fix chat: force synthesis pass + fix ambiguous-column trigger

Two bugs combined to make the chat reply with only cards and no prose:

1. SQL trigger rollup_session_stats was failing with "column reference
   total_cost_usd is ambiguous" because the UPDATE on public.profiles had
   a FROM public.chat_sessions clause and both tables expose that column.
   Persistence of every user message died at this point — sessions were
   created in the DB but had message_count=0 forever. Applied SQL fix
   that qualifies columns with p./s. aliases (production DB updated;
   ALTER FUNCTION run live, not yet codified in a migration file).

2. The free-tier model (nemotron-3-super:free) spent all 5 tool-loop
   turns on hybrid_search calls and never wrote any prose, returning
   content_len=0. Added a forced-synthesis pass in openrouter.ts: when
   the loop exits with empty assembledText but the model did call tools,
   we send ONE final turn with tools omitted from the request payload
   and a user message instructing the model to answer in 3-8 sentences
   citing chunks. openrouterStreamCall now accepts a `withTools` opt
   so the synthesis call can disable tool calling entirely.

Verified end-to-end with the actual user query "O que os astronautas
viram? Quem foi que viu?" on /d/nasa-uap-d6-apollo-17-...:
- content_len: 0 → 947 chars (real synthesis citing Schmitt)
- artifacts: 44 preserved
- assistant message persisted with tool_calls + citations columns

web/app/api/sessions/[id]/messages/route.ts

@@ -128,34 +128,55 @@ Quotes verbatim do documento mantêm idioma original (inglês), narração ao re
 
 export async function POST(request: Request, ctx: { params: Promise<{ id: string }> }) {
   const { id: sessionId } = await ctx.params;
+  const t0 = Date.now();
+  const log = (stage: string, extra: Record<string, unknown> = {}) =>
+    console.log(`[chat ${sessionId.slice(0, 8)}] ${stage}`, { dt: Date.now() - t0, ...extra });
+  log("POST received");
 
   if (!isSupabaseConfigured()) {
+    log("auth_disabled");
     return NextResponse.json({ error: "auth_disabled" }, { status: 503 });
   }
   const supabase = await createClient();
-  const { data: { user } } = await supabase.auth.getUser();
-  if (!user) return NextResponse.json({ error: "unauthenticated" }, { status: 401 });
+  const { data: { user }, error: authError } = await supabase.auth.getUser();
+  if (!user) {
+    log("unauthenticated", { authError: authError?.message });
+    return NextResponse.json({ error: "unauthenticated" }, { status: 401 });
+  }
+  log("user resolved", { user_id: user.id, email: user.email });
 
   const body = (await request.json().catch(() => ({}))) as { content: string };
   if (!body.content?.trim()) {
+    log("empty_message", { received: body });
     return NextResponse.json({ error: "empty_message" }, { status: 400 });
   }
+  log("body parsed", { content_len: body.content.length });
 
-  const { data: session } = await supabase
+  const { data: session, error: sessErr } = await supabase
     .from("chat_sessions").select("*").eq("id", sessionId).maybeSingle();
-  if (!session) return NextResponse.json({ error: "not_found" }, { status: 404 });
+  if (!session) {
+    log("session_not_found", { sessErr: sessErr?.message });
+    return NextResponse.json({ error: "not_found" }, { status: 404 });
+  }
+  log("session ok", { context_doc_id: session.context_doc_id });
 
-  const { data: budgetOk } = await supabase.rpc("check_budget", { p_user_id: user.id });
+  const { data: budgetOk, error: budgetErr } = await supabase.rpc("check_budget", { p_user_id: user.id });
+  log("budget checked", { budgetOk, budgetErr: budgetErr?.message });
   if (budgetOk === false) {
     return NextResponse.json({ error: "budget_exceeded" }, { status: 429 });
   }
 
   // Persist the user message before streaming
-  await supabase.from("messages").insert({
+  const { error: userInsertErr } = await supabase.from("messages").insert({
     session_id: sessionId,
     role: "user",
     content: body.content,
   });
+  if (userInsertErr) {
+    log("user_msg insert FAILED", { error: userInsertErr.message });
+    return NextResponse.json({ error: "persist_failed", message: userInsertErr.message }, { status: 500 });
+  }
+  log("user_msg persisted");
 
   const context = await gatherContext(session.context_doc_id, session.context_page_id);
 
@@ -186,7 +207,13 @@ export async function POST(request: Request, ctx: { params: Promise<{ id: string
   // Persist the final assistant message AFTER the stream completes.
   // Note: this runs concurrently with the response — it does NOT block.
   done.then(async (result) => {
-    await supabase.from("messages").insert({
+    log("stream done", {
+      content_len: result.content.length,
+      tool_calls: result.toolCalls.length,
+      artifacts: result.artifacts?.length ?? 0,
+      tokens: `${result.tokensIn}/${result.tokensOut}`,
+    });
+    const { error: insertErr } = await supabase.from("messages").insert({
       session_id: sessionId,
       role: "assistant",
       content: result.content,
@@ -197,8 +224,10 @@ export async function POST(request: Request, ctx: { params: Promise<{ id: string
       tool_calls: result.toolCalls.length > 0 ? result.toolCalls : null,
       citations: result.artifacts && result.artifacts.length > 0 ? result.artifacts : null,
     });
+    if (insertErr) log("assistant insert FAILED", { error: insertErr.message });
+    else log("assistant persisted");
   }).catch((e) => {
-    console.error("[chat] persist failed:", e);
+    log("STREAM ERROR", { error: e instanceof Error ? e.message : String(e) });
   });
 
   return new Response(stream, {

web/lib/chat/openrouter.ts

@@ -245,6 +245,35 @@ export async function streamWithTools(
     break;
   }
 
+  // Forced synthesis: free-tier models often exhaust the tool-call budget
+  // without ever producing prose, returning content_len=0. If the loop ended
+  // with empty text but the model did call tools, force ONE more turn without
+  // tools so the model must answer in plain text.
+  if (!assembledText.trim() && toolTrace.length > 0) {
+    cb.emit({
+      type: "text_delta",
+      delta: "",
+    });
+    messages.push({
+      role: "user",
+      content:
+        "Com base nas ferramentas que você acabou de chamar e nos resultados acima, " +
+        "responda agora ao usuário EM TEXTO (3-8 frases), em português brasileiro. " +
+        "Cite os chunks no formato [[doc-id/p007#c0042]]. Não chame mais nenhuma ferramenta.",
+    });
+    try {
+      const res = await openrouterStreamCall(messages, modelUsed, { withTools: false });
+      if (res.body) {
+        const final = await readSSE(res.body, cb);
+        assembledText += final.roundText;
+        totalIn += final.usage?.prompt_tokens ?? 0;
+        totalOut += final.usage?.completion_tokens ?? 0;
+      }
+    } catch (e) {
+      cb.emit({ type: "error", message: `synthesis failed: ${e instanceof Error ? e.message : String(e)}` });
+    }
+  }
+
   return {
     content: assembledText,
     model: modelUsed,
@@ -255,15 +284,22 @@ export async function streamWithTools(
   };
 }
 
-async function openrouterStreamCall(messages: OAMsg[], model: string): Promise<Response> {
-  const body = {
+async function openrouterStreamCall(
+  messages: OAMsg[],
+  model: string,
+  opts: { withTools?: boolean } = {},
+): Promise<Response> {
+  const withTools = opts.withTools !== false;
+  const body: Record<string, unknown> = {
     model,
     messages,
-    tools: TOOL_DEFINITIONS,
-    tool_choice: "auto",
     stream: true,
     max_tokens: 1024,
   };
+  if (withTools) {
+    body.tools = TOOL_DEFINITIONS;
+    body.tool_choice = "auto";
+  }
   const res = await fetch(ENDPOINT, {
     method: "POST",
     headers: headers(),