docs: gap analysis implementation status tracker (#658)

Resolves #658. Maps the gap analysis findings to current
implementation status across all 6 categories.

Tracks: memory/search, multi-agent, inference, orchestration,
safety/crisis, accuracy measurement.

Shows which gaps are filled (by PR number), which are in PR,
and which remain future work.

docs/gap-analysis-status.md

@@ -0,0 +1,70 @@
+# Gap Analysis: Actual System vs SOTA — Implementation Status Tracker
+
+Issue #658. Maps gap analysis findings to implementation status.
+
+## Gap Categories
+
+### 1. Memory & Search
+
+| Gap | Target | Status | PR |
+|-----|--------|--------|-----|
+| Semantic search (R@5) | 95-99% | RIDER: +25% E2E | #782 |
+| Hybrid search | Vector + FTS5 + HRR | Hybrid search module | #729 |
+| Context-faithful prompting | +11-14% E2E | Context-faithful module | #786 |
+| Accuracy benchmarks | Measured | benchmark_r5_e2e.py | #790 |
+| Vector embeddings | ChromaDB | Not yet (Qdrant fallback) | Future |
+
+### 2. Multi-Agent Coordination
+
+| Gap | Target | Status | PR |
+|-----|--------|--------|-----|
+| Three-tier memory | Unified | Fragmented (pieces exist) | #653 |
+| DAG task routing | GraphFlow-style | Not implemented | Future |
+| Fleet diary | Structured logs | Not implemented | Future |
+
+### 3. Inference Optimization
+
+| Gap | Target | Status | PR |
+|-----|--------|--------|-----|
+| Cost tracking | $/1M tokens | task_cost_breakdown.py | fleet-ops#267 |
+| Fallback chain | Explicit | Provider routing exists | Existing |
+| vLLM + FP8 | 60% cost reduction | Not yet | Future |
+
+### 4. Workflow Orchestration
+
+| Gap | Target | Status | PR |
+|-----|--------|--------|-----|
+| Retry with backoff | Built-in | Partial (cron retry) | Existing |
+| Task dependencies | Pipeline chaining | Not implemented | Future |
+| Concurrency control | Worker pool | File lock (single) | Existing |
+
+### 5. Safety & Crisis
+
+| Gap | Target | Status | PR |
+|-----|--------|--------|-----|
+| Crisis detection | F1>0.85 | Crisis protocol + SHIELD | #785 |
+| Human confirmation | Tier system | Approval tiers | #697 |
+| 988 Lifeline | Auto-display | Crisis resources | #783 |
+| Emotional presence | Patterns | Research doc | #788 |
+| SOUL.md protocol | Implemented | Crisis protocol | #785 |
+
+### 6. Accuracy Measurement
+
+| Gap | Target | Status | PR |
+|-----|--------|--------|-----|
+| R@5 measurement | Automated | benchmark_r5_e2e.py | #790 |
+| E2E accuracy | Measured | benchmark_r5_e2e.py | #790 |
+| Gap analysis | Documented | r5-vs-e2e-gap-analysis.md | #790 |
+
+## Implementation Priority
+
+1. **DONE:** Crisis support (SOUL.md, 988, detection)
+2. **DONE:** Safety (approval tiers, SHIELD)
+3. **DONE:** Retrieval improvement (RIDER, hybrid search, context-faithful)
+4. **DONE:** Accuracy measurement (benchmark script)
+5. **IN PR:** Cost tracking (task_cost_breakdown.py)
+6. **FUTURE:** DAG routing, pub-sub messaging, vLLM deployment
+
+## Key Insight
+
+The biggest gap was MEASUREMENT — we didn't know if our systems worked. Issue #657 (accuracy measurement) addressed this first, followed by the retrieval improvements that bridge the R@5 vs E2E gap.