From 082d01e8bdf02ddafbfd9b9e50f059fac4a50fc7 Mon Sep 17 00:00:00 2001 From: momentum dev Date: Thu, 1 Oct 2026 21:40:30 -0500 Subject: [PATCH] chore: close the news-scoring outage in the live test record (qwen3:14b from 2026-10-01 22:37 ET) Co-Authored-By: Claude Opus 5.5 Claude-Session: https://claude.ai/code/session_01B3PXXn2tHBzdv6rYtGPz86 --- research/live_test_freeze.json | 5 +++-- 1 file changed, 3 insertions(+), 2 deletions(-) diff --git a/research/live_test_freeze.json b/research/live_test_freeze.json index 6b5bf55..8d0c997 100644 --- a/research/live_test_freeze.json +++ b/research/live_test_freeze.json @@ -86,9 +86,10 @@ "known_deviations": [ { "from": "2026-09-30 ~20:00 ET", - "to": null, + "to": "2026-10-01 22:37 ET", "what": "TrueNAS ollama2 app turned off by the owner (host was out of memory: 843 MiB free of 15 GiB; tools:latest held 7.8 GB at a 131k context). Settings unchanged, but the LLM catalyst score (NEWS_CATALYST_SCORE_ENABLED) returns nothing while it is off, so the rank boost is inert. The dilution veto falls back to its regex floor.", - "restore": "Owner chose qwen3:14b on mason instead of re-enabling TrueNAS Ollama (2026-10-01). config_overrides set OLLAMA_HOST=http://192.168.1.178:11434, OLLAMA_MODEL=qwen3:14b, OLLAMA_THINK=false (needs image >= eed4ec0). Takes effect at the next live-stack restart; set 'to' to that time. The scoring model is then qwen3:14b, not the frozen tools:latest. That is a known, recorded change to the news-scoring input." + "restore": "Owner chose qwen3:14b on mason instead of re-enabling TrueNAS Ollama (2026-10-01). config_overrides set OLLAMA_HOST=http://192.168.1.178:11434, OLLAMA_MODEL=qwen3:14b, OLLAMA_THINK=false (needs image >= eed4ec0). Takes effect at the next live-stack restart; set 'to' to that time. The scoring model is then qwen3:14b, not the frozen tools:latest. That is a known, recorded change to the news-scoring input.", + "outcome": "News scoring restored with qwen3:14b on mason (OLLAMA_THINK=false, image 4361f80). The first restart (22:22) ran the OLD image (TrueNAS had not pulled), and 320 empty-answer rows were cached as 'other'; they were deleted after the container was recreated at 22:36. From 22:37 the scorer is qwen3:14b, not the frozen tools:latest; known weakness: reactive articles and halt-up notices can score as bullish catalysts." } ] }