makaron-cli 0.8.2 → 0.8.4

package/.claude-plugin/plugin.json

@@ -1,6 +1,6 @@
 {
   "name": "makaron-cli",
-  "version": "0.7.3",
+  "version": "0.8.4",
   "description": "AI image editing, video generation, and music creation via CLI. Agents can self-register, create projects, and produce creative media.",
   "author": {
     "name": "Makaron AI",

package/.codex-plugin/plugin.json

@@ -1,6 +1,6 @@
 {
   "name": "makaron-cli",
-  "version": "0.7.3",
+  "version": "0.8.4",
   "description": "AI image editing, video generation, and music creation via CLI. Agents can self-register, create projects, and produce creative media.",
   "displayName": "Makaron",
   "shortDescription": "AI image/video/music creation from the terminal",

package/README.md

@@ -97,6 +97,16 @@ Returns immediately:
 npx makaron-cli chat --project <id> --image ref1.jpg --image ref2.jpg -b "use these as style reference"
 ```
 
+### Inspect existing timeline media
+
+Before starting a follow-up run on an existing project, list the current timeline media so you know what assets are available and which `<<<media_N>>>` references to use:
+
+```bash
+npx makaron-cli project media <projectId> --json
+```
+
+This is project-scoped. `responses get <runId> --pick output` only returns artifacts from one run; `project media` returns the whole project timeline: original uploads, references, generated images, video snapshots, and editable compositions.
+
 ### With video input (MP4/MOV/WebM)
 
 ```bash
@@ -110,8 +120,8 @@ npx makaron-cli chat --project <id> --video party.mp4 --image kid.jpg -b "make t
 npx makaron-cli chat --project <id> --video clip1.mp4 --video clip2.mp4 -b "splice these into one seamless video"
 ```
 
-Video files are uploaded via signed URL. CLI local video uploads follow the same compatibility contract as the normal frontend flow: `.mp4`, `.mov`, or `.webm`, max 200MB, target max 15s with 0.5s metadata tolerance, and <=1080p / 2,086,876 frame pixels. The frontend can transcode oversized videos; the CLI rejects them so later Seedance editing does not fail.
-The agent understands video content natively — it can analyze scenes, edit, extend, and compose videos. Seedance video-reference editing is supported for ~15s videos that meet the same upload limits; Kling remains the base/direct edit path.
+Video files are uploaded via signed URL. CLI local video uploads support `.mp4`, `.mov`, or `.webm`, max 50MB, max 120s with 1s metadata tolerance, and <=1080p / 2,086,876 frame pixels. The frontend can transcode larger videos before upload; the CLI uploads directly to Storage and rejects videos above those limits.
+The agent understands video content natively — it can analyze scenes, edit, extend, and compose videos. Seedance video-reference editing is still limited to ~15s provider references, so longer uploaded videos should be split/prepared by the agent before model submission; Kling remains the base/direct edit path.
 Use `chat --project <id|auto> --video ...` for any project/timeline video work. Direct `video create` is standalone and does not write timeline entries.
 
 ### Check status (single query)
@@ -134,64 +144,6 @@ Outputs one JSON per line as artifacts appear:
 {"event":"done","status":"completed"}
 ```
 
-### New Agent quickstart
-
-For a new Agent, keep the default service flow to two response commands:
-
-```bash
-npx makaron-cli responses next <runId> --json
-npx makaron-cli responses handle <messageId> --run <runId> --choice approve
-npx makaron-cli responses deliver <artifactId> --run <runId> --channel feishu --message-id <messageId>
-```
-
-`responses next` emits a compact timeline, detects text-only checkpoints for creative/service work, and returns `next_commands` when the Agent must handle a Makaron message before waiting for artifacts. It exits with code `3` on an unhandled checkpoint so wrappers stop instead of silently waiting. After handling a checkpoint, run the returned `next_commands.inspect` command to continue. While the run is still generating, it returns `status: "running"` and `blocking: false`. If completed image/video artifacts exist and have not been delivered, it returns `status: "has_artifacts"` and `blocking: true` with compact `undelivered_artifacts` entries containing `kind`, `status`, `url`, `fileName`, and `contentType` when available, plus `next_commands.deliver`; the Agent must send the artifact URL to the user, then record delivery with `responses deliver`. A non-checkpoint response returns `status: "ready"` or `status: "delivered"`. If a run failed, `responses next --json` prints `status: "failed"` and `blocking: true` plus `error.type`, `error.message`, `error.recoverable`, `error.detail`, and `next_command` to stdout before exiting `1`, so wrappers can parse the failure without scraping stderr. Use `--no-fail` to inspect checkpoint JSON without failing. For pure Q&A runs, use:
-
-```bash
-npx makaron-cli responses next <runId> --json --checkpoint-mode off
-```
-
-`responses handle` is the single checkpoint action command. Valid choices are `approve`, `revise`, `ask_user`, and `continue`. `responses deliver` records that a completed artifact was actually delivered to the user, preventing repeated delivery prompts.
-
-### Dialogue events for external Agents
-
-Use this when another Agent needs to read what Makaron said, handle text checkpoints, and relay artifacts without inventing customer-service wording.
-
-```bash
-npx makaron-cli responses events <runId> --jsonl
-# alias: npx makaron-cli responses timeline <runId> --jsonl
-# compact view: npx makaron-cli responses timeline <runId> --jsonl --compact
-# pure Q&A view: npx makaron-cli responses timeline <runId> --jsonl --checkpoint-mode off
-```
-
-`events` and `timeline` are lower-level commands. New Agents should start with `responses next` and use these only when they need raw event streams.
-
-Events use only three factual types:
-
-```json
-{"type":"message","id":"msg_1","runId":"run_xxx","seq":1,"text":"Makaron original message","requires_approval":true,"approval_options":["approve","revise","ask_user","continue"]}
-{"type":"approval","messageId":"msg_1","choice":"approve","status":"recorded"}
-{"type":"artifact","kind":"image","status":"completed","url":"https://..."}
-```
-
-Makaron uses a conservative checkpoint rule for creative/service Agents: if a run stops with substantive text, has no image/video/music/design artifact, and has no continuing execution action such as a tool call, the message is marked `requires_approval: true`. Pure status text such as queued, rendering, uploading, or completed is not treated as a checkpoint. Pure Q&A flows should pass `--checkpoint-mode off`. If a message has `requires_approval: true`, the external Agent must record an approval before continuing to wait for artifacts or claiming completion:
-
-```bash
-npx makaron-cli responses approve msg_1 --run <runId> --note "Proceed."
-npx makaron-cli responses revise msg_1 --run <runId> "make it softer"
-npx makaron-cli responses ask-user msg_1 --run <runId>
-npx makaron-cli responses continue msg_1 --run <runId>
-npx makaron-cli responses handle msg_1 --run <runId> --choice approve
-```
-
-Important: approvals are a local Agent gate in v0. They are recorded by the CLI so wrappers and Skills can fail fast, but they do not pause or resume the remote Makaron runtime yet. Wrappers can enforce the local gate with:
-
-```bash
-npx makaron-cli responses events <runId> --jsonl --checkpoint-mode service --fail-on-unapproved
-# alias: npx makaron-cli responses timeline <runId> --jsonl --compact --fail-on-unapproved
-```
-
-Use `--compact` when relaying to another Agent or chat system; it merges consecutive Makaron content chunks into a single readable message.
-
 ### Extract specific results
 
 ```bash
@@ -254,9 +206,9 @@ For project/timeline video editing, use:
 npx makaron-cli chat --project <id|auto> --video input.mp4 -b "make it funny"
 ```
 
-Options for `video create`: `--script "..."`, `--script-file <path>`, `--image <url>` (repeatable, up to 7), `--video <file|url>`, `--duration 3|5|7|10|15`, `--aspect 9:16|16:9|1:1`, `--model kling|seedance`
+Options for `video create`: `--script "..."`, `--script-file <path>`, `--image <url>` (repeatable, up to 7), `--video <file|url>`, `--duration <seconds>`, `--aspect 9:16|16:9|1:1`, `--model kling|seedance`. SeeDance accepts integer output duration 4-15s (default 5s); Kling supports 5-15s.
 
-Video edit model behavior: `--model kling --video` uses Kling base/direct edit internally; `--model seedance --video` uses the Seedance video-reference path and requires target <=15s, <=1080p input. Tiny metadata padding up to 15.5s is accepted and output duration is clamped to 15s.
+Video edit model behavior: `--model kling --video` uses Kling base/direct edit internally; `--model seedance --video` uses the Seedance video-reference path and requires target <=15s, <=50MB, width/height 300-6000px, aspect ratio 0.4-2.5, and frame pixels 409,600-2,086,876. Tiny metadata padding up to 15.5s is accepted and output duration is clamped to 15s.
 
 ### `music` — Music generation
 
@@ -321,41 +273,6 @@ type MakaronOutput =
 | Motion design | "create an Instagram story with animated text" |
 | Multi-step | "edit the photo then make a video from it" |
 
-## Minimal Agent Wrapper
-
-A new Agent can use this minimal flow:
-
-```bash
-RUN_JSON=$(npx makaron-cli chat --project auto --json -b "$USER_PROMPT")
-RUN_ID=$(echo "$RUN_JSON" | jq -r .runId)
-PROJECT_URL=$(echo "$RUN_JSON" | jq -r .projectUrl)
-send_message "Project created: $PROJECT_URL"
-
-if ! NEXT=$(npx makaron-cli responses next "$RUN_ID" --json); then
-  STATUS=$(echo "$NEXT" | jq -r .status)
-  if [ "$STATUS" = "needs_approval" ]; then
-    MSG_ID=$(echo "$NEXT" | jq -r .checkpoint.id)
-    TEXT=$(echo "$NEXT" | jq -r .checkpoint.text)
-    send_message "$TEXT"
-    npx makaron-cli responses handle "$MSG_ID" --run "$RUN_ID" --choice ask_user
-    exit 3
-  elif [ "$STATUS" = "failed" ]; then
-    send_message "$(echo "$NEXT" | jq -r .error.message)"
-    exit 1
-  fi
-fi
-
-NEXT=$(npx makaron-cli responses next "$RUN_ID" --json --no-fail)
-if [ "$(echo "$NEXT" | jq -r .status)" = "has_artifacts" ]; then
-  ARTIFACT_ID=$(echo "$NEXT" | jq -r ".undelivered_artifacts[0].id")
-  ARTIFACT_URL=$(echo "$NEXT" | jq -r ".undelivered_artifacts[0].url")
-  DELIVERY_MESSAGE_ID=$(send_message "$ARTIFACT_URL")
-  npx makaron-cli responses deliver "$ARTIFACT_ID" --run "$RUN_ID" --channel feishu --message-id "$DELIVERY_MESSAGE_ID"
-fi
-
-RESULT=$(npx makaron-cli responses get "$RUN_ID" --wait --json)
-```
-
 ## Recommended Pattern: Service Flow (Feishu/OpenClaw/Group Chat)
 
 When serving end-users in a chat environment (Feishu, Slack, Discord), use this proactive message pattern:

package/SKILL.md

@@ -86,6 +86,16 @@ Returns immediately:
 npx makaron-cli chat --project <id> --image ref1.jpg --image ref2.jpg -b "use these as style reference"
 ```
 
+### Inspect existing timeline media
+
+Before starting a follow-up run on an existing project, list the current timeline media so you know what assets are available and which `<<<media_N>>>` references to use:
+
+```bash
+npx makaron-cli project media <projectId> --json
+```
+
+This is project-scoped. `responses get <runId> --pick output` only returns artifacts from one run; `project media` returns the whole project timeline: original uploads, references, generated images, video snapshots, and editable compositions.
+
 ### With video input (edit, compose, extend)
 
 ```bash
@@ -102,7 +112,7 @@ npx makaron-cli chat --project <id> --video clip1.mp4 --video clip2.mp4 -b "comb
 npx makaron-cli chat --project auto --video https://example.com/dance.mp4 -b "extend this to 15 seconds"
 ```
 
-Supported formats: MP4, MOV, WebM. CLI local video uploads follow the same compatibility contract as the normal frontend flow: max 200MB, target max 15s with 0.5s metadata tolerance, and <=1080p / 2,086,876 frame pixels. The frontend can transcode oversized videos; the CLI rejects them so later Seedance editing does not fail. Videos are uploaded to the project timeline. The Agent can analyze scenes, edit content, compose multiple clips, extend duration, and add effects — all via natural language. Seedance video-reference editing is supported for ~15s videos that meet these upload limits; Kling remains the base/direct edit path.
+Supported formats: MP4, MOV, WebM. CLI local video uploads support max 50MB, max 120s with 1s metadata tolerance, and <=1080p / 2,086,876 frame pixels. The frontend can transcode larger videos before upload; the CLI uploads directly to Storage and rejects videos above those limits. Videos are uploaded to the project timeline. The Agent can analyze scenes, edit content, compose multiple clips, extend duration, and add effects — all via natural language. Seedance video-reference editing is still limited to ~15s provider references, so longer uploaded videos should be split/prepared by the agent before model submission; Kling remains the base/direct edit path.
 
 Use `chat --project <id|auto> --video ...` for any project/timeline video work. Direct video commands are standalone raw-tool calls.
 
@@ -126,64 +136,6 @@ Outputs one JSON per line as artifacts appear:
 {"event":"done","status":"completed"}
 ```
 
-### New Agent quickstart
-
-For a new Agent, keep the default service flow to two response commands:
-
-```bash
-npx makaron-cli responses next <runId> --json
-npx makaron-cli responses handle <messageId> --run <runId> --choice approve
-npx makaron-cli responses deliver <artifactId> --run <runId> --channel feishu --message-id <messageId>
-```
-
-`responses next` emits a compact timeline, detects text-only checkpoints for creative/service work, and returns `next_commands` when the Agent must handle a Makaron message before waiting for artifacts. It exits with code `3` on an unhandled checkpoint so wrappers stop instead of silently waiting. After handling a checkpoint, run the returned `next_commands.inspect` command to continue. While the run is still generating, it returns `status: "running"` and `blocking: false`. If completed image/video artifacts exist and have not been delivered, it returns `status: "has_artifacts"` and `blocking: true` with compact `undelivered_artifacts` entries containing `kind`, `status`, `url`, `fileName`, and `contentType` when available, plus `next_commands.deliver`; the Agent must send the artifact URL to the user, then record delivery with `responses deliver`. A non-checkpoint response returns `status: "ready"` or `status: "delivered"`. If a run failed, `responses next --json` prints `status: "failed"` and `blocking: true` plus `error.type`, `error.message`, `error.recoverable`, `error.detail`, and `next_command` to stdout before exiting `1`, so wrappers can parse the failure without scraping stderr. Use `--no-fail` to inspect checkpoint JSON without failing. For pure Q&A runs, use:
-
-```bash
-npx makaron-cli responses next <runId> --json --checkpoint-mode off
-```
-
-`responses handle` is the single checkpoint action command. Valid choices are `approve`, `revise`, `ask_user`, and `continue`. `responses deliver` records that a completed artifact was actually delivered to the user, preventing repeated delivery prompts.
-
-### Dialogue events for external Agents
-
-Use this when another Agent needs to read what Makaron said, handle text checkpoints, and relay artifacts without inventing customer-service wording.
-
-```bash
-npx makaron-cli responses events <runId> --jsonl
-# alias: npx makaron-cli responses timeline <runId> --jsonl
-# compact view: npx makaron-cli responses timeline <runId> --jsonl --compact
-# pure Q&A view: npx makaron-cli responses timeline <runId> --jsonl --checkpoint-mode off
-```
-
-`events` and `timeline` are lower-level commands. New Agents should start with `responses next` and use these only when they need raw event streams.
-
-Events use only three factual types:
-
-```json
-{"type":"message","id":"msg_1","runId":"run_xxx","seq":1,"text":"Makaron original message","requires_approval":true,"approval_options":["approve","revise","ask_user","continue"]}
-{"type":"approval","messageId":"msg_1","choice":"approve","status":"recorded"}
-{"type":"artifact","kind":"image","status":"completed","url":"https://..."}
-```
-
-Makaron uses a conservative checkpoint rule for creative/service Agents: if a run stops with substantive text, has no image/video/music/design artifact, and has no continuing execution action such as a tool call, the message is marked `requires_approval: true`. Pure status text such as queued, rendering, uploading, or completed is not treated as a checkpoint. Pure Q&A flows should pass `--checkpoint-mode off`. If a message has `requires_approval: true`, the external Agent must record an approval before continuing to wait for artifacts or claiming completion:
-
-```bash
-npx makaron-cli responses approve msg_1 --run <runId> --note "Proceed."
-npx makaron-cli responses revise msg_1 --run <runId> "make it softer"
-npx makaron-cli responses ask-user msg_1 --run <runId>
-npx makaron-cli responses continue msg_1 --run <runId>
-npx makaron-cli responses handle msg_1 --run <runId> --choice approve
-```
-
-Important: approvals are a local Agent gate in v0. They are recorded by the CLI so wrappers and Skills can fail fast, but they do not pause or resume the remote Makaron runtime yet. Wrappers can enforce the local gate with:
-
-```bash
-npx makaron-cli responses events <runId> --jsonl --checkpoint-mode service --fail-on-unapproved
-# alias: npx makaron-cli responses timeline <runId> --jsonl --compact --fail-on-unapproved
-```
-
-Use `--compact` when relaying to another Agent or chat system; it merges consecutive Makaron content chunks into a single readable message.
-
 ### Extract specific results
 
 ```bash
@@ -246,9 +198,9 @@ npx makaron-cli video status <taskId>
 npx makaron-cli chat --project <id|auto> --video input.mp4 -b "make it funny"
 ```
 
-Options for `video create`: `--script "..."`, `--script-file <path>`, `--image <url>` (repeatable, up to 7), `--video <file|url>`, `--duration 3|5|7|10|15`, `--aspect 9:16|16:9|1:1`, `--model kling|seedance`
+Options for `video create`: `--script "..."`, `--script-file <path>`, `--image <url>` (repeatable, up to 7), `--video <file|url>`, `--duration <seconds>`, `--aspect 9:16|16:9|1:1`, `--model kling|seedance`. SeeDance accepts integer output duration 4-15s (default 5s); Kling supports 5-15s.
 
-Video edit model behavior: `--model kling --video` uses Kling base/direct edit internally; `--model seedance --video` uses the Seedance video-reference path and requires target <=15s, <=1080p input. Tiny metadata padding up to 15.5s is accepted and output duration is clamped to 15s.
+Video edit model behavior: `--model kling --video` uses Kling base/direct edit internally; `--model seedance --video` uses the Seedance video-reference path and requires target <=15s, <=50MB, width/height 300-6000px, aspect ratio 0.4-2.5, and frame pixels 409,600-2,086,876. Tiny metadata padding up to 15.5s is accepted and output duration is clamped to 15s.
 
 ### `music` — Music generation
 
@@ -310,41 +262,6 @@ type MakaronOutput =
 | Motion design | "create an Instagram story with animated text" |
 | Multi-step | "edit the photo then make a video from it" |
 
-## Minimal Agent Wrapper
-
-A new Agent can use this minimal flow:
-
-```bash
-RUN_JSON=$(npx makaron-cli chat --project auto --json -b "$USER_PROMPT")
-RUN_ID=$(echo "$RUN_JSON" | jq -r .runId)
-PROJECT_URL=$(echo "$RUN_JSON" | jq -r .projectUrl)
-send_message "Project created: $PROJECT_URL"
-
-if ! NEXT=$(npx makaron-cli responses next "$RUN_ID" --json); then
-  STATUS=$(echo "$NEXT" | jq -r .status)
-  if [ "$STATUS" = "needs_approval" ]; then
-    MSG_ID=$(echo "$NEXT" | jq -r .checkpoint.id)
-    TEXT=$(echo "$NEXT" | jq -r .checkpoint.text)
-    send_message "$TEXT"
-    npx makaron-cli responses handle "$MSG_ID" --run "$RUN_ID" --choice ask_user
-    exit 3
-  elif [ "$STATUS" = "failed" ]; then
-    send_message "$(echo "$NEXT" | jq -r .error.message)"
-    exit 1
-  fi
-fi
-
-NEXT=$(npx makaron-cli responses next "$RUN_ID" --json --no-fail)
-if [ "$(echo "$NEXT" | jq -r .status)" = "has_artifacts" ]; then
-  ARTIFACT_ID=$(echo "$NEXT" | jq -r ".undelivered_artifacts[0].id")
-  ARTIFACT_URL=$(echo "$NEXT" | jq -r ".undelivered_artifacts[0].url")
-  DELIVERY_MESSAGE_ID=$(send_message "$ARTIFACT_URL")
-  npx makaron-cli responses deliver "$ARTIFACT_ID" --run "$RUN_ID" --channel feishu --message-id "$DELIVERY_MESSAGE_ID"
-fi
-
-RESULT=$(npx makaron-cli responses get "$RUN_ID" --wait --json)
-```
-
 ## Recommended Pattern: Service Flow (Feishu/OpenClaw/Group Chat)
 
 When serving end-users in a chat environment (Feishu, Slack, Discord), use this proactive message pattern: