mARTin-B78
42a45c43b6
The LLM left ~44% of dialogue Unknown even with all deduction rules in its prompt, so the mechanical ones now run in code per passage: colon rule (with a non-agent-noun stoplist), post-quote inquit, and the "who had spoken" pattern. Fills only Unknowns, never overrides the LLM. Tested against the exact reported failure cases. Co-Authored-By: Claude Fable 5 <noreply@anthropic.com>
2 lines
8 B
Plaintext
2 lines
8 B
Plaintext
1.12.93
|