Add OpenAI-compatible LLM provider (URL/model/key configurable)

- New provider 'openai' calls any OpenAI-compatible /chat/completions endpoint
  (OpenAI, OpenRouter, Together, Groq, NVIDIA, vLLM, Ollama, ...), set via
  OPENAI_BASE_URL / OPENAI_API_KEY / OPENAI_MODEL. Now the default; auto-detects.
- Robustness for models that degenerate (e.g. Kimi repetition loops): anti-
  repetition sampling (temperature + frequency penalty), and a schema-aware
  retry — call_json(require_keys=...) retries a fresh sample on degenerate or
  unparseable output (LLMRetryable). Relevance requires 'signals', synth 'briefs'.
- response_format=json_object (toggle via OPENAI_JSON_MODE); base URL accepts a
  full /chat/completions URL or a /v1 base.

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

sales-agent/src/config.py

@@ -28,9 +28,31 @@ def _load_dotenv() -> None:
 _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.
+# 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.
+#
+# "openai" is any OpenAI-compatible /chat/completions endpoint — OpenAI, OpenRouter,
+# Together, Groq, vLLM, Ollama, LM Studio, etc. — configured by three env vars:
+#   OPENAI_BASE_URL  (e.g. https://api.openai.com/v1)
+#   OPENAI_API_KEY
+#   OPENAI_MODEL     (e.g. gpt-4o-mini)
+OPENAI_API_KEY = os.environ.get("OPENAI_API_KEY", "").strip()
+OPENAI_BASE_URL = os.environ.get("OPENAI_BASE_URL", "https://api.openai.com/v1").strip().rstrip("/")
+OPENAI_MODEL = os.environ.get("OPENAI_MODEL", "gpt-4o-mini").strip()
+# Some endpoints/models don't support response_format=json_object — turn off if so.
+OPENAI_JSON_MODE = os.environ.get("OPENAI_JSON_MODE", "1").strip() == "1"
+# Sampling/anti-repetition. A small frequency penalty + non-trivial temperature
+# avoids the repetition-loop degeneration some models (e.g. Kimi) fall into at
+# very low temperature. Penalties are omitted from the request when set to 0
+# (for endpoints that reject them).
+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.
+LLM_CONTENT_RETRIES = int(os.environ.get("LLM_CONTENT_RETRIES", "3"))
+
 ANTHROPIC_API_KEY = os.environ.get("ANTHROPIC_API_KEY", "").strip()
 LLM_MODEL = os.environ.get("LLM_MODEL", "claude-sonnet-4-6")
 
@@ -39,7 +61,9 @@ 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:
+    if OPENAI_API_KEY:
+        _provider = "openai"
+    elif GEMINI_API_KEY:
         _provider = "gemini"
     elif ANTHROPIC_API_KEY:
         _provider = "anthropic"
@@ -48,6 +72,8 @@ if not _provider:
 # 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"
 elif _provider == "gemini" and not GEMINI_API_KEY:
     _provider = "mock"
 elif _provider == "anthropic" and not ANTHROPIC_API_KEY:
@@ -60,6 +86,9 @@ USE_MOCK_LLM = LLM_PROVIDER == "mock"
 def llm_label() -> str:
     if LLM_PROVIDER == "mock":
         return "MOCK reasoner (no LLM key)"
+    if LLM_PROVIDER == "openai":
+        host = OPENAI_BASE_URL.split("//")[-1].split("/")[0]
+        return f"OpenAI-compatible ({OPENAI_MODEL} @ {host})"
     if LLM_PROVIDER == "gemini":
         return f"Gemini ({GEMINI_MODEL})"
     return f"Anthropic ({LLM_MODEL})"