Alan-Jowett / CoPilot-For-Consensus / 20290803884 / 22
78%
main: 78%

DEFAULT BRANCH: main
Ran
Files 2
Run time 0s
Badge
Embed ▾
README BADGES
x

If you need to use a raster PNG badge, change the '.svg' to '.png' in the link

Markdown

Textile

RDoc

HTML

Rst
coverage: 80.297%. Remained the same
20290803884.22

push

github

web-flow 
fix: Generate citations from chunks instead of LLM output (#366)

* fix: Generate citations from chunks instead of LLM output (#365)

All production summarizers (LocalLLM, OpenAI, LlamaCpp) return empty
citations arrays. This fix generates citations from the actual chunks
passed as context to the LLM, ensuring citations reference real source
material and preventing hallucination.

Changes:
- Modified summarization/app/service.py to create Citation objects from
  all chunks in context before formatting citations
- Citations now include message_id, chunk_id, offset from actual chunks

Fixes #365

Signed-off-by: GitHub Copilot <copilot@github.com>

* test: Add coverage for citation generation from chunks

Addresses PR feedback from Copilot reviewer. Added comprehensive test
that verifies citations are generated from chunks in context, not from
LLM output (which may be empty or hallucinated).

Test validates:
- Citations are created from all chunks used as context
- LLM-returned citations are ignored
- Each citation has required fields (message_id, chunk_id, offset, text)
- Citations reference actual messages from context
- No hallucinated citations are included

Related to #365

Signed-off-by: GitHub Copilot <copilot@github.com>

---------

Signed-off-by: GitHub Copilot <copilot@github.com>
Co-authored-by: GitHub Copilot <copilot@github.com>

216 of 269 relevant lines covered (80.3%)

0.8 hits per line

Source Files on job ingestion - 20290803884.22