elpresidank
5e3929a883
fix: comprehensive QA audit — light mode, accessibility, error handling, code quality
...
- Fix light mode: theme-aware graph node labels, remove prose-invert for
theme-safe markdown, add brand/semantic color overrides for light backgrounds
- Add 404 catch-all route redirecting unknown paths to /chat
- FalkorDB: add .catch() to connectPromise, add ensureConnected() to all
store methods (createLiteral, relateNode, relateLiteral, deleteCollection)
- Accessibility: dialog role/aria-modal, toast aria-live, dismiss/zoom/search
button aria-labels, close panel aria-label
- Lazy-load ForceGraph2D (splits 189KB into separate chunk, main bundle -26%)
- Cap conversation localStorage at 200 messages to prevent quota overflow
- Fix pnpm test: add --passWithNoTests to cli/mcp packages
- Add upload error notification instead of silent catch
- Remove unused class-variance-authority dep and dead tabs.tsx component
- Add @types/node to flow package devDependencies
- Remove stale FIXME comment in messages.ts
Co-Authored-By: Claude Opus 4.6 (1M context) <noreply@anthropic.com>
2026-04-07 09:15:59 -05:00
elpresidank
c7eefee607
feat: add Docker entrypoints, LLM providers, pipeline hardening, workbench pages
...
Phase 9 — four parallel workstreams:
- Stream A: 14 Docker entrypoints for containerized deployment
- Stream B: Pipeline hardening — robust JSON parsing, LLM retry logic,
consumer negative-ack, FalkorDB test import fix
- Stream C: Azure OpenAI, OpenAI-compatible, and Mistral LLM providers
- Stream D: Workbench Prompts, Token Cost, Knowledge Cores pages +
Settings feature switches
Co-Authored-By: Claude Opus 4.6 (1M context) <noreply@anthropic.com>
2026-04-07 03:22:55 -05:00
elpresidank
8f7008822a
feat: add document pipeline — PDF decoder, Ollama LLM, storage services
...
Add end-to-end document processing pipeline:
- PDF decoder service (pdfjs-dist) extracts text per page from librarian docs
- Ollama native LLM service for local model inference
- FalkorDB triples store FlowProcessor consumer
- Qdrant graph embeddings store FlowProcessor consumer
- Fix spec name collisions in chunker/extractor (input→chunk-input, etc.)
- Gateway /load endpoint to trigger document processing
- Align flow manager blueprint and seed config with full pipeline topics
- Add runner scripts and test coverage for document load
Co-Authored-By: Claude Opus 4.6 (1M context) <noreply@anthropic.com>
2026-04-06 23:47:43 -05:00
