Muse Wonder 1.0·续4

Muse Wonder 1.0·续4

{
  "id": "resp_6acd1a6b1cc0e8cd73b14849",
  "object": "response",
  "created_at": 1791826539,
  "model": "muse-wonder-1.0",
  "output": [
    {
      "type": "reasoning",
      "id": "rs_6acd1a6b1cc0e8cd73b14849:rs_1ec0edf9-e7f4-4458-a3b9-0ba182aa1df9",
      "summary": [],
      "status": "completed"
    },
    {
      "type": "message",
      "id": "msg_d0518550-0472-4883-89d4-52fd12e29a92",
      "role": "assistant",
      "content": [
        {
          "type": "output_text",
          "text": "# Zero-Downtime Migration Plan\n\n## Security invariants — hold in every phase\n- **Default-deny, fail-closed:** unknown role/action, missing context, engine timeout/error, or stale/malformed policy ⇒ deny.\n- **Tenant isolation:** `resource.tenant_id` must be within the principal’s verified tenant scope unless an explicit cross-tenant rule applies; never trust a client-supplied tenant ID alone.\n- **No privilege expansion:** role normalization or exception migration may never grant more than the legacy intent; resolve ambiguity to less privilege.\n- **Authentication ≠ authorization:** the engine accepts only issuer-verified identity; it never parses raw credentials.\n- Every decision is auditable to principal, tenant, resource, and policy version; exceptions are scoped, owned, approved, and expiring—no wildcard customer bypasses.\n\n## 1. Policy contract\nVersioned, deterministic, side-effect-free:\n\n`Evaluate(Principal, Tenant, Action, Resource, Context) → {decision: Allow|Deny, reason_code, policy_version, obligations[], decision_id}`\n\n- **Principal:** `subject_id`, type (`user|service|job`), verified `tenant_scope[]`, canonical roles, auth strength.\n- **Action/Resource:** canonical actions such as `invoice.read`; resource type, ID, owner tenant, sensitivity/ownership attributes.\n- **Context:** time, request/job ID, source. Background jobs carry a signed, expiring job envelope—`tenant_id`, `initiated_by` or named `system_principal`, purpose, authorized scope. No envelope ⇒ deny.\n\nPolicies are signed, immutable, versioned bundles, deployed atomically with local caching; evaluation performs no writes.\n\n## 2. Inventory\nStatically scan routes, middleware, AST/grep for role strings, and job handlers; supplement with runtime auth logs and owner review. Catalog for every endpoint/job: current check, legacy roles, tenant source, data sensitivity, and config-based customer exceptions. Normalize names explicitly, e.g. `Admin|ADMIN|tenant_admin → tenant.admin`; unmapped values deny in the new model. Convert each exception into a named policy rule with business justification, approver, and expiry.\n\n## 3. Shadow evaluation\nDeploy the engine behind flags with legacy checks still authoritative. Evaluate the same verified inputs, log only the would-be decision, and classify every divergence: intended normalization, legacy over-permission, legacy under-permission, missing attribute, or policy bug. Replay redacted production decision inputs after each fix. Cover a full business cycle, including month-end jobs.\n\n## 4. Compatibility strategy\nUse a strangler adapter at the auth boundary translating legacy claims to canonical roles; keep dual execution until bake-out completes. Gate enforcement by tenant × endpoint × policy version. Policies evolve additively—new fields optional, prior schema versions supported. Dual-read config exceptions and their policy equivalents until equivalence is proven, then freeze config writes. No destructive data/schema changes during migration.\n\n## 5. Test matrix\n- **Roles/tenancy:** each canonical role and legacy alias; unknown/missing role; same-tenant allow/deny; token-vs-URL-vs-resource tenant mismatch; cross-tenant access (must deny).\n- **Principals/jobs:** interactive user, service token, job with valid/expired/replayed/missing signed envelope, retries and scheduler-triggered runs.\n- **Exceptions/failures:** active vs. expired exception, wrong tenant/resource scope; engine down/timeout, malformed or stale bundle, missing attributes—all deny.\n- **Methods:** policy unit tests, contract tests per endpoint, integration tests, production replay, and property/fuzz tests asserting invariants—especially, never allow cross-tenant access.\n\n## 6. Observability\nEmit structured audit events: `decision_id`, hashed subject, tenant, action, resource, legacy and new decisions, reason code, policy version, latency, enforcement mode. Dashboard and alert on decision/diff volume, deny-rate shifts, unknown roles/actions, engine errors, and p99 latency—sliced by tenant, endpoint, version, and principal type. Alert on expiring exceptions and any shadow cross-tenant would-allow.\n\n## 7. Cutover criteria and rollout\nProceed only when: 100% of endpoints/jobs are inventoried; zero critical or unexplained divergences and <0.1% total divergence for 14 days including peak/batch windows; replay and the test matrix pass; added p99 latency is within budget (e.g., <10 ms cached); rollback has been rehearsed; security and service owners sign off.\n\nRoll out internal tenants → low-risk endpoints at 1% → 10% → 50% → 100%, then higher-risk endpoints and jobs, baking each step. Once enforced, keep legacy in shadow briefly, then remove it in a separate release.\n\n## 8. Rollback\nA single flag per tenant/endpoint instantly returns authority to the frozen legacy path—no deploy or data migration required. Alternatively, pin the previous signed policy bundle if the bug is policy-only. After cutover, an engine outage fails closed (deny) rather than auto-falling back; operators explicitly flip the flag if legacy rollback is safer. Retain legacy code, mappings, and audit data until the bake period ends.",
          "annotations": [],
          "logprobs": []
        }
      ],
      "status": "completed"
    }
  ],
  "status": "completed",
  "usage": {
    "input_tokens": 100,
    "output_tokens": 5951,
    "total_tokens": 6051,
    "input_tokens_details": {
      "cached_tokens": 0
    },
    "output_tokens_details": {
      "reasoning_tokens": 4863
    }
  },
  "top_logprobs": 0,
  "temperature": 1,
  "top_p": 1,
  "service_tier": "auto",
  "background": false,
  "tools": [],
  "tool_choice": "auto",
  "truncation": "disabled",
  "completed_at": 1791826539,
  "error": null,
  "incomplete_details": null,
  "instructions": null,
  "parallel_tool_calls": true,
  "store": true,
  "max_output_tokens": 8192
}

</details>

Parameters

▶input

one ofrequired

instructions

string

temperature

numberminimum: 0maximum: 2

max_output_tokens

numberexclusiveMinimum: 0

top_p

numberminimum: 0maximum: 1

stream

boolean

▶tools[]

array

tool_choice

▶text{}

object

▶reasoning{}

object

string

object

stringconst: response

created_at

number

model

string

▶output[]

array

output_text

string

status

stringenum: in_progress, completed, failed, incomplete

▶usage{}

object

API Schemas (Raw)

Input Open Download

Output Open Download

Was this helpful?

YesNo

{"@context":"https://schema.org","@type":"TechArticle","@id":"https://developers.cloudflare.com/ai/models/meta/muse-wonder-1.0/#page","headline":"Muse Wonder 1.0","description":"Muse Wonder 1.0 is Meta's agentic and coding model for complex software engineering, multi-step tool loops, and long-context reasoning.","url":"https://developers.cloudflare.com/ai/models/meta/muse-wonder-1.0/","inLanguage":"en","image":"https://developers.cloudflare.com/og-docs.png","publisher":{"@type":"Organization","name":"Cloudflare","description":"One platform for your apps, agents, and workforce. Build, secure, and scale without managing infrastructure","url":"https://www.cloudflare.com/","sameAs":["https://github.com/cloudflare","https://www.linkedin.com/company/cloudflare","https://x.com/cloudflare"],"logo":{"@type":"ImageObject","url":"https://developers.cloudflare.com/logo.svg"},"address":{"@type":"PostalAddress","streetAddress":"101 Townsend St","addressLocality":"San Francisco","addressRegion":"CA","postalCode":"94107","addressCountry":"US"},"contactPoint":[{"@type":"ContactPoint","contactType":"Customer Support","url":"https://support.cloudflare.com/","availableLanguage":["English"]},{"@type":"ContactPoint","contactType":"Sales","url":"https://www.cloudflare.com/contact/","availableLanguage":["English"]}]},"isPartOf":{"@type":"WebSite","@id":"https://developers.cloudflare.com/#website","name":"Cloudflare Docs","url":"https://developers.cloudflare.com/"}}

description: A multimodal video generation model supporting text-to-video, first and last frame image-to-video, and reference-to-video generation with 768P and 2K output. title: MiniMax H3 image: https://developers.cloudflare.com/og-docs.png

Documentation Index
Fetch the complete documentation index at: https://developers.cloudflare.com/llms.txt
Use this file to discover all available pages before exploring further.

Muse Wonder 1.0·续4

Muse Wonder 1.0·续4

Parameters

API Schemas (Raw)

On this page