phase 0+1: project scaffold, k8s manifests, CI pipeline, steering, hooks, tests

- Repository structure for all services, infra, lakehouse, dashboards
- K8s manifests targeting stonks-oracle namespace with GHCR images
- Ingress via Traefik with ca-issuer TLS for internal services
- ConfigMap wired to existing cluster services (pg, redis, minio, ollama)
- GitHub Actions workflow for lint, test, multi-service container builds
- Dockerfile with build-arg CMD per service
- Makefile for local build/push/deploy
- Steering rules for TDD workflow, K8s conventions, project context
- Agent hooks for lint-on-save, test-on-save, k8s-validate, phase-commit
- Ruff linter config, all lint issues fixed
- 14 passing tests for schemas, config, redis keys
- PostgreSQL migrations, Trino catalogs, Superset config, MinIO lifecycle
This commit is contained in:
Celes Renata
2026-04-11 03:25:08 -07:00
parent 8cfc4f423b
commit ebea70573b
90 changed files with 3590 additions and 19 deletions
+99
View File
@@ -0,0 +1,99 @@
-- Stonks Oracle - Initial PostgreSQL Schema
-- Phase 1: Core data model
-- Extensions
CREATE EXTENSION IF NOT EXISTS "uuid-ossp";
CREATE EXTENSION IF NOT EXISTS "pgcrypto";
-- ============================================================
-- Companies and Watchlists
-- ============================================================
CREATE TABLE companies (
id UUID PRIMARY KEY DEFAULT uuid_generate_v4(),
ticker VARCHAR(20) NOT NULL,
legal_name VARCHAR(500) NOT NULL,
exchange VARCHAR(50),
sector VARCHAR(200),
industry VARCHAR(200),
market_cap_bucket VARCHAR(50),
active BOOLEAN NOT NULL DEFAULT TRUE,
created_at TIMESTAMPTZ NOT NULL DEFAULT NOW(),
updated_at TIMESTAMPTZ NOT NULL DEFAULT NOW(),
UNIQUE(ticker, exchange)
);
CREATE TABLE company_aliases (
id UUID PRIMARY KEY DEFAULT uuid_generate_v4(),
company_id UUID NOT NULL REFERENCES companies(id) ON DELETE CASCADE,
alias VARCHAR(500) NOT NULL,
alias_type VARCHAR(50) NOT NULL DEFAULT 'brand',
created_at TIMESTAMPTZ NOT NULL DEFAULT NOW()
);
CREATE INDEX idx_company_aliases_company ON company_aliases(company_id);
CREATE INDEX idx_company_aliases_alias ON company_aliases(alias);
CREATE TABLE watchlists (
id UUID PRIMARY KEY DEFAULT uuid_generate_v4(),
name VARCHAR(200) NOT NULL UNIQUE,
description TEXT,
active BOOLEAN NOT NULL DEFAULT TRUE,
created_at TIMESTAMPTZ NOT NULL DEFAULT NOW(),
updated_at TIMESTAMPTZ NOT NULL DEFAULT NOW()
);
CREATE TABLE watchlist_members (
id UUID PRIMARY KEY DEFAULT uuid_generate_v4(),
watchlist_id UUID NOT NULL REFERENCES watchlists(id) ON DELETE CASCADE,
company_id UUID NOT NULL REFERENCES companies(id) ON DELETE CASCADE,
added_at TIMESTAMPTZ NOT NULL DEFAULT NOW(),
UNIQUE(watchlist_id, company_id)
);
-- ============================================================
-- Sources and Credentials
-- ============================================================
CREATE TABLE sources (
id UUID PRIMARY KEY DEFAULT uuid_generate_v4(),
company_id UUID NOT NULL REFERENCES companies(id) ON DELETE CASCADE,
source_type VARCHAR(50) NOT NULL,
source_name VARCHAR(200) NOT NULL,
config JSONB NOT NULL DEFAULT '{}',
credibility_score FLOAT DEFAULT 0.5,
retention_days INTEGER DEFAULT 365,
access_policy VARCHAR(50) DEFAULT 'internal',
active BOOLEAN NOT NULL DEFAULT TRUE,
created_at TIMESTAMPTZ NOT NULL DEFAULT NOW(),
updated_at TIMESTAMPTZ NOT NULL DEFAULT NOW()
);
CREATE INDEX idx_sources_company ON sources(company_id);
CREATE INDEX idx_sources_type ON sources(source_type);
CREATE TABLE api_credentials_refs (
id UUID PRIMARY KEY DEFAULT uuid_generate_v4(),
provider VARCHAR(100) NOT NULL UNIQUE,
secret_ref VARCHAR(500) NOT NULL,
created_at TIMESTAMPTZ NOT NULL DEFAULT NOW()
);
-- ============================================================
-- Ingestion Tracking
-- ============================================================
CREATE TABLE ingestion_runs (
id UUID PRIMARY KEY DEFAULT uuid_generate_v4(),
source_id UUID REFERENCES sources(id),
company_id UUID REFERENCES companies(id),
source_type VARCHAR(50) NOT NULL,
status VARCHAR(50) NOT NULL DEFAULT 'pending',
started_at TIMESTAMPTZ NOT NULL DEFAULT NOW(),
completed_at TIMESTAMPTZ,
items_fetched INTEGER DEFAULT 0,
items_new INTEGER DEFAULT 0,
error_message TEXT,
retry_count INTEGER DEFAULT 0,
next_retry_at TIMESTAMPTZ
);
CREATE INDEX idx_ingestion_runs_status ON ingestion_runs(status);
CREATE INDEX idx_ingestion_runs_source ON ingestion_runs(source_id);
@@ -0,0 +1,114 @@
-- Stonks Oracle - Documents and Intelligence Schema
-- ============================================================
-- Market Snapshots
-- ============================================================
CREATE TABLE market_snapshots (
id UUID PRIMARY KEY DEFAULT uuid_generate_v4(),
company_id UUID NOT NULL REFERENCES companies(id),
ticker VARCHAR(20) NOT NULL,
snapshot_type VARCHAR(50) NOT NULL,
data JSONB NOT NULL,
source_provider VARCHAR(100),
captured_at TIMESTAMPTZ NOT NULL DEFAULT NOW(),
storage_ref VARCHAR(1000),
content_hash VARCHAR(128)
);
CREATE INDEX idx_market_snapshots_ticker ON market_snapshots(ticker, captured_at DESC);
CREATE INDEX idx_market_snapshots_hash ON market_snapshots(content_hash);
-- ============================================================
-- Documents
-- ============================================================
CREATE TABLE documents (
id UUID PRIMARY KEY DEFAULT uuid_generate_v4(),
document_type VARCHAR(50) NOT NULL,
source_type VARCHAR(50) NOT NULL,
publisher VARCHAR(500),
url TEXT,
canonical_url TEXT,
title TEXT,
published_at TIMESTAMPTZ,
retrieved_at TIMESTAMPTZ NOT NULL DEFAULT NOW(),
language VARCHAR(10) DEFAULT 'en',
content_hash VARCHAR(128) NOT NULL,
raw_storage_ref VARCHAR(1000),
normalized_storage_ref VARCHAR(1000),
parse_quality_score FLOAT,
parse_confidence VARCHAR(20) DEFAULT 'unknown',
status VARCHAR(50) NOT NULL DEFAULT 'ingested',
created_at TIMESTAMPTZ NOT NULL DEFAULT NOW(),
updated_at TIMESTAMPTZ NOT NULL DEFAULT NOW()
);
CREATE UNIQUE INDEX idx_documents_hash ON documents(content_hash);
CREATE INDEX idx_documents_status ON documents(status);
CREATE INDEX idx_documents_published ON documents(published_at DESC);
CREATE TABLE document_versions (
id UUID PRIMARY KEY DEFAULT uuid_generate_v4(),
document_id UUID NOT NULL REFERENCES documents(id) ON DELETE CASCADE,
version INTEGER NOT NULL DEFAULT 1,
content_hash VARCHAR(128) NOT NULL,
storage_ref VARCHAR(1000),
created_at TIMESTAMPTZ NOT NULL DEFAULT NOW()
);
CREATE TABLE document_company_mentions (
id UUID PRIMARY KEY DEFAULT uuid_generate_v4(),
document_id UUID NOT NULL REFERENCES documents(id) ON DELETE CASCADE,
company_id UUID NOT NULL REFERENCES companies(id),
ticker VARCHAR(20) NOT NULL,
mention_type VARCHAR(50) DEFAULT 'direct',
confidence FLOAT DEFAULT 0.5,
created_at TIMESTAMPTZ NOT NULL DEFAULT NOW()
);
CREATE INDEX idx_doc_mentions_doc ON document_company_mentions(document_id);
CREATE INDEX idx_doc_mentions_company ON document_company_mentions(company_id);
-- ============================================================
-- Document Intelligence (AI Extraction)
-- ============================================================
CREATE TABLE document_intelligence (
id UUID PRIMARY KEY DEFAULT uuid_generate_v4(),
document_id UUID NOT NULL REFERENCES documents(id) ON DELETE CASCADE,
summary TEXT,
macro_themes JSONB DEFAULT '[]',
novelty_score FLOAT,
source_credibility FLOAT,
extraction_warnings JSONB DEFAULT '[]',
confidence FLOAT,
model_provider VARCHAR(50),
model_name VARCHAR(200),
prompt_version VARCHAR(100),
schema_version VARCHAR(50),
raw_output_ref VARCHAR(1000),
prompt_ref VARCHAR(1000),
validation_status VARCHAR(50) DEFAULT 'pending',
validation_errors JSONB DEFAULT '[]',
retry_count INTEGER DEFAULT 0,
created_at TIMESTAMPTZ NOT NULL DEFAULT NOW(),
updated_at TIMESTAMPTZ NOT NULL DEFAULT NOW()
);
CREATE INDEX idx_doc_intel_document ON document_intelligence(document_id);
CREATE INDEX idx_doc_intel_validation ON document_intelligence(validation_status);
CREATE TABLE document_impact_records (
id UUID PRIMARY KEY DEFAULT uuid_generate_v4(),
intelligence_id UUID NOT NULL REFERENCES document_intelligence(id) ON DELETE CASCADE,
company_id UUID NOT NULL REFERENCES companies(id),
ticker VARCHAR(20) NOT NULL,
relevance FLOAT,
sentiment VARCHAR(20),
impact_score FLOAT,
impact_horizon VARCHAR(50),
catalyst_type VARCHAR(50),
key_facts JSONB DEFAULT '[]',
risks JSONB DEFAULT '[]',
evidence_spans JSONB DEFAULT '[]',
created_at TIMESTAMPTZ NOT NULL DEFAULT NOW()
);
CREATE INDEX idx_impact_intel ON document_impact_records(intelligence_id);
CREATE INDEX idx_impact_company ON document_impact_records(company_id);
@@ -0,0 +1,160 @@
-- Stonks Oracle - Trends, Recommendations, Orders Schema
-- ============================================================
-- Trend Windows
-- ============================================================
CREATE TABLE trend_windows (
id UUID PRIMARY KEY DEFAULT uuid_generate_v4(),
entity_type VARCHAR(50) NOT NULL DEFAULT 'company',
entity_id VARCHAR(100) NOT NULL,
window VARCHAR(20) NOT NULL,
trend_direction VARCHAR(20) NOT NULL DEFAULT 'neutral',
trend_strength FLOAT DEFAULT 0.5,
confidence FLOAT DEFAULT 0.5,
top_supporting_evidence JSONB DEFAULT '[]',
top_opposing_evidence JSONB DEFAULT '[]',
dominant_catalysts JSONB DEFAULT '[]',
material_risks JSONB DEFAULT '[]',
contradiction_score FLOAT DEFAULT 0.0,
market_context JSONB DEFAULT '{}',
generated_at TIMESTAMPTZ NOT NULL DEFAULT NOW(),
created_at TIMESTAMPTZ NOT NULL DEFAULT NOW()
);
CREATE INDEX idx_trends_entity ON trend_windows(entity_type, entity_id, window);
CREATE INDEX idx_trends_generated ON trend_windows(generated_at DESC);
-- ============================================================
-- Recommendations
-- ============================================================
CREATE TABLE recommendations (
id UUID PRIMARY KEY DEFAULT uuid_generate_v4(),
ticker VARCHAR(20) NOT NULL,
company_id UUID REFERENCES companies(id),
action VARCHAR(20) NOT NULL DEFAULT 'watch',
mode VARCHAR(30) NOT NULL DEFAULT 'informational',
confidence FLOAT DEFAULT 0.5,
time_horizon VARCHAR(50),
thesis TEXT,
invalidation_conditions JSONB DEFAULT '[]',
portfolio_pct FLOAT DEFAULT 0.02,
max_loss_pct FLOAT DEFAULT 0.005,
model_version VARCHAR(100),
generated_at TIMESTAMPTZ NOT NULL DEFAULT NOW(),
created_at TIMESTAMPTZ NOT NULL DEFAULT NOW()
);
CREATE INDEX idx_recommendations_ticker ON recommendations(ticker, generated_at DESC);
CREATE INDEX idx_recommendations_mode ON recommendations(mode);
CREATE TABLE recommendation_evidence (
id UUID PRIMARY KEY DEFAULT uuid_generate_v4(),
recommendation_id UUID NOT NULL REFERENCES recommendations(id) ON DELETE CASCADE,
document_id UUID REFERENCES documents(id),
intelligence_id UUID REFERENCES document_intelligence(id),
evidence_type VARCHAR(50) DEFAULT 'supporting',
weight FLOAT DEFAULT 1.0,
created_at TIMESTAMPTZ NOT NULL DEFAULT NOW()
);
CREATE INDEX idx_rec_evidence_rec ON recommendation_evidence(recommendation_id);
-- ============================================================
-- Risk Evaluations
-- ============================================================
CREATE TABLE risk_evaluations (
id UUID PRIMARY KEY DEFAULT uuid_generate_v4(),
recommendation_id UUID NOT NULL REFERENCES recommendations(id),
eligible BOOLEAN NOT NULL DEFAULT FALSE,
allowed_mode VARCHAR(30) DEFAULT 'informational',
rejection_reasons JSONB DEFAULT '[]',
risk_checks JSONB DEFAULT '{}',
evaluated_at TIMESTAMPTZ NOT NULL DEFAULT NOW()
);
CREATE INDEX idx_risk_eval_rec ON risk_evaluations(recommendation_id);
-- ============================================================
-- Broker Accounts and Orders
-- ============================================================
CREATE TABLE broker_accounts (
id UUID PRIMARY KEY DEFAULT uuid_generate_v4(),
provider VARCHAR(100) NOT NULL,
account_id VARCHAR(200) NOT NULL,
mode VARCHAR(20) NOT NULL DEFAULT 'paper',
config JSONB DEFAULT '{}',
active BOOLEAN NOT NULL DEFAULT TRUE,
created_at TIMESTAMPTZ NOT NULL DEFAULT NOW()
);
CREATE TABLE orders (
id UUID PRIMARY KEY DEFAULT uuid_generate_v4(),
recommendation_id UUID REFERENCES recommendations(id),
broker_account_id UUID REFERENCES broker_accounts(id),
ticker VARCHAR(20) NOT NULL,
side VARCHAR(10) NOT NULL,
order_type VARCHAR(20) NOT NULL DEFAULT 'market',
quantity NUMERIC NOT NULL,
limit_price NUMERIC,
stop_price NUMERIC,
status VARCHAR(30) NOT NULL DEFAULT 'pending',
idempotency_key VARCHAR(200) NOT NULL UNIQUE,
broker_order_id VARCHAR(200),
decision_trace JSONB DEFAULT '{}',
submitted_at TIMESTAMPTZ,
acknowledged_at TIMESTAMPTZ,
filled_at TIMESTAMPTZ,
cancelled_at TIMESTAMPTZ,
rejected_at TIMESTAMPTZ,
rejection_reason TEXT,
fill_price NUMERIC,
fill_quantity NUMERIC,
created_at TIMESTAMPTZ NOT NULL DEFAULT NOW(),
updated_at TIMESTAMPTZ NOT NULL DEFAULT NOW()
);
CREATE INDEX idx_orders_ticker ON orders(ticker, created_at DESC);
CREATE INDEX idx_orders_status ON orders(status);
CREATE INDEX idx_orders_idempotency ON orders(idempotency_key);
CREATE TABLE order_events (
id UUID PRIMARY KEY DEFAULT uuid_generate_v4(),
order_id UUID NOT NULL REFERENCES orders(id) ON DELETE CASCADE,
event_type VARCHAR(50) NOT NULL,
data JSONB DEFAULT '{}',
broker_timestamp TIMESTAMPTZ,
created_at TIMESTAMPTZ NOT NULL DEFAULT NOW()
);
CREATE INDEX idx_order_events_order ON order_events(order_id);
-- ============================================================
-- Positions
-- ============================================================
CREATE TABLE positions (
id UUID PRIMARY KEY DEFAULT uuid_generate_v4(),
broker_account_id UUID REFERENCES broker_accounts(id),
ticker VARCHAR(20) NOT NULL,
quantity NUMERIC NOT NULL DEFAULT 0,
avg_entry_price NUMERIC,
current_price NUMERIC,
unrealized_pnl NUMERIC,
realized_pnl NUMERIC DEFAULT 0,
updated_at TIMESTAMPTZ NOT NULL DEFAULT NOW()
);
CREATE INDEX idx_positions_ticker ON positions(ticker);
-- ============================================================
-- Audit Events
-- ============================================================
CREATE TABLE audit_events (
id UUID PRIMARY KEY DEFAULT uuid_generate_v4(),
event_type VARCHAR(100) NOT NULL,
entity_type VARCHAR(100),
entity_id UUID,
actor VARCHAR(200) DEFAULT 'system',
data JSONB DEFAULT '{}',
created_at TIMESTAMPTZ NOT NULL DEFAULT NOW()
);
CREATE INDEX idx_audit_events_type ON audit_events(event_type, created_at DESC);
CREATE INDEX idx_audit_events_entity ON audit_events(entity_type, entity_id);