Add a concrete 0-100 swarmness/compliance score, local large-scale stress, and 3000 TPM budget acceptance so the repo can say when it is a swarm by measured criteria instead of prose alone.
Constraint: user required Chinese docs, explicit scenarios, parameters, formulas, pass/fail lines, and git upload.
Rejected: prose-only PASS reports | they did not answer whether the system is a swarm with a concrete score.
Confidence: high
Scope-risk: moderate
Directive: keep production runtime claims separate from local minimal swarm acceptance scores.
Tested: py_compile swarm_minimal examples tests; unittest discover -s tests 45 tests; run_swarm_compliance_score.py; run_tpm_budget_acceptance.py; run_academic_standard_evaluation.py; git diff --check; docs/script secret-pattern scan.
Not-tested: live S07 and production Kubernetes/NewAPI provider-rate-limit stress were not rerun in this upload step.
Co-authored-by: OmX <omx@oh-my-codex.dev>
Turn the remaining minimal-boundary items into executable behavior: locked autonomous claim scaling for 3/5/7 agents, multi-candidate fusion, and challenge-revise-revote consensus.
Constraint: The user asked to implement code directly, complete testing and acceptance, and explain the test standards rather than only updating the comparison document.
Rejected: Leaving SW-AQS-16, candidate fusion, and questioning consensus as documentation-only future work | each now has deterministic code paths and S09 acceptance evidence.
Confidence: high
Scope-risk: moderate
Directive: Future claims about full production readiness must still distinguish this local deterministic S09 acceptance from real runtime/Kubernetes scaling and Manager/Agnet platform integration.
Tested: .venv/bin/python -B -m py_compile swarm_minimal/*.py examples/*.py tests/*.py; .venv/bin/python -B -m unittest tests.test_standard_scenarios; .venv/bin/python -B -m unittest discover -s tests; .venv/bin/python -u -B examples/run_next_boundary_acceptance.py; .venv/bin/python -u -B examples/run_academic_standard_evaluation.py; .venv/bin/python -u -B examples/run_standard_scenario_acceptance.py; .venv/bin/python -B examples/export_model_agnet_io_report.py; .venv/bin/python -B -m unittest tests.test_model_io_report_audit; docs secret pattern scan; git diff --check.
Not-tested: Real Kubernetes/worker runtime 3/5/7 scaling, Redis Stream consumer-driven replanning, and Manager/Agnet approval integration remain outside this local minimal acceptance.
Co-authored-by: OmX <omx@oh-my-codex.dev>
Promote the S07 external FastAPI chain from score-only acceptance to a minimal quality-gated flow with refusal detection, retry/fallback recovery, handoff quality checks, and a multi-round consensus gate before final convergence.
Constraint: The user asked to fix the documented shortcomings around score-only convergence, weak refusal scoring, and unqualified handoff evidence while continuing the minimal version.
Rejected: Replacing the whole coordinator with a production consensus runtime | the minimal fix keeps the existing task pool/convergence shape and adds scenario-level quality gates plus consensus evidence.
Confidence: high
Scope-risk: moderate
Directive: Future S07 runs must keep all_outputs_pass_quality_gate and multi_round_quality_consensus_accepts_chain as required checks before claiming PASS.
Tested: .venv/bin/python -B -m unittest tests.test_standard_scenarios; .venv/bin/python -u -B examples/run_continuous_reasoning_acceptance.py; .venv/bin/python -B examples/export_model_agnet_io_report.py; .venv/bin/python -B -m unittest discover -s tests; .venv/bin/python -B -m py_compile swarm_minimal/*.py examples/*.py tests/*.py; .venv/bin/python -u -B examples/run_academic_standard_evaluation.py; .venv/bin/python -B -m unittest tests.test_model_io_report_audit; git diff --check; docs secret pattern scan.
Not-tested: The combined run_standard_scenario_acceptance wrapper was not rerun after report export to avoid creating a newer live run that would make the exported latest-run report stale.
Co-authored-by: OmX <omx@oh-my-codex.dev>
Add a no-code Chinese explanation of the current Agnet framework logic and implementation process using only Agnet inputs, outputs, handoffs, and convergence behavior.
Constraint: The user asked for a framework logic explanation without code, based on Agnet input and output.
Rejected: Expanding the generated model I/O report again | a standalone narrative keeps the explanation readable and avoids another raw evidence dump.
Confidence: high
Scope-risk: narrow
Directive: Keep this document prose-only; do not add source snippets, command blocks, or inline code markers.
Tested: no backtick/code-marker scan on docs/AGNET_FRAMEWORK_INPUT_OUTPUT_LOGIC.zh-CN.md; .venv/bin/python -B -m unittest discover -s tests; .venv/bin/python -B -m py_compile swarm_minimal/*.py examples/*.py tests/*.py; git diff --check; docs secret pattern scan.
Not-tested: Live S07 was not rerun because this change adds explanatory documentation only.
Co-authored-by: OmX <omx@oh-my-codex.dev>
