mateo-berri bda42a2bda feat(interactions): durable cross-pod settlement for background interaction billing ... Background interaction billing lived only in the creating replica's memory, so a DELETE routed to another replica, or a restart of the creating one, never billed the completed provider work and the budget reservation was refunded at the poll timeout. The create now registers the billing context in a settlement store before returning, the proxy installs a Prisma-backed store at boot (LiteLLM_BackgroundInteractionSettlement, schema-only migration), any replica claims the row once through a conditional update before billing or releasing, startup resumes every unclaimed row with its remaining timeout, and a give-up records an unsettled outcome instead of silently reconciling to zero. The SDK keeps an in-memory store and behaves as before.		2026-09-19 03:50:25 -07:00
..
a2a_protocol	fix(bedrock): sign on a dedicated executor instead of the shared default one	2026-09-09 18:52:00 -07:00
anthropic_interface
assistants	refactor(typing): replace Any with proven types in 89 more backend files	2026-09-02 23:08:42 +00:00
batch_completion
batches	refactor(vertex): move batch usage modality parsing under llms	2026-09-15 02:03:32 +00:00
caching	fix(caching): keep generic add_cache failures at ERROR unless the backend is Redis	2026-09-14 19:59:10 +00:00
completion_extras	fix(router): classify encrypted delegated tasks with native Responses	2026-09-10 12:32:09 -07:00
compression	fix(compression): protect part-level cache_control rows in compress() too	2026-09-14 18:19:51 -07:00
containers	Merge remote-tracking branch 'origin/litellm_internal_staging' into litellm_decrease_anys_opus5_r4	2026-09-02 23:32:10 +00:00
endpoints/speech/speech_to_completion_bridge
evals
experimental_mcp_client	fix(mcp): bind discovery caching to credentials and active callers	2026-09-11 14:49:00 -07:00
files	merge: bring litellm_internal_staging into the Bedrock files delete and list fix	2026-09-09 19:27:40 -07:00
fine_tuning	refactor(typing): replace Any with proven types in 89 more backend files	2026-09-02 23:08:42 +00:00
google_genai
images	refactor(typing): replace Any with proven types in 89 more backend files	2026-09-02 23:08:42 +00:00
integrations	Merge pull request #40702 from BerriAI/litellm_model_armor_logging_only_streaming	2026-09-14 17:23:32 -07:00
interactions	feat(interactions): durable cross-pod settlement for background interaction billing	2026-09-19 03:50:25 -07:00
litellm_core_utils	Merge pull request #41191 from BerriAI/litellm_router_test_cap_resets_per_fallback_hop	2026-09-15 01:13:41 -07:00
llms	Merge pull request #40915 from BerriAI/litellm_internal_copy_37075	2026-09-15 02:06:49 -07:00
models	feat(auto-router): show routed model and savings in Claude Code and Codex (#40330)	2026-09-11 12:52:42 -07:00
ocr	Merge remote-tracking branch 'origin/litellm_internal_staging' into litellm_ocr_custom_pricing	2026-09-12 15:42:59 -07:00
passthrough	fix(passthrough): parse Bedrock stream spend incrementally instead of buffering the whole response (#40724)	2026-09-11 09:53:37 -07:00
proxy	feat(interactions): durable cross-pod settlement for background interaction billing	2026-09-19 03:50:25 -07:00
proxy_auth
rag	chore: merge origin/litellm_internal_staging into litellm_decrease_anys_opus5_r4	2026-09-04 18:59:35 -07:00
realtime_api	refactor(realtime): move Meta Muse Voice onto BaseRealtimeConfig	2026-09-11 20:12:15 -07:00
repositories	feat(interactions): durable cross-pod settlement for background interaction billing	2026-09-19 03:50:25 -07:00
rerank_api
responses	merge: origin/main into litellm_internal_copy_37075	2026-09-15 00:34:18 -07:00
router_strategy	fix(router): honor team and key provider weights	2026-09-14 23:31:52 -07:00
router_utils	Merge pull request #40228 from AaronHowell/litellm_fix_responses_credentials_affinity	2026-09-14 23:09:55 -07:00
rust_bridge	fix(router): record flat retry attempts and cap retries from attempted_retries	2026-09-13 01:05:51 +00:00
sandbox
search	fix(search): forward search-tool params through the router, complete Parallel AI v1 param mapping (#37883)	2026-09-01 21:46:46 -07:00
secret_managers	feat(secret_managers): support customer-managed KMS key for virtual keys stored in AWS Secrets Manager (#40475)	2026-09-11 09:54:08 -07:00
skills	feat(skills): semantic search over the LiteLLM-hosted skill registry (#39401)	2026-09-07 12:28:38 -07:00
types	fix(router): honor team and key provider weights	2026-09-14 23:31:52 -07:00
vector_store_files	refactor(typing): replace Any with proven types in 42 more backend files	2026-09-02 15:35:01 +00:00
vector_stores	Merge remote-tracking branch 'origin/litellm_internal_staging' into litellm_python_version_ci	2026-09-03 00:16:19 -07:00
videos
__init__.py	fix(router): count num_retries_per_request across fallback hops	2026-09-14 23:13:50 -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	fix(lazy_imports): type import_map as Mapping to stay under the LIT001 budget	2026-09-05 16:12:45 -07:00
_lazy_imports_registry.py	Revert "perf: lazy-load SDK symbols so import litellm stays under 60 MB RSS (…"	2026-09-05 16:07:09 -07:00
_logging.py	fix(proxy): read LITELLM_DISABLE_ACCESS_LOG_PATHS per record and match before redaction	2026-09-14 17:27:43 +00:00
_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	chore: merge origin/litellm_internal_staging into litellm_decrease_anys_opus5_r4	2026-09-04 18:59:35 -07:00
_uuid.py
_version.py
anthropic_beta_headers_config.json
anthropic_beta_headers_manager.py
blog_posts.json
budget_manager.py
constants.py	fix(sdk): carry a litellm_proxy error's headers on e.response, not e.headers	2026-09-14 22:22:26 -07:00
cost.json
cost_calculator.py	fix(cost): drop remaining unnecessary cast in batch cost calculator	2026-09-15 02:26:19 +00:00
exceptions.py	fix(sdk): carry a litellm_proxy error's headers on e.response, not e.headers	2026-09-14 22:22:26 -07:00
main.py	fix(openai): keep extra_headers out of the chat request body on the httpx handler path	2026-09-14 22:27:35 +00:00
model_prices_and_context_window_backup.json	fix(cost): bill batch embeddings per modality token rate	2026-09-15 01:50:21 +00:00
policy_templates_backup.json
provider_endpoints_support_backup.json	fix(ocr): send each provider a health-check document it accepts	2026-09-04 22:52:12 -07:00
py.typed
router.py	Merge pull request #41191 from BerriAI/litellm_router_test_cap_resets_per_fallback_hop	2026-09-15 01:13:41 -07:00
scheduler.py
setup_wizard.py
timeout.py
utils.py	Merge remote-tracking branch 'origin/main' into litellm_azure_spend_log_zero_cost	2026-09-14 21:37:19 -07:00