danvics/pediatric-ai-scribe-v3
1
0
Fork 0
Code Issues Pull requests Projects Releases 14 Packages Wiki Activity Actions

Fix JSON parse for Sonnet 4.6: escape literal newlines in strings

Browse source 
Sonnet 4.6 outputs literal newline characters inside JSON string
values (e.g. in HTML body field) instead of \n escape sequences.
Added sanitizeJsonString that walks the string character by character
and escapes unescaped control chars inside quoted values.
This commit is contained in:
Daniel Onyejesi 2026-03-24 19:01:16 -04:00
parent 4b62d073f7
commit 5e3c95d163
1 changed files with 32 additions and 10 deletions
Show stats Download patch file Download diff file Expand all files Collapse all files

42
src/routes/learningAI.js
View file

@ -242,22 +242,44 @@ router.post('/ai-generate', upload.single('file'), async function(req, res) {
var lastBrace = raw.lastIndexOf('}');
if (lastBrace !== -1 && lastBrace < raw.length - 1) raw = raw.substring(0, lastBrace + 1);
// Fix unescaped control characters inside JSON string values.
// Models sometimes output literal newlines/tabs inside strings instead of \n \t.
function sanitizeJsonString(s) {
var inStr = false, escaped = false, out = '';
for (var i = 0; i < s.length; i++) {
var c = s[i];
if (escaped) { out += c; escaped = false; continue; }
if (c === '\\' && inStr) { out += c; escaped = true; continue; }
if (c === '"') { inStr = !inStr; out += c; continue; }
if (inStr && c === '\n') { out += '\\n'; continue; }
if (inStr && c === '\r') { continue; }
if (inStr && c === '\t') { out += '\\t'; continue; }
out += c;
}
return out;
}
var parsed;
try {
parsed = JSON.parse(raw);
} catch (e) {
// Try extracting from first { to last }
var firstBrace = raw.indexOf('{');
var extractedJson = firstBrace >= 0 ? raw.substring(firstBrace, lastBrace + 1) : null;
if (extractedJson) {
try { parsed = JSON.parse(extractedJson); }
catch (e2) {
console.error('[LearningAI] JSON parse failed. Raw (first 500):', raw.substring(0, 500));
console.error('[LearningAI] Direct parse failed:', e.message, '| Pos:', e.message.match(/position (\d+)/)?.[1], '| Char context:', raw.substring(parseInt(e.message.match(/position (\d+)/)?.[1] || 0) - 40, parseInt(e.message.match(/position (\d+)/)?.[1] || 0) + 40));
// Attempt 2: sanitize control chars and retry
try { parsed = JSON.parse(sanitizeJsonString(raw)); }
catch (e2) {
// Attempt 3: extract first { to last }
var firstBrace = raw.indexOf('{');
var extractedJson = firstBrace >= 0 ? raw.substring(firstBrace, lastBrace + 1) : null;
if (extractedJson) {
try { parsed = JSON.parse(sanitizeJsonString(extractedJson)); }
catch (e3) {
console.error('[LearningAI] All parse attempts failed:', e3.message);
return res.status(500).json({ error: 'AI returned invalid JSON. Try again.' });
}
} else {
console.error('[LearningAI] No JSON braces found');
return res.status(500).json({ error: 'AI returned invalid JSON. Try again.' });
}
} else {
console.error('[LearningAI] No JSON found. Raw (first 500):', raw.substring(0, 500));
return res.status(500).json({ error: 'AI returned invalid JSON. Try again.' });
}
}