Conversation
Implement --test-mode flag that simulates the full Ralph loop without calling the real Claude CLI. This enables testing of Slack notifications, log output, and all phases (main loop, code review, cleanup, PR creation) in a deterministic way. Features: - New internal/testmode package with MockClaude that simulates todo progress - Three scenarios: success (default), error, partial - Writes real TODO.md files so existing parsing/tracking works unchanged - Exercises all notification hooks: SessionStart, TodoStarted, TodoCompleted, CodeReviewStarted/Complete, CleanupStarted/Complete, PRCreated, SessionEnd - Demonstrates all log types (standard, verbose, error, success) Also includes: - Sound playback support with Ralph Wiggum quotes - Version injection via ldflags in Makefile - GitHub Actions CI/CD workflows - GoReleaser configuration for releases Slack: https://hevmindworkspace.slack.com/archives/C0A6L0UFU6R/p1768048187219089 Co-Authored-By: Claude Opus 4.5 <noreply@anthropic.com>
Add documentation for the scratchpad_prompt configuration option that
allows customizing the instructions appended to prompts. Includes the
config reference example and explains the {{.AgentDir}} template syntax.
Slack: https://hevmindworkspace.slack.com/archives/C0A6L0UFU6R/p1768050250729429
Co-Authored-By: Claude Opus 4.5 <noreply@anthropic.com>
Add comprehensive agent workflow instructions including: - Fresh plan review: validate ordering and dependencies - Completed plan review: verify implementation, add improvements - Testing: run before/after changes, no regressions - Artifact management: keep items under .agent/items/, clean up when done - Session hygiene: commit after cleanup, keep prompt.md updated Co-Authored-By: Claude Opus 4.5 <noreply@anthropic.com>
The test coverage plan has been fully implemented - all packages now have test files and tests are passing. The prompt.md file is no longer needed. Slack: https://hevmindworkspace.slack.com/archives/C0A6L0UFU6R/p1768050346701169 Co-Authored-By: Claude Opus 4.5 <noreply@anthropic.com>
The pattern `ralph` was too broad and matched both the binary and the internal/ralph/ directory, causing CI failures. Co-Authored-By: Claude Opus 4.5 <noreply@anthropic.com>
golangci-lint doesn't support Go 1.25 yet. Co-Authored-By: Claude Opus 4.5 <noreply@anthropic.com>
Use atomic.Int64 for currentPending and currentComplete fields to prevent data races when UpdateTodoCounts is called concurrently with the observable gauge callbacks. Co-Authored-By: Claude Opus 4.5 <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
Test plan
go test ./...)🤖 Generated with Claude Code