fix(tinybard): add background pre-warming of Kokoro TTS on server startup

fix(tinybard): add requirements.txt at repository root for Hugging Face Spaces build

fix(tinybard): add libespeak-ng-dev and show_error=True for better HF error reporting

fix(tinybard): add system packages and pip requirements for TTS

fix(tinybard): unlock and reuse browser audio context to bypass autoplay block

feat(tinybard): strip progress and mood tags in clean_llm_story

feat(tinybard): improve pacing with five-sentence directive and step awareness

Release develop → main

Release develop → main

Merge docs/llms-dox-translate: translate PRD into DOX hierarchy

docs: translate PRD into DOX hierarchy

feat(tinybard): add Kokoro TTS audio with custom voices & option prefixes

docs: update llms.txt to v0.7.0 — context-aware LLM, verb-based choices, git workflow, Anishinaabe Solarpunk aesthetic

Merge branch 'develop'

feat: context-aware generation — verb-based choices, history-aware story, LLM health delta

fix(tinybard): use correct logger name (log not logger)

fix(tinybard): simplify choice prompt for 1.5B model

fix(tinybard): robust choice parsing — 3 strategies + fallback padding

Merge branch 'develop'

fix: LLM inference uniqueness — force-clear cooldown, deduplicate click handlers, Nanaboozhoo narrator

fix: pin huggingface_hub>=0.36 to avoid old router endpoint

fix: pass model at chat_completion call time, not constructor (HF router fix)

fix: use Llama-3.2-1B-Instruct (free HF Inference), auto-detect provider

Merge branch 'develop'

feat: Anishinaabe Solarpunk Gradio UI with choice input, save/load, and CRT aesthetic

fix: skip uvicorn on HF Spaces, use demo.launch() instead

fix: import BaseModel from pydantic for UserConfig class

fix: restore HF Space YAML front matter in root README

feat: add hf-cli + ml-intern skills; fix tinybard None genre crash

fix: launch Gradio on default port, let HF reverse proxy handle PORT

fix: keep process alive on HF Spaces with sleep loop

fix: call demo.launch() on HF Spaces to keep process alive

fix: skip uvicorn on HF Spaces — Gradio launcher handles serving

fix: import BaseModel from pydantic for UserConfig class

fix: add YAML front matter to root README for HF Space config

Merge branch 'main' of https://github.com/nbiish/build-small-hackathon

merge: develop → main — TinyBard wire-models + save/exit + inference wiring

feat(tinybard): infinite play, save/load, exit button

merge: feat/wire-models-to-hf-spaces — wire TinyBard/CritterCalm/FocusFriend to HF Spaces + inference wiring

feat(tinybard): infinite play, save/load, exit button

feat: add projects/tinybard/modal_inference.py and update llms.txt

feat: add support for custom OpenAI-compatible endpoints in TinyBard

fix: target huggingface.co domain for serverless API to bypass DNS blocks

fix: resolve base_url and model conflict in InferenceClient

fix: route chat completions to free serverless Inference API

fix: lock default model to Qwen/Qwen2.5-1.5B-Instruct

fix: revert default model to Qwen/Qwen2.5-1.5B-Instruct

fix: use Qwen/Qwen2.5-7B-Instruct as default model

feat: upgrade default model to google/gemma-2-9b-it

feat: LLM-driven infinite adventure loop