- LLMClient Protocol for provider-agnostic inference
- VLLMClient for OpenAI-compatible /v1/chat/completions API
- LLM client factory with provider routing (ollama/vllm)
- VLLMConfig with VLLM_* environment variable loading
- Updated extractor worker with health check and provider switching
- Updated event classifier to use LLMClient protocol
- Helm values for vLLM configuration
- 18 unit tests + 6 property-based tests
- Full backward compatibility preserved
- Added pipelineEnabled flag to Helm values (default: true)
- Worker services (scheduler, ingestion, parser, extractor, aggregation,
recommendation, broker-adapter, lake-publisher) scale to 0 when disabled
- API services always run regardless of toggle
- Redis-based runtime toggle: POST /api/ops/pipeline/toggle
- Scheduler checks the flag before each cycle
- Frontend: green/red Pipeline ON/OFF button on the pipeline page
- Beta defaults to pipelineEnabled: false
- Base values.yaml: blanked external URLs (Ollama, Polygon, Alpaca)
so stages only connect to what they explicitly configure
- Migration 026 and OllamaConfig now default to qwen3.5:9b instead of
llama3.1:8b. Existing deployments keep their current model (qwen3.5:9b-fast)
since the migration uses WHERE NOT EXISTS on slug.
- Event classifier system prompt expanded with macro-vs-company filtering:
explicitly instructs the model to NOT classify single-company news
(lawsuits, earnings, management changes, debt crises) as macro events.
Sets severity=low and confidence<0.3 for company-specific articles.
Reserves 'critical' severity for multi-country/global market events.
Prevents over-tagging event_types by requiring direct description.
- Updated test_system_prompt_is_concise threshold to accommodate the
expanded prompt (300 → 1000 chars).
Two tiers of market data:
1. Per-ticker prev bars (existing 50 sources, 15-min cadence) for
watchlist detail — trading decisions, stop-loss, position sizing
2. Grouped daily (new single source, once per day) for broad market
context — correlation analysis, sector rotation, competitive intel
Changes:
- Add grouped_daily endpoint to PolygonMarketAdapter with auto date
calculation (previous trading day, skip weekends)
- Add fetch_global_market_sources() to scheduler for sources without
company_id, scheduled once daily (86400s cadence)
- Update _persist_market_items to use item-level ticker from T field
and look up company_id dynamically for grouped daily bars
- Migration 020: make company_id nullable on sources and
market_snapshots tables, add grouped daily source row
- Fix backtest replay to query market_snapshots data->>'c' for prices
Phase 2 of the autonomous trading engine:
- Replace start()/stop() stubs with real async implementations
- Decision loop: polls recommendations from PostgreSQL, deduplicates
via Redis, evaluates through the full pipeline, submits orders to
stonks:queue:broker_orders
- Stop-loss monitor: fetches prices from Polygon API, checks crossings,
submits immediate sell orders, safety sell after 15 min without data
- Performance loop: computes metrics every 5 min during market hours,
persists daily snapshots at market close
- Risk tier scheduler: evaluates daily at 16:00 ET, persists tier changes
- Rebalance scheduler: evaluates Monday 09:45 ET, respects circuit breaker
- Notification dispatch: SNS + Gmail with rate limiting and retry
- Backtest replay: fetches historical data, simulates decisions, persists
- Real asyncpg/redis connections in FastAPI lifespan (graceful degradation)
- Migration 019: enable paper trading with conservative tier, 5 cap
- Added max_open_positions to TradingConfig with env var loading
- Phase 2 tasks added to autonomous-trading-engine spec
Macro news documents have no ticker, causing upload_normalized_text
and upload_parser_output to produce paths like parsed//2026/...
which MinIO rejects as XMinioInvalidObjectName. Use '_global' as
the path segment when ticker is empty, matching the existing
macro prefix pattern in upload_raw_document.
- Switch Ollama calls from non-streaming to streaming with early termination
- Add loop detection, max token limit, and stall timeout guards
- Add catalyst_type alias normalizer to handle model hallucinations
- Add explicit enum values in extraction prompt for catalyst_type
- Add streaming config knobs to OllamaConfig
Celes Renata