Three QA iterations to convergence (zero issues remaining):
Workbench UI:
- Connection badge: amber "Connected (no auth)" for unauthenticated state
- Theme persistence: restore script in index.html + localStorage sync
- Settings About section: add bottom padding so content isn't clipped
- Clear messages: cancel in-flight requests when clearing chat
- Feature switch labels: proper casing + acronym handling (MCP, LLM)
- Token Cost badge: hidden during loading state
- ARIA: role="switch", aria-checked on toggles, aria-labels on buttons
- ConfigApi: null-safe chaining for getPrompts/getSystemPrompt
Grafana dashboards:
- Auto-refresh 30s on all 3 dashboards
- Panel heights reduced to fit viewport without scrolling
- Anonymous role upgraded to Editor for Explore access
Infrastructure:
- Nginx: DNS resolver with variable-based upstream (prevents crash loop)
- Workbench port set to 3002 in .env
Co-Authored-By: Claude Opus 4.6 (1M context) <noreply@anthropic.com>
Add full pipeline test that generates a real PDF, processes it through
the entire pipeline, and verifies knowledge lands in FalkorDB:
- Create test PDF generator using pdf-lib (2-page doc about Acme Corp)
- Add testFullPipeline() to integration tests with store verification
- Fix FalkorDB client connect() — createClient returns unconnected client
in both TriplesStore and TriplesQuery classes
Results: PDF decoded (2 pages) → chunked (2 chunks) → extracted
(4 relationships) → 16 triples stored in FalkorDB including:
alice-johnson → is-a-senior-engineer → acme-corporation
cloudsync → uses-aws-for-hosting → amazon-web-services
provenance: pages → prov:wasDerivedFrom → source document
Co-Authored-By: Claude Opus 4.6 (1M context) <noreply@anthropic.com>
Two bugs found during end-to-end testing:
1. FlowProcessor never restarted flows when config changed — it only
started them once. Stale NATS JetStream data from previous sessions
caused services to bind to wrong topics. Fix: stop and restart flows
on every config push that includes flow definitions.
2. Gateway publishToTopic sent messages without an id property. Pipeline
FlowProcessor handlers check properties.id and silently return if
missing. Fix: auto-generate a message id when publishing to topics.
Both fixes validated: 13/13 integration tests passing, PDF decoder
correctly receives and processes document messages through the pipeline.
Co-Authored-By: Claude Opus 4.6 (1M context) <noreply@anthropic.com>
Wire up the query and retrieval side of the pipeline so the agent can
answer questions from stored knowledge:
- Triples query service (FalkorDB) — all SPO pattern queries via NATS
- Graph embeddings query service (Qdrant) — entity vector similarity
- Document embeddings query service (Qdrant) — chunk vector similarity
- Graph RAG service — full concept→entity→traverse→score→synthesize pipeline
- Document RAG service — embed→find chunks→synthesize pipeline
- Runner scripts for chunker, extractor, embeddings (missing from Phase 5)
- Add DocumentEmbeddingsRequest/Response schema types
- Add RAG prompt templates (extract-concepts, edge-scoring, synthesize)
- Add graph/doc embeddings query topics to seed config + flow manager
- Add all pipeline/query/retrieval services to docker-compose
- 8 new runner scripts, 8 new pnpm script aliases
Co-Authored-By: Claude Opus 4.6 (1M context) <noreply@anthropic.com>
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>
Marks FlowProcessor and EmbeddingsService constructors as protected
since these classes should only be instantiated via subclasses.
Co-Authored-By: Claude Opus 4.6 (1M context) <noreply@anthropic.com>
* fix: prevent duplicate dispatcher creation race condition in invoke_global_service
Concurrent coroutines could all pass the `if key in self.dispatchers` check
before any of them wrote the result back, because `await dispatcher.start()`
yields to the event loop. This caused multiple Pulsar consumers to be created
on the same shared subscription, distributing responses round-robin and
dropping ~2/3 of them — manifesting as a permanent spinner in the Workbench UI.
Apply a double-checked asyncio.Lock in both `invoke_global_service` and
`invoke_flow_service` so only one dispatcher is ever created per service key.
* test: add concurrent-dispatch tests for race condition fix
Add asyncio.gather-based tests that verify invoke_global_service and
invoke_flow_service create exactly one dispatcher under concurrent calls,
preventing the duplicate Pulsar consumer bug.
Flow Management Service:
- FlowManagerService (AsyncProcessor) handling list/get/start/stop flows
and list/get blueprints via kebab-case wire format
- Default blueprint with all service topic mappings
- Pushes flow config to config service on start/stop
Config Seeding:
- seed-config.ts script pushes prompt templates (extract-relationships,
extract-definitions, document-prompt, kg-prompt) and default flow
definition via gateway REST API
Integration Tests:
- Librarian CRUD: add-document, list-documents, get-content, delete
- Agent query: verifies routing through gateway to agent service
- Skip flags: SKIP_LIBRARIAN=1, SKIP_AGENT=1
Co-Authored-By: Claude Opus 4.6 (1M context) <noreply@anthropic.com>
Multi-stage Containerfile for all Node.js services (single image,
different CMD per docker-compose service). ESM entrypoints for gateway,
config, text-completion, prompt, embeddings, agent, and librarian.
Workbench gets a separate Containerfile (nginx:alpine) with SPA routing
and API/WebSocket proxy to gateway.
Docker Compose updated with 6 app services (gateway, config-service,
text-completion, prompt, embeddings, workbench) using shared
trustgraph-ts:local image.
Co-Authored-By: Claude Opus 4.6 (1M context) <noreply@anthropic.com>
Fix three critical bugs preventing the NATS message pipeline from working:
- FlowProcessor now subscribes to config-push topic (was missing entirely),
using DeliverPolicy.All to replay config on service restart
- NATS streams use wildcard subjects (tg.flow.>) instead of per-topic
narrow filters that caused 503 errors on publish
- Subscriber dispatch loop has exponential backoff on errors to prevent
tight error loops
Add service runner scripts (gateway, config, LLM) and a 7-test
integration suite that verifies config CRUD, WebSocket round-trip,
and full LLM text-completion through the NATS pipeline.
Fix Docker Compose infra: pin Tempo to v2.6.1, remove deprecated Loki
config fields, add user:0 for volume permissions, remap conflicting
ports (FalkorDB 6380, OTLP 4327/4328).
Co-Authored-By: Claude Opus 4.6 (1M context) <noreply@anthropic.com>
Minor fixes from linter: readonly modifiers, unused parameter prefixes,
type narrowing in graph-rag BFS traversal and edge scoring.
Co-Authored-By: Claude Opus 4.6 (1M context) <noreply@anthropic.com>
When --show-provenance is used with tg-show-explain-trace,
display the chunk URI on a Content: line below each Source:
chain. This allows the user to easily fetch the source text
with tg-get-document-content.
Warning generated by librarian responses meant for other
services (chunker, embeddings, etc.) arriving on the shared
response queue. The decoder's subscription picks them up, can't
match them to a pending request, and logs a warning.
Removed the warnings, as not serving a purpose.
Add universal document decoder with multi-format support
using 'unstructured'.
New universal decoder service powered by the unstructured
library, handling DOCX, XLSX, PPTX, HTML, Markdown, CSV, RTF,
ODT, EPUB and more through a single service. Tables are preserved
as HTML markup for better downstream extraction. Images are
stored in the librarian but excluded from the text
pipeline. Configurable section grouping strategies
(whole-document, heading, element-type, count, size) for non-page
formats. Page-based formats (PDF, PPTX, XLSX) are automatically
grouped by page.
All four decoders (PDF, Mistral OCR, Tesseract OCR, universal)
now share the "document-decoder" ident so they are
interchangeable. PDF-only decoders fetch document metadata to
check MIME type and gracefully skip unsupported formats.
Librarian changes: removed MIME type whitelist validation so any
document format can be ingested. Simplified routing so text/plain
goes to text-load and everything else goes to document-load.
Removed dual inline/streaming data paths — documents always use
document_id for content retrieval.
New provenance entity types (tg:Section, tg:Image) and metadata
predicates (tg:elementTypes, tg:tableCount, tg:imageCount) for
richer explainability.
Universal decoder is in its own package (trustgraph-unstructured)
and container image (trustgraph-unstructured).
Page and chunk document IDs were deterministic ({doc_id}/p{num},
{doc_id}/p{num}/c{num}), causing "Document already exists" errors
when reprocessing documents through different flows. Content may
differ between runs due to different parameters or extractors, so
deterministic IDs are incorrect.
Pages now use urn:page:{uuid}, chunks use
urn:chunk:{uuid}. Parent- child relationships are tracked via
librarian metadata and provenance triples.
Also brings Mistral OCR and Tesseract OCR decoders up to parity
with the PDF decoder: librarian fetch/save support, per-page
output with unique IDs, and provenance triple emission. Fixes
Mistral OCR bug where only the first 5 pages were processed.
Embed edge descriptions and compute cosine similarity against grounding
concepts to reduce the number of edges sent to expensive LLM scoring.
Controlled by edge_score_limit parameter (default 30), skipped when edge
count is already below the limit.
Also plumbs edge_score_limit and edge_limit parameters end-to-end:
- CLI args (--edge-score-limit, --edge-limit) in both invoke and service
- Socket client: fix parameter mapping to use hyphenated wire-format keys
- Flow API, message translator, gateway all pass through correctly
- Explainable code path (_question_explainable_api) now forwards all params
- Default edge_score_limit changed from 50 to 30 based on typical subgraph
sizes
