Release v1.3.0

[digitallysavvy]

his PR brings Conversational AI Engine v2.5 capabilities to the Python AgentKit, with a focus on session presets, session analytics, and docs-safe MLLM behavior.

What’s included

• Added first-class AgentKit support for conversation turn analytics via AgentSession.get_turns().
• Bubbled session-level preset and pipeline_id through Agent.create_session(...) and start().
• Added exported AgentKit preset constants and normalization helpers for discoverable preset usage.
• Added preset normalization so preset can be passed as a comma-separated string or a sequence of preset IDs.
• Added automatic preset inference for supported reseller-backed models when credentials are omitted:
  • Deepgram STT: nova-2, nova-3
  • OpenAI LLM: gpt-4o-mini, gpt-4.1-mini, gpt-5-nano, gpt-5-mini
  • OpenAI TTS: tts-1
  • MiniMax TTS: speech-2.6-turbo, speech-2.8-turbo
• Preserved BYOK behavior for the same preset-capable models when credentials are provided.
• Added type-safe guardrails so missing credentials are only allowed for supported reseller-backed models.
• Brought MiniMax preset ergonomics in line with the other preset-backed wrappers by allowing the no-key preset path without forcing provider-specific fields.
• Restored DeepgramSTT() no-arg compatibility to avoid an accidental constructor break.
• Added missing high-level vendors and exports for:
  • GeminiLive
  • LiveAvatarAvatar
  • AnamAvatar
• Narrowed MLLM wrapper behavior to the Agora low-level contract, keeping the Python surface aligned with generated API shapes.
• Updated the core Pydantic compatibility layer for Python 3.14-safe behavior.
• Added focused tests for:
  • get_turns()
  • preset / pipeline_id forwarding
  • preset arrays
  • inferred reseller presets
  • vendor mapping and validation behavior
  • preset inference edge cases
  • low-level contract parity for MLLM, avatar, and TTS/STT wrappers

Why this matters

Developers can use the Python AgentKit high-level API for presets, turn analytics, and vendor wrappers without dropping down to raw generated APIs, while staying
aligned with the Agora low-level contract and keeping credential behavior predictable.

Validation

• PYTHONPATH=src .venv/bin/python -m pytest tests/agentkit -W default
• Result: 34 passed

[digitallysavvy]

new version @plutoless @BenWeekes @yannickbh