|
Some checks are pending
CI / lint-and-test (push) Waiting to run
- Build mixed live-retained and sandbox fixture benchmark results for OE plus CS prompts - Retain full 14/14 Cory-style outcome score without claiming live CS Telegram proof - Update handoff docs and tests for the sandbox-first claim ceiling Files: - docs/reports/leo-working-state-20260709/cory-expected-working-leo-outcomes-20260709.md - docs/reports/leo-working-state-20260709/current-truth-index.md - docs/reports/leo-working-state-20260709/working-leo-cory-outcome-sandbox-results-current.json - docs/reports/leo-working-state-20260709/working-leo-cory-outcome-sandbox-results-current.md - docs/reports/leo-working-state-20260709/working-leo-cory-outcome-sandbox-score-current.json - docs/reports/leo-working-state-20260709/working-leo-cory-outcome-sandbox-score-current.md - docs/reports/leo-working-state-20260709/working-leo-current-state-20260709.md - docs/reports/leo-working-state-20260709/working-leo-execution-plan-current.md - scripts/build_working_leo_cory_outcome_sandbox.py - scripts/working_leo_open_ended_benchmark.py - tests/test_build_working_leo_cory_outcome_sandbox.py - tests/test_working_leo_open_ended_benchmark.py |
||
|---|---|---|
| .. | ||
| phase1b | ||
| reports | ||
| ARCHITECTURE.md | ||
| crabbox-remote-blocker.json | ||
| crabbox.md | ||
| deploy-manifest.md | ||
| DIAGNOSTICS-AGENT-SPEC.md | ||
| gcp-infra-hardening-20260707.md | ||
| gcp-kb-cloudsql-restore-runbook.md | ||
| INFRASTRUCTURE.md | ||
| llm-refinement-decision-engine.md | ||
| model-discovery-registry.md | ||
| multi-model-eval-architecture.md | ||
| personality-layer-may-need-separation-from-knowledge-base.md | ||
| phase1b-agent-routing-spec.md | ||
| PIPELINE-AGENT-SPEC.md | ||
| queue.md | ||
| schema-change-protocol.md | ||
| self-directed-research.md | ||
| telegram-leo-x402-bridge-pr-packet.md | ||
| telegram-leo-x402-priority-spec.md | ||
| tool-registry-spec.md | ||