Skip to content

feat: updating imports and llm cut off chunking - #105

Merged
TEJASNARAYANS merged 2 commits into
mainfrom
long-calls
Jul 27, 2026
Merged

feat: updating imports and llm cut off chunking#105
TEJASNARAYANS merged 2 commits into
mainfrom
long-calls

Conversation

@TEJASNARAYANS

@TEJASNARAYANS TEJASNARAYANS commented Jul 22, 2026

Copy link
Copy Markdown
Contributor

What Changed?

Briefly describe what this PR changes.

Why?

Explain the problem this solves and why this approach was chosen.

How to Test?

List clear steps for reviewers to verify the change.

Release Label

Select one semantic version bump intent for this PR:

  • major - breaking change, next release bumps major version
  • minor - backward-compatible feature, next release bumps minor version
  • fix - backward-compatible bug fix, next release bumps patch version
  • No label (defaults to patch release)

If you do not have permission to apply labels, mention the intended release label here and a maintainer will set it.

Checklist

  • I have read the CONTRIBUTING.md guide.
  • My code follows the project's style guidelines.
  • I have added tests that prove my fix is effective or my feature works.
  • I have updated documentation where needed.

@TEJASNARAYANS TEJASNARAYANS added the fix Fix version release label Jul 22, 2026
@greptile-apps

greptile-apps Bot commented Jul 22, 2026

Copy link
Copy Markdown

Greptile Summary

This PR improves call imports and long-form LLM diarisation. The main changes are:

  • Persists details for source rows skipped during CSV and Excel imports.
  • Supports partial imports when some rows have invalid identifiers or recording URLs.
  • Adds model-specific output token budgets and clearer truncation errors.
  • Expands accepted metric description and example lengths.
  • Updates the import details UI and API types for skipped rows.

Confidence Score: 5/5

The updated code appears safe to merge.

  • No new blocking issue qualifies for this follow-up review.
  • Backend skip details are persisted and serialized consistently.
  • Changed imports have compatible module-loading paths.

Important Files Changed

Filename Overview
app/api/v1/routes/call_imports.py Adds structured parse results, row-skip tracking, and partial import support.
app/services/call_imports/bulk_ops.py Persists skipped-row details and marks imports with no usable rows as failed.
app/workers/tasks/helpers/llm_diarisation.py Adds model-specific output budgets and rejects truncated responses.
frontend/src/pages/callImports/CallImportDetail.tsx Displays skipped-row information for partial imports and updates diarisation guidance.
app/models/schemas.py Adds the skipped-row response shape and expands metric text validation limits.

Reviews (2): Last reviewed commit: "feat: updating long test inputs" | Re-trigger Greptile

</div>
)}

{(data.source_row_skips?.length ?? 0) > 0 && data.total_rows > 0 && (

Copy link
Copy Markdown

Choose a reason for hiding this comment

The reason will be displayed to describe this comment to others. Learn more.

P2 All-Skipped Details Stay Hidden

When every source row is skipped, materialization stores the row details but sets total_rows to zero. This condition then hides those details, so the failed import does not show which rows and values need correction.

Suggested change
{(data.source_row_skips?.length ?? 0) > 0 && data.total_rows > 0 && (
{(data.source_row_skips?.length ?? 0) > 0 && (

Note: If this suggestion doesn't match your team's coding style, reply to this and let me know. I'll remember it for next time!

@TEJASNARAYANS
TEJASNARAYANS merged commit 0b06f7e into main Jul 27, 2026
8 checks passed
Sign up for free to join this conversation on GitHub. Already have an account? Sign in to comment

Labels

fix Fix version release

Projects

None yet

Development

Successfully merging this pull request may close these issues.

1 participant