nogueiraguh ab2d0a3e9b fix: embedding reliability - chunking, truncation, progress bar, shared status ...

- Text chunking: max 8000 chars per document, large CSV rows split with context header
- Text truncation: _embed_text truncates at 8000 chars before sending to model (prevents 400 errors)
- Purge before re-embed: deletes old docs by tenancy+date before inserting new ones
- Shared embedding status: file-based status (/data/.embed_status/) instead of in-memory dict (fixes multi-worker visibility)
- Progress bar: shows green (OK) + red (failures) segments, percentage, processed/total count
- Better error logging: extracts readable error message from OCI API errors

2026-03-21 10:48:21 -03:00

..

.dockerignore

feat: comprehensive security, performance, UX and deployment audit

2026-03-20 13:48:30 -03:00

app.py

fix: embedding reliability - chunking, truncation, progress bar, shared status

2026-03-21 10:48:21 -03:00

cis_reports.py

feat: granular CIS MCP server, chat memory compaction, and UX improvements

2026-03-05 08:26:43 -03:00

Dockerfile

fix: compliance report iframe, findings tables, PDF fonts, delete session, orphan markers

2026-03-20 17:17:42 -03:00

gen_tf_reference.py

feat: Terraform resource reference from provider schema, provider alias fixes, and timestamps

2026-03-08 01:00:47 -03:00

mcp_cis_server.py

feat: resource type validation, 100K max tokens, and auto-split improvements

2026-03-09 01:10:33 -03:00

requirements.txt

feat: knowledge base with URL import, ADB case-sensitivity fix, and RAG enhancements

2026-03-11 02:02:31 -03:00