RafaelRuiz
/
assistance-engine
1
1
Fork 0
Code Issues Pull Requests Packages Projects Releases Wiki Activity

[DOC] ADR-0008 RC-03: add prior probability rationale 

Co-Authored-By: Claude Sonnet 4.6 <noreply@anthropic.com>
This commit is contained in:
rafa-ruiz 2026-04-09 19:56:28 -07:00
parent 4b9e1ff4ca
commit ce2306c4e5
1 changed files with 2 additions and 0 deletions
Show Stats Download Patch File Download Diff File Expand all files Collapse all files

2
docs/ADR/ADR-0008-adaptive-query-routing-intent-history.md
View File

@ -114,6 +114,8 @@ classify(q, history) ≠ f(dominant_type(history))
classify(q, history) = f(intent(q), resolve_references(q, history))
```
**Rationale:** Small LLMs implicitly compute `P(type | history)` instead of `P(type | message_content)`. The distribution of previous intents must not influence the prior probability of the current classification. Each message is an independent classification event — a session with 10 `RETRIEVAL` turns does not make the next message more likely to be `RETRIEVAL`. The `<history_rule>` in the classifier prompt enforces this explicitly.
### RC-04 — RAG bypass (priority: medium)
Query types that bypass Elasticsearch retrieval: