Add was_pii_redacted and pii_types_redacted to the ai_chat audit log
entry. Both are tracked through the full_message build block (typed
message + attachments) so any redaction that occurs is always
reflected in the compliance record.
Fix response.user_message + suffix potentially yielding 'undefined...'
when user_message is absent. Now unconditionally calls
updateMessageContent with (response.user_message ?? message) + suffix,
so the bubble always shows a valid string regardless of backend build.
Update TICKET-pii-bypass-chat-attachments.md to reflect the final
auto-redact design (not block/warn) so automated review comparisons
against the ticket stop flagging design decisions as defects.
Remove frontend detectPiiCmd pre-scan loop — backend is sole redaction
authority; bubble update via response.user_message covers user feedback.
Detect PII on full file content before truncating. Previous order
(truncate to 8000 bytes then scan) could miss PII straddling the
boundary. Now: read full content, scan, redact, then truncate to
EMBED_LIMIT (8000 bytes) at a valid UTF-8 char boundary.
logFileIds IPC: pass undefined (not null) for empty array so Tauri
serialises it correctly to Rust Option::None.
Add MAX_TEXT_SCAN_BYTES (32 KB) guard in scan_text_for_pii to prevent
unbounded regex evaluation on oversized payloads.
Fix clippy uninlined_format_args in ai.rs.
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.
Resolves all four findings from the automated review:
[BLOCKER 1] Attachment PII scan error path left pendingFiles intact,
allowing retry with stale file references. Fix: file content is no
longer held in frontend state at all — PendingFile drops the content
field entirely. logFileIds are captured before setPendingFiles([]) and
passed directly to the backend.
[BLOCKER 2] Raw file content stored in PendingFile.content created a
UI-visible PII surface and a data-residency risk. Fix: frontend never
reads or stores file content. The backend loads file data from disk,
auto-redacts PII in-memory using pii::apply_redactions(), and embeds
the clean text into the AI message. No PII ever touches the frontend.
[WARNING 1] String-based attachment header parsing was fragile and
bypassable. Fix: parsing is gone — backend identifies attachments by
log_file_id, reads them directly from the DB/disk path, and applies
redaction at that level.
[WARNING 2] Error message disclosed PII type list to the caller. Fix:
PII types are logged via tracing::warn only; no type details in the
user-facing error or API response.
Additionally: typed chat messages are now auto-redacted rather than
blocked. scanTextForPiiCmd runs on the typed text; detected spans are
replaced in reverse-offset order before the message is sent to the AI
and stored in the DB. The user sees the redacted form in their chat
bubble.
Architecture:
- chat_message now accepts log_file_ids: Option<Vec<String>>
- Backend reads file → detects PII → redacts in memory → embeds
- Frontend: no readTextFile, no content field, no frontend PII gate
File attachments were embedded into AI messages without any PII
scanning, allowing credentials, tokens, and other sensitive data
to be forwarded to AI providers in plaintext.
Typed chat messages had the same gap: a user could type a password
or API key directly and it would be sent unscanned.
Changes:
- chat_message (Rust): defence-in-depth scan of all attachment body
content (between --- Attached: markers); hard rejects if PII found
- detect_pii (Rust): fix return type from pii::PiiDetectionResult
(spans/original_text) to db::models::PiiDetectionResult
(detections/total_pii_found) to match the TypeScript contract; the
LogUpload PII review workflow was receiving undefined for detections
- scan_text_for_pii (Rust): new command — scans arbitrary text for PII
without creating DB records; used for typed message warnings
- Triage/index.tsx: PendingFile now carries logFileId; handleSend gates
each text attachment through detectPiiCmd (hard block on PII found);
typed message text scanned via scanTextForPiiCmd with a one-time
warning — second send of same message proceeds as acknowledgment
AI history continuity: Changed the history-load query in chat_message to
JOIN ai_conversations and select by issue_id instead of single conversation_id.
This preserves full context when provider/model changes mid-triage.
Deep search: Added DISTINCT to list_issues SELECT and extended the search
filter with EXISTS subqueries covering ai_messages, resolution_steps,
log_files, and timeline_events. Ensures comprehensive search without
duplicate results.
Includes 11 new unit tests covering both features.
- Implement AgentRegistry system with devops-incident-responder agent
- Add domain detection based on conversation keywords
- Inject devops-incident-responder as primary system prompt
- Auto-switch domain prompts silently when context shifts
- Fix version update script to handle JSON format correctly
- Always display version in bottom-left corner
- Add release notes fallback to git commits if CHANGELOG empty
This implements the full devops-incident-responder agent as the primary
system prompt, with domain-specific SME prompts layered on top based on
conversation content analysis. The version display bug is fixed by removing
the collapsed condition, and release notes now have a fallback mechanism.
Add INCIDENT_RESPONSE_FRAMEWORK to domainPrompts.ts and append it to
all 17 domain prompts via getDomainPrompt(). Add system_prompt param
to chat_message command so frontend can inject domain expertise. Record
UTC timeline events (triage_started, log_uploaded, why_level_advanced,
root_cause_identified, rca_generated, postmortem_generated,
document_exported) at key moments with non-blocking calls.
Update tauriCommands.ts with getTimelineEventsCmd, optional metadata on
addTimelineEventCmd, and systemPrompt on chatMessageCmd.
12 new frontend tests (9 domain prompts, 3 timeline events).
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>
analyze_logs() was reading the original log file from disk and sending its
full contents to external AI providers, completely bypassing the redaction
pipeline. The redacted flag in log_files and the .redacted file on disk were
written by apply_redactions() but never consulted on the read path.
Fix: query the redacted column alongside file_path. If the file has not been
redacted, return an error to the caller before any AI provider call is made.
When redacted, read from {path}.redacted instead of the original.
Adds redacted_path_for() helper and two unit tests covering the rejection
and happy-path cases.
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
Rename custom API format handling from custom_rest to custom_rest with backward compatibility, add guided model selection with custom entry in provider settings, and rebrand app naming to Troubleshooting and RCA Assistant across UI, metadata, and docs.
Made-with: Cursor
Inline format arguments across Rust modules to satisfy clippy -D warnings, and configure Cargo to prefer system OpenSSL so clippy builds do not fail on missing vendored Perl modules.
Made-with: Cursor
- Fix download icons (PDF/DOCX) not visible in dark theme by adding text-foreground class
- Fix "Read-only file system" error by using Downloads directory for exports with proper fallback
- Fix Search button visibility in History page by changing variant and adding icon
- Fix domain-only filtering in History page by adding missing filter.domain handling
- Enhance audit log to capture full transmitted data (provider details, messages, content previews)
- Add dirs crate dependency for cross-platform directory detection
- Add success/error feedback for document exports with file path display
- Update Security page to display pretty-printed JSON audit details
Co-Authored-By: Claude Sonnet 4.5 <noreply@anthropic.com>
