diff --git a/ai/setup.py b/ai/setup.py index 04ac4ec..44b63df 100644 --- a/ai/setup.py +++ b/ai/setup.py @@ -74,47 +74,55 @@ def select_best_models(force_refresh=False): model = genai.GenerativeModel(bootstrapper) prompt = f""" ROLE: AI Model Architect - TASK: Select the optimal Gemini models for a book-writing application. Prefer newer Gemini 2.x models when available. + TASK: Select the optimal Gemini models for a book-writing application. + PRIMARY OBJECTIVE: Keep total book generation cost under $2.00. Quality is secondary to this budget. AVAILABLE_MODELS: {json.dumps(compatible)} - PRICING_CONTEXT (USD per 1M tokens, approximate — TIER determines preference): - - FREE TIER: Models with 'exp', 'beta', or 'preview' in name are typically free experimental tiers. - e.g. gemini-2.0-pro-exp = FREE. Use these whenever they exist. - - Gemini 2.5 Flash: ~$0.075 Input / $0.30 Output. Fast and very capable. - - Gemini 2.0 Flash: ~$0.10 Input / $0.40 Output. Cost-effective, excellent quality. - - Gemini 1.5 Flash: ~$0.075 Input / $0.30 Output. Legacy, still reliable. - - Gemini 2.5 Pro (stable/latest): ~$1.25+ Input / $5.00+ Output. EXPENSIVE — avoid unless free/exp. - - Gemini 1.5 Pro (stable): ~$1.25 Input / $5.00 Output. EXPENSIVE — avoid. + PRICING_CONTEXT (USD per 1M tokens — use these to calculate actual book cost): + - FREE TIER: Any model with 'exp', 'beta', or 'preview' in name = $0.00. Always prefer these. + e.g. gemini-2.0-pro-exp = FREE, gemini-2.5-pro-preview = FREE. + - gemini-2.5-flash / gemini-2.5-flash-preview: ~$0.075 Input / $0.30 Output. + - gemini-2.0-flash: ~$0.10 Input / $0.40 Output. + - gemini-1.5-flash: ~$0.075 Input / $0.30 Output. + - gemini-2.5-pro (stable, non-preview): ~$1.25 Input / $10.00 Output. BUDGET BREAKER. + - gemini-1.5-pro (stable): ~$1.25 Input / $5.00 Output. BUDGET BREAKER. - CRITERIA (cost is the primary constraint): - - LOGIC: Needs JSON adherence, plot consistency, instruction following. - -> Prefer by EFFECTIVE COST: Free/Exp Pro (e.g. 2.0-pro-exp) > Flash 2.5 > Flash 2.0 > Flash 1.5 > paid Pro (AVOID) - -> Rule: A free Pro beats Flash. A paid Pro loses to any Flash. - - WRITER: Needs creativity, prose quality, long-form text generation. Flash is sufficient for prose. - -> Prefer: Flash 2.5 > Flash 2.0 > Flash 1.5. Do NOT use Pro — Flash quality is adequate for fiction writing. - - ARTIST: Needs visual description and prompt quality for cover art design. - -> Prefer: Flash 2.0 > Flash 1.5 (speed and visual understanding) + BOOK TOKEN BUDGET (30-chapter novel — use this to calculate real cost before deciding): + Logic role total: ~265,000 input tokens + ~55,000 output tokens + (planning, state tracking, consistency checks, director treatments per chapter) + Writer role total: ~450,000 input tokens + ~135,000 output tokens + (drafting, evaluation, refinement per chapter — 2 passes max) + Artist role total: ~20,000 input tokens + ~5,000 output tokens (cover + marketing copy) - CONSTRAINTS: - - A free/experimental Pro model is ALWAYS preferred over Flash for the Logic role. - - Flash is ALWAYS preferred over a paid Pro model for ALL roles. - - Strongly prefer Gemini 2.x over 1.5 where available. - - 'thinking' models are too slow/expensive for any role. - - Provide a ranking of ALL available models from best to worst overall. + COST FORMULA: cost = (input_tokens / 1,000,000 * input_price) + (output_tokens / 1,000,000 * output_price) + HARD BUDGET: Logic_cost + Writer_cost + Artist_cost must be < $2.00 total. + + SELECTION RULES (apply in order): + 1. FREE FIRST: If a free/exp model exists (any tier, any quality), pick it for Logic. Cost = $0. + 2. FLASH FOR WRITER: Flash is sufficient for fiction prose. Never pick a paid Pro for Writer. + 3. CALCULATE: For non-free models, compute the actual book cost using the token budget above. + Reject any combination that exceeds $2.00 total. + 4. QUALITY TIEBREAK: Among models with similar cost, prefer newer generation (2.x > 1.5). + 5. NO THINKING MODELS: Too slow and expensive for any role. + + ROLES: + - LOGIC: Planning, JSON adherence, plot consistency. Free/exp Pro ideal; Flash acceptable. + - WRITER: Creative prose, chapter drafting. Flash 2.x is sufficient — do NOT use paid Pro. + - ARTIST: Visual prompts for cover art. Cheapest capable Flash model. + - PRO_REWRITE: Emergency full-chapter rewrite (rare, ~1-2x per book). Best free/exp Pro available. + If no free Pro exists, use best Flash — do not use paid Pro even here. OUTPUT_FORMAT (JSON only, no markdown): {{ - "logic": {{ "model": "string", "reason": "string", "estimated_cost": "$X.XX/1M" }}, - "writer": {{ "model": "string", "reason": "string", "estimated_cost": "$X.XX/1M" }}, - "artist": {{ "model": "string", "reason": "string", "estimated_cost": "$X.XX/1M" }}, - "pro_rewrite": {{ "model": "string", "reason": "string", "estimated_cost": "$X.XX/1M" }}, + "logic": {{ "model": "string", "reason": "string", "estimated_cost": "$X.XX/1M", "book_cost": "$X.XX" }}, + "writer": {{ "model": "string", "reason": "string", "estimated_cost": "$X.XX/1M", "book_cost": "$X.XX" }}, + "artist": {{ "model": "string", "reason": "string", "estimated_cost": "$X.XX/1M", "book_cost": "$X.XX" }}, + "pro_rewrite": {{ "model": "string", "reason": "string", "estimated_cost": "$X.XX/1M", "book_cost": "$X.XX" }}, + "total_estimated_book_cost": "$X.XX", "ranking": [ {{ "model": "string", "reason": "string", "estimated_cost": "string" }} ] }} - - NOTE: "pro_rewrite" is the best available Pro model for rare, critical chapter rewrites. - Prefer free/experimental Pro (e.g. gemini-2.0-pro-exp) over paid Pro. If no Pro exists, use best Flash. """ try: @@ -182,20 +190,27 @@ def init_models(force=False): if not force: missing_costs = False for role in ['logic', 'writer', 'artist']: - if 'estimated_cost' not in selected_models.get(role, {}) or selected_models[role].get('estimated_cost') == 'N/A': + role_data = selected_models.get(role, {}) + if 'estimated_cost' not in role_data or role_data.get('estimated_cost') == 'N/A': missing_costs = True + if 'book_cost' not in role_data: + missing_costs = True + if 'total_estimated_book_cost' not in selected_models: + missing_costs = True if missing_costs: utils.log("SYSTEM", "⚠️ Missing cost info in cached models. Forcing refresh.") return init_models(force=True) def get_model_details(role_data): - if isinstance(role_data, dict): return role_data.get('model'), role_data.get('estimated_cost', 'N/A') - return role_data, 'N/A' + if isinstance(role_data, dict): + return role_data.get('model'), role_data.get('estimated_cost', 'N/A'), role_data.get('book_cost', 'N/A') + return role_data, 'N/A', 'N/A' - logic_name, logic_cost = get_model_details(selected_models['logic']) - writer_name, writer_cost = get_model_details(selected_models['writer']) - artist_name, artist_cost = get_model_details(selected_models['artist']) - pro_name, pro_cost = get_model_details(selected_models.get('pro_rewrite', {'model': 'models/gemini-2.0-pro-exp', 'estimated_cost': 'Free'})) + logic_name, logic_cost, logic_book = get_model_details(selected_models['logic']) + writer_name, writer_cost, writer_book = get_model_details(selected_models['writer']) + artist_name, artist_cost, artist_book = get_model_details(selected_models['artist']) + pro_name, pro_cost, _ = get_model_details(selected_models.get('pro_rewrite', {'model': 'models/gemini-2.0-pro-exp', 'estimated_cost': 'Free', 'book_cost': '$0.00'})) + total_book_cost = selected_models.get('total_estimated_book_cost', 'N/A') logic_name = logic_name if config.MODEL_LOGIC_HINT == "AUTO" else config.MODEL_LOGIC_HINT writer_name = writer_name if config.MODEL_WRITER_HINT == "AUTO" else config.MODEL_WRITER_HINT @@ -206,7 +221,8 @@ def init_models(force=False): models.artist_model_name = artist_name models.pro_model_name = pro_name - utils.log("SYSTEM", f"Models: Logic={logic_name} ({logic_cost}) | Writer={writer_name} ({writer_cost}) | Artist={artist_name} | Pro-Rewrite={pro_name} ({pro_cost})") + utils.log("SYSTEM", f"Models: Logic={logic_name} ({logic_cost}, {logic_book}/book) | Writer={writer_name} ({writer_cost}, {writer_book}/book) | Artist={artist_name} | Pro-Rewrite={pro_name} ({pro_cost})") + utils.log("SYSTEM", f"💰 Estimated book generation cost: {total_book_cost} (budget: $2.00)") utils.update_pricing(logic_name, logic_cost) utils.update_pricing(writer_name, writer_cost)