Agents
The Sume video agent from code: Agent Completions, scheduled runs, MCP tools and timeouts, programmatic tool calling, and guardrails for paid APIs.
Start with What is a video agent? How Sume defines and runs one
Qwen3.8-Omni-Flash for audio agents: tool access
Qwen3.8-Omni-Flash is an omnimodal model for agents. Whatever model you pick, give it Sume's hosted MCP tools and check tools_list before any paid call.
@-mention an agent on a video asset: Runway vs Sume
Runway Enterprise lets you @-mention its Agent in asset comments. Sume Agents take work via the Agent Completions API; media jobs report by webhook.
Claude Desktop catch-up run after wake: idempotency key for Sume
Desktop runs one catch-up task after sleep, maybe hours late. Use a date-based idempotency_key, dry_run and max_spend_usd so Sume bills once.
Claude Desktop scheduled task skipped? Computer asleep vs Sume cron
Desktop scheduled tasks only fire while the app is open and the computer is awake. Where a Sume Scheduled cron run differs and when to use each.
Claude Desktop task can reschedule itself; a Sume schedule cannot
Desktop tasks can edit their own cadence with update_scheduled_task. A Sume schedule has a fixed trigger and no write API. What to do instead.
Hermes cron fixes for run now, and Sume's one-active-run rule
Hermes fixed run-now cancelling the next scheduled run. Sume schedules allow one active run: a second is skipped, or rejected if you ask for reject.
Kilo scheduled sessions vs a Sume schedule for recurring renders
Kilo v7.8.3 reports a session waiting on a wakeup or cron task as scheduled. A Sume schedule lives server-side; use it when renders must run unattended.
AI video agent vs a single-model video generator: what you call
A single-model generator returns one clip from a prompt. An agent plans shots, calls tools and assembles a video. How the Sume calls differ.
Agent Completions gaps today: plan around streaming and PDFs
What Sume Agent Completions does not do yet: streaming, thread continuation, assistant turns, PDFs. Workarounds for GPT-6.1 Sol and Sonnet 5.5 agents.
List Agent Completions newest first: audit an overnight agent
After an agent on GPT-6.1 Sol or Sonnet 5.5 ran overnight, GET /v1/agent-runs lists its Sume completions. What to read from each receipt, and what not to infer.
Re-render Sora prompts from an agent: jobs_wait takes 20 ids
An agent re-rendering saved Sora prompts should wait on up to 20 Sume job ids per call, read results in one batch, and not resubmit after a wait slice expires.
Codex Cloud background tasks: three Sume guardrails to set first
OpenAI's Codex Cloud runs tasks in the background while you are away. Before one can call Sume, set read-only scope, idempotency keys and a hard spend cap.
script_run or Agent Completion: which for a GPT-6.1 Sol agent?
A GPT-6.1 Sol coding agent can call Sume via MCP script_run or Agent Completions. Which fits fan-out of known calls, and which fits open-ended tasks.
What did my seller agent spend? Read Sume usage by thread
Amazon's Seller Assistant plugin logs its actions with audit trails. For the media your agent made through Sume, read the cost by thread_id and run_id.
job_scope_forbidden: why an agent run cannot list every Sume job
A thread-bound Sume credential lists only its own thread's jobs, and unattended runs cannot ask for the whole workspace. What to use instead.
Opus 5.5 resists injection better, but keep scraped text in input
Anthropic says Opus 5.5 is more resistant to prompt injection. For a video agent that reads web pages, still send them to a Sume Format run as input data.
Gemini 4 Argon is announced but not public: what to run today
Google announced Gemini 4 Argon on Sept 30 with access limited to cyber defenders. Here is what a Sume Format run uses as its orchestrator meanwhile.
Opus 5.5 hands cyber tasks to Opus 4.8: log the model id
Anthropic says Opus 5.5 re-routes most cybersecurity tasks to Opus 4.8. Keep the model id that served each Sume Format run in your logs to explain odd results.
Gemini managed agents background:true vs a Sume Format 202 receipt
Both return an id to poll instead of holding the connection. Compare the Gemini background flag with the Sume Format run receipt and its four URLs.
Grok 4.7 Fast is only in Cursor and Grok Build, at 2x the rate
xAI's pricing page says Grok 4.7 Fast is not on the public API. Where it runs, what it costs, and what to do if your Sume agent needs a Grok model.
Claude Opus 5.5 programmatic tool calling: when video jobs fit it
Opus 5.5 supports programmatic tool calling. Fan-out video jobs fit it, sequential renders do not. Which Sume calls batch well and which stay one by one.
Agent run webhook: degraded outcome, and canceled runs send nothing
A Sume agent.run webhook has outcome ok, degraded or error, and canceled or skipped runs deliver nothing. Which branch your handler needs to cover.
Agent Completions webhook payload null: fetch result_url (1 MiB)
A Sume agent.run webhook over 1 MiB arrives with payload null and an error carrying result_url, while status still says OK. Verify, then fetch the receipt.
Edit a photo from an AI agent: generate_image with input_references
The hosted MCP generate_image tool takes the same body as POST /v1/images, including input_references. Call tools_schema first, pass an idempotency_key.
Who authorizes agent spend on Sume: mcp:write, key and balance
On Sume, spend is authorized by the token: mcp:read hides paid tools, mcp:write allows them, and an API key sees all. There is no mcp:paid scope.
x402 upto vs exact: how each maps to a Sume spend cap
Apify's x402 upto charges actual usage up to an allowance; exact takes a fixed $1.00 deposit and refunds the rest. Sume's analogue is a per-call spend cap.
AgentCore payments GA vs Sume's API key and credit balance
AWS made AgentCore payments GA on Aug 18, 2026 with x402 upto and MPP. Sume uses an API key or OAuth with a credit balance and per-call spend caps instead.
Hermes Agent cron job that starts a Sume Format run
A Hermes cron job begins with no memory of last week. Write the prompt, idempotency key, spend cap and SILENT or CRON_FAILURE reply so a Sume run starts once.
Hermes cron no-agent script: poll a Sume bulk queue quietly
A Hermes cron script that prints nothing while a Sume bulk queue runs and one line when every item is terminal. Includes the Python, 404 and 429 cases.
What is an AI video agent? One that talks, or one that makes
An AI video agent can mean a live on-camera persona like a Tavus PAL, or an agent that makes videos for you. Which one Sume is, and how to call it from code.
Sume Agent Completions request: required cap, model sume-agent
The minimum valid POST /v1/agent/completions body: instruction or messages, no assistant turns, model sume-agent, required generation_spend_cap_usd.
Sume Agent Completions or a Format run: which should code call?
Pick between POST /v1/agent/completions and a Format run: open-ended instruction versus a reusable recipe, fresh thread each time, schema output, and cost cap.
Sume Action spend cap: 1 dollar default, per-run cap only lowers
A Sume Action carries a default spend cap of 1 dollar. A per-run cap can lower it but not raise it, so a heavy video job needs the cap changed on the Action.
Sume Action overlap: on_active_run skip gives 200, reject gives 409
What happens when a Sume Action run starts while the last one is active: skip gives 200 with status skipped, reject gives 409 action_run_in_progress.
Scheduled Sume runs: cron or API trigger is fixed at create
A Sume Action is either cron or api triggered, chosen at creation. How to author one, why you cannot create it over the public API, and how to run the api kind.
Claude thinking blocks are model-bound: one model per thread
Sonnet 5.5 and Fable 5.1 thinking blocks only work for the model (and account) that made them. Why an agent thread should keep one model, and how to log it.
Scheduled run missing from /v1/jobs? Read /v1/action-runs instead
A Sume scheduled agent run is not a generation job. It never appears in /v1/jobs and has its own statuses, so poll /v1/action-runs/{run_id}.
Fire a cron schedule on demand: api_trigger_enabled, cron kept
A Sume cron schedule can also accept API runs. Turn on api_trigger_enabled and your service can start it now without touching the cadence.
Scheduled run body: unknown fields are silently dropped, not a 400
A typo in a Sume scheduled run body is dropped without an error, unlike a Format run. Check names, then read the receipt to see what applied.
Can I create a Sume scheduled agent by API? Read and run, not create
The Sume API can list, read, run and monitor scheduled agents, but not create, edit or delete them. Authoring is the dashboard or the Agent chat.
Claude Code mcp_tool hook skipped on SessionStart: Sume balance check
Claude Code's mcp_tool hooks are skipped on SessionStart and Setup because no MCP client exists yet. Run a Sume balance check at PreToolUse instead.
Claude Code RETRY_WATCHDOG gives up after 3 timeouts: Sume jobs
Unattended Claude Code sessions using CLAUDE_CODE_RETRY_WATCHDOG now stop after three timeouts. Persist Sume job ids so a restart resumes, not resubmits.
Codex config.toml enabled_tools and required for Sume's read tools
Codex's MCP config can allowlist tools with enabled_tools and fail startup with required. Give a task only Sume's read and wait tools and a longer timeout.
VS Code Copilot automations on a schedule: Sume jobs and idempotency
VS Code automations can run agent tasks hourly, daily, weekly or on demand. Make each Sume create idempotent so a rerun resumes a job instead of paying twice.
Agent retry budget for paid video calls: stop on 402
An agent that calls a paid video API needs three counters: submits, estimated dollars and consecutive 402s. The stop rule, and how Sume's spend cap backs it up.
Claude Code 2.1.288 background session fix: Sume jobs keep running
Claude Code 2.1.288 fixed background sessions ending on plugin reload. A Sume job outlives the session; how to find it and avoid paying twice.
Claude Code plugin agents honor disallowedTools: block Sume paid tools
Since 2.1.288 plugin-defined agents run with their own prompt, tools, disallowedTools and effort. A reviewer agent that can read Sume jobs but never create one.
Codex 0.160 Guardian review reads prior instructions: Sume args
Codex CLI 0.160 adds opt-in Guardian review that can fetch earlier user instructions. Write Sume calls so a reviewer can approve them from the arguments alone.