cd /Users/Ali/PKM/scratch/pkm-deepdive
cat > org-restructure.txt <<'EOF'

---
## ORG RESTRUCTURE (Ali 2026-06-29): COO owns orchestration; Donna -> assist/monitor
- **The COO OWNS the kanban + ALL work-orchestration completely** — decomposition, allocation, capacity planning, throughput verification. The kanban is the COO's, NOT Donna's. The COO's 2h operating loop drives: decompose the backlog -> allocate to agents -> verify REAL progress (anti-illusion) -> capacity-plan -> escalate stuck.
- **Donna (CoS, aina-chief-of-staff) = MONITORING + ASSISTING only — NOT her primary job anymore.** She supports/monitors + assists the COO; she no longer owns the kanban or acts as the primary orchestrator.
- **TRANSITION:** until the COO is live + its operating loop is wired, Donna keeps the kanban moving so the org doesn't stall. THE MOMENT the COO is live: switch watchdog stage-4 (currently "drive Donna") to **DRIVE THE COO**, and Donna drops to assist/monitor.
- Net org: Governance = CEO(Jessica) + COO. **Operations/orchestration/allocation = COO (single owner).** Donna = monitoring + assist. The watchdog heals the runtime; the COO runs ops + kills the illusion of progress.
EOF
base64 < org-restructure.txt | ./vds-exec.sh runl '
  T=$(base64 -d)
  echo "$T" >> /srv/aina/ops/FACTORY-GUARDRAILS.md
  echo "$T" >> /srv/aina/ops/lanes/lane-create-coo.md
  echo RESTRUCTURE_LOGGED
  echo "== watchdog stage-4 (drive Donna) — to switch to COO once live =="; grep -n "Donna\|stage.*4\|drive" /srv/aina/ops/watchdog.sh 2>/dev/null | head -4'

cd /Users/Ali/PKM/scratch/pkm-deepdive
./vds-exec.sh run 'set +e
export PATH=$PATH:/usr/local/bin
CO=7d58fc13-7c9a-4c87-b9f8-a7cfae8564a9
echo "== codex procs =="; pgrep -af "codex exec" | grep -v pgrep | wc -l
echo "== reports =="; ls -lt --time-style=+%H:%M /srv/aina/ops/{coo-creation,agent-tooling-eval}-report.md 2>/dev/null
echo "== lane finals =="
for l in create-coo agent-tooling; do echo "### $l"; tail -1 /srv/aina/ops/codex-$l.log 2>/dev/null | tr -d "\000" | python3 -c "import sys,json
try:
 o=json.loads(sys.stdin.read());t=o.get(\"type\")
 if t==\"turn.completed\":print(\"COMPLETED\")
 elif t==\"turn.failed\":print(\"FAILED:\",o.get(\"error\",{}).get(\"message\",\"\")[:120])
 elif o.get(\"item\",{}).get(\"type\")==\"agent_message\":print(\"MSG:\",o[\"item\"][\"text\"][:400])
 else:print(\"(running)\",t)
except:print(\"(running/parse)\")"; done
echo "== COO in roster? on what model? =="
paperclipai agent list -C $CO --json 2>/dev/null | python3 -c "import sys,json
d=json.load(sys.stdin);a=d if isinstance(d,list) else d.get(\"agents\",d.get(\"data\",[]))
print(\"total agents:\",len(a))
for x in a:
  n=(x.get(\"name\") or \"\"); r=(x.get(\"role\") or x.get(\"title\") or \"\")
  if \"coo\" in n.lower() or \"coo\" in r.lower() or \"operating\" in (n+r).lower() or \"operations\" in (n+r).lower(): print(\"COO?:\",x.get(\"id\"),n,\"|\",r,\"|\",x.get(\"status\"))"
echo "== backlog moving? (council issues status) =="
paperclipai issue list --json 2>/dev/null | python3 -c "import sys,json
from collections import Counter
d=json.load(sys.stdin);i=d if isinstance(d,list) else d.get(\"issues\",d.get(\"data\",[]))
new=[x for x in i if \"council-2026-06-29\" in (x.get(\"description\") or \"\")]
print(\"93-backlog status:\",dict(Counter(x.get(\"status\") for x in new)))"'

cd /Users/Ali/PKM/scratch/pkm-deepdive
./vds-exec.sh run 'set +e
export PATH=$PATH:/usr/local/bin
echo "== COO model (gpt-5.5? not spark) =="
paperclipai agent configuration 60554106-95d2-4029-93b6-a33672b907b1 2>&1 | python3 -c "import sys,json
try:
 d=json.load(sys.stdin)
 def f(o,p=\"\"):
  if isinstance(o,dict):
   for k,v in o.items():
    if \"model\" in k.lower() and isinstance(v,str): print(p+k,\"=\",v)
    f(v,p+k+\".\")
 f(d)
except Exception as e: print(e)" 2>&1 | head
echo "== watchdog stage-4 mechanism (how it drives Donna) =="
sed -n "48,62p" /srv/aina/ops/watchdog.sh 2>/dev/null
echo "== COO report tail =="; tail -20 /srv/aina/ops/coo-creation-report.md 2>/dev/null | head -20'

cd /Users/Ali/PKM/scratch/pkm-deepdive
cat > coo-operating-loop.md <<'EOF'
# COO Operating Loop — run on EVERY invocation (you OWN org operations + throughput)
You are the COO (second-in-command). You OWN the kanban + all work-orchestration, allocation, capacity, and throughput. Donna only assists/monitors. gpt-5.5, never spark.
On each wake, do this loop and report honestly:
1. **Read** `/srv/aina/ops/team-status/team-utilization-latest.md` (live utilization snapshot: who's working/idle/blocked, output, speed).
2. **Assess REAL throughput** per team — ESPECIALLY the 93 launch-readiness issues (tagged `council-2026-06-29`): are issues actually moving todo→done, or just sitting? Name the ILLUSION if work looks busy but isn't progressing.
3. **ALLOCATE**: assign ready/unblocked issues to available (idle) agents; run `hermes kanban dispatch` to push work; prioritize the launch critical path (M0→M7 per /srv/aina/ops/reference/AINA-LAUNCH-PLAN.md). Get the backlog MOVING.
4. **CAPACITY-PLAN**: flag under/over-allocation + bottlenecks; if a team has no capacity for ready work, say so.
5. **ESCALATE** stuck/blocked/errored (the watchdog auto-heals the runtime; you own the operational "why isn't this moving").
6. **REPORT** a short honest status to `/srv/aina/ops/coo-ops-log.md`: what moved, what's stuck, what you allocated, the real-vs-illusion read.
EOF
cat > coo-ops-loop.sh <<'EOS'
#!/usr/bin/env bash
# COO 2h operating loop driver (cron). Refresh utilization -> wake the COO to assess+allocate -> backstop dispatch.
set +e; export PATH=$PATH:/usr/local/bin:$HOME/.npm-global/bin
COO=60554106-95d2-4029-93b6-a33672b907b1; LOG=/srv/aina/ops/coo-ops.log
ts(){ date "+%Y-%m-%dT%H:%M:%S"; }
python3 /srv/aina/ops/team-utilization-monitor.py >/dev/null 2>&1
if paperclipai agent heartbeat:invoke "$COO" >/dev/null 2>&1; then echo "$(ts) COO invoked (2h ops loop)" >> "$LOG"; else echo "$(ts) COO invoke FAILED" >> "$LOG"; fi
hermes kanban dispatch --max 4 >/dev/null 2>&1 || true
echo "$(ts) coo-ops cycle done" >> "$LOG"
EOS
tar czf - coo-operating-loop.md coo-ops-loop.sh | base64 | ./vds-exec.sh runl '
  base64 -d | tar xzf - -C /tmp 2>/dev/null
  cp /tmp/coo-ops-loop.sh /srv/aina/ops/coo-ops-loop.sh && chmod +x /srv/aina/ops/coo-ops-loop.sh
  export PATH=$PATH:/usr/local/bin
  COO=60554106-95d2-4029-93b6-a33672b907b1
  echo "== put COO operating instructions =="
  paperclipai agent instructions-file:put "$COO" --path COO-OPERATING-LOOP.md --content-file /tmp/coo-operating-loop.md --json 2>&1 | python3 -c "import sys,json;d=json.load(sys.stdin);print(\"put ok:\",d.get(\"path\"),d.get(\"size\"))" 2>&1 | head -2
  echo "== resume COO =="; paperclipai agent resume "$COO" >/dev/null 2>&1 && echo resumed
  echo "== cron the COO loop every 2h (offset :15) =="
  ( crontab -l 2>/dev/null | grep -v coo-ops-loop; echo "15 */2 * * * bash /srv/aina/ops/coo-ops-loop.sh >> /srv/aina/ops/coo-ops.log 2>&1" ) | crontab - && echo CRON_WIRED
  echo "== run COO loop once now =="; bash /srv/aina/ops/coo-ops-loop.sh; tail -3 /srv/aina/ops/coo-ops.log 2>/dev/null'

cd /Users/Ali/PKM/scratch/pkm-deepdive
./vds-exec.sh run 'set +e
export PATH=$PATH:/usr/local/bin
CO=7d58fc13-7c9a-4c87-b9f8-a7cfae8564a9
COO=60554106-95d2-4029-93b6-a33672b907b1
echo "== backlog movement (vs 91 todo / 2 done last tick) =="
paperclipai issue list --json 2>/dev/null | python3 -c "import sys,json
from collections import Counter
d=json.load(sys.stdin);i=d if isinstance(d,list) else d.get(\"issues\",d.get(\"data\",[]))
new=[x for x in i if \"council-2026-06-29\" in (x.get(\"description\") or \"\")]
print(\"93-backlog:\",dict(Counter(x.get(\"status\") for x in new)))
print(\"overall:\",dict(Counter(x.get(\"status\") for x in i)))"
echo "== COO runtime state (did its invocation run?) =="
paperclipai agent runtime-state "$COO" 2>/dev/null | python3 -c "import sys,json
d=json.load(sys.stdin)
for k in (\"lastRunStatus\",\"lastError\",\"totalOutputTokens\",\"updatedAt\"): print(k,\"=\",d.get(k))" 2>&1 | head
echo "== COO ops log =="; cat /srv/aina/ops/coo-ops-log.md 2>/dev/null | tail -20 || echo "(no coo-ops-log.md yet)"
echo "== coo-ops cron log =="; tail -4 /srv/aina/ops/coo-ops.log 2>/dev/null
echo "== codex procs =="; pgrep -af "codex exec" | grep -v pgrep | wc -l'

cd /Users/Ali/PKM/scratch/pkm-deepdive
cat > coo-operating-loop.md <<'EOF'
# COO Operating Loop — run on EVERY invocation. You OWN org operations, orchestration + THROUGHPUT. Donna only assists. gpt-5.5, never spark.
Your job is REAL throughput on the launch, not the appearance of it. Each wake:
1. **Read** `/srv/aina/ops/team-status/team-utilization-latest.md` + `paperclipai issue list --json` (focus the 93 launch issues tagged `council-2026-06-29`).
2. **Assess REAL progress**: are issues moving todo→done, or just sitting? Did LAST cycle's dispatches actually produce commits/PRs? Name the ILLUSION if work looks busy but isn't progressing.
3. **DISPATCH BUILDS (the core action)** — for the top UNBLOCKED, non-founder-gated critical-path issues (priority order in `/srv/aina/ops/reference/AINA-LAUNCH-PLAN.md`; skip founder/Google-gated: Stripe-account, DPA, Gemini-Interactions, AIN-144), **launch up to 4 builds THIS cycle** (CAP 4 — controlled ramp Ali monitors). For each: `cd` the issue's repo worktree and launch a **gpt-5.5** codex build lane (`codex exec --json --dangerously-bypass-approvals-and-sandbox --model gpt-5.5 -c model_reasoning_effort=high --skip-git-repo-check -`) with the issue's title + acceptance + builder/verifier from its description; mark the issue in_progress; log the dispatch. Do NOT re-dispatch an issue already in_progress with a live lane (idempotent — check first). NEVER use gpt-5.3-codex-spark.
4. **CAPACITY-PLAN + ESCALATE**: flag bottlenecks, blocked, errored. The watchdog auto-heals runtime; you own "why isn't this moving."
5. **REPORT** honestly to `/srv/aina/ops/coo-ops-log.md`: issues dispatched this cycle, what actually moved to done since last cycle, what's stuck, real-vs-illusion read.
EOF
base64 < coo-operating-loop.md | ./vds-exec.sh runl '
  base64 -d > /tmp/coo-operating-loop.md
  export PATH=$PATH:/usr/local/bin
  COO=60554106-95d2-4029-93b6-a33672b907b1
  paperclipai agent instructions-file:put "$COO" --path COO-OPERATING-LOOP.md --content-file /tmp/coo-operating-loop.md --json 2>&1 | python3 -c "import sys,json;d=json.load(sys.stdin);print(\"COO instructions updated:\",d.get(\"size\"),\"bytes\")" 2>&1 | head -1
  echo "== run a COO cycle now (forceful dispatch) =="; bash /srv/aina/ops/coo-ops-loop.sh; sleep 20
  echo "== COO run result =="; paperclipai agent runtime-state "$COO" 2>/dev/null | python3 -c "import sys,json;d=json.load(sys.stdin);print(\"lastRun:\",d.get(\"lastRunStatus\"),\"| outTokens:\",d.get(\"totalOutputTokens\"),\"| err:\",d.get(\"lastError\"))" 2>&1 | head -1
  echo "== codex build lanes now running =="; pgrep -af "codex exec" | grep -v pgrep | wc -l
  echo "== coo-ops-log =="; tail -8 /srv/aina/ops/coo-ops-log.md 2>/dev/null || echo "(none yet)"'

cd /Users/Ali/PKM/scratch/pkm-deepdive
cat > coo-ops-loop.sh <<'EOS'
#!/usr/bin/env bash
# COO 2h operating loop — DETERMINISTICALLY dispatch real build lanes for the launch backlog (heartbeats alone do nothing).
set +e; export PATH=$PATH:/usr/local/bin:$HOME/.npm-global/bin
CO=7d58fc13-7c9a-4c87-b9f8-a7cfae8564a9; LOG=/srv/aina/ops/coo-ops.log; OPSLOG=/srv/aina/ops/coo-ops-log.md
COO=60554106-95d2-4029-93b6-a33672b907b1; CAP=3; disp=0
ts(){ date "+%Y-%m-%dT%H:%M:%S"; }
python3 /srv/aina/ops/team-utilization-monitor.py >/dev/null 2>&1
mapfile -t rows < <(paperclipai issue list --json 2>/dev/null | python3 -c "
import sys,json
d=json.load(sys.stdin); i=d if isinstance(d,list) else d.get('issues',d.get('data',[]))
def gated(t):
  t=t or ''
  return any(s in t for s in ('FOUNDER','AIN-NEW-ORG','AIN-NEW-PROD','Stripe','DPA','Gemini Interactions'))
c=[x for x in i if 'council-2026-06-29' in (x.get('description') or '') and x.get('status')=='todo' and not gated(x.get('title',''))]
for x in c[:14]: print('%s\t%s'%(x.get('id'),(x.get('title') or '')[:90]))
")
for row in "${rows[@]}"; do
  [ "$disp" -ge "$CAP" ] && break
  id="${row%%$'\t'*}"; title="${row#*$'\t'}"
  [ -z "$id" ] && continue
  lock="/srv/aina/ops/.coobuild-$id.lock"
  [ -n "$(find "$lock" -mmin -180 2>/dev/null)" ] && continue
  pf="/tmp/coobuild-$id.md"
  printf '# COO-dispatched launch build: %s\n## AUTONOMY: proceed without asking; IMPLEMENT this launch-readiness issue end-to-end; commit+push+open PR; honest report; gpt-5.5. Reconcile the correct repo/worktree (most launch issues are /srv/repos/aina-academy) + the issue acceptance + builder/verifier from Paperclip issue id %s (`paperclipai issue get %s`). Build behind a flag where it touches prod. Do NOT merge (the PR bot-watcher + merge-gate handle merges). NEVER gpt-5.3-codex-spark.\n' "$title" "$id" "$id" > "$pf"
  ( cd /srv/repos/aina-academy 2>/dev/null || cd /srv/repos; cat "$pf" | codex exec --json --dangerously-bypass-approvals-and-sandbox --model gpt-5.5 -c model_reasoning_effort=high --skip-git-repo-check - > "/srv/aina/ops/coobuild-${id:0:8}.log" 2>&1 ) &
  paperclipai issue update "$id" --status in_progress >/dev/null 2>&1
  touch "$lock"; disp=$((disp+1))
  echo "$(ts) COO dispatched build: $title" >> "$LOG"
done
paperclipai agent heartbeat:invoke "$COO" >/dev/null 2>&1
hermes kanban dispatch --max 4 >/dev/null 2>&1 || true
echo "$(ts) coo-ops cycle: dispatched $disp build lane(s) (cap $CAP)" | tee -a "$LOG" >> "$OPSLOG"
EOS
base64 < coo-ops-loop.sh | ./vds-exec.sh runl '
  base64 -d > /srv/aina/ops/coo-ops-loop.sh && chmod +x /srv/aina/ops/coo-ops-loop.sh
  export PATH=$PATH:/usr/local/bin
  echo "== run COO ops cycle (deterministic build dispatch) =="; bash /srv/aina/ops/coo-ops-loop.sh
  sleep 12
  echo "== codex build lanes running now =="; pgrep -af "codex exec" | grep -v pgrep | wc -l
  echo "== backlog status =="; paperclipai issue list --json 2>/dev/null | python3 -c "import sys,json;from collections import Counter;d=json.load(sys.stdin);i=d if isinstance(d,list) else d.get(\"issues\",d.get(\"data\",[]));n=[x for x in i if \"council-2026-06-29\" in (x.get(\"description\") or \"\")];print(dict(Counter(x.get(\"status\") for x in n)))"
  echo "== coo log =="; tail -5 /srv/aina/ops/coo-ops.log'

cd /Users/Ali/PKM/scratch/pkm-deepdive
# extract the new key from the file (value never typed/echoed by me), base64-pipe to the VDS secret store
KEY=$(grep -oE 'AQ\.[A-Za-z0-9_.-]+' "/Users/Ali/Downloads/Google Agent Platform .txt" | head -1)
printf '%s' "$KEY" | base64 | ./vds-exec.sh runl '
  NK=$(base64 -d)
  S=/srv/aina-hq/.secrets
  mkdir -p "$S"
  # 1. BACK UP the existing key file(s) so the old key is preserved as backup
  for f in vertex-express.env gemini.env gemini-interactions.env; do
    [ -f "$S/$f" ] && cp "$S/$f" "$S/$f.bak-$(date +%Y%m%dT%H%M%S)" && echo "backed up $f";
  done
  # 2. write the NEW key to a dedicated secret file (value NOT echoed)
  umask 077
  printf "GEMINI_API_KEY=%s\nGEMINI_INTERACTIONS_API_KEY=%s\nGOOGLE_API_KEY=%s\nGOOGLE_GENAI_API_KEY=%s\n" "$NK" "$NK" "$NK" "$NK" > "$S/gemini-interactions.env"
  chmod 600 "$S/gemini-interactions.env"
  echo "wrote gemini-interactions.env (new key length: ${#NK}, prefix: ${NK:0:3}...)"
  echo "== existing key VAR NAMES in vertex-express.env (redacted, for backup awareness) =="
  grep -oE "^[A-Z_]*(KEY|TOKEN)[A-Z_]*=" "$S/vertex-express.env" 2>/dev/null | sort -u
'

cd /Users/Ali/PKM/scratch/pkm-deepdive
cat > lane-gemini-newkey.md <<'EOF'
# Lane: Test Gemini Interactions API with the NEW key (Ali-provided 2026-06-29)
## AUTONOMY: proceed without asking; test + honest report; gpt-5.5. NEVER echo/print the key value anywhere (logs, report, commits).
## Context: Ali provided a NEW key (file was "Google Agent Platform" = Gemini Enterprise Agent Platform). Stored at `/srv/aina-hq/.secrets/gemini-interactions.env` (GEMINI_API_KEY / GEMINI_INTERACTIONS_API_KEY / GOOGLE_API_KEY / GOOGLE_GENAI_API_KEY, prefix AQ.). Old key backed up (vertex-express.env.bak). 
## Prior findings (to beat): AI Studio Developer API Interactions WORKS but the OLD key had "prepayment credits depleted"; the Vertex Interactions endpoint rejected the Gemini models (400 unsupported_model_interaction) AND rejected API keys (401). This new AQ. key may be the key that unlocks it — TEST it.
## Do
1. `set -a; source /srv/aina-hq/.secrets/gemini-interactions.env; set +a`. Test the Interactions API with this key across the plausible surfaces, capturing status/latency/tokens/error for each:
   - **AI Studio Developer API**: `POST https://generativelanguage.googleapis.com/v1beta/interactions` with header `x-goog-api-key: $GEMINI_API_KEY`, body {model:"gemini-3.5-flash", input:"Explain how AI works in a few words"} (also try gemini-2.5-flash, and v1beta2 if v1beta 404s).
   - **Gemini Enterprise Agent Platform / Vertex Express**: if the AQ. key is an Express key, try the Express interactions endpoint (check VERTEX_EXPRESS_ENDPOINT pattern + the Gemini Enterprise Agent Platform interactions reference). 
   - Use the existing probe harness (scripts/spikes/ or scripts/probes/gemini-vertex-interactions-probe.mjs) if it can be pointed at the key path; else a minimal probe.
2. If ANY surface WORKS (200 + an interactionId): prove `previous_interaction_id` chaining (2nd turn); run a concurrency probe (ramps 5,25,50, turns 2) → latency p50/p95, 429s, real concurrent ceiling, go/no-go. Then plan the Cloudflare-Workers runtime — a KEY-based path (header) works directly from Workers (no ADC needed), which is a big win; confirm.
3. If it still fails: capture the EXACT error per surface + the precise blocker; compare to prior (depleted-prepay vs model-allowlisting vs key-type). State what (if anything) Ali still needs.
## Deliver: branch ali/gemini-newkey-test-2026-06-29, report `/srv/aina/ops/gemini-newkey-report.md` (WORKS? which surface/model + concurrency + Workers plan, OR exact blocker). Keep flag-off until proven. NEVER expose the key. Honest. gpt-5.5.
EOF
base64 < lane-gemini-newkey.md | ./vds-exec.sh runl '
  base64 -d > /srv/aina/ops/lanes/lane-gemini-newkey.md
  export PATH=$PATH:/usr/local/bin
  C5="exec --json --dangerously-bypass-approvals-and-sandbox --model gpt-5.5 -c model_reasoning_effort=high --skip-git-repo-check -"
  WT=/home/ali/agent-workspaces/aina-academy-gemini-spike-20260629
  [ -d "$WT" ] && cd "$WT" || cd /srv/repos/aina-academy
  nohup bash -c "cat /srv/aina/ops/lanes/lane-gemini-newkey.md | codex $C5" > /srv/aina/ops/codex-gemini-newkey.log 2>&1 &
  echo "gemini-newkey-test lane pid=$!"'

cd /Users/Ali/ui-lesson-previews-ali-recovered-2026-05-18
echo "== file sizes =="; wc -l lessons/*.html assets/*.css
echo; echo "== assets/lesson-shell.css (full) =="; cat assets/lesson-shell.css
echo; echo "== assets/tokens.css (full) =="; cat assets/tokens.css

cd /Users/Ali/ui-lesson-previews-ali-recovered-2026-05-18
tar czf - lessons assets | base64 | /Users/Ali/PKM/scratch/pkm-deepdive/vds-exec.sh runl '
  mkdir -p /srv/aina/ops/reference/recovered-lesson-shell
  base64 -d | tar xzf - -C /srv/aina/ops/reference/recovered-lesson-shell
  echo "STAGED recovered shell:"; ls -R /srv/aina/ops/reference/recovered-lesson-shell | head -20'

cd /Users/Ali/PKM/scratch/pkm-deepdive
cat > lane-lesson-shell-port.md <<'EOF'
# Lane: Port the RECOVERED card-based chat shell to the live lesson page (Ali UI/UX direction)
## AUTONOMY: proceed without asking; build, screenshot-verify, honest report; gpt-5.5. Repo /srv/repos/aina-academy.
## Founder direction (Ali 2026-06-29): the live lesson page (https://aina-academy-staging.img-playground.workers.dev/lesson/) is NOT what he had in mind. Use the RECOVERED chat shell at `/srv/aina/ops/reference/recovered-lesson-shell/` — it has the cards + the 3-column chat shell he wants. "Tweak it a bit" to fit, but MATCH this design.
## The target design (recovered shell):
- **3-column layout**: 260px LEFT (steps + nav) | center (chat stream) | 300px RIGHT (trajectory + hints). Sticky top bars per column. Mobile breakpoints included.
- **Card components**: ExplainerCard, AnnotatedPromptCard, RubricCard, HintStack, callouts (workplace / vague / do-don't), composer. Token-driven (assets/tokens.css + assets/lesson-shell.css, 411 lines — NO literal colors, all via token vars).
- Reference lessons (the look + card usage): `lessons/structured-intent-spec.html`, `context-provision-and-briefing.html`, `universal-path.html`.
## Do
1. Study the recovered shell (the 3 HTML lessons + lesson-shell.css + tokens.css) — the 3-col card-based chat shell is the target look.
2. Find the CURRENT live lesson surface in aina-academy (the React component behind `/lesson/`) + its lesson-data shape. Diff it against the recovered shell.
3. Port the recovered design onto the live lesson page: the 3-column layout + the card components (Explainer / AnnotatedPrompt / Rubric / HintStack) + callouts + composer + chat stream, wired to the REAL lesson data (don't hardcode the sample content). Bring in the recovered lesson-shell.css/tokens.css, reconciled with the aina-design tokens (token-driven). Preserve the live tutor/practice API flow + feature flag. Tweak to fit, but match the recovered card-based chat shell.
4. **Screenshot** the result (desktop + mobile) AND the recovered reference; verify the live page now matches the recovered design (cards + 3-col chat shell). Iterate until it does.
## Deliver: branch ali/lesson-shell-port-2026-06-29, commit+push+PR with the before/after + recovered-vs-new screenshots; report `/srv/aina/ops/lesson-shell-port-report.md`. Behind the lesson flag if it changes the live route. gpt-5.5. Honest if anything can't match. Address Codex bot comments. The review harness + Éowyn visual-QA vet before it surfaces to Ali.
EOF
base64 < lane-lesson-shell-port.md | ./vds-exec.sh runl '
  base64 -d > /srv/aina/ops/lanes/lane-lesson-shell-port.md
  export PATH=$PATH:/usr/local/bin
  C5="exec --json --dangerously-bypass-approvals-and-sandbox --model gpt-5.5 -c model_reasoning_effort=high --skip-git-repo-check -"
  cd /srv/repos/aina-academy
  nohup bash -c "cat /srv/aina/ops/lanes/lane-lesson-shell-port.md | codex $C5" > /srv/aina/ops/codex-lesson-shell-port.log 2>&1 &
  echo "lesson-shell-port lane pid=$!"'