1 Problem) instead of a blanket pass. Added a pipeline-level
audit banner for architecture-wide findings that don't belong to any
single node (the ASR->LLM->TTS->Avatar cascade is a literal Failure 3
regardless of per-stage latency, and several model names need
verification against real NVIDIA documentation). The chat panel is
now Samantha, whose system prompt carries the rubric verbatim and
defaults to skeptical verdicts over blind passes.
Next.js + React Flow app that turns a pasted pipeline into an
interactive circular node graph (deep sub-component expansion,
Local/NIM implementation toggles, live latency/VRAM metrics), plus
a Claude-powered side panel that explains model tradeoffs and
handoff contracts. Ships with the NVIDIA avatar pipeline as the
first working example.
