mirror of https://github.com/garrytan/gstack.git
614354fc41
Adds the full spec Codex asked for: real provider adapters with auth detection, normalized RunResult, pricing tables, tool compatibility maps, parallel execution with error isolation, and table/JSON/markdown output. Judge stays on Anthropic SDK as the single stable source of quality scoring, gated behind --judge. Codex flagged the original plan as massively under-scoped — the existing runner is Claude-only and the judge is Anthropic-only. You can't benchmark GPT or Gemini without real provider infrastructure. This commit ships it. New architecture: test/helpers/providers/types.ts ProviderAdapter interface test/helpers/providers/claude.ts wraps `claude -p --output-format json` test/helpers/providers/gpt.ts wraps `codex exec --json` test/helpers/providers/gemini.ts wraps `gemini -p --output-format stream-json --yolo` test/helpers/pricing.ts per-model USD cost tables (quarterly) test/helpers/tool-map.ts which tools each CLI exposes test/helpers/benchmark-runner.ts orchestrator (Promise.allSettled) test/helpers/benchmark-judge.ts Anthropic SDK quality scorer bin/gstack-model-benchmark CLI entry test/benchmark-runner.test.ts 9 unit tests (cost math, formatters, tool-map) Per-provider error isolation: - auth → record reason, don't abort batch - timeout → record reason, don't abort batch - rate_limit → record reason, don't abort batch - binary_missing → record in available() check, skip if --skip-unavailable Pricing correction: cached input tokens are disjoint from uncached input tokens (Anthropic/OpenAI report them separately). Original math subtracted them, producing negative costs. Now adds cached at the 10% discount alongside the full uncached input cost. CLI: gstack-model-benchmark --prompt "..." --models claude,gpt,gemini gstack-model-benchmark ./prompt.txt --output json --judge gstack-model-benchmark ./prompt.txt --models claude --timeout-ms 60000 Output formats: table (default), json, markdown. Each shows model, latency, in→out tokens, cost, quality (when --judge used), tool calls, and any errors. Known limitations for v1: - Claude adapter approximates toolCalls as num_turns (stream-json would give exact counts; v2 can upgrade). - Live E2E tests (test/providers.e2e.test.ts) not included — they require CI secrets for all three providers. Unit tests cover the shape and math. - Provider CLIs sometimes return non-JSON error text to stdout; the parsers fall back to treating raw output as plain text in that case. Co-Authored-By: Claude Opus 4.7 (1M context) <noreply@anthropic.com> |
||
|---|---|---|
| .. | ||
| chrome-cdp | ||
| dev-setup | ||
| dev-teardown | ||
| gstack-analytics | ||
| gstack-builder-profile | ||
| gstack-community-dashboard | ||
| gstack-config | ||
| gstack-diff-scope | ||
| gstack-extension | ||
| gstack-global-discover.ts | ||
| gstack-learnings-log | ||
| gstack-learnings-search | ||
| gstack-model-benchmark | ||
| gstack-open-url | ||
| gstack-patch-names | ||
| gstack-platform-detect | ||
| gstack-relink | ||
| gstack-repo-mode | ||
| gstack-review-log | ||
| gstack-review-read | ||
| gstack-session-update | ||
| gstack-settings-hook | ||
| gstack-slug | ||
| gstack-specialist-stats | ||
| gstack-taste-update | ||
| gstack-team-init | ||
| gstack-telemetry-log | ||
| gstack-telemetry-sync | ||
| gstack-timeline-log | ||
| gstack-timeline-read | ||
| gstack-uninstall | ||
| gstack-update-check | ||