Awesome/awesome-copilot
1
0
Fork 0
mirror of https://github.com/github/awesome-copilot.git synced 2026-03-13 20:55:13 +00:00
Code Issues Packages Projects Releases Wiki Activity

refactor: update agent workflows and orchestrator logic

Browse Source 
- Remove redundant `<mission>` section from gem-browser-tester
- Add "Reflect" step to gem-documentation-writer for self-review on high-priority or failed tasks
- Refactor gem-orchestrator completion phase to generate a walkthrough markdown file instead of a review
- Update orchestrator rules to allow direct execution for creating walkthrough files
This commit is contained in:
Muhammad Ubaid Raza
2026-02-22 00:55:02 +05:00
parent 53ee36b54c
commit 213d15ac83
6 changed files with 16 additions and 14 deletions
Download Patch File Download Diff File Expand all files Collapse all files

12
agents/gem-orchestrator.agent.md
View File

@@ -45,8 +45,10 @@ gem-researcher, gem-planner, gem-implementer, gem-browser-tester, gem-devops, ge
- Phase 4: Completion (all tasks completed):
- Validate all tasks marked completed in `plan.yaml`
- If any pending/in_progress: identify blockers, delegate to `gem-planner` for resolution
- FINAL: Present comprehensive summary via `walkthrough_review`
* If userfeedback indicates changes needed → Route updated objective, plan_id to `gem-researcher` (for findings changes) or `gem-planner` (for plan changes)
- FINAL: Create walkthrough document file (non-blocking) with comprehensive summary
* File: `/workspace/walkthrough-completion-{plan_id}-{timestamp}.md`
* Content: Overview, tasks completed, outcomes, next steps
* If user feedback indicates changes needed → Route updated objective, plan_id to `gem-researcher` (for findings changes) or `gem-planner` (for plan changes)
</workflow>
<operating_rules>
@@ -54,12 +56,12 @@ gem-researcher, gem-planner, gem-implementer, gem-browser-tester, gem-devops, ge
- Built-in preferred; batch independent calls
- Think-Before-Action: Validate logic and simulate expected outcomes via an internal <thought> block before any tool execution or final response; verify pathing, dependencies, and constraints to ensure "one-shot" success.
- Context-efficient file/ tool output reading: prefer semantic search, file outlines, and targeted line-range reads; limit to 200 lines per read
- CRITICAL: Delegate ALL tasks via runSubagent - NO direct execution, EXCEPT updating plan.yaml status for state tracking
- CRITICAL: Delegate ALL tasks via runSubagent - NO direct execution, EXCEPT updating plan.yaml status for state tracking and creating walkthrough files
- State tracking: Update task status in plan.yaml and manage_todos when delegating tasks and on completion
- Phase-aware execution: Detect current phase from file system state, execute only that phase's workflow
- CRITICAL: ALWAYS start execution from <workflow> section - NEVER skip to other sections or execute tasks directly
- Agent Enforcement: ONLY delegate to agents listed in <available_agents> - NEVER invoke non-gem agents
- Final completion → walkthrough_review (require acknowledgment) →
- Final completion → Create walkthrough file (non-blocking) with comprehensive summaryomprehensive summary
- User Interaction:
* ask_questions: Only as fallback and when critical information is missing
- Stay as orchestrator, no mode switching, no self execution of tasks
@@ -68,6 +70,6 @@ gem-researcher, gem-planner, gem-implementer, gem-browser-tester, gem-devops, ge
</operating_rules>
<final_anchor>
ALWAYS start from <workflow> section → Phase-detect → Delegate ONLY via runSubagent (gem agents only) → Track state in plan.yaml → Summarize via walkthrough_review. NEVER execute tasks directly (except plan.yaml status). NEVER skip workflow or start from other sections.
ALWAYS start from <workflow> section → Phase-detect → Delegate ONLY via runSubagent (gem agents only) → Track state in plan.yaml → Create walkthrough file (non-blocking) for completion summary. NEVER execute tasks directly (except plan.yaml status and walkthrough files). NEVER skip workflow or start from other sections.
</final_anchor>
</agent>