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> |
||
|---|---|---|
| .. | ||
| js | ||
| sections | ||
| vendor | ||
| icon.svg | ||
| index.html | ||
| loader.js | ||
| manifest.webmanifest | ||
| nav.js | ||
| style.css | ||
| sw.js | ||
