Commit Graph

5 Commits

Author SHA1 Message Date
Leo 93bb4d3327 feat(registry): Phase 3 G0 人類閘門(submit 端強制人類確認 + 舉證)
- submitComponent 加 SubmitOptions(human_confirmation + gherkin_evidence + skip_acceptance)
- G0 閘門:非 skip_acceptance 的新投稿,缺 human_confirmation(confirmed_by_human
  + 非空 reason_why_not_workflow)→ 退稿指回「先試工作流,需人類確認」
- human_confirmation + gherkin_evidence 寫進 KV metadata(軌跡可審)
- components route 從 multipart/JSON 解析這些欄位傳入
- backfill(skip_acceptance)不受閘門影響

design 命名修正:投稿走既有 acr parts publish(非另建指令,符合「修改現有不重建」)。

待續: G0-CLI(acr parts publish 互動式問人類)、G4-CLI(本地跑 Gherkin + evidence)、
R5(MVP_COMPONENTS.txt 白名單 + 本機 hook)。

Co-Authored-By: Claude Opus 4.8 <noreply@anthropic.com>
2026-05-29 18:03:49 +08:00
Leo 497f92a268 feat(arcrun): recipe system + resumable workflow + component registry canon
Three new platform capabilities + one component (kbdb_get) to enable
real AI workflow execution through cypher binding YAML.

## Recipe System (容器 + Recipe 模式)
SDD: .agents/specs/recipe-system/

- prompt_recipe schema (Zod): fragments + inputs + assembly + output
- recipe-expander.ts: expand recipe ref → real prompt by fetching KBDB blocks
  + pulling context fields with transforms (pluck_content / extract_field / etc)
- 7 transform whitelist: json_array / to_string / join / markdown_list /
  extract_field / first / pluck_content
- graph-executor hooks: detect node.data.recipe → expand → inject into ctx
- output JSON parser (with markdown fence stripping for Claude-wrapped JSON)
- Stored in RECIPES KV under prompt_recipe:{name}

## Resumable Workflow (webhook callback resume)
SDD: .agents/specs/resumable-workflow/

- WorkflowPaused class + paused-runs.ts (persist/load/consume in EXEC_CONTEXT KV, 24h TTL)
- graph-executor: detect {pending:true, task_id} → persist state → throw WorkflowPaused
- cypher-handlers: catch → return {success:true, paused:true, task_id, run_id}
- POST /workflows/resume route: consume KV state → resumeFromPaused()
- Auto-inject callback_url for claude_api nodes (PUBLIC_BASE_URL or default cypher.arcrun.dev)
- claude_api/main.go: forward callback_url to Mira daemon, default timeout 25s→120s
- Idempotent (consume = load+delete)

## Component Registry Canon
SDD: .agents/specs/component-registry-canon/

- Add POST /components/index-only endpoint (metadata-only, no wasm/sandbox)
- Backfill script (mjs): scan registry/components/*/contract.yaml → submit to KV
- register-component.sh: SSOT for local + CI hook (deploy.yml change in next commit)
- Drop R2 dead storage from submitComponent + types + wrangler
- Schema relaxed: category enum + auth/ai/platform; cold_start 50→500ms; size 2→8MB

## kbdb_get component
- registry/components/kbdb_get/: TinyGo WASM, two modes (block_id / page_name list)
- .component-builds/kbdb_get/: WASI shim worker (kbdb-get.arcrun.dev)

End-to-end validation: AI uses MCP execute_workflow with recipe ref →
cypher-executor expands prompt from KBDB schema/skill blocks + drafts →
claude_api calls Mira daemon → daemon callback fires resume route →
workflow continues. Verified with real 2KB+ Karpathy LLM Wiki draft.

🤖 Generated with [Claude Code](https://claude.com/claude-code)

Co-Authored-By: Claude Opus 4.7 <noreply@anthropic.com>
2026-05-07 15:52:19 +08:00
Leo 8e2c32e466 feat(registry): component_hash_id — stable id system for workflow references
Problem: canonical_id is readable but mutable; if a component is renamed,
all workflows referencing it by canonical_id break.

Solution: dual-id system
- component_hash_id: cmp_{sha256(canonical_id).slice(0,8)}, derived deterministically,
  never changes, safe for workflow references
- canonical_id: human-readable name, used for search and display
- idx:{canonical_id} KV key: reverse-lookup index for resolving canonical_id → hash_id

Changes:
- types.ts: SandboxResult.component_id → component_hash_id + canonical_id,
  added 'data' to category enum
- submitComponent.ts: deriveHashId(), writes idx: reverse-lookup on submit
- queryComponents.ts: full rewrite — removed KBDB dependency, uses SUBMISSIONS_KV;
  supports both cmp_* and canonical_id as query id; Phase 0 keyword search
  with note to upgrade to Vectorize in Phase 2
- sandboxAcceptance.ts: updated field names, fixed TextDecoder TS type
- ensureTemplate.ts: removed KBDB dependency, now a KV health check
- tests: updated component_id → canonical_id
- CONTRIBUTING.md: explain hash_id derivation and dual-id workflow reference syntax

Co-Authored-By: Claude Sonnet 4.6 <noreply@anthropic.com>
2026-04-16 14:41:22 +08:00
Leo e630fca2df fix(arcrun): address PR #2 review findings
Security:
- init.ts: remove cf_api_token from POST /register (only email sent to arcrun.dev)
- cf-api.ts: remove base64 fallback in encryptCredential, throw clear error if key missing

Correctness:
- submitComponent.ts: replace KBDB dependency with SUBMISSIONS_KV + R2 (standalone)
- registry/types.ts: remove KBDB_URL/KBDB_INTERNAL_TOKEN, add SUBMISSIONS_KV/ANALYTICS_KV
- webhooks.ts: add waitUntil(writeExecutionVerdict) for fire-and-forget analytics
- execution-logger.ts: create missing module (was imported but didn't exist)
- cypher-executor/types.ts + wrangler.toml: add ANALYTICS_KV binding
- gmail/telegram/google_sheets/line_notify/http_request: no_network_syscall false (api category)
- init.ts: replace require() with await import() for ES module compatibility

Cleanup:
- Remove arcrun/builtins/ (dead code — initComponents used old HTTP endpoint model,
  all 21 components now in TinyGo WASM under registry/components/)

Docs:
- tasks.md: update to reflect completed work and remaining items

Co-Authored-By: Claude Sonnet 4.6 <noreply@anthropic.com>
2026-04-16 13:07:28 +08:00
Claude 2707fca32b feat(arcrun): implement arcrun MVP — open-source AI workflow engine
Phase 1-5 complete per .agents/specs/u6u-core-mvp/:

**Phase 1 — Cherry-pick & cleanup**
- Create arcrun/ from cypher-executor, credentials, builtins, registry
- Remove 9 InkStone Service Bindings (KBDB, REGISTRY, CLINIC_*, AICEO, MINI_ME)
- Rewrite component-loader: 3-layer (builtin → WASM_BUCKET R2 → error)
- Remove autoPublishMissing.ts, proxy.ts (AICEO), execution-logger.ts (KBDB)
- Clean all KV namespace IDs and InkStone internal URLs from config files

**Phase 2 — contract.yaml completeness**
- Add credentials_required to gmail, google_sheets, telegram, line_notify
- Add config_example to all 21 components with annotated field descriptions

**Phase 3 — Credential injection**
- Add credential-injector.ts: AES-GCM decrypt from CREDENTIALS_KV
- Integrate into GraphExecutor before WASM execution
- Structured errors with repair instructions when credential missing

**Phase 4 — CLI (acr)**
- cli/package.json: arcrun package, bin: acr, deps: commander/js-yaml/chalk/ora
- 8 commands: init, creds push, push, run, validate, parts, list, logs
- Standard mode: writes directly to user's CF KV via CF REST API
- acr init: interactive setup with arcrun.dev API Key registration

**Phase 5 — Open source release prep**
- README.md: 5-minute quickstart, component table, workflow YAML syntax
- CONTRIBUTING.md: TinyGo dev env, component scaffolding, submission flow
- Security audit: no InkStone internal URLs/IDs in committed files
- .gitignore: exclude credentials.yaml, .wrangler, *.wasm

https://claude.ai/code/session_01BnCdSLVH8tUed9VrrPavgT
2026-04-16 04:06:25 +00:00