thethreemagi/bookapp
1
0
Fork 0
Code Issues Pull Requests Actions Packages Projects Releases Wiki Activity

feat: Prefer Flash models in auto-selection criteria for cost reduction

Browse Source
This commit is contained in:
Mike Wichers
2026-02-22 10:33:38 -05:00
parent 353dc859d2
commit 74cc66eed3
1 changed files with 6 additions and 5 deletions
Download Patch File Download Diff File Expand all files Collapse all files

11
ai/setup.py
View File

@@ -34,7 +34,7 @@ def get_optimal_model(base_type="pro"):
def get_default_models():
return {
"logic": {"model": "models/gemini-2.0-pro-exp", "reason": "Fallback: Gemini 2.0 Pro for complex reasoning and JSON adherence.", "estimated_cost": "$0.00/1M (Experimental)"},
"logic": {"model": "models/gemini-2.0-flash", "reason": "Fallback: Gemini 2.0 Flash for cost-effective logic and JSON adherence.", "estimated_cost": "$0.10/1M"},
"writer": {"model": "models/gemini-2.0-flash", "reason": "Fallback: Gemini 2.0 Flash for fast, high-quality creative writing.", "estimated_cost": "$0.10/1M"},
"artist": {"model": "models/gemini-2.0-flash", "reason": "Fallback: Gemini 2.0 Flash for visual prompt design.", "estimated_cost": "$0.10/1M"},
"ranking": []
@@ -86,17 +86,18 @@ def select_best_models(force_refresh=False):
- Gemini 1.5 Pro: ~$1.25 Input / $5.00 Output. (Legacy, expensive).
CRITERIA:
- LOGIC: Needs complex reasoning, strict JSON adherence, plot consistency, and instruction following.
-> Prefer: Gemini 2.5 Pro > 2.0 Pro > 2.0 Flash > 1.5 Pro
- LOGIC: Needs JSON adherence, plot consistency, and instruction following. COST IS THE PRIORITY — use Flash unless no Flash 2.x exists.
-> Prefer: Gemini 2.5 Flash > 2.0 Flash > 1.5 Flash > 2.5 Pro > 2.0 Pro > 1.5 Pro
- WRITER: Needs creativity, prose quality, long-form text generation, and speed.
-> Prefer: Gemini 2.5 Flash/Pro > 2.0 Flash > 1.5 Flash (balance quality/cost)
-> Prefer: Gemini 2.5 Flash > 2.0 Flash > 1.5 Flash (balance quality/cost; avoid Pro)
- ARTIST: Needs rich visual description, prompt understanding for cover art design.
-> Prefer: Gemini 2.0 Flash > 1.5 Flash (speed and visual understanding)
CONSTRAINTS:
- Strongly prefer Flash over Pro for all roles — Pro models are expensive and only used selectively at runtime for critical rewrites.
- Strongly prefer Gemini 2.x over 1.5 where available.
- Avoid 'experimental' or 'preview' only if a stable 2.x version exists; otherwise experimental 2.x is fine.
- 'thinking' models are too slow/expensive for Writer/Artist roles.
- 'thinking' models are too slow/expensive for any role.
- Provide a ranking of ALL available models from best to worst overall.
OUTPUT_FORMAT (JSON only, no markdown):