Start a new SiXiS project

PROJECT-ONBOARDING-V0-1 / PHASE 1 / PASTE-BASED FLOW

Draft 8c5d03c4…

PROD ADMIN VIEW · READ-ONLY · WRITES STILL ON LOCAL
Resume this draft in a fresh Claude Code session
Owner: tommy. Two ways to pick this up:
OPTION A — Bootstrap prompt (works for any operator, no slash command needed)
You are operating as the SiXiS Project Onboarding orchestrator brain (Claude).

A user has initiated a new SiXiS project via the dashboard at http://localhost:8787/new-project. They have provided this brain dump:

---
I want to evaluate why things are breaking down... Drafts are not being closed properly, the last 2 projects didn't get passed to the Reviewer... need to resolve or clean up "Needs your attention"... address "Protocol Health" and "Pattern Recognition" and do anything to fortify the protocol
---

## CURRENT STACK & DEPLOY STATE (auto-injected from substrate)

**Hosting:**
- `dashboard.sixis.ai` → Vercel static export (`ui/`)
- `dashboard.sixis.ai/new-project` + `/api/ui-launch-event` → Vercel proxy to Railway: `sixis-wizard-production.up.railway.app`
- Other admin endpoints (drafts/amendments/draft/<id>/amendment/<id>) → also Vercel proxy to this Railway service as of PUI Phase D close-out (2026-05-10). Honor-system admin gate via ?owner= URL param. Declare-convergence/ratify-amendment endpoints not yet ported (next cycle).

**Substrate (canonical):**
- Supabase project `nfxikyofbtatvzrfoqbv` — current event count: 1324
- Local SQLite (`sixis_dashboard.db`) is an archive after Phase B replay caught up (2026-05-07). Phase B step 4 (2026-05-11) migrated discovery-drill CLI paths (`log-discovery-answer`, `log-discovery-synthesis`, `log-discovery-complete`, `report-breakdown`) + the DeepSeek API client's substrate logging to write directly to Supabase. Remaining SQLite-writing CLI paths sync up via the post-invoke mirror.
- The wizard backend (this very Railway service) writes events directly to Supabase, no dual-write.

**Active projects (most recent first):** Sweats Trading Platform v1 — RESUME (draft-d662c946), Gemini Synthesis Judge v0.1 (gemini-synthesis-judge-v0-1), Active Attention Engine (active-attention-engine)

**Last shipped change:** Built gcloud ADC + venv + gsc_pull.py demand-brief tool; tested end-to-end; scheduled task updated to pull GSC before Batch 3.

**Council relay discipline — CORRECTED MATRIX (ratified by Tommy 2026-05-11T02:14, Universal Shell amendment in flight):**
- `cross-poll` defaults `--auto-relay ON`. The orchestrator (Claude Code session) drives all brains directly. API/CLI is the PRIMARY path for the two non-browser brains; browser control is FOR THE TWO REMAINING BROWSER-ONLY BRAINS ONLY:
  - **DeepSeek (voter)** → API via `deepseek_api_v0_1/sixis/deepseek_client.py` (`call_deepseek`). Browser fallback at chat.deepseek.com (Expert/DeepThink mode) ONLY when the API client returns `ok=False` with `fallback=browser`.
  - **Gemini (judge + reviewer)** → CLI/API via `gemini-synthesis-judge-v0-1/` (and `gemini-cli-judge-wrapper-v0-1/`). No browser path needed.
  - **GPT (voter)** → ChatGPT desktop app via computer-use MCP. New chat created INSIDE the "SiXiS" project folder (per per-project chat-thread rule).
  - **Claude.ai (voter)** → claude.ai via Claude-in-Chrome MCP. New chat created INSIDE the SiXiS project folder.
- Tommy is NOT a packet-routing relay node. Pipeline: prompt DeepSeek first via API (longest reasoning), kick off GPT + Claude.ai in browser windows while DeepSeek streams, capture all three responses in any order they arrive.

**Ratification cadence (extended convergence rule, ratified 2026-05-07):**
- Genuine multi-brain convergence at any tier (1/2/3) = automatic ratification — orchestrator proceeds without explicit Tommy ask.
- "Doubt is the cross-poll trigger" — when orchestrator has uncertainty, fire a cross-poll, don't decide unilaterally and don't ask Tommy.
- Sovereign-only matters (red-line risks, irreversible data destruction, money movement, account creation) still always escalate.

**Discoveries fold into scope (rule established 2026-05-07):** anything surfaced during this drill that's adjacent and relevant folds INTO the project's scope by default — don't punt to followups unless folding shifts the tier.


Wizard IDs (use these in the CLI commands below — DO NOT change them):
- draft_id: 8c5d03c4-9b07-4331-a721-527d31bab9eb
- cycle_id: 37245c60-914e-443b-bede-66a36fe09099

## Your job

Per FORCED_RULE_PO_01 (Conversational Discovery Drill), drill the user ONE QUESTION AT A TIME.

The internal checklist below is YOUR scaffolding — NOT an interrogation script for the user. Pick the most upstream open question, ask it, listen, let the answer pivot/collapse/deepen the queue.

Internal checklist:
- intent (the frozen Z1 statement of what they want to build)
- scope (in scope vs explicitly out of scope)
- consumers (who/what uses this)
- constraints (technical, time, resources, external commitments)
- success criteria (how they know it shipped well)
- failure modes (what could break, how they'd detect)
- reversibility / tier classification (Tier 1/2/3)
- required artifacts / deliverables
- known unknowns

Do NOT batch questions. Do NOT pre-load 5+ at once. Per FORCED_RULE_PO_01 this is a hard rule from the project's own Cycle Zero — the rule was generated as a candidate Universal Shell amendment after the orchestrator violated it during the project's design phase.

## Substrate logging

After EACH user answer, log it to substrate:
```
cd ~/Documents/Claude/Projects/SixiS/projects/dashboard_v0_1 && python3 scripts/sixis.py log-discovery-answer --draft-id 8c5d03c4-9b07-4331-a721-527d31bab9eb --cycle-id 37245c60-914e-443b-bede-66a36fe09099 --question "<the question you asked>" --answer "<their answer>"
```

When you reach pollable sufficiency (the council can disagree productively without first asking what the project is), summarize the sharpened intent and ask the user to confirm. Then log the synthesis:
```
cd ~/Documents/Claude/Projects/SixiS/projects/dashboard_v0_1 && python3 scripts/sixis.py log-discovery-synthesis --draft-id 8c5d03c4-9b07-4331-a721-527d31bab9eb --cycle-id 37245c60-914e-443b-bede-66a36fe09099 --synthesis "<your sharpened-intent summary>"
```

After the user confirms the synthesis, mark discovery complete:
```
cd ~/Documents/Claude/Projects/SixiS/projects/dashboard_v0_1 && python3 scripts/sixis.py log-discovery-complete --draft-id 8c5d03c4-9b07-4331-a721-527d31bab9eb --cycle-id 37245c60-914e-443b-bede-66a36fe09099
```

Then propose firing the council cross-poll. The standard SiXiS Protocol cross-poll → 2-round mandatory ratification (per amendment 926869fb) → Layer B drafting cycle applies from there.

## Error handling

If anything crashes, the user reports a wizard issue, or you encounter a malformed/unworkable state mid-drill, log a breakdown:
```
cd ~/Documents/Claude/Projects/SixiS/projects/dashboard_v0_1 && python3 scripts/sixis.py report-breakdown --draft-id 8c5d03c4-9b07-4331-a721-527d31bab9eb --cycle-id 37245c60-914e-443b-bede-66a36fe09099 --source claude --description "<what went wrong>"
```

The user can also report breakdowns from the dashboard "Report breakdown" button (pre-fills draft_id automatically).
Paste into any fresh Claude Code chat — Claude runs the discovery drill on the brain dump.
OPTION B — Slash-command shortcut (Tommy's setup only — needs ~/.claude/commands/sixis-pickup.md installed)
/sixis-pickup 8c5d03c4-9b07-4331-a721-527d31bab9eb
Brain dump (raw)
Original input from /new-project. Stored as raw evidence per FORCED_RULE_PO_02; never edited in place.
I want to evaluate why things are breaking down... Drafts are not being closed properly, the last 2 projects didn't get passed to the Reviewer... need to resolve or clean up "Needs your attention"... address "Protocol Health" and "Pattern Recognition" and do anything to fortify the protocol
Event timeline (20)
Every event tagged with this draft_id, in chronological order.
project_draft_started system · 2026-05-15 03:02:17+00:00
You started a new project draft via /new-project (draft_id=8c5d03c4-9b07-4331-a721-527d31bab9eb).
draft_saved system · 2026-05-15 03:02:17+00:00
You saved the brain-dump for draft 8c5d03c4-9b07-4331-a721-527d31bab9eb: "I want to evaluate why things are breaking down... Drafts are not being closed properly, the last 2 projects didn't get passed to the Reviewer... need to resolve or clean up "Needs your attention"... …"
discovery_prompt_generated system · 2026-05-15 03:02:17+00:00
Generated the discovery drill prompt for draft 8c5d03c4-9b07-4331-a721-527d31bab9eb using prompt_templates.discovery_drill v3.
ui_launch_event system · 2026-05-15 03:02:30+00:00
You clicked 'Copy prompt' on /new-project for draft 8c5d03c4-9b07-4331-a721-527d31bab9eb — prompt taken to Claude Code (prompt_hash=70e8e21e0e7f…).
discovery_answer_logged tommy · 2026-05-15 03:05:16+00:00
Q: "Does this feel like one root cause leaking into different surfaces, or genuinely…" — A: "It feels like new sessions are not following clean protocol and have to keep being reminded."
discovery_answer_logged tommy · 2026-05-15 03:07:26+00:00
Q: "When a fresh session misbehaves, what are you reminding it of most often — rules…" — A: "A lot of it is just 'you're not following protocol' — it's the meta-behavior, not a specific missing artifact."
discovery_answer_logged tommy · 2026-05-15 03:12:26+00:00
Q: "What's the specific tell that makes you say 'you're not following protocol'?" — A: "Three concrete tells: (1) showing me schemas when it's not supposed to, (2) asking me things when it should ask the coun…"
discovery_answer_logged tommy · 2026-05-15 03:14:37+00:00
Q: "Which stung more — Reviewer-skip (structural) or the behavioral leaks?" — A: "Behavioral one dominates."
discovery_answer_logged tommy · 2026-05-15 03:16:19+00:00
Q: "Do those existing surfaces actually capture behavioral violations today, or are …" — A: "It's supposed to, but sometimes that also breaks down and I forget to check."
discovery_answer_logged tommy · 2026-05-15 03:18:07+00:00
Q: "End-to-end across all three layers, or scope tighter to just consumption?" — A: "End to end."
discovery_synthesis_logged claude · 2026-05-15 03:24:21+00:00
Claude synthesized the discovery drill intent for draft 8c5d03c4-9b07-4331-a721-527d31bab9eb: "Fortify SiXiS protocol absorption end-to-end so fresh Claude Code sessions embody the protocol rather than just having access to it — and Tommy stops being the protocol cop. The breakdown is a 3-layer…"
wizard_step_completed claude · 2026-05-15 03:25:05+00:00
Claude marked the discovery drill complete for draft 8c5d03c4-9b07-4331-a721-527d31bab9eb. Wizard advances from discovery to intent-freeze step.
breakdown claude · 2026-05-15 03:28:47+00:00
cross-poll CLI failed with sqlite3.IntegrityError: FOREIGN KEY constraint failed. Root cause: wizard backend (Railway) writes draft + cycle rows directly to Supabase, but cross-poll CLI writes to local SQLite which doesn't have a mirror of the wizard-created cycle. This is exactly the kind of substrate-split-brain protocol mechanism gap that folds into the P…
brain_response_logged gpt · 2026-05-15 03:37:03+00:00
GPT Round 1 response for draft 8c5d03c4-9b07-4331-a721-527d31bab9eb: "(1) Vote: 6-card project. 1. Backlog Triage / Proof Card — clear Needs-Your-Attention, Protocol Health, Pattern Recognition. 2. Violation Taxonomy + Event Schema — define behavioral violations as fir…"
brain_response_logged deepseek · 2026-05-15 03:41:46+00:00
DEEPSEEK Round 1 response for draft 8c5d03c4-9b07-4331-a721-527d31bab9eb: "1. **Card breakdown and order** - **Card 1: Triage & Baseline the Backlog** — Clear the current Needs-Your-Attention, Protocol Health, and Pattern Recognition items. Close stale alerts, confirm rea…"
brain_response_logged claude · 2026-05-15 03:45:55+00:00
CLAUDE Round 1 response for draft 8c5d03c4-9b07-4331-a721-527d31bab9eb: "[Brain: Claude | TASK_TYPE: STRATEGY | CYCLE: SiXiS Protocol Fortification — Round 1 | ROLE: Council Voter] **CLAUDE'S STANCE (second-thought anchor, per M-Imperative-2):** The framing is mostly righ…"
brain_response_logged gpt · 2026-05-15 03:51:49+00:00
GPT Round 2 response for draft 8c5d03c4-9b07-4331-a721-527d31bab9eb: "A — SHIFT Adopt hybrid: session-start receipt + mid-session footer + violation feedback loop. Claude is right that session-start alone decays and cannot be the load-bearing surface. But rejecting it…"
brain_response_logged claude · 2026-05-15 03:54:03+00:00
CLAUDE Round 2 response for draft 8c5d03c4-9b07-4331-a721-527d31bab9eb: "[Brain: Claude | TASK_TYPE: STRATEGY | CYCLE: SiXiS Protocol Fortification — Round 2 | ROLE: Council Voter] --- **DIVERGENCE A — SHIFT (partial).** Moving off "reject session-start as load-bearing"…"
brain_response_logged deepseek · 2026-05-15 03:54:24+00:00
DEEPSEEK Round 2 response for draft 8c5d03c4-9b07-4331-a721-527d31bab9eb: "**Divergence A — SHIFT.** Moving from a pure session-start checksum-echo-plus-log-violation to a **combined mechanism**: session-start ceremony *with* mid-session persistence. Session-start prints t…"
breakdown claude · 2026-05-15 03:59:22+00:00
reviewer-bundle SCOPE LEAKAGE: the bundle generated for draft 8c5d03c4 (Protocol Fortification) pulled in 409KB of substrate events from across the entire cycle (37245c60), which is the wizard's own meta-cycle 'Schema & UI Scaffold Lock' and contains events from unrelated work (e.g. daemon architecture, profile-claim atomic, browser load). Gemini's 5 finding…