teleo-infrastructure/.crabbox.yaml
twentyOne2x 71ea7a625c Add decision engine replay harness
- Add source-linked model discovery registry for bakeoff candidates
- Add Rio, Theseus, and KB interop fixtures with deterministic replay proof
- Gate CI on replay output; verify with 424-test suite

`.crabbox.yaml`
`.github/workflows/ci.yml`
`docs/llm-refinement-decision-engine.md`
`docs/model-discovery-registry.md`
`fixtures/decision-engine-eval/kb_interop_propose_only.json`
`fixtures/decision-engine-eval/rio_meteora_lp_incentives.json`
`fixtures/decision-engine-eval/theseus_live_model_switch_reject.json`
`scripts/check_llm_refinement_contract.py`
`scripts/replay_decision_engine_eval.py`
`tests/test_decision_engine_replay.py`
2026-06-01 17:37:38 +02:00

187 lines
4.2 KiB
YAML

profile: teleo-infrastructure-check
provider: hetzner
target: linux
architecture: arm64
class: beast
ttl: 90m
idleTimeout: 20m
capacity:
market: spot
strategy: most-available
fallback: on-demand-after-120s
actions:
workflow: .github/workflows/crabbox.yml
job: hydrate
runnerLabels:
- crabbox
runnerVersion: latest
ephemeral: true
sync:
delete: true
checksum: false
gitSeed: true
fingerprint: true
timeout: 15m
warnFiles: 50000
warnBytes: 5368709120
failFiles: 150000
failBytes: 21474836480
exclude:
- .cache
- .venv
- .pytest_cache
- .ruff_cache
- __pycache__
- "*.pyc"
- "*.db"
- "*.db-wal"
- "*.db-shm"
- "*.log"
- logs
- secrets
- .env
- htmlcov
- dist
- build
- "*.egg-info"
- .turbo
- node_modules
env:
allow:
- CI
- PYTHONWARNINGS
- PHASE1B_AGENT_ROUTING_ENABLED
ssh:
user: crabbox
port: "2222"
# Ordered fallback ports tried after ssh.port; use [] to disable fallback.
fallbackPorts:
- "22"
jobs:
ci-contract:
provider: hetzner
target: linux
architecture: arm64
class: beast
hydrate:
actions: true
githubRunner: false
waitTimeout: 20m
keepAliveMinutes: 90
actions:
workflow: .github/workflows/crabbox.yml
job: hydrate
shell: true
command: >
python3 -m pip install -e '.[dev]' &&
mkdir -p .crabbox-results &&
python3 scripts/check_crabbox_ci_contract.py
--output .crabbox-results/crabbox-ci-contract.json &&
python3 scripts/check_llm_refinement_contract.py
--output .crabbox-results/llm-refinement-contract.json &&
python3 scripts/replay_decision_engine_eval.py
--output .crabbox-results/decision-engine-eval.json
downloads:
- .crabbox-results/crabbox-ci-contract.json
- .crabbox-results/llm-refinement-contract.json
- .crabbox-results/decision-engine-eval.json
stop: always
unit:
provider: hetzner
target: linux
architecture: arm64
class: beast
hydrate:
actions: true
githubRunner: false
waitTimeout: 20m
keepAliveMinutes: 90
actions:
workflow: .github/workflows/crabbox.yml
job: hydrate
shell: true
command: >
python3 -m pip install -e '.[dev]' &&
mkdir -p .crabbox-results &&
python3 -m pytest --junitxml=.crabbox-results/pytest.xml
junit:
- .crabbox-results/pytest.xml
downloads:
- .crabbox-results/pytest.xml
stop: always
lint-phase1b:
provider: hetzner
target: linux
architecture: arm64
class: beast
hydrate:
actions: true
githubRunner: false
waitTimeout: 20m
keepAliveMinutes: 90
actions:
workflow: .github/workflows/crabbox.yml
job: hydrate
shell: true
command: >
python3 -m pip install -e '.[dev]' &&
python3 -m ruff check
lib/agent_routing.py
lib/config.py
lib/db.py
lib/evaluate.py
lib/llm.py
lib/post_extract.py
telegram/approvals.py
scripts/prove_phase1b_local.py
tests/test_agent_routing.py
tests/test_evaluate_agent_routing.py
tests/test_phase1b_end_to_end.py
tests/test_eval_parse.py
tests/test_contributor.py
tests/test_search.py
stop: always
phase1b-local-proof:
provider: hetzner
target: linux
architecture: arm64
class: beast
hydrate:
actions: true
githubRunner: false
waitTimeout: 20m
keepAliveMinutes: 90
actions:
workflow: .github/workflows/crabbox.yml
job: hydrate
shell: true
command: >
python3 -m pip install -e '.[dev]' &&
scripts/crabbox_phase1b_proof.sh
junit:
- .crabbox-results/phase1b-pytest.xml
downloads:
- .crabbox-results/crabbox-ci-contract.json
- proof/phase1b-local-e2e-proof.json
- .crabbox-results/phase1b-pytest.xml
- .crabbox-results/phase1b-proof-summary.json
stop: always
sync-smoke:
provider: hetzner
target: linux
architecture: arm64
class: beast
hydrate:
actions: false
shell: true
command: >
python3 -m compileall
lib
tests
scripts/prove_phase1b_local.py
stop: always