viktorking7
fc0b3e9a1a
Update tool_use_multiturn_server.py
2025-09-27 13:47:07 +02:00
pre-commit-ci[bot]
321478dd5f
[pre-commit.ci] auto fixes from pre-commit.com hooks
...
for more information, see https://pre-commit.ci
2025-08-12 06:45:36 +00:00
interstellarninja
2f6025e65b
fixing precommit formatting errors
2025-08-12 02:42:47 -04:00
pre-commit-ci[bot]
0d05750841
[pre-commit.ci] auto fixes from pre-commit.com hooks
...
for more information, see https://pre-commit.ci
2025-07-24 10:58:41 +00:00
interstellarninja
12d77a1e44
fixing precommit errors
2025-07-24 06:53:41 -04:00
interstellarninja
9ea8ce26c6
Merge branch 'feat/multiturn_tool_use_env' of github.com:interstellarninja/atropos into feat/multiturn_tool_use_env
2025-06-27 01:41:55 -04:00
interstellarninja
b162813048
allowing only one think block
2025-06-26 23:20:30 -04:00
pre-commit-ci[bot]
34d45d2445
[pre-commit.ci] auto fixes from pre-commit.com hooks
...
for more information, see https://pre-commit.ci
2025-06-26 17:12:42 +00:00
interstellarninja
ee8755c388
using scenario for single, multistep and multiturn tool calls
2025-06-26 13:11:43 -04:00
interstellarninja
45bc484931
option to generate all gpt turns
2025-06-24 08:14:14 -04:00
interstellarninja
60be1bbbe8
BaseConfigEnv subclass for experimental variables
2025-06-06 04:46:53 -04:00
interstellarninja
c5b161764c
Fix tool calling turn filtering in multiturn environment
...
- Change filtering from >= to == MAX_TOOL_CALL_TURNS to ensure exact match
- Add VALIDATE_THINK_BLOCKS flag for optional <think> block validation
- Refactor data structure from flat expected_calls to turn-based expected_calls_by_turn
- Extract helper methods from collect_trajectories for better code organization
- Fix Turn 3 issue where prompts ended with tool responses instead of generating tool calls
🤖 Generated with [Claude Code](https://claude.ai/code )
Co-Authored-By: Claude <noreply@anthropic.com>
2025-06-05 10:49:29 -04:00
interstellarninja
fdfe23ea39
creating multi-turn tool-use rl environment
2025-06-04 14:13:01 -04:00
