UPDATE_YOUR_SPACE_NOW.txt

═══════════════════════════════════════════════════════════════════════
   SIMPLE FIX - UPDATE YOUR SPACE (Takes 2 Minutes)
═══════════════════════════════════════════════════════════════════════

PROBLEM: Still getting timeout errors even with token set
CAUSE: Code is still using local models (setdefault doesn't force override)
SOLUTION: Replace with direct assignment to force HF API mode

───────────────────────────────────────────────────────────────────────
STEP 1: Open Your Space
───────────────────────────────────────────────────────────────────────

1. Go to your HuggingFace Space
2. Click "Files" tab
3. Click "app.py" to edit

───────────────────────────────────────────────────────────────────────
STEP 2: Find and Replace Lines 140-170
───────────────────────────────────────────────────────────────────────

FIND THIS (around line 140-170):

    # Set defaults for HuggingFace Spaces (can be overridden with Spaces Variables)
    os.environ.setdefault("USE_HF_API", "False")
    os.environ.setdefault("USE_LMSTUDIO", "False")
    os.environ.setdefault("DEBUG_MODE", os.getenv("DEBUG_MODE", "False"))
    os.environ.setdefault("LLM_BACKEND", "local")
    os.environ.setdefault("LLM_TIMEOUT", "120")
    os.environ.setdefault("MAX_TOKENS_PER_REQUEST", "1500")
    os.environ.setdefault("LLM_TEMPERATURE", "0.7")

    print("✅ Configuration loaded for HuggingFace Spaces")

    # Auto-detect HuggingFace Spaces and force HF API (...)
    # ... (about 20 more lines of auto-detection code)

REPLACE WITH THIS (copy exactly):

    # FORCE HF API for HuggingFace Spaces deployment
    # Local models timeout on free tier - always use HF API when deployed
    print("🚀 Forcing HF API mode for HuggingFace Spaces deployment...")
    os.environ["USE_HF_API"] = "True"
    os.environ["USE_LMSTUDIO"] = "False"
    os.environ["LLM_BACKEND"] = "hf_api"
    os.environ["DEBUG_MODE"] = os.getenv("DEBUG_MODE", "False")
    os.environ["LLM_TIMEOUT"] = "180"  # 3 minutes
    os.environ["MAX_TOKENS_PER_REQUEST"] = "1500"
    os.environ["LLM_TEMPERATURE"] = "0.7"

    # Check if HF token is set (required for HF API)
    hf_token = os.getenv("HUGGINGFACE_TOKEN", "")
    if not hf_token:
        print("="*70)
        print("⚠️  ERROR: HUGGINGFACE_TOKEN not set!")
        print("   This is REQUIRED for HF API mode to work.")
        print("   Add it in Space Settings → Repository Secrets")
        print("   Get token from: https://huggingface.co/settings/tokens")
        print("="*70)
    else:
        print("✅ HuggingFace token detected")

    print("✅ Configuration loaded for HuggingFace Spaces")

───────────────────────────────────────────────────────────────────────
STEP 3: Save and Commit
───────────────────────────────────────────────────────────────────────

1. Click "Commit changes to main"
2. Wait ~2 minutes for Space to restart

───────────────────────────────────────────────────────────────────────
STEP 4: Verify It Worked
───────────────────────────────────────────────────────────────────────

After restart, check the Logs tab. You should see:

    🚀 Forcing HF API mode for HuggingFace Spaces deployment...
    ✅ HuggingFace token detected
    ✅ Configuration loaded for HuggingFace Spaces
    🚀 TranscriptorAI Enterprise - LLM Backend: hf_api
    🔧 USE_HF_API: True

When processing a file, you should see:

    INFO: Calling HF API: microsoft/Phi-3-mini-4k-instruct
    (NOT "Generating with local model")

───────────────────────────────────────────────────────────────────────
KEY DIFFERENCE: setdefault vs direct assignment
───────────────────────────────────────────────────────────────────────

OLD (doesn't work):
    os.environ.setdefault("USE_HF_API", "False")  ← Won't override existing value

NEW (works):
    os.environ["USE_HF_API"] = "True"  ← Always sets it to True

───────────────────────────────────────────────────────────────────────
IF STILL NOT WORKING
───────────────────────────────────────────────────────────────────────

Add this as the FIRST LINE in the analyze() function (around line 178):

    def analyze(files, file_type, user_comments, role_hint, debug_mode, interviewee_type,
                enable_pii_redaction, redaction_level, progress=gr.Progress()):
        """..."""

        # FORCE HF API MODE - add this as first line
        os.environ["USE_HF_API"] = "True"
        os.environ["LLM_BACKEND"] = "hf_api"
        print("🚀🚀🚀 FORCED HF API IN ANALYZE FUNCTION")

        # ... rest of function ...

This ensures it's set RIGHT before processing starts.

───────────────────────────────────────────────────────────────────────
CHECKLIST
───────────────────────────────────────────────────────────────────────

□ Token added to Space Settings → Repository Secrets
□ Replaced lines 140-170 in app.py with new code
□ Committed changes
□ Space restarted
□ Logs show "USE_HF_API: True"
□ Logs show "Calling HF API" (not "local model")
□ Processing completes without timeout
□ Quality Score > 0.00

═══════════════════════════════════════════════════════════════════════
   IF ALL CHECKED: YOUR SPACE IS FIXED! 🎉
═══════════════════════════════════════════════════════════════════════