fix: address tool_result dedup, SDK task ID collision, and doc accuracy

P1: tool_result dedup changed from "first wins" to "last wins"
- claude-client.ts: remove emittedToolResultIds Set, both PostToolUse and
  user message handler emit freely. PostToolUse provides immediate UI feedback;
  user handler's potentially more complete result arrives second.
- route.ts: collectStreamResponse replaces existing contentBlock entry when
  duplicate tool_use_id arrives (last wins for DB persistence).
- ChatView.tsx: onToolResult replaces existing state entry by tool_use_id
  instead of skipping, ensuring most complete result is displayed.

P2: SDK task ID collision risk eliminated
- db.ts: syncSdkTasks now uses full sessionId in task ID
  (`sdk-{fullSessionId}-{index}`) instead of truncated 8-char prefix,
  eliminating cross-session primary key collisions.

P2: Todo ordering stabilized
- db.ts: add sort_order column migration, syncSdkTasks writes array index
  as sort_order. getTasksBySession sorts by sort_order ASC, created_at ASC
  so tasks with identical timestamps maintain insertion order.

P3: Documentation field mapping corrected
- agent-tooling-todo-bridge.md: fix field mapping table — actual implementation
  maps activeForm (not priority) to description column. Updated dedup strategy
  docs from "three-layer skip" to "two-layer last-wins replace".

Lint: fix prefer-const for finalPrompt in claude-client.ts.

Co-Authored-By: Claude Opus 4.6 <noreply@anthropic.com>

src/app/api/chat/route.ts

@@ -272,15 +272,24 @@ async function collectStreamResponse(stream: ReadableStream<string>, sessionId:
             } else if (event.type === 'tool_result') {
               try {
                 const resultData = JSON.parse(event.data);
-                // Dedup: skip if already seen
-                if (!seenToolResultIds.has(resultData.tool_use_id)) {
+                const newBlock = {
+                  type: 'tool_result' as const,
+                  tool_use_id: resultData.tool_use_id,
+                  content: resultData.content,
+                  is_error: resultData.is_error || false,
+                };
+                // Last-wins: if same tool_use_id already exists, replace it
+                // (user handler's result may be more complete than PostToolUse's)
+                if (seenToolResultIds.has(resultData.tool_use_id)) {
+                  const idx = contentBlocks.findIndex(
+                    (b) => b.type === 'tool_result' && 'tool_use_id' in b && b.tool_use_id === resultData.tool_use_id
+                  );
+                  if (idx >= 0) {
+                    contentBlocks[idx] = newBlock;
+                  }
+                } else {
                   seenToolResultIds.add(resultData.tool_use_id);
-                  contentBlocks.push({
-                    type: 'tool_result',
-                    tool_use_id: resultData.tool_use_id,
-                    content: resultData.content,
-                    is_error: resultData.is_error || false,
-                  });
+                  contentBlocks.push(newBlock);
                 }
               } catch {
                 // skip malformed tool_result data