Reduce Copilot token analyzer prompt verbosity to avoid max-ai-credits trips (#4944)

* Initial plan

* Reduce copilot token analyzer report verbosity to avoid AI credit cap

* Add negative assertion for old verbose section header

Ensures the old '## Per-Workflow Details' header cannot be accidentally
reintroduced alongside the new compact '<summary>' version.

Co-authored-by: Copilot <223556219+Copilot@users.noreply.github.com>

---------

Co-authored-by: copilot-swe-agent[bot] <198982749+Copilot@users.noreply.github.com>
Co-authored-by: Landon Cox <landon.cox@microsoft.com>
Co-authored-by: Copilot <223556219+Copilot@users.noreply.github.com>

Author: 3 people

.github/workflows/copilot-token-usage-analyzer.md

@@ -207,7 +207,7 @@ Create an issue with the following structure:
 2. ...
 
 <details>
-<summary><b>Per-Workflow Details</b></summary>
+<summary><b>Top Per-Workflow Details</b></summary>
 
 #### smoke-copilot
 - **Runs**: 3 (links to each run)
@@ -241,4 +241,6 @@ Runs where `token_usage` was null or 0 \u2014 these may not have the api-proxy e
 - **All data is pre-downloaded** \u2014 do not attempt to download artifacts or run `gh run download`. Use only the JSON at `/tmp/gh-aw/token-audit/copilot-logs.json`.
 - **Wrap verbose output** in `<details>` blocks for progressive disclosure.
 - **Round costs** to 2 decimal places, token counts to nearest thousand for readability.
-- **Sort workflows** by estimated cost (highest first) in the summary table.
+- **Sort workflows** by estimated cost (highest first) in the summary table.
+- **Keep output compact**: include detailed bullets for at most the top 10 workflows by token usage; keep remaining workflows in the summary table only.
+- **Avoid verbose rewrites**: if output size is high, trim detail instead of repeatedly reformatting the full report.

scripts/ci/copilot-token-usage-analyzer-workflow.test.ts

@@ -0,0 +1,16 @@
+import * as fs from 'fs';
+import * as path from 'path';
+
+const workflowsDir = path.resolve(__dirname, '../../.github/workflows');
+const sourcePath = path.join(workflowsDir, 'copilot-token-usage-analyzer.md');
+
+describe('copilot token usage analyzer workflow prompt', () => {
+  it('includes explicit compact-output guardrails to reduce AI credit usage', () => {
+    const source = fs.readFileSync(sourcePath, 'utf-8');
+
+    expect(source).toContain('<summary><b>Top Per-Workflow Details</b></summary>');
+    expect(source).not.toMatch(/^##.*Per-Workflow Details/m);
+    expect(source).toContain('include detailed bullets for at most the top 10 workflows by token usage');
+    expect(source).toContain('if output size is high, trim detail instead of repeatedly reformatting the full report');
+  });
+});