jpmschweitzerandClaude Opus 4.5 ba195e401a fix: reduce Tatlock's excessive apologizing ...

Strengthened personality prompt to prevent unnecessary apologies after
successful Librarian delegations. Added explicit "do NOT apologize"
instructions to both system prompt and synthesis prompt.

🤖 Generated with [Claude Code](https://claude.com/claude-code)

Co-Authored-By: Claude Opus 4.5 <noreply@anthropic.com>

2025-12-23 17:52:19 +01:00

..

biographer

fix: Ollama message sanitization and streaming think slugs

2025-12-16 00:19:03 +01:00

housekeeper

feat: optimize Housekeeper for Mistral-Nemo tool calling

2025-12-18 20:58:39 +01:00

librarian

fix: prevent Librarian from fabricating information

2025-12-22 10:28:13 +01:00

steward

feat: integrate tracing throughout request pipeline

2025-12-22 10:26:37 +01:00

tatlock_core

feat: migrate web search from tatlock_core to Librarian

2025-12-15 18:30:16 +01:00

__init__.py

Add agent interface and model implementations

2025-12-06 19:36:53 +01:00

base.py

Add agent interface and model implementations

2025-12-06 19:36:53 +01:00

coordination.py

feat(phase3): add multi-agent coordination engine

2025-12-11 21:29:03 +01:00

delegation.py

feat: integrate tracing throughout request pipeline

2025-12-22 10:26:37 +01:00

lorem_tester.py

Add agent interface and model implementations

2025-12-06 19:36:53 +01:00

orchestration.py

fix: remove <think> wrappers from think messages

2025-12-16 09:12:17 +01:00

protocol.py

feat(phase3): add agent communication protocol

2025-12-11 21:26:52 +01:00

registry.py

rename to Tatlock

2025-12-06 20:59:15 +01:00

tatlock.py

fix: reduce Tatlock's excessive apologizing

2025-12-23 17:52:19 +01:00

tools.py

feat: migrate web search from tatlock_core to Librarian

2025-12-15 18:30:16 +01:00