Move sections to where they read better:
- Phase 1 (Team registration): drop the "Your Agent" block.
- Phase 2 (Meet your agent): host the "Your Agent" section (say-hi / Telegram /
voice) AND the agent chat under it; remove "Pick your domain".
- Module 1 (Domain & events): "Pick your domain" moves here (no more read-only
carry) alongside the ADD Layer 1 card.
- Module 2 (Skills & policies): the chat is gone; the L2/L3 ADD cards show
directly (still auto-prefilled if the three prompts ran in Meet your agent).
Also: OpenYourNode opens the browser-reachable board URL. In self-host/USB mode
the stored url is container-facing (host.docker.internal) which the browser
can't resolve — derive the current host on :8080 instead. Tests updated.
Co-Authored-By: Claude Opus 4.8 <[email protected]>
Restructure the workshop flow into the designer's cockpit: a persistent shell
(header + 5-step stepper + sticky instrument rail) wrapping the phase routes via
a React-Router layout route, so the rail stays mounted across navigation.
- Design system: IBM Plex Mono + Newsreader; the full cockpit token set (light
+ dark) in index.css; a working light/dark theme toggle (store `theme` +
useApplyTheme); a `switch` ui primitive.
- Shell: CockpitLayout, Stepper (forward-gated), PanelChrome helpers. Every
phase page restyled to the editorial panels + the WORKSHOP-FLOW fixes
(channels-after-bind, domain framing + L1 prefill, L2/L3 prefill at 3/3,
in-place submission finale). Store gains `tried` + `channels.saidHi` (v4).
- Live rail (CockpitRail): real node heartbeat + agent activity log + ADD
progress; sim telemetry (useTelemetry) for the waveform/accel/I2C behind a
seam, marked SIM.
- LED-matrix PIXEL MIRROR (real): the rail shows exactly what the physical
matrix displays — API GET /nodes/:team/matrix reads the board's framebuffer
off the :9999 relay (readMatrixFrame + the `matrixget` relay command);
useMatrixMirror polls it and unpacks the 104 bits.
Co-Authored-By: Claude Opus 4.8 <[email protected]>
Module 2 is now a chat straight to the agent instead of Build & flash.
Removed the "Open your node" links and the Live board feed card.
New AgentChat component: three imperative canned prompts —
- List the I2C devices on the bus
- Count to 100 and print the value once a second in the LED matrix
- Scroll GO CLAWS on the LED matrix
Each sends to the agent (fire-and-forget, cloud) and streams its
activity (tools/flash/reply) back into the transcript. A prompt is marked
done on its first terminal step (flash/response); an error resets it to
retry. Prompts run one at a time.
Once all three have run successfully, Module 2 reveals "What's next" —
the ADD Layer 2 (Skills) + Layer 3 (Policies & failure) capture — and
Proceed gates on all-three-tried AND L2 + L3 filled.
Note: BuildFlash / LiveBoardFeed / ActorMap are now orphaned (kept for
possible reuse).
Co-Authored-By: Claude Opus 4.8 <[email protected]>
Reviewed the official APESS 2026 programme against the app as shipped.
The structure held up; several published facts and one scoring bug did not.
Fixes a real scoring defect: AddReview (what judges read) still carried
pre-pivot layer titles - "Reasoning policy", "Action contract", "Failure
modes", "AI-native redesign" - so judges scored "Skills" under the heading
"Reasoning policy". Root cause was two duplicated title lists that drifted
after the domain-node reshape, so both surfaces now render from a single
ADD_LAYERS constant and cannot diverge again.
Also removes dead classifier telemetry from the graded artifact: the ADD
printed "N frames - N nominal - N anomalous - N critical", but nothing has
called recordEvent since the simulator was deleted, so those counters were
permanently zero - and the vocabulary predates the pivot.
Corrects the schedule. The app advertised the lecture at 14:00, inside the
hackathon block; the programme puts it at 10:45-12:15 as a separate morning
session, with the hackathon 14:00-19:00. Moving it out recovers an hour,
which the new timings spend on the sensor work rather than setup.
Reframes the session around designing for failure, per the workshop premise
and the school's "proactive resilient systems" theme:
L3 becomes Policies & failure - which way each failure fails, with the
governing rule that a fail-safe must never quietly report "nominal"
L4 becomes where each decision runs - the degradation path, cloud to
on-board to fully offline, not just the happy path
L5 gains what the loop does when a cycle fails - stale reads, missed
ticks, partial data
Students arrive having spent a week on their own sensor work with these
boards, so the hands-on now points the agent at hardware they already
wired (discover the bus, read it, act on a threshold) instead of only
scrolling text, and the framing invites the domain they are already
measuring. The domain stays free-text.
Adds backup-uno-q.sh: boards are reflashed on the day and a week of
student work is irreplaceable. Denylist rather than allowlist, because we
cannot know where a given team put their data; verifies the archive is
readable and non-trivial before reporting success. Deliberately keeps the
App Lab examples dir - stock, but exactly what someone would edit in place.
Verified end to end: byte-identical restore of a real sketch.
Co-Authored-By: Claude Opus 4.8 <[email protected]>
The board is now a Claude-powered ZeroClaw agent with expert skills that teams
talk to directly (its own dashboard / Telegram / voice). The frontend was built
on the older sensor+harness model; this repoints it.
- State/DTO: AddLayers remapped to the 5 design layers (Domain/Skills/Policies/
Harness/Loops); added session.domain (+ mirrored through TeamSnapshot, sync,
and the SQLite store with a guarded migration); dropped Harness/Provider/RunMode;
persist v2 migrate resets stale state.
- Removed the harness/sim/failover machinery (HarnessProviderSelect, HarnessTuner,
HarnessTomlPreview, ResiliencePanel, TriggerButtons, harness.ts, useSerial,
LiveFeed/serial classifier) and every sim-vs-live branch.
- Onboarding: EnvSetup rebuilt into 'Meet your node' — Open-your-node hero (new
reusable OpenYourNode CTA), say-hi-to-your-agent, a free-text DomainPicker
(domain drives L1-L5), Telegram/voice pointers, and the open->locked lockdown
policy step. Domain is required to proceed.
- Modules repointed: M1 Domain & events (L1), M2 Skills & Policies (L2/L3, skills
reference + actuation-gate framing), M3 Harness (reasoning+tiering) & Loops
(cadence) (L4/L5). BuildFlash reframed as a guided 'ask your node to build X'
that hands off to the node dashboard.
- Judge rubric -> Domain fit/Skills/Policies/Harness/Loops; Lecture + Landing
re-storied to the Claude-node + talk-to-your-node narrative.
Verified: web tsc + 181 tests, api tsc + 58 tests, dead-ref sweep clean.
Co-Authored-By: Claude Opus 4.8 <[email protected]>
Folds the last unmerged workshop work into main:
- ResiliencePanel — the failure-injection 'theater' UI (cloud outage → on-board
Qwen live demo) that visualizes the [agents.chaos] (custom.dead → llamacpp)
failover, plus Module2 integration + api/nodes support.
- build-deploy.sh — one-command aarch64-musl cross-build + adb deploy helper,
REFRESHED for 0.8.3: adds the web SPA prebuild step and the full feature set
(hardware, peripheral-rpi, embedded-web, gateway-voice-duplex) + the
embedded-web/web_dist_dir gotcha.
Config conflict resolved as a union: the branch's custom.dead + [agents.chaos]
demo blocks alongside this session's channels/voice/skills/risk-profile edits.
Verified: tsc clean, web 229 + api 58 tests green.
Co-Authored-By: Claude Opus 4.8 <[email protected]>
In live mode the sense loop runs on the board (ZeroClaw on the Uno Q),
so the browser observes it rather than reading frames over Web Serial.
- useNodeFeed(teamId, enabled): subscribes to the node's SSE activity
feed (openTeamActivity) and seeds liveness with a one-shot getNodeStatus
(the per-team stream only emits status on change). Inert in sim mode.
- LiveBoardFeed: shows the board's real perception->reason->act activity
+ a live tally (agent runs / flashes / errors) + online indicator.
- Module 1/2 are now mode-aware: sim keeps the synthetic IMU feed +
browser classification (the teaching sandbox); live shows LiveBoardFeed
from the actual board. Proceed gates on board online (M1) / real board
activity (M2) in live, unchanged in sim.
Note: this consumes the board's real activity stream (the signal the
Uno Q emits today). Streaming raw IMU frames for browser-side
classification in live mode would need a board-side sensor emitter
(ZeroClaw firmware) + an API frame relay — a separate piece.
Co-Authored-By: Claude Opus 4.8 <[email protected]>
Prototype #1 of the APESS innovation set: make the Uno Q's unique story —
a real LLM running on the board — visible and demonstrable. A team can
inject a cloud outage and watch their agent keep reasoning on the on-board
Qwen, which is exactly ADD Layer 4 (failure modes) / Layer 5 (edge vs cloud)
made concrete instead of merely documented.
- New `fallback` NodeActivityKind (api + client, kept in sync). `mapNodeEvent`
now recognizes ZeroClaw's failover log lines ("ModelProvider call failed",
"Exhausted retries, trying next model") and surfaces them as a first-class
resilience signal — NOT swallowed by the generic error branch. Rendered in
a distinct rose in the board-activity feeds.
- ResiliencePanel (Module 2): a "Simulate cloud outage" button that routes a
prompt through the board's new `chaos` agent; streams the live failover and
shows a "survived" banner when a fallback is followed by a response. Sim mode
plays a deterministic failover so it demos with zero hardware.
- Board config: a `chaos` agent backed by a deliberately-dead cloud endpoint
(:9099) with `fallback = ["llamacpp.local"]`, so the outage is deterministic
and workshop-safe (no tunnel-hacking, no real cloud to kill).
Tests: api 34, front-end 191 (+ResiliencePanel), typecheck clean, build passes.
Live-on-board validation pending (board USB link down at commit time).
Co-Authored-By: Claude Opus 4.8 (1M context) <[email protected]>
Turn the workshop shell into a real on-device agent platform: APESS now
proxies each team's Arduino Uno Q (running ZeroClaw) and drives
generate → compile → flash from the UI, with a simulation fallback.
api — node backbone
- nodes.ts: team→node registry, a pure ZeroClaw /api/events → WsEvent
mapper, per-node live SSE subscription fanned out to the collective hub
AND per-team participant listeners, and a prompt proxy. Bearer tokens
stay server-side; list()/broadcasts never expose them.
- routes: POST/GET/DELETE /nodes (register is admin-only), public
POST /nodes/:teamId/prompt, and a participant-scoped SSE
GET /nodes/:teamId/events.
- WsEvent gains node:status / node:activity.
front-end
- session store: mode 'live' | 'sim' (default sim); a 'local' provider
and a harness.fallbackLocal toggle ("cloud first, on-board Qwen if it
fails") reflected in the harness.toml preview.
- EnvSetup: Simulation / Live board toggle — sim runs a virtual board
(self-test + Proceed with no hardware), live requires a registered node.
- BuildFlash panel (in Module 2): prompt the board, watch activity stream
live (SSE) or a simulated generate→flash sequence.
- lib/api: sendPrompt + openTeamActivity (EventSource).
housekeeping
- better-sqlite3 → 12.11 (Node 26 support; the 11.x native build fails on
Node 26's V8).
- vitest excludes the vendored Uno-QClaw/ tree.
Tests: front-end 172, api 29, typecheck clean, prod build passes.
Co-Authored-By: Claude Opus 4.8 (1M context) <[email protected]>
All four workshop phases are now real screens, replacing WorkshopStub:
- EnvSetup (/workshop/setup): device check + serial self-test (no stats
pollution) + provider/model selection; gated Proceed
- Module1 (/workshop/module1): live IMU feed via useSerial, actor map,
ADD Layer 1 capture; gated on observed frames + L1 goal
- Module2 (/workshop/module2): harness tuner + live TOML preview, test
triggers that classify against the tuned threshold, ADD L2/L3
- AddBuilder (/workshop/add): ADD L4/L5, assembled AddDocument, print-to-PDF
export, deterministic submission code; completes the run
- New components: ActorMap, HarnessTuner, TriggerButtons, AddDocument
23 new tests; suite 86/86 green, typecheck + lint clean, build OK.
Only /admin and /judge remain stubbed (need the backend).
Co-Authored-By: Claude Opus 4.8 (1M context) <[email protected]>
