fix(ai): use correct llama.cpp model name

- Update model to qwen2.5-coder-32b-instruct-Q4_K_M
- Match actual model available in llama.cpp on port 8081

Co-Authored-By: Claude Haiku 4.5 <noreply@anthropic.com>
This commit is contained in:
2026-10-01 21:59:01 +08:00
co-authored by Claude Haiku 4.5
parent e89ecdd5c4
commit 99eca7d242
4 changed files with 8 additions and 8 deletions
@@ -48,7 +48,7 @@ export async function POST(
let res: Awaited<ReturnType<typeof client.chat.completions.create>>
try {
res = await client.chat.completions.create({
model: 'qwen2.5-coder-8k:latest',
model: 'qwen2.5-coder-32b-instruct-Q4_K_M',
max_tokens: 1024,
messages: [
{
@@ -103,7 +103,7 @@ Output exactly this JSON structure:
}
await withUser(session.sub, async tx => {
await writeAuditLog(tx, 'incidents', id, 'ai_triage_suggest', { suggestion: input, model: 'qwen2.5-coder-8k:latest' })
await writeAuditLog(tx, 'incidents', id, 'ai_triage_suggest', { suggestion: input, model: 'qwen2.5-coder-32b-instruct-Q4_K_M' })
})
return NextResponse.json(input)