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
527be42f82
phase 17: restore script — per-bucket size reporting, full DB row count verification
2026-04-12 14:53:19 -07:00
85e0ef7580
phase 17: backup script now reports per-bucket sizes and file counts
2026-04-12 14:46:47 -07:00
dd13045ca6
phase 17: fix backup/restore scripts — use postgres:18-alpine for pg_dump version match
2026-04-12 14:41:08 -07:00
3f5b4adcec
phase 17: add backup/restore scripts — PostgreSQL + MinIO → NFS
2026-04-12 14:21:59 -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
fd35e12d5e
phase 17: switch Ollama to external proxy at 10.1.1.12:2701
2026-04-12 11:37:23 -07:00
80e0f0976f
phase 17: switch back to qwen3.5:9b-fast (Ollama restarted, model available again)
2026-04-12 11:05:42 -07:00
a3e8009fa9
phase 17: revert to qwen3.5:9b (9b-fast was removed from Ollama), add retry script
2026-04-12 10:58:53 -07:00
109a2485cf
phase 17: increase Ollama timeout to 300s for qwen3.5:9b-fast 32k context
2026-04-12 10:32:13 -07:00
7ee1d0f050
phase 17: switch to qwen3.5:9b-fast (32k context), add queue management scripts
2026-04-12 10:19:28 -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
608ccc8b68
phase 17: revert to qwen3.5:9b, keep improved prompt style
2026-04-12 10:06:13 -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
ffcc66ae0b
phase 17: sync standalone k8s/trino.yaml with Helm template (native S3, s3.region)
2026-04-12 08:24:04 -07:00
34787ad825
phase 17: fix Trino hive catalog — use native S3 filesystem, remove defunct hive.s3 props
2026-04-12 08:18:18 -07:00
999648d90b
phase 17: add s3.region to Trino catalog config for MinIO (fixes AWS SDK region error)
2026-04-12 08:16:14 -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
226cc3ff44
phase 17: switch Ollama model to qwen3.5:9b (available on cluster)
2026-04-12 03:10:49 -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
1410d324b7
phase 17: add vertical slice tasks for live pipeline activation
2026-04-11 20:43:47 -07:00
37d5f9b01c
update steering docs and hooks for current project state
2026-04-11 20:41:57 -07:00
99e17be282
phase 16: fix env var fallback - use || instead of ?? for empty string
2026-04-11 20:06:13 -07:00
4d0c38bba7
phase 16: vitest + MSW frontend tests, CI integration
2026-04-11 19:28:38 -07:00
5758a704ec
phase 16: fix UUID serialization in symbol registry responses
2026-04-11 19:22:13 -07:00
6f5b2231a2
phase 16: add registry/risk nginx proxies, add company form, network policies
2026-04-11 19:12:07 -07:00
4cd8961db6
phase 16: add dashboard network policy, allow query-api from dashboard
2026-04-11 18:20:48 -07:00
cc7014e33d
phase 16: fix superset - trino driver in venv, psycopg2 metadata db, core secrets
2026-04-11 17:37:39 -07:00
5f87cbe464
phase 16: custom superset image with trino driver, fix security context
2026-04-11 17:18:17 -07:00
afa627322a
phase 16: fix ruff lint - move imports to top of file
2026-04-11 16:48:50 -07:00
59da3fe89e
phase 16: nginx-unprivileged on 8080, helm dashboard deployment
2026-04-11 16:37:59 -07:00
Celes Renata