multi-agent-lab / docs /architecture

Commit History

feat: Add Hall of Fame leaderboard backed by a dedicated results table
c952d77

agharsallah Codex commited on

feat: Update model references to MiniCPM5 and adjust related documentation and tests for transformers 5.x compatibility
cc8e9f2

agharsallah commited on

Refactor local model configurations and update tests
572f5aa

agharsallah commited on

feat: Update model routing and local provider to support multi-sponsor tiers and auto-class resolution
7a13e4e

agharsallah commited on

feat: Implement early termination for the judge in Twenty Sprouts game and enhance event handling
0460922

agharsallah commited on

feat: Implement audience-only secret badge for Twenty Sprouts game
f6566bb

agharsallah commited on

feat: implement winner celebration overlay and judging mechanics
6432854

agharsallah commited on

feat: Replace llama.cpp backend with in-process transformers backend for local GPU inference
7d636f8

agharsallah commited on

feat: Implement llama.cpp backend for local inference with GGUF models
0f11b49

agharsallah commited on

Merge remote-tracking branch 'origin/main' into worktree-scenarios
1c7b5c9

agharsallah commited on

feat: make every scenario arena-grade with a competition contract
0d0c561

agharsallah Codex commited on

feat: Implement well-known typed fields for verdicts in output models
ce159dc

agharsallah commited on

feat(roadmap): add comprehensive arena roadmap outlining sessions, winners, and leaderboard features
7066a96

agharsallah commited on

feat: update agent personas and scheduling in YAML configurations; enhance event handling and memory deduplication in core logic
27b304e

agharsallah commited on

feat(observability): add OpenTelemetry logging/tracing/metrics foundation
3f7b296

agharsallah Codex commited on

feat(core): add resilient loop and shared blackboard
ba6dd5f

agharsallah Codex commited on

feat: Enhance model routing and deployment flexibility
c1656a8

agharsallah commited on

feat: add the-steeped spy-game scenario (word-pair bluff)
1896ef4

agharsallah Codex commited on

docs: add as-built Fishbowl UI architecture page
0ce95fa

agharsallah Codex commited on

feat: add Fishbowl UI presenter layer and say-vs-think engine support
ade9df5

agharsallah Codex commited on

feat: add Fishbowl UI ADR and implementation plan for Gradio presenter layer
a13e4e8

agharsallah commited on

feat: add optional mem0 cloud backend for memory index and update documentation
c3f5c19

agharsallah commited on

feat: unify model catalogue and self-hosted routing
9dd6dab

agharsallah Codex commited on

feat: update model endpoint URLs and enhance documentation with mermaid diagrams
2a8eab2

agharsallah commited on

feat: add architecture review and scenario authoring documentation
49aa5c4

agharsallah commited on

feat: mem0 as a layered, derived semantic memory index
f487b74

agharsallah Codex commited on

feat: official MCP SDK as an optional tool transport
24b5ffb

agharsallah Codex commited on

feat: Instructor-validated structured output on the live path
99293d7

agharsallah Codex commited on

feat: LiteLLM gateway routing profiles to Modal-served small models
7df0a45

agharsallah Codex commited on

feat: env-gated Postgres event store via SQLAlchemy (layered)
98938c3

agharsallah Codex commited on

feat: update setup instructions and dependencies for uv integration
39e9569

agharsallah commited on

Refactor code structure for improved readability and maintainability
5424fe6

agharsallah commited on

feat: phase 2 architecture — manifest system, structured output, salience memory, SQLite ledger, observer
0d7db8e

agharsallah Codex commited on

feat: scaffold hackathon agent theater
42e32ed

agharsallah Codex commited on