package phraser import ( "encoding/json" "net/http" "net/http/httptest" "regexp" "strings" "testing" ) // unboundedRepeat finds a `*` or `+` applied to a character class or a group. // // Those are the two forms that let the model generate without limit. A literal // `*` inside a quoted terminal is not one, which is why the pattern anchors on // `]` and `)`. var unboundedRepeat = regexp.MustCompile(`[\]\)]\s*[*+]`) // An unbounded ws rule cost 24-30 seconds a turn (Vikunja #531). The model // opened the JSON object, satisfied `ws ::= [ \t\n]*` with whitespace, and ran // to the 512-token cap doing it — both interactive turns measured on // 2026-08-04 decoded exactly 512 tokens of mostly whitespace. // // The rule this test enforces is stronger than "ws is bounded", on purpose. A // grammar is a budget: every repetition in it is something the model is allowed // to do until the token cap, and the cap is not a design. A new rule with a // bare `*` is the same defect wearing a different name, and it would cost // another QA sitting to find. func TestResponseGrammarHasNoUnboundedRepetition(t *testing.T) { for i, line := range strings.Split(responseGrammar, "\n") { if m := unboundedRepeat.FindString(line); m != "" { t.Errorf("responseGrammar line %d has unbounded repetition %q — bound it, a cap is not a design:\n\t%s", i+1, m, strings.TrimSpace(line)) } } } // The measured bound. 400 was too tight for the string rule and the comment on // responseGrammar records why; {0,4} for whitespace was measured the same way, // three runs stopping cleanly at 33 tokens with no repeat penalty at all. func TestResponseGrammarWhitespaceIsBounded(t *testing.T) { if !strings.Contains(responseGrammar, `ws ::= [ \t\n]{0,4}`) { t.Errorf("the ws rule is not the measured {0,4} bound:\n%s", responseGrammar) } } // The phrasing request must carry a repeat penalty. It is not what fixes #531 — // the bounded grammar is — but chatReq having no such field while // Replier.PhraseReply sent 1.3 is how one phrasing path ran away and the other // did not. Two wire structs disagreeing about the sampler is not a decision // anybody made. func TestPhrasingRequestCarriesARepeatPenalty(t *testing.T) { if phraseRepeatPenalty <= 1.0 { t.Fatalf("phraseRepeatPenalty is %v, which is the server default and no penalty at all", phraseRepeatPenalty) } var got []float64 srv := httptest.NewServer(http.HandlerFunc(func(w http.ResponseWriter, r *http.Request) { var req chatReq if err := json.NewDecoder(r.Body).Decode(&req); err != nil { t.Errorf("decode request: %v", err) } got = append(got, req.RepeatPenalty) w.Header().Set("Content-Type", "application/json") w.Write([]byte(`{"choices":[{"message":{"content":"{\"response\": \"ага\", \"mood\": \"neutral\"}"},"finish_reason":"stop"}]}`)) })) defer srv.Close() // Every path, not just one: the defect was a whole transport missing the // field, so a test that checked a single caller would have passed before // the fix as easily as after it. callAllPhrasingPaths(t, NewLLMPhraserAt(srv.URL, Config{LLMNudges: true})) if len(got) == 0 { t.Fatal("no request captured") } for i, p := range got { if p != phraseRepeatPenalty { t.Errorf("request %d sent repeat_penalty %v, want %v", i, p, phraseRepeatPenalty) } } }