feat: wire incident response methodology into AI and record triage events

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).

src-tauri/src/commands/ai.rs

@@ -165,6 +165,7 @@ pub async fn chat_message(
     issue_id: String,
     message: String,
     provider_config: ProviderConfig,
+    system_prompt: Option<String>,
     app_handle: tauri::AppHandle,
     state: State<'_, AppState>,
 ) -> Result<ChatResponse, String> {
@@ -232,7 +233,21 @@ pub async fn chat_message(
     // Search integration sources for relevant context
     let integration_context = search_integration_sources(&message, &app_handle, &state).await;
 
-    let mut messages = history;
+    let mut messages = Vec::new();
+
+    // Inject domain system prompt if provided
+    if let Some(ref prompt) = system_prompt {
+        if !prompt.is_empty() {
+            messages.push(Message {
+                role: "system".into(),
+                content: prompt.clone(),
+                tool_call_id: None,
+                tool_calls: None,
+            });
+        }
+    }
+
+    messages.extend(history);
 
     // If we found integration content, add it to the conversation context
     if !integration_context.is_empty() {

src/lib/domainPrompts.ts

@@ -331,6 +331,58 @@ When analyzing identity and access issues, focus on these key areas:
 Always ask about the Keycloak version, realm configuration (external IdP vs local users vs LDAP), SSSD version and configured domains, and whether this is a first-time setup or a regression.`,
 };
 
+export const INCIDENT_RESPONSE_FRAMEWORK = `
+
+---
+
+## INCIDENT RESPONSE METHODOLOGY
+
+Follow this structured framework for every triage conversation. Each phase must be completed with evidence before advancing.
+
+### Phase 1: Detection & Evidence Gathering
+- **Do NOT propose fixes** until the problem is fully understood
+- Gather: error messages, timestamps, affected systems, scope of impact, recent changes
+- Ask: "What changed? When did it start? Who/what is affected? What has been tried?"
+- Record all evidence with UTC timestamps
+- Establish a clear problem statement before proceeding
+
+### Phase 2: Diagnosis & Hypothesis Testing
+- Apply the scientific method: form hypotheses, test them with evidence
+- **The 3-Fix Rule**: If you cannot confidently identify the root cause after 3 hypotheses, STOP and reassess your assumptions — you may be looking at the wrong system or the wrong layer
+- Check the most common causes first (Occam's Razor): DNS, certificates, disk space, permissions, recent deployments
+- Differentiate between symptoms and causes — treat causes, not symptoms
+- Use binary search to narrow scope: which component, which layer, which change
+
+### Phase 3: Root Cause Analysis with 5-Whys
+- Each "Why" must be backed by evidence, not speculation
+- If you cannot provide evidence for a "Why", state what investigation is needed to confirm
+- Look for systemic issues, not just proximate causes
+- The root cause should explain ALL observed symptoms, not just some
+- Common root cause categories: configuration drift, capacity exhaustion, dependency failure, race condition, human error in process
+
+### Phase 4: Resolution & Prevention
+- **Immediate fix**: What stops the bleeding right now? (rollback, restart, failover)
+- **Permanent fix**: What prevents recurrence? (code fix, config change, automation)
+- **Runbook update**: Document the fix for future oncall engineers
+- Verify the fix resolves ALL symptoms, not just the primary one
+- Monitor for regression after applying the fix
+
+### Phase 5: Post-Incident Review
+- Calculate incident metrics: MTTD (detect), MTTA (acknowledge), MTTR (resolve)
+- Conduct blameless post-mortem focused on systems and processes
+- Identify action items with owners and due dates
+- Categories: monitoring gaps, process improvements, technical debt, training needs
+- Ask: "What would have prevented this? What would have detected it faster? What would have resolved it faster?"
+
+### Communication Practices
+- State your current phase explicitly (e.g., "We are in Phase 2: Diagnosis")
+- Summarize findings at each phase transition
+- Flag assumptions clearly: "ASSUMPTION: ..." vs "CONFIRMED: ..."
+- When advancing the Why level, explicitly state the evidence chain
+`;
+
 export function getDomainPrompt(domainId: string): string {
-  return domainPrompts[domainId] ?? "";
+  const domainSpecific = domainPrompts[domainId] ?? "";
+  if (!domainSpecific) return "";
+  return domainSpecific + INCIDENT_RESPONSE_FRAMEWORK;
 }

src/lib/tauriCommands.ts

@@ -268,8 +268,8 @@ export interface TriageMessage {
 export const analyzeLogsCmd = (issueId: string, logFileIds: string[], providerConfig: ProviderConfig) =>
   invoke<AnalysisResult>("analyze_logs", { issueId, logFileIds, providerConfig });
 
-export const chatMessageCmd = (issueId: string, message: string, providerConfig: ProviderConfig) =>
-  invoke<ChatResponse>("chat_message", { issueId, message, providerConfig });
+export const chatMessageCmd = (issueId: string, message: string, providerConfig: ProviderConfig, systemPrompt?: string) =>
+  invoke<ChatResponse>("chat_message", { issueId, message, providerConfig, systemPrompt: systemPrompt ?? null });
 
 export const listProvidersCmd = () => invoke<ProviderInfo[]>("list_providers");
 
@@ -361,8 +361,11 @@ export const addFiveWhyCmd = (
 export const updateFiveWhyCmd = (entryId: string, answer: string) =>
   invoke<void>("update_five_why", { entryId, answer });
 
-export const addTimelineEventCmd = (issueId: string, eventType: string, description: string) =>
-  invoke<TimelineEvent>("add_timeline_event", { issueId, eventType, description });
+export const addTimelineEventCmd = (issueId: string, eventType: string, description: string, metadata?: string) =>
+  invoke<TimelineEvent>("add_timeline_event", { issueId, eventType, description, metadata: metadata ?? null });
+
+export const getTimelineEventsCmd = (issueId: string) =>
+  invoke<TimelineEvent[]>("get_timeline_events", { issueId });
 
 // ─── Document commands ────────────────────────────────────────────────────────
 

src/pages/Postmortem/index.tsx

@@ -5,7 +5,7 @@ import { DocEditor } from "@/components/DocEditor";
 import { useSettingsStore } from "@/stores/settingsStore";
 import {
   generatePostmortemCmd,
-  
+  addTimelineEventCmd,
   updateDocumentCmd,
   exportDocumentCmd,
   type Document_,
@@ -28,6 +28,7 @@ export default function Postmortem() {
         const generated = await generatePostmortemCmd(id);
         setDoc(generated);
         setContent(generated.content_md);
+        addTimelineEventCmd(id, "postmortem_generated", "Post-mortem document generated").catch(() => {});
       } catch (err) {
         setError(String(err));
       } finally {
@@ -54,6 +55,7 @@ export default function Postmortem() {
     try {
       const path = await exportDocumentCmd(doc.id, doc.title, content, format, "");
       setError(`Document exported to: ${path}`);
+      addTimelineEventCmd(id!, "document_exported", `Post-mortem exported as ${format}`).catch(() => {});
       setTimeout(() => setError(null), 5000);
     } catch (err) {
       setError(`Export failed: ${String(err)}`);

src/pages/RCA/index.tsx

@@ -8,6 +8,7 @@ import {
   generateRcaCmd,
   updateDocumentCmd,
   exportDocumentCmd,
+  addTimelineEventCmd,
   type Document_,
 } from "@/lib/tauriCommands";
 
@@ -29,6 +30,7 @@ export default function RCA() {
         const generated = await generateRcaCmd(id);
         setDoc(generated);
         setContent(generated.content_md);
+        addTimelineEventCmd(id, "rca_generated", "RCA document generated").catch(() => {});
       } catch (err) {
         setError(String(err));
       } finally {
@@ -55,6 +57,7 @@ export default function RCA() {
     try {
       const path = await exportDocumentCmd(doc.id, doc.title, content, format, "");
       setError(`Document exported to: ${path}`);
+      addTimelineEventCmd(id!, "document_exported", `RCA exported as ${format}`).catch(() => {});
       setTimeout(() => setError(null), 5000);
     } catch (err) {
       setError(`Export failed: ${String(err)}`);

src/pages/Triage/index.tsx

@@ -15,6 +15,7 @@ import {
   updateIssueCmd,
   addFiveWhyCmd,
 } from "@/lib/tauriCommands";
+import { getDomainPrompt } from "@/lib/domainPrompts";
 import type { TriageMessage } from "@/lib/tauriCommands";
 
 const CLOSE_PATTERNS = [
@@ -167,7 +168,8 @@ export default function Triage() {
     setPendingFiles([]);
 
     try {
-      const response = await chatMessageCmd(id, aiMessage, provider);
+      const systemPrompt = currentIssue ? getDomainPrompt(currentIssue.category) : undefined;
+      const response = await chatMessageCmd(id, aiMessage, provider, systemPrompt);
       const assistantMsg: TriageMessage = {
         id: `asst-${Date.now()}`,
         issue_id: id,

tests/unit/domainPrompts.test.ts

@@ -0,0 +1,63 @@
+import { describe, it, expect } from "vitest";
+import { getDomainPrompt, DOMAINS, INCIDENT_RESPONSE_FRAMEWORK } from "@/lib/domainPrompts";
+
+describe("Domain Prompts with Incident Response Framework", () => {
+  it("exports INCIDENT_RESPONSE_FRAMEWORK constant", () => {
+    expect(INCIDENT_RESPONSE_FRAMEWORK).toBeDefined();
+    expect(typeof INCIDENT_RESPONSE_FRAMEWORK).toBe("string");
+    expect(INCIDENT_RESPONSE_FRAMEWORK.length).toBeGreaterThan(100);
+  });
+
+  it("framework contains all 5 phases", () => {
+    expect(INCIDENT_RESPONSE_FRAMEWORK).toContain("Phase 1: Detection & Evidence Gathering");
+    expect(INCIDENT_RESPONSE_FRAMEWORK).toContain("Phase 2: Diagnosis & Hypothesis Testing");
+    expect(INCIDENT_RESPONSE_FRAMEWORK).toContain("Phase 3: Root Cause Analysis with 5-Whys");
+    expect(INCIDENT_RESPONSE_FRAMEWORK).toContain("Phase 4: Resolution & Prevention");
+    expect(INCIDENT_RESPONSE_FRAMEWORK).toContain("Phase 5: Post-Incident Review");
+  });
+
+  it("framework contains the 3-Fix Rule", () => {
+    expect(INCIDENT_RESPONSE_FRAMEWORK).toContain("3-Fix Rule");
+  });
+
+  it("framework contains communication practices", () => {
+    expect(INCIDENT_RESPONSE_FRAMEWORK).toContain("Communication Practices");
+  });
+
+  it("all defined domains include incident response methodology", () => {
+    for (const domain of DOMAINS) {
+      const prompt = getDomainPrompt(domain.id);
+      if (prompt) {
+        expect(prompt).toContain("INCIDENT RESPONSE METHODOLOGY");
+        expect(prompt).toContain("Phase 1:");
+        expect(prompt).toContain("Phase 5:");
+      }
+    }
+  });
+
+  it("returns empty string for unknown domain", () => {
+    expect(getDomainPrompt("nonexistent_domain")).toBe("");
+    expect(getDomainPrompt("")).toBe("");
+  });
+
+  it("preserves existing Linux domain content", () => {
+    const prompt = getDomainPrompt("linux");
+    expect(prompt).toContain("senior Linux systems engineer");
+    expect(prompt).toContain("RHEL");
+    expect(prompt).toContain("INCIDENT RESPONSE METHODOLOGY");
+  });
+
+  it("preserves existing Kubernetes domain content", () => {
+    const prompt = getDomainPrompt("kubernetes");
+    expect(prompt).toContain("Kubernetes platform engineer");
+    expect(prompt).toContain("k3s");
+    expect(prompt).toContain("INCIDENT RESPONSE METHODOLOGY");
+  });
+
+  it("preserves existing Network domain content", () => {
+    const prompt = getDomainPrompt("network");
+    expect(prompt).toContain("network engineer");
+    expect(prompt).toContain("Fortigate");
+    expect(prompt).toContain("INCIDENT RESPONSE METHODOLOGY");
+  });
+});

tests/unit/resolution.test.tsx

@@ -35,6 +35,7 @@ const mockIssueDetail = {
     },
   ],
   conversations: [],
+  timeline_events: [],
 };
 
 describe("Resolution Page", () => {

tests/unit/timelineEvents.test.ts

@@ -0,0 +1,54 @@
+import { describe, it, expect, vi, beforeEach } from "vitest";
+import { invoke } from "@tauri-apps/api/core";
+
+const mockInvoke = vi.mocked(invoke);
+
+describe("Timeline Event Commands", () => {
+  beforeEach(() => {
+    mockInvoke.mockReset();
+  });
+
+  it("addTimelineEventCmd calls invoke with correct params", async () => {
+    const mockEvent = {
+      id: "te-1",
+      issue_id: "issue-1",
+      event_type: "triage_started",
+      description: "Started",
+      metadata: "{}",
+      created_at: "2025-01-15 10:00:00 UTC",
+    };
+    mockInvoke.mockResolvedValueOnce(mockEvent as never);
+
+    const { addTimelineEventCmd } = await import("@/lib/tauriCommands");
+    const result = await addTimelineEventCmd("issue-1", "triage_started", "Started");
+    expect(mockInvoke).toHaveBeenCalledWith("add_timeline_event", {
+      issueId: "issue-1",
+      eventType: "triage_started",
+      description: "Started",
+      metadata: null,
+    });
+    expect(result).toEqual(mockEvent);
+  });
+
+  it("addTimelineEventCmd passes metadata when provided", async () => {
+    mockInvoke.mockResolvedValueOnce({} as never);
+
+    const { addTimelineEventCmd } = await import("@/lib/tauriCommands");
+    await addTimelineEventCmd("issue-1", "log_uploaded", "File uploaded", '{"file":"app.log"}');
+    expect(mockInvoke).toHaveBeenCalledWith("add_timeline_event", {
+      issueId: "issue-1",
+      eventType: "log_uploaded",
+      description: "File uploaded",
+      metadata: '{"file":"app.log"}',
+    });
+  });
+
+  it("getTimelineEventsCmd calls invoke with correct params", async () => {
+    mockInvoke.mockResolvedValueOnce([] as never);
+
+    const { getTimelineEventsCmd } = await import("@/lib/tauriCommands");
+    const result = await getTimelineEventsCmd("issue-1");
+    expect(mockInvoke).toHaveBeenCalledWith("get_timeline_events", { issueId: "issue-1" });
+    expect(result).toEqual([]);
+  });
+});