Celes Renata 6880f11c26 fix: add /no_think inline tag to disable Qwen3 thinking mode ...

chat_template_kwargs isn't being respected by the vLLM deployment.
Qwen3 models support /no_think as an inline suffix in the user message
to disable thinking mode. This is the most reliable method across all
serving backends (vLLM, Ollama, SGLang).

2026-04-29 16:11:44 +00:00

..

__init__.py

phase 0+1: project scaffold, k8s manifests, CI pipeline, steering, hooks, tests

2026-04-11 03:25:08 -07:00

eligibility.py

feat: signal math upgrade — probabilistic, regime-aware scoring pipeline

2026-04-29 11:41:48 +00:00

main.py

fix: pipeline stop now halts all workers and flushes queues

2026-04-29 07:59:35 +00:00

suppression.py

feat: competitive intelligence & historical pattern matching layer

2026-04-14 19:42:48 +00:00

thesis_llm.py

fix: add /no_think inline tag to disable Qwen3 thinking mode

2026-04-29 16:11:44 +00:00

worker.py

feat: signal math upgrade — probabilistic, regime-aware scoring pipeline

2026-04-29 11:41:48 +00:00