Model Routing Simulator — AI Company Command Center

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)

2 · Small repo hygiene patch

Task type	SMALL_PATCH
Agent role	DEVELOPER
Risk level	R1
Complexity	LOW
Context size	SMALL
Vision	NONE
Repo write	yes
Long tool loop	no
Architecture reasoning	no
Code generation	yes
Security review	no
Cost sensitivity	HIGH
Latency sensitivity	LOW

Preset expectation: GLM eligible.

Recommended Agent

DEVELOPER

Static default policy: coding evidence dominates · multi-file/long-loop evidence required for larger tasks

Primary Model

GLM-5.3-Flash(x) glm-5.3-flashx VERIFIED_FOR_MEDIUM_MULTI_FILE

Fallback Model

DeepSeek V4.1 Flash deepseek-v4.1-flash VERIFIED

DeepSeek V4.1 Flash (deepseek-v4.1-flash)

Status: VERIFIED · last verified: 2026-10-05 · provenance: STATIC_CONFIG

Verified task classes: MEDIUM_FEATURE, LARGE_FEATURE, SMALL_PATCH, CODE_REVIEW, GIT_AUDIT, README_UPDATE · Unverified: UI_VISION_REVIEW

heavy coding proven [REAL_OBSERVATION]
long agent loops proven [REAL_OBSERVATION]
multi-file repo work proven [REAL_OBSERVATION]
testing/tool loop proven [REAL_OBSERVATION]

Evidence — primary model

GLM-5.3-Flash(x) (glm-5.3-flashx)

Status: VERIFIED_FOR_MEDIUM_MULTI_FILE · last verified: 2026-10-05 · provenance: STATIC_CONFIG

Verified task classes: GIT_AUDIT, README_UPDATE, SMALL_PATCH, MEDIUM_FEATURE · Unverified: LARGE_FEATURE, SECURITY_REVIEW, UI_VISION_REVIEW

read-only Git inventory PASS [REAL_OBSERVATION]
untracked-file inspection PASS [REAL_OBSERVATION]
small repo hygiene coding patch PASS [REAL_OBSERVATION]
531-test verification PASS [REAL_OBSERVATION]
medium multi-file task PASS (MODEL_ROUTING_POLICY_SIMULATOR_V1: ~9 files, 286/286 portal tests, 39 new) [REAL_OBSERVATION]
large feature / long agent loop work NOT YET VERIFIED; one medium task is not enough evidence [REAL_OBSERVATION]

SCORE (transparent, advisory)

The weighted score is advisory only. Hard blockers always override the score. UNKNOWN never counts as positive evidence.

Dimension	Value	Static weight
Capability Match	0.60	weight 0.30
Evidence Strength	1.00	weight 0.25
Task Complexity Fit	1.00	weight 0.15
Risk Fit	0.80	weight 0.10
Context Fit	1.00	weight 0.08
Cost Fit	1.00	weight 0.07
Latency Fit	1.00	weight 0.03
Vision Fit	0.50	weight 0.02
TOTAL	0.850

Routing Reasons

WHY THIS MODEL?

STATUS — GLM-5.3-Flash(x) status = VERIFIED_FOR_MEDIUM_MULTI_FILE
EVIDENCE — verified task classes: GIT_AUDIT, README_UPDATE, SMALL_PATCH, MEDIUM_FEATURE
TASK_MATCH — direct verified evidence for task class SMALL_PATCH
COST — low-cost candidate; evidence threshold met
PARTIAL_SCOPE — VERIFIED_FOR_MEDIUM_MULTI_FILE: verification is scoped to evidenced task classes only; larger task classes remain unverified
NOT_PREFERRED_deepseek-v4.1-flash — DeepSeek V4.1 Flash scored 0.701 vs 0.85 (gap 0.149)
EXCLUDED_kimi-k3 — Kimi K3 excluded: unavailable (upstream HTTP 503 on trivial prompt; provider retry failed)
FALLBACK — fallback DeepSeek V4.1 Flash (deepseek-v4.1-flash): VERIFIED, next-best eligible score 0.701

Hard Blockers

none

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
GLM-5.3-Flash(x): large feature / long agent loop work not yet verified

WHAT WOULD CHANGE THE DECISION?

If GLM-5.3-Flash(x) accumulates 2-3 more successful medium multi-file tasks and comparative token/cost data, the default switch may be reconsidered (currently NOT YET APPROVED)
If GLM-5.3-Flash(x) completes a verified LARGE_FEATURE task, it becomes eligible for large-feature routing
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_PREFERRED QA reviewer should prefer DeepSeek V4.1 Flash (deepseek-v4.1-flash) — different failure modes from GLM-5.3-Flash(x); evidence quality preserved

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.

Model	Status	Proven task classes	Known failures	Last verification
DeepSeek V4.1 Flash	VERIFIED	MEDIUM_FEATURE, LARGE_FEATURE, SMALL_PATCH, CODE_REVIEW, GIT_AUDIT, README_UPDATE	—	2026-10-05
GLM-5.3-Flash(x)	VERIFIED_FOR_MEDIUM_MULTI_FILE	GIT_AUDIT, README_UPDATE, SMALL_PATCH, MEDIUM_FEATURE	—	2026-10-05
Kimi K3	UNAVAILABLE	upstream HTTP 503 on trivial prompt; provider retry failed