@hassangameryt/freeflow 0.1.0 → 0.3.0
This diff represents the content of publicly available package versions that have been released to one of the supported registries. The information contained in this diff is provided for informational purposes only and reflects changes between package versions as they appear in their respective public registries.
- package/.agents/plugins/marketplace.json +1 -1
- package/.claude-plugin/marketplace.json +2 -2
- package/{plugins/freeflow/.claude-plugin → .claude-plugin}/plugin.json +1 -1
- package/{plugins/freeflow/.codex-plugin → .codex-plugin}/plugin.json +1 -1
- package/README.md +25 -16
- package/assets/freeflow-plugin-icon.png +0 -0
- package/{plugins/freeflow/command-surface.json → command-surface.json} +10 -10
- package/evals/README.md +32 -0
- package/evals/fixtures/copy-conventions.md +31 -0
- package/evals/fixtures/output-router/README.md +12 -0
- package/evals/fixtures/output-router/failed-command-output.txt +9 -0
- package/evals/fixtures/output-router/large-router-manual.md +63 -0
- package/evals/fixtures/output-router/native-large-output.txt +40 -0
- package/evals/fixtures/output-router/noisy-test-output.txt +30 -0
- package/evals/fixtures/output-router/verification-output.txt +8 -0
- package/evals/fixtures/tiny-artifact-review-app/README.md +5 -0
- package/evals/fixtures/tiny-artifact-review-app/docs/billing-policy.md +10 -0
- package/evals/fixtures/tiny-artifact-review-app/docs/specs/billing-webhook-api-draft.md +21 -0
- package/evals/fixtures/tiny-artifact-review-app/docs/specs/failed-payment-grace-period.md +24 -0
- package/evals/fixtures/tiny-artifact-review-app/docs/specs/immediate-downgrade.md +17 -0
- package/evals/fixtures/tiny-artifact-review-app/tests/billing.test.md +8 -0
- package/evals/fixtures/tiny-commit-ambiguous-app/.freeflow-eval-setup.sh +15 -0
- package/evals/fixtures/tiny-commit-ambiguous-app/README.md +3 -0
- package/evals/fixtures/tiny-commit-ambiguous-app/src/billing.ts +5 -0
- package/evals/fixtures/tiny-commit-ambiguous-app/src/settings-page.ts +1 -0
- package/evals/fixtures/tiny-commit-ambiguous-app/tests/settings.test.md +5 -0
- package/evals/fixtures/tiny-commit-app/.freeflow-eval-setup.sh +14 -0
- package/evals/fixtures/tiny-commit-app/README.md +3 -0
- package/evals/fixtures/tiny-commit-app/docs/specs/settings-title.md +5 -0
- package/evals/fixtures/tiny-commit-app/src/billing.ts +5 -0
- package/evals/fixtures/tiny-commit-app/src/settings-page.ts +1 -0
- package/evals/fixtures/tiny-commit-app/tests/settings.test.md +5 -0
- package/evals/fixtures/tiny-commit-everything-app/.freeflow-eval-setup.sh +15 -0
- package/evals/fixtures/tiny-commit-everything-app/README.md +3 -0
- package/evals/fixtures/tiny-commit-everything-app/docs/specs/settings-title.md +5 -0
- package/evals/fixtures/tiny-commit-everything-app/src/billing.ts +5 -0
- package/evals/fixtures/tiny-commit-everything-app/src/settings-page.ts +1 -0
- package/evals/fixtures/tiny-commit-everything-app/tests/settings.test.md +5 -0
- package/evals/fixtures/tiny-commit-staged-app/.freeflow-eval-setup.sh +15 -0
- package/evals/fixtures/tiny-commit-staged-app/README.md +3 -0
- package/evals/fixtures/tiny-commit-staged-app/docs/specs/settings-title.md +5 -0
- package/evals/fixtures/tiny-commit-staged-app/src/billing.ts +5 -0
- package/evals/fixtures/tiny-commit-staged-app/src/settings-page.ts +1 -0
- package/evals/fixtures/tiny-commit-staged-app/tests/settings.test.md +5 -0
- package/evals/fixtures/tiny-commit-staged-mixed-app/.freeflow-eval-setup.sh +15 -0
- package/evals/fixtures/tiny-commit-staged-mixed-app/README.md +3 -0
- package/evals/fixtures/tiny-commit-staged-mixed-app/docs/billing-policy.md +3 -0
- package/evals/fixtures/tiny-commit-staged-mixed-app/docs/release-notes.md +3 -0
- package/evals/fixtures/tiny-commit-staged-mixed-app/src/billing.ts +5 -0
- package/evals/fixtures/tiny-dashboard-stale-app/README.md +11 -0
- package/evals/fixtures/tiny-dashboard-stale-app/src/api-client.ts +13 -0
- package/evals/fixtures/tiny-dashboard-stale-app/src/dashboard-data.ts +19 -0
- package/evals/fixtures/tiny-dashboard-stale-app/tests/dashboard-data.test.md +9 -0
- package/evals/fixtures/tiny-decision-destination-app/README.md +6 -0
- package/evals/fixtures/tiny-decision-destination-app/src/risk.ts +8 -0
- package/evals/fixtures/tiny-decision-destination-app/tests/risk.test.md +4 -0
- package/evals/fixtures/tiny-design-depth-app/README.md +15 -0
- package/evals/fixtures/tiny-design-depth-app/src/routes.ts +25 -0
- package/evals/fixtures/tiny-design-depth-app/src/sendEmail.ts +3 -0
- package/evals/fixtures/tiny-design-depth-app/src/sendSms.ts +3 -0
- package/evals/fixtures/tiny-design-depth-app/src/telemetry.ts +3 -0
- package/evals/fixtures/tiny-design-depth-app/tests/routes.test.md +12 -0
- package/evals/fixtures/tiny-eval-method-app/README.md +8 -0
- package/evals/fixtures/tiny-eval-method-app/evals/reports/review-pr-eval-result.md +5 -0
- package/evals/fixtures/tiny-eval-method-app/evals/reports/triage-question-failure.md +17 -0
- package/evals/fixtures/tiny-eval-method-app/evals/runs/review-pr-with-skill-output.diff +11 -0
- package/evals/fixtures/tiny-eval-method-app/evals/runs/review-pr-with-skill-output.md +3 -0
- package/evals/fixtures/tiny-eval-method-app/skills/review-pr/SKILL.md +10 -0
- package/evals/fixtures/tiny-eval-method-app/skills/triage-question/SKILL.md +10 -0
- package/evals/fixtures/tiny-execute-plan-app/README.md +5 -0
- package/evals/fixtures/tiny-execute-plan-app/checks/settings-and-billing-check.sh +5 -0
- package/evals/fixtures/tiny-execute-plan-app/docs/billing-policy.md +10 -0
- package/evals/fixtures/tiny-execute-plan-app/docs/plans/immediate-downgrade-plan.md +11 -0
- package/evals/fixtures/tiny-execute-plan-app/docs/plans/settings-title-plan.md +12 -0
- package/evals/fixtures/tiny-execute-plan-app/docs/plans/settings-title-with-bad-check.md +15 -0
- package/evals/fixtures/tiny-execute-plan-app/docs/plans/unverified-billing-plan.md +9 -0
- package/evals/fixtures/tiny-execute-plan-app/docs/specs/failed-payment-grace-period.md +9 -0
- package/evals/fixtures/tiny-execute-plan-app/docs/specs/settings-title.md +9 -0
- package/evals/fixtures/tiny-execute-plan-app/src/billing.ts +7 -0
- package/evals/fixtures/tiny-execute-plan-app/src/settings-page.ts +1 -0
- package/evals/fixtures/tiny-execute-plan-app/tests/billing.test.md +7 -0
- package/evals/fixtures/tiny-execute-plan-app/tests/settings.test.md +5 -0
- package/evals/fixtures/tiny-execute-review-loop-app/README.md +5 -0
- package/evals/fixtures/tiny-execute-review-loop-app/docs/billing-policy.md +9 -0
- package/evals/fixtures/tiny-execute-review-loop-app/docs/plans/settings-title-plan.md +12 -0
- package/evals/fixtures/tiny-execute-review-loop-app/docs/review/previous-agent-summary.md +15 -0
- package/evals/fixtures/tiny-execute-review-loop-app/docs/review/review-pass-1-non-pass.md +11 -0
- package/evals/fixtures/tiny-execute-review-loop-app/docs/specs/settings-title.md +9 -0
- package/evals/fixtures/tiny-execute-review-loop-app/src/billing.ts +7 -0
- package/evals/fixtures/tiny-execute-review-loop-app/src/settings-page.ts +1 -0
- package/evals/fixtures/tiny-execute-review-loop-app/tests/billing.test.md +7 -0
- package/evals/fixtures/tiny-execute-review-loop-app/tests/settings.test.md +5 -0
- package/evals/fixtures/tiny-flaky-session-app/README.md +10 -0
- package/evals/fixtures/tiny-flaky-session-app/src/session-timeout.ts +13 -0
- package/evals/fixtures/tiny-flaky-session-app/tests/session-timeout.test.md +8 -0
- package/evals/fixtures/tiny-handoff-app/README.md +5 -0
- package/evals/fixtures/tiny-handoff-app/docs/billing-policy.md +10 -0
- package/evals/fixtures/tiny-handoff-app/docs/handoffs/old-agent-handoff.md +8 -0
- package/evals/fixtures/tiny-handoff-app/docs/plans/billing-retry-plan.md +11 -0
- package/evals/fixtures/tiny-handoff-app/src/billing.ts +7 -0
- package/evals/fixtures/tiny-handoff-report-app/README.md +3 -0
- package/evals/fixtures/tiny-handoff-report-app/evals/runs/handoff-3/hof-003/with-skill-output.diff +1 -0
- package/evals/fixtures/tiny-handoff-report-app/evals/runs/handoff-3/hof-003/with-skill-output.md +1 -0
- package/evals/fixtures/tiny-handoff-report-app/evals/scores/hof-003-score.txt +4 -0
- package/evals/fixtures/tiny-plan-app/README.md +5 -0
- package/evals/fixtures/tiny-plan-app/docs/billing-policy.md +10 -0
- package/evals/fixtures/tiny-plan-app/docs/specs/failed-payment-grace-period.md +25 -0
- package/evals/fixtures/tiny-plan-app/src/billing.ts +17 -0
- package/evals/fixtures/tiny-plan-app/src/settings-page.ts +1 -0
- package/evals/fixtures/tiny-plan-app/tests/billing.test.md +8 -0
- package/evals/fixtures/tiny-plan-app/tests/settings.test.md +5 -0
- package/evals/fixtures/tiny-plan-strict-api-app/README.md +3 -0
- package/evals/fixtures/tiny-plan-strict-api-app/docs/billing-policy.md +5 -0
- package/evals/fixtures/tiny-plan-strict-api-app/docs/specs/billing-webhook-api.md +25 -0
- package/evals/fixtures/tiny-plan-strict-api-app/src/billing.ts +5 -0
- package/evals/fixtures/tiny-plan-strict-api-app/src/webhooks.ts +3 -0
- package/evals/fixtures/tiny-plan-strict-api-app/tests/billing-webhook.test.md +8 -0
- package/evals/fixtures/tiny-post-setup-invalid-config-app/.freeflow/config.json +3 -0
- package/evals/fixtures/tiny-post-setup-invalid-config-app/AGENTS.md +15 -0
- package/evals/fixtures/tiny-post-setup-invalid-config-app/README.md +16 -0
- package/evals/fixtures/tiny-post-setup-invalid-config-app/docs/auth-review.md +15 -0
- package/evals/fixtures/tiny-post-setup-invalid-config-app/docs/billing-policy.md +10 -0
- package/evals/fixtures/tiny-post-setup-invalid-config-app/docs/copy-conventions.md +15 -0
- package/evals/fixtures/tiny-post-setup-invalid-config-app/src/auth-middleware.ts +12 -0
- package/evals/fixtures/tiny-post-setup-invalid-config-app/src/billing.ts +20 -0
- package/evals/fixtures/tiny-post-setup-invalid-config-app/src/login-copy.ts +1 -0
- package/evals/fixtures/tiny-post-setup-invalid-config-app/src/settings-page.ts +1 -0
- package/evals/fixtures/tiny-post-setup-invalid-config-app/tests/auth-middleware.test.md +8 -0
- package/evals/fixtures/tiny-post-setup-invalid-config-app/tests/billing.test.md +8 -0
- package/evals/fixtures/tiny-post-setup-invalid-config-app/tests/copy.test.md +7 -0
- package/evals/fixtures/tiny-post-setup-missing-config-app/AGENTS.md +15 -0
- package/evals/fixtures/tiny-post-setup-missing-config-app/README.md +16 -0
- package/evals/fixtures/tiny-post-setup-missing-config-app/docs/auth-review.md +15 -0
- package/evals/fixtures/tiny-post-setup-missing-config-app/docs/billing-policy.md +10 -0
- package/evals/fixtures/tiny-post-setup-missing-config-app/docs/copy-conventions.md +15 -0
- package/evals/fixtures/tiny-post-setup-missing-config-app/src/auth-middleware.ts +12 -0
- package/evals/fixtures/tiny-post-setup-missing-config-app/src/billing.ts +20 -0
- package/evals/fixtures/tiny-post-setup-missing-config-app/src/login-copy.ts +1 -0
- package/evals/fixtures/tiny-post-setup-missing-config-app/src/settings-page.ts +1 -0
- package/evals/fixtures/tiny-post-setup-missing-config-app/tests/auth-middleware.test.md +8 -0
- package/evals/fixtures/tiny-post-setup-missing-config-app/tests/billing.test.md +8 -0
- package/evals/fixtures/tiny-post-setup-missing-config-app/tests/copy.test.md +7 -0
- package/evals/fixtures/tiny-post-setup-source-conflict-app/.freeflow/config.json +3 -0
- package/evals/fixtures/tiny-post-setup-source-conflict-app/AGENTS.md +15 -0
- package/evals/fixtures/tiny-post-setup-source-conflict-app/README.md +16 -0
- package/evals/fixtures/tiny-post-setup-source-conflict-app/docs/auth-review.md +15 -0
- package/evals/fixtures/tiny-post-setup-source-conflict-app/docs/billing-policy.md +10 -0
- package/evals/fixtures/tiny-post-setup-source-conflict-app/docs/copy-conventions.md +15 -0
- package/evals/fixtures/tiny-post-setup-source-conflict-app/src/auth-middleware.ts +12 -0
- package/evals/fixtures/tiny-post-setup-source-conflict-app/src/billing.ts +20 -0
- package/evals/fixtures/tiny-post-setup-source-conflict-app/src/login-copy.ts +1 -0
- package/evals/fixtures/tiny-post-setup-source-conflict-app/src/settings-page.ts +1 -0
- package/evals/fixtures/tiny-post-setup-source-conflict-app/tests/auth-middleware.test.md +8 -0
- package/evals/fixtures/tiny-post-setup-source-conflict-app/tests/billing.test.md +8 -0
- package/evals/fixtures/tiny-post-setup-source-conflict-app/tests/copy.test.md +7 -0
- package/evals/fixtures/tiny-report-performance-app/README.md +11 -0
- package/evals/fixtures/tiny-report-performance-app/docs/performance.md +10 -0
- package/evals/fixtures/tiny-report-performance-app/src/report-summary.ts +29 -0
- package/evals/fixtures/tiny-report-performance-app/tests/report-performance.test.md +8 -0
- package/evals/fixtures/tiny-review-request-app/README.md +3 -0
- package/evals/fixtures/tiny-review-request-app/docs/billing-policy.md +5 -0
- package/evals/fixtures/tiny-review-request-app/docs/plans/billing-webhook-api.md +19 -0
- package/evals/fixtures/tiny-review-request-app/docs/review/previous-agent-summary.md +20 -0
- package/evals/fixtures/tiny-review-request-app/docs/specs/billing-webhook-api.md +25 -0
- package/evals/fixtures/tiny-review-request-app/src/billing.ts +11 -0
- package/evals/fixtures/tiny-review-request-app/src/webhooks.ts +19 -0
- package/evals/fixtures/tiny-review-request-app/tests/billing-webhook.test.md +8 -0
- package/evals/fixtures/tiny-review-work-app/README.md +5 -0
- package/evals/fixtures/tiny-review-work-app/docs/billing-policy.md +9 -0
- package/evals/fixtures/tiny-review-work-app/docs/plans/settings-title-plan.md +12 -0
- package/evals/fixtures/tiny-review-work-app/docs/review/previous-agent-summary.md +15 -0
- package/evals/fixtures/tiny-review-work-app/docs/specs/settings-title.md +9 -0
- package/evals/fixtures/tiny-review-work-app/src/billing.ts +7 -0
- package/evals/fixtures/tiny-review-work-app/src/settings-page.ts +1 -0
- package/evals/fixtures/tiny-review-work-app/tests/billing.test.md +7 -0
- package/evals/fixtures/tiny-review-work-app/tests/settings.test.md +5 -0
- package/evals/fixtures/tiny-saas-app/README.md +16 -0
- package/evals/fixtures/tiny-saas-app/docs/auth-review.md +15 -0
- package/evals/fixtures/tiny-saas-app/docs/billing-policy.md +10 -0
- package/evals/fixtures/tiny-saas-app/docs/copy-conventions.md +15 -0
- package/evals/fixtures/tiny-saas-app/docs/specs/settings-title.md +13 -0
- package/evals/fixtures/tiny-saas-app/src/auth-middleware.ts +12 -0
- package/evals/fixtures/tiny-saas-app/src/billing.ts +20 -0
- package/evals/fixtures/tiny-saas-app/src/login-copy.ts +1 -0
- package/evals/fixtures/tiny-saas-app/src/settings-page.ts +1 -0
- package/evals/fixtures/tiny-saas-app/tests/auth-middleware.test.md +8 -0
- package/evals/fixtures/tiny-saas-app/tests/billing.test.md +8 -0
- package/evals/fixtures/tiny-saas-app/tests/copy.test.md +7 -0
- package/evals/fixtures/tiny-setup-agents-app/AGENTS.md +6 -0
- package/evals/fixtures/tiny-setup-both-app/AGENTS.md +5 -0
- package/evals/fixtures/tiny-setup-both-app/CLAUDE.md +5 -0
- package/evals/fixtures/tiny-setup-claude-app/CLAUDE.md +6 -0
- package/evals/fixtures/tiny-setup-codex-rules-app/.codex/rules/shell.rules +5 -0
- package/evals/fixtures/tiny-setup-codex-rules-app/AGENTS.md +6 -0
- package/evals/fixtures/tiny-setup-conflict-app/AGENTS.md +6 -0
- package/evals/fixtures/tiny-setup-existing-block-app/AGENTS.md +14 -0
- package/evals/fixtures/tiny-setup-four-rules-app/CLAUDE.md +6 -0
- package/evals/fixtures/tiny-skill-dev-app/README.md +10 -0
- package/evals/fixtures/tiny-skill-dev-app/evals/prompts/review-pr-001.txt +8 -0
- package/evals/fixtures/tiny-skill-dev-app/evals/reports/review-pr-failure.md +17 -0
- package/evals/fixtures/tiny-skill-dev-app/skills/review-pr/SKILL.md +13 -0
- package/evals/fixtures/tiny-team-app/README.md +5 -0
- package/evals/fixtures/tiny-team-app/docs/product.md +6 -0
- package/evals/fixtures/tiny-team-app/src/teams.ts +9 -0
- package/evals/fixtures/tiny-team-app/src/users.ts +5 -0
- package/evals/fixtures/tiny-team-app/tests/teams.test.md +7 -0
- package/evals/fixtures/tiny-verify-app/README.md +5 -0
- package/evals/fixtures/tiny-verify-app/src/settings-nav.ts +1 -0
- package/evals/fixtures/tiny-verify-app/src/settings-page.ts +1 -0
- package/evals/fixtures/tiny-verify-app/tests/settings.test.md +7 -0
- package/evals/prompts/aon-001.txt +2 -0
- package/evals/prompts/byp-001.txt +2 -0
- package/evals/prompts/byp-002.txt +2 -0
- package/evals/prompts/cap-001.txt +3 -0
- package/evals/prompts/cap-002.txt +3 -0
- package/evals/prompts/cmd-001.txt +3 -0
- package/evals/prompts/cmd-002.txt +3 -0
- package/evals/prompts/cmd-003.txt +6 -0
- package/evals/prompts/cmd-004.txt +5 -0
- package/evals/prompts/cmd-005.txt +5 -0
- package/evals/prompts/cmd-006.txt +5 -0
- package/evals/prompts/cmd-007.txt +5 -0
- package/evals/prompts/cmd-008.txt +5 -0
- package/evals/prompts/cmd-009.txt +8 -0
- package/evals/prompts/cmd-010.txt +5 -0
- package/evals/prompts/cmd-011.txt +5 -0
- package/evals/prompts/cmd-012.txt +5 -0
- package/evals/prompts/cmd-013.txt +5 -0
- package/evals/prompts/cmd-014.txt +7 -0
- package/evals/prompts/cmd-015.txt +7 -0
- package/evals/prompts/cmd-016.txt +5 -0
- package/evals/prompts/cmt-001.txt +1 -0
- package/evals/prompts/cmt-002.txt +1 -0
- package/evals/prompts/cmt-003.txt +1 -0
- package/evals/prompts/cmt-004.txt +1 -0
- package/evals/prompts/cmt-005.txt +1 -0
- package/evals/prompts/dfd-001.txt +3 -0
- package/evals/prompts/dia-001.txt +3 -0
- package/evals/prompts/dia-002.txt +3 -0
- package/evals/prompts/dia-003.txt +3 -0
- package/evals/prompts/dis-001.txt +5 -0
- package/evals/prompts/dis-002.txt +5 -0
- package/evals/prompts/esk-001.txt +5 -0
- package/evals/prompts/esk-002.txt +5 -0
- package/evals/prompts/esk-003.txt +5 -0
- package/evals/prompts/grc-001.txt +3 -0
- package/evals/prompts/hof-001.txt +3 -0
- package/evals/prompts/hof-002.txt +1 -0
- package/evals/prompts/hof-003.txt +1 -0
- package/evals/prompts/hof-004.txt +1 -0
- package/evals/prompts/hof-005.txt +1 -0
- package/evals/prompts/ivg-001.txt +1 -0
- package/evals/prompts/ivg-002.txt +11 -0
- package/evals/prompts/ivg-003.txt +1 -0
- package/evals/prompts/ivg-004.txt +1 -0
- package/evals/prompts/mode-001.txt +3 -0
- package/evals/prompts/mode-002.txt +1 -0
- package/evals/prompts/mode-003.txt +3 -0
- package/evals/prompts/mode-004.txt +3 -0
- package/evals/prompts/mode-005.txt +3 -0
- package/evals/prompts/mode-006.txt +3 -0
- package/evals/prompts/mode-007.txt +3 -0
- package/evals/prompts/otr-001.txt +3 -0
- package/evals/prompts/otr-002.txt +3 -0
- package/evals/prompts/rar-001.txt +5 -0
- package/evals/prompts/rar-002.txt +3 -0
- package/evals/prompts/rar-003.txt +6 -0
- package/evals/prompts/rar-004.txt +15 -0
- package/evals/prompts/rar-005.txt +10 -0
- package/evals/prompts/rbr-001.txt +3 -0
- package/evals/prompts/rbr-002.txt +3 -0
- package/evals/prompts/rbr-003.txt +7 -0
- package/evals/prompts/rev-001.txt +3 -0
- package/evals/prompts/rev-002.txt +5 -0
- package/evals/prompts/rev-003.txt +6 -0
- package/evals/prompts/rev-004.txt +1 -0
- package/evals/prompts/rev-005.txt +15 -0
- package/evals/prompts/rev-006.txt +5 -0
- package/evals/prompts/stp-001.txt +1 -0
- package/evals/prompts/stp-002.txt +1 -0
- package/evals/prompts/stp-003.txt +1 -0
- package/evals/prompts/stp-004.txt +1 -0
- package/evals/prompts/stp-005.txt +1 -0
- package/evals/prompts/stp-006.txt +1 -0
- package/evals/prompts/stp-007.txt +1 -0
- package/evals/prompts/stp-008.txt +1 -0
- package/evals/prompts/stp-009.txt +1 -0
- package/evals/prompts/stp-010.txt +1 -0
- package/evals/prompts/stp-011.txt +1 -0
- package/evals/prompts/vfy-003.txt +1 -0
- package/evals/prompts/wpl-001.txt +3 -0
- package/evals/prompts/wpl-002.txt +5 -0
- package/evals/prompts/wpl-003.txt +3 -0
- package/evals/prompts/wpl-004.txt +5 -0
- package/evals/prompts/wpl-005.txt +1 -0
- package/evals/prompts/wrc-001.txt +10 -0
- package/evals/prompts/wrc-002.txt +3 -0
- package/evals/prompts/wsk-001.txt +6 -0
- package/evals/prompts/wsp-001.txt +5 -0
- package/evals/prompts/wsp-002.txt +15 -0
- package/evals/prompts/wsp-003.txt +3 -0
- package/evals/prompts/wsp-004.txt +15 -0
- package/evals/prompts/wsp-005.txt +5 -0
- package/evals/prompts/wsp-006.txt +12 -0
- package/evals/prompts/wsp-007.txt +9 -0
- package/evals/prompts/wsp-008.txt +13 -0
- package/evals/prompts/xpl-001.txt +1 -0
- package/evals/prompts/xpl-002.txt +3 -0
- package/evals/prompts/xpl-003.txt +3 -0
- package/evals/prompts/xpl-004.txt +3 -0
- package/evals/prompts/xpl-005.txt +5 -0
- package/evals/prompts/xpl-006.txt +3 -0
- package/evals/registries/adversarial-evals.json +39 -0
- package/evals/registries/fixture-evals.json +2513 -0
- package/evals/registries/handoff-evals.json +74 -0
- package/evals/registries/legacy-evals.json +147 -0
- package/evals/registries/skill-evidence.json +193 -0
- package/evals/registries/verify-work-evals.json +46 -0
- package/evals/reports/acceptance/v0.1-acceptance-report.md +130 -0
- package/evals/reports/by-command-surface/command-surface-1-report.md +45 -0
- package/evals/reports/by-command-surface/command-surface-10-report.md +76 -0
- package/evals/reports/by-command-surface/command-surface-11-report.md +77 -0
- package/evals/reports/by-command-surface/command-surface-12-report.md +91 -0
- package/evals/reports/by-command-surface/command-surface-13-report.md +64 -0
- package/evals/reports/by-command-surface/command-surface-14-report.md +66 -0
- package/evals/reports/by-command-surface/command-surface-15-report.md +124 -0
- package/evals/reports/by-command-surface/command-surface-16-report.md +39 -0
- package/evals/reports/by-command-surface/command-surface-2-report.md +80 -0
- package/evals/reports/by-command-surface/command-surface-3-report.md +86 -0
- package/evals/reports/by-command-surface/command-surface-4-report.md +76 -0
- package/evals/reports/by-command-surface/command-surface-5-report.md +80 -0
- package/evals/reports/by-command-surface/command-surface-6-report.md +74 -0
- package/evals/reports/by-command-surface/command-surface-7-report.md +84 -0
- package/evals/reports/by-command-surface/command-surface-8-report.md +79 -0
- package/evals/reports/by-command-surface/command-surface-9-report.md +79 -0
- package/evals/reports/by-command-surface/command-surface-matrix.md +91 -0
- package/evals/reports/by-skill/bypass-1-report.md +124 -0
- package/evals/reports/by-skill/capture-decisions-1-report.md +99 -0
- package/evals/reports/by-skill/capture-decisions-2-report.md +102 -0
- package/evals/reports/by-skill/commit-work-1-report.md +165 -0
- package/evals/reports/by-skill/commit-work-2-report.md +109 -0
- package/evals/reports/by-skill/design-for-depth-1-report.md +95 -0
- package/evals/reports/by-skill/diagnose-failure-1-report.md +91 -0
- package/evals/reports/by-skill/diagnose-failure-2-report.md +94 -0
- package/evals/reports/by-skill/discover-1-report.md +118 -0
- package/evals/reports/by-skill/evaluate-skill-2-report.md +71 -0
- package/evals/reports/by-skill/execute-plan-1-report.md +103 -0
- package/evals/reports/by-skill/execute-plan-2-report.md +112 -0
- package/evals/reports/by-skill/execute-plan-3-report.md +87 -0
- package/evals/reports/by-skill/grill-context-1-report.md +103 -0
- package/evals/reports/by-skill/handoff-1-report.md +123 -0
- package/evals/reports/by-skill/handoff-2-report.md +105 -0
- package/evals/reports/by-skill/handoff-3-report.md +100 -0
- package/evals/reports/by-skill/handoff-7-report.md +77 -0
- package/evals/reports/by-skill/interview-gate-1-report.md +63 -0
- package/evals/reports/by-skill/interview-gate-2-report.md +105 -0
- package/evals/reports/by-skill/mode-contract-1-report.md +74 -0
- package/evals/reports/by-skill/mode-contract-2-report.md +87 -0
- package/evals/reports/by-skill/mode-contract-3-report.md +65 -0
- package/evals/reports/by-skill/mode-contract-4-report.md +71 -0
- package/evals/reports/by-skill/mode-contract-5-report.md +70 -0
- package/evals/reports/by-skill/output-router-1-report.md +76 -0
- package/evals/reports/by-skill/output-router-2-report.md +65 -0
- package/evals/reports/by-skill/research-1-report.md +144 -0
- package/evals/reports/by-skill/research-brief-1-report.md +94 -0
- package/evals/reports/by-skill/research-brief-2-report.md +75 -0
- package/evals/reports/by-skill/review-artifact-1-report.md +91 -0
- package/evals/reports/by-skill/review-artifact-2-report.md +79 -0
- package/evals/reports/by-skill/review-artifact-3-report.md +120 -0
- package/evals/reports/by-skill/review-artifact-4-report.md +89 -0
- package/evals/reports/by-skill/review-artifact-5-report.md +66 -0
- package/evals/reports/by-skill/review-work-1-report.md +85 -0
- package/evals/reports/by-skill/review-work-2-report.md +87 -0
- package/evals/reports/by-skill/review-work-3-report.md +104 -0
- package/evals/reports/by-skill/review-work-4-report.md +108 -0
- package/evals/reports/by-skill/review-work-5-report.md +73 -0
- package/evals/reports/by-skill/review-work-6-report.md +66 -0
- package/evals/reports/by-skill/setup-freeflow-1-report.md +199 -0
- package/evals/reports/by-skill/setup-freeflow-2-report.md +105 -0
- package/evals/reports/by-skill/setup-freeflow-3-report.md +105 -0
- package/evals/reports/by-skill/setup-freeflow-4-report.md +88 -0
- package/evals/reports/by-skill/setup-freeflow-5-report.md +115 -0
- package/evals/reports/by-skill/skill-authoring-1-report.md +81 -0
- package/evals/reports/by-skill/verify-work-1-report.md +111 -0
- package/evals/reports/by-skill/verify-work-2-report.md +120 -0
- package/evals/reports/by-skill/workflow-1-report.md +65 -0
- package/evals/reports/by-skill/write-plan-1-report.md +123 -0
- package/evals/reports/by-skill/write-plan-2-report.md +98 -0
- package/evals/reports/by-skill/write-plan-3-report.md +110 -0
- package/evals/reports/by-skill/write-spec-1-report.md +88 -0
- package/evals/reports/by-skill/write-spec-2-report.md +89 -0
- package/evals/reports/by-skill/write-spec-3-report.md +90 -0
- package/evals/reports/by-skill/write-spec-4-report.md +167 -0
- package/evals/reports/harness/claude-harness-1-report.md +103 -0
- package/evals/reports/harness/eval-harness-1-report.md +91 -0
- package/evals/reports/iterations/iteration-1-report.md +71 -0
- package/evals/reports/iterations/iteration-2-report.md +78 -0
- package/evals/reports/iterations/iteration-3-report.md +118 -0
- package/evals/reports/iterations/iteration-4-report.md +131 -0
- package/evals/reports/iterations/iteration-5-report.md +149 -0
- package/evals/reports/iterations/iteration-6-report.md +136 -0
- package/evals/reports/runtime/always-on-runtime-1-report.md +107 -0
- package/evals/reports/runtime/context-mode-normalized-benchmark-1-report.md +52 -0
- package/evals/reports/runtime/context-mode-real-deep-baseline-1-report.md +410 -0
- package/evals/reports/runtime/context-mode-real-deep-final-slice-11-report.md +203 -0
- package/evals/reports/runtime/context-mode-real-deep-final-slice-11-review.md +51 -0
- package/evals/reports/runtime/context-saving-native-tools-baseline-1-report.md +99 -0
- package/evals/reports/runtime/eryx-python-compatibility-reprobe-1-report.md +166 -0
- package/evals/reports/runtime/eryx-python-proof-spike-1-report.md +96 -0
- package/evals/reports/runtime/eryx-python-proof-spike-2-report.md +151 -0
- package/evals/reports/runtime/eryx-python-script-derive-execution-1-report.md +233 -0
- package/evals/reports/runtime/jq-script-derive-execution-1-report.md +215 -0
- package/evals/reports/runtime/jq-wasm-proof-spike-1-report.md +67 -0
- package/evals/reports/runtime/output-router-benchmark-1-report.md +81 -0
- package/evals/reports/runtime/output-router-capture-derive-provider-eval-1-report.md +35 -0
- package/evals/reports/runtime/output-router-codex-large-index-sqlite-adhoc-report.md +150 -0
- package/evals/reports/runtime/output-router-codex-qa-benchmark-1-report.md +46 -0
- package/evals/reports/runtime/output-router-command-benchmark-1-report.md +62 -0
- package/evals/reports/runtime/output-router-index-benchmark-1-report.md +64 -0
- package/evals/reports/runtime/output-router-regression-1-report.md +81 -0
- package/evals/reports/runtime/output-router-transform-eval-1-report.md +28 -0
- package/evals/reports/runtime/pi-observed-routing-eval-1-report.md +44 -0
- package/evals/reports/runtime/quickjs-script-derive-execution-1-report.md +159 -0
- package/evals/reports/runtime/quickjs-wasi-proof-spike-1-report.md +55 -0
- package/evals/reports/runtime/render-format-row-protocol-1-report.md +58 -0
- package/evals/reports/runtime/script-sandbox-adapter-selection-review-1-report.md +84 -0
- package/evals/reports/runtime/script-sandbox-probe-resource-hardening-1-report.md +51 -0
- package/evals/reports/runtime/storage-policy-benchmark-1-report.md +176 -0
- package/evals/reports/runtime/vault-index-storage-spike-1-report.md +39 -0
- package/evals/reports/runtime/workflow-context-hook-1-report.md +82 -0
- package/evals/runbooks/adversarial-eval-runbook.md +28 -0
- package/evals/runbooks/fixture-eval-runbook.md +137 -0
- package/evals/runbooks/handoff-eval-runbook.md +22 -0
- package/evals/runbooks/verify-work-eval-runbook.md +27 -0
- package/evals/scripts/audit-command-surface.sh +160 -0
- package/evals/scripts/check-activation-contract.sh +121 -0
- package/evals/scripts/check-runtime-context-hook.sh +183 -0
- package/evals/scripts/grade-fixture-eval.sh +446 -0
- package/evals/scripts/run-claude-fixture-eval.sh +26 -0
- package/evals/scripts/run-codex-fixture-eval.sh +26 -0
- package/evals/scripts/run-eryx-python-proof-spike.js +559 -0
- package/evals/scripts/run-fixture-eval-by-id.sh +23 -0
- package/evals/scripts/run-fixture-eval.sh +464 -0
- package/evals/scripts/run-jq-wasm-proof-spike.js +299 -0
- package/evals/scripts/run-output-router-transform-eval.js +115 -0
- package/evals/scripts/run-pi-observed-routing-eval.js +478 -0
- package/evals/scripts/run-quickjs-wasi-proof-spike.js +339 -0
- package/evals/scripts/skill-evidence.sh +316 -0
- package/evals/scripts/validate-release-metadata.sh +486 -0
- package/evals/suites/v0.1-acceptance-suite.md +131 -0
- package/{plugins/freeflow/hooks → hooks}/freeflow-runtime-context.mjs +65 -14
- package/package.json +46 -13
- package/pi-extension/dist/host-producer-identification.js +186 -0
- package/pi-extension/dist/index.js +85 -0
- package/pi-extension/dist/mcp-config.js +30 -0
- package/pi-extension/dist/native-safety-net.js +209 -0
- package/pi-extension/dist/observed-tool-routing.js +114 -0
- package/pi-extension/dist/renderers.js +835 -0
- package/pi-extension/dist/router-tools.js +438 -0
- package/pi-extension/dist/runtime-context.js +288 -0
- package/pi-extension/dist/schemas.js +254 -0
- package/pi-extension/dist/status.js +449 -0
- package/pi-extension/dist/utils.js +467 -0
- package/pi-extension/src/host-producer-identification.ts +226 -0
- package/pi-extension/src/index.ts +121 -0
- package/pi-extension/src/mcp-config.ts +32 -0
- package/pi-extension/src/native-safety-net.ts +252 -0
- package/pi-extension/src/observed-tool-routing.ts +126 -0
- package/pi-extension/src/renderers.ts +917 -0
- package/pi-extension/src/router-tools.ts +478 -0
- package/pi-extension/src/runtime-context.ts +347 -0
- package/pi-extension/src/schemas.ts +259 -0
- package/pi-extension/src/status.ts +505 -0
- package/pi-extension/src/utils.ts +492 -0
- package/pi-extension/tsconfig.json +16 -0
- package/plugin-docs/README.md +40 -0
- package/plugin-docs/adr/0002-evals-before-hooks.md +17 -0
- package/{plugins/freeflow/docs → plugin-docs}/adr/0003-release-boundary.md +2 -2
- package/plugin-docs/adr/0004-discover-replaces-shallow-discovery-skills.md +26 -0
- package/plugin-docs/adr/README.md +10 -0
- package/plugin-docs/architecture.md +89 -0
- package/plugin-docs/output-router.md +396 -0
- package/plugin-docs/release-evidence.md +77 -0
- package/{plugins/freeflow/docs → plugin-docs}/skills.md +7 -7
- package/{plugins/freeflow/docs → plugin-docs}/workflow.md +4 -4
- package/router/dist/benchmarks/benchmark-harness.d.ts +32 -0
- package/router/dist/benchmarks/benchmark-harness.js +92 -0
- package/router/dist/benchmarks/benchmarks.d.ts +102 -0
- package/router/dist/benchmarks/benchmarks.js +880 -0
- package/router/dist/benchmarks/codex-qa-benchmarks.d.ts +91 -0
- package/router/dist/benchmarks/codex-qa-benchmarks.js +461 -0
- package/router/dist/benchmarks/command-benchmarks.d.ts +128 -0
- package/router/dist/benchmarks/command-benchmarks.js +653 -0
- package/router/dist/benchmarks/context-mode-normalized-benchmarks.d.ts +74 -0
- package/router/dist/benchmarks/context-mode-normalized-benchmarks.js +707 -0
- package/router/dist/benchmarks/context-mode-real-deep-benchmark.d.ts +124 -0
- package/router/dist/benchmarks/context-mode-real-deep-benchmark.js +1295 -0
- package/router/dist/benchmarks/context-saving-baseline.d.ts +54 -0
- package/router/dist/benchmarks/context-saving-baseline.js +439 -0
- package/router/dist/benchmarks/index-benchmarks.d.ts +98 -0
- package/router/dist/benchmarks/index-benchmarks.js +762 -0
- package/router/dist/benchmarks/storage-policy-benchmarks.d.ts +90 -0
- package/router/dist/benchmarks/storage-policy-benchmarks.js +538 -0
- package/router/dist/benchmarks/vault-index-benchmarks.d.ts +47 -0
- package/router/dist/benchmarks/vault-index-benchmarks.js +257 -0
- package/router/dist/config/config.d.ts +96 -0
- package/router/dist/config/config.js +453 -0
- package/router/dist/config/router-contract.d.ts +10 -0
- package/router/dist/config/router-contract.js +54 -0
- package/router/dist/config/schema.d.ts +18 -0
- package/router/dist/config/schema.js +600 -0
- package/router/dist/config/types.d.ts +521 -0
- package/router/dist/config/types.js +30 -0
- package/router/dist/evidence/bounded-evidence.d.ts +40 -0
- package/router/dist/evidence/bounded-evidence.js +310 -0
- package/router/dist/evidence/evidence-range-selector.d.ts +22 -0
- package/router/dist/evidence/evidence-range-selector.js +231 -0
- package/router/dist/evidence/evidence-search.d.ts +25 -0
- package/router/dist/evidence/evidence-search.js +466 -0
- package/router/dist/evidence/evidence.d.ts +38 -0
- package/router/dist/evidence/evidence.js +196 -0
- package/router/dist/evidence/failure-contracts.d.ts +27 -0
- package/router/dist/evidence/failure-contracts.js +160 -0
- package/router/dist/evidence/line-ranges.d.ts +22 -0
- package/router/dist/evidence/line-ranges.js +22 -0
- package/router/dist/experiments/local-index.d.ts +58 -0
- package/router/dist/experiments/local-index.js +562 -0
- package/router/dist/index.d.ts +30 -0
- package/router/dist/index.js +32 -0
- package/router/dist/processing/engine.d.ts +108 -0
- package/router/dist/processing/engine.js +435 -0
- package/router/dist/processing/reducers.d.ts +266 -0
- package/router/dist/processing/reducers.js +1495 -0
- package/router/dist/processing/renderers.d.ts +25 -0
- package/router/dist/processing/renderers.js +186 -0
- package/router/dist/processing/scripts.d.ts +78 -0
- package/router/dist/processing/scripts.js +333 -0
- package/router/dist/repo/repo-traversal.d.ts +18 -0
- package/router/dist/repo/repo-traversal.js +242 -0
- package/router/dist/routing/observed-reducers.d.ts +35 -0
- package/router/dist/routing/observed-reducers.js +647 -0
- package/router/dist/routing/observed-routing.d.ts +17 -0
- package/router/dist/routing/observed-routing.js +377 -0
- package/router/dist/routing/parsers.d.ts +16 -0
- package/router/dist/routing/parsers.js +473 -0
- package/router/dist/routing/run-filters.d.ts +56 -0
- package/router/dist/routing/run-filters.js +230 -0
- package/router/dist/routing/run-reducers.d.ts +30 -0
- package/router/dist/routing/run-reducers.js +110 -0
- package/router/dist/sandbox/adapter-roots.d.ts +38 -0
- package/router/dist/sandbox/adapter-roots.js +64 -0
- package/router/dist/sandbox/eryx-python-adapter.d.ts +9 -0
- package/router/dist/sandbox/eryx-python-adapter.js +797 -0
- package/router/dist/sandbox/jq-wasm-adapter.d.ts +9 -0
- package/router/dist/sandbox/jq-wasm-adapter.js +421 -0
- package/router/dist/sandbox/quickjs-wasi-adapter.d.ts +9 -0
- package/router/dist/sandbox/quickjs-wasi-adapter.js +381 -0
- package/router/dist/sandbox/script-sandbox.d.ts +113 -0
- package/router/dist/sandbox/script-sandbox.js +303 -0
- package/router/dist/setup/script-transform-adapters.d.ts +28 -0
- package/router/dist/setup/script-transform-adapters.js +259 -0
- package/router/dist/tools/batch.d.ts +22 -0
- package/router/dist/tools/batch.js +509 -0
- package/router/dist/tools/run.d.ts +50 -0
- package/router/dist/tools/run.js +1219 -0
- package/router/dist/tools/search.d.ts +44 -0
- package/router/dist/tools/search.js +1205 -0
- package/router/dist/transform/engine.d.ts +143 -0
- package/router/dist/transform/engine.js +1955 -0
- package/router/dist/vault/vault-index.d.ts +106 -0
- package/router/dist/vault/vault-index.js +411 -0
- package/router/dist/vault/vault.d.ts +103 -0
- package/router/dist/vault/vault.js +635 -0
- package/{plugins/freeflow/skills → skills}/commit-work/SKILL.md +17 -16
- package/{plugins/freeflow/skills → skills}/commit-work/references/staging-decisions.md +3 -3
- package/skills/design-for-depth/SKILL.md +90 -0
- package/skills/design-for-depth/references/design-pressure-signals.md +265 -0
- package/skills/design-for-depth/references/software-design-philosophy.md +219 -0
- package/{plugins/freeflow/skills → skills}/diagnose-failure/SKILL.md +6 -1
- package/skills/discover/ARTIFACT-DESTINATIONS.md +58 -0
- package/skills/discover/CHECKPOINTS.md +74 -0
- package/skills/discover/SKILL.md +173 -0
- package/skills/execute-plan/SKILL.md +133 -0
- package/skills/execute-plan/references/execution-map.md +122 -0
- package/{plugins/freeflow/skills → skills}/mode-contract/SKILL.md +10 -5
- package/skills/output-router/SKILL.md +202 -0
- package/skills/output-router/references/safety-policy.md +40 -0
- package/{plugins/freeflow/skills → skills}/review-artifact/SKILL.md +37 -1
- package/{plugins/freeflow/skills → skills}/review-artifact/references/reviewer-prompt.md +14 -2
- package/skills/review-work/SKILL.md +101 -0
- package/{plugins/freeflow/skills → skills}/review-work/references/reviewer-prompt.md +8 -0
- package/skills/setup-freeflow/SKILL.md +106 -0
- package/{plugins/freeflow/skills → skills}/setup-freeflow/references/activation-contract.md +14 -8
- package/{plugins/freeflow/skills → skills}/setup-freeflow/references/host-setup.md +5 -3
- package/skills/setup-freeflow/references/output-router-setup.md +102 -0
- package/{plugins/freeflow/skills → skills}/verify-work/SKILL.md +3 -1
- package/{plugins/freeflow/skills → skills}/workflow/SKILL.md +23 -13
- package/{plugins/freeflow/skills → skills}/workflow/references/workflow-map.md +21 -20
- package/{plugins/freeflow/skills → skills}/write-plan/SKILL.md +9 -1
- package/{plugins/freeflow/skills → skills}/write-skill/SKILL.md +1 -1
- package/{plugins/freeflow/skills → skills}/write-spec/SKILL.md +9 -6
- package/plugins/freeflow/docs/README.md +0 -39
- package/plugins/freeflow/docs/adr/0002-evals-before-hooks.md +0 -17
- package/plugins/freeflow/docs/adr/README.md +0 -7
- package/plugins/freeflow/docs/architecture.md +0 -86
- package/plugins/freeflow/docs/release-evidence.md +0 -49
- package/plugins/freeflow/pi-extension/index.js +0 -250
- package/plugins/freeflow/skills/capture-decisions/SKILL.md +0 -95
- package/plugins/freeflow/skills/capture-decisions/references/destination-guide.md +0 -65
- package/plugins/freeflow/skills/execute-plan/SKILL.md +0 -67
- package/plugins/freeflow/skills/grill-context/SKILL.md +0 -79
- package/plugins/freeflow/skills/grill-context/references/approach-framing.md +0 -52
- package/plugins/freeflow/skills/research-brief/SKILL.md +0 -69
- package/plugins/freeflow/skills/review-work/SKILL.md +0 -73
- package/plugins/freeflow/skills/setup-freeflow/SKILL.md +0 -84
- /package/{plugins/freeflow/assets → assets}/freeflow-plugin-icon-transparent.png +0 -0
- /package/{plugins/freeflow/hooks → hooks}/hooks.json +0 -0
- /package/{plugins/freeflow/docs → plugin-docs}/adr/0001-three-modes.md +0 -0
- /package/{plugins/freeflow/skills → skills}/bypass/SKILL.md +0 -0
- /package/{plugins/freeflow/skills → skills}/diagnose-failure/references/feedback-loop-catalog.md +0 -0
- /package/{plugins/freeflow/skills → skills}/diagnose-failure/references/flaky-and-performance.md +0 -0
- /package/{plugins/freeflow/skills → skills}/evaluate-skill/SKILL.md +0 -0
- /package/{plugins/freeflow/skills → skills}/evaluate-skill/references/eval-patterns.md +0 -0
- /package/{plugins/freeflow/skills → skills}/evaluate-skill/references/grading-priority.md +0 -0
- /package/{plugins/freeflow/skills → skills}/handoff/SKILL.md +0 -0
- /package/{plugins/freeflow/skills → skills}/handoff/references/templates.md +0 -0
- /package/{plugins/freeflow/skills → skills}/interview-gate/SKILL.md +0 -0
- /package/{plugins/freeflow/skills → skills}/write-plan/references/plan-shapes.md +0 -0
- /package/{plugins/freeflow/skills → skills}/write-spec/references/artifact-standards.md +0 -0
- /package/{plugins/freeflow/skills → skills}/write-spec/references/spec-shapes.md +0 -0
|
@@ -0,0 +1,74 @@
|
|
|
1
|
+
export interface RunContextModeNormalizedBenchmarksOptions {
|
|
2
|
+
iterations?: number;
|
|
3
|
+
generatedAt?: string;
|
|
4
|
+
}
|
|
5
|
+
export interface ContextModeNormalizedBenchmarkReport {
|
|
6
|
+
generatedAt: string;
|
|
7
|
+
iterations: number;
|
|
8
|
+
summary: ContextModeNormalizedSummary;
|
|
9
|
+
fixtures: ContextModeFixtureResult[];
|
|
10
|
+
notes: string[];
|
|
11
|
+
}
|
|
12
|
+
export interface ContextModeNormalizedSummary {
|
|
13
|
+
fixtures: number;
|
|
14
|
+
modeResults: number;
|
|
15
|
+
freeflow: ContextModeModeSummary;
|
|
16
|
+
contextModeProxy: ContextModeModeSummary;
|
|
17
|
+
freeflowBetterModelVisibleBytes: number;
|
|
18
|
+
freeflowBetterToolCalls: number;
|
|
19
|
+
allFreeflowFactsPreserved: boolean;
|
|
20
|
+
allFreeflowRecoveryAvailable: boolean;
|
|
21
|
+
publicClaimsAllowed: boolean;
|
|
22
|
+
}
|
|
23
|
+
export interface ContextModeModeSummary {
|
|
24
|
+
passed: number;
|
|
25
|
+
failed: number;
|
|
26
|
+
answerAccurate: number;
|
|
27
|
+
exactFactsPreserved: number;
|
|
28
|
+
recoveryAvailable: number;
|
|
29
|
+
totalRawBytes: number;
|
|
30
|
+
totalModelVisibleBytes: number;
|
|
31
|
+
totalModelVisibleTokensApprox: number;
|
|
32
|
+
totalToolCalls: number;
|
|
33
|
+
totalStorageBytes: number;
|
|
34
|
+
weightedModelVisibleReductionPercent: number;
|
|
35
|
+
}
|
|
36
|
+
export interface ContextModeFixtureResult {
|
|
37
|
+
id: string;
|
|
38
|
+
title: string;
|
|
39
|
+
category: ContextModeFixtureCategory;
|
|
40
|
+
expectedFacts: string[];
|
|
41
|
+
results: ContextModeModeResult[];
|
|
42
|
+
}
|
|
43
|
+
export interface ContextModeModeResult {
|
|
44
|
+
mode: ContextModeMode;
|
|
45
|
+
toolPathUsed: string;
|
|
46
|
+
rawBytes: number;
|
|
47
|
+
modelVisibleBytes: number;
|
|
48
|
+
modelVisibleTokensApprox: number;
|
|
49
|
+
detailsPayloadBytes: number;
|
|
50
|
+
storageBytes: number;
|
|
51
|
+
toolCalls: number;
|
|
52
|
+
latencyMs: {
|
|
53
|
+
p50: number;
|
|
54
|
+
p95: number;
|
|
55
|
+
};
|
|
56
|
+
modelVisibleReductionPercent: number;
|
|
57
|
+
answerAccuracy: boolean;
|
|
58
|
+
exactFactsPreserved: boolean;
|
|
59
|
+
recoveryAvailable: boolean;
|
|
60
|
+
recoveryDetail: string;
|
|
61
|
+
notes: string[];
|
|
62
|
+
}
|
|
63
|
+
type ContextModeFixtureCategory = "command" | "docs" | "logs" | "json-csv" | "repo-search" | "batch";
|
|
64
|
+
type ContextModeMode = "context-mode-normalized-proxy" | "freeflow-owned-tools";
|
|
65
|
+
export declare function runContextModeNormalizedBenchmarks(options?: RunContextModeNormalizedBenchmarksOptions): Promise<ContextModeNormalizedBenchmarkReport>;
|
|
66
|
+
export declare function renderContextModeNormalizedBenchmarkReport(report: ContextModeNormalizedBenchmarkReport): string;
|
|
67
|
+
export interface WriteContextModeNormalizedBenchmarkReportsOptions {
|
|
68
|
+
jsonReportPath?: string | false;
|
|
69
|
+
}
|
|
70
|
+
export declare function writeContextModeNormalizedBenchmarkReports(report: ContextModeNormalizedBenchmarkReport, markdownReportPath: string, options?: WriteContextModeNormalizedBenchmarkReportsOptions): Promise<{
|
|
71
|
+
markdown: string;
|
|
72
|
+
json?: string;
|
|
73
|
+
}>;
|
|
74
|
+
export {};
|