hotfix: Prefer NVIDIA NIM models in OpenCode review pool

.github/workflows/opencode-review-dispatch.yml

@@ -3411,9 +3411,9 @@ jobs:
 
           jq -n '{
             "$schema": "https://opencode.ai/config.json",
-            "model": "github-models/deepseek/deepseek-r1-0528",
-            "small_model": "github-models/deepseek/deepseek-v3-0324",
-            "enabled_providers": ["opencode-free", "opencode", "openai", "openrouter", "github-models"],
+            "model": "nvidia-nim/nvidia/llama-3.3-nemotron-super-49b-v1.5",
+            "small_model": "nvidia-nim/meta/llama-3.3-70b-instruct",
+            "enabled_providers": ["nvidia-nim", "opencode-free", "opencode", "openai", "openrouter", "github-models"],
             "lsp": false,
             "mcp": {},
             "permission": {
@@ -3714,6 +3714,96 @@ jobs:
                   }
                 }
               },
+              "nvidia-nim": {
+                "npm": "@ai-sdk/openai-compatible",
+                "name": "NVIDIA NIM",
+                "options": {
+                  "baseURL": "https://integrate.api.nvidia.com/v1",
+                  "apiKey": "{env:NVIDIA_API_KEY}"
+                },
+                "models": {
+                  "nvidia/llama-3.3-nemotron-super-49b-v1.5": {
+                    "name": "NVIDIA Llama 3.3 Nemotron Super 49B v1.5",
+                    "tool_call": true,
+                    "limit": {
+                      "context": 131072,
+                      "output": 8192
+                    }
+                  },
+                  "nvidia/llama-3.1-nemotron-ultra-253b-v1": {
+                    "name": "NVIDIA Llama 3.1 Nemotron Ultra 253B",
+                    "tool_call": true,
+                    "limit": {
+                      "context": 131072,
+                      "output": 8192
+                    }
+                  },
+                  "nvidia/nemotron-3-super-120b-a12b": {
+                    "name": "NVIDIA Nemotron 3 Super 120B",
+                    "tool_call": true,
+                    "limit": {
+                      "context": 131072,
+                      "output": 8192
+                    }
+                  },
+                  "nvidia/nemotron-3-ultra-550b-a55b": {
+                    "name": "NVIDIA Nemotron 3 Ultra 550B",
+                    "tool_call": true,
+                    "limit": {
+                      "context": 131072,
+                      "output": 8192
+                    }
+                  },
+                  "meta/llama-3.3-70b-instruct": {
+                    "name": "Meta Llama 3.3 70B Instruct (NIM)",
+                    "tool_call": true,
+                    "limit": {
+                      "context": 131072,
+                      "output": 8192
+                    }
+                  },
+                  "meta/llama-3.1-70b-instruct": {
+                    "name": "Meta Llama 3.1 70B Instruct (NIM)",
+                    "tool_call": true,
+                    "limit": {
+                      "context": 131072,
+                      "output": 8192
+                    }
+                  },
+                  "deepseek-ai/deepseek-v4-pro": {
+                    "name": "DeepSeek V4 Pro (NIM)",
+                    "tool_call": true,
+                    "limit": {
+                      "context": 131072,
+                      "output": 8192
+                    }
+                  },
+                  "mistralai/mistral-large-2-instruct": {
+                    "name": "Mistral Large 2 Instruct (NIM)",
+                    "tool_call": true,
+                    "limit": {
+                      "context": 131072,
+                      "output": 8192
+                    }
+                  },
+                  "mistralai/codestral-22b-instruct-v0.1": {
+                    "name": "Codestral 22B Instruct (NIM)",
+                    "tool_call": true,
+                    "limit": {
+                      "context": 32768,
+                      "output": 8192
+                    }
+                  },
+                  "google/gemma-4-31b-it": {
+                    "name": "Gemma 4 31B IT (NIM)",
+                    "tool_call": true,
+                    "limit": {
+                      "context": 131072,
+                      "output": 8192
+                    }
+                  }
+                }
+              },
               "github-models": {
                 "npm": "@ai-sdk/openai-compatible",
                 "name": "GitHub Models",
@@ -3920,6 +4010,12 @@ jobs:
             }
           }' >"${OPENCODE_REVIEW_WORKDIR}/opencode.jsonc"
 
+
+          if ! grep -Fq 'nvidia-nim' "${OPENCODE_REVIEW_WORKDIR}/opencode.jsonc" \
+            || ! grep -Fq 'integrate.api.nvidia.com' "${OPENCODE_REVIEW_WORKDIR}/opencode.jsonc"; then
+            echo '::error::Generated isolated opencode.jsonc is missing the nvidia-nim provider; refusing to run the model pool without NIM priority.'
+            exit 1
+          fi
           printf 'Prepared isolated OpenCode review workspace: %s\n' "$OPENCODE_REVIEW_WORKDIR"
 
       - name: Run OpenCode PR Review model pool
@@ -3937,6 +4033,7 @@ jobs:
           # in the opencode.jsonc "openai" provider block.
           OPENCODE_API_KEY: ${{ secrets.OPENCODE_ZEN_API_KEY }}
           OPENAI_API_KEY: ${{ secrets.OPENAI_API_KEY }}
+          NVIDIA_API_KEY: ${{ secrets.NVIDIA_API_KEY }}
           OPENROUTER_API_KEY: ${{ secrets.OPENROUTER_API_KEY }}
           SHARE: "false"
           NPM_CONFIG_IGNORE_SCRIPTS: "true"
@@ -3958,7 +4055,7 @@ jobs:
           # cost-efficient tier, cheaper than the legacy gpt-5 it replaced
           # ($1/$6 vs $1.25/$10 per 1M tokens) so the org OpenAI budget
           # stretches further between top-ups.
-          OPENCODE_MODEL_CANDIDATES: "${{ needs.validate-pr-metadata.outputs.is_private == 'false' && 'opencode-free/nemotron-3-ultra-free opencode-free/deepseek-v4-flash-free opencode-free/north-mini-code-free opencode-free/laguna-s-2.1-free opencode-free/ling-3.0-flash-free opencode-free/big-pickle opencode-free/mimo-v2.5-free ' || '' }}opencode/gpt-5.6-terra github-models/deepseek/deepseek-v3-0324 openai/gpt-5.6-luna openrouter/deepseek/deepseek-v3.2 openrouter/qwen/qwen3-coder github-models/openai/gpt-4.1 github-models/openai/gpt-5 github-models/openai/gpt-5-chat github-models/openai/o3 github-models/deepseek/deepseek-r1-0528 github-models/deepseek/deepseek-r1"
+          OPENCODE_MODEL_CANDIDATES: "${{ needs.validate-pr-metadata.outputs.is_private == 'false' && 'opencode-free/nemotron-3-ultra-free opencode-free/deepseek-v4-flash-free opencode-free/north-mini-code-free opencode-free/laguna-s-2.1-free opencode-free/ling-3.0-flash-free opencode-free/big-pickle opencode-free/mimo-v2.5-free ' || '' }}nvidia-nim/nvidia/llama-3.3-nemotron-super-49b-v1.5 nvidia-nim/nvidia/llama-3.1-nemotron-ultra-253b-v1 nvidia-nim/nvidia/nemotron-3-super-120b-a12b nvidia-nim/meta/llama-3.3-70b-instruct nvidia-nim/deepseek-ai/deepseek-v4-pro nvidia-nim/mistralai/codestral-22b-instruct-v0.1 opencode/gpt-5.6-terra github-models/deepseek/deepseek-v3-0324 openai/gpt-5.6-luna openrouter/deepseek/deepseek-v3.2 openrouter/qwen/qwen3-coder github-models/openai/gpt-4.1 github-models/openai/gpt-5 github-models/openai/gpt-5-chat github-models/openai/o3 github-models/deepseek/deepseek-r1-0528 github-models/deepseek/deepseek-r1"
           # One attempt per model, then fall through to the next model. Retrying
           # the SAME model 5x let a rate-limited/hung leader consume the whole
           # step, so the pool never reached a healthy fallback model.
@@ -4592,6 +4689,7 @@ jobs:
           # Exposed so the "openai" provider in opencode.jsonc resolves during the
           # failed-check diagnosis opencode run that shares this config.
           OPENAI_API_KEY: ${{ secrets.OPENAI_API_KEY }}
+          NVIDIA_API_KEY: ${{ secrets.NVIDIA_API_KEY }}
           OPENCODE_APP_TOKEN: ${{ steps.opencode_app_token.outputs.token }}
           OPENCODE_EVIDENCE_FILE: ${{ runner.temp }}/opencode-review-evidence.md
           OPENCODE_FAILED_CHECK_EVIDENCE_FILE: ${{ runner.temp }}/opencode-failed-check-evidence.md

docs/nvidia-nim-opencode-hotfix.md

@@ -0,0 +1,41 @@
+# NVIDIA NIM OpenCode model priority (hotfix)
+
+## Why
+
+OpenCode Agent failed to produce a usable review on the PR thread starting at
+ContextualWisdomLab/fast-mlsirm#290 (`opencode-review` check **skipped**, no
+`opencode-agent[bot]` review comment). Central review therefore prioritizes
+**NVIDIA NIM** models as additional catalog candidates so the model pool can
+still emit APPROVE / REQUEST_CHANGES when GitHub Models / free tiers stall.
+
+## Changes
+
+1. `opencode.jsonc`
+   - `enabled_providers`: `nvidia-nim` first, then `github-models`
+   - default `model` / `small_model` prefer NIM Nemotron / Llama 3.3
+   - new OpenAI-compatible provider `nvidia-nim` → `https://integrate.api.nvidia.com/v1`
+     with `apiKey: {env:NVIDIA_API_KEY}`
+2. `.github/workflows/opencode-review-dispatch.yml`
+   - `OPENCODE_MODEL_CANDIDATES` prefixes six NIM models before existing pool
+   - binds `NVIDIA_API_KEY: ${{ secrets.NVIDIA_API_KEY }}`
+3. `scripts/ci/run_opencode_review_model_pool.sh`
+   - skips `nvidia-nim/*` when `NVIDIA_API_KEY` is unset (same pattern as OpenRouter)
+
+## Temporary permission bypass (hotfix only)
+
+For this merge-aid hotfix only:
+
+- Branch-protection / ruleset admin override may be used to land the central
+  `.github` change if required checks conflict during the hotfix window.
+- **Do not** permanently weaken Security Scan, trivy-fs, osv-scan, or
+  CodeQL gates.
+- **Do not** flip OpenCode agent `permission.edit` / `bash` from `deny` to
+  `allow` permanently; review agents remain read-only.
+- Org secret `NVIDIA_API_KEY` must be set on ContextualWisdomLab for NIM pool
+  entries to execute; without it the pool falls through to prior candidates.
+
+## Rollback
+
+Remove the `nvidia-nim/*` prefixes from `OPENCODE_MODEL_CANDIDATES`, drop the
+`nvidia-nim` provider block, and delete this note once GitHub Models / OpenCode
+catalog reliability is restored.

opencode.jsonc

@@ -1,8 +1,8 @@
 {
   "$schema": "https://opencode.ai/config.json",
-  "model": "github-models/deepseek/deepseek-r1-0528",
-  "small_model": "github-models/deepseek/deepseek-v3-0324",
-  "enabled_providers": ["github-models"],
+  "model": "nvidia-nim/nvidia/llama-3.3-nemotron-super-49b-v1.5",
+  "small_model": "nvidia-nim/meta/llama-3.3-70b-instruct",
+  "enabled_providers": ["nvidia-nim", "github-models"],
   "lsp": false,
   "mcp": {},
   "permission": {
@@ -281,6 +281,96 @@
           }
         }
       }
+    },
+    "nvidia-nim": {
+      "npm": "@ai-sdk/openai-compatible",
+      "name": "NVIDIA NIM",
+      "options": {
+        "baseURL": "https://integrate.api.nvidia.com/v1",
+        "apiKey": "{env:NVIDIA_API_KEY}"
+      },
+      "models": {
+        "nvidia/llama-3.3-nemotron-super-49b-v1.5": {
+          "name": "NVIDIA Llama 3.3 Nemotron Super 49B v1.5",
+          "tool_call": true,
+          "limit": {
+            "context": 131072,
+            "output": 8192
+          }
+        },
+        "nvidia/llama-3.1-nemotron-ultra-253b-v1": {
+          "name": "NVIDIA Llama 3.1 Nemotron Ultra 253B",
+          "tool_call": true,
+          "limit": {
+            "context": 131072,
+            "output": 8192
+          }
+        },
+        "nvidia/nemotron-3-super-120b-a12b": {
+          "name": "NVIDIA Nemotron 3 Super 120B",
+          "tool_call": true,
+          "limit": {
+            "context": 131072,
+            "output": 8192
+          }
+        },
+        "nvidia/nemotron-3-ultra-550b-a55b": {
+          "name": "NVIDIA Nemotron 3 Ultra 550B",
+          "tool_call": true,
+          "limit": {
+            "context": 131072,
+            "output": 8192
+          }
+        },
+        "meta/llama-3.3-70b-instruct": {
+          "name": "Meta Llama 3.3 70B Instruct (NIM)",
+          "tool_call": true,
+          "limit": {
+            "context": 131072,
+            "output": 8192
+          }
+        },
+        "meta/llama-3.1-70b-instruct": {
+          "name": "Meta Llama 3.1 70B Instruct (NIM)",
+          "tool_call": true,
+          "limit": {
+            "context": 131072,
+            "output": 8192
+          }
+        },
+        "deepseek-ai/deepseek-v4-pro": {
+          "name": "DeepSeek V4 Pro (NIM)",
+          "tool_call": true,
+          "limit": {
+            "context": 131072,
+            "output": 8192
+          }
+        },
+        "mistralai/mistral-large-2-instruct": {
+          "name": "Mistral Large 2 Instruct (NIM)",
+          "tool_call": true,
+          "limit": {
+            "context": 131072,
+            "output": 8192
+          }
+        },
+        "mistralai/codestral-22b-instruct-v0.1": {
+          "name": "Codestral 22B Instruct (NIM)",
+          "tool_call": true,
+          "limit": {
+            "context": 32768,
+            "output": 8192
+          }
+        },
+        "google/gemma-4-31b-it": {
+          "name": "Gemma 4 31B IT (NIM)",
+          "tool_call": true,
+          "limit": {
+            "context": 131072,
+            "output": 8192
+          }
+        }
+      }
     }
   }
 }

scripts/ci/run_opencode_review_model_pool.sh

@@ -345,6 +345,13 @@ is_openrouter_candidate() {
 	esac
 }
 
+is_nvidia_nim_candidate() {
+	case "$1" in
+	nvidia-nim/*) return 0 ;;
+	*) return 1 ;;
+	esac
+}
+
 is_low_sensitivity_candidate() {
 	case "$1" in
 	openai/*-mini | openai/*-nano | \
@@ -372,6 +379,10 @@ should_skip_model_candidate() {
 		printf 'Skipping OpenCode %s because OPENROUTER_API_KEY is not configured; falling back to the next provider-qualified candidate.\n' "$model_candidate"
 		return 0
 	fi
+	if is_nvidia_nim_candidate "$model_candidate" && [ -z "${NVIDIA_API_KEY:-}" ]; then
+		printf 'Skipping OpenCode %s because NVIDIA_API_KEY is not configured; falling back to the next provider-qualified candidate.\n' "$model_candidate"
+		return 0
+	fi
 	return 1
 }