feat(core): Optional Support for Jinja2 Unrestricted

[keenborder786]

• Description: Optional Support for Jinja2 Unrestricted
• Issue: Jinja2 loop.index0 blocked by RestrictedSandboxedEnvironment when using template_format="jinja2" #34052

[codspeed-hq]

CodSpeed Performance Report

Merging #34054 will degrade performances by 24.18%

_{Comparing keenborder786:feat/jinja_2_unrestricted (bb7c929) with master (525d5c0)¹}

⚠️ Unknown Walltime execution environment detected

Using the Walltime instrument on standard Hosted Runners will lead to inconsistent data.

For the most accurate results, we recommend using CodSpeed Macro Runners: bare-metal machines fine-tuned for performance measurement consistency.

Summary

❌ 6 regressions
✅ 7 untouched
⏩ 21 skipped²

⚠️ Please fix the performance issues or acknowledge them on CodSpeed.

Benchmarks breakdown

	Mode	Benchmark	BASE	HEAD	Change
❌	WallTime	test_async_callbacks_in_sync	18.4 ms	24.3 ms	-24.18%
❌	WallTime	test_import_time[BaseChatModel]	468.8 ms	528 ms	-11.21%
❌	WallTime	test_import_time[HumanMessage]	236.9 ms	265.2 ms	-10.65%
❌	WallTime	test_import_time[PydanticOutputParser]	465.9 ms	528.5 ms	-11.84%
❌	WallTime	test_import_time[Runnable]	444.2 ms	504.4 ms	-11.94%
❌	WallTime	test_import_time[tool]	451.6 ms	509 ms	-11.27%

Footnotes

1. No successful run was found on master (ee3373a) during the generation of this report, so 525d5c0 was used instead as the comparison base. There might be some changes unrelated to this pull request in this report. ↩

2. 21 benchmarks were skipped, so the baseline results were used instead. If they were deleted from the codebase, click here and archive them to remove them from the performance reports. ↩

[eyurtsev]

I don't want to introduce another format yet.

I'd prefer either reverting or relaxing, but going to wait for feedback from users for another 1-2 days.