okstra 0.92.0 → 0.92.1

package/package.json

@@ -1,6 +1,6 @@
 {
   "name": "okstra",
-  "version": "0.92.0",
+  "version": "0.92.1",
   "description": "Multi-agent cross-verification orchestrator runtime + Claude Code skills.",
   "license": "MIT",
   "author": "devonshin",

package/runtime/BUILD.json

@@ -1,5 +1,5 @@
 {
-  "package": "0.92.0",
-  "builtAt": "2026-06-18T07:29:46.716Z",
+  "package": "0.92.1",
+  "builtAt": "2026-06-18T08:35:38.504Z",
   "repoRoot": "/home/runner/work/okstra/okstra"
 }

package/runtime/prompts/wizard/prompts.ko.json

@@ -358,7 +358,7 @@
       }
     },
     "defaults_or_custom": {
-      "label": "역할별 모델·실행 옵션 단계입니다 (참여 워커 구성을 바꾸는 게 아닙니다).\n이번 run 의 워커: {workers}\n· 기본값으로 진행 — 모든 역할을 추천 모델로 둡니다. 추천 기본값: lead·report-writer=opus, claude=opus, codex=gpt-5.5, antigravity=auto (실제 값은 runtime 기본값으로 해소). directive·관련 task 없이 바로 진행.\n· 커스터마이즈 — 역할별 모델을 직접 고르고, 추가 directive·관련 task 도 지정합니다.",
+      "label": "역할별 모델 선택 단계입니다 (참여 워커 구성을 바꾸는 게 아닙니다).\n이번 run 에서 모델을 고를 역할:\n{role_models}\n· 기본값으로 진행 — 위 추천 모델을 그대로 쓰고, directive·관련 task 없이 바로 넘어갑니다.\n· 커스터마이즈 — 위 역할별 모델을 직접 고르고, 추가 directive·관련 task 도 지정합니다.\n(추천 값은 runtime 기본값으로 해소됩니다. 분석에 참여하지 않는 역할은 위 목록에 나오지 않습니다 — 예: antigravity 는 implementation 의 executor 로 선택했을 때만 표시됩니다.)",
       "echo_template": "customize: {value}",
       "options": {
         "defaults": "기본값으로 진행 (역할별 추천 모델 그대로)",

package/runtime/python/okstra_ctl/run.py

@@ -1315,33 +1315,42 @@ class _ModelBindings:
     executor_model_meta: ModelAssignment
 
 
+def recommended_role_models() -> dict[str, str]:
+    """역할 → 추천 모델 display 값 (env override 반영). prepare 의 모델 해소와
+    wizard 의 안내 표기가 공유하는 단일 기준점."""
+    lead_default = _default("OKSTRA_DEFAULT_LEAD_MODEL", "opus")
+    return {
+        "lead": lead_default,
+        "claude": _default("OKSTRA_DEFAULT_CLAUDE_MODEL", "opus"),
+        "codex": _default("OKSTRA_DEFAULT_CODEX_MODEL", "gpt-5.5"),
+        "antigravity": _default("OKSTRA_DEFAULT_ANTIGRAVITY_MODEL", "auto"),
+        "report-writer": _default("OKSTRA_DEFAULT_REPORT_WRITER_MODEL", lead_default),
+    }
+
+
 def _resolve_worker_models(inp: PrepareInputs) -> dict:
     """lead/claude/codex/antigravity/report-writer 모델을 alias → (display, execution) 로 해소."""
-    lead_default = _default("OKSTRA_DEFAULT_LEAD_MODEL", "opus")
-    claude_default = _default("OKSTRA_DEFAULT_CLAUDE_MODEL", "opus")
-    codex_default = _default("OKSTRA_DEFAULT_CODEX_MODEL", "gpt-5.5")
-    antigravity_default = _default("OKSTRA_DEFAULT_ANTIGRAVITY_MODEL", "auto")
-    report_writer_default = _default("OKSTRA_DEFAULT_REPORT_WRITER_MODEL", lead_default)
+    rec = recommended_role_models()
     return {
         "lead": resolve_model_metadata(
             provider="claude", raw_value=inp.lead_model,
-            default_display=lead_default, default_execution=lead_default,
+            default_display=rec["lead"], default_execution=rec["lead"],
         ),
         "cw": resolve_model_metadata(
             provider="claude", raw_value=inp.claude_model,
-            default_display=claude_default, default_execution=claude_default,
+            default_display=rec["claude"], default_execution=rec["claude"],
         ),
         "co": resolve_model_metadata(
             provider="codex", raw_value=inp.codex_model,
-            default_display=codex_default, default_execution=codex_default,
+            default_display=rec["codex"], default_execution=rec["codex"],
         ),
         "ge": resolve_model_metadata(
             provider="antigravity", raw_value=inp.antigravity_model,
-            default_display=antigravity_default, default_execution=antigravity_default,
+            default_display=rec["antigravity"], default_execution=rec["antigravity"],
         ),
         "rw": resolve_model_metadata(
             provider="claude", raw_value=inp.report_writer_model,
-            default_display=report_writer_default, default_execution=report_writer_default,
+            default_display=rec["report-writer"], default_execution=rec["report-writer"],
         ),
     }
 

package/runtime/python/okstra_ctl/wizard.py

@@ -44,6 +44,7 @@ from okstra_ctl.run import (
     _reject_blocking_plan_body_gate,
     _set_data_json_approved_true_if_present,
     _validate_data_json_approval_consistency,
+    recommended_role_models,
 )
 from okstra_ctl.user_response import (
     UserResponseApprovalRecord,
@@ -93,6 +94,15 @@ TASK_TYPE_VALUES = [tt for tt, _ in TASK_TYPES]
 
 EXECUTORS = ["claude", "codex", "antigravity"]
 
+# 역할 한 줄 설명 — defaults_or_custom 안내에서 각 역할이 무슨 일을 하는지 보여준다.
+ROLE_BLURBS = {
+    "lead": "Claude lead · 워커 dispatch·교차검증 수렴·최종 합성",
+    "claude": "독립 분석 워커 (Claude)",
+    "codex": "독립 분석 워커 (Codex)",
+    "antigravity": "독립 분석 워커 (Antigravity)",
+    "report-writer": "최종 리포트 작성 (분석은 하지 않음)",
+}
+
 # Task types that consume an approved plan and need a stage-scope pick:
 # implementation executes a stage, final-verification verifies a stage
 # (or the whole task via `auto`). Both gate the approved-plan + stage steps.
@@ -2357,11 +2367,34 @@ def _submit_reuse_previous(state: WizardState, value: str) -> Optional[str]:
             f"lead-model={state.lead_model or 'default'})")
 
 
+def _role_model_lines(state: WizardState) -> str:
+    """이번 run 에서 실제로 모델을 고르게 되는 역할만, 추천 모델과 함께 나열한다.
+    뒤따르는 *_model 단계의 등장 조건과 1:1 로 맞춰 안내와 실제 화면이 어긋나지
+    않게 한다 (그래서 분석에 참여하지 않는 antigravity 는 executor 일 때만 나온다)."""
+    rec = recommended_role_models()
+    roster = _resolved_roster(state)
+    impl = state.task_type == "implementation"
+
+    def line(role_label: str, blurb: str, model: str) -> str:
+        return f"  · {role_label} ({blurb}) — 추천 {model}"
+
+    lines = [line("lead", ROLE_BLURBS["lead"], rec["lead"])]
+    if impl:
+        ex = state.executor or "claude"
+        lines.append(line(f"executor={ex}", "코드 구현 실행자", rec.get(ex, "auto")))
+    else:
+        for w in ("claude", "codex", "antigravity"):
+            if w in roster:
+                lines.append(line(w, ROLE_BLURBS[w], rec[w]))
+    if impl or "report-writer" in roster:
+        lines.append(line("report-writer", ROLE_BLURBS["report-writer"],
+                          rec["report-writer"]))
+    return "\n".join(lines)
+
+
 def _build_defaults_or_custom(state: WizardState) -> Prompt:
-    roster = (state.workers_override
-              or ",".join(state.profile_workers)
-              or "(profile default)")
-    t = _p(state.workspace_root, "defaults_or_custom", workers=roster)
+    t = _p(state.workspace_root, "defaults_or_custom",
+           role_models=_role_model_lines(state))
     return Prompt(
         step=S_DEFAULTS_OR_CUSTOM, kind="pick",
         label=t["label"],
@@ -3306,11 +3339,16 @@ def _remaining_screens(state: WizardState) -> int:
     return screens
 
 
-def _screen_progress(state: WizardState) -> dict[str, int]:
+def _screen_progress(state: WizardState) -> dict[str, Any]:
     passed = _passed_screens(state)
     total = passed + _remaining_screens(state)
     index = passed + 1
-    return {"index": index, "total": total, "remaining": max(0, total - index)}
+    remaining = max(0, total - index)
+    suffix = "마지막 단계" if remaining == 0 else f"앞으로 {remaining} 스텝 남음"
+    return {
+        "index": index, "total": total, "remaining": remaining,
+        "label": f"Step {index}/{total} · {suffix}",
+    }
 
 
 def prompt_payload(state: WizardState, prompt: Prompt) -> dict[str, Any]:

package/runtime/skills/okstra-run/SKILL.md

@@ -32,7 +32,7 @@ Every wizard call returns JSON. The two shapes you'll see:
             "progress": { "index": 5, "total": 11, "remaining": 6 } } }
 ```
 
-Every non-terminal `next` carries a `progress` object (`done` / `aborted` omit it). `index` is the 1-based number of the **current screen** (pick_group counts as one screen), `total` is the wizard's estimate of the full screen count, and `remaining` = `total − index`. The total is a forward estimate from the current answers, so it may grow by a few when the user opens a branch (e.g. choosing *Customize* adds the model screen). **Always suffix the rendered prompt with the progress marker** — see Step 3.
+Every non-terminal `next` carries a `progress` object (`done` / `aborted` omit it). It holds `index` (1-based number of the **current screen**; pick_group counts as one screen), `total` (the wizard's forward estimate of the full screen count — may grow by a few when the user opens a branch, e.g. choosing *Customize* adds the model screen), `remaining` (`total − index`), and **`label`** — the ready-to-render Korean marker the wizard already composed (e.g. `Step 10/11 · 앞으로 1 스텝 남음`, or `Step 11/11 · 마지막 단계` on the final screen). **Always suffix the rendered prompt with `progress.label` verbatim** — see Step 3. Do not recompute the marker or decide "마지막 단계" yourself; only the wizard knows whether more screens follow.
 
 ```json
 { "ok": false, "error": "approved plan has no APPROVED marker: ...",
@@ -96,7 +96,7 @@ Output: the same `{ok, next}` JSON described above. The first `next` is always `
 
 Repeat until `next.kind == "done"` (or `"aborted"` — terminal cancel, see "How the wizard talks to you"):
 
-1. **Render** the prompt according to `kind` (and `multi` for pick). **Always append the progress marker to the rendered question label** (the `AskUserQuestion` question text, or the `text`-prompt message): suffix `label` with ` (Step <index>/<total> · 남은 <remaining>단계)`, using `next.progress`. When `remaining == 0` (the final `confirm` screen), use `(Step <index>/<total> · 마지막 단계)` instead. Example: `모델을 선택하세요 (Step 8/11 · 남은 3단계)`. Re-prompts after `ok: false` reuse `current.progress` the same way. The progress marker is presentation-only — never send it back to the wizard as part of an answer.
+1. **Render** the prompt according to `kind` (and `multi` for pick). **Always append the progress marker to the rendered question label** (the `AskUserQuestion` question text, or the `text`-prompt message): suffix it with ` (<next.progress.label>)` — render `progress.label` exactly as the wizard sent it, never recompute it. Example: label `Step 8/11 · 앞으로 3 스텝 남음` → `모델을 선택하세요 (Step 8/11 · 앞으로 3 스텝 남음)`. Re-prompts after `ok: false` reuse `current.progress.label` the same way. The progress marker is presentation-only — never send it back to the wizard as part of an answer.
    - `pick` + `multi: false` → `AskUserQuestion` with `multiSelect: false`, `label`, and `options`. The user's chosen option's `value` is the answer string.
    - `pick` + `multi: true` → `AskUserQuestion` with `multiSelect: true`, `label`, and `options`. Join the selected `value`s with `,` into a single literal CSV string (e.g. `"claude,codex,antigravity"`) and submit it as a single `--answer "claude,codex,antigravity"`. Empty selection submits `--answer ""` and the wizard re-prompts.
    - `pick_group` → one `AskUserQuestion` with one question per `questions[]` entry (tab). Map each tab's selected `value` back by `questions[].step`, assemble a JSON object, and submit it as a single literal `--answer '<json>'`.