feat: market regime, self-learning journal, AI investment committee

- regime.py: computed SPY/VIX/sector-momentum snapshot injected into every kickoff
- journal.py: each agent sees its own past picks marked-to-market (learns from wins/losses)
- committee.py: Chief-Risk-Officer LLM pass over the whole book — approve/reduce/veto
  per pick with reasons; memo lands in reports; executor enforces verdicts at open

Co-Authored-By: Claude Opus 4.8 <noreply@anthropic.com>
Claude-Session: https://claude.ai/code/session_016DvdRZkyCy9NJpHYDdPqmS

agents/graph.py

@@ -237,6 +237,7 @@ def run_agent(
     step_budget: int,
     min_steps: int = 0,
     min_seconds: float = 0.0,
+    context_blurb: str = "",
     checkpointer=None,
     model_name: str = "",
 ) -> AgentOutput:
@@ -252,9 +253,12 @@ def run_agent(
     compact_budget = get_settings().compaction_token_budget
 
     date_str = datetime.now().astimezone().strftime("%A %Y-%m-%d")
+    kickoff = RESEARCH_KICKOFF.format(date=date_str, n=persona.target_pick_count)
+    if context_blurb:  # market regime + the agent's own track record (self-learning)
+        kickoff = f"{context_blurb}\n\n{kickoff}"
     messages: list = [
         SystemMessage(content=persona.system_prompt),
-        HumanMessage(content=RESEARCH_KICKOFF.format(date=date_str, n=persona.target_pick_count)),
+        HumanMessage(content=kickoff),
     ]
     running_summary = ""
     reasoning_trace: list[str] = []