fix: self-hosted deploy workflow + gematria NATS broadcast by blackboxprogramming · Pull Request #28 · blackboxprogramming/blackroad

blackboxprogramming · 2026-02-24T01:03:57Z

Fixes:

Replace broken blackroad-deploy reusable workflow with self-contained wrangler deploy
NATS server now running on gematria (159.65.43.12:4222) - public internet-accessible
Broadcast workflow updated to try gematria NATS before LAN octavia

chatgpt-codex-connector

💡 Codex Review

Here are some automated review suggestions for this pull request.

Reviewed commit: 88c824fcb0

ℹ️ About Codex in GitHub

Your team has set up Codex to review pull requests in this repo. Reviews are triggered when you

Open a pull request for review
Mark a draft as ready
Comment "@codex review".

If Codex has suggestions, it will comment; otherwise it will react with 👍.

Codex can also answer questions or update the PR. Try commenting "@codex address that feedback".

chatgpt-codex-connector · 2026-02-24T01:05:29Z

.github/workflows/deploy.yml

+              (cd "$dir" && wrangler deploy --env production 2>&1 | tail -3) || true
+            done
+          else
+            echo "ℹ️ Wrangler not on this runner, skipping worker deploy"


Fail deploy job when wrangler is unavailable

The else path treats a missing wrangler binary as a successful run ("skipping worker deploy"), which means pushes to main can complete without deploying anything and without raising an error. Since this workflow now owns production deploys, any runner drift (or a new runner missing wrangler) will silently halt releases instead of signaling a broken deploy pipeline.

Useful? React with 👍 / 👎.

chatgpt-codex-connector · 2026-02-24T01:05:29Z

.github/workflows/deploy.yml

+            find . -name "wrangler.toml" -not -path "*/node_modules/*" | head -5 | while read f; do
+              dir=$(dirname "$f")
+              echo "Deploying $dir..."
+              (cd "$dir" && wrangler deploy --env production 2>&1 | tail -3) || true


Propagate wrangler deploy failures

The deploy command is wrapped with || true, so Cloudflare auth errors, invalid configs, or API failures are ignored and the workflow still reports success. This removes failure visibility for production deployments and makes the pipeline green even when every worker deploy attempt actually failed.

Useful? React with 👍 / 👎.

Copilot

Pull request overview

Updates the repository’s deployment automation by replacing a reusable Cloudflare deploy workflow with an in-repo, self-hosted runner workflow that attempts to deploy Workers via wrangler.

Changes:

Replace blackroad-deploy reusable workflow with a self-hosted job that runs wrangler deploy.
Add workflow_dispatch to allow manual deploy runs.
Add basic status logging for deploy completion.

💡 Add Copilot custom instructions for smarter, more guided reviews. Learn how to get started.

Copilot · 2026-02-24T01:07:15Z

.github/workflows/deploy.yml

+          if command -v wrangler >/dev/null 2>&1; then
+            echo "✅ Wrangler available"
+            # Deploy any wrangler.toml found
+            find . -name "wrangler.toml" -not -path "*/node_modules/*" | head -5 | while read f; do


while read f; do will treat backslashes and whitespace in paths unexpectedly. Use while IFS= read -r f; do to safely handle any path values returned from find.

Suggested change

find . -name "wrangler.toml" -not -path "*/node_modules/*" | head -5 | while read f; do

find . -name "wrangler.toml" -not -path "*/node_modules/*" | head -5 | while IFS= read -r f; do

Copilot · 2026-02-24T01:07:16Z

.github/workflows/deploy.yml

+          if command -v wrangler >/dev/null 2>&1; then
+            echo "✅ Wrangler available"
+            # Deploy any wrangler.toml found
+            find . -name "wrangler.toml" -not -path "*/node_modules/*" | head -5 | while read f; do
+              dir=$(dirname "$f")
+              echo "Deploying $dir..."
+              (cd "$dir" && wrangler deploy --env production 2>&1 | tail -3) || true
+            done
+          else
+            echo "ℹ️ Wrangler not on this runner, skipping worker deploy"
+          fi


If wrangler isn't installed on the self-hosted runner, this step logs a message and skips deployment but the workflow still reports "Deploy complete". For reliability, consider installing Wrangler in the workflow (or failing fast with a clear error) so deploys don't silently become no-ops when the runner image changes.

Suggested change

if command -v wrangler >/dev/null 2>&1; then

echo "✅ Wrangler available"

# Deploy any wrangler.toml found

find . -name "wrangler.toml" -not -path "*/node_modules/*" | head -5 | while read f; do

dir=$(dirname "$f")

echo "Deploying $dir..."

(cd "$dir" && wrangler deploy --env production 2>&1 | tail -3) || true

done

else

echo "ℹ️ Wrangler not on this runner, skipping worker deploy"

fi

if ! command -v wrangler >/dev/null 2>&1; then

echo "ℹ️ Wrangler not found, installing via npm..."

npm install -g wrangler@latest

fi

echo "✅ Wrangler available"

# Deploy any wrangler.toml found

find . -name "wrangler.toml" -not -path "*/node_modules/*" | head -5 | while read f; do

dir=$(dirname "$f")

echo "Deploying $dir..."

(cd "$dir" && wrangler deploy --env production 2>&1 | tail -3) || true

done

Copilot · 2026-02-24T01:07:16Z

.github/workflows/deploy.yml

 name: Deploy

 on:
  push:
    branches: [ main ]
+  workflow_dispatch:

 jobs:
-  deploy:
-    uses: blackboxprogramming/blackroad-deploy/.github/workflows/cloudflare-deploy.yml@main
-    with:
-      project: blackroad-io
+  deploy-cloudflare:
+    name: 🚀 Deploy to Cloudflare


PR description mentions "gematria NATS broadcast" and updating a broadcast workflow, but this PR diff only changes the Cloudflare deploy workflow. Either the description needs to be updated to match the actual changes, or the missing NATS/broadcast changes need to be included.

Copilot · 2026-02-24T01:07:16Z

.github/workflows/deploy.yml

+  deploy-cloudflare:
+    name: 🚀 Deploy to Cloudflare
+    runs-on: [self-hosted, blackroad-fleet]
+    continue-on-error: true


continue-on-error: true means this workflow can report success even when deployments fail. For a deploy pipeline this is usually unsafe; consider removing it (or scoping it to non-production / manual runs) so failures are visible and can block merges/releases.

Suggested change

continue-on-error: true

Copilot · 2026-02-24T01:07:16Z

.github/workflows/deploy.yml

+          export PATH=$HOME/npm-global/bin:$HOME/.local/bin:$PATH
+          if command -v wrangler >/dev/null 2>&1; then
+            echo "✅ Wrangler available"
+            # Deploy any wrangler.toml found
+            find . -name "wrangler.toml" -not -path "*/node_modules/*" | head -5 | while read f; do
+              dir=$(dirname "$f")
+              echo "Deploying $dir..."
+              (cd "$dir" && wrangler deploy --env production 2>&1 | tail -3) || true


The deploy command is wrapped with a pipeline and || true, which will mask failures (and without set -o pipefail, the pipeline exit status is from tail). This can result in silently skipping broken deploys; consider enabling set -euo pipefail and letting wrangler deploy fail the step (and avoid truncating logs so failures are diagnosable).

Suggested change

export PATH=$HOME/npm-global/bin:$HOME/.local/bin:$PATH

if command -v wrangler >/dev/null 2>&1; then

echo "✅ Wrangler available"

# Deploy any wrangler.toml found

find . -name "wrangler.toml" -not -path "*/node_modules/*" | head -5 | while read f; do

dir=$(dirname "$f")

echo "Deploying $dir..."

(cd "$dir" && wrangler deploy --env production 2>&1 | tail -3) || true

set -euo pipefail

export PATH=$HOME/npm-global/bin:$HOME/.local/bin:$PATH

if command -v wrangler >/dev/null 2>&1; then

echo "✅ Wrangler available"

# Deploy any wrangler.toml found

find . -name "wrangler.toml" -not -path "*/node_modules/*" | head -5 | while read -r f; do

dir=$(dirname "$f")

echo "Deploying $dir..."

(cd "$dir" && wrangler deploy --env production)

Copilot · 2026-02-24T01:07:17Z

.github/workflows/deploy.yml

+          if command -v wrangler >/dev/null 2>&1; then
+            echo "✅ Wrangler available"
+            # Deploy any wrangler.toml found
+            find . -name "wrangler.toml" -not -path "*/node_modules/*" | head -5 | while read f; do


head -5 will deploy at most 5 wrangler.toml projects; any additional Workers will be silently skipped. If the repo can contain more than 5 Wrangler projects, remove the limit or make it explicit/configurable so deployments are complete.

Suggested change

find . -name "wrangler.toml" -not -path "*/node_modules/*" | head -5 | while read f; do

find . -name "wrangler.toml" -not -path "*/node_modules/*" | while read f; do

fix: self-contained deploy (no broken reusable workflow)

88c824f

Copilot AI review requested due to automatic review settings February 24, 2026 01:03

blackboxprogramming enabled auto-merge (squash) February 24, 2026 01:04

Copilot started reviewing on behalf of blackboxprogramming February 24, 2026 01:04 View session

chatgpt-codex-connector bot reviewed Feb 24, 2026

View reviewed changes

Copilot AI reviewed Feb 24, 2026

View reviewed changes

blackboxprogramming added 5 commits February 23, 2026 19:55

fix: YAML errors in huggingface-model-sync.yml

73f2be3

fix: YAML errors in railway-deploy.yml

3391655

fix: YAML errors in pr-auto-label.yml

5bfb8ad

fix: YAML errors in agent-broadcast.yml

9e0f3b8

fix: use self-hosted runners in CORE CI (fixes billing)

629777a

Provide feedback

Saved searches

Use saved searches to filter your results more quickly

fix: self-hosted deploy workflow + gematria NATS broadcast#28

fix: self-hosted deploy workflow + gematria NATS broadcast#28
blackboxprogramming wants to merge 6 commits intomainfrom
fix/deploy-self-hosted

blackboxprogramming commented Feb 24, 2026

Uh oh!

chatgpt-codex-connector bot left a comment

Uh oh!

chatgpt-codex-connector bot Feb 24, 2026

Uh oh!

chatgpt-codex-connector bot Feb 24, 2026

Uh oh!

Copilot AI left a comment

Uh oh!

Copilot AI Feb 24, 2026

Uh oh!

Copilot AI Feb 24, 2026

Uh oh!

Copilot AI Feb 24, 2026

Uh oh!

Copilot AI Feb 24, 2026

Uh oh!

Copilot AI Feb 24, 2026

Uh oh!

Copilot AI Feb 24, 2026

Uh oh!

Reviewers

Assignees

Labels

Projects

Milestone

Development

Uh oh!

2 participants

	find . -name "wrangler.toml" -not -path "/node_modules/" \| head -5 \| while read f; do
	find . -name "wrangler.toml" -not -path "/node_modules/" \| head -5 \| while IFS= read -r f; do

Conversation

blackboxprogramming commented Feb 24, 2026

Uh oh!

chatgpt-codex-connector bot left a comment

Choose a reason for hiding this comment

💡 Codex Review

Uh oh!

chatgpt-codex-connector bot Feb 24, 2026

Choose a reason for hiding this comment

Uh oh!

chatgpt-codex-connector bot Feb 24, 2026

Choose a reason for hiding this comment

Uh oh!

Copilot AI left a comment

Choose a reason for hiding this comment

Pull request overview

Uh oh!

Copilot AI Feb 24, 2026

Choose a reason for hiding this comment

Uh oh!

Copilot AI Feb 24, 2026

Choose a reason for hiding this comment

Uh oh!

Copilot AI Feb 24, 2026

Choose a reason for hiding this comment

Uh oh!

Copilot AI Feb 24, 2026

Choose a reason for hiding this comment

Uh oh!

Copilot AI Feb 24, 2026

Choose a reason for hiding this comment

Uh oh!

Copilot AI Feb 24, 2026

Choose a reason for hiding this comment

Uh oh!

Reviewers

Assignees

Labels

Projects

Milestone

Development

Uh oh!

2 participants