docs(e2e): document live infrastructure verification report and update README

.env.example

@@ -14,7 +14,7 @@ REDIS_URL=redis://localhost:6379/0
 # LLM Provider Configuration
 # Supported providers: "gemini", "openai", "fake"
 LLM_PROVIDER=gemini
-LLM_MODEL=gemini-3.8-flash
+LLM_MODEL=gemini-3.1-flash-lite
 GEMINI_API_KEY=your_gemini_api_key_here
 OPENAI_API_KEY=your_openai_api_key_here
 

README.md

@@ -102,7 +102,7 @@ Edit `.env`:
 ```ini
 # LLM Providers (at least one key or use offline mode)
 LLM_PROVIDER=gemini
-LLM_MODEL=gemini-2.0-flash
+LLM_MODEL=gemini-3.1-flash-lite
 GEMINI_API_KEY=your_gemini_api_key_here
 OPENAI_API_KEY=your_openai_api_key_here
 
@@ -352,6 +352,10 @@ All pull requests trigger GitHub Actions with three jobs: `Lint & Type Check`; a
 `Test Against Live PostgreSQL and Redis`, which runs the `real_infra` tier against real
 PostgreSQL 16 and Redis 7 service containers.
 
+### Live Infrastructure Verification Report
+
+All core agent capabilities, multi-step PostgreSQL queries, AST calculators, security defenses (SQL injection, path traversal), and rate limiters have been validated end-to-end against live PostgreSQL, Redis, and Google Gemini API in Docker Compose. See the full audit telemetry and verbatim command logs in [docs/E2E_REPORT.md](docs/E2E_REPORT.md).
+
 ---
 
 ## Limitations & Future Roadmap

agentkit/config.py

@@ -32,7 +32,7 @@ class Settings(BaseSettings):
         description="LLM provider: gemini, openai, or fake.",
     )
     LLM_MODEL: str = Field(
-        default="gemini-3.8-flash",
+        default="gemini-3.1-flash-lite",
         description="LLM model identifier.",
     )
     GEMINI_API_KEY: str | None = Field(

agentkit/llm/factory.py

@@ -38,7 +38,7 @@ def create_llm_client(
     normalized_provider = provider.strip().lower()
 
     if normalized_provider == "gemini":
-        default_model = model or "gemini-3.8-flash"
+        default_model = model or "gemini-3.1-flash-lite"
         return GeminiClient(api_key=api_key, model=default_model, **kwargs)
 
     if normalized_provider == "openai":

agentkit/llm/gemini.py

@@ -18,14 +18,14 @@ class GeminiClient(LLMClient):
     def __init__(
         self,
         api_key: str | None = None,
-        model: str = "gemini-3.8-flash",
+        model: str = "gemini-3.1-flash-lite",
         client: Any | None = None,
     ) -> None:
         """Initialize the Gemini client adapter.
 
         Args:
             api_key: Gemini API key. If omitted, google-genai attempts ADC/env lookup.
-            model: Gemini model identifier (default: gemini-3.8-flash).
+            model: Gemini model identifier (default: gemini-3.1-flash-lite).
             client: Optional pre-configured genai.Client instance (useful for mocking).
         """
         self.model = model

docker-compose.yml

@@ -77,7 +77,7 @@ services:
       # Compose keeps ${VAR:-} so `down`, `ps` and `logs` still work without it.
       - API_KEYS=${API_KEYS:-}
       - LLM_PROVIDER=${LLM_PROVIDER:-gemini}
-      - LLM_MODEL=${LLM_MODEL:-gemini-3.8-flash}
+      - LLM_MODEL=${LLM_MODEL:-gemini-3.1-flash-lite}
       - GEMINI_API_KEY=${GEMINI_API_KEY:-}
       - OPENAI_API_KEY=${OPENAI_API_KEY:-}
     volumes: