docs: the reply contract has one parser and no legacy shape (V-397)

2026-08-06 01:27:35 +04:00
parent 968477ea59
commit ed0331c774
1 changed files with 8 additions and 3 deletions
@@ -263,9 +263,14 @@ the cascade rather than transitioning the wrong item.
 ## LLM output contract
-All phrasing paths emit `{"response":"...","mood":"..."}` (parsed in `replier_llm.go` and
+All phrasing paths emit `{"response":"...","mood":"..."}`, with fallback to plain text when
-`internal/phraser/llmphraser.go`), with fallback to plain text and the legacy
+the model skips the JSON. **One parser, `parseResponseMood` in
-`{"body","summary"}`. Mood is a fixed enum. Router prompt is a separate contract:
+`internal/phraser/parse.go`**, and every path reaches it: the six `LLMPhraser` methods,
 `PhraseWorld`, and `Replier.PhraseReply`, which `cmd/mavend/replier_llm.go` wraps — that file
 holds the stub fallback and no parsing of its own. The legacy `{"body","summary"}` fallback
 was deleted on 2026-08-06 (V-397): it was the contract before `{"response","mood"}` replaced
 it, no prompt asks for that shape, the GBNF cannot emit it, and no test covered it.
 Mood is a fixed enum. Router prompt is a separate contract:
 `[{"intent":<enum>, key?, value?, text?, verb?}, ...]`, 7 intents (`fact, reminder,
 note, query, act, chat, system`). `llm/check_prompt_parity.py` in the training
 workspace enforces that the Go and relabelling prompts remain identical.