Lazy-load Copilot agent analysis output templates

[Copilot]

The daily ambient-context optimizer flagged copilot-agent-analysis.md as the largest sampled prompt and identified duplicated output-template scaffolding from the structured/prose experiment branches. This change keeps the experiment intact while removing the inactive variant from the initial prompt surface.

• Prompt surface reduction

  • Replaced inline output_format variant templates in copilot-agent-analysis.md with conditional runtime imports.
  • Only the active experiment branch now loads its full report template at runtime.

• Shared template extraction

  • Added:
    • shared/copilot-agent-analysis-structured-output.md
    • shared/copilot-agent-analysis-prose-output.md
  • Moved the existing variant-specific discussion body instructions into those shared fragments without changing their content.

• Generated workflow sync

  • Recompiled copilot-agent-analysis.lock.yml to reflect the new prompt composition.

{{#if experiments.output_format == 'structured' }}
{{#runtime-import? shared/copilot-agent-analysis-structured-output.md}}
{{/if}}
{{#if experiments.output_format == 'prose' }}
{{#runtime-import? shared/copilot-agent-analysis-prose-output.md}}
{{/if}}

• Fixes [ambient-context] Daily Ambient Context Optimizer - 2026-07-31 #49401

[pelikhan]

@copilot use inlined skills instead and update instructions about runtime-imports which are done before execution so the current fix is not helping

[Copilot]

@copilot use inlined skills instead and update instructions about runtime-imports which are done before execution so the current fix is not helping

Addressed in eac1656.

I replaced the runtime-import? split with inline ## skill: blocks in /home/runner/work/gh-aw/gh-aw/.github/workflows/copilot-agent-analysis.md, removed the temporary shared fragments, and updated the workflow docs to state that runtime-import? resolves before the first agent turn and does not reduce the initial prompt surface.

[github-actions]

PR Triage

• Category: chore (lazy-load Copilot agent analysis templates)
• Risk: low (docs + lock file regeneration only)
• Priority score: 30/100 (impact 15, urgency 5, quality 10)
• Mergeable state: draft, unstable
• Recommended action: defer - low-value, still draft

Generated by 🔧 PR Triage Agent · auto · 44.8 AIC · ⌖ 5.88 AIC · ⊞ 7.9K · ◷