Commit Graph

5 Commits

Author SHA1 Message Date
Shaun Arman
a04d6fc8f5 fix(security): backend-only PII redaction; fix fmt CI failure
Some checks failed
Test / frontend-typecheck (pull_request) Successful in 1m52s
Test / frontend-tests (pull_request) Successful in 1m51s
Test / rust-fmt-check (pull_request) Failing after 1m58s
Test / rust-clippy (pull_request) Failing after 3m4s
Test / rust-tests (pull_request) Successful in 4m31s
PR Review Automation / review (pull_request) Successful in 4m43s
Resolves all three findings from the second automated review and
fixes the cargo fmt --check CI failure (formatting drift in analysis.rs
from a prior merge).

[BLOCKER 1 + BLOCKER 2 + WARNING]
Frontend no longer performs any PII scanning or redaction. All three
concerns stemmed from the same root cause: outMessage was derived
on the frontend and used for display, DB storage (via lastUserMsgRef
and the chat bubble), and the AI payload — causing the original message
to be silently replaced before the backend received it.

Fix: frontend sends the original message verbatim. Backend is now the
sole authority. chat_message auto-redacts the typed message text using
PiiDetector + apply_redactions() before building the full payload, logs
the PII types via tracing::warn, and stores only the redacted form in
ai_messages and the audit log. The redacted form is returned to the
caller as ChatResponse.user_message (Option<String>, absent from direct
provider calls).

Frontend uses message (original) for the chat bubble and
lastUserMsgRef — resolution steps show natural language, not
[Password] tokens. The AI and DB see only the redacted version.

CI fix: cargo fmt applied to analysis.rs; all format checks now pass.
2026-05-31 19:36:44 -05:00
Shaun Arman
9e8db9dc81 feat(ai): add tool-calling and integration search as AI data source
This commit implements two major features:

1. Integration Search as Primary AI Data Source
   - Confluence, ServiceNow, and Azure DevOps searches execute before AI queries
   - Search results injected as system context for AI providers
   - Parallel search execution for performance
   - Webview-based fetch for HttpOnly cookie support
   - Persistent browser windows maintain authenticated sessions

2. AI Tool-Calling (Function Calling)
   - Allows AI to automatically execute functions during conversation
   - Implemented for OpenAI-compatible providers and Custom REST provider
   - Created add_ado_comment tool for updating Azure DevOps tickets
   - Iterative tool-calling loop supports multi-step workflows
   - Extensible architecture for adding new tools

Key Files:
- src-tauri/src/ai/tools.rs (NEW) - Tool definitions
- src-tauri/src/integrations/*_search.rs (NEW) - Integration search modules
- src-tauri/src/integrations/webview_fetch.rs (NEW) - HttpOnly cookie workaround
- src-tauri/src/commands/ai.rs - Tool execution and integration search
- src-tauri/src/ai/openai.rs - Tool-calling for OpenAI and Custom REST provider
- All providers updated with tools parameter support

Co-Authored-By: Claude Sonnet 4.5 <noreply@anthropic.com>
2026-04-07 09:35:34 -05:00
Shaun Arman
281e676ad1 fix(security): harden secret handling and audit integrity
Remove high-risk defaults and tighten data handling across auth, storage, IPC, provider calls, and capabilities so sensitive data is better protected by default. Also update README/wiki security guidance and add targeted tests for the new hardening behaviors.

Made-with: Cursor
2026-04-04 23:37:05 -05:00
Shaun Arman
808500b7bd fix: inline format args for Rust 1.88 clippy compatibility 2026-03-15 13:28:59 -05:00
Shaun Arman
8839075805 feat: initial implementation of TFTSR IT Triage & RCA application
Implements Phases 1-8 of the TFTSR implementation plan.

Rust backend (Tauri 2.x, src-tauri/):
- Multi-provider AI: OpenAI-compatible, Anthropic, Gemini, Mistral, Ollama
- PII detection engine: 11 regex patterns with overlap resolution
- SQLCipher AES-256 encrypted database with 10 versioned migrations
- 28 Tauri IPC commands for triage, analysis, document, and system ops
- Ollama: hardware probe, model recommendations, pull/delete with events
- RCA and blameless post-mortem Markdown document generators
- PDF export via printpdf
- Audit log: SHA-256 hash of every external data send
- Integration stubs for Confluence, ServiceNow, Azure DevOps (v0.2)

Frontend (React 18 + TypeScript + Vite, src/):
- 9 pages: full triage workflow NewIssue→LogUpload→Triage→Resolution→RCA→Postmortem→History+Settings
- 7 components: ChatWindow, TriageProgress, PiiDiffViewer, DocEditor, HardwareReport, ModelSelector, UI primitives
- 3 Zustand stores: session, settings (persisted), history
- Type-safe tauriCommands.ts matching Rust backend types exactly
- 8 IT domain system prompts (Linux, Windows, Network, K8s, DB, Virt, HW, Obs)

DevOps:
- .woodpecker/test.yml: rustfmt, clippy, cargo test, tsc, vitest on every push
- .woodpecker/release.yml: linux/amd64 + linux/arm64 builds, Gogs release upload

Verified:
- cargo check: zero errors
- tsc --noEmit: zero errors
- vitest run: 13/13 unit tests passing

Co-Authored-By: Claude Sonnet 4.6 (1M context) <noreply@anthropic.com>
2026-03-14 22:36:25 -05:00