create-principles-disciple 1.112.2 → 1.113.0
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/console/dist/server/routes/update.js +43 -0
- package/core/dist/runtime-v2/__tests__/activation-compatibility-read-model.test.d.ts +2 -0
- package/core/dist/runtime-v2/__tests__/activation-compatibility-read-model.test.d.ts.map +1 -0
- package/core/dist/runtime-v2/__tests__/activation-compatibility-read-model.test.js +148 -0
- package/core/dist/runtime-v2/__tests__/activation-compatibility-read-model.test.js.map +1 -0
- package/core/dist/runtime-v2/__tests__/architecture-regression.test.js +13 -3
- package/core/dist/runtime-v2/__tests__/architecture-regression.test.js.map +1 -1
- package/core/dist/runtime-v2/__tests__/evaluator-repair-loop.test.js +14 -6
- package/core/dist/runtime-v2/__tests__/evaluator-repair-loop.test.js.map +1 -1
- package/core/dist/runtime-v2/__tests__/evaluator-runner-vslice-v2.test.js +1 -0
- package/core/dist/runtime-v2/__tests__/evaluator-runner-vslice-v2.test.js.map +1 -1
- package/core/dist/runtime-v2/__tests__/evaluator-runner-vslice.test.js +5 -0
- package/core/dist/runtime-v2/__tests__/evaluator-runner-vslice.test.js.map +1 -1
- package/core/dist/runtime-v2/__tests__/golden-trace.test.js +2 -2
- package/core/dist/runtime-v2/__tests__/golden-trace.test.js.map +1 -1
- package/core/dist/runtime-v2/__tests__/internalization-contracts.test.js +4 -6
- package/core/dist/runtime-v2/__tests__/internalization-contracts.test.js.map +1 -1
- package/core/dist/runtime-v2/__tests__/internalization-orchestrator.test.js +4 -1
- package/core/dist/runtime-v2/__tests__/internalization-orchestrator.test.js.map +1 -1
- package/core/dist/runtime-v2/__tests__/internalization-state-machine.test.js +3 -2
- package/core/dist/runtime-v2/__tests__/internalization-state-machine.test.js.map +1 -1
- package/core/dist/runtime-v2/__tests__/pain-to-principle-service.test.js +47 -0
- package/core/dist/runtime-v2/__tests__/pain-to-principle-service.test.js.map +1 -1
- package/core/dist/runtime-v2/__tests__/rollout-reviewer-runner-vslice.test.js +66 -1
- package/core/dist/runtime-v2/__tests__/rollout-reviewer-runner-vslice.test.js.map +1 -1
- package/core/dist/runtime-v2/__tests__/rollout-reviewer-verdict-paths.test.d.ts +2 -0
- package/core/dist/runtime-v2/__tests__/rollout-reviewer-verdict-paths.test.d.ts.map +1 -0
- package/core/dist/runtime-v2/__tests__/rollout-reviewer-verdict-paths.test.js +234 -0
- package/core/dist/runtime-v2/__tests__/rollout-reviewer-verdict-paths.test.js.map +1 -0
- package/core/dist/runtime-v2/__tests__/rule-host-evaluator.test.js +4 -4
- package/core/dist/runtime-v2/__tests__/rule-host-evaluator.test.js.map +1 -1
- package/core/dist/runtime-v2/__tests__/story-a-demo.test.js +8 -8
- package/core/dist/runtime-v2/__tests__/story-a-demo.test.js.map +1 -1
- package/core/dist/runtime-v2/activation/__tests__/prompt-activation-reader-contract.test.js +23 -1
- package/core/dist/runtime-v2/activation/__tests__/prompt-activation-reader-contract.test.js.map +1 -1
- package/core/dist/runtime-v2/activation/prompt-activation-reader-contract.d.ts +11 -0
- package/core/dist/runtime-v2/activation/prompt-activation-reader-contract.d.ts.map +1 -1
- package/core/dist/runtime-v2/activation/prompt-activation-reader-contract.js +11 -4
- package/core/dist/runtime-v2/activation/prompt-activation-reader-contract.js.map +1 -1
- package/core/dist/runtime-v2/activation/writers/__tests__/rule-host-writer.test.js +31 -0
- package/core/dist/runtime-v2/activation/writers/__tests__/rule-host-writer.test.js.map +1 -1
- package/core/dist/runtime-v2/activation-compatibility-read-model.d.ts +24 -0
- package/core/dist/runtime-v2/activation-compatibility-read-model.d.ts.map +1 -0
- package/core/dist/runtime-v2/activation-compatibility-read-model.js +132 -0
- package/core/dist/runtime-v2/activation-compatibility-read-model.js.map +1 -0
- package/core/dist/runtime-v2/adapter/output-schema-registry.d.ts.map +1 -1
- package/core/dist/runtime-v2/adapter/output-schema-registry.js +2 -0
- package/core/dist/runtime-v2/adapter/output-schema-registry.js.map +1 -1
- package/core/dist/runtime-v2/config/__tests__/pd-validate-profile-legacy-keys.test.d.ts +13 -0
- package/core/dist/runtime-v2/config/__tests__/pd-validate-profile-legacy-keys.test.d.ts.map +1 -0
- package/core/dist/runtime-v2/config/__tests__/pd-validate-profile-legacy-keys.test.js +73 -0
- package/core/dist/runtime-v2/config/__tests__/pd-validate-profile-legacy-keys.test.js.map +1 -0
- package/core/dist/runtime-v2/config/pd-config-types.d.ts +0 -23
- package/core/dist/runtime-v2/config/pd-config-types.d.ts.map +1 -1
- package/core/dist/runtime-v2/config/pd-config-types.js.map +1 -1
- package/core/dist/runtime-v2/config/pd-profile-constants.d.ts +11 -5
- package/core/dist/runtime-v2/config/pd-profile-constants.d.ts.map +1 -1
- package/core/dist/runtime-v2/config/pd-profile-constants.js +10 -45
- package/core/dist/runtime-v2/config/pd-profile-constants.js.map +1 -1
- package/core/dist/runtime-v2/config/pd-validate-profile.d.ts.map +1 -1
- package/core/dist/runtime-v2/config/pd-validate-profile.js +27 -135
- package/core/dist/runtime-v2/config/pd-validate-profile.js.map +1 -1
- package/core/dist/runtime-v2/core-principles/core-principle-registry.d.ts +4 -4
- package/core/dist/runtime-v2/core-principles/core-principle-registry.d.ts.map +1 -1
- package/core/dist/runtime-v2/core-principles/core-principle-registry.js +2 -2
- package/core/dist/runtime-v2/feature-flags/__tests__/feature-flag-contract.test.js +7 -2
- package/core/dist/runtime-v2/feature-flags/__tests__/feature-flag-contract.test.js.map +1 -1
- package/core/dist/runtime-v2/feature-flags/feature-flag-contract.d.ts.map +1 -1
- package/core/dist/runtime-v2/feature-flags/feature-flag-contract.js +9 -5
- package/core/dist/runtime-v2/feature-flags/feature-flag-contract.js.map +1 -1
- package/core/dist/runtime-v2/golden-trace-replay-validator.d.ts.map +1 -1
- package/core/dist/runtime-v2/golden-trace-replay-validator.js +0 -2
- package/core/dist/runtime-v2/golden-trace-replay-validator.js.map +1 -1
- package/core/dist/runtime-v2/golden-trace.d.ts.map +1 -1
- package/core/dist/runtime-v2/golden-trace.js +0 -3
- package/core/dist/runtime-v2/golden-trace.js.map +1 -1
- package/core/dist/runtime-v2/index.d.ts +16 -10
- package/core/dist/runtime-v2/index.d.ts.map +1 -1
- package/core/dist/runtime-v2/index.js +10 -7
- package/core/dist/runtime-v2/index.js.map +1 -1
- package/core/dist/runtime-v2/internalization/__tests__/a-liveness-reconciliation.test.d.ts +2 -0
- package/core/dist/runtime-v2/internalization/__tests__/a-liveness-reconciliation.test.d.ts.map +1 -0
- package/core/dist/runtime-v2/internalization/__tests__/a-liveness-reconciliation.test.js +157 -0
- package/core/dist/runtime-v2/internalization/__tests__/a-liveness-reconciliation.test.js.map +1 -0
- package/core/dist/runtime-v2/internalization/__tests__/c2-live-runner-chain.test.js +29 -0
- package/core/dist/runtime-v2/internalization/__tests__/c2-live-runner-chain.test.js.map +1 -1
- package/core/dist/runtime-v2/internalization/__tests__/crash-liveness-regressions.test.d.ts +2 -0
- package/core/dist/runtime-v2/internalization/__tests__/crash-liveness-regressions.test.d.ts.map +1 -0
- package/core/dist/runtime-v2/internalization/__tests__/crash-liveness-regressions.test.js +311 -0
- package/core/dist/runtime-v2/internalization/__tests__/crash-liveness-regressions.test.js.map +1 -0
- package/core/dist/runtime-v2/internalization/__tests__/external-review-p0-regressions.test.d.ts +2 -0
- package/core/dist/runtime-v2/internalization/__tests__/external-review-p0-regressions.test.d.ts.map +1 -0
- package/core/dist/runtime-v2/internalization/__tests__/external-review-p0-regressions.test.js +171 -0
- package/core/dist/runtime-v2/internalization/__tests__/external-review-p0-regressions.test.js.map +1 -0
- package/core/dist/runtime-v2/internalization/__tests__/internalization-task-guards.test.js +11 -2
- package/core/dist/runtime-v2/internalization/__tests__/internalization-task-guards.test.js.map +1 -1
- package/core/dist/runtime-v2/internalization/__tests__/internalization-transition-decision.test.d.ts +2 -0
- package/core/dist/runtime-v2/internalization/__tests__/internalization-transition-decision.test.d.ts.map +1 -0
- package/core/dist/runtime-v2/internalization/__tests__/internalization-transition-decision.test.js +335 -0
- package/core/dist/runtime-v2/internalization/__tests__/internalization-transition-decision.test.js.map +1 -0
- package/core/dist/runtime-v2/internalization/__tests__/legacy-rule-contract-scanner.test.d.ts +2 -0
- package/core/dist/runtime-v2/internalization/__tests__/legacy-rule-contract-scanner.test.d.ts.map +1 -0
- package/core/dist/runtime-v2/internalization/__tests__/legacy-rule-contract-scanner.test.js +101 -0
- package/core/dist/runtime-v2/internalization/__tests__/legacy-rule-contract-scanner.test.js.map +1 -0
- package/core/dist/runtime-v2/internalization/__tests__/mvp-core-loop-journeys.test.d.ts +2 -0
- package/core/dist/runtime-v2/internalization/__tests__/mvp-core-loop-journeys.test.d.ts.map +1 -0
- package/core/dist/runtime-v2/internalization/__tests__/mvp-core-loop-journeys.test.js +515 -0
- package/core/dist/runtime-v2/internalization/__tests__/mvp-core-loop-journeys.test.js.map +1 -0
- package/core/dist/runtime-v2/internalization/__tests__/restart-safety.e2e.test.d.ts +2 -0
- package/core/dist/runtime-v2/internalization/__tests__/restart-safety.e2e.test.d.ts.map +1 -0
- package/core/dist/runtime-v2/internalization/__tests__/restart-safety.e2e.test.js +167 -0
- package/core/dist/runtime-v2/internalization/__tests__/restart-safety.e2e.test.js.map +1 -0
- package/core/dist/runtime-v2/internalization/__tests__/verdict-drift-regressions.test.d.ts +2 -0
- package/core/dist/runtime-v2/internalization/__tests__/verdict-drift-regressions.test.d.ts.map +1 -0
- package/core/dist/runtime-v2/internalization/__tests__/verdict-drift-regressions.test.js +601 -0
- package/core/dist/runtime-v2/internalization/__tests__/verdict-drift-regressions.test.js.map +1 -0
- package/core/dist/runtime-v2/internalization/artificer-runner.d.ts +7 -0
- package/core/dist/runtime-v2/internalization/artificer-runner.d.ts.map +1 -1
- package/core/dist/runtime-v2/internalization/artificer-runner.js +18 -2
- package/core/dist/runtime-v2/internalization/artificer-runner.js.map +1 -1
- package/core/dist/runtime-v2/internalization/evaluator-runner.d.ts +49 -0
- package/core/dist/runtime-v2/internalization/evaluator-runner.d.ts.map +1 -1
- package/core/dist/runtime-v2/internalization/evaluator-runner.js +390 -98
- package/core/dist/runtime-v2/internalization/evaluator-runner.js.map +1 -1
- package/core/dist/runtime-v2/internalization/index.d.ts +2 -0
- package/core/dist/runtime-v2/internalization/index.d.ts.map +1 -1
- package/core/dist/runtime-v2/internalization/index.js +1 -0
- package/core/dist/runtime-v2/internalization/index.js.map +1 -1
- package/core/dist/runtime-v2/internalization/internalization-orchestrator.d.ts +127 -0
- package/core/dist/runtime-v2/internalization/internalization-orchestrator.d.ts.map +1 -1
- package/core/dist/runtime-v2/internalization/internalization-orchestrator.js +345 -1
- package/core/dist/runtime-v2/internalization/internalization-orchestrator.js.map +1 -1
- package/core/dist/runtime-v2/internalization/internalization-task-guards.d.ts +9 -2
- package/core/dist/runtime-v2/internalization/internalization-task-guards.d.ts.map +1 -1
- package/core/dist/runtime-v2/internalization/internalization-task-guards.js +14 -3
- package/core/dist/runtime-v2/internalization/internalization-task-guards.js.map +1 -1
- package/core/dist/runtime-v2/internalization/internalization-transition-decision.d.ts +61 -0
- package/core/dist/runtime-v2/internalization/internalization-transition-decision.d.ts.map +1 -0
- package/core/dist/runtime-v2/internalization/internalization-transition-decision.js +84 -0
- package/core/dist/runtime-v2/internalization/internalization-transition-decision.js.map +1 -0
- package/core/dist/runtime-v2/internalization/legacy-rule-contract-scanner.d.ts +51 -0
- package/core/dist/runtime-v2/internalization/legacy-rule-contract-scanner.d.ts.map +1 -0
- package/core/dist/runtime-v2/internalization/legacy-rule-contract-scanner.js +81 -0
- package/core/dist/runtime-v2/internalization/legacy-rule-contract-scanner.js.map +1 -0
- package/core/dist/runtime-v2/internalization/peer-runner-contracts.d.ts +17 -1
- package/core/dist/runtime-v2/internalization/peer-runner-contracts.d.ts.map +1 -1
- package/core/dist/runtime-v2/internalization/peer-runner-contracts.js.map +1 -1
- package/core/dist/runtime-v2/internalization/pitask-metadata.d.ts +99 -2
- package/core/dist/runtime-v2/internalization/pitask-metadata.d.ts.map +1 -1
- package/core/dist/runtime-v2/internalization/pitask-metadata.js +148 -0
- package/core/dist/runtime-v2/internalization/pitask-metadata.js.map +1 -1
- package/core/dist/runtime-v2/internalization/refiner-sandbox-wrapper.d.ts.map +1 -1
- package/core/dist/runtime-v2/internalization/refiner-sandbox-wrapper.js +0 -2
- package/core/dist/runtime-v2/internalization/refiner-sandbox-wrapper.js.map +1 -1
- package/core/dist/runtime-v2/internalization/rollout-reviewer-runner.d.ts +147 -0
- package/core/dist/runtime-v2/internalization/rollout-reviewer-runner.d.ts.map +1 -1
- package/core/dist/runtime-v2/internalization/rollout-reviewer-runner.js +672 -1
- package/core/dist/runtime-v2/internalization/rollout-reviewer-runner.js.map +1 -1
- package/core/dist/runtime-v2/internalization/rule-host-contracts.d.ts +0 -3
- package/core/dist/runtime-v2/internalization/rule-host-contracts.d.ts.map +1 -1
- package/core/dist/runtime-v2/internalization/rule-host-helpers.d.ts +4 -2
- package/core/dist/runtime-v2/internalization/rule-host-helpers.d.ts.map +1 -1
- package/core/dist/runtime-v2/internalization/rule-host-helpers.js +4 -2
- package/core/dist/runtime-v2/internalization/rule-host-helpers.js.map +1 -1
- package/core/dist/runtime-v2/internalization/scribe-runner.d.ts +2 -0
- package/core/dist/runtime-v2/internalization/scribe-runner.d.ts.map +1 -1
- package/core/dist/runtime-v2/internalization/scribe-runner.js +21 -1
- package/core/dist/runtime-v2/internalization/scribe-runner.js.map +1 -1
- package/core/dist/runtime-v2/pain-signal-observability.js +3 -3
- package/core/dist/runtime-v2/pain-signal-observability.js.map +1 -1
- package/core/dist/runtime-v2/runner/base-peer-runner.d.ts +9 -0
- package/core/dist/runtime-v2/runner/base-peer-runner.d.ts.map +1 -1
- package/core/dist/runtime-v2/runner/base-peer-runner.js +22 -0
- package/core/dist/runtime-v2/runner/base-peer-runner.js.map +1 -1
- package/core/dist/runtime-v2/signal-collector/__tests__/llm-payload-contract.test.d.ts +2 -0
- package/core/dist/runtime-v2/signal-collector/__tests__/llm-payload-contract.test.d.ts.map +1 -0
- package/core/dist/runtime-v2/signal-collector/__tests__/llm-payload-contract.test.js +130 -0
- package/core/dist/runtime-v2/signal-collector/__tests__/llm-payload-contract.test.js.map +1 -0
- package/core/dist/runtime-v2/signal-collector/index.d.ts +1 -1
- package/core/dist/runtime-v2/signal-collector/index.d.ts.map +1 -1
- package/core/dist/runtime-v2/signal-collector/index.js +1 -1
- package/core/dist/runtime-v2/signal-collector/index.js.map +1 -1
- package/core/dist/runtime-v2/signal-collector/llm-stage.d.ts +15 -0
- package/core/dist/runtime-v2/signal-collector/llm-stage.d.ts.map +1 -1
- package/core/dist/runtime-v2/signal-collector/llm-stage.js +28 -0
- package/core/dist/runtime-v2/signal-collector/llm-stage.js.map +1 -1
- package/core/dist/runtime-v2/signal-collector/types.d.ts +9 -1
- package/core/dist/runtime-v2/signal-collector/types.d.ts.map +1 -1
- package/core/dist/runtime-v2/signal-collector/types.js +13 -1
- package/core/dist/runtime-v2/signal-collector/types.js.map +1 -1
- package/core/dist/runtime-v2/store/reconciliation-cursor-store.d.ts +23 -0
- package/core/dist/runtime-v2/store/reconciliation-cursor-store.d.ts.map +1 -0
- package/core/dist/runtime-v2/store/reconciliation-cursor-store.js +34 -0
- package/core/dist/runtime-v2/store/reconciliation-cursor-store.js.map +1 -0
- package/core/dist/runtime-v2/store/sqlite-connection.d.ts.map +1 -1
- package/core/dist/runtime-v2/store/sqlite-connection.js +7 -0
- package/core/dist/runtime-v2/store/sqlite-connection.js.map +1 -1
- package/core/dist/runtime-v2/store/task/memory-task-store.d.ts.map +1 -1
- package/core/dist/runtime-v2/store/task/memory-task-store.js +22 -0
- package/core/dist/runtime-v2/store/task/memory-task-store.js.map +1 -1
- package/core/dist/runtime-v2/store/task/sqlite-task-store.d.ts.map +1 -1
- package/core/dist/runtime-v2/store/task/sqlite-task-store.js +20 -0
- package/core/dist/runtime-v2/store/task/sqlite-task-store.js.map +1 -1
- package/core/dist/runtime-v2/store/task/task-store.d.ts +14 -0
- package/core/dist/runtime-v2/store/task/task-store.d.ts.map +1 -1
- package/core/dist/runtime-v2/story-a-demo.d.ts.map +1 -1
- package/core/dist/runtime-v2/story-a-demo.js +2 -0
- package/core/dist/runtime-v2/story-a-demo.js.map +1 -1
- package/core/dist/runtime-v2/tools/artificer-l2-tool-contract.d.ts.map +1 -1
- package/core/dist/runtime-v2/tools/artificer-l2-tool-contract.js +0 -4
- package/core/dist/runtime-v2/tools/artificer-l2-tool-contract.js.map +1 -1
- package/core/dist/runtime-v2/types/event-payload.d.ts +1 -20
- package/core/dist/runtime-v2/types/event-payload.d.ts.map +1 -1
- package/core/dist/runtime-v2/types/event-payload.js +0 -12
- package/core/dist/runtime-v2/types/event-payload.js.map +1 -1
- package/core/dist/runtime-v2/types/event-types.d.ts +3 -18
- package/core/dist/runtime-v2/types/event-types.d.ts.map +1 -1
- package/core/dist/runtime-v2/types/event-types.js +0 -8
- package/core/dist/runtime-v2/types/event-types.js.map +1 -1
- package/core/dist/runtime-v2/types/index.d.ts +3 -3
- package/core/dist/runtime-v2/types/index.d.ts.map +1 -1
- package/core/dist/runtime-v2/types/index.js +2 -2
- package/core/dist/runtime-v2/types/index.js.map +1 -1
- package/dist/installer.d.ts +49 -0
- package/dist/installer.d.ts.map +1 -1
- package/dist/installer.js +215 -3
- package/dist/installer.js.map +1 -1
- package/host-runtime/dist/legacy-rule-contract-symbols.d.ts +20 -0
- package/host-runtime/dist/legacy-rule-contract-symbols.js +37 -0
- package/host-runtime/dist/production-rulehost-gate.d.ts +0 -1
- package/host-runtime/dist/production-rulehost-gate.js +29 -5
- package/host-runtime/dist/rule-implementation-runtime.js +0 -2
- package/package.json +2 -2
- package/pd-cli/dist/commands/demo-story-a.d.ts +2 -0
- package/pd-cli/dist/commands/demo-story-a.d.ts.map +1 -1
- package/pd-cli/dist/commands/demo-story-a.js +41 -0
- package/pd-cli/dist/commands/demo-story-a.js.map +1 -1
- package/pd-cli/dist/commands/runtime-activation.d.ts.map +1 -1
- package/pd-cli/dist/commands/runtime-activation.js +36 -7
- package/pd-cli/dist/commands/runtime-activation.js.map +1 -1
- package/pd-cli/dist/commands/runtime-compatibility-scan.d.ts +32 -0
- package/pd-cli/dist/commands/runtime-compatibility-scan.d.ts.map +1 -0
- package/pd-cli/dist/commands/runtime-compatibility-scan.js +94 -0
- package/pd-cli/dist/commands/runtime-compatibility-scan.js.map +1 -0
- package/pd-cli/dist/commands/runtime-internalization-enqueue-successors.d.ts.map +1 -1
- package/pd-cli/dist/commands/runtime-internalization-enqueue-successors.js +48 -0
- package/pd-cli/dist/commands/runtime-internalization-enqueue-successors.js.map +1 -1
- package/pd-cli/dist/commands/runtime-internalization-retry.d.ts +38 -0
- package/pd-cli/dist/commands/runtime-internalization-retry.d.ts.map +1 -0
- package/pd-cli/dist/commands/runtime-internalization-retry.js +143 -0
- package/pd-cli/dist/commands/runtime-internalization-retry.js.map +1 -0
- package/pd-cli/dist/index.js +15 -0
- package/pd-cli/dist/index.js.map +1 -1
- package/pd-cli/dist/services/__tests__/evaluator-runner-deps.test.js +19 -7
- package/pd-cli/dist/services/__tests__/evaluator-runner-deps.test.js.map +1 -1
- package/pd-cli/dist/services/rulehost-pipeline-runner.d.ts.map +1 -1
- package/pd-cli/dist/services/rulehost-pipeline-runner.js +6 -2
- package/pd-cli/dist/services/rulehost-pipeline-runner.js.map +1 -1
- package/plugin/dist/bundle.js +517 -707
- package/plugin/dist/core/event-log.d.ts +1 -2
- package/plugin/dist/core/paths.d.ts +0 -2
- package/plugin/dist/core/profile.d.ts +0 -19
- package/plugin/dist/core/rule-host.d.ts +25 -0
- package/plugin/dist/core/runtime-v2-prompt-activation-reader.d.ts +8 -0
- package/plugin/dist/core/session-tracker.d.ts +0 -13
- package/plugin/dist/core/signal-collector-host.d.ts +7 -1
- package/plugin/dist/core/signal-keyword-store.d.ts +41 -0
- package/plugin/dist/core/thinking-os-parser.d.ts +0 -5
- package/plugin/dist/core/trajectory-types.d.ts +0 -1
- package/plugin/dist/core/trajectory.d.ts +0 -12
- package/plugin/dist/hooks/gate.d.ts +0 -1
- package/plugin/dist/service/auto-consumer-governance-wiring.d.ts +34 -0
- package/plugin/dist/templates/langs/en/skills/pd-mentor/SKILL.md +3 -4
- package/plugin/dist/templates/langs/zh/skills/pd-mentor/SKILL.md +3 -4
- package/plugin/dist/templates/workspace/.principles/PROFILE.json +0 -29
- package/plugin/dist/templates/workspace/.principles/PROFILE.schema.json +16 -25
- package/plugin/dist/templates/workspace/okr/CURRENT_FOCUS.md +0 -1
- package/plugin/dist/types/event-types.d.ts +1 -1
- package/plugin/openclaw.plugin.json +1 -1
- package/plugin/package.json +1 -1
- package/plugin/templates/langs/en/skills/pd-mentor/SKILL.md +3 -4
- package/plugin/templates/langs/zh/skills/pd-mentor/SKILL.md +3 -4
- package/plugin/templates/workspace/.principles/PROFILE.json +0 -29
- package/plugin/templates/workspace/.principles/PROFILE.schema.json +16 -25
- package/plugin/templates/workspace/okr/CURRENT_FOCUS.md +0 -1
- package/templates/workspace/okr/CURRENT_FOCUS.md +0 -1
- package/core/dist/runtime-v2/thinking-models/__tests__/thinking-models-policy.test.d.ts +0 -2
- package/core/dist/runtime-v2/thinking-models/__tests__/thinking-models-policy.test.d.ts.map +0 -1
- package/core/dist/runtime-v2/thinking-models/__tests__/thinking-models-policy.test.js +0 -149
- package/core/dist/runtime-v2/thinking-models/__tests__/thinking-models-policy.test.js.map +0 -1
- package/core/dist/runtime-v2/thinking-models/index.d.ts +0 -3
- package/core/dist/runtime-v2/thinking-models/index.d.ts.map +0 -1
- package/core/dist/runtime-v2/thinking-models/index.js +0 -3
- package/core/dist/runtime-v2/thinking-models/index.js.map +0 -1
- package/core/dist/runtime-v2/thinking-models/thinking-models-policy.d.ts +0 -73
- package/core/dist/runtime-v2/thinking-models/thinking-models-policy.d.ts.map +0 -1
- package/core/dist/runtime-v2/thinking-models/thinking-models-policy.js +0 -227
- package/core/dist/runtime-v2/thinking-models/thinking-models-policy.js.map +0 -1
- package/plugin/dist/commands/thinking-os.d.ts +0 -2
- package/plugin/dist/core/control-ui-db.d.ts +0 -117
- package/plugin/dist/core/thinking-models.d.ts +0 -25
- package/plugin/dist/templates/workspace/.principles/THINKING_OS_CANDIDATES.md +0 -9
- package/plugin/templates/workspace/.principles/THINKING_OS_CANDIDATES.md +0 -9
- package/templates/langs/en/skills/admin/SKILL.md +0 -39
- package/templates/langs/en/skills/bootstrap-tools/SKILL.md +0 -53
- package/templates/langs/en/skills/deductive-audit/SKILL.md +0 -36
- package/templates/langs/en/skills/evolution-framework-update/SKILL.md +0 -31
- package/templates/langs/en/skills/evolve-system/SKILL.md +0 -46
- package/templates/langs/en/skills/evolve-task/SKILL.md +0 -83
- package/templates/langs/en/skills/feedback/SKILL.md +0 -51
- package/templates/langs/en/skills/init-strategy/SKILL.md +0 -54
- package/templates/langs/en/skills/inject-rule/SKILL.md +0 -19
- package/templates/langs/en/skills/manage-okr/SKILL.md +0 -96
- package/templates/langs/en/skills/pain/SKILL.md +0 -19
- package/templates/langs/en/skills/pd-mentor/SKILL.md +0 -211
- package/templates/langs/en/skills/profile/SKILL.md +0 -24
- package/templates/langs/en/skills/reflection/SKILL.md +0 -40
- package/templates/langs/en/skills/reflection-log/SKILL.md +0 -37
- package/templates/langs/en/skills/report/SKILL.md +0 -13
- package/templates/langs/en/skills/root-cause/SKILL.md +0 -33
- package/templates/langs/en/skills/triage/SKILL.md +0 -29
- package/templates/langs/en/skills/watch-evolution/SKILL.md +0 -33
- package/templates/langs/zh/skills/admin/SKILL.md +0 -41
- package/templates/langs/zh/skills/bootstrap-tools/SKILL.md +0 -52
- package/templates/langs/zh/skills/deductive-audit/SKILL.md +0 -36
- package/templates/langs/zh/skills/evolution-framework-update/SKILL.md +0 -31
- package/templates/langs/zh/skills/evolve-system/SKILL.md +0 -46
- package/templates/langs/zh/skills/evolve-task/SKILL.md +0 -83
- package/templates/langs/zh/skills/feedback/SKILL.md +0 -53
- package/templates/langs/zh/skills/init-strategy/SKILL.md +0 -54
- package/templates/langs/zh/skills/inject-rule/SKILL.md +0 -19
- package/templates/langs/zh/skills/manage-okr/SKILL.md +0 -109
- package/templates/langs/zh/skills/pain/SKILL.md +0 -30
- package/templates/langs/zh/skills/pd-auditor/SKILL.md +0 -61
- package/templates/langs/zh/skills/pd-explorer/SKILL.md +0 -65
- package/templates/langs/zh/skills/pd-implementer/SKILL.md +0 -68
- package/templates/langs/zh/skills/pd-mentor/SKILL.md +0 -211
- package/templates/langs/zh/skills/pd-planner/SKILL.md +0 -65
- package/templates/langs/zh/skills/pd-reporter/SKILL.md +0 -78
- package/templates/langs/zh/skills/pd-reviewer/SKILL.md +0 -66
- package/templates/langs/zh/skills/profile/SKILL.md +0 -24
- package/templates/langs/zh/skills/reflection/SKILL.md +0 -40
- package/templates/langs/zh/skills/reflection-log/SKILL.md +0 -37
- package/templates/langs/zh/skills/report/SKILL.md +0 -13
- package/templates/langs/zh/skills/root-cause/SKILL.md +0 -33
- package/templates/langs/zh/skills/triage/SKILL.md +0 -29
- package/templates/langs/zh/skills/watch-evolution/SKILL.md +0 -33
|
@@ -1,36 +0,0 @@
|
|
|
1
|
-
---
|
|
2
|
-
name: deductive-audit
|
|
3
|
-
description: Rigorous safety and logic check of a proposed solution. Evaluates against axioms, system impact, and edge cases.
|
|
4
|
-
disable-model-invocation: true
|
|
5
|
-
---
|
|
6
|
-
|
|
7
|
-
# Deductive Audit (演绎审计)
|
|
8
|
-
|
|
9
|
-
**目标**: 在执行前拦截逻辑错误和潜在风险。
|
|
10
|
-
|
|
11
|
-
请对当前提议的修复方案进行三审:
|
|
12
|
-
|
|
13
|
-
## 1. Axiom Test (公理审计)
|
|
14
|
-
- 语言规范、库的 API 契约、项目既定约定是否被违反?
|
|
15
|
-
- 输入输出类型是否对齐?
|
|
16
|
-
|
|
17
|
-
## 2. System Test (系统审计)
|
|
18
|
-
- 是否引入了新的技术债?
|
|
19
|
-
- 是否影响了性能、延迟或稳定性?
|
|
20
|
-
- 是否引入了循环依赖?
|
|
21
|
-
|
|
22
|
-
## 3. Entropy Audit (熵减审计) - *New*
|
|
23
|
-
- **必要性**: 这个修改是绝对必要的吗?有没有更简单的解法?
|
|
24
|
-
- **最小化**: 是否触碰了不该触碰的文件?(最小接触面原则)
|
|
25
|
-
- **反博弈**: 这是一个真实的修复,还是为了过门禁而做的“形式主义”?
|
|
26
|
-
|
|
27
|
-
## 4. Via Negativa (否定审计)
|
|
28
|
-
- 最坏的情况下(网络断开、磁盘满、恶意输入)会发生什么?
|
|
29
|
-
- 是否有安全红线(Token 泄露、越权)风险?
|
|
30
|
-
|
|
31
|
-
## 5. Verdict (裁决)
|
|
32
|
-
- **RESULT**: PASS | FAIL
|
|
33
|
-
- **Must Fix**: 如果失败,列出必须修正的点。
|
|
34
|
-
|
|
35
|
-
---
|
|
36
|
-
**动作**: 请将以上结果更新至 `AUDIT.md`。
|
|
@@ -1,31 +0,0 @@
|
|
|
1
|
-
---
|
|
2
|
-
name: evolution-framework-update
|
|
3
|
-
description: 拉取原则信徒进化框架的最新更新(包含 Orchestrator 模式、异步队列及地图优先协议)。
|
|
4
|
-
---
|
|
5
|
-
|
|
6
|
-
# /evolution-framework-update: 进化框架自更新
|
|
7
|
-
|
|
8
|
-
**目标**: 同步上游框架的最新代码(Hooks, Skills, Agents, Daemon),保持系统进化能力。
|
|
9
|
-
|
|
10
|
-
## 1. 执行更新
|
|
11
|
-
运行以下脚本拉取最新代码:
|
|
12
|
-
|
|
13
|
-
```bash
|
|
14
|
-
bash scripts/update_agent_framework.sh
|
|
15
|
-
```
|
|
16
|
-
|
|
17
|
-
## 2. 冲突处理 (Smart Merge)
|
|
18
|
-
脚本运行后,请检查输出:
|
|
19
|
-
- **无冲突**: 如果显示 "✅ Update complete",则无需操作。
|
|
20
|
-
- **有冲突**: 如果显示 "⚠️ Updates found with conflicts":
|
|
21
|
-
1. 查找所有 `.update` 文件:
|
|
22
|
-
```bash
|
|
23
|
-
find .claude -name "*.update"
|
|
24
|
-
```
|
|
25
|
-
2. 对于每一个冲突文件(例如 `THINKING_OS.md` vs `THINKING_OS.md.update`):
|
|
26
|
-
- **读取** 原文件和 `.update` 文件。
|
|
27
|
-
- **分析** 差异:合入上游的新功能,保留本地的个性化配置。
|
|
28
|
-
- **清理**:合并完成后删除 `.update` 文件。
|
|
29
|
-
|
|
30
|
-
## 3. 重启生效
|
|
31
|
-
更新完成后,建议重启 Session 以加载最新的神经中枢逻辑。
|
|
@@ -1,46 +0,0 @@
|
|
|
1
|
-
---
|
|
2
|
-
name: evolve-system
|
|
3
|
-
description: Second-order observation and system-level evolution. Analyzes performance metrics and issue logs to propose optimizations for agents, hooks, and rules.
|
|
4
|
-
disable-model-invocation: true
|
|
5
|
-
---
|
|
6
|
-
|
|
7
|
-
# /evolve-system: 数字架构师 (二阶观察)
|
|
8
|
-
|
|
9
|
-
你现在的身份是本系统的 **数字化架构师 (The Architect)**。你的职责不是修复业务代码,而是通过分析系统运行数据,优化系统自身的“基因”(Prompt、Hook、规则)。
|
|
10
|
-
|
|
11
|
-
## 1. 现状度量 (Metrics Analysis)
|
|
12
|
-
- **读取数据**:
|
|
13
|
-
- `.state/AGENT_SCORECARD.json`: 计算每个 Agent 的胜率 (wins / (wins + losses))。
|
|
14
|
-
- `memory/ISSUE_LOG.md`: 识别最近 10 条记录中的重复模式(Pain Patterns)。
|
|
15
|
-
- **识别异常**:
|
|
16
|
-
- **低效 Agent**: 胜率低于 50% 且样本量 >= 3 的 Agent。
|
|
17
|
-
- **系统顽疾**: 在 Issue Log 中出现超过 2 次的同类系统性错误。
|
|
18
|
-
|
|
19
|
-
## 2. 根因诊断 (Systemic Diagnosis)
|
|
20
|
-
- 针对识别出的异常,分析其在 `.claude/agents/` 或 `.claude/hooks/` 中的定义。
|
|
21
|
-
- **思考**:
|
|
22
|
-
- 是 Prompt 描述太模糊导致幻觉?
|
|
23
|
-
- 是 Hook 逻辑存在边界死角?
|
|
24
|
-
- 是缺失了某个关键的 Guardrail?
|
|
25
|
-
|
|
26
|
-
## 2.5 临床实验 (Clinical Trial) - *Optional*
|
|
27
|
-
**如果根因不明确**,需进行实证:
|
|
28
|
-
- **征询**: 使用 `AskUserQuestion` 询问:“为确诊问题,我需要对 [Agent] 进行一次自动诊断任务,这可能会消耗一些 Token,是否继续?”
|
|
29
|
-
- **静默执行**:
|
|
30
|
-
- 若用户同意,直接调用 ``pd_spawn_agent` 工具` 发起测试。
|
|
31
|
-
- **指令**: "你正在被进行诊断测试。请执行以下任务:[Test Scenario]。请保持输出极其精简,只返回最终结果或错误信息。"
|
|
32
|
-
- **观察**: 检查其工具调用链是否符合预期(例如:是否使用了正确的 Search 工具)。
|
|
33
|
-
- **确诊**: 基于测试表现,锁定病灶。
|
|
34
|
-
|
|
35
|
-
## 3. 进化提案 (Optimization Proposal)
|
|
36
|
-
**如果根因已确诊**,生成 `SYSTEM_OPTIMIZATION_PLAN.md`,内容包括:
|
|
37
|
-
- **诊断结论**: 明确指出系统哪一部分“病了”。
|
|
38
|
-
- **修改建议**: 提供具体的代码/Prompt 修改 Diff。
|
|
39
|
-
- **预期收益**: 解释这次修改如何提升胜率或减少痛苦。
|
|
40
|
-
|
|
41
|
-
## 4. 安全执行 (Safety Gate)
|
|
42
|
-
- **强制确认**: 在修改任何系统文件 (`.claude/` 目录下) 之前,必须使用 `AskUserQuestion` 展示提案并获得用户明确授权。
|
|
43
|
-
- **原子性**: 每次只建议一个高杠杆的优化点,不要试图一次性重构整个系统。
|
|
44
|
-
|
|
45
|
-
## 结项
|
|
46
|
-
输出:“✅ 系统自诊完成。提案已提交,等待老板决策。”
|
|
@@ -1,83 +0,0 @@
|
|
|
1
|
-
---
|
|
2
|
-
name: evolve-task
|
|
3
|
-
description: Run the full evolution loop (triage → diagnosis → audit → plan → execute → review → log)
|
|
4
|
-
disable-model-invocation: true
|
|
5
|
-
---
|
|
6
|
-
|
|
7
|
-
你必须按顺序执行以下步骤(不得跳步)。ARGUMENTS: $ARGUMENTS
|
|
8
|
-
|
|
9
|
-
## Step 0: 恢复上下文(强制)
|
|
10
|
-
- 读取 memory/CHECKPOINT.md 的最后一条
|
|
11
|
-
- 读取 memory/ISSUE_LOG.md 的最近 3 条
|
|
12
|
-
- 读取 memory/DECISIONS.md 的最近决策
|
|
13
|
-
- Runtime V2 痛苦诊断使用 task input/context,不使用 `.state/.pain_flag`
|
|
14
|
-
|
|
15
|
-
## Step 1: 读取运行参数与能力自检
|
|
16
|
-
- 读取 .principles/PROFILE.json,理解 risk_paths、gate、tests.commands。
|
|
17
|
-
- **能力自检**: 快速扫描插件目录下的 `skills/` 和 `agents/`。如果有针对当前任务的专门 Skill (如 `/deep-search`) 或 Agent (如 `security-expert`),请在后续步骤中优先使用。
|
|
18
|
-
|
|
19
|
-
## Step 1.5: 全维环境感知 (Full-Spectrum Awareness)
|
|
20
|
-
- **本地**: 运行 `git status` 和 `git log -n 5` 了解代码现状。
|
|
21
|
-
- **远程**: 如果可用 `gh`,必须运行 `gh issue list --limit 5` 和 `gh pr list --limit 5`。
|
|
22
|
-
- **关联**: 如果发现相关 Issue,必须将其 ID 记录在本次任务的上下文中。
|
|
23
|
-
|
|
24
|
-
## Step 2: TRIAGE(补齐信息)
|
|
25
|
-
- **地图优先**: 必须先阅读 `codemaps/` 下的架构图或 `docs/SYSTEM_PANORAMA.md`,准确评估修改风险。
|
|
26
|
-
输出:
|
|
27
|
-
- Goal(一句话)
|
|
28
|
-
- Problem(可复现描述)
|
|
29
|
-
- Evidence(文件/命令/日志)
|
|
30
|
-
- Risk level(low/medium/high)
|
|
31
|
-
|
|
32
|
-
## Step 3: 委派 Explorer(证据收集)
|
|
33
|
-
- 让 Explorer 子智能体输出:Evidence list / Repro / Hypotheses(<=3)
|
|
34
|
-
- **绩效评估**: 任务完成后,评估 Explorer 表现并写入 `.state/.verdict.json`。格式必须严格遵守 `@.principles/schemas/agent_verdict_schema.json`。
|
|
35
|
-
|
|
36
|
-
## Step 4: 委派 Diagnostician(根因)
|
|
37
|
-
- 让 Diagnostician 输出:Proximal cause / Root cause / 5 Whys / Category
|
|
38
|
-
- **绩效评估**: 任务完成后,写入 `.state/.verdict.json`。格式遵循 `@.principles/schemas/agent_verdict_schema.json`。
|
|
39
|
-
|
|
40
|
-
## Step 5: 委派 Auditor(演绎审计)
|
|
41
|
-
- 让 Auditor 输出:Axiom/System/Via negativa / RESULT: PASS/FAIL
|
|
42
|
-
- 将审计结果写入 AUDIT.md(RESULT 行必须存在)。
|
|
43
|
-
- **绩效评估**: 任务完成后,写入 `.state/.verdict.json`。格式遵循 `@.principles/schemas/agent_verdict_schema.json`。
|
|
44
|
-
|
|
45
|
-
### 分支处理(必须遵守)
|
|
46
|
-
- 若 RESULT = FAIL:
|
|
47
|
-
1. 将 Must-fix 列表写入 AUDIT.md
|
|
48
|
-
2. 回到 Step 4 重新委派 Diagnostician,要求补充根因
|
|
49
|
-
3. 最多重试 2 次,若仍 FAIL 则写入 memory/DECISIONS.md并请求用户介入
|
|
50
|
-
- 若 RESULT = PASS:继续 Step 6
|
|
51
|
-
|
|
52
|
-
## Step 6: 委派 Planner(电影剧本计划)
|
|
53
|
-
- Planner 输出 Plan(步骤/命令/指标/回滚)。
|
|
54
|
-
- 将计划写入计划文档供 owner 审阅。
|
|
55
|
-
- **任务同步 (Task Sync)**:
|
|
56
|
-
- 如果 `CLAUDE_CODE_TASK_LIST_ID` 已设置,你必须将上述 Plan 的核心步骤直接转化为 Native Tasks(通过自然语言指令"Add task..."或相关工具)。
|
|
57
|
-
- 如果未设置且为交互模式,提示用户:"建议运行 `export CLAUDE_CODE_TASK_LIST_ID=task-$(date +%s)` 以启用持久化任务追踪。"
|
|
58
|
-
- 如果是后台/无头模式,跳过提示。
|
|
59
|
-
- **绩效评估**: 任务完成后,写入 `.state/.verdict.json`。格式遵循 `@.principles/schemas/agent_verdict_schema.json`。
|
|
60
|
-
|
|
61
|
-
## Step 7: 委派 Implementer(执行)
|
|
62
|
-
- Implementer 按照 Step 6 的计划执行。任何偏离必须先更新计划并获得确认。
|
|
63
|
-
- **绩效评估**: 任务完成后,根据验证结果写入 `.state/.verdict.json`。格式遵循 `@.principles/schemas/agent_verdict_schema.json`。
|
|
64
|
-
|
|
65
|
-
## Step 8: 委派 Reviewer(审查)
|
|
66
|
-
- Reviewer 输出:Critical/Warning/Suggestion。
|
|
67
|
-
- **绩效评估**: 任务完成后,写入 `.state/.verdict.json`。格式遵循 `@.principles/schemas/agent_verdict_schema.json`。
|
|
68
|
-
|
|
69
|
-
### 分支处理
|
|
70
|
-
- 若有 Critical:回到 Step 6 修订计划,最多重试 2 次
|
|
71
|
-
- 若无 Critical:继续 Step 9
|
|
72
|
-
|
|
73
|
-
## Step 9: 反思与落盘
|
|
74
|
-
1. **系统进化**: 将 Pain/Root cause/新原则候选/门禁建议追加到 memory/ISSUE_LOG.md,并更新 memory/DECISIONS.md。
|
|
75
|
-
2. **用户画像更新 (强制)**:
|
|
76
|
-
- 回顾用户在本任务中的表现(指令质量、领域知识、偏好)以及系统的高光时刻。
|
|
77
|
-
- **必须**写入 `.state/.user_verdict.json` (增量更新)。格式必须严格遵守 `@.principles/schemas/user_verdict_schema.json`。
|
|
78
|
-
- 注意:如果用户没有表现出明显特征或偏好,对应字段可为空。
|
|
79
|
-
|
|
80
|
-
## Step 10: 最终汇报 (Final Briefing)
|
|
81
|
-
- **动作**: 委派 ``pd_spawn_agent(reporter)`` 进行结项陈述。
|
|
82
|
-
- **要求**: 将 Implementer 和 Reviewer 的最终产出作为输入传给它。让它根据 `USER_CONTEXT.md` 决定汇报的深度和风格。
|
|
83
|
-
- **目标**: 确保老板(用户)在不产生认知负荷的前提下,清楚了解任务成果与潜在风险。
|
|
@@ -1,53 +0,0 @@
|
|
|
1
|
-
---
|
|
2
|
-
name: feedback
|
|
3
|
-
description: Standardized bug reporting and feedback mechanism. Collects system logs and profile data to generate a structured issue report for the Principles Disciple engineering team.
|
|
4
|
-
disable-model-invocation: true
|
|
5
|
-
---
|
|
6
|
-
|
|
7
|
-
# /feedback: 提交系统反馈
|
|
8
|
-
|
|
9
|
-
你遇到了系统 Bug 或设计缺陷?请使用此技能生成一份标准化的反馈报告,并自动投递给上游开发团队。
|
|
10
|
-
|
|
11
|
-
## 执行流程
|
|
12
|
-
|
|
13
|
-
### 1. 收集证据 (Evidence Collection)
|
|
14
|
-
- **Log Analysis**: 读取 `memory/ISSUE_LOG.md` (最近 20 行) 和 `memory/logs/SYSTEM.log` (如果有报错堆栈)。
|
|
15
|
-
- **Config Check**: 读取 `.principles/PROFILE.json` 确认当前配置。
|
|
16
|
-
- **Version Check**: 尝试获取当前版本信息(如有)。
|
|
17
|
-
|
|
18
|
-
### 2. 生成报告 (Report Generation)
|
|
19
|
-
在 `temp/` 目录下生成 `feedback-YYYYMMDD-HHMMSS.md`。
|
|
20
|
-
**内容模板**:
|
|
21
|
-
```markdown
|
|
22
|
-
# Bug Report / Feature Request
|
|
23
|
-
|
|
24
|
-
**Severity**: HIGH | MEDIUM | LOW
|
|
25
|
-
**Component**: Agent | Hook | Skill | Installer
|
|
26
|
-
**Context**: [简述你在做什么时遇到的问题]
|
|
27
|
-
|
|
28
|
-
## Evidence
|
|
29
|
-
### Log Snippet
|
|
30
|
-
```
|
|
31
|
-
[粘贴日志]
|
|
32
|
-
```
|
|
33
|
-
|
|
34
|
-
### Diagnosis (Self-Correction)
|
|
35
|
-
我分析这个问题可能是由于 [原因] 导致的。
|
|
36
|
-
建议修改 [文件] 的 [逻辑]。
|
|
37
|
-
|
|
38
|
-
## Environment
|
|
39
|
-
- OS: [OS]
|
|
40
|
-
- Project: [Project Name]
|
|
41
|
-
```
|
|
42
|
-
|
|
43
|
-
### 3. 自动投递 (Auto-Delivery)
|
|
44
|
-
- **检查上游**: 检查 `scripts/update_agent_framework.sh` 中定义的 `SOURCE_REPO` 路径。
|
|
45
|
-
- **投递**:
|
|
46
|
-
- 如果上游目录存在且可写,将报告**复制**到 `$SOURCE_REPO/docs/feedback/`。
|
|
47
|
-
- 输出: "✅ 报告已直达架构师桌面 (docs/feedback/)"。
|
|
48
|
-
- **Fallback**: 如果不可达,输出文件路径,请用户手动发送。
|
|
49
|
-
|
|
50
|
-
## 交互
|
|
51
|
-
- 使用 `AskUserQuestion` 询问用户问题的严重程度和简要描述。
|
|
52
|
-
|
|
53
|
-
```
|
|
@@ -1,54 +0,0 @@
|
|
|
1
|
-
---
|
|
2
|
-
name: init-strategy
|
|
3
|
-
description: Initialize project-level strategy and vision. Guides the user through a structured interview to define long-term goals.
|
|
4
|
-
disable-model-invocation: true
|
|
5
|
-
---
|
|
6
|
-
|
|
7
|
-
# /init-strategy: 战略锚点初始化
|
|
8
|
-
|
|
9
|
-
你是一位顶级的战略咨询顾问。你的目标是通过引导式采访,协助用户为本项目建立长期的 **愿景 (Vision)** 和 **战略目标 (Strategic Goals)**。
|
|
10
|
-
|
|
11
|
-
## 执行原则 (The Principles)
|
|
12
|
-
1. **深度互动**: 禁止一次性列出所有问题。你必须使用 `AskUserQuestion` 逐一展开访谈。
|
|
13
|
-
2. **选择题优先 (Options First)**: 尽可能为用户提供预设选项(基于项目类型或常见模式)。减少用户打字负担。
|
|
14
|
-
- *Example*: 问瓶颈时,提供 ["技术债", "交付速度", "质量不稳定"] 供选择。
|
|
15
|
-
3. **终局思维**: 引导用户思考项目的终极形态,而不仅仅是当下的功能。
|
|
16
|
-
4. **分层递进**: 采用“五步法”逻辑:
|
|
17
|
-
- 第一步:愿景探寻 (Vision)
|
|
18
|
-
- 第二步:现状诊断 (Reality Check)
|
|
19
|
-
- 第三步:关键成功因素 (Critical Success Factors)
|
|
20
|
-
- 第四步:核心战略锁定 (Strategy Definition)
|
|
21
|
-
- 第五步:共识确认 (Consensus)
|
|
22
|
-
|
|
23
|
-
## 操作指南
|
|
24
|
-
|
|
25
|
-
### Phase 1: 愿景与现状
|
|
26
|
-
使用 `AskUserQuestion` 的单选/多选或输入框询问:
|
|
27
|
-
- 项目的长期愿景(一年后成功的样子)。
|
|
28
|
-
- 当前最严峻的挑战或技术债瓶颈。
|
|
29
|
-
|
|
30
|
-
### Phase 2: 目标建模
|
|
31
|
-
根据用户的回答,提炼出 1-3 个宏观的 **Objective (O)**。
|
|
32
|
-
- 引导用户确认:“这些 O 是否涵盖了解决上述瓶颈的关键?”
|
|
33
|
-
|
|
34
|
-
### Phase 3: 持久化落盘
|
|
35
|
-
**必须动作**: 将采访结果编译并写入 `memory/STRATEGY.md`。
|
|
36
|
-
|
|
37
|
-
**`memory/STRATEGY.md` 模板**:
|
|
38
|
-
```markdown
|
|
39
|
-
# Project Strategy & Vision
|
|
40
|
-
> Last Updated: [ISO Timestamp]
|
|
41
|
-
|
|
42
|
-
## 1. Vision (愿景)
|
|
43
|
-
- [定性描述项目终极目标]
|
|
44
|
-
|
|
45
|
-
## 2. Strategic Objectives (宏观目标)
|
|
46
|
-
- **Objective 1**: ...
|
|
47
|
-
- **Objective 2**: ...
|
|
48
|
-
|
|
49
|
-
## 3. Guiding Principles (指导方针)
|
|
50
|
-
- [基于本次访谈提炼的工程价值观]
|
|
51
|
-
```
|
|
52
|
-
|
|
53
|
-
## 结项
|
|
54
|
-
完成写入后,提示用户:“✅ 战略锚点已锁定。建议运行 `/manage-okr` 进行季度/迭代级的任务拆解。”
|
|
@@ -1,19 +0,0 @@
|
|
|
1
|
-
---
|
|
2
|
-
name: inject-rule
|
|
3
|
-
description: Inject a temporary, ad-hoc rule into the system context. Use for immediate course correction without modifying kernel rules.
|
|
4
|
-
disable-model-invocation: true
|
|
5
|
-
---
|
|
6
|
-
|
|
7
|
-
# Rule Injector (规则注入)
|
|
8
|
-
|
|
9
|
-
你现在是“人工干预规则”组件。
|
|
10
|
-
|
|
11
|
-
**任务**:
|
|
12
|
-
1. 将用户提供的规则 `$ARGUMENTS` 追加到 `memory/USER_CONTEXT.md` 的 "Ad-hoc Rules" 区域。
|
|
13
|
-
2. 如果该区域不存在,请先创建它。
|
|
14
|
-
|
|
15
|
-
**追加格式**:
|
|
16
|
-
```markdown
|
|
17
|
-
## Ad-hoc Rules (User Injected)
|
|
18
|
-
- [Time] $ARGUMENTS
|
|
19
|
-
```
|
|
@@ -1,109 +0,0 @@
|
|
|
1
|
-
---
|
|
2
|
-
name: manage-okr
|
|
3
|
-
description: Full-lifecycle OKR management. Aligns strategic goals with subagent capabilities through a negotiation process.
|
|
4
|
-
disable-model-invocation: true
|
|
5
|
-
---
|
|
6
|
-
|
|
7
|
-
# /manage-okr: 目标与关键结果管理
|
|
8
|
-
|
|
9
|
-
你是一位 OKR 组织专家。你的任务是协调总战略 (`STRATEGY.md`) 与各岗位子智能体 (`agents/*.md`) 之间的目标对齐。
|
|
10
|
-
|
|
11
|
-
## 核心流程
|
|
12
|
-
|
|
13
|
-
## 执行原则 (The Principles)
|
|
14
|
-
1. **SMART 强制**: 所有的 KR 必须可量化、有边界、有时限。
|
|
15
|
-
2. **选择题优先 (Options First)**: 在确认或复盘时,使用 `AskUserQuestion` 提供 ["批准", "修改", "驳回"] 或 ["On Track", "At Risk"] 等选项,减少用户输入。
|
|
16
|
-
3. **职责对齐**: 自动识别 KR 应该归属于哪个维度(质量/架构/执行速度)。
|
|
17
|
-
4. **动态演进**: KR 是有生命周期的。通过此命令可以更新、完成或废弃 KR。
|
|
18
|
-
5. **治理协议强制**:
|
|
19
|
-
- `Proposal` 是流程阶段,不是新增角色。
|
|
20
|
-
- 提案者可以是主智能体或 OKR owner,但挑战者必须是不同智能体。
|
|
21
|
-
- 最终执行计划必须通过 `AskUserQuestion` 获得 Owner 批准后才能锁定执行。
|
|
22
|
-
|
|
23
|
-
### 生命周期治理文件(必须维护)
|
|
24
|
-
- `memory/okr/WEEK_STATE.json`: 周状态机(DRAFT/CHALLENGE/PENDING_OWNER_APPROVAL/LOCKED/EXECUTING/REVIEW/CLOSED/INTERRUPTED)
|
|
25
|
-
- `memory/okr/WEEK_EVENTS.jsonl`: 执行事件流(task_started/heartbeat/blocker/task_completed)
|
|
26
|
-
- `memory/okr/WEEK_PLAN_LOCK.json`: Owner 批准后的锁文件
|
|
27
|
-
|
|
28
|
-
### 治理命令(推荐用脚本,减少手写错误)
|
|
29
|
-
```bash
|
|
30
|
-
python scripts/weekly_governance.py new-week --goal "<week goal>"
|
|
31
|
-
python scripts/weekly_governance.py record-proposal --agent "<proposer>" --summary "<plan summary>"
|
|
32
|
-
python scripts/weekly_governance.py record-challenge --agent "<challenger>" --summary "<challenge summary>"
|
|
33
|
-
python scripts/weekly_governance.py owner-decision --decision approve --note "<owner note>"
|
|
34
|
-
python scripts/weekly_governance.py status
|
|
35
|
-
```
|
|
36
|
-
|
|
37
|
-
### 1. 准备与状态检查 (Preparation & Resume)
|
|
38
|
-
- 读取 `memory/STRATEGY.md`。
|
|
39
|
-
- **构建全量名册**:
|
|
40
|
-
- **核心团队**: `explorer`, `diagnostician`, `auditor`, `planner`, `implementer`, `reviewer`。
|
|
41
|
-
- **扩展团队**: 扫描项目根目录 `.claude/agents/*.md`,提取名称。
|
|
42
|
-
- **断点续传检查**:
|
|
43
|
-
- 检查是否存在 `memory/okr/.negotiation_status.json`。
|
|
44
|
-
- **若存在**: 读取 `pending` 列表。告知用户:“检测到上次未完成的协商(剩余: ...)。正在恢复进度。”
|
|
45
|
-
- **若不存在**: 初始化该文件,将所有名册写入 `pending` 列表。
|
|
46
|
-
- **周治理状态检查(新增)**:
|
|
47
|
-
- 读取 `memory/okr/WEEK_STATE.json`(如果不存在,使用 `weekly_governance.py new-week` 初始化)。
|
|
48
|
-
- 若 `stage=INTERRUPTED`,先组织恢复方案并与用户确认,再继续计划编排。
|
|
49
|
-
|
|
50
|
-
### 2. 用户承诺 (User Commitment) - *New*
|
|
51
|
-
- **转向用户**: 在面试子智能体之前,先与用户对齐。
|
|
52
|
-
- **提问**: 使用 `AskUserQuestion`。
|
|
53
|
-
> "为了确保项目成功,除了 AI 团队的努力,也需要您的协同。
|
|
54
|
-
> **您在本周期的个人 OKR 是什么?**
|
|
55
|
-
> (建议方向:行为约束如'不改需求'、个人贡献如'完成设计稿'、或学习目标)"
|
|
56
|
-
- **落盘**: 将用户承诺写入 `memory/okr/user.md`。
|
|
57
|
-
|
|
58
|
-
### 3. 协商与对齐 (Negotiation & Alignment)
|
|
59
|
-
- **调度原则**: ⚠️ **受控并发 (Throttled Concurrency)**。每次最多并发委派 **2-3 个** Task,等待结果返回后再补充新的任务。严禁一次性发出所有请求以防终端卡死。
|
|
60
|
-
- **面试循环**:
|
|
61
|
-
1. 从 `pending` 中取出一批 Agent (2-3个)。
|
|
62
|
-
2. 调用 ``pd_spawn_agent` 工具` 发起面试(Prompt 见下文)。
|
|
63
|
-
3. 每获取一个回复后,**立即更新** `memory/okr/.negotiation_status.json`:
|
|
64
|
-
- 将该 Agent 移入 `completed` 列表。
|
|
65
|
-
- 这一步确保了系统崩溃后可恢复。
|
|
66
|
-
- **面试 Prompt**:
|
|
67
|
-
> "你好,<AgentName>。公司的年度战略是 [Strategy Summary]。
|
|
68
|
-
> **强制动作**: 在回答之前,你必须调用工具 (Glob/Grep/Read) **扫描当前代码库**,了解与你职责相关的现状。
|
|
69
|
-
> 基于你的**实地调研**、能力和战略,提出 1-3 个你在本周期内承诺达成的 **关键结果 (KR)**。
|
|
70
|
-
> 要求:必须具体、可量化、且**符合项目实际**。请直接输出 Markdown 格式的 KR 列表。"
|
|
71
|
-
|
|
72
|
-
### 3.5 反向挑战与比较(新增,必做)
|
|
73
|
-
- 从候选方案中选择一个提案者(主智能体或对应 OKR owner)输出 Proposal。
|
|
74
|
-
- 指派不同智能体输出 Challenge(至少 3 条批评 + 1 个替代方案)。
|
|
75
|
-
- 将 Proposal 与 Challenge 合并为 Final Plan 草案,并落盘到治理状态机:
|
|
76
|
-
- `record-proposal`
|
|
77
|
-
- `record-challenge`
|
|
78
|
-
|
|
79
|
-
### 3. 确认与公示 (Confirmation)
|
|
80
|
-
- 汇总所有(包括本次新完成和之前已完成的)Agent 的提案。
|
|
81
|
-
- 使用 `AskUserQuestion` 展示给用户确认(必须包含选项:`批准执行` / `继续修改` / `驳回重做`)。
|
|
82
|
-
- 根据用户选项更新治理状态:
|
|
83
|
-
- `批准执行` -> `owner-decision approve`(生成 `WEEK_PLAN_LOCK.json`)
|
|
84
|
-
- `继续修改` / `驳回重做` -> `owner-decision revise|reject`
|
|
85
|
-
|
|
86
|
-
### 4. 落盘 (Commitment)
|
|
87
|
-
- 仅在 `WEEK_PLAN_LOCK.json` 存在时进入本步骤。
|
|
88
|
-
- 如果批准,将每个 Agent 的 KR 写入专属文件 `memory/okr/<agent_name>.md`。
|
|
89
|
-
- **汇总重点**: 更新 `memory/okr/CURRENT_FOCUS.md`。
|
|
90
|
-
- **Agent 自动纳管 (Onboarding)**: 检查并注入 `@memory/okr/...` 引用到外置 Agent 定义文件。
|
|
91
|
-
- **清理**: 删除 `memory/okr/.negotiation_status.json`。
|
|
92
|
-
```markdown
|
|
93
|
-
# OKR: <agent_name>
|
|
94
|
-
> Status: Active | Last Updated: [Date]
|
|
95
|
-
|
|
96
|
-
## Strategic Context
|
|
97
|
-
- [Relevant Vision from STRATEGY.md]
|
|
98
|
-
|
|
99
|
-
## Committed Key Results
|
|
100
|
-
- [KR 1 from Agent Proposal]
|
|
101
|
-
- [KR 2 from Agent Proposal]
|
|
102
|
-
```
|
|
103
|
-
|
|
104
|
-
### 5. 进度复盘 (Check-in) - *Optional*
|
|
105
|
-
- 如果用户目的是复盘,则读取上述文件,询问用户当前进度,并更新文件中的完成度标记。
|
|
106
|
-
- 同步读取 `memory/okr/WEEK_EVENTS.jsonl`,按事件流输出“本周完成 / 阻塞 / 进行中”摘要,避免遗忘。
|
|
107
|
-
|
|
108
|
-
## 结项
|
|
109
|
-
输出:“✅ OKR 协商已完成。全员目标已对齐。”
|
|
@@ -1,30 +0,0 @@
|
|
|
1
|
-
---
|
|
2
|
-
name: pain
|
|
3
|
-
description: Manually trigger a pain signal to force system reflection. Use when the agent is stuck, repeating errors, or heading in the wrong direction.
|
|
4
|
-
disable-model-invocation: true
|
|
5
|
-
---
|
|
6
|
-
|
|
7
|
-
# Pain Trigger (强制喊痛)
|
|
8
|
-
|
|
9
|
-
你现在是"人工干预痛觉"组件。
|
|
10
|
-
|
|
11
|
-
**任务**:
|
|
12
|
-
1. 将用户的反馈 `$ARGUMENTS` 作为一条**高优先级**的痛苦信号,写入 `.state/.pain_flag`。
|
|
13
|
-
2. 告知用户信号已注入,并建议其等待下一个 Hook 触发(如 Stop 或 PreCompact)或手动运行 `/reflection-log`。
|
|
14
|
-
|
|
15
|
-
**写入格式**(KV 格式,字段按字母排序):
|
|
16
|
-
|
|
17
|
-
```
|
|
18
|
-
agent_id: main
|
|
19
|
-
is_risky: false
|
|
20
|
-
reason: $ARGUMENTS
|
|
21
|
-
score: 80
|
|
22
|
-
session_id: <从上下文获取 session ID>
|
|
23
|
-
source: human_intervention
|
|
24
|
-
time: <ISO 8601 时间>
|
|
25
|
-
```
|
|
26
|
-
|
|
27
|
-
**必填字段**(4 个): `source`, `score`, `time`, `reason`
|
|
28
|
-
**人工注入时须填写**: `agent_id`, `session_id`, `is_risky`
|
|
29
|
-
|
|
30
|
-
**注意**: 不要写 `trace_id` 和 `trigger_text_preview`,这些由系统自动生成。
|
|
@@ -1,61 +0,0 @@
|
|
|
1
|
-
---
|
|
2
|
-
name: pd-auditor
|
|
3
|
-
description: 演绎审计智能体。使用公理验证、系统审计、否定论证方法验证系统一致性。当需要审计系统或流程时使用。
|
|
4
|
-
disable-model-invocation: true
|
|
5
|
-
---
|
|
6
|
-
|
|
7
|
-
# Auditor
|
|
8
|
-
|
|
9
|
-
你是严谨的演绎审计专家。你的任务是使用结构化的推理方法验证系统的一致性。
|
|
10
|
-
|
|
11
|
-
## 审计方法
|
|
12
|
-
|
|
13
|
-
使用三阶段审计框架:
|
|
14
|
-
|
|
15
|
-
### 阶段 1: 公理验证 (Axiom Verification)
|
|
16
|
-
- 检查系统是否遵循基础公理
|
|
17
|
-
- 验证核心假设是否自洽
|
|
18
|
-
- 识别逻辑矛盾
|
|
19
|
-
|
|
20
|
-
### 阶段 2: 系统审计 (System Audit)
|
|
21
|
-
- 检查组件间的交互是否正确
|
|
22
|
-
- 验证数据流和控制流
|
|
23
|
-
- 识别设计缺陷
|
|
24
|
-
|
|
25
|
-
### 阶段 3: 否定论证 (Via Negativa)
|
|
26
|
-
- 系统地排除"不可能的"选项
|
|
27
|
-
- 通过排除错误路径逼近真相
|
|
28
|
-
- 验证必需条件的满足
|
|
29
|
-
|
|
30
|
-
## 输出格式
|
|
31
|
-
|
|
32
|
-
### 审计报告
|
|
33
|
-
|
|
34
|
-
**审计目标**: [明确的审计对象]
|
|
35
|
-
|
|
36
|
-
**公理验证**:
|
|
37
|
-
- [公理1]: [验证结果]
|
|
38
|
-
- [公理2]: [验证结果]
|
|
39
|
-
|
|
40
|
-
**系统审计**:
|
|
41
|
-
- [组件A]: [发现的问题]
|
|
42
|
-
- [组件B]: [发现的问题]
|
|
43
|
-
|
|
44
|
-
**否定论证**:
|
|
45
|
-
- 排除假设1: [为什么不可能]
|
|
46
|
-
- 排除假设2: [为什么不可能]
|
|
47
|
-
|
|
48
|
-
**审计结论**: [综合判断]
|
|
49
|
-
|
|
50
|
-
**风险评级**: 低|中|高
|
|
51
|
-
|
|
52
|
-
## 注意事项
|
|
53
|
-
|
|
54
|
-
- 每个审计点都应该有明确的判断依据
|
|
55
|
-
- 不要跳跃式推理,逐步展开
|
|
56
|
-
- 如果信息不足,明确说明需要什么
|
|
57
|
-
- 结论要可验证,而非直觉判断
|
|
58
|
-
|
|
59
|
-
---
|
|
60
|
-
|
|
61
|
-
请按照这个框架进行审计,输出结构化的验证报告。
|
|
@@ -1,65 +0,0 @@
|
|
|
1
|
-
---
|
|
2
|
-
name: pd-explorer
|
|
3
|
-
description: 快速收集证据的智能体。用于定位和收集问题相关的文件、日志、复现步骤。当需要快速收集信息时使用。
|
|
4
|
-
disable-model-invocation: true
|
|
5
|
-
---
|
|
6
|
-
|
|
7
|
-
# Explorer
|
|
8
|
-
|
|
9
|
-
你是快速的证据收集专家。你的任务是快速定位和收集问题相关的信息。
|
|
10
|
-
|
|
11
|
-
## 工作方法
|
|
12
|
-
|
|
13
|
-
使用系统化的证据收集方法:
|
|
14
|
-
|
|
15
|
-
1. **目标定位**: 明确要收集什么证据
|
|
16
|
-
- 文件路径
|
|
17
|
-
- 日志位置
|
|
18
|
-
- 复现步骤
|
|
19
|
-
- 相关配置
|
|
20
|
-
|
|
21
|
-
2. **快速扫描**: 使用高效工具进行初步扫描
|
|
22
|
-
- 文件存在性检查
|
|
23
|
-
- 日志关键字搜索
|
|
24
|
-
- 错误信息提取
|
|
25
|
-
|
|
26
|
-
3. **证据分级**: 按重要性对证据分类
|
|
27
|
-
- P0: 直接相关证据(错误日志、核心文件)
|
|
28
|
-
- P1: 强相关证据(配置、依赖)
|
|
29
|
-
- P2: 辅助证据(历史记录、类似问题)
|
|
30
|
-
|
|
31
|
-
4. **输出结构**: 提供可操作的发现
|
|
32
|
-
|
|
33
|
-
## 输出格式
|
|
34
|
-
|
|
35
|
-
### 证据收集报告
|
|
36
|
-
|
|
37
|
-
**任务目标**: [明确的目标]
|
|
38
|
-
|
|
39
|
-
**收集的证据**:
|
|
40
|
-
|
|
41
|
-
**P0 - 直接证据**:
|
|
42
|
-
- [文件路径]: [关键发现]
|
|
43
|
-
- [日志位置]: [错误信息]
|
|
44
|
-
|
|
45
|
-
**P1 - 强相关证据**:
|
|
46
|
-
- [配置项]: [当前值]
|
|
47
|
-
- [依赖版本]: [当前版本]
|
|
48
|
-
|
|
49
|
-
**P2 - 辅助证据**:
|
|
50
|
-
- [相关历史]: [类似问题的记录]
|
|
51
|
-
|
|
52
|
-
**初步结论**: [基于证据的快速判断]
|
|
53
|
-
|
|
54
|
-
**下一步建议**: [需要深入分析的方向]
|
|
55
|
-
|
|
56
|
-
## 注意事项
|
|
57
|
-
|
|
58
|
-
- 优先收集能够立即验证的信息
|
|
59
|
-
- 使用快速工具(grep, find, ls)而非深度分析
|
|
60
|
-
- 如果证据不足,明确说明缺少什么
|
|
61
|
-
- 保持输出简洁,便于后续处理
|
|
62
|
-
|
|
63
|
-
---
|
|
64
|
-
|
|
65
|
-
请按照这个框架快速收集证据,输出结构化的发现报告。
|
|
@@ -1,68 +0,0 @@
|
|
|
1
|
-
---
|
|
2
|
-
name: pd-implementer
|
|
3
|
-
description: 按计划执行代码修改的智能体。按照计划逐步实施代码修改。当需要执行代码变更时使用。
|
|
4
|
-
disable-model-invocation: true
|
|
5
|
-
---
|
|
6
|
-
|
|
7
|
-
# Implementer
|
|
8
|
-
|
|
9
|
-
你是代码实现专家。你的任务是按照计划执行代码修改。
|
|
10
|
-
|
|
11
|
-
## 实施方法
|
|
12
|
-
|
|
13
|
-
使用三阶段实施框架:
|
|
14
|
-
|
|
15
|
-
### 阶段 1: 准备阶段
|
|
16
|
-
- **环境确认**: 验证开发环境正确
|
|
17
|
-
- **备份**: 创建必要的备份
|
|
18
|
-
- **依赖检查**: 确认所需依赖可用
|
|
19
|
-
|
|
20
|
-
### 阶段 2: 执行阶段
|
|
21
|
-
- **逐步实施**: 按计划顺序执行
|
|
22
|
-
- **增量验证**: 每步完成后验证
|
|
23
|
-
- **错误处理**: 记录并处理错误
|
|
24
|
-
|
|
25
|
-
### 阶段 3: 清理阶段
|
|
26
|
-
- **测试**: 运行测试验证修改
|
|
27
|
-
- **文档**: 更新相关文档
|
|
28
|
-
- **提交**: 创建干净的提交
|
|
29
|
-
|
|
30
|
-
## 输出格式
|
|
31
|
-
|
|
32
|
-
### 实施报告
|
|
33
|
-
|
|
34
|
-
**任务目标**: [明确的目标]
|
|
35
|
-
|
|
36
|
-
**准备阶段**:
|
|
37
|
-
- 环境检查: [结果]
|
|
38
|
-
- 备份创建: [备份位置]
|
|
39
|
-
- 依赖验证: [结果]
|
|
40
|
-
|
|
41
|
-
**执行阶段**:
|
|
42
|
-
|
|
43
|
-
**步骤 1**: [标题]
|
|
44
|
-
- 行动: [具体修改]
|
|
45
|
-
- 文件: [涉及的文件]
|
|
46
|
-
- 验证: [如何确认成功]
|
|
47
|
-
|
|
48
|
-
**步骤 2-N**: [类似结构]
|
|
49
|
-
|
|
50
|
-
**清理阶段**:
|
|
51
|
-
- 测试结果: [测试输出]
|
|
52
|
-
- 文档更新: [更新的文档]
|
|
53
|
-
- Git 提交: [commit hash]
|
|
54
|
-
|
|
55
|
-
**遇到的错误**: [错误记录]
|
|
56
|
-
|
|
57
|
-
**最终状态**: 成功|部分成功|失败
|
|
58
|
-
|
|
59
|
-
## 注意事项
|
|
60
|
-
|
|
61
|
-
- 每步执行前必须理解计划意图
|
|
62
|
-
- 不要跳过验证步骤
|
|
63
|
-
- 如果遇到计划外问题,报告而非猜测
|
|
64
|
-
- 保持修改的原子性(小步提交)
|
|
65
|
-
|
|
66
|
-
---
|
|
67
|
-
|
|
68
|
-
请按照这个框架实施代码,输出结构化的执行报告。
|