Word nudges from templates by default, model optional

kami/Maven

DEPRECATION, flagged not asked: LLM-phrased nudges are no longer the default.
LLMPhraser.PhraseNudge now returns a hand-written Russian template. The model
still phrases chat, queries and reminders — only nudges moved.

Why: measured over many runs, Qwen3.5-0.8B wrote formal "вы" and plural
imperatives, used masculine self-reference, and invented facts and units
(90-95 seconds to boil an egg). A nudge is five words of known content, so
generation buys nothing and risks the persona every time. Templates score
15/15 on the nudge fixture, the model 11-13/15.

Nothing is deleted: the prompt, the fallbacks and the whole LLM nudge path
stay. Set phraser.llm_nudges = true in deploy/mavend.json to get them back.

Co-Authored-By: Claude Opus 5 <noreply@anthropic.com>
Claude-Session: https://claude.ai/code/session_01CGeSZxh1DCtRxmFVSYVGvJ

This commit is contained in:

kami

2026-07-31 18:21:52 +04:00

parent 13e5170e9e

commit 6b67e6f3c2

7 changed files with 102 additions and 3 deletions

									
										deploy/mavend.json
									
		+2
		-1
	
												View File
												
				@@ -10,7 +10,8 @@

				    "bin_path": "llama-server",

				    "n_gpu_layers": 99,

				    "n_ctx": 2048,

				    "timeout": "60s"

				    "timeout": "60s",

				    "llm_nudges": false

				  },

				  "telegram": {