devlyn-cli 3.2.1 → 3.3.1
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.md +2 -2
- package/CLAUDE.md +2 -2
- package/README.md +12 -102
- package/bin/devlyn.js +13 -225
- package/bin/instruction-templates.json +8 -0
- package/config/skills/_shared/adapters/grok.md +1 -2
- package/config/skills/_shared/archive_run.py +15 -3
- package/config/skills/_shared/judge-role-evidence.py +21 -1
- package/config/skills/_shared/runtime-principles.md +1 -1
- package/config/skills/_shared/spec-verify-check.py +0 -653
- package/config/skills/_shared/state-phase-write.py +351 -25
- package/config/skills/_shared/task-complete.py +660 -150
- package/config/skills/_shared/terminal-claim-check.py +229 -4
- package/config/skills/_shared/verify-merge-findings.py +93 -2
- package/config/skills/devlyn:ideate/SKILL.md +3 -4
- package/config/skills/devlyn:ideate/references/elicitation.md +2 -35
- package/config/skills/devlyn:ideate/references/from-spec-mode.md +3 -18
- package/config/skills/devlyn:ideate/references/project-mode.md +1 -16
- package/config/skills/devlyn:ideate/references/spec-template.md +0 -2
- package/config/skills/devlyn:queue/SKILL.md +6 -4
- package/config/skills/devlyn:resolve/SKILL.md +16 -25
- package/config/skills/devlyn:resolve/references/free-form-mode.md +0 -14
- package/config/skills/devlyn:resolve/references/outer-loop.md +1 -1
- package/config/skills/devlyn:resolve/references/phases/build-gate.md +1 -1
- package/config/skills/devlyn:resolve/references/phases/cleanup.md +3 -3
- package/config/skills/devlyn:resolve/references/phases/implement.md +1 -1
- package/config/skills/devlyn:resolve/references/phases/probe-derive.md +1 -16
- package/config/skills/devlyn:resolve/references/phases/verify.md +4 -9
- package/config/skills/devlyn:resolve/references/state-schema.md +9 -7
- package/config/skills/devlyn:resolve/references/task-completion.md +47 -38
- package/{config/skills → optional-skills}/code-health-standards/SKILL.md +4 -13
- package/{config/skills → optional-skills}/code-review-standards/SKILL.md +4 -12
- package/{config/skills → optional-skills}/root-cause-analysis/SKILL.md +4 -12
- package/{config/skills → optional-skills}/ui-implementation-standards/SKILL.md +4 -14
- package/package.json +1 -57
- package/benchmark/auto-resolve/BENCHMARK-DESIGN.md +0 -289
- package/benchmark/auto-resolve/BENCHMARK-RESULTS.md +0 -341
- package/benchmark/auto-resolve/README.md +0 -696
- package/benchmark/auto-resolve/RUBRIC.md +0 -177
- package/benchmark/auto-resolve/fixtures/F1-cli-trivial-flag/NOTES.md +0 -34
- package/benchmark/auto-resolve/fixtures/F1-cli-trivial-flag/expected.json +0 -68
- package/benchmark/auto-resolve/fixtures/F1-cli-trivial-flag/metadata.json +0 -10
- package/benchmark/auto-resolve/fixtures/F1-cli-trivial-flag/setup.sh +0 -4
- package/benchmark/auto-resolve/fixtures/F1-cli-trivial-flag/spec.md +0 -44
- package/benchmark/auto-resolve/fixtures/F1-cli-trivial-flag/task.ko.txt +0 -8
- package/benchmark/auto-resolve/fixtures/F1-cli-trivial-flag/task.txt +0 -8
- package/benchmark/auto-resolve/fixtures/F10-persist-write-collision/NOTES.md +0 -68
- package/benchmark/auto-resolve/fixtures/F10-persist-write-collision/expected.json +0 -60
- package/benchmark/auto-resolve/fixtures/F10-persist-write-collision/metadata.json +0 -10
- package/benchmark/auto-resolve/fixtures/F10-persist-write-collision/setup.sh +0 -17
- package/benchmark/auto-resolve/fixtures/F10-persist-write-collision/spec.md +0 -51
- package/benchmark/auto-resolve/fixtures/F10-persist-write-collision/task.txt +0 -9
- package/benchmark/auto-resolve/fixtures/F10-persist-write-collision/verifiers/invalid.js +0 -29
- package/benchmark/auto-resolve/fixtures/F10-persist-write-collision/verifiers/parallel.js +0 -50
- package/benchmark/auto-resolve/fixtures/F11-batch-import-all-or-nothing/NOTES.md +0 -75
- package/benchmark/auto-resolve/fixtures/F11-batch-import-all-or-nothing/expected.json +0 -52
- package/benchmark/auto-resolve/fixtures/F11-batch-import-all-or-nothing/metadata.json +0 -10
- package/benchmark/auto-resolve/fixtures/F11-batch-import-all-or-nothing/setup.sh +0 -171
- package/benchmark/auto-resolve/fixtures/F11-batch-import-all-or-nothing/spec.md +0 -50
- package/benchmark/auto-resolve/fixtures/F11-batch-import-all-or-nothing/task.txt +0 -9
- package/benchmark/auto-resolve/fixtures/F12-webhook-raw-body-signature/NOTES.md +0 -89
- package/benchmark/auto-resolve/fixtures/F12-webhook-raw-body-signature/expected.json +0 -74
- package/benchmark/auto-resolve/fixtures/F12-webhook-raw-body-signature/metadata.json +0 -10
- package/benchmark/auto-resolve/fixtures/F12-webhook-raw-body-signature/setup.sh +0 -251
- package/benchmark/auto-resolve/fixtures/F12-webhook-raw-body-signature/spec.md +0 -57
- package/benchmark/auto-resolve/fixtures/F12-webhook-raw-body-signature/task.txt +0 -13
- package/benchmark/auto-resolve/fixtures/F12-webhook-raw-body-signature/verifiers/replay-malformed-body.js +0 -64
- package/benchmark/auto-resolve/fixtures/F15-frozen-diff-race-review/NOTES.md +0 -104
- package/benchmark/auto-resolve/fixtures/F15-frozen-diff-race-review/expected.json +0 -46
- package/benchmark/auto-resolve/fixtures/F15-frozen-diff-race-review/metadata.json +0 -10
- package/benchmark/auto-resolve/fixtures/F15-frozen-diff-race-review/setup.sh +0 -336
- package/benchmark/auto-resolve/fixtures/F15-frozen-diff-race-review/spec.md +0 -51
- package/benchmark/auto-resolve/fixtures/F15-frozen-diff-race-review/task.txt +0 -9
- package/benchmark/auto-resolve/fixtures/F16-cli-quote-tax-rules/NOTES.md +0 -38
- package/benchmark/auto-resolve/fixtures/F16-cli-quote-tax-rules/expected.json +0 -64
- package/benchmark/auto-resolve/fixtures/F16-cli-quote-tax-rules/metadata.json +0 -10
- package/benchmark/auto-resolve/fixtures/F16-cli-quote-tax-rules/setup.sh +0 -32
- package/benchmark/auto-resolve/fixtures/F16-cli-quote-tax-rules/spec.md +0 -63
- package/benchmark/auto-resolve/fixtures/F16-cli-quote-tax-rules/task.txt +0 -7
- package/benchmark/auto-resolve/fixtures/F16-cli-quote-tax-rules/verifiers/exact-success.js +0 -54
- package/benchmark/auto-resolve/fixtures/F16-cli-quote-tax-rules/verifiers/no-hardcoded-pricing.js +0 -47
- package/benchmark/auto-resolve/fixtures/F16-cli-quote-tax-rules/verifiers/stock-error.js +0 -45
- package/benchmark/auto-resolve/fixtures/F2-cli-medium-subcommand/NOTES.md +0 -57
- package/benchmark/auto-resolve/fixtures/F2-cli-medium-subcommand/expected-pair-plan-registry.json +0 -170
- package/benchmark/auto-resolve/fixtures/F2-cli-medium-subcommand/expected.json +0 -84
- package/benchmark/auto-resolve/fixtures/F2-cli-medium-subcommand/metadata.json +0 -21
- package/benchmark/auto-resolve/fixtures/F2-cli-medium-subcommand/pair-plan.sample-fail.json +0 -214
- package/benchmark/auto-resolve/fixtures/F2-cli-medium-subcommand/pair-plan.sample-pass.json +0 -223
- package/benchmark/auto-resolve/fixtures/F2-cli-medium-subcommand/setup.sh +0 -5
- package/benchmark/auto-resolve/fixtures/F2-cli-medium-subcommand/spec.md +0 -55
- package/benchmark/auto-resolve/fixtures/F2-cli-medium-subcommand/task.txt +0 -14
- package/benchmark/auto-resolve/fixtures/F21-cli-scheduler-priority/NOTES.md +0 -39
- package/benchmark/auto-resolve/fixtures/F21-cli-scheduler-priority/expected.json +0 -62
- package/benchmark/auto-resolve/fixtures/F21-cli-scheduler-priority/metadata.json +0 -10
- package/benchmark/auto-resolve/fixtures/F21-cli-scheduler-priority/setup.sh +0 -2
- package/benchmark/auto-resolve/fixtures/F21-cli-scheduler-priority/spec.md +0 -67
- package/benchmark/auto-resolve/fixtures/F21-cli-scheduler-priority/task.txt +0 -7
- package/benchmark/auto-resolve/fixtures/F21-cli-scheduler-priority/verifiers/error-order.js +0 -55
- package/benchmark/auto-resolve/fixtures/F21-cli-scheduler-priority/verifiers/priority-blocked.js +0 -48
- package/benchmark/auto-resolve/fixtures/F22-cli-ledger-close/NOTES.md +0 -35
- package/benchmark/auto-resolve/fixtures/F22-cli-ledger-close/expected.json +0 -56
- package/benchmark/auto-resolve/fixtures/F22-cli-ledger-close/metadata.json +0 -10
- package/benchmark/auto-resolve/fixtures/F22-cli-ledger-close/setup.sh +0 -2
- package/benchmark/auto-resolve/fixtures/F22-cli-ledger-close/spec.md +0 -64
- package/benchmark/auto-resolve/fixtures/F22-cli-ledger-close/task.txt +0 -7
- package/benchmark/auto-resolve/fixtures/F22-cli-ledger-close/verifiers/conflicting-duplicate.js +0 -34
- package/benchmark/auto-resolve/fixtures/F22-cli-ledger-close/verifiers/idempotent-close.js +0 -41
- package/benchmark/auto-resolve/fixtures/F23-cli-fulfillment-wave/NOTES.md +0 -39
- package/benchmark/auto-resolve/fixtures/F23-cli-fulfillment-wave/expected.json +0 -56
- package/benchmark/auto-resolve/fixtures/F23-cli-fulfillment-wave/metadata.json +0 -10
- package/benchmark/auto-resolve/fixtures/F23-cli-fulfillment-wave/setup.sh +0 -2
- package/benchmark/auto-resolve/fixtures/F23-cli-fulfillment-wave/spec.md +0 -76
- package/benchmark/auto-resolve/fixtures/F23-cli-fulfillment-wave/task.txt +0 -7
- package/benchmark/auto-resolve/fixtures/F23-cli-fulfillment-wave/verifiers/priority-rollback.js +0 -64
- package/benchmark/auto-resolve/fixtures/F23-cli-fulfillment-wave/verifiers/single-warehouse-fefo.js +0 -66
- package/benchmark/auto-resolve/fixtures/F25-cli-cart-promotion-rules/NOTES.md +0 -40
- package/benchmark/auto-resolve/fixtures/F25-cli-cart-promotion-rules/expected.json +0 -66
- package/benchmark/auto-resolve/fixtures/F25-cli-cart-promotion-rules/metadata.json +0 -10
- package/benchmark/auto-resolve/fixtures/F25-cli-cart-promotion-rules/setup.sh +0 -36
- package/benchmark/auto-resolve/fixtures/F25-cli-cart-promotion-rules/spec.md +0 -71
- package/benchmark/auto-resolve/fixtures/F25-cli-cart-promotion-rules/task.txt +0 -7
- package/benchmark/auto-resolve/fixtures/F25-cli-cart-promotion-rules/verifiers/catalog-source.js +0 -57
- package/benchmark/auto-resolve/fixtures/F25-cli-cart-promotion-rules/verifiers/exact-success.js +0 -63
- package/benchmark/auto-resolve/fixtures/F25-cli-cart-promotion-rules/verifiers/stock-error.js +0 -34
- package/benchmark/auto-resolve/fixtures/F26-cli-payout-ledger-rules/NOTES.md +0 -31
- package/benchmark/auto-resolve/fixtures/F26-cli-payout-ledger-rules/expected.json +0 -68
- package/benchmark/auto-resolve/fixtures/F26-cli-payout-ledger-rules/metadata.json +0 -10
- package/benchmark/auto-resolve/fixtures/F26-cli-payout-ledger-rules/setup.sh +0 -17
- package/benchmark/auto-resolve/fixtures/F26-cli-payout-ledger-rules/spec.md +0 -68
- package/benchmark/auto-resolve/fixtures/F26-cli-payout-ledger-rules/task.txt +0 -7
- package/benchmark/auto-resolve/fixtures/F26-cli-payout-ledger-rules/verifiers/conflicting-duplicate.js +0 -29
- package/benchmark/auto-resolve/fixtures/F26-cli-payout-ledger-rules/verifiers/exact-payout.js +0 -58
- package/benchmark/auto-resolve/fixtures/F26-cli-payout-ledger-rules/verifiers/rules-source.js +0 -56
- package/benchmark/auto-resolve/fixtures/F3-backend-contract-risk/NOTES.md +0 -35
- package/benchmark/auto-resolve/fixtures/F3-backend-contract-risk/expected-pair-plan-registry.json +0 -162
- package/benchmark/auto-resolve/fixtures/F3-backend-contract-risk/expected.json +0 -67
- package/benchmark/auto-resolve/fixtures/F3-backend-contract-risk/metadata.json +0 -19
- package/benchmark/auto-resolve/fixtures/F3-backend-contract-risk/setup.sh +0 -4
- package/benchmark/auto-resolve/fixtures/F3-backend-contract-risk/spec.md +0 -55
- package/benchmark/auto-resolve/fixtures/F3-backend-contract-risk/task.txt +0 -9
- package/benchmark/auto-resolve/fixtures/F31-cli-seat-rebalance/NOTES.md +0 -34
- package/benchmark/auto-resolve/fixtures/F31-cli-seat-rebalance/expected.json +0 -57
- package/benchmark/auto-resolve/fixtures/F31-cli-seat-rebalance/metadata.json +0 -10
- package/benchmark/auto-resolve/fixtures/F31-cli-seat-rebalance/setup.sh +0 -2
- package/benchmark/auto-resolve/fixtures/F31-cli-seat-rebalance/spec.md +0 -67
- package/benchmark/auto-resolve/fixtures/F31-cli-seat-rebalance/task.txt +0 -7
- package/benchmark/auto-resolve/fixtures/F31-cli-seat-rebalance/verifiers/duplicate-event-error.js +0 -35
- package/benchmark/auto-resolve/fixtures/F31-cli-seat-rebalance/verifiers/priority-transfer-rollback.js +0 -53
- package/benchmark/auto-resolve/fixtures/F32-cli-subscription-renewal/NOTES.md +0 -38
- package/benchmark/auto-resolve/fixtures/F32-cli-subscription-renewal/expected.json +0 -57
- package/benchmark/auto-resolve/fixtures/F32-cli-subscription-renewal/metadata.json +0 -10
- package/benchmark/auto-resolve/fixtures/F32-cli-subscription-renewal/setup.sh +0 -2
- package/benchmark/auto-resolve/fixtures/F32-cli-subscription-renewal/spec.md +0 -70
- package/benchmark/auto-resolve/fixtures/F32-cli-subscription-renewal/task.txt +0 -3
- package/benchmark/auto-resolve/fixtures/F32-cli-subscription-renewal/verifiers/duplicate-renewal-error.js +0 -42
- package/benchmark/auto-resolve/fixtures/F32-cli-subscription-renewal/verifiers/priority-credit-rollback.js +0 -70
- package/benchmark/auto-resolve/fixtures/F4-web-browser-design/NOTES.md +0 -47
- package/benchmark/auto-resolve/fixtures/F4-web-browser-design/expected.json +0 -57
- package/benchmark/auto-resolve/fixtures/F4-web-browser-design/metadata.json +0 -10
- package/benchmark/auto-resolve/fixtures/F4-web-browser-design/setup.sh +0 -6
- package/benchmark/auto-resolve/fixtures/F4-web-browser-design/spec.md +0 -48
- package/benchmark/auto-resolve/fixtures/F4-web-browser-design/task.txt +0 -9
- package/benchmark/auto-resolve/fixtures/F5-fix-loop-red-green/NOTES.md +0 -45
- package/benchmark/auto-resolve/fixtures/F5-fix-loop-red-green/expected.json +0 -65
- package/benchmark/auto-resolve/fixtures/F5-fix-loop-red-green/metadata.json +0 -10
- package/benchmark/auto-resolve/fixtures/F5-fix-loop-red-green/setup.sh +0 -55
- package/benchmark/auto-resolve/fixtures/F5-fix-loop-red-green/spec.md +0 -48
- package/benchmark/auto-resolve/fixtures/F5-fix-loop-red-green/task.txt +0 -7
- package/benchmark/auto-resolve/fixtures/F6-dep-audit-native-module/NOTES.md +0 -43
- package/benchmark/auto-resolve/fixtures/F6-dep-audit-native-module/expected.json +0 -77
- package/benchmark/auto-resolve/fixtures/F6-dep-audit-native-module/metadata.json +0 -10
- package/benchmark/auto-resolve/fixtures/F6-dep-audit-native-module/setup.sh +0 -4
- package/benchmark/auto-resolve/fixtures/F6-dep-audit-native-module/spec.md +0 -48
- package/benchmark/auto-resolve/fixtures/F6-dep-audit-native-module/task.txt +0 -10
- package/benchmark/auto-resolve/fixtures/F7-out-of-scope-trap/NOTES.md +0 -57
- package/benchmark/auto-resolve/fixtures/F7-out-of-scope-trap/expected.json +0 -76
- package/benchmark/auto-resolve/fixtures/F7-out-of-scope-trap/metadata.json +0 -10
- package/benchmark/auto-resolve/fixtures/F7-out-of-scope-trap/setup.sh +0 -36
- package/benchmark/auto-resolve/fixtures/F7-out-of-scope-trap/spec.md +0 -45
- package/benchmark/auto-resolve/fixtures/F7-out-of-scope-trap/task.txt +0 -7
- package/benchmark/auto-resolve/fixtures/F8-known-limit-ambiguous/NOTES.md +0 -53
- package/benchmark/auto-resolve/fixtures/F8-known-limit-ambiguous/expected.json +0 -63
- package/benchmark/auto-resolve/fixtures/F8-known-limit-ambiguous/metadata.json +0 -10
- package/benchmark/auto-resolve/fixtures/F8-known-limit-ambiguous/setup.sh +0 -4
- package/benchmark/auto-resolve/fixtures/F8-known-limit-ambiguous/spec.md +0 -48
- package/benchmark/auto-resolve/fixtures/F8-known-limit-ambiguous/task.txt +0 -1
- package/benchmark/auto-resolve/fixtures/F9-e2e-ideate-to-resolve/NOTES.md +0 -105
- package/benchmark/auto-resolve/fixtures/F9-e2e-ideate-to-resolve/expected.json +0 -74
- package/benchmark/auto-resolve/fixtures/F9-e2e-ideate-to-resolve/metadata.json +0 -10
- package/benchmark/auto-resolve/fixtures/F9-e2e-ideate-to-resolve/setup.sh +0 -28
- package/benchmark/auto-resolve/fixtures/F9-e2e-ideate-to-resolve/spec.md +0 -59
- package/benchmark/auto-resolve/fixtures/F9-e2e-ideate-to-resolve/task.txt +0 -5
- package/benchmark/auto-resolve/fixtures/SCHEMA.md +0 -188
- package/benchmark/auto-resolve/fixtures/retired/F27-cli-subscription-proration/NOTES.md +0 -37
- package/benchmark/auto-resolve/fixtures/retired/F27-cli-subscription-proration/RETIRED.md +0 -13
- package/benchmark/auto-resolve/fixtures/retired/F27-cli-subscription-proration/expected.json +0 -56
- package/benchmark/auto-resolve/fixtures/retired/F27-cli-subscription-proration/metadata.json +0 -10
- package/benchmark/auto-resolve/fixtures/retired/F27-cli-subscription-proration/setup.sh +0 -18
- package/benchmark/auto-resolve/fixtures/retired/F27-cli-subscription-proration/spec.md +0 -69
- package/benchmark/auto-resolve/fixtures/retired/F27-cli-subscription-proration/task.txt +0 -7
- package/benchmark/auto-resolve/fixtures/retired/F27-cli-subscription-proration/verifiers/exact-proration.js +0 -48
- package/benchmark/auto-resolve/fixtures/retired/F27-cli-subscription-proration/verifiers/rules-source-and-conflict.js +0 -79
- package/benchmark/auto-resolve/fixtures/retired/F28-cli-return-authorization/NOTES.md +0 -54
- package/benchmark/auto-resolve/fixtures/retired/F28-cli-return-authorization/RETIRED.md +0 -7
- package/benchmark/auto-resolve/fixtures/retired/F28-cli-return-authorization/expected.json +0 -67
- package/benchmark/auto-resolve/fixtures/retired/F28-cli-return-authorization/metadata.json +0 -10
- package/benchmark/auto-resolve/fixtures/retired/F28-cli-return-authorization/setup.sh +0 -2
- package/benchmark/auto-resolve/fixtures/retired/F28-cli-return-authorization/spec.md +0 -67
- package/benchmark/auto-resolve/fixtures/retired/F28-cli-return-authorization/task.txt +0 -5
- package/benchmark/auto-resolve/fixtures/retired/F28-cli-return-authorization/verifiers/policy-precedence.js +0 -72
- package/benchmark/auto-resolve/fixtures/retired/F28-cli-return-authorization/verifiers/validation-and-immutability.js +0 -43
- package/benchmark/auto-resolve/fixtures/retired/F28-cli-return-authorization/verifiers/validation-boundary.js +0 -116
- package/benchmark/auto-resolve/fixtures/retired/F30-cli-credit-hold-settlement/NOTES.md +0 -35
- package/benchmark/auto-resolve/fixtures/retired/F30-cli-credit-hold-settlement/RETIRED.md +0 -12
- package/benchmark/auto-resolve/fixtures/retired/F30-cli-credit-hold-settlement/expected.json +0 -58
- package/benchmark/auto-resolve/fixtures/retired/F30-cli-credit-hold-settlement/metadata.json +0 -10
- package/benchmark/auto-resolve/fixtures/retired/F30-cli-credit-hold-settlement/setup.sh +0 -2
- package/benchmark/auto-resolve/fixtures/retired/F30-cli-credit-hold-settlement/spec.md +0 -73
- package/benchmark/auto-resolve/fixtures/retired/F30-cli-credit-hold-settlement/task.txt +0 -17
- package/benchmark/auto-resolve/fixtures/retired/F30-cli-credit-hold-settlement/verifiers/mixed-idempotent-settlement.js +0 -53
- package/benchmark/auto-resolve/fixtures/retired/F30-cli-credit-hold-settlement/verifiers/rejection-boundaries.js +0 -74
- package/benchmark/auto-resolve/fixtures/retired/F34-cli-settle-inflight/NOTES.md +0 -28
- package/benchmark/auto-resolve/fixtures/retired/F34-cli-settle-inflight/RETIRED.md +0 -15
- package/benchmark/auto-resolve/fixtures/retired/F34-cli-settle-inflight/expected.json +0 -57
- package/benchmark/auto-resolve/fixtures/retired/F34-cli-settle-inflight/metadata.json +0 -10
- package/benchmark/auto-resolve/fixtures/retired/F34-cli-settle-inflight/setup.sh +0 -50
- package/benchmark/auto-resolve/fixtures/retired/F34-cli-settle-inflight/spec.md +0 -59
- package/benchmark/auto-resolve/fixtures/retired/F34-cli-settle-inflight/task.txt +0 -9
- package/benchmark/auto-resolve/fixtures/retired/F34-cli-settle-inflight/verifiers/ordered-settlement.js +0 -88
- package/benchmark/auto-resolve/fixtures/retired/F34-cli-settle-inflight/verifiers/reject-invalid.js +0 -45
- package/benchmark/auto-resolve/fixtures/retired/F35-cli-apply-journal/NOTES.md +0 -30
- package/benchmark/auto-resolve/fixtures/retired/F35-cli-apply-journal/RETIRED.md +0 -16
- package/benchmark/auto-resolve/fixtures/retired/F35-cli-apply-journal/expected.json +0 -64
- package/benchmark/auto-resolve/fixtures/retired/F35-cli-apply-journal/metadata.json +0 -10
- package/benchmark/auto-resolve/fixtures/retired/F35-cli-apply-journal/setup.sh +0 -21
- package/benchmark/auto-resolve/fixtures/retired/F35-cli-apply-journal/spec.md +0 -58
- package/benchmark/auto-resolve/fixtures/retired/F35-cli-apply-journal/task.txt +0 -9
- package/benchmark/auto-resolve/fixtures/retired/F35-cli-apply-journal/verifiers/dup-op.js +0 -54
- package/benchmark/auto-resolve/fixtures/retired/F35-cli-apply-journal/verifiers/priority-apply.js +0 -82
- package/benchmark/auto-resolve/fixtures/retired/F35-cli-apply-journal/verifiers/rollback.js +0 -77
- package/benchmark/auto-resolve/fixtures/retired/F36-cli-session-admission/NOTES.md +0 -99
- package/benchmark/auto-resolve/fixtures/retired/F36-cli-session-admission/RETIRED.md +0 -18
- package/benchmark/auto-resolve/fixtures/retired/F36-cli-session-admission/expected.json +0 -64
- package/benchmark/auto-resolve/fixtures/retired/F36-cli-session-admission/metadata.json +0 -10
- package/benchmark/auto-resolve/fixtures/retired/F36-cli-session-admission/setup.sh +0 -4
- package/benchmark/auto-resolve/fixtures/retired/F36-cli-session-admission/spec.md +0 -61
- package/benchmark/auto-resolve/fixtures/retired/F36-cli-session-admission/task.txt +0 -9
- package/benchmark/auto-resolve/fixtures/retired/F36-cli-session-admission/verifiers/correctness-small.js +0 -135
- package/benchmark/auto-resolve/fixtures/retired/F36-cli-session-admission/verifiers/scale.js +0 -100
- package/benchmark/auto-resolve/fixtures/retired/F36-cli-session-admission/verifiers/validation.js +0 -75
- package/benchmark/auto-resolve/fixtures/retired/F37-cli-rule-lookup/NOTES.md +0 -93
- package/benchmark/auto-resolve/fixtures/retired/F37-cli-rule-lookup/RETIRED.md +0 -16
- package/benchmark/auto-resolve/fixtures/retired/F37-cli-rule-lookup/expected.json +0 -65
- package/benchmark/auto-resolve/fixtures/retired/F37-cli-rule-lookup/metadata.json +0 -10
- package/benchmark/auto-resolve/fixtures/retired/F37-cli-rule-lookup/setup.sh +0 -18
- package/benchmark/auto-resolve/fixtures/retired/F37-cli-rule-lookup/spec.md +0 -66
- package/benchmark/auto-resolve/fixtures/retired/F37-cli-rule-lookup/task.txt +0 -9
- package/benchmark/auto-resolve/fixtures/retired/F37-cli-rule-lookup/verifiers/correctness-small.js +0 -84
- package/benchmark/auto-resolve/fixtures/retired/F37-cli-rule-lookup/verifiers/scale.js +0 -184
- package/benchmark/auto-resolve/fixtures/retired/F37-cli-rule-lookup/verifiers/validation.js +0 -74
- package/benchmark/auto-resolve/fixtures/retired/F9-e2e-ideate-to-preflight/NOTES.md +0 -60
- package/benchmark/auto-resolve/fixtures/retired/F9-e2e-ideate-to-preflight/RETIRED.md +0 -29
- package/benchmark/auto-resolve/fixtures/retired/F9-e2e-ideate-to-preflight/expected.json +0 -73
- package/benchmark/auto-resolve/fixtures/retired/F9-e2e-ideate-to-preflight/metadata.json +0 -10
- package/benchmark/auto-resolve/fixtures/retired/F9-e2e-ideate-to-preflight/setup.sh +0 -28
- package/benchmark/auto-resolve/fixtures/retired/F9-e2e-ideate-to-preflight/spec.md +0 -58
- package/benchmark/auto-resolve/fixtures/retired/F9-e2e-ideate-to-preflight/task.txt +0 -5
- package/benchmark/auto-resolve/fixtures/test-repo/README.md +0 -12
- package/benchmark/auto-resolve/fixtures/test-repo/bin/cli.js +0 -63
- package/benchmark/auto-resolve/fixtures/test-repo/package-lock.json +0 -823
- package/benchmark/auto-resolve/fixtures/test-repo/package.json +0 -22
- package/benchmark/auto-resolve/fixtures/test-repo/playwright.config.js +0 -17
- package/benchmark/auto-resolve/fixtures/test-repo/server/index.js +0 -37
- package/benchmark/auto-resolve/fixtures/test-repo/tests/cli.test.js +0 -25
- package/benchmark/auto-resolve/fixtures/test-repo/tests/server.test.js +0 -58
- package/benchmark/auto-resolve/fixtures/test-repo/web/index.html +0 -37
- package/benchmark/auto-resolve/results/20260507-f10-f11-tier1-full-pipeline/headroom-gate.json +0 -25
- package/benchmark/auto-resolve/results/20260507-f10-f11-tier1-full-pipeline/headroom-gate.md +0 -10
- package/benchmark/auto-resolve/results/20260508-f22-exact-error-headroom/headroom-gate.json +0 -18
- package/benchmark/auto-resolve/results/20260508-f22-exact-error-headroom/headroom-gate.md +0 -9
- package/benchmark/auto-resolve/results/20260508-f26-headroom/headroom-gate.json +0 -18
- package/benchmark/auto-resolve/results/20260508-f26-headroom/headroom-gate.md +0 -9
- package/benchmark/auto-resolve/results/20260510-f16-f23-f25-combined-proof/F16-cli-quote-tax-rules/l2_risk_probes/result.json +0 -28
- package/benchmark/auto-resolve/results/20260510-f16-f23-f25-combined-proof/F23-cli-fulfillment-wave/l2_risk_probes/result.json +0 -28
- package/benchmark/auto-resolve/results/20260510-f16-f23-f25-combined-proof/F25-cli-cart-promotion-rules/l2_risk_probes/result.json +0 -30
- package/benchmark/auto-resolve/results/20260510-f16-f23-f25-combined-proof/full-pipeline-pair-gate.json +0 -82
- package/benchmark/auto-resolve/results/20260510-f16-f23-f25-combined-proof/full-pipeline-pair-gate.md +0 -18
- package/benchmark/auto-resolve/results/20260510-f16-f23-f25-combined-proof/headroom-gate.json +0 -46
- package/benchmark/auto-resolve/results/20260510-f16-f23-f25-combined-proof/headroom-gate.md +0 -17
- package/benchmark/auto-resolve/results/20260511-f12-webhook-headroom/headroom-gate.json +0 -28
- package/benchmark/auto-resolve/results/20260511-f12-webhook-headroom/headroom-gate.md +0 -15
- package/benchmark/auto-resolve/results/20260511-f15-concurrency-headroom/headroom-gate.json +0 -28
- package/benchmark/auto-resolve/results/20260511-f15-concurrency-headroom/headroom-gate.md +0 -15
- package/benchmark/auto-resolve/results/20260511-f21-current-riskprobes-v1/F21-cli-scheduler-priority/l2_risk_probes/result.json +0 -32
- package/benchmark/auto-resolve/results/20260511-f21-current-riskprobes-v1/full-pipeline-pair-gate.json +0 -44
- package/benchmark/auto-resolve/results/20260511-f21-current-riskprobes-v1/full-pipeline-pair-gate.md +0 -16
- package/benchmark/auto-resolve/results/20260511-f21-current-riskprobes-v1/headroom-gate.json +0 -18
- package/benchmark/auto-resolve/results/20260511-f21-current-riskprobes-v1/headroom-gate.md +0 -9
- package/benchmark/auto-resolve/results/20260511-f3-http-error-headroom/headroom-gate.json +0 -28
- package/benchmark/auto-resolve/results/20260511-f3-http-error-headroom/headroom-gate.md +0 -15
- package/benchmark/auto-resolve/results/20260512-f2-medium-headroom/headroom-gate.json +0 -28
- package/benchmark/auto-resolve/results/20260512-f2-medium-headroom/headroom-gate.md +0 -15
- package/benchmark/auto-resolve/results/20260512-f31-seat-rebalance-headroom/headroom-gate.json +0 -28
- package/benchmark/auto-resolve/results/20260512-f31-seat-rebalance-headroom/headroom-gate.md +0 -15
- package/benchmark/auto-resolve/results/20260512-f32-subscription-renewal-headroom/headroom-gate.json +0 -28
- package/benchmark/auto-resolve/results/20260512-f32-subscription-renewal-headroom/headroom-gate.md +0 -15
- package/benchmark/auto-resolve/results/20260512-f4-web-headroom/headroom-gate.json +0 -28
- package/benchmark/auto-resolve/results/20260512-f4-web-headroom/headroom-gate.md +0 -15
- package/benchmark/auto-resolve/results/20260512-f5-fixloop-headroom/headroom-gate.json +0 -28
- package/benchmark/auto-resolve/results/20260512-f5-fixloop-headroom/headroom-gate.md +0 -15
- package/benchmark/auto-resolve/results/20260512-f6-checksum-headroom/headroom-gate.json +0 -28
- package/benchmark/auto-resolve/results/20260512-f6-checksum-headroom/headroom-gate.md +0 -15
- package/benchmark/auto-resolve/results/20260512-f7-scope-headroom/headroom-gate.json +0 -28
- package/benchmark/auto-resolve/results/20260512-f7-scope-headroom/headroom-gate.md +0 -15
- package/benchmark/auto-resolve/results/20260512-f9-e2e-headroom/headroom-gate.json +0 -28
- package/benchmark/auto-resolve/results/20260512-f9-e2e-headroom/headroom-gate.md +0 -15
- package/benchmark/auto-resolve/run-real-benchmark.md +0 -303
- package/benchmark/auto-resolve/scripts/audit-headroom-rejections.py +0 -441
- package/benchmark/auto-resolve/scripts/audit-pair-evidence.py +0 -1256
- package/benchmark/auto-resolve/scripts/build-pair-eligible-manifest.py +0 -306
- package/benchmark/auto-resolve/scripts/check-f9-artifacts.py +0 -268
- package/benchmark/auto-resolve/scripts/collect-swebench-predictions.py +0 -108
- package/benchmark/auto-resolve/scripts/compile-report.py +0 -493
- package/benchmark/auto-resolve/scripts/fetch-swebench-instances.py +0 -129
- package/benchmark/auto-resolve/scripts/frozen-verify-gate.py +0 -434
- package/benchmark/auto-resolve/scripts/full-pipeline-pair-gate.py +0 -612
- package/benchmark/auto-resolve/scripts/headroom-gate.py +0 -378
- package/benchmark/auto-resolve/scripts/iter-0033c-compare.py +0 -683
- package/benchmark/auto-resolve/scripts/iter-0033c-l1-summary.py +0 -97
- package/benchmark/auto-resolve/scripts/judge-opus-pass.sh +0 -542
- package/benchmark/auto-resolve/scripts/judge.sh +0 -565
- package/benchmark/auto-resolve/scripts/oracle-scope-tier-a.py +0 -256
- package/benchmark/auto-resolve/scripts/oracle-scope-tier-b.py +0 -287
- package/benchmark/auto-resolve/scripts/oracle-test-fidelity.py +0 -328
- package/benchmark/auto-resolve/scripts/pair-candidate-frontier.py +0 -469
- package/benchmark/auto-resolve/scripts/pair-plan-idgen.py +0 -401
- package/benchmark/auto-resolve/scripts/pair-plan-lint.py +0 -475
- package/benchmark/auto-resolve/scripts/pair-rejected-fixtures.sh +0 -103
- package/benchmark/auto-resolve/scripts/pair_evidence_contract.py +0 -270
- package/benchmark/auto-resolve/scripts/prepare-swebench-frozen-case.py +0 -273
- package/benchmark/auto-resolve/scripts/prepare-swebench-frozen-corpus.py +0 -148
- package/benchmark/auto-resolve/scripts/prepare-swebench-solver-worktree.py +0 -210
- package/benchmark/auto-resolve/scripts/recent-benchmark-summary.py +0 -232
- package/benchmark/auto-resolve/scripts/run-fixture.sh +0 -1024
- package/benchmark/auto-resolve/scripts/run-frozen-verify-pair.sh +0 -683
- package/benchmark/auto-resolve/scripts/run-full-pipeline-pair-candidate.sh +0 -458
- package/benchmark/auto-resolve/scripts/run-headroom-candidate.sh +0 -336
- package/benchmark/auto-resolve/scripts/run-iter-0033c.sh +0 -208
- package/benchmark/auto-resolve/scripts/run-suite.sh +0 -251
- package/benchmark/auto-resolve/scripts/run-swebench-frozen-corpus.sh +0 -310
- package/benchmark/auto-resolve/scripts/run-swebench-solver-batch.sh +0 -257
- package/benchmark/auto-resolve/scripts/ship-gate.py +0 -391
- package/benchmark/auto-resolve/scripts/solo-ceiling-avoidance.py +0 -53
- package/benchmark/auto-resolve/scripts/solo-headroom-hypothesis.py +0 -77
- package/benchmark/auto-resolve/scripts/swebench-frozen-matrix.py +0 -478
- package/benchmark/auto-resolve/scripts/test-audit-headroom-rejections.sh +0 -288
- package/benchmark/auto-resolve/scripts/test-audit-pair-evidence.sh +0 -1672
- package/benchmark/auto-resolve/scripts/test-benchmark-arg-parsing.sh +0 -1015
- package/benchmark/auto-resolve/scripts/test-build-pair-eligible-manifest.sh +0 -491
- package/benchmark/auto-resolve/scripts/test-check-f9-artifacts.sh +0 -91
- package/benchmark/auto-resolve/scripts/test-frozen-verify-gate.sh +0 -517
- package/benchmark/auto-resolve/scripts/test-full-pipeline-pair-gate.sh +0 -610
- package/benchmark/auto-resolve/scripts/test-headroom-gate.sh +0 -401
- package/benchmark/auto-resolve/scripts/test-iter-0033c-compare.sh +0 -525
- package/benchmark/auto-resolve/scripts/test-iter-0033c-l1-summary.sh +0 -254
- package/benchmark/auto-resolve/scripts/test-lint-fixtures.sh +0 -580
- package/benchmark/auto-resolve/scripts/test-pair-candidate-frontier.sh +0 -591
- package/benchmark/auto-resolve/scripts/test-run-full-pipeline-pair-candidate.sh +0 -497
- package/benchmark/auto-resolve/scripts/test-run-headroom-candidate.sh +0 -401
- package/benchmark/auto-resolve/scripts/test-run-swebench-solver-batch.sh +0 -111
- package/benchmark/auto-resolve/scripts/test-ship-gate.sh +0 -1189
- package/benchmark/auto-resolve/scripts/test-swebench-frozen-case.sh +0 -1221
- package/benchmark/auto-resolve/shadow-fixtures/S1-cli-lang-flag/NOTES.md +0 -28
- package/benchmark/auto-resolve/shadow-fixtures/S1-cli-lang-flag/expected.json +0 -63
- package/benchmark/auto-resolve/shadow-fixtures/S1-cli-lang-flag/metadata.json +0 -10
- package/benchmark/auto-resolve/shadow-fixtures/S1-cli-lang-flag/setup.sh +0 -3
- package/benchmark/auto-resolve/shadow-fixtures/S1-cli-lang-flag/spec.md +0 -47
- package/benchmark/auto-resolve/shadow-fixtures/S1-cli-lang-flag/task.txt +0 -1
- package/benchmark/auto-resolve/shadow-fixtures/S2-cli-inventory-reservation/NOTES.md +0 -34
- package/benchmark/auto-resolve/shadow-fixtures/S2-cli-inventory-reservation/expected.json +0 -53
- package/benchmark/auto-resolve/shadow-fixtures/S2-cli-inventory-reservation/metadata.json +0 -10
- package/benchmark/auto-resolve/shadow-fixtures/S2-cli-inventory-reservation/setup.sh +0 -3
- package/benchmark/auto-resolve/shadow-fixtures/S2-cli-inventory-reservation/spec.md +0 -50
- package/benchmark/auto-resolve/shadow-fixtures/S2-cli-inventory-reservation/task.txt +0 -1
- package/benchmark/auto-resolve/shadow-fixtures/S2-cli-inventory-reservation/verifiers/duplicate-order-error.js +0 -27
- package/benchmark/auto-resolve/shadow-fixtures/S2-cli-inventory-reservation/verifiers/priority-stock-reservation.js +0 -44
- package/benchmark/auto-resolve/shadow-fixtures/S3-cli-ticket-assignment/NOTES.md +0 -34
- package/benchmark/auto-resolve/shadow-fixtures/S3-cli-ticket-assignment/expected.json +0 -55
- package/benchmark/auto-resolve/shadow-fixtures/S3-cli-ticket-assignment/metadata.json +0 -10
- package/benchmark/auto-resolve/shadow-fixtures/S3-cli-ticket-assignment/setup.sh +0 -3
- package/benchmark/auto-resolve/shadow-fixtures/S3-cli-ticket-assignment/spec.md +0 -52
- package/benchmark/auto-resolve/shadow-fixtures/S3-cli-ticket-assignment/task.txt +0 -1
- package/benchmark/auto-resolve/shadow-fixtures/S3-cli-ticket-assignment/verifiers/duplicate-ticket-error.js +0 -29
- package/benchmark/auto-resolve/shadow-fixtures/S3-cli-ticket-assignment/verifiers/priority-agent-assignment.js +0 -48
- package/benchmark/auto-resolve/shadow-fixtures/S4-cli-return-routing/NOTES.md +0 -34
- package/benchmark/auto-resolve/shadow-fixtures/S4-cli-return-routing/expected.json +0 -55
- package/benchmark/auto-resolve/shadow-fixtures/S4-cli-return-routing/metadata.json +0 -10
- package/benchmark/auto-resolve/shadow-fixtures/S4-cli-return-routing/setup.sh +0 -3
- package/benchmark/auto-resolve/shadow-fixtures/S4-cli-return-routing/spec.md +0 -55
- package/benchmark/auto-resolve/shadow-fixtures/S4-cli-return-routing/task.txt +0 -1
- package/benchmark/auto-resolve/shadow-fixtures/S4-cli-return-routing/verifiers/duplicate-return-error.js +0 -43
- package/benchmark/auto-resolve/shadow-fixtures/S4-cli-return-routing/verifiers/priority-return-routing.js +0 -70
- package/benchmark/auto-resolve/shadow-fixtures/S5-cli-credit-grant-ledger/NOTES.md +0 -37
- package/benchmark/auto-resolve/shadow-fixtures/S5-cli-credit-grant-ledger/expected.json +0 -54
- package/benchmark/auto-resolve/shadow-fixtures/S5-cli-credit-grant-ledger/metadata.json +0 -10
- package/benchmark/auto-resolve/shadow-fixtures/S5-cli-credit-grant-ledger/setup.sh +0 -3
- package/benchmark/auto-resolve/shadow-fixtures/S5-cli-credit-grant-ledger/spec.md +0 -59
- package/benchmark/auto-resolve/shadow-fixtures/S5-cli-credit-grant-ledger/task.txt +0 -1
- package/benchmark/auto-resolve/shadow-fixtures/S5-cli-credit-grant-ledger/verifiers/credit-ledger-priority.js +0 -98
- package/benchmark/auto-resolve/shadow-fixtures/S5-cli-credit-grant-ledger/verifiers/duplicate-charge-error.js +0 -38
- package/benchmark/auto-resolve/shadow-fixtures/S6-cli-refund-window-ledger/NOTES.md +0 -36
- package/benchmark/auto-resolve/shadow-fixtures/S6-cli-refund-window-ledger/expected.json +0 -56
- package/benchmark/auto-resolve/shadow-fixtures/S6-cli-refund-window-ledger/metadata.json +0 -10
- package/benchmark/auto-resolve/shadow-fixtures/S6-cli-refund-window-ledger/setup.sh +0 -3
- package/benchmark/auto-resolve/shadow-fixtures/S6-cli-refund-window-ledger/spec.md +0 -59
- package/benchmark/auto-resolve/shadow-fixtures/S6-cli-refund-window-ledger/task.txt +0 -1
- package/benchmark/auto-resolve/shadow-fixtures/S6-cli-refund-window-ledger/verifiers/duplicate-refund-error.js +0 -41
- package/benchmark/auto-resolve/shadow-fixtures/S6-cli-refund-window-ledger/verifiers/priority-refund-ledger.js +0 -65
- package/config/skills/_shared/pair-plan-schema.md +0 -298
- package/scripts/lint-fixtures.sh +0 -352
- package/scripts/lint-shadow-fixtures.sh +0 -58
- package/scripts/lint-skills.sh +0 -4265
- package/scripts/test-owner-phases.py +0 -238
|
@@ -1,238 +0,0 @@
|
|
|
1
|
-
#!/usr/bin/env python3
|
|
2
|
-
"""Exercise the candidate's owner phases through the real CLI and Git boundary."""
|
|
3
|
-
import hashlib
|
|
4
|
-
import json
|
|
5
|
-
import os
|
|
6
|
-
from pathlib import Path
|
|
7
|
-
import runpy
|
|
8
|
-
import subprocess
|
|
9
|
-
import sys
|
|
10
|
-
import tempfile
|
|
11
|
-
import unittest
|
|
12
|
-
|
|
13
|
-
SHARED = Path(__file__).resolve().parents[1] / "config/skills/_shared"
|
|
14
|
-
ENV = {k: v for k, v in os.environ.items() if not k.startswith("DEVLYN_INVOCATION_")}
|
|
15
|
-
ENV["PYTHONDONTWRITEBYTECODE"] = "1"
|
|
16
|
-
|
|
17
|
-
|
|
18
|
-
class OwnerPhases(unittest.TestCase):
|
|
19
|
-
def setUp(self):
|
|
20
|
-
self.temp = tempfile.TemporaryDirectory()
|
|
21
|
-
self.addCleanup(self.temp.cleanup)
|
|
22
|
-
self.work = Path(self.temp.name).resolve()
|
|
23
|
-
self.devlyn = self.work / ".devlyn"
|
|
24
|
-
self.devlyn.mkdir()
|
|
25
|
-
self.state_path = self.devlyn / "pipeline.state.json"
|
|
26
|
-
(self.devlyn / "untracked.baseline").write_text("")
|
|
27
|
-
self.git("init", "-q")
|
|
28
|
-
self.git("config", "user.name", "Owner phase test")
|
|
29
|
-
self.git("config", "user.email", "owner@example.invalid")
|
|
30
|
-
(self.work / ".gitignore").write_text(".devlyn/\n")
|
|
31
|
-
(self.work / "source.txt").write_text("original\n")
|
|
32
|
-
self.git("add", ".")
|
|
33
|
-
self.git("commit", "-qm", "fixture")
|
|
34
|
-
self.head = self.git("rev-parse", "HEAD")
|
|
35
|
-
self.save({"version": "3.0", "run_id": "rs-owner-test", "engine": "codex",
|
|
36
|
-
"phases": {}})
|
|
37
|
-
|
|
38
|
-
def git(self, *args):
|
|
39
|
-
return subprocess.check_output(["git", *args], cwd=self.work, text=True).strip()
|
|
40
|
-
|
|
41
|
-
def state(self):
|
|
42
|
-
return json.loads(self.state_path.read_text())
|
|
43
|
-
|
|
44
|
-
def save(self, value):
|
|
45
|
-
self.state_path.write_text(json.dumps(value))
|
|
46
|
-
|
|
47
|
-
def cli(self, phase, *args, error=None):
|
|
48
|
-
before = self.state_path.read_bytes()
|
|
49
|
-
result = subprocess.run(
|
|
50
|
-
[sys.executable, str(SHARED / "state-phase-write.py"), "--devlyn-dir", ".devlyn",
|
|
51
|
-
"--phase", phase, *args], cwd=self.work, env=ENV, capture_output=True, text=True,
|
|
52
|
-
)
|
|
53
|
-
if error:
|
|
54
|
-
self.assertNotEqual(result.returncode, 0, result.stdout)
|
|
55
|
-
self.assertIn(error, result.stderr)
|
|
56
|
-
self.assertEqual(self.state_path.read_bytes(), before)
|
|
57
|
-
else:
|
|
58
|
-
self.assertEqual(result.returncode, 0, result.stderr)
|
|
59
|
-
return result
|
|
60
|
-
|
|
61
|
-
def assert_owner(self, phase):
|
|
62
|
-
entry = self.state()["phases"][phase]
|
|
63
|
-
self.assertEqual(entry["execution_kind"],
|
|
64
|
-
"orchestrator_context" if phase == "plan" else "orchestrator_commands")
|
|
65
|
-
for name in ("engine", "model_requested", "model_effective"):
|
|
66
|
-
self.assertIsNone(entry[name])
|
|
67
|
-
self.assertFalse({"prompt_sha256", "invocation_receipt", "role_argv"} & entry.keys())
|
|
68
|
-
return entry
|
|
69
|
-
|
|
70
|
-
def plan(self):
|
|
71
|
-
self.cli("plan", "spawn", "--round", "0")
|
|
72
|
-
self.assert_owner("plan")
|
|
73
|
-
(self.devlyn / "plan.md").write_text(
|
|
74
|
-
'<!-- devlyn:authorized-surface -->\n# Files\n```json\n'
|
|
75
|
-
'{"authorized_surface":["source.txt"]}\n```\n# Acceptance\nPreserve scope.\n')
|
|
76
|
-
|
|
77
|
-
def test_plan_digest_and_atomic_handoff(self):
|
|
78
|
-
self.plan()
|
|
79
|
-
self.cli("plan", "transition", "--verdict", "PASS", "--next-phase", "implement",
|
|
80
|
-
"--next-round", "0", "--next-engine", "claude")
|
|
81
|
-
entry = self.assert_owner("plan")
|
|
82
|
-
self.assertEqual(entry["output_sha256"],
|
|
83
|
-
hashlib.sha256((self.devlyn / "plan.md").read_bytes()).hexdigest())
|
|
84
|
-
self.cli("plan", "spawn", "--round", "1", "--triggered-by", "plan",
|
|
85
|
-
error="plan-already-in-use")
|
|
86
|
-
(self.devlyn / "plan.md").write_text("widened scope")
|
|
87
|
-
self.cli("implement", "complete", "--verdict", "PASS", error="plan-integrity-mismatch")
|
|
88
|
-
|
|
89
|
-
def test_owner_identity_and_current_round_artifacts(self):
|
|
90
|
-
for phase in ("plan", "cleanup"):
|
|
91
|
-
self.save({"version": "3.0", "run_id": "rs-owner-test", "engine": "codex", "phases": {}})
|
|
92
|
-
spawn = ("spawn", "--round", "0") + (("--pre-sha", self.head) if phase == "cleanup" else ())
|
|
93
|
-
self.cli(phase, *spawn)
|
|
94
|
-
opened = self.state()
|
|
95
|
-
for flag in ("--engine", "--model", "--engine-session-log"):
|
|
96
|
-
self.cli(phase, "complete", "--verdict", "BLOCKED", flag, "false-worker",
|
|
97
|
-
error="cannot claim worker")
|
|
98
|
-
for suffix in ("prompt.0", "worker-session.0.jsonl", "invocation.0.json", "argv.0.json"):
|
|
99
|
-
proof = self.devlyn / f"{phase}.{suffix}"
|
|
100
|
-
proof.symlink_to(self.devlyn / "missing")
|
|
101
|
-
self.cli(phase, "complete", "--verdict", "BLOCKED", error="worker evidence")
|
|
102
|
-
proof.unlink()
|
|
103
|
-
for key, value in (("engine", "codex"), ("prompt_sha256", None),
|
|
104
|
-
("execution_kind", False), ("execution_kind", {})):
|
|
105
|
-
bad = json.loads(json.dumps(opened))
|
|
106
|
-
bad["phases"][phase][key] = value
|
|
107
|
-
self.save(bad)
|
|
108
|
-
self.cli(phase, "complete", "--verdict", "BLOCKED", error="error:")
|
|
109
|
-
self.save(opened)
|
|
110
|
-
|
|
111
|
-
def test_owner_plan_history_is_bound_and_round_limited(self):
|
|
112
|
-
self.plan()
|
|
113
|
-
self.cli("plan", "complete", "--verdict", "NEEDS_WORK")
|
|
114
|
-
old = self.assert_owner("plan")
|
|
115
|
-
self.cli("plan", "spawn", "--round", "1", "--triggered-by", "plan")
|
|
116
|
-
self.assertEqual(self.state()["phases"]["plan"]["history"][0]["output_sha256"], old["output_sha256"])
|
|
117
|
-
self.cli("plan", "complete", "--verdict", "BLOCKED")
|
|
118
|
-
self.cli("plan", "spawn", "--round", "2", "--triggered-by", "plan", error="plan-respawn-exhausted")
|
|
119
|
-
|
|
120
|
-
def test_cleanup_checks_source_and_preserves_atomicity(self):
|
|
121
|
-
self.cli("cleanup", "spawn", "--round", "0", "--pre-sha", self.head)
|
|
122
|
-
self.assert_owner("cleanup")
|
|
123
|
-
args = ("transition", "--verdict", "PASS", "--post-sha", self.head,
|
|
124
|
-
"--next-phase", "verify", "--next-round", "0", "--next-engine", "claude")
|
|
125
|
-
(self.work / "source.txt").write_text("unverified change\n")
|
|
126
|
-
self.cli("cleanup", *args, error="owner-cleanup-source-changed")
|
|
127
|
-
self.git("add", "source.txt")
|
|
128
|
-
self.cli("cleanup", *args, error="owner-cleanup-source-changed")
|
|
129
|
-
(self.work / "source.txt").write_text("original\n")
|
|
130
|
-
self.cli("cleanup", *args, error="owner-cleanup-source-changed")
|
|
131
|
-
(self.work / "source.txt").write_text("unverified change\n")
|
|
132
|
-
self.git("commit", "-qm", "unverified")
|
|
133
|
-
self.cli("cleanup", *args, error="owner-cleanup-source-changed")
|
|
134
|
-
# All mutations are in this disposable test fixture.
|
|
135
|
-
self.git("reset", "--hard", self.head)
|
|
136
|
-
self.cli("cleanup", *args)
|
|
137
|
-
self.assertIsNotNone(self.state()["phases"]["verify"]["started_at"])
|
|
138
|
-
|
|
139
|
-
def test_cleanup_repair_reenters_build_with_durability(self):
|
|
140
|
-
self.cli("cleanup", "spawn", "--round", "0", "--pre-sha", self.head)
|
|
141
|
-
(self.devlyn / "cleanup.findings.jsonl").write_text("")
|
|
142
|
-
self.cli("cleanup", "transition", "--verdict", "FAIL", "--post-sha", self.head,
|
|
143
|
-
"--next-phase", "implement", "--next-round", "1", "--next-triggered-by", "cleanup",
|
|
144
|
-
"--next-engine", "claude")
|
|
145
|
-
self.cli("implement", "transition", "--verdict", "PASS", "--next-phase", "build_gate",
|
|
146
|
-
"--next-round", "1", error="closure-durability")
|
|
147
|
-
self.git("commit", "--allow-empty", "-qm", "chore(pipeline): implement fix round 1")
|
|
148
|
-
self.cli("implement", "durability-enforce", "--round", "1", "--origin-phase", "cleanup")
|
|
149
|
-
for phase in ("cleanup", "verify"):
|
|
150
|
-
self.cli("implement", "transition", "--verdict", "PASS", "--next-phase", phase,
|
|
151
|
-
"--next-round", "1", error="owner-cleanup-repair-route")
|
|
152
|
-
self.cli("implement", "transition", "--verdict", "PASS", "--next-phase", "build_gate", "--next-round", "1")
|
|
153
|
-
self.assert_owner("build_gate")
|
|
154
|
-
fixed_head = self.git("rev-parse", "HEAD")
|
|
155
|
-
(self.devlyn / "spec-verify.results.json").write_text(
|
|
156
|
-
json.dumps({"commands": [], "process_evidence": None}))
|
|
157
|
-
self.cli("build_gate", "transition", "--verdict", "PASS", "--next-phase", "cleanup",
|
|
158
|
-
"--next-round", "1", "--next-pre-sha", fixed_head)
|
|
159
|
-
(self.devlyn / "cleanup.findings.jsonl").write_text("\n")
|
|
160
|
-
self.cli("cleanup", "transition", "--verdict", "PASS", "--post-sha", fixed_head,
|
|
161
|
-
"--next-phase", "verify", "--next-round", "1", "--next-engine", "claude")
|
|
162
|
-
|
|
163
|
-
def test_cleanup_repair_bypass_still_requires_durability(self):
|
|
164
|
-
self.cli("cleanup", "spawn", "--round", "0", "--pre-sha", self.head)
|
|
165
|
-
(self.devlyn / "cleanup.findings.jsonl").write_text("")
|
|
166
|
-
self.cli("cleanup", "transition", "--verdict", "FAIL", "--post-sha", self.head,
|
|
167
|
-
"--next-phase", "implement", "--next-round", "1", "--next-triggered-by", "cleanup",
|
|
168
|
-
"--next-engine", "claude")
|
|
169
|
-
self.git("commit", "--allow-empty", "-qm", "chore(pipeline): implement fix round 1")
|
|
170
|
-
pending = self.state()
|
|
171
|
-
for bypasses, phase in (([], "build_gate"), (["cleanup"], "build_gate"),
|
|
172
|
-
(["build-gate"], "cleanup"), (["build-gate", "cleanup"], "verify")):
|
|
173
|
-
with self.subTest(bypasses=bypasses):
|
|
174
|
-
(self.devlyn / "closure-durability.round-1.json").unlink(missing_ok=True)
|
|
175
|
-
self.save(dict(pending, bypasses=bypasses))
|
|
176
|
-
for wrong_round in ("0", "2"):
|
|
177
|
-
self.cli("implement", "transition", "--verdict", "PASS", "--next-phase", phase,
|
|
178
|
-
"--next-round", wrong_round, error="owner-cleanup-repair-route")
|
|
179
|
-
args = ("transition", "--verdict", "PASS", "--next-phase", phase,
|
|
180
|
-
"--next-round", "1", "--next-pre-sha", self.git("rev-parse", "HEAD"))
|
|
181
|
-
self.cli("implement", *args, error="closure-durability")
|
|
182
|
-
self.cli("implement", "durability-enforce", "--round", "1", "--origin-phase", "cleanup")
|
|
183
|
-
self.cli("implement", *args)
|
|
184
|
-
|
|
185
|
-
def test_historical_cleanup_cannot_take_owner_repair_edge(self):
|
|
186
|
-
self.cli("cleanup", "spawn", "--round", "0", "--engine", "claude", "--pre-sha", self.head)
|
|
187
|
-
for verdict in ("PASS", "FAIL"):
|
|
188
|
-
self.cli("cleanup", "transition", "--verdict", verdict,
|
|
189
|
-
"--next-phase", "implement", "--next-round", "1", "--next-triggered-by", "cleanup",
|
|
190
|
-
"--next-engine", "claude", error="owner-cleanup-failed")
|
|
191
|
-
self.cli("cleanup", "transition", "--verdict", "PASS", "--post-sha", self.head,
|
|
192
|
-
"--next-phase", "verify", "--next-round", "0", "--next-engine", "claude")
|
|
193
|
-
|
|
194
|
-
def test_dirty_cleanup_can_fail_honestly_but_cannot_verify(self):
|
|
195
|
-
self.cli("cleanup", "spawn", "--round", "0", "--pre-sha", self.head)
|
|
196
|
-
opened = self.state_path.read_bytes()
|
|
197
|
-
(self.work / "source.txt").write_text("BUILD left a tracked change\n")
|
|
198
|
-
self.cli("cleanup", "transition", "--verdict", "FAIL", "--post-sha", self.head,
|
|
199
|
-
"--next-phase", "verify", "--next-round", "0", error="repair before VERIFY")
|
|
200
|
-
self.cli("cleanup", "complete", "--verdict", "BLOCKED", "--post-sha", self.head)
|
|
201
|
-
self.assertEqual(self.state()["phases"]["cleanup"]["verdict"], "BLOCKED")
|
|
202
|
-
self.state_path.write_bytes(opened)
|
|
203
|
-
self.cli("cleanup", "transition", "--verdict", "FAIL", "--post-sha", self.head,
|
|
204
|
-
"--next-phase", "implement", "--next-round", "1", "--next-triggered-by", "cleanup",
|
|
205
|
-
"--next-engine", "claude")
|
|
206
|
-
self.assertEqual((self.work / "source.txt").read_text(), "BUILD left a tracked change\n")
|
|
207
|
-
|
|
208
|
-
def test_final_untracked_delta_cannot_bypass_scope(self):
|
|
209
|
-
(self.work / "user-existing.txt").write_text("preserve")
|
|
210
|
-
(self.devlyn / "untracked.baseline").write_text("user-existing.txt\n")
|
|
211
|
-
self.cli("cleanup", "spawn", "--round", "0", "--pre-sha", self.head)
|
|
212
|
-
(self.work / "outside-plan.txt").write_text("leak")
|
|
213
|
-
self.cli("cleanup", "complete", "--verdict", "PASS", "--post-sha", self.head,
|
|
214
|
-
error="owner-cleanup-untracked")
|
|
215
|
-
(self.work / "outside-plan.txt").unlink()
|
|
216
|
-
(self.devlyn / "untracked.baseline").unlink()
|
|
217
|
-
self.cli("cleanup", "complete", "--verdict", "PASS", "--post-sha", self.head,
|
|
218
|
-
error="owner-cleanup-untracked")
|
|
219
|
-
(self.devlyn / "untracked.baseline").write_text("user-existing.txt\n")
|
|
220
|
-
self.cli("cleanup", "complete", "--verdict", "PASS", "--post-sha", self.head)
|
|
221
|
-
self.assertEqual((self.work / "user-existing.txt").read_text(), "preserve")
|
|
222
|
-
|
|
223
|
-
def test_owner_cleanup_does_not_replace_selected_worker(self):
|
|
224
|
-
helper = runpy.run_path(str(SHARED / "state-phase-write.py"))
|
|
225
|
-
(self.devlyn / "engines.json").write_text(json.dumps({"roles": {
|
|
226
|
-
"worker": {"engine": "codex", "model": "gpt-6-astra", "effort": "high"}}}))
|
|
227
|
-
state = self.state()
|
|
228
|
-
frozen = helper["freeze_roles"](state, self.work, "codex")
|
|
229
|
-
self.save(state)
|
|
230
|
-
self.cli("cleanup", "spawn", "--round", "0", "--pre-sha", self.head)
|
|
231
|
-
self.assert_owner("cleanup")
|
|
232
|
-
self.assertEqual(self.state()["role_resolution"], frozen)
|
|
233
|
-
self.cli("implement", "spawn", "--round", "0", "--engine", "claude",
|
|
234
|
-
error="role-selection-mismatch")
|
|
235
|
-
|
|
236
|
-
|
|
237
|
-
if __name__ == "__main__":
|
|
238
|
-
unittest.main(verbosity=2)
|