From 2fa488bd21455f22706a06cf0762af9fd359e818 Mon Sep 17 00:00:00 2001 From: ila Date: Tue, 23 Jun 2026 11:04:38 +0800 Subject: [PATCH] =?UTF-8?q?feat(ai-outfit):=20=E5=B7=A6=E6=A0=8F=E6=96=B0?= =?UTF-8?q?=E5=A2=9E=E3=80=8C=E6=A0=87=E9=A2=98=E7=94=9F=E6=88=90=E3=80=8D?= =?UTF-8?q?(=E7=9C=8B=E5=9B=BE=E2=86=92=E6=8F=90=E7=A4=BA=E8=AF=8D?= =?UTF-8?q?=E2=86=92AI=20=E6=96=87=E5=AD=97=E6=A0=87=E9=A2=98=E2=86=92?= =?UTF-8?q?=E5=86=99=E5=9B=9EA=E5=88=97)=20(=C2=A719.18)?= MIME-Version: 1.0 Content-Type: text/plain; charset=UTF-8 Content-Transfer-Encoding: 8bit AI 穿搭页左栏新增独立的「生成标题」流程：用户写标题提示词，AI 看该行 衣服图（目录行取首图）生成电商标题，逐行立即写回 Excel A 列并刷新明细表； 完成后重载 Excel，紧接「开始生成」跑图即用新标题。移除原「最终生成要求预览」 腾出版面（docs/11 §17）。 - ai_text_service.py：AiTextClient 复用图像服务 HTTP 管道做文本输出； chat/gemini 带图视觉，images/images_edits 明确报错；extract_text 取首条标题 - ai_title.py + TitleResult：单行编排，never raises - excel_service.write_title_result：只写 A 列、不动 D/E/F - config_service：title_model 默认 + load/save_title_prompt + 默认标题话术 - 面板：标题生成组（提示词+标题模型下拉+保存+生成标题）置于话术组上方； _TitleWorker 顺序逐行+立即回填+刷新；与「开始生成」互斥；删预览相关组件 - 测试：文本解析/payload、generate_title（单文件/目录首图/失败）、 write_title_result、面板标题组存在且无预览；全套 py37 通过 Co-Authored-By: Claude Opus 4.8 --- docs/11-ai-outfit.md | 51 ++++- src/app/widgets/ai_outfit_panel.py | 346 ++++++++++++++++++++++------- src/core/ai_title.py | 49 ++++ src/core/models.py | 13 ++ src/services/ai_text_service.py | 185 +++++++++++++++ src/services/config_service.py | 36 +++ src/services/excel_service.py | 16 ++ tasks.md | 26 +++ tests/test_ai_outfit_panel.py | 25 +++ tests/test_ai_text_service.py | 136 ++++++++++++ tests/test_ai_title.py | 108 +++++++++ tests/test_excel_service.py | 16 ++ 12 files changed, 921 insertions(+), 86 deletions(-) create mode 100644 src/core/ai_title.py create mode 100644 src/services/ai_text_service.py create mode 100644 tests/test_ai_text_service.py create mode 100644 tests/test_ai_title.py diff --git a/docs/11-ai-outfit.md b/docs/11-ai-outfit.md index 055c60c..e20e641 100644 --- a/docs/11-ai-outfit.md +++ b/docs/11-ai-outfit.md @@ -164,7 +164,7 @@ Excel 行 → `OutfitTask` 列表的转换由 `excel_service` 完成；核心只 - 提示词模板存 `~/.cmbot/config/outfit_prompt.txt`，界面可查看/编辑/保存；点「开始」前自动保存一次。 - 占位符：仅 `{title}`（标题）；界面只提供「插入标题」按钮，把占位符插入光标处。货号（`product_id`）不进提示词——它只用于 Excel B 列读取与输出文件命名（`货号.jpg`），不影响 AI 生成内容。（`render_prompt` 仍会替换偶然出现的 `{product_id}`，保持兼容，但界面不再引导插入。） - **「保存话术」按钮**：把当前编辑的模板原文（占位符原样保留，**不**存替换后的结果）经 `config_service` 写入 `outfit_prompt.txt`。用途是"改完先存、暂不开跑"并给用户明确反馈；与"开始前自动保存"并存、互为兜底（保留按钮是有意为之，对非技术用户更安心）。 -- **最终提示词预览（内嵌、不弹窗）**：左栏话术编辑下方常驻一块只读预览区，编辑话术时实时把占位符替换成样本行真值，显示最终要发送给 AI 的完整文字。**样本行下拉来自 Excel 的全部有效数据行（标题/货号/衣服图齐全，不看 E 列完成/失败状态）**，因此整表生成完成后仍能预览（见 §10.3）；默认选第一行。未选 Excel / 无有效行时显示带高亮占位符的模板原文 + 提示；缺 `{title}` 占位符时在预览区提示。预览只读，不改话术本身。（早期设计为弹窗 `QDialog`，因调话术需"边改边看"改为内嵌。） +- ~~**最终提示词预览（内嵌、不弹窗）**~~ **（§17 已移除）**：原左栏话术编辑下方的只读预览区 + 样本行下拉，为给左栏让出「标题生成」组（§17）已整体移除。相关历史问题（§10.1 下拉撑宽、§10.3 样本行为空、§10.4 不清空样本）随之作废。 - 缺标题占位符时开始前弹窗询问是否继续。 - 默认话术方向（穿搭/上身，区别于旧项目的主图场景，需另调）：人物上身实穿、保留衣服款式/版型/颜色/印花、合适身材与场景、电商可用、默认纯净不加促销牛皮癣。 @@ -250,7 +250,7 @@ Excel 行 → `OutfitTask` 列表的转换由 `excel_service` 完成；核心只 三栏布局： -- **左栏（数据源 + 话术创作，~360px）**：`Excel` / `输出` 各为**行内一行**（标签 + 路径 + 浏览，省纵向空间）；数据源概览（共 N 行 / 完成 / 待处理 / 失败）；**加大的**穿搭生成话术编辑 +「保存话术」+「插入标题」；下方常驻**加大的最终生成要求预览**（内嵌、实时，标题行右侧放样本行下拉，含 §7.1 自动附加的输出要求）。AI 模型下拉不在此（见右栏）。 +- **左栏（数据源 + 标题/话术创作，~360px）**：`Excel` / `输出` 各为**行内一行**（标签 + 路径 + 浏览，省纵向空间）；数据源概览（共 N 行 / 完成 / 待处理 / 失败）；**「标题生成」组（§17）在上**：标题生成提示词编辑 +「标题模型」下拉 +「保存」+「生成标题」；**「穿搭生成话术」组在下**：话术编辑 +「保存话术」+「插入标题」+ 多套模板下拉（§7.2）。**最终提示词预览已移除（§17）**。图片 AI 模型下拉不在此（见右栏）；标题模型下拉在本栏标题组内。 - **中栏（结果 + 明细）**：顶部「最近结果」缩略图条——**只展示已完成的人物效果图**，新图自动加到最左、首图标「最新」，单击看大图、右键开所在文件夹；下方「处理明细」表（行 / 标题 / 货号 / 衣服图 / 状态 / 结果或原因），按 Excel 行顺序，状态用 完成 / 失败 / 生成中 / 待处理 / 跳过 徽章。 - **右栏（设置 + 运行，~400px）**：生成设置标题与「重试上次失败的行」同排；图片并发数 / 新请求间隔 / 单任务冷却 / 失败重试 / 分辨率 / JPG 质量保持 **3 列 × 2 行**；`AI 模型` 标签与下拉框同排；本次进度 + 统计（完成 / 失败 / 待处理）；开始生成 / 停止生成同排；导出失败清单 / 打开输出目录同排；节省的纵向空间给实时日志（含 §8 心跳行）。 @@ -262,6 +262,8 @@ Excel 行 → `OutfitTask` 列表的转换由 `excel_service` 完成；核心只 ### 10.1 已知问题：左栏内容被中间面板裁掉（下拉框撑宽） +> **§17 更新：已作废。** 撑宽元凶「样本行下拉」随预览一并移除（§17）；保留本节仅作历史记录。新「标题模型」下拉仍套用下方「修复方向」的 elide 策略，防止再撑宽。 + **现象**：「2 AI 穿搭」左栏组件右侧显示不完整，像被中间面板遮挡了一部分。 **定位（离屏实测 1280×720）**： @@ -294,6 +296,8 @@ Excel 行 → `OutfitTask` 列表的转换由 `excel_service` 完成；核心只 ### 10.3 已知问题：全表生成完成后，预览样本行下拉为空 +> **§17 更新：已作废。** 预览与样本行下拉已移除（§17），本问题不复存在。`read_all_rows` 仍保留——它现在是「标题生成」的行来源（§17）。保留本节作历史记录。 + **现象**：选中的 Excel 整表生成成功后，再次选中该文件，「最终生成要求预览」的样本行下拉只显示「(选 Excel 后显示替换效果)」，无可选行。 **原因**：预览样本行用 `_reload_sample_rows()` 填，调的是给**生成**用的 `load_outfit_tasks()`——它按设计**跳过 E=「完成」的行**（失败行也只在勾「重试失败行」时返回）。整表都「完成」→ 返回空 → 下拉空 → 占位文案。预览本只是"拿一行真实数据看话术替换效果"，与"这行要不要重新生成"无关，不该受状态过滤。 @@ -306,6 +310,8 @@ Excel 行 → `OutfitTask` 列表的转换由 `excel_service` 完成；核心只 ### 10.4 改进：整表无待处理行时的提示 + 生成不清空预览样本 +> **§17 更新：改进 2 作废**（预览样本已移除，§17）；**改进 1（无待处理行提示）继续有效**。 + 承接 §10.3。整表都「完成」后点「开始生成」时当前体验不清晰，两项改进: **改进 1 — 无待处理行时给明确提示。** @@ -389,3 +395,44 @@ Excel 行 → `OutfitTask` 列表的转换由 `excel_service` 完成；核心只 - Excel 行顺序处理、图片并发/限速/重试/温和停止生效；实时日志 + 进度 + 结束摘要 + 失败清单导出。 - 日志写入 `~/.cmbot/logs`；AI 密钥不入库。 - 核心逻辑单测通过、不依赖 GUI、Python 3.7 可运行。 + +## 17. 标题生成（左栏独立功能） + +「添加印花」批量导出生成的 Excel（`docs/02` §6.12），A 列「标题」只是占位的**印花名**，不是真正的电商标题。本功能在 AI 穿搭页**左栏**新增一个**独立的「生成标题」**流程：用户写标题提示词，AI **看该行衣服图**（视觉）生成电商标题，**写回 Excel A 列**，再点「开始生成」跑图时图片提示词的 `{title}` 即用上新标题。与「开始生成」（图片）**互不绑定**、各自一个按钮。 + +### 17.1 数据流与回填语义 + +- **行来源**：复用 `excel_service.read_all_rows(excel)`（状态无关）——对全部有效行生成、**覆盖式**写 A，不看 E 列状态、不引入新列（保持与 `标题生成产品图.xlsx` 七列一致）。 +- **逐行看图、各生成 1 条、顺序回填**：按行顺序处理，第 i 行看第 i 行衣服图 → 生成 1 条标题 → **立即**写回第 i 行 A（`write_title_result(excel, row_index, title)`）→ 刷新中栏「处理明细」表该行「标题」列。即「第 n 条标题 → 第 n 行 A，顺序回填 + GUI 实时刷新」。 +- **目录行取首图**：C 列为图片目录时（印花 Excel 即如此），标题写回**一个 A 单元格**（整行一个标题），故只取 `ai_outfit.list_directory_images(dir)` 的**第一张**作视觉参考；标题提示词宜写成概括款式/印花的通用句式。 +- **条数对齐**：因逐行各生成 1 条，标题数永远 = 行数，不存在「AI 返回条数和行数对不上」的兜底问题。提示词即使写「生成 N 条」，每行也**只取第一条**（解析时取首个非空行、去行首序号/符号与首尾引号、单行化）。 +- **"覆盖图片组件的标题" = 写回 A + 重载**：图片生成在「开始生成」时当场 `load_outfit_tasks(excel)` 读 A 列，故标题写回 A 后无需另改图片组件；标题全部生成完**重新加载一次 Excel**，刷新界面与内存任务，紧接着「开始生成」即用新标题。 + +### 17.2 文本服务（复用图像服务的 HTTP 管道） + +- 新增 `services/ai_text_service.py` 的 `AiTextClient(config, session=None)`：复用 `ai_image_service` 的 `AiModelConfig` / `image_to_data_url` / `detect_api_type` / `normalize_api_url` / Bearer 鉴权 / 超时 / session，不重写 HTTP。 +- `generate_text(prompt, image_path=None) -> str`： + - `chat`：`messages=[{role:user, content:[{type:text,text:prompt}, {type:image_url,...}]}]`（带图=视觉）。 + - `gemini`：`contents[].parts=[{text},{inlineData}]`，`generationConfig.responseModalities=["TEXT"]`。 + - `images`/`images_edits`：纯图片接口，不能返回文字 → 抛 `AiTextServiceError`，提示「该模型不能生成文字，请改选文本/视觉模型」。 +- `extract_text_from_response(data)`：取 `choices[0].message.content`（str 或 content 列表的 text）/ gemini `candidates[0].content.parts[].text`；都取不到则抛错；返回**第一条标题**（见 §17.1 解析规则）。 + +### 17.3 模型与提示词 + +- **标题模型独立下拉**：图片/文本模型类型不同（图片模型返回图、不返回文字），左栏标题组内单独放「标题模型」下拉，与图片模型同源（`load_ai_models()`）但**独立记忆**所选（`app_config` 新键 `title_model`）。 +- **标题提示词**：单份，存 `~/.cmbot/config/title_prompt.txt`（`load_title_prompt`/`save_title_prompt`，仿旧式单份，标题侧不做多套模板）；默认文案面向电商女装（结合款式/版型/颜色/印花，输出一行中文标题，不加引号/表情/促销词）。 + +### 17.4 界面与运行 + +- **左栏布局**（§10 已同步）：「标题生成」组在上、「穿搭生成话术」组在下；预览块移除。标题组含：标题提示词编辑、`标题模型`下拉、「保存」、「生成标题」。 +- **运行**：`_TitleWorker(QObject)` 跑在 `QThread`（仿 `_OutfitWorker`），按行顺序逐行生成、立即回填、刷新该行 GUI；失败记日志、跳过该行、继续；用右栏「新请求间隔」做行间节流；温和停止。 +- **互斥**：「生成标题」与「开始生成」运行时互斥（避免同表并发写）。 +- 进度/结果走中栏「处理明细」表与右栏日志（不写 Excel 状态列）。 + +### 17.5 验收要点（标题生成） + +- 左栏有「标题生成」组（提示词 + 标题模型下拉 + 生成标题按钮），无预览块。 +- 选印花生成的 Excel（A=印花名、C=目录），点「生成标题」→ 每行 A 被改写为 AI 标题、明细表标题列实时刷新、D/E/F 未动。 +- 标题模型选到纯图片接口（images/images_edits）时明确报错提示换模型。 +- 生成完重载 Excel，紧接「开始生成」跑图用的是新标题。 +- 文本解析、`generate_title`（单文件/目录取首图/无图失败/客户端异常）、`write_title_result`（只改 A）单测通过，Python 3.7。 diff --git a/src/app/widgets/ai_outfit_panel.py b/src/app/widgets/ai_outfit_panel.py index ec6208d..a558c82 100644 --- a/src/app/widgets/ai_outfit_panel.py +++ b/src/app/widgets/ai_outfit_panel.py @@ -43,7 +43,9 @@ from services.config_service import ( DEFAULT_OUTFIT_PROMPT, load_ai_models, load_outfit_prompts, + load_title_prompt, save_outfit_prompts, + save_title_prompt, ) logger = logging.getLogger(__name__) @@ -136,6 +138,84 @@ class _OutfitWorker(QObject): self.finished.emit(summary) +class _TitleWorker(QObject): + """Generates titles row-by-row on a QThread (docs/11 §17); queued signals. + + Sequential by row: each row's garment image + the title prompt -> one title, + written back to that row's A column immediately. Failures are logged and skipped. + """ + + tasks_loaded = Signal(object) # List[OutfitTask] + log = Signal(str) + progress = Signal(int, int, object) # completed, total, TitleResult + finished = Signal(int, int) # success_count, fail_count + failed = Signal(str) # fatal pre-run error (e.g. Excel locked) + + def __init__(self, excel_path, model_config, prompt, request_interval): + super().__init__() + self._excel_path = excel_path + self._model_config = model_config + self._prompt = prompt + self._interval = float(request_interval or 0.0) + self._stop = False + + def stop(self): + self._stop = True + + def run(self): + import time + + from core.ai_title import generate_title + from core.models import TitleResult + from services.ai_text_service import AiTextClient + from services.excel_service import ( + ensure_excel_writable, + read_all_rows, + write_title_result, + ) + + try: + ensure_excel_writable(self._excel_path) + rows = read_all_rows(self._excel_path) + client = AiTextClient(self._model_config) # one client for the run + except Exception as exc: # noqa: BLE001 - report to UI + self.failed.emit(str(exc)) + return + + self.tasks_loaded.emit(rows) + total = len(rows) + if total == 0: + self.finished.emit(0, 0) + return + + success = fail = 0 + for index, task in enumerate(rows, start=1): + if self._stop: + break + if index > 1 and self._interval > 0: + time.sleep(self._interval) + result = generate_title(task, self._prompt, self._model_config, + api_client=client) + if result.success: + try: + write_title_result(self._excel_path, task.row_index, + result.generated_title) + except Exception as exc: # noqa: BLE001 - keep going + result = TitleResult(task=task, success=False, + error="写回失败：{}".format(exc), attempts=1) + if result.success: + success += 1 + self.log.emit("第 {} 行标题：{}".format( + task.row_index, result.generated_title)) + else: + fail += 1 + self.log.emit("第 {} 行标题失败：{}".format( + task.row_index, result.error)) + self.progress.emit(index, total, result) + + self.finished.emit(success, fail) + + # --------------------------------------------------------------------------- # Main panel # --------------------------------------------------------------------------- @@ -151,6 +231,9 @@ class AiOutfitPanel(QWidget): self._models = [] # list of model dicts from ai_models.json self._thread = None self._worker = None + self._title_thread = None # 标题生成线程（§17） + self._title_worker = None + self._title_fail = 0 # running failure count for title stats self._row_to_table = {} # excel row_index -> table row self._failures = [] # list of OutfitResult (failed) self._last_resolution = "" # for "value actually changed" check (§10.2) @@ -241,7 +324,7 @@ class AiOutfitPanel(QWidget): col.setContentsMargins(12, 12, 12, 12) col.setSpacing(10) - # 数据源 / 输出：行内一行（标签 + 路径 + 浏览），省纵向空间给话术/预览 + # 数据源 / 输出：行内一行（标签 + 路径 + 浏览），省纵向空间给标题/话术 self._excel_edit = QLineEdit() self._excel_edit.setPlaceholderText("选择商品表 .xlsx") col.addLayout(self._inline_path_row("Excel", self._excel_edit, self._browse_excel)) @@ -249,6 +332,9 @@ class AiOutfitPanel(QWidget): self._output_edit.setPlaceholderText("默认：程序旁的「穿搭图片」") col.addLayout(self._inline_path_row("输出", self._output_edit, self._browse_output)) + # 标题生成（§17）：看衣服图 + 提示词 → AI 文字标题 → 写回 Excel A 列 + col.addWidget(self._build_title_group(), stretch=2) + # 穿搭生成话术（多套模板；加大，随窗口高度拉伸） prm = QGroupBox() pv = QVBoxLayout(prm) @@ -271,7 +357,6 @@ class AiOutfitPanel(QWidget): pv.addLayout(trow) self._prompt_edit = QPlainTextEdit() self._prompt_edit.setMinimumHeight(150) - self._prompt_edit.textChanged.connect(self._refresh_preview) pv.addWidget(self._prompt_edit) prow = QHBoxLayout() insert_title_btn = QPushButton("插入标题") @@ -282,31 +367,37 @@ class AiOutfitPanel(QWidget): save_btn.clicked.connect(self._save_prompt) prow.addWidget(save_btn) pv.addLayout(prow) - col.addWidget(prm, stretch=2) - - # 最终生成要求预览（加大；内嵌、实时；替换样本行占位符 + 附加输出要求） - prev = QGroupBox() - pvw = QVBoxLayout(prev) - preview_header = QHBoxLayout() - preview_header.addWidget(QLabel("最终生成要求预览")) - self._sample_combo = QComboBox() - self._compact_combo(self._sample_combo) - self._sample_combo.currentIndexChanged.connect(self._refresh_preview) - preview_header.addWidget(self._sample_combo, stretch=1) - pvw.addLayout(preview_header) - self._preview_warn = QLabel("") - self._preview_warn.setStyleSheet("color:#b87a00;") - self._preview_warn.setVisible(False) - pvw.addWidget(self._preview_warn) - self._preview_view = QPlainTextEdit() - self._preview_view.setReadOnly(True) - self._preview_view.setMinimumHeight(200) - pvw.addWidget(self._preview_view) - col.addWidget(prev, stretch=3) + col.addWidget(prm, stretch=3) scroll.setWidget(inner) return scroll + def _build_title_group(self): + """标题生成组（§17）：提示词 + 标题模型下拉 + 保存 + 生成标题。""" + box = QGroupBox() + v = QVBoxLayout(box) + v.addWidget(QLabel("标题生成提示词")) + self._title_prompt_edit = QPlainTextEdit() + self._title_prompt_edit.setMinimumHeight(110) + v.addWidget(self._title_prompt_edit) + + model_row = QHBoxLayout() + model_row.addWidget(QLabel("标题模型")) + self._title_model_combo = QComboBox() + self._compact_combo(self._title_model_combo) + model_row.addWidget(self._title_model_combo, stretch=1) + v.addLayout(model_row) + + btn_row = QHBoxLayout() + save_title_btn = QPushButton("保存") + save_title_btn.clicked.connect(self._save_title_prompt) + btn_row.addWidget(save_title_btn) + self._title_btn = QPushButton("生成标题") + self._title_btn.clicked.connect(self._start_title) + btn_row.addWidget(self._title_btn) + v.addLayout(btn_row) + return box + def _create_settings_group(self): """生成设置 group (lives in the right run column); two params per row.""" gen = QGroupBox() @@ -331,7 +422,6 @@ class AiOutfitPanel(QWidget): self._retry_count.setRange(0, 10) self._resolution = QComboBox() self._resolution.addItems(_RESOLUTIONS) - self._resolution.currentIndexChanged.connect(self._refresh_preview) # activated = user click only; programmatic sets won't pop (docs/11 §10.2) self._resolution.activated.connect(self._on_resolution_activated) self._quality = QComboBox() @@ -490,24 +580,29 @@ class AiOutfitPanel(QWidget): self._rebuild_prompt_combo() self._apply_prompt(name) + # 标题生成提示词（单份，§17.3） + self._title_prompt_edit.setPlainText(load_title_prompt()) + self._models = load_ai_models() - self._model_combo.clear() - if not self._models: - self._model_combo.addItem("（未配置模型，请在 ai_models.json 添加）") - self._model_combo.setEnabled(False) - else: - self._model_combo.setEnabled(True) - for m in self._models: - self._model_combo.addItem(m.get("name") or m.get("model") or "(未命名)") - self._set_combo(self._model_combo, config.get("outfit_model", "")) + self._fill_model_combo(self._model_combo, config.get("outfit_model", "")) + self._fill_model_combo(self._title_model_combo, config.get("title_model", "")) # Snapshot current dropdown values so a later user re-select of the same # item doesn't trigger the info popup (§10.2). self._last_resolution = self._resolution.currentText() self._last_model = self._model_combo.currentText() if self._models else "" - # Fill the preview's sample-row dropdown from the remembered Excel. - self._reload_sample_rows() + def _fill_model_combo(self, combo, selected_name): + """Fill a model dropdown from self._models (shared by 图片/标题 model, §17.3).""" + combo.clear() + if not self._models: + combo.addItem("（未配置模型，请在 ai_models.json 添加）") + combo.setEnabled(False) + return + combo.setEnabled(True) + for m in self._models: + combo.addItem(m.get("name") or m.get("model") or "(未命名)") + self._set_combo(combo, selected_name) def _set_combo(self, combo, value): idx = combo.findText(str(value)) @@ -527,6 +622,7 @@ class AiOutfitPanel(QWidget): "outfit_quality": self._quality.currentText(), "outfit_retry_failed": self._retry_failed_chk.isChecked(), "outfit_prompt_name": self._current_prompt_name, + "title_model": self._title_model_combo.currentText() if self._models else "", }) # -- left actions --------------------------------------------------- @@ -537,7 +633,6 @@ class AiOutfitPanel(QWidget): if path: self._excel_edit.setText(path) self._emit_config() - self._reload_sample_rows() def _browse_output(self): path = QFileDialog.getExistingDirectory( @@ -574,7 +669,7 @@ class AiOutfitPanel(QWidget): self._current_prompt_name = name self._saved_text = self._prompt_text(name) self._select_prompt_in_combo(name) - self._prompt_edit.setPlainText(self._saved_text) # fires _refresh_preview + self._prompt_edit.setPlainText(self._saved_text) def _store_current_text(self): """Save the editor text into the current template + persist to disk.""" @@ -684,54 +779,133 @@ class AiOutfitPanel(QWidget): self._apply_prompt(self._prompts[min(idx, len(self._prompts) - 1)]["name"]) self._emit_config() - # -- inline prompt preview ------------------------------------------ + # -- 标题生成（§17）------------------------------------------------- - def _fill_sample_combo(self, tasks): - """Populate the sample-row dropdown (None data = no sample).""" - self._sample_combo.blockSignals(True) - self._sample_combo.clear() - if tasks: - for t in tasks: - pid = t.product_id if (t.product_id and t.product_id.strip()) else "(无货号)" - self._sample_combo.addItem( - "第 {} 行 · {} · {}".format(t.row_index, pid, t.title), t) - else: - self._sample_combo.addItem("（选 Excel 后显示替换效果）", None) - self._sample_combo.blockSignals(False) - self._refresh_preview() + def _save_title_prompt(self, silent=False): + save_title_prompt(self._title_prompt_edit.toPlainText()) + if not silent: + self.statusBar_message("标题提示词已保存") - def _reload_sample_rows(self): - """Best-effort: read the chosen Excel to fill the sample dropdown. + def _selected_title_model_config(self): + if not self._models: + QMessageBox.warning( + self, "未配置模型", + "尚未配置 AI 模型。请在 ~/.cmbot/config/ai_models.json 添加后重试。") + return None + idx = self._title_model_combo.currentIndex() + if idx < 0 or idx >= len(self._models): + QMessageBox.warning(self, "未选择标题模型", "请先选择标题模型。") + return None + from services.ai_image_service import AiModelConfig, api_config_errors + data = self._models[idx] + errors = api_config_errors(data) + if errors: + QMessageBox.warning(self, "模型配置有误", "；".join(errors)) + return None + return AiModelConfig.from_dict(data) - Uses read_all_rows (status-independent) so preview still works after the - whole sheet is 完成 (docs/11 §10.3); generation still uses load_outfit_tasks. - """ - excel = self._excel_edit.text().strip() - rows = [] - if excel: - try: - from services.excel_service import read_all_rows - rows = read_all_rows(excel) - except Exception as exc: # noqa: BLE001 - silent for preview - logger.info("Sample rows unavailable: %s", exc) - self._fill_sample_combo(rows) - - def _refresh_preview(self): - if not hasattr(self, "_preview_view"): + def _start_title(self): + if self._thread is not None or self._title_thread is not None: return - from core.ai_outfit import build_output_requirements, render_prompt - template = self._prompt_edit.toPlainText() - self._preview_warn.setVisible("{title}" not in template) - if "{title}" not in template: - self._preview_warn.setText("⚠ 话术缺少 {title} 占位符") - # Mirror what actually gets sent: append the output-requirements block - # for the currently selected resolution (docs/11 §7.1). - resolution = self._resolution.currentText() if hasattr(self, "_resolution") else None - task = self._sample_combo.currentData() if hasattr(self, "_sample_combo") else None - if task is None: - self._preview_view.setPlainText(template + build_output_requirements(resolution)) + excel = self._excel_edit.text().strip() + if not excel: + QMessageBox.information(self, "提示", "请先选择 Excel 文件。") + return + model_config = self._selected_title_model_config() + if model_config is None: + return + prompt = self._title_prompt_edit.toPlainText().strip() + if not prompt: + QMessageBox.information(self, "提示", "请先填写标题生成提示词。") + return + + self._save_title_prompt(silent=True) + self._emit_config() + + # reset run state (shared with image generation) + self._table.setRowCount(0) + self._row_to_table = {} + self._title_fail = 0 + self._progress.setValue(0) + self._log.clear() + + self._title_worker = _TitleWorker( + excel, model_config, prompt, self._interval.value()) + self._title_thread = QThread(self) + self._title_worker.moveToThread(self._title_thread) + self._title_thread.started.connect(self._title_worker.run) + self._title_worker.tasks_loaded.connect(self._on_title_tasks_loaded) + self._title_worker.log.connect(self._append_log) + self._title_worker.progress.connect(self._on_title_progress) + self._title_worker.finished.connect(self._on_title_finished) + self._title_worker.failed.connect(self._on_title_failed) + self._title_worker.finished.connect(self._title_thread.quit) + self._title_worker.failed.connect(self._title_thread.quit) + self._title_thread.finished.connect(self._cleanup_title_thread) + self._title_thread.start() + self._set_title_running(True) + + def _on_title_tasks_loaded(self, tasks): + self._populate_table(tasks) + self._update_stats(0, 0, len(tasks)) + self._append_log("标题生成：已加载 {} 行".format(len(tasks))) + + def _on_title_progress(self, completed, total, result): + row = self._row_to_table.get(result.task.row_index) + if row is not None: + if result.success: + self._set_cell(row, 1, result.generated_title) # refresh 标题 列 + self._set_cell(row, 4, "完成") + self._set_cell(row, 5, "标题已生成") + else: + self._set_cell(row, 4, "失败") + self._set_cell(row, 5, result.error) + if not result.success: + self._title_fail += 1 + self._progress.setValue(completed) + self._update_stats(completed - self._title_fail, self._title_fail, total - completed) + + def _on_title_finished(self, success, fail): + self._set_title_running(False) + msg = "标题生成结束：成功 {}，失败 {}".format(success, fail) + self._append_log(msg) + self._reload_after_titles() + if success or fail: + QMessageBox.information( + self, "标题生成", + msg + "。\n标题已写回 Excel，可点「开始生成」生成穿搭图。") else: - self._preview_view.setPlainText(render_prompt(template, task, resolution)) + QMessageBox.information(self, "标题生成", "该表没有可处理的行。") + + def _on_title_failed(self, message): + self._set_title_running(False) + self._append_log("标题生成无法开始：" + message) + QMessageBox.warning(self, "无法开始", message) + + def _cleanup_title_thread(self): + self._title_thread = None + self._title_worker = None + + def _reload_after_titles(self): + """Re-read Excel so the table + later image generation use new titles.""" + excel = self._excel_edit.text().strip() + if not excel: + return + try: + from services.excel_service import read_all_rows + rows = read_all_rows(excel) + except Exception as exc: # noqa: BLE001 - best effort + logger.info("Reload after titles failed: %s", exc) + return + self._populate_table(rows) + self._update_stats(0, 0, len(rows)) + + def _set_title_running(self, running): + self._title_btn.setEnabled(not running) + self._title_btn.setText("生成中…" if running else "生成标题") + self._start_btn.setEnabled(not running) # mutually exclusive with 开始生成 + self._excel_edit.setEnabled(not running) + self._title_model_combo.setEnabled(not running and bool(self._models)) # -- switch info popups (user-only; §10.2) -------------------------- @@ -767,7 +941,7 @@ class AiOutfitPanel(QWidget): # -- run control ---------------------------------------------------- def _start(self): - if self._thread is not None: + if self._thread is not None or self._title_thread is not None: return excel = self._excel_edit.text().strip() if not excel: @@ -856,11 +1030,14 @@ class AiOutfitPanel(QWidget): self._stop_btn.setEnabled(running) self._excel_edit.setEnabled(not running) self._model_combo.setEnabled(not running and bool(self._models)) + self._title_btn.setEnabled(not running) # mutually exclusive with 生成标题 # -- worker callbacks (UI thread) ----------------------------------- - def _on_tasks_loaded(self, tasks): + def _populate_table(self, tasks): + """Fill the detail table from a task list (shared by image/title runs).""" self._table.setRowCount(len(tasks)) + self._row_to_table = {} for row, task in enumerate(tasks): self._row_to_table[task.row_index] = row self._set_cell(row, 0, str(task.row_index)) @@ -870,9 +1047,10 @@ class AiOutfitPanel(QWidget): self._set_cell(row, 4, "待处理") self._set_cell(row, 5, "—") self._progress.setMaximum(max(1, len(tasks))) + + def _on_tasks_loaded(self, tasks): + self._populate_table(tasks) self._update_stats(0, 0, len(tasks)) - # Preview sample rows are owned by read_all_rows (§10.3/§10.4); don't reset - # them to the run's task list (which is empty when the sheet is all 完成). self._append_log("已加载 {} 行待处理任务".format(len(tasks))) def _on_progress(self, completed, total, result): diff --git a/src/core/ai_title.py b/src/core/ai_title.py new file mode 100644 index 0000000..b577429 --- /dev/null +++ b/src/core/ai_title.py @@ -0,0 +1,49 @@ +"""AI 标题生成单行编排（docs/11 §17）。 + +看该行衣服图（目录行取首图）+ 用户标题提示词 → 调 AI 文本服务生成电商标题。 +返回 TitleResult；never raises（异常聚合进结果）。标题写回 Excel A 列由调用方做。 +""" +import logging + +from core.ai_outfit import list_directory_images, looks_like_directory +from core.models import OutfitTask, TitleResult +from services.ai_text_service import AiTextClient + +logger = logging.getLogger(__name__) + + +def render_title_prompt(template, task): + """Replace {title}/{product_id} in the title prompt (no image-output tail).""" + return str(template).replace("{title}", task.title).replace( + "{product_id}", task.product_id) + + +def _reference_image(garment_path): + """Pick the vision reference: the file itself, or a directory's first image.""" + if looks_like_directory(garment_path): + images = list_directory_images(garment_path) + return str(images[0]) if images else None + return garment_path + + +def generate_title(task, prompt_template, model_config, api_client=None): + """Generate one title for an Excel row and return TitleResult. Never raises.""" + if not isinstance(task, OutfitTask): + raise TypeError("task must be OutfitTask") + + try: + image_path = _reference_image(task.garment_path) + if not image_path: + return TitleResult(task=task, success=False, attempts=1, + error="目录内没有图片：{}".format(task.garment_path)) + prompt = render_title_prompt(prompt_template, task) + client = api_client or AiTextClient(model_config) + title = client.generate_text(prompt, image_path) + if not title: + return TitleResult(task=task, success=False, attempts=1, + error="AI 未返回标题") + logger.info("Generated title row %s -> %s", task.row_index, title) + return TitleResult(task=task, success=True, generated_title=title, attempts=1) + except Exception as exc: # noqa: BLE001 - aggregate + logger.exception("Title generation failed for row %s", task.row_index) + return TitleResult(task=task, success=False, error=str(exc), attempts=1) diff --git a/src/core/models.py b/src/core/models.py index 24edb26..78658e0 100644 --- a/src/core/models.py +++ b/src/core/models.py @@ -182,6 +182,19 @@ class OutfitResult: output_paths: List[str] = field(default_factory=list) +@dataclass +class TitleResult: + """AI 标题生成单行结果（docs/11 §17）。 + + generated_title: 成功时为 AI 生成、清洗后的单行标题（写回 Excel A 列）。 + """ + task: OutfitTask + success: bool + generated_title: str = "" + error: str = "" + attempts: int = 0 + + # --------------------------------------------------------------------------- # 合成结果 # --------------------------------------------------------------------------- diff --git a/src/services/ai_text_service.py b/src/services/ai_text_service.py new file mode 100644 index 0000000..ff62d8c --- /dev/null +++ b/src/services/ai_text_service.py @@ -0,0 +1,185 @@ +"""AI 文本服务（docs/11 §17）：复用图像服务的 HTTP 管道，输出文字（标题）。 + +与 `ai_image_service.ImageApiClient` 平行：同一份 `AiModelConfig`、传图、鉴权、 +超时、session 全部复用，只把「解析图片」换成「解析文字」。仅 chat / gemini 这类 +能返回文字的接口可用；纯图片接口（images / images_edits）会明确报错。 +""" +import logging +import re + +import requests + +from services.ai_image_service import ( + API_CHAT, + API_GEMINI, + API_IMAGES, + API_IMAGES_EDITS, + _coerce_config, + _split_data_url, + detect_api_type, + image_to_data_url, + normalize_api_url, + resolution_timeout, + validate_api_config, +) + +logger = logging.getLogger(__name__) + + +class AiTextServiceError(RuntimeError): + """Raised when AI text (title) generation fails.""" + + +# Strip a leading list marker (1. / 2) / - / • / ①…) from a title line. +_TITLE_LEAD = re.compile(r"^\s*(?:\d+\s*[\.\)、:：]|[-*•])\s*") +_TITLE_CIRCLED = "①②③④⑤⑥⑦⑧⑨⑩" +_TITLE_QUOTES = "\"'「」『』“”‘’" + + +def build_text_payload(config, prompt, image_data_url=None): + """Build a JSON body that asks a chat/gemini model for TEXT output. + + image_data_url optional: when given, the garment image is sent as a vision + reference (docs/11 §17 看图生成). images/images_edits are text-incapable. + """ + cfg = _coerce_config(config) + api_type = detect_api_type(cfg.url, cfg.api_type) + + if api_type == API_CHAT: + content = [{"type": "text", "text": prompt}] + if image_data_url: + content.append({"type": "image_url", "image_url": {"url": image_data_url}}) + payload = { + "model": cfg.model, + "messages": [{"role": "user", "content": content}], + "stream": False, + } + elif api_type == API_GEMINI: + parts = [{"text": prompt}] + if image_data_url: + mime_type, data = _split_data_url(image_data_url) + parts.append({"inlineData": {"mimeType": mime_type, "data": data}}) + payload = { + "contents": [{"parts": parts}], + "generationConfig": {"responseModalities": ["TEXT"]}, + } + else: + raise AiTextServiceError( + "该模型是图片接口（{}），不能生成文字标题，请改选能返回文字的模型" + "（chat 或 gemini）".format(api_type)) + + payload.update(cfg.extra_body) + return payload + + +def _content_to_text(content): + """Flatten an OpenAI chat message 'content' (str or parts list) to text.""" + if isinstance(content, str): + return content + if isinstance(content, list): + texts = [] + for part in content: + if isinstance(part, dict) and isinstance(part.get("text"), str): + texts.append(part["text"]) + elif isinstance(part, str): + texts.append(part) + return "\n".join(texts) + return "" + + +def _extract_raw_text(data): + """Pull the model's text out of a chat or gemini JSON response.""" + if not isinstance(data, dict): + return "" + + choices = data.get("choices") + if isinstance(choices, list) and choices and isinstance(choices[0], dict): + message = choices[0].get("message") + if isinstance(message, dict): + text = _content_to_text(message.get("content")) + if text.strip(): + return text + # Some relays use the legacy completion shape choices[0].text. + legacy = choices[0].get("text") + if isinstance(legacy, str) and legacy.strip(): + return legacy + + candidates = data.get("candidates") + if isinstance(candidates, list) and candidates and isinstance(candidates[0], dict): + content = candidates[0].get("content") + if isinstance(content, dict) and isinstance(content.get("parts"), list): + texts = [p.get("text") for p in content["parts"] + if isinstance(p, dict) and isinstance(p.get("text"), str)] + joined = "\n".join(t for t in texts if t) + if joined.strip(): + return joined + + return "" + + +def _clean_title(text): + """Return the first non-empty line as a single clean title. + + Drops list numbering/bullets and wrapping quotes; even if the prompt asked + for several titles, only the first is used (docs/11 §17.1). + """ + if not text: + return "" + for line in str(text).splitlines(): + stripped = line.strip() + if not stripped: + continue + stripped = _TITLE_LEAD.sub("", stripped) + stripped = stripped.lstrip(_TITLE_CIRCLED).strip() + stripped = stripped.strip(_TITLE_QUOTES).strip() + if stripped: + return stripped + return "" + + +def extract_text_from_response(data): + """Return the first clean title text from an AI JSON response ('' if none).""" + return _clean_title(_extract_raw_text(data)) + + +class AiTextClient: + """HTTP client for AI text (title) generation; mirrors ImageApiClient.""" + + def __init__(self, config, session=None): + self.config = _coerce_config(config) + self.session = session or requests.Session() + if hasattr(self.session, "trust_env"): + self.session.trust_env = False + + def generate_text(self, prompt, image_path=None, resolution="1K"): + validate_api_config(self.config) + api_type = detect_api_type(self.config.url, self.config.api_type) + if api_type in (API_IMAGES, API_IMAGES_EDITS): + raise AiTextServiceError( + "该模型是图片接口（{}），不能生成文字标题，请改选能返回文字的模型" + "（chat 或 gemini）".format(api_type)) + + url = normalize_api_url(self.config.url, api_type) + if api_type == API_GEMINI: + url = url.replace("{model}", self.config.model) + + headers = { + "Authorization": "Bearer {}".format(self.config.api_key), + "Content-Type": "application/json", + } + read_timeout = ( + self.config.timeout_seconds + if self.config.timeout_seconds > 0 + else resolution_timeout(resolution) + ) + timeout = (self.config.connect_timeout_seconds, read_timeout) + + data_url = image_to_data_url(image_path) if image_path else None + payload = build_text_payload(self.config, prompt, data_url) + response = self.session.post(url, headers=headers, json=payload, timeout=timeout) + response.raise_for_status() + + title = extract_text_from_response(response.json()) + if not title: + raise AiTextServiceError("AI 响应中未找到文字标题") + return title diff --git a/src/services/config_service.py b/src/services/config_service.py index 65ce82c..3957e01 100644 --- a/src/services/config_service.py +++ b/src/services/config_service.py @@ -27,12 +27,14 @@ DEFAULT_CONFIG = { "outfit_quality": "均衡", "outfit_retry_failed": False, "outfit_prompt_name": "默认", # last-selected 话术模板 name (docs/11 §7.2) + "title_model": "", # last-selected 标题模型 name (docs/11 §17.3) } _CONFIG_FILENAME = "app_config.json" _AI_MODELS_FILENAME = "ai_models.json" _OUTFIT_PROMPT_FILENAME = "outfit_prompt.txt" # legacy single prompt (migrated) _OUTFIT_PROMPTS_FILENAME = "outfit_prompts.json" # multi named templates (§7.2) +_TITLE_PROMPT_FILENAME = "title_prompt.txt" # single 标题生成提示词 (§17.3) DEFAULT_OUTFIT_PROMPT_NAME = "默认" # Default outfit prompt (docs/11 §7). Seeded into outfit_prompts.json on first run. @@ -42,6 +44,12 @@ DEFAULT_OUTFIT_PROMPT = ( "电商主图风格，不加文字与促销标签。" ) +# Default title prompt (docs/11 §17.3). Used by 标题生成 when title_prompt.txt absent. +DEFAULT_TITLE_PROMPT = ( + "请根据这件女装的款式、版型、颜色与印花特点，生成一条适合台湾蝦皮电商的中文商品标题：" + "突出卖点与适穿场景，控制在 30 字以内。只输出标题本身一行，不要序号、引号、表情或促销词。" +) + def load_config(): """ @@ -173,6 +181,34 @@ def save_outfit_prompt(text): logger.error("Failed to save outfit prompt to %s: %s", prompt_file, exc) +def load_title_prompt(): + """Return the saved 标题生成提示词, or the built-in default (docs/11 §17.3).""" + from services.file_service import get_config_path + prompt_file = get_config_path(_TITLE_PROMPT_FILENAME) + if not prompt_file.exists(): + return DEFAULT_TITLE_PROMPT + try: + with open(str(prompt_file), encoding="utf-8-sig") as f: + text = f.read() + return text if text.strip() else DEFAULT_TITLE_PROMPT + except OSError as exc: + logger.warning("Title prompt unreadable (%s): %s", exc, prompt_file) + return DEFAULT_TITLE_PROMPT + + +def save_title_prompt(text): + """Persist the 标题生成提示词 (utf-8, no BOM). Does not raise.""" + from services.file_service import get_config_path + prompt_file = get_config_path(_TITLE_PROMPT_FILENAME) + try: + prompt_file.parent.mkdir(parents=True, exist_ok=True) + with open(str(prompt_file), "w", encoding="utf-8") as f: + f.write(text) + logger.info("Title prompt saved to %s", prompt_file) + except OSError as exc: + logger.error("Failed to save title prompt to %s: %s", prompt_file, exc) + + def _normalize_prompts(data): """Keep only valid {name, text} entries (non-empty name, string text).""" if not isinstance(data, list): diff --git a/src/services/excel_service.py b/src/services/excel_service.py index bb23eb2..a53d979 100644 --- a/src/services/excel_service.py +++ b/src/services/excel_service.py @@ -173,6 +173,22 @@ def write_outfit_source_excel(excel_path, rows): logger.info("Wrote outfit source Excel: %s (%d rows)", excel_path, len(rows)) +def write_title_result(excel_path, row_index, title): + """Write a generated title into column A (标题) and save (docs/11 §17). + + Only touches the title cell; D/E/F (image-generation status) are untouched. + """ + path = Path(excel_path) + workbook = load_workbook(str(path)) + try: + sheet = workbook.worksheets[0] + sheet.cell(row_index, COL_TITLE).value = title + workbook.save(str(path)) + logger.info("Outfit row %s title written: %s", row_index, title) + finally: + workbook.close() + + def write_outfit_result(excel_path, result): """Write one outfit result to columns D/E/F and save immediately.""" if not isinstance(result, OutfitResult): diff --git a/tasks.md b/tasks.md index b000f8f..ec97623 100644 --- a/tasks.md +++ b/tasks.md @@ -1279,3 +1279,29 @@ - [x] 保留「新请求间隔」启动节流；图片并发数 >1 时日志/缩略图完成顺序允许与文件名排序不同 - [x] 补测试：Excel 行顺序处理、目录内图片并发、单文件行不并发、已存在跳过、部分失败聚合、UI label/default/config 兼容 - [~] 验证：语法检查、`test_outfit_batch.py`、`test_ai_outfit.py`、`test_ai_outfit_panel.py` 通过；全套 `python -m unittest discover -s tests` 当前被工作区未提交的 `packaging/default_config/ai_models.json` 改动阻塞（模型顺序与出厂模板规范不一致），待清理该文件后重跑 + +### 19.18 AI 穿搭左栏「标题生成」 — docs/11 §17 + +前置阅读： + +- `docs/11-ai-outfit.md`（§17 标题生成、§7 提示词、§10 界面、§4.1 目录行） +- `src/services/ai_image_service.py`（`AiModelConfig`/`image_to_data_url`/`detect_api_type`/`normalize_api_url`/`build_payload`/`generate`，复用 HTTP 管道） +- `src/core/ai_outfit.py`（`render_prompt`/`looks_like_directory`/`list_directory_images`） +- `src/services/excel_service.py`（`read_all_rows`/`write_outfit_result`，COL_TITLE） +- `src/services/config_service.py`（`load_ai_models`/`load_outfit_prompt`/`DEFAULT_CONFIG`） +- `src/app/widgets/ai_outfit_panel.py`（`_build_left`/`_OutfitWorker`/预览相关方法） + +背景： + +「添加印花」批量导出的 Excel，A 列「标题」是占位印花名。需在 AI 穿搭页左栏新增**独立**的「生成标题」：用户写标题提示词，AI 看该行衣服图（视觉）生成电商标题，逐行回填 Excel A 列并刷新 GUI；之后「开始生成」跑图即用新标题。已确认：写回 A 列；独立按钮；看图（视觉）；独立「标题模型」下拉；逐行各生成 1 条、第 n 条回填第 n 行 A、重载刷新 GUI。 + +任务： + +- [ ] `src/services/ai_text_service.py`（新建）：`AiTextClient(config, session=None)` 复用 `ai_image_service` 管道；`generate_text(prompt, image_path=None)`（chat/gemini 带图视觉文本输出，images/images_edits 抛 `AiTextServiceError`）；`extract_text_from_response`（chat/gemini 取文本，返回第一条标题：首个非空行、去序号/引号、单行化） +- [ ] `src/core/ai_title.py`（新建）：`render_title_prompt(template, task)`（替换 `{title}`/`{product_id}`，不加图片输出要求尾巴）；`generate_title(task, prompt_template, model_config, api_client=None) -> TitleResult`（目录行取 `list_directory_images` 首图，无图失败，never raises） +- [ ] `src/core/models.py`：新增 `TitleResult`（task/success/generated_title/error/attempts） +- [ ] `src/services/excel_service.py`：新增 `write_title_result(excel_path, row_index, title)`（只写 A 列并保存，不动 D/E/F） +- [ ] `src/services/config_service.py`：`DEFAULT_CONFIG` 增 `title_model`；新增 `load_title_prompt`/`save_title_prompt`（`title_prompt.txt`）+ `DEFAULT_TITLE_PROMPT` +- [ ] `src/app/widgets/ai_outfit_panel.py`：移除预览块（`_sample_combo`/`_preview_*`/`_refresh_preview`/`_fill_sample_combo`/`_reload_sample_rows` 及信号连接）；新增「标题生成」组（提示词编辑 + `标题模型`下拉 + 保存 + 生成标题）置于话术组上方；`apply_config`/`_emit_config` 接 `title_model`+标题提示词；`_TitleWorker` 顺序逐行生成+立即回填+刷新明细表标题列，完成后重载 Excel；「生成标题」与「开始生成」互斥 +- [ ] 测试：`tests/test_ai_text_service.py`（文本解析含多行只取第一条、images_edits 抛错、payload 含图）；`tests/test_ai_title.py`（render、单文件/目录首图/无图失败/异常）；`tests/test_excel_service.py` 加 `write_title_result` 只改 A；删预览后 `ai_outfit_panel` 离屏可构建 +- [ ] 验证：相关单测 + 全套 py37 通过（`test_config_service` 的 `ai_models.json` 顺序失败属并行 §19.13 遗留，与本改动无关）；离屏冒烟（mock `AiTextClient`）：选印花 Excel → 生成标题 → A 列改写、明细表刷新、D/E/F 未动、面板无预览控件 diff --git a/tests/test_ai_outfit_panel.py b/tests/test_ai_outfit_panel.py index 1a8321b..3297991 100644 --- a/tests/test_ai_outfit_panel.py +++ b/tests/test_ai_outfit_panel.py @@ -73,6 +73,31 @@ class TestAiOutfitPanelDefaults(unittest.TestCase): self.assertIn("图片并发数", labels) + def test_title_group_present_and_preview_removed(self): + """标题生成组存在，预览块已移除（docs/11 §17）。""" + from PySide6.QtWidgets import QLabel + + panel = self._panel() + panel.apply_config(dict(DEFAULT_CONFIG)) + + labels = [label.text() for label in panel.findChildren(QLabel)] + self.assertIn("标题生成提示词", labels) + self.assertIn("标题模型", labels) + self.assertNotIn("最终生成要求预览", labels) + # The preview widgets and methods are gone. + self.assertFalse(hasattr(panel, "_preview_view")) + self.assertFalse(hasattr(panel, "_sample_combo")) + self.assertTrue(hasattr(panel, "_title_btn")) + self.assertTrue(hasattr(panel, "_title_model_combo")) + + def test_title_prompt_defaults_loaded(self): + from services.config_service import DEFAULT_TITLE_PROMPT + + panel = self._panel() + panel.apply_config(dict(DEFAULT_CONFIG)) + + self.assertEqual(panel._title_prompt_edit.toPlainText(), DEFAULT_TITLE_PROMPT) + if __name__ == "__main__": unittest.main() diff --git a/tests/test_ai_text_service.py b/tests/test_ai_text_service.py new file mode 100644 index 0000000..770112d --- /dev/null +++ b/tests/test_ai_text_service.py @@ -0,0 +1,136 @@ +"""Tests for the AI text (title) service (docs/11 §17).""" +import sys +import unittest +from pathlib import Path + +sys.path.insert(0, str(Path(__file__).parent.parent / "src")) + + +CHAT_CFG = {"url": "https://relay.example.com/v1/chat/completions", + "model": "gpt-4o", "api_key": "sk-x", "api_type": "chat"} +GEMINI_CFG = {"url": "https://relay.example.com/v1beta/models/{model}:generateContent", + "model": "gemini-2.5-flash", "api_key": "sk-x", "api_type": "gemini"} +IMAGES_EDITS_CFG = {"url": "https://relay.example.com/v1/images/edits", + "model": "img", "api_key": "sk-x", "api_type": "images_edits"} + + +class TestExtractText(unittest.TestCase): + def test_chat_string_content(self): + from services.ai_text_service import extract_text_from_response + + data = {"choices": [{"message": {"content": "纯棉宽松短袖T恤"}}]} + self.assertEqual(extract_text_from_response(data), "纯棉宽松短袖T恤") + + def test_chat_list_content(self): + from services.ai_text_service import extract_text_from_response + + data = {"choices": [{"message": {"content": [ + {"type": "text", "text": "印花连衣裙"}]}}]} + self.assertEqual(extract_text_from_response(data), "印花连衣裙") + + def test_gemini_parts(self): + from services.ai_text_service import extract_text_from_response + + data = {"candidates": [{"content": {"parts": [{"text": "碎花雪纺衫"}]}}]} + self.assertEqual(extract_text_from_response(data), "碎花雪纺衫") + + def test_multiline_takes_first_and_strips_numbering_quotes(self): + from services.ai_text_service import extract_text_from_response + + data = {"choices": [{"message": {"content": + "1. 「韩版宽松卫衣」\n2. 复古工装外套\n3. 简约百搭T恤"}}]} + self.assertEqual(extract_text_from_response(data), "韩版宽松卫衣") + + def test_missing_text_returns_empty(self): + from services.ai_text_service import extract_text_from_response + + self.assertEqual(extract_text_from_response({"choices": []}), "") + self.assertEqual(extract_text_from_response({}), "") + + +class TestBuildTextPayload(unittest.TestCase): + def test_chat_with_image_includes_image_url(self): + from services.ai_text_service import build_text_payload + + payload = build_text_payload(CHAT_CFG, "写标题", "data:image/png;base64,AAA") + content = payload["messages"][0]["content"] + types = [part["type"] for part in content] + self.assertEqual(types, ["text", "image_url"]) + self.assertEqual(content[1]["image_url"]["url"], "data:image/png;base64,AAA") + + def test_chat_without_image_text_only(self): + from services.ai_text_service import build_text_payload + + payload = build_text_payload(CHAT_CFG, "写标题") + content = payload["messages"][0]["content"] + self.assertEqual([p["type"] for p in content], ["text"]) + + def test_gemini_text_only_modality(self): + from services.ai_text_service import build_text_payload + + payload = build_text_payload(GEMINI_CFG, "写标题", + "data:image/jpeg;base64,BBB") + self.assertEqual( + payload["generationConfig"]["responseModalities"], ["TEXT"]) + parts = payload["contents"][0]["parts"] + self.assertIn("inlineData", parts[1]) + + def test_images_edits_rejected(self): + from services.ai_text_service import AiTextServiceError, build_text_payload + + with self.assertRaises(AiTextServiceError): + build_text_payload(IMAGES_EDITS_CFG, "写标题") + + +class _FakeResponse: + def __init__(self, payload): + self._payload = payload + + def raise_for_status(self): + pass + + def json(self): + return self._payload + + +class _FakeSession: + def __init__(self, payload): + self._payload = payload + self.posted = None + + def post(self, url, headers=None, json=None, timeout=None): + self.posted = {"url": url, "headers": headers, "json": json} + return _FakeResponse(self._payload) + + +class TestGenerateText(unittest.TestCase): + def test_generate_text_posts_and_returns_title(self): + from services.ai_text_service import AiTextClient + + session = _FakeSession({"choices": [{"message": {"content": "夏季冰丝防晒衣"}}]}) + client = AiTextClient(CHAT_CFG, session=session) + + # No image_path -> text-only payload; still returns the parsed title. + title = client.generate_text("给这件衣服起标题") + + self.assertEqual(title, "夏季冰丝防晒衣") + self.assertIn("chat/completions", session.posted["url"]) + self.assertEqual(session.posted["headers"]["Authorization"], "Bearer sk-x") + + def test_generate_text_images_edits_raises(self): + from services.ai_text_service import AiTextClient, AiTextServiceError + + client = AiTextClient(IMAGES_EDITS_CFG, session=_FakeSession({})) + with self.assertRaises(AiTextServiceError): + client.generate_text("标题") + + def test_generate_text_empty_response_raises(self): + from services.ai_text_service import AiTextClient, AiTextServiceError + + client = AiTextClient(CHAT_CFG, session=_FakeSession({"choices": []})) + with self.assertRaises(AiTextServiceError): + client.generate_text("标题") + + +if __name__ == "__main__": + unittest.main() diff --git a/tests/test_ai_title.py b/tests/test_ai_title.py new file mode 100644 index 0000000..f51d9f7 --- /dev/null +++ b/tests/test_ai_title.py @@ -0,0 +1,108 @@ +"""Tests for AI title generation core (docs/11 §17).""" +import shutil +import sys +import tempfile +import unittest +from pathlib import Path + +from PIL import Image + +sys.path.insert(0, str(Path(__file__).parent.parent / "src")) + + +class TestAiTitleCore(unittest.TestCase): + def setUp(self): + self.tmp = Path(tempfile.mkdtemp()) + + def tearDown(self): + shutil.rmtree(str(self.tmp), ignore_errors=True) + + def _make_image(self, path): + Image.new("RGB", (32, 32), (120, 80, 40)).save(str(path), format="PNG") + + def _task(self, garment_path, title="占位标题", product_id=""): + from core.models import OutfitTask + + return OutfitTask(row_index=2, title=title, product_id=product_id, + garment_path=str(garment_path)) + + def test_render_title_prompt_replaces_placeholders(self): + from core.ai_title import render_title_prompt + + task = self._task("g.png", title="旧标题", product_id="TY001") + out = render_title_prompt("参考 {title} / {product_id}", task) + + self.assertEqual(out, "参考 旧标题 / TY001") + + def test_generate_title_single_file_success(self): + from core.ai_title import generate_title + + garment = self.tmp / "shirt.png" + self._make_image(garment) + client = _RecordingTextClient("纯棉短袖T恤") + + result = generate_title(self._task(garment), "起个标题 {title}", + model_config={}, api_client=client) + + self.assertTrue(result.success, result.error) + self.assertEqual(result.generated_title, "纯棉短袖T恤") + self.assertEqual(client.image_paths, [str(garment)]) + + def test_generate_title_directory_uses_first_image(self): + from core.ai_title import generate_title + + d = self.tmp / "FG201" + d.mkdir() + for name in ("b.png", "a.png", "c.png"): + self._make_image(d / name) + client = _RecordingTextClient("印花连衣裙") + + result = generate_title(self._task(str(d) + "/"), "话术", + model_config={}, api_client=client) + + self.assertTrue(result.success, result.error) + # Sorted: a.png is the first reference image. + self.assertEqual(client.image_paths, [str(d / "a.png")]) + + def test_generate_title_empty_directory_fails(self): + from core.ai_title import generate_title + + d = self.tmp / "empty" + d.mkdir() + + result = generate_title(self._task(str(d) + "/"), "话术", + model_config={}, api_client=_RecordingTextClient("x")) + + self.assertFalse(result.success) + self.assertIn("没有图片", result.error) + + def test_generate_title_client_error_aggregated(self): + from core.ai_title import generate_title + + garment = self.tmp / "shirt.png" + self._make_image(garment) + + result = generate_title(self._task(garment), "话术", + model_config={}, api_client=_FailingTextClient()) + + self.assertFalse(result.success) + self.assertIn("boom", result.error) + + +class _RecordingTextClient: + def __init__(self, title): + self._title = title + self.image_paths = [] + + def generate_text(self, prompt, image_path=None, resolution="1K"): + self.image_paths.append(str(image_path)) + return self._title + + +class _FailingTextClient: + def generate_text(self, prompt, image_path=None, resolution="1K"): + raise RuntimeError("boom") + + +if __name__ == "__main__": + unittest.main() diff --git a/tests/test_excel_service.py b/tests/test_excel_service.py index 8db81f8..c5de0f4 100644 --- a/tests/test_excel_service.py +++ b/tests/test_excel_service.py @@ -126,6 +126,22 @@ class TestOutfitExcelService(unittest.TestCase): self.assertEqual(tasks[0].product_id, "") self.assertEqual([r.row_index for r in read_all_rows(p)], [2]) + def test_write_title_result_updates_a_only_and_saves(self): + """标题生成回填只改 A 列，不动 D/E/F（docs/11 §17）。""" + from services.excel_service import write_title_result + + # Row 3 starts as 完成 with D/E filled; writing a title must not touch them. + write_title_result(self.excel_path, 3, "AI 生成的电商标题") + + wb = load_workbook(str(self.excel_path)) + try: + ws = wb.active + self.assertEqual(ws.cell(3, 1).value, "AI 生成的电商标题") # A 改写 + self.assertEqual(ws.cell(3, 4).value, r"D:\out\ty002.jpg") # D 不动 + self.assertEqual(ws.cell(3, 5).value, "完成") # E 不动 + finally: + wb.close() + def test_check_excel_writable_true_for_existing_workbook(self): from services.excel_service import check_excel_writable