feat: terraform prompt generator, provider parameter matrix, and model penalties

- Add Terraform Prompt Generator: AI-powered structured prompt generation
  with dedicated chat UI, curated model selection (7 models), conversation
  history with persistent sessions, and OCI TF resource reference context
- Provider parameter matrix: segment API params per model/provider,
  explicitly null unsupported params (freq/pres penalty, temperature)
  to prevent OCI SDK serialization errors
- Add penalties flag to model catalog: only GPT-4.1/4.1-mini/4o support
  frequency_penalty and presence_penalty
- Flat workspace enforcement: prohibit module blocks and duplicate
  variable declarations in Terraform system prompt
- Prompt Generator history: sidebar panel with session persistence,
  restore, rename/delete (agent_type tf-prompt)

README.md

@@ -9,7 +9,7 @@
 </p>
 
 <p align="center">
-  <img src="https://img.shields.io/badge/version-2.3-C74634?style=flat-square" alt="Version">
+  <img src="https://img.shields.io/badge/version-2.4-C74634?style=flat-square" alt="Version">
   <img src="https://img.shields.io/badge/python-3.12-3776AB?style=flat-square" alt="Python">
   <img src="https://img.shields.io/badge/FastAPI-0.115-009688?style=flat-square" alt="FastAPI">
   <img src="https://img.shields.io/badge/OCI-GenAI-C74634?style=flat-square" alt="OCI">
@@ -41,7 +41,8 @@ The platform combines security compliance scanning, AI-powered chat with **RAG (
 - 15 chat models + 3 embedding models across 5 providers: **Meta** (Llama 4), **Google** (Gemini 2.5), **OpenAI** (GPT-5.2/5.1/5 Mini/4.1/4o, o3/o4-mini), **xAI** (Grok 4/3)
 - OCID-based model resolution: catalog maps model IDs to OCI resource IDs per region for reliable API calls
 - 16 OCI regions supported with auto-generated endpoints
-- Full parameter control: temperature, max_tokens, top_p, top_k, frequency/presence penalty
+- **Provider parameter matrix**: automatic parameter segmentation per model — reasoning models (o3/o4-mini) only get `max_completion_tokens` + `reasoning_effort`, OpenAI GPT-4.x gets freq/pres penalties, Google/Meta get `top_k`, xAI gets basic params. Unsupported parameters are explicitly nulled to prevent SDK serialization errors
+- Full parameter control: temperature, max_tokens, top_p, top_k, frequency/presence penalty (when supported by model)
 - Toggle MCP tools on/off per chat session
 - Conversation history with session management
 - On-Demand and Dedicated serving modes
@@ -71,6 +72,18 @@ The platform combines security compliance scanning, AI-powered chat with **RAG (
 - **Multi-region provider management**: auto-detects provider aliases and region variables in generated code, generates `provider.tf` with credentials and correct region references (`var.region` instead of hardcoded values)
 - **System prompt sync**: Terraform system prompt in code is automatically synced to DB on every restart — single source of truth
 - Compact system prompt optimized for OCI Terraform provider best practices (100K max_tokens)
+- **Flat workspace enforcement**: system prompt prohibits `module` blocks (workspace has no subdirectories) and enforces single-file variable declarations (`variables.tf` only)
+
+### 📝 Terraform Prompt Generator
+- **AI-powered prompt generation** for OCI infrastructure — generates structured, optimized prompts to feed into the Terraform Agent
+- Dedicated chat interface (sub-menu under Terraform) matching Terraform Agent layout
+- **Curated model selection**: only 7 recommended models (GPT-4.1, o3, o4-mini, GPT-5.1, GPT-5.2, Gemini 2.5 Pro, Gemini 2.5 Flash), grouped by provider
+- **OCI Terraform Resource Reference**: prompt generation includes the full OCI provider resource catalog as context, ensuring accurate resource names and attributes
+- **Conversation history**: persistent sessions (agent_type `tf-prompt`) with sidebar history panel, rename/delete, session restore
+- **Contextual follow-up**: conversation history sent to GenAI for iterative prompt refinement
+- **Copy & Send**: action buttons on assistant messages to copy the prompt or send directly to the Terraform Agent input
+- Robust system prompt with OCI Provider constraints, inference rules, architecture templates, and workspace restrictions
+- Example prompts as clickable buttons for quick start
 
 ### ⚡ OCI Resource Actions
 - **Start/Stop Compute Instances** directly from OCI Account Explorer with one click
@@ -396,14 +409,14 @@ Allow group <group-name> to read buckets in compartment <compartment-name>
 ```
 oci-cis-agent/
 ├── backend/
-│   ├── app.py              # FastAPI application (~5300 lines)
+│   ├── app.py              # FastAPI application (~5500 lines)
 │   ├── cis_reports.py       # Oracle CIS Benchmark checker (6660 lines, report engine)
 │   ├── mcp_cis_server.py    # MCP server with 12 granular CIS tools (~700 lines)
 │   ├── gen_tf_reference.py  # OCI Terraform provider resource catalog generator
 │   ├── Dockerfile           # Python 3.12 + OCI CLI + Terraform CLI
 │   └── requirements.txt     # Dependencies
 ├── frontend/
-│   └── index.html           # SPA with Oracle Dark Premium theme (~2820 lines)
+│   └── index.html           # SPA with Oracle Dark Premium theme (~2950 lines)
 ├── nginx/
 │   └── default.conf         # Reverse proxy config
 ├── docker-compose.yml       # Orchestration
@@ -560,6 +573,7 @@ oci-cis-agent/
 | POST | `/api/terraform/workspaces/{wid}/cancel` | Cancel running Terraform operation |
 | DELETE | `/api/terraform/workspaces/{wid}` | Delete workspace |
 | POST | `/api/terraform/refresh-reference` | Regenerate OCI Terraform resource reference (UI button) |
+| POST | `/api/terraform/generate-prompt` | Generate structured Terraform prompt via AI (Prompt Generator) |
 
 ### Chat & Reports