3ff910433f
fix: reject empty LLM classifications for global events
...
When the LLM returns empty summary and no key facts, raise ValueError
so the retry logic kicks in instead of persisting an empty event.
Also strip whitespace from summary and filter empty key_facts entries.
Cleaned up 17 empty events from the database.
2026-04-15 19:46:31 +00:00
326c409d63
fix: use _global fallback for empty ticker in MinIO storage paths
...
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.
2026-04-15 19:25:23 +00:00
4ffde8cc06
feat: autonomous trading engine — full implementation
...
- Database migration 018 with 13 tables for trading engine state
- Trading engine service (services/trading/) with 12 pure computation modules:
position sizer, stop-loss manager, reserve pool, circuit breaker,
risk tier controller, correlation matrix, tax lots, trading window,
gradual entry, notifications, micro-trading, backtester
- Core TradingEngine with pre-trade evaluation pipeline and integration wiring
- FastAPI HTTP service with 14 endpoints (health, config, decisions, metrics, backtest)
- Performance tracker with Sharpe ratio, drawdown, profit factor computation
- 194 Python tests (165 property-based + 29 integration)
- Frontend: 13 TanStack Query hooks, 7 dashboard panels, tabbed Trading Engine page
- Helm chart entry, network policy, nginx proxy, ingress for trading-engine
- Shared infrastructure: enums, Redis keys, TradingConfig in AppConfig
2026-04-15 16:12:22 +00:00
da86132f0c
fix: add num_predict=16384 to prevent output truncation on large articles
2026-04-15 03:11:13 +00:00
b8a2cdc52a
fix: fill default values for missing fields in truncated LLM output
2026-04-15 03:08:10 +00:00
00044af993
fix: switch to think=false with json-repair — 20x faster extraction
2026-04-15 02:54:39 +00:00
4f2ae23d42
fix: set num_predict=16384 so model has token budget for thinking + content
2026-04-15 01:47:00 +00:00
46b069a748
fix: switch to non-streaming Ollama calls — streaming breaks thinking mode
2026-04-15 01:19:17 +00:00
ffe19eb23a
fix: handle empty ticker in MinIO storage paths, clean up debug log
2026-04-15 00:39:53 +00:00
8b5b692d3c
fix: update stall timer during thinking phase to prevent premature stream abort
2026-04-15 00:06:49 +00:00
01726af360
fix: remove think=false (Ollama bug #14645 ), bump max_tokens to 32k
2026-04-14 23:50:28 +00:00
8d0526470d
feat: expand seed to 50 companies with competitor relationships and macro source
2026-04-14 21:00:19 +00:00
e1792e06b9
fix: skip non-UUID pattern signal IDs in evidence persistence
2026-04-14 20:18:50 +00:00
d37a5732d0
fix: use timedelta instead of string for interval query params
2026-04-14 20:10:38 +00:00
c438d0d60a
fix: competitor lookup uses ticker join instead of UUID comparison
2026-04-14 20:04:56 +00:00
d8ea58104c
fix: lint errors (import sorting, unused vars)
2026-04-14 19:48:19 +00:00
f7a11d14ea
feat: competitive intelligence & historical pattern matching layer
2026-04-14 19:42:48 +00:00
b478022ba3
fix: data quality query and suppression fallback in recommendation worker
...
- Fix _DATA_QUALITY_QUERY: remove nonexistent d.source_id/s.source_class,
use d.source_type directly
- Fix LIMIT 1 applied after jsonb expansion by restructuring as CTE
- Fix fallback build_quality_context_from_summary returning empty
source_types which always triggered LOW_SOURCE_DIVERSITY suppression
- Update test to reflect corrected fallback behavior
2026-04-14 06:57:46 +00:00
4fbddc307a
fix(extractor): fallback for any unrecognized impact_horizon value
2026-04-12 16:27:37 -07:00
6ae8aa779e
fix(extractor): add underscore variants to impact_horizon normalizer
...
Model returns long_term/short_term/medium_term instead of hyphenated versions
2026-04-12 16:08:25 -07:00
cd782d1552
fix(extractor): streaming with guardrails + catalyst_type normalization
...
- 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
2026-04-12 15:28:20 -07:00
6e2f174b19
phase 17: disable qwen3.5 thinking mode (think:false) to reduce latency and improve structured output
2026-04-12 12:35:24 -07:00
45f0c03639
phase 17: add request-level URL logging to OllamaClient for proxy debugging
2026-04-12 12:32:44 -07:00
1993bfdf3e
phase 17: add extraction output normalization — clamp scores to 0-1, map impact_horizon alternatives
2026-04-12 10:15:38 -07:00
66ed38bf18
phase 17: switch to gemma4:e4b, rewrite prompts for fill-the-fields style with forced ticker inclusion
2026-04-12 10:05:31 -07:00
2e42310f07
phase 17: fix SEC EDGAR 403 — use descriptive User-Agent with contact email per fair access policy
2026-04-12 09:50:29 -07:00
311d76dc0b
phase 17: enrich SEC EDGAR filings with URLs, titles, dedupe by accession number, skip XML fragments
2026-04-12 09:42:12 -07:00
28b3361833
phase 17: remove embedded JSON schema from user prompt (4.7KB saved), Ollama format param handles it
2026-04-12 09:28:28 -07:00
57d0fc7d33
phase 17: pass all tracked tickers to extractor, soften prompt for macro-to-company relevance
2026-04-12 09:18:08 -07:00
59f89d03d2
phase 17: enrich short parsed articles with Polygon description/keywords from raw payload
2026-04-12 08:52:46 -07:00
cd32c3e3fe
phase 17: increase parser→extractor text limit from 8k to 32k chars
2026-04-12 08:37:29 -07:00
4f2f113cda
phase 17: fix text[]/varchar[] type mismatch in coverage-gaps SQL
2026-04-12 04:15:00 -07:00
d16e15c885
phase 17: quote reserved word 'window' in all SQL queries across recommendation worker and query API
2026-04-12 03:45:51 -07:00
181ed2b6cd
phase 17: quote reserved word 'window' in aggregation SQL INSERT
2026-04-12 03:38:45 -07:00
019eaa40d7
phase 17: fix datetime JSON serialization in aggregation worker market_context
2026-04-12 03:31:32 -07:00
48bf4f7e7e
phase 17: extractor fetches normalized text from MinIO when not in job payload
2026-04-12 03:24:10 -07:00
012b973bb7
phase 17: wire extractor→aggregation→recommendation queue chain, add company_id_map to extractor
2026-04-12 03:16:27 -07:00
e4a1d2d69a
phase 17: fix HTML parser NoneType attrs crash in boilerplate stripping
2026-04-12 03:03:07 -07:00
264b83ea56
phase 17: fix Polygon article_url and published_utc field mapping in metadata persistence
2026-04-12 02:58:30 -07:00
0ac4493bd4
phase 17: fix parser URL lookup from DB and extractor text field name mismatch
2026-04-12 02:54:23 -07:00
67cdb0b8c8
phase 17: fix ruff lint error in scheduler import order
2026-04-12 02:47:47 -07:00
f2b9d6c00a
phase 17: fix scheduler config parsing, worker entry points, and seed data for Polygon sources
2026-04-12 02:45:37 -07:00
5758a704ec
phase 16: fix UUID serialization in symbol registry responses
2026-04-11 19:22:13 -07:00
afa627322a
phase 16: fix ruff lint - move imports to top of file
2026-04-11 16:48:50 -07:00
faccb0b8db
phase 16: React dashboard with full platform control and analytics
2026-04-11 16:19:46 -07:00
109440c91e
phase 15: fix ruff lint errors across services
2026-04-11 12:10:01 -07:00
ce10afa034
phase 14-15: docker build validation and helm deployment
2026-04-11 11:59:45 -07:00
7394d241c9
phase 2: symbol registry validation, seed data, nix dev shell
...
- Enhanced CompanyCreate with ticker format validation (1-10 uppercase letters)
- Enhanced SourceCreate with pydantic validators for source_type, access_policy, config URLs
- Added /health endpoint to symbol registry
- Seed data: 10 companies (AAPL, MSFT, NVDA, AMZN, GOOGL, JPM, JNJ, XOM, TSLA, META)
- Seed sources: Alpha Vantage (market), NewsAPI (news), SEC EDGAR (filings), Alpaca (paper trading)
- Seed watchlist: 'Starter 10' with all companies and aliases
- Added flake.nix dev shell (nixos-25.11) with Python 3.12, ruff, pytest, kubectl, helm
- 30 passing tests, lint clean, Docker build verified
2026-04-11 03:41:41 -07:00
ebea70573b
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
2026-04-11 03:25:08 -07:00
Celes Renata