* fix(proxy_server.py): update swagger-ui-bundle.js + bring back swagger in airgapped environments
* fix(proxy_server.py): support local swagger on custom root path
enables on prem usage of litellm
* feat: Add Pillar Security guardrail integration
Implements comprehensive LLM security guardrails using Pillar Security API with support for prompt injection detection, PII/secret detection, content moderation, and multi-mode execution (pre_call, during_call, post_call). Includes complete documentation, testing, and configurable actions on flagged content.
* fix: Resolve MyPy type error in Pillar guardrail config
Restructure PillarGuardrailConfigModel to properly inherit from GuardrailConfigModel[T]
and resolve return type compatibility issue in get_config_model method.
* fix: Resolve MyPy type error in Pillar guardrail config
Restructure PillarGuardrailConfigModel to properly inherit from GuardrailConfigModel[T]
and resolve return type compatibility issue in get_config_model method.
* fix docs
* fix docs
* improved docs
* fix examples, READY
* feat(litellm_pre_call_utils.py): add num_retries to litellm data for backend call
allow user to pass in num retries via request headers
* test(test_litellm_pre_call_utils.py): add unit test
* docs(request_headers.md): document new request header
* fix(common_daily_activity.py): show spend breakdown by model group
Partial fix for https://github.com/BerriAI/litellm/issues/12887
* feat(new_usage.tsx): new tab switcher for viewing usage by model group vs. received model
Closes https://github.com/BerriAI/litellm/issues/12887
* fix(main.py): fix async retryer
Fixes https://github.com/BerriAI/litellm/issues/12830
* fix(forward_clientside_headers_by_model_group.py): filter out 'content-type' from forwardable headers
clientside content-type != proxy content type, can cause requests to hang
* add gemini 2.0 live to model context and priceS
* added files to dump
* Update litellm/model_prices_and_context_window_backup.json
Co-authored-by: Copilot <175728472+Copilot@users.noreply.github.com>
* Update model_prices_and_context_window.json
Co-authored-by: Copilot <175728472+Copilot@users.noreply.github.com>
* added vertex ai live preview
* added vertex ai change
* add input video and image cosT
* add input video and image cosT
---------
Co-authored-by: Ishaan Jaff <ishaanjaffer0324@gmail.com>
Co-authored-by: Copilot <175728472+Copilot@users.noreply.github.com>
* Change Dockerfile.noon_root with alpine base image
* Improve non_root docker image
* Re add the build_admin_ui.sh script step
* Re add the build_admin_ui.sh script step
* Remove unnecessary workdir set
* Remove unnecessary workdir set
* Configure chainguard image
* A bit of optimization and improve comments
* delete extra build_ui script run
* Optimizie Dockerfile copy statements
This aligns the proxy experience with other models that think
automatically (e.g. Deepseek R1 and grok3). It does so by setting
the necessary request input to return thinking, but not specifying
a budget or effort (thus defaulting to the internal automatic level).
* fix(gpt_transformation.py): remove 'cache_control' flag for openai/openai-compatible calls
Fixes https://github.com/BerriAI/litellm/issues/12787
* fix(openrouter/chat/transformation.py): allow passing openrouter cache control flag for claude models
* fix(gpt_transformation.py): fix import
* fix: fix adding tools
