Skip to content

[codex] Add OpenAI compatibility guardrail report #987

New issue

Have a question about this project? Sign up for a free GitHub account to open an issue and contact its maintainers and the community.

Sign up for GitHub

By clicking “Sign up for GitHub”, you agree to our terms of service and privacy statement. We’ll occasionally send you account related emails.

Already on GitHub? Sign in to your account

Draft
mimeding wants to merge 1 commit into
base: main
Choose a base branch
from
+285 −194
Draft

[codex] Add OpenAI compatibility guardrail report #987

Show file tree
Hide file tree
Changes from all commits
Commits
Show all changes
1 commit
Select commit
File filter

Filter by extension

Filter by extension
Conversations
Failed to load comments.
Loading
Jump to
Jump to file
Failed to load files.
Loading
Diff view
Diff view
7 changes: 6 additions & 1 deletion Makefile
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -8,7 +8,7 @@ CONFIG := Release
PROJECT := App/osaurus.xcodeproj
DERIVED := build/DerivedData

.PHONY: help cli app install-cli serve status test ci-test clean bench-setup bench-ingest bench-ingest-chunks bench-run bench evals evals-verbose evals-report evals-all evals-all-verbose evals-all-report
.PHONY: help cli app install-cli serve status test ci-test compat-openai clean bench-setup bench-ingest bench-ingest-chunks bench-run bench evals evals-verbose evals-report evals-all evals-all-verbose evals-all-report

help:
@echo "Targets:"
Expand All @@ -30,6 +30,7 @@ help:
@echo " evals-all-report Same as 'evals-all' but writes per-suite JSON to EVALS_OUT_DIR (build/evals/)"
@echo " test Run OsaurusCore package tests via 'swift test'"
@echo " ci-test Reproduce the CI test-core job locally (xcodebuild + xcbeautify)"
@echo " compat-openai Run OpenAI Chat Completions compatibility checks against HOST/MODEL"
@echo " clean Remove DerivedData build output"

cli:
Expand Down Expand Up @@ -94,6 +95,10 @@ ci-test:
@echo ""
@echo "Done. Inspect failures with: open build/Tests.xcresult"

compat-openai:
@echo "Running OpenAI compatibility checks (HOST=$(HOST), MODEL=$(MODEL))..."
./scripts/openai_compat_report.sh

## ── LOCOMO Benchmark ──────────────────────────────────────────────

BENCH_MODEL ?= openrouter/google/gemini-2.5-flash
Expand Down
10 changes: 10 additions & 0 deletions docs/DEVELOPER_TOOLS.md
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -267,6 +267,16 @@ open build/Tests.xcresult # full Xcode Test Navigator UI

If a test fails on CI but you can't reproduce it on your machine, download the `test-core-xcresult-*` artifact attached to the failed CI run and open it the same way.

### API compatibility reports

Use the OpenAI compatibility report when changing request encoding, response writers, streaming, tool calls, or request validation:

```bash
make compat-openai HOST=http://localhost:1337 MODEL=foundation
```

The script writes a Markdown summary to `results/openai_compat_report.md` and detailed request/response artifacts under `results/openai_compat/`. Set `OUT_DIR=build/compat/openai` if you want scratch artifacts outside tracked result paths.

### Long-running and integration tests

Tests that require external infrastructure (Apple Containerization, real GPU, network, etc.) must:
Expand Down
Loading
Loading