Merge pull request #282 from kerberos-io/feature/add-bump-release-workflow

feature/add-bump-release-workflow

.github/workflows/pr-description.yaml

@@ -2,25 +2,16 @@ name: Autofill PR description
 
 on: pull_request
 
-env:
-  ORGANIZATION: uugai
-  PROJECT: ${{ github.event.repository.name }}
-  PR_NUMBER: ${{ github.event.number }}
-  
 jobs:
   openai-pr-description:
-    runs-on: ubuntu-22.04
-
-    steps:
-      - uses: actions/checkout@v4
-      - name: Autofill PR description if empty using OpenAI
-        uses: cedricve/azureopenai-pr-description@master
-        with:
-          github_token: ${{ secrets.TOKEN }}
-          openai_api_key: ${{ secrets.OPENAI_API_KEY }}
-          azure_openai_api_key: ${{ secrets.AZURE_OPENAI_API_KEY }}
-          azure_openai_endpoint: ${{ secrets.AZURE_OPENAI_ENDPOINT }}
-          azure_openai_version: ${{ secrets.AZURE_OPENAI_VERSION }}
-          openai_model: ${{ secrets.OPENAI_MODEL }}
-          pull_request_url: https://pr${{ env.PR_NUMBER }}.api.kerberos.lol
-          overwrite_description: true
+    uses: uug-ai/workflows/.github/workflows/pr-description.yml@main
+    with:
+      pr_number: ${{ github.event.number }}
+      pull_request_url: ""
+      overwrite_description: true
+    secrets:
+      TOKEN: ${{ secrets.TOKEN }}
+      AZURE_OPENAI_API_KEY: ${{ secrets.AZURE_OPENAI_API_KEY }}
+      OPENAI_MODEL: ${{ secrets.OPENAI_MODEL }}
+      AZURE_OPENAI_ENDPOINT: ${{ secrets.AZURE_OPENAI_ENDPOINT }}
+      AZURE_OPENAI_VERSION: ${{ secrets.AZURE_OPENAI_VERSION }}

.github/workflows/release-bump.yml

@@ -0,0 +1,68 @@
+name: Bump release
+
+# Manually "promote" the agent to a new release.
+# Pick which part of the semantic version to bump, this workflow computes the
+# next vMAJOR.MINOR.PATCH tag, pushes it and triggers the existing
+# release-create pipeline to build and publish the images and GitHub release.
+on:
+  workflow_dispatch:
+    inputs:
+      bump:
+        description: "Which part of the version to bump"
+        required: true
+        default: patch
+        type: choice
+        options:
+          - major
+          - minor
+          - patch
+
+permissions:
+  contents: write
+  actions: write
+
+jobs:
+  bump-release:
+    runs-on: ubuntu-24.04
+    steps:
+      - name: Checkout
+        uses: actions/checkout@v4
+        with:
+          fetch-depth: 0
+          fetch-tags: true
+
+      - name: Compute next version
+        id: version
+        run: |
+          set -euo pipefail
+          latest=$(git tag --list 'v[0-9]*.[0-9]*.[0-9]*' --sort=-v:refname | head -n1)
+          latest=${latest:-v0.0.0}
+          echo "Latest tag: $latest"
+          version=${latest#v}
+          IFS='.' read -r major minor patch <<< "$version"
+          case "${{ github.event.inputs.bump }}" in
+            major) major=$((major + 1)); minor=0; patch=0 ;;
+            minor) minor=$((minor + 1)); patch=0 ;;
+            patch) patch=$((patch + 1)) ;;
+          esac
+          next="v${major}.${minor}.${patch}"
+          echo "Next tag: $next"
+          echo "tag=$next" >> "$GITHUB_OUTPUT"
+
+      - name: Create and push tag
+        run: |
+          set -euo pipefail
+          git config user.name "github-actions[bot]"
+          git config user.email "github-actions[bot]@users.noreply.github.com"
+          git tag -a "${{ steps.version.outputs.tag }}" -m "Release ${{ steps.version.outputs.tag }}"
+          git push origin "${{ steps.version.outputs.tag }}"
+
+      # A tag pushed with the default GITHUB_TOKEN does not trigger other
+      # workflows, so invoke the release pipeline explicitly for the new tag.
+      - name: Trigger release pipeline
+        env:
+          GH_TOKEN: ${{ secrets.GITHUB_TOKEN }}
+        run: |
+          gh workflow run release-create.yml \
+            --ref "${{ steps.version.outputs.tag }}" \
+            -f tag="${{ steps.version.outputs.tag }}"

machinery/src/capture/gortsplib.go

@@ -95,6 +95,129 @@ type Golibrtsp struct {
 	keyframeBufferSize       int
 	keyframeBufferIndex      int
 	keyframeMutex            sync.Mutex
+
+	// Stream health instrumentation. Used to pinpoint the root cause behind
+	// "RTP packets lost" + watchdog restarts by separating downstream
+	// back-pressure from upstream network/camera stalls.
+	health      *streamHealth
+	streamLabel string
+}
+
+// streamHealth instruments the RTSP read path. gortsplib delivers every RTP
+// packet on a single read goroutine; queue.WritePacket() is synchronous, so if
+// a downstream consumer (recording, muxing, WebRTC) is slow or the process is
+// CPU-starved, WritePacket() blocks, the TCP socket is not drained, and the
+// camera advances RTP sequence numbers -> "RTP packets lost". This type makes
+// the two failure modes distinguishable:
+//   - large writeMax / writeAvg  => downstream back-pressure (our side).
+//   - large gapMax with fast writes => upstream network / camera stall.
+type streamHealth struct {
+	mu          sync.Mutex
+	windowStart time.Time
+	lastPacket  time.Time
+	frames      int64
+	writeSum    time.Duration
+	writeMax    time.Duration
+	gapMax      time.Duration
+	lost        uint64
+	decodeErrs  int64
+}
+
+const (
+	streamHealthWindow    = 10 * time.Second
+	streamHealthWriteWarn = 150 * time.Millisecond
+	streamHealthGapWarn   = 1500 * time.Millisecond
+)
+
+func newStreamHealth() *streamHealth {
+	now := time.Now()
+	return &streamHealth{windowStart: now, lastPacket: now}
+}
+
+// observePacket records one processed video frame: the wall-clock gap since the
+// previous frame (arrival cadence) and how long WritePacket() blocked
+// (back-pressure). It emits an immediate warning when either side stalls and a
+// periodic summary every streamHealthWindow.
+func (h *streamHealth) observePacket(streamType string, writeDur time.Duration) {
+	if h == nil {
+		return
+	}
+	h.mu.Lock()
+	defer h.mu.Unlock()
+	now := time.Now()
+	var gap time.Duration
+	if h.frames == 0 {
+		// First frame: initialize timing to avoid counting RTSP setup time as a stall.
+		h.windowStart = now
+		h.lastPacket = now
+		gap = 0
+	} else {
+		gap = now.Sub(h.lastPacket)
+		h.lastPacket = now
+	}
+	h.frames++
+	h.writeSum += writeDur
+	if writeDur > h.writeMax {
+		h.writeMax = writeDur
+	}
+	if gap > h.gapMax {
+		h.gapMax = gap
+	}
+	if writeDur >= streamHealthWriteWarn {
+		log.Log.Warning(fmt.Sprintf(
+			"capture.golibrtsp.health(%s): WritePacket blocked %dms — downstream back-pressure / CPU starvation",
+			streamType, writeDur.Milliseconds()))
+	}
+	if gap >= streamHealthGapWarn {
+		log.Log.Warning(fmt.Sprintf(
+			"capture.golibrtsp.health(%s): %dms since previous frame — upstream network / camera stall",
+			streamType, gap.Milliseconds()))
+	}
+	if now.Sub(h.windowStart) >= streamHealthWindow {
+		elapsed := now.Sub(h.windowStart).Seconds()
+		var avgWriteMs float64
+		if h.frames > 0 {
+			avgWriteMs = float64(h.writeSum.Milliseconds()) / float64(h.frames)
+		}
+		log.Log.Info(fmt.Sprintf(
+			"capture.golibrtsp.health(%s): %.0fs window — frames=%d (%.1f/s) writeAvg=%.1fms writeMax=%dms gapMax=%dms lost=%d decodeErrs=%d",
+			streamType, elapsed, h.frames, float64(h.frames)/elapsed, avgWriteMs,
+			h.writeMax.Milliseconds(), h.gapMax.Milliseconds(), h.lost, h.decodeErrs))
+		h.windowStart = now
+		h.frames = 0
+		h.writeSum = 0
+		h.writeMax = 0
+		h.gapMax = 0
+		h.lost = 0
+		h.decodeErrs = 0
+	}
+}
+
+// observeLost is invoked by gortsplib when RTP sequence numbers skip. On a TCP
+// transport this means the sender (camera) dropped packets because we were not
+// reading fast enough, not loss on the wire.
+func (h *streamHealth) observeLost(streamType string, lost uint64) {
+	if h == nil {
+		return
+	}
+	h.mu.Lock()
+	h.lost += lost
+	h.mu.Unlock()
+	log.Log.Warning(fmt.Sprintf(
+		"capture.golibrtsp.health(%s): %d RTP packet(s) lost — sender-side gap (receiver not draining TCP fast enough)",
+		streamType, lost))
+}
+
+// observeDecodeError is invoked by gortsplib on incomplete/invalid access units,
+// which are a downstream symptom of the loss reported by observeLost.
+func (h *streamHealth) observeDecodeError(streamType string, err error) {
+	if h == nil {
+		return
+	}
+	h.mu.Lock()
+	h.decodeErrs++
+	h.mu.Unlock()
+	log.Log.Debug(fmt.Sprintf("capture.golibrtsp.health(%s): decode error: %s", streamType, err.Error()))
 }
 
 // fpsTracker holds per-stream state for PTS-based FPS calculation.
@@ -195,9 +318,20 @@ func (g *Golibrtsp) Connect(ctx context.Context, ctxOtel context.Context) (err e
 	defer span.End()
 
 	transport := gortsplib.TransportTCP
+	g.health = newStreamHealth()
 	g.Client = gortsplib.Client{
 		RequestBackChannels: false,
 		Transport:           &transport,
+		// Route gortsplib's packet-loss / decode-error reporting through our
+		// structured logger with stream context (replaces its plain stdout
+		// logging). These hooks are what let us tell whether the camera is
+		// dropping packets because we can't drain the socket fast enough.
+		OnPacketsLost: func(lost uint64) {
+			g.health.observeLost(g.streamLabel, lost)
+		},
+		OnDecodeError: func(err error) {
+			g.health.observeDecodeError(g.streamLabel, err)
+		},
 	}
 
 	// parse URL
@@ -550,6 +684,12 @@ func compositionOffsetMs(ext dtsExtractor, au [][]byte, pts int64, clockRate int
 func (g *Golibrtsp) Start(ctx context.Context, streamType string, queue *packets.Queue, configuration *models.Configuration, communication *models.Communication) (err error) {
 	log.Log.Debug("capture.golibrtsp.Start(): started")
 
+	// Label this client's loss/decode/health logging with the stream type.
+	g.streamLabel = streamType
+	if g.health == nil {
+		g.health = newStreamHealth()
+	}
+
 	// called when a MULAW audio RTP packet arrives
 	if g.AudioG711Media != nil && g.AudioG711Forma != nil {
 		g.Client.OnPacketRTP(g.AudioG711Media, g.AudioG711Forma, func(rtppkt *rtp.Packet) {
@@ -821,7 +961,11 @@ func (g *Golibrtsp) Start(ctx context.Context, streamType string, queue *packets
 					pkt.Data = append(annexbNALUStartCode(), pkt.Data...)
 				}
 
+				writeStart := time.Now()
 				queue.WritePacket(pkt)
+				// Records WritePacket() blocking time and frame arrival cadence so
+				// we can tell back-pressure from a network/camera stall.
+				g.health.observePacket(streamType, time.Since(writeStart))
 
 				// This will check if we need to stop the thread,
 				// because of a reconfiguration.
@@ -983,7 +1127,11 @@ func (g *Golibrtsp) Start(ctx context.Context, streamType string, queue *packets
 					}
 				}
 
+				writeStart := time.Now()
 				queue.WritePacket(pkt)
+				// Records WritePacket() blocking time and frame arrival cadence so
+				// we can tell back-pressure from a network/camera stall.
+				g.health.observePacket(streamType, time.Since(writeStart))
 
 				// This will check if we need to stop the thread,
 				// because of a reconfiguration.

machinery/src/components/Kerberos.go

@@ -2,6 +2,7 @@ package components
 
 import (
 	"context"
+	"fmt"
 	"os"
 	"strconv"
 	"sync/atomic"
@@ -446,6 +447,37 @@ func RunAgent(configDirectory string, configuration *models.Configuration, commu
 	return status
 }
 
+// packetAgeString returns a human readable age (e.g. "12s") since the last
+// packet timestamp stored in the given atomic.Value, or "unknown" when no
+// packet has been received yet. Used to add context to watchdog restart logs.
+func packetAgeString(timer *atomic.Value) string {
+	if timer == nil {
+		return "unknown"
+	}
+
+	// atomic.Value panics on Load() if it was never initialized via Store().
+	var v any
+	func() {
+		defer func() {
+			if recover() != nil {
+				v = nil
+			}
+		}()
+		v = timer.Load()
+	}()
+
+	last, ok := v.(int64)
+	if !ok || last == 0 {
+		return "unknown"
+	}
+
+	age := time.Now().Unix() - last
+	if age < 0 {
+		age = 0
+	}
+	return strconv.FormatInt(age, 10) + "s"
+}
+
 // ControlAgent will check if the camera is still connected, if not it will restart the agent.
 // In the other thread we are keeping track of the number of packets received, and particular the keyframe packets.
 // Once we are not receiving any packets anymore, we will restart the agent.
@@ -480,7 +512,8 @@ func ControlAgent(communication *models.Communication) {
 
 				// After 15 seconds without activity this is thrown..
 				if occurence == 3 {
-					log.Log.Info("components.Kerberos.ControlAgent(): Restarting machinery because of blocking mainstream.")
+					log.Log.Info(fmt.Sprintf("components.Kerberos.ControlAgent(): Restarting machinery because of blocking mainstream. (stalledKeyframeCounter=%d, lastPacket=%s ago, isConfiguring=%t)",
+						packetsR, packetAgeString(communication.LastPacketTimer), communication.IsConfiguring.IsSet()))
 					select {
 					case communication.HandleBootstrap <- "restart":
 						log.Log.Info("components.Kerberos.ControlAgent(): Restarting machinery because of blocking substream.")
@@ -507,6 +540,8 @@ func ControlAgent(communication *models.Communication) {
 
 					// After 15 seconds without activity this is thrown..
 					if occurenceSub == 3 {
+						log.Log.Info(fmt.Sprintf("components.Kerberos.ControlAgent(): substream stalled (stalledKeyframeCounter=%d, lastPacket=%s ago, isConfiguring=%t)",
+							packetsSubR, packetAgeString(communication.LastPacketTimerSub), communication.IsConfiguring.IsSet()))
 						select {
 						case communication.HandleBootstrap <- "restart":
 							log.Log.Info("components.Kerberos.ControlAgent(): Restarting machinery because of blocking substream.")