momentum-system

0 Fork 0

Files

T

momentum devandClaude Opus 5.5 eed4ec0b62 fix: catalyst classifier works with qwen3 (OLLAMA_THINK) and no longer hides an empty answer

qwen3 thinks by default. With format=json, Ollama then returns "{}", which the parser
silently read as a confident "other" (sentiment 0, conviction 0), so every headline
scored zero with no error. Two changes:
- OLLAMA_THINK (true/false). It is sent as Ollama's "think" flag only when set, so other
  models are untouched. qwen3:14b needs OLLAMA_THINK=false.
- A JSON object with none of the expected keys is now a failure (None, retried
  next pass), not "other".
Checked through the live code path against qwen3:14b on mason (think=false): 1.4 s per
headline. 5/5 offerings (including an ATM sales agreement and a PIPE) flagged
dilutive. 'Stocks moving' roundups scored no catalyst. Earnings, guidance, analyst,
FDA and contract items were labelled correctly.

Co-Authored-By: Claude Opus 5.5 <noreply@anthropic.com>
Claude-Session: https://claude.ai/code/session_01B3PXXn2tHBzdv6rYtGPz86

2026-10-01 20:59:32 -05:00

integration

Add local-LLM (Ollama) news/catalyst scoring

2026-06-19 17:29:24 +00:00

unit

fix: catalyst classifier works with qwen3 (OLLAMA_THINK) and no longer hides an empty answer

2026-10-01 20:59:32 -05:00

__init__.py

Baseline before Postgres migration (WS0)

2026-06-15 23:39:29 -04:00

conftest.py

Perf: composite (event_type, timestamp) index + test-schema sweep + README