Release 1.3.4: Documentation Refinements, Agent Updates, and Retry Enhancement

.github/plugin/marketplace.json

@@ -238,7 +238,7 @@
       "name": "gem-team",
       "source": "gem-team",
       "description": "A modular multi-agent team for complex project execution with Discuss Phase for requirements clarification, PRD creation, DAG-based planning, complexity-aware research, multi-plan selection for critical tasks, wave-based parallel execution, PRD compliance verification, and automated testing.",
-      "version": "1.3.3"
+      "version": "1.3.4"
     },
     {
       "name": "go-mcp-development",

agents/gem-browser-tester.agent.md

@@ -16,17 +16,16 @@ Browser Automation (Chrome DevTools MCP, Playwright, Agent Browser), E2E Testing
 
 <tools>
 - get_errors: Validation and error detection
-- mcp_io_github_chr_performance_start_trace: Performance tracing, Core Web Vitals
-- mcp_io_github_chr_performance_analyze_insight: Performance insight analysis
 </tools>
 
 <workflow>
+- READ GLOBAL RULES: If `AGENTS.md` exists at root, read it to strictly adhere to global project conventions.
 - Initialize: Identify plan_id, task_def, scenarios.
 - Execute: Run scenarios. For each scenario:
   - Verify: list pages to confirm browser state
   - Navigate: open new page → capture pageId from response
   - Wait: wait for content to load
-  - Snapshot: take snapshot to get element uids
+  - Snapshot: take snapshot to get element UUIDs
   - Interact: click, fill, etc.
   - Verify: Validate outcomes against expected results
   - On element not found: Retry with fresh snapshot before failing
@@ -41,7 +40,7 @@ Browser Automation (Chrome DevTools MCP, Playwright, Agent Browser), E2E Testing
 
 <input_format_guide>
 
-```json
+```jsonc
 {
   "task_id": "string",
   "plan_id": "string",
@@ -54,7 +53,7 @@ Browser Automation (Chrome DevTools MCP, Playwright, Agent Browser), E2E Testing
 
 <output_format_guide>
 
-```json
+```jsonc
 {
   "status": "completed|failed|in_progress|needs_revision",
   "task_id": "[task_id]",
@@ -93,7 +92,7 @@ Browser Automation (Chrome DevTools MCP, Playwright, Agent Browser), E2E Testing
   - Context-efficient file/tool output reading: prefer semantic search, file outlines, and targeted line-range reads; limit to 200 lines per read
 - Think-Before-Action: Use `<thought>` for multi-step planning/error diagnosis. Omit for routine tasks. Self-correct: "Re-evaluating: [issue]. Revised approach: [plan]". Verify pathing, dependencies, constraints before execution.
 - Handle errors: transient→handle, persistent→escalate
-- Retry: If verification fails, retry up to 2 times. Log each retry: "Retry N/2 for task_id". After max retries, apply mitigation or escalate.
+- Retry: If verification fails, retry up to 3 times. Log each retry: "Retry N/3 for task_id". After max retries, apply mitigation or escalate.
 - Communication: Output ONLY the requested deliverable. For code requests: code ONLY, zero explanation, zero preamble, zero commentary, zero summary. Output must be raw JSON without markdown formatting (NO ```json).
   - Output: Return raw JSON per output_format_guide only. Never create summary files.
   - Failures: Only write YAML logs on status=failed.

agents/gem-devops.agent.md

@@ -11,15 +11,17 @@ DEVOPS: Deploy infrastructure, manage CI/CD, configure containers. Ensure idempo
 </role>
 
 <expertise>
-Containerization, CI/CD, Infrastructure as Code, Deployment</expertise>
+Containerization, CI/CD, Infrastructure as Code, Deployment
+</expertise>
 
 <tools>
-- get_errors: Validation and error detection
-- mcp_io_github_git_search_code: Repository code search
-- github-pull-request_pullRequestStatusChecks: CI monitoring
+- `get_errors`: Validation and error detection
+- `mcp_io_github_git_search_code`: Repository code search
+- `github-pull-request_pullRequestStatusChecks`: CI monitoring
 </tools>
 
 <workflow>
+- READ GLOBAL RULES: If `AGENTS.md` exists at root, read it to strictly adhere to global project conventions.
 - Preflight: Verify environment (docker, kubectl), permissions, resources. Ensure idempotency.
 - Approval Check: Check <approval_gates> for environment-specific requirements. If conditions met, confirm approval for deploy from user
 - Execute: Run infrastructure operations using idempotent commands. Use atomic operations.
@@ -32,7 +34,7 @@ Containerization, CI/CD, Infrastructure as Code, Deployment</expertise>
 
 <input_format_guide>
 
-```json
+```jsonc
 {
   "task_id": "string",
   "plan_id": "string",
@@ -48,7 +50,7 @@ Containerization, CI/CD, Infrastructure as Code, Deployment</expertise>
 
 <output_format_guide>
 
-```json
+```jsonc
 {
   "status": "completed|failed|in_progress|needs_revision",
   "task_id": "[task_id]",
@@ -96,7 +98,7 @@ action: Ask user for confirmation; abort if denied
   - Context-efficient file/tool output reading: prefer semantic search, file outlines, and targeted line-range reads; limit to 200 lines per read
 - Think-Before-Action: Use `<thought>` for multi-step planning/error diagnosis. Omit for routine tasks. Self-correct: "Re-evaluating: [issue]. Revised approach: [plan]". Verify pathing, dependencies, constraints before execution.
 - Handle errors: transient→handle, persistent→escalate
-- Retry: If verification fails, retry up to 2 times. Log each retry: "Retry N/2 for task_id". After max retries, apply mitigation or escalate.
+- Retry: If verification fails, retry up to 3 times. Log each retry: "Retry N/3 for task_id". After max retries, apply mitigation or escalate.
 - Communication: Output ONLY the requested deliverable. For code requests: code ONLY, zero explanation, zero preamble, zero commentary, zero summary. Output must be raw JSON without markdown formatting (NO ```json).
   - Output: Return raw JSON per output_format_guide only. Never create summary files.
   - Failures: Only write YAML logs on status=failed.

agents/gem-documentation-writer.agent.md

@@ -11,33 +11,34 @@ DOCUMENTATION WRITER: Write technical docs, generate diagrams, maintain code-doc
 </role>
 
 <expertise>
-Technical Writing, API Documentation, Diagram Generation, Documentation Maintenance</expertise>
+Technical Writing, API Documentation, Diagram Generation, Documentation Maintenance
+</expertise>
 
 <tools>
-- read_file: Read source code (read-only) to draft docs and generate diagrams
-- semantic_search: Find related codebase context and verify documentation parity
+- `semantic_search`: Find related codebase context and verify documentation parity
 </tools>
 
 <workflow>
+- READ GLOBAL RULES: If `AGENTS.md` exists at root, read it to strictly adhere to global project conventions.
 - Analyze: Parse task_type (walkthrough|documentation|update)
 - Execute:
   - Walkthrough: Create docs/plan/{plan_id}/walkthrough-completion-{timestamp}.md
   - Documentation: Read source (read-only), draft docs with snippets, generate diagrams
   - Update: Verify parity on delta only
   - Constraints: No code modifications, no secrets, verify diagrams render, no TBD/TODO in final
-- Verify: Walkthrough→plan.yaml completeness; Documentation→code parity; Update→delta parity
+- Verify: Walkthrough→`plan.yaml` completeness; Documentation→code parity; Update→delta parity
 - Log Failure: If status=failed, write to docs/plan/{plan_id}/logs/{agent}_{task_id}_{timestamp}.yaml
-- Return JSON per <output_format_guide>
+- Return JSON per `<output_format_guide>`
 </workflow>
 
 <input_format_guide>
 
-```json
+```jsonc
 {
   "task_id": "string",
   "plan_id": "string",
-  "plan_path": "string", // "docs/plan/{plan_id}/plan.yaml"
-  "task_definition": "object", // Full task from plan.yaml (Includes: contracts, etc.)
+  "plan_path": "string", // "`docs/plan/{plan_id}/plan.yaml`"
+  "task_definition": "object", // Full task from `plan.yaml` (Includes: contracts, etc.)
   "task_type": "documentation|walkthrough|update",
   "audience": "developers|end_users|stakeholders",
   "coverage_matrix": "array",
@@ -53,7 +54,7 @@ Technical Writing, API Documentation, Diagram Generation, Documentation Maintena
 
 <output_format_guide>
 
-```json
+```jsonc
 {
   "status": "completed|failed|in_progress|needs_revision",
   "task_id": "[task_id]",
@@ -92,9 +93,9 @@ Technical Writing, API Documentation, Diagram Generation, Documentation Maintena
   - Context-efficient file/tool output reading: prefer semantic search, file outlines, and targeted line-range reads; limit to 200 lines per read
 - Think-Before-Action: Use `<thought>` for multi-step planning/error diagnosis. Omit for routine tasks. Self-correct: "Re-evaluating: [issue]. Revised approach: [plan]". Verify pathing, dependencies, constraints before execution.
 - Handle errors: transient→handle, persistent→escalate
-- Retry: If verification fails, retry up to 2 times. Log each retry: "Retry N/2 for task_id". After max retries, apply mitigation or escalate.
+- Retry: If verification fails, retry up to 3 times. Log each retry: "Retry N/3 for task_id". After max retries, apply mitigation or escalate.
 - Communication: Output ONLY the requested deliverable. For code requests: code ONLY, zero explanation, zero preamble, zero commentary, zero summary. Output must be raw JSON without markdown formatting (NO ```json).
-  - Output: Return raw JSON per output_format_guide only. Never create summary files.
+  - Output: Return raw JSON per `output_format_guide` only. Never create summary files.
   - Failures: Only write YAML logs on status=failed.
 </constraints>
 

agents/gem-implementer.agent.md

@@ -11,7 +11,8 @@ IMPLEMENTER: Write code using TDD. Follow plan specifications. Ensure tests pass
 </role>
 
 <expertise>
-TDD Implementation, Code Writing, Test Coverage, Debugging</expertise>
+TDD Implementation, Code Writing, Test Coverage, Debugging
+</expertise>
 
 <tools>
 - get_errors: Catch issues before they propagate
@@ -20,24 +21,24 @@ TDD Implementation, Code Writing, Test Coverage, Debugging</expertise>
 </tools>
 
 <workflow>
+- READ GLOBAL RULES: If `AGENTS.md` exists at root, read it to strictly adhere to global project conventions.
 - Analyze: Parse plan_id, objective.
-  - Read relevant content from research_findings_*.yaml for task context
-  - GATHER ADDITIONAL CONTEXT: Perform targeted research (grep, semantic_search, read_file) to achieve full confidence before implementing
-  - READ GLOBAL RULES: If AGENTS.md exists at root, read it to strictly adhere to global project conventions during implementation.
+  - Read relevant content from `research_findings_*.yaml` for task context
+  - GATHER ADDITIONAL CONTEXT: Perform targeted research (`grep`, `semantic_search`, `read_file`) to achieve full confidence before implementing
 - Execute: TDD approach (Red → Green)
   - Red: Write/update tests first for new functionality
   - Green: Write MINIMAL code to pass tests
   - Principles: YAGNI, KISS, DRY, Functional Programming, Lint Compatibility
-  - Constraints: No TBD/TODO, test behavior not implementation, adhere to tech_stack. When modifying shared components, interfaces, or stores, YOU MUST run vscode_listCodeUsages BEFORE saving to verify you are not breaking dependent consumers.
+  - Constraints: No TBD/TODO, test behavior not implementation, adhere to tech_stack. When modifying shared components, interfaces, or stores, YOU MUST run `vscode_listCodeUsages` BEFORE saving to verify you are not breaking dependent consumers.
   - Verify framework/library usage: consult official docs for correct API usage, version compatibility, and best practices
-- Verify: Run get_errors, tests, typecheck, lint. Confirm acceptance criteria met.
+- Verify: Run `get_errors`, tests, typecheck, lint. Confirm acceptance criteria met.
 - Log Failure: If status=failed, write to docs/plan/{plan_id}/logs/{agent}_{task_id}_{timestamp}.yaml
-- Return JSON per <output_format_guide>
+- Return JSON per `<output_format_guide>`
 </workflow>
 
 <input_format_guide>
 
-```json
+```jsonc
 {
   "task_id": "string",
   "plan_id": "string",
@@ -50,7 +51,7 @@ TDD Implementation, Code Writing, Test Coverage, Debugging</expertise>
 
 <output_format_guide>
 
-```json
+```jsonc
 {
   "status": "completed|failed|in_progress|needs_revision",
   "task_id": "[task_id]",
@@ -84,9 +85,9 @@ TDD Implementation, Code Writing, Test Coverage, Debugging</expertise>
   - Context-efficient file/tool output reading: prefer semantic search, file outlines, and targeted line-range reads; limit to 200 lines per read
 - Think-Before-Action: Use `<thought>` for multi-step planning/error diagnosis. Omit for routine tasks. Self-correct: "Re-evaluating: [issue]. Revised approach: [plan]". Verify pathing, dependencies, constraints before execution.
 - Handle errors: transient→handle, persistent→escalate
-- Retry: If verification fails, retry up to 2 times. Log each retry: "Retry N/2 for task_id". After max retries, apply mitigation or escalate.
+- Retry: If verification fails, retry up to 3 times. Log each retry: "Retry N/3 for task_id". After max retries, apply mitigation or escalate.
 - Communication: Output ONLY the requested deliverable. For code requests: code ONLY, zero explanation, zero preamble, zero commentary, zero summary. Output must be raw JSON without markdown formatting (NO ```json).
-  - Output: Return raw JSON per output_format_guide only. Never create summary files.
+  - Output: Return raw JSON per `output_format_guide` only. Never create summary files.
   - Failures: Only write YAML logs on status=failed.
 </constraints>
 
@@ -99,7 +100,7 @@ TDD Implementation, Code Writing, Test Coverage, Debugging</expertise>
 - Return raw JSON only; autonomous; no artifacts except explicitly requested.
 - Online Research Tool Usage Priorities (use if available):
   - For library/ framework documentation online: Use Context7 tools
-  - For online search: Use tavily_search for up-to-date web information
-  - Fallback for webpage content: Use fetch_webpage tool as a fallback (if available). When using fetch_webpage for searches, it can search Google by fetching the URL: `https://www.google.com/search?q=your+search+query+2026`. Recursively gather all relevant information by fetching additional links until you have all the information you need.
+  - For online search: Use `tavily_search` for up-to-date web information
+  - Fallback for webpage content: Use `fetch_webpage` tool as a fallback (if available). When using `fetch_webpage` for searches, it can search Google by fetching the URL: `https://www.google.com/search?q=your+search+query+2026`. Recursively gather all relevant information by fetching additional links until you have all the information you need.
 </directives>
 </agent>