Implement BDEF v1.1 grading: scoring core, per-deck pipeline, ledger, dashboard, StartOS layer

- Deterministic scoring.py (quant 60 / qual 40 / flags -15, profitability heaviest)
- Per-company JSON ledger with forecast-target chaining deck N-1 -> N
- Single-shot sandbox agent with guided-JSON fallback ladder (no tool loop)
- Portfolio dashboard with sparklines, KPI hit rates, BDEF category bars
- 48 unit tests green; endpoints smoke-tested; npm check+build green

Co-Authored-By: Claude Fable 5 <noreply@anthropic.com>

orchestrator/bm_config.py

@@ -12,13 +12,23 @@ import spark_client as sc
 
 DATA_DIR = os.environ.get("BM_DATA_DIR", "/data")
 HF_TOKEN_PATH = os.path.join(DATA_DIR, "secrets", "hf_token")
+BDEF_PATH = os.path.join(os.path.dirname(os.path.abspath(__file__)), "bdef.md")
 
-DEFAULT_RUBRIC = (
-    "Review the attached document(s). Produce a structured report: a 3-5 sentence "
-    "summary, the key findings and insights, risks or red flags, open questions, "
-    "and concrete recommendations. Cite the document and section for each point. "
-    "Be honest about uncertainty; never invent facts not present in the documents."
-)
+# Scoring weights (composite 0-100 = quant 60 + qual 40 - penalties).
+# Every knob the deterministic scorer uses lives here so the user can retune
+# without a rebuild. Keep flat: StartOS action inputs are flat number fields.
+WEIGHTS_DEFAULTS = {
+    "profitabilityKpi": 30,       # profitability KPI attainment bucket
+    "otherKpi": 20,               # non-profitability measurable KPI bucket
+    "forecastIntegrity": 10,      # deck N actuals vs deck N-1 stated targets
+    "qualCategoryMax": 5,         # each BDEF category A-H maxes at this (8x5=40)
+    "redFlagCap": 15,             # max total penalty
+    "kpiCreditFloor": 0.5,        # actual/target ratio below which credit = 0
+    "droppedKpiPenalty": 2,       # severity of a KPI that silently disappeared
+    "droppedKpiMax": 3,           # count at most this many dropped-KPI flags
+    "evidenceFullCredit": 400,    # quote chars for full qualitative weight
+    "singleSourceFlagFactor": 0.5,  # damping for flags raised by one source only
+}
 
 CONFIG_DEFAULTS = {
     # Spark connection
@@ -39,22 +49,29 @@ CONFIG_DEFAULTS = {
     "proxyPort": 4000,
     "maxConcurrentModels": 1,
     "models": [
-        {"alias": "reviewer-a", "hfModel": "Qwen/Qwen3-32B-FP8", "spark": "primary", "port": 8001},
+        {"alias": "grader-a", "hfModel": "Qwen/Qwen3-32B-FP8", "spark": "primary", "port": 8001},
     ],
-    # Review panel
-    "reviewers": [
-        {"name": "reviewer-1", "model": "reviewer-a", "persona": "", "temperature": None},
+    # Grading panel
+    "graders": [
+        {"name": "munger-lens", "model": "grader-a", "persona": "", "temperature": None},
     ],
-    # Review job settings
-    "reviewInstructions": DEFAULT_RUBRIC,
+    # Which catalog model runs the stage-1 structured extractor ("" = first model)
+    "extractorModel": "",
+    # Grading job settings
+    "bdefOverride": "",           # non-empty replaces the baked-in bdef.md rubric
+    "weights": dict(WEIGHTS_DEFAULTS),
     "networkMode": "airgapped",
     "searxngUrl": "",
-    "synthesisEnabled": True,
-    "synthesisModel": "",
-    "synthesisPersona": "",
+    "adjudicatorEnabled": True,
+    "adjudicatorModel": "",
+    "adjudicatorPersona": "",
     "wipeRemoteDocs": True,
     "autoRunOnDrop": False,
     "networkName": "boardroom-net",
+    # Portfolio companies (authoritative source of pinned targets / aliases).
+    # pinnedTargets: [{kpi, target, unit, direction: gte|lte, profitability}]
+    # kpiAliases: newline-separated "canonical=alias1;alias2" lines.
+    "companies": [],
     # Flags
     "hfTokenSet": False,
 }
@@ -68,9 +85,22 @@ def load() -> dict:
     except FileNotFoundError:
         return merged
     merged.update({k: v for k, v in saved.items() if v is not None})
+    # weights merge key-by-key so a partially-saved weights object keeps defaults
+    w = dict(WEIGHTS_DEFAULTS)
+    w.update({k: v for k, v in (merged.get("weights") or {}).items() if v is not None})
+    merged["weights"] = w
     return merged
 
 
+def bdef_text(cfg: dict) -> str:
+    """The grading rubric: config override if set, else the baked-in spec."""
+    override = (cfg.get("bdefOverride") or "").strip()
+    if override:
+        return override
+    with open(BDEF_PATH, encoding="utf-8") as f:
+        return f.read()
+
+
 def hf_token() -> str | None:
     if os.path.exists(HF_TOKEN_PATH):
         t = open(HF_TOKEN_PATH).read().strip()