Skip to content

[deep-report] Daily Compiler Quality discussion body is literal "test" placeholder (2-day regression) #31039

@github-actions

Description

@github-actions

Problem

The daily-compiler-quality workflow has been creating discussions whose body is just the string test for at least 2 consecutive days:

The agent runs to completion (no errors) but its create_discussion payload is the placeholder used during prompt iteration.

Suggested Fix

Check .github/workflows/daily-compiler-quality.md for a leftover "test" placeholder in the prompt or create_discussion step, and replace it with the real report-rendering instructions. Add a guard that fails the safe_outputs job if the discussion body length is below a sensible floor (say, 200 chars).

Suggested Agent

agentic-workflows sub-agent — small, surgical edit to a single workflow markdown file plus recompile.

Estimated Effort

< 30 minutes.

Source

DeepReport Intelligence Briefing — 2026-05-08. Reference run: §25535221110.

Generated by DeepReport - Intelligence Gathering Agent · ● 18.1M ·

  • expires on May 10, 2026, 3:20 PM UTC

Metadata

Metadata

Type

No type
No fields configured for issues without a type.

Projects

No projects

Milestone

No milestone

Relationships

None yet

Development

No branches or pull requests

Issue actions