llm-multiverse/implementation-plans/_index.md

Implementation Plans Index

Master Table

Issue	Title	Milestone	Status	Language	Plan
#7	Set up proto project structure and build tooling	Phase 1	COMPLETED	Protobuf	issue-007.md
#8	Define common.proto (shared types)	Phase 1	COMPLETED	Protobuf	issue-008.md
#9	Define audit.proto	Phase 1	COMPLETED	Protobuf	issue-009.md
#10	Define secrets.proto	Phase 1	COMPLETED	Protobuf	issue-010.md
#11	Define memory.proto	Phase 1	COMPLETED	Protobuf	issue-011.md
#12	Define model_gateway.proto	Phase 1	COMPLETED	Protobuf	issue-012.md
#13	Define search.proto	Phase 1	COMPLETED	Protobuf	issue-013.md
#14	Define tool_broker.proto	Phase 1	COMPLETED	Protobuf	issue-014.md
#15	Define orchestrator.proto	Phase 1	COMPLETED	Protobuf	issue-015.md
#16	Generate Rust stubs (prost/tonic)	Phase 1	COMPLETED	Rust	issue-016.md
#17	Generate Python stubs (grpcio-tools)	Phase 1	COMPLETED	Python	issue-017.md
#18	Scaffold Audit Service Rust project	Phase 2	COMPLETED	Rust	issue-018.md
#19	Implement append-only file log backend	Phase 2	COMPLETED	Rust	issue-019.md
#20	Implement Append gRPC endpoint	Phase 2	COMPLETED	Rust	issue-020.md
#21	Integration tests for Audit Service	Phase 2	COMPLETED	Rust	issue-021.md
#22	Scaffold Secrets Service Rust project	Phase 3	COMPLETED	Rust	issue-022.md
#23	Implement libsecret / D-Bus backend	Phase 3	COMPLETED	Rust	issue-023.md
#24	Implement kernel keyring fallback	Phase 3	COMPLETED	Rust	issue-024.md
#25	Implement GetSecret gRPC endpoint	Phase 3	COMPLETED	Rust	issue-025.md
#26	Integration tests for Secrets Service	Phase 3	COMPLETED	Rust	issue-026.md
#27	Scaffold Memory Service Rust project	Phase 4	COMPLETED	Rust	issue-027.md
#28	Set up DuckDB schema and VSS extension	Phase 4	COMPLETED	Rust	issue-028.md
#29	Implement embedding generation integration	Phase 4	COMPLETED	Rust	issue-029.md
#30	Implement staged retrieval (coarse-to-fine, 4 stages)	Phase 4	COMPLETED	Rust	issue-030.md
#31	Implement extraction step	Phase 4	COMPLETED	Rust	issue-031.md
#32	Implement semantic cache	Phase 4	COMPLETED	Rust	issue-032.md
#33	Implement provenance tagging and poisoning protection	Phase 4	COMPLETED	Rust	issue-033.md
#114	Tech debt: minor findings from issue #28 review	Phase 4	COMPLETED	Rust	issue-114.md
#116	Tech debt: minor findings from issue #29 review	Phase 4	COMPLETED	Rust	issue-116.md
#118	Tech debt: minor findings from issue #30 review	Phase 4	COMPLETED	Rust	issue-118.md
#120	Tech debt: minor findings from issue #31 review	Phase 4	COMPLETED	Rust	issue-120.md
#122	Tech debt: minor findings from issue #32 review	Phase 4	COMPLETED	Rust	issue-122.md
#126	Tech debt: minor findings from issue #33 review	Phase 4	COMPLETED	Rust	issue-126.md
#34	Implement WriteMemory gRPC endpoint	Phase 4	COMPLETED	Rust	issue-034.md
#35	Implement QueryMemory gRPC endpoint (server-streaming)	Phase 4	COMPLETED	Rust	issue-035.md
#36	Implement GetCorrelated gRPC endpoint	Phase 4	COMPLETED	Rust	issue-036.md
#37	Integration tests for Memory Service	Phase 4	COMPLETED	Rust	issue-037.md
#38	Scaffold Model Gateway Rust project	Phase 5	COMPLETED	Rust	issue-038.md
#39	Implement Ollama HTTP client	Phase 5	COMPLETED	Rust	issue-039.md
#40	Implement model routing logic	Phase 5	COMPLETED	Rust	issue-040.md
#41	Implement StreamInference gRPC endpoint	Phase 5	COMPLETED	Rust	issue-041.md
#42	Implement Inference + GenerateEmbedding endpoints	Phase 5	COMPLETED	Rust	issue-042.md
#43	Integration tests for Model Gateway	Phase 5	COMPLETED	Rust	issue-043.md
#44	Set up SearXNG Docker container	Phase 6	COMPLETED	Docker / YAML	issue-044.md
#45	Scaffold Search Service Python project	Phase 6	COMPLETED	Python	issue-045.md
#46	Implement SearXNG query + snippet filter	Phase 6	COMPLETED	Python	issue-046.md
#47	Implement readability-lxml extraction pipeline	Phase 6	COMPLETED	Python	issue-047.md
#48	Implement summarization step via Model Gateway	Phase 6	COMPLETED	Python	issue-048.md
#49	Implement Search gRPC endpoint	Phase 6	COMPLETED	Python	issue-049.md
#50	Integration tests for Search Service	Phase 6	COMPLETED	Python	issue-050.md

Status Legend

• PLANNED — Plan written, not yet started
• IMPLEMENTING — Currently being implemented
• RETRY — Implementation failed, retry pending
• COMPLETED — Verified and merged
• BLOCKED — Blocked after max retries, needs manual intervention

Service Map

Audit Service

• issue-009.md — audit.proto (AuditService, AuditEntry)
• issue-018.md — Scaffold Audit Service Rust project
• issue-019.md — Append-only file log backend
• issue-020.md — Append gRPC endpoint with validation
• issue-021.md — Integration tests (gRPC client→server)

Secrets Service

• issue-010.md — secrets.proto (SecretsService, GetSecret)
• issue-022.md — Scaffold Secrets Service Rust project
• issue-023.md — libsecret / D-Bus backend (keyring crate)
• issue-024.md — Kernel keyring fallback (linux-keyutils)
• issue-025.md — GetSecret gRPC endpoint with audit logging
• issue-026.md — Integration tests (mock audit, full gRPC flow)

Memory Service

• issue-011.md — memory.proto (MemoryService, MemoryEntry)
• issue-027.md — Scaffold Memory Service Rust project
• issue-028.md — DuckDB schema, VSS extension, HNSW indexes, migrations
• issue-029.md — Embedding generation integration (Model Gateway gRPC client, batch support, DuckDB storage)
• issue-030.md — Staged retrieval pipeline (4-stage coarse-to-fine: HNSW search, description re-rank, corpus re-rank, threshold cutoff)
• issue-031.md — Extraction step (Model Gateway inference for query extraction)
• issue-032.md — Semantic cache (cosine similarity cache with TTL and eviction)
• issue-033.md — Provenance tagging and poisoning protection
• issue-034.md — WriteMemory gRPC endpoint (embedding + provenance + DuckDB storage + audit logging)
• issue-035.md — QueryMemory gRPC endpoint (server-streaming, staged retrieval + extraction + cache)
• issue-036.md — GetCorrelated gRPC endpoint (correlation lookup by memory ID, session, and explicit IDs + audit logging)

Model Gateway

• issue-012.md — model_gateway.proto (ModelGatewayService)
• issue-038.md — Scaffold Model Gateway Rust project
• issue-039.md — Ollama HTTP client (reqwest, streaming, embeddings)
• issue-040.md — Model routing logic (task complexity routing, alias expansion, audit logging)
• issue-041.md — StreamInference gRPC endpoint (server-streaming, Ollama bridge, params mapping)

Search Service

• issue-013.md — search.proto (SearchService)

Tool Broker

• issue-014.md — tool_broker.proto (ToolBrokerService)

Orchestrator

• issue-015.md — orchestrator.proto (OrchestratorService)

Proto Definitions

• issue-007.md — Proto project structure and build tooling
• issue-008.md — Common proto shared types (SessionContext, AgentLineage, AgentType)

Infrastructure / DevOps

• issue-016.md — Rust stub generation (prost/tonic via build.rs)
• issue-017.md — Python stub generation (buf generate)