Merged
Conversation
- DESIGN_V2.md: Comprehensive improvement plan covering storage, protocol simplification, reliability, and DX enhancements - TMUX_IMPROVEMENTS.md: Focused analysis of tmux implementation with specific takeaways for better activity tracking, reconnection, and session discovery
New features for scaling beyond 2-3 agents: - Agent groups (@relay:@backend sends to all backend agents) - Terminal-based dashboard (agent-relay watch) - Coordination patterns (coordinator, pipeline, pub/sub) - Tmux layout helper for viewing multiple agents - Message priority levels (urgent !, normal, low ?) - Agent roles and permissions in teams.json
- Deep dive comparing our polling approach vs streaming alternative - Analyze robustness: injection, parsing, session management - Document Gemini @ symbol conflict with file references - Propose configurable prefix alternatives (>>, /relay, relay::) - Recommend auto-detection of best prefix per CLI type
…h it Key insight: The problem isn't polling vs streaming - it's visibility. Their advantages at scale: - Browser dashboard = single pane of glass - Activity state tracking (active/idle/typing) - Persistent message inbox - Agent discovery Our solution (keep native terminal, add visibility): - TUI dashboard (agent-relay watch) with blessed - Daemon event stream for real-time updates - Wrapper reports activity state - CLI commands: agents, history, send - Architecture: daemon becomes event hub, not just router
Analyzes whether the proposed TUI dashboard (blessed library) is the right approach for scaling to 5-10 agents. Conclusion: it's over- engineered. tmux already provides multi-window support. Recommended simpler approach: - agent-relay team start (multi-window tmux session) - watch -n2 agent-relay agents (live updates, zero code) - agent-relay attach <name> (quick attach helper) This saves ~3 days of implementation and avoids a new dependency.
Replace ai-maestro-specific paths with generic alternatives: - ~/.aimaestro/ → ~/.relay/ - send-aimaestro-message.sh → send-relay-message.sh The doc now uses neutral "alternative approach" terminology.
khaliqgant
added a commit
that referenced
this pull request
Jan 30, 2026
The delete call at line 1221 was unreachable because the worker is only added to activeWorkers at line 1247 (success path). Removing this harmless but confusing dead code. Addresses Devin review comment #4. 🤖 Generated with [Claude Code](https://claude.com/claude-code) Co-Authored-By: Claude Opus 4.5 <noreply@anthropic.com>
khaliqgant
added a commit
that referenced
this pull request
Jan 30, 2026
* injection retries * stabilization delay * Fix activity verification after buffer trim (#349) * more specific snippet * bump trajectories * Add retry logic to OpenCodeWrapper.injectTask() Addresses Devin's review comment about inconsistent retry behavior between OpenCodeWrapper and RelayPtyOrchestrator. OpenCodeWrapper now retries failed task injections up to 3 times with 500ms delays, matching RelayPtyOrchestrator's behavior for consistent reliability. 🤖 Generated with [Claude Code](https://claude.com/claude-code) Co-Authored-By: Claude Opus 4.5 <noreply@anthropic.com> * Remove dead code: activeWorkers.delete before worker added The delete call at line 1221 was unreachable because the worker is only added to activeWorkers at line 1247 (success path). Removing this harmless but confusing dead code. Addresses Devin review comment #4. 🤖 Generated with [Claude Code](https://claude.com/claude-code) Co-Authored-By: Claude Opus 4.5 <noreply@anthropic.com> --------- Co-authored-by: Claude Opus 4.5 <noreply@anthropic.com>
khaliqgant
added a commit
that referenced
this pull request
Apr 1, 2026
template-resolver.ts: shell-escape interpolated variables (CRITICAL #1) broker_tests.rs: uncomment and wire up 5 real tests (CRITICAL #2) worker_tests.rs: uncomment and wire up 5 real tests (CRITICAL #3) worker.rs: log bypass-flag injection, add .. path traversal rejection (CRITICAL #4, #7) verification.ts: export stripInjectedTaskEcho, add path traversal guard (CRITICAL #5) runner.ts: remove duplicate stripInjectedTaskEcho, add ENV_ALLOWLIST filtering (HIGH #17) channel-messenger.ts: add secret scrubbing, hoist regex constants (MEDIUM #27, #28) process-spawner.ts: add settled guard for race condition (MEDIUM #23) step-executor.ts: add sideEffects to callback type, deprecate alias (HIGH #15, #16) index.ts: export StepExecutor directly (MEDIUM #29) workflows/refactor/*.ts: replace hardcoded paths, remove --no-verify (HIGH #8-11) broker.rs: move is_pid_alive to canonical location (HIGH #14) cost/tracker.ts: add restrictive file permissions (MEDIUM #30) cost/pricing.ts: add last-verified date (MEDIUM #31) verification.test.ts: 9 new tests for exported helpers (MEDIUM #32) Co-Authored-By: My Senior Dev <dev@myseniordev.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
2 participants
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.
No description provided.