@HOYALIM has signed the CLA in code-yeongyu/oh-my-openagent#2935

- background_output: snapshot read cursor before consuming, restore on
  /undo message removal so re-reads return data (fixes #2915)
- MCP loader: preserve oauth field in transformMcpServer, add scope/
  projectPath filtering so local-scoped MCPs only load in matching
  directories (fixes #2917)
- runtime-fallback: add 'reached your usage limit' to retryable error
  patterns so quota exhaustion triggers model fallback (fixes #2918)

Verified: bun test (4606 pass / 0 fail), tsc --noEmit clean

.github/workflows/ci.yml

@@ -60,16 +60,33 @@ jobs:
           bun test src/features/opencode-skill-loader/loader.test.ts
           bun test src/hooks/anthropic-context-window-limit-recovery/recovery-hook.test.ts
           bun test src/hooks/anthropic-context-window-limit-recovery/executor.test.ts
+          # src/shared mock-heavy files (mock.module pollutes connected-providers-cache and legacy-plugin-warning)
+          bun test src/shared/model-capabilities.test.ts
+          bun test src/shared/log-legacy-plugin-startup-warning.test.ts
+          bun test src/shared/model-error-classifier.test.ts
+          bun test src/shared/opencode-message-dir.test.ts
+          # session-recovery mock isolation (recover-tool-result-missing mocks ./storage)
+          bun test src/hooks/session-recovery/recover-tool-result-missing.test.ts
+          # legacy-plugin-toast mock isolation (hook.test.ts mocks ./auto-migrate)
+          bun test src/hooks/legacy-plugin-toast/hook.test.ts
 
       - name: Run remaining tests
         run: |
           # Enumerate subdirectories/files explicitly to EXCLUDE mock-heavy files
           # that were already run in isolation above.
+          # Excluded from src/shared: model-capabilities, log-legacy-plugin-startup-warning, model-error-classifier, opencode-message-dir
           # Excluded from src/cli: doctor/formatter.test.ts, doctor/format-default.test.ts
           # Excluded from src/tools: call-omo-agent/sync-executor.test.ts, call-omo-agent/session-creator.test.ts, session-manager (all)
           # Excluded from src/hooks/anthropic-context-window-limit-recovery: recovery-hook.test.ts, executor.test.ts
+          # Build src/shared file list excluding mock-heavy files already run in isolation
+          SHARED_FILES=$(find src/shared -name '*.test.ts' \
+            ! -name 'model-capabilities.test.ts' \
+            ! -name 'log-legacy-plugin-startup-warning.test.ts' \
+            ! -name 'model-error-classifier.test.ts' \
+            ! -name 'opencode-message-dir.test.ts' \
+            | sort | tr '\n' ' ')
           bun test bin script src/config src/mcp src/index.test.ts \
-            src/agents src/shared \
+            src/agents $SHARED_FILES \
             src/cli/run src/cli/config-manager src/cli/mcp-oauth \
             src/cli/index.test.ts src/cli/install.test.ts src/cli/model-fallback.test.ts \
             src/cli/config-manager.test.ts \
@@ -82,6 +99,8 @@ jobs:
             src/tools/call-omo-agent/background-executor.test.ts \
             src/tools/call-omo-agent/subagent-session-creator.test.ts \
             src/hooks/anthropic-context-window-limit-recovery/empty-content-recovery-sdk.test.ts src/hooks/anthropic-context-window-limit-recovery/parser.test.ts src/hooks/anthropic-context-window-limit-recovery/pruning-deduplication.test.ts src/hooks/anthropic-context-window-limit-recovery/recovery-deduplication.test.ts src/hooks/anthropic-context-window-limit-recovery/storage.test.ts \
+            src/hooks/session-recovery/detect-error-type.test.ts src/hooks/session-recovery/index.test.ts src/hooks/session-recovery/recover-empty-content-message-sdk.test.ts src/hooks/session-recovery/resume.test.ts src/hooks/session-recovery/storage \
+            src/hooks/legacy-plugin-toast/auto-migrate.test.ts \
             src/hooks/claude-code-compatibility \
             src/hooks/context-injection \
             src/hooks/provider-toast \

.github/workflows/publish-platform.yml

@@ -56,10 +56,33 @@ jobs:
         env:
           BUN_INSTALL_ALLOW_SCRIPTS: "@ast-grep/napi"
 
+      - name: Validate release inputs
+        id: validate
+        env:
+          INPUT_VERSION: ${{ inputs.version }}
+          INPUT_DIST_TAG: ${{ inputs.dist_tag }}
+        run: |
+          VERSION="$INPUT_VERSION"
+          DIST_TAG="$INPUT_DIST_TAG"
+
+          if ! [[ "$VERSION" =~ ^[0-9]+\.[0-9]+\.[0-9]+(-[0-9A-Za-z]+(\.[0-9A-Za-z]+)*)?$ ]]; then
+            echo "::error::Invalid version: $VERSION"
+            exit 1
+          fi
+
+          if [ -n "$DIST_TAG" ] && ! [[ "$DIST_TAG" =~ ^[a-z][a-z0-9-]*$ ]]; then
+            echo "::error::Invalid dist_tag: $DIST_TAG"
+            exit 1
+          fi
+
+          echo "version=$VERSION" >> $GITHUB_OUTPUT
+          echo "dist_tag=$DIST_TAG" >> $GITHUB_OUTPUT
+
       - name: Check if already published
         id: check
+        env:
+          VERSION: ${{ steps.validate.outputs.version }}
         run: |
-          VERSION="${{ inputs.version }}"
           PLATFORM_KEY="${{ matrix.platform }}"
           PLATFORM_KEY="${PLATFORM_KEY//-/_}"
           
@@ -96,15 +119,18 @@ jobs:
 
       - name: Update version in package.json
         if: steps.check.outputs.skip != 'true'
+        env:
+          VERSION: ${{ steps.validate.outputs.version }}
         run: |
-          VERSION="${{ inputs.version }}"
           cd packages/${{ matrix.platform }}
           jq --arg v "$VERSION" '.version = $v' package.json > tmp.json && mv tmp.json package.json
 
       - name: Set root package version
         if: steps.check.outputs.skip != 'true'
+        env:
+          VERSION: ${{ steps.validate.outputs.version }}
         run: |
-          jq --arg v "${{ inputs.version }}" '.version = $v' package.json > tmp.json && mv tmp.json package.json
+          jq --arg v "$VERSION" '.version = $v' package.json > tmp.json && mv tmp.json package.json
 
       - name: Pre-download baseline compile target
         if: steps.check.outputs.skip != 'true' && endsWith(matrix.platform, '-baseline')
@@ -226,11 +252,33 @@ jobs:
       matrix:
         platform: [darwin-arm64, darwin-x64, darwin-x64-baseline, linux-x64, linux-x64-baseline, linux-arm64, linux-x64-musl, linux-x64-musl-baseline, linux-arm64-musl, windows-x64, windows-x64-baseline]
     steps:
+      - name: Validate release inputs
+        id: validate
+        env:
+          INPUT_VERSION: ${{ inputs.version }}
+          INPUT_DIST_TAG: ${{ inputs.dist_tag }}
+        run: |
+          VERSION="$INPUT_VERSION"
+          DIST_TAG="$INPUT_DIST_TAG"
+
+          if ! [[ "$VERSION" =~ ^[0-9]+\.[0-9]+\.[0-9]+(-[0-9A-Za-z]+(\.[0-9A-Za-z]+)*)?$ ]]; then
+            echo "::error::Invalid version: $VERSION"
+            exit 1
+          fi
+
+          if [ -n "$DIST_TAG" ] && ! [[ "$DIST_TAG" =~ ^[a-z][a-z0-9-]*$ ]]; then
+            echo "::error::Invalid dist_tag: $DIST_TAG"
+            exit 1
+          fi
+
+          echo "version=$VERSION" >> $GITHUB_OUTPUT
+          echo "dist_tag=$DIST_TAG" >> $GITHUB_OUTPUT
+
       - name: Check if already published
         id: check
+        env:
+          VERSION: ${{ steps.validate.outputs.version }}
         run: |
-          VERSION="${{ inputs.version }}"
-          
           OC_STATUS=$(curl -s -o /dev/null -w "%{http_code}" "https://registry.npmjs.org/oh-my-opencode-${{ matrix.platform }}/${VERSION}")
           OA_STATUS=$(curl -s -o /dev/null -w "%{http_code}" "https://registry.npmjs.org/oh-my-openagent-${{ matrix.platform }}/${VERSION}")
           
@@ -288,38 +336,38 @@ jobs:
 
       - name: Publish oh-my-opencode-${{ matrix.platform }}
         if: steps.check.outputs.skip_opencode != 'true' && steps.download.outcome == 'success'
-        run: |
-          cd packages/${{ matrix.platform }}
-          
-          TAG_ARG=""
-          if [ -n "${{ inputs.dist_tag }}" ]; then
-            TAG_ARG="--tag ${{ inputs.dist_tag }}"
-          fi
-          
-          npm publish --access public --provenance $TAG_ARG
         env:
+          DIST_TAG: ${{ steps.validate.outputs.dist_tag }}
           NODE_AUTH_TOKEN: ${{ secrets.NODE_AUTH_TOKEN }}
           NPM_CONFIG_PROVENANCE: true
+        run: |
+          cd packages/${{ matrix.platform }}
+
+          if [ -n "$DIST_TAG" ]; then
+            npm publish --access public --provenance --tag "$DIST_TAG"
+          else
+            npm publish --access public --provenance
+          fi
         timeout-minutes: 15
 
       - name: Publish oh-my-openagent-${{ matrix.platform }}
         if: steps.check.outputs.skip_openagent != 'true' && steps.download.outcome == 'success'
+        env:
+          DIST_TAG: ${{ steps.validate.outputs.dist_tag }}
+          NODE_AUTH_TOKEN: ${{ secrets.NODE_AUTH_TOKEN }}
+          NPM_CONFIG_PROVENANCE: true
         run: |
           cd packages/${{ matrix.platform }}
-          
+
           # Rename package for oh-my-openagent
           jq --arg name "oh-my-openagent-${{ matrix.platform }}" \
              --arg desc "Platform-specific binary for oh-my-openagent (${{ matrix.platform }})" \
              '.name = $name | .description = $desc | .bin = {"oh-my-openagent": (.bin | to_entries | .[0].value)}' \
              package.json > tmp.json && mv tmp.json package.json
-          
-          TAG_ARG=""
-          if [ -n "${{ inputs.dist_tag }}" ]; then
-            TAG_ARG="--tag ${{ inputs.dist_tag }}"
+
+          if [ -n "$DIST_TAG" ]; then
+            npm publish --access public --provenance --tag "$DIST_TAG"
+          else
+            npm publish --access public --provenance
           fi
-          
-          npm publish --access public --provenance $TAG_ARG
-        env:
-          NODE_AUTH_TOKEN: ${{ secrets.NODE_AUTH_TOKEN }}
-          NPM_CONFIG_PROVENANCE: true
         timeout-minutes: 15

.github/workflows/publish.yml

@@ -57,32 +57,51 @@ jobs:
           bun test src/cli/doctor/format-default.test.ts
           bun test src/tools/call-omo-agent/sync-executor.test.ts
           bun test src/tools/call-omo-agent/session-creator.test.ts
+          bun test src/tools/session-manager
           bun test src/features/opencode-skill-loader/loader.test.ts
           bun test src/hooks/anthropic-context-window-limit-recovery/recovery-hook.test.ts
           bun test src/hooks/anthropic-context-window-limit-recovery/executor.test.ts
+          # src/shared mock-heavy files (mock.module pollutes connected-providers-cache and legacy-plugin-warning)
+          bun test src/shared/model-capabilities.test.ts
+          bun test src/shared/log-legacy-plugin-startup-warning.test.ts
+          bun test src/shared/model-error-classifier.test.ts
+          bun test src/shared/opencode-message-dir.test.ts
+          # session-recovery mock isolation (recover-tool-result-missing mocks ./storage)
+          bun test src/hooks/session-recovery/recover-tool-result-missing.test.ts
+          # legacy-plugin-toast mock isolation (hook.test.ts mocks ./auto-migrate)
+          bun test src/hooks/legacy-plugin-toast/hook.test.ts
 
       - name: Run remaining tests
         run: |
           # Enumerate subdirectories/files explicitly to EXCLUDE mock-heavy files
           # that were already run in isolation above.
+          # Excluded from src/shared: model-capabilities, log-legacy-plugin-startup-warning, model-error-classifier, opencode-message-dir
           # Excluded from src/cli: doctor/formatter.test.ts, doctor/format-default.test.ts
-          # Excluded from src/tools: call-omo-agent/sync-executor.test.ts, call-omo-agent/session-creator.test.ts
+          # Excluded from src/tools: call-omo-agent/sync-executor.test.ts, call-omo-agent/session-creator.test.ts, session-manager (all)
           # Excluded from src/hooks/anthropic-context-window-limit-recovery: recovery-hook.test.ts, executor.test.ts
-          # Excluded from src/tools: call-omo-agent/sync-executor.test.ts, call-omo-agent/session-creator.test.ts
+          # Build src/shared file list excluding mock-heavy files already run in isolation
+          SHARED_FILES=$(find src/shared -name '*.test.ts' \
+            ! -name 'model-capabilities.test.ts' \
+            ! -name 'log-legacy-plugin-startup-warning.test.ts' \
+            ! -name 'model-error-classifier.test.ts' \
+            ! -name 'opencode-message-dir.test.ts' \
+            | sort | tr '\n' ' ')
           bun test bin script src/config src/mcp src/index.test.ts \
-            src/agents src/shared \
+            src/agents $SHARED_FILES \
             src/cli/run src/cli/config-manager src/cli/mcp-oauth \
             src/cli/index.test.ts src/cli/install.test.ts src/cli/model-fallback.test.ts \
             src/cli/config-manager.test.ts \
             src/cli/doctor/runner.test.ts src/cli/doctor/checks \
             src/tools/ast-grep src/tools/background-task src/tools/delegate-task \
             src/tools/glob src/tools/grep src/tools/interactive-bash \
-            src/tools/look-at src/tools/lsp src/tools/session-manager \
+            src/tools/look-at src/tools/lsp \
             src/tools/skill src/tools/skill-mcp src/tools/slashcommand src/tools/task \
             src/tools/call-omo-agent/background-agent-executor.test.ts \
             src/tools/call-omo-agent/background-executor.test.ts \
             src/tools/call-omo-agent/subagent-session-creator.test.ts \
             src/hooks/anthropic-context-window-limit-recovery/empty-content-recovery-sdk.test.ts src/hooks/anthropic-context-window-limit-recovery/parser.test.ts src/hooks/anthropic-context-window-limit-recovery/pruning-deduplication.test.ts src/hooks/anthropic-context-window-limit-recovery/recovery-deduplication.test.ts src/hooks/anthropic-context-window-limit-recovery/storage.test.ts \
+            src/hooks/session-recovery/detect-error-type.test.ts src/hooks/session-recovery/index.test.ts src/hooks/session-recovery/recover-empty-content-message-sdk.test.ts src/hooks/session-recovery/resume.test.ts src/hooks/session-recovery/storage \
+            src/hooks/legacy-plugin-toast/auto-migrate.test.ts \
             src/hooks/claude-code-compatibility \
             src/hooks/context-injection \
             src/hooks/provider-toast \
@@ -148,33 +167,47 @@ jobs:
 
       - name: Calculate version
         id: version
+        env:
+          RAW_VERSION: ${{ inputs.version }}
+          BUMP: ${{ inputs.bump }}
         run: |
-          VERSION="${{ inputs.version }}"
+          VERSION="$RAW_VERSION"
           if [ -z "$VERSION" ]; then
             PREV=$(curl -s https://registry.npmjs.org/oh-my-opencode/latest | jq -r '.version // "0.0.0"')
             BASE="${PREV%%-*}"
             IFS='.' read -r MAJOR MINOR PATCH <<< "$BASE"
-            case "${{ inputs.bump }}" in
+            case "$BUMP" in
               major) VERSION="$((MAJOR+1)).0.0" ;;
               minor) VERSION="${MAJOR}.$((MINOR+1)).0" ;;
               *) VERSION="${MAJOR}.${MINOR}.$((PATCH+1))" ;;
             esac
           fi
+
+          if ! [[ "$VERSION" =~ ^[0-9]+\.[0-9]+\.[0-9]+(-[0-9A-Za-z]+(\.[0-9A-Za-z]+)*)?$ ]]; then
+            echo "::error::Invalid version: $VERSION"
+            exit 1
+          fi
+
           echo "version=$VERSION" >> $GITHUB_OUTPUT
-          
+
           if [[ "$VERSION" == *"-"* ]]; then
-            DIST_TAG=$(echo "$VERSION" | cut -d'-' -f2 | cut -d'.' -f1)
+            DIST_TAG=$(printf '%s' "$VERSION" | cut -d'-' -f2 | cut -d'.' -f1)
+            if ! [[ "$DIST_TAG" =~ ^[a-z][a-z0-9-]*$ ]]; then
+              echo "::error::Invalid dist_tag: $DIST_TAG"
+              exit 1
+            fi
             echo "dist_tag=${DIST_TAG:-next}" >> $GITHUB_OUTPUT
           else
             echo "dist_tag=" >> $GITHUB_OUTPUT
           fi
-          
+
           echo "Version: $VERSION"
 
       - name: Check if already published
         id: check
+        env:
+          VERSION: ${{ steps.version.outputs.version }}
         run: |
-          VERSION="${{ steps.version.outputs.version }}"
           STATUS=$(curl -s -o /dev/null -w "%{http_code}" "https://registry.npmjs.org/oh-my-opencode/${VERSION}")
           if [ "$STATUS" = "200" ]; then
             echo "skip=true" >> $GITHUB_OUTPUT
@@ -185,15 +218,16 @@ jobs:
 
       - name: Update version
         if: steps.check.outputs.skip != 'true'
+        env:
+          VERSION: ${{ steps.version.outputs.version }}
         run: |
-          VERSION="${{ steps.version.outputs.version }}"
           jq --arg v "$VERSION" '.version = $v' package.json > tmp.json && mv tmp.json package.json
-          
+
           for platform in darwin-arm64 darwin-x64 darwin-x64-baseline linux-x64 linux-x64-baseline linux-arm64 linux-x64-musl linux-x64-musl-baseline linux-arm64-musl windows-x64 windows-x64-baseline; do
             jq --arg v "$VERSION" '.version = $v' "packages/${platform}/package.json" > tmp.json
             mv tmp.json "packages/${platform}/package.json"
           done
-          
+
           jq --arg v "$VERSION" '.optionalDependencies = (.optionalDependencies | to_entries | map(.value = $v) | from_entries)' package.json > tmp.json && mv tmp.json package.json
 
       - name: Build main package
@@ -206,20 +240,22 @@ jobs:
 
       - name: Publish oh-my-opencode
         if: steps.check.outputs.skip != 'true'
-        run: |
-          TAG_ARG=""
-          if [ -n "${{ steps.version.outputs.dist_tag }}" ]; then
-            TAG_ARG="--tag ${{ steps.version.outputs.dist_tag }}"
-          fi
-          npm publish --access public --provenance $TAG_ARG
         env:
+          DIST_TAG: ${{ steps.version.outputs.dist_tag }}
           NODE_AUTH_TOKEN: ${{ secrets.NODE_AUTH_TOKEN }}
           NPM_CONFIG_PROVENANCE: true
+        run: |
+          if [ -n "$DIST_TAG" ]; then
+            npm publish --access public --provenance --tag "$DIST_TAG"
+          else
+            npm publish --access public --provenance
+          fi
 
       - name: Check if oh-my-openagent already published
         id: check-openagent
+        env:
+          VERSION: ${{ steps.version.outputs.version }}
         run: |
-          VERSION="${{ steps.version.outputs.version }}"
           STATUS=$(curl -s -o /dev/null -w "%{http_code}" "https://registry.npmjs.org/oh-my-openagent/${VERSION}")
           if [ "$STATUS" = "200" ]; then
             echo "skip=true" >> $GITHUB_OUTPUT
@@ -230,9 +266,12 @@ jobs:
 
       - name: Publish oh-my-openagent
         if: steps.check-openagent.outputs.skip != 'true'
+        env:
+          VERSION: ${{ steps.version.outputs.version }}
+          DIST_TAG: ${{ steps.version.outputs.dist_tag }}
+          NODE_AUTH_TOKEN: ${{ secrets.NODE_AUTH_TOKEN }}
+          NPM_CONFIG_PROVENANCE: true
         run: |
-          VERSION="${{ steps.version.outputs.version }}"
-          
           # Update package name, version, and optionalDependencies for oh-my-openagent
           jq --arg v "$VERSION" '
             .name = "oh-my-openagent" |
@@ -243,39 +282,31 @@ jobs:
               from_entries
             )
           ' package.json > tmp.json && mv tmp.json package.json
-          
-          TAG_ARG=""
-          if [ -n "${{ steps.version.outputs.dist_tag }}" ]; then
-            TAG_ARG="--tag ${{ steps.version.outputs.dist_tag }}"
+
+          if [ -n "$DIST_TAG" ]; then
+            npm publish --access public --provenance --tag "$DIST_TAG"
+          else
+            npm publish --access public --provenance
           fi
-          npm publish --access public --provenance $TAG_ARG || echo "::warning::oh-my-openagent publish failed"
-        env:
-          NODE_AUTH_TOKEN: ${{ secrets.NODE_AUTH_TOKEN }}
-          NPM_CONFIG_PROVENANCE: true
 
       - name: Restore package.json
-        if: steps.check-openagent.outputs.skip != 'true'
+        if: always() && steps.check-openagent.outputs.skip != 'true'
         run: |
           git checkout -- package.json
 
-  trigger-platform:
-    runs-on: ubuntu-latest
+  publish-platform:
     needs: publish-main
     if: inputs.skip_platform != true
-    steps:
-      - name: Trigger platform publish workflow
-        run: |
-          gh workflow run publish-platform.yml \
-            --repo ${{ github.repository }} \
-            --ref ${{ github.ref }} \
-            -f version=${{ needs.publish-main.outputs.version }} \
-            -f dist_tag=${{ needs.publish-main.outputs.dist_tag }}
-        env:
-          GH_TOKEN: ${{ secrets.GITHUB_TOKEN }}
+    uses: ./.github/workflows/publish-platform.yml
+    with:
+      version: ${{ needs.publish-main.outputs.version }}
+      dist_tag: ${{ needs.publish-main.outputs.dist_tag }}
+    secrets: inherit
 
   release:
     runs-on: ubuntu-latest
-    needs: publish-main
+    needs: [publish-main, publish-platform]
+    if: always() && needs.publish-main.result == 'success' && (inputs.skip_platform == true || needs.publish-platform.result == 'success')
     steps:
       - uses: actions/checkout@v4
         with:
@@ -299,13 +330,53 @@ jobs:
         env:
           GH_TOKEN: ${{ secrets.GITHUB_TOKEN }}
 
-      - name: Create GitHub release
+      - name: Apply release version to source tree
+        env:
+          VERSION: ${{ needs.publish-main.outputs.version }}
+        run: |
+          jq --arg v "$VERSION" '.version = $v' package.json > tmp.json && mv tmp.json package.json
+
+          for platform in darwin-arm64 darwin-x64 darwin-x64-baseline linux-x64 linux-x64-baseline linux-arm64 linux-x64-musl linux-x64-musl-baseline linux-arm64-musl windows-x64 windows-x64-baseline; do
+            jq --arg v "$VERSION" '.version = $v' "packages/${platform}/package.json" > tmp.json
+            mv tmp.json "packages/${platform}/package.json"
+          done
+
+          jq --arg v "$VERSION" '.optionalDependencies = (.optionalDependencies | to_entries | map(.value = $v) | from_entries)' package.json > tmp.json && mv tmp.json package.json
+
+      - name: Commit version bump
+        env:
+          VERSION: ${{ needs.publish-main.outputs.version }}
+        run: |
+          git config user.email "github-actions[bot]@users.noreply.github.com"
+          git config user.name "github-actions[bot]"
+          git add package.json packages/*/package.json
+          git diff --cached --quiet || git commit -m "release: v${VERSION}"
+
+      - name: Create release tag
+        env:
+          VERSION: ${{ needs.publish-main.outputs.version }}
+        run: |
+          if git rev-parse "v${VERSION}" >/dev/null 2>&1; then
+            echo "::error::Tag v${VERSION} already exists"
+            exit 1
+          fi
+          git tag "v${VERSION}"
+
+      - name: Push release state
+        env:
+          VERSION: ${{ needs.publish-main.outputs.version }}
+          GITHUB_TOKEN: ${{ secrets.GITHUB_TOKEN }}
+        run: |
+          git push origin HEAD
+          git push origin "v${VERSION}"
+
+      - name: Create GitHub release
+        env:
+          VERSION: ${{ needs.publish-main.outputs.version }}
+          GH_TOKEN: ${{ secrets.GITHUB_TOKEN }}
         run: |
-          VERSION="${{ needs.publish-main.outputs.version }}"
           gh release view "v${VERSION}" >/dev/null 2>&1 || \
             gh release create "v${VERSION}" --title "v${VERSION}" --notes-file /tmp/changelog.md
-        env:
-          GH_TOKEN: ${{ secrets.GITHUB_TOKEN }}
 
       - name: Delete draft release
         run: gh release delete next --yes 2>/dev/null || true
@@ -314,13 +385,13 @@ jobs:
 
       - name: Merge to master
         continue-on-error: true
+        env:
+          VERSION: ${{ needs.publish-main.outputs.version }}
+          GITHUB_TOKEN: ${{ secrets.GITHUB_TOKEN }}
         run: |
           git config user.name "github-actions[bot]"
           git config user.email "github-actions[bot]@users.noreply.github.com"
-          VERSION="${{ needs.publish-main.outputs.version }}"
           git stash --include-untracked || true
           git checkout master
           git reset --hard "v${VERSION}"
           git push -f origin master || echo "::warning::Failed to push to master"
-        env:
-          GITHUB_TOKEN: ${{ secrets.GITHUB_TOKEN }}

.github/workflows/refresh-model-capabilities.yml

@@ -0,0 +1,46 @@
+name: Refresh Model Capabilities
+
+on:
+  schedule:
+    - cron: "17 4 * * 1"
+  workflow_dispatch:
+
+permissions:
+  contents: write
+  pull-requests: write
+
+jobs:
+  refresh:
+    runs-on: ubuntu-latest
+    if: github.repository == 'code-yeongyu/oh-my-openagent'
+    steps:
+      - uses: actions/checkout@v4
+
+      - uses: oven-sh/setup-bun@v2
+        with:
+          bun-version: latest
+
+      - name: Install dependencies
+        run: bun install
+        env:
+          BUN_INSTALL_ALLOW_SCRIPTS: "@ast-grep/napi"
+
+      - name: Refresh bundled model capabilities snapshot
+        run: bun run build:model-capabilities
+
+      - name: Validate capability guardrails
+        run: bun run test:model-capabilities
+
+      - name: Create refresh pull request
+        uses: peter-evans/create-pull-request@v7
+        with:
+          commit-message: "chore: refresh model capabilities snapshot"
+          title: "chore: refresh model capabilities snapshot"
+          body: |
+            Automated refresh of `src/generated/model-capabilities.generated.json` from `https://models.dev/api.json`.
+
+            This keeps the bundled capability snapshot aligned with upstream model metadata without relying on manual refreshes.
+          branch: automation/refresh-model-capabilities
+          delete-branch: true
+          labels: |
+            maintenance

.gitignore

@@ -36,3 +36,4 @@ test-injection/
 notepad.md
 oauth-success.html
 *.bun-build
+.omx/

.opencode/skills/github-triage/SKILL.md

@@ -79,47 +79,65 @@ Pass `REPO`, `REPORT_DIR`, and `COMMIT_SHA` to every subagent.
 
 ---
 
-## Phase 1: Fetch All Open Items
+---
 
-<fetch>
-Paginate if 500 results returned.
+## Phase 1: Fetch All Open Items (CORRECTED)
+
+**IMPORTANT:** `body` and `comments` fields may contain control characters that break jq parsing. Fetch basic metadata first, then fetch full details per-item in subagents.
 
 ```bash
-ISSUES=$(gh issue list --repo $REPO --state open --limit 500 \
-  --json number,title,state,createdAt,updatedAt,labels,author,body,comments)
-ISSUE_LEN=$(echo "$ISSUES" | jq length)
-if [ "$ISSUE_LEN" -eq 500 ]; then
-  LAST_DATE=$(echo "$ISSUES" | jq -r '.[-1].createdAt')
+# Step 1: Fetch basic metadata (without body/comments to avoid JSON parsing issues)
+ISSUES_LIST=$(gh issue list --repo $REPO --state open --limit 500 \
+  --json number,title,labels,author,createdAt)
+ISSUE_COUNT=$(echo "$ISSUES_LIST" | jq length)
+
+# Paginate if needed
+if [ "$ISSUE_COUNT" -eq 500 ]; then
+  LAST_DATE=$(echo "$ISSUES_LIST" | jq -r '.[-1].createdAt')
   while true; do
     PAGE=$(gh issue list --repo $REPO --state open --limit 500 \
       --search "created:<$LAST_DATE" \
-      --json number,title,state,createdAt,updatedAt,labels,author,body,comments)
-    PAGE_LEN=$(echo "$PAGE" | jq length)
-    [ "$PAGE_LEN" -eq 0 ] && break
-    ISSUES=$(echo "[$ISSUES, $PAGE]" | jq -s 'add | unique_by(.number)')
-    [ "$PAGE_LEN" -lt 500 ] && break
+      --json number,title,labels,author,createdAt)
+    PAGE_COUNT=$(echo "$PAGE" | jq length)
+    [ "$PAGE_COUNT" -eq 0 ] && break
+    ISSUES_LIST=$(echo "$ISSUES_LIST" "$PAGE" | jq -s '.[0] + .[1] | unique_by(.number)')
+    ISSUE_COUNT=$(echo "$ISSUES_LIST" | jq length)
+    [ "$PAGE_COUNT" -lt 500 ] && break
     LAST_DATE=$(echo "$PAGE" | jq -r '.[-1].createdAt')
   done
 fi
 
-PRS=$(gh pr list --repo $REPO --state open --limit 500 \
-  --json number,title,state,createdAt,updatedAt,labels,author,body,headRefName,baseRefName,isDraft,mergeable,reviewDecision,statusCheckRollup)
-PR_LEN=$(echo "$PRS" | jq length)
-if [ "$PR_LEN" -eq 500 ]; then
-  LAST_DATE=$(echo "$PRS" | jq -r '.[-1].createdAt')
+# Same for PRs
+PRS_LIST=$(gh pr list --repo $REPO --state open --limit 500 \
+  --json number,title,labels,author,headRefName,baseRefName,isDraft,createdAt)
+PR_COUNT=$(echo "$PRS_LIST" | jq length)
+
+if [ "$PR_COUNT" -eq 500 ]; then
+  LAST_DATE=$(echo "$PRS_LIST" | jq -r '.[-1].createdAt')
   while true; do
     PAGE=$(gh pr list --repo $REPO --state open --limit 500 \
       --search "created:<$LAST_DATE" \
-      --json number,title,state,createdAt,updatedAt,labels,author,body,headRefName,baseRefName,isDraft,mergeable,reviewDecision,statusCheckRollup)
-    PAGE_LEN=$(echo "$PAGE" | jq length)
-    [ "$PAGE_LEN" -eq 0 ] && break
-    PRS=$(echo "[$PRS, $PAGE]" | jq -s 'add | unique_by(.number)')
-    [ "$PAGE_LEN" -lt 500 ] && break
+      --json number,title,labels,author,headRefName,baseRefName,isDraft,createdAt)
+    PAGE_COUNT=$(echo "$PAGE" | jq length)
+    [ "$PAGE_COUNT" -eq 0 ] && break
+    PRS_LIST=$(echo "$PRS_LIST" "$PAGE" | jq -s '.[0] + .[1] | unique_by(.number)')
+    PR_COUNT=$(echo "$PRS_LIST" | jq length)
+    [ "$PAGE_COUNT" -lt 500 ] && break
     LAST_DATE=$(echo "$PAGE" | jq -r '.[-1].createdAt')
   done
 fi
+
+echo "Total issues: $ISSUE_COUNT, Total PRs: $PR_COUNT"
 ```
-</fetch>
+
+**LARGE REPOSITORY HANDLING:**
+If total items exceeds 50, you MUST process ALL items. Use the pagination code above to fetch every single open issue and PR.
+**DO NOT** sample or limit to 50 items - process the entire backlog.
+
+Example: If there are 500 open issues, spawn 500 subagents. If there are 1000 open PRs, spawn 1000 subagents.
+
+**Note:** Background task system will queue excess tasks automatically.
+
 
 ---
 

.opencode/skills/work-with-pr/SKILL.md

@@ -282,6 +282,18 @@ Once all three gates pass:
 gh pr merge "$PR_NUMBER" --squash --delete-branch
 ```
 
+### Sync .sisyphus state back to main repo
+
+Before removing the worktree, copy `.sisyphus/` state back. When `.sisyphus/` is gitignored, files written there during worktree execution are not committed or merged — they would be lost on worktree removal.
+
+```bash
+# Sync .sisyphus state from worktree to main repo (preserves task state, plans, notepads)
+if [ -d "$WORKTREE_PATH/.sisyphus" ]; then
+  mkdir -p "$ORIGINAL_DIR/.sisyphus"
+  cp -r "$WORKTREE_PATH/.sisyphus/"* "$ORIGINAL_DIR/.sisyphus/" 2>/dev/null || true
+fi
+```
+
 ### Clean up the worktree
 
 The worktree served its purpose — remove it to avoid disk bloat:

AGENTS.md

@@ -4,7 +4,7 @@
 
 ## OVERVIEW
 
-OpenCode plugin (npm: `oh-my-opencode`) that extends Claude Code (OpenCode fork) with multi-agent orchestration, 46 lifecycle hooks, 26 tools, skill/command/MCP systems, and Claude Code compatibility. 1268 TypeScript files, 160k LOC.
+OpenCode plugin (npm: `oh-my-opencode`) that extends Claude Code (OpenCode fork) with multi-agent orchestration, 48 lifecycle hooks, 26 tools, skill/command/MCP systems, and Claude Code compatibility. 1268 TypeScript files, 160k LOC.
 
 ## STRUCTURE
 
@@ -14,14 +14,14 @@ oh-my-opencode/
 │   ├── index.ts              # Plugin entry: loadConfig → createManagers → createTools → createHooks → createPluginInterface
 │   ├── plugin-config.ts      # JSONC multi-level config: user → project → defaults (Zod v4)
 │   ├── agents/               # 11 agents (Sisyphus, Hephaestus, Oracle, Librarian, Explore, Atlas, Prometheus, Metis, Momus, Multimodal-Looker, Sisyphus-Junior)
-│   ├── hooks/                # 46 hooks across 45 directories + 11 standalone files
+│   ├── hooks/                # 48 lifecycle hooks across dedicated modules and standalone files
 │   ├── tools/                # 26 tools across 15 directories
 │   ├── features/             # 19 feature modules (background-agent, skill-loader, tmux, MCP-OAuth, etc.)
 │   ├── shared/               # 95+ utility files in 13 categories
 │   ├── config/               # Zod v4 schema system (24 files)
 │   ├── cli/                  # CLI: install, run, doctor, mcp-oauth (Commander.js)
 │   ├── mcp/                  # 3 built-in remote MCPs (websearch, context7, grep_app)
-│   ├── plugin/               # 8 OpenCode hook handlers + 46 hook composition
+│   ├── plugin/               # 8 OpenCode hook handlers + 48 hook composition
 │   └── plugin-handlers/      # 6-phase config loading pipeline
 ├── packages/                 # Monorepo: cli-runner, 12 platform binaries
 └── local-ignore/             # Dev-only test fixtures
@@ -34,7 +34,7 @@ OhMyOpenCodePlugin(ctx)
   ├─→ loadPluginConfig()         # JSONC parse → project/user merge → Zod validate → migrate
   ├─→ createManagers()           # TmuxSessionManager, BackgroundManager, SkillMcpManager, ConfigHandler
   ├─→ createTools()              # SkillContext + AvailableCategories + ToolRegistry (26 tools)
-  ├─→ createHooks()              # 3-tier: Core(37) + Continuation(7) + Skill(2) = 46 hooks
+  ├─→ createHooks()              # 3-tier: Core(39) + Continuation(7) + Skill(2) = 48 hooks
   └─→ createPluginInterface()    # 8 OpenCode hook handlers → PluginInterface
 ```
 
@@ -97,7 +97,7 @@ Fields: agents (14 overridable, 21 fields each), categories (8 built-in + custom
 - **Test pattern**: Bun test (`bun:test`), co-located `*.test.ts`, given/when/then style (nested describe with `#given`/`#when`/`#then` prefixes)
 - **CI test split**: mock-heavy tests run in isolation (separate `bun test` processes), rest in batch
 - **Factory pattern**: `createXXX()` for all tools, hooks, agents
-- **Hook tiers**: Session (23) → Tool-Guard (10) → Transform (4) → Continuation (7) → Skill (2)
+- **Hook tiers**: Session (23) → Tool-Guard (12) → Transform (4) → Continuation (7) → Skill (2)
 - **Agent modes**: `primary` (respects UI model) vs `subagent` (own fallback chain) vs `all`
 - **Model resolution**: 4-step: override → category-default → provider-fallback → system-default
 - **Config format**: JSONC with comments, Zod v4 validation, snake_case keys

README.ja.md

@@ -4,6 +4,17 @@
 > コアメンテナーのQが負傷したため、今週は Issue/PR への返信とリリースが遅れる可能性があります。
 > ご理解とご支援に感謝します。
 
+> [!TIP]
+> **Building in Public**
+>
+> メンテナーが Jobdori を使い、oh-my-opencode をリアルタイムで開発・メンテナンスしています。Jobdori は OpenClaw をベースに大幅カスタマイズされた AI アシスタントです。
+> すべての機能開発、修正、Issue トリアージを Discord でライブでご覧いただけます。
+>
+> [![Building in Public](./.github/assets/building-in-public.png)](https://discord.gg/PUwSMR9XNk)
+>
+> [**→ #building-in-public で確認する**](https://discord.gg/PUwSMR9XNk)
+
+
 > [!NOTE]
 >
 > [![Sisyphus Labs - Sisyphus is the agent that codes like your team.](./.github/assets/sisyphuslabs.png?v=2)](https://sisyphuslabs.ai)
@@ -157,7 +168,7 @@ Read this and tell me why it's not just another boilerplate: https://raw.githubu
 
 **Sisyphus** (`claude-opus-4-6` / **`kimi-k2.5`** / **`glm-5`**) はあなたのメインのオーケストレーターです。計画を立て、専門家に委任し、攻撃的な並列実行でタスクを完了まで推進します。途中で投げ出すことはありません。
 
-**Hephaestus** (`gpt-5.3-codex`) はあなたの自律的なディープワーカーです。レシピではなく、目標を与えてください。手取り足取り教えなくても、コードベースを探索し、パターンを研究し、端から端まで実行します。*正当なる職人 (The Legitimate Craftsman).*
+**Hephaestus** (`gpt-5.4`) はあなたの自律的なディープワーカーです。レシピではなく、目標を与えてください。手取り足取り教えなくても、コードベースを探索し、パターンを研究し、端から端まで実行します。*正当なる職人 (The Legitimate Craftsman).*
 
 **Prometheus** (`claude-opus-4-6` / **`kimi-k2.5`** / **`glm-5`**) はあなたの戦略プランナーです。インタビューモードで動作し、コードに触れる前に質問をしてスコープを特定し、詳細な計画を構築します。
 
@@ -165,7 +176,7 @@ Read this and tell me why it's not just another boilerplate: https://raw.githubu
 
 > Anthropicが[私たちのせいでOpenCodeをブロックしました。](https://x.com/thdxr/status/2010149530486911014) だからこそHephaestusは「正当なる職人 (The Legitimate Craftsman)」と呼ばれているのです。皮肉を込めています。
 >
-> Opusで最もよく動きますが、Kimi K2.5 + GPT-5.3 Codexの組み合わせだけでも、バニラのClaude Codeを軽く凌駕します。設定は一切不要です。
+> Opusで最もよく動きますが、Kimi K2.5 + GPT-5.4の組み合わせだけでも、バニラのClaude Codeを軽く凌駕します。設定は一切不要です。
 
 ### エージェントの<E38388><E381AE>ーケストレーション
 

README.ko.md

@@ -4,6 +4,17 @@
 > 핵심 메인테이너 Q가 부상을 입어, 이번 주에는 이슈/PR 응답 및 릴리스가 지연될 수 있습니다.
 > 양해와 응원에 감사드립니다.
 
+> [!TIP]
+> **Building in Public**
+>
+> 메인테이너가 Jobdori를 통해 oh-my-opencode를 실시간으로 개발하고 있습니다. Jobdori는 OpenClaw를 기반으로 대폭 커스터마이징된 AI 어시스턴트입니다.
+> 모든 기능 개발, 버그 수정, 이슈 트리아지를 Discord에서 실시간으로 확인하세요.
+>
+> [![Building in Public](./.github/assets/building-in-public.png)](https://discord.gg/PUwSMR9XNk)
+>
+> [**→ #building-in-public에서 확인하기**](https://discord.gg/PUwSMR9XNk)
+
+
 > [!TIP]
 > 저희와 함께 하세요!
 >
@@ -151,7 +162,7 @@ Read this and tell me why it's not just another boilerplate: https://raw.githubu
 
 **Sisyphus** (`claude-opus-4-6` / **`kimi-k2.5`** / **`glm-5`**)는 당신의 메인 오케스트레이터입니다. 공격적인 병렬 실행으로 계획을 세우고, 전문가들에게 위임하며, 완료될 때까지 밀어붙입니다. 중간에 포기하는 법이 없습니다.
 
-**Hephaestus** (`gpt-5.3-codex`)는 당신의 자율 딥 워커입니다. 레시피가 아니라 목표를 주세요. 베이비시터 없이 알아서 코드베이스를 탐색하고, 패턴을 연구하며, 끝에서 끝까지 전부 해냅니다. *진정한 장인(The Legitimate Craftsman).*
+**Hephaestus** (`gpt-5.4`)는 당신의 자율 딥 워커입니다. 레시피가 아니라 목표를 주세요. 베이비시터 없이 알아서 코드베이스를 탐색하고, 패턴을 연구하며, 끝에서 끝까지 전부 해냅니다. *진정한 장인(The Legitimate Craftsman).*
 
 **Prometheus** (`claude-opus-4-6` / **`kimi-k2.5`** / **`glm-5`**)는 당신의 전략 플래너입니다. 인터뷰 모드로 작동합니다. 코드 한 줄 만지기 전에 질문을 던져 스코프를 파악하고 상세한 계획부터 세웁니다.
 
@@ -159,7 +170,7 @@ Read this and tell me why it's not just another boilerplate: https://raw.githubu
 
 > Anthropic이 [우리 때문에 OpenCode를 막아버렸습니다.](https://x.com/thdxr/status/2010149530486911014) 그래서 Hephaestus의 별명이 "진정한 장인(The Legitimate Craftsman)"인 겁니다. (어디서 많이 들어본 이름이죠?) 아이러니를 노렸습니다.
 >
-> Opus에서 제일 잘 돌아가긴 하지만, Kimi K2.5 + GPT-5.3 Codex 조합만으로도 바닐라 Claude Code는 가볍게 바릅니다. 설정도 필요 없습니다.
+> Opus에서 제일 잘 돌아가긴 하지만, Kimi K2.5 + GPT-5.4 조합만으로도 바닐라 Claude Code는 가볍게 바릅니다. 설정도 필요 없습니다.
 
 ### 에이전트 오케스트레이션
 

README.md

@@ -1,3 +1,13 @@
+> [!TIP]
+> **Building in Public**
+>
+> The maintainer builds and maintains oh-my-opencode in real-time with Jobdori, an AI assistant built on a heavily customized fork of OpenClaw.
+> Every feature, every fix, every issue triage — live in our Discord.
+>
+> [![Building in Public](./.github/assets/building-in-public.png)](https://discord.gg/PUwSMR9XNk)
+>
+> [**→ Watch it happen in #building-in-public**](https://discord.gg/PUwSMR9XNk)
+
 > [!NOTE]
 >
 > [![Sisyphus Labs - Sisyphus is the agent that codes like your team.](./.github/assets/sisyphuslabs.png?v=2)](https://sisyphuslabs.ai)
@@ -101,6 +111,8 @@ Fetch the installation guide and follow it:
 curl -s https://raw.githubusercontent.com/code-yeongyu/oh-my-openagent/refs/heads/dev/docs/guide/installation.md
 ```
 
+**Note**: Use the published package and binary name `oh-my-opencode`. Inside `opencode.json`, the compatibility layer now prefers the plugin entry `oh-my-openagent`, while legacy `oh-my-opencode` entries still load with a warning. Plugin config files still commonly use `oh-my-opencode.json` or `oh-my-opencode.jsonc`, and both legacy and renamed basenames are recognized during the transition.
+
 ---
 
 ## Skip This README
@@ -154,7 +166,7 @@ Even only with following subscriptions, ultrawork will work well (this project i
 
 **Sisyphus** (`claude-opus-4-6` / **`kimi-k2.5`** / **`glm-5`** ) is your main orchestrator. He plans, delegates to specialists, and drives tasks to completion with aggressive parallel execution. He does not stop halfway.
 
-**Hephaestus** (`gpt-5.3-codex`) is your autonomous deep worker. Give him a goal, not a recipe. He explores the codebase, researches patterns, and executes end-to-end without hand-holding. *The Legitimate Craftsman.*
+**Hephaestus** (`gpt-5.4`) is your autonomous deep worker. Give him a goal, not a recipe. He explores the codebase, researches patterns, and executes end-to-end without hand-holding. *The Legitimate Craftsman.*
 
 **Prometheus** (`claude-opus-4-6` / **`kimi-k2.5`** / **`glm-5`** ) is your strategic planner. Interview mode: it questions, identifies scope, and builds a detailed plan before a single line of code is touched.
 
@@ -162,7 +174,7 @@ Every agent is tuned to its model's specific strengths. No manual model-juggling
 
 > Anthropic [blocked OpenCode because of us.](https://x.com/thdxr/status/2010149530486911014) That's why Hephaestus is called "The Legitimate Craftsman." The irony is intentional.
 >
-> We run best on Opus, but Kimi K2.5 + GPT-5.3 Codex already beats vanilla Claude Code. Zero config needed.
+> We run best on Opus, but Kimi K2.5 + GPT-5.4 already beats vanilla Claude Code. Zero config needed.
 
 ### Agent Orchestration
 
@@ -263,11 +275,11 @@ To remove oh-my-opencode:
 
 1. **Remove the plugin from your OpenCode config**
 
-   Edit `~/.config/opencode/opencode.json` (or `opencode.jsonc`) and remove `"oh-my-opencode"` from the `plugin` array:
+   Edit `~/.config/opencode/opencode.json` (or `opencode.jsonc`) and remove either `"oh-my-openagent"` or the legacy `"oh-my-opencode"` entry from the `plugin` array:
 
    ```bash
    # Using jq
-   jq '.plugin = [.plugin[] | select(. != "oh-my-opencode")]' \
+   jq '.plugin = [.plugin[] | select(. != "oh-my-openagent" and . != "oh-my-opencode")]' \
        ~/.config/opencode/opencode.json > /tmp/oc.json && \
        mv /tmp/oc.json ~/.config/opencode/opencode.json
    ```
@@ -275,11 +287,13 @@ To remove oh-my-opencode:
 2. **Remove configuration files (optional)**
 
    ```bash
-   # Remove user config
-   rm -f ~/.config/opencode/oh-my-opencode.json ~/.config/opencode/oh-my-opencode.jsonc
+   # Remove plugin config files recognized during the compatibility window
+   rm -f ~/.config/opencode/oh-my-openagent.jsonc ~/.config/opencode/oh-my-openagent.json \
+         ~/.config/opencode/oh-my-opencode.jsonc ~/.config/opencode/oh-my-opencode.json
 
    # Remove project config (if exists)
-   rm -f .opencode/oh-my-opencode.json .opencode/oh-my-opencode.jsonc
+   rm -f .opencode/oh-my-openagent.jsonc .opencode/oh-my-openagent.json \
+         .opencode/oh-my-opencode.jsonc .opencode/oh-my-opencode.json
    ```
 
 3. **Verify removal**
@@ -304,7 +318,11 @@ See full [Features Documentation](docs/reference/features.md).
 - **Claude Code Compatibility**: Full hook system, commands, skills, agents, MCPs
 - **Built-in MCPs**: websearch (Exa), context7 (docs), grep_app (GitHub search)
 - **Session Tools**: List, read, search, and analyze session history
-- **Productivity Features**: Ralph Loop, Todo Enforcer, GPT permission-tail continuation, Comment Checker, Think Mode, and more
+- **Productivity Features**: Ralph Loop, Todo Enforcer, Comment Checker, Think Mode, and more
+- **Doctor Command**: Built-in diagnostics (`bunx oh-my-opencode doctor`) verify plugin registration, config, models, and environment
+- **Model Fallbacks**: `fallback_models` can mix plain model strings with per-fallback object settings in the same array
+- **File Prompts**: Load prompts from files with `file://` support in agent configurations
+- **Session Recovery**: Automatic recovery from session errors, context window limits, and API failures
 - **Model Setup**: Agent-model matching is built into the [Installation Guide](docs/guide/installation.md#step-5-understand-your-model-setup)
 
 ## Configuration
@@ -314,14 +332,14 @@ Opinionated defaults, adjustable if you insist.
 See [Configuration Documentation](docs/reference/configuration.md).
 
 **Quick Overview:**
-- **Config Locations**: `.opencode/oh-my-opencode.jsonc` or `.opencode/oh-my-opencode.json` (project), `~/.config/opencode/oh-my-opencode.jsonc` or `~/.config/opencode/oh-my-opencode.json` (user)
+- **Config Locations**: The compatibility layer recognizes both `oh-my-openagent.json[c]` and legacy `oh-my-opencode.json[c]` plugin config files. Existing installs still commonly use the legacy basename.
 - **JSONC Support**: Comments and trailing commas supported
 - **Agents**: Override models, temperatures, prompts, and permissions for any agent
 - **Built-in Skills**: `playwright` (browser automation), `git-master` (atomic commits)
 - **Sisyphus Agent**: Main orchestrator with Prometheus (Planner) and Metis (Plan Consultant)
 - **Background Tasks**: Configure concurrency limits per provider/model
 - **Categories**: Domain-specific task delegation (`visual`, `business-logic`, custom)
-- **Hooks**: 25+ built-in hooks, including `gpt-permission-continuation`, all configurable via `disabled_hooks`
+- **Hooks**: 25+ built-in hooks, all configurable via `disabled_hooks`
 - **MCPs**: Built-in websearch (Exa), context7 (docs), grep_app (GitHub search)
 - **LSP**: Full LSP support with refactoring tools
 - **Experimental**: Aggressive truncation, auto-resume, and more

README.ru.md

@@ -4,6 +4,17 @@
 > Ключевой мейнтейнер Q получил травму, поэтому на этой неделе ответы по issue/PR и релизы могут задерживаться.
 > Спасибо за терпение и поддержку.
 
+> [!TIP]
+> **Building in Public**
+>
+> Мейнтейнер разрабатывает и поддерживает oh-my-opencode в режиме реального времени с помощью Jobdori — ИИ-ассистента на базе глубоко кастомизированной версии OpenClaw.
+> Каждая фича, каждый фикс, каждый триаж issue — в прямом эфире в нашем Discord.
+>
+> [![Building in Public](./.github/assets/building-in-public.png)](https://discord.gg/PUwSMR9XNk)
+>
+> [**→ Смотрите в #building-in-public**](https://discord.gg/PUwSMR9XNk)
+
+
 > [!NOTE]
 >
 > [![Sisyphus Labs - Sisyphus is the agent that codes like your team.](./.github/assets/sisyphuslabs.png?v=2)](https://sisyphuslabs.ai)
@@ -141,7 +152,7 @@ Read this and tell me why it's not just another boilerplate: https://raw.githubu
 
 **Sisyphus** (`claude-opus-4-6` / **`kimi-k2.5`** / **`glm-5`**) — главный оркестратор. Он планирует, делегирует задачи специалистам и доводит их до завершения с агрессивным параллельным выполнением. Он не останавливается на полпути.
 
-**Hephaestus** (`gpt-5.3-codex`) — автономный глубокий исполнитель. Дайте ему цель, а не рецепт. Он исследует кодовую базу, изучает паттерны и выполняет задачи сквозным образом без лишних подсказок. *Законный Мастер.*
+**Hephaestus** (`gpt-5.4`) — автономный глубокий исполнитель. Дайте ему цель, а не рецепт. Он исследует кодовую базу, изучает паттерны и выполняет задачи сквозным образом без лишних подсказок. *Законный Мастер.*
 
 **Prometheus** (`claude-opus-4-6` / **`kimi-k2.5`** / **`glm-5`**) — стратегический планировщик. Режим интервью: задаёт вопросы, определяет объём работ и формирует детальный план до того, как написана хотя бы одна строка кода.
 
@@ -149,7 +160,7 @@ Read this and tell me why it's not just another boilerplate: https://raw.githubu
 
 > Anthropic [заблокировал OpenCode из-за нас.](https://x.com/thdxr/status/2010149530486911014) Именно поэтому Hephaestus зовётся «Законным Мастером». Ирония намеренная.
 >
-> Мы работаем лучше всего на Opus, но Kimi K2.5 + GPT-5.3 Codex уже превосходят ванильный Claude Code. Никакой настройки не требуется.
+> Мы работаем лучше всего на Opus, но Kimi K2.5 + GPT-5.4 уже превосходят ванильный Claude Code. Никакой настройки не требуется.
 
 ### Оркестрация агентов
 

README.zh-cn.md

@@ -4,6 +4,17 @@
 > 核心维护者 Q 因受伤，本周 issue/PR 回复和发布可能会延迟。
 > 感谢你的耐心与支持。
 
+> [!TIP]
+> **Building in Public**
+>
+> 维护者正在使用 Jobdori 实时开发和维护 oh-my-opencode。Jobdori 是基于 OpenClaw 深度定制的 AI 助手。
+> 每个功能开发、每次修复、每次 Issue 分类，都在 Discord 上实时进行。
+>
+> [![Building in Public](./.github/assets/building-in-public.png)](https://discord.gg/PUwSMR9XNk)
+>
+> [**→ 在 #building-in-public 频道中查看**](https://discord.gg/PUwSMR9XNk)
+
+
 > [!NOTE]
 >
 > [![Sisyphus Labs - Sisyphus is the agent that codes like your team.](./.github/assets/sisyphuslabs.png?v=2)](https://sisyphuslabs.ai)
@@ -158,7 +169,7 @@ Read this and tell me why it's not just another boilerplate: https://raw.githubu
 
 **Sisyphus** (`claude-opus-4-6` / **`kimi-k2.5`** / **`glm-5`**) 是你的主指挥官。他负责制定计划、分配任务给专家团队，并以极其激进的并行策略推动任务直至完成。他从不半途而废。
 
-**Hephaestus** (`gpt-5.3-codex`) 是你的自主深度工作者。你只需要给他目标，不要给他具体做法。他会自动探索代码库模式，从头到尾独立执行任务，绝不会中途要你当保姆。*名副其实的正牌工匠。*
+**Hephaestus** (`gpt-5.4`) 是你的自主深度工作者。你只需要给他目标，不要给他具体做法。他会自动探索代码库模式，从头到尾独立执行任务，绝不会中途要你当保姆。*名副其实的正牌工匠。*
 
 **Prometheus** (`claude-opus-4-6` / **`kimi-k2.5`** / **`glm-5`**) 是你的战略规划师。他通过访谈模式，在动一行代码之前，先通过提问确定范围并构建详尽的执行计划。
 
@@ -166,7 +177,7 @@ Read this and tell me why it's not just another boilerplate: https://raw.githubu
 
 > Anthropic [因为我们屏蔽了 OpenCode](https://x.com/thdxr/status/2010149530486911014)。这就是为什么我们将 Hephaestus 命名为“正牌工匠 (The Legitimate Craftsman)”。这是一个故意的讽刺。
 >
-> 我们在 Opus 上运行得最好，但仅仅使用 Kimi K2.5 + GPT-5.3 Codex 就足以碾压原版的 Claude Code。完全不需要配置。
+> 我们在 Opus 上运行得最好，但仅仅使用 Kimi K2.5 + GPT-5.4 就足以碾压原版的 Claude Code。完全不需要配置。
 
 ### 智能体调度机制
 

bin/oh-my-opencode.js

@@ -71,9 +71,19 @@ function getSignalExitCode(signal) {
   return 128 + (signalCodeByName[signal] ?? 1);
 }
 
+function getPackageBaseName() {
+  try {
+    const packageJson = JSON.parse(readFileSync(new URL("../package.json", import.meta.url), "utf8"));
+    return packageJson.name || "oh-my-opencode";
+  } catch {
+    return "oh-my-opencode";
+  }
+}
+
 function main() {
   const { platform, arch } = process;
   const libcFamily = getLibcFamily();
+  const packageBaseName = getPackageBaseName();
   const avx2Supported = supportsAvx2();
   
   let packageCandidates;
@@ -83,6 +93,7 @@ function main() {
       arch,
       libcFamily,
       preferBaseline: avx2Supported === false,
+      packageBaseName,
     });
   } catch (error) {
     console.error(`\noh-my-opencode: ${error.message}\n`);

bin/platform.js

@@ -3,11 +3,11 @@
 
 /**
  * Get the platform-specific package name
- * @param {{ platform: string, arch: string, libcFamily?: string | null }} options
+ * @param {{ platform: string, arch: string, libcFamily?: string | null, packageBaseName?: string }} options
  * @returns {string} Package name like "oh-my-opencode-darwin-arm64"
  * @throws {Error} If libc cannot be detected on Linux
  */
-export function getPlatformPackage({ platform, arch, libcFamily }) {
+export function getPlatformPackage({ platform, arch, libcFamily, packageBaseName = "oh-my-opencode" }) {
   let suffix = "";
   if (platform === "linux") {
     if (libcFamily === null || libcFamily === undefined) {
@@ -23,13 +23,13 @@ export function getPlatformPackage({ platform, arch, libcFamily }) {
   
   // Map platform names: win32 -> windows (for package name)
   const os = platform === "win32" ? "windows" : platform;
-  return `oh-my-opencode-${os}-${arch}${suffix}`;
+  return `${packageBaseName}-${os}-${arch}${suffix}`;
 }
 
-/** @param {{ platform: string, arch: string, libcFamily?: string | null, preferBaseline?: boolean }} options */
-export function getPlatformPackageCandidates({ platform, arch, libcFamily, preferBaseline = false }) {
-  const primaryPackage = getPlatformPackage({ platform, arch, libcFamily });
-  const baselinePackage = getBaselinePlatformPackage({ platform, arch, libcFamily });
+/** @param {{ platform: string, arch: string, libcFamily?: string | null, preferBaseline?: boolean, packageBaseName?: string }} options */
+export function getPlatformPackageCandidates({ platform, arch, libcFamily, preferBaseline = false, packageBaseName = "oh-my-opencode" }) {
+  const primaryPackage = getPlatformPackage({ platform, arch, libcFamily, packageBaseName });
+  const baselinePackage = getBaselinePlatformPackage({ platform, arch, libcFamily, packageBaseName });
 
   if (!baselinePackage) {
     return [primaryPackage];
@@ -38,18 +38,18 @@ export function getPlatformPackageCandidates({ platform, arch, libcFamily, prefe
   return preferBaseline ? [baselinePackage, primaryPackage] : [primaryPackage, baselinePackage];
 }
 
-/** @param {{ platform: string, arch: string, libcFamily?: string | null }} options */
-function getBaselinePlatformPackage({ platform, arch, libcFamily }) {
+/** @param {{ platform: string, arch: string, libcFamily?: string | null, packageBaseName?: string }} options */
+function getBaselinePlatformPackage({ platform, arch, libcFamily, packageBaseName = "oh-my-opencode" }) {
   if (arch !== "x64") {
     return null;
   }
 
   if (platform === "darwin") {
-    return "oh-my-opencode-darwin-x64-baseline";
+    return `${packageBaseName}-darwin-x64-baseline`;
   }
 
   if (platform === "win32") {
-    return "oh-my-opencode-windows-x64-baseline";
+    return `${packageBaseName}-windows-x64-baseline`;
   }
 
   if (platform === "linux") {
@@ -61,10 +61,10 @@ function getBaselinePlatformPackage({ platform, arch, libcFamily }) {
     }
 
     if (libcFamily === "musl") {
-      return "oh-my-opencode-linux-x64-musl-baseline";
+      return `${packageBaseName}-linux-x64-musl-baseline`;
     }
 
-    return "oh-my-opencode-linux-x64-baseline";
+    return `${packageBaseName}-linux-x64-baseline`;
   }
 
   return null;

bin/platform.test.ts

@@ -190,6 +190,21 @@ describe("getPlatformPackageCandidates", () => {
     ]);
   });
 
+
+
+  test("supports renamed package family via packageBaseName override", () => {
+    // #given Linux x64 with glibc and renamed package base
+    const input = { platform: "linux", arch: "x64", libcFamily: "glibc", packageBaseName: "oh-my-openagent" };
+
+    // #when getting package candidates
+    const result = getPlatformPackageCandidates(input);
+
+    // #then returns renamed package family candidates
+    expect(result).toEqual([
+      "oh-my-openagent-linux-x64",
+      "oh-my-openagent-linux-x64-baseline",
+    ]);
+  });
   test("returns only one candidate for ARM64", () => {
     // #given non-x64 platform
     const input = { platform: "linux", arch: "arm64", libcFamily: "glibc" };

docs/examples/coding-focused.jsonc

@@ -0,0 +1,88 @@
+{
+  "$schema": "https://raw.githubusercontent.com/code-yeongyu/oh-my-opencode/dev/assets/oh-my-opencode.schema.json",
+
+  // Optimized for intensive coding sessions.
+  // Prioritizes deep implementation agents and fast feedback loops.
+
+  "agents": {
+    // Primary orchestrator: aggressive parallel delegation
+    "sisyphus": {
+      "model": "kimi-for-coding/k2p5",
+      "ultrawork": { "model": "anthropic/claude-opus-4-6", "variant": "max" },
+      "prompt_append": "Delegate heavily to hephaestus for implementation. Parallelize exploration.",
+    },
+
+    // Heavy lifter: maximum autonomy for coding tasks
+    "hephaestus": {
+      "model": "openai/gpt-5.4",
+      "prompt_append": "You are the primary implementation agent. Own the codebase. Explore, decide, execute. Use LSP and AST-grep aggressively.",
+      "permission": { "edit": "allow", "bash": { "git": "allow", "test": "allow" } },
+    },
+
+    // Lightweight planner: quick planning for coding tasks
+    "prometheus": {
+      "model": "opencode/gpt-5-nano",
+      "prompt_append": "Keep plans concise. Focus on file structure and key decisions.",
+    },
+
+    // Debugging and architecture
+    "oracle": { "model": "openai/gpt-5.4", "variant": "high" },
+
+    // Fast docs lookup
+    "librarian": { "model": "github-copilot/grok-code-fast-1" },
+
+    // Rapid codebase navigation
+    "explore": { "model": "github-copilot/grok-code-fast-1" },
+
+    // Frontend and visual work
+    "multimodal-looker": { "model": "google/gemini-3.1-pro" },
+
+    // Plan review: minimal overhead
+    "metis": { "model": "opencode/gpt-5-nano" },
+
+    // Code review focus
+    "momus": { "prompt_append": "Focus on code quality, edge cases, and test coverage." },
+
+    // Long-running coding sessions
+    "atlas": {},
+
+    // Quick fixes and small tasks
+    "sisyphus-junior": { "model": "opencode/gpt-5-nano" },
+  },
+
+  "categories": {
+    // Trivial changes: fastest possible
+    "quick": { "model": "opencode/gpt-5-nano" },
+
+    // Standard coding tasks: good quality, fast
+    "unspecified-low": { "model": "anthropic/claude-sonnet-4-6" },
+
+    // Complex refactors: best quality
+    "unspecified-high": { "model": "openai/gpt-5.3-codex" },
+
+    // Visual work
+    "visual-engineering": { "model": "google/gemini-3.1-pro", "variant": "high" },
+
+    // Deep autonomous work
+    "deep": { "model": "openai/gpt-5.3-codex" },
+
+    // Architecture decisions
+    "ultrabrain": { "model": "openai/gpt-5.4", "variant": "xhigh" },
+  },
+
+  // High concurrency for parallel agent work
+  "background_task": {
+    "defaultConcurrency": 8,
+    "providerConcurrency": {
+      "anthropic": 5,
+      "openai": 5,
+      "google": 10,
+      "github-copilot": 10,
+      "opencode": 15,
+    },
+  },
+
+  // Enable all coding aids
+  "hashline_edit": true,
+  "experimental": { "aggressive_truncation": true, "task_system": true },
+}

docs/examples/default.jsonc

@@ -0,0 +1,71 @@
+{
+  "$schema": "https://raw.githubusercontent.com/code-yeongyu/oh-my-opencode/dev/assets/oh-my-opencode.schema.json",
+
+  // Balanced defaults for general development.
+  // Tuned for reliability across diverse tasks without overspending.
+
+  "agents": {
+    // Main orchestrator: handles delegation and drives tasks to completion
+    "sisyphus": {
+      "model": "anthropic/claude-opus-4-6",
+      "ultrawork": { "model": "anthropic/claude-opus-4-6", "variant": "max" },
+    },
+
+    // Deep autonomous worker: end-to-end implementation
+    "hephaestus": {
+      "model": "openai/gpt-5.4",
+      "prompt_append": "Explore thoroughly, then implement. Prefer small, testable changes.",
+    },
+
+    // Strategic planner: interview mode before execution
+    "prometheus": {
+      "prompt_append": "Always interview first. Validate scope before planning.",
+    },
+
+    // Architecture consultant: complex design and debugging
+    "oracle": { "model": "openai/gpt-5.4", "variant": "high" },
+
+    // Documentation and code search
+    "librarian": { "model": "google/gemini-3-flash" },
+
+    // Fast codebase exploration
+    "explore": { "model": "github-copilot/grok-code-fast-1" },
+
+    // Visual tasks: UI/UX, images, diagrams
+    "multimodal-looker": { "model": "google/gemini-3.1-pro" },
+
+    // Plan consultant: reviews and improves plans
+    "metis": {},
+
+    // Critic and reviewer
+    "momus": {},
+
+    // Continuation and long-running task handler
+    "atlas": {},
+
+    // Lightweight task executor for simple jobs
+    "sisyphus-junior": { "model": "opencode/gpt-5-nano" },
+  },
+
+  "categories": {
+    "quick": { "model": "opencode/gpt-5-nano" },
+    "unspecified-low": { "model": "anthropic/claude-sonnet-4-6" },
+    "unspecified-high": { "model": "anthropic/claude-opus-4-6", "variant": "max" },
+    "writing": { "model": "google/gemini-3-flash" },
+    "visual-engineering": { "model": "google/gemini-3.1-pro", "variant": "high" },
+    "deep": { "model": "openai/gpt-5.3-codex" },
+    "ultrabrain": { "model": "openai/gpt-5.4", "variant": "xhigh" },
+  },
+
+  // Conservative concurrency for cost control
+  "background_task": {
+    "providerConcurrency": {
+      "anthropic": 3,
+      "openai": 3,
+      "google": 5,
+      "opencode": 10,
+    },
+  },
+
+  "experimental": { "aggressive_truncation": true },
+}

docs/examples/planning-focused.jsonc

@@ -0,0 +1,112 @@
+{
+  "$schema": "https://raw.githubusercontent.com/code-yeongyu/oh-my-opencode/dev/assets/oh-my-opencode.schema.json",
+
+  // Optimized for strategic planning, architecture, and complex project design.
+  // Prioritizes deep thinking agents and thorough analysis before execution.
+
+  "agents": {
+    // Orchestrator: delegates to planning agents first
+    "sisyphus": {
+      "model": "anthropic/claude-opus-4-6",
+      "ultrawork": { "model": "anthropic/claude-opus-4-6", "variant": "max" },
+      "prompt_append": "Always consult prometheus and atlas for planning. Never rush to implementation.",
+    },
+
+    // Implementation: uses planning outputs
+    "hephaestus": {
+      "model": "openai/gpt-5.4",
+      "prompt_append": "Follow established plans precisely. Ask for clarification when plans are ambiguous.",
+    },
+
+    // Primary planner: deep interview mode
+    "prometheus": {
+      "model": "anthropic/claude-opus-4-6",
+      "thinking": { "type": "enabled", "budgetTokens": 160000 },
+      "prompt_append": "Interview extensively. Question assumptions. Build exhaustive plans with milestones, risks, and contingencies. Use deep & quick agents heavily in parallel for research.",
+    },
+
+    // Architecture consultant
+    "oracle": {
+      "model": "openai/gpt-5.4",
+      "variant": "xhigh",
+      "thinking": { "type": "enabled", "budgetTokens": 120000 },
+    },
+
+    // Research and documentation
+    "librarian": { "model": "google/gemini-3-flash" },
+
+    // Exploration for research phase
+    "explore": { "model": "github-copilot/grok-code-fast-1" },
+
+    // Visual planning and diagrams
+    "multimodal-looker": { "model": "google/gemini-3.1-pro", "variant": "high" },
+
+    // Plan review and refinement: heavily utilized
+    "metis": {
+      "model": "anthropic/claude-opus-4-6",
+      "prompt_append": "Critically evaluate plans. Identify gaps, risks, and improvements. Be thorough.",
+    },
+
+    // Critic: challenges assumptions
+    "momus": {
+      "model": "openai/gpt-5.4",
+      "prompt_append": "Challenge all assumptions in plans. Look for edge cases, failure modes, and overlooked requirements.",
+    },
+
+    // Long-running planning sessions
+    "atlas": {
+      "prompt_append": "Preserve context across long planning sessions. Track evolving decisions.",
+    },
+
+    // Quick research tasks
+    "sisyphus-junior": { "model": "opencode/gpt-5-nano" },
+  },
+
+  "categories": {
+    "quick": { "model": "opencode/gpt-5-nano" },
+
+    "unspecified-low": { "model": "anthropic/claude-sonnet-4-6" },
+
+    // High-effort planning tasks: maximum reasoning
+    "unspecified-high": {
+      "model": "openai/gpt-5.4",
+      "variant": "xhigh",
+    },
+
+    // Documentation from plans
+    "writing": { "model": "google/gemini-3-flash" },
+
+    // Visual architecture
+    "visual-engineering": { "model": "google/gemini-3.1-pro", "variant": "high" },
+
+    // Deep research and analysis
+    "deep": { "model": "openai/gpt-5.3-codex" },
+
+    // Strategic reasoning
+    "ultrabrain": { "model": "openai/gpt-5.4", "variant": "xhigh" },
+
+    // Creative approaches to problems
+    "artistry": { "model": "google/gemini-3.1-pro", "variant": "high" },
+  },
+
+  // Moderate concurrency: planning is sequential by nature
+  "background_task": {
+    "defaultConcurrency": 5,
+    "staleTimeoutMs": 300000,
+    "providerConcurrency": {
+      "anthropic": 3,
+      "openai": 3,
+    },
+    "modelConcurrency": {
+      "anthropic/claude-opus-4-6": 2,
+      "openai/gpt-5.4": 2,
+    },
+  },
+
+  "sisyphus_agent": {
+    "planner_enabled": true,
+    "replace_plan": true,
+  },
+
+  "experimental": { "aggressive_truncation": true },
+}

docs/guide/agent-model-matching.md

@@ -8,7 +8,7 @@ Think of AI models as developers on a team. Each has a different brain, differen
 
 This isn't a bug. It's the foundation of the entire system.
 
-Oh My OpenCode assigns each agent a model that matches its _working style_ — like building a team where each person is in the role that fits their personality.
+Oh My OpenAgent assigns each agent a model that matches its _working style_ — like building a team where each person is in the role that fits their personality.
 
 ### Sisyphus: The Sociable Lead
 
@@ -27,7 +27,7 @@ Using Sisyphus with older GPT models would be like taking your best project mana
 
 Hephaestus is the developer who stays in their room coding all day. Doesn't talk much. Might seem socially awkward. But give them a hard technical problem and they'll emerge three hours later with a solution nobody else could have found.
 
-**This is why Hephaestus uses GPT-5.3 Codex.** Codex is built for exactly this:
+**This is why Hephaestus uses GPT-5.4.** GPT-5.4 is built for exactly this:
 
 - Deep, autonomous exploration without hand-holding
 - Multi-file reasoning across complex codebases
@@ -64,8 +64,8 @@ These agents have Claude-optimized prompts — long, detailed, mechanics-driven.
 
 | Agent        | Role              | Fallback Chain                         | Notes                                                                                             |
 | ------------ | ----------------- | -------------------------------------- | ------------------------------------------------------------------------------------------------- |
-| **Sisyphus** | Main orchestrator | Claude Opus → opencode-go/kimi-k2.5 → K2P5 → Kimi K2.5 → GPT-5.4 → GLM-5 → Big Pickle | Claude-family first. GPT-5.4 has dedicated prompt support. Kimi available through multiple providers. |
-| **Metis**    | Plan gap analyzer | Claude Opus → GPT-5.4 → opencode-go/glm-5 → K2P5 | Claude preferred. GPT-5.4 as secondary before GLM-5 fallback.                                     |
+| **Sisyphus** | Main orchestrator | anthropic\|github-copilot\|opencode/claude-opus-4-6 (max) → opencode-go/kimi-k2.5 → kimi-for-coding/k2p5 → opencode\|moonshotai\|moonshotai-cn\|firmware\|ollama-cloud\|aihubmix/kimi-k2.5 → openai\|github-copilot\|opencode/gpt-5.4 (medium) → zai-coding-plan\|opencode/glm-5 → opencode/big-pickle | Exact runtime chain from `src/shared/model-requirements.ts`. |
+| **Metis**    | Plan gap analyzer | anthropic\|github-copilot\|opencode/claude-opus-4-6 (max) → openai\|github-copilot\|opencode/gpt-5.4 (high) → opencode-go/glm-5 → kimi-for-coding/k2p5 | Exact runtime chain from `src/shared/model-requirements.ts`. |
 
 ### Dual-Prompt Agents → Claude preferred, GPT supported
 
@@ -73,8 +73,8 @@ These agents ship separate prompts for Claude and GPT families. They auto-detect
 
 | Agent          | Role              | Fallback Chain                         | Notes                                                                |
 | -------------- | ----------------- | -------------------------------------- | -------------------------------------------------------------------- |
-| **Prometheus** | Strategic planner | Claude Opus → GPT-5.4 → opencode-go/glm-5 → Gemini 3.1 Pro | Interview-mode planning. GPT prompt is compact and principle-driven. |
-| **Atlas**      | Todo orchestrator | Claude Sonnet → opencode-go/kimi-k2.5 → GPT-5.4 | Claude first, opencode-go as intermediate, GPT-5.4 as last resort.   |
+| **Prometheus** | Strategic planner | anthropic\|github-copilot\|opencode/claude-opus-4-6 (max) → openai\|github-copilot\|opencode/gpt-5.4 (high) → opencode-go/glm-5 → google\|github-copilot\|opencode/gemini-3.1-pro | Exact runtime chain from `src/shared/model-requirements.ts`. |
+| **Atlas**      | Todo orchestrator | anthropic\|github-copilot\|opencode/claude-sonnet-4-6 → opencode-go/kimi-k2.5 → openai\|github-copilot\|opencode/gpt-5.4 (medium) → opencode-go/minimax-m2.7 | Exact runtime chain from `src/shared/model-requirements.ts`. |
 
 ### Deep Specialists → GPT
 
@@ -82,9 +82,9 @@ These agents are built for GPT's principle-driven style. Their prompts assume au
 
 | Agent          | Role                    | Fallback Chain                         | Notes                                            |
 | -------------- | ----------------------- | -------------------------------------- | ------------------------------------------------ |
-| **Hephaestus** | Autonomous deep worker  | GPT-5.3 Codex → GPT-5.4 (Copilot)     | Requires GPT access. GPT-5.4 via Copilot as fallback. The craftsman. |
-| **Oracle**     | Architecture consultant | GPT-5.4 → Gemini 3.1 Pro → Claude Opus → opencode-go/glm-5 | Read-only high-IQ consultation.                  |
-| **Momus**      | Ruthless reviewer       | GPT-5.4 → Claude Opus → Gemini 3.1 Pro → opencode-go/glm-5 | Verification and plan review. GPT-5.4 uses xhigh variant. |
+| **Hephaestus** | Autonomous deep worker  | GPT-5.4 (medium) | Requires a GPT-capable provider. The craftsman. |
+| **Oracle**     | Architecture consultant | openai\|github-copilot\|opencode/gpt-5.4 (high) → google\|github-copilot\|opencode/gemini-3.1-pro (high) → anthropic\|github-copilot\|opencode/claude-opus-4-6 (max) → opencode-go/glm-5 | Exact runtime chain from `src/shared/model-requirements.ts`. |
+| **Momus**      | Ruthless reviewer       | openai\|github-copilot\|opencode/gpt-5.4 (xhigh) → anthropic\|github-copilot\|opencode/claude-opus-4-6 (max) → google\|github-copilot\|opencode/gemini-3.1-pro (high) → opencode-go/glm-5 | Exact runtime chain from `src/shared/model-requirements.ts`. |
 
 ### Utility Runners → Speed over Intelligence
 
@@ -92,10 +92,10 @@ These agents do grep, search, and retrieval. They intentionally use the fastest,
 
 | Agent                 | Role               | Fallback Chain                                 | Notes                                                 |
 | --------------------- | ------------------ | ---------------------------------------------- | ----------------------------------------------------- |
-| **Explore**           | Fast codebase grep | Grok Code Fast → opencode-go/minimax-m2.5 → MiniMax Free → Haiku → GPT-5-Nano | Speed is everything. Fire 10 in parallel.             |
-| **Librarian**         | Docs/code search   | opencode-go/minimax-m2.5 → MiniMax Free → Haiku → GPT-5-Nano                  | Doc retrieval doesn't need deep reasoning.            |
-| **Multimodal Looker** | Vision/screenshots | GPT-5.4 → opencode-go/kimi-k2.5 → GLM-4.6v → GPT-5-Nano                       | Uses the first available multimodal-capable fallback. |
-| **Sisyphus-Junior**   | Category executor  | Claude Sonnet → opencode-go/kimi-k2.5 → GPT-5.4 → Big Pickle                  | Handles delegated category tasks. Sonnet-tier default. |
+| **Explore**           | Fast codebase grep | github-copilot\|xai/grok-code-fast-1 → opencode-go/minimax-m2.7-highspeed → opencode/minimax-m2.7 → anthropic\|opencode/claude-haiku-4-5 → opencode/gpt-5-nano | Exact runtime chain from `src/shared/model-requirements.ts`. |
+| **Librarian**         | Docs/code search   | opencode-go/minimax-m2.7 → opencode/minimax-m2.7-highspeed → anthropic\|opencode/claude-haiku-4-5 → opencode/gpt-5-nano | Exact runtime chain from `src/shared/model-requirements.ts`. |
+| **Multimodal Looker** | Vision/screenshots | openai\|opencode/gpt-5.4 (medium) → opencode-go/kimi-k2.5 → zai-coding-plan/glm-4.6v → openai\|github-copilot\|opencode/gpt-5-nano | Exact runtime chain from `src/shared/model-requirements.ts`. |
+| **Sisyphus-Junior**   | Category executor  | anthropic\|github-copilot\|opencode/claude-sonnet-4-6 → opencode-go/kimi-k2.5 → openai\|github-copilot\|opencode/gpt-5.4 (medium) → opencode-go/minimax-m2.7 → opencode/big-pickle | Exact runtime chain from `src/shared/model-requirements.ts`. |
 
 ---
 
@@ -119,8 +119,9 @@ Principle-driven, explicit reasoning, deep technical capability. Best for agents
 
 | Model             | Strengths                                                                                       |
 | ----------------- | ----------------------------------------------------------------------------------------------- |
-| **GPT-5.3 Codex** | Deep coding powerhouse. Autonomous exploration. Required for Hephaestus.                        |
+| **GPT-5.3 Codex** | Deep coding powerhouse. Autonomous exploration. Still available for deep category and explicit overrides. |
 | **GPT-5.4**       | High intelligence, strategic reasoning. Default for Oracle, Momus, and a key fallback for Prometheus / Atlas. Uses xhigh variant for Momus. |
+| **GPT-5.4 Mini**  | Fast + strong reasoning. Good for lightweight autonomous tasks. Default for quick category. |
 | **GPT-5-Nano**    | Ultra-cheap, fast. Good for simple utility tasks.                                               |
 
 ### Other Models
@@ -130,7 +131,8 @@ Principle-driven, explicit reasoning, deep technical capability. Best for agents
 | **Gemini 3.1 Pro**   | Excels at visual/frontend tasks. Different reasoning style. Default for `visual-engineering` and `artistry`. |
 | **Gemini 3 Flash**   | Fast. Good for doc search and light tasks.                                                                   |
 | **Grok Code Fast 1** | Blazing fast code grep. Default for Explore agent.                                                           |
-| **MiniMax M2.5**     | Fast and smart. Good for utility tasks and search/retrieval.                                                 |
+| **MiniMax M2.7**     | Fast and smart. Used in OpenCode Go and OpenCode Zen utility fallback chains. |
+| **MiniMax M2.7 Highspeed** | High-speed OpenCode catalog entry used in utility fallback chains that prefer the fastest available MiniMax path. |
 
 ### OpenCode Go
 
@@ -142,11 +144,12 @@ A premium subscription tier ($10/month) that provides reliable access to Chinese
 | ------------------------ | --------------------------------------------------------------------- |
 | **opencode-go/kimi-k2.5** | Vision-capable, Claude-like reasoning. Used by Sisyphus, Atlas, Sisyphus-Junior, Multimodal Looker. |
 | **opencode-go/glm-5**     | Text-only orchestration model. Used by Oracle, Prometheus, Metis, Momus.                           |
-| **opencode-go/minimax-m2.5** | Ultra-cheap, fast responses. Used by Librarian, Explore for utility work.                          |
+| **opencode-go/minimax-m2.7** | Ultra-cheap, fast responses. Used by Librarian, Atlas, and Sisyphus-Junior for utility work. |
+| **opencode-go/minimax-m2.7-highspeed** | Even faster OpenCode Go MiniMax entry used by Explore when the high-speed catalog entry is available. |
 
 **When It Gets Used:**
 
-OpenCode Go models appear in fallback chains as intermediate options. They bridge the gap between premium Claude access and free-tier alternatives. The system tries OpenCode Go models before falling back to free tiers (MiniMax Free, Big Pickle) or GPT alternatives.
+OpenCode Go models appear throughout the fallback chains as intermediate options. Depending on the agent, they can sit before GPT, after GPT, or act as the last structured-model fallback before cheaper utility paths.
 
 **Go-Only Scenarios:**
 
@@ -154,7 +157,7 @@ Some model identifiers like `k2p5` (paid Kimi K2.5) and `glm-5` may only be avai
 
 ### About Free-Tier Fallbacks
 
-You may see model names like `kimi-k2.5-free`, `minimax-m2.5-free`, or `big-pickle` (GLM 4.6) in the source code or logs. These are free-tier versions of the same model families, served through the OpenCode Zen provider. They exist as lower-priority entries in fallback chains.
+You may see model names like `kimi-k2.5-free`, `minimax-m2.7`, `minimax-m2.7-highspeed`, or `big-pickle` (GLM 4.6) in the source code or logs. These are provider-specific or speed-optimized entries in fallback chains.
 
 You don't need to configure them. The system includes them so it degrades gracefully when you don't have every paid subscription. If you have the paid version, the paid version is always preferred.
 
@@ -166,14 +169,14 @@ When agents delegate work, they don't pick a model name — they pick a **catego
 
 | Category             | When Used                  | Fallback Chain                               |
 | -------------------- | -------------------------- | -------------------------------------------- |
-| `visual-engineering` | Frontend, UI, CSS, design  | Gemini 3.1 Pro → GLM 5 → Claude Opus → opencode-go/glm-5 → K2P5 |
-| `ultrabrain`         | Maximum reasoning needed   | GPT-5.4 → Gemini 3.1 Pro → Claude Opus → opencode-go/glm-5 |
-| `deep`               | Deep coding, complex logic | GPT-5.3 Codex → Claude Opus → Gemini 3.1 Pro |
-| `artistry`           | Creative, novel approaches | Gemini 3.1 Pro → Claude Opus → GPT-5.4       |
-| `quick`              | Simple, fast tasks         | Claude Haiku → Gemini Flash → opencode-go/minimax-m2.5 → GPT-5-Nano |
-| `unspecified-high`   | General complex work       | Claude Opus → GPT-5.4 → GLM 5 → K2P5 → opencode-go/glm-5 → Kimi K2.5 |
-| `unspecified-low`    | General standard work      | Claude Sonnet → GPT-5.3 Codex → opencode-go/kimi-k2.5 → Gemini Flash |
-| `writing`            | Text, docs, prose          | Gemini Flash → opencode-go/kimi-k2.5 → Claude Sonnet |
+| `visual-engineering` | Frontend, UI, CSS, design  | google\|github-copilot\|opencode/gemini-3.1-pro (high) → zai-coding-plan\|opencode/glm-5 → anthropic\|github-copilot\|opencode/claude-opus-4-6 (max) → opencode-go/glm-5 → kimi-for-coding/k2p5 |
+| `ultrabrain`         | Maximum reasoning needed   | openai\|opencode/gpt-5.4 (xhigh) → google\|github-copilot\|opencode/gemini-3.1-pro (high) → anthropic\|github-copilot\|opencode/claude-opus-4-6 (max) → opencode-go/glm-5 |
+| `deep`               | Deep coding, complex logic | openai\|opencode/gpt-5.3-codex (medium) → anthropic\|github-copilot\|opencode/claude-opus-4-6 (max) → google\|github-copilot\|opencode/gemini-3.1-pro (high) |
+| `artistry`           | Creative, novel approaches | google\|github-copilot\|opencode/gemini-3.1-pro (high) → anthropic\|github-copilot\|opencode/claude-opus-4-6 (max) → openai\|github-copilot\|opencode/gpt-5.4 |
+| `quick`              | Simple, fast tasks         | openai\|github-copilot\|opencode/gpt-5.4-mini → anthropic\|github-copilot\|opencode/claude-haiku-4-5 → google\|github-copilot\|opencode/gemini-3-flash → opencode-go/minimax-m2.7 → opencode/gpt-5-nano |
+| `unspecified-high`   | General complex work       | anthropic\|github-copilot\|opencode/claude-opus-4-6 (max) → openai\|github-copilot\|opencode/gpt-5.4 (high) → zai-coding-plan\|opencode/glm-5 → kimi-for-coding/k2p5 → opencode-go/glm-5 → opencode/kimi-k2.5 → opencode\|moonshotai\|moonshotai-cn\|firmware\|ollama-cloud\|aihubmix/kimi-k2.5 |
+| `unspecified-low`    | General standard work      | anthropic\|github-copilot\|opencode/claude-sonnet-4-6 → openai\|opencode/gpt-5.3-codex (medium) → opencode-go/kimi-k2.5 → google\|github-copilot\|opencode/gemini-3-flash → opencode-go/minimax-m2.7 |
+| `writing`            | Text, docs, prose          | google\|github-copilot\|opencode/gemini-3-flash → opencode-go/kimi-k2.5 → anthropic\|github-copilot\|opencode/claude-sonnet-4-6 → opencode-go/minimax-m2.7 |
 
 See the [Orchestration System Guide](./orchestration.md) for how agents dispatch tasks to categories.
 
@@ -253,12 +256,46 @@ Run `opencode models` to see available models, `opencode auth login` to authenti
 
 ### How Model Resolution Works
 
-Each agent has a fallback chain. The system tries models in priority order until it finds one available through your connected providers. You don't need to configure providers per model — just authenticate (`opencode auth login`) and the system figures out which models are available and where.
+Each agent has a fallback chain. The system tries models in priority order until it finds one available through your connected providers. You don't need to configure providers per model. Just authenticate (`opencode auth login`) and the system figures out which models are available and where.
+
+Core-agent tab cycling is deterministic via injected runtime order field. The fixed priority order is Sisyphus (order: 1), Hephaestus (order: 2), Prometheus (order: 3), and Atlas (order: 4), then the remaining agents follow.
+
+Your explicit configuration always wins. If you set a specific model for an agent, that choice takes precedence even when resolution data is cold.
+
+Variant and `reasoningEffort` overrides are normalized to model-supported values, so cross-provider overrides degrade gracefully instead of failing hard.
+
+Model capabilities are models.dev-backed, with a refreshable cache and capability diagnostics. Use `bunx oh-my-opencode refresh-model-capabilities` to update the cache, or configure `model_capabilities.auto_refresh_on_start` to refresh at startup.
+
+To see which models your agents will actually use, run `bunx oh-my-opencode doctor`. This shows effective model resolution based on your current authentication and config.
 
 ```
 Agent Request → User Override (if configured) → Fallback Chain → System Default
 ```
 
+### File-Based Prompts
+
+You can load agent system prompts from external files using `file://` URLs in the `prompt` field, or append additional content with `prompt_append`. The `prompt_append` field also works on categories.
+
+```jsonc
+{
+  "agents": {
+    "sisyphus": {
+      "prompt": "file:///path/to/custom-prompt.md"
+    },
+    "oracle": {
+      "prompt_append": "file:///path/to/additional-context.md"
+    }
+  },
+  "categories": {
+    "deep": {
+      "prompt_append": "file:///path/to/deep-category-append.md"
+    }
+  }
+}
+```
+
+The file content is loaded at runtime and injected into the agent's system prompt. Supports `~` expansion for home directory and relative `file://` paths.
+
 ---
 
 ## See Also

docs/guide/installation.md

@@ -26,6 +26,8 @@ Follow the prompts to configure your Claude, ChatGPT, and Gemini subscriptions.
 
 After you install it, you can read this [overview guide](./overview.md) to understand more.
 
+The published package and local binary are still `oh-my-opencode`. Inside `opencode.json`, the compatibility layer now prefers the plugin entry `oh-my-openagent`, while legacy `oh-my-opencode` entries still load with a warning. Plugin config loading recognizes both `oh-my-openagent.json[c]` and `oh-my-opencode.json[c]` during the transition. If you see a "Using legacy package name" warning from `bunx oh-my-opencode doctor`, update your `opencode.json` plugin entry from `"oh-my-opencode"` to `"oh-my-openagent"`.
+
 ## For LLM Agents
 
 > **IMPORTANT: Use `curl` to fetch this file, NOT WebFetch.** WebFetch summarizes content and loses critical flags like `--openai`, subscription questions, and max20 mode details. Always use:
@@ -34,7 +36,7 @@ After you install it, you can read this [overview guide](./overview.md) to under
 > curl -fsSL https://raw.githubusercontent.com/code-yeongyu/oh-my-openagent/refs/heads/dev/docs/guide/installation.md
 > ```
 
-If you're an LLM Agent helping set up oh-my-opencode, Welcome! You'll now help your user to install the best agent harness, OhMyOpenCode. Tell user this with greetings, with test 'oMoMoMoMo...'
+If you're an LLM Agent helping set up oh-my-opencode, welcome. You'll help your user install the harness and verify the rename-compat setup cleanly. Tell user this with greetings, with text 'oMoMoMoMo...'
 
 follow these steps:
 
@@ -69,11 +71,11 @@ Ask the user these questions to determine CLI options:
    - If **no** → `--zai-coding-plan=no` (default)
 
 7. **Do you have an OpenCode Go subscription?**
-   - OpenCode Go is a $10/month subscription providing access to GLM-5, Kimi K2.5, and MiniMax M2.5 models
+   - OpenCode Go is a $10/month subscription providing access to GLM-5, Kimi K2.5, and MiniMax M2.7 models
    - If **yes** → `--opencode-go=yes`
    - If **no** → `--opencode-go=no` (default)
 
-**Provider Priority**: Native (anthropic/, openai/, google/) > Kimi for Coding > GitHub Copilot > OpenCode Go > OpenCode Zen > Z.ai Coding Plan
+**Provider selection is agent-specific.** The installer and runtime do not use one single global provider priority. Each agent resolves against its own fallback chain.
 
 MUST STRONGLY WARNING, WHEN USER SAID THEY DON'T HAVE CLAUDE SUBSCRIPTION, SISYPHUS AGENT MIGHT NOT WORK IDEALLY.
 
@@ -120,8 +122,17 @@ The CLI will:
 
 ```bash
 opencode --version  # Should be 1.0.150 or higher
-cat ~/.config/opencode/opencode.json  # Should contain "oh-my-opencode" in plugin array
+cat ~/.config/opencode/opencode.json  # Should contain "oh-my-openagent" in plugin array, or the legacy "oh-my-opencode" entry while you are still migrating
 ```
+#### Run Doctor Verification
+
+After installation, verify everything is working correctly:
+
+```bash
+bunx oh-my-opencode doctor
+```
+
+This checks system, config, tools, and model resolution, including legacy package name warnings and compatibility-fallback diagnostics.
 
 ### Step 4: Configure Authentication
 
@@ -145,7 +156,7 @@ First, add the opencode-antigravity-auth plugin:
 
 ```json
 {
-  "plugin": ["oh-my-opencode", "opencode-antigravity-auth@latest"]
+  "plugin": ["oh-my-openagent", "opencode-antigravity-auth@latest"]
 }
 ```
 
@@ -154,9 +165,9 @@ First, add the opencode-antigravity-auth plugin:
 You'll also need full model settings in `opencode.json`.
 Read the [opencode-antigravity-auth documentation](https://github.com/NoeFabris/opencode-antigravity-auth), copy the full model configuration from the README, and merge carefully to avoid breaking the user's existing setup. The plugin now uses a **variant system** — models like `antigravity-gemini-3-pro` support `low`/`high` variants instead of separate `-low`/`-high` model entries.
 
-##### oh-my-opencode Agent Model Override
+##### Plugin config model override
 
-The `opencode-antigravity-auth` plugin uses different model names than the built-in Google auth. Override the agent models in `oh-my-opencode.json` (or `.opencode/oh-my-opencode.json`):
+The `opencode-antigravity-auth` plugin uses different model names than the built-in Google auth. Override the agent models in your plugin config file. Existing installs still commonly use `oh-my-opencode.json` or `.opencode/oh-my-opencode.json`, while the compatibility layer also recognizes `oh-my-openagent.json[c]`.
 
 ```json
 {
@@ -176,7 +187,7 @@ The `opencode-antigravity-auth` plugin uses different model names than the built
 
 **Available models (Gemini CLI quota)**:
 
-- `google/gemini-2.5-flash`, `google/gemini-2.5-pro`, `google/gemini-3-flash-preview`, `google/gemini-3-pro-preview`
+- `google/gemini-2.5-flash`, `google/gemini-2.5-pro`, `google/gemini-3-flash-preview`, `google/gemini-3.1-pro-preview`
 
 > **Note**: Legacy tier-suffixed names like `google/antigravity-gemini-3-pro-high` still work but variants are recommended. Use `--variant=high` with the base model name instead.
 
@@ -201,16 +212,16 @@ GitHub Copilot is supported as a **fallback provider** when native providers are
 
 ##### Model Mappings
 
-When GitHub Copilot is the best available provider, oh-my-opencode uses these model assignments:
+When GitHub Copilot is the best available provider, install-time defaults are agent-specific. Common examples are:
 
-| Agent         | Model                             |
-| ------------- | --------------------------------- |
-| **Sisyphus**  | `github-copilot/claude-opus-4-6`  |
-| **Oracle**    | `github-copilot/gpt-5.4`          |
-| **Explore**   | `github-copilot/grok-code-fast-1` |
-| **Librarian** | `github-copilot/gemini-3-flash`   |
+| Agent         | Model                              |
+| ------------- | ---------------------------------- |
+| **Sisyphus**  | `github-copilot/claude-opus-4.6`   |
+| **Oracle**    | `github-copilot/gpt-5.4`           |
+| **Explore**   | `github-copilot/grok-code-fast-1`  |
+| **Atlas**     | `github-copilot/claude-sonnet-4.6` |
 
-GitHub Copilot acts as a proxy provider, routing requests to underlying models based on your subscription.
+GitHub Copilot acts as a proxy provider, routing requests to underlying models based on your subscription. Some agents, like Librarian, are not installed from Copilot alone and instead rely on other configured providers or runtime fallback behavior.
 
 #### Z.ai Coding Plan
 
@@ -227,39 +238,33 @@ If Z.ai is your main provider, the most important fallbacks are:
 
 #### OpenCode Zen
 
-OpenCode Zen provides access to `opencode/` prefixed models including `opencode/claude-opus-4-6`, `opencode/gpt-5.4`, `opencode/gpt-5.3-codex`, `opencode/gpt-5-nano`, `opencode/glm-5`, `opencode/big-pickle`, and `opencode/minimax-m2.5-free`.
+OpenCode Zen provides access to `opencode/` prefixed models including `opencode/claude-opus-4-6`, `opencode/gpt-5.4`, `opencode/gpt-5.3-codex`, `opencode/gpt-5-nano`, `opencode/glm-5`, `opencode/big-pickle`, `opencode/minimax-m2.7`, and `opencode/minimax-m2.7-highspeed`.
 
-When OpenCode Zen is the best available provider (no native or Copilot), these models are used:
+When OpenCode Zen is the best available provider, these are the most relevant source-backed examples:
 
 | Agent         | Model                                                |
 | ------------- | ---------------------------------------------------- |
 | **Sisyphus**  | `opencode/claude-opus-4-6`                           |
 | **Oracle**    | `opencode/gpt-5.4`                                   |
-| **Explore**   | `opencode/gpt-5-nano`                                |
-| **Librarian** | `opencode/minimax-m2.5-free` / `opencode/big-pickle` |
+| **Explore**   | `opencode/minimax-m2.7`                              |
 
 ##### Setup
 
-Run the installer and select "Yes" for GitHub Copilot:
+Run the installer and select "Yes" for OpenCode Zen:
 
 ```bash
 bunx oh-my-opencode install
-# Select your subscriptions (Claude, ChatGPT, Gemini)
-# When prompted: "Do you have a GitHub Copilot subscription?" → Select "Yes"
+# Select your subscriptions (Claude, ChatGPT, Gemini, OpenCode Zen, etc.)
+# When prompted: "Do you have access to OpenCode Zen (opencode/ models)?" → Select "Yes"
 ```
 
 Or use non-interactive mode:
 
 ```bash
-bunx oh-my-opencode install --no-tui --claude=no --openai=no --gemini=no --copilot=yes
+bunx oh-my-opencode install --no-tui --claude=no --openai=no --gemini=no --opencode-zen=yes
 ```
 
-Then authenticate with GitHub:
-
-```bash
-opencode auth login
-# Select: GitHub → Authenticate via OAuth
-```
+This provider uses the `opencode/` model catalog. If your OpenCode environment prompts for provider authentication, follow the OpenCode provider flow for `opencode/` models instead of reusing the fallback-provider auth steps above.
 
 ### Step 5: Understand Your Model Setup
 
@@ -276,7 +281,7 @@ Not all models behave the same way. Understanding which models are "similar" hel
 | **Claude Opus 4.6**      | anthropic, github-copilot, opencode | Best overall. Default for Sisyphus.                                     |
 | **Claude Sonnet 4.6**    | anthropic, github-copilot, opencode | Faster, cheaper. Good balance.                                          |
 | **Claude Haiku 4.5**     | anthropic, opencode                 | Fast and cheap. Good for quick tasks.                                   |
-| **Kimi K2.5**            | kimi-for-coding                     | Behaves very similarly to Claude. Great all-rounder. Default for Atlas. |
+| **Kimi K2.5**            | kimi-for-coding, opencode-go, opencode, moonshotai, moonshotai-cn, firmware, ollama-cloud, aihubmix | Behaves very similarly to Claude. Great all-rounder that appears in several orchestration fallback chains. |
 | **Kimi K2.5 Free**       | opencode                            | Free-tier Kimi. Rate-limited but functional.                            |
 | **GLM 5**                | zai-coding-plan, opencode           | Claude-like behavior. Good for broad tasks.                             |
 | **Big Pickle (GLM 4.6)** | opencode                            | Free-tier GLM. Decent fallback.                                         |
@@ -285,27 +290,28 @@ Not all models behave the same way. Understanding which models are "similar" hel
 
 | Model             | Provider(s)                      | Notes                                             |
 | ----------------- | -------------------------------- | ------------------------------------------------- |
-| **GPT-5.3-codex** | openai, github-copilot, opencode | Deep coding powerhouse. Required for Hephaestus.  |
+| **GPT-5.3-codex** | openai, github-copilot, opencode | Deep coding powerhouse. Still available for deep category and explicit overrides. |
 | **GPT-5.4**       | openai, github-copilot, opencode | High intelligence. Default for Oracle.            |
+| **GPT-5.4 Mini**  | openai, github-copilot, opencode | Fast + strong reasoning. Default for quick category.     |
 | **GPT-5-Nano**    | opencode                         | Ultra-cheap, fast. Good for simple utility tasks. |
 
 **Different-Behavior Models**:
 
 | Model                 | Provider(s)                      | Notes                                                       |
 | --------------------- | -------------------------------- | ----------------------------------------------------------- |
-| **Gemini 3 Pro**      | google, github-copilot, opencode | Excels at visual/frontend tasks. Different reasoning style. |
+| **Gemini 3.1 Pro**    | google, github-copilot, opencode | Excels at visual/frontend tasks. Different reasoning style. |
 | **Gemini 3 Flash**    | google, github-copilot, opencode | Fast, good for doc search and light tasks.                  |
-| **MiniMax M2.5**      | venice                           | Fast and smart. Good for utility tasks.                     |
-| **MiniMax M2.5 Free** | opencode                         | Free-tier MiniMax. Fast for search/retrieval.               |
+| **MiniMax M2.7**      | opencode-go, opencode            | Fast and smart. Utility fallbacks use `minimax-m2.7` or `minimax-m2.7-highspeed` depending on the chain. |
+| **MiniMax M2.7 Highspeed** | opencode-go, opencode       | Faster utility variant used in Explore and other retrieval-heavy fallback chains. |
 
 **Speed-Focused Models**:
 
 | Model                   | Provider(s)            | Speed          | Notes                                                                                                                                         |
 | ----------------------- | ---------------------- | -------------- | --------------------------------------------------------------------------------------------------------------------------------------------- |
-| **Grok Code Fast 1**    | github-copilot, venice | Very fast      | Optimized for code grep/search. Default for Explore.                                                                                          |
+| **Grok Code Fast 1**    | github-copilot, xai    | Very fast      | Optimized for code grep/search. Default for Explore.                                                                                          |
 | **Claude Haiku 4.5**    | anthropic, opencode    | Fast           | Good balance of speed and intelligence.                                                                                                       |
-| **MiniMax M2.5 (Free)** | opencode, venice       | Fast           | Smart for its speed class.                                                                                                                    |
-| **GPT-5.3-codex-spark** | openai                 | Extremely fast | Blazing fast but compacts so aggressively that oh-my-opencode's context management doesn't work well with it. Not recommended for omo agents. |
+| **MiniMax M2.7 Highspeed** | opencode-go, opencode | Very fast    | High-speed MiniMax utility fallback used by runtime chains such as Explore and, on the OpenCode catalog, Librarian.                          |
+| **GPT-5.3-codex-spark** | openai                 | Extremely fast | Blazing fast but compacts so aggressively that oh-my-openagent's context management doesn't work well with it. Not recommended for omo agents. |
 
 #### What Each Agent Does and Which Model It Got
 
@@ -315,8 +321,8 @@ Based on your subscriptions, here's how the agents were configured:
 
 | Agent        | Role             | Default Chain                                   | What It Does                                                                             |
 | ------------ | ---------------- | ----------------------------------------------- | ---------------------------------------------------------------------------------------- |
-| **Sisyphus** | Main ultraworker | Opus (max) → Kimi K2.5 → GLM 5 → Big Pickle     | Primary coding agent. Orchestrates everything. **Never use GPT — no GPT prompt exists.** |
-| **Metis**    | Plan review      | Opus (max) → Kimi K2.5 → GPT-5.4 → Gemini 3 Pro | Reviews Prometheus plans for gaps.                                                       |
+| **Sisyphus** | Main ultraworker | anthropic\|github-copilot\|opencode/claude-opus-4-6 (max) → opencode-go/kimi-k2.5 → kimi-for-coding/k2p5 → opencode\|moonshotai\|moonshotai-cn\|firmware\|ollama-cloud\|aihubmix/kimi-k2.5 → openai\|github-copilot\|opencode/gpt-5.4 (medium) → zai-coding-plan\|opencode/glm-5 → opencode/big-pickle | Primary coding agent. Exact runtime chain from `src/shared/model-requirements.ts`. |
+| **Metis**    | Plan review      | anthropic\|github-copilot\|opencode/claude-opus-4-6 (max) → openai\|github-copilot\|opencode/gpt-5.4 (high) → opencode-go/glm-5 → kimi-for-coding/k2p5 | Reviews Prometheus plans for gaps. Exact runtime chain from `src/shared/model-requirements.ts`. |
 
 **Dual-Prompt Agents** (auto-switch between Claude and GPT prompts):
 
@@ -326,16 +332,16 @@ Priority: **Claude > GPT > Claude-like models**
 
 | Agent          | Role              | Default Chain                                              | GPT Prompt?                                                      |
 | -------------- | ----------------- | ---------------------------------------------------------- | ---------------------------------------------------------------- |
-| **Prometheus** | Strategic planner | Opus (max) → **GPT-5.4 (high)** → Kimi K2.5 → Gemini 3 Pro | Yes — XML-tagged, principle-driven (~300 lines vs ~1,100 Claude) |
-| **Atlas**      | Todo orchestrator | **Kimi K2.5** → Sonnet → GPT-5.4                           | Yes — GPT-optimized todo management                              |
+| **Prometheus** | Strategic planner | anthropic\|github-copilot\|opencode/claude-opus-4-6 (max) → openai\|github-copilot\|opencode/gpt-5.4 (high) → opencode-go/glm-5 → google\|github-copilot\|opencode/gemini-3.1-pro | Yes — XML-tagged, principle-driven (~300 lines vs ~1,100 Claude) |
+| **Atlas**      | Todo orchestrator | anthropic\|github-copilot\|opencode/claude-sonnet-4-6 → opencode-go/kimi-k2.5 → openai\|github-copilot\|opencode/gpt-5.4 (medium) → opencode-go/minimax-m2.7 | Yes - GPT-optimized todo management                              |
 
 **GPT-Native Agents** (built for GPT, don't override to Claude):
 
 | Agent          | Role                   | Default Chain                          | Notes                                                  |
 | -------------- | ---------------------- | -------------------------------------- | ------------------------------------------------------ |
-| **Hephaestus** | Deep autonomous worker | GPT-5.3-codex (medium) only            | "Codex on steroids." No fallback. Requires GPT access. |
-| **Oracle**     | Architecture/debugging | GPT-5.4 (high) → Gemini 3 Pro → Opus   | High-IQ strategic backup. GPT preferred.               |
-| **Momus**      | High-accuracy reviewer | GPT-5.4 (medium) → Opus → Gemini 3 Pro | Verification agent. GPT preferred.                     |
+| **Hephaestus** | Deep autonomous worker | GPT-5.4 (medium) only                  | "Codex on steroids." No fallback. Requires GPT access. |
+| **Oracle**     | Architecture/debugging | openai\|github-copilot\|opencode/gpt-5.4 (high) → google\|github-copilot\|opencode/gemini-3.1-pro (high) → anthropic\|github-copilot\|opencode/claude-opus-4-6 (max) → opencode-go/glm-5 | High-IQ strategic backup. GPT preferred.               |
+| **Momus**      | High-accuracy reviewer | openai\|github-copilot\|opencode/gpt-5.4 (xhigh) → anthropic\|github-copilot\|opencode/claude-opus-4-6 (max) → google\|github-copilot\|opencode/gemini-3.1-pro (high) → opencode-go/glm-5 | Verification agent. GPT preferred.                     |
 
 **Utility Agents** (speed over intelligence):
 
@@ -343,9 +349,9 @@ These agents do search, grep, and retrieval. They intentionally use fast, cheap
 
 | Agent                 | Role               | Default Chain                                                          | Design Rationale                                               |
 | --------------------- | ------------------ | ---------------------------------------------------------------------- | -------------------------------------------------------------- |
-| **Explore**           | Fast codebase grep | MiniMax M2.5 Free → Grok Code Fast → MiniMax M2.5 → Haiku → GPT-5-Nano | Speed is everything. Grok is blazing fast for grep.            |
-| **Librarian**         | Docs/code search   | MiniMax M2.5 Free → Gemini Flash → Big Pickle                          | Entirely free-tier. Doc retrieval doesn't need deep reasoning. |
-| **Multimodal Looker** | Vision/screenshots | Kimi K2.5 → Kimi Free → Gemini Flash → GPT-5.4 → GLM-4.6v              | Kimi excels at multimodal understanding.                       |
+| **Explore**           | Fast codebase grep | github-copilot\|xai/grok-code-fast-1 → opencode-go/minimax-m2.7-highspeed → opencode/minimax-m2.7 → anthropic\|opencode/claude-haiku-4-5 → opencode/gpt-5-nano | Speed is everything. Exact runtime chain from `src/shared/model-requirements.ts`. |
+| **Librarian**         | Docs/code search   | opencode-go/minimax-m2.7 → opencode/minimax-m2.7-highspeed → anthropic\|opencode/claude-haiku-4-5 → opencode/gpt-5-nano | Doc retrieval doesn't need deep reasoning. Exact runtime chain from `src/shared/model-requirements.ts`. |
+| **Multimodal Looker** | Vision/screenshots | openai\|opencode/gpt-5.4 (medium) → opencode-go/kimi-k2.5 → zai-coding-plan/glm-4.6v → openai\|github-copilot\|opencode/gpt-5-nano | GPT-5.4 now leads the default vision path when available. |
 
 #### Why Different Models Need Different Prompts
 
@@ -364,7 +370,7 @@ This is why Prometheus and Atlas ship separate prompts per model family — they
 
 #### Custom Model Configuration
 
-If the user wants to override which model an agent uses, you can customize in `oh-my-opencode.json`:
+If the user wants to override which model an agent uses, you can customize in your plugin config file. Existing installs still commonly use `oh-my-opencode.json`, while the compatibility layer also recognizes `oh-my-openagent.json[c]`.
 
 ```jsonc
 {
@@ -399,18 +405,14 @@ GPT (5.3-codex, 5.2) > Claude Opus (decent fallback) > Gemini (acceptable)
 
 **Dangerous** (no prompt support):
 
-- Sisyphus → GPT: **No GPT prompt. Will degrade significantly.**
+- Sisyphus → older GPT models: **Still a bad fit. GPT-5.4 is the only dedicated GPT prompt path.**
 - Hephaestus → Claude: **Built for Codex. Claude can't replicate this.**
 - Explore → Opus: **Massive cost waste. Explore needs speed, not intelligence.**
 - Librarian → Opus: **Same. Doc search doesn't need Opus-level reasoning.**
 
-#### Provider Priority Chain
+#### Provider Resolution
 
-When multiple providers are available, oh-my-opencode uses this priority:
-
-```
-Native (anthropic/, openai/, google/) > Kimi for Coding > GitHub Copilot > Venice > OpenCode Zen > Z.ai Coding Plan
-```
+There is no single global provider priority. The installer and runtime resolve each agent against its own fallback chain, so the winning provider depends on the agent and the subscriptions you enabled.
 
 ### ⚠️ Warning
 
@@ -424,7 +426,7 @@ Read this document again, think about you have done everything correctly.
 
 #### Say 'Congratulations! 🎉' to the user
 
-Say to user: Congratulations! 🎉 You have successfully set up OhMyOpenCode! Type `opencode` in your terminal to start using it.
+Say to user: Congratulations! 🎉 You have successfully set up OhMyOpenAgent! Type `opencode` in your terminal to start using it.
 
 #### Free advertising
 
@@ -461,3 +463,7 @@ Tell the user of following:
 4. You wanna have your own agent- catalog setup? I can read the [docs](docs/guide/agent-model-matching.md) and set up for you after interviewing!
 
 That's it. The agent will figure out the rest and handle everything automatically.
+
+#### Advanced Configuration
+
+You can customize agent models and fallback chains in your config. The `fallback_models` field accepts either a single string or an array that mixes strings and per-model objects with settings like `variant` and `temperature`. See the [Configuration Reference](../reference/configuration.md) and example configs in `docs/examples/` for details.

docs/guide/orchestration.md

@@ -1,6 +1,6 @@
 # Orchestration System Guide
 
-Oh My OpenCode's orchestration system transforms a simple AI agent into a coordinated development team through **separation of planning and execution**.
+Oh My OpenAgent's orchestration system transforms a simple AI agent into a coordinated development team through **separation of planning and execution**.
 
 ---
 
@@ -298,7 +298,7 @@ task({ category: "quick", prompt: "..." }); // "Just get it done fast"
 | `visual-engineering` | Gemini 3.1 Pro         | Frontend, UI/UX, design, styling, animation                 |
 | `ultrabrain`         | GPT-5.4 (xhigh)        | Deep logical reasoning, complex architecture decisions      |
 | `artistry`           | Gemini 3.1 Pro (high)  | Highly creative or artistic tasks, novel ideas              |
-| `quick`              | Claude Haiku 4.5       | Trivial tasks - single file changes, typo fixes             |
+| `quick`              | GPT-5.4 Mini           | Trivial tasks - single file changes, typo fixes             |
 | `deep`               | GPT-5.3 Codex (medium) | Goal-oriented autonomous problem-solving, thorough research |
 | `unspecified-low`    | Claude Sonnet 4.6      | Tasks that don't fit other categories, low effort           |
 | `unspecified-high`   | Claude Opus 4.6 (max)  | Tasks that don't fit other categories, high effort          |
@@ -420,7 +420,7 @@ Atlas is automatically activated when you run `/start-work`. You don't need to m
 
 | Aspect          | Hephaestus                                 | Sisyphus + `ulw` / `ultrawork`                       |
 | --------------- | ------------------------------------------ | ---------------------------------------------------- |
-| **Model**       | GPT-5.3 Codex (medium reasoning)           | Claude Opus 4.6 / GPT-5.4 / GLM 5 depending on setup |
+| **Model**       | GPT-5.4 (medium reasoning)                 | Claude Opus 4.6 / GPT-5.4 / GLM 5 depending on setup |
 | **Approach**    | Autonomous deep worker                     | Keyword-activated ultrawork mode                     |
 | **Best For**    | Complex architectural work, deep reasoning | General complex tasks, "just do it" scenarios        |
 | **Planning**    | Self-plans during execution                | Uses Prometheus plans if available                   |
@@ -443,8 +443,8 @@ Switch to Hephaestus (Tab → Select Hephaestus) when:
    - "Integrate our Rust core with the TypeScript frontend"
    - "Migrate from MongoDB to PostgreSQL with zero downtime"
 
-4. **You specifically want GPT-5.3 Codex reasoning**
-   - Some problems benefit from GPT-5.3 Codex's training characteristics
+4. **You specifically want GPT-5.4 reasoning**
+   - Some problems benefit from GPT-5.4's training characteristics
 
 **When to Use Sisyphus + `ulw`:**
 
@@ -469,13 +469,13 @@ Use the `ulw` keyword in Sisyphus when:
 **Recommendation:**
 
 - **For most users**: Use `ulw` keyword in Sisyphus. It's the default path and works excellently for 90% of complex tasks.
-- **For power users**: Switch to Hephaestus when you specifically need GPT-5.3 Codex's reasoning style or want the "AmpCode deep mode" experience of fully autonomous exploration and execution.
+- **For power users**: Switch to Hephaestus when you specifically need GPT-5.4's reasoning style or want the "AmpCode deep mode" experience of fully autonomous exploration and execution.
 
 ---
 
 ## Configuration
 
-You can control related features in `oh-my-opencode.json`:
+You can control related features in `oh-my-openagent.json`:
 
 ```jsonc
 {
@@ -520,7 +520,7 @@ Type `exit` or start a new session. Atlas is primarily entered via `/start-work`
 
 **For most tasks**: Type `ulw` in Sisyphus.
 
-**Use Hephaestus when**: You specifically need GPT-5.3 Codex's reasoning style for deep architectural work or complex debugging.
+**Use Hephaestus when**: You specifically need GPT-5.4's reasoning style for deep architectural work or complex debugging.
 
 ---
 

docs/guide/overview.md

@@ -1,6 +1,6 @@
-# What Is Oh My OpenCode?
+# What Is Oh My OpenAgent?
 
-Oh My OpenCode is a multi-model agent orchestration harness for OpenCode. It transforms a single AI agent into a coordinated development team that actually ships code.
+Oh My OpenAgent is a multi-model agent orchestration harness for OpenCode. It transforms a single AI agent into a coordinated development team that actually ships code.
 
 Not locked to Claude. Not locked to OpenAI. Not locked to anyone.
 
@@ -15,7 +15,7 @@ Just better results, cheaper models, real orchestration.
 Paste this into your LLM agent session:
 
 ```
-Install and configure oh-my-opencode by following the instructions here:
+Install and configure oh-my-openagent by following the instructions here:
 https://raw.githubusercontent.com/code-yeongyu/oh-my-openagent/refs/heads/dev/docs/guide/installation.md
 ```
 
@@ -41,13 +41,13 @@ We used to call this "Claude Code on steroids." That was wrong.
 
 This isn't about making Claude Code better. It's about breaking free from the idea that one model, one provider, one way of working is enough. Anthropic wants you locked in. OpenAI wants you locked in. Everyone wants you locked in.
 
-Oh My OpenCode doesn't play that game. It orchestrates across models, picking the right brain for the right job. Claude for orchestration. GPT for deep reasoning. Gemini for frontend. Haiku for quick tasks. All working together, automatically.
+Oh My OpenAgent doesn't play that game. It orchestrates across models, picking the right brain for the right job. Claude for orchestration. GPT for deep reasoning. Gemini for frontend. GPT-5.4 Mini for quick tasks. All working together, automatically.
 
 ---
 
 ## How It Works: Agent Orchestration
 
-Instead of one agent doing everything, Oh My OpenCode uses **specialized agents that delegate to each other** based on task type.
+Instead of one agent doing everything, Oh My OpenAgent uses **specialized agents that delegate to each other** based on task type.
 
 **The Architecture:**
 
@@ -93,15 +93,15 @@ Sisyphus still works best on Claude-family models, Kimi, and GLM. GPT-5.4 now ha
 
 Named with intentional irony. Anthropic blocked OpenCode from using their API because of this project. So the team built an autonomous GPT-native agent instead.
 
-Hephaestus runs on GPT-5.3 Codex. Give him a goal, not a recipe. He explores the codebase, researches patterns, and executes end-to-end without hand-holding. He is the legitimate craftsman because he was born from necessity, not privilege.
+Hephaestus runs on GPT-5.4. Give him a goal, not a recipe. He explores the codebase, researches patterns, and executes end-to-end without hand-holding. He is the legitimate craftsman because he was born from necessity, not privilege.
 
-Use Hephaestus when you need deep architectural reasoning, complex debugging across many files, or cross-domain knowledge synthesis. Switch to him explicitly when the work demands GPT-5.3 Codex's particular strengths.
+Use Hephaestus when you need deep architectural reasoning, complex debugging across many files, or cross-domain knowledge synthesis. Switch to him explicitly when the work demands GPT-5.4's particular strengths.
 
 **Why this beats vanilla Codex CLI:**
 
-- **Multi-model orchestration.** Pure Codex is single-model. OmO routes different tasks to different models automatically. GPT for deep reasoning. Gemini for frontend. Haiku for speed. The right brain for the right job.
+- **Multi-model orchestration.** Pure Codex is single-model. OmO routes different tasks to different models automatically. GPT for deep reasoning. Gemini for frontend. GPT-5.4 Mini for speed. The right brain for the right job.
 - **Background agents.** Fire 5+ agents in parallel. Something Codex simply cannot do. While one agent writes code, another researches patterns, another checks documentation. Like a real dev team.
-- **Category system.** Tasks are routed by intent, not model name. `visual-engineering` gets Gemini. `ultrabrain` gets GPT-5.4. `quick` gets Haiku. No manual juggling.
+- **Category system.** Tasks are routed by intent, not model name. `visual-engineering` gets Gemini. `ultrabrain` gets GPT-5.4. `quick` gets GPT-5.4 Mini. No manual juggling.
 - **Accumulated wisdom.** Subagents learn from previous results. Conventions discovered in task 1 are passed to task 5. Mistakes made early aren't repeated. The system gets smarter as it works.
 
 ### Prometheus: The Strategic Planner
@@ -154,7 +154,7 @@ Use Prometheus for multi-day projects, critical production changes, complex refa
 
 ## Agent Model Matching
 
-Different agents work best with different models. Oh My OpenCode automatically assigns optimal models, but you can customize everything.
+Different agents work best with different models. Oh My OpenAgent automatically assigns optimal models, but you can customize everything.
 
 ### Default Configuration
 
@@ -168,7 +168,7 @@ You can override specific agents or categories in your config:
 
 ```jsonc
 {
-  "$schema": "https://raw.githubusercontent.com/code-yeongyu/oh-my-openagent/dev/assets/oh-my-opencode.schema.json",
+  "$schema": "https://raw.githubusercontent.com/code-yeongyu/oh-my-openagent/dev/assets/oh-my-openagent.schema.json",
 
   "agents": {
     // Main orchestrator: Claude Opus or Kimi K2.5 work best
@@ -195,8 +195,8 @@ You can override specific agents or categories in your config:
     // General high-effort work
     "unspecified-high": { "model": "anthropic/claude-opus-4-6", "variant": "max" },
 
-    // Quick tasks: use the cheapest models
-    "quick": { "model": "anthropic/claude-haiku-4-5" },
+    // Quick tasks: use GPT-5.4-mini (fast and cheap)
+    "quick": { "model": "openai/gpt-5.4-mini" },
 
     // Deep reasoning: GPT-5.4
     "ultrabrain": { "model": "openai/gpt-5.4", "variant": "xhigh" },
@@ -214,14 +214,13 @@ You can override specific agents or categories in your config:
 
 **GPT models** (explicit reasoning, principle-driven):
 
-- GPT-5.3-codex — deep coding powerhouse, required for Hephaestus
-- GPT-5.4 — high intelligence, default for Oracle
+- GPT-5.4 — deep coding powerhouse, required for Hephaestus and default for Oracle
 - GPT-5-Nano — ultra-cheap, fast utility tasks
 
 **Different-behavior models**:
 
-- Gemini 3 Pro — excels at visual/frontend tasks
-- MiniMax M2.5 — fast and smart for utility tasks
+- Gemini 3.1 Pro — excels at visual/frontend tasks
+- MiniMax M2.7 / M2.7-highspeed — fast and smart for utility tasks
 - Grok Code Fast 1 — optimized for code grep/search
 
 See the [Agent-Model Matching Guide](./agent-model-matching.md) for complete details on which models work best for each agent, safe vs dangerous overrides, and provider priority chains.
@@ -232,7 +231,7 @@ See the [Agent-Model Matching Guide](./agent-model-matching.md) for complete det
 
 Claude Code is good. But it's a single agent running a single model doing everything alone.
 
-Oh My OpenCode turns that into a coordinated team:
+Oh My OpenAgent turns that into a coordinated team:
 
 **Parallel execution.** Claude Code processes one thing at a time. OmO fires background agents in parallel — research, implementation, and verification happening simultaneously. Like having 5 engineers instead of 1.
 
@@ -246,7 +245,7 @@ Oh My OpenCode turns that into a coordinated team:
 
 **Discipline enforcement.** Todo enforcer yanks idle agents back to work. Comment checker strips AI slop. Ralph Loop keeps going until 100% done. The system doesn't let the agent slack off.
 
-**The fundamental advantage.** Models have different temperaments. Claude thinks deeply. GPT reasons architecturally. Gemini visualizes. Haiku moves fast. Single-model tools force you to pick one personality for all tasks. Oh My OpenCode leverages them all, routing by task type. This isn't a temporary hack — it's the only architecture that makes sense as models specialize further. The gap between multi-model orchestration and single-model limitation widens every month. We're betting on that future.
+**The fundamental advantage.** Models have different temperaments. Claude thinks deeply. GPT reasons architecturally. Gemini visualizes. Haiku moves fast. Single-model tools force you to pick one personality for all tasks. Oh My OpenAgent leverages them all, routing by task type. This isn't a temporary hack — it's the only architecture that makes sense as models specialize further. The gap between multi-model orchestration and single-model limitation widens every month. We're betting on that future.
 
 ---
 
@@ -256,7 +255,7 @@ Before acting on any request, Sisyphus classifies your true intent.
 
 Are you asking for research? Implementation? Investigation? A fix? The Intent Gate figures out what you actually want, not just the literal words you typed. This means the agent understands context, nuance, and the real goal behind your request.
 
-Claude Code doesn't have this. It takes your prompt and runs. Oh My OpenCode thinks first, then acts.
+Claude Code doesn't have this. It takes your prompt and runs. Oh My OpenAgent thinks first, then acts.
 
 ---
 

docs/manifesto.md

@@ -1,6 +1,6 @@
 # Manifesto
 
-The principles and philosophy behind Oh My OpenCode.
+The principles and philosophy behind Oh My OpenAgent.
 
 ---
 
@@ -20,7 +20,7 @@ When you find yourself:
 
 That's not "human-AI collaboration." That's the AI failing to do its job.
 
-**Oh My OpenCode is built on this premise**: Human intervention during agentic work is fundamentally a wrong signal. If the system is designed correctly, the agent should complete the work without requiring you to babysit it.
+**Oh My OpenAgent is built on this premise**: Human intervention during agentic work is fundamentally a wrong signal. If the system is designed correctly, the agent should complete the work without requiring you to babysit it.
 
 ---
 
@@ -144,7 +144,7 @@ Human Intent → Agent Execution → Verified Result
           (intervention only on true failure)
 ```
 
-Everything in Oh My OpenCode is designed to make this loop work:
+Everything in Oh My OpenAgent is designed to make this loop work:
 
 | Feature | Purpose |
 |---------|---------|

docs/model-capabilities-maintenance.md

@@ -0,0 +1,33 @@
+# Model Capabilities Maintenance
+
+This project treats model capability resolution as a layered system:
+
+1. runtime metadata from connected providers
+2. `models.dev` bundled/runtime snapshot data
+3. explicit compatibility aliases
+4. heuristic fallback as the last resort
+
+## Internal policy
+
+- Built-in OmO agent/category requirement models must use canonical model IDs.
+- Aliases exist only to preserve compatibility with historical OmO names or provider-specific decorations.
+- New decorated names like `-high`, `-low`, or `-thinking` should not be added to built-in requirements when a canonical model ID plus structured settings can express the same thing.
+- If a provider or config input still uses an alias, normalize it at the edge and continue internally with the canonical ID.
+
+## When adding an alias
+
+- Add the alias rule to `src/shared/model-capability-aliases.ts`.
+- Include a rationale for why the alias exists.
+- Add or update tests so the alias is covered explicitly.
+- Ensure the alias canonical target exists in the bundled `models.dev` snapshot.
+
+## Guardrails
+
+`bun run test:model-capabilities` enforces the following invariants:
+
+- exact alias targets must exist in the bundled snapshot
+- exact alias keys must not silently become canonical `models.dev` IDs
+- pattern aliases must not rewrite canonical snapshot IDs
+- built-in requirement models must stay canonical and snapshot-backed
+
+The scheduled `refresh-model-capabilities` workflow runs these guardrails before opening an automated snapshot refresh PR.

docs/reference/cli.md

@@ -1,6 +1,6 @@
 # CLI Reference
 
-Complete reference for the `oh-my-opencode` command-line interface.
+Complete reference for the published `oh-my-opencode` CLI. During the rename transition, OpenCode plugin registration now prefers `oh-my-openagent` inside `opencode.json`.
 
 ## Basic Usage
 
@@ -14,20 +14,21 @@ npx oh-my-opencode
 
 ## Commands
 
-| Command             | Description                               |
-| ------------------- | ----------------------------------------- |
-| `install`           | Interactive setup wizard                  |
-| `doctor`            | Environment diagnostics and health checks |
-| `run`               | OpenCode session runner                   |
-| `mcp oauth`         | MCP OAuth authentication management       |
-| `auth`              | Google Antigravity OAuth authentication   |
-| `get-local-version` | Display local version information         |
+| Command                       | Description                                            |
+| ----------------------------- | ------------------------------------------------------ |
+| `install`                     | Interactive setup wizard                               |
+| `doctor`                      | Environment diagnostics and health checks              |
+| `run`                         | OpenCode session runner with task completion enforcement |
+| `get-local-version`           | Display local version information and update check     |
+| `refresh-model-capabilities`  | Refresh the cached models.dev-based model capabilities |
+| `version`                     | Show version information                               |
+| `mcp oauth`                   | MCP OAuth authentication management                    |
 
 ---
 
 ## install
 
-Interactive installation tool for initial Oh-My-OpenCode setup. Provides a TUI based on `@clack/prompts`.
+Interactive installation tool for initial Oh My OpenCode setup. Provides a TUI based on `@clack/prompts`.
 
 ### Usage
 
@@ -37,24 +38,37 @@ bunx oh-my-opencode install
 
 ### Installation Process
 
-1. **Provider Selection**: Choose your AI provider (Claude, ChatGPT, or Gemini)
-2. **API Key Input**: Enter the API key for your selected provider
-3. **Configuration File Creation**: Generates `opencode.json` or `oh-my-opencode.json` files
-4. **Plugin Registration**: Automatically registers the oh-my-opencode plugin in OpenCode settings
+1. **Subscription Selection**: Choose which providers and subscriptions you actually have
+2. **Plugin Registration**: Registers `oh-my-openagent` in OpenCode settings, or upgrades a legacy `oh-my-opencode` entry during the compatibility window
+3. **Configuration File Creation**: Writes the generated OmO config to `oh-my-opencode.json` in the active OpenCode config directory
+4. **Authentication Hints**: Shows the `opencode auth login` steps for the providers you selected, unless `--skip-auth` is set
 
 ### Options
 
-| Option      | Description                                                      |
-| ----------- | ---------------------------------------------------------------- |
-| `--no-tui`  | Run in non-interactive mode without TUI (for CI/CD environments) |
-| `--verbose` | Display detailed logs                                            |
+| Option | Description |
+| ------ | ----------- |
+| `--no-tui` | Run in non-interactive mode without TUI |
+| `--claude <no\|yes\|max20>` | Claude subscription mode |
+| `--openai <no\|yes>` | OpenAI / ChatGPT subscription |
+| `--gemini <no\|yes>` | Gemini integration |
+| `--copilot <no\|yes>` | GitHub Copilot subscription |
+| `--opencode-zen <no\|yes>` | OpenCode Zen access |
+| `--zai-coding-plan <no\|yes>` | Z.ai Coding Plan subscription |
+| `--kimi-for-coding <no\|yes>` | Kimi for Coding subscription |
+| `--opencode-go <no\|yes>` | OpenCode Go subscription |
+| `--skip-auth` | Skip authentication setup hints |
 
 ---
 
 ## doctor
 
-Diagnoses your environment to ensure Oh-My-OpenCode is functioning correctly. Performs 17+ health checks.
+Diagnoses your environment to ensure Oh My OpenCode is functioning correctly. The current checks are grouped into system, config, tools, and models.
 
+The doctor command detects common issues including:
+- Legacy plugin entry references in `opencode.json` (warns when `oh-my-opencode` is still used instead of `oh-my-openagent`)
+- Configuration file validity and JSONC parsing errors
+- Model resolution and fallback chain verification
+- Missing or misconfigured MCP servers
 ### Usage
 
 ```bash
@@ -63,22 +77,20 @@ bunx oh-my-opencode doctor
 
 ### Diagnostic Categories
 
-| Category           | Check Items                                               |
-| ------------------ | --------------------------------------------------------- |
-| **Installation**   | OpenCode version (>= 1.0.150), plugin registration status |
-| **Configuration**  | Configuration file validity, JSONC parsing                |
-| **Authentication** | Anthropic, OpenAI, Google API key validity                |
-| **Dependencies**   | Bun, Node.js, Git installation status                     |
-| **Tools**          | LSP server status, MCP server status                      |
-| **Updates**        | Latest version check                                      |
+| Category          | Check Items                                                                          |
+| ----------------- | ------------------------------------------------------------------------------------ |
+| **System**        | OpenCode binary, version (>= 1.0.150), plugin registration, legacy package name warning |
+| **Config**        | Configuration file validity, JSONC parsing, Zod schema validation                    |
+| **Tools**         | AST-Grep, LSP servers, GitHub CLI, MCP servers                                       |
+| **Models**        | Model capabilities cache, model resolution, agent/category overrides, availability   |
 
 ### Options
 
-| Option              | Description                                                      |
-| ------------------- | ---------------------------------------------------------------- |
-| `--category <name>` | Check specific category only (e.g., `--category authentication`) |
-| `--json`            | Output results in JSON format                                    |
-| `--verbose`         | Include detailed information                                     |
+| Option       | Description                               |
+| ------------ | ----------------------------------------- |
+| `--status`   | Show compact system dashboard             |
+| `--verbose`  | Show detailed diagnostic information      |
+| `--json`     | Output results in JSON format             |
 
 ### Example Output
 
@@ -86,57 +98,95 @@ bunx oh-my-opencode doctor
 oh-my-opencode doctor
 
 ┌──────────────────────────────────────────────────┐
-│  Oh-My-OpenCode Doctor                           │
+│  Oh-My-OpenAgent Doctor                           │
 └──────────────────────────────────────────────────┘
 
-Installation
+System
   ✓ OpenCode version: 1.0.155 (>= 1.0.150)
   ✓ Plugin registered in opencode.json
 
-Configuration
-  ✓ oh-my-opencode.json is valid
+Config
+  ✓ oh-my-opencode.jsonc is valid
+  ✓ Model resolution: all agents have valid fallback chains
   ⚠ categories.visual-engineering: using default model
 
-Authentication
-  ✓ Anthropic API key configured
-  ✓ OpenAI API key configured
-  ✗ Google API key not found
+Tools
+  ✓ AST-Grep available
+  ✓ LSP servers configured
 
-Dependencies
-  ✓ Bun 1.2.5 installed
-  ✓ Node.js 22.0.0 installed
-  ✓ Git 2.45.0 installed
+Models
+  ✓ 11 agents, 8 categories, 0 overrides
+  ⚠ Some configured models rely on compatibility fallback
 
-Summary: 10 passed, 1 warning, 1 failed
+Summary: 10 passed, 1 warning, 0 failed
 ```
-
 ---
 
 ## run
 
-Executes OpenCode sessions and monitors task completion.
+Run opencode with todo/background task completion enforcement. Unlike 'opencode run', this command waits until all todos are completed or cancelled, and all child sessions (background tasks) are idle.
 
 ### Usage
 
 ```bash
-bunx oh-my-opencode run [prompt]
+bunx oh-my-opencode run <message>
 ```
 
 ### Options
 
-| Option                   | Description                                       |
-| ------------------------ | ------------------------------------------------- |
-| `--enforce-completion`   | Keep session active until all TODOs are completed |
-| `--timeout <seconds>`    | Set maximum execution time                        |
-| `--agent <name>`         | Specify agent to use                              |
-| `--directory <path>`     | Set working directory                             |
-| `--port <number>`        | Set port for session                              |
-| `--attach`               | Attach to existing session                        |
-| `--json`                 | Output in JSON format                             |
-| `--no-timestamp`         | Disable timestamped output                        |
-| `--session-id <id>`      | Resume existing session                           |
-| `--on-complete <action>` | Action on completion                              |
-| `--verbose`              | Enable verbose logging                            |
+| Option                | Description                                                         |
+| --------------------- | ------------------------------------------------------------------- |
+| `-a, --agent <name>`  | Agent to use (default: from CLI/env/config, fallback: Sisyphus)     |
+| `-m, --model <provider/model>` | Model override (e.g., anthropic/claude-sonnet-4)             |
+| `-d, --directory <path>` | Working directory                                                |
+| `-p, --port <port>`  | Server port (attaches if port already in use)                       |
+| `--attach <url>`      | Attach to existing opencode server URL                              |
+| `--on-complete <command>` | Shell command to run after completion                          |
+| `--json`              | Output structured JSON result to stdout                             |
+| `--no-timestamp`      | Disable timestamp prefix in run output                              |
+| `--verbose`           | Show full event stream (default: messages/tools only)               |
+| `--session-id <id>`   | Resume existing session instead of creating new one                 |
+
+---
+
+## get-local-version
+
+Show current installed version and check for updates.
+
+### Usage
+
+```bash
+bunx oh-my-opencode get-local-version
+```
+
+### Options
+
+| Option            | Description                                    |
+| ----------------- | ---------------------------------------------- |
+| `-d, --directory` | Working directory to check config from         |
+| `--json`          | Output in JSON format for scripting            |
+
+### Output
+
+Shows:
+- Current installed version
+- Latest available version on npm
+- Whether you're up to date
+- Special modes (local dev, pinned version)
+
+---
+
+## version
+
+Show version information.
+
+### Usage
+
+```bash
+bunx oh-my-opencode version
+```
+
+`--on-complete` runs through your current shell when possible: `sh` on Unix shells, `pwsh` for PowerShell on non-Windows, `powershell.exe` for PowerShell on Windows, and `cmd.exe` as the Windows fallback.
 
 ---
 
@@ -151,10 +201,10 @@ Manages OAuth 2.1 authentication for remote MCP servers.
 bunx oh-my-opencode mcp oauth login <server-name> --server-url https://api.example.com
 
 # Login with explicit client ID and scopes
-bunx oh-my-opencode mcp oauth login my-api --server-url https://api.example.com --client-id my-client --scopes "read,write"
+bunx oh-my-opencode mcp oauth login my-api --server-url https://api.example.com --client-id my-client --scopes read write
 
 # Remove stored OAuth tokens
-bunx oh-my-opencode mcp oauth logout <server-name>
+bunx oh-my-opencode mcp oauth logout <server-name> --server-url https://api.example.com
 
 # Check OAuth token status
 bunx oh-my-opencode mcp oauth status [server-name]
@@ -166,7 +216,7 @@ bunx oh-my-opencode mcp oauth status [server-name]
 | -------------------- | ------------------------------------------------------------------------- |
 | `--server-url <url>` | MCP server URL (required for login)                                       |
 | `--client-id <id>`   | OAuth client ID (optional if server supports Dynamic Client Registration) |
-| `--scopes <scopes>`  | Comma-separated OAuth scopes                                              |
+| `--scopes <scopes>`  | OAuth scopes as separate variadic arguments (for example: `--scopes read write`) |
 
 ### Token Storage
 
@@ -176,10 +226,20 @@ Tokens are stored in `~/.config/opencode/mcp-oauth.json` with `0600` permissions
 
 ## Configuration Files
 
-The CLI searches for configuration files in the following locations (in priority order):
+The runtime loads user config as the base config, then merges project config on top:
 
-1. **Project Level**: `.opencode/oh-my-opencode.json`
-2. **User Level**: `~/.config/opencode/oh-my-opencode.json`
+1. **Project Level**: `.opencode/oh-my-openagent.jsonc`, `.opencode/oh-my-openagent.json`, `.opencode/oh-my-opencode.jsonc`, or `.opencode/oh-my-opencode.json`
+2. **User Level**: `~/.config/opencode/oh-my-openagent.jsonc`, `~/.config/opencode/oh-my-openagent.json`, `~/.config/opencode/oh-my-opencode.jsonc`, or `~/.config/opencode/oh-my-opencode.json`
+
+**Naming Note**: The published package and binary are still `oh-my-opencode`. Inside `opencode.json`, the compatibility layer now prefers the plugin entry `oh-my-openagent`. Plugin config loading recognizes both `oh-my-openagent.*` and legacy `oh-my-opencode.*` basenames. If both basenames exist in the same directory, the legacy `oh-my-opencode.*` file currently wins.
+
+### Filename Compatibility
+
+Both `.jsonc` and `.json` extensions are supported. JSONC (JSON with Comments) is preferred as it allows:
+- Comments (both `//` and `/* */` styles)
+- Trailing commas in arrays and objects
+
+If both `.jsonc` and `.json` exist in the same directory, the `.jsonc` file takes precedence.
 
 ### JSONC Support
 
@@ -228,19 +288,66 @@ bunx oh-my-opencode install
 # Diagnose with detailed information
 bunx oh-my-opencode doctor --verbose
 
-# Check specific category only
-bunx oh-my-opencode doctor --category authentication
+# Show compact system dashboard
+bunx oh-my-opencode doctor --status
+
+# JSON output for scripting
+bunx oh-my-opencode doctor --json
+```
+
+### "Using legacy package name" Warning
+
+The doctor warns if it finds the legacy plugin entry `oh-my-opencode` in `opencode.json`. Update the plugin array to the canonical `oh-my-openagent` entry:
+
+```bash
+# Replace the legacy plugin entry in user config
+jq '.plugin = (.plugin // [] | map(if . == "oh-my-opencode" then "oh-my-openagent" else . end))' \
+  ~/.config/opencode/opencode.json > /tmp/opencode.json && mv /tmp/opencode.json ~/.config/opencode/opencode.json
+```
+---
+
+## refresh-model-capabilities
+
+Refreshes the cached model capabilities snapshot from models.dev. This updates the local cache used by capability resolution and compatibility diagnostics.
+
+### Usage
+
+```bash
+bunx oh-my-opencode refresh-model-capabilities
+```
+
+### Options
+
+| Option            | Description                                         |
+| ----------------- | --------------------------------------------------- |
+| `-d, --directory` | Working directory to read oh-my-opencode config from |
+| `--source-url <url>` | Override the models.dev source URL               |
+| `--json`          | Output refresh summary as JSON                      |
+
+### Configuration
+
+Configure automatic refresh behavior in your plugin config:
+
+```jsonc
+{
+  "model_capabilities": {
+    "enabled": true,
+    "auto_refresh_on_start": true,
+    "refresh_timeout_ms": 5000,
+    "source_url": "https://models.dev/api.json"
+  }
+}
 ```
 
 ---
 
 ## Non-Interactive Mode
 
-Use the `--no-tui` option for CI/CD environments.
+Use JSON output for CI or scripted diagnostics.
 
 ```bash
 # Run doctor in CI environment
-bunx oh-my-opencode doctor --no-tui --json
+bunx oh-my-opencode doctor --json
 
 # Save results to file
 bunx oh-my-opencode doctor --json > doctor-report.json

docs/reference/configuration.md

@@ -1,6 +1,6 @@
 # Configuration Reference
 
-Complete reference for `oh-my-opencode.jsonc` configuration. This document covers every available option with examples.
+Complete reference for Oh My OpenCode plugin configuration. During the rename transition, the runtime recognizes both `oh-my-openagent.json[c]` and legacy `oh-my-opencode.json[c]` files.
 
 ---
 
@@ -30,6 +30,7 @@ Complete reference for `oh-my-opencode.jsonc` configuration. This document cover
   - [LSP](#lsp)
 - [Advanced](#advanced)
   - [Runtime Fallback](#runtime-fallback)
+  - [Model Capabilities](#model-capabilities)
   - [Hashline Edit](#hashline-edit)
   - [Experimental](#experimental)
 - [Reference](#reference)
@@ -42,16 +43,17 @@ Complete reference for `oh-my-opencode.jsonc` configuration. This document cover
 
 ### File Locations
 
-Priority order (project overrides user):
+User config is loaded first, then project config overrides it. In each directory, the compatibility layer recognizes both the renamed and legacy basenames.
 
-1. `.opencode/oh-my-opencode.jsonc` / `.opencode/oh-my-opencode.json`
+1. Project config: `.opencode/oh-my-openagent.json[c]` or `.opencode/oh-my-opencode.json[c]`
 2. User config (`.jsonc` preferred over `.json`):
 
-| Platform    | Path                                      |
-| ----------- | ----------------------------------------- |
-| macOS/Linux | `~/.config/opencode/oh-my-opencode.jsonc` |
-| Windows     | `%APPDATA%\opencode\oh-my-opencode.jsonc` |
+| Platform    | Path candidates |
+| ----------- | --------------- |
+| macOS/Linux | `~/.config/opencode/oh-my-openagent.json[c]`, `~/.config/opencode/oh-my-opencode.json[c]` |
+| Windows     | `%APPDATA%\opencode\oh-my-openagent.json[c]`, `%APPDATA%\opencode\oh-my-opencode.json[c]` |
 
+**Rename compatibility:** The published package and CLI binary remain `oh-my-opencode`. OpenCode plugin registration prefers `oh-my-openagent`, while legacy `oh-my-opencode` entries and config basenames still load during the transition. Config detection checks `oh-my-opencode` before `oh-my-openagent`, so if both plugin config basenames exist in the same directory, the legacy `oh-my-opencode.*` file currently wins.
 JSONC supports `// line comments`, `/* block comments */`, and trailing commas.
 
 Enable schema autocomplete:
@@ -93,19 +95,19 @@ Here's a practical starting configuration:
   },
 
   "categories": {
-    // quick — trivial tasks
+    // quick - trivial tasks
     "quick": { "model": "opencode/gpt-5-nano" },
 
-    // unspecified-low — moderate tasks
+    // unspecified-low - moderate tasks
     "unspecified-low": { "model": "anthropic/claude-sonnet-4-6" },
 
-    // unspecified-high — complex work
+    // unspecified-high - complex work
     "unspecified-high": { "model": "anthropic/claude-opus-4-6", "variant": "max" },
 
-    // writing — docs/prose
+    // writing - docs/prose
     "writing": { "model": "google/gemini-3-flash" },
 
-    // visual-engineering — Gemini dominates visual tasks
+    // visual-engineering - Gemini dominates visual tasks
     "visual-engineering": {
       "model": "google/gemini-3.1-pro",
       "variant": "high",
@@ -157,26 +159,28 @@ Override built-in agent settings. Available agents: `sisyphus`, `hephaestus`, `p
 
 Disable agents entirely: `{ "disabled_agents": ["oracle", "multimodal-looker"] }`
 
+Core agents receive an injected runtime `order` field for deterministic Tab cycling in the UI: Sisyphus = 1, Hephaestus = 2, Prometheus = 3, Atlas = 4. This is not a user-configurable config key.
+
 #### Agent Options
 
-| Option            | Type          | Description                                            |
-| ----------------- | ------------- | ------------------------------------------------------ |
-| `model`           | string        | Model override (`provider/model`)                      |
-| `fallback_models` | string\|array | Fallback models on API errors                          |
-| `temperature`     | number        | Sampling temperature                                   |
-| `top_p`           | number        | Top-p sampling                                         |
-| `prompt`          | string        | Replace system prompt                                  |
-| `prompt_append`   | string        | Append to system prompt                                |
+| Option            | Type           | Description                                                     |
+| ----------------- | -------------- | --------------------------------------------------------------- |
+| `model`           | string         | Model override (`provider/model`)                               |
+| `fallback_models` | string\|array  | Fallback models on API errors. Supports strings or mixed arrays of strings and object entries with per-model settings |
+| `temperature`     | number         | Sampling temperature                                            |
+| `top_p`           | number         | Top-p sampling                                                  |
+| `prompt`          | string         | Replace system prompt. Supports `file://` URIs                  |
+| `prompt_append`   | string         | Append to system prompt. Supports `file://` URIs                |
 | `tools`           | array         | Allowed tools list                                     |
 | `disable`         | boolean       | Disable this agent                                     |
 | `mode`            | string        | Agent mode                                             |
 | `color`           | string        | UI color                                               |
 | `permission`      | object        | Per-tool permissions (see below)                       |
 | `category`        | string        | Inherit model from category                            |
-| `variant`         | string        | Model variant: `max`, `high`, `medium`, `low`, `xhigh` |
+| `variant`         | string        | Model variant: `max`, `high`, `medium`, `low`, `xhigh`. Normalized to supported values |
 | `maxTokens`       | number        | Max response tokens                                    |
 | `thinking`        | object        | Anthropic extended thinking                            |
-| `reasoningEffort` | string        | OpenAI reasoning: `low`, `medium`, `high`, `xhigh`     |
+| `reasoningEffort` | string        | OpenAI reasoning: `none`, `minimal`, `low`, `medium`, `high`, `xhigh`. Normalized to supported values |
 | `textVerbosity`   | string        | Text verbosity: `low`, `medium`, `high`                |
 | `providerOptions` | object        | Provider-specific options                              |
 
@@ -216,6 +220,65 @@ Control what tools an agent can use:
 | `doom_loop`          | `ask` / `allow` / `deny`                                                    |
 | `external_directory` | `ask` / `allow` / `deny`                                                    |
 
+
+#### Fallback Models with Per-Model Settings
+
+`fallback_models` accepts either a single model string or an array. Array entries can be plain strings or objects with individual model settings:
+
+```jsonc
+{
+  "agents": {
+    "sisyphus": {
+      "model": "anthropic/claude-opus-4-6",
+      "fallback_models": [
+        // Simple string fallback
+        "openai/gpt-5.4",
+        // Object with per-model settings
+        {
+          "model": "google/gemini-3.1-pro",
+          "variant": "high",
+          "temperature": 0.2
+        },
+        {
+          "model": "anthropic/claude-sonnet-4-6",
+          "thinking": { "type": "enabled", "budgetTokens": 64000 }
+        }
+      ]
+    }
+  }
+}
+```
+
+Object entries support: `model`, `variant`, `reasoningEffort`, `temperature`, `top_p`, `maxTokens`, `thinking`.
+
+#### File URIs for Prompts
+
+Both `prompt` and `prompt_append` support loading content from files via `file://` URIs. Category-level `prompt_append` supports the same URI forms.
+
+```jsonc
+{
+  "agents": {
+    "sisyphus": {
+      "prompt_append": "file:///absolute/path/to/prompt.txt"
+    },
+    "oracle": {
+      "prompt": "file://./relative/to/project/prompt.md"
+    },
+    "explore": {
+      "prompt_append": "file://~/home/dir/prompt.txt"
+    }
+  },
+  "categories": {
+    "custom": {
+      "model": "anthropic/claude-sonnet-4-6",
+      "prompt_append": "file://./category-context.md"
+    }
+  }
+}
+```
+
+Paths can be absolute (`file:///abs/path`), relative to project root (`file://./rel/path`), or home-relative (`file://~/home/path`). If a file URI cannot be decoded, resolved, or read, OmO inserts a warning placeholder into the prompt instead of failing hard.
+
 ### Categories
 
 Domain-specific model delegation used by the `task()` tool. When Sisyphus delegates work, it picks a category, not a model name.
@@ -228,7 +291,7 @@ Domain-specific model delegation used by the `task()` tool. When Sisyphus delega
 | `ultrabrain`         | `openai/gpt-5.4` (xhigh)        | Deep logical reasoning, complex architecture   |
 | `deep`               | `openai/gpt-5.3-codex` (medium) | Autonomous problem-solving, thorough research  |
 | `artistry`           | `google/gemini-3.1-pro` (high)  | Creative/unconventional approaches             |
-| `quick`              | `anthropic/claude-haiku-4-5`    | Trivial tasks, typo fixes, single-file changes |
+| `quick`              | `openai/gpt-5.4-mini`           | Trivial tasks, typo fixes, single-file changes |
 | `unspecified-low`    | `anthropic/claude-sonnet-4-6`   | General tasks, low effort                      |
 | `unspecified-high`   | `anthropic/claude-opus-4-6` (max) | General tasks, high effort                   |
 | `writing`            | `google/gemini-3-flash`         | Documentation, prose, technical writing        |
@@ -240,16 +303,16 @@ Domain-specific model delegation used by the `task()` tool. When Sisyphus delega
 | Option              | Type          | Default | Description                                                         |
 | ------------------- | ------------- | ------- | ------------------------------------------------------------------- |
 | `model`             | string        | -       | Model override                                                      |
-| `fallback_models`   | string\|array | -       | Fallback models on API errors                                       |
+| `fallback_models`   | string\|array | -       | Fallback models on API errors. Supports strings or mixed arrays of strings and object entries with per-model settings |
 | `temperature`       | number        | -       | Sampling temperature                                                |
 | `top_p`             | number        | -       | Top-p sampling                                                      |
 | `maxTokens`         | number        | -       | Max response tokens                                                 |
 | `thinking`          | object        | -       | Anthropic extended thinking                                         |
-| `reasoningEffort`   | string        | -       | OpenAI reasoning effort                                             |
+| `reasoningEffort`   | string        | -       | OpenAI reasoning effort. Unsupported values are normalized          |
 | `textVerbosity`     | string        | -       | Text verbosity                                                      |
 | `tools`             | array         | -       | Allowed tools                                                       |
 | `prompt_append`     | string        | -       | Append to system prompt                                             |
-| `variant`           | string        | -       | Model variant                                                       |
+| `variant`           | string        | -       | Model variant. Unsupported values are normalized                    |
 | `description`       | string        | -       | Shown in `task()` tool prompt                                       |
 | `is_unstable_agent` | boolean       | `false` | Force background mode + monitoring. Auto-enabled for Gemini models. |
 
@@ -257,39 +320,64 @@ Disable categories: `{ "disabled_categories": ["ultrabrain"] }`
 
 ### Model Resolution
 
-3-step priority at runtime:
+Runtime priority:
+
+1. **UI-selected model** - model chosen in the OpenCode UI, for primary agents
+2. **User override** - model set in config → used exactly as-is. Even on cold cache, explicit user configuration takes precedence over hardcoded fallback chains
+3. **Category default** - model inherited from the assigned category config
+4. **User `fallback_models`** - user-configured fallback list is tried before built-in fallback chains
+5. **Provider fallback chain** - built-in provider/model chain from OmO source
+6. **System default** - OpenCode's configured default model
+
+#### Model Settings Compatibility
+
+Model settings are compatibility-normalized against model capabilities instead of failing hard.
+
+Normalized fields:
+
+- `variant` - downgraded to the closest supported value
+- `reasoningEffort` - downgraded to the closest supported value, or removed if unsupported
+- `temperature` - removed if unsupported by the model metadata
+- `top_p` - removed if unsupported by the model metadata
+- `maxTokens` - capped to the model's reported max output limit
+- `thinking` - removed if the target model does not support thinking
+
+Examples:
+- Claude models do not support `reasoningEffort` - it is removed automatically
+- GPT-4.1 does not support reasoning - `reasoningEffort` is removed
+- o-series models support `none` through `high` - `xhigh` is downgraded to `high`
+- GPT-5 supports `none`, `minimal`, `low`, `medium`, `high`, `xhigh` - all pass through
+
+Capability data comes from provider runtime metadata first. OmO also ships bundled models.dev-backed capability data, supports a refreshable local models.dev cache, and falls back to heuristic family detection plus alias rules when exact metadata is unavailable. `bunx oh-my-opencode doctor` surfaces capability diagnostics and warns when a configured model relies on compatibility fallback.
 
-1. **User override** — model set in config → used exactly as-is
-2. **Provider fallback chain** — tries each provider in priority order until available
-3. **System default** — falls back to OpenCode's configured default model
 
 #### Agent Provider Chains
 
 | Agent                 | Default Model       | Provider Priority                                                            |
 | --------------------- | ------------------- | ---------------------------------------------------------------------------- |
-| **Sisyphus**          | `claude-opus-4-6`   | `claude-opus-4-6` → `glm-5` → `big-pickle`                                   |
-| **Hephaestus**        | `gpt-5.3-codex`     | `gpt-5.3-codex` → `gpt-5.4` (GitHub Copilot fallback)                        |
-| **oracle**            | `gpt-5.4`           | `gpt-5.4` → `gemini-3.1-pro` → `claude-opus-4-6`                             |
-| **librarian**         | `gemini-3-flash`    | `gemini-3-flash` → `minimax-m2.5-free` → `big-pickle`                        |
-| **explore**           | `grok-code-fast-1`  | `grok-code-fast-1` → `minimax-m2.5-free` → `claude-haiku-4-5` → `gpt-5-nano` |
-| **multimodal-looker** | `gpt-5.3-codex`     | `gpt-5.3-codex` → `k2p5` → `gemini-3-flash` → `glm-4.6v` → `gpt-5-nano`      |
-| **Prometheus**        | `claude-opus-4-6`   | `claude-opus-4-6` → `gpt-5.4` → `gemini-3.1-pro`                             |
-| **Metis**             | `claude-opus-4-6`   | `claude-opus-4-6` → `gpt-5.4` → `gemini-3.1-pro`                             |
-| **Momus**             | `gpt-5.4`           | `gpt-5.4` → `claude-opus-4-6` → `gemini-3.1-pro`                             |
-| **Atlas**             | `claude-sonnet-4-6` | `claude-sonnet-4-6` → `gpt-5.4`                                              |
+| **Sisyphus**          | `claude-opus-4-6`   | `anthropic\|github-copilot\|opencode/claude-opus-4-6 (max)` → `opencode-go/kimi-k2.5` → `kimi-for-coding/k2p5` → `opencode\|moonshotai\|moonshotai-cn\|firmware\|ollama-cloud\|aihubmix/kimi-k2.5` → `openai\|github-copilot\|opencode/gpt-5.4 (medium)` → `zai-coding-plan\|opencode/glm-5` → `opencode/big-pickle` |
+| **Hephaestus**        | `gpt-5.4`           | `gpt-5.4 (medium)`                                                           |
+| **oracle**            | `gpt-5.4`           | `openai\|github-copilot\|opencode/gpt-5.4 (high)` → `google\|github-copilot\|opencode/gemini-3.1-pro (high)` → `anthropic\|github-copilot\|opencode/claude-opus-4-6 (max)` → `opencode-go/glm-5` |
+| **librarian**         | `minimax-m2.7`      | `opencode-go/minimax-m2.7` → `opencode/minimax-m2.7-highspeed` → `anthropic\|opencode/claude-haiku-4-5` → `opencode/gpt-5-nano` |
+| **explore**           | `grok-code-fast-1`  | `github-copilot\|xai/grok-code-fast-1` → `opencode-go/minimax-m2.7-highspeed` → `opencode/minimax-m2.7` → `anthropic\|opencode/claude-haiku-4-5` → `opencode/gpt-5-nano` |
+| **multimodal-looker** | `gpt-5.4`           | `openai\|opencode/gpt-5.4 (medium)` → `opencode-go/kimi-k2.5` → `zai-coding-plan/glm-4.6v` → `openai\|github-copilot\|opencode/gpt-5-nano` |
+| **Prometheus**        | `claude-opus-4-6`   | `anthropic\|github-copilot\|opencode/claude-opus-4-6 (max)` → `openai\|github-copilot\|opencode/gpt-5.4 (high)` → `opencode-go/glm-5` → `google\|github-copilot\|opencode/gemini-3.1-pro` |
+| **Metis**             | `claude-opus-4-6`   | `anthropic\|github-copilot\|opencode/claude-opus-4-6 (max)` → `openai\|github-copilot\|opencode/gpt-5.4 (high)` → `opencode-go/glm-5` → `kimi-for-coding/k2p5` |
+| **Momus**             | `gpt-5.4`           | `openai\|github-copilot\|opencode/gpt-5.4 (xhigh)` → `anthropic\|github-copilot\|opencode/claude-opus-4-6 (max)` → `google\|github-copilot\|opencode/gemini-3.1-pro (high)` → `opencode-go/glm-5` |
+| **Atlas**             | `claude-sonnet-4-6` | `anthropic\|github-copilot\|opencode/claude-sonnet-4-6` → `opencode-go/kimi-k2.5` → `openai\|github-copilot\|opencode/gpt-5.4 (medium)` → `opencode-go/minimax-m2.7` |
 
 #### Category Provider Chains
 
 | Category               | Default Model       | Provider Priority                                              |
 | ---------------------- | ------------------- | -------------------------------------------------------------- |
-| **visual-engineering** | `gemini-3.1-pro`    | `gemini-3.1-pro` → `glm-5` → `claude-opus-4-6`                 |
-| **ultrabrain**         | `gpt-5.4`           | `gpt-5.4` → `gemini-3.1-pro` → `claude-opus-4-6`               |
-| **deep**               | `gpt-5.3-codex`     | `gpt-5.3-codex` → `claude-opus-4-6` → `gemini-3.1-pro`         |
-| **artistry**           | `gemini-3.1-pro`    | `gemini-3.1-pro` → `claude-opus-4-6` → `gpt-5.4`               |
-| **quick**              | `claude-haiku-4-5`  | `claude-haiku-4-5` → `gemini-3-flash` → `gpt-5-nano`           |
-| **unspecified-low**    | `claude-sonnet-4-6` | `claude-sonnet-4-6` → `gpt-5.3-codex` → `gemini-3-flash`       |
-| **unspecified-high**   | `claude-opus-4-6`   | `claude-opus-4-6` → `gpt-5.4 (high)` → `glm-5` → `k2p5` → `kimi-k2.5` |
-| **writing**            | `gemini-3-flash`    | `gemini-3-flash` → `claude-sonnet-4-6`                         |
+| **visual-engineering** | `gemini-3.1-pro`    | `google\|github-copilot\|opencode/gemini-3.1-pro (high)` → `zai-coding-plan\|opencode/glm-5` → `anthropic\|github-copilot\|opencode/claude-opus-4-6 (max)` → `opencode-go/glm-5` → `kimi-for-coding/k2p5` |
+| **ultrabrain**         | `gpt-5.4`           | `openai\|opencode/gpt-5.4 (xhigh)` → `google\|github-copilot\|opencode/gemini-3.1-pro (high)` → `anthropic\|github-copilot\|opencode/claude-opus-4-6 (max)` → `opencode-go/glm-5` |
+| **deep**               | `gpt-5.3-codex`     | `openai\|opencode/gpt-5.3-codex (medium)` → `anthropic\|github-copilot\|opencode/claude-opus-4-6 (max)` → `google\|github-copilot\|opencode/gemini-3.1-pro (high)` |
+| **artistry**           | `gemini-3.1-pro`    | `google\|github-copilot\|opencode/gemini-3.1-pro (high)` → `anthropic\|github-copilot\|opencode/claude-opus-4-6 (max)` → `openai\|github-copilot\|opencode/gpt-5.4` |
+| **quick**              | `gpt-5.4-mini`      | `openai\|github-copilot\|opencode/gpt-5.4-mini` → `anthropic\|github-copilot\|opencode/claude-haiku-4-5` → `google\|github-copilot\|opencode/gemini-3-flash` → `opencode-go/minimax-m2.7` → `opencode/gpt-5-nano` |
+| **unspecified-low**    | `claude-sonnet-4-6` | `anthropic\|github-copilot\|opencode/claude-sonnet-4-6` → `openai\|opencode/gpt-5.3-codex (medium)` → `opencode-go/kimi-k2.5` → `google\|github-copilot\|opencode/gemini-3-flash` → `opencode-go/minimax-m2.7` |
+| **unspecified-high**   | `claude-opus-4-6`   | `anthropic\|github-copilot\|opencode/claude-opus-4-6 (max)` → `openai\|github-copilot\|opencode/gpt-5.4 (high)` → `zai-coding-plan\|opencode/glm-5` → `kimi-for-coding/k2p5` → `opencode-go/glm-5` → `opencode/kimi-k2.5` → `opencode\|moonshotai\|moonshotai-cn\|firmware\|ollama-cloud\|aihubmix/kimi-k2.5` |
+| **writing**            | `gemini-3-flash`    | `google\|github-copilot\|opencode/gemini-3-flash` → `opencode-go/kimi-k2.5` → `anthropic\|github-copilot\|opencode/claude-sonnet-4-6` → `opencode-go/minimax-m2.7` |
 
 Run `bunx oh-my-opencode doctor --verbose` to see effective model resolution for your config.
 
@@ -418,17 +506,17 @@ Disable built-in skills: `{ "disabled_skills": ["playwright"] }`
 Disable built-in hooks via `disabled_hooks`:
 
 ```json
-{ "disabled_hooks": ["comment-checker", "gpt-permission-continuation"] }
+{ "disabled_hooks": ["comment-checker"] }
 ```
 
-Available hooks: `gpt-permission-continuation`, `todo-continuation-enforcer`, `context-window-monitor`, `session-recovery`, `session-notification`, `comment-checker`, `grep-output-truncator`, `tool-output-truncator`, `directory-agents-injector`, `directory-readme-injector`, `empty-task-response-detector`, `think-mode`, `anthropic-context-window-limit-recovery`, `rules-injector`, `background-notification`, `auto-update-checker`, `startup-toast`, `keyword-detector`, `agent-usage-reminder`, `non-interactive-env`, `interactive-bash-session`, `compaction-context-injector`, `thinking-block-validator`, `claude-code-hooks`, `ralph-loop`, `preemptive-compaction`, `auto-slash-command`, `sisyphus-junior-notepad`, `no-sisyphus-gpt`, `start-work`, `runtime-fallback`
+Available hooks: `todo-continuation-enforcer`, `context-window-monitor`, `session-recovery`, `session-notification`, `comment-checker`, `grep-output-truncator`, `tool-output-truncator`, `directory-agents-injector`, `directory-readme-injector`, `empty-task-response-detector`, `think-mode`, `anthropic-context-window-limit-recovery`, `rules-injector`, `background-notification`, `auto-update-checker`, `startup-toast`, `keyword-detector`, `agent-usage-reminder`, `non-interactive-env`, `interactive-bash-session`, `compaction-context-injector`, `thinking-block-validator`, `claude-code-hooks`, `ralph-loop`, `preemptive-compaction`, `auto-slash-command`, `sisyphus-junior-notepad`, `no-sisyphus-gpt`, `start-work`, `runtime-fallback`
 
 **Notes:**
 
-- `directory-agents-injector` — auto-disabled on OpenCode 1.1.37+ (native AGENTS.md support)
-- `gpt-permission-continuation` — resumes GPT sessions only when the last assistant reply ends with a permission-seeking tail like `If you want, ...`. Disable it if you prefer GPT sessions to wait for explicit user follow-up.
-- `no-sisyphus-gpt` — **do not disable**. It blocks incompatible GPT models for Sisyphus while allowing the dedicated GPT-5.4 prompt path.
+- `directory-agents-injector` - auto-disabled on OpenCode 1.1.37+ (native AGENTS.md support)
+- `no-sisyphus-gpt` - **do not disable**. It blocks incompatible GPT models for Sisyphus while allowing the dedicated GPT-5.4 prompt path.
 - `startup-toast` is a sub-feature of `auto-update-checker`. Disable just the toast by adding `startup-toast` to `disabled_hooks`.
+- `session-recovery` - automatically recovers from recoverable session errors (missing tool results, unavailable tools, thinking block violations). Shows toast notifications during recovery. Enable `experimental.auto_resume` for automatic retry after recovery.
 
 ### Commands
 
@@ -505,7 +593,7 @@ Force-enable session notifications:
 { "notification": { "force_enable": true } }
 ```
 
-`force_enable` (`false`) — force session-notification even if external notification plugins are detected.
+`force_enable` (`false`) - force session-notification even if external notification plugins are detected.
 
 ### MCPs
 
@@ -591,12 +679,233 @@ Define `fallback_models` per agent or category:
   "agents": {
     "sisyphus": {
       "model": "anthropic/claude-opus-4-6",
-      "fallback_models": ["openai/gpt-5.4", "google/gemini-3.1-pro"]
+      "fallback_models": [
+        "openai/gpt-5.4",
+        {
+          "model": "google/gemini-3.1-pro",
+          "variant": "high"
+        }
+      ]
     }
   }
 }
 ```
 
+`fallback_models` also supports object-style entries so you can attach settings to a specific fallback model:
+
+```json
+{
+  "agents": {
+    "sisyphus": {
+      "model": "anthropic/claude-opus-4-6",
+      "fallback_models": [
+        "openai/gpt-5.4",
+        {
+          "model": "anthropic/claude-sonnet-4-6",
+          "variant": "high",
+          "thinking": { "type": "enabled", "budgetTokens": 12000 }
+        },
+        {
+          "model": "openai/gpt-5.3-codex",
+          "reasoningEffort": "high",
+          "temperature": 0.2,
+          "top_p": 0.95,
+          "maxTokens": 8192
+        }
+      ]
+    }
+  }
+}
+```
+
+Mixed arrays are allowed, so string entries and object entries can appear together in the same fallback chain.
+
+#### Object-style `fallback_models`
+
+Object entries use the following shape:
+
+| Field | Type | Description |
+| ----- | ---- | ----------- |
+| `model` | string | Fallback model ID. Provider prefix is optional when OmO can inherit the current/default provider. |
+| `variant` | string | Explicit variant override for this fallback entry. |
+| `reasoningEffort` | string | OpenAI reasoning effort override for this fallback entry. |
+| `temperature` | number | Temperature applied if this fallback model becomes active. |
+| `top_p` | number | Top-p applied if this fallback model becomes active. |
+| `maxTokens` | number | Max response tokens applied if this fallback model becomes active. |
+| `thinking` | object | Anthropic thinking config applied if this fallback model becomes active. |
+
+Per-model settings are **fallback-only**. They are promoted only when that specific fallback model is actually selected, so they do not override your primary model settings when the primary model resolves successfully.
+
+`thinking` uses the same shape as the normal agent/category option:
+
+| Field | Type | Description |
+| ----- | ---- | ----------- |
+| `type` | string | `enabled` or `disabled` |
+| `budgetTokens` | number | Optional Anthropic thinking budget |
+
+Object entries can also omit the provider prefix when OmO can infer it from the current/default provider. If you provide both inline variant syntax in `model` and an explicit `variant` field, the explicit `variant` field wins.
+
+#### Full examples
+
+**1. Simple string chain**
+
+Use strings when you only need an ordered fallback chain:
+
+```json
+{
+  "agents": {
+    "atlas": {
+      "model": "anthropic/claude-sonnet-4-6",
+      "fallback_models": [
+        "anthropic/claude-haiku-4-5",
+        "openai/gpt-5.4",
+        "google/gemini-3.1-pro"
+      ]
+    }
+  }
+}
+```
+
+**2. Same-provider shorthand**
+
+If the primary model already establishes the provider, fallback entries can omit the prefix:
+
+```json
+{
+  "agents": {
+    "atlas": {
+      "model": "openai/gpt-5.4",
+      "fallback_models": [
+        "gpt-5.4-mini",
+        {
+          "model": "gpt-5.3-codex",
+          "reasoningEffort": "medium",
+          "maxTokens": 4096
+        }
+      ]
+    }
+  }
+}
+```
+
+In this example OmO treats `gpt-5.4-mini` and `gpt-5.3-codex` as OpenAI fallback entries because the current/default provider is already `openai`.
+
+**3. Mixed cross-provider chain**
+
+Mix string entries and object entries when only some fallback models need special settings:
+
+```json
+{
+  "agents": {
+    "sisyphus": {
+      "model": "anthropic/claude-opus-4-6",
+      "fallback_models": [
+        "openai/gpt-5.4",
+        {
+          "model": "anthropic/claude-sonnet-4-6",
+          "variant": "high",
+          "thinking": { "type": "enabled", "budgetTokens": 12000 }
+        },
+        {
+          "model": "google/gemini-3.1-pro",
+          "variant": "high"
+        }
+      ]
+    }
+  }
+}
+```
+
+**4. Category-level fallback chain**
+
+`fallback_models` works the same way under `categories`:
+
+```json
+{
+  "categories": {
+    "deep": {
+      "model": "openai/gpt-5.3-codex",
+      "fallback_models": [
+        {
+          "model": "openai/gpt-5.4",
+          "reasoningEffort": "xhigh",
+          "maxTokens": 12000
+        },
+        {
+          "model": "anthropic/claude-opus-4-6",
+          "variant": "max",
+          "temperature": 0.2
+        },
+        "google/gemini-3.1-pro(high)"
+      ]
+    }
+  }
+}
+```
+
+**5. Full object entry with every supported field**
+
+This shows every supported object-style parameter in one place:
+
+```json
+{
+  "agents": {
+    "oracle": {
+      "model": "openai/gpt-5.4",
+      "fallback_models": [
+        {
+          "model": "openai/gpt-5.3-codex(low)",
+          "variant": "xhigh",
+          "reasoningEffort": "high",
+          "temperature": 0.3,
+          "top_p": 0.9,
+          "maxTokens": 8192,
+          "thinking": {
+            "type": "disabled"
+          }
+        }
+      ]
+    }
+  }
+}
+```
+
+In this example the explicit `"variant": "xhigh"` overrides the inline `(low)` suffix in `"model"`.
+
+This final example is a **complete shape reference**. In real configs, prefer provider-appropriate settings:
+
+- use `reasoningEffort` for OpenAI reasoning models
+- use `thinking` for Anthropic thinking-capable models
+- use `variant`, `temperature`, `top_p`, and `maxTokens` only when that fallback model supports them
+
+### Model Capabilities
+
+OmO can refresh a local models.dev capability snapshot on startup. This cache is controlled by `model_capabilities`.
+
+```jsonc
+{
+  "model_capabilities": {
+    "enabled": true,
+    "auto_refresh_on_start": true,
+    "refresh_timeout_ms": 5000,
+    "source_url": "https://models.dev/api.json"
+  }
+}
+```
+
+| Option | Default behavior | Description |
+| ------ | ---------------- | ----------- |
+| `enabled` | enabled unless explicitly set to `false` | Master switch for model capability refresh behavior |
+| `auto_refresh_on_start` | refresh on startup unless explicitly set to `false` | Refresh the local models.dev cache during startup checks |
+| `refresh_timeout_ms` | `5000` | Timeout for the startup refresh attempt |
+| `source_url` | `https://models.dev/api.json` | Override the models.dev source URL |
+
+Notes:
+
+- Startup refresh runs through the auto-update checker hook.
+- Manual refresh is available via `bunx oh-my-opencode refresh-model-capabilities`.
+- Provider runtime metadata still takes priority when OmO resolves capabilities for compatibility checks.
+
 ### Hashline Edit
 
 Replaces the built-in `Edit` tool with a hash-anchored version using `LINE#ID` references to prevent stale-line edits. Disabled by default.
@@ -616,7 +925,7 @@ When enabled, two companion hooks are active: `hashline-read-enhancer` (annotate
     "aggressive_truncation": false,
     "auto_resume": false,
     "disable_omo_env": false,
-    "task_system": false,
+    "task_system": true,
     "dynamic_context_pruning": {
       "enabled": false,
       "notification": "detailed",
@@ -646,7 +955,7 @@ When enabled, two companion hooks are active: `hashline-read-enhancer` (annotate
 | `aggressive_truncation`                  | `false`    | Aggressively truncate when token limit exceeded                                      |
 | `auto_resume`                            | `false`    | Auto-resume after thinking block recovery                                            |
 | `disable_omo_env`                        | `false`    | Disable auto-injected `<omo-env>` block (date/time/locale). Improves cache hit rate. |
-| `task_system`                            | `false`    | Enable Sisyphus task system                                                          |
+| `task_system`                            | `true`     | Enable Sisyphus task system                                                          |
 | `dynamic_context_pruning.enabled`        | `false`    | Auto-prune old tool outputs to manage context window                                 |
 | `dynamic_context_pruning.notification`   | `detailed` | Pruning notifications: `off` / `minimal` / `detailed`                                |
 | `turn_protection.turns`                  | `3`        | Recent turns protected from pruning (1–10)                                           |

docs/reference/features.md

@@ -1,34 +1,35 @@
-# Oh-My-OpenCode Features Reference
+# Oh-My-OpenAgent Features Reference
 
 ## Agents
 
-Oh-My-OpenCode provides 11 specialized AI agents. Each has distinct expertise, optimized models, and tool permissions.
+Oh-My-OpenAgent provides 11 specialized AI agents. Each has distinct expertise, optimized models, and tool permissions.
 
 ### Core Agents
 
+Core-agent tab cycling is deterministic via injected runtime order field. The fixed priority order is Sisyphus (order: 1), Hephaestus (order: 2), Prometheus (order: 3), and Atlas (order: 4). Remaining agents follow after that stable core ordering.
+
 | Agent                 | Model              | Purpose                                                                                                                                                                                                                                                                                                                                                          |
 | --------------------- | ------------------ | ---------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------- |
-| **Sisyphus**          | `claude-opus-4-6`  | The default orchestrator. Plans, delegates, and executes complex tasks using specialized subagents with aggressive parallel execution. Todo-driven workflow with extended thinking (32k budget). Fallback: `glm-5` → `big-pickle`.                                                                                                                               |
-| **Hephaestus**        | `gpt-5.3-codex`    | The Legitimate Craftsman. Autonomous deep worker inspired by AmpCode's deep mode. Goal-oriented execution with thorough research before action. Explores codebase patterns, completes tasks end-to-end without premature stopping. Named after the Greek god of forge and craftsmanship. Fallback: `gpt-5.4` on GitHub Copilot. Requires a GPT-capable provider. |
-| **Oracle**            | `gpt-5.4`          | Architecture decisions, code review, debugging. Read-only consultation with stellar logical reasoning and deep analysis. Inspired by AmpCode. Fallback: `gemini-3.1-pro` → `claude-opus-4-6`.                                                                                                                                                                    |
-| **Librarian**         | `gemini-3-flash`   | Multi-repo analysis, documentation lookup, OSS implementation examples. Deep codebase understanding with evidence-based answers. Fallback: `minimax-m2.5-free` → `big-pickle`.                                                                                                                                                                                   |
-| **Explore**           | `grok-code-fast-1` | Fast codebase exploration and contextual grep. Fallback: `minimax-m2.5-free` → `claude-haiku-4-5` → `gpt-5-nano`.                                                                                                                                                                                                                                                |
-| **Multimodal-Looker** | `gpt-5.3-codex`    | Visual content specialist. Analyzes PDFs, images, diagrams to extract information. Fallback: `k2p5` → `gemini-3-flash` → `glm-4.6v` → `gpt-5-nano`.                                                                                                                                                                                                              |
-
+| **Sisyphus**          | `claude-opus-4-6`  | The default orchestrator. Plans, delegates, and executes complex tasks using specialized subagents with aggressive parallel execution. Todo-driven workflow with extended thinking (32k budget). Fallback: `opencode-go/kimi-k2.5` → `kimi-for-coding/k2p5` → `opencode\|moonshotai\|moonshotai-cn\|firmware\|ollama-cloud\|aihubmix/kimi-k2.5` → `openai\|github-copilot\|opencode/gpt-5.4 (medium)` → `zai-coding-plan\|opencode/glm-5` → `opencode/big-pickle`. |
+| **Hephaestus**        | `gpt-5.4`          | The Legitimate Craftsman. Autonomous deep worker inspired by AmpCode's deep mode. Goal-oriented execution with thorough research before action. Explores codebase patterns, completes tasks end-to-end without premature stopping. Named after the Greek god of forge and craftsmanship. Requires a GPT-capable provider. |
+| **Oracle**            | `gpt-5.4`          | Architecture decisions, code review, debugging. Read-only consultation with stellar logical reasoning and deep analysis. Inspired by AmpCode. Fallback: `google\|github-copilot\|opencode/gemini-3.1-pro (high)` → `anthropic\|github-copilot\|opencode/claude-opus-4-6 (max)` → `opencode-go/glm-5`.                                                                                                                                 |
+| **Librarian**         | `minimax-m2.7`     | Multi-repo analysis, documentation lookup, OSS implementation examples. Deep codebase understanding with evidence-based answers. Fallback: `opencode/minimax-m2.7-highspeed` → `anthropic\|opencode/claude-haiku-4-5` → `opencode/gpt-5-nano`.                                                                                                                                               |
+| **Explore**           | `grok-code-fast-1` | Fast codebase exploration and contextual grep. Fallback: `opencode-go/minimax-m2.7-highspeed` → `opencode/minimax-m2.7` → `anthropic\|opencode/claude-haiku-4-5` → `opencode/gpt-5-nano`.                                                                                                                                                                                                      |
+| **Multimodal-Looker** | `gpt-5.4`          | Visual content specialist. Analyzes PDFs, images, diagrams to extract information. Fallback: `opencode-go/kimi-k2.5` → `zai-coding-plan/glm-4.6v` → `openai\|github-copilot\|opencode/gpt-5-nano`.                                                                                                                                                                                                   |
 ### Planning Agents
 
 | Agent          | Model             | Purpose                                                                                                                                            |
 | -------------- | ----------------- | -------------------------------------------------------------------------------------------------------------------------------------------------- |
-| **Prometheus** | `claude-opus-4-6` | Strategic planner with interview mode. Creates detailed work plans through iterative questioning. Fallback: `gpt-5.4` → `gemini-3.1-pro`.          |
-| **Metis**      | `claude-opus-4-6` | Plan consultant — pre-planning analysis. Identifies hidden intentions, ambiguities, and AI failure points. Fallback: `gpt-5.4` → `gemini-3.1-pro`. |
-| **Momus**      | `gpt-5.4`         | Plan reviewer — validates plans against clarity, verifiability, and completeness standards. Fallback: `claude-opus-4-6` → `gemini-3.1-pro`.        |
+| **Prometheus** | `claude-opus-4-6` | Strategic planner with interview mode. Creates detailed work plans through iterative questioning. Fallback: `openai\|github-copilot\|opencode/gpt-5.4 (high)` → `opencode-go/glm-5` → `google\|github-copilot\|opencode/gemini-3.1-pro`. |
+| **Metis**      | `claude-opus-4-6` | Plan consultant — pre-planning analysis. Identifies hidden intentions, ambiguities, and AI failure points. Fallback: `openai\|github-copilot\|opencode/gpt-5.4 (high)` → `opencode-go/glm-5` → `kimi-for-coding/k2p5`. |
+| **Momus**      | `gpt-5.4`         | Plan reviewer — validates plans against clarity, verifiability, and completeness standards. Fallback: `anthropic\|github-copilot\|opencode/claude-opus-4-6 (max)` → `google\|github-copilot\|opencode/gemini-3.1-pro (high)` → `opencode-go/glm-5`. |
 
 ### Orchestration Agents
 
 | Agent               | Model                  | Purpose                                                                                                                                                                                     |
 | ------------------- | ---------------------- | ------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------- |
-| **Atlas**           | `claude-sonnet-4-6`    | Todo-list orchestrator. Executes planned tasks systematically, managing todo items and coordinating work. Fallback: `gpt-5.4` (medium).                                                     |
-| **Sisyphus-Junior** | _(category-dependent)_ | Category-spawned executor. Model is selected automatically based on the task category (visual-engineering, quick, deep, etc.). Used when the main agent delegates work via the `task` tool. |
+| **Atlas**           | `claude-sonnet-4-6`    | Todo-list orchestrator. Executes planned tasks systematically, managing todo items and coordinating work. Fallback: `opencode-go/kimi-k2.5` → `openai\|github-copilot\|opencode/gpt-5.4 (medium)` → `opencode-go/minimax-m2.7`. |
+| **Sisyphus-Junior** | _(category-dependent)_ | Category-spawned executor. Model is selected automatically based on the task category (visual-engineering, quick, deep, etc.). Its built-in general fallback chain is `anthropic\|github-copilot\|opencode/claude-sonnet-4-6` → `opencode-go/kimi-k2.5` → `openai\|github-copilot\|opencode/gpt-5.4 (medium)` → `opencode-go/minimax-m2.7` → `opencode/big-pickle`. |
 
 ### Invoking Agents
 
@@ -89,8 +90,9 @@ When running inside tmux:
 - Watch multiple agents work in real-time
 - Each pane shows agent output live
 - Auto-cleanup when agents complete
+- **Stable agent ordering**: core-agent tab cycling is deterministic via injected runtime order field (Sisyphus: 1, Hephaestus: 2, Prometheus: 3, Atlas: 4)
 
-Customize agent models, prompts, and permissions in `oh-my-opencode.json`.
+Customize agent models, prompts, and permissions in `oh-my-opencode.jsonc`.
 
 ## Category System
 
@@ -111,7 +113,7 @@ By combining these two concepts, you can generate optimal agents through `task`.
 | `ultrabrain`         | `openai/gpt-5.4` (xhigh)        | Deep logical reasoning, complex architecture decisions requiring extensive analysis                                         |
 | `deep`               | `openai/gpt-5.3-codex` (medium) | Goal-oriented autonomous problem-solving. Thorough research before action. For hairy problems requiring deep understanding. |
 | `artistry`           | `google/gemini-3.1-pro` (high)  | Highly creative/artistic tasks, novel ideas                                                                                 |
-| `quick`              | `anthropic/claude-haiku-4-5`    | Trivial tasks - single file changes, typo fixes, simple modifications                                                       |
+| `quick`              | `openai/gpt-5.4-mini`           | Trivial tasks - single file changes, typo fixes, simple modifications                                                       |
 | `unspecified-low`    | `anthropic/claude-sonnet-4-6`   | Tasks that don't fit other categories, low effort required                                                                  |
 | `unspecified-high`   | `anthropic/claude-opus-4-6` (max) | Tasks that don't fit other categories, high effort required                                                               |
 | `writing`            | `google/gemini-3-flash`         | Documentation, prose, technical writing                                                                                     |
@@ -129,7 +131,7 @@ task({
 
 ### Custom Categories
 
-You can define custom categories in `oh-my-opencode.json`.
+You can define custom categories in your plugin config file. During the rename transition, both `oh-my-openagent.json[c]` and legacy `oh-my-opencode.json[c]` basenames are recognized.
 
 #### Category Configuration Schema
 
@@ -188,6 +190,75 @@ When you use a Category, a special agent called **Sisyphus-Junior** performs the
 - **Characteristic**: Cannot **re-delegate** tasks to other agents.
 - **Purpose**: Prevents infinite delegation loops and ensures focus on the assigned task.
 
+## Advanced Configuration
+
+### Rename Compatibility
+
+The published package and binary remain `oh-my-opencode`. Inside `opencode.json`, the compatibility layer now prefers the plugin entry `oh-my-openagent`, while legacy `oh-my-opencode` entries still load with a warning. Plugin config files (`oh-my-openagent.json[c]` or legacy `oh-my-opencode.json[c]`) are recognized during the transition. Run `bunx oh-my-opencode doctor` to check for legacy package name warnings.
+
+### Fallback Models
+
+Configure per-agent fallback chains with arrays that can mix plain model strings and per-model objects:
+
+```jsonc
+{
+  "agents": {
+    "sisyphus": {
+      "fallback_models": [
+        "opencode/glm-5",
+        { "model": "openai/gpt-5.4", "variant": "high" },
+        { "model": "anthropic/claude-sonnet-4-6", "thinking": { "type": "enabled", "budgetTokens": 64000 } }
+      ]
+    }
+  }
+}
+```
+
+When a model errors, the runtime can move through the configured fallback array. Object entries let you tune the backup model itself instead of only swapping the model name.
+
+### File-Based Prompts
+
+Load agent system prompts from external files using `file://` URLs in the `prompt` field, or append additional content with `prompt_append`. The `prompt_append` field also works on categories.
+
+```jsonc
+{
+  "agents": {
+    "sisyphus": {
+      "prompt": "file:///path/to/custom-prompt.md"
+    },
+    "oracle": {
+      "prompt_append": "file:///path/to/additional-context.md"
+    }
+  },
+  "categories": {
+    "deep": {
+      "prompt_append": "file:///path/to/deep-category-append.md"
+    }
+  }
+}
+```
+
+Supports `~` expansion for home directory and relative `file://` paths.
+
+Useful for:
+- Version controlling prompts separately from config
+- Sharing prompts across projects
+- Keeping configuration files concise
+- Adding category-specific context without duplicating base prompts
+
+The file content is loaded at runtime and injected into the agent's system prompt.
+
+### Session Recovery
+
+The system automatically recovers from common session failures without user intervention:
+
+- **Missing tool results**: reconstructs recoverable tool state and skips invalid tool-part IDs instead of failing the whole recovery pass
+- **Thinking block violations**: Recovers from API thinking block mismatches
+- **Empty messages**: Reconstructs message history when content is missing
+- **Context window limits**: Gracefully handles Claude context window exceeded errors with intelligent compaction
+- **JSON parse errors**: Recovers from malformed tool outputs
+
+Recovery happens transparently during agent execution. You see the result, not the failure.
 ## Skills
 
 Skills provide specialized workflows with embedded MCP servers and detailed instructions. A Skill is a mechanism that injects **specialized knowledge (Context)** and **tools (MCP)** for specific domains into agents.
@@ -237,7 +308,7 @@ Skills provide specialized workflows with embedded MCP servers and detailed inst
 
 ### Browser Automation Options
 
-Oh-My-OpenCode provides two browser automation providers, configurable via `browser_automation_engine.provider`.
+Oh-My-OpenAgent provides two browser automation providers, configurable via `browser_automation_engine.provider`.
 
 #### Option 1: Playwright MCP (Default)
 
@@ -558,7 +629,7 @@ Requires `experimental.task_system: true` in config.
 
 #### Task System Details
 
-**Note on Claude Code Alignment**: This implementation follows Claude Code's internal Task tool signatures (`TaskCreate`, `TaskUpdate`, `TaskList`, `TaskGet`) and field naming conventions (`subject`, `blockedBy`, `blocks`, etc.). However, Anthropic has not published official documentation for these tools. This is Oh My OpenCode's own implementation based on observed Claude Code behavior and internal specifications.
+**Note on Claude Code Alignment**: This implementation follows Claude Code's internal Task tool signatures (`TaskCreate`, `TaskUpdate`, `TaskList`, `TaskGet`) and field naming conventions (`subject`, `blockedBy`, `blocks`, etc.). However, Anthropic has not published official documentation for these tools. This is Oh My OpenAgent's own implementation based on observed Claude Code behavior and internal specifications.
 
 **Task Schema**:
 
@@ -680,7 +751,6 @@ Hooks intercept and modify behavior at key points in the agent lifecycle across
 | **ralph-loop**              | Event + Message     | Manages self-referential loop continuation.                                                                                                                 |
 | **start-work**              | Message             | Handles /start-work command execution.                                                                                                                      |
 | **auto-slash-command**      | Message             | Automatically executes slash commands from prompts.                                                                                                         |
-| **gpt-permission-continuation** | Event           | Auto-continues GPT sessions when the final assistant reply ends with a permission-seeking tail such as `If you want, ...`.                               |
 | **stop-continuation-guard** | Event + Message     | Guards the stop-continuation mechanism.                                                                                                                     |
 | **category-skill-reminder** | Event + PostToolUse | Reminds agents about available category skills for delegation.                                                                                              |
 | **anthropic-effort**        | Params              | Adjusts Anthropic API effort level based on context.                                                                                                        |
@@ -735,7 +805,6 @@ Hooks intercept and modify behavior at key points in the agent lifecycle across
 
 | Hook                           | Event | Description                                                |
 | ------------------------------ | ----- | ---------------------------------------------------------- |
-| **gpt-permission-continuation** | Event | Continues GPT replies that end in a permission-seeking tail. |
 | **todo-continuation-enforcer** | Event | Enforces todo completion — yanks idle agents back to work. |
 | **compaction-todo-preserver**  | Event | Preserves todo state during session compaction.            |
 | **unstable-agent-babysitter**  | Event | Handles unstable agent behavior with recovery strategies.  |
@@ -787,12 +856,10 @@ Disable specific hooks in config:
 
 ```json
 {
-  "disabled_hooks": ["comment-checker", "gpt-permission-continuation"]
+  "disabled_hooks": ["comment-checker"]
 }
 ```
 
-Use `gpt-permission-continuation` when you want GPT sessions to stop at permission-seeking endings instead of auto-resuming.
-
 ## MCPs
 
 ### Built-in MCPs
@@ -851,6 +918,38 @@ Pre-authenticate via CLI:
 bunx oh-my-opencode mcp oauth login <server-name> --server-url https://api.example.com
 ```
 
+## Model Capabilities
+
+Model capabilities are models.dev-backed, with a refreshable cache and compatibility diagnostics. The system combines bundled models.dev snapshot data, optional refreshed cache data, provider runtime metadata, and heuristics when exact metadata is unavailable.
+
+### Refreshing Capabilities
+
+Update the local cache with the latest model information:
+
+```bash
+bunx oh-my-opencode refresh-model-capabilities
+```
+
+Configure automatic refresh at startup:
+
+```jsonc
+{
+  "model_capabilities": {
+    "enabled": true,
+    "auto_refresh_on_start": true,
+    "refresh_timeout_ms": 5000,
+    "source_url": "https://models.dev/api.json"
+  }
+}
+```
+
+### Capability Diagnostics
+
+Run `bunx oh-my-opencode doctor` to see capability diagnostics including:
+- effective model resolution for agents and categories
+- warnings when configured models rely on compatibility fallback
+- override compatibility details alongside model resolution output
+
 ## Context Injection
 
 ### Directory AGENTS.md

docs/superpowers/plans/2026-03-17-model-settings-compatibility-resolver.md

@@ -0,0 +1,86 @@
+# Model Settings Compatibility Resolver Implementation Plan
+
+> **For agentic workers:** REQUIRED: Use superpowers:subagent-driven-development (if subagents available) or superpowers:executing-plans to implement this plan. Steps use checkbox (`- [ ]`) syntax for tracking.
+
+**Goal:** Centralize compatibility handling for `variant` and `reasoningEffort` so an already-selected model receives the best valid settings for that exact model.
+
+**Architecture:** Introduce a pure shared resolver in `src/shared/` that computes compatible settings and records downgrades/removals. Integrate it first in `chat.params`, then keep Claude-specific effort logic as a thin layer rather than a special-case policy owner.
+
+**Tech Stack:** TypeScript, Bun test, existing shared model normalization/utilities, OpenCode plugin `chat.params` path.
+
+---
+
+### Task 1: Create the pure compatibility resolver
+
+**Files:**
+- Create: `src/shared/model-settings-compatibility.ts`
+- Create: `src/shared/model-settings-compatibility.test.ts`
+- Modify: `src/shared/index.ts`
+
+- [ ] **Step 1: Write failing tests for exact keep behavior**
+- [ ] **Step 2: Write failing tests for downgrade behavior (`max` -> `high`, `xhigh` -> `high` where needed)**
+- [ ] **Step 3: Write failing tests for unsupported-value removal**
+- [ ] **Step 4: Write failing tests for model-family distinctions (Opus vs Sonnet/Haiku, GPT-family variants)**
+- [ ] **Step 5: Implement the pure resolver with explicit capability ladders**
+- [ ] **Step 6: Export the resolver from `src/shared/index.ts`**
+- [ ] **Step 7: Run `bun test src/shared/model-settings-compatibility.test.ts`**
+- [ ] **Step 8: Commit**
+
+### Task 2: Integrate resolver into chat.params
+
+**Files:**
+- Modify: `src/plugin/chat-params.ts`
+- Modify: `src/plugin/chat-params.test.ts`
+
+- [ ] **Step 1: Write failing tests showing `chat.params` applies resolver output to runtime settings**
+- [ ] **Step 2: Ensure tests cover both `variant` and `reasoningEffort` decisions**
+- [ ] **Step 3: Update `chat-params.ts` to call the shared resolver before hook-specific adjustments**
+- [ ] **Step 4: Preserve existing prompt-param-store merging behavior**
+- [ ] **Step 5: Run `bun test src/plugin/chat-params.test.ts`**
+- [ ] **Step 6: Commit**
+
+### Task 3: Re-scope anthropic-effort around the resolver
+
+**Files:**
+- Modify: `src/hooks/anthropic-effort/hook.ts`
+- Modify: `src/hooks/anthropic-effort/index.test.ts`
+
+- [ ] **Step 1: Write failing tests that codify the intended remaining Anthropic-specific behavior after centralization**
+- [ ] **Step 2: Reduce `anthropic-effort` to Claude/Anthropic-specific effort injection where still needed**
+- [ ] **Step 3: Remove duplicated compatibility policy from the hook if the shared resolver now owns it**
+- [ ] **Step 4: Run `bun test src/hooks/anthropic-effort/index.test.ts`**
+- [ ] **Step 5: Commit**
+
+### Task 4: Add integration/regression coverage across real request paths
+
+**Files:**
+- Modify: `src/plugin/chat-params.test.ts`
+- Modify: `src/hooks/anthropic-effort/index.test.ts`
+- Add tests only where needed in nearby suites
+
+- [ ] **Step 1: Add regression test for non-Opus Claude with `variant=max` resolving to compatible settings without ad hoc path-only logic**
+- [ ] **Step 2: Add regression test for GPT-style `reasoningEffort` compatibility**
+- [ ] **Step 3: Add regression test showing supported values remain unchanged**
+- [ ] **Step 4: Run the focused test set**
+- [ ] **Step 5: Commit**
+
+### Task 5: Verify full quality bar
+
+**Files:**
+- No intended code changes
+
+- [ ] **Step 1: Run `bun run typecheck`**
+- [ ] **Step 2: Run a focused suite for the touched files**
+- [ ] **Step 3: If clean, run `bun test`**
+- [ ] **Step 4: Review diff for accidental scope creep**
+- [ ] **Step 5: Commit any final cleanup**
+
+### Task 6: Prepare PR metadata
+
+**Files:**
+- No repo file change required unless docs are updated further
+
+- [ ] **Step 1: Write a human summary explaining this is settings compatibility, not model fallback**
+- [ ] **Step 2: Document scope: Phase 1 covers `variant` and `reasoningEffort` only**
+- [ ] **Step 3: Document explicit non-goals: no model switching, no automatic upscaling in Phase 1**
+- [ ] **Step 4: Request review**

docs/superpowers/specs/2026-03-17-model-settings-compatibility-design.md

@@ -0,0 +1,164 @@
+# Model Settings Compatibility Resolver Design
+
+## Goal
+
+Introduce a central resolver that takes an already-selected model and a set of desired model settings, then returns the best compatible configuration for that exact model.
+
+This is explicitly separate from model fallback.
+
+## Problem
+
+Today, logic for `variant` and `reasoningEffort` compatibility is scattered across multiple places:
+- `hooks/anthropic-effort`
+- `plugin/chat-params`
+- agent/category/fallback config layers
+- delegate/background prompt plumbing
+
+That creates inconsistent behavior:
+- some paths clamp unsupported levels
+- some paths pass them through unchanged
+- some paths silently drop them
+- some paths use model-family-specific assumptions that do not generalize
+
+The result is brittle request behavior even when the chosen model itself is valid.
+
+## Scope
+
+Phase 1 covers only:
+- `variant`
+- `reasoningEffort`
+
+Out of scope for Phase 1:
+- model fallback itself
+- `thinking`
+- `maxTokens`
+- `temperature`
+- `top_p`
+- automatic upward remapping of settings
+
+## Desired behavior
+
+Given a fixed model and desired settings:
+1. If a desired value is supported, keep it.
+2. If not supported, downgrade to the nearest lower compatible value.
+3. If no compatible value exists, drop the field.
+4. Do not switch models.
+5. Do not automatically upgrade settings in Phase 1.
+
+## Architecture
+
+Add a central module:
+- `src/shared/model-settings-compatibility.ts`
+
+Core API:
+
+```ts
+type DesiredModelSettings = {
+  variant?: string
+  reasoningEffort?: string
+}
+
+type ModelSettingsCompatibilityInput = {
+  providerID: string
+  modelID: string
+  desired: DesiredModelSettings
+}
+
+type ModelSettingsCompatibilityChange = {
+  field: "variant" | "reasoningEffort"
+  from: string
+  to?: string
+  reason: string
+}
+
+type ModelSettingsCompatibilityResult = {
+  variant?: string
+  reasoningEffort?: string
+  changes: ModelSettingsCompatibilityChange[]
+}
+```
+
+## Compatibility model
+
+Phase 1 should be **metadata-first where the platform exposes reliable capability data**, and only fall back to family-based rules when that metadata is absent.
+
+### Variant compatibility
+
+Preferred source of truth:
+- OpenCode/provider model metadata (`variants`)
+
+Fallback when metadata is unavailable:
+- family-based ladders
+
+Examples of fallback ladders:
+- Claude Opus family: `low`, `medium`, `high`, `max`
+- Claude Sonnet/Haiku family: `low`, `medium`, `high`
+- OpenAI GPT family: conservative family fallback only when metadata is missing
+- Unknown family: drop unsupported values conservatively
+
+### Reasoning effort compatibility
+
+Current Phase 1 source of truth:
+- conservative model/provider family heuristics
+
+Reason:
+- the currently available OpenCode SDK/provider metadata exposes model `variants`, but does not expose an equivalent per-model capability list for `reasoningEffort` levels
+
+Examples:
+- GPT/OpenAI-style models: `low`, `medium`, `high`, `xhigh` where supported by family heuristics
+- Claude family via current OpenCode path: treat `reasoningEffort` as unsupported in Phase 1 and remove it
+
+The resolver should remain pure model/settings logic only. Transport restrictions remain the responsibility of the request-building path.
+
+## Separation of concerns
+
+This design intentionally separates:
+- model selection (`resolveModel...`, fallback chains)
+- settings compatibility (this resolver)
+- request transport compatibility (`chat.params`, prompt body constraints)
+
+That keeps responsibilities clear:
+- choose model first
+- normalize settings second
+- build request third
+
+## First integration point
+
+Phase 1 should first integrate into `chat.params`.
+
+Why:
+- it is already the centralized path for request-time tuning
+- it can influence provider-facing options without leaking unsupported fields into prompt payload bodies
+- it avoids trying to patch every prompt constructor at once
+
+## Rollout plan
+
+### Phase 1
+- add resolver module and tests
+- integrate into `chat.params`
+- migrate `anthropic-effort` to either use the resolver or become a thin Claude-specific supplement around it
+
+### Phase 2
+- expand to `thinking`, `maxTokens`, `temperature`, `top_p`
+- formalize request-path capability tables if needed
+
+### Phase 3
+- centralize all variant/reasoning normalization away from scattered hooks and ad hoc callers
+
+## Risks
+
+- Overfitting family rules to current model naming conventions
+- Accidentally changing request semantics on paths that currently rely on implicit behavior
+- Mixing provider transport limitations with model capability logic
+
+## Mitigations
+
+- Keep resolver pure and narrowly scoped in Phase 1
+- Add explicit regression tests for keep/downgrade/drop decisions
+- Integrate at one central point first (`chat.params`)
+- Preserve existing behavior where desired values are already valid
+
+## Recommendation
+
+Proceed with the central resolver as a new, isolated implementation in a dedicated branch/worktree.
+This is the clean long-term path and is more reviewable than continuing to add special-case clamps in hooks.

docs/troubleshooting/ollama.md

@@ -4,7 +4,7 @@
 
 ### Problem
 
-When using Ollama as a provider with oh-my-opencode agents, you may encounter:
+When using Ollama as a provider with oh-my-openagent agents, you may encounter:
 
 ```
 JSON Parse error: Unexpected EOF
@@ -26,7 +26,7 @@ Claude Code SDK expects a single JSON object, not multiple NDJSON lines, causing
 **Why this happens:**
 - **Ollama API**: Returns streaming responses as NDJSON by design
 - **Claude Code SDK**: Doesn't properly handle NDJSON responses for tool calls
-- **oh-my-opencode**: Passes through the SDK's behavior (can't fix at this layer)
+- **oh-my-openagent**: Passes through the SDK's behavior (can't fix at this layer)
 
 ## Solutions
 
@@ -114,7 +114,7 @@ curl -s http://localhost:11434/api/chat \
 
 ## Related Issues
 
-- **oh-my-opencode**: https://github.com/code-yeongyu/oh-my-openagent/issues/1124
+- **oh-my-openagent**: https://github.com/code-yeongyu/oh-my-openagent/issues/1124
 - **Ollama API Docs**: https://github.com/ollama/ollama/blob/main/docs/api.md
 
 ## Getting Help

package.json

@@ -1,6 +1,6 @@
 {
   "name": "oh-my-opencode",
-  "version": "3.11.0",
+  "version": "3.14.0",
   "description": "The Best AI Agent Harness - Batteries-Included OpenCode Plugin with Multi-Model Orchestration, Parallel Background Agents, and Crafted LSP/AST Tools",
   "main": "dist/index.js",
   "types": "dist/index.d.ts",
@@ -25,10 +25,12 @@
     "build:all": "bun run build && bun run build:binaries",
     "build:binaries": "bun run script/build-binaries.ts",
     "build:schema": "bun run script/build-schema.ts",
+    "build:model-capabilities": "bun run script/build-model-capabilities.ts",
     "clean": "rm -rf dist",
     "prepare": "bun run build",
     "postinstall": "node postinstall.mjs",
     "prepublishOnly": "bun run clean && bun run build",
+    "test:model-capabilities": "bun test src/shared/model-capability-aliases.test.ts src/shared/model-capability-guardrails.test.ts src/shared/model-capabilities.test.ts src/cli/doctor/checks/model-resolution.test.ts --bail",
     "typecheck": "tsc --noEmit",
     "test": "bun test"
   },
@@ -76,17 +78,17 @@
     "typescript": "^5.7.3"
   },
   "optionalDependencies": {
-    "oh-my-opencode-darwin-arm64": "3.11.0",
-    "oh-my-opencode-darwin-x64": "3.11.0",
-    "oh-my-opencode-darwin-x64-baseline": "3.11.0",
-    "oh-my-opencode-linux-arm64": "3.11.0",
-    "oh-my-opencode-linux-arm64-musl": "3.11.0",
-    "oh-my-opencode-linux-x64": "3.11.0",
-    "oh-my-opencode-linux-x64-baseline": "3.11.0",
-    "oh-my-opencode-linux-x64-musl": "3.11.0",
-    "oh-my-opencode-linux-x64-musl-baseline": "3.11.0",
-    "oh-my-opencode-windows-x64": "3.11.0",
-    "oh-my-opencode-windows-x64-baseline": "3.11.0"
+    "oh-my-opencode-darwin-arm64": "3.14.0",
+    "oh-my-opencode-darwin-x64": "3.14.0",
+    "oh-my-opencode-darwin-x64-baseline": "3.14.0",
+    "oh-my-opencode-linux-arm64": "3.14.0",
+    "oh-my-opencode-linux-arm64-musl": "3.14.0",
+    "oh-my-opencode-linux-x64": "3.14.0",
+    "oh-my-opencode-linux-x64-baseline": "3.14.0",
+    "oh-my-opencode-linux-x64-musl": "3.14.0",
+    "oh-my-opencode-linux-x64-musl-baseline": "3.14.0",
+    "oh-my-opencode-windows-x64": "3.14.0",
+    "oh-my-opencode-windows-x64-baseline": "3.14.0"
   },
   "overrides": {
     "@opencode-ai/sdk": "^1.2.24"

packages/darwin-arm64/package.json

@@ -1,6 +1,6 @@
 {
   "name": "oh-my-opencode-darwin-arm64",
-  "version": "3.11.0",
+  "version": "3.14.0",
   "description": "Platform-specific binary for oh-my-opencode (darwin-arm64)",
   "license": "MIT",
   "repository": {

packages/darwin-x64-baseline/package.json

@@ -1,6 +1,6 @@
 {
   "name": "oh-my-opencode-darwin-x64-baseline",
-  "version": "3.11.0",
+  "version": "3.14.0",
   "description": "Platform-specific binary for oh-my-opencode (darwin-x64-baseline, no AVX2)",
   "license": "MIT",
   "repository": {

packages/darwin-x64/package.json

@@ -1,6 +1,6 @@
 {
   "name": "oh-my-opencode-darwin-x64",
-  "version": "3.11.0",
+  "version": "3.14.0",
   "description": "Platform-specific binary for oh-my-opencode (darwin-x64)",
   "license": "MIT",
   "repository": {

packages/linux-arm64-musl/package.json

@@ -1,6 +1,6 @@
 {
   "name": "oh-my-opencode-linux-arm64-musl",
-  "version": "3.11.0",
+  "version": "3.14.0",
   "description": "Platform-specific binary for oh-my-opencode (linux-arm64-musl)",
   "license": "MIT",
   "repository": {

packages/linux-arm64/package.json

@@ -1,6 +1,6 @@
 {
   "name": "oh-my-opencode-linux-arm64",
-  "version": "3.11.0",
+  "version": "3.14.0",
   "description": "Platform-specific binary for oh-my-opencode (linux-arm64)",
   "license": "MIT",
   "repository": {

packages/linux-x64-baseline/package.json

@@ -1,6 +1,6 @@
 {
   "name": "oh-my-opencode-linux-x64-baseline",
-  "version": "3.11.0",
+  "version": "3.14.0",
   "description": "Platform-specific binary for oh-my-opencode (linux-x64-baseline, no AVX2)",
   "license": "MIT",
   "repository": {

packages/linux-x64-musl-baseline/package.json

@@ -1,6 +1,6 @@
 {
   "name": "oh-my-opencode-linux-x64-musl-baseline",
-  "version": "3.11.0",
+  "version": "3.14.0",
   "description": "Platform-specific binary for oh-my-opencode (linux-x64-musl-baseline, no AVX2)",
   "license": "MIT",
   "repository": {

packages/linux-x64-musl/package.json

@@ -1,6 +1,6 @@
 {
   "name": "oh-my-opencode-linux-x64-musl",
-  "version": "3.11.0",
+  "version": "3.14.0",
   "description": "Platform-specific binary for oh-my-opencode (linux-x64-musl)",
   "license": "MIT",
   "repository": {

packages/linux-x64/package.json

@@ -1,6 +1,6 @@
 {
   "name": "oh-my-opencode-linux-x64",
-  "version": "3.11.0",
+  "version": "3.14.0",
   "description": "Platform-specific binary for oh-my-opencode (linux-x64)",
   "license": "MIT",
   "repository": {

packages/windows-x64-baseline/package.json

@@ -1,6 +1,6 @@
 {
   "name": "oh-my-opencode-windows-x64-baseline",
-  "version": "3.11.0",
+  "version": "3.14.0",
   "description": "Platform-specific binary for oh-my-opencode (windows-x64-baseline, no AVX2)",
   "license": "MIT",
   "repository": {

packages/windows-x64/package.json

@@ -1,6 +1,6 @@
 {
   "name": "oh-my-opencode-windows-x64",
-  "version": "3.11.0",
+  "version": "3.14.0",
   "description": "Platform-specific binary for oh-my-opencode (windows-x64)",
   "license": "MIT",
   "repository": {

postinstall.mjs

@@ -1,6 +1,7 @@
 // postinstall.mjs
 // Runs after npm install to verify platform binary is available
 
+import { readFileSync } from "node:fs";
 import { createRequire } from "node:module";
 import { getPlatformPackageCandidates, getBinaryPath } from "./bin/platform.js";
 
@@ -22,15 +23,26 @@ function getLibcFamily() {
   }
 }
 
+function getPackageBaseName() {
+  try {
+    const packageJson = JSON.parse(readFileSync(new URL("./package.json", import.meta.url), "utf8"));
+    return packageJson.name || "oh-my-opencode";
+  } catch {
+    return "oh-my-opencode";
+  }
+}
+
 function main() {
   const { platform, arch } = process;
   const libcFamily = getLibcFamily();
+  const packageBaseName = getPackageBaseName();
   
   try {
     const packageCandidates = getPlatformPackageCandidates({
       platform,
       arch,
       libcFamily,
+      packageBaseName,
     });
 
     const resolvedPackage = packageCandidates.find((pkg) => {

script/build-binaries.ts

@@ -101,7 +101,9 @@ async function main() {
   console.log("\n✅ All platform binaries built successfully!\n");
 }
 
-main().catch((error) => {
-  console.error("Fatal error:", error);
-  process.exit(1);
-});
+if (import.meta.main) {
+  main().catch((error) => {
+    console.error("Fatal error:", error);
+    process.exit(1);
+  });
+}

script/build-model-capabilities.ts

@@ -0,0 +1,13 @@
+import { writeFileSync } from "fs"
+import { resolve } from "path"
+import {
+  fetchModelCapabilitiesSnapshot,
+  MODELS_DEV_SOURCE_URL,
+} from "../src/shared/model-capabilities-cache"
+
+const OUTPUT_PATH = resolve(import.meta.dir, "../src/generated/model-capabilities.generated.json")
+
+console.log(`Fetching model capabilities snapshot from ${MODELS_DEV_SOURCE_URL}...`)
+const snapshot = await fetchModelCapabilitiesSnapshot()
+writeFileSync(OUTPUT_PATH, `${JSON.stringify(snapshot, null, 2)}\n`)
+console.log(`Generated ${OUTPUT_PATH} with ${Object.keys(snapshot.models).length} models`)

script/generate-changelog.ts

@@ -34,6 +34,72 @@ async function generateChangelog(previousTag: string): Promise<string[]> {
   return notes
 }
 
+async function getChangedFiles(previousTag: string): Promise<string[]> {
+  try {
+    const diff = await $`git diff --name-only ${previousTag}..HEAD`.text()
+    return diff
+      .split("\n")
+      .map((line) => line.trim())
+      .filter(Boolean)
+  } catch {
+    return []
+  }
+}
+
+function touchesAnyPath(files: string[], candidates: string[]): boolean {
+  return files.some((file) => candidates.some((candidate) => file === candidate || file.startsWith(`${candidate}/`)))
+}
+
+function buildReleaseFraming(files: string[]): string[] {
+  const bullets: string[] = []
+
+  if (
+    touchesAnyPath(files, [
+      "src/index.ts",
+      "src/plugin-config.ts",
+      "bin/platform.js",
+      "postinstall.mjs",
+      "docs",
+    ])
+  ) {
+    bullets.push("Rename transition updates across package detection, plugin/config compatibility, and install surfaces.")
+  }
+
+  if (touchesAnyPath(files, ["src/tools/delegate-task", "src/plugin/tool-registry.ts"])) {
+    bullets.push("Task and tool behavior updates, including delegate-task contract and runtime registration behavior.")
+  }
+
+  if (
+    touchesAnyPath(files, [
+      "src/plugin/tool-registry.ts",
+      "src/plugin-handlers/agent-config-handler.ts",
+      "src/plugin-handlers/tool-config-handler.ts",
+      "src/hooks/tasks-todowrite-disabler",
+    ])
+  ) {
+    bullets.push("Task-system default behavior alignment so omitted configuration behaves consistently across runtime paths.")
+  }
+
+  if (touchesAnyPath(files, [".github/workflows", "docs/guide/installation.md", "postinstall.mjs"])) {
+    bullets.push("Install and publish workflow hardening, including safer release sequencing and package/install fixes.")
+  }
+
+  if (bullets.length === 0) {
+    return []
+  }
+
+  return [
+    "## Minor Compatibility and Stability Release",
+    "",
+    "This release carries compatibility-facing behavior changes and operational hardening. Read the summary below before upgrading or publishing.",
+    "",
+    ...bullets.map((bullet) => `- ${bullet}`),
+    "",
+    "## Commit Summary",
+    "",
+  ]
+}
+
 async function getContributors(previousTag: string): Promise<string[]> {
   const notes: string[] = []
 
@@ -78,9 +144,11 @@ async function main() {
     process.exit(0)
   }
 
+  const changedFiles = await getChangedFiles(previousTag)
   const changelog = await generateChangelog(previousTag)
   const contributors = await getContributors(previousTag)
-  const notes = [...changelog, ...contributors]
+  const framing = buildReleaseFraming(changedFiles)
+  const notes = [...framing, ...changelog, ...contributors]
 
   if (notes.length === 0) {
     console.log("No notable changes")

signatures/cla.json

@@ -2239,6 +2239,166 @@
       "created_at": "2026-03-17T20:42:42Z",
       "repoId": 1108837393,
       "pullRequestNo": 2656
+    },
+    {
+      "name": "walioo",
+      "id": 25835823,
+      "comment_id": 4087098221,
+      "created_at": "2026-03-19T02:13:02Z",
+      "repoId": 1108837393,
+      "pullRequestNo": 2688
+    },
+    {
+      "name": "trafgals",
+      "id": 6454757,
+      "comment_id": 4087725932,
+      "created_at": "2026-03-19T04:22:32Z",
+      "repoId": 1108837393,
+      "pullRequestNo": 2690
+    },
+    {
+      "name": "tonymfer",
+      "id": 66512584,
+      "comment_id": 4091847232,
+      "created_at": "2026-03-19T17:13:49Z",
+      "repoId": 1108837393,
+      "pullRequestNo": 2701
+    },
+    {
+      "name": "nguyentamdat",
+      "id": 16253213,
+      "comment_id": 4096267323,
+      "created_at": "2026-03-20T07:34:22Z",
+      "repoId": 1108837393,
+      "pullRequestNo": 2718
+    },
+    {
+      "name": "whackur",
+      "id": 26926041,
+      "comment_id": 4102330445,
+      "created_at": "2026-03-21T05:27:17Z",
+      "repoId": 1108837393,
+      "pullRequestNo": 2733
+    },
+    {
+      "name": "ndaemy",
+      "id": 18691542,
+      "comment_id": 4103008804,
+      "created_at": "2026-03-21T10:18:22Z",
+      "repoId": 1108837393,
+      "pullRequestNo": 2734
+    },
+    {
+      "name": "0xYiliu",
+      "id": 3838688,
+      "comment_id": 4104738337,
+      "created_at": "2026-03-21T22:59:33Z",
+      "repoId": 1108837393,
+      "pullRequestNo": 2738
+    },
+    {
+      "name": "hunghoang3011",
+      "id": 65234777,
+      "comment_id": 4107900881,
+      "created_at": "2026-03-23T04:28:20Z",
+      "repoId": 1108837393,
+      "pullRequestNo": 2758
+    },
+    {
+      "name": "anas-asghar4831",
+      "id": 110368394,
+      "comment_id": 4128950310,
+      "created_at": "2026-03-25T18:48:19Z",
+      "repoId": 1108837393,
+      "pullRequestNo": 2837
+    },
+    {
+      "name": "clansty",
+      "id": 18461360,
+      "comment_id": 4129934858,
+      "created_at": "2026-03-25T21:33:35Z",
+      "repoId": 1108837393,
+      "pullRequestNo": 2839
+    },
+    {
+      "name": "ventsislav-georgiev",
+      "id": 5616486,
+      "comment_id": 4130417794,
+      "created_at": "2026-03-25T23:11:32Z",
+      "repoId": 1108837393,
+      "pullRequestNo": 2840
+    },
+    {
+      "name": "kuitos",
+      "id": 5206843,
+      "comment_id": 4133207953,
+      "created_at": "2026-03-26T09:55:49Z",
+      "repoId": 1108837393,
+      "pullRequestNo": 2833
+    },
+    {
+      "name": "Jholly2008",
+      "id": 29773273,
+      "comment_id": 4139918265,
+      "created_at": "2026-03-27T03:37:00Z",
+      "repoId": 1108837393,
+      "pullRequestNo": 2871
+    },
+    {
+      "name": "WhiteGiverMa",
+      "id": 152406589,
+      "comment_id": 4140294245,
+      "created_at": "2026-03-27T05:26:37Z",
+      "repoId": 1108837393,
+      "pullRequestNo": 2877
+    },
+    {
+      "name": "codivedev",
+      "id": 249558739,
+      "comment_id": 4142164072,
+      "created_at": "2026-03-27T12:11:45Z",
+      "repoId": 1108837393,
+      "pullRequestNo": 2888
+    },
+    {
+      "name": "AlexDochioiu",
+      "id": 38853913,
+      "comment_id": 4147980685,
+      "created_at": "2026-03-28T12:20:42Z",
+      "repoId": 1108837393,
+      "pullRequestNo": 2916
+    },
+    {
+      "name": "ryandielhenn",
+      "id": 35785891,
+      "comment_id": 4148508024,
+      "created_at": "2026-03-28T17:46:50Z",
+      "repoId": 1108837393,
+      "pullRequestNo": 2919
+    },
+    {
+      "name": "lorenzo-dallamuta",
+      "id": 66994937,
+      "comment_id": 4148848505,
+      "created_at": "2026-03-28T21:30:15Z",
+      "repoId": 1108837393,
+      "pullRequestNo": 2925
+    },
+    {
+      "name": "quangtran88",
+      "id": 107824159,
+      "comment_id": 4149327240,
+      "created_at": "2026-03-29T03:21:39Z",
+      "repoId": 1108837393,
+      "pullRequestNo": 2929
+    },
+    {
+      "name": "HOYALIM",
+      "id": 166576253,
+      "comment_id": 4149626853,
+      "created_at": "2026-03-29T07:31:36Z",
+      "repoId": 1108837393,
+      "pullRequestNo": 2935
     }
   ]
 }

src/AGENTS.md

@@ -14,7 +14,7 @@ Entry point `index.ts` orchestrates 5-step initialization: loadConfig → create
 | `plugin-config.ts` | JSONC parse, multi-level merge, Zod v4 validation |
 | `create-managers.ts` | TmuxSessionManager, BackgroundManager, SkillMcpManager, ConfigHandler |
 | `create-tools.ts` | SkillContext + AvailableCategories + ToolRegistry (26 tools) |
-| `create-hooks.ts` | 3-tier: Core(37) + Continuation(7) + Skill(2) = 46 hooks |
+| `create-hooks.ts` | 3-tier: Core(39) + Continuation(7) + Skill(2) = 48 hooks |
 | `plugin-interface.ts` | 8 OpenCode hook handlers: config, tool, chat.message, chat.params, chat.headers, event, tool.execute.before, tool.execute.after |
 
 ## CONFIG LOADING
@@ -32,10 +32,10 @@ loadPluginConfig(directory, ctx)
 
 ```
 createHooks()
-  ├─→ createCoreHooks()           # 37 hooks
+  ├─→ createCoreHooks()           # 39 hooks
   │   ├─ createSessionHooks()     # 23: contextWindowMonitor, thinkMode, ralphLoop, modelFallback, runtimeFallback, noSisyphusGpt, noHephaestusNonGpt, anthropicEffort, intentGate...
-  │   ├─ createToolGuardHooks()   # 10: commentChecker, rulesInjector, writeExistingFileGuard, jsonErrorRecovery, hashlineReadEnhancer...
+  │   ├─ createToolGuardHooks()   # 12: commentChecker, rulesInjector, writeExistingFileGuard, jsonErrorRecovery, hashlineReadEnhancer...
   │   └─ createTransformHooks()   # 4: claudeCodeHooks, keywordDetector, contextInjector, thinkingBlockValidator
-  ├─→ createContinuationHooks()   # 7: todoContinuationEnforcer, atlas, stopContinuationGuard, ralphLoopActivator...
+  ├─→ createContinuationHooks()   # 7: todoContinuationEnforcer, atlas, stopContinuationGuard, compactionContextInjector...
   └─→ createSkillHooks()          # 2: categorySkillReminder, autoSlashCommand
 ```

src/agents/AGENTS.md

@@ -11,10 +11,10 @@ Agent factories following `createXXXAgent(model) → AgentConfig` pattern. Each
 | Agent | Model | Temp | Mode | Fallback Chain | Purpose |
 |-------|-------|------|------|----------------|---------|
 | **Sisyphus** | claude-opus-4-6 max | 0.1 | all | k2p5 → kimi-k2.5 → gpt-5.4 medium → glm-5 → big-pickle | Main orchestrator, plans + delegates |
-| **Hephaestus** | gpt-5.3-codex medium | 0.1 | all | gpt-5.4 medium (copilot) | Autonomous deep worker |
+| **Hephaestus** | gpt-5.4 medium | 0.1 | all | — | Autonomous deep worker |
 | **Oracle** | gpt-5.4 high | 0.1 | subagent | gemini-3.1-pro high → claude-opus-4-6 max | Read-only consultation |
-| **Librarian** | gemini-3-flash | 0.1 | subagent | minimax-m2.5-free → big-pickle | External docs/code search |
-| **Explore** | grok-code-fast-1 | 0.1 | subagent | minimax-m2.5-free → claude-haiku-4-5 → gpt-5-nano | Contextual grep |
+| **Librarian** | minimax-m2.7 | 0.1 | subagent | minimax-m2.7-highspeed → claude-haiku-4-5 → gpt-5-nano | External docs/code search |
+| **Explore** | grok-code-fast-1 | 0.1 | subagent | minimax-m2.7-highspeed → minimax-m2.7 → claude-haiku-4-5 → gpt-5-nano | Contextual grep |
 | **Multimodal-Looker** | gpt-5.3-codex medium | 0.1 | subagent | k2p5 → gemini-3-flash → glm-4.6v → gpt-5-nano | PDF/image analysis |
 | **Metis** | claude-opus-4-6 max | **0.3** | subagent | gpt-5.4 high → gemini-3.1-pro high | Pre-planning consultant |
 | **Momus** | gpt-5.4 xhigh | 0.1 | subagent | claude-opus-4-6 max → gemini-3.1-pro high | Plan reviewer |

src/agents/builtin-agents/agent-overrides.ts

@@ -44,6 +44,10 @@ export function mergeAgentConfig(
   const { prompt_append, ...rest } = migratedOverride
   const merged = deepMerge(base, rest as Partial<AgentConfig>)
 
+  if (merged.prompt && typeof merged.prompt === 'string' && merged.prompt.startsWith('file://')) {
+    merged.prompt = resolvePromptAppend(merged.prompt, directory)
+  }
+
   if (prompt_append && merged.prompt) {
     merged.prompt = merged.prompt + "\n" + resolvePromptAppend(prompt_append, directory)
   }

src/agents/builtin-agents/atlas-agent.ts

@@ -39,7 +39,7 @@ export function maybeCreateAtlasConfig(input: {
   const atlasRequirement = AGENT_MODEL_REQUIREMENTS["atlas"]
 
   const atlasResolution = applyModelResolution({
-    uiSelectedModel: orchestratorOverride?.model ? undefined : uiSelectedModel,
+    uiSelectedModel: orchestratorOverride?.model !== undefined ? undefined : uiSelectedModel,
     userModel: orchestratorOverride?.model,
     requirement: atlasRequirement,
     availableModels,

src/agents/builtin-agents/general-agents.ts

@@ -8,6 +8,7 @@ import { buildAgent, isFactory } from "../agent-builder"
 import { applyOverrides } from "./agent-overrides"
 import { applyEnvironmentContext } from "./environment-context"
 import { applyModelResolution, getFirstFallbackModel } from "./model-resolution"
+import { log } from "../../shared/logger"
 
 export function collectPendingBuiltinAgents(input: {
   agentSources: Record<BuiltinAgentName, import("../agent-builder").AgentSource>
@@ -69,14 +70,24 @@ export function collectPendingBuiltinAgents(input: {
     const isPrimaryAgent = isFactory(source) && source.mode === "primary"
 
     let resolution = applyModelResolution({
-      uiSelectedModel: (isPrimaryAgent && !override?.model) ? uiSelectedModel : undefined,
+      uiSelectedModel: (isPrimaryAgent && override?.model === undefined) ? uiSelectedModel : undefined,
       userModel: override?.model,
       requirement,
       availableModels,
       systemDefaultModel,
     })
-    if (!resolution && isFirstRunNoCache && !override?.model) {
-      resolution = getFirstFallbackModel(requirement)
+    if (!resolution) {
+      if (override?.model) {
+        // User explicitly configured a model but resolution failed (e.g., cold cache).
+        // Honor the user's choice directly instead of falling back to hardcoded chain.
+        log("[agent-registration] User-configured model not resolved, using as-is", {
+          agent: agentName,
+          configuredModel: override.model,
+        })
+        resolution = { model: override.model, provenance: "override" as const }
+      } else {
+        resolution = getFirstFallbackModel(requirement)
+      }
     }
     if (!resolution) continue
     const { model, variant: resolvedVariant } = resolution

src/agents/builtin-agents/sisyphus-agent.ts

@@ -52,7 +52,7 @@ export function maybeCreateSisyphusConfig(input: {
   if (disabledAgents.includes("sisyphus") || !meetsSisyphusAnyModelRequirement) return undefined
 
   let sisyphusResolution = applyModelResolution({
-    uiSelectedModel: sisyphusOverride?.model ? undefined : uiSelectedModel,
+    uiSelectedModel: sisyphusOverride?.model !== undefined ? undefined : uiSelectedModel,
     userModel: sisyphusOverride?.model,
     requirement: sisyphusRequirement,
     availableModels,

src/agents/dynamic-agent-prompt-builder.test.ts

@@ -181,7 +181,7 @@ describe("buildParallelDelegationSection", () => {
 
   it("#given non-Claude model with deep category #when building #then returns aggressive delegation section", () => {
     //#given
-    const model = "google/gemini-3-pro"
+    const model = "google/gemini-3.1-pro"
     const categories = [deepCategory, otherCategory]
 
     //#when
@@ -237,7 +237,7 @@ describe("buildParallelDelegationSection", () => {
 describe("buildNonClaudePlannerSection", () => {
   it("#given non-Claude model #when building #then returns plan agent section", () => {
     //#given
-    const model = "google/gemini-3-pro"
+    const model = "google/gemini-3.1-pro"
 
     //#when
     const result = buildNonClaudePlannerSection(model)
@@ -272,4 +272,3 @@ describe("buildNonClaudePlannerSection", () => {
   })
 })
 
-

src/agents/dynamic-agent-prompt-builder.ts

@@ -308,6 +308,12 @@ Briefly announce "Consulting Oracle for [reason]" before invocation.
 
 **Collect Oracle results before your final answer. No exceptions.**
 
+**Oracle-dependent implementation is BLOCKED until Oracle finishes.**
+
+- If you asked Oracle for architecture/debugging direction that affects the fix, do not implement before Oracle result arrives.
+- While waiting, only do non-overlapping prep work. Never ship implementation decisions Oracle was asked to decide.
+- Never "time out and continue anyway" for Oracle-dependent tasks.
+
 - Oracle takes minutes. When done with your own work: **end your response** — wait for the \`<system-reminder>\`.
 - Do NOT poll \`background_output\` on a running Oracle. The notification will come.
 - Never cancel Oracle.

src/agents/hephaestus/gpt-5-3-codex.ts

@@ -162,6 +162,10 @@ Asking the user is the LAST resort after exhausting creative alternatives.
 - User asks a question implying work → Answer briefly, DO the implied work in the same turn
 - You wrote a plan in your response → EXECUTE the plan before ending turn — plans are starting lines, not finish lines
 
+### Task Scope Clarification
+
+You handle multi-step sub-tasks of a SINGLE GOAL. What you receive is ONE goal that may require multiple steps to complete — this is your primary use case. Only reject when given MULTIPLE INDEPENDENT goals in one request.
+
 ## Hard Constraints
 
 ${hardBlocks}

src/agents/hephaestus/gpt-5-4.ts

@@ -121,6 +121,10 @@ When blocked: try a different approach → decompose the problem → challenge a
 - User asks a question implying work → Answer briefly, DO the implied work in the same turn
 - You wrote a plan in your response → EXECUTE the plan before ending turn — plans are starting lines, not finish lines
 
+### Task Scope Clarification
+
+You handle multi-step sub-tasks of a SINGLE GOAL. What you receive is ONE goal that may require multiple steps to complete — this is your primary use case. Only reject when given MULTIPLE INDEPENDENT goals in one request.
+
 ## Hard Constraints
 
 ${hardBlocks}

src/agents/hephaestus/gpt.ts

@@ -112,6 +112,10 @@ Asking the user is the LAST resort after exhausting creative alternatives.
 - Note assumptions in final message, not as questions mid-work
 - Need context? Fire explore/librarian in background IMMEDIATELY — continue only with non-overlapping work while they search
 
+### Task Scope Clarification
+
+You handle multi-step sub-tasks of a SINGLE GOAL. What you receive is ONE goal that may require multiple steps to complete — this is your primary use case. Only reject when given MULTIPLE INDEPENDENT goals in one request.
+
 ## Hard Constraints
 
 ${hardBlocks}

src/agents/prometheus/system-prompt.test.ts

@@ -0,0 +1,42 @@
+import { describe, it, expect } from "bun:test"
+import { getPrometheusPrompt } from "./system-prompt"
+
+describe("getPrometheusPrompt", () => {
+  describe("#given question tool is not disabled", () => {
+    describe("#when generating prompt", () => {
+      it("#then should include Question tool references", () => {
+        const prompt = getPrometheusPrompt(undefined, [])
+
+        expect(prompt).toContain("Question({")
+      })
+    })
+  })
+
+  describe("#given question tool is disabled via disabled_tools", () => {
+    describe("#when generating prompt", () => {
+      it("#then should strip Question tool code examples", () => {
+        const prompt = getPrometheusPrompt(undefined, ["question"])
+
+        expect(prompt).not.toContain("Question({")
+      })
+    })
+
+    describe("#when disabled_tools includes question among other tools", () => {
+      it("#then should strip Question tool code examples", () => {
+        const prompt = getPrometheusPrompt(undefined, ["todowrite", "question", "interactive_bash"])
+
+        expect(prompt).not.toContain("Question({")
+      })
+    })
+  })
+
+  describe("#given no disabled_tools provided", () => {
+    describe("#when generating prompt with undefined", () => {
+      it("#then should include Question tool references", () => {
+        const prompt = getPrometheusPrompt(undefined, undefined)
+
+        expect(prompt).toContain("Question({")
+      })
+    })
+  })
+})

src/agents/prometheus/system-prompt.ts

@@ -52,16 +52,34 @@ export function getPrometheusPromptSource(model?: string): PrometheusPromptSourc
  * Gemini models → Gemini-optimized prompt (aggressive tool-call enforcement, thinking checkpoints)
  * Default (Claude, etc.) → Claude-optimized prompt (modular sections)
  */
-export function getPrometheusPrompt(model?: string): string {
+export function getPrometheusPrompt(model?: string, disabledTools?: readonly string[]): string {
   const source = getPrometheusPromptSource(model)
+  const isQuestionDisabled = disabledTools?.includes("question") ?? false
 
+  let prompt: string
   switch (source) {
     case "gpt":
-      return getGptPrometheusPrompt()
+      prompt = getGptPrometheusPrompt()
+      break
     case "gemini":
-      return getGeminiPrometheusPrompt()
+      prompt = getGeminiPrometheusPrompt()
+      break
     case "default":
     default:
-      return PROMETHEUS_SYSTEM_PROMPT
+      prompt = PROMETHEUS_SYSTEM_PROMPT
   }
+
+  if (isQuestionDisabled) {
+    prompt = stripQuestionToolReferences(prompt)
+  }
+
+  return prompt
+}
+
+/**
+ * Removes Question tool usage examples from prompt text when question tool is disabled.
+ */
+function stripQuestionToolReferences(prompt: string): string {
+  // Remove Question({...}) code blocks (multi-line)
+  return prompt.replace(/```typescript\n\s*Question\(\{[\s\S]*?\}\)\s*\n```/g, "")
 }

src/agents/sisyphus-junior/default.ts

@@ -35,6 +35,11 @@ Task NOT complete without:
 - ${verificationText}
 </Verification>
 
+<Termination>
+STOP after first successful verification. Do NOT re-verify.
+Maximum status checks: 2. Then stop regardless.
+</Termination>
+
 <Style>
 - Start immediately. No acknowledgments.
 - Match user's communication style.

src/agents/sisyphus.ts

@@ -127,6 +127,12 @@ This verbalization anchors your routing decision and makes your reasoning transp
 - **Open-ended** ("Improve", "Refactor", "Add feature") → Assess codebase first
 - **Ambiguous** (unclear scope, multiple interpretations) → Ask ONE clarifying question
 
+### Step 1.5: Turn-Local Intent Reset (MANDATORY)
+
+- Reclassify intent from the CURRENT user message only. Never auto-carry "implementation mode" from prior turns.
+- If current message is a question/explanation/investigation request, answer/analyze only. Do NOT create todos or edit files.
+- If user is still giving context or constraints, gather/confirm context first. Do NOT start implementation yet.
+
 ### Step 2: Check for Ambiguity
 
 - Single valid interpretation → Proceed
@@ -135,6 +141,15 @@ This verbalization anchors your routing decision and makes your reasoning transp
 - Missing critical info (file, error, context) → **MUST ask**
 - User's design seems flawed or suboptimal → **MUST raise concern** before implementing
 
+### Step 2.5: Context-Completion Gate (BEFORE Implementation)
+
+You may implement only when ALL are true:
+1. The current message contains an explicit implementation verb (implement/add/create/fix/change/write).
+2. Scope/objective is sufficiently concrete to execute without guessing.
+3. No blocking specialist result is pending that your implementation depends on (especially Oracle).
+
+If any condition fails, do research/clarification only, then wait.
+
 ### Step 3: Validate Before Acting
 
 **Assumptions Check:**

src/agents/sisyphus/gpt-5-4.ts

@@ -167,6 +167,11 @@ Complexity:
 - Open-ended ("improve", "refactor") → assess codebase first, then propose
 - Ambiguous (multiple interpretations with 2x+ effort difference) → ask ONE question
 
+Turn-local reset (mandatory): classify from the CURRENT user message, not conversation momentum.
+- Never carry implementation mode from prior turns.
+- If current turn is question/explanation/investigation, answer or analyze only.
+- If user appears to still be providing context, gather/confirm context first and wait.
+
 Domain guess (provisional — finalized in ROUTE after exploration):
 - Visual (UI, CSS, styling, layout, design, animation) → likely visual-engineering
 - Logic (algorithms, architecture, complex business logic) → likely ultrabrain
@@ -184,6 +189,11 @@ Step 2 — Check before acting:
 - Missing critical info → ask
 - User's design seems flawed → raise concern concisely, propose alternative, ask if they want to proceed anyway
 
+Context-completion gate before implementation:
+- Implement only when the current message explicitly requests implementation (implement/add/create/fix/change/write),
+  scope is concrete enough to execute without guessing, and no blocking specialist result is pending.
+- If any condition fails, continue with research/clarification only and wait.
+
 <ask_gate>
 Proceed unless:
 (a) the action is irreversible,

src/agents/types.test.ts

@@ -1,5 +1,5 @@
 import { describe, test, expect } from "bun:test";
-import { isGptModel, isGeminiModel, isGpt5_4Model } from "./types";
+import { isGptModel, isGeminiModel, isGpt5_4Model, isMiniMaxModel } from "./types";
 
 describe("isGpt5_4Model", () => {
   test("detects gpt-5.4 models", () => {
@@ -79,6 +79,28 @@ describe("isGptModel", () => {
   });
 });
 
+describe("isMiniMaxModel", () => {
+  test("detects minimax models with provider prefix", () => {
+    expect(isMiniMaxModel("opencode-go/minimax-m2.7")).toBe(true);
+    expect(isMiniMaxModel("opencode/minimax-m2.7-highspeed")).toBe(true);
+    expect(isMiniMaxModel("opencode-go/minimax-m2.5")).toBe(true);
+    expect(isMiniMaxModel("opencode/minimax-m2.5-free")).toBe(true);
+  });
+
+  test("detects minimax models without provider prefix", () => {
+    expect(isMiniMaxModel("minimax-m2.7")).toBe(true);
+    expect(isMiniMaxModel("minimax-m2.7-highspeed")).toBe(true);
+    expect(isMiniMaxModel("minimax-m2.5")).toBe(true);
+  });
+
+  test("does not match non-minimax models", () => {
+    expect(isMiniMaxModel("openai/gpt-5.4")).toBe(false);
+    expect(isMiniMaxModel("anthropic/claude-opus-4-6")).toBe(false);
+    expect(isMiniMaxModel("google/gemini-3.1-pro")).toBe(false);
+    expect(isMiniMaxModel("opencode-go/kimi-k2.5")).toBe(false);
+  });
+});
+
 describe("isGeminiModel", () => {
   test("#given google provider models #then returns true", () => {
     expect(isGeminiModel("google/gemini-3.1-pro")).toBe(true);

src/agents/types.ts

@@ -91,6 +91,11 @@ export function isGpt5_3CodexModel(model: string): boolean {
 
 const GEMINI_PROVIDERS = ["google/", "google-vertex/"];
 
+export function isMiniMaxModel(model: string): boolean {
+  const modelName = extractModelName(model).toLowerCase();
+  return modelName.includes("minimax");
+}
+
 export function isGeminiModel(model: string): boolean {
   if (GEMINI_PROVIDERS.some((prefix) => model.startsWith(prefix))) return true;
 
@@ -123,7 +128,7 @@ export type AgentName = BuiltinAgentName;
 export type AgentOverrideConfig = Partial<AgentConfig> & {
   prompt_append?: string;
   variant?: string;
-  fallback_models?: string | string[];
+  fallback_models?: string | (string | import("../config/schema/fallback-models").FallbackModelObject)[];
 };
 
 export type AgentOverrides = Partial<

src/agents/utils.test.ts

@@ -642,7 +642,7 @@ describe("createBuiltinAgents with requiresProvider gating (hephaestus)", () =>
 
       // #then
       expect(agents.hephaestus).toBeDefined()
-      expect(agents.hephaestus.model).toBe("openai/gpt-5.3-codex")
+      expect(agents.hephaestus.model).toBe("openai/gpt-5.4")
     } finally {
       cacheSpy.mockRestore()
       fetchSpy.mockRestore()

src/cli/__snapshots__/model-fallback.test.ts.snap

@@ -202,7 +202,7 @@ exports[`generateModelConfig single native provider uses OpenAI models when only
       "variant": "medium",
     },
     "hephaestus": {
-      "model": "openai/gpt-5.3-codex",
+      "model": "openai/gpt-5.4",
       "variant": "medium",
     },
     "librarian": {
@@ -248,8 +248,7 @@ exports[`generateModelConfig single native provider uses OpenAI models when only
       "variant": "medium",
     },
     "quick": {
-      "model": "openai/gpt-5.3-codex",
-      "variant": "low",
+      "model": "openai/gpt-5.4-mini",
     },
     "ultrabrain": {
       "model": "openai/gpt-5.4",
@@ -288,7 +287,7 @@ exports[`generateModelConfig single native provider uses OpenAI models with isMa
       "variant": "medium",
     },
     "hephaestus": {
-      "model": "openai/gpt-5.3-codex",
+      "model": "openai/gpt-5.4",
       "variant": "medium",
     },
     "librarian": {
@@ -334,8 +333,7 @@ exports[`generateModelConfig single native provider uses OpenAI models with isMa
       "variant": "medium",
     },
     "quick": {
-      "model": "openai/gpt-5.3-codex",
-      "variant": "low",
+      "model": "openai/gpt-5.4-mini",
     },
     "ultrabrain": {
       "model": "openai/gpt-5.4",
@@ -492,7 +490,7 @@ exports[`generateModelConfig all native providers uses preferred models from fal
       "model": "anthropic/claude-haiku-4-5",
     },
     "hephaestus": {
-      "model": "openai/gpt-5.3-codex",
+      "model": "openai/gpt-5.4",
       "variant": "medium",
     },
     "metis": {
@@ -533,7 +531,7 @@ exports[`generateModelConfig all native providers uses preferred models from fal
       "variant": "medium",
     },
     "quick": {
-      "model": "anthropic/claude-haiku-4-5",
+      "model": "openai/gpt-5.4-mini",
     },
     "ultrabrain": {
       "model": "openai/gpt-5.4",
@@ -567,7 +565,7 @@ exports[`generateModelConfig all native providers uses preferred models with isM
       "model": "anthropic/claude-haiku-4-5",
     },
     "hephaestus": {
-      "model": "openai/gpt-5.3-codex",
+      "model": "openai/gpt-5.4",
       "variant": "medium",
     },
     "metis": {
@@ -608,7 +606,7 @@ exports[`generateModelConfig all native providers uses preferred models with isM
       "variant": "medium",
     },
     "quick": {
-      "model": "anthropic/claude-haiku-4-5",
+      "model": "openai/gpt-5.4-mini",
     },
     "ultrabrain": {
       "model": "openai/gpt-5.4",
@@ -643,7 +641,7 @@ exports[`generateModelConfig fallback providers uses OpenCode Zen models when on
       "model": "opencode/claude-haiku-4-5",
     },
     "hephaestus": {
-      "model": "opencode/gpt-5.3-codex",
+      "model": "opencode/gpt-5.4",
       "variant": "medium",
     },
     "metis": {
@@ -684,7 +682,7 @@ exports[`generateModelConfig fallback providers uses OpenCode Zen models when on
       "variant": "medium",
     },
     "quick": {
-      "model": "opencode/claude-haiku-4-5",
+      "model": "opencode/gpt-5.4-mini",
     },
     "ultrabrain": {
       "model": "opencode/gpt-5.4",
@@ -718,7 +716,7 @@ exports[`generateModelConfig fallback providers uses OpenCode Zen models with is
       "model": "opencode/claude-haiku-4-5",
     },
     "hephaestus": {
-      "model": "opencode/gpt-5.3-codex",
+      "model": "opencode/gpt-5.4",
       "variant": "medium",
     },
     "metis": {
@@ -759,7 +757,7 @@ exports[`generateModelConfig fallback providers uses OpenCode Zen models with is
       "variant": "medium",
     },
     "quick": {
-      "model": "opencode/claude-haiku-4-5",
+      "model": "opencode/gpt-5.4-mini",
     },
     "ultrabrain": {
       "model": "opencode/gpt-5.4",
@@ -830,7 +828,7 @@ exports[`generateModelConfig fallback providers uses GitHub Copilot models when
       "variant": "high",
     },
     "quick": {
-      "model": "github-copilot/claude-haiku-4.5",
+      "model": "github-copilot/gpt-5.4-mini",
     },
     "ultrabrain": {
       "model": "github-copilot/gemini-3.1-pro-preview",
@@ -900,7 +898,7 @@ exports[`generateModelConfig fallback providers uses GitHub Copilot models with
       "variant": "high",
     },
     "quick": {
-      "model": "github-copilot/claude-haiku-4.5",
+      "model": "github-copilot/gpt-5.4-mini",
     },
     "ultrabrain": {
       "model": "github-copilot/gemini-3.1-pro-preview",
@@ -1051,7 +1049,7 @@ exports[`generateModelConfig mixed provider scenarios uses Claude + OpenCode Zen
       "model": "anthropic/claude-haiku-4-5",
     },
     "hephaestus": {
-      "model": "opencode/gpt-5.3-codex",
+      "model": "opencode/gpt-5.4",
       "variant": "medium",
     },
     "metis": {
@@ -1092,7 +1090,7 @@ exports[`generateModelConfig mixed provider scenarios uses Claude + OpenCode Zen
       "variant": "medium",
     },
     "quick": {
-      "model": "anthropic/claude-haiku-4-5",
+      "model": "opencode/gpt-5.4-mini",
     },
     "ultrabrain": {
       "model": "opencode/gpt-5.4",
@@ -1126,7 +1124,7 @@ exports[`generateModelConfig mixed provider scenarios uses OpenAI + Copilot comb
       "model": "github-copilot/gpt-5-mini",
     },
     "hephaestus": {
-      "model": "openai/gpt-5.3-codex",
+      "model": "openai/gpt-5.4",
       "variant": "medium",
     },
     "metis": {
@@ -1167,7 +1165,7 @@ exports[`generateModelConfig mixed provider scenarios uses OpenAI + Copilot comb
       "variant": "medium",
     },
     "quick": {
-      "model": "github-copilot/claude-haiku-4.5",
+      "model": "openai/gpt-5.4-mini",
     },
     "ultrabrain": {
       "model": "openai/gpt-5.4",
@@ -1331,7 +1329,7 @@ exports[`generateModelConfig mixed provider scenarios uses all fallback provider
       "model": "opencode/claude-haiku-4-5",
     },
     "hephaestus": {
-      "model": "opencode/gpt-5.3-codex",
+      "model": "github-copilot/gpt-5.4",
       "variant": "medium",
     },
     "librarian": {
@@ -1375,7 +1373,7 @@ exports[`generateModelConfig mixed provider scenarios uses all fallback provider
       "variant": "medium",
     },
     "quick": {
-      "model": "github-copilot/claude-haiku-4.5",
+      "model": "github-copilot/gpt-5.4-mini",
     },
     "ultrabrain": {
       "model": "opencode/gpt-5.4",
@@ -1409,7 +1407,7 @@ exports[`generateModelConfig mixed provider scenarios uses all providers togethe
       "model": "anthropic/claude-haiku-4-5",
     },
     "hephaestus": {
-      "model": "openai/gpt-5.3-codex",
+      "model": "openai/gpt-5.4",
       "variant": "medium",
     },
     "librarian": {
@@ -1453,7 +1451,7 @@ exports[`generateModelConfig mixed provider scenarios uses all providers togethe
       "variant": "medium",
     },
     "quick": {
-      "model": "anthropic/claude-haiku-4-5",
+      "model": "openai/gpt-5.4-mini",
     },
     "ultrabrain": {
       "model": "openai/gpt-5.4",
@@ -1487,7 +1485,7 @@ exports[`generateModelConfig mixed provider scenarios uses all providers with is
       "model": "anthropic/claude-haiku-4-5",
     },
     "hephaestus": {
-      "model": "openai/gpt-5.3-codex",
+      "model": "openai/gpt-5.4",
       "variant": "medium",
     },
     "librarian": {
@@ -1531,7 +1529,7 @@ exports[`generateModelConfig mixed provider scenarios uses all providers with is
       "variant": "medium",
     },
     "quick": {
-      "model": "anthropic/claude-haiku-4-5",
+      "model": "openai/gpt-5.4-mini",
     },
     "ultrabrain": {
       "model": "openai/gpt-5.4",

src/cli/cli-installer.ts

@@ -1,4 +1,5 @@
 import color from "picocolors"
+import { PLUGIN_NAME } from "../shared"
 import type { InstallArgs } from "./types"
 import {
   addPluginToOpenCodeConfig,
@@ -32,7 +33,7 @@ export async function runCliInstaller(args: InstallArgs, version: string): Promi
     }
     console.log()
     printInfo(
-      "Usage: bunx oh-my-opencode install --no-tui --claude=<no|yes|max20> --gemini=<no|yes> --copilot=<no|yes>",
+      `Usage: bunx ${PLUGIN_NAME} install --no-tui --claude=<no|yes|max20> --gemini=<no|yes> --copilot=<no|yes>`,
     )
     console.log()
     return 1
@@ -65,7 +66,7 @@ export async function runCliInstaller(args: InstallArgs, version: string): Promi
 
   const config = argsToConfig(args)
 
-  printStep(step++, totalSteps, "Adding oh-my-opencode plugin...")
+  printStep(step++, totalSteps, `Adding ${PLUGIN_NAME} plugin...`)
   const pluginResult = await addPluginToOpenCodeConfig(version)
   if (!pluginResult.success) {
     printError(`Failed: ${pluginResult.error}`)
@@ -75,7 +76,7 @@ export async function runCliInstaller(args: InstallArgs, version: string): Promi
     `Plugin ${isUpdate ? "verified" : "added"} ${SYMBOLS.arrow} ${color.dim(pluginResult.configPath)}`,
   )
 
-  printStep(step++, totalSteps, "Writing oh-my-opencode configuration...")
+  printStep(step++, totalSteps, `Writing ${PLUGIN_NAME} configuration...`)
   const omoResult = writeOmoConfig(config)
   if (!omoResult.success) {
     printError(`Failed: ${omoResult.error}`)

src/cli/cli-program.ts

@@ -3,6 +3,7 @@ import { install } from "./install"
 import { run } from "./run"
 import { getLocalVersion } from "./get-local-version"
 import { doctor } from "./doctor"
+import { refreshModelCapabilities } from "./refresh-model-capabilities"
 import { createMcpOAuthCommand } from "./mcp-oauth"
 import type { InstallArgs } from "./types"
 import type { RunOptions } from "./run"
@@ -42,7 +43,7 @@ Examples:
 Model Providers (Priority: Native > Copilot > OpenCode Zen > Z.ai > Kimi):
   Claude        Native anthropic/ models (Opus, Sonnet, Haiku)
   OpenAI        Native openai/ models (GPT-5.4 for Oracle)
-  Gemini        Native google/ models (Gemini 3 Pro, Flash)
+  Gemini        Native google/ models (Gemini 3.1 Pro, Flash)
   Copilot       github-copilot/ models (fallback)
   OpenCode Zen  opencode/ models (opencode/claude-opus-4-6, etc.)
    Z.ai          zai-coding-plan/glm-5 (visual-engineering fallback)
@@ -176,6 +177,21 @@ Examples:
     process.exit(exitCode)
   })
 
+program
+  .command("refresh-model-capabilities")
+  .description("Refresh the cached models.dev-based model capabilities snapshot")
+  .option("-d, --directory <path>", "Working directory to read oh-my-opencode config from")
+  .option("--source-url <url>", "Override the models.dev source URL")
+  .option("--json", "Output refresh summary as JSON")
+  .action(async (options) => {
+    const exitCode = await refreshModelCapabilities({
+      directory: options.directory,
+      sourceUrl: options.sourceUrl,
+      json: options.json ?? false,
+    })
+    process.exit(exitCode)
+  })
+
 program
   .command("version")
   .description("Show version information")

src/cli/config-manager.test.ts

@@ -1,300 +0,0 @@
-import { describe, expect, test, mock, afterEach } from "bun:test"
-
-import { getPluginNameWithVersion, fetchNpmDistTags, generateOmoConfig } from "./config-manager"
-import type { InstallConfig } from "./types"
-
-describe("getPluginNameWithVersion", () => {
-  const originalFetch = globalThis.fetch
-
-  afterEach(() => {
-    globalThis.fetch = originalFetch
-  })
-
-  test("returns @latest when current version matches latest tag", async () => {
-    // #given npm dist-tags with latest=2.14.0
-    globalThis.fetch = mock(() =>
-      Promise.resolve({
-        ok: true,
-        json: () => Promise.resolve({ latest: "2.14.0", beta: "3.0.0-beta.3" }),
-      } as Response)
-    ) as unknown as typeof fetch
-
-    // #when current version is 2.14.0
-    const result = await getPluginNameWithVersion("2.14.0")
-
-    // #then should use @latest tag
-    expect(result).toBe("oh-my-opencode@latest")
-  })
-
-  test("returns @beta when current version matches beta tag", async () => {
-    // #given npm dist-tags with beta=3.0.0-beta.3
-    globalThis.fetch = mock(() =>
-      Promise.resolve({
-        ok: true,
-        json: () => Promise.resolve({ latest: "2.14.0", beta: "3.0.0-beta.3" }),
-      } as Response)
-    ) as unknown as typeof fetch
-
-    // #when current version is 3.0.0-beta.3
-    const result = await getPluginNameWithVersion("3.0.0-beta.3")
-
-    // #then should use @beta tag
-    expect(result).toBe("oh-my-opencode@beta")
-  })
-
-  test("returns @next when current version matches next tag", async () => {
-    // #given npm dist-tags with next=3.1.0-next.1
-    globalThis.fetch = mock(() =>
-      Promise.resolve({
-        ok: true,
-        json: () => Promise.resolve({ latest: "2.14.0", beta: "3.0.0-beta.3", next: "3.1.0-next.1" }),
-      } as Response)
-    ) as unknown as typeof fetch
-
-    // #when current version is 3.1.0-next.1
-    const result = await getPluginNameWithVersion("3.1.0-next.1")
-
-    // #then should use @next tag
-    expect(result).toBe("oh-my-opencode@next")
-  })
-
-  test("returns prerelease channel tag when no dist-tag matches prerelease version", async () => {
-    // #given npm dist-tags with beta=3.0.0-beta.3
-    globalThis.fetch = mock(() =>
-      Promise.resolve({
-        ok: true,
-        json: () => Promise.resolve({ latest: "2.14.0", beta: "3.0.0-beta.3" }),
-      } as Response)
-    ) as unknown as typeof fetch
-
-    // #when current version is old beta 3.0.0-beta.2
-    const result = await getPluginNameWithVersion("3.0.0-beta.2")
-
-    // #then should preserve prerelease channel
-    expect(result).toBe("oh-my-opencode@beta")
-  })
-
-  test("returns prerelease channel tag when fetch fails", async () => {
-    // #given network failure
-    globalThis.fetch = mock(() => Promise.reject(new Error("Network error"))) as unknown as typeof fetch
-
-    // #when current version is 3.0.0-beta.3
-    const result = await getPluginNameWithVersion("3.0.0-beta.3")
-
-    // #then should preserve prerelease channel
-    expect(result).toBe("oh-my-opencode@beta")
-  })
-
-  test("returns bare package name when npm returns non-ok response for stable version", async () => {
-    // #given npm returns 404
-    globalThis.fetch = mock(() =>
-      Promise.resolve({
-        ok: false,
-        status: 404,
-      } as Response)
-    ) as unknown as typeof fetch
-
-    // #when current version is 2.14.0
-    const result = await getPluginNameWithVersion("2.14.0")
-
-    // #then should fall back to bare package entry
-    expect(result).toBe("oh-my-opencode")
-  })
-
-  test("prioritizes latest over other tags when version matches multiple", async () => {
-    // #given version matches both latest and beta (during release promotion)
-    globalThis.fetch = mock(() =>
-      Promise.resolve({
-        ok: true,
-        json: () => Promise.resolve({ beta: "3.0.0", latest: "3.0.0", next: "3.1.0-alpha.1" }),
-      } as Response)
-    ) as unknown as typeof fetch
-
-    // #when current version matches both
-    const result = await getPluginNameWithVersion("3.0.0")
-
-    // #then should prioritize @latest
-    expect(result).toBe("oh-my-opencode@latest")
-  })
-})
-
-describe("fetchNpmDistTags", () => {
-  const originalFetch = globalThis.fetch
-
-  afterEach(() => {
-    globalThis.fetch = originalFetch
-  })
-
-  test("returns dist-tags on success", async () => {
-    // #given npm returns dist-tags
-    globalThis.fetch = mock(() =>
-      Promise.resolve({
-        ok: true,
-        json: () => Promise.resolve({ latest: "2.14.0", beta: "3.0.0-beta.3" }),
-      } as Response)
-    ) as unknown as typeof fetch
-
-    // #when fetching dist-tags
-    const result = await fetchNpmDistTags("oh-my-opencode")
-
-    // #then should return the tags
-    expect(result).toEqual({ latest: "2.14.0", beta: "3.0.0-beta.3" })
-  })
-
-  test("returns null on network failure", async () => {
-    // #given network failure
-    globalThis.fetch = mock(() => Promise.reject(new Error("Network error"))) as unknown as typeof fetch
-
-    // #when fetching dist-tags
-    const result = await fetchNpmDistTags("oh-my-opencode")
-
-    // #then should return null
-    expect(result).toBeNull()
-  })
-
-  test("returns null on non-ok response", async () => {
-    // #given npm returns 404
-    globalThis.fetch = mock(() =>
-      Promise.resolve({
-        ok: false,
-        status: 404,
-      } as Response)
-    ) as unknown as typeof fetch
-
-    // #when fetching dist-tags
-    const result = await fetchNpmDistTags("oh-my-opencode")
-
-    // #then should return null
-    expect(result).toBeNull()
-  })
-})
-
-describe("generateOmoConfig - model fallback system", () => {
-  test("uses github-copilot sonnet fallback when only copilot available", () => {
-    // #given user has only copilot (no max plan)
-    const config: InstallConfig = {
-      hasClaude: false,
-      isMax20: false,
-      hasOpenAI: false,
-      hasGemini: false,
-      hasCopilot: true,
-      hasOpencodeZen: false,
-      hasZaiCodingPlan: false,
-      hasKimiForCoding: false,
-    }
-
-    // #when generating config
-    const result = generateOmoConfig(config)
-
-    // #then Sisyphus uses Copilot (OR logic - copilot is in claude-opus-4-6 providers)
-    expect((result.agents as Record<string, { model: string }>).sisyphus.model).toBe("github-copilot/claude-opus-4.6")
-  })
-
-  test("uses ultimate fallback when no providers configured", () => {
-    // #given user has no providers
-    const config: InstallConfig = {
-      hasClaude: false,
-      isMax20: false,
-      hasOpenAI: false,
-      hasGemini: false,
-      hasCopilot: false,
-      hasOpencodeZen: false,
-      hasZaiCodingPlan: false,
-      hasKimiForCoding: false,
-    }
-
-    // #when generating config
-    const result = generateOmoConfig(config)
-
-    // #then Sisyphus is omitted (requires all fallback providers)
-    expect(result.$schema).toBe("https://raw.githubusercontent.com/code-yeongyu/oh-my-openagent/dev/assets/oh-my-opencode.schema.json")
-    expect((result.agents as Record<string, { model: string }>).sisyphus).toBeUndefined()
-  })
-
-  test("uses ZAI model for librarian when Z.ai is available", () => {
-    // #given user has Z.ai and Claude max20
-    const config: InstallConfig = {
-      hasClaude: true,
-      isMax20: true,
-      hasOpenAI: false,
-      hasGemini: false,
-      hasCopilot: false,
-      hasOpencodeZen: false,
-      hasZaiCodingPlan: true,
-      hasKimiForCoding: false,
-    }
-
-    // #when generating config
-    const result = generateOmoConfig(config)
-
-    // #then librarian should use ZAI model
-    expect((result.agents as Record<string, { model: string }>).librarian.model).toBe("zai-coding-plan/glm-4.7")
-    // #then Sisyphus uses Claude (OR logic)
-    expect((result.agents as Record<string, { model: string }>).sisyphus.model).toBe("anthropic/claude-opus-4-6")
-  })
-
-  test("uses native OpenAI models when only ChatGPT available", () => {
-    // #given user has only ChatGPT subscription
-    const config: InstallConfig = {
-      hasClaude: false,
-      isMax20: false,
-      hasOpenAI: true,
-      hasGemini: false,
-      hasCopilot: false,
-      hasOpencodeZen: false,
-      hasZaiCodingPlan: false,
-      hasKimiForCoding: false,
-    }
-
-    // #when generating config
-    const result = generateOmoConfig(config)
-
-    // #then Sisyphus resolves to gpt-5.4 medium (openai is now in sisyphus chain)
-    expect((result.agents as Record<string, { model: string; variant?: string }>).sisyphus.model).toBe("openai/gpt-5.4")
-    expect((result.agents as Record<string, { model: string; variant?: string }>).sisyphus.variant).toBe("medium")
-    // #then Oracle should use native OpenAI (first fallback entry)
-    expect((result.agents as Record<string, { model: string }>).oracle.model).toBe("openai/gpt-5.4")
-    // #then multimodal-looker should use native OpenAI (first fallback entry is gpt-5.4)
-    expect((result.agents as Record<string, { model: string }>)["multimodal-looker"].model).toBe("openai/gpt-5.4")
-  })
-
-  test("uses haiku for explore when Claude max20", () => {
-    // #given user has Claude max20
-    const config: InstallConfig = {
-      hasClaude: true,
-      isMax20: true,
-      hasOpenAI: false,
-      hasGemini: false,
-      hasCopilot: false,
-      hasOpencodeZen: false,
-      hasZaiCodingPlan: false,
-      hasKimiForCoding: false,
-    }
-
-    // #when generating config
-    const result = generateOmoConfig(config)
-
-    // #then explore should use haiku (max20 plan uses Claude quota)
-    expect((result.agents as Record<string, { model: string }>).explore.model).toBe("anthropic/claude-haiku-4-5")
-  })
-
-  test("uses haiku for explore regardless of max20 flag", () => {
-    // #given user has Claude but not max20
-    const config: InstallConfig = {
-      hasClaude: true,
-      isMax20: false,
-      hasOpenAI: false,
-      hasGemini: false,
-      hasCopilot: false,
-      hasOpencodeZen: false,
-      hasZaiCodingPlan: false,
-      hasKimiForCoding: false,
-    }
-
-    // #when generating config
-    const result = generateOmoConfig(config)
-
-    // #then explore should use haiku (isMax20 doesn't affect explore anymore)
-    expect((result.agents as Record<string, { model: string }>).explore.model).toBe("anthropic/claude-haiku-4-5")
-  })
-})

src/cli/config-manager/add-plugin-to-opencode-config.ts

@@ -41,37 +41,39 @@ export async function addPluginToOpenCodeConfig(currentVersion: string): Promise
     const config = parseResult.config
     const plugins = config.plugin ?? []
 
-    // Check for existing plugin (either current or legacy name)
-    const currentNameIndex = plugins.findIndex(
+    const canonicalEntries = plugins.filter(
       (plugin) => plugin === PLUGIN_NAME || plugin.startsWith(`${PLUGIN_NAME}@`)
     )
-    const legacyNameIndex = plugins.findIndex(
+    const legacyEntries = plugins.filter(
       (plugin) => plugin === LEGACY_PLUGIN_NAME || plugin.startsWith(`${LEGACY_PLUGIN_NAME}@`)
     )
+    const otherPlugins = plugins.filter(
+      (plugin) => !(plugin === PLUGIN_NAME || plugin.startsWith(`${PLUGIN_NAME}@`))
+        && !(plugin === LEGACY_PLUGIN_NAME || plugin.startsWith(`${LEGACY_PLUGIN_NAME}@`))
+    )
 
-    // If either name exists, update to new name
-    if (currentNameIndex !== -1) {
-      if (plugins[currentNameIndex] === pluginEntry) {
-        return { success: true, configPath: path }
-      }
-      plugins[currentNameIndex] = pluginEntry
-    } else if (legacyNameIndex !== -1) {
-      // Upgrade legacy name to new name
-      plugins[legacyNameIndex] = pluginEntry
+    const normalizedPlugins = [...otherPlugins]
+
+    if (canonicalEntries.length > 0) {
+      normalizedPlugins.push(canonicalEntries[0])
+    } else if (legacyEntries.length > 0) {
+      const versionMatch = legacyEntries[0].match(/@(.+)$/)
+      const preservedVersion = versionMatch ? versionMatch[1] : null
+      normalizedPlugins.push(preservedVersion ? `${PLUGIN_NAME}@${preservedVersion}` : pluginEntry)
     } else {
-      plugins.push(pluginEntry)
+      normalizedPlugins.push(pluginEntry)
     }
 
-    config.plugin = plugins
+    config.plugin = normalizedPlugins
 
     if (format === "jsonc") {
       const content = readFileSync(path, "utf-8")
-      const pluginArrayRegex = /"plugin"\s*:\s*\[([\s\S]*?)\]/
+      const pluginArrayRegex = /((?:"plugin"|plugin)\s*:\s*)\[([\s\S]*?)\]/
       const match = content.match(pluginArrayRegex)
 
       if (match) {
-        const formattedPlugins = plugins.map((p) => `"${p}"`).join(",\n    ")
-        const newContent = content.replace(pluginArrayRegex, `"plugin": [\n    ${formattedPlugins}\n  ]`)
+        const formattedPlugins = normalizedPlugins.map((p) => `"${p}"`).join(",\n    ")
+        const newContent = content.replace(pluginArrayRegex, `$1[\n    ${formattedPlugins}\n  ]`)
         writeFileSync(path, newContent)
       } else {
         const newContent = content.replace(/(\{)/, `$1\n  "plugin": ["${pluginEntry}"],`)

src/cli/config-manager/generate-omo-config.test.ts

@@ -0,0 +1,142 @@
+/// <reference types="bun-types" />
+
+import { describe, expect, test } from "bun:test"
+
+import { generateOmoConfig } from "../config-manager"
+import type { InstallConfig } from "../types"
+
+describe("generateOmoConfig - model fallback system", () => {
+  test("uses github-copilot sonnet fallback when only copilot available", () => {
+    //#given
+    const config: InstallConfig = {
+      hasClaude: false,
+      isMax20: false,
+      hasOpenAI: false,
+      hasGemini: false,
+      hasCopilot: true,
+      hasOpencodeZen: false,
+      hasZaiCodingPlan: false,
+      hasKimiForCoding: false,
+      hasOpencodeGo: false,
+    }
+
+    //#when
+    const result = generateOmoConfig(config)
+
+    //#then
+    expect([
+      "github-copilot/claude-opus-4.6",
+      "github-copilot/claude-opus-4-6",
+    ]).toContain((result.agents as Record<string, { model: string }>).sisyphus.model)
+  })
+
+  test("uses ultimate fallback when no providers configured", () => {
+    //#given
+    const config: InstallConfig = {
+      hasClaude: false,
+      isMax20: false,
+      hasOpenAI: false,
+      hasGemini: false,
+      hasCopilot: false,
+      hasOpencodeZen: false,
+      hasZaiCodingPlan: false,
+      hasKimiForCoding: false,
+      hasOpencodeGo: false,
+    }
+
+    //#when
+    const result = generateOmoConfig(config)
+
+    //#then
+    expect(result.$schema).toBe("https://raw.githubusercontent.com/code-yeongyu/oh-my-openagent/dev/assets/oh-my-opencode.schema.json")
+    expect((result.agents as Record<string, { model: string }>).sisyphus).toBeUndefined()
+  })
+
+  test("uses ZAI model for librarian when Z.ai is available", () => {
+    //#given
+    const config: InstallConfig = {
+      hasClaude: true,
+      isMax20: true,
+      hasOpenAI: false,
+      hasGemini: false,
+      hasCopilot: false,
+      hasOpencodeZen: false,
+      hasZaiCodingPlan: true,
+      hasKimiForCoding: false,
+      hasOpencodeGo: false,
+    }
+
+    //#when
+    const result = generateOmoConfig(config)
+
+    //#then
+    expect((result.agents as Record<string, { model: string }>).librarian.model).toBe("zai-coding-plan/glm-4.7")
+    expect((result.agents as Record<string, { model: string }>).sisyphus.model).toBe("anthropic/claude-opus-4-6")
+  })
+
+  test("uses native OpenAI models when only ChatGPT available", () => {
+    //#given
+    const config: InstallConfig = {
+      hasClaude: false,
+      isMax20: false,
+      hasOpenAI: true,
+      hasGemini: false,
+      hasCopilot: false,
+      hasOpencodeZen: false,
+      hasZaiCodingPlan: false,
+      hasKimiForCoding: false,
+      hasOpencodeGo: false,
+    }
+
+    //#when
+    const result = generateOmoConfig(config)
+
+    //#then
+    expect((result.agents as Record<string, { model: string; variant?: string }>).sisyphus.model).toBe("openai/gpt-5.4")
+    expect((result.agents as Record<string, { model: string; variant?: string }>).sisyphus.variant).toBe("medium")
+    expect((result.agents as Record<string, { model: string }>).oracle.model).toBe("openai/gpt-5.4")
+    expect((result.agents as Record<string, { model: string }>)['multimodal-looker'].model).toBe("openai/gpt-5.4")
+  })
+
+  test("uses haiku for explore when Claude max20", () => {
+    //#given
+    const config: InstallConfig = {
+      hasClaude: true,
+      isMax20: true,
+      hasOpenAI: false,
+      hasGemini: false,
+      hasCopilot: false,
+      hasOpencodeZen: false,
+      hasZaiCodingPlan: false,
+      hasKimiForCoding: false,
+      hasOpencodeGo: false,
+    }
+
+    //#when
+    const result = generateOmoConfig(config)
+
+    //#then
+    expect((result.agents as Record<string, { model: string }>).explore.model).toBe("anthropic/claude-haiku-4-5")
+  })
+
+  test("uses haiku for explore regardless of max20 flag", () => {
+    //#given
+    const config: InstallConfig = {
+      hasClaude: true,
+      isMax20: false,
+      hasOpenAI: false,
+      hasGemini: false,
+      hasCopilot: false,
+      hasOpencodeZen: false,
+      hasZaiCodingPlan: false,
+      hasKimiForCoding: false,
+      hasOpencodeGo: false,
+    }
+
+    //#when
+    const result = generateOmoConfig(config)
+
+    //#then
+    expect((result.agents as Record<string, { model: string }>).explore.model).toBe("anthropic/claude-haiku-4-5")
+  })
+})

src/cli/config-manager/npm-dist-tags.test.ts

@@ -0,0 +1,56 @@
+/// <reference types="bun-types" />
+
+import { afterEach, describe, expect, mock, test } from "bun:test"
+
+import { fetchNpmDistTags } from "../config-manager"
+
+describe("fetchNpmDistTags", () => {
+  const originalFetch = globalThis.fetch
+
+  afterEach(() => {
+    globalThis.fetch = originalFetch
+  })
+
+  test("returns dist-tags on success", async () => {
+    //#given
+    globalThis.fetch = mock(() =>
+      Promise.resolve({
+        ok: true,
+        json: () => Promise.resolve({ latest: "3.13.1", beta: "3.14.0-beta.1" }),
+      } as Response)
+    ) as unknown as typeof fetch
+
+    //#when
+    const result = await fetchNpmDistTags("oh-my-openagent")
+
+    //#then
+    expect(result).toEqual({ latest: "3.13.1", beta: "3.14.0-beta.1" })
+  })
+
+  test("returns null on network failure", async () => {
+    //#given
+    globalThis.fetch = mock(() => Promise.reject(new Error("Network error"))) as unknown as typeof fetch
+
+    //#when
+    const result = await fetchNpmDistTags("oh-my-openagent")
+
+    //#then
+    expect(result).toBeNull()
+  })
+
+  test("returns null on non-ok response", async () => {
+    //#given
+    globalThis.fetch = mock(() =>
+      Promise.resolve({
+        ok: false,
+        status: 404,
+      } as Response)
+    ) as unknown as typeof fetch
+
+    //#when
+    const result = await fetchNpmDistTags("oh-my-openagent")
+
+    //#then
+    expect(result).toBeNull()
+  })
+})

src/cli/config-manager/plugin-detection.test.ts

@@ -28,10 +28,9 @@ describe("detectCurrentConfig - single package detection", () => {
     delete process.env.OPENCODE_CONFIG_DIR
   })
 
-  it("detects oh-my-opencode in plugin array", () => {
+  it("detects both legacy and canonical plugin entries", () => {
     // given
-    const config = { plugin: ["oh-my-opencode"] }
-    writeFileSync(testConfigPath, JSON.stringify(config, null, 2) + "\n", "utf-8")
+    writeFileSync(testConfigPath, JSON.stringify({ plugin: ["oh-my-opencode", "oh-my-openagent@3.11.0"] }, null, 2) + "\n", "utf-8")
 
     // when
     const result = detectCurrentConfig()
@@ -40,58 +39,9 @@ describe("detectCurrentConfig - single package detection", () => {
     expect(result.isInstalled).toBe(true)
   })
 
-  it("detects oh-my-opencode with version pin", () => {
+  it("returns false when plugin not present with similar name", () => {
     // given
-    const config = { plugin: ["oh-my-opencode@3.11.0"] }
-    writeFileSync(testConfigPath, JSON.stringify(config, null, 2) + "\n", "utf-8")
-
-    // when
-    const result = detectCurrentConfig()
-
-    // then
-    expect(result.isInstalled).toBe(true)
-  })
-
-  it("detects oh-my-openagent as installed (legacy name)", () => {
-    // given
-    const config = { plugin: ["oh-my-openagent"] }
-    writeFileSync(testConfigPath, JSON.stringify(config, null, 2) + "\n", "utf-8")
-
-    // when
-    const result = detectCurrentConfig()
-
-    // then
-    expect(result.isInstalled).toBe(true)
-  })
-
-  it("detects oh-my-openagent with version pin as installed (legacy name)", () => {
-    // given
-    const config = { plugin: ["oh-my-openagent@3.11.0"] }
-    writeFileSync(testConfigPath, JSON.stringify(config, null, 2) + "\n", "utf-8")
-
-    // when
-    const result = detectCurrentConfig()
-
-    // then
-    expect(result.isInstalled).toBe(true)
-  })
-
-  it("returns false when plugin not present", () => {
-    // given
-    const config = { plugin: ["some-other-plugin"] }
-    writeFileSync(testConfigPath, JSON.stringify(config, null, 2) + "\n", "utf-8")
-
-    // when
-    const result = detectCurrentConfig()
-
-    // then
-    expect(result.isInstalled).toBe(false)
-  })
-
-  it("returns false when plugin not present (even with similar name)", () => {
-    // given - not exactly oh-my-openagent
-    const config = { plugin: ["oh-my-openagent-extra"] }
-    writeFileSync(testConfigPath, JSON.stringify(config, null, 2) + "\n", "utf-8")
+    writeFileSync(testConfigPath, JSON.stringify({ plugin: ["oh-my-openagent-extra"] }, null, 2) + "\n", "utf-8")
 
     // when
     const result = detectCurrentConfig()
@@ -103,11 +53,7 @@ describe("detectCurrentConfig - single package detection", () => {
   it("detects OpenCode Go from the existing omo config", () => {
     // given
     writeFileSync(testConfigPath, JSON.stringify({ plugin: ["oh-my-opencode"] }, null, 2) + "\n", "utf-8")
-    writeFileSync(
-      testOmoConfigPath,
-      JSON.stringify({ agents: { atlas: { model: "opencode-go/kimi-k2.5" } } }, null, 2) + "\n",
-      "utf-8",
-    )
+    writeFileSync(testOmoConfigPath, JSON.stringify({ agents: { atlas: { model: "opencode-go/kimi-k2.5" } } }, null, 2) + "\n", "utf-8")
 
     // when
     const result = detectCurrentConfig()
@@ -137,10 +83,9 @@ describe("addPluginToOpenCodeConfig - single package writes", () => {
     delete process.env.OPENCODE_CONFIG_DIR
   })
 
-  it("keeps oh-my-opencode when it already exists", async () => {
+  it("writes canonical plugin entry for new installs", async () => {
     // given
-    const config = { plugin: ["oh-my-opencode"] }
-    writeFileSync(testConfigPath, JSON.stringify(config, null, 2) + "\n", "utf-8")
+    writeFileSync(testConfigPath, JSON.stringify({}, null, 2) + "\n", "utf-8")
 
     // when
     const result = await addPluginToOpenCodeConfig("3.11.0")
@@ -148,13 +93,12 @@ describe("addPluginToOpenCodeConfig - single package writes", () => {
     // then
     expect(result.success).toBe(true)
     const savedConfig = JSON.parse(readFileSync(testConfigPath, "utf-8"))
-    expect(savedConfig.plugin).toContain("oh-my-opencode")
+    expect(savedConfig.plugin).toEqual(["oh-my-openagent"])
   })
 
-  it("replaces version-pinned oh-my-opencode@X.Y.Z", async () => {
+  it("upgrades a bare legacy plugin entry to canonical", async () => {
     // given
-    const config = { plugin: ["oh-my-opencode@3.10.0"] }
-    writeFileSync(testConfigPath, JSON.stringify(config, null, 2) + "\n", "utf-8")
+    writeFileSync(testConfigPath, JSON.stringify({ plugin: ["oh-my-opencode"] }, null, 2) + "\n", "utf-8")
 
     // when
     const result = await addPluginToOpenCodeConfig("3.11.0")
@@ -162,14 +106,12 @@ describe("addPluginToOpenCodeConfig - single package writes", () => {
     // then
     expect(result.success).toBe(true)
     const savedConfig = JSON.parse(readFileSync(testConfigPath, "utf-8"))
-    expect(savedConfig.plugin).toContain("oh-my-opencode")
-    expect(savedConfig.plugin).not.toContain("oh-my-opencode@3.10.0")
+    expect(savedConfig.plugin).toEqual(["oh-my-openagent"])
   })
 
-  it("recognizes oh-my-openagent as already installed (legacy name)", async () => {
+  it("upgrades a version-pinned legacy entry to canonical", async () => {
     // given
-    const config = { plugin: ["oh-my-openagent"] }
-    writeFileSync(testConfigPath, JSON.stringify(config, null, 2) + "\n", "utf-8")
+    writeFileSync(testConfigPath, JSON.stringify({ plugin: ["oh-my-opencode@3.10.0"] }, null, 2) + "\n", "utf-8")
 
     // when
     const result = await addPluginToOpenCodeConfig("3.11.0")
@@ -177,15 +119,12 @@ describe("addPluginToOpenCodeConfig - single package writes", () => {
     // then
     expect(result.success).toBe(true)
     const savedConfig = JSON.parse(readFileSync(testConfigPath, "utf-8"))
-    // Should upgrade to new name
-    expect(savedConfig.plugin).toContain("oh-my-opencode")
-    expect(savedConfig.plugin).not.toContain("oh-my-openagent")
+    expect(savedConfig.plugin).toEqual(["oh-my-openagent@3.10.0"])
   })
 
-  it("replaces version-pinned oh-my-openagent@X.Y.Z with new name", async () => {
+  it("removes stale legacy entry when canonical and legacy entries both exist", async () => {
     // given
-    const config = { plugin: ["oh-my-openagent@3.10.0"] }
-    writeFileSync(testConfigPath, JSON.stringify(config, null, 2) + "\n", "utf-8")
+    writeFileSync(testConfigPath, JSON.stringify({ plugin: ["oh-my-openagent", "oh-my-opencode"] }, null, 2) + "\n", "utf-8")
 
     // when
     const result = await addPluginToOpenCodeConfig("3.11.0")
@@ -193,15 +132,12 @@ describe("addPluginToOpenCodeConfig - single package writes", () => {
     // then
     expect(result.success).toBe(true)
     const savedConfig = JSON.parse(readFileSync(testConfigPath, "utf-8"))
-    // Legacy should be replaced with new name
-    expect(savedConfig.plugin).toContain("oh-my-opencode")
-    expect(savedConfig.plugin).not.toContain("oh-my-openagent")
+    expect(savedConfig.plugin).toEqual(["oh-my-openagent"])
   })
 
-  it("adds new plugin when none exists", async () => {
+  it("preserves a canonical entry when it already exists", async () => {
     // given
-    const config = {}
-    writeFileSync(testConfigPath, JSON.stringify(config, null, 2) + "\n", "utf-8")
+    writeFileSync(testConfigPath, JSON.stringify({ plugin: ["oh-my-openagent@3.10.0"] }, null, 2) + "\n", "utf-8")
 
     // when
     const result = await addPluginToOpenCodeConfig("3.11.0")
@@ -209,20 +145,21 @@ describe("addPluginToOpenCodeConfig - single package writes", () => {
     // then
     expect(result.success).toBe(true)
     const savedConfig = JSON.parse(readFileSync(testConfigPath, "utf-8"))
-    expect(savedConfig.plugin).toContain("oh-my-opencode")
+    expect(savedConfig.plugin).toEqual(["oh-my-openagent@3.10.0"])
   })
 
-  it("adds plugin when plugin array is empty", async () => {
+  it("rewrites quoted jsonc plugin field in place", async () => {
     // given
-    const config = { plugin: [] }
-    writeFileSync(testConfigPath, JSON.stringify(config, null, 2) + "\n", "utf-8")
+    testConfigPath = join(testConfigDir, "opencode.jsonc")
+    writeFileSync(testConfigPath, '{\n  "plugin": ["oh-my-opencode"]\n}\n', "utf-8")
 
     // when
     const result = await addPluginToOpenCodeConfig("3.11.0")
 
     // then
     expect(result.success).toBe(true)
-    const savedConfig = JSON.parse(readFileSync(testConfigPath, "utf-8"))
-    expect(savedConfig.plugin).toContain("oh-my-opencode")
+    const savedContent = readFileSync(testConfigPath, "utf-8")
+    expect(savedContent.includes('"plugin": [\n    "oh-my-openagent"\n  ]')).toBe(true)
+    expect(savedContent.includes("oh-my-opencode")).toBe(false)
   })
 })

src/cli/config-manager/plugin-name-with-version.test.ts

@@ -0,0 +1,56 @@
+/// <reference types="bun-types" />
+
+import { afterEach, describe, expect, mock, test } from "bun:test"
+
+import { getPluginNameWithVersion } from "../config-manager"
+
+describe("getPluginNameWithVersion", () => {
+  const originalFetch = globalThis.fetch
+
+  afterEach(() => {
+    globalThis.fetch = originalFetch
+  })
+
+  test("returns the canonical latest tag when current version matches latest", async () => {
+    //#given
+    globalThis.fetch = mock(() =>
+      Promise.resolve({
+        ok: true,
+        json: () => Promise.resolve({ latest: "3.13.1", beta: "3.14.0-beta.1" }),
+      } as Response)
+    ) as unknown as typeof fetch
+
+    //#when
+    const result = await getPluginNameWithVersion("3.13.1")
+
+    //#then
+    expect(result).toBe("oh-my-openagent@latest")
+  })
+
+  test("preserves the canonical prerelease channel when fetch fails", async () => {
+    //#given
+    globalThis.fetch = mock(() => Promise.reject(new Error("Network error"))) as unknown as typeof fetch
+
+    //#when
+    const result = await getPluginNameWithVersion("3.14.0-beta.1")
+
+    //#then
+    expect(result).toBe("oh-my-openagent@beta")
+  })
+
+  test("returns the canonical bare package name for stable fallback", async () => {
+    //#given
+    globalThis.fetch = mock(() =>
+      Promise.resolve({
+        ok: false,
+        status: 404,
+      } as Response)
+    ) as unknown as typeof fetch
+
+    //#when
+    const result = await getPluginNameWithVersion("3.13.1")
+
+    //#then
+    expect(result).toBe("oh-my-openagent")
+  })
+})

src/cli/config-manager/plugin-name-with-version.ts

@@ -1,6 +1,7 @@
+import { PLUGIN_NAME } from "../../shared"
 import { fetchNpmDistTags } from "./npm-dist-tags"
 
-const DEFAULT_PACKAGE_NAME = "oh-my-opencode"
+const DEFAULT_PACKAGE_NAME = PLUGIN_NAME
 const PRIORITIZED_TAGS = ["latest", "beta", "next"] as const
 
 function getFallbackEntry(version: string, packageName: string): string {

src/cli/doctor/checks/config.ts

@@ -2,15 +2,15 @@ import { readFileSync } from "node:fs"
 import { join } from "node:path"
 
 import { OhMyOpenCodeConfigSchema } from "../../../config"
-import { detectConfigFile, getOpenCodeConfigDir, parseJsonc } from "../../../shared"
+import { detectPluginConfigFile, getOpenCodeConfigDir, parseJsonc } from "../../../shared"
 import { CHECK_IDS, CHECK_NAMES, PACKAGE_NAME } from "../constants"
 import type { CheckResult, DoctorIssue } from "../types"
 import { loadAvailableModelsFromCache } from "./model-resolution-cache"
 import { getModelResolutionInfoWithOverrides } from "./model-resolution"
 import type { OmoConfig } from "./model-resolution-types"
 
-const USER_CONFIG_BASE = join(getOpenCodeConfigDir({ binary: "opencode" }), PACKAGE_NAME)
-const PROJECT_CONFIG_BASE = join(process.cwd(), ".opencode", PACKAGE_NAME)
+const USER_CONFIG_DIR = getOpenCodeConfigDir({ binary: "opencode" })
+const PROJECT_CONFIG_DIR = join(process.cwd(), ".opencode")
 
 interface ConfigValidationResult {
   exists: boolean
@@ -21,10 +21,10 @@ interface ConfigValidationResult {
 }
 
 function findConfigPath(): string | null {
-  const projectConfig = detectConfigFile(PROJECT_CONFIG_BASE)
+  const projectConfig = detectPluginConfigFile(PROJECT_CONFIG_DIR)
   if (projectConfig.format !== "none") return projectConfig.path
 
-  const userConfig = detectConfigFile(USER_CONFIG_BASE)
+  const userConfig = detectPluginConfigFile(USER_CONFIG_DIR)
   if (userConfig.format !== "none") return userConfig.path
 
   return null

src/cli/doctor/checks/model-resolution-config.ts

@@ -1,17 +1,13 @@
 import { readFileSync } from "node:fs"
 import { join } from "node:path"
-import { detectConfigFile, getOpenCodeConfigPaths, parseJsonc } from "../../../shared"
+import { detectPluginConfigFile, getOpenCodeConfigPaths, parseJsonc } from "../../../shared"
 import type { OmoConfig } from "./model-resolution-types"
 
-const PACKAGE_NAME = "oh-my-opencode"
-const USER_CONFIG_BASE = join(
-  getOpenCodeConfigPaths({ binary: "opencode", version: null }).configDir,
-  PACKAGE_NAME
-)
-const PROJECT_CONFIG_BASE = join(process.cwd(), ".opencode", PACKAGE_NAME)
+const USER_CONFIG_DIR = getOpenCodeConfigPaths({ binary: "opencode", version: null }).configDir
+const PROJECT_CONFIG_DIR = join(process.cwd(), ".opencode")
 
 export function loadOmoConfig(): OmoConfig | null {
-  const projectDetected = detectConfigFile(PROJECT_CONFIG_BASE)
+  const projectDetected = detectPluginConfigFile(PROJECT_CONFIG_DIR)
   if (projectDetected.format !== "none") {
     try {
       const content = readFileSync(projectDetected.path, "utf-8")
@@ -21,7 +17,7 @@ export function loadOmoConfig(): OmoConfig | null {
     }
   }
 
-  const userDetected = detectConfigFile(USER_CONFIG_BASE)
+  const userDetected = detectPluginConfigFile(USER_CONFIG_DIR)
   if (userDetected.format !== "none") {
     try {
       const content = readFileSync(userDetected.path, "utf-8")

src/cli/doctor/checks/model-resolution-details.ts

@@ -4,6 +4,10 @@ import { getOpenCodeCacheDir } from "../../../shared"
 import type { AvailableModelsInfo, ModelResolutionInfo, OmoConfig } from "./model-resolution-types"
 import { formatModelWithVariant, getCategoryEffectiveVariant, getEffectiveVariant } from "./model-resolution-variant"
 
+function formatCapabilityResolutionLabel(mode: string | undefined): string {
+  return mode ?? "unknown"
+}
+
 export function buildModelResolutionDetails(options: {
   info: ModelResolutionInfo
   available: AvailableModelsInfo
@@ -37,7 +41,7 @@ export function buildModelResolutionDetails(options: {
       agent.effectiveModel,
       getEffectiveVariant(agent.name, agent.requirement, options.config)
     )
-    details.push(`  ${marker} ${agent.name}: ${display}`)
+    details.push(`  ${marker} ${agent.name}: ${display} [capabilities: ${formatCapabilityResolutionLabel(agent.capabilityDiagnostics?.resolutionMode)}]`)
   }
   details.push("")
   details.push("Categories:")
@@ -47,7 +51,7 @@ export function buildModelResolutionDetails(options: {
       category.effectiveModel,
       getCategoryEffectiveVariant(category.name, category.requirement, options.config)
     )
-    details.push(`  ${marker} ${category.name}: ${display}`)
+    details.push(`  ${marker} ${category.name}: ${display} [capabilities: ${formatCapabilityResolutionLabel(category.capabilityDiagnostics?.resolutionMode)}]`)
   }
   details.push("")
   details.push("● = user override, ○ = provider fallback")

src/cli/doctor/checks/model-resolution-types.ts

@@ -1,3 +1,4 @@
+import type { ModelCapabilitiesDiagnostics } from "../../../shared/model-capabilities"
 import type { ModelRequirement } from "../../../shared/model-requirements"
 
 export interface AgentResolutionInfo {
@@ -7,6 +8,7 @@ export interface AgentResolutionInfo {
   userVariant?: string
   effectiveModel: string
   effectiveResolution: string
+  capabilityDiagnostics?: ModelCapabilitiesDiagnostics
 }
 
 export interface CategoryResolutionInfo {
@@ -16,6 +18,7 @@ export interface CategoryResolutionInfo {
   userVariant?: string
   effectiveModel: string
   effectiveResolution: string
+  capabilityDiagnostics?: ModelCapabilitiesDiagnostics
 }
 
 export interface ModelResolutionInfo {

src/cli/doctor/checks/model-resolution.test.ts

@@ -129,6 +129,19 @@ describe("model-resolution check", () => {
       expect(visual!.userOverride).toBe("google/gemini-3-flash-preview")
       expect(visual!.userVariant).toBe("high")
     })
+
+    it("attaches snapshot-backed capability diagnostics for built-in models", async () => {
+      const { getModelResolutionInfoWithOverrides } = await import("./model-resolution")
+
+      const info = getModelResolutionInfoWithOverrides({})
+      const sisyphus = info.agents.find((a) => a.name === "sisyphus")
+
+      expect(sisyphus).toBeDefined()
+      expect(sisyphus!.capabilityDiagnostics).toMatchObject({
+        resolutionMode: "snapshot-backed",
+        snapshot: { source: "bundled-snapshot" },
+      })
+    })
   })
 
   describe("checkModelResolution", () => {
@@ -162,6 +175,23 @@ describe("model-resolution check", () => {
       expect(result.details!.some((d) => d.includes("Categories:"))).toBe(true)
       // Should have legend
       expect(result.details!.some((d) => d.includes("user override"))).toBe(true)
+      expect(result.details!.some((d) => d.includes("capabilities: snapshot-backed"))).toBe(true)
+    })
+
+    it("collects warnings when configured models rely on compatibility fallback", async () => {
+      const { collectCapabilityResolutionIssues, getModelResolutionInfoWithOverrides } = await import("./model-resolution")
+
+      const info = getModelResolutionInfoWithOverrides({
+        agents: {
+          oracle: { model: "custom/unknown-llm" },
+        },
+      })
+
+      const issues = collectCapabilityResolutionIssues(info)
+
+      expect(issues).toHaveLength(1)
+      expect(issues[0]?.title).toContain("compatibility fallback")
+      expect(issues[0]?.description).toContain("oracle=custom/unknown-llm")
     })
   })
 

src/cli/doctor/checks/model-resolution.ts

@@ -1,4 +1,5 @@
 import { AGENT_MODEL_REQUIREMENTS, CATEGORY_MODEL_REQUIREMENTS } from "../../../shared/model-requirements"
+import { getModelCapabilities } from "../../../shared/model-capabilities"
 import { CHECK_IDS, CHECK_NAMES } from "../constants"
 import type { CheckResult, DoctorIssue } from "../types"
 import { loadAvailableModelsFromCache } from "./model-resolution-cache"
@@ -7,16 +8,36 @@ import { buildModelResolutionDetails } from "./model-resolution-details"
 import { buildEffectiveResolution, getEffectiveModel } from "./model-resolution-effective-model"
 import type { AgentResolutionInfo, CategoryResolutionInfo, ModelResolutionInfo, OmoConfig } from "./model-resolution-types"
 
-export function getModelResolutionInfo(): ModelResolutionInfo {
-  const agents: AgentResolutionInfo[] = Object.entries(AGENT_MODEL_REQUIREMENTS).map(([name, requirement]) => ({
-    name,
-    requirement,
-    effectiveModel: getEffectiveModel(requirement),
-    effectiveResolution: buildEffectiveResolution(requirement),
-  }))
+function parseProviderModel(value: string): { providerID: string; modelID: string } | null {
+  const slashIndex = value.lastIndexOf("/")
+  if (slashIndex <= 0 || slashIndex === value.length - 1) {
+    return null
+  }
 
-  const categories: CategoryResolutionInfo[] = Object.entries(CATEGORY_MODEL_REQUIREMENTS).map(
-    ([name, requirement]) => ({
+  return {
+    providerID: value.slice(0, slashIndex),
+    modelID: value.slice(slashIndex + 1),
+  }
+}
+
+function attachCapabilityDiagnostics<T extends AgentResolutionInfo | CategoryResolutionInfo>(entry: T): T {
+  const parsed = parseProviderModel(entry.effectiveModel)
+  if (!parsed) {
+    return entry
+  }
+
+  return {
+    ...entry,
+    capabilityDiagnostics: getModelCapabilities({
+      providerID: parsed.providerID,
+      modelID: parsed.modelID,
+    }).diagnostics,
+  }
+}
+
+export function getModelResolutionInfo(): ModelResolutionInfo {
+  const agents: AgentResolutionInfo[] = Object.entries(AGENT_MODEL_REQUIREMENTS).map(([name, requirement]) =>
+    attachCapabilityDiagnostics({
       name,
       requirement,
       effectiveModel: getEffectiveModel(requirement),
@@ -24,6 +45,16 @@ export function getModelResolutionInfo(): ModelResolutionInfo {
     })
   )
 
+  const categories: CategoryResolutionInfo[] = Object.entries(CATEGORY_MODEL_REQUIREMENTS).map(
+    ([name, requirement]) =>
+      attachCapabilityDiagnostics({
+        name,
+        requirement,
+        effectiveModel: getEffectiveModel(requirement),
+        effectiveResolution: buildEffectiveResolution(requirement),
+      })
+  )
+
   return { agents, categories }
 }
 
@@ -31,34 +62,60 @@ export function getModelResolutionInfoWithOverrides(config: OmoConfig): ModelRes
   const agents: AgentResolutionInfo[] = Object.entries(AGENT_MODEL_REQUIREMENTS).map(([name, requirement]) => {
     const userOverride = config.agents?.[name]?.model
     const userVariant = config.agents?.[name]?.variant
-    return {
+    return attachCapabilityDiagnostics({
       name,
       requirement,
       userOverride,
       userVariant,
       effectiveModel: getEffectiveModel(requirement, userOverride),
       effectiveResolution: buildEffectiveResolution(requirement, userOverride),
-    }
+    })
   })
 
   const categories: CategoryResolutionInfo[] = Object.entries(CATEGORY_MODEL_REQUIREMENTS).map(
     ([name, requirement]) => {
       const userOverride = config.categories?.[name]?.model
       const userVariant = config.categories?.[name]?.variant
-      return {
+      return attachCapabilityDiagnostics({
         name,
         requirement,
         userOverride,
         userVariant,
         effectiveModel: getEffectiveModel(requirement, userOverride),
         effectiveResolution: buildEffectiveResolution(requirement, userOverride),
-      }
+      })
     }
   )
 
   return { agents, categories }
 }
 
+export function collectCapabilityResolutionIssues(info: ModelResolutionInfo): DoctorIssue[] {
+  const issues: DoctorIssue[] = []
+  const allEntries = [...info.agents, ...info.categories]
+  const fallbackEntries = allEntries.filter((entry) => {
+    const mode = entry.capabilityDiagnostics?.resolutionMode
+    return mode === "alias-backed" || mode === "heuristic-backed" || mode === "unknown"
+  })
+
+  if (fallbackEntries.length === 0) {
+    return issues
+  }
+
+  const summary = fallbackEntries
+    .map((entry) => `${entry.name}=${entry.effectiveModel} (${entry.capabilityDiagnostics?.resolutionMode ?? "unknown"})`)
+    .join(", ")
+
+  issues.push({
+    title: "Configured models rely on compatibility fallback",
+    description: summary,
+    severity: "warning",
+    affects: fallbackEntries.map((entry) => entry.name),
+  })
+
+  return issues
+}
+
 export async function checkModels(): Promise<CheckResult> {
   const config = loadOmoConfig() ?? {}
   const info = getModelResolutionInfoWithOverrides(config)
@@ -75,6 +132,8 @@ export async function checkModels(): Promise<CheckResult> {
     })
   }
 
+  issues.push(...collectCapabilityResolutionIssues(info))
+
   const overrideCount =
     info.agents.filter((agent) => Boolean(agent.userOverride)).length +
     info.categories.filter((category) => Boolean(category.userOverride)).length

src/cli/doctor/checks/system-loaded-version.test.ts

@@ -1,9 +1,10 @@
 import { afterEach, describe, expect, it } from "bun:test"
-import { mkdirSync, mkdtempSync, rmSync, writeFileSync } from "node:fs"
+import { mkdirSync, mkdtempSync, rmSync, symlinkSync, writeFileSync } from "node:fs"
 import { tmpdir } from "node:os"
 import { dirname, join } from "node:path"
 
 import { PACKAGE_NAME } from "../constants"
+import { resolveSymlink } from "../../../shared/file-utils"
 
 const systemLoadedVersionModulePath = "./system-loaded-version?system-loaded-version-test"
 
@@ -104,6 +105,31 @@ describe("system loaded version", () => {
       expect(loadedVersion.expectedVersion).toBe("2.3.4")
       expect(loadedVersion.loadedVersion).toBe("2.3.4")
     })
+
+    it("resolves symlinked config directories before selecting install path", () => {
+      //#given
+      const realConfigDir = createTemporaryDirectory("omo-real-config-")
+      const symlinkBaseDir = createTemporaryDirectory("omo-symlink-base-")
+      const symlinkConfigDir = join(symlinkBaseDir, "config-link")
+
+      symlinkSync(realConfigDir, symlinkConfigDir, process.platform === "win32" ? "junction" : "dir")
+      process.env.OPENCODE_CONFIG_DIR = symlinkConfigDir
+
+      writeJson(join(realConfigDir, "package.json"), {
+        dependencies: { [PACKAGE_NAME]: "4.5.6" },
+      })
+      writeJson(join(realConfigDir, "node_modules", PACKAGE_NAME, "package.json"), {
+        version: "4.5.6",
+      })
+
+      //#when
+      const loadedVersion = getLoadedPluginVersion()
+
+      //#then
+      expect(loadedVersion.cacheDir).toBe(resolveSymlink(symlinkConfigDir))
+      expect(loadedVersion.expectedVersion).toBe("4.5.6")
+      expect(loadedVersion.loadedVersion).toBe("4.5.6")
+    })
   })
 
   describe("getSuggestedInstallTag", () => {

src/cli/doctor/checks/system-loaded-version.ts

@@ -1,7 +1,7 @@
 import { existsSync, readFileSync } from "node:fs"
 import { homedir } from "node:os"
 import { join } from "node:path"
-
+import { resolveSymlink } from "../../../shared/file-utils"
 import { getLatestVersion } from "../../../hooks/auto-update-checker/checker"
 import { extractChannel } from "../../../hooks/auto-update-checker"
 import { PACKAGE_NAME } from "../constants"
@@ -36,6 +36,11 @@ function resolveOpenCodeCacheDir(): string {
   return platformDefault
 }
 
+function resolveExistingDir(dirPath: string): string {
+  if (!existsSync(dirPath)) return dirPath
+  return resolveSymlink(dirPath)
+}
+
 function readPackageJson(filePath: string): PackageJsonShape | null {
   if (!existsSync(filePath)) return null
 
@@ -55,12 +60,13 @@ function normalizeVersion(value: string | undefined): string | null {
 
 export function getLoadedPluginVersion(): LoadedVersionInfo {
   const configPaths = getOpenCodeConfigPaths({ binary: "opencode" })
-  const cacheDir = resolveOpenCodeCacheDir()
+  const configDir = resolveExistingDir(configPaths.configDir)
+  const cacheDir = resolveExistingDir(resolveOpenCodeCacheDir())
   const candidates = [
     {
-      cacheDir: configPaths.configDir,
-      cachePackagePath: configPaths.packageJson,
-      installedPackagePath: join(configPaths.configDir, "node_modules", PACKAGE_NAME, "package.json"),
+      cacheDir: configDir,
+      cachePackagePath: join(configDir, "package.json"),
+      installedPackagePath: join(configDir, "node_modules", PACKAGE_NAME, "package.json"),
     },
     {
       cacheDir,

src/cli/doctor/checks/system.test.ts

@@ -1,9 +1,19 @@
+/// <reference types="bun-types" />
+
 import { beforeEach, describe, expect, it, mock } from "bun:test"
+import { PLUGIN_NAME } from "../../../shared"
+import type { PluginInfo } from "./system-plugin"
+
+type SystemModule = typeof import("./system")
+
+async function importFreshSystemModule(): Promise<SystemModule> {
+  return import(`./system?test=${Date.now()}-${Math.random()}`)
+}
 
 const mockFindOpenCodeBinary = mock(async () => ({ path: "/usr/local/bin/opencode" }))
 const mockGetOpenCodeVersion = mock(async () => "1.0.200")
-const mockCompareVersions = mock(() => true)
-const mockGetPluginInfo = mock(() => ({
+const mockCompareVersions = mock((_leftVersion?: string, _rightVersion?: string) => true)
+const mockGetPluginInfo = mock((): PluginInfo => ({
   registered: true,
   entry: "oh-my-opencode",
   isPinned: false,
@@ -18,7 +28,8 @@ const mockGetLoadedPluginVersion = mock(() => ({
   expectedVersion: "3.0.0",
   loadedVersion: "3.1.0",
 }))
-const mockGetLatestPluginVersion = mock(async () => null)
+const mockGetLatestPluginVersion = mock(async (_currentVersion: string | null) => null as string | null)
+const mockGetSuggestedInstallTag = mock(() => "latest")
 
 mock.module("./system-binary", () => ({
   findOpenCodeBinary: mockFindOpenCodeBinary,
@@ -33,10 +44,9 @@ mock.module("./system-plugin", () => ({
 mock.module("./system-loaded-version", () => ({
   getLoadedPluginVersion: mockGetLoadedPluginVersion,
   getLatestPluginVersion: mockGetLatestPluginVersion,
+  getSuggestedInstallTag: mockGetSuggestedInstallTag,
 }))
 
-const { checkSystem } = await import("./system?test")
-
 describe("system check", () => {
   beforeEach(() => {
     mockFindOpenCodeBinary.mockReset()
@@ -45,6 +55,7 @@ describe("system check", () => {
     mockGetPluginInfo.mockReset()
     mockGetLoadedPluginVersion.mockReset()
     mockGetLatestPluginVersion.mockReset()
+    mockGetSuggestedInstallTag.mockReset()
 
     mockFindOpenCodeBinary.mockResolvedValue({ path: "/usr/local/bin/opencode" })
     mockGetOpenCodeVersion.mockResolvedValue("1.0.200")
@@ -65,10 +76,14 @@ describe("system check", () => {
       loadedVersion: "3.1.0",
     })
     mockGetLatestPluginVersion.mockResolvedValue(null)
+    mockGetSuggestedInstallTag.mockReturnValue("latest")
   })
 
   describe("#given cache directory contains spaces", () => {
     it("uses a quoted cache directory in mismatch fix command", async () => {
+      //#given
+      const { checkSystem } = await importFreshSystemModule()
+
       //#when
       const result = await checkSystem()
 
@@ -87,9 +102,11 @@ describe("system check", () => {
         loadedVersion: "3.0.0-canary.1",
       })
       mockGetLatestPluginVersion.mockResolvedValue("3.0.0-canary.2")
-      mockCompareVersions.mockImplementation((leftVersion: string, rightVersion: string) => {
+      mockGetSuggestedInstallTag.mockReturnValue("canary")
+      mockCompareVersions.mockImplementation((leftVersion?: string, rightVersion?: string) => {
         return !(leftVersion === "3.0.0-canary.1" && rightVersion === "3.0.0-canary.2")
       })
+      const { checkSystem } = await importFreshSystemModule()
 
       //#when
       const result = await checkSystem()
@@ -97,8 +114,94 @@ describe("system check", () => {
       //#then
       const outdatedIssue = result.issues.find((issue) => issue.title === "Loaded plugin is outdated")
       expect(outdatedIssue?.fix).toBe(
-        'Update: cd "/Users/test/Library/Caches/opencode with spaces" && bun add oh-my-opencode@canary'
+        `Update: cd "/Users/test/Library/Caches/opencode with spaces" && bun add ${PLUGIN_NAME}@canary`
       )
     })
   })
+
+  describe("#given OpenCode plugin entry uses legacy package name", () => {
+    it("adds a warning for a bare legacy entry", async () => {
+      //#given
+      mockGetPluginInfo.mockReturnValue({
+        registered: true,
+        entry: "oh-my-opencode",
+        isPinned: false,
+        pinnedVersion: null,
+        configPath: null,
+        isLocalDev: false,
+      })
+      const { checkSystem } = await importFreshSystemModule()
+
+      //#when
+      const result = await checkSystem()
+
+      //#then
+      const legacyEntryIssue = result.issues.find((issue) => issue.title === "Using legacy package name")
+      expect(legacyEntryIssue?.severity).toBe("warning")
+      expect(legacyEntryIssue?.fix).toBe(
+        'Update your opencode.json plugin entry: "oh-my-opencode" → "oh-my-openagent"'
+      )
+    })
+
+    it("adds a warning for a version-pinned legacy entry", async () => {
+      //#given
+      mockGetPluginInfo.mockReturnValue({
+        registered: true,
+        entry: "oh-my-opencode@3.0.0",
+        isPinned: true,
+        pinnedVersion: "3.0.0",
+        configPath: null,
+        isLocalDev: false,
+      })
+      const { checkSystem } = await importFreshSystemModule()
+
+      //#when
+      const result = await checkSystem()
+
+      //#then
+      const legacyEntryIssue = result.issues.find((issue) => issue.title === "Using legacy package name")
+      expect(legacyEntryIssue?.severity).toBe("warning")
+      expect(legacyEntryIssue?.fix).toBe(
+        'Update your opencode.json plugin entry: "oh-my-opencode@3.0.0" → "oh-my-openagent@3.0.0"'
+      )
+    })
+
+    it("does not warn for a canonical plugin entry", async () => {
+      //#given
+      mockGetPluginInfo.mockReturnValue({
+        registered: true,
+        entry: PLUGIN_NAME,
+        isPinned: false,
+        pinnedVersion: null,
+        configPath: null,
+        isLocalDev: false,
+      })
+      const { checkSystem } = await importFreshSystemModule()
+
+      //#when
+      const result = await checkSystem()
+
+      //#then
+      expect(result.issues.some((issue) => issue.title === "Using legacy package name")).toBe(false)
+    })
+
+    it("does not warn for a local-dev legacy entry", async () => {
+      //#given
+      mockGetPluginInfo.mockReturnValue({
+        registered: true,
+        entry: "oh-my-opencode",
+        isPinned: false,
+        pinnedVersion: null,
+        configPath: null,
+        isLocalDev: true,
+      })
+      const { checkSystem } = await importFreshSystemModule()
+
+      //#when
+      const result = await checkSystem()
+
+      //#then
+      expect(result.issues.some((issue) => issue.title === "Using legacy package name")).toBe(false)
+    })
+  })
 })

src/cli/doctor/checks/system.ts

@@ -6,6 +6,7 @@ import { findOpenCodeBinary, getOpenCodeVersion, compareVersions } from "./syste
 import { getPluginInfo } from "./system-plugin"
 import { getLatestPluginVersion, getLoadedPluginVersion, getSuggestedInstallTag } from "./system-loaded-version"
 import { parseJsonc } from "../../../shared"
+import { PLUGIN_NAME, LEGACY_PLUGIN_NAME } from "../../../shared/plugin-identity"
 
 function isConfigValid(configPath: string | null): boolean {
   if (!configPath) return true
@@ -82,14 +83,30 @@ export async function checkSystem(): Promise<CheckResult> {
 
   if (!pluginInfo.registered) {
     issues.push({
-      title: "oh-my-opencode is not registered",
+      title: `${PLUGIN_NAME} is not registered`,
       description: "Plugin entry is missing from OpenCode configuration.",
-      fix: "Run: bunx oh-my-opencode install",
+      fix: `Run: bunx ${PLUGIN_NAME} install`,
       severity: "error",
       affects: ["all agents"],
     })
   }
 
+  if (pluginInfo.entry && !pluginInfo.isLocalDev) {
+    const isLegacyName = pluginInfo.entry === LEGACY_PLUGIN_NAME
+      || pluginInfo.entry.startsWith(`${LEGACY_PLUGIN_NAME}@`)
+
+    if (isLegacyName) {
+      const suggestedEntry = pluginInfo.entry.replace(LEGACY_PLUGIN_NAME, PLUGIN_NAME)
+      issues.push({
+        title: "Using legacy package name",
+        description: `Your opencode.json references "${LEGACY_PLUGIN_NAME}" which has been renamed to "${PLUGIN_NAME}". The old name may stop working in a future release.`,
+        fix: `Update your opencode.json plugin entry: "${pluginInfo.entry}" → "${suggestedEntry}"`,
+        severity: "warning",
+        affects: ["plugin loading"],
+      })
+    }
+  }
+
   if (loadedInfo.expectedVersion && loadedInfo.loadedVersion && loadedInfo.expectedVersion !== loadedInfo.loadedVersion) {
     issues.push({
       title: "Loaded plugin version mismatch",
@@ -108,7 +125,7 @@ export async function checkSystem(): Promise<CheckResult> {
     issues.push({
       title: "Loaded plugin is outdated",
       description: `Loaded ${systemInfo.loadedVersion}, latest ${latestVersion}.`,
-      fix: `Update: cd "${loadedInfo.cacheDir}" && bun add oh-my-opencode@${installTag}`,
+      fix: `Update: cd "${loadedInfo.cacheDir}" && bun add ${PLUGIN_NAME}@${installTag}`,
       severity: "warning",
       affects: ["plugin features"],
     })

src/cli/doctor/constants.ts

@@ -1,4 +1,5 @@
 import color from "picocolors"
+import { PLUGIN_NAME } from "../../shared"
 
 export const SYMBOLS = {
   check: color.green("\u2713"),
@@ -38,6 +39,6 @@ export const EXIT_CODES = {
 
 export const MIN_OPENCODE_VERSION = "1.0.150"
 
-export const PACKAGE_NAME = "oh-my-opencode"
+export const PACKAGE_NAME = PLUGIN_NAME
 
 export const OPENCODE_BINARIES = ["opencode", "opencode-desktop"] as const

src/cli/install.test.ts

@@ -53,6 +53,14 @@ describe("install CLI - binary check behavior", () => {
     isOpenCodeInstalledSpy = spyOn(configManager, "isOpenCodeInstalled").mockResolvedValue(false)
     getOpenCodeVersionSpy = spyOn(configManager, "getOpenCodeVersion").mockResolvedValue(null)
 
+    // given mock npm fetch
+    globalThis.fetch = mock(() =>
+      Promise.resolve({
+        ok: true,
+        json: () => Promise.resolve({ latest: "3.0.0" }),
+      } as Response)
+    ) as unknown as typeof fetch
+
     const args: InstallArgs = {
       tui: false,
       claude: "yes",
@@ -105,10 +113,10 @@ describe("install CLI - binary check behavior", () => {
     const configPath = join(tempDir, "opencode.json")
     expect(existsSync(configPath)).toBe(true)
 
-    // then opencode.json should have plugin entry
     const config = JSON.parse(readFileSync(configPath, "utf-8"))
     expect(config.plugin).toBeDefined()
-    expect(config.plugin.some((p: string) => p.includes("oh-my-opencode"))).toBe(true)
+    expect(config.plugin.some((p: string) => p.includes("oh-my-openagent"))).toBe(true)
+    expect(config.plugin.some((p: string) => p.includes("oh-my-opencode"))).toBe(false)
 
     // then exit code should be 0 (success)
     expect(exitCode).toBe(0)

src/cli/model-fallback.test.ts

@@ -458,7 +458,7 @@ describe("generateModelConfig", () => {
       const result = generateModelConfig(config)
 
       // #then
-      expect(result.agents?.hephaestus?.model).toBe("openai/gpt-5.3-codex")
+      expect(result.agents?.hephaestus?.model).toBe("openai/gpt-5.4")
       expect(result.agents?.hephaestus?.variant).toBe("medium")
     })
 
@@ -484,7 +484,7 @@ describe("generateModelConfig", () => {
       const result = generateModelConfig(config)
 
       // #then
-      expect(result.agents?.hephaestus?.model).toBe("opencode/gpt-5.3-codex")
+      expect(result.agents?.hephaestus?.model).toBe("opencode/gpt-5.4")
       expect(result.agents?.hephaestus?.variant).toBe("medium")
     })
 

src/cli/model-fallback.ts

@@ -55,7 +55,7 @@ export function generateModelConfig(config: InstallConfig): GeneratedOmoConfig {
   for (const [role, req] of Object.entries(CLI_AGENT_MODEL_REQUIREMENTS)) {
     if (role === "librarian") {
       if (avail.opencodeGo) {
-        agents[role] = { model: "opencode-go/minimax-m2.5" }
+        agents[role] = { model: "opencode-go/minimax-m2.7" }
       } else if (avail.zai) {
         agents[role] = { model: ZAI_MODEL }
       }
@@ -68,7 +68,7 @@ export function generateModelConfig(config: InstallConfig): GeneratedOmoConfig {
       } else if (avail.opencodeZen) {
         agents[role] = { model: "opencode/claude-haiku-4-5" }
       } else if (avail.opencodeGo) {
-        agents[role] = { model: "opencode-go/minimax-m2.5" }
+        agents[role] = { model: "opencode-go/minimax-m2.7" }
       } else if (avail.copilot) {
         agents[role] = { model: "github-copilot/gpt-5-mini" }
       } else {

src/cli/openai-only-model-catalog.test.ts

@@ -40,7 +40,7 @@ describe("generateModelConfig OpenAI-only model catalog", () => {
 
     // #then
     expect(result.categories?.artistry).toEqual({ model: "openai/gpt-5.4", variant: "xhigh" })
-    expect(result.categories?.quick).toEqual({ model: "openai/gpt-5.3-codex", variant: "low" })
+    expect(result.categories?.quick).toEqual({ model: "openai/gpt-5.4-mini" })
     expect(result.categories?.["visual-engineering"]).toEqual({ model: "openai/gpt-5.4", variant: "high" })
     expect(result.categories?.writing).toEqual({ model: "openai/gpt-5.4", variant: "medium" })
   })
@@ -53,8 +53,8 @@ describe("generateModelConfig OpenAI-only model catalog", () => {
     const result = generateModelConfig(config)
 
     // #then
-    expect(result.agents?.explore).toEqual({ model: "opencode-go/minimax-m2.5" })
-    expect(result.agents?.librarian).toEqual({ model: "opencode-go/minimax-m2.5" })
-    expect(result.categories?.quick).toEqual({ model: "opencode-go/minimax-m2.5" })
+    expect(result.agents?.explore).toEqual({ model: "opencode-go/minimax-m2.7" })
+    expect(result.agents?.librarian).toEqual({ model: "opencode-go/minimax-m2.7" })
+    expect(result.categories?.quick).toEqual({ model: "openai/gpt-5.4-mini" })
   })
 })

src/cli/openai-only-model-catalog.ts

@@ -7,7 +7,7 @@ const OPENAI_ONLY_AGENT_OVERRIDES: Record<string, AgentConfig> = {
 
 const OPENAI_ONLY_CATEGORY_OVERRIDES: Record<string, CategoryConfig> = {
   artistry: { model: "openai/gpt-5.4", variant: "xhigh" },
-  quick: { model: "openai/gpt-5.3-codex", variant: "low" },
+  quick: { model: "openai/gpt-5.4-mini" },
   "visual-engineering": { model: "openai/gpt-5.4", variant: "high" },
   writing: { model: "openai/gpt-5.4", variant: "medium" },
 }

src/cli/refresh-model-capabilities.test.ts

@@ -0,0 +1,114 @@
+import { describe, expect, it, mock } from "bun:test"
+
+import { refreshModelCapabilities } from "./refresh-model-capabilities"
+
+describe("refreshModelCapabilities", () => {
+  it("uses config source_url when CLI override is absent", async () => {
+    const loadConfig = mock(() => ({
+      model_capabilities: {
+        source_url: "https://mirror.example/api.json",
+      },
+    }))
+    const refreshCache = mock(async () => ({
+      generatedAt: "2026-03-25T00:00:00.000Z",
+      sourceUrl: "https://mirror.example/api.json",
+      models: {
+        "gpt-5.4": { id: "gpt-5.4" },
+      },
+    }))
+    let stdout = ""
+
+    const exitCode = await refreshModelCapabilities(
+      { directory: "/repo", json: false },
+      {
+        loadConfig,
+        refreshCache,
+        stdout: {
+          write: (chunk: string) => {
+            stdout += chunk
+            return true
+          },
+        } as never,
+        stderr: {
+          write: () => true,
+        } as never,
+      },
+    )
+
+    expect(exitCode).toBe(0)
+    expect(loadConfig).toHaveBeenCalledWith("/repo", null)
+    expect(refreshCache).toHaveBeenCalledWith({
+      sourceUrl: "https://mirror.example/api.json",
+    })
+    expect(stdout).toContain("Refreshed model capabilities cache (1 models)")
+  })
+
+  it("CLI sourceUrl overrides config and supports json output", async () => {
+    const refreshCache = mock(async () => ({
+      generatedAt: "2026-03-25T00:00:00.000Z",
+      sourceUrl: "https://override.example/api.json",
+      models: {
+        "gpt-5.4": { id: "gpt-5.4" },
+        "claude-opus-4-6": { id: "claude-opus-4-6" },
+      },
+    }))
+    let stdout = ""
+
+    const exitCode = await refreshModelCapabilities(
+      {
+        directory: "/repo",
+        json: true,
+        sourceUrl: "https://override.example/api.json",
+      },
+      {
+        loadConfig: () => ({}),
+        refreshCache,
+        stdout: {
+          write: (chunk: string) => {
+            stdout += chunk
+            return true
+          },
+        } as never,
+        stderr: {
+          write: () => true,
+        } as never,
+      },
+    )
+
+    expect(exitCode).toBe(0)
+    expect(refreshCache).toHaveBeenCalledWith({
+      sourceUrl: "https://override.example/api.json",
+    })
+    expect(JSON.parse(stdout)).toEqual({
+      sourceUrl: "https://override.example/api.json",
+      generatedAt: "2026-03-25T00:00:00.000Z",
+      modelCount: 2,
+    })
+  })
+
+  it("returns exit code 1 when refresh fails", async () => {
+    let stderr = ""
+
+    const exitCode = await refreshModelCapabilities(
+      { directory: "/repo" },
+      {
+        loadConfig: () => ({}),
+        refreshCache: async () => {
+          throw new Error("boom")
+        },
+        stdout: {
+          write: () => true,
+        } as never,
+        stderr: {
+          write: (chunk: string) => {
+            stderr += chunk
+            return true
+          },
+        } as never,
+      },
+    )
+
+    expect(exitCode).toBe(1)
+    expect(stderr).toContain("Failed to refresh model capabilities cache")
+  })
+})

src/cli/refresh-model-capabilities.ts

@@ -0,0 +1,51 @@
+import { loadPluginConfig } from "../plugin-config"
+import { refreshModelCapabilitiesCache } from "../shared/model-capabilities-cache"
+
+export type RefreshModelCapabilitiesOptions = {
+  directory?: string
+  json?: boolean
+  sourceUrl?: string
+}
+
+type RefreshModelCapabilitiesDeps = {
+  loadConfig?: typeof loadPluginConfig
+  refreshCache?: typeof refreshModelCapabilitiesCache
+  stdout?: Pick<typeof process.stdout, "write">
+  stderr?: Pick<typeof process.stderr, "write">
+}
+
+export async function refreshModelCapabilities(
+  options: RefreshModelCapabilitiesOptions,
+  deps: RefreshModelCapabilitiesDeps = {},
+): Promise<number> {
+  const directory = options.directory ?? process.cwd()
+  const loadConfig = deps.loadConfig ?? loadPluginConfig
+  const refreshCache = deps.refreshCache ?? refreshModelCapabilitiesCache
+  const stdout = deps.stdout ?? process.stdout
+  const stderr = deps.stderr ?? process.stderr
+
+  try {
+    const config = loadConfig(directory, null)
+    const sourceUrl = options.sourceUrl ?? config.model_capabilities?.source_url
+    const snapshot = await refreshCache({ sourceUrl })
+
+    const summary = {
+      sourceUrl: snapshot.sourceUrl,
+      generatedAt: snapshot.generatedAt,
+      modelCount: Object.keys(snapshot.models).length,
+    }
+
+    if (options.json) {
+      stdout.write(`${JSON.stringify(summary, null, 2)}\n`)
+    } else {
+      stdout.write(
+        `Refreshed model capabilities cache (${summary.modelCount} models) from ${summary.sourceUrl}\n`,
+      )
+    }
+
+    return 0
+  } catch (error) {
+    stderr.write(`Failed to refresh model capabilities cache: ${String(error)}\n`)
+    return 1
+  }
+}

src/cli/run/integration.test.ts

@@ -159,8 +159,15 @@ describe("integration: --session-id", () => {
 
 describe("integration: --on-complete", () => {
   let spawnSpy: ReturnType<typeof spyOn>
+  let originalPlatform: NodeJS.Platform
+  let originalEnv: Record<string, string | undefined>
 
   beforeEach(() => {
+    originalPlatform = process.platform
+    originalEnv = {
+      SHELL: process.env.SHELL,
+      PSModulePath: process.env.PSModulePath,
+    }
     spyOn(console, "error").mockImplementation(() => {})
     spawnSpy = spyOn(spawnWithWindowsHideModule, "spawnWithWindowsHide").mockReturnValue({
       exited: Promise.resolve(0),
@@ -172,11 +179,22 @@ describe("integration: --on-complete", () => {
   })
 
   afterEach(() => {
+    Object.defineProperty(process, "platform", { value: originalPlatform })
+    for (const [key, value] of Object.entries(originalEnv)) {
+      if (value !== undefined) {
+        process.env[key] = value
+      } else {
+        delete process.env[key]
+      }
+    }
     spawnSpy.mockRestore()
   })
 
   it("passes all 4 env vars as strings to spawned process", async () => {
     // given
+    Object.defineProperty(process, "platform", { value: "linux" })
+    process.env.SHELL = "/bin/bash"
+    delete process.env.PSModulePath
     spawnSpy.mockClear()
 
     // when
@@ -206,8 +224,15 @@ describe("integration: option combinations", () => {
   let mockStdout: MockWriteStream
   let mockStderr: MockWriteStream
   let spawnSpy: ReturnType<typeof spyOn>
+  let originalPlatform: NodeJS.Platform
+  let originalEnv: Record<string, string | undefined>
 
   beforeEach(() => {
+    originalPlatform = process.platform
+    originalEnv = {
+      SHELL: process.env.SHELL,
+      PSModulePath: process.env.PSModulePath,
+    }
     spyOn(console, "log").mockImplementation(() => {})
     spyOn(console, "error").mockImplementation(() => {})
     mockStdout = createMockWriteStream()
@@ -222,11 +247,22 @@ describe("integration: option combinations", () => {
   })
 
   afterEach(() => {
+    Object.defineProperty(process, "platform", { value: originalPlatform })
+    for (const [key, value] of Object.entries(originalEnv)) {
+      if (value !== undefined) {
+        process.env[key] = value
+      } else {
+        delete process.env[key]
+      }
+    }
     spawnSpy?.mockRestore?.()
   })
 
   it("json output and on-complete hook can both execute", async () => {
     // given - json manager active + on-complete hook ready
+    Object.defineProperty(process, "platform", { value: "linux" })
+    process.env.SHELL = "/bin/bash"
+    delete process.env.PSModulePath
     const result: RunResult = {
       sessionId: "session-123",
       success: true,

src/cli/run/on-complete-hook.test.ts

@@ -4,6 +4,9 @@ import * as loggerModule from "../../shared/logger"
 import { executeOnCompleteHook } from "./on-complete-hook"
 
 describe("executeOnCompleteHook", () => {
+  let originalPlatform: NodeJS.Platform
+  let originalEnv: Record<string, string | undefined>
+
   function createStream(text: string): ReadableStream<Uint8Array> | undefined {
     if (text.length === 0) {
       return undefined
@@ -31,15 +34,32 @@ describe("executeOnCompleteHook", () => {
   let logSpy: ReturnType<typeof spyOn<typeof loggerModule, "log">>
 
   beforeEach(() => {
+    originalPlatform = process.platform
+    originalEnv = {
+      SHELL: process.env.SHELL,
+      PSModulePath: process.env.PSModulePath,
+      ComSpec: process.env.ComSpec,
+    }
     logSpy = spyOn(loggerModule, "log").mockImplementation(() => {})
   })
 
   afterEach(() => {
+    Object.defineProperty(process, "platform", { value: originalPlatform })
+    for (const [key, value] of Object.entries(originalEnv)) {
+      if (value !== undefined) {
+        process.env[key] = value
+      } else {
+        delete process.env[key]
+      }
+    }
     logSpy.mockRestore()
   })
 
-  it("executes command with correct env vars", async () => {
+  it("uses sh on unix shells and passes correct env vars", async () => {
     // given
+    Object.defineProperty(process, "platform", { value: "linux" })
+    process.env.SHELL = "/bin/bash"
+    delete process.env.PSModulePath
     const spawnSpy = spyOn(spawnWithWindowsHideModule, "spawnWithWindowsHide").mockReturnValue(createProc(0))
 
     try {
@@ -68,6 +88,82 @@ describe("executeOnCompleteHook", () => {
     }
   })
 
+  it("uses powershell when PowerShell is detected on Windows", async () => {
+    // given
+    Object.defineProperty(process, "platform", { value: "win32" })
+    process.env.PSModulePath = "C:\\Program Files\\PowerShell\\Modules"
+    delete process.env.SHELL
+    const spawnSpy = spyOn(spawnWithWindowsHideModule, "spawnWithWindowsHide").mockReturnValue(createProc(0))
+
+    try {
+      // when
+      await executeOnCompleteHook({
+        command: "Write-Host done",
+        sessionId: "session-123",
+        exitCode: 0,
+        durationMs: 5000,
+        messageCount: 10,
+      })
+
+      // then
+      const [args] = spawnSpy.mock.calls[0] as Parameters<typeof spawnWithWindowsHideModule.spawnWithWindowsHide>
+      expect(args).toEqual(["powershell.exe", "-NoProfile", "-Command", "Write-Host done"])
+    } finally {
+      spawnSpy.mockRestore()
+    }
+  })
+
+  it("uses pwsh when PowerShell is detected on non-Windows platforms", async () => {
+    // given
+    Object.defineProperty(process, "platform", { value: "linux" })
+    process.env.PSModulePath = "/usr/local/share/powershell/Modules"
+    delete process.env.SHELL
+    const spawnSpy = spyOn(spawnWithWindowsHideModule, "spawnWithWindowsHide").mockReturnValue(createProc(0))
+
+    try {
+      // when
+      await executeOnCompleteHook({
+        command: "Write-Host done",
+        sessionId: "session-123",
+        exitCode: 0,
+        durationMs: 5000,
+        messageCount: 10,
+      })
+
+      // then
+      const [args] = spawnSpy.mock.calls[0] as Parameters<typeof spawnWithWindowsHideModule.spawnWithWindowsHide>
+      expect(args).toEqual(["pwsh", "-NoProfile", "-Command", "Write-Host done"])
+    } finally {
+      spawnSpy.mockRestore()
+    }
+  })
+
+  it("falls back to cmd.exe on Windows when PowerShell is not detected", async () => {
+    // given
+    Object.defineProperty(process, "platform", { value: "win32" })
+    delete process.env.PSModulePath
+    delete process.env.SHELL
+    process.env.ComSpec = "C:\\Windows\\System32\\cmd.exe"
+    const spawnSpy = spyOn(spawnWithWindowsHideModule, "spawnWithWindowsHide").mockReturnValue(createProc(0))
+
+    try {
+      // when
+      await executeOnCompleteHook({
+        command: "echo done",
+        sessionId: "session-123",
+        exitCode: 0,
+        durationMs: 5000,
+        messageCount: 10,
+      })
+
+      // then
+      const [args] = spawnSpy.mock.calls[0] as Parameters<typeof spawnWithWindowsHideModule.spawnWithWindowsHide>
+      expect(args).toEqual(["C:\\Windows\\System32\\cmd.exe", "/d", "/s", "/c", "echo done"])
+    } finally {
+      spawnSpy.mockRestore()
+    }
+  })
+
   it("env var values are strings", async () => {
     // given
     const spawnSpy = spyOn(spawnWithWindowsHideModule, "spawnWithWindowsHide").mockReturnValue(createProc(0))

src/cli/run/on-complete-hook.ts

@@ -1,5 +1,5 @@
 import { spawnWithWindowsHide } from "../../shared/spawn-with-windows-hide"
-import { log } from "../../shared"
+import { detectShellType, log } from "../../shared"
 
 async function readOutput(
   stream: ReadableStream<Uint8Array> | undefined,
@@ -20,6 +20,24 @@ async function readOutput(
   }
 }
 
+function resolveHookShellCommand(command: string): string[] {
+  const shellType = detectShellType()
+
+  switch (shellType) {
+    case "powershell": {
+      const powershellExecutable = process.platform === "win32" ? "powershell.exe" : "pwsh"
+      return [powershellExecutable, "-NoProfile", "-Command", command]
+    }
+    case "cmd":
+      return [process.env.ComSpec || "cmd.exe", "/d", "/s", "/c", command]
+    case "csh":
+      return ["csh", "-c", command]
+    case "unix":
+    default:
+      return ["sh", "-c", command]
+  }
+}
+
 export async function executeOnCompleteHook(options: {
   command: string
   sessionId: string
@@ -37,7 +55,8 @@ export async function executeOnCompleteHook(options: {
   log("Running on-complete hook", { command: trimmedCommand })
 
   try {
-    const proc = spawnWithWindowsHide(["sh", "-c", trimmedCommand], {
+    const shellCommand = resolveHookShellCommand(trimmedCommand)
+    const proc = spawnWithWindowsHide(shellCommand, {
       env: {
         ...process.env,
         SESSION_ID: sessionId,