mateo-berri ec59078ad9 fix: apply configured cache_control_injection_points beside client cache_control marks ... Configured injection points were dropped whenever the request already carried a client-set cache_control anywhere, so an operator's rolling tail checkpoint silently never landed once a caller marked its own system prompt. Only the automatic defaults stand down now. Configured points skip a target the client already marked and stay under the provider's 4-block cap, counting the client's marks on messages, system, tools and the root cache_control first. The chat path carries the tool count as a stamp on the points because the prompt-management hook never receives tools. Fixes #40675		2026-09-19 04:17:38 -07:00
..
a2a_protocol	fix(a2a): narrow discovery status codes through a structural protocol	2026-09-17 17:17:21 -07:00
anthropic_interface	route stuff through dispatch no direct main	2026-09-17 11:06:46 -07:00
assistants
batch_completion
batches	Merge pull request #41138 from BerriAI/litellm_bedrock_files_s3_endpoint_url	2026-09-18 15:04:01 -07:00
caching	refactor(proxy): trim the invalidation docstrings and inject the page read failure	2026-09-16 16:41:13 -07:00
chat_completions	route stuff through dispatch no direct main	2026-09-17 11:06:46 -07:00
completion_extras	style(responses_bridge): apply ruff format	2026-09-16 23:52:53 +00:00
compression	merge: main into litellm_headroom_protect_cached_prefix	2026-09-15 04:12:28 +00:00
containers
endpoints/speech/speech_to_completion_bridge
evals
experimental_mcp_client	fix(mcp): reject missing upstream authentication credentials	2026-09-15 18:06:00 -07:00
files	feat(vertex_ai): stream GCS batch output files from /v1/files/{id}/content	2026-09-16 23:03:22 +00:00
fine_tuning
google_genai
images	feat(azure_ai): support FLUX.2 flex images	2026-09-15 12:25:19 -05:00
integrations	fix: apply configured cache_control_injection_points beside client cache_control marks	2026-09-19 04:17:38 -07:00
interactions	refactor(interactions): remove expired use_legacy_interactions_schema shim	2026-09-17 20:14:07 +00:00
litellm_core_utils	Merge pull request #41685 from BerriAI/litellm_prompt_injection_llm_api_check_dispatch	2026-09-18 23:53:14 -07:00
llms	Merge pull request #41938 from BerriAI/litellm_gemini_cache_control_messages	2026-09-19 01:20:48 -07:00
messages	route stuff through dispatch no direct main	2026-09-17 11:06:46 -07:00
models	fix(proxy): resolve temporary budget grants against the live team default instead of a snapshot	2026-09-18 02:09:09 +00:00
ocr	revert(ocr): stop forwarding client= on the Python path	2026-09-18 19:39:07 -07:00
passthrough	Merge pull request #41557 from BerriAI/litellm_azure_speech_passthrough	2026-09-18 14:05:55 -07:00
proxy	fix(guardrails): treat the stored Javelin api_version default as unset for Azure Content Safety	2026-09-19 02:29:43 -07:00
proxy_auth
rag	Merge remote-tracking branch 'origin/main' into litellm_bedrock_rag_retrieval_filter	2026-09-15 15:21:57 -07:00
realtime_api	fix(vertex_ai): apply finals before interims and refresh the token per stream	2026-09-18 16:53:06 -07:00
repositories	Merge remote-tracking branch 'origin/main' into litellm_lit_3269_project_spend_tracking	2026-09-18 14:22:07 -07:00
rerank_api
responses	Merge pull request #41564 from BerriAI/litellm_responses_bridge_message_item_lit4622	2026-09-18 22:36:28 -07:00
router_strategy	fix(router): reject a blank Jev api_key so it cannot pair with a caller-chosen api_base	2026-09-17 16:38:54 -07:00
router_utils	Merge pull request #41062 from BerriAI/litellm_mistral_codex_reasoning_effort_client_metadata	2026-09-18 14:43:58 -07:00
rust_bridge	feat(rust): serve every gateway HTTP setting natively instead of declining to Python	2026-09-18 19:39:07 -07:00
sandbox
search
secret_managers	refactor(vault): type the KV read body walk as Mapping[str, object]	2026-09-18 09:28:20 +00:00
skills	feat(skills): semantic search over the LiteLLM-hosted skill registry (#39401)	2026-09-07 12:28:38 -07:00
types	fix: apply configured cache_control_injection_points beside client cache_control marks	2026-09-19 04:17:38 -07:00
vector_store_files
vector_stores
videos
__init__.py	Merge pull request #41062 from BerriAI/litellm_mistral_codex_reasoning_effort_client_metadata	2026-09-18 14:43:58 -07:00
_internal_context.py	fix(proxy): price one cost estimate at one moment	2026-09-07 18:38:12 -07:00
_lazy_imports.py
_lazy_imports_registry.py	fix(vertex_ai): keep reasoning_effort unsupported on Vertex AI Mistral partner models	2026-09-18 13:16:56 -07:00
_logging.py	Merge pull request #40934 from BerriAI/litellm_fix_ocr_native_multipage_pdf	2026-09-16 18:06:11 -07:00
_redis.py	fix(redis): accept every truthy flag and sign serverless ElastiCache caches	2026-09-10 10:13:03 -04:00
_redis_credential_provider.py	fix(redis): accept every truthy flag and sign serverless ElastiCache caches	2026-09-10 10:13:03 -04:00
_service_logger.py
_uuid.py
_version.py
anthropic_beta_headers_config.json	Merge pull request #41203 from clonylu/fix/anthropic-thinking-binding-beta-header	2026-09-18 12:50:55 -07:00
anthropic_beta_headers_manager.py
blog_posts.json
budget_manager.py
constants.py	Merge pull request #41914 from BerriAI/litellm_xai_audio_transcription	2026-09-18 20:03:00 -07:00
cost.json
cost_calculator.py	Merge pull request #41318 from BerriAI/litellm_ws_responses_service_tier_pricing	2026-09-15 17:23:35 -07:00
exceptions.py	fix(exceptions): keep internal_server_error as the public type of an upstream 500	2026-09-18 22:28:58 -07:00
main.py	refactor(xai): move native stt routing opt-out behind the provider config	2026-09-19 01:40:00 +00:00
model_prices_and_context_window_backup.json	fix(gemini): keep the 2048 cache minimum on Gemini 2.5 Pro only, per Google's live cachedContents API	2026-09-19 00:07:22 -07:00
policy_templates_backup.json
provider_endpoints_support_backup.json
py.typed
router.py	Merge pull request #40878 from BerriAI/litellm_null_cost_unpriced_deployments	2026-09-18 14:20:52 -07:00
scheduler.py
setup_wizard.py
timeout.py
utils.py	Merge pull request #41893 from BerriAI/litellm_fix_responses_ws_encrypted_content_affinity	2026-09-18 21:09:17 -07:00