Sharang Parnerkar b96dda11fb fix: live progress + concurrency for embedding builds ...

The embedding build progress was only written to MongoDB after every
batch completed (and the final flush + status update only happened at
the very end), so the dashboard would show "0/N chunks (0%)" for the
entire run, then jump straight to "complete." For a repo with 2k+
chunks this looked like the build was stuck.

Three fixes:
- pipeline: call update_build(Running, embedded_count, ...) after each
  batch so /api/v1/chat/:repo_id/status reflects real progress, and
  flush embeddings to Mongo every 200 records so a partial failure does
  not lose everything.
- pipeline: drive batches with FuturesUnordered at concurrency=4 so
  litellm requests overlap instead of going strictly serial (112
  sequential requests for a 2221-chunk repo were the wall-time floor).
- llm client: give the reqwest client a 300s request timeout and 10s
  connect timeout. Previously LlmClient used reqwest::Client::new()
  with no timeout, so a hung embedding call would block the build
  indefinitely.

Co-Authored-By: Claude Sonnet 4.6 <noreply@anthropic.com>

2026-05-13 11:39:37 +02:00

..

src

fix: live progress + concurrency for embedding builds

2026-05-13 11:39:37 +02:00

tests

feat: add E2E test suite with nightly CI, fix dashboard Dockerfile (#52)

2026-03-30 10:04:07 +00:00

Cargo.toml

fix: CVE notifications during scan + help chat doc loading + Dockerfile (#55)

2026-03-30 13:10:56 +00:00