fix(ai): prioritize Groq's most stable model, stop repeating mining disclaimer (#9)

mirror of https://github.com/pezkuwichain/pezkuwi-telegram-miniapp.git synced 2026-08-01 09:15:42 +00:00

User decision after the Groq reliability fix (previous PR): prioritize
Groq's smallest/fastest model, llama-3.1-8b-instant, over gpt-oss-120b —
it's long out of preview and has historically the best free-tier
availability, at the cost of gpt-oss-120b's better Turkish/Kurdish
fluency (which is why it was chosen originally). Model order is now
llama-3.1-8b-instant -> gpt-oss-120b -> llama-3.3-70b-versatile before
the (currently uncredited) Anthropic fallback.

Also fixed a real UX complaint: asking about the Mining Simulation made
the model repeat "this isn't real mining / it's just an estimate" in
nearly every paragraph. Added an explicit instruction to state that once,
briefly, near the start of the answer, and not repeat it — verified live,
the disclaimer now appears once per response instead of several times.

This commit is contained in:

SatoshiQaziMuhammed

2026-07-21 07:52:59 -07:00

committed by

GitHub

parent 9bb9d2cda3

commit 54c94c7558

4 changed files with 32 additions and 18 deletions

									
										src/version.json
									
		+3
		-3
	
												View File
												
				@@ -1,5 +1,5 @@

				{

				  "version": "1.0.241",

				  "buildTime": "2026-07-21T14:31:14.612Z",

				  "buildNumber": 1784644274612

				  "version": "1.0.242",

				  "buildTime": "2026-07-21T14:51:23.002Z",

				  "buildNumber": 1784645483003

				}