@sogni-ai/sogni-intelligence-client 2.1.0

package/dist/schemas/tools/sound_to_video.schema.json

@@ -0,0 +1,70 @@
+{
+  "$schema": "https://json-schema.org/draft/2020-12/schema",
+  "$id": "https://schemas.sogni.ai/creative-agent/2026-04-27.1/tools/sound_to_video.schema.json",
+  "title": "sound_to_video arguments",
+  "schemaVersion": "2026-04-27.1",
+  "description": "Generate video synchronized to audio. Use when the user has uploaded an audio file (mp3, wav, m4a, flac) and the audio is the primary sync target, especially uploaded-audio-only workflows. Also use after generate_music (\"turn that song into a video\", \"make a music video from that\"). Auto-detects generated audio from generate_music if no audio file is uploaded. Seedance animate_photo/generate_video can also attach uploaded audio as a loose @Audio reference when an image or video reference anchors the request; use this tool instead when the soundtrack itself should drive the video. If the user provides a reference image, use ltx23-ia2v; for lip-sync with a face image, use wan-s2v; if no image, use ltx23-a2v. If the user wants dialogue/audio WITHOUT pre-existing audio, use animate_photo instead (LTX 2.3 generates audio natively). Note: Persona voice clips from resolve_personas are NOT used by this tool — for persona voice identity in video, use animate_photo or generate_video instead. LONG AUDIO ON SEEDANCE: Seedance caps each clip at 15s. When the user uploads audio longer than 15s and Seedance is selected (seedance2 or seedance2-fast), do NOT clamp to 15s and drop the rest — split the run into multiple sound_to_video calls in the same turn (one per 15s segment, so a 20s audio becomes two clips: audioStart=0 duration=15, then audioStart=15 duration=5) and finish with a single stitch_video call referencing the resulting clip indices in order with audioIndex pointing at the same uploaded audio so the stitched output carries the full original soundtrack. LTX/WAN models accept up to 20s per clip, so single-call is fine for them.",
+  "type": "object",
+  "additionalProperties": false,
+  "properties": {
+    "prompt": {
+      "type": "string",
+      "description": "Describe the video like a cinematographer. Let the audio define timing — use the prompt for visual interpretation. One flowing paragraph, present tense, specific natural language.\n\nLITERAL PROMPT OVERRIDE: If the user explicitly says not to modify the prompt, or to use it exactly/verbatim/as-is, copy the identified prompt text verbatim instead of applying these construction rules unless a hard requirement is missing. For Seedance, set expandPrompt=false.\n\nSTRUCTURE: shot/style and scale → subject → environment, lighting, color, texture, atmosphere → visual action synced to audio → camera movement. For LTX 2.3 image+audio mode, do not re-describe static details already visible in the reference image; focus on motion, action, camera, and how the image responds to the audio.\n\nMOTION PACING: Scale complexity to duration. <=6s: 1 main visual beat + 1 simple camera move. Around 10s: 2-3 clear beats + 1 camera move. >10s: up to 4 beats in clear sequence. Let the audio define timing, but avoid stacking subject, camera, and environment motion in short clips.\n\nBLOCKING: Direct layout when it affects the shot: left/right placement, foreground/background, facing direction, and relative distance between subjects.\n\nLIP-SYNC: Shot framing, speaker's appearance and setting, physical performance synced to audio — gestures, expressions, jaw movement between phrases. Include acting beats.\n\nMUSIC VISUALIZATION: Visual style, environment, and how elements react to rhythm and energy.\n\nAUDIO-REACTIVE: Motion and visual changes that correspond to sounds in the track.\n\nLTX VOCABULARY: camera (tracking, dolly, pan, tilt, handheld, static frame), lighting/atmosphere (golden hour, neon glow, dramatic shadows, fog, rain, smoke, reflections), scale/pacing (expansive, epic, intimate, claustrophobic, slow motion, time-lapse, lingering shot, continuous shot), style/genre (film noir, painterly, cyberpunk, stop-motion, claymation, 2D/3D animation, hand-drawn, fantasy, thriller, experimental film).\n\nAVOID: Vague prompts, too many competing visual elements, abstract descriptions without visible behavior, rigid numeric constraints, readable text or logos. QUOTING RULE: ONLY use double quotes for spoken dialogue. Never quote on-screen text, overlay text, titles, captions, signs, or any visual text — describe them without quotes.\n\nBATCH VARIATIONS: When numberOfVariations > 1, use Dynamic Prompt syntax to vary the visual interpretation while keeping audio sync intent consistent. Example: \"{abstract neon visualization|nature scene with swaying trees|urban street with rain} synced to the beat\"."
+    },
+    "expandPrompt": {
+      "type": "boolean",
+      "description": "Seedance only. Whether to run the shared Seedance prompt shaper before dispatch. Defaults to true; set false only when the user explicitly asks to submit the compact prompt directly or not modify the prompt."
+    },
+    "audioSourceIndex": {
+      "type": "number",
+      "description": "Index of the uploaded audio file to use (0-based, from uploaded files list). If only one audio file is uploaded, use 0. If no audio was uploaded but generate_music was used earlier, omit this — the tool will automatically find the generated audio."
+    },
+    "sourceImageIndex": {
+      "type": "number",
+      "description": "Optional index of an uploaded image to use as the starting frame (0-based). Required for lip-sync models (WAN S2V). For audio-only-to-video models (LTX 2.3 A2V), this is optional — omit it to generate video purely from text + audio."
+    },
+    "audioStart": {
+      "type": "number",
+      "description": "Start offset in seconds into the audio track. Use when the user says \"start 20 seconds in\", \"skip the intro\", \"use the chorus at 1:30\", etc. Default: 0 (beginning of audio). The video will be synced to the audio starting from this point.",
+      "minimum": 0
+    },
+    "duration": {
+      "type": "number",
+      "description": "Video duration in seconds. Default: 5. Range: 2-20. For music videos, use the MAXIMUM duration (20) since the audio is always longer than the video limit. Use when the user explicitly requests a specific length.",
+      "minimum": 2,
+      "maximum": 20
+    },
+    "videoModel": {
+      "type": "string",
+      "enum": [
+        "wan-s2v",
+        "seedance2",
+        "seedance2-fast",
+        "ltx23-ia2v",
+        "ltx23-a2v"
+      ],
+      "description": "Video model. \"ltx23-ia2v\" (default when image available): LTX 2.3 image+audio to video, audio-reactive with a reference image; Fast/HQ use the distilled 8-step worker and Default Media Quality Pro uses the non-distilled dev worker. \"ltx23-a2v\" (default when no image): LTX 2.3 audio-only to video, no image needed, creates video purely from text prompt + audio with the same quality-tier routing. \"wan-s2v\": WAN 2.2 sound-to-video, best for lip-sync with a face image, fast 4-step. \"seedance2\": Seedance 2.0 audio-reference video, 4-15s; this tool supplies the audio plus a required reference image because Seedance text+audio without image/video is unsupported. \"seedance2-fast\": Seedance 2.0 Fast (720p cap) — pick this whenever the user says \"Seedance fast\", \"seedance-fast\", or asks for 480p/720p; pick \"seedance2\" only when they explicitly request 1080p or the full Seedance variant. For Seedance audio-reference prompts, preserve exact spoken dialogue when the user supplied it, and assign @Image1/@Audio1 roles. If the user asks for speech without words, describe the vocal performance without inventing quoted dialogue. Treat lip-sync, voice cloning, and real-human reference behavior as provider-sensitive rather than guaranteed. Omit to auto-select based on whether an image is present."
+    },
+    "generateAudio": {
+      "type": "boolean",
+      "description": "Seedance only. Whether Seedance should include a generated/native audio track in the final video. Omit by default so the reference audio drives the result; set false only for explicit silent output."
+    },
+    "numberOfVariations": {
+      "type": "number",
+      "description": "Number of video variations to generate (1-16). Default: 1.",
+      "minimum": 1,
+      "maximum": 16
+    },
+    "targetResolution": {
+      "type": "number",
+      "description": "Short-side video resolution target in pixels. Use ONLY when the user asks for a bare named resolution such as \"480p\", \"720p\", or \"1080p\" without exact pixels or an output orientation. This preserves the source/reference aspect ratio. Do NOT set exact-pixel aspectRatio for bare named resolution requests. If the user says \"720p portrait\" or \"720p landscape\", use exact-pixel aspectRatio instead."
+    },
+    "aspectRatio": {
+      "type": "string",
+      "description": "Do NOT set unless the user explicitly requests an aspect ratio, format, orientation, or exact pixel dimensions. When a reference/source image is used and the user did not ask to change its shape, omit this field so the handler preserves the selected source image's own ratio.\n\nFormats: \"16:9\", \"9:16\", \"4:5\", \"1:1\", \"4:3\", \"3:2\", \"21:9\", or exact pixels like \"1920x1080\".\n\nCRITICAL: When the user specifies exact pixel dimensions (e.g., \"1280x720\", \"1080x1920\", \"1920x1080\", \"3840x2160\") or an orientation-qualified named resolution (e.g., \"720p landscape\", \"720p portrait\"), use the exact pixel format, NOT a ratio like \"16:9\" or \"9:16\". Exact user-requested dimensions override the selected default media quality, including Pro/HQ defaults. A bare named video resolution like \"720p resolution\" is only a resolution tier/short-side request; do not turn it into landscape pixels and do not set aspectRatio unless the user also states landscape, portrait, vertical, horizontal, or exact pixels. If requested pixels are in bounds but not on the model's pixel step, still pass the user's exact pixel request; the handler snaps to the nearest supported size internally. Only use ratio format when the user says a generic format name without pixel dimensions.\n\nMappings (use ONLY when user does NOT specify pixel dimensions): landscape/widescreen/YouTube/cinematic → \"16:9\". portrait → \"9:16\". TikTok/Reels/IG Reels → \"1080x1920\". ultrawide/cinema scope → \"21:9\". Instagram post → \"4:5\". square → \"1:1\". standard/TV → \"4:3\". 720p landscape → \"1280x720\". 720p portrait → \"720x1280\". 1080p landscape → \"1920x1080\". 1080p portrait/HD portrait → \"1080x1920\". 4K landscape → \"3840x2160\". 4K portrait → \"2160x3840\". Never set for generic requests like \"make a video\"."
+    }
+  },
+  "required": [
+    "prompt"
+  ]
+}

package/dist/schemas/tools/stitch_video.schema.json

@@ -0,0 +1,52 @@
+{
+  "$schema": "https://json-schema.org/draft/2020-12/schema",
+  "$id": "https://schemas.sogni.ai/creative-agent/2026-04-27.1/tools/stitch_video.schema.json",
+  "title": "stitch_video arguments",
+  "schemaVersion": "2026-04-27.1",
+  "description": "Combine multiple videos into a single continuous video. Sources can be previously generated clips (non-negative indices into the session video-result array, populated by animate_photo, generate_video, sound_to_video, video_to_video, dance_montage — use videoStartIndex from their results to find the indices) and/or uploaded videos (negative indices: -1 = first uploaded video, -2 = second, etc.). Mix and match in any playback order — for example, pass [0, -1] to play the first generated clip followed by the first uploaded video (a generated bumper followed by the user's existing footage). Use when the user wants to join, merge, concatenate, or combine clips, including when they ask to add a generated bumper / intro / outro / tag / sting to an uploaded video. When the user asks to stitch \"these\" or all uploaded videos and does not name a different playback order, use the current upload/UI order exactly: [-1, -2, ...]. If the user explicitly asks for a different order, honor that requested order. Requires at least 2 source videos in total. Never ask the user to re-upload videos that were already generated or that are already attached to the session. When the user generated music with generate_music in this same session and wants it on the stitch (or asked for a music video / soundtrack), pass a non-negative audioIndex to attach that generated track. When the user uploaded an audio file and wants it overlaid on the stitched video (e.g. \"stitch the audio after\", \"overlay the audio\", \"audio on top of the video\"), pass a negative audioIndex (-1 = first uploaded audio, -2 = second, etc.). In both cases the source clips' own audio is replaced by the chosen track. When the user asks for a fade, dissolve, wipe, or slide between clips, pass `transition`; omit `transition` for a hard cut (the default). Do not use this for alternating/interleaved time slices such as \"alternate 1 second from each video\"; this tool only concatenates whole clips end-to-end. Use repeated replace_video_segment calls with replacementVideoIndex and replacementStartSeconds/replacementEndSeconds for existing-video interleaving.",
+  "type": "object",
+  "additionalProperties": false,
+  "properties": {
+    "videoIndices": {
+      "type": "array",
+      "items": {
+        "type": "number"
+      },
+      "description": "Ordered list of source video indices, in the desired playback order. Non-negative values are 0-based indices into the session generated-video array (results from animate_photo, generate_video, sound_to_video, video_to_video, dance_montage in this conversation). Negative values reference uploaded videos: -1 = first uploaded video, -2 = second, etc. Indices may be mixed — for example, [0, -1] plays the first generated clip followed by the first uploaded video. For vague \"these clips\" / \"all uploaded videos\" requests, use current upload/UI order [-1, -2, ...] unless the user explicitly says to reverse or otherwise reorder them."
+    },
+    "audioIndex": {
+      "type": "number",
+      "description": "Optional index of the audio track to mux onto the stitched output. Non-negative values are 0-based indices into the session generated-audio array (results from generate_music). Negative values reference uploaded audio: -1 = first uploaded audio, -2 = second, etc. When set, the chosen track is muxed onto the stitched output and the source clips' own audio is dropped. Use a non-negative value when the user generated music in the same session or asked for a soundtrack / music video stitch; use a negative value when the user wants their uploaded audio overlaid on the stitched video (e.g. \"stitch the audio after\", \"overlay the audio\"). Omit for a silent or source-audio-preserving stitch."
+    },
+    "transition": {
+      "type": "object",
+      "description": "Optional crossfade between adjacent clips. Omit for a hard-cut concat. When set, every adjacent pair of clips is joined with the same transition type and duration.",
+      "properties": {
+        "type": {
+          "type": "string",
+          "enum": [
+            "fade",
+            "dissolve",
+            "wipeleft",
+            "wiperight",
+            "slideup",
+            "slidedown"
+          ],
+          "description": "\"fade\" / \"dissolve\" = soft mix; \"wipeleft\" / \"wiperight\" = horizontal wipe; \"slideup\" / \"slidedown\" = vertical slide. Maps to ffmpeg xfade transition names."
+        },
+        "durationSeconds": {
+          "type": "number",
+          "minimum": 0.2,
+          "maximum": 2,
+          "description": "Length of the crossfade in seconds. Default 0.5. Capped at 2s."
+        }
+      },
+      "required": [
+        "type"
+      ]
+    }
+  },
+  "required": [
+    "videoIndices"
+  ]
+}

package/dist/schemas/tools/video_to_video.schema.json

@@ -0,0 +1,77 @@
+{
+  "$schema": "https://json-schema.org/draft/2020-12/schema",
+  "$id": "https://schemas.sogni.ai/creative-agent/2026-04-27.1/tools/video_to_video.schema.json",
+  "title": "video_to_video arguments",
+  "schemaVersion": "2026-04-27.1",
+  "description": "Transform an existing video using AI. Uses WAN 2.2 Animate (move/replace) with a reference image to animate a photo with the video's motion or swap the video's subject, LTX-2.3 V2V ControlNet (canny/pose/depth/detailer) for video-only transforms, or Seedance V2V when the user explicitly asks to transform, upscale, enhance, restyle, or remaster an uploaded video with Seedance. Requires an uploaded video file. Use when the user wants to animate a photo with video motion, replace subjects in a video, restyle an existing video, or enhance video quality.",
+  "type": "object",
+  "additionalProperties": false,
+  "properties": {
+    "prompt": {
+      "type": "string",
+      "description": "Describe the TARGET appearance (not the transformation process). 2-4 present-tense sentences.\n\nLITERAL PROMPT OVERRIDE: If the user explicitly says not to modify the prompt, or to use it exactly/verbatim/as-is, copy the identified prompt text verbatim instead of applying these construction rules unless a hard requirement is missing. For Seedance, set expandPrompt=false.\n\nFor LTX-2.3 canny/depth/pose modes, the source video preserves composition, depth, or motion. Spend prompt detail on style, atmosphere, lighting, surface texture, color palette, scale, and pacing.\n\nExamples by mode:\n- animate-move (DEFAULT — WAN 2.2 Animate Move: applies camera/motion from source video to reference image): \"Smooth cinematic camera movement following the subject through the scene.\"\n- animate-replace (WAN 2.2 Animate Replace: replaces the subject in the source video with the reference image): \"The person from the reference photo performing the actions from the video.\"\n- canny (LTX-2.3 — edge-detection restyle): \"Hand-drawn watercolor anime style with soft ink edges, muted teal and coral palette, rain mist, neon reflections, warm rim light, preserving original silhouettes and composition.\"\n- pose (LTX-2.3 — tracks skeleton, replace person): \"A glossy cartoon robot with exaggerated proportions, brushed metal texture, glowing cyan joints, energetic stage lighting, preserving the original dance timing and pose.\"\n- depth (LTX-2.3 — depth-map restyle): \"A misty alpine valley at golden hour, expansive scale, volumetric haze, cool blue shadows, warm rim light, cinematic depth, lingering continuous shot.\"\n- detailer (LTX-2.3 — enhance quality): DESCRIBE THE SOURCE, do not request changes. Append quality qualifiers only. E.g. \"The same scene, ultra-sharp and clean, crisp high-resolution detail, preserving all original content, composition, and color.\" Avoid words like \"enhanced textures\", \"restyled\", or any new subjects/objects — they cause drift.\n- seedance-v2v (BytePlus Dreamina Seedance 2.0 V2V): \"Restyle the source clip in a watercolor look with soft ink edges, while preserving its motion and composition.\" Use natural prose; Seedance reads the reference video holistically rather than via control-net constraints, so describe target style/mood/dialogue rather than control strength.\n\nPresent tense. Positive phrasing. Concrete visual details.\n\nBATCH VARIATIONS: When numberOfVariations > 1, use Dynamic Prompt syntax to vary the artistic treatment while keeping control mode and structural intent consistent. Example: \"transform to {watercolor with soft edges|oil painting with bold strokes|anime with clean lines} style\"."
+    },
+    "expandPrompt": {
+      "type": "boolean",
+      "description": "Seedance only. Whether to run the shared Seedance prompt shaper before dispatch. Defaults to true; set false only when the user explicitly asks to submit the compact prompt directly or not modify the prompt."
+    },
+    "videoSourceIndex": {
+      "type": "number",
+      "description": "Which uploaded video to transform. OMIT this field when there is only one uploaded video — the tool auto-selects it. Only pass when you need to pick among multiple uploaded videos. Indexing: 0-based (0 = first uploaded video, 1 = second). Note: this differs from analyze_video which uses negative indices; this tool also tolerates the negative form (-1 = first uploaded) for convenience."
+    },
+    "controlMode": {
+      "type": "string",
+      "enum": [
+        "animate-move",
+        "animate-replace",
+        "canny",
+        "pose",
+        "depth",
+        "detailer",
+        "seedance-v2v"
+      ],
+      "description": "How the source video and (optional) reference image interact. Pick by user intent:\n• \"animate-move\" (DEFAULT) — WAN 2.2 Animate Move. Applies camera movement and motion from the source video to the reference image, bringing a still photo to life. Requires sourceImageIndex.\n• \"animate-replace\" — WAN 2.2 Animate Replace. Replaces the subject in the source video with the person/character from the reference image, keeping the video's background and motion. Requires sourceImageIndex.\n• \"canny\" — LTX-2.3 edge-detection control. Best for restyling while preserving exact composition and silhouettes (e.g. \"make this footage look like anime / oil painting / watercolor\"). Use for subjects with crisp edges — people, objects, graphics. Video-only; no reference image needed.\n• \"pose\" — LTX-2.3 skeletal tracking. Best for replacing a person while keeping their motion (e.g. \"turn this dancer into a robot\"). Image optional — if provided, controls appearance; otherwise the prompt drives appearance. Requires person-centric motion.\n• \"depth\" — LTX-2.3 depth-map control. Best for restyling scenes with perspective, camera movement, or volumetric content (landscapes, interiors, camera pans). Preserves 3D spatial layout rather than 2D edges; more forgiving than canny when edges are noisy. Video-only.\n• \"detailer\" — LTX-2.3 quality enhancement. Sharpens detail and texture WITHOUT restyling. The prompt must DESCRIBE THE ORIGINAL scene with quality qualifiers (sharp, clean, high-resolution) — never request content changes, new textures, or a new look. Pick this when the user asks to \"improve quality\", \"enhance\", \"upscale\", or \"sharpen\" without a creative transformation.\n• \"seedance-v2v\" — BytePlus Dreamina Seedance 2.0 video-to-video. Use only when the user explicitly asks for Seedance on the uploaded source video, such as Seedance Fast upscale, enhance, remaster, restyle, or transform. High-fidelity quality, native audio, time-coded scene control. Seedance V2V reads @Video1 holistically. Use it for restyling, motion transfer, extension, subject replacement, or scene transformation, and assign @Video1 a clear role such as source clip, camera movement, action timing, edit rhythm, or continuation anchor. Distinct from canny/depth/pose which use control-net constraints — Seedance treats the reference video holistically.\nCanny vs depth: canny preserves silhouettes and fine outlines — pick it for subject-led scenes and graphic restyles. Depth preserves 3D structure — pick it for scenes where the camera moves or spatial layout matters more than edge fidelity. Default: \"animate-move\"."
+    },
+    "negativePrompt": {
+      "type": "string",
+      "description": "Non-Seedance only. Optional negative prompt for LTX/Wan video-to-video models. Do not set when controlMode is seedance-v2v or videoModel is seedance2/seedance2-fast; rewrite user-provided Seedance avoid/ban/no-X requests as positive prompt instructions."
+    },
+    "videoModel": {
+      "type": "string",
+      "enum": [
+        "ltx23-v2v",
+        "wan22-animate",
+        "seedance2",
+        "seedance2-fast"
+      ],
+      "description": "Model selector for this video-to-video request. Usually omit; controlMode chooses the non-Seedance model. For controlMode=\"seedance-v2v\", use \"seedance2-fast\" by default, especially when the user asks for Seedance Fast/seedance-fast or 480p/720p. Use \"seedance2\" only when the user explicitly asks for the full/non-fast Seedance model or 1080p."
+    },
+    "generateAudio": {
+      "type": "boolean",
+      "description": "Seedance V2V only. Whether Seedance should generate/retain a native audio track. Omit by default; set false only when the user explicitly asks for silent output or no audio. Use only with controlMode=\"seedance-v2v\"."
+    },
+    "targetResolution": {
+      "type": "number",
+      "description": "Seedance V2V only. Short-side output resolution target in pixels. Use when the user asks for a bare named resolution such as \"480p\", \"720p\", or \"1080p\" without exact dimensions. For Seedance V2V fast, 480p and 720p are supported; preserve the source video shape instead of forcing landscape pixels."
+    },
+    "sourceImageIndex": {
+      "type": "number",
+      "description": "Optional index of a reference image (0-based). Required for \"animate-move\" and \"animate-replace\". Optional for \"pose\" (controls appearance if provided). Ignored by \"canny\", \"depth\", and \"detailer\"."
+    },
+    "duration": {
+      "type": "number",
+      "description": "Output video duration in seconds. Range: 2-20 for WAN/LTX modes and 4-15 for controlMode=\"seedance-v2v\". If omitted, the tool matches the uploaded source video duration when available (capped to the selected model range); otherwise it falls back to 10s for WAN Animate Move/Replace and 5s for LTX-2.3/Seedance modes. For long stitched/bulk WAN Animate Move/Replace work with no explicit per-clip length, prefer about 10s clips rather than 5s chunks. Only pass this when the user explicitly requests a different length.",
+      "minimum": 2,
+      "maximum": 20
+    },
+    "numberOfVariations": {
+      "type": "number",
+      "description": "Number of video variations to generate (1-16). Default: 1.",
+      "minimum": 1,
+      "maximum": 16
+    }
+  },
+  "required": [
+    "prompt"
+  ]
+}

package/dist/schemas/workflows/durable-workflow-run.schema.json

@@ -0,0 +1,165 @@
+{
+  "$schema": "https://json-schema.org/draft/2020-12/schema",
+  "$id": "https://schemas.sogni.ai/creative-agent/2026-04-27.1/workflows/durable-workflow-run.schema.json",
+  "title": "Creative agent durable workflow run contract",
+  "schemaVersion": "2026-04-27.1",
+  "type": "object",
+  "additionalProperties": false,
+  "properties": {
+    "workflowId": { "type": "string" },
+    "status": { "type": "string", "enum": ["queued", "running", "completed", "partial_failure", "waiting_for_user", "failed", "cancelled"] },
+    "backbone": {
+      "type": "object",
+      "additionalProperties": false,
+      "properties": {
+        "schemaVersion": { "type": "string" },
+        "modelKnowledgeVersion": { "type": "string" },
+        "routingPolicyVersion": { "type": "string" }
+      },
+      "required": ["schemaVersion", "modelKnowledgeVersion", "routingPolicyVersion"]
+    },
+    "title": { "type": "string" },
+    "input": { "type": "object", "additionalProperties": true },
+    "steps": {
+      "type": "array",
+      "minItems": 1,
+      "items": {
+        "type": "object",
+        "additionalProperties": false,
+        "properties": {
+          "id": { "type": "string" },
+          "sequence": { "type": "integer", "minimum": 0 },
+          "toolName": {
+            "type": "string",
+            "enum": [
+              "generate_image",
+              "generate_video",
+              "generate_music",
+              "edit_image",
+              "apply_style",
+              "restore_photo",
+              "refine_result",
+              "animate_photo",
+              "change_angle",
+              "video_to_video",
+              "stitch_video",
+              "orbit_video",
+              "dance_montage",
+              "sound_to_video",
+              "extend_video",
+              "replace_video_segment",
+              "overlay_video",
+              "add_subtitles",
+              "analyze_image",
+              "analyze_video",
+              "extract_metadata",
+              "ask_clarifying_question",
+              "finalize_response",
+              "create_asset_manifest",
+              "inspect_asset",
+              "label_asset",
+              "map_assets_for_model",
+              "validate_asset_references"
+            ]
+          },
+          "arguments": { "type": "object", "additionalProperties": true },
+          "dependsOn": {
+            "type": "array",
+            "items": {
+              "type": "object",
+              "additionalProperties": false,
+              "properties": {
+                "sourceStepId": { "type": "string" },
+                "targetArgument": { "type": "string" },
+                "transform": {
+                  "type": "string",
+                  "enum": [
+                    "artifact_url",
+                    "artifact_data_uri",
+                    "image_url",
+                    "video_url",
+                    "audio_url",
+                    "image_index",
+                    "video_index",
+                    "audio_index",
+                    "subtitle_cues",
+                    "subtitle_srt",
+                    "overlay_items",
+                    "asset_ref"
+                  ]
+                },
+                "sourceArtifactId": { "type": "string" },
+                "sourceArtifactIndex": { "type": "integer", "minimum": 0 },
+                "mediaType": { "type": "string", "enum": ["image", "video", "audio"] },
+                "required": { "type": "boolean" }
+              },
+              "required": ["sourceStepId", "targetArgument", "transform"]
+            }
+          }
+        },
+        "required": ["id", "sequence", "toolName", "arguments"]
+      }
+    },
+    "events": {
+      "type": "array",
+      "items": { "type": "object", "additionalProperties": true }
+    },
+    "artifacts": {
+      "type": "array",
+      "items": { "type": "object", "additionalProperties": true }
+    },
+    "lease": {
+      "type": "object",
+      "additionalProperties": false,
+      "properties": {
+        "leaseId": { "type": "string" },
+        "ownerId": { "type": "string" },
+        "acquiredAt": { "type": "string", "format": "date-time" },
+        "heartbeatAt": { "type": "string", "format": "date-time" },
+        "expiresAt": { "type": "string", "format": "date-time" }
+      },
+      "required": ["leaseId", "ownerId", "acquiredAt", "heartbeatAt", "expiresAt"]
+    },
+    "recovery": {
+      "type": "object",
+      "additionalProperties": false,
+      "properties": {
+        "resumeCount": { "type": "integer", "minimum": 0 },
+        "lastResumeAt": { "type": "string", "format": "date-time" },
+        "lastRecoveredAt": { "type": "string", "format": "date-time" },
+        "reason": { "type": "string" }
+      },
+      "required": ["resumeCount"]
+    },
+    "quality": {
+      "type": "object",
+      "additionalProperties": true,
+      "properties": {
+        "postflightAudits": {
+          "type": "array",
+          "items": { "type": "object", "additionalProperties": true }
+        }
+      }
+    },
+    "timestamps": {
+      "type": "object",
+      "additionalProperties": false,
+      "properties": {
+        "createdAt": { "type": "string", "format": "date-time" },
+        "updatedAt": { "type": "string", "format": "date-time" },
+        "completedAt": { "type": "string", "format": "date-time" }
+      },
+      "required": ["createdAt", "updatedAt"]
+    }
+  },
+  "required": [
+    "workflowId",
+    "status",
+    "backbone",
+    "input",
+    "steps",
+    "events",
+    "artifacts",
+    "timestamps"
+  ]
+}

package/dist/schemas/workflows/durable-workflow-step.schema.json

@@ -0,0 +1,141 @@
+{
+  "$schema": "https://json-schema.org/draft/2020-12/schema",
+  "$id": "https://schemas.sogni.ai/creative-agent/2026-04-27.1/workflows/durable-workflow-step.schema.json",
+  "title": "Creative agent durable workflow step metadata",
+  "schemaVersion": "2026-04-27.1",
+  "type": "object",
+  "additionalProperties": false,
+  "properties": {
+    "id": { "type": "string" },
+    "workflowId": { "type": "string" },
+    "sequence": { "type": "integer", "minimum": 0 },
+    "status": { "type": "string", "enum": ["queued", "running", "completed", "partial_failure", "waiting_for_user", "failed", "cancelled"] },
+    "backbone": {
+      "type": "object",
+      "additionalProperties": false,
+      "properties": {
+        "schemaVersion": { "type": "string" },
+        "modelKnowledgeVersion": { "type": "string" },
+        "routingPolicyVersion": { "type": "string" }
+      },
+      "required": ["schemaVersion", "modelKnowledgeVersion", "routingPolicyVersion"]
+    },
+    "implementation": {
+      "type": "object",
+      "additionalProperties": false,
+      "properties": {
+        "runtime": { "type": "string", "enum": ["sogni-chat", "sogni-api", "sogni-client", "creative-agent", "other"] },
+        "version": { "type": "string" }
+      },
+      "required": ["runtime", "version"]
+    },
+    "tool": {
+      "type": "object",
+      "additionalProperties": false,
+      "properties": {
+        "name": { "type": "string" },
+        "schemaVersion": { "type": "string" }
+      },
+      "required": ["name", "schemaVersion"]
+    },
+    "input": {
+      "type": "object",
+      "additionalProperties": false,
+      "properties": {
+        "arguments": { "type": "object", "additionalProperties": true },
+        "normalizedArguments": { "type": "object", "additionalProperties": true }
+      },
+      "required": ["arguments", "normalizedArguments"]
+    },
+    "generation": {
+      "type": "object",
+      "additionalProperties": false,
+      "properties": {
+        "selectedModel": { "type": "string" },
+        "params": { "type": "object", "additionalProperties": true }
+      },
+      "required": ["selectedModel", "params"]
+    },
+    "routing": {
+      "type": "object",
+      "additionalProperties": false,
+      "properties": {
+        "selectedBy": { "type": "string" },
+        "reasons": { "type": "array", "items": { "type": "string" } },
+        "alternatives": {
+          "type": "array",
+          "items": {
+            "type": "object",
+            "additionalProperties": false,
+            "properties": {
+              "modelId": { "type": "string" },
+              "available": { "type": "boolean" },
+              "reason": { "type": "string" }
+            },
+            "required": ["modelId"]
+          }
+        }
+      },
+      "required": ["selectedBy", "reasons", "alternatives"]
+    },
+    "cost": {
+      "type": "object",
+      "additionalProperties": false,
+      "properties": {
+        "estimate": {
+          "type": "object",
+          "additionalProperties": false,
+          "properties": {
+            "costClass": { "type": "string" },
+            "unit": { "type": "string", "enum": ["image", "second", "operation"] },
+            "quantity": { "type": "number", "minimum": 0 }
+          },
+          "required": ["costClass", "unit", "quantity"]
+        },
+        "actual": { "type": "object", "additionalProperties": true }
+      },
+      "required": ["estimate"]
+    },
+    "artifacts": {
+      "type": "array",
+      "items": { "type": "object", "additionalProperties": true }
+    },
+    "idempotencyKey": { "type": "string" },
+    "retry": {
+      "type": "object",
+      "additionalProperties": false,
+      "properties": {
+        "count": { "type": "integer", "minimum": 0 },
+        "classification": { "type": "string", "enum": ["none", "transient", "permanent", "unknown"] }
+      },
+      "required": ["count", "classification"]
+    },
+    "timestamps": {
+      "type": "object",
+      "additionalProperties": false,
+      "properties": {
+        "createdAt": { "type": "string", "format": "date-time" },
+        "updatedAt": { "type": "string", "format": "date-time" },
+        "completedAt": { "type": "string", "format": "date-time" }
+      },
+      "required": ["createdAt", "updatedAt"]
+    }
+  },
+  "required": [
+    "id",
+    "workflowId",
+    "sequence",
+    "status",
+    "backbone",
+    "implementation",
+    "tool",
+    "input",
+    "generation",
+    "routing",
+    "cost",
+    "artifacts",
+    "idempotencyKey",
+    "retry",
+    "timestamps"
+  ]
+}

package/dist/skill-runtime-source/crossSurfaceParity.d.ts

@@ -0,0 +1,23 @@
+export type CrossSurfaceParitySurface = 'chat' | 'api_chat_completions' | 'api_creative_agent_workflows' | 'public_skill';
+export type CrossSurfaceParityFocus = 'subtitles' | 'overlay' | 'uploaded_video_edits' | 'asset_manifest_sequence' | 'cancellation' | 'duplicate_start' | 'skill_media_refs' | 'generated_video_rerender' | 'seedance_storyboard_rerender' | 'image_selection_wait' | 'stitch_after_batch' | 'durable_chat_run_completion_after_close' | 'durable_chat_run_resume_after_worker_restart' | 'durable_chat_run_waiting_for_user' | 'sdk_flat_namespace_rest_parity' | 'api_socket_session_reuse' | 'public_skill_sdk_transport';
+export interface CrossSurfaceParityExpectation {
+    surface: CrossSurfaceParitySurface;
+    entrypoint: string;
+    expectedTools?: string[];
+    expectedRequest?: Record<string, unknown>;
+    expectedBehavior?: string[];
+}
+export interface CrossSurfaceParityFixture {
+    id: string;
+    focus: CrossSurfaceParityFocus;
+    description: string;
+    userText: string;
+    mediaReferences?: Array<{
+        kind: 'image' | 'video' | 'audio';
+        filename: string;
+    }>;
+    expectations: CrossSurfaceParityExpectation[];
+}
+export declare const CROSS_SURFACE_PARITY_SURFACES: CrossSurfaceParitySurface[];
+export declare const CROSS_SURFACE_PARITY_FIXTURES: CrossSurfaceParityFixture[];
+//# sourceMappingURL=crossSurfaceParity.d.ts.map

package/dist/skill-runtime-source/crossSurfaceParity.d.ts.map

@@ -0,0 +1 @@
+{"version":3,"file":"crossSurfaceParity.d.ts","sourceRoot":"","sources":["../../src/skill-runtime-source/crossSurfaceParity.ts"],"names":[],"mappings":"AAAA,MAAM,MAAM,yBAAyB,GACjC,MAAM,GACN,sBAAsB,GACtB,8BAA8B,GAC9B,cAAc,CAAC;AAEnB,MAAM,MAAM,uBAAuB,GAC/B,WAAW,GACX,SAAS,GACT,sBAAsB,GACtB,yBAAyB,GACzB,cAAc,GACd,iBAAiB,GACjB,kBAAkB,GAClB,0BAA0B,GAC1B,8BAA8B,GAC9B,sBAAsB,GACtB,oBAAoB,GACpB,yCAAyC,GACzC,8CAA8C,GAC9C,mCAAmC,GACnC,gCAAgC,GAChC,0BAA0B,GAC1B,4BAA4B,CAAC;AAEjC,MAAM,WAAW,6BAA6B;IAC5C,OAAO,EAAE,yBAAyB,CAAC;IACnC,UAAU,EAAE,MAAM,CAAC;IACnB,aAAa,CAAC,EAAE,MAAM,EAAE,CAAC;IACzB,eAAe,CAAC,EAAE,MAAM,CAAC,MAAM,EAAE,OAAO,CAAC,CAAC;IAC1C,gBAAgB,CAAC,EAAE,MAAM,EAAE,CAAC;CAC7B;AAED,MAAM,WAAW,yBAAyB;IACxC,EAAE,EAAE,MAAM,CAAC;IACX,KAAK,EAAE,uBAAuB,CAAC;IAC/B,WAAW,EAAE,MAAM,CAAC;IACpB,QAAQ,EAAE,MAAM,CAAC;IACjB,eAAe,CAAC,EAAE,KAAK,CAAC;QACtB,IAAI,EAAE,OAAO,GAAG,OAAO,GAAG,OAAO,CAAC;QAClC,QAAQ,EAAE,MAAM,CAAC;KAClB,CAAC,CAAC;IACH,YAAY,EAAE,6BAA6B,EAAE,CAAC;CAC/C;AAED,eAAO,MAAM,6BAA6B,EAAE,yBAAyB,EAKpE,CAAC;AAEF,eAAO,MAAM,6BAA6B,EAAE,yBAAyB,EAwdpE,CAAC"}