@mstar-harness/opencode 1.8.5 → 1.8.7

package/CHANGELOG.md

@@ -6,6 +6,23 @@ The monorepo root [CHANGELOG.md](../../CHANGELOG.md) summarizes cross-surface re
 
 ## [Unreleased]
 
+## [1.8.7] - 2026-08-06
+
+### Bundled harness skills (`harness-skills/` at publish)
+
+- Version alignment with harness **1.8.7** (no OpenCode package API change).
+
+See root [CHANGELOG.md](../../CHANGELOG.md) **1.8.7**.
+
+## [1.8.6] - 2026-08-06
+
+### Bundled harness skills (`harness-skills/` at publish)
+
+- Sync dispatch field-completeness gate: `mstar-dispatch-gates` self-check + anti-pattern, `mstar-host/references/parallel-dispatch.md` hard rule + self-check, `mstar-host/references/omp.md` Review-&-Edit example + N=1 gotcha.
+- Version alignment with harness **1.8.6** (no OpenCode package API change).
+
+See root [CHANGELOG.md](../../CHANGELOG.md) **1.8.6**.
+
 ## [1.8.5] - 2026-08-06
 
 ### Bundled harness skills (`harness-skills/` at publish)

package/harness-skills/mstar-dispatch-gates/SKILL.md

@@ -1,6 +1,6 @@
 ---
 name: mstar-dispatch-gates
-description: Morning Star 派发与委派门禁 —— 仅 PM 可增派 subagent、`Execute as` 与 `Delegation`、承接方反递归 NEVER 红线、SDD implement 串行派发、**SDD 路径 plan QC 强制 tri-review（N=3）**、inline 单席 QC 例外、Assignment 文案≠派发、未齐不发。`project-manager` 派发时必读；leaf 动手前必读反递归。worktree 见 `mstar-branch-worktree`；SDD 见 `mstar-sdd`；宿主见 `mstar-host`。
+description: Morning Star 派发与委派门禁 —— 仅 PM 可增派 subagent、`Execute as` 与 `Delegation`、承接方反递归 NEVER 红线、SDD implement 串行派发、**SDD 路径 plan QC 强制 tri-review（N=3）**、inline 单席 QC 例外、Assignment 文案≠派发、未齐不发、**invoke 角色字段必填（漏写=静默 generic 回退=派发未完成）**。`project-manager` 派发时必读；leaf 动手前必读反递归。worktree 见 `mstar-branch-worktree`；SDD 见 `mstar-sdd`；宿主见 `mstar-host`。
 ---
 
 ## Load order（必读顺序）
@@ -58,6 +58,7 @@ description: Morning Star 派发与委派门禁 —— 仅 PM 可增派 subagent
 - **QC 单席（例外）**：`Execution mode: inline`（hotfix 等），或 Assignment 显式 `QC mode: single` / `QC mode: single — override: <reason>` → `qc-specialist` ×1，`N=1`，写 `{SDD_DIR}/review/qc.md`。
 - **QC targeted re-review**：Assignment 含 **`QC re-review: targeted — reviewers: …`** 时，**N** = 所列席位数（1–3），同条消息发满 **N**。
 - **先自检再发送**：发送前核对「Assignment 条数 = 本条消息中的实际 **派发** 调用条数」。
+- **先自检字段再发送（与 count 同级门禁）**：核对**每条** invoke 都携带与 **`Execute as`** 匹配的角色绑定字段——omp **`agent`** / Cursor **`subagent_type`** / OpenCode **`subagent`** / Kimi·ZCode **`subagent_type`**。**漏写或取默认通用值**（omp 漏 `agent` ⇒ 自动回退 generic `task`，无报错）= **派发未完成**，与 paste-only（零 invoke）**同等级**：当场补齐重发，不得进入下一 gate。**N=1 顺序链（Review & Edit）不豁免**——count 门在 N=1 恒过，**字段门是唯一保护**。
 - **前置步骤与派发回合分离（防串行 rollout）**：为派发准备的 **`bash` / `read` / `glob` / `grep`**（如 `merge-base`、`Review range`、`git rev-parse`）**不计入** `N` 次派发；可在上一条仅含准备的消息完成。准备完成后，**下一条派发消息**须**一次性**含 **`N` 次** Task / subagent invoke。**禁止**先发 `1` 次、等返回再补发其余 `N-1` 次。
 - **未齐不发（emit zero until batch-ready）**：需并发 `N≥2` 而当前只能发 `1` 条时，本条应发 **`0` 条派发 invoke`**（可继续 read/bash 补齐），**禁止**「先发一个顶一下」；`N` 份 payload 就绪后**单次消息发满 `N`**。见 **`mstar-host`** → `references/parallel-dispatch.md`（具备 invoke / Task / subagent 工具的宿主共用）。
 
@@ -114,6 +115,7 @@ When **`Execution mode: sdd`** (`mstar-sdd`):
 - Review-and-edit 链未完成即 commit integration 分支；PM 代做专业角色编辑而不 invoke。
 - Phase 1 review-and-edit 链三角色并行派发，或未等上一角色返回即派发下一角色。
 - Assignment 已写、invoke 为零（paste-only）却进入下一 gate。
+- Task/subagent item 漏写角色绑定字段（omp 漏 `agent` / Cursor 漏 `subagent_type` / OpenCode 漏 `subagent`）⇒ **静默回退 generic worker**，却因 count=N 通过而误判「派发完成」；属 paste-only 同级的 **dispatch-incomplete**。N=1 顺序 Review-&-Edit 链最易在此漏字段。
 
 ## References
 

package/harness-skills/mstar-host/references/omp.md

@@ -77,6 +77,8 @@ task(
 
 Single-task shorthand may exist depending on host version — always match the live schema. Parallel **N** Morning Star assignees ⇒ **one** `task` call with **N** `tasks[]` entries **or** **N** `task` calls in one assistant message when the host requires that shape. Count emitted dispatches = **N**.
 
+**Envelope-first**: write `agent` + `name` as the first fields of each `tasks[]` entry, before the long `task` body — the body crowds them out and `agent` gets silently dropped (omp defaults to generic `task`, no error). SSOT → `parallel-dispatch.md` § Mandatory order.
+
 ## Role agents (C5 — hard constraint)
 
 **Live `task` tool schema is SSOT every session.** Exact `agent` names vary by omp version and which `agents/*.md` were discovered after plugin install/link. Read the tool's Available Agents list before dispatch — do not invent names; do not hard-code stale tables over the live list.
@@ -145,18 +147,16 @@ task(
 )
 ```
 
-Review & Edit / Prepare specialist chain (sequential, **N=1** each turn):
+Review & Edit / Prepare specialist chain (sequential, **N=1** each turn — re-set **`agent`** on **every** dispatch; at N=1 the count gate is trivial, so the **field** gate is the only protection):
 
 ```text
+# pass 1 — product-manager
 task(
   context: "Review & Edit — product scope",
-  tasks: [{
-    name: "ReviewEditProduct",
-    agent: "product-manager",
-    task: "<Assignment: Execute as product-manager; Act as + skill load>"
-  }]
+  tasks: [{ name: "ReviewEditProduct", agent: "product-manager",
+            task: "<Assignment: Execute as product-manager; Act as + skill load>" }]
 )
-# wait for return, then architect, then writing-specialist — each with agent: "<role-id>"
+# repeat for architect, writing-specialist, … — each a separate N=1 dispatch with agent re-set
 ```
 
 For explore-only orientation (no Morning Star role deliverable):
@@ -190,7 +190,7 @@ Cannot emit required **N** → **`Blocked`**.
 
 ### SDD implement (serial)
 
-- **`Execution mode: sdd`**: one implementer `task` entry per task id with `agent` matching the implementer role when listed; task reviewer = new entry (no sticky resume unless host resume/id is available and recorded). Serial rule → **`parallel-dispatch.md`** § SDD implement.
+- **`Execution mode: sdd`**: one implementer `task` entry per task id with `agent` matching the implementer role when listed; task reviewer = new entry with `agent: "reviewer"` (omp L2 review; not qc-specialist*) or `agent: "task"` as last resort + C5b — no sticky resume unless host resume/id is available and recorded. Serial rule → **`parallel-dispatch.md`** § SDD implement.
 - **Never** multiple implementer entries in one message for the same plan.
 
 ## Clarify
@@ -230,3 +230,4 @@ Cannot emit required **N** → **`Blocked`**.
 - omp has no `sessionStart.skill`; new sessions do **not** auto-load PM — invoke `/skill:pm` manually.
 - Do not confuse omp **`task.agent`** with OpenCode **`subagent`** or Cursor **`subagent_type`**.
 - Do not treat Kimi/ZCode “built-ins only → always `coder`/`task`” habits as omp defaults when Morning Star role agents are listed.
+- **Sequential N=1 Review-&-Edit turns are where `agent` gets dropped**: the “all N in one message” pressure is absent and the count gate passes trivially — re-verify **`agent: "<Execute as>"`** on every single dispatch; `tasks:[{task:"…"}]` with no `agent` is a silent generic fallback, not a valid role invoke.

package/harness-skills/mstar-host/references/parallel-dispatch.md

@@ -15,7 +15,7 @@ Printing `## Assignment` in the main thread **without** matching host invocation
 
 ## Mandatory order (dispatch turn)
 
-1. Finalize all `N` Assignment payloads (after any prerequisite turn).
+1. Finalize all `N` Assignment payloads (after any prerequisite turn). **Build each invoke entry envelope-first**: set the role-binding field (omp `agent` / Cursor `subagent_type` / OpenCode `subagent` / Kimi·ZCode `subagent_type`) + `name` *before* writing the long Assignment body.
 2. Count distinct `Execute as` sessions (`N`).
 3. Issue **`N` host invocations first** — OpenCode: **N `task` tool** calls with **subagent**; Cursor: **N `Task`** with `subagent_type` (JSON field shape → `cursor.md` § Task invoke schema); Kimi: **N `Agent`** calls (each prompt carries **Act as** + skill load; `subagent_type` ∈ {`coder`,`explore`,`plan`} only — see `kimi.md` C5/C5b); omp: **one `task` call with N `tasks[]`** (or N `task` calls) with `agent` = live-schema role id matching `Execute as` when listed (else generic built-in) + **Act as** / skill load (see `omp.md` C5/C5b); each with one Assignment body. For parallel work, **all `N` tool calls in one assistant message** when the host allows.
 4. Optionally post a short **Status Update** after invocations (audit trail only — does not replace step 3).
@@ -26,6 +26,7 @@ Printing `## Assignment` in the main thread **without** matching host invocation
 - Do not end the dispatch turn until **`N` invocations emitted**, or mark `Blocked` / `dispatch incomplete`.
 - Dual-track implement: **`N = 2` ⇒ two invocations in one message** when parallel is required.
 - Status Update on dispatch turns: **`Subagent invokes issued: N`** (must match Assignment count). If Assignments were written but `N = 0` → **`dispatch failed — paste-only`**; fix next message.
+- **Per-item field completeness (same severity as paste-only)**: every invocation must carry the role-binding field set to **`Execute as`** — omp **`agent`** / Cursor **`subagent_type`** / OpenCode **`subagent`** / Kimi·ZCode **`subagent_type`**. A missing field (e.g. omp omitting `agent` ⇒ silent generic `task` fallback) = **dispatch incomplete** even though count = N passes. Sequential **N=1** Review-&-Edit turns are not exempt — re-set the field on **every** dispatch.
 
 ## QC default (initial wave)
 
@@ -62,5 +63,6 @@ Formal iteration Phase 2 uses the same SDD + tri rule — not a separate carve-o
 1. Required assignments this turn? (`N`)
 2. Prerequisite-only message? → **zero** batch dispatches unless `N = 1`.
 3. Dispatch message contains **exactly `N`** invocation calls?
-4. QC initial: **`Execution mode: sdd`** → **N=3**? **`inline`** → **N=1**? Targeted re-review → **N** = Assignment reviewer count?
-5. SDD implement → **serial** (never batch implementers); sticky = **resume** same implementer, not parallel
+4. **Each** invocation carries its role-binding field set to **`Execute as`** (omp `agent` / Cursor `subagent_type` / OpenCode `subagent` / Kimi·ZCode `subagent_type`)? A bare `task`/prompt item with no role field = **incomplete**, even at **N=1**.
+5. QC initial: **`Execution mode: sdd`** → **N=3**? **`inline`** → **N=1**? Targeted re-review → **N** = Assignment reviewer count?
+6. SDD implement → **serial** (never batch implementers); sticky = **resume** same implementer, not parallel

package/harness-skills/mstar-sdd/SKILL.md

@@ -45,7 +45,7 @@ Batch all findings for the human in one message. If clean, proceed silently.
    - **`SDD implementer session: fresh`** (default) — new subagent; templates: `references/implementer-prompt.md`
    - **`SDD implementer session: sticky`** — first task: same as fresh + write `{SDD_DIR}/implementer-session.json` with `host_agent_id`; later tasks: host **resume** + `references/implementer-continuation-prompt.md` (see **`references/sticky-implementer-session.md`**)
 5. On `DONE`: `scripts/review-package BASE HEAD` → diff file
-6. Dispatch **fresh** task reviewer — **`subagent_type: generalPurpose`** (L2; **not** `qc-specialist*`) — brief, report, diff, Global Constraints — `references/task-reviewer-prompt.md` — **never** sticky resume for reviewers
+6. Dispatch **fresh** task reviewer — role **`generalPurpose`** (L2; **not** `qc-specialist*`; host role field → `mstar-host` C5) — brief, report, diff, Global Constraints — `references/task-reviewer-prompt.md` — **never** sticky resume for reviewers
 7. Fix loop for Critical/Important; re-review until approved
 8. Append `progress.md`; update `status.json` `task_commits[]` and `implementer-session.json` `last_task` if sticky
 9. Next task

package/harness-skills/mstar-sdd/references/implementer-continuation-prompt.md

@@ -3,11 +3,11 @@
 Use when PM continues **`SDD implementer session: sticky`** for Task N>1. Host: **resume** same agent when supported (`sticky-implementer-session.md`).
 
 ```
-Task / subagent:
-  resume: [HOST_AGENT_ID from implementer-session.json]
-  description: "SDD continue Task N: <name>"
-  model: [same tier as session start unless PM upgrades]
-  prompt: |
+Dispatch:
+  Resume: [HOST_AGENT_ID from implementer-session.json]
+  Name: <CamelCaseId>                 # omp/Cursor name
+  Model: [same tier as session start unless PM upgrades]
+  Prompt body:
     <SUBAGENT-STOP> Skip PM orchestration skills. You are a leaf implementer continuing a sticky SDD session.</SUBAGENT-STOP>
 
     Continue as the same implementer on plan <plan-id>, Working branch: <branch>.

package/harness-skills/mstar-sdd/references/implementer-prompt.md

@@ -5,10 +5,11 @@ Use when PM dispatches an SDD implementer (`mstar-sdd`) — **first task** or **
 For **sticky** continuation (task 2+), use **`implementer-continuation-prompt.md`** instead.
 
 ```
-Task / subagent:
-  description: "SDD implement Task N: <name>"
-  model: [REQUIRED — per Model tier in Assignment and mstar-sdd SKILL]
-  prompt: |
+Dispatch:
+  Role: <Execute as role-id>          # omp agent / Cursor subagent_type / OpenCode subagent → mstar-host C5
+  Name: <CamelCaseId>                 # omp/Cursor name
+  Model: [REQUIRED — per Model tier in Assignment and mstar-sdd SKILL]
+  Prompt body:
     <SUBAGENT-STOP> Skip PM orchestration skills. You are a leaf implementer.</SUBAGENT-STOP>
 
     You are implementing Task N: <name>

package/harness-skills/mstar-sdd/references/task-reviewer-prompt.md

@@ -3,11 +3,12 @@
 One reviewer per task: spec compliance + code quality (`mstar-sdd`).
 
 ```
-Task / subagent:
-  subagent_type: generalPurpose
-  description: "SDD review Task N (spec + quality)"
-  model: [REQUIRED — standard tier default; capable if diff is large/subtle]
-  prompt: |
+Dispatch:
+  Role: generalPurpose                # L2 SDD task reviewer; NOT qc-specialist*
+                                      # omp: agent = "reviewer" or "task" + C5b; Cursor: subagent_type = "generalPurpose" → mstar-host C5
+  Name: <CamelCaseId>                 # omp/Cursor name
+  Model: [REQUIRED — standard tier default; capable if diff is large/subtle]
+  Prompt body:
     <SUBAGENT-STOP> Skip PM orchestration. Read-only review.</SUBAGENT-STOP>
 
     Review one task implementation: spec compliance first, then quality.

package/package.json

@@ -1,6 +1,6 @@
 {
   "name": "@mstar-harness/opencode",
-  "version": "1.8.5",
+  "version": "1.8.7",
   "description": "Morning Star harness OpenCode plugin (skills bootstrap and agent loading).",
   "license": "MIT",
   "repository": {