fix: align Go packet decoder with MeshCore firmware spec

Match the C++ firmware wire format (Packet::writeTo/readFrom): 1. Field order: transport codes are parsed BEFORE path_length byte, matching firmware's header → transport_codes → path_len → path → payload 2. ACK payload: just 4-byte CRC checksum, not dest+src+ackHash. Firmware createAck() writes only ack_crc (4 bytes). 3. TRACE payload: tag(4) + authCode(4) + flags(1) + pathData, matching firmware createTrace() and onRecvPacket() TRACE handler. 4. ADVERT features: parse feat1 (0x20) and feat2 (0x40) optional 2-byte fields between location and name, matching AdvertDataBuilder and AdvertDataParser in the firmware. 5. Transport code naming: code1/code2 instead of nextHop/lastHop, matching firmware's transport_codes[0]/transport_codes[1] naming. Fixes applied to both cmd/ingestor/decoder.go and cmd/server/decoder.go. Tests updated to match new behavior.
2026-05-13 15:54:43 +00:00 · 2026-03-29 14:14:50 +00:00
412 changed files with 55745 additions and 115409 deletions
@@ -0,0 +1 @@
+{"schemaVersion":1,"label":"backend coverage","message":"87.79%","color":"brightgreen"}
@@ -0,0 +1 @@
+{"schemaVersion":1,"label":"backend tests","message":"998 passed","color":"brightgreen"}
@@ -0,0 +1 @@
+{"schemaVersion":1,"label":"coverage","message":"76%","color":"yellow"}
@@ -1 +0,0 @@
-{"schemaVersion":1,"label":"e2e tests","message":"93 passed","color":"brightgreen"}
@@ -1 +1 @@
-{"schemaVersion":1,"label":"frontend coverage","message":"40.01%","color":"red"}
+{"schemaVersion":1,"label":"frontend coverage","message":"31.35%","color":"red"}
@@ -1 +0,0 @@
-{"schemaVersion":1,"label":"go ingestor coverage","message":"70.2%","color":"yellow"}
@@ -1 +0,0 @@
-{"schemaVersion":1,"label":"go server coverage","message":"85.4%","color":"green"}
@@ -0,0 +1 @@
+{"schemaVersion":1,"label":"tests","message":"844/844 passed","color":"brightgreen"}
@@ -1,51 +1,44 @@
-# MeshCore Analyzer — Environment Configuration
-# Copy to .env and customize. All values have sensible defaults.
-#
-# This file is read by BOTH docker compose AND manage.sh — one source of truth.
-# manage.sh setup negotiates and updates only these production managed keys:
-#   PROD_DATA_DIR, PROD_HTTP_PORT, PROD_HTTPS_PORT, PROD_MQTT_PORT, DISABLE_MOSQUITTO
-# Each environment keeps config + data together in one directory:
-#   ~/meshcore-data/config.json, meshcore.db, Caddyfile, theme.json
-#   ~/meshcore-staging-data/config.json, meshcore.db, Caddyfile
-
-# --- Production ---
-# Data directory (database, theme, etc.)
-# Default: ~/meshcore-data
-# Used by: docker compose, manage.sh
-PROD_DATA_DIR=~/meshcore-data
-
-# HTTP port for web UI
-# Default: 80
-# Used by: docker compose
-PROD_HTTP_PORT=80
-
-# HTTPS port for web UI (TLS via Caddy)
-# Default: 443
-# Used by: docker compose
-PROD_HTTPS_PORT=443
-
-# MQTT port for observer connections
-# Default: 1883
-# Used by: docker compose
-PROD_MQTT_PORT=1883
-
-# Disable internal Mosquitto broker (set true to use external MQTT only)
-# Default: false
-# Used by: manage.sh + docker compose overrides
-DISABLE_MOSQUITTO=false
-
-# --- Staging (HTTP only, no HTTPS) ---
-# Data directory
-# Default: ~/meshcore-staging-data
-# Used by: docker compose
-STAGING_DATA_DIR=~/meshcore-staging-data
-
-# HTTP port
-# Default: 82
-# Used by: docker compose
-STAGING_GO_HTTP_PORT=82
-
-# MQTT port
-# Default: 1885
-# Used by: docker compose
-STAGING_GO_MQTT_PORT=1885
+# MeshCore Analyzer — Environment Configuration
+# Copy to .env and customize. All values have sensible defaults.
+#
+# This file is read by BOTH docker compose AND manage.sh — one source of truth.
+# Each environment keeps config + data together in one directory:
+#   ~/meshcore-data/config.json, meshcore.db, Caddyfile, theme.json
+#   ~/meshcore-staging-data/config.json, meshcore.db, Caddyfile
+
+# --- Production ---
+# Data directory (database, theme, etc.)
+# Default: ~/meshcore-data
+# Used by: docker compose, manage.sh
+PROD_DATA_DIR=~/meshcore-data
+
+# HTTP port for web UI
+# Default: 80
+# Used by: docker compose
+PROD_HTTP_PORT=80
+
+# HTTPS port for web UI (TLS via Caddy)
+# Default: 443
+# Used by: docker compose
+PROD_HTTPS_PORT=443
+
+# MQTT port for observer connections
+# Default: 1883
+# Used by: docker compose
+PROD_MQTT_PORT=1883
+
+# --- Staging (HTTP only, no HTTPS) ---
+# Data directory
+# Default: ~/meshcore-staging-data
+# Used by: docker compose
+STAGING_DATA_DIR=~/meshcore-staging-data
+
+# HTTP port
+# Default: 81
+# Used by: docker compose
+STAGING_HTTP_PORT=81
+
+# MQTT port
+# Default: 1884
+# Used by: docker compose
+STAGING_MQTT_PORT=1884
@@ -1,2 +0,0 @@
-# Line ending normalization (CRLF → LF) — no functional changes
-b6e4ebf12eba21c78b72978e55052307ca72dbc1
@@ -1,17 +0,0 @@
-# Force LF line endings for all text files (prevents CRLF churn from Windows agents)
-* text=auto eol=lf
-
-# Explicitly mark binary files
-*.png binary
-*.jpg binary
-*.ico binary
-*.db binary
-
-# Squad: union merge for append-only team state files
-.squad/decisions.md merge=union
-.squad/agents/*/history.md merge=union
-.squad/log/** merge=union
-.squad/orchestration-log/** merge=union
-
-manage.sh text eol=lf
-*.sh text eol=lf
@@ -1,61 +1,61 @@
---
-name: "MeshCore PR Reviewer"
-description: "A specialized agent for reviewing pull requests in the meshcore-analyzer repository. It focuses on SOLID, DRY, testing, Go best practices, frontend testability, observability, and performance to prevent regressions and maintain high code quality."
-model: "gpt-5.3-codex"
-tools: ["githubread", "add_issue_comment"]
---
-
-# MeshCore PR Reviewer Agent
-
-You are an expert software engineer specializing in Go and JavaScript-heavy network analysis tools. Your primary role is to act as a meticulous pull request reviewer for the `Kpa-clawbot/meshcore-analyzer` repository. You are deeply familiar with its architecture, as outlined in `AGENTS.md`, and you enforce its rules rigorously.
-
-Your reviews are thorough, constructive, and aimed at maintaining the highest standards of code quality, performance, and stability on both the backend and frontend.
-
-## Core Principles
-
-1.  **Context is King**: Before any review, consult the `AGENTS.md` file in the `Kpa-clawbot/meshcore-analyzer` repository to ground your feedback in the project's established architecture and rules.
-2.  **Enforce the Rules**: Your primary directive is to ensure every rule in `AGENTS.md` is followed. Call out any deviation.
-3.  **Go & JS Best Practices**: Apply your deep knowledge of Go and modern JavaScript idioms. Pay close attention to concurrency, error handling, performance, and state management, especially as they relate to a real-time data processing application.
-4.  **Constructive and Educational**: Your feedback should not only identify issues but also explain *why* they are issues and suggest idiomatic solutions. Your goal is to mentor and elevate the codebase and its contributors.
-5.  **Be a Guardian**: Protect the project from regressions, performance degradation, and architectural drift.
-
-## Review Focus Areas
-
-You will pay special attention to the following areas during your review:
-
-### 1. Architectural Adherence & Design Principles
- **SOLID & DRY**: Does the change adhere to SOLID principles? Is there duplicated logic that could be refactored? Does it respect the existing separation of concerns?
- **Project Architecture**: Does the PR respect the single Node.js server + static frontend architecture? Are changes in the right place?
-
-### 2. Testing and Validation
- **No commit without tests**: Is the backend logic change covered by unit tests? Is `test-packet-filter.js` or `test-aging.js` updated if necessary?
- **Browser Validation**: Has the contributor confirmed the change works in a browser? Is there a screenshot for visual changes?
- **Cache Busters**: If any `public/` assets (`.js`, `.css`) were modified, has the cache buster in `public/index.html` been bumped in the *same commit*? This is critical.
-
-### 3. Go-Specific Concerns
- **Concurrency**: Are goroutines used safely? Are there potential race conditions? Is synchronization used correctly?
- **Error Handling**: Is error handling explicit and clear? Are errors wrapped with context where appropriate?
- **Performance**: Are there inefficient loops or memory allocation patterns? Scrutinize any new data processing logic.
- **Go Idioms**: Does the code follow standard Go idioms and formatting (`gofmt`)?
-
-### 4. Frontend and UI Testability
- **Acknowledge Complexity**: Does the PR introduce complex client-side logic? Recognize that browser-based functionality is difficult to unit test.
- **Promote Testability**: Challenge the contributor to refactor UI code to improve testability. Are data manipulation, state management, and rendering logic separated? Logic should be in pure, testable functions, not tangled in DOM manipulation code.
- **UI Logic Purity**: Scrutinize client-side JavaScript. Are there large, monolithic functions? Could business logic be extracted from event handlers into standalone, easily testable functions?
- **State Management**: How is client-side state managed? Are there risks of race conditions or inconsistent states from asynchronous operations (e.g., API calls)?
-
-### 5. Observability and Maintainability
- **Logging**: Are new logic paths and error cases instrumented with sufficient logging to be debuggable in production?
- **Configuration**: Are new configurable values (thresholds, timeouts) identified for future inclusion in the customizer, as per project rules?
- **Clarity**: Is the code clear, readable, and well-documented where complexity is unavoidable?
-
-### 6. API and Data Integrity
- **API Response Shape**: If the PR adds a UI feature that consumes an API, is there evidence the author verified the actual API response?
- **Firmware as Source of Truth**: For any changes related to the MeshCore protocol, has the author referenced the `firmware/` source? Challenge any "magic numbers" or assumptions about packet structure.
-
-## Review Process
-
-1.  **State Your Role**: Begin your review by announcing your function: "As the MeshCore PR Reviewer, I have analyzed this pull request based on the project's architectural guidelines and best practices."
-2.  **Provide a Summary**: Give a high-level summary of your findings (e.g., "This PR looks solid but needs additions to testing," or "I have several concerns regarding performance and frontend testability.").
-3.  **Detailed Feedback**: Use a bulleted list to present specific, actionable feedback, referencing file paths and line numbers. For each point, cite the relevant principle or project rule (e.g., "Missing Test Coverage (Rule #1)", "UI Logic Purity (Focus Area #4)").
-4.  **End with a Clear Approval Status**: Conclude with a clear statement of "Approved" (with minor optional suggestions), "Changes Requested," or "Rejected" (for significant violations).
+---
+name: "MeshCore PR Reviewer"
+description: "A specialized agent for reviewing pull requests in the meshcore-analyzer repository. It focuses on SOLID, DRY, testing, Go best practices, frontend testability, observability, and performance to prevent regressions and maintain high code quality."
+model: "gpt-5.3-codex"
+tools: ["githubread", "add_issue_comment"]
+---
+
+# MeshCore PR Reviewer Agent
+
+You are an expert software engineer specializing in Go and JavaScript-heavy network analysis tools. Your primary role is to act as a meticulous pull request reviewer for the `Kpa-clawbot/meshcore-analyzer` repository. You are deeply familiar with its architecture, as outlined in `AGENTS.md`, and you enforce its rules rigorously.
+
+Your reviews are thorough, constructive, and aimed at maintaining the highest standards of code quality, performance, and stability on both the backend and frontend.
+
+## Core Principles
+
+1.  **Context is King**: Before any review, consult the `AGENTS.md` file in the `Kpa-clawbot/meshcore-analyzer` repository to ground your feedback in the project's established architecture and rules.
+2.  **Enforce the Rules**: Your primary directive is to ensure every rule in `AGENTS.md` is followed. Call out any deviation.
+3.  **Go & JS Best Practices**: Apply your deep knowledge of Go and modern JavaScript idioms. Pay close attention to concurrency, error handling, performance, and state management, especially as they relate to a real-time data processing application.
+4.  **Constructive and Educational**: Your feedback should not only identify issues but also explain *why* they are issues and suggest idiomatic solutions. Your goal is to mentor and elevate the codebase and its contributors.
+5.  **Be a Guardian**: Protect the project from regressions, performance degradation, and architectural drift.
+
+## Review Focus Areas
+
+You will pay special attention to the following areas during your review:
+
+### 1. Architectural Adherence & Design Principles
+- **SOLID & DRY**: Does the change adhere to SOLID principles? Is there duplicated logic that could be refactored? Does it respect the existing separation of concerns?
+- **Project Architecture**: Does the PR respect the single Node.js server + static frontend architecture? Are changes in the right place?
+
+### 2. Testing and Validation
+- **No commit without tests**: Is the backend logic change covered by unit tests? Is `test-packet-filter.js` or `test-aging.js` updated if necessary?
+- **Browser Validation**: Has the contributor confirmed the change works in a browser? Is there a screenshot for visual changes?
+- **Cache Busters**: If any `public/` assets (`.js`, `.css`) were modified, has the cache buster in `public/index.html` been bumped in the *same commit*? This is critical.
+
+### 3. Go-Specific Concerns
+- **Concurrency**: Are goroutines used safely? Are there potential race conditions? Is synchronization used correctly?
+- **Error Handling**: Is error handling explicit and clear? Are errors wrapped with context where appropriate?
+- **Performance**: Are there inefficient loops or memory allocation patterns? Scrutinize any new data processing logic.
+- **Go Idioms**: Does the code follow standard Go idioms and formatting (`gofmt`)?
+
+### 4. Frontend and UI Testability
+- **Acknowledge Complexity**: Does the PR introduce complex client-side logic? Recognize that browser-based functionality is difficult to unit test.
+- **Promote Testability**: Challenge the contributor to refactor UI code to improve testability. Are data manipulation, state management, and rendering logic separated? Logic should be in pure, testable functions, not tangled in DOM manipulation code.
+- **UI Logic Purity**: Scrutinize client-side JavaScript. Are there large, monolithic functions? Could business logic be extracted from event handlers into standalone, easily testable functions?
+- **State Management**: How is client-side state managed? Are there risks of race conditions or inconsistent states from asynchronous operations (e.g., API calls)?
+
+### 5. Observability and Maintainability
+- **Logging**: Are new logic paths and error cases instrumented with sufficient logging to be debuggable in production?
+- **Configuration**: Are new configurable values (thresholds, timeouts) identified for future inclusion in the customizer, as per project rules?
+- **Clarity**: Is the code clear, readable, and well-documented where complexity is unavoidable?
+
+### 6. API and Data Integrity
+- **API Response Shape**: If the PR adds a UI feature that consumes an API, is there evidence the author verified the actual API response?
+- **Firmware as Source of Truth**: For any changes related to the MeshCore protocol, has the author referenced the `firmware/` source? Challenge any "magic numbers" or assumptions about packet structure.
+
+## Review Process
+
+1.  **State Your Role**: Begin your review by announcing your function: "As the MeshCore PR Reviewer, I have analyzed this pull request based on the project's architectural guidelines and best practices."
+2.  **Provide a Summary**: Give a high-level summary of your findings (e.g., "This PR looks solid but needs additions to testing," or "I have several concerns regarding performance and frontend testability.").
+3.  **Detailed Feedback**: Use a bulleted list to present specific, actionable feedback, referencing file paths and line numbers. For each point, cite the relevant principle or project rule (e.g., "Missing Test Coverage (Rule #1)", "UI Logic Purity (Focus Area #4)").
+4.  **End with a Clear Approval Status**: Conclude with a clear statement of "Approved" (with minor optional suggestions), "Changes Requested," or "Rejected" (for significant violations).
@@ -1,515 +1,393 @@
-name: CI/CD Pipeline
-
-on:
-  push:
-    branches: [master]
-    tags: ['v*']
-  pull_request:
-    branches: [master]
-  workflow_dispatch:
-
-permissions:
-  contents: read
-  packages: write
-
-concurrency:
-  group: ci-${{ github.event.pull_request.number || github.ref }}
-  cancel-in-progress: true
-
-env:
-  FORCE_JAVASCRIPT_ACTIONS_TO_NODE24: true
-  STAGING_COMPOSE_FILE: docker-compose.staging.yml
-  STAGING_SERVICE: staging-go
-  STAGING_CONTAINER: corescope-staging-go
-
-# Pipeline (sequential, fail-fast):
-#   go-test → e2e-test → build-and-publish → deploy → publish-badges
-#   PRs stop after build-and-publish (no GHCR push). Master continues to deploy + badges.
-
-jobs:
-  # ───────────────────────────────────────────────────────────────
-  # 1. Go Build & Test
-  # ───────────────────────────────────────────────────────────────
-  go-test:
-    name: "✅ Go Build & Test"
-    runs-on: ubuntu-latest
-    steps:
-      - name: Checkout code
-        uses: actions/checkout@v5
-        with:
-          fetch-depth: 0
-
-      - name: Clean Go module cache
-        run: rm -rf ~/go/pkg/mod 2>/dev/null || true
-
-      - name: Set up Go 1.22
-        uses: actions/setup-go@v6
-        with:
-          go-version: '1.22'
-          cache-dependency-path: |
-            cmd/server/go.sum
-            cmd/ingestor/go.sum
-
-      - name: Build and test Go server (with coverage)
-        run: |
-          set -e -o pipefail
-          cd cmd/server
-          go build .
-          go test -coverprofile=server-coverage.out ./... 2>&1 | tee server-test.log
-          echo "--- Go Server Coverage ---"
-          go tool cover -func=server-coverage.out | tail -1
-
-      - name: Build and test Go ingestor (with coverage)
-        run: |
-          set -e -o pipefail
-          cd cmd/ingestor
-          go build .
-          go test -coverprofile=ingestor-coverage.out ./... 2>&1 | tee ingestor-test.log
-          echo "--- Go Ingestor Coverage ---"
-          go tool cover -func=ingestor-coverage.out | tail -1
-
-      - name: Build and test channel library + decrypt CLI
-        run: |
-          set -e -o pipefail
-          cd internal/channel
-          go test ./...
-          echo "--- Channel library tests passed ---"
-          cd ../../cmd/decrypt
-          CGO_ENABLED=0 go build -ldflags="-s -w" -o corescope-decrypt .
-          go test ./...
-          echo "--- Decrypt CLI tests passed ---"
-
-      - name: Run JS unit tests (packet-filter)
-        run: |
-          set -e
-          node test-packet-filter.js
-          node test-channel-decrypt-insecure-context.js
-
-      - name: Verify proto syntax
-        run: |
-          set -e
-          sudo apt-get update -qq
-          sudo apt-get install -y protobuf-compiler
-          for proto in proto/*.proto; do
-            echo "  ✓ $(basename "$proto")"
-            protoc --proto_path=proto --descriptor_set_out=/dev/null "$proto"
-          done
-          echo "✅ All .proto files are syntactically valid"
-
-      - name: Generate Go coverage badges
-        if: success()
-        run: |
-          mkdir -p .badges
-
-          SERVER_COV="0"
-          if [ -f cmd/server/server-coverage.out ]; then
-            SERVER_COV=$(cd cmd/server && go tool cover -func=server-coverage.out | tail -1 | grep -oP '[\d.]+(?=%)')
-          fi
-          SERVER_COLOR="red"
-          if [ "$(echo "$SERVER_COV >= 80" | bc -l 2>/dev/null)" = "1" ]; then SERVER_COLOR="green"
-          elif [ "$(echo "$SERVER_COV >= 60" | bc -l 2>/dev/null)" = "1" ]; then SERVER_COLOR="yellow"; fi
-          echo "{\"schemaVersion\":1,\"label\":\"go server coverage\",\"message\":\"${SERVER_COV}%\",\"color\":\"${SERVER_COLOR}\"}" > .badges/go-server-coverage.json
-
-          INGESTOR_COV="0"
-          if [ -f cmd/ingestor/ingestor-coverage.out ]; then
-            INGESTOR_COV=$(cd cmd/ingestor && go tool cover -func=ingestor-coverage.out | tail -1 | grep -oP '[\d.]+(?=%)')
-          fi
-          INGESTOR_COLOR="red"
-          if [ "$(echo "$INGESTOR_COV >= 80" | bc -l 2>/dev/null)" = "1" ]; then INGESTOR_COLOR="green"
-          elif [ "$(echo "$INGESTOR_COV >= 60" | bc -l 2>/dev/null)" = "1" ]; then INGESTOR_COLOR="yellow"; fi
-          echo "{\"schemaVersion\":1,\"label\":\"go ingestor coverage\",\"message\":\"${INGESTOR_COV}%\",\"color\":\"${INGESTOR_COLOR}\"}" > .badges/go-ingestor-coverage.json
-
-          echo "## Go Coverage" >> $GITHUB_STEP_SUMMARY
-          echo "| Module | Coverage |" >> $GITHUB_STEP_SUMMARY
-          echo "|--------|----------|" >> $GITHUB_STEP_SUMMARY
-          echo "| Server | ${SERVER_COV}% |" >> $GITHUB_STEP_SUMMARY
-          echo "| Ingestor | ${INGESTOR_COV}% |" >> $GITHUB_STEP_SUMMARY
-
-      - name: Upload Go coverage badges
-        if: success()
-        uses: actions/upload-artifact@v6
-        with:
-          name: go-badges
-          path: .badges/go-*.json
-          retention-days: 1
-          if-no-files-found: ignore
-          include-hidden-files: true
-
-  # ───────────────────────────────────────────────────────────────
-  # 2. Playwright E2E Tests (against Go server with fixture DB)
-  # ───────────────────────────────────────────────────────────────
-  e2e-test:
-    name: "🎭 Playwright E2E Tests"
-    needs: [go-test]
-    runs-on: ubuntu-latest
-    defaults:
-      run:
-        shell: bash
-    steps:
-      - name: Checkout code
-        uses: actions/checkout@v5
-        with:
-          fetch-depth: 0
-
-      - name: Set up Node.js 22
-        uses: actions/setup-node@v5
-        with:
-          node-version: '22'
-
-      - name: Clean Go module cache
-        run: rm -rf ~/go/pkg/mod 2>/dev/null || true
-
-      - name: Set up Go 1.22
-        uses: actions/setup-go@v6
-        with:
-          go-version: '1.22'
-          cache-dependency-path: cmd/server/go.sum
-
-      - name: Build Go server
-        run: |
-          cd cmd/server
-          go build -o ../../corescope-server .
-          echo "Go server built successfully"
-
-      - name: Install npm dependencies
-        run: npm ci --production=false
-
-      - name: Install Playwright browser
-        run: |
-          npx playwright install chromium 2>/dev/null || true
-          npx playwright install-deps chromium 2>/dev/null || true
-
-      - name: Instrument frontend JS for coverage
-        run: sh scripts/instrument-frontend.sh
-
-      - name: Freshen fixture timestamps
-        run: bash tools/freshen-fixture.sh test-fixtures/e2e-fixture.db
-
-      - name: Start Go server with fixture DB
-        run: |
-          fuser -k 13581/tcp 2>/dev/null || true
-          sleep 1
-          ./corescope-server -port 13581 -db test-fixtures/e2e-fixture.db -public public-instrumented &
-          echo $! > .server.pid
-          for i in $(seq 1 30); do
-            if curl -sf http://localhost:13581/api/healthz > /dev/null 2>&1; then
-              echo "Server ready after ${i}s"
-              break
-            fi
-            if [ "$i" -eq 30 ]; then
-              echo "Server failed to start within 30s"
-              exit 1
-            fi
-            sleep 1
-          done
-
-      - name: Run Playwright E2E tests (fail-fast)
-        run: |
-          BASE_URL=http://localhost:13581 node test-e2e-playwright.js 2>&1 | tee e2e-output.txt
-
-      - name: Collect frontend coverage (parallel)
-        if: success() && github.event_name == 'push'
-        run: |
-          BASE_URL=http://localhost:13581 node scripts/collect-frontend-coverage.js 2>&1 | tee fe-coverage-output.txt || true
-
-      - name: Generate frontend coverage badges
-        if: success()
-        run: |
-          E2E_PASS=$(grep -oP '[0-9]+(?=/)' e2e-output.txt | tail -1 || echo "0")
-
-          mkdir -p .badges
-          if [ -f .nyc_output/frontend-coverage.json ] || [ -f .nyc_output/e2e-coverage.json ]; then
-            npx nyc report --reporter=text-summary --reporter=text 2>&1 | tee fe-report.txt
-            FE_COVERAGE=$(grep 'Statements' fe-report.txt | head -1 | grep -oP '[\d.]+(?=%)' || echo "0")
-            FE_COVERAGE=${FE_COVERAGE:-0}
-            FE_COLOR="red"
-            [ "$(echo "$FE_COVERAGE > 50" | bc -l 2>/dev/null)" = "1" ] && FE_COLOR="yellow"
-            [ "$(echo "$FE_COVERAGE > 80" | bc -l 2>/dev/null)" = "1" ] && FE_COLOR="brightgreen"
-            echo "{\"schemaVersion\":1,\"label\":\"frontend coverage\",\"message\":\"${FE_COVERAGE}%\",\"color\":\"${FE_COLOR}\"}" > .badges/frontend-coverage.json
-            echo "## Frontend: ${FE_COVERAGE}% coverage" >> $GITHUB_STEP_SUMMARY
-          fi
-          echo "{\"schemaVersion\":1,\"label\":\"e2e tests\",\"message\":\"${E2E_PASS:-0} passed\",\"color\":\"brightgreen\"}" > .badges/e2e-tests.json
-
-      - name: Stop test server
-        if: always()
-        run: |
-          if [ -f .server.pid ]; then
-            kill $(cat .server.pid) 2>/dev/null || true
-            rm -f .server.pid
-          fi
-
-      - name: Upload E2E badges
-        if: success()
-        uses: actions/upload-artifact@v6
-        with:
-          name: e2e-badges
-          path: .badges/
-          retention-days: 1
-          if-no-files-found: ignore
-          include-hidden-files: true
-
-  # ───────────────────────────────────────────────────────────────
-  # 3. Build & Publish Docker Image
-  # ───────────────────────────────────────────────────────────────
-  build-and-publish:
-    name: "🏗️ Build & Publish Docker Image"
-    needs: [e2e-test]
-    runs-on: ubuntu-latest
-    steps:
-      - name: Checkout code
-        uses: actions/checkout@v5
-
-      - name: Compute build metadata
-        id: meta
-        run: |
-          BUILD_TIME=$(date -u '+%Y-%m-%dT%H:%M:%SZ')
-          GIT_COMMIT="${GITHUB_SHA::7}"
-          if [[ "$GITHUB_REF" == refs/tags/v* ]]; then
-            APP_VERSION="${GITHUB_REF#refs/tags/}"
-          else
-            APP_VERSION="edge"
-          fi
-          echo "build_time=$BUILD_TIME" >> "$GITHUB_OUTPUT"
-          echo "git_commit=$GIT_COMMIT" >> "$GITHUB_OUTPUT"
-          echo "app_version=$APP_VERSION" >> "$GITHUB_OUTPUT"
-          echo "Build: version=$APP_VERSION commit=$GIT_COMMIT time=$BUILD_TIME"
-
-      - name: Build Go Docker image (local staging)
-        run: |
-          GIT_COMMIT="${{ steps.meta.outputs.git_commit }}" \
-          APP_VERSION="${{ steps.meta.outputs.app_version }}" \
-          BUILD_TIME="${{ steps.meta.outputs.build_time }}" \
-          docker compose -f "$STAGING_COMPOSE_FILE" -p corescope-staging build "$STAGING_SERVICE"
-          echo "Built Go staging image ✅"
-
-      - name: Set up Docker Buildx
-        if: github.event_name == 'push'
-        uses: docker/setup-buildx-action@v3
-
-      - name: Set up QEMU (arm64 runtime stage)
-        if: github.event_name == 'push'
-        uses: docker/setup-qemu-action@v3
-
-      - name: Log in to GHCR
-        if: github.event_name == 'push'
-        uses: docker/login-action@v3
-        with:
-          registry: ghcr.io
-          username: ${{ github.actor }}
-          password: ${{ secrets.GITHUB_TOKEN }}
-
-      - name: Extract Docker metadata
-        if: github.event_name == 'push'
-        id: docker-meta
-        uses: docker/metadata-action@v5
-        with:
-          images: ghcr.io/kpa-clawbot/corescope
-          tags: |
-            type=semver,pattern=v{{version}}
-            type=semver,pattern=v{{major}}.{{minor}}
-            type=semver,pattern=v{{major}}
-            type=raw,value=latest,enable=${{ startsWith(github.ref, 'refs/tags/v') }}
-            type=edge,branch=master
-
-      - name: Build and push to GHCR
-        if: github.event_name == 'push'
-        uses: docker/build-push-action@v6
-        with:
-          context: .
-          push: true
-          platforms: linux/amd64,linux/arm64
-          tags: ${{ steps.docker-meta.outputs.tags }}
-          labels: ${{ steps.docker-meta.outputs.labels }}
-          build-args: |
-            APP_VERSION=${{ steps.meta.outputs.app_version }}
-            GIT_COMMIT=${{ steps.meta.outputs.git_commit }}
-            BUILD_TIME=${{ steps.meta.outputs.build_time }}
-          cache-from: type=gha
-          cache-to: type=gha,mode=max
-
-  # ───────────────────────────────────────────────────────────────
-  # 4. Release Artifacts (tags only)
-  # ───────────────────────────────────────────────────────────────
-  release-artifacts:
-    name: "📦 Release Artifacts"
-    if: startsWith(github.ref, 'refs/tags/v')
-    needs: [go-test]
-    runs-on: ubuntu-latest
-    permissions:
-      contents: write
-    steps:
-      - name: Checkout code
-        uses: actions/checkout@v5
-
-      - name: Set up Go 1.22
-        uses: actions/setup-go@v6
-        with:
-          go-version: '1.22'
-
-      - name: Build corescope-decrypt (static, linux/amd64)
-        run: |
-          cd cmd/decrypt
-          CGO_ENABLED=0 GOOS=linux GOARCH=amd64 go build -ldflags="-s -w -X main.version=${{ github.ref_name }}" -o ../../corescope-decrypt-linux-amd64 .
-
-      - name: Build corescope-decrypt (static, linux/arm64)
-        run: |
-          cd cmd/decrypt
-          CGO_ENABLED=0 GOOS=linux GOARCH=arm64 go build -ldflags="-s -w -X main.version=${{ github.ref_name }}" -o ../../corescope-decrypt-linux-arm64 .
-
-      - name: Upload release assets
-        uses: softprops/action-gh-release@v2
-        with:
-          files: |
-            corescope-decrypt-linux-amd64
-            corescope-decrypt-linux-arm64
-
-  # ───────────────────────────────────────────────────────────────
-  # 4b. Deploy Staging (master only)
-  # ───────────────────────────────────────────────────────────────
-  deploy:
-    name: "🚀 Deploy Staging"
-    if: github.event_name == 'push'
-    needs: [build-and-publish]
-    runs-on: [self-hosted, meshcore-runner-2]
-    steps:
-      - name: Checkout code
-        uses: actions/checkout@v5
-
-      - name: Pull latest image from GHCR
-        run: |
-          # Try to pull the edge image from GHCR and tag for docker-compose compatibility
-          if docker pull ghcr.io/kpa-clawbot/corescope:edge; then
-            docker tag ghcr.io/kpa-clawbot/corescope:edge corescope-go:latest
-            echo "Pulled and tagged GHCR edge image ✅"
-          else
-            echo "⚠️ GHCR pull failed — falling back to locally built image"
-          fi
-
-      - name: Deploy staging
-        run: |
-          # Force-remove the staging container regardless of how it was created
-          # (compose-managed OR manually created via docker run)
-          docker stop corescope-staging-go 2>/dev/null || true
-          docker rm -f corescope-staging-go 2>/dev/null || true
-          docker compose -f "$STAGING_COMPOSE_FILE" -p corescope-staging down --timeout 30 2>/dev/null || true
-
-          # Wait for container to be fully gone and OS to reclaim memory (3GB limit)
-          for i in $(seq 1 15); do
-            if ! docker ps -a --format '{{.Names}}' | grep -q 'corescope-staging-go'; then
-              break
-            fi
-            sleep 1
-          done
-          sleep 5  # extra pause for OS memory reclaim
-
-          # Ensure staging data dir exists (config.json lives here, no separate file mount)
-          STAGING_DATA="${STAGING_DATA_DIR:-$HOME/meshcore-staging-data}"
-          mkdir -p "$STAGING_DATA"
-
-          # If no config exists, copy the example (CI doesn't have a real prod config)
-          if [ ! -f "$STAGING_DATA/config.json" ]; then
-            echo "Staging config missing — copying config.example.json"
-            cp config.example.json "$STAGING_DATA/config.json" 2>/dev/null || true
-          fi
-
-          docker compose -f "$STAGING_COMPOSE_FILE" -p corescope-staging up -d staging-go
-
-      - name: Healthcheck staging container
-        run: |
-          for i in $(seq 1 120); do
-            HEALTH=$(docker inspect corescope-staging-go --format '{{.State.Health.Status}}' 2>/dev/null || echo "starting")
-            if [ "$HEALTH" = "healthy" ]; then
-              echo "Staging healthy after ${i}s"
-              break
-            fi
-            if [ "$i" -eq 120 ]; then
-              echo "Staging failed health check after 120s"
-              docker logs corescope-staging-go --tail 50
-              exit 1
-            fi
-            sleep 1
-          done
-
-      - name: Smoke test staging API
-        run: |
-          PORT="${STAGING_GO_HTTP_PORT:-80}"
-          if curl -sf "http://localhost:${PORT}/api/stats" | grep -q engine; then
-            echo "Staging verified — engine field present ✅"
-          else
-            echo "Staging /api/stats did not return engine field (port ${PORT})"
-            exit 1
-          fi
-
-      - name: Clean up old Docker images
-        if: always()
-        run: |
-          # Remove dangling images and images older than 24h (keeps current build)
-          echo "--- Docker disk usage before cleanup ---"
-          docker system df
-          docker image prune -af --filter "until=24h" 2>/dev/null || true
-          docker builder prune -f --keep-storage=1GB 2>/dev/null || true
-          echo "--- Docker disk usage after cleanup ---"
-          docker system df
-
-  # ───────────────────────────────────────────────────────────────
-  # 5. Publish Badges & Summary (master only)
-  # ───────────────────────────────────────────────────────────────
-  publish:
-    name: "📝 Publish Badges & Summary"
-    if: github.event_name == 'push'
-    needs: [deploy]
-    runs-on: ubuntu-latest
-    steps:
-      - name: Checkout code
-        uses: actions/checkout@v5
-
-      - name: Download Go coverage badges
-        continue-on-error: true
-        uses: actions/download-artifact@v6
-        with:
-          name: go-badges
-          path: .badges/
-
-      - name: Download E2E badges
-        continue-on-error: true
-        uses: actions/download-artifact@v6
-        with:
-          name: e2e-badges
-          path: .badges/
-
-      - name: Publish coverage badges to repo
-        continue-on-error: true
-        env:
-          GH_TOKEN: ${{ secrets.BADGE_PUSH_TOKEN }}
-        run: |
-          # GITHUB_TOKEN cannot push to protected branches (required status checks).
-          # Use admin PAT (BADGE_PUSH_TOKEN) via GitHub Contents API instead.
-          for badge in .badges/*.json; do
-            FILENAME=$(basename "$badge")
-            FILEPATH=".badges/$FILENAME"
-            CONTENT=$(base64 -w0 "$badge")
-            CURRENT_SHA=$(gh api "repos/${{ github.repository }}/contents/$FILEPATH" --jq '.sha' 2>/dev/null || echo "")
-            if [ -n "$CURRENT_SHA" ]; then
-              gh api "repos/${{ github.repository }}/contents/$FILEPATH" \
-                -X PUT \
-                -f message="ci: update $FILENAME [skip ci]" \
-                -f content="$CONTENT" \
-                -f sha="$CURRENT_SHA" \
-                -f branch="master" \
-                --silent 2>&1 || echo "Failed to update $FILENAME"
-            else
-              gh api "repos/${{ github.repository }}/contents/$FILEPATH" \
-                -X PUT \
-                -f message="ci: update $FILENAME [skip ci]" \
-                -f content="$CONTENT" \
-                -f branch="master" \
-                --silent 2>&1 || echo "Failed to create $FILENAME"
-            fi
-          done
-          echo "Badge publish complete"
-
-      - name: Post deployment summary
-        run: |
-          echo "## Staging Deployed ✓" >> $GITHUB_STEP_SUMMARY
-          echo "" >> $GITHUB_STEP_SUMMARY
-          echo "**Commit:** \`$(git rev-parse --short HEAD)\` — $(git log -1 --format=%s)" >> $GITHUB_STEP_SUMMARY
+name: Deploy
+
+on:
+  push:
+    branches: [master]
+    paths-ignore:
+      - '**.md'
+      - 'LICENSE'
+      - '.gitignore'
+      - 'docs/**'
+  pull_request:
+    branches: [master]
+    paths-ignore:
+      - '**.md'
+      - 'LICENSE'
+      - '.gitignore'
+      - 'docs/**'
+
+concurrency:
+  group: deploy
+  cancel-in-progress: true
+
+env:
+  FORCE_JAVASCRIPT_ACTIONS_TO_NODE24: true
+
+# Pipeline:
+#   node-test (frontend tests) ──┐
+#   go-test                      ├──→ build → deploy → publish
+#                                └─ (both wait)
+#
+# Proto validation flow:
+#   1. go-test job: verify .proto files compile (syntax check)
+#   2. deploy job: capture fresh fixtures from prod, validate protos match actual API responses
+
+jobs:
+  # ───────────────────────────────────────────────────────────────
+  # 1. Go Build & Test — compiles + tests Go modules, coverage badges
+  # ───────────────────────────────────────────────────────────────
+  go-test:
+    name: "✅ Go Build & Test"
+    runs-on: ubuntu-latest
+    steps:
+      - name: Checkout code
+        uses: actions/checkout@v4
+
+      - name: Set up Go 1.22
+        uses: actions/setup-go@v5
+        with:
+          go-version: '1.22'
+          cache-dependency-path: |
+            cmd/server/go.sum
+            cmd/ingestor/go.sum
+
+      - name: Build and test Go server (with coverage)
+        run: |
+          set -e -o pipefail
+          cd cmd/server
+          go build .
+          go test -coverprofile=server-coverage.out ./... 2>&1 | tee server-test.log
+          echo "--- Go Server Coverage ---"
+          go tool cover -func=server-coverage.out | tail -1
+
+      - name: Build and test Go ingestor (with coverage)
+        run: |
+          set -e -o pipefail
+          cd cmd/ingestor
+          go build .
+          go test -coverprofile=ingestor-coverage.out ./... 2>&1 | tee ingestor-test.log
+          echo "--- Go Ingestor Coverage ---"
+          go tool cover -func=ingestor-coverage.out | tail -1
+
+      - name: Verify proto syntax (all .proto files compile)
+        run: |
+          set -e
+          echo "Installing protoc..."
+          sudo apt-get update -qq
+          sudo apt-get install -y protobuf-compiler
+          
+          echo "Checking proto syntax..."
+          for proto in proto/*.proto; do
+            echo "  ✓ $(basename "$proto")"
+            protoc --proto_path=proto --descriptor_set_out=/dev/null "$proto"
+          done
+          echo "✅ All .proto files are syntactically valid"
+
+      - name: Generate Go coverage badges
+        if: always()
+        run: |
+          mkdir -p .badges
+
+          # Parse server coverage
+          SERVER_COV="0"
+          if [ -f cmd/server/server-coverage.out ]; then
+            SERVER_COV=$(cd cmd/server && go tool cover -func=server-coverage.out | tail -1 | grep -oP '[\d.]+(?=%)')
+          fi
+          SERVER_COLOR="red"
+          if [ "$(echo "$SERVER_COV >= 80" | bc -l 2>/dev/null)" = "1" ]; then
+            SERVER_COLOR="green"
+          elif [ "$(echo "$SERVER_COV >= 60" | bc -l 2>/dev/null)" = "1" ]; then
+            SERVER_COLOR="yellow"
+          fi
+          echo "{\"schemaVersion\":1,\"label\":\"go server coverage\",\"message\":\"${SERVER_COV}%\",\"color\":\"${SERVER_COLOR}\"}" > .badges/go-server-coverage.json
+          echo "Go server coverage: ${SERVER_COV}% (${SERVER_COLOR})"
+
+          # Parse ingestor coverage
+          INGESTOR_COV="0"
+          if [ -f cmd/ingestor/ingestor-coverage.out ]; then
+            INGESTOR_COV=$(cd cmd/ingestor && go tool cover -func=ingestor-coverage.out | tail -1 | grep -oP '[\d.]+(?=%)')
+          fi
+          INGESTOR_COLOR="red"
+          if [ "$(echo "$INGESTOR_COV >= 80" | bc -l 2>/dev/null)" = "1" ]; then
+            INGESTOR_COLOR="green"
+          elif [ "$(echo "$INGESTOR_COV >= 60" | bc -l 2>/dev/null)" = "1" ]; then
+            INGESTOR_COLOR="yellow"
+          fi
+          echo "{\"schemaVersion\":1,\"label\":\"go ingestor coverage\",\"message\":\"${INGESTOR_COV}%\",\"color\":\"${INGESTOR_COLOR}\"}" > .badges/go-ingestor-coverage.json
+          echo "Go ingestor coverage: ${INGESTOR_COV}% (${INGESTOR_COLOR})"
+
+          echo "## Go Coverage" >> $GITHUB_STEP_SUMMARY
+          echo "| Module | Coverage |" >> $GITHUB_STEP_SUMMARY
+          echo "|--------|----------|" >> $GITHUB_STEP_SUMMARY
+          echo "| Server | ${SERVER_COV}% |" >> $GITHUB_STEP_SUMMARY
+          echo "| Ingestor | ${INGESTOR_COV}% |" >> $GITHUB_STEP_SUMMARY
+
+      - name: Upload Go coverage badges
+        if: always()
+        uses: actions/upload-artifact@v4
+        with:
+          name: go-badges
+          path: .badges/go-*.json
+          retention-days: 1
+          if-no-files-found: ignore
+
+  # ───────────────────────────────────────────────────────────────
+  # 2. Node.js Tests — backend unit tests + Playwright E2E, coverage
+  # ───────────────────────────────────────────────────────────────
+  node-test:
+    name: "🧪 Node.js Tests"
+    runs-on: self-hosted
+    steps:
+      - name: Checkout code
+        uses: actions/checkout@v4
+        with:
+          fetch-depth: 2
+
+      - name: Set up Node.js 22
+        uses: actions/setup-node@v4
+        with:
+          node-version: '22'
+
+      - name: Install npm dependencies
+        run: npm ci --production=false
+
+      - name: Detect changed files
+        id: changes
+        run: |
+          BACKEND=$(git diff --name-only HEAD~1 | grep -cE '^(server|db|decoder|packet-store|server-helpers|iata-coords)\.js$' || true)
+          FRONTEND=$(git diff --name-only HEAD~1 | grep -cE '^public/' || true)
+          TESTS=$(git diff --name-only HEAD~1 | grep -cE '^test-|^tools/' || true)
+          CI=$(git diff --name-only HEAD~1 | grep -cE '\.github/|package\.json|test-all\.sh|scripts/' || true)
+          # If CI/test infra changed, run everything
+          if [ "$CI" -gt 0 ]; then BACKEND=1; FRONTEND=1; fi
+          # If test files changed, run everything
+          if [ "$TESTS" -gt 0 ]; then BACKEND=1; FRONTEND=1; fi
+          echo "backend=$([[ $BACKEND -gt 0 ]] && echo true || echo false)" >> $GITHUB_OUTPUT
+          echo "frontend=$([[ $FRONTEND -gt 0 ]] && echo true || echo false)" >> $GITHUB_OUTPUT
+          echo "Changes: backend=$BACKEND frontend=$FRONTEND tests=$TESTS ci=$CI"
+
+      - name: Run backend tests with coverage
+        if: steps.changes.outputs.backend == 'true'
+        run: |
+          npx c8 --reporter=text-summary --reporter=text sh test-all.sh 2>&1 | tee test-output.txt
+          
+          TOTAL_PASS=$(grep -oP '\d+(?= passed)' test-output.txt | awk '{s+=$1} END {print s}')
+          TOTAL_FAIL=$(grep -oP '\d+(?= failed)' test-output.txt | awk '{s+=$1} END {print s}')
+          BE_COVERAGE=$(grep 'Statements' test-output.txt | tail -1 | grep -oP '[\d.]+(?=%)')
+          
+          mkdir -p .badges
+          BE_COLOR="red"
+          [ "$(echo "$BE_COVERAGE > 60" | bc -l 2>/dev/null)" = "1" ] && BE_COLOR="yellow"
+          [ "$(echo "$BE_COVERAGE > 80" | bc -l 2>/dev/null)" = "1" ] && BE_COLOR="brightgreen"
+          echo "{\"schemaVersion\":1,\"label\":\"backend tests\",\"message\":\"${TOTAL_PASS} passed\",\"color\":\"brightgreen\"}" > .badges/backend-tests.json
+          echo "{\"schemaVersion\":1,\"label\":\"backend coverage\",\"message\":\"${BE_COVERAGE}%\",\"color\":\"${BE_COLOR}\"}" > .badges/backend-coverage.json
+          
+          echo "## Backend: ${TOTAL_PASS} tests, ${BE_COVERAGE}% coverage" >> $GITHUB_STEP_SUMMARY
+
+      - name: Run backend tests (quick, no coverage)
+        if: steps.changes.outputs.backend == 'false'
+        run: npm run test:unit
+
+      - name: Install Playwright browser
+        if: steps.changes.outputs.frontend == 'true'
+        run: npx playwright install chromium --with-deps 2>/dev/null || true
+
+      - name: Instrument frontend JS for coverage
+        if: steps.changes.outputs.frontend == 'true'
+        run: sh scripts/instrument-frontend.sh
+
+      - name: Start instrumented test server on port 13581
+        if: steps.changes.outputs.frontend == 'true'
+        run: |
+          # Kill any stale server on 13581
+          fuser -k 13581/tcp 2>/dev/null || true
+          sleep 2
+          COVERAGE=1 PORT=13581 node server.js &
+          echo $! > .server.pid
+          echo "Server PID: $(cat .server.pid)"
+          # Health-check poll loop (up to 30s)
+          for i in $(seq 1 30); do
+            if curl -sf http://localhost:13581/api/stats > /dev/null 2>&1; then
+              echo "Server ready after ${i}s"
+              break
+            fi
+            if [ "$i" -eq 30 ]; then
+              echo "Server failed to start within 30s"
+              echo "Last few lines from server logs:"
+              ps aux | grep "PORT=13581" || echo "No server process found"
+              exit 1
+            fi
+            sleep 1
+          done
+
+      - name: Run Playwright E2E tests
+        if: steps.changes.outputs.frontend == 'true'
+        run: BASE_URL=http://localhost:13581 node test-e2e-playwright.js 2>&1 | tee e2e-output.txt
+
+      - name: Collect frontend coverage report
+        if: always() && steps.changes.outputs.frontend == 'true'
+        run: |
+          BASE_URL=http://localhost:13581 node scripts/collect-frontend-coverage.js 2>&1 | tee fe-coverage-output.txt
+          
+          E2E_PASS=$(grep -oP '[0-9]+(?=/)' e2e-output.txt | tail -1)
+          
+          mkdir -p .badges
+          if [ -f .nyc_output/frontend-coverage.json ]; then
+            npx nyc report --reporter=text-summary --reporter=text 2>&1 | tee fe-report.txt
+            FE_COVERAGE=$(grep 'Statements' fe-report.txt | head -1 | grep -oP '[\d.]+(?=%)' || echo "0")
+            FE_COVERAGE=${FE_COVERAGE:-0}
+            FE_COLOR="red"
+            [ "$(echo "$FE_COVERAGE > 50" | bc -l 2>/dev/null)" = "1" ] && FE_COLOR="yellow"
+            [ "$(echo "$FE_COVERAGE > 80" | bc -l 2>/dev/null)" = "1" ] && FE_COLOR="brightgreen"
+            echo "{\"schemaVersion\":1,\"label\":\"frontend coverage\",\"message\":\"${FE_COVERAGE}%\",\"color\":\"${FE_COLOR}\"}" > .badges/frontend-coverage.json
+            echo "## Frontend: ${FE_COVERAGE}% coverage" >> $GITHUB_STEP_SUMMARY
+          fi
+          echo "{\"schemaVersion\":1,\"label\":\"frontend tests\",\"message\":\"${E2E_PASS:-0} E2E passed\",\"color\":\"brightgreen\"}" > .badges/frontend-tests.json
+
+      - name: Stop test server
+        if: always() && steps.changes.outputs.frontend == 'true'
+        run: |
+          if [ -f .server.pid ]; then
+            kill $(cat .server.pid) 2>/dev/null || true
+            rm -f .server.pid
+            echo "Server stopped"
+          fi
+
+      - name: Run frontend E2E (quick, no coverage)
+        if: steps.changes.outputs.frontend == 'false'
+        run: |
+          fuser -k 13581/tcp 2>/dev/null || true
+          PORT=13581 node server.js &
+          SERVER_PID=$!
+          sleep 5
+          BASE_URL=http://localhost:13581 node test-e2e-playwright.js || true
+          kill $SERVER_PID 2>/dev/null || true
+
+      - name: Upload Node.js test badges
+        if: always()
+        uses: actions/upload-artifact@v4
+        with:
+          name: node-badges
+          path: .badges/
+          retention-days: 1
+          if-no-files-found: ignore
+
+  # ───────────────────────────────────────────────────────────────
+  # 3. Build Docker Image
+  # ───────────────────────────────────────────────────────────────
+  build:
+    name: "🏗️ Build Docker Image"
+    if: github.event_name == 'push'
+    needs: [go-test]
+    runs-on: self-hosted
+    steps:
+      - name: Checkout code
+        uses: actions/checkout@v4
+
+      - name: Set up Node.js 22
+        uses: actions/setup-node@v4
+        with:
+          node-version: '22'
+
+      - name: Build Go Docker image
+        run: |
+          echo "${GITHUB_SHA::7}" > .git-commit
+          APP_VERSION=$(node -p "require('./package.json').version") \
+          GIT_COMMIT="${GITHUB_SHA::7}" \
+          docker compose --profile staging-go build staging-go
+          echo "Built Go staging image"
+
+  # ───────────────────────────────────────────────────────────────
+  # 4. Deploy Staging — start on port 82, healthcheck, smoke test
+  # ───────────────────────────────────────────────────────────────
+  deploy:
+    name: "🚀 Deploy Staging"
+    if: github.event_name == 'push'
+    needs: [build]
+    runs-on: self-hosted
+    steps:
+      - name: Checkout code
+        uses: actions/checkout@v4
+
+      - name: Start staging on port 82
+        run: |
+          # Force remove stale containers
+          docker rm -f corescope-staging-go 2>/dev/null || true
+          # Clean up stale ports
+          fuser -k 82/tcp 2>/dev/null || true
+          docker compose --profile staging-go up -d staging-go
+
+      - name: Healthcheck staging container
+        run: |
+          for i in $(seq 1 120); do
+            HEALTH=$(docker inspect corescope-staging-go --format '{{.State.Health.Status}}' 2>/dev/null || echo "starting")
+            if [ "$HEALTH" = "healthy" ]; then
+              echo "Staging healthy after ${i}s"
+              break
+            fi
+            if [ "$i" -eq 120 ]; then
+              echo "Staging failed health check after 120s"
+              docker logs corescope-staging-go --tail 50
+              exit 1
+            fi
+            sleep 1
+          done
+
+      - name: Smoke test staging API
+        run: |
+          if curl -sf http://localhost:82/api/stats | grep -q engine; then
+            echo "Staging verified — engine field present ✅"
+          else
+            echo "Staging /api/stats did not return engine field"
+            exit 1
+          fi
+
+  # ───────────────────────────────────────────────────────────────
+  # 5. Publish Badges & Summary
+  # ───────────────────────────────────────────────────────────────
+  publish:
+    name: "📝 Publish Badges & Summary"
+    if: github.event_name == 'push'
+    needs: [deploy]
+    runs-on: self-hosted
+    steps:
+      - name: Checkout code
+        uses: actions/checkout@v4
+
+      - name: Download Go coverage badges
+        continue-on-error: true
+        uses: actions/download-artifact@v4
+        with:
+          name: go-badges
+          path: .badges/
+
+      - name: Download Node.js test badges
+        continue-on-error: true
+        uses: actions/download-artifact@v4
+        with:
+          name: node-badges
+          path: .badges/
+
+      - name: Publish coverage badges to repo
+        continue-on-error: true
+        run: |
+          git config user.name "github-actions"
+          git config user.email "actions@github.com"
+          git remote set-url origin https://x-access-token:${{ github.token }}@github.com/${{ github.repository }}.git
+          git add .badges/ -f
+          git diff --cached --quiet || (git commit -m "ci: update test badges [skip ci]" && git push) || echo "Badge push failed"
+
+      - name: Post deployment summary
+        run: |
+          echo "## Staging Deployed ✓" >> $GITHUB_STEP_SUMMARY
+          echo "" >> $GITHUB_STEP_SUMMARY
+          echo "**Commit:** \`$(git rev-parse --short HEAD)\` — $(git log -1 --format=%s)" >> $GITHUB_STEP_SUMMARY
+          echo "" >> $GITHUB_STEP_SUMMARY
+          echo "**Staging:** http://<VM_HOST>:82" >> $GITHUB_STEP_SUMMARY
+          echo "" >> $GITHUB_STEP_SUMMARY
+          echo "To promote to production:" >> $GITHUB_STEP_SUMMARY
+          echo "\`\`\`bash" >> $GITHUB_STEP_SUMMARY
+          echo "ssh deploy@\$VM_HOST" >> $GITHUB_STEP_SUMMARY
+          echo "cd /opt/corescope-deploy" >> $GITHUB_STEP_SUMMARY
+          echo "./manage.sh promote" >> $GITHUB_STEP_SUMMARY
+          echo "\`\`\`" >> $GITHUB_STEP_SUMMARY
@@ -1,171 +0,0 @@
-name: Squad Heartbeat (Ralph)
-# ⚠️ SYNC: This workflow is maintained in 4 locations. Changes must be applied to all:
-#   - templates/workflows/squad-heartbeat.yml (source template)
-#   - packages/squad-cli/templates/workflows/squad-heartbeat.yml (CLI package)
-#   - .squad/templates/workflows/squad-heartbeat.yml (installed template)
-#   - .github/workflows/squad-heartbeat.yml (active workflow)
-# Run 'squad upgrade' to sync installed copies from source templates.
-
-on:
-  schedule:
-    # Every 30 minutes — adjust via cron expression as needed
-    - cron: '*/30 * * * *'
-
-  # React to completed work or new squad work
-  issues:
-    types: [closed, labeled]
-  pull_request:
-    types: [closed]
-
-  # Manual trigger
-  workflow_dispatch:
-
-permissions:
-  issues: write
-  contents: read
-  pull-requests: read
-
-jobs:
-  heartbeat:
-    runs-on: ubuntu-latest
-    steps:
-      - uses: actions/checkout@v4
-
-      - name: Check triage script
-        id: check-script
-        run: |
-          if [ -f ".squad/templates/ralph-triage.js" ]; then
-            echo "has_script=true" >> $GITHUB_OUTPUT
-          else
-            echo "has_script=false" >> $GITHUB_OUTPUT
-            echo "⚠️ ralph-triage.js not found — run 'squad upgrade' to install"
-          fi
-
-      - name: Ralph — Smart triage
-        if: steps.check-script.outputs.has_script == 'true'
-        env:
-          GITHUB_TOKEN: ${{ secrets.GITHUB_TOKEN }}
-        run: |
-          node .squad/templates/ralph-triage.js \
-            --squad-dir .squad \
-            --output triage-results.json
-
-      - name: Ralph — Apply triage decisions
-        if: steps.check-script.outputs.has_script == 'true' && hashFiles('triage-results.json') != ''
-        uses: actions/github-script@v7
-        with:
-          script: |
-            const fs = require('fs');
-            const path = 'triage-results.json';
-            if (!fs.existsSync(path)) {
-              core.info('No triage results — board is clear');
-              return;
-            }
-            
-            const results = JSON.parse(fs.readFileSync(path, 'utf8'));
-            if (results.length === 0) {
-              core.info('📋 Board is clear — Ralph found no untriaged issues');
-              return;
-            }
-            
-            for (const decision of results) {
-              try {
-                await github.rest.issues.addLabels({
-                  owner: context.repo.owner,
-                  repo: context.repo.repo,
-                  issue_number: decision.issueNumber,
-                  labels: [decision.label]
-                });
-                
-                await github.rest.issues.createComment({
-                  owner: context.repo.owner,
-                  repo: context.repo.repo,
-                  issue_number: decision.issueNumber,
-                  body: [
-                    '### 🔄 Ralph — Auto-Triage',
-                    '',
-                    `**Assigned to:** ${decision.assignTo}`,
-                    `**Reason:** ${decision.reason}`,
-                    `**Source:** ${decision.source}`,
-                    '',
-                    '> Ralph auto-triaged this issue using routing rules.',
-                    '> To reassign, swap the `squad:*` label.'
-                  ].join('\n')
-                });
-                
-                core.info(`Triaged #${decision.issueNumber} → ${decision.assignTo} (${decision.source})`);
-              } catch (e) {
-                core.warning(`Failed to triage #${decision.issueNumber}: ${e.message}`);
-              }
-            }
-            
-            core.info(`🔄 Ralph triaged ${results.length} issue(s)`);
-
-      # Copilot auto-assign step (uses PAT if available)
-      - name: Ralph — Assign @copilot issues
-        if: success()
-        uses: actions/github-script@v7
-        with:
-          github-token: ${{ secrets.COPILOT_ASSIGN_TOKEN || secrets.GITHUB_TOKEN }}
-          script: |
-            const fs = require('fs');
-
-            let teamFile = '.squad/team.md';
-            if (!fs.existsSync(teamFile)) {
-              teamFile = '.ai-team/team.md';
-            }
-            if (!fs.existsSync(teamFile)) return;
-
-            const content = fs.readFileSync(teamFile, 'utf8');
-
-            // Check if @copilot is on the team with auto-assign
-            const hasCopilot = content.includes('🤖 Coding Agent') || content.includes('@copilot');
-            const autoAssign = content.includes('<!-- copilot-auto-assign: true -->');
-            if (!hasCopilot || !autoAssign) return;
-
-            // Find issues labeled squad:copilot with no assignee
-            try {
-              const { data: copilotIssues } = await github.rest.issues.listForRepo({
-                owner: context.repo.owner,
-                repo: context.repo.repo,
-                labels: 'squad:copilot',
-                state: 'open',
-                per_page: 5
-              });
-
-              const unassigned = copilotIssues.filter(i =>
-                !i.assignees || i.assignees.length === 0
-              );
-
-              if (unassigned.length === 0) {
-                core.info('No unassigned squad:copilot issues');
-                return;
-              }
-
-              // Get repo default branch
-              const { data: repoData } = await github.rest.repos.get({
-                owner: context.repo.owner,
-                repo: context.repo.repo
-              });
-
-              for (const issue of unassigned) {
-                try {
-                  await github.request('POST /repos/{owner}/{repo}/issues/{issue_number}/assignees', {
-                    owner: context.repo.owner,
-                    repo: context.repo.repo,
-                    issue_number: issue.number,
-                    assignees: ['copilot-swe-agent[bot]'],
-                    agent_assignment: {
-                      target_repo: `${context.repo.owner}/${context.repo.repo}`,
-                      base_branch: repoData.default_branch,
-                      custom_instructions: `Read .squad/team.md (or .ai-team/team.md) for team context and .squad/routing.md (or .ai-team/routing.md) for routing rules.`
-                    }
-                  });
-                  core.info(`Assigned copilot-swe-agent[bot] to #${issue.number}`);
-                } catch (e) {
-                  core.warning(`Failed to assign @copilot to #${issue.number}: ${e.message}`);
-                }
-              }
-            } catch (e) {
-              core.info(`No squad:copilot label found or error: ${e.message}`);
-            }
@@ -1,161 +0,0 @@
-name: Squad Issue Assign
-
-on:
-  issues:
-    types: [labeled]
-
-permissions:
-  issues: write
-  contents: read
-
-jobs:
-  assign-work:
-    # Only trigger on squad:{member} labels (not the base "squad" label)
-    if: startsWith(github.event.label.name, 'squad:')
-    runs-on: ubuntu-latest
-    steps:
-      - uses: actions/checkout@v4
-
-      - name: Identify assigned member and trigger work
-        uses: actions/github-script@v7
-        with:
-          script: |
-            const fs = require('fs');
-            const issue = context.payload.issue;
-            const label = context.payload.label.name;
-
-            // Extract member name from label (e.g., "squad:ripley" → "ripley")
-            const memberName = label.replace('squad:', '').toLowerCase();
-
-            // Read team roster — check .squad/ first, fall back to .ai-team/
-            let teamFile = '.squad/team.md';
-            if (!fs.existsSync(teamFile)) {
-              teamFile = '.ai-team/team.md';
-            }
-            if (!fs.existsSync(teamFile)) {
-              core.warning('No .squad/team.md or .ai-team/team.md found — cannot assign work');
-              return;
-            }
-
-            const content = fs.readFileSync(teamFile, 'utf8');
-            const lines = content.split('\n');
-
-            // Check if this is a coding agent assignment
-            const isCopilotAssignment = memberName === 'copilot';
-
-            let assignedMember = null;
-            if (isCopilotAssignment) {
-              assignedMember = { name: '@copilot', role: 'Coding Agent' };
-            } else {
-              let inMembersTable = false;
-              for (const line of lines) {
-                if (line.match(/^##\s+(Members|Team Roster)/i)) {
-                  inMembersTable = true;
-                  continue;
-                }
-                if (inMembersTable && line.startsWith('## ')) {
-                  break;
-                }
-                if (inMembersTable && line.startsWith('|') && !line.includes('---') && !line.includes('Name')) {
-                  const cells = line.split('|').map(c => c.trim()).filter(Boolean);
-                  if (cells.length >= 2 && cells[0].toLowerCase() === memberName) {
-                    assignedMember = { name: cells[0], role: cells[1] };
-                    break;
-                  }
-                }
-              }
-            }
-
-            if (!assignedMember) {
-              core.warning(`No member found matching label "${label}"`);
-              await github.rest.issues.createComment({
-                owner: context.repo.owner,
-                repo: context.repo.repo,
-                issue_number: issue.number,
-                body: `⚠️ No squad member found matching label \`${label}\`. Check \`.squad/team.md\` (or \`.ai-team/team.md\`) for valid member names.`
-              });
-              return;
-            }
-
-            // Post assignment acknowledgment
-            let comment;
-            if (isCopilotAssignment) {
-              comment = [
-                `### 🤖 Routed to @copilot (Coding Agent)`,
-                '',
-                `**Issue:** #${issue.number} — ${issue.title}`,
-                '',
-                `@copilot has been assigned and will pick this up automatically.`,
-                '',
-                `> The coding agent will create a \`copilot/*\` branch and open a draft PR.`,
-                `> Review the PR as you would any team member's work.`,
-              ].join('\n');
-            } else {
-              comment = [
-                `### 📋 Assigned to ${assignedMember.name} (${assignedMember.role})`,
-                '',
-                `**Issue:** #${issue.number} — ${issue.title}`,
-                '',
-                `${assignedMember.name} will pick this up in the next Copilot session.`,
-                '',
-                `> **For Copilot coding agent:** If enabled, this issue will be worked automatically.`,
-                `> Otherwise, start a Copilot session and say:`,
-                `> \`${assignedMember.name}, work on issue #${issue.number}\``,
-              ].join('\n');
-            }
-
-            await github.rest.issues.createComment({
-              owner: context.repo.owner,
-              repo: context.repo.repo,
-              issue_number: issue.number,
-              body: comment
-            });
-
-            core.info(`Issue #${issue.number} assigned to ${assignedMember.name} (${assignedMember.role})`);
-
-      # Separate step: assign @copilot using PAT (required for coding agent)
-      - name: Assign @copilot coding agent
-        if: github.event.label.name == 'squad:copilot'
-        uses: actions/github-script@v7
-        with:
-          github-token: ${{ secrets.COPILOT_ASSIGN_TOKEN }}
-          script: |
-            const owner = context.repo.owner;
-            const repo = context.repo.repo;
-            const issue_number = context.payload.issue.number;
-
-            // Get the default branch name (main, master, etc.)
-            const { data: repoData } = await github.rest.repos.get({ owner, repo });
-            const baseBranch = repoData.default_branch;
-
-            try {
-              await github.request('POST /repos/{owner}/{repo}/issues/{issue_number}/assignees', {
-                owner,
-                repo,
-                issue_number,
-                assignees: ['copilot-swe-agent[bot]'],
-                agent_assignment: {
-                  target_repo: `${owner}/${repo}`,
-                  base_branch: baseBranch,
-                  custom_instructions: '',
-                  custom_agent: '',
-                  model: ''
-                },
-                headers: {
-                  'X-GitHub-Api-Version': '2022-11-28'
-                }
-              });
-              core.info(`Assigned copilot-swe-agent to issue #${issue_number} (base: ${baseBranch})`);
-            } catch (err) {
-              core.warning(`Assignment with agent_assignment failed: ${err.message}`);
-              // Fallback: try without agent_assignment
-              try {
-                await github.rest.issues.addAssignees({
-                  owner, repo, issue_number,
-                  assignees: ['copilot-swe-agent']
-                });
-                core.info(`Fallback assigned copilot-swe-agent to issue #${issue_number}`);
-              } catch (err2) {
-                core.warning(`Fallback also failed: ${err2.message}`);
-              }
-            }
@@ -1,260 +0,0 @@
-name: Squad Triage
-
-on:
-  issues:
-    types: [labeled]
-
-permissions:
-  issues: write
-  contents: read
-
-jobs:
-  triage:
-    if: github.event.label.name == 'squad'
-    runs-on: ubuntu-latest
-    steps:
-      - uses: actions/checkout@v4
-
-      - name: Triage issue via Lead agent
-        uses: actions/github-script@v7
-        with:
-          script: |
-            const fs = require('fs');
-            const issue = context.payload.issue;
-
-            // Read team roster — check .squad/ first, fall back to .ai-team/
-            let teamFile = '.squad/team.md';
-            if (!fs.existsSync(teamFile)) {
-              teamFile = '.ai-team/team.md';
-            }
-            if (!fs.existsSync(teamFile)) {
-              core.warning('No .squad/team.md or .ai-team/team.md found — cannot triage');
-              return;
-            }
-
-            const content = fs.readFileSync(teamFile, 'utf8');
-            const lines = content.split('\n');
-
-            // Check if @copilot is on the team
-            const hasCopilot = content.includes('🤖 Coding Agent');
-            const copilotAutoAssign = content.includes('<!-- copilot-auto-assign: true -->');
-
-            // Parse @copilot capability profile
-            let goodFitKeywords = [];
-            let needsReviewKeywords = [];
-            let notSuitableKeywords = [];
-
-            if (hasCopilot) {
-              // Extract capability tiers from team.md
-              const goodFitMatch = content.match(/🟢\s*Good fit[^:]*:\s*(.+)/i);
-              const needsReviewMatch = content.match(/🟡\s*Needs review[^:]*:\s*(.+)/i);
-              const notSuitableMatch = content.match(/🔴\s*Not suitable[^:]*:\s*(.+)/i);
-
-              if (goodFitMatch) {
-                goodFitKeywords = goodFitMatch[1].toLowerCase().split(',').map(s => s.trim());
-              } else {
-                goodFitKeywords = ['bug fix', 'test coverage', 'lint', 'format', 'dependency update', 'small feature', 'scaffolding', 'doc fix', 'documentation'];
-              }
-              if (needsReviewMatch) {
-                needsReviewKeywords = needsReviewMatch[1].toLowerCase().split(',').map(s => s.trim());
-              } else {
-                needsReviewKeywords = ['medium feature', 'refactoring', 'api endpoint', 'migration'];
-              }
-              if (notSuitableMatch) {
-                notSuitableKeywords = notSuitableMatch[1].toLowerCase().split(',').map(s => s.trim());
-              } else {
-                notSuitableKeywords = ['architecture', 'system design', 'security', 'auth', 'encryption', 'performance'];
-              }
-            }
-
-            const members = [];
-            let inMembersTable = false;
-            for (const line of lines) {
-              if (line.match(/^##\s+(Members|Team Roster)/i)) {
-                inMembersTable = true;
-                continue;
-              }
-              if (inMembersTable && line.startsWith('## ')) {
-                break;
-              }
-              if (inMembersTable && line.startsWith('|') && !line.includes('---') && !line.includes('Name')) {
-                const cells = line.split('|').map(c => c.trim()).filter(Boolean);
-                if (cells.length >= 2 && cells[0] !== 'Scribe') {
-                  members.push({
-                    name: cells[0],
-                    role: cells[1]
-                  });
-                }
-              }
-            }
-
-            // Read routing rules — check .squad/ first, fall back to .ai-team/
-            let routingFile = '.squad/routing.md';
-            if (!fs.existsSync(routingFile)) {
-              routingFile = '.ai-team/routing.md';
-            }
-            let routingContent = '';
-            if (fs.existsSync(routingFile)) {
-              routingContent = fs.readFileSync(routingFile, 'utf8');
-            }
-
-            // Find the Lead
-            const lead = members.find(m =>
-              m.role.toLowerCase().includes('lead') ||
-              m.role.toLowerCase().includes('architect') ||
-              m.role.toLowerCase().includes('coordinator')
-            );
-
-            if (!lead) {
-              core.warning('No Lead role found in team roster — cannot triage');
-              return;
-            }
-
-            // Build triage context
-            const memberList = members.map(m =>
-              `- **${m.name}** (${m.role}) → label: \`squad:${m.name.toLowerCase()}\``
-            ).join('\n');
-
-            // Determine best assignee based on issue content and routing
-            const issueText = `${issue.title}\n${issue.body || ''}`.toLowerCase();
-
-            let assignedMember = null;
-            let triageReason = '';
-            let copilotTier = null;
-
-            // First, evaluate @copilot fit if enabled
-            if (hasCopilot) {
-              const isNotSuitable = notSuitableKeywords.some(kw => issueText.includes(kw));
-              const isGoodFit = !isNotSuitable && goodFitKeywords.some(kw => issueText.includes(kw));
-              const isNeedsReview = !isNotSuitable && !isGoodFit && needsReviewKeywords.some(kw => issueText.includes(kw));
-
-              if (isGoodFit) {
-                copilotTier = 'good-fit';
-                assignedMember = { name: '@copilot', role: 'Coding Agent' };
-                triageReason = '🟢 Good fit for @copilot — matches capability profile';
-              } else if (isNeedsReview) {
-                copilotTier = 'needs-review';
-                assignedMember = { name: '@copilot', role: 'Coding Agent' };
-                triageReason = '🟡 Routing to @copilot (needs review) — a squad member should review the PR';
-              } else if (isNotSuitable) {
-                copilotTier = 'not-suitable';
-                // Fall through to normal routing
-              }
-            }
-
-            // If not routed to @copilot, use keyword-based routing
-            if (!assignedMember) {
-              for (const member of members) {
-                const role = member.role.toLowerCase();
-                if ((role.includes('frontend') || role.includes('ui')) &&
-                    (issueText.includes('ui') || issueText.includes('frontend') ||
-                     issueText.includes('css') || issueText.includes('component') ||
-                     issueText.includes('button') || issueText.includes('page') ||
-                     issueText.includes('layout') || issueText.includes('design'))) {
-                  assignedMember = member;
-                  triageReason = 'Issue relates to frontend/UI work';
-                  break;
-                }
-                if ((role.includes('backend') || role.includes('api') || role.includes('server')) &&
-                    (issueText.includes('api') || issueText.includes('backend') ||
-                     issueText.includes('database') || issueText.includes('endpoint') ||
-                     issueText.includes('server') || issueText.includes('auth'))) {
-                  assignedMember = member;
-                  triageReason = 'Issue relates to backend/API work';
-                  break;
-                }
-                if ((role.includes('test') || role.includes('qa') || role.includes('quality')) &&
-                    (issueText.includes('test') || issueText.includes('bug') ||
-                     issueText.includes('fix') || issueText.includes('regression') ||
-                     issueText.includes('coverage'))) {
-                  assignedMember = member;
-                  triageReason = 'Issue relates to testing/quality work';
-                  break;
-                }
-                if ((role.includes('devops') || role.includes('infra') || role.includes('ops')) &&
-                    (issueText.includes('deploy') || issueText.includes('ci') ||
-                     issueText.includes('pipeline') || issueText.includes('docker') ||
-                     issueText.includes('infrastructure'))) {
-                  assignedMember = member;
-                  triageReason = 'Issue relates to DevOps/infrastructure work';
-                  break;
-                }
-              }
-            }
-
-            // Default to Lead if no routing match
-            if (!assignedMember) {
-              assignedMember = lead;
-              triageReason = 'No specific domain match — assigned to Lead for further analysis';
-            }
-
-            const isCopilot = assignedMember.name === '@copilot';
-            const assignLabel = isCopilot ? 'squad:copilot' : `squad:${assignedMember.name.toLowerCase()}`;
-
-            // Add the member-specific label
-            await github.rest.issues.addLabels({
-              owner: context.repo.owner,
-              repo: context.repo.repo,
-              issue_number: issue.number,
-              labels: [assignLabel]
-            });
-
-            // Apply default triage verdict
-            await github.rest.issues.addLabels({
-              owner: context.repo.owner,
-              repo: context.repo.repo,
-              issue_number: issue.number,
-              labels: ['go:needs-research']
-            });
-
-            // Auto-assign @copilot if enabled
-            if (isCopilot && copilotAutoAssign) {
-              try {
-                await github.rest.issues.addAssignees({
-                  owner: context.repo.owner,
-                  repo: context.repo.repo,
-                  issue_number: issue.number,
-                  assignees: ['copilot']
-                });
-              } catch (err) {
-                core.warning(`Could not auto-assign @copilot: ${err.message}`);
-              }
-            }
-
-            // Build copilot evaluation note
-            let copilotNote = '';
-            if (hasCopilot && !isCopilot) {
-              if (copilotTier === 'not-suitable') {
-                copilotNote = `\n\n**@copilot evaluation:** 🔴 Not suitable — issue involves work outside the coding agent's capability profile.`;
-              } else {
-                copilotNote = `\n\n**@copilot evaluation:** No strong capability match — routed to squad member.`;
-              }
-            }
-
-            // Post triage comment
-            const comment = [
-              `### 🏗️ Squad Triage — ${lead.name} (${lead.role})`,
-              '',
-              `**Issue:** #${issue.number} — ${issue.title}`,
-              `**Assigned to:** ${assignedMember.name} (${assignedMember.role})`,
-              `**Reason:** ${triageReason}`,
-              copilotTier === 'needs-review' ? `\n⚠️ **PR review recommended** — a squad member should review @copilot's work on this one.` : '',
-              copilotNote,
-              '',
-              `---`,
-              '',
-              `**Team roster:**`,
-              memberList,
-              hasCopilot ? `- **@copilot** (Coding Agent) → label: \`squad:copilot\`` : '',
-              '',
-              `> To reassign, remove the current \`squad:*\` label and add the correct one.`,
-            ].filter(Boolean).join('\n');
-
-            await github.rest.issues.createComment({
-              owner: context.repo.owner,
-              repo: context.repo.repo,
-              issue_number: issue.number,
-              body: comment
-            });
-
-            core.info(`Triaged issue #${issue.number} → ${assignedMember.name} (${assignLabel})`);
@@ -1,169 +0,0 @@
-name: Sync Squad Labels
-
-on:
-  push:
-    paths:
-      - '.squad/team.md'
-      - '.ai-team/team.md'
-  workflow_dispatch:
-
-permissions:
-  issues: write
-  contents: read
-
-jobs:
-  sync-labels:
-    runs-on: ubuntu-latest
-    steps:
-      - uses: actions/checkout@v4
-
-      - name: Parse roster and sync labels
-        uses: actions/github-script@v7
-        with:
-          script: |
-            const fs = require('fs');
-            let teamFile = '.squad/team.md';
-            if (!fs.existsSync(teamFile)) {
-              teamFile = '.ai-team/team.md';
-            }
-
-            if (!fs.existsSync(teamFile)) {
-              core.info('No .squad/team.md or .ai-team/team.md found — skipping label sync');
-              return;
-            }
-
-            const content = fs.readFileSync(teamFile, 'utf8');
-            const lines = content.split('\n');
-
-            // Parse the Members table for agent names
-            const members = [];
-            let inMembersTable = false;
-            for (const line of lines) {
-              if (line.match(/^##\s+(Members|Team Roster)/i)) {
-                inMembersTable = true;
-                continue;
-              }
-              if (inMembersTable && line.startsWith('## ')) {
-                break;
-              }
-              if (inMembersTable && line.startsWith('|') && !line.includes('---') && !line.includes('Name')) {
-                const cells = line.split('|').map(c => c.trim()).filter(Boolean);
-                if (cells.length >= 2 && cells[0] !== 'Scribe') {
-                  members.push({
-                    name: cells[0],
-                    role: cells[1]
-                  });
-                }
-              }
-            }
-
-            core.info(`Found ${members.length} squad members: ${members.map(m => m.name).join(', ')}`);
-
-            // Check if @copilot is on the team
-            const hasCopilot = content.includes('🤖 Coding Agent');
-
-            // Define label color palette for squad labels
-            const SQUAD_COLOR = '9B8FCC';
-            const MEMBER_COLOR = '9B8FCC';
-            const COPILOT_COLOR = '10b981';
-
-            // Define go: and release: labels (static)
-            const GO_LABELS = [
-              { name: 'go:yes', color: '0E8A16', description: 'Ready to implement' },
-              { name: 'go:no', color: 'B60205', description: 'Not pursuing' },
-              { name: 'go:needs-research', color: 'FBCA04', description: 'Needs investigation' }
-            ];
-
-            const RELEASE_LABELS = [
-              { name: 'release:v0.4.0', color: '6B8EB5', description: 'Targeted for v0.4.0' },
-              { name: 'release:v0.5.0', color: '6B8EB5', description: 'Targeted for v0.5.0' },
-              { name: 'release:v0.6.0', color: '8B7DB5', description: 'Targeted for v0.6.0' },
-              { name: 'release:v1.0.0', color: '8B7DB5', description: 'Targeted for v1.0.0' },
-              { name: 'release:backlog', color: 'D4E5F7', description: 'Not yet targeted' }
-            ];
-
-            const TYPE_LABELS = [
-              { name: 'type:feature', color: 'DDD1F2', description: 'New capability' },
-              { name: 'type:bug', color: 'FF0422', description: 'Something broken' },
-              { name: 'type:spike', color: 'F2DDD4', description: 'Research/investigation — produces a plan, not code' },
-              { name: 'type:docs', color: 'D4E5F7', description: 'Documentation work' },
-              { name: 'type:chore', color: 'D4E5F7', description: 'Maintenance, refactoring, cleanup' },
-              { name: 'type:epic', color: 'CC4455', description: 'Parent issue that decomposes into sub-issues' }
-            ];
-
-            // High-signal labels — these MUST visually dominate all others
-            const SIGNAL_LABELS = [
-              { name: 'bug', color: 'FF0422', description: 'Something isn\'t working' },
-              { name: 'feedback', color: '00E5FF', description: 'User feedback — high signal, needs attention' }
-            ];
-
-            const PRIORITY_LABELS = [
-              { name: 'priority:p0', color: 'B60205', description: 'Blocking release' },
-              { name: 'priority:p1', color: 'D93F0B', description: 'This sprint' },
-              { name: 'priority:p2', color: 'FBCA04', description: 'Next sprint' }
-            ];
-
-            // Ensure the base "squad" triage label exists
-            const labels = [
-              { name: 'squad', color: SQUAD_COLOR, description: 'Squad triage inbox — Lead will assign to a member' }
-            ];
-
-            for (const member of members) {
-              labels.push({
-                name: `squad:${member.name.toLowerCase()}`,
-                color: MEMBER_COLOR,
-                description: `Assigned to ${member.name} (${member.role})`
-              });
-            }
-
-            // Add @copilot label if coding agent is on the team
-            if (hasCopilot) {
-              labels.push({
-                name: 'squad:copilot',
-                color: COPILOT_COLOR,
-                description: 'Assigned to @copilot (Coding Agent) for autonomous work'
-              });
-            }
-
-            // Add go:, release:, type:, priority:, and high-signal labels
-            labels.push(...GO_LABELS);
-            labels.push(...RELEASE_LABELS);
-            labels.push(...TYPE_LABELS);
-            labels.push(...PRIORITY_LABELS);
-            labels.push(...SIGNAL_LABELS);
-
-            // Sync labels (create or update)
-            for (const label of labels) {
-              try {
-                await github.rest.issues.getLabel({
-                  owner: context.repo.owner,
-                  repo: context.repo.repo,
-                  name: label.name
-                });
-                // Label exists — update it
-                await github.rest.issues.updateLabel({
-                  owner: context.repo.owner,
-                  repo: context.repo.repo,
-                  name: label.name,
-                  color: label.color,
-                  description: label.description
-                });
-                core.info(`Updated label: ${label.name}`);
-              } catch (err) {
-                if (err.status === 404) {
-                  // Label doesn't exist — create it
-                  await github.rest.issues.createLabel({
-                    owner: context.repo.owner,
-                    repo: context.repo.repo,
-                    name: label.name,
-                    color: label.color,
-                    description: label.description
-                  });
-                  core.info(`Created label: ${label.name}`);
-                } else {
-                  throw err;
-                }
-              }
-            }
-
-            core.info(`Label sync complete: ${labels.length} labels synced`);
@@ -27,7 +27,4 @@ replacements.txt
 reps.txt
 cmd/server/server.exe
 cmd/ingestor/ingestor.exe
-# CI trigger
-!test-fixtures/e2e-fixture.db
-corescope-server
-cmd/server/server
+# CI trigger
@@ -1,10 +0,0 @@
-{
-  "include": [
-    "public/*.js"
-  ],
-  "exclude": [
-    "public/vendor/**",
-    "public/leaflet-*.js",
-    "public/qrcode*.js"
-  ]
-}
@@ -1,48 +1,48 @@
-# Bishop — Tester
-
-Unit tests, Playwright E2E, coverage gates, and quality assurance for CoreScope.
-
-## Project Context
-
-**Project:** CoreScope — Real-time LoRa mesh packet analyzer
-**Stack:** Node.js native test runner, Playwright, c8 + nyc (coverage), supertest
-**User:** User
-
-## Responsibilities
-
- Unit tests: test-packet-filter.js, test-aging.js, test-decoder.js, test-decoder-spec.js, test-server-helpers.js, test-server-routes.js, test-packet-store.js, test-db.js, test-frontend-helpers.js, test-regional-filter.js, test-regional-integration.js, test-live-dedup.js
- Playwright E2E: test-e2e-playwright.js (8 browser tests, default localhost:3000)
- E2E tools: tools/e2e-test.js, tools/frontend-test.js
- Coverage: Backend 85%+ (c8), Frontend 42%+ (Istanbul + nyc). Both only go up.
- Review authority: May approve or reject work from Hicks and Newt based on test results
-
-## Boundaries
-
- Test the REAL code — import actual modules, don't copy-paste functions into test files
- Use vm.createContext for frontend helpers (see test-frontend-helpers.js pattern)
- Playwright tests default to localhost:3000 — NEVER run against prod
- Every bug fix gets a regression test
- Every new feature must add tests — test count only goes up
- Run `npm test` to verify all tests pass before approving
-
-## Review Authority
-
- May approve or reject based on test coverage and quality
- On rejection: specify what tests are missing or failing
- Lockout rules apply
-
-## Key Test Commands
-
-```
-npm test                    # all backend tests + coverage summary
-npm run test:unit           # fast: unit tests only
-npm run test:coverage       # all tests + HTML coverage report
-node test-packet-filter.js  # filter engine
-node test-decoder.js        # packet decoder
-node test-server-routes.js  # API routes via supertest
-node test-e2e-playwright.js # 8 Playwright browser tests
-```
-
-## Model
-
-Preferred: auto
+# Bishop — Tester
+
+Unit tests, Playwright E2E, coverage gates, and quality assurance for CoreScope.
+
+## Project Context
+
+**Project:** CoreScope — Real-time LoRa mesh packet analyzer
+**Stack:** Node.js native test runner, Playwright, c8 + nyc (coverage), supertest
+**User:** User
+
+## Responsibilities
+
+- Unit tests: test-packet-filter.js, test-aging.js, test-decoder.js, test-decoder-spec.js, test-server-helpers.js, test-server-routes.js, test-packet-store.js, test-db.js, test-frontend-helpers.js, test-regional-filter.js, test-regional-integration.js, test-live-dedup.js
+- Playwright E2E: test-e2e-playwright.js (8 browser tests, default localhost:3000)
+- E2E tools: tools/e2e-test.js, tools/frontend-test.js
+- Coverage: Backend 85%+ (c8), Frontend 42%+ (Istanbul + nyc). Both only go up.
+- Review authority: May approve or reject work from Hicks and Newt based on test results
+
+## Boundaries
+
+- Test the REAL code — import actual modules, don't copy-paste functions into test files
+- Use vm.createContext for frontend helpers (see test-frontend-helpers.js pattern)
+- Playwright tests default to localhost:3000 — NEVER run against prod
+- Every bug fix gets a regression test
+- Every new feature must add tests — test count only goes up
+- Run `npm test` to verify all tests pass before approving
+
+## Review Authority
+
+- May approve or reject based on test coverage and quality
+- On rejection: specify what tests are missing or failing
+- Lockout rules apply
+
+## Key Test Commands
+
+```
+npm test                    # all backend tests + coverage summary
+npm run test:unit           # fast: unit tests only
+npm run test:coverage       # all tests + HTML coverage report
+node test-packet-filter.js  # filter engine
+node test-decoder.js        # packet decoder
+node test-server-routes.js  # API routes via supertest
+node test-e2e-playwright.js # 8 Playwright browser tests
+```
+
+## Model
+
+Preferred: auto
@@ -1,76 +1,76 @@
-# Bishop — History
-
-## Project Context
-
-CoreScope has 14 test files, 4,290 lines of test code. Backend coverage 85%+, frontend 42%+. Tests use Node.js native runner, Playwright for E2E, c8/nyc for coverage, supertest for API routes. vm.createContext pattern used for testing frontend helpers in Node.js.
-
-User: User
-
-## Learnings
-
- Session started 2026-03-26. Team formed: Kobayashi (Lead), Hicks (Backend), Newt (Frontend), Bishop (Tester).
- E2E run 2026-03-26: 12/16 passed, 4 failed. Results:
-  - ✅ Home page loads
-  - ✅ Nodes page loads with data
-  - ❌ Map page loads with markers — No markers found (empty DB, no geo data)
-  - ✅ Packets page loads with filter
-  - ✅ Node detail loads
-  - ✅ Theme customizer opens
-  - ✅ Dark mode toggle
-  - ✅ Analytics page loads
-  - ✅ Map heat checkbox persists in localStorage
-  - ✅ Map heat checkbox is clickable
-  - ✅ Live heat disabled when ghosts mode active
-  - ✅ Live heat checkbox persists in localStorage
-  - ✅ Heatmap opacity persists in localStorage
-  - ❌ Live heatmap opacity persists — browser closed before test ran (bug: browser.close() on line 274 is before tests 14-16)
-  - ❌ Customizer has separate map/live opacity sliders — same browser-closed bug
-  - ❌ Map re-renders on resize — same browser-closed bug
- BUG FOUND: test-e2e-playwright.js line 274 calls `await browser.close()` before tests 14, 15, 16 execute. Those 3 tests will always fail. The `browser.close()` must be moved after all tests.
- The "Map page loads with markers" failure is expected with an empty local DB — no nodes with coordinates exist to render markers.
- FIX APPLIED 2026-03-26: Moved `browser.close()` from between test 13 and test 14 to after test 16 (just before the summary). Tests 14 ("Live heatmap opacity persists") and 15 ("Customizer has separate map/live opacity sliders") now pass. Test 16 ("Map re-renders on resize") now runs but fails due to empty DB (no markers to count) — same root cause as test 3. Result: 14/16 pass, 2 fail (both map-marker tests, expected with empty DB).
- TESTS ADDED 2026-03-26: Issue #127 (copyToClipboard) — 8 unit tests in test-frontend-helpers.js using vm.createContext + DOM/clipboard mocks. Tests cover: fallback path (execCommand success/fail/throw), clipboard API path, null/undefined input, textarea lifecycle, no-callback usage. Pattern: `makeClipboardSandbox(opts)` helper builds sandbox with configurable navigator.clipboard and document.execCommand mocks. Total frontend helper tests: 47→55.
- TESTS ADDED 2026-03-26: Issue #125 (packet detail dismiss) — 1 E2E test in test-e2e-playwright.js. Tests: click row → pane opens (empty class removed) → click ✕ → pane closes (empty class restored). Skips gracefully when DB has no packets. Inserted before analytics group, before browser.close().
- E2E SPEED OPTIMIZATION 2026-03-26: Rewrote test-e2e-playwright.js for performance per Kobayashi's audit. Changes:
-  - Replaced ALL 19 `waitUntil: 'networkidle'` → `'domcontentloaded'` + targeted `waitForSelector`/`waitForFunction`. networkidle stalls ~500ms+ per navigation due to persistent WebSocket + Leaflet tiles.
-  - Eliminated 11 of 12 `waitForTimeout` sleeps → event-driven waits (waitForSelector, waitForFunction). Only 1 remains: 500ms for packet filter debounce (was 1500ms).
-  - Reordered tests into page groups to eliminate 7 redundant navigations (page.goto 14→7): Home(1,6,7), Nodes(2,5), Map(3,9,10,13,16), Packets(4), Analytics(8), Live(11,12), NoNav(14,15).
-  - Reduced default timeout from 15s to 10s.
-  - All 17 test names and assertions preserved unchanged.
-  - Verified: 17/17 tests pass against local server with generated test data.
- COVERAGE PIPELINE TIMING (measured locally, Windows):
-  - Phase 1: Istanbul instrumentation (22 JS files) — **3.7s**
-  - Phase 2: Server startup (COVERAGE=1) — **~2s** (ready after pre-warm)
-  - Phase 3: Playwright E2E (test-e2e-playwright.js, 17 tests) — **3.7s**
-  - Phase 4: Coverage collector (collect-frontend-coverage.js) — **746s (12.4 min)** ← THE BOTTLENECK
-  - Phase 5: nyc report generation — **1.8s**
-  - TOTAL: ~757s (~12.6 min locally). CI reports ~13 min (matches).
-  - ROOT CAUSE: collect-frontend-coverage.js is a 978-line script that launches a SECOND Playwright browser and exhaustively clicks every UI element on every page to maximize code coverage. It contains:
-    - 169 explicit `waitForTimeout()` calls totaling 104.1s (1.74 min) of hard sleep
-    - 21 `waitUntil: 'networkidle'` navigations (each adds ~2-15s depending on page load + WebSocket/tile activity)
-    - Visits 12 pages: Home, Nodes, Packets, Map, Analytics, Customizer, Channels, Live, Traces, Observers, Perf, plus global router/theme exercises
-    - Heaviest sections by sleep: Packets (13s), Analytics (13.8s), Nodes (11.6s), Live (11.7s), App.js router (10.4s)
-    - The networkidle waits are the real killer — they stall ~500ms-15s EACH waiting for WebSocket + Leaflet tiles to settle
-  - Note: test-e2e-interactions.js (called in combined-coverage.sh) does not exist — it fails silently via `|| true`
-  - OPTIMIZATION OPPORTUNITIES: Replace networkidle→domcontentloaded (same fix as E2E tests), replace waitForTimeout with event-driven waits, reduce/batch page navigations, parallelize independent page exercises
- REGRESSION TESTS ADDED 2026-03-27: Memory optimization (observation deduplication). 8 new tests in test-packet-store.js under "=== Observation deduplication (transmission_id refs) ===" section. Tests verify: (1) observations don't duplicate raw_hex/decoded_json, (2) transmission fields accessible via store.byTxId.get(obs.transmission_id), (3) query() and all() still return transmission fields for backward compat, (4) multiple observations share one transmission_id, (5) getSiblings works after dedup, (6) queryGrouped returns transmission fields, (7) memory estimate reflects dedup savings. 4 tests fail pre-fix (expected — Hicks hasn't applied changes yet), 4 pass (backward compat). Pattern: use hasOwnProperty() to distinguish own vs inherited/absent fields.
- REVIEW 2026-03-27: Hicks RAM fix (observation dedup). REJECTED. Tests pass (42 packet-store + 204 route), but 5 server.js consumers access `.hash`, `.raw_hex`, `.decoded_json`, `.payload_type` on lean observations from `byObserver.get()` or `tx.observations` without enrichment. Broken endpoints: (1) `/api/nodes/bulk-health` line 1141 `o.hash` undefined, (2) `/api/nodes/network-status` line 1220 `o.hash` undefined, (3) `/api/analytics/signal` lines 1298+1306 `p.hash`/`p.raw_hex` undefined, (4) `/api/observers/:id/analytics` lines 2320+2329+2361 `p.payload_type`/`p.decoded_json` undefined + lean objects sent to client as recentPackets, (5) `/api/analytics/subpaths` line 2711 `o.hash` undefined. All are regional filtering or analytics code paths that use `byObserver` directly. Fix: either enrich at these call sites or store `hash` on observations (it's small). The enrichment pattern works for `getById()`, `getSiblings()`, and `/api/packets/:id` but was not applied to the 5 other consumers. Route tests pass because they don't assert on these specific field values in analytics responses.
- BATCH REVIEW 2026-03-27: Reviewed 6 issue fixes pushed without sign-off. Full suite: 971 tests, 0 failures across 11 test files. Cache busters uniform (v=1774625000). Verdicts:
-  - #133 (phantom nodes): ✅ APPROVED. 12 assertions on removePhantomNodes, real db.js code, edge cases (idempotency, real node preserved, stats filtering).
-  - #123 (channel hash): ⚠️ APPROVED WITH NOTES. 6 new decoder tests cover channelHashHex (zero-padding) and decryptionStatus (no_key ×3, decryption_failed). Missing: `decrypted` status untested (needs valid crypto key), frontend rendering of "Ch 0xXX (no key)" untested.
-  - #126 (offline node on map): ✅ APPROVED. 3 regression tests: ambiguous prefix→null, unique prefix→resolves, dead node stays dead. Caching verified. Excellent quality.
-  - #130 (disappearing nodes): ✅ APPROVED. 8 pruneStaleNodes tests cover dim/restore/remove for API vs WS nodes. Real live.js via vm.createContext.
-  - #131 (auto-updating nodes): ⚠️ APPROVED WITH NOTES. 8 solid isAdvertMessage tests (real code). BUT 5 WS handler tests are source-string-match checks (`src.includes('loadNodes(true)')`) — these verify code exists but not that it works at runtime. No runtime test for debounce batching behavior.
-  - #129 (observer comparison): ✅ APPROVED. 11 comprehensive tests for comparePacketSets — all edge cases, performance (10K hashes <500ms), mathematical invariant. Real compare.js via vm.createContext.
-  - NOTES FOR IMPROVEMENT: (1) #131 debounce behavior should get a runtime test via vm.createContext, not string checks. (2) #123 could benefit from a `decrypted` status test if crypto mocking is feasible. Neither is blocking.
- TEST GAP FIX 2026-03-27: Closed both noted gaps from batch review:
-  - #123 (channel hash decryption `decrypted` status): 3 new tests in test-decoder.js. Used require.cache mocking to swap ChannelCrypto module with mock that returns `{success:true, data:{...}}`. Tests cover: (1) decrypted status with sender+message (text formatted as "Sender: message"), (2) decrypted without sender (text is just message), (3) multiple keys tried, first match wins (verifies iteration order + call count). All verify channelHashHex, type='CHAN', channel name, sender, timestamp, flags. require.cache is restored in finally block.
-  - #131 (WS handler runtime tests): Rewrote 5 `src.includes()` string-match tests to use vm.createContext with runtime execution. Created `makeNodesWsSandbox()` helper that provides controllable setTimeout (timer queue), mock DOM, tracked api/invalidateApiCache calls, and real `debouncedOnWS` logic. Tests run actual nodes.js init() and verify: (1) ADVERT triggers refresh with 5s debounce, (2) non-ADVERT doesn't trigger refresh, (3) debounce collapses 3 ADVERTs into 1 API call, (4) _allNodes cache reset forces re-fetch, (5) scroll/selection preserved (panel innerHTML + scrollTop untouched by WS handler). Total: 87 frontend helper tests (same count — 5 replaced, not added), 61 decoder tests (+3).
-  - Technique learned: require.cache mocking is effective for testing code paths that depend on external modules (like ChannelCrypto). Store original, replace exports, restore in finally. Controllable setTimeout (capturing callbacks in array, firing manually) enables testing debounce logic without real timers.
+# Bishop — History
+
+## Project Context
+
+CoreScope has 14 test files, 4,290 lines of test code. Backend coverage 85%+, frontend 42%+. Tests use Node.js native runner, Playwright for E2E, c8/nyc for coverage, supertest for API routes. vm.createContext pattern used for testing frontend helpers in Node.js.
+
+User: User
+
+## Learnings
+
+- Session started 2026-03-26. Team formed: Kobayashi (Lead), Hicks (Backend), Newt (Frontend), Bishop (Tester).
+- E2E run 2026-03-26: 12/16 passed, 4 failed. Results:
+  - ✅ Home page loads
+  - ✅ Nodes page loads with data
+  - ❌ Map page loads with markers — No markers found (empty DB, no geo data)
+  - ✅ Packets page loads with filter
+  - ✅ Node detail loads
+  - ✅ Theme customizer opens
+  - ✅ Dark mode toggle
+  - ✅ Analytics page loads
+  - ✅ Map heat checkbox persists in localStorage
+  - ✅ Map heat checkbox is clickable
+  - ✅ Live heat disabled when ghosts mode active
+  - ✅ Live heat checkbox persists in localStorage
+  - ✅ Heatmap opacity persists in localStorage
+  - ❌ Live heatmap opacity persists — browser closed before test ran (bug: browser.close() on line 274 is before tests 14-16)
+  - ❌ Customizer has separate map/live opacity sliders — same browser-closed bug
+  - ❌ Map re-renders on resize — same browser-closed bug
+- BUG FOUND: test-e2e-playwright.js line 274 calls `await browser.close()` before tests 14, 15, 16 execute. Those 3 tests will always fail. The `browser.close()` must be moved after all tests.
+- The "Map page loads with markers" failure is expected with an empty local DB — no nodes with coordinates exist to render markers.
+- FIX APPLIED 2026-03-26: Moved `browser.close()` from between test 13 and test 14 to after test 16 (just before the summary). Tests 14 ("Live heatmap opacity persists") and 15 ("Customizer has separate map/live opacity sliders") now pass. Test 16 ("Map re-renders on resize") now runs but fails due to empty DB (no markers to count) — same root cause as test 3. Result: 14/16 pass, 2 fail (both map-marker tests, expected with empty DB).
+- TESTS ADDED 2026-03-26: Issue #127 (copyToClipboard) — 8 unit tests in test-frontend-helpers.js using vm.createContext + DOM/clipboard mocks. Tests cover: fallback path (execCommand success/fail/throw), clipboard API path, null/undefined input, textarea lifecycle, no-callback usage. Pattern: `makeClipboardSandbox(opts)` helper builds sandbox with configurable navigator.clipboard and document.execCommand mocks. Total frontend helper tests: 47→55.
+- TESTS ADDED 2026-03-26: Issue #125 (packet detail dismiss) — 1 E2E test in test-e2e-playwright.js. Tests: click row → pane opens (empty class removed) → click ✕ → pane closes (empty class restored). Skips gracefully when DB has no packets. Inserted before analytics group, before browser.close().
+- E2E SPEED OPTIMIZATION 2026-03-26: Rewrote test-e2e-playwright.js for performance per Kobayashi's audit. Changes:
+  - Replaced ALL 19 `waitUntil: 'networkidle'` → `'domcontentloaded'` + targeted `waitForSelector`/`waitForFunction`. networkidle stalls ~500ms+ per navigation due to persistent WebSocket + Leaflet tiles.
+  - Eliminated 11 of 12 `waitForTimeout` sleeps → event-driven waits (waitForSelector, waitForFunction). Only 1 remains: 500ms for packet filter debounce (was 1500ms).
+  - Reordered tests into page groups to eliminate 7 redundant navigations (page.goto 14→7): Home(1,6,7), Nodes(2,5), Map(3,9,10,13,16), Packets(4), Analytics(8), Live(11,12), NoNav(14,15).
+  - Reduced default timeout from 15s to 10s.
+  - All 17 test names and assertions preserved unchanged.
+  - Verified: 17/17 tests pass against local server with generated test data.
+- COVERAGE PIPELINE TIMING (measured locally, Windows):
+  - Phase 1: Istanbul instrumentation (22 JS files) — **3.7s**
+  - Phase 2: Server startup (COVERAGE=1) — **~2s** (ready after pre-warm)
+  - Phase 3: Playwright E2E (test-e2e-playwright.js, 17 tests) — **3.7s**
+  - Phase 4: Coverage collector (collect-frontend-coverage.js) — **746s (12.4 min)** ← THE BOTTLENECK
+  - Phase 5: nyc report generation — **1.8s**
+  - TOTAL: ~757s (~12.6 min locally). CI reports ~13 min (matches).
+  - ROOT CAUSE: collect-frontend-coverage.js is a 978-line script that launches a SECOND Playwright browser and exhaustively clicks every UI element on every page to maximize code coverage. It contains:
+    - 169 explicit `waitForTimeout()` calls totaling 104.1s (1.74 min) of hard sleep
+    - 21 `waitUntil: 'networkidle'` navigations (each adds ~2-15s depending on page load + WebSocket/tile activity)
+    - Visits 12 pages: Home, Nodes, Packets, Map, Analytics, Customizer, Channels, Live, Traces, Observers, Perf, plus global router/theme exercises
+    - Heaviest sections by sleep: Packets (13s), Analytics (13.8s), Nodes (11.6s), Live (11.7s), App.js router (10.4s)
+    - The networkidle waits are the real killer — they stall ~500ms-15s EACH waiting for WebSocket + Leaflet tiles to settle
+  - Note: test-e2e-interactions.js (called in combined-coverage.sh) does not exist — it fails silently via `|| true`
+  - OPTIMIZATION OPPORTUNITIES: Replace networkidle→domcontentloaded (same fix as E2E tests), replace waitForTimeout with event-driven waits, reduce/batch page navigations, parallelize independent page exercises
+- REGRESSION TESTS ADDED 2026-03-27: Memory optimization (observation deduplication). 8 new tests in test-packet-store.js under "=== Observation deduplication (transmission_id refs) ===" section. Tests verify: (1) observations don't duplicate raw_hex/decoded_json, (2) transmission fields accessible via store.byTxId.get(obs.transmission_id), (3) query() and all() still return transmission fields for backward compat, (4) multiple observations share one transmission_id, (5) getSiblings works after dedup, (6) queryGrouped returns transmission fields, (7) memory estimate reflects dedup savings. 4 tests fail pre-fix (expected — Hicks hasn't applied changes yet), 4 pass (backward compat). Pattern: use hasOwnProperty() to distinguish own vs inherited/absent fields.
+- REVIEW 2026-03-27: Hicks RAM fix (observation dedup). REJECTED. Tests pass (42 packet-store + 204 route), but 5 server.js consumers access `.hash`, `.raw_hex`, `.decoded_json`, `.payload_type` on lean observations from `byObserver.get()` or `tx.observations` without enrichment. Broken endpoints: (1) `/api/nodes/bulk-health` line 1141 `o.hash` undefined, (2) `/api/nodes/network-status` line 1220 `o.hash` undefined, (3) `/api/analytics/signal` lines 1298+1306 `p.hash`/`p.raw_hex` undefined, (4) `/api/observers/:id/analytics` lines 2320+2329+2361 `p.payload_type`/`p.decoded_json` undefined + lean objects sent to client as recentPackets, (5) `/api/analytics/subpaths` line 2711 `o.hash` undefined. All are regional filtering or analytics code paths that use `byObserver` directly. Fix: either enrich at these call sites or store `hash` on observations (it's small). The enrichment pattern works for `getById()`, `getSiblings()`, and `/api/packets/:id` but was not applied to the 5 other consumers. Route tests pass because they don't assert on these specific field values in analytics responses.
+- BATCH REVIEW 2026-03-27: Reviewed 6 issue fixes pushed without sign-off. Full suite: 971 tests, 0 failures across 11 test files. Cache busters uniform (v=1774625000). Verdicts:
+  - #133 (phantom nodes): ✅ APPROVED. 12 assertions on removePhantomNodes, real db.js code, edge cases (idempotency, real node preserved, stats filtering).
+  - #123 (channel hash): ⚠️ APPROVED WITH NOTES. 6 new decoder tests cover channelHashHex (zero-padding) and decryptionStatus (no_key ×3, decryption_failed). Missing: `decrypted` status untested (needs valid crypto key), frontend rendering of "Ch 0xXX (no key)" untested.
+  - #126 (offline node on map): ✅ APPROVED. 3 regression tests: ambiguous prefix→null, unique prefix→resolves, dead node stays dead. Caching verified. Excellent quality.
+  - #130 (disappearing nodes): ✅ APPROVED. 8 pruneStaleNodes tests cover dim/restore/remove for API vs WS nodes. Real live.js via vm.createContext.
+  - #131 (auto-updating nodes): ⚠️ APPROVED WITH NOTES. 8 solid isAdvertMessage tests (real code). BUT 5 WS handler tests are source-string-match checks (`src.includes('loadNodes(true)')`) — these verify code exists but not that it works at runtime. No runtime test for debounce batching behavior.
+  - #129 (observer comparison): ✅ APPROVED. 11 comprehensive tests for comparePacketSets — all edge cases, performance (10K hashes <500ms), mathematical invariant. Real compare.js via vm.createContext.
+  - NOTES FOR IMPROVEMENT: (1) #131 debounce behavior should get a runtime test via vm.createContext, not string checks. (2) #123 could benefit from a `decrypted` status test if crypto mocking is feasible. Neither is blocking.
+- TEST GAP FIX 2026-03-27: Closed both noted gaps from batch review:
+  - #123 (channel hash decryption `decrypted` status): 3 new tests in test-decoder.js. Used require.cache mocking to swap ChannelCrypto module with mock that returns `{success:true, data:{...}}`. Tests cover: (1) decrypted status with sender+message (text formatted as "Sender: message"), (2) decrypted without sender (text is just message), (3) multiple keys tried, first match wins (verifies iteration order + call count). All verify channelHashHex, type='CHAN', channel name, sender, timestamp, flags. require.cache is restored in finally block.
+  - #131 (WS handler runtime tests): Rewrote 5 `src.includes()` string-match tests to use vm.createContext with runtime execution. Created `makeNodesWsSandbox()` helper that provides controllable setTimeout (timer queue), mock DOM, tracked api/invalidateApiCache calls, and real `debouncedOnWS` logic. Tests run actual nodes.js init() and verify: (1) ADVERT triggers refresh with 5s debounce, (2) non-ADVERT doesn't trigger refresh, (3) debounce collapses 3 ADVERTs into 1 API call, (4) _allNodes cache reset forces re-fetch, (5) scroll/selection preserved (panel innerHTML + scrollTop untouched by WS handler). Total: 87 frontend helper tests (same count — 5 replaced, not added), 61 decoder tests (+3).
+  - Technique learned: require.cache mocking is effective for testing code paths that depend on external modules (like ChannelCrypto). Store original, replace exports, restore in finally. Controllable setTimeout (capturing callbacks in array, firing manually) enables testing debounce logic without real timers.

 - **Massive session 2026-03-27 (FULL DAY):** Reviewed and approved all 6 fixes, closed 2 test gaps, validated E2E:
  - **Batch PR review:** #123 (channel hash), #126 (ambiguous prefixes), #130 (live map), #131 (WS auto-update), #129 (observer comparison) — 2 gaps identified, resolved.
  - **Gap 1 closed:** #123 decrypted status mocked via require.cache (ChannelCrypto module swap). 3 new decoder tests.
  - **Gap 2 closed:** #131 WS debounce runtime tests via vm.createContext. 5 source-match tests replaced with actual execution tests. Controllable setTimeout technique verified.
  - **Test counts:** 109 db tests (+14 phantom), 204 route tests (+5 WS), 90 frontend tests (+3 pane), 61 decoder tests (+3 channel), 25 Go ingestor tests, 42 Go server tests.
-  - **E2E validation:** 16 Playwright tests passing, all routes functional with merged 1.237M observation DB. Browser smoke tests verified. Coverage 85%+ backend, 42%+ frontend.
+  - **E2E validation:** 16 Playwright tests passing, all routes functional with merged 1.237M observation DB. Browser smoke tests verified. Coverage 85%+ backend, 42%+ frontend.
@@ -1,41 +1,41 @@
-# Hicks — Backend Dev
-
-Server, decoder, packet-store, SQLite, API, MQTT, WebSocket, and performance for CoreScope.
-
-## Project Context
-
-**Project:** CoreScope — Real-time LoRa mesh packet analyzer
-**Stack:** Node.js 18+, Express 5, SQLite (better-sqlite3), MQTT (mqtt), WebSocket (ws)
-**User:** User
-
-## Responsibilities
-
- server.js — Express API routes, MQTT ingestion, WebSocket broadcast
- decoder.js — Custom MeshCore packet parser (header, path, payload, adverts)
- packet-store.js — In-memory ring buffer + indexes (O(1) lookups)
- db.js — SQLite schema, prepared statements, migrations
- server-helpers.js — Shared backend helpers (health checks, geo distance)
- Performance optimization — caching, response times, no O(n²)
- Docker/deployment — Dockerfile, manage.sh, docker-compose
- MeshCore protocol — read firmware source before protocol changes
-
-## Boundaries
-
- Do NOT modify frontend files (public/*.js, public/*.css, index.html)
- Always read AGENTS.md before starting work
- Always read firmware source (firmware/src/) before protocol changes
- Run `npm test` before considering work done
- Cache busters are Newt's job, but flag if you change an API response shape
-
-## Key Files
-
- server.js (2,661 lines) — main backend
- decoder.js (320 lines) — packet parser
- packet-store.js (668 lines) — in-memory store
- db.js (743 lines) — SQLite layer
- server-helpers.js (289 lines) — shared helpers
- iata-coords.js — airport coordinates for regional filtering
-
-## Model
-
-Preferred: auto
+# Hicks — Backend Dev
+
+Server, decoder, packet-store, SQLite, API, MQTT, WebSocket, and performance for CoreScope.
+
+## Project Context
+
+**Project:** CoreScope — Real-time LoRa mesh packet analyzer
+**Stack:** Node.js 18+, Express 5, SQLite (better-sqlite3), MQTT (mqtt), WebSocket (ws)
+**User:** User
+
+## Responsibilities
+
+- server.js — Express API routes, MQTT ingestion, WebSocket broadcast
+- decoder.js — Custom MeshCore packet parser (header, path, payload, adverts)
+- packet-store.js — In-memory ring buffer + indexes (O(1) lookups)
+- db.js — SQLite schema, prepared statements, migrations
+- server-helpers.js — Shared backend helpers (health checks, geo distance)
+- Performance optimization — caching, response times, no O(n²)
+- Docker/deployment — Dockerfile, manage.sh, docker-compose
+- MeshCore protocol — read firmware source before protocol changes
+
+## Boundaries
+
+- Do NOT modify frontend files (public/*.js, public/*.css, index.html)
+- Always read AGENTS.md before starting work
+- Always read firmware source (firmware/src/) before protocol changes
+- Run `npm test` before considering work done
+- Cache busters are Newt's job, but flag if you change an API response shape
+
+## Key Files
+
+- server.js (2,661 lines) — main backend
+- decoder.js (320 lines) — packet parser
+- packet-store.js (668 lines) — in-memory store
+- db.js (743 lines) — SQLite layer
+- server-helpers.js (289 lines) — shared helpers
+- iata-coords.js — airport coordinates for regional filtering
+
+## Model
+
+Preferred: auto
@@ -1,30 +1,30 @@
-# Hicks — History
-
-## Project Context
-
-CoreScope is a real-time LoRa mesh packet analyzer. Node.js + Express + SQLite backend, vanilla JS SPA frontend. Custom decoder.js fixes path_length bug from upstream library. In-memory packet store provides O(1) lookups for 30K+ packets. TTL response cache achieves 7,000× speedup on bulk health endpoint.
-
-User: User
-
-## Learnings
-
- Session started 2026-03-26. Team formed: Kobayashi (Lead), Hicks (Backend), Newt (Frontend), Bishop (Tester).
- Split the monolithic "Frontend coverage (instrumented Playwright)" CI step into 5 discrete steps: Instrument frontend JS, Start test server (with health-check poll replacing sleep 5), Run Playwright E2E tests, Extract coverage + generate report, Stop test server. Cleanup/report steps use `if: always()` so server shutdown happens even on test failure. Server PID shared across steps via .server.pid file. "Frontend E2E only" fast-path left untouched.
- Fixed memory explosion in packet-store.js: observations no longer duplicate transmission fields (hash, raw_hex, decoded_json, payload_type, route_type). Instead, observations store only `transmission_id` as a reference. Added `_enrichObs()` to hydrate observations at API boundaries (getById, getSiblings, enrichObservations). Replaced `.all()` with `.iterate()` for streaming load. Updated `_transmissionsForObserver()` to use transmission_id instead of hash. For a 185MB DB with 50K transmissions × 23 observations avg, this eliminates ~1.17M copies of hex dumps and JSON — projected ~2GB RAM savings.
- Built standalone Go MQTT ingestor (`cmd/ingestor/`). Ported decoder.js → Go (header parsing, path extraction, all payload types, advert decoding with flags/lat/lon/name). Ported db.js v3 schema (transmissions + observations + nodes + observers). Ported computeContentHash (SHA-256 based, path-independent). Uses modernc.org/sqlite (pure Go, no CGO) and paho.mqtt.golang. 25 tests passing (decoder golden fixtures from production data + DB schema compatibility). Supports same config.json format as Node.js server. Handles Format 1 (raw packet) messages; companion bridge format deferred. System Go was 1.17 — installed Go 1.22.5 to support modern dependencies.
- Built standalone Go web server (`cmd/server/`) — READ side of the Go rewrite. 35+ REST API endpoints ported from server.js. All queries go directly to SQLite (no in-memory packet store). WebSocket broadcast via SQLite polling. Static file server with SPA fallback. Uses gorilla/mux for routing, gorilla/websocket for WS, modernc.org/sqlite for DB. 42 tests passing (20 DB query tests, 20+ route integration tests, 2 WebSocket tests). `go vet` clean. Binary compiles to single executable. Analytics endpoints that required Node.js in-memory store (topology, distance, hash-sizes, subpaths) return structural stubs — core data (RF stats, channels, node health, etc.) fully functional via SQL. System Go 1.17 → installed Go 1.22 for build. Each cmd/* module has its own go.mod (no root-level go.mod).
- Go server API parity fix: Rewrote QueryPackets from observation-centric (packets_v view) to transmission-centric (transmissions table + correlated subqueries). This fixes both performance (9s to sub-100ms for unfiltered queries on 1.2M rows) and response shape. Packets now return first_seen, timestamp (= first_seen), observation_count, and NOT created_at/payload_version/score. Node responses now include last_heard (= last_seen fallback), hash_size (null), hash_size_inconsistent (false). Added schema version detection (v2 vs v3 observations table). Fixed QueryGroupedPackets first_seen. Added GetRecentTransmissionsForNode. All tests pass, build clean with Go 1.22.
- Fixed #133 (node count keeps climbing): `db.getStats().totalNodes` used `SELECT COUNT(*) FROM nodes` which counts every node ever seen — 6800+ on a ~200-400 node mesh. Changed `totalNodes` to count only nodes with `last_seen` within 7 days. Added `totalNodesAllTime` for the full historical count. Also filtered role counts in `/api/stats` to the same 7-day window. Added `countActiveNodes` and `countActiveNodesByRole` prepared statements in db.js. 6 new tests (95 total in test-db.js). The existing `idx_nodes_last_seen` index covers the new queries.
- Go server FULL API parity: Rewrote QueryGroupedPackets from packets_v VIEW scan (8s on 1.2M rows) to transmission-centric query (<100ms). Fixed GetStats to use 7-day window for totalNodes + added totalNodesAllTime. Split GetRoleCounts into 7-day (for /api/stats) and all-time (for /api/nodes). Added packetsLastHour + node lat/lon/role to /api/observers via batch queries (GetObserverPacketCounts, GetNodeLocations). Added multi-node filter support (/api/packets?nodes=pk1,pk2). Fixed /api/packets/:id to return parsed path_json in path field. Populated bulk-health per-node stats from SQL. Updated test seed data to use dynamic timestamps for 7-day filter compatibility. All 42+ tests pass, go vet clean.
- Fixed #133 ROOT CAUSE (phantom nodes): `autoLearnHopNodes` in server.js was calling `db.upsertNode()` for every unresolved hop prefix, creating thousands of fake "repeater" nodes with short public_keys (just the 2-4 byte hop prefix). Removed the `upsertNode` call entirely — unresolved hops are now simply cached to skip repeat DB lookups, and display as raw hex prefixes via hop-resolver. Added `db.removePhantomNodes()` that deletes nodes with `LENGTH(public_key) <= 16` (real pubkeys are 64 hex chars). Called at server startup to purge existing phantoms. 14 new test assertions (109 total in test-db.js).
- Fixed #126 (offline node showing on map due to hash prefix collision): `updatePathSeenTimestamps()` and `autoLearnHopNodes()` used `LIKE prefix%` DB queries that non-deterministically picked the first match when multiple nodes shared a hash prefix (e.g. `1CC4` and `1C82` both start with `1C` under 1-byte hash_size). Extracted `resolveUniquePrefixMatch()` that checks for uniqueness — ambiguous prefixes (matching 2+ nodes) are skipped and cached in a negative-cache Set. This prevents dead nodes from getting `last_heard` updates from packets that actually belong to a different node. 3 new tests (207 total in test-server-routes.js).
- Fixed #123 (channel hash for undecrypted GRP_TXT): Added `channelHashHex` (zero-padded uppercase hex) and `decryptionStatus` ('decrypted'|'no_key'|'decryption_failed') fields to `decodeGrpTxt` in decoder.js. Distinguishes between "no channel keys configured" vs "keys tried but decryption failed." Frontend packets.js updated: list preview shows "🔒 Ch 0xXX (status)", detail pane hex breakdown and message area show channel hash with status label. 6 new tests (58 total in test-decoder.js).
- Ported in-memory packet store to Go (`cmd/server/store.go`). PacketStore loads all transmissions + observations from SQLite at startup via streaming query (no .all()), builds 5 indexes (byHash, byTxID, byObsID, byObserver, byNode), picks longest-path observation per transmission for display fields. QueryPackets and QueryGroupedPackets serve from memory with full filter support (type, route, observer, hash, since, until, region, node). Poller ingests new transmissions into store via IngestNewFromDB. Server/routes fall back to direct DB queries when store is nil (backward-compatible with tests). All 42+ existing tests pass, go vet clean, go build clean. System Go 1.17 requires using Go 1.22.5 at C:\go1.22\go\bin.
- Fixed 3 critically slow Go endpoints by switching from SQLite queries against packets_v VIEW (1.2M rows) to in-memory PacketStore queries. `/api/channels` 7.2s→37ms (195×), `/api/channels/:hash/messages` 8.2s→36ms (228×), `/api/analytics/rf` 4.2s→90ms avg (47×). Key optimizations: (1) byPayloadType index reduces channels scan from 52K to 17K packets, (2) struct-based JSON decode avoids map[string]interface{} allocations, (3) per-transmission work hoisted out of 1.2M observation loop for RF, (4) eliminated second-pass time.Parse over 1.2M observations (track min/max timestamps as strings instead), (5) pre-allocated slices with capacity hints, (6) 15-second TTL cache for RF analytics (separate mutex to avoid contention with store RWMutex). Cache invalidation is TTL-only because live mesh generates continuous ingest events. Also fixed `/api/analytics/channels` to use store. All handlers fall back to DB when store is nil (test compat).
- **Massive session 2026-03-27 (FULL DAY):** Delivered 6 critical fixes + Go rewrite completed:
-  - **#133 PHANTOM NODES (ROOT CAUSE):** Backend `autoLearnHopNodes()` removed upsertNode call. Added `db.removePhantomNodes()` (pubkey ≤16 chars). Called at startup. Cascadia: 7,308 → ~200-400 active nodes. 14 new tests, all passing.
-  - **#133 ACTIVE WINDOW:** `/api/stats` `totalNodes` now 7-day window. Added `totalNodesAllTime` for historical. Role counts filtered to 7-day. Go server GetStats updated for parity.
-  - **#126 AMBIGUOUS PREFIXES:** `resolveUniquePrefixMatch()` requires unique prefix match. Ambiguous prefixes skipped, cached in negative-cache. Prevents dead nodes from wrong packet attribution.
-  - **#123 CHANNEL HASH:** Decoder tracks `channelHashHex` + `decryptionStatus` ('decrypted'|'no_key'|'decryption_failed'). All 4 fixes tested, deployed.
-  - **Go API Parity:** QueryGroupedPackets transmission-centric 8s→<100ms. Response shapes match Node.js exactly. All 42+ Go tests passing.
-  - **Database merge:** Staging 185MB (50K tx + 1.2M obs) merged into prod 21MB. 0 data loss. Merged DB 51,723 tx + 1,237,186 obs. Deploy time 8,491ms, memory 860MiB RSS (v.s. 2.7GB pre-RAM-fix). Backups retained 7 days.
+# Hicks — History
+
+## Project Context
+
+CoreScope is a real-time LoRa mesh packet analyzer. Node.js + Express + SQLite backend, vanilla JS SPA frontend. Custom decoder.js fixes path_length bug from upstream library. In-memory packet store provides O(1) lookups for 30K+ packets. TTL response cache achieves 7,000× speedup on bulk health endpoint.
+
+User: User
+
+## Learnings
+
+- Session started 2026-03-26. Team formed: Kobayashi (Lead), Hicks (Backend), Newt (Frontend), Bishop (Tester).
+- Split the monolithic "Frontend coverage (instrumented Playwright)" CI step into 5 discrete steps: Instrument frontend JS, Start test server (with health-check poll replacing sleep 5), Run Playwright E2E tests, Extract coverage + generate report, Stop test server. Cleanup/report steps use `if: always()` so server shutdown happens even on test failure. Server PID shared across steps via .server.pid file. "Frontend E2E only" fast-path left untouched.
+- Fixed memory explosion in packet-store.js: observations no longer duplicate transmission fields (hash, raw_hex, decoded_json, payload_type, route_type). Instead, observations store only `transmission_id` as a reference. Added `_enrichObs()` to hydrate observations at API boundaries (getById, getSiblings, enrichObservations). Replaced `.all()` with `.iterate()` for streaming load. Updated `_transmissionsForObserver()` to use transmission_id instead of hash. For a 185MB DB with 50K transmissions × 23 observations avg, this eliminates ~1.17M copies of hex dumps and JSON — projected ~2GB RAM savings.
+- Built standalone Go MQTT ingestor (`cmd/ingestor/`). Ported decoder.js → Go (header parsing, path extraction, all payload types, advert decoding with flags/lat/lon/name). Ported db.js v3 schema (transmissions + observations + nodes + observers). Ported computeContentHash (SHA-256 based, path-independent). Uses modernc.org/sqlite (pure Go, no CGO) and paho.mqtt.golang. 25 tests passing (decoder golden fixtures from production data + DB schema compatibility). Supports same config.json format as Node.js server. Handles Format 1 (raw packet) messages; companion bridge format deferred. System Go was 1.17 — installed Go 1.22.5 to support modern dependencies.
+- Built standalone Go web server (`cmd/server/`) — READ side of the Go rewrite. 35+ REST API endpoints ported from server.js. All queries go directly to SQLite (no in-memory packet store). WebSocket broadcast via SQLite polling. Static file server with SPA fallback. Uses gorilla/mux for routing, gorilla/websocket for WS, modernc.org/sqlite for DB. 42 tests passing (20 DB query tests, 20+ route integration tests, 2 WebSocket tests). `go vet` clean. Binary compiles to single executable. Analytics endpoints that required Node.js in-memory store (topology, distance, hash-sizes, subpaths) return structural stubs — core data (RF stats, channels, node health, etc.) fully functional via SQL. System Go 1.17 → installed Go 1.22 for build. Each cmd/* module has its own go.mod (no root-level go.mod).
+- Go server API parity fix: Rewrote QueryPackets from observation-centric (packets_v view) to transmission-centric (transmissions table + correlated subqueries). This fixes both performance (9s to sub-100ms for unfiltered queries on 1.2M rows) and response shape. Packets now return first_seen, timestamp (= first_seen), observation_count, and NOT created_at/payload_version/score. Node responses now include last_heard (= last_seen fallback), hash_size (null), hash_size_inconsistent (false). Added schema version detection (v2 vs v3 observations table). Fixed QueryGroupedPackets first_seen. Added GetRecentTransmissionsForNode. All tests pass, build clean with Go 1.22.
+- Fixed #133 (node count keeps climbing): `db.getStats().totalNodes` used `SELECT COUNT(*) FROM nodes` which counts every node ever seen — 6800+ on a ~200-400 node mesh. Changed `totalNodes` to count only nodes with `last_seen` within 7 days. Added `totalNodesAllTime` for the full historical count. Also filtered role counts in `/api/stats` to the same 7-day window. Added `countActiveNodes` and `countActiveNodesByRole` prepared statements in db.js. 6 new tests (95 total in test-db.js). The existing `idx_nodes_last_seen` index covers the new queries.
+- Go server FULL API parity: Rewrote QueryGroupedPackets from packets_v VIEW scan (8s on 1.2M rows) to transmission-centric query (<100ms). Fixed GetStats to use 7-day window for totalNodes + added totalNodesAllTime. Split GetRoleCounts into 7-day (for /api/stats) and all-time (for /api/nodes). Added packetsLastHour + node lat/lon/role to /api/observers via batch queries (GetObserverPacketCounts, GetNodeLocations). Added multi-node filter support (/api/packets?nodes=pk1,pk2). Fixed /api/packets/:id to return parsed path_json in path field. Populated bulk-health per-node stats from SQL. Updated test seed data to use dynamic timestamps for 7-day filter compatibility. All 42+ tests pass, go vet clean.
+- Fixed #133 ROOT CAUSE (phantom nodes): `autoLearnHopNodes` in server.js was calling `db.upsertNode()` for every unresolved hop prefix, creating thousands of fake "repeater" nodes with short public_keys (just the 2-4 byte hop prefix). Removed the `upsertNode` call entirely — unresolved hops are now simply cached to skip repeat DB lookups, and display as raw hex prefixes via hop-resolver. Added `db.removePhantomNodes()` that deletes nodes with `LENGTH(public_key) <= 16` (real pubkeys are 64 hex chars). Called at server startup to purge existing phantoms. 14 new test assertions (109 total in test-db.js).
+- Fixed #126 (offline node showing on map due to hash prefix collision): `updatePathSeenTimestamps()` and `autoLearnHopNodes()` used `LIKE prefix%` DB queries that non-deterministically picked the first match when multiple nodes shared a hash prefix (e.g. `1CC4` and `1C82` both start with `1C` under 1-byte hash_size). Extracted `resolveUniquePrefixMatch()` that checks for uniqueness — ambiguous prefixes (matching 2+ nodes) are skipped and cached in a negative-cache Set. This prevents dead nodes from getting `last_heard` updates from packets that actually belong to a different node. 3 new tests (207 total in test-server-routes.js).
+- Fixed #123 (channel hash for undecrypted GRP_TXT): Added `channelHashHex` (zero-padded uppercase hex) and `decryptionStatus` ('decrypted'|'no_key'|'decryption_failed') fields to `decodeGrpTxt` in decoder.js. Distinguishes between "no channel keys configured" vs "keys tried but decryption failed." Frontend packets.js updated: list preview shows "🔒 Ch 0xXX (status)", detail pane hex breakdown and message area show channel hash with status label. 6 new tests (58 total in test-decoder.js).
+- Ported in-memory packet store to Go (`cmd/server/store.go`). PacketStore loads all transmissions + observations from SQLite at startup via streaming query (no .all()), builds 5 indexes (byHash, byTxID, byObsID, byObserver, byNode), picks longest-path observation per transmission for display fields. QueryPackets and QueryGroupedPackets serve from memory with full filter support (type, route, observer, hash, since, until, region, node). Poller ingests new transmissions into store via IngestNewFromDB. Server/routes fall back to direct DB queries when store is nil (backward-compatible with tests). All 42+ existing tests pass, go vet clean, go build clean. System Go 1.17 requires using Go 1.22.5 at C:\go1.22\go\bin.
+- Fixed 3 critically slow Go endpoints by switching from SQLite queries against packets_v VIEW (1.2M rows) to in-memory PacketStore queries. `/api/channels` 7.2s→37ms (195×), `/api/channels/:hash/messages` 8.2s→36ms (228×), `/api/analytics/rf` 4.2s→90ms avg (47×). Key optimizations: (1) byPayloadType index reduces channels scan from 52K to 17K packets, (2) struct-based JSON decode avoids map[string]interface{} allocations, (3) per-transmission work hoisted out of 1.2M observation loop for RF, (4) eliminated second-pass time.Parse over 1.2M observations (track min/max timestamps as strings instead), (5) pre-allocated slices with capacity hints, (6) 15-second TTL cache for RF analytics (separate mutex to avoid contention with store RWMutex). Cache invalidation is TTL-only because live mesh generates continuous ingest events. Also fixed `/api/analytics/channels` to use store. All handlers fall back to DB when store is nil (test compat).
+- **Massive session 2026-03-27 (FULL DAY):** Delivered 6 critical fixes + Go rewrite completed:
+  - **#133 PHANTOM NODES (ROOT CAUSE):** Backend `autoLearnHopNodes()` removed upsertNode call. Added `db.removePhantomNodes()` (pubkey ≤16 chars). Called at startup. Cascadia: 7,308 → ~200-400 active nodes. 14 new tests, all passing.
+  - **#133 ACTIVE WINDOW:** `/api/stats` `totalNodes` now 7-day window. Added `totalNodesAllTime` for historical. Role counts filtered to 7-day. Go server GetStats updated for parity.
+  - **#126 AMBIGUOUS PREFIXES:** `resolveUniquePrefixMatch()` requires unique prefix match. Ambiguous prefixes skipped, cached in negative-cache. Prevents dead nodes from wrong packet attribution.
+  - **#123 CHANNEL HASH:** Decoder tracks `channelHashHex` + `decryptionStatus` ('decrypted'|'no_key'|'decryption_failed'). All 4 fixes tested, deployed.
+  - **Go API Parity:** QueryGroupedPackets transmission-centric 8s→<100ms. Response shapes match Node.js exactly. All 42+ Go tests passing.
+  - **Database merge:** Staging 185MB (50K tx + 1.2M obs) merged into prod 21MB. 0 data loss. Merged DB 51,723 tx + 1,237,186 obs. Deploy time 8,491ms, memory 860MiB RSS (v.s. 2.7GB pre-RAM-fix). Backups retained 7 days.
@@ -1,41 +1,41 @@
-# Hudson — DevOps Engineer
-
-## Identity
- **Name:** Hudson
- **Role:** DevOps Engineer
- **Emoji:** ⚙️
-
-## Scope
- CI/CD pipeline (`.github/workflows/deploy.yml`)
- Docker configuration (`Dockerfile`, `docker/`)
- Deployment scripts (`manage.sh`)
- Production infrastructure and monitoring
- Server configuration and environment setup
- Performance profiling and optimization of CI/build pipelines
- Database operations (backup, recovery, migration)
- Coverage collection pipeline (`scripts/collect-frontend-coverage.js`)
-
-## Boundaries
- Does NOT write application features — that's Hicks (backend) and Newt (frontend)
- Does NOT write application tests — that's Bishop
- MAY modify test infrastructure (CI config, coverage tooling, test runners)
- MAY modify server startup/config for deployment purposes
- Coordinates with Kobayashi on infrastructure decisions
-
-## Key Files
- `.github/workflows/deploy.yml` — CI/CD pipeline
- `Dockerfile`, `docker/` — Container config
- `manage.sh` — Deployment management script
- `scripts/` — Build and coverage scripts
- `config.example.json` — Configuration template
- `package.json` — Dependencies and scripts
-
-## Principles
- Infrastructure as code — all config in version control
- CI must stay under 10 minutes (currently ~14min — fix this)
- Never break the deploy pipeline
- Test infrastructure changes locally before pushing
- Read AGENTS.md before any work
-
-## Model
-Preferred: auto
+# Hudson — DevOps Engineer
+
+## Identity
+- **Name:** Hudson
+- **Role:** DevOps Engineer
+- **Emoji:** ⚙️
+
+## Scope
+- CI/CD pipeline (`.github/workflows/deploy.yml`)
+- Docker configuration (`Dockerfile`, `docker/`)
+- Deployment scripts (`manage.sh`)
+- Production infrastructure and monitoring
+- Server configuration and environment setup
+- Performance profiling and optimization of CI/build pipelines
+- Database operations (backup, recovery, migration)
+- Coverage collection pipeline (`scripts/collect-frontend-coverage.js`)
+
+## Boundaries
+- Does NOT write application features — that's Hicks (backend) and Newt (frontend)
+- Does NOT write application tests — that's Bishop
+- MAY modify test infrastructure (CI config, coverage tooling, test runners)
+- MAY modify server startup/config for deployment purposes
+- Coordinates with Kobayashi on infrastructure decisions
+
+## Key Files
+- `.github/workflows/deploy.yml` — CI/CD pipeline
+- `Dockerfile`, `docker/` — Container config
+- `manage.sh` — Deployment management script
+- `scripts/` — Build and coverage scripts
+- `config.example.json` — Configuration template
+- `package.json` — Dependencies and scripts
+
+## Principles
+- Infrastructure as code — all config in version control
+- CI must stay under 10 minutes (currently ~14min — fix this)
+- Never break the deploy pipeline
+- Test infrastructure changes locally before pushing
+- Read AGENTS.md before any work
+
+## Model
+Preferred: auto
@@ -84,5 +84,5 @@ Historical context from earlier phases:
 - Only Hudson touches prod infrastructure (user directive)
 - Go staging runs on port 82 (future phase)
 - Backups retained 7 days post-merge
- Manual promotion flow (no auto-promotion to prod)
-
+- Manual promotion flow (no auto-promotion to prod)
+
@@ -1,37 +1,37 @@
-# Kobayashi — Lead
-
-Architecture, code review, and decision-making for CoreScope.
-
-## Project Context
-
-**Project:** CoreScope — Real-time LoRa mesh packet analyzer
-**Stack:** Node.js 18+, Express 5, SQLite, vanilla JS frontend, Leaflet, WebSocket, MQTT
-**User:** User
-
-## Responsibilities
-
- Review architecture decisions and feature proposals
- Code review — approve or reject with actionable feedback
- Scope decisions — what to build, what to defer
- Documentation updates (README, docs/)
- Ensure AGENTS.md rules are followed (plan before implementing, tests required, cache busters, etc.)
- Coordinate multi-domain changes spanning backend and frontend
-
-## Boundaries
-
- Do NOT write implementation code — delegate to Hicks (backend) or Newt (frontend)
- May write small fixes during code review if the change is trivial
- Architecture proposals require user sign-off before implementation starts
-
-## Review Authority
-
- May approve or reject work from Hicks, Newt, and Bishop
- On rejection: specify whether to reassign or escalate
- Lockout rules apply — rejected author cannot self-revise
-
-## Key Files
-
- AGENTS.md — project rules (read before every review)
- server.js — main backend (2,661 lines)
- public/ — frontend modules (22 files)
- package.json — dependencies (keep minimal)
+# Kobayashi — Lead
+
+Architecture, code review, and decision-making for CoreScope.
+
+## Project Context
+
+**Project:** CoreScope — Real-time LoRa mesh packet analyzer
+**Stack:** Node.js 18+, Express 5, SQLite, vanilla JS frontend, Leaflet, WebSocket, MQTT
+**User:** User
+
+## Responsibilities
+
+- Review architecture decisions and feature proposals
+- Code review — approve or reject with actionable feedback
+- Scope decisions — what to build, what to defer
+- Documentation updates (README, docs/)
+- Ensure AGENTS.md rules are followed (plan before implementing, tests required, cache busters, etc.)
+- Coordinate multi-domain changes spanning backend and frontend
+
+## Boundaries
+
+- Do NOT write implementation code — delegate to Hicks (backend) or Newt (frontend)
+- May write small fixes during code review if the change is trivial
+- Architecture proposals require user sign-off before implementation starts
+
+## Review Authority
+
+- May approve or reject work from Hicks, Newt, and Bishop
+- On rejection: specify whether to reassign or escalate
+- Lockout rules apply — rejected author cannot self-revise
+
+## Key Files
+
+- AGENTS.md — project rules (read before every review)
+- server.js — main backend (2,661 lines)
+- public/ — frontend modules (22 files)
+- package.json — dependencies (keep minimal)
@@ -1,33 +1,33 @@
-# Kobayashi — History
-
-## Project Context
-
-CoreScope is a real-time LoRa mesh packet analyzer. Node.js + Express + SQLite backend, vanilla JS SPA frontend with Leaflet maps, WebSocket live feed, MQTT ingestion. Production at v2.6.0, ~18K lines, 85%+ backend test coverage.
-
-User: User
-
-## Learnings
-
- Session started 2026-03-26. Team formed: Kobayashi (Lead), Hicks (Backend), Newt (Frontend), Bishop (Tester).
- **E2E Playwright performance audit (2026-03-26):** 16 tests, single browser/context/page (good). Key bottlenecks: (1) `waitUntil: 'networkidle'` used ~20 times — catastrophic for SPA with WebSocket + map tiles, (2) ~17s of hardcoded `waitForTimeout` sleeps, (3) redundant `page.goto()` to same routes across tests, (4) CI installs Playwright browser on every run with no caching, (5) coverage collection launches a second full browser session, (6) `sleep 5` server startup instead of health-check polling. Estimated 40-50% total runtime reduction achievable.
- **Issue triage session (2026-03-27):** Triaged 4 open issues, assigned to team:
-  - **#131** (Feature: Auto-update nodes tab) → Newt (⚛️). Requires WebSocket real-time updates in nodes.js, similar to existing packets feed.
-  - **#130** (Bug: Disappearing nodes on live map) → Newt (⚛️). High severity, multiple Cascadia Mesh community reports. Likely status calculation or map filter bug. Nodes visible in static list but vanishing from live map.
-  - **#129** (Feature: Packet comparison between observers) → Newt (⚛️). Feature request from letsmesh analyzer. Side-by-side packet filtering for two repeaters to diagnose repeater issues.
-  - **#123** (Feature: Show channel hash on decrypt failure) → Hicks (🔧). Core contributor (lincomatic) request. Decoder needs to track why decrypt failed (no key vs. corruption) and expose channel hash + reason in API response.
- **Massive session — 2026-03-27 (full day):**
-  - **#133 root cause (phantom nodes):** `autoLearnHopNodes()` creates stub nodes for unresolved hop prefixes (2-8 hex chars). Cascadia showed 7,308 nodes (6,638 repeaters) when real size ~200-400. With `hash_size=1`, collision rate high → infinite phantom generation.
-  - **DB merge decision:** Staging DB (185MB, 50K transmissions, 1.2M observations) is superset. Use as merge base. Transmissions dedup by hash (unique), observations all preserved (unique by observer), nodes/observers latest-wins + sum counts. 6-phase execution plan: pre-flight, backup, merge, deploy, validate, cleanup.
-  - **Coordination:** Assigned Hicks phantom cleanup (backend), Newt live page pruning (frontend), Hudson merge execution (DevOps).
-  - **Outcome:** All 4 triaged issues fixed (#131, #130, #129, #123), #133 (phantom nodes) fully resolved, #126 (ambiguous hop prefixes) fixed as bonus, database merged successfully (0 data loss, 2 min downtime, 51,723 tx + 1.237M obs), Go rewrite (MQTT ingestor + web server) completed and ready for staging.
-  - **Team expanded:** Hudson joined for DevOps work, Ripley joined as Support Engineer.
- **Go staging bug triage (2026-03-28):** Filed 8 issues for Go staging bugs missed during API parity work. All found by actually loading the analytics page in a browser — none caught by endpoint-level parity checks.
-  - **#142** (Channels tab: wrong count, all decrypted, undefined fields) → Hicks
-  - **#136** (Hash stats tab: empty) → Hicks
-  - **#138** (Hash issues: no inconsistencies/collision risks shown) → Hicks
-  - **#135** (Topology tab: broken) → Hicks
-  - **#134** (Route patterns: broken) → Hicks
-  - **#140** (bulk-health API: 12s response time) → Hicks
-  - **#137** (Distance tab: broken) → Hicks
-  - **#139** (Commit link: bad contrast) → Newt
-  - **Post-mortem:** Parity was verified by comparing individual endpoint response shapes in isolation. Nobody loaded the analytics page in a browser and looked at it. The agents tested API responses without browser validation of the full UI — exactly the failure mode AGENTS.md rule #2 exists to prevent.
+# Kobayashi — History
+
+## Project Context
+
+CoreScope is a real-time LoRa mesh packet analyzer. Node.js + Express + SQLite backend, vanilla JS SPA frontend with Leaflet maps, WebSocket live feed, MQTT ingestion. Production at v2.6.0, ~18K lines, 85%+ backend test coverage.
+
+User: User
+
+## Learnings
+
+- Session started 2026-03-26. Team formed: Kobayashi (Lead), Hicks (Backend), Newt (Frontend), Bishop (Tester).
+- **E2E Playwright performance audit (2026-03-26):** 16 tests, single browser/context/page (good). Key bottlenecks: (1) `waitUntil: 'networkidle'` used ~20 times — catastrophic for SPA with WebSocket + map tiles, (2) ~17s of hardcoded `waitForTimeout` sleeps, (3) redundant `page.goto()` to same routes across tests, (4) CI installs Playwright browser on every run with no caching, (5) coverage collection launches a second full browser session, (6) `sleep 5` server startup instead of health-check polling. Estimated 40-50% total runtime reduction achievable.
+- **Issue triage session (2026-03-27):** Triaged 4 open issues, assigned to team:
+  - **#131** (Feature: Auto-update nodes tab) → Newt (⚛️). Requires WebSocket real-time updates in nodes.js, similar to existing packets feed.
+  - **#130** (Bug: Disappearing nodes on live map) → Newt (⚛️). High severity, multiple Cascadia Mesh community reports. Likely status calculation or map filter bug. Nodes visible in static list but vanishing from live map.
+  - **#129** (Feature: Packet comparison between observers) → Newt (⚛️). Feature request from letsmesh analyzer. Side-by-side packet filtering for two repeaters to diagnose repeater issues.
+  - **#123** (Feature: Show channel hash on decrypt failure) → Hicks (🔧). Core contributor (lincomatic) request. Decoder needs to track why decrypt failed (no key vs. corruption) and expose channel hash + reason in API response.
+- **Massive session — 2026-03-27 (full day):**
+  - **#133 root cause (phantom nodes):** `autoLearnHopNodes()` creates stub nodes for unresolved hop prefixes (2-8 hex chars). Cascadia showed 7,308 nodes (6,638 repeaters) when real size ~200-400. With `hash_size=1`, collision rate high → infinite phantom generation.
+  - **DB merge decision:** Staging DB (185MB, 50K transmissions, 1.2M observations) is superset. Use as merge base. Transmissions dedup by hash (unique), observations all preserved (unique by observer), nodes/observers latest-wins + sum counts. 6-phase execution plan: pre-flight, backup, merge, deploy, validate, cleanup.
+  - **Coordination:** Assigned Hicks phantom cleanup (backend), Newt live page pruning (frontend), Hudson merge execution (DevOps).
+  - **Outcome:** All 4 triaged issues fixed (#131, #130, #129, #123), #133 (phantom nodes) fully resolved, #126 (ambiguous hop prefixes) fixed as bonus, database merged successfully (0 data loss, 2 min downtime, 51,723 tx + 1.237M obs), Go rewrite (MQTT ingestor + web server) completed and ready for staging.
+  - **Team expanded:** Hudson joined for DevOps work, Ripley joined as Support Engineer.
+- **Go staging bug triage (2026-03-28):** Filed 8 issues for Go staging bugs missed during API parity work. All found by actually loading the analytics page in a browser — none caught by endpoint-level parity checks.
+  - **#142** (Channels tab: wrong count, all decrypted, undefined fields) → Hicks
+  - **#136** (Hash stats tab: empty) → Hicks
+  - **#138** (Hash issues: no inconsistencies/collision risks shown) → Hicks
+  - **#135** (Topology tab: broken) → Hicks
+  - **#134** (Route patterns: broken) → Hicks
+  - **#140** (bulk-health API: 12s response time) → Hicks
+  - **#137** (Distance tab: broken) → Hicks
+  - **#139** (Commit link: bad contrast) → Newt
+  - **Post-mortem:** Parity was verified by comparing individual endpoint response shapes in isolation. Nobody loaded the analytics page in a browser and looked at it. The agents tested API responses without browser validation of the full UI — exactly the failure mode AGENTS.md rule #2 exists to prevent.
@@ -1,45 +1,45 @@
-# Newt — Frontend Dev
-
-Vanilla JS UI, Leaflet maps, live visualization, theming, and all public/ modules for CoreScope.
-
-## Project Context
-
-**Project:** CoreScope — Real-time LoRa mesh packet analyzer
-**Stack:** Vanilla HTML/CSS/JavaScript (ES5/6), Leaflet maps, WebSocket, Canvas animations
-**User:** User
-
-## Responsibilities
-
- public/*.js — All 22 frontend modules (app.js, packets.js, live.js, map.js, nodes.js, channels.js, analytics.js, customize.js, etc.)
- public/style.css, public/live.css, public/home.css — Styling via CSS variables
- public/index.html — SPA shell, cache busters (MUST bump on every .js/.css change)
- packet-filter.js — Wireshark-style filter engine (standalone, testable in Node.js)
- Leaflet map rendering, VCR playback controls, Canvas animations
- Theme customizer (IIFE in customize.js, THEME_CSS_MAP)
-
-## Boundaries
-
- Do NOT modify server-side files (server.js, db.js, packet-store.js, decoder.js)
- All colors MUST use CSS variables — never hardcode #hex outside :root
- Use shared helpers from roles.js (ROLE_COLORS, TYPE_COLORS, getNodeStatus, getHealthThresholds)
- Prefer `n.last_heard || n.last_seen` for display and status
- No per-packet API calls from frontend — fetch bulk, filter client-side
- Run `node test-packet-filter.js` and `node test-frontend-helpers.js` after filter/helper changes
- Always bump cache busters in the SAME commit as code changes
-
-## Key Files
-
- live.js (2,178 lines) — largest frontend module, VCR playback
- analytics.js (1,375 lines) — global analytics dashboard
- customize.js (1,259 lines) — theme customizer IIFE
- packets.js (1,669 lines) — packet feed, detail pane, hex breakdown
- app.js (775 lines) — SPA router, WebSocket, globals
- nodes.js (765 lines) — node directory, detail views
- map.js (699 lines) — Leaflet map rendering
- packet-filter.js — standalone filter engine
- roles.js — shared color maps and helpers
- hop-resolver.js — client-side hop resolution
-
-## Model
-
-Preferred: auto
+# Newt — Frontend Dev
+
+Vanilla JS UI, Leaflet maps, live visualization, theming, and all public/ modules for CoreScope.
+
+## Project Context
+
+**Project:** CoreScope — Real-time LoRa mesh packet analyzer
+**Stack:** Vanilla HTML/CSS/JavaScript (ES5/6), Leaflet maps, WebSocket, Canvas animations
+**User:** User
+
+## Responsibilities
+
+- public/*.js — All 22 frontend modules (app.js, packets.js, live.js, map.js, nodes.js, channels.js, analytics.js, customize.js, etc.)
+- public/style.css, public/live.css, public/home.css — Styling via CSS variables
+- public/index.html — SPA shell, cache busters (MUST bump on every .js/.css change)
+- packet-filter.js — Wireshark-style filter engine (standalone, testable in Node.js)
+- Leaflet map rendering, VCR playback controls, Canvas animations
+- Theme customizer (IIFE in customize.js, THEME_CSS_MAP)
+
+## Boundaries
+
+- Do NOT modify server-side files (server.js, db.js, packet-store.js, decoder.js)
+- All colors MUST use CSS variables — never hardcode #hex outside :root
+- Use shared helpers from roles.js (ROLE_COLORS, TYPE_COLORS, getNodeStatus, getHealthThresholds)
+- Prefer `n.last_heard || n.last_seen` for display and status
+- No per-packet API calls from frontend — fetch bulk, filter client-side
+- Run `node test-packet-filter.js` and `node test-frontend-helpers.js` after filter/helper changes
+- Always bump cache busters in the SAME commit as code changes
+
+## Key Files
+
+- live.js (2,178 lines) — largest frontend module, VCR playback
+- analytics.js (1,375 lines) — global analytics dashboard
+- customize.js (1,259 lines) — theme customizer IIFE
+- packets.js (1,669 lines) — packet feed, detail pane, hex breakdown
+- app.js (775 lines) — SPA router, WebSocket, globals
+- nodes.js (765 lines) — node directory, detail views
+- map.js (699 lines) — Leaflet map rendering
+- packet-filter.js — standalone filter engine
+- roles.js — shared color maps and helpers
+- hop-resolver.js — client-side hop resolution
+
+## Model
+
+Preferred: auto
@@ -1,24 +1,24 @@
-# Newt — History
-
-## Project Context
-
-CoreScope is a real-time LoRa mesh packet analyzer with a vanilla JS SPA frontend. 22 frontend modules, Leaflet maps, WebSocket live feed, VCR playback, Canvas animations, theme customizer with CSS variables. No build step, no framework. ES5/6 for broad browser support.
-
-User: User
-
-## Learnings
-
- Session started 2026-03-26. Team formed: Kobayashi (Lead), Hicks (Backend), Newt (Frontend), Bishop (Tester).
- **Issue #127 fix:** Firefox clipboard API fails silently when `navigator.clipboard.writeText()` is called outside a secure context or without proper user gesture handling. Added `window.copyToClipboard()` shared helper to `roles.js` that tries Clipboard API first, falls back to hidden textarea + `document.execCommand('copy')`. Updated all 3 clipboard call sites: `nodes.js` (Copy URL — the reported bug), `packets.js` (Copy Link — had ugly `prompt()` fallback), `customize.js` (Copy to Clipboard — already worked but now uses shared helper). Cache busters bumped. All tests pass (47 frontend, 62 packet-filter).
- **Issue #125 fix:** Added dismiss/close button (✕) to the packet detail pane on desktop. Extracted `closeDetailPanel()` shared helper and `PANEL_CLOSE_HTML` constant — DRY: Escape handler and click handler both call it. Close button uses event delegation on `#pktRight`, styled with CSS variables (`--text-muted`, `--text`, `--surface-1`) matching the mobile `.mobile-sheet-close` pattern. Hidden when panel is in `.empty` state. Clicking a different row still re-opens with new data. Files changed: `public/packets.js`, `public/style.css`. Cache busters NOT bumped (another agent editing index.html).
- **Issue #122 fix:** Node tooltip (line 45) and node detail panel (line 120) in `channels.js` used `last_seen` alone for "Last seen" display. Changed both to `last_heard || last_seen` per AGENTS.md pitfall. Pattern: always prefer `last_heard || last_seen` for any time-ago display. **Server note for Hicks:** `/api/nodes/search` and `/api/nodes/:pubkey` endpoints don't return `last_heard` — only the bulk `/api/nodes` list endpoint computes it from the in-memory packet store. These endpoints need the same `last_heard` enrichment for the frontend fix to fully take effect. Also, `/api/analytics/channels` has a separate bug: `lastActivity` is overwritten unconditionally (no `>=` check) so it shows the oldest packet's timestamp, not the newest.
- **Issue #130 fix:** Live map `pruneStaleNodes()` (added for #133) was completely removing stale nodes from the map, while the static map dims them with CSS. Root cause: API-loaded nodes and WS-only nodes were treated identically — both got deleted when stale. Fix: mark API-loaded nodes with `_fromAPI = true` in `loadNodes()`. `pruneStaleNodes()` now dims API nodes (fillOpacity 0.25, opacity 0.15) instead of removing them, and restores full opacity when they become active again. WS-only dynamic nodes are still removed to prevent memory leaks. Pattern: **live map should match static map behavior** — never remove database-loaded nodes, only change their visual state. 3 new tests added (63 total frontend tests passing).
- **Issue #129 fix:** Added observer packet comparison feature (`#/compare` page). Users select two observers from dropdowns, click Compare, and see which packets each observer saw in the last 24 hours. Data flow: fetches packets per observer via existing `/api/packets?observer=X&limit=10000&since=24h`, computes set intersection/difference client-side using `comparePacketSets()` (O(n) via Set lookups — no nested loops). UI: three summary cards (both/only-A/only-B with counts and percentages), horizontal stacked bar chart, packet type breakdown for shared packets, and tabbed detail tables (up to 200 rows each, clickable to packet detail). URL is shareable: `#/compare?a=ID1&b=ID2`. Added 🔍 compare button to observers page header. Pure function `comparePacketSets` exposed on `window` for testability. 11 new tests (87 total frontend tests). Files: `public/compare.js` (new), `public/style.css`, `public/observers.js`, `public/index.html`, `test-frontend-helpers.js`. Cache busters bumped.
- **Browser validation of 6 fixes (2026-03-27):** Validated against live prod at `https://analyzer.00id.net`. Results: ✅ #133 (phantom nodes) — API returns 50 nodes, reasonable count, no runaway growth. ✅ #123 (channel hash on undecrypted) — GRP_TXT packets with `decryption_failed` status show `channelHashHex` field; packet detail renders `🔒 Channel Hash: 0xE2 (decryption failed)` via `packets.js:1254-1259`. ⏭ #126 (offline node on map) — skipped, requires specific dead node. ✅ #130 (disappearing nodes on live map) — `pruneStaleNodes()` confirmed at `live.js:1474` dims API-loaded nodes (`fillOpacity:0.25`) instead of removing; `_fromAPI=true` flag set at `live.js:1279`. ✅ #131 (auto-updating node list) — `nodes.js:210-216` wires `debouncedOnWS` handler that triggers `loadNodes(true)` on ADVERT messages; `isAdvertMessage()` at `nodes.js:852` checks `payload_type===4`. ✅ #129 (observer comparison) — `compare.js` deployed with full UI: observer dropdowns, `comparePacketSets()` Set logic, summary cards, bar chart, type breakdown. 16 observers available in prod. Pattern: always verify deployed JS matches source — cache buster `v=1774625000` confirmed consistent across all script tags.
- **Packet detail pane fresh-load fix:** The `detail-collapsed` class added for issue #125's close button wasn't applied on initial render, so the empty right panel was visible on fresh page load. Fix: added `detail-collapsed` to the `split-layout` div in the initial `innerHTML` template (packets.js:183). Pattern: when adding a CSS toggle class, always consider the initial DOM state — if nothing is selected, the default state must match "nothing selected." 3 tests added (90 total frontend). Cache busters bumped.
- **Massive session 2026-03-27 (FULL DAY):** Delivered 4 critical frontend fixes + live page improvements:
-  - **#130 LIVE MAP STALE DIMMING:** `pruneStaleNodes()` distinguishes API-loaded (`_fromAPI`) from WS-only. Dims API nodes (fillOpacity 0.25, opacity 0.15) instead of removing. Matches static map behavior. 3 new tests, all passing.
-  - **#131 NODES TAB WS AUTO-UPDATE:** `loadNodes(refreshOnly)` pattern resets cache + invalidateApiCache + re-fetches. Preserves scroll/selection/listeners. WS handler now triggers on ADVERT messages (payload_type===4). All tests passing.
-  - **#129 OBSERVER COMPARISON PAGE:** New `#/compare` route with shareable params `?a=ID1&b=ID2`. `comparePacketSets()` pure function (O(n) Set operations). UI: summary cards, bar chart, type breakdown, detail tables. 🔍 compare button on observers header.
-  - **#133 LIVE PAGE NODE PRUNING:** Prune every 60s using `getNodeStatus()` from roles.js (per-role health thresholds: 24h companions/sensors, 72h infrastructure). `_liveSeen` timestamp set on insert, updated on re-observation. Bounded memory usage. 
-  - **Database merge:** All frontend endpoints working with merged 1.237M observation DB. Load speed verified. All 4 fixes tested end-to-end in browser.
+# Newt — History
+
+## Project Context
+
+CoreScope is a real-time LoRa mesh packet analyzer with a vanilla JS SPA frontend. 22 frontend modules, Leaflet maps, WebSocket live feed, VCR playback, Canvas animations, theme customizer with CSS variables. No build step, no framework. ES5/6 for broad browser support.
+
+User: User
+
+## Learnings
+
+- Session started 2026-03-26. Team formed: Kobayashi (Lead), Hicks (Backend), Newt (Frontend), Bishop (Tester).
+- **Issue #127 fix:** Firefox clipboard API fails silently when `navigator.clipboard.writeText()` is called outside a secure context or without proper user gesture handling. Added `window.copyToClipboard()` shared helper to `roles.js` that tries Clipboard API first, falls back to hidden textarea + `document.execCommand('copy')`. Updated all 3 clipboard call sites: `nodes.js` (Copy URL — the reported bug), `packets.js` (Copy Link — had ugly `prompt()` fallback), `customize.js` (Copy to Clipboard — already worked but now uses shared helper). Cache busters bumped. All tests pass (47 frontend, 62 packet-filter).
+- **Issue #125 fix:** Added dismiss/close button (✕) to the packet detail pane on desktop. Extracted `closeDetailPanel()` shared helper and `PANEL_CLOSE_HTML` constant — DRY: Escape handler and click handler both call it. Close button uses event delegation on `#pktRight`, styled with CSS variables (`--text-muted`, `--text`, `--surface-1`) matching the mobile `.mobile-sheet-close` pattern. Hidden when panel is in `.empty` state. Clicking a different row still re-opens with new data. Files changed: `public/packets.js`, `public/style.css`. Cache busters NOT bumped (another agent editing index.html).
+- **Issue #122 fix:** Node tooltip (line 45) and node detail panel (line 120) in `channels.js` used `last_seen` alone for "Last seen" display. Changed both to `last_heard || last_seen` per AGENTS.md pitfall. Pattern: always prefer `last_heard || last_seen` for any time-ago display. **Server note for Hicks:** `/api/nodes/search` and `/api/nodes/:pubkey` endpoints don't return `last_heard` — only the bulk `/api/nodes` list endpoint computes it from the in-memory packet store. These endpoints need the same `last_heard` enrichment for the frontend fix to fully take effect. Also, `/api/analytics/channels` has a separate bug: `lastActivity` is overwritten unconditionally (no `>=` check) so it shows the oldest packet's timestamp, not the newest.
+- **Issue #130 fix:** Live map `pruneStaleNodes()` (added for #133) was completely removing stale nodes from the map, while the static map dims them with CSS. Root cause: API-loaded nodes and WS-only nodes were treated identically — both got deleted when stale. Fix: mark API-loaded nodes with `_fromAPI = true` in `loadNodes()`. `pruneStaleNodes()` now dims API nodes (fillOpacity 0.25, opacity 0.15) instead of removing them, and restores full opacity when they become active again. WS-only dynamic nodes are still removed to prevent memory leaks. Pattern: **live map should match static map behavior** — never remove database-loaded nodes, only change their visual state. 3 new tests added (63 total frontend tests passing).
+- **Issue #129 fix:** Added observer packet comparison feature (`#/compare` page). Users select two observers from dropdowns, click Compare, and see which packets each observer saw in the last 24 hours. Data flow: fetches packets per observer via existing `/api/packets?observer=X&limit=10000&since=24h`, computes set intersection/difference client-side using `comparePacketSets()` (O(n) via Set lookups — no nested loops). UI: three summary cards (both/only-A/only-B with counts and percentages), horizontal stacked bar chart, packet type breakdown for shared packets, and tabbed detail tables (up to 200 rows each, clickable to packet detail). URL is shareable: `#/compare?a=ID1&b=ID2`. Added 🔍 compare button to observers page header. Pure function `comparePacketSets` exposed on `window` for testability. 11 new tests (87 total frontend tests). Files: `public/compare.js` (new), `public/style.css`, `public/observers.js`, `public/index.html`, `test-frontend-helpers.js`. Cache busters bumped.
+- **Browser validation of 6 fixes (2026-03-27):** Validated against live prod at `https://analyzer.00id.net`. Results: ✅ #133 (phantom nodes) — API returns 50 nodes, reasonable count, no runaway growth. ✅ #123 (channel hash on undecrypted) — GRP_TXT packets with `decryption_failed` status show `channelHashHex` field; packet detail renders `🔒 Channel Hash: 0xE2 (decryption failed)` via `packets.js:1254-1259`. ⏭ #126 (offline node on map) — skipped, requires specific dead node. ✅ #130 (disappearing nodes on live map) — `pruneStaleNodes()` confirmed at `live.js:1474` dims API-loaded nodes (`fillOpacity:0.25`) instead of removing; `_fromAPI=true` flag set at `live.js:1279`. ✅ #131 (auto-updating node list) — `nodes.js:210-216` wires `debouncedOnWS` handler that triggers `loadNodes(true)` on ADVERT messages; `isAdvertMessage()` at `nodes.js:852` checks `payload_type===4`. ✅ #129 (observer comparison) — `compare.js` deployed with full UI: observer dropdowns, `comparePacketSets()` Set logic, summary cards, bar chart, type breakdown. 16 observers available in prod. Pattern: always verify deployed JS matches source — cache buster `v=1774625000` confirmed consistent across all script tags.
+- **Packet detail pane fresh-load fix:** The `detail-collapsed` class added for issue #125's close button wasn't applied on initial render, so the empty right panel was visible on fresh page load. Fix: added `detail-collapsed` to the `split-layout` div in the initial `innerHTML` template (packets.js:183). Pattern: when adding a CSS toggle class, always consider the initial DOM state — if nothing is selected, the default state must match "nothing selected." 3 tests added (90 total frontend). Cache busters bumped.
+- **Massive session 2026-03-27 (FULL DAY):** Delivered 4 critical frontend fixes + live page improvements:
+  - **#130 LIVE MAP STALE DIMMING:** `pruneStaleNodes()` distinguishes API-loaded (`_fromAPI`) from WS-only. Dims API nodes (fillOpacity 0.25, opacity 0.15) instead of removing. Matches static map behavior. 3 new tests, all passing.
+  - **#131 NODES TAB WS AUTO-UPDATE:** `loadNodes(refreshOnly)` pattern resets cache + invalidateApiCache + re-fetches. Preserves scroll/selection/listeners. WS handler now triggers on ADVERT messages (payload_type===4). All tests passing.
+  - **#129 OBSERVER COMPARISON PAGE:** New `#/compare` route with shareable params `?a=ID1&b=ID2`. `comparePacketSets()` pure function (O(n) Set operations). UI: summary cards, bar chart, type breakdown, detail tables. 🔍 compare button on observers header.
+  - **#133 LIVE PAGE NODE PRUNING:** Prune every 60s using `getNodeStatus()` from roles.js (per-role health thresholds: 24h companions/sensors, 72h infrastructure). `_liveSeen` timestamp set on insert, updated on re-observation. Bounded memory usage. 
+  - **Database merge:** All frontend endpoints working with merged 1.237M observation DB. Load speed verified. All 4 fixes tested end-to-end in browser.
@@ -1,50 +1,50 @@
-# Ripley — Support Engineer
-
-Deep knowledge of every frontend behavior, API response, and user-facing feature in CoreScope. Fields community questions, triages bug reports, and explains "why does X look like Y."
-
-## Project Context
-
-**Project:** CoreScope — Real-time LoRa mesh packet analyzer
-**Stack:** Vanilla JS frontend (public/*.js), Node.js backend, SQLite, WebSocket, MQTT
-**User:** Kpa-clawbot
-
-## Responsibilities
-
- Answer user questions about UI behavior ("why is this node gray?", "why don't I see my repeater?")
- Triage community bug reports and feature requests on GitHub issues
- Know every frontend module intimately — read all public/*.js files before answering
- Know the API response shapes — what each endpoint returns and how the frontend uses it
- Know the status/health system — roles.js thresholds, active/stale/degraded/silent states
- Know the map behavior — marker colors, opacity, filtering, live vs static
- Know the packet display — filter syntax, detail pane, hex breakdown, decoded fields
- Reproduce reported issues by checking live data via API
-
-## Boundaries
-
- Does NOT write code — routes fixes to Hicks (backend) or Newt (frontend)
- Does NOT deploy — routes to Hudson
- MAY comment on GitHub issues with explanations and triage notes
- MAY suggest workarounds to users while fixes are in progress
-
-## Key Knowledge Areas
-
- **Node colors/status:** roles.js defines ROLE_COLORS, health thresholds per role. Gray = stale/silent. Dimmed = opacity 0.25 on live map.
- **last_heard vs last_seen:** Always prefer `last_heard || last_seen`. last_heard from packet store (all traffic), last_seen from DB (adverts only).
- **Hash prefixes:** 1-byte or 2-byte hash_size affects node disambiguation. hash_size_inconsistent flag.
- **Packet types:** ADVERT, TXT_MSG, GRP_TXT, REQ, CHAN, POS — what each means.
- **Observer vs Node:** Observers are MQTT-connected gateways. Nodes are mesh devices.
- **Live vs Static map:** Live map shows real-time WS data + API nodes. Static map shows all known nodes from API.
- **Channel decryption:** channelHashHex, decryptionStatus (decrypted/no_key/decryption_failed)
- **Geo filter:** polygon + bufferKm in config.json, excludes nodes outside boundary
-
-## How to Answer Questions
-
-1. Read the relevant frontend code FIRST — don't guess
-2. Check the live API data if applicable (analyzer.00id.net is public)
-3. Explain in user-friendly terms, not code jargon
-4. If it's a bug, route to the right squad member
-5. If it's expected behavior, explain WHY
-
-## Model
-
-Preferred: auto
+# Ripley — Support Engineer
+
+Deep knowledge of every frontend behavior, API response, and user-facing feature in CoreScope. Fields community questions, triages bug reports, and explains "why does X look like Y."
+
+## Project Context
+
+**Project:** CoreScope — Real-time LoRa mesh packet analyzer
+**Stack:** Vanilla JS frontend (public/*.js), Node.js backend, SQLite, WebSocket, MQTT
+**User:** Kpa-clawbot
+
+## Responsibilities
+
+- Answer user questions about UI behavior ("why is this node gray?", "why don't I see my repeater?")
+- Triage community bug reports and feature requests on GitHub issues
+- Know every frontend module intimately — read all public/*.js files before answering
+- Know the API response shapes — what each endpoint returns and how the frontend uses it
+- Know the status/health system — roles.js thresholds, active/stale/degraded/silent states
+- Know the map behavior — marker colors, opacity, filtering, live vs static
+- Know the packet display — filter syntax, detail pane, hex breakdown, decoded fields
+- Reproduce reported issues by checking live data via API
+
+## Boundaries
+
+- Does NOT write code — routes fixes to Hicks (backend) or Newt (frontend)
+- Does NOT deploy — routes to Hudson
+- MAY comment on GitHub issues with explanations and triage notes
+- MAY suggest workarounds to users while fixes are in progress
+
+## Key Knowledge Areas
+
+- **Node colors/status:** roles.js defines ROLE_COLORS, health thresholds per role. Gray = stale/silent. Dimmed = opacity 0.25 on live map.
+- **last_heard vs last_seen:** Always prefer `last_heard || last_seen`. last_heard from packet store (all traffic), last_seen from DB (adverts only).
+- **Hash prefixes:** 1-byte or 2-byte hash_size affects node disambiguation. hash_size_inconsistent flag.
+- **Packet types:** ADVERT, TXT_MSG, GRP_TXT, REQ, CHAN, POS — what each means.
+- **Observer vs Node:** Observers are MQTT-connected gateways. Nodes are mesh devices.
+- **Live vs Static map:** Live map shows real-time WS data + API nodes. Static map shows all known nodes from API.
+- **Channel decryption:** channelHashHex, decryptionStatus (decrypted/no_key/decryption_failed)
+- **Geo filter:** polygon + bufferKm in config.json, excludes nodes outside boundary
+
+## How to Answer Questions
+
+1. Read the relevant frontend code FIRST — don't guess
+2. Check the live API data if applicable (analyzer.00id.net is public)
+3. Explain in user-friendly terms, not code jargon
+4. If it's a bug, route to the right squad member
+5. If it's expected behavior, explain WHY
+
+## Model
+
+Preferred: auto
@@ -1,11 +1,11 @@
-{
-  "assignments": [
-    {
-      "assignment_id": "meshcore-analyzer-001",
-      "universe": "aliens",
-      "created_at": "2026-03-26T04:22:08Z",
-      "agents": ["Kobayashi", "Hicks", "Newt", "Bishop"],
-      "reason": "Initial team casting for CoreScope project"
-    }
-  ]
-}
+{
+  "assignments": [
+    {
+      "assignment_id": "meshcore-analyzer-001",
+      "universe": "aliens",
+      "created_at": "2026-03-26T04:22:08Z",
+      "agents": ["Kobayashi", "Hicks", "Newt", "Bishop"],
+      "reason": "Initial team casting for CoreScope project"
+    }
+  ]
+}
@@ -1,6 +1,6 @@
-{
-  "version": 1,
-  "universes_allowed": ["aliens"],
-  "max_per_universe": 10,
-  "overflow_strategy": "diegetic_expansion"
-}
+{
+  "version": 1,
+  "universes_allowed": ["aliens"],
+  "max_per_universe": 10,
+  "overflow_strategy": "diegetic_expansion"
+}
@@ -1,52 +1,52 @@
-{
-  "entries": [
-    {
-      "persistent_name": "Kobayashi",
-      "role": "Lead",
-      "universe": "aliens",
-      "created_at": "2026-03-26T04:22:08Z",
-      "legacy_named": false,
-      "status": "active"
-    },
-    {
-      "persistent_name": "Hicks",
-      "role": "Backend Dev",
-      "universe": "aliens",
-      "created_at": "2026-03-26T04:22:08Z",
-      "legacy_named": false,
-      "status": "active"
-    },
-    {
-      "persistent_name": "Newt",
-      "role": "Frontend Dev",
-      "universe": "aliens",
-      "created_at": "2026-03-26T04:22:08Z",
-      "legacy_named": false,
-      "status": "active"
-    },
-    {
-      "persistent_name": "Bishop",
-      "role": "Tester",
-      "universe": "aliens",
-      "created_at": "2026-03-26T04:22:08Z",
-      "legacy_named": false,
-      "status": "active"
-    },
-    {
-      "persistent_name": "Hudson",
-      "role": "DevOps Engineer",
-      "universe": "aliens",
-      "created_at": "2026-03-27T02:00:00Z",
-      "legacy_named": false,
-      "status": "active"
-    },
-    {
-      "persistent_name": "Ripley",
-      "role": "Support Engineer",
-      "universe": "aliens",
-      "created_at": "2026-03-27T16:12:00Z",
-      "legacy_named": false,
-      "status": "active"
-    }
-  ]
-}
+{
+  "entries": [
+    {
+      "persistent_name": "Kobayashi",
+      "role": "Lead",
+      "universe": "aliens",
+      "created_at": "2026-03-26T04:22:08Z",
+      "legacy_named": false,
+      "status": "active"
+    },
+    {
+      "persistent_name": "Hicks",
+      "role": "Backend Dev",
+      "universe": "aliens",
+      "created_at": "2026-03-26T04:22:08Z",
+      "legacy_named": false,
+      "status": "active"
+    },
+    {
+      "persistent_name": "Newt",
+      "role": "Frontend Dev",
+      "universe": "aliens",
+      "created_at": "2026-03-26T04:22:08Z",
+      "legacy_named": false,
+      "status": "active"
+    },
+    {
+      "persistent_name": "Bishop",
+      "role": "Tester",
+      "universe": "aliens",
+      "created_at": "2026-03-26T04:22:08Z",
+      "legacy_named": false,
+      "status": "active"
+    },
+    {
+      "persistent_name": "Hudson",
+      "role": "DevOps Engineer",
+      "universe": "aliens",
+      "created_at": "2026-03-27T02:00:00Z",
+      "legacy_named": false,
+      "status": "active"
+    },
+    {
+      "persistent_name": "Ripley",
+      "role": "Support Engineer",
+      "universe": "aliens",
+      "created_at": "2026-03-27T16:12:00Z",
+      "legacy_named": false,
+      "status": "active"
+    }
+  ]
+}
@@ -1,41 +1,41 @@
-# Ceremonies
-
-> Team meetings that happen before or after work. Each squad configures their own.
-
-## Design Review
-
-| Field | Value |
-|-------|-------|
-| **Trigger** | auto |
-| **When** | before |
-| **Condition** | multi-agent task involving 2+ agents modifying shared systems |
-| **Facilitator** | lead |
-| **Participants** | all-relevant |
-| **Time budget** | focused |
-| **Enabled** | ✅ yes |
-
-**Agenda:**
-1. Review the task and requirements
-2. Agree on interfaces and contracts between components
-3. Identify risks and edge cases
-4. Assign action items
-
---
-
-## Retrospective
-
-| Field | Value |
-|-------|-------|
-| **Trigger** | auto |
-| **When** | after |
-| **Condition** | build failure, test failure, or reviewer rejection |
-| **Facilitator** | lead |
-| **Participants** | all-involved |
-| **Time budget** | focused |
-| **Enabled** | ✅ yes |
-
-**Agenda:**
-1. What happened? (facts only)
-2. Root cause analysis
-3. What should change?
-4. Action items for next iteration
+# Ceremonies
+
+> Team meetings that happen before or after work. Each squad configures their own.
+
+## Design Review
+
+| Field | Value |
+|-------|-------|
+| **Trigger** | auto |
+| **When** | before |
+| **Condition** | multi-agent task involving 2+ agents modifying shared systems |
+| **Facilitator** | lead |
+| **Participants** | all-relevant |
+| **Time budget** | focused |
+| **Enabled** | ✅ yes |
+
+**Agenda:**
+1. Review the task and requirements
+2. Agree on interfaces and contracts between components
+3. Identify risks and edge cases
+4. Assign action items
+
+---
+
+## Retrospective
+
+| Field | Value |
+|-------|-------|
+| **Trigger** | auto |
+| **When** | after |
+| **Condition** | build failure, test failure, or reviewer rejection |
+| **Facilitator** | lead |
+| **Participants** | all-involved |
+| **Time budget** | focused |
+| **Enabled** | ✅ yes |
+
+**Agenda:**
+1. What happened? (facts only)
+2. Root cause analysis
+3. What should change?
+4. Action items for next iteration
@@ -1,354 +1,354 @@
-# Squad Decisions Log
-
---
-
-## Decision: User Directives
-
-### 2026-03-27T04:27 — Docker Compose v2 Plugin Check
-**By:** User (via Copilot)  
-**Decision:** CI pipeline should check if `docker compose` (v2 plugin) is installed on the self-hosted runner and install it if needed, as part of the deploy job itself.  
-**Rationale:** Self-healing CI is preferred over manual VM setup; the VM may not have docker compose v2 installed.
-
-### 2026-03-27T04:39 — Staging DB: Use Old Problematic DB
-**By:** User (via Copilot)  
-**Decision:** Staging environment's primary purpose is debugging the problematic DB that caused 100% CPU on prod. Use the old DB (`~/meshcore-data-old/` on the VM) for staging. Prod keeps its current (new) DB. Never put the problematic DB on prod.  
-**Rationale:** This is the reason the staging environment was built.
-
-### 2026-03-27T06:09 — Plan Go Rewrite (MQTT Separation)
-**By:** User (via Copilot)  
-**Decision:** Start planning a Go rewrite. First step: separate MQTT ingestion (writes to DB) from the web server (reads from DB + serves API/frontend). Two separate services.  
-**Rationale:** Node.js single-thread + V8 heap limitations cause fragility at scale (185MB DB → 2.7GB heap → OOM). Go eliminates heap cap problem and enables real concurrency.
-
-### 2026-03-27T06:31 — NO PII in Git
-**By:** User (via Copilot)  
-**Decision:** NEVER write real names, usernames, email addresses, or any PII to files committed to git. Use "User" for attribution and "deploy" for SSH/server references. This is a PUBLIC repo.  
-**Rationale:** PII was leaked to the public repo and required a full git history rewrite to remove.
-
-### 2026-03-27T02:19 — Production/Infrastructure Touches: Hudson Only
-**By:** User (via Copilot)  
-**Decision:** Production/infrastructure touches (SSH, DB ops, server restarts, Azure operations) should only be done by Hudson (DevOps). No other agents should touch prod directly.  
-**Rationale:** Separation of concerns — dev agents write code, DevOps deploys and manages prod.
-
-### 2026-03-27T03:36 — Staging Environment Architecture
-**By:** User (via Copilot)  
-**Decision:**
-1. No Docker named volumes — always bind mount from `~/meshcore-data` (host location, easy to access)
-2. Staging container runs on plaintext port (e.g., port 81, no HTTPS)
-3. Use Docker Compose to orchestrate prod + staging containers on the same VM
-4. `manage.sh` supports launching prod only OR prod+staging with clear messaging
-5. Ports must be configurable via `manage.sh` or environment, with sane defaults
-
-### 2026-03-27T03:43 — Staging Refinements: Shared Data
-**By:** User (via Copilot)  
-**Decision:**
-1. Staging copies prod DB on launch (snapshot into staging data dir when started)
-2. Staging connects to SAME MQTT broker as prod (not its own Mosquitto)
-
-**Rationale:** Staging needs real data (prod-like conditions) to be useful for testing.
-
-### 2026-03-27T17:13 — Scribe Auto-Run After Agent Batches
-**By:** User (via Copilot)  
-**Decision:** Scribe must run after EVERY batch of agent work automatically. No manual triggers. No reminders needed. This is a process guarantee, not a suggestion.  
-**Rationale:** Coordinator has been forgetting to spawn Scribe after agent batches complete. This is a process failure. Scribe auto-spawn ends the forgetfulness.
-
---
-
-## Decision: Technical Fixes
-
-### Issue #126 — Skip Ambiguous Hop Prefixes
-**By:** Hicks (Backend Dev)  
-**Date:** 2026-03-27  
-**Status:** Implemented
-
-When resolving hop prefixes to full node pubkeys, require a **unique match**. If prefix matches 2+ nodes in DB, skip it and cache in `ambiguousHopPrefixes` (negative cache). Prevents hash prefix collisions (e.g., `1CC4` vs `1C82` sharing prefix `1C` under 1-byte hash_size) from attributing packets to wrong nodes.
-
-**Impact:**
- Hopresixes that collide won't update `lastPathSeenMap` for any node (conservative, correct)
- `disambiguateHops()` still does geometric disambiguation for route visualization
- Performance: `LIMIT 2` query efficient; ambiguous results cached
-
---
-
-### Issue #133 — Phantom Nodes & Active Window
-**By:** Hicks (Backend Dev)  
-**Date:** 2026-03-27  
-**Status:** Implemented
-
-**Part 1: Remove phantom node creation**
- `autoLearnHopNodes()` no longer calls `db.upsertNode()` for unresolved hops
- Added `db.removePhantomNodes()` — deletes nodes where `LENGTH(public_key) <= 16` (real keys are 64 hex chars)
- Called at startup to purge existing phantoms from prior behavior
- Hop-resolver still handles unresolved prefixes gracefully
-
-**Part 2: totalNodes now 7-day active window**
- `/api/stats` `totalNodes` returns only nodes seen in last 7 days (was all-time)
- New field `totalNodesAllTime` for historical tracking
- Role counts (repeaters, rooms, companions, sensors) also filtered to 7-day window
- Frontend: no changes needed (same field name, smaller correct number)
-
-**Impact:** Frontend `totalNodes` now reflects active mesh size. Go server should apply same 7-day filter when querying.
-
---
-
-### Issue #123 — Channel Hash on Undecrypted Messages
-**By:** Hicks  
-**Status:** Implemented
-
-Fixed test coverage for decrypted status tracking on channel messages.
-
---
-
-### Issue #130 — Live Map: Dim Stale Nodes, Don't Remove
-**By:** Newt (Frontend)  
-**Date:** 2026-03-27  
-**Status:** Implemented
-
-`pruneStaleNodes()` in `live.js` now distinguishes API-loaded nodes (`_fromAPI`) from WS-only dynamic nodes. API nodes dimmed (reduced opacity) when stale instead of removed. WS-only nodes still pruned to prevent memory leaks.
-
-**Rationale:** Static map shows stale nodes with faded markers; live map was deleting them, causing user-reported disappearing nodes. Parity expected.
-
-**Pattern:** Database-loaded nodes never removed from map during session. Future live map features should respect `_fromAPI` flag.
-
---
-
-### Issue #131 — Nodes Tab Auto-Update via WebSocket
-**By:** Newt (Frontend)  
-**Date:** 2026-03-27  
-**Status:** Implemented
-
-WS-driven page updates must reset local caches: (1) set local cache to null, (2) call `invalidateApiCache()`, (3) re-fetch. New `loadNodes(refreshOnly)` pattern skips full DOM rebuild, only updates data rows. Preserves scroll, selection, listeners.
-
-**Trap:** Two-layer caching (local variable + API cache) prevents re-fetches. All three reset steps required.
-
-**Pattern:** Other pages doing WS-driven updates should follow same approach.
-
---
-
-### Issue #129 — Observer Comparison Page
-**By:** Newt (Frontend)  
-**Date:** 2026-03-27  
-**Status:** Implemented
-
-Added `comparePacketSets(hashesA, hashesB)` as standalone pure function exposed on `window` for testability. Computes `{ onlyA, onlyB, both }` via Set operations (O(n)).
-
-**Pattern:** Comparison logic decoupled from UI, reusable. Client-side diff avoids new server endpoint. 24-hour window keeps data size reasonable (~10K packets max).
-
---
-
-### Issue #132 — Detail Pane Collapse
-**By:** Newt (Frontend)  
-**Date:** 2026-03-27  
-**Status:** Implemented
-
-Detail pane collapse uses CSS class on parent container. Add `detail-collapsed` class to `.split-layout`, which sets `.panel-right` to `display: none`. `.panel-left` with `flex: 1` fills 100% width naturally.
-
-**Pattern:** CSS class toggling on parent cleaner than inline styles, easier to animate, keeps layout logic in CSS.
-
---
-
-## Decision: Infrastructure & Deployment
-
-### Database Merge — Prod + Staging
-**By:** Kobayashi (Lead) / Hudson (DevOps)  
-**Date:** 2026-03-27  
-**Status:** ✅ Complete
-
-Merged staging DB (185MB, 50K transmissions + 1.2M observations) into prod DB (21MB). Dedup strategy:
- **Transmissions:** `INSERT OR IGNORE` on `hash` (unique key)
- **Observations:** All unique by observer, all preserved
- **Nodes/Observers:** Latest `last_seen` wins, sum counts
-
-**Results:**
- Merged DB: 51,723 transmissions, 1,237,186 observations
- Deployment: Docker Compose managed `meshcore-prod` with bind mounts
- Load time: 8,491ms, Memory: 860MiB RSS (no NODE_OPTIONS needed, RAM fix effective)
- Downtime: ~2 minutes
- Backups: Retained at `/home/deploy/backups/pre-merge-20260327-071425/` until 2026-04-03
-
---
-
-### Unified Docker Volume Paths
-**By:** Hudson (DevOps)  
-**Date:** 2026-03-27  
-**Status:** Applied
-
-Reconciled `manage.sh` and `docker-compose.yml` Docker volume names:
- Caddy volume: `caddy-data` everywhere (prod); `caddy-data-staging` for staging
- Data directory: Bind mount via `PROD_DATA_DIR` env var, default `~/meshcore-data`
- Config/Caddyfile: Mounted from repo checkout for prod, staging data dir for staging
- Removed deprecated `version` key from docker-compose.yml
-
-**Consequence:** `./manage.sh start` and `docker compose up prod` now produce identical mounts. Anyone with data in old `caddy-data-prod` volume will need Caddy to re-provision TLS certs automatically.
-
---
-
-### Staging DB Setup & Production Data Locations
-**By:** Hudson (DevOps)  
-**Date:** 2026-03-27  
-**Status:** Implemented
-
-**Production Data Locations:**
- **Prod DB:** Docker volume `meshcore-data` → `/var/lib/docker/volumes/meshcore-data/_data/meshcore.db` (21MB, fresh)
- **Prod config:** `/home/deploy/meshcore-analyzer/config.json` (bind mount, read-only)
- **Caddyfile:** `/home/deploy/meshcore-analyzer/caddy-config/Caddyfile` (bind mount, read-only)
- **Old (broken) DB:** `~/meshcore-data-old/meshcore.db` (185MB, DO NOT DELETE)
- **Staging data:** `~/meshcore-staging-data/` (copy of broken DB + config)
-
-**Rules:**
- DO NOT delete `~/meshcore-data-old/` — backup of problematic DB
- DO NOT modify staging DB before staging container ready
- Only Hudson touches prod infrastructure
-
---
-
-## Decision: Go Rewrite — API & Storage
-
-### Go MQTT Ingestor (cmd/ingestor/)
-**By:** Hicks (Backend Dev)  
-**Date:** 2026-03-27  
-**Status:** Implemented, 25 tests passing
-
-Standalone Go MQTT ingestor service. Separate process from Node.js web server that handles MQTT packet ingestion + writes to shared SQLite DB.
-
-**Architecture:**
- Single binary, no CGO (uses `modernc.org/sqlite` pure Go)
- Reads same `config.json` (mqttSources array)
- Shares SQLite DB with Node.js (WAL mode for concurrent access)
- Format 1 (raw packet) MQTT only — companion bridge stays in Node.js
- No HTTP/WebSocket — web layer stays in Node.js
-
-**Ported from decoder.js:**
- Packet header/path/payloads, advert with flags/lat/lon/name
- computeContentHash (SHA-256, path-independent)
- db.js v3 schema (transmissions, observations, nodes, observers)
- MQTT connection logic (multi-broker, reconnect, IATA filter)
-
-**Not Ported:** Companion bridge format, channel key decryption, WebSocket broadcast, in-memory packet store.
-
---
-
-### Go Web Server (cmd/server/)
-**By:** Hicks (Backend Dev)  
-**Date:** 2026-03-27  
-**Status:** Implemented, 42 tests passing, `go vet` clean
-
-Standalone Go web server replacing Node.js server's READ side (REST API + WebSocket). Two-component rewrite: ingestor (MQTT writes), server (REST/WS reads).
-
-**Architecture Decisions:**
-1. **Direct SQLite queries** — No in-memory packet store; all reads via `packets_v` view (v3 schema)
-2. **Per-module go.mod** — Each `cmd/*` directory has own `go.mod`
-3. **gorilla/mux for routing** — Handles 35+ parameterized routes cleanly
-4. **SQLite polling for WebSocket** — Polls for new transmission IDs every 1s (decouples from MQTT)
-5. **Analytics stubs** — Topology, distance, hash-sizes, subpath return valid structural responses (empty data). RF/channels implemented via SQL.
-6. **Response shape compatibility** — All endpoints return JSON matching Node.js exactly (frontend works unchanged)
-
-**Files:**
- `cmd/server/main.go` — Entry, HTTP, graceful shutdown
- `cmd/server/db.go` — SQLite read queries
- `cmd/server/routes.go` — 35+ REST API handlers
- `cmd/server/websocket.go` — Hub + SQLite poller
- `cmd/server/README.md` — Build/run docs
-
-**Future Work:** Full analytics via SQL, TTL response cache, shared `internal/db/` package, TLS, region-aware filtering.
-
---
-
-### Go API Parity: Transmission-Centric Queries
-**By:** Hicks (Backend Dev)  
-**Date:** 2026-03-27  
-**Status:** Implemented, all 42+ tests pass
-
-Go server rewrote packet list queries from VIEW-based (slow, wrong shape) to **transmission-centric** with correlated subqueries. Schema version detection (`isV3` flag) handles both v2 and v3 schemas.
-
-**Performance Fix:** `/api/packets?groupByHash=true` — 8s → <100ms (query `transmissions` table 52K rows instead of `packets_v` 1.2M observations).
-
-**Field Parity:**
- `totalNodes` now 7-day active window (was all-time)
- Added `totalNodesAllTime` field
- Role counts use 7-day filter (matches Node.js line 880-886)
- `/api/nodes` counts use no time filter; `/api/stats` uses 7-day (separate methods avoid conflation)
- `/api/packets/:id` now parses `path_json`, returns actual hop array
- `/api/observers` — packetsLastHour, lat, lon, nodeRole computed from SQL
- `/api/nodes/bulk-health` — Per-node stats computed (was returning zeros)
- `/api/packets` — Multi-node filter support (`nodes` query param, comma-separated pubkeys)
-
---
-
-### Go In-Memory Packet Store (cmd/server/store.go)
-**By:** Hicks (Backend Dev)  
-**Date:** 2026-03-26  
-**Status:** Implemented
-
-Port of `packet-store.js` with streaming load, 5 indexes, lean observation structs (only observation-specific fields). `QueryPackets` handles type, route, observer, hash, since, until, region, node. `IngestNewFromDB()` streams new transmissions from DB into memory.
-
-**Trade-offs:**
- Memory: ~450 bytes/tx + ~100 bytes/obs (52K tx + 1.2M obs ≈ ~143MB)
- Startup: One-time load adds few seconds (acceptable)
- DB still used for: analytics, node/observer queries, role counts, region resolution
-
---
-
-### Observation RAM Optimization
-**By:** Hicks (Backend Dev)  
-**Date:** 2026-03-27  
-**Status:** Implemented
-
-Observation objects in in-memory packet store now store only `transmission_id` reference instead of copying `hash`, `raw_hex`, `decoded_json`, `payload_type`, `route_type` from parent. API boundary methods (`getById`, `getSiblings`, `enrichObservations`) hydrate on demand. Load uses `.iterate()` instead of `.all()` to avoid materializing full JOIN.
-
-**Impact:** Eliminates ~1.17M redundant string copies, avoids 1.17M-row array during startup. 2.7GB RAM → acceptable levels with 185MB database.
-
-**Code Pattern:** Any code reading observation objects from `tx.observations` directly must use `pktStore.enrichObservations()` if it needs transmission fields. Internal iteration over observations for observer_id, snr, rssi, path_json works unchanged.
-
---
-
-## Decision: E2E Playwright Performance Improvements
-
-**Author:** Kobayashi (Lead)  
-**Date:** 2026-03-26  
-**Status:** Proposed — awaiting user sign-off before implementation
-
-Playwright E2E tests (16 tests in `test-e2e-playwright.js`) are slow in CI. Analysis identified ~40-50% potential runtime reduction.
-
-### Recommendations (prioritized)
-
-#### HIGH impact (30%+ improvement)
-
-1. **Replace `waitUntil: 'networkidle'` with `'domcontentloaded'` + targeted waits** — used ~20 times; `networkidle` worst-case for SPAs with persistent WebSocket + Leaflet tile loading. Each navigation pays 500ms+ penalty.
-
-2. **Eliminate redundant navigations** — group tests by route; navigate once, run all assertions for that route.
-
-3. **Cache Playwright browser install in CI** — `npx playwright install chromium --with-deps` runs every frontend push. Self-hosted runner should retain browser between runs.
-
-#### MEDIUM impact (10-30%)
-
-4. **Replace hardcoded `waitForTimeout` with event-driven waits** — ~17s scattered. Replace with `waitForSelector`, `waitForFunction`, or `page.waitForResponse`.
-
-5. **Merge coverage collection into E2E run** — `collect-frontend-coverage.js` launches second browser. Extract `window.__coverage__` at E2E end instead.
-
-6. **Replace `sleep 5` server startup with health-check polling** — Start tests as soon as `/api/stats` responsive (~1-2s savings).
-
-#### LOW impact (<10%)
-
-7. **Block unnecessary resources for non-visual tests** — use `page.route()` to abort map tiles, fonts.
-
-8. **Reduce default timeout 15s → 10s** — sufficient for local CI.
-
-### Implementation notes
-
- Items 1-2 are test-file-only (Bishop/Newt scope)
- Items 3, 5-6 are CI pipeline (Hicks scope)
- No architectural changes; all incremental
- All assertions remain identical — only wait strategies change
-
---
-
-### 2026-03-27T20:56:00Z — Protobuf API Contract (Merged)
-**By:** Kpa-clawbot (via Copilot)  
-**Decision:** 
-1. All frontend/backend interfaces get protobuf definitions as single source of truth
-2. Go generates structs with JSON tags from protos; Node stays unchanged — protos derived from Node's current JSON shapes
-3. Proto definitions MUST use inheritance and composition (no repeating field definitions)
-4. Data flow: SQLite → proto struct → JSON; JSON blobs from DB deserialize against proto structs for validation
-5. CI pipeline's proto fixture capture runs against prod (stable reference), not staging
-
-**Rationale:** Eliminates parity bugs between Node and Go. Compiler-enforced contract. Prod is known-good baseline.
+# Squad Decisions Log
+
+---
+
+## Decision: User Directives
+
+### 2026-03-27T04:27 — Docker Compose v2 Plugin Check
+**By:** User (via Copilot)  
+**Decision:** CI pipeline should check if `docker compose` (v2 plugin) is installed on the self-hosted runner and install it if needed, as part of the deploy job itself.  
+**Rationale:** Self-healing CI is preferred over manual VM setup; the VM may not have docker compose v2 installed.
+
+### 2026-03-27T04:39 — Staging DB: Use Old Problematic DB
+**By:** User (via Copilot)  
+**Decision:** Staging environment's primary purpose is debugging the problematic DB that caused 100% CPU on prod. Use the old DB (`~/meshcore-data-old/` on the VM) for staging. Prod keeps its current (new) DB. Never put the problematic DB on prod.  
+**Rationale:** This is the reason the staging environment was built.
+
+### 2026-03-27T06:09 — Plan Go Rewrite (MQTT Separation)
+**By:** User (via Copilot)  
+**Decision:** Start planning a Go rewrite. First step: separate MQTT ingestion (writes to DB) from the web server (reads from DB + serves API/frontend). Two separate services.  
+**Rationale:** Node.js single-thread + V8 heap limitations cause fragility at scale (185MB DB → 2.7GB heap → OOM). Go eliminates heap cap problem and enables real concurrency.
+
+### 2026-03-27T06:31 — NO PII in Git
+**By:** User (via Copilot)  
+**Decision:** NEVER write real names, usernames, email addresses, or any PII to files committed to git. Use "User" for attribution and "deploy" for SSH/server references. This is a PUBLIC repo.  
+**Rationale:** PII was leaked to the public repo and required a full git history rewrite to remove.
+
+### 2026-03-27T02:19 — Production/Infrastructure Touches: Hudson Only
+**By:** User (via Copilot)  
+**Decision:** Production/infrastructure touches (SSH, DB ops, server restarts, Azure operations) should only be done by Hudson (DevOps). No other agents should touch prod directly.  
+**Rationale:** Separation of concerns — dev agents write code, DevOps deploys and manages prod.
+
+### 2026-03-27T03:36 — Staging Environment Architecture
+**By:** User (via Copilot)  
+**Decision:**
+1. No Docker named volumes — always bind mount from `~/meshcore-data` (host location, easy to access)
+2. Staging container runs on plaintext port (e.g., port 81, no HTTPS)
+3. Use Docker Compose to orchestrate prod + staging containers on the same VM
+4. `manage.sh` supports launching prod only OR prod+staging with clear messaging
+5. Ports must be configurable via `manage.sh` or environment, with sane defaults
+
+### 2026-03-27T03:43 — Staging Refinements: Shared Data
+**By:** User (via Copilot)  
+**Decision:**
+1. Staging copies prod DB on launch (snapshot into staging data dir when started)
+2. Staging connects to SAME MQTT broker as prod (not its own Mosquitto)
+
+**Rationale:** Staging needs real data (prod-like conditions) to be useful for testing.
+
+### 2026-03-27T17:13 — Scribe Auto-Run After Agent Batches
+**By:** User (via Copilot)  
+**Decision:** Scribe must run after EVERY batch of agent work automatically. No manual triggers. No reminders needed. This is a process guarantee, not a suggestion.  
+**Rationale:** Coordinator has been forgetting to spawn Scribe after agent batches complete. This is a process failure. Scribe auto-spawn ends the forgetfulness.
+
+---
+
+## Decision: Technical Fixes
+
+### Issue #126 — Skip Ambiguous Hop Prefixes
+**By:** Hicks (Backend Dev)  
+**Date:** 2026-03-27  
+**Status:** Implemented
+
+When resolving hop prefixes to full node pubkeys, require a **unique match**. If prefix matches 2+ nodes in DB, skip it and cache in `ambiguousHopPrefixes` (negative cache). Prevents hash prefix collisions (e.g., `1CC4` vs `1C82` sharing prefix `1C` under 1-byte hash_size) from attributing packets to wrong nodes.
+
+**Impact:**
+- Hopresixes that collide won't update `lastPathSeenMap` for any node (conservative, correct)
+- `disambiguateHops()` still does geometric disambiguation for route visualization
+- Performance: `LIMIT 2` query efficient; ambiguous results cached
+
+---
+
+### Issue #133 — Phantom Nodes & Active Window
+**By:** Hicks (Backend Dev)  
+**Date:** 2026-03-27  
+**Status:** Implemented
+
+**Part 1: Remove phantom node creation**
+- `autoLearnHopNodes()` no longer calls `db.upsertNode()` for unresolved hops
+- Added `db.removePhantomNodes()` — deletes nodes where `LENGTH(public_key) <= 16` (real keys are 64 hex chars)
+- Called at startup to purge existing phantoms from prior behavior
+- Hop-resolver still handles unresolved prefixes gracefully
+
+**Part 2: totalNodes now 7-day active window**
+- `/api/stats` `totalNodes` returns only nodes seen in last 7 days (was all-time)
+- New field `totalNodesAllTime` for historical tracking
+- Role counts (repeaters, rooms, companions, sensors) also filtered to 7-day window
+- Frontend: no changes needed (same field name, smaller correct number)
+
+**Impact:** Frontend `totalNodes` now reflects active mesh size. Go server should apply same 7-day filter when querying.
+
+---
+
+### Issue #123 — Channel Hash on Undecrypted Messages
+**By:** Hicks  
+**Status:** Implemented
+
+Fixed test coverage for decrypted status tracking on channel messages.
+
+---
+
+### Issue #130 — Live Map: Dim Stale Nodes, Don't Remove
+**By:** Newt (Frontend)  
+**Date:** 2026-03-27  
+**Status:** Implemented
+
+`pruneStaleNodes()` in `live.js` now distinguishes API-loaded nodes (`_fromAPI`) from WS-only dynamic nodes. API nodes dimmed (reduced opacity) when stale instead of removed. WS-only nodes still pruned to prevent memory leaks.
+
+**Rationale:** Static map shows stale nodes with faded markers; live map was deleting them, causing user-reported disappearing nodes. Parity expected.
+
+**Pattern:** Database-loaded nodes never removed from map during session. Future live map features should respect `_fromAPI` flag.
+
+---
+
+### Issue #131 — Nodes Tab Auto-Update via WebSocket
+**By:** Newt (Frontend)  
+**Date:** 2026-03-27  
+**Status:** Implemented
+
+WS-driven page updates must reset local caches: (1) set local cache to null, (2) call `invalidateApiCache()`, (3) re-fetch. New `loadNodes(refreshOnly)` pattern skips full DOM rebuild, only updates data rows. Preserves scroll, selection, listeners.
+
+**Trap:** Two-layer caching (local variable + API cache) prevents re-fetches. All three reset steps required.
+
+**Pattern:** Other pages doing WS-driven updates should follow same approach.
+
+---
+
+### Issue #129 — Observer Comparison Page
+**By:** Newt (Frontend)  
+**Date:** 2026-03-27  
+**Status:** Implemented
+
+Added `comparePacketSets(hashesA, hashesB)` as standalone pure function exposed on `window` for testability. Computes `{ onlyA, onlyB, both }` via Set operations (O(n)).
+
+**Pattern:** Comparison logic decoupled from UI, reusable. Client-side diff avoids new server endpoint. 24-hour window keeps data size reasonable (~10K packets max).
+
+---
+
+### Issue #132 — Detail Pane Collapse
+**By:** Newt (Frontend)  
+**Date:** 2026-03-27  
+**Status:** Implemented
+
+Detail pane collapse uses CSS class on parent container. Add `detail-collapsed` class to `.split-layout`, which sets `.panel-right` to `display: none`. `.panel-left` with `flex: 1` fills 100% width naturally.
+
+**Pattern:** CSS class toggling on parent cleaner than inline styles, easier to animate, keeps layout logic in CSS.
+
+---
+
+## Decision: Infrastructure & Deployment
+
+### Database Merge — Prod + Staging
+**By:** Kobayashi (Lead) / Hudson (DevOps)  
+**Date:** 2026-03-27  
+**Status:** ✅ Complete
+
+Merged staging DB (185MB, 50K transmissions + 1.2M observations) into prod DB (21MB). Dedup strategy:
+- **Transmissions:** `INSERT OR IGNORE` on `hash` (unique key)
+- **Observations:** All unique by observer, all preserved
+- **Nodes/Observers:** Latest `last_seen` wins, sum counts
+
+**Results:**
+- Merged DB: 51,723 transmissions, 1,237,186 observations
+- Deployment: Docker Compose managed `meshcore-prod` with bind mounts
+- Load time: 8,491ms, Memory: 860MiB RSS (no NODE_OPTIONS needed, RAM fix effective)
+- Downtime: ~2 minutes
+- Backups: Retained at `/home/deploy/backups/pre-merge-20260327-071425/` until 2026-04-03
+
+---
+
+### Unified Docker Volume Paths
+**By:** Hudson (DevOps)  
+**Date:** 2026-03-27  
+**Status:** Applied
+
+Reconciled `manage.sh` and `docker-compose.yml` Docker volume names:
+- Caddy volume: `caddy-data` everywhere (prod); `caddy-data-staging` for staging
+- Data directory: Bind mount via `PROD_DATA_DIR` env var, default `~/meshcore-data`
+- Config/Caddyfile: Mounted from repo checkout for prod, staging data dir for staging
+- Removed deprecated `version` key from docker-compose.yml
+
+**Consequence:** `./manage.sh start` and `docker compose up prod` now produce identical mounts. Anyone with data in old `caddy-data-prod` volume will need Caddy to re-provision TLS certs automatically.
+
+---
+
+### Staging DB Setup & Production Data Locations
+**By:** Hudson (DevOps)  
+**Date:** 2026-03-27  
+**Status:** Implemented
+
+**Production Data Locations:**
+- **Prod DB:** Docker volume `meshcore-data` → `/var/lib/docker/volumes/meshcore-data/_data/meshcore.db` (21MB, fresh)
+- **Prod config:** `/home/deploy/meshcore-analyzer/config.json` (bind mount, read-only)
+- **Caddyfile:** `/home/deploy/meshcore-analyzer/caddy-config/Caddyfile` (bind mount, read-only)
+- **Old (broken) DB:** `~/meshcore-data-old/meshcore.db` (185MB, DO NOT DELETE)
+- **Staging data:** `~/meshcore-staging-data/` (copy of broken DB + config)
+
+**Rules:**
+- DO NOT delete `~/meshcore-data-old/` — backup of problematic DB
+- DO NOT modify staging DB before staging container ready
+- Only Hudson touches prod infrastructure
+
+---
+
+## Decision: Go Rewrite — API & Storage
+
+### Go MQTT Ingestor (cmd/ingestor/)
+**By:** Hicks (Backend Dev)  
+**Date:** 2026-03-27  
+**Status:** Implemented, 25 tests passing
+
+Standalone Go MQTT ingestor service. Separate process from Node.js web server that handles MQTT packet ingestion + writes to shared SQLite DB.
+
+**Architecture:**
+- Single binary, no CGO (uses `modernc.org/sqlite` pure Go)
+- Reads same `config.json` (mqttSources array)
+- Shares SQLite DB with Node.js (WAL mode for concurrent access)
+- Format 1 (raw packet) MQTT only — companion bridge stays in Node.js
+- No HTTP/WebSocket — web layer stays in Node.js
+
+**Ported from decoder.js:**
+- Packet header/path/payloads, advert with flags/lat/lon/name
+- computeContentHash (SHA-256, path-independent)
+- db.js v3 schema (transmissions, observations, nodes, observers)
+- MQTT connection logic (multi-broker, reconnect, IATA filter)
+
+**Not Ported:** Companion bridge format, channel key decryption, WebSocket broadcast, in-memory packet store.
+
+---
+
+### Go Web Server (cmd/server/)
+**By:** Hicks (Backend Dev)  
+**Date:** 2026-03-27  
+**Status:** Implemented, 42 tests passing, `go vet` clean
+
+Standalone Go web server replacing Node.js server's READ side (REST API + WebSocket). Two-component rewrite: ingestor (MQTT writes), server (REST/WS reads).
+
+**Architecture Decisions:**
+1. **Direct SQLite queries** — No in-memory packet store; all reads via `packets_v` view (v3 schema)
+2. **Per-module go.mod** — Each `cmd/*` directory has own `go.mod`
+3. **gorilla/mux for routing** — Handles 35+ parameterized routes cleanly
+4. **SQLite polling for WebSocket** — Polls for new transmission IDs every 1s (decouples from MQTT)
+5. **Analytics stubs** — Topology, distance, hash-sizes, subpath return valid structural responses (empty data). RF/channels implemented via SQL.
+6. **Response shape compatibility** — All endpoints return JSON matching Node.js exactly (frontend works unchanged)
+
+**Files:**
+- `cmd/server/main.go` — Entry, HTTP, graceful shutdown
+- `cmd/server/db.go` — SQLite read queries
+- `cmd/server/routes.go` — 35+ REST API handlers
+- `cmd/server/websocket.go` — Hub + SQLite poller
+- `cmd/server/README.md` — Build/run docs
+
+**Future Work:** Full analytics via SQL, TTL response cache, shared `internal/db/` package, TLS, region-aware filtering.
+
+---
+
+### Go API Parity: Transmission-Centric Queries
+**By:** Hicks (Backend Dev)  
+**Date:** 2026-03-27  
+**Status:** Implemented, all 42+ tests pass
+
+Go server rewrote packet list queries from VIEW-based (slow, wrong shape) to **transmission-centric** with correlated subqueries. Schema version detection (`isV3` flag) handles both v2 and v3 schemas.
+
+**Performance Fix:** `/api/packets?groupByHash=true` — 8s → <100ms (query `transmissions` table 52K rows instead of `packets_v` 1.2M observations).
+
+**Field Parity:**
+- `totalNodes` now 7-day active window (was all-time)
+- Added `totalNodesAllTime` field
+- Role counts use 7-day filter (matches Node.js line 880-886)
+- `/api/nodes` counts use no time filter; `/api/stats` uses 7-day (separate methods avoid conflation)
+- `/api/packets/:id` now parses `path_json`, returns actual hop array
+- `/api/observers` — packetsLastHour, lat, lon, nodeRole computed from SQL
+- `/api/nodes/bulk-health` — Per-node stats computed (was returning zeros)
+- `/api/packets` — Multi-node filter support (`nodes` query param, comma-separated pubkeys)
+
+---
+
+### Go In-Memory Packet Store (cmd/server/store.go)
+**By:** Hicks (Backend Dev)  
+**Date:** 2026-03-26  
+**Status:** Implemented
+
+Port of `packet-store.js` with streaming load, 5 indexes, lean observation structs (only observation-specific fields). `QueryPackets` handles type, route, observer, hash, since, until, region, node. `IngestNewFromDB()` streams new transmissions from DB into memory.
+
+**Trade-offs:**
+- Memory: ~450 bytes/tx + ~100 bytes/obs (52K tx + 1.2M obs ≈ ~143MB)
+- Startup: One-time load adds few seconds (acceptable)
+- DB still used for: analytics, node/observer queries, role counts, region resolution
+
+---
+
+### Observation RAM Optimization
+**By:** Hicks (Backend Dev)  
+**Date:** 2026-03-27  
+**Status:** Implemented
+
+Observation objects in in-memory packet store now store only `transmission_id` reference instead of copying `hash`, `raw_hex`, `decoded_json`, `payload_type`, `route_type` from parent. API boundary methods (`getById`, `getSiblings`, `enrichObservations`) hydrate on demand. Load uses `.iterate()` instead of `.all()` to avoid materializing full JOIN.
+
+**Impact:** Eliminates ~1.17M redundant string copies, avoids 1.17M-row array during startup. 2.7GB RAM → acceptable levels with 185MB database.
+
+**Code Pattern:** Any code reading observation objects from `tx.observations` directly must use `pktStore.enrichObservations()` if it needs transmission fields. Internal iteration over observations for observer_id, snr, rssi, path_json works unchanged.
+
+---
+
+## Decision: E2E Playwright Performance Improvements
+
+**Author:** Kobayashi (Lead)  
+**Date:** 2026-03-26  
+**Status:** Proposed — awaiting user sign-off before implementation
+
+Playwright E2E tests (16 tests in `test-e2e-playwright.js`) are slow in CI. Analysis identified ~40-50% potential runtime reduction.
+
+### Recommendations (prioritized)
+
+#### HIGH impact (30%+ improvement)
+
+1. **Replace `waitUntil: 'networkidle'` with `'domcontentloaded'` + targeted waits** — used ~20 times; `networkidle` worst-case for SPAs with persistent WebSocket + Leaflet tile loading. Each navigation pays 500ms+ penalty.
+
+2. **Eliminate redundant navigations** — group tests by route; navigate once, run all assertions for that route.
+
+3. **Cache Playwright browser install in CI** — `npx playwright install chromium --with-deps` runs every frontend push. Self-hosted runner should retain browser between runs.
+
+#### MEDIUM impact (10-30%)
+
+4. **Replace hardcoded `waitForTimeout` with event-driven waits** — ~17s scattered. Replace with `waitForSelector`, `waitForFunction`, or `page.waitForResponse`.
+
+5. **Merge coverage collection into E2E run** — `collect-frontend-coverage.js` launches second browser. Extract `window.__coverage__` at E2E end instead.
+
+6. **Replace `sleep 5` server startup with health-check polling** — Start tests as soon as `/api/stats` responsive (~1-2s savings).
+
+#### LOW impact (<10%)
+
+7. **Block unnecessary resources for non-visual tests** — use `page.route()` to abort map tiles, fonts.
+
+8. **Reduce default timeout 15s → 10s** — sufficient for local CI.
+
+### Implementation notes
+
+- Items 1-2 are test-file-only (Bishop/Newt scope)
+- Items 3, 5-6 are CI pipeline (Hicks scope)
+- No architectural changes; all incremental
+- All assertions remain identical — only wait strategies change
+
+---
+
+### 2026-03-27T20:56:00Z — Protobuf API Contract (Merged)
+**By:** Kpa-clawbot (via Copilot)  
+**Decision:** 
+1. All frontend/backend interfaces get protobuf definitions as single source of truth
+2. Go generates structs with JSON tags from protos; Node stays unchanged — protos derived from Node's current JSON shapes
+3. Proto definitions MUST use inheritance and composition (no repeating field definitions)
+4. Data flow: SQLite → proto struct → JSON; JSON blobs from DB deserialize against proto structs for validation
+5. CI pipeline's proto fixture capture runs against prod (stable reference), not staging
+
+**Rationale:** Eliminates parity bugs between Node and Go. Compiler-enforced contract. Prod is known-good baseline.
@@ -1,86 +1,86 @@
-# Spawn Batch — Proto Validation & Typed API Contracts
-
-**Timestamp:** 2026-03-27T22:19:53Z  
-**Scribe:** Orchestration Log Entry  
-**Scope:** Go server proto validation, fixture capture, CI architecture
-
---
-
-## Team Accomplishments (Spawn Manifest)
-
-### Hicks (Backend Dev)
- **Fixed #163:** 15 API violations — type mismatches in route handlers
- **Fixed #164:** 24 proto mismatches — shape inconsistencies between Node.js JSON and Go structs
- **Delivered:** `types.go` — 80 typed Go structs replacing all `map[string]interface{}` in route handlers
- **Impact:** Proto contract fully wired into Go server; compiler now enforces API response shapes
-
-### Bishop (Proto Validation)
- **Validated:** All proto definitions (0 errors)
- **Captured:** 33 Node.js API response fixtures from production
- **Status:** Baseline fixture set ready for CI contract testing
-
-### Hudson (CI/DevOps)
- **Implemented:** CI proto validation pipeline with all 33 fixtures
- **Fixed:** Fixture capture source changed from staging → production
- **Improved:** CI split into parallel tracks (backend tests, frontend tests, proto validation)
- **Impact:** Proto contracts now validated against prod on every push
-
-### Coordinator
- **Fixed:** Fixture capture source (staging → prod)
- **Verified:** Data integrity of captured fixtures
-
---
-
-## Key Milestone: Proto-Enforced API Contract
-
-**Status:** ✅ Complete
-
-Go server now has:
-1. Full type safety (80 structs replacing all `map[string]interface{}`)
-2. Proto definitions as single source of truth
-3. Compiler-enforced JSON field matching (no more mismatches)
-4. CI validation on every push (all 33 fixtures + 0 errors)
-
-**What Changed:**
- All route handlers return typed structs (proto-derived)
- Response shapes match Node.js JSON exactly
- Any shape mismatch caught at compile time, not test time
-
-**Frontend Impact:** None — JSON shapes unchanged, frontend code continues unchanged.
-
---
-
-## Decisions Merged
-
-**New inbox entries processed:**
-1. ✅ `copilot-directive-protobuf-contract.md` → decisions.md (1 decision)
-2. ✅ `copilot-directive-fixtures-from-prod.md` → decisions.md (1 directive)
-
-**Deduplication:** Both entries new (timestamps 2026-03-27T20:56:00Z, 2026-03-27T22:00:00Z). No duplicates detected.
-
---
-
-## Decisions File Status
-
-**Location:** `.squad/decisions/decisions.md`  
-**Current Size:** ~380 lines  
-**Archival Threshold:** 20KB  
-**Status:** ✅ Well under threshold, no archival needed
-
-**Sections:**
-1. User Directives (6 decisions)
-2. Technical Fixes (7 issues)
-3. Infrastructure & Deployment (3 decisions)
-4. Go Rewrite — API & Storage (7 decisions, +2 proto entries)
-5. E2E Playwright Performance (1 proposed strategy)
-
---
-
-## Summary
-
-**Inbox Merged:** 2 entries → decisions.md  
-**Orchestration Log:** 1 new entry (this file)  
-**Files Modified:** `.squad/decisions/decisions.md`  
-**Git Status:** Ready for commit
-
-**Next Action:** Git commit with explicit file list (no `-A` flag).
+# Spawn Batch — Proto Validation & Typed API Contracts
+
+**Timestamp:** 2026-03-27T22:19:53Z  
+**Scribe:** Orchestration Log Entry  
+**Scope:** Go server proto validation, fixture capture, CI architecture
+
+---
+
+## Team Accomplishments (Spawn Manifest)
+
+### Hicks (Backend Dev)
+- **Fixed #163:** 15 API violations — type mismatches in route handlers
+- **Fixed #164:** 24 proto mismatches — shape inconsistencies between Node.js JSON and Go structs
+- **Delivered:** `types.go` — 80 typed Go structs replacing all `map[string]interface{}` in route handlers
+- **Impact:** Proto contract fully wired into Go server; compiler now enforces API response shapes
+
+### Bishop (Proto Validation)
+- **Validated:** All proto definitions (0 errors)
+- **Captured:** 33 Node.js API response fixtures from production
+- **Status:** Baseline fixture set ready for CI contract testing
+
+### Hudson (CI/DevOps)
+- **Implemented:** CI proto validation pipeline with all 33 fixtures
+- **Fixed:** Fixture capture source changed from staging → production
+- **Improved:** CI split into parallel tracks (backend tests, frontend tests, proto validation)
+- **Impact:** Proto contracts now validated against prod on every push
+
+### Coordinator
+- **Fixed:** Fixture capture source (staging → prod)
+- **Verified:** Data integrity of captured fixtures
+
+---
+
+## Key Milestone: Proto-Enforced API Contract
+
+**Status:** ✅ Complete
+
+Go server now has:
+1. Full type safety (80 structs replacing all `map[string]interface{}`)
+2. Proto definitions as single source of truth
+3. Compiler-enforced JSON field matching (no more mismatches)
+4. CI validation on every push (all 33 fixtures + 0 errors)
+
+**What Changed:**
+- All route handlers return typed structs (proto-derived)
+- Response shapes match Node.js JSON exactly
+- Any shape mismatch caught at compile time, not test time
+
+**Frontend Impact:** None — JSON shapes unchanged, frontend code continues unchanged.
+
+---
+
+## Decisions Merged
+
+**New inbox entries processed:**
+1. ✅ `copilot-directive-protobuf-contract.md` → decisions.md (1 decision)
+2. ✅ `copilot-directive-fixtures-from-prod.md` → decisions.md (1 directive)
+
+**Deduplication:** Both entries new (timestamps 2026-03-27T20:56:00Z, 2026-03-27T22:00:00Z). No duplicates detected.
+
+---
+
+## Decisions File Status
+
+**Location:** `.squad/decisions/decisions.md`  
+**Current Size:** ~380 lines  
+**Archival Threshold:** 20KB  
+**Status:** ✅ Well under threshold, no archival needed
+
+**Sections:**
+1. User Directives (6 decisions)
+2. Technical Fixes (7 issues)
+3. Infrastructure & Deployment (3 decisions)
+4. Go Rewrite — API & Storage (7 decisions, +2 proto entries)
+5. E2E Playwright Performance (1 proposed strategy)
+
+---
+
+## Summary
+
+**Inbox Merged:** 2 entries → decisions.md  
+**Orchestration Log:** 1 new entry (this file)  
+**Files Modified:** `.squad/decisions/decisions.md`  
+**Git Status:** Ready for commit
+
+**Next Action:** Git commit with explicit file list (no `-A` flag).
@@ -1,178 +1,178 @@
-# Scribe Orchestration Log
-
-## 2026-03-27 — Session Summary & Finalization
-
-**Agent:** Scribe (Logging)  
-**Date:** 2026-03-27  
-**Task:** Merge decision inbox, write session orchestration log entry, commit .squad/ changes
-
-### Inbox Merge Status
-
-**Decision Inbox Review:** `.squad/decisions/inbox/` directory scanned — **EMPTY** (no new decisions filed during this session).
-
-**Decisions.md Status:** Current file contains 9 decision categories:
-1. User Directives (6 decisions)
-2. Technical Fixes (4 issues: #126, #133 parts 1-2, #123, #130, #131, #129, #132)
-3. Infrastructure & Deployment (3 decisions: DB merge, Docker volumes, staging setup)
-4. Go Rewrite — API & Storage (4 decisions: MQTT ingestor, web server, API parity, observation RAM optimization)
-5. E2E Playwright Performance (proposed, not yet implemented)
-
-**No merges required** — all work captured in existing decision log categories.
-
---
-
-## Session Orchestration Summary
-
-**Session Scope:** #151-160 issues + Go rewrite staging + database merge + E2E expansion
-
-### Agent Deliverables (28 issues closed)
-
-#### Hicks (Backend Dev)
- **Issues Fixed:** #123 (channel hash), #126 (hop prefixes), #133 (phantom nodes × 3), #143 (perf dashboard), #154-#155 (Go server parity)
- **Go Ingestor:** ~800 lines, 25 tests ✅ — MQTT ingestion, packet decode, DB writes
- **Go Server:** ~2000 lines, 42 tests ✅ — REST API (35+ endpoints), WebSocket, SQLite polling
- **API Parity:** All endpoints matching Node.js shape, transmission-centric queries, field fixes
- **Performance:** 8s → <100ms on `/api/packets?groupByHash=true`
- **Testing:** Backend coverage 85%+, all tests passing
-
-#### Newt (Frontend)
- **Issues Fixed:** #130 (live map stale dimming), #131 (WS auto-update), #129 (observer comparison), #133 (live page pruning)
- **Frontend Patterns:** WS cache reset (null + invalidateApiCache + re-fetch), detail pane CSS collapse, time-based eviction
- **Observer Comparison:** New `#/compare` route, pure function `comparePacketSets()` exposed on window
- **E2E:** Playwright tests verified all routes, live page behavior, observer analytics
- **Cache Busters:** Bumped in same commit as code changes
-
-#### Bishop (Tester)
- **PR Reviews:** Approved Hicks #6 + Newt #5 + Hudson DB merge plan with gap coverage
- **Gap Coverage:** 14 phantom node tests, 5 WS handler tests added to backend suite
- **E2E Expansion:** 16 → 42 Playwright tests covering 11 routes + new audio lab, channels, observers, traces, perf pages
- **Coverage Validation:** Frontend 42%+, backend 85%+ (both on target)
- **Outcome:** 526 backend tests + 42 E2E tests, all passing ✅
-
-#### Kobayashi (Lead)
- **Root Cause Analysis:** Issue #133 phantom node creation traced to `autoLearnHopNodes()` with `hash_size=1`
- **DB Merge Plan:** 6-phase strategy (pre-flight, backup, merge, deploy, validate, cleanup) with dedup logic
- **Coordination:** Assigned fix owners, reviewed 6 PRs, approved DB merge execution
- **Outcome:** 185MB staging DB → 51,723 transmissions + 1,237,186 observations merged successfully
-
-#### Hudson (DevOps)
- **Database Merge:** Executed production merge (0 data loss, ~2 min downtime, 8,491ms load time)
- **Docker Compose:** Unified volume paths, reconciled manage.sh ↔ docker-compose.yml (no version key, v2 compatible)
- **Staging Setup:** Created `~/meshcore-staging-data/` with old problematic DB for debugging, separate MQTT/HTTP ports
- **CI Pipeline:** Auto-check `docker compose` install, staging auto-deploy with health checks, manual production promotion
- **Infrastructure:** Azure CLI user restoration, Docker group membership, backup retention (7 days)
- **Outcome:** Production stable (860MiB RSS post-merge), staging ready for Go server deployment (port 82)
-
-#### Coordinator (Manual Triage)
- **Issue Closure:** 9 issues closed manually (#134-#142, duplicates + resolved UI polish)
- **New Issue:** #146 filed (unique node count bug — 6502 nodes caused by phantom cleanup audit gap)
- **Outcome:** Backlog cleaned, new issue scoped for Hicks backend audit
-
-#### Ripley (Support)
- **Onboarding:** Joined as Support Engineer mid-session
- **Knowledge Transfer:** Explained staleness thresholds (24h companions/sensors, 72h infrastructure), 7-day active window, health calculations
- **Documentation Reference:** Pointed to `roles.js` as authoritative source for health thresholds
- **Outcome:** Support engineer ready for operational questions and user escalations
-
---
-
-## Orchestration Log Entries Written
-
-All agent logs already present at session end:
- `bishop-2026-03-27.md` (116 lines) — PR reviews, gap coverage, E2E expansion
- `hicks-2026-03-27.md` (102 lines) — 6 fixes, Go ingestor/server, API parity, perf dashboard
- `newt-2026-03-27.md` (56 lines) — 4 frontend fixes, WS patterns, observer comparison
- `kobayashi-2026-03-27.md` (27 lines) — Root cause analysis, DB merge plan, coordination
- `hudson-2026-03-27.md` (117 lines) — DB merge execution, Docker Compose migration, staging setup, CI pipeline
- `ripley-2026-03-27.md` (30 lines) — Support onboarding, health threshold documentation
-
-**Entry Total:** 448 lines of orchestration logs covering 28 issues, 2 Go services, database merge, staging deployment, CI pipeline updates, 42 E2E tests, 19 backend fixes
-
---
-
-## Decisions.md Review
-
-Current decisions.md (342 lines) contains authoritative log of all technical + infrastructure + deployment decisions made during #151-160 session. No archival needed (well under 20KB threshold). Organized by:
-1. User Directives (process decisions)
-2. Technical Fixes (bug fixes with rationale)
-3. Infrastructure & Deployment (ops decisions)
-4. Go Rewrite — API & Storage (architecture decisions)
-5. E2E Playwright Performance (performance optimization strategy)
-
---
-
-## Git Status
-
-Scribe operations:
- ✅ No inbox → decisions.md merges (inbox empty)
- ✅ Orchestration logs written (6 agent logs, 448 lines)
- ✅ Session summary complete
- ✅ No modifications to non-.squad/ files
- ✅ Ready for commit
-
-### .squad/ Directory Structure
-```
-.squad/
-├── agents/
-│   ├── bishop/
-│   ├── hicks/
-│   ├── kobayashi/
-│   ├── newt/
-│   ├── ripley/
-│   ├── hudson/
-│   └── coordinator/
-├── decisions/
-│   ├── decisions.md (342 lines, final)
-│   └── inbox/ (empty)
-├── orchestration-log/
-│   ├── bishop-2026-03-27.md
-│   ├── hicks-2026-03-27.md
-│   ├── newt-2026-03-27.md
-│   ├── kobayashi-2026-03-27.md
-│   ├── hudson-2026-03-27.md
-│   ├── ripley-2026-03-27.md
-│   └── scribe-2026-03-27.md ← NEW
-├── log/ (session artifacts)
-└── agents/scribe/charter.md
-```
-
---
-
-## Session Impact Summary
-
-| Metric | Before | After | Status |
-|--------|--------|-------|--------|
-| **Issues Closed** | Open backlog | 28 closed | ✅ |
-| **Node Count** | 7,308 (phantom) | ~400 (7-day active) | ✅ Fixed |
-| **Heap Usage** | 2.7GB (OOM risk) | 860MB RSS | ✅ Fixed |
-| **Prod DB Size** | 21MB | 206MB (merged) | ✅ Complete |
-| **Transmissions** | 46K | 51,723 | ✅ Complete |
-| **Observations** | ~50K | 1,237,186 | ✅ Complete |
-| **Go MQTT Ingestor** | Non-existent | 25 tests ✅ | ✅ Delivered |
-| **Go Web Server** | Non-existent | 42 tests ✅ | ✅ Delivered |
-| **E2E Test Coverage** | 16 tests | 42 tests | ✅ Expanded |
-| **Backend Test Coverage** | 80%+ | 85%+ | ✅ Improved |
-| **Frontend Test Coverage** | 38%+ | 42%+ | ✅ Improved |
-| **Staging Environment** | Non-existent | Docker Compose + Go-ready | ✅ Delivered |
-| **API Parity** | Node.js only | Go server 100% match | ✅ Complete |
-| **Production Uptime** | Pre-merge | Post-merge stable | ✅ Restored |
-
---
-
-## Outcome
-
-✅ **Session Complete**
-
- All 28 issues closed
- Go MQTT ingestor + web server deployed to staging (ready for Go runtime performance validation)
- Database merge successful (0 data loss, minimal downtime)
- Staging environment operational (Docker Compose, old DB for debugging)
- E2E test coverage expanded (16 → 42 tests)
- Backend test coverage target met (85%+)
- Production restored to healthy state (860MB RSS, no phantom nodes)
- CI pipeline auto-heals (Docker Compose v2 check)
- All agent logs written to orchestration-log/
- Decisions.md current and comprehensive
- Ready for final git commit
-
-**Status:** 🟢 READY FOR COMMIT
+# Scribe Orchestration Log
+
+## 2026-03-27 — Session Summary & Finalization
+
+**Agent:** Scribe (Logging)  
+**Date:** 2026-03-27  
+**Task:** Merge decision inbox, write session orchestration log entry, commit .squad/ changes
+
+### Inbox Merge Status
+
+**Decision Inbox Review:** `.squad/decisions/inbox/` directory scanned — **EMPTY** (no new decisions filed during this session).
+
+**Decisions.md Status:** Current file contains 9 decision categories:
+1. User Directives (6 decisions)
+2. Technical Fixes (4 issues: #126, #133 parts 1-2, #123, #130, #131, #129, #132)
+3. Infrastructure & Deployment (3 decisions: DB merge, Docker volumes, staging setup)
+4. Go Rewrite — API & Storage (4 decisions: MQTT ingestor, web server, API parity, observation RAM optimization)
+5. E2E Playwright Performance (proposed, not yet implemented)
+
+**No merges required** — all work captured in existing decision log categories.
+
+---
+
+## Session Orchestration Summary
+
+**Session Scope:** #151-160 issues + Go rewrite staging + database merge + E2E expansion
+
+### Agent Deliverables (28 issues closed)
+
+#### Hicks (Backend Dev)
+- **Issues Fixed:** #123 (channel hash), #126 (hop prefixes), #133 (phantom nodes × 3), #143 (perf dashboard), #154-#155 (Go server parity)
+- **Go Ingestor:** ~800 lines, 25 tests ✅ — MQTT ingestion, packet decode, DB writes
+- **Go Server:** ~2000 lines, 42 tests ✅ — REST API (35+ endpoints), WebSocket, SQLite polling
+- **API Parity:** All endpoints matching Node.js shape, transmission-centric queries, field fixes
+- **Performance:** 8s → <100ms on `/api/packets?groupByHash=true`
+- **Testing:** Backend coverage 85%+, all tests passing
+
+#### Newt (Frontend)
+- **Issues Fixed:** #130 (live map stale dimming), #131 (WS auto-update), #129 (observer comparison), #133 (live page pruning)
+- **Frontend Patterns:** WS cache reset (null + invalidateApiCache + re-fetch), detail pane CSS collapse, time-based eviction
+- **Observer Comparison:** New `#/compare` route, pure function `comparePacketSets()` exposed on window
+- **E2E:** Playwright tests verified all routes, live page behavior, observer analytics
+- **Cache Busters:** Bumped in same commit as code changes
+
+#### Bishop (Tester)
+- **PR Reviews:** Approved Hicks #6 + Newt #5 + Hudson DB merge plan with gap coverage
+- **Gap Coverage:** 14 phantom node tests, 5 WS handler tests added to backend suite
+- **E2E Expansion:** 16 → 42 Playwright tests covering 11 routes + new audio lab, channels, observers, traces, perf pages
+- **Coverage Validation:** Frontend 42%+, backend 85%+ (both on target)
+- **Outcome:** 526 backend tests + 42 E2E tests, all passing ✅
+
+#### Kobayashi (Lead)
+- **Root Cause Analysis:** Issue #133 phantom node creation traced to `autoLearnHopNodes()` with `hash_size=1`
+- **DB Merge Plan:** 6-phase strategy (pre-flight, backup, merge, deploy, validate, cleanup) with dedup logic
+- **Coordination:** Assigned fix owners, reviewed 6 PRs, approved DB merge execution
+- **Outcome:** 185MB staging DB → 51,723 transmissions + 1,237,186 observations merged successfully
+
+#### Hudson (DevOps)
+- **Database Merge:** Executed production merge (0 data loss, ~2 min downtime, 8,491ms load time)
+- **Docker Compose:** Unified volume paths, reconciled manage.sh ↔ docker-compose.yml (no version key, v2 compatible)
+- **Staging Setup:** Created `~/meshcore-staging-data/` with old problematic DB for debugging, separate MQTT/HTTP ports
+- **CI Pipeline:** Auto-check `docker compose` install, staging auto-deploy with health checks, manual production promotion
+- **Infrastructure:** Azure CLI user restoration, Docker group membership, backup retention (7 days)
+- **Outcome:** Production stable (860MiB RSS post-merge), staging ready for Go server deployment (port 82)
+
+#### Coordinator (Manual Triage)
+- **Issue Closure:** 9 issues closed manually (#134-#142, duplicates + resolved UI polish)
+- **New Issue:** #146 filed (unique node count bug — 6502 nodes caused by phantom cleanup audit gap)
+- **Outcome:** Backlog cleaned, new issue scoped for Hicks backend audit
+
+#### Ripley (Support)
+- **Onboarding:** Joined as Support Engineer mid-session
+- **Knowledge Transfer:** Explained staleness thresholds (24h companions/sensors, 72h infrastructure), 7-day active window, health calculations
+- **Documentation Reference:** Pointed to `roles.js` as authoritative source for health thresholds
+- **Outcome:** Support engineer ready for operational questions and user escalations
+
+---
+
+## Orchestration Log Entries Written
+
+All agent logs already present at session end:
+- `bishop-2026-03-27.md` (116 lines) — PR reviews, gap coverage, E2E expansion
+- `hicks-2026-03-27.md` (102 lines) — 6 fixes, Go ingestor/server, API parity, perf dashboard
+- `newt-2026-03-27.md` (56 lines) — 4 frontend fixes, WS patterns, observer comparison
+- `kobayashi-2026-03-27.md` (27 lines) — Root cause analysis, DB merge plan, coordination
+- `hudson-2026-03-27.md` (117 lines) — DB merge execution, Docker Compose migration, staging setup, CI pipeline
+- `ripley-2026-03-27.md` (30 lines) — Support onboarding, health threshold documentation
+
+**Entry Total:** 448 lines of orchestration logs covering 28 issues, 2 Go services, database merge, staging deployment, CI pipeline updates, 42 E2E tests, 19 backend fixes
+
+---
+
+## Decisions.md Review
+
+Current decisions.md (342 lines) contains authoritative log of all technical + infrastructure + deployment decisions made during #151-160 session. No archival needed (well under 20KB threshold). Organized by:
+1. User Directives (process decisions)
+2. Technical Fixes (bug fixes with rationale)
+3. Infrastructure & Deployment (ops decisions)
+4. Go Rewrite — API & Storage (architecture decisions)
+5. E2E Playwright Performance (performance optimization strategy)
+
+---
+
+## Git Status
+
+Scribe operations:
+- ✅ No inbox → decisions.md merges (inbox empty)
+- ✅ Orchestration logs written (6 agent logs, 448 lines)
+- ✅ Session summary complete
+- ✅ No modifications to non-.squad/ files
+- ✅ Ready for commit
+
+### .squad/ Directory Structure
+```
+.squad/
+├── agents/
+│   ├── bishop/
+│   ├── hicks/
+│   ├── kobayashi/
+│   ├── newt/
+│   ├── ripley/
+│   ├── hudson/
+│   └── coordinator/
+├── decisions/
+│   ├── decisions.md (342 lines, final)
+│   └── inbox/ (empty)
+├── orchestration-log/
+│   ├── bishop-2026-03-27.md
+│   ├── hicks-2026-03-27.md
+│   ├── newt-2026-03-27.md
+│   ├── kobayashi-2026-03-27.md
+│   ├── hudson-2026-03-27.md
+│   ├── ripley-2026-03-27.md
+│   └── scribe-2026-03-27.md ← NEW
+├── log/ (session artifacts)
+└── agents/scribe/charter.md
+```
+
+---
+
+## Session Impact Summary
+
+| Metric | Before | After | Status |
+|--------|--------|-------|--------|
+| **Issues Closed** | Open backlog | 28 closed | ✅ |
+| **Node Count** | 7,308 (phantom) | ~400 (7-day active) | ✅ Fixed |
+| **Heap Usage** | 2.7GB (OOM risk) | 860MB RSS | ✅ Fixed |
+| **Prod DB Size** | 21MB | 206MB (merged) | ✅ Complete |
+| **Transmissions** | 46K | 51,723 | ✅ Complete |
+| **Observations** | ~50K | 1,237,186 | ✅ Complete |
+| **Go MQTT Ingestor** | Non-existent | 25 tests ✅ | ✅ Delivered |
+| **Go Web Server** | Non-existent | 42 tests ✅ | ✅ Delivered |
+| **E2E Test Coverage** | 16 tests | 42 tests | ✅ Expanded |
+| **Backend Test Coverage** | 80%+ | 85%+ | ✅ Improved |
+| **Frontend Test Coverage** | 38%+ | 42%+ | ✅ Improved |
+| **Staging Environment** | Non-existent | Docker Compose + Go-ready | ✅ Delivered |
+| **API Parity** | Node.js only | Go server 100% match | ✅ Complete |
+| **Production Uptime** | Pre-merge | Post-merge stable | ✅ Restored |
+
+---
+
+## Outcome
+
+✅ **Session Complete**
+
+- All 28 issues closed
+- Go MQTT ingestor + web server deployed to staging (ready for Go runtime performance validation)
+- Database merge successful (0 data loss, minimal downtime)
+- Staging environment operational (Docker Compose, old DB for debugging)
+- E2E test coverage expanded (16 → 42 tests)
+- Backend test coverage target met (85%+)
+- Production restored to healthy state (860MB RSS, no phantom nodes)
+- CI pipeline auto-heals (Docker Compose v2 check)
+- All agent logs written to orchestration-log/
+- Decisions.md current and comprehensive
+- Ready for final git commit
+
+**Status:** 🟢 READY FOR COMMIT
@@ -1,60 +1,60 @@
-# Work Routing
-
-How to decide who handles what.
-
-## Routing Table
-
-| Work Type | Route To | Examples |
-|-----------|----------|----------|
-| Architecture, scope, decisions | Kobayashi | Feature planning, trade-offs, scope decisions |
-| Code review, PR review | Kobayashi | Review PRs, check quality, approve/reject |
-| server.js, API routes, Express | Hicks | Add endpoints, fix API bugs, MQTT config |
-| decoder.js, packet parsing | Hicks | Protocol changes, parser bugs, new packet types |
-| packet-store.js, db.js, SQLite | Hicks | Storage bugs, query optimization, schema changes |
-| server-helpers.js, MQTT, WebSocket | Hicks | Helper functions, real-time data flow |
-| Performance optimization | Hicks | Caching, O(n) improvements, response times |
-| Docker, deployment, manage.sh | Hicks | Container config, deploy scripts |
-| MeshCore protocol/firmware | Hicks | Read firmware source, verify protocol behavior |
-| public/*.js (all frontend modules) | Newt | UI features, interactions, SPA routing |
-| Leaflet maps, live visualization | Newt | Map markers, VCR playback, animations |
-| CSS, theming, customize.js | Newt | Styles, CSS variables, theme customizer |
-| packet-filter.js (filter engine) | Newt | Filter syntax, parser, Wireshark-style queries |
-| index.html, cache busters | Newt | Script tags, version bumps |
-| Unit tests, test-*.js | Bishop | Write/fix tests, coverage improvements |
-| Playwright E2E tests | Bishop | Browser tests, UI verification |
-| Coverage, CI pipeline | Bishop | Coverage targets, CI config |
-| CI/CD pipeline, .github/workflows | Hudson | Pipeline config, step optimization, CI debugging |
-| Docker, Dockerfile, docker/ | Hudson | Container config, build optimization |
-| manage.sh, deployment scripts | Hudson | Deploy scripts, server management |
-| scripts/, coverage tooling | Hudson | Build scripts, coverage collector optimization |
-| Azure, VM, infrastructure | Hudson | az CLI, SSH, server provisioning, monitoring |
-| Production debugging, DB ops | Hudson | SQLite recovery, WAL issues, process diagnostics |
-| User questions, "why does X..." | Ripley | Community support, UI behavior explanations |
-| Bug report triage from users | Ripley | Analyze reports, reproduce, route to dev |
-| GitHub issue comments (support) | Ripley | Explain behavior, suggest workarounds |
-| README, docs/ | Kobayashi | Documentation updates |
-| Session logging | Scribe | Automatic — never needs routing |
-
-## Issue Routing
-
-| Label | Action | Who |
-|-------|--------|-----|
-| `squad` | Triage: analyze issue, assign `squad:{member}` label | Lead |
-| `squad:{name}` | Pick up issue and complete the work | Named member |
-
-### How Issue Assignment Works
-
-1. When a GitHub issue gets the `squad` label, the **Lead** triages it — analyzing content, assigning the right `squad:{member}` label, and commenting with triage notes.
-2. When a `squad:{member}` label is applied, that member picks up the issue in their next session.
-3. Members can reassign by removing their label and adding another member's label.
-4. The `squad` label is the "inbox" — untriaged issues waiting for Lead review.
-
-## Rules
-
-1. **Eager by default** — spawn all agents who could usefully start work, including anticipatory downstream work.
-2. **Scribe always runs** after substantial work, always as `mode: "background"`. Never blocks.
-3. **Quick facts → coordinator answers directly.** Don't spawn an agent for "what port does the server run on?"
-4. **When two agents could handle it**, pick the one whose domain is the primary concern.
-5. **"Team, ..." → fan-out.** Spawn all relevant agents in parallel as `mode: "background"`.
-6. **Anticipate downstream work.** If a feature is being built, spawn the tester to write test cases from requirements simultaneously.
-7. **Issue-labeled work** — when a `squad:{member}` label is applied to an issue, route to that member. The Lead handles all `squad` (base label) triage.
+# Work Routing
+
+How to decide who handles what.
+
+## Routing Table
+
+| Work Type | Route To | Examples |
+|-----------|----------|----------|
+| Architecture, scope, decisions | Kobayashi | Feature planning, trade-offs, scope decisions |
+| Code review, PR review | Kobayashi | Review PRs, check quality, approve/reject |
+| server.js, API routes, Express | Hicks | Add endpoints, fix API bugs, MQTT config |
+| decoder.js, packet parsing | Hicks | Protocol changes, parser bugs, new packet types |
+| packet-store.js, db.js, SQLite | Hicks | Storage bugs, query optimization, schema changes |
+| server-helpers.js, MQTT, WebSocket | Hicks | Helper functions, real-time data flow |
+| Performance optimization | Hicks | Caching, O(n) improvements, response times |
+| Docker, deployment, manage.sh | Hicks | Container config, deploy scripts |
+| MeshCore protocol/firmware | Hicks | Read firmware source, verify protocol behavior |
+| public/*.js (all frontend modules) | Newt | UI features, interactions, SPA routing |
+| Leaflet maps, live visualization | Newt | Map markers, VCR playback, animations |
+| CSS, theming, customize.js | Newt | Styles, CSS variables, theme customizer |
+| packet-filter.js (filter engine) | Newt | Filter syntax, parser, Wireshark-style queries |
+| index.html, cache busters | Newt | Script tags, version bumps |
+| Unit tests, test-*.js | Bishop | Write/fix tests, coverage improvements |
+| Playwright E2E tests | Bishop | Browser tests, UI verification |
+| Coverage, CI pipeline | Bishop | Coverage targets, CI config |
+| CI/CD pipeline, .github/workflows | Hudson | Pipeline config, step optimization, CI debugging |
+| Docker, Dockerfile, docker/ | Hudson | Container config, build optimization |
+| manage.sh, deployment scripts | Hudson | Deploy scripts, server management |
+| scripts/, coverage tooling | Hudson | Build scripts, coverage collector optimization |
+| Azure, VM, infrastructure | Hudson | az CLI, SSH, server provisioning, monitoring |
+| Production debugging, DB ops | Hudson | SQLite recovery, WAL issues, process diagnostics |
+| User questions, "why does X..." | Ripley | Community support, UI behavior explanations |
+| Bug report triage from users | Ripley | Analyze reports, reproduce, route to dev |
+| GitHub issue comments (support) | Ripley | Explain behavior, suggest workarounds |
+| README, docs/ | Kobayashi | Documentation updates |
+| Session logging | Scribe | Automatic — never needs routing |
+
+## Issue Routing
+
+| Label | Action | Who |
+|-------|--------|-----|
+| `squad` | Triage: analyze issue, assign `squad:{member}` label | Lead |
+| `squad:{name}` | Pick up issue and complete the work | Named member |
+
+### How Issue Assignment Works
+
+1. When a GitHub issue gets the `squad` label, the **Lead** triages it — analyzing content, assigning the right `squad:{member}` label, and commenting with triage notes.
+2. When a `squad:{member}` label is applied, that member picks up the issue in their next session.
+3. Members can reassign by removing their label and adding another member's label.
+4. The `squad` label is the "inbox" — untriaged issues waiting for Lead review.
+
+## Rules
+
+1. **Eager by default** — spawn all agents who could usefully start work, including anticipatory downstream work.
+2. **Scribe always runs** after substantial work, always as `mode: "background"`. Never blocks.
+3. **Quick facts → coordinator answers directly.** Don't spawn an agent for "what port does the server run on?"
+4. **When two agents could handle it**, pick the one whose domain is the primary concern.
+5. **"Team, ..." → fan-out.** Spawn all relevant agents in parallel as `mode: "background"`.
+6. **Anticipate downstream work.** If a feature is being built, spawn the tester to write test cases from requirements simultaneously.
+7. **Issue-labeled work** — when a `squad:{member}` label is applied to an issue, route to that member. The Lead handles all `squad` (base label) triage.
@@ -1,4 +1,4 @@
-{
-  "universe_usage_history": [],
-  "assignment_cast_snapshots": {}
-}
+{
+  "universe_usage_history": [],
+  "assignment_cast_snapshots": {}
+}
@@ -1,37 +1,37 @@
-{
-  "casting_policy_version": "1.1",
-  "allowlist_universes": [
-    "The Usual Suspects",
-    "Reservoir Dogs",
-    "Alien",
-    "Ocean's Eleven",
-    "Arrested Development",
-    "Star Wars",
-    "The Matrix",
-    "Firefly",
-    "The Goonies",
-    "The Simpsons",
-    "Breaking Bad",
-    "Lost",
-    "Marvel Cinematic Universe",
-    "DC Universe",
-    "Futurama"
-  ],
-  "universe_capacity": {
-    "The Usual Suspects": 6,
-    "Reservoir Dogs": 8,
-    "Alien": 8,
-    "Ocean's Eleven": 14,
-    "Arrested Development": 15,
-    "Star Wars": 12,
-    "The Matrix": 10,
-    "Firefly": 10,
-    "The Goonies": 8,
-    "The Simpsons": 20,
-    "Breaking Bad": 12,
-    "Lost": 18,
-    "Marvel Cinematic Universe": 25,
-    "DC Universe": 18,
-    "Futurama": 12
-  }
-}
+{
+  "casting_policy_version": "1.1",
+  "allowlist_universes": [
+    "The Usual Suspects",
+    "Reservoir Dogs",
+    "Alien",
+    "Ocean's Eleven",
+    "Arrested Development",
+    "Star Wars",
+    "The Matrix",
+    "Firefly",
+    "The Goonies",
+    "The Simpsons",
+    "Breaking Bad",
+    "Lost",
+    "Marvel Cinematic Universe",
+    "DC Universe",
+    "Futurama"
+  ],
+  "universe_capacity": {
+    "The Usual Suspects": 6,
+    "Reservoir Dogs": 8,
+    "Alien": 8,
+    "Ocean's Eleven": 14,
+    "Arrested Development": 15,
+    "Star Wars": 12,
+    "The Matrix": 10,
+    "Firefly": 10,
+    "The Goonies": 8,
+    "The Simpsons": 20,
+    "Breaking Bad": 12,
+    "Lost": 18,
+    "Marvel Cinematic Universe": 25,
+    "DC Universe": 18,
+    "Futurama": 12
+  }
+}
@@ -1,104 +1,104 @@
-# Casting Reference
-
-On-demand reference for Squad's casting system. Loaded during Init Mode or when adding team members.
-
-## Universe Table
-
-| Universe | Capacity | Shape Tags | Resonance Signals |
-|---|---|---|---|
-| The Usual Suspects | 6 | small, noir, ensemble | crime, heist, mystery, deception |
-| Reservoir Dogs | 8 | small, noir, ensemble | crime, heist, tension, loyalty |
-| Alien | 8 | small, sci-fi, survival | space, isolation, threat, engineering |
-| Ocean's Eleven | 14 | medium, heist, ensemble | planning, coordination, roles, charm |
-| Arrested Development | 15 | medium, comedy, ensemble | dysfunction, business, family, satire |
-| Star Wars | 12 | medium, sci-fi, epic | conflict, mentorship, legacy, rebellion |
-| The Matrix | 10 | medium, sci-fi, cyberpunk | systems, reality, hacking, philosophy |
-| Firefly | 10 | medium, sci-fi, western | frontier, crew, independence, smuggling |
-| The Goonies | 8 | small, adventure, ensemble | exploration, treasure, kids, teamwork |
-| The Simpsons | 20 | large, comedy, ensemble | satire, community, family, absurdity |
-| Breaking Bad | 12 | medium, drama, tension | chemistry, transformation, consequence, power |
-| Lost | 18 | large, mystery, ensemble | survival, mystery, groups, leadership |
-| Marvel Cinematic Universe | 25 | large, action, ensemble | heroism, teamwork, powers, scale |
-| DC Universe | 18 | large, action, ensemble | justice, duality, powers, mythology |
-| Futurama | 12 | medium, sci-fi, comedy | future, robots, space, absurdity |
-
-**Total: 15 universes** — capacity range 6–25.
-
-## Selection Algorithm
-
-Universe selection is deterministic. Score each universe and pick the highest:
-
-```
-score = size_fit + shape_fit + resonance_fit + LRU
-```
-
-| Factor | Description |
-|---|---|
-| `size_fit` | How well the universe capacity matches the team size. Prefer universes where capacity ≥ agent_count with minimal waste. |
-| `shape_fit` | Match universe shape tags against the assignment shape derived from the project description. |
-| `resonance_fit` | Match universe resonance signals against session and repo context signals. |
-| `LRU` | Least-recently-used bonus — prefer universes not used in recent assignments (from `history.json`). |
-
-Same inputs → same choice (unless LRU changes between assignments).
-
-## Casting State File Schemas
-
-### policy.json
-
-Source template: `.squad/templates/casting-policy.json`
-Runtime location: `.squad/casting/policy.json`
-
-```json
-{
-  "casting_policy_version": "1.1",
-  "allowlist_universes": ["Universe Name", "..."],
-  "universe_capacity": {
-    "Universe Name": 10
-  }
-}
-```
-
-### registry.json
-
-Source template: `.squad/templates/casting-registry.json`
-Runtime location: `.squad/casting/registry.json`
-
-```json
-{
-  "agents": {
-    "agent-role-id": {
-      "persistent_name": "CharacterName",
-      "universe": "Universe Name",
-      "created_at": "ISO-8601",
-      "legacy_named": false,
-      "status": "active"
-    }
-  }
-}
-```
-
-### history.json
-
-Source template: `.squad/templates/casting-history.json`
-Runtime location: `.squad/casting/history.json`
-
-```json
-{
-  "universe_usage_history": [
-    {
-      "universe": "Universe Name",
-      "assignment_id": "unique-id",
-      "used_at": "ISO-8601"
-    }
-  ],
-  "assignment_cast_snapshots": {
-    "assignment-id": {
-      "universe": "Universe Name",
-      "agents": {
-        "role-id": "CharacterName"
-      },
-      "created_at": "ISO-8601"
-    }
-  }
-}
-```
+# Casting Reference
+
+On-demand reference for Squad's casting system. Loaded during Init Mode or when adding team members.
+
+## Universe Table
+
+| Universe | Capacity | Shape Tags | Resonance Signals |
+|---|---|---|---|
+| The Usual Suspects | 6 | small, noir, ensemble | crime, heist, mystery, deception |
+| Reservoir Dogs | 8 | small, noir, ensemble | crime, heist, tension, loyalty |
+| Alien | 8 | small, sci-fi, survival | space, isolation, threat, engineering |
+| Ocean's Eleven | 14 | medium, heist, ensemble | planning, coordination, roles, charm |
+| Arrested Development | 15 | medium, comedy, ensemble | dysfunction, business, family, satire |
+| Star Wars | 12 | medium, sci-fi, epic | conflict, mentorship, legacy, rebellion |
+| The Matrix | 10 | medium, sci-fi, cyberpunk | systems, reality, hacking, philosophy |
+| Firefly | 10 | medium, sci-fi, western | frontier, crew, independence, smuggling |
+| The Goonies | 8 | small, adventure, ensemble | exploration, treasure, kids, teamwork |
+| The Simpsons | 20 | large, comedy, ensemble | satire, community, family, absurdity |
+| Breaking Bad | 12 | medium, drama, tension | chemistry, transformation, consequence, power |
+| Lost | 18 | large, mystery, ensemble | survival, mystery, groups, leadership |
+| Marvel Cinematic Universe | 25 | large, action, ensemble | heroism, teamwork, powers, scale |
+| DC Universe | 18 | large, action, ensemble | justice, duality, powers, mythology |
+| Futurama | 12 | medium, sci-fi, comedy | future, robots, space, absurdity |
+
+**Total: 15 universes** — capacity range 6–25.
+
+## Selection Algorithm
+
+Universe selection is deterministic. Score each universe and pick the highest:
+
+```
+score = size_fit + shape_fit + resonance_fit + LRU
+```
+
+| Factor | Description |
+|---|---|
+| `size_fit` | How well the universe capacity matches the team size. Prefer universes where capacity ≥ agent_count with minimal waste. |
+| `shape_fit` | Match universe shape tags against the assignment shape derived from the project description. |
+| `resonance_fit` | Match universe resonance signals against session and repo context signals. |
+| `LRU` | Least-recently-used bonus — prefer universes not used in recent assignments (from `history.json`). |
+
+Same inputs → same choice (unless LRU changes between assignments).
+
+## Casting State File Schemas
+
+### policy.json
+
+Source template: `.squad/templates/casting-policy.json`
+Runtime location: `.squad/casting/policy.json`
+
+```json
+{
+  "casting_policy_version": "1.1",
+  "allowlist_universes": ["Universe Name", "..."],
+  "universe_capacity": {
+    "Universe Name": 10
+  }
+}
+```
+
+### registry.json
+
+Source template: `.squad/templates/casting-registry.json`
+Runtime location: `.squad/casting/registry.json`
+
+```json
+{
+  "agents": {
+    "agent-role-id": {
+      "persistent_name": "CharacterName",
+      "universe": "Universe Name",
+      "created_at": "ISO-8601",
+      "legacy_named": false,
+      "status": "active"
+    }
+  }
+}
+```
+
+### history.json
+
+Source template: `.squad/templates/casting-history.json`
+Runtime location: `.squad/casting/history.json`
+
+```json
+{
+  "universe_usage_history": [
+    {
+      "universe": "Universe Name",
+      "assignment_id": "unique-id",
+      "used_at": "ISO-8601"
+    }
+  ],
+  "assignment_cast_snapshots": {
+    "assignment-id": {
+      "universe": "Universe Name",
+      "agents": {
+        "role-id": "CharacterName"
+      },
+      "created_at": "ISO-8601"
+    }
+  }
+}
+```
@@ -1,3 +1,3 @@
-{
-  "agents": {}
-}
+{
+  "agents": {}
+}
@@ -1,10 +1,10 @@
-[
-    "Fry",
-    "Leela",
-    "Bender",
-    "Farnsworth",
-    "Zoidberg",
-    "Amy",
-    "Zapp",
-    "Kif"
+[
+    "Fry",
+    "Leela",
+    "Bender",
+    "Farnsworth",
+    "Zoidberg",
+    "Amy",
+    "Zapp",
+    "Kif"
 ]
@@ -1,41 +1,41 @@
-# Ceremonies
-
-> Team meetings that happen before or after work. Each squad configures their own.
-
-## Design Review
-
-| Field | Value |
-|-------|-------|
-| **Trigger** | auto |
-| **When** | before |
-| **Condition** | multi-agent task involving 2+ agents modifying shared systems |
-| **Facilitator** | lead |
-| **Participants** | all-relevant |
-| **Time budget** | focused |
-| **Enabled** | ✅ yes |
-
-**Agenda:**
-1. Review the task and requirements
-2. Agree on interfaces and contracts between components
-3. Identify risks and edge cases
-4. Assign action items
-
---
-
-## Retrospective
-
-| Field | Value |
-|-------|-------|
-| **Trigger** | auto |
-| **When** | after |
-| **Condition** | build failure, test failure, or reviewer rejection |
-| **Facilitator** | lead |
-| **Participants** | all-involved |
-| **Time budget** | focused |
-| **Enabled** | ✅ yes |
-
-**Agenda:**
-1. What happened? (facts only)
-2. Root cause analysis
-3. What should change?
-4. Action items for next iteration
+# Ceremonies
+
+> Team meetings that happen before or after work. Each squad configures their own.
+
+## Design Review
+
+| Field | Value |
+|-------|-------|
+| **Trigger** | auto |
+| **When** | before |
+| **Condition** | multi-agent task involving 2+ agents modifying shared systems |
+| **Facilitator** | lead |
+| **Participants** | all-relevant |
+| **Time budget** | focused |
+| **Enabled** | ✅ yes |
+
+**Agenda:**
+1. Review the task and requirements
+2. Agree on interfaces and contracts between components
+3. Identify risks and edge cases
+4. Assign action items
+
+---
+
+## Retrospective
+
+| Field | Value |
+|-------|-------|
+| **Trigger** | auto |
+| **When** | after |
+| **Condition** | build failure, test failure, or reviewer rejection |
+| **Facilitator** | lead |
+| **Participants** | all-involved |
+| **Time budget** | focused |
+| **Enabled** | ✅ yes |
+
+**Agenda:**
+1. What happened? (facts only)
+2. Root cause analysis
+3. What should change?
+4. Action items for next iteration
@@ -1,53 +1,53 @@
-# {Name} — {Role}
-
-> {One-line personality statement — what makes this person tick}
-
-## Identity
-
- **Name:** {Name}
- **Role:** {Role title}
- **Expertise:** {2-3 specific skills relevant to the project}
- **Style:** {How they communicate — direct? thorough? opinionated?}
-
-## What I Own
-
- {Area of responsibility 1}
- {Area of responsibility 2}
- {Area of responsibility 3}
-
-## How I Work
-
- {Key approach or principle 1}
- {Key approach or principle 2}
- {Pattern or convention I follow}
-
-## Boundaries
-
-**I handle:** {types of work this agent does}
-
-**I don't handle:** {types of work that belong to other team members}
-
-**When I'm unsure:** I say so and suggest who might know.
-
-**If I review others' work:** On rejection, I may require a different agent to revise (not the original author) or request a new specialist be spawned. The Coordinator enforces this.
-
-## Model
-
- **Preferred:** auto
- **Rationale:** Coordinator selects the best model based on task type — cost first unless writing code
- **Fallback:** Standard chain — the coordinator handles fallback automatically
-
-## Collaboration
-
-Before starting work, run `git rev-parse --show-toplevel` to find the repo root, or use the `TEAM ROOT` provided in the spawn prompt. All `.squad/` paths must be resolved relative to this root — do not assume CWD is the repo root (you may be in a worktree or subdirectory).
-
-Before starting work, read `.squad/decisions.md` for team decisions that affect me.
-After making a decision others should know, write it to `.squad/decisions/inbox/{my-name}-{brief-slug}.md` — the Scribe will merge it.
-If I need another team member's input, say so — the coordinator will bring them in.
-
-## Voice
-
-{1-2 sentences describing personality. Not generic — specific. This agent has OPINIONS.
-They have preferences. They push back. They have a style that's distinctly theirs.
-Example: "Opinionated about test coverage. Will push back if tests are skipped.
-Prefers integration tests over mocks. Thinks 80% coverage is the floor, not the ceiling."}
+# {Name} — {Role}
+
+> {One-line personality statement — what makes this person tick}
+
+## Identity
+
+- **Name:** {Name}
+- **Role:** {Role title}
+- **Expertise:** {2-3 specific skills relevant to the project}
+- **Style:** {How they communicate — direct? thorough? opinionated?}
+
+## What I Own
+
+- {Area of responsibility 1}
+- {Area of responsibility 2}
+- {Area of responsibility 3}
+
+## How I Work
				`@@ -0,0 +1 @@`
				`{"schemaVersion":1,"label":"backend coverage","message":"87.79%","color":"brightgreen"}`
				`@@ -0,0 +1 @@`
				`{"schemaVersion":1,"label":"backend tests","message":"998 passed","color":"brightgreen"}`
				`@@ -0,0 +1 @@`
				`{"schemaVersion":1,"label":"coverage","message":"76%","color":"yellow"}`
				`@@ -1 +0,0 @@`
				`{"schemaVersion":1,"label":"e2e tests","message":"93 passed","color":"brightgreen"}`
				`@@ -1 +0,0 @@`
				`{"schemaVersion":1,"label":"go ingestor coverage","message":"70.2%","color":"yellow"}`
				`@@ -1 +0,0 @@`
				`{"schemaVersion":1,"label":"go server coverage","message":"85.4%","color":"green"}`
				`@@ -0,0 +1 @@`
				`{"schemaVersion":1,"label":"tests","message":"844/844 passed","color":"brightgreen"}`