feat: make LLM call timeout configurable via MEMORIX_LLM_TIMEOUT_MS#59
Draft
feat: make LLM call timeout configurable via MEMORIX_LLM_TIMEOUT_MS#59
Conversation
…nv var Agent-Logs-Url: https://github.com/AVIDS2/memorix/sessions/0113662d-5917-4d0f-a48c-cca88f51bb5f Co-authored-by: AVIDS2 <172191005+AVIDS2@users.noreply.github.com>
Copilot
AI
changed the title
[WIP] Handle pull request processing
feat: make LLM call timeout configurable via MEMORIX_LLM_TIMEOUT_MS
Apr 6, 2026
AVIDS2
approved these changes
Apr 8, 2026
Owner
AVIDS2
left a comment
AVIDS2
left a comment
There was a problem hiding this comment.
This looks like the stronger of the two timeout PRs. The env-var approach is narrow, safe, and importantly it validates invalid/non-positive values instead of letting configuration mistakes break the LLM path. This does not solve the full timeout family from #57 yet, but as a focused first step this change is acceptable.
Owner
|
We carried forward #58, which now covers this timeout direction more completely (validation, tests, and issue linkage). So from the maintainer side, I’m treating this PR as superseded rather than the primary path forward. If you want, we can close this one to keep the timeout workstream tidy. |
This file contains hidden or bidirectional Unicode text that may be interpreted or compiled differently than what appears below. To review, open the file in an editor that reveals hidden Unicode characters.
Learn more about bidirectional Unicode characters
Sign up for free
to join this conversation on GitHub.
Already have an account?
Sign in to comment
Add this suggestion to a batch that can be applied as a single commit.This suggestion is invalid because no changes were made to the code.Suggestions cannot be applied while the pull request is closed.Suggestions cannot be applied while viewing a subset of changes.Only one suggestion per line can be applied in a batch.Add this suggestion to a batch that can be applied as a single commit.Applying suggestions on deleted lines is not supported.You must change the existing code in this line in order to create a valid suggestion.Outdated suggestions cannot be applied.This suggestion has been applied or marked resolved.Suggestions cannot be applied from pending reviews.Suggestions cannot be applied on multi-line comments.Suggestions cannot be applied while the pull request is queued to merge.Suggestion cannot be applied right now. Please check back later.
The hardcoded 12s LLM timeout is too short for providers behind proxy chains (e.g., CLIProxyAPI → Chutes/Fireworks), causing every call to fall back to heuristic and effectively disabling LLM-enhanced mode.
Changes
src/llm/provider.ts: ReplaceLLM_CALL_TIMEOUT_MS = 12_000with a value read fromMEMORIX_LLM_TIMEOUT_MSenv var, defaulting to 30s. Invalid/non-positive values fall back to the default.