gen_xi6jotfdc8

Decision timeline

1. admission+0 ms

   chat request by prin_admin under profile @company/general-balanced (requested "@company/general-balanced")

2. PRE_ROUTE+0 ms
   allowsize-budgetno findings [0.00ms]
3. PRE_ROUTE+0 ms
   allowprompt-injection-heuristicno findings [0.00ms]
4. PRE_MODEL+0 ms
   allowpattern-dlpno findings [0.00ms]
5. PRE_MODEL+0 ms
   allowsecrets-scannerno findings [0.00ms]
6. cache+0 ms

   cache bypassed (policy off or non-cacheable request)

7. route+0 ms

   selected openai/gpt-5.2 via openai/acct_openai_pool_b_apse1 on node_my_kul_office_01 (B-tier, ap-southeast-1) — objective=balanced, 12 candidates scored, 11 in fallback chain, 6 hard-filter rejections [router router_1.0, policy rp_default/@company/general-balanced@v7]

   18 candidates considered12 survived hard filters6 rejectedobjective: balancedfallback chain: 11router_1.0 · rp_default/@company/general-balanced@v7

   Hard-filter rejections

   • ep_sonnet_anthropic_apse1@node_sg_dc_01egress node node_sg_dc_01 is quarantined
   • ep_sonnet_anthropic_use1@node_sg_dc_01egress node node_sg_dc_01 is quarantined
   • ep_sonnet_bedrock_apse1@node_sg_dc_01egress node node_sg_dc_01 is quarantined
   • ep_gpt52_openai_use1@node_sg_dc_01egress node node_sg_dc_01 is quarantined
   • ep_gpt52_openai_apse1@node_sg_dc_01egress node node_sg_dc_01 is quarantined
   • ep_g3pro_vertex_euw1@node_sg_dc_01egress node node_sg_dc_01 is quarantined

   Score breakdown — top 5

   #	Candidate	quality	cacheSavings	contractValue	completionProbability	cost	latencyPenalty	shadowPrice	retryRisk	affinityPenalty	guardrailCost	Total
   1	openai/gpt-5.2 via openai · node_my_kul_office_01 selected	+0.546	0.000	0.000	+0.388	-0.025	-0.043	-0.010	-0.007	0.000	-0.040	0.809
   2	openai/gpt-5.2 via openai · node_cf_use1_01	+0.546	0.000	0.000	+0.398	-0.025	-0.041	-0.010	-0.001	0.000	-0.060	0.807
   3	anthropic/claude-sonnet via anthropic · node_cf_use1_01	+0.546	0.000	+0.024	+0.398	-0.037	-0.061	-0.029	-0.001	0.000	-0.040	0.800
   4	openai/gpt-5.2 via openai · node_my_kul_office_02	+0.546	0.000	0.000	+0.372	-0.025	-0.044	-0.010	-0.018	0.000	-0.040	0.782
   5	anthropic/claude-sonnet via anthropic · node_my_kul_office_01	+0.546	0.000	+0.024	+0.388	-0.037	-0.063	-0.029	-0.007	0.000	-0.040	0.781

8. attempt #1+0 ms

   #1 openai · account acct_openai_pool_b_apse1 · node node_my_kul_office_01 — succeeded in 1401ms

   succeededopenaiacct_openai_pool_b_apse1pool pool-bnode_my_kul_office_01Tier B1.40 s

   16 in / 335 out

9. POST_MODEL+0 ms
   allowtoxicity-liteno findings [0.00ms]
10. PRE_RETURN+0 ms
    allowschema-validatorno findings [0.00ms]
11. settlement+1401 ms

    settled $0.003370 — 16 in / 335 out tokens (351 total)

    Ledger entries

    • reserve$0.0036budget:bud_proj_corereserve est max for @company/general-balanced
    • settle$0.0034budget:bud_proj_coresettle actual provider usage (351 tok, internal charge $0.003876)
    • settle−$0.0034account:acct_openai_pool_b_apse1credit provider account acct_openai_pool_b_apse1 (double-entry counterpart)
    • refund−$0.0002budget:bud_proj_corerefund unused reservation

    Cost layers (memo §15.3)

    Provider list

    $0.0034

    Contract-adjusted

    $0.0034

    Internal charge

    $0.0039

    Contract savings

    $0.00

    contract ct_openai_metered (metered)

12. complete+1401 ms

    status=succeeded, model=openai/gpt-5.2, 1401ms end-to-end

fabric_metadata

The route-explanation envelope an API caller receives with X-OpenRouter-Metadata: enabled or routing.explain, reconstructed from this generation record.

{
  "requested": "@company/general-balanced",
  "resolved_model": "openai/gpt-5.2",
  "strategy": "balanced",
  "policy_version": "rp_default/@company/general-balanced@v7",
  "router_version": "router_1.0",
  "provider": "openai",
  "region": "ap-southeast-1",
  "account_pool": "pool-b",
  "node": {
    "ref": "node_my_kul_office_01",
    "trust_tier": "B"
  },
  "cache": {
    "response": "BYPASS",
    "prompt_affinity": "MISS",
    "predicted_cached_tokens": 0
  },
  "guardrails": [
    {
      "stage": "PRE_ROUTE",
      "action": "allow",
      "profile": "gp_baseline",
      "evaluations": 2
    },
    {
      "stage": "PRE_MODEL",
      "action": "allow",
      "profile": "gp_baseline",
      "evaluations": 2
    },
    {
      "stage": "POST_MODEL",
      "action": "allow",
      "profile": "gp_baseline",
      "evaluations": 1
    },
    {
      "stage": "PRE_RETURN",
      "action": "allow",
      "profile": "gp_baseline",
      "evaluations": 1
    }
  ],
  "attempts": [
    {
      "provider": "openai",
      "status": 200
    }
  ],
  "routing_reason": [
    "selected openai/gpt-5.2 via openai (balanced objective, score 0.8089)",
    "6 candidate(s) rejected by hard filters"
  ]
}