Smolagents

What's Changed
* Bump dev version: v1.9.0.dev0 by albertvillanova in https://github.com/huggingface/smolagents/pull/544
* Small update to 'Introduction to Agents' docs format by sergiopaniego in https://github.com/huggingface/smolagents/pull/548
* Doc grammar fix by juanqui in https://github.com/huggingface/smolagents/pull/556
* Minor grammar correction by doomspork in https://github.com/huggingface/smolagents/pull/528
* Fix multiagents docs by derekalia in https://github.com/huggingface/smolagents/pull/549
* Fix managed agent example by keetrap in https://github.com/huggingface/smolagents/pull/562
* Add authorized_imports in importFrom errors by CalOmnie in https://github.com/huggingface/smolagents/pull/506
* chore: fix some typos by zoupingshi in https://github.com/huggingface/smolagents/pull/557
* Minor fix in the guilded_tour docs by touseefahmed96 in https://github.com/huggingface/smolagents/pull/578
* Add small readme to open Deep Research by aymeric-roucher in https://github.com/huggingface/smolagents/pull/581
* Fixed Readme that is missing run.py call by jsmidt in https://github.com/huggingface/smolagents/pull/585
* Fix 429 Client Error: Too Many Requests in CI test by albertvillanova in https://github.com/huggingface/smolagents/pull/599
* Remove unused import in guided_tour docs by albertvillanova in https://github.com/huggingface/smolagents/pull/600
* Test evaluate_delete by albertvillanova in https://github.com/huggingface/smolagents/pull/519
* Move check_module_authorized out of import_module for use in get_safe_module by CalOmnie in https://github.com/huggingface/smolagents/pull/507
* Test agent call with provide_run_summary by albertvillanova in https://github.com/huggingface/smolagents/pull/513
* Create PromptTemplates typed dict by albertvillanova in https://github.com/huggingface/smolagents/pull/547
* Refactor and test final answer prompts by albertvillanova in https://github.com/huggingface/smolagents/pull/595
* Make question arg required in Open DeepResearch example by albertvillanova in https://github.com/huggingface/smolagents/pull/617
* Remove unused api-base arg from Open DeepResearch example by albertvillanova in https://github.com/huggingface/smolagents/pull/616
* corrected typo in README.md by blakkd in https://github.com/huggingface/smolagents/pull/609
* MLX model support by g-eoj in https://github.com/huggingface/smolagents/pull/300
* Add support for non-bool comparison operators. by kc9zyz in https://github.com/huggingface/smolagents/pull/612
* docs: add Langfuse OpenTelemetry guide by jannikmaierhoefer in https://github.com/huggingface/smolagents/pull/601
* Remove --prompt argument of instance instruction in README.md by leeivan1007 in https://github.com/huggingface/smolagents/pull/632
* Fix CI quality check by removing trailing whitespace by albertvillanova in https://github.com/huggingface/smolagents/pull/628
* Change math.pow -> pow by Bilokin in https://github.com/huggingface/smolagents/pull/624
* Move plan user prompt to YAML and test text of plan prompts by albertvillanova in https://github.com/huggingface/smolagents/pull/591
* Fix installation instructions in Open-DeepResearch README by albertvillanova in https://github.com/huggingface/smolagents/pull/633
* Remove ManagedAgent from doc by aymeric-roucher in https://github.com/huggingface/smolagents/pull/563
* Refactor operations count state setting by albertvillanova in https://github.com/huggingface/smolagents/pull/631
* LiteLLMModel - detect message flatenning based on model information by sysradium in https://github.com/huggingface/smolagents/pull/553
* Contribute to the documentation by seanxuu in https://github.com/huggingface/smolagents/pull/630
* Adding default parameter for max_new_tokens in TransformersModel by matfrei in https://github.com/huggingface/smolagents/pull/604
* Test evaluate_condition by albertvillanova in https://github.com/huggingface/smolagents/pull/634
* Allow Gradio share parameter passthrough by sysradium in https://github.com/huggingface/smolagents/pull/490
* Fix issue 635. Corrected installation instructions for open_deep_research by nishaddeokar in https://github.com/huggingface/smolagents/pull/636
* Share full agents by aymeric-roucher in https://github.com/huggingface/smolagents/pull/533
* Fix PlanningPromptTemplate and its docstring by albertvillanova in https://github.com/huggingface/smolagents/pull/648
* Fix evaluate_condition for non-bool result by albertvillanova in https://github.com/huggingface/smolagents/pull/638
* Removed reference to deprecated single_step in documentation by crumbly-blue-cheese in https://github.com/huggingface/smolagents/pull/608
* Update README.md by aymeric-roucher in https://github.com/huggingface/smolagents/pull/642
* Fix reference to Transformers in docs by sergiopaniego in https://github.com/huggingface/smolagents/pull/643
* Fix for MLX Model when stop sequence is followed by any chars by g-eoj in https://github.com/huggingface/smolagents/pull/623
* Allow for last_input_token_count=None by Strings-RH in https://github.com/huggingface/smolagents/pull/644

New Contributors
* juanqui made their first contribution in https://github.com/huggingface/smolagents/pull/556
* doomspork made their first contribution in https://github.com/huggingface/smolagents/pull/528
* CalOmnie made their first contribution in https://github.com/huggingface/smolagents/pull/506
* zoupingshi made their first contribution in https://github.com/huggingface/smolagents/pull/557
* NeuroWhAI made their first contribution in https://github.com/huggingface/smolagents/pull/576
* jsmidt made their first contribution in https://github.com/huggingface/smolagents/pull/585
* blakkd made their first contribution in https://github.com/huggingface/smolagents/pull/609
* g-eoj made their first contribution in https://github.com/huggingface/smolagents/pull/300
* kc9zyz made their first contribution in https://github.com/huggingface/smolagents/pull/612
* jannikmaierhoefer made their first contribution in https://github.com/huggingface/smolagents/pull/601
* leeivan1007 made their first contribution in https://github.com/huggingface/smolagents/pull/632
* Bilokin made their first contribution in https://github.com/huggingface/smolagents/pull/624
* seanxuu made their first contribution in https://github.com/huggingface/smolagents/pull/630
* matfrei made their first contribution in https://github.com/huggingface/smolagents/pull/604
* nishaddeokar made their first contribution in https://github.com/huggingface/smolagents/pull/636
* crumbly-blue-cheese made their first contribution in https://github.com/huggingface/smolagents/pull/608
* Strings-RH made their first contribution in https://github.com/huggingface/smolagents/pull/644

**Full Changelog**: https://github.com/huggingface/smolagents/compare/v1.8.1...v1.9.0

Bug Fixes 🐛
* Restore missing user prompt for initial facts by NeuroWhAI in https://github.com/huggingface/smolagents/pull/576
* Bugfix: problems with the prompt refactoring of the planning step by IlyaGusev in https://github.com/huggingface/smolagents/pull/564
* Do not pass system prompt to update plan and test plan prompts by albertvillanova in https://github.com/huggingface/smolagents/pull/586

**Full Changelog**: https://github.com/huggingface/smolagents/compare/v1.8.0...v1.8.1

New features ⭐️
* We added visualization method to display the agent' structure as a tree! 🌳 by aymeric-roucher in https://github.com/huggingface/smolagents/pull/470
<img width="696" alt="image" src="https://github.com/user-attachments/assets/1e2d4011-6ea7-4ef7-9601-f934d9201788" />

* We vastly simplified managed agents in https://github.com/huggingface/smolagents/pull/484
* We've removed the ManagedAgents class: directly provide `name` and `description` attributes to your agent to make it work as a managed agent ! Check an example here.
* We released Open Deep Research in https://github.com/huggingface/smolagents/pull/317!

Fixes 🔧
* Bump dev version: v1.8.0.dev0 by albertvillanova in https://github.com/huggingface/smolagents/pull/451
* Add ToC and CLI docs by merveenoyan in https://github.com/huggingface/smolagents/pull/455
* Fix link to Helium repository in README.md by dross20 in https://github.com/huggingface/smolagents/pull/471
* Remove default max_tokens for all models by albertvillanova in https://github.com/huggingface/smolagents/pull/475
* Improve Readme: shorter intro, VLMs, MCP, etc by aymeric-roucher in https://github.com/huggingface/smolagents/pull/459
* Fix SpeechToTextTool new instance by albertvillanova in https://github.com/huggingface/smolagents/pull/478
* Allow flatten_messages_as_text to be pushed via LiteLLMModel to fix Ollama integration by sysradium in https://github.com/huggingface/smolagents/pull/406
* Fixed demo typo in README.md by hanteed in https://github.com/huggingface/smolagents/pull/481
* Added `HfApiModel` import to `web browser example` by sergiopaniego in https://github.com/huggingface/smolagents/pull/461
* Minor Fix tool push_to_hub by keetrap in https://github.com/huggingface/smolagents/pull/460
* Fix link in README.md by vanrohan in https://github.com/huggingface/smolagents/pull/496
* Fix undefined `step_number` in single_step run by taha-yassine in https://github.com/huggingface/smolagents/pull/495
* Bump litellm to 1.60.2 (fixes 34) by taha-yassine in https://github.com/huggingface/smolagents/pull/488
* Initialize step_number attribute by albertvillanova in https://github.com/huggingface/smolagents/pull/497
* Suppress terminal logging in CI tests by albertvillanova in https://github.com/huggingface/smolagents/pull/504
* Fix link in README.md by Ryanb58 in https://github.com/huggingface/smolagents/pull/492
* Test PrintContainer by albertvillanova in https://github.com/huggingface/smolagents/pull/515
* Add missing default tools to reference docs by touseefahmed96 in https://github.com/huggingface/smolagents/pull/516
* Refactor prompts by aymeric-roucher in https://github.com/huggingface/smolagents/pull/502
* Fix Typo by rehanzo in https://github.com/huggingface/smolagents/pull/529
* Test HfApiModel call with custom_role_conversions by albertvillanova in https://github.com/huggingface/smolagents/pull/517
* Set MAX_WHILE_ITERATIONS as module variable by albertvillanova in https://github.com/huggingface/smolagents/pull/520
* add self.logger = logger for e2b_executor by femto in https://github.com/huggingface/smolagents/pull/537
* Create simpler example open-deep-research by aymeric-roucher in https://github.com/huggingface/smolagents/pull/534
* Support disabling logging to terminal by albertvillanova in https://github.com/huggingface/smolagents/pull/512
* Fix installation with data files by albertvillanova in https://github.com/huggingface/smolagents/pull/536
* Pin openinference-instrumentation-smolagents >= 0.1.4 by albertvillanova in https://github.com/huggingface/smolagents/pull/535
* Delete prompts_path argument and use prompt_templates by albertvillanova in https://github.com/huggingface/smolagents/pull/541
* Fix deprecation warning from importlib.resources.read_text by albertvillanova in https://github.com/huggingface/smolagents/pull/543
* Delete non-exisiting accelerate extra by albertvillanova in https://github.com/huggingface/smolagents/pull/539
* Fix some doc examples by aymeric-roucher in https://github.com/huggingface/smolagents/pull/542
* Test E2B Executor by albertvillanova in https://github.com/huggingface/smolagents/pull/540

New Contributors
* dross20 made their first contribution in https://github.com/huggingface/smolagents/pull/471
* sysradium made their first contribution in https://github.com/huggingface/smolagents/pull/406
* hanteed made their first contribution in https://github.com/huggingface/smolagents/pull/481
* vanrohan made their first contribution in https://github.com/huggingface/smolagents/pull/496
* taha-yassine made their first contribution in https://github.com/huggingface/smolagents/pull/495
* Ryanb58 made their first contribution in https://github.com/huggingface/smolagents/pull/492
* rehanzo made their first contribution in https://github.com/huggingface/smolagents/pull/529
* femto made their first contribution in https://github.com/huggingface/smolagents/pull/537

**Full Changelog**: https://github.com/huggingface/smolagents/compare/v1.7.0...v1.8.0

Main changes

Added commands to directly run agents from CLI: `smolagent` and `webagent` ✨
* Make web browser agent example a CLI script by merveenoyan in https://github.com/huggingface/smolagents/pull/416
* Add CLI for smolagents by aymeric-roucher in https://github.com/huggingface/smolagents/pull/431
- Now you can run `smolagent "Your task!"` from CLI to directly call a smolagent. Try it! `webagent "Find me a cheap train from Paris to Torino before Thursday"` or `smolagent "Who's the current director of La French Tech?"`

Gave a `memory` to agents! 🧠
* Untangling Logging by clefourrier in https://github.com/huggingface/smolagents/pull/316
* Test memory by albertvillanova in https://github.com/huggingface/smolagents/pull/428
- This added a specific `memory` attribute to the agent!
- We used this change to introduce nice functions like an `agent.replay()` function that replays the last run (based on the memories stored, so no further LLM calls)

Other big improvements 💪
* Improve code execution logs in case of error by showing print outputs by aymeric-roucher in https://github.com/huggingface/smolagents/pull/446
- This makes sure that code execution outputs are stored to memory even when an error was raised later on. It should slightly improve the performance of `CodeAgents`

* Update benchmark with Hub datasets by albertvillanova in https://github.com/huggingface/smolagents/pull/412
- This adds storing of benchmarking outputs directly to the Hub. Moving forward, we'll make benchmarking even easier!

Fixes and small improvements
* Bump dev version: v1.7.0.dev0 by albertvillanova in https://github.com/huggingface/smolagents/pull/390
* Fix return type of generator function in `Agent._run()` by abidlabs in https://github.com/huggingface/smolagents/pull/409
* Update minimum Gradio version by abidlabs in https://github.com/huggingface/smolagents/pull/408
* Support third-party Inference providers in `HfApiModel` by julien-c in https://github.com/huggingface/smolagents/pull/422
* Minor fix for agent_from_any_llm.py example by RolandJAAI in https://github.com/huggingface/smolagents/pull/423
* Fix `vlm_web_browser.py` example by abidlabs in https://github.com/huggingface/smolagents/pull/410
* Fix regressions, refactor logging and improve replay function by aymeric-roucher in https://github.com/huggingface/smolagents/pull/419
* Fix installation instruction for GradioUI in error message by jank in https://github.com/huggingface/smolagents/pull/418
* Fix import from deleted logger module by albertvillanova in https://github.com/huggingface/smolagents/pull/433
* Add web search tool and make prompt positional arg by aymeric-roucher in https://github.com/huggingface/smolagents/pull/435
* Remove explicit model arg in HfApiModel - which wouldn't run without Pro by sanjeed5 in https://github.com/huggingface/smolagents/pull/373
* Fix MultiStepAgent.planning_step message content by albertvillanova in https://github.com/huggingface/smolagents/pull/437
* Fix and test MemoryStep by albertvillanova in https://github.com/huggingface/smolagents/pull/432
* Fix get safe module by antoinejeannot in https://github.com/huggingface/smolagents/pull/405
* Remove duplicate final_memory_step creation by albertvillanova in https://github.com/huggingface/smolagents/pull/444
* Remove unused ChatMessageToolCall raw argument by albertvillanova in https://github.com/huggingface/smolagents/pull/445
* Fix TransformersModel docstring by August-murr in https://github.com/huggingface/smolagents/pull/447
* Test get_clean_message_list by albertvillanova in https://github.com/huggingface/smolagents/pull/448
* Add web browser example to doc by aymeric-roucher in https://github.com/huggingface/smolagents/pull/439
* Fix minor issue in e2b by keetrap in https://github.com/huggingface/smolagents/pull/436

New Contributors
* abidlabs made their first contribution in https://github.com/huggingface/smolagents/pull/409
* julien-c made their first contribution in https://github.com/huggingface/smolagents/pull/422
* August-murr made their first contribution in https://github.com/huggingface/smolagents/pull/447

**Full Changelog**: https://github.com/huggingface/smolagents/compare/v1.6.0...v1.7.0

What's Changed
* Bump version to 1.6.0.dev by albertvillanova in https://github.com/huggingface/smolagents/pull/348
* Use transformers as optional dependency by albertvillanova in https://github.com/huggingface/smolagents/pull/360
* Add pip install datasets to RAG example by sanjeed5 in https://github.com/huggingface/smolagents/pull/371
* Update issue templates by aymeric-roucher in https://github.com/huggingface/smolagents/pull/377
* TransformersModel auto-detects VLMs by aymeric-roucher in https://github.com/huggingface/smolagents/pull/378
* Separate tree for Model docs is added by touseefahmed96 in https://github.com/huggingface/smolagents/pull/382
* add kwargs to gradio launch by tocab in https://github.com/huggingface/smolagents/pull/367
* Minor Fix in the example docs by touseefahmed96 in https://github.com/huggingface/smolagents/pull/383
* Fix Extra planning by bvantuan in https://github.com/huggingface/smolagents/pull/362
* Gradio chatbot: step duration, number, token count, support nested thoughts by yvrjsharma in https://github.com/huggingface/smolagents/pull/384
- Gradio Chatbot looks much nicer than before! See below:
<img width="1240" alt="image" src="https://github.com/user-attachments/assets/261088ba-e07a-4293-ac50-188dd5eabe74" />

* Add Chinese translations for text-to-sql example by FanwangM in https://github.com/huggingface/smolagents/pull/366
* Add Chinese translations for RAG by FanwangM in https://github.com/huggingface/smolagents/pull/363
* `Qwen-2VL` -> `Qwen2-VL` model name typo fixed by sergiopaniego in https://github.com/huggingface/smolagents/pull/349
* chore: Fix Typo by Calling is_torch_available() in AgentAudio Class by hironow in https://github.com/huggingface/smolagents/pull/379
* Additional parameters for openai client by touseefahmed96 in https://github.com/huggingface/smolagents/pull/385
* DuckDuckGoSearchTool: add ddgs_kwargs parameter to constructor by onukura in https://github.com/huggingface/smolagents/pull/372
* Fix final_answer issue in e2b_executor by keetrap in https://github.com/huggingface/smolagents/pull/319
* Docs: Text to sql example - minor naming / dedupe by GrahamTheCoder in https://github.com/huggingface/smolagents/pull/376
* Test import without extras by albertvillanova in https://github.com/huggingface/smolagents/pull/370
* Add tool saving test by aymeric-roucher in https://github.com/huggingface/smolagents/pull/389
* Fix blocking of os in authorized imports by aymeric-roucher in https://github.com/huggingface/smolagents/pull/386
* Add test for DDGS Tool kwargs by aymeric-roucher in https://github.com/huggingface/smolagents/pull/387

New Contributors
* tocab made their first contribution in https://github.com/huggingface/smolagents/pull/367
* bvantuan made their first contribution in https://github.com/huggingface/smolagents/pull/362
* sergiopaniego made their first contribution in https://github.com/huggingface/smolagents/pull/349
* hironow made their first contribution in https://github.com/huggingface/smolagents/pull/379
* onukura made their first contribution in https://github.com/huggingface/smolagents/pull/372
* GrahamTheCoder made their first contribution in https://github.com/huggingface/smolagents/pull/376

**Full Changelog**: https://github.com/huggingface/smolagents/compare/v1.5.1...v1.6.0

Bug Fixes 🐛
* Use transformers as optional dependency by albertvillanova in https://github.com/huggingface/smolagents/pull/360

**Full Changelog**: https://github.com/huggingface/smolagents/compare/v1.5.0...v1.5.1