refactor: consolidate Plan+ and AI-DevOps into Build+#226
Conversation
Single coding agent that handles both planning and execution modes. Intent detection replaces agent separation. Pre-edit check remains as safety gate for accidental main branch edits. Includes t079.8 for setup.sh cleanup of removed agents on existing installs.
- Build+ is now the unified coding agent for planning and implementation - Added intent detection: deliberation vs execution mode - Merged Plan+ planning workflow (parallel explore, investigation, synthesis) - Plan+ and AI-DevOps demoted to subagents (@plan-plus, @AIDevops) - Updated generate-opencode-agents.sh to set Build+ as default agent - Updated AGENTS.md, onboarding.md, architecture.md documentation - Cleanup: removed Plan+ and AI-DevOps from primary agent list Closes #t079
|
Warning Rate limit exceeded
⌛ How to resolve this issue?After the wait time has elapsed, a review can be triggered using the We recommend that you space out your commits to avoid hitting the rate limit. 🚦 How do rate limits work?CodeRabbit enforces hourly rate limits for each developer per organization. Our paid plans have higher rate limits than the trial, open-source and free plans. In all cases, we re-allow further reviews after a brief timeout. Please see our FAQ for further information. Thanks for using CodeRabbit! It's free for OSS, and your support helps us grow. If you like it, consider giving us a shout-out. Comment |
Summary of ChangesHello @marcusquinn, I'm Gemini Code Assist1! I'm currently reviewing this pull request and will post my feedback shortly. In the meantime, here's a summary to help you and other reviewers quickly get up to speed! This pull request significantly refactors the agent architecture by unifying the Plan+ and AI-DevOps agents into an enhanced Build+ agent. The core purpose is to streamline the development workflow by providing a single, intelligent agent capable of handling both planning and implementation tasks through automatic intent detection. This change simplifies agent management, reduces context switching for users, and consolidates related functionalities under a more powerful Build+ persona, while retaining specialized functionalities of the former agents as subagents. Highlights
Using Gemini Code AssistThe full guide for Gemini Code Assist can be found on our documentation page, here are some quick tips. Invoking Gemini You can request assistance from Gemini at any point by creating a comment using either
Customization To customize Gemini Code Assist for GitHub experience, repository maintainers can create a configuration file and/or provide a custom code review style guide (such as PEP-8 for Python) by creating and adding files to a Limitations & Feedback Gemini Code Assist may make mistakes. Please leave feedback on any instances where its feedback is incorrect or counter productive. You can react with 👍 and 👎 on @gemini-code-assist comments. If you're interested in giving your feedback about your experience with Gemini Code Assist for Github and other Google products, sign up here. You can also get AI-powered code generation, chat, as well as code reviews directly in the IDE at no cost with the Gemini Code Assist IDE Extension. Footnotes
|
|
🔍 Code Quality Report�[0;35m[MONITOR]�[0m Code Review Monitoring Report �[0;34m[INFO]�[0m Latest Quality Status: �[0;34m[INFO]�[0m Recent monitoring activity: 📈 Current Quality Metrics
Generated on: Sun Jan 25 19:52:56 UTC 2026 Generated by AI DevOps Framework Code Review Monitoring |
![gemini-code-assist[bot]](https://avatars.githubusercontent.com/in/956858?s=60&v=4){kind=small}
There was a problem hiding this comment.
Code Review
This pull request is a well-executed refactoring that consolidates the Plan+ and AI-DevOps agents into a single, unified Build+ agent. The changes are comprehensive, consistently applied across all documentation and configuration files, and significantly simplify the agent architecture. The introduction of intent detection in the Build+ agent is a notable improvement. My review found only one minor issue regarding the clarity of an instruction for the agent, which I've detailed in a comment. Overall, this is a high-quality change that improves the maintainability and usability of the framework.
| 2. **Launch up to 3 Explore agents IN PARALLEL** (single message, multiple tool | ||
| calls) to efficiently explore the codebase: | ||
| - One agent searches for existing implementations | ||
| - Another explores related components | ||
| - A third investigates testing patterns | ||
| - Quality over quantity - use minimum agents necessary (usually 1) |
There was a problem hiding this comment.
The instruction to launch up to 3 agents in parallel is immediately followed by a note to use the minimum necessary, 'usually 1'. This could be confusing for the agent, especially in a section marked as critical. It would be clearer to provide a heuristic for when to use multiple agents, such as for more complex requests.
| 2. **Launch up to 3 Explore agents IN PARALLEL** (single message, multiple tool | |
| calls) to efficiently explore the codebase: | |
| - One agent searches for existing implementations | |
| - Another explores related components | |
| - A third investigates testing patterns | |
| - Quality over quantity - use minimum agents necessary (usually 1) | |
| 2. **Launch 1-3 Explore agents IN PARALLEL** (single message, multiple tool | |
| calls) to efficiently explore the codebase. Start with one agent for simple requests, and consider more for complex tasks: | |
| - One agent can search for existing implementations | |
| - Another can explore related components | |
| - A third can investigate testing patterns |
🤖 Augment PR SummarySummary: Consolidates the framework’s planning and DevOps “main agent” responsibilities into a single unified agent (Build+), and reframes Plan+ / AI-DevOps as specialist subagents. Changes:
Technical Notes: Primary agent selection/order is now centered on Build+, with planning behavior driven by prompt-level intent detection rather than a separate planning-only primary agent. 🤖 Was this summary useful? React with 👍 or 👎 |
![augmentcode[bot]](https://avatars.githubusercontent.com/in/1027498?s=60&v=4){kind=small}
| **[Claude Code](https://Claude.ai/)** is the recommended and primary-tested AI coding agent for aidevops. All features, agents, workflows, and MCP integrations are designed and tested for Claude Code first. Other AI assistants (OpenCode, Cursor, Zed, etc.) are supported as a courtesy for users evaluating aidevops capabilities, but may not receive the same level of testing or integration depth. | ||
|
|
||
| Key OpenCode integrations: | ||
| Key integrations: |
There was a problem hiding this comment.
This now reads as general “Key integrations”, but the bullets are OpenCode-specific (e.g., ~/.config/opencode/commands/, generate-opencode-agents.sh). Consider clarifying which host tool each integration applies to, since the section now recommends Claude Code as primary.
🤖 Was this useful? React with 👍 or 👎
|
|
||
| # Files to skip (not primary agents - includes demoted agents) | ||
| # plan-plus.md and aidevops.md are now subagents, not primary agents | ||
| SKIP_PRIMARY_AGENTS = {"plan-plus.md", "aidevops.md"} |
There was a problem hiding this comment.
Since plan-plus.md/aidevops.md are skipped as primary agents and subagent generation only scans subfolders (find ... -mindepth 2), it looks like @plan-plus/@aidevops won’t be generated into ~/.config/opencode/agent/. This seems to conflict with the later note that they’re available as @subagents.
Other Locations
.agent/scripts/generate-opencode-agents.sh:760
🤖 Was this useful? React with 👍 or 👎
Plan+ was consolidated into Build+ (PR #226) but several files still referenced Plan+ as a primary agent. This caused the list-todo command to fail by routing to a non-existent primary agent. Changes: - list-todo, save-todo, show-plan: agent frontmatter Plan+ → Build+ - conversation-starter: Plan+ section → Build+ deliberation mode - add-new-mcp-to-aidevops: remove Plan+ from primary agent lists - troubleshooting, opencode: update test examples to Build+ - context-guardrails: reference @plan-plus subagent instead - README: update agent structure description Historical references in TODO.md, PLANS.md, CHANGELOG.md preserved. plan-plus.md (the subagent itself) left unchanged - already correct.
* fix: update deprecated Plan+ agent references to Build+ across docs Plan+ was consolidated into Build+ (PR #226) but several files still referenced Plan+ as a primary agent. This caused the list-todo command to fail by routing to a non-existent primary agent. Changes: - list-todo, save-todo, show-plan: agent frontmatter Plan+ → Build+ - conversation-starter: Plan+ section → Build+ deliberation mode - add-new-mcp-to-aidevops: remove Plan+ from primary agent lists - troubleshooting, opencode: update test examples to Build+ - context-guardrails: reference @plan-plus subagent instead - README: update agent structure description Historical references in TODO.md, PLANS.md, CHANGELOG.md preserved. plan-plus.md (the subagent itself) left unchanged - already correct. * fix: remove stale agent count from README per review feedback * fix: remove disabled Plan+/AI-DevOps agent entries that cause providerID TypeError OpenCode iterates all agent entries and tries to resolve model.providerID even for disabled agents. Since Plan+ and AI-DevOps have no model config, this causes: TypeError: undefined is not an object (evaluating 'input.model.providerID') Fix: Stop emitting {"disable": true} entries for Plan+ and AI-DevOps in the generator script. They exist only as subagents (@plan-plus, @AIDevops) and don't need primary agent entries at all. OpenCode's built-in build/plan agents still need disable entries since they'd otherwise appear by default. * revert: restore disabled agent entries in generator script The providerID TypeError is not caused by disabled agent entries. Reverting to original behavior while investigating the actual cause.
1 participant
Summary
@plan-plus,@aidevops)Changes
Build+ Enhancements
Agent Generator Updates
AGENT_ORDERSKIP_PRIMARY_AGENTSset to exclude demoted agentsdefault_agentDocumentation Updates
Testing
Related
Closes t079