name: LLM Hello World

on:
  workflow_dispatch:
    inputs:
      pr_number:
        description: "PR number to review"
        required: true
        type: number
      phase:
        description: "Which phase to run"
        required: true
        type: choice
        options:
          - hello-world
          - token-probe
        default: hello-world

env:
  LLM_ENDPOINT: "https://models.github.ai/inference/chat/completions"
  LLM_MODEL: "openai/gpt-4.1"

permissions:
  contents: read
  pull-requests: write
  models: read

jobs:
  hello-world:
    if: ${{ inputs.phase == 'hello-world' }}
    runs-on: ubuntu-latest
    steps:
      - name: Checkout repository
        uses: actions/checkout@v4

      - name: Fetch PR details
        id: pr
        env:
          GH_TOKEN: ${{ secrets.GITHUB_TOKEN }}
        run: |
          echo "Fetching PR #${{ inputs.pr_number }}..."

          # Fetch PR title and body
          PR_JSON=$(gh pr view ${{ inputs.pr_number }} --json title,body,author)

          if [ $? -ne 0 ]; then
            echo "::error::Failed to fetch PR #${{ inputs.pr_number }}. Does it exist?"
            exit 1
          fi

          PR_TITLE=$(echo "$PR_JSON" | jq -r '.title')
          PR_BODY=$(echo "$PR_JSON" | jq -r '.body // "No description provided"')
          PR_AUTHOR=$(echo "$PR_JSON" | jq -r '.author.login')

          echo "PR Title: $PR_TITLE"
          echo "PR Author: $PR_AUTHOR"

          # Store for next step (escape newlines for multiline)
          {
            echo "title<<EOF"
            echo "$PR_TITLE"
            echo "EOF"
          } >> $GITHUB_OUTPUT

          {
            echo "body<<EOF"
            echo "$PR_BODY"
            echo "EOF"
          } >> $GITHUB_OUTPUT

          echo "author=$PR_AUTHOR" >> $GITHUB_OUTPUT

      - name: Call LLM for summary
        id: llm
        env:
          GITHUB_TOKEN: ${{ secrets.GITHUB_TOKEN }}
        run: |
          echo "Calling LLM to summarize PR..."

          # Build the prompt
          PROMPT="Summarize this PR in one sentence.

          Title: ${{ steps.pr.outputs.title }}

          Description:
          ${{ steps.pr.outputs.body }}"

          # Escape for JSON
          PROMPT_ESCAPED=$(echo "$PROMPT" | jq -Rs .)

          # Call the LLM
          RESPONSE=$(curl -s -w "\n%{http_code}" -X POST "$LLM_ENDPOINT" \
            -H "Authorization: Bearer $GITHUB_TOKEN" \
            -H "Content-Type: application/json" \
            -d "{
              \"model\": \"$LLM_MODEL\",
              \"messages\": [
                {\"role\": \"system\", \"content\": \"You are a helpful assistant that summarizes pull requests concisely.\"},
                {\"role\": \"user\", \"content\": $PROMPT_ESCAPED}
              ],
              \"max_tokens\": 150
            }")

          # Extract HTTP status code (last line)
          HTTP_CODE=$(echo "$RESPONSE" | tail -n1)
          BODY=$(echo "$RESPONSE" | sed '$d')

          echo "HTTP Status: $HTTP_CODE"

          if [ "$HTTP_CODE" != "200" ]; then
            echo "::error::LLM API call failed with status $HTTP_CODE"
            echo "Response: $BODY"
            exit 1
          fi

          # Extract the summary from the response
          SUMMARY=$(echo "$BODY" | jq -r '.choices[0].message.content')

          echo "LLM Summary: $SUMMARY"

          {
            echo "summary<<EOF"
            echo "$SUMMARY"
            echo "EOF"
          } >> $GITHUB_OUTPUT

      - name: Post comment to PR
        env:
          GH_TOKEN: ${{ secrets.GITHUB_TOKEN }}
          SUMMARY: ${{ steps.llm.outputs.summary }}
          AUTHOR: ${{ steps.pr.outputs.author }}
          PR_NUM: ${{ inputs.pr_number }}
        run: |
          echo "Posting comment to PR #$PR_NUM..."

          gh pr comment "$PR_NUM" --body "$(cat <<EOF
          ## LLM Hello World Test

          **Model:** \`$LLM_MODEL\`
          **PR Author:** @$AUTHOR

          ### Summary
          $SUMMARY

          ---
          *This comment was generated by the LLM Hello World workflow (Phase 0a)*
          EOF
          )"

          echo "Comment posted successfully!"

  token-probe:
    if: ${{ inputs.phase == 'token-probe' }}
    runs-on: ubuntu-latest
    steps:
      - name: Probe token limits
        env:
          GITHUB_TOKEN: ${{ secrets.COPILOT_PAT || secrets.GITHUB_TOKEN }}
        run: |
          echo "=== Token Limit Probe ==="
          echo "Testing progressively larger payloads to find the ceiling"
          echo ""

          # Test sizes in characters (roughly 4 chars per token)
          SIZES=(2000 4000 8000 16000 32000 64000)

          # Generate filler text (lorem ipsum style)
          generate_filler() {
            local size=$1
            python3 -c "print(('The quick brown fox jumps over the lazy dog. ' * ($size // 45 + 1))[:$size])"
          }

          echo "| Size (chars) | ~Tokens | HTTP Status | Result |"
          echo "|--------------|---------|-------------|--------|"

          for SIZE in "${SIZES[@]}"; do
            APPROX_TOKENS=$((SIZE / 4))

            # Generate payload of specified size
            FILLER=$(generate_filler $SIZE)

            PROMPT="Respond with exactly one word: 'received'. Here is padding text to test token limits: $FILLER"
            PROMPT_ESCAPED=$(echo "$PROMPT" | jq -Rs .)

            # Call the LLM
            RESPONSE=$(curl -s -w "\n%{http_code}" -X POST "$LLM_ENDPOINT" \
              -H "Authorization: Bearer $GITHUB_TOKEN" \
              -H "Content-Type: application/json" \
              -d "{
                \"model\": \"$LLM_MODEL\",
                \"messages\": [
                  {\"role\": \"user\", \"content\": $PROMPT_ESCAPED}
                ],
                \"max_tokens\": 10
              }" 2>/dev/null)

            HTTP_CODE=$(echo "$RESPONSE" | tail -n1)
            BODY=$(echo "$RESPONSE" | sed '$d')

            if [ "$HTTP_CODE" = "200" ]; then
              RESULT="OK"
            else
              # Extract error message if present
              ERROR_MSG=$(echo "$BODY" | jq -r '.error.message // .message // "Unknown error"' 2>/dev/null | head -c 50)
              RESULT="FAIL: $ERROR_MSG"

              # Log full error for debugging
              echo ""
              echo "::warning::Failed at ${SIZE} chars (~${APPROX_TOKENS} tokens)"
              echo "Full error response:"
              echo "$BODY" | jq . 2>/dev/null || echo "$BODY"
              echo ""
            fi

            echo "| $SIZE | ~$APPROX_TOKENS | $HTTP_CODE | $RESULT |"

            # Stop probing after first failure to avoid hammering the API
            if [ "$HTTP_CODE" != "200" ]; then
              echo ""
              echo "=== Ceiling Found ==="
              echo "Last successful size: $((SIZE / 2)) chars (~$((SIZE / 8)) tokens)"
              echo "First failure at: $SIZE chars (~$APPROX_TOKENS tokens)"
              break
            fi

            # Small delay to avoid rate limiting
            sleep 1
          done

          echo ""
          echo "=== Probe Complete ==="