[SDCICD-1704] feat: expanded LLM report output

README.md

@@ -327,6 +327,61 @@ that ran and statistics about them (e.g. pass/fail, duration). These XML files w
 used by external applications to present metrics and data for others to see into. An example of
 this is they are used to present data in [TestGrid Dashboards][TestGrid Dashboard].
 
+## Slack Notifications
+
+OSDe2e can send AI-powered failure analysis to Slack when tests fail. Each test suite can notify a different Slack channel with failure details, analysis, and logs.
+
+### Setup
+
+**1. Add Workflow to Your Slack Channel**
+
+Each team adds the shared E2E Test Notifications workflow to their channel:
+
+1. Open the workflow: https://slack.com/shortcuts/Ft09RL7M2AMV/60f07b46919da20d103806a8f5bba094
+2. Click **Add to Slack**
+3. Select your destination channel
+4. Copy the webhook URL (starts with `https://hooks.slack.com/workflows/...`)
+
+**2. Get Your Channel ID**
+
+Right-click your channel → **View channel details** → copy the channel ID (starts with `C`, e.g., `C06HQR8HN0L`)
+
+**3. Configure Test Suites**
+
+Set `TEST_SUITES_YAML` with your test images, webhook URLs, and Slack channel IDs:
+
+```bash
+export TEST_SUITES_YAML='
+- image: quay.io/openshift/osde2e-tests:latest
+  slackWebhook: https://hooks.slack.com/workflows/T.../A.../...
+  slackChannel: C06HQR8HN0L
+- image: quay.io/openshift/custom-tests:v1.0
+  slackWebhook: https://hooks.slack.com/workflows/T.../B.../...
+  slackChannel: C07ABC123XY
+'
+```
+
+**4. Enable Notifications**
+
+Enable Slack notifications in your config:
+
+```yaml
+tests:
+  enableSlackNotify: true
+logAnalysis:
+  enableAnalysis: true
+```
+
+### What You'll Receive
+
+When tests fail, you'll get a threaded Slack message with:
+1. **Main message**: Test suite info (what failed)
+2. **Reply 1**: AI analysis (why it failed)
+3. **Reply 2**: Test failure logs (evidence)
+4. **Reply 3**: Cluster details (for debugging)
+
+For implementation details, see [internal/reporter/README.md](internal/reporter/README.md).
+
 ## CI Jobs
 
 Periodic jobs are run daily validating Managed OpenShift clusters, using

internal/aggregator/aggregator.go

@@ -13,6 +13,7 @@ import (
 	"github.com/go-logr/logr"
 	"github.com/joshdk/go-junit"
 	"github.com/openshift/osde2e/internal/sanitizer"
+	"github.com/openshift/osde2e/pkg/common/util"
 )
 
 type Aggregator struct {
@@ -277,8 +278,7 @@ func extractErrorsFromLogFile(logFile string) (string, error) {
 	// use string builder to collect errors
 	var errors strings.Builder
 	for _, line := range lines {
-		// Check all case variants directly - fastest approach
-		if strings.Contains(line, "error") || strings.Contains(line, "Error") || strings.Contains(line, "ERROR") {
+		if util.ContainsErrorMarker(line) {
 			errors.WriteString(line)
 			errors.WriteString("\n") // Add newline separator
 		}

internal/reporter/README.md

@@ -1,6 +1,8 @@
-# Reporter System
+# Reporter System (Developer Documentation)
 
-The reporter system handles notification delivery after LLM analysis completion, providing a flexible and extensible way to send analysis results to external systems.
+The reporter system handles notification delivery after LLM analysis completion. This document covers the internal architecture and implementation details for developers working on the reporter system.
+
+**For user setup instructions, see the [root README](../../README.md#slack-notifications).**
 
 ## Architecture Overview
 
@@ -69,3 +71,123 @@ if len(reporters) > 0 {
     }
 }
 ```
+
+## Slack Workflow Integration
+
+The Slack reporter sends test failure notifications using a **Slack Workflow** that creates threaded messages. This allows teams to add the shared workflow to their channels and receive structured failure notifications.
+
+### How It Works
+
+The workflow creates four messages in a thread:
+
+1. **Initial Message** - Test suite information (what failed)
+2. **First Reply** - AI-powered analysis with root cause and recommendations (briefly why)
+3. **Second Reply** - Extracted test failure logs (evidence - only failure blocks, not full stdout)
+4. **Third Reply** - Cluster information for debugging (least important - cluster is ephemeral)
+
+**Note:** The code sends fallback messages (e.g., "Test output logs not available") when data is unavailable. This ensures the workflow is resilient to version drift between code and workflow changes.
+
+### Message Format
+
+**Summary (Initial Message - What Failed):**
+```
+:failed: Pipeline Failed at E2E Test
+
+====== 🧪 Test Suite Information ======
+• Image: `quay.io/openshift/osde2e-tests`
+• Commit: `abc123`
+• Environment: `stage`
+```
+
+**Analysis (First Reply - Briefly Why):**
+```
+====== 🔍 Possible Cause ======
+<AI-generated root cause analysis>
+
+====== 💡 Recommendations ======
+1. <recommendation 1>
+2. <recommendation 2>
+```
+
+**Extended Logs (Second Reply - Evidence):**
+```
+Found 3 test failure(s):
+
+[FAILED] test description
+<failure context lines>
+...
+```
+
+**Cluster Details (Third Reply - For Debugging):**
+```
+====== ☸️ Cluster Information ======
+• Cluster ID: `abc-123`
+• Name: `my-cluster`
+• Version: `4.20`
+• Provider: `aws`
+• Expiration: `2026-01-28T10:00:00Z`
+```
+
+### Testing
+
+#### Unit Tests
+```bash
+# Run all reporter tests
+go test -v github.com/openshift/osde2e/internal/reporter
+
+# Run specific workflow tests
+go test -v -run TestSlackReporter_buildWorkflowPayload
+go test -v -run TestSlackReporter_extractFailureBlocks
+```
+
+#### Integration Test (with real Slack)
+```bash
+# Set environment variables
+export LOG_ANALYSIS_SLACK_WEBHOOK="https://hooks.slack.com/workflows/..."
+export LOG_ANALYSIS_SLACK_CHANNEL="C06HQR8HN0L"
+
+# Run integration test
+go test -v -run TestSlackReporter_Integration github.com/openshift/osde2e/pkg/e2e
+```
+
+**Note:** Integration test automatically skips if environment variables are not set.
+
+### Workflow Payload Structure
+
+The reporter sends this JSON payload to the Slack Workflow:
+
+```json
+{
+  "channel": "C06HQR8HN0L",
+  "summary": "Pipeline Failed at E2E Test\n\n# Test Suite Info...",
+  "analysis": "# Possible Cause\n...",
+  "extended_logs": "Found 3 test failure(s):\n...",
+  "cluster_details": "# Cluster Information\nCluster ID: abc-123\n...",
+  "image": "quay.io/openshift/osde2e:abc123",
+  "env": "stage",
+  "commit": "abc123"
+}
+```
+
+## Implementation Notes
+
+**Workflow vs Legacy Webhooks:**
+- Workflow webhooks use `/workflows/` in the URL path
+- Legacy incoming webhooks use `/services/` instead
+- The code uses workflow webhooks to support threaded messages
+
+**Payload Limits:**
+- Maximum field length: 30KB per field (enforced by `maxWorkflowFieldLength` constant)
+- Content exceeding limits is truncated with a notice
+- Slack workflows handle much larger payloads than legacy webhooks
+
+**Fallback Behavior:**
+- All optional fields provide fallback messages when data is unavailable
+- This ensures resilience to version drift between code and workflow changes
+- Required fields: `channel`, `summary`, `analysis`
+
+**Log Extraction Strategy:**
+- For logs ≤250 lines: return full content
+- For logs >250 lines: extract up to 3 failure blocks (max 30 lines each)
+- Failure detection: `[FAILED]` markers and `ERROR`/`Error`/`error` strings
+- Block deduplication: skip-ahead logic prevents overlapping extractions