7 Commits
Author SHA1 Message Date
Dhivya-Bharathy 2895163e81 fix: batch-3 E2E — skip optional-deps failures and fix remaining example bugs 2026-07-23 17:04:42 +05:30
Mervin Praison 53d3885415 Release v4.1.0 2026-01-31 08:34:24 +00:00
Mervin Praison 5a1256069f Release v3.5.1 2026-01-08 20:12:14 +00:00
Mervin Praison 0dfab2b8d9 Release v3.4.1 2026-01-08 14:36:54 +00:00
Mervin Praison 561c32ddd5 refactor: update model name from gpt-4o-mini to gpt-5-nano across all files 2025-08-08 07:52:37 +01:00
claude[bot]andMervin Praison 17f3aab1e1 refactor: complete moving HostedMCPServer to examples folder
- Add hosted_server.py to examples/python/custom_tools/
- Update documentation to clarify this is an example implementation
- Keep starlette dependency as it's still used by Agent.launch() for MCP

This makes HostedMCPServer an example implementation rather than
a core package component.

Co-authored-by: Mervin Praison <[email protected]>
2025-07-11 07:41:27 +00:00
claude[bot]andMervin Praison 894a95cfc2 feat: Add minimal latency tracking as custom tool for MCP servers
- Create standalone latency tracking tool without core file modifications
- Add multiple integration methods: tool, decorator, context manager, wrapper
- Provide comprehensive examples for different use cases
- Track planning, tool usage, and LLM generation phases
- Thread-safe implementation supporting concurrent requests

Closes #733

Co-authored-by: Mervin Praison <[email protected]>
2025-07-05 07:30:32 +00:00