Skip to content

fix: use Copilot Auto model router and handle empty LLM responses (#91) #253

New issue

Have a question about this project? Sign up for a free GitHub account to open an issue and contact its maintainers and the community.

Sign up for GitHub

By clicking “Sign up for GitHub”, you agree to our terms of service and privacy statement. We’ll occasionally send you account related emails.

Already on GitHub? Sign in to your account

Open
Sanjay Singh (san360) wants to merge 2 commits into
base: main
Choose a base branch
from
+456 −427
Open

fix: use Copilot Auto model router and handle empty LLM responses (#91) #253

Show file tree
Hide file tree
Changes from all commits
Commits
Show all changes
2 commits
Select commit Hold shift + click to select a range
e8bf7ef
fix: use Copilot Auto model router and handle empty LLM responses (#91)
san360 Sep 2, 2026
c7e9130
chore(deps): revert same-day dependency bumps unavailable in internal…
san360 Sep 2, 2026
File filter

Filter by extension

Filter by extension
Conversations
Failed to load comments.
Loading
Jump to
Jump to file
Failed to load files.
Loading
Diff view
Diff view
6 changes: 6 additions & 0 deletions CHANGELOG.md
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -2,6 +2,12 @@

## Unreleased

- Fix "LLM returned invalid JSON after 3 attempts" on all AI features (#91):
model selection now prefers Copilot's built-in "Auto" router so requests are
routed to a model actually enabled for the user's plan/org, instead of a
hardcoded model family that can be selectable yet silently return empty
responses. Empty responses are now detected and reported with an actionable
message instead of being misreported as an "invalid JSON" parse failure
- Fix parse-worker out-of-memory on large log sets (#106): parsing now runs in a
forked child process with a capped heap and streams results back in per-session
chunks using ack-window backpressure to avoid native IPC buffer growth
Expand Down
Loading
Loading