Ingest
Pull from everywhere
Documents, transcripts, emails, screenshots — collected from separate reservoirs, normalized, cross-referenced.
Showcase
Corpus, pipeline, deploy surfaces, and verification gates — skimmable on a phone.
—Artifacts
—Patterns
—Matters
—Cast
—Brain
What it does
Documents in. Cited evidence out. Every claim walks back to the file it came from — cross-linked across cases, people, dates, and patterns.
Analyze
Name the patterns
A working taxonomy of institutional behaviors, attached to the artifacts that prove them. Every pattern walks back to the receipts.
Recall
Who, what, when, where
Every cast member, case, date, and citation is indexed. Ask the question; the answer arrives with sources attached.
Operate
Ready when you are
Live deadlines, settlement posture, expert status, matter readiness — current with the docket, not chasing it.
Architecture at a glance
Sources → manifest → codex → catalog. Expand for the flow diagram and layer cards.
Flow diagram and layer cards
Source→
Sidecar→
Manifest→
Patterns→
Catalog
Prompt Core
Stonewall Brain
Where retrieval gets ordered and the companion skills get dispatched. The voice and the guardrails live here.
Flat-File Database
Catalog
One markdown manifest, every artifact indexed. Search by character, pattern, date, case, or keyword. Derived indexes open other doors into the same ground truth.
Codex Layer
Canon
Cast, case, artifact, phenomenology, deposition. The reference layer that keeps identity, chronology, patterns, and matter posture from drifting.
Automation
Pipeline & sync
Ingestion, transcription, email consolidation, and two-way sync with the operational systems where the work actually happens.
Rule: the manifest points — the file proves.
The stack
Python, Node, TypeScript, FastAPI portal, Next cockpit, Vercel + Railway deploys.
Full stack table
| Languages | Python 3.12 Node 24 TypeScript Markdown |
|---|---|
| Corpus database | Flat-file (Markdown + JSON) SQLite — catalog/manifest.md is the single source of truth; SQLite mirrors it for keyword search. |
| Public surfaces | Vercel — landing + portal SPA + insights + this page, all statically rendered with public-corpus data. |
| Corpus API |
FastAPI
Uvicorn
httpx
— api.stonewall.esq serves the canonical
corpus stats and reader endpoints from the same flat-file
manifest the static surfaces consume.
|
| Operator console |
Next.js 15
React
Tailwind
— app.stonewall.esq, authenticated, carries
the live-matter workspaces, readers, billing, and
command palette.
|
| Bot runtime |
Railway
Docker
Telegram Bot API
— Stonewall Telegram Bot, polling, deployed from the
repo root scripts/stonewall_bot/.
|
| AI surface | Claude Opus Whisper Gemini TTS-1-HD — orchestration core, voice-to-text, music analysis, voice output. Brain pack mirrors the canonical codices. |
| Sync & intake | pypdfium2 Tesseract extract-msg Notion API — gold-standard 300dpi raster OCR sidecars, email consolidation, Filevine/Domo bridges. |
| CI & gates | GitHub Actions pytest Vitest Playwright — verify-all suite gates manifest consistency, ontology validation, language audit, and brain-pack drift. |
Where the work lives
Three places, one record. The repo holds the canon, the workspace holds the work in progress, the reservoirs are where new evidence comes from. All three move with the docket — nothing here is a snapshot.
Repository
The catalog, the codex, the source artifacts, the static site. Version-controlled, grep-able, inspectable to the byte.
Workspace
Matter registry, archive, message thread, task backlog — relations wired across, morning brief on top.
Evidence reservoirs
Documents, transcripts, exports, screenshots. Pulled from upstream sources, normalized, then read.
Public portal
Search the corpus, count the deadlines, see how patterns reach across matters. The signed-in console holds the live record.
Ship pillars: reliability, security, performance, operations, cost — full table on the standards page.