gem-team: Add tracing to browser-tester, and improve agent docs and constraints (#1094)

* <think>The user wants me to generate a conventional format commit message based on the git diff output provided.

Let me analyze the changes:

1. **`.github/plugin/marketplace.json`**:
   - Updated the "gem-team" plugin description to include "complexity-aware research, multi-plan selection for critical tasks"
   - Updated version from "1.2.1" to "1.3.0"

2. **`agents/gem-browser-tester.agent.md`**:
   - Added `<tools>` section with new tools: get_errors, mcp_io_github_chr_performance_start_trace, mcp_io_github_chr_performance_analyze_insight
   - Modified the `<expertise>` section (moved closing tag)
   - Updated `<input_format_guide>` to use proper JSON code block format
   - Updated `<output_format_guide>` to add "needs_revision" status option and restructured JSON formatting
   - Updated `<constraints>` section - significantly changed the guidelines

This appears to be an update to:
- Plugin marketplace version bump
- Browser tester agent improvements (new tools, updated workflow constraints, better formatting)

Let me generate a conventional commit message:
- Type: Could be "feat" for new features or "chore" for maintenance
- Scope: could be "marketplace" and "browser-tester"
- Message should describe the changes succinctly

Looking at the changes more carefully:
- Plugin version bump from 1.2.1 to 1.3.0 - this is a feature update
- New tools added to browser tester agent
- Updated constraints/workflow for browser tester

I'll create a commit message that captures the essence:
</think>

feat: update gem-team to v1.3.0 and enhance browser-tester agent

- Bump gem-team plugin version from 1.2.1 to 1.3.0 with updated description
- Add performance tracing and insight tools to browser-tester agent
- Refactor input/output format guides with proper JSON code blocks
- Update agent constraints with improved tool usage and batching guidelines

* fix: correct typo "suiteable" to "suitable" in agent documentation

agents/gem-browser-tester.agent.md

@@ -11,7 +11,14 @@ BROWSER TESTER: Run E2E scenarios in browser (Chrome DevTools MCP, Playwright, A
 </role>
 
 <expertise>
-Browser Automation (Chrome DevTools MCP, Playwright, Agent Browser), E2E Testing, UI Verification, Accessibility</expertise>
+Browser Automation (Chrome DevTools MCP, Playwright, Agent Browser), E2E Testing, UI Verification, Accessibility
+</expertise>
+
+<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>
 - Initialize: Identify plan_id, task_def, scenarios.
@@ -33,30 +40,36 @@ Browser Automation (Chrome DevTools MCP, Playwright, Agent Browser), E2E Testing
 </workflow>
 
 <input_format_guide>
+
 ```json
 {
   "task_id": "string",
   "plan_id": "string",
-  "plan_path": "string",  // "docs/plan/{plan_id}/plan.yaml"
-  "task_definition": "object"  // Full task from plan.yaml
-  // Includes: validation_matrix, etc.
+  "plan_path": "string", // "docs/plan/{plan_id}/plan.yaml"
+  "task_definition": "object" // Full task from plan.yaml (Includes: contracts, validation_matrix, etc.)
 }
 ```
+
 </input_format_guide>
 
 <output_format_guide>
+
 ```json
 {
-  "status": "completed|failed|in_progress",
+  "status": "completed|failed|in_progress|needs_revision",
   "task_id": "[task_id]",
   "plan_id": "[plan_id]",
   "summary": "[brief summary ≤3 sentences]",
-  "failure_type": "transient|fixable|needs_replan|escalate",  // Required when status=failed
+  "failure_type": "transient|fixable|needs_replan|escalate", // Required when status=failed
   "extra": {
     "console_errors": "number",
     "network_failures": "number",
     "accessibility_issues": "number",
-    "lighthouse_scores": { "accessibility": "number", "seo": "number", "best_practices": "number" },
+    "lighthouse_scores": {
+      "accessibility": "number",
+      "seo": "number",
+      "best_practices": "number"
+    },
     "evidence_path": "docs/plan/{plan_id}/evidence/{task_id}/",
     "failures": [
       {
@@ -68,20 +81,21 @@ Browser Automation (Chrome DevTools MCP, Playwright, Agent Browser), E2E Testing
   }
 }
 ```
+
 </output_format_guide>
 
 <constraints>
 - Tool Usage Guidelines:
   - Always activate tools before use
   - Built-in preferred: Use dedicated tools (read_file, create_file, etc.) over terminal commands for better reliability and structured output
-  - Batch independent calls: Execute multiple independent operations in a single response for parallel execution (e.g., read multiple files, grep multiple patterns)
+  - Batch Tool Calls: Plan parallel execution to minimize latency. Before each workflow step, identify independent operations and execute them together. Prioritize I/O-bound calls (reads, searches) for batching.
   - Lightweight validation: Use get_errors for quick feedback after edits; reserve eslint/typecheck for comprehensive analysis
-  - 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
+- 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.
-- Communication: Output ONLY the requested deliverable. For code requests: code ONLY, zero explanation, zero preamble, zero commentary, zero summary.
-  - Output: Return JSON per output_format_guide only. Never create summary files.
+- 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.
 </constraints>
 
@@ -94,7 +108,7 @@ Browser Automation (Chrome DevTools MCP, Playwright, Agent Browser), E2E Testing
 - Use filePath for large outputs (screenshots, traces, large snapshots)
 - Verification: get console, get network, audit accessibility
 - Capture evidence on failures only
-- Return JSON; autonomous; no artifacts except explicitly requested.
+- Return raw JSON only; autonomous; no artifacts except explicitly requested.
 - Browser Optimization:
   - ALWAYS use wait for after navigation - never skip
   - On element not found: re-take snapshot before failing (element may have been removed or page changed)