okstra 0.219.0 → 0.219.1

package/runtime/prompts/lead/team-contract.md

@@ -13,7 +13,7 @@ Okstra tasks use one lead plus the exact worker assignments selected in the prep
 
 ### Role Definitions
 
-The start screen assigns a **model ref** (`provider/model`) to each **canonical role** slot: `leader`, `analyser`, `critic`, `designer`, `planner`, `implementer`, `verifier`, `report-writer`, `translator`. A provider name is the front of a model ref, not a role. Every `analyser` in the run shares an identical core responsibility. Specialization is additive — it lives in optional Section 7 of the worker output, NOT in differentiated core questions. Cross-verification only converges if every rostered analyser answers the same questions against the same brief.
+The start screen assigns a **model ref** (`provider/model`) to each **canonical role** slot: `leader`, `analyser`, `critic`, `designer`, `planner`, `implementer`, `verifier`, `report-writer`. A provider name is the front of a model ref, not a role. Every `analyser` in the run shares an identical core responsibility. Specialization is additive — it lives in optional Section 7 of the worker output, NOT in differentiated core questions. Cross-verification only converges if every rostered analyser answers the same questions against the same brief.
 
 | Canonical role | Core responsibility | Notes |
 |------|------|------|
@@ -25,7 +25,6 @@ The start screen assigns a **model ref** (`provider/model`) to each **canonical
 | `implementer` | Sole change author for one approved stage | Used by `implementation` |
 | `verifier` | Independent review of the assigned duty's subject | Duty varies by task type |
 | `report-writer` | **Authors** the final-report file in Phase 6 | Excluded from Phase 4/5 and convergence |
-| `translator` | Translates the designated sidecar only | Phase 7 |
 
 **Dispatch does not invent a missing model assignment.** Launch-time empty slots are filled by the model default chain before the run starts. At dispatch the model for every role comes from `resultContract.workerRoles[*].modelExecutionValue` in `task-manifest.json` (and lead model metadata). There is no per-role hard-coded fallback — see "Model Assignment Rules" below.
 

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

@@ -569,7 +569,6 @@
   },
   "confirmation": {
     "header": "선택 확인:",
-    "translation_scope": "  번역 작업자: {model} — 보고서 작성자와 같은 제공자·모델을 사용합니다. 선택 언어의 보고서가 필요하면 보고서 본문과 관련 분석·검증 결과를 전달해 번역하고 최종 보고서를 생성합니다. 같은 작업 범위의 재검증·수정·재시도에도 위에서 선택한 제공자·모델을 사용합니다.",
     "provider_data_scope": "\n전달 대상: 위 역할·모델 목록의 제공자(현재 세션 및 선택한 외부 모델 제공자).\n전달 자료: `{project_root}`의 이 작업에 대한 작업 개요, 작업 수행에 필요한 저장소 소스·문서, 선택한 근거 자료 및 실행 중 생성되는 관련 분석·검증 결과.\n진행을 선택하면 위 대상에 해당 자료를 전달하여 선택한 작업을 실행하는 것을 승인합니다. 선택에 없는 제공자나 작업과 무관한 자료는 승인 범위에 포함되지 않습니다. 실행 환경의 권한 검토는 별도로 적용됩니다.",
     "static_role": "  static-role   : {role}#{ordinal} / {model}",
     "dynamic_role": "  dynamic-role  : {role} / reuse selected participant model",

package/runtime/python/okstra_ctl/adapters/hosts/codex/relay.md

@@ -190,7 +190,7 @@ If preparation has already failed with a Git lock creation error or `Operation n
 
 ### Permission at the dispatch boundary
 
-Read `runManifest.userAuthorization` before a live dispatch, including `report-finalize`, which can start the translator internally. It preserves the confirmation text and the user response relayed through the wizard; quote its relevant recipient/material scope and response in the execution justification alongside the prepared assignment. The translator reuses the report writer's provider/model, as disclosed at confirmation. Do not wait until translation to inspect that authorization. A missing record is not consent, and the record does not override a host rejection. If review reports missing evidence already present in the record, submit that existing evidence through the permitted review mechanism; ask the user only when the actual approved scope does not cover the dispatch.
+Read `runManifest.userAuthorization` before a live dispatch. It preserves the confirmation text and the user response relayed through the wizard; quote its relevant recipient/material scope and response in the execution justification alongside the prepared assignment. A missing record is not consent, and the record does not override a host rejection. If review reports missing evidence already present in the record, submit that existing evidence through the permitted review mechanism; ask the user only when the actual approved scope does not cover the dispatch.
 
 Before a live CLI worker dispatch, check the current host's declared sandbox and approval policy. In a restricted Codex session, request the host's supported execution permission on the dispatch command itself (`sandbox_permissions: "require_escalated"` for `exec_command` when that mechanism is available and permitted). Scope the request to the prepared run and explain that it starts the selected worker processes. Follow the host's approval decision; a wizard confirmation or a successful preflight does not grant this permission.
 

package/runtime/python/okstra_ctl/adapters/providers/antigravity/adapter.py

@@ -303,7 +303,7 @@ def create_provider() -> ProviderSpec:
             role: "gemini-3.1-pro"
             for role in (
                 "lead", "analyser", "critic", "designer", "planner", "executor",
-                "verifier", "report-writer", "translator",
+                "verifier", "report-writer",
             )
         },
         wrapper="okstra-antigravity-exec.sh",

package/runtime/python/okstra_ctl/adapters/providers/claude/adapter.py

@@ -168,7 +168,6 @@ def create_provider() -> ProviderSpec:
             "executor": "opus",
             "verifier": "opus",
             "report-writer": "sonnet",
-            "translator": "sonnet",
         },
         wrapper="okstra-claude-exec.sh",
         supported_roles=ALL_ROLE_TOKENS,

package/runtime/python/okstra_ctl/adapters/providers/codex/adapter.py

@@ -133,7 +133,7 @@ def create_provider() -> ProviderSpec:
         models=CODEX,
         default_models={
             role: "gpt-6.1-sol"
-            for role in ("lead", "analyser", "critic", "designer", "planner", "executor", "verifier", "report-writer", "translator")
+            for role in ("lead", "analyser", "critic", "designer", "planner", "executor", "verifier", "report-writer")
         },
         wrapper="okstra-codex-exec.sh",
         supported_roles=ALL_ROLE_TOKENS,

package/runtime/python/okstra_ctl/adapters/providers/grok/adapter.py

@@ -308,7 +308,6 @@ def create_provider() -> ProviderSpec:
                 "executor",
                 "verifier",
                 "report-writer",
-                "translator",
             )
         },
         wrapper="okstra-grok-exec.sh",

package/runtime/python/okstra_ctl/adapters/providers/kimi/adapter.py

@@ -104,7 +104,6 @@ def create_provider() -> ProviderSpec:
             "executor": "kimi-k3",
             "verifier": "kimi-k3",
             "report-writer": "kimi-k3",
-            "translator": "kimi-k3",
         },
         wrapper="okstra-kimi-exec.sh",
         supported_roles=ALL_ROLE_TOKENS,

package/runtime/python/okstra_ctl/agent/invocation.py

@@ -39,7 +39,6 @@ AgentAudience = Literal[
     "scope-critic",
     "acceptance-critic",
     "report-writer",
-    "translator",
     "code-reviewer",
     "schedule-verifier",
     "business-flow-investigator",
@@ -604,7 +603,7 @@ def load_role_duty_contract(duty_root: Path, audience: AgentAudience) -> DutyCon
 def digest_duty_catalog(duty_root: Path) -> str:
     """Return the canonical digest of every contract file in a snapshot.
 
-    역할 계약은 하위 `roles/` 에 둔다 — `report-writer` 와 `translator` 는 직무
+    역할 계약은 하위 `roles/` 에 둔다 — `report-writer` 는 직무
     id 이면서 역할 id 라, 한 폴더에 두면 두 계약이 같은 파일 이름을 두고 겹친다.
     """
     names = [

package/runtime/python/okstra_ctl/agent/prompt_cli/cli.py

@@ -114,8 +114,8 @@ def _add_materialize_parser(commands: argparse._SubParsersAction) -> None:
     )
     materialize.add_argument(
         "--audit-source",
-        help=run_only + "; accepted only for report-writer and translator, whose "
-             "result is not their own worker result",
+        help=run_only + "; accepted only for report-writer, whose result is "
+             "not its own worker result",
     )
     materialize.add_argument("--host-runtime", help=standalone_only)
     materialize.add_argument("--execution-runner", choices=("cli-wrapper",), help=standalone_only)

package/runtime/python/okstra_ctl/agent/prompt_cli/jobs.py

@@ -81,8 +81,6 @@ def _metadata_job(
     if metadata.get("executionIdentityVersion") != 2 or metadata["dispatchKind"] != dispatch_kind:
         raise AgentPromptCliError(f"{metadata_path}: expected v2 dispatchKind {dispatch_kind!r}")
     execution = next(row for row in manifest["roleExecutions"] if row["roleExecutionRef"] == metadata["roleExecutionRef"])
-    if execution["role"] == "translator":
-        raise AgentPromptCliError("translator uses canonical reservation dispatch: worker-dispatch --workers translator")
     prompt = _project_input(project, metadata["prompt"]["path"], "prompt")
     anchors = prompt_anchor_values(prompt, ("Result Path", "Worker Result Path"))
     result = anchors.get("Worker Result Path") or anchors.get("Result Path")

package/runtime/python/okstra_ctl/agent/prompt_cli/materialize.py

@@ -99,7 +99,7 @@ _AUDIENCES = frozenset(get_args(AgentAudience))
 # 결과 파일과 별개의 워커 결과 포인터를 가진 audience. 이들만 `--audit-source` 로
 # 두 번째 경로를 받고, 프롬프트에 `**Worker Result Path:**` 앵커가 생긴다.
 # 나머지 audience 의 결과는 하나뿐이고 감사 사이드카는 그 이름에서 파생된다.
-_POINTER_AUDIENCES = frozenset({"report-writer", "translator"})
+_POINTER_AUDIENCES = frozenset({"report-writer"})
 
 
 def _materialize(args: argparse.Namespace) -> PreparedAgentInvocation:
@@ -196,7 +196,7 @@ def _materialize_run(
                 "the same path in the jobs file's workerResultPath"
             )
         audit_source_path = result_path
-    elif args.audience == "report-writer":
+    else:
         if audit_source_path is None:
             # The report writer is the one audience whose result path is not its
             # own worker result: it writes the report body, while the audit
@@ -234,31 +234,6 @@ def _materialize_run(
             result_path=result_path,
             audit_source_path=audit_source_path,
         )
-    elif (
-        audit_source_path is None
-        or _normalized(audit_source_path) == _normalized(result_path)
-    ):
-        # translator 다. report-writer 와 같은 두-경로 audience 인데 종전엔 빠진
-        # `--audit-source` 를 `--result` 로 조용히 접었다. 그러면 프롬프트에
-        # `**Worker Result Path:**` 앵커가 안 생기는데, `worker-dispatch` 는 그
-        # 앵커가 `**Result Path:**` 와 다를 것을 요구하므로 발행은 되지만 어떤
-        # 디스패치도 받지 못하는 예약이 남는다. 예약은 회수 명령이 없어 리드가
-        # 두 번째 id 로 다시 만드는 순간 "exactly one reservation" 이 영영
-        # 깨졌다(2026-09-08 실측, fontsninja-v3-site dev-10627-2
-        # requirements-discovery). 발행 시점에 거절한다.
-        raise AgentPromptCliError(
-            "translator materialization requires --audit-source distinct from "
-            "--result: --result is the translator's own report "
-            "(e.g. worker-results/translator-translations-<task-type>-<seq>.md) "
-            "and --audit-source the worker-result .md the audit sidecar is "
-            "derived from (worker-results/translator-worker-<task-type>-<seq>.md). "
-            "`worker-dispatch --workers translator` reads both from the prompt's "
-            "**Result Path:** and **Worker Result Path:** anchors and refuses a "
-            "prompt without the second. To fix a prompt already published "
-            "without it, re-run this command with the same --invocation-id and "
-            "--prompt plus --replace-undispatched; a new invocation id would "
-            "leave two reservations and block the translator for this run"
-        )
     _validate_run_identity(
         manifest,
         worker_id=args.worker_id,

package/runtime/python/okstra_ctl/agent/prompt_cli/run_identity.py

@@ -29,10 +29,6 @@ def _validate_run_identity(
         expected = "lead"
         if worker_id != "lead":
             raise AgentPromptCliError("lead assignment requires worker ID 'lead'")
-    elif assignment_ref == "translator":
-        expected = "translator"
-        if worker_id != "translator":
-            raise AgentPromptCliError("translator assignment requires worker ID 'translator'")
     elif assignment_ref.startswith("critic/"):
         scope = assignment_ref.split("/", 1)[1]
         expected = CRITIC_DUTY_BY_ASSIGNMENT_SEGMENT.get(scope, "")

package/runtime/python/okstra_ctl/dispatch_core.py

@@ -674,7 +674,7 @@ def _dispatch_cli_wrapper_batch(
         # (`_persisted_write_contract`) attempt 2 의 정책 digest 는 attempt 1 과
         # 다른데, 첫 라운드의 baseline 을 그대로 쓰면 마감의
         # `_validate_snapshot_authority` 가 `policyDigests` 불일치로 죽고 attempt-N
-        # 사이드카는 끝내 안 써진다(실측 2026-09-08, translator attempt 2:
+        # 사이드카는 끝내 안 써진다(실측 2026-09-08, 워커 attempt 2:
         # 산출물 완전·exit 0 인데 dispatcher 예외). 앞 라운드에서 완주한 동료의
         # 변경은 그 attempt 의 감사가 이미 판정했으므로 새 baseline 에 흡수돼도
         # 맞다 — 재시도는 `failed-no-mutation` 뒤에만 오므로(`retry_allowed`)
@@ -920,15 +920,6 @@ def _jobs_from_roster(
         options,
         team_state=team_state,
     )
-    if selected == ["translator"]:
-        return [_translator_job_from_reservation(
-            project_root,
-            workspace_root,
-            manifest,
-            team_state,
-            active_context,
-            options,
-        )]
     _mark_roster_skips(project_root, manifest, team_state, selected, requested_workers, options)
     worker_facts, prompt_paths = _materialize_roster_prompts(
         project_root,
@@ -962,29 +953,6 @@ def _select_workers(
     *,
     team_state: Mapping[str, Any] | None = None,
 ) -> list[str]:
-    # 번역자 디스패치는 roster 를 읽지 않는다 — 근거는 prepare 가 심는 canonical
-    # translator role execution 이다. 그래서 빈 roster 검사보다 앞에 둔다.
-    # 종전에는 뒤에 있어서, roster 가 비는 phase 에서 이 분기에 닿을 수 없었다:
-    # `release-handoff` 는 의도적으로 single-lead 라 `_resolve_roster` 가 빈
-    # 목록을 강제하는데(`run.py`), `reportLanguage` 가 en 이 아니면 render-views 는
-    # 번역 사이드카를 요구한다. 두 요구가 겹치면 예약 경로는 "run manifest has no
-    # recommendedWorkers entries" 로, jobs-file 경로는 "jobs file translator must
-    # use canonical reservation dispatch" 로 막혀 번역자를 띄울 방법이 없었다
-    # (실측 2026-09-07, fontsninja-v3-site dev-10626 release-handoff 001 — 리드가
-    # `okstra report-translate write` 로 우회했고, 그 run 의 매니페스트에는
-    # translator role execution 과 invocationAssignments.translator 가 둘 다 있다).
-    if tuple(requested_workers) == ("translator",):
-        provider = _canonical_translator_provider(manifest)
-        if provider is None:
-            raise DispatchError(
-                "translator dispatch requires a canonical translator role execution"
-            )
-        if provider not in options.supported_worker_wrappers:
-            raise DispatchError(
-                f"unsupported {options.unsupported_worker_label} translator provider: "
-                f"{provider}"
-            )
-        return ["translator"]
     recommended = _string_list(manifest.get("recommendedWorkers"))
     if not recommended:
         raise DispatchError("run manifest has no recommendedWorkers entries")
@@ -1027,270 +995,6 @@ def _select_workers(
     return selected
 
 
-def _canonical_translator_provider(manifest: Mapping[str, Any]) -> str | None:
-    execution = _canonical_translator_execution(manifest)
-    return _string_value(execution.get("provider")) if execution else None
-
-
-def _canonical_translator_execution(
-    manifest: Mapping[str, Any],
-) -> Mapping[str, Any] | None:
-    assignments = manifest.get("invocationAssignments")
-    assignment = (
-        assignments.get("translator") if isinstance(assignments, Mapping) else None
-    )
-    if not isinstance(assignment, Mapping):
-        return None
-    provider = _string_value(assignment.get("provider"))
-    model_execution = _string_value(assignment.get("modelExecutionValue"))
-    runner = _string_value(assignment.get("runner"))
-    if not provider or not model_execution or runner != BACKEND_CLI_WRAPPER:
-        return None
-    role_executions = manifest.get("roleExecutions")
-    matches = [
-        row
-        for row in role_executions
-        if isinstance(row, Mapping)
-        and row.get("role") == "translator"
-        and row.get("provider") == provider
-        and isinstance(row.get("binding"), Mapping)
-        and row["binding"].get("runner") == runner
-        and row["binding"].get("resolvedExecutionValue") == model_execution
-    ] if isinstance(role_executions, list) else []
-    return matches[0] if len(matches) == 1 else None
-
-
-_TRANSLATOR_RESERVATION_KEYS = {
-    "schemaVersion", "executionIdentityVersion", "invocationId",
-    "assignmentRef", "audience", "dispatchKind", "promptPath",
-    "metadataPath", "invocationRef", "participantRef",
-    "roleExecutionRef", "dutyId", "attempt",
-}
-
-
-def _translator_job_from_reservation(
-    project_root: Path,
-    workspace_root: Path,
-    manifest: Mapping[str, Any],
-    team_state: Mapping[str, Any],
-    active_context: Mapping[str, Any],
-    options: _BuildOptions,
-) -> WorkerJob:
-    execution = _canonical_translator_execution(manifest)
-    if execution is None:
-        raise DispatchError(
-            "translator dispatch requires a canonical translator role execution"
-        )
-    candidates, seen = translator_reservations(project_root, manifest, team_state)
-    run_manifest_rel = _string_value(manifest.get("runManifestPath"))
-    if len(candidates) != 1:
-        run_label = run_manifest_rel or "run manifest path unknown"
-        raise DispatchError(
-            "translator dispatch requires exactly one canonical invocation "
-            f"reservation for this run ({run_label}); found {len(candidates)}. "
-            "Translator reservations seen: " + ("; ".join(seen) if seen else "none")
-        )
-    reservation = candidates[0]
-    prompt_path = _resolve_project_path(
-        project_root, _require_string(reservation, "promptPath")
-    )
-    metadata_path = _resolve_project_path(
-        project_root, _require_string(reservation, "metadataPath")
-    )
-    expected_metadata = prompt_path.with_name(prompt_path.name + ".meta.json")
-    if metadata_path != expected_metadata:
-        raise DispatchError("translator invocation metadata path is not prompt-adjacent")
-    metadata = _load_json_object(metadata_path, "agent invocation metadata")
-    invocation = _invocation_job_fields(metadata, prompt_path, manifest)
-    expected = {
-        "invocationId": invocation["invocation_id"],
-        "invocationRef": invocation["invocation_ref"],
-        "participantRef": invocation["participant_ref"],
-        "roleExecutionRef": invocation["role_execution_ref"],
-        "dutyId": invocation["duty_id"],
-        "attempt": invocation["attempt"],
-    }
-    if any(reservation.get(key) != value for key, value in expected.items()):
-        raise DispatchError("translator reservation and invocation metadata differ")
-    if (
-        invocation["audience"] != "translator"
-        or invocation["assignment_ref"] != "translator"
-        or metadata.get("dispatchKind") != "translator"
-    ):
-        raise DispatchError("translator invocation identity is invalid")
-    result_path, worker_result_path = _translator_prompt_outputs(
-        project_root, prompt_path
-    )
-    if result_path == worker_result_path:
-        raise DispatchError(
-            "translator result and standard worker result paths must differ"
-        )
-    provider = _require_string(execution, "provider")
-    binding = execution.get("binding")
-    if not isinstance(binding, Mapping):
-        raise DispatchError("translator role execution has no binding")
-    return WorkerJob(
-        worker_id="translator",
-        provider=provider,
-        backend=options.default_backend,
-        project_root=project_root,
-        model_execution_value=_require_string(binding, "resolvedExecutionValue"),
-        wrapper_path=_resolve_wrapper(provider, workspace_root, options),
-        prompt_path=prompt_path,
-        result_path=result_path,
-        worker_result_path=worker_result_path,
-        completion_paths=(result_path, worker_result_path),
-        worktree_path=_worktree_path(manifest, active_context),
-        role="translator",
-        idle_timeout_seconds=options.idle_timeout_seconds,
-        dispatch_kind="translator",
-        **invocation,
-    )
-
-
-def translator_reservations(
-    project_root: Path,
-    manifest: Mapping[str, Any],
-    team_state: Mapping[str, Any],
-) -> tuple[list[Mapping[str, Any]], list[str]]:
-    """이 run 이 지금 디스패치할 수 있는 translator 예약과, 본 예약 전부의 요약.
-
-    두 소비자가 같은 답을 읽는다: `_translator_job_from_reservation` 은 그 하나를
-    골라 띄우고, `report-finalize` 의 `translate` 단계
-    (`okstra_ctl.report_translation_dispatch`) 는 0건이면 예약을 만든다. 후보를
-    세는 규칙이 두 곳이면 한쪽만 고쳐져 "만들었는데 못 고른다" 가 나온다.
-    """
-    execution = _canonical_translator_execution(manifest)
-    if execution is None:
-        raise DispatchError(
-            "translator dispatch requires a canonical translator role execution"
-        )
-    contract = manifest.get("agentContract")
-    if not isinstance(contract, Mapping):
-        raise DispatchError("translator dispatch requires an agent contract")
-    reservation_root = _resolve_required_path(
-        project_root, contract, "invocationReservationRootPath"
-    )
-    dispatched_ids = {
-        str(row.get("dispatchId") or "")
-        for collection in (
-            team_state.get("workerDispatches") or [],
-            team_state.get("agentDispatches") or [],
-        )
-        for row in collection
-        if isinstance(row, Mapping)
-    }
-    return _translator_reservation_candidates(
-        project_root,
-        reservation_root,
-        execution=execution,
-        dispatched_ids=dispatched_ids,
-        run_manifest_rel=_string_value(manifest.get("runManifestPath")),
-    )
-
-
-def _translator_reservation_candidates(
-    project_root: Path,
-    reservation_root: Path,
-    *,
-    execution: Mapping[str, Any],
-    dispatched_ids: set[str],
-    run_manifest_rel: str,
-) -> tuple[list[Mapping[str, Any]], list[str]]:
-    """이 run 이 디스패치할 수 있는 translator 예약과, 본 예약 전부의 요약.
-
-    예약 디렉터리(`prompts/.agent-invocations/`)는 run 이 아니라 task type 단위라
-    같은 task 의 이전 run 이 남긴 translator 예약이 함께 놓인다. translator 는
-    `assignmentRef` 가 접미 없는 `translator` 하나이고, 이전 run 의 디스패치는
-    이번 run 의 team-state 에 없으므로 "아직 디스패치 안 됨" 으로 읽혀 후보가
-    둘이 됐다 — 두 번째 run 부터 번역이 영영 막혔다(2026-09-03 실측,
-    fontsninja-v3-site dev-10626-1 r02·r04). 예약 자체는 run 을 모르지만 그 옆의
-    `.meta.json` 은 `contractSource.runManifestPath` 로 자기 run 을 안다. 그
-    값을 이번 run 의 `runManifestPath` 와 대조한다. 매니페스트가 그 경로를 안
-    가진 레거시 run 은 종전대로 run 을 가리지 않는다.
-    """
-    candidates: list[Mapping[str, Any]] = []
-    seen: list[str] = []
-    for path in sorted(reservation_root.glob("*.json")):
-        reservation = _load_json_object(path, "agent invocation reservation")
-        if not (
-            set(reservation) == _TRANSLATOR_RESERVATION_KEYS
-            and reservation.get("schemaVersion") == "2.0"
-            and reservation.get("executionIdentityVersion") == 2
-            and reservation.get("assignmentRef") == "translator"
-            and reservation.get("audience") == "translator"
-            and reservation.get("dispatchKind") == "translator"
-            and reservation.get("dutyId") == "translator"
-        ):
-            continue
-        invocation_id = str(reservation.get("invocationId") or "")
-        reservation_run = _reservation_run_manifest_rel(project_root, reservation)
-        dispatched = _build_dispatch_id(
-            invocation_id, int(reservation.get("attempt") or 0),
-        ) in dispatched_ids
-        seen.append(
-            f"{invocation_id} (run {reservation_run or 'unknown'}"
-            + (", dispatched" if dispatched else "")
-            + ")"
-        )
-        if dispatched:
-            continue
-        if (
-            reservation.get("participantRef") != execution.get("participantRef")
-            or reservation.get("roleExecutionRef") != execution.get("roleExecutionRef")
-        ):
-            continue
-        if run_manifest_rel and (
-            reservation_run is None
-            or os.path.normpath(reservation_run) != os.path.normpath(run_manifest_rel)
-        ):
-            continue
-        candidates.append(reservation)
-    return candidates, seen
-
-
-def _reservation_run_manifest_rel(
-    project_root: Path, reservation: Mapping[str, Any],
-) -> str | None:
-    """예약 옆 `.meta.json` 의 `contractSource.runManifestPath`. 못 읽으면 None."""
-    metadata_value = _string_value(reservation.get("metadataPath"))
-    if not metadata_value:
-        return None
-    try:
-        metadata = _load_json_object(
-            _resolve_project_path(project_root, metadata_value),
-            "agent invocation metadata",
-        )
-    except DispatchError:
-        return None
-    source = metadata.get("contractSource")
-    if not isinstance(source, Mapping):
-        return None
-    return _string_value(source.get("runManifestPath")) or None
-
-
-def _translator_prompt_outputs(
-    project_root: Path, prompt_path: Path,
-) -> tuple[Path, Path]:
-    try:
-        lines = prompt_path.read_text(encoding="utf-8").splitlines()
-    except OSError as exc:
-        raise DispatchError(f"cannot read translator prompt: {exc}") from exc
-    values: list[str] = []
-    for header in ("Result Path", "Worker Result Path"):
-        prefix = f"**{header}:** "
-        matches = [line[len(prefix):].strip() for line in lines if line.startswith(prefix)]
-        if len(matches) != 1 or not matches[0]:
-            raise DispatchError(
-                f"translator prompt requires exactly one non-empty {prefix.strip()} header"
-            )
-        values.append(matches[0])
-    return (
-        _resolve_project_path(project_root, values[0]),
-        _resolve_project_path(project_root, values[1]),
-    )
-
-
 def _select_cli_wrapper_assignments(
     recommended: Sequence[str],
     requested_workers: Sequence[str],
@@ -2878,27 +2582,6 @@ def _wrapper_log_tail(job: WorkerJob) -> str | None:
     return tail.decode("utf-8", errors="replace").strip() or None
 
 
-def _projectionless_translator(plan: DispatchPlan, job: WorkerJob) -> bool:
-    if not (
-        job.has_execution_identity
-        and job.role == "translator"
-        and job.worker_id == "translator"
-        and job.audience == "translator"
-        and job.assignment_ref == "translator"
-        and job.duty_id == "translator"
-        and job.dispatch_kind == "translator"
-    ):
-        return False
-    execution = _canonical_translator_execution(plan.manifest)
-    return bool(
-        execution
-        and execution.get("roleExecutionRef") == job.role_execution_ref
-        and execution.get("participantRef") == job.participant_ref
-        and execution.get("executionLabel") == job.execution_label
-        and execution.get("provider") == job.provider
-    )
-
-
 def _transition_job_status(
     plan: DispatchPlan,
     job: WorkerJob,
@@ -2907,24 +2590,6 @@ def _transition_job_status(
     *,
     model_execution_value: str = "",
 ) -> None:
-    if not _projectionless_translator(plan, job):
-        _transition_worker_status(
-            plan.team_state_path,
-            job.worker_id,
-            status,
-            reason,
-            model_execution_value=model_execution_value,
-        )
-        return
-    team_state = _load_json_object(plan.team_state_path, "team-state")
-    workers = team_state.get("workers")
-    if not isinstance(workers, list):
-        raise DispatchError("team-state workers must be an array")
-    if not any(
-        isinstance(row, Mapping) and row.get("workerId") == job.worker_id
-        for row in workers
-    ):
-        return
     _transition_worker_status(
         plan.team_state_path,
         job.worker_id,
@@ -2945,20 +2610,9 @@ def _job_terminal_status(
         row for row in workers
         if isinstance(row, Mapping) and row.get("workerId") == job.worker_id
     ]
-    if len(matches) == 1:
-        return _string_value(matches[0].get("status"))
-    if matches or not _projectionless_translator(plan, job):
+    if len(matches) != 1:
         raise DispatchError(f"team-state has no unique workerId={job.worker_id}")
-    dispatches = team_state.get("workerDispatches")
-    records = [
-        row for row in dispatches
-        if isinstance(row, Mapping)
-        and row.get("promptPath") == str(job.prompt_path)
-        and row.get("attempt") == attempt
-    ] if isinstance(dispatches, list) else []
-    if len(records) != 1:
-        raise DispatchError("translator dispatch has no unique status record")
-    return _string_value(records[0].get("status"))
+    return _string_value(matches[0].get("status"))
 
 
 def _record_dispatch(

package/runtime/python/okstra_ctl/dispatch_state.py

@@ -2221,19 +2221,6 @@ def _validate_v2_jobs_file_authority(
         )
     if errors:
         raise DispatchError("jobs file v2 authority: " + "; ".join(errors))
-    role_executions = {
-        string_value(row.get("roleExecutionRef")): row
-        for row in manifest.get("roleExecutions") or []
-        if isinstance(row, Mapping)
-    }
-    if any(
-        isinstance(role_executions.get(job.role_execution_ref), Mapping)
-        and role_executions[job.role_execution_ref].get("role") == "translator"
-        for job in jobs
-    ):
-        raise DispatchError(
-            "jobs file translator must use canonical reservation dispatch"
-        )
 
 
 def worker_jobs_from_file(

package/runtime/python/okstra_ctl/domain/provider.py

@@ -275,6 +275,6 @@ def _legacy_execution_capabilities(roles: frozenset[str]) -> frozenset[str]:
             capabilities.add("source-readonly")
         if role == "implementer":
             capabilities.add("project-mutation")
-        if role in {"report-writer", "translator"}:
+        if role == "report-writer":
             capabilities.add("extended-artifact-authoring")
     return frozenset(capabilities)

package/runtime/python/okstra_ctl/domain/role.py

@@ -35,11 +35,6 @@ ROLE_DEFINITIONS = (
         (),
         _READONLY_CAPABILITIES | frozenset({"extended-artifact-authoring"}),
     ),
-    RoleDefinition(
-        "translator",
-        (),
-        _READONLY_CAPABILITIES | frozenset({"extended-artifact-authoring"}),
-    ),
 )
 
 DUTY_ROLE_IDS = {
@@ -61,7 +56,6 @@ DUTY_ROLE_IDS = {
     "schedule-verifier": "verifier",
     "business-flow-investigator": "analyser",
     "report-writer": "report-writer",
-    "translator": "translator",
 }