Model Routing Simulator

Static MOCK presets · deterministic policy · no live model calls · recommendations are advisory
DCP READ-ONLY: CONNECTED DEVELOPMENT / UI PREVIEW DCP BATCH 5/6 SOAK IN PROGRESS TELEMETRY: UNKNOWN COMMAND EXECUTION LOCKED
READ-ONLY SIMULATOR · Deterministic policy evaluation over a STATIC development registry. No live model calls, no routing changes, no execution. Recommendations are advisory; authority stays with the owner.

Task Input (preset scenario)

8 · UI screenshot review (vision REQUIRED)

Task typeUI_VISION_REVIEW
Agent roleQA
Risk levelR1
ComplexityLOW
Context sizeSMALL
VisionREQUIRED
Repo writeno
Long tool loopno
Architecture reasoningno
Code generationno
Security reviewno
Cost sensitivityMEDIUM
Latency sensitivityLOW
Preset expectation: only model with VERIFIED vision capability; otherwise UNKNOWN / MANUAL SELECTION.

Recommended Agent

QA

Static default policy: prefer different reviewer model from Developer when practical

Primary Model

MANUAL SELECTION (UNKNOWN — no model with sufficient evidence) NEEDS MANUAL SELECTION

Fallback Model

none eligible

Evidence

No primary model — no evidence-based selection possible.

Routing Reasons

WHY THIS MODEL?

  • BLOCKED_deepseek-v4.1-flash — DeepSeek V4.1 Flash: VISION_UNVERIFIED
  • BLOCKED_glm-5.3-flashx — GLM-5.3-Flash(x): VISION_UNVERIFIED, PARTIAL_NO_TASK_EVIDENCE
  • BLOCKED_kimi-k3 — Kimi K3: UNAVAILABLE, VISION_UNVERIFIED

Hard Blockers

  • BLOCKED_deepseek-v4.1-flash — DeepSeek V4.1 Flash: VISION_UNVERIFIED
  • BLOCKED_glm-5.3-flashx — GLM-5.3-Flash(x): VISION_UNVERIFIED, PARTIAL_NO_TASK_EVIDENCE
  • BLOCKED_kimi-k3 — Kimi K3: UNAVAILABLE, VISION_UNVERIFIED

WHAT IS STILL UNKNOWN?

  • DeepSeek V4.1 Flash: vision support UNKNOWN
  • GLM-5.3-Flash(x): vision support UNKNOWN
  • Kimi K3: vision support UNKNOWN
  • Kimi K3: cost multiplier UNKNOWN
  • no model with sufficient evidence for this task
  • UNKNOWN -> NEEDS MANUAL SELECTION

WHAT WOULD CHANGE THE DECISION?

  • If Kimi K3 becomes reachable AND accumulates verified evidence in our environment, it re-enters the candidate pool
  • If this task is R3/R4, owner approval is required regardless of model choice

Diversity-of-Failure

DIVERSITY_NOT_APPLICABLE

MODEL ROUTING != EXECUTION AUTHORITY

Selecting a model never grants sudo, Docker mutation, production write, DB mutation, deploy, network change or approval power. Authority is governed by risk policy, owner approval and DCP controls.

Model Status (static development registry)

Kimi K3 is UNAVAILABLE (HTTP 503 upstream provider failure) and is never displayed as selectable or recommended.
ModelStatusProven task classesKnown failuresLast verification
DeepSeek V4.1 FlashVERIFIEDMEDIUM_FEATURE, LARGE_FEATURE, SMALL_PATCH, CODE_REVIEW, GIT_AUDIT, README_UPDATE—2026-10-05
GLM-5.3-Flash(x)VERIFIED_FOR_MEDIUM_MULTI_FILEGIT_AUDIT, README_UPDATE, SMALL_PATCH, MEDIUM_FEATURE—2026-10-05
Kimi K3UNAVAILABLEupstream HTTP 503 on trivial prompt; provider retry failed