free-short-video 7.0.6 → 7.1.1

package/README.md

@@ -1,20 +1,22 @@
 ---
 
-# What's New in v7.0.6
+# What's New in v7.1.1
 
 ## What's New
 
 ### Features & Improvements
 
-* **Style preset picker shows what is active.** The preset dropdown was rebuilt as a native-select-style control: the trigger displays the currently selected preset name, the list marks the active entry with a checkmark, and a one-line hint under the field explains what picking a preset does. The trigger label, placeholder and hint are localized in all 22 interface languages.
+- **`agnes-video-2.5-flash` is the default video model.** With the legacy Video 2.0 channel retired upstream, the model lineup now covers the 2.5 series only, and every video task is submitted through the 2.5 standard protocol (`mode` / `seconds` / `size` / `aspect_ratio`). The per-model guidance shown in the create-task form reflects the available models.
+- **Configurable configuration directory for npm deployments.** A new `AGNES_CONFIG_DIR` environment variable lets `npx free-short-video` users keep `config.json` (their saved keys and settings) in a stable location such as `~/.agnes_config`, instead of inside the ephemeral npm cache that is lost on `npm cache clean` or a cache-directory change.
+- **Image uploads are validated on arrival.** Non-whitelisted file types are rejected with a readable message instead of being silently rewritten, and uploaded bytes are checked to be a decodable image. A corrupt file now fails immediately with a clear, scene-scoped message rather than surfacing as a low-level error during generation.
+- **Feedback panel and diagnostic report fully localized.** The remaining feedback-panel and diagnostic-report labels that still appeared in English on non-English interfaces are now translated across all 22 interface languages.
 
 ### Bug Fixes
 
-* **No more Chinese visual style inside non-Chinese tasks.** The hardcoded Chinese style default was removed from the Creative and Poetry task forms, from the shared legacy task-creation endpoint, and from the Creative and Poetry task models. Leaving the style field empty now pre-fills it on page load with the language-neutral default preset (an English cinematic prompt), so the task, the generated scene prompts and the diagnostic report all stay in the language the user is working in.
-
----
-
-Existing projects do not need to be recreated. Reopening a Creative or Poetry form after upgrading shows the preset name in the style field, and you can pick any other preset — or clear the field — as before.
+- **Custom end-frame images keep their scene mapping.** Uploaded end-frame images are now saved to their own scene index, so an empty slot no longer shifts later images onto the wrong scenes.
+- **Chat calls retry once on an empty response** instead of aborting the screenwriting stage with a `None` or `KeyError`.
+- **Poetry scene prompts use a language-neutral default style.** When no style is specified, the default hint is no longer a hardcoded Chinese phrase, so non-Chinese runs stay in their own language.
+- **API-key authentication diagnostics no longer write the configured site domain into the log line.**
 
 ---
 
@@ -102,12 +104,45 @@ schema.org structured data for SEO/GEO indexing. GitHub does not execute this sc
 
 > **🖥️ Try it now — no install needed:** Visit [video.lichuanyang.top](https://video.lichuanyang.top) and experience **Simple Video** mode directly in your browser. Just enter a prompt and generate a free AI video instantly.
 
-## 🚀 Two Ways to Use — Both Completely Free
+## 🚀 Three Ways to Use — All Completely Free
 
 | Project | Run Where | Features | Link |
 |---------|-----------|----------|------|
 | **[Agnes Video Generator](https://github.com/lcy362/agnes-video-generator)** (this project) | **Download & run locally** | **More powerful** — TTS narration, auto subtitles, digital anchor, image-to-video, keyframes animation, manuscript-to-video, checkpoint resume & more | [GitHub](https://github.com/lcy362/agnes-video-generator) |
 | **[FreeShortVideoStudio](https://github.com/lcy362/free-short-video-studio)** | **Fully online, in the browser** | Lightweight, zero install — no setup at all, **features under active construction** | [video.lichuanyang.top/studio](https://video.lichuanyang.top/studio) · [GitHub](https://github.com/lcy362/free-short-video-studio) |
+| **[Agnes Video Generator](https://github.com/lcy362/agnes-video-generator)** — **agent-ready** | **Driven by an AI coding agent** | **Least effort** — ships [`AGENTS.md`](AGENTS.md) plus a companion skill set (usage / troubleshoot / contrib): the agent installs the project, generates the video and debugs failures itself | [Agent guide](docs/public/agent-operations.md) · [Flint](https://github.com/lcy362/flint) |
+
+## 🤖 Or Let an AI Agent Drive It
+
+This project ships an [`AGENTS.md`](AGENTS.md) written for AI coding assistants, so an agent can install it, generate videos and debug failures after reading one document. Clone the repo, then tell your agent:
+
+> "Read the AGENTS.md in this project, install dependencies, configure the API key `<your-key>`, and start the server."
+
+Then ask it to prove the setup with `"Run the deployment verification checks."` — it executes the four-layer checklist (connectivity → static analysis → endpoint tests → features) and reports each result.
+
+**Want your agent to skip the learning step?** Install the companion skill set — three ready-made skills (**usage**: deploy, pick a mode, submit and watch a task, edit artifacts at Manual Mode checkpoints; **troubleshoot**: find out why a run failed; **contrib**: change the code, get the PR through CI) plus small scripts for task control, deployment verification, evidence collection, media checks and the local CI gate:
+
+**[lcy362/agnes-video-generator-skills](https://github.com/lcy362/agnes-video-generator-skills)**
+
+Clone the repository first:
+
+```bash
+git clone https://github.com/lcy362/agnes-video-generator-skills.git
+```
+
+**Recommended — let [flint](https://github.com/lcy362/flint) install and distribute it.** flint is a local-first, open-source skills manager that keeps your skills in one place and deploys them into any agent or project directory by symlink or copy. It works on local sources only — it never clones anything for you — so you register the directory you just cloned, and the three skills appear in front of every agent you use:
+
+```bash
+npx flint-skills-hub     # Sources → add the cloned directory (flint reads its skills/ subdirectory)
+```
+
+**Or copy it in by hand** — no flint required, but you repeat it for every project and every new agent:
+
+```bash
+cp -R agnes-video-generator-skills/skills/* <project>/.agents/skills/     # any agent that reads .agents/skills
+```
+
+Full guide: **[Let an AI Agent Operate This Project](docs/public/agent-operations.md)**.
 
 ## ⭐ Support & Contribute
 
@@ -193,6 +228,7 @@ Full walkthrough: [Getting Started → Configure API Key](docs/public/getting-st
 
 - **[Features](docs/public/features.md)** — Creation modes, the completely free AI model chain, AI narration & smart subtitles, flexible creative controls, production-grade reliability, and the multilingual Web UI.
 - **[Getting Started](docs/public/getting-started.md)** — Install and deploy in 4 ways: Manual (`start.sh`), Docker, npm (`npx free-short-video`), or AI-Agent assisted.
+- **[AI Agent Operations](docs/public/agent-operations.md)** — Three levels of agent-driven operation: hand your agent `AGENTS.md`, install the companion skill set, or distribute it to every agent with flint.
 - **[Usage Guide](docs/public/usage.md)** — Configure your API key, pick a video mode, resume from checkpoints, the three chaining modes, and logs & output layout.
 - **[Architecture](docs/public/architecture.md)** — Project structure and tech stack.
 - **[API Reference](docs/public/api.md)** — Full REST endpoint list (progress via polling, no WebSocket).

package/core/api/agnes_chat.py

@@ -191,20 +191,34 @@ class AgnesChatAPI:
         from core.config import get_settings
 
         timeout_retry_limit = 1
-        data = self._request_with_retry(
-            {
-                "model": self.model,
-                "messages": [
-                    {"role": "system", "content": system_prompt},
-                    {"role": "user", "content": user_prompt},
-                ],
-                "temperature": 0.7,
-                "max_tokens": max_tokens,
-            },
-            timeout=get_settings().agnes_chat_timeout,
-            timeout_retry_limit=timeout_retry_limit,
-        )
-        return data["choices"][0]["message"]["content"]
+        payload = {
+            "model": self.model,
+            "messages": [
+                {"role": "system", "content": system_prompt},
+                {"role": "user", "content": user_prompt},
+            ],
+            "temperature": 0.7,
+            "max_tokens": max_tokens,
+        }
+        # 空响应守卫：缺失 / 空正文时重试一次，避免把 ``None`` 或 KeyError 直接
+        # 抛给上层（原实现为裸 ``data["choices"][0]["message"]["content"]``）。
+        content = ""
+        for attempt in range(2):
+            data = self._request_with_retry(
+                payload,
+                timeout=get_settings().agnes_chat_timeout,
+                timeout_retry_limit=timeout_retry_limit,
+            )
+            try:
+                content = data["choices"][0]["message"]["content"] or ""
+            except (KeyError, IndexError, TypeError):
+                content = ""
+            if isinstance(content, str) and content.strip():
+                return content
+            content = ""
+            if attempt == 0:
+                logger.warning("[AgnesChat] Empty chat response; retrying once...")
+        raise RuntimeError("Agnes Chat returned empty content after retry")
 
     def chat_json(self, system_prompt: str, user_prompt: str, max_tokens: int = 4096) -> dict:
         """Chat 调用并解析 JSON 响应（健壮版）。

package/core/api/agnes_image.py

@@ -12,6 +12,7 @@ import requests
 from core.api.error_collector import collect_error, collect_error_from_exception
 from core.api.key_manager import get_key_ring
 from core.api.rate_limiter import get_rate_limiter
+from core.api.retry_policy import BusyTracker, busy_delay, fault_delay, is_busy_signal
 from core.config import get_base_url_for_key
 from utils.image import download_image
 from utils.image_normalizer import normalize_reference_path
@@ -21,6 +22,9 @@ logger = logging.getLogger(__name__)
 # 图像生成读超时基数（秒）：timeout = 基数 * (attempt + 1)，首次 120s 逐步放宽
 _READ_TIMEOUT_BASE_SECONDS = 120
 
+# v7.2 忙轨次数封顶：等效旧的 300s 预算 ÷ 20s 间隔基数
+_BUSY_MAX_ATTEMPTS = 15
+
 
 class ImageOutput:
     def __init__(self, fmt: str, ext: str, data: str):
@@ -159,6 +163,8 @@ class AgnesImageAPI:
         rotations = 0
         ring = get_key_ring()
         max_rotations = len(ring) * max_retries
+        # 忙轨（429 / 所有 503）：首跳贴限流 + 固定间隔 + 次数封顶
+        busy: BusyTracker | None = None
         while attempt < max_retries:
             try:
                 # 全局限速：在发起 HTTP 请求前获取令牌（2.3 异步原生）
@@ -174,9 +180,12 @@ class AgnesImageAPI:
                     timeout=(30, read_timeout),
                 )
 
-                # 429 限流：多 Key 换 Key 立即重试；否则指数退避
-                if resp.status_code == 429:
-                    if ring.has_multiple() and rotations < max_rotations:
+                # ── 忙轨（429 / 所有 503）────────────────────────────────
+                # 多 Key 先换 Key 立即重试；换无可换则首跳贴限流（交给共享令牌桶）、
+                # 之后固定间隔重试（不逐级加长），由次数封顶兜底。
+                if is_busy_signal(resp.status_code):
+                    if (resp.status_code == 429 and ring.has_multiple()
+                            and rotations < max_rotations):
                         rotations += 1
                         ring.rotate()
                         logger.warning(
@@ -184,40 +193,56 @@ class AgnesImageAPI:
                             f"(image, rotation {rotations})"
                         )
                         continue
-                    if attempt < max_retries - 1:
-                        delay = retry_base_delay * (attempt + 1)
-                        logger.warning(
-                            f"[AgnesImage] 429 rate limit, "
-                            f"retry {attempt + 1}/{max_retries} in {delay:.0f}s..."
+                    if busy is None:
+                        from core.config import get_settings
+                        busy = BusyTracker(
+                            get_settings().agnes_busy_retry_attempts
+                            or _BUSY_MAX_ATTEMPTS
                         )
+                    error_type = (
+                        "RateLimit429" if resp.status_code == 429
+                        else f"Busy{resp.status_code}"
+                    )
+                    if busy.exhausted():
+                        # 次数用尽：交给调用方按原语义抛错（记录最终失败）
                         collect_error(
                             "image", "generate_single_image",
                             prompt=prompt,
-                            error_type="RateLimit429",
-                            error_message="HTTP 429: rate limited",
-                            status_code=429,
+                            error_type=error_type,
+                            error_message=(
+                                f"HTTP {resp.status_code}: busy retries exhausted"
+                            ),
+                            status_code=resp.status_code,
                             response_body=resp.text,
-                            retry_count=attempt + 1,
+                            retry_count=busy.retries,
                         )
-                        await asyncio.sleep(delay)
-                        attempt += 1
-                        continue
-                    # 退避耗尽：记录最终失败并抛出
+                        resp.raise_for_status()
+                        break
+                    busy.retries += 1
+                    # 第 1 次重试 0s（贴着限流），之后固定基数
+                    delay = busy_delay(retry_base_delay, 0.0, busy.retries - 1)
+                    logger.warning(
+                        f"[AgnesImage] {resp.status_code} busy, "
+                        f"retry #{busy.retries}/{busy.max_attempts} in {delay:.0f}s..."
+                    )
                     collect_error(
                         "image", "generate_single_image",
                         prompt=prompt,
-                        error_type="RateLimit429",
-                        error_message="HTTP 429: retries exhausted",
-                        status_code=429,
+                        error_type=error_type,
+                        error_message=(
+                            "HTTP 429: rate limited" if resp.status_code == 429
+                            else f"HTTP {resp.status_code}: server busy"
+                        ),
+                        status_code=resp.status_code,
                         response_body=resp.text,
-                        retry_count=max_retries,
+                        retry_count=busy.retries,
                     )
-                    resp.raise_for_status()
-                    break
+                    await asyncio.sleep(delay)
+                    continue
 
-                # 5xx 服务端错误：退避重试
+                # 故障轨（非忙 5xx）：退避逐级加长 + max_retries 次数封顶
                 if resp.status_code >= 500 and attempt < max_retries - 1:
-                    delay = retry_base_delay * (attempt + 1)
+                    delay = fault_delay(retry_base_delay, attempt)
                     logger.warning(
                         f"[AgnesImage] {resp.status_code} server error, "
                         f"retry {attempt + 1}/{max_retries} in {delay:.0f}s..."
@@ -247,7 +272,7 @@ class AgnesImageAPI:
                     exc=e, prompt=prompt, retry_count=attempt + 1,
                 )
                 if attempt < max_retries - 1:
-                    delay = retry_base_delay * (attempt + 1)
+                    delay = fault_delay(retry_base_delay, attempt)
                     logger.warning(
                         f"[AgnesImage] {type(e).__name__}, "
                         f"retry {attempt + 1}/{max_retries} in {delay:.0f}s..."