feat: add /fullsend upgrade command and improve local setup docs#14
Merged
Conversation
…ting Documents the two-layer env architecture (runner context vs sandbox .env.d), per-agent env file requirements (GH_TOKEN, GIT_BOT_EMAIL), custom image requirement, sandbox log inspection, and common local setup mistakes. Co-Authored-By: Claude Opus 4.6 <noreply@anthropic.com>
There was a problem hiding this comment.
Pull request overview
Updates the /fullsend help setup local setup reference to better document RHDH-specific requirements when running fullsend agents locally (GCP env config, custom sandbox image, per-agent env files, and troubleshooting/log inspection).
Changes:
- Expands the local setup guide with clearer GCP env-file examples and an explicit requirement to use the RHDH custom sandbox image.
- Adds guidance for per-agent env files (common variables + example triage/code envs) and updated local run commands.
- Adds sandbox log inspection steps plus an RHDH-specific troubleshooting table.
💡 Add Copilot custom instructions for smarter, more guided reviews. Learn how to get started.
Comment on lines
+39
to
40
| GOOGLE_APPLICATION_CREDENTIALS=/Users/<you>/.config/fullsend/fullsend-local-credentials.json | ||
| FULLSEND_SANDBOX_IMAGE=ghcr.io/redhat-developer/rhdh-fullsend-code:latest |
Comment on lines
114
to
+116
| fullsend run triage \ | ||
| --fullsend-dir /path/to/fullsend/internal/scaffold/fullsend-repo/ \ | ||
| --target-repo /path/to/your/target-repo/ \ | ||
| --fullsend-dir ~/src/rhdh/asdlc-lab/resources/fullsend-ai/fullsend/internal/scaffold/fullsend-repo/ \ | ||
| --target-repo ~/src/rhdh/rhdh-plugins/ \ |
Comment on lines
+122
to
+124
| fullsend run code \ | ||
| --fullsend-dir ~/src/rhdh/asdlc-lab/resources/fullsend-ai/fullsend/internal/scaffold/fullsend-repo/ \ | ||
| --target-repo ~/src/rhdh/rhdh-plugins/ \ |
Comment on lines
+138
to
+145
| # Find the latest run output | ||
| ls -td /tmp/fullsend/agent-*/ | head -1 | ||
|
|
||
| # Check for DENIED requests | ||
| grep "DENIED" /tmp/fullsend/agent-*/logs/openshell-sandbox.log | sort | uniq -c | sort -rn | ||
|
|
||
| # Full sandbox log | ||
| less /tmp/fullsend/agent-*/logs/openshell-sandbox.log |
Comment on lines
16
to
20
| Direct the user to the canonical upstream guide for all generic setup: | ||
|
|
||
| ``` | ||
| 📘 Follow the upstream guide first: | ||
| Follow the upstream guide first: | ||
| https://github.com/fullsend-ai/fullsend/blob/main/docs/guides/user/running-agents-locally.md |
This file contains hidden or bidirectional Unicode text that may be interpreted or compiled differently than what appears below. To review, open the file in an editor that reveals hidden Unicode characters.
Learn more about bidirectional Unicode characters
Sign up for free
to join this conversation on GitHub.
Already have an account?
Sign in to comment
Add this suggestion to a batch that can be applied as a single commit.This suggestion is invalid because no changes were made to the code.Suggestions cannot be applied while the pull request is closed.Suggestions cannot be applied while viewing a subset of changes.Only one suggestion per line can be applied in a batch.Add this suggestion to a batch that can be applied as a single commit.Applying suggestions on deleted lines is not supported.You must change the existing code in this line in order to create a valid suggestion.Outdated suggestions cannot be applied.This suggestion has been applied or marked resolved.Suggestions cannot be applied from pending reviews.Suggestions cannot be applied on multi-line comments.Suggestions cannot be applied while the pull request is queued to merge.Suggestion cannot be applied right now. Please check back later.
Summary
/fullsend upgradecommand with step-by-step upgrade procedure and smoke testTest plan
/fullsend upgradeand verify it loads the reference/fullsend help setupand verify updated local setup guide🤖 Generated with Claude Code