fix(workflow): use gpt-5.4-mini and raise max-ai-credits for copilot-token-usage-analyzer#4877
Conversation
…x-ai-credits to 2500
✅ Coverage Check PassedOverall Coverage
📁 Per-file Coverage Changes (1 files)
Coverage comparison generated by |
There was a problem hiding this comment.
Pull request overview
This PR updates the daily Copilot token usage analyzer workflow to use a cheaper Copilot model (gpt-5.4-mini) and increases the AI-credits budget to avoid prematurely tripping the workflow’s max-ai-credits guardrail during larger analyses.
Changes:
- Pin Copilot engine model to
gpt-5.4-miniin the source.mdworkflow definition. - Raise workflow
max-ai-creditsto2500and propagate the updated model/credits into the compiled.lock.yml. - Update the compiled lock workflow’s environment/config wiring to reflect the pinned model and higher max credits.
Show a summary per file
| File | Description |
|---|---|
.github/workflows/copilot-token-usage-analyzer.md |
Pins Copilot engine model to gpt-5.4-mini and raises max-ai-credits to 2500. |
.github/workflows/copilot-token-usage-analyzer.lock.yml |
Updates compiled workflow to use the new model and max-ai-credits, but currently appears to miss required repo post-processing conventions for lock files. |
Copilot's findings
Tip
Add Copilot custom instructions for smarter, more guided reviews. Learn how to get started.
- Files reviewed: 2/2 changed files
- Comments generated: 4
| - name: Install AWF binary | ||
| run: bash "${RUNNER_TEMP}/gh-aw/actions/install_awf_binary.sh" v0.27.2 |
This comment has been minimized.
This comment has been minimized.
This comment has been minimized.
This comment has been minimized.
This comment has been minimized.
This comment has been minimized.
This comment has been minimized.
This comment has been minimized.
This comment has been minimized.
This comment has been minimized.
This comment has been minimized.
This comment has been minimized.
Co-authored-by: Copilot Autofix powered by AI <175728472+Copilot@users.noreply.github.com>
Co-authored-by: Copilot Autofix powered by AI <175728472+Copilot@users.noreply.github.com>
Co-authored-by: Copilot Autofix powered by AI <175728472+Copilot@users.noreply.github.com>
This comment has been minimized.
This comment has been minimized.
This comment has been minimized.
This comment has been minimized.
This comment has been minimized.
This comment has been minimized.
This comment has been minimized.
This comment has been minimized.
This comment has been minimized.
This comment has been minimized.
This comment has been minimized.
This comment has been minimized.
This comment has been minimized.
This comment has been minimized.
This comment has been minimized.
This comment has been minimized.
🔥 Smoke Test Results — PASS
PR: fix(workflow): use gpt-5.4-mini and raise max-ai-credits for copilot-token-usage-analyzer
|
Smoke Test Results — Auth mode: PAT (COPILOT_GITHUB_TOKEN)
Overall: FAIL — pre-step template variables were not substituted; HTTP and file tests could not be verified. PR: "fix(workflow): use gpt-5.4-mini and raise max-ai-credits for copilot-token-usage-analyzer"
|
|
Smoke Test: Copilot BYOK (Direct Mode) ✅ PASS
Running in direct BYOK mode (
|
|
Smoke test results: Warning Firewall blocked 1 domainThe following domain was blocked by the firewall during workflow execution:
network:
allowed:
- defaults
- "registry.npmjs.org"See Network Configuration for more information.
|
|
|
🏗️ Build Test Suite Results
Overall: 8/8 ecosystems passed — ✅ PASS
|
Smoke Test: GitHub Actions Services Connectivity
Overall: FAIL
|
|
✅ fix(workflow): use gpt-5.4-mini and raise max-ai-credits for copilot-token-usage-analyzer Overall: PASS cc
|
The daily Copilot token usage analyzer was hitting its
max-ai-credits: 1000guardrail because the workflow defaulted toclaude-sonnet-4.6— a frontier model unnecessarily expensive for structured JSON analysis and report generation.Changes
copilot-token-usage-analyzer.md— pinengine.model: gpt-5.4-mini(replaces theGH_AW_DEFAULT_MODEL_COPILOTfallback chain that resolved toclaude-sonnet-4.6); setmax-ai-credits: 2500to match the actual workload size (up to 50 runs + historical trend comparison)copilot-token-usage-analyzer.lock.yml— recompiled;COPILOT_MODEL,GH_AW_INFO_MODEL,maxAiCreditsin the AWF firewall config, andGH_AW_MAX_AI_CREDITSenv all updated to reflect the new values