makaron-cli 0.7.10 → 0.7.11

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)
@@ -134,43 +144,6 @@ Outputs one JSON per line as artifacts appear:
 {"event":"done","status":"completed"}
 ```
 
-### 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 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>
-```
-
-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
@@ -300,33 +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: $PROJECT_URL"
-
-if ! npx makaron-cli responses timeline "$RUN_ID" --jsonl --compact --checkpoint-mode service --fail-on-unapproved > /tmp/makaron-events.jsonl; then
-  npx makaron-cli responses timeline "$RUN_ID" --jsonl --compact | while read -r event; do
-    TYPE=$(echo "$event" | jq -r .type)
-    REQUIRES=$(echo "$event" | jq -r ".requires_approval // false")
-    TEXT=$(echo "$event" | jq -r ".text // empty")
-    MSG_ID=$(echo "$event" | jq -r ".id // empty")
-    if [ "$TYPE" = "message" ] && [ "$REQUIRES" = "true" ]; then
-      send_message "$TEXT"
-      npx makaron-cli responses ask-user "$MSG_ID" --run "$RUN_ID"
-      exit 3
-    fi
-  done
-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.
 
@@ -126,43 +136,6 @@ Outputs one JSON per line as artifacts appear:
 {"event":"done","status":"completed"}
 ```
 
-### 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 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>
-```
-
-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
@@ -289,33 +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: $PROJECT_URL"
-
-if ! npx makaron-cli responses timeline "$RUN_ID" --jsonl --compact --checkpoint-mode service --fail-on-unapproved > /tmp/makaron-events.jsonl; then
-  npx makaron-cli responses timeline "$RUN_ID" --jsonl --compact | while read -r event; do
-    TYPE=$(echo "$event" | jq -r .type)
-    REQUIRES=$(echo "$event" | jq -r ".requires_approval // false")
-    TEXT=$(echo "$event" | jq -r ".text // empty")
-    MSG_ID=$(echo "$event" | jq -r ".id // empty")
-    if [ "$TYPE" = "message" ] && [ "$REQUIRES" = "true" ]; then
-      send_message "$TEXT"
-      npx makaron-cli responses ask-user "$MSG_ID" --run "$RUN_ID"
-      exit 3
-    fi
-  done
-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/bin/makaron.mjs

@@ -19,7 +19,6 @@ import { execFileSync } from 'child_process';
 // ─── Config ──────────────────────────────────────────────────────────────────
 
 const AUTH_FILE = path.join(process.env.HOME || '~', '.makaron', 'auth.json');
-const APPROVALS_FILE = path.join(path.dirname(AUTH_FILE), 'approvals.json');
 const DEFAULT_URL = 'https://www.makaron.app';
 const BASE_URL = process.env.MAKARON_URL || DEFAULT_URL;
 const APP_URL = process.env.MAKARON_APP_URL || DEFAULT_URL;
@@ -28,9 +27,12 @@ const APP_URL = process.env.MAKARON_APP_URL || DEFAULT_URL;
 const SUPABASE_URL = 'https://sdyrtztrjgmmpnirswxt.supabase.co';
 const SUPABASE_ANON_KEY = 'sb_publishable_FJFN2YYaWaQjABUKLqxQcA_fhxPLFDY';
 
-const MAX_VIDEO_FILE_SIZE = 200 * 1024 * 1024;
-const MAX_VIDEO_DURATION = 15;
-const MAX_VIDEO_DURATION_TOLERANCE = 0.5;
+const MAX_VIDEO_UPLOAD_FILE_SIZE_MB = 50;
+const MAX_VIDEO_UPLOAD_FILE_SIZE = MAX_VIDEO_UPLOAD_FILE_SIZE_MB * 1024 * 1024;
+const MAX_VIDEO_UPLOAD_DURATION = 120;
+const MAX_VIDEO_UPLOAD_DURATION_TOLERANCE = 1;
+const MAX_VIDEO_PROVIDER_REFERENCE_DURATION = 15;
+const MAX_VIDEO_PROVIDER_REFERENCE_DURATION_TOLERANCE = 0.5;
 const MAX_VIDEO_FRAME_PIXELS = 2_086_876;
 
 function getCliVersion() {
@@ -63,20 +65,6 @@ function saveAuth(data) {
   fs.writeFileSync(AUTH_FILE, JSON.stringify(data, null, 2));
 }
 
-function loadApprovals() {
-  try {
-    return JSON.parse(fs.readFileSync(APPROVALS_FILE, 'utf-8'));
-  } catch {
-    return [];
-  }
-}
-
-function saveApprovals(approvals) {
-  const dir = path.dirname(APPROVALS_FILE);
-  if (!fs.existsSync(dir)) fs.mkdirSync(dir, { recursive: true });
-  fs.writeFileSync(APPROVALS_FILE, JSON.stringify(approvals, null, 2));
-}
-
 function buildCookie(tokenJson) {
   const url = tokenJson._supabaseUrl || SUPABASE_URL;
   const ref = url.match(/\/\/([^.]+)\./)?.[1] || '';
@@ -441,248 +429,6 @@ function applyPick(data, field) {
   }
 }
 
-// ─── Dialogue Events (message / approval / artifact) ─────────────────────────
-
-function stableEventId(prefix, runId, seq, fallback) {
-  return fallback || `${prefix}_${runId}_${seq ?? Date.now()}`;
-}
-
-function inferApprovalIntent(text) {
-  if (!text) return false;
-  const normalized = text.toLowerCase().replace(/\s+/g, ' ').trim();
-  const hasEnglishApprovalIntent = /\b(shall i|should i|do you want me to|confirm|approve|approval|permission)\b/.test(normalized);
-  const hasEnglishAction = /\b(go ahead|proceed|continue|generate|create|submit|start|run|render)\b/.test(normalized);
-  const hasChineseApprovalIntent = /(是否|要不要|是否要|需要我|请确认|确认|同意|批准|可以吗|是否可以)/.test(normalized);
-  const hasChineseAction = /(继续|开始|生成|创建|提交|执行|渲染|出图|出视频|制作)/.test(normalized);
-  return (hasEnglishApprovalIntent && hasEnglishAction) || (hasChineseApprovalIntent && hasChineseAction);
-}
-
-function isPureStatusMessage(text, sourceType, status) {
-  const normalized = String(text || '').toLowerCase().replace(/\s+/g, ' ').trim();
-  if (sourceType === 'status') return true;
-  if (status && !normalized) return true;
-  if (!normalized) return false;
-  return /^(queued|running|rendering|uploading|processing|generating|completed|complete|done|failed|aborted|started|submitted|waiting|polling)(\.|…|\.\.\.)?$/.test(normalized)
-    || /^(排队中|队列中|运行中|渲染中|上传中|处理中|生成中|已完成|完成|失败|已失败|已提交|等待中)$/.test(normalized);
-}
-
-function hasExplicitApprovalRequirement(data, text) {
-  return Boolean(
-    data.requires_approval
-      || data.requiresApproval
-      || data.action_required
-      || data.actionRequired
-      || data.proposal
-      || inferApprovalIntent(text)
-  );
-}
-
-function isPureQaRun(data) {
-  const raw = [
-    data.intent,
-    data.mode,
-    data.workflow,
-    data.workflow_type,
-    data.workflowType,
-    data.run_type,
-    data.runType,
-    data.kind,
-  ].filter(Boolean).join(' ').toLowerCase();
-  return /\b(qa|q&a|question_answer|question-answer|answer|pure_qa|pure-qa)\b/.test(raw);
-}
-
-function normalizeDialogueMessage(runId, projectId, ev, context = {}) {
-  const data = ev.data || ev;
-  const text = data.text || data.message || data.content || data.statusText || '';
-  if (!text && ev.type !== 'tool_call') return null;
-  const explicitApproval = hasExplicitApprovalRequirement(data, text);
-  const textOnlyCheckpoint = Boolean(
-    context.stoppedWithoutArtifacts
-      && !explicitApproval
-      && !isPureStatusMessage(text, ev.type, data.status)
-  );
-  const requiresApproval = explicitApproval || textOnlyCheckpoint;
-  const message = {
-    type: 'message',
-    id: stableEventId('msg', runId, ev.seq, data.id || ev.id),
-    runId,
-    projectId,
-    seq: ev.seq,
-    status: data.status || undefined,
-    text: text || `${data.tool || 'tool_call'}${data.input?.description ? `: ${data.input.description}` : ''}`,
-  };
-  if (ev.type) message.source_type = ev.type;
-  if (requiresApproval) {
-    message.requires_approval = true;
-    message.approval_options = data.approval_options || data.approvalOptions || ['approve', 'revise', 'ask_user', 'continue'];
-    if (textOnlyCheckpoint) message.approval_reason = 'text_only_checkpoint';
-  }
-  if (data.proposal) message.proposal = data.proposal;
-  return message;
-}
-
-function normalizeDialogueArtifact(runId, projectId, item, seq) {
-  if (!item) return null;
-  const kind = item.type || item.kind || (item.imageUrl ? 'image' : item.videoUrl ? 'video' : undefined);
-  if (!kind) return null;
-  if (!['image', 'video', 'design', 'music', 'audio', 'file'].includes(kind)) return null;
-  const artifact = {
-    type: 'artifact',
-    id: stableEventId('artifact', runId, seq, item.id || item.snapshotId || item.taskId),
-    runId,
-    projectId,
-    seq,
-    kind,
-    status: item.status || (item.url || item.imageUrl || item.videoUrl || item.audioUrl ? 'completed' : 'running'),
-  };
-  const url = item.url || item.imageUrl || item.videoUrl || item.audioUrl;
-  if (url) artifact.url = url;
-  if (item.error) artifact.error = item.error;
-  if (item.taskId) artifact.taskId = item.taskId;
-  if (item.snapshotId) artifact.snapshotId = item.snapshotId;
-  return artifact;
-}
-
-function normalizeDialogueEvent(runId, projectId, ev, context = {}) {
-  const data = ev.data || {};
-  if (ev.type === 'message' || ev.type === 'approval' || ev.type === 'artifact') {
-    return { ...data, ...ev, runId: ev.runId || runId, projectId: ev.projectId || projectId };
-  }
-  switch (ev.type) {
-    case 'content':
-    case 'status':
-    case 'tool_call':
-    case 'error':
-      return normalizeDialogueMessage(runId, projectId, ev, context);
-    case 'image':
-      return normalizeDialogueArtifact(runId, projectId, { type: 'image', status: data.imageUrl ? 'completed' : 'running', imageUrl: data.imageUrl, snapshotId: data.snapshotId }, ev.seq);
-    case 'render':
-      return normalizeDialogueArtifact(runId, projectId, { type: data.animation ? 'video' : 'design', status: data.published ? 'completed' : 'running', url: data.url, snapshotId: data.snapshotId }, ev.seq);
-    case 'animation_task':
-    case 'video_snapshot':
-      return normalizeDialogueArtifact(runId, projectId, { type: 'video', status: 'running', taskId: data.taskId, snapshotId: data.snapshotId }, ev.seq);
-    case 'music_task':
-      return normalizeDialogueArtifact(runId, projectId, { type: 'music', status: 'running', taskId: data.taskId }, ev.seq);
-    default:
-      return null;
-  }
-}
-
-function buildDialogueEvents(runId, data) {
-  const projectId = data.projectId || data.project_id;
-  const events = [];
-  const hasArtifacts = Boolean(
-    (data.output || []).some(item => normalizeDialogueArtifact(runId, projectId, item, item.seq))
-      || (data.events || []).some(ev => normalizeDialogueEvent(runId, projectId, ev, { stoppedWithoutArtifacts: false })?.type === 'artifact')
-  );
-  const hasContinuationAction = (data.events || []).some(ev => ['tool_call', 'image', 'render', 'animation_task', 'video_snapshot', 'music_task'].includes(ev.type));
-  const checkpointMode = data.checkpointMode || 'service';
-  const context = {
-    stoppedWithoutArtifacts: checkpointMode !== 'off'
-      && !isPureQaRun(data)
-      && !hasArtifacts
-      && !hasContinuationAction
-      && !data.incomplete
-      && ['completed', 'failed', 'aborted', 'waiting', 'needs_input'].includes(data.status),
-  };
-  for (const ev of data.events || []) {
-    const normalized = normalizeDialogueEvent(runId, projectId, ev, context);
-    if (normalized) events.push(normalized);
-  }
-  for (const item of data.output || []) {
-    const normalized = normalizeDialogueArtifact(runId, projectId, item, item.seq);
-    if (normalized && !events.some(ev => ev.type === 'artifact' && ev.id === normalized.id)) events.push(normalized);
-  }
-  for (const approval of loadApprovals().filter(item => item.runId === runId)) {
-    events.push(approval);
-  }
-  return events;
-}
-
-function compactDialogueEvents(events) {
-  const compacted = [];
-  for (const ev of events) {
-    const prev = compacted[compacted.length - 1];
-    const canMerge = prev
-      && ev.type === 'message'
-      && prev.type === 'message'
-      && ev.source_type === 'content'
-      && prev.source_type === 'content'
-      && !ev.requires_approval
-      && !prev.requires_approval
-      && !ev.proposal
-      && !prev.proposal;
-    if (canMerge) {
-      prev.text = `${prev.text}${ev.text}`;
-      prev.id = `${prev.id}+${ev.id}`;
-      prev.seq_end = ev.seq;
-    } else {
-      compacted.push({ ...ev });
-    }
-  }
-  return compacted;
-}
-
-function findUnhandledApprovalMessages(events) {
-  const approved = new Set(events.filter(ev => ev.type === 'approval').map(ev => ev.messageId || ev.message_id));
-  return events.filter(ev => ev.type === 'message' && ev.requires_approval && !approved.has(ev.id));
-}
-
-async function fetchRun(baseUrl, headers, runId, opts = {}) {
-  const params = new URLSearchParams();
-  if (opts.events) params.set('events', 'true');
-  const suffix = params.toString() ? `?${params}` : '';
-  const res = await fetch(`${baseUrl}/api/agent/run/${runId}${suffix}`, { headers });
-  if (!res.ok) { process.stderr.write(`Error ${res.status}: ${await res.text()}\n`); process.exit(1); }
-  return normalizeRunResponse(await res.json());
-}
-
-async function printDialogueEvents(baseUrl, headers, runId, opts = {}) {
-  const { jsonl = false, failOnUnapproved = false, follow = false, interval = 5000, compact = false, checkpointMode = 'service' } = opts;
-  const printed = new Set();
-
-  while (true) {
-    const data = await fetchRun(baseUrl, headers, runId, { events: true });
-    const dialogueEvents = buildDialogueEvents(runId, { ...data, checkpointMode });
-    const events = compact ? compactDialogueEvents(dialogueEvents) : dialogueEvents;
-    const unhandled = findUnhandledApprovalMessages(events);
-    if (failOnUnapproved && unhandled.length) {
-      process.stderr.write(`Unhandled Makaron message requires approval: ${unhandled.map(ev => ev.id).join(', ')}\n`);
-      process.exit(3);
-    }
-
-    const nextEvents = follow ? events.filter(ev => !printed.has(`${ev.type}:${ev.id || ev.seq}`)) : events;
-    for (const ev of nextEvents) {
-      printed.add(`${ev.type}:${ev.id || ev.seq}`);
-      if (jsonl) console.log(JSON.stringify(ev));
-    }
-    if (!jsonl) console.log(JSON.stringify(nextEvents, null, 2));
-
-    if (!follow || (!data.incomplete && ['completed', 'failed', 'aborted'].includes(data.status))) {
-      if (data.status === 'failed' || data.status === 'aborted') process.exit(1);
-      return;
-    }
-    await new Promise(r => setTimeout(r, data.next_poll_after_ms || interval));
-  }
-}
-
-function recordApproval(runId, messageId, choice, note) {
-  const approvals = loadApprovals();
-  const approval = {
-    type: 'approval',
-    id: `approval_${Date.now()}`,
-    runId,
-    messageId,
-    choice,
-    status: 'recorded',
-    createdAt: new Date().toISOString(),
-  };
-  if (note) approval.note = note;
-  approvals.push(approval);
-  saveApprovals(approvals);
-  console.log(JSON.stringify(approval));
-}
-
 // ─── Watch (incremental event stream) ───────────────────────────────────────
 
 async function watchRun(baseUrl, headers, runId, opts = {}) {
@@ -840,6 +586,34 @@ async function listProjects(baseUrl, headers) {
   console.log('');
 }
 
+async function listProjectMedia(baseUrl, headers, projectId, opts = {}) {
+  const res = await fetch(`${baseUrl}/api/projects/${projectId}/media`, { headers });
+  if (!res.ok) { console.error('Project media failed:', await res.text()); process.exit(1); }
+  const data = await res.json();
+  if (opts.json) {
+    console.log(JSON.stringify(data, null, 2));
+    return data;
+  }
+
+  console.log(`🎞️  ${data.title || 'Untitled'}`);
+  console.log(`   Project: ${data.projectUrl || `${APP_URL}/projects/${projectId}`}`);
+  const media = data.media || [];
+  if (!media.length) {
+    console.log('   No timeline media yet.');
+    return data;
+  }
+  for (const item of media) {
+    const ref = item.ref || `<<<media_${item.index}>>>`;
+    const status = item.status && item.status !== 'completed' ? ` ${item.status}` : '';
+    const duration = typeof item.duration === 'number' ? ` ${item.duration}s` : '';
+    const dimensions = item.width && item.height ? ` ${item.width}x${item.height}` : '';
+    const description = item.description ? ` — ${item.description}` : '';
+    const url = item.url ? `\n      ${item.url}` : '';
+    console.log(`  ${String(item.index).padStart(2)}. ${ref} [${item.type}${status}${duration}${dimensions}]${description}${url}`);
+  }
+  return data;
+}
+
 function timeSince(date) {
   const s = Math.floor((Date.now() - date.getTime()) / 1000);
   if (s < 60) return 'just now';
@@ -991,13 +765,15 @@ function probeLocalVideo(videoPath) {
   return probeVideoWithFfprobe(videoPath) || probeVideoWithFfmpeg(videoPath);
 }
 
-function validateVideoFile(videoPath) {
+function validateVideoFile(videoPath, options = {}) {
+  const maxDuration = options.maxDuration ?? MAX_VIDEO_UPLOAD_DURATION;
+  const durationTolerance = options.durationTolerance ?? MAX_VIDEO_UPLOAD_DURATION_TOLERANCE;
   if (!fs.existsSync(videoPath)) {
     return { ok: false, error: `Video file not found: ${videoPath}` };
   }
   const stat = fs.statSync(videoPath);
-  if (stat.size > MAX_VIDEO_FILE_SIZE) {
-    return { ok: false, error: `Video too large: ${(stat.size / 1024 / 1024).toFixed(1)}MB (max 200MB)` };
+  if (stat.size > MAX_VIDEO_UPLOAD_FILE_SIZE) {
+    return { ok: false, error: `Video too large: ${(stat.size / 1024 / 1024).toFixed(1)}MB (max ${MAX_VIDEO_UPLOAD_FILE_SIZE_MB}MB). The CLI uploads directly to Storage; use the frontend to transcode larger videos first.` };
   }
   const ext = path.extname(videoPath).slice(1).toLowerCase();
   if (!['mp4', 'mov', 'webm'].includes(ext)) {
@@ -1007,8 +783,8 @@ function validateVideoFile(videoPath) {
   if (!meta) {
     return { ok: false, error: 'Cannot read video duration/resolution. Install ffmpeg/ffprobe or use the normal frontend upload flow.' };
   }
-  if (meta.duration > MAX_VIDEO_DURATION + MAX_VIDEO_DURATION_TOLERANCE) {
-    return { ok: false, error: `Video too long: ${formatSeconds(meta.duration)}s (max ${MAX_VIDEO_DURATION}s, with ${MAX_VIDEO_DURATION_TOLERANCE}s metadata tolerance)` };
+  if (meta.duration > maxDuration + durationTolerance) {
+    return { ok: false, error: `Video too long: ${formatSeconds(meta.duration)}s (max ${maxDuration}s, with ${durationTolerance}s metadata tolerance)` };
   }
   if (meta.width * meta.height > MAX_VIDEO_FRAME_PIXELS) {
     return { ok: false, error: `Video resolution too high: ${meta.width}x${meta.height} (${meta.width * meta.height} px). Max is <=1080p (${MAX_VIDEO_FRAME_PIXELS} px). Re-upload through the frontend to transcode, or export a smaller video.` };
@@ -1025,8 +801,8 @@ function validateVideoFileForAnalysis(videoPath) {
   if (stat.size === 0) {
     return { ok: false, error: `Video file is empty: ${videoPath}` };
   }
-  if (stat.size > MAX_VIDEO_FILE_SIZE) {
-    return { ok: false, error: `Video too large: ${(stat.size / 1024 / 1024).toFixed(1)}MB (max 200MB)` };
+  if (stat.size > MAX_VIDEO_UPLOAD_FILE_SIZE) {
+    return { ok: false, error: `Video too large: ${(stat.size / 1024 / 1024).toFixed(1)}MB (max ${MAX_VIDEO_UPLOAD_FILE_SIZE_MB}MB). The CLI uploads directly to Storage; use the frontend to transcode larger videos first.` };
   }
   const ext = path.extname(videoPath).slice(1).toLowerCase();
   if (!['mp4', 'mov', 'webm'].includes(ext)) {
@@ -1212,7 +988,7 @@ if (command === '--version' || command === '-v' || command === 'version') {
     const uploadedVideoUrls = [...prevalidatedVideoUrlList];
     const uploadedVideoMetas = prevalidatedVideoUrlList.map(() => null);
     if (prevalidatedVideoUrlList.length) {
-      process.stderr.write(`📹 Assuming public video URL(s) already match Makaron upload limits: ≤${MAX_VIDEO_DURATION}s, ≤200MB, ≤1080p.\n`);
+      process.stderr.write(`📹 Assuming public video URL(s) already match Makaron upload limits: ≤${MAX_VIDEO_UPLOAD_DURATION}s, ≤${MAX_VIDEO_UPLOAD_FILE_SIZE_MB}MB, ≤1080p.\n`);
     }
     for (const videoPath of prevalidatedVideoFileList) {
       process.stderr.write(`📹 Uploading ${path.basename(videoPath)} (${(fs.statSync(videoPath).size/1024/1024).toFixed(1)}MB)...\n`);
@@ -1228,7 +1004,7 @@ if (command === '--version' || command === '-v' || command === 'version') {
 
     // Add videos to project via projects/create (same as images)
     if (uploadedVideoUrls.length === 0) {
-      process.stderr.write(`❌ No valid videos were uploaded. Local videos must be MP4/MOV/WebM, ≤${MAX_VIDEO_DURATION}s, ≤200MB, and ≤1080p.\n`);
+      process.stderr.write(`❌ No valid videos were uploaded. Local videos must be MP4/MOV/WebM, ≤${MAX_VIDEO_UPLOAD_DURATION}s, ≤${MAX_VIDEO_UPLOAD_FILE_SIZE_MB}MB, and ≤1080p.\n`);
       process.exit(1);
     }
 
@@ -1317,38 +1093,6 @@ if (command === '--version' || command === '-v' || command === 'version') {
     }
     await watchRun(baseUrl, headers, runId, { interval, jsonl });
 
-  } else if (sub === 'events' || sub === 'timeline') {
-    const runId = args[2];
-    if (!runId) { console.error(`Usage: makaron responses ${sub} <runId> [--jsonl] [--compact] [--checkpoint-mode service|off] [--follow] [--interval <ms>] [--fail-on-unapproved]`); process.exit(1); }
-    let interval = 5000, jsonl = false, follow = false, failOnUnapproved = false, compact = false, checkpointMode = 'service';
-    for (let i = 3; i < args.length; i++) {
-      if (args[i] === '--jsonl') jsonl = true;
-      else if (args[i] === '--compact') compact = true;
-      else if (args[i] === '--checkpoint-mode' && args[i + 1]) checkpointMode = args[++i];
-      else if (args[i] === '--follow') follow = true;
-      else if (args[i] === '--fail-on-unapproved') failOnUnapproved = true;
-      else if (args[i] === '--interval' && args[i + 1]) interval = parseInt(args[++i]);
-    }
-    if (!['service', 'off'].includes(checkpointMode)) {
-      console.error('--checkpoint-mode must be service or off');
-      process.exit(1);
-    }
-    await printDialogueEvents(baseUrl, headers, runId, { interval, jsonl, follow, failOnUnapproved, compact, checkpointMode });
-
-  } else if (['approve', 'revise', 'ask-user', 'continue'].includes(sub)) {
-    const messageId = args[2];
-    if (!messageId) { console.error(`Usage: makaron responses ${sub} <messageId> --run <runId> [--note <text>]`); process.exit(1); }
-    let runId = null, note = null;
-    const noteParts = [];
-    for (let i = 3; i < args.length; i++) {
-      if (args[i] === '--run' && args[i + 1]) runId = args[++i];
-      else if (args[i] === '--note' && args[i + 1]) note = args[++i];
-      else noteParts.push(args[i]);
-    }
-    if (!runId) { console.error(`Usage: makaron responses ${sub} <messageId> --run <runId> [--note <text>]`); process.exit(1); }
-    if (!note && noteParts.length) note = noteParts.join(' ');
-    recordApproval(runId, messageId, sub === 'ask-user' ? 'ask_user' : sub, note);
-
   } else if (sub === 'list') {
     let projectId = null;
     for (let i = 2; i < args.length; i++) {
@@ -1372,13 +1116,6 @@ if (command === '--version' || command === '-v' || command === 'version') {
   responses get <runId>                  Get status and output (JSON)
   responses get <runId> --wait           Poll until completed
   responses get <runId> --pick <field>   Extract: first_image_url, first_video_url, project_url, output
-  responses events <runId> --jsonl       Emit message/approval/artifact events for external Agents
-  responses timeline <runId> --jsonl     Alias for responses events
-  responses timeline <runId> --checkpoint-mode off   Disable text-only checkpoints for pure Q&A
-  responses approve <messageId> --run <runId>    Record approval for a Makaron message
-  responses revise <messageId> --run <runId>     Record revision request for a Makaron message
-  responses ask-user <messageId> --run <runId>   Record that the user must decide
-  responses continue <messageId> --run <runId>   Record continue decision
   responses watch <runId> --jsonl        Watch until done (incremental events)
   responses list --project <id>          List runs for a project
 `);
@@ -1386,6 +1123,19 @@ if (command === '--version' || command === '-v' || command === 'version') {
 } else if (command === 'list' || command === 'ls') {
   const { headers, baseUrl } = getAuth();
   await listProjects(baseUrl, headers);
+} else if (command === 'project' || command === 'projects') {
+  const { headers, baseUrl } = getAuth();
+  const sub = args[1];
+  if (sub === 'media') {
+    const projectId = args[2];
+    if (!projectId) { console.error('Usage: makaron project media <projectId> [--json]'); process.exit(1); }
+    const jsonOutput = args.includes('--json');
+    await listProjectMedia(baseUrl, headers, projectId, { json: jsonOutput });
+  } else {
+    console.log(`Project commands:
+  project media <projectId> --json      List timeline media for a project
+`);
+  }
 } else if (command === 'abort') {
   const { headers, baseUrl } = getAuth();
   const runId = args[1];
@@ -1487,10 +1237,13 @@ if (command === '--version' || command === '-v' || command === 'version') {
     let videoUrl = isHttpUrl(video) ? video : null;
     let inputVideoMeta = null;
     if (videoUrl) {
-      process.stderr.write(`📹 Assuming public video URL already matches Makaron upload limits: ≤${MAX_VIDEO_DURATION}s, ≤200MB, ≤1080p.\n`);
+      process.stderr.write(`📹 Assuming public video URL already matches provider reference limits: ≤${MAX_VIDEO_PROVIDER_REFERENCE_DURATION}s, ≤${MAX_VIDEO_UPLOAD_FILE_SIZE_MB}MB, ≤1080p.\n`);
     }
     if (video && !videoUrl) {
-      const valid = validateVideoFile(video);
+      const valid = validateVideoFile(video, {
+        maxDuration: MAX_VIDEO_PROVIDER_REFERENCE_DURATION,
+        durationTolerance: MAX_VIDEO_PROVIDER_REFERENCE_DURATION_TOLERANCE,
+      });
       if (!valid.ok) { console.error(`❌ ${valid.error}`); process.exit(1); }
       inputVideoMeta = valid.meta;
       process.stderr.write(`📹 Uploading ${path.basename(video)} (${(fs.statSync(video).size/1024/1024).toFixed(1)}MB)...\n`);
@@ -1503,7 +1256,7 @@ if (command === '--version' || command === '-v' || command === 'version') {
     const vArgs = videoUrl
       ? { videoUrl, editPrompt: script, images, videoModel: videoModel || 'kling', referType: (videoModel || 'kling') === 'seedance' ? 'feature' : 'base' }
       : { script, images };
-    const effectiveDuration = duration || (inputVideoMeta?.duration ? Math.min(MAX_VIDEO_DURATION, Math.round(inputVideoMeta.duration)) : undefined);
+    const effectiveDuration = duration || (inputVideoMeta?.duration ? Math.min(MAX_VIDEO_PROVIDER_REFERENCE_DURATION, Math.round(inputVideoMeta.duration)) : undefined);
     if (effectiveDuration) vArgs.duration = effectiveDuration;
     if (aspectRatio) vArgs.aspectRatio = aspectRatio;
     if (videoModel && !videoUrl) vArgs.videoModel = videoModel;
@@ -1804,6 +1557,7 @@ Commands:
   claim                              Get claim URL for human to link account
   login                              Log in to Makaron (human interactive)
   list (ls)                          List all projects
+  project media <projectId> --json    List timeline media for a project
   create --image <file>              Create project from local image
   create --image-url <url>           Create project from URL
   create --title "name"              Create empty project (text-to-image)
@@ -1816,8 +1570,6 @@ Commands:
 
   responses get <runId>              Get run status and results
   responses get <runId> --wait       Poll until completed
-  responses events <runId> --jsonl   Emit message/approval/artifact events
-  responses timeline <runId> --checkpoint-mode off   Disable text-only checkpoints for pure Q&A
   responses list --project <id>      List runs for a project
   abort <runId>                      Abort a running Agent
 

package/package.json

@@ -1,6 +1,6 @@
 {
   "name": "makaron-cli",
-  "version": "0.7.10",
+  "version": "0.7.11",
   "description": "Talk to Makaron Agent from the terminal — create projects, edit images, generate videos",
   "type": "module",
   "scripts": {

package/skills/makaron/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.
 
@@ -126,43 +136,6 @@ Outputs one JSON per line as artifacts appear:
 {"event":"done","status":"completed"}
 ```
 
-### 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 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>
-```
-
-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
@@ -289,33 +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: $PROJECT_URL"
-
-if ! npx makaron-cli responses timeline "$RUN_ID" --jsonl --compact --checkpoint-mode service --fail-on-unapproved > /tmp/makaron-events.jsonl; then
-  npx makaron-cli responses timeline "$RUN_ID" --jsonl --compact | while read -r event; do
-    TYPE=$(echo "$event" | jq -r .type)
-    REQUIRES=$(echo "$event" | jq -r ".requires_approval // false")
-    TEXT=$(echo "$event" | jq -r ".text // empty")
-    MSG_ID=$(echo "$event" | jq -r ".id // empty")
-    if [ "$TYPE" = "message" ] && [ "$REQUIRES" = "true" ]; then
-      send_message "$TEXT"
-      npx makaron-cli responses ask-user "$MSG_ID" --run "$RUN_ID"
-      exit 3
-    fi
-  done
-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: