ollaagent 0.1.8__tar.gz → 0.2.0__tar.gz

{ollaagent-0.1.8 → ollaagent-0.2.0}/CHANGELOG.md

@@ -7,6 +7,31 @@ Versioning: [Semantic Versioning](https://semver.org/spec/v2.0.0.html)
 
 ---
 
+## [0.2.0] - 2026-03-23
+
+### Fixed
+- 이중 출력 완전 해결 — `Live(auto_refresh=False)` + `live.refresh()` + `Markdown` 유지
+  - `Text` + 완료 후 Markdown 재출력 방식 폐기
+  - chunk마다 즉시 Markdown 갱신 → 실시간성 + 가독성 동시 확보
+
+### Removed
+- 불필요해진 `Text` import 제거
+- `transient=True` 관련 테스트 3종 제거
+
+---
+
+## [0.1.9] - 2026-03-23
+
+### Fixed
+- 스트리밍 중 plain text와 Markdown이 이중 출력되던 문제 — `Live(transient=True)` 적용으로 스트림 종료 시 plain text 자동 삭제
+
+### Tests
+- `test_markdown_printed_once_after_stream` — Markdown 1회만 출력 검증
+- `test_markdown_not_printed_when_no_content` — content 없으면 Markdown 미출력 검증
+- `test_live_created_with_transient_true` — `transient=True` 설정 검증
+
+---
+
 ## [0.1.8] - 2026-03-23
 
 ### Fixed

{ollaagent-0.1.8 → ollaagent-0.2.0}/PKG-INFO

@@ -1,6 +1,6 @@
 Metadata-Version: 2.4
 Name: ollaagent
-Version: 0.1.8
+Version: 0.2.0
 Summary: Local LLM agent powered by ollama — memory, plan mode, subagents
 License-File: LICENSE
 Requires-Python: >=3.11

{ollaagent-0.1.8 → ollaagent-0.2.0}/ollaAgent/agent.py

@@ -15,7 +15,7 @@ try:
 except ImportError:
     pass  # Windows 환경에서는 무시
 
-__version__ = "0.1.8"
+__version__ = "0.2.0"
 
 from dotenv import load_dotenv
 from ollama import Client
@@ -23,7 +23,6 @@ from rich.console import Console
 from rich.live import Live
 from rich.markdown import Markdown
 from rich.panel import Panel
-from rich.text import Text
 
 from ollaAgent.config_loader import build_system_prompt, load_config
 from ollaAgent.memory import SESSION_DIR, SessionMemory, save_session
@@ -420,17 +419,13 @@ def stream_response(stream: Any) -> tuple[str, str, dict[int, dict], int]:
             content = msg.get("content") or ""
             if content:
                 assistant_content += content
-                live.update(Text(assistant_content))
+                live.update(Markdown(assistant_content))
                 live.refresh()  # 매 chunk 즉시 출력
             _accumulate_tool_calls(msg, accumulated_tool_calls)
             # done=True 인 마지막 chunk에서 토큰 수 캡처
             if chunk.get("done"):
                 prompt_eval_count = chunk.get("prompt_eval_count") or 0
 
-    # 스트림 완료 후 Markdown으로 최종 렌더링 (가독성 확보)
-    if assistant_content:
-        console.print(Markdown(assistant_content))
-
     return (
         assistant_content,
         thinking_content,

{ollaagent-0.1.8 → ollaagent-0.2.0}/pyproject.toml

@@ -1,6 +1,6 @@
 [project]
 name = "ollaagent"
-version = "0.1.8"
+version = "0.2.0"
 description = "Local LLM agent powered by ollama — memory, plan mode, subagents"
 readme = "README.md"
 requires-python = ">=3.11"

{ollaagent-0.1.8 → ollaagent-0.2.0}/uv.lock

@@ -187,7 +187,7 @@ wheels = [
 
 [[package]]
 name = "ollaagent"
-version = "0.1.7"
+version = "0.1.9"
 source = { editable = "." }
 dependencies = [
     { name = "ollama" },