Update llm_router.py

llm_router.py

@@ -1,23 +1,57 @@
-import cohere, openai, anthropic
-from settings import COHERE_API_KEY, COHERE_MODEL_PRIMARY, MODEL_SETTINGS, OPENAI_API_KEY, OPENAI_MODEL_FALLBACK, ANTHROPIC_API_KEY, ANTHROPIC_MODEL_FALLBACK
-
-def cohere_chat(prompt: str):
-    if not COHERE_API_KEY: return None
-    c=cohere.Client(COHERE_API_KEY)
-    r=c.chat(model=COHERE_MODEL_PRIMARY, message=prompt, temperature=MODEL_SETTINGS["temperature"])
-    return r.text if hasattr(r,"text") else None
-
-def openai_chat(prompt: str):
-    if not OPENAI_API_KEY: return None
-    openai.api_key=OPENAI_API_KEY
-    r=openai.ChatCompletion.create(model=OPENAI_MODEL_FALLBACK, messages=[{"role":"user","content":prompt}])
-    return r["choices"][0]["message"]["content"]
-
-def anthropic_chat(prompt: str):
-    if not ANTHROPIC_API_KEY: return None
-    a=anthropic.Anthropic(api_key=ANTHROPIC_API_KEY)
-    r=a.messages.create(model=ANTHROPIC_MODEL_FALLBACK, messages=[{"role":"user","content":prompt}])
-    return r.content[0].text
-
-def generate_with_fallback(prompt: str):
-    return cohere_chat(prompt) or openai_chat(prompt) or anthropic_chat(prompt) or ""
+from typing import Optional, List
+import cohere
+from settings import COHERE_API_KEY, COHERE_MODEL_PRIMARY, MODEL_SETTINGS
+from local_llm import LocalLLM
+
+_local = None
+
+def _local_llm() -> LocalLLM:
+    global _local
+    if _local is None:
+        _local = LocalLLM()
+    return _local
+
+def cohere_chat(prompt: str) -> Optional[str]:
+    if not COHERE_API_KEY:
+        return None
+    try:
+        cli = cohere.Client(api_key=COHERE_API_KEY)
+        resp = cli.chat(
+            model=COHERE_MODEL_PRIMARY,
+            message=prompt,
+            temperature=MODEL_SETTINGS["temperature"],
+            max_tokens=MODEL_SETTINGS["max_new_tokens"],
+        )
+        if hasattr(resp, "text") and resp.text: return resp.text
+        if hasattr(resp, "reply") and resp.reply: return resp.reply
+        if hasattr(resp, "generations") and resp.generations: return resp.generations[0].text
+    except Exception:
+        return None
+    return None
+
+def open_fallback_chat(prompt: str) -> Optional[str]:
+    return _local_llm().chat(prompt)
+
+def generate_narrative(scenario_text: str, structured_sections_md: str, rag_snippets: List[str]) -> str:
+    grounding = "\n\n".join([f"[RAG {i+1}]\n{t}" for i, t in enumerate(rag_snippets or [])])
+    prompt = f"""You are a Canadian healthcare operations copilot.
+Follow the scenario's requested deliverables exactly. Use the structured computations provided (already calculated deterministically) and the RAG snippets for grounding.
+
+# Scenario
+{scenario_text}
+
+# Deterministic Results (already computed)
+{structured_sections_md}
+
+# Grounding (Canadian sources, snippets)
+{grounding}
+
+Write a concise, decision-ready report tailored to provincial operations leaders.
+Do not invent numbers. If data are missing, say so clearly.
+"""
+    out = cohere_chat(prompt)
+    if out: return out
+    out = open_fallback_chat(prompt)
+    if out: return out
+    return "Unable to generate narrative at this time."
+