oh-my-customcodex 0.5.16 → 0.5.18

package/README.md

@@ -229,9 +229,9 @@ Key rules: R010 (orchestrator never writes files), R009 (parallel execution mand
 
 ---
 
-### Guides (51)
+### Guides (52)
 
-Reference documentation covering best practices, architecture decisions, and integration patterns. Located in `guides/` at project root, covering topics from agent design to CI/CD to observability.
+Reference documentation covering best practices, architecture decisions, release compatibility, and integration patterns. Located in `guides/` at project root, covering topics from agent design to CI/CD to observability.
 
 ---
 
@@ -289,7 +289,7 @@ your-project/
 │   └── ontology/               # Knowledge graph for RAG
 ├── .agents/
 │   └── skills/                 # 121 installed skill modules
-└── guides/                     # 51 reference documents
+└── guides/                     # 52 reference documents
 ```
 
 ### Source Repository And Compatibility Surfaces

package/dist/cli/index.js

@@ -3091,7 +3091,7 @@ var init_package = __esm(() => {
     workspaces: [
       "packages/*"
     ],
-    version: "0.5.16",
+    version: "0.5.18",
     requiresCC: ">=2.1.121",
     claudeCode: {
       minimumVersion: "2.1.121",

package/dist/index.js

@@ -2316,7 +2316,7 @@ var package_default = {
   workspaces: [
     "packages/*"
   ],
-  version: "0.5.16",
+  version: "0.5.18",
   requiresCC: ">=2.1.121",
   claudeCode: {
     minimumVersion: "2.1.121",

package/package.json

@@ -3,7 +3,7 @@
   "workspaces": [
     "packages/*"
   ],
-  "version": "0.5.16",
+  "version": "0.5.18",
   "requiresCC": ">=2.1.121",
   "claudeCode": {
     "minimumVersion": "2.1.121",

package/templates/.claude/rules/MUST-completion-verification.md

@@ -162,6 +162,10 @@ When a user sends a new instruction while work is in progress, completion status
 3. If the new message adds a requirement, add it to the completion contract before closing.
 4. If no conflict exists, continue but explicitly preserve the new requirement in the next verification pass.
 
+### Tool-Call Payload Completeness
+
+도구 호출의 required 파라미터는 invoke 전에 확인한다(완료 선언 후가 아니라 호출 시점의 전제조건). announce(prefix)만 출력하고 payload의 required 필드를 누락하는 패턴은 R008 "Required-Parameter Completeness Check"가 canonical owner다. Reference: #1487 / upstream #1324.
+
 ## Completion Contract Format — [Contract] + [Done] with criterion/evidence pairs. See template via Read tool.
 
 <!-- DETAIL: Completion Contract Format

package/templates/.claude/rules/MUST-parallel-execution.md

@@ -34,6 +34,19 @@ Before writing/editing multiple files:
 5. Running agent stalled (2x+ duration)? → Spawn independent follow-up tasks immediately
 6. Parallel dispatch announced? → put all announced tool calls in the same message
 
+### LLM Batch Output Token Budget
+
+For N-item structured LLM batches, pre-compute output tokens and chunk variable-size lists (default ≤40 items); raising `max_tokens` alone is not enough. Reference: #1486 / upstream #1321 and #1320.
+
+<!-- DETAIL: LLM Batch Output Token Budget
+The giant-prompt heuristic governs input tokens. The symmetric output-side rule: when a single LLM call processes N items (scoring/classifying/extracting) and must emit structured output (for example JSON) per item, pre-compute the output budget = N × per-item output tokens before the call. Exceeding `max_tokens` truncates the response mid-structure, so the call can appear to succeed while JSON parsing fails.
+
+| Anti-pattern | Required |
+|--------------|----------|
+| Single batch call over a variable-size list with a fixed small `max_tokens` | Chunk into bounded batches (default ≤40 items), constrain per-item output length, and set `max_tokens` to fit one chunk |
+| Raising `max_tokens` alone | Insufficient — it only defers the failure as the list grows. Chunking is the invariant fix. |
+-->
+
 ### Common Violations to Avoid
 
 <!-- DETAIL: Common Violations Short Examples

package/templates/.claude/rules/MUST-tool-identification.md

@@ -50,6 +50,18 @@ Incorrect parallel: tool_call(url1), tool_call(url2), tool_call(cmd) — no iden
 Correct parallel: list ALL [agent][model] → Tool/Fetching/Running lines FIRST, then all tool_calls
 -->
 
+
+### Required-Parameter Completeness Check
+
+R008 prefix(announce)와 실제 도구 호출은 분리된 단계다. prefix를 출력한 뒤 호출 payload에서 도구 스키마상 required 파라미터를 누락하면 호출이 실패하거나 빈 동작이 된다. 호출 직전, prefix 존재뿐 아니라 required 파라미터가 모두 채워졌는지 확인한다.
+
+| Anti-pattern | Required |
+|--------------|----------|
+| `[agent][model] → Tool: AskUserQuestion` prefix만 출력하고 `questions` 파라미터 없이/빈 배열로 호출 | prefix + `questions` 배열(최소 1개) 모두 채워 호출 |
+| announce 후 payload의 required 필드 누락 (announce-payload separation gap) | announce와 동일 메시지에서 required 필드 완비 호출 |
+
+Cross-reference: R020 (action-completeness precondition — invoke 전에 required 파라미터 확인). Reference issue: #1487 / upstream #1324 (AskUserQuestion `questions` 누락 재발 방지).
+
 ## Models
 
 | Model | Use |
@@ -100,6 +112,31 @@ matches the spawn announcement:
   [2] lang-python-expert:sonnet → Python code review
 ```
 
+## Tier-3 Interaction Tool Prefix (MANDATORY)
+
+R008 "every tool call" applies to Tier-3 interaction tools too — not only file/exec tools. Applying the `[agent][model] → Tool:` prefix to Bash/Read/Agent while omitting it on `AskUserQuestion`, `TodoWrite`, `EnterPlanMode`, `ExitPlanMode`, `request_user_input`, or equivalent structured-question tools is a violation.
+
+| Tool | R008 prefix required? |
+|------|----------------------|
+| AskUserQuestion / `request_user_input` / structured question | YES — `[agent][model] → Tool: AskUserQuestion` or equivalent before the call |
+| TodoWrite / `update_plan` | YES |
+| EnterPlanMode / ExitPlanMode | YES |
+| Skill | NO separate R008 prefix — identified via the R007 integrated header instead |
+
+Skill invocation is the one exception: it is identified through the R007 integrated identification block (`┌─ Agent: {agent} → {skill-name}`), not a standalone R008 tool prefix.
+
+Reference issue: #1486 / upstream #1321 (AskUserQuestion prefix omission); complements #1487 required-payload completeness.
+
+## Multi-Turn Self-Check
+
+도구 호출 전 매번 확인한다:
+
+1. 이 호출 위에 `[agent-name][model] → Tool: <tool-name>` 라인이 있는가?
+2. agent-name과 model이 현재 컨텍스트와 일치하는가?
+3. 이 호출에 도구 스키마상 required 파라미터가 모두 채워져 있는가? 예: AskUserQuestion/request_user_input 계열은 `questions` 배열이 비어 있지 않아야 한다. prefix(announce)만 출력하고 실제 호출 payload의 required 필드를 누락하면 안 된다.
+
+체크 실패 시 즉시 prefix/필수 파라미터를 보완한 후 호출.
+
 ## Example
 
 ```

package/templates/AGENTS.md.en

@@ -134,7 +134,7 @@ project/
 |   +-- contexts/                # Context files (ecomode)
 +-- .agents/
 |   +-- skills/                  # Installed skills (120 directories)
-+-- guides/                      # Reference docs (51 topics)
++-- guides/                      # Reference docs (52 topics)
 ```
 
 ## OMX Command Routing

package/templates/AGENTS.md.ko

@@ -134,7 +134,7 @@ project/
 |   +-- contexts/                # 컨텍스트 파일 (ecomode)
 +-- .agents/
 |   +-- skills/                  # 설치된 스킬 (120 디렉토리)
-+-- guides/                      # 레퍼런스 문서 (51 토픽)
++-- guides/                      # 레퍼런스 문서 (52 토픽)
 ```
 
 ## OMX 명령 라우팅

package/templates/CLAUDE.md

@@ -120,7 +120,7 @@ project/
 |   +-- contexts/                # 컨텍스트 파일 (ecomode)
 +-- .agents/
 |   +-- skills/                  # 스킬 (120 디렉토리)
-+-- guides/                      # 레퍼런스 문서 (51 토픽)
++-- guides/                      # 레퍼런스 문서 (52 토픽)
 ```
 
 ## 오케스트레이션

package/templates/CLAUDE.md.en

@@ -136,7 +136,7 @@ project/
 |   +-- rules/                   # Global rules (22 files)
 |   +-- hooks/                   # Hook scripts (security, validation, HUD)
 |   +-- contexts/                # Context files (4 files)
-+-- guides/                      # Reference docs (51 topics)
++-- guides/                      # Reference docs (52 topics)
 ```
 
 ## Orchestration

package/templates/CLAUDE.md.ko

@@ -136,7 +136,7 @@ project/
 |   +-- rules/                   # 전역 규칙 (22 파일)
 |   +-- hooks/                   # 훅 스크립트 (보안, 검증, HUD)
 |   +-- contexts/                # 컨텍스트 파일 (4 파일)
-+-- guides/                      # 레퍼런스 문서 (51 토픽)
++-- guides/                      # 레퍼런스 문서 (52 토픽)
 ```
 
 ## 오케스트레이션

package/templates/README.md

@@ -52,7 +52,7 @@ templates/
 |   +-- contexts/                     # context files
 |   +-- ontology/                     # ontology and routing metadata
 |   +-- schemas/                      # tool input schemas
-+-- guides/                           # reference docs (51 topics)
++-- guides/                           # reference docs (52 topics)
 ```
 
 ## Components
@@ -77,7 +77,7 @@ Reusable workflow and reference skill modules. During Codex installation these l
 
 Global agent behavior rules. During Codex installation these land under `.codex/rules/`.
 
-### Guides (51)
+### Guides (52)
 
 `templates/guides/*/`
 

package/templates/guides/index.yaml

@@ -20,6 +20,12 @@ guides:
     source:
       type: internal
 
+  - name: openai-codex
+    description: OpenAI Codex release compatibility decisions for Codex/OMX sessions
+    path: ./openai-codex/
+    source:
+      type: internal
+
   # Frontend
   - name: claude-design
     description: Claude Design artifact handoff workflow — connecting Anthropic's conversational design tool outputs to Claude Code's fe-design-expert implementation pipeline

package/templates/guides/openai-codex/01-version-compatibility.md

@@ -0,0 +1,21 @@
+# OpenAI Codex Version Compatibility
+
+This guide records OpenAI Codex release-note impact decisions for oh-my-customcodex. Use it for Codex/OMX runtime compatibility notes; keep Claude-only release notes in `guides/claude-code/15-version-compatibility.md`.
+
+## rust-v0.138.0 / CLI 0.138.0
+
+Source: upstream OpenAI Codex release `rust-v0.138.0`, Codex-port issue #1481.
+
+| Change | Impact on oh-my-customcodex | Action |
+| --- | --- | --- |
+| `/app` can hand off the current CLI thread into Codex Desktop on macOS and native Windows | Useful operator workflow, but not a packaged template contract. | No runtime change. Mention only when documenting Desktop handoff troubleshooting. |
+| Local image attachments and generated images expose saved file paths to the model | Helps visual iteration and image-edit follow-up references. | Keep visual workflows file-path aware; do not store generated image paths as durable release evidence unless explicitly requested. |
+| Reasoning effort shortcuts and model-advertised effort ordering improved | Aligns with OMX guidance to prefer `reasoning_effort` over hardcoded model overrides for child agents. | Preserve repo model-routing guidance; avoid stale frontier model names. |
+| App-server integrations can read account token usage and auth supports v2 personal access tokens | Useful observability/auth signal for app-server deployments, not required by this package. | Track as external runtime capability; no dependency or config change. |
+| Plugin commands gained richer `--json` output and marketplace/source metadata | Can improve future automation around plugin inventory. | Prefer JSON output when automating plugin add/remove/list/detail; keep `omcustomcodex list` as package inventory source. |
+| Workspace instruction loading is more accurate for remote and symlinked workspaces | Reduces false AGENTS.md discovery issues in Codex itself. | Keep nested AGENTS.md guidance intact and continue verifying repo-local instructions directly. |
+| Startup, MCP credential refresh, large stream processing, and TUI/goal fixes are additive stability improvements | Lower operational friction for Codex sessions. | No package change beyond this compatibility record. |
+
+## Compatibility rule
+
+OpenAI Codex release-monitor issues should be closed as no-op only when there is no repo-owned surface to update. If a release changes workflow vocabulary, diagnostics, plugin automation, AGENTS.md loading, or visual iteration evidence, record the decision here and mirror it into templates.

package/templates/guides/openai-codex/index.yaml

@@ -0,0 +1,7 @@
+# OpenAI Codex Guide Index
+
+documents:
+  - name: version-compatibility
+    title: Version compatibility
+    description: OpenAI Codex release-note impact decisions for oh-my-customcodex
+    path: ./01-version-compatibility.md

package/templates/manifest.json

@@ -1,5 +1,5 @@
 {
-  "version": "0.5.16",
+  "version": "0.5.18",
   "requiresCC": ">=2.1.121",
   "claudeCode": {
     "minimumVersion": "2.1.121",
@@ -29,7 +29,7 @@
       "name": "guides",
       "path": "guides",
       "description": "Reference documentation",
-      "files": 51
+      "files": 52
     },
     {
       "name": "hooks",

package/templates/workflows/auto-dev.yaml

@@ -151,9 +151,11 @@ steps:
       Required version preflight for npm package releases:
       - Determine NEW_VERSION before creating a release branch, PR, or tag.
       - Update `package.json` and `templates/manifest.json` to NEW_VERSION in the same commit.
+      - Promote `CHANGELOG.md` before the release PR/tag: move non-empty `## [Unreleased]` entries into `## [NEW_VERSION] - YYYY-MM-DD`, then re-create an empty `## [Unreleased]` section above it.
+      - If `CHANGELOG.md` has no user/package-visible entry for NEW_VERSION, add a concise release summary before continuing instead of relying on GitHub auto-generated release notes.
       - Use same-directory temporary files for generated JSON writes; do not write through `/tmp`.
       - Run `bash .github/scripts/verify-version-sync.sh` after the bump and before tag or PR creation.
-      - Commit the bump with `chore(release): bump to v{NEW_VERSION}` before any release tag is created.
+      - Commit the bump and changelog promotion with `chore(release): bump to v{NEW_VERSION}` before any release tag is created.
 
       Before creating `release/v*`, check whether a local branch named exactly
       `release` exists. Git stores refs as files/directories, so