Initial commit: prospecting agent loop MVP

Closed-loop account-intelligence system: harvest -> relevance filter vs.
Capability Library -> synthesize -> score -> deliver -> feedback.

- 40-capability Broadcom + VMware library
- Live Exa.ai news connector with hard free-plan request ceilings
- Provider-agnostic LLM layer (Gemini/Anthropic) with offline mock fallback
- LLM confidence wired into composite scoring + low-confidence floor
- 7-account pilot list

Co-Authored-By: Claude Opus 4.8 <noreply@anthropic.com>

sales-agent/src/config.py

@@ -0,0 +1,103 @@
+"""Central config & paths. Loads a .env file if present (no external deps)."""
+from __future__ import annotations
+
+import os
+from pathlib import Path
+
+ROOT = Path(__file__).resolve().parent.parent
+DATA_DIR = ROOT / "data"
+OUTPUT_DIR = ROOT / "output"
+STATE_DIR = OUTPUT_DIR / "state"
+BRIEFS_DIR = OUTPUT_DIR / "briefs"
+
+
+def _load_dotenv() -> None:
+    """Minimal .env loader so the user can keep keys in sales-agent/.env."""
+    env_path = ROOT / ".env"
+    if not env_path.exists():
+        return
+    for line in env_path.read_text().splitlines():
+        line = line.strip()
+        if not line or line.startswith("#") or "=" not in line:
+            continue
+        key, _, val = line.partition("=")
+        key, val = key.strip(), val.strip().strip('"').strip("'")
+        os.environ.setdefault(key, val)
+
+
+_load_dotenv()
+
+# --- LLM ---
+# Provider abstraction: gemini | anthropic | mock. If LLM_PROVIDER is unset we
+# auto-detect from whichever key is present (Gemini preferred), falling back to
+# a deterministic mock reasoner so the loop still runs offline.
+ANTHROPIC_API_KEY = os.environ.get("ANTHROPIC_API_KEY", "").strip()
+LLM_MODEL = os.environ.get("LLM_MODEL", "claude-sonnet-4-6")
+
+GEMINI_API_KEY = os.environ.get("GEMINI_API_KEY", "").strip()
+GEMINI_MODEL = os.environ.get("GEMINI_MODEL", "gemini-2.5-flash")
+
+_provider = os.environ.get("LLM_PROVIDER", "").strip().lower()
+if not _provider:
+    if GEMINI_API_KEY:
+        _provider = "gemini"
+    elif ANTHROPIC_API_KEY:
+        _provider = "anthropic"
+    else:
+        _provider = "mock"
+# A forced USE_MOCK_LLM=1, or selecting a provider whose key is missing, => mock.
+if os.environ.get("USE_MOCK_LLM", "").strip() == "1":
+    _provider = "mock"
+elif _provider == "gemini" and not GEMINI_API_KEY:
+    _provider = "mock"
+elif _provider == "anthropic" and not ANTHROPIC_API_KEY:
+    _provider = "mock"
+
+LLM_PROVIDER = _provider
+USE_MOCK_LLM = LLM_PROVIDER == "mock"
+
+
+def llm_label() -> str:
+    if LLM_PROVIDER == "mock":
+        return "MOCK reasoner (no LLM key)"
+    if LLM_PROVIDER == "gemini":
+        return f"Gemini ({GEMINI_MODEL})"
+    return f"Anthropic ({LLM_MODEL})"
+
+# --- Scoring thresholds (Phase 5 of the design) ---
+PRIORITY_THRESHOLD = float(os.environ.get("PRIORITY_THRESHOLD", "0.72"))
+STANDARD_THRESHOLD = float(os.environ.get("STANDARD_THRESHOLD", "0.45"))
+# Briefs whose LLM confidence falls below this floor are demoted to "low"
+# (logged, not delivered) regardless of composite score — keeps weak matches
+# the model itself doubts out of the rep's queue.
+CONFIDENCE_FLOOR = float(os.environ.get("CONFIDENCE_FLOOR", "0.35"))
+
+# --- Exa.ai news/web harvester ---
+EXA_API_KEY = os.environ.get("EXA_API_KEY", "").strip()
+# Enabled only when a key is present AND not explicitly turned off.
+EXA_ENABLED = (os.environ.get("EXA_ENABLED", "1").strip() == "1") and bool(EXA_API_KEY)
+# Hard request ceilings to protect the free plan. The connector will NOT call
+# Exa once either cap is reached; the monthly counter persists across runs.
+EXA_MONTHLY_REQUEST_CAP = int(os.environ.get("EXA_MONTHLY_REQUEST_CAP", "1000"))
+EXA_PER_RUN_REQUEST_CAP = int(os.environ.get("EXA_PER_RUN_REQUEST_CAP", "25"))
+EXA_RESULTS_PER_QUERY = int(os.environ.get("EXA_RESULTS_PER_QUERY", "5"))
+EXA_LOOKBACK_DAYS = int(os.environ.get("EXA_LOOKBACK_DAYS", "45"))
+# Scope news search to each account's own domain (newsroom/press/IR) to cut
+# third-party ticker/analyst noise. Toggle off in .env or per-run with
+# `loop --no-domain-filter` to include broad third-party coverage.
+EXA_DOMAIN_FILTER = os.environ.get("EXA_DOMAIN_FILTER", "1").strip() == "1"
+
+# --- Dedup / suppression windows ---
+SEMANTIC_DEDUP_DAYS = 90
+SAME_TYPE_SUPPRESS_DAYS = 14
+
+# Per-tier harvest cadence (informational for the scheduler; the MVP runs on demand)
+TIER_CADENCE_HOURS = {"strategic": 24, "enterprise": 60, "growth": 168}
+
+# Brief expiry (opportunities decay if not acted on)
+BRIEF_TTL_DAYS = 21
+
+
+def ensure_dirs() -> None:
+    for d in (OUTPUT_DIR, STATE_DIR, BRIEFS_DIR):
+        d.mkdir(parents=True, exist_ok=True)