Implementation Phases
All 7 phases are complete — 46 stories across 7 epics.
Phase Summary
| Phase | Stories | Lines Changed | Key Deliverables |
|---|---|---|---|
| 0: Architecture Spike | 4 | — | ADK 2.0 workflow skeleton, 20 nodes, schemas, end-to-end demo |
| 1: Evidence-First MVP | 8 | — | 7 agents, REST API, citations, claim-evidence traceability |
| 2: STORM-Grade Iterative | 6 | +1,406/-675 | Moderator, scheduler, stopping conditions, info-gain metrics |
| 3: Co-STORM Collaboration | 8 | +1,197/-144 | Events, approvals, interventions, concept map, knowledge organizer |
| 4: Epistemic Reliability | 6 | +1,167/-35 | Counter-evidence, contradictions, confidence, verification |
| 5: Enterprise Governance | 8 | +336/-5 | Identity, policy engine, audit log, source classification |
| 6: Continuous Research | 6 | +389 | Watch mode, skill registry, knowledge publishing |
Phase 0: Architecture Spike
Exit criterion: A research run can be interrupted and resumed without duplicating completed stages.
- 20-node ADK 2.0 Workflow graph (sequential)
- Source and claim data schemas (14 Pydantic v2 models)
- Session persistence
- Event streaming infrastructure
- Web search tool integration
Phase 1: Evidence-First MVP
Exit criteria: All substantive report claims map to claim records. All source-derived claims map to evidence.
- Research Director, Perspective Planner, Question Architect
- Query Planner with 10 search strategies
- Evidence Curator with exact excerpt preservation
- Claim Builder with atomic claims and epistemic status
- Outline Architect and Section Writer
- Citation linking: report → claim → evidence → source
- REST API: create, inspect, export research runs
Phase 2: STORM-Grade Iterative Research
Exit criterion: Compute-matched evaluation demonstrates better coverage than one-shot RAG.
- Research Moderator Agent: stagnation detection, rebalancing
- Evidence-conditioned follow-up question generation
- Frontier scheduler with priority function: Priority = w_m·M + w_r·R + w_d·D + w_u·U + w_n·N − w_c·C
- Iterative stopping conditions: budget, coverage, info gain
- Perspective budget allocation
- Information-gain metrics: IG_t = α·N_c + β·N_e + γ·N_k + δ·C_r − λ·D
Phase 3: Co-STORM-Style Collaboration
Exit criterion: Users can steer a running investigation without corrupting workflow state.
- Streaming event infrastructure (16 event types)
- Live research frontier API
- User intervention API: add_question, challenge_claim, exclude_source, increase_depth
- Approval gates A/B/C/D with configurable triggers
- Knowledge Organizer Agent + concept map projection
- Mid-run scope changes
Phase 4: Epistemic Reliability
Exit criterion: Material unsupported-inference rate meets production threshold (<5%).
- Counter-Evidence Agent: contradiction search, independence checks
- Contradiction detection and resolution tracking
- Source independence clustering (deterministic)
- Confidence model: authority × independence × freshness × corroboration
- Verification Agent with independent prompt from writer
- Citation entailment with keyword overlap heuristics
- Cross-section consistency checks
Phase 5: Enterprise Governance
Exit criterion: Security, authorization, and audit release gates pass.
- Identity engine: principal context propagation through all nodes
- Policy engine: role-to-tool allowlists, stage-based tool reduction
- Real source policy: deduplication, classification, domain filtering
- Immutable audit log with chain verification
- Prompt injection defenses
Phase 6: Continuous Research and Reusable SOPs
Exit criterion: A saved research workflow can update prior findings without rebuilding blindly.
- Continuous watch mode with delta detection
- Source content change detection + claim invalidation cascade
- Research Skill Registry with progressive disclosure
- 5 domain templates: architecture analysis, security, standards, vendor validation, executive briefs
- Knowledge-layer publishing: validated claims → long-term memory
Dependency Graph
Phase 0 ──► Phase 1 ──► Phase 2 ──► Phase 3 ──► Phase 5 ──► Phase 6
│ │ │
└──► Phase 4 ─┘────────────┘ - Phase 4 depends on Phase 2 (needs iterative loop)
- Phase 5 depends on Phase 3 (approval center) and Phase 4 (verification)
- Phase 6 depends on Phase 5 (governance + audit)