feat(strategist) S3: propose_lead / declare_investigation_complete

DESIGN_STRATEGIST.md §2.5. The strategist's two write actions.

propose_lead validates motivating_hypothesis exists in the graph,
validates expected_evidence_type is a real edge type, validates
source_id refers to a real source in the case — fast specific
errors so the strategist gets fixable feedback rather than a
generic crash. On success, calls graph.add_lead with proposed_by=
"strategist" and round_number=graph.current_strategist_round so
the round-completion code can collect this round's leads.

declare_investigation_complete sets graph.strategist_complete_requested
which the orchestrator inspects after each strategist run to decide
whether to break the loop. reason must come from a closed enum so
the audit log is consistent.

EvidenceGraph gains two transient run-context fields:
  current_strategist_round       — set by orchestrator at start of round
  strategist_complete_requested  — flipped by declare_complete

These are intentionally NOT persisted — they're per-run flags, not
graph state.

Both tools required to be in InvestigationStrategist.mandatory_record_
tools (added in S4) so the agent's forced-retry mechanism kicks in if
it returns without taking a documented decision.

Co-Authored-By: Claude Opus 4.7 (1M context) <noreply@anthropic.com>

evidence_graph.py

@@ -680,6 +680,15 @@ class EvidenceGraph:
         self.budgets: dict[str, int] = {}
         self.run_start_monotonic: float | None = None
 
+        # Current strategist round number. Set by the orchestrator at the
+        # top of each strategist loop iteration so propose_lead / declare_
+        # investigation_complete can tag their actions correctly. 0 when
+        # the strategist is not running.
+        self.current_strategist_round: int = 0
+        # Set to True by declare_investigation_complete so the orchestrator
+        # knows to break out of the strategist loop after this round.
+        self.strategist_complete_requested: bool = False
+
         # _current_agent / _current_task_id are exposed as @property below,
         # backed by module-level ContextVars (race-free under asyncio.gather).