Constrain the phrasing output with a GBNF grammar

The 0.8B answered about one chat turn in three with open reasoning as plain text, so no JSON ever closed and the fallback shipped "Thinking Process:" to the user. A grammar makes that output impossible.

Co-Authored-By: Claude Opus 5 <noreply@anthropic.com>
Claude-Session: https://claude.ai/code/session_01CGeSZxh1DCtRxmFVSYVGvJ

internal/phraser/llmphraser.go

@@ -45,6 +45,13 @@ type Config struct {
 	// address him, the time) fresh for each turn. See internal/persona.
 	// nil ⇒ no block, the prompts stand alone.
 	ContextBlock func() string
+
+	// NoGrammar turns the GBNF constraint off (zero value ⇒ grammar ON).
+	// The escape hatch exists because the target resident model — the
+	// locally CPT'd Qwen3-1.7B — does not exist yet: if its chat template
+	// ever fights the grammar, the fix should be a config flip on the
+	// deploy box, not a code change and a rebuild.
+	NoGrammar bool
 }
 
 func DefaultConfig(modelPath string) Config {
@@ -290,6 +297,7 @@ func (p *LLMPhraser) chatWithMessages(ctx context.Context, msgs []chatMsg, maxTo
 		Messages:    msgs,
 		Temperature: 0.7,
 		MaxTokens:   maxTokens,
+		Grammar:     p.grammar(),
 	}
 	body, err := json.Marshal(req)
 	if err != nil {
@@ -369,6 +377,37 @@ type chatReq struct {
 	Messages    []chatMsg `json:"messages"`
 	Temperature float64   `json:"temperature"`
 	MaxTokens   int       `json:"max_tokens"`
+	// Grammar is llama-server's `grammar` field (GBNF). Same wiring as
+	// internal/llm.Req.Grammar. Empty ⇒ unconstrained sampling.
+	Grammar string `json:"grammar,omitempty"`
+}
+
+// responseGrammar — GBNF constraining the model to the documented phrasing
+// contract and nothing else: {"response": "<text>", "mood": "<enum>"}.
+//
+// Without it a 0.8B answers roughly one chat turn in three with open reasoning
+// as plain text ("Thinking Process:" …), which no tag-stripper can remove and
+// which eats the token budget before the JSON closes. Modelled on
+// routeGrammar in internal/router/llmrouter.go so the two read alike.
+//
+// text accepts ANY codepoint except the two JSON must escape — the replies are
+// Russian, so an ASCII-only rule would make every reply empty. The escape rule
+// is what lets the model close a string it opened with a quote inside. Length
+// is bounded so a repetition loop truncates the field, not the JSON object.
+const responseGrammar = `
+root   ::= "{" ws "\"response\"" ws ":" ws string ws "," ws "\"mood\"" ws ":" ws mood ws "}"
+mood   ::= "\"neutral\"" | "\"happy\"" | "\"thinking\"" | "\"tired\"" | "\"confused\""
+string ::= "\"" ([^"\\] | "\\" ["\\/bfnrt]){0,400} "\""
+ws     ::= [ \t\n]*
+`
+
+// grammar returns the GBNF to attach to a phrasing request, or "" when the
+// operator turned it off.
+func (p *LLMPhraser) grammar() string {
+	if p.cfg.NoGrammar {
+		return ""
+	}
+	return responseGrammar
 }
 
 type chatResp struct {
@@ -393,6 +432,7 @@ func (p *LLMPhraser) chatWithSystem(ctx context.Context, system, user string, ma
 		},
 		Temperature: 0.7,
 		MaxTokens:   maxTokens,
+		Grammar:     p.grammar(),
 	}
 	body, err := json.Marshal(req)
 	if err != nil {