docs: update M3.8 task specs (M3.8.3-6 detailed)

M3.8.3 ✅ COMPLETE (7 tests)
- MetricsCollector: per-project aggregation
- Structured logging (tracing)
- Prometheus export format

M3.8.4 ✅ IMPLICIT (no work needed)
- Query path already clean (no compression)
- Only cache_metrics() uses optimizer (for observability)

M3.8.5 ⏳ ACTIVE (16 tests spec'd)
- Compression ratio benchmarks (5 tests: log/json/text/diff/mixed)
- Search quality validation (8 tests: pgvector/opensearch/fusion)
- Performance baseline (3 tests: latency/throughput/memory)

M3.8.6 ⏳ PENDING (13 gate assertions)
- Safety (6): no data loss, deterministic, structure preservation
- Performance (4): latency p99 <3ms, throughput 1000+/sec, memory <100MB
- Quality (3): compression targets, search improvement, cache accuracy

Project progress: 64/78 complete (82%), 8/13 gates green
Total M3.8 tests: 103 (62+5+7+0+16+13)

tasks/M3.8.6-m3.8-gate.md

@@ -0,0 +1,171 @@
+# M3.8.6 — M3.8 Composition Gate
+
+| Field | Value |
+|---|---|
+| Phase | M3.8 — Context optimization |
+| Size | M — 1 day |
+| Status | ⬜ Not started |
+| Depends | M3.8.5 (benchmarks) |
+| Blocks | Production deployment |
+
+## Goal
+
+Verify M3.8 implementation meets all safety, performance, and quality constraints
+before production rollout.
+
+## Gate Assertions
+
+### Safety (6 assertions)
+
+1. **No data loss** — Optimized chunks preserve all semantic content
+   ```rust
+   assert!(semantic_similarity(original, optimized) > 0.95);
+   ```
+
+2. **Deterministic output** — Same input always produces same output
+   ```rust
+   assert_eq!(optimize(text), optimize(text));
+   ```
+
+3. **Structure preservation** — JSON/logs remain parseable
+   ```rust
+   assert!(parse_json(&optimized).is_ok());
+   assert!(grep_logs(&optimized).count() > 0);
+   ```
+
+4. **Metadata preserved** — Breadcrumb, role, provenance untouched
+   ```rust
+   assert_eq!(original.provenance, optimized.provenance);
+   assert_eq!(original.breadcrumb, optimized.breadcrumb);
+   ```
+
+5. **Error handling** — Graceful fallback on optimization failure
+   ```rust
+   assert!(optimize_with_fallback(bad_input).is_ok());
+   ```
+
+6. **Thread safety** — Concurrent optimization doesn't corrupt state
+   ```rust
+   assert!(concurrent_optimize(1000).all_ok());
+   ```
+
+### Performance (4 assertions)
+
+1. **Latency** — Per-record optimization <3ms p99
+   ```rust
+   assert!(latency_p99() < Duration::from_millis(3));
+   ```
+
+2. **Throughput** — Sustained 1000+ records/sec
+   ```rust
+   assert!(throughput_records_per_sec() >= 1000);
+   ```
+
+3. **Memory** — Cache stays <100MB (max 1000 entries)
+   ```rust
+   assert!(cache_size_mb() < 100);
+   ```
+
+4. **No regressions** — Existing tests still pass
+   ```rust
+   assert!(all_prompt_tests_pass());
+   assert!(all_ingest_tests_pass());
+   ```
+
+### Quality (3 assertions)
+
+1. **Compression targets met** — All content types
+   ```rust
+   assert!(log_ratio >= 85.0 && log_ratio <= 95.0);
+   assert!(json_ratio >= 70.0 && json_ratio <= 90.0);
+   assert!(text_ratio >= 30.0 && text_ratio <= 50.0);
+   ```
+
+2. **Search quality improves** — pgvector + OpenSearch
+   ```rust
+   assert!(embedding_similarity > 0.95);
+   assert!(opensearch_mrr_improvement > 10);
+   ```
+
+3. **No false positives** — Cache eligibility accurate
+   ```rust
+   assert!(drift_metric_accurate < 0.05);  // <5% error
+   ```
+
+## Test Implementation
+
+File: `tests/it_m3_8_gate.rs` (400 LOC)
+
+```rust
+#[test]
+fn m3_8_gate_no_data_loss() { ... }
+
+#[test]
+fn m3_8_gate_deterministic() { ... }
+
+#[test]
+fn m3_8_gate_structure_preservation() { ... }
+
+#[test]
+fn m3_8_gate_metadata_preservation() { ... }
+
+#[test]
+fn m3_8_gate_error_handling() { ... }
+
+#[test]
+fn m3_8_gate_thread_safety() { ... }
+
+#[test]
+fn m3_8_gate_latency_p99() { ... }
+
+#[test]
+fn m3_8_gate_throughput_sustained() { ... }
+
+#[test]
+fn m3_8_gate_memory_bounded() { ... }
+
+#[test]
+fn m3_8_gate_no_regressions() { ... }
+
+#[test]
+fn m3_8_gate_compression_targets() { ... }
+
+#[test]
+fn m3_8_gate_search_quality() { ... }
+
+#[test]
+fn m3_8_gate_cache_eligibility() { ... }
+```
+
+Total: **13 gate assertions**
+
+## Acceptance Criteria
+
+✅ All 13 assertions passing
+✅ All 62 M3.8.1 optimizer tests passing
+✅ All 5 M3.8.2 ingest tests passing
+✅ All 7 M3.8.3 metrics tests passing
+✅ All 16 M3.8.5 benchmark tests passing
+✅ All 11 existing prompt tests passing
+✅ No regressions in other modules
+✅ Documentation complete
+
+## Success Criteria
+
+- **Safety**: 6/6 assertions ✅
+- **Performance**: 4/4 assertions ✅
+- **Quality**: 3/3 assertions ✅
+- **Coverage**: 100% of compressors tested
+- **Documentation**: BENCHMARKS.md + GATE.md
+
+## Timeline
+
+- M3.8.1: ✅ Done (62 tests)
+- M3.8.2: ✅ Done (5 tests)
+- M3.8.3: ✅ Done (7 tests)
+- M3.8.4: ✅ Done (implicit, 0 tests)
+- M3.8.5: ⏳ In progress (16 tests)
+- M3.8.6: ⏳ Next (13 tests)
+
+**Total M3.8**: 103 tests
+**Expected gate pass rate**: 100%