- Official resource docs injection from registry.terraform.io (on-demand fetch + SQLite cache)
- Smart tfvars auto-generation from declared variables (tenancy_ocid, user_ocid, etc.)
- Multi-region provider: use var.region instead of hardcoded OCI config region
- RPC anti-cycle rule in system prompt
- System prompt auto-sync to DB on restart
- Fix UI flickering: animations scoped to tab switch only (tab-enter class)
- Terraform polling timeout increased to 60 min
- Terminal output updates without full page re-render
- Fix ${IC.bot} literal rendering in chat empty state
- Chat empty state icon scaled to 48px
- README updated to v2.2 with all changes
- Add light/dark mode toggle with localStorage persistence
- Oracle-branded dark mode: deep backgrounds, vibrant status colors
- Original light mode preserved as default
- All hardcoded colors replaced with CSS custom properties
- Add full config export/import (OCI creds+keys, GenAI, MCP, prompts, settings)
- Add Terraform inline prompt editor with auto-save
- Add ADB Update Network Access and ACL display in Explorer
- Add auto-refresh after Start/Stop resource actions
- Update README with new features
- Add export/import endpoints for full config backup (OCI, GenAI, MCP, prompts, settings, ADB)
- Export includes private keys (base64) for complete environment migration
- Import merges by ID (skips existing, no duplicates)
- Fix Resource Plan parser to recognize free-form format (model skips ```plan blocks)
- Fix replan not clearing previous apply/destroy outputs
- Fix duplicate CIS Compliance Scanner MCP server on multi-worker startup
- Add Terraform prompt editor with auto-save in menu
- Add Update Network Access endpoint and UI for ADB ACL management
- Add inline prompt editor with auto-save in Terraform agent menu
- Persist resize bar positions across re-renders (Explorer + Terraform)
- Restore full Terraform session state from history (files, plan, outputs, OCI config)
- Parse free-form Resource Plan format (model often skips ```plan blocks)
- Auto-refresh resource state after Start/Stop actions
- Clear previous apply/destroy outputs on Re-plan
- Deduplicate CIS Compliance Scanner MCP server on startup
- Show ACL IPs in Explorer for Autonomous Databases
- Detect user IP via /api/oci/my-ip endpoint
- Add SQLite-based resource type validation with suggestions for invalid types
- Increase Terraform max_tokens from 32K to 100K for large infra generation
- Generate resource reference at startup to survive volume mount overwrites
- Add invalid resource type examples to system prompt (RPC peer, subnet route table)
- Add prompt size logging for Terraform agent
- Translate remaining Portuguese code comment to English
- Add 3-layer protection pipeline for model-generated Terraform code:
1. Frontend auto-split: splits monolithic HCL into multiple files by resource type
2. Backend auto-split: Python port as last defense before writing to disk
3. Backend deduplication: removes monolithic leftovers with duplicate resources
- Fix single-line block expansion to handle ALL HCL blocks (nested included):
ingress_security_rules, egress_security_rules, route_rules, match_criteria, etc.
- Add prompt size logging for terraform agent diagnostics
- Strengthen system prompt: minimum 3 files, final reminder section
Always declare variable "region", remove invalid resource types with
correct alternatives, and ensure RPC dependencies exist on both sides
before peering.
Ensure subnets always reference valid route tables, DRG attachments
point to existing resources, and RPC peering has correct peer_id
and peer_region_name configuration.
Cross-references, CIDRs, security lists, route tables, dependencies,
resource type names, valid arguments, and variable declarations must
all be verified before the model delivers any code.
- fmTf now merges new code blocks with existing S.tfFiles: updated files
are replaced by name, untouched files are preserved, new files are added
- System prompt changed: model generates ONLY the files that need fixing
instead of all 25 files, drastically reducing output size
- Prevents model from discarding existing work when correcting errors
- Inject existing workspace files + plan/apply output into Terraform chat
context so model corrects in-place instead of regenerating from scratch
- Add "REGRA CRÍTICA: Correção de Arquivos Existentes" to system prompt
requiring the model to preserve file structure and fix surgically
- Increase Terraform Agent max_tokens from 16K to 32K
- Remove "Nova conversa" button from Terraform toolbar
- Move Start/Stop Instance and ADB buttons from Terraform Resources
panel to OCI Account Explorer (instances and databases tabs)
- Remove unused _ociResOid helper and old action functions
Change the system prompt from "single file by default" to "multiple files
by default" organized by function (variables.tf, networking.tf, compute.tf,
etc.), which was causing the model to only generate 1-2 files.
- Add dropdown menu (⋮) in Terraform toolbar with "Atualizar Referência TF" button
- Remove standalone reference-status API endpoint, keep only refresh-reference
- Button triggers `terraform providers schema -json` regeneration with progress feedback
- Shows line count and update timestamp after successful refresh
- Update README with new line counts
- Add gen_tf_reference.py to generate OCI Terraform provider resource catalog (~937 resources) from `terraform providers schema -json`
- Auto-inject categorized resource reference into Terraform Agent system prompt to prevent invalid resource type names
- Build-time reference generation in Dockerfile, refreshable via POST /api/terraform/refresh-reference
- Provider alias detection with brace-matching parser for multi-region deployments
- Clean old .tf files before writing new ones on Re-plan
- Message timestamps in terraform chat and history
- Partial DOM rendering to eliminate screen flickering
- Layout overflow fix (no scroll beyond viewport)
Replace button-based file layout with a clean list view featuring colored
file-type badges (HTML/CSV/JSON/XLSX), formatted sizes, download icons,
hover highlights, and category headers with emoji icons. Collapsible
report cards now show file count and use chevron rotation animation.
Add Terraform Agent tab with AI-powered IaC generation (plan/apply/destroy lifecycle,
workspace management, compartment selection, Terraform CLI v1.7.5 in container).
Expand OCI Explorer from 6 to 40+ resource types across 8 categories with tree-view
navigation and resizable panels. Add compartment filtering and error tracking to MCP
CIS server, increase tool timeout to 30min with auto-retry. Add chat sidebar, chat
audit logs, and tune memory compaction (6K threshold, 20 recent messages). Trim model
catalog from 69 to 15 curated models. Update README for v2.1.
Keep only the best model per provider family (Meta, Google, OpenAI, xAI).
Remove Codex variants, Image/Audio/Search models, ProtectAI, and redundant
versions. GPT-4.1 is now pre-selected when creating a new GenAI config.
Async chat processing eliminates 504 timeouts - POST returns immediately,
backend processes in background, frontend polls for results with timestamps.
Scale to ~12 simultaneous chats via 8 uvicorn workers + 16-thread executor.
Parallelized MCP data collection, 2h session cache, 5min tool timeout.
Full dead code cleanup across backend, frontend, MCP, docker, and nginx.
Add image/PDF/text file upload in chat via new /api/chat/upload endpoint
with OCI GenAI ImageContent and DocumentContent support. Frontend shows
attach button, file preview, and handles multipart upload seamlessly.
Add optional regions parameter to all CIS MCP scan tools for targeting
specific OCI regions instead of full tenancy. Session cache scoped by
config+regions for concurrent multi-region scans.
Add orphaned report auto-detection on progress poll (marks as failed if
process not found). Increase nginx proxy timeout to 15 minutes. Improve
$api error handling for non-JSON responses (504 HTML pages).
Update README to v1.9.
Move report history/status table to Reports tab. Simplify Downloads tab
to show only completed reports with expandable file browser grouped by
category. Add CIS Level description tooltip and fix log expand persisting
during report generation polling.
Replace lightweight cis_runner.py with Oracle's official cis_reports.py engine
(6660 lines, 48 CIS + 11 OBP checks). Add granular execution parameters (Level,
OBP, Raw Data, Redact), per-report file storage with category browser, tenancy
filter in Downloads, and individual file download.
Add CIS Engine auto-update: check/download latest cis_reports.py from Oracle's
GitHub repo with automatic patch reapplication (admin UI card + 3 new endpoints).
Save engine version to app_settings on startup.
Update README to v1.8 with new features, API endpoints, and versioning table.
GPT-5.2 Pro and its dated variant only support the Responses API,
not Chat Completions. OCI GenAI uses chat/completions internally,
causing a 400 error. Also trim debug log to a shorter format.
Custom dropdown with search filter and max-height scroll (220px).
Models grouped by provider with sticky group headers. Click outside
to close. Handles 60+ models without overwhelming the UI.
Remove temperature, max_tokens, top_p, top_k, frequency/presence
penalty fields from the GenAI Config tab. That tab is now focused
on adding custom models not in the catalog.
Parameters are now managed exclusively in the Chat tab via the
collapsible gear panel, available for both direct models and saved
configs. Inline params override stored defaults when using presets.
Users can now pick any model from the full catalog directly in the Chat
tab using optgroups by provider (OpenAI, Google, Meta, Cohere, xAI),
without needing to pre-configure it in GenAI Config. OCI credentials,
region, and compartment auto-fill from the selected credential.
A collapsible parameters panel (temperature, max_tokens, top_p, top_k,
frequency/presence penalty) is available via the gear icon.
Saved GenAI configs still appear at the top of the dropdown as presets.
OpenAI models reject 'max_tokens' and require 'max_completion_tokens'.
Also skip 'top_k' for OpenAI as it is unsupported. Detection is based
on the provider field in the model catalog.
Models like OpenAI GPT-5.2 require the full OCID rather than the short
model_id. The catalog now maps model IDs to OCIDs per region (us-ashburn-1).
_call_genai and _embed_text resolve the OCID for the configured region
at runtime, falling back to short model_id for unmapped regions.
New models added from OCI portal: GPT-5.3/5.2/5.1/5 Codex, GPT Image
1/1.5, Llama Guard 4, ProtectAI DeBERTa, OpenAI Text Embedding 3
Large/Small. Total: 69 chat + 11 embedding models.
Add all models available in OCI GenAI Ashburn region including
OpenAI GPT-5.2/5.1/5/4.1/4o, o1/o3/o4-mini, GPT Audio,
xAI Grok 4.1/4 reasoning/non-reasoning variants, and update
README with complete model table and Model IDs.
- Add "Personalizado (usar OCID)" option in model select dropdown
- Validate OCID is required when custom model is selected
- Improve Model OCID field hint text explaining portal usage
- Show "OCID Personalizado" label in config table for custom models
- Allows using any OCI GenAI model via OCID from the portal
