Marius Popa dc365a1b27 Fix Ollama agent single-token responses (#1591) ...

Agent mode treated local /v1 endpoints, including Ollama on :11434, as native-tool-capable by host/model heuristics. On Ollama's OpenAI-compatible surface some models that advertise tool support stop after a single token when schemas are sent (issue #1567). Default local Ollama /v1 back to fenced tool blocks unless the endpoint explicitly has supports_tools=True.

Also compare both the runtime chat URL and the normalized endpoint base when reading ModelEndpoint.supports_tools. That keeps a saved base URL such as http://localhost:11434/v1 effective when the active session URL is /v1/chat/completions.

Tests: .venv/bin/python -m pytest tests/test_tool_support_heuristic.py

2026-06-04 11:45:10 +01:00

5.8 KiB

Raw Permalink Blame History

View Raw