elpresidank
|
25d4227cb5
|
fix: resolve FlowProcessor topic collisions, librarian timeout, tests
Fix critical bug where all FlowProcessor services shared the same spec
names ("request"/"response"), causing them to steal each other's NATS
topics. Now each service uses unique spec names matching the flow config
topic keys (e.g., "text-completion-request", "prompt-request",
"agent-request").
Fix librarian NATS consumer timeout (500ms → 2000ms, below NATS minimum).
Update seed-config and test-pipeline with correct flow topic mappings.
Add prompt template runner script.
Smoke test results: 11/11 passing (config CRUD, WebSocket, LLM,
librarian CRUD). Agent routing verified via manual curl test.
Co-Authored-By: Claude Opus 4.6 (1M context) <noreply@anthropic.com>
|
2026-04-06 01:02:10 -05:00 |
|
elpresidank
|
f09ef4de45
|
feat: add document pipeline, ReAct agent, and knowledge core services
Document Pipeline (Team A):
- LibrarianService: document storage with filesystem backend, metadata
persistence, child document hierarchy, collection management
- ChunkingService: recursive character text splitter with configurable
chunk size/overlap, FlowProcessor pattern
- KnowledgeExtractService: combined relationship + definition extraction
using prompt service and LLM, emits RDF triples and entity contexts
- KnowledgeCoreService: knowledge core CRUD with streaming export and
flow-based loading
ReAct Agent (Team B):
- StreamingReActParser: state machine for parsing LLM output into
Thought/Action/ActionInput/FinalAnswer sections
- Three MVP tools: KnowledgeQuery (GraphRAG), DocumentQuery (DocRAG),
TriplesQuery with RequestResponse clients
- AgentService FlowProcessor with ReAct loop, tool execution, and
streaming chunk responses (thought/observation/answer)
Co-Authored-By: Claude Opus 4.6 (1M context) <noreply@anthropic.com>
|
2026-04-06 00:19:37 -05:00 |
|