Merge branch 'main' into docs-fix-model-ids

docs/guides/graphrag.md

@@ -195,7 +195,7 @@ apt29_intel = context.retrieve(
 ```python
 from semantica.llms import LiteLLM
 
-llm = LiteLLM(model="anthropic/claude-sonnet-4-20250514")
+llm = LiteLLM(model="anthropic/claude-sonnet-5")
 
 result = context.query_with_reasoning(
     "What are APT29's known TTPs against healthcare infrastructure, "
@@ -281,7 +281,7 @@ context.store(
     link_entities=True,
 )
 
-llm    = LiteLLM(model="anthropic/claude-sonnet-4-20250514")
+llm    = LiteLLM(model="anthropic/claude-sonnet-5")
 result = context.query_with_reasoning(
     "Trace the C2 infrastructure chain for APT29 operations targeting "
     "ITAR-controlled contractors in 2025. Include IP ranges, ASNs, and TTPs.",
@@ -351,7 +351,7 @@ Parent: wmiprvse.exe
 Sigma match: T1053.005 Scheduled Task/Job
 """
 
-llm    = LiteLLM(model="anthropic/claude-sonnet-4-20250514")
+llm    = LiteLLM(model="anthropic/claude-sonnet-5")
 triage = soc_context.query_with_reasoning(
     "Triage this SIEM alert and identify the correct response runbook:\n{}".format(alert_text),
     llm_provider=llm,
@@ -425,7 +425,7 @@ Patient: 68F, AF, CKD stage 3b (eGFR 32). On warfarin (INR target 2.0–3.0).
 Presenting for elective hip replacement. Concurrent: amiodarone 200mg, atorvastatin 40mg.
 """
 
-llm    = LiteLLM(model="anthropic/claude-sonnet-4-20250514")
+llm    = LiteLLM(model="anthropic/claude-sonnet-5")
 answer = clinical_context.query_with_reasoning(
     "What is the evidence-based warfarin bridging protocol for this patient "
     "given CKD and amiodarone interaction risk?\n\n{}".format(patient_context),
@@ -495,7 +495,7 @@ compliance_context.store(
     extract_relationships=True,
 )
 
-llm    = LiteLLM(model="anthropic/claude-sonnet-4-20250514")
+llm    = LiteLLM(model="anthropic/claude-sonnet-5")
 answer = compliance_context.query_with_reasoning(
     "Under Basel III CRE20, what are the RWA calculation requirements for "
     "commercial real estate exposures with LTV > 80%? "

docs/guides/llm-integrations.md

@@ -275,20 +275,20 @@ print(data)
 
 **LiteLLM** is a universal adapter that provides a single interface to over 100 different LLM providers, including Anthropic Claude, Azure OpenAI, AWS Bedrock, Google Vertex AI, and local Ollama instances. It acts as a translation layer, converting your unified API calls into provider-specific requests, enabling easy switching between providers without code changes.
 
-`LiteLLM` is the Swiss Army knife. It wraps the `litellm` library, which speaks to every major provider using a unified completion API. The model string encodes both provider and model name: `"anthropic/claude-sonnet-4-20250514"`, `"azure/gpt-4o"`, `"bedrock/anthropic.claude-3-5-sonnet-20241022-v2:0"`, `"ollama/llama3.2"`. Change the string, change the provider — no other code changes needed.
+`LiteLLM` is the Swiss Army knife. It wraps the `litellm` library, which speaks to every major provider using a unified completion API. The model string encodes both provider and model name: `"anthropic/claude-sonnet-5"`, `"azure/gpt-4o"`, `"bedrock/anthropic.claude-sonnet-4-5-20250929-v1:0"`, `"ollama/llama3.2"`. Change the string, change the provider — no other code changes needed.
 
 ```python
 from semantica.llms import LiteLLM
 
 # Anthropic Claude — highest accuracy for complex reasoning
-llm = LiteLLM(model="anthropic/claude-sonnet-4-20250514")
+llm = LiteLLM(model="anthropic/claude-sonnet-5")
 # Reads ANTHROPIC_API_KEY from environment
 
 # Azure OpenAI — compliance and data-residency requirements
 llm = LiteLLM(model="azure/gpt-4o", api_key="YOUR_AZURE_KEY")
 
 # AWS Bedrock — existing cloud agreement, no new vendor
-llm = LiteLLM(model="bedrock/anthropic.claude-3-5-sonnet-20241022-v2:0")
+llm = LiteLLM(model="bedrock/anthropic.claude-sonnet-4-5-20250929-v1:0")
 
 # Google Vertex AI
 llm = LiteLLM(model="vertex_ai/gemini-1.5-pro")
@@ -306,7 +306,7 @@ The environment-variable convention for each provider: `ANTHROPIC_API_KEY`, `AZU
 import os
 
 PROVIDER_MAP = {
-    "prod":    "anthropic/claude-sonnet-4-20250514",
+    "prod":    "anthropic/claude-sonnet-5",
     "staging": "openai/gpt-4o-mini",
     "local":   "ollama/llama3.2",
     "azure":   "azure/gpt-4o",
@@ -378,7 +378,7 @@ print("FAST: {}  (conf={:.0%})".format(fast_result["response"], fast_result["con
 
 # Tier 2: deep answer with Claude if confidence is below threshold
 if fast_result["confidence"] < 0.85:
-    deep_llm = LiteLLM(model="anthropic/claude-sonnet-4-20250514")
+    deep_llm = LiteLLM(model="anthropic/claude-sonnet-5")
     deep_result = context.query_with_reasoning(
         query, llm_provider=deep_llm, max_results=15, max_hops=3
     )
@@ -574,7 +574,7 @@ print("TRIAGE: {} (conf={:.0%})".format(triage["response"], triage["confidence"]
 
 # Tier 2: escalate to Claude for deep analysis if Tier 1 is uncertain
 if triage["confidence"] < 0.88:
-    deep_llm = LiteLLM(model="anthropic/claude-sonnet-4-20250514")
+    deep_llm = LiteLLM(model="anthropic/claude-sonnet-5")
     deep = context.query_with_reasoning(
         "Full MITRE ATT&CK analysis of this alert: identify the attack chain, "
         "blast radius, affected systems, and recommended containment steps.",
@@ -630,7 +630,7 @@ for d in drugs:
 # trastuzumab (conf=0.98), pertuzumab (conf=0.97), docetaxel (conf=0.96)
 
 # Report synthesis with Claude — switch to azure/gpt-4o for HIPAA by changing one string
-report_llm = LiteLLM(model="anthropic/claude-sonnet-4-20250514")
+report_llm = LiteLLM(model="anthropic/claude-sonnet-5")
 # For HIPAA-constrained Azure deployment:
 # report_llm = LiteLLM(model="azure/gpt-4o", api_key="YOUR_AZURE_KEY")
 
@@ -682,7 +682,7 @@ question = (
 
 # Two-provider consensus — same query, same graph, different LLMs
 gpt4o  = OpenAI(model="gpt-4o", api_key="YOUR_OAI_KEY")
-claude = LiteLLM(model="anthropic/claude-sonnet-4-20250514")
+claude = LiteLLM(model="anthropic/claude-sonnet-5")
 
 answer_a = context.query_with_reasoning(question, llm_provider=gpt4o,  max_results=10)
 answer_b = context.query_with_reasoning(question, llm_provider=claude, max_results=10)

docs/guides/multi-agent.md

@@ -197,7 +197,7 @@ reasoning_agent.load("./pipeline/enriched_intel/")
 # All memories, graph nodes, and vector embeddings from both ingestion agents are now available.
 
 # Use a high-capability model for the synthesis step
-llm = LiteLLM(model="anthropic/claude-sonnet-4-20250514")
+llm = LiteLLM(model="anthropic/claude-sonnet-5")
 
 synthesis = reasoning_agent.query_with_reasoning(
     "Summarize the APT29 exploitation of CVE-2024-3400: affected products, "
@@ -428,7 +428,7 @@ tier1.store(
 
 # --- Tier 2: deep investigation when Tier 1 confidence is low ---
 if triage["confidence"] < 0.90:
-    deep_llm = LiteLLM(model="anthropic/claude-sonnet-4-20250514")
+    deep_llm = LiteLLM(model="anthropic/claude-sonnet-5")
 
     investigation = tier2.query_with_reasoning(
         "Full MITRE ATT&CK analysis of incident {}. "
@@ -533,7 +533,7 @@ t1.start(); t2.start()
 t1.join();  t2.join()
 
 # Chief agent synthesizes across literature and experimental data
-llm = LiteLLM(model="anthropic/claude-sonnet-4-20250514")
+llm = LiteLLM(model="anthropic/claude-sonnet-5")
 
 synthesis = chief.query_with_reasoning(
     "Identify the top two candidate compounds for KRAS G12C NSCLC that show "
@@ -576,7 +576,7 @@ credit_officer  = make_desk_agent()
 committee_chair = make_desk_agent()
 
 app_id = "LOAN-2025-88421"
-llm    = LiteLLM(model="anthropic/claude-sonnet-4-20250514")
+llm    = LiteLLM(model="anthropic/claude-sonnet-5")
 
 # --- Risk Desk: PD/LGD/EL analysis ---
 risk_desk.store(

docs/guides/ontology.md

@@ -477,7 +477,7 @@ regs = [
 ]
 
 # Use an LLM to extract the conceptual model from regulatory prose
-llm_gen  = LLMOntologyGenerator(provider="anthropic", model="claude-sonnet-4-20250514")
+llm_gen  = LLMOntologyGenerator(provider="anthropic", model="claude-sonnet-5")
 ontology = llm_gen.generate_ontology_from_text(
     "\n\n".join(r.text[:8000] for r in regs)  # token-safe excerpt per document
 )

docs/reference/llms.md

@@ -129,7 +129,7 @@ from semantica.llms import Groq, OpenAI, LiteLLM, HuggingFaceLLM
     from semantica.llms import LiteLLM
 
     llm = LiteLLM(
-        model="anthropic/claude-sonnet-4-20250514",
+        model="anthropic/claude-sonnet-5",
         api_key=os.getenv("ANTHROPIC_API_KEY"),
         temperature=0.0,
     )
@@ -198,7 +198,7 @@ llm = Groq(api_key=os.getenv("GROQ_API_KEY"), model="llama-3.1-8b-instant")
 # Method 3: Multiple providers via LiteLLM
 providers = {
     "fast": LiteLLM(model="groq/llama-3.1-8b-instant", api_key=os.getenv("GROQ_API_KEY")),
-    "smart": LiteLLM(model="anthropic/claude-sonnet-4-20250514", api_key=os.getenv("ANTHROPIC_API_KEY"))
+    "smart": LiteLLM(model="anthropic/claude-sonnet-5", api_key=os.getenv("ANTHROPIC_API_KEY"))
 }
 ```
 
@@ -252,7 +252,7 @@ from semantica.llms import LiteLLM
 # pip install "semantica[llm-litellm]"
 
 # Anthropic Claude
-llm = LiteLLM(model="anthropic/claude-opus-4-5",         api_key=os.getenv("ANTHROPIC_API_KEY"))
+llm = LiteLLM(model="anthropic/claude-opus-4-7",         api_key=os.getenv("ANTHROPIC_API_KEY"))
 
 # Google Gemini
 llm = LiteLLM(model="gemini/gemini-1.5-pro",             api_key=os.getenv("GOOGLE_API_KEY"))
@@ -267,7 +267,7 @@ llm = LiteLLM(model="deepseek/deepseek-chat",            api_key=os.getenv("DEEP
 llm = LiteLLM(model="azure/gpt-4o",                      api_key=os.getenv("AZURE_API_KEY"))
 
 # AWS Bedrock
-llm = LiteLLM(model="bedrock/anthropic.claude-3-5-sonnet-20241022-v2:0")
+llm = LiteLLM(model="bedrock/anthropic.claude-sonnet-4-5-20250929-v1:0")
 
 # Novita AI
 llm = LiteLLM(model="novita/deepseek/deepseek-v3.2",     api_key=os.getenv("NOVITA_API_KEY"))
@@ -297,12 +297,12 @@ from semantica.llms import LiteLLM
 
 # Pattern: LiteLLM(model="<provider>/<model-name>")
 providers = {
-    "Anthropic":  LiteLLM(model="anthropic/claude-opus-4-5",       api_key=os.getenv("ANTHROPIC_API_KEY")),
+    "Anthropic":  LiteLLM(model="anthropic/claude-opus-4-7",       api_key=os.getenv("ANTHROPIC_API_KEY")),
     "Gemini":     LiteLLM(model="gemini/gemini-1.5-pro",            api_key=os.getenv("GOOGLE_API_KEY")),
     "Ollama":     LiteLLM(model="ollama/llama3.2:3b",               api_base="http://localhost:11434"),
     "DeepSeek":   LiteLLM(model="deepseek/deepseek-chat",           api_key=os.getenv("DEEPSEEK_API_KEY")),
     "Azure":      LiteLLM(model="azure/gpt-4o",                     api_key=os.getenv("AZURE_API_KEY")),
-    "Bedrock":    LiteLLM(model="bedrock/anthropic.claude-3-5-sonnet-20241022-v2:0"),
+    "Bedrock":    LiteLLM(model="bedrock/anthropic.claude-sonnet-4-5-20250929-v1:0"),
     "Cohere":     LiteLLM(model="cohere/command-r-plus",            api_key=os.getenv("COHERE_API_KEY")),
     "Novita AI":  LiteLLM(model="novita/deepseek/deepseek-v3.2",    api_key=os.getenv("NOVITA_API_KEY")),
 }
@@ -416,7 +416,7 @@ for text in texts:
 | :---------- | :--------------------------- | :----------- |
 | **Entity Extraction** | `Groq("llama-3.3-70b-versatile")` | Fast, good accuracy for structured tasks |
 | **Relation Extraction** | `OpenAI("gpt-4o")` | Best at complex relationship reasoning |
-| **Complex Analysis** | `LiteLLM("anthropic/claude-sonnet-4-20250514")` | Highest reasoning capability |
+| **Complex Analysis** | `LiteLLM("anthropic/claude-sonnet-5")` | Highest reasoning capability |
 | **High Volume/Cost** | `LiteLLM("deepseek/deepseek-chat")` | Lowest cost per token |
 
 ### Error Handling

semantica/llms/__init__.py

@@ -35,7 +35,7 @@ Example Usage:
     >>> llm = LiteLLM(model="openai/gpt-4o", api_key="your-key")
     >>> response = llm.generate("Hello, world!")
     >>> # Or use other providers via LiteLLM
-    >>> llm = LiteLLM(model="anthropic/claude-sonnet-4-20250514")
+    >>> llm = LiteLLM(model="anthropic/claude-sonnet-5")
     >>> response = llm.generate("Hello, world!")
     >>>
     >>> # Anthropic provider

semantica/llms/litellm.py

@@ -31,7 +31,7 @@ class LiteLLM:
     Provides unified interface to 100+ LLM providers through LiteLLM library.
     Supports providers like OpenAI, Anthropic, Groq, Azure, Bedrock, Vertex AI, etc.
     
-    Model format: "provider/model-name" (e.g., "openai/gpt-4o", "anthropic/claude-sonnet-4-20250514", "groq/llama-3.1-8b-instant")
+    Model format: "provider/model-name" (e.g., "openai/gpt-4o", "anthropic/claude-sonnet-5", "groq/llama-3.1-8b-instant")
     
     Example:
         >>> from semantica.llms import LiteLLM
@@ -39,7 +39,7 @@ class LiteLLM:
         >>> response = llm.generate("What is AI?")
         >>> 
         >>> # Use with different providers
-        >>> llm = LiteLLM(model="anthropic/claude-sonnet-4-20250514")
+        >>> llm = LiteLLM(model="anthropic/claude-sonnet-5")
         >>> response = llm.generate("Hello!")
     """
 
@@ -54,7 +54,7 @@ class LiteLLM:
 
         Args:
             model: Model identifier in format "provider/model-name"
-                   Examples: "openai/gpt-4o", "anthropic/claude-sonnet-4-20250514",
+                   Examples: "openai/gpt-4o", "anthropic/claude-sonnet-5",
                              "groq/llama-3.1-8b-instant", "azure/gpt-4", etc.
             api_key: API key (optional, can use environment variables)
             **kwargs: Additional LiteLLM options (temperature, max_tokens, etc.)