kenaz 0.3.18 → 0.3.20
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/core/.claude/commands/agent-worker.md +1 -1
- package/core/.claude/commands/architect.md +1 -2
- package/core/.claude/commands/spec.md +1 -1
- package/core/.claude/commands//347/224/242/345/223/201.md +1 -1
- package/core/.claude/hooks/__tests__/task-1977-dedupe-guard.test.js +8 -8
- package/core/.claude/skills/architect_agent/SKILL.md +11 -92
- package/core/.claude/skills/assessment_agent/SKILL.md +0 -1
- package/core/.claude/skills/backend_engineer/SKILL.md +3 -6
- package/core/.claude/skills/code_reviewer/SKILL.md +1 -1
- package/core/.claude/skills/code_reviewer/patterns.yaml +1 -1
- package/core/.claude/skills/designer/SKILL.md +3 -6
- package/core/.claude/skills/dev_agent/SKILL.md +30 -491
- package/core/.claude/skills/developer/SKILL.md +3 -6
- package/core/.claude/skills/feature_agent/SKILL.md +3 -17
- package/core/.claude/skills/product_manager/SKILL.md +29 -1064
- package/core/.claude/skills/qa_engineer/SKILL.md +12 -17
- package/core/.claude/skills/spec_optimizer/SKILL.md +25 -275
- package/core/.claude/skills/sre_agent/SKILL.md +3 -6
- package/core/.collaboration/README.md +2 -3
- package/core/.collaboration/core/task-api.js +5 -138
- package/core/.collaboration/docs/CLI.md +0 -2
- package/core/.failure/INDEX.yaml +6 -40
- package/core/.failure/agent-execution/FAIL-013-search-cwd-drift-and-case-mismatch.yaml +1 -1
- package/core/.failure/tools/README.md +9 -227
- package/core/.formation/bifrost/launch.js +1 -6
- package/core/.formation/bifrost/launch.test.js +1 -1
- package/core/.formation/bifrost/shared/ansuz-boot-policy.js +3 -3
- package/core/.formation/bifrost/shared/ansuz-boot-policy.test.js +1 -2
- package/core/.formation/tools/__tests__/arms.test.js +41 -0
- package/core/.formation/tools/__tests__/diagnose-bug.test.js +10 -0
- package/core/.formation/tools/__tests__/m1-hmap-convid.test.js +1 -124
- package/core/.formation/tools/arms.js +48 -0
- package/core/.formation/tools/dispatch.js +24 -15
- package/core/.formation/tools/kenaz-stats.js +32 -8
- package/core/.formation/tools/kenaz-stats.test.js +15 -2
- package/core/.formation/tools/loader.js +17 -140
- package/core/.formation/tools/post-complete.js +0 -31
- package/core/.formation/tools/prompt.js +16 -1
- package/core/.formation/tools/prompt.test.js +20 -0
- package/core/.rule/INDEX.yaml +0 -18
- package/core/.rule/general/agent-workflow.yaml +14 -164
- package/core/.rule/general/project-self-containment.yaml +8 -19
- package/core/.rule/general/rust-verify-target.yaml +6 -5
- package/core/.rule/general/synapse-code-intelligence.yaml +3 -3
- package/core/.specialist/Amelia/capability.yaml +12 -12
- package/core/.specialist/Amelia/workflow.yaml +2 -2
- package/core/.specialist/Ansuz/SYSTEM_DOC.md +20 -578
- package/core/.specialist/Ansuz/cognitive_principles.yaml +2 -3
- package/core/.specialist/Ansuz/concepts/boot_rules_summary.yaml +0 -1
- package/core/.specialist/Ansuz/concepts/deep_knowledge_pointers.yaml +1 -2
- package/core/.specialist/Ansuz/core.yaml +6 -108
- package/core/.specialist/Ansuz/guards/lesson_guards.yaml +0 -3
- package/core/.specialist/Ansuz/identity_contract.yaml +0 -1
- package/core/.specialist/Ansuz/knowledge.yaml +0 -4
- package/core/.specialist/Ansuz/rule.yaml +0 -1
- package/core/.specialist/Ansuz/tools/handoff-session-identity.test.js +6 -150
- package/core/.specialist/tests/runtime-discovery/README.md +1 -1
- package/core/.specialist/tools/__tests__/task-2374-usage-counter.test.js +1 -12
- package/core/.specialist/tools/ansuz-boot-fast.js +7 -4
- package/core/.specialist/tools/ansuz-boot-fast.test.js +10 -3
- package/core/.specialist/tools/prompt-files.test.js +1 -0
- package/core/.specialist/tools/task-bridge.js +1 -66
- package/core/.system/README.md +11 -552
- package/core/.system/collaboration/README.md +10 -174
- package/core/CLAUDE.md +1 -6
- package/core/KENAZ_CORE_VERSION +1 -1
- package/core/dev/scripts/js-yaml-resolution.test.js +1 -1
- package/core/dev/scripts/peer-identity-e2e.js +402 -0
- package/core/dev/scripts/peer-identity-e2e.md +47 -0
- package/core/dev/scripts/relay-admin.js +94 -0
- package/core/dev/scripts/relay-admin.test.js +131 -0
- package/core/dev/scripts/run-rust-tests.js +9 -45
- package/core/dev/scripts/rust-verify-worktree.js +4 -4
- package/core/dev/scripts/verify-target-dir.js +6 -6
- package/core/plugins/kenaz/INVENTORY.md +8 -8
- package/core/plugins/kenaz/README.md +10 -0
- package/core/plugins/kenaz/commands/architect.md +1 -2
- package/core/plugins/kenaz/commands/spec.md +1 -1
- package/core/plugins/kenaz/commands//347/224/242/345/223/201.md +1 -1
- package/core/plugins/kenaz/guidance.md +1 -1
- package/core/plugins/kenaz/hooks/kenaz-hook.js +2 -1
- package/core/plugins/kenaz/hooks/sdk-gate.js +9 -0
- package/core/plugins/kenaz/scripts/kenaz.test.js +15 -3
- package/core/plugins/kenaz/scripts/sync.js +1 -1
- package/core/plugins/kenaz/scripts/ygg.js +8 -0
- package/core/plugins/kenaz/scripts/ygg.test.js +72 -0
- package/core/plugins/kenaz/skills/architect_agent/SKILL.md +11 -92
- package/core/plugins/kenaz/skills/assessment_agent/SKILL.md +0 -1
- package/core/plugins/kenaz/skills/backend_engineer/SKILL.md +3 -6
- package/core/plugins/kenaz/skills/code_reviewer/SKILL.md +1 -1
- package/core/plugins/kenaz/skills/code_reviewer/patterns.yaml +1 -1
- package/core/plugins/kenaz/skills/designer/SKILL.md +3 -6
- package/core/plugins/kenaz/skills/dev_agent/SKILL.md +30 -491
- package/core/plugins/kenaz/skills/developer/SKILL.md +3 -6
- package/core/plugins/kenaz/skills/feature_agent/SKILL.md +3 -17
- package/core/plugins/kenaz/skills/product_manager/SKILL.md +29 -1064
- package/core/plugins/kenaz/skills/qa_engineer/SKILL.md +12 -17
- package/core/plugins/kenaz/skills/spec_optimizer/SKILL.md +25 -275
- package/core/plugins/kenaz/skills/sre_agent/SKILL.md +3 -6
- package/core/plugins/kenaz-peer/hooks/register.test.ts +32 -0
- package/core/plugins/kenaz-peer/hooks/register.ts +9 -0
- package/package.json +6 -6
- package/core/.claude/commands/archive.md +0 -24
- package/core/.claude/commands/init.md +0 -112
- package/core/.claude/commands/legacy_dev.md +0 -18
- package/core/.claude/commands/product-review.md +0 -131
- package/core/.claude/commands/strategy.md +0 -141
- package/core/.claude/commands/sunny.md +0 -1
- package/core/.claude/commands//347/224/242/345/223/201/346/252/242/350/246/226.md +0 -129
- package/core/.claude/commands//351/200/262/345/272/246.md +0 -15
- package/core/.claude/hooks/__tests__/substrate.test.js +0 -122
- package/core/.claude/hooks/_substrate-paths.js +0 -95
- package/core/.claude/hooks/context-check.js +0 -51
- package/core/.claude/hooks/fatigue-check.js +0 -52
- package/core/.claude/hooks/handoff-snapshot-on-commit.js +0 -154
- package/core/.claude/hooks/handoff-snapshot-on-question.js +0 -158
- package/core/.claude/hooks/handoff-staleness.js +0 -197
- package/core/.claude/hooks/jev-thalamus-context.js +0 -17
- package/core/.claude/hooks/jev-thalamus-context.test.js +0 -41
- package/core/.claude/hooks/lease-release.js +0 -119
- package/core/.claude/hooks/lease-touch.js +0 -96
- package/core/.claude/hooks/reflex-feedback.js +0 -5
- package/core/.claude/hooks/session-init.ps1 +0 -49
- package/core/.claude/hooks/sound-event.js +0 -70
- package/core/.claude/hooks/sound-event.sh +0 -37
- package/core/.claude/hooks/stream-delta.js +0 -169
- package/core/.claude/no-hooks.settings.json +0 -3
- package/core/.claude/skills/legacy_dev/SKILL.md +0 -202
- package/core/.claude/skills/sunny/SKILL.md +0 -74
- package/core/.collaboration/cli/commands/assign.js +0 -39
- package/core/.collaboration/cli/commands/claim.js +0 -33
- package/core/.collaboration/cli/commands/complete.js +0 -44
- package/core/.collaboration/cli/commands/create.js +0 -110
- package/core/.collaboration/cli/commands/get.js +0 -83
- package/core/.collaboration/cli/commands/index.js +0 -52
- package/core/.collaboration/cli/commands/list.js +0 -51
- package/core/.collaboration/cli/commands/lock.js +0 -45
- package/core/.collaboration/cli/commands/rebuild.js +0 -39
- package/core/.collaboration/cli/commands/search.js +0 -61
- package/core/.collaboration/cli/commands/stats.js +0 -61
- package/core/.collaboration/cli/commands/transfer.js +0 -41
- package/core/.collaboration/cli/commands/unlock.js +0 -48
- package/core/.collaboration/cli/formatters/help-formatter.js +0 -70
- package/core/.collaboration/cli/formatters/index.js +0 -7
- package/core/.collaboration/cli/task-cli.js +0 -46
- package/core/.collaboration/cli/utils/arg-parser.js +0 -74
- package/core/.collaboration/cli/utils/git-user.js +0 -25
- package/core/.collaboration/cli/utils/index.js +0 -9
- package/core/.collaboration/cli/utils/output.js +0 -10
- package/core/.collaboration/config/default.yaml +0 -189
- package/core/.collaboration/core/conflict-resolver.js +0 -461
- package/core/.collaboration/core/conflict-resolver.test.js +0 -389
- package/core/.collaboration/core/migrate-legacy.js +0 -260
- package/core/.collaboration/docs/API.md +0 -787
- package/core/.collaboration/docs/ARCHITECTURE.md +0 -596
- package/core/.collaboration/docs/FAQ.md +0 -695
- package/core/.collaboration/docs/MIGRATION.md +0 -804
- package/core/.collaboration/docs/examples/README.md +0 -320
- package/core/.collaboration/docs/examples/advanced-queries.js +0 -261
- package/core/.collaboration/docs/examples/basic-usage.js +0 -184
- package/core/.collaboration/docs/examples/team-workflow.js +0 -352
- package/core/.failure/agent-execution/FAIL-001-agent-no-output.yaml +0 -391
- package/core/.failure/agent-execution/FAIL-007-pm-lead-wrong-team-invocation.yaml +0 -0
- package/core/.failure/agent-execution/FAIL-010-phase0-poem-format-skipped.yaml +0 -28
- package/core/.failure/agent-execution/FAIL-010-skipping-cognitive-checkpoint-after-verification.yaml +0 -59
- package/core/.failure/agent-execution/FAIL-012-grep-shortcut-during-investigation.yaml +0 -85
- package/core/.failure/architecture/FAIL-006-python-version-compatibility.yaml +0 -445
- package/core/.failure/pipeline/FAIL-003-queue-pollution.yaml +0 -335
- package/core/.failure/pipeline/README.md +0 -95
- package/core/.failure/retired/FAIL-009-skipping-synapse-pulse-before-code-change.yaml +0 -49
- package/core/.failure/tools/USAGE_GUIDE.md +0 -323
- package/core/.failure/tools/check_failures.ps1 +0 -387
- package/core/.failure/tools/log_failure.ps1 +0 -474
- package/core/.formation/.episode-input.json +0 -10
- package/core/.formation/.merge-lock +0 -1
- package/core/.formation/lead.yaml +0 -118
- package/core/.formation/legacy.bak/designer.yaml +0 -57
- package/core/.formation/legacy.bak/pm.yaml +0 -57
- package/core/.formation/legacy.bak/qa.yaml +0 -57
- package/core/.formation/legacy.bak/review.yaml +0 -62
- package/core/.formation/legacy.bak/scheduler.yaml +0 -129
- package/core/.formation/legacy.bak/sre.yaml +0 -57
- package/core/.formation/role-map.yaml +0 -274
- package/core/.formation/roles/_shared/modules/code_review.yaml +0 -98
- package/core/.formation/roles/_shared/modules/security.yaml +0 -103
- package/core/.formation/roles/_shared/modules/testing.yaml +0 -14
- package/core/.formation/roles/backend/role.yaml +0 -93
- package/core/.formation/roles/code_reviewer/role.yaml +0 -102
- package/core/.formation/roles/database_optimizer/role.yaml +0 -107
- package/core/.formation/roles/designer/role.yaml +0 -66
- package/core/.formation/roles/developer/role.yaml +0 -75
- package/core/.formation/roles/frontend/role.yaml +0 -134
- package/core/.formation/roles/incident_response/role.yaml +0 -89
- package/core/.formation/roles/qa/role.yaml +0 -89
- package/core/.formation/roles/security/role.yaml +0 -87
- package/core/.formation/roles/sre/role.yaml +0 -66
- package/core/.formation/skills/coordinator.yaml +0 -52
- package/core/.formation/solo/diagnosis.yaml +0 -78
- package/core/.formation/solo/strategy.yaml +0 -121
- package/core/.formation/tests/hello.txt +0 -2
- package/core/.formation/tools/coordinator.js +0 -350
- package/core/.formation/tools/jev-correction.js +0 -214
- package/core/.formation/tools/jev-correction.test.js +0 -178
- package/core/.formation/tools/log-reader.js +0 -232
- package/core/.formation/tools/revert-daemon-state.js +0 -162
- package/core/.formation/tools/test-drift.js +0 -148
- package/core/.formation/unit/heimdall.yaml +0 -96
- package/core/.formation/unit/plan.yaml +0 -67
- package/core/.formation/unit/think.yaml +0 -58
- package/core/.kenaz/MUNINN_SNAPSHOT9_EPISODE.json +0 -32
- package/core/.kenaz/MUNINN_SNAPSHOT9_RUNE.json +0 -23
- package/core/.kenaz/MUNINN_SNAPSHOT9_SUMMARY.md +0 -89
- package/core/.kenaz/ash_TASK_1428-20260507.json +0 -14
- package/core/.kenaz/muninn_episode_write.ps1 +0 -17
- package/core/.kenaz/muninn_snapshot11_rune_candidates.md +0 -63
- package/core/.kenaz/muninn_snapshot1_rune_candidates.md +0 -49
- package/core/.kenaz/runes_TASK_1428.json +0 -57
- package/core/.kenaz/tmp_heimdall_proposal_8d3e392.json +0 -13
- package/core/.kenaz/tmp_props.json +0 -1
- package/core/.kenaz/tmp_sounddrop_t1_prompt.txt +0 -371
- package/core/.rule/MECHANIZED.md +0 -61
- package/core/.rule/general/cortex-memory-recall.yaml +0 -446
- package/core/.rule/general/pipeline.yaml +0 -246
- package/core/.rule/general/sunny-access-control.yaml +0 -60
- package/core/.rule/general/system-invariants.yaml +0 -231
- package/core/.rule/pipeline/PPL-002-completed-task-archival.yaml +0 -528
- package/core/.rule/pipeline/auto-update.yaml +0 -282
- package/core/.rule/pipeline/task-execution.yaml +0 -365
- package/core/.specialist/Ansuz/concepts/phase_protocol.yaml +0 -65
- package/core/.specialist/Ansuz/experiments/boot_ablation_replay.js +0 -197
- package/core/.specialist/Ansuz/tools/bootstrap-anchors.js +0 -289
- package/core/.specialist/Ansuz/workflow.yaml +0 -1225
- package/core/.specialist/experiments/rg_benchmark.js +0 -523
- package/core/.specialist/experiments/rg_benchmark_results.json +0 -27
- package/core/.specialist/tools/jev-optional-context.js +0 -107
- package/core/.specialist/tools/jev-optional-context.test.js +0 -152
- package/core/.specialist/tools/memory-action-log.js +0 -839
- package/core/.specialist/tools/phase-gate.js +0 -3534
- package/core/.specialist/tools/phase-gate.test.js +0 -85
- package/core/.specialist/tools/precompute-runner.js +0 -444
- package/core/.specialist/tools/rule-engine.js +0 -621
- package/core/.specialist/tools/task-bridge-jev.test.js +0 -170
- package/core/.synapse/memory-shared.json.sync +0 -1
- package/core/.system/agent-skills/README.md +0 -724
- package/core/.system/cli-tools/README.md +0 -724
- package/core/.system/cortex/MODULES.md +0 -1046
- package/core/.system/dashboard/FRONTEND.md +0 -812
- package/core/.system/dashboard/README.md +0 -737
- package/core/.system/failure/README.md +0 -723
- package/core/.system/formation/LEGACY_SKILLS.md +0 -974
- package/core/.system/formation/POST_COMPLETE.md +0 -602
- package/core/.system/formation/README.md +0 -1094
- package/core/.system/formation/TOOLS_REFERENCE.md +0 -1145
- package/core/.system/kenaz/README.md +0 -787
- package/core/.system/memory/README.md +0 -719
- package/core/.system/pipeline/README.md +0 -712
- package/core/.system/rule/README.md +0 -794
- package/core/.system/sunny/README.md +0 -476
- package/core/.system/sunny/RULES.json +0 -89
- package/core/.system/sunny/knowledge/INDEX.md +0 -37
- package/core/.system/sunny/knowledge/agent-teams-api.md +0 -0
- package/core/.system/sunny/knowledge/ansuz-specialist.md +0 -500
- package/core/.system/sunny/knowledge/claude-cli-spawn.md +0 -177
- package/core/.system/sunny/knowledge/collaboration-api.md +0 -925
- package/core/.system/sunny/teammates/README.md +0 -107
- package/core/.system/sunny/teammates/how_to_use.yaml +0 -101
- package/core/.system/sunny/teammates/tools/headless/launcher.js +0 -318
- package/core/.system/sunny/teammates/tools/powershell/launcher.js +0 -241
- package/core/.system/sunny/teammates/tools/powershell/start.bat +0 -50
- package/core/.system/sunny/teammates/tools/utils/env.js +0 -96
- package/core/.system/sunny/teammates/tools/utils/format-output.js +0 -329
- package/core/.system/sunny/tools.json +0 -101
- package/core/dev/scripts/cleanup-queue.js +0 -184
- package/core/dev/scripts/cleanup_queue.js +0 -86
- package/core/dev/scripts/legacy/README.md +0 -39
- package/core/dev/scripts/legacy/dev_agent_scheduler.ps1.bak +0 -536
- package/core/dev/scripts/legacy/multi_agent_scheduler.ps1.bak +0 -1978
- package/core/dev/scripts/matrix/CLI_README.md +0 -214
- package/core/dev/scripts/matrix/README.md +0 -310
- package/core/dev/scripts/matrix/package-lock.json +0 -4266
- package/core/dev/scripts/matrix/package.json +0 -55
- package/core/dev/scripts/matrix/src/abbreviations.ts +0 -295
- package/core/dev/scripts/matrix/src/cli/commands/convert.ts +0 -211
- package/core/dev/scripts/matrix/src/cli/commands/create.ts +0 -95
- package/core/dev/scripts/matrix/src/cli/commands/delete.ts +0 -102
- package/core/dev/scripts/matrix/src/cli/commands/list-tags.ts.wip +0 -140
- package/core/dev/scripts/matrix/src/cli/commands/manage-tags.ts.wip +0 -173
- package/core/dev/scripts/matrix/src/cli/commands/query.ts +0 -261
- package/core/dev/scripts/matrix/src/cli/commands/read.ts +0 -77
- package/core/dev/scripts/matrix/src/cli/commands/stats.ts.wip +0 -168
- package/core/dev/scripts/matrix/src/cli/commands/tokens.ts.wip +0 -126
- package/core/dev/scripts/matrix/src/cli/commands/update.ts +0 -147
- package/core/dev/scripts/matrix/src/cli/commands/validate.ts +0 -275
- package/core/dev/scripts/matrix/src/cli/index.ts +0 -350
- package/core/dev/scripts/matrix/src/cli/utils/file-handler.ts +0 -72
- package/core/dev/scripts/matrix/src/cli/utils/logger.ts +0 -65
- package/core/dev/scripts/matrix/src/index.ts +0 -62
- package/core/dev/scripts/matrix/src/indexer/tag-indexer.ts +0 -165
- package/core/dev/scripts/matrix/src/parser.ts +0 -281
- package/core/dev/scripts/matrix/src/serializer.ts +0 -151
- package/core/dev/scripts/matrix/src/validator.ts +0 -301
- package/core/dev/scripts/matrix/tests/abbreviations.test.ts +0 -122
- package/core/dev/scripts/matrix/tests/cli.test.ts +0 -177
- package/core/dev/scripts/matrix/tests/convert.test.ts +0 -143
- package/core/dev/scripts/matrix/tests/parser.test.ts +0 -203
- package/core/dev/scripts/matrix/tests/query.test.ts +0 -85
- package/core/dev/scripts/matrix/tests/serializer.test.ts +0 -197
- package/core/dev/scripts/matrix/tests/validate.test.ts +0 -141
- package/core/dev/scripts/matrix/tests/validator.test.ts +0 -167
- package/core/dev/scripts/matrix/tsconfig.json +0 -20
- package/core/dev/scripts/matrix/types/index.d.ts +0 -111
- package/core/dev/scripts/matrix/types/index.d.ts.map +0 -1
- package/core/dev/scripts/matrix/types/index.js +0 -8
- package/core/dev/scripts/matrix/types/index.js.map +0 -1
- package/core/dev/scripts/matrix/types/index.ts +0 -124
- package/core/dev/scripts/memory-usage-report.js +0 -152
- package/core/dev/scripts/probe/ansuz-scaffold-ablation.js +0 -579
- package/core/dev/scripts/probe/ansuz-scaffold-ablation.test.js +0 -244
- package/core/dev/scripts/probe/hook-latency-probe.js +0 -315
- package/core/dev/scripts/probe/hook-latency-probe.test.js +0 -105
- package/core/dev/scripts/probe/prediction-signal-auc.js +0 -483
- package/core/dev/scripts/probe/prediction-signal-auc.test.js +0 -200
- package/core/dev/scripts/test-pty-ws-tunnel.js +0 -229
- package/core/dev/scripts/validate_pipeline.js +0 -197
- package/core/dev/spikes/task2145-evidence-20261004/backend-log-excerpt.txt +0 -56
- package/core/dev/spikes/task2145-evidence-20261004/graph.shadow +0 -0
- package/core/dev/spikes/task2145-evidence-20261004/graph.wal +0 -0
- package/core/dev/spikes/task2145-evidence-20261004/graph_corrupt_suspect.marker +0 -1
- package/core/plugins/kenaz/commands/strategy.md +0 -141
|
@@ -1,1145 +0,0 @@
|
|
|
1
|
-
# Formation 工具鏈完整參考
|
|
2
|
-
|
|
3
|
-
**版本**: v2.0
|
|
4
|
-
**最後更新**: 2026-02-20
|
|
5
|
-
|
|
6
|
-
本文檔詳細說明 `.formation/tools/` 下所有模組的函數簽名、參數、呼叫關係與設計意圖。
|
|
7
|
-
|
|
8
|
-
---
|
|
9
|
-
|
|
10
|
-
## 目錄
|
|
11
|
-
|
|
12
|
-
1. [系統架構總覽](#系統架構總覽)
|
|
13
|
-
2. [headless.js — Dispatch 入口](#headlessjs--dispatch-入口)
|
|
14
|
-
3. [prompt.js — Prompt 組裝 + Principles 注入](#promptjs--prompt-組裝--principles-注入)
|
|
15
|
-
4. [runner.js — Subagent 執行](#runnerjs--subagent-執行)
|
|
16
|
-
5. [logger.js — Log 管理](#loggerjs--log-管理)
|
|
17
|
-
6. [utils.js — 工具函數](#utilsjs--工具函數)
|
|
18
|
-
7. [loader.js — 任務載入三層 Fallback](#loaderjs--任務載入三層-fallback)
|
|
19
|
-
8. [呼叫關係圖](#呼叫關係圖)
|
|
20
|
-
9. [關鍵流程範例](#關鍵流程範例)
|
|
21
|
-
|
|
22
|
-
---
|
|
23
|
-
|
|
24
|
-
## 系統架構總覽
|
|
25
|
-
|
|
26
|
-
Formation 工具鏈採用**分層架構**,各模組職責清晰:
|
|
27
|
-
|
|
28
|
-
```
|
|
29
|
-
┌──────────────────────────────────────────────────────────┐
|
|
30
|
-
│ L5: headless.js — 陣型編排層(5 種陣型的執行邏輯) │
|
|
31
|
-
│ launch() → launchUnit/Solo/Squad/Legion/Legacy │
|
|
32
|
-
└────────────────────┬─────────────────────────────────────┘
|
|
33
|
-
↓
|
|
34
|
-
┌──────────────────────────────────────────────────────────┐
|
|
35
|
-
│ L4: runner.js — 進程啟動層(統一的 claude 進程管理) │
|
|
36
|
-
│ runSingle / runHeadless / runLegionLead / runParallel │
|
|
37
|
-
└────────────────────┬─────────────────────────────────────┘
|
|
38
|
-
↓
|
|
39
|
-
┌──────────────────────────────────────────────────────────┐
|
|
40
|
-
│ L3: prompt.js — Prompt 組裝層(針對不同陣型組裝 prompt) │
|
|
41
|
-
│ buildPrompt → Unit/Solo/Squad/Legion/Legacy builders │
|
|
42
|
-
└────────────────────┬─────────────────────────────────────┘
|
|
43
|
-
↓
|
|
44
|
-
┌──────────────────────────────────────────────────────────┐
|
|
45
|
-
│ L2: loader.js — 資料載入層(skill YAML + 任務三層查詢) │
|
|
46
|
-
│ loadSkill / loadTask │
|
|
47
|
-
└────────────────────┬─────────────────────────────────────┘
|
|
48
|
-
↓
|
|
49
|
-
┌──────────────────────────────────────────────────────────┐
|
|
50
|
-
│ L1: logger.js + utils.js — 基礎設施層 │
|
|
51
|
-
│ createLogWriter / formatEntry / generateSessionId │
|
|
52
|
-
└──────────────────────────────────────────────────────────┘
|
|
53
|
-
```
|
|
54
|
-
|
|
55
|
-
**設計原則**:
|
|
56
|
-
- **單一職責**:每個模組只負責一件事(編排 / 進程 / prompt / 載入 / 日誌)
|
|
57
|
-
- **依賴單向**:L5 依賴 L4,L4 依賴 L3,依此類推,無循環依賴
|
|
58
|
-
- **可測試性**:每層可獨立測試,dry-run 可在 prompt 層停下
|
|
59
|
-
|
|
60
|
-
---
|
|
61
|
-
|
|
62
|
-
## headless.js — Dispatch 入口
|
|
63
|
-
|
|
64
|
-
**職責**:根據 `--formation` 參數分發到 5 種陣型的執行邏輯
|
|
65
|
-
|
|
66
|
-
### 主入口
|
|
67
|
-
|
|
68
|
-
#### `launch(options)`
|
|
69
|
-
|
|
70
|
-
陣型編排的總調度器。
|
|
71
|
-
|
|
72
|
-
**參數**:
|
|
73
|
-
```js
|
|
74
|
-
{
|
|
75
|
-
formation: 'unit' | 'solo' | 'squad' | 'legion' | 'legacy',
|
|
76
|
-
skill: string, // 技能名稱(YAML 檔名,不含 .yaml)
|
|
77
|
-
task: string | null, // TASK_ID 或任務描述(null 則自動尋找)
|
|
78
|
-
dryRun: boolean, // true=只印 prompt,不啟動進程
|
|
79
|
-
mode: string | null // 分析模式(squad 用),如 'optimization', 'innovation'
|
|
80
|
-
}
|
|
81
|
-
```
|
|
82
|
-
|
|
83
|
-
**回傳**:
|
|
84
|
-
- `unit/solo`: `ChildProcess`(單一進程)
|
|
85
|
-
- `squad`: `ChildProcess[]`(並行進程陣列)
|
|
86
|
-
- `legion`: `ChildProcess`(lead 進程)
|
|
87
|
-
- `legacy`: `null`(scheduler loop 在 legacy-scheduler.js)
|
|
88
|
-
|
|
89
|
-
**流程**:
|
|
90
|
-
1. 若 `task` 為空且非 legacy → 呼叫 `findNextTask()` 自動選擇任務
|
|
91
|
-
2. 載入 skill YAML (`loadSkill`) 和任務資料 (`loadTask`)
|
|
92
|
-
3. 組裝 prompt (`buildPrompt`)
|
|
93
|
-
4. 若 `dryRun=true` → 印出 prompt,結束
|
|
94
|
-
5. 分發到對應陣型的 launcher 函數
|
|
95
|
-
|
|
96
|
-
---
|
|
97
|
-
|
|
98
|
-
### 陣型 Launchers
|
|
99
|
-
|
|
100
|
-
#### `launchUnit(opts)`
|
|
101
|
-
|
|
102
|
-
**單一 agent 直接執行**(最簡單的模式)
|
|
103
|
-
|
|
104
|
-
**參數**:
|
|
105
|
-
```js
|
|
106
|
-
{
|
|
107
|
-
rawPrompt: string, // 組裝好的 prompt
|
|
108
|
-
skill: string,
|
|
109
|
-
sessionId: string
|
|
110
|
-
}
|
|
111
|
-
```
|
|
112
|
-
|
|
113
|
-
**行為**:
|
|
114
|
-
- 呼叫 `runHeadless({ prompt: HEADLESS_PREFIX + rawPrompt, ... })`
|
|
115
|
-
- 輸出壓縮、原始 stdout 直通
|
|
116
|
-
|
|
117
|
-
---
|
|
118
|
-
|
|
119
|
-
#### `launchSolo(opts)`
|
|
120
|
-
|
|
121
|
-
**單一 agent 多視角分析**(agent 自主切換視角)
|
|
122
|
-
|
|
123
|
-
**參數** / **行為**:與 `launchUnit` 相同,差異在 prompt 結構(含 perspectives)
|
|
124
|
-
|
|
125
|
-
---
|
|
126
|
-
|
|
127
|
-
#### `launchSquad(opts)`
|
|
128
|
-
|
|
129
|
-
**多 agent 並行 + 辯論 + 整合**(複雜度最高的陣型)
|
|
130
|
-
|
|
131
|
-
**參數**:
|
|
132
|
-
```js
|
|
133
|
-
{
|
|
134
|
-
rawPrompt: Array<{ memberId, prompt, skill }>, // 成員 prompt 陣列
|
|
135
|
-
skill: string,
|
|
136
|
-
sessionId: string,
|
|
137
|
-
skillDef: object // 完整的 skill YAML(含 debate/merge 設定)
|
|
138
|
-
}
|
|
139
|
-
```
|
|
140
|
-
|
|
141
|
-
**執行流程**:
|
|
142
|
-
1. **Round 1**:並行啟動所有成員 (`runHeadless` × N),各自獨立分析
|
|
143
|
-
2. 等待所有成員完成 (`waitAll`)
|
|
144
|
-
3. 若啟用 debate → **Round 2**:每個成員讀取其他人的報告,寫反駁
|
|
145
|
-
4. **Synthesis**:整合者讀取所有報告,產出最終報告
|
|
146
|
-
|
|
147
|
-
**關鍵函數**:
|
|
148
|
-
- `waitAll(children)`: 等待所有進程完成,回傳 `Promise<{ memberId, exitCode, logPath }[]>`
|
|
149
|
-
- `printResults(label, results, total)`: 格式化輸出進程執行結果
|
|
150
|
-
- `hasSuccess(results)`: 檢查是否有至少一個成功
|
|
151
|
-
- `squadSynthesis(opts)`: 啟動整合 agent
|
|
152
|
-
|
|
153
|
-
---
|
|
154
|
-
|
|
155
|
-
#### `launchLegion(opts)`
|
|
156
|
-
|
|
157
|
-
**Agent Teams 啟動**(使用 Claude Code 官方 teammate 功能)
|
|
158
|
-
|
|
159
|
-
**參數**:
|
|
160
|
-
```js
|
|
161
|
-
{
|
|
162
|
-
rawPrompt: { // buildLegionPrompts 的輸出
|
|
163
|
-
teamName: string,
|
|
164
|
-
teamDesc: string,
|
|
165
|
-
lead: { prompt },
|
|
166
|
-
members: [{ name, agentType, prompt }]
|
|
167
|
-
},
|
|
168
|
-
skill: string,
|
|
169
|
-
sessionId: string
|
|
170
|
-
}
|
|
171
|
-
```
|
|
172
|
-
|
|
173
|
-
**行為**:
|
|
174
|
-
- 用 `buildLegionLeadPrompt(legionConfig)` 組裝 lead prompt
|
|
175
|
-
- 呼叫 `runLegionLead({ prompt, ... })` 啟動 lead agent
|
|
176
|
-
- Lead agent 用 `Task` 工具 spawn teammates(進程內並行)
|
|
177
|
-
|
|
178
|
-
---
|
|
179
|
-
|
|
180
|
-
#### `launchLegacy(opts)`
|
|
181
|
-
|
|
182
|
-
**連續排程器**(Rust SingleAgentScheduler 對等實作)
|
|
183
|
-
|
|
184
|
-
**參數**:
|
|
185
|
-
```js
|
|
186
|
-
{
|
|
187
|
-
skillDef: object // legacy skill YAML(含 config 設定)
|
|
188
|
-
}
|
|
189
|
-
```
|
|
190
|
-
|
|
191
|
-
**行為**:
|
|
192
|
-
- 從 `skillDef.config` 提取參數(initial_delay_secs, interval_minutes 等)
|
|
193
|
-
- 呼叫 `legacy-scheduler.js` 的 `start(overrides)`
|
|
194
|
-
- 回傳 `null`(scheduler loop 不是 child process)
|
|
195
|
-
|
|
196
|
-
---
|
|
197
|
-
|
|
198
|
-
### 自動任務選擇
|
|
199
|
-
|
|
200
|
-
#### `findNextTask()`
|
|
201
|
-
|
|
202
|
-
從 `.collaboration/tasks/backlog/` 中找出最高優先級的任務。
|
|
203
|
-
|
|
204
|
-
**回傳**:
|
|
205
|
-
```js
|
|
206
|
-
{
|
|
207
|
-
id: 'TASK_XXX',
|
|
208
|
-
title: string,
|
|
209
|
-
priority: number // 0=P0, 1=P1, 2=P2, 3=P3
|
|
210
|
-
} | null
|
|
211
|
-
```
|
|
212
|
-
|
|
213
|
-
**排序規則**:
|
|
214
|
-
1. 優先級排序(P0 > P1 > P2 > P3)
|
|
215
|
-
2. 同優先級按 ID 數字排序(TASK_150 > TASK_151)
|
|
216
|
-
3. 跳過有未完成依賴的任務(檢查 dependencies 是否都在 done/)
|
|
217
|
-
|
|
218
|
-
---
|
|
219
|
-
|
|
220
|
-
### Dry Run
|
|
221
|
-
|
|
222
|
-
#### `printDryRun(formation, rawPrompt, skillDef, skill)`
|
|
223
|
-
|
|
224
|
-
列印 prompt 但不執行,用於偵錯。
|
|
225
|
-
|
|
226
|
-
**行為**:
|
|
227
|
-
- `legion`: 印 lead prompt
|
|
228
|
-
- `squad`: 印 R1 所有成員 prompt + R2 debate prompts + synthesis prompt
|
|
229
|
-
- 其他: 直接印 `HEADLESS_PREFIX + rawPrompt`
|
|
230
|
-
|
|
231
|
-
---
|
|
232
|
-
|
|
233
|
-
## prompt.js — Prompt 組裝 + Principles 注入
|
|
234
|
-
|
|
235
|
-
**職責**:根據 skill YAML 和陣型,組裝出符合格式的 prompt
|
|
236
|
-
|
|
237
|
-
### 主入口
|
|
238
|
-
|
|
239
|
-
#### `buildPrompt(skillDef, taskInput, taskData, options)`
|
|
240
|
-
|
|
241
|
-
根據陣型分發到對應的 prompt builder。
|
|
242
|
-
|
|
243
|
-
**參數**:
|
|
244
|
-
```js
|
|
245
|
-
skillDef: object, // loadSkill 回傳的 YAML 解析結果
|
|
246
|
-
taskInput: string, // TASK_ID 或任務描述
|
|
247
|
-
taskData: string | null, // loadTask 回傳的 YAML 文本(或 null)
|
|
248
|
-
options: {
|
|
249
|
-
analysisMode?: string // 'optimization' | 'innovation'(squad 用)
|
|
250
|
-
}
|
|
251
|
-
```
|
|
252
|
-
|
|
253
|
-
**回傳**:
|
|
254
|
-
- `unit/solo/legacy`: `string`(單一 prompt)
|
|
255
|
-
- `squad`: `Array<{ memberId, prompt, skill }>`
|
|
256
|
-
- `legion`: `{ teamName, teamDesc, lead, members }`
|
|
257
|
-
|
|
258
|
-
---
|
|
259
|
-
|
|
260
|
-
### 陣型 Builders
|
|
261
|
-
|
|
262
|
-
#### `buildUnitPrompt(skillDef, taskInput, taskData)`
|
|
263
|
-
|
|
264
|
-
組裝單一 agent 的 prompt(最簡單結構)
|
|
265
|
-
|
|
266
|
-
**Prompt 結構**:
|
|
267
|
-
```
|
|
268
|
-
## Role
|
|
269
|
-
{role.identity}
|
|
270
|
-
Priority: {role.priority}
|
|
271
|
-
|
|
272
|
-
## Behavior
|
|
273
|
-
- {behavior[0]}
|
|
274
|
-
- {behavior[1]}
|
|
275
|
-
...
|
|
276
|
-
|
|
277
|
-
## Task
|
|
278
|
-
{taskInput 或 taskData}
|
|
279
|
-
|
|
280
|
-
## Workflow
|
|
281
|
-
### {workflow[0].step}
|
|
282
|
-
...
|
|
283
|
-
|
|
284
|
-
## Expected Output
|
|
285
|
-
Primary: {output.primary}
|
|
286
|
-
Secondary: {output.secondary}
|
|
287
|
-
```
|
|
288
|
-
|
|
289
|
-
---
|
|
290
|
-
|
|
291
|
-
#### `buildSoloPrompt(skillDef, taskInput, taskData)`
|
|
292
|
-
|
|
293
|
-
在 unit 基礎上加入**可用視角 (perspectives)** 和**分析原則 (analysis_principles)**
|
|
294
|
-
|
|
295
|
-
**額外區塊**:
|
|
296
|
-
```
|
|
297
|
-
## Analysis Principles
|
|
298
|
-
### {principle.name}
|
|
299
|
-
{principle.description}
|
|
300
|
-
|
|
301
|
-
## Available Perspectives
|
|
302
|
-
### {perspective.name}
|
|
303
|
-
- 關注:{perspective.lens}
|
|
304
|
-
- 何時切換:{perspective.trigger}
|
|
305
|
-
```
|
|
306
|
-
|
|
307
|
-
---
|
|
308
|
-
|
|
309
|
-
#### `buildSquadPrompts(skillDef, taskInput, taskData, options)`
|
|
310
|
-
|
|
311
|
-
為每個成員分別組裝 prompt(**最複雜的 builder**)
|
|
312
|
-
|
|
313
|
-
**成員 Prompt 結構**:
|
|
314
|
-
```
|
|
315
|
-
## Role
|
|
316
|
-
{member.role}
|
|
317
|
-
|
|
318
|
-
## Analysis Mode: {analysisMode}
|
|
319
|
-
{modeConfig.description}
|
|
320
|
-
**你在此模式下的立場調整**:
|
|
321
|
-
{member.mode_behavior[analysisMode]}
|
|
322
|
-
|
|
323
|
-
## Principles (絕對遵守)
|
|
324
|
-
{skillDef.principles.focus}
|
|
325
|
-
**禁止 (違反即失敗)**:
|
|
326
|
-
- ❌ {forbidden[0]}
|
|
327
|
-
...
|
|
328
|
-
**必須遵守**:
|
|
329
|
-
- ✅ {required[0]}
|
|
330
|
-
...
|
|
331
|
-
|
|
332
|
-
## Identity
|
|
333
|
-
你是 Squad 的成員 **{member.name}** (id: {member.id})。
|
|
334
|
-
你與其他成員並行工作,各自獨立,不能互相通訊。
|
|
335
|
-
完成你負責的部分後回報結果,Lead 會負責整合。
|
|
336
|
-
|
|
337
|
-
## Scope (你只能碰這些檔案)
|
|
338
|
-
Include:
|
|
339
|
-
- {scope.include[0]}
|
|
340
|
-
- ...
|
|
341
|
-
Exclude:
|
|
342
|
-
- {scope.exclude[0]}
|
|
343
|
-
- ...
|
|
344
|
-
|
|
345
|
-
## Shared Context (所有成員共享的約定)
|
|
346
|
-
{skillDef.shared_context.description}
|
|
347
|
-
### {key}
|
|
348
|
-
{value}
|
|
349
|
-
|
|
350
|
-
## Behavior
|
|
351
|
-
- {skillDef.behavior[0]}
|
|
352
|
-
- {member.behavior[0]}
|
|
353
|
-
...
|
|
354
|
-
|
|
355
|
-
## Task
|
|
356
|
-
{taskInput 或 taskData}
|
|
357
|
-
|
|
358
|
-
## Workflow
|
|
359
|
-
{member.workflow 或 skillDef.collaboration.workflow}
|
|
360
|
-
|
|
361
|
-
## Expected Output
|
|
362
|
-
{member.output 或 skillDef.output}
|
|
363
|
-
```
|
|
364
|
-
|
|
365
|
-
**關鍵函數**:
|
|
366
|
-
- `buildSharedContextBlock(skillDef)`: 組裝 shared_context 區塊(成員共用的約定)
|
|
367
|
-
|
|
368
|
-
---
|
|
369
|
-
|
|
370
|
-
#### `buildLegionPrompts(skillDef, taskInput, taskData)`
|
|
371
|
-
|
|
372
|
-
組裝 team lead 和每個成員的 prompt。
|
|
373
|
-
|
|
374
|
-
**回傳結構**:
|
|
375
|
-
```js
|
|
376
|
-
{
|
|
377
|
-
teamName: string, // 團隊名稱(自動轉 kebab-case)
|
|
378
|
-
teamDesc: string, // 團隊描述
|
|
379
|
-
lead: {
|
|
380
|
-
prompt: string // Lead agent 的 prompt
|
|
381
|
-
},
|
|
382
|
-
members: [
|
|
383
|
-
{
|
|
384
|
-
name: string, // 成員名稱
|
|
385
|
-
agentType: string, // 'general-purpose' 等
|
|
386
|
-
prompt: string // 成員的 prompt
|
|
387
|
-
}
|
|
388
|
-
]
|
|
389
|
-
}
|
|
390
|
-
```
|
|
391
|
-
|
|
392
|
-
**Lead Prompt 結構**:
|
|
393
|
-
```
|
|
394
|
-
## Role
|
|
395
|
-
你是 {teamName} 的 Team Lead。
|
|
396
|
-
{role.identity}
|
|
397
|
-
|
|
398
|
-
## Team Members
|
|
399
|
-
- **{member.name}**: {member.role}
|
|
400
|
-
|
|
401
|
-
## Communication Rules
|
|
402
|
-
### Principles
|
|
403
|
-
- {comm.principles[0]}
|
|
404
|
-
...
|
|
405
|
-
### Patterns
|
|
406
|
-
- **{pattern.name}**: {pattern.who} — {pattern.content}
|
|
407
|
-
...
|
|
408
|
-
### Broadcast Policy
|
|
409
|
-
{comm.broadcast_policy}
|
|
410
|
-
|
|
411
|
-
## Task
|
|
412
|
-
{taskInput}
|
|
413
|
-
|
|
414
|
-
## Lifecycle
|
|
415
|
-
### {phase}
|
|
416
|
-
{description}
|
|
417
|
-
Lead actions:
|
|
418
|
-
- {lead_actions[0]}
|
|
419
|
-
Exit criteria:
|
|
420
|
-
- {exit_criteria[0]}
|
|
421
|
-
|
|
422
|
-
## Expected Output
|
|
423
|
-
...
|
|
424
|
-
```
|
|
425
|
-
|
|
426
|
-
**Member Prompt**:
|
|
427
|
-
- 優先使用 `skillDef.member_prompts[member.id]`(如 forge 的 designer/implementer)
|
|
428
|
-
- 否則自動生成(Role + Responsibilities + Skills + Scope + Team Context)
|
|
429
|
-
|
|
430
|
-
---
|
|
431
|
-
|
|
432
|
-
#### `buildLegacyPrompt(skillDef)`
|
|
433
|
-
|
|
434
|
-
回傳 scheduler 配置摘要(供 dry-run 顯示)
|
|
435
|
-
|
|
436
|
-
---
|
|
437
|
-
|
|
438
|
-
### Squad 專用:Synthesis 與 Debate
|
|
439
|
-
|
|
440
|
-
#### `buildSquadSynthesisPrompt(skillDef, reportDir)`
|
|
441
|
-
|
|
442
|
-
組裝整合 agent 的 prompt,讀取所有成員報告並整合。
|
|
443
|
-
|
|
444
|
-
**Prompt 結構**:
|
|
445
|
-
```
|
|
446
|
-
## Role
|
|
447
|
-
你是 Squad Synthesis Agent(整合者)。
|
|
448
|
-
你不偏袒任何一方。
|
|
449
|
-
|
|
450
|
-
## Principles (整合時也必須遵守)
|
|
451
|
-
{skillDef.principles.focus}
|
|
452
|
-
**禁止**: {forbidden}
|
|
453
|
-
**必須遵守**: {required}
|
|
454
|
-
|
|
455
|
-
## Merge Strategy: {merge.strategy}
|
|
456
|
-
{merge.description}
|
|
457
|
-
|
|
458
|
-
## Merge Steps (按順序執行)
|
|
459
|
-
### Step: {step.step}
|
|
460
|
-
{step.action}
|
|
461
|
-
**Partial Failure Handling**: {step.on_partial_failure}
|
|
462
|
-
|
|
463
|
-
## Reports Location
|
|
464
|
-
所有成員報告位於 `.formation/reports/{reportDir}/` 目錄。
|
|
465
|
-
**執行步驟**:
|
|
466
|
-
1. 用 Glob 工具掃描 `.formation/reports/{reportDir}/*.md`
|
|
467
|
-
2. 排除 synthesis.md
|
|
468
|
-
3. 用 Read 工具逐一讀取每份報告
|
|
469
|
-
4. 按照上述 Merge Steps 逐步整合
|
|
470
|
-
|
|
471
|
-
## Squad Members(供參考)
|
|
472
|
-
- **{member.name}** ({member.id}): {roleFirstLine}
|
|
473
|
-
|
|
474
|
-
## Output
|
|
475
|
-
將整合報告寫入 `.formation/reports/{reportDir}/synthesis.md`
|
|
476
|
-
```
|
|
477
|
-
|
|
478
|
-
---
|
|
479
|
-
|
|
480
|
-
#### `buildSquadDebatePrompts(skillDef, reportDir)`
|
|
481
|
-
|
|
482
|
-
組裝 Round 2 交叉辯論的 prompts(每個成員讀其他人的報告)
|
|
483
|
-
|
|
484
|
-
**回傳**:`Array<{ memberId, prompt, skill }>`(格式與 buildSquadPrompts 相同)
|
|
485
|
-
|
|
486
|
-
**Prompt 結構**:
|
|
487
|
-
```
|
|
488
|
-
## Role
|
|
489
|
-
你是 **{member.name}**,這是你的第二輪分析(辯論回合)。
|
|
490
|
-
|
|
491
|
-
## 你的立場(簡要提醒)
|
|
492
|
-
{roleFirstLine}
|
|
493
|
-
|
|
494
|
-
## Debate Instructions
|
|
495
|
-
{member.debate_instructions}
|
|
496
|
-
|
|
497
|
-
## Debate Rules
|
|
498
|
-
- {debate.rules[0]}
|
|
499
|
-
...
|
|
500
|
-
|
|
501
|
-
## Reports to Read
|
|
502
|
-
- **{other.name}**: `.formation/reports/{reportDir}/{other.id}.md`
|
|
503
|
-
|
|
504
|
-
用 Read 工具讀取上述報告,然後寫出你的回應。
|
|
505
|
-
|
|
506
|
-
## Output
|
|
507
|
-
將反駁報告寫入 `.formation/reports/{reportDir}/{member.id}-r2.md`
|
|
508
|
-
```
|
|
509
|
-
|
|
510
|
-
---
|
|
511
|
-
|
|
512
|
-
### Legion 專用
|
|
513
|
-
|
|
514
|
-
#### `buildLegionLeadPrompt(config)`
|
|
515
|
-
|
|
516
|
-
組裝 Legion lead 的完整 headless prompt(複製 Sunny teammate 成功模式)
|
|
517
|
-
|
|
518
|
-
**結構**:
|
|
519
|
-
```
|
|
520
|
-
{LEGION_SYSTEM_PREFIX}
|
|
521
|
-
Create an agent team with {members.length} teammates:
|
|
522
|
-
1. "{name}" - {desc}
|
|
523
|
-
2. ...
|
|
524
|
-
|
|
525
|
-
Task: {taskMatch}
|
|
526
|
-
|
|
527
|
-
{LEGION_AUTO_EXECUTE}
|
|
528
|
-
```
|
|
529
|
-
|
|
530
|
-
**常數定義**:
|
|
531
|
-
- `LEGION_SYSTEM_PREFIX`: 定義 Team Lead 的角色與責任
|
|
532
|
-
- `LEGION_AUTO_EXECUTE`: 強制執行規則(立即建 teammates,進入 polling loop,等所有人完成)
|
|
533
|
-
|
|
534
|
-
---
|
|
535
|
-
|
|
536
|
-
### 共用片段
|
|
537
|
-
|
|
538
|
-
#### `appendBehavior(lines, skillDef)`
|
|
539
|
-
|
|
540
|
-
將 `skillDef.behavior` 陣列附加到 lines。
|
|
541
|
-
|
|
542
|
-
#### `appendTask(lines, taskInput, taskData)`
|
|
543
|
-
|
|
544
|
-
組裝 Task 區塊:
|
|
545
|
-
- 若有 taskData → 用 ` ``` ` 包起來顯示
|
|
546
|
-
- 否則直接顯示 taskInput
|
|
547
|
-
|
|
548
|
-
#### `appendWorkflow(lines, skillDef)`
|
|
549
|
-
|
|
550
|
-
組裝 Workflow 區塊(從 `skillDef.collaboration.workflow`)
|
|
551
|
-
|
|
552
|
-
#### `appendOutput(lines, skillDef)`
|
|
553
|
-
|
|
554
|
-
組裝 Output 區塊(`primary` + `secondary`)
|
|
555
|
-
|
|
556
|
-
---
|
|
557
|
-
|
|
558
|
-
### Headless 常數
|
|
559
|
-
|
|
560
|
-
#### `HEADLESS_PREFIX`
|
|
561
|
-
|
|
562
|
-
強制規則:
|
|
563
|
-
1. 直接執行,不要提問
|
|
564
|
-
2. 不要讀取 CLAUDE.md
|
|
565
|
-
3. 完成後輸出結構化結果
|
|
566
|
-
4. 遇到無法執行的問題,輸出錯誤描述後結束
|
|
567
|
-
5. **禁止執行任何 git 操作**(Git 由 Formation Lead 統一管理)
|
|
568
|
-
|
|
569
|
-
---
|
|
570
|
-
|
|
571
|
-
## runner.js — Subagent 執行
|
|
572
|
-
|
|
573
|
-
**職責**:統一的 `claude` 進程啟動與輸出收集
|
|
574
|
-
|
|
575
|
-
### 內部:進程管理
|
|
576
|
-
|
|
577
|
-
#### `spawnClaude(opts)`
|
|
578
|
-
|
|
579
|
-
所有 `run*` 函數的底層實作。
|
|
580
|
-
|
|
581
|
-
**參數**:
|
|
582
|
-
```js
|
|
583
|
-
{
|
|
584
|
-
prompt: string, // 完整 prompt(已包含 HEADLESS_PREFIX)
|
|
585
|
-
formation: string, // 陣型名稱(用於 log 目錄)
|
|
586
|
-
skill: string, // 技能名稱
|
|
587
|
-
sessionId: string, // session ID
|
|
588
|
-
memberId?: string, // 成員 ID(squad/legion 用)
|
|
589
|
-
silent?: boolean, // 不輸出到 console
|
|
590
|
-
outputPath?: string, // 自訂 log 路徑
|
|
591
|
-
cleanPrompt?: boolean, // true=壓縮 prompt(移除換行、多餘空格)
|
|
592
|
-
allowedTools?: string, // 允許的工具清單(逗號分隔)
|
|
593
|
-
extraArgs?: string[], // 額外的 claude CLI 參數
|
|
594
|
-
pipeRaw?: boolean, // true=原始 stdout 直通,false=格式化輸出
|
|
595
|
-
onLog?: (formatted: string) => void // 自訂 log handler
|
|
596
|
-
}
|
|
597
|
-
```
|
|
598
|
-
|
|
599
|
-
**回傳**:`ChildProcess`(附加 `_formation` 屬性)
|
|
600
|
-
|
|
601
|
-
**流程**:
|
|
602
|
-
1. 建立 log writer (`createLogWriter`)
|
|
603
|
-
2. 啟動 `claude.cmd -p - --dangerously-skip-permissions --output-format stream-json ...`
|
|
604
|
-
3. 將 prompt 透過 stdin 傳入
|
|
605
|
-
4. 呼叫 `collectOutput(child, log, opts)` 收集輸出
|
|
606
|
-
5. 附加 `_formation` 屬性到 child process
|
|
607
|
-
|
|
608
|
-
**`_formation` 屬性**:
|
|
609
|
-
```js
|
|
610
|
-
{
|
|
611
|
-
logPath: string, // log 檔案路徑
|
|
612
|
-
memberId: string, // 成員 ID
|
|
613
|
-
log: object // log writer 實例
|
|
614
|
-
}
|
|
615
|
-
```
|
|
616
|
-
|
|
617
|
-
---
|
|
618
|
-
|
|
619
|
-
#### `collectOutput(child, log, opts)`
|
|
620
|
-
|
|
621
|
-
收集 `claude` 進程的 stdout/stderr,寫入 log。
|
|
622
|
-
|
|
623
|
-
**參數**:
|
|
624
|
-
```js
|
|
625
|
-
child: ChildProcess,
|
|
626
|
-
log: LogWriter,
|
|
627
|
-
opts: {
|
|
628
|
-
silent?: boolean, // 不輸出到 console
|
|
629
|
-
memberId?: string, // 成員 ID(顯示用)
|
|
630
|
-
pipeRaw?: boolean, // true=直通,false=格式化
|
|
631
|
-
onLog?: (line) => void // 自訂 handler
|
|
632
|
-
}
|
|
633
|
-
```
|
|
634
|
-
|
|
635
|
-
**行為**:
|
|
636
|
-
1. 監聽 `stdout.data` 事件,解析 stream-json 格式
|
|
637
|
-
2. 用 `formatEntry(entry)` 格式化每條 entry
|
|
638
|
-
3. 寫入 log 檔案
|
|
639
|
-
4. 若 `!silent && !pipeRaw` → 輸出到 console
|
|
640
|
-
5. 偵測到 `type: 'result'` → emit `formation:done` 並延遲 kill(Windows fix)
|
|
641
|
-
6. 監聽 `close/exit/formation:done` → 呼叫 `log.writeFooter(code)`
|
|
642
|
-
|
|
643
|
-
**Windows 特殊處理**:
|
|
644
|
-
- `claude.cmd` 有時進程不 exit,偵測到 `result` 就 emit 完成信號並延遲 kill
|
|
645
|
-
|
|
646
|
-
---
|
|
647
|
-
|
|
648
|
-
### 公開 API
|
|
649
|
-
|
|
650
|
-
#### `runSingle(opts)`
|
|
651
|
-
|
|
652
|
-
啟動單一 claude subagent(**格式化輸出**)
|
|
653
|
-
|
|
654
|
-
**用途**:dispatch.js 用(一般模式)
|
|
655
|
-
|
|
656
|
-
---
|
|
657
|
-
|
|
658
|
-
#### `runHeadless(opts)`
|
|
659
|
-
|
|
660
|
-
無頭模式:**壓縮 prompt + 原始 stdout 直通**
|
|
661
|
-
|
|
662
|
-
**用途**:Unit / Solo / Squad 成員
|
|
663
|
-
|
|
664
|
-
---
|
|
665
|
-
|
|
666
|
-
#### `runLegionLead(opts)`
|
|
667
|
-
|
|
668
|
-
Agent Teams 模式:啟用 `--teammate-mode in-process` + `Task` 工具
|
|
669
|
-
|
|
670
|
-
**預設參數覆蓋**:
|
|
671
|
-
```js
|
|
672
|
-
{
|
|
673
|
-
cleanPrompt: true,
|
|
674
|
-
pipeRaw: true,
|
|
675
|
-
allowedTools: 'Bash,Read,Edit,Write,Glob,Grep,Task',
|
|
676
|
-
extraArgs: ['--teammate-mode', 'in-process']
|
|
677
|
-
}
|
|
678
|
-
```
|
|
679
|
-
|
|
680
|
-
---
|
|
681
|
-
|
|
682
|
-
#### `runParallel(opts)`
|
|
683
|
-
|
|
684
|
-
並行啟動多個 claude subagent(**dispatch 用**)
|
|
685
|
-
|
|
686
|
-
**參數**:
|
|
687
|
-
```js
|
|
688
|
-
{
|
|
689
|
-
members: Array<{ memberId, prompt, skill }>,
|
|
690
|
-
formation: string,
|
|
691
|
-
sessionId: string
|
|
692
|
-
}
|
|
693
|
-
```
|
|
694
|
-
|
|
695
|
-
**回傳**:`Promise<Array<{ memberId, exitCode, logPath }>>`
|
|
696
|
-
|
|
697
|
-
**行為**:
|
|
698
|
-
1. 用 `runSingle` 並行啟動所有成員
|
|
699
|
-
2. 用 `Promise.all` 等待所有進程完成
|
|
700
|
-
3. 輸出執行結果摘要
|
|
701
|
-
|
|
702
|
-
---
|
|
703
|
-
|
|
704
|
-
## logger.js — Log 管理
|
|
705
|
-
|
|
706
|
-
**職責**:Claude subagent 的 stream-json 格式化與 log 寫入
|
|
707
|
-
|
|
708
|
-
### Log Writer
|
|
709
|
-
|
|
710
|
-
#### `createLogWriter(opts)`
|
|
711
|
-
|
|
712
|
-
建立 log writer 實例。
|
|
713
|
-
|
|
714
|
-
**參數**:
|
|
715
|
-
```js
|
|
716
|
-
{
|
|
717
|
-
formation: string, // 陣型(決定 log 目錄)
|
|
718
|
-
skill: string, // 技能名稱
|
|
719
|
-
sessionId: string, // session ID
|
|
720
|
-
outputPath?: string, // 自訂輸出路徑
|
|
721
|
-
memberId?: string // Squad 成員 ID
|
|
722
|
-
}
|
|
723
|
-
```
|
|
724
|
-
|
|
725
|
-
**回傳**:
|
|
726
|
-
```js
|
|
727
|
-
{
|
|
728
|
-
stream: WriteStream, // fs.createWriteStream 實例
|
|
729
|
-
path: string, // log 檔案絕對路徑
|
|
730
|
-
writeHeader: () => void, // 寫入 header(formation, skill, session, 時間)
|
|
731
|
-
writeFooter: (code) => void // 寫入 footer(finished, exit code)
|
|
732
|
-
}
|
|
733
|
-
```
|
|
734
|
-
|
|
735
|
-
**Log 目錄結構**:
|
|
736
|
-
```
|
|
737
|
-
.formation/logs/{formation}/{skill}_{memberId?}_{sessionId}.log
|
|
738
|
-
```
|
|
739
|
-
|
|
740
|
-
---
|
|
741
|
-
|
|
742
|
-
### Entry 格式化
|
|
743
|
-
|
|
744
|
-
#### `formatEntry(entry)`
|
|
745
|
-
|
|
746
|
-
格式化 stream-json 的一條 entry。
|
|
747
|
-
|
|
748
|
-
**參數**:
|
|
749
|
-
```js
|
|
750
|
-
entry: {
|
|
751
|
-
type: 'system' | 'assistant' | 'user' | 'result',
|
|
752
|
-
subtype?: string,
|
|
753
|
-
message?: { content: [...] },
|
|
754
|
-
...
|
|
755
|
-
}
|
|
756
|
-
```
|
|
757
|
-
|
|
758
|
-
**回傳**:`string | null`(格式化後的文本,或 null 表示跳過)
|
|
759
|
-
|
|
760
|
-
**支援的 entry types**:
|
|
761
|
-
|
|
762
|
-
1. **system**:
|
|
763
|
-
- `init`: `[SYSTEM][INIT] model=... cwd=...`
|
|
764
|
-
- `hook_started`: `[SYSTEM][HOOK] {hook_name} started`
|
|
765
|
-
- `hook_response`: `[SYSTEM][HOOK] {hook_name} OK/FAILED`
|
|
766
|
-
|
|
767
|
-
2. **assistant**(agent 輸出 + 工具呼叫):
|
|
768
|
-
- `text` block → 移除 markdown 格式,分行輸出 `[Agent] ...`
|
|
769
|
-
- `tool_use` block → `[Agent][{tool}] {detail}`
|
|
770
|
-
|
|
771
|
-
3. **user**(tool results、teammate 訊息):
|
|
772
|
-
- `tool_use_result.status === 'teammate_spawned'` → `[SYSTEM][Spawned] ...`
|
|
773
|
-
- `message.content` 包含 "Message from" → `[Teammate:{name}] | ...`
|
|
774
|
-
|
|
775
|
-
4. **result**(session 結束摘要):
|
|
776
|
-
- `[RESULT] {subtype}`
|
|
777
|
-
- `Duration: {duration_ms/1000}s`
|
|
778
|
-
- `Cost: ${total_cost_usd}`
|
|
779
|
-
- `Turns: {num_turns}`
|
|
780
|
-
- 摘要前 10 行
|
|
781
|
-
|
|
782
|
-
---
|
|
783
|
-
|
|
784
|
-
#### `formatToolUse(ts, block)`
|
|
785
|
-
|
|
786
|
-
格式化 tool_use block。
|
|
787
|
-
|
|
788
|
-
**工具清單**:
|
|
789
|
-
- `Bash`: 顯示 `description` 或 `command` 前 60 字元
|
|
790
|
-
- `Read/Write/Edit`: 顯示 `file_path`
|
|
791
|
-
- `Glob/Grep`: 顯示 `pattern`
|
|
792
|
-
- `TeamCreate`: 顯示 `team_name`
|
|
793
|
-
- `Task`: 顯示 `name` 和 `subagent_type`
|
|
794
|
-
- `SendMessage`: 顯示 `recipient` 和 `type`,並附加完整訊息內容
|
|
795
|
-
|
|
796
|
-
**格式**:
|
|
797
|
-
```
|
|
798
|
-
[HH:MM:SS][Agent][{tool}] {detail}
|
|
799
|
-
| {message line 1}
|
|
800
|
-
| {message line 2}
|
|
801
|
-
| ...
|
|
802
|
-
```
|
|
803
|
-
|
|
804
|
-
---
|
|
805
|
-
|
|
806
|
-
#### `formatUser(ts, entry)`
|
|
807
|
-
|
|
808
|
-
格式化 user events(tool results、teammate 訊息)
|
|
809
|
-
|
|
810
|
-
**格式**:
|
|
811
|
-
```
|
|
812
|
-
[HH:MM:SS][SYSTEM][Spawned] Teammate "{name}" model=...
|
|
813
|
-
[HH:MM:SS][Teammate:{name}]
|
|
814
|
-
| {message line 1}
|
|
815
|
-
| {message line 2}
|
|
816
|
-
| ...
|
|
817
|
-
```
|
|
818
|
-
|
|
819
|
-
---
|
|
820
|
-
|
|
821
|
-
#### `formatResult(ts, entry)`
|
|
822
|
-
|
|
823
|
-
格式化 session 結束摘要。
|
|
824
|
-
|
|
825
|
-
**格式**:
|
|
826
|
-
```
|
|
827
|
-
[HH:MM:SS][RESULT] {subtype}
|
|
828
|
-
Duration: {seconds}s
|
|
829
|
-
Cost: ${usd}
|
|
830
|
-
Turns: {num_turns}
|
|
831
|
-
{result line 1}
|
|
832
|
-
{result line 2}
|
|
833
|
-
...
|
|
834
|
-
```
|
|
835
|
-
|
|
836
|
-
---
|
|
837
|
-
|
|
838
|
-
## utils.js — 工具函數
|
|
839
|
-
|
|
840
|
-
**職責**:路徑常數、Session ID 生成、Git Bash 偵測、環境變數設定
|
|
841
|
-
|
|
842
|
-
### 路徑常數
|
|
843
|
-
|
|
844
|
-
```js
|
|
845
|
-
ROOT // D:\repo\side\ava\KenazAI
|
|
846
|
-
FORMATION_DIR // {ROOT}/.formation
|
|
847
|
-
COLLABORATION_API // {ROOT}/.collaboration/core/task-api.js
|
|
848
|
-
LOG_DIR // {ROOT}/.formation/logs
|
|
849
|
-
```
|
|
850
|
-
|
|
851
|
-
---
|
|
852
|
-
|
|
853
|
-
### Session ID
|
|
854
|
-
|
|
855
|
-
#### `generateSessionId()`
|
|
856
|
-
|
|
857
|
-
生成唯一的 session ID。
|
|
858
|
-
|
|
859
|
-
**格式**:`YYYYMMDD-HHMMSS-{4 位隨機 hex}`
|
|
860
|
-
|
|
861
|
-
**範例**:`20260220-123045-a3f9`
|
|
862
|
-
|
|
863
|
-
---
|
|
864
|
-
|
|
865
|
-
### Git Bash 偵測
|
|
866
|
-
|
|
867
|
-
#### `detectGitBash()`
|
|
868
|
-
|
|
869
|
-
Windows 專用:自動偵測 Git Bash 路徑。
|
|
870
|
-
|
|
871
|
-
**回傳**:`string | null`(bash.exe 的絕對路徑)
|
|
872
|
-
|
|
873
|
-
**偵測順序**:
|
|
874
|
-
1. 從 `where git` 找到 git.exe 路徑
|
|
875
|
-
2. 往上找包含 `bin/bash.exe` 的 Git 根目錄
|
|
876
|
-
3. Fallback 到固定路徑清單:
|
|
877
|
-
- `C:\Program Files\Git\bin\bash.exe`
|
|
878
|
-
- `C:\Program Files (x86)\Git\bin\bash.exe`
|
|
879
|
-
- `D:\Program Files\Git\bin\bash.exe`
|
|
880
|
-
|
|
881
|
-
---
|
|
882
|
-
|
|
883
|
-
### 環境變數
|
|
884
|
-
|
|
885
|
-
#### `getClaudeEnv()`
|
|
886
|
-
|
|
887
|
-
建立 claude 進程的環境變數。
|
|
888
|
-
|
|
889
|
-
**回傳**:`object`(繼承 `process.env` 並修改)
|
|
890
|
-
|
|
891
|
-
**變更**:
|
|
892
|
-
1. 設定 `CLAUDE_CODE_EXPERIMENTAL_AGENT_TEAMS=1`(啟用 agent teams)
|
|
893
|
-
2. 刪除 `CLAUDECODE`(避免 nested session 錯誤)
|
|
894
|
-
3. Windows: 設定 `CLAUDE_CODE_GIT_BASH_PATH`(若未設定)
|
|
895
|
-
|
|
896
|
-
---
|
|
897
|
-
|
|
898
|
-
## loader.js — 任務載入三層 Fallback
|
|
899
|
-
|
|
900
|
-
**職責**:載入 skill YAML + 任務資料(支援新舊兩套任務系統)
|
|
901
|
-
|
|
902
|
-
### Skill 載入
|
|
903
|
-
|
|
904
|
-
#### `loadSkill(formation, skill)`
|
|
905
|
-
|
|
906
|
-
載入 skill YAML 定義。
|
|
907
|
-
|
|
908
|
-
**參數**:
|
|
909
|
-
```js
|
|
910
|
-
formation: string, // 陣型名稱(決定子目錄)
|
|
911
|
-
skill: string // 技能名稱(YAML 檔名,不含 .yaml)
|
|
912
|
-
```
|
|
913
|
-
|
|
914
|
-
**回傳**:`object`(YAML 解析結果)
|
|
915
|
-
|
|
916
|
-
**路徑**:`.formation/{formation}/{skill}.yaml`
|
|
917
|
-
|
|
918
|
-
**錯誤處理**:檔案不存在 → `console.error` + `process.exit(1)`
|
|
919
|
-
|
|
920
|
-
---
|
|
921
|
-
|
|
922
|
-
#### `listSkills(formation)`
|
|
923
|
-
|
|
924
|
-
列出某個陣型下所有可用的 skill。
|
|
925
|
-
|
|
926
|
-
**回傳**:`string[]`(skill 名稱列表,不含 .yaml)
|
|
927
|
-
|
|
928
|
-
---
|
|
929
|
-
|
|
930
|
-
### 任務載入(三層 Fallback)
|
|
931
|
-
|
|
932
|
-
#### `loadTask(taskId)`
|
|
933
|
-
|
|
934
|
-
載入任務資料,支援新舊兩套任務系統。
|
|
935
|
-
|
|
936
|
-
**參數**:
|
|
937
|
-
```js
|
|
938
|
-
taskId: string // TASK_XXX 格式(若不符合或為 null 則回傳 null)
|
|
939
|
-
```
|
|
940
|
-
|
|
941
|
-
**回傳**:`string | null`(YAML 或 JSON 文本)
|
|
942
|
-
|
|
943
|
-
**查詢順序**:
|
|
944
|
-
|
|
945
|
-
1. **新系統** (`.collaboration/tasks/`)
|
|
946
|
-
- 呼叫 `node .collaboration/core/task-api.js get {taskId}`
|
|
947
|
-
- 目錄結構:`{status}/{taskId}_{git_user}.yaml`(status = backlog/active/done/blocked)
|
|
948
|
-
|
|
949
|
-
2. **舊系統 YAML** (`dev/pipeline/completed/` + `tasks/`)
|
|
950
|
-
- 掃描兩個目錄,找到以 `{taskId}` 開頭且 `.yaml` 結尾的檔案
|
|
951
|
-
- 讀取並回傳檔案內容
|
|
952
|
-
|
|
953
|
-
3. **舊系統 JSON** (`dev/pipeline/TASK_QUEUE.json`)
|
|
954
|
-
- 解析 JSON 檔案
|
|
955
|
-
- 從 `tasks` 陣列找到 `id === taskId` 的任務
|
|
956
|
-
- 用 `yaml.dump` 轉為 YAML 格式回傳
|
|
957
|
-
|
|
958
|
-
**錯誤處理**:
|
|
959
|
-
- 所有層都失敗 → `console.warn` + 回傳 `null`(不中斷執行)
|
|
960
|
-
|
|
961
|
-
---
|
|
962
|
-
|
|
963
|
-
### 實作細節
|
|
964
|
-
|
|
965
|
-
#### `loadTaskFromCollaboration(taskId)`
|
|
966
|
-
|
|
967
|
-
新系統載入邏輯。
|
|
968
|
-
|
|
969
|
-
**實作**:
|
|
970
|
-
```js
|
|
971
|
-
const result = execSync(
|
|
972
|
-
`node "${COLLABORATION_API}" get ${taskId}`,
|
|
973
|
-
{ encoding: 'utf8', cwd: ROOT, timeout: 10000 }
|
|
974
|
-
);
|
|
975
|
-
```
|
|
976
|
-
|
|
977
|
-
**錯誤處理**:捕捉 exception 並回傳 `null`
|
|
978
|
-
|
|
979
|
-
---
|
|
980
|
-
|
|
981
|
-
#### `loadTaskFromLegacyYaml(taskId)`
|
|
982
|
-
|
|
983
|
-
舊系統 YAML 檔載入。
|
|
984
|
-
|
|
985
|
-
**實作**:
|
|
986
|
-
```js
|
|
987
|
-
const dirs = ['completed', 'tasks'];
|
|
988
|
-
for (const dir of dirs) {
|
|
989
|
-
const files = fs.readdirSync(dirPath);
|
|
990
|
-
const match = files.find(f => f.startsWith(taskId) && f.endsWith('.yaml'));
|
|
991
|
-
if (match) return fs.readFileSync(...);
|
|
992
|
-
}
|
|
993
|
-
```
|
|
994
|
-
|
|
995
|
-
---
|
|
996
|
-
|
|
997
|
-
#### `loadTaskFromLegacyQueue(taskId)`
|
|
998
|
-
|
|
999
|
-
舊系統 JSON 索引載入。
|
|
1000
|
-
|
|
1001
|
-
**實作**:
|
|
1002
|
-
```js
|
|
1003
|
-
const queue = JSON.parse(fs.readFileSync(LEGACY_TASK_QUEUE, 'utf8'));
|
|
1004
|
-
const task = queue.tasks.find(t => t.id === taskId);
|
|
1005
|
-
if (task) return yaml.dump(task, { lineWidth: -1 });
|
|
1006
|
-
```
|
|
1007
|
-
|
|
1008
|
-
---
|
|
1009
|
-
|
|
1010
|
-
## 呼叫關係圖
|
|
1011
|
-
|
|
1012
|
-
```
|
|
1013
|
-
CLI (node .formation/tools/headless.js --formation=squad --skill=blitz)
|
|
1014
|
-
↓
|
|
1015
|
-
headless.js:launch()
|
|
1016
|
-
↓
|
|
1017
|
-
├─→ loader.js:loadSkill(formation, skill) → 載入 YAML
|
|
1018
|
-
├─→ loader.js:loadTask(taskId) → 三層 fallback 載入任務
|
|
1019
|
-
├─→ prompt.js:buildPrompt(skillDef, taskInput) → 組裝 prompt
|
|
1020
|
-
↓
|
|
1021
|
-
├── formation='squad' → headless.js:launchSquad()
|
|
1022
|
-
│ ↓
|
|
1023
|
-
│ ├─→ runner.js:runHeadless() × N (Round 1)
|
|
1024
|
-
│ │ ↓
|
|
1025
|
-
│ │ ├─→ runner.js:spawnClaude()
|
|
1026
|
-
│ │ │ ↓
|
|
1027
|
-
│ │ │ ├─→ logger.js:createLogWriter()
|
|
1028
|
-
│ │ │ ├─→ utils.js:getClaudeEnv()
|
|
1029
|
-
│ │ │ └─→ runner.js:collectOutput()
|
|
1030
|
-
│ │ │ ↓
|
|
1031
|
-
│ │ │ └─→ logger.js:formatEntry() → log 寫入
|
|
1032
|
-
│ │ └─→ waitAll() → 等待所有進程完成
|
|
1033
|
-
│ ↓
|
|
1034
|
-
│ ├─→ prompt.js:buildSquadDebatePrompts() (Round 2)
|
|
1035
|
-
│ ├─→ runner.js:runHeadless() × N (Round 2)
|
|
1036
|
-
│ └─→ headless.js:squadSynthesis()
|
|
1037
|
-
│ ↓
|
|
1038
|
-
│ └─→ prompt.js:buildSquadSynthesisPrompt()
|
|
1039
|
-
│ ↓
|
|
1040
|
-
│ └─→ runner.js:runHeadless()
|
|
1041
|
-
│
|
|
1042
|
-
├── formation='legion' → headless.js:launchLegion()
|
|
1043
|
-
│ ↓
|
|
1044
|
-
│ ├─→ prompt.js:buildLegionLeadPrompt()
|
|
1045
|
-
│ └─→ runner.js:runLegionLead()
|
|
1046
|
-
│ ↓
|
|
1047
|
-
│ └─→ runner.js:spawnClaude(extraArgs: ['--teammate-mode', ...])
|
|
1048
|
-
│
|
|
1049
|
-
├── formation='unit' → headless.js:launchUnit()
|
|
1050
|
-
│ ↓
|
|
1051
|
-
│ └─→ runner.js:runHeadless()
|
|
1052
|
-
│
|
|
1053
|
-
├── formation='solo' → headless.js:launchSolo()
|
|
1054
|
-
│ ↓
|
|
1055
|
-
│ └─→ runner.js:runHeadless()
|
|
1056
|
-
│
|
|
1057
|
-
└── formation='legacy' → headless.js:launchLegacy()
|
|
1058
|
-
↓
|
|
1059
|
-
└─→ legacy-scheduler.js:start()
|
|
1060
|
-
```
|
|
1061
|
-
|
|
1062
|
-
---
|
|
1063
|
-
|
|
1064
|
-
## 關鍵流程範例
|
|
1065
|
-
|
|
1066
|
-
### 範例 1:Unit 執行流程
|
|
1067
|
-
|
|
1068
|
-
**命令**:
|
|
1069
|
-
```bash
|
|
1070
|
-
node .formation/tools/headless.js --skill=do --task="修正按鈕顏色"
|
|
1071
|
-
```
|
|
1072
|
-
|
|
1073
|
-
**流程**:
|
|
1074
|
-
1. `headless.launch()` 解析參數:`formation='unit', skill='do', task='修正按鈕顏色'`
|
|
1075
|
-
2. `loader.loadSkill('unit', 'do')` → 讀取 `.formation/unit/do.yaml`
|
|
1076
|
-
3. `prompt.buildPrompt()` → 呼叫 `buildUnitPrompt()` 組裝 prompt
|
|
1077
|
-
4. `headless.launchUnit()` → 呼叫 `runner.runHeadless()`
|
|
1078
|
-
5. `runner.spawnClaude()` 啟動 `claude.cmd -p - ...`
|
|
1079
|
-
6. `collectOutput()` 收集輸出,`formatEntry()` 格式化每條 entry
|
|
1080
|
-
7. 寫入 `.formation/logs/unit/do_{sessionId}.log`
|
|
1081
|
-
|
|
1082
|
-
---
|
|
1083
|
-
|
|
1084
|
-
### 範例 2:Squad 執行流程(含 Debate)
|
|
1085
|
-
|
|
1086
|
-
**命令**:
|
|
1087
|
-
```bash
|
|
1088
|
-
node .formation/tools/headless.js --formation=squad --skill=blitz --task=TASK_201
|
|
1089
|
-
```
|
|
1090
|
-
|
|
1091
|
-
**流程**:
|
|
1092
|
-
1. `headless.launch()` 解析參數:`formation='squad', skill='blitz', task='TASK_201'`
|
|
1093
|
-
2. `loader.loadTask('TASK_201')` → 三層 fallback 載入任務 YAML
|
|
1094
|
-
3. `prompt.buildSquadPrompts()` → 回傳 `[{ memberId, prompt, skill }, ...]`
|
|
1095
|
-
4. `headless.launchSquad()`:
|
|
1096
|
-
- **Round 1**:`runHeadless()` × N,並行啟動所有成員
|
|
1097
|
-
- `waitAll()` 等待所有進程完成
|
|
1098
|
-
- 若 `skillDef.debate.enabled=true`:
|
|
1099
|
-
- **Round 2**:`buildSquadDebatePrompts()` 組裝辯論 prompts
|
|
1100
|
-
- `runHeadless()` × N,成員互相讀取報告
|
|
1101
|
-
- **Synthesis**:`buildSquadSynthesisPrompt()` + `runHeadless()`
|
|
1102
|
-
5. 每個成員的輸出分別寫入:
|
|
1103
|
-
- R1: `.formation/logs/squad/{member.id}_{sessionId}.log`
|
|
1104
|
-
- R2: `.formation/logs/squad/{member.id}-r2_{sessionId}.log`
|
|
1105
|
-
- Synthesis: `.formation/logs/squad/{skill}-synthesis_{sessionId}.log`
|
|
1106
|
-
|
|
1107
|
-
---
|
|
1108
|
-
|
|
1109
|
-
### 範例 3:Legion 執行流程
|
|
1110
|
-
|
|
1111
|
-
**命令**:
|
|
1112
|
-
```bash
|
|
1113
|
-
node .formation/tools/headless.js --formation=legion --skill=forge --task=TASK_202
|
|
1114
|
-
```
|
|
1115
|
-
|
|
1116
|
-
**流程**:
|
|
1117
|
-
1. `prompt.buildLegionPrompts()` → 回傳 `{ teamName, lead, members }`
|
|
1118
|
-
2. `prompt.buildLegionLeadPrompt()` → 組裝 lead prompt(含 `LEGION_AUTO_EXECUTE`)
|
|
1119
|
-
3. `runner.runLegionLead()` → 啟動 lead agent(`--teammate-mode in-process`)
|
|
1120
|
-
4. Lead agent 用 `Task` 工具 spawn teammates(進程內並行)
|
|
1121
|
-
5. Lead agent 進入 polling loop(`sleep 5` + check messages)
|
|
1122
|
-
6. 等待所有 teammates 回報 → 整合結果 → 結束
|
|
1123
|
-
|
|
1124
|
-
---
|
|
1125
|
-
|
|
1126
|
-
## 總結
|
|
1127
|
-
|
|
1128
|
-
Formation 工具鏈設計遵循以下核心原則:
|
|
1129
|
-
|
|
1130
|
-
1. **分層架構**:L1 基礎設施 → L2 載入 → L3 prompt → L4 進程 → L5 編排
|
|
1131
|
-
2. **單一職責**:每個模組只做一件事,介面清晰
|
|
1132
|
-
3. **可測試性**:dry-run 可在 prompt 層停下,不啟動進程
|
|
1133
|
-
4. **統一進程管理**:所有陣型的 subagent 啟動都經過 `runner.js`
|
|
1134
|
-
5. **統一日誌格式**:所有 log 都經過 `logger.js` 格式化
|
|
1135
|
-
6. **雙系統相容**:任務載入支援新舊兩套系統(三層 fallback)
|
|
1136
|
-
|
|
1137
|
-
**擴展建議**:
|
|
1138
|
-
- 新增陣型:在 `.formation/{formation}/` 建立 YAML,在 `headless.js` 新增 launcher
|
|
1139
|
-
- 新增工具支援:在 `logger.js:formatToolUse()` 新增格式化規則
|
|
1140
|
-
- 調整 prompt 結構:修改 `prompt.js` 對應的 builder 函數
|
|
1141
|
-
|
|
1142
|
-
**維護要點**:
|
|
1143
|
-
- 修改 prompt 結構時,同步更新 `.formation/{formation}/` 下的 YAML 範例
|
|
1144
|
-
- 新增環境變數時,在 `utils.js:getClaudeEnv()` 統一設定
|
|
1145
|
-
- 修改 log 格式時,確保與 Sunny 的 `format-output.js` 保持一致
|