Improve signal quality (Exa news category) and remove mock fallback

Exa harvester:
- EXA_CATEGORY=news (default) restricts to news articles, excluding evergreen
  careers/marketing landing pages that were producing irrelevant signals.
- Event-focused query (acquisition/earnings/launch/leadership), dropped
  hiring/career terms that pulled recruiting pages.
- Domain scoping now OFF by default (broad-web news about the account beats
  first-party careers pages); add EXA_EXCLUDE_DOMAINS and loop --domain-filter.

LLM layer:
- Remove the mock reasoner entirely (no provider => loop refuses to run).
- On HTTP 429, WAIT (LLM_RATELIMIT_WAIT_SECONDS, default 900s; honors
  Retry-After) and retry up to LLM_RATELIMIT_MAX_RETRIES (24) instead of
  degrading to mock output.
- If the LLM is ultimately unavailable for an account, skip it and leave its
  signals unconsumed (retried next run) — never fabricate briefs.

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

sales-agent/src/config.py

@@ -28,12 +28,13 @@ def _load_dotenv() -> None:
 _load_dotenv()
 
 # --- LLM ---
-# Provider abstraction: openai | gemini | anthropic | mock. If LLM_PROVIDER is
-# unset we auto-detect from whichever key is present (OpenAI-compatible first),
-# falling back to a deterministic mock reasoner so the loop still runs offline.
+# Provider abstraction: openai | gemini | anthropic. If LLM_PROVIDER is unset we
+# auto-detect from whichever key is present (OpenAI-compatible first). There is NO
+# mock fallback: the loop refuses to run without a configured provider, and on
+# rate limits it WAITS and retries rather than emitting low-quality output.
 #
 # "openai" is any OpenAI-compatible /chat/completions endpoint — OpenAI, OpenRouter,
-# Together, Groq, vLLM, Ollama, LM Studio, etc. — configured by three env vars:
+# Together, Groq, NVIDIA, vLLM, Ollama, LM Studio, etc. — configured by:
 #   OPENAI_BASE_URL  (e.g. https://api.openai.com/v1)
 #   OPENAI_API_KEY
 #   OPENAI_MODEL     (e.g. gpt-4o-mini)
@@ -50,8 +51,13 @@ OPENAI_TEMPERATURE = float(os.environ.get("OPENAI_TEMPERATURE", "0.5"))
 OPENAI_FREQUENCY_PENALTY = float(os.environ.get("OPENAI_FREQUENCY_PENALTY", "0.4"))
 OPENAI_PRESENCE_PENALTY = float(os.environ.get("OPENAI_PRESENCE_PENALTY", "0.0"))
 # Retries when a model returns degenerate/unparseable content (stochastic — a
-# retry usually succeeds). Distinct from the network/429 backoff.
+# retry usually succeeds).
 LLM_CONTENT_RETRIES = int(os.environ.get("LLM_CONTENT_RETRIES", "3"))
+# On HTTP 429 (rate limit) we WAIT this long and retry (no mock fallback). Honors
+# a Retry-After response header when present. Lets the loop grind slowly but
+# correctly through a tight rate limit instead of degrading quality.
+LLM_RATELIMIT_WAIT_SECONDS = int(os.environ.get("LLM_RATELIMIT_WAIT_SECONDS", "900"))
+LLM_RATELIMIT_MAX_RETRIES = int(os.environ.get("LLM_RATELIMIT_MAX_RETRIES", "24"))
 
 ANTHROPIC_API_KEY = os.environ.get("ANTHROPIC_API_KEY", "").strip()
 LLM_MODEL = os.environ.get("LLM_MODEL", "claude-sonnet-4-6")
@@ -68,24 +74,22 @@ if not _provider:
     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 == "openai" and not OPENAI_API_KEY:
-    _provider = "mock"
+        _provider = "none"
+# Selecting a provider whose key is missing => no usable provider.
+if _provider == "openai" and not OPENAI_API_KEY:
+    _provider = "none"
 elif _provider == "gemini" and not GEMINI_API_KEY:
-    _provider = "mock"
+    _provider = "none"
 elif _provider == "anthropic" and not ANTHROPIC_API_KEY:
-    _provider = "mock"
+    _provider = "none"
 
 LLM_PROVIDER = _provider
-USE_MOCK_LLM = LLM_PROVIDER == "mock"
+LLM_CONFIGURED = LLM_PROVIDER != "none"
 
 
 def llm_label() -> str:
-    if LLM_PROVIDER == "mock":
-        return "MOCK reasoner (no LLM key)"
+    if LLM_PROVIDER == "none":
+        return "NONE (no LLM provider configured)"
     if LLM_PROVIDER == "openai":
         host = OPENAI_BASE_URL.split("//")[-1].split("/")[0]
         return f"OpenAI-compatible ({OPENAI_MODEL} @ {host})"
@@ -111,10 +115,18 @@ 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"
+# Exa content category. "news" restricts results to news articles (press releases,
+# coverage) and keeps out evergreen pages like careers/marketing landing pages —
+# the single biggest signal-quality lever. Set to "" to disable category filtering.
+EXA_CATEGORY = os.environ.get("EXA_CATEGORY", "news").strip()
+# Domain scoping is OFF by default now: with category=news, broad-web search finds
+# actual news ABOUT the account from outlets, whereas scoping to the company's own
+# domain surfaces careers/marketing pages. Turn on for first-party newsroom only.
+EXA_DOMAIN_FILTER = os.environ.get("EXA_DOMAIN_FILTER", "0").strip() == "1"
+# Hosts to always exclude (comma-separated) — e.g. careers/talent subdomains.
+EXA_EXCLUDE_DOMAINS = [
+    d.strip() for d in os.environ.get("EXA_EXCLUDE_DOMAINS", "").split(",") if d.strip()
+]
 
 # --- Dedup / suppression windows ---
 SEMANTIC_DEDUP_DAYS = 90