docs: Docker recipe for sandboxed agents#372
Merged
tomasz-tomczyk merged 2 commits intomainfrom Apr 28, 2026
Merged
Conversation
Adds integrations/docker/ with a Dockerfile, entrypoint.sh, and README showing how to run crit alongside an AI agent inside a container while keeping the review UI reachable from the host browser. Crit's 127.0.0.1 bind is preserved; a socat bridge in the entrypoint is the only thing exposed to docker port forwarding. Linked from the Agent Integrations section of the main README. Co-Authored-By: Claude Opus 4.7 (1M context) <noreply@anthropic.com>
Codecov Report✅ All modified and coverable lines are covered by tests. Additional details and impacted files@@ Coverage Diff @@
## main #372 +/- ##
==========================================
+ Coverage 66.62% 66.70% +0.07%
==========================================
Files 18 18
Lines 7964 7964
==========================================
+ Hits 5306 5312 +6
+ Misses 2259 2255 -4
+ Partials 399 397 -2
Flags with carried forward coverage won't be shown. Click here to find out more. ☔ View full report in Codecov by Sentry. 🚀 New features to boost your workflow:
|
Better fit alongside Build from Source / Go / Nix / Download Binary than under Agent Integrations. Co-Authored-By: Claude Opus 4.7 (1M context) <noreply@anthropic.com>
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
1 participant
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Outdated suggestions cannot be applied.This suggestion has been applied or marked resolved.Suggestions cannot be applied from pending reviews.Suggestions cannot be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
integrations/docker/with a workingDockerfile,entrypoint.sh, and recipe-styleREADME.mdfor runningcritalongside an AI coding agent (Claude Code, etc.) inside a container, with the review UI reachable from the host browser.127.0.0.1-only bind. Asocatbridge inside the container is the only thing exposed todocker -pforwarding — threat model unchanged.README.md.The recipe targets the workflow where the agent is sandboxed in a container but the human still reviews from their host browser. Defaults:
BRIDGE_PORT=8080(host-facing),CRIT_PORT=8081(loopback inside container). Multi-agent setups just bump host-side-pmappings.Test plan
docker build -t crit-agent integrations/docker/succeedsdocker run -p 8080:8080 crit-agent+ runningcrit plan.mdinside → host browser at http://localhost:8080 loads the review UIclaude --versionworks inside the container🤖 Generated with Claude Code