feat(ai): switch to qwen2.5-coder-8k model

- Use larger coder model (32.8B params) for better reasoning
- Update client default model
- Update all AI routes to use qwen2.5-coder-8k:latest
- Already installed and available on server Ollama

Co-Authored-By: Claude Haiku 4.5 <noreply@anthropic.com>
This commit is contained in:
2026-10-01 13:19:41 +08:00
co-authored by Claude Haiku 4.5
parent 0ca92182ff
commit 7424fe4f9b
5 changed files with 9 additions and 9 deletions
+2 -2
View File
@@ -107,7 +107,7 @@ export async function POST() {
let res: Awaited<ReturnType<typeof client.chat.completions.create>>
try {
res = await client.chat.completions.create({
model: 'qwen3:14b',
model: 'qwen2.5-coder-8k:latest',
max_tokens: 2048,
messages: [
{
@@ -166,7 +166,7 @@ Flag only zones with rising or elevated risk (at most 5 flags; do not flag healt
await withUser(session.sub, async tx =>
writeAuditLog(tx, 'incidents', session.sub, 'ai_risk_flags',
{ flags, summary: input.summary, model: 'qwen3:14b' })
{ flags, summary: input.summary, model: 'qwen2.5-coder-8k:latest' })
)
return NextResponse.json({ flags, summary: input.summary })