[BOT ISSUE] Groq: missing deprecation flags for qwen-2.5-coder-32b, qwen-qwq-32b, and llama-guard-3-8b

[github-actions]

Summary

Three Groq-only models are past their official shutdown dates but have no deprecated flag in the catalog. These are dead endpoints.

Model ID	Shutdown Date	Days Since Shutdown
qwen-2.5-coder-32b	2025-04-14	439
qwen-qwq-32b	2025-07-14	348
llama-guard-3-8b	2025-06-06	386

All three have available_providers: ["groq"] — Groq is their only provider.

Sources

• Groq deprecations page — lists all three with explicit shutdown dates
• Groq pricing page — none of these models are listed (confirming shutdown)

Verification

Check	Status	Detail
Cross-source	✅	Shutdown dates confirmed on deprecations page; absence confirmed on pricing page
Already fixed	✅	Confirmed no deprecation flags on any of these entries
ID format	✅	All IDs match existing catalog entries
Duplicate check	✅	Not covered by any open issue

Local Files Inspected

• packages/proxy/schema/model_list.json — qwen-2.5-coder-32b at line ~3960, qwen-qwq-32b at line ~3967, llama-guard-3-8b at line ~5517

{
  "kind": "stale_metadata",
  "provider": "groq",
  "models": ["qwen-2.5-coder-32b", "qwen-qwq-32b", "llama-guard-3-8b"],
  "status": "active",
  "model_specs": {
    "qwen-2.5-coder-32b": {
      "format": "openai",
      "flavor": "chat",
      "input_cost_per_mil_tokens": 0.29,
      "output_cost_per_mil_tokens": 0.39,
      "displayName": "Qwen 2.5 Coder 32B",
      "deprecated": true,
      "deprecation_date": "2025-04-14",
      "available_providers": ["groq"]
    },
    "qwen-qwq-32b": {
      "format": "openai",
      "flavor": "chat",
      "input_cost_per_mil_tokens": 0.29,
      "output_cost_per_mil_tokens": 0.39,
      "displayName": "Qwen QwQ 32B",
      "reasoning": true,
      "deprecated": true,
      "deprecation_date": "2025-07-14",
      "available_providers": ["groq"]
    },
    "llama-guard-3-8b": {
      "format": "openai",
      "flavor": "chat",
      "input_cost_per_mil_tokens": 0.2,
      "output_cost_per_mil_tokens": 0.2,
      "displayName": "Llama Guard 3 8B",
      "deprecated": true,
      "deprecation_date": "2025-06-06",
      "available_providers": ["groq"]
    }
  },
  "source_urls": [
    "https://console.groq.com/docs/deprecations",
    "https://groq.com/pricing/"
  ]
}

[github-actions]

Prepared catalog updates for qwen-2.5-coder-32b, qwen-qwq-32b, llama-guard-3-8b. Updated models: qwen-2.5-coder-32b, qwen-qwq-32b, llama-guard-3-8b.

Verification sources: https://console.groq.com/docs/deprecations, https://groq.com/pricing/
Verified metadata applied:

• qwen-2.5-coder-32b: format=openai, flavor=chat, displayName=Qwen 2.5 Coder 32B, max_input_tokens=not provided, max_output_tokens=not provided, pricing(input/output per 1M)=0.29/0.39, providers=groq, deprecated=true, deprecation_date=2025-04-14
• qwen-qwq-32b: format=openai, flavor=chat, displayName=Qwen QwQ 32B, max_input_tokens=not provided, max_output_tokens=not provided, pricing(input/output per 1M)=0.29/0.39, providers=groq, reasoning=true, deprecated=true, deprecation_date=2025-07-14
• llama-guard-3-8b: format=openai, flavor=chat, displayName=Llama Guard 3 8B, max_input_tokens=not provided, max_output_tokens=not provided, pricing(input/output per 1M)=0.2/0.2, providers=groq, deprecated=true, deprecation_date=2025-06-06

Included in the daily batch PR: #876