@remixmate/cli 0.12.8 → 0.13.0

package/skills/render-video/version.json

@@ -2,6 +2,6 @@
   "skillName": "render-video",
   "repoName": "agent-skill-media-maker",
   "skillId": "473",
-  "version": "V38",
+  "version": "V39",
   "skillDescription": "Final-render skill: loads a persisted RenderPlan by `job_id` and drives the Remotion engine to produce the final video.\n\nUse this skill as soon as the user mentions any of these intents (after assets are already prepared):\n- Render the video, composite the video, export the video\n- Turn the prepared assets into the final clip\n- Render with Remotion\n\nPrerequisite: assets must already be generated via `prepare_video_assets`. This skill never resolves or regenerates assets — pass it a `job_id` from a previous `prepare_video_assets` call.\n\n⚠️ Stop-and-confirm gate: never call this skill until the user has explicitly confirmed the assets prepared by `prepare_video_assets`. If those assets were prepared in the current turn and the user has not replied since, stop and ask instead of rendering."
 }

package/skills/template-registry/SKILL.md

@@ -140,7 +140,7 @@ remixmate template-registry --template-id <templateId>                 # then re
 remixmate template-registry --template-id <templateId> --slide-id key-points --slide-id timeline   # exact schemas of the chosen layouts
 ```
 
-Detail mode used to pretty-print, which nearly doubled the size (html-slide: 37 K → 65 K characters) and pushed the plain call past the agent's tool-result cap — the result was spilled to a file the agent cannot open, so it re-called with other flags, and re-read the whole contract on the next turn too (session review 2026-09-27). Output is now always compact, and `slideSchemas` — two thirds of a multi-layout template — is a menu until you name the layouts.
+Detail mode used to pretty-print, which nearly doubled the size (a multi-layout template: 37 K → 65 K characters) and pushed the plain call past the agent's tool-result cap — the result was spilled to a file the agent cannot open, so it re-called with other flags, and re-read the whole contract on the next turn too (session review 2026-09-27). Output is now always compact, and `slideSchemas` — two thirds of a multi-layout template — is a menu until you name the layouts.
 
 This mirrors the list/detail split described in `scripts/registry_loader.py` (P1.2), realized CLI-side so it holds even while the backend still serves one merged registry payload.
 

package/skills/template-registry/scripts/match_template.py

@@ -102,8 +102,6 @@ def build_binding(template: dict, dsl: dict) -> dict:
 
 
 
-
-
         custom = scene.get("customPayload") or {}
         template_data = custom.get("templateData") or scene.get("templateData") or {}
 
@@ -131,6 +129,8 @@ def build_binding(template: dict, dsl: dict) -> dict:
         dual_channel = sorted(dual_channel)
 
 
+
+
         for k, v in template_data.items():
             if k not in props:
                 props[k] = v

package/skills/template-registry/scripts/payload_hydrator.py

@@ -129,11 +129,19 @@ def hydration_spec(template_config: Optional[dict]) -> Optional[dict]:
             "Upgrade @remixmate/cli or fix the template."
         )
 
+
+
+    doc_kind = spec.get("docKind")
+    if not isinstance(doc_kind, str) or not doc_kind:
+        raise HydrationError(
+            "template declares capabilities.payloadHydration without docKind (e.g. the file "
+            "extension the extractor should parse). Fix the template's payloadHydration."
+        )
     index_field = spec.get("indexField")
     return {
         "payload_field": payload_field,
         "source": source,
-        "doc_kind": spec.get("docKind") or "pptx",
+        "doc_kind": doc_kind,
         "fields": spec.get("fields") or "content,layout",
         "index_field": index_field if isinstance(index_field, str) and index_field else DEFAULT_INDEX_FIELD,
     }

package/skills/template-registry/scripts/render_job_client.py

@@ -77,6 +77,10 @@ def _post(path: str, payload: dict, priv_token: str, timeout: int = 30) -> dict:
     except urllib.error.URLError as e:
         raise RuntimeError(f"network request failed ({path}): {e.reason}") from e
 
+
+    except (OSError, ValueError) as e:
+        raise RuntimeError(f"request failed ({path}): {type(e).__name__}: {e}") from e
+
     _record_billing(result)
 
     if result.get("code") != 0:

package/skills/template-registry/version.json

@@ -2,6 +2,6 @@
   "skillName": "template-registry",
   "repoName": "agent-skill-media-maker",
   "skillId": "475",
-  "version": "V29",
+  "version": "V30",
   "skillDescription": "Video-template registry skill. Stores every video-template definition and lists the available templates (templateId / name / aspect ratio / style tags).\n\nUse this skill as soon as the user mentions any of these intents:\n- View available templates / list every template\n\nNote: DSL→TemplateBinding is no longer a separate exposed step — once prepare_video_assets receives a template_id it builds the binding internally."
 }

package/skills/template-registry/video_dsl/runtime/dsl_validator.py

@@ -573,6 +573,30 @@ def _check_slide_id_chosen(dsl: dict) -> list[ValidationError]:
     return errors
 
 
+def _cross_field_marks(slide_schema: dict) -> tuple[list, list]:
+
+
+
+
+
+
+    line_marks: list = []
+    substring_marks: list = []
+    props = (slide_schema or {}).get("properties") or {}
+    for key, spec in props.items():
+        if not isinstance(spec, dict):
+            continue
+        if isinstance(spec.get("x-lineIndexOf"), str):
+            line_marks.append((None, key, spec["x-lineIndexOf"]))
+        if isinstance(spec.get("x-substringOf"), str):
+            substring_marks.append((key, spec["x-substringOf"]))
+        item_props = ((spec.get("items") or {}).get("properties") or {}) if spec.get("type") == "array" else {}
+        for sub_key, sub_spec in item_props.items():
+            if isinstance(sub_spec, dict) and isinstance(sub_spec.get("x-lineIndexOf"), str):
+                line_marks.append((key, sub_key, sub_spec["x-lineIndexOf"]))
+    return line_marks, substring_marks
+
+
 def _check_slide_cross_field(dsl: dict) -> list[ValidationError]:
 
 
@@ -611,23 +635,31 @@ def _check_slide_cross_field(dsl: dict) -> list[ValidationError]:
         if not tdata:
             continue
         base = f"scenes[{idx}].customPayload.templateData"
+        line_marks, substring_marks = _cross_field_marks(schemas.get(slide_id) or {})
 
 
-        code = tdata.get("code")
-        annotations = tdata.get("annotations")
-        if isinstance(code, str) and isinstance(annotations, list):
-            total = len(code.split("\n"))
-            for i, note in enumerate(annotations):
-                if not isinstance(note, dict):
-                    continue
-                line = note.get("line")
+        for array_key, key, ref in line_marks:
+            text = tdata.get(ref)
+            if not isinstance(text, str):
+                continue
+            total = len(text.split("\n"))
+            if array_key is None:
+                targets = [(f"{base}.{key}", tdata.get(key))]
+            else:
+                rows = tdata.get(array_key)
+                targets = [
+                    (f"{base}.{array_key}[{i}].{key}", row.get(key))
+                    for i, row in enumerate(rows if isinstance(rows, list) else [])
+                    if isinstance(row, dict)
+                ]
+            for path, line in targets:
                 if not isinstance(line, int) or isinstance(line, bool):
                     continue
                 if line < 1 or line > total:
                     errors.append(ValidationError(
-                        f"{base}.annotations[{i}].line",
-                        f"scene '{sid}': annotation points at line {line} but the code block has "
-                        f"{total} line(s) — while that narration line plays, no code line lights "
+                        path,
+                        f"scene '{sid}': {key} points at line {line} of '{ref}', which has "
+                        f"{total} line(s) — while that narration line plays, nothing lights "
                         "up at all. Line numbers are 1-based.",
                     ))
 
@@ -648,20 +680,14 @@ def _check_slide_cross_field(dsl: dict) -> list[ValidationError]:
                     ))
 
 
-
-        if "highlight" in ((schemas.get(slide_id) or {}).get("properties") or {}):
-            highlight = tdata.get("highlight")
-            title = tdata.get("title")
-            if (
-                isinstance(highlight, str)
-                and highlight.strip()
-                and isinstance(title, str)
-                and highlight not in title
-            ):
+        for key, ref in substring_marks:
+            part, whole = tdata.get(key), tdata.get(ref)
+            if isinstance(part, str) and part.strip() and isinstance(whole, str) and part not in whole:
                 errors.append(ValidationError(
-                    f"{base}.highlight",
-                    f"scene '{sid}': highlight '{highlight}' is not a substring of title "
-                    f"'{title}' — the two-colour split silently falls back to a single colour.",
+                    f"{base}.{key}",
+                    f"scene '{sid}': {key} '{part}' is not a substring of {ref} "
+                    f"'{whole}' — the template declares it must be, and silently drops "
+                    "the emphasis otherwise.",
                     severity="warning",
                 ))
 

package/skills/template-registry/video_dsl/schema/render-plan-v1alpha1.json

@@ -122,7 +122,13 @@
         },
         "layers": {
           "type": "array",
-          "items": { "$ref": "#/definitions/Layer" }
+          "items": { "$ref": "#/definitions/Layer" },
+          "description": "已废弃：render_video 不再写入，读到旧 RenderPlan 里的也会丢掉。场景用到的素材以 props 里的 assetId 引用为准"
+        },
+        "textLayers": {
+          "type": "array",
+          "items": { "type": "object" },
+          "description": "DSL 场景 textLayers 的原样拷贝（渲染不读，供剪映导出等只拿到 RenderPlan 的下游还原文本图层）"
         },
         "subtitleSegments": {
           "type": "array",

package/skills/video-parser/scripts/analyze_video.py

@@ -808,11 +808,13 @@ def build_assets_summary(decon: dict) -> dict:
             "url": audio.get("url", ""),
         }
 
+
     kf_list = []
     for kf in keyframes:
         kf_list.append({
             "index": kf["index"],
             "localPath": kf.get("localPath", ""),
+            "url": kf.get("url", ""),
             "timestampSec": kf.get("timestampSec", 0.0),
         })
 

package/skills/video-parser/version.json

@@ -2,6 +2,6 @@
   "skillName": "video-parser",
   "repoName": "agent-skill-media-maker",
   "skillId": "553",
-  "version": "V3",
+  "version": "V4",
   "skillDescription": "Video deconstruction skill. Splits a video into reusable content assets — audio, ASR transcript, scene segments, keyframe images.\n\nUse this skill as soon as the user mentions any of these intents:\n- Deconstruct / split / analyze / parse a video\n- Extract keyframes, extract the script from a video, transcribe a video\n- Pull content assets or raw material out of a video\n\nEven when the user does not say \"deconstruct\" explicitly, use this skill whenever they want to extract script text, keyframes, or structured information from a video."
 }