docs: add Korean README translation

…se pydantic base

- ArtifactFrontmatterBase (pydantic BaseModel) with persona / step_label /
  done / artifact_type / created_at — shape parallel to TurnEnvelope
  (§02-CONTEXT lesson HKUDS#2: one model, two serialization surfaces)
- Module-level _REGISTERED dict + register_schema / get_schema /
  list_registered / reset_registry accessors — structural twin of
  PhaseRegistry (§02-CONTEXT lesson HKUDS#3)
- Duplicate artifact_type raises ValueError naming both existing and
  attempted classes (§02-CONTEXT D-03 collision rule)
- get_schema returns None for unregistered names — Pitfall HKUDS#6 caller
  distinguishes this from pydantic ValidationError
- Activates Plan 02-01's lazy-import guarded loop end-to-end; the Phase 0
  regression matrix stays 12/12 green

…r increment + turn_id dedupe

- 9 tests covering D-14..D-17 + Pitfall HKUDS#2/HKUDS#3/HKUDS#16 invariants
- Module import fails at RED (ModuleNotFoundError)
- Covers: 0/1/2 no-progress turns, TaskCompleted reset, net-positive artifact delta,
  per-agent isolation, turn_id dedupe, question file write, ForcedProgressTriggered emit

…ressSignal routing-policy field

- clawteam/harness/forced_progress_gate.py: PhaseGate subclass with 2-turn per-agent
  threshold, strict per-agent attribution (no sprint-wide summation), multi-choice
  question writer (A=keep waiting, B=restart agent, C=abort sprint), ForcedProgressTriggered
  emit, module-level increment_turn_counter + reset_turn_counter_state helpers (Pitfall HKUDS#2
  turn_id dedupe).
- clawteam/harness/theater_detector.py: re-export shim — flips the skipif gate on
  tests/test_cycle_detector.py::test_progress_signal_breaks_cycle_streak_per_pitfall3
  so the previously-skipped Pitfall HKUDS#3 progress-signal test now runs green.
- clawteam/harness/artifacts.py: ArtifactStore.__init__ accepts turn_counter_callback
  kwarg (keyword-only, defaults None — BC preserved); write() invokes callback at end
  of hook chain when metadata carries an agent field (D-14 site HKUDS#2).
- clawteam/transport/base.py: module-level _TURN_COUNTER_CALLBACK slot + set_turn_counter_callback
  setter + get_turn_counter_callback test helper; _pre_deliver_hooks invokes callback
  on successful envelope validation (D-14 site HKUDS#1); _reset_drift_counters also clears
  the callback for clean sprint teardown.
- clawteam/team/routing_policy.py: _append_event gains progress_signal kwarg and writes
  progressSignal key onto every recentEvents entry (Plan 02-08 reserved the field,
  Plan 02-09 populates it — Pitfall HKUDS#3 seam).

Verification:
- pytest tests/test_forced_progress_gate.py -q → 9 passed
- pytest tests/test_cycle_detector.py -q → 7 passed (progress-signal test now active)
- pytest tests/test_transport_envelope.py tests/test_artifact_caps.py -q → all pass
- pytest tests/test_template_regression_matrix.py -q → 12 passed
- pytest tests/test_sprint_state.py tests/test_interaction_gate.py tests/test_event_types_phase2.py -q → peer green
- Full suite: 734 passed in 107s
- Ruff clean on all modified files

…n tests

- EXISTING_TEMPLATES_PHASE3 canonical list + len==6 guard (T-09-02)
- gstack_plugin_loaded fixture: fresh GstackSprintPlugin per test, minimal
  fake ctx, no EvidenceSchemaRegistry touch (avoids test-ordering collision
  with tests/test_gstack_plugin.py)
- test_existing_template_spawn_unaffected_by_gstack_plugin[6 templates] —
  asserts TeamConfig.template != 'gstack', member roster != 11 gstack roles,
  leader_role != 'ceo' for each of software-dev/hedge-fund/code-review/
  harness-default/research-paper/strategy-room (Pitfall 14 + QUALITY-14 +
  success-criterion HKUDS#2)
- test_reflect_phase_does_not_trigger_phase6_pending_write_for_non_gstack
  [6 templates] — T-07-01 HIGH severity 2nd-layer mitigation anchor;
  runtime assertion that emitting a Reflect event for non-gstack teams
  never writes _phase6_pending/<sprint>-retro.json
- test_all_six_existing_templates_parse_with_gstack_loaded — aggregate
  assertion that each existing template's phases != gstack phases AND
  leader_role != 'ceo' (success-criterion HKUDS#7)

Full-suite delta: +13 new passing tests (958 -> 971 passed). 3 pre-existing
failures unchanged (documented in deferred-items.md).