Exec Report row adder
Read this first — capture is ALREADY automatic (2026-06-07). EVERY wrapped
chat_agent_*is captured by_resolve_exec_report_specwith no code at all, observational/output and read-only agents INCLUDED. This procedure is an OPTIONAL refinement: use it only to merge a sharedagent_key(a direct@tool+ its wrapped launch), fix the display casing, or give the table a CSS-matched caption gradient. A missing entry does NOT hide an agent.And it never sets the row's colour. SUCCESS/FAILED is decided by
agent/agent_verdict.pyfrom the agent's OWNINI_SECTIONself-report, which OUTRANKS the process exit code. Its CLOSED vocabulary has five disjoint sets: diagnostic-completed and work-completed statuses are green; degraded, work-not-done, and agent-error statuses are red. A completed read-only diagnostic must stillsys.exit(0). Never write a numeric return code instatus:; emitreturncode,success, and a semantic status token. Never add a special case tomcp_agent.pyor re-inline any vocabulary set — there is exactly ONE definition inagent_verdict.py, guarded byagent/test_status_vocabulary.py.
Three-step procedure (matches docs/claude/exec-report.md):
Add an entry to
_EXEC_REPORT_TOOLSinTlamatini/agent/mcp_agent.py:"${input.tool_name}": ("${input.agent_key}", "${input.agent_display}"),Add CSS rules in
agent_page.css:.exec-report-caption-${input.agent_key}(gradient mirroring.canvas-item.${input.agent_key}-agentfrom agentic_control_panel.css).exec-report-${input.agent_key} .exec-report-cmd { border-left: 3px solid <primary>; }- If the caption is dark, append
.exec-report-${input.agent_key} thead thto the dark-tinted override selector list.
Run
python Tlamatini/manage.py test agent.tests.ExecReportCaptureTests agent.test_agent_verdict agent.test_exec_report_verdict agent.test_status_vocabulary. Report the pass/fail status. If the verdict/colour logic was touched at all, also runagent.test_agent_verdictandagent.test_exec_report_verdict.
Return { rows_added, tests_pass }.