Describe the Bug

INFERENCE_JOB_TIMEOUT_SEC does not seem to respect a value more than 10 minutes.

Steps to Reproduce

1)set INFERENCE_JOB_TIMEOUT_SEC to 900 seconds.
2) run inference
3) see inference server log.

Expected Behaviour

Log from karakeep:
2025-11-13T07:27:04.106Z error: [inference][9] inference job failed: Error: Request timed out.
Error: Request timed out.
at OpenAI.makeRequest (file:///app/apps/workers/dist/index.js:61806:46)
at process.processTicksAndRejections (node:internal/process/task_queues:105:5)
at async OpenAIInferenceClient.inferFromText (file:///app/apps/workers/dist/index.js:68941:26)
at async inferTagsFromText (file:///app/apps/workers/dist/index.js:86516:9)
at async inferTags (file:///app/apps/workers/dist/index.js:86523:49)
at async runTagging (file:///app/apps/workers/dist/index.js:86606:15)
at async Object.runOpenAI [as run] (file:///app/apps/workers/dist/index.js:86671:4)
at async Runner.runOnce (file:///app/apps/workers/node_modules/.pnpm/liteque@0.6.2_@opentelemetry+api@1.9.0_@types+better-sqlite3@7.6.13_@types[email protected]_bette_ieiqokhfddhykknqx65h5kqwm4/node_modules/liteque/dist/index.js:261:4)

Log from llamaswap server:
[INFO] Request 127.0.0.1 "GET / HTTP/1.1" 302 26 "curl/7.81.0" 75.677µs
2025/11/13 07:17:03 http: proxy error: context canceled
[WARN] metrics skipped, HTTP status=502, path=/v1/chat/completions
[INFO] Request 192.168.144.3 "POST /v1/chat/completions HTTP/1.1" 502 -1 "OpenAI/JS 4.104.0" 9m59.990315582s
srv cancel_tasks: cancel task, id_task = 3
srv log_server_r: request: POST /v1/chat/completions 127.0.0.1 200
srv params_from_: Chat format: Content-only

Screenshots or Additional Context

timeouts are respected

Device Details

No response

Exact Karakeep Version

v0.28

Have you checked the troubleshooting guide?

• I have checked the troubleshooting guide and I haven't found a solution to my problem