Commit History

fix: switch model back to gemini-2.5-flash per user request
a3ec5c7

Sanket22g commited on

fix: initialize raw variable to avoid UnboundLocalError during 429 quota exceptions, and switch to gemini-2.0-flash for higher daily limit
8087b81

Sanket22g commited on

fix: use strict=False in json.loads to gracefully handle literal newlines
b625b13

Sanket22g commited on

chore: add raw output to fallback rationale for debugging
5e9094f

Sanket22g commited on

fix: prompt formatting to avoid literal newlines in json strings
2f4e961

Sanket22g commited on

feat: migrate to google-genai SDK for reliable JSON response
6db567d

Sanket22g commited on

fix: robust JSON extraction for gemini-2.5-flash responses
5bd351c

Sanket22g commited on

feat: upgrade to gemini-2.5-flash model
2564428

Sanket22g commited on

chore: restart to pick up new GEMINI_API_KEY secret
b53e7b7

Sanket22g commited on

fix: pin google-generativeai==0.8.3, system_instruction in model constructor
616229b

Sanket22g commited on

fix: move system_instruction to model constructor (Gemini SDK compat)
9536fd5

Sanket22g commited on

feat: Vera bot - FastAPI + Gemini 2.0 Flash, 4-context composer, auto-reply detection
69eb640

Sanket22g commited on