fez5587/momentum-system
1
0 Fork 0
Code Issues 5 Pull Requests Actions Packages Projects Releases Wiki Activity

chore: close the news-scoring outage in the live test record (qwen3:14b from 2026-10-01 22:37 ET)

Browse Source 
Co-Authored-By: Claude Opus 5.5 <noreply@anthropic.com>
Claude-Session: https://claude.ai/code/session_01B3PXXn2tHBzdv6rYtGPz86
This commit is contained in:
momentum devandClaude Opus 5.5 committed 2026-10-01 21:40:30 -05:00
1 parent 6189885aed
commit 082d01e8bd
1 file changed
+3 -2
Download Patch File Download Diff File Expand all files Collapse all files
research/live_test_freeze.json
+3 -2
View File
@@ -86,9 +86,10 @@
"known_deviations": [ "known_deviations": [
{ {
"from": "2026-09-30 ~20:00 ET", "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.", "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."
} }
] ]
} }