发布 v0.8.3

.trellis/.version

@@ -1 +1 @@
-0.6.7
+0.6.10

.trellis/spec/backend/auth-login-methods.md

@@ -0,0 +1,132 @@
+# Auth Login Methods(登录方式接入契约)
+
+> 面板现有登录方式:密码(+可选 TOTP)、OIDC / GitHub(OAuth)、通行密钥(Passkey / WebAuthn)、Web3 钱包(EIP-4361)。
+> 新增或修改任何登录方式时,以下契约是安全红线,缺一不可。
+
+## 1. 登录守卫(防爆破)
+
+公开登录端点的失败必须计入 `loginGuard`:`guardKey(clientIP, <账号标识>)`,账号未知用固定占位名(如 passkey 的 `__passkey__`),已知用其标识(如钱包地址小写)。锁定检查在校验之前;失败经 `auth.failLogin`(自带阈值转锁定与告警推送),成功 `guard.success`。阈值/时长取安全设置,不硬编码。
+
+## 2. 系统日志留痕
+
+公开登录端点不经系统日志中间件,handler 必须显式 `logs.Record` 成败(参考 `authHandler.recordLogin` / `passkeyHandler.recordLogin` / `walletHandler.recordWallet`);登录失败是安全关键事件,不允许无痕。JWT 组内的绑定/解绑由中间件自动留痕,无需额外埋点。
+
+## 3. 令牌版本(TokenVersion)
+
+绑定、解绑、凭据及认证因子变更均属敏感变更:必须在事务内
+`bumpTokenVersionTx`(或 `RevokeSessions`)使旧 JWT 失效，并按第 6 节携带
+`TokenProof`、接续操作者会话。因子写入与版本递增不得拆成两个独立提交。
+
+## 4. 「至少一种登录方式」不变量
+
+密码登录禁用要求至少一种在当前 `EffectiveAppURL` 下**可实际登录**的免密方式
+(`usablePasswordlessTx`);地址为空时 Passkey、钱包和 OAuth 均不可用。禁用期间移除
+最后一种免密方式被拒:解绑身份走 `ensureNotLastLogin`,删通行密钥走对称检查。
+这些检查都在事务内先 `lockUserForAuthChange` 锁用户行,防并发绕过。新登录方式要
+明确决策如何参与该不变量:
+
+- **复用 `UserIdentity` 表**(如钱包,provider+subject 唯一)→ 走 `identityCountTx` 自动参与,零改动;
+- **独立表**(如 Passkey 的 `UserPasskey`)→ 参照 `passkeyCountTx` 增加计数入口,并在开启门槛(`hasAnyPasswordless`)与两个 `ensureNot*` 检查里对称接入;api 层把 `ErrLastIdentity` 映射 409。
+
+## 5. 挑战/状态的一次性消费
+
+挑战-响应类流程(OAuth state、WebAuthn challenge、SIWE nonce)一律进程内 `map + mutex + TTL + gc`,取用即删(参考 `oauthPending` / `passkeyPending` / `walletPending`);不落库、不引 Redis。TTL 5-10 分钟。
+
+## 6. 场景：已鉴权敏感事务的提交屏障
+
+### 1. Scope / Trigger
+
+凡请求先通过 JWT 中间件、随后仍会读取 body、等待外部回调或写入认证/安全配置，
+都必须防止请求处理期间的 Logout、定点撤销或撤销全部会话被旧请求绕过。
+
+### 2. Signatures
+
+```go
+type TokenProof struct {
+    Ver uint
+    Jti string
+}
+
+func tokenProofOf(c *gin.Context) service.TokenProof
+func (s *AuthService) ensureTokenCurrentTx(
+    tx *gorm.DB, user *model.User, proof TokenProof,
+) error
+func (s *AuthService) RenewToken(
+    ctx context.Context, username, oldToken string, meta SessionMeta,
+) (string, time.Time, error)
+```
+
+持久化契约使用 `user_sessions.token_id` 表示逻辑会话；敏感换发不改变该 JTI。
+
+### 3. Contracts
+
+- `RequireAuth` 必须把本次请求实际观察到的 `TokenVersion + JTI` 写入 Context，
+  Handler 不得事后只按用户名读取“最新版本”代替 proof。
+- 敏感事务、`RevokeSession` 与 Logout 的数据库路径统一先锁用户行，再检查/更新
+  会话行；持锁后调用 `ensureTokenCurrentTx`。
+- proof 通过后，认证因子写入、版本递增及事务内换发必须同成同败。需要在 Handler
+  末尾换发的旧接口，`RenewToken` 也须重新锁用户并确认当前版本恰为
+  `oldClaims.Ver + 1`。
+- 换发沿用旧 JWT 的合法 JTI；有旧会话行时只接续未撤销行，存在但已撤销或更新
+  失败必须关闭。兼容期无行 Token 可建行，但仍沿用旧 JTI，因此 Logout 的
+  tombstone 能同时撤销换发前后的 JWT。
+- Logout 持久撤销须按 JTI 会话行解析稳定的 `user_id`，不得只按旧 JWT 的可变
+  username/subject 找用户；JTI tombstone 至少保留“旧 JWT 剩余寿命 +
+  一个完整 `tokenTTL`”，兜住 legacy 无行换发、改名提交和持久化撤销之间的
+  窄窗口。
+- 外部身份登录须在用户锁内重查身份仍绑定；OAuth 登录还须在最终签发事务内重查
+  Provider 当前可用。
+- proof 不二次检查自然到期：请求在 JWT 未过期时通过中间件即取得本次请求的认证
+  边界；不得为此额外引入长事务、分布式锁或持久状态机。
+
+### 4. Validation & Error Matrix
+
+| 条件 | 结果 |
+| --- | --- |
+| `user.TokenVersion != proof.Ver` | `ErrTokenStale` → HTTP 401 |
+| JTI tombstone 命中或会话行已撤销 | `ErrTokenStale` → HTTP 401 |
+| 旧会话行存在但接续命中 0 行 | 失败关闭，不得 fallback 创建 |
+| 已验签当前版本的兼容 Token 确无会话行 | 沿用原 JTI 创建会话行 |
+| 改名后用换发前 JWT Logout | 按 JTI/user_id 撤销新旧 JWT；旧 subject 不参与归属 |
+| Handler 分段换发时版本不是 `oldVer + 1` | `ErrTokenStale`，前端重新登录 |
+| 登录签发前身份已解绑 / Provider 已不可用 | 拒绝登录，不签发 JWT |
+
+### 5. Good / Base / Bad Cases
+
+- Good：TOTP 激活事务内依次锁用户、验 proof、写因子、递增版本、沿用 JTI 换发。
+- Base：无会话行的存量 JWT 可完成一次合法变更，但换发后的 JWT 与旧 JWT 共用
+  JTI，后到 Logout 可同时撤销。
+- Bad：proof 普通查询通过后释放锁，定点撤销完成，再把旧行更新失败当“无行”创建
+  新会话；这会复活已撤销 Token。
+
+### 6. Tests Required
+
+- TOTP 激活 × 撤销全部：旧 proof 返回 `ErrTokenStale`，因子与版本均不改变。
+- proof check → 定点撤销 → renew：撤销后的行不得被新建替代。
+- recorded 与 legacy 无行会话各测一次“改名后 old-token Logout”：换发 JWT
+  必须随同失效；recorded 行写入 `revoked_at`，legacy tombstone 覆盖 fresh expiry。
+- OAuth/钱包登录在最终事务前删除身份：不得签发会话；OAuth 禁用同理。
+- Security/OAuth PATCH 使用已撤销 proof：返回 `ErrTokenStale` 且设置不落库。
+
+### 7. Wrong vs Correct
+
+```go
+// Wrong：只按最新用户状态改因子，随后无条件签最新版本 JWT。
+saveFactor()
+bumpTokenVersion()
+return IssueToken(ctx, username)
+
+// Correct：请求 proof、因子写入、版本递增和会话接续共享事务与用户锁。
+return db.Transaction(func(tx *gorm.DB) error {
+    user, err := lockUserForAuthChange(tx, username)
+    if err != nil { return err }
+    if err := auth.ensureTokenCurrentTx(tx, user, proof); err != nil { return err }
+    return changeFactorAndRenewTx(tx, user, oldToken)
+})
+```
+
+## 其他约定
+
+- 面板地址依赖:RP ID / 回调 / SIWE domain 均派生自 `settings.EffectiveAppURL()`,为空时返回引导错误(文案对齐 `ErrOAuthNoAppURL`),不得回退猜测。
+- 登录失败对外文案统一、不透出内部细节(防探测);错误变量集中定义在对应 service 文件头部。
+- 新端点全量 swagger 中文注释并重新生成 docs/;providers 公开端点(`/auth/oauth/providers`)按需追加 `<method>Login` 可用性布尔,供登录页渲染入口。

.trellis/spec/backend/database-guidelines.md

@@ -60,3 +60,7 @@ db.Model(&model.AiChannel{}).
 **Fix**:键值加入 `cred.CompartmentID`(空 = 租户根,天然区分)。
 
 **Prevention**:缓存键必须覆盖影响回源结果的**全部**输入维度(租户、区间、区域、过滤参数);给 Credentials/查询结构体新增会改变结果的字段时,同步检查 `ckey` 调用点;隔离行为写进 `cached_test.go` 的 isolation 用例。
+
+## GORM 列名与 map 更新
+
+- GORM 默认命名把连续大写按公共缩写拆分:`UserOCID` → `user_oc_id`、`TenancyOCID` → `tenancy_oc_id`(不是 `user_ocid`)。用 `Updates(map[string]any{...})` 写裸列名前先确认真实列名(`schema.Parse` 或查建表 SQL),SQLite 下写错列名报 "no such column" 才暴露,MySQL/PG 同错。零值字段(如清空 `passphrase_enc`)必须走 map 更新,struct 更新会忽略零值。(2026-07-23 activate-api-key 切换签名用户)

.trellis/spec/backend/index.md

@@ -22,6 +22,7 @@ Gin + GORM + SQLite(纯 Go 驱动 `glebarez/sqlite`,免 CGO;默认与推荐)+ AE
 | [IdP Icon Upload](./idp-icon-upload.md) | IdP 公共图标上传、校验与清理契约 | 已填 |
 | [Database Guidelines](./database-guidelines.md) | GORM 实战约定与常见坑 | 已填 |
 | [OCI Audit](./oci-audit.md) | 审计事件双通道数据源、检索语义与预算纪律 | 已填 |
+| [Auth Login Methods](./auth-login-methods.md) | 登录方式接入契约(守卫/留痕/令牌版本/不变量/一次性挑战) | 已填 |
 
 ---
 

.trellis/spec/backend/oci-audit.md

@@ -20,7 +20,7 @@
 
 ## 日志回传链路(logrelay)资源命名与描述纪律
 
-- **命名派生**:Topic 前缀、IAM Policy 名、SCH Connector DisplayName 一律由 `relayResourceNames(tenancyOCID)`(见 `internal/oci/logrelay_names.go`)基于 `SHA-256(tenancyOCID)[:4]` 派生 `<8hex>-audit` / `<8hex>-audit-p`。**不得在 `logrelay.go` 里再引入品牌明文**(`oci-portal` / `ociportal` / `logs` 等),否则跨租户恒定字面量会成为 Oracle 内部风控识别「共用同一套 oci-portal」的强指纹;背景与证据分档见调研档案 `docs/oci-sdk-caller-fingerprint.md`。
+- **命名派生**:Topic 前缀、IAM Policy 名、SCH Connector DisplayName 一律由 `relayResourceNames(tenancyOCID)`(见 `internal/oci/logrelay_names.go`)基于 `SHA-256(tenancyOCID)[:4]` 派生 `<8hex>-audit` / `<8hex>-audit-p`。**不得在 `logrelay.go` 里再引入品牌明文**(`oci-portal` / `ociportal` / `logs` 等),否则跨租户恒定字面量会成为 Oracle 内部风控识别「共用同一套 oci-portal」的强指纹;背景与证据分档见工作区任务归档 `.trellis/tasks/archive/2026-07/07-22-research-oci-caller-info/research/oci-sdk-caller-fingerprint.md`。
 - **描述文本**:Topic 与 Policy 的 `Description` 用集中常量 `relayTopicDescNew` / `relayPolicyDescNew`(中性英文),不允许写 `oci-portal 日志回传:...` 等品牌/中文明文;SCH Connector 干脆不设 `Description`,避免恒定文案。
 - **向后兼容 legacy 命名**:`findRelayTopic` / `findRelayPolicy` / `findRelayConnector` 支持传入多前缀/多名称,顺序为「新命名 → legacy 命名」;新增查找需求要沿用变参签名,不要单独硬编码 legacy 常量到业务函数里。命中 legacy 资源时,`refreshRelayTopicDesc` / `refreshRelayPolicyDesc` 会尽力刷新描述为中性文案,失败不阻塞主流程(权限/服务限流等场景直接忽略)。
 - **测试**:命名派生、legacy 常量值、描述中性性由 `logrelay_names_test.go` table-driven 锁定;若必须调整 legacy 常量,先评估是否会让存量租户找不到既有资源导致重复创建。

.trellis/workflow.md

@@ -183,7 +183,7 @@ Complex task: ask the user if you can create a Trellis task and enter the planni
 - 1.0 Create task `[required · once]` (only after task-creation consent)
 - 1.1 Requirement exploration `[required · repeatable]` (`prd.md`; complex tasks also need `design.md` + `implement.md`)
 - 1.2 Research `[optional · repeatable]`
-- 1.3 Configure context `[required · once]` — Claude Code, Cursor, OpenCode, Codex, Kiro, Gemini, Qoder, CodeBuddy, Copilot, Droid, Pi, Oh My Pi, ZCode, Reasonix (sub-agent-dispatch platforms only; inline platforms skip)
+- 1.3 Configure context `[required · once]` — Claude Code, Cursor, OpenCode, Codex, Kiro, Gemini, Qoder, CodeBuddy, Copilot, Droid, Pi, Oh My Pi, ZCode, Snow, Reasonix, Grok, Kimi Code (sub-agent-dispatch platforms only; inline platforms skip)
 - 1.4 Activate task `[required · once]` (review gate, then `task.py start`; status → in_progress)
 - 1.5 Completion criteria
 
@@ -220,7 +220,7 @@ Inline mode: skip jsonl curation; Phase 2 reads artifacts/specs via `trellis-bef
      therefore must cover every required step from implementation through
      commit, including Phase 3.3 spec update and Phase 3.4 commit. -->
 
-Sub-agent dispatch protocol applies to all platforms and all sub-agents, including class-2 Codex/Gemini/Qoder/Copilot/ZCode/Reasonix/Trae and `trellis-research`: every dispatch prompt starts with `Active task: <task path from task.py current>` before role-specific instructions.
+Sub-agent dispatch protocol applies to all platforms and all sub-agents, including native Codex `SubagentStart` context injection with child-side pull fallback, class-2 Gemini/Qoder/Copilot/Reasonix/Trae/Grok/Kimi Code, hook-backed ZCode/Snow, and `trellis-research`: every dispatch prompt starts with `Active task: <task path from task.py current>` before role-specific instructions. On Grok Build, use `spawn_subagent` with `subagent_type` set to the Trellis agent name (e.g. `trellis-implement`). On Kimi Code, dispatch the built-in `coder` / `explore` sub-agent with the matching `.kimi-code/skills/trellis-<role>/SKILL.md` instructions.
 
 [workflow-state:in_progress]
 Tools: `trellis-implement` / `trellis-research` are sub-agent types only (Task/Agent tool, NOT Skill; there is no skill by these names). `trellis-update-spec` is a skill. `trellis-check` exists as both; prefer the Agent form when verifying after code changes.
@@ -272,13 +272,13 @@ Code committed. Run `/trellis:finish-work`; if dirty, return to Phase 3.4 first.
 
 When a user request matches one of these intents inside an active task, route first, then load the detailed phase step if needed.
 
-[Claude Code, Cursor, OpenCode, codex-sub-agent, Kiro, Gemini, Qoder, CodeBuddy, Copilot, Droid, Pi, Oh My Pi, ZCode, Reasonix, Trae]
+[Claude Code, Cursor, OpenCode, codex-sub-agent, Kiro, Gemini, Qoder, CodeBuddy, Copilot, Droid, Pi, Oh My Pi, ZCode, Snow, Reasonix, Trae, Grok, Kimi Code]
 
 - Planning or unclear requirements -> `trellis-brainstorm`.
 - `in_progress` implementation/check -> dispatch `trellis-implement` / `trellis-check`.
 - Repeated debugging -> `trellis-break-loop`; spec updates -> `trellis-update-spec`.
 
-[/Claude Code, Cursor, OpenCode, codex-sub-agent, Kiro, Gemini, Qoder, CodeBuddy, Copilot, Droid, Pi, Oh My Pi, ZCode, Reasonix, Trae]
+[/Claude Code, Cursor, OpenCode, codex-sub-agent, Kiro, Gemini, Qoder, CodeBuddy, Copilot, Droid, Pi, Oh My Pi, ZCode, Snow, Reasonix, Trae, Grok, Kimi Code]
 
 [codex-inline, Kilo, Antigravity, Devin]
 
@@ -353,7 +353,7 @@ Return to this step whenever requirements change and revise the relevant artifac
 
 Research can happen at any time during requirement exploration. It isn't limited to local code — you can use any available tool (MCP servers, skills, web search, etc.) to look up external information, including third-party library docs, industry practices, API references, etc.
 
-[Claude Code, Cursor, OpenCode, codex-sub-agent, Kiro, Gemini, Qoder, CodeBuddy, Copilot, Droid, Pi, Oh My Pi, ZCode, Reasonix, Trae]
+[Claude Code, Cursor, OpenCode, codex-sub-agent, Kiro, Gemini, Qoder, CodeBuddy, Copilot, Droid, Pi, Oh My Pi, ZCode, Snow, Reasonix, Trae, Grok, Kimi Code]
 
 Spawn the research sub-agent:
 
@@ -361,11 +361,11 @@ Spawn the research sub-agent:
 - **Task description**: Research <specific question>
 - **Key requirement**: Research output MUST be persisted to `{TASK_DIR}/research/`
 
-[/Claude Code, Cursor, OpenCode, codex-sub-agent, Kiro, Gemini, Qoder, CodeBuddy, Copilot, Droid, Pi, Oh My Pi, ZCode, Reasonix, Trae]
+[/Claude Code, Cursor, OpenCode, codex-sub-agent, Kiro, Gemini, Qoder, CodeBuddy, Copilot, Droid, Pi, Oh My Pi, ZCode, Snow, Reasonix, Trae, Grok, Kimi Code]
 
 [codex-inline, Kilo, Antigravity, Devin]
 
-Do the research in the main session directly and write findings into `{TASK_DIR}/research/`. (For `codex-inline` this avoids the `fork_turns="none"` isolation that prevents `trellis-research` sub-agents from resolving the active task path.)
+Do the research in the main session directly and write findings into `{TASK_DIR}/research/`. `codex-inline` is the explicit mode that keeps work in the main session.
 
 [/codex-inline, Kilo, Antigravity, Devin]
 
@@ -380,7 +380,7 @@ Brainstorm and research can interleave freely — pause to research a technical
 
 #### 1.3 Configure context `[required · once]`
 
-[Claude Code, Cursor, OpenCode, codex-sub-agent, Kiro, Gemini, Qoder, CodeBuddy, Copilot, Droid, Pi, Oh My Pi, ZCode, Reasonix, Trae]
+[Claude Code, Cursor, OpenCode, codex-sub-agent, Kiro, Gemini, Qoder, CodeBuddy, Copilot, Droid, Pi, Oh My Pi, ZCode, Snow, Reasonix, Trae, Grok, Kimi Code]
 
 Curate `implement.jsonl` and `check.jsonl` so the Phase 2 sub-agents get the right spec/research context. These files were seeded on `task create` with a single self-describing `_example` line; your job here is to fill in real entries.
 
@@ -425,7 +425,7 @@ Ready gate: both `implement.jsonl` and `check.jsonl` must contain at least one r
 
 Skip this step only when both files already have real curated entries.
 
-[/Claude Code, Cursor, OpenCode, codex-sub-agent, Kiro, Gemini, Qoder, CodeBuddy, Copilot, Droid, Pi, Oh My Pi, ZCode, Reasonix, Trae]
+[/Claude Code, Cursor, OpenCode, codex-sub-agent, Kiro, Gemini, Qoder, CodeBuddy, Copilot, Droid, Pi, Oh My Pi, ZCode, Snow, Reasonix, Trae, Grok, Kimi Code]
 
 [codex-inline, Kilo, Antigravity, Devin]
 
@@ -458,11 +458,11 @@ If `task.py start` errors with a session-identity message (no context key from h
 | `design.md` exists (complex tasks) | ✅ |
 | `implement.md` exists (complex tasks) | ✅ |
 
-[Claude Code, Cursor, OpenCode, codex-sub-agent, Kiro, Gemini, Qoder, CodeBuddy, Copilot, Droid, Pi, Oh My Pi, ZCode, Reasonix, Trae]
+[Claude Code, Cursor, OpenCode, codex-sub-agent, Kiro, Gemini, Qoder, CodeBuddy, Copilot, Droid, Pi, Oh My Pi, ZCode, Snow, Reasonix, Trae, Grok, Kimi Code]
 
 | `implement.jsonl` and `check.jsonl` each contain at least one real curated entry (seed row does not count) | ✅ |
 
-[/Claude Code, Cursor, OpenCode, codex-sub-agent, Kiro, Gemini, Qoder, CodeBuddy, Copilot, Droid, Pi, Oh My Pi, ZCode, Reasonix, Trae]
+[/Claude Code, Cursor, OpenCode, codex-sub-agent, Kiro, Gemini, Qoder, CodeBuddy, Copilot, Droid, Pi, Oh My Pi, ZCode, Snow, Reasonix, Trae, Grok, Kimi Code]
 
 ---
 
@@ -472,21 +472,22 @@ Goal: turn reviewed planning artifacts into code that passes quality checks.
 
 #### 2.1 Implement `[required · repeatable]`
 
-[Claude Code, Cursor, OpenCode, CodeBuddy, Droid, Pi, Oh My Pi]
+[Claude Code, Cursor, OpenCode, codex-sub-agent, CodeBuddy, Droid, Pi, ZCode, Snow, Oh My Pi]
 
 Spawn the implement sub-agent:
 
 - **Agent type**: `trellis-implement`
 - **Task description**: Implement the reviewed task artifacts, consulting materials under `{TASK_DIR}/research/`; finish by running project lint and type-check
-- **Dispatch prompt guard**: Tell the spawned agent it is already the `trellis-implement` sub-agent and must implement directly, not spawn another `trellis-implement` / `trellis-check`.
+- **Dispatch prompt guard**: The prompt MUST start with `Active task: <task path>`, then tell the spawned agent it is already the `trellis-implement` sub-agent and must implement directly, not spawn another `trellis-implement` / `trellis-check`.
 
 The platform hook/plugin auto-handles:
 - Reads `implement.jsonl` and injects referenced spec/research files into the agent prompt
 - Injects `prd.md`, `design.md` if present, and `implement.md` if present
+- For Codex, `SubagentStart` supplies native context injection; the agent profile keeps child-side loading as the fallback
 
-[/Claude Code, Cursor, OpenCode, CodeBuddy, Droid, Pi, Oh My Pi]
+[/Claude Code, Cursor, OpenCode, codex-sub-agent, CodeBuddy, Droid, Pi, ZCode, Snow, Oh My Pi]
 
-[codex-sub-agent, Gemini, Qoder, Copilot, ZCode, Reasonix, Trae]
+[Gemini, Qoder, Copilot, Reasonix, Trae, Grok, Kimi Code]
 
 Spawn the implement sub-agent:
 
@@ -498,7 +499,7 @@ The pull-based sub-agent definition auto-handles the context load requirement:
 - Resolves the active task with `task.py current --source`, then reads `prd.md`, `design.md` if present, and `implement.md` if present
 - Reads `implement.jsonl` and requires the agent to load each referenced spec/research file before coding
 
-[/codex-sub-agent, Gemini, Qoder, Copilot, ZCode, Reasonix, Trae]
+[/Gemini, Qoder, Copilot, Reasonix, Trae, Grok, Kimi Code]
 
 [Kiro]
 
@@ -526,13 +527,13 @@ The platform prelude auto-handles the context load requirement:
 
 #### 2.2 Quality check `[required · repeatable]`
 
-[Claude Code, Cursor, OpenCode, codex-sub-agent, Kiro, Gemini, Qoder, CodeBuddy, Copilot, Droid, Pi, Oh My Pi, ZCode, Reasonix, Trae]
+[Claude Code, Cursor, OpenCode, codex-sub-agent, Kiro, Gemini, Qoder, CodeBuddy, Copilot, Droid, Pi, Oh My Pi, ZCode, Snow, Reasonix, Trae, Grok, Kimi Code]
 
 Spawn the check sub-agent:
 
 - **Agent type**: `trellis-check`
 - **Task description**: Review all code changes against specs and task artifacts; fix any findings directly; ensure lint and type-check pass
-- **Dispatch prompt guard**: Tell the spawned agent it is already the `trellis-check` sub-agent and must review/fix directly, not spawn another `trellis-check` / `trellis-implement`.
+- **Dispatch prompt guard**: The prompt MUST start with `Active task: <task path>`, then tell the spawned agent it is already the `trellis-check` sub-agent and must review/fix directly, not spawn another `trellis-check` / `trellis-implement`.
 
 The check agent's job:
 - Review code changes against specs
@@ -540,7 +541,7 @@ The check agent's job:
 - Auto-fix issues it finds
 - Run lint and typecheck to verify
 
-[/Claude Code, Cursor, OpenCode, codex-sub-agent, Kiro, Gemini, Qoder, CodeBuddy, Copilot, Droid, Pi, Oh My Pi, ZCode, Reasonix, Trae]
+[/Claude Code, Cursor, OpenCode, codex-sub-agent, Kiro, Gemini, Qoder, CodeBuddy, Copilot, Droid, Pi, Oh My Pi, ZCode, Snow, Reasonix, Trae, Grok, Kimi Code]
 
 [codex-inline, Kilo, Antigravity, Devin]