feat: Phase 3.5 — DPO training pair generation from Deep Dive pipeline

Wire arXiv relevance filter output directly into DPO pair generation,
closing the loop between research synthesis and overnight training data.

New module: dpo_generator.py
- DPOPairGenerator class with 3 pair strategies:
  * summarize: paper → fleet-grounded analysis (chosen) vs generic (rejected)
  * relevance: 'what matters to Hermes?' → scored context vs vague
  * implication: 'what should we do?' → actionable insight vs platitude
- Extracts synthesis excerpts matched to each ranked item
- Outputs to ~/.timmy/training-data/dpo-pairs/deepdive_{timestamp}.jsonl
- Format: {prompt, chosen, rejected, task_type, evidence_ids,
  source_session, safety_flags, metadata}

Pipeline changes (pipeline.py):
- Import DPOPairGenerator with graceful degradation
- Initialize from config deepdive.training.dpo section
- Execute as Phase 3.5 between synthesis and audio
- DPO results included in pipeline return dict
- Wrapped in try/except — DPO failure never blocks delivery

Config changes (config.yaml):
- New deepdive.training.dpo section with:
  enabled, output_dir, min_score, max_pairs_per_run, pair_types

Integration tested: 2 mock items × 3 pair types = 6 valid JSONL pairs.
Chosen responses consistently richer than rejected (assert-verified).

intelligence/deepdive/config.yaml

@@ -88,6 +88,18 @@ deepdive:
     speed: 1.0
     output_format: "mp3"  # piper outputs WAV, convert for Telegram
 
+  # Phase 3.5: DPO Training Pair Generation
+  training:
+    dpo:
+      enabled: true
+      output_dir: "~/.timmy/training-data/dpo-pairs"
+      min_score: 0.5        # Only generate pairs from items above this relevance score
+      max_pairs_per_run: 30  # Cap pairs per pipeline execution
+      pair_types:            # Which pair strategies to use
+        - "summarize"        # Paper summary → fleet-grounded analysis
+        - "relevance"        # Relevance analysis → scored fleet context
+        - "implication"      # Implications → actionable insight
+
   # Phase 0: Fleet Context Grounding
   fleet_context:
     enabled: true