feat(models): Allow reliable models and update model selection logic in UI

feat(session): finalize run on verdict and enhance leaderboard recording logic

feat(commentary): introduce universal rafters-critic for scenario commentary and cadence control

feat(lab): add roster model defaults merging to preserve user selections for newly added agents

Merge pull request #22 from abducodez/feat/hall-of-fame-leaderboard

feat: Add Hall of Fame leaderboard backed by a dedicated results table

feat(feed): update media rendering to use native components with badges instead of inline tags

feat(commentator): update cadence logic to use a fixed count instead of per-speaker quorum

feat(media): introduce MediaRouter and stubs for image and speech generation

feat: Update model references to MiniCPM5 and adjust related documentation and tests for transformers 5.x compatibility

Refactor local provider to support on-device loading with accelerate

feat: Add use_cache parameter to support KV cache handling in models and update tests

Refactor local model configurations and update tests

feat: Update model routing and local provider to support multi-sponsor tiers and auto-class resolution

feat: Ensure full materialization of model weights to prevent meta tensor issues in ZeroGPU

feat: Enhance Secret Keeper's response logic to confirm correct guesses and improve consistency in answers

feat: Implement early termination for the judge in Twenty Sprouts game and enhance event handling

feat: Enhance color handling and styling across fishbowl components

feat: Implement audience-only secret badge for Twenty Sprouts game

feat: implement winner celebration overlay and judging mechanics

Refactor modal service and logging setup

fix: Ensure proper unpacking of BatchEncoding in model generation to prevent AttributeError

feat: Replace llama.cpp backend with in-process transformers backend for local GPU inference

Implement local in-process inference backend for transformers models

feat: Implement llama.cpp backend for local inference with GGUF models

feat: Handle FP8 KV cache incompatibility with snapshot models in build command

Merge pull request #21 from abducodez/worktree-scenarios

feat: Add FP8 quantization support for model serving with environment overrides

Merge remote-tracking branch 'origin/main' into worktree-scenarios

feat: make every scenario arena-grade with a competition contract

feat: Implement well-known typed fields for verdicts in output models

feat: implement per-event model attribution for enhanced event tracking

Merge pull request #18 from abducodez/worktree-modal-check

Merge remote-tracking branch 'origin/main' into worktree-small-enhancement

feat: implement Archive feature for past session management

feat(fishbowl): badge each agent's model + auto-follow the live feed

feat(fishbowl): seed is a preset dropdown that fills an editable beat textbox

feat(fishbowl): scenario-adaptive Lab with per-agent & per-scenario config editing

feat: update agent personas and scheduling in YAML configurations; enhance event handling and memory deduplication in core logic

fix(modal): shorten cascade slug to fit DNS limit; add endpoint health tooling

feat: update HF model catalogue to prioritize chat-capable model and adjust tests for new routing logic

feat: require live infrastructure for event store and inference, removing offline mode

feat: refine structured output handling with guided decoding and mode adjustments

feat(observability): instrument models, conductor, memory, ledger (Units 2-6)

feat(observability): add OpenTelemetry logging/tracing/metrics foundation

feat: add Hugging Face inference backend next to Modal

feat(tests): add tests for handling first-person openers in clean_clue function

feat: implement streaming agent responses and enhance conversation flow with repeat guards

feat: enhance agent personas and improve model performance tuning

feat(core): add resilient loop and shared blackboard